diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-checkpoint.pt b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc4d96d39e6221c31748a1f4f8ae642427c11b96 --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92cd948b279a905508cb483313e8b868afea238da49812dafc3094bf34283d59 +size 15336322587 diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-optimizer.pt b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..025025f1307944c94b689993451ec6a25867236b --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324015c252de171b474d90a0b3892c50e9c90b49315a81b59018a647c292877c +size 30672706842 diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-scheduler.pt b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4f09f488c3f319b68cc9fde89e14a033705ac40 --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/checkpoints/latest-scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba4d4ded2fe863df5701c02896d2a60bb9e25903168be9a20a3a5a9fe9e6ba5 +size 1192 diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/config.json b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/config.json new file mode 100644 index 0000000000000000000000000000000000000000..635cfb1d27866ff60942f524a2043153cc782510 --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/config.json @@ -0,0 +1,74 @@ +{ + "dataset": { + "align_stage_components": [ + "download/llava-laion-cc-sbu-558k/chat.json", + "download/llava-laion-cc-sbu-558k" + ], + "dataset_id": "obelics", + "dataset_resampled": true, + "dataset_root_dir": "/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/datacomp/datacomp_hq_single_pkl_pil:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/OBELICS/obelics_hq_35_single_pkl_pil:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/synthdog-en/synthdog_single_pkl_pil/", + "finetune_stage_components": [ + "/fsx-training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/llava/llava_v1_5_mix665k.json", + "/fsx-training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/llava/data" + ], + "max_num_images": 6, + "min_num_images": 1, + "train_num_samples": 2441408, + "type": "obelics", + "workers": 4 + }, + "model": { + "align_epochs": 1, + "align_global_batch_size": 256, + "align_learning_rate": 0.001, + "align_lr_scheduler_type": "linear-warmup+cosine-decay", + "align_max_grad_norm": 1.0, + "align_max_steps": null, + "align_per_device_batch_size": 16, + "align_train_strategy": "fsdp-shard-grad-op", + "align_warmup_ratio": 0.03, + "align_weight_decay": 0.0, + "arch_specifier": "no-align+avgpool", + "enable_gradient_checkpointing": true, + "enable_mixed_precision_training": true, + "finetune_epochs": 1, + "finetune_global_batch_size": 128, + "finetune_learning_rate": 2e-05, + "finetune_lr_scheduler_type": "linear-warmup+cosine-decay", + "finetune_max_grad_norm": 1.0, + "finetune_max_steps": null, + "finetune_per_device_batch_size": 16, + "finetune_train_strategy": "fsdp-full-shard", + "finetune_warmup_ratio": 0.03, + "finetune_weight_decay": 0.1, + "image_resize_strategy": "resize-naive", + "llm_backbone_id": "phi3-3b", + "llm_max_length": 4096, + "model_id": "phi3-3b-continue-training-hq_35", + "pretrain_epochs": 1, + "pretrain_global_batch_size": 256, + "pretrain_learning_rate": 5e-05, + "pretrain_lr_scheduler_type": "linear-warmup+cosine-decay", + "pretrain_max_grad_norm": 1.0, + "pretrain_max_steps": 9536, + "pretrain_per_device_batch_size": 8, + "pretrain_train_strategy": "fsdp-full-shard", + "pretrain_warmup_ratio": 0.03, + "pretrain_weight_decay": 0.01, + "reduce_in_full_precision": false, + "type": "one-stage+7b", + "vision_backbone_id": "siglip-vit-so400m-384px" + }, + "mount_path": "/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/models", + "pretrained_checkpoint": null, + "run_id": "obelics+phi3-3b-continue-training-hq_35+stage-pretrain+x7", + "run_root_dir": "/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/checkpoints/mllm_pretrain_checkpoints", + "seed": 7, + "stage": "pretrain", + "trackers": [ + "jsonl", + "wandb" + ], + "wandb_entity": null, + "wandb_project": "mmpretrain" +} \ No newline at end of file diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/config.yaml b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1071de9baebed6c2364ff96cc0ede2b744b3d534 --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/config.yaml @@ -0,0 +1,67 @@ +dataset: + align_stage_components: + - download/llava-laion-cc-sbu-558k/chat.json + - download/llava-laion-cc-sbu-558k + dataset_id: obelics + dataset_resampled: true + dataset_root_dir: /fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/datacomp/datacomp_hq_single_pkl_pil:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/OBELICS/obelics_hq_35_single_pkl_pil:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/synthdog-en/synthdog_single_pkl_pil/ + finetune_stage_components: + - /fsx-training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/llava/llava_v1_5_mix665k.json + - /fsx-training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/llava/data + max_num_images: 6 + min_num_images: 1 + train_num_samples: 2441408 + type: obelics + workers: 4 +model: + align_epochs: 1 + align_global_batch_size: 256 + align_learning_rate: 0.001 + align_lr_scheduler_type: linear-warmup+cosine-decay + align_max_grad_norm: 1.0 + align_max_steps: null + align_per_device_batch_size: 16 + align_train_strategy: fsdp-shard-grad-op + align_warmup_ratio: 0.03 + align_weight_decay: 0.0 + arch_specifier: no-align+avgpool + enable_gradient_checkpointing: true + enable_mixed_precision_training: true + finetune_epochs: 1 + finetune_global_batch_size: 128 + finetune_learning_rate: 2.0e-05 + finetune_lr_scheduler_type: linear-warmup+cosine-decay + finetune_max_grad_norm: 1.0 + finetune_max_steps: null + finetune_per_device_batch_size: 16 + finetune_train_strategy: fsdp-full-shard + finetune_warmup_ratio: 0.03 + finetune_weight_decay: 0.1 + image_resize_strategy: resize-naive + llm_backbone_id: phi3-3b + llm_max_length: 4096 + model_id: phi3-3b-continue-training-hq_35 + pretrain_epochs: 1 + pretrain_global_batch_size: 256 + pretrain_learning_rate: 5.0e-05 + pretrain_lr_scheduler_type: linear-warmup+cosine-decay + pretrain_max_grad_norm: 1.0 + pretrain_max_steps: 9536 + pretrain_per_device_batch_size: 8 + pretrain_train_strategy: fsdp-full-shard + pretrain_warmup_ratio: 0.03 + pretrain_weight_decay: 0.01 + reduce_in_full_precision: false + type: one-stage+7b + vision_backbone_id: siglip-vit-so400m-384px +mount_path: /fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/models +pretrained_checkpoint: null +run_id: obelics+phi3-3b-continue-training-hq_35+stage-pretrain+x7 +run_root_dir: /fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/checkpoints/mllm_pretrain_checkpoints +seed: 7 +stage: pretrain +trackers: +- jsonl +- wandb +wandb_entity: null +wandb_project: mmpretrain diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/notes.txt b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/notes.txt new file mode 100644 index 0000000000000000000000000000000000000000..5c3ebd4e33b9dce2209924f336769c570452b4bb --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/notes.txt @@ -0,0 +1,3 @@ +we use the joint 280k caption and interleaved data of Claude-3.5 generation to train this classifier +then we select top30% +the endofchunk token is addded to the corpus \ No newline at end of file diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/obelics+phi3-3b-continue-training-hq_35+stage-pretrain+x7.jsonl b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/obelics+phi3-3b-continue-training-hq_35+stage-pretrain+x7.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..78ef81f1a43194c0d7f46cbd5e6a5c06bfdfd3ac --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/obelics+phi3-3b-continue-training-hq_35+stage-pretrain+x7.jsonl @@ -0,0 +1,9536 @@ +{"Pretrain/Learning Rate": 1.7482517482517484e-07, "Pretrain/Loss": 3.109079360961914, "Pretrain/Loss (Raw)": 3.109079360961914, "Pretrain/Step": 1, "Pretrain/Step Time": 12.685293912887573} +{"Pretrain/Learning Rate": 3.496503496503497e-07, "Pretrain/Loss": 3.144956588745117, "Pretrain/Loss (Raw)": 3.1808338165283203, "Pretrain/Step": 2, "Pretrain/Step Time": 10.49549400806427} +{"Pretrain/Learning Rate": 5.244755244755246e-07, "Pretrain/Loss": 3.6842379570007324, "Pretrain/Loss (Raw)": 4.762800216674805, "Pretrain/Step": 3, "Pretrain/Step Time": 9.730501810709635} +{"Pretrain/Learning Rate": 6.993006993006994e-07, "Pretrain/Loss": 3.6643316745758057, "Pretrain/Loss (Raw)": 3.6046135425567627, "Pretrain/Step": 4, "Pretrain/Step Time": 9.453338623046875} +{"Pretrain/Learning Rate": 8.741258741258743e-07, "Pretrain/Loss": 3.599637985229492, "Pretrain/Loss (Raw)": 3.340862989425659, "Pretrain/Step": 5, "Pretrain/Step Time": 9.169699811935425} +{"Pretrain/Learning Rate": 1.0489510489510491e-06, "Pretrain/Loss": 3.510218381881714, "Pretrain/Loss (Raw)": 3.063120126724243, "Pretrain/Step": 6, "Pretrain/Step Time": 9.041971643765768} +{"Pretrain/Learning Rate": 1.2237762237762238e-06, "Pretrain/Loss": 3.5415797233581543, "Pretrain/Loss (Raw)": 3.7297465801239014, "Pretrain/Step": 7, "Pretrain/Step Time": 8.925822598593575} +{"Pretrain/Learning Rate": 1.3986013986013987e-06, "Pretrain/Loss": 3.617053508758545, "Pretrain/Loss (Raw)": 4.14537239074707, "Pretrain/Step": 8, "Pretrain/Step Time": 8.839798390865326} +{"Pretrain/Learning Rate": 1.5734265734265736e-06, "Pretrain/Loss": 3.5393011569976807, "Pretrain/Loss (Raw)": 2.9172801971435547, "Pretrain/Step": 9, "Pretrain/Step Time": 8.747192515267265} +{"Pretrain/Learning Rate": 1.7482517482517485e-06, "Pretrain/Loss": 3.593153715133667, "Pretrain/Loss (Raw)": 4.077829360961914, "Pretrain/Step": 10, "Pretrain/Step Time": 8.697983813285827} +{"Pretrain/Learning Rate": 1.9230769230769234e-06, "Pretrain/Loss": 3.5813026428222656, "Pretrain/Loss (Raw)": 3.462789297103882, "Pretrain/Step": 11, "Pretrain/Step Time": 8.66211427341808} +{"Pretrain/Learning Rate": 2.0979020979020983e-06, "Pretrain/Loss": 3.5084309577941895, "Pretrain/Loss (Raw)": 2.7068419456481934, "Pretrain/Step": 12, "Pretrain/Step Time": 8.629947980244955} +{"Pretrain/Learning Rate": 2.2727272727272728e-06, "Pretrain/Loss": 3.462176561355591, "Pretrain/Loss (Raw)": 2.9071223735809326, "Pretrain/Step": 13, "Pretrain/Step Time": 8.620788941016563} +{"Pretrain/Learning Rate": 2.4475524475524477e-06, "Pretrain/Loss": 3.4036030769348145, "Pretrain/Loss (Raw)": 2.6421492099761963, "Pretrain/Step": 14, "Pretrain/Step Time": 8.604569911956787} +{"Pretrain/Learning Rate": 2.6223776223776225e-06, "Pretrain/Loss": 3.3485207557678223, "Pretrain/Loss (Raw)": 2.5773696899414062, "Pretrain/Step": 15, "Pretrain/Step Time": 8.673123820622761} +{"Pretrain/Learning Rate": 2.7972027972027974e-06, "Pretrain/Loss": 3.3221993446350098, "Pretrain/Loss (Raw)": 2.9273810386657715, "Pretrain/Step": 16, "Pretrain/Step Time": 8.669459775090218} +{"Pretrain/Learning Rate": 2.9720279720279723e-06, "Pretrain/Loss": 3.281111240386963, "Pretrain/Loss (Raw)": 2.623703718185425, "Pretrain/Step": 17, "Pretrain/Step Time": 8.642429001191083} +{"Pretrain/Learning Rate": 3.1468531468531472e-06, "Pretrain/Loss": 3.231696367263794, "Pretrain/Loss (Raw)": 2.391637086868286, "Pretrain/Step": 18, "Pretrain/Step Time": 8.627926614549425} +{"Pretrain/Learning Rate": 3.3216783216783217e-06, "Pretrain/Loss": 3.205287456512451, "Pretrain/Loss (Raw)": 2.7299323081970215, "Pretrain/Step": 19, "Pretrain/Step Time": 8.594543507224635} +{"Pretrain/Learning Rate": 3.496503496503497e-06, "Pretrain/Loss": 3.2055184841156006, "Pretrain/Loss (Raw)": 3.2098968029022217, "Pretrain/Step": 20, "Pretrain/Step Time": 8.58257042169571} +{"Pretrain/Learning Rate": 3.6713286713286715e-06, "Pretrain/Loss": 3.188166379928589, "Pretrain/Loss (Raw)": 2.841137409210205, "Pretrain/Step": 21, "Pretrain/Step Time": 8.567618142990838} +{"Pretrain/Learning Rate": 3.846153846153847e-06, "Pretrain/Loss": 3.163358688354492, "Pretrain/Loss (Raw)": 2.6423847675323486, "Pretrain/Step": 22, "Pretrain/Step Time": 8.548497904430736} +{"Pretrain/Learning Rate": 4.020979020979021e-06, "Pretrain/Loss": 3.131335735321045, "Pretrain/Loss (Raw)": 2.426841974258423, "Pretrain/Step": 23, "Pretrain/Step Time": 8.538830446160357} +{"Pretrain/Learning Rate": 4.195804195804197e-06, "Pretrain/Loss": 3.1209335327148438, "Pretrain/Loss (Raw)": 2.881686210632324, "Pretrain/Step": 24, "Pretrain/Step Time": 8.522080759207407} +{"Pretrain/Learning Rate": 4.370629370629371e-06, "Pretrain/Loss": 3.1060338020324707, "Pretrain/Loss (Raw)": 2.7484376430511475, "Pretrain/Step": 25, "Pretrain/Step Time": 8.503194942474366} +{"Pretrain/Learning Rate": 4.5454545454545455e-06, "Pretrain/Loss": 3.0898289680480957, "Pretrain/Loss (Raw)": 2.684701919555664, "Pretrain/Step": 26, "Pretrain/Step Time": 8.492335787186256} +{"Pretrain/Learning Rate": 4.72027972027972e-06, "Pretrain/Loss": 3.07187819480896, "Pretrain/Loss (Raw)": 2.6051626205444336, "Pretrain/Step": 27, "Pretrain/Step Time": 8.485024805422183} +{"Pretrain/Learning Rate": 4.895104895104895e-06, "Pretrain/Loss": 3.04416561126709, "Pretrain/Loss (Raw)": 2.295917272567749, "Pretrain/Step": 28, "Pretrain/Step Time": 8.469470705304827} +{"Pretrain/Learning Rate": 5.06993006993007e-06, "Pretrain/Loss": 3.0289154052734375, "Pretrain/Loss (Raw)": 2.601916790008545, "Pretrain/Step": 29, "Pretrain/Step Time": 8.477677098635969} +{"Pretrain/Learning Rate": 5.244755244755245e-06, "Pretrain/Loss": 3.008728504180908, "Pretrain/Loss (Raw)": 2.4232990741729736, "Pretrain/Step": 30, "Pretrain/Step Time": 8.481023931503296} +{"Pretrain/Learning Rate": 5.419580419580419e-06, "Pretrain/Loss": 2.9950063228607178, "Pretrain/Loss (Raw)": 2.583357095718384, "Pretrain/Step": 31, "Pretrain/Step Time": 8.477556790074994} +{"Pretrain/Learning Rate": 5.594405594405595e-06, "Pretrain/Loss": 2.9767656326293945, "Pretrain/Loss (Raw)": 2.4112942218780518, "Pretrain/Step": 32, "Pretrain/Step Time": 8.49165604263544} +{"Pretrain/Learning Rate": 5.76923076923077e-06, "Pretrain/Loss": 2.961876153945923, "Pretrain/Loss (Raw)": 2.485419273376465, "Pretrain/Step": 33, "Pretrain/Step Time": 8.496111645843044} +{"Pretrain/Learning Rate": 5.944055944055945e-06, "Pretrain/Loss": 2.943711280822754, "Pretrain/Loss (Raw)": 2.3442625999450684, "Pretrain/Step": 34, "Pretrain/Step Time": 8.48806600710925} +{"Pretrain/Learning Rate": 6.1188811188811196e-06, "Pretrain/Loss": 2.9325151443481445, "Pretrain/Loss (Raw)": 2.551851272583008, "Pretrain/Step": 35, "Pretrain/Step Time": 8.477752317701068} +{"Pretrain/Learning Rate": 6.2937062937062944e-06, "Pretrain/Loss": 2.9147939682006836, "Pretrain/Loss (Raw)": 2.2945492267608643, "Pretrain/Step": 36, "Pretrain/Step Time": 8.468176974190605} +{"Pretrain/Learning Rate": 6.468531468531469e-06, "Pretrain/Loss": 2.896500587463379, "Pretrain/Loss (Raw)": 2.237940549850464, "Pretrain/Step": 37, "Pretrain/Step Time": 8.459445663400599} +{"Pretrain/Learning Rate": 6.643356643356643e-06, "Pretrain/Loss": 2.884580612182617, "Pretrain/Loss (Raw)": 2.4435362815856934, "Pretrain/Step": 38, "Pretrain/Step Time": 8.452227316404644} +{"Pretrain/Learning Rate": 6.818181818181818e-06, "Pretrain/Loss": 2.881157875061035, "Pretrain/Loss (Raw)": 2.751096725463867, "Pretrain/Step": 39, "Pretrain/Step Time": 8.444608816733727} +{"Pretrain/Learning Rate": 6.993006993006994e-06, "Pretrain/Loss": 2.8673393726348877, "Pretrain/Loss (Raw)": 2.328420877456665, "Pretrain/Step": 40, "Pretrain/Step Time": 8.43633189201355} +{"Pretrain/Learning Rate": 7.167832167832168e-06, "Pretrain/Loss": 2.8520264625549316, "Pretrain/Loss (Raw)": 2.2395248413085938, "Pretrain/Step": 41, "Pretrain/Step Time": 8.429426704964987} +{"Pretrain/Learning Rate": 7.342657342657343e-06, "Pretrain/Loss": 2.843113660812378, "Pretrain/Loss (Raw)": 2.4776744842529297, "Pretrain/Step": 42, "Pretrain/Step Time": 8.426022251447042} +{"Pretrain/Learning Rate": 7.517482517482517e-06, "Pretrain/Loss": 2.8345563411712646, "Pretrain/Loss (Raw)": 2.475149154663086, "Pretrain/Step": 43, "Pretrain/Step Time": 8.424742016681405} +{"Pretrain/Learning Rate": 7.692307692307694e-06, "Pretrain/Loss": 2.822314500808716, "Pretrain/Loss (Raw)": 2.295921564102173, "Pretrain/Step": 44, "Pretrain/Step Time": 8.417825281620026} +{"Pretrain/Learning Rate": 7.867132867132867e-06, "Pretrain/Loss": 2.8085694313049316, "Pretrain/Loss (Raw)": 2.2037813663482666, "Pretrain/Step": 45, "Pretrain/Step Time": 8.42103090286255} +{"Pretrain/Learning Rate": 8.041958041958042e-06, "Pretrain/Loss": 2.8005685806274414, "Pretrain/Loss (Raw)": 2.4405293464660645, "Pretrain/Step": 46, "Pretrain/Step Time": 8.423721064691959} +{"Pretrain/Learning Rate": 8.216783216783217e-06, "Pretrain/Loss": 2.792611837387085, "Pretrain/Loss (Raw)": 2.426603317260742, "Pretrain/Step": 47, "Pretrain/Step Time": 8.422264753504002} +{"Pretrain/Learning Rate": 8.391608391608393e-06, "Pretrain/Loss": 2.782835006713867, "Pretrain/Loss (Raw)": 2.323319435119629, "Pretrain/Step": 48, "Pretrain/Step Time": 8.435325980186462} +{"Pretrain/Learning Rate": 8.566433566433566e-06, "Pretrain/Loss": 2.772557497024536, "Pretrain/Loss (Raw)": 2.279228925704956, "Pretrain/Step": 49, "Pretrain/Step Time": 8.437021566897023} +{"Pretrain/Learning Rate": 8.741258741258741e-06, "Pretrain/Loss": 2.767803192138672, "Pretrain/Loss (Raw)": 2.5348663330078125, "Pretrain/Step": 50, "Pretrain/Step Time": 8.435101099014283} +{"Pretrain/Learning Rate": 8.916083916083918e-06, "Pretrain/Loss": 2.7614197731018066, "Pretrain/Loss (Raw)": 2.4422264099121094, "Pretrain/Step": 51, "Pretrain/Step Time": 8.43261147480385} +{"Pretrain/Learning Rate": 9.090909090909091e-06, "Pretrain/Loss": 2.7527520656585693, "Pretrain/Loss (Raw)": 2.310699701309204, "Pretrain/Step": 52, "Pretrain/Step Time": 8.428804163749401} +{"Pretrain/Learning Rate": 9.265734265734266e-06, "Pretrain/Loss": 2.7461304664611816, "Pretrain/Loss (Raw)": 2.401808023452759, "Pretrain/Step": 53, "Pretrain/Step Time": 8.42790613984162} +{"Pretrain/Learning Rate": 9.44055944055944e-06, "Pretrain/Loss": 2.7403414249420166, "Pretrain/Loss (Raw)": 2.433533191680908, "Pretrain/Step": 54, "Pretrain/Step Time": 8.422323262249982} +{"Pretrain/Learning Rate": 9.615384615384616e-06, "Pretrain/Loss": 2.7311503887176514, "Pretrain/Loss (Raw)": 2.2348318099975586, "Pretrain/Step": 55, "Pretrain/Step Time": 8.417132043838501} +{"Pretrain/Learning Rate": 9.79020979020979e-06, "Pretrain/Loss": 2.7225375175476074, "Pretrain/Loss (Raw)": 2.2488315105438232, "Pretrain/Step": 56, "Pretrain/Step Time": 8.411685692412513} +{"Pretrain/Learning Rate": 9.965034965034966e-06, "Pretrain/Loss": 2.7117700576782227, "Pretrain/Loss (Raw)": 2.1087918281555176, "Pretrain/Step": 57, "Pretrain/Step Time": 8.413106324379903} +{"Pretrain/Learning Rate": 1.013986013986014e-05, "Pretrain/Loss": 2.706146240234375, "Pretrain/Loss (Raw)": 2.3855807781219482, "Pretrain/Step": 58, "Pretrain/Step Time": 8.411028290617056} +{"Pretrain/Learning Rate": 1.0314685314685315e-05, "Pretrain/Loss": 2.7018635272979736, "Pretrain/Loss (Raw)": 2.45345401763916, "Pretrain/Step": 59, "Pretrain/Step Time": 8.414615922055003} +{"Pretrain/Learning Rate": 1.048951048951049e-05, "Pretrain/Loss": 2.692368268966675, "Pretrain/Loss (Raw)": 2.132154703140259, "Pretrain/Step": 60, "Pretrain/Step Time": 8.41145118077596} +{"Pretrain/Learning Rate": 1.0664335664335665e-05, "Pretrain/Loss": 2.6869254112243652, "Pretrain/Loss (Raw)": 2.360388994216919, "Pretrain/Step": 61, "Pretrain/Step Time": 8.411365153359585} +{"Pretrain/Learning Rate": 1.0839160839160838e-05, "Pretrain/Loss": 2.6818325519561768, "Pretrain/Loss (Raw)": 2.371145725250244, "Pretrain/Step": 62, "Pretrain/Step Time": 8.409963653933618} +{"Pretrain/Learning Rate": 1.1013986013986015e-05, "Pretrain/Loss": 2.677574634552002, "Pretrain/Loss (Raw)": 2.413566827774048, "Pretrain/Step": 63, "Pretrain/Step Time": 8.415874659069} +{"Pretrain/Learning Rate": 1.118881118881119e-05, "Pretrain/Loss": 2.6737024784088135, "Pretrain/Loss (Raw)": 2.429771661758423, "Pretrain/Step": 64, "Pretrain/Step Time": 8.417390782386065} +{"Pretrain/Learning Rate": 1.1363636363636365e-05, "Pretrain/Loss": 2.667339563369751, "Pretrain/Loss (Raw)": 2.260117530822754, "Pretrain/Step": 65, "Pretrain/Step Time": 8.42643484702477} +{"Pretrain/Learning Rate": 1.153846153846154e-05, "Pretrain/Loss": 2.664241075515747, "Pretrain/Loss (Raw)": 2.4628233909606934, "Pretrain/Step": 66, "Pretrain/Step Time": 8.422291275226709} +{"Pretrain/Learning Rate": 1.1713286713286714e-05, "Pretrain/Loss": 2.658647060394287, "Pretrain/Loss (Raw)": 2.2894604206085205, "Pretrain/Step": 67, "Pretrain/Step Time": 8.419794096875547} +{"Pretrain/Learning Rate": 1.188811188811189e-05, "Pretrain/Loss": 2.65493106842041, "Pretrain/Loss (Raw)": 2.405940294265747, "Pretrain/Step": 68, "Pretrain/Step Time": 8.416234261849347} +{"Pretrain/Learning Rate": 1.2062937062937063e-05, "Pretrain/Loss": 2.648300886154175, "Pretrain/Loss (Raw)": 2.1974616050720215, "Pretrain/Step": 69, "Pretrain/Step Time": 8.417289588762367} +{"Pretrain/Learning Rate": 1.2237762237762239e-05, "Pretrain/Loss": 2.6428048610687256, "Pretrain/Loss (Raw)": 2.2635698318481445, "Pretrain/Step": 70, "Pretrain/Step Time": 8.41606901373182} +{"Pretrain/Learning Rate": 1.2412587412587414e-05, "Pretrain/Loss": 2.638737440109253, "Pretrain/Loss (Raw)": 2.354020833969116, "Pretrain/Step": 71, "Pretrain/Step Time": 8.414454490366117} +{"Pretrain/Learning Rate": 1.2587412587412589e-05, "Pretrain/Loss": 2.635958671569824, "Pretrain/Loss (Raw)": 2.4386563301086426, "Pretrain/Step": 72, "Pretrain/Step Time": 8.418063756492403} +{"Pretrain/Learning Rate": 1.2762237762237764e-05, "Pretrain/Loss": 2.630946397781372, "Pretrain/Loss (Raw)": 2.270055055618286, "Pretrain/Step": 73, "Pretrain/Step Time": 8.428738505872962} +{"Pretrain/Learning Rate": 1.2937062937062939e-05, "Pretrain/Loss": 2.6255993843078613, "Pretrain/Loss (Raw)": 2.2352614402770996, "Pretrain/Step": 74, "Pretrain/Step Time": 8.43373313465634} +{"Pretrain/Learning Rate": 1.3111888111888112e-05, "Pretrain/Loss": 2.6215052604675293, "Pretrain/Loss (Raw)": 2.318547010421753, "Pretrain/Step": 75, "Pretrain/Step Time": 8.433399702707927} +{"Pretrain/Learning Rate": 1.3286713286713287e-05, "Pretrain/Loss": 2.617969036102295, "Pretrain/Loss (Raw)": 2.352771043777466, "Pretrain/Step": 76, "Pretrain/Step Time": 8.430217529598035} +{"Pretrain/Learning Rate": 1.3461538461538462e-05, "Pretrain/Loss": 2.6141867637634277, "Pretrain/Loss (Raw)": 2.3267321586608887, "Pretrain/Step": 77, "Pretrain/Step Time": 8.430687343919432} +{"Pretrain/Learning Rate": 1.3636363636363637e-05, "Pretrain/Loss": 2.608693838119507, "Pretrain/Loss (Raw)": 2.1857457160949707, "Pretrain/Step": 78, "Pretrain/Step Time": 8.426862964263329} +{"Pretrain/Learning Rate": 1.381118881118881e-05, "Pretrain/Loss": 2.601241111755371, "Pretrain/Loss (Raw)": 2.0199060440063477, "Pretrain/Step": 79, "Pretrain/Step Time": 8.43278193473816} +{"Pretrain/Learning Rate": 1.3986013986013988e-05, "Pretrain/Loss": 2.597811460494995, "Pretrain/Loss (Raw)": 2.3268864154815674, "Pretrain/Step": 80, "Pretrain/Step Time": 8.439208793640137} +{"Pretrain/Learning Rate": 1.4160839160839163e-05, "Pretrain/Loss": 2.5940892696380615, "Pretrain/Loss (Raw)": 2.296302556991577, "Pretrain/Step": 81, "Pretrain/Step Time": 8.44042256143358} +{"Pretrain/Learning Rate": 1.4335664335664336e-05, "Pretrain/Loss": 2.591613292694092, "Pretrain/Loss (Raw)": 2.3910727500915527, "Pretrain/Step": 82, "Pretrain/Step Time": 8.440671906238649} +{"Pretrain/Learning Rate": 1.4510489510489511e-05, "Pretrain/Loss": 2.591926336288452, "Pretrain/Loss (Raw)": 2.6175975799560547, "Pretrain/Step": 83, "Pretrain/Step Time": 8.440902534737644} +{"Pretrain/Learning Rate": 1.4685314685314686e-05, "Pretrain/Loss": 2.588747501373291, "Pretrain/Loss (Raw)": 2.3248844146728516, "Pretrain/Step": 84, "Pretrain/Step Time": 8.440125908170428} +{"Pretrain/Learning Rate": 1.486013986013986e-05, "Pretrain/Loss": 2.5818870067596436, "Pretrain/Loss (Raw)": 2.0055992603302, "Pretrain/Step": 85, "Pretrain/Step Time": 8.441532920388614} +{"Pretrain/Learning Rate": 1.5034965034965034e-05, "Pretrain/Loss": 2.580601930618286, "Pretrain/Loss (Raw)": 2.4713892936706543, "Pretrain/Step": 86, "Pretrain/Step Time": 8.439794947934706} +{"Pretrain/Learning Rate": 1.5209790209790212e-05, "Pretrain/Loss": 2.576735496520996, "Pretrain/Loss (Raw)": 2.2442233562469482, "Pretrain/Step": 87, "Pretrain/Step Time": 8.437555858458596} +{"Pretrain/Learning Rate": 1.5384615384615387e-05, "Pretrain/Loss": 2.575334072113037, "Pretrain/Loss (Raw)": 2.4534049034118652, "Pretrain/Step": 88, "Pretrain/Step Time": 8.436114820567044} +{"Pretrain/Learning Rate": 1.555944055944056e-05, "Pretrain/Loss": 2.571746587753296, "Pretrain/Loss (Raw)": 2.256024122238159, "Pretrain/Step": 89, "Pretrain/Step Time": 8.434495119566328} +{"Pretrain/Learning Rate": 1.5734265734265734e-05, "Pretrain/Loss": 2.566314458847046, "Pretrain/Loss (Raw)": 2.0828733444213867, "Pretrain/Step": 90, "Pretrain/Step Time": 8.433544532457988} +{"Pretrain/Learning Rate": 1.590909090909091e-05, "Pretrain/Loss": 2.5665836334228516, "Pretrain/Loss (Raw)": 2.590810537338257, "Pretrain/Step": 91, "Pretrain/Step Time": 8.432939767837524} +{"Pretrain/Learning Rate": 1.6083916083916083e-05, "Pretrain/Loss": 2.563009738922119, "Pretrain/Loss (Raw)": 2.237780809402466, "Pretrain/Step": 92, "Pretrain/Step Time": 8.431992808113927} +{"Pretrain/Learning Rate": 1.625874125874126e-05, "Pretrain/Loss": 2.5606696605682373, "Pretrain/Loss (Raw)": 2.3453822135925293, "Pretrain/Step": 93, "Pretrain/Step Time": 8.433087069501159} +{"Pretrain/Learning Rate": 1.6433566433566433e-05, "Pretrain/Loss": 2.5560214519500732, "Pretrain/Loss (Raw)": 2.1237547397613525, "Pretrain/Step": 94, "Pretrain/Step Time": 8.432896474574475} +{"Pretrain/Learning Rate": 1.660839160839161e-05, "Pretrain/Loss": 2.5559685230255127, "Pretrain/Loss (Raw)": 2.550973415374756, "Pretrain/Step": 95, "Pretrain/Step Time": 8.438217037602476} +{"Pretrain/Learning Rate": 1.6783216783216786e-05, "Pretrain/Loss": 2.5533976554870605, "Pretrain/Loss (Raw)": 2.309148073196411, "Pretrain/Step": 96, "Pretrain/Step Time": 8.437975312272707} +{"Pretrain/Learning Rate": 1.695804195804196e-05, "Pretrain/Loss": 2.5509772300720215, "Pretrain/Loss (Raw)": 2.3186535835266113, "Pretrain/Step": 97, "Pretrain/Step Time": 8.447388479390096} +{"Pretrain/Learning Rate": 1.7132867132867133e-05, "Pretrain/Loss": 2.5480234622955322, "Pretrain/Loss (Raw)": 2.2615129947662354, "Pretrain/Step": 98, "Pretrain/Step Time": 8.4461000208952} +{"Pretrain/Learning Rate": 1.730769230769231e-05, "Pretrain/Loss": 2.5461771488189697, "Pretrain/Loss (Raw)": 2.3652267456054688, "Pretrain/Step": 99, "Pretrain/Step Time": 8.445608408764155} +{"Pretrain/Learning Rate": 1.7482517482517483e-05, "Pretrain/Loss": 2.542768716812134, "Pretrain/Loss (Raw)": 2.2053346633911133, "Pretrain/Step": 100, "Pretrain/Step Time": 8.446989934444428} +{"Pretrain/Learning Rate": 1.7657342657342656e-05, "Pretrain/Loss": 2.539476156234741, "Pretrain/Loss (Raw)": 2.2102057933807373, "Pretrain/Step": 101, "Pretrain/Step Time": 8.446199542224997} +{"Pretrain/Learning Rate": 1.7832167832167836e-05, "Pretrain/Loss": 2.5360031127929688, "Pretrain/Loss (Raw)": 2.185237407684326, "Pretrain/Step": 102, "Pretrain/Step Time": 8.443659873569713} +{"Pretrain/Learning Rate": 1.800699300699301e-05, "Pretrain/Loss": 2.533252716064453, "Pretrain/Loss (Raw)": 2.252718210220337, "Pretrain/Step": 103, "Pretrain/Step Time": 8.441364563784553} +{"Pretrain/Learning Rate": 1.8181818181818182e-05, "Pretrain/Loss": 2.5306949615478516, "Pretrain/Loss (Raw)": 2.267242431640625, "Pretrain/Step": 104, "Pretrain/Step Time": 8.443234943426573} +{"Pretrain/Learning Rate": 1.835664335664336e-05, "Pretrain/Loss": 2.528409957885742, "Pretrain/Loss (Raw)": 2.290757417678833, "Pretrain/Step": 105, "Pretrain/Step Time": 8.440855850492206} +{"Pretrain/Learning Rate": 1.8531468531468532e-05, "Pretrain/Loss": 2.526700973510742, "Pretrain/Loss (Raw)": 2.3472585678100586, "Pretrain/Step": 106, "Pretrain/Step Time": 8.439621653196946} +{"Pretrain/Learning Rate": 1.8706293706293705e-05, "Pretrain/Loss": 2.5233144760131836, "Pretrain/Loss (Raw)": 2.1643717288970947, "Pretrain/Step": 107, "Pretrain/Step Time": 8.437412293157845} +{"Pretrain/Learning Rate": 1.888111888111888e-05, "Pretrain/Loss": 2.5199551582336426, "Pretrain/Loss (Raw)": 2.1605029106140137, "Pretrain/Step": 108, "Pretrain/Step Time": 8.441521454740453} +{"Pretrain/Learning Rate": 1.9055944055944055e-05, "Pretrain/Loss": 2.517702579498291, "Pretrain/Loss (Raw)": 2.274453639984131, "Pretrain/Step": 109, "Pretrain/Step Time": 8.441852455839104} +{"Pretrain/Learning Rate": 1.923076923076923e-05, "Pretrain/Loss": 2.5138065814971924, "Pretrain/Loss (Raw)": 2.0891330242156982, "Pretrain/Step": 110, "Pretrain/Step Time": 8.442624022743919} +{"Pretrain/Learning Rate": 1.9405594405594408e-05, "Pretrain/Loss": 2.5133440494537354, "Pretrain/Loss (Raw)": 2.4624361991882324, "Pretrain/Step": 111, "Pretrain/Step Time": 8.44120879216237} +{"Pretrain/Learning Rate": 1.958041958041958e-05, "Pretrain/Loss": 2.5110344886779785, "Pretrain/Loss (Raw)": 2.2546708583831787, "Pretrain/Step": 112, "Pretrain/Step Time": 8.446013035518783} +{"Pretrain/Learning Rate": 1.9755244755244758e-05, "Pretrain/Loss": 2.5090041160583496, "Pretrain/Loss (Raw)": 2.2816109657287598, "Pretrain/Step": 113, "Pretrain/Step Time": 8.446574413670902} +{"Pretrain/Learning Rate": 1.993006993006993e-05, "Pretrain/Loss": 2.509037494659424, "Pretrain/Loss (Raw)": 2.512822389602661, "Pretrain/Step": 114, "Pretrain/Step Time": 8.452115853627523} +{"Pretrain/Learning Rate": 2.0104895104895104e-05, "Pretrain/Loss": 2.5080673694610596, "Pretrain/Loss (Raw)": 2.3974809646606445, "Pretrain/Step": 115, "Pretrain/Step Time": 8.452115825984789} +{"Pretrain/Learning Rate": 2.027972027972028e-05, "Pretrain/Loss": 2.5054125785827637, "Pretrain/Loss (Raw)": 2.200106620788574, "Pretrain/Step": 116, "Pretrain/Step Time": 8.452230599419824} +{"Pretrain/Learning Rate": 2.0454545454545457e-05, "Pretrain/Loss": 2.503352165222168, "Pretrain/Loss (Raw)": 2.2643191814422607, "Pretrain/Step": 117, "Pretrain/Step Time": 8.44954455204499} +{"Pretrain/Learning Rate": 2.062937062937063e-05, "Pretrain/Loss": 2.501420259475708, "Pretrain/Loss (Raw)": 2.275442123413086, "Pretrain/Step": 118, "Pretrain/Step Time": 8.448714215876693} +{"Pretrain/Learning Rate": 2.0804195804195807e-05, "Pretrain/Loss": 2.4984259605407715, "Pretrain/Loss (Raw)": 2.145047664642334, "Pretrain/Step": 119, "Pretrain/Step Time": 8.446799668945184} +{"Pretrain/Learning Rate": 2.097902097902098e-05, "Pretrain/Loss": 2.4968278408050537, "Pretrain/Loss (Raw)": 2.3066651821136475, "Pretrain/Step": 120, "Pretrain/Step Time": 8.44654988249143} +{"Pretrain/Learning Rate": 2.1153846153846154e-05, "Pretrain/Loss": 2.495558500289917, "Pretrain/Loss (Raw)": 2.343240261077881, "Pretrain/Step": 121, "Pretrain/Step Time": 8.444918388177541} +{"Pretrain/Learning Rate": 2.132867132867133e-05, "Pretrain/Loss": 2.4941349029541016, "Pretrain/Loss (Raw)": 2.321883201599121, "Pretrain/Step": 122, "Pretrain/Step Time": 8.44331183980723} +{"Pretrain/Learning Rate": 2.1503496503496503e-05, "Pretrain/Loss": 2.4908673763275146, "Pretrain/Loss (Raw)": 2.09224796295166, "Pretrain/Step": 123, "Pretrain/Step Time": 8.44255891078856} +{"Pretrain/Learning Rate": 2.1678321678321677e-05, "Pretrain/Loss": 2.4897844791412354, "Pretrain/Loss (Raw)": 2.3565478324890137, "Pretrain/Step": 124, "Pretrain/Step Time": 8.44247539966337} +{"Pretrain/Learning Rate": 2.1853146853146857e-05, "Pretrain/Loss": 2.4874815940856934, "Pretrain/Loss (Raw)": 2.201909065246582, "Pretrain/Step": 125, "Pretrain/Step Time": 8.441252696990967} +{"Pretrain/Learning Rate": 2.202797202797203e-05, "Pretrain/Loss": 2.4859745502471924, "Pretrain/Loss (Raw)": 2.2976348400115967, "Pretrain/Step": 126, "Pretrain/Step Time": 8.440225296550327} +{"Pretrain/Learning Rate": 2.2202797202797203e-05, "Pretrain/Loss": 2.483196496963501, "Pretrain/Loss (Raw)": 2.1331896781921387, "Pretrain/Step": 127, "Pretrain/Step Time": 8.443887269403053} +{"Pretrain/Learning Rate": 2.237762237762238e-05, "Pretrain/Loss": 2.4800643920898438, "Pretrain/Loss (Raw)": 2.0822362899780273, "Pretrain/Step": 128, "Pretrain/Step Time": 8.443548670038581} +{"Pretrain/Learning Rate": 2.2552447552447553e-05, "Pretrain/Loss": 2.4739913940429688, "Pretrain/Loss (Raw)": 2.331756591796875, "Pretrain/Step": 129, "Pretrain/Step Time": 8.411532478407025} +{"Pretrain/Learning Rate": 2.272727272727273e-05, "Pretrain/Loss": 2.4668784141540527, "Pretrain/Loss (Raw)": 2.270402431488037, "Pretrain/Step": 130, "Pretrain/Step Time": 8.415411654859781} +{"Pretrain/Learning Rate": 2.2902097902097902e-05, "Pretrain/Loss": 2.447775363922119, "Pretrain/Loss (Raw)": 2.317582845687866, "Pretrain/Step": 131, "Pretrain/Step Time": 8.417342066764832} +{"Pretrain/Learning Rate": 2.307692307692308e-05, "Pretrain/Loss": 2.4381790161132812, "Pretrain/Loss (Raw)": 2.3762741088867188, "Pretrain/Step": 132, "Pretrain/Step Time": 8.415499178692698} +{"Pretrain/Learning Rate": 2.3251748251748252e-05, "Pretrain/Loss": 2.430784225463867, "Pretrain/Loss (Raw)": 2.3943324089050293, "Pretrain/Step": 133, "Pretrain/Step Time": 8.417571261525154} +{"Pretrain/Learning Rate": 2.342657342657343e-05, "Pretrain/Loss": 2.423020362854004, "Pretrain/Loss (Raw)": 2.0693559646606445, "Pretrain/Step": 134, "Pretrain/Step Time": 8.416563924401999} +{"Pretrain/Learning Rate": 2.3601398601398602e-05, "Pretrain/Loss": 2.412325143814087, "Pretrain/Loss (Raw)": 2.3607466220855713, "Pretrain/Step": 135, "Pretrain/Step Time": 8.417835060507059} +{"Pretrain/Learning Rate": 2.377622377622378e-05, "Pretrain/Loss": 2.3965816497802734, "Pretrain/Loss (Raw)": 2.1301891803741455, "Pretrain/Step": 136, "Pretrain/Step Time": 8.419064298272133} +{"Pretrain/Learning Rate": 2.3951048951048952e-05, "Pretrain/Loss": 2.389895439147949, "Pretrain/Loss (Raw)": 2.0614395141601562, "Pretrain/Step": 137, "Pretrain/Step Time": 8.419989600777626} +{"Pretrain/Learning Rate": 2.4125874125874125e-05, "Pretrain/Loss": 2.3751168251037598, "Pretrain/Loss (Raw)": 2.1862072944641113, "Pretrain/Step": 138, "Pretrain/Step Time": 8.420477632433176} +{"Pretrain/Learning Rate": 2.43006993006993e-05, "Pretrain/Loss": 2.3671536445617676, "Pretrain/Loss (Raw)": 2.443483352661133, "Pretrain/Step": 139, "Pretrain/Step Time": 8.419899368658662} +{"Pretrain/Learning Rate": 2.4475524475524478e-05, "Pretrain/Loss": 2.363863945007324, "Pretrain/Loss (Raw)": 2.2857511043548584, "Pretrain/Step": 140, "Pretrain/Step Time": 8.422320235520601} +{"Pretrain/Learning Rate": 2.465034965034965e-05, "Pretrain/Loss": 2.358505964279175, "Pretrain/Loss (Raw)": 2.22131085395813, "Pretrain/Step": 141, "Pretrain/Step Time": 8.420109761878848} +{"Pretrain/Learning Rate": 2.4825174825174828e-05, "Pretrain/Loss": 2.355562686920166, "Pretrain/Loss (Raw)": 2.2653968334198, "Pretrain/Step": 142, "Pretrain/Step Time": 8.420024933293462} +{"Pretrain/Learning Rate": 2.5e-05, "Pretrain/Loss": 2.3521437644958496, "Pretrain/Loss (Raw)": 2.1397461891174316, "Pretrain/Step": 143, "Pretrain/Step Time": 8.41118130274117} +{"Pretrain/Learning Rate": 2.5174825174825178e-05, "Pretrain/Loss": 2.347562313079834, "Pretrain/Loss (Raw)": 2.340961456298828, "Pretrain/Step": 144, "Pretrain/Step Time": 8.411529114469886} +{"Pretrain/Learning Rate": 2.534965034965035e-05, "Pretrain/Loss": 2.3455934524536133, "Pretrain/Loss (Raw)": 2.371675968170166, "Pretrain/Step": 145, "Pretrain/Step Time": 8.413061380386353} +{"Pretrain/Learning Rate": 2.5524475524475528e-05, "Pretrain/Loss": 2.3439531326293945, "Pretrain/Loss (Raw)": 2.181705951690674, "Pretrain/Step": 146, "Pretrain/Step Time": 8.412535889074206} +{"Pretrain/Learning Rate": 2.5699300699300697e-05, "Pretrain/Loss": 2.3395180702209473, "Pretrain/Loss (Raw)": 2.1622321605682373, "Pretrain/Step": 147, "Pretrain/Step Time": 8.4198376853019} +{"Pretrain/Learning Rate": 2.5874125874125877e-05, "Pretrain/Loss": 2.331268787384033, "Pretrain/Loss (Raw)": 2.15397572517395, "Pretrain/Step": 148, "Pretrain/Step Time": 8.418290488421917} +{"Pretrain/Learning Rate": 2.6048951048951047e-05, "Pretrain/Loss": 2.3287668228149414, "Pretrain/Loss (Raw)": 2.5208864212036133, "Pretrain/Step": 149, "Pretrain/Step Time": 8.422018337994814} +{"Pretrain/Learning Rate": 2.6223776223776224e-05, "Pretrain/Loss": 2.325338840484619, "Pretrain/Loss (Raw)": 2.203613042831421, "Pretrain/Step": 150, "Pretrain/Step Time": 8.423982286825776} +{"Pretrain/Learning Rate": 2.6398601398601404e-05, "Pretrain/Loss": 2.3231606483459473, "Pretrain/Loss (Raw)": 2.148054361343384, "Pretrain/Step": 151, "Pretrain/Step Time": 8.422512985765934} +{"Pretrain/Learning Rate": 2.6573426573426574e-05, "Pretrain/Loss": 2.317314624786377, "Pretrain/Loss (Raw)": 2.1333799362182617, "Pretrain/Step": 152, "Pretrain/Step Time": 8.425539173185825} +{"Pretrain/Learning Rate": 2.674825174825175e-05, "Pretrain/Loss": 2.3137426376342773, "Pretrain/Loss (Raw)": 2.2912306785583496, "Pretrain/Step": 153, "Pretrain/Step Time": 8.426706621423364} +{"Pretrain/Learning Rate": 2.6923076923076923e-05, "Pretrain/Loss": 2.310443639755249, "Pretrain/Loss (Raw)": 2.2624075412750244, "Pretrain/Step": 154, "Pretrain/Step Time": 8.427204938605428} +{"Pretrain/Learning Rate": 2.70979020979021e-05, "Pretrain/Loss": 2.307185649871826, "Pretrain/Loss (Raw)": 2.1881210803985596, "Pretrain/Step": 155, "Pretrain/Step Time": 8.426489880308509} +{"Pretrain/Learning Rate": 2.7272727272727273e-05, "Pretrain/Loss": 2.3076705932617188, "Pretrain/Loss (Raw)": 2.358001470565796, "Pretrain/Step": 156, "Pretrain/Step Time": 8.427209712564945} +{"Pretrain/Learning Rate": 2.744755244755245e-05, "Pretrain/Loss": 2.3048996925354004, "Pretrain/Loss (Raw)": 2.2472424507141113, "Pretrain/Step": 157, "Pretrain/Step Time": 8.42489855736494} +{"Pretrain/Learning Rate": 2.762237762237762e-05, "Pretrain/Loss": 2.303006172180176, "Pretrain/Loss (Raw)": 2.1809258460998535, "Pretrain/Step": 158, "Pretrain/Step Time": 8.422808649018407} +{"Pretrain/Learning Rate": 2.77972027972028e-05, "Pretrain/Loss": 2.3002593517303467, "Pretrain/Loss (Raw)": 2.2317912578582764, "Pretrain/Step": 159, "Pretrain/Step Time": 8.422870744019747} +{"Pretrain/Learning Rate": 2.7972027972027976e-05, "Pretrain/Loss": 2.299868583679199, "Pretrain/Loss (Raw)": 2.3612492084503174, "Pretrain/Step": 160, "Pretrain/Step Time": 8.421829929575324} +{"Pretrain/Learning Rate": 2.8146853146853146e-05, "Pretrain/Loss": 2.299081802368164, "Pretrain/Loss (Raw)": 2.384721279144287, "Pretrain/Step": 161, "Pretrain/Step Time": 8.419693551957607} +{"Pretrain/Learning Rate": 2.8321678321678326e-05, "Pretrain/Loss": 2.29870343208313, "Pretrain/Loss (Raw)": 2.2958192825317383, "Pretrain/Step": 162, "Pretrain/Step Time": 8.420237286016345} +{"Pretrain/Learning Rate": 2.8496503496503496e-05, "Pretrain/Loss": 2.2960283756256104, "Pretrain/Loss (Raw)": 2.209475517272949, "Pretrain/Step": 163, "Pretrain/Step Time": 8.424334006384015} +{"Pretrain/Learning Rate": 2.8671328671328672e-05, "Pretrain/Loss": 2.2954907417297363, "Pretrain/Loss (Raw)": 2.2256906032562256, "Pretrain/Step": 164, "Pretrain/Step Time": 8.425174729898572} +{"Pretrain/Learning Rate": 2.8846153846153845e-05, "Pretrain/Loss": 2.296774387359619, "Pretrain/Loss (Raw)": 2.4022629261016846, "Pretrain/Step": 165, "Pretrain/Step Time": 8.428028488531709} +{"Pretrain/Learning Rate": 2.9020979020979022e-05, "Pretrain/Loss": 2.2939116954803467, "Pretrain/Loss (Raw)": 2.0771119594573975, "Pretrain/Step": 166, "Pretrain/Step Time": 8.428768180310726} +{"Pretrain/Learning Rate": 2.91958041958042e-05, "Pretrain/Loss": 2.2886993885040283, "Pretrain/Loss (Raw)": 2.083937883377075, "Pretrain/Step": 167, "Pretrain/Step Time": 8.430532593280077} +{"Pretrain/Learning Rate": 2.9370629370629372e-05, "Pretrain/Loss": 2.2866899967193604, "Pretrain/Loss (Raw)": 2.071197032928467, "Pretrain/Step": 168, "Pretrain/Step Time": 8.432279167696834} +{"Pretrain/Learning Rate": 2.954545454545455e-05, "Pretrain/Loss": 2.286397695541382, "Pretrain/Loss (Raw)": 2.2021358013153076, "Pretrain/Step": 169, "Pretrain/Step Time": 8.433134205639362} +{"Pretrain/Learning Rate": 2.972027972027972e-05, "Pretrain/Loss": 2.284158229827881, "Pretrain/Loss (Raw)": 2.190988540649414, "Pretrain/Step": 170, "Pretrain/Step Time": 8.433038195595145} +{"Pretrain/Learning Rate": 2.9895104895104898e-05, "Pretrain/Loss": 2.282792329788208, "Pretrain/Loss (Raw)": 2.3003315925598145, "Pretrain/Step": 171, "Pretrain/Step Time": 8.432908875867724} +{"Pretrain/Learning Rate": 3.0069930069930068e-05, "Pretrain/Loss": 2.283339023590088, "Pretrain/Loss (Raw)": 2.365899085998535, "Pretrain/Step": 172, "Pretrain/Step Time": 8.434100741520524} +{"Pretrain/Learning Rate": 3.0244755244755245e-05, "Pretrain/Loss": 2.2835466861724854, "Pretrain/Loss (Raw)": 2.2303662300109863, "Pretrain/Step": 173, "Pretrain/Step Time": 8.432693511247635} +{"Pretrain/Learning Rate": 3.0419580419580425e-05, "Pretrain/Loss": 2.2820563316345215, "Pretrain/Loss (Raw)": 2.249741792678833, "Pretrain/Step": 174, "Pretrain/Step Time": 8.431216726079583} +{"Pretrain/Learning Rate": 3.0594405594405594e-05, "Pretrain/Loss": 2.2790110111236572, "Pretrain/Loss (Raw)": 2.0368192195892334, "Pretrain/Step": 175, "Pretrain/Step Time": 8.4325390458107} +{"Pretrain/Learning Rate": 3.0769230769230774e-05, "Pretrain/Loss": 2.278198480606079, "Pretrain/Loss (Raw)": 2.2193052768707275, "Pretrain/Step": 176, "Pretrain/Step Time": 8.431306421756744} +{"Pretrain/Learning Rate": 3.094405594405594e-05, "Pretrain/Loss": 2.278268337249756, "Pretrain/Loss (Raw)": 2.2881762981414795, "Pretrain/Step": 177, "Pretrain/Step Time": 8.43349114432931} +{"Pretrain/Learning Rate": 3.111888111888112e-05, "Pretrain/Loss": 2.2749276161193848, "Pretrain/Loss (Raw)": 2.107250213623047, "Pretrain/Step": 178, "Pretrain/Step Time": 8.433222625404596} +{"Pretrain/Learning Rate": 3.1293706293706294e-05, "Pretrain/Loss": 2.2743642330169678, "Pretrain/Loss (Raw)": 2.3701272010803223, "Pretrain/Step": 179, "Pretrain/Step Time": 8.435131354257464} +{"Pretrain/Learning Rate": 3.146853146853147e-05, "Pretrain/Loss": 2.275056838989258, "Pretrain/Loss (Raw)": 2.3993382453918457, "Pretrain/Step": 180, "Pretrain/Step Time": 8.437808837741613} +{"Pretrain/Learning Rate": 3.164335664335665e-05, "Pretrain/Loss": 2.2738475799560547, "Pretrain/Loss (Raw)": 2.24702787399292, "Pretrain/Step": 181, "Pretrain/Step Time": 8.437743827700615} +{"Pretrain/Learning Rate": 3.181818181818182e-05, "Pretrain/Loss": 2.271916627883911, "Pretrain/Loss (Raw)": 2.186370372772217, "Pretrain/Step": 182, "Pretrain/Step Time": 8.438489435240626} +{"Pretrain/Learning Rate": 3.1993006993006994e-05, "Pretrain/Loss": 2.2722301483154297, "Pretrain/Loss (Raw)": 2.2749669551849365, "Pretrain/Step": 183, "Pretrain/Step Time": 8.441409515216947} +{"Pretrain/Learning Rate": 3.216783216783217e-05, "Pretrain/Loss": 2.2732129096984863, "Pretrain/Loss (Raw)": 2.3746228218078613, "Pretrain/Step": 184, "Pretrain/Step Time": 8.442736698314548} +{"Pretrain/Learning Rate": 3.234265734265735e-05, "Pretrain/Loss": 2.2745585441589355, "Pretrain/Loss (Raw)": 2.2810614109039307, "Pretrain/Step": 185, "Pretrain/Step Time": 8.440261816605926} +{"Pretrain/Learning Rate": 3.251748251748252e-05, "Pretrain/Loss": 2.2727174758911133, "Pretrain/Loss (Raw)": 2.149916410446167, "Pretrain/Step": 186, "Pretrain/Step Time": 8.43991431221366} +{"Pretrain/Learning Rate": 3.269230769230769e-05, "Pretrain/Loss": 2.2708096504211426, "Pretrain/Loss (Raw)": 2.209228038787842, "Pretrain/Step": 187, "Pretrain/Step Time": 8.43694531172514} +{"Pretrain/Learning Rate": 3.2867132867132866e-05, "Pretrain/Loss": 2.271848201751709, "Pretrain/Loss (Raw)": 2.2651207447052, "Pretrain/Step": 188, "Pretrain/Step Time": 8.43728713132441} +{"Pretrain/Learning Rate": 3.3041958041958046e-05, "Pretrain/Loss": 2.2711050510406494, "Pretrain/Loss (Raw)": 2.2652530670166016, "Pretrain/Step": 189, "Pretrain/Step Time": 8.43966849707067} +{"Pretrain/Learning Rate": 3.321678321678322e-05, "Pretrain/Loss": 2.2703323364257812, "Pretrain/Loss (Raw)": 2.2722272872924805, "Pretrain/Step": 190, "Pretrain/Step Time": 8.442256582900882} +{"Pretrain/Learning Rate": 3.339160839160839e-05, "Pretrain/Loss": 2.268768310546875, "Pretrain/Loss (Raw)": 2.213365077972412, "Pretrain/Step": 191, "Pretrain/Step Time": 8.440180765464902} +{"Pretrain/Learning Rate": 3.356643356643357e-05, "Pretrain/Loss": 2.266768217086792, "Pretrain/Loss (Raw)": 2.1737797260284424, "Pretrain/Step": 192, "Pretrain/Step Time": 8.442576583474874} +{"Pretrain/Learning Rate": 3.374125874125874e-05, "Pretrain/Loss": 2.266756296157837, "Pretrain/Loss (Raw)": 2.258572578430176, "Pretrain/Step": 193, "Pretrain/Step Time": 8.441172190010548} +{"Pretrain/Learning Rate": 3.391608391608392e-05, "Pretrain/Loss": 2.2644786834716797, "Pretrain/Loss (Raw)": 2.1713247299194336, "Pretrain/Step": 194, "Pretrain/Step Time": 8.443860940635204} +{"Pretrain/Learning Rate": 3.409090909090909e-05, "Pretrain/Loss": 2.2632994651794434, "Pretrain/Loss (Raw)": 2.138489246368408, "Pretrain/Step": 195, "Pretrain/Step Time": 8.4460552893579} +{"Pretrain/Learning Rate": 3.4265734265734265e-05, "Pretrain/Loss": 2.2619030475616455, "Pretrain/Loss (Raw)": 2.227207660675049, "Pretrain/Step": 196, "Pretrain/Step Time": 8.448581330478191} +{"Pretrain/Learning Rate": 3.4440559440559445e-05, "Pretrain/Loss": 2.2621397972106934, "Pretrain/Loss (Raw)": 2.2277438640594482, "Pretrain/Step": 197, "Pretrain/Step Time": 8.446984607726336} +{"Pretrain/Learning Rate": 3.461538461538462e-05, "Pretrain/Loss": 2.2622714042663574, "Pretrain/Loss (Raw)": 2.2804346084594727, "Pretrain/Step": 198, "Pretrain/Step Time": 8.448266422376037} +{"Pretrain/Learning Rate": 3.479020979020979e-05, "Pretrain/Loss": 2.2601780891418457, "Pretrain/Loss (Raw)": 2.08609676361084, "Pretrain/Step": 199, "Pretrain/Step Time": 8.451328067108989} +{"Pretrain/Learning Rate": 3.4965034965034965e-05, "Pretrain/Loss": 2.257612943649292, "Pretrain/Loss (Raw)": 2.110304355621338, "Pretrain/Step": 200, "Pretrain/Step Time": 8.448089968413115} +{"Pretrain/Learning Rate": 3.5139860139860145e-05, "Pretrain/Loss": 2.258457660675049, "Pretrain/Loss (Raw)": 2.378195285797119, "Pretrain/Step": 201, "Pretrain/Step Time": 8.44194576703012} +{"Pretrain/Learning Rate": 3.531468531468531e-05, "Pretrain/Loss": 2.256568193435669, "Pretrain/Loss (Raw)": 1.9934048652648926, "Pretrain/Step": 202, "Pretrain/Step Time": 8.43948194757104} +{"Pretrain/Learning Rate": 3.548951048951049e-05, "Pretrain/Loss": 2.256296157836914, "Pretrain/Loss (Raw)": 2.283686637878418, "Pretrain/Step": 203, "Pretrain/Step Time": 8.438762033358216} +{"Pretrain/Learning Rate": 3.566433566433567e-05, "Pretrain/Loss": 2.255697250366211, "Pretrain/Loss (Raw)": 2.276137351989746, "Pretrain/Step": 204, "Pretrain/Step Time": 8.441508060321212} +{"Pretrain/Learning Rate": 3.583916083916084e-05, "Pretrain/Loss": 2.255586624145508, "Pretrain/Loss (Raw)": 2.3125627040863037, "Pretrain/Step": 205, "Pretrain/Step Time": 8.440797459334135} +{"Pretrain/Learning Rate": 3.601398601398602e-05, "Pretrain/Loss": 2.254599094390869, "Pretrain/Loss (Raw)": 2.0593206882476807, "Pretrain/Step": 206, "Pretrain/Step Time": 8.441995412111282} +{"Pretrain/Learning Rate": 3.618881118881119e-05, "Pretrain/Loss": 2.2554802894592285, "Pretrain/Loss (Raw)": 2.1327409744262695, "Pretrain/Step": 207, "Pretrain/Step Time": 8.438359420746565} +{"Pretrain/Learning Rate": 3.6363636363636364e-05, "Pretrain/Loss": 2.254396677017212, "Pretrain/Loss (Raw)": 2.188192129135132, "Pretrain/Step": 208, "Pretrain/Step Time": 8.433364387601614} +{"Pretrain/Learning Rate": 3.653846153846154e-05, "Pretrain/Loss": 2.2524232864379883, "Pretrain/Loss (Raw)": 2.043694496154785, "Pretrain/Step": 209, "Pretrain/Step Time": 8.438625752925873} +{"Pretrain/Learning Rate": 3.671328671328672e-05, "Pretrain/Loss": 2.2518343925476074, "Pretrain/Loss (Raw)": 2.3157029151916504, "Pretrain/Step": 210, "Pretrain/Step Time": 8.438799031078815} +{"Pretrain/Learning Rate": 3.688811188811189e-05, "Pretrain/Loss": 2.24674129486084, "Pretrain/Loss (Raw)": 1.9656486511230469, "Pretrain/Step": 211, "Pretrain/Step Time": 8.441393783316016} +{"Pretrain/Learning Rate": 3.7062937062937064e-05, "Pretrain/Loss": 2.2457895278930664, "Pretrain/Loss (Raw)": 2.2030839920043945, "Pretrain/Step": 212, "Pretrain/Step Time": 8.442349722608924} +{"Pretrain/Learning Rate": 3.7237762237762244e-05, "Pretrain/Loss": 2.2469124794006348, "Pretrain/Loss (Raw)": 2.149304151535034, "Pretrain/Step": 213, "Pretrain/Step Time": 8.440118318423629} +{"Pretrain/Learning Rate": 3.741258741258741e-05, "Pretrain/Loss": 2.2458338737487793, "Pretrain/Loss (Raw)": 2.333371639251709, "Pretrain/Step": 214, "Pretrain/Step Time": 8.440705319866538} +{"Pretrain/Learning Rate": 3.758741258741259e-05, "Pretrain/Loss": 2.2449865341186523, "Pretrain/Loss (Raw)": 2.1357712745666504, "Pretrain/Step": 215, "Pretrain/Step Time": 8.44400686956942} +{"Pretrain/Learning Rate": 3.776223776223776e-05, "Pretrain/Loss": 2.24310302734375, "Pretrain/Loss (Raw)": 2.212298631668091, "Pretrain/Step": 216, "Pretrain/Step Time": 8.445080902427435} +{"Pretrain/Learning Rate": 3.7937062937062936e-05, "Pretrain/Loss": 2.2433481216430664, "Pretrain/Loss (Raw)": 2.2873895168304443, "Pretrain/Step": 217, "Pretrain/Step Time": 8.445282489061356} +{"Pretrain/Learning Rate": 3.811188811188811e-05, "Pretrain/Loss": 2.2443935871124268, "Pretrain/Loss (Raw)": 2.216691732406616, "Pretrain/Step": 218, "Pretrain/Step Time": 8.443777648732066} +{"Pretrain/Learning Rate": 3.828671328671329e-05, "Pretrain/Loss": 2.240959882736206, "Pretrain/Loss (Raw)": 2.151270627975464, "Pretrain/Step": 219, "Pretrain/Step Time": 8.443633560091257} +{"Pretrain/Learning Rate": 3.846153846153846e-05, "Pretrain/Loss": 2.240752935409546, "Pretrain/Loss (Raw)": 2.211329936981201, "Pretrain/Step": 220, "Pretrain/Step Time": 8.44346096739173} +{"Pretrain/Learning Rate": 3.8636363636363636e-05, "Pretrain/Loss": 2.2398738861083984, "Pretrain/Loss (Raw)": 2.232835531234741, "Pretrain/Step": 221, "Pretrain/Step Time": 8.442580400034785} +{"Pretrain/Learning Rate": 3.8811188811188816e-05, "Pretrain/Loss": 2.240649700164795, "Pretrain/Loss (Raw)": 2.223048686981201, "Pretrain/Step": 222, "Pretrain/Step Time": 8.442124104127288} +{"Pretrain/Learning Rate": 3.898601398601399e-05, "Pretrain/Loss": 2.2372021675109863, "Pretrain/Loss (Raw)": 2.1096932888031006, "Pretrain/Step": 223, "Pretrain/Step Time": 8.436907453462481} +{"Pretrain/Learning Rate": 3.916083916083916e-05, "Pretrain/Loss": 2.2356889247894287, "Pretrain/Loss (Raw)": 2.115485191345215, "Pretrain/Step": 224, "Pretrain/Step Time": 8.436228357255459} +{"Pretrain/Learning Rate": 3.9335664335664336e-05, "Pretrain/Loss": 2.2352583408355713, "Pretrain/Loss (Raw)": 2.2635154724121094, "Pretrain/Step": 225, "Pretrain/Step Time": 8.430262869223952} +{"Pretrain/Learning Rate": 3.9510489510489516e-05, "Pretrain/Loss": 2.236062526702881, "Pretrain/Loss (Raw)": 2.364436626434326, "Pretrain/Step": 226, "Pretrain/Step Time": 8.436648160219193} +{"Pretrain/Learning Rate": 3.968531468531469e-05, "Pretrain/Loss": 2.233863353729248, "Pretrain/Loss (Raw)": 2.0837604999542236, "Pretrain/Step": 227, "Pretrain/Step Time": 8.439103050157428} +{"Pretrain/Learning Rate": 3.986013986013986e-05, "Pretrain/Loss": 2.2345290184020996, "Pretrain/Loss (Raw)": 2.290529727935791, "Pretrain/Step": 228, "Pretrain/Step Time": 8.436939591541886} +{"Pretrain/Learning Rate": 4.0034965034965035e-05, "Pretrain/Loss": 2.2341647148132324, "Pretrain/Loss (Raw)": 2.1635489463806152, "Pretrain/Step": 229, "Pretrain/Step Time": 8.434979667887092} +{"Pretrain/Learning Rate": 4.020979020979021e-05, "Pretrain/Loss": 2.2331676483154297, "Pretrain/Loss (Raw)": 2.0576207637786865, "Pretrain/Step": 230, "Pretrain/Step Time": 8.437136439606547} +{"Pretrain/Learning Rate": 4.038461538461539e-05, "Pretrain/Loss": 2.2332770824432373, "Pretrain/Loss (Raw)": 2.266756296157837, "Pretrain/Step": 231, "Pretrain/Step Time": 8.439341083168983} +{"Pretrain/Learning Rate": 4.055944055944056e-05, "Pretrain/Loss": 2.2311835289001465, "Pretrain/Loss (Raw)": 1.9992574453353882, "Pretrain/Step": 232, "Pretrain/Step Time": 8.436905309557915} +{"Pretrain/Learning Rate": 4.0734265734265735e-05, "Pretrain/Loss": 2.2304654121398926, "Pretrain/Loss (Raw)": 2.19881010055542, "Pretrain/Step": 233, "Pretrain/Step Time": 8.435994116589427} +{"Pretrain/Learning Rate": 4.0909090909090915e-05, "Pretrain/Loss": 2.2295517921447754, "Pretrain/Loss (Raw)": 2.2303340435028076, "Pretrain/Step": 234, "Pretrain/Step Time": 8.435242548584938} +{"Pretrain/Learning Rate": 4.108391608391609e-05, "Pretrain/Loss": 2.229306221008301, "Pretrain/Loss (Raw)": 2.1329329013824463, "Pretrain/Step": 235, "Pretrain/Step Time": 8.435151213780046} +{"Pretrain/Learning Rate": 4.125874125874126e-05, "Pretrain/Loss": 2.2293715476989746, "Pretrain/Loss (Raw)": 2.168869733810425, "Pretrain/Step": 236, "Pretrain/Step Time": 8.430873766541481} +{"Pretrain/Learning Rate": 4.1433566433566434e-05, "Pretrain/Loss": 2.2298874855041504, "Pretrain/Loss (Raw)": 2.3405046463012695, "Pretrain/Step": 237, "Pretrain/Step Time": 8.43198449909687} +{"Pretrain/Learning Rate": 4.1608391608391614e-05, "Pretrain/Loss": 2.2304635047912598, "Pretrain/Loss (Raw)": 2.162891387939453, "Pretrain/Step": 238, "Pretrain/Step Time": 8.430299025028944} +{"Pretrain/Learning Rate": 4.178321678321678e-05, "Pretrain/Loss": 2.2281506061553955, "Pretrain/Loss (Raw)": 2.1663498878479004, "Pretrain/Step": 239, "Pretrain/Step Time": 8.432645432651043} +{"Pretrain/Learning Rate": 4.195804195804196e-05, "Pretrain/Loss": 2.228447914123535, "Pretrain/Loss (Raw)": 2.29274582862854, "Pretrain/Step": 240, "Pretrain/Step Time": 8.427160698920488} +{"Pretrain/Learning Rate": 4.213286713286714e-05, "Pretrain/Loss": 2.2282915115356445, "Pretrain/Loss (Raw)": 2.2615878582000732, "Pretrain/Step": 241, "Pretrain/Step Time": 8.428828302770853} +{"Pretrain/Learning Rate": 4.230769230769231e-05, "Pretrain/Loss": 2.2254714965820312, "Pretrain/Loss (Raw)": 2.151843786239624, "Pretrain/Step": 242, "Pretrain/Step Time": 8.422243501991034} +{"Pretrain/Learning Rate": 4.248251748251749e-05, "Pretrain/Loss": 2.2242393493652344, "Pretrain/Loss (Raw)": 2.239753007888794, "Pretrain/Step": 243, "Pretrain/Step Time": 8.425353599712253} +{"Pretrain/Learning Rate": 4.265734265734266e-05, "Pretrain/Loss": 2.222848892211914, "Pretrain/Loss (Raw)": 2.0221524238586426, "Pretrain/Step": 244, "Pretrain/Step Time": 8.42605309933424} +{"Pretrain/Learning Rate": 4.2832167832167833e-05, "Pretrain/Loss": 2.222480058670044, "Pretrain/Loss (Raw)": 2.2170941829681396, "Pretrain/Step": 245, "Pretrain/Step Time": 8.42775846272707} +{"Pretrain/Learning Rate": 4.300699300699301e-05, "Pretrain/Loss": 2.2211647033691406, "Pretrain/Loss (Raw)": 2.1070852279663086, "Pretrain/Step": 246, "Pretrain/Step Time": 8.428782884031534} +{"Pretrain/Learning Rate": 4.318181818181819e-05, "Pretrain/Loss": 2.220668315887451, "Pretrain/Loss (Raw)": 2.081502676010132, "Pretrain/Step": 247, "Pretrain/Step Time": 8.428301116451621} +{"Pretrain/Learning Rate": 4.335664335664335e-05, "Pretrain/Loss": 2.2195987701416016, "Pretrain/Loss (Raw)": 2.169797658920288, "Pretrain/Step": 248, "Pretrain/Step Time": 8.427327124401927} +{"Pretrain/Learning Rate": 4.353146853146853e-05, "Pretrain/Loss": 2.2184371948242188, "Pretrain/Loss (Raw)": 2.194531202316284, "Pretrain/Step": 249, "Pretrain/Step Time": 8.430241571739316} +{"Pretrain/Learning Rate": 4.370629370629371e-05, "Pretrain/Loss": 2.2173733711242676, "Pretrain/Loss (Raw)": 2.185715436935425, "Pretrain/Step": 250, "Pretrain/Step Time": 8.430562734603882} +{"Pretrain/Learning Rate": 4.388111888111888e-05, "Pretrain/Loss": 2.218126058578491, "Pretrain/Loss (Raw)": 2.1885900497436523, "Pretrain/Step": 251, "Pretrain/Step Time": 8.429573182016611} +{"Pretrain/Learning Rate": 4.405594405594406e-05, "Pretrain/Loss": 2.2179574966430664, "Pretrain/Loss (Raw)": 2.334963321685791, "Pretrain/Step": 252, "Pretrain/Step Time": 8.430213801562786} +{"Pretrain/Learning Rate": 4.423076923076923e-05, "Pretrain/Loss": 2.2167959213256836, "Pretrain/Loss (Raw)": 2.0532584190368652, "Pretrain/Step": 253, "Pretrain/Step Time": 8.429914386942983} +{"Pretrain/Learning Rate": 4.4405594405594406e-05, "Pretrain/Loss": 2.215538263320923, "Pretrain/Loss (Raw)": 2.1366474628448486, "Pretrain/Step": 254, "Pretrain/Step Time": 8.431718919426203} +{"Pretrain/Learning Rate": 4.458041958041958e-05, "Pretrain/Loss": 2.2162561416625977, "Pretrain/Loss (Raw)": 2.225081443786621, "Pretrain/Step": 255, "Pretrain/Step Time": 8.42718980461359} +{"Pretrain/Learning Rate": 4.475524475524476e-05, "Pretrain/Loss": 2.2160086631774902, "Pretrain/Loss (Raw)": 2.050568103790283, "Pretrain/Step": 256, "Pretrain/Step Time": 8.426030391827226} +{"Pretrain/Learning Rate": 4.493006993006993e-05, "Pretrain/Loss": 2.2155399322509766, "Pretrain/Loss (Raw)": 2.2717480659484863, "Pretrain/Step": 257, "Pretrain/Step Time": 8.42400462180376} +{"Pretrain/Learning Rate": 4.5104895104895105e-05, "Pretrain/Loss": 2.2147669792175293, "Pretrain/Loss (Raw)": 2.1714632511138916, "Pretrain/Step": 258, "Pretrain/Step Time": 8.421556793153286} +{"Pretrain/Learning Rate": 4.5279720279720285e-05, "Pretrain/Loss": 2.2145841121673584, "Pretrain/Loss (Raw)": 2.2941675186157227, "Pretrain/Step": 259, "Pretrain/Step Time": 8.424866436049342} +{"Pretrain/Learning Rate": 4.545454545454546e-05, "Pretrain/Loss": 2.210811138153076, "Pretrain/Loss (Raw)": 1.8933115005493164, "Pretrain/Step": 260, "Pretrain/Step Time": 8.424888113513589} +{"Pretrain/Learning Rate": 4.562937062937063e-05, "Pretrain/Loss": 2.209056854248047, "Pretrain/Loss (Raw)": 2.1698076725006104, "Pretrain/Step": 261, "Pretrain/Step Time": 8.424473935738206} +{"Pretrain/Learning Rate": 4.5804195804195805e-05, "Pretrain/Loss": 2.2102408409118652, "Pretrain/Loss (Raw)": 2.2209060192108154, "Pretrain/Step": 262, "Pretrain/Step Time": 8.425658024847507} +{"Pretrain/Learning Rate": 4.597902097902098e-05, "Pretrain/Loss": 2.2082762718200684, "Pretrain/Loss (Raw)": 2.1093010902404785, "Pretrain/Step": 263, "Pretrain/Step Time": 8.424229711294174} +{"Pretrain/Learning Rate": 4.615384615384616e-05, "Pretrain/Loss": 2.2075915336608887, "Pretrain/Loss (Raw)": 2.0425288677215576, "Pretrain/Step": 264, "Pretrain/Step Time": 8.424374716356397} +{"Pretrain/Learning Rate": 4.632867132867133e-05, "Pretrain/Loss": 2.208559989929199, "Pretrain/Loss (Raw)": 2.1853716373443604, "Pretrain/Step": 265, "Pretrain/Step Time": 8.42558167874813} +{"Pretrain/Learning Rate": 4.6503496503496505e-05, "Pretrain/Loss": 2.209632635116577, "Pretrain/Loss (Raw)": 2.3235344886779785, "Pretrain/Step": 266, "Pretrain/Step Time": 8.426056085154414} +{"Pretrain/Learning Rate": 4.667832167832168e-05, "Pretrain/Loss": 2.208468437194824, "Pretrain/Loss (Raw)": 2.294466018676758, "Pretrain/Step": 267, "Pretrain/Step Time": 8.425311084836721} +{"Pretrain/Learning Rate": 4.685314685314686e-05, "Pretrain/Loss": 2.2082157135009766, "Pretrain/Loss (Raw)": 2.2533814907073975, "Pretrain/Step": 268, "Pretrain/Step Time": 8.423379868268967} +{"Pretrain/Learning Rate": 4.702797202797203e-05, "Pretrain/Loss": 2.2081375122070312, "Pretrain/Loss (Raw)": 2.2112996578216553, "Pretrain/Step": 269, "Pretrain/Step Time": 8.422128207981586} +{"Pretrain/Learning Rate": 4.7202797202797204e-05, "Pretrain/Loss": 2.2082905769348145, "Pretrain/Loss (Raw)": 2.284987211227417, "Pretrain/Step": 270, "Pretrain/Step Time": 8.423269376158714} +{"Pretrain/Learning Rate": 4.7377622377622384e-05, "Pretrain/Loss": 2.2091474533081055, "Pretrain/Loss (Raw)": 2.249462604522705, "Pretrain/Step": 271, "Pretrain/Step Time": 8.42176883853972} +{"Pretrain/Learning Rate": 4.755244755244756e-05, "Pretrain/Loss": 2.207561492919922, "Pretrain/Loss (Raw)": 2.137958526611328, "Pretrain/Step": 272, "Pretrain/Step Time": 8.419849999248981} +{"Pretrain/Learning Rate": 4.772727272727273e-05, "Pretrain/Loss": 2.206267833709717, "Pretrain/Loss (Raw)": 2.206061363220215, "Pretrain/Step": 273, "Pretrain/Step Time": 8.423390313982964} +{"Pretrain/Learning Rate": 4.7902097902097904e-05, "Pretrain/Loss": 2.207418441772461, "Pretrain/Loss (Raw)": 2.328984498977661, "Pretrain/Step": 274, "Pretrain/Step Time": 8.425656221807003} +{"Pretrain/Learning Rate": 4.8076923076923084e-05, "Pretrain/Loss": 2.2088255882263184, "Pretrain/Loss (Raw)": 2.342315912246704, "Pretrain/Step": 275, "Pretrain/Step Time": 8.42349911481142} +{"Pretrain/Learning Rate": 4.825174825174825e-05, "Pretrain/Loss": 2.2087388038635254, "Pretrain/Loss (Raw)": 2.1428868770599365, "Pretrain/Step": 276, "Pretrain/Step Time": 8.42641369253397} +{"Pretrain/Learning Rate": 4.842657342657343e-05, "Pretrain/Loss": 2.2061121463775635, "Pretrain/Loss (Raw)": 2.184694766998291, "Pretrain/Step": 277, "Pretrain/Step Time": 8.422036284580827} +{"Pretrain/Learning Rate": 4.86013986013986e-05, "Pretrain/Loss": 2.205829381942749, "Pretrain/Loss (Raw)": 2.1674113273620605, "Pretrain/Step": 278, "Pretrain/Step Time": 8.4233363494277} +{"Pretrain/Learning Rate": 4.8776223776223776e-05, "Pretrain/Loss": 2.205592632293701, "Pretrain/Loss (Raw)": 2.1177587509155273, "Pretrain/Step": 279, "Pretrain/Step Time": 8.424486301839352} +{"Pretrain/Learning Rate": 4.8951048951048956e-05, "Pretrain/Loss": 2.206130027770996, "Pretrain/Loss (Raw)": 2.2021563053131104, "Pretrain/Step": 280, "Pretrain/Step Time": 8.422121368348598} +{"Pretrain/Learning Rate": 4.912587412587413e-05, "Pretrain/Loss": 2.2068281173706055, "Pretrain/Loss (Raw)": 2.3805861473083496, "Pretrain/Step": 281, "Pretrain/Step Time": 8.424221018329263} +{"Pretrain/Learning Rate": 4.93006993006993e-05, "Pretrain/Loss": 2.2060298919677734, "Pretrain/Loss (Raw)": 2.1602377891540527, "Pretrain/Step": 282, "Pretrain/Step Time": 8.424261935055256} +{"Pretrain/Learning Rate": 4.9475524475524476e-05, "Pretrain/Loss": 2.206080913543701, "Pretrain/Loss (Raw)": 2.19462251663208, "Pretrain/Step": 283, "Pretrain/Step Time": 8.427695974707603} +{"Pretrain/Learning Rate": 4.9650349650349656e-05, "Pretrain/Loss": 2.205897569656372, "Pretrain/Loss (Raw)": 2.334562301635742, "Pretrain/Step": 284, "Pretrain/Step Time": 8.428576037287712} +{"Pretrain/Learning Rate": 4.982517482517482e-05, "Pretrain/Loss": 2.204594135284424, "Pretrain/Loss (Raw)": 2.0803725719451904, "Pretrain/Step": 285, "Pretrain/Step Time": 8.427745886147022} +{"Pretrain/Learning Rate": 5e-05, "Pretrain/Loss": 2.2062811851501465, "Pretrain/Loss (Raw)": 2.3968961238861084, "Pretrain/Step": 286, "Pretrain/Step Time": 8.426394956186414} +{"Pretrain/Learning Rate": 4.99999985581294e-05, "Pretrain/Loss": 2.2054312229156494, "Pretrain/Loss (Raw)": 2.123012065887451, "Pretrain/Step": 287, "Pretrain/Step Time": 8.425971632823348} +{"Pretrain/Learning Rate": 4.9999994232517746e-05, "Pretrain/Loss": 2.2026548385620117, "Pretrain/Loss (Raw)": 2.0058579444885254, "Pretrain/Step": 288, "Pretrain/Step Time": 8.422062765806913} +{"Pretrain/Learning Rate": 4.999998702316553e-05, "Pretrain/Loss": 2.2009129524230957, "Pretrain/Loss (Raw)": 2.1617469787597656, "Pretrain/Step": 289, "Pretrain/Step Time": 8.423876468092203} +{"Pretrain/Learning Rate": 4.999997693007361e-05, "Pretrain/Loss": 2.2001631259918213, "Pretrain/Loss (Raw)": 2.1998558044433594, "Pretrain/Step": 290, "Pretrain/Step Time": 8.425313794985414} +{"Pretrain/Learning Rate": 4.999996395324314e-05, "Pretrain/Loss": 2.2004964351654053, "Pretrain/Loss (Raw)": 2.252122640609741, "Pretrain/Step": 291, "Pretrain/Step Time": 8.426609564572573} +{"Pretrain/Learning Rate": 4.999994809267561e-05, "Pretrain/Loss": 2.2004923820495605, "Pretrain/Loss (Raw)": 2.225172519683838, "Pretrain/Step": 292, "Pretrain/Step Time": 8.425980530679226} +{"Pretrain/Learning Rate": 4.999992934837285e-05, "Pretrain/Loss": 2.2000651359558105, "Pretrain/Loss (Raw)": 2.347602128982544, "Pretrain/Step": 293, "Pretrain/Step Time": 8.427731255069375} +{"Pretrain/Learning Rate": 4.9999907720337026e-05, "Pretrain/Loss": 2.201106071472168, "Pretrain/Loss (Raw)": 2.2103488445281982, "Pretrain/Step": 294, "Pretrain/Step Time": 8.428840911015868} +{"Pretrain/Learning Rate": 4.999988320857063e-05, "Pretrain/Loss": 2.2016212940216064, "Pretrain/Loss (Raw)": 2.149873971939087, "Pretrain/Step": 295, "Pretrain/Step Time": 8.429644597694278} +{"Pretrain/Learning Rate": 4.999985581307649e-05, "Pretrain/Loss": 2.201235294342041, "Pretrain/Loss (Raw)": 2.02177095413208, "Pretrain/Step": 296, "Pretrain/Step Time": 8.429482309147716} +{"Pretrain/Learning Rate": 4.999982553385778e-05, "Pretrain/Loss": 2.2011828422546387, "Pretrain/Loss (Raw)": 2.1954588890075684, "Pretrain/Step": 297, "Pretrain/Step Time": 8.430813293904066} +{"Pretrain/Learning Rate": 4.999979237091797e-05, "Pretrain/Loss": 2.2013072967529297, "Pretrain/Loss (Raw)": 2.2068939208984375, "Pretrain/Step": 298, "Pretrain/Step Time": 8.431918321177363} +{"Pretrain/Learning Rate": 4.99997563242609e-05, "Pretrain/Loss": 2.2007336616516113, "Pretrain/Loss (Raw)": 2.226900577545166, "Pretrain/Step": 299, "Pretrain/Step Time": 8.43421453051269} +{"Pretrain/Learning Rate": 4.999971739389072e-05, "Pretrain/Loss": 2.1984567642211914, "Pretrain/Loss (Raw)": 2.0744686126708984, "Pretrain/Step": 300, "Pretrain/Step Time": 8.43484790623188} +{"Pretrain/Learning Rate": 4.999967557981192e-05, "Pretrain/Loss": 2.1989450454711914, "Pretrain/Loss (Raw)": 2.29289174079895, "Pretrain/Step": 301, "Pretrain/Step Time": 8.434291800484061} +{"Pretrain/Learning Rate": 4.999963088202934e-05, "Pretrain/Loss": 2.1984634399414062, "Pretrain/Loss (Raw)": 2.188066005706787, "Pretrain/Step": 302, "Pretrain/Step Time": 8.434115812182426} +{"Pretrain/Learning Rate": 4.9999583300548115e-05, "Pretrain/Loss": 2.199922561645508, "Pretrain/Loss (Raw)": 2.223609685897827, "Pretrain/Step": 303, "Pretrain/Step Time": 8.431978007778525} +{"Pretrain/Learning Rate": 4.9999532835373744e-05, "Pretrain/Loss": 2.199519395828247, "Pretrain/Loss (Raw)": 2.167682409286499, "Pretrain/Step": 304, "Pretrain/Step Time": 8.430052114650607} +{"Pretrain/Learning Rate": 4.999947948651204e-05, "Pretrain/Loss": 2.1996240615844727, "Pretrain/Loss (Raw)": 2.3015496730804443, "Pretrain/Step": 305, "Pretrain/Step Time": 8.428978595882654} +{"Pretrain/Learning Rate": 4.9999423253969166e-05, "Pretrain/Loss": 2.200127124786377, "Pretrain/Loss (Raw)": 2.17169451713562, "Pretrain/Step": 306, "Pretrain/Step Time": 8.428910456597805} +{"Pretrain/Learning Rate": 4.999936413775161e-05, "Pretrain/Loss": 2.198219060897827, "Pretrain/Loss (Raw)": 2.1258702278137207, "Pretrain/Step": 307, "Pretrain/Step Time": 8.431508207693696} +{"Pretrain/Learning Rate": 4.9999302137866186e-05, "Pretrain/Loss": 2.1954736709594727, "Pretrain/Loss (Raw)": 2.0479352474212646, "Pretrain/Step": 308, "Pretrain/Step Time": 8.427505251020193} +{"Pretrain/Learning Rate": 4.999923725432004e-05, "Pretrain/Loss": 2.1946940422058105, "Pretrain/Loss (Raw)": 2.147221326828003, "Pretrain/Step": 309, "Pretrain/Step Time": 8.430227125063539} +{"Pretrain/Learning Rate": 4.999916948712066e-05, "Pretrain/Loss": 2.195617914199829, "Pretrain/Loss (Raw)": 2.304647445678711, "Pretrain/Step": 310, "Pretrain/Step Time": 8.431380826979876} +{"Pretrain/Learning Rate": 4.999909883627587e-05, "Pretrain/Loss": 2.194350481033325, "Pretrain/Loss (Raw)": 2.1127090454101562, "Pretrain/Step": 311, "Pretrain/Step Time": 8.429622428491712} +{"Pretrain/Learning Rate": 4.999902530179381e-05, "Pretrain/Loss": 2.1936140060424805, "Pretrain/Loss (Raw)": 2.2803492546081543, "Pretrain/Step": 312, "Pretrain/Step Time": 8.428852239623666} +{"Pretrain/Learning Rate": 4.999894888368297e-05, "Pretrain/Loss": 2.191269874572754, "Pretrain/Loss (Raw)": 1.9810278415679932, "Pretrain/Step": 313, "Pretrain/Step Time": 8.435180053114891} +{"Pretrain/Learning Rate": 4.9998869581952165e-05, "Pretrain/Loss": 2.190861940383911, "Pretrain/Loss (Raw)": 2.09770131111145, "Pretrain/Step": 314, "Pretrain/Step Time": 8.43364385329187} +{"Pretrain/Learning Rate": 4.999878739661054e-05, "Pretrain/Loss": 2.1914865970611572, "Pretrain/Loss (Raw)": 2.28916597366333, "Pretrain/Step": 315, "Pretrain/Step Time": 8.43389818072319} +{"Pretrain/Learning Rate": 4.9998702327667565e-05, "Pretrain/Loss": 2.1901063919067383, "Pretrain/Loss (Raw)": 2.0884649753570557, "Pretrain/Step": 316, "Pretrain/Step Time": 8.436379376798868} +{"Pretrain/Learning Rate": 4.999861437513307e-05, "Pretrain/Loss": 2.189720630645752, "Pretrain/Loss (Raw)": 2.2159056663513184, "Pretrain/Step": 317, "Pretrain/Step Time": 8.432467440143228} +{"Pretrain/Learning Rate": 4.999852353901719e-05, "Pretrain/Loss": 2.188572883605957, "Pretrain/Loss (Raw)": 2.125297784805298, "Pretrain/Step": 318, "Pretrain/Step Time": 8.429417775943875} +{"Pretrain/Learning Rate": 4.999842981933041e-05, "Pretrain/Loss": 2.187983512878418, "Pretrain/Loss (Raw)": 2.137941360473633, "Pretrain/Step": 319, "Pretrain/Step Time": 8.430147007107735} +{"Pretrain/Learning Rate": 4.999833321608352e-05, "Pretrain/Loss": 2.1907243728637695, "Pretrain/Loss (Raw)": 2.5246057510375977, "Pretrain/Step": 320, "Pretrain/Step Time": 8.430328615009785} +{"Pretrain/Learning Rate": 4.999823372928769e-05, "Pretrain/Loss": 2.1909329891204834, "Pretrain/Loss (Raw)": 2.2852492332458496, "Pretrain/Step": 321, "Pretrain/Step Time": 8.427400689572096} +{"Pretrain/Learning Rate": 4.999813135895438e-05, "Pretrain/Loss": 2.189829111099243, "Pretrain/Loss (Raw)": 2.030043601989746, "Pretrain/Step": 322, "Pretrain/Step Time": 8.426852114498615} +{"Pretrain/Learning Rate": 4.9998026105095405e-05, "Pretrain/Loss": 2.1895408630371094, "Pretrain/Loss (Raw)": 2.1016018390655518, "Pretrain/Step": 323, "Pretrain/Step Time": 8.429396273568273} +{"Pretrain/Learning Rate": 4.999791796772291e-05, "Pretrain/Loss": 2.1899776458740234, "Pretrain/Loss (Raw)": 2.283092975616455, "Pretrain/Step": 324, "Pretrain/Step Time": 8.427024168893695} +{"Pretrain/Learning Rate": 4.999780694684934e-05, "Pretrain/Loss": 2.1876821517944336, "Pretrain/Loss (Raw)": 1.9339232444763184, "Pretrain/Step": 325, "Pretrain/Step Time": 8.429968066513538} +{"Pretrain/Learning Rate": 4.999769304248755e-05, "Pretrain/Loss": 2.1856300830841064, "Pretrain/Loss (Raw)": 2.0177788734436035, "Pretrain/Step": 326, "Pretrain/Step Time": 8.429684720933437} +{"Pretrain/Learning Rate": 4.9997576254650635e-05, "Pretrain/Loss": 2.185572624206543, "Pretrain/Loss (Raw)": 2.0787198543548584, "Pretrain/Step": 327, "Pretrain/Step Time": 8.425637444481254} +{"Pretrain/Learning Rate": 4.9997456583352096e-05, "Pretrain/Loss": 2.186178684234619, "Pretrain/Loss (Raw)": 2.1878950595855713, "Pretrain/Step": 328, "Pretrain/Step Time": 8.42790993861854} +{"Pretrain/Learning Rate": 4.999733402860572e-05, "Pretrain/Loss": 2.185117721557617, "Pretrain/Loss (Raw)": 2.2423787117004395, "Pretrain/Step": 329, "Pretrain/Step Time": 8.42522251792252} +{"Pretrain/Learning Rate": 4.999720859042565e-05, "Pretrain/Loss": 2.1871867179870605, "Pretrain/Loss (Raw)": 2.2582714557647705, "Pretrain/Step": 330, "Pretrain/Step Time": 8.42451643012464} +{"Pretrain/Learning Rate": 4.9997080268826344e-05, "Pretrain/Loss": 2.186659097671509, "Pretrain/Loss (Raw)": 2.2161190509796143, "Pretrain/Step": 331, "Pretrain/Step Time": 8.427459234371781} +{"Pretrain/Learning Rate": 4.999694906382262e-05, "Pretrain/Loss": 2.1858103275299072, "Pretrain/Loss (Raw)": 2.1675162315368652, "Pretrain/Step": 332, "Pretrain/Step Time": 8.429080190137029} +{"Pretrain/Learning Rate": 4.9996814975429604e-05, "Pretrain/Loss": 2.1845622062683105, "Pretrain/Loss (Raw)": 2.1528244018554688, "Pretrain/Step": 333, "Pretrain/Step Time": 8.42963502369821} +{"Pretrain/Learning Rate": 4.9996678003662776e-05, "Pretrain/Loss": 2.1853151321411133, "Pretrain/Loss (Raw)": 2.15565824508667, "Pretrain/Step": 334, "Pretrain/Step Time": 8.432002041488886} +{"Pretrain/Learning Rate": 4.999653814853791e-05, "Pretrain/Loss": 2.1871438026428223, "Pretrain/Loss (Raw)": 2.366837501525879, "Pretrain/Step": 335, "Pretrain/Step Time": 8.430251184850931} +{"Pretrain/Learning Rate": 4.999639541007116e-05, "Pretrain/Loss": 2.1881942749023438, "Pretrain/Loss (Raw)": 2.3226475715637207, "Pretrain/Step": 336, "Pretrain/Step Time": 8.432228917255998} +{"Pretrain/Learning Rate": 4.999624978827899e-05, "Pretrain/Loss": 2.1895060539245605, "Pretrain/Loss (Raw)": 2.2115838527679443, "Pretrain/Step": 337, "Pretrain/Step Time": 8.425083374604583} +{"Pretrain/Learning Rate": 4.999610128317818e-05, "Pretrain/Loss": 2.1872997283935547, "Pretrain/Loss (Raw)": 2.0333051681518555, "Pretrain/Step": 338, "Pretrain/Step Time": 8.42451485618949} +{"Pretrain/Learning Rate": 4.9995949894785874e-05, "Pretrain/Loss": 2.1899170875549316, "Pretrain/Loss (Raw)": 2.3006591796875, "Pretrain/Step": 339, "Pretrain/Step Time": 8.421872509643435} +{"Pretrain/Learning Rate": 4.9995795623119537e-05, "Pretrain/Loss": 2.1905603408813477, "Pretrain/Loss (Raw)": 2.2854127883911133, "Pretrain/Step": 340, "Pretrain/Step Time": 8.421444170176983} +{"Pretrain/Learning Rate": 4.999563846819696e-05, "Pretrain/Loss": 2.1915338039398193, "Pretrain/Loss (Raw)": 2.2739126682281494, "Pretrain/Step": 341, "Pretrain/Step Time": 8.423620898276567} +{"Pretrain/Learning Rate": 4.999547843003626e-05, "Pretrain/Loss": 2.1916451454162598, "Pretrain/Loss (Raw)": 2.3476176261901855, "Pretrain/Step": 342, "Pretrain/Step Time": 8.423408851027489} +{"Pretrain/Learning Rate": 4.9995315508655916e-05, "Pretrain/Loss": 2.1919398307800293, "Pretrain/Loss (Raw)": 2.1735074520111084, "Pretrain/Step": 343, "Pretrain/Step Time": 8.420726161450148} +{"Pretrain/Learning Rate": 4.99951497040747e-05, "Pretrain/Loss": 2.190001964569092, "Pretrain/Loss (Raw)": 1.9642293453216553, "Pretrain/Step": 344, "Pretrain/Step Time": 8.419636145234108} +{"Pretrain/Learning Rate": 4.999498101631177e-05, "Pretrain/Loss": 2.189633369445801, "Pretrain/Loss (Raw)": 2.240248680114746, "Pretrain/Step": 345, "Pretrain/Step Time": 8.420324375852942} +{"Pretrain/Learning Rate": 4.999480944538655e-05, "Pretrain/Loss": 2.189255952835083, "Pretrain/Loss (Raw)": 2.168379783630371, "Pretrain/Step": 346, "Pretrain/Step Time": 8.42076788470149} +{"Pretrain/Learning Rate": 4.999463499131885e-05, "Pretrain/Loss": 2.189406156539917, "Pretrain/Loss (Raw)": 2.1704771518707275, "Pretrain/Step": 347, "Pretrain/Step Time": 8.41907255910337} +{"Pretrain/Learning Rate": 4.9994457654128776e-05, "Pretrain/Loss": 2.189216136932373, "Pretrain/Loss (Raw)": 2.1869843006134033, "Pretrain/Step": 348, "Pretrain/Step Time": 8.421310069039464} +{"Pretrain/Learning Rate": 4.99942774338368e-05, "Pretrain/Loss": 2.1881418228149414, "Pretrain/Loss (Raw)": 2.095364570617676, "Pretrain/Step": 349, "Pretrain/Step Time": 8.424295518547297} +{"Pretrain/Learning Rate": 4.999409433046372e-05, "Pretrain/Loss": 2.187927722930908, "Pretrain/Loss (Raw)": 2.19564151763916, "Pretrain/Step": 350, "Pretrain/Step Time": 8.422983134165406} +{"Pretrain/Learning Rate": 4.999390834403063e-05, "Pretrain/Loss": 2.1877007484436035, "Pretrain/Loss (Raw)": 2.0806288719177246, "Pretrain/Step": 351, "Pretrain/Step Time": 8.423842350021005} +{"Pretrain/Learning Rate": 4.999371947455899e-05, "Pretrain/Loss": 2.188274383544922, "Pretrain/Loss (Raw)": 2.1889262199401855, "Pretrain/Step": 352, "Pretrain/Step Time": 8.422712536528707} +{"Pretrain/Learning Rate": 4.99935277220706e-05, "Pretrain/Loss": 2.1866726875305176, "Pretrain/Loss (Raw)": 2.0585038661956787, "Pretrain/Step": 353, "Pretrain/Step Time": 8.424543906003237} +{"Pretrain/Learning Rate": 4.999333308658757e-05, "Pretrain/Loss": 2.1857900619506836, "Pretrain/Loss (Raw)": 2.2514326572418213, "Pretrain/Step": 354, "Pretrain/Step Time": 8.418067207559943} +{"Pretrain/Learning Rate": 4.999313556813236e-05, "Pretrain/Loss": 2.1868550777435303, "Pretrain/Loss (Raw)": 2.220095157623291, "Pretrain/Step": 355, "Pretrain/Step Time": 8.416111059486866} +{"Pretrain/Learning Rate": 4.9992935166727725e-05, "Pretrain/Loss": 2.1875736713409424, "Pretrain/Loss (Raw)": 2.3824915885925293, "Pretrain/Step": 356, "Pretrain/Step Time": 8.415986336767673} +{"Pretrain/Learning Rate": 4.9992731882396815e-05, "Pretrain/Loss": 2.187417507171631, "Pretrain/Loss (Raw)": 2.1435482501983643, "Pretrain/Step": 357, "Pretrain/Step Time": 8.4179568849504} +{"Pretrain/Learning Rate": 4.9992525715163065e-05, "Pretrain/Loss": 2.188905715942383, "Pretrain/Loss (Raw)": 2.2481441497802734, "Pretrain/Step": 358, "Pretrain/Step Time": 8.41731726936996} +{"Pretrain/Learning Rate": 4.999231666505025e-05, "Pretrain/Loss": 2.1873397827148438, "Pretrain/Loss (Raw)": 2.066281795501709, "Pretrain/Step": 359, "Pretrain/Step Time": 8.41566239669919} +{"Pretrain/Learning Rate": 4.99921047320825e-05, "Pretrain/Loss": 2.1897449493408203, "Pretrain/Loss (Raw)": 2.307159185409546, "Pretrain/Step": 360, "Pretrain/Step Time": 8.418686022982001} +{"Pretrain/Learning Rate": 4.999188991628425e-05, "Pretrain/Loss": 2.188760757446289, "Pretrain/Loss (Raw)": 2.0728037357330322, "Pretrain/Step": 361, "Pretrain/Step Time": 8.420833304524422} +{"Pretrain/Learning Rate": 4.999167221768028e-05, "Pretrain/Loss": 2.1879825592041016, "Pretrain/Loss (Raw)": 2.1307320594787598, "Pretrain/Step": 362, "Pretrain/Step Time": 8.42065312154591} +{"Pretrain/Learning Rate": 4.99914516362957e-05, "Pretrain/Loss": 2.186619281768799, "Pretrain/Loss (Raw)": 1.9584211111068726, "Pretrain/Step": 363, "Pretrain/Step Time": 8.42024208791554} +{"Pretrain/Learning Rate": 4.999122817215596e-05, "Pretrain/Loss": 2.186845302581787, "Pretrain/Loss (Raw)": 2.197788953781128, "Pretrain/Step": 364, "Pretrain/Step Time": 8.422143395990133} +{"Pretrain/Learning Rate": 4.999100182528683e-05, "Pretrain/Loss": 2.1843087673187256, "Pretrain/Loss (Raw)": 2.0158681869506836, "Pretrain/Step": 365, "Pretrain/Step Time": 8.421258790418506} +{"Pretrain/Learning Rate": 4.999077259571442e-05, "Pretrain/Loss": 2.183041572570801, "Pretrain/Loss (Raw)": 2.0007123947143555, "Pretrain/Step": 366, "Pretrain/Step Time": 8.4218721203506} +{"Pretrain/Learning Rate": 4.9990540483465174e-05, "Pretrain/Loss": 2.1836471557617188, "Pretrain/Loss (Raw)": 2.243813991546631, "Pretrain/Step": 367, "Pretrain/Step Time": 8.420473832637072} +{"Pretrain/Learning Rate": 4.999030548856587e-05, "Pretrain/Loss": 2.1818671226501465, "Pretrain/Loss (Raw)": 2.064910888671875, "Pretrain/Step": 368, "Pretrain/Step Time": 8.421226499602199} +{"Pretrain/Learning Rate": 4.999006761104361e-05, "Pretrain/Loss": 2.18247127532959, "Pretrain/Loss (Raw)": 2.338940143585205, "Pretrain/Step": 369, "Pretrain/Step Time": 8.422076720744371} +{"Pretrain/Learning Rate": 4.998982685092583e-05, "Pretrain/Loss": 2.1819772720336914, "Pretrain/Loss (Raw)": 2.088616132736206, "Pretrain/Step": 370, "Pretrain/Step Time": 8.422444205731153} +{"Pretrain/Learning Rate": 4.998958320824031e-05, "Pretrain/Loss": 2.181375026702881, "Pretrain/Loss (Raw)": 2.162649631500244, "Pretrain/Step": 371, "Pretrain/Step Time": 8.421229047700763} +{"Pretrain/Learning Rate": 4.9989336683015145e-05, "Pretrain/Loss": 2.18282413482666, "Pretrain/Loss (Raw)": 2.207610845565796, "Pretrain/Step": 372, "Pretrain/Step Time": 8.422132894396782} +{"Pretrain/Learning Rate": 4.9989087275278766e-05, "Pretrain/Loss": 2.181915760040283, "Pretrain/Loss (Raw)": 2.1008286476135254, "Pretrain/Step": 373, "Pretrain/Step Time": 8.426799267530441} +{"Pretrain/Learning Rate": 4.9988834985059966e-05, "Pretrain/Loss": 2.182912826538086, "Pretrain/Loss (Raw)": 2.234718084335327, "Pretrain/Step": 374, "Pretrain/Step Time": 8.426751479506493} +{"Pretrain/Learning Rate": 4.998857981238782e-05, "Pretrain/Loss": 2.183852195739746, "Pretrain/Loss (Raw)": 2.2017548084259033, "Pretrain/Step": 375, "Pretrain/Step Time": 8.428153153508902} +{"Pretrain/Learning Rate": 4.9988321757291786e-05, "Pretrain/Loss": 2.184756278991699, "Pretrain/Loss (Raw)": 2.2855300903320312, "Pretrain/Step": 376, "Pretrain/Step Time": 8.428312158212066} +{"Pretrain/Learning Rate": 4.998806081980162e-05, "Pretrain/Loss": 2.1850435733795166, "Pretrain/Loss (Raw)": 2.2312848567962646, "Pretrain/Step": 377, "Pretrain/Step Time": 8.42795967683196} +{"Pretrain/Learning Rate": 4.998779699994741e-05, "Pretrain/Loss": 2.185640335083008, "Pretrain/Loss (Raw)": 2.2621099948883057, "Pretrain/Step": 378, "Pretrain/Step Time": 8.428884094581008} +{"Pretrain/Learning Rate": 4.99875302977596e-05, "Pretrain/Loss": 2.185244560241699, "Pretrain/Loss (Raw)": 2.1379435062408447, "Pretrain/Step": 379, "Pretrain/Step Time": 8.430987963452935} +{"Pretrain/Learning Rate": 4.9987260713268954e-05, "Pretrain/Loss": 2.183713912963867, "Pretrain/Loss (Raw)": 2.1390323638916016, "Pretrain/Step": 380, "Pretrain/Step Time": 8.42838211543858} +{"Pretrain/Learning Rate": 4.998698824650656e-05, "Pretrain/Loss": 2.1835474967956543, "Pretrain/Loss (Raw)": 2.0319700241088867, "Pretrain/Step": 381, "Pretrain/Step Time": 8.430693348869681} +{"Pretrain/Learning Rate": 4.998671289750386e-05, "Pretrain/Loss": 2.184008836746216, "Pretrain/Loss (Raw)": 2.195709705352783, "Pretrain/Step": 382, "Pretrain/Step Time": 8.427404873073101} +{"Pretrain/Learning Rate": 4.998643466629261e-05, "Pretrain/Loss": 2.1846487522125244, "Pretrain/Loss (Raw)": 2.3069584369659424, "Pretrain/Step": 383, "Pretrain/Step Time": 8.43007612042129} +{"Pretrain/Learning Rate": 4.9986153552904894e-05, "Pretrain/Loss": 2.185905933380127, "Pretrain/Loss (Raw)": 2.211472749710083, "Pretrain/Step": 384, "Pretrain/Step Time": 8.433524215593934} +{"Pretrain/Learning Rate": 4.998586955737315e-05, "Pretrain/Loss": 2.1836328506469727, "Pretrain/Loss (Raw)": 1.9807844161987305, "Pretrain/Step": 385, "Pretrain/Step Time": 8.434964774176478} +{"Pretrain/Learning Rate": 4.998558267973014e-05, "Pretrain/Loss": 2.1848206520080566, "Pretrain/Loss (Raw)": 2.3235363960266113, "Pretrain/Step": 386, "Pretrain/Step Time": 8.433172037824988} +{"Pretrain/Learning Rate": 4.998529292000894e-05, "Pretrain/Loss": 2.185889720916748, "Pretrain/Loss (Raw)": 2.431009292602539, "Pretrain/Step": 387, "Pretrain/Step Time": 8.429444786161184} +{"Pretrain/Learning Rate": 4.9985000278242974e-05, "Pretrain/Loss": 2.1865956783294678, "Pretrain/Loss (Raw)": 1.983660101890564, "Pretrain/Step": 388, "Pretrain/Step Time": 8.429786344990134} +{"Pretrain/Learning Rate": 4.998470475446602e-05, "Pretrain/Loss": 2.1844520568847656, "Pretrain/Loss (Raw)": 1.895447850227356, "Pretrain/Step": 389, "Pretrain/Step Time": 8.434030152857304} +{"Pretrain/Learning Rate": 4.998440634871215e-05, "Pretrain/Loss": 2.184034824371338, "Pretrain/Loss (Raw)": 2.1675221920013428, "Pretrain/Step": 390, "Pretrain/Step Time": 8.43564490787685} +{"Pretrain/Learning Rate": 4.998410506101578e-05, "Pretrain/Loss": 2.1841554641723633, "Pretrain/Loss (Raw)": 2.124690294265747, "Pretrain/Step": 391, "Pretrain/Step Time": 8.435361318290234} +{"Pretrain/Learning Rate": 4.998380089141169e-05, "Pretrain/Loss": 2.184347629547119, "Pretrain/Loss (Raw)": 2.0671277046203613, "Pretrain/Step": 392, "Pretrain/Step Time": 8.437104776501656} +{"Pretrain/Learning Rate": 4.998349383993493e-05, "Pretrain/Loss": 2.184203863143921, "Pretrain/Loss (Raw)": 2.166977882385254, "Pretrain/Step": 393, "Pretrain/Step Time": 8.439176937565207} +{"Pretrain/Learning Rate": 4.998318390662094e-05, "Pretrain/Loss": 2.1833479404449463, "Pretrain/Loss (Raw)": 2.2140018939971924, "Pretrain/Step": 394, "Pretrain/Step Time": 8.43716897815466} +{"Pretrain/Learning Rate": 4.998287109150547e-05, "Pretrain/Loss": 2.1822729110717773, "Pretrain/Loss (Raw)": 2.1568384170532227, "Pretrain/Step": 395, "Pretrain/Step Time": 8.43760596960783} +{"Pretrain/Learning Rate": 4.9982555394624595e-05, "Pretrain/Loss": 2.182115077972412, "Pretrain/Loss (Raw)": 2.2331931591033936, "Pretrain/Step": 396, "Pretrain/Step Time": 8.43997229076922} +{"Pretrain/Learning Rate": 4.998223681601473e-05, "Pretrain/Loss": 2.180410146713257, "Pretrain/Loss (Raw)": 1.9930408000946045, "Pretrain/Step": 397, "Pretrain/Step Time": 8.44307085312903} +{"Pretrain/Learning Rate": 4.9981915355712636e-05, "Pretrain/Loss": 2.178842306137085, "Pretrain/Loss (Raw)": 2.0843453407287598, "Pretrain/Step": 398, "Pretrain/Step Time": 8.440454289317131} +{"Pretrain/Learning Rate": 4.998159101375538e-05, "Pretrain/Loss": 2.178049087524414, "Pretrain/Loss (Raw)": 2.147866725921631, "Pretrain/Step": 399, "Pretrain/Step Time": 8.442335428670049} +{"Pretrain/Learning Rate": 4.998126379018039e-05, "Pretrain/Loss": 2.17779803276062, "Pretrain/Loss (Raw)": 2.1058554649353027, "Pretrain/Step": 400, "Pretrain/Step Time": 8.441272042691708} +{"Pretrain/Learning Rate": 4.9980933685025385e-05, "Pretrain/Loss": 2.1779189109802246, "Pretrain/Loss (Raw)": 2.2215263843536377, "Pretrain/Step": 401, "Pretrain/Step Time": 8.440925801172853} +{"Pretrain/Learning Rate": 4.998060069832847e-05, "Pretrain/Loss": 2.1766958236694336, "Pretrain/Loss (Raw)": 2.1724371910095215, "Pretrain/Step": 402, "Pretrain/Step Time": 8.439956732094288} +{"Pretrain/Learning Rate": 4.9980264830128035e-05, "Pretrain/Loss": 2.1754631996154785, "Pretrain/Loss (Raw)": 2.184563636779785, "Pretrain/Step": 403, "Pretrain/Step Time": 8.43776805140078} +{"Pretrain/Learning Rate": 4.9979926080462834e-05, "Pretrain/Loss": 2.176162004470825, "Pretrain/Loss (Raw)": 2.2323102951049805, "Pretrain/Step": 404, "Pretrain/Step Time": 8.435941714793444} +{"Pretrain/Learning Rate": 4.997958444937194e-05, "Pretrain/Loss": 2.175877094268799, "Pretrain/Loss (Raw)": 2.148216962814331, "Pretrain/Step": 405, "Pretrain/Step Time": 8.43735484778881} +{"Pretrain/Learning Rate": 4.9979239936894765e-05, "Pretrain/Loss": 2.1758811473846436, "Pretrain/Loss (Raw)": 2.1679699420928955, "Pretrain/Step": 406, "Pretrain/Step Time": 8.437392108142376} +{"Pretrain/Learning Rate": 4.997889254307103e-05, "Pretrain/Loss": 2.176236152648926, "Pretrain/Loss (Raw)": 2.1631689071655273, "Pretrain/Step": 407, "Pretrain/Step Time": 8.440134331583977} +{"Pretrain/Learning Rate": 4.997854226794082e-05, "Pretrain/Loss": 2.1753361225128174, "Pretrain/Loss (Raw)": 2.0869686603546143, "Pretrain/Step": 408, "Pretrain/Step Time": 8.439810201525688} +{"Pretrain/Learning Rate": 4.997818911154454e-05, "Pretrain/Loss": 2.1748390197753906, "Pretrain/Loss (Raw)": 2.3169496059417725, "Pretrain/Step": 409, "Pretrain/Step Time": 8.441215984523296} +{"Pretrain/Learning Rate": 4.997783307392292e-05, "Pretrain/Loss": 2.1756045818328857, "Pretrain/Loss (Raw)": 2.258232831954956, "Pretrain/Step": 410, "Pretrain/Step Time": 8.443166075274348} +{"Pretrain/Learning Rate": 4.9977474155117045e-05, "Pretrain/Loss": 2.175365924835205, "Pretrain/Loss (Raw)": 2.1640658378601074, "Pretrain/Step": 411, "Pretrain/Step Time": 8.439472382888198} +{"Pretrain/Learning Rate": 4.9977112355168286e-05, "Pretrain/Loss": 2.1738216876983643, "Pretrain/Loss (Raw)": 2.136902332305908, "Pretrain/Step": 412, "Pretrain/Step Time": 8.445424797013402} +{"Pretrain/Learning Rate": 4.997674767411841e-05, "Pretrain/Loss": 2.1755409240722656, "Pretrain/Loss (Raw)": 2.3004422187805176, "Pretrain/Step": 413, "Pretrain/Step Time": 8.444855658337474} +{"Pretrain/Learning Rate": 4.997638011200946e-05, "Pretrain/Loss": 2.1737143993377686, "Pretrain/Loss (Raw)": 2.1631174087524414, "Pretrain/Step": 414, "Pretrain/Step Time": 8.449289912357926} +{"Pretrain/Learning Rate": 4.997600966888384e-05, "Pretrain/Loss": 2.172351360321045, "Pretrain/Loss (Raw)": 1.948487639427185, "Pretrain/Step": 415, "Pretrain/Step Time": 8.449698571115732} +{"Pretrain/Learning Rate": 4.997563634478428e-05, "Pretrain/Loss": 2.173661708831787, "Pretrain/Loss (Raw)": 2.1736130714416504, "Pretrain/Step": 416, "Pretrain/Step Time": 8.449873412027955} +{"Pretrain/Learning Rate": 4.9975260139753856e-05, "Pretrain/Loss": 2.1744649410247803, "Pretrain/Loss (Raw)": 2.2645602226257324, "Pretrain/Step": 417, "Pretrain/Step Time": 8.44829765893519} +{"Pretrain/Learning Rate": 4.997488105383594e-05, "Pretrain/Loss": 2.1733570098876953, "Pretrain/Loss (Raw)": 2.058027982711792, "Pretrain/Step": 418, "Pretrain/Step Time": 8.447140891104937} +{"Pretrain/Learning Rate": 4.997449908707428e-05, "Pretrain/Loss": 2.1722288131713867, "Pretrain/Loss (Raw)": 2.1077189445495605, "Pretrain/Step": 419, "Pretrain/Step Time": 8.445939809083939} +{"Pretrain/Learning Rate": 4.997411423951292e-05, "Pretrain/Loss": 2.1707682609558105, "Pretrain/Loss (Raw)": 2.038222551345825, "Pretrain/Step": 420, "Pretrain/Step Time": 8.449905768036842} +{"Pretrain/Learning Rate": 4.997372651119626e-05, "Pretrain/Loss": 2.1674647331237793, "Pretrain/Loss (Raw)": 1.9247311353683472, "Pretrain/Step": 421, "Pretrain/Step Time": 8.448092544451356} +{"Pretrain/Learning Rate": 4.9973335902169026e-05, "Pretrain/Loss": 2.1674818992614746, "Pretrain/Loss (Raw)": 2.2125890254974365, "Pretrain/Step": 422, "Pretrain/Step Time": 8.448187632486224} +{"Pretrain/Learning Rate": 4.997294241247628e-05, "Pretrain/Loss": 2.167325735092163, "Pretrain/Loss (Raw)": 2.1298587322235107, "Pretrain/Step": 423, "Pretrain/Step Time": 8.446647362783551} +{"Pretrain/Learning Rate": 4.9972546042163385e-05, "Pretrain/Loss": 2.168700695037842, "Pretrain/Loss (Raw)": 2.1977932453155518, "Pretrain/Step": 424, "Pretrain/Step Time": 8.449056128039956} +{"Pretrain/Learning Rate": 4.997214679127608e-05, "Pretrain/Loss": 2.1701526641845703, "Pretrain/Loss (Raw)": 2.381296396255493, "Pretrain/Step": 425, "Pretrain/Step Time": 8.447105184197426} +{"Pretrain/Learning Rate": 4.997174465986044e-05, "Pretrain/Loss": 2.170642852783203, "Pretrain/Loss (Raw)": 2.269622325897217, "Pretrain/Step": 426, "Pretrain/Step Time": 8.447760371491313} +{"Pretrain/Learning Rate": 4.997133964796281e-05, "Pretrain/Loss": 2.1710848808288574, "Pretrain/Loss (Raw)": 2.283505439758301, "Pretrain/Step": 427, "Pretrain/Step Time": 8.444474404677749} +{"Pretrain/Learning Rate": 4.997093175562994e-05, "Pretrain/Loss": 2.171508312225342, "Pretrain/Loss (Raw)": 2.128664016723633, "Pretrain/Step": 428, "Pretrain/Step Time": 8.444585770368576} +{"Pretrain/Learning Rate": 4.997052098290886e-05, "Pretrain/Loss": 2.1696794033050537, "Pretrain/Loss (Raw)": 2.058790445327759, "Pretrain/Step": 429, "Pretrain/Step Time": 8.446326296776533} +{"Pretrain/Learning Rate": 4.997010732984696e-05, "Pretrain/Loss": 2.1712329387664795, "Pretrain/Loss (Raw)": 2.386913537979126, "Pretrain/Step": 430, "Pretrain/Step Time": 8.449597179889679} +{"Pretrain/Learning Rate": 4.996969079649195e-05, "Pretrain/Loss": 2.1709046363830566, "Pretrain/Loss (Raw)": 2.181605100631714, "Pretrain/Step": 431, "Pretrain/Step Time": 8.450820108875632} +{"Pretrain/Learning Rate": 4.996927138289189e-05, "Pretrain/Loss": 2.170515537261963, "Pretrain/Loss (Raw)": 2.117858409881592, "Pretrain/Step": 432, "Pretrain/Step Time": 8.448879754170775} +{"Pretrain/Learning Rate": 4.996884908909515e-05, "Pretrain/Loss": 2.1692914962768555, "Pretrain/Loss (Raw)": 2.144871711730957, "Pretrain/Step": 433, "Pretrain/Step Time": 8.445115473121405} +{"Pretrain/Learning Rate": 4.996842391515044e-05, "Pretrain/Loss": 2.168144941329956, "Pretrain/Loss (Raw)": 2.024932861328125, "Pretrain/Step": 434, "Pretrain/Step Time": 8.447667740285397} +{"Pretrain/Learning Rate": 4.9967995861106806e-05, "Pretrain/Loss": 2.1687259674072266, "Pretrain/Loss (Raw)": 2.2002594470977783, "Pretrain/Step": 435, "Pretrain/Step Time": 8.448243170976639} +{"Pretrain/Learning Rate": 4.996756492701362e-05, "Pretrain/Loss": 2.17043399810791, "Pretrain/Loss (Raw)": 2.2665536403656006, "Pretrain/Step": 436, "Pretrain/Step Time": 8.449908267706633} +{"Pretrain/Learning Rate": 4.99671311129206e-05, "Pretrain/Loss": 2.170217275619507, "Pretrain/Loss (Raw)": 2.1194772720336914, "Pretrain/Step": 437, "Pretrain/Step Time": 8.445606160908937} +{"Pretrain/Learning Rate": 4.9966694418877776e-05, "Pretrain/Loss": 2.169241189956665, "Pretrain/Loss (Raw)": 2.1797025203704834, "Pretrain/Step": 438, "Pretrain/Step Time": 8.44790905714035} +{"Pretrain/Learning Rate": 4.9966254844935535e-05, "Pretrain/Loss": 2.167051315307617, "Pretrain/Loss (Raw)": 1.8324064016342163, "Pretrain/Step": 439, "Pretrain/Step Time": 8.447209475561976} +{"Pretrain/Learning Rate": 4.996581239114456e-05, "Pretrain/Loss": 2.1662826538085938, "Pretrain/Loss (Raw)": 2.181983470916748, "Pretrain/Step": 440, "Pretrain/Step Time": 8.447526887059212} +{"Pretrain/Learning Rate": 4.99653670575559e-05, "Pretrain/Loss": 2.1670475006103516, "Pretrain/Loss (Raw)": 2.078899383544922, "Pretrain/Step": 441, "Pretrain/Step Time": 8.447151683270931} +{"Pretrain/Learning Rate": 4.996491884422093e-05, "Pretrain/Loss": 2.1681151390075684, "Pretrain/Loss (Raw)": 2.234393835067749, "Pretrain/Step": 442, "Pretrain/Step Time": 8.44886277243495} +{"Pretrain/Learning Rate": 4.9964467751191334e-05, "Pretrain/Loss": 2.167417526245117, "Pretrain/Loss (Raw)": 2.1998586654663086, "Pretrain/Step": 443, "Pretrain/Step Time": 8.449872963130474} +{"Pretrain/Learning Rate": 4.996401377851916e-05, "Pretrain/Loss": 2.1661171913146973, "Pretrain/Loss (Raw)": 1.922026515007019, "Pretrain/Step": 444, "Pretrain/Step Time": 8.451274106279016} +{"Pretrain/Learning Rate": 4.9963556926256776e-05, "Pretrain/Loss": 2.1655752658843994, "Pretrain/Loss (Raw)": 2.1465208530426025, "Pretrain/Step": 445, "Pretrain/Step Time": 8.451841812580824} +{"Pretrain/Learning Rate": 4.996309719445687e-05, "Pretrain/Loss": 2.1636886596679688, "Pretrain/Loss (Raw)": 1.8838077783584595, "Pretrain/Step": 446, "Pretrain/Step Time": 8.454822424799204} +{"Pretrain/Learning Rate": 4.9962634583172475e-05, "Pretrain/Loss": 2.1640264987945557, "Pretrain/Loss (Raw)": 2.1811976432800293, "Pretrain/Step": 447, "Pretrain/Step Time": 8.451992113143206} +{"Pretrain/Learning Rate": 4.9962169092456956e-05, "Pretrain/Loss": 2.1620054244995117, "Pretrain/Loss (Raw)": 2.2658920288085938, "Pretrain/Step": 448, "Pretrain/Step Time": 8.448386944830418} +{"Pretrain/Learning Rate": 4.9961700722364e-05, "Pretrain/Loss": 2.1596319675445557, "Pretrain/Loss (Raw)": 1.98145592212677, "Pretrain/Step": 449, "Pretrain/Step Time": 8.447536552324891} +{"Pretrain/Learning Rate": 4.9961229472947634e-05, "Pretrain/Loss": 2.1602025032043457, "Pretrain/Loss (Raw)": 2.1030707359313965, "Pretrain/Step": 450, "Pretrain/Step Time": 8.447948884218931} +{"Pretrain/Learning Rate": 4.9960755344262225e-05, "Pretrain/Loss": 2.161461353302002, "Pretrain/Loss (Raw)": 2.2627463340759277, "Pretrain/Step": 451, "Pretrain/Step Time": 8.445038121193647} +{"Pretrain/Learning Rate": 4.9960278336362465e-05, "Pretrain/Loss": 2.160830020904541, "Pretrain/Loss (Raw)": 2.2022669315338135, "Pretrain/Step": 452, "Pretrain/Step Time": 8.448593685403466} +{"Pretrain/Learning Rate": 4.9959798449303365e-05, "Pretrain/Loss": 2.1616811752319336, "Pretrain/Loss (Raw)": 2.0428621768951416, "Pretrain/Step": 453, "Pretrain/Step Time": 8.446106180548668} +{"Pretrain/Learning Rate": 4.995931568314029e-05, "Pretrain/Loss": 2.1623878479003906, "Pretrain/Loss (Raw)": 2.1082301139831543, "Pretrain/Step": 454, "Pretrain/Step Time": 8.443858360871673} +{"Pretrain/Learning Rate": 4.995883003792891e-05, "Pretrain/Loss": 2.16214656829834, "Pretrain/Loss (Raw)": 2.047844409942627, "Pretrain/Step": 455, "Pretrain/Step Time": 8.446066105738282} +{"Pretrain/Learning Rate": 4.9958341513725264e-05, "Pretrain/Loss": 2.1610403060913086, "Pretrain/Loss (Raw)": 2.0463080406188965, "Pretrain/Step": 456, "Pretrain/Step Time": 8.443712763488293} +{"Pretrain/Learning Rate": 4.9957850110585696e-05, "Pretrain/Loss": 2.1608760356903076, "Pretrain/Loss (Raw)": 2.221337080001831, "Pretrain/Step": 457, "Pretrain/Step Time": 8.452606678009033} +{"Pretrain/Learning Rate": 4.9957355828566884e-05, "Pretrain/Loss": 2.1602206230163574, "Pretrain/Loss (Raw)": 2.174393653869629, "Pretrain/Step": 458, "Pretrain/Step Time": 8.454227985814214} +{"Pretrain/Learning Rate": 4.995685866772586e-05, "Pretrain/Loss": 2.159789800643921, "Pretrain/Loss (Raw)": 2.160975933074951, "Pretrain/Step": 459, "Pretrain/Step Time": 8.452759927138686} +{"Pretrain/Learning Rate": 4.9956358628119945e-05, "Pretrain/Loss": 2.159623146057129, "Pretrain/Loss (Raw)": 2.14617919921875, "Pretrain/Step": 460, "Pretrain/Step Time": 8.44937065243721} +{"Pretrain/Learning Rate": 4.9955855709806845e-05, "Pretrain/Loss": 2.160024642944336, "Pretrain/Loss (Raw)": 2.2041831016540527, "Pretrain/Step": 461, "Pretrain/Step Time": 8.448602966964245} +{"Pretrain/Learning Rate": 4.9955349912844554e-05, "Pretrain/Loss": 2.160933017730713, "Pretrain/Loss (Raw)": 2.2719693183898926, "Pretrain/Step": 462, "Pretrain/Step Time": 8.446769846603274} +{"Pretrain/Learning Rate": 4.995484123729141e-05, "Pretrain/Loss": 2.1591074466705322, "Pretrain/Loss (Raw)": 2.1331663131713867, "Pretrain/Step": 463, "Pretrain/Step Time": 8.447435474023223} +{"Pretrain/Learning Rate": 4.995432968320611e-05, "Pretrain/Loss": 2.1578242778778076, "Pretrain/Loss (Raw)": 2.1583869457244873, "Pretrain/Step": 464, "Pretrain/Step Time": 8.445763546973467} +{"Pretrain/Learning Rate": 4.995381525064765e-05, "Pretrain/Loss": 2.158655881881714, "Pretrain/Loss (Raw)": 2.3180365562438965, "Pretrain/Step": 465, "Pretrain/Step Time": 8.446386413648725} +{"Pretrain/Learning Rate": 4.995329793967537e-05, "Pretrain/Loss": 2.1597251892089844, "Pretrain/Loss (Raw)": 2.170158624649048, "Pretrain/Step": 466, "Pretrain/Step Time": 8.449124673381448} +{"Pretrain/Learning Rate": 4.995277775034893e-05, "Pretrain/Loss": 2.158510446548462, "Pretrain/Loss (Raw)": 2.1452012062072754, "Pretrain/Step": 467, "Pretrain/Step Time": 8.44935717061162} +{"Pretrain/Learning Rate": 4.995225468272836e-05, "Pretrain/Loss": 2.1567139625549316, "Pretrain/Loss (Raw)": 2.055453062057495, "Pretrain/Step": 468, "Pretrain/Step Time": 8.449473727494478} +{"Pretrain/Learning Rate": 4.995172873687398e-05, "Pretrain/Loss": 2.1557400226593018, "Pretrain/Loss (Raw)": 2.1492502689361572, "Pretrain/Step": 469, "Pretrain/Step Time": 8.449762225151062} +{"Pretrain/Learning Rate": 4.995119991284646e-05, "Pretrain/Loss": 2.1540026664733887, "Pretrain/Loss (Raw)": 2.125241994857788, "Pretrain/Step": 470, "Pretrain/Step Time": 8.449726277962327} +{"Pretrain/Learning Rate": 4.995066821070679e-05, "Pretrain/Loss": 2.1549017429351807, "Pretrain/Loss (Raw)": 2.288567304611206, "Pretrain/Step": 471, "Pretrain/Step Time": 8.448383331298828} +{"Pretrain/Learning Rate": 4.9950133630516315e-05, "Pretrain/Loss": 2.1570401191711426, "Pretrain/Loss (Raw)": 2.2379636764526367, "Pretrain/Step": 472, "Pretrain/Step Time": 8.451114324852824} +{"Pretrain/Learning Rate": 4.9949596172336696e-05, "Pretrain/Loss": 2.1550204753875732, "Pretrain/Loss (Raw)": 1.9817146062850952, "Pretrain/Step": 473, "Pretrain/Step Time": 8.456237418577075} +{"Pretrain/Learning Rate": 4.994905583622992e-05, "Pretrain/Loss": 2.154658794403076, "Pretrain/Loss (Raw)": 2.122079849243164, "Pretrain/Step": 474, "Pretrain/Step Time": 8.458137478679419} +{"Pretrain/Learning Rate": 4.9948512622258325e-05, "Pretrain/Loss": 2.1553966999053955, "Pretrain/Loss (Raw)": 2.264946460723877, "Pretrain/Step": 475, "Pretrain/Step Time": 8.46091690286994} +{"Pretrain/Learning Rate": 4.994796653048457e-05, "Pretrain/Loss": 2.154548406600952, "Pretrain/Loss (Raw)": 2.078385829925537, "Pretrain/Step": 476, "Pretrain/Step Time": 8.45801316946745} +{"Pretrain/Learning Rate": 4.994741756097164e-05, "Pretrain/Loss": 2.1567161083221436, "Pretrain/Loss (Raw)": 2.372831106185913, "Pretrain/Step": 477, "Pretrain/Step Time": 8.45612963102758} +{"Pretrain/Learning Rate": 4.994686571378286e-05, "Pretrain/Loss": 2.1565780639648438, "Pretrain/Loss (Raw)": 2.1779983043670654, "Pretrain/Step": 478, "Pretrain/Step Time": 8.45629925839603} +{"Pretrain/Learning Rate": 4.994631098898189e-05, "Pretrain/Loss": 2.1576290130615234, "Pretrain/Loss (Raw)": 2.215146541595459, "Pretrain/Step": 479, "Pretrain/Step Time": 8.457990458235145} +{"Pretrain/Learning Rate": 4.994575338663271e-05, "Pretrain/Loss": 2.156871795654297, "Pretrain/Loss (Raw)": 2.092012882232666, "Pretrain/Step": 480, "Pretrain/Step Time": 8.458116633817554} +{"Pretrain/Learning Rate": 4.994519290679964e-05, "Pretrain/Loss": 2.158569097518921, "Pretrain/Loss (Raw)": 2.2757327556610107, "Pretrain/Step": 481, "Pretrain/Step Time": 8.45848904363811} +{"Pretrain/Learning Rate": 4.994462954954734e-05, "Pretrain/Loss": 2.1573100090026855, "Pretrain/Loss (Raw)": 2.0902915000915527, "Pretrain/Step": 482, "Pretrain/Step Time": 8.461706822738051} +{"Pretrain/Learning Rate": 4.994406331494079e-05, "Pretrain/Loss": 2.1566314697265625, "Pretrain/Loss (Raw)": 2.1332082748413086, "Pretrain/Step": 483, "Pretrain/Step Time": 8.461725268512964} +{"Pretrain/Learning Rate": 4.994349420304531e-05, "Pretrain/Loss": 2.154294967651367, "Pretrain/Loss (Raw)": 2.08341646194458, "Pretrain/Step": 484, "Pretrain/Step Time": 8.464443076401949} +{"Pretrain/Learning Rate": 4.9942922213926525e-05, "Pretrain/Loss": 2.1546483039855957, "Pretrain/Loss (Raw)": 2.188805103302002, "Pretrain/Step": 485, "Pretrain/Step Time": 8.464564673602581} +{"Pretrain/Learning Rate": 4.994234734765043e-05, "Pretrain/Loss": 2.153695583343506, "Pretrain/Loss (Raw)": 2.1261870861053467, "Pretrain/Step": 486, "Pretrain/Step Time": 8.464389361441135} +{"Pretrain/Learning Rate": 4.994176960428334e-05, "Pretrain/Loss": 2.1533453464508057, "Pretrain/Loss (Raw)": 2.0214309692382812, "Pretrain/Step": 487, "Pretrain/Step Time": 8.466879602521658} +{"Pretrain/Learning Rate": 4.9941188983891885e-05, "Pretrain/Loss": 2.1526589393615723, "Pretrain/Loss (Raw)": 2.2193071842193604, "Pretrain/Step": 488, "Pretrain/Step Time": 8.466109868139029} +{"Pretrain/Learning Rate": 4.9940605486543045e-05, "Pretrain/Loss": 2.152200222015381, "Pretrain/Loss (Raw)": 2.014066219329834, "Pretrain/Step": 489, "Pretrain/Step Time": 8.465668551623821} +{"Pretrain/Learning Rate": 4.994001911230414e-05, "Pretrain/Loss": 2.1527633666992188, "Pretrain/Loss (Raw)": 2.2028472423553467, "Pretrain/Step": 490, "Pretrain/Step Time": 8.469238456338644} +{"Pretrain/Learning Rate": 4.993942986124278e-05, "Pretrain/Loss": 2.1553397178649902, "Pretrain/Loss (Raw)": 2.2881672382354736, "Pretrain/Step": 491, "Pretrain/Step Time": 8.47099750302732} +{"Pretrain/Learning Rate": 4.9938837733426955e-05, "Pretrain/Loss": 2.153698444366455, "Pretrain/Loss (Raw)": 1.9877188205718994, "Pretrain/Step": 492, "Pretrain/Step Time": 8.472559103742242} +{"Pretrain/Learning Rate": 4.993824272892497e-05, "Pretrain/Loss": 2.1557726860046387, "Pretrain/Loss (Raw)": 2.2813799381256104, "Pretrain/Step": 493, "Pretrain/Step Time": 8.473993819206953} +{"Pretrain/Learning Rate": 4.993764484780543e-05, "Pretrain/Loss": 2.1568145751953125, "Pretrain/Loss (Raw)": 2.134103298187256, "Pretrain/Step": 494, "Pretrain/Step Time": 8.473936872556806} +{"Pretrain/Learning Rate": 4.993704409013734e-05, "Pretrain/Loss": 2.1567862033843994, "Pretrain/Loss (Raw)": 2.2401633262634277, "Pretrain/Step": 495, "Pretrain/Step Time": 8.474116845056415} +{"Pretrain/Learning Rate": 4.993644045598997e-05, "Pretrain/Loss": 2.157581329345703, "Pretrain/Loss (Raw)": 2.1666972637176514, "Pretrain/Step": 496, "Pretrain/Step Time": 8.475483497604728} +{"Pretrain/Learning Rate": 4.9935833945432955e-05, "Pretrain/Loss": 2.153989315032959, "Pretrain/Loss (Raw)": 1.879122257232666, "Pretrain/Step": 497, "Pretrain/Step Time": 8.4712795317173} +{"Pretrain/Learning Rate": 4.993522455853626e-05, "Pretrain/Loss": 2.15533447265625, "Pretrain/Loss (Raw)": 2.260833740234375, "Pretrain/Step": 498, "Pretrain/Step Time": 8.473975032567978} +{"Pretrain/Learning Rate": 4.9934612295370174e-05, "Pretrain/Loss": 2.154963970184326, "Pretrain/Loss (Raw)": 2.1151933670043945, "Pretrain/Step": 499, "Pretrain/Step Time": 8.478279192000628} +{"Pretrain/Learning Rate": 4.993399715600532e-05, "Pretrain/Loss": 2.155130386352539, "Pretrain/Loss (Raw)": 2.228947877883911, "Pretrain/Step": 500, "Pretrain/Step Time": 8.476338801905513} +{"Pretrain/Learning Rate": 4.993337914051266e-05, "Pretrain/Loss": 2.156355619430542, "Pretrain/Loss (Raw)": 2.2576379776000977, "Pretrain/Step": 501, "Pretrain/Step Time": 8.471105860546231} +{"Pretrain/Learning Rate": 4.993275824896348e-05, "Pretrain/Loss": 2.1551766395568848, "Pretrain/Loss (Raw)": 2.083806037902832, "Pretrain/Step": 502, "Pretrain/Step Time": 8.471030045300722} +{"Pretrain/Learning Rate": 4.993213448142939e-05, "Pretrain/Loss": 2.1555347442626953, "Pretrain/Loss (Raw)": 2.2475688457489014, "Pretrain/Step": 503, "Pretrain/Step Time": 8.471616514027119} +{"Pretrain/Learning Rate": 4.993150783798236e-05, "Pretrain/Loss": 2.1545605659484863, "Pretrain/Loss (Raw)": 2.160858392715454, "Pretrain/Step": 504, "Pretrain/Step Time": 8.473876487463713} +{"Pretrain/Learning Rate": 4.9930878318694655e-05, "Pretrain/Loss": 2.155762195587158, "Pretrain/Loss (Raw)": 2.385103702545166, "Pretrain/Step": 505, "Pretrain/Step Time": 8.474838748574257} +{"Pretrain/Learning Rate": 4.99302459236389e-05, "Pretrain/Loss": 2.1537609100341797, "Pretrain/Loss (Raw)": 2.005927801132202, "Pretrain/Step": 506, "Pretrain/Step Time": 8.474035767838359} +{"Pretrain/Learning Rate": 4.992961065288804e-05, "Pretrain/Loss": 2.1531929969787598, "Pretrain/Loss (Raw)": 2.06526255607605, "Pretrain/Step": 507, "Pretrain/Step Time": 8.473324470221996} +{"Pretrain/Learning Rate": 4.992897250651535e-05, "Pretrain/Loss": 2.1525540351867676, "Pretrain/Loss (Raw)": 2.057236433029175, "Pretrain/Step": 508, "Pretrain/Step Time": 8.474376190453768} +{"Pretrain/Learning Rate": 4.992833148459444e-05, "Pretrain/Loss": 2.153986930847168, "Pretrain/Loss (Raw)": 2.215386390686035, "Pretrain/Step": 509, "Pretrain/Step Time": 8.475756589323282} +{"Pretrain/Learning Rate": 4.992768758719926e-05, "Pretrain/Loss": 2.152893304824829, "Pretrain/Loss (Raw)": 2.0557310581207275, "Pretrain/Step": 510, "Pretrain/Step Time": 8.476144284009933} +{"Pretrain/Learning Rate": 4.992704081440407e-05, "Pretrain/Loss": 2.1512300968170166, "Pretrain/Loss (Raw)": 2.0940773487091064, "Pretrain/Step": 511, "Pretrain/Step Time": 8.474171848967671} +{"Pretrain/Learning Rate": 4.992639116628349e-05, "Pretrain/Loss": 2.150998592376709, "Pretrain/Loss (Raw)": 2.18180251121521, "Pretrain/Step": 512, "Pretrain/Step Time": 8.47409439086914} +{"Pretrain/Learning Rate": 4.9925738642912447e-05, "Pretrain/Loss": 2.1526408195495605, "Pretrain/Loss (Raw)": 2.190985918045044, "Pretrain/Step": 513, "Pretrain/Step Time": 8.472856845706701} +{"Pretrain/Learning Rate": 4.99250832443662e-05, "Pretrain/Loss": 2.1517632007598877, "Pretrain/Loss (Raw)": 2.2112293243408203, "Pretrain/Step": 514, "Pretrain/Step Time": 8.475740130990744} +{"Pretrain/Learning Rate": 4.9924424970720376e-05, "Pretrain/Loss": 2.149503707885742, "Pretrain/Loss (Raw)": 2.1417996883392334, "Pretrain/Step": 515, "Pretrain/Step Time": 8.478274317458272} +{"Pretrain/Learning Rate": 4.992376382205088e-05, "Pretrain/Loss": 2.1505887508392334, "Pretrain/Loss (Raw)": 2.1225297451019287, "Pretrain/Step": 516, "Pretrain/Step Time": 8.47802404128015} +{"Pretrain/Learning Rate": 4.9923099798433985e-05, "Pretrain/Loss": 2.1537599563598633, "Pretrain/Loss (Raw)": 2.301342248916626, "Pretrain/Step": 517, "Pretrain/Step Time": 8.474600734189153} +{"Pretrain/Learning Rate": 4.992243289994629e-05, "Pretrain/Loss": 2.1539106369018555, "Pretrain/Loss (Raw)": 2.186837673187256, "Pretrain/Step": 518, "Pretrain/Step Time": 8.471784686669707} +{"Pretrain/Learning Rate": 4.992176312666472e-05, "Pretrain/Loss": 2.1531572341918945, "Pretrain/Loss (Raw)": 2.0282649993896484, "Pretrain/Step": 519, "Pretrain/Step Time": 8.47337056696415} +{"Pretrain/Learning Rate": 4.992109047866653e-05, "Pretrain/Loss": 2.1533846855163574, "Pretrain/Loss (Raw)": 2.0962562561035156, "Pretrain/Step": 520, "Pretrain/Step Time": 8.473254732787609} +{"Pretrain/Learning Rate": 4.992041495602932e-05, "Pretrain/Loss": 2.1530826091766357, "Pretrain/Loss (Raw)": 2.1282923221588135, "Pretrain/Step": 521, "Pretrain/Step Time": 8.473708424717188} +{"Pretrain/Learning Rate": 4.9919736558830984e-05, "Pretrain/Loss": 2.1523139476776123, "Pretrain/Loss (Raw)": 2.1156232357025146, "Pretrain/Step": 522, "Pretrain/Step Time": 8.474495751783252} +{"Pretrain/Learning Rate": 4.9919055287149805e-05, "Pretrain/Loss": 2.152228355407715, "Pretrain/Loss (Raw)": 2.145864725112915, "Pretrain/Step": 523, "Pretrain/Step Time": 8.477113422006369} +{"Pretrain/Learning Rate": 4.991837114106436e-05, "Pretrain/Loss": 2.151851177215576, "Pretrain/Loss (Raw)": 2.1849114894866943, "Pretrain/Step": 524, "Pretrain/Step Time": 8.477781433612108} +{"Pretrain/Learning Rate": 4.991768412065355e-05, "Pretrain/Loss": 2.1530649662017822, "Pretrain/Loss (Raw)": 2.1483912467956543, "Pretrain/Step": 525, "Pretrain/Step Time": 8.475986484438181} +{"Pretrain/Learning Rate": 4.991699422599664e-05, "Pretrain/Loss": 2.153546094894409, "Pretrain/Loss (Raw)": 2.145954132080078, "Pretrain/Step": 526, "Pretrain/Step Time": 8.477193519473076} +{"Pretrain/Learning Rate": 4.99163014571732e-05, "Pretrain/Loss": 2.1529014110565186, "Pretrain/Loss (Raw)": 2.0653529167175293, "Pretrain/Step": 527, "Pretrain/Step Time": 8.475563440471888} +{"Pretrain/Learning Rate": 4.991560581426315e-05, "Pretrain/Loss": 2.1523070335388184, "Pretrain/Loss (Raw)": 2.029742956161499, "Pretrain/Step": 528, "Pretrain/Step Time": 8.479106474667788} +{"Pretrain/Learning Rate": 4.991490729734671e-05, "Pretrain/Loss": 2.1513023376464844, "Pretrain/Loss (Raw)": 2.0929245948791504, "Pretrain/Step": 529, "Pretrain/Step Time": 8.477319233119488} +{"Pretrain/Learning Rate": 4.991420590650448e-05, "Pretrain/Loss": 2.1511969566345215, "Pretrain/Loss (Raw)": 2.159003734588623, "Pretrain/Step": 530, "Pretrain/Step Time": 8.477080129086971} +{"Pretrain/Learning Rate": 4.9913501641817354e-05, "Pretrain/Loss": 2.1494193077087402, "Pretrain/Loss (Raw)": 1.9570074081420898, "Pretrain/Step": 531, "Pretrain/Step Time": 8.476475646719337} +{"Pretrain/Learning Rate": 4.9912794503366566e-05, "Pretrain/Loss": 2.148327112197876, "Pretrain/Loss (Raw)": 2.092487096786499, "Pretrain/Step": 532, "Pretrain/Step Time": 8.480603951960802} +{"Pretrain/Learning Rate": 4.991208449123369e-05, "Pretrain/Loss": 2.148845672607422, "Pretrain/Loss (Raw)": 2.214590072631836, "Pretrain/Step": 533, "Pretrain/Step Time": 8.481914959847927} +{"Pretrain/Learning Rate": 4.991137160550062e-05, "Pretrain/Loss": 2.1475882530212402, "Pretrain/Loss (Raw)": 2.0070459842681885, "Pretrain/Step": 534, "Pretrain/Step Time": 8.478928379714489} +{"Pretrain/Learning Rate": 4.991065584624959e-05, "Pretrain/Loss": 2.1467082500457764, "Pretrain/Loss (Raw)": 2.050496816635132, "Pretrain/Step": 535, "Pretrain/Step Time": 8.481155360117555} +{"Pretrain/Learning Rate": 4.9909937213563165e-05, "Pretrain/Loss": 2.147665023803711, "Pretrain/Loss (Raw)": 2.209442377090454, "Pretrain/Step": 536, "Pretrain/Step Time": 8.48400497250259} +{"Pretrain/Learning Rate": 4.9909215707524236e-05, "Pretrain/Loss": 2.1459147930145264, "Pretrain/Loss (Raw)": 2.092930555343628, "Pretrain/Step": 537, "Pretrain/Step Time": 8.483942469581962} +{"Pretrain/Learning Rate": 4.9908491328216025e-05, "Pretrain/Loss": 2.1450977325439453, "Pretrain/Loss (Raw)": 2.1536450386047363, "Pretrain/Step": 538, "Pretrain/Step Time": 8.483492432162166} +{"Pretrain/Learning Rate": 4.9907764075722094e-05, "Pretrain/Loss": 2.1454622745513916, "Pretrain/Loss (Raw)": 2.2107362747192383, "Pretrain/Step": 539, "Pretrain/Step Time": 8.484740123152733} +{"Pretrain/Learning Rate": 4.9907033950126336e-05, "Pretrain/Loss": 2.1442031860351562, "Pretrain/Loss (Raw)": 1.975728154182434, "Pretrain/Step": 540, "Pretrain/Step Time": 8.479738932102919} +{"Pretrain/Learning Rate": 4.990630095151296e-05, "Pretrain/Loss": 2.1448724269866943, "Pretrain/Loss (Raw)": 2.3861045837402344, "Pretrain/Step": 541, "Pretrain/Step Time": 8.481784930452704} +{"Pretrain/Learning Rate": 4.990556507996652e-05, "Pretrain/Loss": 2.1454384326934814, "Pretrain/Loss (Raw)": 2.2355704307556152, "Pretrain/Step": 542, "Pretrain/Step Time": 8.479456786066294} +{"Pretrain/Learning Rate": 4.99048263355719e-05, "Pretrain/Loss": 2.1474337577819824, "Pretrain/Loss (Raw)": 2.2038938999176025, "Pretrain/Step": 543, "Pretrain/Step Time": 8.479275308549404} +{"Pretrain/Learning Rate": 4.990408471841432e-05, "Pretrain/Loss": 2.147566318511963, "Pretrain/Loss (Raw)": 2.1905629634857178, "Pretrain/Step": 544, "Pretrain/Step Time": 8.480155386030674} +{"Pretrain/Learning Rate": 4.990334022857932e-05, "Pretrain/Loss": 2.1467082500457764, "Pretrain/Loss (Raw)": 2.1547434329986572, "Pretrain/Step": 545, "Pretrain/Step Time": 8.480418665334582} +{"Pretrain/Learning Rate": 4.990259286615276e-05, "Pretrain/Loss": 2.1475725173950195, "Pretrain/Loss (Raw)": 2.1686644554138184, "Pretrain/Step": 546, "Pretrain/Step Time": 8.480018129572272} +{"Pretrain/Learning Rate": 4.9901842631220884e-05, "Pretrain/Loss": 2.146937847137451, "Pretrain/Loss (Raw)": 2.0264575481414795, "Pretrain/Step": 547, "Pretrain/Step Time": 8.481640728190541} +{"Pretrain/Learning Rate": 4.9901089523870205e-05, "Pretrain/Loss": 2.1459431648254395, "Pretrain/Loss (Raw)": 1.9109032154083252, "Pretrain/Step": 548, "Pretrain/Step Time": 8.478948794305325} +{"Pretrain/Learning Rate": 4.99003335441876e-05, "Pretrain/Loss": 2.1476800441741943, "Pretrain/Loss (Raw)": 2.147077798843384, "Pretrain/Step": 549, "Pretrain/Step Time": 8.478120289742947} +{"Pretrain/Learning Rate": 4.989957469226027e-05, "Pretrain/Loss": 2.1473488807678223, "Pretrain/Loss (Raw)": 2.1701838970184326, "Pretrain/Step": 550, "Pretrain/Step Time": 8.480843102559447} +{"Pretrain/Learning Rate": 4.989881296817575e-05, "Pretrain/Loss": 2.1473753452301025, "Pretrain/Loss (Raw)": 2.1332409381866455, "Pretrain/Step": 551, "Pretrain/Step Time": 8.481524204835296} +{"Pretrain/Learning Rate": 4.9898048372021905e-05, "Pretrain/Loss": 2.147106647491455, "Pretrain/Loss (Raw)": 2.163426399230957, "Pretrain/Step": 552, "Pretrain/Step Time": 8.479740345850587} +{"Pretrain/Learning Rate": 4.9897280903886937e-05, "Pretrain/Loss": 2.1445345878601074, "Pretrain/Loss (Raw)": 2.0520591735839844, "Pretrain/Step": 553, "Pretrain/Step Time": 8.485321804881096} +{"Pretrain/Learning Rate": 4.989651056385936e-05, "Pretrain/Loss": 2.1428542137145996, "Pretrain/Loss (Raw)": 2.0545153617858887, "Pretrain/Step": 554, "Pretrain/Step Time": 8.48283639550209} +{"Pretrain/Learning Rate": 4.989573735202803e-05, "Pretrain/Loss": 2.1414501667022705, "Pretrain/Loss (Raw)": 2.1038084030151367, "Pretrain/Step": 555, "Pretrain/Step Time": 8.484237035736442} +{"Pretrain/Learning Rate": 4.989496126848215e-05, "Pretrain/Loss": 2.142373561859131, "Pretrain/Loss (Raw)": 2.2468435764312744, "Pretrain/Step": 556, "Pretrain/Step Time": 8.483362665399909} +{"Pretrain/Learning Rate": 4.9894182313311244e-05, "Pretrain/Loss": 2.1428256034851074, "Pretrain/Loss (Raw)": 2.11663556098938, "Pretrain/Step": 557, "Pretrain/Step Time": 8.483368752524257} +{"Pretrain/Learning Rate": 4.9893400486605154e-05, "Pretrain/Loss": 2.140955924987793, "Pretrain/Loss (Raw)": 2.147634267807007, "Pretrain/Step": 558, "Pretrain/Step Time": 8.482262531295419} +{"Pretrain/Learning Rate": 4.9892615788454065e-05, "Pretrain/Loss": 2.141263008117676, "Pretrain/Loss (Raw)": 2.220899820327759, "Pretrain/Step": 559, "Pretrain/Step Time": 8.48067762888968} +{"Pretrain/Learning Rate": 4.989182821894849e-05, "Pretrain/Loss": 2.141132116317749, "Pretrain/Loss (Raw)": 2.1010799407958984, "Pretrain/Step": 560, "Pretrain/Step Time": 8.481761856004596} +{"Pretrain/Learning Rate": 4.989103777817928e-05, "Pretrain/Loss": 2.140878677368164, "Pretrain/Loss (Raw)": 2.1124632358551025, "Pretrain/Step": 561, "Pretrain/Step Time": 8.482568945735693} +{"Pretrain/Learning Rate": 4.989024446623761e-05, "Pretrain/Loss": 2.1424288749694824, "Pretrain/Loss (Raw)": 2.2233598232269287, "Pretrain/Step": 562, "Pretrain/Step Time": 8.484173201024532} +{"Pretrain/Learning Rate": 4.988944828321498e-05, "Pretrain/Loss": 2.1431779861450195, "Pretrain/Loss (Raw)": 2.296140670776367, "Pretrain/Step": 563, "Pretrain/Step Time": 8.481005847454071} +{"Pretrain/Learning Rate": 4.988864922920325e-05, "Pretrain/Loss": 2.140486717224121, "Pretrain/Loss (Raw)": 1.9220763444900513, "Pretrain/Step": 564, "Pretrain/Step Time": 8.483052909374237} +{"Pretrain/Learning Rate": 4.988784730429457e-05, "Pretrain/Loss": 2.1410484313964844, "Pretrain/Loss (Raw)": 2.191377878189087, "Pretrain/Step": 565, "Pretrain/Step Time": 8.488001246005297} +{"Pretrain/Learning Rate": 4.988704250858145e-05, "Pretrain/Loss": 2.1418938636779785, "Pretrain/Loss (Raw)": 2.28790020942688, "Pretrain/Step": 566, "Pretrain/Step Time": 8.483509248122573} +{"Pretrain/Learning Rate": 4.9886234842156724e-05, "Pretrain/Loss": 2.1428494453430176, "Pretrain/Loss (Raw)": 1.9547274112701416, "Pretrain/Step": 567, "Pretrain/Step Time": 8.485159447416663} +{"Pretrain/Learning Rate": 4.988542430511356e-05, "Pretrain/Loss": 2.143228054046631, "Pretrain/Loss (Raw)": 2.2304282188415527, "Pretrain/Step": 568, "Pretrain/Step Time": 8.488709570840001} +{"Pretrain/Learning Rate": 4.988461089754544e-05, "Pretrain/Loss": 2.143136501312256, "Pretrain/Loss (Raw)": 2.0671589374542236, "Pretrain/Step": 569, "Pretrain/Step Time": 8.486092505976558} +{"Pretrain/Learning Rate": 4.98837946195462e-05, "Pretrain/Loss": 2.143728733062744, "Pretrain/Loss (Raw)": 2.3102521896362305, "Pretrain/Step": 570, "Pretrain/Step Time": 8.4909038990736} +{"Pretrain/Learning Rate": 4.988297547121e-05, "Pretrain/Loss": 2.143989324569702, "Pretrain/Loss (Raw)": 2.2332091331481934, "Pretrain/Step": 571, "Pretrain/Step Time": 8.491478020325303} +{"Pretrain/Learning Rate": 4.988215345263132e-05, "Pretrain/Loss": 2.1457414627075195, "Pretrain/Loss (Raw)": 2.146301746368408, "Pretrain/Step": 572, "Pretrain/Step Time": 8.488382186740637} +{"Pretrain/Learning Rate": 4.9881328563904984e-05, "Pretrain/Loss": 2.144596576690674, "Pretrain/Loss (Raw)": 1.9999359846115112, "Pretrain/Step": 573, "Pretrain/Step Time": 8.489672290161252} +{"Pretrain/Learning Rate": 4.988050080512614e-05, "Pretrain/Loss": 2.1467888355255127, "Pretrain/Loss (Raw)": 2.1644482612609863, "Pretrain/Step": 574, "Pretrain/Step Time": 8.486960493028164} +{"Pretrain/Learning Rate": 4.987967017639027e-05, "Pretrain/Loss": 2.146853446960449, "Pretrain/Loss (Raw)": 2.1894686222076416, "Pretrain/Step": 575, "Pretrain/Step Time": 8.491665227338672} +{"Pretrain/Learning Rate": 4.9878836677793196e-05, "Pretrain/Loss": 2.1459622383117676, "Pretrain/Loss (Raw)": 2.1517820358276367, "Pretrain/Step": 576, "Pretrain/Step Time": 8.4899882953614} +{"Pretrain/Learning Rate": 4.987800030943105e-05, "Pretrain/Loss": 2.146977186203003, "Pretrain/Loss (Raw)": 2.111398696899414, "Pretrain/Step": 577, "Pretrain/Step Time": 8.493820324540138} +{"Pretrain/Learning Rate": 4.9877161071400314e-05, "Pretrain/Loss": 2.145880699157715, "Pretrain/Loss (Raw)": 1.9627162218093872, "Pretrain/Step": 578, "Pretrain/Step Time": 8.49267496354878} +{"Pretrain/Learning Rate": 4.9876318963797786e-05, "Pretrain/Loss": 2.1445653438568115, "Pretrain/Loss (Raw)": 2.094383955001831, "Pretrain/Step": 579, "Pretrain/Step Time": 8.495886407792568} +{"Pretrain/Learning Rate": 4.987547398672061e-05, "Pretrain/Loss": 2.1436424255371094, "Pretrain/Loss (Raw)": 2.084116220474243, "Pretrain/Step": 580, "Pretrain/Step Time": 8.492264354601502} +{"Pretrain/Learning Rate": 4.987462614026625e-05, "Pretrain/Loss": 2.1458373069763184, "Pretrain/Loss (Raw)": 2.323814868927002, "Pretrain/Step": 581, "Pretrain/Step Time": 8.493346417322755} +{"Pretrain/Learning Rate": 4.987377542453251e-05, "Pretrain/Loss": 2.147003173828125, "Pretrain/Loss (Raw)": 2.25748348236084, "Pretrain/Step": 582, "Pretrain/Step Time": 8.493733517825603} +{"Pretrain/Learning Rate": 4.987292183961751e-05, "Pretrain/Loss": 2.148426055908203, "Pretrain/Loss (Raw)": 2.2299740314483643, "Pretrain/Step": 583, "Pretrain/Step Time": 8.494171094149351} +{"Pretrain/Learning Rate": 4.987206538561972e-05, "Pretrain/Loss": 2.149402141571045, "Pretrain/Loss (Raw)": 2.1712279319763184, "Pretrain/Step": 584, "Pretrain/Step Time": 8.49690980836749} +{"Pretrain/Learning Rate": 4.987120606263793e-05, "Pretrain/Loss": 2.147923469543457, "Pretrain/Loss (Raw)": 2.032069683074951, "Pretrain/Step": 585, "Pretrain/Step Time": 8.492054948583245} +{"Pretrain/Learning Rate": 4.9870343870771256e-05, "Pretrain/Loss": 2.147089958190918, "Pretrain/Loss (Raw)": 2.0676944255828857, "Pretrain/Step": 586, "Pretrain/Step Time": 8.49507481046021} +{"Pretrain/Learning Rate": 4.9869478810119164e-05, "Pretrain/Loss": 2.1462314128875732, "Pretrain/Loss (Raw)": 2.0511045455932617, "Pretrain/Step": 587, "Pretrain/Step Time": 8.493937009945512} +{"Pretrain/Learning Rate": 4.986861088078143e-05, "Pretrain/Loss": 2.1465299129486084, "Pretrain/Loss (Raw)": 2.1843645572662354, "Pretrain/Step": 588, "Pretrain/Step Time": 8.495038475841284} +{"Pretrain/Learning Rate": 4.986774008285816e-05, "Pretrain/Loss": 2.1465303897857666, "Pretrain/Loss (Raw)": 2.2042534351348877, "Pretrain/Step": 589, "Pretrain/Step Time": 8.49694037437439} +{"Pretrain/Learning Rate": 4.986686641644982e-05, "Pretrain/Loss": 2.1448147296905518, "Pretrain/Loss (Raw)": 2.0523667335510254, "Pretrain/Step": 590, "Pretrain/Step Time": 8.49559510499239} +{"Pretrain/Learning Rate": 4.986598988165718e-05, "Pretrain/Loss": 2.1448066234588623, "Pretrain/Loss (Raw)": 2.1321394443511963, "Pretrain/Step": 591, "Pretrain/Step Time": 8.496942047029734} +{"Pretrain/Learning Rate": 4.986511047858134e-05, "Pretrain/Loss": 2.1446943283081055, "Pretrain/Loss (Raw)": 2.144009590148926, "Pretrain/Step": 592, "Pretrain/Step Time": 8.49672021344304} +{"Pretrain/Learning Rate": 4.986422820732375e-05, "Pretrain/Loss": 2.1438894271850586, "Pretrain/Loss (Raw)": 2.215000867843628, "Pretrain/Step": 593, "Pretrain/Step Time": 8.500221585854888} +{"Pretrain/Learning Rate": 4.986334306798617e-05, "Pretrain/Loss": 2.1432993412017822, "Pretrain/Loss (Raw)": 2.094630002975464, "Pretrain/Step": 594, "Pretrain/Step Time": 8.497916169464588} +{"Pretrain/Learning Rate": 4.9862455060670696e-05, "Pretrain/Loss": 2.142491579055786, "Pretrain/Loss (Raw)": 2.0418007373809814, "Pretrain/Step": 595, "Pretrain/Step Time": 8.496251419186592} +{"Pretrain/Learning Rate": 4.9861564185479784e-05, "Pretrain/Loss": 2.1435563564300537, "Pretrain/Loss (Raw)": 2.1917567253112793, "Pretrain/Step": 596, "Pretrain/Step Time": 8.497078593820333} +{"Pretrain/Learning Rate": 4.9860670442516175e-05, "Pretrain/Loss": 2.1436190605163574, "Pretrain/Loss (Raw)": 2.1572721004486084, "Pretrain/Step": 597, "Pretrain/Step Time": 8.493998140096664} +{"Pretrain/Learning Rate": 4.985977383188296e-05, "Pretrain/Loss": 2.141580581665039, "Pretrain/Loss (Raw)": 1.8643121719360352, "Pretrain/Step": 598, "Pretrain/Step Time": 8.495264200493693} +{"Pretrain/Learning Rate": 4.9858874353683574e-05, "Pretrain/Loss": 2.139995574951172, "Pretrain/Loss (Raw)": 2.085695505142212, "Pretrain/Step": 599, "Pretrain/Step Time": 8.499417755752802} +{"Pretrain/Learning Rate": 4.985797200802177e-05, "Pretrain/Loss": 2.1395468711853027, "Pretrain/Loss (Raw)": 2.1805241107940674, "Pretrain/Step": 600, "Pretrain/Step Time": 8.495264936238527} +{"Pretrain/Learning Rate": 4.9857066795001625e-05, "Pretrain/Loss": 2.142261505126953, "Pretrain/Loss (Raw)": 2.3292038440704346, "Pretrain/Step": 601, "Pretrain/Step Time": 8.493396895006299} +{"Pretrain/Learning Rate": 4.985615871472758e-05, "Pretrain/Loss": 2.142798900604248, "Pretrain/Loss (Raw)": 2.1908645629882812, "Pretrain/Step": 602, "Pretrain/Step Time": 8.499327877536416} +{"Pretrain/Learning Rate": 4.9855247767304337e-05, "Pretrain/Loss": 2.1416237354278564, "Pretrain/Loss (Raw)": 2.114516496658325, "Pretrain/Step": 603, "Pretrain/Step Time": 8.500542867928743} +{"Pretrain/Learning Rate": 4.985433395283701e-05, "Pretrain/Loss": 2.1423449516296387, "Pretrain/Loss (Raw)": 2.1707146167755127, "Pretrain/Step": 604, "Pretrain/Step Time": 8.501849228516221} +{"Pretrain/Learning Rate": 4.985341727143099e-05, "Pretrain/Loss": 2.139051914215088, "Pretrain/Loss (Raw)": 1.9513193368911743, "Pretrain/Step": 605, "Pretrain/Step Time": 8.501944340765476} +{"Pretrain/Learning Rate": 4.9852497723192024e-05, "Pretrain/Loss": 2.1395435333251953, "Pretrain/Loss (Raw)": 2.240922689437866, "Pretrain/Step": 606, "Pretrain/Step Time": 8.504274802282453} +{"Pretrain/Learning Rate": 4.985157530822619e-05, "Pretrain/Loss": 2.1391923427581787, "Pretrain/Loss (Raw)": 2.170189142227173, "Pretrain/Step": 607, "Pretrain/Step Time": 8.501497467979789} +{"Pretrain/Learning Rate": 4.985065002663987e-05, "Pretrain/Loss": 2.139040946960449, "Pretrain/Loss (Raw)": 2.072631597518921, "Pretrain/Step": 608, "Pretrain/Step Time": 8.502932136878371} +{"Pretrain/Learning Rate": 4.9849721878539804e-05, "Pretrain/Loss": 2.1374711990356445, "Pretrain/Loss (Raw)": 2.0747978687286377, "Pretrain/Step": 609, "Pretrain/Step Time": 8.49915779940784} +{"Pretrain/Learning Rate": 4.984879086403304e-05, "Pretrain/Loss": 2.13736629486084, "Pretrain/Loss (Raw)": 2.0768659114837646, "Pretrain/Step": 610, "Pretrain/Step Time": 8.499734621495008} +{"Pretrain/Learning Rate": 4.9847856983226996e-05, "Pretrain/Loss": 2.138629674911499, "Pretrain/Loss (Raw)": 2.294929265975952, "Pretrain/Step": 611, "Pretrain/Step Time": 8.502513671293855} +{"Pretrain/Learning Rate": 4.984692023622938e-05, "Pretrain/Loss": 2.1384592056274414, "Pretrain/Loss (Raw)": 2.0616157054901123, "Pretrain/Step": 612, "Pretrain/Step Time": 8.503811517730355} +{"Pretrain/Learning Rate": 4.984598062314825e-05, "Pretrain/Loss": 2.138272762298584, "Pretrain/Loss (Raw)": 2.1649200916290283, "Pretrain/Step": 613, "Pretrain/Step Time": 8.503444688394666} +{"Pretrain/Learning Rate": 4.984503814409198e-05, "Pretrain/Loss": 2.1369786262512207, "Pretrain/Loss (Raw)": 1.960531234741211, "Pretrain/Step": 614, "Pretrain/Step Time": 8.502993542701006} +{"Pretrain/Learning Rate": 4.984409279916929e-05, "Pretrain/Loss": 2.1378161907196045, "Pretrain/Loss (Raw)": 2.1286354064941406, "Pretrain/Step": 615, "Pretrain/Step Time": 8.501459648832679} +{"Pretrain/Learning Rate": 4.984314458848923e-05, "Pretrain/Loss": 2.1356325149536133, "Pretrain/Loss (Raw)": 1.9398202896118164, "Pretrain/Step": 616, "Pretrain/Step Time": 8.501068539917469} +{"Pretrain/Learning Rate": 4.9842193512161165e-05, "Pretrain/Loss": 2.1362791061401367, "Pretrain/Loss (Raw)": 2.096815824508667, "Pretrain/Step": 617, "Pretrain/Step Time": 8.500321762636304} +{"Pretrain/Learning Rate": 4.9841239570294815e-05, "Pretrain/Loss": 2.1361517906188965, "Pretrain/Loss (Raw)": 2.186528205871582, "Pretrain/Step": 618, "Pretrain/Step Time": 8.501139288768172} +{"Pretrain/Learning Rate": 4.984028276300021e-05, "Pretrain/Loss": 2.1347484588623047, "Pretrain/Loss (Raw)": 2.1085476875305176, "Pretrain/Step": 619, "Pretrain/Step Time": 8.501813689246774} +{"Pretrain/Learning Rate": 4.9839323090387725e-05, "Pretrain/Loss": 2.13619327545166, "Pretrain/Loss (Raw)": 2.172666311264038, "Pretrain/Step": 620, "Pretrain/Step Time": 8.499337336048484} +{"Pretrain/Learning Rate": 4.983836055256804e-05, "Pretrain/Loss": 2.1329855918884277, "Pretrain/Loss (Raw)": 1.8707866668701172, "Pretrain/Step": 621, "Pretrain/Step Time": 8.496016358956695} +{"Pretrain/Learning Rate": 4.98373951496522e-05, "Pretrain/Loss": 2.132701873779297, "Pretrain/Loss (Raw)": 2.097813367843628, "Pretrain/Step": 622, "Pretrain/Step Time": 8.495633536949754} +{"Pretrain/Learning Rate": 4.9836426881751554e-05, "Pretrain/Loss": 2.13094425201416, "Pretrain/Loss (Raw)": 2.0151851177215576, "Pretrain/Step": 623, "Pretrain/Step Time": 8.493450241163373} +{"Pretrain/Learning Rate": 4.9835455748977795e-05, "Pretrain/Loss": 2.130711078643799, "Pretrain/Loss (Raw)": 2.1368398666381836, "Pretrain/Step": 624, "Pretrain/Step Time": 8.494038628414273} +{"Pretrain/Learning Rate": 4.983448175144294e-05, "Pretrain/Loss": 2.1324350833892822, "Pretrain/Loss (Raw)": 2.099790096282959, "Pretrain/Step": 625, "Pretrain/Step Time": 8.493441715836525} +{"Pretrain/Learning Rate": 4.983350488925935e-05, "Pretrain/Loss": 2.130460500717163, "Pretrain/Loss (Raw)": 2.0081124305725098, "Pretrain/Step": 626, "Pretrain/Step Time": 8.494847288355231} +{"Pretrain/Learning Rate": 4.9832525162539696e-05, "Pretrain/Loss": 2.132052421569824, "Pretrain/Loss (Raw)": 2.318938970565796, "Pretrain/Step": 627, "Pretrain/Step Time": 8.49038358591497} +{"Pretrain/Learning Rate": 4.9831542571396995e-05, "Pretrain/Loss": 2.1318514347076416, "Pretrain/Loss (Raw)": 2.2032344341278076, "Pretrain/Step": 628, "Pretrain/Step Time": 8.491784017533064} +{"Pretrain/Learning Rate": 4.983055711594457e-05, "Pretrain/Loss": 2.129063606262207, "Pretrain/Loss (Raw)": 1.9007503986358643, "Pretrain/Step": 629, "Pretrain/Step Time": 8.493122451007366} +{"Pretrain/Learning Rate": 4.982956879629612e-05, "Pretrain/Loss": 2.1294729709625244, "Pretrain/Loss (Raw)": 2.136216402053833, "Pretrain/Step": 630, "Pretrain/Step Time": 8.49352166056633} +{"Pretrain/Learning Rate": 4.982857761256564e-05, "Pretrain/Loss": 2.128903865814209, "Pretrain/Loss (Raw)": 2.174750804901123, "Pretrain/Step": 631, "Pretrain/Step Time": 8.491180436685681} +{"Pretrain/Learning Rate": 4.982758356486745e-05, "Pretrain/Loss": 2.1285603046417236, "Pretrain/Loss (Raw)": 2.1168713569641113, "Pretrain/Step": 632, "Pretrain/Step Time": 8.490062445402145} +{"Pretrain/Learning Rate": 4.982658665331622e-05, "Pretrain/Loss": 2.1263866424560547, "Pretrain/Loss (Raw)": 2.106870174407959, "Pretrain/Step": 633, "Pretrain/Step Time": 8.48786643333733} +{"Pretrain/Learning Rate": 4.982558687802695e-05, "Pretrain/Loss": 2.1272013187408447, "Pretrain/Loss (Raw)": 2.1102075576782227, "Pretrain/Step": 634, "Pretrain/Step Time": 8.488795099779963} +{"Pretrain/Learning Rate": 4.982458423911495e-05, "Pretrain/Loss": 2.1277430057525635, "Pretrain/Loss (Raw)": 2.134593963623047, "Pretrain/Step": 635, "Pretrain/Step Time": 8.49148335121572} +{"Pretrain/Learning Rate": 4.982357873669589e-05, "Pretrain/Loss": 2.128872871398926, "Pretrain/Loss (Raw)": 2.201871871948242, "Pretrain/Step": 636, "Pretrain/Step Time": 8.496848981827497} +{"Pretrain/Learning Rate": 4.9822570370885733e-05, "Pretrain/Loss": 2.126556634902954, "Pretrain/Loss (Raw)": 1.9188973903656006, "Pretrain/Step": 637, "Pretrain/Step Time": 8.493518985807896} +{"Pretrain/Learning Rate": 4.982155914180082e-05, "Pretrain/Loss": 2.1261656284332275, "Pretrain/Loss (Raw)": 2.005697011947632, "Pretrain/Step": 638, "Pretrain/Step Time": 8.495982697233558} +{"Pretrain/Learning Rate": 4.982054504955778e-05, "Pretrain/Loss": 2.1262290477752686, "Pretrain/Loss (Raw)": 2.1021978855133057, "Pretrain/Step": 639, "Pretrain/Step Time": 8.495332594960928} +{"Pretrain/Learning Rate": 4.981952809427359e-05, "Pretrain/Loss": 2.12552547454834, "Pretrain/Loss (Raw)": 2.091759204864502, "Pretrain/Step": 640, "Pretrain/Step Time": 8.49375374801457} +{"Pretrain/Learning Rate": 4.9818508276065554e-05, "Pretrain/Loss": 2.123997211456299, "Pretrain/Loss (Raw)": 1.9953457117080688, "Pretrain/Step": 641, "Pretrain/Step Time": 8.494654264301062} +{"Pretrain/Learning Rate": 4.981748559505132e-05, "Pretrain/Loss": 2.1229231357574463, "Pretrain/Loss (Raw)": 2.073755979537964, "Pretrain/Step": 642, "Pretrain/Step Time": 8.493330538272858} +{"Pretrain/Learning Rate": 4.9816460051348835e-05, "Pretrain/Loss": 2.123640298843384, "Pretrain/Loss (Raw)": 2.2335736751556396, "Pretrain/Step": 643, "Pretrain/Step Time": 8.493738697841763} +{"Pretrain/Learning Rate": 4.98154316450764e-05, "Pretrain/Loss": 2.124154567718506, "Pretrain/Loss (Raw)": 2.188369035720825, "Pretrain/Step": 644, "Pretrain/Step Time": 8.49651082418859} +{"Pretrain/Learning Rate": 4.981440037635266e-05, "Pretrain/Loss": 2.121185541152954, "Pretrain/Loss (Raw)": 1.9212912321090698, "Pretrain/Step": 645, "Pretrain/Step Time": 8.494473706930876} +{"Pretrain/Learning Rate": 4.981336624529655e-05, "Pretrain/Loss": 2.121622085571289, "Pretrain/Loss (Raw)": 2.2427306175231934, "Pretrain/Step": 646, "Pretrain/Step Time": 8.498133517801762} +{"Pretrain/Learning Rate": 4.981232925202736e-05, "Pretrain/Loss": 2.1218600273132324, "Pretrain/Loss (Raw)": 2.058741331100464, "Pretrain/Step": 647, "Pretrain/Step Time": 8.498076193034649} +{"Pretrain/Learning Rate": 4.9811289396664715e-05, "Pretrain/Loss": 2.1212167739868164, "Pretrain/Loss (Raw)": 2.013896942138672, "Pretrain/Step": 648, "Pretrain/Step Time": 8.497960306704044} +{"Pretrain/Learning Rate": 4.9810246679328554e-05, "Pretrain/Loss": 2.1210310459136963, "Pretrain/Loss (Raw)": 2.1045029163360596, "Pretrain/Step": 649, "Pretrain/Step Time": 8.494495019316673} +{"Pretrain/Learning Rate": 4.9809201100139156e-05, "Pretrain/Loss": 2.120551347732544, "Pretrain/Loss (Raw)": 2.0542361736297607, "Pretrain/Step": 650, "Pretrain/Step Time": 8.497122881934047} +{"Pretrain/Learning Rate": 4.980815265921713e-05, "Pretrain/Loss": 2.120295524597168, "Pretrain/Loss (Raw)": 2.113126277923584, "Pretrain/Step": 651, "Pretrain/Step Time": 8.495550693944097} +{"Pretrain/Learning Rate": 4.9807101356683415e-05, "Pretrain/Loss": 2.1211416721343994, "Pretrain/Loss (Raw)": 2.293215274810791, "Pretrain/Step": 652, "Pretrain/Step Time": 8.493682835251093} +{"Pretrain/Learning Rate": 4.9806047192659276e-05, "Pretrain/Loss": 2.1210954189300537, "Pretrain/Loss (Raw)": 2.142443895339966, "Pretrain/Step": 653, "Pretrain/Step Time": 8.4933021068573} +{"Pretrain/Learning Rate": 4.980499016726632e-05, "Pretrain/Loss": 2.120149850845337, "Pretrain/Loss (Raw)": 2.024963617324829, "Pretrain/Step": 654, "Pretrain/Step Time": 8.496093153953552} +{"Pretrain/Learning Rate": 4.9803930280626455e-05, "Pretrain/Loss": 2.121220350265503, "Pretrain/Loss (Raw)": 2.202362060546875, "Pretrain/Step": 655, "Pretrain/Step Time": 8.496507190167904} +{"Pretrain/Learning Rate": 4.980286753286195e-05, "Pretrain/Loss": 2.1219451427459717, "Pretrain/Loss (Raw)": 2.122530698776245, "Pretrain/Step": 656, "Pretrain/Step Time": 8.496527357026935} +{"Pretrain/Learning Rate": 4.980180192409539e-05, "Pretrain/Loss": 2.122494697570801, "Pretrain/Loss (Raw)": 2.1632275581359863, "Pretrain/Step": 657, "Pretrain/Step Time": 8.493382204324007} +{"Pretrain/Learning Rate": 4.98007334544497e-05, "Pretrain/Loss": 2.120948314666748, "Pretrain/Loss (Raw)": 1.961111068725586, "Pretrain/Step": 658, "Pretrain/Step Time": 8.494558647274971} +{"Pretrain/Learning Rate": 4.979966212404811e-05, "Pretrain/Loss": 2.1224560737609863, "Pretrain/Loss (Raw)": 2.149991035461426, "Pretrain/Step": 659, "Pretrain/Step Time": 8.491938265040517} +{"Pretrain/Learning Rate": 4.979858793301422e-05, "Pretrain/Loss": 2.122636318206787, "Pretrain/Loss (Raw)": 2.1155495643615723, "Pretrain/Step": 660, "Pretrain/Step Time": 8.491990517824888} +{"Pretrain/Learning Rate": 4.979751088147192e-05, "Pretrain/Loss": 2.1206858158111572, "Pretrain/Loss (Raw)": 1.9649357795715332, "Pretrain/Step": 661, "Pretrain/Step Time": 8.493116596713662} +{"Pretrain/Learning Rate": 4.979643096954546e-05, "Pretrain/Loss": 2.122009754180908, "Pretrain/Loss (Raw)": 2.1765036582946777, "Pretrain/Step": 662, "Pretrain/Step Time": 8.493449291214347} +{"Pretrain/Learning Rate": 4.97953481973594e-05, "Pretrain/Loss": 2.124089241027832, "Pretrain/Loss (Raw)": 2.3166821002960205, "Pretrain/Step": 663, "Pretrain/Step Time": 8.491673620417714} +{"Pretrain/Learning Rate": 4.979426256503864e-05, "Pretrain/Loss": 2.1235084533691406, "Pretrain/Loss (Raw)": 2.1350908279418945, "Pretrain/Step": 664, "Pretrain/Step Time": 8.49130642786622} +{"Pretrain/Learning Rate": 4.9793174072708405e-05, "Pretrain/Loss": 2.1232428550720215, "Pretrain/Loss (Raw)": 2.0589184761047363, "Pretrain/Step": 665, "Pretrain/Step Time": 8.488217199221253} +{"Pretrain/Learning Rate": 4.979208272049425e-05, "Pretrain/Loss": 2.123602867126465, "Pretrain/Loss (Raw)": 2.1997435092926025, "Pretrain/Step": 666, "Pretrain/Step Time": 8.489252258092165} +{"Pretrain/Learning Rate": 4.9790988508522076e-05, "Pretrain/Loss": 2.1232974529266357, "Pretrain/Loss (Raw)": 2.1716420650482178, "Pretrain/Step": 667, "Pretrain/Step Time": 8.490806927904487} +{"Pretrain/Learning Rate": 4.978989143691808e-05, "Pretrain/Loss": 2.1248936653137207, "Pretrain/Loss (Raw)": 2.1800458431243896, "Pretrain/Step": 668, "Pretrain/Step Time": 8.491934303194284} +{"Pretrain/Learning Rate": 4.978879150580882e-05, "Pretrain/Loss": 2.123753070831299, "Pretrain/Loss (Raw)": 2.240105628967285, "Pretrain/Step": 669, "Pretrain/Step Time": 8.490937577560544} +{"Pretrain/Learning Rate": 4.978768871532118e-05, "Pretrain/Loss": 2.123837947845459, "Pretrain/Loss (Raw)": 2.2464466094970703, "Pretrain/Step": 670, "Pretrain/Step Time": 8.490029504522681} +{"Pretrain/Learning Rate": 4.978658306558235e-05, "Pretrain/Loss": 2.1238880157470703, "Pretrain/Loss (Raw)": 2.210284948348999, "Pretrain/Step": 671, "Pretrain/Step Time": 8.490356700494885} +{"Pretrain/Learning Rate": 4.978547455671987e-05, "Pretrain/Loss": 2.122401237487793, "Pretrain/Loss (Raw)": 2.000281572341919, "Pretrain/Step": 672, "Pretrain/Step Time": 8.488915514200926} +{"Pretrain/Learning Rate": 4.978436318886162e-05, "Pretrain/Loss": 2.1214871406555176, "Pretrain/Loss (Raw)": 2.037720203399658, "Pretrain/Step": 673, "Pretrain/Step Time": 8.48959037475288} +{"Pretrain/Learning Rate": 4.978324896213577e-05, "Pretrain/Loss": 2.1219654083251953, "Pretrain/Loss (Raw)": 2.229888916015625, "Pretrain/Step": 674, "Pretrain/Step Time": 8.489520445466042} +{"Pretrain/Learning Rate": 4.978213187667088e-05, "Pretrain/Loss": 2.121951103210449, "Pretrain/Loss (Raw)": 2.024616003036499, "Pretrain/Step": 675, "Pretrain/Step Time": 8.486862886697054} +{"Pretrain/Learning Rate": 4.978101193259578e-05, "Pretrain/Loss": 2.124300956726074, "Pretrain/Loss (Raw)": 2.211693525314331, "Pretrain/Step": 676, "Pretrain/Step Time": 8.488486386835575} +{"Pretrain/Learning Rate": 4.977988913003967e-05, "Pretrain/Loss": 2.123518466949463, "Pretrain/Loss (Raw)": 2.0469231605529785, "Pretrain/Step": 677, "Pretrain/Step Time": 8.488124370574951} +{"Pretrain/Learning Rate": 4.977876346913204e-05, "Pretrain/Loss": 2.1226346492767334, "Pretrain/Loss (Raw)": 2.057037830352783, "Pretrain/Step": 678, "Pretrain/Step Time": 8.48298822529614} +{"Pretrain/Learning Rate": 4.977763495000276e-05, "Pretrain/Loss": 2.12184739112854, "Pretrain/Loss (Raw)": 2.032475471496582, "Pretrain/Step": 679, "Pretrain/Step Time": 8.483665943145752} +{"Pretrain/Learning Rate": 4.9776503572782e-05, "Pretrain/Loss": 2.120511054992676, "Pretrain/Loss (Raw)": 1.9923640489578247, "Pretrain/Step": 680, "Pretrain/Step Time": 8.487054696306586} +{"Pretrain/Learning Rate": 4.9775369337600255e-05, "Pretrain/Loss": 2.1216182708740234, "Pretrain/Loss (Raw)": 2.19381046295166, "Pretrain/Step": 681, "Pretrain/Step Time": 8.483959466218948} +{"Pretrain/Learning Rate": 4.977423224458837e-05, "Pretrain/Loss": 2.1217546463012695, "Pretrain/Loss (Raw)": 2.0719709396362305, "Pretrain/Step": 682, "Pretrain/Step Time": 8.483789661899209} +{"Pretrain/Learning Rate": 4.9773092293877496e-05, "Pretrain/Loss": 2.1223714351654053, "Pretrain/Loss (Raw)": 2.1827445030212402, "Pretrain/Step": 683, "Pretrain/Step Time": 8.48448465205729} +{"Pretrain/Learning Rate": 4.9771949485599134e-05, "Pretrain/Loss": 2.120896339416504, "Pretrain/Loss (Raw)": 2.058009147644043, "Pretrain/Step": 684, "Pretrain/Step Time": 8.487099619582295} +{"Pretrain/Learning Rate": 4.9770803819885104e-05, "Pretrain/Loss": 2.1208245754241943, "Pretrain/Loss (Raw)": 2.107475757598877, "Pretrain/Step": 685, "Pretrain/Step Time": 8.484994729980826} +{"Pretrain/Learning Rate": 4.9769655296867554e-05, "Pretrain/Loss": 2.122075080871582, "Pretrain/Loss (Raw)": 2.307680368423462, "Pretrain/Step": 686, "Pretrain/Step Time": 8.48494272865355} +{"Pretrain/Learning Rate": 4.9768503916678976e-05, "Pretrain/Loss": 2.120847702026367, "Pretrain/Loss (Raw)": 2.063819408416748, "Pretrain/Step": 687, "Pretrain/Step Time": 8.486793665215373} +{"Pretrain/Learning Rate": 4.976734967945217e-05, "Pretrain/Loss": 2.1215944290161133, "Pretrain/Loss (Raw)": 2.196641683578491, "Pretrain/Step": 688, "Pretrain/Step Time": 8.485614845529199} +{"Pretrain/Learning Rate": 4.976619258532029e-05, "Pretrain/Loss": 2.1230359077453613, "Pretrain/Loss (Raw)": 2.2969813346862793, "Pretrain/Step": 689, "Pretrain/Step Time": 8.48834827542305} +{"Pretrain/Learning Rate": 4.976503263441679e-05, "Pretrain/Loss": 2.1211581230163574, "Pretrain/Loss (Raw)": 1.9830039739608765, "Pretrain/Step": 690, "Pretrain/Step Time": 8.48375373147428} +{"Pretrain/Learning Rate": 4.976386982687549e-05, "Pretrain/Loss": 2.1200990676879883, "Pretrain/Loss (Raw)": 2.160581588745117, "Pretrain/Step": 691, "Pretrain/Step Time": 8.481410851702094} +{"Pretrain/Learning Rate": 4.97627041628305e-05, "Pretrain/Loss": 2.1215834617614746, "Pretrain/Loss (Raw)": 2.1120707988739014, "Pretrain/Step": 692, "Pretrain/Step Time": 8.482823396101594} +{"Pretrain/Learning Rate": 4.976153564241628e-05, "Pretrain/Loss": 2.120820999145508, "Pretrain/Loss (Raw)": 2.0938026905059814, "Pretrain/Step": 693, "Pretrain/Step Time": 8.47868481092155} +{"Pretrain/Learning Rate": 4.976036426576763e-05, "Pretrain/Loss": 2.118712902069092, "Pretrain/Loss (Raw)": 2.018044948577881, "Pretrain/Step": 694, "Pretrain/Step Time": 8.481641473248601} +{"Pretrain/Learning Rate": 4.975919003301968e-05, "Pretrain/Loss": 2.1205646991729736, "Pretrain/Loss (Raw)": 2.1917576789855957, "Pretrain/Step": 695, "Pretrain/Step Time": 8.481908505782485} +{"Pretrain/Learning Rate": 4.9758012944307844e-05, "Pretrain/Loss": 2.1205954551696777, "Pretrain/Loss (Raw)": 2.234382152557373, "Pretrain/Step": 696, "Pretrain/Step Time": 8.479990610852838} +{"Pretrain/Learning Rate": 4.9756832999767914e-05, "Pretrain/Loss": 2.1215786933898926, "Pretrain/Loss (Raw)": 2.1929807662963867, "Pretrain/Step": 697, "Pretrain/Step Time": 8.481233529746532} +{"Pretrain/Learning Rate": 4.975565019953601e-05, "Pretrain/Loss": 2.120567798614502, "Pretrain/Loss (Raw)": 2.180896282196045, "Pretrain/Step": 698, "Pretrain/Step Time": 8.475014641880989} +{"Pretrain/Learning Rate": 4.9754464543748546e-05, "Pretrain/Loss": 2.118600606918335, "Pretrain/Loss (Raw)": 1.9813878536224365, "Pretrain/Step": 699, "Pretrain/Step Time": 8.476354395970702} +{"Pretrain/Learning Rate": 4.975327603254229e-05, "Pretrain/Loss": 2.1189866065979004, "Pretrain/Loss (Raw)": 2.1957263946533203, "Pretrain/Step": 700, "Pretrain/Step Time": 8.474927019327879} +{"Pretrain/Learning Rate": 4.9752084666054353e-05, "Pretrain/Loss": 2.119551181793213, "Pretrain/Loss (Raw)": 2.072197437286377, "Pretrain/Step": 701, "Pretrain/Step Time": 8.478531176224351} +{"Pretrain/Learning Rate": 4.975089044442215e-05, "Pretrain/Loss": 2.119399070739746, "Pretrain/Loss (Raw)": 2.1449644565582275, "Pretrain/Step": 702, "Pretrain/Step Time": 8.481747679412365} +{"Pretrain/Learning Rate": 4.974969336778343e-05, "Pretrain/Loss": 2.1187584400177, "Pretrain/Loss (Raw)": 2.1074867248535156, "Pretrain/Step": 703, "Pretrain/Step Time": 8.480300532653928} +{"Pretrain/Learning Rate": 4.974849343627628e-05, "Pretrain/Loss": 2.1173670291900635, "Pretrain/Loss (Raw)": 1.973680019378662, "Pretrain/Step": 704, "Pretrain/Step Time": 8.483653636649251} +{"Pretrain/Learning Rate": 4.97472906500391e-05, "Pretrain/Loss": 2.1176657676696777, "Pretrain/Loss (Raw)": 2.1496193408966064, "Pretrain/Step": 705, "Pretrain/Step Time": 8.47866915166378} +{"Pretrain/Learning Rate": 4.974608500921064e-05, "Pretrain/Loss": 2.119000196456909, "Pretrain/Loss (Raw)": 2.1335349082946777, "Pretrain/Step": 706, "Pretrain/Step Time": 8.480118662118912} +{"Pretrain/Learning Rate": 4.974487651392998e-05, "Pretrain/Loss": 2.119114637374878, "Pretrain/Loss (Raw)": 2.1090288162231445, "Pretrain/Step": 707, "Pretrain/Step Time": 8.47541756927967} +{"Pretrain/Learning Rate": 4.974366516433651e-05, "Pretrain/Loss": 2.1202011108398438, "Pretrain/Loss (Raw)": 2.2231545448303223, "Pretrain/Step": 708, "Pretrain/Step Time": 8.476125860586762} +{"Pretrain/Learning Rate": 4.974245096056995e-05, "Pretrain/Loss": 2.1185965538024902, "Pretrain/Loss (Raw)": 2.1184802055358887, "Pretrain/Step": 709, "Pretrain/Step Time": 8.475608941167593} +{"Pretrain/Learning Rate": 4.974123390277038e-05, "Pretrain/Loss": 2.118835926055908, "Pretrain/Loss (Raw)": 2.2880773544311523, "Pretrain/Step": 710, "Pretrain/Step Time": 8.478721903637052} +{"Pretrain/Learning Rate": 4.974001399107816e-05, "Pretrain/Loss": 2.1185317039489746, "Pretrain/Loss (Raw)": 2.1910417079925537, "Pretrain/Step": 711, "Pretrain/Step Time": 8.476786013692617} +{"Pretrain/Learning Rate": 4.9738791225634027e-05, "Pretrain/Loss": 2.1187360286712646, "Pretrain/Loss (Raw)": 2.1973886489868164, "Pretrain/Step": 712, "Pretrain/Step Time": 8.473707804456353} +{"Pretrain/Learning Rate": 4.973756560657902e-05, "Pretrain/Loss": 2.120028495788574, "Pretrain/Loss (Raw)": 2.197526216506958, "Pretrain/Step": 713, "Pretrain/Step Time": 8.470306510105729} +{"Pretrain/Learning Rate": 4.973633713405451e-05, "Pretrain/Loss": 2.120474100112915, "Pretrain/Loss (Raw)": 2.124720573425293, "Pretrain/Step": 714, "Pretrain/Step Time": 8.46675912849605} +{"Pretrain/Learning Rate": 4.973510580820221e-05, "Pretrain/Loss": 2.1204237937927246, "Pretrain/Loss (Raw)": 2.044680118560791, "Pretrain/Step": 715, "Pretrain/Step Time": 8.466041864827275} +{"Pretrain/Learning Rate": 4.973387162916415e-05, "Pretrain/Loss": 2.121285915374756, "Pretrain/Loss (Raw)": 2.294692277908325, "Pretrain/Step": 716, "Pretrain/Step Time": 8.465993892401457} +{"Pretrain/Learning Rate": 4.9732634597082685e-05, "Pretrain/Loss": 2.121133327484131, "Pretrain/Loss (Raw)": 2.184709310531616, "Pretrain/Step": 717, "Pretrain/Step Time": 8.464446319267154} +{"Pretrain/Learning Rate": 4.973139471210051e-05, "Pretrain/Loss": 2.1224045753479004, "Pretrain/Loss (Raw)": 2.215120315551758, "Pretrain/Step": 718, "Pretrain/Step Time": 8.467097761109471} +{"Pretrain/Learning Rate": 4.973015197436064e-05, "Pretrain/Loss": 2.1216213703155518, "Pretrain/Loss (Raw)": 2.0318784713745117, "Pretrain/Step": 719, "Pretrain/Step Time": 8.46622141264379} +{"Pretrain/Learning Rate": 4.972890638400644e-05, "Pretrain/Loss": 2.1210670471191406, "Pretrain/Loss (Raw)": 2.073061227798462, "Pretrain/Step": 720, "Pretrain/Step Time": 8.466666782274842} +{"Pretrain/Learning Rate": 4.972765794118158e-05, "Pretrain/Loss": 2.120413064956665, "Pretrain/Loss (Raw)": 2.1312854290008545, "Pretrain/Step": 721, "Pretrain/Step Time": 8.463367218151689} +{"Pretrain/Learning Rate": 4.972640664603006e-05, "Pretrain/Loss": 2.119659423828125, "Pretrain/Loss (Raw)": 1.9981439113616943, "Pretrain/Step": 722, "Pretrain/Step Time": 8.465362912043929} +{"Pretrain/Learning Rate": 4.972515249869622e-05, "Pretrain/Loss": 2.1208345890045166, "Pretrain/Loss (Raw)": 2.1922318935394287, "Pretrain/Step": 723, "Pretrain/Step Time": 8.465369086712599} +{"Pretrain/Learning Rate": 4.972389549932474e-05, "Pretrain/Loss": 2.119311571121216, "Pretrain/Loss (Raw)": 1.996819019317627, "Pretrain/Step": 724, "Pretrain/Step Time": 8.467588007450104} +{"Pretrain/Learning Rate": 4.97226356480606e-05, "Pretrain/Loss": 2.1178483963012695, "Pretrain/Loss (Raw)": 1.9699801206588745, "Pretrain/Step": 725, "Pretrain/Step Time": 8.467354966327548} +{"Pretrain/Learning Rate": 4.972137294504912e-05, "Pretrain/Loss": 2.120121479034424, "Pretrain/Loss (Raw)": 2.1552836894989014, "Pretrain/Step": 726, "Pretrain/Step Time": 8.465909019112587} +{"Pretrain/Learning Rate": 4.972010739043596e-05, "Pretrain/Loss": 2.121123790740967, "Pretrain/Loss (Raw)": 2.213991165161133, "Pretrain/Step": 727, "Pretrain/Step Time": 8.466671762987971} +{"Pretrain/Learning Rate": 4.97188389843671e-05, "Pretrain/Loss": 2.1205801963806152, "Pretrain/Loss (Raw)": 2.1109180450439453, "Pretrain/Step": 728, "Pretrain/Step Time": 8.469615584239364} +{"Pretrain/Learning Rate": 4.971756772698886e-05, "Pretrain/Loss": 2.120746612548828, "Pretrain/Loss (Raw)": 2.35054349899292, "Pretrain/Step": 729, "Pretrain/Step Time": 8.465789498761296} +{"Pretrain/Learning Rate": 4.971629361844785e-05, "Pretrain/Loss": 2.120486259460449, "Pretrain/Loss (Raw)": 2.157506227493286, "Pretrain/Step": 730, "Pretrain/Step Time": 8.460868764668703} +{"Pretrain/Learning Rate": 4.9715016658891064e-05, "Pretrain/Loss": 2.120370864868164, "Pretrain/Loss (Raw)": 2.0997440814971924, "Pretrain/Step": 731, "Pretrain/Step Time": 8.460509579628706} +{"Pretrain/Learning Rate": 4.97137368484658e-05, "Pretrain/Loss": 2.118712902069092, "Pretrain/Loss (Raw)": 1.9585069417953491, "Pretrain/Step": 732, "Pretrain/Step Time": 8.461249744519591} +{"Pretrain/Learning Rate": 4.9712454187319666e-05, "Pretrain/Loss": 2.1197214126586914, "Pretrain/Loss (Raw)": 2.080430507659912, "Pretrain/Step": 733, "Pretrain/Step Time": 8.459209019318223} +{"Pretrain/Learning Rate": 4.971116867560064e-05, "Pretrain/Loss": 2.1162567138671875, "Pretrain/Loss (Raw)": 1.797402262687683, "Pretrain/Step": 734, "Pretrain/Step Time": 8.462638951838017} +{"Pretrain/Learning Rate": 4.970988031345698e-05, "Pretrain/Loss": 2.116422176361084, "Pretrain/Loss (Raw)": 2.191370964050293, "Pretrain/Step": 735, "Pretrain/Step Time": 8.465271320194006} +{"Pretrain/Learning Rate": 4.9708589101037306e-05, "Pretrain/Loss": 2.1166813373565674, "Pretrain/Loss (Raw)": 2.1058380603790283, "Pretrain/Step": 736, "Pretrain/Step Time": 8.464412605389953} +{"Pretrain/Learning Rate": 4.970729503849058e-05, "Pretrain/Loss": 2.1169333457946777, "Pretrain/Loss (Raw)": 2.1070332527160645, "Pretrain/Step": 737, "Pretrain/Step Time": 8.467099713161588} +{"Pretrain/Learning Rate": 4.970599812596603e-05, "Pretrain/Loss": 2.1175315380096436, "Pretrain/Loss (Raw)": 2.153437852859497, "Pretrain/Step": 738, "Pretrain/Step Time": 8.46442530117929} +{"Pretrain/Learning Rate": 4.9704698363613294e-05, "Pretrain/Loss": 2.1154212951660156, "Pretrain/Loss (Raw)": 2.0248045921325684, "Pretrain/Step": 739, "Pretrain/Step Time": 8.460898814722896} +{"Pretrain/Learning Rate": 4.9703395751582284e-05, "Pretrain/Loss": 2.116252899169922, "Pretrain/Loss (Raw)": 2.168095827102661, "Pretrain/Step": 740, "Pretrain/Step Time": 8.457838414236903} +{"Pretrain/Learning Rate": 4.9702090290023253e-05, "Pretrain/Loss": 2.116438865661621, "Pretrain/Loss (Raw)": 2.1887052059173584, "Pretrain/Step": 741, "Pretrain/Step Time": 8.45700260065496} +{"Pretrain/Learning Rate": 4.970078197908678e-05, "Pretrain/Loss": 2.117461919784546, "Pretrain/Loss (Raw)": 2.091479539871216, "Pretrain/Step": 742, "Pretrain/Step Time": 8.456541763618588} +{"Pretrain/Learning Rate": 4.969947081892379e-05, "Pretrain/Loss": 2.1180224418640137, "Pretrain/Loss (Raw)": 2.200364828109741, "Pretrain/Step": 743, "Pretrain/Step Time": 8.456739047542214} +{"Pretrain/Learning Rate": 4.969815680968553e-05, "Pretrain/Loss": 2.1195883750915527, "Pretrain/Loss (Raw)": 2.1402838230133057, "Pretrain/Step": 744, "Pretrain/Step Time": 8.455803956836462} +{"Pretrain/Learning Rate": 4.969683995152356e-05, "Pretrain/Loss": 2.12015962600708, "Pretrain/Loss (Raw)": 2.1699280738830566, "Pretrain/Step": 745, "Pretrain/Step Time": 8.457330331206322} +{"Pretrain/Learning Rate": 4.969552024458977e-05, "Pretrain/Loss": 2.1209123134613037, "Pretrain/Loss (Raw)": 2.2828776836395264, "Pretrain/Step": 746, "Pretrain/Step Time": 8.457396863028407} +{"Pretrain/Learning Rate": 4.96941976890364e-05, "Pretrain/Loss": 2.120485782623291, "Pretrain/Loss (Raw)": 2.05393648147583, "Pretrain/Step": 747, "Pretrain/Step Time": 8.45795945264399} +{"Pretrain/Learning Rate": 4.969287228501601e-05, "Pretrain/Loss": 2.120480537414551, "Pretrain/Loss (Raw)": 2.171985626220703, "Pretrain/Step": 748, "Pretrain/Step Time": 8.458771016448736} +{"Pretrain/Learning Rate": 4.969154403268148e-05, "Pretrain/Loss": 2.123168706893921, "Pretrain/Loss (Raw)": 2.214898109436035, "Pretrain/Step": 749, "Pretrain/Step Time": 8.460086029022932} +{"Pretrain/Learning Rate": 4.969021293218602e-05, "Pretrain/Loss": 2.1219632625579834, "Pretrain/Loss (Raw)": 1.9435093402862549, "Pretrain/Step": 750, "Pretrain/Step Time": 8.461376838386059} +{"Pretrain/Learning Rate": 4.968887898368318e-05, "Pretrain/Loss": 2.123250961303711, "Pretrain/Loss (Raw)": 2.180004596710205, "Pretrain/Step": 751, "Pretrain/Step Time": 8.462962975725532} +{"Pretrain/Learning Rate": 4.968754218732682e-05, "Pretrain/Loss": 2.1224966049194336, "Pretrain/Loss (Raw)": 2.0402891635894775, "Pretrain/Step": 752, "Pretrain/Step Time": 8.46294180303812} +{"Pretrain/Learning Rate": 4.968620254327115e-05, "Pretrain/Loss": 2.123563528060913, "Pretrain/Loss (Raw)": 2.2363433837890625, "Pretrain/Step": 753, "Pretrain/Step Time": 8.463000323623419} +{"Pretrain/Learning Rate": 4.968486005167069e-05, "Pretrain/Loss": 2.1231918334960938, "Pretrain/Loss (Raw)": 1.960552453994751, "Pretrain/Step": 754, "Pretrain/Step Time": 8.461165325716138} +{"Pretrain/Learning Rate": 4.968351471268029e-05, "Pretrain/Loss": 2.120058059692383, "Pretrain/Loss (Raw)": 1.917807698249817, "Pretrain/Step": 755, "Pretrain/Step Time": 8.457559932023287} +{"Pretrain/Learning Rate": 4.968216652645515e-05, "Pretrain/Loss": 2.1194021701812744, "Pretrain/Loss (Raw)": 2.1192917823791504, "Pretrain/Step": 756, "Pretrain/Step Time": 8.454495156183839} +{"Pretrain/Learning Rate": 4.9680815493150776e-05, "Pretrain/Loss": 2.120968818664551, "Pretrain/Loss (Raw)": 2.101278066635132, "Pretrain/Step": 757, "Pretrain/Step Time": 8.454595217481256} +{"Pretrain/Learning Rate": 4.9679461612923006e-05, "Pretrain/Loss": 2.121396541595459, "Pretrain/Loss (Raw)": 2.1909706592559814, "Pretrain/Step": 758, "Pretrain/Step Time": 8.451053839176893} +{"Pretrain/Learning Rate": 4.9678104885928015e-05, "Pretrain/Loss": 2.119792938232422, "Pretrain/Loss (Raw)": 1.9695014953613281, "Pretrain/Step": 759, "Pretrain/Step Time": 8.45506239682436} +{"Pretrain/Learning Rate": 4.967674531232229e-05, "Pretrain/Loss": 2.119105815887451, "Pretrain/Loss (Raw)": 2.0288853645324707, "Pretrain/Step": 760, "Pretrain/Step Time": 8.455859512090683} +{"Pretrain/Learning Rate": 4.967538289226267e-05, "Pretrain/Loss": 2.1187820434570312, "Pretrain/Loss (Raw)": 2.0654244422912598, "Pretrain/Step": 761, "Pretrain/Step Time": 8.45535871759057} +{"Pretrain/Learning Rate": 4.967401762590631e-05, "Pretrain/Loss": 2.118699550628662, "Pretrain/Loss (Raw)": 2.099663734436035, "Pretrain/Step": 762, "Pretrain/Step Time": 8.454679023474455} +{"Pretrain/Learning Rate": 4.967264951341069e-05, "Pretrain/Loss": 2.1179757118225098, "Pretrain/Loss (Raw)": 2.0419557094573975, "Pretrain/Step": 763, "Pretrain/Step Time": 8.455959467217326} +{"Pretrain/Learning Rate": 4.96712785549336e-05, "Pretrain/Loss": 2.1185975074768066, "Pretrain/Loss (Raw)": 2.281433343887329, "Pretrain/Step": 764, "Pretrain/Step Time": 8.452422708272934} +{"Pretrain/Learning Rate": 4.966990475063321e-05, "Pretrain/Loss": 2.1198785305023193, "Pretrain/Loss (Raw)": 2.0828773975372314, "Pretrain/Step": 765, "Pretrain/Step Time": 8.452131541445851} +{"Pretrain/Learning Rate": 4.9668528100667986e-05, "Pretrain/Loss": 2.121865749359131, "Pretrain/Loss (Raw)": 2.2600533962249756, "Pretrain/Step": 766, "Pretrain/Step Time": 8.454033272340894} +{"Pretrain/Learning Rate": 4.96671486051967e-05, "Pretrain/Loss": 2.121767997741699, "Pretrain/Loss (Raw)": 2.089712381362915, "Pretrain/Step": 767, "Pretrain/Step Time": 8.457200547680259} +{"Pretrain/Learning Rate": 4.96657662643785e-05, "Pretrain/Loss": 2.120666980743408, "Pretrain/Loss (Raw)": 1.9508206844329834, "Pretrain/Step": 768, "Pretrain/Step Time": 8.45459008961916} +{"Pretrain/Learning Rate": 4.966438107837283e-05, "Pretrain/Loss": 2.12192964553833, "Pretrain/Loss (Raw)": 2.156930685043335, "Pretrain/Step": 769, "Pretrain/Step Time": 8.455924844369292} +{"Pretrain/Learning Rate": 4.966299304733947e-05, "Pretrain/Loss": 2.121170997619629, "Pretrain/Loss (Raw)": 1.9766829013824463, "Pretrain/Step": 770, "Pretrain/Step Time": 8.457430176436901} +{"Pretrain/Learning Rate": 4.9661602171438524e-05, "Pretrain/Loss": 2.120258331298828, "Pretrain/Loss (Raw)": 2.11676287651062, "Pretrain/Step": 771, "Pretrain/Step Time": 8.45248412527144} +{"Pretrain/Learning Rate": 4.966020845083044e-05, "Pretrain/Loss": 2.120673656463623, "Pretrain/Loss (Raw)": 2.2415192127227783, "Pretrain/Step": 772, "Pretrain/Step Time": 8.448855813592672} +{"Pretrain/Learning Rate": 4.965881188567597e-05, "Pretrain/Loss": 2.122459888458252, "Pretrain/Loss (Raw)": 2.149919033050537, "Pretrain/Step": 773, "Pretrain/Step Time": 8.450320297852159} +{"Pretrain/Learning Rate": 4.965741247613622e-05, "Pretrain/Loss": 2.1218574047088623, "Pretrain/Loss (Raw)": 2.1656339168548584, "Pretrain/Step": 774, "Pretrain/Step Time": 8.446930922567844} +{"Pretrain/Learning Rate": 4.9656010222372604e-05, "Pretrain/Loss": 2.121523141860962, "Pretrain/Loss (Raw)": 2.015937089920044, "Pretrain/Step": 775, "Pretrain/Step Time": 8.448964182287455} +{"Pretrain/Learning Rate": 4.965460512454687e-05, "Pretrain/Loss": 2.122809648513794, "Pretrain/Loss (Raw)": 2.1785781383514404, "Pretrain/Step": 776, "Pretrain/Step Time": 8.446021048352122} +{"Pretrain/Learning Rate": 4.965319718282111e-05, "Pretrain/Loss": 2.1251494884490967, "Pretrain/Loss (Raw)": 2.403989791870117, "Pretrain/Step": 777, "Pretrain/Step Time": 8.448298586532474} +{"Pretrain/Learning Rate": 4.965178639735771e-05, "Pretrain/Loss": 2.1259403228759766, "Pretrain/Loss (Raw)": 2.1554653644561768, "Pretrain/Step": 778, "Pretrain/Step Time": 8.448802027851343} +{"Pretrain/Learning Rate": 4.965037276831942e-05, "Pretrain/Loss": 2.1257400512695312, "Pretrain/Loss (Raw)": 2.0875141620635986, "Pretrain/Step": 779, "Pretrain/Step Time": 8.450069598853588} +{"Pretrain/Learning Rate": 4.9648956295869284e-05, "Pretrain/Loss": 2.1250996589660645, "Pretrain/Loss (Raw)": 2.211225748062134, "Pretrain/Step": 780, "Pretrain/Step Time": 8.44865476898849} +{"Pretrain/Learning Rate": 4.9647536980170704e-05, "Pretrain/Loss": 2.125962257385254, "Pretrain/Loss (Raw)": 2.252828359603882, "Pretrain/Step": 781, "Pretrain/Step Time": 8.448966039344668} +{"Pretrain/Learning Rate": 4.96461148213874e-05, "Pretrain/Loss": 2.1259877681732178, "Pretrain/Loss (Raw)": 2.02827787399292, "Pretrain/Step": 782, "Pretrain/Step Time": 8.446767386049032} +{"Pretrain/Learning Rate": 4.964468981968341e-05, "Pretrain/Loss": 2.1249990463256836, "Pretrain/Loss (Raw)": 2.075807809829712, "Pretrain/Step": 783, "Pretrain/Step Time": 8.447720730677247} +{"Pretrain/Learning Rate": 4.964326197522311e-05, "Pretrain/Loss": 2.1257739067077637, "Pretrain/Loss (Raw)": 2.2217025756835938, "Pretrain/Step": 784, "Pretrain/Step Time": 8.447858717292547} +{"Pretrain/Learning Rate": 4.96418312881712e-05, "Pretrain/Loss": 2.124208450317383, "Pretrain/Loss (Raw)": 1.9628554582595825, "Pretrain/Step": 785, "Pretrain/Step Time": 8.44853381626308} +{"Pretrain/Learning Rate": 4.9640397758692715e-05, "Pretrain/Loss": 2.1263041496276855, "Pretrain/Loss (Raw)": 2.2293667793273926, "Pretrain/Step": 786, "Pretrain/Step Time": 8.4475387185812} +{"Pretrain/Learning Rate": 4.9638961386953006e-05, "Pretrain/Loss": 2.1265392303466797, "Pretrain/Loss (Raw)": 2.1800596714019775, "Pretrain/Step": 787, "Pretrain/Step Time": 8.451137401163578} +{"Pretrain/Learning Rate": 4.963752217311775e-05, "Pretrain/Loss": 2.125995397567749, "Pretrain/Loss (Raw)": 2.0459389686584473, "Pretrain/Step": 788, "Pretrain/Step Time": 8.4473023917526} +{"Pretrain/Learning Rate": 4.963608011735298e-05, "Pretrain/Loss": 2.1267640590667725, "Pretrain/Loss (Raw)": 2.0633132457733154, "Pretrain/Step": 789, "Pretrain/Step Time": 8.44402153417468} +{"Pretrain/Learning Rate": 4.963463521982503e-05, "Pretrain/Loss": 2.127255916595459, "Pretrain/Loss (Raw)": 2.2394609451293945, "Pretrain/Step": 790, "Pretrain/Step Time": 8.447474723681808} +{"Pretrain/Learning Rate": 4.963318748070056e-05, "Pretrain/Loss": 2.125072956085205, "Pretrain/Loss (Raw)": 2.037257194519043, "Pretrain/Step": 791, "Pretrain/Step Time": 8.444290461018682} +{"Pretrain/Learning Rate": 4.963173690014656e-05, "Pretrain/Loss": 2.1253700256347656, "Pretrain/Loss (Raw)": 2.1731529235839844, "Pretrain/Step": 792, "Pretrain/Step Time": 8.443649535998702} +{"Pretrain/Learning Rate": 4.9630283478330386e-05, "Pretrain/Loss": 2.1239848136901855, "Pretrain/Loss (Raw)": 1.8816007375717163, "Pretrain/Step": 793, "Pretrain/Step Time": 8.44758166000247} +{"Pretrain/Learning Rate": 4.962882721541966e-05, "Pretrain/Loss": 2.124560594558716, "Pretrain/Loss (Raw)": 2.273423910140991, "Pretrain/Step": 794, "Pretrain/Step Time": 8.446789348497987} +{"Pretrain/Learning Rate": 4.9627368111582365e-05, "Pretrain/Loss": 2.123581886291504, "Pretrain/Loss (Raw)": 2.0463709831237793, "Pretrain/Step": 795, "Pretrain/Step Time": 8.444416282698512} +{"Pretrain/Learning Rate": 4.962590616698681e-05, "Pretrain/Loss": 2.123286008834839, "Pretrain/Loss (Raw)": 2.1421892642974854, "Pretrain/Step": 796, "Pretrain/Step Time": 8.447524713352323} +{"Pretrain/Learning Rate": 4.962444138180164e-05, "Pretrain/Loss": 2.122129440307617, "Pretrain/Loss (Raw)": 2.0920493602752686, "Pretrain/Step": 797, "Pretrain/Step Time": 8.447365313768387} +{"Pretrain/Learning Rate": 4.962297375619581e-05, "Pretrain/Loss": 2.121755361557007, "Pretrain/Loss (Raw)": 2.1985843181610107, "Pretrain/Step": 798, "Pretrain/Step Time": 8.4461374823004} +{"Pretrain/Learning Rate": 4.962150329033861e-05, "Pretrain/Loss": 2.1226789951324463, "Pretrain/Loss (Raw)": 2.3284995555877686, "Pretrain/Step": 799, "Pretrain/Step Time": 8.450506784021854} +{"Pretrain/Learning Rate": 4.962002998439965e-05, "Pretrain/Loss": 2.1256797313690186, "Pretrain/Loss (Raw)": 2.3843724727630615, "Pretrain/Step": 800, "Pretrain/Step Time": 8.45012298412621} +{"Pretrain/Learning Rate": 4.961855383854889e-05, "Pretrain/Loss": 2.126938819885254, "Pretrain/Loss (Raw)": 2.198885917663574, "Pretrain/Step": 801, "Pretrain/Step Time": 8.45156510360539} +{"Pretrain/Learning Rate": 4.96170748529566e-05, "Pretrain/Loss": 2.1259498596191406, "Pretrain/Loss (Raw)": 2.1032965183258057, "Pretrain/Step": 802, "Pretrain/Step Time": 8.451580321416259} +{"Pretrain/Learning Rate": 4.9615593027793374e-05, "Pretrain/Loss": 2.126600742340088, "Pretrain/Loss (Raw)": 2.107931613922119, "Pretrain/Step": 803, "Pretrain/Step Time": 8.450373468920588} +{"Pretrain/Learning Rate": 4.9614108363230135e-05, "Pretrain/Loss": 2.125882863998413, "Pretrain/Loss (Raw)": 2.119804620742798, "Pretrain/Step": 804, "Pretrain/Step Time": 8.451335780322552} +{"Pretrain/Learning Rate": 4.961262085943815e-05, "Pretrain/Loss": 2.126146078109741, "Pretrain/Loss (Raw)": 2.080612897872925, "Pretrain/Step": 805, "Pretrain/Step Time": 8.45110228098929} +{"Pretrain/Learning Rate": 4.961113051658901e-05, "Pretrain/Loss": 2.126439094543457, "Pretrain/Loss (Raw)": 2.094541072845459, "Pretrain/Step": 806, "Pretrain/Step Time": 8.452643981203437} +{"Pretrain/Learning Rate": 4.9609637334854596e-05, "Pretrain/Loss": 2.1276233196258545, "Pretrain/Loss (Raw)": 2.1840624809265137, "Pretrain/Step": 807, "Pretrain/Step Time": 8.453621290624142} +{"Pretrain/Learning Rate": 4.9608141314407174e-05, "Pretrain/Loss": 2.128005027770996, "Pretrain/Loss (Raw)": 2.0412228107452393, "Pretrain/Step": 808, "Pretrain/Step Time": 8.449831632897258} +{"Pretrain/Learning Rate": 4.960664245541931e-05, "Pretrain/Loss": 2.127272844314575, "Pretrain/Loss (Raw)": 2.100093126296997, "Pretrain/Step": 809, "Pretrain/Step Time": 8.451916990801692} +{"Pretrain/Learning Rate": 4.9605140758063866e-05, "Pretrain/Loss": 2.128422737121582, "Pretrain/Loss (Raw)": 2.2191550731658936, "Pretrain/Step": 810, "Pretrain/Step Time": 8.453477799892426} +{"Pretrain/Learning Rate": 4.960363622251409e-05, "Pretrain/Loss": 2.1280014514923096, "Pretrain/Loss (Raw)": 2.1288294792175293, "Pretrain/Step": 811, "Pretrain/Step Time": 8.45603922009468} +{"Pretrain/Learning Rate": 4.960212884894352e-05, "Pretrain/Loss": 2.127777099609375, "Pretrain/Loss (Raw)": 2.029257297515869, "Pretrain/Step": 812, "Pretrain/Step Time": 8.455678962171078} +{"Pretrain/Learning Rate": 4.960061863752604e-05, "Pretrain/Loss": 2.1281042098999023, "Pretrain/Loss (Raw)": 2.149390697479248, "Pretrain/Step": 813, "Pretrain/Step Time": 8.455482741817832} +{"Pretrain/Learning Rate": 4.9599105588435846e-05, "Pretrain/Loss": 2.1268093585968018, "Pretrain/Loss (Raw)": 2.1419155597686768, "Pretrain/Step": 814, "Pretrain/Step Time": 8.458265956491232} +{"Pretrain/Learning Rate": 4.959758970184746e-05, "Pretrain/Loss": 2.127331256866455, "Pretrain/Loss (Raw)": 2.130640745162964, "Pretrain/Step": 815, "Pretrain/Step Time": 8.4561985488981} +{"Pretrain/Learning Rate": 4.959607097793575e-05, "Pretrain/Loss": 2.1262240409851074, "Pretrain/Loss (Raw)": 2.0549142360687256, "Pretrain/Step": 816, "Pretrain/Step Time": 8.459658032283187} +{"Pretrain/Learning Rate": 4.959454941687589e-05, "Pretrain/Loss": 2.1241259574890137, "Pretrain/Loss (Raw)": 2.02839732170105, "Pretrain/Step": 817, "Pretrain/Step Time": 8.456817492842674} +{"Pretrain/Learning Rate": 4.9593025018843406e-05, "Pretrain/Loss": 2.1238622665405273, "Pretrain/Loss (Raw)": 1.949257493019104, "Pretrain/Step": 818, "Pretrain/Step Time": 8.459487833082676} +{"Pretrain/Learning Rate": 4.959149778401412e-05, "Pretrain/Loss": 2.1234614849090576, "Pretrain/Loss (Raw)": 2.1092889308929443, "Pretrain/Step": 819, "Pretrain/Step Time": 8.460535056889057} +{"Pretrain/Learning Rate": 4.958996771256422e-05, "Pretrain/Loss": 2.1242668628692627, "Pretrain/Loss (Raw)": 2.2151472568511963, "Pretrain/Step": 820, "Pretrain/Step Time": 8.454945873469114} +{"Pretrain/Learning Rate": 4.9588434804670174e-05, "Pretrain/Loss": 2.123310089111328, "Pretrain/Loss (Raw)": 1.9713751077651978, "Pretrain/Step": 821, "Pretrain/Step Time": 8.456463376060128} +{"Pretrain/Learning Rate": 4.958689906050882e-05, "Pretrain/Loss": 2.1244654655456543, "Pretrain/Loss (Raw)": 2.165921449661255, "Pretrain/Step": 822, "Pretrain/Step Time": 8.454811545088887} +{"Pretrain/Learning Rate": 4.95853604802573e-05, "Pretrain/Loss": 2.1259403228759766, "Pretrain/Loss (Raw)": 2.3805181980133057, "Pretrain/Step": 823, "Pretrain/Step Time": 8.453804766759276} +{"Pretrain/Learning Rate": 4.958381906409308e-05, "Pretrain/Loss": 2.125566005706787, "Pretrain/Loss (Raw)": 2.186467170715332, "Pretrain/Step": 824, "Pretrain/Step Time": 8.453662365674973} +{"Pretrain/Learning Rate": 4.9582274812193984e-05, "Pretrain/Loss": 2.124741315841675, "Pretrain/Loss (Raw)": 2.0874154567718506, "Pretrain/Step": 825, "Pretrain/Step Time": 8.45182403922081} +{"Pretrain/Learning Rate": 4.958072772473812e-05, "Pretrain/Loss": 2.124915599822998, "Pretrain/Loss (Raw)": 2.203221559524536, "Pretrain/Step": 826, "Pretrain/Step Time": 8.45464383251965} +{"Pretrain/Learning Rate": 4.9579177801903945e-05, "Pretrain/Loss": 2.1263267993927, "Pretrain/Loss (Raw)": 2.1620190143585205, "Pretrain/Step": 827, "Pretrain/Step Time": 8.451117467135191} +{"Pretrain/Learning Rate": 4.9577625043870255e-05, "Pretrain/Loss": 2.1248297691345215, "Pretrain/Loss (Raw)": 2.004117488861084, "Pretrain/Step": 828, "Pretrain/Step Time": 8.451274940744042} +{"Pretrain/Learning Rate": 4.957606945081615e-05, "Pretrain/Loss": 2.125542163848877, "Pretrain/Loss (Raw)": 2.1634018421173096, "Pretrain/Step": 829, "Pretrain/Step Time": 8.447530409321189} +{"Pretrain/Learning Rate": 4.957451102292108e-05, "Pretrain/Loss": 2.1245217323303223, "Pretrain/Loss (Raw)": 2.0143167972564697, "Pretrain/Step": 830, "Pretrain/Step Time": 8.445660397410393} +{"Pretrain/Learning Rate": 4.9572949760364795e-05, "Pretrain/Loss": 2.1248395442962646, "Pretrain/Loss (Raw)": 2.148165702819824, "Pretrain/Step": 831, "Pretrain/Step Time": 8.442419309169054} +{"Pretrain/Learning Rate": 4.957138566332739e-05, "Pretrain/Loss": 2.1266677379608154, "Pretrain/Loss (Raw)": 2.2076940536499023, "Pretrain/Step": 832, "Pretrain/Step Time": 8.440225601196289} +{"Pretrain/Learning Rate": 4.956981873198928e-05, "Pretrain/Loss": 2.1264309883117676, "Pretrain/Loss (Raw)": 2.119293212890625, "Pretrain/Step": 833, "Pretrain/Step Time": 8.441463019698858} +{"Pretrain/Learning Rate": 4.956824896653122e-05, "Pretrain/Loss": 2.1264424324035645, "Pretrain/Loss (Raw)": 2.135011672973633, "Pretrain/Step": 834, "Pretrain/Step Time": 8.440967669710517} +{"Pretrain/Learning Rate": 4.956667636713427e-05, "Pretrain/Loss": 2.1264114379882812, "Pretrain/Loss (Raw)": 2.105072021484375, "Pretrain/Step": 835, "Pretrain/Step Time": 8.442188151180744} +{"Pretrain/Learning Rate": 4.956510093397983e-05, "Pretrain/Loss": 2.124480724334717, "Pretrain/Loss (Raw)": 1.9759931564331055, "Pretrain/Step": 836, "Pretrain/Step Time": 8.443529326468706} +{"Pretrain/Learning Rate": 4.956352266724964e-05, "Pretrain/Loss": 2.12393856048584, "Pretrain/Loss (Raw)": 2.0491323471069336, "Pretrain/Step": 837, "Pretrain/Step Time": 8.442216968163848} +{"Pretrain/Learning Rate": 4.9561941567125736e-05, "Pretrain/Loss": 2.1235194206237793, "Pretrain/Loss (Raw)": 2.2344136238098145, "Pretrain/Step": 838, "Pretrain/Step Time": 8.438812769949436} +{"Pretrain/Learning Rate": 4.956035763379051e-05, "Pretrain/Loss": 2.1222939491271973, "Pretrain/Loss (Raw)": 2.0342042446136475, "Pretrain/Step": 839, "Pretrain/Step Time": 8.439668502658606} +{"Pretrain/Learning Rate": 4.955877086742666e-05, "Pretrain/Loss": 2.1204075813293457, "Pretrain/Loss (Raw)": 1.9559073448181152, "Pretrain/Step": 840, "Pretrain/Step Time": 8.442242620512843} +{"Pretrain/Learning Rate": 4.9557181268217227e-05, "Pretrain/Loss": 2.1188135147094727, "Pretrain/Loss (Raw)": 1.993486762046814, "Pretrain/Step": 841, "Pretrain/Step Time": 8.445339191704988} +{"Pretrain/Learning Rate": 4.955558883634555e-05, "Pretrain/Loss": 2.1188340187072754, "Pretrain/Loss (Raw)": 2.127359628677368, "Pretrain/Step": 842, "Pretrain/Step Time": 8.442824559286237} +{"Pretrain/Learning Rate": 4.955399357199534e-05, "Pretrain/Loss": 2.1204543113708496, "Pretrain/Loss (Raw)": 2.25205659866333, "Pretrain/Step": 843, "Pretrain/Step Time": 8.442150611430407} +{"Pretrain/Learning Rate": 4.95523954753506e-05, "Pretrain/Loss": 2.1194560527801514, "Pretrain/Loss (Raw)": 2.166914463043213, "Pretrain/Step": 844, "Pretrain/Step Time": 8.44041476212442} +{"Pretrain/Learning Rate": 4.9550794546595664e-05, "Pretrain/Loss": 2.1190028190612793, "Pretrain/Loss (Raw)": 2.1267309188842773, "Pretrain/Step": 845, "Pretrain/Step Time": 8.441992482170463} +{"Pretrain/Learning Rate": 4.954919078591521e-05, "Pretrain/Loss": 2.1178722381591797, "Pretrain/Loss (Raw)": 2.0703837871551514, "Pretrain/Step": 846, "Pretrain/Step Time": 8.442724073305726} +{"Pretrain/Learning Rate": 4.9547584193494224e-05, "Pretrain/Loss": 2.1178059577941895, "Pretrain/Loss (Raw)": 2.0233678817749023, "Pretrain/Step": 847, "Pretrain/Step Time": 8.441456571221352} +{"Pretrain/Learning Rate": 4.9545974769518033e-05, "Pretrain/Loss": 2.118079423904419, "Pretrain/Loss (Raw)": 2.108088493347168, "Pretrain/Step": 848, "Pretrain/Step Time": 8.442527644336224} +{"Pretrain/Learning Rate": 4.954436251417227e-05, "Pretrain/Loss": 2.118070602416992, "Pretrain/Loss (Raw)": 2.130125045776367, "Pretrain/Step": 849, "Pretrain/Step Time": 8.444356018677354} +{"Pretrain/Learning Rate": 4.9542747427642924e-05, "Pretrain/Loss": 2.1180973052978516, "Pretrain/Loss (Raw)": 2.0015711784362793, "Pretrain/Step": 850, "Pretrain/Step Time": 8.441422605887055} +{"Pretrain/Learning Rate": 4.954112951011628e-05, "Pretrain/Loss": 2.1165475845336914, "Pretrain/Loss (Raw)": 1.9938889741897583, "Pretrain/Step": 851, "Pretrain/Step Time": 8.441374888643622} +{"Pretrain/Learning Rate": 4.953950876177898e-05, "Pretrain/Loss": 2.116936683654785, "Pretrain/Loss (Raw)": 2.0465972423553467, "Pretrain/Step": 852, "Pretrain/Step Time": 8.443098746240139} +{"Pretrain/Learning Rate": 4.953788518281796e-05, "Pretrain/Loss": 2.116994619369507, "Pretrain/Loss (Raw)": 1.9774384498596191, "Pretrain/Step": 853, "Pretrain/Step Time": 8.444281853735447} +{"Pretrain/Learning Rate": 4.953625877342051e-05, "Pretrain/Loss": 2.1169486045837402, "Pretrain/Loss (Raw)": 2.14937162399292, "Pretrain/Step": 854, "Pretrain/Step Time": 8.445895167067647} +{"Pretrain/Learning Rate": 4.9534629533774235e-05, "Pretrain/Loss": 2.115922689437866, "Pretrain/Loss (Raw)": 2.082674980163574, "Pretrain/Step": 855, "Pretrain/Step Time": 8.442609243094921} +{"Pretrain/Learning Rate": 4.9532997464067065e-05, "Pretrain/Loss": 2.1168911457061768, "Pretrain/Loss (Raw)": 2.234882116317749, "Pretrain/Step": 856, "Pretrain/Step Time": 8.440644880756736} +{"Pretrain/Learning Rate": 4.953136256448726e-05, "Pretrain/Loss": 2.1142468452453613, "Pretrain/Loss (Raw)": 2.0120723247528076, "Pretrain/Step": 857, "Pretrain/Step Time": 8.441943928599358} +{"Pretrain/Learning Rate": 4.9529724835223404e-05, "Pretrain/Loss": 2.114072561264038, "Pretrain/Loss (Raw)": 2.1351847648620605, "Pretrain/Step": 858, "Pretrain/Step Time": 8.439185604453087} +{"Pretrain/Learning Rate": 4.9528084276464406e-05, "Pretrain/Loss": 2.116490125656128, "Pretrain/Loss (Raw)": 2.4092180728912354, "Pretrain/Step": 859, "Pretrain/Step Time": 8.43559911288321} +{"Pretrain/Learning Rate": 4.9526440888399506e-05, "Pretrain/Loss": 2.1189706325531006, "Pretrain/Loss (Raw)": 2.275994300842285, "Pretrain/Step": 860, "Pretrain/Step Time": 8.43520686775446} +{"Pretrain/Learning Rate": 4.952479467121827e-05, "Pretrain/Loss": 2.1197094917297363, "Pretrain/Loss (Raw)": 2.175025224685669, "Pretrain/Step": 861, "Pretrain/Step Time": 8.438189677894115} +{"Pretrain/Learning Rate": 4.952314562511059e-05, "Pretrain/Loss": 2.1209616661071777, "Pretrain/Loss (Raw)": 1.9576667547225952, "Pretrain/Step": 862, "Pretrain/Step Time": 8.435253107920289} +{"Pretrain/Learning Rate": 4.952149375026668e-05, "Pretrain/Loss": 2.121351718902588, "Pretrain/Loss (Raw)": 2.241288423538208, "Pretrain/Step": 863, "Pretrain/Step Time": 8.432725897058845} +{"Pretrain/Learning Rate": 4.951983904687708e-05, "Pretrain/Loss": 2.1209402084350586, "Pretrain/Loss (Raw)": 2.053187608718872, "Pretrain/Step": 864, "Pretrain/Step Time": 8.435496658086777} +{"Pretrain/Learning Rate": 4.9518181515132666e-05, "Pretrain/Loss": 2.1206297874450684, "Pretrain/Loss (Raw)": 2.0672829151153564, "Pretrain/Step": 865, "Pretrain/Step Time": 8.432615710422397} +{"Pretrain/Learning Rate": 4.9516521155224625e-05, "Pretrain/Loss": 2.1205215454101562, "Pretrain/Loss (Raw)": 2.1395649909973145, "Pretrain/Step": 866, "Pretrain/Step Time": 8.432449886575341} +{"Pretrain/Learning Rate": 4.951485796734449e-05, "Pretrain/Loss": 2.1197917461395264, "Pretrain/Loss (Raw)": 1.9314167499542236, "Pretrain/Step": 867, "Pretrain/Step Time": 8.432263439521194} +{"Pretrain/Learning Rate": 4.95131919516841e-05, "Pretrain/Loss": 2.1195545196533203, "Pretrain/Loss (Raw)": 2.1377029418945312, "Pretrain/Step": 868, "Pretrain/Step Time": 8.434127733111382} +{"Pretrain/Learning Rate": 4.951152310843564e-05, "Pretrain/Loss": 2.119325637817383, "Pretrain/Loss (Raw)": 2.1594295501708984, "Pretrain/Step": 869, "Pretrain/Step Time": 8.437875807285309} +{"Pretrain/Learning Rate": 4.950985143779159e-05, "Pretrain/Loss": 2.11938738822937, "Pretrain/Loss (Raw)": 2.0993781089782715, "Pretrain/Step": 870, "Pretrain/Step Time": 8.438177661970258} +{"Pretrain/Learning Rate": 4.950817693994481e-05, "Pretrain/Loss": 2.118387460708618, "Pretrain/Loss (Raw)": 2.0723717212677, "Pretrain/Step": 871, "Pretrain/Step Time": 8.438779896125197} +{"Pretrain/Learning Rate": 4.950649961508841e-05, "Pretrain/Loss": 2.1178102493286133, "Pretrain/Loss (Raw)": 2.0664238929748535, "Pretrain/Step": 872, "Pretrain/Step Time": 8.437430337071419} +{"Pretrain/Learning Rate": 4.9504819463415906e-05, "Pretrain/Loss": 2.117976188659668, "Pretrain/Loss (Raw)": 2.1911399364471436, "Pretrain/Step": 873, "Pretrain/Step Time": 8.438202198594809} +{"Pretrain/Learning Rate": 4.950313648512108e-05, "Pretrain/Loss": 2.1159586906433105, "Pretrain/Loss (Raw)": 2.024655818939209, "Pretrain/Step": 874, "Pretrain/Step Time": 8.436106594279408} +{"Pretrain/Learning Rate": 4.9501450680398084e-05, "Pretrain/Loss": 2.1167054176330566, "Pretrain/Loss (Raw)": 2.1495213508605957, "Pretrain/Step": 875, "Pretrain/Step Time": 8.434956701472402} +{"Pretrain/Learning Rate": 4.949976204944135e-05, "Pretrain/Loss": 2.1147782802581787, "Pretrain/Loss (Raw)": 1.925307035446167, "Pretrain/Step": 876, "Pretrain/Step Time": 8.433556044474244} +{"Pretrain/Learning Rate": 4.949807059244568e-05, "Pretrain/Loss": 2.1142396926879883, "Pretrain/Loss (Raw)": 2.1459543704986572, "Pretrain/Step": 877, "Pretrain/Step Time": 8.431620888411999} +{"Pretrain/Learning Rate": 4.949637630960617e-05, "Pretrain/Loss": 2.1164662837982178, "Pretrain/Loss (Raw)": 2.2285068035125732, "Pretrain/Step": 878, "Pretrain/Step Time": 8.431340549141169} +{"Pretrain/Learning Rate": 4.949467920111827e-05, "Pretrain/Loss": 2.115999221801758, "Pretrain/Loss (Raw)": 2.1202406883239746, "Pretrain/Step": 879, "Pretrain/Step Time": 8.430727008730173} +{"Pretrain/Learning Rate": 4.949297926717773e-05, "Pretrain/Loss": 2.1159610748291016, "Pretrain/Loss (Raw)": 2.0353810787200928, "Pretrain/Step": 880, "Pretrain/Step Time": 8.431553350761533} +{"Pretrain/Learning Rate": 4.949127650798063e-05, "Pretrain/Loss": 2.114500045776367, "Pretrain/Loss (Raw)": 2.0493478775024414, "Pretrain/Step": 881, "Pretrain/Step Time": 8.436563685536385} +{"Pretrain/Learning Rate": 4.9489570923723404e-05, "Pretrain/Loss": 2.115841865539551, "Pretrain/Loss (Raw)": 2.132300615310669, "Pretrain/Step": 882, "Pretrain/Step Time": 8.43418139591813} +{"Pretrain/Learning Rate": 4.948786251460277e-05, "Pretrain/Loss": 2.1161231994628906, "Pretrain/Loss (Raw)": 1.9538354873657227, "Pretrain/Step": 883, "Pretrain/Step Time": 8.435590816661716} +{"Pretrain/Learning Rate": 4.948615128081581e-05, "Pretrain/Loss": 2.1162679195404053, "Pretrain/Loss (Raw)": 2.137796640396118, "Pretrain/Step": 884, "Pretrain/Step Time": 8.437688324600458} +{"Pretrain/Learning Rate": 4.94844372225599e-05, "Pretrain/Loss": 2.1157402992248535, "Pretrain/Loss (Raw)": 2.0337352752685547, "Pretrain/Step": 885, "Pretrain/Step Time": 8.4374321103096} +{"Pretrain/Learning Rate": 4.948272034003275e-05, "Pretrain/Loss": 2.1150214672088623, "Pretrain/Loss (Raw)": 2.098961114883423, "Pretrain/Step": 886, "Pretrain/Step Time": 8.442894579842687} +{"Pretrain/Learning Rate": 4.948100063343243e-05, "Pretrain/Loss": 2.1152210235595703, "Pretrain/Loss (Raw)": 1.9950618743896484, "Pretrain/Step": 887, "Pretrain/Step Time": 8.44005717150867} +{"Pretrain/Learning Rate": 4.947927810295728e-05, "Pretrain/Loss": 2.116837501525879, "Pretrain/Loss (Raw)": 2.2358078956604004, "Pretrain/Step": 888, "Pretrain/Step Time": 8.43908373452723} +{"Pretrain/Learning Rate": 4.9477552748805996e-05, "Pretrain/Loss": 2.1172428131103516, "Pretrain/Loss (Raw)": 2.117285966873169, "Pretrain/Step": 889, "Pretrain/Step Time": 8.43975386209786} +{"Pretrain/Learning Rate": 4.947582457117762e-05, "Pretrain/Loss": 2.1175737380981445, "Pretrain/Loss (Raw)": 2.141997814178467, "Pretrain/Step": 890, "Pretrain/Step Time": 8.440966978669167} +{"Pretrain/Learning Rate": 4.947409357027147e-05, "Pretrain/Loss": 2.1190929412841797, "Pretrain/Loss (Raw)": 2.2364296913146973, "Pretrain/Step": 891, "Pretrain/Step Time": 8.435963219031692} +{"Pretrain/Learning Rate": 4.947235974628724e-05, "Pretrain/Loss": 2.116971015930176, "Pretrain/Loss (Raw)": 2.009831666946411, "Pretrain/Step": 892, "Pretrain/Step Time": 8.434330891817808} +{"Pretrain/Learning Rate": 4.947062309942491e-05, "Pretrain/Loss": 2.1176702976226807, "Pretrain/Loss (Raw)": 2.172377824783325, "Pretrain/Step": 893, "Pretrain/Step Time": 8.437696812674403} +{"Pretrain/Learning Rate": 4.946888362988479e-05, "Pretrain/Loss": 2.1158523559570312, "Pretrain/Loss (Raw)": 2.0273842811584473, "Pretrain/Step": 894, "Pretrain/Step Time": 8.43368716724217} +{"Pretrain/Learning Rate": 4.9467141337867556e-05, "Pretrain/Loss": 2.116668462753296, "Pretrain/Loss (Raw)": 2.194155216217041, "Pretrain/Step": 895, "Pretrain/Step Time": 8.43313536606729} +{"Pretrain/Learning Rate": 4.946539622357417e-05, "Pretrain/Loss": 2.118196964263916, "Pretrain/Loss (Raw)": 2.146496057510376, "Pretrain/Step": 896, "Pretrain/Step Time": 8.435481637716293} +{"Pretrain/Learning Rate": 4.9463648287205924e-05, "Pretrain/Loss": 2.118203639984131, "Pretrain/Loss (Raw)": 2.1577818393707275, "Pretrain/Step": 897, "Pretrain/Step Time": 8.43235763348639} +{"Pretrain/Learning Rate": 4.946189752896444e-05, "Pretrain/Loss": 2.1185197830200195, "Pretrain/Loss (Raw)": 2.0171375274658203, "Pretrain/Step": 898, "Pretrain/Step Time": 8.434991439804435} +{"Pretrain/Learning Rate": 4.946014394905167e-05, "Pretrain/Loss": 2.1186115741729736, "Pretrain/Loss (Raw)": 2.128493547439575, "Pretrain/Step": 899, "Pretrain/Step Time": 8.437196537852287} +{"Pretrain/Learning Rate": 4.94583875476699e-05, "Pretrain/Loss": 2.1167941093444824, "Pretrain/Loss (Raw)": 2.0088746547698975, "Pretrain/Step": 900, "Pretrain/Step Time": 8.436168614774942} +{"Pretrain/Learning Rate": 4.9456628325021714e-05, "Pretrain/Loss": 2.1174590587615967, "Pretrain/Loss (Raw)": 2.23504900932312, "Pretrain/Step": 901, "Pretrain/Step Time": 8.438365943729877} +{"Pretrain/Learning Rate": 4.945486628131005e-05, "Pretrain/Loss": 2.116802215576172, "Pretrain/Loss (Raw)": 2.0815420150756836, "Pretrain/Step": 902, "Pretrain/Step Time": 8.439382480457425} +{"Pretrain/Learning Rate": 4.9453101416738155e-05, "Pretrain/Loss": 2.118131399154663, "Pretrain/Loss (Raw)": 2.1860668659210205, "Pretrain/Step": 903, "Pretrain/Step Time": 8.439754841849208} +{"Pretrain/Learning Rate": 4.945133373150961e-05, "Pretrain/Loss": 2.1179137229919434, "Pretrain/Loss (Raw)": 2.1507303714752197, "Pretrain/Step": 904, "Pretrain/Step Time": 8.44006939791143} +{"Pretrain/Learning Rate": 4.94495632258283e-05, "Pretrain/Loss": 2.116255760192871, "Pretrain/Loss (Raw)": 2.1918020248413086, "Pretrain/Step": 905, "Pretrain/Step Time": 8.44008956849575} +{"Pretrain/Learning Rate": 4.944778989989847e-05, "Pretrain/Loss": 2.115527868270874, "Pretrain/Loss (Raw)": 2.062260150909424, "Pretrain/Step": 906, "Pretrain/Step Time": 8.437432397156954} +{"Pretrain/Learning Rate": 4.944601375392467e-05, "Pretrain/Loss": 2.1160030364990234, "Pretrain/Loss (Raw)": 2.1483373641967773, "Pretrain/Step": 907, "Pretrain/Step Time": 8.439063984900713} +{"Pretrain/Learning Rate": 4.944423478811177e-05, "Pretrain/Loss": 2.1150174140930176, "Pretrain/Loss (Raw)": 2.085066080093384, "Pretrain/Step": 908, "Pretrain/Step Time": 8.439417108893394} +{"Pretrain/Learning Rate": 4.944245300266498e-05, "Pretrain/Loss": 2.113218069076538, "Pretrain/Loss (Raw)": 2.0225229263305664, "Pretrain/Step": 909, "Pretrain/Step Time": 8.442086458206177} +{"Pretrain/Learning Rate": 4.944066839778982e-05, "Pretrain/Loss": 2.1140270233154297, "Pretrain/Loss (Raw)": 2.131830930709839, "Pretrain/Step": 910, "Pretrain/Step Time": 8.443662455305457} +{"Pretrain/Learning Rate": 4.943888097369216e-05, "Pretrain/Loss": 2.1156251430511475, "Pretrain/Loss (Raw)": 2.2803421020507812, "Pretrain/Step": 911, "Pretrain/Step Time": 8.442473597824574} +{"Pretrain/Learning Rate": 4.943709073057816e-05, "Pretrain/Loss": 2.1142263412475586, "Pretrain/Loss (Raw)": 2.042651891708374, "Pretrain/Step": 912, "Pretrain/Step Time": 8.440543493255973} +{"Pretrain/Learning Rate": 4.943529766865434e-05, "Pretrain/Loss": 2.1163105964660645, "Pretrain/Loss (Raw)": 2.2296860218048096, "Pretrain/Step": 913, "Pretrain/Step Time": 8.446365270763636} +{"Pretrain/Learning Rate": 4.9433501788127514e-05, "Pretrain/Loss": 2.114767074584961, "Pretrain/Loss (Raw)": 2.0317747592926025, "Pretrain/Step": 914, "Pretrain/Step Time": 8.445064444094896} +{"Pretrain/Learning Rate": 4.943170308920484e-05, "Pretrain/Loss": 2.114531993865967, "Pretrain/Loss (Raw)": 2.1499626636505127, "Pretrain/Step": 915, "Pretrain/Step Time": 8.446238109841943} +{"Pretrain/Learning Rate": 4.9429901572093807e-05, "Pretrain/Loss": 2.1149401664733887, "Pretrain/Loss (Raw)": 2.098193407058716, "Pretrain/Step": 916, "Pretrain/Step Time": 8.442989712581038} +{"Pretrain/Learning Rate": 4.942809723700221e-05, "Pretrain/Loss": 2.115400552749634, "Pretrain/Loss (Raw)": 2.1222479343414307, "Pretrain/Step": 917, "Pretrain/Step Time": 8.445581167936325} +{"Pretrain/Learning Rate": 4.9426290084138186e-05, "Pretrain/Loss": 2.1149978637695312, "Pretrain/Loss (Raw)": 2.187885284423828, "Pretrain/Step": 918, "Pretrain/Step Time": 8.44325115531683} +{"Pretrain/Learning Rate": 4.9424480113710175e-05, "Pretrain/Loss": 2.1155073642730713, "Pretrain/Loss (Raw)": 2.102471351623535, "Pretrain/Step": 919, "Pretrain/Step Time": 8.444865707308054} +{"Pretrain/Learning Rate": 4.9422667325926975e-05, "Pretrain/Loss": 2.115671157836914, "Pretrain/Loss (Raw)": 2.1941168308258057, "Pretrain/Step": 920, "Pretrain/Step Time": 8.446883287280798} +{"Pretrain/Learning Rate": 4.9420851720997676e-05, "Pretrain/Loss": 2.115248680114746, "Pretrain/Loss (Raw)": 1.8275678157806396, "Pretrain/Step": 921, "Pretrain/Step Time": 8.44375172443688} +{"Pretrain/Learning Rate": 4.941903329913172e-05, "Pretrain/Loss": 2.114123582839966, "Pretrain/Loss (Raw)": 2.129384756088257, "Pretrain/Step": 922, "Pretrain/Step Time": 8.442570241168141} +{"Pretrain/Learning Rate": 4.9417212060538845e-05, "Pretrain/Loss": 2.1151933670043945, "Pretrain/Loss (Raw)": 2.183304786682129, "Pretrain/Step": 923, "Pretrain/Step Time": 8.447273133322597} +{"Pretrain/Learning Rate": 4.9415388005429144e-05, "Pretrain/Loss": 2.1147971153259277, "Pretrain/Loss (Raw)": 2.0914487838745117, "Pretrain/Step": 924, "Pretrain/Step Time": 8.440799126401544} +{"Pretrain/Learning Rate": 4.941356113401302e-05, "Pretrain/Loss": 2.115565299987793, "Pretrain/Loss (Raw)": 2.190396308898926, "Pretrain/Step": 925, "Pretrain/Step Time": 8.44035337306559} +{"Pretrain/Learning Rate": 4.94117314465012e-05, "Pretrain/Loss": 2.115469455718994, "Pretrain/Loss (Raw)": 2.1863317489624023, "Pretrain/Step": 926, "Pretrain/Step Time": 8.44342995248735} +{"Pretrain/Learning Rate": 4.940989894310473e-05, "Pretrain/Loss": 2.11259388923645, "Pretrain/Loss (Raw)": 1.9604160785675049, "Pretrain/Step": 927, "Pretrain/Step Time": 8.43645889684558} +{"Pretrain/Learning Rate": 4.9408063624034994e-05, "Pretrain/Loss": 2.1104631423950195, "Pretrain/Loss (Raw)": 2.111643075942993, "Pretrain/Step": 928, "Pretrain/Step Time": 8.438429035246372} +{"Pretrain/Learning Rate": 4.9406225489503704e-05, "Pretrain/Loss": 2.1092987060546875, "Pretrain/Loss (Raw)": 2.0498266220092773, "Pretrain/Step": 929, "Pretrain/Step Time": 8.436480278149247} +{"Pretrain/Learning Rate": 4.940438453972288e-05, "Pretrain/Loss": 2.109553337097168, "Pretrain/Loss (Raw)": 2.1358954906463623, "Pretrain/Step": 930, "Pretrain/Step Time": 8.436305226758122} +{"Pretrain/Learning Rate": 4.940254077490487e-05, "Pretrain/Loss": 2.108370304107666, "Pretrain/Loss (Raw)": 1.9564851522445679, "Pretrain/Step": 931, "Pretrain/Step Time": 8.439309608191252} +{"Pretrain/Learning Rate": 4.9400694195262365e-05, "Pretrain/Loss": 2.1084516048431396, "Pretrain/Loss (Raw)": 2.1302433013916016, "Pretrain/Step": 932, "Pretrain/Step Time": 8.435599762946367} +{"Pretrain/Learning Rate": 4.9398844801008354e-05, "Pretrain/Loss": 2.108767032623291, "Pretrain/Loss (Raw)": 2.121004104614258, "Pretrain/Step": 933, "Pretrain/Step Time": 8.439023518934846} +{"Pretrain/Learning Rate": 4.9396992592356174e-05, "Pretrain/Loss": 2.1080398559570312, "Pretrain/Loss (Raw)": 2.0014171600341797, "Pretrain/Step": 934, "Pretrain/Step Time": 8.44016975723207} +{"Pretrain/Learning Rate": 4.939513756951947e-05, "Pretrain/Loss": 2.1071271896362305, "Pretrain/Loss (Raw)": 2.0672497749328613, "Pretrain/Step": 935, "Pretrain/Step Time": 8.436678890138865} +{"Pretrain/Learning Rate": 4.939327973271221e-05, "Pretrain/Loss": 2.1077146530151367, "Pretrain/Loss (Raw)": 2.1164069175720215, "Pretrain/Step": 936, "Pretrain/Step Time": 8.438089424744248} +{"Pretrain/Learning Rate": 4.939141908214871e-05, "Pretrain/Loss": 2.1077985763549805, "Pretrain/Loss (Raw)": 2.110849142074585, "Pretrain/Step": 937, "Pretrain/Step Time": 8.433834845200181} +{"Pretrain/Learning Rate": 4.93895556180436e-05, "Pretrain/Loss": 2.1074678897857666, "Pretrain/Loss (Raw)": 2.176828622817993, "Pretrain/Step": 938, "Pretrain/Step Time": 8.436158042401075} +{"Pretrain/Learning Rate": 4.938768934061182e-05, "Pretrain/Loss": 2.1070027351379395, "Pretrain/Loss (Raw)": 2.0692825317382812, "Pretrain/Step": 939, "Pretrain/Step Time": 8.433463780209422} +{"Pretrain/Learning Rate": 4.9385820250068635e-05, "Pretrain/Loss": 2.108537435531616, "Pretrain/Loss (Raw)": 2.2257080078125, "Pretrain/Step": 940, "Pretrain/Step Time": 8.432095596566796} +{"Pretrain/Learning Rate": 4.938394834662966e-05, "Pretrain/Loss": 2.1081936359405518, "Pretrain/Loss (Raw)": 2.105388879776001, "Pretrain/Step": 941, "Pretrain/Step Time": 8.432232670485973} +{"Pretrain/Learning Rate": 4.9382073630510816e-05, "Pretrain/Loss": 2.109354019165039, "Pretrain/Loss (Raw)": 2.290459394454956, "Pretrain/Step": 942, "Pretrain/Step Time": 8.427230617031455} +{"Pretrain/Learning Rate": 4.938019610192835e-05, "Pretrain/Loss": 2.108159065246582, "Pretrain/Loss (Raw)": 1.9777013063430786, "Pretrain/Step": 943, "Pretrain/Step Time": 8.43087168596685} +{"Pretrain/Learning Rate": 4.9378315761098814e-05, "Pretrain/Loss": 2.109055995941162, "Pretrain/Loss (Raw)": 2.1697237491607666, "Pretrain/Step": 944, "Pretrain/Step Time": 8.425392335280776} +{"Pretrain/Learning Rate": 4.937643260823914e-05, "Pretrain/Loss": 2.1095659732818604, "Pretrain/Loss (Raw)": 2.093636989593506, "Pretrain/Step": 945, "Pretrain/Step Time": 8.427521135658026} +{"Pretrain/Learning Rate": 4.9374546643566525e-05, "Pretrain/Loss": 2.111131429672241, "Pretrain/Loss (Raw)": 2.1496260166168213, "Pretrain/Step": 946, "Pretrain/Step Time": 8.426912622526288} +{"Pretrain/Learning Rate": 4.9372657867298514e-05, "Pretrain/Loss": 2.1103694438934326, "Pretrain/Loss (Raw)": 2.011767625808716, "Pretrain/Step": 947, "Pretrain/Step Time": 8.427834641188383} +{"Pretrain/Learning Rate": 4.937076627965299e-05, "Pretrain/Loss": 2.109470844268799, "Pretrain/Loss (Raw)": 2.100149631500244, "Pretrain/Step": 948, "Pretrain/Step Time": 8.430028161033988} +{"Pretrain/Learning Rate": 4.936887188084813e-05, "Pretrain/Loss": 2.1106696128845215, "Pretrain/Loss (Raw)": 2.1247663497924805, "Pretrain/Step": 949, "Pretrain/Step Time": 8.432271897792816} +{"Pretrain/Learning Rate": 4.9366974671102475e-05, "Pretrain/Loss": 2.1084184646606445, "Pretrain/Loss (Raw)": 1.8778048753738403, "Pretrain/Step": 950, "Pretrain/Step Time": 8.43382697366178} +{"Pretrain/Learning Rate": 4.9365074650634855e-05, "Pretrain/Loss": 2.1057252883911133, "Pretrain/Loss (Raw)": 2.035799980163574, "Pretrain/Step": 951, "Pretrain/Step Time": 8.435184560716152} +{"Pretrain/Learning Rate": 4.9363171819664434e-05, "Pretrain/Loss": 2.1053285598754883, "Pretrain/Loss (Raw)": 2.1356892585754395, "Pretrain/Step": 952, "Pretrain/Step Time": 8.433465514332056} +{"Pretrain/Learning Rate": 4.9361266178410704e-05, "Pretrain/Loss": 2.1052260398864746, "Pretrain/Loss (Raw)": 2.074262857437134, "Pretrain/Step": 953, "Pretrain/Step Time": 8.435259008780122} +{"Pretrain/Learning Rate": 4.935935772709348e-05, "Pretrain/Loss": 2.1047730445861816, "Pretrain/Loss (Raw)": 2.14526104927063, "Pretrain/Step": 954, "Pretrain/Step Time": 8.433804890140891} +{"Pretrain/Learning Rate": 4.93574464659329e-05, "Pretrain/Loss": 2.105112075805664, "Pretrain/Loss (Raw)": 2.2054150104522705, "Pretrain/Step": 955, "Pretrain/Step Time": 8.437225436791778} +{"Pretrain/Learning Rate": 4.935553239514944e-05, "Pretrain/Loss": 2.1072423458099365, "Pretrain/Loss (Raw)": 2.276792287826538, "Pretrain/Step": 956, "Pretrain/Step Time": 8.437306536361575} +{"Pretrain/Learning Rate": 4.935361551496387e-05, "Pretrain/Loss": 2.107407569885254, "Pretrain/Loss (Raw)": 2.1845650672912598, "Pretrain/Step": 957, "Pretrain/Step Time": 8.434691522270441} +{"Pretrain/Learning Rate": 4.935169582559731e-05, "Pretrain/Loss": 2.109829902648926, "Pretrain/Loss (Raw)": 2.324347734451294, "Pretrain/Step": 958, "Pretrain/Step Time": 8.436083290725946} +{"Pretrain/Learning Rate": 4.934977332727119e-05, "Pretrain/Loss": 2.1094353199005127, "Pretrain/Loss (Raw)": 2.0976665019989014, "Pretrain/Step": 959, "Pretrain/Step Time": 8.436955774202943} +{"Pretrain/Learning Rate": 4.934784802020728e-05, "Pretrain/Loss": 2.1079373359680176, "Pretrain/Loss (Raw)": 2.0159730911254883, "Pretrain/Step": 960, "Pretrain/Step Time": 8.436591990292072} +{"Pretrain/Learning Rate": 4.934591990462766e-05, "Pretrain/Loss": 2.107997179031372, "Pretrain/Loss (Raw)": 2.1269330978393555, "Pretrain/Step": 961, "Pretrain/Step Time": 8.43680701032281} +{"Pretrain/Learning Rate": 4.9343988980754724e-05, "Pretrain/Loss": 2.1070802211761475, "Pretrain/Loss (Raw)": 2.0176339149475098, "Pretrain/Step": 962, "Pretrain/Step Time": 8.437029143795371} +{"Pretrain/Learning Rate": 4.9342055248811226e-05, "Pretrain/Loss": 2.105665445327759, "Pretrain/Loss (Raw)": 1.9239845275878906, "Pretrain/Step": 963, "Pretrain/Step Time": 8.435161055997014} +{"Pretrain/Learning Rate": 4.93401187090202e-05, "Pretrain/Loss": 2.1073360443115234, "Pretrain/Loss (Raw)": 2.189824104309082, "Pretrain/Step": 964, "Pretrain/Step Time": 8.433862717822194} +{"Pretrain/Learning Rate": 4.933817936160504e-05, "Pretrain/Loss": 2.108081102371216, "Pretrain/Loss (Raw)": 2.144484519958496, "Pretrain/Step": 965, "Pretrain/Step Time": 8.436990352347493} +{"Pretrain/Learning Rate": 4.933623720678944e-05, "Pretrain/Loss": 2.106459617614746, "Pretrain/Loss (Raw)": 2.0268876552581787, "Pretrain/Step": 966, "Pretrain/Step Time": 8.438400702551007} +{"Pretrain/Learning Rate": 4.933429224479743e-05, "Pretrain/Loss": 2.107232093811035, "Pretrain/Loss (Raw)": 2.1330556869506836, "Pretrain/Step": 967, "Pretrain/Step Time": 8.436539638787508} +{"Pretrain/Learning Rate": 4.933234447585337e-05, "Pretrain/Loss": 2.107356548309326, "Pretrain/Loss (Raw)": 1.9718834161758423, "Pretrain/Step": 968, "Pretrain/Step Time": 8.434515938162804} +{"Pretrain/Learning Rate": 4.933039390018191e-05, "Pretrain/Loss": 2.106748580932617, "Pretrain/Loss (Raw)": 1.9156227111816406, "Pretrain/Step": 969, "Pretrain/Step Time": 8.434234319254756} +{"Pretrain/Learning Rate": 4.932844051800808e-05, "Pretrain/Loss": 2.107445240020752, "Pretrain/Loss (Raw)": 2.2165589332580566, "Pretrain/Step": 970, "Pretrain/Step Time": 8.436400584876537} +{"Pretrain/Learning Rate": 4.9326484329557175e-05, "Pretrain/Loss": 2.1046767234802246, "Pretrain/Loss (Raw)": 1.8976643085479736, "Pretrain/Step": 971, "Pretrain/Step Time": 8.437931539490819} +{"Pretrain/Learning Rate": 4.932452533505486e-05, "Pretrain/Loss": 2.103208541870117, "Pretrain/Loss (Raw)": 1.9790124893188477, "Pretrain/Step": 972, "Pretrain/Step Time": 8.438867937773466} +{"Pretrain/Learning Rate": 4.932256353472709e-05, "Pretrain/Loss": 2.104912281036377, "Pretrain/Loss (Raw)": 2.344810724258423, "Pretrain/Step": 973, "Pretrain/Step Time": 8.438110049813986} +{"Pretrain/Learning Rate": 4.9320598928800166e-05, "Pretrain/Loss": 2.1063671112060547, "Pretrain/Loss (Raw)": 2.2565791606903076, "Pretrain/Step": 974, "Pretrain/Step Time": 8.435438776388764} +{"Pretrain/Learning Rate": 4.93186315175007e-05, "Pretrain/Loss": 2.1076488494873047, "Pretrain/Loss (Raw)": 2.187431573867798, "Pretrain/Step": 975, "Pretrain/Step Time": 8.436914740130305} +{"Pretrain/Learning Rate": 4.9316661301055637e-05, "Pretrain/Loss": 2.107177734375, "Pretrain/Loss (Raw)": 2.0478203296661377, "Pretrain/Step": 976, "Pretrain/Step Time": 8.43761532008648} +{"Pretrain/Learning Rate": 4.931468827969224e-05, "Pretrain/Loss": 2.107201099395752, "Pretrain/Loss (Raw)": 2.133094310760498, "Pretrain/Step": 977, "Pretrain/Step Time": 8.437754301354289} +{"Pretrain/Learning Rate": 4.9312712453638096e-05, "Pretrain/Loss": 2.108407497406006, "Pretrain/Loss (Raw)": 2.1559929847717285, "Pretrain/Step": 978, "Pretrain/Step Time": 8.436272023245692} +{"Pretrain/Learning Rate": 4.931073382312111e-05, "Pretrain/Loss": 2.1092429161071777, "Pretrain/Loss (Raw)": 2.1008214950561523, "Pretrain/Step": 979, "Pretrain/Step Time": 8.440005078911781} +{"Pretrain/Learning Rate": 4.930875238836952e-05, "Pretrain/Loss": 2.1104888916015625, "Pretrain/Loss (Raw)": 2.2060863971710205, "Pretrain/Step": 980, "Pretrain/Step Time": 8.434087485074997} +{"Pretrain/Learning Rate": 4.930676814961189e-05, "Pretrain/Loss": 2.1123528480529785, "Pretrain/Loss (Raw)": 2.216026544570923, "Pretrain/Step": 981, "Pretrain/Step Time": 8.433963788673282} +{"Pretrain/Learning Rate": 4.930478110707709e-05, "Pretrain/Loss": 2.1108591556549072, "Pretrain/Loss (Raw)": 1.9581571817398071, "Pretrain/Step": 982, "Pretrain/Step Time": 8.434877609834075} +{"Pretrain/Learning Rate": 4.930279126099433e-05, "Pretrain/Loss": 2.111255645751953, "Pretrain/Loss (Raw)": 2.1334140300750732, "Pretrain/Step": 983, "Pretrain/Step Time": 8.43351780436933} +{"Pretrain/Learning Rate": 4.930079861159315e-05, "Pretrain/Loss": 2.1110053062438965, "Pretrain/Loss (Raw)": 2.2028541564941406, "Pretrain/Step": 984, "Pretrain/Step Time": 8.43598984926939} +{"Pretrain/Learning Rate": 4.929880315910338e-05, "Pretrain/Loss": 2.1125688552856445, "Pretrain/Loss (Raw)": 2.212198257446289, "Pretrain/Step": 985, "Pretrain/Step Time": 8.434978691861033} +{"Pretrain/Learning Rate": 4.92968049037552e-05, "Pretrain/Loss": 2.113036870956421, "Pretrain/Loss (Raw)": 2.1951098442077637, "Pretrain/Step": 986, "Pretrain/Step Time": 8.436185264959931} +{"Pretrain/Learning Rate": 4.9294803845779124e-05, "Pretrain/Loss": 2.1117656230926514, "Pretrain/Loss (Raw)": 2.24649977684021, "Pretrain/Step": 987, "Pretrain/Step Time": 8.43941238336265} +{"Pretrain/Learning Rate": 4.929279998540596e-05, "Pretrain/Loss": 2.1110057830810547, "Pretrain/Loss (Raw)": 2.17875337600708, "Pretrain/Step": 988, "Pretrain/Step Time": 8.44163889810443} +{"Pretrain/Learning Rate": 4.929079332286685e-05, "Pretrain/Loss": 2.1109414100646973, "Pretrain/Loss (Raw)": 2.1667895317077637, "Pretrain/Step": 989, "Pretrain/Step Time": 8.439290737733245} +{"Pretrain/Learning Rate": 4.9288783858393273e-05, "Pretrain/Loss": 2.112973690032959, "Pretrain/Loss (Raw)": 2.217763662338257, "Pretrain/Step": 990, "Pretrain/Step Time": 8.43728650175035} +{"Pretrain/Learning Rate": 4.928677159221701e-05, "Pretrain/Loss": 2.113152027130127, "Pretrain/Loss (Raw)": 2.2641351222991943, "Pretrain/Step": 991, "Pretrain/Step Time": 8.438042288646102} +{"Pretrain/Learning Rate": 4.928475652457017e-05, "Pretrain/Loss": 2.1146528720855713, "Pretrain/Loss (Raw)": 2.2453017234802246, "Pretrain/Step": 992, "Pretrain/Step Time": 8.437616739422083} +{"Pretrain/Learning Rate": 4.9282738655685215e-05, "Pretrain/Loss": 2.117100715637207, "Pretrain/Loss (Raw)": 2.380582332611084, "Pretrain/Step": 993, "Pretrain/Step Time": 8.437341824173927} +{"Pretrain/Learning Rate": 4.928071798579488e-05, "Pretrain/Loss": 2.1169040203094482, "Pretrain/Loss (Raw)": 2.1143898963928223, "Pretrain/Step": 994, "Pretrain/Step Time": 8.436019599437714} +{"Pretrain/Learning Rate": 4.9278694515132265e-05, "Pretrain/Loss": 2.118619441986084, "Pretrain/Loss (Raw)": 2.1510112285614014, "Pretrain/Step": 995, "Pretrain/Step Time": 8.439203642308712} +{"Pretrain/Learning Rate": 4.9276668243930765e-05, "Pretrain/Loss": 2.1182174682617188, "Pretrain/Loss (Raw)": 2.086238145828247, "Pretrain/Step": 996, "Pretrain/Step Time": 8.436974879354239} +{"Pretrain/Learning Rate": 4.927463917242411e-05, "Pretrain/Loss": 2.1181976795196533, "Pretrain/Loss (Raw)": 2.156911849975586, "Pretrain/Step": 997, "Pretrain/Step Time": 8.43557620048523} +{"Pretrain/Learning Rate": 4.927260730084636e-05, "Pretrain/Loss": 2.117906332015991, "Pretrain/Loss (Raw)": 2.062069892883301, "Pretrain/Step": 998, "Pretrain/Step Time": 8.43641172721982} +{"Pretrain/Learning Rate": 4.9270572629431896e-05, "Pretrain/Loss": 2.1177306175231934, "Pretrain/Loss (Raw)": 2.049887180328369, "Pretrain/Step": 999, "Pretrain/Step Time": 8.435355490073562} +{"Pretrain/Learning Rate": 4.92685351584154e-05, "Pretrain/Loss": 2.1182990074157715, "Pretrain/Loss (Raw)": 2.1391782760620117, "Pretrain/Step": 1000, "Pretrain/Step Time": 8.43752196058631} +{"Pretrain/Learning Rate": 4.926649488803191e-05, "Pretrain/Loss": 2.1191036701202393, "Pretrain/Loss (Raw)": 2.29412579536438, "Pretrain/Step": 1001, "Pretrain/Step Time": 8.436443435028195} +{"Pretrain/Learning Rate": 4.926445181851676e-05, "Pretrain/Loss": 2.1178736686706543, "Pretrain/Loss (Raw)": 1.8672312498092651, "Pretrain/Step": 1002, "Pretrain/Step Time": 8.436164086684585} +{"Pretrain/Learning Rate": 4.9262405950105606e-05, "Pretrain/Loss": 2.117074966430664, "Pretrain/Loss (Raw)": 2.0472750663757324, "Pretrain/Step": 1003, "Pretrain/Step Time": 8.437483251094818} +{"Pretrain/Learning Rate": 4.926035728303446e-05, "Pretrain/Loss": 2.117433786392212, "Pretrain/Loss (Raw)": 1.9712581634521484, "Pretrain/Step": 1004, "Pretrain/Step Time": 8.43689808063209} +{"Pretrain/Learning Rate": 4.925830581753964e-05, "Pretrain/Loss": 2.11710262298584, "Pretrain/Loss (Raw)": 2.103551149368286, "Pretrain/Step": 1005, "Pretrain/Step Time": 8.437440155074} +{"Pretrain/Learning Rate": 4.925625155385776e-05, "Pretrain/Loss": 2.115889310836792, "Pretrain/Loss (Raw)": 2.073195457458496, "Pretrain/Step": 1006, "Pretrain/Step Time": 8.441246576607227} +{"Pretrain/Learning Rate": 4.925419449222578e-05, "Pretrain/Loss": 2.1166343688964844, "Pretrain/Loss (Raw)": 2.215604782104492, "Pretrain/Step": 1007, "Pretrain/Step Time": 8.44128036312759} +{"Pretrain/Learning Rate": 4.9252134632881e-05, "Pretrain/Loss": 2.1175971031188965, "Pretrain/Loss (Raw)": 2.158613920211792, "Pretrain/Step": 1008, "Pretrain/Step Time": 8.440359637141228} +{"Pretrain/Learning Rate": 4.925007197606101e-05, "Pretrain/Loss": 2.1180777549743652, "Pretrain/Loss (Raw)": 2.1108615398406982, "Pretrain/Step": 1009, "Pretrain/Step Time": 8.43588144145906} +{"Pretrain/Learning Rate": 4.924800652200373e-05, "Pretrain/Loss": 2.117701292037964, "Pretrain/Loss (Raw)": 2.0841124057769775, "Pretrain/Step": 1010, "Pretrain/Step Time": 8.437259433791041} +{"Pretrain/Learning Rate": 4.9245938270947435e-05, "Pretrain/Loss": 2.1172261238098145, "Pretrain/Loss (Raw)": 1.893019199371338, "Pretrain/Step": 1011, "Pretrain/Step Time": 8.43885580636561} +{"Pretrain/Learning Rate": 4.924386722313067e-05, "Pretrain/Loss": 2.1173014640808105, "Pretrain/Loss (Raw)": 2.147474765777588, "Pretrain/Step": 1012, "Pretrain/Step Time": 8.437588578090072} +{"Pretrain/Learning Rate": 4.924179337879234e-05, "Pretrain/Loss": 2.118044376373291, "Pretrain/Loss (Raw)": 2.1288199424743652, "Pretrain/Step": 1013, "Pretrain/Step Time": 8.438359381631017} +{"Pretrain/Learning Rate": 4.923971673817167e-05, "Pretrain/Loss": 2.117678165435791, "Pretrain/Loss (Raw)": 2.052095890045166, "Pretrain/Step": 1014, "Pretrain/Step Time": 8.434405529871583} +{"Pretrain/Learning Rate": 4.9237637301508187e-05, "Pretrain/Loss": 2.117975950241089, "Pretrain/Loss (Raw)": 2.0331532955169678, "Pretrain/Step": 1015, "Pretrain/Step Time": 8.437987314537168} +{"Pretrain/Learning Rate": 4.923555506904176e-05, "Pretrain/Loss": 2.117537260055542, "Pretrain/Loss (Raw)": 2.1796836853027344, "Pretrain/Step": 1016, "Pretrain/Step Time": 8.438129791989923} +{"Pretrain/Learning Rate": 4.9233470041012576e-05, "Pretrain/Loss": 2.118060350418091, "Pretrain/Loss (Raw)": 2.184218645095825, "Pretrain/Step": 1017, "Pretrain/Step Time": 8.44022073969245} +{"Pretrain/Learning Rate": 4.923138221766114e-05, "Pretrain/Loss": 2.117081642150879, "Pretrain/Loss (Raw)": 2.01672625541687, "Pretrain/Step": 1018, "Pretrain/Step Time": 8.440716253593564} +{"Pretrain/Learning Rate": 4.9229291599228277e-05, "Pretrain/Loss": 2.115847110748291, "Pretrain/Loss (Raw)": 2.0783867835998535, "Pretrain/Step": 1019, "Pretrain/Step Time": 8.442066995427012} +{"Pretrain/Learning Rate": 4.922719818595514e-05, "Pretrain/Loss": 2.1152703762054443, "Pretrain/Loss (Raw)": 1.936050534248352, "Pretrain/Step": 1020, "Pretrain/Step Time": 8.443237066268921} +{"Pretrain/Learning Rate": 4.922510197808321e-05, "Pretrain/Loss": 2.1156530380249023, "Pretrain/Loss (Raw)": 2.2213428020477295, "Pretrain/Step": 1021, "Pretrain/Step Time": 8.441004795953631} +{"Pretrain/Learning Rate": 4.922300297585428e-05, "Pretrain/Loss": 2.1173787117004395, "Pretrain/Loss (Raw)": 2.248258352279663, "Pretrain/Step": 1022, "Pretrain/Step Time": 8.444862470030785} +{"Pretrain/Learning Rate": 4.922090117951047e-05, "Pretrain/Loss": 2.1161398887634277, "Pretrain/Loss (Raw)": 2.035583019256592, "Pretrain/Step": 1023, "Pretrain/Step Time": 8.443406144157052} +{"Pretrain/Learning Rate": 4.921879658929422e-05, "Pretrain/Loss": 2.115926742553711, "Pretrain/Loss (Raw)": 2.1192333698272705, "Pretrain/Step": 1024, "Pretrain/Step Time": 8.440386783331633} +{"Pretrain/Learning Rate": 4.92166892054483e-05, "Pretrain/Loss": 2.115060329437256, "Pretrain/Loss (Raw)": 2.046867609024048, "Pretrain/Step": 1025, "Pretrain/Step Time": 8.445434650406241} +{"Pretrain/Learning Rate": 4.9214579028215776e-05, "Pretrain/Loss": 2.1154303550720215, "Pretrain/Loss (Raw)": 2.064484119415283, "Pretrain/Step": 1026, "Pretrain/Step Time": 8.442318825051188} +{"Pretrain/Learning Rate": 4.921246605784008e-05, "Pretrain/Loss": 2.115569591522217, "Pretrain/Loss (Raw)": 2.146317481994629, "Pretrain/Step": 1027, "Pretrain/Step Time": 8.444132205098867} +{"Pretrain/Learning Rate": 4.921035029456493e-05, "Pretrain/Loss": 2.115015983581543, "Pretrain/Loss (Raw)": 1.938012719154358, "Pretrain/Step": 1028, "Pretrain/Step Time": 8.445876743644476} +{"Pretrain/Learning Rate": 4.920823173863439e-05, "Pretrain/Loss": 2.1146607398986816, "Pretrain/Loss (Raw)": 2.189600706100464, "Pretrain/Step": 1029, "Pretrain/Step Time": 8.446259481832385} +{"Pretrain/Learning Rate": 4.920611039029282e-05, "Pretrain/Loss": 2.115185260772705, "Pretrain/Loss (Raw)": 2.1486599445343018, "Pretrain/Step": 1030, "Pretrain/Step Time": 8.443286905065179} +{"Pretrain/Learning Rate": 4.920398624978493e-05, "Pretrain/Loss": 2.115605354309082, "Pretrain/Loss (Raw)": 2.239863395690918, "Pretrain/Step": 1031, "Pretrain/Step Time": 8.440298311412334} +{"Pretrain/Learning Rate": 4.920185931735572e-05, "Pretrain/Loss": 2.1158196926116943, "Pretrain/Loss (Raw)": 2.178169012069702, "Pretrain/Step": 1032, "Pretrain/Step Time": 8.440849836915731} +{"Pretrain/Learning Rate": 4.9199729593250555e-05, "Pretrain/Loss": 2.1162590980529785, "Pretrain/Loss (Raw)": 2.2480087280273438, "Pretrain/Step": 1033, "Pretrain/Step Time": 8.441210813820362} +{"Pretrain/Learning Rate": 4.919759707771507e-05, "Pretrain/Loss": 2.118495464324951, "Pretrain/Loss (Raw)": 2.3485286235809326, "Pretrain/Step": 1034, "Pretrain/Step Time": 8.44336848706007} +{"Pretrain/Learning Rate": 4.9195461770995274e-05, "Pretrain/Loss": 2.117664337158203, "Pretrain/Loss (Raw)": 2.0419375896453857, "Pretrain/Step": 1035, "Pretrain/Step Time": 8.442692024633288} +{"Pretrain/Learning Rate": 4.9193323673337476e-05, "Pretrain/Loss": 2.1171131134033203, "Pretrain/Loss (Raw)": 2.014519691467285, "Pretrain/Step": 1036, "Pretrain/Step Time": 8.444863041862845} +{"Pretrain/Learning Rate": 4.919118278498828e-05, "Pretrain/Loss": 2.118485927581787, "Pretrain/Loss (Raw)": 2.198273181915283, "Pretrain/Step": 1037, "Pretrain/Step Time": 8.443761797621846} +{"Pretrain/Learning Rate": 4.9189039106194655e-05, "Pretrain/Loss": 2.1182007789611816, "Pretrain/Loss (Raw)": 2.095306873321533, "Pretrain/Step": 1038, "Pretrain/Step Time": 8.44196431338787} +{"Pretrain/Learning Rate": 4.918689263720387e-05, "Pretrain/Loss": 2.1164638996124268, "Pretrain/Loss (Raw)": 2.0580270290374756, "Pretrain/Step": 1039, "Pretrain/Step Time": 8.441053496673703} +{"Pretrain/Learning Rate": 4.918474337826352e-05, "Pretrain/Loss": 2.117105484008789, "Pretrain/Loss (Raw)": 2.124802827835083, "Pretrain/Step": 1040, "Pretrain/Step Time": 8.438587756827474} +{"Pretrain/Learning Rate": 4.918259132962153e-05, "Pretrain/Loss": 2.1147470474243164, "Pretrain/Loss (Raw)": 1.9277721643447876, "Pretrain/Step": 1041, "Pretrain/Step Time": 8.434179171919823} +{"Pretrain/Learning Rate": 4.918043649152612e-05, "Pretrain/Loss": 2.114495038986206, "Pretrain/Loss (Raw)": 1.9994966983795166, "Pretrain/Step": 1042, "Pretrain/Step Time": 8.436056170612574} +{"Pretrain/Learning Rate": 4.917827886422585e-05, "Pretrain/Loss": 2.1146738529205322, "Pretrain/Loss (Raw)": 2.1728827953338623, "Pretrain/Step": 1043, "Pretrain/Step Time": 8.436129620298743} +{"Pretrain/Learning Rate": 4.9176118447969625e-05, "Pretrain/Loss": 2.1144731044769287, "Pretrain/Loss (Raw)": 2.072482109069824, "Pretrain/Step": 1044, "Pretrain/Step Time": 8.438522096723318} +{"Pretrain/Learning Rate": 4.917395524300662e-05, "Pretrain/Loss": 2.1140708923339844, "Pretrain/Loss (Raw)": 2.0707764625549316, "Pretrain/Step": 1045, "Pretrain/Step Time": 8.436231913045049} +{"Pretrain/Learning Rate": 4.917178924958638e-05, "Pretrain/Loss": 2.113314390182495, "Pretrain/Loss (Raw)": 2.0910425186157227, "Pretrain/Step": 1046, "Pretrain/Step Time": 8.436049908399582} +{"Pretrain/Learning Rate": 4.9169620467958746e-05, "Pretrain/Loss": 2.111204147338867, "Pretrain/Loss (Raw)": 1.8323956727981567, "Pretrain/Step": 1047, "Pretrain/Step Time": 8.436815347522497} +{"Pretrain/Learning Rate": 4.916744889837388e-05, "Pretrain/Loss": 2.1116719245910645, "Pretrain/Loss (Raw)": 2.2539734840393066, "Pretrain/Step": 1048, "Pretrain/Step Time": 8.440594824030995} +{"Pretrain/Learning Rate": 4.916527454108227e-05, "Pretrain/Loss": 2.1124424934387207, "Pretrain/Loss (Raw)": 1.9261866807937622, "Pretrain/Step": 1049, "Pretrain/Step Time": 8.441883035004139} +{"Pretrain/Learning Rate": 4.916309739633475e-05, "Pretrain/Loss": 2.1140763759613037, "Pretrain/Loss (Raw)": 2.338512897491455, "Pretrain/Step": 1050, "Pretrain/Step Time": 8.442091926932335} +{"Pretrain/Learning Rate": 4.916091746438243e-05, "Pretrain/Loss": 2.1142311096191406, "Pretrain/Loss (Raw)": 2.203111171722412, "Pretrain/Step": 1051, "Pretrain/Step Time": 8.44250176101923} +{"Pretrain/Learning Rate": 4.915873474547677e-05, "Pretrain/Loss": 2.1154565811157227, "Pretrain/Loss (Raw)": 2.2483162879943848, "Pretrain/Step": 1052, "Pretrain/Step Time": 8.444449234753847} +{"Pretrain/Learning Rate": 4.915654923986955e-05, "Pretrain/Loss": 2.1144752502441406, "Pretrain/Loss (Raw)": 2.0647873878479004, "Pretrain/Step": 1053, "Pretrain/Step Time": 8.442925257608294} +{"Pretrain/Learning Rate": 4.915436094781286e-05, "Pretrain/Loss": 2.1128578186035156, "Pretrain/Loss (Raw)": 1.979297399520874, "Pretrain/Step": 1054, "Pretrain/Step Time": 8.446723805740476} +{"Pretrain/Learning Rate": 4.9152169869559126e-05, "Pretrain/Loss": 2.11460018157959, "Pretrain/Loss (Raw)": 2.1834471225738525, "Pretrain/Step": 1055, "Pretrain/Step Time": 8.452737350016832} +{"Pretrain/Learning Rate": 4.9149976005361085e-05, "Pretrain/Loss": 2.1147727966308594, "Pretrain/Loss (Raw)": 2.1337192058563232, "Pretrain/Step": 1056, "Pretrain/Step Time": 8.45183522067964} +{"Pretrain/Learning Rate": 4.9147779355471796e-05, "Pretrain/Loss": 2.1149516105651855, "Pretrain/Loss (Raw)": 2.072739362716675, "Pretrain/Step": 1057, "Pretrain/Step Time": 8.451431578025222} +{"Pretrain/Learning Rate": 4.9145579920144645e-05, "Pretrain/Loss": 2.1149020195007324, "Pretrain/Loss (Raw)": 2.1295197010040283, "Pretrain/Step": 1058, "Pretrain/Step Time": 8.452008627355099} +{"Pretrain/Learning Rate": 4.914337769963334e-05, "Pretrain/Loss": 2.1169474124908447, "Pretrain/Loss (Raw)": 2.218308210372925, "Pretrain/Step": 1059, "Pretrain/Step Time": 8.449649944901466} +{"Pretrain/Learning Rate": 4.9141172694191896e-05, "Pretrain/Loss": 2.1162590980529785, "Pretrain/Loss (Raw)": 2.0421245098114014, "Pretrain/Step": 1060, "Pretrain/Step Time": 8.453351464122534} +{"Pretrain/Learning Rate": 4.9138964904074667e-05, "Pretrain/Loss": 2.115640640258789, "Pretrain/Loss (Raw)": 2.0418648719787598, "Pretrain/Step": 1061, "Pretrain/Step Time": 8.449886048212647} +{"Pretrain/Learning Rate": 4.9136754329536326e-05, "Pretrain/Loss": 2.1153416633605957, "Pretrain/Loss (Raw)": 1.9631472826004028, "Pretrain/Step": 1062, "Pretrain/Step Time": 8.449115989729762} +{"Pretrain/Learning Rate": 4.913454097083185e-05, "Pretrain/Loss": 2.1162266731262207, "Pretrain/Loss (Raw)": 2.1805317401885986, "Pretrain/Step": 1063, "Pretrain/Step Time": 8.450769692659378} +{"Pretrain/Learning Rate": 4.913232482821656e-05, "Pretrain/Loss": 2.116497755050659, "Pretrain/Loss (Raw)": 2.1511199474334717, "Pretrain/Step": 1064, "Pretrain/Step Time": 8.450772661715746} +{"Pretrain/Learning Rate": 4.913010590194607e-05, "Pretrain/Loss": 2.1142516136169434, "Pretrain/Loss (Raw)": 1.8233165740966797, "Pretrain/Step": 1065, "Pretrain/Step Time": 8.45823529548943} +{"Pretrain/Learning Rate": 4.9127884192276354e-05, "Pretrain/Loss": 2.1143150329589844, "Pretrain/Loss (Raw)": 2.184929847717285, "Pretrain/Step": 1066, "Pretrain/Step Time": 8.454974215477705} +{"Pretrain/Learning Rate": 4.9125659699463664e-05, "Pretrain/Loss": 2.114337921142578, "Pretrain/Loss (Raw)": 2.072239637374878, "Pretrain/Step": 1067, "Pretrain/Step Time": 8.459240576252341} +{"Pretrain/Learning Rate": 4.912343242376462e-05, "Pretrain/Loss": 2.113152027130127, "Pretrain/Loss (Raw)": 2.073887825012207, "Pretrain/Step": 1068, "Pretrain/Step Time": 8.457396661862731} +{"Pretrain/Learning Rate": 4.9121202365436114e-05, "Pretrain/Loss": 2.1118013858795166, "Pretrain/Loss (Raw)": 1.9325377941131592, "Pretrain/Step": 1069, "Pretrain/Step Time": 8.461018623784184} +{"Pretrain/Learning Rate": 4.9118969524735403e-05, "Pretrain/Loss": 2.11042857170105, "Pretrain/Loss (Raw)": 2.114722728729248, "Pretrain/Step": 1070, "Pretrain/Step Time": 8.465531093999743} +{"Pretrain/Learning Rate": 4.911673390192002e-05, "Pretrain/Loss": 2.1116080284118652, "Pretrain/Loss (Raw)": 2.128699779510498, "Pretrain/Step": 1071, "Pretrain/Step Time": 8.463745756074786} +{"Pretrain/Learning Rate": 4.9114495497247864e-05, "Pretrain/Loss": 2.110991954803467, "Pretrain/Loss (Raw)": 2.0908377170562744, "Pretrain/Step": 1072, "Pretrain/Step Time": 8.467468379065394} +{"Pretrain/Learning Rate": 4.911225431097712e-05, "Pretrain/Loss": 2.110743999481201, "Pretrain/Loss (Raw)": 2.061913251876831, "Pretrain/Step": 1073, "Pretrain/Step Time": 8.464487046003342} +{"Pretrain/Learning Rate": 4.911001034336633e-05, "Pretrain/Loss": 2.11063814163208, "Pretrain/Loss (Raw)": 2.1360514163970947, "Pretrain/Step": 1074, "Pretrain/Step Time": 8.463297806680202} +{"Pretrain/Learning Rate": 4.9107763594674303e-05, "Pretrain/Loss": 2.1095588207244873, "Pretrain/Loss (Raw)": 1.8736178874969482, "Pretrain/Step": 1075, "Pretrain/Step Time": 8.464039018377662} +{"Pretrain/Learning Rate": 4.910551406516023e-05, "Pretrain/Loss": 2.109652042388916, "Pretrain/Loss (Raw)": 2.1121037006378174, "Pretrain/Step": 1076, "Pretrain/Step Time": 8.463401671499014} +{"Pretrain/Learning Rate": 4.910326175508357e-05, "Pretrain/Loss": 2.1099205017089844, "Pretrain/Loss (Raw)": 2.1591131687164307, "Pretrain/Step": 1077, "Pretrain/Step Time": 8.464484417811036} +{"Pretrain/Learning Rate": 4.9101006664704145e-05, "Pretrain/Loss": 2.1115400791168213, "Pretrain/Loss (Raw)": 2.085118293762207, "Pretrain/Step": 1078, "Pretrain/Step Time": 8.463418766856194} +{"Pretrain/Learning Rate": 4.909874879428207e-05, "Pretrain/Loss": 2.1117241382598877, "Pretrain/Loss (Raw)": 2.0593600273132324, "Pretrain/Step": 1079, "Pretrain/Step Time": 8.464911008253694} +{"Pretrain/Learning Rate": 4.909648814407779e-05, "Pretrain/Loss": 2.111924886703491, "Pretrain/Loss (Raw)": 2.161390781402588, "Pretrain/Step": 1080, "Pretrain/Step Time": 8.466300792992115} +{"Pretrain/Learning Rate": 4.909422471435207e-05, "Pretrain/Loss": 2.112990140914917, "Pretrain/Loss (Raw)": 2.2106125354766846, "Pretrain/Step": 1081, "Pretrain/Step Time": 8.463919810950756} +{"Pretrain/Learning Rate": 4.9091958505366e-05, "Pretrain/Loss": 2.112419605255127, "Pretrain/Loss (Raw)": 2.072225332260132, "Pretrain/Step": 1082, "Pretrain/Step Time": 8.466703489422798} +{"Pretrain/Learning Rate": 4.9089689517380974e-05, "Pretrain/Loss": 2.111543655395508, "Pretrain/Loss (Raw)": 2.093273639678955, "Pretrain/Step": 1083, "Pretrain/Step Time": 8.466042747721076} +{"Pretrain/Learning Rate": 4.908741775065873e-05, "Pretrain/Loss": 2.1087706089019775, "Pretrain/Loss (Raw)": 1.9218571186065674, "Pretrain/Step": 1084, "Pretrain/Step Time": 8.467870006337762} +{"Pretrain/Learning Rate": 4.908514320546131e-05, "Pretrain/Loss": 2.1057732105255127, "Pretrain/Loss (Raw)": 1.8009006977081299, "Pretrain/Step": 1085, "Pretrain/Step Time": 8.470403179526329} +{"Pretrain/Learning Rate": 4.90828658820511e-05, "Pretrain/Loss": 2.10493803024292, "Pretrain/Loss (Raw)": 2.2174510955810547, "Pretrain/Step": 1086, "Pretrain/Step Time": 8.46689723804593} +{"Pretrain/Learning Rate": 4.908058578069077e-05, "Pretrain/Loss": 2.105780601501465, "Pretrain/Loss (Raw)": 2.2055089473724365, "Pretrain/Step": 1087, "Pretrain/Step Time": 8.467019964009523} +{"Pretrain/Learning Rate": 4.907830290164332e-05, "Pretrain/Loss": 2.107900381088257, "Pretrain/Loss (Raw)": 2.287308931350708, "Pretrain/Step": 1088, "Pretrain/Step Time": 8.469484305009246} +{"Pretrain/Learning Rate": 4.90760172451721e-05, "Pretrain/Loss": 2.1076173782348633, "Pretrain/Loss (Raw)": 2.0907251834869385, "Pretrain/Step": 1089, "Pretrain/Step Time": 8.469630680978298} +{"Pretrain/Learning Rate": 4.9073728811540756e-05, "Pretrain/Loss": 2.1085500717163086, "Pretrain/Loss (Raw)": 2.1369874477386475, "Pretrain/Step": 1090, "Pretrain/Step Time": 8.467944046482444} +{"Pretrain/Learning Rate": 4.907143760101325e-05, "Pretrain/Loss": 2.1101508140563965, "Pretrain/Loss (Raw)": 2.1289007663726807, "Pretrain/Step": 1091, "Pretrain/Step Time": 8.471003217622638} +{"Pretrain/Learning Rate": 4.9069143613853876e-05, "Pretrain/Loss": 2.109684944152832, "Pretrain/Loss (Raw)": 2.1301987171173096, "Pretrain/Step": 1092, "Pretrain/Step Time": 8.475667404010892} +{"Pretrain/Learning Rate": 4.906684685032724e-05, "Pretrain/Loss": 2.1096103191375732, "Pretrain/Loss (Raw)": 2.1349234580993652, "Pretrain/Step": 1093, "Pretrain/Step Time": 8.471756651997566} +{"Pretrain/Learning Rate": 4.9064547310698285e-05, "Pretrain/Loss": 2.1100778579711914, "Pretrain/Loss (Raw)": 2.086733102798462, "Pretrain/Step": 1094, "Pretrain/Step Time": 8.472831381484866} +{"Pretrain/Learning Rate": 4.906224499523225e-05, "Pretrain/Loss": 2.1086840629577637, "Pretrain/Loss (Raw)": 1.9546486139297485, "Pretrain/Step": 1095, "Pretrain/Step Time": 8.477201122790575} +{"Pretrain/Learning Rate": 4.9059939904194716e-05, "Pretrain/Loss": 2.109964370727539, "Pretrain/Loss (Raw)": 2.135745048522949, "Pretrain/Step": 1096, "Pretrain/Step Time": 8.477854937314987} +{"Pretrain/Learning Rate": 4.905763203785156e-05, "Pretrain/Loss": 2.111687660217285, "Pretrain/Loss (Raw)": 2.1362195014953613, "Pretrain/Step": 1097, "Pretrain/Step Time": 8.476463997736573} +{"Pretrain/Learning Rate": 4.905532139646901e-05, "Pretrain/Loss": 2.109966278076172, "Pretrain/Loss (Raw)": 1.9962260723114014, "Pretrain/Step": 1098, "Pretrain/Step Time": 8.47916372679174} +{"Pretrain/Learning Rate": 4.9053007980313594e-05, "Pretrain/Loss": 2.111192226409912, "Pretrain/Loss (Raw)": 2.0545947551727295, "Pretrain/Step": 1099, "Pretrain/Step Time": 8.479163318872452} +{"Pretrain/Learning Rate": 4.905069178965215e-05, "Pretrain/Loss": 2.1113359928131104, "Pretrain/Loss (Raw)": 1.9973934888839722, "Pretrain/Step": 1100, "Pretrain/Step Time": 8.478091822937131} +{"Pretrain/Learning Rate": 4.904837282475187e-05, "Pretrain/Loss": 2.110050678253174, "Pretrain/Loss (Raw)": 2.180284261703491, "Pretrain/Step": 1101, "Pretrain/Step Time": 8.479498898610473} +{"Pretrain/Learning Rate": 4.904605108588023e-05, "Pretrain/Loss": 2.1101279258728027, "Pretrain/Loss (Raw)": 2.2665035724639893, "Pretrain/Step": 1102, "Pretrain/Step Time": 8.480627056211233} +{"Pretrain/Learning Rate": 4.9043726573305045e-05, "Pretrain/Loss": 2.109886646270752, "Pretrain/Loss (Raw)": 2.156517267227173, "Pretrain/Step": 1103, "Pretrain/Step Time": 8.480104321613908} +{"Pretrain/Learning Rate": 4.904139928729445e-05, "Pretrain/Loss": 2.111424446105957, "Pretrain/Loss (Raw)": 2.2446563243865967, "Pretrain/Step": 1104, "Pretrain/Step Time": 8.480639657005668} +{"Pretrain/Learning Rate": 4.90390692281169e-05, "Pretrain/Loss": 2.1101579666137695, "Pretrain/Loss (Raw)": 1.9709988832473755, "Pretrain/Step": 1105, "Pretrain/Step Time": 8.477331593632698} +{"Pretrain/Learning Rate": 4.903673639604116e-05, "Pretrain/Loss": 2.1104836463928223, "Pretrain/Loss (Raw)": 2.197683334350586, "Pretrain/Step": 1106, "Pretrain/Step Time": 8.484496656805277} +{"Pretrain/Learning Rate": 4.903440079133633e-05, "Pretrain/Loss": 2.1115832328796387, "Pretrain/Loss (Raw)": 2.241572618484497, "Pretrain/Step": 1107, "Pretrain/Step Time": 8.480906754732132} +{"Pretrain/Learning Rate": 4.9032062414271804e-05, "Pretrain/Loss": 2.1101889610290527, "Pretrain/Loss (Raw)": 2.027623414993286, "Pretrain/Step": 1108, "Pretrain/Step Time": 8.483896385878325} +{"Pretrain/Learning Rate": 4.9029721265117335e-05, "Pretrain/Loss": 2.1105222702026367, "Pretrain/Loss (Raw)": 2.258671283721924, "Pretrain/Step": 1109, "Pretrain/Step Time": 8.483718970790505} +{"Pretrain/Learning Rate": 4.9027377344142955e-05, "Pretrain/Loss": 2.111823558807373, "Pretrain/Loss (Raw)": 2.1247427463531494, "Pretrain/Step": 1110, "Pretrain/Step Time": 8.481891056522727} +{"Pretrain/Learning Rate": 4.9025030651619046e-05, "Pretrain/Loss": 2.112215042114258, "Pretrain/Loss (Raw)": 2.1835155487060547, "Pretrain/Step": 1111, "Pretrain/Step Time": 8.48240871541202} +{"Pretrain/Learning Rate": 4.90226811878163e-05, "Pretrain/Loss": 2.11252498626709, "Pretrain/Loss (Raw)": 2.2425155639648438, "Pretrain/Step": 1112, "Pretrain/Step Time": 8.48191255517304} +{"Pretrain/Learning Rate": 4.902032895300571e-05, "Pretrain/Loss": 2.1123974323272705, "Pretrain/Loss (Raw)": 2.195876121520996, "Pretrain/Step": 1113, "Pretrain/Step Time": 8.485025780275464} +{"Pretrain/Learning Rate": 4.901797394745862e-05, "Pretrain/Loss": 2.1125786304473877, "Pretrain/Loss (Raw)": 2.2183194160461426, "Pretrain/Step": 1114, "Pretrain/Step Time": 8.484430734068155} +{"Pretrain/Learning Rate": 4.9015616171446674e-05, "Pretrain/Loss": 2.1110310554504395, "Pretrain/Loss (Raw)": 2.0483994483947754, "Pretrain/Step": 1115, "Pretrain/Step Time": 8.482393762096763} +{"Pretrain/Learning Rate": 4.9013255625241846e-05, "Pretrain/Loss": 2.1111576557159424, "Pretrain/Loss (Raw)": 2.1949498653411865, "Pretrain/Step": 1116, "Pretrain/Step Time": 8.480804808437824} +{"Pretrain/Learning Rate": 4.901089230911642e-05, "Pretrain/Loss": 2.110790967941284, "Pretrain/Loss (Raw)": 2.1198503971099854, "Pretrain/Step": 1117, "Pretrain/Step Time": 8.480613043531775} +{"Pretrain/Learning Rate": 4.900852622334301e-05, "Pretrain/Loss": 2.110046625137329, "Pretrain/Loss (Raw)": 2.122514009475708, "Pretrain/Step": 1118, "Pretrain/Step Time": 8.479436272755265} +{"Pretrain/Learning Rate": 4.900615736819453e-05, "Pretrain/Loss": 2.1091318130493164, "Pretrain/Loss (Raw)": 2.1470274925231934, "Pretrain/Step": 1119, "Pretrain/Step Time": 8.481392115354538} +{"Pretrain/Learning Rate": 4.900378574394423e-05, "Pretrain/Loss": 2.1082763671875, "Pretrain/Loss (Raw)": 2.1358113288879395, "Pretrain/Step": 1120, "Pretrain/Step Time": 8.482163973152637} +{"Pretrain/Learning Rate": 4.900141135086569e-05, "Pretrain/Loss": 2.105273485183716, "Pretrain/Loss (Raw)": 1.9961868524551392, "Pretrain/Step": 1121, "Pretrain/Step Time": 8.482677049934864} +{"Pretrain/Learning Rate": 4.899903418923278e-05, "Pretrain/Loss": 2.1036527156829834, "Pretrain/Loss (Raw)": 1.90696120262146, "Pretrain/Step": 1122, "Pretrain/Step Time": 8.484111946076155} +{"Pretrain/Learning Rate": 4.8996654259319705e-05, "Pretrain/Loss": 2.103081464767456, "Pretrain/Loss (Raw)": 2.0778701305389404, "Pretrain/Step": 1123, "Pretrain/Step Time": 8.48279464803636} +{"Pretrain/Learning Rate": 4.8994271561401e-05, "Pretrain/Loss": 2.1033968925476074, "Pretrain/Loss (Raw)": 2.126608371734619, "Pretrain/Step": 1124, "Pretrain/Step Time": 8.482467088848352} +{"Pretrain/Learning Rate": 4.899188609575151e-05, "Pretrain/Loss": 2.102365255355835, "Pretrain/Loss (Raw)": 2.0248687267303467, "Pretrain/Step": 1125, "Pretrain/Step Time": 8.482170002534986} +{"Pretrain/Learning Rate": 4.8989497862646374e-05, "Pretrain/Loss": 2.1028707027435303, "Pretrain/Loss (Raw)": 2.126768112182617, "Pretrain/Step": 1126, "Pretrain/Step Time": 8.483511256054044} +{"Pretrain/Learning Rate": 4.89871068623611e-05, "Pretrain/Loss": 2.1026153564453125, "Pretrain/Loss (Raw)": 2.0172009468078613, "Pretrain/Step": 1127, "Pretrain/Step Time": 8.481348298490047} +{"Pretrain/Learning Rate": 4.898471309517148e-05, "Pretrain/Loss": 2.1026198863983154, "Pretrain/Loss (Raw)": 2.1397817134857178, "Pretrain/Step": 1128, "Pretrain/Step Time": 8.479663453996181} +{"Pretrain/Learning Rate": 4.898231656135363e-05, "Pretrain/Loss": 2.1027259826660156, "Pretrain/Loss (Raw)": 2.3076882362365723, "Pretrain/Step": 1129, "Pretrain/Step Time": 8.481788128614426} +{"Pretrain/Learning Rate": 4.897991726118399e-05, "Pretrain/Loss": 2.1046056747436523, "Pretrain/Loss (Raw)": 2.107816219329834, "Pretrain/Step": 1130, "Pretrain/Step Time": 8.480613179504871} +{"Pretrain/Learning Rate": 4.8977515194939325e-05, "Pretrain/Loss": 2.1050806045532227, "Pretrain/Loss (Raw)": 2.108074426651001, "Pretrain/Step": 1131, "Pretrain/Step Time": 8.481620617210865} +{"Pretrain/Learning Rate": 4.8975110362896716e-05, "Pretrain/Loss": 2.1062185764312744, "Pretrain/Loss (Raw)": 2.1169352531433105, "Pretrain/Step": 1132, "Pretrain/Step Time": 8.483367135748267} +{"Pretrain/Learning Rate": 4.897270276533354e-05, "Pretrain/Loss": 2.1061363220214844, "Pretrain/Loss (Raw)": 2.0930333137512207, "Pretrain/Step": 1133, "Pretrain/Step Time": 8.48355413787067} +{"Pretrain/Learning Rate": 4.897029240252753e-05, "Pretrain/Loss": 2.105928421020508, "Pretrain/Loss (Raw)": 2.0465707778930664, "Pretrain/Step": 1134, "Pretrain/Step Time": 8.481466555967927} +{"Pretrain/Learning Rate": 4.896787927475671e-05, "Pretrain/Loss": 2.1056020259857178, "Pretrain/Loss (Raw)": 2.173830986022949, "Pretrain/Step": 1135, "Pretrain/Step Time": 8.480160191655159} +{"Pretrain/Learning Rate": 4.896546338229945e-05, "Pretrain/Loss": 2.1041719913482666, "Pretrain/Loss (Raw)": 1.9755595922470093, "Pretrain/Step": 1136, "Pretrain/Step Time": 8.479774456471205} +{"Pretrain/Learning Rate": 4.89630447254344e-05, "Pretrain/Loss": 2.104076385498047, "Pretrain/Loss (Raw)": 2.098612070083618, "Pretrain/Step": 1137, "Pretrain/Step Time": 8.48028652742505} +{"Pretrain/Learning Rate": 4.8960623304440565e-05, "Pretrain/Loss": 2.103477954864502, "Pretrain/Loss (Raw)": 2.0075252056121826, "Pretrain/Step": 1138, "Pretrain/Step Time": 8.483593130484223} +{"Pretrain/Learning Rate": 4.8958199119597256e-05, "Pretrain/Loss": 2.104541540145874, "Pretrain/Loss (Raw)": 2.0291709899902344, "Pretrain/Step": 1139, "Pretrain/Step Time": 8.480227276682854} +{"Pretrain/Learning Rate": 4.895577217118409e-05, "Pretrain/Loss": 2.1039345264434814, "Pretrain/Loss (Raw)": 2.0697762966156006, "Pretrain/Step": 1140, "Pretrain/Step Time": 8.480603396892548} +{"Pretrain/Learning Rate": 4.895334245948103e-05, "Pretrain/Loss": 2.1031126976013184, "Pretrain/Loss (Raw)": 2.0236074924468994, "Pretrain/Step": 1141, "Pretrain/Step Time": 8.479810180142522} +{"Pretrain/Learning Rate": 4.8950909984768335e-05, "Pretrain/Loss": 2.1035399436950684, "Pretrain/Loss (Raw)": 2.1067895889282227, "Pretrain/Step": 1142, "Pretrain/Step Time": 8.484286019578576} +{"Pretrain/Learning Rate": 4.894847474732658e-05, "Pretrain/Loss": 2.104431629180908, "Pretrain/Loss (Raw)": 2.147282600402832, "Pretrain/Step": 1143, "Pretrain/Step Time": 8.478172602131963} +{"Pretrain/Learning Rate": 4.894603674743669e-05, "Pretrain/Loss": 2.1037938594818115, "Pretrain/Loss (Raw)": 2.0980710983276367, "Pretrain/Step": 1144, "Pretrain/Step Time": 8.477016851305962} +{"Pretrain/Learning Rate": 4.894359598537988e-05, "Pretrain/Loss": 2.102739095687866, "Pretrain/Loss (Raw)": 2.049185276031494, "Pretrain/Step": 1145, "Pretrain/Step Time": 8.476393360644579} +{"Pretrain/Learning Rate": 4.894115246143768e-05, "Pretrain/Loss": 2.1036629676818848, "Pretrain/Loss (Raw)": 2.1349947452545166, "Pretrain/Step": 1146, "Pretrain/Step Time": 8.474220102652907} +{"Pretrain/Learning Rate": 4.893870617589196e-05, "Pretrain/Loss": 2.101804733276367, "Pretrain/Loss (Raw)": 1.8405431509017944, "Pretrain/Step": 1147, "Pretrain/Step Time": 8.474924379959702} +{"Pretrain/Learning Rate": 4.893625712902489e-05, "Pretrain/Loss": 2.103264808654785, "Pretrain/Loss (Raw)": 2.122922420501709, "Pretrain/Step": 1148, "Pretrain/Step Time": 8.473609548062086} +{"Pretrain/Learning Rate": 4.8933805321118975e-05, "Pretrain/Loss": 2.1031885147094727, "Pretrain/Loss (Raw)": 2.2115845680236816, "Pretrain/Step": 1149, "Pretrain/Step Time": 8.473840931430459} +{"Pretrain/Learning Rate": 4.893135075245702e-05, "Pretrain/Loss": 2.1020593643188477, "Pretrain/Loss (Raw)": 2.103747606277466, "Pretrain/Step": 1150, "Pretrain/Step Time": 8.473221393302083} +{"Pretrain/Learning Rate": 4.892889342332218e-05, "Pretrain/Loss": 2.1033005714416504, "Pretrain/Loss (Raw)": 2.194463014602661, "Pretrain/Step": 1151, "Pretrain/Step Time": 8.472770316526294} +{"Pretrain/Learning Rate": 4.892643333399788e-05, "Pretrain/Loss": 2.1022167205810547, "Pretrain/Loss (Raw)": 1.9804965257644653, "Pretrain/Step": 1152, "Pretrain/Step Time": 8.474287036806345} +{"Pretrain/Learning Rate": 4.892397048476791e-05, "Pretrain/Loss": 2.103201389312744, "Pretrain/Loss (Raw)": 2.17289137840271, "Pretrain/Step": 1153, "Pretrain/Step Time": 8.47115021944046} +{"Pretrain/Learning Rate": 4.892150487591635e-05, "Pretrain/Loss": 2.1033453941345215, "Pretrain/Loss (Raw)": 2.082908868789673, "Pretrain/Step": 1154, "Pretrain/Step Time": 8.469360679388046} +{"Pretrain/Learning Rate": 4.891903650772761e-05, "Pretrain/Loss": 2.1017277240753174, "Pretrain/Loss (Raw)": 1.9392735958099365, "Pretrain/Step": 1155, "Pretrain/Step Time": 8.467067437246442} +{"Pretrain/Learning Rate": 4.891656538048642e-05, "Pretrain/Loss": 2.1041319370269775, "Pretrain/Loss (Raw)": 2.2457363605499268, "Pretrain/Step": 1156, "Pretrain/Step Time": 8.466850593686104} +{"Pretrain/Learning Rate": 4.891409149447781e-05, "Pretrain/Loss": 2.102950096130371, "Pretrain/Loss (Raw)": 2.038320779800415, "Pretrain/Step": 1157, "Pretrain/Step Time": 8.46458620019257} +{"Pretrain/Learning Rate": 4.8911614849987154e-05, "Pretrain/Loss": 2.1023008823394775, "Pretrain/Loss (Raw)": 2.0655555725097656, "Pretrain/Step": 1158, "Pretrain/Step Time": 8.466505790129304} +{"Pretrain/Learning Rate": 4.890913544730013e-05, "Pretrain/Loss": 2.10140323638916, "Pretrain/Loss (Raw)": 2.124983787536621, "Pretrain/Step": 1159, "Pretrain/Step Time": 8.466835951432586} +{"Pretrain/Learning Rate": 4.890665328670273e-05, "Pretrain/Loss": 2.100459575653076, "Pretrain/Loss (Raw)": 2.0573527812957764, "Pretrain/Step": 1160, "Pretrain/Step Time": 8.469213970005512} +{"Pretrain/Learning Rate": 4.890416836848127e-05, "Pretrain/Loss": 2.0987181663513184, "Pretrain/Loss (Raw)": 2.025090217590332, "Pretrain/Step": 1161, "Pretrain/Step Time": 8.467941490933299} +{"Pretrain/Learning Rate": 4.89016806929224e-05, "Pretrain/Loss": 2.0974068641662598, "Pretrain/Loss (Raw)": 2.180694341659546, "Pretrain/Step": 1162, "Pretrain/Step Time": 8.46504390053451} +{"Pretrain/Learning Rate": 4.889919026031306e-05, "Pretrain/Loss": 2.0980381965637207, "Pretrain/Loss (Raw)": 2.1227457523345947, "Pretrain/Step": 1163, "Pretrain/Step Time": 8.46340350061655} +{"Pretrain/Learning Rate": 4.889669707094052e-05, "Pretrain/Loss": 2.098576068878174, "Pretrain/Loss (Raw)": 2.083397150039673, "Pretrain/Step": 1164, "Pretrain/Step Time": 8.462002579122782} +{"Pretrain/Learning Rate": 4.889420112509237e-05, "Pretrain/Loss": 2.0969221591949463, "Pretrain/Loss (Raw)": 1.986565113067627, "Pretrain/Step": 1165, "Pretrain/Step Time": 8.462039157748222} +{"Pretrain/Learning Rate": 4.889170242305652e-05, "Pretrain/Loss": 2.0970335006713867, "Pretrain/Loss (Raw)": 2.109563112258911, "Pretrain/Step": 1166, "Pretrain/Step Time": 8.460715405642986} +{"Pretrain/Learning Rate": 4.8889200965121184e-05, "Pretrain/Loss": 2.0978996753692627, "Pretrain/Loss (Raw)": 2.1689069271087646, "Pretrain/Step": 1167, "Pretrain/Step Time": 8.463344087824225} +{"Pretrain/Learning Rate": 4.8886696751574926e-05, "Pretrain/Loss": 2.0970468521118164, "Pretrain/Loss (Raw)": 2.0156402587890625, "Pretrain/Step": 1168, "Pretrain/Step Time": 8.46826976723969} +{"Pretrain/Learning Rate": 4.888418978270658e-05, "Pretrain/Loss": 2.098341941833496, "Pretrain/Loss (Raw)": 2.0935001373291016, "Pretrain/Step": 1169, "Pretrain/Step Time": 8.465610539540648} +{"Pretrain/Learning Rate": 4.888168005880533e-05, "Pretrain/Loss": 2.0987472534179688, "Pretrain/Loss (Raw)": 2.051405668258667, "Pretrain/Step": 1170, "Pretrain/Step Time": 8.464286079630256} +{"Pretrain/Learning Rate": 4.887916758016069e-05, "Pretrain/Loss": 2.097975492477417, "Pretrain/Loss (Raw)": 2.0741002559661865, "Pretrain/Step": 1171, "Pretrain/Step Time": 8.462269224226475} +{"Pretrain/Learning Rate": 4.887665234706246e-05, "Pretrain/Loss": 2.0985474586486816, "Pretrain/Loss (Raw)": 2.1456594467163086, "Pretrain/Step": 1172, "Pretrain/Step Time": 8.465303622186184} +{"Pretrain/Learning Rate": 4.887413435980077e-05, "Pretrain/Loss": 2.0995326042175293, "Pretrain/Loss (Raw)": 2.1968894004821777, "Pretrain/Step": 1173, "Pretrain/Step Time": 8.466584412381053} +{"Pretrain/Learning Rate": 4.887161361866608e-05, "Pretrain/Loss": 2.0994722843170166, "Pretrain/Loss (Raw)": 2.0833308696746826, "Pretrain/Step": 1174, "Pretrain/Step Time": 8.466376820579171} +{"Pretrain/Learning Rate": 4.886909012394913e-05, "Pretrain/Loss": 2.1005940437316895, "Pretrain/Loss (Raw)": 1.975968360900879, "Pretrain/Step": 1175, "Pretrain/Step Time": 8.464706705883145} +{"Pretrain/Learning Rate": 4.886656387594104e-05, "Pretrain/Loss": 2.099940776824951, "Pretrain/Loss (Raw)": 2.1703789234161377, "Pretrain/Step": 1176, "Pretrain/Step Time": 8.459130853414536} +{"Pretrain/Learning Rate": 4.886403487493319e-05, "Pretrain/Loss": 2.101736068725586, "Pretrain/Loss (Raw)": 2.155987501144409, "Pretrain/Step": 1177, "Pretrain/Step Time": 8.456593826413155} +{"Pretrain/Learning Rate": 4.88615031212173e-05, "Pretrain/Loss": 2.1010336875915527, "Pretrain/Loss (Raw)": 2.248588800430298, "Pretrain/Step": 1178, "Pretrain/Step Time": 8.455561829730868} +{"Pretrain/Learning Rate": 4.885896861508541e-05, "Pretrain/Loss": 2.1001222133636475, "Pretrain/Loss (Raw)": 2.0864460468292236, "Pretrain/Step": 1179, "Pretrain/Step Time": 8.45443075709045} +{"Pretrain/Learning Rate": 4.885643135682988e-05, "Pretrain/Loss": 2.0990495681762695, "Pretrain/Loss (Raw)": 2.111018419265747, "Pretrain/Step": 1180, "Pretrain/Step Time": 8.45405625551939} +{"Pretrain/Learning Rate": 4.885389134674338e-05, "Pretrain/Loss": 2.0982794761657715, "Pretrain/Loss (Raw)": 1.9662352800369263, "Pretrain/Step": 1181, "Pretrain/Step Time": 8.456765200942755} +{"Pretrain/Learning Rate": 4.885134858511888e-05, "Pretrain/Loss": 2.0994553565979004, "Pretrain/Loss (Raw)": 2.1297929286956787, "Pretrain/Step": 1182, "Pretrain/Step Time": 8.453783143311739} +{"Pretrain/Learning Rate": 4.8848803072249715e-05, "Pretrain/Loss": 2.0989952087402344, "Pretrain/Loss (Raw)": 2.124563455581665, "Pretrain/Step": 1183, "Pretrain/Step Time": 8.453025380149484} +{"Pretrain/Learning Rate": 4.884625480842949e-05, "Pretrain/Loss": 2.0990986824035645, "Pretrain/Loss (Raw)": 2.146951198577881, "Pretrain/Step": 1184, "Pretrain/Step Time": 8.453318344429135} +{"Pretrain/Learning Rate": 4.884370379395215e-05, "Pretrain/Loss": 2.0994598865509033, "Pretrain/Loss (Raw)": 2.118968963623047, "Pretrain/Step": 1185, "Pretrain/Step Time": 8.456323711201549} +{"Pretrain/Learning Rate": 4.884115002911197e-05, "Pretrain/Loss": 2.0991930961608887, "Pretrain/Loss (Raw)": 2.0953516960144043, "Pretrain/Step": 1186, "Pretrain/Step Time": 8.45717286504805} +{"Pretrain/Learning Rate": 4.8838593514203505e-05, "Pretrain/Loss": 2.09818696975708, "Pretrain/Loss (Raw)": 2.08956241607666, "Pretrain/Step": 1187, "Pretrain/Step Time": 8.454606395214796} +{"Pretrain/Learning Rate": 4.8836034249521653e-05, "Pretrain/Loss": 2.099003314971924, "Pretrain/Loss (Raw)": 2.146618366241455, "Pretrain/Step": 1188, "Pretrain/Step Time": 8.45431261882186} +{"Pretrain/Learning Rate": 4.883347223536163e-05, "Pretrain/Loss": 2.1003332138061523, "Pretrain/Loss (Raw)": 2.212055206298828, "Pretrain/Step": 1189, "Pretrain/Step Time": 8.454308945685625} +{"Pretrain/Learning Rate": 4.883090747201897e-05, "Pretrain/Loss": 2.100693702697754, "Pretrain/Loss (Raw)": 2.0093154907226562, "Pretrain/Step": 1190, "Pretrain/Step Time": 8.455601273104548} +{"Pretrain/Learning Rate": 4.8828339959789493e-05, "Pretrain/Loss": 2.1001174449920654, "Pretrain/Loss (Raw)": 2.1067404747009277, "Pretrain/Step": 1191, "Pretrain/Step Time": 8.459122585132718} +{"Pretrain/Learning Rate": 4.8825769698969384e-05, "Pretrain/Loss": 2.099717617034912, "Pretrain/Loss (Raw)": 2.0999372005462646, "Pretrain/Step": 1192, "Pretrain/Step Time": 8.458721786737442} +{"Pretrain/Learning Rate": 4.882319668985511e-05, "Pretrain/Loss": 2.1013150215148926, "Pretrain/Loss (Raw)": 2.0278186798095703, "Pretrain/Step": 1193, "Pretrain/Step Time": 8.451718788594007} +{"Pretrain/Learning Rate": 4.8820620932743465e-05, "Pretrain/Loss": 2.1007184982299805, "Pretrain/Loss (Raw)": 2.108553647994995, "Pretrain/Step": 1194, "Pretrain/Step Time": 8.45293009094894} +{"Pretrain/Learning Rate": 4.8818042427931576e-05, "Pretrain/Loss": 2.099895477294922, "Pretrain/Loss (Raw)": 1.966896653175354, "Pretrain/Step": 1195, "Pretrain/Step Time": 8.44771515764296} +{"Pretrain/Learning Rate": 4.8815461175716857e-05, "Pretrain/Loss": 2.0988028049468994, "Pretrain/Loss (Raw)": 1.9340503215789795, "Pretrain/Step": 1196, "Pretrain/Step Time": 8.45364242605865} +{"Pretrain/Learning Rate": 4.881287717639706e-05, "Pretrain/Loss": 2.10029935836792, "Pretrain/Loss (Raw)": 2.1240787506103516, "Pretrain/Step": 1197, "Pretrain/Step Time": 8.449371084570885} +{"Pretrain/Learning Rate": 4.8810290430270255e-05, "Pretrain/Loss": 2.100163698196411, "Pretrain/Loss (Raw)": 2.097372055053711, "Pretrain/Step": 1198, "Pretrain/Step Time": 8.44627209752798} +{"Pretrain/Learning Rate": 4.8807700937634814e-05, "Pretrain/Loss": 2.100294828414917, "Pretrain/Loss (Raw)": 2.145477294921875, "Pretrain/Step": 1199, "Pretrain/Step Time": 8.447643429040909} +{"Pretrain/Learning Rate": 4.8805108698789435e-05, "Pretrain/Loss": 2.1008784770965576, "Pretrain/Loss (Raw)": 2.165553092956543, "Pretrain/Step": 1200, "Pretrain/Step Time": 8.445305781438947} +{"Pretrain/Learning Rate": 4.880251371403313e-05, "Pretrain/Loss": 2.101414680480957, "Pretrain/Loss (Raw)": 2.13055157661438, "Pretrain/Step": 1201, "Pretrain/Step Time": 8.44543632864952} +{"Pretrain/Learning Rate": 4.879991598366524e-05, "Pretrain/Loss": 2.102023124694824, "Pretrain/Loss (Raw)": 2.213927984237671, "Pretrain/Step": 1202, "Pretrain/Step Time": 8.44916138984263} +{"Pretrain/Learning Rate": 4.87973155079854e-05, "Pretrain/Loss": 2.103518009185791, "Pretrain/Loss (Raw)": 2.064960241317749, "Pretrain/Step": 1203, "Pretrain/Step Time": 8.446955416351557} +{"Pretrain/Learning Rate": 4.879471228729358e-05, "Pretrain/Loss": 2.102583169937134, "Pretrain/Loss (Raw)": 1.992435097694397, "Pretrain/Step": 1204, "Pretrain/Step Time": 8.44774754345417} +{"Pretrain/Learning Rate": 4.8792106321890063e-05, "Pretrain/Loss": 2.1021502017974854, "Pretrain/Loss (Raw)": 2.103693723678589, "Pretrain/Step": 1205, "Pretrain/Step Time": 8.446335995569825} +{"Pretrain/Learning Rate": 4.878949761207544e-05, "Pretrain/Loss": 2.1036715507507324, "Pretrain/Loss (Raw)": 2.2798542976379395, "Pretrain/Step": 1206, "Pretrain/Step Time": 8.448372075334191} +{"Pretrain/Learning Rate": 4.8786886158150627e-05, "Pretrain/Loss": 2.1051223278045654, "Pretrain/Loss (Raw)": 2.245055675506592, "Pretrain/Step": 1207, "Pretrain/Step Time": 8.444546753540635} +{"Pretrain/Learning Rate": 4.878427196041686e-05, "Pretrain/Loss": 2.1036453247070312, "Pretrain/Loss (Raw)": 1.9723455905914307, "Pretrain/Step": 1208, "Pretrain/Step Time": 8.444797860458493} +{"Pretrain/Learning Rate": 4.878165501917568e-05, "Pretrain/Loss": 2.102571964263916, "Pretrain/Loss (Raw)": 2.0732243061065674, "Pretrain/Step": 1209, "Pretrain/Step Time": 8.444296102970839} +{"Pretrain/Learning Rate": 4.877903533472894e-05, "Pretrain/Loss": 2.1014223098754883, "Pretrain/Loss (Raw)": 1.9250894784927368, "Pretrain/Step": 1210, "Pretrain/Step Time": 8.441052561625838} +{"Pretrain/Learning Rate": 4.877641290737884e-05, "Pretrain/Loss": 2.1019539833068848, "Pretrain/Loss (Raw)": 2.16129207611084, "Pretrain/Step": 1211, "Pretrain/Step Time": 8.440721549093723} +{"Pretrain/Learning Rate": 4.877378773742787e-05, "Pretrain/Loss": 2.103137254714966, "Pretrain/Loss (Raw)": 2.073331832885742, "Pretrain/Step": 1212, "Pretrain/Step Time": 8.443772541359067} +{"Pretrain/Learning Rate": 4.877115982517883e-05, "Pretrain/Loss": 2.1059863567352295, "Pretrain/Loss (Raw)": 2.1655771732330322, "Pretrain/Step": 1213, "Pretrain/Step Time": 8.443395644426346} +{"Pretrain/Learning Rate": 4.8768529170934866e-05, "Pretrain/Loss": 2.1043200492858887, "Pretrain/Loss (Raw)": 2.0041444301605225, "Pretrain/Step": 1214, "Pretrain/Step Time": 8.44319229759276} +{"Pretrain/Learning Rate": 4.876589577499941e-05, "Pretrain/Loss": 2.1014318466186523, "Pretrain/Loss (Raw)": 1.8358360528945923, "Pretrain/Step": 1215, "Pretrain/Step Time": 8.446674507111311} +{"Pretrain/Learning Rate": 4.876325963767623e-05, "Pretrain/Loss": 2.099841833114624, "Pretrain/Loss (Raw)": 2.083782434463501, "Pretrain/Step": 1216, "Pretrain/Step Time": 8.445953546091914} +{"Pretrain/Learning Rate": 4.876062075926941e-05, "Pretrain/Loss": 2.1004223823547363, "Pretrain/Loss (Raw)": 2.1650466918945312, "Pretrain/Step": 1217, "Pretrain/Step Time": 8.445204433053732} +{"Pretrain/Learning Rate": 4.8757979140083324e-05, "Pretrain/Loss": 2.100131034851074, "Pretrain/Loss (Raw)": 2.099669933319092, "Pretrain/Step": 1218, "Pretrain/Step Time": 8.445350836962461} +{"Pretrain/Learning Rate": 4.875533478042269e-05, "Pretrain/Loss": 2.1002259254455566, "Pretrain/Loss (Raw)": 2.1410603523254395, "Pretrain/Step": 1219, "Pretrain/Step Time": 8.443127382546663} +{"Pretrain/Learning Rate": 4.875268768059255e-05, "Pretrain/Loss": 2.10017466545105, "Pretrain/Loss (Raw)": 2.1236302852630615, "Pretrain/Step": 1220, "Pretrain/Step Time": 8.439503101631999} +{"Pretrain/Learning Rate": 4.875003784089822e-05, "Pretrain/Loss": 2.1010656356811523, "Pretrain/Loss (Raw)": 2.2489936351776123, "Pretrain/Step": 1221, "Pretrain/Step Time": 8.443242875859141} +{"Pretrain/Learning Rate": 4.874738526164538e-05, "Pretrain/Loss": 2.1005125045776367, "Pretrain/Loss (Raw)": 2.015897750854492, "Pretrain/Step": 1222, "Pretrain/Step Time": 8.444378720596433} +{"Pretrain/Learning Rate": 4.8744729943139996e-05, "Pretrain/Loss": 2.1025028228759766, "Pretrain/Loss (Raw)": 2.209439516067505, "Pretrain/Step": 1223, "Pretrain/Step Time": 8.441358244046569} +{"Pretrain/Learning Rate": 4.8742071885688356e-05, "Pretrain/Loss": 2.1037724018096924, "Pretrain/Loss (Raw)": 2.2982356548309326, "Pretrain/Step": 1224, "Pretrain/Step Time": 8.443375214934349} +{"Pretrain/Learning Rate": 4.8739411089597065e-05, "Pretrain/Loss": 2.1034739017486572, "Pretrain/Loss (Raw)": 2.0980191230773926, "Pretrain/Step": 1225, "Pretrain/Step Time": 8.442294413223863} +{"Pretrain/Learning Rate": 4.8736747555173047e-05, "Pretrain/Loss": 2.101423978805542, "Pretrain/Loss (Raw)": 1.7338505983352661, "Pretrain/Step": 1226, "Pretrain/Step Time": 8.439608965069056} +{"Pretrain/Learning Rate": 4.8734081282723544e-05, "Pretrain/Loss": 2.1019420623779297, "Pretrain/Loss (Raw)": 2.1209189891815186, "Pretrain/Step": 1227, "Pretrain/Step Time": 8.439203348010778} +{"Pretrain/Learning Rate": 4.8731412272556105e-05, "Pretrain/Loss": 2.102104902267456, "Pretrain/Loss (Raw)": 2.018209457397461, "Pretrain/Step": 1228, "Pretrain/Step Time": 8.440806457772851} +{"Pretrain/Learning Rate": 4.87287405249786e-05, "Pretrain/Loss": 2.1025431156158447, "Pretrain/Loss (Raw)": 2.2363691329956055, "Pretrain/Step": 1229, "Pretrain/Step Time": 8.440148461610079} +{"Pretrain/Learning Rate": 4.872606604029921e-05, "Pretrain/Loss": 2.1025209426879883, "Pretrain/Loss (Raw)": 2.263688802719116, "Pretrain/Step": 1230, "Pretrain/Step Time": 8.441656418144703} +{"Pretrain/Learning Rate": 4.872338881882644e-05, "Pretrain/Loss": 2.102597713470459, "Pretrain/Loss (Raw)": 2.1663401126861572, "Pretrain/Step": 1231, "Pretrain/Step Time": 8.441987780854106} +{"Pretrain/Learning Rate": 4.872070886086912e-05, "Pretrain/Loss": 2.1014108657836914, "Pretrain/Loss (Raw)": 2.092700958251953, "Pretrain/Step": 1232, "Pretrain/Step Time": 8.437684506177902} +{"Pretrain/Learning Rate": 4.8718026166736357e-05, "Pretrain/Loss": 2.102932929992676, "Pretrain/Loss (Raw)": 2.1658496856689453, "Pretrain/Step": 1233, "Pretrain/Step Time": 8.439937213435769} +{"Pretrain/Learning Rate": 4.8715340736737616e-05, "Pretrain/Loss": 2.103001594543457, "Pretrain/Loss (Raw)": 2.2064716815948486, "Pretrain/Step": 1234, "Pretrain/Step Time": 8.435377310961485} +{"Pretrain/Learning Rate": 4.871265257118265e-05, "Pretrain/Loss": 2.102200984954834, "Pretrain/Loss (Raw)": 2.139106512069702, "Pretrain/Step": 1235, "Pretrain/Step Time": 8.435298906639218} +{"Pretrain/Learning Rate": 4.870996167038154e-05, "Pretrain/Loss": 2.102531909942627, "Pretrain/Loss (Raw)": 2.069948673248291, "Pretrain/Step": 1236, "Pretrain/Step Time": 8.43260202743113} +{"Pretrain/Learning Rate": 4.870726803464469e-05, "Pretrain/Loss": 2.1017446517944336, "Pretrain/Loss (Raw)": 2.157895088195801, "Pretrain/Step": 1237, "Pretrain/Step Time": 8.433462204411626} +{"Pretrain/Learning Rate": 4.8704571664282806e-05, "Pretrain/Loss": 2.1017813682556152, "Pretrain/Loss (Raw)": 2.129472494125366, "Pretrain/Step": 1238, "Pretrain/Step Time": 8.433816822245717} +{"Pretrain/Learning Rate": 4.870187255960691e-05, "Pretrain/Loss": 2.1019203662872314, "Pretrain/Loss (Raw)": 2.2013020515441895, "Pretrain/Step": 1239, "Pretrain/Step Time": 8.434118010103703} +{"Pretrain/Learning Rate": 4.869917072092834e-05, "Pretrain/Loss": 2.1008365154266357, "Pretrain/Loss (Raw)": 2.1037721633911133, "Pretrain/Step": 1240, "Pretrain/Step Time": 8.433595402166247} +{"Pretrain/Learning Rate": 4.869646614855876e-05, "Pretrain/Loss": 2.1020514965057373, "Pretrain/Loss (Raw)": 2.3513998985290527, "Pretrain/Step": 1241, "Pretrain/Step Time": 8.431324791163206} +{"Pretrain/Learning Rate": 4.869375884281013e-05, "Pretrain/Loss": 2.1016883850097656, "Pretrain/Loss (Raw)": 2.1718640327453613, "Pretrain/Step": 1242, "Pretrain/Step Time": 8.429159441962838} +{"Pretrain/Learning Rate": 4.869104880399475e-05, "Pretrain/Loss": 2.1025471687316895, "Pretrain/Loss (Raw)": 2.158285617828369, "Pretrain/Step": 1243, "Pretrain/Step Time": 8.434223772957921} +{"Pretrain/Learning Rate": 4.868833603242522e-05, "Pretrain/Loss": 2.102062463760376, "Pretrain/Loss (Raw)": 2.1329233646392822, "Pretrain/Step": 1244, "Pretrain/Step Time": 8.432380072772503} +{"Pretrain/Learning Rate": 4.8685620528414445e-05, "Pretrain/Loss": 2.1009063720703125, "Pretrain/Loss (Raw)": 1.9718559980392456, "Pretrain/Step": 1245, "Pretrain/Step Time": 8.43493340909481} +{"Pretrain/Learning Rate": 4.8682902292275664e-05, "Pretrain/Loss": 2.101731538772583, "Pretrain/Loss (Raw)": 2.2281429767608643, "Pretrain/Step": 1246, "Pretrain/Step Time": 8.44035748951137} +{"Pretrain/Learning Rate": 4.868018132432244e-05, "Pretrain/Loss": 2.1012113094329834, "Pretrain/Loss (Raw)": 2.080444574356079, "Pretrain/Step": 1247, "Pretrain/Step Time": 8.437180534005165} +{"Pretrain/Learning Rate": 4.867745762486861e-05, "Pretrain/Loss": 2.101475238800049, "Pretrain/Loss (Raw)": 2.1695950031280518, "Pretrain/Step": 1248, "Pretrain/Step Time": 8.436919379979372} +{"Pretrain/Learning Rate": 4.867473119422837e-05, "Pretrain/Loss": 2.101271629333496, "Pretrain/Loss (Raw)": 1.970141887664795, "Pretrain/Step": 1249, "Pretrain/Step Time": 8.436344496905804} +{"Pretrain/Learning Rate": 4.8672002032716203e-05, "Pretrain/Loss": 2.103592872619629, "Pretrain/Loss (Raw)": 2.2040717601776123, "Pretrain/Step": 1250, "Pretrain/Step Time": 8.436700571328402} +{"Pretrain/Learning Rate": 4.866927014064692e-05, "Pretrain/Loss": 2.1038079261779785, "Pretrain/Loss (Raw)": 2.1053988933563232, "Pretrain/Step": 1251, "Pretrain/Step Time": 8.434264255687594} +{"Pretrain/Learning Rate": 4.866653551833564e-05, "Pretrain/Loss": 2.103480577468872, "Pretrain/Loss (Raw)": 2.0846951007843018, "Pretrain/Step": 1252, "Pretrain/Step Time": 8.434830240905285} +{"Pretrain/Learning Rate": 4.8663798166097816e-05, "Pretrain/Loss": 2.102756977081299, "Pretrain/Loss (Raw)": 1.9322288036346436, "Pretrain/Step": 1253, "Pretrain/Step Time": 8.43429315276444} +{"Pretrain/Learning Rate": 4.8661058084249176e-05, "Pretrain/Loss": 2.102931022644043, "Pretrain/Loss (Raw)": 2.1490604877471924, "Pretrain/Step": 1254, "Pretrain/Step Time": 8.435381278395653} +{"Pretrain/Learning Rate": 4.865831527310581e-05, "Pretrain/Loss": 2.1035690307617188, "Pretrain/Loss (Raw)": 2.098865270614624, "Pretrain/Step": 1255, "Pretrain/Step Time": 8.437539752572775} +{"Pretrain/Learning Rate": 4.86555697329841e-05, "Pretrain/Loss": 2.103712320327759, "Pretrain/Loss (Raw)": 2.158118963241577, "Pretrain/Step": 1256, "Pretrain/Step Time": 8.43729836307466} +{"Pretrain/Learning Rate": 4.865282146420072e-05, "Pretrain/Loss": 2.1014108657836914, "Pretrain/Loss (Raw)": 2.0131075382232666, "Pretrain/Step": 1257, "Pretrain/Step Time": 8.436085814610124} +{"Pretrain/Learning Rate": 4.86500704670727e-05, "Pretrain/Loss": 2.101576805114746, "Pretrain/Loss (Raw)": 2.1290719509124756, "Pretrain/Step": 1258, "Pretrain/Step Time": 8.43830243498087} +{"Pretrain/Learning Rate": 4.8647316741917366e-05, "Pretrain/Loss": 2.10109543800354, "Pretrain/Loss (Raw)": 2.0464441776275635, "Pretrain/Step": 1259, "Pretrain/Step Time": 8.435898516327143} +{"Pretrain/Learning Rate": 4.8644560289052354e-05, "Pretrain/Loss": 2.100059986114502, "Pretrain/Loss (Raw)": 1.9844101667404175, "Pretrain/Step": 1260, "Pretrain/Step Time": 8.434399047866464} +{"Pretrain/Learning Rate": 4.864180110879562e-05, "Pretrain/Loss": 2.1016359329223633, "Pretrain/Loss (Raw)": 2.294729232788086, "Pretrain/Step": 1261, "Pretrain/Step Time": 8.435701979324222} +{"Pretrain/Learning Rate": 4.8639039201465444e-05, "Pretrain/Loss": 2.1005330085754395, "Pretrain/Loss (Raw)": 1.9054101705551147, "Pretrain/Step": 1262, "Pretrain/Step Time": 8.434277484193444} +{"Pretrain/Learning Rate": 4.8636274567380394e-05, "Pretrain/Loss": 2.10009765625, "Pretrain/Loss (Raw)": 2.118102788925171, "Pretrain/Step": 1263, "Pretrain/Step Time": 8.43628192320466} +{"Pretrain/Learning Rate": 4.8633507206859385e-05, "Pretrain/Loss": 2.101046085357666, "Pretrain/Loss (Raw)": 2.096971035003662, "Pretrain/Step": 1264, "Pretrain/Step Time": 8.435883229598403} +{"Pretrain/Learning Rate": 4.863073712022162e-05, "Pretrain/Loss": 2.1024532318115234, "Pretrain/Loss (Raw)": 2.2787156105041504, "Pretrain/Step": 1265, "Pretrain/Step Time": 8.434685591608286} +{"Pretrain/Learning Rate": 4.862796430778663e-05, "Pretrain/Loss": 2.1019287109375, "Pretrain/Loss (Raw)": 1.9404016733169556, "Pretrain/Step": 1266, "Pretrain/Step Time": 8.434061259031296} +{"Pretrain/Learning Rate": 4.8625188769874274e-05, "Pretrain/Loss": 2.1017842292785645, "Pretrain/Loss (Raw)": 2.0106539726257324, "Pretrain/Step": 1267, "Pretrain/Step Time": 8.434073435142636} +{"Pretrain/Learning Rate": 4.8622410506804686e-05, "Pretrain/Loss": 2.1016952991485596, "Pretrain/Loss (Raw)": 2.058403253555298, "Pretrain/Step": 1268, "Pretrain/Step Time": 8.438751207664609} +{"Pretrain/Learning Rate": 4.8619629518898344e-05, "Pretrain/Loss": 2.101820707321167, "Pretrain/Loss (Raw)": 2.039674758911133, "Pretrain/Step": 1269, "Pretrain/Step Time": 8.437201004475355} +{"Pretrain/Learning Rate": 4.861684580647605e-05, "Pretrain/Loss": 2.1011993885040283, "Pretrain/Loss (Raw)": 2.0272607803344727, "Pretrain/Step": 1270, "Pretrain/Step Time": 8.43402436748147} +{"Pretrain/Learning Rate": 4.861405936985888e-05, "Pretrain/Loss": 2.1011457443237305, "Pretrain/Loss (Raw)": 2.1404213905334473, "Pretrain/Step": 1271, "Pretrain/Step Time": 8.435845721513033} +{"Pretrain/Learning Rate": 4.861127020936827e-05, "Pretrain/Loss": 2.1017870903015137, "Pretrain/Loss (Raw)": 2.180128335952759, "Pretrain/Step": 1272, "Pretrain/Step Time": 8.435765415430069} +{"Pretrain/Learning Rate": 4.8608478325325935e-05, "Pretrain/Loss": 2.1026530265808105, "Pretrain/Loss (Raw)": 2.1600587368011475, "Pretrain/Step": 1273, "Pretrain/Step Time": 8.434763861820102} +{"Pretrain/Learning Rate": 4.860568371805392e-05, "Pretrain/Loss": 2.103179931640625, "Pretrain/Loss (Raw)": 2.2024288177490234, "Pretrain/Step": 1274, "Pretrain/Step Time": 8.43592818081379} +{"Pretrain/Learning Rate": 4.860288638787458e-05, "Pretrain/Loss": 2.1059722900390625, "Pretrain/Loss (Raw)": 2.1979753971099854, "Pretrain/Step": 1275, "Pretrain/Step Time": 8.439931904897094} +{"Pretrain/Learning Rate": 4.860008633511059e-05, "Pretrain/Loss": 2.102907180786133, "Pretrain/Loss (Raw)": 1.730579137802124, "Pretrain/Step": 1276, "Pretrain/Step Time": 8.44142011553049} +{"Pretrain/Learning Rate": 4.859728356008495e-05, "Pretrain/Loss": 2.1013526916503906, "Pretrain/Loss (Raw)": 2.0125977993011475, "Pretrain/Step": 1277, "Pretrain/Step Time": 8.44087840989232} +{"Pretrain/Learning Rate": 4.859447806312093e-05, "Pretrain/Loss": 2.101661205291748, "Pretrain/Loss (Raw)": 2.143253803253174, "Pretrain/Step": 1278, "Pretrain/Step Time": 8.440496627241373} +{"Pretrain/Learning Rate": 4.859166984454216e-05, "Pretrain/Loss": 2.1019933223724365, "Pretrain/Loss (Raw)": 2.236971855163574, "Pretrain/Step": 1279, "Pretrain/Step Time": 8.44081219099462} +{"Pretrain/Learning Rate": 4.858885890467256e-05, "Pretrain/Loss": 2.102705240249634, "Pretrain/Loss (Raw)": 2.071606397628784, "Pretrain/Step": 1280, "Pretrain/Step Time": 8.440442897379398} +{"Pretrain/Learning Rate": 4.8586045243836386e-05, "Pretrain/Loss": 2.103355646133423, "Pretrain/Loss (Raw)": 2.2561731338500977, "Pretrain/Step": 1281, "Pretrain/Step Time": 8.44199282862246} +{"Pretrain/Learning Rate": 4.858322886235817e-05, "Pretrain/Loss": 2.102569103240967, "Pretrain/Loss (Raw)": 1.9822219610214233, "Pretrain/Step": 1282, "Pretrain/Step Time": 8.441118996590376} +{"Pretrain/Learning Rate": 4.85804097605628e-05, "Pretrain/Loss": 2.104269027709961, "Pretrain/Loss (Raw)": 2.1568331718444824, "Pretrain/Step": 1283, "Pretrain/Step Time": 8.444304859265685} +{"Pretrain/Learning Rate": 4.857758793877545e-05, "Pretrain/Loss": 2.10231351852417, "Pretrain/Loss (Raw)": 1.9954659938812256, "Pretrain/Step": 1284, "Pretrain/Step Time": 8.44334058277309} +{"Pretrain/Learning Rate": 4.8574763397321614e-05, "Pretrain/Loss": 2.1028358936309814, "Pretrain/Loss (Raw)": 2.1051714420318604, "Pretrain/Step": 1285, "Pretrain/Step Time": 8.442191461101174} +{"Pretrain/Learning Rate": 4.857193613652711e-05, "Pretrain/Loss": 2.102262496948242, "Pretrain/Loss (Raw)": 1.992152452468872, "Pretrain/Step": 1286, "Pretrain/Step Time": 8.445366881787777} +{"Pretrain/Learning Rate": 4.856910615671805e-05, "Pretrain/Loss": 2.104304552078247, "Pretrain/Loss (Raw)": 2.3863706588745117, "Pretrain/Step": 1287, "Pretrain/Step Time": 8.444210143759847} +{"Pretrain/Learning Rate": 4.856627345822088e-05, "Pretrain/Loss": 2.1057376861572266, "Pretrain/Loss (Raw)": 2.2407915592193604, "Pretrain/Step": 1288, "Pretrain/Step Time": 8.441743416711688} +{"Pretrain/Learning Rate": 4.8563438041362354e-05, "Pretrain/Loss": 2.105942726135254, "Pretrain/Loss (Raw)": 2.051344871520996, "Pretrain/Step": 1289, "Pretrain/Step Time": 8.442135946825147} +{"Pretrain/Learning Rate": 4.8560599906469515e-05, "Pretrain/Loss": 2.1060454845428467, "Pretrain/Loss (Raw)": 2.193851947784424, "Pretrain/Step": 1290, "Pretrain/Step Time": 8.44429819099605} +{"Pretrain/Learning Rate": 4.855775905386977e-05, "Pretrain/Loss": 2.105966567993164, "Pretrain/Loss (Raw)": 2.112626314163208, "Pretrain/Step": 1291, "Pretrain/Step Time": 8.44782143086195} +{"Pretrain/Learning Rate": 4.855491548389079e-05, "Pretrain/Loss": 2.1063790321350098, "Pretrain/Loss (Raw)": 2.136192560195923, "Pretrain/Step": 1292, "Pretrain/Step Time": 8.450694624334574} +{"Pretrain/Learning Rate": 4.8552069196860595e-05, "Pretrain/Loss": 2.1082139015197754, "Pretrain/Loss (Raw)": 2.22145938873291, "Pretrain/Step": 1293, "Pretrain/Step Time": 8.450496042147279} +{"Pretrain/Learning Rate": 4.8549220193107494e-05, "Pretrain/Loss": 2.106330394744873, "Pretrain/Loss (Raw)": 1.8684650659561157, "Pretrain/Step": 1294, "Pretrain/Step Time": 8.450507026165724} +{"Pretrain/Learning Rate": 4.854636847296011e-05, "Pretrain/Loss": 2.1045589447021484, "Pretrain/Loss (Raw)": 1.9421380758285522, "Pretrain/Step": 1295, "Pretrain/Step Time": 8.450809797272086} +{"Pretrain/Learning Rate": 4.8543514036747405e-05, "Pretrain/Loss": 2.1051723957061768, "Pretrain/Loss (Raw)": 2.0941803455352783, "Pretrain/Step": 1296, "Pretrain/Step Time": 8.447707895189524} +{"Pretrain/Learning Rate": 4.854065688479863e-05, "Pretrain/Loss": 2.103433132171631, "Pretrain/Loss (Raw)": 1.870863437652588, "Pretrain/Step": 1297, "Pretrain/Step Time": 8.451395060867071} +{"Pretrain/Learning Rate": 4.8537797017443356e-05, "Pretrain/Loss": 2.1049869060516357, "Pretrain/Loss (Raw)": 2.2502949237823486, "Pretrain/Step": 1298, "Pretrain/Step Time": 8.45395147614181} +{"Pretrain/Learning Rate": 4.853493443501147e-05, "Pretrain/Loss": 2.1063995361328125, "Pretrain/Loss (Raw)": 2.2549078464508057, "Pretrain/Step": 1299, "Pretrain/Step Time": 8.454039596021175} +{"Pretrain/Learning Rate": 4.8532069137833156e-05, "Pretrain/Loss": 2.105823040008545, "Pretrain/Loss (Raw)": 2.071890354156494, "Pretrain/Step": 1300, "Pretrain/Step Time": 8.451280480250716} +{"Pretrain/Learning Rate": 4.852920112623895e-05, "Pretrain/Loss": 2.104442834854126, "Pretrain/Loss (Raw)": 2.0202107429504395, "Pretrain/Step": 1301, "Pretrain/Step Time": 8.451248705387115} +{"Pretrain/Learning Rate": 4.8526330400559664e-05, "Pretrain/Loss": 2.103804588317871, "Pretrain/Loss (Raw)": 2.001657009124756, "Pretrain/Step": 1302, "Pretrain/Step Time": 8.452012604102492} +{"Pretrain/Learning Rate": 4.8523456961126425e-05, "Pretrain/Loss": 2.1044809818267822, "Pretrain/Loss (Raw)": 2.062513828277588, "Pretrain/Step": 1303, "Pretrain/Step Time": 8.450452852994204} +{"Pretrain/Learning Rate": 4.852058080827069e-05, "Pretrain/Loss": 2.103992223739624, "Pretrain/Loss (Raw)": 2.1078290939331055, "Pretrain/Step": 1304, "Pretrain/Step Time": 8.451651690527797} +{"Pretrain/Learning Rate": 4.851770194232423e-05, "Pretrain/Loss": 2.102034568786621, "Pretrain/Loss (Raw)": 1.9053993225097656, "Pretrain/Step": 1305, "Pretrain/Step Time": 8.451694909483194} +{"Pretrain/Learning Rate": 4.8514820363619115e-05, "Pretrain/Loss": 2.099071502685547, "Pretrain/Loss (Raw)": 1.8693302869796753, "Pretrain/Step": 1306, "Pretrain/Step Time": 8.453891854733229} +{"Pretrain/Learning Rate": 4.8511936072487735e-05, "Pretrain/Loss": 2.0997161865234375, "Pretrain/Loss (Raw)": 2.168955087661743, "Pretrain/Step": 1307, "Pretrain/Step Time": 8.451957607641816} +{"Pretrain/Learning Rate": 4.850904906926279e-05, "Pretrain/Loss": 2.099252462387085, "Pretrain/Loss (Raw)": 2.0516738891601562, "Pretrain/Step": 1308, "Pretrain/Step Time": 8.458107324317098} +{"Pretrain/Learning Rate": 4.85061593542773e-05, "Pretrain/Loss": 2.100344181060791, "Pretrain/Loss (Raw)": 2.1059489250183105, "Pretrain/Step": 1309, "Pretrain/Step Time": 8.457948552444577} +{"Pretrain/Learning Rate": 4.850326692786459e-05, "Pretrain/Loss": 2.099092960357666, "Pretrain/Loss (Raw)": 1.9696555137634277, "Pretrain/Step": 1310, "Pretrain/Step Time": 8.45468639396131} +{"Pretrain/Learning Rate": 4.850037179035829e-05, "Pretrain/Loss": 2.098314046859741, "Pretrain/Loss (Raw)": 2.0248477458953857, "Pretrain/Step": 1311, "Pretrain/Step Time": 8.45265150256455} +{"Pretrain/Learning Rate": 4.849747394209237e-05, "Pretrain/Loss": 2.0965325832366943, "Pretrain/Loss (Raw)": 1.9189420938491821, "Pretrain/Step": 1312, "Pretrain/Step Time": 8.452592451125383} +{"Pretrain/Learning Rate": 4.849457338340109e-05, "Pretrain/Loss": 2.0957913398742676, "Pretrain/Loss (Raw)": 2.0240910053253174, "Pretrain/Step": 1313, "Pretrain/Step Time": 8.450576420873404} +{"Pretrain/Learning Rate": 4.849167011461903e-05, "Pretrain/Loss": 2.094038486480713, "Pretrain/Loss (Raw)": 1.8709816932678223, "Pretrain/Step": 1314, "Pretrain/Step Time": 8.451276211068034} +{"Pretrain/Learning Rate": 4.8488764136081065e-05, "Pretrain/Loss": 2.0927605628967285, "Pretrain/Loss (Raw)": 1.9259767532348633, "Pretrain/Step": 1315, "Pretrain/Step Time": 8.455651948228478} +{"Pretrain/Learning Rate": 4.848585544812242e-05, "Pretrain/Loss": 2.0925910472869873, "Pretrain/Loss (Raw)": 2.1249372959136963, "Pretrain/Step": 1316, "Pretrain/Step Time": 8.454483192414045} +{"Pretrain/Learning Rate": 4.84829440510786e-05, "Pretrain/Loss": 2.090867519378662, "Pretrain/Loss (Raw)": 1.9914735555648804, "Pretrain/Step": 1317, "Pretrain/Step Time": 8.454416513442993} +{"Pretrain/Learning Rate": 4.848002994528543e-05, "Pretrain/Loss": 2.091761827468872, "Pretrain/Loss (Raw)": 2.123758554458618, "Pretrain/Step": 1318, "Pretrain/Step Time": 8.452748667448759} +{"Pretrain/Learning Rate": 4.847711313107907e-05, "Pretrain/Loss": 2.091341018676758, "Pretrain/Loss (Raw)": 2.0528712272644043, "Pretrain/Step": 1319, "Pretrain/Step Time": 8.449053002521396} +{"Pretrain/Learning Rate": 4.847419360879596e-05, "Pretrain/Loss": 2.0912599563598633, "Pretrain/Loss (Raw)": 2.089559316635132, "Pretrain/Step": 1320, "Pretrain/Step Time": 8.449235565960407} +{"Pretrain/Learning Rate": 4.847127137877286e-05, "Pretrain/Loss": 2.0920181274414062, "Pretrain/Loss (Raw)": 2.1248574256896973, "Pretrain/Step": 1321, "Pretrain/Step Time": 8.450464921072125} +{"Pretrain/Learning Rate": 4.846834644134686e-05, "Pretrain/Loss": 2.0919952392578125, "Pretrain/Loss (Raw)": 2.105642318725586, "Pretrain/Step": 1322, "Pretrain/Step Time": 8.44956805743277} +{"Pretrain/Learning Rate": 4.846541879685533e-05, "Pretrain/Loss": 2.0923213958740234, "Pretrain/Loss (Raw)": 2.0086193084716797, "Pretrain/Step": 1323, "Pretrain/Step Time": 8.4516841173172} +{"Pretrain/Learning Rate": 4.846248844563601e-05, "Pretrain/Loss": 2.093174457550049, "Pretrain/Loss (Raw)": 2.0432419776916504, "Pretrain/Step": 1324, "Pretrain/Step Time": 8.448238730430603} +{"Pretrain/Learning Rate": 4.845955538802688e-05, "Pretrain/Loss": 2.0932443141937256, "Pretrain/Loss (Raw)": 2.1330416202545166, "Pretrain/Step": 1325, "Pretrain/Step Time": 8.451244501397014} +{"Pretrain/Learning Rate": 4.8456619624366286e-05, "Pretrain/Loss": 2.0934314727783203, "Pretrain/Loss (Raw)": 2.121342897415161, "Pretrain/Step": 1326, "Pretrain/Step Time": 8.452412441372871} +{"Pretrain/Learning Rate": 4.845368115499286e-05, "Pretrain/Loss": 2.093970775604248, "Pretrain/Loss (Raw)": 2.2145004272460938, "Pretrain/Step": 1327, "Pretrain/Step Time": 8.450189661234617} +{"Pretrain/Learning Rate": 4.8450739980245555e-05, "Pretrain/Loss": 2.09250545501709, "Pretrain/Loss (Raw)": 1.9779794216156006, "Pretrain/Step": 1328, "Pretrain/Step Time": 8.450751533731818} +{"Pretrain/Learning Rate": 4.8447796100463626e-05, "Pretrain/Loss": 2.0924339294433594, "Pretrain/Loss (Raw)": 2.121412515640259, "Pretrain/Step": 1329, "Pretrain/Step Time": 8.454649055376649} +{"Pretrain/Learning Rate": 4.844484951598667e-05, "Pretrain/Loss": 2.0929579734802246, "Pretrain/Loss (Raw)": 2.280979633331299, "Pretrain/Step": 1330, "Pretrain/Step Time": 8.450443025678396} +{"Pretrain/Learning Rate": 4.844190022715456e-05, "Pretrain/Loss": 2.0935916900634766, "Pretrain/Loss (Raw)": 2.1460764408111572, "Pretrain/Step": 1331, "Pretrain/Step Time": 8.45171320438385} +{"Pretrain/Learning Rate": 4.843894823430749e-05, "Pretrain/Loss": 2.0931458473205566, "Pretrain/Loss (Raw)": 1.9353814125061035, "Pretrain/Step": 1332, "Pretrain/Step Time": 8.453511890023947} +{"Pretrain/Learning Rate": 4.843599353778598e-05, "Pretrain/Loss": 2.0927469730377197, "Pretrain/Loss (Raw)": 2.05265474319458, "Pretrain/Step": 1333, "Pretrain/Step Time": 8.451069165021181} +{"Pretrain/Learning Rate": 4.843303613793085e-05, "Pretrain/Loss": 2.0916810035705566, "Pretrain/Loss (Raw)": 2.1433792114257812, "Pretrain/Step": 1334, "Pretrain/Step Time": 8.449936395511031} +{"Pretrain/Learning Rate": 4.843007603508324e-05, "Pretrain/Loss": 2.090193033218384, "Pretrain/Loss (Raw)": 2.0546226501464844, "Pretrain/Step": 1335, "Pretrain/Step Time": 8.45106991007924} +{"Pretrain/Learning Rate": 4.842711322958459e-05, "Pretrain/Loss": 2.0913875102996826, "Pretrain/Loss (Raw)": 2.12522292137146, "Pretrain/Step": 1336, "Pretrain/Step Time": 8.45017235726118} +{"Pretrain/Learning Rate": 4.842414772177667e-05, "Pretrain/Loss": 2.09171199798584, "Pretrain/Loss (Raw)": 2.1147749423980713, "Pretrain/Step": 1337, "Pretrain/Step Time": 8.450156839564443} +{"Pretrain/Learning Rate": 4.842117951200153e-05, "Pretrain/Loss": 2.093945026397705, "Pretrain/Loss (Raw)": 2.210919141769409, "Pretrain/Step": 1338, "Pretrain/Step Time": 8.46089049614966} +{"Pretrain/Learning Rate": 4.841820860060157e-05, "Pretrain/Loss": 2.093258857727051, "Pretrain/Loss (Raw)": 2.0734548568725586, "Pretrain/Step": 1339, "Pretrain/Step Time": 8.460942329838872} +{"Pretrain/Learning Rate": 4.841523498791948e-05, "Pretrain/Loss": 2.0927155017852783, "Pretrain/Loss (Raw)": 2.0037684440612793, "Pretrain/Step": 1340, "Pretrain/Step Time": 8.457907415926456} +{"Pretrain/Learning Rate": 4.841225867429826e-05, "Pretrain/Loss": 2.0919077396392822, "Pretrain/Loss (Raw)": 2.062204599380493, "Pretrain/Step": 1341, "Pretrain/Step Time": 8.458499055355787} +{"Pretrain/Learning Rate": 4.840927966008123e-05, "Pretrain/Loss": 2.092254638671875, "Pretrain/Loss (Raw)": 2.0485033988952637, "Pretrain/Step": 1342, "Pretrain/Step Time": 8.460826495662332} +{"Pretrain/Learning Rate": 4.840629794561202e-05, "Pretrain/Loss": 2.093991994857788, "Pretrain/Loss (Raw)": 2.058253049850464, "Pretrain/Step": 1343, "Pretrain/Step Time": 8.4573724437505} +{"Pretrain/Learning Rate": 4.840331353123456e-05, "Pretrain/Loss": 2.0944995880126953, "Pretrain/Loss (Raw)": 2.1487205028533936, "Pretrain/Step": 1344, "Pretrain/Step Time": 8.460637541487813} +{"Pretrain/Learning Rate": 4.8400326417293115e-05, "Pretrain/Loss": 2.0933034420013428, "Pretrain/Loss (Raw)": 2.0119547843933105, "Pretrain/Step": 1345, "Pretrain/Step Time": 8.462315618991852} +{"Pretrain/Learning Rate": 4.839733660413224e-05, "Pretrain/Loss": 2.092984199523926, "Pretrain/Loss (Raw)": 2.0588181018829346, "Pretrain/Step": 1346, "Pretrain/Step Time": 8.462902471423149} +{"Pretrain/Learning Rate": 4.8394344092096814e-05, "Pretrain/Loss": 2.091641902923584, "Pretrain/Loss (Raw)": 1.9692299365997314, "Pretrain/Step": 1347, "Pretrain/Step Time": 8.462658001109958} +{"Pretrain/Learning Rate": 4.839134888153202e-05, "Pretrain/Loss": 2.09152889251709, "Pretrain/Loss (Raw)": 2.1091678142547607, "Pretrain/Step": 1348, "Pretrain/Step Time": 8.464539974927902} +{"Pretrain/Learning Rate": 4.8388350972783346e-05, "Pretrain/Loss": 2.089430809020996, "Pretrain/Loss (Raw)": 1.9804643392562866, "Pretrain/Step": 1349, "Pretrain/Step Time": 8.462295586243272} +{"Pretrain/Learning Rate": 4.8385350366196605e-05, "Pretrain/Loss": 2.0903587341308594, "Pretrain/Loss (Raw)": 2.134633779525757, "Pretrain/Step": 1350, "Pretrain/Step Time": 8.46242168918252} +{"Pretrain/Learning Rate": 4.838234706211792e-05, "Pretrain/Loss": 2.088278293609619, "Pretrain/Loss (Raw)": 1.9431850910186768, "Pretrain/Step": 1351, "Pretrain/Step Time": 8.461426319554448} +{"Pretrain/Learning Rate": 4.8379341060893725e-05, "Pretrain/Loss": 2.0865705013275146, "Pretrain/Loss (Raw)": 2.0796098709106445, "Pretrain/Step": 1352, "Pretrain/Step Time": 8.458552932366729} +{"Pretrain/Learning Rate": 4.8376332362870745e-05, "Pretrain/Loss": 2.085498332977295, "Pretrain/Loss (Raw)": 1.960778832435608, "Pretrain/Step": 1353, "Pretrain/Step Time": 8.459599973633885} +{"Pretrain/Learning Rate": 4.8373320968396046e-05, "Pretrain/Loss": 2.087106227874756, "Pretrain/Loss (Raw)": 1.9396543502807617, "Pretrain/Step": 1354, "Pretrain/Step Time": 8.457692064344883} +{"Pretrain/Learning Rate": 4.837030687781699e-05, "Pretrain/Loss": 2.0854945182800293, "Pretrain/Loss (Raw)": 1.914629578590393, "Pretrain/Step": 1355, "Pretrain/Step Time": 8.460619177669287} +{"Pretrain/Learning Rate": 4.8367290091481245e-05, "Pretrain/Loss": 2.085818290710449, "Pretrain/Loss (Raw)": 2.0596868991851807, "Pretrain/Step": 1356, "Pretrain/Step Time": 8.462946342304349} +{"Pretrain/Learning Rate": 4.8364270609736794e-05, "Pretrain/Loss": 2.083667755126953, "Pretrain/Loss (Raw)": 1.9611008167266846, "Pretrain/Step": 1357, "Pretrain/Step Time": 8.4641971308738} +{"Pretrain/Learning Rate": 4.836124843293195e-05, "Pretrain/Loss": 2.0831832885742188, "Pretrain/Loss (Raw)": 2.2016730308532715, "Pretrain/Step": 1358, "Pretrain/Step Time": 8.46712158806622} +{"Pretrain/Learning Rate": 4.8358223561415304e-05, "Pretrain/Loss": 2.0820634365081787, "Pretrain/Loss (Raw)": 2.0229837894439697, "Pretrain/Step": 1359, "Pretrain/Step Time": 8.46848488226533} +{"Pretrain/Learning Rate": 4.835519599553578e-05, "Pretrain/Loss": 2.080629348754883, "Pretrain/Loss (Raw)": 1.909103512763977, "Pretrain/Step": 1360, "Pretrain/Step Time": 8.471196284517646} +{"Pretrain/Learning Rate": 4.8352165735642604e-05, "Pretrain/Loss": 2.0793638229370117, "Pretrain/Loss (Raw)": 2.00388240814209, "Pretrain/Step": 1361, "Pretrain/Step Time": 8.470868891105056} +{"Pretrain/Learning Rate": 4.8349132782085316e-05, "Pretrain/Loss": 2.077639579772949, "Pretrain/Loss (Raw)": 1.9857600927352905, "Pretrain/Step": 1362, "Pretrain/Step Time": 8.470652094110847} +{"Pretrain/Learning Rate": 4.8346097135213766e-05, "Pretrain/Loss": 2.0773658752441406, "Pretrain/Loss (Raw)": 2.104081392288208, "Pretrain/Step": 1363, "Pretrain/Step Time": 8.470788072794676} +{"Pretrain/Learning Rate": 4.834305879537813e-05, "Pretrain/Loss": 2.0785577297210693, "Pretrain/Loss (Raw)": 2.222529172897339, "Pretrain/Step": 1364, "Pretrain/Step Time": 8.471665691584349} +{"Pretrain/Learning Rate": 4.8340017762928845e-05, "Pretrain/Loss": 2.0770368576049805, "Pretrain/Loss (Raw)": 1.9632132053375244, "Pretrain/Step": 1365, "Pretrain/Step Time": 8.473242208361626} +{"Pretrain/Learning Rate": 4.833697403821672e-05, "Pretrain/Loss": 2.0773606300354004, "Pretrain/Loss (Raw)": 2.1709065437316895, "Pretrain/Step": 1366, "Pretrain/Step Time": 8.473594339564443} +{"Pretrain/Learning Rate": 4.833392762159285e-05, "Pretrain/Loss": 2.0755248069763184, "Pretrain/Loss (Raw)": 1.9663158655166626, "Pretrain/Step": 1367, "Pretrain/Step Time": 8.473362941294909} +{"Pretrain/Learning Rate": 4.833087851340862e-05, "Pretrain/Loss": 2.0752360820770264, "Pretrain/Loss (Raw)": 2.0668227672576904, "Pretrain/Step": 1368, "Pretrain/Step Time": 8.473569938912988} +{"Pretrain/Learning Rate": 4.832782671401575e-05, "Pretrain/Loss": 2.074145793914795, "Pretrain/Loss (Raw)": 2.21185040473938, "Pretrain/Step": 1369, "Pretrain/Step Time": 8.473857786506414} +{"Pretrain/Learning Rate": 4.8324772223766276e-05, "Pretrain/Loss": 2.074441909790039, "Pretrain/Loss (Raw)": 2.209754467010498, "Pretrain/Step": 1370, "Pretrain/Step Time": 8.47672319598496} +{"Pretrain/Learning Rate": 4.832171504301252e-05, "Pretrain/Loss": 2.0730295181274414, "Pretrain/Loss (Raw)": 1.977523684501648, "Pretrain/Step": 1371, "Pretrain/Step Time": 8.471482386812568} +{"Pretrain/Learning Rate": 4.8318655172107126e-05, "Pretrain/Loss": 2.0716352462768555, "Pretrain/Loss (Raw)": 1.9544622898101807, "Pretrain/Step": 1372, "Pretrain/Step Time": 8.4725320674479} +{"Pretrain/Learning Rate": 4.831559261140305e-05, "Pretrain/Loss": 2.0725598335266113, "Pretrain/Loss (Raw)": 2.0901761054992676, "Pretrain/Step": 1373, "Pretrain/Step Time": 8.474120387807488} +{"Pretrain/Learning Rate": 4.831252736125357e-05, "Pretrain/Loss": 2.072303295135498, "Pretrain/Loss (Raw)": 2.1953125, "Pretrain/Step": 1374, "Pretrain/Step Time": 8.469404924660921} +{"Pretrain/Learning Rate": 4.830945942201224e-05, "Pretrain/Loss": 2.0727152824401855, "Pretrain/Loss (Raw)": 2.133165121078491, "Pretrain/Step": 1375, "Pretrain/Step Time": 8.472003176808357} +{"Pretrain/Learning Rate": 4.830638879403297e-05, "Pretrain/Loss": 2.0723116397857666, "Pretrain/Loss (Raw)": 2.117943286895752, "Pretrain/Step": 1376, "Pretrain/Step Time": 8.470830643549562} +{"Pretrain/Learning Rate": 4.830331547766993e-05, "Pretrain/Loss": 2.0739338397979736, "Pretrain/Loss (Raw)": 2.1777679920196533, "Pretrain/Step": 1377, "Pretrain/Step Time": 8.472054421901703} +{"Pretrain/Learning Rate": 4.830023947327764e-05, "Pretrain/Loss": 2.0733304023742676, "Pretrain/Loss (Raw)": 2.1268255710601807, "Pretrain/Step": 1378, "Pretrain/Step Time": 8.470611182972789} +{"Pretrain/Learning Rate": 4.8297160781210925e-05, "Pretrain/Loss": 2.0722553730010986, "Pretrain/Loss (Raw)": 1.9678280353546143, "Pretrain/Step": 1379, "Pretrain/Step Time": 8.473211536183953} +{"Pretrain/Learning Rate": 4.82940794018249e-05, "Pretrain/Loss": 2.071133613586426, "Pretrain/Loss (Raw)": 1.9411075115203857, "Pretrain/Step": 1380, "Pretrain/Step Time": 8.474576395004988} +{"Pretrain/Learning Rate": 4.8290995335475e-05, "Pretrain/Loss": 2.0712661743164062, "Pretrain/Loss (Raw)": 1.9491674900054932, "Pretrain/Step": 1381, "Pretrain/Step Time": 8.473401742056012} +{"Pretrain/Learning Rate": 4.828790858251697e-05, "Pretrain/Loss": 2.0687270164489746, "Pretrain/Loss (Raw)": 1.8240727186203003, "Pretrain/Step": 1382, "Pretrain/Step Time": 8.471683954820037} +{"Pretrain/Learning Rate": 4.828481914330687e-05, "Pretrain/Loss": 2.069701910018921, "Pretrain/Loss (Raw)": 2.2236487865448, "Pretrain/Step": 1383, "Pretrain/Step Time": 8.474680224433541} +{"Pretrain/Learning Rate": 4.828172701820106e-05, "Pretrain/Loss": 2.069842576980591, "Pretrain/Loss (Raw)": 2.176121473312378, "Pretrain/Step": 1384, "Pretrain/Step Time": 8.475262736901641} +{"Pretrain/Learning Rate": 4.827863220755623e-05, "Pretrain/Loss": 2.07043719291687, "Pretrain/Loss (Raw)": 2.0891940593719482, "Pretrain/Step": 1385, "Pretrain/Step Time": 8.474149515852332} +{"Pretrain/Learning Rate": 4.827553471172935e-05, "Pretrain/Loss": 2.0713589191436768, "Pretrain/Loss (Raw)": 2.2470736503601074, "Pretrain/Step": 1386, "Pretrain/Step Time": 8.470638170838356} +{"Pretrain/Learning Rate": 4.827243453107772e-05, "Pretrain/Loss": 2.0719051361083984, "Pretrain/Loss (Raw)": 2.116384267807007, "Pretrain/Step": 1387, "Pretrain/Step Time": 8.472302958369255} +{"Pretrain/Learning Rate": 4.826933166595895e-05, "Pretrain/Loss": 2.073470115661621, "Pretrain/Loss (Raw)": 2.18469500541687, "Pretrain/Step": 1388, "Pretrain/Step Time": 8.475985227152705} +{"Pretrain/Learning Rate": 4.826622611673094e-05, "Pretrain/Loss": 2.071335792541504, "Pretrain/Loss (Raw)": 2.0215585231781006, "Pretrain/Step": 1389, "Pretrain/Step Time": 8.474703101441264} +{"Pretrain/Learning Rate": 4.826311788375193e-05, "Pretrain/Loss": 2.0728745460510254, "Pretrain/Loss (Raw)": 2.1023457050323486, "Pretrain/Step": 1390, "Pretrain/Step Time": 8.474283078685403} +{"Pretrain/Learning Rate": 4.826000696738045e-05, "Pretrain/Loss": 2.071347713470459, "Pretrain/Loss (Raw)": 1.9227056503295898, "Pretrain/Step": 1391, "Pretrain/Step Time": 8.475682811811566} +{"Pretrain/Learning Rate": 4.825689336797534e-05, "Pretrain/Loss": 2.0721259117126465, "Pretrain/Loss (Raw)": 2.196561813354492, "Pretrain/Step": 1392, "Pretrain/Step Time": 8.473825167864561} +{"Pretrain/Learning Rate": 4.825377708589575e-05, "Pretrain/Loss": 2.069903612136841, "Pretrain/Loss (Raw)": 1.9942351579666138, "Pretrain/Step": 1393, "Pretrain/Step Time": 8.478149516507983} +{"Pretrain/Learning Rate": 4.8250658121501144e-05, "Pretrain/Loss": 2.0721168518066406, "Pretrain/Loss (Raw)": 2.2236945629119873, "Pretrain/Step": 1394, "Pretrain/Step Time": 8.473710499703884} +{"Pretrain/Learning Rate": 4.82475364751513e-05, "Pretrain/Loss": 2.071305751800537, "Pretrain/Loss (Raw)": 1.906862735748291, "Pretrain/Step": 1395, "Pretrain/Step Time": 8.475794900208712} +{"Pretrain/Learning Rate": 4.8244412147206284e-05, "Pretrain/Loss": 2.0717287063598633, "Pretrain/Loss (Raw)": 2.1125271320343018, "Pretrain/Step": 1396, "Pretrain/Step Time": 8.473299803212285} +{"Pretrain/Learning Rate": 4.8241285138026506e-05, "Pretrain/Loss": 2.0708160400390625, "Pretrain/Loss (Raw)": 1.9228450059890747, "Pretrain/Step": 1397, "Pretrain/Step Time": 8.47400601580739} +{"Pretrain/Learning Rate": 4.823815544797265e-05, "Pretrain/Loss": 2.071016311645508, "Pretrain/Loss (Raw)": 2.052919864654541, "Pretrain/Step": 1398, "Pretrain/Step Time": 8.475326092913747} +{"Pretrain/Learning Rate": 4.823502307740573e-05, "Pretrain/Loss": 2.0704853534698486, "Pretrain/Loss (Raw)": 2.0724575519561768, "Pretrain/Step": 1399, "Pretrain/Step Time": 8.477739859372377} +{"Pretrain/Learning Rate": 4.823188802668707e-05, "Pretrain/Loss": 2.0704662799835205, "Pretrain/Loss (Raw)": 2.177675247192383, "Pretrain/Step": 1400, "Pretrain/Step Time": 8.477526439353824} +{"Pretrain/Learning Rate": 4.8228750296178275e-05, "Pretrain/Loss": 2.06998872756958, "Pretrain/Loss (Raw)": 2.0989110469818115, "Pretrain/Step": 1401, "Pretrain/Step Time": 8.474311901256442} +{"Pretrain/Learning Rate": 4.822560988624131e-05, "Pretrain/Loss": 2.069498062133789, "Pretrain/Loss (Raw)": 2.139631748199463, "Pretrain/Step": 1402, "Pretrain/Step Time": 8.47645140439272} +{"Pretrain/Learning Rate": 4.8222466797238396e-05, "Pretrain/Loss": 2.0685248374938965, "Pretrain/Loss (Raw)": 2.073420286178589, "Pretrain/Step": 1403, "Pretrain/Step Time": 8.471131715923548} +{"Pretrain/Learning Rate": 4.821932102953211e-05, "Pretrain/Loss": 2.0700302124023438, "Pretrain/Loss (Raw)": 1.9232583045959473, "Pretrain/Step": 1404, "Pretrain/Step Time": 8.471746161580086} +{"Pretrain/Learning Rate": 4.821617258348529e-05, "Pretrain/Loss": 2.071234941482544, "Pretrain/Loss (Raw)": 2.1668195724487305, "Pretrain/Step": 1405, "Pretrain/Step Time": 8.472878899425268} +{"Pretrain/Learning Rate": 4.821302145946113e-05, "Pretrain/Loss": 2.0702810287475586, "Pretrain/Loss (Raw)": 2.0211362838745117, "Pretrain/Step": 1406, "Pretrain/Step Time": 8.47551610134542} +{"Pretrain/Learning Rate": 4.8209867657823104e-05, "Pretrain/Loss": 2.0681962966918945, "Pretrain/Loss (Raw)": 1.9701505899429321, "Pretrain/Step": 1407, "Pretrain/Step Time": 8.474852573126554} +{"Pretrain/Learning Rate": 4.8206711178934996e-05, "Pretrain/Loss": 2.0682458877563477, "Pretrain/Loss (Raw)": 2.0779213905334473, "Pretrain/Step": 1408, "Pretrain/Step Time": 8.478905053809285} +{"Pretrain/Learning Rate": 4.8203552023160905e-05, "Pretrain/Loss": 2.0670061111450195, "Pretrain/Loss (Raw)": 2.0974721908569336, "Pretrain/Step": 1409, "Pretrain/Step Time": 8.473612304776907} +{"Pretrain/Learning Rate": 4.8200390190865254e-05, "Pretrain/Loss": 2.068587064743042, "Pretrain/Loss (Raw)": 2.184608221054077, "Pretrain/Step": 1410, "Pretrain/Step Time": 8.478035414591432} +{"Pretrain/Learning Rate": 4.819722568241274e-05, "Pretrain/Loss": 2.0666472911834717, "Pretrain/Loss (Raw)": 1.9085414409637451, "Pretrain/Step": 1411, "Pretrain/Step Time": 8.47548072040081} +{"Pretrain/Learning Rate": 4.819405849816839e-05, "Pretrain/Loss": 2.067115306854248, "Pretrain/Loss (Raw)": 2.0553908348083496, "Pretrain/Step": 1412, "Pretrain/Step Time": 8.476047409698367} +{"Pretrain/Learning Rate": 4.8190888638497556e-05, "Pretrain/Loss": 2.067290782928467, "Pretrain/Loss (Raw)": 2.127586603164673, "Pretrain/Step": 1413, "Pretrain/Step Time": 8.478770030662417} +{"Pretrain/Learning Rate": 4.8187716103765856e-05, "Pretrain/Loss": 2.0674734115600586, "Pretrain/Loss (Raw)": 2.0155293941497803, "Pretrain/Step": 1414, "Pretrain/Step Time": 8.47721448726952} +{"Pretrain/Learning Rate": 4.818454089433926e-05, "Pretrain/Loss": 2.0659584999084473, "Pretrain/Loss (Raw)": 2.192499876022339, "Pretrain/Step": 1415, "Pretrain/Step Time": 8.476447470486164} +{"Pretrain/Learning Rate": 4.8181363010584013e-05, "Pretrain/Loss": 2.06553316116333, "Pretrain/Loss (Raw)": 2.1863248348236084, "Pretrain/Step": 1416, "Pretrain/Step Time": 8.480865573510528} +{"Pretrain/Learning Rate": 4.81781824528667e-05, "Pretrain/Loss": 2.0647497177124023, "Pretrain/Loss (Raw)": 1.9510704278945923, "Pretrain/Step": 1417, "Pretrain/Step Time": 8.480318006128073} +{"Pretrain/Learning Rate": 4.8174999221554176e-05, "Pretrain/Loss": 2.064267635345459, "Pretrain/Loss (Raw)": 2.1321661472320557, "Pretrain/Step": 1418, "Pretrain/Step Time": 8.481009935960174} +{"Pretrain/Learning Rate": 4.8171813317013635e-05, "Pretrain/Loss": 2.062769651412964, "Pretrain/Loss (Raw)": 1.9208662509918213, "Pretrain/Step": 1419, "Pretrain/Step Time": 8.476107850670815} +{"Pretrain/Learning Rate": 4.816862473961258e-05, "Pretrain/Loss": 2.0628297328948975, "Pretrain/Loss (Raw)": 2.143900156021118, "Pretrain/Step": 1420, "Pretrain/Step Time": 8.47387646138668} +{"Pretrain/Learning Rate": 4.8165433489718795e-05, "Pretrain/Loss": 2.0628931522369385, "Pretrain/Loss (Raw)": 2.2295656204223633, "Pretrain/Step": 1421, "Pretrain/Step Time": 8.473573613911867} +{"Pretrain/Learning Rate": 4.81622395677004e-05, "Pretrain/Loss": 2.064286470413208, "Pretrain/Loss (Raw)": 2.0468075275421143, "Pretrain/Step": 1422, "Pretrain/Step Time": 8.478240966796875} +{"Pretrain/Learning Rate": 4.8159042973925814e-05, "Pretrain/Loss": 2.0653443336486816, "Pretrain/Loss (Raw)": 2.077533483505249, "Pretrain/Step": 1423, "Pretrain/Step Time": 8.478084571659565} +{"Pretrain/Learning Rate": 4.815584370876376e-05, "Pretrain/Loss": 2.066512107849121, "Pretrain/Loss (Raw)": 2.243649482727051, "Pretrain/Step": 1424, "Pretrain/Step Time": 8.48110224865377} +{"Pretrain/Learning Rate": 4.815264177258326e-05, "Pretrain/Loss": 2.0685739517211914, "Pretrain/Loss (Raw)": 2.134800672531128, "Pretrain/Step": 1425, "Pretrain/Step Time": 8.480513436719775} +{"Pretrain/Learning Rate": 4.814943716575369e-05, "Pretrain/Loss": 2.0672712326049805, "Pretrain/Loss (Raw)": 2.083536386489868, "Pretrain/Step": 1426, "Pretrain/Step Time": 8.47745387069881} +{"Pretrain/Learning Rate": 4.8146229888644656e-05, "Pretrain/Loss": 2.0656633377075195, "Pretrain/Loss (Raw)": 2.0491201877593994, "Pretrain/Step": 1427, "Pretrain/Step Time": 8.478577541187406} +{"Pretrain/Learning Rate": 4.814301994162615e-05, "Pretrain/Loss": 2.065403461456299, "Pretrain/Loss (Raw)": 2.038618564605713, "Pretrain/Step": 1428, "Pretrain/Step Time": 8.481268741190434} +{"Pretrain/Learning Rate": 4.8139807325068425e-05, "Pretrain/Loss": 2.065960168838501, "Pretrain/Loss (Raw)": 2.091435432434082, "Pretrain/Step": 1429, "Pretrain/Step Time": 8.480847964063287} +{"Pretrain/Learning Rate": 4.813659203934205e-05, "Pretrain/Loss": 2.0674962997436523, "Pretrain/Loss (Raw)": 2.1983070373535156, "Pretrain/Step": 1430, "Pretrain/Step Time": 8.479236368089914} +{"Pretrain/Learning Rate": 4.8133374084817927e-05, "Pretrain/Loss": 2.068368911743164, "Pretrain/Loss (Raw)": 2.1741931438446045, "Pretrain/Step": 1431, "Pretrain/Step Time": 8.480441559106112} +{"Pretrain/Learning Rate": 4.8130153461867225e-05, "Pretrain/Loss": 2.067556858062744, "Pretrain/Loss (Raw)": 2.003890037536621, "Pretrain/Step": 1432, "Pretrain/Step Time": 8.479045929387212} +{"Pretrain/Learning Rate": 4.812693017086145e-05, "Pretrain/Loss": 2.0687098503112793, "Pretrain/Loss (Raw)": 2.05298113822937, "Pretrain/Step": 1433, "Pretrain/Step Time": 8.482522189617157} +{"Pretrain/Learning Rate": 4.8123704212172415e-05, "Pretrain/Loss": 2.070586919784546, "Pretrain/Loss (Raw)": 2.1095941066741943, "Pretrain/Step": 1434, "Pretrain/Step Time": 8.483698224648833} +{"Pretrain/Learning Rate": 4.8120475586172223e-05, "Pretrain/Loss": 2.0701708793640137, "Pretrain/Loss (Raw)": 2.115736484527588, "Pretrain/Step": 1435, "Pretrain/Step Time": 8.482765953987837} +{"Pretrain/Learning Rate": 4.811724429323329e-05, "Pretrain/Loss": 2.070009231567383, "Pretrain/Loss (Raw)": 2.0309853553771973, "Pretrain/Step": 1436, "Pretrain/Step Time": 8.47689202427864} +{"Pretrain/Learning Rate": 4.811401033372835e-05, "Pretrain/Loss": 2.0708065032958984, "Pretrain/Loss (Raw)": 2.2079708576202393, "Pretrain/Step": 1437, "Pretrain/Step Time": 8.480301452800632} +{"Pretrain/Learning Rate": 4.811077370803044e-05, "Pretrain/Loss": 2.0722923278808594, "Pretrain/Loss (Raw)": 2.1598474979400635, "Pretrain/Step": 1438, "Pretrain/Step Time": 8.480284476652741} +{"Pretrain/Learning Rate": 4.810753441651292e-05, "Pretrain/Loss": 2.072032928466797, "Pretrain/Loss (Raw)": 1.9916306734085083, "Pretrain/Step": 1439, "Pretrain/Step Time": 8.4811048861593} +{"Pretrain/Learning Rate": 4.8104292459549415e-05, "Pretrain/Loss": 2.0729076862335205, "Pretrain/Loss (Raw)": 2.0309112071990967, "Pretrain/Step": 1440, "Pretrain/Step Time": 8.481335522606969} +{"Pretrain/Learning Rate": 4.810104783751389e-05, "Pretrain/Loss": 2.0722849369049072, "Pretrain/Loss (Raw)": 1.944381594657898, "Pretrain/Step": 1441, "Pretrain/Step Time": 8.48273847438395} +{"Pretrain/Learning Rate": 4.8097800550780625e-05, "Pretrain/Loss": 2.0743603706359863, "Pretrain/Loss (Raw)": 2.1366469860076904, "Pretrain/Step": 1442, "Pretrain/Step Time": 8.484190179035068} +{"Pretrain/Learning Rate": 4.809455059972418e-05, "Pretrain/Loss": 2.0753841400146484, "Pretrain/Loss (Raw)": 2.0570216178894043, "Pretrain/Step": 1443, "Pretrain/Step Time": 8.482248520478606} +{"Pretrain/Learning Rate": 4.809129798471944e-05, "Pretrain/Loss": 2.0763230323791504, "Pretrain/Loss (Raw)": 2.245117664337158, "Pretrain/Step": 1444, "Pretrain/Step Time": 8.482566801831126} +{"Pretrain/Learning Rate": 4.808804270614159e-05, "Pretrain/Loss": 2.077219009399414, "Pretrain/Loss (Raw)": 2.106142997741699, "Pretrain/Step": 1445, "Pretrain/Step Time": 8.482736200094223} +{"Pretrain/Learning Rate": 4.8084784764366123e-05, "Pretrain/Loss": 2.0763614177703857, "Pretrain/Loss (Raw)": 2.013993740081787, "Pretrain/Step": 1446, "Pretrain/Step Time": 8.484680116176605} +{"Pretrain/Learning Rate": 4.8081524159768855e-05, "Pretrain/Loss": 2.0772275924682617, "Pretrain/Loss (Raw)": 2.1637399196624756, "Pretrain/Step": 1447, "Pretrain/Step Time": 8.485387599095702} +{"Pretrain/Learning Rate": 4.8078260892725876e-05, "Pretrain/Loss": 2.0769546031951904, "Pretrain/Loss (Raw)": 2.054628610610962, "Pretrain/Step": 1448, "Pretrain/Step Time": 8.482762126252055} +{"Pretrain/Learning Rate": 4.807499496361362e-05, "Pretrain/Loss": 2.076291084289551, "Pretrain/Loss (Raw)": 2.039912700653076, "Pretrain/Step": 1449, "Pretrain/Step Time": 8.484154671430588} +{"Pretrain/Learning Rate": 4.807172637280881e-05, "Pretrain/Loss": 2.075425148010254, "Pretrain/Loss (Raw)": 1.994796872138977, "Pretrain/Step": 1450, "Pretrain/Step Time": 8.485949603840709} +{"Pretrain/Learning Rate": 4.806845512068846e-05, "Pretrain/Loss": 2.075014114379883, "Pretrain/Loss (Raw)": 1.9560444355010986, "Pretrain/Step": 1451, "Pretrain/Step Time": 8.486605940386653} +{"Pretrain/Learning Rate": 4.806518120762993e-05, "Pretrain/Loss": 2.076486110687256, "Pretrain/Loss (Raw)": 2.2316222190856934, "Pretrain/Step": 1452, "Pretrain/Step Time": 8.488824933767319} +{"Pretrain/Learning Rate": 4.806190463401085e-05, "Pretrain/Loss": 2.0770270824432373, "Pretrain/Loss (Raw)": 2.2023165225982666, "Pretrain/Step": 1453, "Pretrain/Step Time": 8.48721350543201} +{"Pretrain/Learning Rate": 4.8058625400209165e-05, "Pretrain/Loss": 2.0766918659210205, "Pretrain/Loss (Raw)": 2.0784244537353516, "Pretrain/Step": 1454, "Pretrain/Step Time": 8.4829016700387} +{"Pretrain/Learning Rate": 4.805534350660315e-05, "Pretrain/Loss": 2.0766615867614746, "Pretrain/Loss (Raw)": 2.2106120586395264, "Pretrain/Step": 1455, "Pretrain/Step Time": 8.484972471371293} +{"Pretrain/Learning Rate": 4.805205895357137e-05, "Pretrain/Loss": 2.0762810707092285, "Pretrain/Loss (Raw)": 1.9292559623718262, "Pretrain/Step": 1456, "Pretrain/Step Time": 8.48673152923584} +{"Pretrain/Learning Rate": 4.804877174149268e-05, "Pretrain/Loss": 2.0772223472595215, "Pretrain/Loss (Raw)": 2.2419238090515137, "Pretrain/Step": 1457, "Pretrain/Step Time": 8.484609635546803} +{"Pretrain/Learning Rate": 4.804548187074628e-05, "Pretrain/Loss": 2.076143741607666, "Pretrain/Loss (Raw)": 2.142883539199829, "Pretrain/Step": 1458, "Pretrain/Step Time": 8.487839628010988} +{"Pretrain/Learning Rate": 4.804218934171163e-05, "Pretrain/Loss": 2.0756514072418213, "Pretrain/Loss (Raw)": 2.0830960273742676, "Pretrain/Step": 1459, "Pretrain/Step Time": 8.48893317207694} +{"Pretrain/Learning Rate": 4.8038894154768554e-05, "Pretrain/Loss": 2.076732635498047, "Pretrain/Loss (Raw)": 2.0737571716308594, "Pretrain/Step": 1460, "Pretrain/Step Time": 8.485858930274844} +{"Pretrain/Learning Rate": 4.8035596310297124e-05, "Pretrain/Loss": 2.0779850482940674, "Pretrain/Loss (Raw)": 2.2129809856414795, "Pretrain/Step": 1461, "Pretrain/Step Time": 8.484262501820922} +{"Pretrain/Learning Rate": 4.8032295808677754e-05, "Pretrain/Loss": 2.077303886413574, "Pretrain/Loss (Raw)": 2.0561704635620117, "Pretrain/Step": 1462, "Pretrain/Step Time": 8.484732631593943} +{"Pretrain/Learning Rate": 4.802899265029116e-05, "Pretrain/Loss": 2.077767848968506, "Pretrain/Loss (Raw)": 2.1140530109405518, "Pretrain/Step": 1463, "Pretrain/Step Time": 8.48347301222384} +{"Pretrain/Learning Rate": 4.802568683551836e-05, "Pretrain/Loss": 2.077935218811035, "Pretrain/Loss (Raw)": 2.146618127822876, "Pretrain/Step": 1464, "Pretrain/Step Time": 8.48415369167924} +{"Pretrain/Learning Rate": 4.802237836474067e-05, "Pretrain/Loss": 2.0766232013702393, "Pretrain/Loss (Raw)": 1.9468361139297485, "Pretrain/Step": 1465, "Pretrain/Step Time": 8.486102381721139} +{"Pretrain/Learning Rate": 4.801906723833973e-05, "Pretrain/Loss": 2.0749878883361816, "Pretrain/Loss (Raw)": 2.0016062259674072, "Pretrain/Step": 1466, "Pretrain/Step Time": 8.477913867682219} +{"Pretrain/Learning Rate": 4.8015753456697465e-05, "Pretrain/Loss": 2.0751099586486816, "Pretrain/Loss (Raw)": 2.0890581607818604, "Pretrain/Step": 1467, "Pretrain/Step Time": 8.480266612023115} +{"Pretrain/Learning Rate": 4.801243702019614e-05, "Pretrain/Loss": 2.075711965560913, "Pretrain/Loss (Raw)": 2.0808470249176025, "Pretrain/Step": 1468, "Pretrain/Step Time": 8.477885352447629} +{"Pretrain/Learning Rate": 4.8009117929218285e-05, "Pretrain/Loss": 2.0751285552978516, "Pretrain/Loss (Raw)": 1.9875155687332153, "Pretrain/Step": 1469, "Pretrain/Step Time": 8.478190716356039} +{"Pretrain/Learning Rate": 4.800579618414676e-05, "Pretrain/Loss": 2.074854612350464, "Pretrain/Loss (Raw)": 2.0134458541870117, "Pretrain/Step": 1470, "Pretrain/Step Time": 8.478493921458721} +{"Pretrain/Learning Rate": 4.8002471785364734e-05, "Pretrain/Loss": 2.0755209922790527, "Pretrain/Loss (Raw)": 2.1435277462005615, "Pretrain/Step": 1471, "Pretrain/Step Time": 8.47640130110085} +{"Pretrain/Learning Rate": 4.799914473325567e-05, "Pretrain/Loss": 2.074756622314453, "Pretrain/Loss (Raw)": 2.050896167755127, "Pretrain/Step": 1472, "Pretrain/Step Time": 8.473696177825332} +{"Pretrain/Learning Rate": 4.7995815028203344e-05, "Pretrain/Loss": 2.074214220046997, "Pretrain/Loss (Raw)": 1.942525863647461, "Pretrain/Step": 1473, "Pretrain/Step Time": 8.47501190006733} +{"Pretrain/Learning Rate": 4.799248267059183e-05, "Pretrain/Loss": 2.073678731918335, "Pretrain/Loss (Raw)": 1.990282416343689, "Pretrain/Step": 1474, "Pretrain/Step Time": 8.476534720510244} +{"Pretrain/Learning Rate": 4.798914766080554e-05, "Pretrain/Loss": 2.074266195297241, "Pretrain/Loss (Raw)": 2.0444273948669434, "Pretrain/Step": 1475, "Pretrain/Step Time": 8.477369233965874} +{"Pretrain/Learning Rate": 4.798580999922912e-05, "Pretrain/Loss": 2.074432373046875, "Pretrain/Loss (Raw)": 2.13047194480896, "Pretrain/Step": 1476, "Pretrain/Step Time": 8.476399194449186} +{"Pretrain/Learning Rate": 4.7982469686247614e-05, "Pretrain/Loss": 2.075561285018921, "Pretrain/Loss (Raw)": 2.1249279975891113, "Pretrain/Step": 1477, "Pretrain/Step Time": 8.474673656746745} +{"Pretrain/Learning Rate": 4.797912672224629e-05, "Pretrain/Loss": 2.0748813152313232, "Pretrain/Loss (Raw)": 2.04758358001709, "Pretrain/Step": 1478, "Pretrain/Step Time": 8.474528161808848} +{"Pretrain/Learning Rate": 4.797578110761078e-05, "Pretrain/Loss": 2.0764803886413574, "Pretrain/Loss (Raw)": 2.1478614807128906, "Pretrain/Step": 1479, "Pretrain/Step Time": 8.475733315572143} +{"Pretrain/Learning Rate": 4.797243284272701e-05, "Pretrain/Loss": 2.078233242034912, "Pretrain/Loss (Raw)": 2.3039820194244385, "Pretrain/Step": 1480, "Pretrain/Step Time": 8.478381527587771} +{"Pretrain/Learning Rate": 4.7969081927981165e-05, "Pretrain/Loss": 2.079242706298828, "Pretrain/Loss (Raw)": 2.0899949073791504, "Pretrain/Step": 1481, "Pretrain/Step Time": 8.47696739807725} +{"Pretrain/Learning Rate": 4.79657283637598e-05, "Pretrain/Loss": 2.08260178565979, "Pretrain/Loss (Raw)": 2.3696277141571045, "Pretrain/Step": 1482, "Pretrain/Step Time": 8.480802871286869} +{"Pretrain/Learning Rate": 4.796237215044973e-05, "Pretrain/Loss": 2.0829529762268066, "Pretrain/Loss (Raw)": 1.9595636129379272, "Pretrain/Step": 1483, "Pretrain/Step Time": 8.480768106877804} +{"Pretrain/Learning Rate": 4.795901328843811e-05, "Pretrain/Loss": 2.083738088607788, "Pretrain/Loss (Raw)": 2.160205602645874, "Pretrain/Step": 1484, "Pretrain/Step Time": 8.478870779275894} +{"Pretrain/Learning Rate": 4.7955651778112375e-05, "Pretrain/Loss": 2.084137439727783, "Pretrain/Loss (Raw)": 2.0122194290161133, "Pretrain/Step": 1485, "Pretrain/Step Time": 8.474855756387115} +{"Pretrain/Learning Rate": 4.795228761986028e-05, "Pretrain/Loss": 2.083287000656128, "Pretrain/Loss (Raw)": 2.092801094055176, "Pretrain/Step": 1486, "Pretrain/Step Time": 8.469791596755385} +{"Pretrain/Learning Rate": 4.7948920814069866e-05, "Pretrain/Loss": 2.0842080116271973, "Pretrain/Loss (Raw)": 2.140878200531006, "Pretrain/Step": 1487, "Pretrain/Step Time": 8.467438023537397} +{"Pretrain/Learning Rate": 4.79455513611295e-05, "Pretrain/Loss": 2.085336923599243, "Pretrain/Loss (Raw)": 2.0536160469055176, "Pretrain/Step": 1488, "Pretrain/Step Time": 8.465859020128846} +{"Pretrain/Learning Rate": 4.794217926142785e-05, "Pretrain/Loss": 2.0859546661376953, "Pretrain/Loss (Raw)": 2.0829412937164307, "Pretrain/Step": 1489, "Pretrain/Step Time": 8.473560474812984} +{"Pretrain/Learning Rate": 4.7938804515353887e-05, "Pretrain/Loss": 2.0860776901245117, "Pretrain/Loss (Raw)": 2.0015063285827637, "Pretrain/Step": 1490, "Pretrain/Step Time": 8.472692320123315} +{"Pretrain/Learning Rate": 4.793542712329688e-05, "Pretrain/Loss": 2.0847296714782715, "Pretrain/Loss (Raw)": 1.931524634361267, "Pretrain/Step": 1491, "Pretrain/Step Time": 8.473136173561215} +{"Pretrain/Learning Rate": 4.793204708564641e-05, "Pretrain/Loss": 2.0835776329040527, "Pretrain/Loss (Raw)": 2.075087547302246, "Pretrain/Step": 1492, "Pretrain/Step Time": 8.476012274622917} +{"Pretrain/Learning Rate": 4.792866440279238e-05, "Pretrain/Loss": 2.0822105407714844, "Pretrain/Loss (Raw)": 1.788209080696106, "Pretrain/Step": 1493, "Pretrain/Step Time": 8.474335687234998} +{"Pretrain/Learning Rate": 4.792527907512496e-05, "Pretrain/Loss": 2.081580638885498, "Pretrain/Loss (Raw)": 2.0902788639068604, "Pretrain/Step": 1494, "Pretrain/Step Time": 8.473455840721726} +{"Pretrain/Learning Rate": 4.792189110303467e-05, "Pretrain/Loss": 2.0830130577087402, "Pretrain/Loss (Raw)": 2.149660587310791, "Pretrain/Step": 1495, "Pretrain/Step Time": 8.478398384526372} +{"Pretrain/Learning Rate": 4.7918500486912274e-05, "Pretrain/Loss": 2.082516670227051, "Pretrain/Loss (Raw)": 2.0032765865325928, "Pretrain/Step": 1496, "Pretrain/Step Time": 8.476624101400375} +{"Pretrain/Learning Rate": 4.791510722714892e-05, "Pretrain/Loss": 2.082038402557373, "Pretrain/Loss (Raw)": 2.150663375854492, "Pretrain/Step": 1497, "Pretrain/Step Time": 8.47474299557507} +{"Pretrain/Learning Rate": 4.791171132413599e-05, "Pretrain/Loss": 2.0803937911987305, "Pretrain/Loss (Raw)": 1.9992430210113525, "Pretrain/Step": 1498, "Pretrain/Step Time": 8.47703556343913} +{"Pretrain/Learning Rate": 4.790831277826521e-05, "Pretrain/Loss": 2.081369400024414, "Pretrain/Loss (Raw)": 2.102381706237793, "Pretrain/Step": 1499, "Pretrain/Step Time": 8.477161351591349} +{"Pretrain/Learning Rate": 4.790491158992861e-05, "Pretrain/Loss": 2.0833523273468018, "Pretrain/Loss (Raw)": 2.2083017826080322, "Pretrain/Step": 1500, "Pretrain/Step Time": 8.475590750575066} +{"Pretrain/Learning Rate": 4.79015077595185e-05, "Pretrain/Loss": 2.0844762325286865, "Pretrain/Loss (Raw)": 2.234029769897461, "Pretrain/Step": 1501, "Pretrain/Step Time": 8.478397591039538} +{"Pretrain/Learning Rate": 4.789810128742752e-05, "Pretrain/Loss": 2.0834670066833496, "Pretrain/Loss (Raw)": 2.066113233566284, "Pretrain/Step": 1502, "Pretrain/Step Time": 8.478712046518922} +{"Pretrain/Learning Rate": 4.789469217404861e-05, "Pretrain/Loss": 2.082923650741577, "Pretrain/Loss (Raw)": 2.0636343955993652, "Pretrain/Step": 1503, "Pretrain/Step Time": 8.478620253503323} +{"Pretrain/Learning Rate": 4.7891280419774985e-05, "Pretrain/Loss": 2.0825700759887695, "Pretrain/Loss (Raw)": 2.0726892948150635, "Pretrain/Step": 1504, "Pretrain/Step Time": 8.479686930775642} +{"Pretrain/Learning Rate": 4.7887866025000225e-05, "Pretrain/Loss": 2.0820424556732178, "Pretrain/Loss (Raw)": 2.1102237701416016, "Pretrain/Step": 1505, "Pretrain/Step Time": 8.480965603142977} +{"Pretrain/Learning Rate": 4.788444899011816e-05, "Pretrain/Loss": 2.080885410308838, "Pretrain/Loss (Raw)": 1.9787147045135498, "Pretrain/Step": 1506, "Pretrain/Step Time": 8.482100388035178} +{"Pretrain/Learning Rate": 4.788102931552294e-05, "Pretrain/Loss": 2.0815563201904297, "Pretrain/Loss (Raw)": 2.0537259578704834, "Pretrain/Step": 1507, "Pretrain/Step Time": 8.481598928570747} +{"Pretrain/Learning Rate": 4.787760700160904e-05, "Pretrain/Loss": 2.08313250541687, "Pretrain/Loss (Raw)": 2.1428494453430176, "Pretrain/Step": 1508, "Pretrain/Step Time": 8.481028851121664} +{"Pretrain/Learning Rate": 4.78741820487712e-05, "Pretrain/Loss": 2.0830044746398926, "Pretrain/Loss (Raw)": 1.9327894449234009, "Pretrain/Step": 1509, "Pretrain/Step Time": 8.484060782939196} +{"Pretrain/Learning Rate": 4.78707544574045e-05, "Pretrain/Loss": 2.0868873596191406, "Pretrain/Loss (Raw)": 2.321051597595215, "Pretrain/Step": 1510, "Pretrain/Step Time": 8.482512693852186} +{"Pretrain/Learning Rate": 4.786732422790432e-05, "Pretrain/Loss": 2.086066961288452, "Pretrain/Loss (Raw)": 2.1186413764953613, "Pretrain/Step": 1511, "Pretrain/Step Time": 8.481346383690834} +{"Pretrain/Learning Rate": 4.786389136066633e-05, "Pretrain/Loss": 2.085052013397217, "Pretrain/Loss (Raw)": 2.046229362487793, "Pretrain/Step": 1512, "Pretrain/Step Time": 8.480121057480574} +{"Pretrain/Learning Rate": 4.7860455856086487e-05, "Pretrain/Loss": 2.0852274894714355, "Pretrain/Loss (Raw)": 2.111651659011841, "Pretrain/Step": 1513, "Pretrain/Step Time": 8.481571918353438} +{"Pretrain/Learning Rate": 4.785701771456111e-05, "Pretrain/Loss": 2.0835068225860596, "Pretrain/Loss (Raw)": 2.026838541030884, "Pretrain/Step": 1514, "Pretrain/Step Time": 8.482560874894261} +{"Pretrain/Learning Rate": 4.785357693648677e-05, "Pretrain/Loss": 2.083447217941284, "Pretrain/Loss (Raw)": 2.1087148189544678, "Pretrain/Step": 1515, "Pretrain/Step Time": 8.486159900203347} +{"Pretrain/Learning Rate": 4.785013352226036e-05, "Pretrain/Loss": 2.08270263671875, "Pretrain/Loss (Raw)": 2.089411973953247, "Pretrain/Step": 1516, "Pretrain/Step Time": 8.481947841122746} +{"Pretrain/Learning Rate": 4.784668747227907e-05, "Pretrain/Loss": 2.0826282501220703, "Pretrain/Loss (Raw)": 2.0120389461517334, "Pretrain/Step": 1517, "Pretrain/Step Time": 8.484260132536292} +{"Pretrain/Learning Rate": 4.7843238786940425e-05, "Pretrain/Loss": 2.082460641860962, "Pretrain/Loss (Raw)": 2.080886125564575, "Pretrain/Step": 1518, "Pretrain/Step Time": 8.48211494460702} +{"Pretrain/Learning Rate": 4.783978746664221e-05, "Pretrain/Loss": 2.083155632019043, "Pretrain/Loss (Raw)": 2.011688232421875, "Pretrain/Step": 1519, "Pretrain/Step Time": 8.48054227232933} +{"Pretrain/Learning Rate": 4.783633351178253e-05, "Pretrain/Loss": 2.082547426223755, "Pretrain/Loss (Raw)": 2.1186790466308594, "Pretrain/Step": 1520, "Pretrain/Step Time": 8.485901633277535} +{"Pretrain/Learning Rate": 4.783287692275981e-05, "Pretrain/Loss": 2.0830979347229004, "Pretrain/Loss (Raw)": 2.0647215843200684, "Pretrain/Step": 1521, "Pretrain/Step Time": 8.482426716014743} +{"Pretrain/Learning Rate": 4.7829417699972754e-05, "Pretrain/Loss": 2.082672357559204, "Pretrain/Loss (Raw)": 2.169214963912964, "Pretrain/Step": 1522, "Pretrain/Step Time": 8.4839277099818} +{"Pretrain/Learning Rate": 4.782595584382039e-05, "Pretrain/Loss": 2.083731174468994, "Pretrain/Loss (Raw)": 2.0423691272735596, "Pretrain/Step": 1523, "Pretrain/Step Time": 8.482614183798432} +{"Pretrain/Learning Rate": 4.782249135470205e-05, "Pretrain/Loss": 2.0834310054779053, "Pretrain/Loss (Raw)": 2.0741429328918457, "Pretrain/Step": 1524, "Pretrain/Step Time": 8.481189021840692} +{"Pretrain/Learning Rate": 4.781902423301734e-05, "Pretrain/Loss": 2.0833520889282227, "Pretrain/Loss (Raw)": 1.9127566814422607, "Pretrain/Step": 1525, "Pretrain/Step Time": 8.482083819806576} +{"Pretrain/Learning Rate": 4.781555447916621e-05, "Pretrain/Loss": 2.083826780319214, "Pretrain/Loss (Raw)": 2.113647937774658, "Pretrain/Step": 1526, "Pretrain/Step Time": 8.479511799290776} +{"Pretrain/Learning Rate": 4.7812082093548894e-05, "Pretrain/Loss": 2.0839269161224365, "Pretrain/Loss (Raw)": 2.0852763652801514, "Pretrain/Step": 1527, "Pretrain/Step Time": 8.480412786826491} +{"Pretrain/Learning Rate": 4.780860707656592e-05, "Pretrain/Loss": 2.0831923484802246, "Pretrain/Loss (Raw)": 2.0836384296417236, "Pretrain/Step": 1528, "Pretrain/Step Time": 8.480646388605237} +{"Pretrain/Learning Rate": 4.780512942861813e-05, "Pretrain/Loss": 2.083878517150879, "Pretrain/Loss (Raw)": 2.1867644786834717, "Pretrain/Step": 1529, "Pretrain/Step Time": 8.482902761548758} +{"Pretrain/Learning Rate": 4.780164915010669e-05, "Pretrain/Loss": 2.0840322971343994, "Pretrain/Loss (Raw)": 2.159311532974243, "Pretrain/Step": 1530, "Pretrain/Step Time": 8.483633514493704} +{"Pretrain/Learning Rate": 4.779816624143302e-05, "Pretrain/Loss": 2.0838356018066406, "Pretrain/Loss (Raw)": 2.048218011856079, "Pretrain/Step": 1531, "Pretrain/Step Time": 8.48637368157506} +{"Pretrain/Learning Rate": 4.7794680702998895e-05, "Pretrain/Loss": 2.084685802459717, "Pretrain/Loss (Raw)": 2.0321085453033447, "Pretrain/Step": 1532, "Pretrain/Step Time": 8.486346311867237} +{"Pretrain/Learning Rate": 4.7791192535206355e-05, "Pretrain/Loss": 2.0851783752441406, "Pretrain/Loss (Raw)": 2.229879856109619, "Pretrain/Step": 1533, "Pretrain/Step Time": 8.485026432201266} +{"Pretrain/Learning Rate": 4.778770173845777e-05, "Pretrain/Loss": 2.0864646434783936, "Pretrain/Loss (Raw)": 2.1857547760009766, "Pretrain/Step": 1534, "Pretrain/Step Time": 8.479903291910887} +{"Pretrain/Learning Rate": 4.778420831315579e-05, "Pretrain/Loss": 2.087639808654785, "Pretrain/Loss (Raw)": 2.120577573776245, "Pretrain/Step": 1535, "Pretrain/Step Time": 8.481124797835946} +{"Pretrain/Learning Rate": 4.77807122597034e-05, "Pretrain/Loss": 2.087672233581543, "Pretrain/Loss (Raw)": 2.082082748413086, "Pretrain/Step": 1536, "Pretrain/Step Time": 8.482231847941875} +{"Pretrain/Learning Rate": 4.777721357850384e-05, "Pretrain/Loss": 2.088209629058838, "Pretrain/Loss (Raw)": 2.1662437915802, "Pretrain/Step": 1537, "Pretrain/Step Time": 8.484460052102804} +{"Pretrain/Learning Rate": 4.7773712269960716e-05, "Pretrain/Loss": 2.085442543029785, "Pretrain/Loss (Raw)": 1.830418348312378, "Pretrain/Step": 1538, "Pretrain/Step Time": 8.482021590694785} +{"Pretrain/Learning Rate": 4.7770208334477875e-05, "Pretrain/Loss": 2.0863423347473145, "Pretrain/Loss (Raw)": 2.0237209796905518, "Pretrain/Step": 1539, "Pretrain/Step Time": 8.484194297343493} +{"Pretrain/Learning Rate": 4.77667017724595e-05, "Pretrain/Loss": 2.085507392883301, "Pretrain/Loss (Raw)": 1.948530673980713, "Pretrain/Step": 1540, "Pretrain/Step Time": 8.484984697774053} +{"Pretrain/Learning Rate": 4.776319258431009e-05, "Pretrain/Loss": 2.0856354236602783, "Pretrain/Loss (Raw)": 2.143972635269165, "Pretrain/Step": 1541, "Pretrain/Step Time": 8.4826076682657} +{"Pretrain/Learning Rate": 4.7759680770434404e-05, "Pretrain/Loss": 2.0875067710876465, "Pretrain/Loss (Raw)": 2.2550301551818848, "Pretrain/Step": 1542, "Pretrain/Step Time": 8.482922287657857} +{"Pretrain/Learning Rate": 4.775616633123754e-05, "Pretrain/Loss": 2.087900400161743, "Pretrain/Loss (Raw)": 2.2429039478302, "Pretrain/Step": 1543, "Pretrain/Step Time": 8.483571659773588} +{"Pretrain/Learning Rate": 4.775264926712489e-05, "Pretrain/Loss": 2.0871424674987793, "Pretrain/Loss (Raw)": 2.089324712753296, "Pretrain/Step": 1544, "Pretrain/Step Time": 8.482943320646882} +{"Pretrain/Learning Rate": 4.774912957850215e-05, "Pretrain/Loss": 2.088282585144043, "Pretrain/Loss (Raw)": 2.0970163345336914, "Pretrain/Step": 1545, "Pretrain/Step Time": 8.484909635037184} +{"Pretrain/Learning Rate": 4.7745607265775295e-05, "Pretrain/Loss": 2.087308406829834, "Pretrain/Loss (Raw)": 2.0074462890625, "Pretrain/Step": 1546, "Pretrain/Step Time": 8.484274690970778} +{"Pretrain/Learning Rate": 4.7742082329350644e-05, "Pretrain/Loss": 2.0888357162475586, "Pretrain/Loss (Raw)": 2.1163597106933594, "Pretrain/Step": 1547, "Pretrain/Step Time": 8.485213236883283} +{"Pretrain/Learning Rate": 4.773855476963479e-05, "Pretrain/Loss": 2.090343475341797, "Pretrain/Loss (Raw)": 2.336890459060669, "Pretrain/Step": 1548, "Pretrain/Step Time": 8.487946651875973} +{"Pretrain/Learning Rate": 4.773502458703463e-05, "Pretrain/Loss": 2.090435743331909, "Pretrain/Loss (Raw)": 2.2413854598999023, "Pretrain/Step": 1549, "Pretrain/Step Time": 8.488475745543838} +{"Pretrain/Learning Rate": 4.773149178195737e-05, "Pretrain/Loss": 2.091548442840576, "Pretrain/Loss (Raw)": 2.1892127990722656, "Pretrain/Step": 1550, "Pretrain/Step Time": 8.485619384795427} +{"Pretrain/Learning Rate": 4.772795635481052e-05, "Pretrain/Loss": 2.091045618057251, "Pretrain/Loss (Raw)": 2.013181447982788, "Pretrain/Step": 1551, "Pretrain/Step Time": 8.485081171616912} +{"Pretrain/Learning Rate": 4.77244183060019e-05, "Pretrain/Loss": 2.089966058731079, "Pretrain/Loss (Raw)": 2.1054680347442627, "Pretrain/Step": 1552, "Pretrain/Step Time": 8.483484974130988} +{"Pretrain/Learning Rate": 4.772087763593961e-05, "Pretrain/Loss": 2.0896902084350586, "Pretrain/Loss (Raw)": 2.099506139755249, "Pretrain/Step": 1553, "Pretrain/Step Time": 8.479795899242163} +{"Pretrain/Learning Rate": 4.7717334345032065e-05, "Pretrain/Loss": 2.090193033218384, "Pretrain/Loss (Raw)": 2.1478917598724365, "Pretrain/Step": 1554, "Pretrain/Step Time": 8.483215114101768} +{"Pretrain/Learning Rate": 4.7713788433687995e-05, "Pretrain/Loss": 2.0915114879608154, "Pretrain/Loss (Raw)": 2.217884063720703, "Pretrain/Step": 1555, "Pretrain/Step Time": 8.482916861772537} +{"Pretrain/Learning Rate": 4.7710239902316405e-05, "Pretrain/Loss": 2.091355800628662, "Pretrain/Loss (Raw)": 2.0187110900878906, "Pretrain/Step": 1556, "Pretrain/Step Time": 8.478725312277675} +{"Pretrain/Learning Rate": 4.770668875132663e-05, "Pretrain/Loss": 2.091423988342285, "Pretrain/Loss (Raw)": 2.100139617919922, "Pretrain/Step": 1557, "Pretrain/Step Time": 8.479109914973378} +{"Pretrain/Learning Rate": 4.7703134981128285e-05, "Pretrain/Loss": 2.0912911891937256, "Pretrain/Loss (Raw)": 2.181302070617676, "Pretrain/Step": 1558, "Pretrain/Step Time": 8.480088584125042} +{"Pretrain/Learning Rate": 4.76995785921313e-05, "Pretrain/Loss": 2.0903384685516357, "Pretrain/Loss (Raw)": 2.0522336959838867, "Pretrain/Step": 1559, "Pretrain/Step Time": 8.481873599812388} +{"Pretrain/Learning Rate": 4.7696019584745886e-05, "Pretrain/Loss": 2.0906529426574707, "Pretrain/Loss (Raw)": 2.0441575050354004, "Pretrain/Step": 1560, "Pretrain/Step Time": 8.487559735774994} +{"Pretrain/Learning Rate": 4.769245795938261e-05, "Pretrain/Loss": 2.0907504558563232, "Pretrain/Loss (Raw)": 2.0654728412628174, "Pretrain/Step": 1561, "Pretrain/Step Time": 8.484333140775561} +{"Pretrain/Learning Rate": 4.768889371645227e-05, "Pretrain/Loss": 2.091369390487671, "Pretrain/Loss (Raw)": 2.1888110637664795, "Pretrain/Step": 1562, "Pretrain/Step Time": 8.4831599034369} +{"Pretrain/Learning Rate": 4.768532685636602e-05, "Pretrain/Loss": 2.0911812782287598, "Pretrain/Loss (Raw)": 2.0916662216186523, "Pretrain/Step": 1563, "Pretrain/Step Time": 8.485170530155301} +{"Pretrain/Learning Rate": 4.768175737953529e-05, "Pretrain/Loss": 2.0901355743408203, "Pretrain/Loss (Raw)": 1.8971549272537231, "Pretrain/Step": 1564, "Pretrain/Step Time": 8.486812891438603} +{"Pretrain/Learning Rate": 4.767818528637181e-05, "Pretrain/Loss": 2.0885848999023438, "Pretrain/Loss (Raw)": 2.0094313621520996, "Pretrain/Step": 1565, "Pretrain/Step Time": 8.48433238454163} +{"Pretrain/Learning Rate": 4.767461057728763e-05, "Pretrain/Loss": 2.088660717010498, "Pretrain/Loss (Raw)": 2.16957426071167, "Pretrain/Step": 1566, "Pretrain/Step Time": 8.486785234883428} +{"Pretrain/Learning Rate": 4.7671033252695083e-05, "Pretrain/Loss": 2.0896568298339844, "Pretrain/Loss (Raw)": 2.119126081466675, "Pretrain/Step": 1567, "Pretrain/Step Time": 8.483476670458913} +{"Pretrain/Learning Rate": 4.7667453313006825e-05, "Pretrain/Loss": 2.089387893676758, "Pretrain/Loss (Raw)": 1.9964817762374878, "Pretrain/Step": 1568, "Pretrain/Step Time": 8.485963368788362} +{"Pretrain/Learning Rate": 4.76638707586358e-05, "Pretrain/Loss": 2.08992600440979, "Pretrain/Loss (Raw)": 2.013274908065796, "Pretrain/Step": 1569, "Pretrain/Step Time": 8.486845668405294} +{"Pretrain/Learning Rate": 4.766028558999524e-05, "Pretrain/Loss": 2.089603900909424, "Pretrain/Loss (Raw)": 2.0954060554504395, "Pretrain/Step": 1570, "Pretrain/Step Time": 8.48403149843216} +{"Pretrain/Learning Rate": 4.765669780749869e-05, "Pretrain/Loss": 2.090074062347412, "Pretrain/Loss (Raw)": 2.117236852645874, "Pretrain/Step": 1571, "Pretrain/Step Time": 8.486904015764594} +{"Pretrain/Learning Rate": 4.7653107411560026e-05, "Pretrain/Loss": 2.0896406173706055, "Pretrain/Loss (Raw)": 2.189624071121216, "Pretrain/Step": 1572, "Pretrain/Step Time": 8.484830083325505} +{"Pretrain/Learning Rate": 4.7649514402593374e-05, "Pretrain/Loss": 2.0902206897735596, "Pretrain/Loss (Raw)": 2.180377244949341, "Pretrain/Step": 1573, "Pretrain/Step Time": 8.484056331217289} +{"Pretrain/Learning Rate": 4.76459187810132e-05, "Pretrain/Loss": 2.089120626449585, "Pretrain/Loss (Raw)": 1.8731833696365356, "Pretrain/Step": 1574, "Pretrain/Step Time": 8.48404890857637} +{"Pretrain/Learning Rate": 4.764232054723425e-05, "Pretrain/Loss": 2.0887207984924316, "Pretrain/Loss (Raw)": 2.112551212310791, "Pretrain/Step": 1575, "Pretrain/Step Time": 8.48615674301982} +{"Pretrain/Learning Rate": 4.7638719701671584e-05, "Pretrain/Loss": 2.088662624359131, "Pretrain/Loss (Raw)": 2.0472042560577393, "Pretrain/Step": 1576, "Pretrain/Step Time": 8.487799018621445} +{"Pretrain/Learning Rate": 4.763511624474055e-05, "Pretrain/Loss": 2.0877933502197266, "Pretrain/Loss (Raw)": 1.9286508560180664, "Pretrain/Step": 1577, "Pretrain/Step Time": 8.487696724012494} +{"Pretrain/Learning Rate": 4.763151017685682e-05, "Pretrain/Loss": 2.087054491043091, "Pretrain/Loss (Raw)": 1.9002249240875244, "Pretrain/Step": 1578, "Pretrain/Step Time": 8.487664924934506} +{"Pretrain/Learning Rate": 4.762790149843634e-05, "Pretrain/Loss": 2.0880861282348633, "Pretrain/Loss (Raw)": 2.088087797164917, "Pretrain/Step": 1579, "Pretrain/Step Time": 8.487380884587765} +{"Pretrain/Learning Rate": 4.7624290209895384e-05, "Pretrain/Loss": 2.088587760925293, "Pretrain/Loss (Raw)": 2.2958128452301025, "Pretrain/Step": 1580, "Pretrain/Step Time": 8.485706569626927} +{"Pretrain/Learning Rate": 4.762067631165049e-05, "Pretrain/Loss": 2.085679292678833, "Pretrain/Loss (Raw)": 1.830045461654663, "Pretrain/Step": 1581, "Pretrain/Step Time": 8.486081525683403} +{"Pretrain/Learning Rate": 4.7617059804118534e-05, "Pretrain/Loss": 2.086143970489502, "Pretrain/Loss (Raw)": 2.1379001140594482, "Pretrain/Step": 1582, "Pretrain/Step Time": 8.48818426951766} +{"Pretrain/Learning Rate": 4.761344068771668e-05, "Pretrain/Loss": 2.084359884262085, "Pretrain/Loss (Raw)": 1.9822689294815063, "Pretrain/Step": 1583, "Pretrain/Step Time": 8.488415937870741} +{"Pretrain/Learning Rate": 4.7609818962862394e-05, "Pretrain/Loss": 2.0851809978485107, "Pretrain/Loss (Raw)": 2.0343284606933594, "Pretrain/Step": 1584, "Pretrain/Step Time": 8.486053675413132} +{"Pretrain/Learning Rate": 4.760619462997343e-05, "Pretrain/Loss": 2.0837953090667725, "Pretrain/Loss (Raw)": 2.0645804405212402, "Pretrain/Step": 1585, "Pretrain/Step Time": 8.486795349046588} +{"Pretrain/Learning Rate": 4.760256768946787e-05, "Pretrain/Loss": 2.083561420440674, "Pretrain/Loss (Raw)": 2.1129095554351807, "Pretrain/Step": 1586, "Pretrain/Step Time": 8.486202718690038} +{"Pretrain/Learning Rate": 4.759893814176406e-05, "Pretrain/Loss": 2.084853410720825, "Pretrain/Loss (Raw)": 2.248518228530884, "Pretrain/Step": 1587, "Pretrain/Step Time": 8.488662483170629} +{"Pretrain/Learning Rate": 4.759530598728068e-05, "Pretrain/Loss": 2.084622859954834, "Pretrain/Loss (Raw)": 2.044199228286743, "Pretrain/Step": 1588, "Pretrain/Step Time": 8.491168467327952} +{"Pretrain/Learning Rate": 4.7591671226436695e-05, "Pretrain/Loss": 2.0833332538604736, "Pretrain/Loss (Raw)": 2.0479187965393066, "Pretrain/Step": 1589, "Pretrain/Step Time": 8.491453021764755} +{"Pretrain/Learning Rate": 4.7588033859651376e-05, "Pretrain/Loss": 2.0821406841278076, "Pretrain/Loss (Raw)": 1.9035407304763794, "Pretrain/Step": 1590, "Pretrain/Step Time": 8.489632412791252} +{"Pretrain/Learning Rate": 4.758439388734429e-05, "Pretrain/Loss": 2.080761194229126, "Pretrain/Loss (Raw)": 1.937463641166687, "Pretrain/Step": 1591, "Pretrain/Step Time": 8.491388563066721} +{"Pretrain/Learning Rate": 4.75807513099353e-05, "Pretrain/Loss": 2.080878257751465, "Pretrain/Loss (Raw)": 2.161609411239624, "Pretrain/Step": 1592, "Pretrain/Step Time": 8.492390386760235} +{"Pretrain/Learning Rate": 4.7577106127844585e-05, "Pretrain/Loss": 2.0814919471740723, "Pretrain/Loss (Raw)": 2.025414228439331, "Pretrain/Step": 1593, "Pretrain/Step Time": 8.494850896298885} +{"Pretrain/Learning Rate": 4.757345834149261e-05, "Pretrain/Loss": 2.0823588371276855, "Pretrain/Loss (Raw)": 2.1125524044036865, "Pretrain/Step": 1594, "Pretrain/Step Time": 8.494635470211506} +{"Pretrain/Learning Rate": 4.756980795130015e-05, "Pretrain/Loss": 2.0849599838256836, "Pretrain/Loss (Raw)": 2.4220168590545654, "Pretrain/Step": 1595, "Pretrain/Step Time": 8.49029847420752} +{"Pretrain/Learning Rate": 4.7566154957688274e-05, "Pretrain/Loss": 2.0859906673431396, "Pretrain/Loss (Raw)": 2.2127599716186523, "Pretrain/Step": 1596, "Pretrain/Step Time": 8.494046553969383} +{"Pretrain/Learning Rate": 4.7562499361078356e-05, "Pretrain/Loss": 2.0865044593811035, "Pretrain/Loss (Raw)": 2.053297996520996, "Pretrain/Step": 1597, "Pretrain/Step Time": 8.495899815112352} +{"Pretrain/Learning Rate": 4.755884116189207e-05, "Pretrain/Loss": 2.0854885578155518, "Pretrain/Loss (Raw)": 1.8833959102630615, "Pretrain/Step": 1598, "Pretrain/Step Time": 8.495406091213226} +{"Pretrain/Learning Rate": 4.755518036055137e-05, "Pretrain/Loss": 2.085111379623413, "Pretrain/Loss (Raw)": 2.095255136489868, "Pretrain/Step": 1599, "Pretrain/Step Time": 8.498787686228752} +{"Pretrain/Learning Rate": 4.7551516957478546e-05, "Pretrain/Loss": 2.0836734771728516, "Pretrain/Loss (Raw)": 1.8668441772460938, "Pretrain/Step": 1600, "Pretrain/Step Time": 8.496956773102283} +{"Pretrain/Learning Rate": 4.754785095309617e-05, "Pretrain/Loss": 2.0838968753814697, "Pretrain/Loss (Raw)": 1.971128225326538, "Pretrain/Step": 1601, "Pretrain/Step Time": 8.495713409036398} +{"Pretrain/Learning Rate": 4.7544182347827116e-05, "Pretrain/Loss": 2.0851387977600098, "Pretrain/Loss (Raw)": 2.1492393016815186, "Pretrain/Step": 1602, "Pretrain/Step Time": 8.494518954306841} +{"Pretrain/Learning Rate": 4.754051114209455e-05, "Pretrain/Loss": 2.0861525535583496, "Pretrain/Loss (Raw)": 2.1741836071014404, "Pretrain/Step": 1603, "Pretrain/Step Time": 8.495862262323499} +{"Pretrain/Learning Rate": 4.753683733632193e-05, "Pretrain/Loss": 2.084679126739502, "Pretrain/Loss (Raw)": 1.941874623298645, "Pretrain/Step": 1604, "Pretrain/Step Time": 8.498115753754973} +{"Pretrain/Learning Rate": 4.7533160930933056e-05, "Pretrain/Loss": 2.0831966400146484, "Pretrain/Loss (Raw)": 1.9351719617843628, "Pretrain/Step": 1605, "Pretrain/Step Time": 8.501436294987798} +{"Pretrain/Learning Rate": 4.752948192635198e-05, "Pretrain/Loss": 2.0836234092712402, "Pretrain/Loss (Raw)": 2.102226734161377, "Pretrain/Step": 1606, "Pretrain/Step Time": 8.499064698815346} +{"Pretrain/Learning Rate": 4.752580032300309e-05, "Pretrain/Loss": 2.0836849212646484, "Pretrain/Loss (Raw)": 2.1557087898254395, "Pretrain/Step": 1607, "Pretrain/Step Time": 8.498635096475482} +{"Pretrain/Learning Rate": 4.752211612131104e-05, "Pretrain/Loss": 2.08225154876709, "Pretrain/Loss (Raw)": 2.1205196380615234, "Pretrain/Step": 1608, "Pretrain/Step Time": 8.496411174535751} +{"Pretrain/Learning Rate": 4.751842932170082e-05, "Pretrain/Loss": 2.0810439586639404, "Pretrain/Loss (Raw)": 1.9354251623153687, "Pretrain/Step": 1609, "Pretrain/Step Time": 8.497389409691095} +{"Pretrain/Learning Rate": 4.7514739924597686e-05, "Pretrain/Loss": 2.0788955688476562, "Pretrain/Loss (Raw)": 2.094611883163452, "Pretrain/Step": 1610, "Pretrain/Step Time": 8.493553299456835} +{"Pretrain/Learning Rate": 4.751104793042722e-05, "Pretrain/Loss": 2.077608346939087, "Pretrain/Loss (Raw)": 1.794808030128479, "Pretrain/Step": 1611, "Pretrain/Step Time": 8.491251705214381} +{"Pretrain/Learning Rate": 4.7507353339615275e-05, "Pretrain/Loss": 2.076202869415283, "Pretrain/Loss (Raw)": 1.9803181886672974, "Pretrain/Step": 1612, "Pretrain/Step Time": 8.490511620417237} +{"Pretrain/Learning Rate": 4.7503656152588036e-05, "Pretrain/Loss": 2.0768394470214844, "Pretrain/Loss (Raw)": 2.0936813354492188, "Pretrain/Step": 1613, "Pretrain/Step Time": 8.492281377315521} +{"Pretrain/Learning Rate": 4.749995636977197e-05, "Pretrain/Loss": 2.0762758255004883, "Pretrain/Loss (Raw)": 2.0206658840179443, "Pretrain/Step": 1614, "Pretrain/Step Time": 8.493267685174942} +{"Pretrain/Learning Rate": 4.7496253991593844e-05, "Pretrain/Loss": 2.0763955116271973, "Pretrain/Loss (Raw)": 2.1561930179595947, "Pretrain/Step": 1615, "Pretrain/Step Time": 8.494624434038997} +{"Pretrain/Learning Rate": 4.749254901848073e-05, "Pretrain/Loss": 2.07696270942688, "Pretrain/Loss (Raw)": 2.1262474060058594, "Pretrain/Step": 1616, "Pretrain/Step Time": 8.49602722749114} +{"Pretrain/Learning Rate": 4.7488841450859975e-05, "Pretrain/Loss": 2.0779519081115723, "Pretrain/Loss (Raw)": 2.2095351219177246, "Pretrain/Step": 1617, "Pretrain/Step Time": 8.488427663221955} +{"Pretrain/Learning Rate": 4.7485131289159276e-05, "Pretrain/Loss": 2.0800602436065674, "Pretrain/Loss (Raw)": 2.271378993988037, "Pretrain/Step": 1618, "Pretrain/Step Time": 8.489720914512873} +{"Pretrain/Learning Rate": 4.7481418533806586e-05, "Pretrain/Loss": 2.0812907218933105, "Pretrain/Loss (Raw)": 2.0889976024627686, "Pretrain/Step": 1619, "Pretrain/Step Time": 8.487675406038761} +{"Pretrain/Learning Rate": 4.747770318523016e-05, "Pretrain/Loss": 2.0810317993164062, "Pretrain/Loss (Raw)": 2.041980504989624, "Pretrain/Step": 1620, "Pretrain/Step Time": 8.482803966850042} +{"Pretrain/Learning Rate": 4.7473985243858575e-05, "Pretrain/Loss": 2.083566188812256, "Pretrain/Loss (Raw)": 2.1125919818878174, "Pretrain/Step": 1621, "Pretrain/Step Time": 8.483929969370365} +{"Pretrain/Learning Rate": 4.7470264710120697e-05, "Pretrain/Loss": 2.0852694511413574, "Pretrain/Loss (Raw)": 2.3082993030548096, "Pretrain/Step": 1622, "Pretrain/Step Time": 8.484684588387609} +{"Pretrain/Learning Rate": 4.746654158444567e-05, "Pretrain/Loss": 2.083280086517334, "Pretrain/Loss (Raw)": 1.8950320482254028, "Pretrain/Step": 1623, "Pretrain/Step Time": 8.480157285928726} +{"Pretrain/Learning Rate": 4.7462815867262964e-05, "Pretrain/Loss": 2.082326889038086, "Pretrain/Loss (Raw)": 1.8812708854675293, "Pretrain/Step": 1624, "Pretrain/Step Time": 8.48291613906622} +{"Pretrain/Learning Rate": 4.745908755900236e-05, "Pretrain/Loss": 2.080677032470703, "Pretrain/Loss (Raw)": 1.9394537210464478, "Pretrain/Step": 1625, "Pretrain/Step Time": 8.483500890433788} +{"Pretrain/Learning Rate": 4.7455356660093886e-05, "Pretrain/Loss": 2.0819387435913086, "Pretrain/Loss (Raw)": 2.1607847213745117, "Pretrain/Step": 1626, "Pretrain/Step Time": 8.481582835316658} +{"Pretrain/Learning Rate": 4.745162317096791e-05, "Pretrain/Loss": 2.0822415351867676, "Pretrain/Loss (Raw)": 2.141085624694824, "Pretrain/Step": 1627, "Pretrain/Step Time": 8.484710624441504} +{"Pretrain/Learning Rate": 4.7447887092055095e-05, "Pretrain/Loss": 2.0804803371429443, "Pretrain/Loss (Raw)": 1.9828933477401733, "Pretrain/Step": 1628, "Pretrain/Step Time": 8.485193144530058} +{"Pretrain/Learning Rate": 4.744414842378639e-05, "Pretrain/Loss": 2.0783495903015137, "Pretrain/Loss (Raw)": 1.9612877368927002, "Pretrain/Step": 1629, "Pretrain/Step Time": 8.480605935677886} +{"Pretrain/Learning Rate": 4.744040716659306e-05, "Pretrain/Loss": 2.079618453979492, "Pretrain/Loss (Raw)": 2.2285430431365967, "Pretrain/Step": 1630, "Pretrain/Step Time": 8.479705044999719} +{"Pretrain/Learning Rate": 4.7436663320906636e-05, "Pretrain/Loss": 2.0793304443359375, "Pretrain/Loss (Raw)": 2.026758909225464, "Pretrain/Step": 1631, "Pretrain/Step Time": 8.480892607942224} +{"Pretrain/Learning Rate": 4.7432916887158993e-05, "Pretrain/Loss": 2.08123779296875, "Pretrain/Loss (Raw)": 2.3168373107910156, "Pretrain/Step": 1632, "Pretrain/Step Time": 8.47929498180747} +{"Pretrain/Learning Rate": 4.742916786578227e-05, "Pretrain/Loss": 2.0813167095184326, "Pretrain/Loss (Raw)": 2.1203179359436035, "Pretrain/Step": 1633, "Pretrain/Step Time": 8.47790884040296} +{"Pretrain/Learning Rate": 4.742541625720892e-05, "Pretrain/Loss": 2.0824978351593018, "Pretrain/Loss (Raw)": 2.129905939102173, "Pretrain/Step": 1634, "Pretrain/Step Time": 8.478482399135828} +{"Pretrain/Learning Rate": 4.7421662061871674e-05, "Pretrain/Loss": 2.0818448066711426, "Pretrain/Loss (Raw)": 1.9701157808303833, "Pretrain/Step": 1635, "Pretrain/Step Time": 8.480603244155645} +{"Pretrain/Learning Rate": 4.7417905280203594e-05, "Pretrain/Loss": 2.082582950592041, "Pretrain/Loss (Raw)": 2.2373435497283936, "Pretrain/Step": 1636, "Pretrain/Step Time": 8.47937293536961} +{"Pretrain/Learning Rate": 4.741414591263802e-05, "Pretrain/Loss": 2.080749034881592, "Pretrain/Loss (Raw)": 1.6980575323104858, "Pretrain/Step": 1637, "Pretrain/Step Time": 8.477781439200044} +{"Pretrain/Learning Rate": 4.741038395960859e-05, "Pretrain/Loss": 2.078843116760254, "Pretrain/Loss (Raw)": 2.0770814418792725, "Pretrain/Step": 1638, "Pretrain/Step Time": 8.477477511391044} +{"Pretrain/Learning Rate": 4.740661942154925e-05, "Pretrain/Loss": 2.079042911529541, "Pretrain/Loss (Raw)": 2.144223690032959, "Pretrain/Step": 1639, "Pretrain/Step Time": 8.477970598265529} +{"Pretrain/Learning Rate": 4.740285229889423e-05, "Pretrain/Loss": 2.0793519020080566, "Pretrain/Loss (Raw)": 2.0857934951782227, "Pretrain/Step": 1640, "Pretrain/Step Time": 8.478078776970506} +{"Pretrain/Learning Rate": 4.739908259207807e-05, "Pretrain/Loss": 2.0792064666748047, "Pretrain/Loss (Raw)": 2.0930306911468506, "Pretrain/Step": 1641, "Pretrain/Step Time": 8.478231808170676} +{"Pretrain/Learning Rate": 4.73953103015356e-05, "Pretrain/Loss": 2.079216480255127, "Pretrain/Loss (Raw)": 2.0281431674957275, "Pretrain/Step": 1642, "Pretrain/Step Time": 8.478881262242794} +{"Pretrain/Learning Rate": 4.7391535427701966e-05, "Pretrain/Loss": 2.0786101818084717, "Pretrain/Loss (Raw)": 2.0310792922973633, "Pretrain/Step": 1643, "Pretrain/Step Time": 8.47333961725235} +{"Pretrain/Learning Rate": 4.738775797101258e-05, "Pretrain/Loss": 2.0780797004699707, "Pretrain/Loss (Raw)": 2.0215003490448, "Pretrain/Step": 1644, "Pretrain/Step Time": 8.474443333223462} +{"Pretrain/Learning Rate": 4.738397793190319e-05, "Pretrain/Loss": 2.077308177947998, "Pretrain/Loss (Raw)": 1.9133070707321167, "Pretrain/Step": 1645, "Pretrain/Step Time": 8.470439679920673} +{"Pretrain/Learning Rate": 4.7380195310809806e-05, "Pretrain/Loss": 2.0781073570251465, "Pretrain/Loss (Raw)": 2.1831939220428467, "Pretrain/Step": 1646, "Pretrain/Step Time": 8.474375784397125} +{"Pretrain/Learning Rate": 4.7376410108168753e-05, "Pretrain/Loss": 2.079688787460327, "Pretrain/Loss (Raw)": 2.2140955924987793, "Pretrain/Step": 1647, "Pretrain/Step Time": 8.47503962367773} +{"Pretrain/Learning Rate": 4.737262232441667e-05, "Pretrain/Loss": 2.0778889656066895, "Pretrain/Loss (Raw)": 1.8882944583892822, "Pretrain/Step": 1648, "Pretrain/Step Time": 8.470078811049461} +{"Pretrain/Learning Rate": 4.736883195999045e-05, "Pretrain/Loss": 2.077329635620117, "Pretrain/Loss (Raw)": 1.993132472038269, "Pretrain/Step": 1649, "Pretrain/Step Time": 8.469082606956363} +{"Pretrain/Learning Rate": 4.736503901532734e-05, "Pretrain/Loss": 2.076176166534424, "Pretrain/Loss (Raw)": 2.0215892791748047, "Pretrain/Step": 1650, "Pretrain/Step Time": 8.473194116726518} +{"Pretrain/Learning Rate": 4.736124349086482e-05, "Pretrain/Loss": 2.076211452484131, "Pretrain/Loss (Raw)": 2.0468690395355225, "Pretrain/Step": 1651, "Pretrain/Step Time": 8.474482899531722} +{"Pretrain/Learning Rate": 4.7357445387040746e-05, "Pretrain/Loss": 2.076589345932007, "Pretrain/Loss (Raw)": 2.122502565383911, "Pretrain/Step": 1652, "Pretrain/Step Time": 8.476427927613258} +{"Pretrain/Learning Rate": 4.7353644704293185e-05, "Pretrain/Loss": 2.0768496990203857, "Pretrain/Loss (Raw)": 1.9460822343826294, "Pretrain/Step": 1653, "Pretrain/Step Time": 8.475943448022008} +{"Pretrain/Learning Rate": 4.734984144306057e-05, "Pretrain/Loss": 2.076627254486084, "Pretrain/Loss (Raw)": 2.0852034091949463, "Pretrain/Step": 1654, "Pretrain/Step Time": 8.475442171096802} +{"Pretrain/Learning Rate": 4.73460356037816e-05, "Pretrain/Loss": 2.0764336585998535, "Pretrain/Loss (Raw)": 2.0604443550109863, "Pretrain/Step": 1655, "Pretrain/Step Time": 8.473725816234946} +{"Pretrain/Learning Rate": 4.7342227186895275e-05, "Pretrain/Loss": 2.0751657485961914, "Pretrain/Loss (Raw)": 1.9213892221450806, "Pretrain/Step": 1656, "Pretrain/Step Time": 8.475418819114566} +{"Pretrain/Learning Rate": 4.733841619284089e-05, "Pretrain/Loss": 2.074237585067749, "Pretrain/Loss (Raw)": 2.0679337978363037, "Pretrain/Step": 1657, "Pretrain/Step Time": 8.475196098908782} +{"Pretrain/Learning Rate": 4.733460262205805e-05, "Pretrain/Loss": 2.074267864227295, "Pretrain/Loss (Raw)": 2.1632144451141357, "Pretrain/Step": 1658, "Pretrain/Step Time": 8.472383787855506} +{"Pretrain/Learning Rate": 4.733078647498665e-05, "Pretrain/Loss": 2.075015068054199, "Pretrain/Loss (Raw)": 2.1438376903533936, "Pretrain/Step": 1659, "Pretrain/Step Time": 8.47075815871358} +{"Pretrain/Learning Rate": 4.732696775206688e-05, "Pretrain/Loss": 2.0761566162109375, "Pretrain/Loss (Raw)": 2.178226947784424, "Pretrain/Step": 1660, "Pretrain/Step Time": 8.469647051766515} +{"Pretrain/Learning Rate": 4.732314645373921e-05, "Pretrain/Loss": 2.074336290359497, "Pretrain/Loss (Raw)": 1.9968793392181396, "Pretrain/Step": 1661, "Pretrain/Step Time": 8.469493206590414} +{"Pretrain/Learning Rate": 4.731932258044446e-05, "Pretrain/Loss": 2.0735981464385986, "Pretrain/Loss (Raw)": 2.0912861824035645, "Pretrain/Step": 1662, "Pretrain/Step Time": 8.46901448816061} +{"Pretrain/Learning Rate": 4.731549613262368e-05, "Pretrain/Loss": 2.0716841220855713, "Pretrain/Loss (Raw)": 1.8755862712860107, "Pretrain/Step": 1663, "Pretrain/Step Time": 8.471034564077854} +{"Pretrain/Learning Rate": 4.731166711071827e-05, "Pretrain/Loss": 2.071408748626709, "Pretrain/Loss (Raw)": 2.0468318462371826, "Pretrain/Step": 1664, "Pretrain/Step Time": 8.467396404594183} +{"Pretrain/Learning Rate": 4.730783551516991e-05, "Pretrain/Loss": 2.0707662105560303, "Pretrain/Loss (Raw)": 2.0839970111846924, "Pretrain/Step": 1665, "Pretrain/Step Time": 8.46867953427136} +{"Pretrain/Learning Rate": 4.730400134642055e-05, "Pretrain/Loss": 2.0719001293182373, "Pretrain/Loss (Raw)": 1.9755607843399048, "Pretrain/Step": 1666, "Pretrain/Step Time": 8.46879843622446} +{"Pretrain/Learning Rate": 4.7300164604912475e-05, "Pretrain/Loss": 2.072963237762451, "Pretrain/Loss (Raw)": 2.159780979156494, "Pretrain/Step": 1667, "Pretrain/Step Time": 8.465433616191149} +{"Pretrain/Learning Rate": 4.729632529108825e-05, "Pretrain/Loss": 2.074357032775879, "Pretrain/Loss (Raw)": 2.1269335746765137, "Pretrain/Step": 1668, "Pretrain/Step Time": 8.46712177991867} +{"Pretrain/Learning Rate": 4.7292483405390736e-05, "Pretrain/Loss": 2.0732476711273193, "Pretrain/Loss (Raw)": 2.0019891262054443, "Pretrain/Step": 1669, "Pretrain/Step Time": 8.469198897480965} +{"Pretrain/Learning Rate": 4.72886389482631e-05, "Pretrain/Loss": 2.0718297958374023, "Pretrain/Loss (Raw)": 2.073561191558838, "Pretrain/Step": 1670, "Pretrain/Step Time": 8.466927904635668} +{"Pretrain/Learning Rate": 4.7284791920148784e-05, "Pretrain/Loss": 2.07114839553833, "Pretrain/Loss (Raw)": 2.1556484699249268, "Pretrain/Step": 1671, "Pretrain/Step Time": 8.469325421378016} +{"Pretrain/Learning Rate": 4.728094232149156e-05, "Pretrain/Loss": 2.0708365440368652, "Pretrain/Loss (Raw)": 2.049424171447754, "Pretrain/Step": 1672, "Pretrain/Step Time": 8.46706528775394} +{"Pretrain/Learning Rate": 4.727709015273547e-05, "Pretrain/Loss": 2.069342851638794, "Pretrain/Loss (Raw)": 1.9058291912078857, "Pretrain/Step": 1673, "Pretrain/Step Time": 8.464746180921793} +{"Pretrain/Learning Rate": 4.727323541432486e-05, "Pretrain/Loss": 2.0688254833221436, "Pretrain/Loss (Raw)": 1.9412144422531128, "Pretrain/Step": 1674, "Pretrain/Step Time": 8.466966640204191} +{"Pretrain/Learning Rate": 4.726937810670437e-05, "Pretrain/Loss": 2.068044662475586, "Pretrain/Loss (Raw)": 2.0164146423339844, "Pretrain/Step": 1675, "Pretrain/Step Time": 8.470172293484211} +{"Pretrain/Learning Rate": 4.7265518230318944e-05, "Pretrain/Loss": 2.066478967666626, "Pretrain/Loss (Raw)": 2.1364853382110596, "Pretrain/Step": 1676, "Pretrain/Step Time": 8.468007357791066} +{"Pretrain/Learning Rate": 4.7261655785613814e-05, "Pretrain/Loss": 2.0662248134613037, "Pretrain/Loss (Raw)": 2.2088522911071777, "Pretrain/Step": 1677, "Pretrain/Step Time": 8.46703665703535} +{"Pretrain/Learning Rate": 4.725779077303451e-05, "Pretrain/Loss": 2.065871477127075, "Pretrain/Loss (Raw)": 2.143982410430908, "Pretrain/Step": 1678, "Pretrain/Step Time": 8.46656751446426} +{"Pretrain/Learning Rate": 4.7253923193026863e-05, "Pretrain/Loss": 2.065645933151245, "Pretrain/Loss (Raw)": 1.9843262434005737, "Pretrain/Step": 1679, "Pretrain/Step Time": 8.465412136167288} +{"Pretrain/Learning Rate": 4.7250053046036994e-05, "Pretrain/Loss": 2.0635814666748047, "Pretrain/Loss (Raw)": 1.8412067890167236, "Pretrain/Step": 1680, "Pretrain/Step Time": 8.466232363134623} +{"Pretrain/Learning Rate": 4.724618033251133e-05, "Pretrain/Loss": 2.063758373260498, "Pretrain/Loss (Raw)": 2.1221492290496826, "Pretrain/Step": 1681, "Pretrain/Step Time": 8.467669785022736} +{"Pretrain/Learning Rate": 4.724230505289658e-05, "Pretrain/Loss": 2.0628180503845215, "Pretrain/Loss (Raw)": 2.0275073051452637, "Pretrain/Step": 1682, "Pretrain/Step Time": 8.469311580061913} +{"Pretrain/Learning Rate": 4.723842720763976e-05, "Pretrain/Loss": 2.06245493888855, "Pretrain/Loss (Raw)": 2.1714444160461426, "Pretrain/Step": 1683, "Pretrain/Step Time": 8.466633850708604} +{"Pretrain/Learning Rate": 4.723454679718817e-05, "Pretrain/Loss": 2.0622973442077637, "Pretrain/Loss (Raw)": 1.9985285997390747, "Pretrain/Step": 1684, "Pretrain/Step Time": 8.469024883583188} +{"Pretrain/Learning Rate": 4.723066382198943e-05, "Pretrain/Loss": 2.061781167984009, "Pretrain/Loss (Raw)": 2.034065008163452, "Pretrain/Step": 1685, "Pretrain/Step Time": 8.469532698392868} +{"Pretrain/Learning Rate": 4.7226778282491424e-05, "Pretrain/Loss": 2.0606892108917236, "Pretrain/Loss (Raw)": 2.04152512550354, "Pretrain/Step": 1686, "Pretrain/Step Time": 8.471382724121213} +{"Pretrain/Learning Rate": 4.722289017914236e-05, "Pretrain/Loss": 2.0615203380584717, "Pretrain/Loss (Raw)": 2.158627986907959, "Pretrain/Step": 1687, "Pretrain/Step Time": 8.469077223911881} +{"Pretrain/Learning Rate": 4.721899951239072e-05, "Pretrain/Loss": 2.061743974685669, "Pretrain/Loss (Raw)": 2.0727663040161133, "Pretrain/Step": 1688, "Pretrain/Step Time": 8.461874866858125} +{"Pretrain/Learning Rate": 4.72151062826853e-05, "Pretrain/Loss": 2.0616466999053955, "Pretrain/Loss (Raw)": 2.0530316829681396, "Pretrain/Step": 1689, "Pretrain/Step Time": 8.462571831420064} +{"Pretrain/Learning Rate": 4.721121049047517e-05, "Pretrain/Loss": 2.0611472129821777, "Pretrain/Loss (Raw)": 2.1248867511749268, "Pretrain/Step": 1690, "Pretrain/Step Time": 8.46228052675724} +{"Pretrain/Learning Rate": 4.720731213620972e-05, "Pretrain/Loss": 2.062049627304077, "Pretrain/Loss (Raw)": 2.207167625427246, "Pretrain/Step": 1691, "Pretrain/Step Time": 8.458434864878654} +{"Pretrain/Learning Rate": 4.720341122033862e-05, "Pretrain/Loss": 2.062223434448242, "Pretrain/Loss (Raw)": 1.9194145202636719, "Pretrain/Step": 1692, "Pretrain/Step Time": 8.459444541484118} +{"Pretrain/Learning Rate": 4.719950774331183e-05, "Pretrain/Loss": 2.0616517066955566, "Pretrain/Loss (Raw)": 1.9362468719482422, "Pretrain/Step": 1693, "Pretrain/Step Time": 8.459272403270006} +{"Pretrain/Learning Rate": 4.7195601705579626e-05, "Pretrain/Loss": 2.0611793994903564, "Pretrain/Loss (Raw)": 2.1091012954711914, "Pretrain/Step": 1694, "Pretrain/Step Time": 8.458779081702232} +{"Pretrain/Learning Rate": 4.719169310759257e-05, "Pretrain/Loss": 2.060234546661377, "Pretrain/Loss (Raw)": 1.998185634613037, "Pretrain/Step": 1695, "Pretrain/Step Time": 8.463442226871848} +{"Pretrain/Learning Rate": 4.7187781949801514e-05, "Pretrain/Loss": 2.061434745788574, "Pretrain/Loss (Raw)": 2.1501057147979736, "Pretrain/Step": 1696, "Pretrain/Step Time": 8.46024907566607} +{"Pretrain/Learning Rate": 4.71838682326576e-05, "Pretrain/Loss": 2.0619282722473145, "Pretrain/Loss (Raw)": 2.0764403343200684, "Pretrain/Step": 1697, "Pretrain/Step Time": 8.459155777469277} +{"Pretrain/Learning Rate": 4.717995195661229e-05, "Pretrain/Loss": 2.060033082962036, "Pretrain/Loss (Raw)": 1.8528450727462769, "Pretrain/Step": 1698, "Pretrain/Step Time": 8.460195684805512} +{"Pretrain/Learning Rate": 4.7176033122117317e-05, "Pretrain/Loss": 2.058544635772705, "Pretrain/Loss (Raw)": 1.9267200231552124, "Pretrain/Step": 1699, "Pretrain/Step Time": 8.457163862884045} +{"Pretrain/Learning Rate": 4.7172111729624706e-05, "Pretrain/Loss": 2.0579867362976074, "Pretrain/Loss (Raw)": 2.1182329654693604, "Pretrain/Step": 1700, "Pretrain/Step Time": 8.45817256718874} +{"Pretrain/Learning Rate": 4.71681877795868e-05, "Pretrain/Loss": 2.0580835342407227, "Pretrain/Loss (Raw)": 2.1927244663238525, "Pretrain/Step": 1701, "Pretrain/Step Time": 8.458870820701122} +{"Pretrain/Learning Rate": 4.716426127245624e-05, "Pretrain/Loss": 2.0583155155181885, "Pretrain/Loss (Raw)": 1.9028816223144531, "Pretrain/Step": 1702, "Pretrain/Step Time": 8.45817998982966} +{"Pretrain/Learning Rate": 4.716033220868592e-05, "Pretrain/Loss": 2.058598518371582, "Pretrain/Loss (Raw)": 2.1487839221954346, "Pretrain/Step": 1703, "Pretrain/Step Time": 8.457002388313413} +{"Pretrain/Learning Rate": 4.7156400588729066e-05, "Pretrain/Loss": 2.057837963104248, "Pretrain/Loss (Raw)": 1.9498519897460938, "Pretrain/Step": 1704, "Pretrain/Step Time": 8.456670412793756} +{"Pretrain/Learning Rate": 4.7152466413039184e-05, "Pretrain/Loss": 2.0582804679870605, "Pretrain/Loss (Raw)": 1.9852761030197144, "Pretrain/Step": 1705, "Pretrain/Step Time": 8.456321878358722} +{"Pretrain/Learning Rate": 4.71485296820701e-05, "Pretrain/Loss": 2.0588717460632324, "Pretrain/Loss (Raw)": 1.975949764251709, "Pretrain/Step": 1706, "Pretrain/Step Time": 8.455282598733902} +{"Pretrain/Learning Rate": 4.7144590396275896e-05, "Pretrain/Loss": 2.0586354732513428, "Pretrain/Loss (Raw)": 2.05780291557312, "Pretrain/Step": 1707, "Pretrain/Step Time": 8.451723055914044} +{"Pretrain/Learning Rate": 4.714064855611097e-05, "Pretrain/Loss": 2.057788610458374, "Pretrain/Loss (Raw)": 2.18743634223938, "Pretrain/Step": 1708, "Pretrain/Step Time": 8.449596278369427} +{"Pretrain/Learning Rate": 4.713670416203001e-05, "Pretrain/Loss": 2.0596797466278076, "Pretrain/Loss (Raw)": 2.0721094608306885, "Pretrain/Step": 1709, "Pretrain/Step Time": 8.450497929006815} +{"Pretrain/Learning Rate": 4.7132757214488013e-05, "Pretrain/Loss": 2.059535264968872, "Pretrain/Loss (Raw)": 2.119396448135376, "Pretrain/Step": 1710, "Pretrain/Step Time": 8.456097910180688} +{"Pretrain/Learning Rate": 4.712880771394024e-05, "Pretrain/Loss": 2.0612497329711914, "Pretrain/Loss (Raw)": 2.2017033100128174, "Pretrain/Step": 1711, "Pretrain/Step Time": 8.453330544754863} +{"Pretrain/Learning Rate": 4.712485566084228e-05, "Pretrain/Loss": 2.0624375343322754, "Pretrain/Loss (Raw)": 2.1863932609558105, "Pretrain/Step": 1712, "Pretrain/Step Time": 8.457026274874806} +{"Pretrain/Learning Rate": 4.712090105565e-05, "Pretrain/Loss": 2.0623092651367188, "Pretrain/Loss (Raw)": 2.0481390953063965, "Pretrain/Step": 1713, "Pretrain/Step Time": 8.455315625295043} +{"Pretrain/Learning Rate": 4.7116943898819546e-05, "Pretrain/Loss": 2.062613010406494, "Pretrain/Loss (Raw)": 2.1517996788024902, "Pretrain/Step": 1714, "Pretrain/Step Time": 8.455133523792028} +{"Pretrain/Learning Rate": 4.711298419080739e-05, "Pretrain/Loss": 2.0609922409057617, "Pretrain/Loss (Raw)": 2.0410685539245605, "Pretrain/Step": 1715, "Pretrain/Step Time": 8.450854195281863} +{"Pretrain/Learning Rate": 4.710902193207029e-05, "Pretrain/Loss": 2.063446044921875, "Pretrain/Loss (Raw)": 2.3582980632781982, "Pretrain/Step": 1716, "Pretrain/Step Time": 8.450701732188463} +{"Pretrain/Learning Rate": 4.710505712306526e-05, "Pretrain/Loss": 2.064215660095215, "Pretrain/Loss (Raw)": 2.146406888961792, "Pretrain/Step": 1717, "Pretrain/Step Time": 8.451124558225274} +{"Pretrain/Learning Rate": 4.710108976424967e-05, "Pretrain/Loss": 2.06461501121521, "Pretrain/Loss (Raw)": 1.9546633958816528, "Pretrain/Step": 1718, "Pretrain/Step Time": 8.455908294767141} +{"Pretrain/Learning Rate": 4.709711985608114e-05, "Pretrain/Loss": 2.0656352043151855, "Pretrain/Loss (Raw)": 2.0680348873138428, "Pretrain/Step": 1719, "Pretrain/Step Time": 8.454848008230329} +{"Pretrain/Learning Rate": 4.7093147399017604e-05, "Pretrain/Loss": 2.0645461082458496, "Pretrain/Loss (Raw)": 2.0222134590148926, "Pretrain/Step": 1720, "Pretrain/Step Time": 8.452388603240252} +{"Pretrain/Learning Rate": 4.708917239351727e-05, "Pretrain/Loss": 2.064608573913574, "Pretrain/Loss (Raw)": 2.03342866897583, "Pretrain/Step": 1721, "Pretrain/Step Time": 8.447088846936822} +{"Pretrain/Learning Rate": 4.708519484003867e-05, "Pretrain/Loss": 2.063803195953369, "Pretrain/Loss (Raw)": 2.009472131729126, "Pretrain/Step": 1722, "Pretrain/Step Time": 8.449234198778868} +{"Pretrain/Learning Rate": 4.708121473904061e-05, "Pretrain/Loss": 2.0601837635040283, "Pretrain/Loss (Raw)": 1.958703637123108, "Pretrain/Step": 1723, "Pretrain/Step Time": 8.449393717572093} +{"Pretrain/Learning Rate": 4.707723209098218e-05, "Pretrain/Loss": 2.0606017112731934, "Pretrain/Loss (Raw)": 2.266251802444458, "Pretrain/Step": 1724, "Pretrain/Step Time": 8.450559997931123} +{"Pretrain/Learning Rate": 4.70732468963228e-05, "Pretrain/Loss": 2.062267780303955, "Pretrain/Loss (Raw)": 2.2665841579437256, "Pretrain/Step": 1725, "Pretrain/Step Time": 8.447169210761786} +{"Pretrain/Learning Rate": 4.7069259155522135e-05, "Pretrain/Loss": 2.0644054412841797, "Pretrain/Loss (Raw)": 2.1569931507110596, "Pretrain/Step": 1726, "Pretrain/Step Time": 8.44984078221023} +{"Pretrain/Learning Rate": 4.706526886904019e-05, "Pretrain/Loss": 2.064084529876709, "Pretrain/Loss (Raw)": 2.0541863441467285, "Pretrain/Step": 1727, "Pretrain/Step Time": 8.451505085453391} +{"Pretrain/Learning Rate": 4.706127603733723e-05, "Pretrain/Loss": 2.0653584003448486, "Pretrain/Loss (Raw)": 2.0298988819122314, "Pretrain/Step": 1728, "Pretrain/Step Time": 8.451081536710262} +{"Pretrain/Learning Rate": 4.7057280660873835e-05, "Pretrain/Loss": 2.0662636756896973, "Pretrain/Loss (Raw)": 2.08699107170105, "Pretrain/Step": 1729, "Pretrain/Step Time": 8.452627835795283} +{"Pretrain/Learning Rate": 4.705328274011086e-05, "Pretrain/Loss": 2.066373348236084, "Pretrain/Loss (Raw)": 2.163285493850708, "Pretrain/Step": 1730, "Pretrain/Step Time": 8.452580811455846} +{"Pretrain/Learning Rate": 4.704928227550949e-05, "Pretrain/Loss": 2.0659470558166504, "Pretrain/Loss (Raw)": 2.1196200847625732, "Pretrain/Step": 1731, "Pretrain/Step Time": 8.452560735866427} +{"Pretrain/Learning Rate": 4.704527926753114e-05, "Pretrain/Loss": 2.067427635192871, "Pretrain/Loss (Raw)": 2.131392002105713, "Pretrain/Step": 1732, "Pretrain/Step Time": 8.448033135384321} +{"Pretrain/Learning Rate": 4.704127371663758e-05, "Pretrain/Loss": 2.0691304206848145, "Pretrain/Loss (Raw)": 2.153132677078247, "Pretrain/Step": 1733, "Pretrain/Step Time": 8.447534289211035} +{"Pretrain/Learning Rate": 4.7037265623290836e-05, "Pretrain/Loss": 2.0665292739868164, "Pretrain/Loss (Raw)": 1.7692593336105347, "Pretrain/Step": 1734, "Pretrain/Step Time": 8.449792180210352} +{"Pretrain/Learning Rate": 4.703325498795326e-05, "Pretrain/Loss": 2.0665369033813477, "Pretrain/Loss (Raw)": 2.1566758155822754, "Pretrain/Step": 1735, "Pretrain/Step Time": 8.451742466539145} +{"Pretrain/Learning Rate": 4.7029241811087457e-05, "Pretrain/Loss": 2.0661110877990723, "Pretrain/Loss (Raw)": 2.0660250186920166, "Pretrain/Step": 1736, "Pretrain/Step Time": 8.452922338619828} +{"Pretrain/Learning Rate": 4.702522609315635e-05, "Pretrain/Loss": 2.0664291381835938, "Pretrain/Loss (Raw)": 1.9761381149291992, "Pretrain/Step": 1737, "Pretrain/Step Time": 8.454678576439619} +{"Pretrain/Learning Rate": 4.702120783462316e-05, "Pretrain/Loss": 2.065114974975586, "Pretrain/Loss (Raw)": 1.9264130592346191, "Pretrain/Step": 1738, "Pretrain/Step Time": 8.456926204264164} +{"Pretrain/Learning Rate": 4.7017187035951384e-05, "Pretrain/Loss": 2.0678293704986572, "Pretrain/Loss (Raw)": 2.1422414779663086, "Pretrain/Step": 1739, "Pretrain/Step Time": 8.455588441342115} +{"Pretrain/Learning Rate": 4.7013163697604814e-05, "Pretrain/Loss": 2.0688674449920654, "Pretrain/Loss (Raw)": 2.1131863594055176, "Pretrain/Step": 1740, "Pretrain/Step Time": 8.454359408468008} +{"Pretrain/Learning Rate": 4.7009137820047546e-05, "Pretrain/Loss": 2.0692667961120605, "Pretrain/Loss (Raw)": 2.14481258392334, "Pretrain/Step": 1741, "Pretrain/Step Time": 8.457135614007711} +{"Pretrain/Learning Rate": 4.700510940374397e-05, "Pretrain/Loss": 2.0707931518554688, "Pretrain/Loss (Raw)": 2.216042995452881, "Pretrain/Step": 1742, "Pretrain/Step Time": 8.453402468934655} +{"Pretrain/Learning Rate": 4.700107844915876e-05, "Pretrain/Loss": 2.0705666542053223, "Pretrain/Loss (Raw)": 2.1271986961364746, "Pretrain/Step": 1743, "Pretrain/Step Time": 8.455377405509353} +{"Pretrain/Learning Rate": 4.699704495675689e-05, "Pretrain/Loss": 2.070140838623047, "Pretrain/Loss (Raw)": 2.0717415809631348, "Pretrain/Step": 1744, "Pretrain/Step Time": 8.455342514440417} +{"Pretrain/Learning Rate": 4.69930089270036e-05, "Pretrain/Loss": 2.0689051151275635, "Pretrain/Loss (Raw)": 2.051346778869629, "Pretrain/Step": 1745, "Pretrain/Step Time": 8.454199271276593} +{"Pretrain/Learning Rate": 4.698897036036446e-05, "Pretrain/Loss": 2.0676510334014893, "Pretrain/Loss (Raw)": 2.110867977142334, "Pretrain/Step": 1746, "Pretrain/Step Time": 8.456593289971352} +{"Pretrain/Learning Rate": 4.6984929257305323e-05, "Pretrain/Loss": 2.066802740097046, "Pretrain/Loss (Raw)": 1.9804123640060425, "Pretrain/Step": 1747, "Pretrain/Step Time": 8.458898602053523} +{"Pretrain/Learning Rate": 4.698088561829232e-05, "Pretrain/Loss": 2.066812038421631, "Pretrain/Loss (Raw)": 2.043184995651245, "Pretrain/Step": 1748, "Pretrain/Step Time": 8.4585766736418} +{"Pretrain/Learning Rate": 4.697683944379189e-05, "Pretrain/Loss": 2.0675015449523926, "Pretrain/Loss (Raw)": 2.2008399963378906, "Pretrain/Step": 1749, "Pretrain/Step Time": 8.455031637102365} +{"Pretrain/Learning Rate": 4.697279073427074e-05, "Pretrain/Loss": 2.0661046504974365, "Pretrain/Loss (Raw)": 2.129502058029175, "Pretrain/Step": 1750, "Pretrain/Step Time": 8.455106541514397} +{"Pretrain/Learning Rate": 4.696873949019591e-05, "Pretrain/Loss": 2.067080020904541, "Pretrain/Loss (Raw)": 2.0198757648468018, "Pretrain/Step": 1751, "Pretrain/Step Time": 8.45454671420157} +{"Pretrain/Learning Rate": 4.69646857120347e-05, "Pretrain/Loss": 2.0674142837524414, "Pretrain/Loss (Raw)": 1.9240546226501465, "Pretrain/Step": 1752, "Pretrain/Step Time": 8.456972299143672} +{"Pretrain/Learning Rate": 4.696062940025471e-05, "Pretrain/Loss": 2.067518472671509, "Pretrain/Loss (Raw)": 1.9527817964553833, "Pretrain/Step": 1753, "Pretrain/Step Time": 8.458199709653854} +{"Pretrain/Learning Rate": 4.695657055532384e-05, "Pretrain/Loss": 2.0663156509399414, "Pretrain/Loss (Raw)": 2.006828784942627, "Pretrain/Step": 1754, "Pretrain/Step Time": 8.456208292394876} +{"Pretrain/Learning Rate": 4.695250917771027e-05, "Pretrain/Loss": 2.0657296180725098, "Pretrain/Loss (Raw)": 2.0660817623138428, "Pretrain/Step": 1755, "Pretrain/Step Time": 8.458371927961707} +{"Pretrain/Learning Rate": 4.6948445267882486e-05, "Pretrain/Loss": 2.067077159881592, "Pretrain/Loss (Raw)": 2.1553752422332764, "Pretrain/Step": 1756, "Pretrain/Step Time": 8.458827141672373} +{"Pretrain/Learning Rate": 4.6944378826309247e-05, "Pretrain/Loss": 2.0680174827575684, "Pretrain/Loss (Raw)": 2.0816566944122314, "Pretrain/Step": 1757, "Pretrain/Step Time": 8.457295883446932} +{"Pretrain/Learning Rate": 4.694030985345962e-05, "Pretrain/Loss": 2.0672402381896973, "Pretrain/Loss (Raw)": 2.1290457248687744, "Pretrain/Step": 1758, "Pretrain/Step Time": 8.458755733445287} +{"Pretrain/Learning Rate": 4.693623834980297e-05, "Pretrain/Loss": 2.0665154457092285, "Pretrain/Loss (Raw)": 1.9339654445648193, "Pretrain/Step": 1759, "Pretrain/Step Time": 8.457719860598445} +{"Pretrain/Learning Rate": 4.6932164315808936e-05, "Pretrain/Loss": 2.064640998840332, "Pretrain/Loss (Raw)": 2.076930284500122, "Pretrain/Step": 1760, "Pretrain/Step Time": 8.459854295477271} +{"Pretrain/Learning Rate": 4.692808775194745e-05, "Pretrain/Loss": 2.0623559951782227, "Pretrain/Loss (Raw)": 1.8278143405914307, "Pretrain/Step": 1761, "Pretrain/Step Time": 8.458327542990446} +{"Pretrain/Learning Rate": 4.692400865868874e-05, "Pretrain/Loss": 2.0624184608459473, "Pretrain/Loss (Raw)": 2.1379363536834717, "Pretrain/Step": 1762, "Pretrain/Step Time": 8.457538679242134} +{"Pretrain/Learning Rate": 4.691992703650335e-05, "Pretrain/Loss": 2.0639688968658447, "Pretrain/Loss (Raw)": 2.1685373783111572, "Pretrain/Step": 1763, "Pretrain/Step Time": 8.453198086470366} +{"Pretrain/Learning Rate": 4.691584288586207e-05, "Pretrain/Loss": 2.0631582736968994, "Pretrain/Loss (Raw)": 2.1336007118225098, "Pretrain/Step": 1764, "Pretrain/Step Time": 8.453832248225808} +{"Pretrain/Learning Rate": 4.691175620723602e-05, "Pretrain/Loss": 2.064791679382324, "Pretrain/Loss (Raw)": 1.9071120023727417, "Pretrain/Step": 1765, "Pretrain/Step Time": 8.453350512310863} +{"Pretrain/Learning Rate": 4.690766700109659e-05, "Pretrain/Loss": 2.065380573272705, "Pretrain/Loss (Raw)": 2.152508020401001, "Pretrain/Step": 1766, "Pretrain/Step Time": 8.453680174425244} +{"Pretrain/Learning Rate": 4.690357526791547e-05, "Pretrain/Loss": 2.0644264221191406, "Pretrain/Loss (Raw)": 2.022052526473999, "Pretrain/Step": 1767, "Pretrain/Step Time": 8.454658625647426} +{"Pretrain/Learning Rate": 4.689948100816465e-05, "Pretrain/Loss": 2.0634329319000244, "Pretrain/Loss (Raw)": 1.9586520195007324, "Pretrain/Step": 1768, "Pretrain/Step Time": 8.455685518682003} +{"Pretrain/Learning Rate": 4.6895384222316375e-05, "Pretrain/Loss": 2.0638480186462402, "Pretrain/Loss (Raw)": 2.1461374759674072, "Pretrain/Step": 1769, "Pretrain/Step Time": 8.458142396062613} +{"Pretrain/Learning Rate": 4.689128491084324e-05, "Pretrain/Loss": 2.0639562606811523, "Pretrain/Loss (Raw)": 2.0419821739196777, "Pretrain/Step": 1770, "Pretrain/Step Time": 8.457135777920485} +{"Pretrain/Learning Rate": 4.688718307421807e-05, "Pretrain/Loss": 2.064455986022949, "Pretrain/Loss (Raw)": 2.09505295753479, "Pretrain/Step": 1771, "Pretrain/Step Time": 8.459617612883449} +{"Pretrain/Learning Rate": 4.688307871291403e-05, "Pretrain/Loss": 2.0638198852539062, "Pretrain/Loss (Raw)": 1.9401179552078247, "Pretrain/Step": 1772, "Pretrain/Step Time": 8.457745872437954} +{"Pretrain/Learning Rate": 4.687897182740455e-05, "Pretrain/Loss": 2.0640697479248047, "Pretrain/Loss (Raw)": 1.9452754259109497, "Pretrain/Step": 1773, "Pretrain/Step Time": 8.460788782685995} +{"Pretrain/Learning Rate": 4.6874862418163364e-05, "Pretrain/Loss": 2.0637731552124023, "Pretrain/Loss (Raw)": 2.1452128887176514, "Pretrain/Step": 1774, "Pretrain/Step Time": 8.459801750257611} +{"Pretrain/Learning Rate": 4.687075048566448e-05, "Pretrain/Loss": 2.0639498233795166, "Pretrain/Loss (Raw)": 2.236706256866455, "Pretrain/Step": 1775, "Pretrain/Step Time": 8.462134674191475} +{"Pretrain/Learning Rate": 4.686663603038222e-05, "Pretrain/Loss": 2.064821481704712, "Pretrain/Loss (Raw)": 1.9998693466186523, "Pretrain/Step": 1776, "Pretrain/Step Time": 8.463588431477547} +{"Pretrain/Learning Rate": 4.6862519052791165e-05, "Pretrain/Loss": 2.0652389526367188, "Pretrain/Loss (Raw)": 2.046581268310547, "Pretrain/Step": 1777, "Pretrain/Step Time": 8.466430347412825} +{"Pretrain/Learning Rate": 4.685839955336623e-05, "Pretrain/Loss": 2.0671257972717285, "Pretrain/Loss (Raw)": 2.263091802597046, "Pretrain/Step": 1778, "Pretrain/Step Time": 8.460989646613598} +{"Pretrain/Learning Rate": 4.6854277532582584e-05, "Pretrain/Loss": 2.067255973815918, "Pretrain/Loss (Raw)": 2.063539743423462, "Pretrain/Step": 1779, "Pretrain/Step Time": 8.461795765906572} +{"Pretrain/Learning Rate": 4.6850152990915706e-05, "Pretrain/Loss": 2.0642285346984863, "Pretrain/Loss (Raw)": 1.7349891662597656, "Pretrain/Step": 1780, "Pretrain/Step Time": 8.460068797692657} +{"Pretrain/Learning Rate": 4.684602592884136e-05, "Pretrain/Loss": 2.065621852874756, "Pretrain/Loss (Raw)": 2.1244122982025146, "Pretrain/Step": 1781, "Pretrain/Step Time": 8.461393451318145} +{"Pretrain/Learning Rate": 4.68418963468356e-05, "Pretrain/Loss": 2.065854072570801, "Pretrain/Loss (Raw)": 2.114969253540039, "Pretrain/Step": 1782, "Pretrain/Step Time": 8.462239088490605} +{"Pretrain/Learning Rate": 4.6837764245374774e-05, "Pretrain/Loss": 2.0658187866210938, "Pretrain/Loss (Raw)": 2.055898904800415, "Pretrain/Step": 1783, "Pretrain/Step Time": 8.464353447780013} +{"Pretrain/Learning Rate": 4.683362962493552e-05, "Pretrain/Loss": 2.066547155380249, "Pretrain/Loss (Raw)": 2.014636993408203, "Pretrain/Step": 1784, "Pretrain/Step Time": 8.462975680828094} +{"Pretrain/Learning Rate": 4.6829492485994756e-05, "Pretrain/Loss": 2.066679000854492, "Pretrain/Loss (Raw)": 2.084791898727417, "Pretrain/Step": 1785, "Pretrain/Step Time": 8.464086890220642} +{"Pretrain/Learning Rate": 4.6825352829029705e-05, "Pretrain/Loss": 2.064208507537842, "Pretrain/Loss (Raw)": 1.8469676971435547, "Pretrain/Step": 1786, "Pretrain/Step Time": 8.46219078078866} +{"Pretrain/Learning Rate": 4.6821210654517875e-05, "Pretrain/Loss": 2.063267469406128, "Pretrain/Loss (Raw)": 2.0234124660491943, "Pretrain/Step": 1787, "Pretrain/Step Time": 8.464402455836535} +{"Pretrain/Learning Rate": 4.681706596293707e-05, "Pretrain/Loss": 2.0610504150390625, "Pretrain/Loss (Raw)": 1.894458532333374, "Pretrain/Step": 1788, "Pretrain/Step Time": 8.464360430836678} +{"Pretrain/Learning Rate": 4.681291875476537e-05, "Pretrain/Loss": 2.0620954036712646, "Pretrain/Loss (Raw)": 2.1306350231170654, "Pretrain/Step": 1789, "Pretrain/Step Time": 8.464323598891497} +{"Pretrain/Learning Rate": 4.680876903048115e-05, "Pretrain/Loss": 2.062438488006592, "Pretrain/Loss (Raw)": 2.135204315185547, "Pretrain/Step": 1790, "Pretrain/Step Time": 8.469470132142305} +{"Pretrain/Learning Rate": 4.6804616790563097e-05, "Pretrain/Loss": 2.0638058185577393, "Pretrain/Loss (Raw)": 2.0505757331848145, "Pretrain/Step": 1791, "Pretrain/Step Time": 8.465269541367888} +{"Pretrain/Learning Rate": 4.6800462035490155e-05, "Pretrain/Loss": 2.0636768341064453, "Pretrain/Loss (Raw)": 2.0303492546081543, "Pretrain/Step": 1792, "Pretrain/Step Time": 8.468677274882793} +{"Pretrain/Learning Rate": 4.6796304765741585e-05, "Pretrain/Loss": 2.062892436981201, "Pretrain/Loss (Raw)": 1.983607292175293, "Pretrain/Step": 1793, "Pretrain/Step Time": 8.470046585425735} +{"Pretrain/Learning Rate": 4.679214498179691e-05, "Pretrain/Loss": 2.0629916191101074, "Pretrain/Loss (Raw)": 1.9882217645645142, "Pretrain/Step": 1794, "Pretrain/Step Time": 8.470366530120373} +{"Pretrain/Learning Rate": 4.678798268413597e-05, "Pretrain/Loss": 2.0618035793304443, "Pretrain/Loss (Raw)": 2.0077168941497803, "Pretrain/Step": 1795, "Pretrain/Step Time": 8.471018658950925} +{"Pretrain/Learning Rate": 4.678381787323889e-05, "Pretrain/Loss": 2.0582592487335205, "Pretrain/Loss (Raw)": 1.673262357711792, "Pretrain/Step": 1796, "Pretrain/Step Time": 8.470751710236073} +{"Pretrain/Learning Rate": 4.677965054958607e-05, "Pretrain/Loss": 2.0592284202575684, "Pretrain/Loss (Raw)": 2.1260411739349365, "Pretrain/Step": 1797, "Pretrain/Step Time": 8.468650572001934} +{"Pretrain/Learning Rate": 4.6775480713658216e-05, "Pretrain/Loss": 2.0599451065063477, "Pretrain/Loss (Raw)": 2.1652865409851074, "Pretrain/Step": 1798, "Pretrain/Step Time": 8.468888349831104} +{"Pretrain/Learning Rate": 4.677130836593632e-05, "Pretrain/Loss": 2.060030937194824, "Pretrain/Loss (Raw)": 2.16664981842041, "Pretrain/Step": 1799, "Pretrain/Step Time": 8.468557007610798} +{"Pretrain/Learning Rate": 4.676713350690164e-05, "Pretrain/Loss": 2.0592195987701416, "Pretrain/Loss (Raw)": 1.945575475692749, "Pretrain/Step": 1800, "Pretrain/Step Time": 8.472320955246687} +{"Pretrain/Learning Rate": 4.6762956137035774e-05, "Pretrain/Loss": 2.0593552589416504, "Pretrain/Loss (Raw)": 1.923178791999817, "Pretrain/Step": 1801, "Pretrain/Step Time": 8.475431820377707} +{"Pretrain/Learning Rate": 4.675877625682055e-05, "Pretrain/Loss": 2.0615487098693848, "Pretrain/Loss (Raw)": 2.2219765186309814, "Pretrain/Step": 1802, "Pretrain/Step Time": 8.47276015020907} +{"Pretrain/Learning Rate": 4.675459386673815e-05, "Pretrain/Loss": 2.061614513397217, "Pretrain/Loss (Raw)": 2.0248615741729736, "Pretrain/Step": 1803, "Pretrain/Step Time": 8.46896630898118} +{"Pretrain/Learning Rate": 4.6750408967270976e-05, "Pretrain/Loss": 2.0617759227752686, "Pretrain/Loss (Raw)": 2.157127857208252, "Pretrain/Step": 1804, "Pretrain/Step Time": 8.46867235377431} +{"Pretrain/Learning Rate": 4.674622155890178e-05, "Pretrain/Loss": 2.0608973503112793, "Pretrain/Loss (Raw)": 2.0964114665985107, "Pretrain/Step": 1805, "Pretrain/Step Time": 8.471309781074524} +{"Pretrain/Learning Rate": 4.674203164211357e-05, "Pretrain/Loss": 2.0605602264404297, "Pretrain/Loss (Raw)": 2.100834608078003, "Pretrain/Step": 1806, "Pretrain/Step Time": 8.4685403611511} +{"Pretrain/Learning Rate": 4.673783921738964e-05, "Pretrain/Loss": 2.0600876808166504, "Pretrain/Loss (Raw)": 1.9238064289093018, "Pretrain/Step": 1807, "Pretrain/Step Time": 8.469508077949286} +{"Pretrain/Learning Rate": 4.673364428521361e-05, "Pretrain/Loss": 2.063687801361084, "Pretrain/Loss (Raw)": 2.3020310401916504, "Pretrain/Step": 1808, "Pretrain/Step Time": 8.470103520900011} +{"Pretrain/Learning Rate": 4.672944684606934e-05, "Pretrain/Loss": 2.0635290145874023, "Pretrain/Loss (Raw)": 2.10186505317688, "Pretrain/Step": 1809, "Pretrain/Step Time": 8.47094625607133} +{"Pretrain/Learning Rate": 4.672524690044102e-05, "Pretrain/Loss": 2.0645194053649902, "Pretrain/Loss (Raw)": 2.1542258262634277, "Pretrain/Step": 1810, "Pretrain/Step Time": 8.470686184242368} +{"Pretrain/Learning Rate": 4.67210444488131e-05, "Pretrain/Loss": 2.0646562576293945, "Pretrain/Loss (Raw)": 2.1889615058898926, "Pretrain/Step": 1811, "Pretrain/Step Time": 8.471912454813719} +{"Pretrain/Learning Rate": 4.671683949167034e-05, "Pretrain/Loss": 2.06510591506958, "Pretrain/Loss (Raw)": 2.0561115741729736, "Pretrain/Step": 1812, "Pretrain/Step Time": 8.473512692376971} +{"Pretrain/Learning Rate": 4.6712632029497765e-05, "Pretrain/Loss": 2.0643904209136963, "Pretrain/Loss (Raw)": 1.9424806833267212, "Pretrain/Step": 1813, "Pretrain/Step Time": 8.472690055146813} +{"Pretrain/Learning Rate": 4.670842206278073e-05, "Pretrain/Loss": 2.064276933670044, "Pretrain/Loss (Raw)": 2.026987314224243, "Pretrain/Step": 1814, "Pretrain/Step Time": 8.472845494747162} +{"Pretrain/Learning Rate": 4.6704209592004836e-05, "Pretrain/Loss": 2.0645604133605957, "Pretrain/Loss (Raw)": 2.194927453994751, "Pretrain/Step": 1815, "Pretrain/Step Time": 8.472242332994938} +{"Pretrain/Learning Rate": 4.6699994617655985e-05, "Pretrain/Loss": 2.065084457397461, "Pretrain/Loss (Raw)": 2.139827251434326, "Pretrain/Step": 1816, "Pretrain/Step Time": 8.474751569330692} +{"Pretrain/Learning Rate": 4.669577714022039e-05, "Pretrain/Loss": 2.063652515411377, "Pretrain/Loss (Raw)": 1.8697715997695923, "Pretrain/Step": 1817, "Pretrain/Step Time": 8.482518984004855} +{"Pretrain/Learning Rate": 4.6691557160184516e-05, "Pretrain/Loss": 2.0622334480285645, "Pretrain/Loss (Raw)": 1.9432127475738525, "Pretrain/Step": 1818, "Pretrain/Step Time": 8.482447477057576} +{"Pretrain/Learning Rate": 4.668733467803515e-05, "Pretrain/Loss": 2.0610265731811523, "Pretrain/Loss (Raw)": 2.0527243614196777, "Pretrain/Step": 1819, "Pretrain/Step Time": 8.484194932505488} +{"Pretrain/Learning Rate": 4.668310969425935e-05, "Pretrain/Loss": 2.062107801437378, "Pretrain/Loss (Raw)": 2.0577852725982666, "Pretrain/Step": 1820, "Pretrain/Step Time": 8.485921064391732} +{"Pretrain/Learning Rate": 4.667888220934448e-05, "Pretrain/Loss": 2.061750650405884, "Pretrain/Loss (Raw)": 1.8905476331710815, "Pretrain/Step": 1821, "Pretrain/Step Time": 8.486477272585034} +{"Pretrain/Learning Rate": 4.667465222377815e-05, "Pretrain/Loss": 2.061378002166748, "Pretrain/Loss (Raw)": 2.061397075653076, "Pretrain/Step": 1822, "Pretrain/Step Time": 8.485288988798857} +{"Pretrain/Learning Rate": 4.667041973804831e-05, "Pretrain/Loss": 2.062345266342163, "Pretrain/Loss (Raw)": 2.1219987869262695, "Pretrain/Step": 1823, "Pretrain/Step Time": 8.481216687709093} +{"Pretrain/Learning Rate": 4.666618475264316e-05, "Pretrain/Loss": 2.0618724822998047, "Pretrain/Loss (Raw)": 2.0895862579345703, "Pretrain/Step": 1824, "Pretrain/Step Time": 8.481017582118511} +{"Pretrain/Learning Rate": 4.666194726805122e-05, "Pretrain/Loss": 2.060865879058838, "Pretrain/Loss (Raw)": 1.9476168155670166, "Pretrain/Step": 1825, "Pretrain/Step Time": 8.481294045224786} +{"Pretrain/Learning Rate": 4.6657707284761274e-05, "Pretrain/Loss": 2.062262773513794, "Pretrain/Loss (Raw)": 2.0316121578216553, "Pretrain/Step": 1826, "Pretrain/Step Time": 8.483858423307538} +{"Pretrain/Learning Rate": 4.665346480326241e-05, "Pretrain/Loss": 2.061769485473633, "Pretrain/Loss (Raw)": 1.8635940551757812, "Pretrain/Step": 1827, "Pretrain/Step Time": 8.482342727482319} +{"Pretrain/Learning Rate": 4.664921982404399e-05, "Pretrain/Loss": 2.0600414276123047, "Pretrain/Loss (Raw)": 1.897034764289856, "Pretrain/Step": 1828, "Pretrain/Step Time": 8.485761191695929} +{"Pretrain/Learning Rate": 4.664497234759566e-05, "Pretrain/Loss": 2.0584545135498047, "Pretrain/Loss (Raw)": 1.9896255731582642, "Pretrain/Step": 1829, "Pretrain/Step Time": 8.484738856554031} +{"Pretrain/Learning Rate": 4.664072237440739e-05, "Pretrain/Loss": 2.0602097511291504, "Pretrain/Loss (Raw)": 2.1275174617767334, "Pretrain/Step": 1830, "Pretrain/Step Time": 8.484033258631825} +{"Pretrain/Learning Rate": 4.6636469904969386e-05, "Pretrain/Loss": 2.0603668689727783, "Pretrain/Loss (Raw)": 2.168919563293457, "Pretrain/Step": 1831, "Pretrain/Step Time": 8.482038140296936} +{"Pretrain/Learning Rate": 4.663221493977219e-05, "Pretrain/Loss": 2.0618600845336914, "Pretrain/Loss (Raw)": 2.1409480571746826, "Pretrain/Step": 1832, "Pretrain/Step Time": 8.484377078711987} +{"Pretrain/Learning Rate": 4.66279574793066e-05, "Pretrain/Loss": 2.0615453720092773, "Pretrain/Loss (Raw)": 1.944999098777771, "Pretrain/Step": 1833, "Pretrain/Step Time": 8.482683027163148} +{"Pretrain/Learning Rate": 4.6623697524063713e-05, "Pretrain/Loss": 2.061495304107666, "Pretrain/Loss (Raw)": 1.9695608615875244, "Pretrain/Step": 1834, "Pretrain/Step Time": 8.483725801110268} +{"Pretrain/Learning Rate": 4.661943507453492e-05, "Pretrain/Loss": 2.061901569366455, "Pretrain/Loss (Raw)": 2.1097795963287354, "Pretrain/Step": 1835, "Pretrain/Step Time": 8.488885832950473} +{"Pretrain/Learning Rate": 4.661517013121189e-05, "Pretrain/Loss": 2.0618185997009277, "Pretrain/Loss (Raw)": 2.176823377609253, "Pretrain/Step": 1836, "Pretrain/Step Time": 8.490695092827082} +{"Pretrain/Learning Rate": 4.6610902694586576e-05, "Pretrain/Loss": 2.0623977184295654, "Pretrain/Loss (Raw)": 2.1462442874908447, "Pretrain/Step": 1837, "Pretrain/Step Time": 8.490967577323318} +{"Pretrain/Learning Rate": 4.660663276515124e-05, "Pretrain/Loss": 2.061654567718506, "Pretrain/Loss (Raw)": 2.0242621898651123, "Pretrain/Step": 1838, "Pretrain/Step Time": 8.486552964895964} +{"Pretrain/Learning Rate": 4.66023603433984e-05, "Pretrain/Loss": 2.058668851852417, "Pretrain/Loss (Raw)": 1.819558024406433, "Pretrain/Step": 1839, "Pretrain/Step Time": 8.48763981461525} +{"Pretrain/Learning Rate": 4.659808542982088e-05, "Pretrain/Loss": 2.0571646690368652, "Pretrain/Loss (Raw)": 1.9938563108444214, "Pretrain/Step": 1840, "Pretrain/Step Time": 8.485349420458078} +{"Pretrain/Learning Rate": 4.659380802491181e-05, "Pretrain/Loss": 2.058525562286377, "Pretrain/Loss (Raw)": 2.222322463989258, "Pretrain/Step": 1841, "Pretrain/Step Time": 8.489622449502349} +{"Pretrain/Learning Rate": 4.6589528129164564e-05, "Pretrain/Loss": 2.0570943355560303, "Pretrain/Loss (Raw)": 1.9686176776885986, "Pretrain/Step": 1842, "Pretrain/Step Time": 8.488414773717523} +{"Pretrain/Learning Rate": 4.658524574307284e-05, "Pretrain/Loss": 2.058281660079956, "Pretrain/Loss (Raw)": 2.193032741546631, "Pretrain/Step": 1843, "Pretrain/Step Time": 8.487864177674055} +{"Pretrain/Learning Rate": 4.6580960867130604e-05, "Pretrain/Loss": 2.055678367614746, "Pretrain/Loss (Raw)": 2.025059223175049, "Pretrain/Step": 1844, "Pretrain/Step Time": 8.488647917285562} +{"Pretrain/Learning Rate": 4.6576673501832114e-05, "Pretrain/Loss": 2.0537004470825195, "Pretrain/Loss (Raw)": 1.893271803855896, "Pretrain/Step": 1845, "Pretrain/Step Time": 8.487513242289424} +{"Pretrain/Learning Rate": 4.6572383647671913e-05, "Pretrain/Loss": 2.0545265674591064, "Pretrain/Loss (Raw)": 2.060394763946533, "Pretrain/Step": 1846, "Pretrain/Step Time": 8.482438942417502} +{"Pretrain/Learning Rate": 4.6568091305144853e-05, "Pretrain/Loss": 2.0544357299804688, "Pretrain/Loss (Raw)": 2.0564124584198, "Pretrain/Step": 1847, "Pretrain/Step Time": 8.484702138230205} +{"Pretrain/Learning Rate": 4.656379647474603e-05, "Pretrain/Loss": 2.0550668239593506, "Pretrain/Loss (Raw)": 2.1029646396636963, "Pretrain/Step": 1848, "Pretrain/Step Time": 8.485150337219238} +{"Pretrain/Learning Rate": 4.655949915697086e-05, "Pretrain/Loss": 2.055055618286133, "Pretrain/Loss (Raw)": 2.0320382118225098, "Pretrain/Step": 1849, "Pretrain/Step Time": 8.489133961498737} +{"Pretrain/Learning Rate": 4.655519935231505e-05, "Pretrain/Loss": 2.055896282196045, "Pretrain/Loss (Raw)": 2.1170620918273926, "Pretrain/Step": 1850, "Pretrain/Step Time": 8.487243175506592} +{"Pretrain/Learning Rate": 4.655089706127456e-05, "Pretrain/Loss": 2.0566959381103516, "Pretrain/Loss (Raw)": 2.0610599517822266, "Pretrain/Step": 1851, "Pretrain/Step Time": 8.49014263600111} +{"Pretrain/Learning Rate": 4.654659228434567e-05, "Pretrain/Loss": 2.0559370517730713, "Pretrain/Loss (Raw)": 2.1691086292266846, "Pretrain/Step": 1852, "Pretrain/Step Time": 8.487738851457834} +{"Pretrain/Learning Rate": 4.654228502202493e-05, "Pretrain/Loss": 2.055952548980713, "Pretrain/Loss (Raw)": 2.2685530185699463, "Pretrain/Step": 1853, "Pretrain/Step Time": 8.489021366462111} +{"Pretrain/Learning Rate": 4.6537975274809186e-05, "Pretrain/Loss": 2.055907726287842, "Pretrain/Loss (Raw)": 2.151256561279297, "Pretrain/Step": 1854, "Pretrain/Step Time": 8.486480752006173} +{"Pretrain/Learning Rate": 4.653366304319556e-05, "Pretrain/Loss": 2.056166172027588, "Pretrain/Loss (Raw)": 2.0872862339019775, "Pretrain/Step": 1855, "Pretrain/Step Time": 8.481325218454003} +{"Pretrain/Learning Rate": 4.652934832768148e-05, "Pretrain/Loss": 2.055753231048584, "Pretrain/Loss (Raw)": 1.9770251512527466, "Pretrain/Step": 1856, "Pretrain/Step Time": 8.484584860503674} +{"Pretrain/Learning Rate": 4.652503112876463e-05, "Pretrain/Loss": 2.0561180114746094, "Pretrain/Loss (Raw)": 2.133685827255249, "Pretrain/Step": 1857, "Pretrain/Step Time": 8.484256057068706} +{"Pretrain/Learning Rate": 4.6520711446943e-05, "Pretrain/Loss": 2.0552709102630615, "Pretrain/Loss (Raw)": 2.054872512817383, "Pretrain/Step": 1858, "Pretrain/Step Time": 8.486427664756775} +{"Pretrain/Learning Rate": 4.651638928271487e-05, "Pretrain/Loss": 2.0551071166992188, "Pretrain/Loss (Raw)": 2.0986671447753906, "Pretrain/Step": 1859, "Pretrain/Step Time": 8.487298352643847} +{"Pretrain/Learning Rate": 4.65120646365788e-05, "Pretrain/Loss": 2.054353713989258, "Pretrain/Loss (Raw)": 2.034929037094116, "Pretrain/Step": 1860, "Pretrain/Step Time": 8.488267546519637} +{"Pretrain/Learning Rate": 4.650773750903363e-05, "Pretrain/Loss": 2.0534627437591553, "Pretrain/Loss (Raw)": 2.0391042232513428, "Pretrain/Step": 1861, "Pretrain/Step Time": 8.486650001257658} +{"Pretrain/Learning Rate": 4.65034079005785e-05, "Pretrain/Loss": 2.054576873779297, "Pretrain/Loss (Raw)": 1.9118719100952148, "Pretrain/Step": 1862, "Pretrain/Step Time": 8.484025767073035} +{"Pretrain/Learning Rate": 4.649907581171282e-05, "Pretrain/Loss": 2.054055690765381, "Pretrain/Loss (Raw)": 2.0899388790130615, "Pretrain/Step": 1863, "Pretrain/Step Time": 8.48071451857686} +{"Pretrain/Learning Rate": 4.64947412429363e-05, "Pretrain/Loss": 2.053284168243408, "Pretrain/Loss (Raw)": 1.9672490358352661, "Pretrain/Step": 1864, "Pretrain/Step Time": 8.479453597217798} +{"Pretrain/Learning Rate": 4.6490404194748937e-05, "Pretrain/Loss": 2.053173303604126, "Pretrain/Loss (Raw)": 1.961972951889038, "Pretrain/Step": 1865, "Pretrain/Step Time": 8.478413766250014} +{"Pretrain/Learning Rate": 4.6486064667651003e-05, "Pretrain/Loss": 2.0543596744537354, "Pretrain/Loss (Raw)": 2.078263998031616, "Pretrain/Step": 1866, "Pretrain/Step Time": 8.478200867772102} +{"Pretrain/Learning Rate": 4.6481722662143056e-05, "Pretrain/Loss": 2.0542044639587402, "Pretrain/Loss (Raw)": 2.1223931312561035, "Pretrain/Step": 1867, "Pretrain/Step Time": 8.477774338796735} +{"Pretrain/Learning Rate": 4.6477378178725954e-05, "Pretrain/Loss": 2.053175926208496, "Pretrain/Loss (Raw)": 1.9815037250518799, "Pretrain/Step": 1868, "Pretrain/Step Time": 8.481102462857962} +{"Pretrain/Learning Rate": 4.647303121790082e-05, "Pretrain/Loss": 2.052320957183838, "Pretrain/Loss (Raw)": 2.0353925228118896, "Pretrain/Step": 1869, "Pretrain/Step Time": 8.479691995307803} +{"Pretrain/Learning Rate": 4.646868178016909e-05, "Pretrain/Loss": 2.051142692565918, "Pretrain/Loss (Raw)": 2.065237522125244, "Pretrain/Step": 1870, "Pretrain/Step Time": 8.483604945242405} +{"Pretrain/Learning Rate": 4.646432986603245e-05, "Pretrain/Loss": 2.050617218017578, "Pretrain/Loss (Raw)": 2.05995774269104, "Pretrain/Step": 1871, "Pretrain/Step Time": 8.481032382696867} +{"Pretrain/Learning Rate": 4.645997547599292e-05, "Pretrain/Loss": 2.050088882446289, "Pretrain/Loss (Raw)": 2.004106283187866, "Pretrain/Step": 1872, "Pretrain/Step Time": 8.480623550713062} +{"Pretrain/Learning Rate": 4.6455618610552745e-05, "Pretrain/Loss": 2.0501887798309326, "Pretrain/Loss (Raw)": 2.0641062259674072, "Pretrain/Step": 1873, "Pretrain/Step Time": 8.482565419748425} +{"Pretrain/Learning Rate": 4.645125927021451e-05, "Pretrain/Loss": 2.048703670501709, "Pretrain/Loss (Raw)": 1.9207704067230225, "Pretrain/Step": 1874, "Pretrain/Step Time": 8.481308151036501} +{"Pretrain/Learning Rate": 4.6446897455481053e-05, "Pretrain/Loss": 2.0499095916748047, "Pretrain/Loss (Raw)": 2.134755849838257, "Pretrain/Step": 1875, "Pretrain/Step Time": 8.483727587386966} +{"Pretrain/Learning Rate": 4.6442533166855514e-05, "Pretrain/Loss": 2.051453113555908, "Pretrain/Loss (Raw)": 2.240800380706787, "Pretrain/Step": 1876, "Pretrain/Step Time": 8.487765209749341} +{"Pretrain/Learning Rate": 4.643816640484131e-05, "Pretrain/Loss": 2.0507030487060547, "Pretrain/Loss (Raw)": 2.104813814163208, "Pretrain/Step": 1877, "Pretrain/Step Time": 8.49035083502531} +{"Pretrain/Learning Rate": 4.643379716994214e-05, "Pretrain/Loss": 2.0501515865325928, "Pretrain/Loss (Raw)": 2.058912992477417, "Pretrain/Step": 1878, "Pretrain/Step Time": 8.48926997371018} +{"Pretrain/Learning Rate": 4.6429425462662e-05, "Pretrain/Loss": 2.0511271953582764, "Pretrain/Loss (Raw)": 2.144747018814087, "Pretrain/Step": 1879, "Pretrain/Step Time": 8.490248147398233} +{"Pretrain/Learning Rate": 4.642505128350517e-05, "Pretrain/Loss": 2.051595687866211, "Pretrain/Loss (Raw)": 1.9840461015701294, "Pretrain/Step": 1880, "Pretrain/Step Time": 8.487265300005674} +{"Pretrain/Learning Rate": 4.6420674632976205e-05, "Pretrain/Loss": 2.052927017211914, "Pretrain/Loss (Raw)": 2.1231698989868164, "Pretrain/Step": 1881, "Pretrain/Step Time": 8.485103463754058} +{"Pretrain/Learning Rate": 4.6416295511579946e-05, "Pretrain/Loss": 2.0530190467834473, "Pretrain/Loss (Raw)": 2.0186030864715576, "Pretrain/Step": 1882, "Pretrain/Step Time": 8.48874725587666} +{"Pretrain/Learning Rate": 4.641191391982152e-05, "Pretrain/Loss": 2.0531888008117676, "Pretrain/Loss (Raw)": 2.0878236293792725, "Pretrain/Step": 1883, "Pretrain/Step Time": 8.484092995524406} +{"Pretrain/Learning Rate": 4.6407529858206354e-05, "Pretrain/Loss": 2.0529184341430664, "Pretrain/Loss (Raw)": 2.120746374130249, "Pretrain/Step": 1884, "Pretrain/Step Time": 8.487226087599993} +{"Pretrain/Learning Rate": 4.640314332724014e-05, "Pretrain/Loss": 2.0520434379577637, "Pretrain/Loss (Raw)": 1.9696757793426514, "Pretrain/Step": 1885, "Pretrain/Step Time": 8.489719279110432} +{"Pretrain/Learning Rate": 4.639875432742886e-05, "Pretrain/Loss": 2.0506584644317627, "Pretrain/Loss (Raw)": 1.951759934425354, "Pretrain/Step": 1886, "Pretrain/Step Time": 8.492746662348509} +{"Pretrain/Learning Rate": 4.6394362859278794e-05, "Pretrain/Loss": 2.0518245697021484, "Pretrain/Loss (Raw)": 2.0832560062408447, "Pretrain/Step": 1887, "Pretrain/Step Time": 8.491558393463492} +{"Pretrain/Learning Rate": 4.6389968923296494e-05, "Pretrain/Loss": 2.0517807006835938, "Pretrain/Loss (Raw)": 2.0713160037994385, "Pretrain/Step": 1888, "Pretrain/Step Time": 8.487365804612637} +{"Pretrain/Learning Rate": 4.63855725199888e-05, "Pretrain/Loss": 2.0540804862976074, "Pretrain/Loss (Raw)": 2.122166633605957, "Pretrain/Step": 1889, "Pretrain/Step Time": 8.488263506442308} +{"Pretrain/Learning Rate": 4.638117364986282e-05, "Pretrain/Loss": 2.0526609420776367, "Pretrain/Loss (Raw)": 1.9562571048736572, "Pretrain/Step": 1890, "Pretrain/Step Time": 8.491410905495286} +{"Pretrain/Learning Rate": 4.637677231342598e-05, "Pretrain/Loss": 2.050788402557373, "Pretrain/Loss (Raw)": 1.9288203716278076, "Pretrain/Step": 1891, "Pretrain/Step Time": 8.493977466598153} +{"Pretrain/Learning Rate": 4.637236851118595e-05, "Pretrain/Loss": 2.050525665283203, "Pretrain/Loss (Raw)": 2.0999677181243896, "Pretrain/Step": 1892, "Pretrain/Step Time": 8.493300193920732} +{"Pretrain/Learning Rate": 4.6367962243650745e-05, "Pretrain/Loss": 2.051339626312256, "Pretrain/Loss (Raw)": 2.0112967491149902, "Pretrain/Step": 1893, "Pretrain/Step Time": 8.49421875551343} +{"Pretrain/Learning Rate": 4.636355351132859e-05, "Pretrain/Loss": 2.0510759353637695, "Pretrain/Loss (Raw)": 2.118753433227539, "Pretrain/Step": 1894, "Pretrain/Step Time": 8.492996029555798} +{"Pretrain/Learning Rate": 4.635914231472805e-05, "Pretrain/Loss": 2.0521950721740723, "Pretrain/Loss (Raw)": 2.16532301902771, "Pretrain/Step": 1895, "Pretrain/Step Time": 8.490918492898345} +{"Pretrain/Learning Rate": 4.635472865435795e-05, "Pretrain/Loss": 2.050729274749756, "Pretrain/Loss (Raw)": 1.7710459232330322, "Pretrain/Step": 1896, "Pretrain/Step Time": 8.493432246148586} +{"Pretrain/Learning Rate": 4.63503125307274e-05, "Pretrain/Loss": 2.049665689468384, "Pretrain/Loss (Raw)": 2.009983539581299, "Pretrain/Step": 1897, "Pretrain/Step Time": 8.488738985732198} +{"Pretrain/Learning Rate": 4.634589394434581e-05, "Pretrain/Loss": 2.0504276752471924, "Pretrain/Loss (Raw)": 2.1395070552825928, "Pretrain/Step": 1898, "Pretrain/Step Time": 8.491053741425276} +{"Pretrain/Learning Rate": 4.6341472895722854e-05, "Pretrain/Loss": 2.0506739616394043, "Pretrain/Loss (Raw)": 2.1265997886657715, "Pretrain/Step": 1899, "Pretrain/Step Time": 8.492763413116336} +{"Pretrain/Learning Rate": 4.6337049385368496e-05, "Pretrain/Loss": 2.0517799854278564, "Pretrain/Loss (Raw)": 2.0816686153411865, "Pretrain/Step": 1900, "Pretrain/Step Time": 8.49386478960514} +{"Pretrain/Learning Rate": 4.633262341379299e-05, "Pretrain/Loss": 2.0529773235321045, "Pretrain/Loss (Raw)": 2.098548173904419, "Pretrain/Step": 1901, "Pretrain/Step Time": 8.493949232622981} +{"Pretrain/Learning Rate": 4.632819498150688e-05, "Pretrain/Loss": 2.052859306335449, "Pretrain/Loss (Raw)": 2.130098342895508, "Pretrain/Step": 1902, "Pretrain/Step Time": 8.4918870087713} +{"Pretrain/Learning Rate": 4.632376408902096e-05, "Pretrain/Loss": 2.051079750061035, "Pretrain/Loss (Raw)": 2.0089170932769775, "Pretrain/Step": 1903, "Pretrain/Step Time": 8.48857057467103} +{"Pretrain/Learning Rate": 4.631933073684635e-05, "Pretrain/Loss": 2.051405429840088, "Pretrain/Loss (Raw)": 2.041583299636841, "Pretrain/Step": 1904, "Pretrain/Step Time": 8.488326780498028} +{"Pretrain/Learning Rate": 4.631489492549443e-05, "Pretrain/Loss": 2.0515432357788086, "Pretrain/Loss (Raw)": 2.0641849040985107, "Pretrain/Step": 1905, "Pretrain/Step Time": 8.48571852967143} +{"Pretrain/Learning Rate": 4.6310456655476876e-05, "Pretrain/Loss": 2.0489373207092285, "Pretrain/Loss (Raw)": 1.9295568466186523, "Pretrain/Step": 1906, "Pretrain/Step Time": 8.489775162190199} +{"Pretrain/Learning Rate": 4.630601592730564e-05, "Pretrain/Loss": 2.0489449501037598, "Pretrain/Loss (Raw)": 2.0644941329956055, "Pretrain/Step": 1907, "Pretrain/Step Time": 8.491155488416553} +{"Pretrain/Learning Rate": 4.630157274149294e-05, "Pretrain/Loss": 2.0509862899780273, "Pretrain/Loss (Raw)": 1.9962888956069946, "Pretrain/Step": 1908, "Pretrain/Step Time": 8.491207472980022} +{"Pretrain/Learning Rate": 4.6297127098551316e-05, "Pretrain/Loss": 2.051697254180908, "Pretrain/Loss (Raw)": 2.2154226303100586, "Pretrain/Step": 1909, "Pretrain/Step Time": 8.489854609593749} +{"Pretrain/Learning Rate": 4.6292678998993576e-05, "Pretrain/Loss": 2.050722599029541, "Pretrain/Loss (Raw)": 1.9901889562606812, "Pretrain/Step": 1910, "Pretrain/Step Time": 8.492144392803311} +{"Pretrain/Learning Rate": 4.628822844333278e-05, "Pretrain/Loss": 2.0501835346221924, "Pretrain/Loss (Raw)": 1.9869204759597778, "Pretrain/Step": 1911, "Pretrain/Step Time": 8.489242358133197} +{"Pretrain/Learning Rate": 4.6283775432082325e-05, "Pretrain/Loss": 2.051133394241333, "Pretrain/Loss (Raw)": 2.1362459659576416, "Pretrain/Step": 1912, "Pretrain/Step Time": 8.488669879734516} +{"Pretrain/Learning Rate": 4.627931996575585e-05, "Pretrain/Loss": 2.0508193969726562, "Pretrain/Loss (Raw)": 2.0445613861083984, "Pretrain/Step": 1913, "Pretrain/Step Time": 8.488667437806726} +{"Pretrain/Learning Rate": 4.6274862044867304e-05, "Pretrain/Loss": 2.0532801151275635, "Pretrain/Loss (Raw)": 2.161956548690796, "Pretrain/Step": 1914, "Pretrain/Step Time": 8.48809626325965} +{"Pretrain/Learning Rate": 4.627040166993089e-05, "Pretrain/Loss": 2.0535969734191895, "Pretrain/Loss (Raw)": 2.0639798641204834, "Pretrain/Step": 1915, "Pretrain/Step Time": 8.485106967389584} +{"Pretrain/Learning Rate": 4.626593884146111e-05, "Pretrain/Loss": 2.054504156112671, "Pretrain/Loss (Raw)": 2.010561227798462, "Pretrain/Step": 1916, "Pretrain/Step Time": 8.487485965713859} +{"Pretrain/Learning Rate": 4.626147355997277e-05, "Pretrain/Loss": 2.0546107292175293, "Pretrain/Loss (Raw)": 2.144275665283203, "Pretrain/Step": 1917, "Pretrain/Step Time": 8.488120649009943} +{"Pretrain/Learning Rate": 4.625700582598092e-05, "Pretrain/Loss": 2.05397891998291, "Pretrain/Loss (Raw)": 2.0543246269226074, "Pretrain/Step": 1918, "Pretrain/Step Time": 8.483507612720132} +{"Pretrain/Learning Rate": 4.6252535640000924e-05, "Pretrain/Loss": 2.0546936988830566, "Pretrain/Loss (Raw)": 2.142102003097534, "Pretrain/Step": 1919, "Pretrain/Step Time": 8.482554130256176} +{"Pretrain/Learning Rate": 4.6248063002548404e-05, "Pretrain/Loss": 2.05582857131958, "Pretrain/Loss (Raw)": 2.1755881309509277, "Pretrain/Step": 1920, "Pretrain/Step Time": 8.48364701680839} +{"Pretrain/Learning Rate": 4.6243587914139285e-05, "Pretrain/Loss": 2.0550734996795654, "Pretrain/Loss (Raw)": 1.886960744857788, "Pretrain/Step": 1921, "Pretrain/Step Time": 8.482712982222438} +{"Pretrain/Learning Rate": 4.6239110375289775e-05, "Pretrain/Loss": 2.053969383239746, "Pretrain/Loss (Raw)": 1.8468996286392212, "Pretrain/Step": 1922, "Pretrain/Step Time": 8.482823858037591} +{"Pretrain/Learning Rate": 4.623463038651633e-05, "Pretrain/Loss": 2.053532600402832, "Pretrain/Loss (Raw)": 1.951799988746643, "Pretrain/Step": 1923, "Pretrain/Step Time": 8.48393546976149} +{"Pretrain/Learning Rate": 4.623014794833574e-05, "Pretrain/Loss": 2.057187557220459, "Pretrain/Loss (Raw)": 2.141092300415039, "Pretrain/Step": 1924, "Pretrain/Step Time": 8.484135398641229} +{"Pretrain/Learning Rate": 4.622566306126506e-05, "Pretrain/Loss": 2.0569822788238525, "Pretrain/Loss (Raw)": 2.0997703075408936, "Pretrain/Step": 1925, "Pretrain/Step Time": 8.485141733661294} +{"Pretrain/Learning Rate": 4.6221175725821586e-05, "Pretrain/Loss": 2.0547242164611816, "Pretrain/Loss (Raw)": 1.8762588500976562, "Pretrain/Step": 1926, "Pretrain/Step Time": 8.487416977062821} +{"Pretrain/Learning Rate": 4.6216685942522956e-05, "Pretrain/Loss": 2.0537710189819336, "Pretrain/Loss (Raw)": 2.044620990753174, "Pretrain/Step": 1927, "Pretrain/Step Time": 8.48749596066773} +{"Pretrain/Learning Rate": 4.621219371188706e-05, "Pretrain/Loss": 2.054145097732544, "Pretrain/Loss (Raw)": 1.993483543395996, "Pretrain/Step": 1928, "Pretrain/Step Time": 8.481347369030118} +{"Pretrain/Learning Rate": 4.620769903443207e-05, "Pretrain/Loss": 2.053278923034668, "Pretrain/Loss (Raw)": 1.8122731447219849, "Pretrain/Step": 1929, "Pretrain/Step Time": 8.480662995949388} +{"Pretrain/Learning Rate": 4.620320191067645e-05, "Pretrain/Loss": 2.052279472351074, "Pretrain/Loss (Raw)": 2.094059944152832, "Pretrain/Step": 1930, "Pretrain/Step Time": 8.479612274095416} +{"Pretrain/Learning Rate": 4.619870234113894e-05, "Pretrain/Loss": 2.0532822608947754, "Pretrain/Loss (Raw)": 2.153226137161255, "Pretrain/Step": 1931, "Pretrain/Step Time": 8.4812739379704} +{"Pretrain/Learning Rate": 4.619420032633857e-05, "Pretrain/Loss": 2.0535168647766113, "Pretrain/Loss (Raw)": 2.187147378921509, "Pretrain/Step": 1932, "Pretrain/Step Time": 8.480129463598132} +{"Pretrain/Learning Rate": 4.6189695866794635e-05, "Pretrain/Loss": 2.055737018585205, "Pretrain/Loss (Raw)": 2.3806025981903076, "Pretrain/Step": 1933, "Pretrain/Step Time": 8.47751946002245} +{"Pretrain/Learning Rate": 4.618518896302674e-05, "Pretrain/Loss": 2.0547704696655273, "Pretrain/Loss (Raw)": 1.9771180152893066, "Pretrain/Step": 1934, "Pretrain/Step Time": 8.480016563087702} +{"Pretrain/Learning Rate": 4.618067961555473e-05, "Pretrain/Loss": 2.0551819801330566, "Pretrain/Loss (Raw)": 1.976477026939392, "Pretrain/Step": 1935, "Pretrain/Step Time": 8.478700930252671} +{"Pretrain/Learning Rate": 4.6176167824898773e-05, "Pretrain/Loss": 2.0533242225646973, "Pretrain/Loss (Raw)": 2.064263343811035, "Pretrain/Step": 1936, "Pretrain/Step Time": 8.481556959450245} +{"Pretrain/Learning Rate": 4.61716535915793e-05, "Pretrain/Loss": 2.0524346828460693, "Pretrain/Loss (Raw)": 1.9879937171936035, "Pretrain/Step": 1937, "Pretrain/Step Time": 8.481824483722448} +{"Pretrain/Learning Rate": 4.616713691611703e-05, "Pretrain/Loss": 2.052183151245117, "Pretrain/Loss (Raw)": 2.1219985485076904, "Pretrain/Step": 1938, "Pretrain/Step Time": 8.478040523827076} +{"Pretrain/Learning Rate": 4.616261779903295e-05, "Pretrain/Loss": 2.050990581512451, "Pretrain/Loss (Raw)": 2.036323070526123, "Pretrain/Step": 1939, "Pretrain/Step Time": 8.479462096467614} +{"Pretrain/Learning Rate": 4.615809624084834e-05, "Pretrain/Loss": 2.051260232925415, "Pretrain/Loss (Raw)": 2.0906355381011963, "Pretrain/Step": 1940, "Pretrain/Step Time": 8.482866017147899} +{"Pretrain/Learning Rate": 4.6153572242084776e-05, "Pretrain/Loss": 2.0528347492218018, "Pretrain/Loss (Raw)": 2.1440134048461914, "Pretrain/Step": 1941, "Pretrain/Step Time": 8.482757296413183} +{"Pretrain/Learning Rate": 4.6149045803264076e-05, "Pretrain/Loss": 2.0536327362060547, "Pretrain/Loss (Raw)": 2.129150629043579, "Pretrain/Step": 1942, "Pretrain/Step Time": 8.482919374480844} +{"Pretrain/Learning Rate": 4.614451692490838e-05, "Pretrain/Loss": 2.0522103309631348, "Pretrain/Loss (Raw)": 2.0128471851348877, "Pretrain/Step": 1943, "Pretrain/Step Time": 8.485114699229598} +{"Pretrain/Learning Rate": 4.613998560754009e-05, "Pretrain/Loss": 2.0527162551879883, "Pretrain/Loss (Raw)": 2.204580068588257, "Pretrain/Step": 1944, "Pretrain/Step Time": 8.482008069753647} +{"Pretrain/Learning Rate": 4.613545185168188e-05, "Pretrain/Loss": 2.0544495582580566, "Pretrain/Loss (Raw)": 2.0916574001312256, "Pretrain/Step": 1945, "Pretrain/Step Time": 8.47751159220934} +{"Pretrain/Learning Rate": 4.6130915657856734e-05, "Pretrain/Loss": 2.05418062210083, "Pretrain/Loss (Raw)": 1.908758521080017, "Pretrain/Step": 1946, "Pretrain/Step Time": 8.475191289559007} +{"Pretrain/Learning Rate": 4.61263770265879e-05, "Pretrain/Loss": 2.053872585296631, "Pretrain/Loss (Raw)": 2.013296365737915, "Pretrain/Step": 1947, "Pretrain/Step Time": 8.477352252230048} +{"Pretrain/Learning Rate": 4.6121835958398886e-05, "Pretrain/Loss": 2.0532941818237305, "Pretrain/Loss (Raw)": 1.9837435483932495, "Pretrain/Step": 1948, "Pretrain/Step Time": 8.47790739312768} +{"Pretrain/Learning Rate": 4.611729245381352e-05, "Pretrain/Loss": 2.054774761199951, "Pretrain/Loss (Raw)": 2.0800724029541016, "Pretrain/Step": 1949, "Pretrain/Step Time": 8.475411711260676} +{"Pretrain/Learning Rate": 4.61127465133559e-05, "Pretrain/Loss": 2.0555834770202637, "Pretrain/Loss (Raw)": 2.164912223815918, "Pretrain/Step": 1950, "Pretrain/Step Time": 8.47565178759396} +{"Pretrain/Learning Rate": 4.610819813755038e-05, "Pretrain/Loss": 2.05418062210083, "Pretrain/Loss (Raw)": 1.9424309730529785, "Pretrain/Step": 1951, "Pretrain/Step Time": 8.48057740740478} +{"Pretrain/Learning Rate": 4.610364732692163e-05, "Pretrain/Loss": 2.053074836730957, "Pretrain/Loss (Raw)": 1.94803786277771, "Pretrain/Step": 1952, "Pretrain/Step Time": 8.480482606217265} +{"Pretrain/Learning Rate": 4.609909408199456e-05, "Pretrain/Loss": 2.0549826622009277, "Pretrain/Loss (Raw)": 2.1918442249298096, "Pretrain/Step": 1953, "Pretrain/Step Time": 8.480016896501184} +{"Pretrain/Learning Rate": 4.609453840329442e-05, "Pretrain/Loss": 2.0557665824890137, "Pretrain/Loss (Raw)": 2.1319468021392822, "Pretrain/Step": 1954, "Pretrain/Step Time": 8.478016441687942} +{"Pretrain/Learning Rate": 4.6089980291346685e-05, "Pretrain/Loss": 2.0564212799072266, "Pretrain/Loss (Raw)": 1.9474058151245117, "Pretrain/Step": 1955, "Pretrain/Step Time": 8.477715687826276} +{"Pretrain/Learning Rate": 4.608541974667714e-05, "Pretrain/Loss": 2.056373119354248, "Pretrain/Loss (Raw)": 1.8908298015594482, "Pretrain/Step": 1956, "Pretrain/Step Time": 8.478167243301868} +{"Pretrain/Learning Rate": 4.608085676981183e-05, "Pretrain/Loss": 2.056896448135376, "Pretrain/Loss (Raw)": 2.056640625, "Pretrain/Step": 1957, "Pretrain/Step Time": 8.480287548154593} +{"Pretrain/Learning Rate": 4.6076291361277096e-05, "Pretrain/Loss": 2.057227611541748, "Pretrain/Loss (Raw)": 2.1698920726776123, "Pretrain/Step": 1958, "Pretrain/Step Time": 8.478027133271098} +{"Pretrain/Learning Rate": 4.6071723521599566e-05, "Pretrain/Loss": 2.057797431945801, "Pretrain/Loss (Raw)": 2.2418694496154785, "Pretrain/Step": 1959, "Pretrain/Step Time": 8.47843743674457} +{"Pretrain/Learning Rate": 4.606715325130613e-05, "Pretrain/Loss": 2.0562472343444824, "Pretrain/Loss (Raw)": 1.9425067901611328, "Pretrain/Step": 1960, "Pretrain/Step Time": 8.476216960698366} +{"Pretrain/Learning Rate": 4.606258055092397e-05, "Pretrain/Loss": 2.05629825592041, "Pretrain/Loss (Raw)": 1.9515619277954102, "Pretrain/Step": 1961, "Pretrain/Step Time": 8.474441222846508} +{"Pretrain/Learning Rate": 4.6058005420980544e-05, "Pretrain/Loss": 2.056373357772827, "Pretrain/Loss (Raw)": 1.9791427850723267, "Pretrain/Step": 1962, "Pretrain/Step Time": 8.476094821467996} +{"Pretrain/Learning Rate": 4.605342786200359e-05, "Pretrain/Loss": 2.0557875633239746, "Pretrain/Loss (Raw)": 2.034795045852661, "Pretrain/Step": 1963, "Pretrain/Step Time": 8.473168350756168} +{"Pretrain/Learning Rate": 4.6048847874521146e-05, "Pretrain/Loss": 2.055779218673706, "Pretrain/Loss (Raw)": 2.17575740814209, "Pretrain/Step": 1964, "Pretrain/Step Time": 8.47465730458498} +{"Pretrain/Learning Rate": 4.6044265459061486e-05, "Pretrain/Loss": 2.05526065826416, "Pretrain/Loss (Raw)": 2.0798823833465576, "Pretrain/Step": 1965, "Pretrain/Step Time": 8.47139560058713} +{"Pretrain/Learning Rate": 4.6039680616153204e-05, "Pretrain/Loss": 2.054847002029419, "Pretrain/Loss (Raw)": 1.9713244438171387, "Pretrain/Step": 1966, "Pretrain/Step Time": 8.472217163071036} +{"Pretrain/Learning Rate": 4.603509334632515e-05, "Pretrain/Loss": 2.0555596351623535, "Pretrain/Loss (Raw)": 1.9107913970947266, "Pretrain/Step": 1967, "Pretrain/Step Time": 8.471661547198892} +{"Pretrain/Learning Rate": 4.603050365010648e-05, "Pretrain/Loss": 2.055879592895508, "Pretrain/Loss (Raw)": 2.0347862243652344, "Pretrain/Step": 1968, "Pretrain/Step Time": 8.471168972551823} +{"Pretrain/Learning Rate": 4.6025911528026596e-05, "Pretrain/Loss": 2.053402900695801, "Pretrain/Loss (Raw)": 1.9053255319595337, "Pretrain/Step": 1969, "Pretrain/Step Time": 8.467902097851038} +{"Pretrain/Learning Rate": 4.6021316980615216e-05, "Pretrain/Loss": 2.053593397140503, "Pretrain/Loss (Raw)": 1.9929648637771606, "Pretrain/Step": 1970, "Pretrain/Step Time": 8.46762240678072} +{"Pretrain/Learning Rate": 4.60167200084023e-05, "Pretrain/Loss": 2.0530662536621094, "Pretrain/Loss (Raw)": 2.1255674362182617, "Pretrain/Step": 1971, "Pretrain/Step Time": 8.474155880510807} +{"Pretrain/Learning Rate": 4.601212061191812e-05, "Pretrain/Loss": 2.0539650917053223, "Pretrain/Loss (Raw)": 2.140137195587158, "Pretrain/Step": 1972, "Pretrain/Step Time": 8.472720634192228} +{"Pretrain/Learning Rate": 4.6007518791693214e-05, "Pretrain/Loss": 2.057023763656616, "Pretrain/Loss (Raw)": 2.2847719192504883, "Pretrain/Step": 1973, "Pretrain/Step Time": 8.475047068670392} +{"Pretrain/Learning Rate": 4.6002914548258404e-05, "Pretrain/Loss": 2.0571064949035645, "Pretrain/Loss (Raw)": 2.07094669342041, "Pretrain/Step": 1974, "Pretrain/Step Time": 8.478665893897414} +{"Pretrain/Learning Rate": 4.599830788214477e-05, "Pretrain/Loss": 2.057551145553589, "Pretrain/Loss (Raw)": 2.1133577823638916, "Pretrain/Step": 1975, "Pretrain/Step Time": 8.479147225618362} +{"Pretrain/Learning Rate": 4.599369879388371e-05, "Pretrain/Loss": 2.0579605102539062, "Pretrain/Loss (Raw)": 2.1553430557250977, "Pretrain/Step": 1976, "Pretrain/Step Time": 8.47946484386921} +{"Pretrain/Learning Rate": 4.598908728400687e-05, "Pretrain/Loss": 2.0598948001861572, "Pretrain/Loss (Raw)": 2.2796547412872314, "Pretrain/Step": 1977, "Pretrain/Step Time": 8.47949188388884} +{"Pretrain/Learning Rate": 4.598447335304618e-05, "Pretrain/Loss": 2.0603184700012207, "Pretrain/Loss (Raw)": 2.1712753772735596, "Pretrain/Step": 1978, "Pretrain/Step Time": 8.477523224428296} +{"Pretrain/Learning Rate": 4.597985700153387e-05, "Pretrain/Loss": 2.060448169708252, "Pretrain/Loss (Raw)": 2.0776591300964355, "Pretrain/Step": 1979, "Pretrain/Step Time": 8.472728123888373} +{"Pretrain/Learning Rate": 4.597523823000243e-05, "Pretrain/Loss": 2.059488296508789, "Pretrain/Loss (Raw)": 2.046246290206909, "Pretrain/Step": 1980, "Pretrain/Step Time": 8.475143402814865} +{"Pretrain/Learning Rate": 4.597061703898462e-05, "Pretrain/Loss": 2.0578231811523438, "Pretrain/Loss (Raw)": 2.055455207824707, "Pretrain/Step": 1981, "Pretrain/Step Time": 8.475400727242231} +{"Pretrain/Learning Rate": 4.596599342901351e-05, "Pretrain/Loss": 2.0576210021972656, "Pretrain/Loss (Raw)": 2.125333309173584, "Pretrain/Step": 1982, "Pretrain/Step Time": 8.47632310166955} +{"Pretrain/Learning Rate": 4.596136740062243e-05, "Pretrain/Loss": 2.057382106781006, "Pretrain/Loss (Raw)": 2.0567166805267334, "Pretrain/Step": 1983, "Pretrain/Step Time": 8.482703849673271} +{"Pretrain/Learning Rate": 4.5956738954344985e-05, "Pretrain/Loss": 2.05790376663208, "Pretrain/Loss (Raw)": 2.043804407119751, "Pretrain/Step": 1984, "Pretrain/Step Time": 8.479038069024682} +{"Pretrain/Learning Rate": 4.5952108090715066e-05, "Pretrain/Loss": 2.053811550140381, "Pretrain/Loss (Raw)": 1.6099035739898682, "Pretrain/Step": 1985, "Pretrain/Step Time": 8.476612284779549} +{"Pretrain/Learning Rate": 4.594747481026684e-05, "Pretrain/Loss": 2.0533337593078613, "Pretrain/Loss (Raw)": 1.9936704635620117, "Pretrain/Step": 1986, "Pretrain/Step Time": 8.477972507476807} +{"Pretrain/Learning Rate": 4.5942839113534755e-05, "Pretrain/Loss": 2.053168535232544, "Pretrain/Loss (Raw)": 2.077550172805786, "Pretrain/Step": 1987, "Pretrain/Step Time": 8.476107591763139} +{"Pretrain/Learning Rate": 4.593820100105355e-05, "Pretrain/Loss": 2.0529346466064453, "Pretrain/Loss (Raw)": 2.004971981048584, "Pretrain/Step": 1988, "Pretrain/Step Time": 8.477771487087011} +{"Pretrain/Learning Rate": 4.5933560473358204e-05, "Pretrain/Loss": 2.0526058673858643, "Pretrain/Loss (Raw)": 1.9970506429672241, "Pretrain/Step": 1989, "Pretrain/Step Time": 8.478467086330056} +{"Pretrain/Learning Rate": 4.5928917530984016e-05, "Pretrain/Loss": 2.0531458854675293, "Pretrain/Loss (Raw)": 1.980942964553833, "Pretrain/Step": 1990, "Pretrain/Step Time": 8.478370437398553} +{"Pretrain/Learning Rate": 4.5924272174466554e-05, "Pretrain/Loss": 2.0530261993408203, "Pretrain/Loss (Raw)": 2.074665069580078, "Pretrain/Step": 1991, "Pretrain/Step Time": 8.482865799218416} +{"Pretrain/Learning Rate": 4.5919624404341646e-05, "Pretrain/Loss": 2.0537099838256836, "Pretrain/Loss (Raw)": 2.0547690391540527, "Pretrain/Step": 1992, "Pretrain/Step Time": 8.48197608999908} +{"Pretrain/Learning Rate": 4.591497422114541e-05, "Pretrain/Loss": 2.053495407104492, "Pretrain/Loss (Raw)": 1.9345003366470337, "Pretrain/Step": 1993, "Pretrain/Step Time": 8.483192997053266} +{"Pretrain/Learning Rate": 4.591032162541425e-05, "Pretrain/Loss": 2.0542078018188477, "Pretrain/Loss (Raw)": 2.1694741249084473, "Pretrain/Step": 1994, "Pretrain/Step Time": 8.48164027184248} +{"Pretrain/Learning Rate": 4.590566661768484e-05, "Pretrain/Loss": 2.0550808906555176, "Pretrain/Loss (Raw)": 2.234135150909424, "Pretrain/Step": 1995, "Pretrain/Step Time": 8.48235103301704} +{"Pretrain/Learning Rate": 4.5901009198494125e-05, "Pretrain/Loss": 2.0560803413391113, "Pretrain/Loss (Raw)": 2.109386444091797, "Pretrain/Step": 1996, "Pretrain/Step Time": 8.479647567495704} +{"Pretrain/Learning Rate": 4.5896349368379356e-05, "Pretrain/Loss": 2.057180881500244, "Pretrain/Loss (Raw)": 2.176300048828125, "Pretrain/Step": 1997, "Pretrain/Step Time": 8.47986089810729} +{"Pretrain/Learning Rate": 4.5891687127878025e-05, "Pretrain/Loss": 2.0578126907348633, "Pretrain/Loss (Raw)": 2.146108627319336, "Pretrain/Step": 1998, "Pretrain/Step Time": 8.482199730351567} +{"Pretrain/Learning Rate": 4.5887022477527926e-05, "Pretrain/Loss": 2.057180166244507, "Pretrain/Loss (Raw)": 1.9789857864379883, "Pretrain/Step": 1999, "Pretrain/Step Time": 8.480612959712744} +{"Pretrain/Learning Rate": 4.5882355417867126e-05, "Pretrain/Loss": 2.057859420776367, "Pretrain/Loss (Raw)": 2.091052770614624, "Pretrain/Step": 2000, "Pretrain/Step Time": 8.482112873345613} +{"Pretrain/Learning Rate": 4.587768594943396e-05, "Pretrain/Loss": 2.0586142539978027, "Pretrain/Loss (Raw)": 2.160714626312256, "Pretrain/Step": 2001, "Pretrain/Step Time": 8.480207288637757} +{"Pretrain/Learning Rate": 4.587301407276707e-05, "Pretrain/Loss": 2.0609211921691895, "Pretrain/Loss (Raw)": 2.2160582542419434, "Pretrain/Step": 2002, "Pretrain/Step Time": 8.477798324078321} +{"Pretrain/Learning Rate": 4.5868339788405334e-05, "Pretrain/Loss": 2.0600900650024414, "Pretrain/Loss (Raw)": 2.028407573699951, "Pretrain/Step": 2003, "Pretrain/Step Time": 8.477207256481051} +{"Pretrain/Learning Rate": 4.586366309688793e-05, "Pretrain/Loss": 2.0590438842773438, "Pretrain/Loss (Raw)": 2.1068687438964844, "Pretrain/Step": 2004, "Pretrain/Step Time": 8.476337429136038} +{"Pretrain/Learning Rate": 4.585898399875433e-05, "Pretrain/Loss": 2.058413028717041, "Pretrain/Loss (Raw)": 2.024059772491455, "Pretrain/Step": 2005, "Pretrain/Step Time": 8.474800555035472} +{"Pretrain/Learning Rate": 4.585430249454426e-05, "Pretrain/Loss": 2.0582785606384277, "Pretrain/Loss (Raw)": 2.0417098999023438, "Pretrain/Step": 2006, "Pretrain/Step Time": 8.478900328278542} +{"Pretrain/Learning Rate": 4.584961858479772e-05, "Pretrain/Loss": 2.056372880935669, "Pretrain/Loss (Raw)": 1.9008315801620483, "Pretrain/Step": 2007, "Pretrain/Step Time": 8.476966155692935} +{"Pretrain/Learning Rate": 4.5844932270054994e-05, "Pretrain/Loss": 2.0574615001678467, "Pretrain/Loss (Raw)": 2.123361110687256, "Pretrain/Step": 2008, "Pretrain/Step Time": 8.477345189079642} +{"Pretrain/Learning Rate": 4.584024355085666e-05, "Pretrain/Loss": 2.057425022125244, "Pretrain/Loss (Raw)": 2.1185154914855957, "Pretrain/Step": 2009, "Pretrain/Step Time": 8.479641307145357} +{"Pretrain/Learning Rate": 4.583555242774357e-05, "Pretrain/Loss": 2.0578317642211914, "Pretrain/Loss (Raw)": 2.0706734657287598, "Pretrain/Step": 2010, "Pretrain/Step Time": 8.477820223197341} +{"Pretrain/Learning Rate": 4.5830858901256826e-05, "Pretrain/Loss": 2.058018684387207, "Pretrain/Loss (Raw)": 2.1117608547210693, "Pretrain/Step": 2011, "Pretrain/Step Time": 8.476198947057128} +{"Pretrain/Learning Rate": 4.5826162971937816e-05, "Pretrain/Loss": 2.0582001209259033, "Pretrain/Loss (Raw)": 2.1439361572265625, "Pretrain/Step": 2012, "Pretrain/Step Time": 8.472683846950531} +{"Pretrain/Learning Rate": 4.582146464032824e-05, "Pretrain/Loss": 2.0597877502441406, "Pretrain/Loss (Raw)": 2.172905921936035, "Pretrain/Step": 2013, "Pretrain/Step Time": 8.468858670443296} +{"Pretrain/Learning Rate": 4.5816763906970025e-05, "Pretrain/Loss": 2.0617337226867676, "Pretrain/Loss (Raw)": 2.200835704803467, "Pretrain/Step": 2014, "Pretrain/Step Time": 8.47093965858221} +{"Pretrain/Learning Rate": 4.5812060772405406e-05, "Pretrain/Loss": 2.061004161834717, "Pretrain/Loss (Raw)": 1.9898817539215088, "Pretrain/Step": 2015, "Pretrain/Step Time": 8.472238037735224} +{"Pretrain/Learning Rate": 4.58073552371769e-05, "Pretrain/Loss": 2.0612809658050537, "Pretrain/Loss (Raw)": 2.1067144870758057, "Pretrain/Step": 2016, "Pretrain/Step Time": 8.475176304578781} +{"Pretrain/Learning Rate": 4.580264730182727e-05, "Pretrain/Loss": 2.0609121322631836, "Pretrain/Loss (Raw)": 2.074986696243286, "Pretrain/Step": 2017, "Pretrain/Step Time": 8.472829600796103} +{"Pretrain/Learning Rate": 4.57979369668996e-05, "Pretrain/Loss": 2.0611445903778076, "Pretrain/Loss (Raw)": 1.9860166311264038, "Pretrain/Step": 2018, "Pretrain/Step Time": 8.470592455938458} +{"Pretrain/Learning Rate": 4.579322423293719e-05, "Pretrain/Loss": 2.062258005142212, "Pretrain/Loss (Raw)": 2.0713322162628174, "Pretrain/Step": 2019, "Pretrain/Step Time": 8.471680533140898} +{"Pretrain/Learning Rate": 4.578850910048369e-05, "Pretrain/Loss": 2.0613720417022705, "Pretrain/Loss (Raw)": 1.986562728881836, "Pretrain/Step": 2020, "Pretrain/Step Time": 8.473443306982517} +{"Pretrain/Learning Rate": 4.578379157008296e-05, "Pretrain/Loss": 2.0609419345855713, "Pretrain/Loss (Raw)": 1.9562386274337769, "Pretrain/Step": 2021, "Pretrain/Step Time": 8.470813175663352} +{"Pretrain/Learning Rate": 4.577907164227918e-05, "Pretrain/Loss": 2.0599443912506104, "Pretrain/Loss (Raw)": 1.9910733699798584, "Pretrain/Step": 2022, "Pretrain/Step Time": 8.474303944036365} +{"Pretrain/Learning Rate": 4.577434931761679e-05, "Pretrain/Loss": 2.059174060821533, "Pretrain/Loss (Raw)": 2.066723108291626, "Pretrain/Step": 2023, "Pretrain/Step Time": 8.472930444404483} +{"Pretrain/Learning Rate": 4.57696245966405e-05, "Pretrain/Loss": 2.060354709625244, "Pretrain/Loss (Raw)": 1.922134518623352, "Pretrain/Step": 2024, "Pretrain/Step Time": 8.470594661310315} +{"Pretrain/Learning Rate": 4.5764897479895317e-05, "Pretrain/Loss": 2.061225652694702, "Pretrain/Loss (Raw)": 2.1214866638183594, "Pretrain/Step": 2025, "Pretrain/Step Time": 8.470589328557253} +{"Pretrain/Learning Rate": 4.57601679679265e-05, "Pretrain/Loss": 2.0601675510406494, "Pretrain/Loss (Raw)": 2.004077911376953, "Pretrain/Step": 2026, "Pretrain/Step Time": 8.469973416998982} +{"Pretrain/Learning Rate": 4.575543606127962e-05, "Pretrain/Loss": 2.0592050552368164, "Pretrain/Loss (Raw)": 2.0034101009368896, "Pretrain/Step": 2027, "Pretrain/Step Time": 8.466017313301563} +{"Pretrain/Learning Rate": 4.5750701760500466e-05, "Pretrain/Loss": 2.0584194660186768, "Pretrain/Loss (Raw)": 1.9810993671417236, "Pretrain/Step": 2028, "Pretrain/Step Time": 8.466447019949555} +{"Pretrain/Learning Rate": 4.574596506613516e-05, "Pretrain/Loss": 2.0588321685791016, "Pretrain/Loss (Raw)": 2.151402473449707, "Pretrain/Step": 2029, "Pretrain/Step Time": 8.466664433479309} +{"Pretrain/Learning Rate": 4.574122597873009e-05, "Pretrain/Loss": 2.058384418487549, "Pretrain/Loss (Raw)": 2.0727479457855225, "Pretrain/Step": 2030, "Pretrain/Step Time": 8.468850694596767} +{"Pretrain/Learning Rate": 4.573648449883188e-05, "Pretrain/Loss": 2.0593180656433105, "Pretrain/Loss (Raw)": 2.1284327507019043, "Pretrain/Step": 2031, "Pretrain/Step Time": 8.468397287651896} +{"Pretrain/Learning Rate": 4.573174062698747e-05, "Pretrain/Loss": 2.0594794750213623, "Pretrain/Loss (Raw)": 2.062227249145508, "Pretrain/Step": 2032, "Pretrain/Step Time": 8.467688076198101} +{"Pretrain/Learning Rate": 4.572699436374407e-05, "Pretrain/Loss": 2.0598268508911133, "Pretrain/Loss (Raw)": 2.1086606979370117, "Pretrain/Step": 2033, "Pretrain/Step Time": 8.468139776960015} +{"Pretrain/Learning Rate": 4.572224570964915e-05, "Pretrain/Loss": 2.060976028442383, "Pretrain/Loss (Raw)": 2.0766592025756836, "Pretrain/Step": 2034, "Pretrain/Step Time": 8.466955706477165} +{"Pretrain/Learning Rate": 4.571749466525047e-05, "Pretrain/Loss": 2.0620360374450684, "Pretrain/Loss (Raw)": 2.2001826763153076, "Pretrain/Step": 2035, "Pretrain/Step Time": 8.464612323790789} +{"Pretrain/Learning Rate": 4.571274123109606e-05, "Pretrain/Loss": 2.06196928024292, "Pretrain/Loss (Raw)": 1.9877409934997559, "Pretrain/Step": 2036, "Pretrain/Step Time": 8.465204164385796} +{"Pretrain/Learning Rate": 4.570798540773422e-05, "Pretrain/Loss": 2.0620694160461426, "Pretrain/Loss (Raw)": 2.228222370147705, "Pretrain/Step": 2037, "Pretrain/Step Time": 8.470935478806496} +{"Pretrain/Learning Rate": 4.570322719571355e-05, "Pretrain/Loss": 2.0623745918273926, "Pretrain/Loss (Raw)": 2.0292606353759766, "Pretrain/Step": 2038, "Pretrain/Step Time": 8.471513161435723} +{"Pretrain/Learning Rate": 4.56984665955829e-05, "Pretrain/Loss": 2.063169002532959, "Pretrain/Loss (Raw)": 2.0886001586914062, "Pretrain/Step": 2039, "Pretrain/Step Time": 8.473947014659643} +{"Pretrain/Learning Rate": 4.56937036078914e-05, "Pretrain/Loss": 2.0631895065307617, "Pretrain/Loss (Raw)": 2.138873815536499, "Pretrain/Step": 2040, "Pretrain/Step Time": 8.474245062097907} +{"Pretrain/Learning Rate": 4.568893823318846e-05, "Pretrain/Loss": 2.0628883838653564, "Pretrain/Loss (Raw)": 2.006023645401001, "Pretrain/Step": 2041, "Pretrain/Step Time": 8.471557857468724} +{"Pretrain/Learning Rate": 4.568417047202377e-05, "Pretrain/Loss": 2.060760498046875, "Pretrain/Loss (Raw)": 1.889611840248108, "Pretrain/Step": 2042, "Pretrain/Step Time": 8.475553296506405} +{"Pretrain/Learning Rate": 4.567940032494727e-05, "Pretrain/Loss": 2.0606725215911865, "Pretrain/Loss (Raw)": 2.0527031421661377, "Pretrain/Step": 2043, "Pretrain/Step Time": 8.477678805589676} +{"Pretrain/Learning Rate": 4.5674627792509225e-05, "Pretrain/Loss": 2.0612149238586426, "Pretrain/Loss (Raw)": 2.0799689292907715, "Pretrain/Step": 2044, "Pretrain/Step Time": 8.473063714802265} +{"Pretrain/Learning Rate": 4.5669852875260134e-05, "Pretrain/Loss": 2.0599045753479004, "Pretrain/Loss (Raw)": 1.9765667915344238, "Pretrain/Step": 2045, "Pretrain/Step Time": 8.475862257182598} +{"Pretrain/Learning Rate": 4.5665075573750766e-05, "Pretrain/Loss": 2.0602736473083496, "Pretrain/Loss (Raw)": 2.1015536785125732, "Pretrain/Step": 2046, "Pretrain/Step Time": 8.475715391337872} +{"Pretrain/Learning Rate": 4.5660295888532195e-05, "Pretrain/Loss": 2.0605273246765137, "Pretrain/Loss (Raw)": 2.1745941638946533, "Pretrain/Step": 2047, "Pretrain/Step Time": 8.478541042655706} +{"Pretrain/Learning Rate": 4.565551382015576e-05, "Pretrain/Loss": 2.0605599880218506, "Pretrain/Loss (Raw)": 2.1797592639923096, "Pretrain/Step": 2048, "Pretrain/Step Time": 8.476926678791642} +{"Pretrain/Learning Rate": 4.565072936917305e-05, "Pretrain/Loss": 2.062429904937744, "Pretrain/Loss (Raw)": 2.12630558013916, "Pretrain/Step": 2049, "Pretrain/Step Time": 8.477060470730066} +{"Pretrain/Learning Rate": 4.564594253613598e-05, "Pretrain/Loss": 2.0638787746429443, "Pretrain/Loss (Raw)": 2.0323500633239746, "Pretrain/Step": 2050, "Pretrain/Step Time": 8.475812459364533} +{"Pretrain/Learning Rate": 4.564115332159668e-05, "Pretrain/Loss": 2.0641510486602783, "Pretrain/Loss (Raw)": 1.9866799116134644, "Pretrain/Step": 2051, "Pretrain/Step Time": 8.474726693704724} +{"Pretrain/Learning Rate": 4.563636172610761e-05, "Pretrain/Loss": 2.06469988822937, "Pretrain/Loss (Raw)": 2.211310863494873, "Pretrain/Step": 2052, "Pretrain/Step Time": 8.474388018250465} +{"Pretrain/Learning Rate": 4.563156775022147e-05, "Pretrain/Loss": 2.0658817291259766, "Pretrain/Loss (Raw)": 2.2510485649108887, "Pretrain/Step": 2053, "Pretrain/Step Time": 8.47536265105009} +{"Pretrain/Learning Rate": 4.562677139449123e-05, "Pretrain/Loss": 2.0667505264282227, "Pretrain/Loss (Raw)": 1.98749577999115, "Pretrain/Step": 2054, "Pretrain/Step Time": 8.47291961312294} +{"Pretrain/Learning Rate": 4.562197265947016e-05, "Pretrain/Loss": 2.0684311389923096, "Pretrain/Loss (Raw)": 2.2597057819366455, "Pretrain/Step": 2055, "Pretrain/Step Time": 8.474978480488062} +{"Pretrain/Learning Rate": 4.561717154571179e-05, "Pretrain/Loss": 2.069768190383911, "Pretrain/Loss (Raw)": 2.1646392345428467, "Pretrain/Step": 2056, "Pretrain/Step Time": 8.476716978475451} +{"Pretrain/Learning Rate": 4.561236805376994e-05, "Pretrain/Loss": 2.0715527534484863, "Pretrain/Loss (Raw)": 2.04068922996521, "Pretrain/Step": 2057, "Pretrain/Step Time": 8.473852641880512} +{"Pretrain/Learning Rate": 4.560756218419867e-05, "Pretrain/Loss": 2.0704126358032227, "Pretrain/Loss (Raw)": 1.9481135606765747, "Pretrain/Step": 2058, "Pretrain/Step Time": 8.47610779106617} +{"Pretrain/Learning Rate": 4.560275393755233e-05, "Pretrain/Loss": 2.0693986415863037, "Pretrain/Loss (Raw)": 2.023470640182495, "Pretrain/Step": 2059, "Pretrain/Step Time": 8.476102968677878} +{"Pretrain/Learning Rate": 4.5597943314385586e-05, "Pretrain/Loss": 2.067732095718384, "Pretrain/Loss (Raw)": 1.9738123416900635, "Pretrain/Step": 2060, "Pretrain/Step Time": 8.473523683845997} +{"Pretrain/Learning Rate": 4.559313031525331e-05, "Pretrain/Loss": 2.0646355152130127, "Pretrain/Loss (Raw)": 1.9842478036880493, "Pretrain/Step": 2061, "Pretrain/Step Time": 8.474711798131466} +{"Pretrain/Learning Rate": 4.558831494071069e-05, "Pretrain/Loss": 2.0651655197143555, "Pretrain/Loss (Raw)": 2.0449752807617188, "Pretrain/Step": 2062, "Pretrain/Step Time": 8.477589117363095} +{"Pretrain/Learning Rate": 4.558349719131317e-05, "Pretrain/Loss": 2.0655083656311035, "Pretrain/Loss (Raw)": 2.020322322845459, "Pretrain/Step": 2063, "Pretrain/Step Time": 8.479214807972312} +{"Pretrain/Learning Rate": 4.5578677067616494e-05, "Pretrain/Loss": 2.0668468475341797, "Pretrain/Loss (Raw)": 2.235600471496582, "Pretrain/Step": 2064, "Pretrain/Step Time": 8.473741430789232} +{"Pretrain/Learning Rate": 4.5573854570176645e-05, "Pretrain/Loss": 2.0686604976654053, "Pretrain/Loss (Raw)": 2.220132350921631, "Pretrain/Step": 2065, "Pretrain/Step Time": 8.473105346783996} +{"Pretrain/Learning Rate": 4.5569029699549904e-05, "Pretrain/Loss": 2.067437171936035, "Pretrain/Loss (Raw)": 1.9654074907302856, "Pretrain/Step": 2066, "Pretrain/Step Time": 8.47546754218638} +{"Pretrain/Learning Rate": 4.556420245629281e-05, "Pretrain/Loss": 2.069490909576416, "Pretrain/Loss (Raw)": 2.2992312908172607, "Pretrain/Step": 2067, "Pretrain/Step Time": 8.474853169173002} +{"Pretrain/Learning Rate": 4.555937284096219e-05, "Pretrain/Loss": 2.0697317123413086, "Pretrain/Loss (Raw)": 2.1214489936828613, "Pretrain/Step": 2068, "Pretrain/Step Time": 8.470545515418053} +{"Pretrain/Learning Rate": 4.555454085411514e-05, "Pretrain/Loss": 2.0699174404144287, "Pretrain/Loss (Raw)": 2.167802572250366, "Pretrain/Step": 2069, "Pretrain/Step Time": 8.469288831576705} +{"Pretrain/Learning Rate": 4.554970649630903e-05, "Pretrain/Loss": 2.069943428039551, "Pretrain/Loss (Raw)": 2.1324822902679443, "Pretrain/Step": 2070, "Pretrain/Step Time": 8.471291486173868} +{"Pretrain/Learning Rate": 4.554486976810149e-05, "Pretrain/Loss": 2.0705981254577637, "Pretrain/Loss (Raw)": 2.0966155529022217, "Pretrain/Step": 2071, "Pretrain/Step Time": 8.470466192811728} +{"Pretrain/Learning Rate": 4.554003067005045e-05, "Pretrain/Loss": 2.0678250789642334, "Pretrain/Loss (Raw)": 1.8496333360671997, "Pretrain/Step": 2072, "Pretrain/Step Time": 8.473825853317976} +{"Pretrain/Learning Rate": 4.553518920271408e-05, "Pretrain/Loss": 2.067798137664795, "Pretrain/Loss (Raw)": 2.0882227420806885, "Pretrain/Step": 2073, "Pretrain/Step Time": 8.47005544602871} +{"Pretrain/Learning Rate": 4.553034536665086e-05, "Pretrain/Loss": 2.0692145824432373, "Pretrain/Loss (Raw)": 2.090043544769287, "Pretrain/Step": 2074, "Pretrain/Step Time": 8.47302852384746} +{"Pretrain/Learning Rate": 4.552549916241952e-05, "Pretrain/Loss": 2.0687742233276367, "Pretrain/Loss (Raw)": 1.9569648504257202, "Pretrain/Step": 2075, "Pretrain/Step Time": 8.46959413588047} +{"Pretrain/Learning Rate": 4.5520650590579055e-05, "Pretrain/Loss": 2.069265127182007, "Pretrain/Loss (Raw)": 2.046551465988159, "Pretrain/Step": 2076, "Pretrain/Step Time": 8.465218633413315} +{"Pretrain/Learning Rate": 4.5515799651688765e-05, "Pretrain/Loss": 2.068361282348633, "Pretrain/Loss (Raw)": 1.9643886089324951, "Pretrain/Step": 2077, "Pretrain/Step Time": 8.465817829594016} +{"Pretrain/Learning Rate": 4.5510946346308185e-05, "Pretrain/Loss": 2.0664868354797363, "Pretrain/Loss (Raw)": 1.9250119924545288, "Pretrain/Step": 2078, "Pretrain/Step Time": 8.465166877955198} +{"Pretrain/Learning Rate": 4.550609067499716e-05, "Pretrain/Loss": 2.0686497688293457, "Pretrain/Loss (Raw)": 2.219242572784424, "Pretrain/Step": 2079, "Pretrain/Step Time": 8.46062701381743} +{"Pretrain/Learning Rate": 4.550123263831578e-05, "Pretrain/Loss": 2.069748878479004, "Pretrain/Loss (Raw)": 2.0887131690979004, "Pretrain/Step": 2080, "Pretrain/Step Time": 8.463037893176079} +{"Pretrain/Learning Rate": 4.549637223682441e-05, "Pretrain/Loss": 2.069216012954712, "Pretrain/Loss (Raw)": 2.123650312423706, "Pretrain/Step": 2081, "Pretrain/Step Time": 8.463471380993724} +{"Pretrain/Learning Rate": 4.5491509471083724e-05, "Pretrain/Loss": 2.0682125091552734, "Pretrain/Loss (Raw)": 2.003504991531372, "Pretrain/Step": 2082, "Pretrain/Step Time": 8.46296363696456} +{"Pretrain/Learning Rate": 4.548664434165461e-05, "Pretrain/Loss": 2.0697925090789795, "Pretrain/Loss (Raw)": 2.1496520042419434, "Pretrain/Step": 2083, "Pretrain/Step Time": 8.465151250362396} +{"Pretrain/Learning Rate": 4.5481776849098274e-05, "Pretrain/Loss": 2.0693581104278564, "Pretrain/Loss (Raw)": 1.8352195024490356, "Pretrain/Step": 2084, "Pretrain/Step Time": 8.462467696517706} +{"Pretrain/Learning Rate": 4.547690699397618e-05, "Pretrain/Loss": 2.0679752826690674, "Pretrain/Loss (Raw)": 1.8796395063400269, "Pretrain/Step": 2085, "Pretrain/Step Time": 8.462698994204402} +{"Pretrain/Learning Rate": 4.547203477685005e-05, "Pretrain/Loss": 2.0673112869262695, "Pretrain/Loss (Raw)": 2.0849368572235107, "Pretrain/Step": 2086, "Pretrain/Step Time": 8.46473735384643} +{"Pretrain/Learning Rate": 4.546716019828191e-05, "Pretrain/Loss": 2.0659286975860596, "Pretrain/Loss (Raw)": 2.064864158630371, "Pretrain/Step": 2087, "Pretrain/Step Time": 8.464892752468586} +{"Pretrain/Learning Rate": 4.546228325883403e-05, "Pretrain/Loss": 2.067472219467163, "Pretrain/Loss (Raw)": 2.1400725841522217, "Pretrain/Step": 2088, "Pretrain/Step Time": 8.466522181406617} +{"Pretrain/Learning Rate": 4.545740395906897e-05, "Pretrain/Loss": 2.06856632232666, "Pretrain/Loss (Raw)": 2.0916073322296143, "Pretrain/Step": 2089, "Pretrain/Step Time": 8.470127394422889} +{"Pretrain/Learning Rate": 4.545252229954955e-05, "Pretrain/Loss": 2.070204257965088, "Pretrain/Loss (Raw)": 2.1887903213500977, "Pretrain/Step": 2090, "Pretrain/Step Time": 8.467922547832131} +{"Pretrain/Learning Rate": 4.5447638280838875e-05, "Pretrain/Loss": 2.0685853958129883, "Pretrain/Loss (Raw)": 1.827610969543457, "Pretrain/Step": 2091, "Pretrain/Step Time": 8.466638950631022} +{"Pretrain/Learning Rate": 4.544275190350031e-05, "Pretrain/Loss": 2.0672621726989746, "Pretrain/Loss (Raw)": 2.0063581466674805, "Pretrain/Step": 2092, "Pretrain/Step Time": 8.463561683893204} +{"Pretrain/Learning Rate": 4.5437863168097496e-05, "Pretrain/Loss": 2.0670015811920166, "Pretrain/Loss (Raw)": 2.0465304851531982, "Pretrain/Step": 2093, "Pretrain/Step Time": 8.46576933376491} +{"Pretrain/Learning Rate": 4.543297207519434e-05, "Pretrain/Loss": 2.067877769470215, "Pretrain/Loss (Raw)": 2.0834758281707764, "Pretrain/Step": 2094, "Pretrain/Step Time": 8.46279319934547} +{"Pretrain/Learning Rate": 4.542807862535504e-05, "Pretrain/Loss": 2.0686898231506348, "Pretrain/Loss (Raw)": 2.0147182941436768, "Pretrain/Step": 2095, "Pretrain/Step Time": 8.461874309927225} +{"Pretrain/Learning Rate": 4.5423182819144055e-05, "Pretrain/Loss": 2.069347858428955, "Pretrain/Loss (Raw)": 2.119032621383667, "Pretrain/Step": 2096, "Pretrain/Step Time": 8.461507264524698} +{"Pretrain/Learning Rate": 4.541828465712611e-05, "Pretrain/Loss": 2.0705313682556152, "Pretrain/Loss (Raw)": 2.056809186935425, "Pretrain/Step": 2097, "Pretrain/Step Time": 8.460402531549335} +{"Pretrain/Learning Rate": 4.54133841398662e-05, "Pretrain/Loss": 2.072652816772461, "Pretrain/Loss (Raw)": 2.264496326446533, "Pretrain/Step": 2098, "Pretrain/Step Time": 8.460120491683483} +{"Pretrain/Learning Rate": 4.5408481267929605e-05, "Pretrain/Loss": 2.07000732421875, "Pretrain/Loss (Raw)": 1.7869824171066284, "Pretrain/Step": 2099, "Pretrain/Step Time": 8.456085285171866} +{"Pretrain/Learning Rate": 4.5403576041881864e-05, "Pretrain/Loss": 2.071115255355835, "Pretrain/Loss (Raw)": 2.2819340229034424, "Pretrain/Step": 2100, "Pretrain/Step Time": 8.45518285036087} +{"Pretrain/Learning Rate": 4.53986684622888e-05, "Pretrain/Loss": 2.0695621967315674, "Pretrain/Loss (Raw)": 2.085986375808716, "Pretrain/Step": 2101, "Pretrain/Step Time": 8.453841971233487} +{"Pretrain/Learning Rate": 4.539375852971649e-05, "Pretrain/Loss": 2.07047438621521, "Pretrain/Loss (Raw)": 2.1876957416534424, "Pretrain/Step": 2102, "Pretrain/Step Time": 8.454789144918323} +{"Pretrain/Learning Rate": 4.538884624473131e-05, "Pretrain/Loss": 2.0700812339782715, "Pretrain/Loss (Raw)": 2.0630455017089844, "Pretrain/Step": 2103, "Pretrain/Step Time": 8.453026400879025} +{"Pretrain/Learning Rate": 4.538393160789988e-05, "Pretrain/Loss": 2.0703985691070557, "Pretrain/Loss (Raw)": 2.195972204208374, "Pretrain/Step": 2104, "Pretrain/Step Time": 8.45452313311398} +{"Pretrain/Learning Rate": 4.5379014619789104e-05, "Pretrain/Loss": 2.068183660507202, "Pretrain/Loss (Raw)": 1.9961333274841309, "Pretrain/Step": 2105, "Pretrain/Step Time": 8.455317320302129} +{"Pretrain/Learning Rate": 4.537409528096615e-05, "Pretrain/Loss": 2.068035125732422, "Pretrain/Loss (Raw)": 2.1522679328918457, "Pretrain/Step": 2106, "Pretrain/Step Time": 8.456196695566177} +{"Pretrain/Learning Rate": 4.536917359199847e-05, "Pretrain/Loss": 2.068720579147339, "Pretrain/Loss (Raw)": 2.165403127670288, "Pretrain/Step": 2107, "Pretrain/Step Time": 8.461806796491146} +{"Pretrain/Learning Rate": 4.536424955345376e-05, "Pretrain/Loss": 2.068519115447998, "Pretrain/Loss (Raw)": 2.02044415473938, "Pretrain/Step": 2108, "Pretrain/Step Time": 8.458565145730972} +{"Pretrain/Learning Rate": 4.5359323165900036e-05, "Pretrain/Loss": 2.0688674449920654, "Pretrain/Loss (Raw)": 2.100037097930908, "Pretrain/Step": 2109, "Pretrain/Step Time": 8.457774706184864} +{"Pretrain/Learning Rate": 4.535439442990553e-05, "Pretrain/Loss": 2.0688304901123047, "Pretrain/Loss (Raw)": 2.1205930709838867, "Pretrain/Step": 2110, "Pretrain/Step Time": 8.45527858287096} +{"Pretrain/Learning Rate": 4.534946334603879e-05, "Pretrain/Loss": 2.068028211593628, "Pretrain/Loss (Raw)": 1.9540377855300903, "Pretrain/Step": 2111, "Pretrain/Step Time": 8.451942136511207} +{"Pretrain/Learning Rate": 4.5344529914868596e-05, "Pretrain/Loss": 2.0674946308135986, "Pretrain/Loss (Raw)": 1.9755200147628784, "Pretrain/Step": 2112, "Pretrain/Step Time": 8.453444264829159} +{"Pretrain/Learning Rate": 4.533959413696403e-05, "Pretrain/Loss": 2.070711374282837, "Pretrain/Loss (Raw)": 2.0216355323791504, "Pretrain/Step": 2113, "Pretrain/Step Time": 8.451913062483072} +{"Pretrain/Learning Rate": 4.533465601289443e-05, "Pretrain/Loss": 2.0706071853637695, "Pretrain/Loss (Raw)": 1.9803414344787598, "Pretrain/Step": 2114, "Pretrain/Step Time": 8.450754845514894} +{"Pretrain/Learning Rate": 4.53297155432294e-05, "Pretrain/Loss": 2.0713396072387695, "Pretrain/Loss (Raw)": 2.171313524246216, "Pretrain/Step": 2115, "Pretrain/Step Time": 8.451592499390244} +{"Pretrain/Learning Rate": 4.5324772728538825e-05, "Pretrain/Loss": 2.072089672088623, "Pretrain/Loss (Raw)": 2.1009631156921387, "Pretrain/Step": 2116, "Pretrain/Step Time": 8.451051212847233} +{"Pretrain/Learning Rate": 4.531982756939286e-05, "Pretrain/Loss": 2.0701355934143066, "Pretrain/Loss (Raw)": 1.7469218969345093, "Pretrain/Step": 2117, "Pretrain/Step Time": 8.450169768184423} +{"Pretrain/Learning Rate": 4.531488006636193e-05, "Pretrain/Loss": 2.0705299377441406, "Pretrain/Loss (Raw)": 2.0314218997955322, "Pretrain/Step": 2118, "Pretrain/Step Time": 8.453340681269765} +{"Pretrain/Learning Rate": 4.530993022001671e-05, "Pretrain/Loss": 2.068572998046875, "Pretrain/Loss (Raw)": 1.8241902589797974, "Pretrain/Step": 2119, "Pretrain/Step Time": 8.451445968821645} +{"Pretrain/Learning Rate": 4.530497803092819e-05, "Pretrain/Loss": 2.0677490234375, "Pretrain/Loss (Raw)": 1.9493036270141602, "Pretrain/Step": 2120, "Pretrain/Step Time": 8.452203899621964} +{"Pretrain/Learning Rate": 4.530002349966759e-05, "Pretrain/Loss": 2.068632125854492, "Pretrain/Loss (Raw)": 2.0475101470947266, "Pretrain/Step": 2121, "Pretrain/Step Time": 8.45009203441441} +{"Pretrain/Learning Rate": 4.529506662680641e-05, "Pretrain/Loss": 2.066286087036133, "Pretrain/Loss (Raw)": 1.8692028522491455, "Pretrain/Step": 2122, "Pretrain/Step Time": 8.45294606499374} +{"Pretrain/Learning Rate": 4.5290107412916427e-05, "Pretrain/Loss": 2.066122055053711, "Pretrain/Loss (Raw)": 2.213120698928833, "Pretrain/Step": 2123, "Pretrain/Step Time": 8.454753441736102} +{"Pretrain/Learning Rate": 4.5285145858569686e-05, "Pretrain/Loss": 2.0658440589904785, "Pretrain/Loss (Raw)": 2.073819875717163, "Pretrain/Step": 2124, "Pretrain/Step Time": 8.453568482771516} +{"Pretrain/Learning Rate": 4.5280181964338495e-05, "Pretrain/Loss": 2.0658035278320312, "Pretrain/Loss (Raw)": 2.171107769012451, "Pretrain/Step": 2125, "Pretrain/Step Time": 8.450630195438862} +{"Pretrain/Learning Rate": 4.527521573079544e-05, "Pretrain/Loss": 2.0662474632263184, "Pretrain/Loss (Raw)": 2.2029333114624023, "Pretrain/Step": 2126, "Pretrain/Step Time": 8.448485471308231} +{"Pretrain/Learning Rate": 4.527024715851338e-05, "Pretrain/Loss": 2.0666861534118652, "Pretrain/Loss (Raw)": 2.0351643562316895, "Pretrain/Step": 2127, "Pretrain/Step Time": 8.450945541262627} +{"Pretrain/Learning Rate": 4.526527624806543e-05, "Pretrain/Loss": 2.0654244422912598, "Pretrain/Loss (Raw)": 1.9295320510864258, "Pretrain/Step": 2128, "Pretrain/Step Time": 8.449851168319583} +{"Pretrain/Learning Rate": 4.5260303000025e-05, "Pretrain/Loss": 2.064985752105713, "Pretrain/Loss (Raw)": 2.1045596599578857, "Pretrain/Step": 2129, "Pretrain/Step Time": 8.449072750285268} +{"Pretrain/Learning Rate": 4.525532741496572e-05, "Pretrain/Loss": 2.0632686614990234, "Pretrain/Loss (Raw)": 1.9962862730026245, "Pretrain/Step": 2130, "Pretrain/Step Time": 8.4475510828197} +{"Pretrain/Learning Rate": 4.525034949346155e-05, "Pretrain/Loss": 2.063187837600708, "Pretrain/Loss (Raw)": 2.018038034439087, "Pretrain/Step": 2131, "Pretrain/Step Time": 8.445702588185668} +{"Pretrain/Learning Rate": 4.524536923608668e-05, "Pretrain/Loss": 2.064096212387085, "Pretrain/Loss (Raw)": 2.223140001296997, "Pretrain/Step": 2132, "Pretrain/Step Time": 8.444263815879822} +{"Pretrain/Learning Rate": 4.524038664341558e-05, "Pretrain/Loss": 2.064946174621582, "Pretrain/Loss (Raw)": 2.1328494548797607, "Pretrain/Step": 2133, "Pretrain/Step Time": 8.450927045196295} +{"Pretrain/Learning Rate": 4.5235401716023e-05, "Pretrain/Loss": 2.066277503967285, "Pretrain/Loss (Raw)": 2.212141275405884, "Pretrain/Step": 2134, "Pretrain/Step Time": 8.447762310504913} +{"Pretrain/Learning Rate": 4.523041445448394e-05, "Pretrain/Loss": 2.067291259765625, "Pretrain/Loss (Raw)": 2.0305793285369873, "Pretrain/Step": 2135, "Pretrain/Step Time": 8.448914272710681} +{"Pretrain/Learning Rate": 4.522542485937369e-05, "Pretrain/Loss": 2.0671849250793457, "Pretrain/Loss (Raw)": 2.1097614765167236, "Pretrain/Step": 2136, "Pretrain/Step Time": 8.447954533621669} +{"Pretrain/Learning Rate": 4.522043293126778e-05, "Pretrain/Loss": 2.0675430297851562, "Pretrain/Loss (Raw)": 2.1643388271331787, "Pretrain/Step": 2137, "Pretrain/Step Time": 8.445601504296064} +{"Pretrain/Learning Rate": 4.5215438670742045e-05, "Pretrain/Loss": 2.067049503326416, "Pretrain/Loss (Raw)": 2.0075085163116455, "Pretrain/Step": 2138, "Pretrain/Step Time": 8.44728615693748} +{"Pretrain/Learning Rate": 4.521044207837256e-05, "Pretrain/Loss": 2.0666074752807617, "Pretrain/Loss (Raw)": 2.055175542831421, "Pretrain/Step": 2139, "Pretrain/Step Time": 8.449209487065673} +{"Pretrain/Learning Rate": 4.5205443154735684e-05, "Pretrain/Loss": 2.06728458404541, "Pretrain/Loss (Raw)": 2.230609178543091, "Pretrain/Step": 2140, "Pretrain/Step Time": 8.447527807205915} +{"Pretrain/Learning Rate": 4.5200441900408045e-05, "Pretrain/Loss": 2.0652294158935547, "Pretrain/Loss (Raw)": 1.9098275899887085, "Pretrain/Step": 2141, "Pretrain/Step Time": 8.450882764533162} +{"Pretrain/Learning Rate": 4.519543831596652e-05, "Pretrain/Loss": 2.065070390701294, "Pretrain/Loss (Raw)": 2.180500030517578, "Pretrain/Step": 2142, "Pretrain/Step Time": 8.446565171703696} +{"Pretrain/Learning Rate": 4.519043240198829e-05, "Pretrain/Loss": 2.0663185119628906, "Pretrain/Loss (Raw)": 2.149651527404785, "Pretrain/Step": 2143, "Pretrain/Step Time": 8.446024967357516} +{"Pretrain/Learning Rate": 4.518542415905077e-05, "Pretrain/Loss": 2.065277576446533, "Pretrain/Loss (Raw)": 1.973455786705017, "Pretrain/Step": 2144, "Pretrain/Step Time": 8.44737003929913} +{"Pretrain/Learning Rate": 4.518041358773169e-05, "Pretrain/Loss": 2.063626766204834, "Pretrain/Loss (Raw)": 1.8636881113052368, "Pretrain/Step": 2145, "Pretrain/Step Time": 8.451900394633412} +{"Pretrain/Learning Rate": 4.517540068860897e-05, "Pretrain/Loss": 2.063553810119629, "Pretrain/Loss (Raw)": 1.9766932725906372, "Pretrain/Step": 2146, "Pretrain/Step Time": 8.450102204456925} +{"Pretrain/Learning Rate": 4.5170385462260875e-05, "Pretrain/Loss": 2.063171625137329, "Pretrain/Loss (Raw)": 2.0223724842071533, "Pretrain/Step": 2147, "Pretrain/Step Time": 8.446640431880951} +{"Pretrain/Learning Rate": 4.516536790926592e-05, "Pretrain/Loss": 2.063169002532959, "Pretrain/Loss (Raw)": 1.9862381219863892, "Pretrain/Step": 2148, "Pretrain/Step Time": 8.44939548894763} +{"Pretrain/Learning Rate": 4.516034803020285e-05, "Pretrain/Loss": 2.0643677711486816, "Pretrain/Loss (Raw)": 2.109668731689453, "Pretrain/Step": 2149, "Pretrain/Step Time": 8.450655397027731} +{"Pretrain/Learning Rate": 4.515532582565072e-05, "Pretrain/Loss": 2.06424617767334, "Pretrain/Loss (Raw)": 1.975545883178711, "Pretrain/Step": 2150, "Pretrain/Step Time": 8.453216832131147} +{"Pretrain/Learning Rate": 4.515030129618884e-05, "Pretrain/Loss": 2.0652146339416504, "Pretrain/Loss (Raw)": 2.190692186355591, "Pretrain/Step": 2151, "Pretrain/Step Time": 8.452320316806436} +{"Pretrain/Learning Rate": 4.514527444239679e-05, "Pretrain/Loss": 2.0656323432922363, "Pretrain/Loss (Raw)": 1.975574016571045, "Pretrain/Step": 2152, "Pretrain/Step Time": 8.452849203720689} +{"Pretrain/Learning Rate": 4.514024526485441e-05, "Pretrain/Loss": 2.064450740814209, "Pretrain/Loss (Raw)": 1.9702481031417847, "Pretrain/Step": 2153, "Pretrain/Step Time": 8.452973779290915} +{"Pretrain/Learning Rate": 4.513521376414181e-05, "Pretrain/Loss": 2.0646188259124756, "Pretrain/Loss (Raw)": 2.0256035327911377, "Pretrain/Step": 2154, "Pretrain/Step Time": 8.453788483515382} +{"Pretrain/Learning Rate": 4.513017994083939e-05, "Pretrain/Loss": 2.0658628940582275, "Pretrain/Loss (Raw)": 2.162626266479492, "Pretrain/Step": 2155, "Pretrain/Step Time": 8.45336571149528} +{"Pretrain/Learning Rate": 4.512514379552779e-05, "Pretrain/Loss": 2.066471576690674, "Pretrain/Loss (Raw)": 2.059033155441284, "Pretrain/Step": 2156, "Pretrain/Step Time": 8.453155811876059} +{"Pretrain/Learning Rate": 4.512010532878792e-05, "Pretrain/Loss": 2.0669384002685547, "Pretrain/Loss (Raw)": 2.2111423015594482, "Pretrain/Step": 2157, "Pretrain/Step Time": 8.45151861384511} +{"Pretrain/Learning Rate": 4.511506454120097e-05, "Pretrain/Loss": 2.0678491592407227, "Pretrain/Loss (Raw)": 2.189326524734497, "Pretrain/Step": 2158, "Pretrain/Step Time": 8.448903953656554} +{"Pretrain/Learning Rate": 4.5110021433348396e-05, "Pretrain/Loss": 2.066741943359375, "Pretrain/Loss (Raw)": 1.986700415611267, "Pretrain/Step": 2159, "Pretrain/Step Time": 8.45240524597466} +{"Pretrain/Learning Rate": 4.510497600581192e-05, "Pretrain/Loss": 2.0665252208709717, "Pretrain/Loss (Raw)": 2.03450608253479, "Pretrain/Step": 2160, "Pretrain/Step Time": 8.455569509416819} +{"Pretrain/Learning Rate": 4.5099928259173516e-05, "Pretrain/Loss": 2.0650148391723633, "Pretrain/Loss (Raw)": 1.9153387546539307, "Pretrain/Step": 2161, "Pretrain/Step Time": 8.458214048296213} +{"Pretrain/Learning Rate": 4.509487819401545e-05, "Pretrain/Loss": 2.064671516418457, "Pretrain/Loss (Raw)": 2.0327296257019043, "Pretrain/Step": 2162, "Pretrain/Step Time": 8.45756135135889} +{"Pretrain/Learning Rate": 4.508982581092026e-05, "Pretrain/Loss": 2.0641229152679443, "Pretrain/Loss (Raw)": 2.129910469055176, "Pretrain/Step": 2163, "Pretrain/Step Time": 8.45625277608633} +{"Pretrain/Learning Rate": 4.508477111047072e-05, "Pretrain/Loss": 2.065488338470459, "Pretrain/Loss (Raw)": 2.162537097930908, "Pretrain/Step": 2164, "Pretrain/Step Time": 8.455147938802838} +{"Pretrain/Learning Rate": 4.5079714093249884e-05, "Pretrain/Loss": 2.063739776611328, "Pretrain/Loss (Raw)": 2.004412889480591, "Pretrain/Step": 2165, "Pretrain/Step Time": 8.451556766405702} +{"Pretrain/Learning Rate": 4.507465475984109e-05, "Pretrain/Loss": 2.0650954246520996, "Pretrain/Loss (Raw)": 2.202770471572876, "Pretrain/Step": 2166, "Pretrain/Step Time": 8.450542004778981} +{"Pretrain/Learning Rate": 4.5069593110827926e-05, "Pretrain/Loss": 2.0652196407318115, "Pretrain/Loss (Raw)": 2.1045026779174805, "Pretrain/Step": 2167, "Pretrain/Step Time": 8.450943876057863} +{"Pretrain/Learning Rate": 4.506452914679424e-05, "Pretrain/Loss": 2.065634250640869, "Pretrain/Loss (Raw)": 2.1919426918029785, "Pretrain/Step": 2168, "Pretrain/Step Time": 8.450339017435908} +{"Pretrain/Learning Rate": 4.505946286832418e-05, "Pretrain/Loss": 2.0668156147003174, "Pretrain/Loss (Raw)": 2.1572396755218506, "Pretrain/Step": 2169, "Pretrain/Step Time": 8.45595789141953} +{"Pretrain/Learning Rate": 4.505439427600211e-05, "Pretrain/Loss": 2.067025661468506, "Pretrain/Loss (Raw)": 1.9165077209472656, "Pretrain/Step": 2170, "Pretrain/Step Time": 8.452620584517717} +{"Pretrain/Learning Rate": 4.5049323370412724e-05, "Pretrain/Loss": 2.0656416416168213, "Pretrain/Loss (Raw)": 1.8755336999893188, "Pretrain/Step": 2171, "Pretrain/Step Time": 8.453314846381545} +{"Pretrain/Learning Rate": 4.504425015214092e-05, "Pretrain/Loss": 2.0659265518188477, "Pretrain/Loss (Raw)": 2.116461992263794, "Pretrain/Step": 2172, "Pretrain/Step Time": 8.455034028738737} +{"Pretrain/Learning Rate": 4.503917462177192e-05, "Pretrain/Loss": 2.0674538612365723, "Pretrain/Loss (Raw)": 2.17205810546875, "Pretrain/Step": 2173, "Pretrain/Step Time": 8.452803898602724} +{"Pretrain/Learning Rate": 4.503409677989116e-05, "Pretrain/Loss": 2.067936420440674, "Pretrain/Loss (Raw)": 2.163306713104248, "Pretrain/Step": 2174, "Pretrain/Step Time": 8.45235351473093} +{"Pretrain/Learning Rate": 4.502901662708437e-05, "Pretrain/Loss": 2.0657927989959717, "Pretrain/Loss (Raw)": 1.900210976600647, "Pretrain/Step": 2175, "Pretrain/Step Time": 8.452497696503997} +{"Pretrain/Learning Rate": 4.502393416393756e-05, "Pretrain/Loss": 2.0656986236572266, "Pretrain/Loss (Raw)": 2.167707681655884, "Pretrain/Step": 2176, "Pretrain/Step Time": 8.450922258198261} +{"Pretrain/Learning Rate": 4.5018849391036986e-05, "Pretrain/Loss": 2.0640249252319336, "Pretrain/Loss (Raw)": 1.9120733737945557, "Pretrain/Step": 2177, "Pretrain/Step Time": 8.452158987522125} +{"Pretrain/Learning Rate": 4.501376230896917e-05, "Pretrain/Loss": 2.065774440765381, "Pretrain/Loss (Raw)": 2.2562918663024902, "Pretrain/Step": 2178, "Pretrain/Step Time": 8.449490953236818} +{"Pretrain/Learning Rate": 4.500867291832089e-05, "Pretrain/Loss": 2.0661520957946777, "Pretrain/Loss (Raw)": 2.0350167751312256, "Pretrain/Step": 2179, "Pretrain/Step Time": 8.451296048238873} +{"Pretrain/Learning Rate": 4.5003581219679233e-05, "Pretrain/Loss": 2.0644543170928955, "Pretrain/Loss (Raw)": 1.9940078258514404, "Pretrain/Step": 2180, "Pretrain/Step Time": 8.449272004887462} +{"Pretrain/Learning Rate": 4.499848721363151e-05, "Pretrain/Loss": 2.0632224082946777, "Pretrain/Loss (Raw)": 2.09334659576416, "Pretrain/Step": 2181, "Pretrain/Step Time": 8.447602272033691} +{"Pretrain/Learning Rate": 4.499339090076532e-05, "Pretrain/Loss": 2.064734935760498, "Pretrain/Loss (Raw)": 2.1811065673828125, "Pretrain/Step": 2182, "Pretrain/Step Time": 8.446709521114826} +{"Pretrain/Learning Rate": 4.498829228166851e-05, "Pretrain/Loss": 2.062856912612915, "Pretrain/Loss (Raw)": 2.0193164348602295, "Pretrain/Step": 2183, "Pretrain/Step Time": 8.446912921965122} +{"Pretrain/Learning Rate": 4.498319135692921e-05, "Pretrain/Loss": 2.0622243881225586, "Pretrain/Loss (Raw)": 2.083691120147705, "Pretrain/Step": 2184, "Pretrain/Step Time": 8.44717850908637} +{"Pretrain/Learning Rate": 4.4978088127135806e-05, "Pretrain/Loss": 2.0627405643463135, "Pretrain/Loss (Raw)": 2.106748104095459, "Pretrain/Step": 2185, "Pretrain/Step Time": 8.45044082030654} +{"Pretrain/Learning Rate": 4.497298259287696e-05, "Pretrain/Loss": 2.0629289150238037, "Pretrain/Loss (Raw)": 1.9722236394882202, "Pretrain/Step": 2186, "Pretrain/Step Time": 8.45018899999559} +{"Pretrain/Learning Rate": 4.496787475474159e-05, "Pretrain/Loss": 2.06333065032959, "Pretrain/Loss (Raw)": 2.0748910903930664, "Pretrain/Step": 2187, "Pretrain/Step Time": 8.449206285178661} +{"Pretrain/Learning Rate": 4.496276461331889e-05, "Pretrain/Loss": 2.0652432441711426, "Pretrain/Loss (Raw)": 2.2186279296875, "Pretrain/Step": 2188, "Pretrain/Step Time": 8.451185313984752} +{"Pretrain/Learning Rate": 4.49576521691983e-05, "Pretrain/Loss": 2.066986083984375, "Pretrain/Loss (Raw)": 2.2073209285736084, "Pretrain/Step": 2189, "Pretrain/Step Time": 8.450316835194826} +{"Pretrain/Learning Rate": 4.495253742296955e-05, "Pretrain/Loss": 2.067516326904297, "Pretrain/Loss (Raw)": 2.1128621101379395, "Pretrain/Step": 2190, "Pretrain/Step Time": 8.446990290656686} +{"Pretrain/Learning Rate": 4.4947420375222616e-05, "Pretrain/Loss": 2.06620192527771, "Pretrain/Loss (Raw)": 1.8520675897598267, "Pretrain/Step": 2191, "Pretrain/Step Time": 8.445093547925353} +{"Pretrain/Learning Rate": 4.4942301026547755e-05, "Pretrain/Loss": 2.06307315826416, "Pretrain/Loss (Raw)": 1.8350965976715088, "Pretrain/Step": 2192, "Pretrain/Step Time": 8.4501140601933} +{"Pretrain/Learning Rate": 4.4937179377535476e-05, "Pretrain/Loss": 2.061680316925049, "Pretrain/Loss (Raw)": 2.04186749458313, "Pretrain/Step": 2193, "Pretrain/Step Time": 8.449581818655133} +{"Pretrain/Learning Rate": 4.493205542877656e-05, "Pretrain/Loss": 2.063061237335205, "Pretrain/Loss (Raw)": 2.142176628112793, "Pretrain/Step": 2194, "Pretrain/Step Time": 8.450106827542186} +{"Pretrain/Learning Rate": 4.4926929180862064e-05, "Pretrain/Loss": 2.0625576972961426, "Pretrain/Loss (Raw)": 2.2347724437713623, "Pretrain/Step": 2195, "Pretrain/Step Time": 8.44824281334877} +{"Pretrain/Learning Rate": 4.4921800634383294e-05, "Pretrain/Loss": 2.063361644744873, "Pretrain/Loss (Raw)": 2.2243432998657227, "Pretrain/Step": 2196, "Pretrain/Step Time": 8.45008217357099} +{"Pretrain/Learning Rate": 4.491666978993181e-05, "Pretrain/Loss": 2.062753677368164, "Pretrain/Loss (Raw)": 2.090015172958374, "Pretrain/Step": 2197, "Pretrain/Step Time": 8.44998531229794} +{"Pretrain/Learning Rate": 4.4911536648099464e-05, "Pretrain/Loss": 2.0603301525115967, "Pretrain/Loss (Raw)": 1.822252631187439, "Pretrain/Step": 2198, "Pretrain/Step Time": 8.446798756718636} +{"Pretrain/Learning Rate": 4.4906401209478367e-05, "Pretrain/Loss": 2.060652732849121, "Pretrain/Loss (Raw)": 2.137894630432129, "Pretrain/Step": 2199, "Pretrain/Step Time": 8.447197137400508} +{"Pretrain/Learning Rate": 4.4901263474660894e-05, "Pretrain/Loss": 2.0613317489624023, "Pretrain/Loss (Raw)": 1.9365534782409668, "Pretrain/Step": 2200, "Pretrain/Step Time": 8.446620067581534} +{"Pretrain/Learning Rate": 4.489612344423966e-05, "Pretrain/Loss": 2.0613760948181152, "Pretrain/Loss (Raw)": 2.0939090251922607, "Pretrain/Step": 2201, "Pretrain/Step Time": 8.452272759750485} +{"Pretrain/Learning Rate": 4.489098111880759e-05, "Pretrain/Loss": 2.0606369972229004, "Pretrain/Loss (Raw)": 1.995436191558838, "Pretrain/Step": 2202, "Pretrain/Step Time": 8.450987657532096} +{"Pretrain/Learning Rate": 4.4885836498957824e-05, "Pretrain/Loss": 2.0619747638702393, "Pretrain/Loss (Raw)": 2.128208637237549, "Pretrain/Step": 2203, "Pretrain/Step Time": 8.450919654220343} +{"Pretrain/Learning Rate": 4.488068958528382e-05, "Pretrain/Loss": 2.0624544620513916, "Pretrain/Loss (Raw)": 2.1079397201538086, "Pretrain/Step": 2204, "Pretrain/Step Time": 8.452497297897935} +{"Pretrain/Learning Rate": 4.487554037837925e-05, "Pretrain/Loss": 2.063417911529541, "Pretrain/Loss (Raw)": 2.087686538696289, "Pretrain/Step": 2205, "Pretrain/Step Time": 8.453965688124299} +{"Pretrain/Learning Rate": 4.487038887883809e-05, "Pretrain/Loss": 2.064479351043701, "Pretrain/Loss (Raw)": 2.0608980655670166, "Pretrain/Step": 2206, "Pretrain/Step Time": 8.452917527407408} +{"Pretrain/Learning Rate": 4.4865235087254545e-05, "Pretrain/Loss": 2.0629348754882812, "Pretrain/Loss (Raw)": 2.0215680599212646, "Pretrain/Step": 2207, "Pretrain/Step Time": 8.459034143015742} +{"Pretrain/Learning Rate": 4.486007900422312e-05, "Pretrain/Loss": 2.062255859375, "Pretrain/Loss (Raw)": 2.0017528533935547, "Pretrain/Step": 2208, "Pretrain/Step Time": 8.456664945930243} +{"Pretrain/Learning Rate": 4.485492063033856e-05, "Pretrain/Loss": 2.0622358322143555, "Pretrain/Loss (Raw)": 2.1211109161376953, "Pretrain/Step": 2209, "Pretrain/Step Time": 8.458777165040374} +{"Pretrain/Learning Rate": 4.484975996619589e-05, "Pretrain/Loss": 2.062499761581421, "Pretrain/Loss (Raw)": 2.037278175354004, "Pretrain/Step": 2210, "Pretrain/Step Time": 8.459021650254726} +{"Pretrain/Learning Rate": 4.484459701239038e-05, "Pretrain/Loss": 2.0624969005584717, "Pretrain/Loss (Raw)": 2.1492810249328613, "Pretrain/Step": 2211, "Pretrain/Step Time": 8.459139313548803} +{"Pretrain/Learning Rate": 4.483943176951757e-05, "Pretrain/Loss": 2.064211368560791, "Pretrain/Loss (Raw)": 2.0546813011169434, "Pretrain/Step": 2212, "Pretrain/Step Time": 8.456447675824165} +{"Pretrain/Learning Rate": 4.4834264238173285e-05, "Pretrain/Loss": 2.064504623413086, "Pretrain/Loss (Raw)": 1.9172041416168213, "Pretrain/Step": 2213, "Pretrain/Step Time": 8.45848191715777} +{"Pretrain/Learning Rate": 4.4829094418953586e-05, "Pretrain/Loss": 2.064296007156372, "Pretrain/Loss (Raw)": 2.058209180831909, "Pretrain/Step": 2214, "Pretrain/Step Time": 8.460043182596564} +{"Pretrain/Learning Rate": 4.482392231245481e-05, "Pretrain/Loss": 2.0649542808532715, "Pretrain/Loss (Raw)": 2.1491329669952393, "Pretrain/Step": 2215, "Pretrain/Step Time": 8.458556370809674} +{"Pretrain/Learning Rate": 4.4818747919273575e-05, "Pretrain/Loss": 2.064811944961548, "Pretrain/Loss (Raw)": 2.1218442916870117, "Pretrain/Step": 2216, "Pretrain/Step Time": 8.460171407088637} +{"Pretrain/Learning Rate": 4.4813571240006726e-05, "Pretrain/Loss": 2.064770221710205, "Pretrain/Loss (Raw)": 2.0862627029418945, "Pretrain/Step": 2217, "Pretrain/Step Time": 8.460883058607578} +{"Pretrain/Learning Rate": 4.48083922752514e-05, "Pretrain/Loss": 2.0626096725463867, "Pretrain/Loss (Raw)": 1.9122451543807983, "Pretrain/Step": 2218, "Pretrain/Step Time": 8.460148321464658} +{"Pretrain/Learning Rate": 4.480321102560499e-05, "Pretrain/Loss": 2.064241886138916, "Pretrain/Loss (Raw)": 2.0365235805511475, "Pretrain/Step": 2219, "Pretrain/Step Time": 8.462779441848397} +{"Pretrain/Learning Rate": 4.4798027491665134e-05, "Pretrain/Loss": 2.064911127090454, "Pretrain/Loss (Raw)": 2.092040538787842, "Pretrain/Step": 2220, "Pretrain/Step Time": 8.46460616774857} +{"Pretrain/Learning Rate": 4.4792841674029776e-05, "Pretrain/Loss": 2.0646986961364746, "Pretrain/Loss (Raw)": 2.019317150115967, "Pretrain/Step": 2221, "Pretrain/Step Time": 8.46408548206091} +{"Pretrain/Learning Rate": 4.4787653573297075e-05, "Pretrain/Loss": 2.064811944961548, "Pretrain/Loss (Raw)": 2.097989797592163, "Pretrain/Step": 2222, "Pretrain/Step Time": 8.46588252298534} +{"Pretrain/Learning Rate": 4.47824631900655e-05, "Pretrain/Loss": 2.0657901763916016, "Pretrain/Loss (Raw)": 2.1399242877960205, "Pretrain/Step": 2223, "Pretrain/Step Time": 8.466748861595988} +{"Pretrain/Learning Rate": 4.477727052493375e-05, "Pretrain/Loss": 2.0663609504699707, "Pretrain/Loss (Raw)": 2.1921186447143555, "Pretrain/Step": 2224, "Pretrain/Step Time": 8.467216221615672} +{"Pretrain/Learning Rate": 4.4772075578500785e-05, "Pretrain/Loss": 2.0664567947387695, "Pretrain/Loss (Raw)": 2.0690526962280273, "Pretrain/Step": 2225, "Pretrain/Step Time": 8.470463261008263} +{"Pretrain/Learning Rate": 4.476687835136585e-05, "Pretrain/Loss": 2.0656111240386963, "Pretrain/Loss (Raw)": 2.1562464237213135, "Pretrain/Step": 2226, "Pretrain/Step Time": 8.471367061138153} +{"Pretrain/Learning Rate": 4.476167884412845e-05, "Pretrain/Loss": 2.067742347717285, "Pretrain/Loss (Raw)": 2.059769630432129, "Pretrain/Step": 2227, "Pretrain/Step Time": 8.470371520146728} +{"Pretrain/Learning Rate": 4.475647705738833e-05, "Pretrain/Loss": 2.06707763671875, "Pretrain/Loss (Raw)": 2.196852445602417, "Pretrain/Step": 2228, "Pretrain/Step Time": 8.473459547385573} +{"Pretrain/Learning Rate": 4.475127299174554e-05, "Pretrain/Loss": 2.067166805267334, "Pretrain/Loss (Raw)": 2.097400188446045, "Pretrain/Step": 2229, "Pretrain/Step Time": 8.47484695352614} +{"Pretrain/Learning Rate": 4.4746066647800344e-05, "Pretrain/Loss": 2.067054271697998, "Pretrain/Loss (Raw)": 2.173292398452759, "Pretrain/Step": 2230, "Pretrain/Step Time": 8.473577689379454} +{"Pretrain/Learning Rate": 4.4740858026153297e-05, "Pretrain/Loss": 2.065598964691162, "Pretrain/Loss (Raw)": 1.876753330230713, "Pretrain/Step": 2231, "Pretrain/Step Time": 8.473262270912528} +{"Pretrain/Learning Rate": 4.4735647127405215e-05, "Pretrain/Loss": 2.0636379718780518, "Pretrain/Loss (Raw)": 1.9450098276138306, "Pretrain/Step": 2232, "Pretrain/Step Time": 8.472969211637974} +{"Pretrain/Learning Rate": 4.473043395215718e-05, "Pretrain/Loss": 2.06473445892334, "Pretrain/Loss (Raw)": 2.1364471912384033, "Pretrain/Step": 2233, "Pretrain/Step Time": 8.468204129487276} +{"Pretrain/Learning Rate": 4.4725218501010514e-05, "Pretrain/Loss": 2.0644028186798096, "Pretrain/Loss (Raw)": 2.109835386276245, "Pretrain/Step": 2234, "Pretrain/Step Time": 8.472974536940455} +{"Pretrain/Learning Rate": 4.472000077456683e-05, "Pretrain/Loss": 2.0634732246398926, "Pretrain/Loss (Raw)": 2.0464026927948, "Pretrain/Step": 2235, "Pretrain/Step Time": 8.47088293172419} +{"Pretrain/Learning Rate": 4.471478077342798e-05, "Pretrain/Loss": 2.064910650253296, "Pretrain/Loss (Raw)": 2.204451560974121, "Pretrain/Step": 2236, "Pretrain/Step Time": 8.469990707933903} +{"Pretrain/Learning Rate": 4.4709558498196104e-05, "Pretrain/Loss": 2.0647201538085938, "Pretrain/Loss (Raw)": 2.0756726264953613, "Pretrain/Step": 2237, "Pretrain/Step Time": 8.470099737867713} +{"Pretrain/Learning Rate": 4.4704333949473575e-05, "Pretrain/Loss": 2.0642876625061035, "Pretrain/Loss (Raw)": 2.065218925476074, "Pretrain/Step": 2238, "Pretrain/Step Time": 8.472785092890263} +{"Pretrain/Learning Rate": 4.469910712786305e-05, "Pretrain/Loss": 2.0654141902923584, "Pretrain/Loss (Raw)": 2.09822940826416, "Pretrain/Step": 2239, "Pretrain/Step Time": 8.473317375406623} +{"Pretrain/Learning Rate": 4.469387803396745e-05, "Pretrain/Loss": 2.0654735565185547, "Pretrain/Loss (Raw)": 1.9831315279006958, "Pretrain/Step": 2240, "Pretrain/Step Time": 8.471634421497583} +{"Pretrain/Learning Rate": 4.4688646668389935e-05, "Pretrain/Loss": 2.0662951469421387, "Pretrain/Loss (Raw)": 2.1268112659454346, "Pretrain/Step": 2241, "Pretrain/Step Time": 8.474654333665967} +{"Pretrain/Learning Rate": 4.468341303173394e-05, "Pretrain/Loss": 2.0671770572662354, "Pretrain/Loss (Raw)": 2.093200445175171, "Pretrain/Step": 2242, "Pretrain/Step Time": 8.470795679837465} +{"Pretrain/Learning Rate": 4.4678177124603174e-05, "Pretrain/Loss": 2.06666898727417, "Pretrain/Loss (Raw)": 2.106259822845459, "Pretrain/Step": 2243, "Pretrain/Step Time": 8.472530376166105} +{"Pretrain/Learning Rate": 4.46729389476016e-05, "Pretrain/Loss": 2.065856456756592, "Pretrain/Loss (Raw)": 1.9969935417175293, "Pretrain/Step": 2244, "Pretrain/Step Time": 8.47332906909287} +{"Pretrain/Learning Rate": 4.466769850133342e-05, "Pretrain/Loss": 2.0679264068603516, "Pretrain/Loss (Raw)": 2.01186203956604, "Pretrain/Step": 2245, "Pretrain/Step Time": 8.47698114439845} +{"Pretrain/Learning Rate": 4.466245578640313e-05, "Pretrain/Loss": 2.0679306983947754, "Pretrain/Loss (Raw)": 2.0319836139678955, "Pretrain/Step": 2246, "Pretrain/Step Time": 8.47413250617683} +{"Pretrain/Learning Rate": 4.465721080341547e-05, "Pretrain/Loss": 2.0675501823425293, "Pretrain/Loss (Raw)": 1.7754721641540527, "Pretrain/Step": 2247, "Pretrain/Step Time": 8.477265127003193} +{"Pretrain/Learning Rate": 4.465196355297546e-05, "Pretrain/Loss": 2.0691027641296387, "Pretrain/Loss (Raw)": 2.148042678833008, "Pretrain/Step": 2248, "Pretrain/Step Time": 8.477309469133615} +{"Pretrain/Learning Rate": 4.464671403568836e-05, "Pretrain/Loss": 2.070769786834717, "Pretrain/Loss (Raw)": 2.2608985900878906, "Pretrain/Step": 2249, "Pretrain/Step Time": 8.480703579261899} +{"Pretrain/Learning Rate": 4.46414622521597e-05, "Pretrain/Loss": 2.072977066040039, "Pretrain/Loss (Raw)": 2.151724100112915, "Pretrain/Step": 2250, "Pretrain/Step Time": 8.481334131211042} +{"Pretrain/Learning Rate": 4.463620820299528e-05, "Pretrain/Loss": 2.0732758045196533, "Pretrain/Loss (Raw)": 2.2513558864593506, "Pretrain/Step": 2251, "Pretrain/Step Time": 8.478733954951167} +{"Pretrain/Learning Rate": 4.463095188880113e-05, "Pretrain/Loss": 2.0721147060394287, "Pretrain/Loss (Raw)": 1.9251999855041504, "Pretrain/Step": 2252, "Pretrain/Step Time": 8.485163005068898} +{"Pretrain/Learning Rate": 4.462569331018359e-05, "Pretrain/Loss": 2.0697991847991943, "Pretrain/Loss (Raw)": 1.8747304677963257, "Pretrain/Step": 2253, "Pretrain/Step Time": 8.485098706558347} +{"Pretrain/Learning Rate": 4.4620432467749217e-05, "Pretrain/Loss": 2.0700509548187256, "Pretrain/Loss (Raw)": 2.2351388931274414, "Pretrain/Step": 2254, "Pretrain/Step Time": 8.483574269339442} +{"Pretrain/Learning Rate": 4.461516936210486e-05, "Pretrain/Loss": 2.069610595703125, "Pretrain/Loss (Raw)": 1.9788320064544678, "Pretrain/Step": 2255, "Pretrain/Step Time": 8.484595850110054} +{"Pretrain/Learning Rate": 4.460990399385761e-05, "Pretrain/Loss": 2.070876359939575, "Pretrain/Loss (Raw)": 2.091543436050415, "Pretrain/Step": 2256, "Pretrain/Step Time": 8.483474219217896} +{"Pretrain/Learning Rate": 4.4604636363614813e-05, "Pretrain/Loss": 2.0702075958251953, "Pretrain/Loss (Raw)": 2.0189690589904785, "Pretrain/Step": 2257, "Pretrain/Step Time": 8.485735211521387} +{"Pretrain/Learning Rate": 4.4599366471984104e-05, "Pretrain/Loss": 2.071197509765625, "Pretrain/Loss (Raw)": 2.122966766357422, "Pretrain/Step": 2258, "Pretrain/Step Time": 8.491079863160849} +{"Pretrain/Learning Rate": 4.459409431957337e-05, "Pretrain/Loss": 2.071538209915161, "Pretrain/Loss (Raw)": 2.061624526977539, "Pretrain/Step": 2259, "Pretrain/Step Time": 8.49072203412652} +{"Pretrain/Learning Rate": 4.4588819906990745e-05, "Pretrain/Loss": 2.07064151763916, "Pretrain/Loss (Raw)": 2.108366012573242, "Pretrain/Step": 2260, "Pretrain/Step Time": 8.490747544914484} +{"Pretrain/Learning Rate": 4.4583543234844616e-05, "Pretrain/Loss": 2.0690579414367676, "Pretrain/Loss (Raw)": 1.9301613569259644, "Pretrain/Step": 2261, "Pretrain/Step Time": 8.485115559771657} +{"Pretrain/Learning Rate": 4.457826430374366e-05, "Pretrain/Loss": 2.067629337310791, "Pretrain/Loss (Raw)": 2.029283046722412, "Pretrain/Step": 2262, "Pretrain/Step Time": 8.486497309058905} +{"Pretrain/Learning Rate": 4.45729831142968e-05, "Pretrain/Loss": 2.0655970573425293, "Pretrain/Loss (Raw)": 1.7704532146453857, "Pretrain/Step": 2263, "Pretrain/Step Time": 8.487399581819773} +{"Pretrain/Learning Rate": 4.456769966711321e-05, "Pretrain/Loss": 2.0650339126586914, "Pretrain/Loss (Raw)": 2.037691354751587, "Pretrain/Step": 2264, "Pretrain/Step Time": 8.485996965318918} +{"Pretrain/Learning Rate": 4.456241396280234e-05, "Pretrain/Loss": 2.0650386810302734, "Pretrain/Loss (Raw)": 2.1649322509765625, "Pretrain/Step": 2265, "Pretrain/Step Time": 8.488089935854077} +{"Pretrain/Learning Rate": 4.4557126001973904e-05, "Pretrain/Loss": 2.066542387008667, "Pretrain/Loss (Raw)": 2.1999902725219727, "Pretrain/Step": 2266, "Pretrain/Step Time": 8.48574317060411} +{"Pretrain/Learning Rate": 4.455183578523785e-05, "Pretrain/Loss": 2.0659842491149902, "Pretrain/Loss (Raw)": 1.9837151765823364, "Pretrain/Step": 2267, "Pretrain/Step Time": 8.48493080586195} +{"Pretrain/Learning Rate": 4.4546543313204414e-05, "Pretrain/Loss": 2.06282377243042, "Pretrain/Loss (Raw)": 1.826089859008789, "Pretrain/Step": 2268, "Pretrain/Step Time": 8.490904366597533} +{"Pretrain/Learning Rate": 4.454124858648407e-05, "Pretrain/Loss": 2.063890218734741, "Pretrain/Loss (Raw)": 2.046327590942383, "Pretrain/Step": 2269, "Pretrain/Step Time": 8.487444108352065} +{"Pretrain/Learning Rate": 4.453595160568757e-05, "Pretrain/Loss": 2.059556007385254, "Pretrain/Loss (Raw)": 1.62571120262146, "Pretrain/Step": 2270, "Pretrain/Step Time": 8.487490214407444} +{"Pretrain/Learning Rate": 4.453065237142592e-05, "Pretrain/Loss": 2.060744285583496, "Pretrain/Loss (Raw)": 2.3017756938934326, "Pretrain/Step": 2271, "Pretrain/Step Time": 8.484774459153414} +{"Pretrain/Learning Rate": 4.452535088431038e-05, "Pretrain/Loss": 2.0617213249206543, "Pretrain/Loss (Raw)": 2.0985119342803955, "Pretrain/Step": 2272, "Pretrain/Step Time": 8.483408929780126} +{"Pretrain/Learning Rate": 4.452004714495248e-05, "Pretrain/Loss": 2.065126657485962, "Pretrain/Loss (Raw)": 2.299565553665161, "Pretrain/Step": 2273, "Pretrain/Step Time": 8.480373812839389} +{"Pretrain/Learning Rate": 4.4514741153964e-05, "Pretrain/Loss": 2.0649960041046143, "Pretrain/Loss (Raw)": 1.9599618911743164, "Pretrain/Step": 2274, "Pretrain/Step Time": 8.48315180838108} +{"Pretrain/Learning Rate": 4.4509432911956985e-05, "Pretrain/Loss": 2.0638041496276855, "Pretrain/Loss (Raw)": 1.8698022365570068, "Pretrain/Step": 2275, "Pretrain/Step Time": 8.48677870631218} +{"Pretrain/Learning Rate": 4.450412241954374e-05, "Pretrain/Loss": 2.064028739929199, "Pretrain/Loss (Raw)": 2.015026330947876, "Pretrain/Step": 2276, "Pretrain/Step Time": 8.482332576066256} +{"Pretrain/Learning Rate": 4.449880967733683e-05, "Pretrain/Loss": 2.062485694885254, "Pretrain/Loss (Raw)": 1.912123680114746, "Pretrain/Step": 2277, "Pretrain/Step Time": 8.481929674744606} +{"Pretrain/Learning Rate": 4.449349468594908e-05, "Pretrain/Loss": 2.062910795211792, "Pretrain/Loss (Raw)": 2.029973268508911, "Pretrain/Step": 2278, "Pretrain/Step Time": 8.479445684701204} +{"Pretrain/Learning Rate": 4.448817744599356e-05, "Pretrain/Loss": 2.061868190765381, "Pretrain/Loss (Raw)": 2.0572237968444824, "Pretrain/Step": 2279, "Pretrain/Step Time": 8.48146934621036} +{"Pretrain/Learning Rate": 4.4482857958083625e-05, "Pretrain/Loss": 2.062110424041748, "Pretrain/Loss (Raw)": 2.006589412689209, "Pretrain/Step": 2280, "Pretrain/Step Time": 8.47962947562337} +{"Pretrain/Learning Rate": 4.447753622283287e-05, "Pretrain/Loss": 2.0631392002105713, "Pretrain/Loss (Raw)": 2.101926803588867, "Pretrain/Step": 2281, "Pretrain/Step Time": 8.480538258329034} +{"Pretrain/Learning Rate": 4.447221224085516e-05, "Pretrain/Loss": 2.062936782836914, "Pretrain/Loss (Raw)": 1.9997220039367676, "Pretrain/Step": 2282, "Pretrain/Step Time": 8.480795247480273} +{"Pretrain/Learning Rate": 4.4466886012764605e-05, "Pretrain/Loss": 2.061633586883545, "Pretrain/Loss (Raw)": 1.9958113431930542, "Pretrain/Step": 2283, "Pretrain/Step Time": 8.482217343524098} +{"Pretrain/Learning Rate": 4.4461557539175594e-05, "Pretrain/Loss": 2.0620484352111816, "Pretrain/Loss (Raw)": 2.112128257751465, "Pretrain/Step": 2284, "Pretrain/Step Time": 8.485667603090405} +{"Pretrain/Learning Rate": 4.445622682070275e-05, "Pretrain/Loss": 2.0610787868499756, "Pretrain/Loss (Raw)": 2.087012529373169, "Pretrain/Step": 2285, "Pretrain/Step Time": 8.485669137910008} +{"Pretrain/Learning Rate": 4.445089385796099e-05, "Pretrain/Loss": 2.0592739582061768, "Pretrain/Loss (Raw)": 1.9582982063293457, "Pretrain/Step": 2286, "Pretrain/Step Time": 8.485621616244316} +{"Pretrain/Learning Rate": 4.4445558651565457e-05, "Pretrain/Loss": 2.059515953063965, "Pretrain/Loss (Raw)": 2.017699956893921, "Pretrain/Step": 2287, "Pretrain/Step Time": 8.485779134556651} +{"Pretrain/Learning Rate": 4.444022120213157e-05, "Pretrain/Loss": 2.0591750144958496, "Pretrain/Loss (Raw)": 1.9908719062805176, "Pretrain/Step": 2288, "Pretrain/Step Time": 8.481920579448342} +{"Pretrain/Learning Rate": 4.4434881510274994e-05, "Pretrain/Loss": 2.06062912940979, "Pretrain/Loss (Raw)": 2.1014552116394043, "Pretrain/Step": 2289, "Pretrain/Step Time": 8.482760487124324} +{"Pretrain/Learning Rate": 4.442953957661167e-05, "Pretrain/Loss": 2.061034679412842, "Pretrain/Loss (Raw)": 2.0846481323242188, "Pretrain/Step": 2290, "Pretrain/Step Time": 8.481493417173624} +{"Pretrain/Learning Rate": 4.4424195401757776e-05, "Pretrain/Loss": 2.0615861415863037, "Pretrain/Loss (Raw)": 2.200479745864868, "Pretrain/Step": 2291, "Pretrain/Step Time": 8.482602467760444} +{"Pretrain/Learning Rate": 4.441884898632977e-05, "Pretrain/Loss": 2.060795783996582, "Pretrain/Loss (Raw)": 2.06139874458313, "Pretrain/Step": 2292, "Pretrain/Step Time": 8.483761556446552} +{"Pretrain/Learning Rate": 4.441350033094437e-05, "Pretrain/Loss": 2.0607857704162598, "Pretrain/Loss (Raw)": 2.003126621246338, "Pretrain/Step": 2293, "Pretrain/Step Time": 8.482029126957059} +{"Pretrain/Learning Rate": 4.440814943621852e-05, "Pretrain/Loss": 2.058863878250122, "Pretrain/Loss (Raw)": 1.9567654132843018, "Pretrain/Step": 2294, "Pretrain/Step Time": 8.481293888762593} +{"Pretrain/Learning Rate": 4.440279630276946e-05, "Pretrain/Loss": 2.05930233001709, "Pretrain/Loss (Raw)": 2.1606178283691406, "Pretrain/Step": 2295, "Pretrain/Step Time": 8.482140436768532} +{"Pretrain/Learning Rate": 4.439744093121465e-05, "Pretrain/Loss": 2.0583581924438477, "Pretrain/Loss (Raw)": 2.071112871170044, "Pretrain/Step": 2296, "Pretrain/Step Time": 8.48451435007155} +{"Pretrain/Learning Rate": 4.439208332217186e-05, "Pretrain/Loss": 2.056696891784668, "Pretrain/Loss (Raw)": 1.944550633430481, "Pretrain/Step": 2297, "Pretrain/Step Time": 8.480346085503697} +{"Pretrain/Learning Rate": 4.438672347625907e-05, "Pretrain/Loss": 2.057197093963623, "Pretrain/Loss (Raw)": 1.9805362224578857, "Pretrain/Step": 2298, "Pretrain/Step Time": 8.482489585876465} +{"Pretrain/Learning Rate": 4.4381361394094535e-05, "Pretrain/Loss": 2.0582478046417236, "Pretrain/Loss (Raw)": 2.0100433826446533, "Pretrain/Step": 2299, "Pretrain/Step Time": 8.477850640192628} +{"Pretrain/Learning Rate": 4.437599707629678e-05, "Pretrain/Loss": 2.05887508392334, "Pretrain/Loss (Raw)": 2.1967523097991943, "Pretrain/Step": 2300, "Pretrain/Step Time": 8.478749653324485} +{"Pretrain/Learning Rate": 4.437063052348457e-05, "Pretrain/Loss": 2.057473659515381, "Pretrain/Loss (Raw)": 1.9926542043685913, "Pretrain/Step": 2301, "Pretrain/Step Time": 8.478511391207576} +{"Pretrain/Learning Rate": 4.436526173627693e-05, "Pretrain/Loss": 2.056029796600342, "Pretrain/Loss (Raw)": 1.9784986972808838, "Pretrain/Step": 2302, "Pretrain/Step Time": 8.481190321967006} +{"Pretrain/Learning Rate": 4.435989071529316e-05, "Pretrain/Loss": 2.057279586791992, "Pretrain/Loss (Raw)": 2.0601909160614014, "Pretrain/Step": 2303, "Pretrain/Step Time": 8.482078827917576} +{"Pretrain/Learning Rate": 4.43545174611528e-05, "Pretrain/Loss": 2.054713726043701, "Pretrain/Loss (Raw)": 1.8392868041992188, "Pretrain/Step": 2304, "Pretrain/Step Time": 8.47854171693325} +{"Pretrain/Learning Rate": 4.434914197447565e-05, "Pretrain/Loss": 2.0550947189331055, "Pretrain/Loss (Raw)": 1.9608510732650757, "Pretrain/Step": 2305, "Pretrain/Step Time": 8.477423008531332} +{"Pretrain/Learning Rate": 4.4343764255881784e-05, "Pretrain/Loss": 2.052462100982666, "Pretrain/Loss (Raw)": 1.919290542602539, "Pretrain/Step": 2306, "Pretrain/Step Time": 8.481188111007214} +{"Pretrain/Learning Rate": 4.433838430599149e-05, "Pretrain/Loss": 2.0525739192962646, "Pretrain/Loss (Raw)": 2.0493266582489014, "Pretrain/Step": 2307, "Pretrain/Step Time": 8.479055784642696} +{"Pretrain/Learning Rate": 4.433300212542537e-05, "Pretrain/Loss": 2.052686929702759, "Pretrain/Loss (Raw)": 2.008486270904541, "Pretrain/Step": 2308, "Pretrain/Step Time": 8.47984155640006} +{"Pretrain/Learning Rate": 4.432761771480426e-05, "Pretrain/Loss": 2.052535057067871, "Pretrain/Loss (Raw)": 2.073896646499634, "Pretrain/Step": 2309, "Pretrain/Step Time": 8.480863217264414} +{"Pretrain/Learning Rate": 4.4322231074749227e-05, "Pretrain/Loss": 2.0516180992126465, "Pretrain/Loss (Raw)": 2.0637617111206055, "Pretrain/Step": 2310, "Pretrain/Step Time": 8.4841312430799} +{"Pretrain/Learning Rate": 4.431684220588163e-05, "Pretrain/Loss": 2.050924301147461, "Pretrain/Loss (Raw)": 1.930500864982605, "Pretrain/Step": 2311, "Pretrain/Step Time": 8.485058227553964} +{"Pretrain/Learning Rate": 4.4311451108823076e-05, "Pretrain/Loss": 2.0518360137939453, "Pretrain/Loss (Raw)": 2.2003626823425293, "Pretrain/Step": 2312, "Pretrain/Step Time": 8.484680140390992} +{"Pretrain/Learning Rate": 4.4306057784195423e-05, "Pretrain/Loss": 2.051795482635498, "Pretrain/Loss (Raw)": 2.101583957672119, "Pretrain/Step": 2313, "Pretrain/Step Time": 8.484773077070713} +{"Pretrain/Learning Rate": 4.430066223262079e-05, "Pretrain/Loss": 2.053004503250122, "Pretrain/Loss (Raw)": 2.1269826889038086, "Pretrain/Step": 2314, "Pretrain/Step Time": 8.482154546305537} +{"Pretrain/Learning Rate": 4.4295264454721544e-05, "Pretrain/Loss": 2.0513036251068115, "Pretrain/Loss (Raw)": 1.8571608066558838, "Pretrain/Step": 2315, "Pretrain/Step Time": 8.482979940250516} +{"Pretrain/Learning Rate": 4.4289864451120335e-05, "Pretrain/Loss": 2.050250291824341, "Pretrain/Loss (Raw)": 2.083805561065674, "Pretrain/Step": 2316, "Pretrain/Step Time": 8.484097450971603} +{"Pretrain/Learning Rate": 4.4284462222440036e-05, "Pretrain/Loss": 2.0495738983154297, "Pretrain/Loss (Raw)": 2.120746612548828, "Pretrain/Step": 2317, "Pretrain/Step Time": 8.484869200736284} +{"Pretrain/Learning Rate": 4.427905776930379e-05, "Pretrain/Loss": 2.049415349960327, "Pretrain/Loss (Raw)": 2.0925753116607666, "Pretrain/Step": 2318, "Pretrain/Step Time": 8.49042090214789} +{"Pretrain/Learning Rate": 4.4273651092335016e-05, "Pretrain/Loss": 2.050662040710449, "Pretrain/Loss (Raw)": 2.0116522312164307, "Pretrain/Step": 2319, "Pretrain/Step Time": 8.49299916997552} +{"Pretrain/Learning Rate": 4.426824219215736e-05, "Pretrain/Loss": 2.0516889095306396, "Pretrain/Loss (Raw)": 1.966517686843872, "Pretrain/Step": 2320, "Pretrain/Step Time": 8.48965634033084} +{"Pretrain/Learning Rate": 4.426283106939474e-05, "Pretrain/Loss": 2.0526065826416016, "Pretrain/Loss (Raw)": 2.159348487854004, "Pretrain/Step": 2321, "Pretrain/Step Time": 8.49115951359272} +{"Pretrain/Learning Rate": 4.4257417724671314e-05, "Pretrain/Loss": 2.051903247833252, "Pretrain/Loss (Raw)": 2.0521228313446045, "Pretrain/Step": 2322, "Pretrain/Step Time": 8.486255949363112} +{"Pretrain/Learning Rate": 4.425200215861153e-05, "Pretrain/Loss": 2.049135684967041, "Pretrain/Loss (Raw)": 1.8804954290390015, "Pretrain/Step": 2323, "Pretrain/Step Time": 8.487208273261786} +{"Pretrain/Learning Rate": 4.424658437184006e-05, "Pretrain/Loss": 2.047457456588745, "Pretrain/Loss (Raw)": 2.0095632076263428, "Pretrain/Step": 2324, "Pretrain/Step Time": 8.490334061905742} +{"Pretrain/Learning Rate": 4.424116436498185e-05, "Pretrain/Loss": 2.047163486480713, "Pretrain/Loss (Raw)": 2.052405834197998, "Pretrain/Step": 2325, "Pretrain/Step Time": 8.490851953625679} +{"Pretrain/Learning Rate": 4.423574213866208e-05, "Pretrain/Loss": 2.0483756065368652, "Pretrain/Loss (Raw)": 1.9773932695388794, "Pretrain/Step": 2326, "Pretrain/Step Time": 8.490510677918792} +{"Pretrain/Learning Rate": 4.423031769350623e-05, "Pretrain/Loss": 2.0484907627105713, "Pretrain/Loss (Raw)": 2.1526296138763428, "Pretrain/Step": 2327, "Pretrain/Step Time": 8.492760568857193} +{"Pretrain/Learning Rate": 4.4224891030139986e-05, "Pretrain/Loss": 2.049572467803955, "Pretrain/Loss (Raw)": 2.0749940872192383, "Pretrain/Step": 2328, "Pretrain/Step Time": 8.492245599627495} +{"Pretrain/Learning Rate": 4.421946214918932e-05, "Pretrain/Loss": 2.050154685974121, "Pretrain/Loss (Raw)": 2.168426036834717, "Pretrain/Step": 2329, "Pretrain/Step Time": 8.48771726153791} +{"Pretrain/Learning Rate": 4.4214031051280444e-05, "Pretrain/Loss": 2.0506138801574707, "Pretrain/Loss (Raw)": 2.054241418838501, "Pretrain/Step": 2330, "Pretrain/Step Time": 8.491242064163089} +{"Pretrain/Learning Rate": 4.4208597737039845e-05, "Pretrain/Loss": 2.0494537353515625, "Pretrain/Loss (Raw)": 1.9797050952911377, "Pretrain/Step": 2331, "Pretrain/Step Time": 8.494226271286607} +{"Pretrain/Learning Rate": 4.420316220709424e-05, "Pretrain/Loss": 2.051302909851074, "Pretrain/Loss (Raw)": 2.344622850418091, "Pretrain/Step": 2332, "Pretrain/Step Time": 8.49238353408873} +{"Pretrain/Learning Rate": 4.419772446207063e-05, "Pretrain/Loss": 2.049948215484619, "Pretrain/Loss (Raw)": 1.9143028259277344, "Pretrain/Step": 2333, "Pretrain/Step Time": 8.493071116507053} +{"Pretrain/Learning Rate": 4.4192284502596245e-05, "Pretrain/Loss": 2.0508670806884766, "Pretrain/Loss (Raw)": 2.17852520942688, "Pretrain/Step": 2334, "Pretrain/Step Time": 8.496723582968116} +{"Pretrain/Learning Rate": 4.41868423292986e-05, "Pretrain/Loss": 2.0512614250183105, "Pretrain/Loss (Raw)": 2.0720200538635254, "Pretrain/Step": 2335, "Pretrain/Step Time": 8.49108967743814} +{"Pretrain/Learning Rate": 4.418139794280541e-05, "Pretrain/Loss": 2.051950454711914, "Pretrain/Loss (Raw)": 2.089937210083008, "Pretrain/Step": 2336, "Pretrain/Step Time": 8.494721308350563} +{"Pretrain/Learning Rate": 4.4175951343744725e-05, "Pretrain/Loss": 2.0493569374084473, "Pretrain/Loss (Raw)": 1.7891792058944702, "Pretrain/Step": 2337, "Pretrain/Step Time": 8.489595502614975} +{"Pretrain/Learning Rate": 4.417050253274479e-05, "Pretrain/Loss": 2.0498499870300293, "Pretrain/Loss (Raw)": 2.100348711013794, "Pretrain/Step": 2338, "Pretrain/Step Time": 8.488045083358884} +{"Pretrain/Learning Rate": 4.4165051510434124e-05, "Pretrain/Loss": 2.049531936645508, "Pretrain/Loss (Raw)": 2.1085762977600098, "Pretrain/Step": 2339, "Pretrain/Step Time": 8.490332022309303} +{"Pretrain/Learning Rate": 4.41595982774415e-05, "Pretrain/Loss": 2.049722194671631, "Pretrain/Loss (Raw)": 2.0790584087371826, "Pretrain/Step": 2340, "Pretrain/Step Time": 8.491597091779113} +{"Pretrain/Learning Rate": 4.4154142834395954e-05, "Pretrain/Loss": 2.0495991706848145, "Pretrain/Loss (Raw)": 1.9014369249343872, "Pretrain/Step": 2341, "Pretrain/Step Time": 8.487298857420683} +{"Pretrain/Learning Rate": 4.414868518192675e-05, "Pretrain/Loss": 2.049515724182129, "Pretrain/Loss (Raw)": 2.0475361347198486, "Pretrain/Step": 2342, "Pretrain/Step Time": 8.488249802961946} +{"Pretrain/Learning Rate": 4.414322532066345e-05, "Pretrain/Loss": 2.048006296157837, "Pretrain/Loss (Raw)": 1.955930233001709, "Pretrain/Step": 2343, "Pretrain/Step Time": 8.491750357672572} +{"Pretrain/Learning Rate": 4.4137763251235835e-05, "Pretrain/Loss": 2.045872449874878, "Pretrain/Loss (Raw)": 1.8487002849578857, "Pretrain/Step": 2344, "Pretrain/Step Time": 8.488706225529313} +{"Pretrain/Learning Rate": 4.413229897427396e-05, "Pretrain/Loss": 2.0450382232666016, "Pretrain/Loss (Raw)": 1.9794830083847046, "Pretrain/Step": 2345, "Pretrain/Step Time": 8.487800614908338} +{"Pretrain/Learning Rate": 4.412683249040811e-05, "Pretrain/Loss": 2.0466079711914062, "Pretrain/Loss (Raw)": 2.113173246383667, "Pretrain/Step": 2346, "Pretrain/Step Time": 8.487641260027885} +{"Pretrain/Learning Rate": 4.4121363800268854e-05, "Pretrain/Loss": 2.0450546741485596, "Pretrain/Loss (Raw)": 1.8377082347869873, "Pretrain/Step": 2347, "Pretrain/Step Time": 8.48547537997365} +{"Pretrain/Learning Rate": 4.411589290448701e-05, "Pretrain/Loss": 2.046705722808838, "Pretrain/Loss (Raw)": 2.303356409072876, "Pretrain/Step": 2348, "Pretrain/Step Time": 8.48426024056971} +{"Pretrain/Learning Rate": 4.4110419803693635e-05, "Pretrain/Loss": 2.0464282035827637, "Pretrain/Loss (Raw)": 1.9838110208511353, "Pretrain/Step": 2349, "Pretrain/Step Time": 8.486411331221461} +{"Pretrain/Learning Rate": 4.4104944498520054e-05, "Pretrain/Loss": 2.046113967895508, "Pretrain/Loss (Raw)": 2.0577924251556396, "Pretrain/Step": 2350, "Pretrain/Step Time": 8.488128487020731} +{"Pretrain/Learning Rate": 4.4099466989597836e-05, "Pretrain/Loss": 2.0449562072753906, "Pretrain/Loss (Raw)": 1.9917062520980835, "Pretrain/Step": 2351, "Pretrain/Step Time": 8.491071151569486} +{"Pretrain/Learning Rate": 4.409398727755882e-05, "Pretrain/Loss": 2.043182849884033, "Pretrain/Loss (Raw)": 1.9651411771774292, "Pretrain/Step": 2352, "Pretrain/Step Time": 8.491268316283822} +{"Pretrain/Learning Rate": 4.408850536303507e-05, "Pretrain/Loss": 2.0449013710021973, "Pretrain/Loss (Raw)": 2.2890071868896484, "Pretrain/Step": 2353, "Pretrain/Step Time": 8.488382356241345} +{"Pretrain/Learning Rate": 4.4083021246658944e-05, "Pretrain/Loss": 2.044085741043091, "Pretrain/Loss (Raw)": 2.051848888397217, "Pretrain/Step": 2354, "Pretrain/Step Time": 8.486778639256954} +{"Pretrain/Learning Rate": 4.4077534929063025e-05, "Pretrain/Loss": 2.0457606315612793, "Pretrain/Loss (Raw)": 2.274169683456421, "Pretrain/Step": 2355, "Pretrain/Step Time": 8.488438688218594} +{"Pretrain/Learning Rate": 4.4072046410880145e-05, "Pretrain/Loss": 2.0450520515441895, "Pretrain/Loss (Raw)": 2.106158971786499, "Pretrain/Step": 2356, "Pretrain/Step Time": 8.487312192097306} +{"Pretrain/Learning Rate": 4.406655569274342e-05, "Pretrain/Loss": 2.045139789581299, "Pretrain/Loss (Raw)": 2.1086130142211914, "Pretrain/Step": 2357, "Pretrain/Step Time": 8.488389790058136} +{"Pretrain/Learning Rate": 4.40610627752862e-05, "Pretrain/Loss": 2.044290781021118, "Pretrain/Loss (Raw)": 2.0646286010742188, "Pretrain/Step": 2358, "Pretrain/Step Time": 8.486152095720172} +{"Pretrain/Learning Rate": 4.405556765914208e-05, "Pretrain/Loss": 2.046814441680908, "Pretrain/Loss (Raw)": 2.1997950077056885, "Pretrain/Step": 2359, "Pretrain/Step Time": 8.486614486202598} +{"Pretrain/Learning Rate": 4.405007034494494e-05, "Pretrain/Loss": 2.0477066040039062, "Pretrain/Loss (Raw)": 2.0592033863067627, "Pretrain/Step": 2360, "Pretrain/Step Time": 8.484693856909871} +{"Pretrain/Learning Rate": 4.404457083332886e-05, "Pretrain/Loss": 2.04648756980896, "Pretrain/Loss (Raw)": 1.9803860187530518, "Pretrain/Step": 2361, "Pretrain/Step Time": 8.48946401104331} +{"Pretrain/Learning Rate": 4.4039069124928244e-05, "Pretrain/Loss": 2.0468716621398926, "Pretrain/Loss (Raw)": 2.1590144634246826, "Pretrain/Step": 2362, "Pretrain/Step Time": 8.482678508386016} +{"Pretrain/Learning Rate": 4.4033565220377694e-05, "Pretrain/Loss": 2.0466833114624023, "Pretrain/Loss (Raw)": 2.0223000049591064, "Pretrain/Step": 2363, "Pretrain/Step Time": 8.482218232005835} +{"Pretrain/Learning Rate": 4.402805912031208e-05, "Pretrain/Loss": 2.0462679862976074, "Pretrain/Loss (Raw)": 2.1512808799743652, "Pretrain/Step": 2364, "Pretrain/Step Time": 8.481330547481775} +{"Pretrain/Learning Rate": 4.4022550825366526e-05, "Pretrain/Loss": 2.0457077026367188, "Pretrain/Loss (Raw)": 2.0039851665496826, "Pretrain/Step": 2365, "Pretrain/Step Time": 8.479195488616824} +{"Pretrain/Learning Rate": 4.401704033617643e-05, "Pretrain/Loss": 2.047264575958252, "Pretrain/Loss (Raw)": 2.2644968032836914, "Pretrain/Step": 2366, "Pretrain/Step Time": 8.476621970534325} +{"Pretrain/Learning Rate": 4.4011527653377415e-05, "Pretrain/Loss": 2.0472657680511475, "Pretrain/Loss (Raw)": 2.0983524322509766, "Pretrain/Step": 2367, "Pretrain/Step Time": 8.480192866176367} +{"Pretrain/Learning Rate": 4.400601277760536e-05, "Pretrain/Loss": 2.0475330352783203, "Pretrain/Loss (Raw)": 2.0173494815826416, "Pretrain/Step": 2368, "Pretrain/Step Time": 8.484578305855393} +{"Pretrain/Learning Rate": 4.400049570949641e-05, "Pretrain/Loss": 2.045600414276123, "Pretrain/Loss (Raw)": 1.8794341087341309, "Pretrain/Step": 2369, "Pretrain/Step Time": 8.482755661010742} +{"Pretrain/Learning Rate": 4.399497644968696e-05, "Pretrain/Loss": 2.044158935546875, "Pretrain/Loss (Raw)": 1.9087055921554565, "Pretrain/Step": 2370, "Pretrain/Step Time": 8.484563760459423} +{"Pretrain/Learning Rate": 4.398945499881366e-05, "Pretrain/Loss": 2.043889045715332, "Pretrain/Loss (Raw)": 2.0716800689697266, "Pretrain/Step": 2371, "Pretrain/Step Time": 8.482443170621991} +{"Pretrain/Learning Rate": 4.3983931357513385e-05, "Pretrain/Loss": 2.044132709503174, "Pretrain/Loss (Raw)": 2.0281789302825928, "Pretrain/Step": 2372, "Pretrain/Step Time": 8.479633659124374} +{"Pretrain/Learning Rate": 4.3978405526423305e-05, "Pretrain/Loss": 2.0450143814086914, "Pretrain/Loss (Raw)": 2.124738931655884, "Pretrain/Step": 2373, "Pretrain/Step Time": 8.477642983198166} +{"Pretrain/Learning Rate": 4.397287750618082e-05, "Pretrain/Loss": 2.0471558570861816, "Pretrain/Loss (Raw)": 2.306100845336914, "Pretrain/Step": 2374, "Pretrain/Step Time": 8.480566231533885} +{"Pretrain/Learning Rate": 4.3967347297423575e-05, "Pretrain/Loss": 2.0496139526367188, "Pretrain/Loss (Raw)": 2.090087890625, "Pretrain/Step": 2375, "Pretrain/Step Time": 8.47661749087274} +{"Pretrain/Learning Rate": 4.3961814900789495e-05, "Pretrain/Loss": 2.0487749576568604, "Pretrain/Loss (Raw)": 2.0406763553619385, "Pretrain/Step": 2376, "Pretrain/Step Time": 8.478418253362179} +{"Pretrain/Learning Rate": 4.395628031691672e-05, "Pretrain/Loss": 2.0467474460601807, "Pretrain/Loss (Raw)": 2.001343250274658, "Pretrain/Step": 2377, "Pretrain/Step Time": 8.47664419002831} +{"Pretrain/Learning Rate": 4.395074354644368e-05, "Pretrain/Loss": 2.0460009574890137, "Pretrain/Loss (Raw)": 2.0561981201171875, "Pretrain/Step": 2378, "Pretrain/Step Time": 8.472440913319588} +{"Pretrain/Learning Rate": 4.3945204590009024e-05, "Pretrain/Loss": 2.044612169265747, "Pretrain/Loss (Raw)": 2.073575973510742, "Pretrain/Step": 2379, "Pretrain/Step Time": 8.474919265136123} +{"Pretrain/Learning Rate": 4.3939663448251687e-05, "Pretrain/Loss": 2.0459704399108887, "Pretrain/Loss (Raw)": 2.0990586280822754, "Pretrain/Step": 2380, "Pretrain/Step Time": 8.469265896826982} +{"Pretrain/Learning Rate": 4.393412012181082e-05, "Pretrain/Loss": 2.047689437866211, "Pretrain/Loss (Raw)": 2.0947837829589844, "Pretrain/Step": 2381, "Pretrain/Step Time": 8.469218742102385} +{"Pretrain/Learning Rate": 4.3928574611325844e-05, "Pretrain/Loss": 2.04640531539917, "Pretrain/Loss (Raw)": 2.070756673812866, "Pretrain/Step": 2382, "Pretrain/Step Time": 8.471761647611856} +{"Pretrain/Learning Rate": 4.392302691743645e-05, "Pretrain/Loss": 2.048698902130127, "Pretrain/Loss (Raw)": 2.2724125385284424, "Pretrain/Step": 2383, "Pretrain/Step Time": 8.470956932753325} +{"Pretrain/Learning Rate": 4.3917477040782554e-05, "Pretrain/Loss": 2.0475821495056152, "Pretrain/Loss (Raw)": 1.9485993385314941, "Pretrain/Step": 2384, "Pretrain/Step Time": 8.47160635329783} +{"Pretrain/Learning Rate": 4.3911924982004315e-05, "Pretrain/Loss": 2.0467774868011475, "Pretrain/Loss (Raw)": 1.9159629344940186, "Pretrain/Step": 2385, "Pretrain/Step Time": 8.476445689797401} +{"Pretrain/Learning Rate": 4.3906370741742186e-05, "Pretrain/Loss": 2.0461301803588867, "Pretrain/Loss (Raw)": 2.04013991355896, "Pretrain/Step": 2386, "Pretrain/Step Time": 8.472879905253649} +{"Pretrain/Learning Rate": 4.390081432063683e-05, "Pretrain/Loss": 2.046481132507324, "Pretrain/Loss (Raw)": 2.106520891189575, "Pretrain/Step": 2387, "Pretrain/Step Time": 8.47297152876854} +{"Pretrain/Learning Rate": 4.389525571932919e-05, "Pretrain/Loss": 2.045912981033325, "Pretrain/Loss (Raw)": 2.0356462001800537, "Pretrain/Step": 2388, "Pretrain/Step Time": 8.477352794259787} +{"Pretrain/Learning Rate": 4.388969493846044e-05, "Pretrain/Loss": 2.046523094177246, "Pretrain/Loss (Raw)": 2.0082614421844482, "Pretrain/Step": 2389, "Pretrain/Step Time": 8.476993020623922} +{"Pretrain/Learning Rate": 4.388413197867202e-05, "Pretrain/Loss": 2.0468664169311523, "Pretrain/Loss (Raw)": 2.073202133178711, "Pretrain/Step": 2390, "Pretrain/Step Time": 8.474813496693969} +{"Pretrain/Learning Rate": 4.3878566840605604e-05, "Pretrain/Loss": 2.048492908477783, "Pretrain/Loss (Raw)": 1.9786970615386963, "Pretrain/Step": 2391, "Pretrain/Step Time": 8.477260509505868} +{"Pretrain/Learning Rate": 4.387299952490315e-05, "Pretrain/Loss": 2.049497604370117, "Pretrain/Loss (Raw)": 2.1662590503692627, "Pretrain/Step": 2392, "Pretrain/Step Time": 8.478342728689313} +{"Pretrain/Learning Rate": 4.3867430032206823e-05, "Pretrain/Loss": 2.048704147338867, "Pretrain/Loss (Raw)": 2.063354015350342, "Pretrain/Step": 2393, "Pretrain/Step Time": 8.478583835065365} +{"Pretrain/Learning Rate": 4.386185836315908e-05, "Pretrain/Loss": 2.046663284301758, "Pretrain/Loss (Raw)": 1.9387975931167603, "Pretrain/Step": 2394, "Pretrain/Step Time": 8.481471262872219} +{"Pretrain/Learning Rate": 4.3856284518402594e-05, "Pretrain/Loss": 2.048020362854004, "Pretrain/Loss (Raw)": 2.1574130058288574, "Pretrain/Step": 2395, "Pretrain/Step Time": 8.479535762220621} +{"Pretrain/Learning Rate": 4.385070849858033e-05, "Pretrain/Loss": 2.0469319820404053, "Pretrain/Loss (Raw)": 1.6867802143096924, "Pretrain/Step": 2396, "Pretrain/Step Time": 8.478685829788446} +{"Pretrain/Learning Rate": 4.3845130304335455e-05, "Pretrain/Loss": 2.047799587249756, "Pretrain/Loss (Raw)": 2.1573526859283447, "Pretrain/Step": 2397, "Pretrain/Step Time": 8.481765639036894} +{"Pretrain/Learning Rate": 4.383954993631142e-05, "Pretrain/Loss": 2.049800157546997, "Pretrain/Loss (Raw)": 1.8817709684371948, "Pretrain/Step": 2398, "Pretrain/Step Time": 8.482222948223352} +{"Pretrain/Learning Rate": 4.383396739515192e-05, "Pretrain/Loss": 2.0483274459838867, "Pretrain/Loss (Raw)": 2.113325595855713, "Pretrain/Step": 2399, "Pretrain/Step Time": 8.482948584482074} +{"Pretrain/Learning Rate": 4.382838268150091e-05, "Pretrain/Loss": 2.047966480255127, "Pretrain/Loss (Raw)": 2.052297830581665, "Pretrain/Step": 2400, "Pretrain/Step Time": 8.486433720216155} +{"Pretrain/Learning Rate": 4.382279579600256e-05, "Pretrain/Loss": 2.046696901321411, "Pretrain/Loss (Raw)": 2.137044906616211, "Pretrain/Step": 2401, "Pretrain/Step Time": 8.48829435557127} +{"Pretrain/Learning Rate": 4.381720673930134e-05, "Pretrain/Loss": 2.047801971435547, "Pretrain/Loss (Raw)": 2.1014113426208496, "Pretrain/Step": 2402, "Pretrain/Step Time": 8.486123813316226} +{"Pretrain/Learning Rate": 4.381161551204194e-05, "Pretrain/Loss": 2.0486526489257812, "Pretrain/Loss (Raw)": 1.9786806106567383, "Pretrain/Step": 2403, "Pretrain/Step Time": 8.484445199370384} +{"Pretrain/Learning Rate": 4.3806022114869296e-05, "Pretrain/Loss": 2.0496177673339844, "Pretrain/Loss (Raw)": 2.1385722160339355, "Pretrain/Step": 2404, "Pretrain/Step Time": 8.48367183841765} +{"Pretrain/Learning Rate": 4.3800426548428605e-05, "Pretrain/Loss": 2.0497963428497314, "Pretrain/Loss (Raw)": 1.9349730014801025, "Pretrain/Step": 2405, "Pretrain/Step Time": 8.48505767993629} +{"Pretrain/Learning Rate": 4.379482881336532e-05, "Pretrain/Loss": 2.0508389472961426, "Pretrain/Loss (Raw)": 2.1634318828582764, "Pretrain/Step": 2406, "Pretrain/Step Time": 8.48309457115829} +{"Pretrain/Learning Rate": 4.3789228910325134e-05, "Pretrain/Loss": 2.051743268966675, "Pretrain/Loss (Raw)": 2.1729815006256104, "Pretrain/Step": 2407, "Pretrain/Step Time": 8.481409160420299} +{"Pretrain/Learning Rate": 4.3783626839954005e-05, "Pretrain/Loss": 2.051297664642334, "Pretrain/Loss (Raw)": 1.9495471715927124, "Pretrain/Step": 2408, "Pretrain/Step Time": 8.484399039298296} +{"Pretrain/Learning Rate": 4.3778022602898116e-05, "Pretrain/Loss": 2.051128625869751, "Pretrain/Loss (Raw)": 2.08028244972229, "Pretrain/Step": 2409, "Pretrain/Step Time": 8.484789868816733} +{"Pretrain/Learning Rate": 4.3772416199803924e-05, "Pretrain/Loss": 2.052271842956543, "Pretrain/Loss (Raw)": 2.1460628509521484, "Pretrain/Step": 2410, "Pretrain/Step Time": 8.48287413828075} +{"Pretrain/Learning Rate": 4.3766807631318106e-05, "Pretrain/Loss": 2.0539774894714355, "Pretrain/Loss (Raw)": 2.2141506671905518, "Pretrain/Step": 2411, "Pretrain/Step Time": 8.484788140282035} +{"Pretrain/Learning Rate": 4.376119689808764e-05, "Pretrain/Loss": 2.0545990467071533, "Pretrain/Loss (Raw)": 2.191657066345215, "Pretrain/Step": 2412, "Pretrain/Step Time": 8.480676302686334} +{"Pretrain/Learning Rate": 4.3755584000759695e-05, "Pretrain/Loss": 2.0529260635375977, "Pretrain/Loss (Raw)": 1.8728805780410767, "Pretrain/Step": 2413, "Pretrain/Step Time": 8.482472281903028} +{"Pretrain/Learning Rate": 4.3749968939981734e-05, "Pretrain/Loss": 2.054743528366089, "Pretrain/Loss (Raw)": 2.1909165382385254, "Pretrain/Step": 2414, "Pretrain/Step Time": 8.483170110732317} +{"Pretrain/Learning Rate": 4.374435171640144e-05, "Pretrain/Loss": 2.0551066398620605, "Pretrain/Loss (Raw)": 2.064199447631836, "Pretrain/Step": 2415, "Pretrain/Step Time": 8.484485387802124} +{"Pretrain/Learning Rate": 4.373873233066676e-05, "Pretrain/Loss": 2.054885149002075, "Pretrain/Loss (Raw)": 1.9625170230865479, "Pretrain/Step": 2416, "Pretrain/Step Time": 8.483938781544566} +{"Pretrain/Learning Rate": 4.373311078342589e-05, "Pretrain/Loss": 2.054638385772705, "Pretrain/Loss (Raw)": 2.0698912143707275, "Pretrain/Step": 2417, "Pretrain/Step Time": 8.483981881290674} +{"Pretrain/Learning Rate": 4.3727487075327286e-05, "Pretrain/Loss": 2.0553231239318848, "Pretrain/Loss (Raw)": 2.172255277633667, "Pretrain/Step": 2418, "Pretrain/Step Time": 8.483455104753375} +{"Pretrain/Learning Rate": 4.372186120701962e-05, "Pretrain/Loss": 2.054227352142334, "Pretrain/Loss (Raw)": 2.060248374938965, "Pretrain/Step": 2419, "Pretrain/Step Time": 8.485686900094151} +{"Pretrain/Learning Rate": 4.371623317915184e-05, "Pretrain/Loss": 2.053610324859619, "Pretrain/Loss (Raw)": 1.9823940992355347, "Pretrain/Step": 2420, "Pretrain/Step Time": 8.483278952538967} +{"Pretrain/Learning Rate": 4.371060299237315e-05, "Pretrain/Loss": 2.056123971939087, "Pretrain/Loss (Raw)": 2.32490611076355, "Pretrain/Step": 2421, "Pretrain/Step Time": 8.485353451222181} +{"Pretrain/Learning Rate": 4.370497064733298e-05, "Pretrain/Loss": 2.057804822921753, "Pretrain/Loss (Raw)": 2.171879768371582, "Pretrain/Step": 2422, "Pretrain/Step Time": 8.483578778803349} +{"Pretrain/Learning Rate": 4.369933614468101e-05, "Pretrain/Loss": 2.0569815635681152, "Pretrain/Loss (Raw)": 2.055279016494751, "Pretrain/Step": 2423, "Pretrain/Step Time": 8.485557209700346} +{"Pretrain/Learning Rate": 4.369369948506719e-05, "Pretrain/Loss": 2.0562005043029785, "Pretrain/Loss (Raw)": 1.9711198806762695, "Pretrain/Step": 2424, "Pretrain/Step Time": 8.488433236256242} +{"Pretrain/Learning Rate": 4.368806066914171e-05, "Pretrain/Loss": 2.0558738708496094, "Pretrain/Loss (Raw)": 1.9027562141418457, "Pretrain/Step": 2425, "Pretrain/Step Time": 8.48830241151154} +{"Pretrain/Learning Rate": 4.368241969755499e-05, "Pretrain/Loss": 2.056344509124756, "Pretrain/Loss (Raw)": 2.0407602787017822, "Pretrain/Step": 2426, "Pretrain/Step Time": 8.487201202660799} +{"Pretrain/Learning Rate": 4.3676776570957726e-05, "Pretrain/Loss": 2.0570871829986572, "Pretrain/Loss (Raw)": 2.105100393295288, "Pretrain/Step": 2427, "Pretrain/Step Time": 8.48753266222775} +{"Pretrain/Learning Rate": 4.367113129000085e-05, "Pretrain/Loss": 2.0563669204711914, "Pretrain/Loss (Raw)": 2.104569435119629, "Pretrain/Step": 2428, "Pretrain/Step Time": 8.489346908405423} +{"Pretrain/Learning Rate": 4.366548385533554e-05, "Pretrain/Loss": 2.0562820434570312, "Pretrain/Loss (Raw)": 1.9817898273468018, "Pretrain/Step": 2429, "Pretrain/Step Time": 8.490611335262656} +{"Pretrain/Learning Rate": 4.3659834267613234e-05, "Pretrain/Loss": 2.055574655532837, "Pretrain/Loss (Raw)": 1.8879356384277344, "Pretrain/Step": 2430, "Pretrain/Step Time": 8.489085426554084} +{"Pretrain/Learning Rate": 4.365418252748559e-05, "Pretrain/Loss": 2.056318759918213, "Pretrain/Loss (Raw)": 2.1554412841796875, "Pretrain/Step": 2431, "Pretrain/Step Time": 8.488716503605247} +{"Pretrain/Learning Rate": 4.3648528635604556e-05, "Pretrain/Loss": 2.059145212173462, "Pretrain/Loss (Raw)": 2.201087236404419, "Pretrain/Step": 2432, "Pretrain/Step Time": 8.490073636174202} +{"Pretrain/Learning Rate": 4.36428725926223e-05, "Pretrain/Loss": 2.0596084594726562, "Pretrain/Loss (Raw)": 2.0201480388641357, "Pretrain/Step": 2433, "Pretrain/Step Time": 8.489747248589993} +{"Pretrain/Learning Rate": 4.3637214399191234e-05, "Pretrain/Loss": 2.06008243560791, "Pretrain/Loss (Raw)": 1.9799550771713257, "Pretrain/Step": 2434, "Pretrain/Step Time": 8.48868971131742} +{"Pretrain/Learning Rate": 4.363155405596404e-05, "Pretrain/Loss": 2.060255289077759, "Pretrain/Loss (Raw)": 2.071450710296631, "Pretrain/Step": 2435, "Pretrain/Step Time": 8.492442620918155} +{"Pretrain/Learning Rate": 4.3625891563593626e-05, "Pretrain/Loss": 2.0608315467834473, "Pretrain/Loss (Raw)": 2.0822527408599854, "Pretrain/Step": 2436, "Pretrain/Step Time": 8.492296166718006} +{"Pretrain/Learning Rate": 4.3620226922733174e-05, "Pretrain/Loss": 2.059849262237549, "Pretrain/Loss (Raw)": 1.9481695890426636, "Pretrain/Step": 2437, "Pretrain/Step Time": 8.491492008790374} +{"Pretrain/Learning Rate": 4.361456013403609e-05, "Pretrain/Loss": 2.0604701042175293, "Pretrain/Loss (Raw)": 2.143188238143921, "Pretrain/Step": 2438, "Pretrain/Step Time": 8.489795865491033} +{"Pretrain/Learning Rate": 4.360889119815604e-05, "Pretrain/Loss": 2.0613749027252197, "Pretrain/Loss (Raw)": 2.0463459491729736, "Pretrain/Step": 2439, "Pretrain/Step Time": 8.486329440027475} +{"Pretrain/Learning Rate": 4.360322011574692e-05, "Pretrain/Loss": 2.059748649597168, "Pretrain/Loss (Raw)": 1.992228627204895, "Pretrain/Step": 2440, "Pretrain/Step Time": 8.487557290121913} +{"Pretrain/Learning Rate": 4.3597546887462904e-05, "Pretrain/Loss": 2.057664394378662, "Pretrain/Loss (Raw)": 1.83479642868042, "Pretrain/Step": 2441, "Pretrain/Step Time": 8.485764982178807} +{"Pretrain/Learning Rate": 4.3591871513958395e-05, "Pretrain/Loss": 2.0574941635131836, "Pretrain/Loss (Raw)": 2.105146646499634, "Pretrain/Step": 2442, "Pretrain/Step Time": 8.485824450850487} +{"Pretrain/Learning Rate": 4.3586193995888024e-05, "Pretrain/Loss": 2.0591635704040527, "Pretrain/Loss (Raw)": 2.07084059715271, "Pretrain/Step": 2443, "Pretrain/Step Time": 8.488978346809745} +{"Pretrain/Learning Rate": 4.3580514333906716e-05, "Pretrain/Loss": 2.0599284172058105, "Pretrain/Loss (Raw)": 2.1817469596862793, "Pretrain/Step": 2444, "Pretrain/Step Time": 8.488344717770815} +{"Pretrain/Learning Rate": 4.357483252866961e-05, "Pretrain/Loss": 2.0576729774475098, "Pretrain/Loss (Raw)": 1.8320305347442627, "Pretrain/Step": 2445, "Pretrain/Step Time": 8.488124810159206} +{"Pretrain/Learning Rate": 4.356914858083211e-05, "Pretrain/Loss": 2.0558249950408936, "Pretrain/Loss (Raw)": 1.8560233116149902, "Pretrain/Step": 2446, "Pretrain/Step Time": 8.483937541022897} +{"Pretrain/Learning Rate": 4.3563462491049834e-05, "Pretrain/Loss": 2.054107904434204, "Pretrain/Loss (Raw)": 1.7918819189071655, "Pretrain/Step": 2447, "Pretrain/Step Time": 8.482035152614117} +{"Pretrain/Learning Rate": 4.3557774259978685e-05, "Pretrain/Loss": 2.05446457862854, "Pretrain/Loss (Raw)": 2.0121703147888184, "Pretrain/Step": 2448, "Pretrain/Step Time": 8.481001637876034} +{"Pretrain/Learning Rate": 4.35520838882748e-05, "Pretrain/Loss": 2.053919792175293, "Pretrain/Loss (Raw)": 2.0896108150482178, "Pretrain/Step": 2449, "Pretrain/Step Time": 8.485427439212799} +{"Pretrain/Learning Rate": 4.354639137659455e-05, "Pretrain/Loss": 2.0549612045288086, "Pretrain/Loss (Raw)": 2.1854140758514404, "Pretrain/Step": 2450, "Pretrain/Step Time": 8.487690633162856} +{"Pretrain/Learning Rate": 4.354069672559458e-05, "Pretrain/Loss": 2.056948661804199, "Pretrain/Loss (Raw)": 2.1349315643310547, "Pretrain/Step": 2451, "Pretrain/Step Time": 8.489979717880487} +{"Pretrain/Learning Rate": 4.353499993593176e-05, "Pretrain/Loss": 2.058011054992676, "Pretrain/Loss (Raw)": 2.1455347537994385, "Pretrain/Step": 2452, "Pretrain/Step Time": 8.48258857615292} +{"Pretrain/Learning Rate": 4.35293010082632e-05, "Pretrain/Loss": 2.059096336364746, "Pretrain/Loss (Raw)": 2.191328763961792, "Pretrain/Step": 2453, "Pretrain/Step Time": 8.481577457860112} +{"Pretrain/Learning Rate": 4.35235999432463e-05, "Pretrain/Loss": 2.0597145557403564, "Pretrain/Loss (Raw)": 2.0564968585968018, "Pretrain/Step": 2454, "Pretrain/Step Time": 8.482941115275025} +{"Pretrain/Learning Rate": 4.3517896741538634e-05, "Pretrain/Loss": 2.059347152709961, "Pretrain/Loss (Raw)": 2.1055989265441895, "Pretrain/Step": 2455, "Pretrain/Step Time": 8.480825651437044} +{"Pretrain/Learning Rate": 4.35121914037981e-05, "Pretrain/Loss": 2.0587804317474365, "Pretrain/Loss (Raw)": 2.002464532852173, "Pretrain/Step": 2456, "Pretrain/Step Time": 8.483151402324438} +{"Pretrain/Learning Rate": 4.3506483930682785e-05, "Pretrain/Loss": 2.0576179027557373, "Pretrain/Loss (Raw)": 2.019620895385742, "Pretrain/Step": 2457, "Pretrain/Step Time": 8.48480393178761} +{"Pretrain/Learning Rate": 4.3500774322851064e-05, "Pretrain/Loss": 2.0579376220703125, "Pretrain/Loss (Raw)": 2.0951714515686035, "Pretrain/Step": 2458, "Pretrain/Step Time": 8.481312407180667} +{"Pretrain/Learning Rate": 4.349506258096152e-05, "Pretrain/Loss": 2.056609869003296, "Pretrain/Loss (Raw)": 1.8097323179244995, "Pretrain/Step": 2459, "Pretrain/Step Time": 8.480294531211257} +{"Pretrain/Learning Rate": 4.3489348705673e-05, "Pretrain/Loss": 2.055016279220581, "Pretrain/Loss (Raw)": 2.140655755996704, "Pretrain/Step": 2460, "Pretrain/Step Time": 8.483641570433974} +{"Pretrain/Learning Rate": 4.348363269764462e-05, "Pretrain/Loss": 2.057088613510132, "Pretrain/Loss (Raw)": 2.179565191268921, "Pretrain/Step": 2461, "Pretrain/Step Time": 8.48028434254229} +{"Pretrain/Learning Rate": 4.3477914557535684e-05, "Pretrain/Loss": 2.0559678077697754, "Pretrain/Loss (Raw)": 2.035064697265625, "Pretrain/Step": 2462, "Pretrain/Step Time": 8.480263957753778} +{"Pretrain/Learning Rate": 4.3472194286005815e-05, "Pretrain/Loss": 2.055083751678467, "Pretrain/Loss (Raw)": 1.9588559865951538, "Pretrain/Step": 2463, "Pretrain/Step Time": 8.480956824496388} +{"Pretrain/Learning Rate": 4.346647188371482e-05, "Pretrain/Loss": 2.0541110038757324, "Pretrain/Loss (Raw)": 1.9654000997543335, "Pretrain/Step": 2464, "Pretrain/Step Time": 8.478844976052642} +{"Pretrain/Learning Rate": 4.346074735132278e-05, "Pretrain/Loss": 2.05572772026062, "Pretrain/Loss (Raw)": 1.9961533546447754, "Pretrain/Step": 2465, "Pretrain/Step Time": 8.48211382701993} +{"Pretrain/Learning Rate": 4.345502068949002e-05, "Pretrain/Loss": 2.0558462142944336, "Pretrain/Loss (Raw)": 2.115504264831543, "Pretrain/Step": 2466, "Pretrain/Step Time": 8.483455423265696} +{"Pretrain/Learning Rate": 4.344929189887712e-05, "Pretrain/Loss": 2.054136037826538, "Pretrain/Loss (Raw)": 1.889674425125122, "Pretrain/Step": 2467, "Pretrain/Step Time": 8.481298489496112} +{"Pretrain/Learning Rate": 4.344356098014487e-05, "Pretrain/Loss": 2.0518035888671875, "Pretrain/Loss (Raw)": 1.780505657196045, "Pretrain/Step": 2468, "Pretrain/Step Time": 8.481275018304586} +{"Pretrain/Learning Rate": 4.343782793395435e-05, "Pretrain/Loss": 2.0523505210876465, "Pretrain/Loss (Raw)": 1.9714415073394775, "Pretrain/Step": 2469, "Pretrain/Step Time": 8.481685388833284} +{"Pretrain/Learning Rate": 4.3432092760966856e-05, "Pretrain/Loss": 2.0535507202148438, "Pretrain/Loss (Raw)": 2.2011404037475586, "Pretrain/Step": 2470, "Pretrain/Step Time": 8.48096957989037} +{"Pretrain/Learning Rate": 4.342635546184394e-05, "Pretrain/Loss": 2.0543713569641113, "Pretrain/Loss (Raw)": 2.0609700679779053, "Pretrain/Step": 2471, "Pretrain/Step Time": 8.478430673480034} +{"Pretrain/Learning Rate": 4.34206160372474e-05, "Pretrain/Loss": 2.056729555130005, "Pretrain/Loss (Raw)": 2.150560140609741, "Pretrain/Step": 2472, "Pretrain/Step Time": 8.481074120849371} +{"Pretrain/Learning Rate": 4.341487448783926e-05, "Pretrain/Loss": 2.054442882537842, "Pretrain/Loss (Raw)": 1.68679940700531, "Pretrain/Step": 2473, "Pretrain/Step Time": 8.480427717790008} +{"Pretrain/Learning Rate": 4.340913081428183e-05, "Pretrain/Loss": 2.054069995880127, "Pretrain/Loss (Raw)": 2.0654473304748535, "Pretrain/Step": 2474, "Pretrain/Step Time": 8.480526944622397} +{"Pretrain/Learning Rate": 4.340338501723763e-05, "Pretrain/Loss": 2.0554332733154297, "Pretrain/Loss (Raw)": 2.0122056007385254, "Pretrain/Step": 2475, "Pretrain/Step Time": 8.479769106954336} +{"Pretrain/Learning Rate": 4.339763709736944e-05, "Pretrain/Loss": 2.054410934448242, "Pretrain/Loss (Raw)": 2.172490119934082, "Pretrain/Step": 2476, "Pretrain/Step Time": 8.480509705841541} +{"Pretrain/Learning Rate": 4.3391887055340266e-05, "Pretrain/Loss": 2.055410146713257, "Pretrain/Loss (Raw)": 2.1117303371429443, "Pretrain/Step": 2477, "Pretrain/Step Time": 8.479150174185634} +{"Pretrain/Learning Rate": 4.3386134891813385e-05, "Pretrain/Loss": 2.055929183959961, "Pretrain/Loss (Raw)": 2.1241822242736816, "Pretrain/Step": 2478, "Pretrain/Step Time": 8.479106053709984} +{"Pretrain/Learning Rate": 4.338038060745231e-05, "Pretrain/Loss": 2.05625319480896, "Pretrain/Loss (Raw)": 2.0332252979278564, "Pretrain/Step": 2479, "Pretrain/Step Time": 8.481146644800901} +{"Pretrain/Learning Rate": 4.3374624202920785e-05, "Pretrain/Loss": 2.0578975677490234, "Pretrain/Loss (Raw)": 2.175583600997925, "Pretrain/Step": 2480, "Pretrain/Step Time": 8.47999314032495} +{"Pretrain/Learning Rate": 4.336886567888283e-05, "Pretrain/Loss": 2.0549097061157227, "Pretrain/Loss (Raw)": 1.9066003561019897, "Pretrain/Step": 2481, "Pretrain/Step Time": 8.480738561600447} +{"Pretrain/Learning Rate": 4.336310503600266e-05, "Pretrain/Loss": 2.0534439086914062, "Pretrain/Loss (Raw)": 1.8642315864562988, "Pretrain/Step": 2482, "Pretrain/Step Time": 8.482854532077909} +{"Pretrain/Learning Rate": 4.335734227494478e-05, "Pretrain/Loss": 2.05025577545166, "Pretrain/Loss (Raw)": 1.8660801649093628, "Pretrain/Step": 2483, "Pretrain/Step Time": 8.48016507178545} +{"Pretrain/Learning Rate": 4.3351577396373923e-05, "Pretrain/Loss": 2.049921751022339, "Pretrain/Loss (Raw)": 2.063371181488037, "Pretrain/Step": 2484, "Pretrain/Step Time": 8.47968329116702} +{"Pretrain/Learning Rate": 4.334581040095506e-05, "Pretrain/Loss": 2.049379825592041, "Pretrain/Loss (Raw)": 2.0392704010009766, "Pretrain/Step": 2485, "Pretrain/Step Time": 8.477896507829428} +{"Pretrain/Learning Rate": 4.3340041289353415e-05, "Pretrain/Loss": 2.050658702850342, "Pretrain/Loss (Raw)": 2.2283198833465576, "Pretrain/Step": 2486, "Pretrain/Step Time": 8.479924345389009} +{"Pretrain/Learning Rate": 4.333427006223445e-05, "Pretrain/Loss": 2.04990553855896, "Pretrain/Loss (Raw)": 2.103397846221924, "Pretrain/Step": 2487, "Pretrain/Step Time": 8.479311550036073} +{"Pretrain/Learning Rate": 4.332849672026388e-05, "Pretrain/Loss": 2.050457000732422, "Pretrain/Loss (Raw)": 2.1297857761383057, "Pretrain/Step": 2488, "Pretrain/Step Time": 8.483135856688023} +{"Pretrain/Learning Rate": 4.332272126410766e-05, "Pretrain/Loss": 2.050905227661133, "Pretrain/Loss (Raw)": 2.0377533435821533, "Pretrain/Step": 2489, "Pretrain/Step Time": 8.47872737981379} +{"Pretrain/Learning Rate": 4.331694369443197e-05, "Pretrain/Loss": 2.050755023956299, "Pretrain/Loss (Raw)": 2.1397807598114014, "Pretrain/Step": 2490, "Pretrain/Step Time": 8.479744354262948} +{"Pretrain/Learning Rate": 4.3311164011903274e-05, "Pretrain/Loss": 2.0525050163269043, "Pretrain/Loss (Raw)": 2.2463297843933105, "Pretrain/Step": 2491, "Pretrain/Step Time": 8.479444837197661} +{"Pretrain/Learning Rate": 4.330538221718823e-05, "Pretrain/Loss": 2.0504262447357178, "Pretrain/Loss (Raw)": 1.8851642608642578, "Pretrain/Step": 2492, "Pretrain/Step Time": 8.480049189180136} +{"Pretrain/Learning Rate": 4.3299598310953793e-05, "Pretrain/Loss": 2.0483202934265137, "Pretrain/Loss (Raw)": 1.7344486713409424, "Pretrain/Step": 2493, "Pretrain/Step Time": 8.488665103912354} +{"Pretrain/Learning Rate": 4.329381229386711e-05, "Pretrain/Loss": 2.04742431640625, "Pretrain/Loss (Raw)": 2.149803876876831, "Pretrain/Step": 2494, "Pretrain/Step Time": 8.488264134153724} +{"Pretrain/Learning Rate": 4.3288024166595614e-05, "Pretrain/Loss": 2.0461907386779785, "Pretrain/Loss (Raw)": 1.9404603242874146, "Pretrain/Step": 2495, "Pretrain/Step Time": 8.483967386186123} +{"Pretrain/Learning Rate": 4.328223392980696e-05, "Pretrain/Loss": 2.047822952270508, "Pretrain/Loss (Raw)": 2.2262346744537354, "Pretrain/Step": 2496, "Pretrain/Step Time": 8.482470471411943} +{"Pretrain/Learning Rate": 4.327644158416905e-05, "Pretrain/Loss": 2.0488927364349365, "Pretrain/Loss (Raw)": 2.0163981914520264, "Pretrain/Step": 2497, "Pretrain/Step Time": 8.484519515186548} +{"Pretrain/Learning Rate": 4.3270647130350016e-05, "Pretrain/Loss": 2.0510339736938477, "Pretrain/Loss (Raw)": 2.182803153991699, "Pretrain/Step": 2498, "Pretrain/Step Time": 8.48354977555573} +{"Pretrain/Learning Rate": 4.326485056901826e-05, "Pretrain/Loss": 2.0517354011535645, "Pretrain/Loss (Raw)": 2.1614372730255127, "Pretrain/Step": 2499, "Pretrain/Step Time": 8.486091049388051} +{"Pretrain/Learning Rate": 4.325905190084241e-05, "Pretrain/Loss": 2.0512800216674805, "Pretrain/Loss (Raw)": 1.9698718786239624, "Pretrain/Step": 2500, "Pretrain/Step Time": 8.486091997474432} +{"Pretrain/Learning Rate": 4.325325112649134e-05, "Pretrain/Loss": 2.0511674880981445, "Pretrain/Loss (Raw)": 2.110389232635498, "Pretrain/Step": 2501, "Pretrain/Step Time": 8.486237885430455} +{"Pretrain/Learning Rate": 4.324744824663417e-05, "Pretrain/Loss": 2.050037384033203, "Pretrain/Loss (Raw)": 2.1614291667938232, "Pretrain/Step": 2502, "Pretrain/Step Time": 8.486299641430378} +{"Pretrain/Learning Rate": 4.3241643261940243e-05, "Pretrain/Loss": 2.0507540702819824, "Pretrain/Loss (Raw)": 2.18182373046875, "Pretrain/Step": 2503, "Pretrain/Step Time": 8.486810768023133} +{"Pretrain/Learning Rate": 4.323583617307919e-05, "Pretrain/Loss": 2.0495362281799316, "Pretrain/Loss (Raw)": 1.884753942489624, "Pretrain/Step": 2504, "Pretrain/Step Time": 8.484705893322825} +{"Pretrain/Learning Rate": 4.323002698072085e-05, "Pretrain/Loss": 2.0508856773376465, "Pretrain/Loss (Raw)": 2.1740899085998535, "Pretrain/Step": 2505, "Pretrain/Step Time": 8.486067676916718} +{"Pretrain/Learning Rate": 4.3224215685535294e-05, "Pretrain/Loss": 2.051687240600586, "Pretrain/Loss (Raw)": 2.158812999725342, "Pretrain/Step": 2506, "Pretrain/Step Time": 8.489452082663774} +{"Pretrain/Learning Rate": 4.321840228819286e-05, "Pretrain/Loss": 2.0509915351867676, "Pretrain/Loss (Raw)": 1.984525442123413, "Pretrain/Step": 2507, "Pretrain/Step Time": 8.486543817445636} +{"Pretrain/Learning Rate": 4.321258678936413e-05, "Pretrain/Loss": 2.050450563430786, "Pretrain/Loss (Raw)": 2.0298047065734863, "Pretrain/Step": 2508, "Pretrain/Step Time": 8.490687863901258} +{"Pretrain/Learning Rate": 4.3206769189719906e-05, "Pretrain/Loss": 2.0507025718688965, "Pretrain/Loss (Raw)": 2.127063274383545, "Pretrain/Step": 2509, "Pretrain/Step Time": 8.493248965591192} +{"Pretrain/Learning Rate": 4.320094948993127e-05, "Pretrain/Loss": 2.0517773628234863, "Pretrain/Loss (Raw)": 2.2083046436309814, "Pretrain/Step": 2510, "Pretrain/Step Time": 8.491896042600274} +{"Pretrain/Learning Rate": 4.319512769066949e-05, "Pretrain/Loss": 2.0496933460235596, "Pretrain/Loss (Raw)": 2.0056705474853516, "Pretrain/Step": 2511, "Pretrain/Step Time": 8.490272102877498} +{"Pretrain/Learning Rate": 4.318930379260614e-05, "Pretrain/Loss": 2.0509696006774902, "Pretrain/Loss (Raw)": 2.1119658946990967, "Pretrain/Step": 2512, "Pretrain/Step Time": 8.492822356522083} +{"Pretrain/Learning Rate": 4.318347779641298e-05, "Pretrain/Loss": 2.051652431488037, "Pretrain/Loss (Raw)": 2.003361701965332, "Pretrain/Step": 2513, "Pretrain/Step Time": 8.4888952113688} +{"Pretrain/Learning Rate": 4.3177649702762046e-05, "Pretrain/Loss": 2.052196979522705, "Pretrain/Loss (Raw)": 2.109835147857666, "Pretrain/Step": 2514, "Pretrain/Step Time": 8.490156939253211} +{"Pretrain/Learning Rate": 4.317181951232562e-05, "Pretrain/Loss": 2.0507991313934326, "Pretrain/Loss (Raw)": 1.9275879859924316, "Pretrain/Step": 2515, "Pretrain/Step Time": 8.492890259250998} +{"Pretrain/Learning Rate": 4.316598722577618e-05, "Pretrain/Loss": 2.048226833343506, "Pretrain/Loss (Raw)": 1.7063850164413452, "Pretrain/Step": 2516, "Pretrain/Step Time": 8.489597985520959} +{"Pretrain/Learning Rate": 4.31601528437865e-05, "Pretrain/Loss": 2.0503640174865723, "Pretrain/Loss (Raw)": 2.2818610668182373, "Pretrain/Step": 2517, "Pretrain/Step Time": 8.491699021309614} +{"Pretrain/Learning Rate": 4.315431636702959e-05, "Pretrain/Loss": 2.0509743690490723, "Pretrain/Loss (Raw)": 2.1513314247131348, "Pretrain/Step": 2518, "Pretrain/Step Time": 8.490982135757804} +{"Pretrain/Learning Rate": 4.3148477796178653e-05, "Pretrain/Loss": 2.051243782043457, "Pretrain/Loss (Raw)": 2.0131728649139404, "Pretrain/Step": 2519, "Pretrain/Step Time": 8.487840481102467} +{"Pretrain/Learning Rate": 4.3142637131907184e-05, "Pretrain/Loss": 2.049262046813965, "Pretrain/Loss (Raw)": 1.9125568866729736, "Pretrain/Step": 2520, "Pretrain/Step Time": 8.488095441833138} +{"Pretrain/Learning Rate": 4.313679437488889e-05, "Pretrain/Loss": 2.049922466278076, "Pretrain/Loss (Raw)": 2.1479246616363525, "Pretrain/Step": 2521, "Pretrain/Step Time": 8.491022439673543} +{"Pretrain/Learning Rate": 4.3130949525797746e-05, "Pretrain/Loss": 2.050354242324829, "Pretrain/Loss (Raw)": 1.994047999382019, "Pretrain/Step": 2522, "Pretrain/Step Time": 8.488946706056595} +{"Pretrain/Learning Rate": 4.312510258530794e-05, "Pretrain/Loss": 2.0502920150756836, "Pretrain/Loss (Raw)": 2.1494338512420654, "Pretrain/Step": 2523, "Pretrain/Step Time": 8.489841451868415} +{"Pretrain/Learning Rate": 4.311925355409393e-05, "Pretrain/Loss": 2.0521998405456543, "Pretrain/Loss (Raw)": 1.9310203790664673, "Pretrain/Step": 2524, "Pretrain/Step Time": 8.486533435061574} +{"Pretrain/Learning Rate": 4.311340243283038e-05, "Pretrain/Loss": 2.051734447479248, "Pretrain/Loss (Raw)": 2.0977604389190674, "Pretrain/Step": 2525, "Pretrain/Step Time": 8.486705992370844} +{"Pretrain/Learning Rate": 4.3107549222192234e-05, "Pretrain/Loss": 2.0536346435546875, "Pretrain/Loss (Raw)": 2.125007390975952, "Pretrain/Step": 2526, "Pretrain/Step Time": 8.484814789146185} +{"Pretrain/Learning Rate": 4.310169392285464e-05, "Pretrain/Loss": 2.05246639251709, "Pretrain/Loss (Raw)": 1.9637861251831055, "Pretrain/Step": 2527, "Pretrain/Step Time": 8.488458514213562} +{"Pretrain/Learning Rate": 4.3095836535493016e-05, "Pretrain/Loss": 2.0518879890441895, "Pretrain/Loss (Raw)": 1.9782434701919556, "Pretrain/Step": 2528, "Pretrain/Step Time": 8.483096206560731} +{"Pretrain/Learning Rate": 4.308997706078301e-05, "Pretrain/Loss": 2.052591323852539, "Pretrain/Loss (Raw)": 2.2270660400390625, "Pretrain/Step": 2529, "Pretrain/Step Time": 8.481775986030698} +{"Pretrain/Learning Rate": 4.3084115499400506e-05, "Pretrain/Loss": 2.0516810417175293, "Pretrain/Loss (Raw)": 1.9849015474319458, "Pretrain/Step": 2530, "Pretrain/Step Time": 8.480826800689101} +{"Pretrain/Learning Rate": 4.3078251852021636e-05, "Pretrain/Loss": 2.0521559715270996, "Pretrain/Loss (Raw)": 2.0394787788391113, "Pretrain/Step": 2531, "Pretrain/Step Time": 8.483617734164} +{"Pretrain/Learning Rate": 4.3072386119322764e-05, "Pretrain/Loss": 2.0494511127471924, "Pretrain/Loss (Raw)": 1.7923511266708374, "Pretrain/Step": 2532, "Pretrain/Step Time": 8.485444407910109} +{"Pretrain/Learning Rate": 4.306651830198051e-05, "Pretrain/Loss": 2.0510640144348145, "Pretrain/Loss (Raw)": 2.1414248943328857, "Pretrain/Step": 2533, "Pretrain/Step Time": 8.48424031585455} +{"Pretrain/Learning Rate": 4.306064840067171e-05, "Pretrain/Loss": 2.050203323364258, "Pretrain/Loss (Raw)": 2.053283214569092, "Pretrain/Step": 2534, "Pretrain/Step Time": 8.487207546830177} +{"Pretrain/Learning Rate": 4.3054776416073474e-05, "Pretrain/Loss": 2.049030303955078, "Pretrain/Loss (Raw)": 2.022801637649536, "Pretrain/Step": 2535, "Pretrain/Step Time": 8.486124027520418} +{"Pretrain/Learning Rate": 4.3048902348863116e-05, "Pretrain/Loss": 2.050049066543579, "Pretrain/Loss (Raw)": 2.0799646377563477, "Pretrain/Step": 2536, "Pretrain/Step Time": 8.486109113320708} +{"Pretrain/Learning Rate": 4.304302619971822e-05, "Pretrain/Loss": 2.0500094890594482, "Pretrain/Loss (Raw)": 2.0752320289611816, "Pretrain/Step": 2537, "Pretrain/Step Time": 8.485279362648726} +{"Pretrain/Learning Rate": 4.3037147969316583e-05, "Pretrain/Loss": 2.049382209777832, "Pretrain/Loss (Raw)": 2.0657758712768555, "Pretrain/Step": 2538, "Pretrain/Step Time": 8.48819238692522} +{"Pretrain/Learning Rate": 4.303126765833628e-05, "Pretrain/Loss": 2.049070358276367, "Pretrain/Loss (Raw)": 2.1742069721221924, "Pretrain/Step": 2539, "Pretrain/Step Time": 8.4858658015728} +{"Pretrain/Learning Rate": 4.3025385267455575e-05, "Pretrain/Loss": 2.048560619354248, "Pretrain/Loss (Raw)": 2.126437187194824, "Pretrain/Step": 2540, "Pretrain/Step Time": 8.489062201231718} +{"Pretrain/Learning Rate": 4.3019500797353025e-05, "Pretrain/Loss": 2.050304412841797, "Pretrain/Loss (Raw)": 2.0960845947265625, "Pretrain/Step": 2541, "Pretrain/Step Time": 8.488694466650486} +{"Pretrain/Learning Rate": 4.301361424870739e-05, "Pretrain/Loss": 2.0491976737976074, "Pretrain/Loss (Raw)": 2.049238443374634, "Pretrain/Step": 2542, "Pretrain/Step Time": 8.489366944879293} +{"Pretrain/Learning Rate": 4.3007725622197674e-05, "Pretrain/Loss": 2.0488412380218506, "Pretrain/Loss (Raw)": 2.0185675621032715, "Pretrain/Step": 2543, "Pretrain/Step Time": 8.48706616833806} +{"Pretrain/Learning Rate": 4.300183491850314e-05, "Pretrain/Loss": 2.048004627227783, "Pretrain/Loss (Raw)": 1.8554296493530273, "Pretrain/Step": 2544, "Pretrain/Step Time": 8.490395735949278} +{"Pretrain/Learning Rate": 4.2995942138303276e-05, "Pretrain/Loss": 2.0479815006256104, "Pretrain/Loss (Raw)": 2.0669281482696533, "Pretrain/Step": 2545, "Pretrain/Step Time": 8.487525008618832} +{"Pretrain/Learning Rate": 4.299004728227781e-05, "Pretrain/Loss": 2.0464248657226562, "Pretrain/Loss (Raw)": 1.9730241298675537, "Pretrain/Step": 2546, "Pretrain/Step Time": 8.48822427354753} +{"Pretrain/Learning Rate": 4.2984150351106714e-05, "Pretrain/Loss": 2.046274185180664, "Pretrain/Loss (Raw)": 2.0409622192382812, "Pretrain/Step": 2547, "Pretrain/Step Time": 8.48954882659018} +{"Pretrain/Learning Rate": 4.297825134547019e-05, "Pretrain/Loss": 2.046016216278076, "Pretrain/Loss (Raw)": 1.949351191520691, "Pretrain/Step": 2548, "Pretrain/Step Time": 8.487942788749933} +{"Pretrain/Learning Rate": 4.29723502660487e-05, "Pretrain/Loss": 2.0441298484802246, "Pretrain/Loss (Raw)": 2.0834531784057617, "Pretrain/Step": 2549, "Pretrain/Step Time": 8.483712887391448} +{"Pretrain/Learning Rate": 4.296644711352291e-05, "Pretrain/Loss": 2.043194532394409, "Pretrain/Loss (Raw)": 2.052194356918335, "Pretrain/Step": 2550, "Pretrain/Step Time": 8.487093219533563} +{"Pretrain/Learning Rate": 4.296054188857377e-05, "Pretrain/Loss": 2.0423574447631836, "Pretrain/Loss (Raw)": 1.9481183290481567, "Pretrain/Step": 2551, "Pretrain/Step Time": 8.481708575040102} +{"Pretrain/Learning Rate": 4.295463459188243e-05, "Pretrain/Loss": 2.0437607765197754, "Pretrain/Loss (Raw)": 2.150709867477417, "Pretrain/Step": 2552, "Pretrain/Step Time": 8.479002092033625} +{"Pretrain/Learning Rate": 4.29487252241303e-05, "Pretrain/Loss": 2.0432143211364746, "Pretrain/Loss (Raw)": 1.83285653591156, "Pretrain/Step": 2553, "Pretrain/Step Time": 8.480992062017322} +{"Pretrain/Learning Rate": 4.2942813785999026e-05, "Pretrain/Loss": 2.0431809425354004, "Pretrain/Loss (Raw)": 2.03647780418396, "Pretrain/Step": 2554, "Pretrain/Step Time": 8.482179701328278} +{"Pretrain/Learning Rate": 4.2936900278170484e-05, "Pretrain/Loss": 2.04252552986145, "Pretrain/Loss (Raw)": 2.0212085247039795, "Pretrain/Step": 2555, "Pretrain/Step Time": 8.48232737928629} +{"Pretrain/Learning Rate": 4.2930984701326796e-05, "Pretrain/Loss": 2.0418381690979004, "Pretrain/Loss (Raw)": 2.016575336456299, "Pretrain/Step": 2556, "Pretrain/Step Time": 8.480571322143078} +{"Pretrain/Learning Rate": 4.2925067056150325e-05, "Pretrain/Loss": 2.042760133743286, "Pretrain/Loss (Raw)": 2.0998167991638184, "Pretrain/Step": 2557, "Pretrain/Step Time": 8.480096133425832} +{"Pretrain/Learning Rate": 4.291914734332367e-05, "Pretrain/Loss": 2.0449419021606445, "Pretrain/Loss (Raw)": 2.1671791076660156, "Pretrain/Step": 2558, "Pretrain/Step Time": 8.479388993233442} +{"Pretrain/Learning Rate": 4.2913225563529674e-05, "Pretrain/Loss": 2.0442419052124023, "Pretrain/Loss (Raw)": 2.065849542617798, "Pretrain/Step": 2559, "Pretrain/Step Time": 8.480429729446769} +{"Pretrain/Learning Rate": 4.29073017174514e-05, "Pretrain/Loss": 2.043520927429199, "Pretrain/Loss (Raw)": 2.108793020248413, "Pretrain/Step": 2560, "Pretrain/Step Time": 8.482021503150463} +{"Pretrain/Learning Rate": 4.290137580577216e-05, "Pretrain/Loss": 2.0439977645874023, "Pretrain/Loss (Raw)": 2.0811758041381836, "Pretrain/Step": 2561, "Pretrain/Step Time": 8.482206888496876} +{"Pretrain/Learning Rate": 4.289544782917552e-05, "Pretrain/Loss": 2.041978597640991, "Pretrain/Loss (Raw)": 1.7215495109558105, "Pretrain/Step": 2562, "Pretrain/Step Time": 8.482818491756916} +{"Pretrain/Learning Rate": 4.288951778834525e-05, "Pretrain/Loss": 2.040794849395752, "Pretrain/Loss (Raw)": 1.9199247360229492, "Pretrain/Step": 2563, "Pretrain/Step Time": 8.479519072920084} +{"Pretrain/Learning Rate": 4.28835856839654e-05, "Pretrain/Loss": 2.040876865386963, "Pretrain/Loss (Raw)": 2.092721462249756, "Pretrain/Step": 2564, "Pretrain/Step Time": 8.479593181982636} +{"Pretrain/Learning Rate": 4.2877651516720215e-05, "Pretrain/Loss": 2.042295217514038, "Pretrain/Loss (Raw)": 2.129734754562378, "Pretrain/Step": 2565, "Pretrain/Step Time": 8.479449758306146} +{"Pretrain/Learning Rate": 4.287171528729422e-05, "Pretrain/Loss": 2.0415115356445312, "Pretrain/Loss (Raw)": 2.0428619384765625, "Pretrain/Step": 2566, "Pretrain/Step Time": 8.482207572087646} +{"Pretrain/Learning Rate": 4.286577699637215e-05, "Pretrain/Loss": 2.0418827533721924, "Pretrain/Loss (Raw)": 2.09384822845459, "Pretrain/Step": 2567, "Pretrain/Step Time": 8.482943676412106} +{"Pretrain/Learning Rate": 4.2859836644638976e-05, "Pretrain/Loss": 2.0415873527526855, "Pretrain/Loss (Raw)": 1.954414963722229, "Pretrain/Step": 2568, "Pretrain/Step Time": 8.48066927678883} +{"Pretrain/Learning Rate": 4.2853894232779924e-05, "Pretrain/Loss": 2.042522430419922, "Pretrain/Loss (Raw)": 1.954482078552246, "Pretrain/Step": 2569, "Pretrain/Step Time": 8.48437843285501} +{"Pretrain/Learning Rate": 4.2847949761480445e-05, "Pretrain/Loss": 2.042421817779541, "Pretrain/Loss (Raw)": 2.0922863483428955, "Pretrain/Step": 2570, "Pretrain/Step Time": 8.483306167647243} +{"Pretrain/Learning Rate": 4.284200323142623e-05, "Pretrain/Loss": 2.042642831802368, "Pretrain/Loss (Raw)": 2.099135160446167, "Pretrain/Step": 2571, "Pretrain/Step Time": 8.482749946415424} +{"Pretrain/Learning Rate": 4.283605464330322e-05, "Pretrain/Loss": 2.0407350063323975, "Pretrain/Loss (Raw)": 1.9375402927398682, "Pretrain/Step": 2572, "Pretrain/Step Time": 8.482509268447757} +{"Pretrain/Learning Rate": 4.283010399779757e-05, "Pretrain/Loss": 2.043337821960449, "Pretrain/Loss (Raw)": 2.1652190685272217, "Pretrain/Step": 2573, "Pretrain/Step Time": 8.482953170314431} +{"Pretrain/Learning Rate": 4.2824151295595696e-05, "Pretrain/Loss": 2.0440258979797363, "Pretrain/Loss (Raw)": 1.944067358970642, "Pretrain/Step": 2574, "Pretrain/Step Time": 8.482815738767385} +{"Pretrain/Learning Rate": 4.281819653738422e-05, "Pretrain/Loss": 2.045677423477173, "Pretrain/Loss (Raw)": 2.0032927989959717, "Pretrain/Step": 2575, "Pretrain/Step Time": 8.482246365398169} +{"Pretrain/Learning Rate": 4.281223972385005e-05, "Pretrain/Loss": 2.045562505722046, "Pretrain/Loss (Raw)": 1.9974541664123535, "Pretrain/Step": 2576, "Pretrain/Step Time": 8.48102798499167} +{"Pretrain/Learning Rate": 4.280628085568028e-05, "Pretrain/Loss": 2.0445375442504883, "Pretrain/Loss (Raw)": 1.9584041833877563, "Pretrain/Step": 2577, "Pretrain/Step Time": 8.478268707171082} +{"Pretrain/Learning Rate": 4.280031993356227e-05, "Pretrain/Loss": 2.039137125015259, "Pretrain/Loss (Raw)": 1.4941872358322144, "Pretrain/Step": 2578, "Pretrain/Step Time": 8.4807780534029} +{"Pretrain/Learning Rate": 4.279435695818361e-05, "Pretrain/Loss": 2.0389528274536133, "Pretrain/Loss (Raw)": 2.1113100051879883, "Pretrain/Step": 2579, "Pretrain/Step Time": 8.480715438723564} +{"Pretrain/Learning Rate": 4.278839193023214e-05, "Pretrain/Loss": 2.039365768432617, "Pretrain/Loss (Raw)": 2.198423147201538, "Pretrain/Step": 2580, "Pretrain/Step Time": 8.483430931344628} +{"Pretrain/Learning Rate": 4.2782424850395896e-05, "Pretrain/Loss": 2.038234233856201, "Pretrain/Loss (Raw)": 2.0464680194854736, "Pretrain/Step": 2581, "Pretrain/Step Time": 8.483642794191837} +{"Pretrain/Learning Rate": 4.2776455719363205e-05, "Pretrain/Loss": 2.0388023853302, "Pretrain/Loss (Raw)": 2.1292216777801514, "Pretrain/Step": 2582, "Pretrain/Step Time": 8.481404591351748} +{"Pretrain/Learning Rate": 4.277048453782259e-05, "Pretrain/Loss": 2.03772234916687, "Pretrain/Loss (Raw)": 1.9673625230789185, "Pretrain/Step": 2583, "Pretrain/Step Time": 8.482361916452646} +{"Pretrain/Learning Rate": 4.2764511306462826e-05, "Pretrain/Loss": 2.0379414558410645, "Pretrain/Loss (Raw)": 2.030519485473633, "Pretrain/Step": 2584, "Pretrain/Step Time": 8.47917553782463} +{"Pretrain/Learning Rate": 4.2758536025972936e-05, "Pretrain/Loss": 2.0380167961120605, "Pretrain/Loss (Raw)": 2.0292646884918213, "Pretrain/Step": 2585, "Pretrain/Step Time": 8.475393652915955} +{"Pretrain/Learning Rate": 4.275255869704214e-05, "Pretrain/Loss": 2.0371670722961426, "Pretrain/Loss (Raw)": 1.9863911867141724, "Pretrain/Step": 2586, "Pretrain/Step Time": 8.478237513452768} +{"Pretrain/Learning Rate": 4.274657932035996e-05, "Pretrain/Loss": 2.0399608612060547, "Pretrain/Loss (Raw)": 2.167344570159912, "Pretrain/Step": 2587, "Pretrain/Step Time": 8.480876902118325} +{"Pretrain/Learning Rate": 4.2740597896616075e-05, "Pretrain/Loss": 2.0386650562286377, "Pretrain/Loss (Raw)": 1.974782109260559, "Pretrain/Step": 2588, "Pretrain/Step Time": 8.475555075332522} +{"Pretrain/Learning Rate": 4.273461442650046e-05, "Pretrain/Loss": 2.037238597869873, "Pretrain/Loss (Raw)": 1.996995449066162, "Pretrain/Step": 2589, "Pretrain/Step Time": 8.477564880624413} +{"Pretrain/Learning Rate": 4.272862891070331e-05, "Pretrain/Loss": 2.0381178855895996, "Pretrain/Loss (Raw)": 2.1476128101348877, "Pretrain/Step": 2590, "Pretrain/Step Time": 8.476575376465917} +{"Pretrain/Learning Rate": 4.272264134991503e-05, "Pretrain/Loss": 2.0395143032073975, "Pretrain/Loss (Raw)": 2.137580156326294, "Pretrain/Step": 2591, "Pretrain/Step Time": 8.473984831944108} +{"Pretrain/Learning Rate": 4.271665174482631e-05, "Pretrain/Loss": 2.037958860397339, "Pretrain/Loss (Raw)": 1.7663156986236572, "Pretrain/Step": 2592, "Pretrain/Step Time": 8.473675828427076} +{"Pretrain/Learning Rate": 4.271066009612804e-05, "Pretrain/Loss": 2.0404138565063477, "Pretrain/Loss (Raw)": 2.310399055480957, "Pretrain/Step": 2593, "Pretrain/Step Time": 8.469315234571695} +{"Pretrain/Learning Rate": 4.270466640451134e-05, "Pretrain/Loss": 2.038656234741211, "Pretrain/Loss (Raw)": 1.8905282020568848, "Pretrain/Step": 2594, "Pretrain/Step Time": 8.469729762524366} +{"Pretrain/Learning Rate": 4.26986706706676e-05, "Pretrain/Loss": 2.0389206409454346, "Pretrain/Loss (Raw)": 1.9235221147537231, "Pretrain/Step": 2595, "Pretrain/Step Time": 8.472607837989926} +{"Pretrain/Learning Rate": 4.269267289528842e-05, "Pretrain/Loss": 2.0414068698883057, "Pretrain/Loss (Raw)": 2.0987277030944824, "Pretrain/Step": 2596, "Pretrain/Step Time": 8.472904903814197} +{"Pretrain/Learning Rate": 4.268667307906564e-05, "Pretrain/Loss": 2.04262638092041, "Pretrain/Loss (Raw)": 2.127568244934082, "Pretrain/Step": 2597, "Pretrain/Step Time": 8.470861515030265} +{"Pretrain/Learning Rate": 4.2680671222691325e-05, "Pretrain/Loss": 2.0420734882354736, "Pretrain/Loss (Raw)": 2.130335569381714, "Pretrain/Step": 2598, "Pretrain/Step Time": 8.471251690760255} +{"Pretrain/Learning Rate": 4.2674667326857807e-05, "Pretrain/Loss": 2.042027473449707, "Pretrain/Loss (Raw)": 2.0550906658172607, "Pretrain/Step": 2599, "Pretrain/Step Time": 8.472052162513137} +{"Pretrain/Learning Rate": 4.2668661392257624e-05, "Pretrain/Loss": 2.0415186882019043, "Pretrain/Loss (Raw)": 2.08541202545166, "Pretrain/Step": 2600, "Pretrain/Step Time": 8.469350071623921} +{"Pretrain/Learning Rate": 4.2662653419583556e-05, "Pretrain/Loss": 2.0441370010375977, "Pretrain/Loss (Raw)": 2.0219550132751465, "Pretrain/Step": 2601, "Pretrain/Step Time": 8.468361608684063} +{"Pretrain/Learning Rate": 4.2656643409528624e-05, "Pretrain/Loss": 2.042304277420044, "Pretrain/Loss (Raw)": 1.8308594226837158, "Pretrain/Step": 2602, "Pretrain/Step Time": 8.467728767544031} +{"Pretrain/Learning Rate": 4.265063136278608e-05, "Pretrain/Loss": 2.0433707237243652, "Pretrain/Loss (Raw)": 2.1487350463867188, "Pretrain/Step": 2603, "Pretrain/Step Time": 8.469786068424582} +{"Pretrain/Learning Rate": 4.264461728004941e-05, "Pretrain/Loss": 2.0439529418945312, "Pretrain/Loss (Raw)": 2.246994972229004, "Pretrain/Step": 2604, "Pretrain/Step Time": 8.470320645719767} +{"Pretrain/Learning Rate": 4.2638601162012335e-05, "Pretrain/Loss": 2.043313503265381, "Pretrain/Loss (Raw)": 2.0298948287963867, "Pretrain/Step": 2605, "Pretrain/Step Time": 8.469858922064304} +{"Pretrain/Learning Rate": 4.263258300936882e-05, "Pretrain/Loss": 2.0419154167175293, "Pretrain/Loss (Raw)": 1.9451948404312134, "Pretrain/Step": 2606, "Pretrain/Step Time": 8.48337166942656} +{"Pretrain/Learning Rate": 4.262656282281305e-05, "Pretrain/Loss": 2.040389060974121, "Pretrain/Loss (Raw)": 1.8378781080245972, "Pretrain/Step": 2607, "Pretrain/Step Time": 8.480060243979096} +{"Pretrain/Learning Rate": 4.262054060303945e-05, "Pretrain/Loss": 2.0391335487365723, "Pretrain/Loss (Raw)": 2.0148603916168213, "Pretrain/Step": 2608, "Pretrain/Step Time": 8.47903542406857} +{"Pretrain/Learning Rate": 4.261451635074269e-05, "Pretrain/Loss": 2.0407614707946777, "Pretrain/Loss (Raw)": 2.1149964332580566, "Pretrain/Step": 2609, "Pretrain/Step Time": 8.48124716244638} +{"Pretrain/Learning Rate": 4.2608490066617654e-05, "Pretrain/Loss": 2.0417613983154297, "Pretrain/Loss (Raw)": 1.9921907186508179, "Pretrain/Step": 2610, "Pretrain/Step Time": 8.480760091915727} +{"Pretrain/Learning Rate": 4.260246175135948e-05, "Pretrain/Loss": 2.044495105743408, "Pretrain/Loss (Raw)": 2.2160305976867676, "Pretrain/Step": 2611, "Pretrain/Step Time": 8.48189377784729} +{"Pretrain/Learning Rate": 4.259643140566352e-05, "Pretrain/Loss": 2.0458173751831055, "Pretrain/Loss (Raw)": 2.2326197624206543, "Pretrain/Step": 2612, "Pretrain/Step Time": 8.48867229372263} +{"Pretrain/Learning Rate": 4.259039903022539e-05, "Pretrain/Loss": 2.0460925102233887, "Pretrain/Loss (Raw)": 2.07450795173645, "Pretrain/Step": 2613, "Pretrain/Step Time": 8.487036745995283} +{"Pretrain/Learning Rate": 4.2584364625740914e-05, "Pretrain/Loss": 2.0447049140930176, "Pretrain/Loss (Raw)": 2.050664186477661, "Pretrain/Step": 2614, "Pretrain/Step Time": 8.486402254551649} +{"Pretrain/Learning Rate": 4.257832819290615e-05, "Pretrain/Loss": 2.0450658798217773, "Pretrain/Loss (Raw)": 2.1496195793151855, "Pretrain/Step": 2615, "Pretrain/Step Time": 8.486634572967887} +{"Pretrain/Learning Rate": 4.257228973241741e-05, "Pretrain/Loss": 2.0458929538726807, "Pretrain/Loss (Raw)": 2.235639810562134, "Pretrain/Step": 2616, "Pretrain/Step Time": 8.483539102599025} +{"Pretrain/Learning Rate": 4.256624924497123e-05, "Pretrain/Loss": 2.046430826187134, "Pretrain/Loss (Raw)": 2.106605052947998, "Pretrain/Step": 2617, "Pretrain/Step Time": 8.482460472732782} +{"Pretrain/Learning Rate": 4.2560206731264376e-05, "Pretrain/Loss": 2.047031879425049, "Pretrain/Loss (Raw)": 2.2167203426361084, "Pretrain/Step": 2618, "Pretrain/Step Time": 8.4876903668046} +{"Pretrain/Learning Rate": 4.2554162191993844e-05, "Pretrain/Loss": 2.045764446258545, "Pretrain/Loss (Raw)": 2.0841145515441895, "Pretrain/Step": 2619, "Pretrain/Step Time": 8.488253302872181} +{"Pretrain/Learning Rate": 4.254811562785686e-05, "Pretrain/Loss": 2.046332836151123, "Pretrain/Loss (Raw)": 1.9579167366027832, "Pretrain/Step": 2620, "Pretrain/Step Time": 8.49001065082848} +{"Pretrain/Learning Rate": 4.254206703955091e-05, "Pretrain/Loss": 2.0491557121276855, "Pretrain/Loss (Raw)": 2.0957679748535156, "Pretrain/Step": 2621, "Pretrain/Step Time": 8.482344832271338} +{"Pretrain/Learning Rate": 4.25360164277737e-05, "Pretrain/Loss": 2.0487570762634277, "Pretrain/Loss (Raw)": 2.098752021789551, "Pretrain/Step": 2622, "Pretrain/Step Time": 8.482374986633658} +{"Pretrain/Learning Rate": 4.2529963793223146e-05, "Pretrain/Loss": 2.0510170459747314, "Pretrain/Loss (Raw)": 2.2297611236572266, "Pretrain/Step": 2623, "Pretrain/Step Time": 8.48186127282679} +{"Pretrain/Learning Rate": 4.252390913659744e-05, "Pretrain/Loss": 2.050783634185791, "Pretrain/Loss (Raw)": 2.1963565349578857, "Pretrain/Step": 2624, "Pretrain/Step Time": 8.48155765607953} +{"Pretrain/Learning Rate": 4.251785245859497e-05, "Pretrain/Loss": 2.0502989292144775, "Pretrain/Loss (Raw)": 1.9543554782867432, "Pretrain/Step": 2625, "Pretrain/Step Time": 8.479549210518599} +{"Pretrain/Learning Rate": 4.251179375991438e-05, "Pretrain/Loss": 2.0492444038391113, "Pretrain/Loss (Raw)": 2.0478243827819824, "Pretrain/Step": 2626, "Pretrain/Step Time": 8.478714121505618} +{"Pretrain/Learning Rate": 4.250573304125453e-05, "Pretrain/Loss": 2.0489912033081055, "Pretrain/Loss (Raw)": 2.129025936126709, "Pretrain/Step": 2627, "Pretrain/Step Time": 8.475905936211348} +{"Pretrain/Learning Rate": 4.2499670303314516e-05, "Pretrain/Loss": 2.050206184387207, "Pretrain/Loss (Raw)": 2.1253738403320312, "Pretrain/Step": 2628, "Pretrain/Step Time": 8.475985456258059} +{"Pretrain/Learning Rate": 4.249360554679369e-05, "Pretrain/Loss": 2.0494744777679443, "Pretrain/Loss (Raw)": 2.0167477130889893, "Pretrain/Step": 2629, "Pretrain/Step Time": 8.47753213532269} +{"Pretrain/Learning Rate": 4.248753877239161e-05, "Pretrain/Loss": 2.048818349838257, "Pretrain/Loss (Raw)": 2.077430009841919, "Pretrain/Step": 2630, "Pretrain/Step Time": 8.4732267241925} +{"Pretrain/Learning Rate": 4.248146998080808e-05, "Pretrain/Loss": 2.0478177070617676, "Pretrain/Loss (Raw)": 2.0537562370300293, "Pretrain/Step": 2631, "Pretrain/Step Time": 8.47777516208589} +{"Pretrain/Learning Rate": 4.2475399172743134e-05, "Pretrain/Loss": 2.04962420463562, "Pretrain/Loss (Raw)": 2.115981101989746, "Pretrain/Step": 2632, "Pretrain/Step Time": 8.479123366996646} +{"Pretrain/Learning Rate": 4.246932634889703e-05, "Pretrain/Loss": 2.0488603115081787, "Pretrain/Loss (Raw)": 2.0762932300567627, "Pretrain/Step": 2633, "Pretrain/Step Time": 8.476215766742826} +{"Pretrain/Learning Rate": 4.246325150997027e-05, "Pretrain/Loss": 2.0471243858337402, "Pretrain/Loss (Raw)": 1.9366317987442017, "Pretrain/Step": 2634, "Pretrain/Step Time": 8.474454808980227} +{"Pretrain/Learning Rate": 4.245717465666359e-05, "Pretrain/Loss": 2.0478172302246094, "Pretrain/Loss (Raw)": 2.0732176303863525, "Pretrain/Step": 2635, "Pretrain/Step Time": 8.478512361645699} +{"Pretrain/Learning Rate": 4.2451095789677945e-05, "Pretrain/Loss": 2.046977996826172, "Pretrain/Loss (Raw)": 1.9223750829696655, "Pretrain/Step": 2636, "Pretrain/Step Time": 8.478307666257024} +{"Pretrain/Learning Rate": 4.244501490971454e-05, "Pretrain/Loss": 2.045348644256592, "Pretrain/Loss (Raw)": 1.9185187816619873, "Pretrain/Step": 2637, "Pretrain/Step Time": 8.479557268321514} +{"Pretrain/Learning Rate": 4.243893201747478e-05, "Pretrain/Loss": 2.0436792373657227, "Pretrain/Loss (Raw)": 1.9945900440216064, "Pretrain/Step": 2638, "Pretrain/Step Time": 8.481021326035261} +{"Pretrain/Learning Rate": 4.2432847113660356e-05, "Pretrain/Loss": 2.044175148010254, "Pretrain/Loss (Raw)": 2.0691750049591064, "Pretrain/Step": 2639, "Pretrain/Step Time": 8.480936711654067} +{"Pretrain/Learning Rate": 4.242676019897314e-05, "Pretrain/Loss": 2.0439038276672363, "Pretrain/Loss (Raw)": 2.077207565307617, "Pretrain/Step": 2640, "Pretrain/Step Time": 8.477549171075225} +{"Pretrain/Learning Rate": 4.242067127411526e-05, "Pretrain/Loss": 2.045130729675293, "Pretrain/Loss (Raw)": 2.160423994064331, "Pretrain/Step": 2641, "Pretrain/Step Time": 8.480427633970976} +{"Pretrain/Learning Rate": 4.241458033978907e-05, "Pretrain/Loss": 2.044630527496338, "Pretrain/Loss (Raw)": 2.045821189880371, "Pretrain/Step": 2642, "Pretrain/Step Time": 8.48141628690064} +{"Pretrain/Learning Rate": 4.240848739669715e-05, "Pretrain/Loss": 2.0457253456115723, "Pretrain/Loss (Raw)": 2.0677080154418945, "Pretrain/Step": 2643, "Pretrain/Step Time": 8.479119446128607} +{"Pretrain/Learning Rate": 4.240239244554233e-05, "Pretrain/Loss": 2.049009323120117, "Pretrain/Loss (Raw)": 2.126739978790283, "Pretrain/Step": 2644, "Pretrain/Step Time": 8.478228610008955} +{"Pretrain/Learning Rate": 4.239629548702767e-05, "Pretrain/Loss": 2.0448131561279297, "Pretrain/Loss (Raw)": 1.744764804840088, "Pretrain/Step": 2645, "Pretrain/Step Time": 8.479164382442832} +{"Pretrain/Learning Rate": 4.239019652185642e-05, "Pretrain/Loss": 2.0456647872924805, "Pretrain/Loss (Raw)": 2.260319471359253, "Pretrain/Step": 2646, "Pretrain/Step Time": 8.48469989746809} +{"Pretrain/Learning Rate": 4.238409555073212e-05, "Pretrain/Loss": 2.046375274658203, "Pretrain/Loss (Raw)": 2.1041159629821777, "Pretrain/Step": 2647, "Pretrain/Step Time": 8.485179278999567} +{"Pretrain/Learning Rate": 4.237799257435852e-05, "Pretrain/Loss": 2.0472302436828613, "Pretrain/Loss (Raw)": 2.02199649810791, "Pretrain/Step": 2648, "Pretrain/Step Time": 8.485102489590645} +{"Pretrain/Learning Rate": 4.237188759343956e-05, "Pretrain/Loss": 2.046468496322632, "Pretrain/Loss (Raw)": 2.05041241645813, "Pretrain/Step": 2649, "Pretrain/Step Time": 8.48106656037271} +{"Pretrain/Learning Rate": 4.236578060867949e-05, "Pretrain/Loss": 2.0462045669555664, "Pretrain/Loss (Raw)": 1.9602749347686768, "Pretrain/Step": 2650, "Pretrain/Step Time": 8.483144398778677} +{"Pretrain/Learning Rate": 4.235967162078272e-05, "Pretrain/Loss": 2.0457043647766113, "Pretrain/Loss (Raw)": 2.0853993892669678, "Pretrain/Step": 2651, "Pretrain/Step Time": 8.484306221827865} +{"Pretrain/Learning Rate": 4.235356063045393e-05, "Pretrain/Loss": 2.0470170974731445, "Pretrain/Loss (Raw)": 2.099083185195923, "Pretrain/Step": 2652, "Pretrain/Step Time": 8.487044099718332} +{"Pretrain/Learning Rate": 4.234744763839802e-05, "Pretrain/Loss": 2.0466511249542236, "Pretrain/Loss (Raw)": 2.0508899688720703, "Pretrain/Step": 2653, "Pretrain/Step Time": 8.484297396615148} +{"Pretrain/Learning Rate": 4.234133264532012e-05, "Pretrain/Loss": 2.0447306632995605, "Pretrain/Loss (Raw)": 1.8791762590408325, "Pretrain/Step": 2654, "Pretrain/Step Time": 8.485211923718452} +{"Pretrain/Learning Rate": 4.2335215651925605e-05, "Pretrain/Loss": 2.045478343963623, "Pretrain/Loss (Raw)": 2.059514045715332, "Pretrain/Step": 2655, "Pretrain/Step Time": 8.482752732932568} +{"Pretrain/Learning Rate": 4.2329096658920045e-05, "Pretrain/Loss": 2.0461554527282715, "Pretrain/Loss (Raw)": 2.064901113510132, "Pretrain/Step": 2656, "Pretrain/Step Time": 8.483868027105927} +{"Pretrain/Learning Rate": 4.232297566700928e-05, "Pretrain/Loss": 2.0449142456054688, "Pretrain/Loss (Raw)": 2.0681819915771484, "Pretrain/Step": 2657, "Pretrain/Step Time": 8.482369486242533} +{"Pretrain/Learning Rate": 4.2316852676899356e-05, "Pretrain/Loss": 2.043811559677124, "Pretrain/Loss (Raw)": 1.8437700271606445, "Pretrain/Step": 2658, "Pretrain/Step Time": 8.484782110899687} +{"Pretrain/Learning Rate": 4.231072768929656e-05, "Pretrain/Loss": 2.0447731018066406, "Pretrain/Loss (Raw)": 2.162533760070801, "Pretrain/Step": 2659, "Pretrain/Step Time": 8.481336671859026} +{"Pretrain/Learning Rate": 4.2304600704907414e-05, "Pretrain/Loss": 2.0475411415100098, "Pretrain/Loss (Raw)": 2.146676540374756, "Pretrain/Step": 2660, "Pretrain/Step Time": 8.479264926165342} +{"Pretrain/Learning Rate": 4.229847172443866e-05, "Pretrain/Loss": 2.047779083251953, "Pretrain/Loss (Raw)": 2.17189359664917, "Pretrain/Step": 2661, "Pretrain/Step Time": 8.481774765998125} +{"Pretrain/Learning Rate": 4.229234074859727e-05, "Pretrain/Loss": 2.0481793880462646, "Pretrain/Loss (Raw)": 2.104536533355713, "Pretrain/Step": 2662, "Pretrain/Step Time": 8.480255767703056} +{"Pretrain/Learning Rate": 4.228620777809045e-05, "Pretrain/Loss": 2.04970645904541, "Pretrain/Loss (Raw)": 2.2182703018188477, "Pretrain/Step": 2663, "Pretrain/Step Time": 8.484260749071836} +{"Pretrain/Learning Rate": 4.2280072813625634e-05, "Pretrain/Loss": 2.0476903915405273, "Pretrain/Loss (Raw)": 1.8219012022018433, "Pretrain/Step": 2664, "Pretrain/Step Time": 8.482021987438202} +{"Pretrain/Learning Rate": 4.227393585591049e-05, "Pretrain/Loss": 2.0473721027374268, "Pretrain/Loss (Raw)": 2.034487724304199, "Pretrain/Step": 2665, "Pretrain/Step Time": 8.482229840010405} +{"Pretrain/Learning Rate": 4.2267796905652924e-05, "Pretrain/Loss": 2.0459799766540527, "Pretrain/Loss (Raw)": 1.8876020908355713, "Pretrain/Step": 2666, "Pretrain/Step Time": 8.483701933175325} +{"Pretrain/Learning Rate": 4.2261655963561044e-05, "Pretrain/Loss": 2.04561710357666, "Pretrain/Loss (Raw)": 2.127713441848755, "Pretrain/Step": 2667, "Pretrain/Step Time": 8.483290329575539} +{"Pretrain/Learning Rate": 4.225551303034322e-05, "Pretrain/Loss": 2.045267105102539, "Pretrain/Loss (Raw)": 2.0816593170166016, "Pretrain/Step": 2668, "Pretrain/Step Time": 8.482769634574652} +{"Pretrain/Learning Rate": 4.224936810670803e-05, "Pretrain/Loss": 2.045933246612549, "Pretrain/Loss (Raw)": 2.181346893310547, "Pretrain/Step": 2669, "Pretrain/Step Time": 8.482182433828712} +{"Pretrain/Learning Rate": 4.224322119336429e-05, "Pretrain/Loss": 2.0472872257232666, "Pretrain/Loss (Raw)": 2.2225539684295654, "Pretrain/Step": 2670, "Pretrain/Step Time": 8.481378195807338} +{"Pretrain/Learning Rate": 4.223707229102105e-05, "Pretrain/Loss": 2.0479161739349365, "Pretrain/Loss (Raw)": 2.0990676879882812, "Pretrain/Step": 2671, "Pretrain/Step Time": 8.479858877137303} +{"Pretrain/Learning Rate": 4.223092140038758e-05, "Pretrain/Loss": 2.0488784313201904, "Pretrain/Loss (Raw)": 1.9785882234573364, "Pretrain/Step": 2672, "Pretrain/Step Time": 8.477406430989504} +{"Pretrain/Learning Rate": 4.222476852217338e-05, "Pretrain/Loss": 2.049233913421631, "Pretrain/Loss (Raw)": 2.1124093532562256, "Pretrain/Step": 2673, "Pretrain/Step Time": 8.477810250595212} +{"Pretrain/Learning Rate": 4.221861365708818e-05, "Pretrain/Loss": 2.0510480403900146, "Pretrain/Loss (Raw)": 2.205265760421753, "Pretrain/Step": 2674, "Pretrain/Step Time": 8.476749060675502} +{"Pretrain/Learning Rate": 4.221245680584194e-05, "Pretrain/Loss": 2.050290584564209, "Pretrain/Loss (Raw)": 1.9440048933029175, "Pretrain/Step": 2675, "Pretrain/Step Time": 8.475263692438602} +{"Pretrain/Learning Rate": 4.220629796914487e-05, "Pretrain/Loss": 2.050445079803467, "Pretrain/Loss (Raw)": 1.9690907001495361, "Pretrain/Step": 2676, "Pretrain/Step Time": 8.479069260880351} +{"Pretrain/Learning Rate": 4.220013714770737e-05, "Pretrain/Loss": 2.0476276874542236, "Pretrain/Loss (Raw)": 1.7228738069534302, "Pretrain/Step": 2677, "Pretrain/Step Time": 8.482011457905173} +{"Pretrain/Learning Rate": 4.2193974342240096e-05, "Pretrain/Loss": 2.048189878463745, "Pretrain/Loss (Raw)": 2.124161720275879, "Pretrain/Step": 2678, "Pretrain/Step Time": 8.480435172095895} +{"Pretrain/Learning Rate": 4.2187809553453924e-05, "Pretrain/Loss": 2.046762466430664, "Pretrain/Loss (Raw)": 1.7653802633285522, "Pretrain/Step": 2679, "Pretrain/Step Time": 8.480158319696784} +{"Pretrain/Learning Rate": 4.2181642782059955e-05, "Pretrain/Loss": 2.045588970184326, "Pretrain/Loss (Raw)": 2.000481367111206, "Pretrain/Step": 2680, "Pretrain/Step Time": 8.482320411130786} +{"Pretrain/Learning Rate": 4.2175474028769534e-05, "Pretrain/Loss": 2.0453946590423584, "Pretrain/Loss (Raw)": 1.8080130815505981, "Pretrain/Step": 2681, "Pretrain/Step Time": 8.479898871853948} +{"Pretrain/Learning Rate": 4.2169303294294216e-05, "Pretrain/Loss": 2.044276714324951, "Pretrain/Loss (Raw)": 1.8933992385864258, "Pretrain/Step": 2682, "Pretrain/Step Time": 8.477960715070367} +{"Pretrain/Learning Rate": 4.21631305793458e-05, "Pretrain/Loss": 2.0441267490386963, "Pretrain/Loss (Raw)": 2.0019900798797607, "Pretrain/Step": 2683, "Pretrain/Step Time": 8.481715785339475} +{"Pretrain/Learning Rate": 4.2156955884636304e-05, "Pretrain/Loss": 2.0459558963775635, "Pretrain/Loss (Raw)": 2.250709295272827, "Pretrain/Step": 2684, "Pretrain/Step Time": 8.480030244216323} +{"Pretrain/Learning Rate": 4.215077921087798e-05, "Pretrain/Loss": 2.04496431350708, "Pretrain/Loss (Raw)": 1.97291898727417, "Pretrain/Step": 2685, "Pretrain/Step Time": 8.481726145371795} +{"Pretrain/Learning Rate": 4.214460055878329e-05, "Pretrain/Loss": 2.0452871322631836, "Pretrain/Loss (Raw)": 2.208479881286621, "Pretrain/Step": 2686, "Pretrain/Step Time": 8.482621235772967} +{"Pretrain/Learning Rate": 4.213841992906496e-05, "Pretrain/Loss": 2.043792724609375, "Pretrain/Loss (Raw)": 1.8745745420455933, "Pretrain/Step": 2687, "Pretrain/Step Time": 8.479888597503304} +{"Pretrain/Learning Rate": 4.213223732243591e-05, "Pretrain/Loss": 2.043604612350464, "Pretrain/Loss (Raw)": 2.0846848487854004, "Pretrain/Step": 2688, "Pretrain/Step Time": 8.477928614243865} +{"Pretrain/Learning Rate": 4.21260527396093e-05, "Pretrain/Loss": 2.044741630554199, "Pretrain/Loss (Raw)": 2.226708173751831, "Pretrain/Step": 2689, "Pretrain/Step Time": 8.478515909984708} +{"Pretrain/Learning Rate": 4.211986618129854e-05, "Pretrain/Loss": 2.046783924102783, "Pretrain/Loss (Raw)": 1.9829775094985962, "Pretrain/Step": 2690, "Pretrain/Step Time": 8.478106338530779} +{"Pretrain/Learning Rate": 4.211367764821722e-05, "Pretrain/Loss": 2.0504188537597656, "Pretrain/Loss (Raw)": 2.385197401046753, "Pretrain/Step": 2691, "Pretrain/Step Time": 8.481793647632003} +{"Pretrain/Learning Rate": 4.2107487141079206e-05, "Pretrain/Loss": 2.050996780395508, "Pretrain/Loss (Raw)": 2.1666924953460693, "Pretrain/Step": 2692, "Pretrain/Step Time": 8.481690803542733} +{"Pretrain/Learning Rate": 4.2101294660598556e-05, "Pretrain/Loss": 2.0503005981445312, "Pretrain/Loss (Raw)": 2.0406270027160645, "Pretrain/Step": 2693, "Pretrain/Step Time": 8.483400233089924} +{"Pretrain/Learning Rate": 4.209510020748957e-05, "Pretrain/Loss": 2.049992322921753, "Pretrain/Loss (Raw)": 2.003418445587158, "Pretrain/Step": 2694, "Pretrain/Step Time": 8.482595596462488} +{"Pretrain/Learning Rate": 4.2088903782466795e-05, "Pretrain/Loss": 2.048595905303955, "Pretrain/Loss (Raw)": 1.915083408355713, "Pretrain/Step": 2695, "Pretrain/Step Time": 8.482142250984907} +{"Pretrain/Learning Rate": 4.208270538624497e-05, "Pretrain/Loss": 2.0484488010406494, "Pretrain/Loss (Raw)": 1.9355965852737427, "Pretrain/Step": 2696, "Pretrain/Step Time": 8.483155474066734} +{"Pretrain/Learning Rate": 4.207650501953908e-05, "Pretrain/Loss": 2.04886531829834, "Pretrain/Loss (Raw)": 2.0077850818634033, "Pretrain/Step": 2697, "Pretrain/Step Time": 8.480096392333508} +{"Pretrain/Learning Rate": 4.2070302683064345e-05, "Pretrain/Loss": 2.049535036087036, "Pretrain/Loss (Raw)": 2.1780128479003906, "Pretrain/Step": 2698, "Pretrain/Step Time": 8.48468224145472} +{"Pretrain/Learning Rate": 4.206409837753618e-05, "Pretrain/Loss": 2.049182415008545, "Pretrain/Loss (Raw)": 2.054023504257202, "Pretrain/Step": 2699, "Pretrain/Step Time": 8.480549070984125} +{"Pretrain/Learning Rate": 4.2057892103670274e-05, "Pretrain/Loss": 2.049163818359375, "Pretrain/Loss (Raw)": 1.935157060623169, "Pretrain/Step": 2700, "Pretrain/Step Time": 8.482285698875785} +{"Pretrain/Learning Rate": 4.205168386218251e-05, "Pretrain/Loss": 2.047234535217285, "Pretrain/Loss (Raw)": 1.9182571172714233, "Pretrain/Step": 2701, "Pretrain/Step Time": 8.479834277182817} +{"Pretrain/Learning Rate": 4.2045473653789e-05, "Pretrain/Loss": 2.0454764366149902, "Pretrain/Loss (Raw)": 1.719065546989441, "Pretrain/Step": 2702, "Pretrain/Step Time": 8.48040416650474} +{"Pretrain/Learning Rate": 4.2039261479206094e-05, "Pretrain/Loss": 2.046046018600464, "Pretrain/Loss (Raw)": 2.076176404953003, "Pretrain/Step": 2703, "Pretrain/Step Time": 8.483765929937363} +{"Pretrain/Learning Rate": 4.203304733915036e-05, "Pretrain/Loss": 2.0464019775390625, "Pretrain/Loss (Raw)": 2.0430166721343994, "Pretrain/Step": 2704, "Pretrain/Step Time": 8.483475156128407} +{"Pretrain/Learning Rate": 4.202683123433862e-05, "Pretrain/Loss": 2.0461249351501465, "Pretrain/Loss (Raw)": 1.9229445457458496, "Pretrain/Step": 2705, "Pretrain/Step Time": 8.481413690373302} +{"Pretrain/Learning Rate": 4.202061316548787e-05, "Pretrain/Loss": 2.049210548400879, "Pretrain/Loss (Raw)": 1.889132022857666, "Pretrain/Step": 2706, "Pretrain/Step Time": 8.477126663550735} +{"Pretrain/Learning Rate": 4.2014393133315366e-05, "Pretrain/Loss": 2.049757957458496, "Pretrain/Loss (Raw)": 2.1813721656799316, "Pretrain/Step": 2707, "Pretrain/Step Time": 8.47535821609199} +{"Pretrain/Learning Rate": 4.20081711385386e-05, "Pretrain/Loss": 2.0474886894226074, "Pretrain/Loss (Raw)": 1.907959222793579, "Pretrain/Step": 2708, "Pretrain/Step Time": 8.47627610899508} +{"Pretrain/Learning Rate": 4.200194718187527e-05, "Pretrain/Loss": 2.04788875579834, "Pretrain/Loss (Raw)": 2.0976603031158447, "Pretrain/Step": 2709, "Pretrain/Step Time": 8.480465680360794} +{"Pretrain/Learning Rate": 4.1995721264043296e-05, "Pretrain/Loss": 2.046955108642578, "Pretrain/Loss (Raw)": 2.0097339153289795, "Pretrain/Step": 2710, "Pretrain/Step Time": 8.48084861971438} +{"Pretrain/Learning Rate": 4.1989493385760864e-05, "Pretrain/Loss": 2.04935884475708, "Pretrain/Loss (Raw)": 2.2750256061553955, "Pretrain/Step": 2711, "Pretrain/Step Time": 8.481086913496256} +{"Pretrain/Learning Rate": 4.198326354774633e-05, "Pretrain/Loss": 2.0500576496124268, "Pretrain/Loss (Raw)": 2.1200079917907715, "Pretrain/Step": 2712, "Pretrain/Step Time": 8.481108227744699} +{"Pretrain/Learning Rate": 4.197703175071832e-05, "Pretrain/Loss": 2.049947738647461, "Pretrain/Loss (Raw)": 2.015148639678955, "Pretrain/Step": 2713, "Pretrain/Step Time": 8.483337078243494} +{"Pretrain/Learning Rate": 4.197079799539566e-05, "Pretrain/Loss": 2.0488898754119873, "Pretrain/Loss (Raw)": 1.8510035276412964, "Pretrain/Step": 2714, "Pretrain/Step Time": 8.482033899053931} +{"Pretrain/Learning Rate": 4.196456228249742e-05, "Pretrain/Loss": 2.040917158126831, "Pretrain/Loss (Raw)": 1.1468489170074463, "Pretrain/Step": 2715, "Pretrain/Step Time": 8.481620399281383} +{"Pretrain/Learning Rate": 4.1958324612742875e-05, "Pretrain/Loss": 2.0415759086608887, "Pretrain/Loss (Raw)": 2.059131622314453, "Pretrain/Step": 2716, "Pretrain/Step Time": 8.483049716800451} +{"Pretrain/Learning Rate": 4.195208498685155e-05, "Pretrain/Loss": 2.040879249572754, "Pretrain/Loss (Raw)": 1.9077690839767456, "Pretrain/Step": 2717, "Pretrain/Step Time": 8.485158052295446} +{"Pretrain/Learning Rate": 4.194584340554318e-05, "Pretrain/Loss": 2.0397138595581055, "Pretrain/Loss (Raw)": 1.9984395503997803, "Pretrain/Step": 2718, "Pretrain/Step Time": 8.487377168610692} +{"Pretrain/Learning Rate": 4.193959986953773e-05, "Pretrain/Loss": 2.0399169921875, "Pretrain/Loss (Raw)": 2.163626194000244, "Pretrain/Step": 2719, "Pretrain/Step Time": 8.489620612934232} +{"Pretrain/Learning Rate": 4.193335437955538e-05, "Pretrain/Loss": 2.0419299602508545, "Pretrain/Loss (Raw)": 2.023973226547241, "Pretrain/Step": 2720, "Pretrain/Step Time": 8.488768363371491} +{"Pretrain/Learning Rate": 4.192710693631656e-05, "Pretrain/Loss": 2.0398571491241455, "Pretrain/Loss (Raw)": 2.0450501441955566, "Pretrain/Step": 2721, "Pretrain/Step Time": 8.488440150395036} +{"Pretrain/Learning Rate": 4.1920857540541905e-05, "Pretrain/Loss": 2.0403800010681152, "Pretrain/Loss (Raw)": 1.9574755430221558, "Pretrain/Step": 2722, "Pretrain/Step Time": 8.48630447871983} +{"Pretrain/Learning Rate": 4.191460619295227e-05, "Pretrain/Loss": 2.041255474090576, "Pretrain/Loss (Raw)": 2.035574436187744, "Pretrain/Step": 2723, "Pretrain/Step Time": 8.484067281708121} +{"Pretrain/Learning Rate": 4.1908352894268765e-05, "Pretrain/Loss": 2.040487766265869, "Pretrain/Loss (Raw)": 2.0004820823669434, "Pretrain/Step": 2724, "Pretrain/Step Time": 8.483164243400097} +{"Pretrain/Learning Rate": 4.190209764521269e-05, "Pretrain/Loss": 2.0401744842529297, "Pretrain/Loss (Raw)": 2.0874428749084473, "Pretrain/Step": 2725, "Pretrain/Step Time": 8.487124368548393} +{"Pretrain/Learning Rate": 4.1895840446505594e-05, "Pretrain/Loss": 2.0391111373901367, "Pretrain/Loss (Raw)": 1.9942162036895752, "Pretrain/Step": 2726, "Pretrain/Step Time": 8.48489191941917} +{"Pretrain/Learning Rate": 4.188958129886924e-05, "Pretrain/Loss": 2.038888931274414, "Pretrain/Loss (Raw)": 2.0266523361206055, "Pretrain/Step": 2727, "Pretrain/Step Time": 8.486472446471453} +{"Pretrain/Learning Rate": 4.188332020302561e-05, "Pretrain/Loss": 2.0385680198669434, "Pretrain/Loss (Raw)": 2.0443711280822754, "Pretrain/Step": 2728, "Pretrain/Step Time": 8.489055214449763} +{"Pretrain/Learning Rate": 4.1877057159696944e-05, "Pretrain/Loss": 2.0394811630249023, "Pretrain/Loss (Raw)": 2.138795852661133, "Pretrain/Step": 2729, "Pretrain/Step Time": 8.488241789862514} +{"Pretrain/Learning Rate": 4.187079216960565e-05, "Pretrain/Loss": 2.0397961139678955, "Pretrain/Loss (Raw)": 1.87118661403656, "Pretrain/Step": 2730, "Pretrain/Step Time": 8.488689376041293} +{"Pretrain/Learning Rate": 4.1864525233474414e-05, "Pretrain/Loss": 2.0379223823547363, "Pretrain/Loss (Raw)": 1.9088895320892334, "Pretrain/Step": 2731, "Pretrain/Step Time": 8.489019418135285} +{"Pretrain/Learning Rate": 4.1858256352026125e-05, "Pretrain/Loss": 2.0369515419006348, "Pretrain/Loss (Raw)": 2.1227200031280518, "Pretrain/Step": 2732, "Pretrain/Step Time": 8.48955031298101} +{"Pretrain/Learning Rate": 4.185198552598388e-05, "Pretrain/Loss": 2.0380382537841797, "Pretrain/Loss (Raw)": 2.1690216064453125, "Pretrain/Step": 2733, "Pretrain/Step Time": 8.487631818279624} +{"Pretrain/Learning Rate": 4.184571275607103e-05, "Pretrain/Loss": 2.0377676486968994, "Pretrain/Loss (Raw)": 1.9105397462844849, "Pretrain/Step": 2734, "Pretrain/Step Time": 8.4738276489079} +{"Pretrain/Learning Rate": 4.183943804301114e-05, "Pretrain/Loss": 2.039597272872925, "Pretrain/Loss (Raw)": 2.0720722675323486, "Pretrain/Step": 2735, "Pretrain/Step Time": 8.472140004858375} +{"Pretrain/Learning Rate": 4.1833161387527986e-05, "Pretrain/Loss": 2.039623975753784, "Pretrain/Loss (Raw)": 2.0182883739471436, "Pretrain/Step": 2736, "Pretrain/Step Time": 8.475357852876186} +{"Pretrain/Learning Rate": 4.182688279034558e-05, "Pretrain/Loss": 2.0398292541503906, "Pretrain/Loss (Raw)": 2.1412353515625, "Pretrain/Step": 2737, "Pretrain/Step Time": 8.47202000580728} +{"Pretrain/Learning Rate": 4.182060225218816e-05, "Pretrain/Loss": 2.0391111373901367, "Pretrain/Loss (Raw)": 1.9003183841705322, "Pretrain/Step": 2738, "Pretrain/Step Time": 8.47204658575356} +{"Pretrain/Learning Rate": 4.181431977378018e-05, "Pretrain/Loss": 2.0372910499572754, "Pretrain/Loss (Raw)": 1.9830286502838135, "Pretrain/Step": 2739, "Pretrain/Step Time": 8.472835611552} +{"Pretrain/Learning Rate": 4.180803535584632e-05, "Pretrain/Loss": 2.035109519958496, "Pretrain/Loss (Raw)": 1.95341157913208, "Pretrain/Step": 2740, "Pretrain/Step Time": 8.464331297203898} +{"Pretrain/Learning Rate": 4.180174899911149e-05, "Pretrain/Loss": 2.034559726715088, "Pretrain/Loss (Raw)": 2.0041325092315674, "Pretrain/Step": 2741, "Pretrain/Step Time": 8.465390587225556} +{"Pretrain/Learning Rate": 4.179546070430082e-05, "Pretrain/Loss": 2.035024642944336, "Pretrain/Loss (Raw)": 2.110170602798462, "Pretrain/Step": 2742, "Pretrain/Step Time": 8.470463601872325} +{"Pretrain/Learning Rate": 4.1789170472139655e-05, "Pretrain/Loss": 2.034027576446533, "Pretrain/Loss (Raw)": 2.021981716156006, "Pretrain/Step": 2743, "Pretrain/Step Time": 8.472682874649763} +{"Pretrain/Learning Rate": 4.178287830335358e-05, "Pretrain/Loss": 2.0330827236175537, "Pretrain/Loss (Raw)": 2.114706039428711, "Pretrain/Step": 2744, "Pretrain/Step Time": 8.474146526306868} +{"Pretrain/Learning Rate": 4.177658419866839e-05, "Pretrain/Loss": 2.03212308883667, "Pretrain/Loss (Raw)": 1.9837510585784912, "Pretrain/Step": 2745, "Pretrain/Step Time": 8.478247787803411} +{"Pretrain/Learning Rate": 4.177028815881011e-05, "Pretrain/Loss": 2.0315327644348145, "Pretrain/Loss (Raw)": 2.141207695007324, "Pretrain/Step": 2746, "Pretrain/Step Time": 8.474570138379931} +{"Pretrain/Learning Rate": 4.176399018450499e-05, "Pretrain/Loss": 2.0299201011657715, "Pretrain/Loss (Raw)": 1.8776576519012451, "Pretrain/Step": 2747, "Pretrain/Step Time": 8.47357483766973} +{"Pretrain/Learning Rate": 4.1757690276479476e-05, "Pretrain/Loss": 2.0312907695770264, "Pretrain/Loss (Raw)": 2.1333701610565186, "Pretrain/Step": 2748, "Pretrain/Step Time": 8.47432966530323} +{"Pretrain/Learning Rate": 4.175138843546029e-05, "Pretrain/Loss": 2.0325536727905273, "Pretrain/Loss (Raw)": 2.257417917251587, "Pretrain/Step": 2749, "Pretrain/Step Time": 8.476871244609356} +{"Pretrain/Learning Rate": 4.174508466217434e-05, "Pretrain/Loss": 2.029930353164673, "Pretrain/Loss (Raw)": 1.7629777193069458, "Pretrain/Step": 2750, "Pretrain/Step Time": 8.48072787746787} +{"Pretrain/Learning Rate": 4.1738778957348744e-05, "Pretrain/Loss": 2.0265769958496094, "Pretrain/Loss (Raw)": 1.8005046844482422, "Pretrain/Step": 2751, "Pretrain/Step Time": 8.479294586926699} +{"Pretrain/Learning Rate": 4.173247132171089e-05, "Pretrain/Loss": 2.0258922576904297, "Pretrain/Loss (Raw)": 2.1087136268615723, "Pretrain/Step": 2752, "Pretrain/Step Time": 8.47835430316627} +{"Pretrain/Learning Rate": 4.1726161755988344e-05, "Pretrain/Loss": 2.02705717086792, "Pretrain/Loss (Raw)": 2.103452682495117, "Pretrain/Step": 2753, "Pretrain/Step Time": 8.480023557320237} +{"Pretrain/Learning Rate": 4.171985026090892e-05, "Pretrain/Loss": 2.0249691009521484, "Pretrain/Loss (Raw)": 1.7805488109588623, "Pretrain/Step": 2754, "Pretrain/Step Time": 8.48021767474711} +{"Pretrain/Learning Rate": 4.171353683720064e-05, "Pretrain/Loss": 2.024195432662964, "Pretrain/Loss (Raw)": 2.0300259590148926, "Pretrain/Step": 2755, "Pretrain/Step Time": 8.48346259817481} +{"Pretrain/Learning Rate": 4.170722148559176e-05, "Pretrain/Loss": 2.023981809616089, "Pretrain/Loss (Raw)": 2.098018169403076, "Pretrain/Step": 2756, "Pretrain/Step Time": 8.484206276014447} +{"Pretrain/Learning Rate": 4.1700904206810755e-05, "Pretrain/Loss": 2.0247690677642822, "Pretrain/Loss (Raw)": 2.1175267696380615, "Pretrain/Step": 2757, "Pretrain/Step Time": 8.482205526903272} +{"Pretrain/Learning Rate": 4.169458500158632e-05, "Pretrain/Loss": 2.0236167907714844, "Pretrain/Loss (Raw)": 1.9299404621124268, "Pretrain/Step": 2758, "Pretrain/Step Time": 8.485790142789483} +{"Pretrain/Learning Rate": 4.168826387064737e-05, "Pretrain/Loss": 2.0237436294555664, "Pretrain/Loss (Raw)": 2.0699820518493652, "Pretrain/Step": 2759, "Pretrain/Step Time": 8.481716999784112} +{"Pretrain/Learning Rate": 4.168194081472305e-05, "Pretrain/Loss": 2.023442268371582, "Pretrain/Loss (Raw)": 2.0773942470550537, "Pretrain/Step": 2760, "Pretrain/Step Time": 8.479876669123769} +{"Pretrain/Learning Rate": 4.167561583454272e-05, "Pretrain/Loss": 2.023311138153076, "Pretrain/Loss (Raw)": 2.0595202445983887, "Pretrain/Step": 2761, "Pretrain/Step Time": 8.48628418892622} +{"Pretrain/Learning Rate": 4.166928893083596e-05, "Pretrain/Loss": 2.024609088897705, "Pretrain/Loss (Raw)": 2.1027846336364746, "Pretrain/Step": 2762, "Pretrain/Step Time": 8.485234504565597} +{"Pretrain/Learning Rate": 4.166296010433258e-05, "Pretrain/Loss": 2.024233102798462, "Pretrain/Loss (Raw)": 2.025087356567383, "Pretrain/Step": 2763, "Pretrain/Step Time": 8.482651269063354} +{"Pretrain/Learning Rate": 4.16566293557626e-05, "Pretrain/Loss": 2.026154041290283, "Pretrain/Loss (Raw)": 2.168275833129883, "Pretrain/Step": 2764, "Pretrain/Step Time": 8.48474777303636} +{"Pretrain/Learning Rate": 4.165029668585629e-05, "Pretrain/Loss": 2.0281832218170166, "Pretrain/Loss (Raw)": 2.17822527885437, "Pretrain/Step": 2765, "Pretrain/Step Time": 8.481495274230838} +{"Pretrain/Learning Rate": 4.164396209534411e-05, "Pretrain/Loss": 2.027981758117676, "Pretrain/Loss (Raw)": 1.9688175916671753, "Pretrain/Step": 2766, "Pretrain/Step Time": 8.48229544237256} +{"Pretrain/Learning Rate": 4.163762558495674e-05, "Pretrain/Loss": 2.029594659805298, "Pretrain/Loss (Raw)": 2.2756218910217285, "Pretrain/Step": 2767, "Pretrain/Step Time": 8.48591585457325} +{"Pretrain/Learning Rate": 4.163128715542511e-05, "Pretrain/Loss": 2.029407501220703, "Pretrain/Loss (Raw)": 2.0532174110412598, "Pretrain/Step": 2768, "Pretrain/Step Time": 8.485814217478037} +{"Pretrain/Learning Rate": 4.162494680748036e-05, "Pretrain/Loss": 2.0292649269104004, "Pretrain/Loss (Raw)": 2.1421961784362793, "Pretrain/Step": 2769, "Pretrain/Step Time": 8.482072550803423} +{"Pretrain/Learning Rate": 4.1618604541853826e-05, "Pretrain/Loss": 2.029811382293701, "Pretrain/Loss (Raw)": 2.1157596111297607, "Pretrain/Step": 2770, "Pretrain/Step Time": 8.479100655764341} +{"Pretrain/Learning Rate": 4.1612260359277114e-05, "Pretrain/Loss": 2.029226303100586, "Pretrain/Loss (Raw)": 1.992823839187622, "Pretrain/Step": 2771, "Pretrain/Step Time": 8.482660749927163} +{"Pretrain/Learning Rate": 4.160591426048199e-05, "Pretrain/Loss": 2.0292088985443115, "Pretrain/Loss (Raw)": 2.1245105266571045, "Pretrain/Step": 2772, "Pretrain/Step Time": 8.48182555474341} +{"Pretrain/Learning Rate": 4.1599566246200495e-05, "Pretrain/Loss": 2.0318808555603027, "Pretrain/Loss (Raw)": 2.0868000984191895, "Pretrain/Step": 2773, "Pretrain/Step Time": 8.481163760647178} +{"Pretrain/Learning Rate": 4.159321631716487e-05, "Pretrain/Loss": 2.0306010246276855, "Pretrain/Loss (Raw)": 2.096456527709961, "Pretrain/Step": 2774, "Pretrain/Step Time": 8.476133693009615} +{"Pretrain/Learning Rate": 4.158686447410758e-05, "Pretrain/Loss": 2.0309998989105225, "Pretrain/Loss (Raw)": 2.155184507369995, "Pretrain/Step": 2775, "Pretrain/Step Time": 8.478565029799938} +{"Pretrain/Learning Rate": 4.158051071776129e-05, "Pretrain/Loss": 2.032301187515259, "Pretrain/Loss (Raw)": 2.188558578491211, "Pretrain/Step": 2776, "Pretrain/Step Time": 8.477164551615715} +{"Pretrain/Learning Rate": 4.157415504885893e-05, "Pretrain/Loss": 2.032614231109619, "Pretrain/Loss (Raw)": 2.0904929637908936, "Pretrain/Step": 2777, "Pretrain/Step Time": 8.479086518287659} +{"Pretrain/Learning Rate": 4.156779746813359e-05, "Pretrain/Loss": 2.0354819297790527, "Pretrain/Loss (Raw)": 2.3273558616638184, "Pretrain/Step": 2778, "Pretrain/Step Time": 8.479804778471589} +{"Pretrain/Learning Rate": 4.1561437976318655e-05, "Pretrain/Loss": 2.0357658863067627, "Pretrain/Loss (Raw)": 2.121729850769043, "Pretrain/Step": 2779, "Pretrain/Step Time": 8.480037512257695} +{"Pretrain/Learning Rate": 4.155507657414766e-05, "Pretrain/Loss": 2.0359673500061035, "Pretrain/Loss (Raw)": 2.1248779296875, "Pretrain/Step": 2780, "Pretrain/Step Time": 8.477443393319845} +{"Pretrain/Learning Rate": 4.15487132623544e-05, "Pretrain/Loss": 2.036961317062378, "Pretrain/Loss (Raw)": 2.178112030029297, "Pretrain/Step": 2781, "Pretrain/Step Time": 8.481190722435713} +{"Pretrain/Learning Rate": 4.1542348041672884e-05, "Pretrain/Loss": 2.0381240844726562, "Pretrain/Loss (Raw)": 2.0280368328094482, "Pretrain/Step": 2782, "Pretrain/Step Time": 8.48077442497015} +{"Pretrain/Learning Rate": 4.153598091283733e-05, "Pretrain/Loss": 2.038177013397217, "Pretrain/Loss (Raw)": 2.066270112991333, "Pretrain/Step": 2783, "Pretrain/Step Time": 8.481952492147684} +{"Pretrain/Learning Rate": 4.15296118765822e-05, "Pretrain/Loss": 2.0380632877349854, "Pretrain/Loss (Raw)": 2.050333261489868, "Pretrain/Step": 2784, "Pretrain/Step Time": 8.481125863268971} +{"Pretrain/Learning Rate": 4.152324093364213e-05, "Pretrain/Loss": 2.038203716278076, "Pretrain/Loss (Raw)": 2.086183786392212, "Pretrain/Step": 2785, "Pretrain/Step Time": 8.48120367154479} +{"Pretrain/Learning Rate": 4.151686808475204e-05, "Pretrain/Loss": 2.040067195892334, "Pretrain/Loss (Raw)": 2.0822887420654297, "Pretrain/Step": 2786, "Pretrain/Step Time": 8.481166599318385} +{"Pretrain/Learning Rate": 4.151049333064702e-05, "Pretrain/Loss": 2.0382790565490723, "Pretrain/Loss (Raw)": 1.9336400032043457, "Pretrain/Step": 2787, "Pretrain/Step Time": 8.48223426938057} +{"Pretrain/Learning Rate": 4.1504116672062386e-05, "Pretrain/Loss": 2.037325382232666, "Pretrain/Loss (Raw)": 2.024592638015747, "Pretrain/Step": 2788, "Pretrain/Step Time": 8.48359457962215} +{"Pretrain/Learning Rate": 4.14977381097337e-05, "Pretrain/Loss": 2.036611557006836, "Pretrain/Loss (Raw)": 2.0805184841156006, "Pretrain/Step": 2789, "Pretrain/Step Time": 8.483204921707511} +{"Pretrain/Learning Rate": 4.149135764439672e-05, "Pretrain/Loss": 2.0362424850463867, "Pretrain/Loss (Raw)": 2.05730938911438, "Pretrain/Step": 2790, "Pretrain/Step Time": 8.488913748413324} +{"Pretrain/Learning Rate": 4.1484975276787435e-05, "Pretrain/Loss": 2.0356533527374268, "Pretrain/Loss (Raw)": 2.142853021621704, "Pretrain/Step": 2791, "Pretrain/Step Time": 8.484508480876684} +{"Pretrain/Learning Rate": 4.147859100764204e-05, "Pretrain/Loss": 2.0373616218566895, "Pretrain/Loss (Raw)": 2.0405468940734863, "Pretrain/Step": 2792, "Pretrain/Step Time": 8.48645087517798} +{"Pretrain/Learning Rate": 4.1472204837696974e-05, "Pretrain/Loss": 2.037111282348633, "Pretrain/Loss (Raw)": 2.0024547576904297, "Pretrain/Step": 2793, "Pretrain/Step Time": 8.485983692109585} +{"Pretrain/Learning Rate": 4.146581676768885e-05, "Pretrain/Loss": 2.03670072555542, "Pretrain/Loss (Raw)": 1.8350727558135986, "Pretrain/Step": 2794, "Pretrain/Step Time": 8.485127350315452} +{"Pretrain/Learning Rate": 4.145942679835456e-05, "Pretrain/Loss": 2.035832405090332, "Pretrain/Loss (Raw)": 2.016547918319702, "Pretrain/Step": 2795, "Pretrain/Step Time": 8.485163155943155} +{"Pretrain/Learning Rate": 4.145303493043118e-05, "Pretrain/Loss": 2.0368032455444336, "Pretrain/Loss (Raw)": 2.205960988998413, "Pretrain/Step": 2796, "Pretrain/Step Time": 8.484961619600654} +{"Pretrain/Learning Rate": 4.1446641164655984e-05, "Pretrain/Loss": 2.0358476638793945, "Pretrain/Loss (Raw)": 2.0589985847473145, "Pretrain/Step": 2797, "Pretrain/Step Time": 8.484646014869213} +{"Pretrain/Learning Rate": 4.144024550176653e-05, "Pretrain/Loss": 2.034189224243164, "Pretrain/Loss (Raw)": 2.010295867919922, "Pretrain/Step": 2798, "Pretrain/Step Time": 8.484956119209528} +{"Pretrain/Learning Rate": 4.143384794250052e-05, "Pretrain/Loss": 2.0317931175231934, "Pretrain/Loss (Raw)": 1.792346477508545, "Pretrain/Step": 2799, "Pretrain/Step Time": 8.485665263608098} +{"Pretrain/Learning Rate": 4.142744848759593e-05, "Pretrain/Loss": 2.030879497528076, "Pretrain/Loss (Raw)": 1.8616405725479126, "Pretrain/Step": 2800, "Pretrain/Step Time": 8.488994801416993} +{"Pretrain/Learning Rate": 4.142104713779093e-05, "Pretrain/Loss": 2.0303640365600586, "Pretrain/Loss (Raw)": 2.046452522277832, "Pretrain/Step": 2801, "Pretrain/Step Time": 8.488301454111934} +{"Pretrain/Learning Rate": 4.1414643893823914e-05, "Pretrain/Loss": 2.029472827911377, "Pretrain/Loss (Raw)": 2.091193437576294, "Pretrain/Step": 2802, "Pretrain/Step Time": 8.487690782174468} +{"Pretrain/Learning Rate": 4.1408238756433495e-05, "Pretrain/Loss": 2.0305161476135254, "Pretrain/Loss (Raw)": 2.077561855316162, "Pretrain/Step": 2803, "Pretrain/Step Time": 8.484565649181604} +{"Pretrain/Learning Rate": 4.14018317263585e-05, "Pretrain/Loss": 2.0313494205474854, "Pretrain/Loss (Raw)": 2.075716018676758, "Pretrain/Step": 2804, "Pretrain/Step Time": 8.483845042064786} +{"Pretrain/Learning Rate": 4.1395422804337974e-05, "Pretrain/Loss": 2.033168077468872, "Pretrain/Loss (Raw)": 1.9556657075881958, "Pretrain/Step": 2805, "Pretrain/Step Time": 8.48372589983046} +{"Pretrain/Learning Rate": 4.1389011991111195e-05, "Pretrain/Loss": 2.0316009521484375, "Pretrain/Loss (Raw)": 1.92354416847229, "Pretrain/Step": 2806, "Pretrain/Step Time": 8.48621648736298} +{"Pretrain/Learning Rate": 4.138259928741764e-05, "Pretrain/Loss": 2.0336878299713135, "Pretrain/Loss (Raw)": 2.032522678375244, "Pretrain/Step": 2807, "Pretrain/Step Time": 8.48980968631804} +{"Pretrain/Learning Rate": 4.137618469399702e-05, "Pretrain/Loss": 2.0346224308013916, "Pretrain/Loss (Raw)": 2.1201138496398926, "Pretrain/Step": 2808, "Pretrain/Step Time": 8.486741287633777} +{"Pretrain/Learning Rate": 4.136976821158924e-05, "Pretrain/Loss": 2.035846710205078, "Pretrain/Loss (Raw)": 1.9647094011306763, "Pretrain/Step": 2809, "Pretrain/Step Time": 8.488658141344786} +{"Pretrain/Learning Rate": 4.1363349840934464e-05, "Pretrain/Loss": 2.0375454425811768, "Pretrain/Loss (Raw)": 2.110846519470215, "Pretrain/Step": 2810, "Pretrain/Step Time": 8.49080509878695} +{"Pretrain/Learning Rate": 4.135692958277302e-05, "Pretrain/Loss": 2.0386743545532227, "Pretrain/Loss (Raw)": 2.146488904953003, "Pretrain/Step": 2811, "Pretrain/Step Time": 8.488044256344438} +{"Pretrain/Learning Rate": 4.13505074378455e-05, "Pretrain/Loss": 2.0367743968963623, "Pretrain/Loss (Raw)": 2.0075221061706543, "Pretrain/Step": 2812, "Pretrain/Step Time": 8.487529562786222} +{"Pretrain/Learning Rate": 4.13440834068927e-05, "Pretrain/Loss": 2.037245273590088, "Pretrain/Loss (Raw)": 2.033169984817505, "Pretrain/Step": 2813, "Pretrain/Step Time": 8.486500648781657} +{"Pretrain/Learning Rate": 4.133765749065562e-05, "Pretrain/Loss": 2.035036563873291, "Pretrain/Loss (Raw)": 1.9257683753967285, "Pretrain/Step": 2814, "Pretrain/Step Time": 8.492741286754608} +{"Pretrain/Learning Rate": 4.133122968987549e-05, "Pretrain/Loss": 2.0365753173828125, "Pretrain/Loss (Raw)": 2.0715856552124023, "Pretrain/Step": 2815, "Pretrain/Step Time": 8.492854695767164} +{"Pretrain/Learning Rate": 4.1324800005293754e-05, "Pretrain/Loss": 2.037135124206543, "Pretrain/Loss (Raw)": 2.1563117504119873, "Pretrain/Step": 2816, "Pretrain/Step Time": 8.493817400187254} +{"Pretrain/Learning Rate": 4.131836843765207e-05, "Pretrain/Loss": 2.0363454818725586, "Pretrain/Loss (Raw)": 2.125622034072876, "Pretrain/Step": 2817, "Pretrain/Step Time": 8.49113087169826} +{"Pretrain/Learning Rate": 4.131193498769232e-05, "Pretrain/Loss": 2.0378382205963135, "Pretrain/Loss (Raw)": 2.1740517616271973, "Pretrain/Step": 2818, "Pretrain/Step Time": 8.489224705845118} +{"Pretrain/Learning Rate": 4.130549965615662e-05, "Pretrain/Loss": 2.0349230766296387, "Pretrain/Loss (Raw)": 2.012079954147339, "Pretrain/Step": 2819, "Pretrain/Step Time": 8.485326660797} +{"Pretrain/Learning Rate": 4.129906244378724e-05, "Pretrain/Loss": 2.0334267616271973, "Pretrain/Loss (Raw)": 1.9751405715942383, "Pretrain/Step": 2820, "Pretrain/Step Time": 8.485170533880591} +{"Pretrain/Learning Rate": 4.129262335132675e-05, "Pretrain/Loss": 2.0345728397369385, "Pretrain/Loss (Raw)": 2.187321424484253, "Pretrain/Step": 2821, "Pretrain/Step Time": 8.484235303476453} +{"Pretrain/Learning Rate": 4.128618237951788e-05, "Pretrain/Loss": 2.0344314575195312, "Pretrain/Loss (Raw)": 1.985328197479248, "Pretrain/Step": 2822, "Pretrain/Step Time": 8.480991745367646} +{"Pretrain/Learning Rate": 4.1279739529103586e-05, "Pretrain/Loss": 2.0360283851623535, "Pretrain/Loss (Raw)": 2.119492530822754, "Pretrain/Step": 2823, "Pretrain/Step Time": 8.480397842824459} +{"Pretrain/Learning Rate": 4.127329480082708e-05, "Pretrain/Loss": 2.0372042655944824, "Pretrain/Loss (Raw)": 2.0861053466796875, "Pretrain/Step": 2824, "Pretrain/Step Time": 8.481918919831514} +{"Pretrain/Learning Rate": 4.126684819543172e-05, "Pretrain/Loss": 2.0382304191589355, "Pretrain/Loss (Raw)": 2.1391327381134033, "Pretrain/Step": 2825, "Pretrain/Step Time": 8.482261763885617} +{"Pretrain/Learning Rate": 4.126039971366114e-05, "Pretrain/Loss": 2.0375256538391113, "Pretrain/Loss (Raw)": 2.087800979614258, "Pretrain/Step": 2826, "Pretrain/Step Time": 8.482195595279336} +{"Pretrain/Learning Rate": 4.1253949356259166e-05, "Pretrain/Loss": 2.0381269454956055, "Pretrain/Loss (Raw)": 2.131009340286255, "Pretrain/Step": 2827, "Pretrain/Step Time": 8.481010004878044} +{"Pretrain/Learning Rate": 4.1247497123969844e-05, "Pretrain/Loss": 2.03928279876709, "Pretrain/Loss (Raw)": 2.083070993423462, "Pretrain/Step": 2828, "Pretrain/Step Time": 8.48116479255259} +{"Pretrain/Learning Rate": 4.124104301753745e-05, "Pretrain/Loss": 2.0403380393981934, "Pretrain/Loss (Raw)": 2.0533552169799805, "Pretrain/Step": 2829, "Pretrain/Step Time": 8.483692858368158} +{"Pretrain/Learning Rate": 4.123458703770645e-05, "Pretrain/Loss": 2.042325735092163, "Pretrain/Loss (Raw)": 1.973476767539978, "Pretrain/Step": 2830, "Pretrain/Step Time": 8.486368270590901} +{"Pretrain/Learning Rate": 4.122812918522153e-05, "Pretrain/Loss": 2.041494369506836, "Pretrain/Loss (Raw)": 1.969781756401062, "Pretrain/Step": 2831, "Pretrain/Step Time": 8.484116235747933} +{"Pretrain/Learning Rate": 4.122166946082762e-05, "Pretrain/Loss": 2.0420985221862793, "Pretrain/Loss (Raw)": 2.1203248500823975, "Pretrain/Step": 2832, "Pretrain/Step Time": 8.485639978200197} +{"Pretrain/Learning Rate": 4.1215207865269835e-05, "Pretrain/Loss": 2.0421199798583984, "Pretrain/Loss (Raw)": 1.925685167312622, "Pretrain/Step": 2833, "Pretrain/Step Time": 8.48504376783967} +{"Pretrain/Learning Rate": 4.120874439929352e-05, "Pretrain/Loss": 2.0430939197540283, "Pretrain/Loss (Raw)": 2.0138206481933594, "Pretrain/Step": 2834, "Pretrain/Step Time": 8.485348282381892} +{"Pretrain/Learning Rate": 4.120227906364423e-05, "Pretrain/Loss": 2.042273998260498, "Pretrain/Loss (Raw)": 2.076416492462158, "Pretrain/Step": 2835, "Pretrain/Step Time": 8.486784612759948} +{"Pretrain/Learning Rate": 4.1195811859067754e-05, "Pretrain/Loss": 2.043128252029419, "Pretrain/Loss (Raw)": 2.0172979831695557, "Pretrain/Step": 2836, "Pretrain/Step Time": 8.484057668596506} +{"Pretrain/Learning Rate": 4.118934278631007e-05, "Pretrain/Loss": 2.0426831245422363, "Pretrain/Loss (Raw)": 2.040680408477783, "Pretrain/Step": 2837, "Pretrain/Step Time": 8.479734787717462} +{"Pretrain/Learning Rate": 4.1182871846117375e-05, "Pretrain/Loss": 2.043944835662842, "Pretrain/Loss (Raw)": 2.1712427139282227, "Pretrain/Step": 2838, "Pretrain/Step Time": 8.480930015444756} +{"Pretrain/Learning Rate": 4.1176399039236116e-05, "Pretrain/Loss": 2.0426595211029053, "Pretrain/Loss (Raw)": 2.110501289367676, "Pretrain/Step": 2839, "Pretrain/Step Time": 8.47754511423409} +{"Pretrain/Learning Rate": 4.11699243664129e-05, "Pretrain/Loss": 2.0417065620422363, "Pretrain/Loss (Raw)": 1.9980627298355103, "Pretrain/Step": 2840, "Pretrain/Step Time": 8.478569140657783} +{"Pretrain/Learning Rate": 4.116344782839459e-05, "Pretrain/Loss": 2.041614055633545, "Pretrain/Loss (Raw)": 2.003283739089966, "Pretrain/Step": 2841, "Pretrain/Step Time": 8.480455903336406} +{"Pretrain/Learning Rate": 4.115696942592826e-05, "Pretrain/Loss": 2.0433740615844727, "Pretrain/Loss (Raw)": 2.0762736797332764, "Pretrain/Step": 2842, "Pretrain/Step Time": 8.479593832045794} +{"Pretrain/Learning Rate": 4.115048915976118e-05, "Pretrain/Loss": 2.0506677627563477, "Pretrain/Loss (Raw)": 2.0804550647735596, "Pretrain/Step": 2843, "Pretrain/Step Time": 8.47691822052002} +{"Pretrain/Learning Rate": 4.114400703064085e-05, "Pretrain/Loss": 2.049711227416992, "Pretrain/Loss (Raw)": 1.9366886615753174, "Pretrain/Step": 2844, "Pretrain/Step Time": 8.478148685768247} +{"Pretrain/Learning Rate": 4.1137523039314994e-05, "Pretrain/Loss": 2.049194812774658, "Pretrain/Loss (Raw)": 1.841652750968933, "Pretrain/Step": 2845, "Pretrain/Step Time": 8.474887814372778} +{"Pretrain/Learning Rate": 4.113103718653152e-05, "Pretrain/Loss": 2.0494067668914795, "Pretrain/Loss (Raw)": 2.025590419769287, "Pretrain/Step": 2846, "Pretrain/Step Time": 8.47388213314116} +{"Pretrain/Learning Rate": 4.112454947303856e-05, "Pretrain/Loss": 2.047593832015991, "Pretrain/Loss (Raw)": 1.93155837059021, "Pretrain/Step": 2847, "Pretrain/Step Time": 8.474357541650534} +{"Pretrain/Learning Rate": 4.111805989958451e-05, "Pretrain/Loss": 2.0475058555603027, "Pretrain/Loss (Raw)": 2.0127203464508057, "Pretrain/Step": 2848, "Pretrain/Step Time": 8.477668218314648} +{"Pretrain/Learning Rate": 4.11115684669179e-05, "Pretrain/Loss": 2.0475635528564453, "Pretrain/Loss (Raw)": 2.0524399280548096, "Pretrain/Step": 2849, "Pretrain/Step Time": 8.480030037462711} +{"Pretrain/Learning Rate": 4.110507517578753e-05, "Pretrain/Loss": 2.048743486404419, "Pretrain/Loss (Raw)": 2.108506679534912, "Pretrain/Step": 2850, "Pretrain/Step Time": 8.478710282593966} +{"Pretrain/Learning Rate": 4.10985800269424e-05, "Pretrain/Loss": 2.0465621948242188, "Pretrain/Loss (Raw)": 1.756373405456543, "Pretrain/Step": 2851, "Pretrain/Step Time": 8.47743571549654} +{"Pretrain/Learning Rate": 4.109208302113173e-05, "Pretrain/Loss": 2.0469419956207275, "Pretrain/Loss (Raw)": 2.0490787029266357, "Pretrain/Step": 2852, "Pretrain/Step Time": 8.479960141703486} +{"Pretrain/Learning Rate": 4.108558415910493e-05, "Pretrain/Loss": 2.044783592224121, "Pretrain/Loss (Raw)": 1.8111627101898193, "Pretrain/Step": 2853, "Pretrain/Step Time": 8.479642279446125} +{"Pretrain/Learning Rate": 4.107908344161165e-05, "Pretrain/Loss": 2.0452871322631836, "Pretrain/Loss (Raw)": 2.0586581230163574, "Pretrain/Step": 2854, "Pretrain/Step Time": 8.480828011408448} +{"Pretrain/Learning Rate": 4.107258086940174e-05, "Pretrain/Loss": 2.045429229736328, "Pretrain/Loss (Raw)": 2.0448620319366455, "Pretrain/Step": 2855, "Pretrain/Step Time": 8.476534646004438} +{"Pretrain/Learning Rate": 4.106607644322529e-05, "Pretrain/Loss": 2.045584201812744, "Pretrain/Loss (Raw)": 2.0642237663269043, "Pretrain/Step": 2856, "Pretrain/Step Time": 8.475549023598433} +{"Pretrain/Learning Rate": 4.105957016383256e-05, "Pretrain/Loss": 2.045186758041382, "Pretrain/Loss (Raw)": 2.0879125595092773, "Pretrain/Step": 2857, "Pretrain/Step Time": 8.476676786318421} +{"Pretrain/Learning Rate": 4.1053062031974055e-05, "Pretrain/Loss": 2.045818328857422, "Pretrain/Loss (Raw)": 1.9520429372787476, "Pretrain/Step": 2858, "Pretrain/Step Time": 8.477311443537474} +{"Pretrain/Learning Rate": 4.104655204840048e-05, "Pretrain/Loss": 2.0474586486816406, "Pretrain/Loss (Raw)": 2.118828058242798, "Pretrain/Step": 2859, "Pretrain/Step Time": 8.474178100004792} +{"Pretrain/Learning Rate": 4.104004021386277e-05, "Pretrain/Loss": 2.047128677368164, "Pretrain/Loss (Raw)": 2.0805001258850098, "Pretrain/Step": 2860, "Pretrain/Step Time": 8.47486312687397} +{"Pretrain/Learning Rate": 4.1033526529112064e-05, "Pretrain/Loss": 2.045109272003174, "Pretrain/Loss (Raw)": 1.910536766052246, "Pretrain/Step": 2861, "Pretrain/Step Time": 8.476826777681708} +{"Pretrain/Learning Rate": 4.1027010994899705e-05, "Pretrain/Loss": 2.0467963218688965, "Pretrain/Loss (Raw)": 2.1264724731445312, "Pretrain/Step": 2862, "Pretrain/Step Time": 8.476300027221441} +{"Pretrain/Learning Rate": 4.1020493611977265e-05, "Pretrain/Loss": 2.0470359325408936, "Pretrain/Loss (Raw)": 2.10274600982666, "Pretrain/Step": 2863, "Pretrain/Step Time": 8.475628716871142} +{"Pretrain/Learning Rate": 4.10139743810965e-05, "Pretrain/Loss": 2.0468811988830566, "Pretrain/Loss (Raw)": 1.998478889465332, "Pretrain/Step": 2864, "Pretrain/Step Time": 8.474988719448447} +{"Pretrain/Learning Rate": 4.100745330300943e-05, "Pretrain/Loss": 2.046180009841919, "Pretrain/Loss (Raw)": 2.0514845848083496, "Pretrain/Step": 2865, "Pretrain/Step Time": 8.473667984828353} +{"Pretrain/Learning Rate": 4.100093037846825e-05, "Pretrain/Loss": 2.0492355823516846, "Pretrain/Loss (Raw)": 2.2914326190948486, "Pretrain/Step": 2866, "Pretrain/Step Time": 8.474937334656715} +{"Pretrain/Learning Rate": 4.099440560822536e-05, "Pretrain/Loss": 2.050912857055664, "Pretrain/Loss (Raw)": 2.197723627090454, "Pretrain/Step": 2867, "Pretrain/Step Time": 8.471139812842011} +{"Pretrain/Learning Rate": 4.0987878993033415e-05, "Pretrain/Loss": 2.0518319606781006, "Pretrain/Loss (Raw)": 2.0710504055023193, "Pretrain/Step": 2868, "Pretrain/Step Time": 8.473346861079335} +{"Pretrain/Learning Rate": 4.098135053364525e-05, "Pretrain/Loss": 2.052344560623169, "Pretrain/Loss (Raw)": 2.069749116897583, "Pretrain/Step": 2869, "Pretrain/Step Time": 8.472766820341349} +{"Pretrain/Learning Rate": 4.097482023081391e-05, "Pretrain/Loss": 2.053034782409668, "Pretrain/Loss (Raw)": 2.1985387802124023, "Pretrain/Step": 2870, "Pretrain/Step Time": 8.470445942133665} +{"Pretrain/Learning Rate": 4.096828808529267e-05, "Pretrain/Loss": 2.0536370277404785, "Pretrain/Loss (Raw)": 2.0990495681762695, "Pretrain/Step": 2871, "Pretrain/Step Time": 8.467673635110259} +{"Pretrain/Learning Rate": 4.0961754097835015e-05, "Pretrain/Loss": 2.053983688354492, "Pretrain/Loss (Raw)": 2.1590464115142822, "Pretrain/Step": 2872, "Pretrain/Step Time": 8.467538326978683} +{"Pretrain/Learning Rate": 4.0955218269194626e-05, "Pretrain/Loss": 2.0552546977996826, "Pretrain/Loss (Raw)": 2.1464743614196777, "Pretrain/Step": 2873, "Pretrain/Step Time": 8.467617150396109} +{"Pretrain/Learning Rate": 4.0948680600125433e-05, "Pretrain/Loss": 2.054994583129883, "Pretrain/Loss (Raw)": 2.1078922748565674, "Pretrain/Step": 2874, "Pretrain/Step Time": 8.466590076684952} +{"Pretrain/Learning Rate": 4.094214109138153e-05, "Pretrain/Loss": 2.0563347339630127, "Pretrain/Loss (Raw)": 2.0492231845855713, "Pretrain/Step": 2875, "Pretrain/Step Time": 8.46658437512815} +{"Pretrain/Learning Rate": 4.093559974371725e-05, "Pretrain/Loss": 2.0553574562072754, "Pretrain/Loss (Raw)": 2.0082616806030273, "Pretrain/Step": 2876, "Pretrain/Step Time": 8.467016698792577} +{"Pretrain/Learning Rate": 4.092905655788714e-05, "Pretrain/Loss": 2.0540804862976074, "Pretrain/Loss (Raw)": 2.0939910411834717, "Pretrain/Step": 2877, "Pretrain/Step Time": 8.466204861178994} +{"Pretrain/Learning Rate": 4.092251153464595e-05, "Pretrain/Loss": 2.057147741317749, "Pretrain/Loss (Raw)": 2.1555638313293457, "Pretrain/Step": 2878, "Pretrain/Step Time": 8.465410646051168} +{"Pretrain/Learning Rate": 4.091596467474866e-05, "Pretrain/Loss": 2.059891700744629, "Pretrain/Loss (Raw)": 2.151740074157715, "Pretrain/Step": 2879, "Pretrain/Step Time": 8.466045372188091} +{"Pretrain/Learning Rate": 4.0909415978950434e-05, "Pretrain/Loss": 2.058804512023926, "Pretrain/Loss (Raw)": 1.969528079032898, "Pretrain/Step": 2880, "Pretrain/Step Time": 8.465367630124092} +{"Pretrain/Learning Rate": 4.0902865448006665e-05, "Pretrain/Loss": 2.05667781829834, "Pretrain/Loss (Raw)": 1.8312410116195679, "Pretrain/Step": 2881, "Pretrain/Step Time": 8.46489461697638} +{"Pretrain/Learning Rate": 4.0896313082672956e-05, "Pretrain/Loss": 2.0579490661621094, "Pretrain/Loss (Raw)": 1.9432735443115234, "Pretrain/Step": 2882, "Pretrain/Step Time": 8.465192642062902} +{"Pretrain/Learning Rate": 4.088975888370512e-05, "Pretrain/Loss": 2.058321475982666, "Pretrain/Loss (Raw)": 2.077711343765259, "Pretrain/Step": 2883, "Pretrain/Step Time": 8.46320130303502} +{"Pretrain/Learning Rate": 4.088320285185918e-05, "Pretrain/Loss": 2.059807538986206, "Pretrain/Loss (Raw)": 2.2882449626922607, "Pretrain/Step": 2884, "Pretrain/Step Time": 8.461452212184668} +{"Pretrain/Learning Rate": 4.087664498789137e-05, "Pretrain/Loss": 2.059370994567871, "Pretrain/Loss (Raw)": 2.0616250038146973, "Pretrain/Step": 2885, "Pretrain/Step Time": 8.462198980152607} +{"Pretrain/Learning Rate": 4.0870085292558145e-05, "Pretrain/Loss": 2.0596988201141357, "Pretrain/Loss (Raw)": 1.9719109535217285, "Pretrain/Step": 2886, "Pretrain/Step Time": 8.459809388965368} +{"Pretrain/Learning Rate": 4.0863523766616157e-05, "Pretrain/Loss": 2.0615148544311523, "Pretrain/Loss (Raw)": 2.302428722381592, "Pretrain/Step": 2887, "Pretrain/Step Time": 8.458029236644506} +{"Pretrain/Learning Rate": 4.085696041082228e-05, "Pretrain/Loss": 2.061814308166504, "Pretrain/Loss (Raw)": 2.1157350540161133, "Pretrain/Step": 2888, "Pretrain/Step Time": 8.457774750888348} +{"Pretrain/Learning Rate": 4.085039522593358e-05, "Pretrain/Loss": 2.0614538192749023, "Pretrain/Loss (Raw)": 2.0133657455444336, "Pretrain/Step": 2889, "Pretrain/Step Time": 8.454877566546202} +{"Pretrain/Learning Rate": 4.084382821270737e-05, "Pretrain/Loss": 2.060698986053467, "Pretrain/Loss (Raw)": 2.0061724185943604, "Pretrain/Step": 2890, "Pretrain/Step Time": 8.45706912688911} +{"Pretrain/Learning Rate": 4.083725937190115e-05, "Pretrain/Loss": 2.0610597133636475, "Pretrain/Loss (Raw)": 2.0712664127349854, "Pretrain/Step": 2891, "Pretrain/Step Time": 8.458677738904953} +{"Pretrain/Learning Rate": 4.083068870427262e-05, "Pretrain/Loss": 2.0600569248199463, "Pretrain/Loss (Raw)": 2.0399057865142822, "Pretrain/Step": 2892, "Pretrain/Step Time": 8.455026315525174} +{"Pretrain/Learning Rate": 4.082411621057971e-05, "Pretrain/Loss": 2.059765338897705, "Pretrain/Loss (Raw)": 2.1409268379211426, "Pretrain/Step": 2893, "Pretrain/Step Time": 8.454754726961255} +{"Pretrain/Learning Rate": 4.081754189158056e-05, "Pretrain/Loss": 2.0605976581573486, "Pretrain/Loss (Raw)": 2.0753414630889893, "Pretrain/Step": 2894, "Pretrain/Step Time": 8.456676112487912} +{"Pretrain/Learning Rate": 4.081096574803351e-05, "Pretrain/Loss": 2.057645320892334, "Pretrain/Loss (Raw)": 1.8976930379867554, "Pretrain/Step": 2895, "Pretrain/Step Time": 8.453206431120634} +{"Pretrain/Learning Rate": 4.080438778069711e-05, "Pretrain/Loss": 2.0581588745117188, "Pretrain/Loss (Raw)": 2.118969202041626, "Pretrain/Step": 2896, "Pretrain/Step Time": 8.453533958643675} +{"Pretrain/Learning Rate": 4.0797807990330136e-05, "Pretrain/Loss": 2.056569814682007, "Pretrain/Loss (Raw)": 1.9388076066970825, "Pretrain/Step": 2897, "Pretrain/Step Time": 8.453161193057895} +{"Pretrain/Learning Rate": 4.079122637769157e-05, "Pretrain/Loss": 2.0563390254974365, "Pretrain/Loss (Raw)": 2.0862197875976562, "Pretrain/Step": 2898, "Pretrain/Step Time": 8.45280129276216} +{"Pretrain/Learning Rate": 4.078464294354059e-05, "Pretrain/Loss": 2.0569982528686523, "Pretrain/Loss (Raw)": 2.0772032737731934, "Pretrain/Step": 2899, "Pretrain/Step Time": 8.451447641476989} +{"Pretrain/Learning Rate": 4.07780576886366e-05, "Pretrain/Loss": 2.0566487312316895, "Pretrain/Loss (Raw)": 2.07979154586792, "Pretrain/Step": 2900, "Pretrain/Step Time": 8.452999778091908} +{"Pretrain/Learning Rate": 4.077147061373918e-05, "Pretrain/Loss": 2.0572006702423096, "Pretrain/Loss (Raw)": 2.157439708709717, "Pretrain/Step": 2901, "Pretrain/Step Time": 8.45263489894569} +{"Pretrain/Learning Rate": 4.0764881719608185e-05, "Pretrain/Loss": 2.058718681335449, "Pretrain/Loss (Raw)": 2.2907490730285645, "Pretrain/Step": 2902, "Pretrain/Step Time": 8.453557660803199} +{"Pretrain/Learning Rate": 4.0758291007003615e-05, "Pretrain/Loss": 2.0589332580566406, "Pretrain/Loss (Raw)": 2.1826350688934326, "Pretrain/Step": 2903, "Pretrain/Step Time": 8.451014356687665} +{"Pretrain/Learning Rate": 4.075169847668572e-05, "Pretrain/Loss": 2.0567240715026855, "Pretrain/Loss (Raw)": 1.9058045148849487, "Pretrain/Step": 2904, "Pretrain/Step Time": 8.452032212167978} +{"Pretrain/Learning Rate": 4.074510412941493e-05, "Pretrain/Loss": 2.0545496940612793, "Pretrain/Loss (Raw)": 1.8121427297592163, "Pretrain/Step": 2905, "Pretrain/Step Time": 8.450544472783804} +{"Pretrain/Learning Rate": 4.073850796595192e-05, "Pretrain/Loss": 2.0525894165039062, "Pretrain/Loss (Raw)": 2.076474905014038, "Pretrain/Step": 2906, "Pretrain/Step Time": 8.448349747806787} +{"Pretrain/Learning Rate": 4.073190998705755e-05, "Pretrain/Loss": 2.052865982055664, "Pretrain/Loss (Raw)": 2.1570985317230225, "Pretrain/Step": 2907, "Pretrain/Step Time": 8.450261238962412} +{"Pretrain/Learning Rate": 4.0725310193492895e-05, "Pretrain/Loss": 2.0539467334747314, "Pretrain/Loss (Raw)": 2.2632365226745605, "Pretrain/Step": 2908, "Pretrain/Step Time": 8.450872166082263} +{"Pretrain/Learning Rate": 4.0718708586019225e-05, "Pretrain/Loss": 2.053433895111084, "Pretrain/Loss (Raw)": 2.1124799251556396, "Pretrain/Step": 2909, "Pretrain/Step Time": 8.447478495538235} +{"Pretrain/Learning Rate": 4.071210516539804e-05, "Pretrain/Loss": 2.0523147583007812, "Pretrain/Loss (Raw)": 1.8848055601119995, "Pretrain/Step": 2910, "Pretrain/Step Time": 8.44995129108429} +{"Pretrain/Learning Rate": 4.070549993239106e-05, "Pretrain/Loss": 2.052295684814453, "Pretrain/Loss (Raw)": 2.063809633255005, "Pretrain/Step": 2911, "Pretrain/Step Time": 8.447104543447495} +{"Pretrain/Learning Rate": 4.069889288776018e-05, "Pretrain/Loss": 2.052204132080078, "Pretrain/Loss (Raw)": 2.0386228561401367, "Pretrain/Step": 2912, "Pretrain/Step Time": 8.446957886219025} +{"Pretrain/Learning Rate": 4.0692284032267516e-05, "Pretrain/Loss": 2.051633596420288, "Pretrain/Loss (Raw)": 2.0131287574768066, "Pretrain/Step": 2913, "Pretrain/Step Time": 8.450418964028358} +{"Pretrain/Learning Rate": 4.06856733666754e-05, "Pretrain/Loss": 2.0525054931640625, "Pretrain/Loss (Raw)": 2.1939072608947754, "Pretrain/Step": 2914, "Pretrain/Step Time": 8.4492526371032} +{"Pretrain/Learning Rate": 4.0679060891746386e-05, "Pretrain/Loss": 2.053605079650879, "Pretrain/Loss (Raw)": 2.0743682384490967, "Pretrain/Step": 2915, "Pretrain/Step Time": 8.446199653670192} +{"Pretrain/Learning Rate": 4.06724466082432e-05, "Pretrain/Loss": 2.054269313812256, "Pretrain/Loss (Raw)": 2.109637498855591, "Pretrain/Step": 2916, "Pretrain/Step Time": 8.446003599092364} +{"Pretrain/Learning Rate": 4.066583051692881e-05, "Pretrain/Loss": 2.0545806884765625, "Pretrain/Loss (Raw)": 2.1203694343566895, "Pretrain/Step": 2917, "Pretrain/Step Time": 8.443955203518271} +{"Pretrain/Learning Rate": 4.065921261856637e-05, "Pretrain/Loss": 2.0552103519439697, "Pretrain/Loss (Raw)": 2.137911796569824, "Pretrain/Step": 2918, "Pretrain/Step Time": 8.43718876130879} +{"Pretrain/Learning Rate": 4.065259291391926e-05, "Pretrain/Loss": 2.054142951965332, "Pretrain/Loss (Raw)": 2.0062224864959717, "Pretrain/Step": 2919, "Pretrain/Step Time": 8.439648987725377} +{"Pretrain/Learning Rate": 4.064597140375105e-05, "Pretrain/Loss": 2.053891897201538, "Pretrain/Loss (Raw)": 2.0084049701690674, "Pretrain/Step": 2920, "Pretrain/Step Time": 8.438291335478425} +{"Pretrain/Learning Rate": 4.0639348088825554e-05, "Pretrain/Loss": 2.054597854614258, "Pretrain/Loss (Raw)": 2.0928144454956055, "Pretrain/Step": 2921, "Pretrain/Step Time": 8.437654260545969} +{"Pretrain/Learning Rate": 4.063272296990674e-05, "Pretrain/Loss": 2.055664300918579, "Pretrain/Loss (Raw)": 1.9715783596038818, "Pretrain/Step": 2922, "Pretrain/Step Time": 8.434846432879567} +{"Pretrain/Learning Rate": 4.0626096047758824e-05, "Pretrain/Loss": 2.0570154190063477, "Pretrain/Loss (Raw)": 2.1894803047180176, "Pretrain/Step": 2923, "Pretrain/Step Time": 8.434809923171997} +{"Pretrain/Learning Rate": 4.061946732314622e-05, "Pretrain/Loss": 2.055474281311035, "Pretrain/Loss (Raw)": 2.0086894035339355, "Pretrain/Step": 2924, "Pretrain/Step Time": 8.43363519012928} +{"Pretrain/Learning Rate": 4.061283679683356e-05, "Pretrain/Loss": 2.055912971496582, "Pretrain/Loss (Raw)": 2.115177631378174, "Pretrain/Step": 2925, "Pretrain/Step Time": 8.434598622843623} +{"Pretrain/Learning Rate": 4.060620446958565e-05, "Pretrain/Loss": 2.0566070079803467, "Pretrain/Loss (Raw)": 2.099128484725952, "Pretrain/Step": 2926, "Pretrain/Step Time": 8.433701215311885} +{"Pretrain/Learning Rate": 4.0599570342167546e-05, "Pretrain/Loss": 2.0588626861572266, "Pretrain/Loss (Raw)": 2.0810623168945312, "Pretrain/Step": 2927, "Pretrain/Step Time": 8.431052641943097} +{"Pretrain/Learning Rate": 4.0592934415344485e-05, "Pretrain/Loss": 2.0606560707092285, "Pretrain/Loss (Raw)": 2.0912106037139893, "Pretrain/Step": 2928, "Pretrain/Step Time": 8.429023070260882} +{"Pretrain/Learning Rate": 4.058629668988192e-05, "Pretrain/Loss": 2.0607028007507324, "Pretrain/Loss (Raw)": 2.052405595779419, "Pretrain/Step": 2929, "Pretrain/Step Time": 8.430407628417015} +{"Pretrain/Learning Rate": 4.0579657166545505e-05, "Pretrain/Loss": 2.0605289936065674, "Pretrain/Loss (Raw)": 2.0689682960510254, "Pretrain/Step": 2930, "Pretrain/Step Time": 8.43545052409172} +{"Pretrain/Learning Rate": 4.0573015846101117e-05, "Pretrain/Loss": 2.0612337589263916, "Pretrain/Loss (Raw)": 2.1677820682525635, "Pretrain/Step": 2931, "Pretrain/Step Time": 8.435007683932781} +{"Pretrain/Learning Rate": 4.056637272931482e-05, "Pretrain/Loss": 2.060275077819824, "Pretrain/Loss (Raw)": 1.9529755115509033, "Pretrain/Step": 2932, "Pretrain/Step Time": 8.43600618839264} +{"Pretrain/Learning Rate": 4.0559727816952894e-05, "Pretrain/Loss": 2.0611562728881836, "Pretrain/Loss (Raw)": 2.0684609413146973, "Pretrain/Step": 2933, "Pretrain/Step Time": 8.435824368149042} +{"Pretrain/Learning Rate": 4.0553081109781844e-05, "Pretrain/Loss": 2.061521053314209, "Pretrain/Loss (Raw)": 1.9702390432357788, "Pretrain/Step": 2934, "Pretrain/Step Time": 8.433377597481012} +{"Pretrain/Learning Rate": 4.054643260856834e-05, "Pretrain/Loss": 2.0619678497314453, "Pretrain/Loss (Raw)": 2.089728593826294, "Pretrain/Step": 2935, "Pretrain/Step Time": 8.429902391508222} +{"Pretrain/Learning Rate": 4.053978231407931e-05, "Pretrain/Loss": 2.061450719833374, "Pretrain/Loss (Raw)": 2.053922176361084, "Pretrain/Step": 2936, "Pretrain/Step Time": 8.428142564371228} +{"Pretrain/Learning Rate": 4.053313022708184e-05, "Pretrain/Loss": 2.0619752407073975, "Pretrain/Loss (Raw)": 2.0318446159362793, "Pretrain/Step": 2937, "Pretrain/Step Time": 8.425622548907995} +{"Pretrain/Learning Rate": 4.052647634834327e-05, "Pretrain/Loss": 2.062530517578125, "Pretrain/Loss (Raw)": 2.18192720413208, "Pretrain/Step": 2938, "Pretrain/Step Time": 8.428128754720092} +{"Pretrain/Learning Rate": 4.0519820678631094e-05, "Pretrain/Loss": 2.0623319149017334, "Pretrain/Loss (Raw)": 2.1210713386535645, "Pretrain/Step": 2939, "Pretrain/Step Time": 8.428026728332043} +{"Pretrain/Learning Rate": 4.051316321871307e-05, "Pretrain/Loss": 2.0624728202819824, "Pretrain/Loss (Raw)": 2.0255544185638428, "Pretrain/Step": 2940, "Pretrain/Step Time": 8.429101768881083} +{"Pretrain/Learning Rate": 4.050650396935711e-05, "Pretrain/Loss": 2.0627360343933105, "Pretrain/Loss (Raw)": 2.066840887069702, "Pretrain/Step": 2941, "Pretrain/Step Time": 8.427576210349798} +{"Pretrain/Learning Rate": 4.049984293133138e-05, "Pretrain/Loss": 2.063424587249756, "Pretrain/Loss (Raw)": 2.0139057636260986, "Pretrain/Step": 2942, "Pretrain/Step Time": 8.424437955021858} +{"Pretrain/Learning Rate": 4.04931801054042e-05, "Pretrain/Loss": 2.0617222785949707, "Pretrain/Loss (Raw)": 1.8536808490753174, "Pretrain/Step": 2943, "Pretrain/Step Time": 8.425318144261837} +{"Pretrain/Learning Rate": 4.048651549234415e-05, "Pretrain/Loss": 2.059684991836548, "Pretrain/Loss (Raw)": 1.8955488204956055, "Pretrain/Step": 2944, "Pretrain/Step Time": 8.424237364903092} +{"Pretrain/Learning Rate": 4.0479849092919974e-05, "Pretrain/Loss": 2.0590107440948486, "Pretrain/Loss (Raw)": 2.039329767227173, "Pretrain/Step": 2945, "Pretrain/Step Time": 8.426137862727046} +{"Pretrain/Learning Rate": 4.047318090790065e-05, "Pretrain/Loss": 2.056621551513672, "Pretrain/Loss (Raw)": 1.8682535886764526, "Pretrain/Step": 2946, "Pretrain/Step Time": 8.429852539673448} +{"Pretrain/Learning Rate": 4.046651093805534e-05, "Pretrain/Loss": 2.0560641288757324, "Pretrain/Loss (Raw)": 1.9407057762145996, "Pretrain/Step": 2947, "Pretrain/Step Time": 8.429772689938545} +{"Pretrain/Learning Rate": 4.0459839184153435e-05, "Pretrain/Loss": 2.056835651397705, "Pretrain/Loss (Raw)": 2.0738725662231445, "Pretrain/Step": 2948, "Pretrain/Step Time": 8.428033042699099} +{"Pretrain/Learning Rate": 4.045316564696451e-05, "Pretrain/Loss": 2.0549476146698, "Pretrain/Loss (Raw)": 1.9456548690795898, "Pretrain/Step": 2949, "Pretrain/Step Time": 8.429578140377998} +{"Pretrain/Learning Rate": 4.044649032725836e-05, "Pretrain/Loss": 2.055807113647461, "Pretrain/Loss (Raw)": 2.0953471660614014, "Pretrain/Step": 2950, "Pretrain/Step Time": 8.431322293356061} +{"Pretrain/Learning Rate": 4.043981322580498e-05, "Pretrain/Loss": 2.0562403202056885, "Pretrain/Loss (Raw)": 2.1749539375305176, "Pretrain/Step": 2951, "Pretrain/Step Time": 8.432193906977773} +{"Pretrain/Learning Rate": 4.043313434337457e-05, "Pretrain/Loss": 2.055856227874756, "Pretrain/Loss (Raw)": 2.0369391441345215, "Pretrain/Step": 2952, "Pretrain/Step Time": 8.429362958297133} +{"Pretrain/Learning Rate": 4.042645368073754e-05, "Pretrain/Loss": 2.0557875633239746, "Pretrain/Loss (Raw)": 2.130354642868042, "Pretrain/Step": 2953, "Pretrain/Step Time": 8.429037479683757} +{"Pretrain/Learning Rate": 4.0419771238664485e-05, "Pretrain/Loss": 2.0556416511535645, "Pretrain/Loss (Raw)": 2.0691428184509277, "Pretrain/Step": 2954, "Pretrain/Step Time": 8.42610233835876} +{"Pretrain/Learning Rate": 4.041308701792625e-05, "Pretrain/Loss": 2.0551156997680664, "Pretrain/Loss (Raw)": 2.063673257827759, "Pretrain/Step": 2955, "Pretrain/Step Time": 8.429280895739794} +{"Pretrain/Learning Rate": 4.040640101929384e-05, "Pretrain/Loss": 2.055431842803955, "Pretrain/Loss (Raw)": 2.123525619506836, "Pretrain/Step": 2956, "Pretrain/Step Time": 8.429414076730609} +{"Pretrain/Learning Rate": 4.039971324353849e-05, "Pretrain/Loss": 2.0554652214050293, "Pretrain/Loss (Raw)": 2.057623863220215, "Pretrain/Step": 2957, "Pretrain/Step Time": 8.429913500323892} +{"Pretrain/Learning Rate": 4.039302369143162e-05, "Pretrain/Loss": 2.055649757385254, "Pretrain/Loss (Raw)": 1.9971128702163696, "Pretrain/Step": 2958, "Pretrain/Step Time": 8.428052812814713} +{"Pretrain/Learning Rate": 4.0386332363744886e-05, "Pretrain/Loss": 2.0570459365844727, "Pretrain/Loss (Raw)": 2.1484601497650146, "Pretrain/Step": 2959, "Pretrain/Step Time": 8.428168492391706} +{"Pretrain/Learning Rate": 4.037963926125011e-05, "Pretrain/Loss": 2.05646014213562, "Pretrain/Loss (Raw)": 2.045355796813965, "Pretrain/Step": 2960, "Pretrain/Step Time": 8.426612541079521} +{"Pretrain/Learning Rate": 4.0372944384719364e-05, "Pretrain/Loss": 2.0564441680908203, "Pretrain/Loss (Raw)": 1.9236630201339722, "Pretrain/Step": 2961, "Pretrain/Step Time": 8.427522033452988} +{"Pretrain/Learning Rate": 4.036624773492488e-05, "Pretrain/Loss": 2.057079553604126, "Pretrain/Loss (Raw)": 2.0951313972473145, "Pretrain/Step": 2962, "Pretrain/Step Time": 8.429758494719863} +{"Pretrain/Learning Rate": 4.035954931263912e-05, "Pretrain/Loss": 2.0531163215637207, "Pretrain/Loss (Raw)": 1.5691051483154297, "Pretrain/Step": 2963, "Pretrain/Step Time": 8.429041750729084} +{"Pretrain/Learning Rate": 4.035284911863474e-05, "Pretrain/Loss": 2.053292751312256, "Pretrain/Loss (Raw)": 2.0398800373077393, "Pretrain/Step": 2964, "Pretrain/Step Time": 8.42850036546588} +{"Pretrain/Learning Rate": 4.034614715368461e-05, "Pretrain/Loss": 2.0528414249420166, "Pretrain/Loss (Raw)": 1.9829226732254028, "Pretrain/Step": 2965, "Pretrain/Step Time": 8.432216811925173} +{"Pretrain/Learning Rate": 4.0339443418561805e-05, "Pretrain/Loss": 2.052034616470337, "Pretrain/Loss (Raw)": 2.0679738521575928, "Pretrain/Step": 2966, "Pretrain/Step Time": 8.430541874840856} +{"Pretrain/Learning Rate": 4.0332737914039585e-05, "Pretrain/Loss": 2.053140163421631, "Pretrain/Loss (Raw)": 2.2520315647125244, "Pretrain/Step": 2967, "Pretrain/Step Time": 8.436533452942967} +{"Pretrain/Learning Rate": 4.032603064089144e-05, "Pretrain/Loss": 2.0540595054626465, "Pretrain/Loss (Raw)": 2.115711212158203, "Pretrain/Step": 2968, "Pretrain/Step Time": 8.435535354539752} +{"Pretrain/Learning Rate": 4.0319321599891044e-05, "Pretrain/Loss": 2.0540428161621094, "Pretrain/Loss (Raw)": 2.001157522201538, "Pretrain/Step": 2969, "Pretrain/Step Time": 8.43259415216744} +{"Pretrain/Learning Rate": 4.0312610791812286e-05, "Pretrain/Loss": 2.0545294284820557, "Pretrain/Loss (Raw)": 2.1385552883148193, "Pretrain/Step": 2970, "Pretrain/Step Time": 8.431724758818746} +{"Pretrain/Learning Rate": 4.030589821742926e-05, "Pretrain/Loss": 2.0523147583007812, "Pretrain/Loss (Raw)": 1.7969915866851807, "Pretrain/Step": 2971, "Pretrain/Step Time": 8.432179214432836} +{"Pretrain/Learning Rate": 4.029918387751625e-05, "Pretrain/Loss": 2.0527024269104004, "Pretrain/Loss (Raw)": 1.986282229423523, "Pretrain/Step": 2972, "Pretrain/Step Time": 8.431932089850307} +{"Pretrain/Learning Rate": 4.029246777284775e-05, "Pretrain/Loss": 2.0538558959960938, "Pretrain/Loss (Raw)": 1.9893251657485962, "Pretrain/Step": 2973, "Pretrain/Step Time": 8.432262370362878} +{"Pretrain/Learning Rate": 4.0285749904198476e-05, "Pretrain/Loss": 2.054744243621826, "Pretrain/Loss (Raw)": 2.1392757892608643, "Pretrain/Step": 2974, "Pretrain/Step Time": 8.43419909849763} +{"Pretrain/Learning Rate": 4.027903027234332e-05, "Pretrain/Loss": 2.055483341217041, "Pretrain/Loss (Raw)": 2.0261828899383545, "Pretrain/Step": 2975, "Pretrain/Step Time": 8.434899853542447} +{"Pretrain/Learning Rate": 4.0272308878057385e-05, "Pretrain/Loss": 2.0564346313476562, "Pretrain/Loss (Raw)": 2.134458303451538, "Pretrain/Step": 2976, "Pretrain/Step Time": 8.431207528337836} +{"Pretrain/Learning Rate": 4.026558572211599e-05, "Pretrain/Loss": 2.056602716445923, "Pretrain/Loss (Raw)": 2.0739872455596924, "Pretrain/Step": 2977, "Pretrain/Step Time": 8.429475890472531} +{"Pretrain/Learning Rate": 4.025886080529465e-05, "Pretrain/Loss": 2.055565595626831, "Pretrain/Loss (Raw)": 1.97573721408844, "Pretrain/Step": 2978, "Pretrain/Step Time": 8.434842878952622} +{"Pretrain/Learning Rate": 4.025213412836908e-05, "Pretrain/Loss": 2.05690860748291, "Pretrain/Loss (Raw)": 1.9282841682434082, "Pretrain/Step": 2979, "Pretrain/Step Time": 8.43352198600769} +{"Pretrain/Learning Rate": 4.0245405692115195e-05, "Pretrain/Loss": 2.056607723236084, "Pretrain/Loss (Raw)": 2.010568857192993, "Pretrain/Step": 2980, "Pretrain/Step Time": 8.433446560055017} +{"Pretrain/Learning Rate": 4.023867549730912e-05, "Pretrain/Loss": 2.0580713748931885, "Pretrain/Loss (Raw)": 1.998500108718872, "Pretrain/Step": 2981, "Pretrain/Step Time": 8.433578474447131} +{"Pretrain/Learning Rate": 4.023194354472719e-05, "Pretrain/Loss": 2.058272123336792, "Pretrain/Loss (Raw)": 2.084351062774658, "Pretrain/Step": 2982, "Pretrain/Step Time": 8.432878162711859} +{"Pretrain/Learning Rate": 4.022520983514592e-05, "Pretrain/Loss": 2.0580458641052246, "Pretrain/Loss (Raw)": 2.01592755317688, "Pretrain/Step": 2983, "Pretrain/Step Time": 8.434827176854014} +{"Pretrain/Learning Rate": 4.021847436934204e-05, "Pretrain/Loss": 2.058541774749756, "Pretrain/Loss (Raw)": 2.127692461013794, "Pretrain/Step": 2984, "Pretrain/Step Time": 8.434138391166925} +{"Pretrain/Learning Rate": 4.021173714809249e-05, "Pretrain/Loss": 2.0581741333007812, "Pretrain/Loss (Raw)": 2.0408318042755127, "Pretrain/Step": 2985, "Pretrain/Step Time": 8.432593176141381} +{"Pretrain/Learning Rate": 4.0204998172174415e-05, "Pretrain/Loss": 2.058828592300415, "Pretrain/Loss (Raw)": 2.0358190536499023, "Pretrain/Step": 2986, "Pretrain/Step Time": 8.433354968205094} +{"Pretrain/Learning Rate": 4.019825744236514e-05, "Pretrain/Loss": 2.0590500831604004, "Pretrain/Loss (Raw)": 2.147186279296875, "Pretrain/Step": 2987, "Pretrain/Step Time": 8.435363652184606} +{"Pretrain/Learning Rate": 4.01915149594422e-05, "Pretrain/Loss": 2.059094190597534, "Pretrain/Loss (Raw)": 2.086155414581299, "Pretrain/Step": 2988, "Pretrain/Step Time": 8.433702919632196} +{"Pretrain/Learning Rate": 4.018477072418336e-05, "Pretrain/Loss": 2.0612313747406006, "Pretrain/Loss (Raw)": 2.1840837001800537, "Pretrain/Step": 2989, "Pretrain/Step Time": 8.434495938941836} +{"Pretrain/Learning Rate": 4.0178024737366554e-05, "Pretrain/Loss": 2.0608673095703125, "Pretrain/Loss (Raw)": 2.0798542499542236, "Pretrain/Step": 2990, "Pretrain/Step Time": 8.434030462056398} +{"Pretrain/Learning Rate": 4.017127699976992e-05, "Pretrain/Loss": 2.060124397277832, "Pretrain/Loss (Raw)": 2.0076534748077393, "Pretrain/Step": 2991, "Pretrain/Step Time": 8.436955463141203} +{"Pretrain/Learning Rate": 4.0164527512171826e-05, "Pretrain/Loss": 2.060148239135742, "Pretrain/Loss (Raw)": 2.0015571117401123, "Pretrain/Step": 2992, "Pretrain/Step Time": 8.43614948913455} +{"Pretrain/Learning Rate": 4.0157776275350805e-05, "Pretrain/Loss": 2.05885910987854, "Pretrain/Loss (Raw)": 1.8864800930023193, "Pretrain/Step": 2993, "Pretrain/Step Time": 8.439431581646204} +{"Pretrain/Learning Rate": 4.015102329008562e-05, "Pretrain/Loss": 2.0567829608917236, "Pretrain/Loss (Raw)": 2.025679111480713, "Pretrain/Step": 2994, "Pretrain/Step Time": 8.438248101621866} +{"Pretrain/Learning Rate": 4.014426855715523e-05, "Pretrain/Loss": 2.0561676025390625, "Pretrain/Loss (Raw)": 2.1189777851104736, "Pretrain/Step": 2995, "Pretrain/Step Time": 8.438837422057986} +{"Pretrain/Learning Rate": 4.013751207733877e-05, "Pretrain/Loss": 2.055074453353882, "Pretrain/Loss (Raw)": 1.9311130046844482, "Pretrain/Step": 2996, "Pretrain/Step Time": 8.438617300242186} +{"Pretrain/Learning Rate": 4.0130753851415614e-05, "Pretrain/Loss": 2.053954601287842, "Pretrain/Loss (Raw)": 1.9263784885406494, "Pretrain/Step": 2997, "Pretrain/Step Time": 8.441441148519516} +{"Pretrain/Learning Rate": 4.012399388016533e-05, "Pretrain/Loss": 2.053675413131714, "Pretrain/Loss (Raw)": 2.1628220081329346, "Pretrain/Step": 2998, "Pretrain/Step Time": 8.439465070143342} +{"Pretrain/Learning Rate": 4.0117232164367655e-05, "Pretrain/Loss": 2.0534682273864746, "Pretrain/Loss (Raw)": 2.072504758834839, "Pretrain/Step": 2999, "Pretrain/Step Time": 8.438820481300354} +{"Pretrain/Learning Rate": 4.011046870480257e-05, "Pretrain/Loss": 2.051931858062744, "Pretrain/Loss (Raw)": 1.9624329805374146, "Pretrain/Step": 3000, "Pretrain/Step Time": 8.438809752464294} +{"Pretrain/Learning Rate": 4.010370350225022e-05, "Pretrain/Loss": 2.0525095462799072, "Pretrain/Loss (Raw)": 2.2203896045684814, "Pretrain/Step": 3001, "Pretrain/Step Time": 8.435114707797766} +{"Pretrain/Learning Rate": 4.0096936557490995e-05, "Pretrain/Loss": 2.051635265350342, "Pretrain/Loss (Raw)": 1.9960026741027832, "Pretrain/Step": 3002, "Pretrain/Step Time": 8.43581909313798} +{"Pretrain/Learning Rate": 4.009016787130543e-05, "Pretrain/Loss": 2.0516719818115234, "Pretrain/Loss (Raw)": 2.053926706314087, "Pretrain/Step": 3003, "Pretrain/Step Time": 8.438701840117574} +{"Pretrain/Learning Rate": 4.008339744447431e-05, "Pretrain/Loss": 2.051380157470703, "Pretrain/Loss (Raw)": 1.970931887626648, "Pretrain/Step": 3004, "Pretrain/Step Time": 8.436293644830585} +{"Pretrain/Learning Rate": 4.00766252777786e-05, "Pretrain/Loss": 2.049924850463867, "Pretrain/Loss (Raw)": 1.9076788425445557, "Pretrain/Step": 3005, "Pretrain/Step Time": 8.437967145815492} +{"Pretrain/Learning Rate": 4.006985137199945e-05, "Pretrain/Loss": 2.0496997833251953, "Pretrain/Loss (Raw)": 2.1267521381378174, "Pretrain/Step": 3006, "Pretrain/Step Time": 8.435908436775208} +{"Pretrain/Learning Rate": 4.0063075727918245e-05, "Pretrain/Loss": 2.049072027206421, "Pretrain/Loss (Raw)": 2.0713844299316406, "Pretrain/Step": 3007, "Pretrain/Step Time": 8.438062315806746} +{"Pretrain/Learning Rate": 4.0056298346316555e-05, "Pretrain/Loss": 2.047614097595215, "Pretrain/Loss (Raw)": 1.7829399108886719, "Pretrain/Step": 3008, "Pretrain/Step Time": 8.43995543755591} +{"Pretrain/Learning Rate": 4.0049519227976135e-05, "Pretrain/Loss": 2.0482163429260254, "Pretrain/Loss (Raw)": 1.908332347869873, "Pretrain/Step": 3009, "Pretrain/Step Time": 8.438368629664183} +{"Pretrain/Learning Rate": 4.004273837367896e-05, "Pretrain/Loss": 2.048236131668091, "Pretrain/Loss (Raw)": 1.9457950592041016, "Pretrain/Step": 3010, "Pretrain/Step Time": 8.44042556360364} +{"Pretrain/Learning Rate": 4.0035955784207203e-05, "Pretrain/Loss": 2.0480895042419434, "Pretrain/Loss (Raw)": 2.058941602706909, "Pretrain/Step": 3011, "Pretrain/Step Time": 8.438575653359294} +{"Pretrain/Learning Rate": 4.002917146034323e-05, "Pretrain/Loss": 2.0457470417022705, "Pretrain/Loss (Raw)": 1.9884151220321655, "Pretrain/Step": 3012, "Pretrain/Step Time": 8.441133555024862} +{"Pretrain/Learning Rate": 4.002238540286961e-05, "Pretrain/Loss": 2.045785903930664, "Pretrain/Loss (Raw)": 2.0665721893310547, "Pretrain/Step": 3013, "Pretrain/Step Time": 8.43979555927217} +{"Pretrain/Learning Rate": 4.0015597612569113e-05, "Pretrain/Loss": 2.0464348793029785, "Pretrain/Loss (Raw)": 2.0549914836883545, "Pretrain/Step": 3014, "Pretrain/Step Time": 8.440997760742903} +{"Pretrain/Learning Rate": 4.0008808090224714e-05, "Pretrain/Loss": 2.0455822944641113, "Pretrain/Loss (Raw)": 2.1933062076568604, "Pretrain/Step": 3015, "Pretrain/Step Time": 8.443771086633205} +{"Pretrain/Learning Rate": 4.000201683661957e-05, "Pretrain/Loss": 2.0443084239959717, "Pretrain/Loss (Raw)": 1.9526668787002563, "Pretrain/Step": 3016, "Pretrain/Step Time": 8.44628075696528} +{"Pretrain/Learning Rate": 3.999522385253706e-05, "Pretrain/Loss": 2.0461225509643555, "Pretrain/Loss (Raw)": 2.2455649375915527, "Pretrain/Step": 3017, "Pretrain/Step Time": 8.443290943279862} +{"Pretrain/Learning Rate": 3.998842913876074e-05, "Pretrain/Loss": 2.0453224182128906, "Pretrain/Loss (Raw)": 1.9038090705871582, "Pretrain/Step": 3018, "Pretrain/Step Time": 8.440463811159134} +{"Pretrain/Learning Rate": 3.9981632696074394e-05, "Pretrain/Loss": 2.045604705810547, "Pretrain/Loss (Raw)": 2.1073827743530273, "Pretrain/Step": 3019, "Pretrain/Step Time": 8.440458077937365} +{"Pretrain/Learning Rate": 3.997483452526198e-05, "Pretrain/Loss": 2.045926570892334, "Pretrain/Loss (Raw)": 2.081099510192871, "Pretrain/Step": 3020, "Pretrain/Step Time": 8.43916886486113} +{"Pretrain/Learning Rate": 3.996803462710767e-05, "Pretrain/Loss": 2.0458896160125732, "Pretrain/Loss (Raw)": 2.1361703872680664, "Pretrain/Step": 3021, "Pretrain/Step Time": 8.439900992438197} +{"Pretrain/Learning Rate": 3.996123300239581e-05, "Pretrain/Loss": 2.0463552474975586, "Pretrain/Loss (Raw)": 2.1349551677703857, "Pretrain/Step": 3022, "Pretrain/Step Time": 8.43804162926972} +{"Pretrain/Learning Rate": 3.9954429651911e-05, "Pretrain/Loss": 2.046444892883301, "Pretrain/Loss (Raw)": 1.909185528755188, "Pretrain/Step": 3023, "Pretrain/Step Time": 8.440420899540186} +{"Pretrain/Learning Rate": 3.9947624576437975e-05, "Pretrain/Loss": 2.0455663204193115, "Pretrain/Loss (Raw)": 2.0064821243286133, "Pretrain/Step": 3024, "Pretrain/Step Time": 8.442578280344605} +{"Pretrain/Learning Rate": 3.994081777676171e-05, "Pretrain/Loss": 2.045534610748291, "Pretrain/Loss (Raw)": 1.934775948524475, "Pretrain/Step": 3025, "Pretrain/Step Time": 8.442123970016837} +{"Pretrain/Learning Rate": 3.993400925366736e-05, "Pretrain/Loss": 2.046196460723877, "Pretrain/Loss (Raw)": 2.170921564102173, "Pretrain/Step": 3026, "Pretrain/Step Time": 8.440875120460987} +{"Pretrain/Learning Rate": 3.9927199007940294e-05, "Pretrain/Loss": 2.0459723472595215, "Pretrain/Loss (Raw)": 2.0485141277313232, "Pretrain/Step": 3027, "Pretrain/Step Time": 8.437210349366069} +{"Pretrain/Learning Rate": 3.9920387040366076e-05, "Pretrain/Loss": 2.0456199645996094, "Pretrain/Loss (Raw)": 2.034705400466919, "Pretrain/Step": 3028, "Pretrain/Step Time": 8.436432803049684} +{"Pretrain/Learning Rate": 3.9913573351730455e-05, "Pretrain/Loss": 2.044614315032959, "Pretrain/Loss (Raw)": 2.0286903381347656, "Pretrain/Step": 3029, "Pretrain/Step Time": 8.435230309143662} +{"Pretrain/Learning Rate": 3.990675794281938e-05, "Pretrain/Loss": 2.044281005859375, "Pretrain/Loss (Raw)": 2.248106002807617, "Pretrain/Step": 3030, "Pretrain/Step Time": 8.436386534944177} +{"Pretrain/Learning Rate": 3.989994081441902e-05, "Pretrain/Loss": 2.044003486633301, "Pretrain/Loss (Raw)": 2.147094964981079, "Pretrain/Step": 3031, "Pretrain/Step Time": 8.438060021027923} +{"Pretrain/Learning Rate": 3.989312196731572e-05, "Pretrain/Loss": 2.044949531555176, "Pretrain/Loss (Raw)": 2.0268921852111816, "Pretrain/Step": 3032, "Pretrain/Step Time": 8.43849759362638} +{"Pretrain/Learning Rate": 3.9886301402296036e-05, "Pretrain/Loss": 2.0463461875915527, "Pretrain/Loss (Raw)": 1.990936279296875, "Pretrain/Step": 3033, "Pretrain/Step Time": 8.437348579987884} +{"Pretrain/Learning Rate": 3.9879479120146723e-05, "Pretrain/Loss": 2.0439796447753906, "Pretrain/Loss (Raw)": 1.7735786437988281, "Pretrain/Step": 3034, "Pretrain/Step Time": 8.438663132488728} +{"Pretrain/Learning Rate": 3.987265512165471e-05, "Pretrain/Loss": 2.0433170795440674, "Pretrain/Loss (Raw)": 2.0722742080688477, "Pretrain/Step": 3035, "Pretrain/Step Time": 8.437016054987907} +{"Pretrain/Learning Rate": 3.986582940760717e-05, "Pretrain/Loss": 2.041447162628174, "Pretrain/Loss (Raw)": 2.0238583087921143, "Pretrain/Step": 3036, "Pretrain/Step Time": 8.437462231144309} +{"Pretrain/Learning Rate": 3.9859001978791424e-05, "Pretrain/Loss": 2.041022300720215, "Pretrain/Loss (Raw)": 2.058103561401367, "Pretrain/Step": 3037, "Pretrain/Step Time": 8.437275132164359} +{"Pretrain/Learning Rate": 3.9852172835995025e-05, "Pretrain/Loss": 2.041470766067505, "Pretrain/Loss (Raw)": 1.942215085029602, "Pretrain/Step": 3038, "Pretrain/Step Time": 8.433003548532724} +{"Pretrain/Learning Rate": 3.9845341980005704e-05, "Pretrain/Loss": 2.0408310890197754, "Pretrain/Loss (Raw)": 1.9819425344467163, "Pretrain/Step": 3039, "Pretrain/Step Time": 8.434105044230819} +{"Pretrain/Learning Rate": 3.9838509411611405e-05, "Pretrain/Loss": 2.0395827293395996, "Pretrain/Loss (Raw)": 1.878797173500061, "Pretrain/Step": 3040, "Pretrain/Step Time": 8.433392729610205} +{"Pretrain/Learning Rate": 3.9831675131600255e-05, "Pretrain/Loss": 2.037079095840454, "Pretrain/Loss (Raw)": 1.6926755905151367, "Pretrain/Step": 3041, "Pretrain/Step Time": 8.438458131626248} +{"Pretrain/Learning Rate": 3.98248391407606e-05, "Pretrain/Loss": 2.035428047180176, "Pretrain/Loss (Raw)": 1.982613444328308, "Pretrain/Step": 3042, "Pretrain/Step Time": 8.438334055244923} +{"Pretrain/Learning Rate": 3.9818001439880954e-05, "Pretrain/Loss": 2.0356950759887695, "Pretrain/Loss (Raw)": 2.108536720275879, "Pretrain/Step": 3043, "Pretrain/Step Time": 8.438000034540892} +{"Pretrain/Learning Rate": 3.9811162029750045e-05, "Pretrain/Loss": 2.0352354049682617, "Pretrain/Loss (Raw)": 2.0507798194885254, "Pretrain/Step": 3044, "Pretrain/Step Time": 8.438197696581483} +{"Pretrain/Learning Rate": 3.980432091115681e-05, "Pretrain/Loss": 2.035118579864502, "Pretrain/Loss (Raw)": 2.105407476425171, "Pretrain/Step": 3045, "Pretrain/Step Time": 8.439288755878806} +{"Pretrain/Learning Rate": 3.979747808489036e-05, "Pretrain/Loss": 2.0341405868530273, "Pretrain/Loss (Raw)": 2.012730598449707, "Pretrain/Step": 3046, "Pretrain/Step Time": 8.437438245862722} +{"Pretrain/Learning Rate": 3.979063355174001e-05, "Pretrain/Loss": 2.0340945720672607, "Pretrain/Loss (Raw)": 2.0003561973571777, "Pretrain/Step": 3047, "Pretrain/Step Time": 8.440313557162881} +{"Pretrain/Learning Rate": 3.978378731249528e-05, "Pretrain/Loss": 2.0338551998138428, "Pretrain/Loss (Raw)": 1.977746605873108, "Pretrain/Step": 3048, "Pretrain/Step Time": 8.444844266399741} +{"Pretrain/Learning Rate": 3.9776939367945876e-05, "Pretrain/Loss": 2.0334692001342773, "Pretrain/Loss (Raw)": 2.0434086322784424, "Pretrain/Step": 3049, "Pretrain/Step Time": 8.446689238771796} +{"Pretrain/Learning Rate": 3.977008971888171e-05, "Pretrain/Loss": 2.0330934524536133, "Pretrain/Loss (Raw)": 1.923497200012207, "Pretrain/Step": 3050, "Pretrain/Step Time": 8.44635191373527} +{"Pretrain/Learning Rate": 3.976323836609288e-05, "Pretrain/Loss": 2.0317564010620117, "Pretrain/Loss (Raw)": 2.0183379650115967, "Pretrain/Step": 3051, "Pretrain/Step Time": 8.446093339473009} +{"Pretrain/Learning Rate": 3.97563853103697e-05, "Pretrain/Loss": 2.0333356857299805, "Pretrain/Loss (Raw)": 2.2108466625213623, "Pretrain/Step": 3052, "Pretrain/Step Time": 8.44827570579946} +{"Pretrain/Learning Rate": 3.9749530552502656e-05, "Pretrain/Loss": 2.0324513912200928, "Pretrain/Loss (Raw)": 2.0019752979278564, "Pretrain/Step": 3053, "Pretrain/Step Time": 8.447794439271092} +{"Pretrain/Learning Rate": 3.974267409328245e-05, "Pretrain/Loss": 2.03212308883667, "Pretrain/Loss (Raw)": 2.057089328765869, "Pretrain/Step": 3054, "Pretrain/Step Time": 8.449713103473186} +{"Pretrain/Learning Rate": 3.973581593349997e-05, "Pretrain/Loss": 2.032177448272705, "Pretrain/Loss (Raw)": 2.0880379676818848, "Pretrain/Step": 3055, "Pretrain/Step Time": 8.450790334492922} +{"Pretrain/Learning Rate": 3.97289560739463e-05, "Pretrain/Loss": 2.0325212478637695, "Pretrain/Loss (Raw)": 2.135209321975708, "Pretrain/Step": 3056, "Pretrain/Step Time": 8.450418869033456} +{"Pretrain/Learning Rate": 3.972209451541272e-05, "Pretrain/Loss": 2.0332748889923096, "Pretrain/Loss (Raw)": 2.148855686187744, "Pretrain/Step": 3057, "Pretrain/Step Time": 8.451431602239609} +{"Pretrain/Learning Rate": 3.971523125869071e-05, "Pretrain/Loss": 2.0330581665039062, "Pretrain/Loss (Raw)": 2.0412609577178955, "Pretrain/Step": 3058, "Pretrain/Step Time": 8.449157703667879} +{"Pretrain/Learning Rate": 3.970836630457194e-05, "Pretrain/Loss": 2.031571865081787, "Pretrain/Loss (Raw)": 1.9775221347808838, "Pretrain/Step": 3059, "Pretrain/Step Time": 8.45063098706305} +{"Pretrain/Learning Rate": 3.9701499653848296e-05, "Pretrain/Loss": 2.0318007469177246, "Pretrain/Loss (Raw)": 1.9822708368301392, "Pretrain/Step": 3060, "Pretrain/Step Time": 8.44751107506454} +{"Pretrain/Learning Rate": 3.969463130731183e-05, "Pretrain/Loss": 2.0317249298095703, "Pretrain/Loss (Raw)": 2.0587363243103027, "Pretrain/Step": 3061, "Pretrain/Step Time": 8.44634580053389} +{"Pretrain/Learning Rate": 3.968776126575481e-05, "Pretrain/Loss": 2.033069133758545, "Pretrain/Loss (Raw)": 2.1423065662384033, "Pretrain/Step": 3062, "Pretrain/Step Time": 8.445436675101519} +{"Pretrain/Learning Rate": 3.968088952996969e-05, "Pretrain/Loss": 2.0330169200897217, "Pretrain/Loss (Raw)": 2.0830557346343994, "Pretrain/Step": 3063, "Pretrain/Step Time": 8.445106418803334} +{"Pretrain/Learning Rate": 3.967401610074911e-05, "Pretrain/Loss": 2.0331854820251465, "Pretrain/Loss (Raw)": 2.0754787921905518, "Pretrain/Step": 3064, "Pretrain/Step Time": 8.448431003838778} +{"Pretrain/Learning Rate": 3.966714097888594e-05, "Pretrain/Loss": 2.0336546897888184, "Pretrain/Loss (Raw)": 2.0919158458709717, "Pretrain/Step": 3065, "Pretrain/Step Time": 8.451250536367297} +{"Pretrain/Learning Rate": 3.966026416517321e-05, "Pretrain/Loss": 2.0323359966278076, "Pretrain/Loss (Raw)": 2.0131378173828125, "Pretrain/Step": 3066, "Pretrain/Step Time": 8.448722725734115} +{"Pretrain/Learning Rate": 3.965338566040416e-05, "Pretrain/Loss": 2.0318763256073, "Pretrain/Loss (Raw)": 2.0622506141662598, "Pretrain/Step": 3067, "Pretrain/Step Time": 8.449771374464035} +{"Pretrain/Learning Rate": 3.964650546537222e-05, "Pretrain/Loss": 2.0319154262542725, "Pretrain/Loss (Raw)": 2.030543804168701, "Pretrain/Step": 3068, "Pretrain/Step Time": 8.450597561895847} +{"Pretrain/Learning Rate": 3.963962358087103e-05, "Pretrain/Loss": 2.0316381454467773, "Pretrain/Loss (Raw)": 2.0313642024993896, "Pretrain/Step": 3069, "Pretrain/Step Time": 8.45310821942985} +{"Pretrain/Learning Rate": 3.96327400076944e-05, "Pretrain/Loss": 2.033435344696045, "Pretrain/Loss (Raw)": 2.2439208030700684, "Pretrain/Step": 3070, "Pretrain/Step Time": 8.450764711946249} +{"Pretrain/Learning Rate": 3.962585474663636e-05, "Pretrain/Loss": 2.036055088043213, "Pretrain/Loss (Raw)": 2.189016342163086, "Pretrain/Step": 3071, "Pretrain/Step Time": 8.448989411816001} +{"Pretrain/Learning Rate": 3.96189677984911e-05, "Pretrain/Loss": 2.0356101989746094, "Pretrain/Loss (Raw)": 1.8386026620864868, "Pretrain/Step": 3072, "Pretrain/Step Time": 8.450277464464307} +{"Pretrain/Learning Rate": 3.961207916405305e-05, "Pretrain/Loss": 2.0354113578796387, "Pretrain/Loss (Raw)": 2.0138754844665527, "Pretrain/Step": 3073, "Pretrain/Step Time": 8.452154947444797} +{"Pretrain/Learning Rate": 3.9605188844116815e-05, "Pretrain/Loss": 2.036585569381714, "Pretrain/Loss (Raw)": 2.0185558795928955, "Pretrain/Step": 3074, "Pretrain/Step Time": 8.451825458556414} +{"Pretrain/Learning Rate": 3.959829683947717e-05, "Pretrain/Loss": 2.0389404296875, "Pretrain/Loss (Raw)": 2.2421464920043945, "Pretrain/Step": 3075, "Pretrain/Step Time": 8.450454669073224} +{"Pretrain/Learning Rate": 3.9591403150929104e-05, "Pretrain/Loss": 2.038715124130249, "Pretrain/Loss (Raw)": 2.0450334548950195, "Pretrain/Step": 3076, "Pretrain/Step Time": 8.453500770032406} +{"Pretrain/Learning Rate": 3.9584507779267824e-05, "Pretrain/Loss": 2.0392863750457764, "Pretrain/Loss (Raw)": 2.018754243850708, "Pretrain/Step": 3077, "Pretrain/Step Time": 8.451353227719665} +{"Pretrain/Learning Rate": 3.957761072528869e-05, "Pretrain/Loss": 2.038834571838379, "Pretrain/Loss (Raw)": 2.037544012069702, "Pretrain/Step": 3078, "Pretrain/Step Time": 8.449658202007413} +{"Pretrain/Learning Rate": 3.957071198978729e-05, "Pretrain/Loss": 2.0378546714782715, "Pretrain/Loss (Raw)": 2.0494894981384277, "Pretrain/Step": 3079, "Pretrain/Step Time": 8.450583884492517} +{"Pretrain/Learning Rate": 3.956381157355938e-05, "Pretrain/Loss": 2.0382678508758545, "Pretrain/Loss (Raw)": 2.089827060699463, "Pretrain/Step": 3080, "Pretrain/Step Time": 8.454743333160877} +{"Pretrain/Learning Rate": 3.9556909477400914e-05, "Pretrain/Loss": 2.0378713607788086, "Pretrain/Loss (Raw)": 2.0795950889587402, "Pretrain/Step": 3081, "Pretrain/Step Time": 8.453868417069316} +{"Pretrain/Learning Rate": 3.9550005702108076e-05, "Pretrain/Loss": 2.037787675857544, "Pretrain/Loss (Raw)": 2.058454990386963, "Pretrain/Step": 3082, "Pretrain/Step Time": 8.455127317458391} +{"Pretrain/Learning Rate": 3.9543100248477174e-05, "Pretrain/Loss": 2.0370442867279053, "Pretrain/Loss (Raw)": 1.9685369729995728, "Pretrain/Step": 3083, "Pretrain/Step Time": 8.454170323908329} +{"Pretrain/Learning Rate": 3.9536193117304777e-05, "Pretrain/Loss": 2.0361123085021973, "Pretrain/Loss (Raw)": 2.004197359085083, "Pretrain/Step": 3084, "Pretrain/Step Time": 8.452769143506885} +{"Pretrain/Learning Rate": 3.952928430938761e-05, "Pretrain/Loss": 2.037473201751709, "Pretrain/Loss (Raw)": 2.231822967529297, "Pretrain/Step": 3085, "Pretrain/Step Time": 8.451327918097377} +{"Pretrain/Learning Rate": 3.95223738255226e-05, "Pretrain/Loss": 2.0373222827911377, "Pretrain/Loss (Raw)": 1.9778016805648804, "Pretrain/Step": 3086, "Pretrain/Step Time": 8.448244400322437} +{"Pretrain/Learning Rate": 3.951546166650688e-05, "Pretrain/Loss": 2.0371809005737305, "Pretrain/Loss (Raw)": 2.1303844451904297, "Pretrain/Step": 3087, "Pretrain/Step Time": 8.446909034624696} +{"Pretrain/Learning Rate": 3.9508547833137756e-05, "Pretrain/Loss": 2.0383052825927734, "Pretrain/Loss (Raw)": 2.1892621517181396, "Pretrain/Step": 3088, "Pretrain/Step Time": 8.447005150839686} +{"Pretrain/Learning Rate": 3.950163232621273e-05, "Pretrain/Loss": 2.039012908935547, "Pretrain/Loss (Raw)": 2.014219045639038, "Pretrain/Step": 3089, "Pretrain/Step Time": 8.447262639179826} +{"Pretrain/Learning Rate": 3.9494715146529525e-05, "Pretrain/Loss": 2.037696361541748, "Pretrain/Loss (Raw)": 1.9266573190689087, "Pretrain/Step": 3090, "Pretrain/Step Time": 8.447774536907673} +{"Pretrain/Learning Rate": 3.948779629488602e-05, "Pretrain/Loss": 2.0424046516418457, "Pretrain/Loss (Raw)": 2.171741247177124, "Pretrain/Step": 3091, "Pretrain/Step Time": 8.448539031669497} +{"Pretrain/Learning Rate": 3.94808757720803e-05, "Pretrain/Loss": 2.041433095932007, "Pretrain/Loss (Raw)": 1.9155282974243164, "Pretrain/Step": 3092, "Pretrain/Step Time": 8.45218245126307} +{"Pretrain/Learning Rate": 3.9473953578910644e-05, "Pretrain/Loss": 2.041700601577759, "Pretrain/Loss (Raw)": 2.0171451568603516, "Pretrain/Step": 3093, "Pretrain/Step Time": 8.451318737119436} +{"Pretrain/Learning Rate": 3.946702971617553e-05, "Pretrain/Loss": 2.041929244995117, "Pretrain/Loss (Raw)": 2.0972485542297363, "Pretrain/Step": 3094, "Pretrain/Step Time": 8.451111538335681} +{"Pretrain/Learning Rate": 3.946010418467363e-05, "Pretrain/Loss": 2.040675163269043, "Pretrain/Loss (Raw)": 2.0914907455444336, "Pretrain/Step": 3095, "Pretrain/Step Time": 8.445913139730692} +{"Pretrain/Learning Rate": 3.9453176985203785e-05, "Pretrain/Loss": 2.0419681072235107, "Pretrain/Loss (Raw)": 2.281215190887451, "Pretrain/Step": 3096, "Pretrain/Step Time": 8.44859715551138} +{"Pretrain/Learning Rate": 3.944624811856506e-05, "Pretrain/Loss": 2.0429205894470215, "Pretrain/Loss (Raw)": 2.1231091022491455, "Pretrain/Step": 3097, "Pretrain/Step Time": 8.44980102404952} +{"Pretrain/Learning Rate": 3.943931758555669e-05, "Pretrain/Loss": 2.0429673194885254, "Pretrain/Loss (Raw)": 2.144529104232788, "Pretrain/Step": 3098, "Pretrain/Step Time": 8.45120401121676} +{"Pretrain/Learning Rate": 3.943238538697811e-05, "Pretrain/Loss": 2.0449459552764893, "Pretrain/Loss (Raw)": 2.0502445697784424, "Pretrain/Step": 3099, "Pretrain/Step Time": 8.449747033417225} +{"Pretrain/Learning Rate": 3.9425451523628954e-05, "Pretrain/Loss": 2.0456249713897705, "Pretrain/Loss (Raw)": 2.0731873512268066, "Pretrain/Step": 3100, "Pretrain/Step Time": 8.44882726110518} +{"Pretrain/Learning Rate": 3.941851599630902e-05, "Pretrain/Loss": 2.046565532684326, "Pretrain/Loss (Raw)": 2.1097230911254883, "Pretrain/Step": 3101, "Pretrain/Step Time": 8.447793412953615} +{"Pretrain/Learning Rate": 3.9411578805818344e-05, "Pretrain/Loss": 2.04525089263916, "Pretrain/Loss (Raw)": 1.9710023403167725, "Pretrain/Step": 3102, "Pretrain/Step Time": 8.445537976920605} +{"Pretrain/Learning Rate": 3.940463995295712e-05, "Pretrain/Loss": 2.044796943664551, "Pretrain/Loss (Raw)": 1.9680871963500977, "Pretrain/Step": 3103, "Pretrain/Step Time": 8.443316580727696} +{"Pretrain/Learning Rate": 3.939769943852573e-05, "Pretrain/Loss": 2.044462203979492, "Pretrain/Loss (Raw)": 2.091587543487549, "Pretrain/Step": 3104, "Pretrain/Step Time": 8.446420766413212} +{"Pretrain/Learning Rate": 3.9390757263324774e-05, "Pretrain/Loss": 2.0430760383605957, "Pretrain/Loss (Raw)": 1.8965734243392944, "Pretrain/Step": 3105, "Pretrain/Step Time": 8.448466319590807} +{"Pretrain/Learning Rate": 3.9383813428155025e-05, "Pretrain/Loss": 2.0427935123443604, "Pretrain/Loss (Raw)": 1.9395792484283447, "Pretrain/Step": 3106, "Pretrain/Step Time": 8.442735869437456} +{"Pretrain/Learning Rate": 3.937686793381745e-05, "Pretrain/Loss": 2.044490337371826, "Pretrain/Loss (Raw)": 2.1454789638519287, "Pretrain/Step": 3107, "Pretrain/Step Time": 8.448042506352067} +{"Pretrain/Learning Rate": 3.936992078111321e-05, "Pretrain/Loss": 2.044961452484131, "Pretrain/Loss (Raw)": 2.0708470344543457, "Pretrain/Step": 3108, "Pretrain/Step Time": 8.447090603411198} +{"Pretrain/Learning Rate": 3.936297197084367e-05, "Pretrain/Loss": 2.04506778717041, "Pretrain/Loss (Raw)": 2.012122392654419, "Pretrain/Step": 3109, "Pretrain/Step Time": 8.44726494885981} +{"Pretrain/Learning Rate": 3.935602150381034e-05, "Pretrain/Loss": 2.0449440479278564, "Pretrain/Loss (Raw)": 2.068514108657837, "Pretrain/Step": 3110, "Pretrain/Step Time": 8.445787727832794} +{"Pretrain/Learning Rate": 3.934906938081499e-05, "Pretrain/Loss": 2.0444910526275635, "Pretrain/Loss (Raw)": 1.95794677734375, "Pretrain/Step": 3111, "Pretrain/Step Time": 8.449540792033076} +{"Pretrain/Learning Rate": 3.934211560265952e-05, "Pretrain/Loss": 2.0448520183563232, "Pretrain/Loss (Raw)": 2.1738836765289307, "Pretrain/Step": 3112, "Pretrain/Step Time": 8.448081446811557} +{"Pretrain/Learning Rate": 3.933516017014607e-05, "Pretrain/Loss": 2.0431907176971436, "Pretrain/Loss (Raw)": 1.828208088874817, "Pretrain/Step": 3113, "Pretrain/Step Time": 8.448135234415531} +{"Pretrain/Learning Rate": 3.932820308407692e-05, "Pretrain/Loss": 2.0438594818115234, "Pretrain/Loss (Raw)": 2.121391773223877, "Pretrain/Step": 3114, "Pretrain/Step Time": 8.44820411875844} +{"Pretrain/Learning Rate": 3.932124434525458e-05, "Pretrain/Loss": 2.0450732707977295, "Pretrain/Loss (Raw)": 2.3025600910186768, "Pretrain/Step": 3115, "Pretrain/Step Time": 8.446589693427086} +{"Pretrain/Learning Rate": 3.931428395448174e-05, "Pretrain/Loss": 2.043360948562622, "Pretrain/Loss (Raw)": 1.8669918775558472, "Pretrain/Step": 3116, "Pretrain/Step Time": 8.448535127565265} +{"Pretrain/Learning Rate": 3.930732191256128e-05, "Pretrain/Loss": 2.0404133796691895, "Pretrain/Loss (Raw)": 1.806777000427246, "Pretrain/Step": 3117, "Pretrain/Step Time": 8.4453842099756} +{"Pretrain/Learning Rate": 3.930035822029626e-05, "Pretrain/Loss": 2.0395946502685547, "Pretrain/Loss (Raw)": 1.9750851392745972, "Pretrain/Step": 3118, "Pretrain/Step Time": 8.442876299843192} +{"Pretrain/Learning Rate": 3.9293392878489945e-05, "Pretrain/Loss": 2.0388271808624268, "Pretrain/Loss (Raw)": 1.909406065940857, "Pretrain/Step": 3119, "Pretrain/Step Time": 8.442287851125002} +{"Pretrain/Learning Rate": 3.928642588794579e-05, "Pretrain/Loss": 2.0390000343322754, "Pretrain/Loss (Raw)": 2.0236518383026123, "Pretrain/Step": 3120, "Pretrain/Step Time": 8.44159696623683} +{"Pretrain/Learning Rate": 3.927945724946742e-05, "Pretrain/Loss": 2.0402791500091553, "Pretrain/Loss (Raw)": 2.0502400398254395, "Pretrain/Step": 3121, "Pretrain/Step Time": 8.439425230026245} +{"Pretrain/Learning Rate": 3.927248696385868e-05, "Pretrain/Loss": 2.0414535999298096, "Pretrain/Loss (Raw)": 2.176011323928833, "Pretrain/Step": 3122, "Pretrain/Step Time": 8.4411366507411} +{"Pretrain/Learning Rate": 3.926551503192358e-05, "Pretrain/Loss": 2.0431225299835205, "Pretrain/Loss (Raw)": 2.3326051235198975, "Pretrain/Step": 3123, "Pretrain/Step Time": 8.444319834932685} +{"Pretrain/Learning Rate": 3.925854145446635e-05, "Pretrain/Loss": 2.0447864532470703, "Pretrain/Loss (Raw)": 2.144108295440674, "Pretrain/Step": 3124, "Pretrain/Step Time": 8.443278905004263} +{"Pretrain/Learning Rate": 3.925156623229136e-05, "Pretrain/Loss": 2.0459818840026855, "Pretrain/Loss (Raw)": 2.079385280609131, "Pretrain/Step": 3125, "Pretrain/Step Time": 8.442052356898785} +{"Pretrain/Learning Rate": 3.924458936620321e-05, "Pretrain/Loss": 2.043766498565674, "Pretrain/Loss (Raw)": 1.8792526721954346, "Pretrain/Step": 3126, "Pretrain/Step Time": 8.440341932699084} +{"Pretrain/Learning Rate": 3.923761085700669e-05, "Pretrain/Loss": 2.0432777404785156, "Pretrain/Loss (Raw)": 2.0099334716796875, "Pretrain/Step": 3127, "Pretrain/Step Time": 8.442751994356513} +{"Pretrain/Learning Rate": 3.923063070550676e-05, "Pretrain/Loss": 2.045138120651245, "Pretrain/Loss (Raw)": 2.2005422115325928, "Pretrain/Step": 3128, "Pretrain/Step Time": 8.444525955244899} +{"Pretrain/Learning Rate": 3.922364891250857e-05, "Pretrain/Loss": 2.043436050415039, "Pretrain/Loss (Raw)": 2.0025460720062256, "Pretrain/Step": 3129, "Pretrain/Step Time": 8.445894969627261} +{"Pretrain/Learning Rate": 3.921666547881749e-05, "Pretrain/Loss": 2.0448949337005615, "Pretrain/Loss (Raw)": 2.1827356815338135, "Pretrain/Step": 3130, "Pretrain/Step Time": 8.443918401375413} +{"Pretrain/Learning Rate": 3.920968040523904e-05, "Pretrain/Loss": 2.0442919731140137, "Pretrain/Loss (Raw)": 1.9767357110977173, "Pretrain/Step": 3131, "Pretrain/Step Time": 8.445339256897569} +{"Pretrain/Learning Rate": 3.920269369257895e-05, "Pretrain/Loss": 2.043897867202759, "Pretrain/Loss (Raw)": 1.920497179031372, "Pretrain/Step": 3132, "Pretrain/Step Time": 8.448607822880149} +{"Pretrain/Learning Rate": 3.919570534164313e-05, "Pretrain/Loss": 2.0442678928375244, "Pretrain/Loss (Raw)": 1.9550405740737915, "Pretrain/Step": 3133, "Pretrain/Step Time": 8.447804166004062} +{"Pretrain/Learning Rate": 3.918871535323769e-05, "Pretrain/Loss": 2.0435380935668945, "Pretrain/Loss (Raw)": 2.033345937728882, "Pretrain/Step": 3134, "Pretrain/Step Time": 8.446628294885159} +{"Pretrain/Learning Rate": 3.9181723728168916e-05, "Pretrain/Loss": 2.0434911251068115, "Pretrain/Loss (Raw)": 2.0653560161590576, "Pretrain/Step": 3135, "Pretrain/Step Time": 8.44537116214633} +{"Pretrain/Learning Rate": 3.9174730467243294e-05, "Pretrain/Loss": 2.0453267097473145, "Pretrain/Loss (Raw)": 2.0178966522216797, "Pretrain/Step": 3136, "Pretrain/Step Time": 8.443362332880497} +{"Pretrain/Learning Rate": 3.91677355712675e-05, "Pretrain/Loss": 2.046337127685547, "Pretrain/Loss (Raw)": 2.0376923084259033, "Pretrain/Step": 3137, "Pretrain/Step Time": 8.444249352440238} +{"Pretrain/Learning Rate": 3.9160739041048375e-05, "Pretrain/Loss": 2.0460948944091797, "Pretrain/Loss (Raw)": 1.9147809743881226, "Pretrain/Step": 3138, "Pretrain/Step Time": 8.443373158574104} +{"Pretrain/Learning Rate": 3.915374087739299e-05, "Pretrain/Loss": 2.0444343090057373, "Pretrain/Loss (Raw)": 1.8463795185089111, "Pretrain/Step": 3139, "Pretrain/Step Time": 8.445286436006427} +{"Pretrain/Learning Rate": 3.914674108110857e-05, "Pretrain/Loss": 2.044875144958496, "Pretrain/Loss (Raw)": 2.0448474884033203, "Pretrain/Step": 3140, "Pretrain/Step Time": 8.448231596499681} +{"Pretrain/Learning Rate": 3.913973965300253e-05, "Pretrain/Loss": 2.046091079711914, "Pretrain/Loss (Raw)": 2.2221930027008057, "Pretrain/Step": 3141, "Pretrain/Step Time": 8.448306143283844} +{"Pretrain/Learning Rate": 3.913273659388249e-05, "Pretrain/Loss": 2.046891689300537, "Pretrain/Loss (Raw)": 2.157480478286743, "Pretrain/Step": 3142, "Pretrain/Step Time": 8.446813894435763} +{"Pretrain/Learning Rate": 3.912573190455626e-05, "Pretrain/Loss": 2.0468008518218994, "Pretrain/Loss (Raw)": 2.181683301925659, "Pretrain/Step": 3143, "Pretrain/Step Time": 8.446980966255069} +{"Pretrain/Learning Rate": 3.911872558583181e-05, "Pretrain/Loss": 2.0475945472717285, "Pretrain/Loss (Raw)": 2.054263114929199, "Pretrain/Step": 3144, "Pretrain/Step Time": 8.446207089349627} +{"Pretrain/Learning Rate": 3.911171763851733e-05, "Pretrain/Loss": 2.0460867881774902, "Pretrain/Loss (Raw)": 2.0525434017181396, "Pretrain/Step": 3145, "Pretrain/Step Time": 8.449044039472938} +{"Pretrain/Learning Rate": 3.910470806342117e-05, "Pretrain/Loss": 2.0486793518066406, "Pretrain/Loss (Raw)": 2.2356879711151123, "Pretrain/Step": 3146, "Pretrain/Step Time": 8.45127927325666} +{"Pretrain/Learning Rate": 3.9097696861351896e-05, "Pretrain/Loss": 2.0483760833740234, "Pretrain/Loss (Raw)": 2.068537950515747, "Pretrain/Step": 3147, "Pretrain/Step Time": 8.449299668893218} +{"Pretrain/Learning Rate": 3.9090684033118254e-05, "Pretrain/Loss": 2.0475754737854004, "Pretrain/Loss (Raw)": 1.978644847869873, "Pretrain/Step": 3148, "Pretrain/Step Time": 8.447907954454422} +{"Pretrain/Learning Rate": 3.908366957952915e-05, "Pretrain/Loss": 2.0470685958862305, "Pretrain/Loss (Raw)": 2.0712926387786865, "Pretrain/Step": 3149, "Pretrain/Step Time": 8.448157226666808} +{"Pretrain/Learning Rate": 3.907665350139371e-05, "Pretrain/Loss": 2.0470409393310547, "Pretrain/Loss (Raw)": 2.1314120292663574, "Pretrain/Step": 3150, "Pretrain/Step Time": 8.444062199443579} +{"Pretrain/Learning Rate": 3.906963579952124e-05, "Pretrain/Loss": 2.047489643096924, "Pretrain/Loss (Raw)": 1.9665989875793457, "Pretrain/Step": 3151, "Pretrain/Step Time": 8.4406643435359} +{"Pretrain/Learning Rate": 3.906261647472122e-05, "Pretrain/Loss": 2.0477945804595947, "Pretrain/Loss (Raw)": 2.0455307960510254, "Pretrain/Step": 3152, "Pretrain/Step Time": 8.443264842033386} +{"Pretrain/Learning Rate": 3.905559552780333e-05, "Pretrain/Loss": 2.0480923652648926, "Pretrain/Loss (Raw)": 1.9728825092315674, "Pretrain/Step": 3153, "Pretrain/Step Time": 8.4410035982728} +{"Pretrain/Learning Rate": 3.904857295957744e-05, "Pretrain/Loss": 2.04805326461792, "Pretrain/Loss (Raw)": 2.1659367084503174, "Pretrain/Step": 3154, "Pretrain/Step Time": 8.443918837234378} +{"Pretrain/Learning Rate": 3.90415487708536e-05, "Pretrain/Loss": 2.047403573989868, "Pretrain/Loss (Raw)": 1.9653266668319702, "Pretrain/Step": 3155, "Pretrain/Step Time": 8.445816647261381} +{"Pretrain/Learning Rate": 3.903452296244204e-05, "Pretrain/Loss": 2.0461504459381104, "Pretrain/Loss (Raw)": 1.8743351697921753, "Pretrain/Step": 3156, "Pretrain/Step Time": 8.448754584416747} +{"Pretrain/Learning Rate": 3.9027495535153185e-05, "Pretrain/Loss": 2.0449979305267334, "Pretrain/Loss (Raw)": 1.8811578750610352, "Pretrain/Step": 3157, "Pretrain/Step Time": 8.449391525238752} +{"Pretrain/Learning Rate": 3.902046648979766e-05, "Pretrain/Loss": 2.0420703887939453, "Pretrain/Loss (Raw)": 1.8733711242675781, "Pretrain/Step": 3158, "Pretrain/Step Time": 8.447151759639382} +{"Pretrain/Learning Rate": 3.901343582718624e-05, "Pretrain/Loss": 2.0429580211639404, "Pretrain/Loss (Raw)": 2.2607128620147705, "Pretrain/Step": 3159, "Pretrain/Step Time": 8.444636929780245} +{"Pretrain/Learning Rate": 3.900640354812992e-05, "Pretrain/Loss": 2.0422868728637695, "Pretrain/Loss (Raw)": 1.9410024881362915, "Pretrain/Step": 3160, "Pretrain/Step Time": 8.4465825650841} +{"Pretrain/Learning Rate": 3.899936965343989e-05, "Pretrain/Loss": 2.042513847351074, "Pretrain/Loss (Raw)": 2.0199851989746094, "Pretrain/Step": 3161, "Pretrain/Step Time": 8.448026403784752} +{"Pretrain/Learning Rate": 3.8992334143927475e-05, "Pretrain/Loss": 2.0449304580688477, "Pretrain/Loss (Raw)": 2.0828778743743896, "Pretrain/Step": 3162, "Pretrain/Step Time": 8.446256935596466} +{"Pretrain/Learning Rate": 3.8985297020404244e-05, "Pretrain/Loss": 2.0459492206573486, "Pretrain/Loss (Raw)": 2.202671766281128, "Pretrain/Step": 3163, "Pretrain/Step Time": 8.44586475379765} +{"Pretrain/Learning Rate": 3.897825828368191e-05, "Pretrain/Loss": 2.0469560623168945, "Pretrain/Loss (Raw)": 2.152773141860962, "Pretrain/Step": 3164, "Pretrain/Step Time": 8.448358431458473} +{"Pretrain/Learning Rate": 3.897121793457239e-05, "Pretrain/Loss": 2.0459842681884766, "Pretrain/Loss (Raw)": 1.933698058128357, "Pretrain/Step": 3165, "Pretrain/Step Time": 8.447183264419436} +{"Pretrain/Learning Rate": 3.896417597388781e-05, "Pretrain/Loss": 2.0459823608398438, "Pretrain/Loss (Raw)": 1.9419761896133423, "Pretrain/Step": 3166, "Pretrain/Step Time": 8.44854493252933} +{"Pretrain/Learning Rate": 3.8957132402440425e-05, "Pretrain/Loss": 2.045816421508789, "Pretrain/Loss (Raw)": 1.9606722593307495, "Pretrain/Step": 3167, "Pretrain/Step Time": 8.448931947350502} +{"Pretrain/Learning Rate": 3.895008722104272e-05, "Pretrain/Loss": 2.0475921630859375, "Pretrain/Loss (Raw)": 2.106142282485962, "Pretrain/Step": 3168, "Pretrain/Step Time": 8.449078265577555} +{"Pretrain/Learning Rate": 3.894304043050736e-05, "Pretrain/Loss": 2.049671173095703, "Pretrain/Loss (Raw)": 1.9587470293045044, "Pretrain/Step": 3169, "Pretrain/Step Time": 8.44163703918457} +{"Pretrain/Learning Rate": 3.893599203164718e-05, "Pretrain/Loss": 2.049957752227783, "Pretrain/Loss (Raw)": 2.0193209648132324, "Pretrain/Step": 3170, "Pretrain/Step Time": 8.442203793674707} +{"Pretrain/Learning Rate": 3.892894202527523e-05, "Pretrain/Loss": 2.0496201515197754, "Pretrain/Loss (Raw)": 2.065314531326294, "Pretrain/Step": 3171, "Pretrain/Step Time": 8.44157100841403} +{"Pretrain/Learning Rate": 3.8921890412204705e-05, "Pretrain/Loss": 2.0502939224243164, "Pretrain/Loss (Raw)": 2.1370482444763184, "Pretrain/Step": 3172, "Pretrain/Step Time": 8.445750935003161} +{"Pretrain/Learning Rate": 3.891483719324901e-05, "Pretrain/Loss": 2.0490498542785645, "Pretrain/Loss (Raw)": 1.9461464881896973, "Pretrain/Step": 3173, "Pretrain/Step Time": 8.446780690923333} +{"Pretrain/Learning Rate": 3.890778236922174e-05, "Pretrain/Loss": 2.0500617027282715, "Pretrain/Loss (Raw)": 2.1422200202941895, "Pretrain/Step": 3174, "Pretrain/Step Time": 8.447396114468575} +{"Pretrain/Learning Rate": 3.890072594093666e-05, "Pretrain/Loss": 2.0503292083740234, "Pretrain/Loss (Raw)": 2.034618616104126, "Pretrain/Step": 3175, "Pretrain/Step Time": 8.442741602659225} +{"Pretrain/Learning Rate": 3.8893667909207734e-05, "Pretrain/Loss": 2.0502426624298096, "Pretrain/Loss (Raw)": 1.9666632413864136, "Pretrain/Step": 3176, "Pretrain/Step Time": 8.438364528119564} +{"Pretrain/Learning Rate": 3.888660827484908e-05, "Pretrain/Loss": 2.0496344566345215, "Pretrain/Loss (Raw)": 1.9655641317367554, "Pretrain/Step": 3177, "Pretrain/Step Time": 8.438861928880215} +{"Pretrain/Learning Rate": 3.887954703867506e-05, "Pretrain/Loss": 2.0511465072631836, "Pretrain/Loss (Raw)": 2.1170287132263184, "Pretrain/Step": 3178, "Pretrain/Step Time": 8.439802311360836} +{"Pretrain/Learning Rate": 3.887248420150016e-05, "Pretrain/Loss": 2.051727771759033, "Pretrain/Loss (Raw)": 2.0927462577819824, "Pretrain/Step": 3179, "Pretrain/Step Time": 8.441901978105307} +{"Pretrain/Learning Rate": 3.886541976413908e-05, "Pretrain/Loss": 2.050689220428467, "Pretrain/Loss (Raw)": 2.077939510345459, "Pretrain/Step": 3180, "Pretrain/Step Time": 8.441031150519848} +{"Pretrain/Learning Rate": 3.88583537274067e-05, "Pretrain/Loss": 2.0513720512390137, "Pretrain/Loss (Raw)": 2.089352607727051, "Pretrain/Step": 3181, "Pretrain/Step Time": 8.440460873767734} +{"Pretrain/Learning Rate": 3.885128609211809e-05, "Pretrain/Loss": 2.0516090393066406, "Pretrain/Loss (Raw)": 2.087421417236328, "Pretrain/Step": 3182, "Pretrain/Step Time": 8.439588965848088} +{"Pretrain/Learning Rate": 3.88442168590885e-05, "Pretrain/Loss": 2.0528225898742676, "Pretrain/Loss (Raw)": 2.243356704711914, "Pretrain/Step": 3183, "Pretrain/Step Time": 8.441180983558297} +{"Pretrain/Learning Rate": 3.8837146029133367e-05, "Pretrain/Loss": 2.0522055625915527, "Pretrain/Loss (Raw)": 2.0562551021575928, "Pretrain/Step": 3184, "Pretrain/Step Time": 8.439795106649399} +{"Pretrain/Learning Rate": 3.8830073603068294e-05, "Pretrain/Loss": 2.051433563232422, "Pretrain/Loss (Raw)": 2.050039291381836, "Pretrain/Step": 3185, "Pretrain/Step Time": 8.437312882393599} +{"Pretrain/Learning Rate": 3.882299958170909e-05, "Pretrain/Loss": 2.0515429973602295, "Pretrain/Loss (Raw)": 2.055250644683838, "Pretrain/Step": 3186, "Pretrain/Step Time": 8.437542408704758} +{"Pretrain/Learning Rate": 3.881592396587175e-05, "Pretrain/Loss": 2.0517120361328125, "Pretrain/Loss (Raw)": 1.9991583824157715, "Pretrain/Step": 3187, "Pretrain/Step Time": 8.43793074786663} +{"Pretrain/Learning Rate": 3.880884675637242e-05, "Pretrain/Loss": 2.0502045154571533, "Pretrain/Loss (Raw)": 1.7893214225769043, "Pretrain/Step": 3188, "Pretrain/Step Time": 8.43776392005384} +{"Pretrain/Learning Rate": 3.880176795402748e-05, "Pretrain/Loss": 2.049607276916504, "Pretrain/Loss (Raw)": 1.9822649955749512, "Pretrain/Step": 3189, "Pretrain/Step Time": 8.441390877589583} +{"Pretrain/Learning Rate": 3.879468755965346e-05, "Pretrain/Loss": 2.049210548400879, "Pretrain/Loss (Raw)": 2.09153413772583, "Pretrain/Step": 3190, "Pretrain/Step Time": 8.445046480745077} +{"Pretrain/Learning Rate": 3.8787605574067074e-05, "Pretrain/Loss": 2.0481700897216797, "Pretrain/Loss (Raw)": 1.9499112367630005, "Pretrain/Step": 3191, "Pretrain/Step Time": 8.444311417639256} +{"Pretrain/Learning Rate": 3.878052199808523e-05, "Pretrain/Loss": 2.048213481903076, "Pretrain/Loss (Raw)": 2.0810272693634033, "Pretrain/Step": 3192, "Pretrain/Step Time": 8.441993528977036} +{"Pretrain/Learning Rate": 3.877343683252501e-05, "Pretrain/Loss": 2.048281192779541, "Pretrain/Loss (Raw)": 2.1005778312683105, "Pretrain/Step": 3193, "Pretrain/Step Time": 8.441632496193051} +{"Pretrain/Learning Rate": 3.87663500782037e-05, "Pretrain/Loss": 2.0481886863708496, "Pretrain/Loss (Raw)": 2.0012805461883545, "Pretrain/Step": 3194, "Pretrain/Step Time": 8.439831923693419} +{"Pretrain/Learning Rate": 3.875926173593875e-05, "Pretrain/Loss": 2.048914909362793, "Pretrain/Loss (Raw)": 2.1552159786224365, "Pretrain/Step": 3195, "Pretrain/Step Time": 8.439194208011031} +{"Pretrain/Learning Rate": 3.8752171806547787e-05, "Pretrain/Loss": 2.050121784210205, "Pretrain/Loss (Raw)": 2.185030698776245, "Pretrain/Step": 3196, "Pretrain/Step Time": 8.438743023201823} +{"Pretrain/Learning Rate": 3.874508029084863e-05, "Pretrain/Loss": 2.049971580505371, "Pretrain/Loss (Raw)": 2.01214599609375, "Pretrain/Step": 3197, "Pretrain/Step Time": 8.435120113193989} +{"Pretrain/Learning Rate": 3.8737987189659315e-05, "Pretrain/Loss": 2.048661947250366, "Pretrain/Loss (Raw)": 2.0762722492218018, "Pretrain/Step": 3198, "Pretrain/Step Time": 8.436420563608408} +{"Pretrain/Learning Rate": 3.873089250379799e-05, "Pretrain/Loss": 2.0474634170532227, "Pretrain/Loss (Raw)": 2.0356006622314453, "Pretrain/Step": 3199, "Pretrain/Step Time": 8.43749963119626} +{"Pretrain/Learning Rate": 3.872379623408304e-05, "Pretrain/Loss": 2.0489754676818848, "Pretrain/Loss (Raw)": 2.032144784927368, "Pretrain/Step": 3200, "Pretrain/Step Time": 8.436119752004743} +{"Pretrain/Learning Rate": 3.871669838133303e-05, "Pretrain/Loss": 2.0497236251831055, "Pretrain/Loss (Raw)": 2.109659433364868, "Pretrain/Step": 3201, "Pretrain/Step Time": 8.433297250419855} +{"Pretrain/Learning Rate": 3.870959894636666e-05, "Pretrain/Loss": 2.0498898029327393, "Pretrain/Loss (Raw)": 2.0398099422454834, "Pretrain/Step": 3202, "Pretrain/Step Time": 8.432059837505221} +{"Pretrain/Learning Rate": 3.870249793000289e-05, "Pretrain/Loss": 2.0490715503692627, "Pretrain/Loss (Raw)": 2.1374192237854004, "Pretrain/Step": 3203, "Pretrain/Step Time": 8.435337943956256} +{"Pretrain/Learning Rate": 3.869539533306079e-05, "Pretrain/Loss": 2.0485782623291016, "Pretrain/Loss (Raw)": 1.981902003288269, "Pretrain/Step": 3204, "Pretrain/Step Time": 8.433665696531534} +{"Pretrain/Learning Rate": 3.8688291156359655e-05, "Pretrain/Loss": 2.048377513885498, "Pretrain/Loss (Raw)": 1.9930444955825806, "Pretrain/Step": 3205, "Pretrain/Step Time": 8.433595050126314} +{"Pretrain/Learning Rate": 3.868118540071894e-05, "Pretrain/Loss": 2.0484542846679688, "Pretrain/Loss (Raw)": 2.0473618507385254, "Pretrain/Step": 3206, "Pretrain/Step Time": 8.440434945747256} +{"Pretrain/Learning Rate": 3.8674078066958296e-05, "Pretrain/Loss": 2.048030376434326, "Pretrain/Loss (Raw)": 1.9952270984649658, "Pretrain/Step": 3207, "Pretrain/Step Time": 8.438955565914512} +{"Pretrain/Learning Rate": 3.866696915589756e-05, "Pretrain/Loss": 2.0475025177001953, "Pretrain/Loss (Raw)": 2.0222723484039307, "Pretrain/Step": 3208, "Pretrain/Step Time": 8.436096668243408} +{"Pretrain/Learning Rate": 3.865985866835673e-05, "Pretrain/Loss": 2.047362804412842, "Pretrain/Loss (Raw)": 2.061699628829956, "Pretrain/Step": 3209, "Pretrain/Step Time": 8.437735360115767} +{"Pretrain/Learning Rate": 3.8652746605156e-05, "Pretrain/Loss": 2.048037052154541, "Pretrain/Loss (Raw)": 2.1447834968566895, "Pretrain/Step": 3210, "Pretrain/Step Time": 8.436874827370048} +{"Pretrain/Learning Rate": 3.8645632967115753e-05, "Pretrain/Loss": 2.049111843109131, "Pretrain/Loss (Raw)": 2.106078863143921, "Pretrain/Step": 3211, "Pretrain/Step Time": 8.439013062044978} +{"Pretrain/Learning Rate": 3.863851775505654e-05, "Pretrain/Loss": 2.049558162689209, "Pretrain/Loss (Raw)": 2.0613133907318115, "Pretrain/Step": 3212, "Pretrain/Step Time": 8.438545698300004} +{"Pretrain/Learning Rate": 3.8631400969799095e-05, "Pretrain/Loss": 2.048191547393799, "Pretrain/Loss (Raw)": 2.0569324493408203, "Pretrain/Step": 3213, "Pretrain/Step Time": 8.43881344795227} +{"Pretrain/Learning Rate": 3.862428261216433e-05, "Pretrain/Loss": 2.048414707183838, "Pretrain/Loss (Raw)": 2.0063529014587402, "Pretrain/Step": 3214, "Pretrain/Step Time": 8.439034879207611} +{"Pretrain/Learning Rate": 3.861716268297336e-05, "Pretrain/Loss": 2.0489189624786377, "Pretrain/Loss (Raw)": 2.1949353218078613, "Pretrain/Step": 3215, "Pretrain/Step Time": 8.439266920089722} +{"Pretrain/Learning Rate": 3.861004118304746e-05, "Pretrain/Loss": 2.0479722023010254, "Pretrain/Loss (Raw)": 2.0680863857269287, "Pretrain/Step": 3216, "Pretrain/Step Time": 8.438572563230991} +{"Pretrain/Learning Rate": 3.86029181132081e-05, "Pretrain/Loss": 2.047128915786743, "Pretrain/Loss (Raw)": 1.9062631130218506, "Pretrain/Step": 3217, "Pretrain/Step Time": 8.440258421003819} +{"Pretrain/Learning Rate": 3.85957934742769e-05, "Pretrain/Loss": 2.0494909286499023, "Pretrain/Loss (Raw)": 2.229005813598633, "Pretrain/Step": 3218, "Pretrain/Step Time": 8.435463279485703} +{"Pretrain/Learning Rate": 3.858866726707572e-05, "Pretrain/Loss": 2.0486931800842285, "Pretrain/Loss (Raw)": 2.06962251663208, "Pretrain/Step": 3219, "Pretrain/Step Time": 8.438411083072424} +{"Pretrain/Learning Rate": 3.858153949242653e-05, "Pretrain/Loss": 2.0505597591400146, "Pretrain/Loss (Raw)": 2.1544625759124756, "Pretrain/Step": 3220, "Pretrain/Step Time": 8.436877582222223} +{"Pretrain/Learning Rate": 3.857441015115154e-05, "Pretrain/Loss": 2.0514159202575684, "Pretrain/Loss (Raw)": 2.126723289489746, "Pretrain/Step": 3221, "Pretrain/Step Time": 8.435492703691125} +{"Pretrain/Learning Rate": 3.856727924407311e-05, "Pretrain/Loss": 2.051389694213867, "Pretrain/Loss (Raw)": 2.0938661098480225, "Pretrain/Step": 3222, "Pretrain/Step Time": 8.442139133810997} +{"Pretrain/Learning Rate": 3.856014677201378e-05, "Pretrain/Loss": 2.0504536628723145, "Pretrain/Loss (Raw)": 1.9717110395431519, "Pretrain/Step": 3223, "Pretrain/Step Time": 8.443598758429289} +{"Pretrain/Learning Rate": 3.855301273579629e-05, "Pretrain/Loss": 2.0489349365234375, "Pretrain/Loss (Raw)": 2.0868003368377686, "Pretrain/Step": 3224, "Pretrain/Step Time": 8.444627545773983} +{"Pretrain/Learning Rate": 3.8545877136243545e-05, "Pretrain/Loss": 2.0477311611175537, "Pretrain/Loss (Raw)": 1.9690176248550415, "Pretrain/Step": 3225, "Pretrain/Step Time": 8.445538852363825} +{"Pretrain/Learning Rate": 3.8538739974178635e-05, "Pretrain/Loss": 2.0463500022888184, "Pretrain/Loss (Raw)": 1.9677631855010986, "Pretrain/Step": 3226, "Pretrain/Step Time": 8.441183233633637} +{"Pretrain/Learning Rate": 3.853160125042482e-05, "Pretrain/Loss": 2.047478199005127, "Pretrain/Loss (Raw)": 2.194655656814575, "Pretrain/Step": 3227, "Pretrain/Step Time": 8.445041261613369} +{"Pretrain/Learning Rate": 3.852446096580556e-05, "Pretrain/Loss": 2.047574996948242, "Pretrain/Loss (Raw)": 2.085559129714966, "Pretrain/Step": 3228, "Pretrain/Step Time": 8.446442533284426} +{"Pretrain/Learning Rate": 3.851731912114448e-05, "Pretrain/Loss": 2.046457529067993, "Pretrain/Loss (Raw)": 1.9666907787322998, "Pretrain/Step": 3229, "Pretrain/Step Time": 8.447519404813647} +{"Pretrain/Learning Rate": 3.8510175717265387e-05, "Pretrain/Loss": 2.046865463256836, "Pretrain/Loss (Raw)": 2.0232279300689697, "Pretrain/Step": 3230, "Pretrain/Step Time": 8.446381859481335} +{"Pretrain/Learning Rate": 3.8503030754992276e-05, "Pretrain/Loss": 2.047123670578003, "Pretrain/Loss (Raw)": 2.0011487007141113, "Pretrain/Step": 3231, "Pretrain/Step Time": 8.445404436439276} +{"Pretrain/Learning Rate": 3.849588423514932e-05, "Pretrain/Loss": 2.0466666221618652, "Pretrain/Loss (Raw)": 2.033078193664551, "Pretrain/Step": 3232, "Pretrain/Step Time": 8.443602135404944} +{"Pretrain/Learning Rate": 3.848873615856084e-05, "Pretrain/Loss": 2.0452938079833984, "Pretrain/Loss (Raw)": 1.7208327054977417, "Pretrain/Step": 3233, "Pretrain/Step Time": 8.443722657859325} +{"Pretrain/Learning Rate": 3.848158652605141e-05, "Pretrain/Loss": 2.045962333679199, "Pretrain/Loss (Raw)": 2.0251622200012207, "Pretrain/Step": 3234, "Pretrain/Step Time": 8.446881659328938} +{"Pretrain/Learning Rate": 3.847443533844569e-05, "Pretrain/Loss": 2.044764995574951, "Pretrain/Loss (Raw)": 1.9922202825546265, "Pretrain/Step": 3235, "Pretrain/Step Time": 8.444443885236979} +{"Pretrain/Learning Rate": 3.84672825965686e-05, "Pretrain/Loss": 2.043076992034912, "Pretrain/Loss (Raw)": 1.8547805547714233, "Pretrain/Step": 3236, "Pretrain/Step Time": 8.44352156855166} +{"Pretrain/Learning Rate": 3.846012830124519e-05, "Pretrain/Loss": 2.0430703163146973, "Pretrain/Loss (Raw)": 2.0112924575805664, "Pretrain/Step": 3237, "Pretrain/Step Time": 8.44078523106873} +{"Pretrain/Learning Rate": 3.845297245330071e-05, "Pretrain/Loss": 2.042531728744507, "Pretrain/Loss (Raw)": 1.9995489120483398, "Pretrain/Step": 3238, "Pretrain/Step Time": 8.444245293736458} +{"Pretrain/Learning Rate": 3.8445815053560595e-05, "Pretrain/Loss": 2.043344497680664, "Pretrain/Loss (Raw)": 2.0619897842407227, "Pretrain/Step": 3239, "Pretrain/Step Time": 8.441439475864172} +{"Pretrain/Learning Rate": 3.8438656102850435e-05, "Pretrain/Loss": 2.0423736572265625, "Pretrain/Loss (Raw)": 2.0495991706848145, "Pretrain/Step": 3240, "Pretrain/Step Time": 8.441903155297041} +{"Pretrain/Learning Rate": 3.843149560199601e-05, "Pretrain/Loss": 2.0441372394561768, "Pretrain/Loss (Raw)": 2.053955554962158, "Pretrain/Step": 3241, "Pretrain/Step Time": 8.442554228007793} +{"Pretrain/Learning Rate": 3.842433355182329e-05, "Pretrain/Loss": 2.043807029724121, "Pretrain/Loss (Raw)": 2.079127788543701, "Pretrain/Step": 3242, "Pretrain/Step Time": 8.440140768885612} +{"Pretrain/Learning Rate": 3.8417169953158414e-05, "Pretrain/Loss": 2.0431509017944336, "Pretrain/Loss (Raw)": 2.2185795307159424, "Pretrain/Step": 3243, "Pretrain/Step Time": 8.44368495233357} +{"Pretrain/Learning Rate": 3.841000480682769e-05, "Pretrain/Loss": 2.0446763038635254, "Pretrain/Loss (Raw)": 2.0622544288635254, "Pretrain/Step": 3244, "Pretrain/Step Time": 8.442297840490937} +{"Pretrain/Learning Rate": 3.840283811365764e-05, "Pretrain/Loss": 2.0484225749969482, "Pretrain/Loss (Raw)": 2.286292791366577, "Pretrain/Step": 3245, "Pretrain/Step Time": 8.44307542219758} +{"Pretrain/Learning Rate": 3.8395669874474915e-05, "Pretrain/Loss": 2.0504350662231445, "Pretrain/Loss (Raw)": 2.2326769828796387, "Pretrain/Step": 3246, "Pretrain/Step Time": 8.447112934663892} +{"Pretrain/Learning Rate": 3.838850009010638e-05, "Pretrain/Loss": 2.052273988723755, "Pretrain/Loss (Raw)": 2.1448028087615967, "Pretrain/Step": 3247, "Pretrain/Step Time": 8.445396270602942} +{"Pretrain/Learning Rate": 3.8381328761379066e-05, "Pretrain/Loss": 2.052861213684082, "Pretrain/Loss (Raw)": 2.098790407180786, "Pretrain/Step": 3248, "Pretrain/Step Time": 8.444775272160769} +{"Pretrain/Learning Rate": 3.837415588912018e-05, "Pretrain/Loss": 2.0537476539611816, "Pretrain/Loss (Raw)": 2.1637086868286133, "Pretrain/Step": 3249, "Pretrain/Step Time": 8.44687344133854} +{"Pretrain/Learning Rate": 3.836698147415711e-05, "Pretrain/Loss": 2.0530893802642822, "Pretrain/Loss (Raw)": 2.0917623043060303, "Pretrain/Step": 3250, "Pretrain/Step Time": 8.44347469508648} +{"Pretrain/Learning Rate": 3.835980551731743e-05, "Pretrain/Loss": 2.050767660140991, "Pretrain/Loss (Raw)": 2.035423755645752, "Pretrain/Step": 3251, "Pretrain/Step Time": 8.441869175061584} +{"Pretrain/Learning Rate": 3.835262801942887e-05, "Pretrain/Loss": 2.0510482788085938, "Pretrain/Loss (Raw)": 2.1800243854522705, "Pretrain/Step": 3252, "Pretrain/Step Time": 8.44332630559802} +{"Pretrain/Learning Rate": 3.834544898131937e-05, "Pretrain/Loss": 2.050476312637329, "Pretrain/Loss (Raw)": 2.0061872005462646, "Pretrain/Step": 3253, "Pretrain/Step Time": 8.44211982190609} +{"Pretrain/Learning Rate": 3.833826840381701e-05, "Pretrain/Loss": 2.0504398345947266, "Pretrain/Loss (Raw)": 1.874587059020996, "Pretrain/Step": 3254, "Pretrain/Step Time": 8.442762402817607} +{"Pretrain/Learning Rate": 3.833108628775009e-05, "Pretrain/Loss": 2.051156520843506, "Pretrain/Loss (Raw)": 2.1016719341278076, "Pretrain/Step": 3255, "Pretrain/Step Time": 8.44215602427721} +{"Pretrain/Learning Rate": 3.832390263394704e-05, "Pretrain/Loss": 2.049384593963623, "Pretrain/Loss (Raw)": 1.9736897945404053, "Pretrain/Step": 3256, "Pretrain/Step Time": 8.439772292971611} +{"Pretrain/Learning Rate": 3.8316717443236504e-05, "Pretrain/Loss": 2.0496978759765625, "Pretrain/Loss (Raw)": 2.042663812637329, "Pretrain/Step": 3257, "Pretrain/Step Time": 8.439983863383532} +{"Pretrain/Learning Rate": 3.830953071644729e-05, "Pretrain/Loss": 2.0493967533111572, "Pretrain/Loss (Raw)": 2.1441762447357178, "Pretrain/Step": 3258, "Pretrain/Step Time": 8.44390407949686} +{"Pretrain/Learning Rate": 3.830234245440839e-05, "Pretrain/Loss": 2.050107955932617, "Pretrain/Loss (Raw)": 2.0678162574768066, "Pretrain/Step": 3259, "Pretrain/Step Time": 8.440804656594992} +{"Pretrain/Learning Rate": 3.8295152657948963e-05, "Pretrain/Loss": 2.0510988235473633, "Pretrain/Loss (Raw)": 2.04732084274292, "Pretrain/Step": 3260, "Pretrain/Step Time": 8.43886398896575} +{"Pretrain/Learning Rate": 3.828796132789835e-05, "Pretrain/Loss": 2.0521841049194336, "Pretrain/Loss (Raw)": 2.0939486026763916, "Pretrain/Step": 3261, "Pretrain/Step Time": 8.436367163434625} +{"Pretrain/Learning Rate": 3.8280768465086066e-05, "Pretrain/Loss": 2.051711082458496, "Pretrain/Loss (Raw)": 1.972786545753479, "Pretrain/Step": 3262, "Pretrain/Step Time": 8.441189171746373} +{"Pretrain/Learning Rate": 3.827357407034181e-05, "Pretrain/Loss": 2.051934242248535, "Pretrain/Loss (Raw)": 2.093944787979126, "Pretrain/Step": 3263, "Pretrain/Step Time": 8.44064311310649} +{"Pretrain/Learning Rate": 3.826637814449544e-05, "Pretrain/Loss": 2.0534579753875732, "Pretrain/Loss (Raw)": 2.212908983230591, "Pretrain/Step": 3264, "Pretrain/Step Time": 8.442396454513073} +{"Pretrain/Learning Rate": 3.825918068837702e-05, "Pretrain/Loss": 2.05361008644104, "Pretrain/Loss (Raw)": 2.0571746826171875, "Pretrain/Step": 3265, "Pretrain/Step Time": 8.44107042439282} +{"Pretrain/Learning Rate": 3.825198170281677e-05, "Pretrain/Loss": 2.0557188987731934, "Pretrain/Loss (Raw)": 2.184720516204834, "Pretrain/Step": 3266, "Pretrain/Step Time": 8.438859857618809} +{"Pretrain/Learning Rate": 3.8244781188645084e-05, "Pretrain/Loss": 2.057894706726074, "Pretrain/Loss (Raw)": 2.124863624572754, "Pretrain/Step": 3267, "Pretrain/Step Time": 8.43864581361413} +{"Pretrain/Learning Rate": 3.823757914669254e-05, "Pretrain/Loss": 2.0583019256591797, "Pretrain/Loss (Raw)": 2.0969760417938232, "Pretrain/Step": 3268, "Pretrain/Step Time": 8.437440341338515} +{"Pretrain/Learning Rate": 3.8230375577789895e-05, "Pretrain/Loss": 2.0564019680023193, "Pretrain/Loss (Raw)": 1.9789971113204956, "Pretrain/Step": 3269, "Pretrain/Step Time": 8.43846658617258} +{"Pretrain/Learning Rate": 3.8223170482768076e-05, "Pretrain/Loss": 2.054957866668701, "Pretrain/Loss (Raw)": 1.9726223945617676, "Pretrain/Step": 3270, "Pretrain/Step Time": 8.437783613801003} +{"Pretrain/Learning Rate": 3.821596386245819e-05, "Pretrain/Loss": 2.0537919998168945, "Pretrain/Loss (Raw)": 2.032458782196045, "Pretrain/Step": 3271, "Pretrain/Step Time": 8.434383563697338} +{"Pretrain/Learning Rate": 3.8208755717691514e-05, "Pretrain/Loss": 2.053107738494873, "Pretrain/Loss (Raw)": 1.9666717052459717, "Pretrain/Step": 3272, "Pretrain/Step Time": 8.439382120966911} +{"Pretrain/Learning Rate": 3.820154604929952e-05, "Pretrain/Loss": 2.052773952484131, "Pretrain/Loss (Raw)": 2.009812831878662, "Pretrain/Step": 3273, "Pretrain/Step Time": 8.434771314263344} +{"Pretrain/Learning Rate": 3.819433485811382e-05, "Pretrain/Loss": 2.049044132232666, "Pretrain/Loss (Raw)": 1.7582969665527344, "Pretrain/Step": 3274, "Pretrain/Step Time": 8.439969215542078} +{"Pretrain/Learning Rate": 3.8187122144966225e-05, "Pretrain/Loss": 2.0490293502807617, "Pretrain/Loss (Raw)": 2.0666558742523193, "Pretrain/Step": 3275, "Pretrain/Step Time": 8.44179817661643} +{"Pretrain/Learning Rate": 3.8179907910688736e-05, "Pretrain/Loss": 2.049191474914551, "Pretrain/Loss (Raw)": 1.9993740320205688, "Pretrain/Step": 3276, "Pretrain/Step Time": 8.443076798692346} +{"Pretrain/Learning Rate": 3.817269215611349e-05, "Pretrain/Loss": 2.0490262508392334, "Pretrain/Loss (Raw)": 2.0501513481140137, "Pretrain/Step": 3277, "Pretrain/Step Time": 8.442611563950777} +{"Pretrain/Learning Rate": 3.816547488207284e-05, "Pretrain/Loss": 2.048548698425293, "Pretrain/Loss (Raw)": 2.070295572280884, "Pretrain/Step": 3278, "Pretrain/Step Time": 8.44399505481124} +{"Pretrain/Learning Rate": 3.815825608939928e-05, "Pretrain/Loss": 2.0485663414001465, "Pretrain/Loss (Raw)": 1.9688619375228882, "Pretrain/Step": 3279, "Pretrain/Step Time": 8.445110967382789} +{"Pretrain/Learning Rate": 3.815103577892551e-05, "Pretrain/Loss": 2.0488088130950928, "Pretrain/Loss (Raw)": 2.076545000076294, "Pretrain/Step": 3280, "Pretrain/Step Time": 8.440401770174503} +{"Pretrain/Learning Rate": 3.8143813951484396e-05, "Pretrain/Loss": 2.0496766567230225, "Pretrain/Loss (Raw)": 2.0839664936065674, "Pretrain/Step": 3281, "Pretrain/Step Time": 8.445059390738606} +{"Pretrain/Learning Rate": 3.813659060790895e-05, "Pretrain/Loss": 2.048783540725708, "Pretrain/Loss (Raw)": 2.051638603210449, "Pretrain/Step": 3282, "Pretrain/Step Time": 8.444163030013442} +{"Pretrain/Learning Rate": 3.81293657490324e-05, "Pretrain/Loss": 2.049816608428955, "Pretrain/Loss (Raw)": 2.0975682735443115, "Pretrain/Step": 3283, "Pretrain/Step Time": 8.44456234946847} +{"Pretrain/Learning Rate": 3.812213937568811e-05, "Pretrain/Loss": 2.050302505493164, "Pretrain/Loss (Raw)": 1.9364838600158691, "Pretrain/Step": 3284, "Pretrain/Step Time": 8.442922728136182} +{"Pretrain/Learning Rate": 3.811491148870967e-05, "Pretrain/Loss": 2.0506458282470703, "Pretrain/Loss (Raw)": 1.9251203536987305, "Pretrain/Step": 3285, "Pretrain/Step Time": 8.441358352079988} +{"Pretrain/Learning Rate": 3.8107682088930794e-05, "Pretrain/Loss": 2.0516903400421143, "Pretrain/Loss (Raw)": 2.007066488265991, "Pretrain/Step": 3286, "Pretrain/Step Time": 8.443651923909783} +{"Pretrain/Learning Rate": 3.81004511771854e-05, "Pretrain/Loss": 2.0501856803894043, "Pretrain/Loss (Raw)": 2.068141460418701, "Pretrain/Step": 3287, "Pretrain/Step Time": 8.447358716279268} +{"Pretrain/Learning Rate": 3.809321875430756e-05, "Pretrain/Loss": 2.0512027740478516, "Pretrain/Loss (Raw)": 2.071153163909912, "Pretrain/Step": 3288, "Pretrain/Step Time": 8.444544794037938} +{"Pretrain/Learning Rate": 3.808598482113154e-05, "Pretrain/Loss": 2.050952196121216, "Pretrain/Loss (Raw)": 1.9879131317138672, "Pretrain/Step": 3289, "Pretrain/Step Time": 8.444288613274693} +{"Pretrain/Learning Rate": 3.8078749378491766e-05, "Pretrain/Loss": 2.05000901222229, "Pretrain/Loss (Raw)": 1.9621771574020386, "Pretrain/Step": 3290, "Pretrain/Step Time": 8.445114143192768} +{"Pretrain/Learning Rate": 3.8071512427222855e-05, "Pretrain/Loss": 2.048893928527832, "Pretrain/Loss (Raw)": 2.0599312782287598, "Pretrain/Step": 3291, "Pretrain/Step Time": 8.445557750761509} +{"Pretrain/Learning Rate": 3.8064273968159574e-05, "Pretrain/Loss": 2.047412872314453, "Pretrain/Loss (Raw)": 1.963216781616211, "Pretrain/Step": 3292, "Pretrain/Step Time": 8.441899303346872} +{"Pretrain/Learning Rate": 3.805703400213688e-05, "Pretrain/Loss": 2.0473880767822266, "Pretrain/Loss (Raw)": 1.9304966926574707, "Pretrain/Step": 3293, "Pretrain/Step Time": 8.44578923471272} +{"Pretrain/Learning Rate": 3.8049792529989905e-05, "Pretrain/Loss": 2.047412395477295, "Pretrain/Loss (Raw)": 1.9450979232788086, "Pretrain/Step": 3294, "Pretrain/Step Time": 8.447294969111681} +{"Pretrain/Learning Rate": 3.8042549552553955e-05, "Pretrain/Loss": 2.046112298965454, "Pretrain/Loss (Raw)": 1.7942527532577515, "Pretrain/Step": 3295, "Pretrain/Step Time": 8.446646550670266} +{"Pretrain/Learning Rate": 3.803530507066448e-05, "Pretrain/Loss": 2.0452871322631836, "Pretrain/Loss (Raw)": 2.000535488128662, "Pretrain/Step": 3296, "Pretrain/Step Time": 8.446535874158144} +{"Pretrain/Learning Rate": 3.8028059085157166e-05, "Pretrain/Loss": 2.0469963550567627, "Pretrain/Loss (Raw)": 2.177515983581543, "Pretrain/Step": 3297, "Pretrain/Step Time": 8.447446973994374} +{"Pretrain/Learning Rate": 3.80208115968678e-05, "Pretrain/Loss": 2.048086166381836, "Pretrain/Loss (Raw)": 2.1588351726531982, "Pretrain/Step": 3298, "Pretrain/Step Time": 8.448802258819342} +{"Pretrain/Learning Rate": 3.8013562606632394e-05, "Pretrain/Loss": 2.0470809936523438, "Pretrain/Loss (Raw)": 1.9366480112075806, "Pretrain/Step": 3299, "Pretrain/Step Time": 8.452421953901649} +{"Pretrain/Learning Rate": 3.800631211528712e-05, "Pretrain/Loss": 2.044574737548828, "Pretrain/Loss (Raw)": 1.8162273168563843, "Pretrain/Step": 3300, "Pretrain/Step Time": 8.449036741629243} +{"Pretrain/Learning Rate": 3.799906012366832e-05, "Pretrain/Loss": 2.0451602935791016, "Pretrain/Loss (Raw)": 2.021096706390381, "Pretrain/Step": 3301, "Pretrain/Step Time": 8.446843139827251} +{"Pretrain/Learning Rate": 3.799180663261249e-05, "Pretrain/Loss": 2.0436973571777344, "Pretrain/Loss (Raw)": 1.954969048500061, "Pretrain/Step": 3302, "Pretrain/Step Time": 8.450823297724128} +{"Pretrain/Learning Rate": 3.798455164295633e-05, "Pretrain/Loss": 2.0440163612365723, "Pretrain/Loss (Raw)": 2.07546067237854, "Pretrain/Step": 3303, "Pretrain/Step Time": 8.452010497450829} +{"Pretrain/Learning Rate": 3.797729515553671e-05, "Pretrain/Loss": 2.044663667678833, "Pretrain/Loss (Raw)": 2.0495052337646484, "Pretrain/Step": 3304, "Pretrain/Step Time": 8.452114744111896} +{"Pretrain/Learning Rate": 3.7970037171190656e-05, "Pretrain/Loss": 2.0465610027313232, "Pretrain/Loss (Raw)": 2.208425998687744, "Pretrain/Step": 3305, "Pretrain/Step Time": 8.450416883453727} +{"Pretrain/Learning Rate": 3.796277769075536e-05, "Pretrain/Loss": 2.045773506164551, "Pretrain/Loss (Raw)": 2.016249656677246, "Pretrain/Step": 3306, "Pretrain/Step Time": 8.44848639331758} +{"Pretrain/Learning Rate": 3.7955516715068226e-05, "Pretrain/Loss": 2.0451316833496094, "Pretrain/Loss (Raw)": 2.0105931758880615, "Pretrain/Step": 3307, "Pretrain/Step Time": 8.449047951027751} +{"Pretrain/Learning Rate": 3.7948254244966785e-05, "Pretrain/Loss": 2.04522442817688, "Pretrain/Loss (Raw)": 2.0898149013519287, "Pretrain/Step": 3308, "Pretrain/Step Time": 8.44859660230577} +{"Pretrain/Learning Rate": 3.794099028128877e-05, "Pretrain/Loss": 2.0447821617126465, "Pretrain/Loss (Raw)": 2.032747507095337, "Pretrain/Step": 3309, "Pretrain/Step Time": 8.450774859637022} +{"Pretrain/Learning Rate": 3.793372482487207e-05, "Pretrain/Loss": 2.042287826538086, "Pretrain/Loss (Raw)": 1.7681204080581665, "Pretrain/Step": 3310, "Pretrain/Step Time": 8.45186760649085} +{"Pretrain/Learning Rate": 3.792645787655476e-05, "Pretrain/Loss": 2.0406334400177, "Pretrain/Loss (Raw)": 2.031599998474121, "Pretrain/Step": 3311, "Pretrain/Step Time": 8.449367750436068} +{"Pretrain/Learning Rate": 3.7919189437175074e-05, "Pretrain/Loss": 2.040095806121826, "Pretrain/Loss (Raw)": 1.9874240159988403, "Pretrain/Step": 3312, "Pretrain/Step Time": 8.450958833098412} +{"Pretrain/Learning Rate": 3.791191950757143e-05, "Pretrain/Loss": 2.0393729209899902, "Pretrain/Loss (Raw)": 1.9575185775756836, "Pretrain/Step": 3313, "Pretrain/Step Time": 8.452208852395415} +{"Pretrain/Learning Rate": 3.790464808858241e-05, "Pretrain/Loss": 2.039224624633789, "Pretrain/Loss (Raw)": 2.0362823009490967, "Pretrain/Step": 3314, "Pretrain/Step Time": 8.451284293085337} +{"Pretrain/Learning Rate": 3.7897375181046766e-05, "Pretrain/Loss": 2.040863037109375, "Pretrain/Loss (Raw)": 2.2088894844055176, "Pretrain/Step": 3315, "Pretrain/Step Time": 8.450004298239946} +{"Pretrain/Learning Rate": 3.789010078580342e-05, "Pretrain/Loss": 2.043565034866333, "Pretrain/Loss (Raw)": 2.135148763656616, "Pretrain/Step": 3316, "Pretrain/Step Time": 8.451011769473553} +{"Pretrain/Learning Rate": 3.7882824903691484e-05, "Pretrain/Loss": 2.0429790019989014, "Pretrain/Loss (Raw)": 1.907241702079773, "Pretrain/Step": 3317, "Pretrain/Step Time": 8.44618815369904} +{"Pretrain/Learning Rate": 3.7875547535550224e-05, "Pretrain/Loss": 2.04353404045105, "Pretrain/Loss (Raw)": 2.1626007556915283, "Pretrain/Step": 3318, "Pretrain/Step Time": 8.44336030445993} +{"Pretrain/Learning Rate": 3.7868268682219076e-05, "Pretrain/Loss": 2.044227361679077, "Pretrain/Loss (Raw)": 2.038652181625366, "Pretrain/Step": 3319, "Pretrain/Step Time": 8.443958658725023} +{"Pretrain/Learning Rate": 3.786098834453766e-05, "Pretrain/Loss": 2.0444326400756836, "Pretrain/Loss (Raw)": 2.107313871383667, "Pretrain/Step": 3320, "Pretrain/Step Time": 8.447126155719161} +{"Pretrain/Learning Rate": 3.785370652334577e-05, "Pretrain/Loss": 2.0417065620422363, "Pretrain/Loss (Raw)": 1.751607894897461, "Pretrain/Step": 3321, "Pretrain/Step Time": 8.446628106757998} +{"Pretrain/Learning Rate": 3.784642321948333e-05, "Pretrain/Loss": 2.0421581268310547, "Pretrain/Loss (Raw)": 2.0590779781341553, "Pretrain/Step": 3322, "Pretrain/Step Time": 8.446953870356083} +{"Pretrain/Learning Rate": 3.78391384337905e-05, "Pretrain/Loss": 2.040790557861328, "Pretrain/Loss (Raw)": 1.9801725149154663, "Pretrain/Step": 3323, "Pretrain/Step Time": 8.445894503965974} +{"Pretrain/Learning Rate": 3.783185216710756e-05, "Pretrain/Loss": 2.039423942565918, "Pretrain/Loss (Raw)": 2.010124444961548, "Pretrain/Step": 3324, "Pretrain/Step Time": 8.445249624550343} +{"Pretrain/Learning Rate": 3.782456442027498e-05, "Pretrain/Loss": 2.0399727821350098, "Pretrain/Loss (Raw)": 2.082402229309082, "Pretrain/Step": 3325, "Pretrain/Step Time": 8.449280986562371} +{"Pretrain/Learning Rate": 3.78172751941334e-05, "Pretrain/Loss": 2.0401742458343506, "Pretrain/Loss (Raw)": 2.1020729541778564, "Pretrain/Step": 3326, "Pretrain/Step Time": 8.447168467566371} +{"Pretrain/Learning Rate": 3.780998448952363e-05, "Pretrain/Loss": 2.039829730987549, "Pretrain/Loss (Raw)": 1.9915012121200562, "Pretrain/Step": 3327, "Pretrain/Step Time": 8.447832472622395} +{"Pretrain/Learning Rate": 3.7802692307286654e-05, "Pretrain/Loss": 2.0397722721099854, "Pretrain/Loss (Raw)": 2.02478289604187, "Pretrain/Step": 3328, "Pretrain/Step Time": 8.44794499874115} +{"Pretrain/Learning Rate": 3.779539864826362e-05, "Pretrain/Loss": 2.0405848026275635, "Pretrain/Loss (Raw)": 2.213625431060791, "Pretrain/Step": 3329, "Pretrain/Step Time": 8.449885649606586} +{"Pretrain/Learning Rate": 3.778810351329585e-05, "Pretrain/Loss": 2.0394134521484375, "Pretrain/Loss (Raw)": 1.8898807764053345, "Pretrain/Step": 3330, "Pretrain/Step Time": 8.450007716193795} +{"Pretrain/Learning Rate": 3.778080690322483e-05, "Pretrain/Loss": 2.038071632385254, "Pretrain/Loss (Raw)": 1.9656903743743896, "Pretrain/Step": 3331, "Pretrain/Step Time": 8.447936149314046} +{"Pretrain/Learning Rate": 3.7773508818892224e-05, "Pretrain/Loss": 2.0377516746520996, "Pretrain/Loss (Raw)": 1.9409340620040894, "Pretrain/Step": 3332, "Pretrain/Step Time": 8.448507390916348} +{"Pretrain/Learning Rate": 3.776620926113986e-05, "Pretrain/Loss": 2.0392239093780518, "Pretrain/Loss (Raw)": 2.181485891342163, "Pretrain/Step": 3333, "Pretrain/Step Time": 8.449753928929567} +{"Pretrain/Learning Rate": 3.775890823080976e-05, "Pretrain/Loss": 2.0383710861206055, "Pretrain/Loss (Raw)": 1.9382202625274658, "Pretrain/Step": 3334, "Pretrain/Step Time": 8.44334433041513} +{"Pretrain/Learning Rate": 3.7751605728744064e-05, "Pretrain/Loss": 2.0371510982513428, "Pretrain/Loss (Raw)": 1.8390729427337646, "Pretrain/Step": 3335, "Pretrain/Step Time": 8.441897889599204} +{"Pretrain/Learning Rate": 3.774430175578514e-05, "Pretrain/Loss": 2.0377025604248047, "Pretrain/Loss (Raw)": 2.0928421020507812, "Pretrain/Step": 3336, "Pretrain/Step Time": 8.44435908086598} +{"Pretrain/Learning Rate": 3.773699631277548e-05, "Pretrain/Loss": 2.036527156829834, "Pretrain/Loss (Raw)": 1.9112786054611206, "Pretrain/Step": 3337, "Pretrain/Step Time": 8.444167321547866} +{"Pretrain/Learning Rate": 3.772968940055777e-05, "Pretrain/Loss": 2.035494804382324, "Pretrain/Loss (Raw)": 2.012603998184204, "Pretrain/Step": 3338, "Pretrain/Step Time": 8.443399986252189} +{"Pretrain/Learning Rate": 3.7722381019974864e-05, "Pretrain/Loss": 2.0354018211364746, "Pretrain/Loss (Raw)": 2.094200372695923, "Pretrain/Step": 3339, "Pretrain/Step Time": 8.440121077001095} +{"Pretrain/Learning Rate": 3.771507117186978e-05, "Pretrain/Loss": 2.035137176513672, "Pretrain/Loss (Raw)": 2.0274455547332764, "Pretrain/Step": 3340, "Pretrain/Step Time": 8.442465402185917} +{"Pretrain/Learning Rate": 3.77077598570857e-05, "Pretrain/Loss": 2.035377025604248, "Pretrain/Loss (Raw)": 2.0876221656799316, "Pretrain/Step": 3341, "Pretrain/Step Time": 8.441032405942678} +{"Pretrain/Learning Rate": 3.770044707646599e-05, "Pretrain/Loss": 2.0353097915649414, "Pretrain/Loss (Raw)": 1.9977566003799438, "Pretrain/Step": 3342, "Pretrain/Step Time": 8.445383612066507} +{"Pretrain/Learning Rate": 3.7693132830854185e-05, "Pretrain/Loss": 2.0347328186035156, "Pretrain/Loss (Raw)": 2.121074914932251, "Pretrain/Step": 3343, "Pretrain/Step Time": 8.444065304473042} +{"Pretrain/Learning Rate": 3.768581712109395e-05, "Pretrain/Loss": 2.033656358718872, "Pretrain/Loss (Raw)": 1.9302940368652344, "Pretrain/Step": 3344, "Pretrain/Step Time": 8.445568697527051} +{"Pretrain/Learning Rate": 3.767849994802918e-05, "Pretrain/Loss": 2.0340495109558105, "Pretrain/Loss (Raw)": 1.9565635919570923, "Pretrain/Step": 3345, "Pretrain/Step Time": 8.442690016701818} +{"Pretrain/Learning Rate": 3.767118131250388e-05, "Pretrain/Loss": 2.0329155921936035, "Pretrain/Loss (Raw)": 2.0838639736175537, "Pretrain/Step": 3346, "Pretrain/Step Time": 8.448697425425053} +{"Pretrain/Learning Rate": 3.7663861215362284e-05, "Pretrain/Loss": 2.0316638946533203, "Pretrain/Loss (Raw)": 1.9094264507293701, "Pretrain/Step": 3347, "Pretrain/Step Time": 8.443728221580386} +{"Pretrain/Learning Rate": 3.765653965744874e-05, "Pretrain/Loss": 2.0307211875915527, "Pretrain/Loss (Raw)": 2.0337941646575928, "Pretrain/Step": 3348, "Pretrain/Step Time": 8.441618520766497} +{"Pretrain/Learning Rate": 3.76492166396078e-05, "Pretrain/Loss": 2.0301785469055176, "Pretrain/Loss (Raw)": 2.057279586791992, "Pretrain/Step": 3349, "Pretrain/Step Time": 8.444347886368632} +{"Pretrain/Learning Rate": 3.7641892162684164e-05, "Pretrain/Loss": 2.030339241027832, "Pretrain/Loss (Raw)": 2.114438056945801, "Pretrain/Step": 3350, "Pretrain/Step Time": 8.440140631049871} +{"Pretrain/Learning Rate": 3.7634566227522713e-05, "Pretrain/Loss": 2.030869960784912, "Pretrain/Loss (Raw)": 2.039625406265259, "Pretrain/Step": 3351, "Pretrain/Step Time": 8.439299806952477} +{"Pretrain/Learning Rate": 3.762723883496848e-05, "Pretrain/Loss": 2.0306410789489746, "Pretrain/Loss (Raw)": 2.0575180053710938, "Pretrain/Step": 3352, "Pretrain/Step Time": 8.436607470735908} +{"Pretrain/Learning Rate": 3.761990998586669e-05, "Pretrain/Loss": 2.03092622756958, "Pretrain/Loss (Raw)": 2.005519390106201, "Pretrain/Step": 3353, "Pretrain/Step Time": 8.43555154837668} +{"Pretrain/Learning Rate": 3.761257968106271e-05, "Pretrain/Loss": 2.031508684158325, "Pretrain/Loss (Raw)": 2.0423052310943604, "Pretrain/Step": 3354, "Pretrain/Step Time": 8.43701458722353} +{"Pretrain/Learning Rate": 3.760524792140211e-05, "Pretrain/Loss": 2.031715154647827, "Pretrain/Loss (Raw)": 2.2210822105407715, "Pretrain/Step": 3355, "Pretrain/Step Time": 8.436670074239373} +{"Pretrain/Learning Rate": 3.759791470773058e-05, "Pretrain/Loss": 2.031233787536621, "Pretrain/Loss (Raw)": 2.0239462852478027, "Pretrain/Step": 3356, "Pretrain/Step Time": 8.435880482196808} +{"Pretrain/Learning Rate": 3.759058004089402e-05, "Pretrain/Loss": 2.0329177379608154, "Pretrain/Loss (Raw)": 2.1822304725646973, "Pretrain/Step": 3357, "Pretrain/Step Time": 8.436869660392404} +{"Pretrain/Learning Rate": 3.758324392173849e-05, "Pretrain/Loss": 2.0331456661224365, "Pretrain/Loss (Raw)": 2.0523977279663086, "Pretrain/Step": 3358, "Pretrain/Step Time": 8.437852213159204} +{"Pretrain/Learning Rate": 3.7575906351110176e-05, "Pretrain/Loss": 2.0318918228149414, "Pretrain/Loss (Raw)": 1.8406692743301392, "Pretrain/Step": 3359, "Pretrain/Step Time": 8.440051121637225} +{"Pretrain/Learning Rate": 3.756856732985549e-05, "Pretrain/Loss": 2.0332283973693848, "Pretrain/Loss (Raw)": 2.2041525840759277, "Pretrain/Step": 3360, "Pretrain/Step Time": 8.441356820985675} +{"Pretrain/Learning Rate": 3.756122685882098e-05, "Pretrain/Loss": 2.037219524383545, "Pretrain/Loss (Raw)": 2.231729507446289, "Pretrain/Step": 3361, "Pretrain/Step Time": 8.441221617162228} +{"Pretrain/Learning Rate": 3.755388493885337e-05, "Pretrain/Loss": 2.0383028984069824, "Pretrain/Loss (Raw)": 2.16379451751709, "Pretrain/Step": 3362, "Pretrain/Step Time": 8.44329266063869} +{"Pretrain/Learning Rate": 3.7546541570799534e-05, "Pretrain/Loss": 2.039152145385742, "Pretrain/Loss (Raw)": 2.1009230613708496, "Pretrain/Step": 3363, "Pretrain/Step Time": 8.441437335684896} +{"Pretrain/Learning Rate": 3.753919675550654e-05, "Pretrain/Loss": 2.0429117679595947, "Pretrain/Loss (Raw)": 2.3360283374786377, "Pretrain/Step": 3364, "Pretrain/Step Time": 8.4400571025908} +{"Pretrain/Learning Rate": 3.753185049382162e-05, "Pretrain/Loss": 2.043229103088379, "Pretrain/Loss (Raw)": 2.0519115924835205, "Pretrain/Step": 3365, "Pretrain/Step Time": 8.442617760971189} +{"Pretrain/Learning Rate": 3.752450278659214e-05, "Pretrain/Loss": 2.0436692237854004, "Pretrain/Loss (Raw)": 2.0558924674987793, "Pretrain/Step": 3366, "Pretrain/Step Time": 8.443066075444221} +{"Pretrain/Learning Rate": 3.7517153634665665e-05, "Pretrain/Loss": 2.04373836517334, "Pretrain/Loss (Raw)": 2.0708067417144775, "Pretrain/Step": 3367, "Pretrain/Step Time": 8.44149612262845} +{"Pretrain/Learning Rate": 3.750980303888991e-05, "Pretrain/Loss": 2.043489933013916, "Pretrain/Loss (Raw)": 2.0178091526031494, "Pretrain/Step": 3368, "Pretrain/Step Time": 8.440292622894049} +{"Pretrain/Learning Rate": 3.750245100011278e-05, "Pretrain/Loss": 2.0436322689056396, "Pretrain/Loss (Raw)": 2.072200059890747, "Pretrain/Step": 3369, "Pretrain/Step Time": 8.442108437418938} +{"Pretrain/Learning Rate": 3.749509751918232e-05, "Pretrain/Loss": 2.0431370735168457, "Pretrain/Loss (Raw)": 2.015717029571533, "Pretrain/Step": 3370, "Pretrain/Step Time": 8.445937247946858} +{"Pretrain/Learning Rate": 3.748774259694675e-05, "Pretrain/Loss": 2.0407638549804688, "Pretrain/Loss (Raw)": 1.9148246049880981, "Pretrain/Step": 3371, "Pretrain/Step Time": 8.445894399657845} +{"Pretrain/Learning Rate": 3.748038623425446e-05, "Pretrain/Loss": 2.0407874584198, "Pretrain/Loss (Raw)": 2.065277099609375, "Pretrain/Step": 3372, "Pretrain/Step Time": 8.443153416737914} +{"Pretrain/Learning Rate": 3.747302843195401e-05, "Pretrain/Loss": 2.039611339569092, "Pretrain/Loss (Raw)": 2.135728597640991, "Pretrain/Step": 3373, "Pretrain/Step Time": 8.447324285283685} +{"Pretrain/Learning Rate": 3.746566919089411e-05, "Pretrain/Loss": 2.0378410816192627, "Pretrain/Loss (Raw)": 2.006091833114624, "Pretrain/Step": 3374, "Pretrain/Step Time": 8.448378037661314} +{"Pretrain/Learning Rate": 3.745830851192364e-05, "Pretrain/Loss": 2.036468982696533, "Pretrain/Loss (Raw)": 1.9691689014434814, "Pretrain/Step": 3375, "Pretrain/Step Time": 8.44748998247087} +{"Pretrain/Learning Rate": 3.745094639589167e-05, "Pretrain/Loss": 2.037541627883911, "Pretrain/Loss (Raw)": 2.236095428466797, "Pretrain/Step": 3376, "Pretrain/Step Time": 8.446014765650034} +{"Pretrain/Learning Rate": 3.744358284364741e-05, "Pretrain/Loss": 2.036332368850708, "Pretrain/Loss (Raw)": 2.008950710296631, "Pretrain/Step": 3377, "Pretrain/Step Time": 8.446801975369453} +{"Pretrain/Learning Rate": 3.743621785604024e-05, "Pretrain/Loss": 2.035869598388672, "Pretrain/Loss (Raw)": 2.0325140953063965, "Pretrain/Step": 3378, "Pretrain/Step Time": 8.448614368215203} +{"Pretrain/Learning Rate": 3.742885143391971e-05, "Pretrain/Loss": 2.035719394683838, "Pretrain/Loss (Raw)": 2.0162084102630615, "Pretrain/Step": 3379, "Pretrain/Step Time": 8.447326585650444} +{"Pretrain/Learning Rate": 3.7421483578135536e-05, "Pretrain/Loss": 2.034079074859619, "Pretrain/Loss (Raw)": 1.9700589179992676, "Pretrain/Step": 3380, "Pretrain/Step Time": 8.449994472786784} +{"Pretrain/Learning Rate": 3.7414114289537596e-05, "Pretrain/Loss": 2.034409523010254, "Pretrain/Loss (Raw)": 2.0484862327575684, "Pretrain/Step": 3381, "Pretrain/Step Time": 8.449963115155697} +{"Pretrain/Learning Rate": 3.740674356897593e-05, "Pretrain/Loss": 2.035598039627075, "Pretrain/Loss (Raw)": 2.026691436767578, "Pretrain/Step": 3382, "Pretrain/Step Time": 8.452435292303562} +{"Pretrain/Learning Rate": 3.739937141730076e-05, "Pretrain/Loss": 2.036010265350342, "Pretrain/Loss (Raw)": 2.1544289588928223, "Pretrain/Step": 3383, "Pretrain/Step Time": 8.452064514160156} +{"Pretrain/Learning Rate": 3.7391997835362455e-05, "Pretrain/Loss": 2.0362801551818848, "Pretrain/Loss (Raw)": 2.008265972137451, "Pretrain/Step": 3384, "Pretrain/Step Time": 8.452153930440545} +{"Pretrain/Learning Rate": 3.7384622824011555e-05, "Pretrain/Loss": 2.0357840061187744, "Pretrain/Loss (Raw)": 1.97916841506958, "Pretrain/Step": 3385, "Pretrain/Step Time": 8.451578289270401} +{"Pretrain/Learning Rate": 3.737724638409876e-05, "Pretrain/Loss": 2.034860134124756, "Pretrain/Loss (Raw)": 2.0258989334106445, "Pretrain/Step": 3386, "Pretrain/Step Time": 8.453141488134861} +{"Pretrain/Learning Rate": 3.736986851647495e-05, "Pretrain/Loss": 2.0345726013183594, "Pretrain/Loss (Raw)": 2.0310091972351074, "Pretrain/Step": 3387, "Pretrain/Step Time": 8.452956074848771} +{"Pretrain/Learning Rate": 3.736248922199115e-05, "Pretrain/Loss": 2.0349650382995605, "Pretrain/Loss (Raw)": 2.0975773334503174, "Pretrain/Step": 3388, "Pretrain/Step Time": 8.4521473813802} +{"Pretrain/Learning Rate": 3.735510850149856e-05, "Pretrain/Loss": 2.034764289855957, "Pretrain/Loss (Raw)": 2.068235397338867, "Pretrain/Step": 3389, "Pretrain/Step Time": 8.454555245116353} +{"Pretrain/Learning Rate": 3.734772635584855e-05, "Pretrain/Loss": 2.0357842445373535, "Pretrain/Loss (Raw)": 2.103320837020874, "Pretrain/Step": 3390, "Pretrain/Step Time": 8.450882572680712} +{"Pretrain/Learning Rate": 3.7340342785892646e-05, "Pretrain/Loss": 2.0359303951263428, "Pretrain/Loss (Raw)": 2.112675189971924, "Pretrain/Step": 3391, "Pretrain/Step Time": 8.454230763018131} +{"Pretrain/Learning Rate": 3.7332957792482534e-05, "Pretrain/Loss": 2.034569263458252, "Pretrain/Loss (Raw)": 2.0386669635772705, "Pretrain/Step": 3392, "Pretrain/Step Time": 8.456187454983592} +{"Pretrain/Learning Rate": 3.7325571376470076e-05, "Pretrain/Loss": 2.0345888137817383, "Pretrain/Loss (Raw)": 2.0597083568573, "Pretrain/Step": 3393, "Pretrain/Step Time": 8.456903919577599} +{"Pretrain/Learning Rate": 3.731818353870729e-05, "Pretrain/Loss": 2.0325701236724854, "Pretrain/Loss (Raw)": 1.9263043403625488, "Pretrain/Step": 3394, "Pretrain/Step Time": 8.459080945700407} +{"Pretrain/Learning Rate": 3.731079428004637e-05, "Pretrain/Loss": 2.0320920944213867, "Pretrain/Loss (Raw)": 2.063701868057251, "Pretrain/Step": 3395, "Pretrain/Step Time": 8.457058787345886} +{"Pretrain/Learning Rate": 3.7303403601339644e-05, "Pretrain/Loss": 2.0315639972686768, "Pretrain/Loss (Raw)": 2.0293636322021484, "Pretrain/Step": 3396, "Pretrain/Step Time": 8.452669071033597} +{"Pretrain/Learning Rate": 3.729601150343964e-05, "Pretrain/Loss": 2.032442569732666, "Pretrain/Loss (Raw)": 2.0914251804351807, "Pretrain/Step": 3397, "Pretrain/Step Time": 8.454632030799985} +{"Pretrain/Learning Rate": 3.728861798719903e-05, "Pretrain/Loss": 2.0327095985412598, "Pretrain/Loss (Raw)": 2.0068163871765137, "Pretrain/Step": 3398, "Pretrain/Step Time": 8.456304363906384} +{"Pretrain/Learning Rate": 3.728122305347066e-05, "Pretrain/Loss": 2.0328125953674316, "Pretrain/Loss (Raw)": 2.045654773712158, "Pretrain/Step": 3399, "Pretrain/Step Time": 8.458583226427436} +{"Pretrain/Learning Rate": 3.727382670310753e-05, "Pretrain/Loss": 2.0327529907226562, "Pretrain/Loss (Raw)": 1.9590281248092651, "Pretrain/Step": 3400, "Pretrain/Step Time": 8.45339486375451} +{"Pretrain/Learning Rate": 3.726642893696279e-05, "Pretrain/Loss": 2.0340466499328613, "Pretrain/Loss (Raw)": 2.175429582595825, "Pretrain/Step": 3401, "Pretrain/Step Time": 8.457152282819152} +{"Pretrain/Learning Rate": 3.7259029755889786e-05, "Pretrain/Loss": 2.0350100994110107, "Pretrain/Loss (Raw)": 1.8815971612930298, "Pretrain/Step": 3402, "Pretrain/Step Time": 8.450752334669232} +{"Pretrain/Learning Rate": 3.725162916074201e-05, "Pretrain/Loss": 2.033827304840088, "Pretrain/Loss (Raw)": 1.915258526802063, "Pretrain/Step": 3403, "Pretrain/Step Time": 8.451456489041448} +{"Pretrain/Learning Rate": 3.7244227152373115e-05, "Pretrain/Loss": 2.033442974090576, "Pretrain/Loss (Raw)": 1.9501800537109375, "Pretrain/Step": 3404, "Pretrain/Step Time": 8.453829023987055} +{"Pretrain/Learning Rate": 3.7236823731636924e-05, "Pretrain/Loss": 2.033015489578247, "Pretrain/Loss (Raw)": 1.9954352378845215, "Pretrain/Step": 3405, "Pretrain/Step Time": 8.458115618675947} +{"Pretrain/Learning Rate": 3.722941889938741e-05, "Pretrain/Loss": 2.032588005065918, "Pretrain/Loss (Raw)": 2.01556134223938, "Pretrain/Step": 3406, "Pretrain/Step Time": 8.457280270755291} +{"Pretrain/Learning Rate": 3.7222012656478733e-05, "Pretrain/Loss": 2.033708095550537, "Pretrain/Loss (Raw)": 2.112255811691284, "Pretrain/Step": 3407, "Pretrain/Step Time": 8.465155635029078} +{"Pretrain/Learning Rate": 3.7214605003765185e-05, "Pretrain/Loss": 2.0331974029541016, "Pretrain/Loss (Raw)": 2.0111756324768066, "Pretrain/Step": 3408, "Pretrain/Step Time": 8.466661963611841} +{"Pretrain/Learning Rate": 3.720719594210124e-05, "Pretrain/Loss": 2.032886505126953, "Pretrain/Loss (Raw)": 2.0441808700561523, "Pretrain/Step": 3409, "Pretrain/Step Time": 8.463136168196797} +{"Pretrain/Learning Rate": 3.7199785472341535e-05, "Pretrain/Loss": 2.0329833030700684, "Pretrain/Loss (Raw)": 2.064002752304077, "Pretrain/Step": 3410, "Pretrain/Step Time": 8.46289082057774} +{"Pretrain/Learning Rate": 3.719237359534087e-05, "Pretrain/Loss": 2.033144950866699, "Pretrain/Loss (Raw)": 2.1182563304901123, "Pretrain/Step": 3411, "Pretrain/Step Time": 8.46370437182486} +{"Pretrain/Learning Rate": 3.7184960311954185e-05, "Pretrain/Loss": 2.0322787761688232, "Pretrain/Loss (Raw)": 1.8256118297576904, "Pretrain/Step": 3412, "Pretrain/Step Time": 8.46088227815926} +{"Pretrain/Learning Rate": 3.717754562303661e-05, "Pretrain/Loss": 2.03328275680542, "Pretrain/Loss (Raw)": 2.0536298751831055, "Pretrain/Step": 3413, "Pretrain/Step Time": 8.46314505301416} +{"Pretrain/Learning Rate": 3.717012952944344e-05, "Pretrain/Loss": 2.034426212310791, "Pretrain/Loss (Raw)": 2.153444766998291, "Pretrain/Step": 3414, "Pretrain/Step Time": 8.465391766279936} +{"Pretrain/Learning Rate": 3.716271203203009e-05, "Pretrain/Loss": 2.0333666801452637, "Pretrain/Loss (Raw)": 1.9324923753738403, "Pretrain/Step": 3415, "Pretrain/Step Time": 8.462882190942764} +{"Pretrain/Learning Rate": 3.71552931316522e-05, "Pretrain/Loss": 2.0327444076538086, "Pretrain/Loss (Raw)": 1.9915008544921875, "Pretrain/Step": 3416, "Pretrain/Step Time": 8.462219130247831} +{"Pretrain/Learning Rate": 3.71478728291655e-05, "Pretrain/Loss": 2.031449794769287, "Pretrain/Loss (Raw)": 1.8222644329071045, "Pretrain/Step": 3417, "Pretrain/Step Time": 8.462237477302551} +{"Pretrain/Learning Rate": 3.714045112542594e-05, "Pretrain/Loss": 2.0325865745544434, "Pretrain/Loss (Raw)": 2.107642889022827, "Pretrain/Step": 3418, "Pretrain/Step Time": 8.45899112150073} +{"Pretrain/Learning Rate": 3.7133028021289626e-05, "Pretrain/Loss": 2.030733585357666, "Pretrain/Loss (Raw)": 1.82275390625, "Pretrain/Step": 3419, "Pretrain/Step Time": 8.46476911753416} +{"Pretrain/Learning Rate": 3.712560351761277e-05, "Pretrain/Loss": 2.0306057929992676, "Pretrain/Loss (Raw)": 1.946837067604065, "Pretrain/Step": 3420, "Pretrain/Step Time": 8.464528869837523} +{"Pretrain/Learning Rate": 3.711817761525183e-05, "Pretrain/Loss": 2.030754804611206, "Pretrain/Loss (Raw)": 1.9495974779129028, "Pretrain/Step": 3421, "Pretrain/Step Time": 8.462645929306746} +{"Pretrain/Learning Rate": 3.7110750315063344e-05, "Pretrain/Loss": 2.031450033187866, "Pretrain/Loss (Raw)": 2.034095287322998, "Pretrain/Step": 3422, "Pretrain/Step Time": 8.461610097438097} +{"Pretrain/Learning Rate": 3.7103321617904076e-05, "Pretrain/Loss": 2.031144618988037, "Pretrain/Loss (Raw)": 1.7551161050796509, "Pretrain/Step": 3423, "Pretrain/Step Time": 8.466831849887967} +{"Pretrain/Learning Rate": 3.709589152463092e-05, "Pretrain/Loss": 2.030348300933838, "Pretrain/Loss (Raw)": 1.8986314535140991, "Pretrain/Step": 3424, "Pretrain/Step Time": 8.467569736763835} +{"Pretrain/Learning Rate": 3.7088460036100917e-05, "Pretrain/Loss": 2.029778003692627, "Pretrain/Loss (Raw)": 2.1045289039611816, "Pretrain/Step": 3425, "Pretrain/Step Time": 8.468246841803193} +{"Pretrain/Learning Rate": 3.70810271531713e-05, "Pretrain/Loss": 2.026491165161133, "Pretrain/Loss (Raw)": 1.738145112991333, "Pretrain/Step": 3426, "Pretrain/Step Time": 8.46894995123148} +{"Pretrain/Learning Rate": 3.7073592876699444e-05, "Pretrain/Loss": 2.0268943309783936, "Pretrain/Loss (Raw)": 1.9882310628890991, "Pretrain/Step": 3427, "Pretrain/Step Time": 8.467854959890246} +{"Pretrain/Learning Rate": 3.706615720754288e-05, "Pretrain/Loss": 2.0286355018615723, "Pretrain/Loss (Raw)": 2.039098024368286, "Pretrain/Step": 3428, "Pretrain/Step Time": 8.466464014723897} +{"Pretrain/Learning Rate": 3.7058720146559346e-05, "Pretrain/Loss": 2.0272302627563477, "Pretrain/Loss (Raw)": 1.8412044048309326, "Pretrain/Step": 3429, "Pretrain/Step Time": 8.467530712485313} +{"Pretrain/Learning Rate": 3.705128169460667e-05, "Pretrain/Loss": 2.0285873413085938, "Pretrain/Loss (Raw)": 2.1286821365356445, "Pretrain/Step": 3430, "Pretrain/Step Time": 8.469151474535465} +{"Pretrain/Learning Rate": 3.704384185254288e-05, "Pretrain/Loss": 2.0295159816741943, "Pretrain/Loss (Raw)": 2.194324493408203, "Pretrain/Step": 3431, "Pretrain/Step Time": 8.47052451968193} +{"Pretrain/Learning Rate": 3.703640062122618e-05, "Pretrain/Loss": 2.0297954082489014, "Pretrain/Loss (Raw)": 2.085270881652832, "Pretrain/Step": 3432, "Pretrain/Step Time": 8.467805989086628} +{"Pretrain/Learning Rate": 3.702895800151489e-05, "Pretrain/Loss": 2.0283942222595215, "Pretrain/Loss (Raw)": 2.0290818214416504, "Pretrain/Step": 3433, "Pretrain/Step Time": 8.46799124777317} +{"Pretrain/Learning Rate": 3.702151399426752e-05, "Pretrain/Loss": 2.028014659881592, "Pretrain/Loss (Raw)": 1.967656135559082, "Pretrain/Step": 3434, "Pretrain/Step Time": 8.468879351392388} +{"Pretrain/Learning Rate": 3.7014068600342734e-05, "Pretrain/Loss": 2.0283286571502686, "Pretrain/Loss (Raw)": 2.050802707672119, "Pretrain/Step": 3435, "Pretrain/Step Time": 8.467466730624437} +{"Pretrain/Learning Rate": 3.7006621820599356e-05, "Pretrain/Loss": 2.0265326499938965, "Pretrain/Loss (Raw)": 1.8599202632904053, "Pretrain/Step": 3436, "Pretrain/Step Time": 8.467812430113554} +{"Pretrain/Learning Rate": 3.6999173655896374e-05, "Pretrain/Loss": 2.0255515575408936, "Pretrain/Loss (Raw)": 1.9071660041809082, "Pretrain/Step": 3437, "Pretrain/Step Time": 8.466173047199845} +{"Pretrain/Learning Rate": 3.699172410709293e-05, "Pretrain/Loss": 2.0278573036193848, "Pretrain/Loss (Raw)": 2.0632598400115967, "Pretrain/Step": 3438, "Pretrain/Step Time": 8.463370906189084} +{"Pretrain/Learning Rate": 3.698427317504832e-05, "Pretrain/Loss": 2.0273702144622803, "Pretrain/Loss (Raw)": 1.9692447185516357, "Pretrain/Step": 3439, "Pretrain/Step Time": 8.466976780444384} +{"Pretrain/Learning Rate": 3.697682086062201e-05, "Pretrain/Loss": 2.0267016887664795, "Pretrain/Loss (Raw)": 1.9018713235855103, "Pretrain/Step": 3440, "Pretrain/Step Time": 8.469793811440468} +{"Pretrain/Learning Rate": 3.696936716467363e-05, "Pretrain/Loss": 2.0290513038635254, "Pretrain/Loss (Raw)": 2.2582483291625977, "Pretrain/Step": 3441, "Pretrain/Step Time": 8.468428613618016} +{"Pretrain/Learning Rate": 3.696191208806295e-05, "Pretrain/Loss": 2.028952121734619, "Pretrain/Loss (Raw)": 2.023568868637085, "Pretrain/Step": 3442, "Pretrain/Step Time": 8.468451576307416} +{"Pretrain/Learning Rate": 3.695445563164991e-05, "Pretrain/Loss": 2.0288634300231934, "Pretrain/Loss (Raw)": 2.197566270828247, "Pretrain/Step": 3443, "Pretrain/Step Time": 8.47100660763681} +{"Pretrain/Learning Rate": 3.694699779629461e-05, "Pretrain/Loss": 2.0290169715881348, "Pretrain/Loss (Raw)": 2.1547796726226807, "Pretrain/Step": 3444, "Pretrain/Step Time": 8.470533482730389} +{"Pretrain/Learning Rate": 3.693953858285733e-05, "Pretrain/Loss": 2.0305161476135254, "Pretrain/Loss (Raw)": 2.0991368293762207, "Pretrain/Step": 3445, "Pretrain/Step Time": 8.471425296738744} +{"Pretrain/Learning Rate": 3.693207799219845e-05, "Pretrain/Loss": 2.02860426902771, "Pretrain/Loss (Raw)": 1.917893648147583, "Pretrain/Step": 3446, "Pretrain/Step Time": 8.472057102248073} +{"Pretrain/Learning Rate": 3.692461602517859e-05, "Pretrain/Loss": 2.028304100036621, "Pretrain/Loss (Raw)": 2.0002455711364746, "Pretrain/Step": 3447, "Pretrain/Step Time": 8.474291091784835} +{"Pretrain/Learning Rate": 3.691715268265844e-05, "Pretrain/Loss": 2.026942729949951, "Pretrain/Loss (Raw)": 1.933058738708496, "Pretrain/Step": 3448, "Pretrain/Step Time": 8.473437482491136} +{"Pretrain/Learning Rate": 3.690968796549893e-05, "Pretrain/Loss": 2.0293569564819336, "Pretrain/Loss (Raw)": 2.0606110095977783, "Pretrain/Step": 3449, "Pretrain/Step Time": 8.472641443833709} +{"Pretrain/Learning Rate": 3.69022218745611e-05, "Pretrain/Loss": 2.028262138366699, "Pretrain/Loss (Raw)": 1.9189209938049316, "Pretrain/Step": 3450, "Pretrain/Step Time": 8.47280235774815} +{"Pretrain/Learning Rate": 3.689475441070615e-05, "Pretrain/Loss": 2.028613328933716, "Pretrain/Loss (Raw)": 2.0251529216766357, "Pretrain/Step": 3451, "Pretrain/Step Time": 8.477374322712421} +{"Pretrain/Learning Rate": 3.688728557479546e-05, "Pretrain/Loss": 2.0296430587768555, "Pretrain/Loss (Raw)": 2.141930103302002, "Pretrain/Step": 3452, "Pretrain/Step Time": 8.476709313690662} +{"Pretrain/Learning Rate": 3.6879815367690565e-05, "Pretrain/Loss": 2.0292091369628906, "Pretrain/Loss (Raw)": 2.0268492698669434, "Pretrain/Step": 3453, "Pretrain/Step Time": 8.473048694431782} +{"Pretrain/Learning Rate": 3.687234379025313e-05, "Pretrain/Loss": 2.028675079345703, "Pretrain/Loss (Raw)": 2.033719539642334, "Pretrain/Step": 3454, "Pretrain/Step Time": 8.473216896876693} +{"Pretrain/Learning Rate": 3.686487084334502e-05, "Pretrain/Loss": 2.028512954711914, "Pretrain/Loss (Raw)": 1.9707452058792114, "Pretrain/Step": 3455, "Pretrain/Step Time": 8.472192054614425} +{"Pretrain/Learning Rate": 3.685739652782822e-05, "Pretrain/Loss": 2.0288758277893066, "Pretrain/Loss (Raw)": 2.0712358951568604, "Pretrain/Step": 3456, "Pretrain/Step Time": 8.478025319054723} +{"Pretrain/Learning Rate": 3.6849920844564906e-05, "Pretrain/Loss": 2.028982639312744, "Pretrain/Loss (Raw)": 2.227290630340576, "Pretrain/Step": 3457, "Pretrain/Step Time": 8.47458571381867} +{"Pretrain/Learning Rate": 3.6842443794417384e-05, "Pretrain/Loss": 2.0299456119537354, "Pretrain/Loss (Raw)": 2.0131278038024902, "Pretrain/Step": 3458, "Pretrain/Step Time": 8.476829322054982} +{"Pretrain/Learning Rate": 3.683496537824813e-05, "Pretrain/Loss": 2.030366897583008, "Pretrain/Loss (Raw)": 2.019622564315796, "Pretrain/Step": 3459, "Pretrain/Step Time": 8.477397443726659} +{"Pretrain/Learning Rate": 3.6827485596919776e-05, "Pretrain/Loss": 2.030557632446289, "Pretrain/Loss (Raw)": 1.9653584957122803, "Pretrain/Step": 3460, "Pretrain/Step Time": 8.47575164027512} +{"Pretrain/Learning Rate": 3.682000445129512e-05, "Pretrain/Loss": 2.0303127765655518, "Pretrain/Loss (Raw)": 2.1501500606536865, "Pretrain/Step": 3461, "Pretrain/Step Time": 8.475227009505033} +{"Pretrain/Learning Rate": 3.6812521942237104e-05, "Pretrain/Loss": 2.0287580490112305, "Pretrain/Loss (Raw)": 1.7392123937606812, "Pretrain/Step": 3462, "Pretrain/Step Time": 8.477076711133122} +{"Pretrain/Learning Rate": 3.680503807060883e-05, "Pretrain/Loss": 2.0309653282165527, "Pretrain/Loss (Raw)": 2.1215999126434326, "Pretrain/Step": 3463, "Pretrain/Step Time": 8.478476358577609} +{"Pretrain/Learning Rate": 3.6797552837273566e-05, "Pretrain/Loss": 2.0314583778381348, "Pretrain/Loss (Raw)": 2.155953884124756, "Pretrain/Step": 3464, "Pretrain/Step Time": 8.476522296667099} +{"Pretrain/Learning Rate": 3.679006624309472e-05, "Pretrain/Loss": 2.0324208736419678, "Pretrain/Loss (Raw)": 2.034492254257202, "Pretrain/Step": 3465, "Pretrain/Step Time": 8.477468119934201} +{"Pretrain/Learning Rate": 3.678257828893589e-05, "Pretrain/Loss": 2.0326714515686035, "Pretrain/Loss (Raw)": 2.044644594192505, "Pretrain/Step": 3466, "Pretrain/Step Time": 8.478219665586948} +{"Pretrain/Learning Rate": 3.6775088975660796e-05, "Pretrain/Loss": 2.030975103378296, "Pretrain/Loss (Raw)": 1.8770948648452759, "Pretrain/Step": 3467, "Pretrain/Step Time": 8.478222480043769} +{"Pretrain/Learning Rate": 3.6767598304133324e-05, "Pretrain/Loss": 2.031853199005127, "Pretrain/Loss (Raw)": 2.1398251056671143, "Pretrain/Step": 3468, "Pretrain/Step Time": 8.476223401725292} +{"Pretrain/Learning Rate": 3.676010627521751e-05, "Pretrain/Loss": 2.031733989715576, "Pretrain/Loss (Raw)": 2.072396993637085, "Pretrain/Step": 3469, "Pretrain/Step Time": 8.477217366918921} +{"Pretrain/Learning Rate": 3.6752612889777574e-05, "Pretrain/Loss": 2.032241106033325, "Pretrain/Loss (Raw)": 2.062640905380249, "Pretrain/Step": 3470, "Pretrain/Step Time": 8.475871989503503} +{"Pretrain/Learning Rate": 3.674511814867788e-05, "Pretrain/Loss": 2.032402992248535, "Pretrain/Loss (Raw)": 2.141803503036499, "Pretrain/Step": 3471, "Pretrain/Step Time": 8.478544890880585} +{"Pretrain/Learning Rate": 3.673762205278293e-05, "Pretrain/Loss": 2.0343260765075684, "Pretrain/Loss (Raw)": 2.1764261722564697, "Pretrain/Step": 3472, "Pretrain/Step Time": 8.478677233681083} +{"Pretrain/Learning Rate": 3.6730124602957396e-05, "Pretrain/Loss": 2.034853935241699, "Pretrain/Loss (Raw)": 2.0241618156433105, "Pretrain/Step": 3473, "Pretrain/Step Time": 8.479577016085386} +{"Pretrain/Learning Rate": 3.6722625800066124e-05, "Pretrain/Loss": 2.0357587337493896, "Pretrain/Loss (Raw)": 2.1996660232543945, "Pretrain/Step": 3474, "Pretrain/Step Time": 8.478212390094995} +{"Pretrain/Learning Rate": 3.671512564497408e-05, "Pretrain/Loss": 2.037416458129883, "Pretrain/Loss (Raw)": 2.1216137409210205, "Pretrain/Step": 3475, "Pretrain/Step Time": 8.480347231030464} +{"Pretrain/Learning Rate": 3.6707624138546414e-05, "Pretrain/Loss": 2.0396480560302734, "Pretrain/Loss (Raw)": 2.3194284439086914, "Pretrain/Step": 3476, "Pretrain/Step Time": 8.480842275545001} +{"Pretrain/Learning Rate": 3.670012128164841e-05, "Pretrain/Loss": 2.0397822856903076, "Pretrain/Loss (Raw)": 2.074479818344116, "Pretrain/Step": 3477, "Pretrain/Step Time": 8.477356985211372} +{"Pretrain/Learning Rate": 3.669261707514553e-05, "Pretrain/Loss": 2.038564682006836, "Pretrain/Loss (Raw)": 1.9585741758346558, "Pretrain/Step": 3478, "Pretrain/Step Time": 8.47513030283153} +{"Pretrain/Learning Rate": 3.6685111519903384e-05, "Pretrain/Loss": 2.0388526916503906, "Pretrain/Loss (Raw)": 2.0764877796173096, "Pretrain/Step": 3479, "Pretrain/Step Time": 8.478214796632528} +{"Pretrain/Learning Rate": 3.667760461678772e-05, "Pretrain/Loss": 2.037868022918701, "Pretrain/Loss (Raw)": 1.9314900636672974, "Pretrain/Step": 3480, "Pretrain/Step Time": 8.479004707187414} +{"Pretrain/Learning Rate": 3.667009636666447e-05, "Pretrain/Loss": 2.0372700691223145, "Pretrain/Loss (Raw)": 1.9289742708206177, "Pretrain/Step": 3481, "Pretrain/Step Time": 8.478173928335309} +{"Pretrain/Learning Rate": 3.6662586770399714e-05, "Pretrain/Loss": 2.0381369590759277, "Pretrain/Loss (Raw)": 2.1532745361328125, "Pretrain/Step": 3482, "Pretrain/Step Time": 8.481921123340726} +{"Pretrain/Learning Rate": 3.665507582885968e-05, "Pretrain/Loss": 2.036729335784912, "Pretrain/Loss (Raw)": 2.0409185886383057, "Pretrain/Step": 3483, "Pretrain/Step Time": 8.478784553706646} +{"Pretrain/Learning Rate": 3.664756354291073e-05, "Pretrain/Loss": 2.0364913940429688, "Pretrain/Loss (Raw)": 1.993467926979065, "Pretrain/Step": 3484, "Pretrain/Step Time": 8.47729523293674} +{"Pretrain/Learning Rate": 3.6640049913419414e-05, "Pretrain/Loss": 2.034078598022461, "Pretrain/Loss (Raw)": 1.873408555984497, "Pretrain/Step": 3485, "Pretrain/Step Time": 8.474936010316014} +{"Pretrain/Learning Rate": 3.663253494125244e-05, "Pretrain/Loss": 2.034667491912842, "Pretrain/Loss (Raw)": 2.127749443054199, "Pretrain/Step": 3486, "Pretrain/Step Time": 8.473015803843737} +{"Pretrain/Learning Rate": 3.6625018627276644e-05, "Pretrain/Loss": 2.0359973907470703, "Pretrain/Loss (Raw)": 2.010920524597168, "Pretrain/Step": 3487, "Pretrain/Step Time": 8.475425280630589} +{"Pretrain/Learning Rate": 3.661750097235904e-05, "Pretrain/Loss": 2.0348572731018066, "Pretrain/Loss (Raw)": 2.0582330226898193, "Pretrain/Step": 3488, "Pretrain/Step Time": 8.47623122856021} +{"Pretrain/Learning Rate": 3.660998197736677e-05, "Pretrain/Loss": 2.0332813262939453, "Pretrain/Loss (Raw)": 2.0299739837646484, "Pretrain/Step": 3489, "Pretrain/Step Time": 8.475773435086012} +{"Pretrain/Learning Rate": 3.6602461643167174e-05, "Pretrain/Loss": 2.0325143337249756, "Pretrain/Loss (Raw)": 2.0656230449676514, "Pretrain/Step": 3490, "Pretrain/Step Time": 8.470645420253277} +{"Pretrain/Learning Rate": 3.65949399706277e-05, "Pretrain/Loss": 2.03293776512146, "Pretrain/Loss (Raw)": 2.155130624771118, "Pretrain/Step": 3491, "Pretrain/Step Time": 8.474216137081385} +{"Pretrain/Learning Rate": 3.6587416960615985e-05, "Pretrain/Loss": 2.030552387237549, "Pretrain/Loss (Raw)": 2.030707359313965, "Pretrain/Step": 3492, "Pretrain/Step Time": 8.474168591201305} +{"Pretrain/Learning Rate": 3.657989261399978e-05, "Pretrain/Loss": 2.0302131175994873, "Pretrain/Loss (Raw)": 2.008484363555908, "Pretrain/Step": 3493, "Pretrain/Step Time": 8.47367319278419} +{"Pretrain/Learning Rate": 3.6572366931647035e-05, "Pretrain/Loss": 2.0304677486419678, "Pretrain/Loss (Raw)": 2.088482618331909, "Pretrain/Step": 3494, "Pretrain/Step Time": 8.46961353905499} +{"Pretrain/Learning Rate": 3.656483991442583e-05, "Pretrain/Loss": 2.030022382736206, "Pretrain/Loss (Raw)": 2.0138094425201416, "Pretrain/Step": 3495, "Pretrain/Step Time": 8.471064867451787} +{"Pretrain/Learning Rate": 3.655731156320441e-05, "Pretrain/Loss": 2.0281481742858887, "Pretrain/Loss (Raw)": 1.7778886556625366, "Pretrain/Step": 3496, "Pretrain/Step Time": 8.473537499085069} +{"Pretrain/Learning Rate": 3.654978187885116e-05, "Pretrain/Loss": 2.028722047805786, "Pretrain/Loss (Raw)": 2.1456565856933594, "Pretrain/Step": 3497, "Pretrain/Step Time": 8.47270100750029} +{"Pretrain/Learning Rate": 3.654225086223463e-05, "Pretrain/Loss": 2.0282907485961914, "Pretrain/Loss (Raw)": 1.9605062007904053, "Pretrain/Step": 3498, "Pretrain/Step Time": 8.470666524022818} +{"Pretrain/Learning Rate": 3.653471851422352e-05, "Pretrain/Loss": 2.028331756591797, "Pretrain/Loss (Raw)": 1.9201043844223022, "Pretrain/Step": 3499, "Pretrain/Step Time": 8.469356128945947} +{"Pretrain/Learning Rate": 3.6527184835686685e-05, "Pretrain/Loss": 2.028797149658203, "Pretrain/Loss (Raw)": 2.1248276233673096, "Pretrain/Step": 3500, "Pretrain/Step Time": 8.47212284617126} +{"Pretrain/Learning Rate": 3.651964982749312e-05, "Pretrain/Loss": 2.028352975845337, "Pretrain/Loss (Raw)": 2.0788614749908447, "Pretrain/Step": 3501, "Pretrain/Step Time": 8.467618446797132} +{"Pretrain/Learning Rate": 3.6512113490512004e-05, "Pretrain/Loss": 2.028883934020996, "Pretrain/Loss (Raw)": 2.07405424118042, "Pretrain/Step": 3502, "Pretrain/Step Time": 8.465146956965327} +{"Pretrain/Learning Rate": 3.6504575825612644e-05, "Pretrain/Loss": 2.0294013023376465, "Pretrain/Loss (Raw)": 2.0353994369506836, "Pretrain/Step": 3503, "Pretrain/Step Time": 8.468228029087186} +{"Pretrain/Learning Rate": 3.64970368336645e-05, "Pretrain/Loss": 2.0269699096679688, "Pretrain/Loss (Raw)": 1.9249073266983032, "Pretrain/Step": 3504, "Pretrain/Step Time": 8.471173664554954} +{"Pretrain/Learning Rate": 3.6489496515537204e-05, "Pretrain/Loss": 2.027594566345215, "Pretrain/Loss (Raw)": 2.088874101638794, "Pretrain/Step": 3505, "Pretrain/Step Time": 8.470381120219827} +{"Pretrain/Learning Rate": 3.648195487210051e-05, "Pretrain/Loss": 2.027740955352783, "Pretrain/Loss (Raw)": 2.0512561798095703, "Pretrain/Step": 3506, "Pretrain/Step Time": 8.469338139519095} +{"Pretrain/Learning Rate": 3.647441190422437e-05, "Pretrain/Loss": 2.026855945587158, "Pretrain/Loss (Raw)": 1.9029430150985718, "Pretrain/Step": 3507, "Pretrain/Step Time": 8.469841971993446} +{"Pretrain/Learning Rate": 3.646686761277884e-05, "Pretrain/Loss": 2.0273478031158447, "Pretrain/Loss (Raw)": 2.032986640930176, "Pretrain/Step": 3508, "Pretrain/Step Time": 8.466835962608457} +{"Pretrain/Learning Rate": 3.6459321998634175e-05, "Pretrain/Loss": 2.028151035308838, "Pretrain/Loss (Raw)": 2.151310920715332, "Pretrain/Step": 3509, "Pretrain/Step Time": 8.46792383864522} +{"Pretrain/Learning Rate": 3.6451775062660726e-05, "Pretrain/Loss": 2.027209758758545, "Pretrain/Loss (Raw)": 1.9062271118164062, "Pretrain/Step": 3510, "Pretrain/Step Time": 8.466674039140344} +{"Pretrain/Learning Rate": 3.6444226805729056e-05, "Pretrain/Loss": 2.0251240730285645, "Pretrain/Loss (Raw)": 1.8874750137329102, "Pretrain/Step": 3511, "Pretrain/Step Time": 8.465660309419036} +{"Pretrain/Learning Rate": 3.6436677228709846e-05, "Pretrain/Loss": 2.024151563644409, "Pretrain/Loss (Raw)": 1.883764386177063, "Pretrain/Step": 3512, "Pretrain/Step Time": 8.464318195357919} +{"Pretrain/Learning Rate": 3.642912633247394e-05, "Pretrain/Loss": 2.0256905555725098, "Pretrain/Loss (Raw)": 2.1761484146118164, "Pretrain/Step": 3513, "Pretrain/Step Time": 8.464132808148861} +{"Pretrain/Learning Rate": 3.642157411789233e-05, "Pretrain/Loss": 2.0273356437683105, "Pretrain/Loss (Raw)": 2.23647403717041, "Pretrain/Step": 3514, "Pretrain/Step Time": 8.460617749020457} +{"Pretrain/Learning Rate": 3.641402058583615e-05, "Pretrain/Loss": 2.027956247329712, "Pretrain/Loss (Raw)": 2.1104633808135986, "Pretrain/Step": 3515, "Pretrain/Step Time": 8.46190296113491} +{"Pretrain/Learning Rate": 3.6406465737176706e-05, "Pretrain/Loss": 2.027949810028076, "Pretrain/Loss (Raw)": 2.0967509746551514, "Pretrain/Step": 3516, "Pretrain/Step Time": 8.46273791603744} +{"Pretrain/Learning Rate": 3.6398909572785464e-05, "Pretrain/Loss": 2.028574228286743, "Pretrain/Loss (Raw)": 2.148141860961914, "Pretrain/Step": 3517, "Pretrain/Step Time": 8.459164693951607} +{"Pretrain/Learning Rate": 3.6391352093534e-05, "Pretrain/Loss": 2.026909589767456, "Pretrain/Loss (Raw)": 1.8902616500854492, "Pretrain/Step": 3518, "Pretrain/Step Time": 8.458640517666936} +{"Pretrain/Learning Rate": 3.638379330029407e-05, "Pretrain/Loss": 2.025733709335327, "Pretrain/Loss (Raw)": 1.9621570110321045, "Pretrain/Step": 3519, "Pretrain/Step Time": 8.460916442796588} +{"Pretrain/Learning Rate": 3.637623319393758e-05, "Pretrain/Loss": 2.0262889862060547, "Pretrain/Loss (Raw)": 2.1097521781921387, "Pretrain/Step": 3520, "Pretrain/Step Time": 8.45847594551742} +{"Pretrain/Learning Rate": 3.63686717753366e-05, "Pretrain/Loss": 2.02207350730896, "Pretrain/Loss (Raw)": 1.5200926065444946, "Pretrain/Step": 3521, "Pretrain/Step Time": 8.460288712754846} +{"Pretrain/Learning Rate": 3.6361109045363315e-05, "Pretrain/Loss": 2.02470064163208, "Pretrain/Loss (Raw)": 2.262599229812622, "Pretrain/Step": 3522, "Pretrain/Step Time": 8.46013150550425} +{"Pretrain/Learning Rate": 3.63535450048901e-05, "Pretrain/Loss": 2.024977207183838, "Pretrain/Loss (Raw)": 2.099133014678955, "Pretrain/Step": 3523, "Pretrain/Step Time": 8.46194763481617} +{"Pretrain/Learning Rate": 3.634597965478946e-05, "Pretrain/Loss": 2.0245072841644287, "Pretrain/Loss (Raw)": 1.9691808223724365, "Pretrain/Step": 3524, "Pretrain/Step Time": 8.465021835640073} +{"Pretrain/Learning Rate": 3.633841299593406e-05, "Pretrain/Loss": 2.0222008228302, "Pretrain/Loss (Raw)": 1.7961875200271606, "Pretrain/Step": 3525, "Pretrain/Step Time": 8.461997039616108} +{"Pretrain/Learning Rate": 3.6330845029196695e-05, "Pretrain/Loss": 2.0216240882873535, "Pretrain/Loss (Raw)": 1.9330267906188965, "Pretrain/Step": 3526, "Pretrain/Step Time": 8.462870357558131} +{"Pretrain/Learning Rate": 3.632327575545034e-05, "Pretrain/Loss": 2.022068738937378, "Pretrain/Loss (Raw)": 2.102557420730591, "Pretrain/Step": 3527, "Pretrain/Step Time": 8.460833188146353} +{"Pretrain/Learning Rate": 3.6315705175568106e-05, "Pretrain/Loss": 2.023494243621826, "Pretrain/Loss (Raw)": 2.1414825916290283, "Pretrain/Step": 3528, "Pretrain/Step Time": 8.461163805797696} +{"Pretrain/Learning Rate": 3.630813329042326e-05, "Pretrain/Loss": 2.023651123046875, "Pretrain/Loss (Raw)": 2.1955082416534424, "Pretrain/Step": 3529, "Pretrain/Step Time": 8.459354853257537} +{"Pretrain/Learning Rate": 3.6300560100889207e-05, "Pretrain/Loss": 2.024752378463745, "Pretrain/Loss (Raw)": 2.0225510597229004, "Pretrain/Step": 3530, "Pretrain/Step Time": 8.459783541038632} +{"Pretrain/Learning Rate": 3.629298560783952e-05, "Pretrain/Loss": 2.0260422229766846, "Pretrain/Loss (Raw)": 2.080371618270874, "Pretrain/Step": 3531, "Pretrain/Step Time": 8.458562197163701} +{"Pretrain/Learning Rate": 3.628540981214792e-05, "Pretrain/Loss": 2.027376174926758, "Pretrain/Loss (Raw)": 2.120903491973877, "Pretrain/Step": 3532, "Pretrain/Step Time": 8.457276243716478} +{"Pretrain/Learning Rate": 3.627783271468825e-05, "Pretrain/Loss": 2.0303077697753906, "Pretrain/Loss (Raw)": 2.3707070350646973, "Pretrain/Step": 3533, "Pretrain/Step Time": 8.45354651287198} +{"Pretrain/Learning Rate": 3.627025431633455e-05, "Pretrain/Loss": 2.030501127243042, "Pretrain/Loss (Raw)": 2.0403008460998535, "Pretrain/Step": 3534, "Pretrain/Step Time": 8.452613418921828} +{"Pretrain/Learning Rate": 3.6262674617960974e-05, "Pretrain/Loss": 2.0305280685424805, "Pretrain/Loss (Raw)": 2.1157054901123047, "Pretrain/Step": 3535, "Pretrain/Step Time": 8.449235018342733} +{"Pretrain/Learning Rate": 3.6255093620441834e-05, "Pretrain/Loss": 2.0305705070495605, "Pretrain/Loss (Raw)": 2.0165863037109375, "Pretrain/Step": 3536, "Pretrain/Step Time": 8.450145142152905} +{"Pretrain/Learning Rate": 3.6247511324651606e-05, "Pretrain/Loss": 2.0283074378967285, "Pretrain/Loss (Raw)": 1.7545199394226074, "Pretrain/Step": 3537, "Pretrain/Step Time": 8.451671166345477} +{"Pretrain/Learning Rate": 3.6239927731464896e-05, "Pretrain/Loss": 2.0277934074401855, "Pretrain/Loss (Raw)": 1.9982134103775024, "Pretrain/Step": 3538, "Pretrain/Step Time": 8.45121586509049} +{"Pretrain/Learning Rate": 3.6232342841756464e-05, "Pretrain/Loss": 2.026759147644043, "Pretrain/Loss (Raw)": 1.9858832359313965, "Pretrain/Step": 3539, "Pretrain/Step Time": 8.452829642221332} +{"Pretrain/Learning Rate": 3.622475665640125e-05, "Pretrain/Loss": 2.0288033485412598, "Pretrain/Loss (Raw)": 2.087284564971924, "Pretrain/Step": 3540, "Pretrain/Step Time": 8.452530277892947} +{"Pretrain/Learning Rate": 3.621716917627429e-05, "Pretrain/Loss": 2.027257204055786, "Pretrain/Loss (Raw)": 1.8556947708129883, "Pretrain/Step": 3541, "Pretrain/Step Time": 8.450419679284096} +{"Pretrain/Learning Rate": 3.6209580402250815e-05, "Pretrain/Loss": 2.026144504547119, "Pretrain/Loss (Raw)": 2.0110232830047607, "Pretrain/Step": 3542, "Pretrain/Step Time": 8.446903271600604} +{"Pretrain/Learning Rate": 3.620199033520617e-05, "Pretrain/Loss": 2.0280323028564453, "Pretrain/Loss (Raw)": 2.1741461753845215, "Pretrain/Step": 3543, "Pretrain/Step Time": 8.449703365564346} +{"Pretrain/Learning Rate": 3.619439897601587e-05, "Pretrain/Loss": 2.0288636684417725, "Pretrain/Loss (Raw)": 2.0978963375091553, "Pretrain/Step": 3544, "Pretrain/Step Time": 8.450775906443596} +{"Pretrain/Learning Rate": 3.61868063255556e-05, "Pretrain/Loss": 2.0313892364501953, "Pretrain/Loss (Raw)": 2.1455554962158203, "Pretrain/Step": 3545, "Pretrain/Step Time": 8.449127458035946} +{"Pretrain/Learning Rate": 3.617921238470114e-05, "Pretrain/Loss": 2.03049635887146, "Pretrain/Loss (Raw)": 1.9933406114578247, "Pretrain/Step": 3546, "Pretrain/Step Time": 8.453329436480999} +{"Pretrain/Learning Rate": 3.617161715432847e-05, "Pretrain/Loss": 2.0332486629486084, "Pretrain/Loss (Raw)": 2.175048351287842, "Pretrain/Step": 3547, "Pretrain/Step Time": 8.445468366146088} +{"Pretrain/Learning Rate": 3.616402063531368e-05, "Pretrain/Loss": 2.0346150398254395, "Pretrain/Loss (Raw)": 2.1217241287231445, "Pretrain/Step": 3548, "Pretrain/Step Time": 8.449962198734283} +{"Pretrain/Learning Rate": 3.6156422828533035e-05, "Pretrain/Loss": 2.0355801582336426, "Pretrain/Loss (Raw)": 2.0731594562530518, "Pretrain/Step": 3549, "Pretrain/Step Time": 8.448533972725272} +{"Pretrain/Learning Rate": 3.6148823734862934e-05, "Pretrain/Loss": 2.034205913543701, "Pretrain/Loss (Raw)": 1.8581738471984863, "Pretrain/Step": 3550, "Pretrain/Step Time": 8.449763055890799} +{"Pretrain/Learning Rate": 3.6141223355179944e-05, "Pretrain/Loss": 2.034287929534912, "Pretrain/Loss (Raw)": 1.765613079071045, "Pretrain/Step": 3551, "Pretrain/Step Time": 8.444790242239833} +{"Pretrain/Learning Rate": 3.613362169036074e-05, "Pretrain/Loss": 2.0360970497131348, "Pretrain/Loss (Raw)": 2.130183219909668, "Pretrain/Step": 3552, "Pretrain/Step Time": 8.447807271033525} +{"Pretrain/Learning Rate": 3.61260187412822e-05, "Pretrain/Loss": 2.035327911376953, "Pretrain/Loss (Raw)": 2.006105422973633, "Pretrain/Step": 3553, "Pretrain/Step Time": 8.447673907503486} +{"Pretrain/Learning Rate": 3.61184145088213e-05, "Pretrain/Loss": 2.0372681617736816, "Pretrain/Loss (Raw)": 1.9865072965621948, "Pretrain/Step": 3554, "Pretrain/Step Time": 8.44417522661388} +{"Pretrain/Learning Rate": 3.6110808993855194e-05, "Pretrain/Loss": 2.034738540649414, "Pretrain/Loss (Raw)": 1.6644067764282227, "Pretrain/Step": 3555, "Pretrain/Step Time": 8.447439081966877} +{"Pretrain/Learning Rate": 3.6103202197261175e-05, "Pretrain/Loss": 2.03515887260437, "Pretrain/Loss (Raw)": 2.092914342880249, "Pretrain/Step": 3556, "Pretrain/Step Time": 8.446989828720689} +{"Pretrain/Learning Rate": 3.609559411991669e-05, "Pretrain/Loss": 2.037229061126709, "Pretrain/Loss (Raw)": 2.106178045272827, "Pretrain/Step": 3557, "Pretrain/Step Time": 8.448669966310263} +{"Pretrain/Learning Rate": 3.608798476269932e-05, "Pretrain/Loss": 2.0374503135681152, "Pretrain/Loss (Raw)": 2.1570076942443848, "Pretrain/Step": 3558, "Pretrain/Step Time": 8.442585807293653} +{"Pretrain/Learning Rate": 3.60803741264868e-05, "Pretrain/Loss": 2.036041259765625, "Pretrain/Loss (Raw)": 2.013976573944092, "Pretrain/Step": 3559, "Pretrain/Step Time": 8.442235108464956} +{"Pretrain/Learning Rate": 3.607276221215703e-05, "Pretrain/Loss": 2.037273645401001, "Pretrain/Loss (Raw)": 2.2430076599121094, "Pretrain/Step": 3560, "Pretrain/Step Time": 8.443667413666844} +{"Pretrain/Learning Rate": 3.606514902058802e-05, "Pretrain/Loss": 2.0373120307922363, "Pretrain/Loss (Raw)": 2.0339860916137695, "Pretrain/Step": 3561, "Pretrain/Step Time": 8.445761764422059} +{"Pretrain/Learning Rate": 3.6057534552657954e-05, "Pretrain/Loss": 2.03713059425354, "Pretrain/Loss (Raw)": 1.9444518089294434, "Pretrain/Step": 3562, "Pretrain/Step Time": 8.447147734463215} +{"Pretrain/Learning Rate": 3.604991880924518e-05, "Pretrain/Loss": 2.0381438732147217, "Pretrain/Loss (Raw)": 2.1805012226104736, "Pretrain/Step": 3563, "Pretrain/Step Time": 8.449357826262712} +{"Pretrain/Learning Rate": 3.604230179122814e-05, "Pretrain/Loss": 2.0378501415252686, "Pretrain/Loss (Raw)": 1.822323203086853, "Pretrain/Step": 3564, "Pretrain/Step Time": 8.449404621496797} +{"Pretrain/Learning Rate": 3.6034683499485465e-05, "Pretrain/Loss": 2.040713310241699, "Pretrain/Loss (Raw)": 2.2736434936523438, "Pretrain/Step": 3565, "Pretrain/Step Time": 8.448114091530442} +{"Pretrain/Learning Rate": 3.602706393489594e-05, "Pretrain/Loss": 2.0411875247955322, "Pretrain/Loss (Raw)": 2.1239829063415527, "Pretrain/Step": 3566, "Pretrain/Step Time": 8.448522167280316} +{"Pretrain/Learning Rate": 3.6019443098338466e-05, "Pretrain/Loss": 2.040619373321533, "Pretrain/Loss (Raw)": 1.8965058326721191, "Pretrain/Step": 3567, "Pretrain/Step Time": 8.448391681537032} +{"Pretrain/Learning Rate": 3.6011820990692094e-05, "Pretrain/Loss": 2.0422091484069824, "Pretrain/Loss (Raw)": 2.105368137359619, "Pretrain/Step": 3568, "Pretrain/Step Time": 8.446051293984056} +{"Pretrain/Learning Rate": 3.6004197612836044e-05, "Pretrain/Loss": 2.0410470962524414, "Pretrain/Loss (Raw)": 2.1094918251037598, "Pretrain/Step": 3569, "Pretrain/Step Time": 8.448292002081871} +{"Pretrain/Learning Rate": 3.599657296564966e-05, "Pretrain/Loss": 2.041343927383423, "Pretrain/Loss (Raw)": 2.061593770980835, "Pretrain/Step": 3570, "Pretrain/Step Time": 8.44541677646339} +{"Pretrain/Learning Rate": 3.598894705001246e-05, "Pretrain/Loss": 2.0410704612731934, "Pretrain/Loss (Raw)": 2.1625638008117676, "Pretrain/Step": 3571, "Pretrain/Step Time": 8.445969980210066} +{"Pretrain/Learning Rate": 3.598131986680408e-05, "Pretrain/Loss": 2.040729522705078, "Pretrain/Loss (Raw)": 2.111135244369507, "Pretrain/Step": 3572, "Pretrain/Step Time": 8.44886620901525} +{"Pretrain/Learning Rate": 3.59736914169043e-05, "Pretrain/Loss": 2.040372371673584, "Pretrain/Loss (Raw)": 2.0534207820892334, "Pretrain/Step": 3573, "Pretrain/Step Time": 8.450497969985008} +{"Pretrain/Learning Rate": 3.596606170119308e-05, "Pretrain/Loss": 2.040461778640747, "Pretrain/Loss (Raw)": 1.9293123483657837, "Pretrain/Step": 3574, "Pretrain/Step Time": 8.449230948463082} +{"Pretrain/Learning Rate": 3.59584307205505e-05, "Pretrain/Loss": 2.041616678237915, "Pretrain/Loss (Raw)": 2.148097515106201, "Pretrain/Step": 3575, "Pretrain/Step Time": 8.449008949100971} +{"Pretrain/Learning Rate": 3.5950798475856783e-05, "Pretrain/Loss": 2.041959285736084, "Pretrain/Loss (Raw)": 1.976871132850647, "Pretrain/Step": 3576, "Pretrain/Step Time": 8.446588875725865} +{"Pretrain/Learning Rate": 3.59431649679923e-05, "Pretrain/Loss": 2.0409021377563477, "Pretrain/Loss (Raw)": 1.9253301620483398, "Pretrain/Step": 3577, "Pretrain/Step Time": 8.446310799568892} +{"Pretrain/Learning Rate": 3.59355301978376e-05, "Pretrain/Loss": 2.0402326583862305, "Pretrain/Loss (Raw)": 1.8332240581512451, "Pretrain/Step": 3578, "Pretrain/Step Time": 8.44617846980691} +{"Pretrain/Learning Rate": 3.592789416627332e-05, "Pretrain/Loss": 2.038905382156372, "Pretrain/Loss (Raw)": 1.8552663326263428, "Pretrain/Step": 3579, "Pretrain/Step Time": 8.443350711837411} +{"Pretrain/Learning Rate": 3.59202568741803e-05, "Pretrain/Loss": 2.0384979248046875, "Pretrain/Loss (Raw)": 2.089780569076538, "Pretrain/Step": 3580, "Pretrain/Step Time": 8.448052044957876} +{"Pretrain/Learning Rate": 3.5912618322439485e-05, "Pretrain/Loss": 2.038078784942627, "Pretrain/Loss (Raw)": 1.973189353942871, "Pretrain/Step": 3581, "Pretrain/Step Time": 8.446966767311096} +{"Pretrain/Learning Rate": 3.590497851193198e-05, "Pretrain/Loss": 2.037593364715576, "Pretrain/Loss (Raw)": 1.971559762954712, "Pretrain/Step": 3582, "Pretrain/Step Time": 8.446275644004345} +{"Pretrain/Learning Rate": 3.589733744353904e-05, "Pretrain/Loss": 2.0380194187164307, "Pretrain/Loss (Raw)": 2.0253100395202637, "Pretrain/Step": 3583, "Pretrain/Step Time": 8.44867723248899} +{"Pretrain/Learning Rate": 3.588969511814205e-05, "Pretrain/Loss": 2.0378260612487793, "Pretrain/Loss (Raw)": 2.046475887298584, "Pretrain/Step": 3584, "Pretrain/Step Time": 8.442856796085835} +{"Pretrain/Learning Rate": 3.588205153662256e-05, "Pretrain/Loss": 2.036590099334717, "Pretrain/Loss (Raw)": 2.0690758228302, "Pretrain/Step": 3585, "Pretrain/Step Time": 8.448695868253708} +{"Pretrain/Learning Rate": 3.587440669986224e-05, "Pretrain/Loss": 2.039142608642578, "Pretrain/Loss (Raw)": 2.3398549556732178, "Pretrain/Step": 3586, "Pretrain/Step Time": 8.449747741222382} +{"Pretrain/Learning Rate": 3.586676060874293e-05, "Pretrain/Loss": 2.0398945808410645, "Pretrain/Loss (Raw)": 2.1159045696258545, "Pretrain/Step": 3587, "Pretrain/Step Time": 8.448284655809402} +{"Pretrain/Learning Rate": 3.585911326414661e-05, "Pretrain/Loss": 2.0408506393432617, "Pretrain/Loss (Raw)": 2.087728261947632, "Pretrain/Step": 3588, "Pretrain/Step Time": 8.450448427349329} +{"Pretrain/Learning Rate": 3.5851464666955385e-05, "Pretrain/Loss": 2.040764808654785, "Pretrain/Loss (Raw)": 2.1391711235046387, "Pretrain/Step": 3589, "Pretrain/Step Time": 8.450546357780695} +{"Pretrain/Learning Rate": 3.5843814818051534e-05, "Pretrain/Loss": 2.0432097911834717, "Pretrain/Loss (Raw)": 2.052121162414551, "Pretrain/Step": 3590, "Pretrain/Step Time": 8.452212404459715} +{"Pretrain/Learning Rate": 3.583616371831745e-05, "Pretrain/Loss": 2.043057441711426, "Pretrain/Loss (Raw)": 2.102132558822632, "Pretrain/Step": 3591, "Pretrain/Step Time": 8.454157285392284} +{"Pretrain/Learning Rate": 3.5828511368635685e-05, "Pretrain/Loss": 2.0424089431762695, "Pretrain/Loss (Raw)": 2.072916269302368, "Pretrain/Step": 3592, "Pretrain/Step Time": 8.454120406880975} +{"Pretrain/Learning Rate": 3.5820857769888944e-05, "Pretrain/Loss": 2.0430970191955566, "Pretrain/Loss (Raw)": 2.122598886489868, "Pretrain/Step": 3593, "Pretrain/Step Time": 8.450243165716529} +{"Pretrain/Learning Rate": 3.5813202922960056e-05, "Pretrain/Loss": 2.0427255630493164, "Pretrain/Loss (Raw)": 1.9970805644989014, "Pretrain/Step": 3594, "Pretrain/Step Time": 8.451485924422741} +{"Pretrain/Learning Rate": 3.5805546828732015e-05, "Pretrain/Loss": 2.04463529586792, "Pretrain/Loss (Raw)": 2.121561288833618, "Pretrain/Step": 3595, "Pretrain/Step Time": 8.455094272270799} +{"Pretrain/Learning Rate": 3.5797889488087945e-05, "Pretrain/Loss": 2.044464111328125, "Pretrain/Loss (Raw)": 2.117873191833496, "Pretrain/Step": 3596, "Pretrain/Step Time": 8.453961454331875} +{"Pretrain/Learning Rate": 3.579023090191112e-05, "Pretrain/Loss": 2.044313430786133, "Pretrain/Loss (Raw)": 2.0531225204467773, "Pretrain/Step": 3597, "Pretrain/Step Time": 8.455779606476426} +{"Pretrain/Learning Rate": 3.578257107108494e-05, "Pretrain/Loss": 2.0443899631500244, "Pretrain/Loss (Raw)": 2.0724360942840576, "Pretrain/Step": 3598, "Pretrain/Step Time": 8.452681547030807} +{"Pretrain/Learning Rate": 3.577490999649298e-05, "Pretrain/Loss": 2.043895721435547, "Pretrain/Loss (Raw)": 2.0785820484161377, "Pretrain/Step": 3599, "Pretrain/Step Time": 8.454313619062304} +{"Pretrain/Learning Rate": 3.576724767901895e-05, "Pretrain/Loss": 2.0427870750427246, "Pretrain/Loss (Raw)": 2.034482479095459, "Pretrain/Step": 3600, "Pretrain/Step Time": 8.454213516786695} +{"Pretrain/Learning Rate": 3.575958411954668e-05, "Pretrain/Loss": 2.0423972606658936, "Pretrain/Loss (Raw)": 1.974275827407837, "Pretrain/Step": 3601, "Pretrain/Step Time": 8.454710338264704} +{"Pretrain/Learning Rate": 3.575191931896016e-05, "Pretrain/Loss": 2.040971040725708, "Pretrain/Loss (Raw)": 2.0170931816101074, "Pretrain/Step": 3602, "Pretrain/Step Time": 8.453561982139945} +{"Pretrain/Learning Rate": 3.574425327814352e-05, "Pretrain/Loss": 2.0406227111816406, "Pretrain/Loss (Raw)": 2.0770599842071533, "Pretrain/Step": 3603, "Pretrain/Step Time": 8.45755728892982} +{"Pretrain/Learning Rate": 3.573658599798105e-05, "Pretrain/Loss": 2.0397136211395264, "Pretrain/Loss (Raw)": 2.2030410766601562, "Pretrain/Step": 3604, "Pretrain/Step Time": 8.458100898191333} +{"Pretrain/Learning Rate": 3.572891747935716e-05, "Pretrain/Loss": 2.0390572547912598, "Pretrain/Loss (Raw)": 1.9904766082763672, "Pretrain/Step": 3605, "Pretrain/Step Time": 8.460411597043276} +{"Pretrain/Learning Rate": 3.572124772315639e-05, "Pretrain/Loss": 2.0391645431518555, "Pretrain/Loss (Raw)": 1.9722919464111328, "Pretrain/Step": 3606, "Pretrain/Step Time": 8.463396003469825} +{"Pretrain/Learning Rate": 3.5713576730263476e-05, "Pretrain/Loss": 2.0397047996520996, "Pretrain/Loss (Raw)": 2.1456520557403564, "Pretrain/Step": 3607, "Pretrain/Step Time": 8.46083047799766} +{"Pretrain/Learning Rate": 3.570590450156325e-05, "Pretrain/Loss": 2.0410408973693848, "Pretrain/Loss (Raw)": 2.102508306503296, "Pretrain/Step": 3608, "Pretrain/Step Time": 8.458900345489383} +{"Pretrain/Learning Rate": 3.569823103794071e-05, "Pretrain/Loss": 2.039736747741699, "Pretrain/Loss (Raw)": 1.7620242834091187, "Pretrain/Step": 3609, "Pretrain/Step Time": 8.461399922147393} +{"Pretrain/Learning Rate": 3.5690556340280965e-05, "Pretrain/Loss": 2.03829288482666, "Pretrain/Loss (Raw)": 1.9684523344039917, "Pretrain/Step": 3610, "Pretrain/Step Time": 8.45784025080502} +{"Pretrain/Learning Rate": 3.5682880409469315e-05, "Pretrain/Loss": 2.0355262756347656, "Pretrain/Loss (Raw)": 1.6868327856063843, "Pretrain/Step": 3611, "Pretrain/Step Time": 8.462798034772277} +{"Pretrain/Learning Rate": 3.567520324639116e-05, "Pretrain/Loss": 2.0368785858154297, "Pretrain/Loss (Raw)": 2.1665332317352295, "Pretrain/Step": 3612, "Pretrain/Step Time": 8.467129345983267} +{"Pretrain/Learning Rate": 3.5667524851932066e-05, "Pretrain/Loss": 2.038766384124756, "Pretrain/Loss (Raw)": 2.115083932876587, "Pretrain/Step": 3613, "Pretrain/Step Time": 8.467837862670422} +{"Pretrain/Learning Rate": 3.5659845226977715e-05, "Pretrain/Loss": 2.0376126766204834, "Pretrain/Loss (Raw)": 1.9800468683242798, "Pretrain/Step": 3614, "Pretrain/Step Time": 8.466604374349117} +{"Pretrain/Learning Rate": 3.565216437241398e-05, "Pretrain/Loss": 2.0376200675964355, "Pretrain/Loss (Raw)": 2.011902093887329, "Pretrain/Step": 3615, "Pretrain/Step Time": 8.465454427525401} +{"Pretrain/Learning Rate": 3.564448228912682e-05, "Pretrain/Loss": 2.0369386672973633, "Pretrain/Loss (Raw)": 1.9709856510162354, "Pretrain/Step": 3616, "Pretrain/Step Time": 8.46252503991127} +{"Pretrain/Learning Rate": 3.563679897800237e-05, "Pretrain/Loss": 2.0360593795776367, "Pretrain/Loss (Raw)": 1.9174306392669678, "Pretrain/Step": 3617, "Pretrain/Step Time": 8.463543651625514} +{"Pretrain/Learning Rate": 3.5629114439926896e-05, "Pretrain/Loss": 2.035545587539673, "Pretrain/Loss (Raw)": 1.999849557876587, "Pretrain/Step": 3618, "Pretrain/Step Time": 8.46690122783184} +{"Pretrain/Learning Rate": 3.5621428675786806e-05, "Pretrain/Loss": 2.034234046936035, "Pretrain/Loss (Raw)": 1.9872581958770752, "Pretrain/Step": 3619, "Pretrain/Step Time": 8.462986193597317} +{"Pretrain/Learning Rate": 3.561374168646865e-05, "Pretrain/Loss": 2.035277843475342, "Pretrain/Loss (Raw)": 2.1642906665802, "Pretrain/Step": 3620, "Pretrain/Step Time": 8.468133376911283} +{"Pretrain/Learning Rate": 3.560605347285913e-05, "Pretrain/Loss": 2.035883903503418, "Pretrain/Loss (Raw)": 2.086116313934326, "Pretrain/Step": 3621, "Pretrain/Step Time": 8.468795476481318} +{"Pretrain/Learning Rate": 3.559836403584505e-05, "Pretrain/Loss": 2.035350799560547, "Pretrain/Loss (Raw)": 2.0202152729034424, "Pretrain/Step": 3622, "Pretrain/Step Time": 8.468410378322005} +{"Pretrain/Learning Rate": 3.559067337631341e-05, "Pretrain/Loss": 2.0355489253997803, "Pretrain/Loss (Raw)": 2.0391743183135986, "Pretrain/Step": 3623, "Pretrain/Step Time": 8.470565551891923} +{"Pretrain/Learning Rate": 3.558298149515133e-05, "Pretrain/Loss": 2.0354130268096924, "Pretrain/Loss (Raw)": 1.7604949474334717, "Pretrain/Step": 3624, "Pretrain/Step Time": 8.469233443960547} +{"Pretrain/Learning Rate": 3.557528839324604e-05, "Pretrain/Loss": 2.0340466499328613, "Pretrain/Loss (Raw)": 1.9707615375518799, "Pretrain/Step": 3625, "Pretrain/Step Time": 8.468322165310383} +{"Pretrain/Learning Rate": 3.556759407148496e-05, "Pretrain/Loss": 2.0341947078704834, "Pretrain/Loss (Raw)": 1.979448914527893, "Pretrain/Step": 3626, "Pretrain/Step Time": 8.470149639993906} +{"Pretrain/Learning Rate": 3.555989853075561e-05, "Pretrain/Loss": 2.0352210998535156, "Pretrain/Loss (Raw)": 2.051487922668457, "Pretrain/Step": 3627, "Pretrain/Step Time": 8.467813715338707} +{"Pretrain/Learning Rate": 3.5552201771945676e-05, "Pretrain/Loss": 2.03529953956604, "Pretrain/Loss (Raw)": 2.134833574295044, "Pretrain/Step": 3628, "Pretrain/Step Time": 8.470160661265254} +{"Pretrain/Learning Rate": 3.554450379594298e-05, "Pretrain/Loss": 2.034803867340088, "Pretrain/Loss (Raw)": 2.0154478549957275, "Pretrain/Step": 3629, "Pretrain/Step Time": 8.47008952498436} +{"Pretrain/Learning Rate": 3.5536804603635474e-05, "Pretrain/Loss": 2.036062240600586, "Pretrain/Loss (Raw)": 2.2350847721099854, "Pretrain/Step": 3630, "Pretrain/Step Time": 8.469984035938978} +{"Pretrain/Learning Rate": 3.5529104195911256e-05, "Pretrain/Loss": 2.0364742279052734, "Pretrain/Loss (Raw)": 2.0881693363189697, "Pretrain/Step": 3631, "Pretrain/Step Time": 8.468469368293881} +{"Pretrain/Learning Rate": 3.552140257365858e-05, "Pretrain/Loss": 2.036573886871338, "Pretrain/Loss (Raw)": 1.93765389919281, "Pretrain/Step": 3632, "Pretrain/Step Time": 8.470373004674911} +{"Pretrain/Learning Rate": 3.551369973776581e-05, "Pretrain/Loss": 2.035817861557007, "Pretrain/Loss (Raw)": 1.9921190738677979, "Pretrain/Step": 3633, "Pretrain/Step Time": 8.46885109320283} +{"Pretrain/Learning Rate": 3.550599568912148e-05, "Pretrain/Loss": 2.0363080501556396, "Pretrain/Loss (Raw)": 2.113994836807251, "Pretrain/Step": 3634, "Pretrain/Step Time": 8.47024829313159} +{"Pretrain/Learning Rate": 3.5498290428614214e-05, "Pretrain/Loss": 2.0367164611816406, "Pretrain/Loss (Raw)": 1.9552080631256104, "Pretrain/Step": 3635, "Pretrain/Step Time": 8.47041499428451} +{"Pretrain/Learning Rate": 3.549058395713285e-05, "Pretrain/Loss": 2.0382018089294434, "Pretrain/Loss (Raw)": 2.223109245300293, "Pretrain/Step": 3636, "Pretrain/Step Time": 8.471694324165583} +{"Pretrain/Learning Rate": 3.548287627556632e-05, "Pretrain/Loss": 2.037466049194336, "Pretrain/Loss (Raw)": 2.0571744441986084, "Pretrain/Step": 3637, "Pretrain/Step Time": 8.472548114135861} +{"Pretrain/Learning Rate": 3.5475167384803685e-05, "Pretrain/Loss": 2.0387015342712402, "Pretrain/Loss (Raw)": 2.064338207244873, "Pretrain/Step": 3638, "Pretrain/Step Time": 8.47339577972889} +{"Pretrain/Learning Rate": 3.546745728573418e-05, "Pretrain/Loss": 2.0399184226989746, "Pretrain/Loss (Raw)": 2.0432417392730713, "Pretrain/Step": 3639, "Pretrain/Step Time": 8.47300986200571} +{"Pretrain/Learning Rate": 3.545974597924715e-05, "Pretrain/Loss": 2.040672540664673, "Pretrain/Loss (Raw)": 1.9803037643432617, "Pretrain/Step": 3640, "Pretrain/Step Time": 8.475770179182291} +{"Pretrain/Learning Rate": 3.54520334662321e-05, "Pretrain/Loss": 2.0380029678344727, "Pretrain/Loss (Raw)": 1.834417700767517, "Pretrain/Step": 3641, "Pretrain/Step Time": 8.474912863224745} +{"Pretrain/Learning Rate": 3.544431974757866e-05, "Pretrain/Loss": 2.03745174407959, "Pretrain/Loss (Raw)": 2.165895700454712, "Pretrain/Step": 3642, "Pretrain/Step Time": 8.47722310014069} +{"Pretrain/Learning Rate": 3.543660482417662e-05, "Pretrain/Loss": 2.03756046295166, "Pretrain/Loss (Raw)": 2.1244304180145264, "Pretrain/Step": 3643, "Pretrain/Step Time": 8.476770352572203} +{"Pretrain/Learning Rate": 3.542888869691586e-05, "Pretrain/Loss": 2.0375540256500244, "Pretrain/Loss (Raw)": 2.0958945751190186, "Pretrain/Step": 3644, "Pretrain/Step Time": 8.475006615743041} +{"Pretrain/Learning Rate": 3.542117136668647e-05, "Pretrain/Loss": 2.0358834266662598, "Pretrain/Loss (Raw)": 1.934341549873352, "Pretrain/Step": 3645, "Pretrain/Step Time": 8.476935727521777} +{"Pretrain/Learning Rate": 3.5413452834378625e-05, "Pretrain/Loss": 2.0374932289123535, "Pretrain/Loss (Raw)": 2.096257209777832, "Pretrain/Step": 3646, "Pretrain/Step Time": 8.477413512766361} +{"Pretrain/Learning Rate": 3.5405733100882657e-05, "Pretrain/Loss": 2.0385327339172363, "Pretrain/Loss (Raw)": 2.0952327251434326, "Pretrain/Step": 3647, "Pretrain/Step Time": 8.47215654887259} +{"Pretrain/Learning Rate": 3.5398012167089014e-05, "Pretrain/Loss": 2.0366272926330566, "Pretrain/Loss (Raw)": 1.8658603429794312, "Pretrain/Step": 3648, "Pretrain/Step Time": 8.46923272125423} +{"Pretrain/Learning Rate": 3.5390290033888336e-05, "Pretrain/Loss": 2.0408260822296143, "Pretrain/Loss (Raw)": 2.0575528144836426, "Pretrain/Step": 3649, "Pretrain/Step Time": 8.468945821747184} +{"Pretrain/Learning Rate": 3.5382566702171356e-05, "Pretrain/Loss": 2.039323329925537, "Pretrain/Loss (Raw)": 2.070254325866699, "Pretrain/Step": 3650, "Pretrain/Step Time": 8.466544101014733} +{"Pretrain/Learning Rate": 3.5374842172828955e-05, "Pretrain/Loss": 2.038670778274536, "Pretrain/Loss (Raw)": 2.0156009197235107, "Pretrain/Step": 3651, "Pretrain/Step Time": 8.466336844488978} +{"Pretrain/Learning Rate": 3.5367116446752145e-05, "Pretrain/Loss": 2.0391523838043213, "Pretrain/Loss (Raw)": 2.0308220386505127, "Pretrain/Step": 3652, "Pretrain/Step Time": 8.466106494888663} +{"Pretrain/Learning Rate": 3.535938952483211e-05, "Pretrain/Loss": 2.0403976440429688, "Pretrain/Loss (Raw)": 1.9555795192718506, "Pretrain/Step": 3653, "Pretrain/Step Time": 8.47119820304215} +{"Pretrain/Learning Rate": 3.5351661407960126e-05, "Pretrain/Loss": 2.0420615673065186, "Pretrain/Loss (Raw)": 2.1460113525390625, "Pretrain/Step": 3654, "Pretrain/Step Time": 8.468521421775222} +{"Pretrain/Learning Rate": 3.534393209702764e-05, "Pretrain/Loss": 2.0413742065429688, "Pretrain/Loss (Raw)": 2.014554738998413, "Pretrain/Step": 3655, "Pretrain/Step Time": 8.47271247021854} +{"Pretrain/Learning Rate": 3.533620159292621e-05, "Pretrain/Loss": 2.040574789047241, "Pretrain/Loss (Raw)": 2.0391786098480225, "Pretrain/Step": 3656, "Pretrain/Step Time": 8.473080236464739} +{"Pretrain/Learning Rate": 3.532846989654757e-05, "Pretrain/Loss": 2.0402612686157227, "Pretrain/Loss (Raw)": 2.1553595066070557, "Pretrain/Step": 3657, "Pretrain/Step Time": 8.472792217507958} +{"Pretrain/Learning Rate": 3.532073700878355e-05, "Pretrain/Loss": 2.0394723415374756, "Pretrain/Loss (Raw)": 1.921568512916565, "Pretrain/Step": 3658, "Pretrain/Step Time": 8.474102783948183} +{"Pretrain/Learning Rate": 3.5313002930526155e-05, "Pretrain/Loss": 2.0396738052368164, "Pretrain/Loss (Raw)": 2.106175422668457, "Pretrain/Step": 3659, "Pretrain/Step Time": 8.475698061287403} +{"Pretrain/Learning Rate": 3.5305267662667484e-05, "Pretrain/Loss": 2.0388553142547607, "Pretrain/Loss (Raw)": 2.016125440597534, "Pretrain/Step": 3660, "Pretrain/Step Time": 8.474097860977054} +{"Pretrain/Learning Rate": 3.529753120609982e-05, "Pretrain/Loss": 2.0345449447631836, "Pretrain/Loss (Raw)": 1.8189682960510254, "Pretrain/Step": 3661, "Pretrain/Step Time": 8.472752658650279} +{"Pretrain/Learning Rate": 3.528979356171555e-05, "Pretrain/Loss": 2.0350160598754883, "Pretrain/Loss (Raw)": 2.1006133556365967, "Pretrain/Step": 3662, "Pretrain/Step Time": 8.475140264257789} +{"Pretrain/Learning Rate": 3.5282054730407196e-05, "Pretrain/Loss": 2.0346124172210693, "Pretrain/Loss (Raw)": 2.0640299320220947, "Pretrain/Step": 3663, "Pretrain/Step Time": 8.473418802022934} +{"Pretrain/Learning Rate": 3.527431471306745e-05, "Pretrain/Loss": 2.0355262756347656, "Pretrain/Loss (Raw)": 2.1335623264312744, "Pretrain/Step": 3664, "Pretrain/Step Time": 8.469864567741752} +{"Pretrain/Learning Rate": 3.5266573510589114e-05, "Pretrain/Loss": 2.037787914276123, "Pretrain/Loss (Raw)": 2.0440402030944824, "Pretrain/Step": 3665, "Pretrain/Step Time": 8.472498059272766} +{"Pretrain/Learning Rate": 3.525883112386513e-05, "Pretrain/Loss": 2.0376076698303223, "Pretrain/Loss (Raw)": 1.9751074314117432, "Pretrain/Step": 3666, "Pretrain/Step Time": 8.472108470275998} +{"Pretrain/Learning Rate": 3.5251087553788586e-05, "Pretrain/Loss": 2.038384437561035, "Pretrain/Loss (Raw)": 2.0853424072265625, "Pretrain/Step": 3667, "Pretrain/Step Time": 8.46976170502603} +{"Pretrain/Learning Rate": 3.524334280125269e-05, "Pretrain/Loss": 2.037478446960449, "Pretrain/Loss (Raw)": 1.9713014364242554, "Pretrain/Step": 3668, "Pretrain/Step Time": 8.47279360704124} +{"Pretrain/Learning Rate": 3.52355968671508e-05, "Pretrain/Loss": 2.038658618927002, "Pretrain/Loss (Raw)": 2.006776809692383, "Pretrain/Step": 3669, "Pretrain/Step Time": 8.477455731481314} +{"Pretrain/Learning Rate": 3.522784975237641e-05, "Pretrain/Loss": 2.0400986671447754, "Pretrain/Loss (Raw)": 2.1953368186950684, "Pretrain/Step": 3670, "Pretrain/Step Time": 8.475165320560336} +{"Pretrain/Learning Rate": 3.5220101457823146e-05, "Pretrain/Loss": 2.0392308235168457, "Pretrain/Loss (Raw)": 2.0630412101745605, "Pretrain/Step": 3671, "Pretrain/Step Time": 8.472251251339912} +{"Pretrain/Learning Rate": 3.521235198438477e-05, "Pretrain/Loss": 2.0386195182800293, "Pretrain/Loss (Raw)": 2.0196499824523926, "Pretrain/Step": 3672, "Pretrain/Step Time": 8.473325941711664} +{"Pretrain/Learning Rate": 3.520460133295518e-05, "Pretrain/Loss": 2.037999153137207, "Pretrain/Loss (Raw)": 2.066162586212158, "Pretrain/Step": 3673, "Pretrain/Step Time": 8.473231591284275} +{"Pretrain/Learning Rate": 3.519684950442841e-05, "Pretrain/Loss": 2.039236068725586, "Pretrain/Loss (Raw)": 2.1516902446746826, "Pretrain/Step": 3674, "Pretrain/Step Time": 8.472450187429786} +{"Pretrain/Learning Rate": 3.5189096499698645e-05, "Pretrain/Loss": 2.039149045944214, "Pretrain/Loss (Raw)": 2.1638846397399902, "Pretrain/Step": 3675, "Pretrain/Step Time": 8.47481282055378} +{"Pretrain/Learning Rate": 3.518134231966017e-05, "Pretrain/Loss": 2.03745698928833, "Pretrain/Loss (Raw)": 1.9051367044448853, "Pretrain/Step": 3676, "Pretrain/Step Time": 8.472711076959968} +{"Pretrain/Learning Rate": 3.517358696520744e-05, "Pretrain/Loss": 2.035557508468628, "Pretrain/Loss (Raw)": 1.8300420045852661, "Pretrain/Step": 3677, "Pretrain/Step Time": 8.473030736669898} +{"Pretrain/Learning Rate": 3.516583043723502e-05, "Pretrain/Loss": 2.03816556930542, "Pretrain/Loss (Raw)": 2.1919989585876465, "Pretrain/Step": 3678, "Pretrain/Step Time": 8.477118151262403} +{"Pretrain/Learning Rate": 3.515807273663764e-05, "Pretrain/Loss": 2.039685010910034, "Pretrain/Loss (Raw)": 1.960082769393921, "Pretrain/Step": 3679, "Pretrain/Step Time": 8.478627651929855} +{"Pretrain/Learning Rate": 3.515031386431014e-05, "Pretrain/Loss": 2.040060520172119, "Pretrain/Loss (Raw)": 2.178286075592041, "Pretrain/Step": 3680, "Pretrain/Step Time": 8.476201191544533} +{"Pretrain/Learning Rate": 3.5142553821147494e-05, "Pretrain/Loss": 2.040182590484619, "Pretrain/Loss (Raw)": 2.0217225551605225, "Pretrain/Step": 3681, "Pretrain/Step Time": 8.475335089489818} +{"Pretrain/Learning Rate": 3.513479260804484e-05, "Pretrain/Loss": 2.0417354106903076, "Pretrain/Loss (Raw)": 2.1852478981018066, "Pretrain/Step": 3682, "Pretrain/Step Time": 8.475879343226552} +{"Pretrain/Learning Rate": 3.512703022589741e-05, "Pretrain/Loss": 2.0456647872924805, "Pretrain/Loss (Raw)": 2.1673672199249268, "Pretrain/Step": 3683, "Pretrain/Step Time": 8.470830610021949} +{"Pretrain/Learning Rate": 3.5119266675600615e-05, "Pretrain/Loss": 2.045274257659912, "Pretrain/Loss (Raw)": 2.042907238006592, "Pretrain/Step": 3684, "Pretrain/Step Time": 8.475721068680286} +{"Pretrain/Learning Rate": 3.511150195804996e-05, "Pretrain/Loss": 2.04541015625, "Pretrain/Loss (Raw)": 2.1236064434051514, "Pretrain/Step": 3685, "Pretrain/Step Time": 8.474480528384447} +{"Pretrain/Learning Rate": 3.5103736074141105e-05, "Pretrain/Loss": 2.0449154376983643, "Pretrain/Loss (Raw)": 2.093684673309326, "Pretrain/Step": 3686, "Pretrain/Step Time": 8.476755905896425} +{"Pretrain/Learning Rate": 3.5095969024769845e-05, "Pretrain/Loss": 2.0455093383789062, "Pretrain/Loss (Raw)": 2.089994192123413, "Pretrain/Step": 3687, "Pretrain/Step Time": 8.476208291947842} +{"Pretrain/Learning Rate": 3.508820081083211e-05, "Pretrain/Loss": 2.0440633296966553, "Pretrain/Loss (Raw)": 2.0579071044921875, "Pretrain/Step": 3688, "Pretrain/Step Time": 8.478388633579016} +{"Pretrain/Learning Rate": 3.508043143322395e-05, "Pretrain/Loss": 2.0437874794006348, "Pretrain/Loss (Raw)": 1.9987022876739502, "Pretrain/Step": 3689, "Pretrain/Step Time": 8.474951103329659} +{"Pretrain/Learning Rate": 3.507266089284157e-05, "Pretrain/Loss": 2.044853687286377, "Pretrain/Loss (Raw)": 2.080918312072754, "Pretrain/Step": 3690, "Pretrain/Step Time": 8.475122136995196} +{"Pretrain/Learning Rate": 3.506488919058129e-05, "Pretrain/Loss": 2.044762134552002, "Pretrain/Loss (Raw)": 2.168757200241089, "Pretrain/Step": 3691, "Pretrain/Step Time": 8.470794878900051} +{"Pretrain/Learning Rate": 3.505711632733959e-05, "Pretrain/Loss": 2.048158645629883, "Pretrain/Loss (Raw)": 2.257077217102051, "Pretrain/Step": 3692, "Pretrain/Step Time": 8.470731034874916} +{"Pretrain/Learning Rate": 3.504934230401305e-05, "Pretrain/Loss": 2.0459046363830566, "Pretrain/Loss (Raw)": 1.9851337671279907, "Pretrain/Step": 3693, "Pretrain/Step Time": 8.47269144281745} +{"Pretrain/Learning Rate": 3.504156712149841e-05, "Pretrain/Loss": 2.045273542404175, "Pretrain/Loss (Raw)": 2.0432143211364746, "Pretrain/Step": 3694, "Pretrain/Step Time": 8.473799157887697} +{"Pretrain/Learning Rate": 3.503379078069253e-05, "Pretrain/Loss": 2.0463948249816895, "Pretrain/Loss (Raw)": 2.0399997234344482, "Pretrain/Step": 3695, "Pretrain/Step Time": 8.472788982093334} +{"Pretrain/Learning Rate": 3.50260132824924e-05, "Pretrain/Loss": 2.0449228286743164, "Pretrain/Loss (Raw)": 1.9169986248016357, "Pretrain/Step": 3696, "Pretrain/Step Time": 8.470848536118865} +{"Pretrain/Learning Rate": 3.5018234627795175e-05, "Pretrain/Loss": 2.0433273315429688, "Pretrain/Loss (Raw)": 1.905243158340454, "Pretrain/Step": 3697, "Pretrain/Step Time": 8.468868773430586} +{"Pretrain/Learning Rate": 3.50104548174981e-05, "Pretrain/Loss": 2.0422511100769043, "Pretrain/Loss (Raw)": 1.9238245487213135, "Pretrain/Step": 3698, "Pretrain/Step Time": 8.470596427097917} +{"Pretrain/Learning Rate": 3.500267385249858e-05, "Pretrain/Loss": 2.0410375595092773, "Pretrain/Loss (Raw)": 2.007242202758789, "Pretrain/Step": 3699, "Pretrain/Step Time": 8.467946097254753} +{"Pretrain/Learning Rate": 3.4994891733694147e-05, "Pretrain/Loss": 2.0401411056518555, "Pretrain/Loss (Raw)": 1.9963643550872803, "Pretrain/Step": 3700, "Pretrain/Step Time": 8.469592425972223} +{"Pretrain/Learning Rate": 3.4987108461982474e-05, "Pretrain/Loss": 2.038949966430664, "Pretrain/Loss (Raw)": 1.9010086059570312, "Pretrain/Step": 3701, "Pretrain/Step Time": 8.469957537949085} +{"Pretrain/Learning Rate": 3.497932403826133e-05, "Pretrain/Loss": 2.0403714179992676, "Pretrain/Loss (Raw)": 2.111240863800049, "Pretrain/Step": 3702, "Pretrain/Step Time": 8.472743652760983} +{"Pretrain/Learning Rate": 3.497153846342868e-05, "Pretrain/Loss": 2.0419135093688965, "Pretrain/Loss (Raw)": 2.3455071449279785, "Pretrain/Step": 3703, "Pretrain/Step Time": 8.469980271533132} +{"Pretrain/Learning Rate": 3.4963751738382566e-05, "Pretrain/Loss": 2.0428543090820312, "Pretrain/Loss (Raw)": 2.0972626209259033, "Pretrain/Step": 3704, "Pretrain/Step Time": 8.471881777048111} +{"Pretrain/Learning Rate": 3.49559638640212e-05, "Pretrain/Loss": 2.044896125793457, "Pretrain/Loss (Raw)": 2.1867048740386963, "Pretrain/Step": 3705, "Pretrain/Step Time": 8.473355278372765} +{"Pretrain/Learning Rate": 3.494817484124289e-05, "Pretrain/Loss": 2.0464489459991455, "Pretrain/Loss (Raw)": 2.0319583415985107, "Pretrain/Step": 3706, "Pretrain/Step Time": 8.475507782772183} +{"Pretrain/Learning Rate": 3.4940384670946105e-05, "Pretrain/Loss": 2.0471267700195312, "Pretrain/Loss (Raw)": 1.9420461654663086, "Pretrain/Step": 3707, "Pretrain/Step Time": 8.477773426100612} +{"Pretrain/Learning Rate": 3.4932593354029454e-05, "Pretrain/Loss": 2.0467705726623535, "Pretrain/Loss (Raw)": 2.0441572666168213, "Pretrain/Step": 3708, "Pretrain/Step Time": 8.47356104105711} +{"Pretrain/Learning Rate": 3.4924800891391644e-05, "Pretrain/Loss": 2.047006130218506, "Pretrain/Loss (Raw)": 2.003364324569702, "Pretrain/Step": 3709, "Pretrain/Step Time": 8.475879438221455} +{"Pretrain/Learning Rate": 3.491700728393154e-05, "Pretrain/Loss": 2.0480377674102783, "Pretrain/Loss (Raw)": 2.103600263595581, "Pretrain/Step": 3710, "Pretrain/Step Time": 8.476078554987907} +{"Pretrain/Learning Rate": 3.490921253254813e-05, "Pretrain/Loss": 2.0485119819641113, "Pretrain/Loss (Raw)": 2.0860025882720947, "Pretrain/Step": 3711, "Pretrain/Step Time": 8.474429056048393} +{"Pretrain/Learning Rate": 3.4901416638140536e-05, "Pretrain/Loss": 2.045952796936035, "Pretrain/Loss (Raw)": 1.7188973426818848, "Pretrain/Step": 3712, "Pretrain/Step Time": 8.475319040939212} +{"Pretrain/Learning Rate": 3.4893619601608017e-05, "Pretrain/Loss": 2.046380043029785, "Pretrain/Loss (Raw)": 2.1237668991088867, "Pretrain/Step": 3713, "Pretrain/Step Time": 8.47017078474164} +{"Pretrain/Learning Rate": 3.488582142384995e-05, "Pretrain/Loss": 2.0422592163085938, "Pretrain/Loss (Raw)": 1.8123955726623535, "Pretrain/Step": 3714, "Pretrain/Step Time": 8.464419869706035} +{"Pretrain/Learning Rate": 3.4878022105765854e-05, "Pretrain/Loss": 2.0405960083007812, "Pretrain/Loss (Raw)": 1.9030221700668335, "Pretrain/Step": 3715, "Pretrain/Step Time": 8.466356713324785} +{"Pretrain/Learning Rate": 3.487022164825538e-05, "Pretrain/Loss": 2.0404367446899414, "Pretrain/Loss (Raw)": 2.0673248767852783, "Pretrain/Step": 3716, "Pretrain/Step Time": 8.46735717356205} +{"Pretrain/Learning Rate": 3.4862420052218316e-05, "Pretrain/Loss": 2.0389797687530518, "Pretrain/Loss (Raw)": 1.9526939392089844, "Pretrain/Step": 3717, "Pretrain/Step Time": 8.465948743745685} +{"Pretrain/Learning Rate": 3.485461731855456e-05, "Pretrain/Loss": 2.0377073287963867, "Pretrain/Loss (Raw)": 1.8892186880111694, "Pretrain/Step": 3718, "Pretrain/Step Time": 8.465782571583986} +{"Pretrain/Learning Rate": 3.484681344816416e-05, "Pretrain/Loss": 2.037583351135254, "Pretrain/Loss (Raw)": 2.086308717727661, "Pretrain/Step": 3719, "Pretrain/Step Time": 8.464103017002344} +{"Pretrain/Learning Rate": 3.483900844194728e-05, "Pretrain/Loss": 2.0375356674194336, "Pretrain/Loss (Raw)": 2.0667877197265625, "Pretrain/Step": 3720, "Pretrain/Step Time": 8.461468594148755} +{"Pretrain/Learning Rate": 3.483120230080425e-05, "Pretrain/Loss": 2.0358242988586426, "Pretrain/Loss (Raw)": 1.9035700559616089, "Pretrain/Step": 3721, "Pretrain/Step Time": 8.463383678346872} +{"Pretrain/Learning Rate": 3.482339502563547e-05, "Pretrain/Loss": 2.036914825439453, "Pretrain/Loss (Raw)": 2.136647939682007, "Pretrain/Step": 3722, "Pretrain/Step Time": 8.464883396402001} +{"Pretrain/Learning Rate": 3.481558661734153e-05, "Pretrain/Loss": 2.037142038345337, "Pretrain/Loss (Raw)": 2.150658130645752, "Pretrain/Step": 3723, "Pretrain/Step Time": 8.46266102232039} +{"Pretrain/Learning Rate": 3.4807777076823137e-05, "Pretrain/Loss": 2.0355288982391357, "Pretrain/Loss (Raw)": 1.9113858938217163, "Pretrain/Step": 3724, "Pretrain/Step Time": 8.4653006978333} +{"Pretrain/Learning Rate": 3.4799966404981095e-05, "Pretrain/Loss": 2.0351579189300537, "Pretrain/Loss (Raw)": 2.005622148513794, "Pretrain/Step": 3725, "Pretrain/Step Time": 8.465052165091038} +{"Pretrain/Learning Rate": 3.479215460271637e-05, "Pretrain/Loss": 2.035781145095825, "Pretrain/Loss (Raw)": 2.152215003967285, "Pretrain/Step": 3726, "Pretrain/Step Time": 8.463580245152116} +{"Pretrain/Learning Rate": 3.4784341670930065e-05, "Pretrain/Loss": 2.0363006591796875, "Pretrain/Loss (Raw)": 2.1450674533843994, "Pretrain/Step": 3727, "Pretrain/Step Time": 8.460542745888233} +{"Pretrain/Learning Rate": 3.477652761052338e-05, "Pretrain/Loss": 2.036283493041992, "Pretrain/Loss (Raw)": 2.0323100090026855, "Pretrain/Step": 3728, "Pretrain/Step Time": 8.45812120847404} +{"Pretrain/Learning Rate": 3.476871242239767e-05, "Pretrain/Loss": 2.0373971462249756, "Pretrain/Loss (Raw)": 2.1168155670166016, "Pretrain/Step": 3729, "Pretrain/Step Time": 8.457353796809912} +{"Pretrain/Learning Rate": 3.4760896107454414e-05, "Pretrain/Loss": 2.039005756378174, "Pretrain/Loss (Raw)": 2.2230091094970703, "Pretrain/Step": 3730, "Pretrain/Step Time": 8.458166612312198} +{"Pretrain/Learning Rate": 3.4753078666595215e-05, "Pretrain/Loss": 2.0395658016204834, "Pretrain/Loss (Raw)": 2.1487226486206055, "Pretrain/Step": 3731, "Pretrain/Step Time": 8.451410382986069} +{"Pretrain/Learning Rate": 3.474526010072183e-05, "Pretrain/Loss": 2.037947416305542, "Pretrain/Loss (Raw)": 1.9958959817886353, "Pretrain/Step": 3732, "Pretrain/Step Time": 8.45827479660511} +{"Pretrain/Learning Rate": 3.473744041073611e-05, "Pretrain/Loss": 2.039520740509033, "Pretrain/Loss (Raw)": 2.1918740272521973, "Pretrain/Step": 3733, "Pretrain/Step Time": 8.455501416698098} +{"Pretrain/Learning Rate": 3.472961959754007e-05, "Pretrain/Loss": 2.040006160736084, "Pretrain/Loss (Raw)": 2.034417152404785, "Pretrain/Step": 3734, "Pretrain/Step Time": 8.455837925896049} +{"Pretrain/Learning Rate": 3.4721797662035824e-05, "Pretrain/Loss": 2.0382304191589355, "Pretrain/Loss (Raw)": 1.9183613061904907, "Pretrain/Step": 3735, "Pretrain/Step Time": 8.454385651275516} +{"Pretrain/Learning Rate": 3.471397460512563e-05, "Pretrain/Loss": 2.0368387699127197, "Pretrain/Loss (Raw)": 1.924378752708435, "Pretrain/Step": 3736, "Pretrain/Step Time": 8.453091656789184} +{"Pretrain/Learning Rate": 3.4706150427711895e-05, "Pretrain/Loss": 2.0389151573181152, "Pretrain/Loss (Raw)": 2.02781343460083, "Pretrain/Step": 3737, "Pretrain/Step Time": 8.453369695693254} +{"Pretrain/Learning Rate": 3.4698325130697104e-05, "Pretrain/Loss": 2.0404114723205566, "Pretrain/Loss (Raw)": 2.1599507331848145, "Pretrain/Step": 3738, "Pretrain/Step Time": 8.455950850620866} +{"Pretrain/Learning Rate": 3.469049871498392e-05, "Pretrain/Loss": 2.042938709259033, "Pretrain/Loss (Raw)": 2.010319232940674, "Pretrain/Step": 3739, "Pretrain/Step Time": 8.451290668919683} +{"Pretrain/Learning Rate": 3.4682671181475115e-05, "Pretrain/Loss": 2.0415406227111816, "Pretrain/Loss (Raw)": 1.9875915050506592, "Pretrain/Step": 3740, "Pretrain/Step Time": 8.448721123859286} +{"Pretrain/Learning Rate": 3.467484253107359e-05, "Pretrain/Loss": 2.041350841522217, "Pretrain/Loss (Raw)": 2.090775728225708, "Pretrain/Step": 3741, "Pretrain/Step Time": 8.452650494873524} +{"Pretrain/Learning Rate": 3.466701276468238e-05, "Pretrain/Loss": 2.0416059494018555, "Pretrain/Loss (Raw)": 2.0127296447753906, "Pretrain/Step": 3742, "Pretrain/Step Time": 8.458027891814709} +{"Pretrain/Learning Rate": 3.465918188320465e-05, "Pretrain/Loss": 2.0409655570983887, "Pretrain/Loss (Raw)": 1.9299249649047852, "Pretrain/Step": 3743, "Pretrain/Step Time": 8.456364132463932} +{"Pretrain/Learning Rate": 3.465134988754368e-05, "Pretrain/Loss": 2.0416946411132812, "Pretrain/Loss (Raw)": 2.064303398132324, "Pretrain/Step": 3744, "Pretrain/Step Time": 8.454850999638438} +{"Pretrain/Learning Rate": 3.464351677860289e-05, "Pretrain/Loss": 2.0430235862731934, "Pretrain/Loss (Raw)": 2.087526321411133, "Pretrain/Step": 3745, "Pretrain/Step Time": 8.45670753531158} +{"Pretrain/Learning Rate": 3.4635682557285834e-05, "Pretrain/Loss": 2.0451436042785645, "Pretrain/Loss (Raw)": 2.2712295055389404, "Pretrain/Step": 3746, "Pretrain/Step Time": 8.458135919645429} +{"Pretrain/Learning Rate": 3.462784722449617e-05, "Pretrain/Loss": 2.0451722145080566, "Pretrain/Loss (Raw)": 1.990906000137329, "Pretrain/Step": 3747, "Pretrain/Step Time": 8.460339266806841} +{"Pretrain/Learning Rate": 3.4620010781137726e-05, "Pretrain/Loss": 2.0438148975372314, "Pretrain/Loss (Raw)": 1.990549921989441, "Pretrain/Step": 3748, "Pretrain/Step Time": 8.45767073519528} +{"Pretrain/Learning Rate": 3.461217322811441e-05, "Pretrain/Loss": 2.0432586669921875, "Pretrain/Loss (Raw)": 2.014949083328247, "Pretrain/Step": 3749, "Pretrain/Step Time": 8.455517133697867} +{"Pretrain/Learning Rate": 3.460433456633029e-05, "Pretrain/Loss": 2.0428104400634766, "Pretrain/Loss (Raw)": 1.962827444076538, "Pretrain/Step": 3750, "Pretrain/Step Time": 8.45963355526328} +{"Pretrain/Learning Rate": 3.459649479668956e-05, "Pretrain/Loss": 2.0416958332061768, "Pretrain/Loss (Raw)": 1.8965044021606445, "Pretrain/Step": 3751, "Pretrain/Step Time": 8.458441216498613} +{"Pretrain/Learning Rate": 3.4588653920096526e-05, "Pretrain/Loss": 2.0443882942199707, "Pretrain/Loss (Raw)": 2.1051089763641357, "Pretrain/Step": 3752, "Pretrain/Step Time": 8.457729635760188} +{"Pretrain/Learning Rate": 3.4580811937455635e-05, "Pretrain/Loss": 2.044302225112915, "Pretrain/Loss (Raw)": 1.9597569704055786, "Pretrain/Step": 3753, "Pretrain/Step Time": 8.457945197820663} +{"Pretrain/Learning Rate": 3.457296884967144e-05, "Pretrain/Loss": 2.043959856033325, "Pretrain/Loss (Raw)": 1.9356203079223633, "Pretrain/Step": 3754, "Pretrain/Step Time": 8.457790113985538} +{"Pretrain/Learning Rate": 3.456512465764867e-05, "Pretrain/Loss": 2.0439095497131348, "Pretrain/Loss (Raw)": 2.0450384616851807, "Pretrain/Step": 3755, "Pretrain/Step Time": 8.459617547690868} +{"Pretrain/Learning Rate": 3.455727936229212e-05, "Pretrain/Loss": 2.042644500732422, "Pretrain/Loss (Raw)": 1.9729050397872925, "Pretrain/Step": 3756, "Pretrain/Step Time": 8.454521143808961} +{"Pretrain/Learning Rate": 3.454943296450675e-05, "Pretrain/Loss": 2.043431043624878, "Pretrain/Loss (Raw)": 2.116140127182007, "Pretrain/Step": 3757, "Pretrain/Step Time": 8.457252284511924} +{"Pretrain/Learning Rate": 3.454158546519766e-05, "Pretrain/Loss": 2.038909435272217, "Pretrain/Loss (Raw)": 1.6563383340835571, "Pretrain/Step": 3758, "Pretrain/Step Time": 8.456803588196635} +{"Pretrain/Learning Rate": 3.453373686527003e-05, "Pretrain/Loss": 2.0390286445617676, "Pretrain/Loss (Raw)": 2.1034231185913086, "Pretrain/Step": 3759, "Pretrain/Step Time": 8.455243265256286} +{"Pretrain/Learning Rate": 3.45258871656292e-05, "Pretrain/Loss": 2.0391182899475098, "Pretrain/Loss (Raw)": 1.9491002559661865, "Pretrain/Step": 3760, "Pretrain/Step Time": 8.454410856589675} +{"Pretrain/Learning Rate": 3.451803636718064e-05, "Pretrain/Loss": 2.0399858951568604, "Pretrain/Loss (Raw)": 2.1031713485717773, "Pretrain/Step": 3761, "Pretrain/Step Time": 8.455959901213646} +{"Pretrain/Learning Rate": 3.451018447082993e-05, "Pretrain/Loss": 2.0394299030303955, "Pretrain/Loss (Raw)": 2.042844772338867, "Pretrain/Step": 3762, "Pretrain/Step Time": 8.45213065110147} +{"Pretrain/Learning Rate": 3.450233147748278e-05, "Pretrain/Loss": 2.039396286010742, "Pretrain/Loss (Raw)": 1.9508776664733887, "Pretrain/Step": 3763, "Pretrain/Step Time": 8.456427624449134} +{"Pretrain/Learning Rate": 3.4494477388045035e-05, "Pretrain/Loss": 2.0377891063690186, "Pretrain/Loss (Raw)": 2.017404317855835, "Pretrain/Step": 3764, "Pretrain/Step Time": 8.454355796799064} +{"Pretrain/Learning Rate": 3.448662220342265e-05, "Pretrain/Loss": 2.039125442504883, "Pretrain/Loss (Raw)": 2.228257179260254, "Pretrain/Step": 3765, "Pretrain/Step Time": 8.453786076977849} +{"Pretrain/Learning Rate": 3.447876592452174e-05, "Pretrain/Loss": 2.0395002365112305, "Pretrain/Loss (Raw)": 2.1122970581054688, "Pretrain/Step": 3766, "Pretrain/Step Time": 8.453120624646544} +{"Pretrain/Learning Rate": 3.4470908552248504e-05, "Pretrain/Loss": 2.039411783218384, "Pretrain/Loss (Raw)": 2.031916618347168, "Pretrain/Step": 3767, "Pretrain/Step Time": 8.453320944681764} +{"Pretrain/Learning Rate": 3.44630500875093e-05, "Pretrain/Loss": 2.040131092071533, "Pretrain/Loss (Raw)": 2.0723917484283447, "Pretrain/Step": 3768, "Pretrain/Step Time": 8.45278649777174} +{"Pretrain/Learning Rate": 3.4455190531210595e-05, "Pretrain/Loss": 2.042029857635498, "Pretrain/Loss (Raw)": 2.077414035797119, "Pretrain/Step": 3769, "Pretrain/Step Time": 8.455198157578707} +{"Pretrain/Learning Rate": 3.4447329884258985e-05, "Pretrain/Loss": 2.0412540435791016, "Pretrain/Loss (Raw)": 2.0666089057922363, "Pretrain/Step": 3770, "Pretrain/Step Time": 8.457344526425004} +{"Pretrain/Learning Rate": 3.44394681475612e-05, "Pretrain/Loss": 2.040950298309326, "Pretrain/Loss (Raw)": 2.08557391166687, "Pretrain/Step": 3771, "Pretrain/Step Time": 8.455505132675171} +{"Pretrain/Learning Rate": 3.443160532202406e-05, "Pretrain/Loss": 2.041184663772583, "Pretrain/Loss (Raw)": 2.125885248184204, "Pretrain/Step": 3772, "Pretrain/Step Time": 8.455295085906982} +{"Pretrain/Learning Rate": 3.442374140855457e-05, "Pretrain/Loss": 2.0435400009155273, "Pretrain/Loss (Raw)": 2.235793352127075, "Pretrain/Step": 3773, "Pretrain/Step Time": 8.457811804488301} +{"Pretrain/Learning Rate": 3.441587640805983e-05, "Pretrain/Loss": 2.042293071746826, "Pretrain/Loss (Raw)": 1.9366871118545532, "Pretrain/Step": 3774, "Pretrain/Step Time": 8.457392422482371} +{"Pretrain/Learning Rate": 3.4408010321447046e-05, "Pretrain/Loss": 2.0411124229431152, "Pretrain/Loss (Raw)": 1.9440727233886719, "Pretrain/Step": 3775, "Pretrain/Step Time": 8.459236729890108} +{"Pretrain/Learning Rate": 3.440014314962357e-05, "Pretrain/Loss": 2.0411510467529297, "Pretrain/Loss (Raw)": 1.8708245754241943, "Pretrain/Step": 3776, "Pretrain/Step Time": 8.463308546692133} +{"Pretrain/Learning Rate": 3.439227489349691e-05, "Pretrain/Loss": 2.0412659645080566, "Pretrain/Loss (Raw)": 2.072260618209839, "Pretrain/Step": 3777, "Pretrain/Step Time": 8.462219355627894} +{"Pretrain/Learning Rate": 3.438440555397462e-05, "Pretrain/Loss": 2.042009115219116, "Pretrain/Loss (Raw)": 2.1653788089752197, "Pretrain/Step": 3778, "Pretrain/Step Time": 8.463723225519061} +{"Pretrain/Learning Rate": 3.437653513196446e-05, "Pretrain/Loss": 2.0420351028442383, "Pretrain/Loss (Raw)": 2.0189239978790283, "Pretrain/Step": 3779, "Pretrain/Step Time": 8.46359284594655} +{"Pretrain/Learning Rate": 3.436866362837425e-05, "Pretrain/Loss": 2.0421793460845947, "Pretrain/Loss (Raw)": 2.0492968559265137, "Pretrain/Step": 3780, "Pretrain/Step Time": 8.463470745831728} +{"Pretrain/Learning Rate": 3.436079104411199e-05, "Pretrain/Loss": 2.041886568069458, "Pretrain/Loss (Raw)": 1.9180951118469238, "Pretrain/Step": 3781, "Pretrain/Step Time": 8.457308305427432} +{"Pretrain/Learning Rate": 3.435291738008579e-05, "Pretrain/Loss": 2.0420994758605957, "Pretrain/Loss (Raw)": 2.1732537746429443, "Pretrain/Step": 3782, "Pretrain/Step Time": 8.460174411535263} +{"Pretrain/Learning Rate": 3.434504263720384e-05, "Pretrain/Loss": 2.042591094970703, "Pretrain/Loss (Raw)": 2.077505111694336, "Pretrain/Step": 3783, "Pretrain/Step Time": 8.459937719628215} +{"Pretrain/Learning Rate": 3.433716681637451e-05, "Pretrain/Loss": 2.040905237197876, "Pretrain/Loss (Raw)": 1.8233789205551147, "Pretrain/Step": 3784, "Pretrain/Step Time": 8.460231695324183} +{"Pretrain/Learning Rate": 3.432928991850627e-05, "Pretrain/Loss": 2.0410804748535156, "Pretrain/Loss (Raw)": 2.1777796745300293, "Pretrain/Step": 3785, "Pretrain/Step Time": 8.460124123841524} +{"Pretrain/Learning Rate": 3.432141194450772e-05, "Pretrain/Loss": 2.0414931774139404, "Pretrain/Loss (Raw)": 1.9744013547897339, "Pretrain/Step": 3786, "Pretrain/Step Time": 8.456506723538041} +{"Pretrain/Learning Rate": 3.431353289528758e-05, "Pretrain/Loss": 2.0401453971862793, "Pretrain/Loss (Raw)": 1.9336740970611572, "Pretrain/Step": 3787, "Pretrain/Step Time": 8.45747616700828} +{"Pretrain/Learning Rate": 3.4305652771754684e-05, "Pretrain/Loss": 2.0407397747039795, "Pretrain/Loss (Raw)": 2.0922181606292725, "Pretrain/Step": 3788, "Pretrain/Step Time": 8.458561653271317} +{"Pretrain/Learning Rate": 3.429777157481801e-05, "Pretrain/Loss": 2.0427308082580566, "Pretrain/Loss (Raw)": 2.0738039016723633, "Pretrain/Step": 3789, "Pretrain/Step Time": 8.460019025951624} +{"Pretrain/Learning Rate": 3.428988930538666e-05, "Pretrain/Loss": 2.042447566986084, "Pretrain/Loss (Raw)": 2.0643272399902344, "Pretrain/Step": 3790, "Pretrain/Step Time": 8.458159001544118} +{"Pretrain/Learning Rate": 3.4282005964369835e-05, "Pretrain/Loss": 2.042051315307617, "Pretrain/Loss (Raw)": 2.013349771499634, "Pretrain/Step": 3791, "Pretrain/Step Time": 8.456256095319986} +{"Pretrain/Learning Rate": 3.4274121552676884e-05, "Pretrain/Loss": 2.0418925285339355, "Pretrain/Loss (Raw)": 2.1132214069366455, "Pretrain/Step": 3792, "Pretrain/Step Time": 8.456233162432909} +{"Pretrain/Learning Rate": 3.426623607121728e-05, "Pretrain/Loss": 2.0412797927856445, "Pretrain/Loss (Raw)": 1.9656246900558472, "Pretrain/Step": 3793, "Pretrain/Step Time": 8.453672723844647} +{"Pretrain/Learning Rate": 3.4258349520900595e-05, "Pretrain/Loss": 2.042634963989258, "Pretrain/Loss (Raw)": 2.148556709289551, "Pretrain/Step": 3794, "Pretrain/Step Time": 8.454518614336848} +{"Pretrain/Learning Rate": 3.4250461902636554e-05, "Pretrain/Loss": 2.042668342590332, "Pretrain/Loss (Raw)": 2.089606285095215, "Pretrain/Step": 3795, "Pretrain/Step Time": 8.454236885532737} +{"Pretrain/Learning Rate": 3.4242573217334976e-05, "Pretrain/Loss": 2.0420875549316406, "Pretrain/Loss (Raw)": 1.8969874382019043, "Pretrain/Step": 3796, "Pretrain/Step Time": 8.45160337537527} +{"Pretrain/Learning Rate": 3.423468346590583e-05, "Pretrain/Loss": 2.0416083335876465, "Pretrain/Loss (Raw)": 1.945418357849121, "Pretrain/Step": 3797, "Pretrain/Step Time": 8.448039459064603} +{"Pretrain/Learning Rate": 3.4226792649259184e-05, "Pretrain/Loss": 2.0397632122039795, "Pretrain/Loss (Raw)": 1.959164023399353, "Pretrain/Step": 3798, "Pretrain/Step Time": 8.450208682566881} +{"Pretrain/Learning Rate": 3.421890076830525e-05, "Pretrain/Loss": 2.040050983428955, "Pretrain/Loss (Raw)": 2.0998997688293457, "Pretrain/Step": 3799, "Pretrain/Step Time": 8.451834572479129} +{"Pretrain/Learning Rate": 3.421100782395436e-05, "Pretrain/Loss": 2.0393357276916504, "Pretrain/Loss (Raw)": 1.9280529022216797, "Pretrain/Step": 3800, "Pretrain/Step Time": 8.451766530051827} +{"Pretrain/Learning Rate": 3.4203113817116957e-05, "Pretrain/Loss": 2.0391929149627686, "Pretrain/Loss (Raw)": 2.047917366027832, "Pretrain/Step": 3801, "Pretrain/Step Time": 8.453486232087016} +{"Pretrain/Learning Rate": 3.419521874870359e-05, "Pretrain/Loss": 2.037970542907715, "Pretrain/Loss (Raw)": 1.9952294826507568, "Pretrain/Step": 3802, "Pretrain/Step Time": 8.453069549053907} +{"Pretrain/Learning Rate": 3.4187322619624995e-05, "Pretrain/Loss": 2.0375852584838867, "Pretrain/Loss (Raw)": 2.1145553588867188, "Pretrain/Step": 3803, "Pretrain/Step Time": 8.451447453349829} +{"Pretrain/Learning Rate": 3.417942543079195e-05, "Pretrain/Loss": 2.0386996269226074, "Pretrain/Loss (Raw)": 2.04779314994812, "Pretrain/Step": 3804, "Pretrain/Step Time": 8.453435840085149} +{"Pretrain/Learning Rate": 3.4171527183115415e-05, "Pretrain/Loss": 2.0415682792663574, "Pretrain/Loss (Raw)": 2.197218179702759, "Pretrain/Step": 3805, "Pretrain/Step Time": 8.452981144189835} +{"Pretrain/Learning Rate": 3.4163627877506435e-05, "Pretrain/Loss": 2.0409836769104004, "Pretrain/Loss (Raw)": 2.1171505451202393, "Pretrain/Step": 3806, "Pretrain/Step Time": 8.447871947661042} +{"Pretrain/Learning Rate": 3.41557275148762e-05, "Pretrain/Loss": 2.042046070098877, "Pretrain/Loss (Raw)": 2.096076726913452, "Pretrain/Step": 3807, "Pretrain/Step Time": 8.450743176043034} +{"Pretrain/Learning Rate": 3.414782609613602e-05, "Pretrain/Loss": 2.041609287261963, "Pretrain/Loss (Raw)": 2.1223700046539307, "Pretrain/Step": 3808, "Pretrain/Step Time": 8.449771329760551} +{"Pretrain/Learning Rate": 3.413992362219731e-05, "Pretrain/Loss": 2.0400776863098145, "Pretrain/Loss (Raw)": 1.8256988525390625, "Pretrain/Step": 3809, "Pretrain/Step Time": 8.451272690668702} +{"Pretrain/Learning Rate": 3.413202009397163e-05, "Pretrain/Loss": 2.0386834144592285, "Pretrain/Loss (Raw)": 2.006758451461792, "Pretrain/Step": 3810, "Pretrain/Step Time": 8.45692907832563} +{"Pretrain/Learning Rate": 3.412411551237064e-05, "Pretrain/Loss": 2.0372140407562256, "Pretrain/Loss (Raw)": 1.9792996644973755, "Pretrain/Step": 3811, "Pretrain/Step Time": 8.45718339458108} +{"Pretrain/Learning Rate": 3.411620987830612e-05, "Pretrain/Loss": 2.0377197265625, "Pretrain/Loss (Raw)": 2.1076245307922363, "Pretrain/Step": 3812, "Pretrain/Step Time": 8.451861903071404} +{"Pretrain/Learning Rate": 3.410830319269e-05, "Pretrain/Loss": 2.0371203422546387, "Pretrain/Loss (Raw)": 2.046884536743164, "Pretrain/Step": 3813, "Pretrain/Step Time": 8.451436733826995} +{"Pretrain/Learning Rate": 3.410039545643431e-05, "Pretrain/Loss": 2.0375709533691406, "Pretrain/Loss (Raw)": 2.151392936706543, "Pretrain/Step": 3814, "Pretrain/Step Time": 8.450455091893673} +{"Pretrain/Learning Rate": 3.40924866704512e-05, "Pretrain/Loss": 2.037752628326416, "Pretrain/Loss (Raw)": 2.1132287979125977, "Pretrain/Step": 3815, "Pretrain/Step Time": 8.44967701099813} +{"Pretrain/Learning Rate": 3.408457683565295e-05, "Pretrain/Loss": 2.038024425506592, "Pretrain/Loss (Raw)": 2.092719078063965, "Pretrain/Step": 3816, "Pretrain/Step Time": 8.44777631573379} +{"Pretrain/Learning Rate": 3.407666595295195e-05, "Pretrain/Loss": 2.0401957035064697, "Pretrain/Loss (Raw)": 2.2766036987304688, "Pretrain/Step": 3817, "Pretrain/Step Time": 8.453504275530577} +{"Pretrain/Learning Rate": 3.4068754023260726e-05, "Pretrain/Loss": 2.0379512310028076, "Pretrain/Loss (Raw)": 1.7936232089996338, "Pretrain/Step": 3818, "Pretrain/Step Time": 8.45191346667707} +{"Pretrain/Learning Rate": 3.406084104749192e-05, "Pretrain/Loss": 2.0353188514709473, "Pretrain/Loss (Raw)": 1.8318367004394531, "Pretrain/Step": 3819, "Pretrain/Step Time": 8.451907286420465} +{"Pretrain/Learning Rate": 3.4052927026558265e-05, "Pretrain/Loss": 2.032688856124878, "Pretrain/Loss (Raw)": 1.9204298257827759, "Pretrain/Step": 3820, "Pretrain/Step Time": 8.456267258152366} +{"Pretrain/Learning Rate": 3.404501196137267e-05, "Pretrain/Loss": 2.03361177444458, "Pretrain/Loss (Raw)": 2.103257417678833, "Pretrain/Step": 3821, "Pretrain/Step Time": 8.454114001244307} +{"Pretrain/Learning Rate": 3.4037095852848126e-05, "Pretrain/Loss": 2.0331871509552, "Pretrain/Loss (Raw)": 1.9888734817504883, "Pretrain/Step": 3822, "Pretrain/Step Time": 8.453643836081028} +{"Pretrain/Learning Rate": 3.4029178701897744e-05, "Pretrain/Loss": 2.0349786281585693, "Pretrain/Loss (Raw)": 2.2692856788635254, "Pretrain/Step": 3823, "Pretrain/Step Time": 8.45279579795897} +{"Pretrain/Learning Rate": 3.402126050943478e-05, "Pretrain/Loss": 2.035828113555908, "Pretrain/Loss (Raw)": 2.025737762451172, "Pretrain/Step": 3824, "Pretrain/Step Time": 8.454464001581073} +{"Pretrain/Learning Rate": 3.401334127637259e-05, "Pretrain/Loss": 2.0345675945281982, "Pretrain/Loss (Raw)": 1.7438985109329224, "Pretrain/Step": 3825, "Pretrain/Step Time": 8.45586421340704} +{"Pretrain/Learning Rate": 3.400542100362464e-05, "Pretrain/Loss": 2.035346746444702, "Pretrain/Loss (Raw)": 2.023554801940918, "Pretrain/Step": 3826, "Pretrain/Step Time": 8.456097831949592} +{"Pretrain/Learning Rate": 3.399749969210455e-05, "Pretrain/Loss": 2.0363805294036865, "Pretrain/Loss (Raw)": 2.1395838260650635, "Pretrain/Step": 3827, "Pretrain/Step Time": 8.45572235994041} +{"Pretrain/Learning Rate": 3.3989577342726025e-05, "Pretrain/Loss": 2.0370140075683594, "Pretrain/Loss (Raw)": 2.0774576663970947, "Pretrain/Step": 3828, "Pretrain/Step Time": 8.456952147185802} +{"Pretrain/Learning Rate": 3.398165395640292e-05, "Pretrain/Loss": 2.0383212566375732, "Pretrain/Loss (Raw)": 2.068328619003296, "Pretrain/Step": 3829, "Pretrain/Step Time": 8.455149780958891} +{"Pretrain/Learning Rate": 3.397372953404918e-05, "Pretrain/Loss": 2.037956953048706, "Pretrain/Loss (Raw)": 2.064594030380249, "Pretrain/Step": 3830, "Pretrain/Step Time": 8.45133781991899} +{"Pretrain/Learning Rate": 3.39658040765789e-05, "Pretrain/Loss": 2.0355119705200195, "Pretrain/Loss (Raw)": 2.0325682163238525, "Pretrain/Step": 3831, "Pretrain/Step Time": 8.454818107187748} +{"Pretrain/Learning Rate": 3.395787758490626e-05, "Pretrain/Loss": 2.034583806991577, "Pretrain/Loss (Raw)": 1.9784538745880127, "Pretrain/Step": 3832, "Pretrain/Step Time": 8.454072350636125} +{"Pretrain/Learning Rate": 3.3949950059945594e-05, "Pretrain/Loss": 2.034010171890259, "Pretrain/Loss (Raw)": 2.113248825073242, "Pretrain/Step": 3833, "Pretrain/Step Time": 8.456172505393624} +{"Pretrain/Learning Rate": 3.394202150261134e-05, "Pretrain/Loss": 2.0349724292755127, "Pretrain/Loss (Raw)": 2.155118703842163, "Pretrain/Step": 3834, "Pretrain/Step Time": 8.456999119371176} +{"Pretrain/Learning Rate": 3.3934091913818046e-05, "Pretrain/Loss": 2.0351386070251465, "Pretrain/Loss (Raw)": 1.9633313417434692, "Pretrain/Step": 3835, "Pretrain/Step Time": 8.45231617987156} +{"Pretrain/Learning Rate": 3.392616129448038e-05, "Pretrain/Loss": 2.035848617553711, "Pretrain/Loss (Raw)": 2.1350417137145996, "Pretrain/Step": 3836, "Pretrain/Step Time": 8.454598193988204} +{"Pretrain/Learning Rate": 3.391822964551315e-05, "Pretrain/Loss": 2.035398006439209, "Pretrain/Loss (Raw)": 1.9456942081451416, "Pretrain/Step": 3837, "Pretrain/Step Time": 8.454650115221739} +{"Pretrain/Learning Rate": 3.3910296967831266e-05, "Pretrain/Loss": 2.0336177349090576, "Pretrain/Loss (Raw)": 1.8757206201553345, "Pretrain/Step": 3838, "Pretrain/Step Time": 8.455334153026342} +{"Pretrain/Learning Rate": 3.390236326234977e-05, "Pretrain/Loss": 2.0327255725860596, "Pretrain/Loss (Raw)": 1.9718080759048462, "Pretrain/Step": 3839, "Pretrain/Step Time": 8.456784566864371} +{"Pretrain/Learning Rate": 3.389442852998378e-05, "Pretrain/Loss": 2.0365633964538574, "Pretrain/Loss (Raw)": 2.210141181945801, "Pretrain/Step": 3840, "Pretrain/Step Time": 8.460257641971111} +{"Pretrain/Learning Rate": 3.3886492771648593e-05, "Pretrain/Loss": 2.0352561473846436, "Pretrain/Loss (Raw)": 1.9564343690872192, "Pretrain/Step": 3841, "Pretrain/Step Time": 8.460386648774147} +{"Pretrain/Learning Rate": 3.3878555988259585e-05, "Pretrain/Loss": 2.037637710571289, "Pretrain/Loss (Raw)": 2.11724591255188, "Pretrain/Step": 3842, "Pretrain/Step Time": 8.461835984140635} +{"Pretrain/Learning Rate": 3.387061818073227e-05, "Pretrain/Loss": 2.0383291244506836, "Pretrain/Loss (Raw)": 1.9915168285369873, "Pretrain/Step": 3843, "Pretrain/Step Time": 8.460456687957048} +{"Pretrain/Learning Rate": 3.386267934998226e-05, "Pretrain/Loss": 2.0387187004089355, "Pretrain/Loss (Raw)": 2.117215394973755, "Pretrain/Step": 3844, "Pretrain/Step Time": 8.457818543538451} +{"Pretrain/Learning Rate": 3.385473949692531e-05, "Pretrain/Loss": 2.037954330444336, "Pretrain/Loss (Raw)": 1.8548216819763184, "Pretrain/Step": 3845, "Pretrain/Step Time": 8.461542623117566} +{"Pretrain/Learning Rate": 3.384679862247726e-05, "Pretrain/Loss": 2.039073944091797, "Pretrain/Loss (Raw)": 2.0325162410736084, "Pretrain/Step": 3846, "Pretrain/Step Time": 8.458338562399149} +{"Pretrain/Learning Rate": 3.383885672755411e-05, "Pretrain/Loss": 2.039245367050171, "Pretrain/Loss (Raw)": 2.108285427093506, "Pretrain/Step": 3847, "Pretrain/Step Time": 8.457127979025245} +{"Pretrain/Learning Rate": 3.383091381307193e-05, "Pretrain/Loss": 2.038623332977295, "Pretrain/Loss (Raw)": 1.9871575832366943, "Pretrain/Step": 3848, "Pretrain/Step Time": 8.463436860591173} +{"Pretrain/Learning Rate": 3.3822969879946947e-05, "Pretrain/Loss": 2.0379767417907715, "Pretrain/Loss (Raw)": 1.8207794427871704, "Pretrain/Step": 3849, "Pretrain/Step Time": 8.464042680338025} +{"Pretrain/Learning Rate": 3.38150249290955e-05, "Pretrain/Loss": 2.037580728530884, "Pretrain/Loss (Raw)": 2.0859625339508057, "Pretrain/Step": 3850, "Pretrain/Step Time": 8.461548464372754} +{"Pretrain/Learning Rate": 3.3807078961434013e-05, "Pretrain/Loss": 2.0362555980682373, "Pretrain/Loss (Raw)": 1.981066107749939, "Pretrain/Step": 3851, "Pretrain/Step Time": 8.462108284235} +{"Pretrain/Learning Rate": 3.3799131977879064e-05, "Pretrain/Loss": 2.038034439086914, "Pretrain/Loss (Raw)": 2.1390676498413086, "Pretrain/Step": 3852, "Pretrain/Step Time": 8.462439013645053} +{"Pretrain/Learning Rate": 3.379118397934734e-05, "Pretrain/Loss": 2.0383708477020264, "Pretrain/Loss (Raw)": 2.0486929416656494, "Pretrain/Step": 3853, "Pretrain/Step Time": 8.463799450546503} +{"Pretrain/Learning Rate": 3.3783234966755625e-05, "Pretrain/Loss": 2.037670612335205, "Pretrain/Loss (Raw)": 2.0625710487365723, "Pretrain/Step": 3854, "Pretrain/Step Time": 8.464280053973198} +{"Pretrain/Learning Rate": 3.377528494102086e-05, "Pretrain/Loss": 2.0364584922790527, "Pretrain/Loss (Raw)": 1.989924669265747, "Pretrain/Step": 3855, "Pretrain/Step Time": 8.468768512830138} +{"Pretrain/Learning Rate": 3.376733390306004e-05, "Pretrain/Loss": 2.0364956855773926, "Pretrain/Loss (Raw)": 2.0370824337005615, "Pretrain/Step": 3856, "Pretrain/Step Time": 8.469884188845754} +{"Pretrain/Learning Rate": 3.375938185379035e-05, "Pretrain/Loss": 2.0357272624969482, "Pretrain/Loss (Raw)": 2.0184473991394043, "Pretrain/Step": 3857, "Pretrain/Step Time": 8.474535156041384} +{"Pretrain/Learning Rate": 3.375142879412903e-05, "Pretrain/Loss": 2.0339150428771973, "Pretrain/Loss (Raw)": 1.9910417795181274, "Pretrain/Step": 3858, "Pretrain/Step Time": 8.472686935216188} +{"Pretrain/Learning Rate": 3.374347472499348e-05, "Pretrain/Loss": 2.033444881439209, "Pretrain/Loss (Raw)": 2.0885252952575684, "Pretrain/Step": 3859, "Pretrain/Step Time": 8.475791044533253} +{"Pretrain/Learning Rate": 3.37355196473012e-05, "Pretrain/Loss": 2.0320005416870117, "Pretrain/Loss (Raw)": 1.8110677003860474, "Pretrain/Step": 3860, "Pretrain/Step Time": 8.468487305566669} +{"Pretrain/Learning Rate": 3.3727563561969787e-05, "Pretrain/Loss": 2.029768466949463, "Pretrain/Loss (Raw)": 1.9061254262924194, "Pretrain/Step": 3861, "Pretrain/Step Time": 8.468683505430818} +{"Pretrain/Learning Rate": 3.3719606469916984e-05, "Pretrain/Loss": 2.030026912689209, "Pretrain/Loss (Raw)": 2.06750750541687, "Pretrain/Step": 3862, "Pretrain/Step Time": 8.46728409267962} +{"Pretrain/Learning Rate": 3.371164837206065e-05, "Pretrain/Loss": 2.0308361053466797, "Pretrain/Loss (Raw)": 2.0219571590423584, "Pretrain/Step": 3863, "Pretrain/Step Time": 8.467403627932072} +{"Pretrain/Learning Rate": 3.370368926931873e-05, "Pretrain/Loss": 2.031597137451172, "Pretrain/Loss (Raw)": 2.021785020828247, "Pretrain/Step": 3864, "Pretrain/Step Time": 8.467741835862398} +{"Pretrain/Learning Rate": 3.3695729162609315e-05, "Pretrain/Loss": 2.031524658203125, "Pretrain/Loss (Raw)": 2.0185458660125732, "Pretrain/Step": 3865, "Pretrain/Step Time": 8.469116669148207} +{"Pretrain/Learning Rate": 3.368776805285059e-05, "Pretrain/Loss": 2.0321531295776367, "Pretrain/Loss (Raw)": 2.240361213684082, "Pretrain/Step": 3866, "Pretrain/Step Time": 8.468028202652931} +{"Pretrain/Learning Rate": 3.367980594096088e-05, "Pretrain/Loss": 2.0304903984069824, "Pretrain/Loss (Raw)": 1.7975120544433594, "Pretrain/Step": 3867, "Pretrain/Step Time": 8.470046531409025} +{"Pretrain/Learning Rate": 3.367184282785861e-05, "Pretrain/Loss": 2.0312440395355225, "Pretrain/Loss (Raw)": 2.08404541015625, "Pretrain/Step": 3868, "Pretrain/Step Time": 8.476724904030561} +{"Pretrain/Learning Rate": 3.366387871446231e-05, "Pretrain/Loss": 2.030520439147949, "Pretrain/Loss (Raw)": 1.9981848001480103, "Pretrain/Step": 3869, "Pretrain/Step Time": 8.471911298111081} +{"Pretrain/Learning Rate": 3.365591360169064e-05, "Pretrain/Loss": 2.030320167541504, "Pretrain/Loss (Raw)": 1.9870644807815552, "Pretrain/Step": 3870, "Pretrain/Step Time": 8.468405731022358} +{"Pretrain/Learning Rate": 3.364794749046239e-05, "Pretrain/Loss": 2.0299253463745117, "Pretrain/Loss (Raw)": 1.8793848752975464, "Pretrain/Step": 3871, "Pretrain/Step Time": 8.46937626041472} +{"Pretrain/Learning Rate": 3.3639980381696426e-05, "Pretrain/Loss": 2.0301809310913086, "Pretrain/Loss (Raw)": 2.097012758255005, "Pretrain/Step": 3872, "Pretrain/Step Time": 8.473523262888193} +{"Pretrain/Learning Rate": 3.363201227631176e-05, "Pretrain/Loss": 2.030639410018921, "Pretrain/Loss (Raw)": 2.146232843399048, "Pretrain/Step": 3873, "Pretrain/Step Time": 8.470191266387701} +{"Pretrain/Learning Rate": 3.362404317522752e-05, "Pretrain/Loss": 2.0296101570129395, "Pretrain/Loss (Raw)": 2.1394827365875244, "Pretrain/Step": 3874, "Pretrain/Step Time": 8.472962187603116} +{"Pretrain/Learning Rate": 3.3616073079362926e-05, "Pretrain/Loss": 2.030959129333496, "Pretrain/Loss (Raw)": 2.1635689735412598, "Pretrain/Step": 3875, "Pretrain/Step Time": 8.46977304853499} +{"Pretrain/Learning Rate": 3.360810198963733e-05, "Pretrain/Loss": 2.029348134994507, "Pretrain/Loss (Raw)": 1.7843540906906128, "Pretrain/Step": 3876, "Pretrain/Step Time": 8.469870675355196} +{"Pretrain/Learning Rate": 3.36001299069702e-05, "Pretrain/Loss": 2.030137300491333, "Pretrain/Loss (Raw)": 2.1159605979919434, "Pretrain/Step": 3877, "Pretrain/Step Time": 8.47167576290667} +{"Pretrain/Learning Rate": 3.35921568322811e-05, "Pretrain/Loss": 2.03110671043396, "Pretrain/Loss (Raw)": 2.0869030952453613, "Pretrain/Step": 3878, "Pretrain/Step Time": 8.474327964708209} +{"Pretrain/Learning Rate": 3.3584182766489736e-05, "Pretrain/Loss": 2.033317804336548, "Pretrain/Loss (Raw)": 2.179521322250366, "Pretrain/Step": 3879, "Pretrain/Step Time": 8.471607929095626} +{"Pretrain/Learning Rate": 3.35762077105159e-05, "Pretrain/Loss": 2.032196044921875, "Pretrain/Loss (Raw)": 1.961527943611145, "Pretrain/Step": 3880, "Pretrain/Step Time": 8.472423508763313} +{"Pretrain/Learning Rate": 3.356823166527952e-05, "Pretrain/Loss": 2.034327507019043, "Pretrain/Loss (Raw)": 2.232565402984619, "Pretrain/Step": 3881, "Pretrain/Step Time": 8.473195988684893} +{"Pretrain/Learning Rate": 3.356025463170063e-05, "Pretrain/Loss": 2.0361838340759277, "Pretrain/Loss (Raw)": 2.173250198364258, "Pretrain/Step": 3882, "Pretrain/Step Time": 8.472248692065477} +{"Pretrain/Learning Rate": 3.355227661069937e-05, "Pretrain/Loss": 2.0367250442504883, "Pretrain/Loss (Raw)": 2.1142971515655518, "Pretrain/Step": 3883, "Pretrain/Step Time": 8.471226815134287} +{"Pretrain/Learning Rate": 3.354429760319602e-05, "Pretrain/Loss": 2.037555456161499, "Pretrain/Loss (Raw)": 2.0792031288146973, "Pretrain/Step": 3884, "Pretrain/Step Time": 8.472318494692445} +{"Pretrain/Learning Rate": 3.3536317610110946e-05, "Pretrain/Loss": 2.0368213653564453, "Pretrain/Loss (Raw)": 2.0222036838531494, "Pretrain/Step": 3885, "Pretrain/Step Time": 8.474112898111343} +{"Pretrain/Learning Rate": 3.3528336632364624e-05, "Pretrain/Loss": 2.0396780967712402, "Pretrain/Loss (Raw)": 2.021970510482788, "Pretrain/Step": 3886, "Pretrain/Step Time": 8.474532896652818} +{"Pretrain/Learning Rate": 3.352035467087767e-05, "Pretrain/Loss": 2.0393800735473633, "Pretrain/Loss (Raw)": 2.0652778148651123, "Pretrain/Step": 3887, "Pretrain/Step Time": 8.47392382659018} +{"Pretrain/Learning Rate": 3.351237172657081e-05, "Pretrain/Loss": 2.0384225845336914, "Pretrain/Loss (Raw)": 1.8265316486358643, "Pretrain/Step": 3888, "Pretrain/Step Time": 8.473335610702634} +{"Pretrain/Learning Rate": 3.3504387800364856e-05, "Pretrain/Loss": 2.0382943153381348, "Pretrain/Loss (Raw)": 2.086752414703369, "Pretrain/Step": 3889, "Pretrain/Step Time": 8.473455090075731} +{"Pretrain/Learning Rate": 3.349640289318075e-05, "Pretrain/Loss": 2.037787675857544, "Pretrain/Loss (Raw)": 1.9780234098434448, "Pretrain/Step": 3890, "Pretrain/Step Time": 8.476943418383598} +{"Pretrain/Learning Rate": 3.348841700593956e-05, "Pretrain/Loss": 2.0400443077087402, "Pretrain/Loss (Raw)": 2.239743947982788, "Pretrain/Step": 3891, "Pretrain/Step Time": 8.472609395161271} +{"Pretrain/Learning Rate": 3.3480430139562455e-05, "Pretrain/Loss": 2.040724277496338, "Pretrain/Loss (Raw)": 2.1044182777404785, "Pretrain/Step": 3892, "Pretrain/Step Time": 8.472041301429272} +{"Pretrain/Learning Rate": 3.3472442294970716e-05, "Pretrain/Loss": 2.0399529933929443, "Pretrain/Loss (Raw)": 2.1295225620269775, "Pretrain/Step": 3893, "Pretrain/Step Time": 8.473948311060667} +{"Pretrain/Learning Rate": 3.346445347308573e-05, "Pretrain/Loss": 2.0388708114624023, "Pretrain/Loss (Raw)": 1.973792552947998, "Pretrain/Step": 3894, "Pretrain/Step Time": 8.471016773954034} +{"Pretrain/Learning Rate": 3.345646367482902e-05, "Pretrain/Loss": 2.0380282402038574, "Pretrain/Loss (Raw)": 1.9240622520446777, "Pretrain/Step": 3895, "Pretrain/Step Time": 8.472420250996947} +{"Pretrain/Learning Rate": 3.344847290112219e-05, "Pretrain/Loss": 2.037846088409424, "Pretrain/Loss (Raw)": 2.04909348487854, "Pretrain/Step": 3896, "Pretrain/Step Time": 8.472433628514409} +{"Pretrain/Learning Rate": 3.3440481152886974e-05, "Pretrain/Loss": 2.0378527641296387, "Pretrain/Loss (Raw)": 2.0782392024993896, "Pretrain/Step": 3897, "Pretrain/Step Time": 8.473787486553192} +{"Pretrain/Learning Rate": 3.343248843104523e-05, "Pretrain/Loss": 2.038231372833252, "Pretrain/Loss (Raw)": 2.115060806274414, "Pretrain/Step": 3898, "Pretrain/Step Time": 8.469349080696702} +{"Pretrain/Learning Rate": 3.34244947365189e-05, "Pretrain/Loss": 2.0382513999938965, "Pretrain/Loss (Raw)": 2.088141441345215, "Pretrain/Step": 3899, "Pretrain/Step Time": 8.471106052398682} +{"Pretrain/Learning Rate": 3.341650007023008e-05, "Pretrain/Loss": 2.0354843139648438, "Pretrain/Loss (Raw)": 1.7717288732528687, "Pretrain/Step": 3900, "Pretrain/Step Time": 8.472715979442} +{"Pretrain/Learning Rate": 3.340850443310092e-05, "Pretrain/Loss": 2.033700466156006, "Pretrain/Loss (Raw)": 2.007439374923706, "Pretrain/Step": 3901, "Pretrain/Step Time": 8.474959226325154} +{"Pretrain/Learning Rate": 3.3400507826053736e-05, "Pretrain/Loss": 2.03358793258667, "Pretrain/Loss (Raw)": 1.9222866296768188, "Pretrain/Step": 3902, "Pretrain/Step Time": 8.475067039951682} +{"Pretrain/Learning Rate": 3.3392510250010926e-05, "Pretrain/Loss": 2.034287452697754, "Pretrain/Loss (Raw)": 2.0335960388183594, "Pretrain/Step": 3903, "Pretrain/Step Time": 8.472182035446167} +{"Pretrain/Learning Rate": 3.338451170589501e-05, "Pretrain/Loss": 2.0374088287353516, "Pretrain/Loss (Raw)": 2.270390748977661, "Pretrain/Step": 3904, "Pretrain/Step Time": 8.46913193538785} +{"Pretrain/Learning Rate": 3.337651219462861e-05, "Pretrain/Loss": 2.0363783836364746, "Pretrain/Loss (Raw)": 1.9403412342071533, "Pretrain/Step": 3905, "Pretrain/Step Time": 8.469701273366809} +{"Pretrain/Learning Rate": 3.336851171713447e-05, "Pretrain/Loss": 2.0341978073120117, "Pretrain/Loss (Raw)": 1.886269450187683, "Pretrain/Step": 3906, "Pretrain/Step Time": 8.473045144230127} +{"Pretrain/Learning Rate": 3.3360510274335446e-05, "Pretrain/Loss": 2.034299850463867, "Pretrain/Loss (Raw)": 2.032013177871704, "Pretrain/Step": 3907, "Pretrain/Step Time": 8.473087819293141} +{"Pretrain/Learning Rate": 3.33525078671545e-05, "Pretrain/Loss": 2.033759117126465, "Pretrain/Loss (Raw)": 1.9800834655761719, "Pretrain/Step": 3908, "Pretrain/Step Time": 8.47173291258514} +{"Pretrain/Learning Rate": 3.3344504496514705e-05, "Pretrain/Loss": 2.033924102783203, "Pretrain/Loss (Raw)": 1.939193844795227, "Pretrain/Step": 3909, "Pretrain/Step Time": 8.475191486999393} +{"Pretrain/Learning Rate": 3.333650016333926e-05, "Pretrain/Loss": 2.0323309898376465, "Pretrain/Loss (Raw)": 1.9693306684494019, "Pretrain/Step": 3910, "Pretrain/Step Time": 8.471588607877493} +{"Pretrain/Learning Rate": 3.332849486855144e-05, "Pretrain/Loss": 2.0319583415985107, "Pretrain/Loss (Raw)": 2.029823064804077, "Pretrain/Step": 3911, "Pretrain/Step Time": 8.47056357190013} +{"Pretrain/Learning Rate": 3.332048861307467e-05, "Pretrain/Loss": 2.033297538757324, "Pretrain/Loss (Raw)": 1.9947872161865234, "Pretrain/Step": 3912, "Pretrain/Step Time": 8.472020329907537} +{"Pretrain/Learning Rate": 3.331248139783246e-05, "Pretrain/Loss": 2.032651424407959, "Pretrain/Loss (Raw)": 2.095062732696533, "Pretrain/Step": 3913, "Pretrain/Step Time": 8.471132697537541} +{"Pretrain/Learning Rate": 3.330447322374844e-05, "Pretrain/Loss": 2.0340042114257812, "Pretrain/Loss (Raw)": 2.1475882530212402, "Pretrain/Step": 3914, "Pretrain/Step Time": 8.474413249641657} +{"Pretrain/Learning Rate": 3.329646409174635e-05, "Pretrain/Loss": 2.035501003265381, "Pretrain/Loss (Raw)": 2.125262975692749, "Pretrain/Step": 3915, "Pretrain/Step Time": 8.471797809004784} +{"Pretrain/Learning Rate": 3.3288454002750044e-05, "Pretrain/Loss": 2.036346435546875, "Pretrain/Loss (Raw)": 2.200423240661621, "Pretrain/Step": 3916, "Pretrain/Step Time": 8.471766578033566} +{"Pretrain/Learning Rate": 3.3280442957683486e-05, "Pretrain/Loss": 2.035421133041382, "Pretrain/Loss (Raw)": 1.9553488492965698, "Pretrain/Step": 3917, "Pretrain/Step Time": 8.472717696800828} +{"Pretrain/Learning Rate": 3.327243095747075e-05, "Pretrain/Loss": 2.0365638732910156, "Pretrain/Loss (Raw)": 2.2106220722198486, "Pretrain/Step": 3918, "Pretrain/Step Time": 8.476467337459326} +{"Pretrain/Learning Rate": 3.3264418003036e-05, "Pretrain/Loss": 2.0369396209716797, "Pretrain/Loss (Raw)": 2.0614144802093506, "Pretrain/Step": 3919, "Pretrain/Step Time": 8.478778192773461} +{"Pretrain/Learning Rate": 3.3256404095303526e-05, "Pretrain/Loss": 2.036781072616577, "Pretrain/Loss (Raw)": 2.0929577350616455, "Pretrain/Step": 3920, "Pretrain/Step Time": 8.480934230610728} +{"Pretrain/Learning Rate": 3.324838923519776e-05, "Pretrain/Loss": 2.036503791809082, "Pretrain/Loss (Raw)": 1.9301387071609497, "Pretrain/Step": 3921, "Pretrain/Step Time": 8.477459479123354} +{"Pretrain/Learning Rate": 3.324037342364319e-05, "Pretrain/Loss": 2.0353641510009766, "Pretrain/Loss (Raw)": 2.002652883529663, "Pretrain/Step": 3922, "Pretrain/Step Time": 8.482486410066485} +{"Pretrain/Learning Rate": 3.3232356661564435e-05, "Pretrain/Loss": 2.0343823432922363, "Pretrain/Loss (Raw)": 1.9639445543289185, "Pretrain/Step": 3923, "Pretrain/Step Time": 8.482683816924691} +{"Pretrain/Learning Rate": 3.322433894988624e-05, "Pretrain/Loss": 2.0348339080810547, "Pretrain/Loss (Raw)": 1.9547874927520752, "Pretrain/Step": 3924, "Pretrain/Step Time": 8.484055675566196} +{"Pretrain/Learning Rate": 3.321632028953343e-05, "Pretrain/Loss": 2.036576747894287, "Pretrain/Loss (Raw)": 2.168494939804077, "Pretrain/Step": 3925, "Pretrain/Step Time": 8.485477140173316} +{"Pretrain/Learning Rate": 3.3208300681430964e-05, "Pretrain/Loss": 2.0384907722473145, "Pretrain/Loss (Raw)": 2.2041492462158203, "Pretrain/Step": 3926, "Pretrain/Step Time": 8.484861001372337} +{"Pretrain/Learning Rate": 3.320028012650391e-05, "Pretrain/Loss": 2.037855625152588, "Pretrain/Loss (Raw)": 2.018606424331665, "Pretrain/Step": 3927, "Pretrain/Step Time": 8.482911735773087} +{"Pretrain/Learning Rate": 3.319225862567741e-05, "Pretrain/Loss": 2.039393901824951, "Pretrain/Loss (Raw)": 2.124972343444824, "Pretrain/Step": 3928, "Pretrain/Step Time": 8.482906937599182} +{"Pretrain/Learning Rate": 3.318423617987676e-05, "Pretrain/Loss": 2.041335105895996, "Pretrain/Loss (Raw)": 2.296368360519409, "Pretrain/Step": 3929, "Pretrain/Step Time": 8.482827179133892} +{"Pretrain/Learning Rate": 3.317621279002735e-05, "Pretrain/Loss": 2.042574882507324, "Pretrain/Loss (Raw)": 2.153933048248291, "Pretrain/Step": 3930, "Pretrain/Step Time": 8.478791201487184} +{"Pretrain/Learning Rate": 3.3168188457054654e-05, "Pretrain/Loss": 2.044358730316162, "Pretrain/Loss (Raw)": 2.342865228652954, "Pretrain/Step": 3931, "Pretrain/Step Time": 8.483043868094683} +{"Pretrain/Learning Rate": 3.3160163181884307e-05, "Pretrain/Loss": 2.0445966720581055, "Pretrain/Loss (Raw)": 2.0782577991485596, "Pretrain/Step": 3932, "Pretrain/Step Time": 8.480029182508588} +{"Pretrain/Learning Rate": 3.3152136965441996e-05, "Pretrain/Loss": 2.0440101623535156, "Pretrain/Loss (Raw)": 2.1221563816070557, "Pretrain/Step": 3933, "Pretrain/Step Time": 8.481643171980977} +{"Pretrain/Learning Rate": 3.314410980865355e-05, "Pretrain/Loss": 2.041642665863037, "Pretrain/Loss (Raw)": 1.8141204118728638, "Pretrain/Step": 3934, "Pretrain/Step Time": 8.480198569595814} +{"Pretrain/Learning Rate": 3.3136081712444905e-05, "Pretrain/Loss": 2.040478467941284, "Pretrain/Loss (Raw)": 1.9470266103744507, "Pretrain/Step": 3935, "Pretrain/Step Time": 8.478571685031056} +{"Pretrain/Learning Rate": 3.312805267774209e-05, "Pretrain/Loss": 2.0376100540161133, "Pretrain/Loss (Raw)": 1.7552316188812256, "Pretrain/Step": 3936, "Pretrain/Step Time": 8.480385756120086} +{"Pretrain/Learning Rate": 3.312002270547125e-05, "Pretrain/Loss": 2.0391461849212646, "Pretrain/Loss (Raw)": 2.0223453044891357, "Pretrain/Step": 3937, "Pretrain/Step Time": 8.480411319062114} +{"Pretrain/Learning Rate": 3.311199179655865e-05, "Pretrain/Loss": 2.0391273498535156, "Pretrain/Loss (Raw)": 2.004338026046753, "Pretrain/Step": 3938, "Pretrain/Step Time": 8.477050682529807} +{"Pretrain/Learning Rate": 3.3103959951930654e-05, "Pretrain/Loss": 2.0397696495056152, "Pretrain/Loss (Raw)": 2.061488389968872, "Pretrain/Step": 3939, "Pretrain/Step Time": 8.483172139152884} +{"Pretrain/Learning Rate": 3.309592717251371e-05, "Pretrain/Loss": 2.0380096435546875, "Pretrain/Loss (Raw)": 1.8823655843734741, "Pretrain/Step": 3940, "Pretrain/Step Time": 8.484237434342504} +{"Pretrain/Learning Rate": 3.308789345923442e-05, "Pretrain/Loss": 2.037315845489502, "Pretrain/Loss (Raw)": 1.9580888748168945, "Pretrain/Step": 3941, "Pretrain/Step Time": 8.484838541597128} +{"Pretrain/Learning Rate": 3.3079858813019465e-05, "Pretrain/Loss": 2.0366570949554443, "Pretrain/Loss (Raw)": 2.067045211791992, "Pretrain/Step": 3942, "Pretrain/Step Time": 8.484010387212038} +{"Pretrain/Learning Rate": 3.307182323479563e-05, "Pretrain/Loss": 2.0373735427856445, "Pretrain/Loss (Raw)": 2.2049431800842285, "Pretrain/Step": 3943, "Pretrain/Step Time": 8.484204772859812} +{"Pretrain/Learning Rate": 3.306378672548982e-05, "Pretrain/Loss": 2.035949468612671, "Pretrain/Loss (Raw)": 1.9104621410369873, "Pretrain/Step": 3944, "Pretrain/Step Time": 8.487510785460472} +{"Pretrain/Learning Rate": 3.305574928602905e-05, "Pretrain/Loss": 2.0343265533447266, "Pretrain/Loss (Raw)": 2.0688493251800537, "Pretrain/Step": 3945, "Pretrain/Step Time": 8.485461585223675} +{"Pretrain/Learning Rate": 3.304771091734043e-05, "Pretrain/Loss": 2.036593437194824, "Pretrain/Loss (Raw)": 2.0837817192077637, "Pretrain/Step": 3946, "Pretrain/Step Time": 8.48577848635614} +{"Pretrain/Learning Rate": 3.3039671620351185e-05, "Pretrain/Loss": 2.0377304553985596, "Pretrain/Loss (Raw)": 1.9773765802383423, "Pretrain/Step": 3947, "Pretrain/Step Time": 8.489088734611869} +{"Pretrain/Learning Rate": 3.3031631395988644e-05, "Pretrain/Loss": 2.0396811962127686, "Pretrain/Loss (Raw)": 2.1701245307922363, "Pretrain/Step": 3948, "Pretrain/Step Time": 8.482700368389487} +{"Pretrain/Learning Rate": 3.302359024518024e-05, "Pretrain/Loss": 2.038956642150879, "Pretrain/Loss (Raw)": 2.0105109214782715, "Pretrain/Step": 3949, "Pretrain/Step Time": 8.483460005372763} +{"Pretrain/Learning Rate": 3.3015548168853525e-05, "Pretrain/Loss": 2.0397751331329346, "Pretrain/Loss (Raw)": 2.0936310291290283, "Pretrain/Step": 3950, "Pretrain/Step Time": 8.487459097057581} +{"Pretrain/Learning Rate": 3.300750516793614e-05, "Pretrain/Loss": 2.0376315116882324, "Pretrain/Loss (Raw)": 1.994908332824707, "Pretrain/Step": 3951, "Pretrain/Step Time": 8.48943704739213} +{"Pretrain/Learning Rate": 3.2999461243355854e-05, "Pretrain/Loss": 2.0360114574432373, "Pretrain/Loss (Raw)": 1.8183869123458862, "Pretrain/Step": 3952, "Pretrain/Step Time": 8.487424204126} +{"Pretrain/Learning Rate": 3.299141639604053e-05, "Pretrain/Loss": 2.0383644104003906, "Pretrain/Loss (Raw)": 2.045086145401001, "Pretrain/Step": 3953, "Pretrain/Step Time": 8.489910742267966} +{"Pretrain/Learning Rate": 3.298337062691812e-05, "Pretrain/Loss": 2.0384535789489746, "Pretrain/Loss (Raw)": 2.0349555015563965, "Pretrain/Step": 3954, "Pretrain/Step Time": 8.491756785660982} +{"Pretrain/Learning Rate": 3.297532393691672e-05, "Pretrain/Loss": 2.038166046142578, "Pretrain/Loss (Raw)": 2.1027767658233643, "Pretrain/Step": 3955, "Pretrain/Step Time": 8.4909393992275} +{"Pretrain/Learning Rate": 3.29672763269645e-05, "Pretrain/Loss": 2.0383076667785645, "Pretrain/Loss (Raw)": 2.095597982406616, "Pretrain/Step": 3956, "Pretrain/Step Time": 8.490927241742611} +{"Pretrain/Learning Rate": 3.295922779798976e-05, "Pretrain/Loss": 2.0376546382904053, "Pretrain/Loss (Raw)": 1.9847286939620972, "Pretrain/Step": 3957, "Pretrain/Step Time": 8.491742426529527} +{"Pretrain/Learning Rate": 3.2951178350920895e-05, "Pretrain/Loss": 2.03914737701416, "Pretrain/Loss (Raw)": 2.2556612491607666, "Pretrain/Step": 3958, "Pretrain/Step Time": 8.492575135082006} +{"Pretrain/Learning Rate": 3.2943127986686393e-05, "Pretrain/Loss": 2.041079044342041, "Pretrain/Loss (Raw)": 2.279822587966919, "Pretrain/Step": 3959, "Pretrain/Step Time": 8.491703210398555} +{"Pretrain/Learning Rate": 3.293507670621488e-05, "Pretrain/Loss": 2.0416812896728516, "Pretrain/Loss (Raw)": 2.0555403232574463, "Pretrain/Step": 3960, "Pretrain/Step Time": 8.49179775826633} +{"Pretrain/Learning Rate": 3.2927024510435055e-05, "Pretrain/Loss": 2.0416910648345947, "Pretrain/Loss (Raw)": 2.1145098209381104, "Pretrain/Step": 3961, "Pretrain/Step Time": 8.491479344666004} +{"Pretrain/Learning Rate": 3.2918971400275734e-05, "Pretrain/Loss": 2.0415899753570557, "Pretrain/Loss (Raw)": 2.14217472076416, "Pretrain/Step": 3962, "Pretrain/Step Time": 8.487797230482101} +{"Pretrain/Learning Rate": 3.2910917376665845e-05, "Pretrain/Loss": 2.041081428527832, "Pretrain/Loss (Raw)": 1.8982480764389038, "Pretrain/Step": 3963, "Pretrain/Step Time": 8.488562209531665} +{"Pretrain/Learning Rate": 3.290286244053442e-05, "Pretrain/Loss": 2.040579319000244, "Pretrain/Loss (Raw)": 2.0707507133483887, "Pretrain/Step": 3964, "Pretrain/Step Time": 8.488479882478714} +{"Pretrain/Learning Rate": 3.289480659281058e-05, "Pretrain/Loss": 2.041877269744873, "Pretrain/Loss (Raw)": 2.111833095550537, "Pretrain/Step": 3965, "Pretrain/Step Time": 8.488876648247242} +{"Pretrain/Learning Rate": 3.288674983442359e-05, "Pretrain/Loss": 2.044609785079956, "Pretrain/Loss (Raw)": 2.2254703044891357, "Pretrain/Step": 3966, "Pretrain/Step Time": 8.485781097784638} +{"Pretrain/Learning Rate": 3.287869216630277e-05, "Pretrain/Loss": 2.045624256134033, "Pretrain/Loss (Raw)": 2.1016697883605957, "Pretrain/Step": 3967, "Pretrain/Step Time": 8.485219169408083} +{"Pretrain/Learning Rate": 3.287063358937757e-05, "Pretrain/Loss": 2.044708251953125, "Pretrain/Loss (Raw)": 2.092881679534912, "Pretrain/Step": 3968, "Pretrain/Step Time": 8.484080156311393} +{"Pretrain/Learning Rate": 3.286257410457756e-05, "Pretrain/Loss": 2.0465006828308105, "Pretrain/Loss (Raw)": 2.185908079147339, "Pretrain/Step": 3969, "Pretrain/Step Time": 8.483029626309872} +{"Pretrain/Learning Rate": 3.285451371283239e-05, "Pretrain/Loss": 2.0461654663085938, "Pretrain/Loss (Raw)": 2.0742874145507812, "Pretrain/Step": 3970, "Pretrain/Step Time": 8.486271049827337} +{"Pretrain/Learning Rate": 3.2846452415071826e-05, "Pretrain/Loss": 2.046233892440796, "Pretrain/Loss (Raw)": 2.000290870666504, "Pretrain/Step": 3971, "Pretrain/Step Time": 8.490905730053782} +{"Pretrain/Learning Rate": 3.283839021222573e-05, "Pretrain/Loss": 2.046797037124634, "Pretrain/Loss (Raw)": 2.1893043518066406, "Pretrain/Step": 3972, "Pretrain/Step Time": 8.492627931758761} +{"Pretrain/Learning Rate": 3.2830327105224074e-05, "Pretrain/Loss": 2.0473079681396484, "Pretrain/Loss (Raw)": 1.9202263355255127, "Pretrain/Step": 3973, "Pretrain/Step Time": 8.491354156285524} +{"Pretrain/Learning Rate": 3.282226309499694e-05, "Pretrain/Loss": 2.047764778137207, "Pretrain/Loss (Raw)": 2.0909922122955322, "Pretrain/Step": 3974, "Pretrain/Step Time": 8.49199509434402} +{"Pretrain/Learning Rate": 3.281419818247451e-05, "Pretrain/Loss": 2.047074317932129, "Pretrain/Loss (Raw)": 2.0198943614959717, "Pretrain/Step": 3975, "Pretrain/Step Time": 8.492354055866599} +{"Pretrain/Learning Rate": 3.280613236858707e-05, "Pretrain/Loss": 2.047091007232666, "Pretrain/Loss (Raw)": 1.9893276691436768, "Pretrain/Step": 3976, "Pretrain/Step Time": 8.497311115264893} +{"Pretrain/Learning Rate": 3.2798065654265e-05, "Pretrain/Loss": 2.048884868621826, "Pretrain/Loss (Raw)": 2.050361156463623, "Pretrain/Step": 3977, "Pretrain/Step Time": 8.496778013184667} +{"Pretrain/Learning Rate": 3.2789998040438794e-05, "Pretrain/Loss": 2.0479397773742676, "Pretrain/Loss (Raw)": 1.9649980068206787, "Pretrain/Step": 3978, "Pretrain/Step Time": 8.495978252962232} +{"Pretrain/Learning Rate": 3.278192952803905e-05, "Pretrain/Loss": 2.0485687255859375, "Pretrain/Loss (Raw)": 2.0615413188934326, "Pretrain/Step": 3979, "Pretrain/Step Time": 8.499310096725821} +{"Pretrain/Learning Rate": 3.277386011799647e-05, "Pretrain/Loss": 2.0463552474975586, "Pretrain/Loss (Raw)": 1.8557578325271606, "Pretrain/Step": 3980, "Pretrain/Step Time": 8.496868122369051} +{"Pretrain/Learning Rate": 3.276578981124186e-05, "Pretrain/Loss": 2.047724723815918, "Pretrain/Loss (Raw)": 2.223987102508545, "Pretrain/Step": 3981, "Pretrain/Step Time": 8.497181667014956} +{"Pretrain/Learning Rate": 3.275771860870613e-05, "Pretrain/Loss": 2.04728627204895, "Pretrain/Loss (Raw)": 2.006452798843384, "Pretrain/Step": 3982, "Pretrain/Step Time": 8.497874846681952} +{"Pretrain/Learning Rate": 3.2749646511320276e-05, "Pretrain/Loss": 2.0479702949523926, "Pretrain/Loss (Raw)": 2.0774738788604736, "Pretrain/Step": 3983, "Pretrain/Step Time": 8.492558266967535} +{"Pretrain/Learning Rate": 3.2741573520015425e-05, "Pretrain/Loss": 2.0482993125915527, "Pretrain/Loss (Raw)": 2.0792176723480225, "Pretrain/Step": 3984, "Pretrain/Step Time": 8.494838001206517} +{"Pretrain/Learning Rate": 3.273349963572279e-05, "Pretrain/Loss": 2.049187421798706, "Pretrain/Loss (Raw)": 2.132117509841919, "Pretrain/Step": 3985, "Pretrain/Step Time": 8.492278788238764} +{"Pretrain/Learning Rate": 3.272542485937369e-05, "Pretrain/Loss": 2.051100015640259, "Pretrain/Loss (Raw)": 2.2358481884002686, "Pretrain/Step": 3986, "Pretrain/Step Time": 8.490716136991978} +{"Pretrain/Learning Rate": 3.271734919189955e-05, "Pretrain/Loss": 2.051182508468628, "Pretrain/Loss (Raw)": 2.0990898609161377, "Pretrain/Step": 3987, "Pretrain/Step Time": 8.49306937865913} +{"Pretrain/Learning Rate": 3.270927263423188e-05, "Pretrain/Loss": 2.0520119667053223, "Pretrain/Loss (Raw)": 1.9172228574752808, "Pretrain/Step": 3988, "Pretrain/Step Time": 8.494399931281805} +{"Pretrain/Learning Rate": 3.270119518730233e-05, "Pretrain/Loss": 2.053562641143799, "Pretrain/Loss (Raw)": 2.1046509742736816, "Pretrain/Step": 3989, "Pretrain/Step Time": 8.49484701640904} +{"Pretrain/Learning Rate": 3.269311685204262e-05, "Pretrain/Loss": 2.0527749061584473, "Pretrain/Loss (Raw)": 1.9666354656219482, "Pretrain/Step": 3990, "Pretrain/Step Time": 8.493082018569112} +{"Pretrain/Learning Rate": 3.268503762938458e-05, "Pretrain/Loss": 2.053328514099121, "Pretrain/Loss (Raw)": 2.092855215072632, "Pretrain/Step": 3991, "Pretrain/Step Time": 8.494627609848976} +{"Pretrain/Learning Rate": 3.267695752026016e-05, "Pretrain/Loss": 2.053600788116455, "Pretrain/Loss (Raw)": 2.056624412536621, "Pretrain/Step": 3992, "Pretrain/Step Time": 8.496915146708488} +{"Pretrain/Learning Rate": 3.266887652560138e-05, "Pretrain/Loss": 2.053546905517578, "Pretrain/Loss (Raw)": 2.0116536617279053, "Pretrain/Step": 3993, "Pretrain/Step Time": 8.493056911975145} +{"Pretrain/Learning Rate": 3.26607946463404e-05, "Pretrain/Loss": 2.0537166595458984, "Pretrain/Loss (Raw)": 2.2620575428009033, "Pretrain/Step": 3994, "Pretrain/Step Time": 8.49662590585649} +{"Pretrain/Learning Rate": 3.265271188340944e-05, "Pretrain/Loss": 2.056364059448242, "Pretrain/Loss (Raw)": 2.1364097595214844, "Pretrain/Step": 3995, "Pretrain/Step Time": 8.494134165346622} +{"Pretrain/Learning Rate": 3.264462823774085e-05, "Pretrain/Loss": 2.0564417839050293, "Pretrain/Loss (Raw)": 2.0939950942993164, "Pretrain/Step": 3996, "Pretrain/Step Time": 8.48575141467154} +{"Pretrain/Learning Rate": 3.263654371026709e-05, "Pretrain/Loss": 2.057969570159912, "Pretrain/Loss (Raw)": 2.1937127113342285, "Pretrain/Step": 3997, "Pretrain/Step Time": 8.49048207141459} +{"Pretrain/Learning Rate": 3.2628458301920685e-05, "Pretrain/Loss": 2.058413028717041, "Pretrain/Loss (Raw)": 2.043846607208252, "Pretrain/Step": 3998, "Pretrain/Step Time": 8.488823575899005} +{"Pretrain/Learning Rate": 3.26203720136343e-05, "Pretrain/Loss": 2.0586276054382324, "Pretrain/Loss (Raw)": 1.9068721532821655, "Pretrain/Step": 3999, "Pretrain/Step Time": 8.486814506351948} +{"Pretrain/Learning Rate": 3.2612284846340687e-05, "Pretrain/Loss": 2.0577197074890137, "Pretrain/Loss (Raw)": 1.9808107614517212, "Pretrain/Step": 4000, "Pretrain/Step Time": 8.483710082247853} +{"Pretrain/Learning Rate": 3.260419680097268e-05, "Pretrain/Loss": 2.057943344116211, "Pretrain/Loss (Raw)": 2.174809694290161, "Pretrain/Step": 4001, "Pretrain/Step Time": 8.487725147977471} +{"Pretrain/Learning Rate": 3.2596107878463254e-05, "Pretrain/Loss": 2.0553362369537354, "Pretrain/Loss (Raw)": 1.8057913780212402, "Pretrain/Step": 4002, "Pretrain/Step Time": 8.480932796373963} +{"Pretrain/Learning Rate": 3.258801807974545e-05, "Pretrain/Loss": 2.054157257080078, "Pretrain/Loss (Raw)": 2.012669086456299, "Pretrain/Step": 4003, "Pretrain/Step Time": 8.484594460576773} +{"Pretrain/Learning Rate": 3.257992740575243e-05, "Pretrain/Loss": 2.056201219558716, "Pretrain/Loss (Raw)": 2.0459694862365723, "Pretrain/Step": 4004, "Pretrain/Step Time": 8.482858901843429} +{"Pretrain/Learning Rate": 3.257183585741745e-05, "Pretrain/Loss": 2.0552098751068115, "Pretrain/Loss (Raw)": 1.9890750646591187, "Pretrain/Step": 4005, "Pretrain/Step Time": 8.48566215671599} +{"Pretrain/Learning Rate": 3.2563743435673855e-05, "Pretrain/Loss": 2.05532169342041, "Pretrain/Loss (Raw)": 2.1012063026428223, "Pretrain/Step": 4006, "Pretrain/Step Time": 8.48028946109116} +{"Pretrain/Learning Rate": 3.255565014145512e-05, "Pretrain/Loss": 2.0545268058776855, "Pretrain/Loss (Raw)": 2.077782154083252, "Pretrain/Step": 4007, "Pretrain/Step Time": 8.482116624712944} +{"Pretrain/Learning Rate": 3.2547555975694796e-05, "Pretrain/Loss": 2.053983211517334, "Pretrain/Loss (Raw)": 1.891961932182312, "Pretrain/Step": 4008, "Pretrain/Step Time": 8.479592464864254} +{"Pretrain/Learning Rate": 3.253946093932654e-05, "Pretrain/Loss": 2.050422191619873, "Pretrain/Loss (Raw)": 1.776745319366455, "Pretrain/Step": 4009, "Pretrain/Step Time": 8.479842718690634} +{"Pretrain/Learning Rate": 3.2531365033284115e-05, "Pretrain/Loss": 2.0496816635131836, "Pretrain/Loss (Raw)": 2.0784294605255127, "Pretrain/Step": 4010, "Pretrain/Step Time": 8.480973402038217} +{"Pretrain/Learning Rate": 3.252326825850139e-05, "Pretrain/Loss": 2.0479073524475098, "Pretrain/Loss (Raw)": 1.887230634689331, "Pretrain/Step": 4011, "Pretrain/Step Time": 8.479945298284292} +{"Pretrain/Learning Rate": 3.25151706159123e-05, "Pretrain/Loss": 2.04733943939209, "Pretrain/Loss (Raw)": 2.0064773559570312, "Pretrain/Step": 4012, "Pretrain/Step Time": 8.480935655534267} +{"Pretrain/Learning Rate": 3.250707210645093e-05, "Pretrain/Loss": 2.047060012817383, "Pretrain/Loss (Raw)": 1.986464262008667, "Pretrain/Step": 4013, "Pretrain/Step Time": 8.479003136977553} +{"Pretrain/Learning Rate": 3.249897273105143e-05, "Pretrain/Loss": 2.046938419342041, "Pretrain/Loss (Raw)": 2.006408929824829, "Pretrain/Step": 4014, "Pretrain/Step Time": 8.480053311213851} +{"Pretrain/Learning Rate": 3.249087249064805e-05, "Pretrain/Loss": 2.047610282897949, "Pretrain/Loss (Raw)": 2.1512930393218994, "Pretrain/Step": 4015, "Pretrain/Step Time": 8.481069894507527} +{"Pretrain/Learning Rate": 3.248277138617517e-05, "Pretrain/Loss": 2.048093557357788, "Pretrain/Loss (Raw)": 1.888370156288147, "Pretrain/Step": 4016, "Pretrain/Step Time": 8.484603051096201} +{"Pretrain/Learning Rate": 3.247466941856724e-05, "Pretrain/Loss": 2.0477771759033203, "Pretrain/Loss (Raw)": 2.0462427139282227, "Pretrain/Step": 4017, "Pretrain/Step Time": 8.483634697273374} +{"Pretrain/Learning Rate": 3.246656658875882e-05, "Pretrain/Loss": 2.048325777053833, "Pretrain/Loss (Raw)": 2.0482375621795654, "Pretrain/Step": 4018, "Pretrain/Step Time": 8.482847278937697} +{"Pretrain/Learning Rate": 3.2458462897684566e-05, "Pretrain/Loss": 2.0472068786621094, "Pretrain/Loss (Raw)": 2.0965540409088135, "Pretrain/Step": 4019, "Pretrain/Step Time": 8.48136318102479} +{"Pretrain/Learning Rate": 3.2450358346279234e-05, "Pretrain/Loss": 2.0467209815979004, "Pretrain/Loss (Raw)": 2.0422017574310303, "Pretrain/Step": 4020, "Pretrain/Step Time": 8.48874220624566} +{"Pretrain/Learning Rate": 3.2442252935477696e-05, "Pretrain/Loss": 2.0430374145507812, "Pretrain/Loss (Raw)": 1.6580212116241455, "Pretrain/Step": 4021, "Pretrain/Step Time": 8.487125439569354} +{"Pretrain/Learning Rate": 3.243414666621489e-05, "Pretrain/Loss": 2.0427260398864746, "Pretrain/Loss (Raw)": 1.9339501857757568, "Pretrain/Step": 4022, "Pretrain/Step Time": 8.488157557323575} +{"Pretrain/Learning Rate": 3.2426039539425876e-05, "Pretrain/Loss": 2.041344165802002, "Pretrain/Loss (Raw)": 1.7471745014190674, "Pretrain/Step": 4023, "Pretrain/Step Time": 8.488414073362947} +{"Pretrain/Learning Rate": 3.241793155604581e-05, "Pretrain/Loss": 2.0410895347595215, "Pretrain/Loss (Raw)": 2.0165255069732666, "Pretrain/Step": 4024, "Pretrain/Step Time": 8.489417901262641} +{"Pretrain/Learning Rate": 3.240982271700995e-05, "Pretrain/Loss": 2.0408406257629395, "Pretrain/Loss (Raw)": 2.046370267868042, "Pretrain/Step": 4025, "Pretrain/Step Time": 8.484157821163535} +{"Pretrain/Learning Rate": 3.2401713023253644e-05, "Pretrain/Loss": 2.037952423095703, "Pretrain/Loss (Raw)": 1.7453569173812866, "Pretrain/Step": 4026, "Pretrain/Step Time": 8.484807047992945} +{"Pretrain/Learning Rate": 3.2393602475712344e-05, "Pretrain/Loss": 2.0371079444885254, "Pretrain/Loss (Raw)": 1.9800432920455933, "Pretrain/Step": 4027, "Pretrain/Step Time": 8.48452932573855} +{"Pretrain/Learning Rate": 3.23854910753216e-05, "Pretrain/Loss": 2.038789749145508, "Pretrain/Loss (Raw)": 1.9870316982269287, "Pretrain/Step": 4028, "Pretrain/Step Time": 8.48377962037921} +{"Pretrain/Learning Rate": 3.237737882301705e-05, "Pretrain/Loss": 2.0382022857666016, "Pretrain/Loss (Raw)": 1.9322271347045898, "Pretrain/Step": 4029, "Pretrain/Step Time": 8.48012812808156} +{"Pretrain/Learning Rate": 3.236926571973444e-05, "Pretrain/Loss": 2.038315773010254, "Pretrain/Loss (Raw)": 1.9368242025375366, "Pretrain/Step": 4030, "Pretrain/Step Time": 8.479892075061798} +{"Pretrain/Learning Rate": 3.2361151766409624e-05, "Pretrain/Loss": 2.0362708568573, "Pretrain/Loss (Raw)": 1.771841049194336, "Pretrain/Step": 4031, "Pretrain/Step Time": 8.481012092903256} +{"Pretrain/Learning Rate": 3.2353036963978536e-05, "Pretrain/Loss": 2.034573554992676, "Pretrain/Loss (Raw)": 2.0531044006347656, "Pretrain/Step": 4032, "Pretrain/Step Time": 8.482327034696937} +{"Pretrain/Learning Rate": 3.234492131337722e-05, "Pretrain/Loss": 2.035841941833496, "Pretrain/Loss (Raw)": 2.102701187133789, "Pretrain/Step": 4033, "Pretrain/Step Time": 8.480439011007547} +{"Pretrain/Learning Rate": 3.233680481554182e-05, "Pretrain/Loss": 2.0363175868988037, "Pretrain/Loss (Raw)": 1.9471420049667358, "Pretrain/Step": 4034, "Pretrain/Step Time": 8.477819884195924} +{"Pretrain/Learning Rate": 3.232868747140855e-05, "Pretrain/Loss": 2.0337257385253906, "Pretrain/Loss (Raw)": 1.70029878616333, "Pretrain/Step": 4035, "Pretrain/Step Time": 8.475501084700227} +{"Pretrain/Learning Rate": 3.232056928191376e-05, "Pretrain/Loss": 2.035222053527832, "Pretrain/Loss (Raw)": 2.1716091632843018, "Pretrain/Step": 4036, "Pretrain/Step Time": 8.47861846908927} +{"Pretrain/Learning Rate": 3.231245024799388e-05, "Pretrain/Loss": 2.036447048187256, "Pretrain/Loss (Raw)": 2.0959970951080322, "Pretrain/Step": 4037, "Pretrain/Step Time": 8.482809416949749} +{"Pretrain/Learning Rate": 3.2304330370585436e-05, "Pretrain/Loss": 2.0366744995117188, "Pretrain/Loss (Raw)": 1.9984331130981445, "Pretrain/Step": 4038, "Pretrain/Step Time": 8.484746927395463} +{"Pretrain/Learning Rate": 3.2296209650625044e-05, "Pretrain/Loss": 2.035796880722046, "Pretrain/Loss (Raw)": 1.9174753427505493, "Pretrain/Step": 4039, "Pretrain/Step Time": 8.482148448005319} +{"Pretrain/Learning Rate": 3.228808808904943e-05, "Pretrain/Loss": 2.036902666091919, "Pretrain/Loss (Raw)": 2.1363391876220703, "Pretrain/Step": 4040, "Pretrain/Step Time": 8.482887579128146} +{"Pretrain/Learning Rate": 3.227996568679542e-05, "Pretrain/Loss": 2.03682279586792, "Pretrain/Loss (Raw)": 2.084822177886963, "Pretrain/Step": 4041, "Pretrain/Step Time": 8.48294080235064} +{"Pretrain/Learning Rate": 3.2271842444799925e-05, "Pretrain/Loss": 2.0347604751586914, "Pretrain/Loss (Raw)": 1.8836153745651245, "Pretrain/Step": 4042, "Pretrain/Step Time": 8.483213057741523} +{"Pretrain/Learning Rate": 3.2263718363999964e-05, "Pretrain/Loss": 2.0336215496063232, "Pretrain/Loss (Raw)": 1.9794697761535645, "Pretrain/Step": 4043, "Pretrain/Step Time": 8.484108241274953} +{"Pretrain/Learning Rate": 3.2255593445332645e-05, "Pretrain/Loss": 2.0324182510375977, "Pretrain/Loss (Raw)": 2.046400785446167, "Pretrain/Step": 4044, "Pretrain/Step Time": 8.481882613152266} +{"Pretrain/Learning Rate": 3.2247467689735164e-05, "Pretrain/Loss": 2.030268430709839, "Pretrain/Loss (Raw)": 1.6801891326904297, "Pretrain/Step": 4045, "Pretrain/Step Time": 8.48199169896543} +{"Pretrain/Learning Rate": 3.2239341098144834e-05, "Pretrain/Loss": 2.028571605682373, "Pretrain/Loss (Raw)": 1.9934194087982178, "Pretrain/Step": 4046, "Pretrain/Step Time": 8.481056774035096} +{"Pretrain/Learning Rate": 3.2231213671499057e-05, "Pretrain/Loss": 2.0280346870422363, "Pretrain/Loss (Raw)": 1.9926905632019043, "Pretrain/Step": 4047, "Pretrain/Step Time": 8.492971427738667} +{"Pretrain/Learning Rate": 3.2223085410735314e-05, "Pretrain/Loss": 2.027589797973633, "Pretrain/Loss (Raw)": 2.03603196144104, "Pretrain/Step": 4048, "Pretrain/Step Time": 8.492726827040315} +{"Pretrain/Learning Rate": 3.221495631679121e-05, "Pretrain/Loss": 2.0280909538269043, "Pretrain/Loss (Raw)": 1.994287133216858, "Pretrain/Step": 4049, "Pretrain/Step Time": 8.493333680555224} +{"Pretrain/Learning Rate": 3.220682639060444e-05, "Pretrain/Loss": 2.0279455184936523, "Pretrain/Loss (Raw)": 1.984001636505127, "Pretrain/Step": 4050, "Pretrain/Step Time": 8.490736113861203} +{"Pretrain/Learning Rate": 3.219869563311277e-05, "Pretrain/Loss": 2.028254508972168, "Pretrain/Loss (Raw)": 2.003504514694214, "Pretrain/Step": 4051, "Pretrain/Step Time": 8.4888900462538} +{"Pretrain/Learning Rate": 3.219056404525409e-05, "Pretrain/Loss": 2.0290565490722656, "Pretrain/Loss (Raw)": 2.057448148727417, "Pretrain/Step": 4052, "Pretrain/Step Time": 8.491258600726724} +{"Pretrain/Learning Rate": 3.218243162796638e-05, "Pretrain/Loss": 2.0285863876342773, "Pretrain/Loss (Raw)": 2.1083285808563232, "Pretrain/Step": 4053, "Pretrain/Step Time": 8.48913667537272} +{"Pretrain/Learning Rate": 3.217429838218769e-05, "Pretrain/Loss": 2.027801275253296, "Pretrain/Loss (Raw)": 2.103646993637085, "Pretrain/Step": 4054, "Pretrain/Step Time": 8.492537939921021} +{"Pretrain/Learning Rate": 3.2166164308856224e-05, "Pretrain/Loss": 2.0276007652282715, "Pretrain/Loss (Raw)": 1.9929627180099487, "Pretrain/Step": 4055, "Pretrain/Step Time": 8.492129694670439} +{"Pretrain/Learning Rate": 3.215802940891021e-05, "Pretrain/Loss": 2.028343439102173, "Pretrain/Loss (Raw)": 2.2200326919555664, "Pretrain/Step": 4056, "Pretrain/Step Time": 8.49054492637515} +{"Pretrain/Learning Rate": 3.2149893683288024e-05, "Pretrain/Loss": 2.0242700576782227, "Pretrain/Loss (Raw)": 1.7749582529067993, "Pretrain/Step": 4057, "Pretrain/Step Time": 8.492385698482394} +{"Pretrain/Learning Rate": 3.214175713292811e-05, "Pretrain/Loss": 2.022829532623291, "Pretrain/Loss (Raw)": 1.969566822052002, "Pretrain/Step": 4058, "Pretrain/Step Time": 8.494176555424929} +{"Pretrain/Learning Rate": 3.213361975876902e-05, "Pretrain/Loss": 2.019930362701416, "Pretrain/Loss (Raw)": 1.9717373847961426, "Pretrain/Step": 4059, "Pretrain/Step Time": 8.490078952163458} +{"Pretrain/Learning Rate": 3.21254815617494e-05, "Pretrain/Loss": 2.0197675228118896, "Pretrain/Loss (Raw)": 2.057427406311035, "Pretrain/Step": 4060, "Pretrain/Step Time": 8.487183472141623} +{"Pretrain/Learning Rate": 3.211734254280799e-05, "Pretrain/Loss": 2.0191240310668945, "Pretrain/Loss (Raw)": 2.0398104190826416, "Pretrain/Step": 4061, "Pretrain/Step Time": 8.485291367396712} +{"Pretrain/Learning Rate": 3.210920270288362e-05, "Pretrain/Loss": 2.019350528717041, "Pretrain/Loss (Raw)": 1.8430778980255127, "Pretrain/Step": 4062, "Pretrain/Step Time": 8.484437646344304} +{"Pretrain/Learning Rate": 3.2101062042915215e-05, "Pretrain/Loss": 2.021606922149658, "Pretrain/Loss (Raw)": 2.2358620166778564, "Pretrain/Step": 4063, "Pretrain/Step Time": 8.488297276198864} +{"Pretrain/Learning Rate": 3.209292056384179e-05, "Pretrain/Loss": 2.0245721340179443, "Pretrain/Loss (Raw)": 2.1347835063934326, "Pretrain/Step": 4064, "Pretrain/Step Time": 8.48578949086368} +{"Pretrain/Learning Rate": 3.2084778266602476e-05, "Pretrain/Loss": 2.0260772705078125, "Pretrain/Loss (Raw)": 2.2149903774261475, "Pretrain/Step": 4065, "Pretrain/Step Time": 8.485268650576472} +{"Pretrain/Learning Rate": 3.207663515213648e-05, "Pretrain/Loss": 2.02616548538208, "Pretrain/Loss (Raw)": 2.0156657695770264, "Pretrain/Step": 4066, "Pretrain/Step Time": 8.48107773810625} +{"Pretrain/Learning Rate": 3.206849122138311e-05, "Pretrain/Loss": 2.0267913341522217, "Pretrain/Loss (Raw)": 2.1415600776672363, "Pretrain/Step": 4067, "Pretrain/Step Time": 8.47497041709721} +{"Pretrain/Learning Rate": 3.2060346475281755e-05, "Pretrain/Loss": 2.026931047439575, "Pretrain/Loss (Raw)": 1.9002567529678345, "Pretrain/Step": 4068, "Pretrain/Step Time": 8.476866388693452} +{"Pretrain/Learning Rate": 3.205220091477191e-05, "Pretrain/Loss": 2.027853012084961, "Pretrain/Loss (Raw)": 2.0760865211486816, "Pretrain/Step": 4069, "Pretrain/Step Time": 8.474275764077902} +{"Pretrain/Learning Rate": 3.204405454079318e-05, "Pretrain/Loss": 2.0278210639953613, "Pretrain/Loss (Raw)": 2.062950372695923, "Pretrain/Step": 4070, "Pretrain/Step Time": 8.47588043473661} +{"Pretrain/Learning Rate": 3.2035907354285234e-05, "Pretrain/Loss": 2.026078701019287, "Pretrain/Loss (Raw)": 1.9819250106811523, "Pretrain/Step": 4071, "Pretrain/Step Time": 8.482185289263725} +{"Pretrain/Learning Rate": 3.2027759356187844e-05, "Pretrain/Loss": 2.028184652328491, "Pretrain/Loss (Raw)": 2.180039167404175, "Pretrain/Step": 4072, "Pretrain/Step Time": 8.483836093917489} +{"Pretrain/Learning Rate": 3.201961054744088e-05, "Pretrain/Loss": 2.026233196258545, "Pretrain/Loss (Raw)": 1.8190555572509766, "Pretrain/Step": 4073, "Pretrain/Step Time": 8.483440905809402} +{"Pretrain/Learning Rate": 3.201146092898431e-05, "Pretrain/Loss": 2.025268077850342, "Pretrain/Loss (Raw)": 1.9602530002593994, "Pretrain/Step": 4074, "Pretrain/Step Time": 8.481410030275583} +{"Pretrain/Learning Rate": 3.2003310501758174e-05, "Pretrain/Loss": 2.025684356689453, "Pretrain/Loss (Raw)": 2.030669689178467, "Pretrain/Step": 4075, "Pretrain/Step Time": 8.478637849912047} +{"Pretrain/Learning Rate": 3.1995159266702644e-05, "Pretrain/Loss": 2.024172306060791, "Pretrain/Loss (Raw)": 1.9765548706054688, "Pretrain/Step": 4076, "Pretrain/Step Time": 8.480363667011261} +{"Pretrain/Learning Rate": 3.1987007224757946e-05, "Pretrain/Loss": 2.024355173110962, "Pretrain/Loss (Raw)": 2.033942937850952, "Pretrain/Step": 4077, "Pretrain/Step Time": 8.479734178632498} +{"Pretrain/Learning Rate": 3.197885437686443e-05, "Pretrain/Loss": 2.0235533714294434, "Pretrain/Loss (Raw)": 1.9909999370574951, "Pretrain/Step": 4078, "Pretrain/Step Time": 8.48271339200437} +{"Pretrain/Learning Rate": 3.1970700723962504e-05, "Pretrain/Loss": 2.0256800651550293, "Pretrain/Loss (Raw)": 2.2671148777008057, "Pretrain/Step": 4079, "Pretrain/Step Time": 8.481106719002128} +{"Pretrain/Learning Rate": 3.1962546266992696e-05, "Pretrain/Loss": 2.0283360481262207, "Pretrain/Loss (Raw)": 2.15836238861084, "Pretrain/Step": 4080, "Pretrain/Step Time": 8.480356000363827} +{"Pretrain/Learning Rate": 3.1954391006895637e-05, "Pretrain/Loss": 2.0278804302215576, "Pretrain/Loss (Raw)": 1.9867582321166992, "Pretrain/Step": 4081, "Pretrain/Step Time": 8.47731213644147} +{"Pretrain/Learning Rate": 3.1946234944612006e-05, "Pretrain/Loss": 2.0239953994750977, "Pretrain/Loss (Raw)": 1.5376851558685303, "Pretrain/Step": 4082, "Pretrain/Step Time": 8.477120829746127} +{"Pretrain/Learning Rate": 3.193807808108262e-05, "Pretrain/Loss": 2.022722005844116, "Pretrain/Loss (Raw)": 1.9397690296173096, "Pretrain/Step": 4083, "Pretrain/Step Time": 8.477982046082616} +{"Pretrain/Learning Rate": 3.1929920417248364e-05, "Pretrain/Loss": 2.021994113922119, "Pretrain/Loss (Raw)": 2.002413272857666, "Pretrain/Step": 4084, "Pretrain/Step Time": 8.474479328840971} +{"Pretrain/Learning Rate": 3.192176195405023e-05, "Pretrain/Loss": 2.022390365600586, "Pretrain/Loss (Raw)": 2.0354535579681396, "Pretrain/Step": 4085, "Pretrain/Step Time": 8.474155133590102} +{"Pretrain/Learning Rate": 3.191360269242928e-05, "Pretrain/Loss": 2.020122528076172, "Pretrain/Loss (Raw)": 1.965414047241211, "Pretrain/Step": 4086, "Pretrain/Step Time": 8.477219976484776} +{"Pretrain/Learning Rate": 3.190544263332669e-05, "Pretrain/Loss": 2.0189943313598633, "Pretrain/Loss (Raw)": 2.1353702545166016, "Pretrain/Step": 4087, "Pretrain/Step Time": 8.47648903541267} +{"Pretrain/Learning Rate": 3.1897281777683715e-05, "Pretrain/Loss": 2.017826557159424, "Pretrain/Loss (Raw)": 1.9060548543930054, "Pretrain/Step": 4088, "Pretrain/Step Time": 8.481289433315396} +{"Pretrain/Learning Rate": 3.1889120126441725e-05, "Pretrain/Loss": 2.0184102058410645, "Pretrain/Loss (Raw)": 2.189258098602295, "Pretrain/Step": 4089, "Pretrain/Step Time": 8.478833176195621} +{"Pretrain/Learning Rate": 3.188095768054214e-05, "Pretrain/Loss": 2.0186820030212402, "Pretrain/Loss (Raw)": 2.176983594894409, "Pretrain/Step": 4090, "Pretrain/Step Time": 8.480814369395375} +{"Pretrain/Learning Rate": 3.18727944409265e-05, "Pretrain/Loss": 2.0202786922454834, "Pretrain/Loss (Raw)": 2.102595329284668, "Pretrain/Step": 4091, "Pretrain/Step Time": 8.48218628205359} +{"Pretrain/Learning Rate": 3.186463040853645e-05, "Pretrain/Loss": 2.0171873569488525, "Pretrain/Loss (Raw)": 1.6750462055206299, "Pretrain/Step": 4092, "Pretrain/Step Time": 8.480004684999585} +{"Pretrain/Learning Rate": 3.185646558431368e-05, "Pretrain/Loss": 2.0180342197418213, "Pretrain/Loss (Raw)": 2.220241069793701, "Pretrain/Step": 4093, "Pretrain/Step Time": 8.478710349649191} +{"Pretrain/Learning Rate": 3.184829996920002e-05, "Pretrain/Loss": 2.015256404876709, "Pretrain/Loss (Raw)": 1.869910717010498, "Pretrain/Step": 4094, "Pretrain/Step Time": 8.484985090792179} +{"Pretrain/Learning Rate": 3.184013356413737e-05, "Pretrain/Loss": 2.0144541263580322, "Pretrain/Loss (Raw)": 1.998972773551941, "Pretrain/Step": 4095, "Pretrain/Step Time": 8.483173551037908} +{"Pretrain/Learning Rate": 3.183196637006771e-05, "Pretrain/Loss": 2.0125513076782227, "Pretrain/Loss (Raw)": 1.8493010997772217, "Pretrain/Step": 4096, "Pretrain/Step Time": 8.4831763189286} +{"Pretrain/Learning Rate": 3.1823798387933134e-05, "Pretrain/Loss": 2.012953042984009, "Pretrain/Loss (Raw)": 2.2373735904693604, "Pretrain/Step": 4097, "Pretrain/Step Time": 8.483816945925355} +{"Pretrain/Learning Rate": 3.181562961867581e-05, "Pretrain/Loss": 2.0136165618896484, "Pretrain/Loss (Raw)": 2.1591954231262207, "Pretrain/Step": 4098, "Pretrain/Step Time": 8.481098297983408} +{"Pretrain/Learning Rate": 3.1807460063238e-05, "Pretrain/Loss": 2.013235092163086, "Pretrain/Loss (Raw)": 1.9514590501785278, "Pretrain/Step": 4099, "Pretrain/Step Time": 8.478234058246017} +{"Pretrain/Learning Rate": 3.1799289722562075e-05, "Pretrain/Loss": 2.0124030113220215, "Pretrain/Loss (Raw)": 2.0828006267547607, "Pretrain/Step": 4100, "Pretrain/Step Time": 8.478121479973197} +{"Pretrain/Learning Rate": 3.179111859759046e-05, "Pretrain/Loss": 2.013453722000122, "Pretrain/Loss (Raw)": 2.0547213554382324, "Pretrain/Step": 4101, "Pretrain/Step Time": 8.478656815364957} +{"Pretrain/Learning Rate": 3.178294668926571e-05, "Pretrain/Loss": 2.011720657348633, "Pretrain/Loss (Raw)": 1.8691458702087402, "Pretrain/Step": 4102, "Pretrain/Step Time": 8.48392828181386} +{"Pretrain/Learning Rate": 3.177477399853045e-05, "Pretrain/Loss": 2.012192964553833, "Pretrain/Loss (Raw)": 2.0803534984588623, "Pretrain/Step": 4103, "Pretrain/Step Time": 8.483213152736425} +{"Pretrain/Learning Rate": 3.176660052632737e-05, "Pretrain/Loss": 2.012528419494629, "Pretrain/Loss (Raw)": 2.0322489738464355, "Pretrain/Step": 4104, "Pretrain/Step Time": 8.476704547181726} +{"Pretrain/Learning Rate": 3.1758426273599315e-05, "Pretrain/Loss": 2.012402296066284, "Pretrain/Loss (Raw)": 2.0342533588409424, "Pretrain/Step": 4105, "Pretrain/Step Time": 8.476676687598228} +{"Pretrain/Learning Rate": 3.1750251241289145e-05, "Pretrain/Loss": 2.0134174823760986, "Pretrain/Loss (Raw)": 2.09495210647583, "Pretrain/Step": 4106, "Pretrain/Step Time": 8.478353606536984} +{"Pretrain/Learning Rate": 3.174207543033988e-05, "Pretrain/Loss": 2.013552665710449, "Pretrain/Loss (Raw)": 2.0788168907165527, "Pretrain/Step": 4107, "Pretrain/Step Time": 8.471871687099338} +{"Pretrain/Learning Rate": 3.173389884169458e-05, "Pretrain/Loss": 2.014465808868408, "Pretrain/Loss (Raw)": 1.972671389579773, "Pretrain/Step": 4108, "Pretrain/Step Time": 8.473035492002964} +{"Pretrain/Learning Rate": 3.1725721476296416e-05, "Pretrain/Loss": 2.011624813079834, "Pretrain/Loss (Raw)": 1.8602898120880127, "Pretrain/Step": 4109, "Pretrain/Step Time": 8.471244003623724} +{"Pretrain/Learning Rate": 3.1717543335088646e-05, "Pretrain/Loss": 2.0085067749023438, "Pretrain/Loss (Raw)": 1.6073594093322754, "Pretrain/Step": 4110, "Pretrain/Step Time": 8.470563061535358} +{"Pretrain/Learning Rate": 3.1709364419014615e-05, "Pretrain/Loss": 2.008929491043091, "Pretrain/Loss (Raw)": 2.1315934658050537, "Pretrain/Step": 4111, "Pretrain/Step Time": 8.476465966552496} +{"Pretrain/Learning Rate": 3.170118472901775e-05, "Pretrain/Loss": 2.008798599243164, "Pretrain/Loss (Raw)": 2.0624353885650635, "Pretrain/Step": 4112, "Pretrain/Step Time": 8.474344516173005} +{"Pretrain/Learning Rate": 3.1693004266041584e-05, "Pretrain/Loss": 2.0078206062316895, "Pretrain/Loss (Raw)": 2.006965398788452, "Pretrain/Step": 4113, "Pretrain/Step Time": 8.473548291251063} +{"Pretrain/Learning Rate": 3.168482303102972e-05, "Pretrain/Loss": 2.005276679992676, "Pretrain/Loss (Raw)": 1.910244345664978, "Pretrain/Step": 4114, "Pretrain/Step Time": 8.475147653371096} +{"Pretrain/Learning Rate": 3.1676641024925875e-05, "Pretrain/Loss": 2.0048227310180664, "Pretrain/Loss (Raw)": 2.0409462451934814, "Pretrain/Step": 4115, "Pretrain/Step Time": 8.470538355410099} +{"Pretrain/Learning Rate": 3.166845824867384e-05, "Pretrain/Loss": 2.0055501461029053, "Pretrain/Loss (Raw)": 2.0103394985198975, "Pretrain/Step": 4116, "Pretrain/Step Time": 8.471559938043356} +{"Pretrain/Learning Rate": 3.166027470321748e-05, "Pretrain/Loss": 2.0061020851135254, "Pretrain/Loss (Raw)": 2.1753053665161133, "Pretrain/Step": 4117, "Pretrain/Step Time": 8.471634520217776} +{"Pretrain/Learning Rate": 3.1652090389500776e-05, "Pretrain/Loss": 2.0070650577545166, "Pretrain/Loss (Raw)": 2.089890241622925, "Pretrain/Step": 4118, "Pretrain/Step Time": 8.476278876885772} +{"Pretrain/Learning Rate": 3.164390530846779e-05, "Pretrain/Loss": 2.006535768508911, "Pretrain/Loss (Raw)": 2.025099277496338, "Pretrain/Step": 4119, "Pretrain/Step Time": 8.482503531500697} +{"Pretrain/Learning Rate": 3.163571946106265e-05, "Pretrain/Loss": 2.0066654682159424, "Pretrain/Loss (Raw)": 2.0732274055480957, "Pretrain/Step": 4120, "Pretrain/Step Time": 8.48019497282803} +{"Pretrain/Learning Rate": 3.162753284822962e-05, "Pretrain/Loss": 2.005734443664551, "Pretrain/Loss (Raw)": 1.89249587059021, "Pretrain/Step": 4121, "Pretrain/Step Time": 8.48328128643334} +{"Pretrain/Learning Rate": 3.161934547091299e-05, "Pretrain/Loss": 2.004481792449951, "Pretrain/Loss (Raw)": 2.1017322540283203, "Pretrain/Step": 4122, "Pretrain/Step Time": 8.482962539419532} +{"Pretrain/Learning Rate": 3.1611157330057185e-05, "Pretrain/Loss": 2.0024986267089844, "Pretrain/Loss (Raw)": 1.8825596570968628, "Pretrain/Step": 4123, "Pretrain/Step Time": 8.482165183871984} +{"Pretrain/Learning Rate": 3.160296842660671e-05, "Pretrain/Loss": 2.001906394958496, "Pretrain/Loss (Raw)": 2.018195867538452, "Pretrain/Step": 4124, "Pretrain/Step Time": 8.484620600938797} +{"Pretrain/Learning Rate": 3.159477876150615e-05, "Pretrain/Loss": 1.9984583854675293, "Pretrain/Loss (Raw)": 1.7523529529571533, "Pretrain/Step": 4125, "Pretrain/Step Time": 8.482881987467408} +{"Pretrain/Learning Rate": 3.158658833570017e-05, "Pretrain/Loss": 1.9977396726608276, "Pretrain/Loss (Raw)": 1.951846957206726, "Pretrain/Step": 4126, "Pretrain/Step Time": 8.48591136932373} +{"Pretrain/Learning Rate": 3.157839715013355e-05, "Pretrain/Loss": 1.9990234375, "Pretrain/Loss (Raw)": 2.0712103843688965, "Pretrain/Step": 4127, "Pretrain/Step Time": 8.487933859229088} +{"Pretrain/Learning Rate": 3.1570205205751125e-05, "Pretrain/Loss": 1.9972773790359497, "Pretrain/Loss (Raw)": 1.7572910785675049, "Pretrain/Step": 4128, "Pretrain/Step Time": 8.490979623049498} +{"Pretrain/Learning Rate": 3.156201250349784e-05, "Pretrain/Loss": 1.9943573474884033, "Pretrain/Loss (Raw)": 1.801046371459961, "Pretrain/Step": 4129, "Pretrain/Step Time": 8.487140921875834} +{"Pretrain/Learning Rate": 3.155381904431872e-05, "Pretrain/Loss": 1.9970176219940186, "Pretrain/Loss (Raw)": 2.1463277339935303, "Pretrain/Step": 4130, "Pretrain/Step Time": 8.487776581197977} +{"Pretrain/Learning Rate": 3.154562482915887e-05, "Pretrain/Loss": 1.9971768856048584, "Pretrain/Loss (Raw)": 2.033031940460205, "Pretrain/Step": 4131, "Pretrain/Step Time": 8.48898109793663} +{"Pretrain/Learning Rate": 3.15374298589635e-05, "Pretrain/Loss": 1.9958279132843018, "Pretrain/Loss (Raw)": 1.8733060359954834, "Pretrain/Step": 4132, "Pretrain/Step Time": 8.489764844998717} +{"Pretrain/Learning Rate": 3.1529234134677896e-05, "Pretrain/Loss": 1.996155023574829, "Pretrain/Loss (Raw)": 2.0309503078460693, "Pretrain/Step": 4133, "Pretrain/Step Time": 8.486000135540962} +{"Pretrain/Learning Rate": 3.152103765724743e-05, "Pretrain/Loss": 1.9967173337936401, "Pretrain/Loss (Raw)": 2.1731929779052734, "Pretrain/Step": 4134, "Pretrain/Step Time": 8.486305246129632} +{"Pretrain/Learning Rate": 3.151284042761755e-05, "Pretrain/Loss": 1.9966177940368652, "Pretrain/Loss (Raw)": 2.065030574798584, "Pretrain/Step": 4135, "Pretrain/Step Time": 8.493504701182246} +{"Pretrain/Learning Rate": 3.150464244673383e-05, "Pretrain/Loss": 1.9967474937438965, "Pretrain/Loss (Raw)": 1.9085617065429688, "Pretrain/Step": 4136, "Pretrain/Step Time": 8.495911169797182} +{"Pretrain/Learning Rate": 3.149644371554189e-05, "Pretrain/Loss": 1.9986109733581543, "Pretrain/Loss (Raw)": 2.0152716636657715, "Pretrain/Step": 4137, "Pretrain/Step Time": 8.497393535450101} +{"Pretrain/Learning Rate": 3.148824423498744e-05, "Pretrain/Loss": 1.9988250732421875, "Pretrain/Loss (Raw)": 2.1058454513549805, "Pretrain/Step": 4138, "Pretrain/Step Time": 8.49563884921372} +{"Pretrain/Learning Rate": 3.14800440060163e-05, "Pretrain/Loss": 2.0005693435668945, "Pretrain/Loss (Raw)": 2.110496759414673, "Pretrain/Step": 4139, "Pretrain/Step Time": 8.495760258287191} +{"Pretrain/Learning Rate": 3.147184302957436e-05, "Pretrain/Loss": 1.9990267753601074, "Pretrain/Loss (Raw)": 1.8090143203735352, "Pretrain/Step": 4140, "Pretrain/Step Time": 8.498904157429934} +{"Pretrain/Learning Rate": 3.1463641306607604e-05, "Pretrain/Loss": 1.9985346794128418, "Pretrain/Loss (Raw)": 1.9234739542007446, "Pretrain/Step": 4141, "Pretrain/Step Time": 8.497602017596364} +{"Pretrain/Learning Rate": 3.14554388380621e-05, "Pretrain/Loss": 1.9998037815093994, "Pretrain/Loss (Raw)": 2.1688649654388428, "Pretrain/Step": 4142, "Pretrain/Step Time": 8.495686469599605} +{"Pretrain/Learning Rate": 3.144723562488398e-05, "Pretrain/Loss": 1.9986283779144287, "Pretrain/Loss (Raw)": 2.00085186958313, "Pretrain/Step": 4143, "Pretrain/Step Time": 8.49722827412188} +{"Pretrain/Learning Rate": 3.143903166801951e-05, "Pretrain/Loss": 2.0002288818359375, "Pretrain/Loss (Raw)": 2.0932328701019287, "Pretrain/Step": 4144, "Pretrain/Step Time": 8.494749914854765} +{"Pretrain/Learning Rate": 3.1430826968415e-05, "Pretrain/Loss": 2.000725746154785, "Pretrain/Loss (Raw)": 2.10982608795166, "Pretrain/Step": 4145, "Pretrain/Step Time": 8.492459896951914} +{"Pretrain/Learning Rate": 3.142262152701685e-05, "Pretrain/Loss": 2.0027525424957275, "Pretrain/Loss (Raw)": 2.3076748847961426, "Pretrain/Step": 4146, "Pretrain/Step Time": 8.493647592142224} +{"Pretrain/Learning Rate": 3.141441534477158e-05, "Pretrain/Loss": 2.00197172164917, "Pretrain/Loss (Raw)": 1.9966009855270386, "Pretrain/Step": 4147, "Pretrain/Step Time": 8.495562000200152} +{"Pretrain/Learning Rate": 3.140620842262573e-05, "Pretrain/Loss": 2.0018136501312256, "Pretrain/Loss (Raw)": 2.021972179412842, "Pretrain/Step": 4148, "Pretrain/Step Time": 8.487483359873295} +{"Pretrain/Learning Rate": 3.1398000761526e-05, "Pretrain/Loss": 2.004997730255127, "Pretrain/Loss (Raw)": 2.0656065940856934, "Pretrain/Step": 4149, "Pretrain/Step Time": 8.484670259058475} +{"Pretrain/Learning Rate": 3.138979236241914e-05, "Pretrain/Loss": 2.005880355834961, "Pretrain/Loss (Raw)": 2.0468978881835938, "Pretrain/Step": 4150, "Pretrain/Step Time": 8.488212192431092} +{"Pretrain/Learning Rate": 3.1381583226251965e-05, "Pretrain/Loss": 2.008655071258545, "Pretrain/Loss (Raw)": 2.102351427078247, "Pretrain/Step": 4151, "Pretrain/Step Time": 8.487030988559127} +{"Pretrain/Learning Rate": 3.1373373353971416e-05, "Pretrain/Loss": 2.00883150100708, "Pretrain/Loss (Raw)": 2.0391011238098145, "Pretrain/Step": 4152, "Pretrain/Step Time": 8.488136008381844} +{"Pretrain/Learning Rate": 3.136516274652449e-05, "Pretrain/Loss": 2.0085747241973877, "Pretrain/Loss (Raw)": 2.0135133266448975, "Pretrain/Step": 4153, "Pretrain/Step Time": 8.489444257691503} +{"Pretrain/Learning Rate": 3.135695140485827e-05, "Pretrain/Loss": 2.0103020668029785, "Pretrain/Loss (Raw)": 1.966434121131897, "Pretrain/Step": 4154, "Pretrain/Step Time": 8.490208897739649} +{"Pretrain/Learning Rate": 3.134873932991995e-05, "Pretrain/Loss": 2.0103766918182373, "Pretrain/Loss (Raw)": 1.9896231889724731, "Pretrain/Step": 4155, "Pretrain/Step Time": 8.487412124872208} +{"Pretrain/Learning Rate": 3.134052652265677e-05, "Pretrain/Loss": 2.0097556114196777, "Pretrain/Loss (Raw)": 1.9075027704238892, "Pretrain/Step": 4156, "Pretrain/Step Time": 8.489226115867496} +{"Pretrain/Learning Rate": 3.133231298401608e-05, "Pretrain/Loss": 2.009512424468994, "Pretrain/Loss (Raw)": 1.9010984897613525, "Pretrain/Step": 4157, "Pretrain/Step Time": 8.489058123901486} +{"Pretrain/Learning Rate": 3.132409871494533e-05, "Pretrain/Loss": 2.0098958015441895, "Pretrain/Loss (Raw)": 1.985897183418274, "Pretrain/Step": 4158, "Pretrain/Step Time": 8.490845914930105} +{"Pretrain/Learning Rate": 3.1315883716392e-05, "Pretrain/Loss": 2.0128860473632812, "Pretrain/Loss (Raw)": 2.1545982360839844, "Pretrain/Step": 4159, "Pretrain/Step Time": 8.490797821432352} +{"Pretrain/Learning Rate": 3.130766798930371e-05, "Pretrain/Loss": 2.0119590759277344, "Pretrain/Loss (Raw)": 1.9344565868377686, "Pretrain/Step": 4160, "Pretrain/Step Time": 8.489622769877315} +{"Pretrain/Learning Rate": 3.1299451534628135e-05, "Pretrain/Loss": 2.009000539779663, "Pretrain/Loss (Raw)": 1.724007248878479, "Pretrain/Step": 4161, "Pretrain/Step Time": 8.495652373880148} +{"Pretrain/Learning Rate": 3.129123435331304e-05, "Pretrain/Loss": 2.008584499359131, "Pretrain/Loss (Raw)": 1.8939127922058105, "Pretrain/Step": 4162, "Pretrain/Step Time": 8.494470464065671} +{"Pretrain/Learning Rate": 3.128301644630627e-05, "Pretrain/Loss": 2.0099024772644043, "Pretrain/Loss (Raw)": 1.8689862489700317, "Pretrain/Step": 4163, "Pretrain/Step Time": 8.494472369551659} +{"Pretrain/Learning Rate": 3.127479781455576e-05, "Pretrain/Loss": 2.0086960792541504, "Pretrain/Loss (Raw)": 2.0171751976013184, "Pretrain/Step": 4164, "Pretrain/Step Time": 8.4935418702662} +{"Pretrain/Learning Rate": 3.126657845900952e-05, "Pretrain/Loss": 2.0094428062438965, "Pretrain/Loss (Raw)": 2.1915972232818604, "Pretrain/Step": 4165, "Pretrain/Step Time": 8.487122317776084} +{"Pretrain/Learning Rate": 3.125835838061567e-05, "Pretrain/Loss": 2.009643793106079, "Pretrain/Loss (Raw)": 2.0241637229919434, "Pretrain/Step": 4166, "Pretrain/Step Time": 8.489754904061556} +{"Pretrain/Learning Rate": 3.125013758032237e-05, "Pretrain/Loss": 2.0111002922058105, "Pretrain/Loss (Raw)": 2.103903293609619, "Pretrain/Step": 4167, "Pretrain/Step Time": 8.489980867132545} +{"Pretrain/Learning Rate": 3.1241916059077906e-05, "Pretrain/Loss": 2.0102226734161377, "Pretrain/Loss (Raw)": 2.023998260498047, "Pretrain/Step": 4168, "Pretrain/Step Time": 8.489107068628073} +{"Pretrain/Learning Rate": 3.123369381783061e-05, "Pretrain/Loss": 2.007629871368408, "Pretrain/Loss (Raw)": 1.7529481649398804, "Pretrain/Step": 4169, "Pretrain/Step Time": 8.492131436243653} +{"Pretrain/Learning Rate": 3.122547085752893e-05, "Pretrain/Loss": 2.0097174644470215, "Pretrain/Loss (Raw)": 2.1508255004882812, "Pretrain/Step": 4170, "Pretrain/Step Time": 8.492321755737066} +{"Pretrain/Learning Rate": 3.121724717912138e-05, "Pretrain/Loss": 2.009464979171753, "Pretrain/Loss (Raw)": 1.9471498727798462, "Pretrain/Step": 4171, "Pretrain/Step Time": 8.490024270489812} +{"Pretrain/Learning Rate": 3.1209022783556534e-05, "Pretrain/Loss": 2.0103209018707275, "Pretrain/Loss (Raw)": 2.1559433937072754, "Pretrain/Step": 4172, "Pretrain/Step Time": 8.490348795428872} +{"Pretrain/Learning Rate": 3.12007976717831e-05, "Pretrain/Loss": 2.0132808685302734, "Pretrain/Loss (Raw)": 2.059069871902466, "Pretrain/Step": 4173, "Pretrain/Step Time": 8.490216532722116} +{"Pretrain/Learning Rate": 3.119257184474984e-05, "Pretrain/Loss": 2.014498233795166, "Pretrain/Loss (Raw)": 2.149256706237793, "Pretrain/Step": 4174, "Pretrain/Step Time": 8.488279635086656} +{"Pretrain/Learning Rate": 3.118434530340559e-05, "Pretrain/Loss": 2.012970209121704, "Pretrain/Loss (Raw)": 1.7971038818359375, "Pretrain/Step": 4175, "Pretrain/Step Time": 8.474854979664087} +{"Pretrain/Learning Rate": 3.117611804869928e-05, "Pretrain/Loss": 2.0110578536987305, "Pretrain/Loss (Raw)": 1.7912237644195557, "Pretrain/Step": 4176, "Pretrain/Step Time": 8.473047839477658} +{"Pretrain/Learning Rate": 3.116789008157993e-05, "Pretrain/Loss": 2.0104856491088867, "Pretrain/Loss (Raw)": 1.9210872650146484, "Pretrain/Step": 4177, "Pretrain/Step Time": 8.47884770296514} +{"Pretrain/Learning Rate": 3.115966140299662e-05, "Pretrain/Loss": 2.0102038383483887, "Pretrain/Loss (Raw)": 1.9479084014892578, "Pretrain/Step": 4178, "Pretrain/Step Time": 8.478547595441341} +{"Pretrain/Learning Rate": 3.115143201389853e-05, "Pretrain/Loss": 2.0082926750183105, "Pretrain/Loss (Raw)": 1.7588698863983154, "Pretrain/Step": 4179, "Pretrain/Step Time": 8.47906967997551} +{"Pretrain/Learning Rate": 3.114320191523493e-05, "Pretrain/Loss": 2.008439779281616, "Pretrain/Loss (Raw)": 2.0762836933135986, "Pretrain/Step": 4180, "Pretrain/Step Time": 8.477934665977955} +{"Pretrain/Learning Rate": 3.113497110795514e-05, "Pretrain/Loss": 2.0076868534088135, "Pretrain/Loss (Raw)": 2.011939764022827, "Pretrain/Step": 4181, "Pretrain/Step Time": 8.47806727513671} +{"Pretrain/Learning Rate": 3.112673959300859e-05, "Pretrain/Loss": 2.00758695602417, "Pretrain/Loss (Raw)": 2.090885877609253, "Pretrain/Step": 4182, "Pretrain/Step Time": 8.473932391032577} +{"Pretrain/Learning Rate": 3.1118507371344776e-05, "Pretrain/Loss": 2.0088746547698975, "Pretrain/Loss (Raw)": 2.1577789783477783, "Pretrain/Step": 4183, "Pretrain/Step Time": 8.478111695498228} +{"Pretrain/Learning Rate": 3.111027444391329e-05, "Pretrain/Loss": 2.007902145385742, "Pretrain/Loss (Raw)": 2.095555543899536, "Pretrain/Step": 4184, "Pretrain/Step Time": 8.47899616882205} +{"Pretrain/Learning Rate": 3.1102040811663796e-05, "Pretrain/Loss": 2.008787155151367, "Pretrain/Loss (Raw)": 1.8882203102111816, "Pretrain/Step": 4185, "Pretrain/Step Time": 8.480107693001628} +{"Pretrain/Learning Rate": 3.109380647554604e-05, "Pretrain/Loss": 2.0099005699157715, "Pretrain/Loss (Raw)": 2.1121273040771484, "Pretrain/Step": 4186, "Pretrain/Step Time": 8.482827818021178} +{"Pretrain/Learning Rate": 3.108557143650985e-05, "Pretrain/Loss": 2.00999116897583, "Pretrain/Loss (Raw)": 1.9832971096038818, "Pretrain/Step": 4187, "Pretrain/Step Time": 8.484672924503684} +{"Pretrain/Learning Rate": 3.1077335695505127e-05, "Pretrain/Loss": 2.009385585784912, "Pretrain/Loss (Raw)": 1.9799084663391113, "Pretrain/Step": 4188, "Pretrain/Step Time": 8.48694214783609} +{"Pretrain/Learning Rate": 3.1069099253481875e-05, "Pretrain/Loss": 2.0097904205322266, "Pretrain/Loss (Raw)": 2.091637134552002, "Pretrain/Step": 4189, "Pretrain/Step Time": 8.488221628591418} +{"Pretrain/Learning Rate": 3.1060862111390154e-05, "Pretrain/Loss": 2.01088547706604, "Pretrain/Loss (Raw)": 1.9832648038864136, "Pretrain/Step": 4190, "Pretrain/Step Time": 8.49267720989883} +{"Pretrain/Learning Rate": 3.105262427018011e-05, "Pretrain/Loss": 2.008574962615967, "Pretrain/Loss (Raw)": 1.940117359161377, "Pretrain/Step": 4191, "Pretrain/Step Time": 8.488907115533948} +{"Pretrain/Learning Rate": 3.1044385730802e-05, "Pretrain/Loss": 2.0062015056610107, "Pretrain/Loss (Raw)": 1.8309539556503296, "Pretrain/Step": 4192, "Pretrain/Step Time": 8.490762747824192} +{"Pretrain/Learning Rate": 3.10361464942061e-05, "Pretrain/Loss": 2.004932165145874, "Pretrain/Loss (Raw)": 2.0525238513946533, "Pretrain/Step": 4193, "Pretrain/Step Time": 8.490011909976602} +{"Pretrain/Learning Rate": 3.102790656134284e-05, "Pretrain/Loss": 2.0028324127197266, "Pretrain/Loss (Raw)": 1.7469168901443481, "Pretrain/Step": 4194, "Pretrain/Step Time": 8.490758439525962} +{"Pretrain/Learning Rate": 3.1019665933162674e-05, "Pretrain/Loss": 2.002957582473755, "Pretrain/Loss (Raw)": 2.1575613021850586, "Pretrain/Step": 4195, "Pretrain/Step Time": 8.496240332722664} +{"Pretrain/Learning Rate": 3.101142461061615e-05, "Pretrain/Loss": 2.002274513244629, "Pretrain/Loss (Raw)": 1.8128308057785034, "Pretrain/Step": 4196, "Pretrain/Step Time": 8.49385072849691} +{"Pretrain/Learning Rate": 3.1003182594653916e-05, "Pretrain/Loss": 2.0027599334716797, "Pretrain/Loss (Raw)": 2.138225793838501, "Pretrain/Step": 4197, "Pretrain/Step Time": 8.493702359497547} +{"Pretrain/Learning Rate": 3.0994939886226677e-05, "Pretrain/Loss": 2.0051310062408447, "Pretrain/Loss (Raw)": 2.366436719894409, "Pretrain/Step": 4198, "Pretrain/Step Time": 8.497203566133976} +{"Pretrain/Learning Rate": 3.098669648628523e-05, "Pretrain/Loss": 2.0077531337738037, "Pretrain/Loss (Raw)": 2.3175551891326904, "Pretrain/Step": 4199, "Pretrain/Step Time": 8.492295365780592} +{"Pretrain/Learning Rate": 3.0978452395780444e-05, "Pretrain/Loss": 2.0058674812316895, "Pretrain/Loss (Raw)": 1.9386787414550781, "Pretrain/Step": 4200, "Pretrain/Step Time": 8.487915854901075} +{"Pretrain/Learning Rate": 3.097020761566328e-05, "Pretrain/Loss": 2.0077061653137207, "Pretrain/Loss (Raw)": 2.054408073425293, "Pretrain/Step": 4201, "Pretrain/Step Time": 8.490126272663474} +{"Pretrain/Learning Rate": 3.0961962146884765e-05, "Pretrain/Loss": 2.0069899559020996, "Pretrain/Loss (Raw)": 1.8685753345489502, "Pretrain/Step": 4202, "Pretrain/Step Time": 8.492597997188568} +{"Pretrain/Learning Rate": 3.095371599039601e-05, "Pretrain/Loss": 2.0068304538726807, "Pretrain/Loss (Raw)": 2.010258913040161, "Pretrain/Step": 4203, "Pretrain/Step Time": 8.494673257693648} +{"Pretrain/Learning Rate": 3.094546914714821e-05, "Pretrain/Loss": 2.0069568157196045, "Pretrain/Loss (Raw)": 1.9927165508270264, "Pretrain/Step": 4204, "Pretrain/Step Time": 8.495680809020996} +{"Pretrain/Learning Rate": 3.093722161809263e-05, "Pretrain/Loss": 2.0068132877349854, "Pretrain/Loss (Raw)": 2.015578031539917, "Pretrain/Step": 4205, "Pretrain/Step Time": 8.497979266569018} +{"Pretrain/Learning Rate": 3.092897340418062e-05, "Pretrain/Loss": 2.0075244903564453, "Pretrain/Loss (Raw)": 2.0820651054382324, "Pretrain/Step": 4206, "Pretrain/Step Time": 8.490391191095114} +{"Pretrain/Learning Rate": 3.092072450636361e-05, "Pretrain/Loss": 2.0052318572998047, "Pretrain/Loss (Raw)": 1.9736511707305908, "Pretrain/Step": 4207, "Pretrain/Step Time": 8.494435442611575} +{"Pretrain/Learning Rate": 3.091247492559312e-05, "Pretrain/Loss": 2.005695343017578, "Pretrain/Loss (Raw)": 2.217679023742676, "Pretrain/Step": 4208, "Pretrain/Step Time": 8.494929492473602} +{"Pretrain/Learning Rate": 3.090422466282072e-05, "Pretrain/Loss": 2.007417678833008, "Pretrain/Loss (Raw)": 2.207213878631592, "Pretrain/Step": 4209, "Pretrain/Step Time": 8.495584651827812} +{"Pretrain/Learning Rate": 3.089597371899808e-05, "Pretrain/Loss": 2.010708808898926, "Pretrain/Loss (Raw)": 1.9589189291000366, "Pretrain/Step": 4210, "Pretrain/Step Time": 8.497020615264773} +{"Pretrain/Learning Rate": 3.088772209507694e-05, "Pretrain/Loss": 2.0108156204223633, "Pretrain/Loss (Raw)": 1.9534547328948975, "Pretrain/Step": 4211, "Pretrain/Step Time": 8.497880632057786} +{"Pretrain/Learning Rate": 3.087946979200913e-05, "Pretrain/Loss": 2.0100607872009277, "Pretrain/Loss (Raw)": 1.9057931900024414, "Pretrain/Step": 4212, "Pretrain/Step Time": 8.497526062652469} +{"Pretrain/Learning Rate": 3.0871216810746544e-05, "Pretrain/Loss": 2.010251998901367, "Pretrain/Loss (Raw)": 2.05993390083313, "Pretrain/Step": 4213, "Pretrain/Step Time": 8.502104183658957} +{"Pretrain/Learning Rate": 3.0862963152241166e-05, "Pretrain/Loss": 2.010927677154541, "Pretrain/Loss (Raw)": 2.0518887042999268, "Pretrain/Step": 4214, "Pretrain/Step Time": 8.501989861950278} +{"Pretrain/Learning Rate": 3.085470881744504e-05, "Pretrain/Loss": 2.0085127353668213, "Pretrain/Loss (Raw)": 1.8262678384780884, "Pretrain/Step": 4215, "Pretrain/Step Time": 8.502302575856447} +{"Pretrain/Learning Rate": 3.0846453807310316e-05, "Pretrain/Loss": 2.008927822113037, "Pretrain/Loss (Raw)": 1.9591842889785767, "Pretrain/Step": 4216, "Pretrain/Step Time": 8.496720971539617} +{"Pretrain/Learning Rate": 3.0838198122789196e-05, "Pretrain/Loss": 2.0084853172302246, "Pretrain/Loss (Raw)": 2.132610321044922, "Pretrain/Step": 4217, "Pretrain/Step Time": 8.497062481939793} +{"Pretrain/Learning Rate": 3.082994176483398e-05, "Pretrain/Loss": 2.0057687759399414, "Pretrain/Loss (Raw)": 1.8292973041534424, "Pretrain/Step": 4218, "Pretrain/Step Time": 8.496142067015171} +{"Pretrain/Learning Rate": 3.082168473439702e-05, "Pretrain/Loss": 2.0049734115600586, "Pretrain/Loss (Raw)": 2.0007667541503906, "Pretrain/Step": 4219, "Pretrain/Step Time": 8.499477880075574} +{"Pretrain/Learning Rate": 3.0813427032430783e-05, "Pretrain/Loss": 2.0075814723968506, "Pretrain/Loss (Raw)": 2.008859395980835, "Pretrain/Step": 4220, "Pretrain/Step Time": 8.4987389203161} +{"Pretrain/Learning Rate": 3.080516865988778e-05, "Pretrain/Loss": 2.005211591720581, "Pretrain/Loss (Raw)": 1.9169179201126099, "Pretrain/Step": 4221, "Pretrain/Step Time": 8.497431550174952} +{"Pretrain/Learning Rate": 3.0796909617720604e-05, "Pretrain/Loss": 2.0054173469543457, "Pretrain/Loss (Raw)": 1.896236538887024, "Pretrain/Step": 4222, "Pretrain/Step Time": 8.497811643406749} +{"Pretrain/Learning Rate": 3.078864990688194e-05, "Pretrain/Loss": 2.0058162212371826, "Pretrain/Loss (Raw)": 2.0500478744506836, "Pretrain/Step": 4223, "Pretrain/Step Time": 8.497130706906319} +{"Pretrain/Learning Rate": 3.0780389528324554e-05, "Pretrain/Loss": 2.0067906379699707, "Pretrain/Loss (Raw)": 1.9740122556686401, "Pretrain/Step": 4224, "Pretrain/Step Time": 8.49885742366314} +{"Pretrain/Learning Rate": 3.077212848300126e-05, "Pretrain/Loss": 2.0041892528533936, "Pretrain/Loss (Raw)": 1.904412865638733, "Pretrain/Step": 4225, "Pretrain/Step Time": 8.499937418848276} +{"Pretrain/Learning Rate": 3.076386677186498e-05, "Pretrain/Loss": 2.0013699531555176, "Pretrain/Loss (Raw)": 1.7982879877090454, "Pretrain/Step": 4226, "Pretrain/Step Time": 8.501547506079078} +{"Pretrain/Learning Rate": 3.0755604395868686e-05, "Pretrain/Loss": 2.002840280532837, "Pretrain/Loss (Raw)": 2.139678478240967, "Pretrain/Step": 4227, "Pretrain/Step Time": 8.500283712521195} +{"Pretrain/Learning Rate": 3.0747341355965455e-05, "Pretrain/Loss": 2.001396656036377, "Pretrain/Loss (Raw)": 1.898039698600769, "Pretrain/Step": 4228, "Pretrain/Step Time": 8.500422690063715} +{"Pretrain/Learning Rate": 3.073907765310841e-05, "Pretrain/Loss": 2.000861167907715, "Pretrain/Loss (Raw)": 1.9861794710159302, "Pretrain/Step": 4229, "Pretrain/Step Time": 8.499317329376936} +{"Pretrain/Learning Rate": 3.073081328825078e-05, "Pretrain/Loss": 2.0016090869903564, "Pretrain/Loss (Raw)": 1.9648692607879639, "Pretrain/Step": 4230, "Pretrain/Step Time": 8.493942555040121} +{"Pretrain/Learning Rate": 3.072254826234585e-05, "Pretrain/Loss": 2.001734733581543, "Pretrain/Loss (Raw)": 2.0964395999908447, "Pretrain/Step": 4231, "Pretrain/Step Time": 8.494018599390984} +{"Pretrain/Learning Rate": 3.071428257634699e-05, "Pretrain/Loss": 2.0025248527526855, "Pretrain/Loss (Raw)": 2.1333799362182617, "Pretrain/Step": 4232, "Pretrain/Step Time": 8.493617288768291} +{"Pretrain/Learning Rate": 3.0706016231207635e-05, "Pretrain/Loss": 2.0025172233581543, "Pretrain/Loss (Raw)": 2.0332767963409424, "Pretrain/Step": 4233, "Pretrain/Step Time": 8.491594729945064} +{"Pretrain/Learning Rate": 3.069774922788132e-05, "Pretrain/Loss": 2.001293897628784, "Pretrain/Loss (Raw)": 1.9383751153945923, "Pretrain/Step": 4234, "Pretrain/Step Time": 8.490871606394649} +{"Pretrain/Learning Rate": 3.0689481567321634e-05, "Pretrain/Loss": 1.9997010231018066, "Pretrain/Loss (Raw)": 1.87490975856781, "Pretrain/Step": 4235, "Pretrain/Step Time": 8.492773853242397} +{"Pretrain/Learning Rate": 3.0681213250482255e-05, "Pretrain/Loss": 1.9992865324020386, "Pretrain/Loss (Raw)": 1.9196070432662964, "Pretrain/Step": 4236, "Pretrain/Step Time": 8.491367341950536} +{"Pretrain/Learning Rate": 3.0672944278316916e-05, "Pretrain/Loss": 2.000537633895874, "Pretrain/Loss (Raw)": 2.0204505920410156, "Pretrain/Step": 4237, "Pretrain/Step Time": 8.49213670939207} +{"Pretrain/Learning Rate": 3.066467465177945e-05, "Pretrain/Loss": 2.0042991638183594, "Pretrain/Loss (Raw)": 2.0888352394104004, "Pretrain/Step": 4238, "Pretrain/Step Time": 8.493597757071257} +{"Pretrain/Learning Rate": 3.065640437182376e-05, "Pretrain/Loss": 2.0037617683410645, "Pretrain/Loss (Raw)": 2.062784433364868, "Pretrain/Step": 4239, "Pretrain/Step Time": 8.490125944837928} +{"Pretrain/Learning Rate": 3.0648133439403795e-05, "Pretrain/Loss": 2.003650665283203, "Pretrain/Loss (Raw)": 2.048234701156616, "Pretrain/Step": 4240, "Pretrain/Step Time": 8.492071529850364} +{"Pretrain/Learning Rate": 3.0639861855473635e-05, "Pretrain/Loss": 2.0026583671569824, "Pretrain/Loss (Raw)": 1.8799397945404053, "Pretrain/Step": 4241, "Pretrain/Step Time": 8.491627702489495} +{"Pretrain/Learning Rate": 3.0631589620987396e-05, "Pretrain/Loss": 2.0034842491149902, "Pretrain/Loss (Raw)": 2.0159764289855957, "Pretrain/Step": 4242, "Pretrain/Step Time": 8.493036957457662} +{"Pretrain/Learning Rate": 3.062331673689926e-05, "Pretrain/Loss": 2.0042099952697754, "Pretrain/Loss (Raw)": 2.133833169937134, "Pretrain/Step": 4243, "Pretrain/Step Time": 8.495366277173162} +{"Pretrain/Learning Rate": 3.0615043204163524e-05, "Pretrain/Loss": 2.0045552253723145, "Pretrain/Loss (Raw)": 2.054536819458008, "Pretrain/Step": 4244, "Pretrain/Step Time": 8.491539979353547} +{"Pretrain/Learning Rate": 3.0606769023734536e-05, "Pretrain/Loss": 2.003077983856201, "Pretrain/Loss (Raw)": 1.9862014055252075, "Pretrain/Step": 4245, "Pretrain/Step Time": 8.493296397849917} +{"Pretrain/Learning Rate": 3.05984941965667e-05, "Pretrain/Loss": 2.001967430114746, "Pretrain/Loss (Raw)": 1.947750449180603, "Pretrain/Step": 4246, "Pretrain/Step Time": 8.488727578893304} +{"Pretrain/Learning Rate": 3.059021872361453e-05, "Pretrain/Loss": 2.0021145343780518, "Pretrain/Loss (Raw)": 2.043945789337158, "Pretrain/Step": 4247, "Pretrain/Step Time": 8.483472894877195} +{"Pretrain/Learning Rate": 3.058194260583259e-05, "Pretrain/Loss": 2.0017049312591553, "Pretrain/Loss (Raw)": 2.0207924842834473, "Pretrain/Step": 4248, "Pretrain/Step Time": 8.484737960621715} +{"Pretrain/Learning Rate": 3.057366584417553e-05, "Pretrain/Loss": 2.0026025772094727, "Pretrain/Loss (Raw)": 2.0073907375335693, "Pretrain/Step": 4249, "Pretrain/Step Time": 8.482294568791986} +{"Pretrain/Learning Rate": 3.056538843959808e-05, "Pretrain/Loss": 2.0023574829101562, "Pretrain/Loss (Raw)": 2.0703518390655518, "Pretrain/Step": 4250, "Pretrain/Step Time": 8.481941295787692} +{"Pretrain/Learning Rate": 3.055711039305503e-05, "Pretrain/Loss": 2.0044302940368652, "Pretrain/Loss (Raw)": 2.147866725921631, "Pretrain/Step": 4251, "Pretrain/Step Time": 8.483112007379532} +{"Pretrain/Learning Rate": 3.054883170550125e-05, "Pretrain/Loss": 2.004889488220215, "Pretrain/Loss (Raw)": 2.0769670009613037, "Pretrain/Step": 4252, "Pretrain/Step Time": 8.484830072149634} +{"Pretrain/Learning Rate": 3.054055237789167e-05, "Pretrain/Loss": 2.0076146125793457, "Pretrain/Loss (Raw)": 2.1011955738067627, "Pretrain/Step": 4253, "Pretrain/Step Time": 8.482628263533115} +{"Pretrain/Learning Rate": 3.053227241118134e-05, "Pretrain/Loss": 2.008523464202881, "Pretrain/Loss (Raw)": 2.068190813064575, "Pretrain/Step": 4254, "Pretrain/Step Time": 8.480263521894813} +{"Pretrain/Learning Rate": 3.0523991806325326e-05, "Pretrain/Loss": 2.0083651542663574, "Pretrain/Loss (Raw)": 2.050902843475342, "Pretrain/Step": 4255, "Pretrain/Step Time": 8.477541720494628} +{"Pretrain/Learning Rate": 3.0515710564278788e-05, "Pretrain/Loss": 2.0108602046966553, "Pretrain/Loss (Raw)": 2.0766899585723877, "Pretrain/Step": 4256, "Pretrain/Step Time": 8.477504467591643} +{"Pretrain/Learning Rate": 3.050742868599698e-05, "Pretrain/Loss": 2.0125105381011963, "Pretrain/Loss (Raw)": 2.012277841567993, "Pretrain/Step": 4257, "Pretrain/Step Time": 8.477354986593127} +{"Pretrain/Learning Rate": 3.049914617243521e-05, "Pretrain/Loss": 2.011791944503784, "Pretrain/Loss (Raw)": 2.0543477535247803, "Pretrain/Step": 4258, "Pretrain/Step Time": 8.48026367276907} +{"Pretrain/Learning Rate": 3.049086302454886e-05, "Pretrain/Loss": 2.012073278427124, "Pretrain/Loss (Raw)": 2.0690407752990723, "Pretrain/Step": 4259, "Pretrain/Step Time": 8.478268079459667} +{"Pretrain/Learning Rate": 3.048257924329339e-05, "Pretrain/Loss": 2.0123910903930664, "Pretrain/Loss (Raw)": 1.9139975309371948, "Pretrain/Step": 4260, "Pretrain/Step Time": 8.478043880313635} +{"Pretrain/Learning Rate": 3.0474294829624327e-05, "Pretrain/Loss": 2.011218547821045, "Pretrain/Loss (Raw)": 1.8808881044387817, "Pretrain/Step": 4261, "Pretrain/Step Time": 8.477625602856278} +{"Pretrain/Learning Rate": 3.046600978449729e-05, "Pretrain/Loss": 2.0104217529296875, "Pretrain/Loss (Raw)": 2.071154832839966, "Pretrain/Step": 4262, "Pretrain/Step Time": 8.478540496900678} +{"Pretrain/Learning Rate": 3.0457724108867942e-05, "Pretrain/Loss": 2.0109636783599854, "Pretrain/Loss (Raw)": 2.1344313621520996, "Pretrain/Step": 4263, "Pretrain/Step Time": 8.472777603194118} +{"Pretrain/Learning Rate": 3.044943780369203e-05, "Pretrain/Loss": 2.01273512840271, "Pretrain/Loss (Raw)": 2.1352906227111816, "Pretrain/Step": 4264, "Pretrain/Step Time": 8.47279836051166} +{"Pretrain/Learning Rate": 3.0441150869925384e-05, "Pretrain/Loss": 2.013288974761963, "Pretrain/Loss (Raw)": 2.0861656665802, "Pretrain/Step": 4265, "Pretrain/Step Time": 8.47639117948711} +{"Pretrain/Learning Rate": 3.04328633085239e-05, "Pretrain/Loss": 2.0116071701049805, "Pretrain/Loss (Raw)": 1.8905686140060425, "Pretrain/Step": 4266, "Pretrain/Step Time": 8.475844519212842} +{"Pretrain/Learning Rate": 3.0424575120443537e-05, "Pretrain/Loss": 2.0104992389678955, "Pretrain/Loss (Raw)": 1.9686689376831055, "Pretrain/Step": 4267, "Pretrain/Step Time": 8.475111175328493} +{"Pretrain/Learning Rate": 3.041628630664035e-05, "Pretrain/Loss": 2.0114235877990723, "Pretrain/Loss (Raw)": 1.9273394346237183, "Pretrain/Step": 4268, "Pretrain/Step Time": 8.474734915420413} +{"Pretrain/Learning Rate": 3.0407996868070433e-05, "Pretrain/Loss": 2.0111782550811768, "Pretrain/Loss (Raw)": 1.8920972347259521, "Pretrain/Step": 4269, "Pretrain/Step Time": 8.47406823001802} +{"Pretrain/Learning Rate": 3.039970680568998e-05, "Pretrain/Loss": 2.010920524597168, "Pretrain/Loss (Raw)": 2.1358354091644287, "Pretrain/Step": 4270, "Pretrain/Step Time": 8.474633978679776} +{"Pretrain/Learning Rate": 3.0391416120455253e-05, "Pretrain/Loss": 2.012725353240967, "Pretrain/Loss (Raw)": 2.231877565383911, "Pretrain/Step": 4271, "Pretrain/Step Time": 8.473488913848996} +{"Pretrain/Learning Rate": 3.0383124813322557e-05, "Pretrain/Loss": 2.0116701126098633, "Pretrain/Loss (Raw)": 1.958163857460022, "Pretrain/Step": 4272, "Pretrain/Step Time": 8.472228616476059} +{"Pretrain/Learning Rate": 3.0374832885248313e-05, "Pretrain/Loss": 2.0106186866760254, "Pretrain/Loss (Raw)": 1.9752602577209473, "Pretrain/Step": 4273, "Pretrain/Step Time": 8.476486679166555} +{"Pretrain/Learning Rate": 3.036654033718898e-05, "Pretrain/Loss": 2.0087482929229736, "Pretrain/Loss (Raw)": 2.0682742595672607, "Pretrain/Step": 4274, "Pretrain/Step Time": 8.474627925083041} +{"Pretrain/Learning Rate": 3.0358247170101108e-05, "Pretrain/Loss": 2.0092318058013916, "Pretrain/Loss (Raw)": 2.0584635734558105, "Pretrain/Step": 4275, "Pretrain/Step Time": 8.476266242563725} +{"Pretrain/Learning Rate": 3.034995338494131e-05, "Pretrain/Loss": 2.0108628273010254, "Pretrain/Loss (Raw)": 2.2307510375976562, "Pretrain/Step": 4276, "Pretrain/Step Time": 8.478280263021588} +{"Pretrain/Learning Rate": 3.0341658982666266e-05, "Pretrain/Loss": 2.006075620651245, "Pretrain/Loss (Raw)": 1.452857494354248, "Pretrain/Step": 4277, "Pretrain/Step Time": 8.479978678748012} +{"Pretrain/Learning Rate": 3.0333363964232738e-05, "Pretrain/Loss": 2.0062360763549805, "Pretrain/Loss (Raw)": 2.0674288272857666, "Pretrain/Step": 4278, "Pretrain/Step Time": 8.475897362455726} +{"Pretrain/Learning Rate": 3.032506833059755e-05, "Pretrain/Loss": 2.0060248374938965, "Pretrain/Loss (Raw)": 2.0753414630889893, "Pretrain/Step": 4279, "Pretrain/Step Time": 8.474513618275523} +{"Pretrain/Learning Rate": 3.0316772082717603e-05, "Pretrain/Loss": 2.006077766418457, "Pretrain/Loss (Raw)": 2.0458385944366455, "Pretrain/Step": 4280, "Pretrain/Step Time": 8.475687684491277} +{"Pretrain/Learning Rate": 3.0308475221549864e-05, "Pretrain/Loss": 2.007584571838379, "Pretrain/Loss (Raw)": 2.206397533416748, "Pretrain/Step": 4281, "Pretrain/Step Time": 8.475440334528685} +{"Pretrain/Learning Rate": 3.0300177748051373e-05, "Pretrain/Loss": 2.0075228214263916, "Pretrain/Loss (Raw)": 1.9585384130477905, "Pretrain/Step": 4282, "Pretrain/Step Time": 8.475261798128486} +{"Pretrain/Learning Rate": 3.0291879663179235e-05, "Pretrain/Loss": 2.007821798324585, "Pretrain/Loss (Raw)": 2.027869939804077, "Pretrain/Step": 4283, "Pretrain/Step Time": 8.477610697969794} +{"Pretrain/Learning Rate": 3.0283580967890645e-05, "Pretrain/Loss": 2.009096145629883, "Pretrain/Loss (Raw)": 2.0706350803375244, "Pretrain/Step": 4284, "Pretrain/Step Time": 8.47871858626604} +{"Pretrain/Learning Rate": 3.0275281663142846e-05, "Pretrain/Loss": 2.011241912841797, "Pretrain/Loss (Raw)": 2.175751209259033, "Pretrain/Step": 4285, "Pretrain/Step Time": 8.4758733920753} +{"Pretrain/Learning Rate": 3.0266981749893157e-05, "Pretrain/Loss": 2.0105550289154053, "Pretrain/Loss (Raw)": 1.8979578018188477, "Pretrain/Step": 4286, "Pretrain/Step Time": 8.473494976758957} +{"Pretrain/Learning Rate": 3.025868122909898e-05, "Pretrain/Loss": 2.0109243392944336, "Pretrain/Loss (Raw)": 2.2018883228302, "Pretrain/Step": 4287, "Pretrain/Step Time": 8.473310539498925} +{"Pretrain/Learning Rate": 3.0250380101717774e-05, "Pretrain/Loss": 2.0109751224517822, "Pretrain/Loss (Raw)": 1.9409563541412354, "Pretrain/Step": 4288, "Pretrain/Step Time": 8.474809419363737} +{"Pretrain/Learning Rate": 3.024207836870706e-05, "Pretrain/Loss": 2.014338493347168, "Pretrain/Loss (Raw)": 2.154515504837036, "Pretrain/Step": 4289, "Pretrain/Step Time": 8.47118940204382} +{"Pretrain/Learning Rate": 3.023377603102445e-05, "Pretrain/Loss": 2.013944625854492, "Pretrain/Loss (Raw)": 1.8435108661651611, "Pretrain/Step": 4290, "Pretrain/Step Time": 8.472022643312812} +{"Pretrain/Learning Rate": 3.0225473089627616e-05, "Pretrain/Loss": 2.0155768394470215, "Pretrain/Loss (Raw)": 2.077890157699585, "Pretrain/Step": 4291, "Pretrain/Step Time": 8.474281664937735} +{"Pretrain/Learning Rate": 3.02171695454743e-05, "Pretrain/Loss": 2.0163419246673584, "Pretrain/Loss (Raw)": 2.1151180267333984, "Pretrain/Step": 4292, "Pretrain/Step Time": 8.47214462980628} +{"Pretrain/Learning Rate": 3.0208865399522306e-05, "Pretrain/Loss": 2.013737201690674, "Pretrain/Loss (Raw)": 1.8581857681274414, "Pretrain/Step": 4293, "Pretrain/Step Time": 8.473283033818007} +{"Pretrain/Learning Rate": 3.0200560652729516e-05, "Pretrain/Loss": 2.0145819187164307, "Pretrain/Loss (Raw)": 2.132293224334717, "Pretrain/Step": 4294, "Pretrain/Step Time": 8.470678381621838} +{"Pretrain/Learning Rate": 3.019225530605389e-05, "Pretrain/Loss": 2.013092517852783, "Pretrain/Loss (Raw)": 1.9132649898529053, "Pretrain/Step": 4295, "Pretrain/Step Time": 8.47159462608397} +{"Pretrain/Learning Rate": 3.018394936045344e-05, "Pretrain/Loss": 2.0136656761169434, "Pretrain/Loss (Raw)": 2.097351551055908, "Pretrain/Step": 4296, "Pretrain/Step Time": 8.467826828360558} +{"Pretrain/Learning Rate": 3.0175642816886253e-05, "Pretrain/Loss": 2.016846179962158, "Pretrain/Loss (Raw)": 2.1600663661956787, "Pretrain/Step": 4297, "Pretrain/Step Time": 8.467741157859564} +{"Pretrain/Learning Rate": 3.0167335676310476e-05, "Pretrain/Loss": 2.015317678451538, "Pretrain/Loss (Raw)": 1.9551866054534912, "Pretrain/Step": 4298, "Pretrain/Step Time": 8.468184990808368} +{"Pretrain/Learning Rate": 3.015902793968435e-05, "Pretrain/Loss": 2.0163707733154297, "Pretrain/Loss (Raw)": 2.081909418106079, "Pretrain/Step": 4299, "Pretrain/Step Time": 8.47081440873444} +{"Pretrain/Learning Rate": 3.0150719607966166e-05, "Pretrain/Loss": 2.0164084434509277, "Pretrain/Loss (Raw)": 2.1607987880706787, "Pretrain/Step": 4300, "Pretrain/Step Time": 8.472805686295033} +{"Pretrain/Learning Rate": 3.014241068211428e-05, "Pretrain/Loss": 2.0155537128448486, "Pretrain/Loss (Raw)": 1.9496580362319946, "Pretrain/Step": 4301, "Pretrain/Step Time": 8.4700738042593} +{"Pretrain/Learning Rate": 3.0134101163087137e-05, "Pretrain/Loss": 2.0131077766418457, "Pretrain/Loss (Raw)": 1.836177110671997, "Pretrain/Step": 4302, "Pretrain/Step Time": 8.473471069708467} +{"Pretrain/Learning Rate": 3.012579105184322e-05, "Pretrain/Loss": 2.0155553817749023, "Pretrain/Loss (Raw)": 2.1103718280792236, "Pretrain/Step": 4303, "Pretrain/Step Time": 8.473797583952546} +{"Pretrain/Learning Rate": 3.0117480349341114e-05, "Pretrain/Loss": 2.0178864002227783, "Pretrain/Loss (Raw)": 2.0896224975585938, "Pretrain/Step": 4304, "Pretrain/Step Time": 8.475346015766263} +{"Pretrain/Learning Rate": 3.010916905653945e-05, "Pretrain/Loss": 2.0165510177612305, "Pretrain/Loss (Raw)": 1.7501344680786133, "Pretrain/Step": 4305, "Pretrain/Step Time": 8.47553813830018} +{"Pretrain/Learning Rate": 3.0100857174396922e-05, "Pretrain/Loss": 2.017632484436035, "Pretrain/Loss (Raw)": 2.0863585472106934, "Pretrain/Step": 4306, "Pretrain/Step Time": 8.4739891551435} +{"Pretrain/Learning Rate": 3.0092544703872315e-05, "Pretrain/Loss": 2.0193591117858887, "Pretrain/Loss (Raw)": 1.9798647165298462, "Pretrain/Step": 4307, "Pretrain/Step Time": 8.474451767280698} +{"Pretrain/Learning Rate": 3.008423164592447e-05, "Pretrain/Loss": 2.0183310508728027, "Pretrain/Loss (Raw)": 1.9447097778320312, "Pretrain/Step": 4308, "Pretrain/Step Time": 8.47725191526115} +{"Pretrain/Learning Rate": 3.0075918001512286e-05, "Pretrain/Loss": 2.0200247764587402, "Pretrain/Loss (Raw)": 2.2287049293518066, "Pretrain/Step": 4309, "Pretrain/Step Time": 8.477082779631019} +{"Pretrain/Learning Rate": 3.0067603771594748e-05, "Pretrain/Loss": 2.017791271209717, "Pretrain/Loss (Raw)": 1.8050272464752197, "Pretrain/Step": 4310, "Pretrain/Step Time": 8.478085666894913} +{"Pretrain/Learning Rate": 3.0059288957130892e-05, "Pretrain/Loss": 2.0164787769317627, "Pretrain/Loss (Raw)": 1.98976469039917, "Pretrain/Step": 4311, "Pretrain/Step Time": 8.47618504986167} +{"Pretrain/Learning Rate": 3.005097355907984e-05, "Pretrain/Loss": 2.016554117202759, "Pretrain/Loss (Raw)": 2.105198383331299, "Pretrain/Step": 4312, "Pretrain/Step Time": 8.475099565461278} +{"Pretrain/Learning Rate": 3.0042657578400763e-05, "Pretrain/Loss": 2.018742084503174, "Pretrain/Loss (Raw)": 2.168272018432617, "Pretrain/Step": 4313, "Pretrain/Step Time": 8.471193004399538} +{"Pretrain/Learning Rate": 3.0034341016052897e-05, "Pretrain/Loss": 2.0184059143066406, "Pretrain/Loss (Raw)": 2.069119453430176, "Pretrain/Step": 4314, "Pretrain/Step Time": 8.471034759655595} +{"Pretrain/Learning Rate": 3.0026023872995567e-05, "Pretrain/Loss": 2.0185797214508057, "Pretrain/Loss (Raw)": 2.0055315494537354, "Pretrain/Step": 4315, "Pretrain/Step Time": 8.469237552955747} +{"Pretrain/Learning Rate": 3.0017706150188153e-05, "Pretrain/Loss": 2.019968032836914, "Pretrain/Loss (Raw)": 2.1576039791107178, "Pretrain/Step": 4316, "Pretrain/Step Time": 8.467706877738237} +{"Pretrain/Learning Rate": 3.0009387848590094e-05, "Pretrain/Loss": 2.0203070640563965, "Pretrain/Loss (Raw)": 2.1350274085998535, "Pretrain/Step": 4317, "Pretrain/Step Time": 8.4681081995368} +{"Pretrain/Learning Rate": 3.000106896916091e-05, "Pretrain/Loss": 2.022380828857422, "Pretrain/Loss (Raw)": 2.2487282752990723, "Pretrain/Step": 4318, "Pretrain/Step Time": 8.465632500126958} +{"Pretrain/Learning Rate": 2.9992749512860173e-05, "Pretrain/Loss": 2.0237884521484375, "Pretrain/Loss (Raw)": 2.1202635765075684, "Pretrain/Step": 4319, "Pretrain/Step Time": 8.461318790912628} +{"Pretrain/Learning Rate": 2.9984429480647548e-05, "Pretrain/Loss": 2.0237975120544434, "Pretrain/Loss (Raw)": 1.832162857055664, "Pretrain/Step": 4320, "Pretrain/Step Time": 8.461384890601039} +{"Pretrain/Learning Rate": 2.997610887348272e-05, "Pretrain/Loss": 2.024468421936035, "Pretrain/Loss (Raw)": 2.138361692428589, "Pretrain/Step": 4321, "Pretrain/Step Time": 8.460730800405145} +{"Pretrain/Learning Rate": 2.996778769232549e-05, "Pretrain/Loss": 2.02547025680542, "Pretrain/Loss (Raw)": 1.8751665353775024, "Pretrain/Step": 4322, "Pretrain/Step Time": 8.462834378704429} +{"Pretrain/Learning Rate": 2.995946593813569e-05, "Pretrain/Loss": 2.025669574737549, "Pretrain/Loss (Raw)": 2.1830499172210693, "Pretrain/Step": 4323, "Pretrain/Step Time": 8.461830576881766} +{"Pretrain/Learning Rate": 2.995114361187324e-05, "Pretrain/Loss": 2.0257575511932373, "Pretrain/Loss (Raw)": 1.8241174221038818, "Pretrain/Step": 4324, "Pretrain/Step Time": 8.463324438780546} +{"Pretrain/Learning Rate": 2.994282071449811e-05, "Pretrain/Loss": 2.0264408588409424, "Pretrain/Loss (Raw)": 2.225693464279175, "Pretrain/Step": 4325, "Pretrain/Step Time": 8.464451398700476} +{"Pretrain/Learning Rate": 2.9934497246970357e-05, "Pretrain/Loss": 2.023458957672119, "Pretrain/Loss (Raw)": 1.9847437143325806, "Pretrain/Step": 4326, "Pretrain/Step Time": 8.461922636255622} +{"Pretrain/Learning Rate": 2.992617321025007e-05, "Pretrain/Loss": 2.021719455718994, "Pretrain/Loss (Raw)": 2.0948803424835205, "Pretrain/Step": 4327, "Pretrain/Step Time": 8.460549376904964} +{"Pretrain/Learning Rate": 2.9917848605297437e-05, "Pretrain/Loss": 2.0212960243225098, "Pretrain/Loss (Raw)": 1.8844953775405884, "Pretrain/Step": 4328, "Pretrain/Step Time": 8.46159085445106} +{"Pretrain/Learning Rate": 2.99095234330727e-05, "Pretrain/Loss": 2.020580291748047, "Pretrain/Loss (Raw)": 1.9628177881240845, "Pretrain/Step": 4329, "Pretrain/Step Time": 8.458377346396446} +{"Pretrain/Learning Rate": 2.990119769453616e-05, "Pretrain/Loss": 2.023056983947754, "Pretrain/Loss (Raw)": 2.185580015182495, "Pretrain/Step": 4330, "Pretrain/Step Time": 8.45726634375751} +{"Pretrain/Learning Rate": 2.989287139064819e-05, "Pretrain/Loss": 2.0224857330322266, "Pretrain/Loss (Raw)": 1.9371182918548584, "Pretrain/Step": 4331, "Pretrain/Step Time": 8.457789668813348} +{"Pretrain/Learning Rate": 2.988454452236922e-05, "Pretrain/Loss": 2.0228185653686523, "Pretrain/Loss (Raw)": 2.0353474617004395, "Pretrain/Step": 4332, "Pretrain/Step Time": 8.454523265361786} +{"Pretrain/Learning Rate": 2.9876217090659753e-05, "Pretrain/Loss": 2.022994041442871, "Pretrain/Loss (Raw)": 2.0380094051361084, "Pretrain/Step": 4333, "Pretrain/Step Time": 8.45324519649148} +{"Pretrain/Learning Rate": 2.9867889096480362e-05, "Pretrain/Loss": 2.0222907066345215, "Pretrain/Loss (Raw)": 1.992084264755249, "Pretrain/Step": 4334, "Pretrain/Step Time": 8.457842184230685} +{"Pretrain/Learning Rate": 2.985956054079167e-05, "Pretrain/Loss": 2.0226902961730957, "Pretrain/Loss (Raw)": 2.0247602462768555, "Pretrain/Step": 4335, "Pretrain/Step Time": 8.452124936506152} +{"Pretrain/Learning Rate": 2.985123142455438e-05, "Pretrain/Loss": 2.020446300506592, "Pretrain/Loss (Raw)": 1.9304651021957397, "Pretrain/Step": 4336, "Pretrain/Step Time": 8.451746936887503} +{"Pretrain/Learning Rate": 2.9842901748729256e-05, "Pretrain/Loss": 2.0198888778686523, "Pretrain/Loss (Raw)": 2.1358401775360107, "Pretrain/Step": 4337, "Pretrain/Step Time": 8.454640716314316} +{"Pretrain/Learning Rate": 2.9834571514277116e-05, "Pretrain/Loss": 2.019758701324463, "Pretrain/Loss (Raw)": 1.9422714710235596, "Pretrain/Step": 4338, "Pretrain/Step Time": 8.453428987413645} +{"Pretrain/Learning Rate": 2.982624072215885e-05, "Pretrain/Loss": 2.021369218826294, "Pretrain/Loss (Raw)": 2.1595797538757324, "Pretrain/Step": 4339, "Pretrain/Step Time": 8.456261763349175} +{"Pretrain/Learning Rate": 2.9817909373335405e-05, "Pretrain/Loss": 2.0208733081817627, "Pretrain/Loss (Raw)": 1.8423537015914917, "Pretrain/Step": 4340, "Pretrain/Step Time": 8.45803740248084} +{"Pretrain/Learning Rate": 2.9809577468767813e-05, "Pretrain/Loss": 2.02077054977417, "Pretrain/Loss (Raw)": 2.0467655658721924, "Pretrain/Step": 4341, "Pretrain/Step Time": 8.45242153480649} +{"Pretrain/Learning Rate": 2.9801245009417155e-05, "Pretrain/Loss": 2.02011775970459, "Pretrain/Loss (Raw)": 1.9683340787887573, "Pretrain/Step": 4342, "Pretrain/Step Time": 8.45331733673811} +{"Pretrain/Learning Rate": 2.979291199624456e-05, "Pretrain/Loss": 2.0211801528930664, "Pretrain/Loss (Raw)": 1.9622446298599243, "Pretrain/Step": 4343, "Pretrain/Step Time": 8.452191565185785} +{"Pretrain/Learning Rate": 2.978457843021126e-05, "Pretrain/Loss": 2.0202555656433105, "Pretrain/Loss (Raw)": 1.8408286571502686, "Pretrain/Step": 4344, "Pretrain/Step Time": 8.451921319589019} +{"Pretrain/Learning Rate": 2.9776244312278518e-05, "Pretrain/Loss": 2.018735885620117, "Pretrain/Loss (Raw)": 1.9381217956542969, "Pretrain/Step": 4345, "Pretrain/Step Time": 8.450747150927782} +{"Pretrain/Learning Rate": 2.9767909643407675e-05, "Pretrain/Loss": 2.0192954540252686, "Pretrain/Loss (Raw)": 1.9009244441986084, "Pretrain/Step": 4346, "Pretrain/Step Time": 8.451846273615956} +{"Pretrain/Learning Rate": 2.975957442456013e-05, "Pretrain/Loss": 2.0197439193725586, "Pretrain/Loss (Raw)": 2.0581257343292236, "Pretrain/Step": 4347, "Pretrain/Step Time": 8.446410413831472} +{"Pretrain/Learning Rate": 2.9751238656697344e-05, "Pretrain/Loss": 2.0197596549987793, "Pretrain/Loss (Raw)": 2.0109095573425293, "Pretrain/Step": 4348, "Pretrain/Step Time": 8.451608944684267} +{"Pretrain/Learning Rate": 2.9742902340780848e-05, "Pretrain/Loss": 2.022197723388672, "Pretrain/Loss (Raw)": 2.228989601135254, "Pretrain/Step": 4349, "Pretrain/Step Time": 8.451735839247704} +{"Pretrain/Learning Rate": 2.9734565477772236e-05, "Pretrain/Loss": 2.023064613342285, "Pretrain/Loss (Raw)": 2.0072124004364014, "Pretrain/Step": 4350, "Pretrain/Step Time": 8.446207089349627} +{"Pretrain/Learning Rate": 2.9726228068633155e-05, "Pretrain/Loss": 2.0225048065185547, "Pretrain/Loss (Raw)": 1.9783518314361572, "Pretrain/Step": 4351, "Pretrain/Step Time": 8.448285471647978} +{"Pretrain/Learning Rate": 2.9717890114325336e-05, "Pretrain/Loss": 2.0230631828308105, "Pretrain/Loss (Raw)": 2.045498847961426, "Pretrain/Step": 4352, "Pretrain/Step Time": 8.446522625163198} +{"Pretrain/Learning Rate": 2.9709551615810544e-05, "Pretrain/Loss": 2.0253543853759766, "Pretrain/Loss (Raw)": 2.1976728439331055, "Pretrain/Step": 4353, "Pretrain/Step Time": 8.445572959259152} +{"Pretrain/Learning Rate": 2.9701212574050636e-05, "Pretrain/Loss": 2.025294542312622, "Pretrain/Loss (Raw)": 1.7906599044799805, "Pretrain/Step": 4354, "Pretrain/Step Time": 8.44424101524055} +{"Pretrain/Learning Rate": 2.9692872990007503e-05, "Pretrain/Loss": 2.0264105796813965, "Pretrain/Loss (Raw)": 2.282527446746826, "Pretrain/Step": 4355, "Pretrain/Step Time": 8.443606119602919} +{"Pretrain/Learning Rate": 2.9684532864643122e-05, "Pretrain/Loss": 2.0266497135162354, "Pretrain/Loss (Raw)": 1.9286500215530396, "Pretrain/Step": 4356, "Pretrain/Step Time": 8.449707839637995} +{"Pretrain/Learning Rate": 2.9676192198919518e-05, "Pretrain/Loss": 2.0263760089874268, "Pretrain/Loss (Raw)": 1.9511483907699585, "Pretrain/Step": 4357, "Pretrain/Step Time": 8.450179116800427} +{"Pretrain/Learning Rate": 2.966785099379879e-05, "Pretrain/Loss": 2.0279464721679688, "Pretrain/Loss (Raw)": 2.165895938873291, "Pretrain/Step": 4358, "Pretrain/Step Time": 8.44957303069532} +{"Pretrain/Learning Rate": 2.9659509250243085e-05, "Pretrain/Loss": 2.026444435119629, "Pretrain/Loss (Raw)": 1.904160976409912, "Pretrain/Step": 4359, "Pretrain/Step Time": 8.453223722055554} +{"Pretrain/Learning Rate": 2.9651166969214633e-05, "Pretrain/Loss": 2.02516508102417, "Pretrain/Loss (Raw)": 1.9696427583694458, "Pretrain/Step": 4360, "Pretrain/Step Time": 8.44962871260941} +{"Pretrain/Learning Rate": 2.9642824151675702e-05, "Pretrain/Loss": 2.023613691329956, "Pretrain/Loss (Raw)": 1.8346699476242065, "Pretrain/Step": 4361, "Pretrain/Step Time": 8.45274286530912} +{"Pretrain/Learning Rate": 2.9634480798588637e-05, "Pretrain/Loss": 2.0248703956604004, "Pretrain/Loss (Raw)": 2.099247694015503, "Pretrain/Step": 4362, "Pretrain/Step Time": 8.451829340308905} +{"Pretrain/Learning Rate": 2.9626136910915846e-05, "Pretrain/Loss": 2.026348829269409, "Pretrain/Loss (Raw)": 2.06414532661438, "Pretrain/Step": 4363, "Pretrain/Step Time": 8.453885208815336} +{"Pretrain/Learning Rate": 2.9617792489619776e-05, "Pretrain/Loss": 2.0277607440948486, "Pretrain/Loss (Raw)": 2.1003429889678955, "Pretrain/Step": 4364, "Pretrain/Step Time": 8.45289290510118} +{"Pretrain/Learning Rate": 2.9609447535662972e-05, "Pretrain/Loss": 2.0288214683532715, "Pretrain/Loss (Raw)": 2.1562094688415527, "Pretrain/Step": 4365, "Pretrain/Step Time": 8.450036719441414} +{"Pretrain/Learning Rate": 2.9601102050008018e-05, "Pretrain/Loss": 2.027137279510498, "Pretrain/Loss (Raw)": 1.8732596635818481, "Pretrain/Step": 4366, "Pretrain/Step Time": 8.450313739478588} +{"Pretrain/Learning Rate": 2.9592756033617554e-05, "Pretrain/Loss": 2.0268564224243164, "Pretrain/Loss (Raw)": 2.0268070697784424, "Pretrain/Step": 4367, "Pretrain/Step Time": 8.450787253677845} +{"Pretrain/Learning Rate": 2.95844094874543e-05, "Pretrain/Loss": 2.0268678665161133, "Pretrain/Loss (Raw)": 2.049729824066162, "Pretrain/Step": 4368, "Pretrain/Step Time": 8.451203428208828} +{"Pretrain/Learning Rate": 2.957606241248102e-05, "Pretrain/Loss": 2.028773069381714, "Pretrain/Loss (Raw)": 2.1238067150115967, "Pretrain/Step": 4369, "Pretrain/Step Time": 8.451579615473747} +{"Pretrain/Learning Rate": 2.9567714809660552e-05, "Pretrain/Loss": 2.028233051300049, "Pretrain/Loss (Raw)": 1.9468464851379395, "Pretrain/Step": 4370, "Pretrain/Step Time": 8.451567102223635} +{"Pretrain/Learning Rate": 2.955936667995578e-05, "Pretrain/Loss": 2.0281219482421875, "Pretrain/Loss (Raw)": 2.119628429412842, "Pretrain/Step": 4371, "Pretrain/Step Time": 8.453109957277775} +{"Pretrain/Learning Rate": 2.9551018024329668e-05, "Pretrain/Loss": 2.028817892074585, "Pretrain/Loss (Raw)": 2.1436033248901367, "Pretrain/Step": 4372, "Pretrain/Step Time": 8.454723488539457} +{"Pretrain/Learning Rate": 2.954266884374523e-05, "Pretrain/Loss": 2.0293490886688232, "Pretrain/Loss (Raw)": 2.05419659614563, "Pretrain/Step": 4373, "Pretrain/Step Time": 8.455264270305634} +{"Pretrain/Learning Rate": 2.953431913916553e-05, "Pretrain/Loss": 2.029654026031494, "Pretrain/Loss (Raw)": 1.9867726564407349, "Pretrain/Step": 4374, "Pretrain/Step Time": 8.46358041651547} +{"Pretrain/Learning Rate": 2.9525968911553707e-05, "Pretrain/Loss": 2.0306639671325684, "Pretrain/Loss (Raw)": 2.173232078552246, "Pretrain/Step": 4375, "Pretrain/Step Time": 8.461511835455894} +{"Pretrain/Learning Rate": 2.9517618161872973e-05, "Pretrain/Loss": 2.0310516357421875, "Pretrain/Loss (Raw)": 2.0703935623168945, "Pretrain/Step": 4376, "Pretrain/Step Time": 8.464919075369835} +{"Pretrain/Learning Rate": 2.950926689108656e-05, "Pretrain/Loss": 2.0308380126953125, "Pretrain/Loss (Raw)": 1.9800516366958618, "Pretrain/Step": 4377, "Pretrain/Step Time": 8.465114442631602} +{"Pretrain/Learning Rate": 2.95009151001578e-05, "Pretrain/Loss": 2.030282735824585, "Pretrain/Loss (Raw)": 1.999286413192749, "Pretrain/Step": 4378, "Pretrain/Step Time": 8.463881077244878} +{"Pretrain/Learning Rate": 2.9492562790050072e-05, "Pretrain/Loss": 2.028860092163086, "Pretrain/Loss (Raw)": 1.9657691717147827, "Pretrain/Step": 4379, "Pretrain/Step Time": 8.462314181029797} +{"Pretrain/Learning Rate": 2.9484209961726798e-05, "Pretrain/Loss": 2.0297093391418457, "Pretrain/Loss (Raw)": 2.1856870651245117, "Pretrain/Step": 4380, "Pretrain/Step Time": 8.462039653211832} +{"Pretrain/Learning Rate": 2.9475856616151488e-05, "Pretrain/Loss": 2.0283806324005127, "Pretrain/Loss (Raw)": 1.9310928583145142, "Pretrain/Step": 4381, "Pretrain/Step Time": 8.461735619232059} +{"Pretrain/Learning Rate": 2.946750275428768e-05, "Pretrain/Loss": 2.027409791946411, "Pretrain/Loss (Raw)": 1.9439153671264648, "Pretrain/Step": 4382, "Pretrain/Step Time": 8.463796840980649} +{"Pretrain/Learning Rate": 2.9459148377099e-05, "Pretrain/Loss": 2.0280261039733887, "Pretrain/Loss (Raw)": 2.129786252975464, "Pretrain/Step": 4383, "Pretrain/Step Time": 8.465877033770084} +{"Pretrain/Learning Rate": 2.9450793485549128e-05, "Pretrain/Loss": 2.0267891883850098, "Pretrain/Loss (Raw)": 1.9183770418167114, "Pretrain/Step": 4384, "Pretrain/Step Time": 8.464381324127316} +{"Pretrain/Learning Rate": 2.9442438080601787e-05, "Pretrain/Loss": 2.0276622772216797, "Pretrain/Loss (Raw)": 2.1240432262420654, "Pretrain/Step": 4385, "Pretrain/Step Time": 8.46323724463582} +{"Pretrain/Learning Rate": 2.9434082163220773e-05, "Pretrain/Loss": 2.0251736640930176, "Pretrain/Loss (Raw)": 1.7357866764068604, "Pretrain/Step": 4386, "Pretrain/Step Time": 8.463805343955755} +{"Pretrain/Learning Rate": 2.9425725734369946e-05, "Pretrain/Loss": 2.0248074531555176, "Pretrain/Loss (Raw)": 2.0222034454345703, "Pretrain/Step": 4387, "Pretrain/Step Time": 8.462349079549313} +{"Pretrain/Learning Rate": 2.941736879501321e-05, "Pretrain/Loss": 2.0255565643310547, "Pretrain/Loss (Raw)": 2.0098392963409424, "Pretrain/Step": 4388, "Pretrain/Step Time": 8.466566206887364} +{"Pretrain/Learning Rate": 2.940901134611454e-05, "Pretrain/Loss": 2.026249408721924, "Pretrain/Loss (Raw)": 1.9695708751678467, "Pretrain/Step": 4389, "Pretrain/Step Time": 8.465936759486794} +{"Pretrain/Learning Rate": 2.940065338863795e-05, "Pretrain/Loss": 2.0258121490478516, "Pretrain/Loss (Raw)": 2.01518177986145, "Pretrain/Step": 4390, "Pretrain/Step Time": 8.467836070805788} +{"Pretrain/Learning Rate": 2.939229492354754e-05, "Pretrain/Loss": 2.0253398418426514, "Pretrain/Loss (Raw)": 2.0739998817443848, "Pretrain/Step": 4391, "Pretrain/Step Time": 8.464737797155976} +{"Pretrain/Learning Rate": 2.938393595180746e-05, "Pretrain/Loss": 2.0251693725585938, "Pretrain/Loss (Raw)": 2.1134889125823975, "Pretrain/Step": 4392, "Pretrain/Step Time": 8.465494504198432} +{"Pretrain/Learning Rate": 2.9375576474381905e-05, "Pretrain/Loss": 2.026068925857544, "Pretrain/Loss (Raw)": 2.2012877464294434, "Pretrain/Step": 4393, "Pretrain/Step Time": 8.461679257452488} +{"Pretrain/Learning Rate": 2.9367216492235138e-05, "Pretrain/Loss": 2.0277130603790283, "Pretrain/Loss (Raw)": 2.101040840148926, "Pretrain/Step": 4394, "Pretrain/Step Time": 8.466056413948536} +{"Pretrain/Learning Rate": 2.9358856006331487e-05, "Pretrain/Loss": 2.0280513763427734, "Pretrain/Loss (Raw)": 2.0119645595550537, "Pretrain/Step": 4395, "Pretrain/Step Time": 8.468886978924274} +{"Pretrain/Learning Rate": 2.9350495017635334e-05, "Pretrain/Loss": 2.0286312103271484, "Pretrain/Loss (Raw)": 2.001555919647217, "Pretrain/Step": 4396, "Pretrain/Step Time": 8.46532073803246} +{"Pretrain/Learning Rate": 2.9342133527111105e-05, "Pretrain/Loss": 2.0312418937683105, "Pretrain/Loss (Raw)": 2.226243734359741, "Pretrain/Step": 4397, "Pretrain/Step Time": 8.467355027794838} +{"Pretrain/Learning Rate": 2.933377153572329e-05, "Pretrain/Loss": 2.0303072929382324, "Pretrain/Loss (Raw)": 2.0162224769592285, "Pretrain/Step": 4398, "Pretrain/Step Time": 8.46679968945682} +{"Pretrain/Learning Rate": 2.932540904443646e-05, "Pretrain/Loss": 2.0288634300231934, "Pretrain/Loss (Raw)": 2.0470640659332275, "Pretrain/Step": 4399, "Pretrain/Step Time": 8.465813681483269} +{"Pretrain/Learning Rate": 2.9317046054215218e-05, "Pretrain/Loss": 2.030441999435425, "Pretrain/Loss (Raw)": 2.160212516784668, "Pretrain/Step": 4400, "Pretrain/Step Time": 8.464836051687598} +{"Pretrain/Learning Rate": 2.9308682566024224e-05, "Pretrain/Loss": 2.032001256942749, "Pretrain/Loss (Raw)": 2.1748600006103516, "Pretrain/Step": 4401, "Pretrain/Step Time": 8.464593699201941} +{"Pretrain/Learning Rate": 2.930031858082822e-05, "Pretrain/Loss": 2.0330700874328613, "Pretrain/Loss (Raw)": 2.205087661743164, "Pretrain/Step": 4402, "Pretrain/Step Time": 8.46523085795343} +{"Pretrain/Learning Rate": 2.9291954099591973e-05, "Pretrain/Loss": 2.0336339473724365, "Pretrain/Loss (Raw)": 2.1306350231170654, "Pretrain/Step": 4403, "Pretrain/Step Time": 8.464730627834797} +{"Pretrain/Learning Rate": 2.928358912328033e-05, "Pretrain/Loss": 2.0331196784973145, "Pretrain/Loss (Raw)": 2.1648898124694824, "Pretrain/Step": 4404, "Pretrain/Step Time": 8.463490536436439} +{"Pretrain/Learning Rate": 2.9275223652858193e-05, "Pretrain/Loss": 2.038905620574951, "Pretrain/Loss (Raw)": 2.1934611797332764, "Pretrain/Step": 4405, "Pretrain/Step Time": 8.464342020452023} +{"Pretrain/Learning Rate": 2.92668576892905e-05, "Pretrain/Loss": 2.038823127746582, "Pretrain/Loss (Raw)": 2.0569140911102295, "Pretrain/Step": 4406, "Pretrain/Step Time": 8.46511417068541} +{"Pretrain/Learning Rate": 2.9258491233542274e-05, "Pretrain/Loss": 2.0386528968811035, "Pretrain/Loss (Raw)": 2.053539991378784, "Pretrain/Step": 4407, "Pretrain/Step Time": 8.468698868528008} +{"Pretrain/Learning Rate": 2.9250124286578584e-05, "Pretrain/Loss": 2.0385499000549316, "Pretrain/Loss (Raw)": 2.0326578617095947, "Pretrain/Step": 4408, "Pretrain/Step Time": 8.464102381840348} +{"Pretrain/Learning Rate": 2.9241756849364542e-05, "Pretrain/Loss": 2.037233591079712, "Pretrain/Loss (Raw)": 2.037886142730713, "Pretrain/Step": 4409, "Pretrain/Step Time": 8.467172699049115} +{"Pretrain/Learning Rate": 2.923338892286535e-05, "Pretrain/Loss": 2.0351996421813965, "Pretrain/Loss (Raw)": 1.6982271671295166, "Pretrain/Step": 4410, "Pretrain/Step Time": 8.471660017967224} +{"Pretrain/Learning Rate": 2.9225020508046232e-05, "Pretrain/Loss": 2.0360727310180664, "Pretrain/Loss (Raw)": 2.1396217346191406, "Pretrain/Step": 4411, "Pretrain/Step Time": 8.471476417034864} +{"Pretrain/Learning Rate": 2.921665160587248e-05, "Pretrain/Loss": 2.034144878387451, "Pretrain/Loss (Raw)": 1.823822259902954, "Pretrain/Step": 4412, "Pretrain/Step Time": 8.468441490083933} +{"Pretrain/Learning Rate": 2.9208282217309447e-05, "Pretrain/Loss": 2.033602476119995, "Pretrain/Loss (Raw)": 2.1063549518585205, "Pretrain/Step": 4413, "Pretrain/Step Time": 8.472247892990708} +{"Pretrain/Learning Rate": 2.919991234332254e-05, "Pretrain/Loss": 2.035438060760498, "Pretrain/Loss (Raw)": 2.1328933238983154, "Pretrain/Step": 4414, "Pretrain/Step Time": 8.472323823720217} +{"Pretrain/Learning Rate": 2.9191541984877218e-05, "Pretrain/Loss": 2.03420352935791, "Pretrain/Loss (Raw)": 2.043872833251953, "Pretrain/Step": 4415, "Pretrain/Step Time": 8.473286390304565} +{"Pretrain/Learning Rate": 2.9183171142939005e-05, "Pretrain/Loss": 2.0358381271362305, "Pretrain/Loss (Raw)": 2.1501903533935547, "Pretrain/Step": 4416, "Pretrain/Step Time": 8.471988271921873} +{"Pretrain/Learning Rate": 2.9174799818473464e-05, "Pretrain/Loss": 2.035634756088257, "Pretrain/Loss (Raw)": 2.1285054683685303, "Pretrain/Step": 4417, "Pretrain/Step Time": 8.470724705606699} +{"Pretrain/Learning Rate": 2.916642801244624e-05, "Pretrain/Loss": 2.035721778869629, "Pretrain/Loss (Raw)": 1.8546417951583862, "Pretrain/Step": 4418, "Pretrain/Step Time": 8.474403154104948} +{"Pretrain/Learning Rate": 2.9158055725823e-05, "Pretrain/Loss": 2.033423900604248, "Pretrain/Loss (Raw)": 1.7837733030319214, "Pretrain/Step": 4419, "Pretrain/Step Time": 8.477174047380686} +{"Pretrain/Learning Rate": 2.9149682959569498e-05, "Pretrain/Loss": 2.032970905303955, "Pretrain/Loss (Raw)": 2.0571060180664062, "Pretrain/Step": 4420, "Pretrain/Step Time": 8.476519798859954} +{"Pretrain/Learning Rate": 2.9141309714651526e-05, "Pretrain/Loss": 2.0353479385375977, "Pretrain/Loss (Raw)": 2.162482738494873, "Pretrain/Step": 4421, "Pretrain/Step Time": 8.478640664368868} +{"Pretrain/Learning Rate": 2.9132935992034938e-05, "Pretrain/Loss": 2.0315704345703125, "Pretrain/Loss (Raw)": 1.6487786769866943, "Pretrain/Step": 4422, "Pretrain/Step Time": 8.47906924970448} +{"Pretrain/Learning Rate": 2.912456179268563e-05, "Pretrain/Loss": 2.033477783203125, "Pretrain/Loss (Raw)": 2.1573610305786133, "Pretrain/Step": 4423, "Pretrain/Step Time": 8.480139411985874} +{"Pretrain/Learning Rate": 2.9116187117569564e-05, "Pretrain/Loss": 2.034167528152466, "Pretrain/Loss (Raw)": 2.1856582164764404, "Pretrain/Step": 4424, "Pretrain/Step Time": 8.482264466583729} +{"Pretrain/Learning Rate": 2.9107811967652766e-05, "Pretrain/Loss": 2.03355073928833, "Pretrain/Loss (Raw)": 2.0811219215393066, "Pretrain/Step": 4425, "Pretrain/Step Time": 8.480660647153854} +{"Pretrain/Learning Rate": 2.9099436343901306e-05, "Pretrain/Loss": 2.034973621368408, "Pretrain/Loss (Raw)": 2.137340784072876, "Pretrain/Step": 4426, "Pretrain/Step Time": 8.481395825743675} +{"Pretrain/Learning Rate": 2.909106024728129e-05, "Pretrain/Loss": 2.035707950592041, "Pretrain/Loss (Raw)": 2.1758787631988525, "Pretrain/Step": 4427, "Pretrain/Step Time": 8.481267038732767} +{"Pretrain/Learning Rate": 2.908268367875892e-05, "Pretrain/Loss": 2.0362703800201416, "Pretrain/Loss (Raw)": 2.2327733039855957, "Pretrain/Step": 4428, "Pretrain/Step Time": 8.48207893781364} +{"Pretrain/Learning Rate": 2.9074306639300424e-05, "Pretrain/Loss": 2.037201404571533, "Pretrain/Loss (Raw)": 2.068862199783325, "Pretrain/Step": 4429, "Pretrain/Step Time": 8.48510286770761} +{"Pretrain/Learning Rate": 2.9065929129872094e-05, "Pretrain/Loss": 2.0393378734588623, "Pretrain/Loss (Raw)": 2.109632968902588, "Pretrain/Step": 4430, "Pretrain/Step Time": 8.480608498677611} +{"Pretrain/Learning Rate": 2.9057551151440265e-05, "Pretrain/Loss": 2.038893461227417, "Pretrain/Loss (Raw)": 2.0534825325012207, "Pretrain/Step": 4431, "Pretrain/Step Time": 8.479248113930225} +{"Pretrain/Learning Rate": 2.9049172704971332e-05, "Pretrain/Loss": 2.0383334159851074, "Pretrain/Loss (Raw)": 2.017953634262085, "Pretrain/Step": 4432, "Pretrain/Step Time": 8.477794233709574} +{"Pretrain/Learning Rate": 2.904079379143175e-05, "Pretrain/Loss": 2.0391979217529297, "Pretrain/Loss (Raw)": 1.8607585430145264, "Pretrain/Step": 4433, "Pretrain/Step Time": 8.473690776154399} +{"Pretrain/Learning Rate": 2.9032414411788027e-05, "Pretrain/Loss": 2.039250135421753, "Pretrain/Loss (Raw)": 2.0930638313293457, "Pretrain/Step": 4434, "Pretrain/Step Time": 8.477752132341266} +{"Pretrain/Learning Rate": 2.902403456700672e-05, "Pretrain/Loss": 2.0392112731933594, "Pretrain/Loss (Raw)": 1.9748592376708984, "Pretrain/Step": 4435, "Pretrain/Step Time": 8.478101784363389} +{"Pretrain/Learning Rate": 2.901565425805443e-05, "Pretrain/Loss": 2.0395119190216064, "Pretrain/Loss (Raw)": 1.983198881149292, "Pretrain/Step": 4436, "Pretrain/Step Time": 8.478055430576205} +{"Pretrain/Learning Rate": 2.9007273485897847e-05, "Pretrain/Loss": 2.0370144844055176, "Pretrain/Loss (Raw)": 1.9090232849121094, "Pretrain/Step": 4437, "Pretrain/Step Time": 8.479038277640939} +{"Pretrain/Learning Rate": 2.8998892251503675e-05, "Pretrain/Loss": 2.037059783935547, "Pretrain/Loss (Raw)": 1.8108503818511963, "Pretrain/Step": 4438, "Pretrain/Step Time": 8.47909821011126} +{"Pretrain/Learning Rate": 2.899051055583868e-05, "Pretrain/Loss": 2.037290573120117, "Pretrain/Loss (Raw)": 2.0192930698394775, "Pretrain/Step": 4439, "Pretrain/Step Time": 8.47606910392642} +{"Pretrain/Learning Rate": 2.898212839986969e-05, "Pretrain/Loss": 2.037259340286255, "Pretrain/Loss (Raw)": 2.1012187004089355, "Pretrain/Step": 4440, "Pretrain/Step Time": 8.476938854902983} +{"Pretrain/Learning Rate": 2.8973745784563593e-05, "Pretrain/Loss": 2.0373706817626953, "Pretrain/Loss (Raw)": 2.1825032234191895, "Pretrain/Step": 4441, "Pretrain/Step Time": 8.480249870568514} +{"Pretrain/Learning Rate": 2.8965362710887324e-05, "Pretrain/Loss": 2.0374929904937744, "Pretrain/Loss (Raw)": 2.084789991378784, "Pretrain/Step": 4442, "Pretrain/Step Time": 8.477745240554214} +{"Pretrain/Learning Rate": 2.8956979179807846e-05, "Pretrain/Loss": 2.0386569499969482, "Pretrain/Loss (Raw)": 2.1545145511627197, "Pretrain/Step": 4443, "Pretrain/Step Time": 8.477524813264608} +{"Pretrain/Learning Rate": 2.8948595192292216e-05, "Pretrain/Loss": 2.0365452766418457, "Pretrain/Loss (Raw)": 1.8873313665390015, "Pretrain/Step": 4444, "Pretrain/Step Time": 8.485069142654538} +{"Pretrain/Learning Rate": 2.8940210749307522e-05, "Pretrain/Loss": 2.0362491607666016, "Pretrain/Loss (Raw)": 2.0971152782440186, "Pretrain/Step": 4445, "Pretrain/Step Time": 8.483223835006356} +{"Pretrain/Learning Rate": 2.8931825851820904e-05, "Pretrain/Loss": 2.0349206924438477, "Pretrain/Loss (Raw)": 2.078686237335205, "Pretrain/Step": 4446, "Pretrain/Step Time": 8.483134329319} +{"Pretrain/Learning Rate": 2.8923440500799557e-05, "Pretrain/Loss": 2.0340638160705566, "Pretrain/Loss (Raw)": 2.0105576515197754, "Pretrain/Step": 4447, "Pretrain/Step Time": 8.485961286351085} +{"Pretrain/Learning Rate": 2.891505469721072e-05, "Pretrain/Loss": 2.035625696182251, "Pretrain/Loss (Raw)": 2.032104969024658, "Pretrain/Step": 4448, "Pretrain/Step Time": 8.484787430614233} +{"Pretrain/Learning Rate": 2.8906668442021702e-05, "Pretrain/Loss": 2.034968852996826, "Pretrain/Loss (Raw)": 2.054255723953247, "Pretrain/Step": 4449, "Pretrain/Step Time": 8.485277032479644} +{"Pretrain/Learning Rate": 2.889828173619985e-05, "Pretrain/Loss": 2.0358705520629883, "Pretrain/Loss (Raw)": 1.9906119108200073, "Pretrain/Step": 4450, "Pretrain/Step Time": 8.486932484433055} +{"Pretrain/Learning Rate": 2.8889894580712574e-05, "Pretrain/Loss": 2.0344343185424805, "Pretrain/Loss (Raw)": 1.9991955757141113, "Pretrain/Step": 4451, "Pretrain/Step Time": 8.48248434625566} +{"Pretrain/Learning Rate": 2.888150697652732e-05, "Pretrain/Loss": 2.0320165157318115, "Pretrain/Loss (Raw)": 1.5146549940109253, "Pretrain/Step": 4452, "Pretrain/Step Time": 8.486188556998968} +{"Pretrain/Learning Rate": 2.8873118924611603e-05, "Pretrain/Loss": 2.0315330028533936, "Pretrain/Loss (Raw)": 2.1637680530548096, "Pretrain/Step": 4453, "Pretrain/Step Time": 8.486615717411041} +{"Pretrain/Learning Rate": 2.8864730425932984e-05, "Pretrain/Loss": 2.0317344665527344, "Pretrain/Loss (Raw)": 2.010573148727417, "Pretrain/Step": 4454, "Pretrain/Step Time": 8.48701411858201} +{"Pretrain/Learning Rate": 2.8856341481459066e-05, "Pretrain/Loss": 2.031099796295166, "Pretrain/Loss (Raw)": 2.0136239528656006, "Pretrain/Step": 4455, "Pretrain/Step Time": 8.487717524170876} +{"Pretrain/Learning Rate": 2.884795209215751e-05, "Pretrain/Loss": 2.032196521759033, "Pretrain/Loss (Raw)": 2.024902582168579, "Pretrain/Step": 4456, "Pretrain/Step Time": 8.488732414320111} +{"Pretrain/Learning Rate": 2.8839562258996028e-05, "Pretrain/Loss": 2.0310440063476562, "Pretrain/Loss (Raw)": 1.8152772188186646, "Pretrain/Step": 4457, "Pretrain/Step Time": 8.487543178722262} +{"Pretrain/Learning Rate": 2.8831171982942396e-05, "Pretrain/Loss": 2.0300498008728027, "Pretrain/Loss (Raw)": 2.0583062171936035, "Pretrain/Step": 4458, "Pretrain/Step Time": 8.488452058285475} +{"Pretrain/Learning Rate": 2.882278126496442e-05, "Pretrain/Loss": 2.0310990810394287, "Pretrain/Loss (Raw)": 2.071428060531616, "Pretrain/Step": 4459, "Pretrain/Step Time": 8.486936209723353} +{"Pretrain/Learning Rate": 2.881439010602997e-05, "Pretrain/Loss": 2.0310699939727783, "Pretrain/Loss (Raw)": 2.03163743019104, "Pretrain/Step": 4460, "Pretrain/Step Time": 8.488677339628339} +{"Pretrain/Learning Rate": 2.8805998507106956e-05, "Pretrain/Loss": 2.0310850143432617, "Pretrain/Loss (Raw)": 2.0399117469787598, "Pretrain/Step": 4461, "Pretrain/Step Time": 8.491946371272206} +{"Pretrain/Learning Rate": 2.8797606469163357e-05, "Pretrain/Loss": 2.03049373626709, "Pretrain/Loss (Raw)": 1.916418433189392, "Pretrain/Step": 4462, "Pretrain/Step Time": 8.489586222916842} +{"Pretrain/Learning Rate": 2.8789213993167192e-05, "Pretrain/Loss": 2.031238079071045, "Pretrain/Loss (Raw)": 2.1200571060180664, "Pretrain/Step": 4463, "Pretrain/Step Time": 8.489221839234233} +{"Pretrain/Learning Rate": 2.8780821080086516e-05, "Pretrain/Loss": 2.0317366123199463, "Pretrain/Loss (Raw)": 1.9942651987075806, "Pretrain/Step": 4464, "Pretrain/Step Time": 8.491499608382583} +{"Pretrain/Learning Rate": 2.8772427730889463e-05, "Pretrain/Loss": 2.0300095081329346, "Pretrain/Loss (Raw)": 1.914751648902893, "Pretrain/Step": 4465, "Pretrain/Step Time": 8.48928751796484} +{"Pretrain/Learning Rate": 2.8764033946544195e-05, "Pretrain/Loss": 2.031270980834961, "Pretrain/Loss (Raw)": 2.1037492752075195, "Pretrain/Step": 4466, "Pretrain/Step Time": 8.488899955525994} +{"Pretrain/Learning Rate": 2.875563972801893e-05, "Pretrain/Loss": 2.0284109115600586, "Pretrain/Loss (Raw)": 1.7934921979904175, "Pretrain/Step": 4467, "Pretrain/Step Time": 8.487948078662157} +{"Pretrain/Learning Rate": 2.874724507628195e-05, "Pretrain/Loss": 2.0283820629119873, "Pretrain/Loss (Raw)": 1.838672399520874, "Pretrain/Step": 4468, "Pretrain/Step Time": 8.485786778852344} +{"Pretrain/Learning Rate": 2.873884999230155e-05, "Pretrain/Loss": 2.0288898944854736, "Pretrain/Loss (Raw)": 2.111741065979004, "Pretrain/Step": 4469, "Pretrain/Step Time": 8.488460402935743} +{"Pretrain/Learning Rate": 2.873045447704613e-05, "Pretrain/Loss": 2.029336929321289, "Pretrain/Loss (Raw)": 2.025580883026123, "Pretrain/Step": 4470, "Pretrain/Step Time": 8.484493173658848} +{"Pretrain/Learning Rate": 2.8722058531484103e-05, "Pretrain/Loss": 2.0296261310577393, "Pretrain/Loss (Raw)": 1.9992574453353882, "Pretrain/Step": 4471, "Pretrain/Step Time": 8.486388675868511} +{"Pretrain/Learning Rate": 2.8713662156583925e-05, "Pretrain/Loss": 2.0301241874694824, "Pretrain/Loss (Raw)": 1.9045612812042236, "Pretrain/Step": 4472, "Pretrain/Step Time": 8.487705878913403} +{"Pretrain/Learning Rate": 2.8705265353314124e-05, "Pretrain/Loss": 2.032484292984009, "Pretrain/Loss (Raw)": 2.240220785140991, "Pretrain/Step": 4473, "Pretrain/Step Time": 8.489237315952778} +{"Pretrain/Learning Rate": 2.8696868122643268e-05, "Pretrain/Loss": 2.034080743789673, "Pretrain/Loss (Raw)": 2.1052780151367188, "Pretrain/Step": 4474, "Pretrain/Step Time": 8.486238092184067} +{"Pretrain/Learning Rate": 2.868847046553997e-05, "Pretrain/Loss": 2.0339019298553467, "Pretrain/Loss (Raw)": 2.0352189540863037, "Pretrain/Step": 4475, "Pretrain/Step Time": 8.490101099014282} +{"Pretrain/Learning Rate": 2.86800723829729e-05, "Pretrain/Loss": 2.0329442024230957, "Pretrain/Loss (Raw)": 1.888342261314392, "Pretrain/Step": 4476, "Pretrain/Step Time": 8.486629636958241} +{"Pretrain/Learning Rate": 2.8671673875910772e-05, "Pretrain/Loss": 2.0328369140625, "Pretrain/Loss (Raw)": 2.2152621746063232, "Pretrain/Step": 4477, "Pretrain/Step Time": 8.486318547278643} +{"Pretrain/Learning Rate": 2.8663274945322355e-05, "Pretrain/Loss": 2.032670021057129, "Pretrain/Loss (Raw)": 1.9858496189117432, "Pretrain/Step": 4478, "Pretrain/Step Time": 8.487950026988983} +{"Pretrain/Learning Rate": 2.8654875592176462e-05, "Pretrain/Loss": 2.0324325561523438, "Pretrain/Loss (Raw)": 1.9479398727416992, "Pretrain/Step": 4479, "Pretrain/Step Time": 8.488674957305193} +{"Pretrain/Learning Rate": 2.8646475817441952e-05, "Pretrain/Loss": 2.0325469970703125, "Pretrain/Loss (Raw)": 2.060152053833008, "Pretrain/Step": 4480, "Pretrain/Step Time": 8.485804600641131} +{"Pretrain/Learning Rate": 2.8638075622087747e-05, "Pretrain/Loss": 2.031672716140747, "Pretrain/Loss (Raw)": 2.0857582092285156, "Pretrain/Step": 4481, "Pretrain/Step Time": 8.486539689823985} +{"Pretrain/Learning Rate": 2.8629675007082784e-05, "Pretrain/Loss": 2.031989574432373, "Pretrain/Loss (Raw)": 1.8312221765518188, "Pretrain/Step": 4482, "Pretrain/Step Time": 8.48810925707221} +{"Pretrain/Learning Rate": 2.862127397339609e-05, "Pretrain/Loss": 2.0305533409118652, "Pretrain/Loss (Raw)": 2.0987133979797363, "Pretrain/Step": 4483, "Pretrain/Step Time": 8.489393398165703} +{"Pretrain/Learning Rate": 2.8612872521996714e-05, "Pretrain/Loss": 2.031632423400879, "Pretrain/Loss (Raw)": 2.066748857498169, "Pretrain/Step": 4484, "Pretrain/Step Time": 8.480637667700648} +{"Pretrain/Learning Rate": 2.8604470653853766e-05, "Pretrain/Loss": 2.0319557189941406, "Pretrain/Loss (Raw)": 1.9925408363342285, "Pretrain/Step": 4485, "Pretrain/Step Time": 8.482173409312963} +{"Pretrain/Learning Rate": 2.8596068369936386e-05, "Pretrain/Loss": 2.030581474304199, "Pretrain/Loss (Raw)": 1.9899791479110718, "Pretrain/Step": 4486, "Pretrain/Step Time": 8.482762604951859} +{"Pretrain/Learning Rate": 2.858766567121379e-05, "Pretrain/Loss": 2.0314273834228516, "Pretrain/Loss (Raw)": 2.012436866760254, "Pretrain/Step": 4487, "Pretrain/Step Time": 8.480663763359189} +{"Pretrain/Learning Rate": 2.857926255865523e-05, "Pretrain/Loss": 2.0317859649658203, "Pretrain/Loss (Raw)": 2.015543222427368, "Pretrain/Step": 4488, "Pretrain/Step Time": 8.48651116527617} +{"Pretrain/Learning Rate": 2.857085903322998e-05, "Pretrain/Loss": 2.0317392349243164, "Pretrain/Loss (Raw)": 1.8286666870117188, "Pretrain/Step": 4489, "Pretrain/Step Time": 8.483493668958545} +{"Pretrain/Learning Rate": 2.8562455095907392e-05, "Pretrain/Loss": 2.030937910079956, "Pretrain/Loss (Raw)": 1.9967079162597656, "Pretrain/Step": 4490, "Pretrain/Step Time": 8.485888870432973} +{"Pretrain/Learning Rate": 2.855405074765686e-05, "Pretrain/Loss": 2.031007766723633, "Pretrain/Loss (Raw)": 2.0730817317962646, "Pretrain/Step": 4491, "Pretrain/Step Time": 8.487841049209237} +{"Pretrain/Learning Rate": 2.8545645989447832e-05, "Pretrain/Loss": 2.0304250717163086, "Pretrain/Loss (Raw)": 2.025768280029297, "Pretrain/Step": 4492, "Pretrain/Step Time": 8.490576401352882} +{"Pretrain/Learning Rate": 2.8537240822249784e-05, "Pretrain/Loss": 2.028813362121582, "Pretrain/Loss (Raw)": 1.9499077796936035, "Pretrain/Step": 4493, "Pretrain/Step Time": 8.49058391712606} +{"Pretrain/Learning Rate": 2.8528835247032242e-05, "Pretrain/Loss": 2.030031204223633, "Pretrain/Loss (Raw)": 2.0291507244110107, "Pretrain/Step": 4494, "Pretrain/Step Time": 8.492598550394177} +{"Pretrain/Learning Rate": 2.8520429264764805e-05, "Pretrain/Loss": 2.0277538299560547, "Pretrain/Loss (Raw)": 1.7352991104125977, "Pretrain/Step": 4495, "Pretrain/Step Time": 8.491101499646902} +{"Pretrain/Learning Rate": 2.8512022876417087e-05, "Pretrain/Loss": 2.0288312435150146, "Pretrain/Loss (Raw)": 2.1876184940338135, "Pretrain/Step": 4496, "Pretrain/Step Time": 8.487665187567472} +{"Pretrain/Learning Rate": 2.8503616082958766e-05, "Pretrain/Loss": 2.026672124862671, "Pretrain/Loss (Raw)": 1.8474373817443848, "Pretrain/Step": 4497, "Pretrain/Step Time": 8.487094542011619} +{"Pretrain/Learning Rate": 2.8495208885359555e-05, "Pretrain/Loss": 2.0264132022857666, "Pretrain/Loss (Raw)": 1.9137245416641235, "Pretrain/Step": 4498, "Pretrain/Step Time": 8.484817154705524} +{"Pretrain/Learning Rate": 2.8486801284589225e-05, "Pretrain/Loss": 2.0246331691741943, "Pretrain/Loss (Raw)": 1.8917831182479858, "Pretrain/Step": 4499, "Pretrain/Step Time": 8.481962032616138} +{"Pretrain/Learning Rate": 2.84783932816176e-05, "Pretrain/Loss": 2.0239715576171875, "Pretrain/Loss (Raw)": 2.058901309967041, "Pretrain/Step": 4500, "Pretrain/Step Time": 8.483502564951777} +{"Pretrain/Learning Rate": 2.8469984877414525e-05, "Pretrain/Loss": 2.021925926208496, "Pretrain/Loss (Raw)": 1.792367696762085, "Pretrain/Step": 4501, "Pretrain/Step Time": 8.48327567614615} +{"Pretrain/Learning Rate": 2.8461576072949926e-05, "Pretrain/Loss": 2.023517608642578, "Pretrain/Loss (Raw)": 2.19050669670105, "Pretrain/Step": 4502, "Pretrain/Step Time": 8.476005034521222} +{"Pretrain/Learning Rate": 2.8453166869193725e-05, "Pretrain/Loss": 2.022963047027588, "Pretrain/Loss (Raw)": 2.102280378341675, "Pretrain/Step": 4503, "Pretrain/Step Time": 8.477897139266133} +{"Pretrain/Learning Rate": 2.844475726711595e-05, "Pretrain/Loss": 2.023258686065674, "Pretrain/Loss (Raw)": 2.1081817150115967, "Pretrain/Step": 4504, "Pretrain/Step Time": 8.4736467897892} +{"Pretrain/Learning Rate": 2.8436347267686636e-05, "Pretrain/Loss": 2.0228943824768066, "Pretrain/Loss (Raw)": 1.9334386587142944, "Pretrain/Step": 4505, "Pretrain/Step Time": 8.47689027711749} +{"Pretrain/Learning Rate": 2.8427936871875876e-05, "Pretrain/Loss": 2.0226387977600098, "Pretrain/Loss (Raw)": 1.9665864706039429, "Pretrain/Step": 4506, "Pretrain/Step Time": 8.473700683563948} +{"Pretrain/Learning Rate": 2.8419526080653792e-05, "Pretrain/Loss": 2.0196404457092285, "Pretrain/Loss (Raw)": 1.5819746255874634, "Pretrain/Step": 4507, "Pretrain/Step Time": 8.477736815810204} +{"Pretrain/Learning Rate": 2.8411114894990585e-05, "Pretrain/Loss": 2.0193777084350586, "Pretrain/Loss (Raw)": 2.152050018310547, "Pretrain/Step": 4508, "Pretrain/Step Time": 8.478984087705612} +{"Pretrain/Learning Rate": 2.8402703315856465e-05, "Pretrain/Loss": 2.0203304290771484, "Pretrain/Loss (Raw)": 2.0530550479888916, "Pretrain/Step": 4509, "Pretrain/Step Time": 8.480050830170512} +{"Pretrain/Learning Rate": 2.8394291344221724e-05, "Pretrain/Loss": 2.0207865238189697, "Pretrain/Loss (Raw)": 2.00227952003479, "Pretrain/Step": 4510, "Pretrain/Step Time": 8.47777672111988} +{"Pretrain/Learning Rate": 2.8385878981056662e-05, "Pretrain/Loss": 2.020683765411377, "Pretrain/Loss (Raw)": 2.116652727127075, "Pretrain/Step": 4511, "Pretrain/Step Time": 8.480223089456558} +{"Pretrain/Learning Rate": 2.837746622733165e-05, "Pretrain/Loss": 2.0217957496643066, "Pretrain/Loss (Raw)": 2.0606727600097656, "Pretrain/Step": 4512, "Pretrain/Step Time": 8.477634187787771} +{"Pretrain/Learning Rate": 2.8369053084017094e-05, "Pretrain/Loss": 2.020967721939087, "Pretrain/Loss (Raw)": 2.0180704593658447, "Pretrain/Step": 4513, "Pretrain/Step Time": 8.478221585974097} +{"Pretrain/Learning Rate": 2.8360639552083455e-05, "Pretrain/Loss": 2.0241968631744385, "Pretrain/Loss (Raw)": 2.1491246223449707, "Pretrain/Step": 4514, "Pretrain/Step Time": 8.47476577758789} +{"Pretrain/Learning Rate": 2.8352225632501224e-05, "Pretrain/Loss": 2.023742198944092, "Pretrain/Loss (Raw)": 1.9640214443206787, "Pretrain/Step": 4515, "Pretrain/Step Time": 8.472785778343678} +{"Pretrain/Learning Rate": 2.8343811326240945e-05, "Pretrain/Loss": 2.0235860347747803, "Pretrain/Loss (Raw)": 1.9898185729980469, "Pretrain/Step": 4516, "Pretrain/Step Time": 8.471566807478666} +{"Pretrain/Learning Rate": 2.833539663427319e-05, "Pretrain/Loss": 2.0243701934814453, "Pretrain/Loss (Raw)": 2.0699543952941895, "Pretrain/Step": 4517, "Pretrain/Step Time": 8.473927656188607} +{"Pretrain/Learning Rate": 2.8326981557568622e-05, "Pretrain/Loss": 2.0255441665649414, "Pretrain/Loss (Raw)": 2.165447235107422, "Pretrain/Step": 4518, "Pretrain/Step Time": 8.471159067004919} +{"Pretrain/Learning Rate": 2.831856609709789e-05, "Pretrain/Loss": 2.025839328765869, "Pretrain/Loss (Raw)": 2.111783266067505, "Pretrain/Step": 4519, "Pretrain/Step Time": 8.473823700100183} +{"Pretrain/Learning Rate": 2.831015025383173e-05, "Pretrain/Loss": 2.0264081954956055, "Pretrain/Loss (Raw)": 2.1862869262695312, "Pretrain/Step": 4520, "Pretrain/Step Time": 8.476701078936458} +{"Pretrain/Learning Rate": 2.8301734028740905e-05, "Pretrain/Loss": 2.0268850326538086, "Pretrain/Loss (Raw)": 2.2623493671417236, "Pretrain/Step": 4521, "Pretrain/Step Time": 8.477340914309025} +{"Pretrain/Learning Rate": 2.8293317422796217e-05, "Pretrain/Loss": 2.025547742843628, "Pretrain/Loss (Raw)": 1.929853081703186, "Pretrain/Step": 4522, "Pretrain/Step Time": 8.472786575555801} +{"Pretrain/Learning Rate": 2.8284900436968527e-05, "Pretrain/Loss": 2.0255870819091797, "Pretrain/Loss (Raw)": 2.0169849395751953, "Pretrain/Step": 4523, "Pretrain/Step Time": 8.473577672615647} +{"Pretrain/Learning Rate": 2.8276483072228715e-05, "Pretrain/Loss": 2.026332378387451, "Pretrain/Loss (Raw)": 2.096980333328247, "Pretrain/Step": 4524, "Pretrain/Step Time": 8.477056691423059} +{"Pretrain/Learning Rate": 2.826806532954773e-05, "Pretrain/Loss": 2.0250654220581055, "Pretrain/Loss (Raw)": 2.0640361309051514, "Pretrain/Step": 4525, "Pretrain/Step Time": 8.476204501464963} +{"Pretrain/Learning Rate": 2.8259647209896572e-05, "Pretrain/Loss": 2.0262033939361572, "Pretrain/Loss (Raw)": 2.1618990898132324, "Pretrain/Step": 4526, "Pretrain/Step Time": 8.473910147324204} +{"Pretrain/Learning Rate": 2.8251228714246246e-05, "Pretrain/Loss": 2.0249433517456055, "Pretrain/Loss (Raw)": 1.8857839107513428, "Pretrain/Step": 4527, "Pretrain/Step Time": 8.478742888197303} +{"Pretrain/Learning Rate": 2.824280984356783e-05, "Pretrain/Loss": 2.019774913787842, "Pretrain/Loss (Raw)": 1.4986401796340942, "Pretrain/Step": 4528, "Pretrain/Step Time": 8.480482384562492} +{"Pretrain/Learning Rate": 2.8234390598832437e-05, "Pretrain/Loss": 2.0193252563476562, "Pretrain/Loss (Raw)": 2.117335319519043, "Pretrain/Step": 4529, "Pretrain/Step Time": 8.47708679921925} +{"Pretrain/Learning Rate": 2.8225970981011233e-05, "Pretrain/Loss": 2.017031669616699, "Pretrain/Loss (Raw)": 1.9114807844161987, "Pretrain/Step": 4530, "Pretrain/Step Time": 8.475280530750751} +{"Pretrain/Learning Rate": 2.821755099107541e-05, "Pretrain/Loss": 2.0164263248443604, "Pretrain/Loss (Raw)": 2.0531625747680664, "Pretrain/Step": 4531, "Pretrain/Step Time": 8.476717052981257} +{"Pretrain/Learning Rate": 2.82091306299962e-05, "Pretrain/Loss": 2.015930414199829, "Pretrain/Loss (Raw)": 2.101414680480957, "Pretrain/Step": 4532, "Pretrain/Step Time": 8.475380636751652} +{"Pretrain/Learning Rate": 2.8200709898744902e-05, "Pretrain/Loss": 2.015040874481201, "Pretrain/Loss (Raw)": 2.0796220302581787, "Pretrain/Step": 4533, "Pretrain/Step Time": 8.47838644683361} +{"Pretrain/Learning Rate": 2.8192288798292847e-05, "Pretrain/Loss": 2.014643430709839, "Pretrain/Loss (Raw)": 2.006026029586792, "Pretrain/Step": 4534, "Pretrain/Step Time": 8.47825831361115} +{"Pretrain/Learning Rate": 2.8183867329611395e-05, "Pretrain/Loss": 2.0139665603637695, "Pretrain/Loss (Raw)": 1.9668954610824585, "Pretrain/Step": 4535, "Pretrain/Step Time": 8.475763723254204} +{"Pretrain/Learning Rate": 2.8175445493671972e-05, "Pretrain/Loss": 2.0135397911071777, "Pretrain/Loss (Raw)": 1.9780235290527344, "Pretrain/Step": 4536, "Pretrain/Step Time": 8.477624168619514} +{"Pretrain/Learning Rate": 2.8167023291446022e-05, "Pretrain/Loss": 2.0134470462799072, "Pretrain/Loss (Raw)": 2.0260162353515625, "Pretrain/Step": 4537, "Pretrain/Step Time": 8.482028149068356} +{"Pretrain/Learning Rate": 2.8158600723905055e-05, "Pretrain/Loss": 2.016698122024536, "Pretrain/Loss (Raw)": 2.1143646240234375, "Pretrain/Step": 4538, "Pretrain/Step Time": 8.474083395674825} +{"Pretrain/Learning Rate": 2.8150177792020604e-05, "Pretrain/Loss": 2.0157432556152344, "Pretrain/Loss (Raw)": 2.017380475997925, "Pretrain/Step": 4539, "Pretrain/Step Time": 8.481565361842513} +{"Pretrain/Learning Rate": 2.8141754496764244e-05, "Pretrain/Loss": 2.015465259552002, "Pretrain/Loss (Raw)": 1.7882474660873413, "Pretrain/Step": 4540, "Pretrain/Step Time": 8.484397046267986} +{"Pretrain/Learning Rate": 2.8133330839107608e-05, "Pretrain/Loss": 2.0141489505767822, "Pretrain/Loss (Raw)": 1.937878131866455, "Pretrain/Step": 4541, "Pretrain/Step Time": 8.48222803324461} +{"Pretrain/Learning Rate": 2.8124906820022366e-05, "Pretrain/Loss": 2.0141284465789795, "Pretrain/Loss (Raw)": 2.1302731037139893, "Pretrain/Step": 4542, "Pretrain/Step Time": 8.482427464798093} +{"Pretrain/Learning Rate": 2.8116482440480218e-05, "Pretrain/Loss": 2.013735771179199, "Pretrain/Loss (Raw)": 1.9935963153839111, "Pretrain/Step": 4543, "Pretrain/Step Time": 8.485043166205287} +{"Pretrain/Learning Rate": 2.8108057701452915e-05, "Pretrain/Loss": 2.011580467224121, "Pretrain/Loss (Raw)": 1.8743165731430054, "Pretrain/Step": 4544, "Pretrain/Step Time": 8.486577972769737} +{"Pretrain/Learning Rate": 2.8099632603912247e-05, "Pretrain/Loss": 2.0116007328033447, "Pretrain/Loss (Raw)": 2.1311182975769043, "Pretrain/Step": 4545, "Pretrain/Step Time": 8.48593857884407} +{"Pretrain/Learning Rate": 2.8091207148830044e-05, "Pretrain/Loss": 2.0118026733398438, "Pretrain/Loss (Raw)": 1.8804614543914795, "Pretrain/Step": 4546, "Pretrain/Step Time": 8.482535563409328} +{"Pretrain/Learning Rate": 2.8082781337178195e-05, "Pretrain/Loss": 2.0138766765594482, "Pretrain/Loss (Raw)": 2.0492639541625977, "Pretrain/Step": 4547, "Pretrain/Step Time": 8.478243900462985} +{"Pretrain/Learning Rate": 2.8074355169928603e-05, "Pretrain/Loss": 2.014103412628174, "Pretrain/Loss (Raw)": 2.086141586303711, "Pretrain/Step": 4548, "Pretrain/Step Time": 8.478557946160436} +{"Pretrain/Learning Rate": 2.8065928648053207e-05, "Pretrain/Loss": 2.0129029750823975, "Pretrain/Loss (Raw)": 2.00882625579834, "Pretrain/Step": 4549, "Pretrain/Step Time": 8.479092303663492} +{"Pretrain/Learning Rate": 2.805750177252403e-05, "Pretrain/Loss": 2.017467498779297, "Pretrain/Loss (Raw)": 2.233043909072876, "Pretrain/Step": 4550, "Pretrain/Step Time": 8.480666613206267} +{"Pretrain/Learning Rate": 2.8049074544313094e-05, "Pretrain/Loss": 2.016165256500244, "Pretrain/Loss (Raw)": 1.9906744956970215, "Pretrain/Step": 4551, "Pretrain/Step Time": 8.48491377942264} +{"Pretrain/Learning Rate": 2.8040646964392482e-05, "Pretrain/Loss": 2.014493465423584, "Pretrain/Loss (Raw)": 1.9716482162475586, "Pretrain/Step": 4552, "Pretrain/Step Time": 8.48435040563345} +{"Pretrain/Learning Rate": 2.8032219033734308e-05, "Pretrain/Loss": 2.01425838470459, "Pretrain/Loss (Raw)": 2.0510315895080566, "Pretrain/Step": 4553, "Pretrain/Step Time": 8.488754235208035} +{"Pretrain/Learning Rate": 2.8023790753310737e-05, "Pretrain/Loss": 2.014044761657715, "Pretrain/Loss (Raw)": 2.109999656677246, "Pretrain/Step": 4554, "Pretrain/Step Time": 8.484044628217816} +{"Pretrain/Learning Rate": 2.8015362124093968e-05, "Pretrain/Loss": 2.0134873390197754, "Pretrain/Loss (Raw)": 2.1045312881469727, "Pretrain/Step": 4555, "Pretrain/Step Time": 8.483878243714571} +{"Pretrain/Learning Rate": 2.8006933147056234e-05, "Pretrain/Loss": 2.0115902423858643, "Pretrain/Loss (Raw)": 1.9899401664733887, "Pretrain/Step": 4556, "Pretrain/Step Time": 8.48348694294691} +{"Pretrain/Learning Rate": 2.7998503823169818e-05, "Pretrain/Loss": 2.011448860168457, "Pretrain/Loss (Raw)": 2.050793170928955, "Pretrain/Step": 4557, "Pretrain/Step Time": 8.481651844456792} +{"Pretrain/Learning Rate": 2.799007415340705e-05, "Pretrain/Loss": 2.0121777057647705, "Pretrain/Loss (Raw)": 2.202904224395752, "Pretrain/Step": 4558, "Pretrain/Step Time": 8.481918953359127} +{"Pretrain/Learning Rate": 2.7981644138740267e-05, "Pretrain/Loss": 2.011998414993286, "Pretrain/Loss (Raw)": 2.0305399894714355, "Pretrain/Step": 4559, "Pretrain/Step Time": 8.481506424024701} +{"Pretrain/Learning Rate": 2.7973213780141882e-05, "Pretrain/Loss": 2.012382984161377, "Pretrain/Loss (Raw)": 2.0671768188476562, "Pretrain/Step": 4560, "Pretrain/Step Time": 8.484493428841233} +{"Pretrain/Learning Rate": 2.7964783078584333e-05, "Pretrain/Loss": 2.0130419731140137, "Pretrain/Loss (Raw)": 1.9450932741165161, "Pretrain/Step": 4561, "Pretrain/Step Time": 8.485407197847962} +{"Pretrain/Learning Rate": 2.7956352035040094e-05, "Pretrain/Loss": 2.0131945610046387, "Pretrain/Loss (Raw)": 2.112590789794922, "Pretrain/Step": 4562, "Pretrain/Step Time": 8.480216002091765} +{"Pretrain/Learning Rate": 2.7947920650481695e-05, "Pretrain/Loss": 2.0135881900787354, "Pretrain/Loss (Raw)": 2.0252630710601807, "Pretrain/Step": 4563, "Pretrain/Step Time": 8.480466309934855} +{"Pretrain/Learning Rate": 2.7939488925881685e-05, "Pretrain/Loss": 2.013965129852295, "Pretrain/Loss (Raw)": 2.0314385890960693, "Pretrain/Step": 4564, "Pretrain/Step Time": 8.4801828507334} +{"Pretrain/Learning Rate": 2.7931056862212652e-05, "Pretrain/Loss": 2.012296199798584, "Pretrain/Loss (Raw)": 1.6954039335250854, "Pretrain/Step": 4565, "Pretrain/Step Time": 8.480780832469463} +{"Pretrain/Learning Rate": 2.792262446044725e-05, "Pretrain/Loss": 2.0142135620117188, "Pretrain/Loss (Raw)": 2.0562777519226074, "Pretrain/Step": 4566, "Pretrain/Step Time": 8.479352692142129} +{"Pretrain/Learning Rate": 2.7914191721558135e-05, "Pretrain/Loss": 2.0138094425201416, "Pretrain/Loss (Raw)": 1.967576026916504, "Pretrain/Step": 4567, "Pretrain/Step Time": 8.484783060848713} +{"Pretrain/Learning Rate": 2.790575864651803e-05, "Pretrain/Loss": 2.012322425842285, "Pretrain/Loss (Raw)": 1.9108843803405762, "Pretrain/Step": 4568, "Pretrain/Step Time": 8.485058438032866} +{"Pretrain/Learning Rate": 2.7897325236299688e-05, "Pretrain/Loss": 2.0122830867767334, "Pretrain/Loss (Raw)": 2.1774446964263916, "Pretrain/Step": 4569, "Pretrain/Step Time": 8.481843838468194} +{"Pretrain/Learning Rate": 2.7888891491875897e-05, "Pretrain/Loss": 2.0119547843933105, "Pretrain/Loss (Raw)": 2.0427563190460205, "Pretrain/Step": 4570, "Pretrain/Step Time": 8.485041227191687} +{"Pretrain/Learning Rate": 2.788045741421949e-05, "Pretrain/Loss": 2.011296272277832, "Pretrain/Loss (Raw)": 2.0702412128448486, "Pretrain/Step": 4571, "Pretrain/Step Time": 8.487156931310892} +{"Pretrain/Learning Rate": 2.7872023004303337e-05, "Pretrain/Loss": 2.0119073390960693, "Pretrain/Loss (Raw)": 1.9655423164367676, "Pretrain/Step": 4572, "Pretrain/Step Time": 8.481910115107894} +{"Pretrain/Learning Rate": 2.786358826310034e-05, "Pretrain/Loss": 2.013127326965332, "Pretrain/Loss (Raw)": 2.2532689571380615, "Pretrain/Step": 4573, "Pretrain/Step Time": 8.48498097807169} +{"Pretrain/Learning Rate": 2.7855153191583432e-05, "Pretrain/Loss": 2.0131447315216064, "Pretrain/Loss (Raw)": 2.0809195041656494, "Pretrain/Step": 4574, "Pretrain/Step Time": 8.484524443745613} +{"Pretrain/Learning Rate": 2.7846717790725614e-05, "Pretrain/Loss": 2.0113871097564697, "Pretrain/Loss (Raw)": 1.7855921983718872, "Pretrain/Step": 4575, "Pretrain/Step Time": 8.486619360744953} +{"Pretrain/Learning Rate": 2.78382820614999e-05, "Pretrain/Loss": 2.0118377208709717, "Pretrain/Loss (Raw)": 2.0897717475891113, "Pretrain/Step": 4576, "Pretrain/Step Time": 8.487438192591071} +{"Pretrain/Learning Rate": 2.7829846004879338e-05, "Pretrain/Loss": 2.011950969696045, "Pretrain/Loss (Raw)": 2.0687925815582275, "Pretrain/Step": 4577, "Pretrain/Step Time": 8.485978310927749} +{"Pretrain/Learning Rate": 2.782140962183704e-05, "Pretrain/Loss": 2.011845588684082, "Pretrain/Loss (Raw)": 1.9770681858062744, "Pretrain/Step": 4578, "Pretrain/Step Time": 8.487066466361284} +{"Pretrain/Learning Rate": 2.781297291334614e-05, "Pretrain/Loss": 2.012113094329834, "Pretrain/Loss (Raw)": 2.0334632396698, "Pretrain/Step": 4579, "Pretrain/Step Time": 8.488927097991109} +{"Pretrain/Learning Rate": 2.78045358803798e-05, "Pretrain/Loss": 2.0165624618530273, "Pretrain/Loss (Raw)": 2.0841336250305176, "Pretrain/Step": 4580, "Pretrain/Step Time": 8.483976813033223} +{"Pretrain/Learning Rate": 2.779609852391123e-05, "Pretrain/Loss": 2.0145761966705322, "Pretrain/Loss (Raw)": 1.9095680713653564, "Pretrain/Step": 4581, "Pretrain/Step Time": 8.484383456408978} +{"Pretrain/Learning Rate": 2.7787660844913676e-05, "Pretrain/Loss": 2.0124635696411133, "Pretrain/Loss (Raw)": 1.7401241064071655, "Pretrain/Step": 4582, "Pretrain/Step Time": 8.483950449153781} +{"Pretrain/Learning Rate": 2.7779222844360426e-05, "Pretrain/Loss": 2.0127835273742676, "Pretrain/Loss (Raw)": 2.054595470428467, "Pretrain/Step": 4583, "Pretrain/Step Time": 8.48330290056765} +{"Pretrain/Learning Rate": 2.7770784523224796e-05, "Pretrain/Loss": 2.01261305809021, "Pretrain/Loss (Raw)": 2.0030887126922607, "Pretrain/Step": 4584, "Pretrain/Step Time": 8.484413066878915} +{"Pretrain/Learning Rate": 2.7762345882480144e-05, "Pretrain/Loss": 2.0151710510253906, "Pretrain/Loss (Raw)": 2.142716884613037, "Pretrain/Step": 4585, "Pretrain/Step Time": 8.486386036500335} +{"Pretrain/Learning Rate": 2.7753906923099865e-05, "Pretrain/Loss": 2.015805244445801, "Pretrain/Loss (Raw)": 2.1394622325897217, "Pretrain/Step": 4586, "Pretrain/Step Time": 8.486207211390138} +{"Pretrain/Learning Rate": 2.7745467646057393e-05, "Pretrain/Loss": 2.015148878097534, "Pretrain/Loss (Raw)": 1.9874217510223389, "Pretrain/Step": 4587, "Pretrain/Step Time": 8.485165528953075} +{"Pretrain/Learning Rate": 2.7737028052326188e-05, "Pretrain/Loss": 2.0147647857666016, "Pretrain/Loss (Raw)": 1.982442021369934, "Pretrain/Step": 4588, "Pretrain/Step Time": 8.488105453550816} +{"Pretrain/Learning Rate": 2.7728588142879762e-05, "Pretrain/Loss": 2.0159428119659424, "Pretrain/Loss (Raw)": 2.1907308101654053, "Pretrain/Step": 4589, "Pretrain/Step Time": 8.482487596571445} +{"Pretrain/Learning Rate": 2.7720147918691658e-05, "Pretrain/Loss": 2.0154881477355957, "Pretrain/Loss (Raw)": 1.8582019805908203, "Pretrain/Step": 4590, "Pretrain/Step Time": 8.483593901619315} +{"Pretrain/Learning Rate": 2.771170738073544e-05, "Pretrain/Loss": 2.015510082244873, "Pretrain/Loss (Raw)": 2.122878313064575, "Pretrain/Step": 4591, "Pretrain/Step Time": 8.485161747783422} +{"Pretrain/Learning Rate": 2.7703266529984734e-05, "Pretrain/Loss": 2.015261173248291, "Pretrain/Loss (Raw)": 1.9624162912368774, "Pretrain/Step": 4592, "Pretrain/Step Time": 8.485452292487025} +{"Pretrain/Learning Rate": 2.7694825367413178e-05, "Pretrain/Loss": 2.017026424407959, "Pretrain/Loss (Raw)": 2.140692949295044, "Pretrain/Step": 4593, "Pretrain/Step Time": 8.483525715768337} +{"Pretrain/Learning Rate": 2.7686383893994473e-05, "Pretrain/Loss": 2.0175745487213135, "Pretrain/Loss (Raw)": 2.1739087104797363, "Pretrain/Step": 4594, "Pretrain/Step Time": 8.48235396668315} +{"Pretrain/Learning Rate": 2.767794211070232e-05, "Pretrain/Loss": 2.019120693206787, "Pretrain/Loss (Raw)": 1.9913861751556396, "Pretrain/Step": 4595, "Pretrain/Step Time": 8.48128666356206} +{"Pretrain/Learning Rate": 2.7669500018510485e-05, "Pretrain/Loss": 2.020901679992676, "Pretrain/Loss (Raw)": 2.0666515827178955, "Pretrain/Step": 4596, "Pretrain/Step Time": 8.482311259955168} +{"Pretrain/Learning Rate": 2.7661057618392765e-05, "Pretrain/Loss": 2.020998001098633, "Pretrain/Loss (Raw)": 2.1240954399108887, "Pretrain/Step": 4597, "Pretrain/Step Time": 8.481275826692581} +{"Pretrain/Learning Rate": 2.7652614911322987e-05, "Pretrain/Loss": 2.021176815032959, "Pretrain/Loss (Raw)": 2.0484204292297363, "Pretrain/Step": 4598, "Pretrain/Step Time": 8.482256105169654} +{"Pretrain/Learning Rate": 2.7644171898275008e-05, "Pretrain/Loss": 2.021696090698242, "Pretrain/Loss (Raw)": 2.0657389163970947, "Pretrain/Step": 4599, "Pretrain/Step Time": 8.48183398321271} +{"Pretrain/Learning Rate": 2.763572858022273e-05, "Pretrain/Loss": 2.0198230743408203, "Pretrain/Loss (Raw)": 1.6648294925689697, "Pretrain/Step": 4600, "Pretrain/Step Time": 8.484031647443771} +{"Pretrain/Learning Rate": 2.762728495814008e-05, "Pretrain/Loss": 2.0176453590393066, "Pretrain/Loss (Raw)": 1.961487889289856, "Pretrain/Step": 4601, "Pretrain/Step Time": 8.482767544686794} +{"Pretrain/Learning Rate": 2.7618841033001047e-05, "Pretrain/Loss": 2.016822099685669, "Pretrain/Loss (Raw)": 1.9998778104782104, "Pretrain/Step": 4602, "Pretrain/Step Time": 8.487756930291653} +{"Pretrain/Learning Rate": 2.761039680577961e-05, "Pretrain/Loss": 2.0163931846618652, "Pretrain/Loss (Raw)": 1.9803118705749512, "Pretrain/Step": 4603, "Pretrain/Step Time": 8.484068544581532} +{"Pretrain/Learning Rate": 2.7601952277449816e-05, "Pretrain/Loss": 2.018474578857422, "Pretrain/Loss (Raw)": 2.154780626296997, "Pretrain/Step": 4604, "Pretrain/Step Time": 8.484980007633567} +{"Pretrain/Learning Rate": 2.759350744898575e-05, "Pretrain/Loss": 2.016315460205078, "Pretrain/Loss (Raw)": 1.9388930797576904, "Pretrain/Step": 4605, "Pretrain/Step Time": 8.48926605656743} +{"Pretrain/Learning Rate": 2.7585062321361516e-05, "Pretrain/Loss": 2.016829490661621, "Pretrain/Loss (Raw)": 2.0516517162323, "Pretrain/Step": 4606, "Pretrain/Step Time": 8.488185392692685} +{"Pretrain/Learning Rate": 2.757661689555124e-05, "Pretrain/Loss": 2.0186614990234375, "Pretrain/Loss (Raw)": 2.1824331283569336, "Pretrain/Step": 4607, "Pretrain/Step Time": 8.488265508785844} +{"Pretrain/Learning Rate": 2.7568171172529118e-05, "Pretrain/Loss": 2.018336772918701, "Pretrain/Loss (Raw)": 2.0185699462890625, "Pretrain/Step": 4608, "Pretrain/Step Time": 8.49087768048048} +{"Pretrain/Learning Rate": 2.7559725153269346e-05, "Pretrain/Loss": 2.018949508666992, "Pretrain/Loss (Raw)": 2.1642301082611084, "Pretrain/Step": 4609, "Pretrain/Step Time": 8.49056770466268} +{"Pretrain/Learning Rate": 2.7551278838746185e-05, "Pretrain/Loss": 2.0199670791625977, "Pretrain/Loss (Raw)": 1.9614213705062866, "Pretrain/Step": 4610, "Pretrain/Step Time": 8.488034192472696} +{"Pretrain/Learning Rate": 2.75428322299339e-05, "Pretrain/Loss": 2.0193514823913574, "Pretrain/Loss (Raw)": 2.019932270050049, "Pretrain/Step": 4611, "Pretrain/Step Time": 8.48571603000164} +{"Pretrain/Learning Rate": 2.753438532780681e-05, "Pretrain/Loss": 2.0210623741149902, "Pretrain/Loss (Raw)": 2.285738468170166, "Pretrain/Step": 4612, "Pretrain/Step Time": 8.490400027483702} +{"Pretrain/Learning Rate": 2.7525938133339273e-05, "Pretrain/Loss": 2.021272659301758, "Pretrain/Loss (Raw)": 2.0194716453552246, "Pretrain/Step": 4613, "Pretrain/Step Time": 8.490571754053235} +{"Pretrain/Learning Rate": 2.7517490647505658e-05, "Pretrain/Loss": 2.0219037532806396, "Pretrain/Loss (Raw)": 2.070760726928711, "Pretrain/Step": 4614, "Pretrain/Step Time": 8.491669107228518} +{"Pretrain/Learning Rate": 2.7509042871280372e-05, "Pretrain/Loss": 2.021937608718872, "Pretrain/Loss (Raw)": 2.0167641639709473, "Pretrain/Step": 4615, "Pretrain/Step Time": 8.489737724885345} +{"Pretrain/Learning Rate": 2.750059480563788e-05, "Pretrain/Loss": 2.021810531616211, "Pretrain/Loss (Raw)": 1.9992918968200684, "Pretrain/Step": 4616, "Pretrain/Step Time": 8.489035591483116} +{"Pretrain/Learning Rate": 2.7492146451552654e-05, "Pretrain/Loss": 2.0237910747528076, "Pretrain/Loss (Raw)": 2.082155466079712, "Pretrain/Step": 4617, "Pretrain/Step Time": 8.49110222607851} +{"Pretrain/Learning Rate": 2.7483697809999214e-05, "Pretrain/Loss": 2.0233421325683594, "Pretrain/Loss (Raw)": 1.9392366409301758, "Pretrain/Step": 4618, "Pretrain/Step Time": 8.488862294703722} +{"Pretrain/Learning Rate": 2.74752488819521e-05, "Pretrain/Loss": 2.022488832473755, "Pretrain/Loss (Raw)": 1.9638937711715698, "Pretrain/Step": 4619, "Pretrain/Step Time": 8.485475696623325} +{"Pretrain/Learning Rate": 2.7466799668385896e-05, "Pretrain/Loss": 2.022838592529297, "Pretrain/Loss (Raw)": 2.070493698120117, "Pretrain/Step": 4620, "Pretrain/Step Time": 8.483541695401073} +{"Pretrain/Learning Rate": 2.745835017027522e-05, "Pretrain/Loss": 2.022498607635498, "Pretrain/Loss (Raw)": 1.9064209461212158, "Pretrain/Step": 4621, "Pretrain/Step Time": 8.485672296956182} +{"Pretrain/Learning Rate": 2.7449900388594718e-05, "Pretrain/Loss": 2.0233757495880127, "Pretrain/Loss (Raw)": 2.1414284706115723, "Pretrain/Step": 4622, "Pretrain/Step Time": 8.484200544655323} +{"Pretrain/Learning Rate": 2.7441450324319068e-05, "Pretrain/Loss": 2.022996425628662, "Pretrain/Loss (Raw)": 1.6867218017578125, "Pretrain/Step": 4623, "Pretrain/Step Time": 8.484778631478548} +{"Pretrain/Learning Rate": 2.7432999978422974e-05, "Pretrain/Loss": 2.0225319862365723, "Pretrain/Loss (Raw)": 2.12819504737854, "Pretrain/Step": 4624, "Pretrain/Step Time": 8.485541764646769} +{"Pretrain/Learning Rate": 2.7424549351881192e-05, "Pretrain/Loss": 2.022738456726074, "Pretrain/Loss (Raw)": 1.8738579750061035, "Pretrain/Step": 4625, "Pretrain/Step Time": 8.489126594737172} +{"Pretrain/Learning Rate": 2.7416098445668497e-05, "Pretrain/Loss": 2.023826837539673, "Pretrain/Loss (Raw)": 2.05304217338562, "Pretrain/Step": 4626, "Pretrain/Step Time": 8.48898491077125} +{"Pretrain/Learning Rate": 2.740764726075969e-05, "Pretrain/Loss": 2.023963212966919, "Pretrain/Loss (Raw)": 1.9092440605163574, "Pretrain/Step": 4627, "Pretrain/Step Time": 8.489637775346637} +{"Pretrain/Learning Rate": 2.739919579812961e-05, "Pretrain/Loss": 2.02315092086792, "Pretrain/Loss (Raw)": 1.9549052715301514, "Pretrain/Step": 4628, "Pretrain/Step Time": 8.490780441090465} +{"Pretrain/Learning Rate": 2.7390744058753155e-05, "Pretrain/Loss": 2.0252604484558105, "Pretrain/Loss (Raw)": 2.062389373779297, "Pretrain/Step": 4629, "Pretrain/Step Time": 8.489764586091042} +{"Pretrain/Learning Rate": 2.7382292043605207e-05, "Pretrain/Loss": 2.0242738723754883, "Pretrain/Loss (Raw)": 2.0642261505126953, "Pretrain/Step": 4630, "Pretrain/Step Time": 8.489591166377068} +{"Pretrain/Learning Rate": 2.7373839753660706e-05, "Pretrain/Loss": 2.023815631866455, "Pretrain/Loss (Raw)": 2.043637990951538, "Pretrain/Step": 4631, "Pretrain/Step Time": 8.48872047662735} +{"Pretrain/Learning Rate": 2.7365387189894624e-05, "Pretrain/Loss": 2.0235188007354736, "Pretrain/Loss (Raw)": 2.0701839923858643, "Pretrain/Step": 4632, "Pretrain/Step Time": 8.49216554313898} +{"Pretrain/Learning Rate": 2.735693435328196e-05, "Pretrain/Loss": 2.02553653717041, "Pretrain/Loss (Raw)": 2.1916911602020264, "Pretrain/Step": 4633, "Pretrain/Step Time": 8.486613841727376} +{"Pretrain/Learning Rate": 2.7348481244797752e-05, "Pretrain/Loss": 2.0254838466644287, "Pretrain/Loss (Raw)": 1.9598650932312012, "Pretrain/Step": 4634, "Pretrain/Step Time": 8.490981716662645} +{"Pretrain/Learning Rate": 2.7340027865417055e-05, "Pretrain/Loss": 2.0274131298065186, "Pretrain/Loss (Raw)": 1.828939437866211, "Pretrain/Step": 4635, "Pretrain/Step Time": 8.489621056243777} +{"Pretrain/Learning Rate": 2.7331574216114964e-05, "Pretrain/Loss": 2.0238730907440186, "Pretrain/Loss (Raw)": 1.6988897323608398, "Pretrain/Step": 4636, "Pretrain/Step Time": 8.486093066632748} +{"Pretrain/Learning Rate": 2.7323120297866604e-05, "Pretrain/Loss": 2.024740219116211, "Pretrain/Loss (Raw)": 2.1640522480010986, "Pretrain/Step": 4637, "Pretrain/Step Time": 8.4885313808918} +{"Pretrain/Learning Rate": 2.731466611164714e-05, "Pretrain/Loss": 2.0257105827331543, "Pretrain/Loss (Raw)": 2.1264965534210205, "Pretrain/Step": 4638, "Pretrain/Step Time": 8.488471856340766} +{"Pretrain/Learning Rate": 2.730621165843175e-05, "Pretrain/Loss": 2.024110794067383, "Pretrain/Loss (Raw)": 1.911876916885376, "Pretrain/Step": 4639, "Pretrain/Step Time": 8.487065160647035} +{"Pretrain/Learning Rate": 2.7297756939195662e-05, "Pretrain/Loss": 2.0233991146087646, "Pretrain/Loss (Raw)": 1.9695734977722168, "Pretrain/Step": 4640, "Pretrain/Step Time": 8.48806618526578} +{"Pretrain/Learning Rate": 2.728930195491411e-05, "Pretrain/Loss": 2.022679567337036, "Pretrain/Loss (Raw)": 1.9259557723999023, "Pretrain/Step": 4641, "Pretrain/Step Time": 8.491310983896255} +{"Pretrain/Learning Rate": 2.728084670656239e-05, "Pretrain/Loss": 2.021846294403076, "Pretrain/Loss (Raw)": 2.0425024032592773, "Pretrain/Step": 4642, "Pretrain/Step Time": 8.493713807314634} +{"Pretrain/Learning Rate": 2.72723911951158e-05, "Pretrain/Loss": 2.023066997528076, "Pretrain/Loss (Raw)": 2.120274066925049, "Pretrain/Step": 4643, "Pretrain/Step Time": 8.493375357240438} +{"Pretrain/Learning Rate": 2.7263935421549684e-05, "Pretrain/Loss": 2.022772789001465, "Pretrain/Loss (Raw)": 1.952152967453003, "Pretrain/Step": 4644, "Pretrain/Step Time": 8.491155428811908} +{"Pretrain/Learning Rate": 2.725547938683941e-05, "Pretrain/Loss": 2.0234766006469727, "Pretrain/Loss (Raw)": 2.1600284576416016, "Pretrain/Step": 4645, "Pretrain/Step Time": 8.489295037463307} +{"Pretrain/Learning Rate": 2.7247023091960376e-05, "Pretrain/Loss": 2.021975040435791, "Pretrain/Loss (Raw)": 1.9732598066329956, "Pretrain/Step": 4646, "Pretrain/Step Time": 8.4883216265589} +{"Pretrain/Learning Rate": 2.7238566537888033e-05, "Pretrain/Loss": 2.022556781768799, "Pretrain/Loss (Raw)": 2.1862471103668213, "Pretrain/Step": 4647, "Pretrain/Step Time": 8.487536182627082} +{"Pretrain/Learning Rate": 2.7230109725597825e-05, "Pretrain/Loss": 2.0222504138946533, "Pretrain/Loss (Raw)": 2.1470534801483154, "Pretrain/Step": 4648, "Pretrain/Step Time": 8.491833603009582} +{"Pretrain/Learning Rate": 2.722165265606523e-05, "Pretrain/Loss": 2.019615888595581, "Pretrain/Loss (Raw)": 1.9251272678375244, "Pretrain/Step": 4649, "Pretrain/Step Time": 8.488817159086466} +{"Pretrain/Learning Rate": 2.7213195330265795e-05, "Pretrain/Loss": 2.020721673965454, "Pretrain/Loss (Raw)": 2.0714077949523926, "Pretrain/Step": 4650, "Pretrain/Step Time": 8.489481721073389} +{"Pretrain/Learning Rate": 2.7204737749175046e-05, "Pretrain/Loss": 2.0207648277282715, "Pretrain/Loss (Raw)": 2.022533655166626, "Pretrain/Step": 4651, "Pretrain/Step Time": 8.488522406667471} +{"Pretrain/Learning Rate": 2.7196279913768584e-05, "Pretrain/Loss": 2.0200202465057373, "Pretrain/Loss (Raw)": 2.0016367435455322, "Pretrain/Step": 4652, "Pretrain/Step Time": 8.488884814083576} +{"Pretrain/Learning Rate": 2.7187821825021998e-05, "Pretrain/Loss": 2.0198283195495605, "Pretrain/Loss (Raw)": 2.0394461154937744, "Pretrain/Step": 4653, "Pretrain/Step Time": 8.489343367516994} +{"Pretrain/Learning Rate": 2.717936348391093e-05, "Pretrain/Loss": 2.0186333656311035, "Pretrain/Loss (Raw)": 2.008960485458374, "Pretrain/Step": 4654, "Pretrain/Step Time": 8.492467496544123} +{"Pretrain/Learning Rate": 2.717090489141106e-05, "Pretrain/Loss": 2.0194740295410156, "Pretrain/Loss (Raw)": 1.9933770895004272, "Pretrain/Step": 4655, "Pretrain/Step Time": 8.488209508359432} +{"Pretrain/Learning Rate": 2.716244604849807e-05, "Pretrain/Loss": 2.022228479385376, "Pretrain/Loss (Raw)": 1.8512572050094604, "Pretrain/Step": 4656, "Pretrain/Step Time": 8.487403266131878} +{"Pretrain/Learning Rate": 2.7153986956147687e-05, "Pretrain/Loss": 2.020629405975342, "Pretrain/Loss (Raw)": 1.912611722946167, "Pretrain/Step": 4657, "Pretrain/Step Time": 8.489146869629622} +{"Pretrain/Learning Rate": 2.7145527615335663e-05, "Pretrain/Loss": 2.021228790283203, "Pretrain/Loss (Raw)": 1.988232135772705, "Pretrain/Step": 4658, "Pretrain/Step Time": 8.48959918320179} +{"Pretrain/Learning Rate": 2.7137068027037787e-05, "Pretrain/Loss": 2.021322250366211, "Pretrain/Loss (Raw)": 2.0651230812072754, "Pretrain/Step": 4659, "Pretrain/Step Time": 8.486713582649827} +{"Pretrain/Learning Rate": 2.7128608192229867e-05, "Pretrain/Loss": 2.0218634605407715, "Pretrain/Loss (Raw)": 2.1706604957580566, "Pretrain/Step": 4660, "Pretrain/Step Time": 8.4899737611413} +{"Pretrain/Learning Rate": 2.7120148111887732e-05, "Pretrain/Loss": 2.022488594055176, "Pretrain/Loss (Raw)": 2.1596438884735107, "Pretrain/Step": 4661, "Pretrain/Step Time": 8.486003769561648} +{"Pretrain/Learning Rate": 2.711168778698726e-05, "Pretrain/Loss": 2.024092197418213, "Pretrain/Loss (Raw)": 2.2113168239593506, "Pretrain/Step": 4662, "Pretrain/Step Time": 8.485815174877644} +{"Pretrain/Learning Rate": 2.7103227218504345e-05, "Pretrain/Loss": 2.0247507095336914, "Pretrain/Loss (Raw)": 2.051187038421631, "Pretrain/Step": 4663, "Pretrain/Step Time": 8.487461898475885} +{"Pretrain/Learning Rate": 2.7094766407414917e-05, "Pretrain/Loss": 2.0257997512817383, "Pretrain/Loss (Raw)": 2.112271308898926, "Pretrain/Step": 4664, "Pretrain/Step Time": 8.490280751138926} +{"Pretrain/Learning Rate": 2.7086305354694907e-05, "Pretrain/Loss": 2.0257744789123535, "Pretrain/Loss (Raw)": 2.0228123664855957, "Pretrain/Step": 4665, "Pretrain/Step Time": 8.483891261741519} +{"Pretrain/Learning Rate": 2.7077844061320317e-05, "Pretrain/Loss": 2.023632764816284, "Pretrain/Loss (Raw)": 1.8402036428451538, "Pretrain/Step": 4666, "Pretrain/Step Time": 8.485303213819861} +{"Pretrain/Learning Rate": 2.706938252826714e-05, "Pretrain/Loss": 2.0225625038146973, "Pretrain/Loss (Raw)": 1.8804097175598145, "Pretrain/Step": 4667, "Pretrain/Step Time": 8.476251186802983} +{"Pretrain/Learning Rate": 2.7060920756511422e-05, "Pretrain/Loss": 2.023430347442627, "Pretrain/Loss (Raw)": 1.8993003368377686, "Pretrain/Step": 4668, "Pretrain/Step Time": 8.474934319034219} +{"Pretrain/Learning Rate": 2.705245874702921e-05, "Pretrain/Loss": 2.0238490104675293, "Pretrain/Loss (Raw)": 1.9914696216583252, "Pretrain/Step": 4669, "Pretrain/Step Time": 8.478066105395555} +{"Pretrain/Learning Rate": 2.7043996500796605e-05, "Pretrain/Loss": 2.0226659774780273, "Pretrain/Loss (Raw)": 1.9788509607315063, "Pretrain/Step": 4670, "Pretrain/Step Time": 8.481539446860552} +{"Pretrain/Learning Rate": 2.703553401878972e-05, "Pretrain/Loss": 2.0246381759643555, "Pretrain/Loss (Raw)": 2.2460224628448486, "Pretrain/Step": 4671, "Pretrain/Step Time": 8.477517185732722} +{"Pretrain/Learning Rate": 2.7027071301984713e-05, "Pretrain/Loss": 2.0250425338745117, "Pretrain/Loss (Raw)": 1.9261054992675781, "Pretrain/Step": 4672, "Pretrain/Step Time": 8.47767430357635} +{"Pretrain/Learning Rate": 2.701860835135773e-05, "Pretrain/Loss": 2.0236525535583496, "Pretrain/Loss (Raw)": 1.9531664848327637, "Pretrain/Step": 4673, "Pretrain/Step Time": 8.47653866559267} +{"Pretrain/Learning Rate": 2.7010145167884994e-05, "Pretrain/Loss": 2.025343894958496, "Pretrain/Loss (Raw)": 2.096993923187256, "Pretrain/Step": 4674, "Pretrain/Step Time": 8.478199174627662} +{"Pretrain/Learning Rate": 2.7001681752542713e-05, "Pretrain/Loss": 2.023226261138916, "Pretrain/Loss (Raw)": 1.7781871557235718, "Pretrain/Step": 4675, "Pretrain/Step Time": 8.479260737076402} +{"Pretrain/Learning Rate": 2.6993218106307145e-05, "Pretrain/Loss": 2.0231409072875977, "Pretrain/Loss (Raw)": 2.0752320289611816, "Pretrain/Step": 4676, "Pretrain/Step Time": 8.47901688888669} +{"Pretrain/Learning Rate": 2.698475423015457e-05, "Pretrain/Loss": 2.024479627609253, "Pretrain/Loss (Raw)": 2.180147409439087, "Pretrain/Step": 4677, "Pretrain/Step Time": 8.475039776414633} +{"Pretrain/Learning Rate": 2.6976290125061288e-05, "Pretrain/Loss": 2.021975040435791, "Pretrain/Loss (Raw)": 1.912487506866455, "Pretrain/Step": 4678, "Pretrain/Step Time": 8.47737111710012} +{"Pretrain/Learning Rate": 2.6967825792003644e-05, "Pretrain/Loss": 2.022566556930542, "Pretrain/Loss (Raw)": 2.066380023956299, "Pretrain/Step": 4679, "Pretrain/Step Time": 8.471579818055034} +{"Pretrain/Learning Rate": 2.6959361231957975e-05, "Pretrain/Loss": 2.024369239807129, "Pretrain/Loss (Raw)": 2.2024152278900146, "Pretrain/Step": 4680, "Pretrain/Step Time": 8.477592976763844} +{"Pretrain/Learning Rate": 2.6950896445900687e-05, "Pretrain/Loss": 2.0221848487854004, "Pretrain/Loss (Raw)": 1.771406650543213, "Pretrain/Step": 4681, "Pretrain/Step Time": 8.4735990408808} +{"Pretrain/Learning Rate": 2.694243143480818e-05, "Pretrain/Loss": 2.0210962295532227, "Pretrain/Loss (Raw)": 1.9706461429595947, "Pretrain/Step": 4682, "Pretrain/Step Time": 8.473806301131845} +{"Pretrain/Learning Rate": 2.693396619965688e-05, "Pretrain/Loss": 2.0201876163482666, "Pretrain/Loss (Raw)": 1.988236427307129, "Pretrain/Step": 4683, "Pretrain/Step Time": 8.476639403030276} +{"Pretrain/Learning Rate": 2.6925500741423265e-05, "Pretrain/Loss": 2.0199522972106934, "Pretrain/Loss (Raw)": 1.9598026275634766, "Pretrain/Step": 4684, "Pretrain/Step Time": 8.477887803688645} +{"Pretrain/Learning Rate": 2.691703506108381e-05, "Pretrain/Loss": 2.0200324058532715, "Pretrain/Loss (Raw)": 2.0610406398773193, "Pretrain/Step": 4685, "Pretrain/Step Time": 8.47638731636107} +{"Pretrain/Learning Rate": 2.6908569159615038e-05, "Pretrain/Loss": 2.01796817779541, "Pretrain/Loss (Raw)": 1.9387004375457764, "Pretrain/Step": 4686, "Pretrain/Step Time": 8.479789732024074} +{"Pretrain/Learning Rate": 2.6900103037993492e-05, "Pretrain/Loss": 2.018512725830078, "Pretrain/Loss (Raw)": 2.100252151489258, "Pretrain/Step": 4687, "Pretrain/Step Time": 8.480559976771474} +{"Pretrain/Learning Rate": 2.6891636697195716e-05, "Pretrain/Loss": 2.01910138130188, "Pretrain/Loss (Raw)": 2.1425185203552246, "Pretrain/Step": 4688, "Pretrain/Step Time": 8.478968404233456} +{"Pretrain/Learning Rate": 2.6883170138198323e-05, "Pretrain/Loss": 2.0204100608825684, "Pretrain/Loss (Raw)": 2.11260986328125, "Pretrain/Step": 4689, "Pretrain/Step Time": 8.47940763272345} +{"Pretrain/Learning Rate": 2.687470336197791e-05, "Pretrain/Loss": 2.0179100036621094, "Pretrain/Loss (Raw)": 1.792589545249939, "Pretrain/Step": 4690, "Pretrain/Step Time": 8.479790156707168} +{"Pretrain/Learning Rate": 2.6866236369511122e-05, "Pretrain/Loss": 2.017699718475342, "Pretrain/Loss (Raw)": 1.9983309507369995, "Pretrain/Step": 4691, "Pretrain/Step Time": 8.481062572449446} +{"Pretrain/Learning Rate": 2.6857769161774627e-05, "Pretrain/Loss": 2.0177407264709473, "Pretrain/Loss (Raw)": 2.036693572998047, "Pretrain/Step": 4692, "Pretrain/Step Time": 8.477621825411916} +{"Pretrain/Learning Rate": 2.6849301739745108e-05, "Pretrain/Loss": 2.020542860031128, "Pretrain/Loss (Raw)": 2.054051160812378, "Pretrain/Step": 4693, "Pretrain/Step Time": 8.479748701676726} +{"Pretrain/Learning Rate": 2.6840834104399293e-05, "Pretrain/Loss": 2.020214557647705, "Pretrain/Loss (Raw)": 2.0142602920532227, "Pretrain/Step": 4694, "Pretrain/Step Time": 8.479777378961444} +{"Pretrain/Learning Rate": 2.68323662567139e-05, "Pretrain/Loss": 2.0191879272460938, "Pretrain/Loss (Raw)": 1.8361698389053345, "Pretrain/Step": 4695, "Pretrain/Step Time": 8.477359965443611} +{"Pretrain/Learning Rate": 2.6823898197665703e-05, "Pretrain/Loss": 2.0196805000305176, "Pretrain/Loss (Raw)": 1.9739480018615723, "Pretrain/Step": 4696, "Pretrain/Step Time": 8.47662221826613} +{"Pretrain/Learning Rate": 2.68154299282315e-05, "Pretrain/Loss": 2.0190014839172363, "Pretrain/Loss (Raw)": 2.090510368347168, "Pretrain/Step": 4697, "Pretrain/Step Time": 8.479035016149282} +{"Pretrain/Learning Rate": 2.680696144938809e-05, "Pretrain/Loss": 2.0188345909118652, "Pretrain/Loss (Raw)": 2.021395444869995, "Pretrain/Step": 4698, "Pretrain/Step Time": 8.478962022811174} +{"Pretrain/Learning Rate": 2.6798492762112303e-05, "Pretrain/Loss": 2.0178632736206055, "Pretrain/Loss (Raw)": 1.9459121227264404, "Pretrain/Step": 4699, "Pretrain/Step Time": 8.477894194424152} +{"Pretrain/Learning Rate": 2.679002386738102e-05, "Pretrain/Loss": 2.019131898880005, "Pretrain/Loss (Raw)": 2.1279468536376953, "Pretrain/Step": 4700, "Pretrain/Step Time": 8.478682693094015} +{"Pretrain/Learning Rate": 2.67815547661711e-05, "Pretrain/Loss": 2.016359806060791, "Pretrain/Loss (Raw)": 1.898400902748108, "Pretrain/Step": 4701, "Pretrain/Step Time": 8.47834563627839} +{"Pretrain/Learning Rate": 2.677308545945948e-05, "Pretrain/Loss": 2.0163774490356445, "Pretrain/Loss (Raw)": 2.0832231044769287, "Pretrain/Step": 4702, "Pretrain/Step Time": 8.478233449161053} +{"Pretrain/Learning Rate": 2.676461594822306e-05, "Pretrain/Loss": 2.018977642059326, "Pretrain/Loss (Raw)": 2.118428945541382, "Pretrain/Step": 4703, "Pretrain/Step Time": 8.47768996283412} +{"Pretrain/Learning Rate": 2.6756146233438816e-05, "Pretrain/Loss": 2.018265724182129, "Pretrain/Loss (Raw)": 1.9986294507980347, "Pretrain/Step": 4704, "Pretrain/Step Time": 8.479131693020463} +{"Pretrain/Learning Rate": 2.6747676316083726e-05, "Pretrain/Loss": 2.019197940826416, "Pretrain/Loss (Raw)": 2.1881351470947266, "Pretrain/Step": 4705, "Pretrain/Step Time": 8.479701595380902} +{"Pretrain/Learning Rate": 2.673920619713478e-05, "Pretrain/Loss": 2.0179500579833984, "Pretrain/Loss (Raw)": 1.817309856414795, "Pretrain/Step": 4706, "Pretrain/Step Time": 8.47678660415113} +{"Pretrain/Learning Rate": 2.6730735877569014e-05, "Pretrain/Loss": 2.0173630714416504, "Pretrain/Loss (Raw)": 1.9583150148391724, "Pretrain/Step": 4707, "Pretrain/Step Time": 8.47505029477179} +{"Pretrain/Learning Rate": 2.6722265358363473e-05, "Pretrain/Loss": 2.017303705215454, "Pretrain/Loss (Raw)": 2.0765528678894043, "Pretrain/Step": 4708, "Pretrain/Step Time": 8.476307529956102} +{"Pretrain/Learning Rate": 2.6713794640495227e-05, "Pretrain/Loss": 2.0190796852111816, "Pretrain/Loss (Raw)": 2.1368789672851562, "Pretrain/Step": 4709, "Pretrain/Step Time": 8.475926153361797} +{"Pretrain/Learning Rate": 2.6705323724941374e-05, "Pretrain/Loss": 2.0214109420776367, "Pretrain/Loss (Raw)": 2.0385496616363525, "Pretrain/Step": 4710, "Pretrain/Step Time": 8.474798385053873} +{"Pretrain/Learning Rate": 2.6696852612679023e-05, "Pretrain/Loss": 2.0205178260803223, "Pretrain/Loss (Raw)": 1.9402636289596558, "Pretrain/Step": 4711, "Pretrain/Step Time": 8.477419437840581} +{"Pretrain/Learning Rate": 2.668838130468532e-05, "Pretrain/Loss": 2.019535541534424, "Pretrain/Loss (Raw)": 1.8773460388183594, "Pretrain/Step": 4712, "Pretrain/Step Time": 8.478101372718811} +{"Pretrain/Learning Rate": 2.667990980193743e-05, "Pretrain/Loss": 2.018423318862915, "Pretrain/Loss (Raw)": 2.000375986099243, "Pretrain/Step": 4713, "Pretrain/Step Time": 8.476035431027412} +{"Pretrain/Learning Rate": 2.667143810541254e-05, "Pretrain/Loss": 2.016422986984253, "Pretrain/Loss (Raw)": 1.8834041357040405, "Pretrain/Step": 4714, "Pretrain/Step Time": 8.476062972098589} +{"Pretrain/Learning Rate": 2.666296621608784e-05, "Pretrain/Loss": 2.017571449279785, "Pretrain/Loss (Raw)": 2.1344263553619385, "Pretrain/Step": 4715, "Pretrain/Step Time": 8.481681078672409} +{"Pretrain/Learning Rate": 2.6654494134940582e-05, "Pretrain/Loss": 2.018270492553711, "Pretrain/Loss (Raw)": 2.0719211101531982, "Pretrain/Step": 4716, "Pretrain/Step Time": 8.478737710043788} +{"Pretrain/Learning Rate": 2.6646021862948e-05, "Pretrain/Loss": 2.017251968383789, "Pretrain/Loss (Raw)": 2.0603315830230713, "Pretrain/Step": 4717, "Pretrain/Step Time": 8.480410730466247} +{"Pretrain/Learning Rate": 2.663754940108738e-05, "Pretrain/Loss": 2.0189356803894043, "Pretrain/Loss (Raw)": 2.0737643241882324, "Pretrain/Step": 4718, "Pretrain/Step Time": 8.48060236312449} +{"Pretrain/Learning Rate": 2.6629076750336008e-05, "Pretrain/Loss": 2.0180516242980957, "Pretrain/Loss (Raw)": 2.009692907333374, "Pretrain/Step": 4719, "Pretrain/Step Time": 8.479914590716362} +{"Pretrain/Learning Rate": 2.66206039116712e-05, "Pretrain/Loss": 2.0186514854431152, "Pretrain/Loss (Raw)": 2.039226770401001, "Pretrain/Step": 4720, "Pretrain/Step Time": 8.479807896539569} +{"Pretrain/Learning Rate": 2.6612130886070315e-05, "Pretrain/Loss": 2.018256664276123, "Pretrain/Loss (Raw)": 2.090146064758301, "Pretrain/Step": 4721, "Pretrain/Step Time": 8.478739108890295} +{"Pretrain/Learning Rate": 2.6603657674510686e-05, "Pretrain/Loss": 2.014202117919922, "Pretrain/Loss (Raw)": 1.6548980474472046, "Pretrain/Step": 4722, "Pretrain/Step Time": 8.47824802622199} +{"Pretrain/Learning Rate": 2.6595184277969713e-05, "Pretrain/Loss": 2.014458656311035, "Pretrain/Loss (Raw)": 2.024261951446533, "Pretrain/Step": 4723, "Pretrain/Step Time": 8.47767661139369} +{"Pretrain/Learning Rate": 2.65867106974248e-05, "Pretrain/Loss": 2.012521266937256, "Pretrain/Loss (Raw)": 1.8186311721801758, "Pretrain/Step": 4724, "Pretrain/Step Time": 8.481316480785608} +{"Pretrain/Learning Rate": 2.657823693385335e-05, "Pretrain/Loss": 2.0122220516204834, "Pretrain/Loss (Raw)": 2.0858049392700195, "Pretrain/Step": 4725, "Pretrain/Step Time": 8.481054244562984} +{"Pretrain/Learning Rate": 2.656976298823284e-05, "Pretrain/Loss": 2.012639284133911, "Pretrain/Loss (Raw)": 2.10182785987854, "Pretrain/Step": 4726, "Pretrain/Step Time": 8.480115175247192} +{"Pretrain/Learning Rate": 2.656128886154071e-05, "Pretrain/Loss": 2.0121850967407227, "Pretrain/Loss (Raw)": 2.0076205730438232, "Pretrain/Step": 4727, "Pretrain/Step Time": 8.480225736275315} +{"Pretrain/Learning Rate": 2.6552814554754463e-05, "Pretrain/Loss": 2.014448881149292, "Pretrain/Loss (Raw)": 1.9545859098434448, "Pretrain/Step": 4728, "Pretrain/Step Time": 8.482334656640887} +{"Pretrain/Learning Rate": 2.6544340068851604e-05, "Pretrain/Loss": 2.0145134925842285, "Pretrain/Loss (Raw)": 1.9697641134262085, "Pretrain/Step": 4729, "Pretrain/Step Time": 8.480157751590014} +{"Pretrain/Learning Rate": 2.6535865404809658e-05, "Pretrain/Loss": 2.0145111083984375, "Pretrain/Loss (Raw)": 1.9995428323745728, "Pretrain/Step": 4730, "Pretrain/Step Time": 8.480468321591616} +{"Pretrain/Learning Rate": 2.652739056360618e-05, "Pretrain/Loss": 2.014740467071533, "Pretrain/Loss (Raw)": 2.0096917152404785, "Pretrain/Step": 4731, "Pretrain/Step Time": 8.482815274968743} +{"Pretrain/Learning Rate": 2.6518915546218736e-05, "Pretrain/Loss": 2.014702320098877, "Pretrain/Loss (Raw)": 2.149868965148926, "Pretrain/Step": 4732, "Pretrain/Step Time": 8.482537580654025} +{"Pretrain/Learning Rate": 2.6510440353624914e-05, "Pretrain/Loss": 2.015815258026123, "Pretrain/Loss (Raw)": 2.0813655853271484, "Pretrain/Step": 4733, "Pretrain/Step Time": 8.479404143989086} +{"Pretrain/Learning Rate": 2.650196498680234e-05, "Pretrain/Loss": 2.0154809951782227, "Pretrain/Loss (Raw)": 2.008902072906494, "Pretrain/Step": 4734, "Pretrain/Step Time": 8.480325896292925} +{"Pretrain/Learning Rate": 2.649348944672862e-05, "Pretrain/Loss": 2.01289701461792, "Pretrain/Loss (Raw)": 1.8516563177108765, "Pretrain/Step": 4735, "Pretrain/Step Time": 8.480014730244875} +{"Pretrain/Learning Rate": 2.648501373438142e-05, "Pretrain/Loss": 2.013579845428467, "Pretrain/Loss (Raw)": 2.1060030460357666, "Pretrain/Step": 4736, "Pretrain/Step Time": 8.480526616796851} +{"Pretrain/Learning Rate": 2.647653785073841e-05, "Pretrain/Loss": 2.011618137359619, "Pretrain/Loss (Raw)": 1.9131001234054565, "Pretrain/Step": 4737, "Pretrain/Step Time": 8.48027097247541} +{"Pretrain/Learning Rate": 2.6468061796777278e-05, "Pretrain/Loss": 2.011953830718994, "Pretrain/Loss (Raw)": 2.004390001296997, "Pretrain/Step": 4738, "Pretrain/Step Time": 8.48200587183237} +{"Pretrain/Learning Rate": 2.645958557347573e-05, "Pretrain/Loss": 2.0120134353637695, "Pretrain/Loss (Raw)": 2.027576208114624, "Pretrain/Step": 4739, "Pretrain/Step Time": 8.482450501993299} +{"Pretrain/Learning Rate": 2.6451109181811505e-05, "Pretrain/Loss": 2.009202003479004, "Pretrain/Loss (Raw)": 1.9258971214294434, "Pretrain/Step": 4740, "Pretrain/Step Time": 8.482391012832522} +{"Pretrain/Learning Rate": 2.6442632622762344e-05, "Pretrain/Loss": 2.0093913078308105, "Pretrain/Loss (Raw)": 2.04363751411438, "Pretrain/Step": 4741, "Pretrain/Step Time": 8.479270992800593} +{"Pretrain/Learning Rate": 2.6434155897306018e-05, "Pretrain/Loss": 2.008673667907715, "Pretrain/Loss (Raw)": 1.9789234399795532, "Pretrain/Step": 4742, "Pretrain/Step Time": 8.478233892470598} +{"Pretrain/Learning Rate": 2.6425679006420306e-05, "Pretrain/Loss": 2.0087685585021973, "Pretrain/Loss (Raw)": 2.0289039611816406, "Pretrain/Step": 4743, "Pretrain/Step Time": 8.48005060851574} +{"Pretrain/Learning Rate": 2.6417201951083025e-05, "Pretrain/Loss": 2.0099027156829834, "Pretrain/Loss (Raw)": 2.1445024013519287, "Pretrain/Step": 4744, "Pretrain/Step Time": 8.477026412263513} +{"Pretrain/Learning Rate": 2.6408724732272e-05, "Pretrain/Loss": 2.0086593627929688, "Pretrain/Loss (Raw)": 1.9229786396026611, "Pretrain/Step": 4745, "Pretrain/Step Time": 8.480931971222162} +{"Pretrain/Learning Rate": 2.640024735096507e-05, "Pretrain/Loss": 2.0096611976623535, "Pretrain/Loss (Raw)": 2.06748366355896, "Pretrain/Step": 4746, "Pretrain/Step Time": 8.481763042509556} +{"Pretrain/Learning Rate": 2.63917698081401e-05, "Pretrain/Loss": 2.0115747451782227, "Pretrain/Loss (Raw)": 2.208834648132324, "Pretrain/Step": 4747, "Pretrain/Step Time": 8.48631702363491} +{"Pretrain/Learning Rate": 2.6383292104774977e-05, "Pretrain/Loss": 2.01084566116333, "Pretrain/Loss (Raw)": 1.9771658182144165, "Pretrain/Step": 4748, "Pretrain/Step Time": 8.486047515645623} +{"Pretrain/Learning Rate": 2.6374814241847583e-05, "Pretrain/Loss": 2.012014865875244, "Pretrain/Loss (Raw)": 2.0560386180877686, "Pretrain/Step": 4749, "Pretrain/Step Time": 8.486166534945369} +{"Pretrain/Learning Rate": 2.6366336220335862e-05, "Pretrain/Loss": 2.0118699073791504, "Pretrain/Loss (Raw)": 2.1229355335235596, "Pretrain/Step": 4750, "Pretrain/Step Time": 8.485871424898505} +{"Pretrain/Learning Rate": 2.635785804121773e-05, "Pretrain/Loss": 2.0145883560180664, "Pretrain/Loss (Raw)": 2.0346462726593018, "Pretrain/Step": 4751, "Pretrain/Step Time": 8.4842196572572} +{"Pretrain/Learning Rate": 2.6349379705471155e-05, "Pretrain/Loss": 2.013563632965088, "Pretrain/Loss (Raw)": 1.997066617012024, "Pretrain/Step": 4752, "Pretrain/Step Time": 8.486821740865707} +{"Pretrain/Learning Rate": 2.6340901214074103e-05, "Pretrain/Loss": 2.014068603515625, "Pretrain/Loss (Raw)": 1.9384459257125854, "Pretrain/Step": 4753, "Pretrain/Step Time": 8.484463930130005} +{"Pretrain/Learning Rate": 2.6332422568004566e-05, "Pretrain/Loss": 2.015265941619873, "Pretrain/Loss (Raw)": 2.206334114074707, "Pretrain/Step": 4754, "Pretrain/Step Time": 8.484737219288945} +{"Pretrain/Learning Rate": 2.632394376824056e-05, "Pretrain/Loss": 2.0156848430633545, "Pretrain/Loss (Raw)": 1.9628478288650513, "Pretrain/Step": 4755, "Pretrain/Step Time": 8.482626194134355} +{"Pretrain/Learning Rate": 2.6315464815760105e-05, "Pretrain/Loss": 2.018239736557007, "Pretrain/Loss (Raw)": 2.281963348388672, "Pretrain/Step": 4756, "Pretrain/Step Time": 8.480736188590527} +{"Pretrain/Learning Rate": 2.6306985711541238e-05, "Pretrain/Loss": 2.018101215362549, "Pretrain/Loss (Raw)": 2.044600486755371, "Pretrain/Step": 4757, "Pretrain/Step Time": 8.48050669580698} +{"Pretrain/Learning Rate": 2.629850645656204e-05, "Pretrain/Loss": 2.017519474029541, "Pretrain/Loss (Raw)": 1.9898210763931274, "Pretrain/Step": 4758, "Pretrain/Step Time": 8.478508703410625} +{"Pretrain/Learning Rate": 2.6290027051800565e-05, "Pretrain/Loss": 2.0173137187957764, "Pretrain/Loss (Raw)": 2.017280101776123, "Pretrain/Step": 4759, "Pretrain/Step Time": 8.484001571312547} +{"Pretrain/Learning Rate": 2.628154749823493e-05, "Pretrain/Loss": 2.0178041458129883, "Pretrain/Loss (Raw)": 2.132967233657837, "Pretrain/Step": 4760, "Pretrain/Step Time": 8.48460498265922} +{"Pretrain/Learning Rate": 2.6273067796843244e-05, "Pretrain/Loss": 2.0167598724365234, "Pretrain/Loss (Raw)": 2.0579946041107178, "Pretrain/Step": 4761, "Pretrain/Step Time": 8.484732197597623} +{"Pretrain/Learning Rate": 2.6264587948603626e-05, "Pretrain/Loss": 2.0162851810455322, "Pretrain/Loss (Raw)": 1.8991268873214722, "Pretrain/Step": 4762, "Pretrain/Step Time": 8.483206091448665} +{"Pretrain/Learning Rate": 2.6256107954494242e-05, "Pretrain/Loss": 2.016791343688965, "Pretrain/Loss (Raw)": 1.893723487854004, "Pretrain/Step": 4763, "Pretrain/Step Time": 8.483990436419845} +{"Pretrain/Learning Rate": 2.624762781549324e-05, "Pretrain/Loss": 2.0156798362731934, "Pretrain/Loss (Raw)": 1.55661940574646, "Pretrain/Step": 4764, "Pretrain/Step Time": 8.483667807653546} +{"Pretrain/Learning Rate": 2.6239147532578812e-05, "Pretrain/Loss": 2.014774799346924, "Pretrain/Loss (Raw)": 2.0482029914855957, "Pretrain/Step": 4765, "Pretrain/Step Time": 8.488140126690269} +{"Pretrain/Learning Rate": 2.6230667106729156e-05, "Pretrain/Loss": 2.0143589973449707, "Pretrain/Loss (Raw)": 2.073293924331665, "Pretrain/Step": 4766, "Pretrain/Step Time": 8.489193161949515} +{"Pretrain/Learning Rate": 2.6222186538922473e-05, "Pretrain/Loss": 2.015970468521118, "Pretrain/Loss (Raw)": 2.1181180477142334, "Pretrain/Step": 4767, "Pretrain/Step Time": 8.489570669829845} +{"Pretrain/Learning Rate": 2.6213705830137008e-05, "Pretrain/Loss": 2.016245126724243, "Pretrain/Loss (Raw)": 2.0047388076782227, "Pretrain/Step": 4768, "Pretrain/Step Time": 8.490386683493853} +{"Pretrain/Learning Rate": 2.6205224981350997e-05, "Pretrain/Loss": 2.0175509452819824, "Pretrain/Loss (Raw)": 2.0930864810943604, "Pretrain/Step": 4769, "Pretrain/Step Time": 8.488610491156578} +{"Pretrain/Learning Rate": 2.6196743993542712e-05, "Pretrain/Loss": 2.0174357891082764, "Pretrain/Loss (Raw)": 2.0277671813964844, "Pretrain/Step": 4770, "Pretrain/Step Time": 8.48477952554822} +{"Pretrain/Learning Rate": 2.6188262867690428e-05, "Pretrain/Loss": 2.0172781944274902, "Pretrain/Loss (Raw)": 2.10009765625, "Pretrain/Step": 4771, "Pretrain/Step Time": 8.488788383081555} +{"Pretrain/Learning Rate": 2.6179781604772435e-05, "Pretrain/Loss": 2.018367290496826, "Pretrain/Loss (Raw)": 2.0915708541870117, "Pretrain/Step": 4772, "Pretrain/Step Time": 8.486821200698614} +{"Pretrain/Learning Rate": 2.6171300205767052e-05, "Pretrain/Loss": 2.017875909805298, "Pretrain/Loss (Raw)": 2.097127676010132, "Pretrain/Step": 4773, "Pretrain/Step Time": 8.488723512738943} +{"Pretrain/Learning Rate": 2.6162818671652606e-05, "Pretrain/Loss": 2.02005672454834, "Pretrain/Loss (Raw)": 2.252408981323242, "Pretrain/Step": 4774, "Pretrain/Step Time": 8.490399099886417} +{"Pretrain/Learning Rate": 2.615433700340743e-05, "Pretrain/Loss": 2.0188217163085938, "Pretrain/Loss (Raw)": 2.0281617641448975, "Pretrain/Step": 4775, "Pretrain/Step Time": 8.490488678216934} +{"Pretrain/Learning Rate": 2.614585520200989e-05, "Pretrain/Loss": 2.017050266265869, "Pretrain/Loss (Raw)": 1.920304298400879, "Pretrain/Step": 4776, "Pretrain/Step Time": 8.485132660716772} +{"Pretrain/Learning Rate": 2.613737326843835e-05, "Pretrain/Loss": 2.017587184906006, "Pretrain/Loss (Raw)": 1.9938721656799316, "Pretrain/Step": 4777, "Pretrain/Step Time": 8.485393738374114} +{"Pretrain/Learning Rate": 2.6128891203671202e-05, "Pretrain/Loss": 2.018339157104492, "Pretrain/Loss (Raw)": 2.1676523685455322, "Pretrain/Step": 4778, "Pretrain/Step Time": 8.484767362475395} +{"Pretrain/Learning Rate": 2.612040900868685e-05, "Pretrain/Loss": 2.018551826477051, "Pretrain/Loss (Raw)": 2.0497469902038574, "Pretrain/Step": 4779, "Pretrain/Step Time": 8.487733874469995} +{"Pretrain/Learning Rate": 2.6111926684463717e-05, "Pretrain/Loss": 2.018850803375244, "Pretrain/Loss (Raw)": 2.039902925491333, "Pretrain/Step": 4780, "Pretrain/Step Time": 8.48369661718607} +{"Pretrain/Learning Rate": 2.6103444231980236e-05, "Pretrain/Loss": 2.019071578979492, "Pretrain/Loss (Raw)": 2.0676932334899902, "Pretrain/Step": 4781, "Pretrain/Step Time": 8.485441584140062} +{"Pretrain/Learning Rate": 2.609496165221485e-05, "Pretrain/Loss": 2.0188112258911133, "Pretrain/Loss (Raw)": 1.9756461381912231, "Pretrain/Step": 4782, "Pretrain/Step Time": 8.48570043221116} +{"Pretrain/Learning Rate": 2.6086478946146015e-05, "Pretrain/Loss": 2.0180811882019043, "Pretrain/Loss (Raw)": 1.8999143838882446, "Pretrain/Step": 4783, "Pretrain/Step Time": 8.491291619837284} +{"Pretrain/Learning Rate": 2.6077996114752218e-05, "Pretrain/Loss": 2.019784927368164, "Pretrain/Loss (Raw)": 2.0693602561950684, "Pretrain/Step": 4784, "Pretrain/Step Time": 8.491423377767205} +{"Pretrain/Learning Rate": 2.6069513159011947e-05, "Pretrain/Loss": 2.02042818069458, "Pretrain/Loss (Raw)": 1.9949514865875244, "Pretrain/Step": 4785, "Pretrain/Step Time": 8.4901511259377} +{"Pretrain/Learning Rate": 2.606103007990371e-05, "Pretrain/Loss": 2.0215535163879395, "Pretrain/Loss (Raw)": 2.1322624683380127, "Pretrain/Step": 4786, "Pretrain/Step Time": 8.489609006792307} +{"Pretrain/Learning Rate": 2.6052546878406025e-05, "Pretrain/Loss": 2.0214128494262695, "Pretrain/Loss (Raw)": 2.047137498855591, "Pretrain/Step": 4787, "Pretrain/Step Time": 8.491449758410454} +{"Pretrain/Learning Rate": 2.6044063555497426e-05, "Pretrain/Loss": 2.0201773643493652, "Pretrain/Loss (Raw)": 2.012539863586426, "Pretrain/Step": 4788, "Pretrain/Step Time": 8.491250639781356} +{"Pretrain/Learning Rate": 2.603558011215647e-05, "Pretrain/Loss": 2.0177743434906006, "Pretrain/Loss (Raw)": 1.8520268201828003, "Pretrain/Step": 4789, "Pretrain/Step Time": 8.491999311372638} +{"Pretrain/Learning Rate": 2.6027096549361713e-05, "Pretrain/Loss": 2.0153446197509766, "Pretrain/Loss (Raw)": 1.9003249406814575, "Pretrain/Step": 4790, "Pretrain/Step Time": 8.491846727207303} +{"Pretrain/Learning Rate": 2.601861286809172e-05, "Pretrain/Loss": 2.0163841247558594, "Pretrain/Loss (Raw)": 2.18422532081604, "Pretrain/Step": 4791, "Pretrain/Step Time": 8.490157760679722} +{"Pretrain/Learning Rate": 2.6010129069325096e-05, "Pretrain/Loss": 2.0153024196624756, "Pretrain/Loss (Raw)": 1.973824143409729, "Pretrain/Step": 4792, "Pretrain/Step Time": 8.485811395570636} +{"Pretrain/Learning Rate": 2.6001645154040438e-05, "Pretrain/Loss": 2.0168206691741943, "Pretrain/Loss (Raw)": 2.2171478271484375, "Pretrain/Step": 4793, "Pretrain/Step Time": 8.488230124115944} +{"Pretrain/Learning Rate": 2.5993161123216365e-05, "Pretrain/Loss": 2.018059015274048, "Pretrain/Loss (Raw)": 1.9987142086029053, "Pretrain/Step": 4794, "Pretrain/Step Time": 8.488290295004845} +{"Pretrain/Learning Rate": 2.59846769778315e-05, "Pretrain/Loss": 2.0191121101379395, "Pretrain/Loss (Raw)": 2.015206813812256, "Pretrain/Step": 4795, "Pretrain/Step Time": 8.488428769633174} +{"Pretrain/Learning Rate": 2.5976192718864494e-05, "Pretrain/Loss": 2.020498514175415, "Pretrain/Loss (Raw)": 2.076763391494751, "Pretrain/Step": 4796, "Pretrain/Step Time": 8.487979032099247} +{"Pretrain/Learning Rate": 2.5967708347294005e-05, "Pretrain/Loss": 2.0191335678100586, "Pretrain/Loss (Raw)": 1.8167262077331543, "Pretrain/Step": 4797, "Pretrain/Step Time": 8.489777212962508} +{"Pretrain/Learning Rate": 2.5959223864098696e-05, "Pretrain/Loss": 2.02018666267395, "Pretrain/Loss (Raw)": 2.1136834621429443, "Pretrain/Step": 4798, "Pretrain/Step Time": 8.491202738136053} +{"Pretrain/Learning Rate": 2.595073927025725e-05, "Pretrain/Loss": 2.019751787185669, "Pretrain/Loss (Raw)": 2.190329074859619, "Pretrain/Step": 4799, "Pretrain/Step Time": 8.492506515234709} +{"Pretrain/Learning Rate": 2.594225456674837e-05, "Pretrain/Loss": 2.0204849243164062, "Pretrain/Loss (Raw)": 2.019987106323242, "Pretrain/Step": 4800, "Pretrain/Step Time": 8.492339555174112} +{"Pretrain/Learning Rate": 2.5933769754550747e-05, "Pretrain/Loss": 2.0205864906311035, "Pretrain/Loss (Raw)": 1.9661180973052979, "Pretrain/Step": 4801, "Pretrain/Step Time": 8.49382315762341} +{"Pretrain/Learning Rate": 2.5925284834643122e-05, "Pretrain/Loss": 2.018510341644287, "Pretrain/Loss (Raw)": 1.8312560319900513, "Pretrain/Step": 4802, "Pretrain/Step Time": 8.49136951006949} +{"Pretrain/Learning Rate": 2.5916799808004206e-05, "Pretrain/Loss": 2.0209391117095947, "Pretrain/Loss (Raw)": 2.089085578918457, "Pretrain/Step": 4803, "Pretrain/Step Time": 8.491202373057604} +{"Pretrain/Learning Rate": 2.5908314675612756e-05, "Pretrain/Loss": 2.021876096725464, "Pretrain/Loss (Raw)": 2.195160388946533, "Pretrain/Step": 4804, "Pretrain/Step Time": 8.495954906567931} +{"Pretrain/Learning Rate": 2.589982943844753e-05, "Pretrain/Loss": 2.021284818649292, "Pretrain/Loss (Raw)": 2.1044695377349854, "Pretrain/Step": 4805, "Pretrain/Step Time": 8.49590902402997} +{"Pretrain/Learning Rate": 2.589134409748729e-05, "Pretrain/Loss": 2.022336006164551, "Pretrain/Loss (Raw)": 2.0470566749572754, "Pretrain/Step": 4806, "Pretrain/Step Time": 8.49279391206801} +{"Pretrain/Learning Rate": 2.5882858653710827e-05, "Pretrain/Loss": 2.022956609725952, "Pretrain/Loss (Raw)": 2.1457958221435547, "Pretrain/Step": 4807, "Pretrain/Step Time": 8.49459925480187} +{"Pretrain/Learning Rate": 2.5874373108096932e-05, "Pretrain/Loss": 2.0206761360168457, "Pretrain/Loss (Raw)": 1.9105230569839478, "Pretrain/Step": 4808, "Pretrain/Step Time": 8.487602706998587} +{"Pretrain/Learning Rate": 2.5865887461624398e-05, "Pretrain/Loss": 2.022812604904175, "Pretrain/Loss (Raw)": 2.0448696613311768, "Pretrain/Step": 4809, "Pretrain/Step Time": 8.487702390179038} +{"Pretrain/Learning Rate": 2.5857401715272056e-05, "Pretrain/Loss": 2.022209644317627, "Pretrain/Loss (Raw)": 1.893449306488037, "Pretrain/Step": 4810, "Pretrain/Step Time": 8.492172813042998} +{"Pretrain/Learning Rate": 2.5848915870018718e-05, "Pretrain/Loss": 2.0221118927001953, "Pretrain/Loss (Raw)": 1.9757490158081055, "Pretrain/Step": 4811, "Pretrain/Step Time": 8.48792265728116} +{"Pretrain/Learning Rate": 2.584042992684324e-05, "Pretrain/Loss": 2.0220577716827393, "Pretrain/Loss (Raw)": 1.9528653621673584, "Pretrain/Step": 4812, "Pretrain/Step Time": 8.48519354313612} +{"Pretrain/Learning Rate": 2.5831943886724467e-05, "Pretrain/Loss": 2.0216307640075684, "Pretrain/Loss (Raw)": 2.0063910484313965, "Pretrain/Step": 4813, "Pretrain/Step Time": 8.486972074955702} +{"Pretrain/Learning Rate": 2.5823457750641255e-05, "Pretrain/Loss": 2.023463726043701, "Pretrain/Loss (Raw)": 2.1733028888702393, "Pretrain/Step": 4814, "Pretrain/Step Time": 8.488227982074022} +{"Pretrain/Learning Rate": 2.5814971519572483e-05, "Pretrain/Loss": 2.0227127075195312, "Pretrain/Loss (Raw)": 2.0041277408599854, "Pretrain/Step": 4815, "Pretrain/Step Time": 8.493828756734729} +{"Pretrain/Learning Rate": 2.5806485194497037e-05, "Pretrain/Loss": 2.0226240158081055, "Pretrain/Loss (Raw)": 2.1311450004577637, "Pretrain/Step": 4816, "Pretrain/Step Time": 8.496120285242796} +{"Pretrain/Learning Rate": 2.57979987763938e-05, "Pretrain/Loss": 2.0187888145446777, "Pretrain/Loss (Raw)": 1.6217131614685059, "Pretrain/Step": 4817, "Pretrain/Step Time": 8.494016114622355} +{"Pretrain/Learning Rate": 2.578951226624169e-05, "Pretrain/Loss": 2.0194263458251953, "Pretrain/Loss (Raw)": 1.8742188215255737, "Pretrain/Step": 4818, "Pretrain/Step Time": 8.494041055440903} +{"Pretrain/Learning Rate": 2.578102566501961e-05, "Pretrain/Loss": 2.019352912902832, "Pretrain/Loss (Raw)": 1.9889276027679443, "Pretrain/Step": 4819, "Pretrain/Step Time": 8.491758406162262} +{"Pretrain/Learning Rate": 2.5772538973706496e-05, "Pretrain/Loss": 2.01796293258667, "Pretrain/Loss (Raw)": 1.8587665557861328, "Pretrain/Step": 4820, "Pretrain/Step Time": 8.489606566727161} +{"Pretrain/Learning Rate": 2.5764052193281285e-05, "Pretrain/Loss": 2.017810821533203, "Pretrain/Loss (Raw)": 2.034586191177368, "Pretrain/Step": 4821, "Pretrain/Step Time": 8.486588718369603} +{"Pretrain/Learning Rate": 2.575556532472292e-05, "Pretrain/Loss": 2.0169596672058105, "Pretrain/Loss (Raw)": 1.9053266048431396, "Pretrain/Step": 4822, "Pretrain/Step Time": 8.486370261758566} +{"Pretrain/Learning Rate": 2.574707836901037e-05, "Pretrain/Loss": 2.018387794494629, "Pretrain/Loss (Raw)": 2.018970012664795, "Pretrain/Step": 4823, "Pretrain/Step Time": 8.487892726436257} +{"Pretrain/Learning Rate": 2.5738591327122586e-05, "Pretrain/Loss": 2.0184035301208496, "Pretrain/Loss (Raw)": 1.9759246110916138, "Pretrain/Step": 4824, "Pretrain/Step Time": 8.486923858523369} +{"Pretrain/Learning Rate": 2.5730104200038547e-05, "Pretrain/Loss": 2.015516757965088, "Pretrain/Loss (Raw)": 1.7210092544555664, "Pretrain/Step": 4825, "Pretrain/Step Time": 8.487643079832196} +{"Pretrain/Learning Rate": 2.572161698873725e-05, "Pretrain/Loss": 2.0154991149902344, "Pretrain/Loss (Raw)": 2.019134283065796, "Pretrain/Step": 4826, "Pretrain/Step Time": 8.48708420060575} +{"Pretrain/Learning Rate": 2.5713129694197685e-05, "Pretrain/Loss": 2.01690936088562, "Pretrain/Loss (Raw)": 2.126450538635254, "Pretrain/Step": 4827, "Pretrain/Step Time": 8.486459121108055} +{"Pretrain/Learning Rate": 2.5704642317398857e-05, "Pretrain/Loss": 2.016392707824707, "Pretrain/Loss (Raw)": 2.0618231296539307, "Pretrain/Step": 4828, "Pretrain/Step Time": 8.483333935961127} +{"Pretrain/Learning Rate": 2.5696154859319794e-05, "Pretrain/Loss": 2.0160441398620605, "Pretrain/Loss (Raw)": 1.853766679763794, "Pretrain/Step": 4829, "Pretrain/Step Time": 8.487288543954492} +{"Pretrain/Learning Rate": 2.5687667320939508e-05, "Pretrain/Loss": 2.016665458679199, "Pretrain/Loss (Raw)": 2.162740468978882, "Pretrain/Step": 4830, "Pretrain/Step Time": 8.485582899302244} +{"Pretrain/Learning Rate": 2.5679179703237038e-05, "Pretrain/Loss": 2.0157768726348877, "Pretrain/Loss (Raw)": 2.004694938659668, "Pretrain/Step": 4831, "Pretrain/Step Time": 8.489125864580274} +{"Pretrain/Learning Rate": 2.567069200719143e-05, "Pretrain/Loss": 2.0165767669677734, "Pretrain/Loss (Raw)": 2.101018190383911, "Pretrain/Step": 4832, "Pretrain/Step Time": 8.48888066969812} +{"Pretrain/Learning Rate": 2.5662204233781734e-05, "Pretrain/Loss": 2.014941692352295, "Pretrain/Loss (Raw)": 1.978846549987793, "Pretrain/Step": 4833, "Pretrain/Step Time": 8.489393284544349} +{"Pretrain/Learning Rate": 2.5653716383987013e-05, "Pretrain/Loss": 2.01737642288208, "Pretrain/Loss (Raw)": 2.1289517879486084, "Pretrain/Step": 4834, "Pretrain/Step Time": 8.48776975646615} +{"Pretrain/Learning Rate": 2.5645228458786336e-05, "Pretrain/Loss": 2.0190765857696533, "Pretrain/Loss (Raw)": 2.1759490966796875, "Pretrain/Step": 4835, "Pretrain/Step Time": 8.49026309326291} +{"Pretrain/Learning Rate": 2.5636740459158777e-05, "Pretrain/Loss": 2.0176942348480225, "Pretrain/Loss (Raw)": 1.899614691734314, "Pretrain/Step": 4836, "Pretrain/Step Time": 8.487500511109829} +{"Pretrain/Learning Rate": 2.562825238608344e-05, "Pretrain/Loss": 2.0168545246124268, "Pretrain/Loss (Raw)": 2.029381275177002, "Pretrain/Step": 4837, "Pretrain/Step Time": 8.489484356716275} +{"Pretrain/Learning Rate": 2.56197642405394e-05, "Pretrain/Loss": 2.0168962478637695, "Pretrain/Loss (Raw)": 2.043903112411499, "Pretrain/Step": 4838, "Pretrain/Step Time": 8.490212904289365} +{"Pretrain/Learning Rate": 2.5611276023505785e-05, "Pretrain/Loss": 2.0166118144989014, "Pretrain/Loss (Raw)": 1.9038480520248413, "Pretrain/Step": 4839, "Pretrain/Step Time": 8.489212576299906} +{"Pretrain/Learning Rate": 2.5602787735961692e-05, "Pretrain/Loss": 2.017146587371826, "Pretrain/Loss (Raw)": 1.9458025693893433, "Pretrain/Step": 4840, "Pretrain/Step Time": 8.489400690421462} +{"Pretrain/Learning Rate": 2.5594299378886237e-05, "Pretrain/Loss": 2.0151286125183105, "Pretrain/Loss (Raw)": 1.7420661449432373, "Pretrain/Step": 4841, "Pretrain/Step Time": 8.49160347878933} +{"Pretrain/Learning Rate": 2.5585810953258572e-05, "Pretrain/Loss": 2.0140438079833984, "Pretrain/Loss (Raw)": 1.7445425987243652, "Pretrain/Step": 4842, "Pretrain/Step Time": 8.490611961111426} +{"Pretrain/Learning Rate": 2.5577322460057807e-05, "Pretrain/Loss": 2.013655662536621, "Pretrain/Loss (Raw)": 2.0847747325897217, "Pretrain/Step": 4843, "Pretrain/Step Time": 8.486161733046174} +{"Pretrain/Learning Rate": 2.5568833900263105e-05, "Pretrain/Loss": 2.0124545097351074, "Pretrain/Loss (Raw)": 1.9181371927261353, "Pretrain/Step": 4844, "Pretrain/Step Time": 8.486842764541507} +{"Pretrain/Learning Rate": 2.556034527485361e-05, "Pretrain/Loss": 2.0135748386383057, "Pretrain/Loss (Raw)": 2.2037603855133057, "Pretrain/Step": 4845, "Pretrain/Step Time": 8.489565283060074} +{"Pretrain/Learning Rate": 2.5551856584808482e-05, "Pretrain/Loss": 2.0125069618225098, "Pretrain/Loss (Raw)": 1.9370731115341187, "Pretrain/Step": 4846, "Pretrain/Step Time": 8.489774581044912} +{"Pretrain/Learning Rate": 2.5543367831106895e-05, "Pretrain/Loss": 2.012418746948242, "Pretrain/Loss (Raw)": 1.9983816146850586, "Pretrain/Step": 4847, "Pretrain/Step Time": 8.491724945604801} +{"Pretrain/Learning Rate": 2.5534879014728013e-05, "Pretrain/Loss": 2.011979103088379, "Pretrain/Loss (Raw)": 1.9829634428024292, "Pretrain/Step": 4848, "Pretrain/Step Time": 8.492908677086234} +{"Pretrain/Learning Rate": 2.5526390136651035e-05, "Pretrain/Loss": 2.0123157501220703, "Pretrain/Loss (Raw)": 2.1332225799560547, "Pretrain/Step": 4849, "Pretrain/Step Time": 8.492365466430783} +{"Pretrain/Learning Rate": 2.5517901197855137e-05, "Pretrain/Loss": 2.0151963233947754, "Pretrain/Loss (Raw)": 2.0236313343048096, "Pretrain/Step": 4850, "Pretrain/Step Time": 8.491515943780541} +{"Pretrain/Learning Rate": 2.5509412199319517e-05, "Pretrain/Loss": 2.0165979862213135, "Pretrain/Loss (Raw)": 2.203676700592041, "Pretrain/Step": 4851, "Pretrain/Step Time": 8.48968723602593} +{"Pretrain/Learning Rate": 2.5500923142023374e-05, "Pretrain/Loss": 2.0184926986694336, "Pretrain/Loss (Raw)": 2.061124324798584, "Pretrain/Step": 4852, "Pretrain/Step Time": 8.483662599697709} +{"Pretrain/Learning Rate": 2.5492434026945927e-05, "Pretrain/Loss": 2.0172574520111084, "Pretrain/Loss (Raw)": 1.9277125597000122, "Pretrain/Step": 4853, "Pretrain/Step Time": 8.48279924876988} +{"Pretrain/Learning Rate": 2.5483944855066383e-05, "Pretrain/Loss": 2.0185439586639404, "Pretrain/Loss (Raw)": 2.2665162086486816, "Pretrain/Step": 4854, "Pretrain/Step Time": 8.484005017206073} +{"Pretrain/Learning Rate": 2.5475455627363976e-05, "Pretrain/Loss": 2.0171308517456055, "Pretrain/Loss (Raw)": 1.8267030715942383, "Pretrain/Step": 4855, "Pretrain/Step Time": 8.481130911037326} +{"Pretrain/Learning Rate": 2.5466966344817927e-05, "Pretrain/Loss": 2.017789602279663, "Pretrain/Loss (Raw)": 2.038947105407715, "Pretrain/Step": 4856, "Pretrain/Step Time": 8.47776436060667} +{"Pretrain/Learning Rate": 2.5458477008407477e-05, "Pretrain/Loss": 2.018782615661621, "Pretrain/Loss (Raw)": 2.0968947410583496, "Pretrain/Step": 4857, "Pretrain/Step Time": 8.47957468777895} +{"Pretrain/Learning Rate": 2.5449987619111865e-05, "Pretrain/Loss": 2.0176613330841064, "Pretrain/Loss (Raw)": 1.8559808731079102, "Pretrain/Step": 4858, "Pretrain/Step Time": 8.4798343796283} +{"Pretrain/Learning Rate": 2.5441498177910338e-05, "Pretrain/Loss": 2.0179214477539062, "Pretrain/Loss (Raw)": 2.042975425720215, "Pretrain/Step": 4859, "Pretrain/Step Time": 8.475784106180072} +{"Pretrain/Learning Rate": 2.543300868578215e-05, "Pretrain/Loss": 2.0169341564178467, "Pretrain/Loss (Raw)": 2.0235109329223633, "Pretrain/Step": 4860, "Pretrain/Step Time": 8.476595060899854} +{"Pretrain/Learning Rate": 2.542451914370656e-05, "Pretrain/Loss": 2.0148563385009766, "Pretrain/Loss (Raw)": 1.8154150247573853, "Pretrain/Step": 4861, "Pretrain/Step Time": 8.485374508425593} +{"Pretrain/Learning Rate": 2.541602955266284e-05, "Pretrain/Loss": 2.016063690185547, "Pretrain/Loss (Raw)": 2.1634538173675537, "Pretrain/Step": 4862, "Pretrain/Step Time": 8.48722543567419} +{"Pretrain/Learning Rate": 2.5407539913630256e-05, "Pretrain/Loss": 2.0178675651550293, "Pretrain/Loss (Raw)": 2.0825233459472656, "Pretrain/Step": 4863, "Pretrain/Step Time": 8.488269811496139} +{"Pretrain/Learning Rate": 2.5399050227588085e-05, "Pretrain/Loss": 2.016794204711914, "Pretrain/Loss (Raw)": 1.9686421155929565, "Pretrain/Step": 4864, "Pretrain/Step Time": 8.488433310762048} +{"Pretrain/Learning Rate": 2.5390560495515614e-05, "Pretrain/Loss": 2.0175018310546875, "Pretrain/Loss (Raw)": 2.003652572631836, "Pretrain/Step": 4865, "Pretrain/Step Time": 8.489587193354964} +{"Pretrain/Learning Rate": 2.5382070718392133e-05, "Pretrain/Loss": 2.0171189308166504, "Pretrain/Loss (Raw)": 1.9553556442260742, "Pretrain/Step": 4866, "Pretrain/Step Time": 8.489201879128814} +{"Pretrain/Learning Rate": 2.5373580897196914e-05, "Pretrain/Loss": 2.0182852745056152, "Pretrain/Loss (Raw)": 2.176910400390625, "Pretrain/Step": 4867, "Pretrain/Step Time": 8.488875560462475} +{"Pretrain/Learning Rate": 2.5365091032909277e-05, "Pretrain/Loss": 2.0192208290100098, "Pretrain/Loss (Raw)": 2.0455994606018066, "Pretrain/Step": 4868, "Pretrain/Step Time": 8.487353140488267} +{"Pretrain/Learning Rate": 2.5356601126508518e-05, "Pretrain/Loss": 2.0192477703094482, "Pretrain/Loss (Raw)": 2.047104597091675, "Pretrain/Step": 4869, "Pretrain/Step Time": 8.487357422709465} +{"Pretrain/Learning Rate": 2.5348111178973937e-05, "Pretrain/Loss": 2.0190701484680176, "Pretrain/Loss (Raw)": 1.9562183618545532, "Pretrain/Step": 4870, "Pretrain/Step Time": 8.490417700260878} +{"Pretrain/Learning Rate": 2.533962119128487e-05, "Pretrain/Loss": 2.018709659576416, "Pretrain/Loss (Raw)": 1.9827343225479126, "Pretrain/Step": 4871, "Pretrain/Step Time": 8.488823026418686} +{"Pretrain/Learning Rate": 2.53311311644206e-05, "Pretrain/Loss": 2.0177416801452637, "Pretrain/Loss (Raw)": 2.020627737045288, "Pretrain/Step": 4872, "Pretrain/Step Time": 8.488130569458008} +{"Pretrain/Learning Rate": 2.5322641099360477e-05, "Pretrain/Loss": 2.017709255218506, "Pretrain/Loss (Raw)": 1.9187871217727661, "Pretrain/Step": 4873, "Pretrain/Step Time": 8.485609350726008} +{"Pretrain/Learning Rate": 2.531415099708382e-05, "Pretrain/Loss": 2.0177359580993652, "Pretrain/Loss (Raw)": 2.0709009170532227, "Pretrain/Step": 4874, "Pretrain/Step Time": 8.488106608390808} +{"Pretrain/Learning Rate": 2.5305660858569947e-05, "Pretrain/Loss": 2.0175528526306152, "Pretrain/Loss (Raw)": 2.185396909713745, "Pretrain/Step": 4875, "Pretrain/Step Time": 8.482751524075866} +{"Pretrain/Learning Rate": 2.529717068479821e-05, "Pretrain/Loss": 2.0194876194000244, "Pretrain/Loss (Raw)": 2.2248406410217285, "Pretrain/Step": 4876, "Pretrain/Step Time": 8.485076816752553} +{"Pretrain/Learning Rate": 2.5288680476747926e-05, "Pretrain/Loss": 2.0189762115478516, "Pretrain/Loss (Raw)": 1.990591049194336, "Pretrain/Step": 4877, "Pretrain/Step Time": 8.485556345432997} +{"Pretrain/Learning Rate": 2.528019023539846e-05, "Pretrain/Loss": 2.018803596496582, "Pretrain/Loss (Raw)": 2.100804090499878, "Pretrain/Step": 4878, "Pretrain/Step Time": 8.485776245594025} +{"Pretrain/Learning Rate": 2.527169996172915e-05, "Pretrain/Loss": 2.018181562423706, "Pretrain/Loss (Raw)": 1.9550285339355469, "Pretrain/Step": 4879, "Pretrain/Step Time": 8.486147154122591} +{"Pretrain/Learning Rate": 2.526320965671934e-05, "Pretrain/Loss": 2.019622325897217, "Pretrain/Loss (Raw)": 2.181501626968384, "Pretrain/Step": 4880, "Pretrain/Step Time": 8.488234648481011} +{"Pretrain/Learning Rate": 2.5254719321348392e-05, "Pretrain/Loss": 2.0203726291656494, "Pretrain/Loss (Raw)": 2.0344974994659424, "Pretrain/Step": 4881, "Pretrain/Step Time": 8.485124254599214} +{"Pretrain/Learning Rate": 2.5246228956595662e-05, "Pretrain/Loss": 2.0190658569335938, "Pretrain/Loss (Raw)": 2.0390257835388184, "Pretrain/Step": 4882, "Pretrain/Step Time": 8.4864058829844} +{"Pretrain/Learning Rate": 2.52377385634405e-05, "Pretrain/Loss": 2.0195484161376953, "Pretrain/Loss (Raw)": 2.024648427963257, "Pretrain/Step": 4883, "Pretrain/Step Time": 8.485304214060307} +{"Pretrain/Learning Rate": 2.5229248142862288e-05, "Pretrain/Loss": 2.016291618347168, "Pretrain/Loss (Raw)": 1.8650885820388794, "Pretrain/Step": 4884, "Pretrain/Step Time": 8.487184397876263} +{"Pretrain/Learning Rate": 2.5220757695840375e-05, "Pretrain/Loss": 2.0164904594421387, "Pretrain/Loss (Raw)": 2.07002854347229, "Pretrain/Step": 4885, "Pretrain/Step Time": 8.48508439026773} +{"Pretrain/Learning Rate": 2.521226722335414e-05, "Pretrain/Loss": 2.018768787384033, "Pretrain/Loss (Raw)": 2.2814674377441406, "Pretrain/Step": 4886, "Pretrain/Step Time": 8.48792521469295} +{"Pretrain/Learning Rate": 2.5203776726382962e-05, "Pretrain/Loss": 2.018782615661621, "Pretrain/Loss (Raw)": 2.0190131664276123, "Pretrain/Step": 4887, "Pretrain/Step Time": 8.481614282354712} +{"Pretrain/Learning Rate": 2.5195286205906206e-05, "Pretrain/Loss": 2.0176315307617188, "Pretrain/Loss (Raw)": 1.9856619834899902, "Pretrain/Step": 4888, "Pretrain/Step Time": 8.479176403954625} +{"Pretrain/Learning Rate": 2.5186795662903255e-05, "Pretrain/Loss": 2.0191657543182373, "Pretrain/Loss (Raw)": 2.254362106323242, "Pretrain/Step": 4889, "Pretrain/Step Time": 8.481354454532266} +{"Pretrain/Learning Rate": 2.5178305098353488e-05, "Pretrain/Loss": 2.0222761631011963, "Pretrain/Loss (Raw)": 2.2972819805145264, "Pretrain/Step": 4890, "Pretrain/Step Time": 8.478689305484295} +{"Pretrain/Learning Rate": 2.5169814513236296e-05, "Pretrain/Loss": 2.0237488746643066, "Pretrain/Loss (Raw)": 2.0822157859802246, "Pretrain/Step": 4891, "Pretrain/Step Time": 8.480275884270668} +{"Pretrain/Learning Rate": 2.5161323908531058e-05, "Pretrain/Loss": 2.0264787673950195, "Pretrain/Loss (Raw)": 1.906051754951477, "Pretrain/Step": 4892, "Pretrain/Step Time": 8.481008756905794} +{"Pretrain/Learning Rate": 2.515283328521716e-05, "Pretrain/Loss": 2.0247488021850586, "Pretrain/Loss (Raw)": 1.826796293258667, "Pretrain/Step": 4893, "Pretrain/Step Time": 8.478873515501618} +{"Pretrain/Learning Rate": 2.5144342644274e-05, "Pretrain/Loss": 2.024484634399414, "Pretrain/Loss (Raw)": 2.0394418239593506, "Pretrain/Step": 4894, "Pretrain/Step Time": 8.4827152621001} +{"Pretrain/Learning Rate": 2.5135851986680962e-05, "Pretrain/Loss": 2.024306297302246, "Pretrain/Loss (Raw)": 2.095292329788208, "Pretrain/Step": 4895, "Pretrain/Step Time": 8.481647159904242} +{"Pretrain/Learning Rate": 2.5127361313417447e-05, "Pretrain/Loss": 2.023876190185547, "Pretrain/Loss (Raw)": 1.949704885482788, "Pretrain/Step": 4896, "Pretrain/Step Time": 8.482728261500597} +{"Pretrain/Learning Rate": 2.5118870625462853e-05, "Pretrain/Loss": 2.0235671997070312, "Pretrain/Loss (Raw)": 2.0535593032836914, "Pretrain/Step": 4897, "Pretrain/Step Time": 8.482044016942382} +{"Pretrain/Learning Rate": 2.5110379923796567e-05, "Pretrain/Loss": 2.0234804153442383, "Pretrain/Loss (Raw)": 2.0166144371032715, "Pretrain/Step": 4898, "Pretrain/Step Time": 8.484529444947839} +{"Pretrain/Learning Rate": 2.5101889209398004e-05, "Pretrain/Loss": 2.023669719696045, "Pretrain/Loss (Raw)": 2.1243274211883545, "Pretrain/Step": 4899, "Pretrain/Step Time": 8.484751235693693} +{"Pretrain/Learning Rate": 2.5093398483246554e-05, "Pretrain/Loss": 2.024143695831299, "Pretrain/Loss (Raw)": 2.15222430229187, "Pretrain/Step": 4900, "Pretrain/Step Time": 8.48517893627286} +{"Pretrain/Learning Rate": 2.5084907746321618e-05, "Pretrain/Loss": 2.023655891418457, "Pretrain/Loss (Raw)": 2.034724473953247, "Pretrain/Step": 4901, "Pretrain/Step Time": 8.48546864837408} +{"Pretrain/Learning Rate": 2.507641699960261e-05, "Pretrain/Loss": 2.0231916904449463, "Pretrain/Loss (Raw)": 2.1929662227630615, "Pretrain/Step": 4902, "Pretrain/Step Time": 8.485377738252282} +{"Pretrain/Learning Rate": 2.5067926244068917e-05, "Pretrain/Loss": 2.0237820148468018, "Pretrain/Loss (Raw)": 2.1037445068359375, "Pretrain/Step": 4903, "Pretrain/Step Time": 8.483256010338664} +{"Pretrain/Learning Rate": 2.505943548069996e-05, "Pretrain/Loss": 2.024310827255249, "Pretrain/Loss (Raw)": 1.9879828691482544, "Pretrain/Step": 4904, "Pretrain/Step Time": 8.48145161755383} +{"Pretrain/Learning Rate": 2.505094471047515e-05, "Pretrain/Loss": 2.02260160446167, "Pretrain/Loss (Raw)": 1.775124192237854, "Pretrain/Step": 4905, "Pretrain/Step Time": 8.483361467719078} +{"Pretrain/Learning Rate": 2.5042453934373873e-05, "Pretrain/Loss": 2.021860122680664, "Pretrain/Loss (Raw)": 2.072726249694824, "Pretrain/Step": 4906, "Pretrain/Step Time": 8.48399313353002} +{"Pretrain/Learning Rate": 2.5033963153375556e-05, "Pretrain/Loss": 2.020636558532715, "Pretrain/Loss (Raw)": 1.8931204080581665, "Pretrain/Step": 4907, "Pretrain/Step Time": 8.482243886217475} +{"Pretrain/Learning Rate": 2.5025472368459606e-05, "Pretrain/Loss": 2.018885374069214, "Pretrain/Loss (Raw)": 1.815753698348999, "Pretrain/Step": 4908, "Pretrain/Step Time": 8.484892416745424} +{"Pretrain/Learning Rate": 2.501698158060542e-05, "Pretrain/Loss": 2.019054889678955, "Pretrain/Loss (Raw)": 2.0893752574920654, "Pretrain/Step": 4909, "Pretrain/Step Time": 8.482886772602797} +{"Pretrain/Learning Rate": 2.5008490790792415e-05, "Pretrain/Loss": 2.0187392234802246, "Pretrain/Loss (Raw)": 1.9352494478225708, "Pretrain/Step": 4910, "Pretrain/Step Time": 8.481913432478905} +{"Pretrain/Learning Rate": 2.5e-05, "Pretrain/Loss": 2.0196239948272705, "Pretrain/Loss (Raw)": 2.0131828784942627, "Pretrain/Step": 4911, "Pretrain/Step Time": 8.483109250664711} +{"Pretrain/Learning Rate": 2.4991509209207588e-05, "Pretrain/Loss": 2.0199942588806152, "Pretrain/Loss (Raw)": 2.116752862930298, "Pretrain/Step": 4912, "Pretrain/Step Time": 8.482107376679778} +{"Pretrain/Learning Rate": 2.498301841939458e-05, "Pretrain/Loss": 2.0195252895355225, "Pretrain/Loss (Raw)": 1.934929370880127, "Pretrain/Step": 4913, "Pretrain/Step Time": 8.483025608584285} +{"Pretrain/Learning Rate": 2.4974527631540403e-05, "Pretrain/Loss": 2.0194873809814453, "Pretrain/Loss (Raw)": 2.1273903846740723, "Pretrain/Step": 4914, "Pretrain/Step Time": 8.489260146394372} +{"Pretrain/Learning Rate": 2.4966036846624447e-05, "Pretrain/Loss": 2.019223928451538, "Pretrain/Loss (Raw)": 2.013432025909424, "Pretrain/Step": 4915, "Pretrain/Step Time": 8.488193105906248} +{"Pretrain/Learning Rate": 2.4957546065626133e-05, "Pretrain/Loss": 2.0191826820373535, "Pretrain/Loss (Raw)": 2.0072524547576904, "Pretrain/Step": 4916, "Pretrain/Step Time": 8.484434803947806} +{"Pretrain/Learning Rate": 2.494905528952486e-05, "Pretrain/Loss": 2.0213756561279297, "Pretrain/Loss (Raw)": 2.1327414512634277, "Pretrain/Step": 4917, "Pretrain/Step Time": 8.488629491999745} +{"Pretrain/Learning Rate": 2.4940564519300038e-05, "Pretrain/Loss": 2.0202062129974365, "Pretrain/Loss (Raw)": 1.7506293058395386, "Pretrain/Step": 4918, "Pretrain/Step Time": 8.489788772538304} +{"Pretrain/Learning Rate": 2.4932073755931092e-05, "Pretrain/Loss": 2.0182394981384277, "Pretrain/Loss (Raw)": 1.9324990510940552, "Pretrain/Step": 4919, "Pretrain/Step Time": 8.49087448604405} +{"Pretrain/Learning Rate": 2.49235830003974e-05, "Pretrain/Loss": 2.019160747528076, "Pretrain/Loss (Raw)": 2.091729164123535, "Pretrain/Step": 4920, "Pretrain/Step Time": 8.490751087665558} +{"Pretrain/Learning Rate": 2.4915092253678388e-05, "Pretrain/Loss": 2.0182371139526367, "Pretrain/Loss (Raw)": 2.098933458328247, "Pretrain/Step": 4921, "Pretrain/Step Time": 8.489949906244874} +{"Pretrain/Learning Rate": 2.490660151675345e-05, "Pretrain/Loss": 2.018505811691284, "Pretrain/Loss (Raw)": 2.0331084728240967, "Pretrain/Step": 4922, "Pretrain/Step Time": 8.490355309098959} +{"Pretrain/Learning Rate": 2.4898110790602e-05, "Pretrain/Loss": 2.018115997314453, "Pretrain/Loss (Raw)": 1.9652910232543945, "Pretrain/Step": 4923, "Pretrain/Step Time": 8.491167644038796} +{"Pretrain/Learning Rate": 2.4889620076203432e-05, "Pretrain/Loss": 2.018216371536255, "Pretrain/Loss (Raw)": 2.0896313190460205, "Pretrain/Step": 4924, "Pretrain/Step Time": 8.494379973039031} +{"Pretrain/Learning Rate": 2.488112937453716e-05, "Pretrain/Loss": 2.019775390625, "Pretrain/Loss (Raw)": 2.016251802444458, "Pretrain/Step": 4925, "Pretrain/Step Time": 8.489788509905338} +{"Pretrain/Learning Rate": 2.4872638686582563e-05, "Pretrain/Loss": 2.01931095123291, "Pretrain/Loss (Raw)": 2.0542376041412354, "Pretrain/Step": 4926, "Pretrain/Step Time": 8.485232999548316} +{"Pretrain/Learning Rate": 2.4864148013319044e-05, "Pretrain/Loss": 2.017867088317871, "Pretrain/Loss (Raw)": 2.0055277347564697, "Pretrain/Step": 4927, "Pretrain/Step Time": 8.485839918255806} +{"Pretrain/Learning Rate": 2.4855657355726007e-05, "Pretrain/Loss": 2.0167653560638428, "Pretrain/Loss (Raw)": 1.8789690732955933, "Pretrain/Step": 4928, "Pretrain/Step Time": 8.488849338144064} +{"Pretrain/Learning Rate": 2.4847166714782842e-05, "Pretrain/Loss": 2.0171022415161133, "Pretrain/Loss (Raw)": 2.0092101097106934, "Pretrain/Step": 4929, "Pretrain/Step Time": 8.49050509557128} +{"Pretrain/Learning Rate": 2.4838676091468954e-05, "Pretrain/Loss": 2.0180704593658447, "Pretrain/Loss (Raw)": 1.955209493637085, "Pretrain/Step": 4930, "Pretrain/Step Time": 8.495186526328325} +{"Pretrain/Learning Rate": 2.483018548676371e-05, "Pretrain/Loss": 2.018141746520996, "Pretrain/Loss (Raw)": 2.098203182220459, "Pretrain/Step": 4931, "Pretrain/Step Time": 8.493310805410147} +{"Pretrain/Learning Rate": 2.4821694901646518e-05, "Pretrain/Loss": 2.0180957317352295, "Pretrain/Loss (Raw)": 2.1892874240875244, "Pretrain/Step": 4932, "Pretrain/Step Time": 8.490130927413702} +{"Pretrain/Learning Rate": 2.481320433709675e-05, "Pretrain/Loss": 2.017010450363159, "Pretrain/Loss (Raw)": 1.965538740158081, "Pretrain/Step": 4933, "Pretrain/Step Time": 8.489304153248668} +{"Pretrain/Learning Rate": 2.4804713794093797e-05, "Pretrain/Loss": 2.0168519020080566, "Pretrain/Loss (Raw)": 2.0267767906188965, "Pretrain/Step": 4934, "Pretrain/Step Time": 8.489435436204076} +{"Pretrain/Learning Rate": 2.479622327361705e-05, "Pretrain/Loss": 2.0157668590545654, "Pretrain/Loss (Raw)": 2.006887197494507, "Pretrain/Step": 4935, "Pretrain/Step Time": 8.487115217372775} +{"Pretrain/Learning Rate": 2.4787732776645865e-05, "Pretrain/Loss": 2.0171024799346924, "Pretrain/Loss (Raw)": 2.0814967155456543, "Pretrain/Step": 4936, "Pretrain/Step Time": 8.490176189690828} +{"Pretrain/Learning Rate": 2.477924230415963e-05, "Pretrain/Loss": 2.017794370651245, "Pretrain/Loss (Raw)": 2.1334187984466553, "Pretrain/Step": 4937, "Pretrain/Step Time": 8.488569123670459} +{"Pretrain/Learning Rate": 2.4770751857137718e-05, "Pretrain/Loss": 2.018704414367676, "Pretrain/Loss (Raw)": 2.009962558746338, "Pretrain/Step": 4938, "Pretrain/Step Time": 8.487957136705518} +{"Pretrain/Learning Rate": 2.47622614365595e-05, "Pretrain/Loss": 2.0178415775299072, "Pretrain/Loss (Raw)": 1.865289330482483, "Pretrain/Step": 4939, "Pretrain/Step Time": 8.486704785376787} +{"Pretrain/Learning Rate": 2.475377104340435e-05, "Pretrain/Loss": 2.0179312229156494, "Pretrain/Loss (Raw)": 1.9643481969833374, "Pretrain/Step": 4940, "Pretrain/Step Time": 8.491760915145278} +{"Pretrain/Learning Rate": 2.4745280678651614e-05, "Pretrain/Loss": 2.018505334854126, "Pretrain/Loss (Raw)": 2.0798656940460205, "Pretrain/Step": 4941, "Pretrain/Step Time": 8.48982834815979} +{"Pretrain/Learning Rate": 2.4736790343280667e-05, "Pretrain/Loss": 2.017009973526001, "Pretrain/Loss (Raw)": 1.9819155931472778, "Pretrain/Step": 4942, "Pretrain/Step Time": 8.486568756401539} +{"Pretrain/Learning Rate": 2.4728300038270854e-05, "Pretrain/Loss": 2.015918254852295, "Pretrain/Loss (Raw)": 1.8643478155136108, "Pretrain/Step": 4943, "Pretrain/Step Time": 8.48176834732294} +{"Pretrain/Learning Rate": 2.471980976460154e-05, "Pretrain/Loss": 2.015138864517212, "Pretrain/Loss (Raw)": 2.0314276218414307, "Pretrain/Step": 4944, "Pretrain/Step Time": 8.480057062581182} +{"Pretrain/Learning Rate": 2.471131952325207e-05, "Pretrain/Loss": 2.0183844566345215, "Pretrain/Loss (Raw)": 2.0371205806732178, "Pretrain/Step": 4945, "Pretrain/Step Time": 8.483600987121463} +{"Pretrain/Learning Rate": 2.4702829315201803e-05, "Pretrain/Loss": 2.0204172134399414, "Pretrain/Loss (Raw)": 2.1344330310821533, "Pretrain/Step": 4946, "Pretrain/Step Time": 8.484720991924405} +{"Pretrain/Learning Rate": 2.4694339141430055e-05, "Pretrain/Loss": 2.0194435119628906, "Pretrain/Loss (Raw)": 1.8642723560333252, "Pretrain/Step": 4947, "Pretrain/Step Time": 8.487316966056824} +{"Pretrain/Learning Rate": 2.4685849002916183e-05, "Pretrain/Loss": 2.020371913909912, "Pretrain/Loss (Raw)": 1.9776254892349243, "Pretrain/Step": 4948, "Pretrain/Step Time": 8.489463787525892} +{"Pretrain/Learning Rate": 2.4677358900639525e-05, "Pretrain/Loss": 2.0194852352142334, "Pretrain/Loss (Raw)": 1.9210559129714966, "Pretrain/Step": 4949, "Pretrain/Step Time": 8.489060077816248} +{"Pretrain/Learning Rate": 2.4668868835579398e-05, "Pretrain/Loss": 2.021571159362793, "Pretrain/Loss (Raw)": 2.1723339557647705, "Pretrain/Step": 4950, "Pretrain/Step Time": 8.489051088690758} +{"Pretrain/Learning Rate": 2.4660378808715147e-05, "Pretrain/Loss": 2.0214672088623047, "Pretrain/Loss (Raw)": 2.0056755542755127, "Pretrain/Step": 4951, "Pretrain/Step Time": 8.486364400014281} +{"Pretrain/Learning Rate": 2.4651888821026065e-05, "Pretrain/Loss": 2.022948980331421, "Pretrain/Loss (Raw)": 2.1655917167663574, "Pretrain/Step": 4952, "Pretrain/Step Time": 8.486475022509694} +{"Pretrain/Learning Rate": 2.4643398873491488e-05, "Pretrain/Loss": 2.0242042541503906, "Pretrain/Loss (Raw)": 1.8816697597503662, "Pretrain/Step": 4953, "Pretrain/Step Time": 8.48488556779921} +{"Pretrain/Learning Rate": 2.4634908967090725e-05, "Pretrain/Loss": 2.024895191192627, "Pretrain/Loss (Raw)": 2.1075899600982666, "Pretrain/Step": 4954, "Pretrain/Step Time": 8.485924746841192} +{"Pretrain/Learning Rate": 2.4626419102803085e-05, "Pretrain/Loss": 2.024792194366455, "Pretrain/Loss (Raw)": 2.113255500793457, "Pretrain/Step": 4955, "Pretrain/Step Time": 8.486771643161774} +{"Pretrain/Learning Rate": 2.4617929281607883e-05, "Pretrain/Loss": 2.0242888927459717, "Pretrain/Loss (Raw)": 1.997405767440796, "Pretrain/Step": 4956, "Pretrain/Step Time": 8.491324827075005} +{"Pretrain/Learning Rate": 2.4609439504484392e-05, "Pretrain/Loss": 2.0256147384643555, "Pretrain/Loss (Raw)": 2.0234622955322266, "Pretrain/Step": 4957, "Pretrain/Step Time": 8.485204441472888} +{"Pretrain/Learning Rate": 2.460094977241192e-05, "Pretrain/Loss": 2.022146224975586, "Pretrain/Loss (Raw)": 1.7187834978103638, "Pretrain/Step": 4958, "Pretrain/Step Time": 8.488747859373689} +{"Pretrain/Learning Rate": 2.4592460086369747e-05, "Pretrain/Loss": 2.0215344429016113, "Pretrain/Loss (Raw)": 1.9264062643051147, "Pretrain/Step": 4959, "Pretrain/Step Time": 8.482353342697024} +{"Pretrain/Learning Rate": 2.4583970447337163e-05, "Pretrain/Loss": 2.0221846103668213, "Pretrain/Loss (Raw)": 2.184229612350464, "Pretrain/Step": 4960, "Pretrain/Step Time": 8.486160323023796} +{"Pretrain/Learning Rate": 2.4575480856293447e-05, "Pretrain/Loss": 2.022594690322876, "Pretrain/Loss (Raw)": 2.031315803527832, "Pretrain/Step": 4961, "Pretrain/Step Time": 8.487834399566054} +{"Pretrain/Learning Rate": 2.456699131421786e-05, "Pretrain/Loss": 2.0224266052246094, "Pretrain/Loss (Raw)": 2.107443332672119, "Pretrain/Step": 4962, "Pretrain/Step Time": 8.490087056532502} +{"Pretrain/Learning Rate": 2.4558501822089668e-05, "Pretrain/Loss": 2.0208702087402344, "Pretrain/Loss (Raw)": 1.9767448902130127, "Pretrain/Step": 4963, "Pretrain/Step Time": 8.488336883485317} +{"Pretrain/Learning Rate": 2.4550012380888138e-05, "Pretrain/Loss": 2.0210952758789062, "Pretrain/Loss (Raw)": 1.9284194707870483, "Pretrain/Step": 4964, "Pretrain/Step Time": 8.491171706467867} +{"Pretrain/Learning Rate": 2.454152299159253e-05, "Pretrain/Loss": 2.0206847190856934, "Pretrain/Loss (Raw)": 1.9767975807189941, "Pretrain/Step": 4965, "Pretrain/Step Time": 8.489596035331488} +{"Pretrain/Learning Rate": 2.4533033655182072e-05, "Pretrain/Loss": 2.0210092067718506, "Pretrain/Loss (Raw)": 2.085465669631958, "Pretrain/Step": 4966, "Pretrain/Step Time": 8.49097259156406} +{"Pretrain/Learning Rate": 2.4524544372636034e-05, "Pretrain/Loss": 2.021852493286133, "Pretrain/Loss (Raw)": 2.0117998123168945, "Pretrain/Step": 4967, "Pretrain/Step Time": 8.489667184650898} +{"Pretrain/Learning Rate": 2.4516055144933623e-05, "Pretrain/Loss": 2.022152900695801, "Pretrain/Loss (Raw)": 1.984244704246521, "Pretrain/Step": 4968, "Pretrain/Step Time": 8.484240427613258} +{"Pretrain/Learning Rate": 2.450756597305408e-05, "Pretrain/Loss": 2.023764133453369, "Pretrain/Loss (Raw)": 1.9482849836349487, "Pretrain/Step": 4969, "Pretrain/Step Time": 8.486118748784065} +{"Pretrain/Learning Rate": 2.4499076857976628e-05, "Pretrain/Loss": 2.0254974365234375, "Pretrain/Loss (Raw)": 1.9664419889450073, "Pretrain/Step": 4970, "Pretrain/Step Time": 8.488929128274322} +{"Pretrain/Learning Rate": 2.4490587800680486e-05, "Pretrain/Loss": 2.023655414581299, "Pretrain/Loss (Raw)": 1.8489501476287842, "Pretrain/Step": 4971, "Pretrain/Step Time": 8.488055944442749} +{"Pretrain/Learning Rate": 2.4482098802144872e-05, "Pretrain/Loss": 2.0228030681610107, "Pretrain/Loss (Raw)": 1.8090547323226929, "Pretrain/Step": 4972, "Pretrain/Step Time": 8.48841992020607} +{"Pretrain/Learning Rate": 2.447360986334897e-05, "Pretrain/Loss": 2.020244836807251, "Pretrain/Loss (Raw)": 1.876319408416748, "Pretrain/Step": 4973, "Pretrain/Step Time": 8.49086600355804} +{"Pretrain/Learning Rate": 2.446512098527199e-05, "Pretrain/Loss": 2.0197458267211914, "Pretrain/Loss (Raw)": 1.8732061386108398, "Pretrain/Step": 4974, "Pretrain/Step Time": 8.489906640723348} +{"Pretrain/Learning Rate": 2.445663216889311e-05, "Pretrain/Loss": 2.02097225189209, "Pretrain/Loss (Raw)": 2.155367612838745, "Pretrain/Step": 4975, "Pretrain/Step Time": 8.488740630447865} +{"Pretrain/Learning Rate": 2.444814341519152e-05, "Pretrain/Loss": 2.0218889713287354, "Pretrain/Loss (Raw)": 2.1002728939056396, "Pretrain/Step": 4976, "Pretrain/Step Time": 8.485246984288096} +{"Pretrain/Learning Rate": 2.44396547251464e-05, "Pretrain/Loss": 2.0207996368408203, "Pretrain/Loss (Raw)": 1.9937878847122192, "Pretrain/Step": 4977, "Pretrain/Step Time": 8.48984213732183} +{"Pretrain/Learning Rate": 2.4431166099736908e-05, "Pretrain/Loss": 2.0206856727600098, "Pretrain/Loss (Raw)": 2.0090370178222656, "Pretrain/Step": 4978, "Pretrain/Step Time": 8.49549707211554} +{"Pretrain/Learning Rate": 2.44226775399422e-05, "Pretrain/Loss": 2.01733136177063, "Pretrain/Loss (Raw)": 1.7743531465530396, "Pretrain/Step": 4979, "Pretrain/Step Time": 8.500521719455719} +{"Pretrain/Learning Rate": 2.4414189046741437e-05, "Pretrain/Loss": 2.0167057514190674, "Pretrain/Loss (Raw)": 1.9810206890106201, "Pretrain/Step": 4980, "Pretrain/Step Time": 8.500666309148073} +{"Pretrain/Learning Rate": 2.440570062111376e-05, "Pretrain/Loss": 2.0180506706237793, "Pretrain/Loss (Raw)": 2.099905490875244, "Pretrain/Step": 4981, "Pretrain/Step Time": 8.4994624145329} +{"Pretrain/Learning Rate": 2.4397212264038313e-05, "Pretrain/Loss": 2.0151920318603516, "Pretrain/Loss (Raw)": 1.900580644607544, "Pretrain/Step": 4982, "Pretrain/Step Time": 8.499540723860264} +{"Pretrain/Learning Rate": 2.438872397649422e-05, "Pretrain/Loss": 2.0167431831359863, "Pretrain/Loss (Raw)": 2.025265693664551, "Pretrain/Step": 4983, "Pretrain/Step Time": 8.501382518559694} +{"Pretrain/Learning Rate": 2.4380235759460603e-05, "Pretrain/Loss": 2.0166749954223633, "Pretrain/Loss (Raw)": 2.0301969051361084, "Pretrain/Step": 4984, "Pretrain/Step Time": 8.499762253835797} +{"Pretrain/Learning Rate": 2.4371747613916566e-05, "Pretrain/Loss": 2.016287326812744, "Pretrain/Loss (Raw)": 2.0472805500030518, "Pretrain/Step": 4985, "Pretrain/Step Time": 8.49986981973052} +{"Pretrain/Learning Rate": 2.4363259540841222e-05, "Pretrain/Loss": 2.0176405906677246, "Pretrain/Loss (Raw)": 2.0292065143585205, "Pretrain/Step": 4986, "Pretrain/Step Time": 8.4952392578125} +{"Pretrain/Learning Rate": 2.4354771541213663e-05, "Pretrain/Loss": 2.017627716064453, "Pretrain/Loss (Raw)": 2.0413403511047363, "Pretrain/Step": 4987, "Pretrain/Step Time": 8.500465640798211} +{"Pretrain/Learning Rate": 2.4346283616012996e-05, "Pretrain/Loss": 2.017505407333374, "Pretrain/Loss (Raw)": 2.00783109664917, "Pretrain/Step": 4988, "Pretrain/Step Time": 8.498748313635588} +{"Pretrain/Learning Rate": 2.433779576621827e-05, "Pretrain/Loss": 2.0181689262390137, "Pretrain/Loss (Raw)": 1.9003483057022095, "Pretrain/Step": 4989, "Pretrain/Step Time": 8.491726642474532} +{"Pretrain/Learning Rate": 2.432930799280857e-05, "Pretrain/Loss": 2.0187010765075684, "Pretrain/Loss (Raw)": 2.2315638065338135, "Pretrain/Step": 4990, "Pretrain/Step Time": 8.491557020694017} +{"Pretrain/Learning Rate": 2.4320820296762964e-05, "Pretrain/Loss": 2.0149452686309814, "Pretrain/Loss (Raw)": 1.6017861366271973, "Pretrain/Step": 4991, "Pretrain/Step Time": 8.490873120725155} +{"Pretrain/Learning Rate": 2.431233267906049e-05, "Pretrain/Loss": 2.015979766845703, "Pretrain/Loss (Raw)": 2.1010630130767822, "Pretrain/Step": 4992, "Pretrain/Step Time": 8.489599201828241} +{"Pretrain/Learning Rate": 2.4303845140680215e-05, "Pretrain/Loss": 2.01690936088562, "Pretrain/Loss (Raw)": 2.1226346492767334, "Pretrain/Step": 4993, "Pretrain/Step Time": 8.493234395980835} +{"Pretrain/Learning Rate": 2.429535768260115e-05, "Pretrain/Loss": 2.01676082611084, "Pretrain/Loss (Raw)": 1.9363558292388916, "Pretrain/Step": 4994, "Pretrain/Step Time": 8.493894821032882} +{"Pretrain/Learning Rate": 2.428687030580232e-05, "Pretrain/Loss": 2.0156774520874023, "Pretrain/Loss (Raw)": 2.0382211208343506, "Pretrain/Step": 4995, "Pretrain/Step Time": 8.495087448507547} +{"Pretrain/Learning Rate": 2.4278383011262755e-05, "Pretrain/Loss": 2.0151493549346924, "Pretrain/Loss (Raw)": 1.9779973030090332, "Pretrain/Step": 4996, "Pretrain/Step Time": 8.494530556723475} +{"Pretrain/Learning Rate": 2.4269895799961452e-05, "Pretrain/Loss": 2.015958309173584, "Pretrain/Loss (Raw)": 2.150693416595459, "Pretrain/Step": 4997, "Pretrain/Step Time": 8.497019160538912} +{"Pretrain/Learning Rate": 2.4261408672877427e-05, "Pretrain/Loss": 2.0165491104125977, "Pretrain/Loss (Raw)": 2.0318045616149902, "Pretrain/Step": 4998, "Pretrain/Step Time": 8.49512298591435} +{"Pretrain/Learning Rate": 2.425292163098964e-05, "Pretrain/Loss": 2.015742778778076, "Pretrain/Loss (Raw)": 1.8795502185821533, "Pretrain/Step": 4999, "Pretrain/Step Time": 8.494934730231762} +{"Pretrain/Learning Rate": 2.4244434675277082e-05, "Pretrain/Loss": 2.0155913829803467, "Pretrain/Loss (Raw)": 2.001232624053955, "Pretrain/Step": 5000, "Pretrain/Step Time": 8.492754504084587} +{"Pretrain/Learning Rate": 2.4235947806718717e-05, "Pretrain/Loss": 2.015312910079956, "Pretrain/Loss (Raw)": 1.8831390142440796, "Pretrain/Step": 5001, "Pretrain/Step Time": 9.595633396878839} +{"Pretrain/Learning Rate": 2.4227461026293503e-05, "Pretrain/Loss": 2.014770030975342, "Pretrain/Loss (Raw)": 2.001403331756592, "Pretrain/Step": 5002, "Pretrain/Step Time": 9.595614351332188} +{"Pretrain/Learning Rate": 2.421897433498039e-05, "Pretrain/Loss": 2.0142250061035156, "Pretrain/Loss (Raw)": 2.1156601905822754, "Pretrain/Step": 5003, "Pretrain/Step Time": 9.594030039384961} +{"Pretrain/Learning Rate": 2.4210487733758326e-05, "Pretrain/Loss": 2.012810468673706, "Pretrain/Loss (Raw)": 2.0437676906585693, "Pretrain/Step": 5004, "Pretrain/Step Time": 9.593933241441846} +{"Pretrain/Learning Rate": 2.4202001223606208e-05, "Pretrain/Loss": 2.0139365196228027, "Pretrain/Loss (Raw)": 2.1347434520721436, "Pretrain/Step": 5005, "Pretrain/Step Time": 9.593315383419394} +{"Pretrain/Learning Rate": 2.419351480550297e-05, "Pretrain/Loss": 2.014298439025879, "Pretrain/Loss (Raw)": 2.1471078395843506, "Pretrain/Step": 5006, "Pretrain/Step Time": 9.59236416220665} +{"Pretrain/Learning Rate": 2.4185028480427523e-05, "Pretrain/Loss": 2.0144691467285156, "Pretrain/Loss (Raw)": 1.9768913984298706, "Pretrain/Step": 5007, "Pretrain/Step Time": 9.594356272369623} +{"Pretrain/Learning Rate": 2.4176542249358747e-05, "Pretrain/Loss": 2.0128333568573, "Pretrain/Loss (Raw)": 1.972119927406311, "Pretrain/Step": 5008, "Pretrain/Step Time": 9.589306211099029} +{"Pretrain/Learning Rate": 2.4168056113275545e-05, "Pretrain/Loss": 2.011476516723633, "Pretrain/Loss (Raw)": 1.8608285188674927, "Pretrain/Step": 5009, "Pretrain/Step Time": 9.591889515519142} +{"Pretrain/Learning Rate": 2.4159570073156765e-05, "Pretrain/Loss": 2.0115456581115723, "Pretrain/Loss (Raw)": 2.047865152359009, "Pretrain/Step": 5010, "Pretrain/Step Time": 9.595960834994912} +{"Pretrain/Learning Rate": 2.4151084129981285e-05, "Pretrain/Loss": 2.012559413909912, "Pretrain/Loss (Raw)": 2.1543946266174316, "Pretrain/Step": 5011, "Pretrain/Step Time": 9.597703024744987} +{"Pretrain/Learning Rate": 2.414259828472795e-05, "Pretrain/Loss": 2.013880491256714, "Pretrain/Loss (Raw)": 2.0342016220092773, "Pretrain/Step": 5012, "Pretrain/Step Time": 9.59499941021204} +{"Pretrain/Learning Rate": 2.4134112538375604e-05, "Pretrain/Loss": 2.014194965362549, "Pretrain/Loss (Raw)": 2.110286235809326, "Pretrain/Step": 5013, "Pretrain/Step Time": 9.599437547847629} +{"Pretrain/Learning Rate": 2.412562689190308e-05, "Pretrain/Loss": 2.0119540691375732, "Pretrain/Loss (Raw)": 1.9946290254592896, "Pretrain/Step": 5014, "Pretrain/Step Time": 9.598526580259204} +{"Pretrain/Learning Rate": 2.4117141346289175e-05, "Pretrain/Loss": 2.0115435123443604, "Pretrain/Loss (Raw)": 1.9664676189422607, "Pretrain/Step": 5015, "Pretrain/Step Time": 9.6005714610219} +{"Pretrain/Learning Rate": 2.4108655902512713e-05, "Pretrain/Loss": 2.0115015506744385, "Pretrain/Loss (Raw)": 1.98029363155365, "Pretrain/Step": 5016, "Pretrain/Step Time": 9.599888613447547} +{"Pretrain/Learning Rate": 2.4100170561552478e-05, "Pretrain/Loss": 2.009746551513672, "Pretrain/Loss (Raw)": 2.02970814704895, "Pretrain/Step": 5017, "Pretrain/Step Time": 9.59805298782885} +{"Pretrain/Learning Rate": 2.4091685324387246e-05, "Pretrain/Loss": 2.0082943439483643, "Pretrain/Loss (Raw)": 2.1114048957824707, "Pretrain/Step": 5018, "Pretrain/Step Time": 9.60032065026462} +{"Pretrain/Learning Rate": 2.408320019199581e-05, "Pretrain/Loss": 2.009181022644043, "Pretrain/Loss (Raw)": 2.195690393447876, "Pretrain/Step": 5019, "Pretrain/Step Time": 9.596194667741656} +{"Pretrain/Learning Rate": 2.4074715165356894e-05, "Pretrain/Loss": 2.008939743041992, "Pretrain/Loss (Raw)": 1.8751740455627441, "Pretrain/Step": 5020, "Pretrain/Step Time": 9.59836607426405} +{"Pretrain/Learning Rate": 2.406623024544926e-05, "Pretrain/Loss": 2.011359453201294, "Pretrain/Loss (Raw)": 2.136532783508301, "Pretrain/Step": 5021, "Pretrain/Step Time": 9.592604329809546} +{"Pretrain/Learning Rate": 2.4057745433251635e-05, "Pretrain/Loss": 2.011768341064453, "Pretrain/Loss (Raw)": 2.0917882919311523, "Pretrain/Step": 5022, "Pretrain/Step Time": 9.590254470705986} +{"Pretrain/Learning Rate": 2.4049260729742748e-05, "Pretrain/Loss": 2.010132312774658, "Pretrain/Loss (Raw)": 1.8858944177627563, "Pretrain/Step": 5023, "Pretrain/Step Time": 9.589785769581795} +{"Pretrain/Learning Rate": 2.4040776135901306e-05, "Pretrain/Loss": 2.00964617729187, "Pretrain/Loss (Raw)": 1.887442946434021, "Pretrain/Step": 5024, "Pretrain/Step Time": 9.593681935220957} +{"Pretrain/Learning Rate": 2.4032291652706e-05, "Pretrain/Loss": 2.0092477798461914, "Pretrain/Loss (Raw)": 2.0025742053985596, "Pretrain/Step": 5025, "Pretrain/Step Time": 9.593252839520574} +{"Pretrain/Learning Rate": 2.402380728113551e-05, "Pretrain/Loss": 2.0076518058776855, "Pretrain/Loss (Raw)": 1.8123235702514648, "Pretrain/Step": 5026, "Pretrain/Step Time": 9.594527984037995} +{"Pretrain/Learning Rate": 2.4015323022168505e-05, "Pretrain/Loss": 2.0064215660095215, "Pretrain/Loss (Raw)": 1.9668643474578857, "Pretrain/Step": 5027, "Pretrain/Step Time": 9.590432081371546} +{"Pretrain/Learning Rate": 2.400683887678364e-05, "Pretrain/Loss": 2.0063304901123047, "Pretrain/Loss (Raw)": 2.140557289123535, "Pretrain/Step": 5028, "Pretrain/Step Time": 9.592270726338029} +{"Pretrain/Learning Rate": 2.3998354845959565e-05, "Pretrain/Loss": 2.0066943168640137, "Pretrain/Loss (Raw)": 2.0813162326812744, "Pretrain/Step": 5029, "Pretrain/Step Time": 9.590841580182314} +{"Pretrain/Learning Rate": 2.3989870930674913e-05, "Pretrain/Loss": 2.0047144889831543, "Pretrain/Loss (Raw)": 1.9395440816879272, "Pretrain/Step": 5030, "Pretrain/Step Time": 9.590730210766196} +{"Pretrain/Learning Rate": 2.3981387131908287e-05, "Pretrain/Loss": 2.0047690868377686, "Pretrain/Loss (Raw)": 2.1107351779937744, "Pretrain/Step": 5031, "Pretrain/Step Time": 9.592495027929544} +{"Pretrain/Learning Rate": 2.3972903450638296e-05, "Pretrain/Loss": 2.005368232727051, "Pretrain/Loss (Raw)": 2.0646793842315674, "Pretrain/Step": 5032, "Pretrain/Step Time": 9.590272404253483} +{"Pretrain/Learning Rate": 2.3964419887843536e-05, "Pretrain/Loss": 2.0077743530273438, "Pretrain/Loss (Raw)": 2.0830817222595215, "Pretrain/Step": 5033, "Pretrain/Step Time": 9.587442006915808} +{"Pretrain/Learning Rate": 2.3955936444502573e-05, "Pretrain/Loss": 2.0077736377716064, "Pretrain/Loss (Raw)": 2.072648048400879, "Pretrain/Step": 5034, "Pretrain/Step Time": 9.584119364619255} +{"Pretrain/Learning Rate": 2.3947453121593984e-05, "Pretrain/Loss": 2.009917736053467, "Pretrain/Loss (Raw)": 2.1675591468811035, "Pretrain/Step": 5035, "Pretrain/Step Time": 9.583676848560572} +{"Pretrain/Learning Rate": 2.39389699200963e-05, "Pretrain/Loss": 2.011378288269043, "Pretrain/Loss (Raw)": 2.0027196407318115, "Pretrain/Step": 5036, "Pretrain/Step Time": 9.580484507605433} +{"Pretrain/Learning Rate": 2.393048684098806e-05, "Pretrain/Loss": 2.0108776092529297, "Pretrain/Loss (Raw)": 2.025258779525757, "Pretrain/Step": 5037, "Pretrain/Step Time": 9.579469066113234} +{"Pretrain/Learning Rate": 2.3922003885247788e-05, "Pretrain/Loss": 2.012474775314331, "Pretrain/Loss (Raw)": 2.1397016048431396, "Pretrain/Step": 5038, "Pretrain/Step Time": 9.580422727391124} +{"Pretrain/Learning Rate": 2.3913521053853987e-05, "Pretrain/Loss": 2.010300636291504, "Pretrain/Loss (Raw)": 1.7349262237548828, "Pretrain/Step": 5039, "Pretrain/Step Time": 9.577540727332234} +{"Pretrain/Learning Rate": 2.3905038347785165e-05, "Pretrain/Loss": 2.009690046310425, "Pretrain/Loss (Raw)": 2.0385560989379883, "Pretrain/Step": 5040, "Pretrain/Step Time": 9.583404069766402} +{"Pretrain/Learning Rate": 2.389655576801977e-05, "Pretrain/Loss": 2.0105648040771484, "Pretrain/Loss (Raw)": 2.046910524368286, "Pretrain/Step": 5041, "Pretrain/Step Time": 9.582171730697155} +{"Pretrain/Learning Rate": 2.3888073315536285e-05, "Pretrain/Loss": 2.0101590156555176, "Pretrain/Loss (Raw)": 2.0754354000091553, "Pretrain/Step": 5042, "Pretrain/Step Time": 9.578410038724542} +{"Pretrain/Learning Rate": 2.387959099131315e-05, "Pretrain/Loss": 2.010450601577759, "Pretrain/Loss (Raw)": 2.0507524013519287, "Pretrain/Step": 5043, "Pretrain/Step Time": 9.578131042420864} +{"Pretrain/Learning Rate": 2.38711087963288e-05, "Pretrain/Loss": 2.011777877807617, "Pretrain/Loss (Raw)": 2.177168130874634, "Pretrain/Step": 5044, "Pretrain/Step Time": 9.578784422948956} +{"Pretrain/Learning Rate": 2.386262673156165e-05, "Pretrain/Loss": 2.01066255569458, "Pretrain/Loss (Raw)": 1.9899736642837524, "Pretrain/Step": 5045, "Pretrain/Step Time": 9.578367281705141} +{"Pretrain/Learning Rate": 2.3854144797990122e-05, "Pretrain/Loss": 2.0139737129211426, "Pretrain/Loss (Raw)": 2.174449920654297, "Pretrain/Step": 5046, "Pretrain/Step Time": 9.576915852725506} +{"Pretrain/Learning Rate": 2.3845662996592576e-05, "Pretrain/Loss": 2.0123908519744873, "Pretrain/Loss (Raw)": 1.7298990488052368, "Pretrain/Step": 5047, "Pretrain/Step Time": 9.57608538493514} +{"Pretrain/Learning Rate": 2.38371813283474e-05, "Pretrain/Loss": 2.0082130432128906, "Pretrain/Loss (Raw)": 1.5569568872451782, "Pretrain/Step": 5048, "Pretrain/Step Time": 9.57647298462689} +{"Pretrain/Learning Rate": 2.382869979423295e-05, "Pretrain/Loss": 2.007664203643799, "Pretrain/Loss (Raw)": 2.0287065505981445, "Pretrain/Step": 5049, "Pretrain/Step Time": 9.575110221281648} +{"Pretrain/Learning Rate": 2.3820218395227567e-05, "Pretrain/Loss": 2.0080575942993164, "Pretrain/Loss (Raw)": 2.083461284637451, "Pretrain/Step": 5050, "Pretrain/Step Time": 9.574846690520644} +{"Pretrain/Learning Rate": 2.3811737132309584e-05, "Pretrain/Loss": 2.0073957443237305, "Pretrain/Loss (Raw)": 1.880547285079956, "Pretrain/Step": 5051, "Pretrain/Step Time": 9.574235366657376} +{"Pretrain/Learning Rate": 2.3803256006457297e-05, "Pretrain/Loss": 2.0085558891296387, "Pretrain/Loss (Raw)": 2.2381253242492676, "Pretrain/Step": 5052, "Pretrain/Step Time": 9.570090970024467} +{"Pretrain/Learning Rate": 2.3794775018649005e-05, "Pretrain/Loss": 2.0076711177825928, "Pretrain/Loss (Raw)": 1.9030264616012573, "Pretrain/Step": 5053, "Pretrain/Step Time": 9.572394413873553} +{"Pretrain/Learning Rate": 2.3786294169862998e-05, "Pretrain/Loss": 2.0062062740325928, "Pretrain/Loss (Raw)": 1.866725206375122, "Pretrain/Step": 5054, "Pretrain/Step Time": 9.57365040667355} +{"Pretrain/Learning Rate": 2.3777813461077526e-05, "Pretrain/Loss": 2.0080344676971436, "Pretrain/Loss (Raw)": 2.2395522594451904, "Pretrain/Step": 5055, "Pretrain/Step Time": 9.577179996296763} +{"Pretrain/Learning Rate": 2.3769332893270853e-05, "Pretrain/Loss": 2.009894371032715, "Pretrain/Loss (Raw)": 2.1170146465301514, "Pretrain/Step": 5056, "Pretrain/Step Time": 9.573365613818169} +{"Pretrain/Learning Rate": 2.376085246742119e-05, "Pretrain/Loss": 2.008141040802002, "Pretrain/Loss (Raw)": 1.7847766876220703, "Pretrain/Step": 5057, "Pretrain/Step Time": 9.574579341337085} +{"Pretrain/Learning Rate": 2.3752372184506764e-05, "Pretrain/Loss": 2.007148027420044, "Pretrain/Loss (Raw)": 1.8281172513961792, "Pretrain/Step": 5058, "Pretrain/Step Time": 9.569285908713937} +{"Pretrain/Learning Rate": 2.3743892045505764e-05, "Pretrain/Loss": 2.0078890323638916, "Pretrain/Loss (Raw)": 2.1930594444274902, "Pretrain/Step": 5059, "Pretrain/Step Time": 9.57065449655056} +{"Pretrain/Learning Rate": 2.3735412051396376e-05, "Pretrain/Loss": 2.005345344543457, "Pretrain/Loss (Raw)": 1.8637027740478516, "Pretrain/Step": 5060, "Pretrain/Step Time": 9.570604098960757} +{"Pretrain/Learning Rate": 2.3726932203156772e-05, "Pretrain/Loss": 2.006251811981201, "Pretrain/Loss (Raw)": 2.0815556049346924, "Pretrain/Step": 5061, "Pretrain/Step Time": 9.57275847159326} +{"Pretrain/Learning Rate": 2.3718452501765078e-05, "Pretrain/Loss": 2.006270408630371, "Pretrain/Loss (Raw)": 2.0291569232940674, "Pretrain/Step": 5062, "Pretrain/Step Time": 9.570610355585814} +{"Pretrain/Learning Rate": 2.370997294819944e-05, "Pretrain/Loss": 2.005613088607788, "Pretrain/Loss (Raw)": 1.9227547645568848, "Pretrain/Step": 5063, "Pretrain/Step Time": 9.573236741125584} +{"Pretrain/Learning Rate": 2.370149354343797e-05, "Pretrain/Loss": 2.0045785903930664, "Pretrain/Loss (Raw)": 1.9490770101547241, "Pretrain/Step": 5064, "Pretrain/Step Time": 9.569985615089536} +{"Pretrain/Learning Rate": 2.369301428845876e-05, "Pretrain/Loss": 2.003850221633911, "Pretrain/Loss (Raw)": 2.040175199508667, "Pretrain/Step": 5065, "Pretrain/Step Time": 9.572359969839454} +{"Pretrain/Learning Rate": 2.36845351842399e-05, "Pretrain/Loss": 2.004443645477295, "Pretrain/Loss (Raw)": 2.085928440093994, "Pretrain/Step": 5066, "Pretrain/Step Time": 9.569479297846556} +{"Pretrain/Learning Rate": 2.3676056231759448e-05, "Pretrain/Loss": 2.006251811981201, "Pretrain/Loss (Raw)": 2.0967352390289307, "Pretrain/Step": 5067, "Pretrain/Step Time": 9.570654014125466} +{"Pretrain/Learning Rate": 2.366757743199544e-05, "Pretrain/Loss": 2.005707263946533, "Pretrain/Loss (Raw)": 1.894638180732727, "Pretrain/Step": 5068, "Pretrain/Step Time": 9.565935699269176} +{"Pretrain/Learning Rate": 2.36590987859259e-05, "Pretrain/Loss": 2.005553722381592, "Pretrain/Loss (Raw)": 2.0602355003356934, "Pretrain/Step": 5069, "Pretrain/Step Time": 9.566760497167706} +{"Pretrain/Learning Rate": 2.3650620294528848e-05, "Pretrain/Loss": 2.0069124698638916, "Pretrain/Loss (Raw)": 2.1558194160461426, "Pretrain/Step": 5070, "Pretrain/Step Time": 9.567616283893585} +{"Pretrain/Learning Rate": 2.364214195878227e-05, "Pretrain/Loss": 2.0089006423950195, "Pretrain/Loss (Raw)": 2.1188557147979736, "Pretrain/Step": 5071, "Pretrain/Step Time": 9.567682273685932} +{"Pretrain/Learning Rate": 2.3633663779664147e-05, "Pretrain/Loss": 2.0078377723693848, "Pretrain/Loss (Raw)": 1.8953418731689453, "Pretrain/Step": 5072, "Pretrain/Step Time": 9.56642540730536} +{"Pretrain/Learning Rate": 2.362518575815242e-05, "Pretrain/Loss": 2.006603240966797, "Pretrain/Loss (Raw)": 1.8791297674179077, "Pretrain/Step": 5073, "Pretrain/Step Time": 9.570063918828964} +{"Pretrain/Learning Rate": 2.3616707895225032e-05, "Pretrain/Loss": 2.0071704387664795, "Pretrain/Loss (Raw)": 2.2070443630218506, "Pretrain/Step": 5074, "Pretrain/Step Time": 9.569527201354504} +{"Pretrain/Learning Rate": 2.3608230191859906e-05, "Pretrain/Loss": 2.0070712566375732, "Pretrain/Loss (Raw)": 1.8515639305114746, "Pretrain/Step": 5075, "Pretrain/Step Time": 9.566991278901696} +{"Pretrain/Learning Rate": 2.3599752649034933e-05, "Pretrain/Loss": 2.007162570953369, "Pretrain/Loss (Raw)": 1.9893205165863037, "Pretrain/Step": 5076, "Pretrain/Step Time": 9.565451458096504} +{"Pretrain/Learning Rate": 2.3591275267728013e-05, "Pretrain/Loss": 2.007966995239258, "Pretrain/Loss (Raw)": 2.0239927768707275, "Pretrain/Step": 5077, "Pretrain/Step Time": 9.570821236819029} +{"Pretrain/Learning Rate": 2.358279804891698e-05, "Pretrain/Loss": 2.0072479248046875, "Pretrain/Loss (Raw)": 2.080322027206421, "Pretrain/Step": 5078, "Pretrain/Step Time": 9.571574533358216} +{"Pretrain/Learning Rate": 2.35743209935797e-05, "Pretrain/Loss": 2.0076308250427246, "Pretrain/Loss (Raw)": 2.0546607971191406, "Pretrain/Step": 5079, "Pretrain/Step Time": 9.57362269796431} +{"Pretrain/Learning Rate": 2.356584410269399e-05, "Pretrain/Loss": 2.0061020851135254, "Pretrain/Loss (Raw)": 1.9699147939682007, "Pretrain/Step": 5080, "Pretrain/Step Time": 9.574576554819942} +{"Pretrain/Learning Rate": 2.355736737723766e-05, "Pretrain/Loss": 2.007350444793701, "Pretrain/Loss (Raw)": 2.041461229324341, "Pretrain/Step": 5081, "Pretrain/Step Time": 9.573272738605738} +{"Pretrain/Learning Rate": 2.3548890818188497e-05, "Pretrain/Loss": 2.0070972442626953, "Pretrain/Loss (Raw)": 2.0751612186431885, "Pretrain/Step": 5082, "Pretrain/Step Time": 9.57160235568881} +{"Pretrain/Learning Rate": 2.3540414426524275e-05, "Pretrain/Loss": 2.0069832801818848, "Pretrain/Loss (Raw)": 2.098686695098877, "Pretrain/Step": 5083, "Pretrain/Step Time": 9.57120667397976} +{"Pretrain/Learning Rate": 2.353193820322273e-05, "Pretrain/Loss": 2.0069968700408936, "Pretrain/Loss (Raw)": 1.9991406202316284, "Pretrain/Step": 5084, "Pretrain/Step Time": 9.56614106707275} +{"Pretrain/Learning Rate": 2.3523462149261593e-05, "Pretrain/Loss": 2.006479024887085, "Pretrain/Loss (Raw)": 1.9571974277496338, "Pretrain/Step": 5085, "Pretrain/Step Time": 9.566114377230406} +{"Pretrain/Learning Rate": 2.351498626561858e-05, "Pretrain/Loss": 2.0097832679748535, "Pretrain/Loss (Raw)": 2.1417369842529297, "Pretrain/Step": 5086, "Pretrain/Step Time": 9.564791075885296} +{"Pretrain/Learning Rate": 2.350651055327138e-05, "Pretrain/Loss": 2.010885715484619, "Pretrain/Loss (Raw)": 2.067518711090088, "Pretrain/Step": 5087, "Pretrain/Step Time": 9.567251471802592} +{"Pretrain/Learning Rate": 2.349803501319767e-05, "Pretrain/Loss": 2.0094966888427734, "Pretrain/Loss (Raw)": 2.0064144134521484, "Pretrain/Step": 5088, "Pretrain/Step Time": 9.563438806682825} +{"Pretrain/Learning Rate": 2.3489559646375088e-05, "Pretrain/Loss": 2.0082244873046875, "Pretrain/Loss (Raw)": 1.868507981300354, "Pretrain/Step": 5089, "Pretrain/Step Time": 9.566586654633284} +{"Pretrain/Learning Rate": 2.3481084453781267e-05, "Pretrain/Loss": 2.0074119567871094, "Pretrain/Loss (Raw)": 2.0034210681915283, "Pretrain/Step": 5090, "Pretrain/Step Time": 9.565628595650196} +{"Pretrain/Learning Rate": 2.3472609436393825e-05, "Pretrain/Loss": 2.0075507164001465, "Pretrain/Loss (Raw)": 1.9944932460784912, "Pretrain/Step": 5091, "Pretrain/Step Time": 9.56498964317143} +{"Pretrain/Learning Rate": 2.3464134595190344e-05, "Pretrain/Loss": 2.007533073425293, "Pretrain/Loss (Raw)": 1.9261435270309448, "Pretrain/Step": 5092, "Pretrain/Step Time": 9.57033289782703} +{"Pretrain/Learning Rate": 2.345565993114841e-05, "Pretrain/Loss": 2.00718355178833, "Pretrain/Loss (Raw)": 1.9320638179779053, "Pretrain/Step": 5093, "Pretrain/Step Time": 9.569598289206624} +{"Pretrain/Learning Rate": 2.3447185445245546e-05, "Pretrain/Loss": 2.0077595710754395, "Pretrain/Loss (Raw)": 2.159210681915283, "Pretrain/Step": 5094, "Pretrain/Step Time": 9.568922212347388} +{"Pretrain/Learning Rate": 2.3438711138459292e-05, "Pretrain/Loss": 2.0076658725738525, "Pretrain/Loss (Raw)": 1.999817132949829, "Pretrain/Step": 5095, "Pretrain/Step Time": 9.568261913955212} +{"Pretrain/Learning Rate": 2.3430237011767167e-05, "Pretrain/Loss": 2.0069756507873535, "Pretrain/Loss (Raw)": 1.8959020376205444, "Pretrain/Step": 5096, "Pretrain/Step Time": 9.574528669938445} +{"Pretrain/Learning Rate": 2.3421763066146645e-05, "Pretrain/Loss": 2.0090155601501465, "Pretrain/Loss (Raw)": 2.2093634605407715, "Pretrain/Step": 5097, "Pretrain/Step Time": 9.571464084088802} +{"Pretrain/Learning Rate": 2.3413289302575214e-05, "Pretrain/Loss": 2.009112596511841, "Pretrain/Loss (Raw)": 1.9788724184036255, "Pretrain/Step": 5098, "Pretrain/Step Time": 9.569696558639407} +{"Pretrain/Learning Rate": 2.3404815722030292e-05, "Pretrain/Loss": 2.0104284286499023, "Pretrain/Loss (Raw)": 2.0173845291137695, "Pretrain/Step": 5099, "Pretrain/Step Time": 9.571296084672213} +{"Pretrain/Learning Rate": 2.339634232548932e-05, "Pretrain/Loss": 2.0143630504608154, "Pretrain/Loss (Raw)": 2.312669515609741, "Pretrain/Step": 5100, "Pretrain/Step Time": 9.568509915843606} +{"Pretrain/Learning Rate": 2.3387869113929694e-05, "Pretrain/Loss": 2.0161526203155518, "Pretrain/Loss (Raw)": 2.105391263961792, "Pretrain/Step": 5101, "Pretrain/Step Time": 9.563712207600474} +{"Pretrain/Learning Rate": 2.3379396088328797e-05, "Pretrain/Loss": 2.0170507431030273, "Pretrain/Loss (Raw)": 1.9881757497787476, "Pretrain/Step": 5102, "Pretrain/Step Time": 9.563091918826103} +{"Pretrain/Learning Rate": 2.3370923249663994e-05, "Pretrain/Loss": 2.0145816802978516, "Pretrain/Loss (Raw)": 1.839320421218872, "Pretrain/Step": 5103, "Pretrain/Step Time": 9.564254563301802} +{"Pretrain/Learning Rate": 2.336245059891263e-05, "Pretrain/Loss": 2.0137298107147217, "Pretrain/Loss (Raw)": 1.9912474155426025, "Pretrain/Step": 5104, "Pretrain/Step Time": 9.565439581871033} +{"Pretrain/Learning Rate": 2.3353978137052008e-05, "Pretrain/Loss": 2.014177083969116, "Pretrain/Loss (Raw)": 2.0510284900665283, "Pretrain/Step": 5105, "Pretrain/Step Time": 9.565467467531562} +{"Pretrain/Learning Rate": 2.3345505865059424e-05, "Pretrain/Loss": 2.0129568576812744, "Pretrain/Loss (Raw)": 1.852861762046814, "Pretrain/Step": 5106, "Pretrain/Step Time": 9.563363160938025} +{"Pretrain/Learning Rate": 2.3337033783912164e-05, "Pretrain/Loss": 2.0142927169799805, "Pretrain/Loss (Raw)": 1.9453481435775757, "Pretrain/Step": 5107, "Pretrain/Step Time": 9.563312323763967} +{"Pretrain/Learning Rate": 2.3328561894587466e-05, "Pretrain/Loss": 2.0150318145751953, "Pretrain/Loss (Raw)": 2.0755743980407715, "Pretrain/Step": 5108, "Pretrain/Step Time": 9.565951988101006} +{"Pretrain/Learning Rate": 2.3320090198062575e-05, "Pretrain/Loss": 2.0148439407348633, "Pretrain/Loss (Raw)": 2.075897216796875, "Pretrain/Step": 5109, "Pretrain/Step Time": 9.567421663552523} +{"Pretrain/Learning Rate": 2.3311618695314684e-05, "Pretrain/Loss": 2.01560115814209, "Pretrain/Loss (Raw)": 1.9975017309188843, "Pretrain/Step": 5110, "Pretrain/Step Time": 9.56567170470953} +{"Pretrain/Learning Rate": 2.3303147387320983e-05, "Pretrain/Loss": 2.0142881870269775, "Pretrain/Loss (Raw)": 1.8572101593017578, "Pretrain/Step": 5111, "Pretrain/Step Time": 9.566292772069573} +{"Pretrain/Learning Rate": 2.3294676275058632e-05, "Pretrain/Loss": 2.013916015625, "Pretrain/Loss (Raw)": 1.9825546741485596, "Pretrain/Step": 5112, "Pretrain/Step Time": 9.569022800773382} +{"Pretrain/Learning Rate": 2.3286205359504775e-05, "Pretrain/Loss": 2.013096332550049, "Pretrain/Loss (Raw)": 1.942352056503296, "Pretrain/Step": 5113, "Pretrain/Step Time": 9.573936346918344} +{"Pretrain/Learning Rate": 2.3277734641636536e-05, "Pretrain/Loss": 2.0128214359283447, "Pretrain/Loss (Raw)": 1.994035243988037, "Pretrain/Step": 5114, "Pretrain/Step Time": 9.5732537265867} +{"Pretrain/Learning Rate": 2.3269264122430992e-05, "Pretrain/Loss": 2.0127010345458984, "Pretrain/Loss (Raw)": 2.0259058475494385, "Pretrain/Step": 5115, "Pretrain/Step Time": 9.570393797010183} +{"Pretrain/Learning Rate": 2.3260793802865224e-05, "Pretrain/Loss": 2.0124406814575195, "Pretrain/Loss (Raw)": 1.9745047092437744, "Pretrain/Step": 5116, "Pretrain/Step Time": 9.57198734767735} +{"Pretrain/Learning Rate": 2.3252323683916283e-05, "Pretrain/Loss": 2.0135560035705566, "Pretrain/Loss (Raw)": 2.043102741241455, "Pretrain/Step": 5117, "Pretrain/Step Time": 9.568974295631051} +{"Pretrain/Learning Rate": 2.3243853766561186e-05, "Pretrain/Loss": 2.0107884407043457, "Pretrain/Loss (Raw)": 1.8773716688156128, "Pretrain/Step": 5118, "Pretrain/Step Time": 9.568803614005446} +{"Pretrain/Learning Rate": 2.323538405177695e-05, "Pretrain/Loss": 2.0141289234161377, "Pretrain/Loss (Raw)": 2.029324531555176, "Pretrain/Step": 5119, "Pretrain/Step Time": 9.570949114859104} +{"Pretrain/Learning Rate": 2.3226914540540534e-05, "Pretrain/Loss": 2.0130951404571533, "Pretrain/Loss (Raw)": 1.9687542915344238, "Pretrain/Step": 5120, "Pretrain/Step Time": 9.570923388004303} +{"Pretrain/Learning Rate": 2.3218445233828904e-05, "Pretrain/Loss": 2.0115373134613037, "Pretrain/Loss (Raw)": 1.9232195615768433, "Pretrain/Step": 5121, "Pretrain/Step Time": 9.568466385826468} +{"Pretrain/Learning Rate": 2.3209976132618987e-05, "Pretrain/Loss": 2.0129752159118652, "Pretrain/Loss (Raw)": 2.1204373836517334, "Pretrain/Step": 5122, "Pretrain/Step Time": 9.565460044890642} +{"Pretrain/Learning Rate": 2.3201507237887696e-05, "Pretrain/Loss": 2.0147433280944824, "Pretrain/Loss (Raw)": 2.2645304203033447, "Pretrain/Step": 5123, "Pretrain/Step Time": 9.568762050941586} +{"Pretrain/Learning Rate": 2.3193038550611918e-05, "Pretrain/Loss": 2.0144927501678467, "Pretrain/Loss (Raw)": 1.9459103345870972, "Pretrain/Step": 5124, "Pretrain/Step Time": 9.566199587658048} +{"Pretrain/Learning Rate": 2.3184570071768508e-05, "Pretrain/Loss": 2.0140788555145264, "Pretrain/Loss (Raw)": 2.09771990776062, "Pretrain/Step": 5125, "Pretrain/Step Time": 9.5687908641994} +{"Pretrain/Learning Rate": 2.3176101802334303e-05, "Pretrain/Loss": 2.013652801513672, "Pretrain/Loss (Raw)": 1.9772753715515137, "Pretrain/Step": 5126, "Pretrain/Step Time": 9.566500233486295} +{"Pretrain/Learning Rate": 2.3167633743286104e-05, "Pretrain/Loss": 2.0137574672698975, "Pretrain/Loss (Raw)": 1.8929334878921509, "Pretrain/Step": 5127, "Pretrain/Step Time": 9.569630615413189} +{"Pretrain/Learning Rate": 2.3159165895600716e-05, "Pretrain/Loss": 2.014303684234619, "Pretrain/Loss (Raw)": 2.0711705684661865, "Pretrain/Step": 5128, "Pretrain/Step Time": 9.574445270001888} +{"Pretrain/Learning Rate": 2.315069826025489e-05, "Pretrain/Loss": 2.0166635513305664, "Pretrain/Loss (Raw)": 2.1852102279663086, "Pretrain/Step": 5129, "Pretrain/Step Time": 8.470236796885729} +{"Pretrain/Learning Rate": 2.3142230838225382e-05, "Pretrain/Loss": 2.0162720680236816, "Pretrain/Loss (Raw)": 1.9512616395950317, "Pretrain/Step": 5130, "Pretrain/Step Time": 8.46663923561573} +{"Pretrain/Learning Rate": 2.3133763630488884e-05, "Pretrain/Loss": 2.0156476497650146, "Pretrain/Loss (Raw)": 2.0357370376586914, "Pretrain/Step": 5131, "Pretrain/Step Time": 8.467994069680572} +{"Pretrain/Learning Rate": 2.3125296638022095e-05, "Pretrain/Loss": 2.0155272483825684, "Pretrain/Loss (Raw)": 2.028348684310913, "Pretrain/Step": 5132, "Pretrain/Step Time": 8.465228298678994} +{"Pretrain/Learning Rate": 2.3116829861801686e-05, "Pretrain/Loss": 2.0163168907165527, "Pretrain/Loss (Raw)": 2.2358219623565674, "Pretrain/Step": 5133, "Pretrain/Step Time": 8.465735662728548} +{"Pretrain/Learning Rate": 2.3108363302804283e-05, "Pretrain/Loss": 2.0145020484924316, "Pretrain/Loss (Raw)": 1.9148039817810059, "Pretrain/Step": 5134, "Pretrain/Step Time": 8.466744109988213} +{"Pretrain/Learning Rate": 2.309989696200652e-05, "Pretrain/Loss": 2.014901876449585, "Pretrain/Loss (Raw)": 2.0280771255493164, "Pretrain/Step": 5135, "Pretrain/Step Time": 8.463893916457891} +{"Pretrain/Learning Rate": 2.3091430840384964e-05, "Pretrain/Loss": 2.0145840644836426, "Pretrain/Loss (Raw)": 1.9314651489257812, "Pretrain/Step": 5136, "Pretrain/Step Time": 8.467018369585276} +{"Pretrain/Learning Rate": 2.3082964938916192e-05, "Pretrain/Loss": 2.0154197216033936, "Pretrain/Loss (Raw)": 1.9677642583847046, "Pretrain/Step": 5137, "Pretrain/Step Time": 8.466708132997155} +{"Pretrain/Learning Rate": 2.307449925857674e-05, "Pretrain/Loss": 2.0169525146484375, "Pretrain/Loss (Raw)": 2.244083881378174, "Pretrain/Step": 5138, "Pretrain/Step Time": 8.463883250951767} +{"Pretrain/Learning Rate": 2.3066033800343122e-05, "Pretrain/Loss": 2.0156478881835938, "Pretrain/Loss (Raw)": 1.987383246421814, "Pretrain/Step": 5139, "Pretrain/Step Time": 8.468252575024962} +{"Pretrain/Learning Rate": 2.3057568565191835e-05, "Pretrain/Loss": 2.0153772830963135, "Pretrain/Loss (Raw)": 1.9995753765106201, "Pretrain/Step": 5140, "Pretrain/Step Time": 8.468743843957782} +{"Pretrain/Learning Rate": 2.304910355409932e-05, "Pretrain/Loss": 2.0146312713623047, "Pretrain/Loss (Raw)": 2.014780044555664, "Pretrain/Step": 5141, "Pretrain/Step Time": 8.466703373938799} +{"Pretrain/Learning Rate": 2.3040638768042027e-05, "Pretrain/Loss": 2.0156023502349854, "Pretrain/Loss (Raw)": 2.1189403533935547, "Pretrain/Step": 5142, "Pretrain/Step Time": 8.467567522078753} +{"Pretrain/Learning Rate": 2.3032174207996362e-05, "Pretrain/Loss": 2.0166687965393066, "Pretrain/Loss (Raw)": 2.1029715538024902, "Pretrain/Step": 5143, "Pretrain/Step Time": 8.464676704257727} +{"Pretrain/Learning Rate": 2.302370987493871e-05, "Pretrain/Loss": 2.015554904937744, "Pretrain/Loss (Raw)": 1.8377220630645752, "Pretrain/Step": 5144, "Pretrain/Step Time": 8.464727466925979} +{"Pretrain/Learning Rate": 2.3015245769845433e-05, "Pretrain/Loss": 2.0150766372680664, "Pretrain/Loss (Raw)": 1.968490719795227, "Pretrain/Step": 5145, "Pretrain/Step Time": 8.467117108404636} +{"Pretrain/Learning Rate": 2.3006781893692864e-05, "Pretrain/Loss": 2.012908935546875, "Pretrain/Loss (Raw)": 1.8339277505874634, "Pretrain/Step": 5146, "Pretrain/Step Time": 8.46740803308785} +{"Pretrain/Learning Rate": 2.2998318247457296e-05, "Pretrain/Loss": 2.0112924575805664, "Pretrain/Loss (Raw)": 1.9887967109680176, "Pretrain/Step": 5147, "Pretrain/Step Time": 8.466513812541962} +{"Pretrain/Learning Rate": 2.2989854832115012e-05, "Pretrain/Loss": 2.009913921356201, "Pretrain/Loss (Raw)": 1.6987015008926392, "Pretrain/Step": 5148, "Pretrain/Step Time": 8.464075582101941} +{"Pretrain/Learning Rate": 2.2981391648642275e-05, "Pretrain/Loss": 2.0075831413269043, "Pretrain/Loss (Raw)": 1.8381826877593994, "Pretrain/Step": 5149, "Pretrain/Step Time": 8.46485261619091} +{"Pretrain/Learning Rate": 2.2972928698015296e-05, "Pretrain/Loss": 2.0058529376983643, "Pretrain/Loss (Raw)": 1.870342493057251, "Pretrain/Step": 5150, "Pretrain/Step Time": 8.465402279049158} +{"Pretrain/Learning Rate": 2.2964465981210282e-05, "Pretrain/Loss": 2.005675792694092, "Pretrain/Loss (Raw)": 1.8632409572601318, "Pretrain/Step": 5151, "Pretrain/Step Time": 8.465147754177451} +{"Pretrain/Learning Rate": 2.2956003499203404e-05, "Pretrain/Loss": 2.0074448585510254, "Pretrain/Loss (Raw)": 2.1138761043548584, "Pretrain/Step": 5152, "Pretrain/Step Time": 8.461408471688628} +{"Pretrain/Learning Rate": 2.2947541252970797e-05, "Pretrain/Loss": 2.008967638015747, "Pretrain/Loss (Raw)": 2.197460651397705, "Pretrain/Step": 5153, "Pretrain/Step Time": 8.462625954300165} +{"Pretrain/Learning Rate": 2.2939079243488587e-05, "Pretrain/Loss": 2.0115742683410645, "Pretrain/Loss (Raw)": 2.1459715366363525, "Pretrain/Step": 5154, "Pretrain/Step Time": 8.462933007627726} +{"Pretrain/Learning Rate": 2.293061747173286e-05, "Pretrain/Loss": 2.0118393898010254, "Pretrain/Loss (Raw)": 2.000803232192993, "Pretrain/Step": 5155, "Pretrain/Step Time": 8.463989017531276} +{"Pretrain/Learning Rate": 2.2922155938679692e-05, "Pretrain/Loss": 2.0117950439453125, "Pretrain/Loss (Raw)": 2.1348869800567627, "Pretrain/Step": 5156, "Pretrain/Step Time": 8.467199297621846} +{"Pretrain/Learning Rate": 2.29136946453051e-05, "Pretrain/Loss": 2.012556791305542, "Pretrain/Loss (Raw)": 2.1788136959075928, "Pretrain/Step": 5157, "Pretrain/Step Time": 8.46879286505282} +{"Pretrain/Learning Rate": 2.290523359258509e-05, "Pretrain/Loss": 2.0145702362060547, "Pretrain/Loss (Raw)": 2.197255849838257, "Pretrain/Step": 5158, "Pretrain/Step Time": 8.469241607934237} +{"Pretrain/Learning Rate": 2.289677278149566e-05, "Pretrain/Loss": 2.0134735107421875, "Pretrain/Loss (Raw)": 1.9703842401504517, "Pretrain/Step": 5159, "Pretrain/Step Time": 8.468635722994804} +{"Pretrain/Learning Rate": 2.2888312213012742e-05, "Pretrain/Loss": 2.012320041656494, "Pretrain/Loss (Raw)": 1.9170284271240234, "Pretrain/Step": 5160, "Pretrain/Step Time": 8.471325354650617} +{"Pretrain/Learning Rate": 2.287985188811228e-05, "Pretrain/Loss": 2.0111653804779053, "Pretrain/Loss (Raw)": 1.9352620840072632, "Pretrain/Step": 5161, "Pretrain/Step Time": 8.471543215215206} +{"Pretrain/Learning Rate": 2.2871391807770146e-05, "Pretrain/Loss": 2.0102896690368652, "Pretrain/Loss (Raw)": 1.9605915546417236, "Pretrain/Step": 5162, "Pretrain/Step Time": 8.475205222144723} +{"Pretrain/Learning Rate": 2.286293197296222e-05, "Pretrain/Loss": 2.0085158348083496, "Pretrain/Loss (Raw)": 1.9404857158660889, "Pretrain/Step": 5163, "Pretrain/Step Time": 8.473855379968882} +{"Pretrain/Learning Rate": 2.285447238466434e-05, "Pretrain/Loss": 2.009061813354492, "Pretrain/Loss (Raw)": 2.0725913047790527, "Pretrain/Step": 5164, "Pretrain/Step Time": 8.475426571443677} +{"Pretrain/Learning Rate": 2.2846013043852315e-05, "Pretrain/Loss": 2.008679151535034, "Pretrain/Loss (Raw)": 1.976287841796875, "Pretrain/Step": 5165, "Pretrain/Step Time": 8.477505071088672} +{"Pretrain/Learning Rate": 2.2837553951501933e-05, "Pretrain/Loss": 2.0084729194641113, "Pretrain/Loss (Raw)": 2.1133010387420654, "Pretrain/Step": 5166, "Pretrain/Step Time": 8.474660884588957} +{"Pretrain/Learning Rate": 2.2829095108588947e-05, "Pretrain/Loss": 2.0098612308502197, "Pretrain/Loss (Raw)": 1.912652611732483, "Pretrain/Step": 5167, "Pretrain/Step Time": 8.471442630514503} +{"Pretrain/Learning Rate": 2.2820636516089075e-05, "Pretrain/Loss": 2.0108344554901123, "Pretrain/Loss (Raw)": 2.1631226539611816, "Pretrain/Step": 5168, "Pretrain/Step Time": 8.470475332811475} +{"Pretrain/Learning Rate": 2.2812178174978008e-05, "Pretrain/Loss": 2.010448694229126, "Pretrain/Loss (Raw)": 1.9975104331970215, "Pretrain/Step": 5169, "Pretrain/Step Time": 8.472953911870718} +{"Pretrain/Learning Rate": 2.280372008623142e-05, "Pretrain/Loss": 2.0082292556762695, "Pretrain/Loss (Raw)": 1.7913352251052856, "Pretrain/Step": 5170, "Pretrain/Step Time": 8.473081812262535} +{"Pretrain/Learning Rate": 2.279526225082495e-05, "Pretrain/Loss": 2.0082640647888184, "Pretrain/Loss (Raw)": 2.0552265644073486, "Pretrain/Step": 5171, "Pretrain/Step Time": 8.47718502394855} +{"Pretrain/Learning Rate": 2.2786804669734217e-05, "Pretrain/Loss": 2.008152484893799, "Pretrain/Loss (Raw)": 2.162898540496826, "Pretrain/Step": 5172, "Pretrain/Step Time": 8.47997467033565} +{"Pretrain/Learning Rate": 2.277834734393477e-05, "Pretrain/Loss": 2.0074400901794434, "Pretrain/Loss (Raw)": 1.8987897634506226, "Pretrain/Step": 5173, "Pretrain/Step Time": 8.476893171668053} +{"Pretrain/Learning Rate": 2.2769890274402184e-05, "Pretrain/Loss": 2.006338119506836, "Pretrain/Loss (Raw)": 2.03340220451355, "Pretrain/Step": 5174, "Pretrain/Step Time": 8.475888645276427} +{"Pretrain/Learning Rate": 2.2761433462111973e-05, "Pretrain/Loss": 2.0082077980041504, "Pretrain/Loss (Raw)": 1.9691892862319946, "Pretrain/Step": 5175, "Pretrain/Step Time": 8.478823190554976} +{"Pretrain/Learning Rate": 2.275297690803962e-05, "Pretrain/Loss": 2.012974739074707, "Pretrain/Loss (Raw)": 2.167158365249634, "Pretrain/Step": 5176, "Pretrain/Step Time": 8.477072712033987} +{"Pretrain/Learning Rate": 2.27445206131606e-05, "Pretrain/Loss": 2.0122976303100586, "Pretrain/Loss (Raw)": 1.9420281648635864, "Pretrain/Step": 5177, "Pretrain/Step Time": 8.477702593430877} +{"Pretrain/Learning Rate": 2.273606457845033e-05, "Pretrain/Loss": 2.011016368865967, "Pretrain/Loss (Raw)": 1.9194259643554688, "Pretrain/Step": 5178, "Pretrain/Step Time": 8.477478137239814} +{"Pretrain/Learning Rate": 2.272760880488421e-05, "Pretrain/Loss": 2.0120949745178223, "Pretrain/Loss (Raw)": 2.018603563308716, "Pretrain/Step": 5179, "Pretrain/Step Time": 8.479508500546217} +{"Pretrain/Learning Rate": 2.2719153293437613e-05, "Pretrain/Loss": 2.0105397701263428, "Pretrain/Loss (Raw)": 2.0390923023223877, "Pretrain/Step": 5180, "Pretrain/Step Time": 8.479745026677847} +{"Pretrain/Learning Rate": 2.2710698045085887e-05, "Pretrain/Loss": 2.009610176086426, "Pretrain/Loss (Raw)": 1.7840425968170166, "Pretrain/Step": 5181, "Pretrain/Step Time": 8.481480468064547} +{"Pretrain/Learning Rate": 2.270224306080435e-05, "Pretrain/Loss": 2.0094408988952637, "Pretrain/Loss (Raw)": 1.8450701236724854, "Pretrain/Step": 5182, "Pretrain/Step Time": 8.4805988650769} +{"Pretrain/Learning Rate": 2.2693788341568252e-05, "Pretrain/Loss": 2.008951425552368, "Pretrain/Loss (Raw)": 2.176880121231079, "Pretrain/Step": 5183, "Pretrain/Step Time": 8.4762604534626} +{"Pretrain/Learning Rate": 2.2685333888352866e-05, "Pretrain/Loss": 2.007932662963867, "Pretrain/Loss (Raw)": 1.9866331815719604, "Pretrain/Step": 5184, "Pretrain/Step Time": 8.47474006563425} +{"Pretrain/Learning Rate": 2.26768797021334e-05, "Pretrain/Loss": 2.0102715492248535, "Pretrain/Loss (Raw)": 2.0841362476348877, "Pretrain/Step": 5185, "Pretrain/Step Time": 8.473400855436921} +{"Pretrain/Learning Rate": 2.2668425783885038e-05, "Pretrain/Loss": 2.0119361877441406, "Pretrain/Loss (Raw)": 2.04119873046875, "Pretrain/Step": 5186, "Pretrain/Step Time": 8.475672159343958} +{"Pretrain/Learning Rate": 2.2659972134582947e-05, "Pretrain/Loss": 2.0102620124816895, "Pretrain/Loss (Raw)": 1.9787598848342896, "Pretrain/Step": 5187, "Pretrain/Step Time": 8.479212237522006} +{"Pretrain/Learning Rate": 2.2651518755202257e-05, "Pretrain/Loss": 2.012183904647827, "Pretrain/Loss (Raw)": 2.1097047328948975, "Pretrain/Step": 5188, "Pretrain/Step Time": 8.480018638074398} +{"Pretrain/Learning Rate": 2.2643065646718042e-05, "Pretrain/Loss": 2.010704517364502, "Pretrain/Loss (Raw)": 1.8922145366668701, "Pretrain/Step": 5189, "Pretrain/Step Time": 8.478241883218288} +{"Pretrain/Learning Rate": 2.2634612810105378e-05, "Pretrain/Loss": 2.0088155269622803, "Pretrain/Loss (Raw)": 1.7873414754867554, "Pretrain/Step": 5190, "Pretrain/Step Time": 8.481055295094848} +{"Pretrain/Learning Rate": 2.26261602463393e-05, "Pretrain/Loss": 2.009566307067871, "Pretrain/Loss (Raw)": 2.0188653469085693, "Pretrain/Step": 5191, "Pretrain/Step Time": 8.480722548440099} +{"Pretrain/Learning Rate": 2.26177079563948e-05, "Pretrain/Loss": 2.0100769996643066, "Pretrain/Loss (Raw)": 2.014432668685913, "Pretrain/Step": 5192, "Pretrain/Step Time": 8.482842741534114} +{"Pretrain/Learning Rate": 2.260925594124685e-05, "Pretrain/Loss": 2.009272813796997, "Pretrain/Loss (Raw)": 1.9372457265853882, "Pretrain/Step": 5193, "Pretrain/Step Time": 8.481835445389152} +{"Pretrain/Learning Rate": 2.260080420187039e-05, "Pretrain/Loss": 2.0097365379333496, "Pretrain/Loss (Raw)": 2.145259141921997, "Pretrain/Step": 5194, "Pretrain/Step Time": 8.483962535858154} +{"Pretrain/Learning Rate": 2.259235273924032e-05, "Pretrain/Loss": 2.0088205337524414, "Pretrain/Loss (Raw)": 1.9795200824737549, "Pretrain/Step": 5195, "Pretrain/Step Time": 8.482372967526317} +{"Pretrain/Learning Rate": 2.258390155433151e-05, "Pretrain/Loss": 2.009902238845825, "Pretrain/Loss (Raw)": 2.0331039428710938, "Pretrain/Step": 5196, "Pretrain/Step Time": 8.481702046468854} +{"Pretrain/Learning Rate": 2.257545064811881e-05, "Pretrain/Loss": 2.010192394256592, "Pretrain/Loss (Raw)": 2.097350835800171, "Pretrain/Step": 5197, "Pretrain/Step Time": 8.483716152608395} +{"Pretrain/Learning Rate": 2.2567000021577035e-05, "Pretrain/Loss": 2.0109386444091797, "Pretrain/Loss (Raw)": 2.251340866088867, "Pretrain/Step": 5198, "Pretrain/Step Time": 8.481341134756804} +{"Pretrain/Learning Rate": 2.255854967568094e-05, "Pretrain/Loss": 2.010589599609375, "Pretrain/Loss (Raw)": 2.0741970539093018, "Pretrain/Step": 5199, "Pretrain/Step Time": 8.47764328867197} +{"Pretrain/Learning Rate": 2.2550099611405285e-05, "Pretrain/Loss": 2.0095322132110596, "Pretrain/Loss (Raw)": 1.7599865198135376, "Pretrain/Step": 5200, "Pretrain/Step Time": 8.480940928682685} +{"Pretrain/Learning Rate": 2.2541649829724783e-05, "Pretrain/Loss": 2.0085530281066895, "Pretrain/Loss (Raw)": 1.7538080215454102, "Pretrain/Step": 5201, "Pretrain/Step Time": 8.47503942064941} +{"Pretrain/Learning Rate": 2.2533200331614103e-05, "Pretrain/Loss": 2.0071868896484375, "Pretrain/Loss (Raw)": 2.032148838043213, "Pretrain/Step": 5202, "Pretrain/Step Time": 8.474559476599097} +{"Pretrain/Learning Rate": 2.2524751118047903e-05, "Pretrain/Loss": 2.0078094005584717, "Pretrain/Loss (Raw)": 1.931252360343933, "Pretrain/Step": 5203, "Pretrain/Step Time": 8.476736037060618} +{"Pretrain/Learning Rate": 2.2516302190000795e-05, "Pretrain/Loss": 2.0077033042907715, "Pretrain/Loss (Raw)": 1.9757479429244995, "Pretrain/Step": 5204, "Pretrain/Step Time": 8.48227846994996} +{"Pretrain/Learning Rate": 2.250785354844735e-05, "Pretrain/Loss": 2.0061440467834473, "Pretrain/Loss (Raw)": 1.8244065046310425, "Pretrain/Step": 5205, "Pretrain/Step Time": 8.477393291890621} +{"Pretrain/Learning Rate": 2.2499405194362122e-05, "Pretrain/Loss": 2.0041279792785645, "Pretrain/Loss (Raw)": 1.822274923324585, "Pretrain/Step": 5206, "Pretrain/Step Time": 8.479638207703829} +{"Pretrain/Learning Rate": 2.2490957128719624e-05, "Pretrain/Loss": 2.003903388977051, "Pretrain/Loss (Raw)": 2.0259315967559814, "Pretrain/Step": 5207, "Pretrain/Step Time": 8.477061085402966} +{"Pretrain/Learning Rate": 2.2482509352494348e-05, "Pretrain/Loss": 2.0044450759887695, "Pretrain/Loss (Raw)": 2.0392038822174072, "Pretrain/Step": 5208, "Pretrain/Step Time": 8.477545456960797} +{"Pretrain/Learning Rate": 2.2474061866660732e-05, "Pretrain/Loss": 2.005272388458252, "Pretrain/Loss (Raw)": 2.147378444671631, "Pretrain/Step": 5209, "Pretrain/Step Time": 8.481458703055978} +{"Pretrain/Learning Rate": 2.2465614672193193e-05, "Pretrain/Loss": 2.0044965744018555, "Pretrain/Loss (Raw)": 1.9758260250091553, "Pretrain/Step": 5210, "Pretrain/Step Time": 8.480178071185946} +{"Pretrain/Learning Rate": 2.2457167770066105e-05, "Pretrain/Loss": 2.004859447479248, "Pretrain/Loss (Raw)": 2.1451783180236816, "Pretrain/Step": 5211, "Pretrain/Step Time": 8.480462031438947} +{"Pretrain/Learning Rate": 2.2448721161253818e-05, "Pretrain/Loss": 2.0044708251953125, "Pretrain/Loss (Raw)": 1.9493945837020874, "Pretrain/Step": 5212, "Pretrain/Step Time": 8.481697238981724} +{"Pretrain/Learning Rate": 2.2440274846730653e-05, "Pretrain/Loss": 2.0036211013793945, "Pretrain/Loss (Raw)": 1.848412036895752, "Pretrain/Step": 5213, "Pretrain/Step Time": 8.48159433528781} +{"Pretrain/Learning Rate": 2.2431828827470895e-05, "Pretrain/Loss": 2.001283645629883, "Pretrain/Loss (Raw)": 1.8425562381744385, "Pretrain/Step": 5214, "Pretrain/Step Time": 8.480469638481736} +{"Pretrain/Learning Rate": 2.2423383104448767e-05, "Pretrain/Loss": 1.999918818473816, "Pretrain/Loss (Raw)": 1.8928223848342896, "Pretrain/Step": 5215, "Pretrain/Step Time": 8.479233976453543} +{"Pretrain/Learning Rate": 2.2414937678638493e-05, "Pretrain/Loss": 1.999742865562439, "Pretrain/Loss (Raw)": 1.9838736057281494, "Pretrain/Step": 5216, "Pretrain/Step Time": 8.478921992704272} +{"Pretrain/Learning Rate": 2.2406492551014252e-05, "Pretrain/Loss": 1.9997150897979736, "Pretrain/Loss (Raw)": 1.8649603128433228, "Pretrain/Step": 5217, "Pretrain/Step Time": 8.477956600487232} +{"Pretrain/Learning Rate": 2.239804772255018e-05, "Pretrain/Loss": 1.9990860223770142, "Pretrain/Loss (Raw)": 1.9229097366333008, "Pretrain/Step": 5218, "Pretrain/Step Time": 8.477883167564869} +{"Pretrain/Learning Rate": 2.23896031942204e-05, "Pretrain/Loss": 1.9983140230178833, "Pretrain/Loss (Raw)": 1.8956584930419922, "Pretrain/Step": 5219, "Pretrain/Step Time": 8.480282668024302} +{"Pretrain/Learning Rate": 2.2381158966998966e-05, "Pretrain/Loss": 1.9979807138442993, "Pretrain/Loss (Raw)": 1.8834915161132812, "Pretrain/Step": 5220, "Pretrain/Step Time": 8.473947113379836} +{"Pretrain/Learning Rate": 2.2372715041859922e-05, "Pretrain/Loss": 1.9997742176055908, "Pretrain/Loss (Raw)": 2.1616222858428955, "Pretrain/Step": 5221, "Pretrain/Step Time": 8.47853147611022} +{"Pretrain/Learning Rate": 2.2364271419777273e-05, "Pretrain/Loss": 1.9983829259872437, "Pretrain/Loss (Raw)": 1.9811331033706665, "Pretrain/Step": 5222, "Pretrain/Step Time": 8.476880254223943} +{"Pretrain/Learning Rate": 2.2355828101724995e-05, "Pretrain/Loss": 1.9987797737121582, "Pretrain/Loss (Raw)": 2.050621509552002, "Pretrain/Step": 5223, "Pretrain/Step Time": 8.47969657368958} +{"Pretrain/Learning Rate": 2.2347385088677015e-05, "Pretrain/Loss": 1.9984424114227295, "Pretrain/Loss (Raw)": 1.852709412574768, "Pretrain/Step": 5224, "Pretrain/Step Time": 8.47572011500597} +{"Pretrain/Learning Rate": 2.233894238160724e-05, "Pretrain/Loss": 1.9980597496032715, "Pretrain/Loss (Raw)": 2.160383462905884, "Pretrain/Step": 5225, "Pretrain/Step Time": 8.474694637581706} +{"Pretrain/Learning Rate": 2.2330499981489524e-05, "Pretrain/Loss": 1.998573899269104, "Pretrain/Loss (Raw)": 2.044691801071167, "Pretrain/Step": 5226, "Pretrain/Step Time": 8.475727956742048} +{"Pretrain/Learning Rate": 2.2322057889297686e-05, "Pretrain/Loss": 2.0001935958862305, "Pretrain/Loss (Raw)": 2.224717378616333, "Pretrain/Step": 5227, "Pretrain/Step Time": 8.472809026017785} +{"Pretrain/Learning Rate": 2.2313616106005533e-05, "Pretrain/Loss": 1.9978034496307373, "Pretrain/Loss (Raw)": 2.0067074298858643, "Pretrain/Step": 5228, "Pretrain/Step Time": 8.47392606548965} +{"Pretrain/Learning Rate": 2.230517463258682e-05, "Pretrain/Loss": 1.9974397420883179, "Pretrain/Loss (Raw)": 2.058858633041382, "Pretrain/Step": 5229, "Pretrain/Step Time": 8.474683471024036} +{"Pretrain/Learning Rate": 2.2296733470015275e-05, "Pretrain/Loss": 1.99832284450531, "Pretrain/Loss (Raw)": 2.1012122631073, "Pretrain/Step": 5230, "Pretrain/Step Time": 8.473964428529143} +{"Pretrain/Learning Rate": 2.2288292619264564e-05, "Pretrain/Loss": 2.0006003379821777, "Pretrain/Loss (Raw)": 2.1308226585388184, "Pretrain/Step": 5231, "Pretrain/Step Time": 8.473334519192576} +{"Pretrain/Learning Rate": 2.2279852081308345e-05, "Pretrain/Loss": 2.000303268432617, "Pretrain/Loss (Raw)": 1.953234314918518, "Pretrain/Step": 5232, "Pretrain/Step Time": 8.472208693623543} +{"Pretrain/Learning Rate": 2.227141185712024e-05, "Pretrain/Loss": 2.0008511543273926, "Pretrain/Loss (Raw)": 2.1211297512054443, "Pretrain/Step": 5233, "Pretrain/Step Time": 8.47308292798698} +{"Pretrain/Learning Rate": 2.226297194767381e-05, "Pretrain/Loss": 2.0002803802490234, "Pretrain/Loss (Raw)": 1.7798336744308472, "Pretrain/Step": 5234, "Pretrain/Step Time": 8.47124346345663} +{"Pretrain/Learning Rate": 2.2254532353942613e-05, "Pretrain/Loss": 2.0015859603881836, "Pretrain/Loss (Raw)": 2.1124374866485596, "Pretrain/Step": 5235, "Pretrain/Step Time": 8.46965816244483} +{"Pretrain/Learning Rate": 2.2246093076900144e-05, "Pretrain/Loss": 2.0038180351257324, "Pretrain/Loss (Raw)": 2.361290454864502, "Pretrain/Step": 5236, "Pretrain/Step Time": 8.467703284695745} +{"Pretrain/Learning Rate": 2.223765411751986e-05, "Pretrain/Loss": 2.003340482711792, "Pretrain/Loss (Raw)": 2.014777421951294, "Pretrain/Step": 5237, "Pretrain/Step Time": 8.46719903498888} +{"Pretrain/Learning Rate": 2.222921547677521e-05, "Pretrain/Loss": 2.00374436378479, "Pretrain/Loss (Raw)": 2.049207925796509, "Pretrain/Step": 5238, "Pretrain/Step Time": 8.46898383833468} +{"Pretrain/Learning Rate": 2.2220777155639576e-05, "Pretrain/Loss": 2.0055384635925293, "Pretrain/Loss (Raw)": 2.0868260860443115, "Pretrain/Step": 5239, "Pretrain/Step Time": 8.468241076916456} +{"Pretrain/Learning Rate": 2.2212339155086333e-05, "Pretrain/Loss": 2.005014181137085, "Pretrain/Loss (Raw)": 1.9154443740844727, "Pretrain/Step": 5240, "Pretrain/Step Time": 8.468455554917455} +{"Pretrain/Learning Rate": 2.220390147608878e-05, "Pretrain/Loss": 2.006229877471924, "Pretrain/Loss (Raw)": 2.0979676246643066, "Pretrain/Step": 5241, "Pretrain/Step Time": 8.463095037266612} +{"Pretrain/Learning Rate": 2.2195464119620208e-05, "Pretrain/Loss": 2.0079593658447266, "Pretrain/Loss (Raw)": 2.215451240539551, "Pretrain/Step": 5242, "Pretrain/Step Time": 8.464034901931882} +{"Pretrain/Learning Rate": 2.2187027086653866e-05, "Pretrain/Loss": 2.0080113410949707, "Pretrain/Loss (Raw)": 2.0325214862823486, "Pretrain/Step": 5243, "Pretrain/Step Time": 8.464363498613238} +{"Pretrain/Learning Rate": 2.217859037816296e-05, "Pretrain/Loss": 2.0092387199401855, "Pretrain/Loss (Raw)": 2.1316277980804443, "Pretrain/Step": 5244, "Pretrain/Step Time": 8.462227148935199} +{"Pretrain/Learning Rate": 2.217015399512066e-05, "Pretrain/Loss": 2.0082473754882812, "Pretrain/Loss (Raw)": 1.916211485862732, "Pretrain/Step": 5245, "Pretrain/Step Time": 8.464763790369034} +{"Pretrain/Learning Rate": 2.2161717938500113e-05, "Pretrain/Loss": 2.010129928588867, "Pretrain/Loss (Raw)": 2.118359088897705, "Pretrain/Step": 5246, "Pretrain/Step Time": 8.463872073218226} +{"Pretrain/Learning Rate": 2.2153282209274395e-05, "Pretrain/Loss": 2.0112669467926025, "Pretrain/Loss (Raw)": 2.1748270988464355, "Pretrain/Step": 5247, "Pretrain/Step Time": 8.458868322893977} +{"Pretrain/Learning Rate": 2.2144846808416574e-05, "Pretrain/Loss": 2.011368751525879, "Pretrain/Loss (Raw)": 1.9817829132080078, "Pretrain/Step": 5248, "Pretrain/Step Time": 8.459281288087368} +{"Pretrain/Learning Rate": 2.2136411736899667e-05, "Pretrain/Loss": 2.011993408203125, "Pretrain/Loss (Raw)": 2.0031960010528564, "Pretrain/Step": 5249, "Pretrain/Step Time": 8.456909392029047} +{"Pretrain/Learning Rate": 2.2127976995696665e-05, "Pretrain/Loss": 2.0114057064056396, "Pretrain/Loss (Raw)": 2.045206308364868, "Pretrain/Step": 5250, "Pretrain/Step Time": 8.46373433060944} +{"Pretrain/Learning Rate": 2.211954258578051e-05, "Pretrain/Loss": 2.0095114707946777, "Pretrain/Loss (Raw)": 2.022059679031372, "Pretrain/Step": 5251, "Pretrain/Step Time": 8.463093975558877} +{"Pretrain/Learning Rate": 2.2111108508124105e-05, "Pretrain/Loss": 2.009873390197754, "Pretrain/Loss (Raw)": 1.9922314882278442, "Pretrain/Step": 5252, "Pretrain/Step Time": 8.465444646775723} +{"Pretrain/Learning Rate": 2.2102674763700314e-05, "Pretrain/Loss": 2.009507179260254, "Pretrain/Loss (Raw)": 2.050840139389038, "Pretrain/Step": 5253, "Pretrain/Step Time": 8.459990818053484} +{"Pretrain/Learning Rate": 2.209424135348197e-05, "Pretrain/Loss": 2.0106983184814453, "Pretrain/Loss (Raw)": 2.1297574043273926, "Pretrain/Step": 5254, "Pretrain/Step Time": 8.462858008220792} +{"Pretrain/Learning Rate": 2.2085808278441868e-05, "Pretrain/Loss": 2.0119285583496094, "Pretrain/Loss (Raw)": 2.050429344177246, "Pretrain/Step": 5255, "Pretrain/Step Time": 8.460657488554716} +{"Pretrain/Learning Rate": 2.2077375539552765e-05, "Pretrain/Loss": 2.0106823444366455, "Pretrain/Loss (Raw)": 1.9116015434265137, "Pretrain/Step": 5256, "Pretrain/Step Time": 8.457744089886546} +{"Pretrain/Learning Rate": 2.2068943137787353e-05, "Pretrain/Loss": 2.0089197158813477, "Pretrain/Loss (Raw)": 1.9596378803253174, "Pretrain/Step": 5257, "Pretrain/Step Time": 8.456601744517684} +{"Pretrain/Learning Rate": 2.2060511074118324e-05, "Pretrain/Loss": 2.00962233543396, "Pretrain/Loss (Raw)": 2.0411829948425293, "Pretrain/Step": 5258, "Pretrain/Step Time": 8.459239885210991} +{"Pretrain/Learning Rate": 2.205207934951831e-05, "Pretrain/Loss": 2.009382724761963, "Pretrain/Loss (Raw)": 2.0050532817840576, "Pretrain/Step": 5259, "Pretrain/Step Time": 8.459625970572233} +{"Pretrain/Learning Rate": 2.204364796495991e-05, "Pretrain/Loss": 2.0099000930786133, "Pretrain/Loss (Raw)": 2.0945589542388916, "Pretrain/Step": 5260, "Pretrain/Step Time": 8.461118195205927} +{"Pretrain/Learning Rate": 2.203521692141568e-05, "Pretrain/Loss": 2.0073423385620117, "Pretrain/Loss (Raw)": 1.9084495306015015, "Pretrain/Step": 5261, "Pretrain/Step Time": 8.458592504262924} +{"Pretrain/Learning Rate": 2.2026786219858127e-05, "Pretrain/Loss": 2.0087931156158447, "Pretrain/Loss (Raw)": 2.1005046367645264, "Pretrain/Step": 5262, "Pretrain/Step Time": 8.458015989512205} +{"Pretrain/Learning Rate": 2.2018355861259742e-05, "Pretrain/Loss": 2.0096068382263184, "Pretrain/Loss (Raw)": 2.1322214603424072, "Pretrain/Step": 5263, "Pretrain/Step Time": 8.460461840033531} +{"Pretrain/Learning Rate": 2.200992584659296e-05, "Pretrain/Loss": 2.011500597000122, "Pretrain/Loss (Raw)": 2.1738808155059814, "Pretrain/Step": 5264, "Pretrain/Step Time": 8.458585629239678} +{"Pretrain/Learning Rate": 2.200149617683018e-05, "Pretrain/Loss": 2.0121753215789795, "Pretrain/Loss (Raw)": 2.0541269779205322, "Pretrain/Step": 5265, "Pretrain/Step Time": 8.458777897059917} +{"Pretrain/Learning Rate": 2.199306685294377e-05, "Pretrain/Loss": 2.0103960037231445, "Pretrain/Loss (Raw)": 2.0163302421569824, "Pretrain/Step": 5266, "Pretrain/Step Time": 8.455917488783598} +{"Pretrain/Learning Rate": 2.1984637875906038e-05, "Pretrain/Loss": 2.0122904777526855, "Pretrain/Loss (Raw)": 2.2298874855041504, "Pretrain/Step": 5267, "Pretrain/Step Time": 8.459972433745861} +{"Pretrain/Learning Rate": 2.197620924668927e-05, "Pretrain/Loss": 2.0125808715820312, "Pretrain/Loss (Raw)": 2.0367541313171387, "Pretrain/Step": 5268, "Pretrain/Step Time": 8.462934546172619} +{"Pretrain/Learning Rate": 2.1967780966265695e-05, "Pretrain/Loss": 2.013010263442993, "Pretrain/Loss (Raw)": 2.06972336769104, "Pretrain/Step": 5269, "Pretrain/Step Time": 8.465069247409701} +{"Pretrain/Learning Rate": 2.195935303560752e-05, "Pretrain/Loss": 2.0137085914611816, "Pretrain/Loss (Raw)": 2.2083277702331543, "Pretrain/Step": 5270, "Pretrain/Step Time": 8.461590999737382} +{"Pretrain/Learning Rate": 2.195092545568691e-05, "Pretrain/Loss": 2.014251708984375, "Pretrain/Loss (Raw)": 2.1724860668182373, "Pretrain/Step": 5271, "Pretrain/Step Time": 8.463186709210277} +{"Pretrain/Learning Rate": 2.194249822747598e-05, "Pretrain/Loss": 2.0151097774505615, "Pretrain/Loss (Raw)": 1.9475566148757935, "Pretrain/Step": 5272, "Pretrain/Step Time": 8.464495388790965} +{"Pretrain/Learning Rate": 2.19340713519468e-05, "Pretrain/Loss": 2.0149459838867188, "Pretrain/Loss (Raw)": 1.947506308555603, "Pretrain/Step": 5273, "Pretrain/Step Time": 8.463502934202552} +{"Pretrain/Learning Rate": 2.1925644830071407e-05, "Pretrain/Loss": 2.017326831817627, "Pretrain/Loss (Raw)": 2.1387014389038086, "Pretrain/Step": 5274, "Pretrain/Step Time": 8.462158454582095} +{"Pretrain/Learning Rate": 2.1917218662821808e-05, "Pretrain/Loss": 2.0182855129241943, "Pretrain/Loss (Raw)": 2.111501693725586, "Pretrain/Step": 5275, "Pretrain/Step Time": 8.462934939190745} +{"Pretrain/Learning Rate": 2.1908792851169952e-05, "Pretrain/Loss": 2.0224239826202393, "Pretrain/Loss (Raw)": 2.2284204959869385, "Pretrain/Step": 5276, "Pretrain/Step Time": 8.462336355820298} +{"Pretrain/Learning Rate": 2.1900367396087755e-05, "Pretrain/Loss": 2.0242555141448975, "Pretrain/Loss (Raw)": 2.0726158618927, "Pretrain/Step": 5277, "Pretrain/Step Time": 8.464167330414057} +{"Pretrain/Learning Rate": 2.1891942298547094e-05, "Pretrain/Loss": 2.0252175331115723, "Pretrain/Loss (Raw)": 1.9935051202774048, "Pretrain/Step": 5278, "Pretrain/Step Time": 8.462359281256795} +{"Pretrain/Learning Rate": 2.1883517559519788e-05, "Pretrain/Loss": 2.0264620780944824, "Pretrain/Loss (Raw)": 2.022549867630005, "Pretrain/Step": 5279, "Pretrain/Step Time": 8.462108505889773} +{"Pretrain/Learning Rate": 2.187509317997764e-05, "Pretrain/Loss": 2.0250132083892822, "Pretrain/Loss (Raw)": 1.9284111261367798, "Pretrain/Step": 5280, "Pretrain/Step Time": 8.464348457753658} +{"Pretrain/Learning Rate": 2.186666916089239e-05, "Pretrain/Loss": 2.024038314819336, "Pretrain/Loss (Raw)": 2.0726566314697266, "Pretrain/Step": 5281, "Pretrain/Step Time": 8.464030604809523} +{"Pretrain/Learning Rate": 2.1858245503235765e-05, "Pretrain/Loss": 2.0229651927948, "Pretrain/Loss (Raw)": 2.0086252689361572, "Pretrain/Step": 5282, "Pretrain/Step Time": 8.460396483540535} +{"Pretrain/Learning Rate": 2.1849822207979408e-05, "Pretrain/Loss": 2.02315092086792, "Pretrain/Loss (Raw)": 2.024571418762207, "Pretrain/Step": 5283, "Pretrain/Step Time": 8.46275458112359} +{"Pretrain/Learning Rate": 2.184139927609495e-05, "Pretrain/Loss": 2.0220530033111572, "Pretrain/Loss (Raw)": 1.9943656921386719, "Pretrain/Step": 5284, "Pretrain/Step Time": 8.46441499888897} +{"Pretrain/Learning Rate": 2.183297670855398e-05, "Pretrain/Loss": 2.0222721099853516, "Pretrain/Loss (Raw)": 2.2068450450897217, "Pretrain/Step": 5285, "Pretrain/Step Time": 8.46390175446868} +{"Pretrain/Learning Rate": 2.182455450632803e-05, "Pretrain/Loss": 2.0204696655273438, "Pretrain/Loss (Raw)": 1.966511845588684, "Pretrain/Step": 5286, "Pretrain/Step Time": 8.462279867380857} +{"Pretrain/Learning Rate": 2.1816132670388604e-05, "Pretrain/Loss": 2.0209462642669678, "Pretrain/Loss (Raw)": 2.0314300060272217, "Pretrain/Step": 5287, "Pretrain/Step Time": 8.461783135309815} +{"Pretrain/Learning Rate": 2.1807711201707166e-05, "Pretrain/Loss": 2.022571086883545, "Pretrain/Loss (Raw)": 2.124979257583618, "Pretrain/Step": 5288, "Pretrain/Step Time": 8.460384279489517} +{"Pretrain/Learning Rate": 2.1799290101255104e-05, "Pretrain/Loss": 2.02331280708313, "Pretrain/Loss (Raw)": 2.0302038192749023, "Pretrain/Step": 5289, "Pretrain/Step Time": 8.461047951132059} +{"Pretrain/Learning Rate": 2.1790869370003805e-05, "Pretrain/Loss": 2.018616199493408, "Pretrain/Loss (Raw)": 1.3594260215759277, "Pretrain/Step": 5290, "Pretrain/Step Time": 8.463732060045004} +{"Pretrain/Learning Rate": 2.17824490089246e-05, "Pretrain/Loss": 2.0203542709350586, "Pretrain/Loss (Raw)": 2.1629621982574463, "Pretrain/Step": 5291, "Pretrain/Step Time": 8.461942261084914} +{"Pretrain/Learning Rate": 2.1774029018988772e-05, "Pretrain/Loss": 2.020954132080078, "Pretrain/Loss (Raw)": 2.149371862411499, "Pretrain/Step": 5292, "Pretrain/Step Time": 8.461070641875267} +{"Pretrain/Learning Rate": 2.1765609401167565e-05, "Pretrain/Loss": 2.020383834838867, "Pretrain/Loss (Raw)": 1.9032970666885376, "Pretrain/Step": 5293, "Pretrain/Step Time": 8.460124514997005} +{"Pretrain/Learning Rate": 2.1757190156432177e-05, "Pretrain/Loss": 2.0191357135772705, "Pretrain/Loss (Raw)": 1.9535415172576904, "Pretrain/Step": 5294, "Pretrain/Step Time": 8.459365459159017} +{"Pretrain/Learning Rate": 2.174877128575376e-05, "Pretrain/Loss": 2.0191702842712402, "Pretrain/Loss (Raw)": 1.9171037673950195, "Pretrain/Step": 5295, "Pretrain/Step Time": 8.467848280444741} +{"Pretrain/Learning Rate": 2.1740352790103434e-05, "Pretrain/Loss": 2.0163755416870117, "Pretrain/Loss (Raw)": 1.8053911924362183, "Pretrain/Step": 5296, "Pretrain/Step Time": 8.464181836694479} +{"Pretrain/Learning Rate": 2.1731934670452264e-05, "Pretrain/Loss": 2.0160562992095947, "Pretrain/Loss (Raw)": 1.9566195011138916, "Pretrain/Step": 5297, "Pretrain/Step Time": 8.461008368059993} +{"Pretrain/Learning Rate": 2.1723516927771294e-05, "Pretrain/Loss": 2.018238067626953, "Pretrain/Loss (Raw)": 2.0706233978271484, "Pretrain/Step": 5298, "Pretrain/Step Time": 8.464266637340188} +{"Pretrain/Learning Rate": 2.1715099563031486e-05, "Pretrain/Loss": 2.0167930126190186, "Pretrain/Loss (Raw)": 1.8702337741851807, "Pretrain/Step": 5299, "Pretrain/Step Time": 8.464470649138093} +{"Pretrain/Learning Rate": 2.1706682577203786e-05, "Pretrain/Loss": 2.014249324798584, "Pretrain/Loss (Raw)": 1.8373191356658936, "Pretrain/Step": 5300, "Pretrain/Step Time": 8.464016204699874} +{"Pretrain/Learning Rate": 2.16982659712591e-05, "Pretrain/Loss": 2.015972852706909, "Pretrain/Loss (Raw)": 2.119391918182373, "Pretrain/Step": 5301, "Pretrain/Step Time": 8.464082043617964} +{"Pretrain/Learning Rate": 2.1689849746168268e-05, "Pretrain/Loss": 2.0159554481506348, "Pretrain/Loss (Raw)": 2.031165361404419, "Pretrain/Step": 5302, "Pretrain/Step Time": 8.471595041453838} +{"Pretrain/Learning Rate": 2.1681433902902118e-05, "Pretrain/Loss": 2.0162620544433594, "Pretrain/Loss (Raw)": 2.0084564685821533, "Pretrain/Step": 5303, "Pretrain/Step Time": 8.467931630089879} +{"Pretrain/Learning Rate": 2.1673018442431387e-05, "Pretrain/Loss": 2.01238751411438, "Pretrain/Loss (Raw)": 1.6712177991867065, "Pretrain/Step": 5304, "Pretrain/Step Time": 8.471318911761045} +{"Pretrain/Learning Rate": 2.166460336572681e-05, "Pretrain/Loss": 2.014068126678467, "Pretrain/Loss (Raw)": 2.157146453857422, "Pretrain/Step": 5305, "Pretrain/Step Time": 8.46917917393148} +{"Pretrain/Learning Rate": 2.1656188673759065e-05, "Pretrain/Loss": 2.0150113105773926, "Pretrain/Loss (Raw)": 2.040123224258423, "Pretrain/Step": 5306, "Pretrain/Step Time": 8.470890616998076} +{"Pretrain/Learning Rate": 2.1647774367498778e-05, "Pretrain/Loss": 2.014314651489258, "Pretrain/Loss (Raw)": 1.9294514656066895, "Pretrain/Step": 5307, "Pretrain/Step Time": 8.470637496560812} +{"Pretrain/Learning Rate": 2.1639360447916547e-05, "Pretrain/Loss": 2.01349139213562, "Pretrain/Loss (Raw)": 1.9337353706359863, "Pretrain/Step": 5308, "Pretrain/Step Time": 8.469130117446184} +{"Pretrain/Learning Rate": 2.163094691598291e-05, "Pretrain/Loss": 2.015348434448242, "Pretrain/Loss (Raw)": 2.021742820739746, "Pretrain/Step": 5309, "Pretrain/Step Time": 8.464013995602727} +{"Pretrain/Learning Rate": 2.1622533772668356e-05, "Pretrain/Loss": 2.0158896446228027, "Pretrain/Loss (Raw)": 1.9143345355987549, "Pretrain/Step": 5310, "Pretrain/Step Time": 8.469013577327132} +{"Pretrain/Learning Rate": 2.1614121018943344e-05, "Pretrain/Loss": 2.014315128326416, "Pretrain/Loss (Raw)": 1.9753475189208984, "Pretrain/Step": 5311, "Pretrain/Step Time": 8.46715396642685} +{"Pretrain/Learning Rate": 2.1605708655778282e-05, "Pretrain/Loss": 2.015956163406372, "Pretrain/Loss (Raw)": 2.1966805458068848, "Pretrain/Step": 5312, "Pretrain/Step Time": 8.468361740931869} +{"Pretrain/Learning Rate": 2.159729668414353e-05, "Pretrain/Loss": 2.0135955810546875, "Pretrain/Loss (Raw)": 1.7819968461990356, "Pretrain/Step": 5313, "Pretrain/Step Time": 8.465631056576967} +{"Pretrain/Learning Rate": 2.1588885105009427e-05, "Pretrain/Loss": 2.013925790786743, "Pretrain/Loss (Raw)": 2.0834436416625977, "Pretrain/Step": 5314, "Pretrain/Step Time": 8.463877599686384} +{"Pretrain/Learning Rate": 2.158047391934621e-05, "Pretrain/Loss": 2.0142598152160645, "Pretrain/Loss (Raw)": 2.0215258598327637, "Pretrain/Step": 5315, "Pretrain/Step Time": 8.461783530190587} +{"Pretrain/Learning Rate": 2.157206312812413e-05, "Pretrain/Loss": 2.0120911598205566, "Pretrain/Loss (Raw)": 1.8320996761322021, "Pretrain/Step": 5316, "Pretrain/Step Time": 8.467371815815568} +{"Pretrain/Learning Rate": 2.1563652732313367e-05, "Pretrain/Loss": 2.0122389793395996, "Pretrain/Loss (Raw)": 1.9111326932907104, "Pretrain/Step": 5317, "Pretrain/Step Time": 8.46900411695242} +{"Pretrain/Learning Rate": 2.155524273288405e-05, "Pretrain/Loss": 2.0149641036987305, "Pretrain/Loss (Raw)": 2.136178731918335, "Pretrain/Step": 5318, "Pretrain/Step Time": 8.47060308419168} +{"Pretrain/Learning Rate": 2.1546833130806277e-05, "Pretrain/Loss": 2.015104293823242, "Pretrain/Loss (Raw)": 2.0368118286132812, "Pretrain/Step": 5319, "Pretrain/Step Time": 8.468505816534162} +{"Pretrain/Learning Rate": 2.153842392705009e-05, "Pretrain/Loss": 2.0157105922698975, "Pretrain/Loss (Raw)": 2.0920214653015137, "Pretrain/Step": 5320, "Pretrain/Step Time": 8.472234206274152} +{"Pretrain/Learning Rate": 2.1530015122585478e-05, "Pretrain/Loss": 2.016784191131592, "Pretrain/Loss (Raw)": 2.0746982097625732, "Pretrain/Step": 5321, "Pretrain/Step Time": 8.46991235204041} +{"Pretrain/Learning Rate": 2.1521606718382406e-05, "Pretrain/Loss": 2.016057014465332, "Pretrain/Loss (Raw)": 2.0521578788757324, "Pretrain/Step": 5322, "Pretrain/Step Time": 8.46761005371809} +{"Pretrain/Learning Rate": 2.1513198715410777e-05, "Pretrain/Loss": 2.0180962085723877, "Pretrain/Loss (Raw)": 2.240523099899292, "Pretrain/Step": 5323, "Pretrain/Step Time": 8.468638332560658} +{"Pretrain/Learning Rate": 2.150479111464045e-05, "Pretrain/Loss": 2.017306327819824, "Pretrain/Loss (Raw)": 1.932009220123291, "Pretrain/Step": 5324, "Pretrain/Step Time": 8.469394572079182} +{"Pretrain/Learning Rate": 2.1496383917041247e-05, "Pretrain/Loss": 2.0171756744384766, "Pretrain/Loss (Raw)": 2.0806314945220947, "Pretrain/Step": 5325, "Pretrain/Step Time": 8.468969015404582} +{"Pretrain/Learning Rate": 2.148797712358292e-05, "Pretrain/Loss": 2.014772415161133, "Pretrain/Loss (Raw)": 1.9437439441680908, "Pretrain/Step": 5326, "Pretrain/Step Time": 8.469045352190733} +{"Pretrain/Learning Rate": 2.1479570735235198e-05, "Pretrain/Loss": 2.0136430263519287, "Pretrain/Loss (Raw)": 1.9296085834503174, "Pretrain/Step": 5327, "Pretrain/Step Time": 8.47479148209095} +{"Pretrain/Learning Rate": 2.1471164752967757e-05, "Pretrain/Loss": 2.015639305114746, "Pretrain/Loss (Raw)": 2.0155224800109863, "Pretrain/Step": 5328, "Pretrain/Step Time": 8.471254862844944} +{"Pretrain/Learning Rate": 2.1462759177750218e-05, "Pretrain/Loss": 2.018397331237793, "Pretrain/Loss (Raw)": 2.1068549156188965, "Pretrain/Step": 5329, "Pretrain/Step Time": 8.469508972018957} +{"Pretrain/Learning Rate": 2.1454354010552174e-05, "Pretrain/Loss": 2.0163631439208984, "Pretrain/Loss (Raw)": 1.7717293500900269, "Pretrain/Step": 5330, "Pretrain/Step Time": 8.47177811153233} +{"Pretrain/Learning Rate": 2.144594925234314e-05, "Pretrain/Loss": 2.0172557830810547, "Pretrain/Loss (Raw)": 2.0455024242401123, "Pretrain/Step": 5331, "Pretrain/Step Time": 8.470355546101928} +{"Pretrain/Learning Rate": 2.143754490409261e-05, "Pretrain/Loss": 2.017605781555176, "Pretrain/Loss (Raw)": 2.0205626487731934, "Pretrain/Step": 5332, "Pretrain/Step Time": 8.468274967744946} +{"Pretrain/Learning Rate": 2.1429140966770027e-05, "Pretrain/Loss": 2.019287109375, "Pretrain/Loss (Raw)": 2.039609670639038, "Pretrain/Step": 5333, "Pretrain/Step Time": 8.47339777648449} +{"Pretrain/Learning Rate": 2.142073744134478e-05, "Pretrain/Loss": 2.0211329460144043, "Pretrain/Loss (Raw)": 2.058527946472168, "Pretrain/Step": 5334, "Pretrain/Step Time": 8.471382590010762} +{"Pretrain/Learning Rate": 2.141233432878621e-05, "Pretrain/Loss": 2.0218570232391357, "Pretrain/Loss (Raw)": 2.1186370849609375, "Pretrain/Step": 5335, "Pretrain/Step Time": 8.473854284733534} +{"Pretrain/Learning Rate": 2.1403931630063616e-05, "Pretrain/Loss": 2.0220727920532227, "Pretrain/Loss (Raw)": 2.0668115615844727, "Pretrain/Step": 5336, "Pretrain/Step Time": 8.479233108460903} +{"Pretrain/Learning Rate": 2.1395529346146243e-05, "Pretrain/Loss": 2.0212645530700684, "Pretrain/Loss (Raw)": 2.0439484119415283, "Pretrain/Step": 5337, "Pretrain/Step Time": 8.478050820529461} +{"Pretrain/Learning Rate": 2.138712747800329e-05, "Pretrain/Loss": 2.0211219787597656, "Pretrain/Loss (Raw)": 1.9575713872909546, "Pretrain/Step": 5338, "Pretrain/Step Time": 8.477484298869967} +{"Pretrain/Learning Rate": 2.1378726026603913e-05, "Pretrain/Loss": 2.0209875106811523, "Pretrain/Loss (Raw)": 2.1279516220092773, "Pretrain/Step": 5339, "Pretrain/Step Time": 8.478164663538337} +{"Pretrain/Learning Rate": 2.1370324992917225e-05, "Pretrain/Loss": 2.0225319862365723, "Pretrain/Loss (Raw)": 2.1470859050750732, "Pretrain/Step": 5340, "Pretrain/Step Time": 8.478718962520361} +{"Pretrain/Learning Rate": 2.1361924377912266e-05, "Pretrain/Loss": 2.025620937347412, "Pretrain/Loss (Raw)": 2.24381160736084, "Pretrain/Step": 5341, "Pretrain/Step Time": 8.479595622047782} +{"Pretrain/Learning Rate": 2.135352418255805e-05, "Pretrain/Loss": 2.026679515838623, "Pretrain/Loss (Raw)": 1.978075623512268, "Pretrain/Step": 5342, "Pretrain/Step Time": 8.482655117288232} +{"Pretrain/Learning Rate": 2.1345124407823544e-05, "Pretrain/Loss": 2.027738094329834, "Pretrain/Loss (Raw)": 2.0282750129699707, "Pretrain/Step": 5343, "Pretrain/Step Time": 8.481045380234718} +{"Pretrain/Learning Rate": 2.1336725054677647e-05, "Pretrain/Loss": 2.027172565460205, "Pretrain/Loss (Raw)": 1.9115153551101685, "Pretrain/Step": 5344, "Pretrain/Step Time": 8.478309532627463} +{"Pretrain/Learning Rate": 2.1328326124089227e-05, "Pretrain/Loss": 2.0290465354919434, "Pretrain/Loss (Raw)": 2.104851722717285, "Pretrain/Step": 5345, "Pretrain/Step Time": 8.474436989054084} +{"Pretrain/Learning Rate": 2.131992761702711e-05, "Pretrain/Loss": 2.029987335205078, "Pretrain/Loss (Raw)": 2.04331111907959, "Pretrain/Step": 5346, "Pretrain/Step Time": 8.474847570061684} +{"Pretrain/Learning Rate": 2.131152953446004e-05, "Pretrain/Loss": 2.0311825275421143, "Pretrain/Loss (Raw)": 2.0486254692077637, "Pretrain/Step": 5347, "Pretrain/Step Time": 8.479625850915909} +{"Pretrain/Learning Rate": 2.1303131877356738e-05, "Pretrain/Loss": 2.0324718952178955, "Pretrain/Loss (Raw)": 2.048527479171753, "Pretrain/Step": 5348, "Pretrain/Step Time": 8.48094829171896} +{"Pretrain/Learning Rate": 2.1294734646685878e-05, "Pretrain/Loss": 2.0316672325134277, "Pretrain/Loss (Raw)": 2.058645725250244, "Pretrain/Step": 5349, "Pretrain/Step Time": 8.479161387309432} +{"Pretrain/Learning Rate": 2.128633784341608e-05, "Pretrain/Loss": 2.0326128005981445, "Pretrain/Loss (Raw)": 2.1021783351898193, "Pretrain/Step": 5350, "Pretrain/Step Time": 8.47705365717411} +{"Pretrain/Learning Rate": 2.1277941468515906e-05, "Pretrain/Loss": 2.0320491790771484, "Pretrain/Loss (Raw)": 1.9784373044967651, "Pretrain/Step": 5351, "Pretrain/Step Time": 8.478569764643908} +{"Pretrain/Learning Rate": 2.1269545522953873e-05, "Pretrain/Loss": 2.033653974533081, "Pretrain/Loss (Raw)": 2.0581390857696533, "Pretrain/Step": 5352, "Pretrain/Step Time": 8.477167394012213} +{"Pretrain/Learning Rate": 2.126115000769845e-05, "Pretrain/Loss": 2.031294822692871, "Pretrain/Loss (Raw)": 1.85841703414917, "Pretrain/Step": 5353, "Pretrain/Step Time": 8.47830406203866} +{"Pretrain/Learning Rate": 2.125275492371806e-05, "Pretrain/Loss": 2.0315423011779785, "Pretrain/Loss (Raw)": 2.0763423442840576, "Pretrain/Step": 5354, "Pretrain/Step Time": 8.476587135344744} +{"Pretrain/Learning Rate": 2.1244360271981073e-05, "Pretrain/Loss": 2.029613494873047, "Pretrain/Loss (Raw)": 1.9778717756271362, "Pretrain/Step": 5355, "Pretrain/Step Time": 8.47635192796588} +{"Pretrain/Learning Rate": 2.123596605345582e-05, "Pretrain/Loss": 2.030179023742676, "Pretrain/Loss (Raw)": 2.0790579319000244, "Pretrain/Step": 5356, "Pretrain/Step Time": 8.476235711947083} +{"Pretrain/Learning Rate": 2.1227572269110546e-05, "Pretrain/Loss": 2.029646158218384, "Pretrain/Loss (Raw)": 1.990687370300293, "Pretrain/Step": 5357, "Pretrain/Step Time": 8.475719628855586} +{"Pretrain/Learning Rate": 2.1219178919913486e-05, "Pretrain/Loss": 2.0288753509521484, "Pretrain/Loss (Raw)": 2.002525568008423, "Pretrain/Step": 5358, "Pretrain/Step Time": 8.475169626995921} +{"Pretrain/Learning Rate": 2.1210786006832817e-05, "Pretrain/Loss": 2.026763439178467, "Pretrain/Loss (Raw)": 1.860511302947998, "Pretrain/Step": 5359, "Pretrain/Step Time": 8.475015737116337} +{"Pretrain/Learning Rate": 2.1202393530836642e-05, "Pretrain/Loss": 2.027592182159424, "Pretrain/Loss (Raw)": 2.0592825412750244, "Pretrain/Step": 5360, "Pretrain/Step Time": 8.476286826655269} +{"Pretrain/Learning Rate": 2.119400149289305e-05, "Pretrain/Loss": 2.0256800651550293, "Pretrain/Loss (Raw)": 1.8763892650604248, "Pretrain/Step": 5361, "Pretrain/Step Time": 8.4707918651402} +{"Pretrain/Learning Rate": 2.118560989397004e-05, "Pretrain/Loss": 2.0287604331970215, "Pretrain/Loss (Raw)": 2.1741344928741455, "Pretrain/Step": 5362, "Pretrain/Step Time": 8.46985931508243} +{"Pretrain/Learning Rate": 2.1177218735035588e-05, "Pretrain/Loss": 2.0288498401641846, "Pretrain/Loss (Raw)": 2.1238808631896973, "Pretrain/Step": 5363, "Pretrain/Step Time": 8.4698121342808} +{"Pretrain/Learning Rate": 2.1168828017057607e-05, "Pretrain/Loss": 2.0267655849456787, "Pretrain/Loss (Raw)": 2.0944931507110596, "Pretrain/Step": 5364, "Pretrain/Step Time": 8.470338163897395} +{"Pretrain/Learning Rate": 2.116043774100397e-05, "Pretrain/Loss": 2.0257558822631836, "Pretrain/Loss (Raw)": 1.8855620622634888, "Pretrain/Step": 5365, "Pretrain/Step Time": 8.471947275102139} +{"Pretrain/Learning Rate": 2.1152047907842498e-05, "Pretrain/Loss": 2.024827241897583, "Pretrain/Loss (Raw)": 1.93035089969635, "Pretrain/Step": 5366, "Pretrain/Step Time": 8.476426742970943} +{"Pretrain/Learning Rate": 2.1143658518540947e-05, "Pretrain/Loss": 2.024583339691162, "Pretrain/Loss (Raw)": 2.055584669113159, "Pretrain/Step": 5367, "Pretrain/Step Time": 8.476567473262548} +{"Pretrain/Learning Rate": 2.1135269574067025e-05, "Pretrain/Loss": 2.025651693344116, "Pretrain/Loss (Raw)": 2.052194118499756, "Pretrain/Step": 5368, "Pretrain/Step Time": 8.478411003947258} +{"Pretrain/Learning Rate": 2.1126881075388403e-05, "Pretrain/Loss": 2.025580644607544, "Pretrain/Loss (Raw)": 2.0888798236846924, "Pretrain/Step": 5369, "Pretrain/Step Time": 8.479797868058085} +{"Pretrain/Learning Rate": 2.111849302347268e-05, "Pretrain/Loss": 2.023475170135498, "Pretrain/Loss (Raw)": 1.9459563493728638, "Pretrain/Step": 5370, "Pretrain/Step Time": 8.481084803119302} +{"Pretrain/Learning Rate": 2.1110105419287428e-05, "Pretrain/Loss": 2.0222673416137695, "Pretrain/Loss (Raw)": 1.8779243230819702, "Pretrain/Step": 5371, "Pretrain/Step Time": 8.480971606448293} +{"Pretrain/Learning Rate": 2.110171826380016e-05, "Pretrain/Loss": 2.0204646587371826, "Pretrain/Loss (Raw)": 1.9008573293685913, "Pretrain/Step": 5372, "Pretrain/Step Time": 8.48049989156425} +{"Pretrain/Learning Rate": 2.1093331557978307e-05, "Pretrain/Loss": 2.0207936763763428, "Pretrain/Loss (Raw)": 1.9583386182785034, "Pretrain/Step": 5373, "Pretrain/Step Time": 8.479272495955229} +{"Pretrain/Learning Rate": 2.1084945302789286e-05, "Pretrain/Loss": 2.01723051071167, "Pretrain/Loss (Raw)": 1.6622626781463623, "Pretrain/Step": 5374, "Pretrain/Step Time": 8.47851175069809} +{"Pretrain/Learning Rate": 2.107655949920045e-05, "Pretrain/Loss": 2.0168581008911133, "Pretrain/Loss (Raw)": 2.1271612644195557, "Pretrain/Step": 5375, "Pretrain/Step Time": 8.477666046470404} +{"Pretrain/Learning Rate": 2.10681741481791e-05, "Pretrain/Loss": 2.0186824798583984, "Pretrain/Loss (Raw)": 2.2153279781341553, "Pretrain/Step": 5376, "Pretrain/Step Time": 8.475077142938972} +{"Pretrain/Learning Rate": 2.105978925069248e-05, "Pretrain/Loss": 2.0163066387176514, "Pretrain/Loss (Raw)": 1.6990541219711304, "Pretrain/Step": 5377, "Pretrain/Step Time": 8.476086696609855} +{"Pretrain/Learning Rate": 2.1051404807707787e-05, "Pretrain/Loss": 2.0154457092285156, "Pretrain/Loss (Raw)": 1.9349955320358276, "Pretrain/Step": 5378, "Pretrain/Step Time": 8.468917533755302} +{"Pretrain/Learning Rate": 2.1043020820192157e-05, "Pretrain/Loss": 2.0157294273376465, "Pretrain/Loss (Raw)": 2.0584020614624023, "Pretrain/Step": 5379, "Pretrain/Step Time": 8.467161685228348} +{"Pretrain/Learning Rate": 2.1034637289112685e-05, "Pretrain/Loss": 2.0166919231414795, "Pretrain/Loss (Raw)": 2.1154379844665527, "Pretrain/Step": 5380, "Pretrain/Step Time": 8.470059890300035} +{"Pretrain/Learning Rate": 2.1026254215436406e-05, "Pretrain/Loss": 2.017127275466919, "Pretrain/Loss (Raw)": 2.1065738201141357, "Pretrain/Step": 5381, "Pretrain/Step Time": 8.471792750060558} +{"Pretrain/Learning Rate": 2.101787160013032e-05, "Pretrain/Loss": 2.017197847366333, "Pretrain/Loss (Raw)": 2.138784885406494, "Pretrain/Step": 5382, "Pretrain/Step Time": 8.469372114166617} +{"Pretrain/Learning Rate": 2.1009489444161332e-05, "Pretrain/Loss": 2.016042709350586, "Pretrain/Loss (Raw)": 1.9025636911392212, "Pretrain/Step": 5383, "Pretrain/Step Time": 8.473444120958447} +{"Pretrain/Learning Rate": 2.1001107748496334e-05, "Pretrain/Loss": 2.0172362327575684, "Pretrain/Loss (Raw)": 2.0643723011016846, "Pretrain/Step": 5384, "Pretrain/Step Time": 8.473931010812521} +{"Pretrain/Learning Rate": 2.099272651410216e-05, "Pretrain/Loss": 2.0173895359039307, "Pretrain/Loss (Raw)": 1.9792569875717163, "Pretrain/Step": 5385, "Pretrain/Step Time": 8.477233499288559} +{"Pretrain/Learning Rate": 2.098434574194557e-05, "Pretrain/Loss": 2.0176949501037598, "Pretrain/Loss (Raw)": 2.0802712440490723, "Pretrain/Step": 5386, "Pretrain/Step Time": 8.476692736148834} +{"Pretrain/Learning Rate": 2.0975965432993283e-05, "Pretrain/Loss": 2.018101215362549, "Pretrain/Loss (Raw)": 2.0570762157440186, "Pretrain/Step": 5387, "Pretrain/Step Time": 8.476463602855802} +{"Pretrain/Learning Rate": 2.0967585588211982e-05, "Pretrain/Loss": 2.0177268981933594, "Pretrain/Loss (Raw)": 2.0466296672821045, "Pretrain/Step": 5388, "Pretrain/Step Time": 8.476902566850185} +{"Pretrain/Learning Rate": 2.0959206208568254e-05, "Pretrain/Loss": 2.0195906162261963, "Pretrain/Loss (Raw)": 2.147022008895874, "Pretrain/Step": 5389, "Pretrain/Step Time": 8.476183384656906} +{"Pretrain/Learning Rate": 2.0950827295028674e-05, "Pretrain/Loss": 2.0194449424743652, "Pretrain/Loss (Raw)": 2.0818698406219482, "Pretrain/Step": 5390, "Pretrain/Step Time": 8.474121123552322} +{"Pretrain/Learning Rate": 2.094244884855974e-05, "Pretrain/Loss": 2.0180912017822266, "Pretrain/Loss (Raw)": 1.9589134454727173, "Pretrain/Step": 5391, "Pretrain/Step Time": 8.47276809439063} +{"Pretrain/Learning Rate": 2.0934070870127912e-05, "Pretrain/Loss": 2.0162196159362793, "Pretrain/Loss (Raw)": 1.9343472719192505, "Pretrain/Step": 5392, "Pretrain/Step Time": 8.471717219799757} +{"Pretrain/Learning Rate": 2.0925693360699578e-05, "Pretrain/Loss": 2.0164523124694824, "Pretrain/Loss (Raw)": 2.0838840007781982, "Pretrain/Step": 5393, "Pretrain/Step Time": 8.469719806686044} +{"Pretrain/Learning Rate": 2.0917316321241085e-05, "Pretrain/Loss": 2.0181212425231934, "Pretrain/Loss (Raw)": 2.2299439907073975, "Pretrain/Step": 5394, "Pretrain/Step Time": 8.470943663269281} +{"Pretrain/Learning Rate": 2.0908939752718714e-05, "Pretrain/Loss": 2.016605854034424, "Pretrain/Loss (Raw)": 2.0359294414520264, "Pretrain/Step": 5395, "Pretrain/Step Time": 8.465852212160826} +{"Pretrain/Learning Rate": 2.0900563656098704e-05, "Pretrain/Loss": 2.01653790473938, "Pretrain/Loss (Raw)": 2.0280792713165283, "Pretrain/Step": 5396, "Pretrain/Step Time": 8.463491505011916} +{"Pretrain/Learning Rate": 2.0892188032347236e-05, "Pretrain/Loss": 2.0149965286254883, "Pretrain/Loss (Raw)": 1.872413158416748, "Pretrain/Step": 5397, "Pretrain/Step Time": 8.462578130885959} +{"Pretrain/Learning Rate": 2.0883812882430445e-05, "Pretrain/Loss": 2.013376235961914, "Pretrain/Loss (Raw)": 2.0009474754333496, "Pretrain/Step": 5398, "Pretrain/Step Time": 8.464755561202765} +{"Pretrain/Learning Rate": 2.087543820731438e-05, "Pretrain/Loss": 2.0116453170776367, "Pretrain/Loss (Raw)": 1.9509227275848389, "Pretrain/Step": 5399, "Pretrain/Step Time": 8.468192430213094} +{"Pretrain/Learning Rate": 2.086706400796507e-05, "Pretrain/Loss": 2.01212477684021, "Pretrain/Loss (Raw)": 2.008918285369873, "Pretrain/Step": 5400, "Pretrain/Step Time": 8.468003595247865} +{"Pretrain/Learning Rate": 2.085869028534848e-05, "Pretrain/Loss": 2.0126662254333496, "Pretrain/Loss (Raw)": 2.0167839527130127, "Pretrain/Step": 5401, "Pretrain/Step Time": 8.466560255736113} +{"Pretrain/Learning Rate": 2.0850317040430505e-05, "Pretrain/Loss": 2.0121846199035645, "Pretrain/Loss (Raw)": 2.0770721435546875, "Pretrain/Step": 5402, "Pretrain/Step Time": 8.468055259436369} +{"Pretrain/Learning Rate": 2.084194427417701e-05, "Pretrain/Loss": 2.013430118560791, "Pretrain/Loss (Raw)": 2.270913600921631, "Pretrain/Step": 5403, "Pretrain/Step Time": 8.46917506121099} +{"Pretrain/Learning Rate": 2.0833571987553772e-05, "Pretrain/Loss": 2.011425495147705, "Pretrain/Loss (Raw)": 1.9718738794326782, "Pretrain/Step": 5404, "Pretrain/Step Time": 8.469072729349136} +{"Pretrain/Learning Rate": 2.0825200181526542e-05, "Pretrain/Loss": 2.011298656463623, "Pretrain/Loss (Raw)": 2.056377410888672, "Pretrain/Step": 5405, "Pretrain/Step Time": 8.467957928776741} +{"Pretrain/Learning Rate": 2.0816828857061e-05, "Pretrain/Loss": 2.011824607849121, "Pretrain/Loss (Raw)": 2.060826301574707, "Pretrain/Step": 5406, "Pretrain/Step Time": 8.467037165537477} +{"Pretrain/Learning Rate": 2.0808458015122785e-05, "Pretrain/Loss": 2.0111608505249023, "Pretrain/Loss (Raw)": 1.9375760555267334, "Pretrain/Step": 5407, "Pretrain/Step Time": 8.46923105046153} +{"Pretrain/Learning Rate": 2.0800087656677467e-05, "Pretrain/Loss": 2.011249542236328, "Pretrain/Loss (Raw)": 1.9397832155227661, "Pretrain/Step": 5408, "Pretrain/Step Time": 8.46519609540701} +{"Pretrain/Learning Rate": 2.0791717782690562e-05, "Pretrain/Loss": 2.011963129043579, "Pretrain/Loss (Raw)": 2.1639564037323, "Pretrain/Step": 5409, "Pretrain/Step Time": 8.465974787250161} +{"Pretrain/Learning Rate": 2.0783348394127526e-05, "Pretrain/Loss": 2.012556314468384, "Pretrain/Loss (Raw)": 2.0845532417297363, "Pretrain/Step": 5410, "Pretrain/Step Time": 8.4670938141644} +{"Pretrain/Learning Rate": 2.0774979491953777e-05, "Pretrain/Loss": 2.0122199058532715, "Pretrain/Loss (Raw)": 1.9815336465835571, "Pretrain/Step": 5411, "Pretrain/Step Time": 8.469412747770548} +{"Pretrain/Learning Rate": 2.0766611077134654e-05, "Pretrain/Loss": 2.0120773315429688, "Pretrain/Loss (Raw)": 1.9761114120483398, "Pretrain/Step": 5412, "Pretrain/Step Time": 8.466252809390426} +{"Pretrain/Learning Rate": 2.0758243150635453e-05, "Pretrain/Loss": 2.0100765228271484, "Pretrain/Loss (Raw)": 1.9507282972335815, "Pretrain/Step": 5413, "Pretrain/Step Time": 8.465873401612043} +{"Pretrain/Learning Rate": 2.074987571342143e-05, "Pretrain/Loss": 2.010767936706543, "Pretrain/Loss (Raw)": 2.0550498962402344, "Pretrain/Step": 5414, "Pretrain/Step Time": 8.468161230906844} +{"Pretrain/Learning Rate": 2.0741508766457735e-05, "Pretrain/Loss": 2.008720874786377, "Pretrain/Loss (Raw)": 1.7693531513214111, "Pretrain/Step": 5415, "Pretrain/Step Time": 8.47119065001607} +{"Pretrain/Learning Rate": 2.0733142310709508e-05, "Pretrain/Loss": 2.0085058212280273, "Pretrain/Loss (Raw)": 2.097484827041626, "Pretrain/Step": 5416, "Pretrain/Step Time": 8.471269179135561} +{"Pretrain/Learning Rate": 2.0724776347141816e-05, "Pretrain/Loss": 2.0073413848876953, "Pretrain/Loss (Raw)": 1.8811492919921875, "Pretrain/Step": 5417, "Pretrain/Step Time": 8.471878375858068} +{"Pretrain/Learning Rate": 2.0716410876719674e-05, "Pretrain/Loss": 2.012518882751465, "Pretrain/Loss (Raw)": 2.0221376419067383, "Pretrain/Step": 5418, "Pretrain/Step Time": 8.467603327706456} +{"Pretrain/Learning Rate": 2.0708045900408036e-05, "Pretrain/Loss": 2.012848377227783, "Pretrain/Loss (Raw)": 2.205146312713623, "Pretrain/Step": 5419, "Pretrain/Step Time": 8.470363741740584} +{"Pretrain/Learning Rate": 2.069968141917179e-05, "Pretrain/Loss": 2.0129144191741943, "Pretrain/Loss (Raw)": 2.157827377319336, "Pretrain/Step": 5420, "Pretrain/Step Time": 8.471364354714751} +{"Pretrain/Learning Rate": 2.0691317433975778e-05, "Pretrain/Loss": 2.015775680541992, "Pretrain/Loss (Raw)": 2.2695069313049316, "Pretrain/Step": 5421, "Pretrain/Step Time": 8.469882467761636} +{"Pretrain/Learning Rate": 2.0682953945784785e-05, "Pretrain/Loss": 2.0151748657226562, "Pretrain/Loss (Raw)": 1.8766833543777466, "Pretrain/Step": 5422, "Pretrain/Step Time": 8.472523646429181} +{"Pretrain/Learning Rate": 2.067459095556354e-05, "Pretrain/Loss": 2.0161285400390625, "Pretrain/Loss (Raw)": 2.039134979248047, "Pretrain/Step": 5423, "Pretrain/Step Time": 8.463262820616364} +{"Pretrain/Learning Rate": 2.0666228464276707e-05, "Pretrain/Loss": 2.01841139793396, "Pretrain/Loss (Raw)": 2.0976221561431885, "Pretrain/Step": 5424, "Pretrain/Step Time": 8.46240053139627} +{"Pretrain/Learning Rate": 2.0657866472888907e-05, "Pretrain/Loss": 2.0182952880859375, "Pretrain/Loss (Raw)": 1.9417181015014648, "Pretrain/Step": 5425, "Pretrain/Step Time": 8.463816614821553} +{"Pretrain/Learning Rate": 2.0649504982364672e-05, "Pretrain/Loss": 2.0174059867858887, "Pretrain/Loss (Raw)": 1.9567997455596924, "Pretrain/Step": 5426, "Pretrain/Step Time": 8.458839436993003} +{"Pretrain/Learning Rate": 2.0641143993668515e-05, "Pretrain/Loss": 2.017591953277588, "Pretrain/Loss (Raw)": 1.8940389156341553, "Pretrain/Step": 5427, "Pretrain/Step Time": 8.457292014732957} +{"Pretrain/Learning Rate": 2.0632783507764864e-05, "Pretrain/Loss": 2.017685890197754, "Pretrain/Loss (Raw)": 1.8493813276290894, "Pretrain/Step": 5428, "Pretrain/Step Time": 8.456764865666628} +{"Pretrain/Learning Rate": 2.0624423525618098e-05, "Pretrain/Loss": 2.016915798187256, "Pretrain/Loss (Raw)": 2.0208024978637695, "Pretrain/Step": 5429, "Pretrain/Step Time": 8.456525769084692} +{"Pretrain/Learning Rate": 2.061606404819255e-05, "Pretrain/Loss": 2.015700340270996, "Pretrain/Loss (Raw)": 1.8755875825881958, "Pretrain/Step": 5430, "Pretrain/Step Time": 8.451810548081994} +{"Pretrain/Learning Rate": 2.0607705076452465e-05, "Pretrain/Loss": 2.017305850982666, "Pretrain/Loss (Raw)": 2.213942766189575, "Pretrain/Step": 5431, "Pretrain/Step Time": 8.45293360389769} +{"Pretrain/Learning Rate": 2.0599346611362056e-05, "Pretrain/Loss": 2.0207366943359375, "Pretrain/Loss (Raw)": 2.1103925704956055, "Pretrain/Step": 5432, "Pretrain/Step Time": 8.456982931122184} +{"Pretrain/Learning Rate": 2.0590988653885468e-05, "Pretrain/Loss": 2.020313262939453, "Pretrain/Loss (Raw)": 2.102919816970825, "Pretrain/Step": 5433, "Pretrain/Step Time": 8.458285072818398} +{"Pretrain/Learning Rate": 2.0582631204986794e-05, "Pretrain/Loss": 2.0203778743743896, "Pretrain/Loss (Raw)": 2.0483996868133545, "Pretrain/Step": 5434, "Pretrain/Step Time": 8.45518571138382} +{"Pretrain/Learning Rate": 2.057427426563006e-05, "Pretrain/Loss": 2.020714282989502, "Pretrain/Loss (Raw)": 1.9724998474121094, "Pretrain/Step": 5435, "Pretrain/Step Time": 8.455210683867335} +{"Pretrain/Learning Rate": 2.056591783677923e-05, "Pretrain/Loss": 2.0214109420776367, "Pretrain/Loss (Raw)": 2.022952079772949, "Pretrain/Step": 5436, "Pretrain/Step Time": 8.455868246033788} +{"Pretrain/Learning Rate": 2.055756191939822e-05, "Pretrain/Loss": 2.0212247371673584, "Pretrain/Loss (Raw)": 1.9978948831558228, "Pretrain/Step": 5437, "Pretrain/Step Time": 8.456972097977996} +{"Pretrain/Learning Rate": 2.0549206514450874e-05, "Pretrain/Loss": 2.0221362113952637, "Pretrain/Loss (Raw)": 2.0309810638427734, "Pretrain/Step": 5438, "Pretrain/Step Time": 8.453812280669808} +{"Pretrain/Learning Rate": 2.0540851622900997e-05, "Pretrain/Loss": 2.022948980331421, "Pretrain/Loss (Raw)": 2.0794174671173096, "Pretrain/Step": 5439, "Pretrain/Step Time": 8.453822096809745} +{"Pretrain/Learning Rate": 2.0532497245712327e-05, "Pretrain/Loss": 2.0224809646606445, "Pretrain/Loss (Raw)": 2.1367669105529785, "Pretrain/Step": 5440, "Pretrain/Step Time": 8.45294151455164} +{"Pretrain/Learning Rate": 2.0524143383848525e-05, "Pretrain/Loss": 2.0242366790771484, "Pretrain/Loss (Raw)": 2.0067265033721924, "Pretrain/Step": 5441, "Pretrain/Step Time": 8.45504348538816} +{"Pretrain/Learning Rate": 2.0515790038273204e-05, "Pretrain/Loss": 2.0236055850982666, "Pretrain/Loss (Raw)": 2.0026419162750244, "Pretrain/Step": 5442, "Pretrain/Step Time": 8.455076601356268} +{"Pretrain/Learning Rate": 2.0507437209949937e-05, "Pretrain/Loss": 2.0222511291503906, "Pretrain/Loss (Raw)": 1.8481417894363403, "Pretrain/Step": 5443, "Pretrain/Step Time": 8.45866216532886} +{"Pretrain/Learning Rate": 2.04990848998422e-05, "Pretrain/Loss": 2.024477005004883, "Pretrain/Loss (Raw)": 2.1170527935028076, "Pretrain/Step": 5444, "Pretrain/Step Time": 8.452426739037037} +{"Pretrain/Learning Rate": 2.0490733108913438e-05, "Pretrain/Loss": 2.025448799133301, "Pretrain/Loss (Raw)": 2.035491943359375, "Pretrain/Step": 5445, "Pretrain/Step Time": 8.450589193031192} +{"Pretrain/Learning Rate": 2.0482381838127036e-05, "Pretrain/Loss": 2.0241122245788574, "Pretrain/Loss (Raw)": 1.9651154279708862, "Pretrain/Step": 5446, "Pretrain/Step Time": 8.452161209657788} +{"Pretrain/Learning Rate": 2.0474031088446295e-05, "Pretrain/Loss": 2.024383068084717, "Pretrain/Loss (Raw)": 2.0714855194091797, "Pretrain/Step": 5447, "Pretrain/Step Time": 8.452335331588984} +{"Pretrain/Learning Rate": 2.0465680860834477e-05, "Pretrain/Loss": 2.023331642150879, "Pretrain/Loss (Raw)": 1.9574189186096191, "Pretrain/Step": 5448, "Pretrain/Step Time": 8.452934723347425} +{"Pretrain/Learning Rate": 2.0457331156254776e-05, "Pretrain/Loss": 2.0244927406311035, "Pretrain/Loss (Raw)": 2.2233388423919678, "Pretrain/Step": 5449, "Pretrain/Step Time": 8.454960964620113} +{"Pretrain/Learning Rate": 2.0448981975670338e-05, "Pretrain/Loss": 2.024057626724243, "Pretrain/Loss (Raw)": 1.9964405298233032, "Pretrain/Step": 5450, "Pretrain/Step Time": 8.454388225451112} +{"Pretrain/Learning Rate": 2.0440633320044225e-05, "Pretrain/Loss": 2.0239980220794678, "Pretrain/Loss (Raw)": 2.2328941822052, "Pretrain/Step": 5451, "Pretrain/Step Time": 8.45605332031846} +{"Pretrain/Learning Rate": 2.0432285190339453e-05, "Pretrain/Loss": 2.0245521068573, "Pretrain/Loss (Raw)": 2.0029492378234863, "Pretrain/Step": 5452, "Pretrain/Step Time": 8.459499726071954} +{"Pretrain/Learning Rate": 2.0423937587518987e-05, "Pretrain/Loss": 2.0255117416381836, "Pretrain/Loss (Raw)": 2.203462600708008, "Pretrain/Step": 5453, "Pretrain/Step Time": 8.4584971498698} +{"Pretrain/Learning Rate": 2.0415590512545705e-05, "Pretrain/Loss": 2.02620005607605, "Pretrain/Loss (Raw)": 2.03183913230896, "Pretrain/Step": 5454, "Pretrain/Step Time": 8.459440551698208} +{"Pretrain/Learning Rate": 2.0407243966382445e-05, "Pretrain/Loss": 2.026975154876709, "Pretrain/Loss (Raw)": 2.028834819793701, "Pretrain/Step": 5455, "Pretrain/Step Time": 8.454031888395548} +{"Pretrain/Learning Rate": 2.039889794999199e-05, "Pretrain/Loss": 2.027637243270874, "Pretrain/Loss (Raw)": 2.100255012512207, "Pretrain/Step": 5456, "Pretrain/Step Time": 8.454946711659431} +{"Pretrain/Learning Rate": 2.039055246433703e-05, "Pretrain/Loss": 2.0266904830932617, "Pretrain/Loss (Raw)": 1.985655426979065, "Pretrain/Step": 5457, "Pretrain/Step Time": 8.455249113962054} +{"Pretrain/Learning Rate": 2.0382207510380226e-05, "Pretrain/Loss": 2.0282254219055176, "Pretrain/Loss (Raw)": 1.9682385921478271, "Pretrain/Step": 5458, "Pretrain/Step Time": 8.45431081019342} +{"Pretrain/Learning Rate": 2.037386308908416e-05, "Pretrain/Loss": 2.027928352355957, "Pretrain/Loss (Raw)": 2.0074663162231445, "Pretrain/Step": 5459, "Pretrain/Step Time": 8.456856334581971} +{"Pretrain/Learning Rate": 2.0365519201411366e-05, "Pretrain/Loss": 2.0280065536499023, "Pretrain/Loss (Raw)": 2.0305533409118652, "Pretrain/Step": 5460, "Pretrain/Step Time": 8.455491540953517} +{"Pretrain/Learning Rate": 2.0357175848324307e-05, "Pretrain/Loss": 2.027585506439209, "Pretrain/Loss (Raw)": 1.9857521057128906, "Pretrain/Step": 5461, "Pretrain/Step Time": 8.447375647723675} +{"Pretrain/Learning Rate": 2.0348833030785376e-05, "Pretrain/Loss": 2.0273890495300293, "Pretrain/Loss (Raw)": 2.0333869457244873, "Pretrain/Step": 5462, "Pretrain/Step Time": 8.454430984333158} +{"Pretrain/Learning Rate": 2.0340490749756918e-05, "Pretrain/Loss": 2.0255682468414307, "Pretrain/Loss (Raw)": 1.8855410814285278, "Pretrain/Step": 5463, "Pretrain/Step Time": 8.452725049108267} +{"Pretrain/Learning Rate": 2.033214900620122e-05, "Pretrain/Loss": 2.0250186920166016, "Pretrain/Loss (Raw)": 1.9964700937271118, "Pretrain/Step": 5464, "Pretrain/Step Time": 8.445632562041283} +{"Pretrain/Learning Rate": 2.0323807801080484e-05, "Pretrain/Loss": 2.025785446166992, "Pretrain/Loss (Raw)": 2.1421165466308594, "Pretrain/Step": 5465, "Pretrain/Step Time": 8.447007620707154} +{"Pretrain/Learning Rate": 2.031546713535688e-05, "Pretrain/Loss": 2.0259952545166016, "Pretrain/Loss (Raw)": 1.984412431716919, "Pretrain/Step": 5466, "Pretrain/Step Time": 8.44674482010305} +{"Pretrain/Learning Rate": 2.0307127009992503e-05, "Pretrain/Loss": 2.025742530822754, "Pretrain/Loss (Raw)": 2.09559965133667, "Pretrain/Step": 5467, "Pretrain/Step Time": 8.445365780964494} +{"Pretrain/Learning Rate": 2.0298787425949373e-05, "Pretrain/Loss": 2.0237889289855957, "Pretrain/Loss (Raw)": 1.8970274925231934, "Pretrain/Step": 5468, "Pretrain/Step Time": 8.445500710979104} +{"Pretrain/Learning Rate": 2.0290448384189462e-05, "Pretrain/Loss": 2.021176338195801, "Pretrain/Loss (Raw)": 1.909376621246338, "Pretrain/Step": 5469, "Pretrain/Step Time": 8.446220442652702} +{"Pretrain/Learning Rate": 2.028210988567467e-05, "Pretrain/Loss": 2.0223307609558105, "Pretrain/Loss (Raw)": 2.1258599758148193, "Pretrain/Step": 5470, "Pretrain/Step Time": 8.443653898313642} +{"Pretrain/Learning Rate": 2.027377193136684e-05, "Pretrain/Loss": 2.0225698947906494, "Pretrain/Loss (Raw)": 2.0588674545288086, "Pretrain/Step": 5471, "Pretrain/Step Time": 8.443662647157907} +{"Pretrain/Learning Rate": 2.0265434522227776e-05, "Pretrain/Loss": 2.023397922515869, "Pretrain/Loss (Raw)": 2.017519950866699, "Pretrain/Step": 5472, "Pretrain/Step Time": 8.443866904824972} +{"Pretrain/Learning Rate": 2.025709765921916e-05, "Pretrain/Loss": 2.0223069190979004, "Pretrain/Loss (Raw)": 1.9651916027069092, "Pretrain/Step": 5473, "Pretrain/Step Time": 8.443361900746822} +{"Pretrain/Learning Rate": 2.0248761343302662e-05, "Pretrain/Loss": 2.0224452018737793, "Pretrain/Loss (Raw)": 2.061004400253296, "Pretrain/Step": 5474, "Pretrain/Step Time": 8.441501267254353} +{"Pretrain/Learning Rate": 2.0240425575439875e-05, "Pretrain/Loss": 2.0227246284484863, "Pretrain/Loss (Raw)": 2.084400177001953, "Pretrain/Step": 5475, "Pretrain/Step Time": 8.437147747725248} +{"Pretrain/Learning Rate": 2.023209035659233e-05, "Pretrain/Loss": 2.0219430923461914, "Pretrain/Loss (Raw)": 1.9485218524932861, "Pretrain/Step": 5476, "Pretrain/Step Time": 8.434731593355536} +{"Pretrain/Learning Rate": 2.0223755687721488e-05, "Pretrain/Loss": 2.023350238800049, "Pretrain/Loss (Raw)": 2.2387561798095703, "Pretrain/Step": 5477, "Pretrain/Step Time": 8.432792332023382} +{"Pretrain/Learning Rate": 2.0215421569788747e-05, "Pretrain/Loss": 2.0236716270446777, "Pretrain/Loss (Raw)": 2.143327236175537, "Pretrain/Step": 5478, "Pretrain/Step Time": 8.4397058673203} +{"Pretrain/Learning Rate": 2.020708800375544e-05, "Pretrain/Loss": 2.023245334625244, "Pretrain/Loss (Raw)": 1.9238699674606323, "Pretrain/Step": 5479, "Pretrain/Step Time": 8.43354774452746} +{"Pretrain/Learning Rate": 2.019875499058285e-05, "Pretrain/Loss": 2.0234813690185547, "Pretrain/Loss (Raw)": 2.0883402824401855, "Pretrain/Step": 5480, "Pretrain/Step Time": 8.43818779103458} +{"Pretrain/Learning Rate": 2.0190422531232186e-05, "Pretrain/Loss": 2.024038314819336, "Pretrain/Loss (Raw)": 1.9297051429748535, "Pretrain/Step": 5481, "Pretrain/Step Time": 8.43723444826901} +{"Pretrain/Learning Rate": 2.01820906266646e-05, "Pretrain/Loss": 2.024237632751465, "Pretrain/Loss (Raw)": 2.1018316745758057, "Pretrain/Step": 5482, "Pretrain/Step Time": 8.440439527854323} +{"Pretrain/Learning Rate": 2.017375927784116e-05, "Pretrain/Loss": 2.0263774394989014, "Pretrain/Loss (Raw)": 2.2517809867858887, "Pretrain/Step": 5483, "Pretrain/Step Time": 8.440937934443355} +{"Pretrain/Learning Rate": 2.016542848572289e-05, "Pretrain/Loss": 2.0269460678100586, "Pretrain/Loss (Raw)": 2.1518311500549316, "Pretrain/Step": 5484, "Pretrain/Step Time": 8.44158055819571} +{"Pretrain/Learning Rate": 2.015709825127075e-05, "Pretrain/Loss": 2.027682304382324, "Pretrain/Loss (Raw)": 2.08494234085083, "Pretrain/Step": 5485, "Pretrain/Step Time": 8.440130243077874} +{"Pretrain/Learning Rate": 2.0148768575445617e-05, "Pretrain/Loss": 2.0273756980895996, "Pretrain/Loss (Raw)": 1.9632954597473145, "Pretrain/Step": 5486, "Pretrain/Step Time": 8.441542342305183} +{"Pretrain/Learning Rate": 2.0140439459208326e-05, "Pretrain/Loss": 2.0283045768737793, "Pretrain/Loss (Raw)": 1.9793853759765625, "Pretrain/Step": 5487, "Pretrain/Step Time": 8.441203055903316} +{"Pretrain/Learning Rate": 2.0132110903519647e-05, "Pretrain/Loss": 2.0284769535064697, "Pretrain/Loss (Raw)": 2.0813262462615967, "Pretrain/Step": 5488, "Pretrain/Step Time": 8.440516894683242} +{"Pretrain/Learning Rate": 2.0123782909340257e-05, "Pretrain/Loss": 2.030179023742676, "Pretrain/Loss (Raw)": 2.094290256500244, "Pretrain/Step": 5489, "Pretrain/Step Time": 8.441380793228745} +{"Pretrain/Learning Rate": 2.011545547763079e-05, "Pretrain/Loss": 2.0298819541931152, "Pretrain/Loss (Raw)": 2.136082410812378, "Pretrain/Step": 5490, "Pretrain/Step Time": 8.441794851794839} +{"Pretrain/Learning Rate": 2.0107128609351815e-05, "Pretrain/Loss": 2.0287506580352783, "Pretrain/Loss (Raw)": 1.9790706634521484, "Pretrain/Step": 5491, "Pretrain/Step Time": 8.441172059625387} +{"Pretrain/Learning Rate": 2.0098802305463845e-05, "Pretrain/Loss": 2.028489589691162, "Pretrain/Loss (Raw)": 2.0611045360565186, "Pretrain/Step": 5492, "Pretrain/Step Time": 8.439182525500655} +{"Pretrain/Learning Rate": 2.0090476566927308e-05, "Pretrain/Loss": 2.028601884841919, "Pretrain/Loss (Raw)": 1.8999296426773071, "Pretrain/Step": 5493, "Pretrain/Step Time": 8.4379753023386} +{"Pretrain/Learning Rate": 2.0082151394702566e-05, "Pretrain/Loss": 2.0310263633728027, "Pretrain/Loss (Raw)": 2.2407052516937256, "Pretrain/Step": 5494, "Pretrain/Step Time": 8.4365268163383} +{"Pretrain/Learning Rate": 2.0073826789749937e-05, "Pretrain/Loss": 2.029743194580078, "Pretrain/Loss (Raw)": 1.8913078308105469, "Pretrain/Step": 5495, "Pretrain/Step Time": 8.439124017953873} +{"Pretrain/Learning Rate": 2.0065502753029653e-05, "Pretrain/Loss": 2.0323848724365234, "Pretrain/Loss (Raw)": 2.390315294265747, "Pretrain/Step": 5496, "Pretrain/Step Time": 8.435350803658366} +{"Pretrain/Learning Rate": 2.005717928550189e-05, "Pretrain/Loss": 2.032090663909912, "Pretrain/Loss (Raw)": 2.0512313842773438, "Pretrain/Step": 5497, "Pretrain/Step Time": 8.43502551689744} +{"Pretrain/Learning Rate": 2.0048856388126773e-05, "Pretrain/Loss": 2.033050060272217, "Pretrain/Loss (Raw)": 2.068774938583374, "Pretrain/Step": 5498, "Pretrain/Step Time": 8.438788071274757} +{"Pretrain/Learning Rate": 2.004053406186432e-05, "Pretrain/Loss": 2.0342330932617188, "Pretrain/Loss (Raw)": 2.029345750808716, "Pretrain/Step": 5499, "Pretrain/Step Time": 8.438877120614052} +{"Pretrain/Learning Rate": 2.0032212307674517e-05, "Pretrain/Loss": 2.0350489616394043, "Pretrain/Loss (Raw)": 2.005286455154419, "Pretrain/Step": 5500, "Pretrain/Step Time": 8.441118447110057} +{"Pretrain/Learning Rate": 2.002389112651728e-05, "Pretrain/Loss": 2.0360608100891113, "Pretrain/Loss (Raw)": 2.0878729820251465, "Pretrain/Step": 5501, "Pretrain/Step Time": 8.441126506775618} +{"Pretrain/Learning Rate": 2.001557051935246e-05, "Pretrain/Loss": 2.038900375366211, "Pretrain/Loss (Raw)": 2.025688886642456, "Pretrain/Step": 5502, "Pretrain/Step Time": 8.440886840224266} +{"Pretrain/Learning Rate": 2.000725048713983e-05, "Pretrain/Loss": 2.037142753601074, "Pretrain/Loss (Raw)": 1.9021838903427124, "Pretrain/Step": 5503, "Pretrain/Step Time": 8.441713212057948} +{"Pretrain/Learning Rate": 1.9998931030839098e-05, "Pretrain/Loss": 2.0359654426574707, "Pretrain/Loss (Raw)": 2.0646250247955322, "Pretrain/Step": 5504, "Pretrain/Step Time": 8.442642712965608} +{"Pretrain/Learning Rate": 1.9990612151409908e-05, "Pretrain/Loss": 2.039275646209717, "Pretrain/Loss (Raw)": 2.122792959213257, "Pretrain/Step": 5505, "Pretrain/Step Time": 8.44196549244225} +{"Pretrain/Learning Rate": 1.998229384981185e-05, "Pretrain/Loss": 2.0416364669799805, "Pretrain/Loss (Raw)": 2.237180471420288, "Pretrain/Step": 5506, "Pretrain/Step Time": 8.44385002925992} +{"Pretrain/Learning Rate": 1.9973976127004435e-05, "Pretrain/Loss": 2.042508840560913, "Pretrain/Loss (Raw)": 2.1700587272644043, "Pretrain/Step": 5507, "Pretrain/Step Time": 8.441822782158852} +{"Pretrain/Learning Rate": 1.99656589839471e-05, "Pretrain/Loss": 2.0426082611083984, "Pretrain/Loss (Raw)": 2.128171682357788, "Pretrain/Step": 5508, "Pretrain/Step Time": 8.438976475968957} +{"Pretrain/Learning Rate": 1.995734242159925e-05, "Pretrain/Loss": 2.0430068969726562, "Pretrain/Loss (Raw)": 2.1575849056243896, "Pretrain/Step": 5509, "Pretrain/Step Time": 8.438539192080498} +{"Pretrain/Learning Rate": 1.9949026440920164e-05, "Pretrain/Loss": 2.040309429168701, "Pretrain/Loss (Raw)": 1.7935290336608887, "Pretrain/Step": 5510, "Pretrain/Step Time": 8.443094991147518} +{"Pretrain/Learning Rate": 1.994071104286911e-05, "Pretrain/Loss": 2.0415215492248535, "Pretrain/Loss (Raw)": 2.0576789379119873, "Pretrain/Step": 5511, "Pretrain/Step Time": 8.437961999326944} +{"Pretrain/Learning Rate": 1.9932396228405255e-05, "Pretrain/Loss": 2.0410585403442383, "Pretrain/Loss (Raw)": 2.005150556564331, "Pretrain/Step": 5512, "Pretrain/Step Time": 8.442416148260236} +{"Pretrain/Learning Rate": 1.9924081998487716e-05, "Pretrain/Loss": 2.041876792907715, "Pretrain/Loss (Raw)": 2.083984613418579, "Pretrain/Step": 5513, "Pretrain/Step Time": 8.439371295273304} +{"Pretrain/Learning Rate": 1.991576835407554e-05, "Pretrain/Loss": 2.0412790775299072, "Pretrain/Loss (Raw)": 2.003749370574951, "Pretrain/Step": 5514, "Pretrain/Step Time": 8.443000938743353} +{"Pretrain/Learning Rate": 1.9907455296127688e-05, "Pretrain/Loss": 2.0399181842803955, "Pretrain/Loss (Raw)": 1.8828884363174438, "Pretrain/Step": 5515, "Pretrain/Step Time": 8.443990288302302} +{"Pretrain/Learning Rate": 1.989914282560308e-05, "Pretrain/Loss": 2.039496898651123, "Pretrain/Loss (Raw)": 1.9926847219467163, "Pretrain/Step": 5516, "Pretrain/Step Time": 8.442487731575966} +{"Pretrain/Learning Rate": 1.989083094346055e-05, "Pretrain/Loss": 2.0378565788269043, "Pretrain/Loss (Raw)": 1.937066674232483, "Pretrain/Step": 5517, "Pretrain/Step Time": 8.44380846992135} +{"Pretrain/Learning Rate": 1.988251965065889e-05, "Pretrain/Loss": 2.0365819931030273, "Pretrain/Loss (Raw)": 1.9187437295913696, "Pretrain/Step": 5518, "Pretrain/Step Time": 8.445437734946609} +{"Pretrain/Learning Rate": 1.9874208948156784e-05, "Pretrain/Loss": 2.0365707874298096, "Pretrain/Loss (Raw)": 1.9574778079986572, "Pretrain/Step": 5519, "Pretrain/Step Time": 8.447906045243144} +{"Pretrain/Learning Rate": 1.9865898836912876e-05, "Pretrain/Loss": 2.0361452102661133, "Pretrain/Loss (Raw)": 1.879870057106018, "Pretrain/Step": 5520, "Pretrain/Step Time": 8.4477111492306} +{"Pretrain/Learning Rate": 1.9857589317885723e-05, "Pretrain/Loss": 2.035543918609619, "Pretrain/Loss (Raw)": 2.0069100856781006, "Pretrain/Step": 5521, "Pretrain/Step Time": 8.449100906029344} +{"Pretrain/Learning Rate": 1.984928039203384e-05, "Pretrain/Loss": 2.033273696899414, "Pretrain/Loss (Raw)": 1.9393671751022339, "Pretrain/Step": 5522, "Pretrain/Step Time": 8.449310155585408} +{"Pretrain/Learning Rate": 1.9840972060315653e-05, "Pretrain/Loss": 2.033679962158203, "Pretrain/Loss (Raw)": 2.0879085063934326, "Pretrain/Step": 5523, "Pretrain/Step Time": 8.447311667725444} +{"Pretrain/Learning Rate": 1.9832664323689533e-05, "Pretrain/Loss": 2.0324251651763916, "Pretrain/Loss (Raw)": 1.8674671649932861, "Pretrain/Step": 5524, "Pretrain/Step Time": 8.44712371379137} +{"Pretrain/Learning Rate": 1.982435718311376e-05, "Pretrain/Loss": 2.0338640213012695, "Pretrain/Loss (Raw)": 2.0565884113311768, "Pretrain/Step": 5525, "Pretrain/Step Time": 8.446783600375056} +{"Pretrain/Learning Rate": 1.9816050639546567e-05, "Pretrain/Loss": 2.033214569091797, "Pretrain/Loss (Raw)": 1.9178276062011719, "Pretrain/Step": 5526, "Pretrain/Step Time": 8.447405315935612} +{"Pretrain/Learning Rate": 1.9807744693946115e-05, "Pretrain/Loss": 2.034419536590576, "Pretrain/Loss (Raw)": 2.1051599979400635, "Pretrain/Step": 5527, "Pretrain/Step Time": 8.444033272564411} +{"Pretrain/Learning Rate": 1.9799439347270483e-05, "Pretrain/Loss": 2.0358963012695312, "Pretrain/Loss (Raw)": 2.1979587078094482, "Pretrain/Step": 5528, "Pretrain/Step Time": 8.440959591418505} +{"Pretrain/Learning Rate": 1.9791134600477696e-05, "Pretrain/Loss": 2.036041498184204, "Pretrain/Loss (Raw)": 2.03535532951355, "Pretrain/Step": 5529, "Pretrain/Step Time": 8.44472766853869} +{"Pretrain/Learning Rate": 1.978283045452571e-05, "Pretrain/Loss": 2.037156343460083, "Pretrain/Loss (Raw)": 2.21976375579834, "Pretrain/Step": 5530, "Pretrain/Step Time": 8.446397069841623} +{"Pretrain/Learning Rate": 1.977452691037239e-05, "Pretrain/Loss": 2.0354809761047363, "Pretrain/Loss (Raw)": 2.0564746856689453, "Pretrain/Step": 5531, "Pretrain/Step Time": 8.445654449984431} +{"Pretrain/Learning Rate": 1.9766223968975554e-05, "Pretrain/Loss": 2.036410331726074, "Pretrain/Loss (Raw)": 2.090829610824585, "Pretrain/Step": 5532, "Pretrain/Step Time": 8.447110053151846} +{"Pretrain/Learning Rate": 1.975792163129294e-05, "Pretrain/Loss": 2.035595178604126, "Pretrain/Loss (Raw)": 1.9520395994186401, "Pretrain/Step": 5533, "Pretrain/Step Time": 8.446670012548566} +{"Pretrain/Learning Rate": 1.9749619898282235e-05, "Pretrain/Loss": 2.03588604927063, "Pretrain/Loss (Raw)": 2.0980639457702637, "Pretrain/Step": 5534, "Pretrain/Step Time": 8.446436056867242} +{"Pretrain/Learning Rate": 1.9741318770901026e-05, "Pretrain/Loss": 2.0377743244171143, "Pretrain/Loss (Raw)": 2.1792821884155273, "Pretrain/Step": 5535, "Pretrain/Step Time": 8.446499111130834} +{"Pretrain/Learning Rate": 1.973301825010685e-05, "Pretrain/Loss": 2.0367238521575928, "Pretrain/Loss (Raw)": 1.805314302444458, "Pretrain/Step": 5536, "Pretrain/Step Time": 8.446756983175874} +{"Pretrain/Learning Rate": 1.9724718336857163e-05, "Pretrain/Loss": 2.0357067584991455, "Pretrain/Loss (Raw)": 2.0337741374969482, "Pretrain/Step": 5537, "Pretrain/Step Time": 8.444749811664224} +{"Pretrain/Learning Rate": 1.971641903210936e-05, "Pretrain/Loss": 2.0341436862945557, "Pretrain/Loss (Raw)": 1.884478211402893, "Pretrain/Step": 5538, "Pretrain/Step Time": 8.445260297507048} +{"Pretrain/Learning Rate": 1.9708120336820764e-05, "Pretrain/Loss": 2.035790205001831, "Pretrain/Loss (Raw)": 2.192279100418091, "Pretrain/Step": 5539, "Pretrain/Step Time": 8.44017350114882} +{"Pretrain/Learning Rate": 1.969982225194864e-05, "Pretrain/Loss": 2.0356853008270264, "Pretrain/Loss (Raw)": 1.9626736640930176, "Pretrain/Step": 5540, "Pretrain/Step Time": 8.440369857475162} +{"Pretrain/Learning Rate": 1.9691524778450145e-05, "Pretrain/Loss": 2.036146640777588, "Pretrain/Loss (Raw)": 2.009782314300537, "Pretrain/Step": 5541, "Pretrain/Step Time": 8.441435258835554} +{"Pretrain/Learning Rate": 1.9683227917282403e-05, "Pretrain/Loss": 2.0364890098571777, "Pretrain/Loss (Raw)": 2.0988879203796387, "Pretrain/Step": 5542, "Pretrain/Step Time": 8.440561804920435} +{"Pretrain/Learning Rate": 1.9674931669402452e-05, "Pretrain/Loss": 2.0383429527282715, "Pretrain/Loss (Raw)": 2.0066795349121094, "Pretrain/Step": 5543, "Pretrain/Step Time": 8.438221473246813} +{"Pretrain/Learning Rate": 1.9666636035767265e-05, "Pretrain/Loss": 2.037177801132202, "Pretrain/Loss (Raw)": 1.9483156204223633, "Pretrain/Step": 5544, "Pretrain/Step Time": 8.440437156707048} +{"Pretrain/Learning Rate": 1.9658341017333736e-05, "Pretrain/Loss": 2.0382537841796875, "Pretrain/Loss (Raw)": 2.01889967918396, "Pretrain/Step": 5545, "Pretrain/Step Time": 8.439340924844146} +{"Pretrain/Learning Rate": 1.96500466150587e-05, "Pretrain/Loss": 2.0379509925842285, "Pretrain/Loss (Raw)": 1.9833669662475586, "Pretrain/Step": 5546, "Pretrain/Step Time": 8.441212115809321} +{"Pretrain/Learning Rate": 1.9641752829898898e-05, "Pretrain/Loss": 2.0365941524505615, "Pretrain/Loss (Raw)": 2.031451940536499, "Pretrain/Step": 5547, "Pretrain/Step Time": 8.443451344966888} +{"Pretrain/Learning Rate": 1.9633459662811025e-05, "Pretrain/Loss": 2.035470485687256, "Pretrain/Loss (Raw)": 2.0140209197998047, "Pretrain/Step": 5548, "Pretrain/Step Time": 8.444425171241164} +{"Pretrain/Learning Rate": 1.962516711475169e-05, "Pretrain/Loss": 2.0327491760253906, "Pretrain/Loss (Raw)": 1.9211846590042114, "Pretrain/Step": 5549, "Pretrain/Step Time": 8.444183979183435} +{"Pretrain/Learning Rate": 1.9616875186677442e-05, "Pretrain/Loss": 2.034989833831787, "Pretrain/Loss (Raw)": 2.1634907722473145, "Pretrain/Step": 5550, "Pretrain/Step Time": 8.442817345261574} +{"Pretrain/Learning Rate": 1.9608583879544763e-05, "Pretrain/Loss": 2.035038948059082, "Pretrain/Loss (Raw)": 2.0453877449035645, "Pretrain/Step": 5551, "Pretrain/Step Time": 8.445297429338098} +{"Pretrain/Learning Rate": 1.9600293194310022e-05, "Pretrain/Loss": 2.0346314907073975, "Pretrain/Loss (Raw)": 2.0454845428466797, "Pretrain/Step": 5552, "Pretrain/Step Time": 8.445741863921285} +{"Pretrain/Learning Rate": 1.9592003131929572e-05, "Pretrain/Loss": 2.0343403816223145, "Pretrain/Loss (Raw)": 1.9044750928878784, "Pretrain/Step": 5553, "Pretrain/Step Time": 8.44525488652289} +{"Pretrain/Learning Rate": 1.9583713693359655e-05, "Pretrain/Loss": 2.0354933738708496, "Pretrain/Loss (Raw)": 2.104349136352539, "Pretrain/Step": 5554, "Pretrain/Step Time": 8.448254078626633} +{"Pretrain/Learning Rate": 1.9575424879556462e-05, "Pretrain/Loss": 2.0367324352264404, "Pretrain/Loss (Raw)": 2.0526514053344727, "Pretrain/Step": 5555, "Pretrain/Step Time": 8.446423649787903} +{"Pretrain/Learning Rate": 1.956713669147611e-05, "Pretrain/Loss": 2.038064479827881, "Pretrain/Loss (Raw)": 2.019885778427124, "Pretrain/Step": 5556, "Pretrain/Step Time": 8.445860723033547} +{"Pretrain/Learning Rate": 1.9558849130074622e-05, "Pretrain/Loss": 2.0394093990325928, "Pretrain/Loss (Raw)": 2.1929514408111572, "Pretrain/Step": 5557, "Pretrain/Step Time": 8.445200270041823} +{"Pretrain/Learning Rate": 1.9550562196307975e-05, "Pretrain/Loss": 2.037595272064209, "Pretrain/Loss (Raw)": 1.643389344215393, "Pretrain/Step": 5558, "Pretrain/Step Time": 8.443216810002923} +{"Pretrain/Learning Rate": 1.9542275891132063e-05, "Pretrain/Loss": 2.0360822677612305, "Pretrain/Loss (Raw)": 2.020278215408325, "Pretrain/Step": 5559, "Pretrain/Step Time": 8.442690031602979} +{"Pretrain/Learning Rate": 1.9533990215502714e-05, "Pretrain/Loss": 2.035660982131958, "Pretrain/Loss (Raw)": 2.056459426879883, "Pretrain/Step": 5560, "Pretrain/Step Time": 8.434135861694813} +{"Pretrain/Learning Rate": 1.9525705170375675e-05, "Pretrain/Loss": 2.0352530479431152, "Pretrain/Loss (Raw)": 2.050712823867798, "Pretrain/Step": 5561, "Pretrain/Step Time": 8.43811851926148} +{"Pretrain/Learning Rate": 1.951742075670662e-05, "Pretrain/Loss": 2.03495454788208, "Pretrain/Loss (Raw)": 2.0101616382598877, "Pretrain/Step": 5562, "Pretrain/Step Time": 8.439178735017776} +{"Pretrain/Learning Rate": 1.950913697545115e-05, "Pretrain/Loss": 2.031435012817383, "Pretrain/Loss (Raw)": 1.5220180749893188, "Pretrain/Step": 5563, "Pretrain/Step Time": 8.442127684131265} +{"Pretrain/Learning Rate": 1.9500853827564793e-05, "Pretrain/Loss": 2.032335042953491, "Pretrain/Loss (Raw)": 2.1381447315216064, "Pretrain/Step": 5564, "Pretrain/Step Time": 8.444772927090526} +{"Pretrain/Learning Rate": 1.9492571314003022e-05, "Pretrain/Loss": 2.031902313232422, "Pretrain/Loss (Raw)": 1.9425019025802612, "Pretrain/Step": 5565, "Pretrain/Step Time": 8.445843229070306} +{"Pretrain/Learning Rate": 1.948428943572121e-05, "Pretrain/Loss": 2.03334379196167, "Pretrain/Loss (Raw)": 2.215503692626953, "Pretrain/Step": 5566, "Pretrain/Step Time": 8.445235280320048} +{"Pretrain/Learning Rate": 1.947600819367469e-05, "Pretrain/Loss": 2.033405303955078, "Pretrain/Loss (Raw)": 2.0872750282287598, "Pretrain/Step": 5567, "Pretrain/Step Time": 8.446095334365964} +{"Pretrain/Learning Rate": 1.9467727588818667e-05, "Pretrain/Loss": 2.031168222427368, "Pretrain/Loss (Raw)": 1.8504170179367065, "Pretrain/Step": 5568, "Pretrain/Step Time": 8.44843235053122} +{"Pretrain/Learning Rate": 1.945944762210833e-05, "Pretrain/Loss": 2.0315418243408203, "Pretrain/Loss (Raw)": 2.0545926094055176, "Pretrain/Step": 5569, "Pretrain/Step Time": 8.448145769536495} +{"Pretrain/Learning Rate": 1.9451168294498756e-05, "Pretrain/Loss": 2.0313148498535156, "Pretrain/Loss (Raw)": 1.9735461473464966, "Pretrain/Step": 5570, "Pretrain/Step Time": 8.450190154835582} +{"Pretrain/Learning Rate": 1.9442889606944968e-05, "Pretrain/Loss": 2.0339465141296387, "Pretrain/Loss (Raw)": 2.1850106716156006, "Pretrain/Step": 5571, "Pretrain/Step Time": 8.445715827867389} +{"Pretrain/Learning Rate": 1.9434611560401926e-05, "Pretrain/Loss": 2.0322561264038086, "Pretrain/Loss (Raw)": 1.900683879852295, "Pretrain/Step": 5572, "Pretrain/Step Time": 8.445399997755885} +{"Pretrain/Learning Rate": 1.942633415582447e-05, "Pretrain/Loss": 2.0329532623291016, "Pretrain/Loss (Raw)": 2.12471604347229, "Pretrain/Step": 5573, "Pretrain/Step Time": 8.446661900728941} +{"Pretrain/Learning Rate": 1.9418057394167418e-05, "Pretrain/Loss": 2.029473304748535, "Pretrain/Loss (Raw)": 1.5196620225906372, "Pretrain/Step": 5574, "Pretrain/Step Time": 8.441611133515835} +{"Pretrain/Learning Rate": 1.9409781276385475e-05, "Pretrain/Loss": 2.0295844078063965, "Pretrain/Loss (Raw)": 2.085733413696289, "Pretrain/Step": 5575, "Pretrain/Step Time": 8.442378519102931} +{"Pretrain/Learning Rate": 1.9401505803433306e-05, "Pretrain/Loss": 2.029561758041382, "Pretrain/Loss (Raw)": 1.9545131921768188, "Pretrain/Step": 5576, "Pretrain/Step Time": 8.43627092987299} +{"Pretrain/Learning Rate": 1.9393230976265473e-05, "Pretrain/Loss": 2.028207778930664, "Pretrain/Loss (Raw)": 2.0500235557556152, "Pretrain/Step": 5577, "Pretrain/Step Time": 8.439747141674161} +{"Pretrain/Learning Rate": 1.938495679583648e-05, "Pretrain/Loss": 2.0261378288269043, "Pretrain/Loss (Raw)": 1.7314810752868652, "Pretrain/Step": 5578, "Pretrain/Step Time": 8.44110788591206} +{"Pretrain/Learning Rate": 1.9376683263100743e-05, "Pretrain/Loss": 2.0241756439208984, "Pretrain/Loss (Raw)": 1.9817548990249634, "Pretrain/Step": 5579, "Pretrain/Step Time": 8.442407982423902} +{"Pretrain/Learning Rate": 1.936841037901261e-05, "Pretrain/Loss": 2.02388334274292, "Pretrain/Loss (Raw)": 1.9655147790908813, "Pretrain/Step": 5580, "Pretrain/Step Time": 8.439596816897392} +{"Pretrain/Learning Rate": 1.9360138144526364e-05, "Pretrain/Loss": 2.0235626697540283, "Pretrain/Loss (Raw)": 2.1624503135681152, "Pretrain/Step": 5581, "Pretrain/Step Time": 8.439941134303808} +{"Pretrain/Learning Rate": 1.935186656059621e-05, "Pretrain/Loss": 2.024362802505493, "Pretrain/Loss (Raw)": 2.1342291831970215, "Pretrain/Step": 5582, "Pretrain/Step Time": 8.441293379291892} +{"Pretrain/Learning Rate": 1.9343595628176254e-05, "Pretrain/Loss": 2.0249266624450684, "Pretrain/Loss (Raw)": 2.1010351181030273, "Pretrain/Step": 5583, "Pretrain/Step Time": 8.443890796974301} +{"Pretrain/Learning Rate": 1.9335325348220557e-05, "Pretrain/Loss": 2.0253665447235107, "Pretrain/Loss (Raw)": 2.1565425395965576, "Pretrain/Step": 5584, "Pretrain/Step Time": 8.443243144080043} +{"Pretrain/Learning Rate": 1.9327055721683086e-05, "Pretrain/Loss": 2.0248870849609375, "Pretrain/Loss (Raw)": 1.924314260482788, "Pretrain/Step": 5585, "Pretrain/Step Time": 8.444893587380648} +{"Pretrain/Learning Rate": 1.9318786749517755e-05, "Pretrain/Loss": 2.0248522758483887, "Pretrain/Loss (Raw)": 1.9637541770935059, "Pretrain/Step": 5586, "Pretrain/Step Time": 8.444019926711917} +{"Pretrain/Learning Rate": 1.9310518432678365e-05, "Pretrain/Loss": 2.023881196975708, "Pretrain/Loss (Raw)": 1.8831511735916138, "Pretrain/Step": 5587, "Pretrain/Step Time": 8.440047636628151} +{"Pretrain/Learning Rate": 1.9302250772118687e-05, "Pretrain/Loss": 2.0241873264312744, "Pretrain/Loss (Raw)": 2.06974720954895, "Pretrain/Step": 5588, "Pretrain/Step Time": 8.440596802160144} +{"Pretrain/Learning Rate": 1.9293983768792367e-05, "Pretrain/Loss": 2.0248193740844727, "Pretrain/Loss (Raw)": 2.0666418075561523, "Pretrain/Step": 5589, "Pretrain/Step Time": 8.44259812310338} +{"Pretrain/Learning Rate": 1.9285717423653016e-05, "Pretrain/Loss": 2.025923490524292, "Pretrain/Loss (Raw)": 2.174717903137207, "Pretrain/Step": 5590, "Pretrain/Step Time": 8.435708863660693} +{"Pretrain/Learning Rate": 1.9277451737654152e-05, "Pretrain/Loss": 2.0269455909729004, "Pretrain/Loss (Raw)": 2.0164053440093994, "Pretrain/Step": 5591, "Pretrain/Step Time": 8.438922422006726} +{"Pretrain/Learning Rate": 1.9269186711749223e-05, "Pretrain/Loss": 2.0267715454101562, "Pretrain/Loss (Raw)": 1.974158525466919, "Pretrain/Step": 5592, "Pretrain/Step Time": 8.44028757326305} +{"Pretrain/Learning Rate": 1.9260922346891597e-05, "Pretrain/Loss": 2.0259361267089844, "Pretrain/Loss (Raw)": 2.0351877212524414, "Pretrain/Step": 5593, "Pretrain/Step Time": 8.438797574490309} +{"Pretrain/Learning Rate": 1.9252658644034554e-05, "Pretrain/Loss": 2.025712013244629, "Pretrain/Loss (Raw)": 1.95571768283844, "Pretrain/Step": 5594, "Pretrain/Step Time": 8.440854886546731} +{"Pretrain/Learning Rate": 1.9244395604131323e-05, "Pretrain/Loss": 2.0243494510650635, "Pretrain/Loss (Raw)": 1.9212150573730469, "Pretrain/Step": 5595, "Pretrain/Step Time": 8.44039292447269} +{"Pretrain/Learning Rate": 1.9236133228135027e-05, "Pretrain/Loss": 2.02496075630188, "Pretrain/Loss (Raw)": 1.9752616882324219, "Pretrain/Step": 5596, "Pretrain/Step Time": 8.445348305627704} +{"Pretrain/Learning Rate": 1.922787151699874e-05, "Pretrain/Loss": 2.024754524230957, "Pretrain/Loss (Raw)": 1.88300621509552, "Pretrain/Step": 5597, "Pretrain/Step Time": 8.444671347737312} +{"Pretrain/Learning Rate": 1.921961047167546e-05, "Pretrain/Loss": 2.0229291915893555, "Pretrain/Loss (Raw)": 1.8921778202056885, "Pretrain/Step": 5598, "Pretrain/Step Time": 8.444863267242908} +{"Pretrain/Learning Rate": 1.9211350093118063e-05, "Pretrain/Loss": 2.0233583450317383, "Pretrain/Loss (Raw)": 2.1138412952423096, "Pretrain/Step": 5599, "Pretrain/Step Time": 8.446985650807619} +{"Pretrain/Learning Rate": 1.92030903822794e-05, "Pretrain/Loss": 2.023348331451416, "Pretrain/Loss (Raw)": 2.0162429809570312, "Pretrain/Step": 5600, "Pretrain/Step Time": 8.449160885065794} +{"Pretrain/Learning Rate": 1.9194831340112225e-05, "Pretrain/Loss": 2.02401065826416, "Pretrain/Loss (Raw)": 2.0499184131622314, "Pretrain/Step": 5601, "Pretrain/Step Time": 8.450547683984041} +{"Pretrain/Learning Rate": 1.9186572967569222e-05, "Pretrain/Loss": 2.0240728855133057, "Pretrain/Loss (Raw)": 2.0689897537231445, "Pretrain/Step": 5602, "Pretrain/Step Time": 8.450253043323755} +{"Pretrain/Learning Rate": 1.9178315265602983e-05, "Pretrain/Loss": 2.0225870609283447, "Pretrain/Loss (Raw)": 1.894219160079956, "Pretrain/Step": 5603, "Pretrain/Step Time": 8.449431309476495} +{"Pretrain/Learning Rate": 1.9170058235166033e-05, "Pretrain/Loss": 2.024991989135742, "Pretrain/Loss (Raw)": 2.2563657760620117, "Pretrain/Step": 5604, "Pretrain/Step Time": 8.449048262089491} +{"Pretrain/Learning Rate": 1.916180187721081e-05, "Pretrain/Loss": 2.022998332977295, "Pretrain/Loss (Raw)": 1.983535647392273, "Pretrain/Step": 5605, "Pretrain/Step Time": 8.447551736608148} +{"Pretrain/Learning Rate": 1.9153546192689694e-05, "Pretrain/Loss": 2.021501064300537, "Pretrain/Loss (Raw)": 1.9516764879226685, "Pretrain/Step": 5606, "Pretrain/Step Time": 8.441183675080538} +{"Pretrain/Learning Rate": 1.914529118255496e-05, "Pretrain/Loss": 2.0223965644836426, "Pretrain/Loss (Raw)": 2.0385348796844482, "Pretrain/Step": 5607, "Pretrain/Step Time": 8.444714611396194} +{"Pretrain/Learning Rate": 1.913703684775884e-05, "Pretrain/Loss": 2.0223350524902344, "Pretrain/Loss (Raw)": 2.0804643630981445, "Pretrain/Step": 5608, "Pretrain/Step Time": 8.443612998351455} +{"Pretrain/Learning Rate": 1.912878318925346e-05, "Pretrain/Loss": 2.0242514610290527, "Pretrain/Loss (Raw)": 2.174980878829956, "Pretrain/Step": 5609, "Pretrain/Step Time": 8.446080259978771} +{"Pretrain/Learning Rate": 1.9120530207990875e-05, "Pretrain/Loss": 2.0239927768707275, "Pretrain/Loss (Raw)": 2.068723678588867, "Pretrain/Step": 5610, "Pretrain/Step Time": 8.443992674350739} +{"Pretrain/Learning Rate": 1.9112277904923065e-05, "Pretrain/Loss": 2.0218636989593506, "Pretrain/Loss (Raw)": 1.9792646169662476, "Pretrain/Step": 5611, "Pretrain/Step Time": 8.444457925856113} +{"Pretrain/Learning Rate": 1.9104026281001926e-05, "Pretrain/Loss": 2.021287441253662, "Pretrain/Loss (Raw)": 2.0780928134918213, "Pretrain/Step": 5612, "Pretrain/Step Time": 8.446992494165897} +{"Pretrain/Learning Rate": 1.9095775337179282e-05, "Pretrain/Loss": 2.021350383758545, "Pretrain/Loss (Raw)": 2.09298038482666, "Pretrain/Step": 5613, "Pretrain/Step Time": 8.449686899781227} +{"Pretrain/Learning Rate": 1.908752507440689e-05, "Pretrain/Loss": 2.0219268798828125, "Pretrain/Loss (Raw)": 2.037083864212036, "Pretrain/Step": 5614, "Pretrain/Step Time": 8.448988316580653} +{"Pretrain/Learning Rate": 1.9079275493636392e-05, "Pretrain/Loss": 2.021829605102539, "Pretrain/Loss (Raw)": 1.9669189453125, "Pretrain/Step": 5615, "Pretrain/Step Time": 8.451162431389093} +{"Pretrain/Learning Rate": 1.9071026595819386e-05, "Pretrain/Loss": 2.0205235481262207, "Pretrain/Loss (Raw)": 1.9141756296157837, "Pretrain/Step": 5616, "Pretrain/Step Time": 8.45183408074081} +{"Pretrain/Learning Rate": 1.9062778381907376e-05, "Pretrain/Loss": 2.0184316635131836, "Pretrain/Loss (Raw)": 1.8265079259872437, "Pretrain/Step": 5617, "Pretrain/Step Time": 8.454317765310407} +{"Pretrain/Learning Rate": 1.90545308528518e-05, "Pretrain/Loss": 2.018655300140381, "Pretrain/Loss (Raw)": 2.1647064685821533, "Pretrain/Step": 5618, "Pretrain/Step Time": 8.454373963177204} +{"Pretrain/Learning Rate": 1.9046284009604e-05, "Pretrain/Loss": 2.0183258056640625, "Pretrain/Loss (Raw)": 1.9369182586669922, "Pretrain/Step": 5619, "Pretrain/Step Time": 8.45344090461731} +{"Pretrain/Learning Rate": 1.9038037853115248e-05, "Pretrain/Loss": 2.018343687057495, "Pretrain/Loss (Raw)": 2.063394546508789, "Pretrain/Step": 5620, "Pretrain/Step Time": 8.455221770331264} +{"Pretrain/Learning Rate": 1.9029792384336728e-05, "Pretrain/Loss": 2.020627975463867, "Pretrain/Loss (Raw)": 2.1922976970672607, "Pretrain/Step": 5621, "Pretrain/Step Time": 8.454718558117747} +{"Pretrain/Learning Rate": 1.9021547604219558e-05, "Pretrain/Loss": 2.019132614135742, "Pretrain/Loss (Raw)": 2.0492827892303467, "Pretrain/Step": 5622, "Pretrain/Step Time": 8.449125608429313} +{"Pretrain/Learning Rate": 1.9013303513714774e-05, "Pretrain/Loss": 2.0208899974823, "Pretrain/Loss (Raw)": 2.1162898540496826, "Pretrain/Step": 5623, "Pretrain/Step Time": 8.446980152279139} +{"Pretrain/Learning Rate": 1.9005060113773333e-05, "Pretrain/Loss": 2.016676902770996, "Pretrain/Loss (Raw)": 1.851038932800293, "Pretrain/Step": 5624, "Pretrain/Step Time": 8.448288720101118} +{"Pretrain/Learning Rate": 1.8996817405346093e-05, "Pretrain/Loss": 2.0152225494384766, "Pretrain/Loss (Raw)": 1.8650624752044678, "Pretrain/Step": 5625, "Pretrain/Step Time": 8.450969560071826} +{"Pretrain/Learning Rate": 1.8988575389383853e-05, "Pretrain/Loss": 2.014862060546875, "Pretrain/Loss (Raw)": 2.0226283073425293, "Pretrain/Step": 5626, "Pretrain/Step Time": 8.44642118923366} +{"Pretrain/Learning Rate": 1.8980334066837332e-05, "Pretrain/Loss": 2.0136518478393555, "Pretrain/Loss (Raw)": 1.8744268417358398, "Pretrain/Step": 5627, "Pretrain/Step Time": 8.450039513409138} +{"Pretrain/Learning Rate": 1.8972093438657166e-05, "Pretrain/Loss": 2.0141196250915527, "Pretrain/Loss (Raw)": 2.0651793479919434, "Pretrain/Step": 5628, "Pretrain/Step Time": 8.448419457301497} +{"Pretrain/Learning Rate": 1.8963853505793898e-05, "Pretrain/Loss": 2.013833522796631, "Pretrain/Loss (Raw)": 2.051231622695923, "Pretrain/Step": 5629, "Pretrain/Step Time": 8.453687923029065} +{"Pretrain/Learning Rate": 1.8955614269198015e-05, "Pretrain/Loss": 2.0131349563598633, "Pretrain/Loss (Raw)": 1.936303734779358, "Pretrain/Step": 5630, "Pretrain/Step Time": 8.453100746497512} +{"Pretrain/Learning Rate": 1.8947375729819894e-05, "Pretrain/Loss": 2.0133581161499023, "Pretrain/Loss (Raw)": 1.9307652711868286, "Pretrain/Step": 5631, "Pretrain/Step Time": 8.45503249578178} +{"Pretrain/Learning Rate": 1.8939137888609855e-05, "Pretrain/Loss": 2.0149784088134766, "Pretrain/Loss (Raw)": 2.2719733715057373, "Pretrain/Step": 5632, "Pretrain/Step Time": 8.45540714263916} +{"Pretrain/Learning Rate": 1.8930900746518128e-05, "Pretrain/Loss": 2.0125699043273926, "Pretrain/Loss (Raw)": 1.8145281076431274, "Pretrain/Step": 5633, "Pretrain/Step Time": 8.458060137927532} +{"Pretrain/Learning Rate": 1.892266430449487e-05, "Pretrain/Loss": 2.012368679046631, "Pretrain/Loss (Raw)": 2.2114288806915283, "Pretrain/Step": 5634, "Pretrain/Step Time": 8.45627411082387} +{"Pretrain/Learning Rate": 1.891442856349016e-05, "Pretrain/Loss": 2.011305809020996, "Pretrain/Loss (Raw)": 2.0340325832366943, "Pretrain/Step": 5635, "Pretrain/Step Time": 8.459533954039216} +{"Pretrain/Learning Rate": 1.8906193524453964e-05, "Pretrain/Loss": 2.010160446166992, "Pretrain/Loss (Raw)": 1.9815595149993896, "Pretrain/Step": 5636, "Pretrain/Step Time": 8.459128702059388} +{"Pretrain/Learning Rate": 1.8897959188336206e-05, "Pretrain/Loss": 2.009190559387207, "Pretrain/Loss (Raw)": 2.033438205718994, "Pretrain/Step": 5637, "Pretrain/Step Time": 8.456980427727103} +{"Pretrain/Learning Rate": 1.8889725556086713e-05, "Pretrain/Loss": 2.010067939758301, "Pretrain/Loss (Raw)": 1.905781865119934, "Pretrain/Step": 5638, "Pretrain/Step Time": 8.454894870519638} +{"Pretrain/Learning Rate": 1.8881492628655223e-05, "Pretrain/Loss": 2.010096549987793, "Pretrain/Loss (Raw)": 2.0613958835601807, "Pretrain/Step": 5639, "Pretrain/Step Time": 8.456144971773028} +{"Pretrain/Learning Rate": 1.887326040699142e-05, "Pretrain/Loss": 2.010828971862793, "Pretrain/Loss (Raw)": 2.0988574028015137, "Pretrain/Step": 5640, "Pretrain/Step Time": 8.450598053634167} +{"Pretrain/Learning Rate": 1.886502889204487e-05, "Pretrain/Loss": 2.0090057849884033, "Pretrain/Loss (Raw)": 1.8506231307983398, "Pretrain/Step": 5641, "Pretrain/Step Time": 8.44884805008769} +{"Pretrain/Learning Rate": 1.8856798084765077e-05, "Pretrain/Loss": 2.0089054107666016, "Pretrain/Loss (Raw)": 1.9909130334854126, "Pretrain/Step": 5642, "Pretrain/Step Time": 8.444244299083948} +{"Pretrain/Learning Rate": 1.8848567986101467e-05, "Pretrain/Loss": 2.01086688041687, "Pretrain/Loss (Raw)": 2.133964776992798, "Pretrain/Step": 5643, "Pretrain/Step Time": 8.443296743556857} +{"Pretrain/Learning Rate": 1.8840338597003384e-05, "Pretrain/Loss": 2.0102548599243164, "Pretrain/Loss (Raw)": 1.9143314361572266, "Pretrain/Step": 5644, "Pretrain/Step Time": 8.44537248276174} +{"Pretrain/Learning Rate": 1.8832109918420074e-05, "Pretrain/Loss": 2.010594367980957, "Pretrain/Loss (Raw)": 1.9805448055267334, "Pretrain/Step": 5645, "Pretrain/Step Time": 8.443804301321507} +{"Pretrain/Learning Rate": 1.8823881951300727e-05, "Pretrain/Loss": 2.01182222366333, "Pretrain/Loss (Raw)": 2.0758848190307617, "Pretrain/Step": 5646, "Pretrain/Step Time": 8.448017532005906} +{"Pretrain/Learning Rate": 1.8815654696594418e-05, "Pretrain/Loss": 2.012521505355835, "Pretrain/Loss (Raw)": 2.047008514404297, "Pretrain/Step": 5647, "Pretrain/Step Time": 8.443275371566415} +{"Pretrain/Learning Rate": 1.8807428155250164e-05, "Pretrain/Loss": 2.014603614807129, "Pretrain/Loss (Raw)": 2.1463851928710938, "Pretrain/Step": 5648, "Pretrain/Step Time": 8.444917282089591} +{"Pretrain/Learning Rate": 1.87992023282169e-05, "Pretrain/Loss": 2.014437198638916, "Pretrain/Loss (Raw)": 1.985575556755066, "Pretrain/Step": 5649, "Pretrain/Step Time": 8.449974492192268} +{"Pretrain/Learning Rate": 1.879097721644346e-05, "Pretrain/Loss": 2.015958786010742, "Pretrain/Loss (Raw)": 2.1341440677642822, "Pretrain/Step": 5650, "Pretrain/Step Time": 8.44869307987392} +{"Pretrain/Learning Rate": 1.8782752820878634e-05, "Pretrain/Loss": 2.0158638954162598, "Pretrain/Loss (Raw)": 2.0757787227630615, "Pretrain/Step": 5651, "Pretrain/Step Time": 8.446904584765434} +{"Pretrain/Learning Rate": 1.8774529142471074e-05, "Pretrain/Loss": 2.0157885551452637, "Pretrain/Loss (Raw)": 1.857812523841858, "Pretrain/Step": 5652, "Pretrain/Step Time": 8.446001429110765} +{"Pretrain/Learning Rate": 1.8766306182169394e-05, "Pretrain/Loss": 2.0149426460266113, "Pretrain/Loss (Raw)": 1.9483333826065063, "Pretrain/Step": 5653, "Pretrain/Step Time": 8.444764381274581} +{"Pretrain/Learning Rate": 1.87580839409221e-05, "Pretrain/Loss": 2.0160670280456543, "Pretrain/Loss (Raw)": 2.061701536178589, "Pretrain/Step": 5654, "Pretrain/Step Time": 8.44404911249876} +{"Pretrain/Learning Rate": 1.8749862419677626e-05, "Pretrain/Loss": 2.0152196884155273, "Pretrain/Loss (Raw)": 1.9967156648635864, "Pretrain/Step": 5655, "Pretrain/Step Time": 8.443803252652287} +{"Pretrain/Learning Rate": 1.874164161938434e-05, "Pretrain/Loss": 2.0139026641845703, "Pretrain/Loss (Raw)": 2.029362678527832, "Pretrain/Step": 5656, "Pretrain/Step Time": 8.44701418466866} +{"Pretrain/Learning Rate": 1.8733421540990484e-05, "Pretrain/Loss": 2.0143508911132812, "Pretrain/Loss (Raw)": 2.0927488803863525, "Pretrain/Step": 5657, "Pretrain/Step Time": 8.445699395611882} +{"Pretrain/Learning Rate": 1.8725202185444247e-05, "Pretrain/Loss": 2.0118985176086426, "Pretrain/Loss (Raw)": 1.9058517217636108, "Pretrain/Step": 5658, "Pretrain/Step Time": 8.442880030721426} +{"Pretrain/Learning Rate": 1.8716983553693736e-05, "Pretrain/Loss": 2.0116615295410156, "Pretrain/Loss (Raw)": 2.026148557662964, "Pretrain/Step": 5659, "Pretrain/Step Time": 8.443089397624135} +{"Pretrain/Learning Rate": 1.8708765646686972e-05, "Pretrain/Loss": 2.0089879035949707, "Pretrain/Loss (Raw)": 1.7485960721969604, "Pretrain/Step": 5660, "Pretrain/Step Time": 8.44564476236701} +{"Pretrain/Learning Rate": 1.8700548465371874e-05, "Pretrain/Loss": 2.0101678371429443, "Pretrain/Loss (Raw)": 2.1030712127685547, "Pretrain/Step": 5661, "Pretrain/Step Time": 8.446653578430414} +{"Pretrain/Learning Rate": 1.86923320106963e-05, "Pretrain/Loss": 2.0098514556884766, "Pretrain/Loss (Raw)": 2.0575811862945557, "Pretrain/Step": 5662, "Pretrain/Step Time": 8.448624027892947} +{"Pretrain/Learning Rate": 1.8684116283608006e-05, "Pretrain/Loss": 2.007683753967285, "Pretrain/Loss (Raw)": 1.9018137454986572, "Pretrain/Step": 5663, "Pretrain/Step Time": 8.447155034169555} +{"Pretrain/Learning Rate": 1.867590128505468e-05, "Pretrain/Loss": 2.0079171657562256, "Pretrain/Loss (Raw)": 1.8351815938949585, "Pretrain/Step": 5664, "Pretrain/Step Time": 8.446948789060116} +{"Pretrain/Learning Rate": 1.8667687015983913e-05, "Pretrain/Loss": 2.0073678493499756, "Pretrain/Loss (Raw)": 1.963455319404602, "Pretrain/Step": 5665, "Pretrain/Step Time": 8.449412390589714} +{"Pretrain/Learning Rate": 1.865947347734323e-05, "Pretrain/Loss": 2.0097014904022217, "Pretrain/Loss (Raw)": 2.183189868927002, "Pretrain/Step": 5666, "Pretrain/Step Time": 8.452301163226366} +{"Pretrain/Learning Rate": 1.8651260670080063e-05, "Pretrain/Loss": 2.007643699645996, "Pretrain/Loss (Raw)": 1.9289003610610962, "Pretrain/Step": 5667, "Pretrain/Step Time": 8.451036481186748} +{"Pretrain/Learning Rate": 1.8643048595141733e-05, "Pretrain/Loss": 2.007596492767334, "Pretrain/Loss (Raw)": 1.9566320180892944, "Pretrain/Step": 5668, "Pretrain/Step Time": 8.44716015458107} +{"Pretrain/Learning Rate": 1.863483725347552e-05, "Pretrain/Loss": 2.0080924034118652, "Pretrain/Loss (Raw)": 2.073256492614746, "Pretrain/Step": 5669, "Pretrain/Step Time": 8.446915801614523} +{"Pretrain/Learning Rate": 1.862662664602859e-05, "Pretrain/Loss": 2.0062522888183594, "Pretrain/Loss (Raw)": 1.8633191585540771, "Pretrain/Step": 5670, "Pretrain/Step Time": 8.44711291603744} +{"Pretrain/Learning Rate": 1.861841677374803e-05, "Pretrain/Loss": 2.006666660308838, "Pretrain/Loss (Raw)": 2.059741735458374, "Pretrain/Step": 5671, "Pretrain/Step Time": 8.446124283596873} +{"Pretrain/Learning Rate": 1.8610207637580872e-05, "Pretrain/Loss": 2.0066845417022705, "Pretrain/Loss (Raw)": 1.9506127834320068, "Pretrain/Step": 5672, "Pretrain/Step Time": 8.444145694375038} +{"Pretrain/Learning Rate": 1.8601999238474e-05, "Pretrain/Loss": 2.0069618225097656, "Pretrain/Loss (Raw)": 2.0543854236602783, "Pretrain/Step": 5673, "Pretrain/Step Time": 8.443365536630154} +{"Pretrain/Learning Rate": 1.859379157737427e-05, "Pretrain/Loss": 2.008315324783325, "Pretrain/Loss (Raw)": 2.1565847396850586, "Pretrain/Step": 5674, "Pretrain/Step Time": 8.449147328734398} +{"Pretrain/Learning Rate": 1.858558465522843e-05, "Pretrain/Loss": 2.00698184967041, "Pretrain/Loss (Raw)": 1.8608235120773315, "Pretrain/Step": 5675, "Pretrain/Step Time": 8.446200530976057} +{"Pretrain/Learning Rate": 1.857737847298315e-05, "Pretrain/Loss": 2.0070266723632812, "Pretrain/Loss (Raw)": 2.019723415374756, "Pretrain/Step": 5676, "Pretrain/Step Time": 8.444102935492992} +{"Pretrain/Learning Rate": 1.856917303158501e-05, "Pretrain/Loss": 2.007664680480957, "Pretrain/Loss (Raw)": 2.0028653144836426, "Pretrain/Step": 5677, "Pretrain/Step Time": 8.44875449128449} +{"Pretrain/Learning Rate": 1.8560968331980493e-05, "Pretrain/Loss": 2.005340099334717, "Pretrain/Loss (Raw)": 1.8659155368804932, "Pretrain/Step": 5678, "Pretrain/Step Time": 8.448373323306441} +{"Pretrain/Learning Rate": 1.8552764375116023e-05, "Pretrain/Loss": 2.004995346069336, "Pretrain/Loss (Raw)": 2.0012855529785156, "Pretrain/Step": 5679, "Pretrain/Step Time": 8.449363501742482} +{"Pretrain/Learning Rate": 1.8544561161937906e-05, "Pretrain/Loss": 2.0039751529693604, "Pretrain/Loss (Raw)": 1.9148924350738525, "Pretrain/Step": 5680, "Pretrain/Step Time": 8.44764387793839} +{"Pretrain/Learning Rate": 1.8536358693392398e-05, "Pretrain/Loss": 2.0056350231170654, "Pretrain/Loss (Raw)": 2.1169493198394775, "Pretrain/Step": 5681, "Pretrain/Step Time": 8.447415847331285} +{"Pretrain/Learning Rate": 1.8528156970425647e-05, "Pretrain/Loss": 2.0044429302215576, "Pretrain/Loss (Raw)": 1.9517419338226318, "Pretrain/Step": 5682, "Pretrain/Step Time": 8.446304872632027} +{"Pretrain/Learning Rate": 1.851995599398371e-05, "Pretrain/Loss": 2.004070520401001, "Pretrain/Loss (Raw)": 2.005000591278076, "Pretrain/Step": 5683, "Pretrain/Step Time": 8.447270380333066} +{"Pretrain/Learning Rate": 1.8511755765012566e-05, "Pretrain/Loss": 2.0054171085357666, "Pretrain/Loss (Raw)": 2.192262887954712, "Pretrain/Step": 5684, "Pretrain/Step Time": 8.448419192805886} +{"Pretrain/Learning Rate": 1.850355628445812e-05, "Pretrain/Loss": 2.0027947425842285, "Pretrain/Loss (Raw)": 1.8572618961334229, "Pretrain/Step": 5685, "Pretrain/Step Time": 8.448791773989797} +{"Pretrain/Learning Rate": 1.8495357553266178e-05, "Pretrain/Loss": 2.0054006576538086, "Pretrain/Loss (Raw)": 1.976936936378479, "Pretrain/Step": 5686, "Pretrain/Step Time": 8.44881466589868} +{"Pretrain/Learning Rate": 1.848715957238245e-05, "Pretrain/Loss": 2.003479480743408, "Pretrain/Loss (Raw)": 1.7743722200393677, "Pretrain/Step": 5687, "Pretrain/Step Time": 8.448728604242206} +{"Pretrain/Learning Rate": 1.8478962342752583e-05, "Pretrain/Loss": 2.000182628631592, "Pretrain/Loss (Raw)": 1.6344640254974365, "Pretrain/Step": 5688, "Pretrain/Step Time": 8.452714951708913} +{"Pretrain/Learning Rate": 1.8470765865322113e-05, "Pretrain/Loss": 1.999088168144226, "Pretrain/Loss (Raw)": 1.9106216430664062, "Pretrain/Step": 5689, "Pretrain/Step Time": 8.448383659124374} +{"Pretrain/Learning Rate": 1.8462570141036505e-05, "Pretrain/Loss": 1.9994208812713623, "Pretrain/Loss (Raw)": 2.052741527557373, "Pretrain/Step": 5690, "Pretrain/Step Time": 8.448441138491035} +{"Pretrain/Learning Rate": 1.845437517084113e-05, "Pretrain/Loss": 2.003143310546875, "Pretrain/Loss (Raw)": 1.998496174812317, "Pretrain/Step": 5691, "Pretrain/Step Time": 8.444143131375313} +{"Pretrain/Learning Rate": 1.8446180955681282e-05, "Pretrain/Loss": 2.0039572715759277, "Pretrain/Loss (Raw)": 2.24234938621521, "Pretrain/Step": 5692, "Pretrain/Step Time": 8.44415195658803} +{"Pretrain/Learning Rate": 1.843798749650217e-05, "Pretrain/Loss": 2.004941463470459, "Pretrain/Loss (Raw)": 2.0684750080108643, "Pretrain/Step": 5693, "Pretrain/Step Time": 8.444556407630444} +{"Pretrain/Learning Rate": 1.8429794794248877e-05, "Pretrain/Loss": 2.0044236183166504, "Pretrain/Loss (Raw)": 2.149226665496826, "Pretrain/Step": 5694, "Pretrain/Step Time": 8.445455376058817} +{"Pretrain/Learning Rate": 1.842160284986646e-05, "Pretrain/Loss": 2.0032975673675537, "Pretrain/Loss (Raw)": 1.9431205987930298, "Pretrain/Step": 5695, "Pretrain/Step Time": 8.446336701512337} +{"Pretrain/Learning Rate": 1.8413411664299828e-05, "Pretrain/Loss": 2.004966974258423, "Pretrain/Loss (Raw)": 2.0641095638275146, "Pretrain/Step": 5696, "Pretrain/Step Time": 8.445123229175806} +{"Pretrain/Learning Rate": 1.840522123849385e-05, "Pretrain/Loss": 2.0020337104797363, "Pretrain/Loss (Raw)": 1.6791325807571411, "Pretrain/Step": 5697, "Pretrain/Step Time": 8.448944374918938} +{"Pretrain/Learning Rate": 1.8397031573393297e-05, "Pretrain/Loss": 2.003378391265869, "Pretrain/Loss (Raw)": 2.1456451416015625, "Pretrain/Step": 5698, "Pretrain/Step Time": 8.448053421452641} +{"Pretrain/Learning Rate": 1.838884266994282e-05, "Pretrain/Loss": 2.0034067630767822, "Pretrain/Loss (Raw)": 2.1886653900146484, "Pretrain/Step": 5699, "Pretrain/Step Time": 8.44819212704897} +{"Pretrain/Learning Rate": 1.8380654529087017e-05, "Pretrain/Loss": 2.0050625801086426, "Pretrain/Loss (Raw)": 2.112633228302002, "Pretrain/Step": 5700, "Pretrain/Step Time": 8.448061414062977} +{"Pretrain/Learning Rate": 1.8372467151770388e-05, "Pretrain/Loss": 2.0040602684020996, "Pretrain/Loss (Raw)": 1.9964118003845215, "Pretrain/Step": 5701, "Pretrain/Step Time": 8.446622893214226} +{"Pretrain/Learning Rate": 1.8364280538937352e-05, "Pretrain/Loss": 2.007709503173828, "Pretrain/Loss (Raw)": 1.9867804050445557, "Pretrain/Step": 5702, "Pretrain/Step Time": 8.446974404156208} +{"Pretrain/Learning Rate": 1.835609469153222e-05, "Pretrain/Loss": 2.007727861404419, "Pretrain/Loss (Raw)": 2.0880727767944336, "Pretrain/Step": 5703, "Pretrain/Step Time": 8.446578336879611} +{"Pretrain/Learning Rate": 1.834790961049923e-05, "Pretrain/Loss": 2.0076920986175537, "Pretrain/Loss (Raw)": 1.949934959411621, "Pretrain/Step": 5704, "Pretrain/Step Time": 8.450042497366667} +{"Pretrain/Learning Rate": 1.8339725296782525e-05, "Pretrain/Loss": 2.004779100418091, "Pretrain/Loss (Raw)": 1.6771459579467773, "Pretrain/Step": 5705, "Pretrain/Step Time": 8.447538260370493} +{"Pretrain/Learning Rate": 1.8331541751326167e-05, "Pretrain/Loss": 2.0058507919311523, "Pretrain/Loss (Raw)": 1.8686507940292358, "Pretrain/Step": 5706, "Pretrain/Step Time": 8.4479745849967} +{"Pretrain/Learning Rate": 1.8323358975074124e-05, "Pretrain/Loss": 2.0053329467773438, "Pretrain/Loss (Raw)": 1.9155024290084839, "Pretrain/Step": 5707, "Pretrain/Step Time": 8.448004389181733} +{"Pretrain/Learning Rate": 1.8315176968970277e-05, "Pretrain/Loss": 2.0056328773498535, "Pretrain/Loss (Raw)": 2.0038959980010986, "Pretrain/Step": 5708, "Pretrain/Step Time": 8.447332153096795} +{"Pretrain/Learning Rate": 1.8306995733958425e-05, "Pretrain/Loss": 2.004446029663086, "Pretrain/Loss (Raw)": 2.0105109214782715, "Pretrain/Step": 5709, "Pretrain/Step Time": 8.445564465597272} +{"Pretrain/Learning Rate": 1.8298815270982258e-05, "Pretrain/Loss": 2.0033135414123535, "Pretrain/Loss (Raw)": 1.9892677068710327, "Pretrain/Step": 5710, "Pretrain/Step Time": 8.44749341905117} +{"Pretrain/Learning Rate": 1.8290635580985394e-05, "Pretrain/Loss": 2.002800464630127, "Pretrain/Loss (Raw)": 2.0353715419769287, "Pretrain/Step": 5711, "Pretrain/Step Time": 8.447441847994924} +{"Pretrain/Learning Rate": 1.828245666491136e-05, "Pretrain/Loss": 2.0016825199127197, "Pretrain/Loss (Raw)": 2.01344895362854, "Pretrain/Step": 5712, "Pretrain/Step Time": 8.448176361620426} +{"Pretrain/Learning Rate": 1.8274278523703583e-05, "Pretrain/Loss": 2.0010952949523926, "Pretrain/Loss (Raw)": 1.8491621017456055, "Pretrain/Step": 5713, "Pretrain/Step Time": 8.447197521105409} +{"Pretrain/Learning Rate": 1.8266101158305427e-05, "Pretrain/Loss": 2.002006769180298, "Pretrain/Loss (Raw)": 2.080414295196533, "Pretrain/Step": 5714, "Pretrain/Step Time": 8.447016956284642} +{"Pretrain/Learning Rate": 1.8257924569660126e-05, "Pretrain/Loss": 2.002619981765747, "Pretrain/Loss (Raw)": 1.9616484642028809, "Pretrain/Step": 5715, "Pretrain/Step Time": 8.450281344354153} +{"Pretrain/Learning Rate": 1.8249748758710854e-05, "Pretrain/Loss": 2.002479314804077, "Pretrain/Loss (Raw)": 2.051732063293457, "Pretrain/Step": 5716, "Pretrain/Step Time": 8.44847416691482} +{"Pretrain/Learning Rate": 1.8241573726400695e-05, "Pretrain/Loss": 2.000305652618408, "Pretrain/Loss (Raw)": 1.7884421348571777, "Pretrain/Step": 5717, "Pretrain/Step Time": 8.449279770255089} +{"Pretrain/Learning Rate": 1.823339947367263e-05, "Pretrain/Loss": 1.99918532371521, "Pretrain/Loss (Raw)": 2.0312817096710205, "Pretrain/Step": 5718, "Pretrain/Step Time": 8.449694830924273} +{"Pretrain/Learning Rate": 1.8225226001469566e-05, "Pretrain/Loss": 1.997632622718811, "Pretrain/Loss (Raw)": 1.8176813125610352, "Pretrain/Step": 5719, "Pretrain/Step Time": 8.443001128733158} +{"Pretrain/Learning Rate": 1.8217053310734294e-05, "Pretrain/Loss": 1.9977003335952759, "Pretrain/Loss (Raw)": 1.9828251600265503, "Pretrain/Step": 5720, "Pretrain/Step Time": 8.443527495488524} +{"Pretrain/Learning Rate": 1.8208881402409543e-05, "Pretrain/Loss": 1.999016523361206, "Pretrain/Loss (Raw)": 2.2036476135253906, "Pretrain/Step": 5721, "Pretrain/Step Time": 8.44460428506136} +{"Pretrain/Learning Rate": 1.8200710277437928e-05, "Pretrain/Loss": 1.9988837242126465, "Pretrain/Loss (Raw)": 1.9387125968933105, "Pretrain/Step": 5722, "Pretrain/Step Time": 8.442704129964113} +{"Pretrain/Learning Rate": 1.8192539936761996e-05, "Pretrain/Loss": 1.9999480247497559, "Pretrain/Loss (Raw)": 2.057478904724121, "Pretrain/Step": 5723, "Pretrain/Step Time": 8.445608926936984} +{"Pretrain/Learning Rate": 1.81843703813242e-05, "Pretrain/Loss": 2.001262664794922, "Pretrain/Loss (Raw)": 2.143493175506592, "Pretrain/Step": 5724, "Pretrain/Step Time": 8.440577417612076} +{"Pretrain/Learning Rate": 1.817620161206687e-05, "Pretrain/Loss": 2.003970146179199, "Pretrain/Loss (Raw)": 2.229574680328369, "Pretrain/Step": 5725, "Pretrain/Step Time": 8.441558146849275} +{"Pretrain/Learning Rate": 1.8168033629932297e-05, "Pretrain/Loss": 2.003617763519287, "Pretrain/Loss (Raw)": 1.847088098526001, "Pretrain/Step": 5726, "Pretrain/Step Time": 8.44392660073936} +{"Pretrain/Learning Rate": 1.8159866435862635e-05, "Pretrain/Loss": 2.002943277359009, "Pretrain/Loss (Raw)": 2.027489185333252, "Pretrain/Step": 5727, "Pretrain/Step Time": 8.443138845264912} +{"Pretrain/Learning Rate": 1.8151700030799982e-05, "Pretrain/Loss": 2.002534866333008, "Pretrain/Loss (Raw)": 1.9639697074890137, "Pretrain/Step": 5728, "Pretrain/Step Time": 8.443542301654816} +{"Pretrain/Learning Rate": 1.814353441568632e-05, "Pretrain/Loss": 2.0031518936157227, "Pretrain/Loss (Raw)": 2.1289114952087402, "Pretrain/Step": 5729, "Pretrain/Step Time": 8.443473411723971} +{"Pretrain/Learning Rate": 1.8135369591463565e-05, "Pretrain/Loss": 2.002998113632202, "Pretrain/Loss (Raw)": 2.0492987632751465, "Pretrain/Step": 5730, "Pretrain/Step Time": 8.445589447394013} +{"Pretrain/Learning Rate": 1.8127205559073507e-05, "Pretrain/Loss": 2.0046210289001465, "Pretrain/Loss (Raw)": 2.1019704341888428, "Pretrain/Step": 5731, "Pretrain/Step Time": 8.443906541913748} +{"Pretrain/Learning Rate": 1.8119042319457868e-05, "Pretrain/Loss": 2.003969192504883, "Pretrain/Loss (Raw)": 2.1729307174682617, "Pretrain/Step": 5732, "Pretrain/Step Time": 8.445905355736613} +{"Pretrain/Learning Rate": 1.8110879873558278e-05, "Pretrain/Loss": 2.0041024684906006, "Pretrain/Loss (Raw)": 2.000579595565796, "Pretrain/Step": 5733, "Pretrain/Step Time": 8.447577148675919} +{"Pretrain/Learning Rate": 1.8102718222316277e-05, "Pretrain/Loss": 2.0054385662078857, "Pretrain/Loss (Raw)": 2.1226887702941895, "Pretrain/Step": 5734, "Pretrain/Step Time": 8.448578206822276} +{"Pretrain/Learning Rate": 1.8094557366673316e-05, "Pretrain/Loss": 2.0041890144348145, "Pretrain/Loss (Raw)": 1.878587007522583, "Pretrain/Step": 5735, "Pretrain/Step Time": 8.446114035323262} +{"Pretrain/Learning Rate": 1.8086397307570723e-05, "Pretrain/Loss": 1.9995436668395996, "Pretrain/Loss (Raw)": 1.4858733415603638, "Pretrain/Step": 5736, "Pretrain/Step Time": 8.444498233497143} +{"Pretrain/Learning Rate": 1.807823804594978e-05, "Pretrain/Loss": 1.9986965656280518, "Pretrain/Loss (Raw)": 2.0665483474731445, "Pretrain/Step": 5737, "Pretrain/Step Time": 8.443390497937799} +{"Pretrain/Learning Rate": 1.8070079582751638e-05, "Pretrain/Loss": 1.9987261295318604, "Pretrain/Loss (Raw)": 2.0725064277648926, "Pretrain/Step": 5738, "Pretrain/Step Time": 8.442991377785802} +{"Pretrain/Learning Rate": 1.806192191891738e-05, "Pretrain/Loss": 1.999030590057373, "Pretrain/Loss (Raw)": 2.0182652473449707, "Pretrain/Step": 5739, "Pretrain/Step Time": 8.446041226387024} +{"Pretrain/Learning Rate": 1.8053765055388004e-05, "Pretrain/Loss": 1.9960198402404785, "Pretrain/Loss (Raw)": 1.6927096843719482, "Pretrain/Step": 5740, "Pretrain/Step Time": 8.444934129714966} +{"Pretrain/Learning Rate": 1.8045608993104373e-05, "Pretrain/Loss": 1.9953410625457764, "Pretrain/Loss (Raw)": 2.0060784816741943, "Pretrain/Step": 5741, "Pretrain/Step Time": 8.442793495953083} +{"Pretrain/Learning Rate": 1.8037453733007303e-05, "Pretrain/Loss": 1.9954965114593506, "Pretrain/Loss (Raw)": 2.056968927383423, "Pretrain/Step": 5742, "Pretrain/Step Time": 8.447386238723993} +{"Pretrain/Learning Rate": 1.8029299276037498e-05, "Pretrain/Loss": 1.996029019355774, "Pretrain/Loss (Raw)": 2.0350911617279053, "Pretrain/Step": 5743, "Pretrain/Step Time": 8.44522382877767} +{"Pretrain/Learning Rate": 1.8021145623135575e-05, "Pretrain/Loss": 1.9973196983337402, "Pretrain/Loss (Raw)": 2.0793933868408203, "Pretrain/Step": 5744, "Pretrain/Step Time": 8.445603556931019} +{"Pretrain/Learning Rate": 1.8012992775242056e-05, "Pretrain/Loss": 1.9999582767486572, "Pretrain/Loss (Raw)": 2.1642324924468994, "Pretrain/Step": 5745, "Pretrain/Step Time": 8.442194188013673} +{"Pretrain/Learning Rate": 1.8004840733297365e-05, "Pretrain/Loss": 1.998678207397461, "Pretrain/Loss (Raw)": 2.0008673667907715, "Pretrain/Step": 5746, "Pretrain/Step Time": 8.442758744582534} +{"Pretrain/Learning Rate": 1.7996689498241832e-05, "Pretrain/Loss": 1.9981307983398438, "Pretrain/Loss (Raw)": 1.8668395280838013, "Pretrain/Step": 5747, "Pretrain/Step Time": 8.440474458038807} +{"Pretrain/Learning Rate": 1.79885390710157e-05, "Pretrain/Loss": 1.9970712661743164, "Pretrain/Loss (Raw)": 1.9277759790420532, "Pretrain/Step": 5748, "Pretrain/Step Time": 8.441288461908698} +{"Pretrain/Learning Rate": 1.7980389452559124e-05, "Pretrain/Loss": 1.994560718536377, "Pretrain/Loss (Raw)": 1.8709609508514404, "Pretrain/Step": 5749, "Pretrain/Step Time": 8.44348169863224} +{"Pretrain/Learning Rate": 1.7972240643812162e-05, "Pretrain/Loss": 1.9959182739257812, "Pretrain/Loss (Raw)": 2.2230443954467773, "Pretrain/Step": 5750, "Pretrain/Step Time": 8.446768881753087} +{"Pretrain/Learning Rate": 1.7964092645714776e-05, "Pretrain/Loss": 1.9954191446304321, "Pretrain/Loss (Raw)": 2.052394151687622, "Pretrain/Step": 5751, "Pretrain/Step Time": 8.446166081354022} +{"Pretrain/Learning Rate": 1.7955945459206822e-05, "Pretrain/Loss": 1.9976996183395386, "Pretrain/Loss (Raw)": 2.142932653427124, "Pretrain/Step": 5752, "Pretrain/Step Time": 8.442484650760889} +{"Pretrain/Learning Rate": 1.794779908522809e-05, "Pretrain/Loss": 1.9995613098144531, "Pretrain/Loss (Raw)": 2.1033668518066406, "Pretrain/Step": 5753, "Pretrain/Step Time": 8.4400983043015} +{"Pretrain/Learning Rate": 1.793965352471825e-05, "Pretrain/Loss": 1.9988622665405273, "Pretrain/Loss (Raw)": 1.933152437210083, "Pretrain/Step": 5754, "Pretrain/Step Time": 8.439460841938853} +{"Pretrain/Learning Rate": 1.7931508778616895e-05, "Pretrain/Loss": 1.9989473819732666, "Pretrain/Loss (Raw)": 1.88534414768219, "Pretrain/Step": 5755, "Pretrain/Step Time": 8.439678499475121} +{"Pretrain/Learning Rate": 1.7923364847863527e-05, "Pretrain/Loss": 1.9980239868164062, "Pretrain/Loss (Raw)": 1.946960687637329, "Pretrain/Step": 5756, "Pretrain/Step Time": 8.444681445136666} +{"Pretrain/Learning Rate": 1.791522173339753e-05, "Pretrain/Loss": 1.9973180294036865, "Pretrain/Loss (Raw)": 1.9608575105667114, "Pretrain/Step": 5757, "Pretrain/Step Time": 8.439833410084248} +{"Pretrain/Learning Rate": 1.7907079436158213e-05, "Pretrain/Loss": 1.9984686374664307, "Pretrain/Loss (Raw)": 2.0836029052734375, "Pretrain/Step": 5758, "Pretrain/Step Time": 8.444393772631884} +{"Pretrain/Learning Rate": 1.789893795708479e-05, "Pretrain/Loss": 1.9993679523468018, "Pretrain/Loss (Raw)": 2.0458664894104004, "Pretrain/Step": 5759, "Pretrain/Step Time": 8.443633360788226} +{"Pretrain/Learning Rate": 1.789079729711638e-05, "Pretrain/Loss": 1.9968208074569702, "Pretrain/Loss (Raw)": 1.945934534072876, "Pretrain/Step": 5760, "Pretrain/Step Time": 8.443504523485899} +{"Pretrain/Learning Rate": 1.7882657457192013e-05, "Pretrain/Loss": 1.998488426208496, "Pretrain/Loss (Raw)": 2.028000593185425, "Pretrain/Step": 5761, "Pretrain/Step Time": 8.439948005601764} +{"Pretrain/Learning Rate": 1.7874518438250597e-05, "Pretrain/Loss": 1.9983224868774414, "Pretrain/Loss (Raw)": 2.190195083618164, "Pretrain/Step": 5762, "Pretrain/Step Time": 8.440718155354261} +{"Pretrain/Learning Rate": 1.7866380241230983e-05, "Pretrain/Loss": 1.9978277683258057, "Pretrain/Loss (Raw)": 1.9706851243972778, "Pretrain/Step": 5763, "Pretrain/Step Time": 8.438154615461826} +{"Pretrain/Learning Rate": 1.7858242867071896e-05, "Pretrain/Loss": 1.9975385665893555, "Pretrain/Loss (Raw)": 1.9445430040359497, "Pretrain/Step": 5764, "Pretrain/Step Time": 8.437207652255893} +{"Pretrain/Learning Rate": 1.785010631671198e-05, "Pretrain/Loss": 1.998124599456787, "Pretrain/Loss (Raw)": 2.108438730239868, "Pretrain/Step": 5765, "Pretrain/Step Time": 8.438813623040915} +{"Pretrain/Learning Rate": 1.784197059108979e-05, "Pretrain/Loss": 1.9992351531982422, "Pretrain/Loss (Raw)": 2.0479347705841064, "Pretrain/Step": 5766, "Pretrain/Step Time": 8.435493398457766} +{"Pretrain/Learning Rate": 1.7833835691143785e-05, "Pretrain/Loss": 1.9984630346298218, "Pretrain/Loss (Raw)": 1.9625675678253174, "Pretrain/Step": 5767, "Pretrain/Step Time": 8.43568597175181} +{"Pretrain/Learning Rate": 1.7825701617812307e-05, "Pretrain/Loss": 1.9991216659545898, "Pretrain/Loss (Raw)": 2.1831681728363037, "Pretrain/Step": 5768, "Pretrain/Step Time": 8.43915112130344} +{"Pretrain/Learning Rate": 1.7817568372033628e-05, "Pretrain/Loss": 2.001072645187378, "Pretrain/Loss (Raw)": 2.100337028503418, "Pretrain/Step": 5769, "Pretrain/Step Time": 8.441036427393556} +{"Pretrain/Learning Rate": 1.780943595474591e-05, "Pretrain/Loss": 2.002305030822754, "Pretrain/Loss (Raw)": 2.1486682891845703, "Pretrain/Step": 5770, "Pretrain/Step Time": 8.440602984279394} +{"Pretrain/Learning Rate": 1.7801304366887235e-05, "Pretrain/Loss": 1.998558521270752, "Pretrain/Loss (Raw)": 1.6544137001037598, "Pretrain/Step": 5771, "Pretrain/Step Time": 8.441727429628372} +{"Pretrain/Learning Rate": 1.779317360939557e-05, "Pretrain/Loss": 1.9999504089355469, "Pretrain/Loss (Raw)": 2.0924925804138184, "Pretrain/Step": 5772, "Pretrain/Step Time": 8.442405615001917} +{"Pretrain/Learning Rate": 1.7785043683208794e-05, "Pretrain/Loss": 1.9984230995178223, "Pretrain/Loss (Raw)": 1.785037875175476, "Pretrain/Step": 5773, "Pretrain/Step Time": 8.445392025634646} +{"Pretrain/Learning Rate": 1.777691458926469e-05, "Pretrain/Loss": 1.9990533590316772, "Pretrain/Loss (Raw)": 2.1565747261047363, "Pretrain/Step": 5774, "Pretrain/Step Time": 8.443302903324366} +{"Pretrain/Learning Rate": 1.7768786328500953e-05, "Pretrain/Loss": 2.000011444091797, "Pretrain/Loss (Raw)": 2.1696274280548096, "Pretrain/Step": 5775, "Pretrain/Step Time": 8.445916147902608} +{"Pretrain/Learning Rate": 1.776065890185517e-05, "Pretrain/Loss": 1.999894618988037, "Pretrain/Loss (Raw)": 2.131441831588745, "Pretrain/Step": 5776, "Pretrain/Step Time": 8.445464031770825} +{"Pretrain/Learning Rate": 1.7752532310264846e-05, "Pretrain/Loss": 1.9980735778808594, "Pretrain/Loss (Raw)": 1.7524895668029785, "Pretrain/Step": 5777, "Pretrain/Step Time": 8.440933646634221} +{"Pretrain/Learning Rate": 1.7744406554667364e-05, "Pretrain/Loss": 1.9967221021652222, "Pretrain/Loss (Raw)": 1.961155652999878, "Pretrain/Step": 5778, "Pretrain/Step Time": 8.44307916238904} +{"Pretrain/Learning Rate": 1.7736281636000045e-05, "Pretrain/Loss": 1.9957168102264404, "Pretrain/Loss (Raw)": 1.9470980167388916, "Pretrain/Step": 5779, "Pretrain/Step Time": 8.443148845806718} +{"Pretrain/Learning Rate": 1.7728157555200075e-05, "Pretrain/Loss": 1.9971036911010742, "Pretrain/Loss (Raw)": 2.0353214740753174, "Pretrain/Step": 5780, "Pretrain/Step Time": 8.44245533272624} +{"Pretrain/Learning Rate": 1.772003431320458e-05, "Pretrain/Loss": 1.9981293678283691, "Pretrain/Loss (Raw)": 2.079619884490967, "Pretrain/Step": 5781, "Pretrain/Step Time": 8.44155964627862} +{"Pretrain/Learning Rate": 1.771191191095058e-05, "Pretrain/Loss": 1.9967923164367676, "Pretrain/Loss (Raw)": 1.8905622959136963, "Pretrain/Step": 5782, "Pretrain/Step Time": 8.442892700433731} +{"Pretrain/Learning Rate": 1.770379034937497e-05, "Pretrain/Loss": 1.9964076280593872, "Pretrain/Loss (Raw)": 1.9474760293960571, "Pretrain/Step": 5783, "Pretrain/Step Time": 8.444480204954743} +{"Pretrain/Learning Rate": 1.7695669629414573e-05, "Pretrain/Loss": 1.996398687362671, "Pretrain/Loss (Raw)": 2.0282270908355713, "Pretrain/Step": 5784, "Pretrain/Step Time": 8.44493505358696} +{"Pretrain/Learning Rate": 1.768754975200612e-05, "Pretrain/Loss": 1.996341347694397, "Pretrain/Loss (Raw)": 2.0853943824768066, "Pretrain/Step": 5785, "Pretrain/Step Time": 8.443373000249267} +{"Pretrain/Learning Rate": 1.7679430718086243e-05, "Pretrain/Loss": 1.9977202415466309, "Pretrain/Loss (Raw)": 2.082366466522217, "Pretrain/Step": 5786, "Pretrain/Step Time": 8.441965859383345} +{"Pretrain/Learning Rate": 1.7671312528591454e-05, "Pretrain/Loss": 1.9974267482757568, "Pretrain/Loss (Raw)": 1.9885754585266113, "Pretrain/Step": 5787, "Pretrain/Step Time": 8.441811120137572} +{"Pretrain/Learning Rate": 1.7663195184458196e-05, "Pretrain/Loss": 2.000229835510254, "Pretrain/Loss (Raw)": 2.1074059009552, "Pretrain/Step": 5788, "Pretrain/Step Time": 8.438904214650393} +{"Pretrain/Learning Rate": 1.7655078686622782e-05, "Pretrain/Loss": 2.0012362003326416, "Pretrain/Loss (Raw)": 2.2318837642669678, "Pretrain/Step": 5789, "Pretrain/Step Time": 8.43914951197803} +{"Pretrain/Learning Rate": 1.764696303602147e-05, "Pretrain/Loss": 2.0019989013671875, "Pretrain/Loss (Raw)": 2.155205011367798, "Pretrain/Step": 5790, "Pretrain/Step Time": 8.437443010509014} +{"Pretrain/Learning Rate": 1.763884823359038e-05, "Pretrain/Loss": 2.0026631355285645, "Pretrain/Loss (Raw)": 1.9868052005767822, "Pretrain/Step": 5791, "Pretrain/Step Time": 8.440515892580152} +{"Pretrain/Learning Rate": 1.763073428026556e-05, "Pretrain/Loss": 2.0045552253723145, "Pretrain/Loss (Raw)": 2.0773892402648926, "Pretrain/Step": 5792, "Pretrain/Step Time": 8.439183089882135} +{"Pretrain/Learning Rate": 1.7622621176982964e-05, "Pretrain/Loss": 2.005843162536621, "Pretrain/Loss (Raw)": 2.1283164024353027, "Pretrain/Step": 5793, "Pretrain/Step Time": 8.437199838459492} +{"Pretrain/Learning Rate": 1.7614508924678412e-05, "Pretrain/Loss": 2.0052690505981445, "Pretrain/Loss (Raw)": 2.1097254753112793, "Pretrain/Step": 5794, "Pretrain/Step Time": 8.437903573736548} +{"Pretrain/Learning Rate": 1.7606397524287665e-05, "Pretrain/Loss": 2.007784366607666, "Pretrain/Loss (Raw)": 2.250866413116455, "Pretrain/Step": 5795, "Pretrain/Step Time": 8.440930601209402} +{"Pretrain/Learning Rate": 1.759828697674636e-05, "Pretrain/Loss": 2.0088963508605957, "Pretrain/Loss (Raw)": 2.0989434719085693, "Pretrain/Step": 5796, "Pretrain/Step Time": 8.44076906889677} +{"Pretrain/Learning Rate": 1.759017728299005e-05, "Pretrain/Loss": 2.0089504718780518, "Pretrain/Loss (Raw)": 2.0801808834075928, "Pretrain/Step": 5797, "Pretrain/Step Time": 8.438928106799722} +{"Pretrain/Learning Rate": 1.7582068443954198e-05, "Pretrain/Loss": 2.0093188285827637, "Pretrain/Loss (Raw)": 1.9104762077331543, "Pretrain/Step": 5798, "Pretrain/Step Time": 8.440042704343796} +{"Pretrain/Learning Rate": 1.7573960460574133e-05, "Pretrain/Loss": 2.0087666511535645, "Pretrain/Loss (Raw)": 1.9890730381011963, "Pretrain/Step": 5799, "Pretrain/Step Time": 8.440830644220114} +{"Pretrain/Learning Rate": 1.756585333378512e-05, "Pretrain/Loss": 2.0094025135040283, "Pretrain/Loss (Raw)": 2.031987190246582, "Pretrain/Step": 5800, "Pretrain/Step Time": 8.440784530714154} +{"Pretrain/Learning Rate": 1.7557747064522313e-05, "Pretrain/Loss": 2.0094995498657227, "Pretrain/Loss (Raw)": 2.0667810440063477, "Pretrain/Step": 5801, "Pretrain/Step Time": 8.445897301658988} +{"Pretrain/Learning Rate": 1.7549641653720765e-05, "Pretrain/Loss": 2.009661912918091, "Pretrain/Loss (Raw)": 2.1773996353149414, "Pretrain/Step": 5802, "Pretrain/Step Time": 8.440332194790244} +{"Pretrain/Learning Rate": 1.7541537102315443e-05, "Pretrain/Loss": 2.0114529132843018, "Pretrain/Loss (Raw)": 2.090064287185669, "Pretrain/Step": 5803, "Pretrain/Step Time": 8.440946631133556} +{"Pretrain/Learning Rate": 1.7533433411241188e-05, "Pretrain/Loss": 2.0096802711486816, "Pretrain/Loss (Raw)": 1.7928297519683838, "Pretrain/Step": 5804, "Pretrain/Step Time": 8.443017330020666} +{"Pretrain/Learning Rate": 1.7525330581432768e-05, "Pretrain/Loss": 2.0097858905792236, "Pretrain/Loss (Raw)": 2.0163824558258057, "Pretrain/Step": 5805, "Pretrain/Step Time": 8.440343331545591} +{"Pretrain/Learning Rate": 1.7517228613824833e-05, "Pretrain/Loss": 2.0106287002563477, "Pretrain/Loss (Raw)": 1.9737763404846191, "Pretrain/Step": 5806, "Pretrain/Step Time": 8.440517600625753} +{"Pretrain/Learning Rate": 1.7509127509351952e-05, "Pretrain/Loss": 2.0107622146606445, "Pretrain/Loss (Raw)": 2.018378734588623, "Pretrain/Step": 5807, "Pretrain/Step Time": 8.44009230658412} +{"Pretrain/Learning Rate": 1.7501027268948578e-05, "Pretrain/Loss": 2.010895252227783, "Pretrain/Loss (Raw)": 1.931929349899292, "Pretrain/Step": 5808, "Pretrain/Step Time": 8.440954932942986} +{"Pretrain/Learning Rate": 1.7492927893549083e-05, "Pretrain/Loss": 2.0096755027770996, "Pretrain/Loss (Raw)": 1.9608430862426758, "Pretrain/Step": 5809, "Pretrain/Step Time": 8.44196118414402} +{"Pretrain/Learning Rate": 1.74848293840877e-05, "Pretrain/Loss": 2.009903907775879, "Pretrain/Loss (Raw)": 1.9809727668762207, "Pretrain/Step": 5810, "Pretrain/Step Time": 8.441554851830006} +{"Pretrain/Learning Rate": 1.747673174149862e-05, "Pretrain/Loss": 2.0094470977783203, "Pretrain/Loss (Raw)": 1.946532964706421, "Pretrain/Step": 5811, "Pretrain/Step Time": 8.44017475284636} +{"Pretrain/Learning Rate": 1.7468634966715884e-05, "Pretrain/Loss": 2.00864839553833, "Pretrain/Loss (Raw)": 2.0900042057037354, "Pretrain/Step": 5812, "Pretrain/Step Time": 8.437398474663496} +{"Pretrain/Learning Rate": 1.7460539060673458e-05, "Pretrain/Loss": 2.009969711303711, "Pretrain/Loss (Raw)": 2.0264105796813965, "Pretrain/Step": 5813, "Pretrain/Step Time": 8.436137845739722} +{"Pretrain/Learning Rate": 1.7452444024305214e-05, "Pretrain/Loss": 2.0101685523986816, "Pretrain/Loss (Raw)": 2.002382516860962, "Pretrain/Step": 5814, "Pretrain/Step Time": 8.436456279829144} +{"Pretrain/Learning Rate": 1.7444349858544886e-05, "Pretrain/Loss": 2.0128087997436523, "Pretrain/Loss (Raw)": 2.1123008728027344, "Pretrain/Step": 5815, "Pretrain/Step Time": 8.437454780563712} +{"Pretrain/Learning Rate": 1.7436256564326147e-05, "Pretrain/Loss": 2.0162384510040283, "Pretrain/Loss (Raw)": 2.0734715461730957, "Pretrain/Step": 5816, "Pretrain/Step Time": 8.436511792242527} +{"Pretrain/Learning Rate": 1.7428164142582555e-05, "Pretrain/Loss": 2.0172481536865234, "Pretrain/Loss (Raw)": 2.039846181869507, "Pretrain/Step": 5817, "Pretrain/Step Time": 8.438164316117764} +{"Pretrain/Learning Rate": 1.7420072594247568e-05, "Pretrain/Loss": 2.0182671546936035, "Pretrain/Loss (Raw)": 2.183211326599121, "Pretrain/Step": 5818, "Pretrain/Step Time": 8.43882773630321} +{"Pretrain/Learning Rate": 1.7411981920254555e-05, "Pretrain/Loss": 2.0194015502929688, "Pretrain/Loss (Raw)": 2.1436927318573, "Pretrain/Step": 5819, "Pretrain/Step Time": 8.442296890541911} +{"Pretrain/Learning Rate": 1.740389212153675e-05, "Pretrain/Loss": 2.0176520347595215, "Pretrain/Loss (Raw)": 2.018414258956909, "Pretrain/Step": 5820, "Pretrain/Step Time": 8.440773911774158} +{"Pretrain/Learning Rate": 1.7395803199027323e-05, "Pretrain/Loss": 2.0189952850341797, "Pretrain/Loss (Raw)": 2.2403817176818848, "Pretrain/Step": 5821, "Pretrain/Step Time": 8.438529143109918} +{"Pretrain/Learning Rate": 1.7387715153659323e-05, "Pretrain/Loss": 2.0176594257354736, "Pretrain/Loss (Raw)": 1.9782438278198242, "Pretrain/Step": 5822, "Pretrain/Step Time": 8.441506000235677} +{"Pretrain/Learning Rate": 1.7379627986365702e-05, "Pretrain/Loss": 2.018885612487793, "Pretrain/Loss (Raw)": 2.1000609397888184, "Pretrain/Step": 5823, "Pretrain/Step Time": 8.441353054717183} +{"Pretrain/Learning Rate": 1.7371541698079324e-05, "Pretrain/Loss": 2.0166425704956055, "Pretrain/Loss (Raw)": 1.7770309448242188, "Pretrain/Step": 5824, "Pretrain/Step Time": 8.440355863422155} +{"Pretrain/Learning Rate": 1.7363456289732922e-05, "Pretrain/Loss": 2.0192384719848633, "Pretrain/Loss (Raw)": 2.011411428451538, "Pretrain/Step": 5825, "Pretrain/Step Time": 8.437316559255123} +{"Pretrain/Learning Rate": 1.7355371762259153e-05, "Pretrain/Loss": 2.0176215171813965, "Pretrain/Loss (Raw)": 1.9386978149414062, "Pretrain/Step": 5826, "Pretrain/Step Time": 8.440256522968411} +{"Pretrain/Learning Rate": 1.7347288116590565e-05, "Pretrain/Loss": 2.01663875579834, "Pretrain/Loss (Raw)": 2.062828779220581, "Pretrain/Step": 5827, "Pretrain/Step Time": 8.438459537923336} +{"Pretrain/Learning Rate": 1.733920535365961e-05, "Pretrain/Loss": 2.0154895782470703, "Pretrain/Loss (Raw)": 1.9655537605285645, "Pretrain/Step": 5828, "Pretrain/Step Time": 8.437665652483702} +{"Pretrain/Learning Rate": 1.733112347439862e-05, "Pretrain/Loss": 2.0148584842681885, "Pretrain/Loss (Raw)": 1.9156254529953003, "Pretrain/Step": 5829, "Pretrain/Step Time": 8.438600532710552} +{"Pretrain/Learning Rate": 1.732304247973985e-05, "Pretrain/Loss": 2.0154690742492676, "Pretrain/Loss (Raw)": 2.064936876296997, "Pretrain/Step": 5830, "Pretrain/Step Time": 8.438143126666546} +{"Pretrain/Learning Rate": 1.7314962370615423e-05, "Pretrain/Loss": 2.016366481781006, "Pretrain/Loss (Raw)": 2.2029366493225098, "Pretrain/Step": 5831, "Pretrain/Step Time": 8.437450051307678} +{"Pretrain/Learning Rate": 1.7306883147957383e-05, "Pretrain/Loss": 2.017031192779541, "Pretrain/Loss (Raw)": 2.035029888153076, "Pretrain/Step": 5832, "Pretrain/Step Time": 8.437122462317348} +{"Pretrain/Learning Rate": 1.7298804812697673e-05, "Pretrain/Loss": 2.0190534591674805, "Pretrain/Loss (Raw)": 1.9359971284866333, "Pretrain/Step": 5833, "Pretrain/Step Time": 8.436909126117826} +{"Pretrain/Learning Rate": 1.7290727365768116e-05, "Pretrain/Loss": 2.020524501800537, "Pretrain/Loss (Raw)": 2.056954860687256, "Pretrain/Step": 5834, "Pretrain/Step Time": 8.436413923278451} +{"Pretrain/Learning Rate": 1.7282650808100463e-05, "Pretrain/Loss": 2.0216851234436035, "Pretrain/Loss (Raw)": 2.0640385150909424, "Pretrain/Step": 5835, "Pretrain/Step Time": 8.435428716242313} +{"Pretrain/Learning Rate": 1.7274575140626318e-05, "Pretrain/Loss": 2.0216479301452637, "Pretrain/Loss (Raw)": 1.9991464614868164, "Pretrain/Step": 5836, "Pretrain/Step Time": 8.440658075734973} +{"Pretrain/Learning Rate": 1.7266500364277217e-05, "Pretrain/Loss": 2.019984245300293, "Pretrain/Loss (Raw)": 1.7975503206253052, "Pretrain/Step": 5837, "Pretrain/Step Time": 8.443999072536826} +{"Pretrain/Learning Rate": 1.725842647998458e-05, "Pretrain/Loss": 2.0203309059143066, "Pretrain/Loss (Raw)": 2.033649444580078, "Pretrain/Step": 5838, "Pretrain/Step Time": 8.440281208604574} +{"Pretrain/Learning Rate": 1.7250353488679723e-05, "Pretrain/Loss": 2.020855188369751, "Pretrain/Loss (Raw)": 2.1024715900421143, "Pretrain/Step": 5839, "Pretrain/Step Time": 8.442152876406908} +{"Pretrain/Learning Rate": 1.724228139129388e-05, "Pretrain/Loss": 2.020958662033081, "Pretrain/Loss (Raw)": 2.0267016887664795, "Pretrain/Step": 5840, "Pretrain/Step Time": 8.441473584622145} +{"Pretrain/Learning Rate": 1.7234210188758144e-05, "Pretrain/Loss": 2.0214486122131348, "Pretrain/Loss (Raw)": 1.91187584400177, "Pretrain/Step": 5841, "Pretrain/Step Time": 8.443264316767454} +{"Pretrain/Learning Rate": 1.7226139882003534e-05, "Pretrain/Loss": 2.020078659057617, "Pretrain/Loss (Raw)": 1.9050607681274414, "Pretrain/Step": 5842, "Pretrain/Step Time": 8.445780199021101} +{"Pretrain/Learning Rate": 1.721807047196095e-05, "Pretrain/Loss": 2.0209150314331055, "Pretrain/Loss (Raw)": 2.068695068359375, "Pretrain/Step": 5843, "Pretrain/Step Time": 8.443148650228977} +{"Pretrain/Learning Rate": 1.721000195956121e-05, "Pretrain/Loss": 2.0205776691436768, "Pretrain/Loss (Raw)": 2.0085413455963135, "Pretrain/Step": 5844, "Pretrain/Step Time": 8.44340250827372} +{"Pretrain/Learning Rate": 1.7201934345735012e-05, "Pretrain/Loss": 2.0215096473693848, "Pretrain/Loss (Raw)": 1.907731056213379, "Pretrain/Step": 5845, "Pretrain/Step Time": 8.443692810833454} +{"Pretrain/Learning Rate": 1.719386763141294e-05, "Pretrain/Loss": 2.0210630893707275, "Pretrain/Loss (Raw)": 1.9741382598876953, "Pretrain/Step": 5846, "Pretrain/Step Time": 8.445478774607182} +{"Pretrain/Learning Rate": 1.7185801817525498e-05, "Pretrain/Loss": 2.0226569175720215, "Pretrain/Loss (Raw)": 2.0216944217681885, "Pretrain/Step": 5847, "Pretrain/Step Time": 8.447283774614334} +{"Pretrain/Learning Rate": 1.717773690500306e-05, "Pretrain/Loss": 2.0220632553100586, "Pretrain/Loss (Raw)": 1.906847357749939, "Pretrain/Step": 5848, "Pretrain/Step Time": 8.450273158028722} +{"Pretrain/Learning Rate": 1.7169672894775928e-05, "Pretrain/Loss": 2.020456314086914, "Pretrain/Loss (Raw)": 1.9979438781738281, "Pretrain/Step": 5849, "Pretrain/Step Time": 8.445765141397715} +{"Pretrain/Learning Rate": 1.716160978777427e-05, "Pretrain/Loss": 2.021043062210083, "Pretrain/Loss (Raw)": 2.013822555541992, "Pretrain/Step": 5850, "Pretrain/Step Time": 8.449364304542542} +{"Pretrain/Learning Rate": 1.7153547584928183e-05, "Pretrain/Loss": 2.019864559173584, "Pretrain/Loss (Raw)": 1.906619906425476, "Pretrain/Step": 5851, "Pretrain/Step Time": 8.4468963611871} +{"Pretrain/Learning Rate": 1.714548628716761e-05, "Pretrain/Loss": 2.018807888031006, "Pretrain/Loss (Raw)": 2.008261203765869, "Pretrain/Step": 5852, "Pretrain/Step Time": 8.451719244942069} +{"Pretrain/Learning Rate": 1.7137425895422437e-05, "Pretrain/Loss": 2.016622304916382, "Pretrain/Loss (Raw)": 1.9498223066329956, "Pretrain/Step": 5853, "Pretrain/Step Time": 8.45395553484559} +{"Pretrain/Learning Rate": 1.7129366410622433e-05, "Pretrain/Loss": 2.0183939933776855, "Pretrain/Loss (Raw)": 2.0738320350646973, "Pretrain/Step": 5854, "Pretrain/Step Time": 8.453969961032271} +{"Pretrain/Learning Rate": 1.7121307833697238e-05, "Pretrain/Loss": 2.0188746452331543, "Pretrain/Loss (Raw)": 2.0890419483184814, "Pretrain/Step": 5855, "Pretrain/Step Time": 8.452802730724216} +{"Pretrain/Learning Rate": 1.7113250165576423e-05, "Pretrain/Loss": 2.0186429023742676, "Pretrain/Loss (Raw)": 1.9342924356460571, "Pretrain/Step": 5856, "Pretrain/Step Time": 8.454749219119549} +{"Pretrain/Learning Rate": 1.7105193407189423e-05, "Pretrain/Loss": 2.0165181159973145, "Pretrain/Loss (Raw)": 1.8569345474243164, "Pretrain/Step": 5857, "Pretrain/Step Time": 8.452542254701257} +{"Pretrain/Learning Rate": 1.7097137559465587e-05, "Pretrain/Loss": 2.0171945095062256, "Pretrain/Loss (Raw)": 2.1358680725097656, "Pretrain/Step": 5858, "Pretrain/Step Time": 8.45127939991653} +{"Pretrain/Learning Rate": 1.7089082623334158e-05, "Pretrain/Loss": 2.0157883167266846, "Pretrain/Loss (Raw)": 1.9219979047775269, "Pretrain/Step": 5859, "Pretrain/Step Time": 8.457269685342908} +{"Pretrain/Learning Rate": 1.7081028599724268e-05, "Pretrain/Loss": 2.0142438411712646, "Pretrain/Loss (Raw)": 1.9752248525619507, "Pretrain/Step": 5860, "Pretrain/Step Time": 8.458253072574735} +{"Pretrain/Learning Rate": 1.7072975489564958e-05, "Pretrain/Loss": 2.014392375946045, "Pretrain/Loss (Raw)": 2.0195722579956055, "Pretrain/Step": 5861, "Pretrain/Step Time": 8.45691222883761} +{"Pretrain/Learning Rate": 1.7064923293785127e-05, "Pretrain/Loss": 2.0142626762390137, "Pretrain/Loss (Raw)": 2.10612416267395, "Pretrain/Step": 5862, "Pretrain/Step Time": 8.460246680304408} +{"Pretrain/Learning Rate": 1.705687201331361e-05, "Pretrain/Loss": 2.014984607696533, "Pretrain/Loss (Raw)": 1.9709922075271606, "Pretrain/Step": 5863, "Pretrain/Step Time": 8.462207607924938} +{"Pretrain/Learning Rate": 1.704882164907911e-05, "Pretrain/Loss": 2.0194239616394043, "Pretrain/Loss (Raw)": 2.0540733337402344, "Pretrain/Step": 5864, "Pretrain/Step Time": 8.461001662537456} +{"Pretrain/Learning Rate": 1.704077220201024e-05, "Pretrain/Loss": 2.0177159309387207, "Pretrain/Loss (Raw)": 1.8479454517364502, "Pretrain/Step": 5865, "Pretrain/Step Time": 8.46442142687738} +{"Pretrain/Learning Rate": 1.703272367303551e-05, "Pretrain/Loss": 2.01501727104187, "Pretrain/Loss (Raw)": 1.727077841758728, "Pretrain/Step": 5866, "Pretrain/Step Time": 8.465320641174912} +{"Pretrain/Learning Rate": 1.702467606308329e-05, "Pretrain/Loss": 2.0150222778320312, "Pretrain/Loss (Raw)": 2.0188956260681152, "Pretrain/Step": 5867, "Pretrain/Step Time": 8.464358920231462} +{"Pretrain/Learning Rate": 1.7016629373081887e-05, "Pretrain/Loss": 2.017896890640259, "Pretrain/Loss (Raw)": 2.060661554336548, "Pretrain/Step": 5868, "Pretrain/Step Time": 8.462975945323706} +{"Pretrain/Learning Rate": 1.7008583603959484e-05, "Pretrain/Loss": 2.015235185623169, "Pretrain/Loss (Raw)": 1.6653869152069092, "Pretrain/Step": 5869, "Pretrain/Step Time": 8.469884265214205} +{"Pretrain/Learning Rate": 1.7000538756644152e-05, "Pretrain/Loss": 2.015982151031494, "Pretrain/Loss (Raw)": 2.1525936126708984, "Pretrain/Step": 5870, "Pretrain/Step Time": 8.464248655363917} +{"Pretrain/Learning Rate": 1.699249483206386e-05, "Pretrain/Loss": 2.015484094619751, "Pretrain/Loss (Raw)": 1.9713224172592163, "Pretrain/Step": 5871, "Pretrain/Step Time": 8.462708411738276} +{"Pretrain/Learning Rate": 1.6984451831146488e-05, "Pretrain/Loss": 2.014270305633545, "Pretrain/Loss (Raw)": 1.9240370988845825, "Pretrain/Step": 5872, "Pretrain/Step Time": 8.463237872347236} +{"Pretrain/Learning Rate": 1.6976409754819767e-05, "Pretrain/Loss": 2.012890577316284, "Pretrain/Loss (Raw)": 1.9876066446304321, "Pretrain/Step": 5873, "Pretrain/Step Time": 8.465974962338805} +{"Pretrain/Learning Rate": 1.6968368604011366e-05, "Pretrain/Loss": 2.013495922088623, "Pretrain/Loss (Raw)": 2.078366279602051, "Pretrain/Step": 5874, "Pretrain/Step Time": 8.465028833597898} +{"Pretrain/Learning Rate": 1.6960328379648818e-05, "Pretrain/Loss": 2.015552043914795, "Pretrain/Loss (Raw)": 2.130040407180786, "Pretrain/Step": 5875, "Pretrain/Step Time": 8.467533892020583} +{"Pretrain/Learning Rate": 1.6952289082659567e-05, "Pretrain/Loss": 2.015932321548462, "Pretrain/Loss (Raw)": 1.976433277130127, "Pretrain/Step": 5876, "Pretrain/Step Time": 8.467718159779906} +{"Pretrain/Learning Rate": 1.6944250713970956e-05, "Pretrain/Loss": 2.0158960819244385, "Pretrain/Loss (Raw)": 1.866308331489563, "Pretrain/Step": 5877, "Pretrain/Step Time": 8.466569438576698} +{"Pretrain/Learning Rate": 1.6936213274510183e-05, "Pretrain/Loss": 2.013895034790039, "Pretrain/Loss (Raw)": 1.9669164419174194, "Pretrain/Step": 5878, "Pretrain/Step Time": 8.462806042283773} +{"Pretrain/Learning Rate": 1.692817676520438e-05, "Pretrain/Loss": 2.01231050491333, "Pretrain/Loss (Raw)": 1.8495732545852661, "Pretrain/Step": 5879, "Pretrain/Step Time": 8.466131778433919} +{"Pretrain/Learning Rate": 1.6920141186980544e-05, "Pretrain/Loss": 2.011918306350708, "Pretrain/Loss (Raw)": 2.0927255153656006, "Pretrain/Step": 5880, "Pretrain/Step Time": 8.469945646822453} +{"Pretrain/Learning Rate": 1.6912106540765583e-05, "Pretrain/Loss": 2.0107107162475586, "Pretrain/Loss (Raw)": 1.948782205581665, "Pretrain/Step": 5881, "Pretrain/Step Time": 8.469248542562127} +{"Pretrain/Learning Rate": 1.69040728274863e-05, "Pretrain/Loss": 2.0116240978240967, "Pretrain/Loss (Raw)": 2.0500850677490234, "Pretrain/Step": 5882, "Pretrain/Step Time": 8.469491641968489} +{"Pretrain/Learning Rate": 1.6896040048069362e-05, "Pretrain/Loss": 2.0136711597442627, "Pretrain/Loss (Raw)": 2.147378921508789, "Pretrain/Step": 5883, "Pretrain/Step Time": 8.468881074339151} +{"Pretrain/Learning Rate": 1.6888008203441353e-05, "Pretrain/Loss": 2.013136863708496, "Pretrain/Loss (Raw)": 1.8785649538040161, "Pretrain/Step": 5884, "Pretrain/Step Time": 8.466938149183989} +{"Pretrain/Learning Rate": 1.687997729452875e-05, "Pretrain/Loss": 2.0138044357299805, "Pretrain/Loss (Raw)": 2.04628324508667, "Pretrain/Step": 5885, "Pretrain/Step Time": 8.469163896515965} +{"Pretrain/Learning Rate": 1.6871947322257915e-05, "Pretrain/Loss": 2.0142107009887695, "Pretrain/Loss (Raw)": 2.1356327533721924, "Pretrain/Step": 5886, "Pretrain/Step Time": 8.466244105249643} +{"Pretrain/Learning Rate": 1.6863918287555104e-05, "Pretrain/Loss": 2.0143625736236572, "Pretrain/Loss (Raw)": 2.065288782119751, "Pretrain/Step": 5887, "Pretrain/Step Time": 8.466070588678122} +{"Pretrain/Learning Rate": 1.6855890191346455e-05, "Pretrain/Loss": 2.0145316123962402, "Pretrain/Loss (Raw)": 1.9676088094711304, "Pretrain/Step": 5888, "Pretrain/Step Time": 8.464750466868281} +{"Pretrain/Learning Rate": 1.6847863034558013e-05, "Pretrain/Loss": 2.0130763053894043, "Pretrain/Loss (Raw)": 1.841692328453064, "Pretrain/Step": 5889, "Pretrain/Step Time": 8.466911958530545} +{"Pretrain/Learning Rate": 1.68398368181157e-05, "Pretrain/Loss": 2.010808229446411, "Pretrain/Loss (Raw)": 1.8998980522155762, "Pretrain/Step": 5890, "Pretrain/Step Time": 8.46681453846395} +{"Pretrain/Learning Rate": 1.683181154294534e-05, "Pretrain/Loss": 2.0113823413848877, "Pretrain/Loss (Raw)": 2.0441606044769287, "Pretrain/Step": 5891, "Pretrain/Step Time": 8.466287482529879} +{"Pretrain/Learning Rate": 1.682378720997265e-05, "Pretrain/Loss": 2.0119712352752686, "Pretrain/Loss (Raw)": 2.019925832748413, "Pretrain/Step": 5892, "Pretrain/Step Time": 8.469066293910146} +{"Pretrain/Learning Rate": 1.6815763820123247e-05, "Pretrain/Loss": 2.0112266540527344, "Pretrain/Loss (Raw)": 2.013131856918335, "Pretrain/Step": 5893, "Pretrain/Step Time": 8.468206536024809} +{"Pretrain/Learning Rate": 1.6807741374322596e-05, "Pretrain/Loss": 2.0107789039611816, "Pretrain/Loss (Raw)": 1.9906151294708252, "Pretrain/Step": 5894, "Pretrain/Step Time": 8.471366360783577} +{"Pretrain/Learning Rate": 1.67997198734961e-05, "Pretrain/Loss": 2.0113396644592285, "Pretrain/Loss (Raw)": 2.034360885620117, "Pretrain/Step": 5895, "Pretrain/Step Time": 8.470259184017777} +{"Pretrain/Learning Rate": 1.679169931856904e-05, "Pretrain/Loss": 2.009737491607666, "Pretrain/Loss (Raw)": 1.9780975580215454, "Pretrain/Step": 5896, "Pretrain/Step Time": 8.469577899202704} +{"Pretrain/Learning Rate": 1.678367971046657e-05, "Pretrain/Loss": 2.0086259841918945, "Pretrain/Loss (Raw)": 1.958035945892334, "Pretrain/Step": 5897, "Pretrain/Step Time": 8.469275025650859} +{"Pretrain/Learning Rate": 1.6775661050113772e-05, "Pretrain/Loss": 2.007603645324707, "Pretrain/Loss (Raw)": 2.0178134441375732, "Pretrain/Step": 5898, "Pretrain/Step Time": 8.469291293993592} +{"Pretrain/Learning Rate": 1.6767643338435574e-05, "Pretrain/Loss": 2.0099804401397705, "Pretrain/Loss (Raw)": 1.9586445093154907, "Pretrain/Step": 5899, "Pretrain/Step Time": 8.470825593918562} +{"Pretrain/Learning Rate": 1.675962657635682e-05, "Pretrain/Loss": 2.009202718734741, "Pretrain/Loss (Raw)": 1.9929499626159668, "Pretrain/Step": 5900, "Pretrain/Step Time": 8.467367766425014} +{"Pretrain/Learning Rate": 1.6751610764802245e-05, "Pretrain/Loss": 2.0106124877929688, "Pretrain/Loss (Raw)": 1.965472936630249, "Pretrain/Step": 5901, "Pretrain/Step Time": 8.472085308283567} +{"Pretrain/Learning Rate": 1.674359590469647e-05, "Pretrain/Loss": 2.0063183307647705, "Pretrain/Loss (Raw)": 1.6069263219833374, "Pretrain/Step": 5902, "Pretrain/Step Time": 8.472293179482222} +{"Pretrain/Learning Rate": 1.6735581996964014e-05, "Pretrain/Loss": 2.0051984786987305, "Pretrain/Loss (Raw)": 2.0262887477874756, "Pretrain/Step": 5903, "Pretrain/Step Time": 8.471503552049398} +{"Pretrain/Learning Rate": 1.672756904252926e-05, "Pretrain/Loss": 2.0022826194763184, "Pretrain/Loss (Raw)": 1.758239984512329, "Pretrain/Step": 5904, "Pretrain/Step Time": 8.473073294386268} +{"Pretrain/Learning Rate": 1.671955704231652e-05, "Pretrain/Loss": 2.0042824745178223, "Pretrain/Loss (Raw)": 2.0084519386291504, "Pretrain/Step": 5905, "Pretrain/Step Time": 8.46993139386177} +{"Pretrain/Learning Rate": 1.6711545997249955e-05, "Pretrain/Loss": 2.004746437072754, "Pretrain/Loss (Raw)": 2.020545721054077, "Pretrain/Step": 5906, "Pretrain/Step Time": 8.47071142680943} +{"Pretrain/Learning Rate": 1.670353590825365e-05, "Pretrain/Loss": 2.0046467781066895, "Pretrain/Loss (Raw)": 1.9343383312225342, "Pretrain/Step": 5907, "Pretrain/Step Time": 8.473564270883799} +{"Pretrain/Learning Rate": 1.669552677625156e-05, "Pretrain/Loss": 2.00555419921875, "Pretrain/Loss (Raw)": 2.151447296142578, "Pretrain/Step": 5908, "Pretrain/Step Time": 8.474972376599908} +{"Pretrain/Learning Rate": 1.6687518602167552e-05, "Pretrain/Loss": 2.00467586517334, "Pretrain/Loss (Raw)": 1.967233419418335, "Pretrain/Step": 5909, "Pretrain/Step Time": 8.478041995316744} +{"Pretrain/Learning Rate": 1.6679511386925337e-05, "Pretrain/Loss": 2.0052671432495117, "Pretrain/Loss (Raw)": 1.9662446975708008, "Pretrain/Step": 5910, "Pretrain/Step Time": 8.474292293190956} +{"Pretrain/Learning Rate": 1.667150513144856e-05, "Pretrain/Loss": 2.004568099975586, "Pretrain/Loss (Raw)": 1.8579641580581665, "Pretrain/Step": 5911, "Pretrain/Step Time": 8.473996251821518} +{"Pretrain/Learning Rate": 1.6663499836660745e-05, "Pretrain/Loss": 2.003650665283203, "Pretrain/Loss (Raw)": 1.9108307361602783, "Pretrain/Step": 5912, "Pretrain/Step Time": 8.471528822556138} +{"Pretrain/Learning Rate": 1.665549550348529e-05, "Pretrain/Loss": 2.001063823699951, "Pretrain/Loss (Raw)": 1.754258394241333, "Pretrain/Step": 5913, "Pretrain/Step Time": 8.474268028512597} +{"Pretrain/Learning Rate": 1.6647492132845508e-05, "Pretrain/Loss": 2.001359462738037, "Pretrain/Loss (Raw)": 2.1202170848846436, "Pretrain/Step": 5914, "Pretrain/Step Time": 8.479219987988472} +{"Pretrain/Learning Rate": 1.6639489725664563e-05, "Pretrain/Loss": 2.0011816024780273, "Pretrain/Loss (Raw)": 1.9658019542694092, "Pretrain/Step": 5915, "Pretrain/Step Time": 8.480188837274909} +{"Pretrain/Learning Rate": 1.6631488282865537e-05, "Pretrain/Loss": 1.999717116355896, "Pretrain/Loss (Raw)": 1.9199565649032593, "Pretrain/Step": 5916, "Pretrain/Step Time": 8.479991057887673} +{"Pretrain/Learning Rate": 1.6623487805371397e-05, "Pretrain/Loss": 1.9980655908584595, "Pretrain/Loss (Raw)": 2.0204885005950928, "Pretrain/Step": 5917, "Pretrain/Step Time": 8.480941966176033} +{"Pretrain/Learning Rate": 1.6615488294105e-05, "Pretrain/Loss": 1.996600866317749, "Pretrain/Loss (Raw)": 1.967727541923523, "Pretrain/Step": 5918, "Pretrain/Step Time": 8.480986960232258} +{"Pretrain/Learning Rate": 1.6607489749989087e-05, "Pretrain/Loss": 1.9965660572052002, "Pretrain/Loss (Raw)": 1.982342004776001, "Pretrain/Step": 5919, "Pretrain/Step Time": 8.477289248257875} +{"Pretrain/Learning Rate": 1.659949217394627e-05, "Pretrain/Loss": 1.9961402416229248, "Pretrain/Loss (Raw)": 2.022887706756592, "Pretrain/Step": 5920, "Pretrain/Step Time": 8.481272662058473} +{"Pretrain/Learning Rate": 1.6591495566899085e-05, "Pretrain/Loss": 1.9939765930175781, "Pretrain/Loss (Raw)": 1.8513506650924683, "Pretrain/Step": 5921, "Pretrain/Step Time": 8.479011833667755} +{"Pretrain/Learning Rate": 1.658349992976993e-05, "Pretrain/Loss": 1.9929425716400146, "Pretrain/Loss (Raw)": 1.9773964881896973, "Pretrain/Step": 5922, "Pretrain/Step Time": 8.475973900407553} +{"Pretrain/Learning Rate": 1.6575505263481095e-05, "Pretrain/Loss": 1.9917806386947632, "Pretrain/Loss (Raw)": 2.102123260498047, "Pretrain/Step": 5923, "Pretrain/Step Time": 8.476218407973647} +{"Pretrain/Learning Rate": 1.656751156895478e-05, "Pretrain/Loss": 1.9905261993408203, "Pretrain/Loss (Raw)": 1.938378930091858, "Pretrain/Step": 5924, "Pretrain/Step Time": 8.479994915425777} +{"Pretrain/Learning Rate": 1.6559518847113035e-05, "Pretrain/Loss": 1.9897778034210205, "Pretrain/Loss (Raw)": 1.9843956232070923, "Pretrain/Step": 5925, "Pretrain/Step Time": 8.478711219504476} +{"Pretrain/Learning Rate": 1.655152709887782e-05, "Pretrain/Loss": 1.990410566329956, "Pretrain/Loss (Raw)": 1.9914692640304565, "Pretrain/Step": 5926, "Pretrain/Step Time": 8.477407032623887} +{"Pretrain/Learning Rate": 1.654353632517099e-05, "Pretrain/Loss": 1.9912776947021484, "Pretrain/Loss (Raw)": 2.1000614166259766, "Pretrain/Step": 5927, "Pretrain/Step Time": 8.477293349802494} +{"Pretrain/Learning Rate": 1.6535546526914274e-05, "Pretrain/Loss": 1.9917187690734863, "Pretrain/Loss (Raw)": 2.088449001312256, "Pretrain/Step": 5928, "Pretrain/Step Time": 8.477455982938409} +{"Pretrain/Learning Rate": 1.6527557705029286e-05, "Pretrain/Loss": 1.991263747215271, "Pretrain/Loss (Raw)": 2.0085196495056152, "Pretrain/Step": 5929, "Pretrain/Step Time": 8.476523283869028} +{"Pretrain/Learning Rate": 1.6519569860437547e-05, "Pretrain/Loss": 1.9905014038085938, "Pretrain/Loss (Raw)": 2.079843044281006, "Pretrain/Step": 5930, "Pretrain/Step Time": 8.477313071489334} +{"Pretrain/Learning Rate": 1.6511582994060442e-05, "Pretrain/Loss": 1.9894124269485474, "Pretrain/Loss (Raw)": 1.9506667852401733, "Pretrain/Step": 5931, "Pretrain/Step Time": 8.479834239929914} +{"Pretrain/Learning Rate": 1.6503597106819255e-05, "Pretrain/Loss": 1.9905685186386108, "Pretrain/Loss (Raw)": 1.9408241510391235, "Pretrain/Step": 5932, "Pretrain/Step Time": 8.48043180629611} +{"Pretrain/Learning Rate": 1.6495612199635154e-05, "Pretrain/Loss": 1.9904347658157349, "Pretrain/Loss (Raw)": 1.9992337226867676, "Pretrain/Step": 5933, "Pretrain/Step Time": 8.480603190138936} +{"Pretrain/Learning Rate": 1.6487628273429196e-05, "Pretrain/Loss": 1.991361141204834, "Pretrain/Loss (Raw)": 2.09236478805542, "Pretrain/Step": 5934, "Pretrain/Step Time": 8.481475226581097} +{"Pretrain/Learning Rate": 1.6479645329122333e-05, "Pretrain/Loss": 1.9915014505386353, "Pretrain/Loss (Raw)": 2.0363335609436035, "Pretrain/Step": 5935, "Pretrain/Step Time": 8.479042718186975} +{"Pretrain/Learning Rate": 1.647166336763538e-05, "Pretrain/Loss": 1.992553472518921, "Pretrain/Loss (Raw)": 2.0666065216064453, "Pretrain/Step": 5936, "Pretrain/Step Time": 8.4774199295789} +{"Pretrain/Learning Rate": 1.646368238988906e-05, "Pretrain/Loss": 1.9922599792480469, "Pretrain/Loss (Raw)": 1.9232515096664429, "Pretrain/Step": 5937, "Pretrain/Step Time": 8.481697358191013} +{"Pretrain/Learning Rate": 1.6455702396803983e-05, "Pretrain/Loss": 1.9920566082000732, "Pretrain/Loss (Raw)": 1.9549497365951538, "Pretrain/Step": 5938, "Pretrain/Step Time": 8.4814049936831} +{"Pretrain/Learning Rate": 1.6447723389300623e-05, "Pretrain/Loss": 1.9934134483337402, "Pretrain/Loss (Raw)": 2.1202125549316406, "Pretrain/Step": 5939, "Pretrain/Step Time": 8.481255427002907} +{"Pretrain/Learning Rate": 1.643974536829938e-05, "Pretrain/Loss": 1.9932546615600586, "Pretrain/Loss (Raw)": 2.0696747303009033, "Pretrain/Step": 5940, "Pretrain/Step Time": 8.483519649133086} +{"Pretrain/Learning Rate": 1.6431768334720485e-05, "Pretrain/Loss": 1.993354320526123, "Pretrain/Loss (Raw)": 2.0391743183135986, "Pretrain/Step": 5941, "Pretrain/Step Time": 8.482148746028543} +{"Pretrain/Learning Rate": 1.6423792289484103e-05, "Pretrain/Loss": 1.9935181140899658, "Pretrain/Loss (Raw)": 2.023346185684204, "Pretrain/Step": 5942, "Pretrain/Step Time": 8.483660086989403} +{"Pretrain/Learning Rate": 1.6415817233510266e-05, "Pretrain/Loss": 1.9929628372192383, "Pretrain/Loss (Raw)": 2.041236639022827, "Pretrain/Step": 5943, "Pretrain/Step Time": 8.489194655790925} +{"Pretrain/Learning Rate": 1.6407843167718897e-05, "Pretrain/Loss": 1.9903292655944824, "Pretrain/Loss (Raw)": 1.7363723516464233, "Pretrain/Step": 5944, "Pretrain/Step Time": 8.490056324750185} +{"Pretrain/Learning Rate": 1.6399870093029808e-05, "Pretrain/Loss": 1.9885280132293701, "Pretrain/Loss (Raw)": 1.8092656135559082, "Pretrain/Step": 5945, "Pretrain/Step Time": 8.488035313785076} +{"Pretrain/Learning Rate": 1.639189801036267e-05, "Pretrain/Loss": 1.987143635749817, "Pretrain/Loss (Raw)": 2.006023645401001, "Pretrain/Step": 5946, "Pretrain/Step Time": 8.490620775148273} +{"Pretrain/Learning Rate": 1.6383926920637077e-05, "Pretrain/Loss": 1.9864592552185059, "Pretrain/Loss (Raw)": 2.056094169616699, "Pretrain/Step": 5947, "Pretrain/Step Time": 8.489199863746762} +{"Pretrain/Learning Rate": 1.637595682477248e-05, "Pretrain/Loss": 1.9888765811920166, "Pretrain/Loss (Raw)": 2.327838897705078, "Pretrain/Step": 5948, "Pretrain/Step Time": 8.490809485316277} +{"Pretrain/Learning Rate": 1.6367987723688237e-05, "Pretrain/Loss": 1.985929012298584, "Pretrain/Loss (Raw)": 1.8630633354187012, "Pretrain/Step": 5949, "Pretrain/Step Time": 8.494894377887249} +{"Pretrain/Learning Rate": 1.6360019618303573e-05, "Pretrain/Loss": 1.9871788024902344, "Pretrain/Loss (Raw)": 2.1382431983947754, "Pretrain/Step": 5950, "Pretrain/Step Time": 8.492333436384797} +{"Pretrain/Learning Rate": 1.635205250953762e-05, "Pretrain/Loss": 1.9876270294189453, "Pretrain/Loss (Raw)": 2.1574065685272217, "Pretrain/Step": 5951, "Pretrain/Step Time": 8.493416368961334} +{"Pretrain/Learning Rate": 1.634408639830936e-05, "Pretrain/Loss": 1.9898357391357422, "Pretrain/Loss (Raw)": 2.0597643852233887, "Pretrain/Step": 5952, "Pretrain/Step Time": 8.493583576753736} +{"Pretrain/Learning Rate": 1.6336121285537695e-05, "Pretrain/Loss": 1.990126132965088, "Pretrain/Loss (Raw)": 2.0485804080963135, "Pretrain/Step": 5953, "Pretrain/Step Time": 8.493565056473017} +{"Pretrain/Learning Rate": 1.63281571721414e-05, "Pretrain/Loss": 1.9905147552490234, "Pretrain/Loss (Raw)": 1.9884412288665771, "Pretrain/Step": 5954, "Pretrain/Step Time": 8.489389821887016} +{"Pretrain/Learning Rate": 1.6320194059039118e-05, "Pretrain/Loss": 1.9888628721237183, "Pretrain/Loss (Raw)": 1.8513860702514648, "Pretrain/Step": 5955, "Pretrain/Step Time": 8.494333995506167} +{"Pretrain/Learning Rate": 1.6312231947149413e-05, "Pretrain/Loss": 1.9880975484848022, "Pretrain/Loss (Raw)": 1.86759352684021, "Pretrain/Step": 5956, "Pretrain/Step Time": 8.493986835703254} +{"Pretrain/Learning Rate": 1.6304270837390694e-05, "Pretrain/Loss": 1.9856464862823486, "Pretrain/Loss (Raw)": 1.6018797159194946, "Pretrain/Step": 5957, "Pretrain/Step Time": 8.496163327246904} +{"Pretrain/Learning Rate": 1.6296310730681275e-05, "Pretrain/Loss": 1.9857532978057861, "Pretrain/Loss (Raw)": 2.0786285400390625, "Pretrain/Step": 5958, "Pretrain/Step Time": 8.494375184178352} +{"Pretrain/Learning Rate": 1.628835162793935e-05, "Pretrain/Loss": 1.985049843788147, "Pretrain/Loss (Raw)": 2.1128756999969482, "Pretrain/Step": 5959, "Pretrain/Step Time": 8.498026298359036} +{"Pretrain/Learning Rate": 1.6280393530083012e-05, "Pretrain/Loss": 1.9837205410003662, "Pretrain/Loss (Raw)": 1.8648875951766968, "Pretrain/Step": 5960, "Pretrain/Step Time": 8.496670315042138} +{"Pretrain/Learning Rate": 1.627243643803022e-05, "Pretrain/Loss": 1.9843006134033203, "Pretrain/Loss (Raw)": 2.0102412700653076, "Pretrain/Step": 5961, "Pretrain/Step Time": 8.499833442270756} +{"Pretrain/Learning Rate": 1.6264480352698812e-05, "Pretrain/Loss": 1.9854605197906494, "Pretrain/Loss (Raw)": 2.2054316997528076, "Pretrain/Step": 5962, "Pretrain/Step Time": 8.499252513051033} +{"Pretrain/Learning Rate": 1.6256525275006527e-05, "Pretrain/Loss": 1.985849380493164, "Pretrain/Loss (Raw)": 2.113814353942871, "Pretrain/Step": 5963, "Pretrain/Step Time": 8.500855904072523} +{"Pretrain/Learning Rate": 1.624857120587097e-05, "Pretrain/Loss": 1.985771656036377, "Pretrain/Loss (Raw)": 1.9891996383666992, "Pretrain/Step": 5964, "Pretrain/Step Time": 8.49771561101079} +{"Pretrain/Learning Rate": 1.6240618146209658e-05, "Pretrain/Loss": 1.9870785474777222, "Pretrain/Loss (Raw)": 1.9648147821426392, "Pretrain/Step": 5965, "Pretrain/Step Time": 8.497583547607064} +{"Pretrain/Learning Rate": 1.6232666096939968e-05, "Pretrain/Loss": 1.9884740114212036, "Pretrain/Loss (Raw)": 2.212277412414551, "Pretrain/Step": 5966, "Pretrain/Step Time": 8.497888682410121} +{"Pretrain/Learning Rate": 1.6224715058979157e-05, "Pretrain/Loss": 1.9876394271850586, "Pretrain/Loss (Raw)": 1.9956376552581787, "Pretrain/Step": 5967, "Pretrain/Step Time": 8.496251929551363} +{"Pretrain/Learning Rate": 1.6216765033244377e-05, "Pretrain/Loss": 1.9865745306015015, "Pretrain/Loss (Raw)": 1.8904001712799072, "Pretrain/Step": 5968, "Pretrain/Step Time": 8.496033616364002} +{"Pretrain/Learning Rate": 1.6208816020652666e-05, "Pretrain/Loss": 1.9879860877990723, "Pretrain/Loss (Raw)": 2.0925538539886475, "Pretrain/Step": 5969, "Pretrain/Step Time": 8.493728406727314} +{"Pretrain/Learning Rate": 1.620086802212094e-05, "Pretrain/Loss": 1.9890782833099365, "Pretrain/Loss (Raw)": 2.0448625087738037, "Pretrain/Step": 5970, "Pretrain/Step Time": 8.492770252749324} +{"Pretrain/Learning Rate": 1.6192921038565992e-05, "Pretrain/Loss": 1.9850552082061768, "Pretrain/Loss (Raw)": 1.5537480115890503, "Pretrain/Step": 5971, "Pretrain/Step Time": 8.495442032814026} +{"Pretrain/Learning Rate": 1.618497507090451e-05, "Pretrain/Loss": 1.9861292839050293, "Pretrain/Loss (Raw)": 2.146015167236328, "Pretrain/Step": 5972, "Pretrain/Step Time": 8.495220456272364} +{"Pretrain/Learning Rate": 1.617703012005306e-05, "Pretrain/Loss": 1.9857096672058105, "Pretrain/Loss (Raw)": 1.854021668434143, "Pretrain/Step": 5973, "Pretrain/Step Time": 8.495493141934276} +{"Pretrain/Learning Rate": 1.6169086186928075e-05, "Pretrain/Loss": 1.984473705291748, "Pretrain/Loss (Raw)": 1.8159422874450684, "Pretrain/Step": 5974, "Pretrain/Step Time": 8.493172166869044} +{"Pretrain/Learning Rate": 1.61611432724459e-05, "Pretrain/Loss": 1.9846386909484863, "Pretrain/Loss (Raw)": 2.0427916049957275, "Pretrain/Step": 5975, "Pretrain/Step Time": 8.495739182457328} +{"Pretrain/Learning Rate": 1.615320137752274e-05, "Pretrain/Loss": 1.9856340885162354, "Pretrain/Loss (Raw)": 2.0342745780944824, "Pretrain/Step": 5976, "Pretrain/Step Time": 8.491214863955975} +{"Pretrain/Learning Rate": 1.61452605030747e-05, "Pretrain/Loss": 1.9863359928131104, "Pretrain/Loss (Raw)": 2.0877838134765625, "Pretrain/Step": 5977, "Pretrain/Step Time": 8.492351634427905} +{"Pretrain/Learning Rate": 1.6137320650017743e-05, "Pretrain/Loss": 1.9862139225006104, "Pretrain/Loss (Raw)": 1.9982037544250488, "Pretrain/Step": 5978, "Pretrain/Step Time": 8.491720080375671} +{"Pretrain/Learning Rate": 1.612938181926773e-05, "Pretrain/Loss": 1.9880003929138184, "Pretrain/Loss (Raw)": 2.1352806091308594, "Pretrain/Step": 5979, "Pretrain/Step Time": 8.493510922417045} +{"Pretrain/Learning Rate": 1.6121444011740417e-05, "Pretrain/Loss": 1.9883214235305786, "Pretrain/Loss (Raw)": 2.049362897872925, "Pretrain/Step": 5980, "Pretrain/Step Time": 8.489873362705112} +{"Pretrain/Learning Rate": 1.611350722835141e-05, "Pretrain/Loss": 1.9887168407440186, "Pretrain/Loss (Raw)": 2.000424861907959, "Pretrain/Step": 5981, "Pretrain/Step Time": 8.489367255941033} +{"Pretrain/Learning Rate": 1.610557147001623e-05, "Pretrain/Loss": 1.9883525371551514, "Pretrain/Loss (Raw)": 2.0272116661071777, "Pretrain/Step": 5982, "Pretrain/Step Time": 8.492191946133971} +{"Pretrain/Learning Rate": 1.6097636737650245e-05, "Pretrain/Loss": 1.9875884056091309, "Pretrain/Loss (Raw)": 1.991213321685791, "Pretrain/Step": 5983, "Pretrain/Step Time": 8.493872299790382} +{"Pretrain/Learning Rate": 1.6089703032168733e-05, "Pretrain/Loss": 1.987046480178833, "Pretrain/Loss (Raw)": 1.8649314641952515, "Pretrain/Step": 5984, "Pretrain/Step Time": 8.490242315456271} +{"Pretrain/Learning Rate": 1.6081770354486846e-05, "Pretrain/Loss": 1.9888968467712402, "Pretrain/Loss (Raw)": 2.093780755996704, "Pretrain/Step": 5985, "Pretrain/Step Time": 8.489769598469138} +{"Pretrain/Learning Rate": 1.6073838705519616e-05, "Pretrain/Loss": 1.9877698421478271, "Pretrain/Loss (Raw)": 1.9916259050369263, "Pretrain/Step": 5986, "Pretrain/Step Time": 8.494066653773189} +{"Pretrain/Learning Rate": 1.606590808618196e-05, "Pretrain/Loss": 1.9888657331466675, "Pretrain/Loss (Raw)": 2.062265396118164, "Pretrain/Step": 5987, "Pretrain/Step Time": 8.488452965393662} +{"Pretrain/Learning Rate": 1.6057978497388664e-05, "Pretrain/Loss": 1.9886786937713623, "Pretrain/Loss (Raw)": 1.951291799545288, "Pretrain/Step": 5988, "Pretrain/Step Time": 8.486670829355717} +{"Pretrain/Learning Rate": 1.6050049940054408e-05, "Pretrain/Loss": 1.9882409572601318, "Pretrain/Loss (Raw)": 1.963535189628601, "Pretrain/Step": 5989, "Pretrain/Step Time": 8.486160596832633} +{"Pretrain/Learning Rate": 1.604212241509374e-05, "Pretrain/Loss": 1.987915277481079, "Pretrain/Loss (Raw)": 2.064427614212036, "Pretrain/Step": 5990, "Pretrain/Step Time": 8.48453770019114} +{"Pretrain/Learning Rate": 1.6034195923421105e-05, "Pretrain/Loss": 1.9886970520019531, "Pretrain/Loss (Raw)": 2.0710716247558594, "Pretrain/Step": 5991, "Pretrain/Step Time": 8.485435873270035} +{"Pretrain/Learning Rate": 1.602627046595082e-05, "Pretrain/Loss": 1.9898114204406738, "Pretrain/Loss (Raw)": 2.1967062950134277, "Pretrain/Step": 5992, "Pretrain/Step Time": 8.484069637954235} +{"Pretrain/Learning Rate": 1.6018346043597092e-05, "Pretrain/Loss": 1.9900617599487305, "Pretrain/Loss (Raw)": 1.8799967765808105, "Pretrain/Step": 5993, "Pretrain/Step Time": 8.483897982165217} +{"Pretrain/Learning Rate": 1.601042265727398e-05, "Pretrain/Loss": 1.993731141090393, "Pretrain/Loss (Raw)": 2.1967620849609375, "Pretrain/Step": 5994, "Pretrain/Step Time": 8.482317566871643} +{"Pretrain/Learning Rate": 1.6002500307895458e-05, "Pretrain/Loss": 1.9925837516784668, "Pretrain/Loss (Raw)": 1.872031569480896, "Pretrain/Step": 5995, "Pretrain/Step Time": 8.481088694185019} +{"Pretrain/Learning Rate": 1.5994578996375363e-05, "Pretrain/Loss": 1.9917941093444824, "Pretrain/Loss (Raw)": 1.9595805406570435, "Pretrain/Step": 5996, "Pretrain/Step Time": 8.482795478776097} +{"Pretrain/Learning Rate": 1.598665872362742e-05, "Pretrain/Loss": 1.994449257850647, "Pretrain/Loss (Raw)": 2.005241632461548, "Pretrain/Step": 5997, "Pretrain/Step Time": 8.477369390428066} +{"Pretrain/Learning Rate": 1.5978739490565227e-05, "Pretrain/Loss": 1.9933052062988281, "Pretrain/Loss (Raw)": 2.0061607360839844, "Pretrain/Step": 5998, "Pretrain/Step Time": 8.479868568480015} +{"Pretrain/Learning Rate": 1.5970821298102255e-05, "Pretrain/Loss": 1.9955873489379883, "Pretrain/Loss (Raw)": 2.263427972793579, "Pretrain/Step": 5999, "Pretrain/Step Time": 8.482410298660398} +{"Pretrain/Learning Rate": 1.5962904147151876e-05, "Pretrain/Loss": 1.996711015701294, "Pretrain/Loss (Raw)": 2.0678772926330566, "Pretrain/Step": 6000, "Pretrain/Step Time": 8.481768425554037} +{"Pretrain/Learning Rate": 1.5954988038627328e-05, "Pretrain/Loss": 1.9952391386032104, "Pretrain/Loss (Raw)": 1.7991909980773926, "Pretrain/Step": 6001, "Pretrain/Step Time": 8.482028312981129} +{"Pretrain/Learning Rate": 1.594707297344173e-05, "Pretrain/Loss": 1.9940532445907593, "Pretrain/Loss (Raw)": 1.9265902042388916, "Pretrain/Step": 6002, "Pretrain/Step Time": 8.48299633897841} +{"Pretrain/Learning Rate": 1.5939158952508092e-05, "Pretrain/Loss": 1.9925353527069092, "Pretrain/Loss (Raw)": 1.9357300996780396, "Pretrain/Step": 6003, "Pretrain/Step Time": 8.48141112178564} +{"Pretrain/Learning Rate": 1.593124597673928e-05, "Pretrain/Loss": 1.9930081367492676, "Pretrain/Loss (Raw)": 2.0369679927825928, "Pretrain/Step": 6004, "Pretrain/Step Time": 8.480756940320134} +{"Pretrain/Learning Rate": 1.5923334047048056e-05, "Pretrain/Loss": 1.992653489112854, "Pretrain/Loss (Raw)": 1.8209078311920166, "Pretrain/Step": 6005, "Pretrain/Step Time": 8.481882493942976} +{"Pretrain/Learning Rate": 1.5915423164347055e-05, "Pretrain/Loss": 1.9923065900802612, "Pretrain/Loss (Raw)": 1.9225115776062012, "Pretrain/Step": 6006, "Pretrain/Step Time": 8.483335115015507} +{"Pretrain/Learning Rate": 1.5907513329548802e-05, "Pretrain/Loss": 1.992835521697998, "Pretrain/Loss (Raw)": 1.9172849655151367, "Pretrain/Step": 6007, "Pretrain/Step Time": 8.483996469527483} +{"Pretrain/Learning Rate": 1.589960454356569e-05, "Pretrain/Loss": 1.9878555536270142, "Pretrain/Loss (Raw)": 1.4552781581878662, "Pretrain/Step": 6008, "Pretrain/Step Time": 8.482210917398334} +{"Pretrain/Learning Rate": 1.5891696807310007e-05, "Pretrain/Loss": 1.9899848699569702, "Pretrain/Loss (Raw)": 2.2213351726531982, "Pretrain/Step": 6009, "Pretrain/Step Time": 8.482492916285992} +{"Pretrain/Learning Rate": 1.5883790121693885e-05, "Pretrain/Loss": 1.9900932312011719, "Pretrain/Loss (Raw)": 2.0639700889587402, "Pretrain/Step": 6010, "Pretrain/Step Time": 8.483239633962512} +{"Pretrain/Learning Rate": 1.587588448762937e-05, "Pretrain/Loss": 1.9863755702972412, "Pretrain/Loss (Raw)": 1.671513557434082, "Pretrain/Step": 6011, "Pretrain/Step Time": 8.483169235289097} +{"Pretrain/Learning Rate": 1.586797990602838e-05, "Pretrain/Loss": 1.9888854026794434, "Pretrain/Loss (Raw)": 2.1998178958892822, "Pretrain/Step": 6012, "Pretrain/Step Time": 8.478503545746207} +{"Pretrain/Learning Rate": 1.586007637780269e-05, "Pretrain/Loss": 1.98816978931427, "Pretrain/Loss (Raw)": 1.954689383506775, "Pretrain/Step": 6013, "Pretrain/Step Time": 8.477273529395461} +{"Pretrain/Learning Rate": 1.5852173903863986e-05, "Pretrain/Loss": 1.9884333610534668, "Pretrain/Loss (Raw)": 2.1693577766418457, "Pretrain/Step": 6014, "Pretrain/Step Time": 8.482333330437541} +{"Pretrain/Learning Rate": 1.5844272485123806e-05, "Pretrain/Loss": 1.987218976020813, "Pretrain/Loss (Raw)": 1.9098502397537231, "Pretrain/Step": 6015, "Pretrain/Step Time": 8.483656549826264} +{"Pretrain/Learning Rate": 1.583637212249357e-05, "Pretrain/Loss": 1.9875000715255737, "Pretrain/Loss (Raw)": 2.0035924911499023, "Pretrain/Step": 6016, "Pretrain/Step Time": 8.48532896116376} +{"Pretrain/Learning Rate": 1.5828472816884594e-05, "Pretrain/Loss": 1.989962100982666, "Pretrain/Loss (Raw)": 2.1568195819854736, "Pretrain/Step": 6017, "Pretrain/Step Time": 8.483584307134151} +{"Pretrain/Learning Rate": 1.5820574569208053e-05, "Pretrain/Loss": 1.9902338981628418, "Pretrain/Loss (Raw)": 1.9347059726715088, "Pretrain/Step": 6018, "Pretrain/Step Time": 8.484503315761685} +{"Pretrain/Learning Rate": 1.5812677380375018e-05, "Pretrain/Loss": 1.990167498588562, "Pretrain/Loss (Raw)": 2.035651922225952, "Pretrain/Step": 6019, "Pretrain/Step Time": 8.485240260139108} +{"Pretrain/Learning Rate": 1.5804781251296406e-05, "Pretrain/Loss": 1.9902939796447754, "Pretrain/Loss (Raw)": 2.036099433898926, "Pretrain/Step": 6020, "Pretrain/Step Time": 8.483160316944122} +{"Pretrain/Learning Rate": 1.5796886182883053e-05, "Pretrain/Loss": 1.9899919033050537, "Pretrain/Loss (Raw)": 1.9745031595230103, "Pretrain/Step": 6021, "Pretrain/Step Time": 8.4861925765872} +{"Pretrain/Learning Rate": 1.5788992176045643e-05, "Pretrain/Loss": 1.9910283088684082, "Pretrain/Loss (Raw)": 2.1232643127441406, "Pretrain/Step": 6022, "Pretrain/Step Time": 8.485848432406783} +{"Pretrain/Learning Rate": 1.5781099231694747e-05, "Pretrain/Loss": 1.9915344715118408, "Pretrain/Loss (Raw)": 2.0991556644439697, "Pretrain/Step": 6023, "Pretrain/Step Time": 8.4875443354249} +{"Pretrain/Learning Rate": 1.5773207350740825e-05, "Pretrain/Loss": 1.9921718835830688, "Pretrain/Loss (Raw)": 2.0596706867218018, "Pretrain/Step": 6024, "Pretrain/Step Time": 8.486491311341524} +{"Pretrain/Learning Rate": 1.5765316534094182e-05, "Pretrain/Loss": 1.99214768409729, "Pretrain/Loss (Raw)": 1.9549423456192017, "Pretrain/Step": 6025, "Pretrain/Step Time": 8.48678594827652} +{"Pretrain/Learning Rate": 1.575742678266503e-05, "Pretrain/Loss": 1.992546558380127, "Pretrain/Loss (Raw)": 2.0688819885253906, "Pretrain/Step": 6026, "Pretrain/Step Time": 8.488876102492213} +{"Pretrain/Learning Rate": 1.5749538097363452e-05, "Pretrain/Loss": 1.9923055171966553, "Pretrain/Loss (Raw)": 1.9277958869934082, "Pretrain/Step": 6027, "Pretrain/Step Time": 8.48757435940206} +{"Pretrain/Learning Rate": 1.57416504790994e-05, "Pretrain/Loss": 1.9937578439712524, "Pretrain/Loss (Raw)": 2.1788201332092285, "Pretrain/Step": 6028, "Pretrain/Step Time": 8.488457553088665} +{"Pretrain/Learning Rate": 1.5733763928782723e-05, "Pretrain/Loss": 1.9949119091033936, "Pretrain/Loss (Raw)": 2.1132123470306396, "Pretrain/Step": 6029, "Pretrain/Step Time": 8.48107273131609} +{"Pretrain/Learning Rate": 1.572587844732312e-05, "Pretrain/Loss": 1.9959115982055664, "Pretrain/Loss (Raw)": 1.7348766326904297, "Pretrain/Step": 6030, "Pretrain/Step Time": 8.483737535774708} +{"Pretrain/Learning Rate": 1.5717994035630174e-05, "Pretrain/Loss": 1.9970024824142456, "Pretrain/Loss (Raw)": 2.165919542312622, "Pretrain/Step": 6031, "Pretrain/Step Time": 8.485747067257762} +{"Pretrain/Learning Rate": 1.571011069461335e-05, "Pretrain/Loss": 1.9988559484481812, "Pretrain/Loss (Raw)": 1.9954912662506104, "Pretrain/Step": 6032, "Pretrain/Step Time": 8.484137069433928} +{"Pretrain/Learning Rate": 1.5702228425181995e-05, "Pretrain/Loss": 1.9993579387664795, "Pretrain/Loss (Raw)": 2.072697401046753, "Pretrain/Step": 6033, "Pretrain/Step Time": 8.487628119066358} +{"Pretrain/Learning Rate": 1.569434722824532e-05, "Pretrain/Loss": 2.000581979751587, "Pretrain/Loss (Raw)": 2.1772263050079346, "Pretrain/Step": 6034, "Pretrain/Step Time": 8.487735701724887} +{"Pretrain/Learning Rate": 1.568646710471244e-05, "Pretrain/Loss": 2.001227378845215, "Pretrain/Loss (Raw)": 2.0169265270233154, "Pretrain/Step": 6035, "Pretrain/Step Time": 8.485354639589787} +{"Pretrain/Learning Rate": 1.567858805549229e-05, "Pretrain/Loss": 2.0012927055358887, "Pretrain/Loss (Raw)": 2.1598293781280518, "Pretrain/Step": 6036, "Pretrain/Step Time": 8.486360844224691} +{"Pretrain/Learning Rate": 1.567071008149373e-05, "Pretrain/Loss": 2.002931594848633, "Pretrain/Loss (Raw)": 2.177020788192749, "Pretrain/Step": 6037, "Pretrain/Step Time": 8.484306747093797} +{"Pretrain/Learning Rate": 1.5662833183625493e-05, "Pretrain/Loss": 2.004009485244751, "Pretrain/Loss (Raw)": 2.1042137145996094, "Pretrain/Step": 6038, "Pretrain/Step Time": 8.487699935212731} +{"Pretrain/Learning Rate": 1.5654957362796162e-05, "Pretrain/Loss": 2.0049877166748047, "Pretrain/Loss (Raw)": 1.9831581115722656, "Pretrain/Step": 6039, "Pretrain/Step Time": 8.48581518791616} +{"Pretrain/Learning Rate": 1.564708261991422e-05, "Pretrain/Loss": 2.006754159927368, "Pretrain/Loss (Raw)": 2.1369545459747314, "Pretrain/Step": 6040, "Pretrain/Step Time": 8.491103302687407} +{"Pretrain/Learning Rate": 1.5639208955888007e-05, "Pretrain/Loss": 2.0094573497772217, "Pretrain/Loss (Raw)": 2.1002705097198486, "Pretrain/Step": 6041, "Pretrain/Step Time": 8.487497953698039} +{"Pretrain/Learning Rate": 1.563133637162575e-05, "Pretrain/Loss": 2.008958101272583, "Pretrain/Loss (Raw)": 2.05631422996521, "Pretrain/Step": 6042, "Pretrain/Step Time": 8.482396760955453} +{"Pretrain/Learning Rate": 1.5623464868035548e-05, "Pretrain/Loss": 2.008948802947998, "Pretrain/Loss (Raw)": 1.9646027088165283, "Pretrain/Step": 6043, "Pretrain/Step Time": 8.48497555591166} +{"Pretrain/Learning Rate": 1.561559444602538e-05, "Pretrain/Loss": 2.0100603103637695, "Pretrain/Loss (Raw)": 2.0622050762176514, "Pretrain/Step": 6044, "Pretrain/Step Time": 8.48438080213964} +{"Pretrain/Learning Rate": 1.5607725106503105e-05, "Pretrain/Loss": 2.009256601333618, "Pretrain/Loss (Raw)": 1.9176439046859741, "Pretrain/Step": 6045, "Pretrain/Step Time": 8.480996826663613} +{"Pretrain/Learning Rate": 1.5599856850376426e-05, "Pretrain/Loss": 2.0100436210632324, "Pretrain/Loss (Raw)": 2.068464994430542, "Pretrain/Step": 6046, "Pretrain/Step Time": 8.483200009912252} +{"Pretrain/Learning Rate": 1.5591989678552963e-05, "Pretrain/Loss": 2.010389566421509, "Pretrain/Loss (Raw)": 2.0266242027282715, "Pretrain/Step": 6047, "Pretrain/Step Time": 8.486139740794897} +{"Pretrain/Learning Rate": 1.5584123591940178e-05, "Pretrain/Loss": 2.008275032043457, "Pretrain/Loss (Raw)": 1.7522388696670532, "Pretrain/Step": 6048, "Pretrain/Step Time": 8.486916093155742} +{"Pretrain/Learning Rate": 1.557625859144543e-05, "Pretrain/Loss": 2.00980281829834, "Pretrain/Loss (Raw)": 2.046875238418579, "Pretrain/Step": 6049, "Pretrain/Step Time": 8.490729851648211} +{"Pretrain/Learning Rate": 1.556839467797594e-05, "Pretrain/Loss": 2.009268283843994, "Pretrain/Loss (Raw)": 1.9089852571487427, "Pretrain/Step": 6050, "Pretrain/Step Time": 8.490514751523733} +{"Pretrain/Learning Rate": 1.556053185243882e-05, "Pretrain/Loss": 2.008991241455078, "Pretrain/Loss (Raw)": 2.066667079925537, "Pretrain/Step": 6051, "Pretrain/Step Time": 8.488364888355136} +{"Pretrain/Learning Rate": 1.5552670115741024e-05, "Pretrain/Loss": 2.009716033935547, "Pretrain/Loss (Raw)": 2.0311782360076904, "Pretrain/Step": 6052, "Pretrain/Step Time": 8.48545616865158} +{"Pretrain/Learning Rate": 1.5544809468789407e-05, "Pretrain/Loss": 2.0100202560424805, "Pretrain/Loss (Raw)": 2.0233242511749268, "Pretrain/Step": 6053, "Pretrain/Step Time": 8.490911141037941} +{"Pretrain/Learning Rate": 1.5536949912490702e-05, "Pretrain/Loss": 2.011122941970825, "Pretrain/Loss (Raw)": 2.132613182067871, "Pretrain/Step": 6054, "Pretrain/Step Time": 8.490935277193785} +{"Pretrain/Learning Rate": 1.5529091447751495e-05, "Pretrain/Loss": 2.0111653804779053, "Pretrain/Loss (Raw)": 2.1054694652557373, "Pretrain/Step": 6055, "Pretrain/Step Time": 8.489714503288269} +{"Pretrain/Learning Rate": 1.5521234075478265e-05, "Pretrain/Loss": 2.010944366455078, "Pretrain/Loss (Raw)": 2.060194253921509, "Pretrain/Step": 6056, "Pretrain/Step Time": 8.49112755432725} +{"Pretrain/Learning Rate": 1.5513377796577356e-05, "Pretrain/Loss": 2.008145809173584, "Pretrain/Loss (Raw)": 1.650263786315918, "Pretrain/Step": 6057, "Pretrain/Step Time": 8.488016093149781} +{"Pretrain/Learning Rate": 1.5505522611954975e-05, "Pretrain/Loss": 2.008199453353882, "Pretrain/Loss (Raw)": 2.0867373943328857, "Pretrain/Step": 6058, "Pretrain/Step Time": 8.485463513061404} +{"Pretrain/Learning Rate": 1.549766852251723e-05, "Pretrain/Loss": 2.0087151527404785, "Pretrain/Loss (Raw)": 2.016660690307617, "Pretrain/Step": 6059, "Pretrain/Step Time": 8.479318972676992} +{"Pretrain/Learning Rate": 1.5489815529170078e-05, "Pretrain/Loss": 2.009695053100586, "Pretrain/Loss (Raw)": 2.066239833831787, "Pretrain/Step": 6060, "Pretrain/Step Time": 8.479460408911109} +{"Pretrain/Learning Rate": 1.548196363281937e-05, "Pretrain/Loss": 2.010373115539551, "Pretrain/Loss (Raw)": 2.0860378742218018, "Pretrain/Step": 6061, "Pretrain/Step Time": 8.479632457718253} +{"Pretrain/Learning Rate": 1.5474112834370802e-05, "Pretrain/Loss": 2.0091476440429688, "Pretrain/Loss (Raw)": 1.935538411140442, "Pretrain/Step": 6062, "Pretrain/Step Time": 8.484939452260733} +{"Pretrain/Learning Rate": 1.5466263134729975e-05, "Pretrain/Loss": 2.0073673725128174, "Pretrain/Loss (Raw)": 1.8084341287612915, "Pretrain/Step": 6063, "Pretrain/Step Time": 8.485978044569492} +{"Pretrain/Learning Rate": 1.5458414534802348e-05, "Pretrain/Loss": 2.0062196254730225, "Pretrain/Loss (Raw)": 1.9196914434432983, "Pretrain/Step": 6064, "Pretrain/Step Time": 8.490262571722269} +{"Pretrain/Learning Rate": 1.5450567035493246e-05, "Pretrain/Loss": 2.0066981315612793, "Pretrain/Loss (Raw)": 1.9844908714294434, "Pretrain/Step": 6065, "Pretrain/Step Time": 8.487799489870667} +{"Pretrain/Learning Rate": 1.5442720637707892e-05, "Pretrain/Loss": 2.0086286067962646, "Pretrain/Loss (Raw)": 2.2020623683929443, "Pretrain/Step": 6066, "Pretrain/Step Time": 8.486339712515473} +{"Pretrain/Learning Rate": 1.5434875342351342e-05, "Pretrain/Loss": 2.007171630859375, "Pretrain/Loss (Raw)": 1.9337074756622314, "Pretrain/Step": 6067, "Pretrain/Step Time": 8.487021632492542} +{"Pretrain/Learning Rate": 1.5427031150328563e-05, "Pretrain/Loss": 2.0049166679382324, "Pretrain/Loss (Raw)": 1.7810466289520264, "Pretrain/Step": 6068, "Pretrain/Step Time": 8.484668277204037} +{"Pretrain/Learning Rate": 1.5419188062544374e-05, "Pretrain/Loss": 2.004408836364746, "Pretrain/Loss (Raw)": 1.9741544723510742, "Pretrain/Step": 6069, "Pretrain/Step Time": 8.49133370257914} +{"Pretrain/Learning Rate": 1.5411346079903476e-05, "Pretrain/Loss": 2.0052876472473145, "Pretrain/Loss (Raw)": 2.1358556747436523, "Pretrain/Step": 6070, "Pretrain/Step Time": 8.492990104481578} +{"Pretrain/Learning Rate": 1.540350520331044e-05, "Pretrain/Loss": 2.005162239074707, "Pretrain/Loss (Raw)": 2.0251827239990234, "Pretrain/Step": 6071, "Pretrain/Step Time": 8.484994439408183} +{"Pretrain/Learning Rate": 1.539566543366971e-05, "Pretrain/Loss": 2.008043050765991, "Pretrain/Loss (Raw)": 2.1051225662231445, "Pretrain/Step": 6072, "Pretrain/Step Time": 8.483359079807997} +{"Pretrain/Learning Rate": 1.5387826771885597e-05, "Pretrain/Loss": 2.0097036361694336, "Pretrain/Loss (Raw)": 2.0218210220336914, "Pretrain/Step": 6073, "Pretrain/Step Time": 8.485762944445014} +{"Pretrain/Learning Rate": 1.537998921886228e-05, "Pretrain/Loss": 2.0086090564727783, "Pretrain/Loss (Raw)": 1.8659268617630005, "Pretrain/Step": 6074, "Pretrain/Step Time": 8.485375678166747} +{"Pretrain/Learning Rate": 1.5372152775503827e-05, "Pretrain/Loss": 2.0084261894226074, "Pretrain/Loss (Raw)": 2.032663106918335, "Pretrain/Step": 6075, "Pretrain/Step Time": 8.484285494312644} +{"Pretrain/Learning Rate": 1.536431744271417e-05, "Pretrain/Loss": 2.006505012512207, "Pretrain/Loss (Raw)": 2.0819106101989746, "Pretrain/Step": 6076, "Pretrain/Step Time": 8.481073858216405} +{"Pretrain/Learning Rate": 1.535648322139712e-05, "Pretrain/Loss": 2.0065057277679443, "Pretrain/Loss (Raw)": 1.8631911277770996, "Pretrain/Step": 6077, "Pretrain/Step Time": 8.47994808666408} +{"Pretrain/Learning Rate": 1.534865011245633e-05, "Pretrain/Loss": 2.0073800086975098, "Pretrain/Loss (Raw)": 2.2501208782196045, "Pretrain/Step": 6078, "Pretrain/Step Time": 8.47988161817193} +{"Pretrain/Learning Rate": 1.5340818116795357e-05, "Pretrain/Loss": 2.007112979888916, "Pretrain/Loss (Raw)": 2.12325382232666, "Pretrain/Step": 6079, "Pretrain/Step Time": 8.479900630190969} +{"Pretrain/Learning Rate": 1.5332987235317626e-05, "Pretrain/Loss": 2.0071229934692383, "Pretrain/Loss (Raw)": 2.061037302017212, "Pretrain/Step": 6080, "Pretrain/Step Time": 8.479801101610065} +{"Pretrain/Learning Rate": 1.5325157468926414e-05, "Pretrain/Loss": 2.006725311279297, "Pretrain/Loss (Raw)": 1.9976805448532104, "Pretrain/Step": 6081, "Pretrain/Step Time": 8.48198469541967} +{"Pretrain/Learning Rate": 1.53173288185249e-05, "Pretrain/Loss": 2.0070979595184326, "Pretrain/Loss (Raw)": 2.0361387729644775, "Pretrain/Step": 6082, "Pretrain/Step Time": 8.483308078721166} +{"Pretrain/Learning Rate": 1.5309501285016093e-05, "Pretrain/Loss": 2.008042573928833, "Pretrain/Loss (Raw)": 1.9722933769226074, "Pretrain/Step": 6083, "Pretrain/Step Time": 8.47893838584423} +{"Pretrain/Learning Rate": 1.5301674869302906e-05, "Pretrain/Loss": 2.0089967250823975, "Pretrain/Loss (Raw)": 1.98972487449646, "Pretrain/Step": 6084, "Pretrain/Step Time": 8.48439142294228} +{"Pretrain/Learning Rate": 1.5293849572288117e-05, "Pretrain/Loss": 2.010948657989502, "Pretrain/Loss (Raw)": 1.8517167568206787, "Pretrain/Step": 6085, "Pretrain/Step Time": 8.481980660930276} +{"Pretrain/Learning Rate": 1.5286025394874364e-05, "Pretrain/Loss": 2.0096449851989746, "Pretrain/Loss (Raw)": 1.9117823839187622, "Pretrain/Step": 6086, "Pretrain/Step Time": 8.486978491768241} +{"Pretrain/Learning Rate": 1.5278202337964182e-05, "Pretrain/Loss": 2.0085575580596924, "Pretrain/Loss (Raw)": 1.9736809730529785, "Pretrain/Step": 6087, "Pretrain/Step Time": 8.483699228614569} +{"Pretrain/Learning Rate": 1.5270380402459933e-05, "Pretrain/Loss": 2.008690357208252, "Pretrain/Loss (Raw)": 1.8818718194961548, "Pretrain/Step": 6088, "Pretrain/Step Time": 8.483484387397766} +{"Pretrain/Learning Rate": 1.526255958926389e-05, "Pretrain/Loss": 2.0072474479675293, "Pretrain/Loss (Raw)": 1.8255640268325806, "Pretrain/Step": 6089, "Pretrain/Step Time": 8.481668001040816} +{"Pretrain/Learning Rate": 1.5254739899278173e-05, "Pretrain/Loss": 2.0060184001922607, "Pretrain/Loss (Raw)": 2.0481178760528564, "Pretrain/Step": 6090, "Pretrain/Step Time": 8.483069892972708} +{"Pretrain/Learning Rate": 1.5246921333404784e-05, "Pretrain/Loss": 2.004594326019287, "Pretrain/Loss (Raw)": 1.931522011756897, "Pretrain/Step": 6091, "Pretrain/Step Time": 8.481448067352176} +{"Pretrain/Learning Rate": 1.5239103892545589e-05, "Pretrain/Loss": 2.004883289337158, "Pretrain/Loss (Raw)": 2.026193380355835, "Pretrain/Step": 6092, "Pretrain/Step Time": 8.480492491275072} +{"Pretrain/Learning Rate": 1.5231287577602343e-05, "Pretrain/Loss": 2.0037667751312256, "Pretrain/Loss (Raw)": 1.8218843936920166, "Pretrain/Step": 6093, "Pretrain/Step Time": 8.47998983412981} +{"Pretrain/Learning Rate": 1.5223472389476628e-05, "Pretrain/Loss": 2.001446008682251, "Pretrain/Loss (Raw)": 1.9152191877365112, "Pretrain/Step": 6094, "Pretrain/Step Time": 8.48029631190002} +{"Pretrain/Learning Rate": 1.521565832906994e-05, "Pretrain/Loss": 2.003023147583008, "Pretrain/Loss (Raw)": 2.1975157260894775, "Pretrain/Step": 6095, "Pretrain/Step Time": 8.480400023981929} +{"Pretrain/Learning Rate": 1.520784539728363e-05, "Pretrain/Loss": 2.0048723220825195, "Pretrain/Loss (Raw)": 2.1270976066589355, "Pretrain/Step": 6096, "Pretrain/Step Time": 8.483988659456372} +{"Pretrain/Learning Rate": 1.520003359501891e-05, "Pretrain/Loss": 2.0020592212677, "Pretrain/Loss (Raw)": 1.7324752807617188, "Pretrain/Step": 6097, "Pretrain/Step Time": 8.486828355118632} +{"Pretrain/Learning Rate": 1.519222292317687e-05, "Pretrain/Loss": 2.0026443004608154, "Pretrain/Loss (Raw)": 2.119739532470703, "Pretrain/Step": 6098, "Pretrain/Step Time": 8.488233093172312} +{"Pretrain/Learning Rate": 1.5184413382658471e-05, "Pretrain/Loss": 2.0058984756469727, "Pretrain/Loss (Raw)": 1.9703079462051392, "Pretrain/Step": 6099, "Pretrain/Step Time": 8.48692574724555} +{"Pretrain/Learning Rate": 1.5176604974364533e-05, "Pretrain/Loss": 2.004979133605957, "Pretrain/Loss (Raw)": 2.0283043384552, "Pretrain/Step": 6100, "Pretrain/Step Time": 8.486091457307339} +{"Pretrain/Learning Rate": 1.5168797699195763e-05, "Pretrain/Loss": 2.0066633224487305, "Pretrain/Loss (Raw)": 2.069619655609131, "Pretrain/Step": 6101, "Pretrain/Step Time": 8.48611561767757} +{"Pretrain/Learning Rate": 1.5160991558052722e-05, "Pretrain/Loss": 2.005904197692871, "Pretrain/Loss (Raw)": 1.7187527418136597, "Pretrain/Step": 6102, "Pretrain/Step Time": 8.489945961162448} +{"Pretrain/Learning Rate": 1.5153186551835857e-05, "Pretrain/Loss": 2.007086992263794, "Pretrain/Loss (Raw)": 2.1942014694213867, "Pretrain/Step": 6103, "Pretrain/Step Time": 8.488446339964867} +{"Pretrain/Learning Rate": 1.5145382681445453e-05, "Pretrain/Loss": 2.005248546600342, "Pretrain/Loss (Raw)": 1.7989503145217896, "Pretrain/Step": 6104, "Pretrain/Step Time": 8.490262411534786} +{"Pretrain/Learning Rate": 1.513757994778169e-05, "Pretrain/Loss": 2.005019187927246, "Pretrain/Loss (Raw)": 2.0584490299224854, "Pretrain/Step": 6105, "Pretrain/Step Time": 8.489595964550972} +{"Pretrain/Learning Rate": 1.5129778351744623e-05, "Pretrain/Loss": 2.0045981407165527, "Pretrain/Loss (Raw)": 1.9443185329437256, "Pretrain/Step": 6106, "Pretrain/Step Time": 8.487803783267736} +{"Pretrain/Learning Rate": 1.5121977894234147e-05, "Pretrain/Loss": 2.0026230812072754, "Pretrain/Loss (Raw)": 1.8824487924575806, "Pretrain/Step": 6107, "Pretrain/Step Time": 8.489561293274164} +{"Pretrain/Learning Rate": 1.511417857615005e-05, "Pretrain/Loss": 2.001495361328125, "Pretrain/Loss (Raw)": 1.905003309249878, "Pretrain/Step": 6108, "Pretrain/Step Time": 8.48871960863471} +{"Pretrain/Learning Rate": 1.5106380398391993e-05, "Pretrain/Loss": 2.0022032260894775, "Pretrain/Loss (Raw)": 2.091059684753418, "Pretrain/Step": 6109, "Pretrain/Step Time": 8.485865773633122} +{"Pretrain/Learning Rate": 1.509858336185947e-05, "Pretrain/Loss": 2.0002920627593994, "Pretrain/Loss (Raw)": 1.7825736999511719, "Pretrain/Step": 6110, "Pretrain/Step Time": 8.48359270952642} +{"Pretrain/Learning Rate": 1.5090787467451872e-05, "Pretrain/Loss": 1.9995323419570923, "Pretrain/Loss (Raw)": 1.8939489126205444, "Pretrain/Step": 6111, "Pretrain/Step Time": 8.48450150899589} +{"Pretrain/Learning Rate": 1.5082992716068461e-05, "Pretrain/Loss": 2.001239061355591, "Pretrain/Loss (Raw)": 2.083416223526001, "Pretrain/Step": 6112, "Pretrain/Step Time": 8.485700381919742} +{"Pretrain/Learning Rate": 1.5075199108608357e-05, "Pretrain/Loss": 2.000347852706909, "Pretrain/Loss (Raw)": 1.9796969890594482, "Pretrain/Step": 6113, "Pretrain/Step Time": 8.492931332439184} +{"Pretrain/Learning Rate": 1.506740664597055e-05, "Pretrain/Loss": 2.0001163482666016, "Pretrain/Loss (Raw)": 1.9619673490524292, "Pretrain/Step": 6114, "Pretrain/Step Time": 8.490040538832545} +{"Pretrain/Learning Rate": 1.50596153290539e-05, "Pretrain/Loss": 2.0002987384796143, "Pretrain/Loss (Raw)": 2.085648536682129, "Pretrain/Step": 6115, "Pretrain/Step Time": 8.491065319627523} +{"Pretrain/Learning Rate": 1.5051825158757116e-05, "Pretrain/Loss": 2.0014567375183105, "Pretrain/Loss (Raw)": 2.0995099544525146, "Pretrain/Step": 6116, "Pretrain/Step Time": 8.491698008030653} +{"Pretrain/Learning Rate": 1.5044036135978809e-05, "Pretrain/Loss": 2.0006632804870605, "Pretrain/Loss (Raw)": 1.8619760274887085, "Pretrain/Step": 6117, "Pretrain/Step Time": 8.492199765518308} +{"Pretrain/Learning Rate": 1.5036248261617433e-05, "Pretrain/Loss": 2.001490831375122, "Pretrain/Loss (Raw)": 2.1703338623046875, "Pretrain/Step": 6118, "Pretrain/Step Time": 8.49150069244206} +{"Pretrain/Learning Rate": 1.5028461536571328e-05, "Pretrain/Loss": 2.001030921936035, "Pretrain/Loss (Raw)": 2.012200117111206, "Pretrain/Step": 6119, "Pretrain/Step Time": 8.49442314170301} +{"Pretrain/Learning Rate": 1.5020675961738672e-05, "Pretrain/Loss": 2.0002450942993164, "Pretrain/Loss (Raw)": 2.0961191654205322, "Pretrain/Step": 6120, "Pretrain/Step Time": 8.497459655627608} +{"Pretrain/Learning Rate": 1.5012891538017537e-05, "Pretrain/Loss": 1.9998745918273926, "Pretrain/Loss (Raw)": 1.8325999975204468, "Pretrain/Step": 6121, "Pretrain/Step Time": 8.492512300610542} +{"Pretrain/Learning Rate": 1.5005108266305856e-05, "Pretrain/Loss": 1.9989044666290283, "Pretrain/Loss (Raw)": 2.0725700855255127, "Pretrain/Step": 6122, "Pretrain/Step Time": 8.4919045958668} +{"Pretrain/Learning Rate": 1.4997326147501422e-05, "Pretrain/Loss": 2.0001449584960938, "Pretrain/Loss (Raw)": 2.030794620513916, "Pretrain/Step": 6123, "Pretrain/Step Time": 8.49102190695703} +{"Pretrain/Learning Rate": 1.498954518250191e-05, "Pretrain/Loss": 1.9993655681610107, "Pretrain/Loss (Raw)": 1.8598456382751465, "Pretrain/Step": 6124, "Pretrain/Step Time": 8.489821029826999} +{"Pretrain/Learning Rate": 1.4981765372204834e-05, "Pretrain/Loss": 2.0002365112304688, "Pretrain/Loss (Raw)": 2.1167349815368652, "Pretrain/Step": 6125, "Pretrain/Step Time": 8.487943446263671} +{"Pretrain/Learning Rate": 1.4973986717507599e-05, "Pretrain/Loss": 2.00044584274292, "Pretrain/Loss (Raw)": 2.032928705215454, "Pretrain/Step": 6126, "Pretrain/Step Time": 8.489498794078827} +{"Pretrain/Learning Rate": 1.4966209219307476e-05, "Pretrain/Loss": 1.9995592832565308, "Pretrain/Loss (Raw)": 2.1499454975128174, "Pretrain/Step": 6127, "Pretrain/Step Time": 8.488343270495534} +{"Pretrain/Learning Rate": 1.4958432878501593e-05, "Pretrain/Loss": 2.0001819133758545, "Pretrain/Loss (Raw)": 2.147597074508667, "Pretrain/Step": 6128, "Pretrain/Step Time": 8.488580470904708} +{"Pretrain/Learning Rate": 1.4950657695986952e-05, "Pretrain/Loss": 2.0015363693237305, "Pretrain/Loss (Raw)": 1.9725416898727417, "Pretrain/Step": 6129, "Pretrain/Step Time": 8.485886814072728} +{"Pretrain/Learning Rate": 1.4942883672660418e-05, "Pretrain/Loss": 2.001567840576172, "Pretrain/Loss (Raw)": 1.9306108951568604, "Pretrain/Step": 6130, "Pretrain/Step Time": 8.48970751464367} +{"Pretrain/Learning Rate": 1.4935110809418712e-05, "Pretrain/Loss": 2.002814769744873, "Pretrain/Loss (Raw)": 2.0953609943389893, "Pretrain/Step": 6131, "Pretrain/Step Time": 8.491382379084826} +{"Pretrain/Learning Rate": 1.4927339107158437e-05, "Pretrain/Loss": 2.002598762512207, "Pretrain/Loss (Raw)": 2.009331464767456, "Pretrain/Step": 6132, "Pretrain/Step Time": 8.490854747593403} +{"Pretrain/Learning Rate": 1.4919568566776055e-05, "Pretrain/Loss": 2.0022974014282227, "Pretrain/Loss (Raw)": 1.7823306322097778, "Pretrain/Step": 6133, "Pretrain/Step Time": 8.489466534927487} +{"Pretrain/Learning Rate": 1.4911799189167896e-05, "Pretrain/Loss": 2.0020508766174316, "Pretrain/Loss (Raw)": 1.8909357786178589, "Pretrain/Step": 6134, "Pretrain/Step Time": 8.489276500418782} +{"Pretrain/Learning Rate": 1.4904030975230166e-05, "Pretrain/Loss": 2.003405809402466, "Pretrain/Loss (Raw)": 2.0907297134399414, "Pretrain/Step": 6135, "Pretrain/Step Time": 8.486835880205035} +{"Pretrain/Learning Rate": 1.4896263925858903e-05, "Pretrain/Loss": 2.007493019104004, "Pretrain/Loss (Raw)": 1.9784226417541504, "Pretrain/Step": 6136, "Pretrain/Step Time": 8.486066669225693} +{"Pretrain/Learning Rate": 1.4888498041950045e-05, "Pretrain/Loss": 2.0059618949890137, "Pretrain/Loss (Raw)": 2.0253660678863525, "Pretrain/Step": 6137, "Pretrain/Step Time": 8.485726794227958} +{"Pretrain/Learning Rate": 1.4880733324399394e-05, "Pretrain/Loss": 2.004058837890625, "Pretrain/Loss (Raw)": 1.820386290550232, "Pretrain/Step": 6138, "Pretrain/Step Time": 8.486860897392035} +{"Pretrain/Learning Rate": 1.4872969774102589e-05, "Pretrain/Loss": 2.0064873695373535, "Pretrain/Loss (Raw)": 1.9823371171951294, "Pretrain/Step": 6139, "Pretrain/Step Time": 8.4854297041893} +{"Pretrain/Learning Rate": 1.4865207391955171e-05, "Pretrain/Loss": 2.0056138038635254, "Pretrain/Loss (Raw)": 2.088043212890625, "Pretrain/Step": 6140, "Pretrain/Step Time": 8.48490091226995} +{"Pretrain/Learning Rate": 1.485744617885251e-05, "Pretrain/Loss": 2.0070109367370605, "Pretrain/Loss (Raw)": 2.1335084438323975, "Pretrain/Step": 6141, "Pretrain/Step Time": 8.485258273780346} +{"Pretrain/Learning Rate": 1.484968613568987e-05, "Pretrain/Loss": 2.00618314743042, "Pretrain/Loss (Raw)": 2.0633702278137207, "Pretrain/Step": 6142, "Pretrain/Step Time": 8.483486473560333} +{"Pretrain/Learning Rate": 1.4841927263362365e-05, "Pretrain/Loss": 2.0055174827575684, "Pretrain/Loss (Raw)": 1.8246474266052246, "Pretrain/Step": 6143, "Pretrain/Step Time": 8.482583655044436} +{"Pretrain/Learning Rate": 1.483416956276498e-05, "Pretrain/Loss": 2.0057425498962402, "Pretrain/Loss (Raw)": 2.032409906387329, "Pretrain/Step": 6144, "Pretrain/Step Time": 8.48717755638063} +{"Pretrain/Learning Rate": 1.4826413034792574e-05, "Pretrain/Loss": 2.0046780109405518, "Pretrain/Loss (Raw)": 2.0205533504486084, "Pretrain/Step": 6145, "Pretrain/Step Time": 8.486849701032043} +{"Pretrain/Learning Rate": 1.481865768033984e-05, "Pretrain/Loss": 2.006030559539795, "Pretrain/Loss (Raw)": 2.1078338623046875, "Pretrain/Step": 6146, "Pretrain/Step Time": 8.490937808528543} +{"Pretrain/Learning Rate": 1.4810903500301365e-05, "Pretrain/Loss": 2.004565954208374, "Pretrain/Loss (Raw)": 1.8481744527816772, "Pretrain/Step": 6147, "Pretrain/Step Time": 8.490999169647694} +{"Pretrain/Learning Rate": 1.4803150495571594e-05, "Pretrain/Loss": 1.9993664026260376, "Pretrain/Loss (Raw)": 1.3705811500549316, "Pretrain/Step": 6148, "Pretrain/Step Time": 8.494114762172103} +{"Pretrain/Learning Rate": 1.4795398667044824e-05, "Pretrain/Loss": 2.000293731689453, "Pretrain/Loss (Raw)": 2.0931928157806396, "Pretrain/Step": 6149, "Pretrain/Step Time": 8.493068100884557} +{"Pretrain/Learning Rate": 1.4787648015615235e-05, "Pretrain/Loss": 1.9985864162445068, "Pretrain/Loss (Raw)": 1.9047237634658813, "Pretrain/Step": 6150, "Pretrain/Step Time": 8.489120932295918} +{"Pretrain/Learning Rate": 1.4779898542176865e-05, "Pretrain/Loss": 1.998777985572815, "Pretrain/Loss (Raw)": 2.123694658279419, "Pretrain/Step": 6151, "Pretrain/Step Time": 8.491005102172494} +{"Pretrain/Learning Rate": 1.4772150247623598e-05, "Pretrain/Loss": 1.997571349143982, "Pretrain/Loss (Raw)": 1.905221700668335, "Pretrain/Step": 6152, "Pretrain/Step Time": 8.490102246403694} +{"Pretrain/Learning Rate": 1.4764403132849205e-05, "Pretrain/Loss": 1.997305154800415, "Pretrain/Loss (Raw)": 1.9208592176437378, "Pretrain/Step": 6153, "Pretrain/Step Time": 8.489792155101895} +{"Pretrain/Learning Rate": 1.4756657198747314e-05, "Pretrain/Loss": 1.9964752197265625, "Pretrain/Loss (Raw)": 1.9626470804214478, "Pretrain/Step": 6154, "Pretrain/Step Time": 8.48813553713262} +{"Pretrain/Learning Rate": 1.4748912446211422e-05, "Pretrain/Loss": 1.9973013401031494, "Pretrain/Loss (Raw)": 2.0335164070129395, "Pretrain/Step": 6155, "Pretrain/Step Time": 8.488400211557746} +{"Pretrain/Learning Rate": 1.4741168876134876e-05, "Pretrain/Loss": 1.9960217475891113, "Pretrain/Loss (Raw)": 2.0150558948516846, "Pretrain/Step": 6156, "Pretrain/Step Time": 8.488182419911027} +{"Pretrain/Learning Rate": 1.4733426489410895e-05, "Pretrain/Loss": 1.995770812034607, "Pretrain/Loss (Raw)": 2.0810985565185547, "Pretrain/Step": 6157, "Pretrain/Step Time": 8.48997326940298} +{"Pretrain/Learning Rate": 1.4725685286932556e-05, "Pretrain/Loss": 1.9970972537994385, "Pretrain/Loss (Raw)": 1.9046586751937866, "Pretrain/Step": 6158, "Pretrain/Step Time": 8.485654281452298} +{"Pretrain/Learning Rate": 1.4717945269592803e-05, "Pretrain/Loss": 1.9950040578842163, "Pretrain/Loss (Raw)": 1.8979859352111816, "Pretrain/Step": 6159, "Pretrain/Step Time": 8.487193129956722} +{"Pretrain/Learning Rate": 1.4710206438284457e-05, "Pretrain/Loss": 1.9939591884613037, "Pretrain/Loss (Raw)": 1.8617523908615112, "Pretrain/Step": 6160, "Pretrain/Step Time": 8.488651189953089} +{"Pretrain/Learning Rate": 1.4702468793900188e-05, "Pretrain/Loss": 1.992615818977356, "Pretrain/Loss (Raw)": 1.900740385055542, "Pretrain/Step": 6161, "Pretrain/Step Time": 8.487318011000752} +{"Pretrain/Learning Rate": 1.4694732337332517e-05, "Pretrain/Loss": 1.9910907745361328, "Pretrain/Loss (Raw)": 1.9820294380187988, "Pretrain/Step": 6162, "Pretrain/Step Time": 8.48502498306334} +{"Pretrain/Learning Rate": 1.468699706947385e-05, "Pretrain/Loss": 1.9903106689453125, "Pretrain/Loss (Raw)": 1.917063593864441, "Pretrain/Step": 6163, "Pretrain/Step Time": 8.485405370593071} +{"Pretrain/Learning Rate": 1.467926299121645e-05, "Pretrain/Loss": 1.9891636371612549, "Pretrain/Loss (Raw)": 2.0130271911621094, "Pretrain/Step": 6164, "Pretrain/Step Time": 8.48651478253305} +{"Pretrain/Learning Rate": 1.467153010345243e-05, "Pretrain/Loss": 1.9887669086456299, "Pretrain/Loss (Raw)": 2.1262261867523193, "Pretrain/Step": 6165, "Pretrain/Step Time": 8.485961066558957} +{"Pretrain/Learning Rate": 1.4663798407073799e-05, "Pretrain/Loss": 1.9882454872131348, "Pretrain/Loss (Raw)": 2.0374691486358643, "Pretrain/Step": 6166, "Pretrain/Step Time": 8.488007578998804} +{"Pretrain/Learning Rate": 1.4656067902972375e-05, "Pretrain/Loss": 1.9873263835906982, "Pretrain/Loss (Raw)": 1.8655093908309937, "Pretrain/Step": 6167, "Pretrain/Step Time": 8.492634924128652} +{"Pretrain/Learning Rate": 1.4648338592039884e-05, "Pretrain/Loss": 1.987644910812378, "Pretrain/Loss (Raw)": 2.177743673324585, "Pretrain/Step": 6168, "Pretrain/Step Time": 8.48481473326683} +{"Pretrain/Learning Rate": 1.4640610475167898e-05, "Pretrain/Loss": 1.986579179763794, "Pretrain/Loss (Raw)": 1.9638527631759644, "Pretrain/Step": 6169, "Pretrain/Step Time": 8.485511453822255} +{"Pretrain/Learning Rate": 1.4632883553247854e-05, "Pretrain/Loss": 1.9861592054367065, "Pretrain/Loss (Raw)": 2.0025558471679688, "Pretrain/Step": 6170, "Pretrain/Step Time": 8.48312996327877} +{"Pretrain/Learning Rate": 1.4625157827171054e-05, "Pretrain/Loss": 1.9872092008590698, "Pretrain/Loss (Raw)": 2.098998785018921, "Pretrain/Step": 6171, "Pretrain/Step Time": 8.4796819742769} +{"Pretrain/Learning Rate": 1.461743329782865e-05, "Pretrain/Loss": 1.9856092929840088, "Pretrain/Loss (Raw)": 1.8574285507202148, "Pretrain/Step": 6172, "Pretrain/Step Time": 8.48067975975573} +{"Pretrain/Learning Rate": 1.4609709966111668e-05, "Pretrain/Loss": 1.9867445230484009, "Pretrain/Loss (Raw)": 2.062941551208496, "Pretrain/Step": 6173, "Pretrain/Step Time": 8.48283770121634} +{"Pretrain/Learning Rate": 1.4601987832910988e-05, "Pretrain/Loss": 1.9867808818817139, "Pretrain/Loss (Raw)": 2.0731306076049805, "Pretrain/Step": 6174, "Pretrain/Step Time": 8.481407457962632} +{"Pretrain/Learning Rate": 1.4594266899117348e-05, "Pretrain/Loss": 1.986959457397461, "Pretrain/Loss (Raw)": 2.049482583999634, "Pretrain/Step": 6175, "Pretrain/Step Time": 8.476738886907697} +{"Pretrain/Learning Rate": 1.4586547165621384e-05, "Pretrain/Loss": 1.988617181777954, "Pretrain/Loss (Raw)": 1.9644241333007812, "Pretrain/Step": 6176, "Pretrain/Step Time": 8.476158669218421} +{"Pretrain/Learning Rate": 1.457882863331353e-05, "Pretrain/Loss": 1.9883066415786743, "Pretrain/Loss (Raw)": 2.0071167945861816, "Pretrain/Step": 6177, "Pretrain/Step Time": 8.474383912980556} +{"Pretrain/Learning Rate": 1.4571111303084145e-05, "Pretrain/Loss": 1.989328384399414, "Pretrain/Loss (Raw)": 2.039776563644409, "Pretrain/Step": 6178, "Pretrain/Step Time": 8.47462554462254} +{"Pretrain/Learning Rate": 1.4563395175823394e-05, "Pretrain/Loss": 1.9882384538650513, "Pretrain/Loss (Raw)": 1.927148461341858, "Pretrain/Step": 6179, "Pretrain/Step Time": 8.477888425812125} +{"Pretrain/Learning Rate": 1.4555680252421341e-05, "Pretrain/Loss": 1.9864333868026733, "Pretrain/Loss (Raw)": 1.8001337051391602, "Pretrain/Step": 6180, "Pretrain/Step Time": 8.476750526577234} +{"Pretrain/Learning Rate": 1.4547966533767904e-05, "Pretrain/Loss": 1.9864941835403442, "Pretrain/Loss (Raw)": 2.031107187271118, "Pretrain/Step": 6181, "Pretrain/Step Time": 8.470692038536072} +{"Pretrain/Learning Rate": 1.4540254020752859e-05, "Pretrain/Loss": 1.9849176406860352, "Pretrain/Loss (Raw)": 1.9308034181594849, "Pretrain/Step": 6182, "Pretrain/Step Time": 8.471873437985778} +{"Pretrain/Learning Rate": 1.4532542714265829e-05, "Pretrain/Loss": 1.9837560653686523, "Pretrain/Loss (Raw)": 1.9567943811416626, "Pretrain/Step": 6183, "Pretrain/Step Time": 8.475225456058979} +{"Pretrain/Learning Rate": 1.452483261519632e-05, "Pretrain/Loss": 1.982005000114441, "Pretrain/Loss (Raw)": 1.8360694646835327, "Pretrain/Step": 6184, "Pretrain/Step Time": 8.474629767239094} +{"Pretrain/Learning Rate": 1.4517123724433686e-05, "Pretrain/Loss": 1.9837672710418701, "Pretrain/Loss (Raw)": 1.8758383989334106, "Pretrain/Step": 6185, "Pretrain/Step Time": 8.47619367390871} +{"Pretrain/Learning Rate": 1.4509416042867149e-05, "Pretrain/Loss": 1.9826927185058594, "Pretrain/Loss (Raw)": 1.9491933584213257, "Pretrain/Step": 6186, "Pretrain/Step Time": 8.477555317804217} +{"Pretrain/Learning Rate": 1.450170957138579e-05, "Pretrain/Loss": 1.9835515022277832, "Pretrain/Loss (Raw)": 2.126574993133545, "Pretrain/Step": 6187, "Pretrain/Step Time": 8.47917297668755} +{"Pretrain/Learning Rate": 1.449400431087854e-05, "Pretrain/Loss": 1.9828507900238037, "Pretrain/Loss (Raw)": 1.9765512943267822, "Pretrain/Step": 6188, "Pretrain/Step Time": 8.47607689164579} +{"Pretrain/Learning Rate": 1.4486300262234193e-05, "Pretrain/Loss": 1.980236530303955, "Pretrain/Loss (Raw)": 1.751397967338562, "Pretrain/Step": 6189, "Pretrain/Step Time": 8.475907510146499} +{"Pretrain/Learning Rate": 1.4478597426341422e-05, "Pretrain/Loss": 1.9799466133117676, "Pretrain/Loss (Raw)": 1.898434042930603, "Pretrain/Step": 6190, "Pretrain/Step Time": 8.474589684978127} +{"Pretrain/Learning Rate": 1.4470895804088736e-05, "Pretrain/Loss": 1.9819387197494507, "Pretrain/Loss (Raw)": 2.063432455062866, "Pretrain/Step": 6191, "Pretrain/Step Time": 8.473373912274837} +{"Pretrain/Learning Rate": 1.4463195396364531e-05, "Pretrain/Loss": 1.9824411869049072, "Pretrain/Loss (Raw)": 1.984015941619873, "Pretrain/Step": 6192, "Pretrain/Step Time": 8.470870347693563} +{"Pretrain/Learning Rate": 1.4455496204057023e-05, "Pretrain/Loss": 1.9818549156188965, "Pretrain/Loss (Raw)": 1.909434199333191, "Pretrain/Step": 6193, "Pretrain/Step Time": 8.470529107376933} +{"Pretrain/Learning Rate": 1.4447798228054333e-05, "Pretrain/Loss": 1.9815555810928345, "Pretrain/Loss (Raw)": 2.1637580394744873, "Pretrain/Step": 6194, "Pretrain/Step Time": 8.47444406338036} +{"Pretrain/Learning Rate": 1.44401014692444e-05, "Pretrain/Loss": 1.9831557273864746, "Pretrain/Loss (Raw)": 2.138531446456909, "Pretrain/Step": 6195, "Pretrain/Step Time": 8.476440185680985} +{"Pretrain/Learning Rate": 1.443240592851505e-05, "Pretrain/Loss": 1.9834144115447998, "Pretrain/Loss (Raw)": 1.8141461610794067, "Pretrain/Step": 6196, "Pretrain/Step Time": 8.478626457974315} +{"Pretrain/Learning Rate": 1.4424711606753964e-05, "Pretrain/Loss": 1.9833621978759766, "Pretrain/Loss (Raw)": 1.9674721956253052, "Pretrain/Step": 6197, "Pretrain/Step Time": 8.472807012498379} +{"Pretrain/Learning Rate": 1.4417018504848684e-05, "Pretrain/Loss": 1.9829471111297607, "Pretrain/Loss (Raw)": 2.0827291011810303, "Pretrain/Step": 6198, "Pretrain/Step Time": 8.470351941883564} +{"Pretrain/Learning Rate": 1.4409326623686592e-05, "Pretrain/Loss": 1.9799292087554932, "Pretrain/Loss (Raw)": 1.6388940811157227, "Pretrain/Step": 6199, "Pretrain/Step Time": 8.474599922075868} +{"Pretrain/Learning Rate": 1.4401635964154956e-05, "Pretrain/Loss": 1.9785282611846924, "Pretrain/Loss (Raw)": 1.925794243812561, "Pretrain/Step": 6200, "Pretrain/Step Time": 8.474543757736683} +{"Pretrain/Learning Rate": 1.4393946527140884e-05, "Pretrain/Loss": 1.9784471988677979, "Pretrain/Loss (Raw)": 2.0114521980285645, "Pretrain/Step": 6201, "Pretrain/Step Time": 8.474182175472379} +{"Pretrain/Learning Rate": 1.4386258313531353e-05, "Pretrain/Loss": 1.979915738105774, "Pretrain/Loss (Raw)": 2.0539004802703857, "Pretrain/Step": 6202, "Pretrain/Step Time": 8.47064707428217} +{"Pretrain/Learning Rate": 1.4378571324213203e-05, "Pretrain/Loss": 1.9796435832977295, "Pretrain/Loss (Raw)": 1.9978139400482178, "Pretrain/Step": 6203, "Pretrain/Step Time": 8.470766263082623} +{"Pretrain/Learning Rate": 1.437088556007311e-05, "Pretrain/Loss": 1.9786875247955322, "Pretrain/Loss (Raw)": 1.9595413208007812, "Pretrain/Step": 6204, "Pretrain/Step Time": 8.472110876813531} +{"Pretrain/Learning Rate": 1.4363201021997635e-05, "Pretrain/Loss": 1.9813711643218994, "Pretrain/Loss (Raw)": 2.2067058086395264, "Pretrain/Step": 6205, "Pretrain/Step Time": 8.471388351172209} +{"Pretrain/Learning Rate": 1.4355517710873184e-05, "Pretrain/Loss": 1.977985143661499, "Pretrain/Loss (Raw)": 1.8166942596435547, "Pretrain/Step": 6206, "Pretrain/Step Time": 8.468188047409058} +{"Pretrain/Learning Rate": 1.434783562758602e-05, "Pretrain/Loss": 1.978184461593628, "Pretrain/Loss (Raw)": 2.148775100708008, "Pretrain/Step": 6207, "Pretrain/Step Time": 8.468530947342515} +{"Pretrain/Learning Rate": 1.4340154773022286e-05, "Pretrain/Loss": 1.9770511388778687, "Pretrain/Loss (Raw)": 1.9159730672836304, "Pretrain/Step": 6208, "Pretrain/Step Time": 8.472945041954517} +{"Pretrain/Learning Rate": 1.4332475148067943e-05, "Pretrain/Loss": 1.97597074508667, "Pretrain/Loss (Raw)": 1.8593782186508179, "Pretrain/Step": 6209, "Pretrain/Step Time": 8.470071464776993} +{"Pretrain/Learning Rate": 1.4324796753608841e-05, "Pretrain/Loss": 1.9757827520370483, "Pretrain/Loss (Raw)": 2.012078046798706, "Pretrain/Step": 6210, "Pretrain/Step Time": 8.471854120492935} +{"Pretrain/Learning Rate": 1.4317119590530692e-05, "Pretrain/Loss": 1.9747209548950195, "Pretrain/Loss (Raw)": 1.836395025253296, "Pretrain/Step": 6211, "Pretrain/Step Time": 8.471954956650734} +{"Pretrain/Learning Rate": 1.4309443659719036e-05, "Pretrain/Loss": 1.9758708477020264, "Pretrain/Loss (Raw)": 2.1368937492370605, "Pretrain/Step": 6212, "Pretrain/Step Time": 8.469474552199244} +{"Pretrain/Learning Rate": 1.4301768962059295e-05, "Pretrain/Loss": 1.9767054319381714, "Pretrain/Loss (Raw)": 1.9585543870925903, "Pretrain/Step": 6213, "Pretrain/Step Time": 8.469683922827244} +{"Pretrain/Learning Rate": 1.4294095498436755e-05, "Pretrain/Loss": 1.978039026260376, "Pretrain/Loss (Raw)": 2.0824711322784424, "Pretrain/Step": 6214, "Pretrain/Step Time": 8.4681287240237} +{"Pretrain/Learning Rate": 1.4286423269736526e-05, "Pretrain/Loss": 1.9792903661727905, "Pretrain/Loss (Raw)": 2.133864402770996, "Pretrain/Step": 6215, "Pretrain/Step Time": 8.467937117442489} +{"Pretrain/Learning Rate": 1.427875227684361e-05, "Pretrain/Loss": 1.9808216094970703, "Pretrain/Loss (Raw)": 2.0778799057006836, "Pretrain/Step": 6216, "Pretrain/Step Time": 8.470932697877288} +{"Pretrain/Learning Rate": 1.4271082520642854e-05, "Pretrain/Loss": 1.9826393127441406, "Pretrain/Loss (Raw)": 2.0582103729248047, "Pretrain/Step": 6217, "Pretrain/Step Time": 8.468371560797095} +{"Pretrain/Learning Rate": 1.4263414002018955e-05, "Pretrain/Loss": 1.9824182987213135, "Pretrain/Loss (Raw)": 2.0198419094085693, "Pretrain/Step": 6218, "Pretrain/Step Time": 8.466177683323622} +{"Pretrain/Learning Rate": 1.4255746721856486e-05, "Pretrain/Loss": 1.9848874807357788, "Pretrain/Loss (Raw)": 2.2475767135620117, "Pretrain/Step": 6219, "Pretrain/Step Time": 8.466121869161725} +{"Pretrain/Learning Rate": 1.424808068103985e-05, "Pretrain/Loss": 1.9832839965820312, "Pretrain/Loss (Raw)": 1.820939302444458, "Pretrain/Step": 6220, "Pretrain/Step Time": 8.463826293125749} +{"Pretrain/Learning Rate": 1.4240415880453326e-05, "Pretrain/Loss": 1.9844926595687866, "Pretrain/Loss (Raw)": 1.9766042232513428, "Pretrain/Step": 6221, "Pretrain/Step Time": 8.46355452015996} +{"Pretrain/Learning Rate": 1.4232752320981052e-05, "Pretrain/Loss": 1.9845731258392334, "Pretrain/Loss (Raw)": 1.9255207777023315, "Pretrain/Step": 6222, "Pretrain/Step Time": 8.466029319912195} +{"Pretrain/Learning Rate": 1.4225090003507013e-05, "Pretrain/Loss": 1.9835014343261719, "Pretrain/Loss (Raw)": 2.0603373050689697, "Pretrain/Step": 6223, "Pretrain/Step Time": 8.467204520478845} +{"Pretrain/Learning Rate": 1.4217428928915064e-05, "Pretrain/Loss": 1.9820023775100708, "Pretrain/Loss (Raw)": 1.9352163076400757, "Pretrain/Step": 6224, "Pretrain/Step Time": 8.465623524039984} +{"Pretrain/Learning Rate": 1.4209769098088888e-05, "Pretrain/Loss": 1.9844107627868652, "Pretrain/Loss (Raw)": 2.040743589401245, "Pretrain/Step": 6225, "Pretrain/Step Time": 8.462701138108969} +{"Pretrain/Learning Rate": 1.420211051191206e-05, "Pretrain/Loss": 1.9828170537948608, "Pretrain/Loss (Raw)": 1.9157390594482422, "Pretrain/Step": 6226, "Pretrain/Step Time": 8.460310481488705} +{"Pretrain/Learning Rate": 1.4194453171267996e-05, "Pretrain/Loss": 1.9825222492218018, "Pretrain/Loss (Raw)": 1.9325765371322632, "Pretrain/Step": 6227, "Pretrain/Step Time": 8.462125711143017} +{"Pretrain/Learning Rate": 1.4186797077039948e-05, "Pretrain/Loss": 1.9822148084640503, "Pretrain/Loss (Raw)": 1.9889529943466187, "Pretrain/Step": 6228, "Pretrain/Step Time": 8.461497573181987} +{"Pretrain/Learning Rate": 1.4179142230111065e-05, "Pretrain/Loss": 1.9809035062789917, "Pretrain/Loss (Raw)": 1.9017810821533203, "Pretrain/Step": 6229, "Pretrain/Step Time": 8.460509041324258} +{"Pretrain/Learning Rate": 1.4171488631364327e-05, "Pretrain/Loss": 1.9811850786209106, "Pretrain/Loss (Raw)": 1.7547869682312012, "Pretrain/Step": 6230, "Pretrain/Step Time": 8.455964608117938} +{"Pretrain/Learning Rate": 1.4163836281682563e-05, "Pretrain/Loss": 1.9800573587417603, "Pretrain/Loss (Raw)": 2.0498507022857666, "Pretrain/Step": 6231, "Pretrain/Step Time": 8.458944708108902} +{"Pretrain/Learning Rate": 1.4156185181948473e-05, "Pretrain/Loss": 1.9820303916931152, "Pretrain/Loss (Raw)": 2.051490545272827, "Pretrain/Step": 6232, "Pretrain/Step Time": 8.457260522991419} +{"Pretrain/Learning Rate": 1.4148535333044613e-05, "Pretrain/Loss": 1.980843424797058, "Pretrain/Loss (Raw)": 1.9065243005752563, "Pretrain/Step": 6233, "Pretrain/Step Time": 8.458720380440354} +{"Pretrain/Learning Rate": 1.4140886735853387e-05, "Pretrain/Loss": 1.981170654296875, "Pretrain/Loss (Raw)": 1.9862061738967896, "Pretrain/Step": 6234, "Pretrain/Step Time": 8.458718180656433} +{"Pretrain/Learning Rate": 1.4133239391257075e-05, "Pretrain/Loss": 1.9815393686294556, "Pretrain/Loss (Raw)": 1.9296401739120483, "Pretrain/Step": 6235, "Pretrain/Step Time": 8.455365043133497} +{"Pretrain/Learning Rate": 1.4125593300137766e-05, "Pretrain/Loss": 1.9813891649246216, "Pretrain/Loss (Raw)": 1.8857911825180054, "Pretrain/Step": 6236, "Pretrain/Step Time": 8.4541846383363} +{"Pretrain/Learning Rate": 1.411794846337745e-05, "Pretrain/Loss": 1.9816718101501465, "Pretrain/Loss (Raw)": 2.127241849899292, "Pretrain/Step": 6237, "Pretrain/Step Time": 8.45245797559619} +{"Pretrain/Learning Rate": 1.4110304881857955e-05, "Pretrain/Loss": 1.982337236404419, "Pretrain/Loss (Raw)": 1.8677339553833008, "Pretrain/Step": 6238, "Pretrain/Step Time": 8.454675998538733} +{"Pretrain/Learning Rate": 1.410266255646096e-05, "Pretrain/Loss": 1.9850795269012451, "Pretrain/Loss (Raw)": 2.244976043701172, "Pretrain/Step": 6239, "Pretrain/Step Time": 8.452978748828173} +{"Pretrain/Learning Rate": 1.4095021488068028e-05, "Pretrain/Loss": 1.9844828844070435, "Pretrain/Loss (Raw)": 2.0070297718048096, "Pretrain/Step": 6240, "Pretrain/Step Time": 8.453417969867587} +{"Pretrain/Learning Rate": 1.4087381677560518e-05, "Pretrain/Loss": 1.9851154088974, "Pretrain/Loss (Raw)": 2.0606610774993896, "Pretrain/Step": 6241, "Pretrain/Step Time": 8.448561660945415} +{"Pretrain/Learning Rate": 1.40797431258197e-05, "Pretrain/Loss": 1.9837477207183838, "Pretrain/Loss (Raw)": 1.7869051694869995, "Pretrain/Step": 6242, "Pretrain/Step Time": 8.447166780009866} +{"Pretrain/Learning Rate": 1.4072105833726684e-05, "Pretrain/Loss": 1.979384422302246, "Pretrain/Loss (Raw)": 1.5271555185317993, "Pretrain/Step": 6243, "Pretrain/Step Time": 8.449476873502135} +{"Pretrain/Learning Rate": 1.4064469802162411e-05, "Pretrain/Loss": 1.9791595935821533, "Pretrain/Loss (Raw)": 2.0707240104675293, "Pretrain/Step": 6244, "Pretrain/Step Time": 8.44714630767703} +{"Pretrain/Learning Rate": 1.405683503200771e-05, "Pretrain/Loss": 1.9809056520462036, "Pretrain/Loss (Raw)": 2.085480213165283, "Pretrain/Step": 6245, "Pretrain/Step Time": 8.44713950715959} +{"Pretrain/Learning Rate": 1.4049201524143236e-05, "Pretrain/Loss": 1.9785847663879395, "Pretrain/Loss (Raw)": 1.8732564449310303, "Pretrain/Step": 6246, "Pretrain/Step Time": 8.448086444288492} +{"Pretrain/Learning Rate": 1.4041569279449513e-05, "Pretrain/Loss": 1.9780824184417725, "Pretrain/Loss (Raw)": 1.9478886127471924, "Pretrain/Step": 6247, "Pretrain/Step Time": 8.446263900026679} +{"Pretrain/Learning Rate": 1.4033938298806925e-05, "Pretrain/Loss": 1.9783074855804443, "Pretrain/Loss (Raw)": 2.1249284744262695, "Pretrain/Step": 6248, "Pretrain/Step Time": 8.444138994440436} +{"Pretrain/Learning Rate": 1.4026308583095704e-05, "Pretrain/Loss": 1.9807215929031372, "Pretrain/Loss (Raw)": 2.1416079998016357, "Pretrain/Step": 6249, "Pretrain/Step Time": 8.444412786513567} +{"Pretrain/Learning Rate": 1.4018680133195928e-05, "Pretrain/Loss": 1.9801841974258423, "Pretrain/Loss (Raw)": 2.003788471221924, "Pretrain/Step": 6250, "Pretrain/Step Time": 8.445663029327989} +{"Pretrain/Learning Rate": 1.401105294998755e-05, "Pretrain/Loss": 1.9810357093811035, "Pretrain/Loss (Raw)": 2.1397879123687744, "Pretrain/Step": 6251, "Pretrain/Step Time": 8.44494397751987} +{"Pretrain/Learning Rate": 1.4003427034350341e-05, "Pretrain/Loss": 1.9820436239242554, "Pretrain/Loss (Raw)": 1.988855242729187, "Pretrain/Step": 6252, "Pretrain/Step Time": 8.443076722323895} +{"Pretrain/Learning Rate": 1.3995802387163964e-05, "Pretrain/Loss": 1.9812698364257812, "Pretrain/Loss (Raw)": 2.017702341079712, "Pretrain/Step": 6253, "Pretrain/Step Time": 8.446081906557083} +{"Pretrain/Learning Rate": 1.3988179009307911e-05, "Pretrain/Loss": 1.9817638397216797, "Pretrain/Loss (Raw)": 2.0961451530456543, "Pretrain/Step": 6254, "Pretrain/Step Time": 8.443380992859602} +{"Pretrain/Learning Rate": 1.398055690166154e-05, "Pretrain/Loss": 1.9810709953308105, "Pretrain/Loss (Raw)": 2.0612692832946777, "Pretrain/Step": 6255, "Pretrain/Step Time": 8.443866034969687} +{"Pretrain/Learning Rate": 1.3972936065104063e-05, "Pretrain/Loss": 1.9800119400024414, "Pretrain/Loss (Raw)": 2.0120251178741455, "Pretrain/Step": 6256, "Pretrain/Step Time": 8.444843767210841} +{"Pretrain/Learning Rate": 1.3965316500514534e-05, "Pretrain/Loss": 1.981663465499878, "Pretrain/Loss (Raw)": 2.1839404106140137, "Pretrain/Step": 6257, "Pretrain/Step Time": 8.448504349216819} +{"Pretrain/Learning Rate": 1.3957698208771863e-05, "Pretrain/Loss": 1.9794588088989258, "Pretrain/Loss (Raw)": 1.6484183073043823, "Pretrain/Step": 6258, "Pretrain/Step Time": 8.44235403649509} +{"Pretrain/Learning Rate": 1.3950081190754827e-05, "Pretrain/Loss": 1.978176474571228, "Pretrain/Loss (Raw)": 1.9312283992767334, "Pretrain/Step": 6259, "Pretrain/Step Time": 8.443906119093299} +{"Pretrain/Learning Rate": 1.3942465447342052e-05, "Pretrain/Loss": 1.979480504989624, "Pretrain/Loss (Raw)": 2.1762330532073975, "Pretrain/Step": 6260, "Pretrain/Step Time": 8.444979360327125} +{"Pretrain/Learning Rate": 1.393485097941199e-05, "Pretrain/Loss": 1.9806239604949951, "Pretrain/Loss (Raw)": 1.9287149906158447, "Pretrain/Step": 6261, "Pretrain/Step Time": 8.444372247904539} +{"Pretrain/Learning Rate": 1.3927237787842987e-05, "Pretrain/Loss": 1.982865571975708, "Pretrain/Loss (Raw)": 2.1778533458709717, "Pretrain/Step": 6262, "Pretrain/Step Time": 8.442973647266626} +{"Pretrain/Learning Rate": 1.3919625873513206e-05, "Pretrain/Loss": 1.982187032699585, "Pretrain/Loss (Raw)": 2.003876209259033, "Pretrain/Step": 6263, "Pretrain/Step Time": 8.441805871203542} +{"Pretrain/Learning Rate": 1.3912015237300687e-05, "Pretrain/Loss": 1.98187255859375, "Pretrain/Loss (Raw)": 1.9381564855575562, "Pretrain/Step": 6264, "Pretrain/Step Time": 8.447169618681073} +{"Pretrain/Learning Rate": 1.3904405880083316e-05, "Pretrain/Loss": 1.9826902151107788, "Pretrain/Loss (Raw)": 2.1300368309020996, "Pretrain/Step": 6265, "Pretrain/Step Time": 8.445985097438097} +{"Pretrain/Learning Rate": 1.3896797802738832e-05, "Pretrain/Loss": 1.9834169149398804, "Pretrain/Loss (Raw)": 1.9134114980697632, "Pretrain/Step": 6266, "Pretrain/Step Time": 8.448844889178872} +{"Pretrain/Learning Rate": 1.3889191006144814e-05, "Pretrain/Loss": 1.9833875894546509, "Pretrain/Loss (Raw)": 1.9785833358764648, "Pretrain/Step": 6267, "Pretrain/Step Time": 8.447305135428905} +{"Pretrain/Learning Rate": 1.3881585491178706e-05, "Pretrain/Loss": 1.9841125011444092, "Pretrain/Loss (Raw)": 2.180826425552368, "Pretrain/Step": 6268, "Pretrain/Step Time": 8.449770810082555} +{"Pretrain/Learning Rate": 1.3873981258717805e-05, "Pretrain/Loss": 1.9835962057113647, "Pretrain/Loss (Raw)": 2.0674209594726562, "Pretrain/Step": 6269, "Pretrain/Step Time": 8.445734774693847} +{"Pretrain/Learning Rate": 1.3866378309639258e-05, "Pretrain/Loss": 1.9822288751602173, "Pretrain/Loss (Raw)": 1.8883438110351562, "Pretrain/Step": 6270, "Pretrain/Step Time": 8.442028122022748} +{"Pretrain/Learning Rate": 1.385877664482006e-05, "Pretrain/Loss": 1.9830578565597534, "Pretrain/Loss (Raw)": 1.930773138999939, "Pretrain/Step": 6271, "Pretrain/Step Time": 8.441316168755293} +{"Pretrain/Learning Rate": 1.3851176265137067e-05, "Pretrain/Loss": 1.9820213317871094, "Pretrain/Loss (Raw)": 1.8997197151184082, "Pretrain/Step": 6272, "Pretrain/Step Time": 8.43958155065775} +{"Pretrain/Learning Rate": 1.3843577171466968e-05, "Pretrain/Loss": 1.9826351404190063, "Pretrain/Loss (Raw)": 2.099130630493164, "Pretrain/Step": 6273, "Pretrain/Step Time": 8.443204874172807} +{"Pretrain/Learning Rate": 1.3835979364686319e-05, "Pretrain/Loss": 1.981042504310608, "Pretrain/Loss (Raw)": 1.903973937034607, "Pretrain/Step": 6274, "Pretrain/Step Time": 8.43726597353816} +{"Pretrain/Learning Rate": 1.3828382845671529e-05, "Pretrain/Loss": 1.981555461883545, "Pretrain/Loss (Raw)": 1.913841962814331, "Pretrain/Step": 6275, "Pretrain/Step Time": 8.437715627253056} +{"Pretrain/Learning Rate": 1.382078761529886e-05, "Pretrain/Loss": 1.986396312713623, "Pretrain/Loss (Raw)": 1.9902116060256958, "Pretrain/Step": 6276, "Pretrain/Step Time": 8.434680225327611} +{"Pretrain/Learning Rate": 1.3813193674444402e-05, "Pretrain/Loss": 1.986046314239502, "Pretrain/Loss (Raw)": 2.0483951568603516, "Pretrain/Step": 6277, "Pretrain/Step Time": 8.436394622549415} +{"Pretrain/Learning Rate": 1.3805601023984132e-05, "Pretrain/Loss": 1.986973524093628, "Pretrain/Loss (Raw)": 2.0233821868896484, "Pretrain/Step": 6278, "Pretrain/Step Time": 8.438459787517786} +{"Pretrain/Learning Rate": 1.379800966479384e-05, "Pretrain/Loss": 1.9861669540405273, "Pretrain/Loss (Raw)": 2.0204615592956543, "Pretrain/Step": 6279, "Pretrain/Step Time": 8.435289528220892} +{"Pretrain/Learning Rate": 1.3790419597749199e-05, "Pretrain/Loss": 1.9871070384979248, "Pretrain/Loss (Raw)": 2.025560140609741, "Pretrain/Step": 6280, "Pretrain/Step Time": 8.436362870037556} +{"Pretrain/Learning Rate": 1.3782830823725713e-05, "Pretrain/Loss": 1.988684058189392, "Pretrain/Loss (Raw)": 2.122718572616577, "Pretrain/Step": 6281, "Pretrain/Step Time": 8.435510594397783} +{"Pretrain/Learning Rate": 1.3775243343598762e-05, "Pretrain/Loss": 1.9895904064178467, "Pretrain/Loss (Raw)": 2.0786633491516113, "Pretrain/Step": 6282, "Pretrain/Step Time": 8.433230757713318} +{"Pretrain/Learning Rate": 1.3767657158243535e-05, "Pretrain/Loss": 1.9883188009262085, "Pretrain/Loss (Raw)": 1.8707401752471924, "Pretrain/Step": 6283, "Pretrain/Step Time": 8.436738671734929} +{"Pretrain/Learning Rate": 1.3760072268535112e-05, "Pretrain/Loss": 1.988726258277893, "Pretrain/Loss (Raw)": 2.0672223567962646, "Pretrain/Step": 6284, "Pretrain/Step Time": 8.437568180263042} +{"Pretrain/Learning Rate": 1.3752488675348401e-05, "Pretrain/Loss": 1.9878425598144531, "Pretrain/Loss (Raw)": 1.9679782390594482, "Pretrain/Step": 6285, "Pretrain/Step Time": 8.438953032717109} +{"Pretrain/Learning Rate": 1.3744906379558165e-05, "Pretrain/Loss": 1.9882303476333618, "Pretrain/Loss (Raw)": 1.9542919397354126, "Pretrain/Step": 6286, "Pretrain/Step Time": 8.440635234117508} +{"Pretrain/Learning Rate": 1.3737325382039037e-05, "Pretrain/Loss": 1.988254427909851, "Pretrain/Loss (Raw)": 1.901064157485962, "Pretrain/Step": 6287, "Pretrain/Step Time": 8.437765195965767} +{"Pretrain/Learning Rate": 1.3729745683665457e-05, "Pretrain/Loss": 1.987937092781067, "Pretrain/Loss (Raw)": 1.821137547492981, "Pretrain/Step": 6288, "Pretrain/Step Time": 8.437753157690167} +{"Pretrain/Learning Rate": 1.3722167285311749e-05, "Pretrain/Loss": 1.9891700744628906, "Pretrain/Loss (Raw)": 2.0585644245147705, "Pretrain/Step": 6289, "Pretrain/Step Time": 8.438343284651637} +{"Pretrain/Learning Rate": 1.3714590187852086e-05, "Pretrain/Loss": 1.9892339706420898, "Pretrain/Loss (Raw)": 1.9902065992355347, "Pretrain/Step": 6290, "Pretrain/Step Time": 8.43869549408555} +{"Pretrain/Learning Rate": 1.3707014392160477e-05, "Pretrain/Loss": 1.990720272064209, "Pretrain/Loss (Raw)": 2.1073012351989746, "Pretrain/Step": 6291, "Pretrain/Step Time": 8.440150523558259} +{"Pretrain/Learning Rate": 1.36994398991108e-05, "Pretrain/Loss": 1.9909664392471313, "Pretrain/Loss (Raw)": 2.0445480346679688, "Pretrain/Step": 6292, "Pretrain/Step Time": 8.435129282996058} +{"Pretrain/Learning Rate": 1.3691866709576744e-05, "Pretrain/Loss": 1.9917728900909424, "Pretrain/Loss (Raw)": 2.2294585704803467, "Pretrain/Step": 6293, "Pretrain/Step Time": 8.436347058042884} +{"Pretrain/Learning Rate": 1.3684294824431895e-05, "Pretrain/Loss": 1.9919829368591309, "Pretrain/Loss (Raw)": 2.0643389225006104, "Pretrain/Step": 6294, "Pretrain/Step Time": 8.432340262457728} +{"Pretrain/Learning Rate": 1.3676724244549672e-05, "Pretrain/Loss": 1.9926717281341553, "Pretrain/Loss (Raw)": 1.9536798000335693, "Pretrain/Step": 6295, "Pretrain/Step Time": 8.430091762915254} +{"Pretrain/Learning Rate": 1.3669154970803313e-05, "Pretrain/Loss": 1.9907312393188477, "Pretrain/Loss (Raw)": 1.9293794631958008, "Pretrain/Step": 6296, "Pretrain/Step Time": 8.433448260650039} +{"Pretrain/Learning Rate": 1.366158700406595e-05, "Pretrain/Loss": 1.991184949874878, "Pretrain/Loss (Raw)": 2.021918296813965, "Pretrain/Step": 6297, "Pretrain/Step Time": 8.433147333562374} +{"Pretrain/Learning Rate": 1.365402034521055e-05, "Pretrain/Loss": 1.990976333618164, "Pretrain/Loss (Raw)": 1.975853443145752, "Pretrain/Step": 6298, "Pretrain/Step Time": 8.436129542067647} +{"Pretrain/Learning Rate": 1.3646454995109905e-05, "Pretrain/Loss": 1.9904577732086182, "Pretrain/Loss (Raw)": 2.032604932785034, "Pretrain/Step": 6299, "Pretrain/Step Time": 8.44167635589838} +{"Pretrain/Learning Rate": 1.3638890954636691e-05, "Pretrain/Loss": 1.9898425340652466, "Pretrain/Loss (Raw)": 1.7786988019943237, "Pretrain/Step": 6300, "Pretrain/Step Time": 8.442102307453752} +{"Pretrain/Learning Rate": 1.3631328224663408e-05, "Pretrain/Loss": 1.9917527437210083, "Pretrain/Loss (Raw)": 2.3074429035186768, "Pretrain/Step": 6301, "Pretrain/Step Time": 8.4435099568218} +{"Pretrain/Learning Rate": 1.3623766806062421e-05, "Pretrain/Loss": 1.9900091886520386, "Pretrain/Loss (Raw)": 1.8499644994735718, "Pretrain/Step": 6302, "Pretrain/Step Time": 8.441986231133342} +{"Pretrain/Learning Rate": 1.3616206699705944e-05, "Pretrain/Loss": 1.9902589321136475, "Pretrain/Loss (Raw)": 2.081428050994873, "Pretrain/Step": 6303, "Pretrain/Step Time": 8.444813897833228} +{"Pretrain/Learning Rate": 1.3608647906466016e-05, "Pretrain/Loss": 1.9914300441741943, "Pretrain/Loss (Raw)": 2.1143338680267334, "Pretrain/Step": 6304, "Pretrain/Step Time": 8.445282313972712} +{"Pretrain/Learning Rate": 1.3601090427214547e-05, "Pretrain/Loss": 1.9928569793701172, "Pretrain/Loss (Raw)": 2.189772844314575, "Pretrain/Step": 6305, "Pretrain/Step Time": 8.44547845236957} +{"Pretrain/Learning Rate": 1.3593534262823288e-05, "Pretrain/Loss": 1.9909007549285889, "Pretrain/Loss (Raw)": 1.7893682718276978, "Pretrain/Step": 6306, "Pretrain/Step Time": 8.447212886065245} +{"Pretrain/Learning Rate": 1.3585979414163847e-05, "Pretrain/Loss": 1.9924092292785645, "Pretrain/Loss (Raw)": 2.1202352046966553, "Pretrain/Step": 6307, "Pretrain/Step Time": 8.445658015087247} +{"Pretrain/Learning Rate": 1.357842588210768e-05, "Pretrain/Loss": 1.9917973279953003, "Pretrain/Loss (Raw)": 1.7218126058578491, "Pretrain/Step": 6308, "Pretrain/Step Time": 8.447487378492951} +{"Pretrain/Learning Rate": 1.3570873667526063e-05, "Pretrain/Loss": 1.990718960762024, "Pretrain/Loss (Raw)": 1.8930755853652954, "Pretrain/Step": 6309, "Pretrain/Step Time": 8.449340559542179} +{"Pretrain/Learning Rate": 1.3563322771290151e-05, "Pretrain/Loss": 1.991208553314209, "Pretrain/Loss (Raw)": 1.9934650659561157, "Pretrain/Step": 6310, "Pretrain/Step Time": 8.44746221601963} +{"Pretrain/Learning Rate": 1.3555773194270948e-05, "Pretrain/Loss": 1.9913653135299683, "Pretrain/Loss (Raw)": 1.976865530014038, "Pretrain/Step": 6311, "Pretrain/Step Time": 8.446123136207461} +{"Pretrain/Learning Rate": 1.3548224937339276e-05, "Pretrain/Loss": 1.992844820022583, "Pretrain/Loss (Raw)": 2.0254552364349365, "Pretrain/Step": 6312, "Pretrain/Step Time": 8.446886884048581} +{"Pretrain/Learning Rate": 1.3540678001365836e-05, "Pretrain/Loss": 1.9937806129455566, "Pretrain/Loss (Raw)": 1.9956070184707642, "Pretrain/Step": 6313, "Pretrain/Step Time": 8.446216341108084} +{"Pretrain/Learning Rate": 1.3533132387221168e-05, "Pretrain/Loss": 1.9937238693237305, "Pretrain/Loss (Raw)": 1.9419444799423218, "Pretrain/Step": 6314, "Pretrain/Step Time": 8.444353241473436} +{"Pretrain/Learning Rate": 1.352558809577564e-05, "Pretrain/Loss": 1.9928085803985596, "Pretrain/Loss (Raw)": 2.0093977451324463, "Pretrain/Step": 6315, "Pretrain/Step Time": 8.447954468429089} +{"Pretrain/Learning Rate": 1.3518045127899493e-05, "Pretrain/Loss": 1.9933736324310303, "Pretrain/Loss (Raw)": 2.0488979816436768, "Pretrain/Step": 6316, "Pretrain/Step Time": 8.450110511854291} +{"Pretrain/Learning Rate": 1.3510503484462805e-05, "Pretrain/Loss": 1.99528968334198, "Pretrain/Loss (Raw)": 1.9966471195220947, "Pretrain/Step": 6317, "Pretrain/Step Time": 8.451069189235568} +{"Pretrain/Learning Rate": 1.3502963166335504e-05, "Pretrain/Loss": 1.996201753616333, "Pretrain/Loss (Raw)": 2.015181541442871, "Pretrain/Step": 6318, "Pretrain/Step Time": 8.446820655837655} +{"Pretrain/Learning Rate": 1.3495424174387367e-05, "Pretrain/Loss": 1.9956176280975342, "Pretrain/Loss (Raw)": 1.988661289215088, "Pretrain/Step": 6319, "Pretrain/Step Time": 8.447996128350496} +{"Pretrain/Learning Rate": 1.3487886509488002e-05, "Pretrain/Loss": 1.995639681816101, "Pretrain/Loss (Raw)": 1.9868361949920654, "Pretrain/Step": 6320, "Pretrain/Step Time": 8.447533240541816} +{"Pretrain/Learning Rate": 1.3480350172506883e-05, "Pretrain/Loss": 1.9957011938095093, "Pretrain/Loss (Raw)": 1.9173078536987305, "Pretrain/Step": 6321, "Pretrain/Step Time": 8.447292221710086} +{"Pretrain/Learning Rate": 1.3472815164313325e-05, "Pretrain/Loss": 1.9946601390838623, "Pretrain/Loss (Raw)": 2.0305018424987793, "Pretrain/Step": 6322, "Pretrain/Step Time": 8.445074332877994} +{"Pretrain/Learning Rate": 1.3465281485776481e-05, "Pretrain/Loss": 1.9931511878967285, "Pretrain/Loss (Raw)": 1.9453917741775513, "Pretrain/Step": 6323, "Pretrain/Step Time": 8.445575753226876} +{"Pretrain/Learning Rate": 1.345774913776538e-05, "Pretrain/Loss": 1.9929066896438599, "Pretrain/Loss (Raw)": 1.7828525304794312, "Pretrain/Step": 6324, "Pretrain/Step Time": 8.44891600124538} +{"Pretrain/Learning Rate": 1.3450218121148844e-05, "Pretrain/Loss": 1.9940927028656006, "Pretrain/Loss (Raw)": 2.1192736625671387, "Pretrain/Step": 6325, "Pretrain/Step Time": 8.448931897059083} +{"Pretrain/Learning Rate": 1.3442688436795592e-05, "Pretrain/Loss": 1.9923923015594482, "Pretrain/Loss (Raw)": 1.8650774955749512, "Pretrain/Step": 6326, "Pretrain/Step Time": 8.452486731112003} +{"Pretrain/Learning Rate": 1.3435160085574177e-05, "Pretrain/Loss": 1.995341181755066, "Pretrain/Loss (Raw)": 2.0163495540618896, "Pretrain/Step": 6327, "Pretrain/Step Time": 8.448699420318007} +{"Pretrain/Learning Rate": 1.3427633068352974e-05, "Pretrain/Loss": 1.9961265325546265, "Pretrain/Loss (Raw)": 2.026320457458496, "Pretrain/Step": 6328, "Pretrain/Step Time": 8.449148189276457} +{"Pretrain/Learning Rate": 1.3420107386000227e-05, "Pretrain/Loss": 1.9964847564697266, "Pretrain/Loss (Raw)": 2.0573058128356934, "Pretrain/Step": 6329, "Pretrain/Step Time": 8.449907317757607} +{"Pretrain/Learning Rate": 1.3412583039384036e-05, "Pretrain/Loss": 1.9961366653442383, "Pretrain/Loss (Raw)": 2.009359836578369, "Pretrain/Step": 6330, "Pretrain/Step Time": 8.450248762965202} +{"Pretrain/Learning Rate": 1.3405060029372308e-05, "Pretrain/Loss": 1.996450424194336, "Pretrain/Loss (Raw)": 2.037950277328491, "Pretrain/Step": 6331, "Pretrain/Step Time": 8.44976431876421} +{"Pretrain/Learning Rate": 1.3397538356832828e-05, "Pretrain/Loss": 1.9977329969406128, "Pretrain/Loss (Raw)": 2.123718738555908, "Pretrain/Step": 6332, "Pretrain/Step Time": 8.452213170006871} +{"Pretrain/Learning Rate": 1.3390018022633225e-05, "Pretrain/Loss": 1.9974782466888428, "Pretrain/Loss (Raw)": 2.174102306365967, "Pretrain/Step": 6333, "Pretrain/Step Time": 8.453316235914826} +{"Pretrain/Learning Rate": 1.338249902764096e-05, "Pretrain/Loss": 1.9991482496261597, "Pretrain/Loss (Raw)": 2.030451774597168, "Pretrain/Step": 6334, "Pretrain/Step Time": 8.457448353990912} +{"Pretrain/Learning Rate": 1.3374981372723362e-05, "Pretrain/Loss": 1.9980690479278564, "Pretrain/Loss (Raw)": 2.0106420516967773, "Pretrain/Step": 6335, "Pretrain/Step Time": 8.455745058134198} +{"Pretrain/Learning Rate": 1.3367465058747567e-05, "Pretrain/Loss": 1.999588966369629, "Pretrain/Loss (Raw)": 2.110517978668213, "Pretrain/Step": 6336, "Pretrain/Step Time": 8.451591512188315} +{"Pretrain/Learning Rate": 1.3359950086580588e-05, "Pretrain/Loss": 2.0013766288757324, "Pretrain/Loss (Raw)": 2.088191270828247, "Pretrain/Step": 6337, "Pretrain/Step Time": 8.453090282157063} +{"Pretrain/Learning Rate": 1.335243645708928e-05, "Pretrain/Loss": 2.0014705657958984, "Pretrain/Loss (Raw)": 2.024117946624756, "Pretrain/Step": 6338, "Pretrain/Step Time": 8.451294101774693} +{"Pretrain/Learning Rate": 1.3344924171140328e-05, "Pretrain/Loss": 2.0023903846740723, "Pretrain/Loss (Raw)": 1.9541308879852295, "Pretrain/Step": 6339, "Pretrain/Step Time": 8.453931966796517} +{"Pretrain/Learning Rate": 1.333741322960029e-05, "Pretrain/Loss": 2.000870704650879, "Pretrain/Loss (Raw)": 1.9423725605010986, "Pretrain/Step": 6340, "Pretrain/Step Time": 8.45649397559464} +{"Pretrain/Learning Rate": 1.3329903633335528e-05, "Pretrain/Loss": 1.9996440410614014, "Pretrain/Loss (Raw)": 1.8015421628952026, "Pretrain/Step": 6341, "Pretrain/Step Time": 8.457759285345674} +{"Pretrain/Learning Rate": 1.3322395383212277e-05, "Pretrain/Loss": 1.9982783794403076, "Pretrain/Loss (Raw)": 1.9076565504074097, "Pretrain/Step": 6342, "Pretrain/Step Time": 8.45533781312406} +{"Pretrain/Learning Rate": 1.3314888480096618e-05, "Pretrain/Loss": 1.99680495262146, "Pretrain/Loss (Raw)": 1.9452563524246216, "Pretrain/Step": 6343, "Pretrain/Step Time": 8.455590991303325} +{"Pretrain/Learning Rate": 1.3307382924854479e-05, "Pretrain/Loss": 1.9952937364578247, "Pretrain/Loss (Raw)": 1.8844558000564575, "Pretrain/Step": 6344, "Pretrain/Step Time": 8.450159061700106} +{"Pretrain/Learning Rate": 1.3299878718351594e-05, "Pretrain/Loss": 1.993552565574646, "Pretrain/Loss (Raw)": 1.835331916809082, "Pretrain/Step": 6345, "Pretrain/Step Time": 8.449393156915903} +{"Pretrain/Learning Rate": 1.3292375861453598e-05, "Pretrain/Loss": 1.9933741092681885, "Pretrain/Loss (Raw)": 1.9970005750656128, "Pretrain/Step": 6346, "Pretrain/Step Time": 8.452468499541283} +{"Pretrain/Learning Rate": 1.3284874355025928e-05, "Pretrain/Loss": 1.9917241334915161, "Pretrain/Loss (Raw)": 2.0363829135894775, "Pretrain/Step": 6347, "Pretrain/Step Time": 8.4504229798913} +{"Pretrain/Learning Rate": 1.3277374199933879e-05, "Pretrain/Loss": 1.991714596748352, "Pretrain/Loss (Raw)": 1.8197168111801147, "Pretrain/Step": 6348, "Pretrain/Step Time": 8.454966889694333} +{"Pretrain/Learning Rate": 1.3269875397042598e-05, "Pretrain/Loss": 1.992168664932251, "Pretrain/Loss (Raw)": 2.034738302230835, "Pretrain/Step": 6349, "Pretrain/Step Time": 8.454178769141436} +{"Pretrain/Learning Rate": 1.3262377947217069e-05, "Pretrain/Loss": 1.9918513298034668, "Pretrain/Loss (Raw)": 1.884894609451294, "Pretrain/Step": 6350, "Pretrain/Step Time": 8.459378331899643} +{"Pretrain/Learning Rate": 1.3254881851322126e-05, "Pretrain/Loss": 1.9900667667388916, "Pretrain/Loss (Raw)": 1.831896424293518, "Pretrain/Step": 6351, "Pretrain/Step Time": 8.456795759499073} +{"Pretrain/Learning Rate": 1.3247387110222426e-05, "Pretrain/Loss": 1.991015911102295, "Pretrain/Loss (Raw)": 2.0567171573638916, "Pretrain/Step": 6352, "Pretrain/Step Time": 8.455508131533861} +{"Pretrain/Learning Rate": 1.3239893724782492e-05, "Pretrain/Loss": 1.9894245862960815, "Pretrain/Loss (Raw)": 1.8370474576950073, "Pretrain/Step": 6353, "Pretrain/Step Time": 8.456180926412344} +{"Pretrain/Learning Rate": 1.3232401695866687e-05, "Pretrain/Loss": 1.9894449710845947, "Pretrain/Loss (Raw)": 1.9183481931686401, "Pretrain/Step": 6354, "Pretrain/Step Time": 8.456525981426239} +{"Pretrain/Learning Rate": 1.3224911024339207e-05, "Pretrain/Loss": 1.991210699081421, "Pretrain/Loss (Raw)": 2.158599376678467, "Pretrain/Step": 6355, "Pretrain/Step Time": 8.45345108024776} +{"Pretrain/Learning Rate": 1.3217421711064112e-05, "Pretrain/Loss": 1.9908369779586792, "Pretrain/Loss (Raw)": 1.9411191940307617, "Pretrain/Step": 6356, "Pretrain/Step Time": 8.460227210074663} +{"Pretrain/Learning Rate": 1.3209933756905274e-05, "Pretrain/Loss": 1.9917603731155396, "Pretrain/Loss (Raw)": 2.0199880599975586, "Pretrain/Step": 6357, "Pretrain/Step Time": 8.459927013143897} +{"Pretrain/Learning Rate": 1.3202447162726433e-05, "Pretrain/Loss": 1.9915051460266113, "Pretrain/Loss (Raw)": 1.7220968008041382, "Pretrain/Step": 6358, "Pretrain/Step Time": 8.46453713811934} +{"Pretrain/Learning Rate": 1.3194961929391167e-05, "Pretrain/Loss": 1.990718126296997, "Pretrain/Loss (Raw)": 1.9491088390350342, "Pretrain/Step": 6359, "Pretrain/Step Time": 8.459015771746635} +{"Pretrain/Learning Rate": 1.3187478057762904e-05, "Pretrain/Loss": 1.990228533744812, "Pretrain/Loss (Raw)": 1.9888368844985962, "Pretrain/Step": 6360, "Pretrain/Step Time": 8.461692929267883} +{"Pretrain/Learning Rate": 1.3179995548704883e-05, "Pretrain/Loss": 1.9913887977600098, "Pretrain/Loss (Raw)": 2.055023670196533, "Pretrain/Step": 6361, "Pretrain/Step Time": 8.459611169993877} +{"Pretrain/Learning Rate": 1.3172514403080233e-05, "Pretrain/Loss": 1.9909816980361938, "Pretrain/Loss (Raw)": 1.9341096878051758, "Pretrain/Step": 6362, "Pretrain/Step Time": 8.461526835337281} +{"Pretrain/Learning Rate": 1.3165034621751882e-05, "Pretrain/Loss": 1.9906306266784668, "Pretrain/Loss (Raw)": 1.884696364402771, "Pretrain/Step": 6363, "Pretrain/Step Time": 8.461815809831023} +{"Pretrain/Learning Rate": 1.3157556205582627e-05, "Pretrain/Loss": 1.9923784732818604, "Pretrain/Loss (Raw)": 2.10951566696167, "Pretrain/Step": 6364, "Pretrain/Step Time": 8.462080957368016} +{"Pretrain/Learning Rate": 1.3150079155435102e-05, "Pretrain/Loss": 1.99037766456604, "Pretrain/Loss (Raw)": 1.8711597919464111, "Pretrain/Step": 6365, "Pretrain/Step Time": 8.464482173323631} +{"Pretrain/Learning Rate": 1.3142603472171788e-05, "Pretrain/Loss": 1.9911131858825684, "Pretrain/Loss (Raw)": 1.9618785381317139, "Pretrain/Step": 6366, "Pretrain/Step Time": 8.46214460581541} +{"Pretrain/Learning Rate": 1.3135129156654991e-05, "Pretrain/Loss": 1.9867910146713257, "Pretrain/Loss (Raw)": 1.6917303800582886, "Pretrain/Step": 6367, "Pretrain/Step Time": 8.463161597028375} +{"Pretrain/Learning Rate": 1.3127656209746875e-05, "Pretrain/Loss": 1.9878666400909424, "Pretrain/Loss (Raw)": 2.1447033882141113, "Pretrain/Step": 6368, "Pretrain/Step Time": 8.462752485647798} +{"Pretrain/Learning Rate": 1.3120184632309446e-05, "Pretrain/Loss": 1.9881116151809692, "Pretrain/Loss (Raw)": 2.0920212268829346, "Pretrain/Step": 6369, "Pretrain/Step Time": 8.46263131685555} +{"Pretrain/Learning Rate": 1.3112714425204541e-05, "Pretrain/Loss": 1.9900226593017578, "Pretrain/Loss (Raw)": 2.0315089225769043, "Pretrain/Step": 6370, "Pretrain/Step Time": 8.464080661535263} +{"Pretrain/Learning Rate": 1.3105245589293851e-05, "Pretrain/Loss": 1.992771863937378, "Pretrain/Loss (Raw)": 1.8790631294250488, "Pretrain/Step": 6371, "Pretrain/Step Time": 8.460023384541273} +{"Pretrain/Learning Rate": 1.3097778125438912e-05, "Pretrain/Loss": 1.9927541017532349, "Pretrain/Loss (Raw)": 2.0684385299682617, "Pretrain/Step": 6372, "Pretrain/Step Time": 8.462270120158792} +{"Pretrain/Learning Rate": 1.3090312034501073e-05, "Pretrain/Loss": 1.9931827783584595, "Pretrain/Loss (Raw)": 2.1403722763061523, "Pretrain/Step": 6373, "Pretrain/Step Time": 8.46565835364163} +{"Pretrain/Learning Rate": 1.3082847317341557e-05, "Pretrain/Loss": 1.9941260814666748, "Pretrain/Loss (Raw)": 1.9939937591552734, "Pretrain/Step": 6374, "Pretrain/Step Time": 8.465525854378939} +{"Pretrain/Learning Rate": 1.3075383974821415e-05, "Pretrain/Loss": 1.994350552558899, "Pretrain/Loss (Raw)": 1.9766178131103516, "Pretrain/Step": 6375, "Pretrain/Step Time": 8.461353234946728} +{"Pretrain/Learning Rate": 1.3067922007801547e-05, "Pretrain/Loss": 1.9927740097045898, "Pretrain/Loss (Raw)": 1.9231308698654175, "Pretrain/Step": 6376, "Pretrain/Step Time": 8.462240170687437} +{"Pretrain/Learning Rate": 1.3060461417142677e-05, "Pretrain/Loss": 1.9920037984848022, "Pretrain/Loss (Raw)": 2.043020725250244, "Pretrain/Step": 6377, "Pretrain/Step Time": 8.465571604669094} +{"Pretrain/Learning Rate": 1.3053002203705395e-05, "Pretrain/Loss": 1.9922821521759033, "Pretrain/Loss (Raw)": 2.0394177436828613, "Pretrain/Step": 6378, "Pretrain/Step Time": 8.464687755331397} +{"Pretrain/Learning Rate": 1.3045544368350098e-05, "Pretrain/Loss": 1.9890451431274414, "Pretrain/Loss (Raw)": 1.7254596948623657, "Pretrain/Step": 6379, "Pretrain/Step Time": 8.46982810087502} +{"Pretrain/Learning Rate": 1.3038087911937058e-05, "Pretrain/Loss": 1.9886962175369263, "Pretrain/Loss (Raw)": 1.9441781044006348, "Pretrain/Step": 6380, "Pretrain/Step Time": 8.470387382432818} +{"Pretrain/Learning Rate": 1.3030632835326379e-05, "Pretrain/Loss": 1.988822340965271, "Pretrain/Loss (Raw)": 2.0338544845581055, "Pretrain/Step": 6381, "Pretrain/Step Time": 8.47012821212411} +{"Pretrain/Learning Rate": 1.3023179139378e-05, "Pretrain/Loss": 1.9881572723388672, "Pretrain/Loss (Raw)": 2.0110061168670654, "Pretrain/Step": 6382, "Pretrain/Step Time": 8.470058303326368} +{"Pretrain/Learning Rate": 1.301572682495169e-05, "Pretrain/Loss": 1.9864757061004639, "Pretrain/Loss (Raw)": 1.846049427986145, "Pretrain/Step": 6383, "Pretrain/Step Time": 8.472303200513124} +{"Pretrain/Learning Rate": 1.300827589290708e-05, "Pretrain/Loss": 1.9869053363800049, "Pretrain/Loss (Raw)": 2.067004680633545, "Pretrain/Step": 6384, "Pretrain/Step Time": 8.471467193216085} +{"Pretrain/Learning Rate": 1.3000826344103629e-05, "Pretrain/Loss": 1.9837937355041504, "Pretrain/Loss (Raw)": 1.7856642007827759, "Pretrain/Step": 6385, "Pretrain/Step Time": 8.469136731699109} +{"Pretrain/Learning Rate": 1.2993378179400645e-05, "Pretrain/Loss": 1.984822154045105, "Pretrain/Loss (Raw)": 1.7800463438034058, "Pretrain/Step": 6386, "Pretrain/Step Time": 8.4729271735996} +{"Pretrain/Learning Rate": 1.2985931399657279e-05, "Pretrain/Loss": 1.9853863716125488, "Pretrain/Loss (Raw)": 2.003453493118286, "Pretrain/Step": 6387, "Pretrain/Step Time": 8.470069617033005} +{"Pretrain/Learning Rate": 1.2978486005732493e-05, "Pretrain/Loss": 1.985734224319458, "Pretrain/Loss (Raw)": 2.220743417739868, "Pretrain/Step": 6388, "Pretrain/Step Time": 8.467697249725461} +{"Pretrain/Learning Rate": 1.297104199848512e-05, "Pretrain/Loss": 1.9854274988174438, "Pretrain/Loss (Raw)": 1.889470100402832, "Pretrain/Step": 6389, "Pretrain/Step Time": 8.470477661117911} +{"Pretrain/Learning Rate": 1.2963599378773828e-05, "Pretrain/Loss": 1.9832086563110352, "Pretrain/Loss (Raw)": 1.893837571144104, "Pretrain/Step": 6390, "Pretrain/Step Time": 8.472711523994803} +{"Pretrain/Learning Rate": 1.2956158147457115e-05, "Pretrain/Loss": 1.9837970733642578, "Pretrain/Loss (Raw)": 2.079195261001587, "Pretrain/Step": 6391, "Pretrain/Step Time": 8.472446436062455} +{"Pretrain/Learning Rate": 1.2948718305393329e-05, "Pretrain/Loss": 1.9844577312469482, "Pretrain/Loss (Raw)": 2.022719383239746, "Pretrain/Step": 6392, "Pretrain/Step Time": 8.46718462742865} +{"Pretrain/Learning Rate": 1.294127985344066e-05, "Pretrain/Loss": 1.9840024709701538, "Pretrain/Loss (Raw)": 2.0717594623565674, "Pretrain/Step": 6393, "Pretrain/Step Time": 8.468350358307362} +{"Pretrain/Learning Rate": 1.2933842792457113e-05, "Pretrain/Loss": 1.9860787391662598, "Pretrain/Loss (Raw)": 2.179175615310669, "Pretrain/Step": 6394, "Pretrain/Step Time": 8.464508121833205} +{"Pretrain/Learning Rate": 1.2926407123300571e-05, "Pretrain/Loss": 1.9848536252975464, "Pretrain/Loss (Raw)": 1.821762204170227, "Pretrain/Step": 6395, "Pretrain/Step Time": 8.46482652798295} +{"Pretrain/Learning Rate": 1.2918972846828712e-05, "Pretrain/Loss": 1.9825915098190308, "Pretrain/Loss (Raw)": 1.891279697418213, "Pretrain/Step": 6396, "Pretrain/Step Time": 8.465690933167934} +{"Pretrain/Learning Rate": 1.291153996389909e-05, "Pretrain/Loss": 1.9824061393737793, "Pretrain/Loss (Raw)": 2.0436947345733643, "Pretrain/Step": 6397, "Pretrain/Step Time": 8.465583337470889} +{"Pretrain/Learning Rate": 1.2904108475369096e-05, "Pretrain/Loss": 1.9831335544586182, "Pretrain/Loss (Raw)": 1.9814512729644775, "Pretrain/Step": 6398, "Pretrain/Step Time": 8.468150524422526} +{"Pretrain/Learning Rate": 1.2896678382095928e-05, "Pretrain/Loss": 1.9841976165771484, "Pretrain/Loss (Raw)": 2.0669686794281006, "Pretrain/Step": 6399, "Pretrain/Step Time": 8.470171747729182} +{"Pretrain/Learning Rate": 1.2889249684936655e-05, "Pretrain/Loss": 1.9852468967437744, "Pretrain/Loss (Raw)": 2.034040927886963, "Pretrain/Step": 6400, "Pretrain/Step Time": 8.466553093865514} +{"Pretrain/Learning Rate": 1.2881822384748177e-05, "Pretrain/Loss": 1.9850976467132568, "Pretrain/Loss (Raw)": 2.080014228820801, "Pretrain/Step": 6401, "Pretrain/Step Time": 8.468723703175783} +{"Pretrain/Learning Rate": 1.2874396482387224e-05, "Pretrain/Loss": 1.9860036373138428, "Pretrain/Loss (Raw)": 2.0199434757232666, "Pretrain/Step": 6402, "Pretrain/Step Time": 8.4720368552953} +{"Pretrain/Learning Rate": 1.286697197871039e-05, "Pretrain/Loss": 1.9871008396148682, "Pretrain/Loss (Raw)": 2.0542800426483154, "Pretrain/Step": 6403, "Pretrain/Step Time": 8.470600839704275} +{"Pretrain/Learning Rate": 1.2859548874574062e-05, "Pretrain/Loss": 1.9867308139801025, "Pretrain/Loss (Raw)": 1.9428513050079346, "Pretrain/Step": 6404, "Pretrain/Step Time": 8.47385141812265} +{"Pretrain/Learning Rate": 1.2852127170834505e-05, "Pretrain/Loss": 1.9860548973083496, "Pretrain/Loss (Raw)": 1.96187424659729, "Pretrain/Step": 6405, "Pretrain/Step Time": 8.473095456138253} +{"Pretrain/Learning Rate": 1.284470686834781e-05, "Pretrain/Loss": 1.9874205589294434, "Pretrain/Loss (Raw)": 2.1981890201568604, "Pretrain/Step": 6406, "Pretrain/Step Time": 8.47231357358396} +{"Pretrain/Learning Rate": 1.2837287967969905e-05, "Pretrain/Loss": 1.987863302230835, "Pretrain/Loss (Raw)": 2.077134609222412, "Pretrain/Step": 6407, "Pretrain/Step Time": 8.476517850533128} +{"Pretrain/Learning Rate": 1.282987047055657e-05, "Pretrain/Loss": 1.987160563468933, "Pretrain/Loss (Raw)": 1.935627818107605, "Pretrain/Step": 6408, "Pretrain/Step Time": 8.475904982537031} +{"Pretrain/Learning Rate": 1.282245437696339e-05, "Pretrain/Loss": 1.9869258403778076, "Pretrain/Loss (Raw)": 2.092667818069458, "Pretrain/Step": 6409, "Pretrain/Step Time": 8.475001519545913} +{"Pretrain/Learning Rate": 1.2815039688045815e-05, "Pretrain/Loss": 1.9879732131958008, "Pretrain/Loss (Raw)": 2.212709426879883, "Pretrain/Step": 6410, "Pretrain/Step Time": 8.47543140500784} +{"Pretrain/Learning Rate": 1.2807626404659142e-05, "Pretrain/Loss": 1.9896464347839355, "Pretrain/Loss (Raw)": 2.0849111080169678, "Pretrain/Step": 6411, "Pretrain/Step Time": 8.473866967484355} +{"Pretrain/Learning Rate": 1.280021452765847e-05, "Pretrain/Loss": 1.9899884462356567, "Pretrain/Loss (Raw)": 2.111008405685425, "Pretrain/Step": 6412, "Pretrain/Step Time": 8.473298897966743} +{"Pretrain/Learning Rate": 1.2792804057898764e-05, "Pretrain/Loss": 1.9920670986175537, "Pretrain/Loss (Raw)": 2.234041452407837, "Pretrain/Step": 6413, "Pretrain/Step Time": 8.472138281911612} +{"Pretrain/Learning Rate": 1.2785394996234828e-05, "Pretrain/Loss": 1.9910759925842285, "Pretrain/Loss (Raw)": 1.8274325132369995, "Pretrain/Step": 6414, "Pretrain/Step Time": 8.471976237371564} +{"Pretrain/Learning Rate": 1.2777987343521277e-05, "Pretrain/Loss": 1.9926544427871704, "Pretrain/Loss (Raw)": 2.103116512298584, "Pretrain/Step": 6415, "Pretrain/Step Time": 8.475399499759078} +{"Pretrain/Learning Rate": 1.2770581100612594e-05, "Pretrain/Loss": 1.994067668914795, "Pretrain/Loss (Raw)": 2.002035140991211, "Pretrain/Step": 6416, "Pretrain/Step Time": 8.47466898523271} +{"Pretrain/Learning Rate": 1.2763176268363081e-05, "Pretrain/Loss": 1.9929637908935547, "Pretrain/Loss (Raw)": 1.9172672033309937, "Pretrain/Step": 6417, "Pretrain/Step Time": 8.473974868655205} +{"Pretrain/Learning Rate": 1.2755772847626884e-05, "Pretrain/Loss": 1.992760181427002, "Pretrain/Loss (Raw)": 1.964125394821167, "Pretrain/Step": 6418, "Pretrain/Step Time": 8.476039633154869} +{"Pretrain/Learning Rate": 1.2748370839258e-05, "Pretrain/Loss": 1.9922516345977783, "Pretrain/Loss (Raw)": 2.0422210693359375, "Pretrain/Step": 6419, "Pretrain/Step Time": 8.475154800340533} +{"Pretrain/Learning Rate": 1.274097024411022e-05, "Pretrain/Loss": 1.9913525581359863, "Pretrain/Loss (Raw)": 1.929452657699585, "Pretrain/Step": 6420, "Pretrain/Step Time": 8.477551985532045} +{"Pretrain/Learning Rate": 1.2733571063037214e-05, "Pretrain/Loss": 1.9893171787261963, "Pretrain/Loss (Raw)": 1.9689363241195679, "Pretrain/Step": 6421, "Pretrain/Step Time": 8.483534460887313} +{"Pretrain/Learning Rate": 1.272617329689248e-05, "Pretrain/Loss": 1.9887239933013916, "Pretrain/Loss (Raw)": 1.9884098768234253, "Pretrain/Step": 6422, "Pretrain/Step Time": 8.484126061201096} +{"Pretrain/Learning Rate": 1.2718776946529337e-05, "Pretrain/Loss": 1.9869441986083984, "Pretrain/Loss (Raw)": 1.725873589515686, "Pretrain/Step": 6423, "Pretrain/Step Time": 8.483913887292147} +{"Pretrain/Learning Rate": 1.271138201280097e-05, "Pretrain/Loss": 1.9875340461730957, "Pretrain/Loss (Raw)": 2.004894971847534, "Pretrain/Step": 6424, "Pretrain/Step Time": 8.483259277418256} +{"Pretrain/Learning Rate": 1.2703988496560363e-05, "Pretrain/Loss": 1.9877675771713257, "Pretrain/Loss (Raw)": 2.05180025100708, "Pretrain/Step": 6425, "Pretrain/Step Time": 8.484444499015808} +{"Pretrain/Learning Rate": 1.2696596398660357e-05, "Pretrain/Loss": 1.987659215927124, "Pretrain/Loss (Raw)": 1.9619625806808472, "Pretrain/Step": 6426, "Pretrain/Step Time": 8.484252110123634} +{"Pretrain/Learning Rate": 1.2689205719953633e-05, "Pretrain/Loss": 1.9873487949371338, "Pretrain/Loss (Raw)": 1.99288809299469, "Pretrain/Step": 6427, "Pretrain/Step Time": 8.4831264000386} +{"Pretrain/Learning Rate": 1.2681816461292715e-05, "Pretrain/Loss": 1.989031434059143, "Pretrain/Loss (Raw)": 1.9940714836120605, "Pretrain/Step": 6428, "Pretrain/Step Time": 8.479330470785499} +{"Pretrain/Learning Rate": 1.2674428623529926e-05, "Pretrain/Loss": 1.986090898513794, "Pretrain/Loss (Raw)": 1.9310417175292969, "Pretrain/Step": 6429, "Pretrain/Step Time": 8.478132398799062} +{"Pretrain/Learning Rate": 1.2667042207517477e-05, "Pretrain/Loss": 1.988018274307251, "Pretrain/Loss (Raw)": 2.096686601638794, "Pretrain/Step": 6430, "Pretrain/Step Time": 8.480964828282595} +{"Pretrain/Learning Rate": 1.2659657214107365e-05, "Pretrain/Loss": 1.9872679710388184, "Pretrain/Loss (Raw)": 1.9853785037994385, "Pretrain/Step": 6431, "Pretrain/Step Time": 8.483055613934994} +{"Pretrain/Learning Rate": 1.2652273644151458e-05, "Pretrain/Loss": 1.986978530883789, "Pretrain/Loss (Raw)": 2.077293872833252, "Pretrain/Step": 6432, "Pretrain/Step Time": 8.480373343452811} +{"Pretrain/Learning Rate": 1.2644891498501443e-05, "Pretrain/Loss": 1.987093448638916, "Pretrain/Loss (Raw)": 2.2044925689697266, "Pretrain/Step": 6433, "Pretrain/Step Time": 8.484804846346378} +{"Pretrain/Learning Rate": 1.2637510778008854e-05, "Pretrain/Loss": 1.9878828525543213, "Pretrain/Loss (Raw)": 1.8904162645339966, "Pretrain/Step": 6434, "Pretrain/Step Time": 8.484684368595481} +{"Pretrain/Learning Rate": 1.263013148352506e-05, "Pretrain/Loss": 1.9870507717132568, "Pretrain/Loss (Raw)": 2.0137057304382324, "Pretrain/Step": 6435, "Pretrain/Step Time": 8.483547247946262} +{"Pretrain/Learning Rate": 1.2622753615901244e-05, "Pretrain/Loss": 1.989307165145874, "Pretrain/Loss (Raw)": 2.010638475418091, "Pretrain/Step": 6436, "Pretrain/Step Time": 8.48416238091886} +{"Pretrain/Learning Rate": 1.2615377175988449e-05, "Pretrain/Loss": 1.9886207580566406, "Pretrain/Loss (Raw)": 1.8052177429199219, "Pretrain/Step": 6437, "Pretrain/Step Time": 8.485563844442368} +{"Pretrain/Learning Rate": 1.2608002164637544e-05, "Pretrain/Loss": 1.9878815412521362, "Pretrain/Loss (Raw)": 1.8988348245620728, "Pretrain/Step": 6438, "Pretrain/Step Time": 8.485976859927177} +{"Pretrain/Learning Rate": 1.2600628582699236e-05, "Pretrain/Loss": 1.9867526292800903, "Pretrain/Loss (Raw)": 1.8323651552200317, "Pretrain/Step": 6439, "Pretrain/Step Time": 8.488576335832477} +{"Pretrain/Learning Rate": 1.259325643102407e-05, "Pretrain/Loss": 1.9860913753509521, "Pretrain/Loss (Raw)": 1.940812349319458, "Pretrain/Step": 6440, "Pretrain/Step Time": 8.484581077471375} +{"Pretrain/Learning Rate": 1.2585885710462408e-05, "Pretrain/Loss": 1.9859554767608643, "Pretrain/Loss (Raw)": 1.9782183170318604, "Pretrain/Step": 6441, "Pretrain/Step Time": 8.484335005283356} +{"Pretrain/Learning Rate": 1.2578516421864467e-05, "Pretrain/Loss": 1.9852358102798462, "Pretrain/Loss (Raw)": 1.8498296737670898, "Pretrain/Step": 6442, "Pretrain/Step Time": 8.485747316852212} +{"Pretrain/Learning Rate": 1.2571148566080288e-05, "Pretrain/Loss": 1.984990119934082, "Pretrain/Loss (Raw)": 1.977943778038025, "Pretrain/Step": 6443, "Pretrain/Step Time": 8.48491925559938} +{"Pretrain/Learning Rate": 1.2563782143959769e-05, "Pretrain/Loss": 1.9830468893051147, "Pretrain/Loss (Raw)": 1.8001664876937866, "Pretrain/Step": 6444, "Pretrain/Step Time": 8.4804767947644} +{"Pretrain/Learning Rate": 1.2556417156352596e-05, "Pretrain/Loss": 1.981994390487671, "Pretrain/Loss (Raw)": 1.8619329929351807, "Pretrain/Step": 6445, "Pretrain/Step Time": 8.478295532986522} +{"Pretrain/Learning Rate": 1.2549053604108341e-05, "Pretrain/Loss": 1.9812500476837158, "Pretrain/Loss (Raw)": 1.9198901653289795, "Pretrain/Step": 6446, "Pretrain/Step Time": 8.480853721499443} +{"Pretrain/Learning Rate": 1.2541691488076369e-05, "Pretrain/Loss": 1.981809377670288, "Pretrain/Loss (Raw)": 2.0602669715881348, "Pretrain/Step": 6447, "Pretrain/Step Time": 8.484320726245642} +{"Pretrain/Learning Rate": 1.2534330809105902e-05, "Pretrain/Loss": 1.9821115732192993, "Pretrain/Loss (Raw)": 2.025519847869873, "Pretrain/Step": 6448, "Pretrain/Step Time": 8.48508114926517} +{"Pretrain/Learning Rate": 1.2526971568045998e-05, "Pretrain/Loss": 1.9805784225463867, "Pretrain/Loss (Raw)": 1.7210747003555298, "Pretrain/Step": 6449, "Pretrain/Step Time": 8.486150689423084} +{"Pretrain/Learning Rate": 1.2519613765745542e-05, "Pretrain/Loss": 1.9805665016174316, "Pretrain/Loss (Raw)": 2.028972625732422, "Pretrain/Step": 6450, "Pretrain/Step Time": 8.485754681751132} +{"Pretrain/Learning Rate": 1.2512257403053257e-05, "Pretrain/Loss": 1.980238914489746, "Pretrain/Loss (Raw)": 1.9034600257873535, "Pretrain/Step": 6451, "Pretrain/Step Time": 8.481274889782071} +{"Pretrain/Learning Rate": 1.2504902480817687e-05, "Pretrain/Loss": 1.979918122291565, "Pretrain/Loss (Raw)": 1.7417852878570557, "Pretrain/Step": 6452, "Pretrain/Step Time": 8.483504762873054} +{"Pretrain/Learning Rate": 1.2497548999887224e-05, "Pretrain/Loss": 1.9789334535598755, "Pretrain/Loss (Raw)": 1.993225336074829, "Pretrain/Step": 6453, "Pretrain/Step Time": 8.485159009695053} +{"Pretrain/Learning Rate": 1.2490196961110088e-05, "Pretrain/Loss": 1.9808529615402222, "Pretrain/Loss (Raw)": 2.1107823848724365, "Pretrain/Step": 6454, "Pretrain/Step Time": 8.479012655094266} +{"Pretrain/Learning Rate": 1.2482846365334339e-05, "Pretrain/Loss": 1.9800676107406616, "Pretrain/Loss (Raw)": 1.9158271551132202, "Pretrain/Step": 6455, "Pretrain/Step Time": 8.480398792773485} +{"Pretrain/Learning Rate": 1.2475497213407869e-05, "Pretrain/Loss": 1.981980562210083, "Pretrain/Loss (Raw)": 2.271182060241699, "Pretrain/Step": 6456, "Pretrain/Step Time": 8.48308072052896} +{"Pretrain/Learning Rate": 1.2468149506178386e-05, "Pretrain/Loss": 1.9815831184387207, "Pretrain/Loss (Raw)": 2.006418466567993, "Pretrain/Step": 6457, "Pretrain/Step Time": 8.482316175475717} +{"Pretrain/Learning Rate": 1.2460803244493454e-05, "Pretrain/Loss": 1.9821791648864746, "Pretrain/Loss (Raw)": 2.0856637954711914, "Pretrain/Step": 6458, "Pretrain/Step Time": 8.482851495966315} +{"Pretrain/Learning Rate": 1.2453458429200463e-05, "Pretrain/Loss": 1.9815709590911865, "Pretrain/Loss (Raw)": 1.960098147392273, "Pretrain/Step": 6459, "Pretrain/Step Time": 8.4832813590765} +{"Pretrain/Learning Rate": 1.244611506114664e-05, "Pretrain/Loss": 1.9810999631881714, "Pretrain/Loss (Raw)": 2.063427209854126, "Pretrain/Step": 6460, "Pretrain/Step Time": 8.479860045015812} +{"Pretrain/Learning Rate": 1.2438773141179025e-05, "Pretrain/Loss": 1.9804904460906982, "Pretrain/Loss (Raw)": 2.096095323562622, "Pretrain/Step": 6461, "Pretrain/Step Time": 8.478588243946433} +{"Pretrain/Learning Rate": 1.2431432670144521e-05, "Pretrain/Loss": 1.9804465770721436, "Pretrain/Loss (Raw)": 2.0248377323150635, "Pretrain/Step": 6462, "Pretrain/Step Time": 8.476670367643237} +{"Pretrain/Learning Rate": 1.2424093648889834e-05, "Pretrain/Loss": 1.9799785614013672, "Pretrain/Loss (Raw)": 1.9507346153259277, "Pretrain/Step": 6463, "Pretrain/Step Time": 8.477514587342739} +{"Pretrain/Learning Rate": 1.2416756078261527e-05, "Pretrain/Loss": 1.9774223566055298, "Pretrain/Loss (Raw)": 1.783316731452942, "Pretrain/Step": 6464, "Pretrain/Step Time": 8.47934907861054} +{"Pretrain/Learning Rate": 1.2409419959105981e-05, "Pretrain/Loss": 1.9760847091674805, "Pretrain/Loss (Raw)": 1.91698157787323, "Pretrain/Step": 6465, "Pretrain/Step Time": 8.481060680001974} +{"Pretrain/Learning Rate": 1.2402085292269428e-05, "Pretrain/Loss": 1.9760417938232422, "Pretrain/Loss (Raw)": 2.0186188220977783, "Pretrain/Step": 6466, "Pretrain/Step Time": 8.481235532090068} +{"Pretrain/Learning Rate": 1.2394752078597902e-05, "Pretrain/Loss": 1.972733497619629, "Pretrain/Loss (Raw)": 1.5306684970855713, "Pretrain/Step": 6467, "Pretrain/Step Time": 8.481438396498561} +{"Pretrain/Learning Rate": 1.238742031893729e-05, "Pretrain/Loss": 1.973888635635376, "Pretrain/Loss (Raw)": 2.090240955352783, "Pretrain/Step": 6468, "Pretrain/Step Time": 8.478356780484319} +{"Pretrain/Learning Rate": 1.2380090014133317e-05, "Pretrain/Loss": 1.975490927696228, "Pretrain/Loss (Raw)": 2.006624221801758, "Pretrain/Step": 6469, "Pretrain/Step Time": 8.479330901056528} +{"Pretrain/Learning Rate": 1.2372761165031521e-05, "Pretrain/Loss": 1.9764907360076904, "Pretrain/Loss (Raw)": 2.0356359481811523, "Pretrain/Step": 6470, "Pretrain/Step Time": 8.47914145886898} +{"Pretrain/Learning Rate": 1.2365433772477289e-05, "Pretrain/Loss": 1.9785356521606445, "Pretrain/Loss (Raw)": 2.2070040702819824, "Pretrain/Step": 6471, "Pretrain/Step Time": 8.478341801092029} +{"Pretrain/Learning Rate": 1.2358107837315841e-05, "Pretrain/Loss": 1.9792068004608154, "Pretrain/Loss (Raw)": 1.9703681468963623, "Pretrain/Step": 6472, "Pretrain/Step Time": 8.483325056731701} +{"Pretrain/Learning Rate": 1.2350783360392201e-05, "Pretrain/Loss": 1.9781091213226318, "Pretrain/Loss (Raw)": 1.694815754890442, "Pretrain/Step": 6473, "Pretrain/Step Time": 8.48463268391788} +{"Pretrain/Learning Rate": 1.2343460342551258e-05, "Pretrain/Loss": 1.9782848358154297, "Pretrain/Loss (Raw)": 2.0195071697235107, "Pretrain/Step": 6474, "Pretrain/Step Time": 8.483546122908592} +{"Pretrain/Learning Rate": 1.2336138784637713e-05, "Pretrain/Loss": 1.9784016609191895, "Pretrain/Loss (Raw)": 2.0513341426849365, "Pretrain/Step": 6475, "Pretrain/Step Time": 8.482558650895953} +{"Pretrain/Learning Rate": 1.232881868749611e-05, "Pretrain/Loss": 1.978806495666504, "Pretrain/Loss (Raw)": 1.8715304136276245, "Pretrain/Step": 6476, "Pretrain/Step Time": 8.483653079718351} +{"Pretrain/Learning Rate": 1.232150005197083e-05, "Pretrain/Loss": 1.9786714315414429, "Pretrain/Loss (Raw)": 2.0174505710601807, "Pretrain/Step": 6477, "Pretrain/Step Time": 8.483317418023944} +{"Pretrain/Learning Rate": 1.2314182878906052e-05, "Pretrain/Loss": 1.9785728454589844, "Pretrain/Loss (Raw)": 1.872275471687317, "Pretrain/Step": 6478, "Pretrain/Step Time": 8.474750792607665} +{"Pretrain/Learning Rate": 1.230686716914583e-05, "Pretrain/Loss": 1.9791252613067627, "Pretrain/Loss (Raw)": 1.9025894403457642, "Pretrain/Step": 6479, "Pretrain/Step Time": 8.477283271029592} +{"Pretrain/Learning Rate": 1.229955292353401e-05, "Pretrain/Loss": 1.9778778553009033, "Pretrain/Loss (Raw)": 1.8970565795898438, "Pretrain/Step": 6480, "Pretrain/Step Time": 8.479440998286009} +{"Pretrain/Learning Rate": 1.22922401429143e-05, "Pretrain/Loss": 1.9771480560302734, "Pretrain/Loss (Raw)": 1.7436466217041016, "Pretrain/Step": 6481, "Pretrain/Step Time": 8.482125710695982} +{"Pretrain/Learning Rate": 1.228492882813023e-05, "Pretrain/Loss": 1.9776802062988281, "Pretrain/Loss (Raw)": 1.986471176147461, "Pretrain/Step": 6482, "Pretrain/Step Time": 8.482750535011292} +{"Pretrain/Learning Rate": 1.2277618980025141e-05, "Pretrain/Loss": 1.9770681858062744, "Pretrain/Loss (Raw)": 2.080249071121216, "Pretrain/Step": 6483, "Pretrain/Step Time": 8.484297083690763} +{"Pretrain/Learning Rate": 1.2270310599442234e-05, "Pretrain/Loss": 1.9777848720550537, "Pretrain/Loss (Raw)": 2.032846450805664, "Pretrain/Step": 6484, "Pretrain/Step Time": 8.478791544213891} +{"Pretrain/Learning Rate": 1.2263003687224524e-05, "Pretrain/Loss": 1.9786012172698975, "Pretrain/Loss (Raw)": 2.1244993209838867, "Pretrain/Step": 6485, "Pretrain/Step Time": 8.479364914819598} +{"Pretrain/Learning Rate": 1.2255698244214864e-05, "Pretrain/Loss": 1.9808704853057861, "Pretrain/Loss (Raw)": 2.012540817260742, "Pretrain/Step": 6486, "Pretrain/Step Time": 8.477614775300026} +{"Pretrain/Learning Rate": 1.2248394271255942e-05, "Pretrain/Loss": 1.9811962842941284, "Pretrain/Loss (Raw)": 1.990805745124817, "Pretrain/Step": 6487, "Pretrain/Step Time": 8.479692630469799} +{"Pretrain/Learning Rate": 1.224109176919025e-05, "Pretrain/Loss": 1.9819495677947998, "Pretrain/Loss (Raw)": 2.0852627754211426, "Pretrain/Step": 6488, "Pretrain/Step Time": 8.48140667192638} +{"Pretrain/Learning Rate": 1.223379073886014e-05, "Pretrain/Loss": 1.9800338745117188, "Pretrain/Loss (Raw)": 1.809818983078003, "Pretrain/Step": 6489, "Pretrain/Step Time": 8.481967948377132} +{"Pretrain/Learning Rate": 1.222649118110778e-05, "Pretrain/Loss": 1.9800879955291748, "Pretrain/Loss (Raw)": 1.9410412311553955, "Pretrain/Step": 6490, "Pretrain/Step Time": 8.480569511651993} +{"Pretrain/Learning Rate": 1.2219193096775172e-05, "Pretrain/Loss": 1.9805998802185059, "Pretrain/Loss (Raw)": 1.95021653175354, "Pretrain/Step": 6491, "Pretrain/Step Time": 8.481857467442751} +{"Pretrain/Learning Rate": 1.2211896486704152e-05, "Pretrain/Loss": 1.979201316833496, "Pretrain/Loss (Raw)": 1.9305014610290527, "Pretrain/Step": 6492, "Pretrain/Step Time": 8.482275998219848} +{"Pretrain/Learning Rate": 1.2204601351736385e-05, "Pretrain/Loss": 1.9807747602462769, "Pretrain/Loss (Raw)": 2.0725595951080322, "Pretrain/Step": 6493, "Pretrain/Step Time": 8.479699946939945} +{"Pretrain/Learning Rate": 1.2197307692713348e-05, "Pretrain/Loss": 1.9813306331634521, "Pretrain/Loss (Raw)": 2.0330440998077393, "Pretrain/Step": 6494, "Pretrain/Step Time": 8.479055687785149} +{"Pretrain/Learning Rate": 1.2190015510476379e-05, "Pretrain/Loss": 1.9836413860321045, "Pretrain/Loss (Raw)": 1.9874833822250366, "Pretrain/Step": 6495, "Pretrain/Step Time": 8.479939123615623} +{"Pretrain/Learning Rate": 1.2182724805866607e-05, "Pretrain/Loss": 1.9817934036254883, "Pretrain/Loss (Raw)": 1.9081827402114868, "Pretrain/Step": 6496, "Pretrain/Step Time": 8.478703143075109} +{"Pretrain/Learning Rate": 1.2175435579725029e-05, "Pretrain/Loss": 1.9805095195770264, "Pretrain/Loss (Raw)": 1.9276790618896484, "Pretrain/Step": 6497, "Pretrain/Step Time": 8.481083462014794} +{"Pretrain/Learning Rate": 1.2168147832892457e-05, "Pretrain/Loss": 1.9812947511672974, "Pretrain/Loss (Raw)": 2.132024049758911, "Pretrain/Step": 6498, "Pretrain/Step Time": 8.480198506265879} +{"Pretrain/Learning Rate": 1.2160861566209512e-05, "Pretrain/Loss": 1.9802738428115845, "Pretrain/Loss (Raw)": 1.7483817338943481, "Pretrain/Step": 6499, "Pretrain/Step Time": 8.483306519687176} +{"Pretrain/Learning Rate": 1.2153576780516674e-05, "Pretrain/Loss": 1.9788260459899902, "Pretrain/Loss (Raw)": 1.883118748664856, "Pretrain/Step": 6500, "Pretrain/Step Time": 8.483344295993447} +{"Pretrain/Learning Rate": 1.2146293476654242e-05, "Pretrain/Loss": 1.9766557216644287, "Pretrain/Loss (Raw)": 1.8625569343566895, "Pretrain/Step": 6501, "Pretrain/Step Time": 8.480635518208146} +{"Pretrain/Learning Rate": 1.2139011655462337e-05, "Pretrain/Loss": 1.9774028062820435, "Pretrain/Loss (Raw)": 2.0896317958831787, "Pretrain/Step": 6502, "Pretrain/Step Time": 8.481558857485652} +{"Pretrain/Learning Rate": 1.2131731317780932e-05, "Pretrain/Loss": 1.9779185056686401, "Pretrain/Loss (Raw)": 2.042613983154297, "Pretrain/Step": 6503, "Pretrain/Step Time": 8.482704807072878} +{"Pretrain/Learning Rate": 1.2124452464449784e-05, "Pretrain/Loss": 1.9782798290252686, "Pretrain/Loss (Raw)": 1.969393014907837, "Pretrain/Step": 6504, "Pretrain/Step Time": 8.48473785072565} +{"Pretrain/Learning Rate": 1.211717509630852e-05, "Pretrain/Loss": 1.9778907299041748, "Pretrain/Loss (Raw)": 1.9932289123535156, "Pretrain/Step": 6505, "Pretrain/Step Time": 8.481168983504176} +{"Pretrain/Learning Rate": 1.2109899214196582e-05, "Pretrain/Loss": 1.9770232439041138, "Pretrain/Loss (Raw)": 1.9283632040023804, "Pretrain/Step": 6506, "Pretrain/Step Time": 8.486155243590474} +{"Pretrain/Learning Rate": 1.210262481895324e-05, "Pretrain/Loss": 1.9796510934829712, "Pretrain/Loss (Raw)": 2.061830759048462, "Pretrain/Step": 6507, "Pretrain/Step Time": 8.480486648157239} +{"Pretrain/Learning Rate": 1.2095351911417599e-05, "Pretrain/Loss": 1.9791803359985352, "Pretrain/Loss (Raw)": 1.8839176893234253, "Pretrain/Step": 6508, "Pretrain/Step Time": 8.481546610593796} +{"Pretrain/Learning Rate": 1.2088080492428574e-05, "Pretrain/Loss": 1.9800348281860352, "Pretrain/Loss (Raw)": 2.143228769302368, "Pretrain/Step": 6509, "Pretrain/Step Time": 8.481090795248747} +{"Pretrain/Learning Rate": 1.2080810562824927e-05, "Pretrain/Loss": 1.9809505939483643, "Pretrain/Loss (Raw)": 2.1282155513763428, "Pretrain/Step": 6510, "Pretrain/Step Time": 8.480059629306197} +{"Pretrain/Learning Rate": 1.2073542123445239e-05, "Pretrain/Loss": 1.982075810432434, "Pretrain/Loss (Raw)": 1.99009108543396, "Pretrain/Step": 6511, "Pretrain/Step Time": 8.478607526049018} +{"Pretrain/Learning Rate": 1.2066275175127936e-05, "Pretrain/Loss": 1.9817235469818115, "Pretrain/Loss (Raw)": 2.02191162109375, "Pretrain/Step": 6512, "Pretrain/Step Time": 8.482068663462996} +{"Pretrain/Learning Rate": 1.2059009718711234e-05, "Pretrain/Loss": 1.9833509922027588, "Pretrain/Loss (Raw)": 1.9939756393432617, "Pretrain/Step": 6513, "Pretrain/Step Time": 8.486338285729289} +{"Pretrain/Learning Rate": 1.2051745755033226e-05, "Pretrain/Loss": 1.9862241744995117, "Pretrain/Loss (Raw)": 2.1478240489959717, "Pretrain/Step": 6514, "Pretrain/Step Time": 8.484969850629568} +{"Pretrain/Learning Rate": 1.2044483284931785e-05, "Pretrain/Loss": 1.9870045185089111, "Pretrain/Loss (Raw)": 2.103332757949829, "Pretrain/Step": 6515, "Pretrain/Step Time": 8.488826040178537} +{"Pretrain/Learning Rate": 1.2037222309244642e-05, "Pretrain/Loss": 1.985761046409607, "Pretrain/Loss (Raw)": 2.0615739822387695, "Pretrain/Step": 6516, "Pretrain/Step Time": 8.487846592441201} +{"Pretrain/Learning Rate": 1.2029962828809351e-05, "Pretrain/Loss": 1.98793625831604, "Pretrain/Loss (Raw)": 2.1678884029388428, "Pretrain/Step": 6517, "Pretrain/Step Time": 8.486147407442331} +{"Pretrain/Learning Rate": 1.202270484446329e-05, "Pretrain/Loss": 1.9877049922943115, "Pretrain/Loss (Raw)": 1.864260196685791, "Pretrain/Step": 6518, "Pretrain/Step Time": 8.488013694062829} +{"Pretrain/Learning Rate": 1.2015448357043674e-05, "Pretrain/Loss": 1.9892098903656006, "Pretrain/Loss (Raw)": 2.271810531616211, "Pretrain/Step": 6519, "Pretrain/Step Time": 8.487420065328479} +{"Pretrain/Learning Rate": 1.2008193367387519e-05, "Pretrain/Loss": 1.9881010055541992, "Pretrain/Loss (Raw)": 1.8807692527770996, "Pretrain/Step": 6520, "Pretrain/Step Time": 8.487126231193542} +{"Pretrain/Learning Rate": 1.200093987633169e-05, "Pretrain/Loss": 1.9880154132843018, "Pretrain/Loss (Raw)": 2.060823440551758, "Pretrain/Step": 6521, "Pretrain/Step Time": 8.487623106688261} +{"Pretrain/Learning Rate": 1.1993687884712882e-05, "Pretrain/Loss": 1.98690664768219, "Pretrain/Loss (Raw)": 2.0372395515441895, "Pretrain/Step": 6522, "Pretrain/Step Time": 8.489491742104292} +{"Pretrain/Learning Rate": 1.1986437393367604e-05, "Pretrain/Loss": 1.989164113998413, "Pretrain/Loss (Raw)": 2.1107301712036133, "Pretrain/Step": 6523, "Pretrain/Step Time": 8.491195699200034} +{"Pretrain/Learning Rate": 1.1979188403132208e-05, "Pretrain/Loss": 1.9888010025024414, "Pretrain/Loss (Raw)": 1.8447957038879395, "Pretrain/Step": 6524, "Pretrain/Step Time": 8.48885932751} +{"Pretrain/Learning Rate": 1.1971940914842845e-05, "Pretrain/Loss": 1.9884233474731445, "Pretrain/Loss (Raw)": 1.995349407196045, "Pretrain/Step": 6525, "Pretrain/Step Time": 8.491562293842435} +{"Pretrain/Learning Rate": 1.1964694929335518e-05, "Pretrain/Loss": 1.9868626594543457, "Pretrain/Loss (Raw)": 1.7816882133483887, "Pretrain/Step": 6526, "Pretrain/Step Time": 8.489407755434513} +{"Pretrain/Learning Rate": 1.195745044744605e-05, "Pretrain/Loss": 1.9869275093078613, "Pretrain/Loss (Raw)": 2.075261354446411, "Pretrain/Step": 6527, "Pretrain/Step Time": 8.488413659855723} +{"Pretrain/Learning Rate": 1.1950207470010102e-05, "Pretrain/Loss": 1.9873770475387573, "Pretrain/Loss (Raw)": 2.0915896892547607, "Pretrain/Step": 6528, "Pretrain/Step Time": 8.490336941555142} +{"Pretrain/Learning Rate": 1.1942965997863123e-05, "Pretrain/Loss": 1.986757755279541, "Pretrain/Loss (Raw)": 2.0007498264312744, "Pretrain/Step": 6529, "Pretrain/Step Time": 8.484120087698102} +{"Pretrain/Learning Rate": 1.193572603184044e-05, "Pretrain/Loss": 1.986595630645752, "Pretrain/Loss (Raw)": 1.9991953372955322, "Pretrain/Step": 6530, "Pretrain/Step Time": 8.483699196949601} +{"Pretrain/Learning Rate": 1.1928487572777159e-05, "Pretrain/Loss": 1.9871253967285156, "Pretrain/Loss (Raw)": 2.122080087661743, "Pretrain/Step": 6531, "Pretrain/Step Time": 8.490312857553363} +{"Pretrain/Learning Rate": 1.192125062150824e-05, "Pretrain/Loss": 1.9881539344787598, "Pretrain/Loss (Raw)": 2.0744993686676025, "Pretrain/Step": 6532, "Pretrain/Step Time": 8.487900579348207} +{"Pretrain/Learning Rate": 1.1914015178868468e-05, "Pretrain/Loss": 1.9896888732910156, "Pretrain/Loss (Raw)": 2.1583445072174072, "Pretrain/Step": 6533, "Pretrain/Step Time": 8.48625079356134} +{"Pretrain/Learning Rate": 1.1906781245692444e-05, "Pretrain/Loss": 1.9878612756729126, "Pretrain/Loss (Raw)": 1.964258074760437, "Pretrain/Step": 6534, "Pretrain/Step Time": 8.488620897755027} +{"Pretrain/Learning Rate": 1.1899548822814613e-05, "Pretrain/Loss": 1.98856782913208, "Pretrain/Loss (Raw)": 2.167586326599121, "Pretrain/Step": 6535, "Pretrain/Step Time": 8.484996294602752} +{"Pretrain/Learning Rate": 1.1892317911069212e-05, "Pretrain/Loss": 1.9890756607055664, "Pretrain/Loss (Raw)": 2.000619888305664, "Pretrain/Step": 6536, "Pretrain/Step Time": 8.486459087580442} +{"Pretrain/Learning Rate": 1.1885088511290332e-05, "Pretrain/Loss": 1.9884114265441895, "Pretrain/Loss (Raw)": 2.007652521133423, "Pretrain/Step": 6537, "Pretrain/Step Time": 8.488125681877136} +{"Pretrain/Learning Rate": 1.1877860624311887e-05, "Pretrain/Loss": 1.988147258758545, "Pretrain/Loss (Raw)": 2.1788909435272217, "Pretrain/Step": 6538, "Pretrain/Step Time": 8.490917168557644} +{"Pretrain/Learning Rate": 1.1870634250967605e-05, "Pretrain/Loss": 1.9887218475341797, "Pretrain/Loss (Raw)": 2.158444881439209, "Pretrain/Step": 6539, "Pretrain/Step Time": 8.48773525096476} +{"Pretrain/Learning Rate": 1.1863409392091057e-05, "Pretrain/Loss": 1.9873671531677246, "Pretrain/Loss (Raw)": 1.9376120567321777, "Pretrain/Step": 6540, "Pretrain/Step Time": 8.487360281869769} +{"Pretrain/Learning Rate": 1.1856186048515611e-05, "Pretrain/Loss": 1.9852793216705322, "Pretrain/Loss (Raw)": 1.966805100440979, "Pretrain/Step": 6541, "Pretrain/Step Time": 8.488874463364482} +{"Pretrain/Learning Rate": 1.1848964221074486e-05, "Pretrain/Loss": 1.9878705739974976, "Pretrain/Loss (Raw)": 2.1591134071350098, "Pretrain/Step": 6542, "Pretrain/Step Time": 8.487084662541747} +{"Pretrain/Learning Rate": 1.1841743910600713e-05, "Pretrain/Loss": 1.9880144596099854, "Pretrain/Loss (Raw)": 2.121520757675171, "Pretrain/Step": 6543, "Pretrain/Step Time": 8.482994817197323} +{"Pretrain/Learning Rate": 1.183452511792717e-05, "Pretrain/Loss": 1.988150954246521, "Pretrain/Loss (Raw)": 2.0195255279541016, "Pretrain/Step": 6544, "Pretrain/Step Time": 8.483299970626831} +{"Pretrain/Learning Rate": 1.1827307843886515e-05, "Pretrain/Loss": 1.9885096549987793, "Pretrain/Loss (Raw)": 1.9631810188293457, "Pretrain/Step": 6545, "Pretrain/Step Time": 8.482582867145538} +{"Pretrain/Learning Rate": 1.182009208931128e-05, "Pretrain/Loss": 1.9895473718643188, "Pretrain/Loss (Raw)": 2.096961498260498, "Pretrain/Step": 6546, "Pretrain/Step Time": 8.484189815819263} +{"Pretrain/Learning Rate": 1.1812877855033782e-05, "Pretrain/Loss": 1.989964246749878, "Pretrain/Loss (Raw)": 2.0955631732940674, "Pretrain/Step": 6547, "Pretrain/Step Time": 8.482351243495941} +{"Pretrain/Learning Rate": 1.1805665141886191e-05, "Pretrain/Loss": 1.9901694059371948, "Pretrain/Loss (Raw)": 1.955709457397461, "Pretrain/Step": 6548, "Pretrain/Step Time": 8.48734231106937} +{"Pretrain/Learning Rate": 1.1798453950700488e-05, "Pretrain/Loss": 1.990778923034668, "Pretrain/Loss (Raw)": 2.0469624996185303, "Pretrain/Step": 6549, "Pretrain/Step Time": 8.480450581759214} +{"Pretrain/Learning Rate": 1.1791244282308484e-05, "Pretrain/Loss": 1.9919483661651611, "Pretrain/Loss (Raw)": 2.1380786895751953, "Pretrain/Step": 6550, "Pretrain/Step Time": 8.480736019089818} +{"Pretrain/Learning Rate": 1.1784036137541818e-05, "Pretrain/Loss": 1.9950664043426514, "Pretrain/Loss (Raw)": 2.1249940395355225, "Pretrain/Step": 6551, "Pretrain/Step Time": 8.479788482189178} +{"Pretrain/Learning Rate": 1.177682951723193e-05, "Pretrain/Loss": 1.9939312934875488, "Pretrain/Loss (Raw)": 1.8596124649047852, "Pretrain/Step": 6552, "Pretrain/Step Time": 8.479848064482212} +{"Pretrain/Learning Rate": 1.176962442221011e-05, "Pretrain/Loss": 1.9934792518615723, "Pretrain/Loss (Raw)": 1.9939364194869995, "Pretrain/Step": 6553, "Pretrain/Step Time": 8.47917784564197} +{"Pretrain/Learning Rate": 1.1762420853307463e-05, "Pretrain/Loss": 1.9932788610458374, "Pretrain/Loss (Raw)": 1.9363123178482056, "Pretrain/Step": 6554, "Pretrain/Step Time": 8.477882597595453} +{"Pretrain/Learning Rate": 1.1755218811354918e-05, "Pretrain/Loss": 1.9928228855133057, "Pretrain/Loss (Raw)": 1.9345142841339111, "Pretrain/Step": 6555, "Pretrain/Step Time": 8.478151926770806} +{"Pretrain/Learning Rate": 1.1748018297183238e-05, "Pretrain/Loss": 1.9925789833068848, "Pretrain/Loss (Raw)": 1.9628578424453735, "Pretrain/Step": 6556, "Pretrain/Step Time": 8.479479121044278} +{"Pretrain/Learning Rate": 1.1740819311622982e-05, "Pretrain/Loss": 1.9943327903747559, "Pretrain/Loss (Raw)": 2.1555280685424805, "Pretrain/Step": 6557, "Pretrain/Step Time": 8.476792870089412} +{"Pretrain/Learning Rate": 1.1733621855504559e-05, "Pretrain/Loss": 1.9946377277374268, "Pretrain/Loss (Raw)": 2.135715961456299, "Pretrain/Step": 6558, "Pretrain/Step Time": 8.477457884699106} +{"Pretrain/Learning Rate": 1.1726425929658194e-05, "Pretrain/Loss": 1.9946811199188232, "Pretrain/Loss (Raw)": 1.9909249544143677, "Pretrain/Step": 6559, "Pretrain/Step Time": 8.477453634142876} +{"Pretrain/Learning Rate": 1.1719231534913933e-05, "Pretrain/Loss": 1.994423747062683, "Pretrain/Loss (Raw)": 2.044358253479004, "Pretrain/Step": 6560, "Pretrain/Step Time": 8.476820811629295} +{"Pretrain/Learning Rate": 1.1712038672101654e-05, "Pretrain/Loss": 1.9923659563064575, "Pretrain/Loss (Raw)": 1.9411077499389648, "Pretrain/Step": 6561, "Pretrain/Step Time": 8.476354649290442} +{"Pretrain/Learning Rate": 1.1704847342051037e-05, "Pretrain/Loss": 1.995106816291809, "Pretrain/Loss (Raw)": 2.2412378787994385, "Pretrain/Step": 6562, "Pretrain/Step Time": 8.474036913365126} +{"Pretrain/Learning Rate": 1.1697657545591615e-05, "Pretrain/Loss": 1.994739294052124, "Pretrain/Loss (Raw)": 1.9666703939437866, "Pretrain/Step": 6563, "Pretrain/Step Time": 8.472848130390048} +{"Pretrain/Learning Rate": 1.1690469283552713e-05, "Pretrain/Loss": 1.9955456256866455, "Pretrain/Loss (Raw)": 2.1138486862182617, "Pretrain/Step": 6564, "Pretrain/Step Time": 8.47427854500711} +{"Pretrain/Learning Rate": 1.16832825567635e-05, "Pretrain/Loss": 1.9967275857925415, "Pretrain/Loss (Raw)": 1.9565048217773438, "Pretrain/Step": 6565, "Pretrain/Step Time": 8.474751848727465} +{"Pretrain/Learning Rate": 1.1676097366052974e-05, "Pretrain/Loss": 1.996166706085205, "Pretrain/Loss (Raw)": 1.827034831047058, "Pretrain/Step": 6566, "Pretrain/Step Time": 8.47554137930274} +{"Pretrain/Learning Rate": 1.1668913712249924e-05, "Pretrain/Loss": 1.9971470832824707, "Pretrain/Loss (Raw)": 1.9578608274459839, "Pretrain/Step": 6567, "Pretrain/Step Time": 8.472411775961518} +{"Pretrain/Learning Rate": 1.1661731596182995e-05, "Pretrain/Loss": 1.99825119972229, "Pretrain/Loss (Raw)": 2.082131862640381, "Pretrain/Step": 6568, "Pretrain/Step Time": 8.473627818748355} +{"Pretrain/Learning Rate": 1.1654551018680637e-05, "Pretrain/Loss": 1.9983569383621216, "Pretrain/Loss (Raw)": 1.991757869720459, "Pretrain/Step": 6569, "Pretrain/Step Time": 8.475445922464132} +{"Pretrain/Learning Rate": 1.164737198057113e-05, "Pretrain/Loss": 2.0001654624938965, "Pretrain/Loss (Raw)": 2.081343412399292, "Pretrain/Step": 6570, "Pretrain/Step Time": 8.473646011203527} +{"Pretrain/Learning Rate": 1.1640194482682573e-05, "Pretrain/Loss": 1.9997804164886475, "Pretrain/Loss (Raw)": 1.9286351203918457, "Pretrain/Step": 6571, "Pretrain/Step Time": 8.473199520260096} +{"Pretrain/Learning Rate": 1.1633018525842895e-05, "Pretrain/Loss": 2.0008983612060547, "Pretrain/Loss (Raw)": 1.9432557821273804, "Pretrain/Step": 6572, "Pretrain/Step Time": 8.47767561674118} +{"Pretrain/Learning Rate": 1.1625844110879825e-05, "Pretrain/Loss": 2.0015921592712402, "Pretrain/Loss (Raw)": 1.9507580995559692, "Pretrain/Step": 6573, "Pretrain/Step Time": 8.477076949551702} +{"Pretrain/Learning Rate": 1.1618671238620938e-05, "Pretrain/Loss": 2.0018692016601562, "Pretrain/Loss (Raw)": 1.9553254842758179, "Pretrain/Step": 6574, "Pretrain/Step Time": 8.474057229235768} +{"Pretrain/Learning Rate": 1.1611499909893616e-05, "Pretrain/Loss": 2.00123929977417, "Pretrain/Loss (Raw)": 1.979658603668213, "Pretrain/Step": 6575, "Pretrain/Step Time": 8.470106072723866} +{"Pretrain/Learning Rate": 1.1604330125525079e-05, "Pretrain/Loss": 2.001270055770874, "Pretrain/Loss (Raw)": 2.0294413566589355, "Pretrain/Step": 6576, "Pretrain/Step Time": 8.471846466884017} +{"Pretrain/Learning Rate": 1.1597161886342362e-05, "Pretrain/Loss": 2.0031380653381348, "Pretrain/Loss (Raw)": 1.9602090120315552, "Pretrain/Step": 6577, "Pretrain/Step Time": 8.47035506553948} +{"Pretrain/Learning Rate": 1.1589995193172303e-05, "Pretrain/Loss": 2.001796245574951, "Pretrain/Loss (Raw)": 1.8572144508361816, "Pretrain/Step": 6578, "Pretrain/Step Time": 8.476357653737068} +{"Pretrain/Learning Rate": 1.1582830046841595e-05, "Pretrain/Loss": 2.002516031265259, "Pretrain/Loss (Raw)": 1.9955838918685913, "Pretrain/Step": 6579, "Pretrain/Step Time": 8.477371552959085} +{"Pretrain/Learning Rate": 1.1575666448176717e-05, "Pretrain/Loss": 2.004274845123291, "Pretrain/Loss (Raw)": 1.9669089317321777, "Pretrain/Step": 6580, "Pretrain/Step Time": 8.47226900793612} +{"Pretrain/Learning Rate": 1.1568504398003996e-05, "Pretrain/Loss": 2.0052123069763184, "Pretrain/Loss (Raw)": 2.1131961345672607, "Pretrain/Step": 6581, "Pretrain/Step Time": 8.47497764788568} +{"Pretrain/Learning Rate": 1.1561343897149583e-05, "Pretrain/Loss": 2.0046889781951904, "Pretrain/Loss (Raw)": 2.043820381164551, "Pretrain/Step": 6582, "Pretrain/Step Time": 8.476127421483397} +{"Pretrain/Learning Rate": 1.1554184946439417e-05, "Pretrain/Loss": 2.0024685859680176, "Pretrain/Loss (Raw)": 1.631618857383728, "Pretrain/Step": 6583, "Pretrain/Step Time": 8.478689454495907} +{"Pretrain/Learning Rate": 1.1547027546699293e-05, "Pretrain/Loss": 2.000220537185669, "Pretrain/Loss (Raw)": 1.9834398031234741, "Pretrain/Step": 6584, "Pretrain/Step Time": 8.47847729548812} +{"Pretrain/Learning Rate": 1.1539871698754814e-05, "Pretrain/Loss": 1.999271273612976, "Pretrain/Loss (Raw)": 1.884900689125061, "Pretrain/Step": 6585, "Pretrain/Step Time": 8.477116972208023} +{"Pretrain/Learning Rate": 1.1532717403431403e-05, "Pretrain/Loss": 1.9975254535675049, "Pretrain/Loss (Raw)": 1.8622006177902222, "Pretrain/Step": 6586, "Pretrain/Step Time": 8.476825317367911} +{"Pretrain/Learning Rate": 1.152556466155432e-05, "Pretrain/Loss": 1.9973299503326416, "Pretrain/Loss (Raw)": 1.9350855350494385, "Pretrain/Step": 6587, "Pretrain/Step Time": 8.475891077890992} +{"Pretrain/Learning Rate": 1.1518413473948606e-05, "Pretrain/Loss": 1.9964206218719482, "Pretrain/Loss (Raw)": 1.9470138549804688, "Pretrain/Step": 6588, "Pretrain/Step Time": 8.478044375777245} +{"Pretrain/Learning Rate": 1.151126384143916e-05, "Pretrain/Loss": 1.995947241783142, "Pretrain/Loss (Raw)": 2.0355045795440674, "Pretrain/Step": 6589, "Pretrain/Step Time": 8.477418269962072} +{"Pretrain/Learning Rate": 1.150411576485069e-05, "Pretrain/Loss": 1.9954230785369873, "Pretrain/Loss (Raw)": 1.957737922668457, "Pretrain/Step": 6590, "Pretrain/Step Time": 8.476470930501819} +{"Pretrain/Learning Rate": 1.1496969245007721e-05, "Pretrain/Loss": 1.9966228008270264, "Pretrain/Loss (Raw)": 2.1043286323547363, "Pretrain/Step": 6591, "Pretrain/Step Time": 8.475152472034097} +{"Pretrain/Learning Rate": 1.1489824282734609e-05, "Pretrain/Loss": 1.9983396530151367, "Pretrain/Loss (Raw)": 2.0030558109283447, "Pretrain/Step": 6592, "Pretrain/Step Time": 8.476118875667453} +{"Pretrain/Learning Rate": 1.1482680878855526e-05, "Pretrain/Loss": 1.9992369413375854, "Pretrain/Loss (Raw)": 2.031832695007324, "Pretrain/Step": 6593, "Pretrain/Step Time": 8.47407172061503} +{"Pretrain/Learning Rate": 1.1475539034194443e-05, "Pretrain/Loss": 1.9970847368240356, "Pretrain/Loss (Raw)": 1.7431379556655884, "Pretrain/Step": 6594, "Pretrain/Step Time": 8.474510688334703} +{"Pretrain/Learning Rate": 1.1468398749575188e-05, "Pretrain/Loss": 1.9991613626480103, "Pretrain/Loss (Raw)": 1.7964836359024048, "Pretrain/Step": 6595, "Pretrain/Step Time": 8.471629673615098} +{"Pretrain/Learning Rate": 1.1461260025821375e-05, "Pretrain/Loss": 1.9985655546188354, "Pretrain/Loss (Raw)": 2.013972759246826, "Pretrain/Step": 6596, "Pretrain/Step Time": 8.470311436802149} +{"Pretrain/Learning Rate": 1.1454122863756459e-05, "Pretrain/Loss": 1.9967284202575684, "Pretrain/Loss (Raw)": 1.7714588642120361, "Pretrain/Step": 6597, "Pretrain/Step Time": 8.470298754051328} +{"Pretrain/Learning Rate": 1.144698726420372e-05, "Pretrain/Loss": 1.997402548789978, "Pretrain/Loss (Raw)": 2.121934175491333, "Pretrain/Step": 6598, "Pretrain/Step Time": 8.471610978245735} +{"Pretrain/Learning Rate": 1.1439853227986228e-05, "Pretrain/Loss": 1.9945757389068604, "Pretrain/Loss (Raw)": 1.845184087753296, "Pretrain/Step": 6599, "Pretrain/Step Time": 8.474300848320127} +{"Pretrain/Learning Rate": 1.1432720755926898e-05, "Pretrain/Loss": 1.9947351217269897, "Pretrain/Loss (Raw)": 1.9907554388046265, "Pretrain/Step": 6600, "Pretrain/Step Time": 8.475439392030239} +{"Pretrain/Learning Rate": 1.1425589848848464e-05, "Pretrain/Loss": 1.9972357749938965, "Pretrain/Loss (Raw)": 2.0149006843566895, "Pretrain/Step": 6601, "Pretrain/Step Time": 8.475906984880567} +{"Pretrain/Learning Rate": 1.141846050757347e-05, "Pretrain/Loss": 1.9968905448913574, "Pretrain/Loss (Raw)": 1.9753113985061646, "Pretrain/Step": 6602, "Pretrain/Step Time": 8.47532676719129} +{"Pretrain/Learning Rate": 1.1411332732924293e-05, "Pretrain/Loss": 1.996255874633789, "Pretrain/Loss (Raw)": 1.9700959920883179, "Pretrain/Step": 6603, "Pretrain/Step Time": 8.47675970941782} +{"Pretrain/Learning Rate": 1.1404206525723103e-05, "Pretrain/Loss": 1.996943712234497, "Pretrain/Loss (Raw)": 1.9595859050750732, "Pretrain/Step": 6604, "Pretrain/Step Time": 8.471229869872332} +{"Pretrain/Learning Rate": 1.1397081886791907e-05, "Pretrain/Loss": 1.9965968132019043, "Pretrain/Loss (Raw)": 1.9730385541915894, "Pretrain/Step": 6605, "Pretrain/Step Time": 8.47168766707182} +{"Pretrain/Learning Rate": 1.1389958816952537e-05, "Pretrain/Loss": 1.9974725246429443, "Pretrain/Loss (Raw)": 1.9843673706054688, "Pretrain/Step": 6606, "Pretrain/Step Time": 8.471184458583593} +{"Pretrain/Learning Rate": 1.1382837317026638e-05, "Pretrain/Loss": 1.9974780082702637, "Pretrain/Loss (Raw)": 1.903306245803833, "Pretrain/Step": 6607, "Pretrain/Step Time": 8.47040656208992} +{"Pretrain/Learning Rate": 1.1375717387835675e-05, "Pretrain/Loss": 2.00020694732666, "Pretrain/Loss (Raw)": 2.2463526725769043, "Pretrain/Step": 6608, "Pretrain/Step Time": 8.468771938234568} +{"Pretrain/Learning Rate": 1.1368599030200913e-05, "Pretrain/Loss": 2.000535011291504, "Pretrain/Loss (Raw)": 1.7856347560882568, "Pretrain/Step": 6609, "Pretrain/Step Time": 8.467409707605839} +{"Pretrain/Learning Rate": 1.1361482244943463e-05, "Pretrain/Loss": 1.999876856803894, "Pretrain/Loss (Raw)": 1.902229905128479, "Pretrain/Step": 6610, "Pretrain/Step Time": 8.466411536559463} +{"Pretrain/Learning Rate": 1.1354367032884244e-05, "Pretrain/Loss": 1.9996919631958008, "Pretrain/Loss (Raw)": 2.0565762519836426, "Pretrain/Step": 6611, "Pretrain/Step Time": 8.467868814244866} +{"Pretrain/Learning Rate": 1.1347253394844004e-05, "Pretrain/Loss": 1.9974122047424316, "Pretrain/Loss (Raw)": 1.7410428524017334, "Pretrain/Step": 6612, "Pretrain/Step Time": 8.468427838757634} +{"Pretrain/Learning Rate": 1.1340141331643276e-05, "Pretrain/Loss": 1.996591567993164, "Pretrain/Loss (Raw)": 2.0194520950317383, "Pretrain/Step": 6613, "Pretrain/Step Time": 8.468120960518718} +{"Pretrain/Learning Rate": 1.1333030844102452e-05, "Pretrain/Loss": 1.9969995021820068, "Pretrain/Loss (Raw)": 2.0647759437561035, "Pretrain/Step": 6614, "Pretrain/Step Time": 8.46643185056746} +{"Pretrain/Learning Rate": 1.1325921933041711e-05, "Pretrain/Loss": 1.996671199798584, "Pretrain/Loss (Raw)": 1.948769211769104, "Pretrain/Step": 6615, "Pretrain/Step Time": 8.468125080689788} +{"Pretrain/Learning Rate": 1.131881459928107e-05, "Pretrain/Loss": 1.99712073802948, "Pretrain/Loss (Raw)": 2.1428020000457764, "Pretrain/Step": 6616, "Pretrain/Step Time": 8.468223497271538} +{"Pretrain/Learning Rate": 1.1311708843640354e-05, "Pretrain/Loss": 1.9962879419326782, "Pretrain/Loss (Raw)": 1.7032276391983032, "Pretrain/Step": 6617, "Pretrain/Step Time": 8.468050552532077} +{"Pretrain/Learning Rate": 1.1304604666939214e-05, "Pretrain/Loss": 1.9954133033752441, "Pretrain/Loss (Raw)": 1.8290812969207764, "Pretrain/Step": 6618, "Pretrain/Step Time": 8.465752536430955} +{"Pretrain/Learning Rate": 1.1297502069997121e-05, "Pretrain/Loss": 1.9965901374816895, "Pretrain/Loss (Raw)": 2.100851535797119, "Pretrain/Step": 6619, "Pretrain/Step Time": 8.467139733955264} +{"Pretrain/Learning Rate": 1.1290401053633339e-05, "Pretrain/Loss": 1.996946096420288, "Pretrain/Loss (Raw)": 1.9760737419128418, "Pretrain/Step": 6620, "Pretrain/Step Time": 8.467005010694265} +{"Pretrain/Learning Rate": 1.128330161866698e-05, "Pretrain/Loss": 1.9965877532958984, "Pretrain/Loss (Raw)": 2.026688814163208, "Pretrain/Step": 6621, "Pretrain/Step Time": 8.47151373513043} +{"Pretrain/Learning Rate": 1.127620376591696e-05, "Pretrain/Loss": 1.996656060218811, "Pretrain/Loss (Raw)": 2.041790246963501, "Pretrain/Step": 6622, "Pretrain/Step Time": 8.469046622514725} +{"Pretrain/Learning Rate": 1.1269107496202008e-05, "Pretrain/Loss": 1.9984307289123535, "Pretrain/Loss (Raw)": 2.2146315574645996, "Pretrain/Step": 6623, "Pretrain/Step Time": 8.466892378404737} +{"Pretrain/Learning Rate": 1.1262012810340694e-05, "Pretrain/Loss": 2.000051975250244, "Pretrain/Loss (Raw)": 2.1156809329986572, "Pretrain/Step": 6624, "Pretrain/Step Time": 8.467991890385747} +{"Pretrain/Learning Rate": 1.1254919709151365e-05, "Pretrain/Loss": 2.000481128692627, "Pretrain/Loss (Raw)": 1.9826345443725586, "Pretrain/Step": 6625, "Pretrain/Step Time": 8.465394364669919} +{"Pretrain/Learning Rate": 1.1247828193452214e-05, "Pretrain/Loss": 1.9993572235107422, "Pretrain/Loss (Raw)": 1.9881662130355835, "Pretrain/Step": 6626, "Pretrain/Step Time": 8.464691011235118} +{"Pretrain/Learning Rate": 1.1240738264061252e-05, "Pretrain/Loss": 2.000572443008423, "Pretrain/Loss (Raw)": 1.903911828994751, "Pretrain/Step": 6627, "Pretrain/Step Time": 8.464606307446957} +{"Pretrain/Learning Rate": 1.1233649921796305e-05, "Pretrain/Loss": 2.0026025772094727, "Pretrain/Loss (Raw)": 2.1429972648620605, "Pretrain/Step": 6628, "Pretrain/Step Time": 8.464794747531414} +{"Pretrain/Learning Rate": 1.122656316747499e-05, "Pretrain/Loss": 2.004295825958252, "Pretrain/Loss (Raw)": 2.0792667865753174, "Pretrain/Step": 6629, "Pretrain/Step Time": 8.4658986274153} +{"Pretrain/Learning Rate": 1.1219478001914782e-05, "Pretrain/Loss": 2.0041980743408203, "Pretrain/Loss (Raw)": 2.0771546363830566, "Pretrain/Step": 6630, "Pretrain/Step Time": 8.465566497296095} +{"Pretrain/Learning Rate": 1.1212394425932936e-05, "Pretrain/Loss": 2.0041966438293457, "Pretrain/Loss (Raw)": 2.042397975921631, "Pretrain/Step": 6631, "Pretrain/Step Time": 8.465864770114422} +{"Pretrain/Learning Rate": 1.120531244034655e-05, "Pretrain/Loss": 2.003162145614624, "Pretrain/Loss (Raw)": 1.8369874954223633, "Pretrain/Step": 6632, "Pretrain/Step Time": 8.466218307614326} +{"Pretrain/Learning Rate": 1.1198232045972523e-05, "Pretrain/Loss": 2.003901958465576, "Pretrain/Loss (Raw)": 2.087961196899414, "Pretrain/Step": 6633, "Pretrain/Step Time": 8.467210164293647} +{"Pretrain/Learning Rate": 1.1191153243627577e-05, "Pretrain/Loss": 2.0063257217407227, "Pretrain/Loss (Raw)": 2.2385714054107666, "Pretrain/Step": 6634, "Pretrain/Step Time": 8.463615024462342} +{"Pretrain/Learning Rate": 1.1184076034128266e-05, "Pretrain/Loss": 2.0041990280151367, "Pretrain/Loss (Raw)": 1.7896146774291992, "Pretrain/Step": 6635, "Pretrain/Step Time": 8.467992831021547} +{"Pretrain/Learning Rate": 1.1177000418290917e-05, "Pretrain/Loss": 2.0056395530700684, "Pretrain/Loss (Raw)": 2.0683069229125977, "Pretrain/Step": 6636, "Pretrain/Step Time": 8.47111812978983} +{"Pretrain/Learning Rate": 1.1169926396931712e-05, "Pretrain/Loss": 2.004685640335083, "Pretrain/Loss (Raw)": 2.021127223968506, "Pretrain/Step": 6637, "Pretrain/Step Time": 8.468172926455736} +{"Pretrain/Learning Rate": 1.1162853970866638e-05, "Pretrain/Loss": 2.004523992538452, "Pretrain/Loss (Raw)": 2.107536792755127, "Pretrain/Step": 6638, "Pretrain/Step Time": 8.469126626849174} +{"Pretrain/Learning Rate": 1.1155783140911496e-05, "Pretrain/Loss": 2.0054991245269775, "Pretrain/Loss (Raw)": 2.114891290664673, "Pretrain/Step": 6639, "Pretrain/Step Time": 8.47149027697742} +{"Pretrain/Learning Rate": 1.1148713907881913e-05, "Pretrain/Loss": 2.006119728088379, "Pretrain/Loss (Raw)": 2.1013333797454834, "Pretrain/Step": 6640, "Pretrain/Step Time": 8.467157768085599} +{"Pretrain/Learning Rate": 1.1141646272593303e-05, "Pretrain/Loss": 2.00810170173645, "Pretrain/Loss (Raw)": 2.2477099895477295, "Pretrain/Step": 6641, "Pretrain/Step Time": 8.46273573115468} +{"Pretrain/Learning Rate": 1.1134580235860926e-05, "Pretrain/Loss": 2.00612735748291, "Pretrain/Loss (Raw)": 1.8950942754745483, "Pretrain/Step": 6642, "Pretrain/Step Time": 8.469390278682113} +{"Pretrain/Learning Rate": 1.1127515798499844e-05, "Pretrain/Loss": 2.0058164596557617, "Pretrain/Loss (Raw)": 2.063538074493408, "Pretrain/Step": 6643, "Pretrain/Step Time": 8.467212870717049} +{"Pretrain/Learning Rate": 1.112045296132494e-05, "Pretrain/Loss": 2.0047833919525146, "Pretrain/Loss (Raw)": 1.9293112754821777, "Pretrain/Step": 6644, "Pretrain/Step Time": 8.47341886907816} +{"Pretrain/Learning Rate": 1.111339172515092e-05, "Pretrain/Loss": 2.0027079582214355, "Pretrain/Loss (Raw)": 1.9022451639175415, "Pretrain/Step": 6645, "Pretrain/Step Time": 8.473705066367984} +{"Pretrain/Learning Rate": 1.1106332090792274e-05, "Pretrain/Loss": 2.0045042037963867, "Pretrain/Loss (Raw)": 2.094202995300293, "Pretrain/Step": 6646, "Pretrain/Step Time": 8.473717181012034} +{"Pretrain/Learning Rate": 1.109927405906335e-05, "Pretrain/Loss": 2.0022878646850586, "Pretrain/Loss (Raw)": 1.9881324768066406, "Pretrain/Step": 6647, "Pretrain/Step Time": 8.476097302511334} +{"Pretrain/Learning Rate": 1.1092217630778268e-05, "Pretrain/Loss": 2.001386880874634, "Pretrain/Loss (Raw)": 1.7654287815093994, "Pretrain/Step": 6648, "Pretrain/Step Time": 8.476484278216958} +{"Pretrain/Learning Rate": 1.1085162806750992e-05, "Pretrain/Loss": 2.0016722679138184, "Pretrain/Loss (Raw)": 2.0973401069641113, "Pretrain/Step": 6649, "Pretrain/Step Time": 8.476388985291123} +{"Pretrain/Learning Rate": 1.107810958779531e-05, "Pretrain/Loss": 2.0023112297058105, "Pretrain/Loss (Raw)": 2.1190168857574463, "Pretrain/Step": 6650, "Pretrain/Step Time": 8.474442791193724} +{"Pretrain/Learning Rate": 1.1071057974724782e-05, "Pretrain/Loss": 2.002619981765747, "Pretrain/Loss (Raw)": 2.150268077850342, "Pretrain/Step": 6651, "Pretrain/Step Time": 8.472055561840534} +{"Pretrain/Learning Rate": 1.1064007968352821e-05, "Pretrain/Loss": 2.0026752948760986, "Pretrain/Loss (Raw)": 1.851853370666504, "Pretrain/Step": 6652, "Pretrain/Step Time": 8.473659867420793} +{"Pretrain/Learning Rate": 1.1056959569492648e-05, "Pretrain/Loss": 2.0013608932495117, "Pretrain/Loss (Raw)": 1.8271318674087524, "Pretrain/Step": 6653, "Pretrain/Step Time": 8.475646207109094} +{"Pretrain/Learning Rate": 1.1049912778957284e-05, "Pretrain/Loss": 2.002513885498047, "Pretrain/Loss (Raw)": 1.9292707443237305, "Pretrain/Step": 6654, "Pretrain/Step Time": 8.475750964134932} +{"Pretrain/Learning Rate": 1.1042867597559581e-05, "Pretrain/Loss": 2.0036699771881104, "Pretrain/Loss (Raw)": 2.2232391834259033, "Pretrain/Step": 6655, "Pretrain/Step Time": 8.476822523400187} +{"Pretrain/Learning Rate": 1.1035824026112204e-05, "Pretrain/Loss": 2.0052578449249268, "Pretrain/Loss (Raw)": 2.294830322265625, "Pretrain/Step": 6656, "Pretrain/Step Time": 8.473706195130944} +{"Pretrain/Learning Rate": 1.102878206542761e-05, "Pretrain/Loss": 2.00341796875, "Pretrain/Loss (Raw)": 1.7652469873428345, "Pretrain/Step": 6657, "Pretrain/Step Time": 8.478038301691413} +{"Pretrain/Learning Rate": 1.1021741716318093e-05, "Pretrain/Loss": 2.003538131713867, "Pretrain/Loss (Raw)": 2.0145678520202637, "Pretrain/Step": 6658, "Pretrain/Step Time": 8.47657422348857} +{"Pretrain/Learning Rate": 1.1014702979595759e-05, "Pretrain/Loss": 2.000936508178711, "Pretrain/Loss (Raw)": 1.7890667915344238, "Pretrain/Step": 6659, "Pretrain/Step Time": 8.474879587069154} +{"Pretrain/Learning Rate": 1.100766585607252e-05, "Pretrain/Loss": 2.001209020614624, "Pretrain/Loss (Raw)": 2.1093828678131104, "Pretrain/Step": 6660, "Pretrain/Step Time": 8.474892428144813} +{"Pretrain/Learning Rate": 1.1000630346560117e-05, "Pretrain/Loss": 1.9989720582962036, "Pretrain/Loss (Raw)": 1.8720252513885498, "Pretrain/Step": 6661, "Pretrain/Step Time": 8.473756734281778} +{"Pretrain/Learning Rate": 1.0993596451870075e-05, "Pretrain/Loss": 1.9957891702651978, "Pretrain/Loss (Raw)": 1.5568543672561646, "Pretrain/Step": 6662, "Pretrain/Step Time": 8.475774485617876} +{"Pretrain/Learning Rate": 1.0986564172813768e-05, "Pretrain/Loss": 1.9947038888931274, "Pretrain/Loss (Raw)": 2.0286669731140137, "Pretrain/Step": 6663, "Pretrain/Step Time": 8.475854709744453} +{"Pretrain/Learning Rate": 1.097953351020235e-05, "Pretrain/Loss": 1.9950275421142578, "Pretrain/Loss (Raw)": 2.042051076889038, "Pretrain/Step": 6664, "Pretrain/Step Time": 8.47604849934578} +{"Pretrain/Learning Rate": 1.0972504464846817e-05, "Pretrain/Loss": 1.9948478937149048, "Pretrain/Loss (Raw)": 1.9846547842025757, "Pretrain/Step": 6665, "Pretrain/Step Time": 8.476213628426194} +{"Pretrain/Learning Rate": 1.0965477037557972e-05, "Pretrain/Loss": 1.9946558475494385, "Pretrain/Loss (Raw)": 2.1542932987213135, "Pretrain/Step": 6666, "Pretrain/Step Time": 8.474834233522415} +{"Pretrain/Learning Rate": 1.0958451229146408e-05, "Pretrain/Loss": 1.9934957027435303, "Pretrain/Loss (Raw)": 2.009941577911377, "Pretrain/Step": 6667, "Pretrain/Step Time": 8.47439838014543} +{"Pretrain/Learning Rate": 1.0951427040422562e-05, "Pretrain/Loss": 1.994330883026123, "Pretrain/Loss (Raw)": 2.044529676437378, "Pretrain/Step": 6668, "Pretrain/Step Time": 8.480487680062652} +{"Pretrain/Learning Rate": 1.0944404472196667e-05, "Pretrain/Loss": 1.9947267770767212, "Pretrain/Loss (Raw)": 2.017486333847046, "Pretrain/Step": 6669, "Pretrain/Step Time": 8.476935375481844} +{"Pretrain/Learning Rate": 1.093738352527878e-05, "Pretrain/Loss": 1.9941256046295166, "Pretrain/Loss (Raw)": 2.082156181335449, "Pretrain/Step": 6670, "Pretrain/Step Time": 8.478014953434467} +{"Pretrain/Learning Rate": 1.093036420047876e-05, "Pretrain/Loss": 1.9932918548583984, "Pretrain/Loss (Raw)": 2.0148134231567383, "Pretrain/Step": 6671, "Pretrain/Step Time": 8.476885149255395} +{"Pretrain/Learning Rate": 1.0923346498606297e-05, "Pretrain/Loss": 1.99318265914917, "Pretrain/Loss (Raw)": 2.0055315494537354, "Pretrain/Step": 6672, "Pretrain/Step Time": 8.474716806784272} +{"Pretrain/Learning Rate": 1.0916330420470854e-05, "Pretrain/Loss": 1.9935321807861328, "Pretrain/Loss (Raw)": 2.00791597366333, "Pretrain/Step": 6673, "Pretrain/Step Time": 8.477549366652966} +{"Pretrain/Learning Rate": 1.090931596688175e-05, "Pretrain/Loss": 1.9936491250991821, "Pretrain/Loss (Raw)": 2.1119422912597656, "Pretrain/Step": 6674, "Pretrain/Step Time": 8.472784467041492} +{"Pretrain/Learning Rate": 1.0902303138648098e-05, "Pretrain/Loss": 1.9930601119995117, "Pretrain/Loss (Raw)": 2.0201609134674072, "Pretrain/Step": 6675, "Pretrain/Step Time": 8.476624391973019} +{"Pretrain/Learning Rate": 1.0895291936578825e-05, "Pretrain/Loss": 1.9950003623962402, "Pretrain/Loss (Raw)": 2.204072952270508, "Pretrain/Step": 6676, "Pretrain/Step Time": 8.471091566607356} +{"Pretrain/Learning Rate": 1.088828236148268e-05, "Pretrain/Loss": 1.9958795309066772, "Pretrain/Loss (Raw)": 2.1594913005828857, "Pretrain/Step": 6677, "Pretrain/Step Time": 8.475422754883766} +{"Pretrain/Learning Rate": 1.0881274414168194e-05, "Pretrain/Loss": 1.9952301979064941, "Pretrain/Loss (Raw)": 2.0549685955047607, "Pretrain/Step": 6678, "Pretrain/Step Time": 8.475874396041036} +{"Pretrain/Learning Rate": 1.0874268095443755e-05, "Pretrain/Loss": 1.9947731494903564, "Pretrain/Loss (Raw)": 2.06649112701416, "Pretrain/Step": 6679, "Pretrain/Step Time": 8.473875453695655} +{"Pretrain/Learning Rate": 1.0867263406117515e-05, "Pretrain/Loss": 1.9958844184875488, "Pretrain/Loss (Raw)": 2.0018560886383057, "Pretrain/Step": 6680, "Pretrain/Step Time": 8.479997489601374} +{"Pretrain/Learning Rate": 1.0860260346997474e-05, "Pretrain/Loss": 1.9957232475280762, "Pretrain/Loss (Raw)": 1.9733073711395264, "Pretrain/Step": 6681, "Pretrain/Step Time": 8.480224125087261} +{"Pretrain/Learning Rate": 1.0853258918891446e-05, "Pretrain/Loss": 1.99570894241333, "Pretrain/Loss (Raw)": 1.9344680309295654, "Pretrain/Step": 6682, "Pretrain/Step Time": 8.482877690345049} +{"Pretrain/Learning Rate": 1.0846259122607017e-05, "Pretrain/Loss": 1.997450590133667, "Pretrain/Loss (Raw)": 2.157438039779663, "Pretrain/Step": 6683, "Pretrain/Step Time": 8.476478423923254} +{"Pretrain/Learning Rate": 1.0839260958951628e-05, "Pretrain/Loss": 1.9975204467773438, "Pretrain/Loss (Raw)": 1.9718029499053955, "Pretrain/Step": 6684, "Pretrain/Step Time": 8.478446740657091} +{"Pretrain/Learning Rate": 1.0832264428732509e-05, "Pretrain/Loss": 1.993934154510498, "Pretrain/Loss (Raw)": 1.696496605873108, "Pretrain/Step": 6685, "Pretrain/Step Time": 8.483600793406367} +{"Pretrain/Learning Rate": 1.0825269532756707e-05, "Pretrain/Loss": 1.9916280508041382, "Pretrain/Loss (Raw)": 1.8405358791351318, "Pretrain/Step": 6686, "Pretrain/Step Time": 8.482171127572656} +{"Pretrain/Learning Rate": 1.0818276271831093e-05, "Pretrain/Loss": 1.9933077096939087, "Pretrain/Loss (Raw)": 2.205925226211548, "Pretrain/Step": 6687, "Pretrain/Step Time": 8.479826157912612} +{"Pretrain/Learning Rate": 1.0811284646762321e-05, "Pretrain/Loss": 1.9923667907714844, "Pretrain/Loss (Raw)": 1.9239108562469482, "Pretrain/Step": 6688, "Pretrain/Step Time": 8.480981616303325} +{"Pretrain/Learning Rate": 1.0804294658356876e-05, "Pretrain/Loss": 1.9930353164672852, "Pretrain/Loss (Raw)": 2.026684522628784, "Pretrain/Step": 6689, "Pretrain/Step Time": 8.476625688374043} +{"Pretrain/Learning Rate": 1.0797306307421054e-05, "Pretrain/Loss": 1.9908313751220703, "Pretrain/Loss (Raw)": 1.959136962890625, "Pretrain/Step": 6690, "Pretrain/Step Time": 8.480593079701066} +{"Pretrain/Learning Rate": 1.0790319594760958e-05, "Pretrain/Loss": 1.990941047668457, "Pretrain/Loss (Raw)": 1.9807020425796509, "Pretrain/Step": 6691, "Pretrain/Step Time": 8.480573976412416} +{"Pretrain/Learning Rate": 1.0783334521182507e-05, "Pretrain/Loss": 1.989683985710144, "Pretrain/Loss (Raw)": 1.952946424484253, "Pretrain/Step": 6692, "Pretrain/Step Time": 8.48147727176547} +{"Pretrain/Learning Rate": 1.0776351087491426e-05, "Pretrain/Loss": 1.9913651943206787, "Pretrain/Loss (Raw)": 2.171700954437256, "Pretrain/Step": 6693, "Pretrain/Step Time": 8.481844242662191} +{"Pretrain/Learning Rate": 1.0769369294493245e-05, "Pretrain/Loss": 1.9926811456680298, "Pretrain/Loss (Raw)": 1.995470404624939, "Pretrain/Step": 6694, "Pretrain/Step Time": 8.481922732666135} +{"Pretrain/Learning Rate": 1.0762389142993312e-05, "Pretrain/Loss": 1.9930769205093384, "Pretrain/Loss (Raw)": 2.008533477783203, "Pretrain/Step": 6695, "Pretrain/Step Time": 8.48460461013019} +{"Pretrain/Learning Rate": 1.0755410633796798e-05, "Pretrain/Loss": 1.9939043521881104, "Pretrain/Loss (Raw)": 2.188032388687134, "Pretrain/Step": 6696, "Pretrain/Step Time": 8.487579746171832} +{"Pretrain/Learning Rate": 1.074843376770865e-05, "Pretrain/Loss": 1.9940346479415894, "Pretrain/Loss (Raw)": 2.008443832397461, "Pretrain/Step": 6697, "Pretrain/Step Time": 8.485070768743753} +{"Pretrain/Learning Rate": 1.0741458545533669e-05, "Pretrain/Loss": 1.9928648471832275, "Pretrain/Loss (Raw)": 1.9316082000732422, "Pretrain/Step": 6698, "Pretrain/Step Time": 8.486414209008217} +{"Pretrain/Learning Rate": 1.0734484968076425e-05, "Pretrain/Loss": 1.993891954421997, "Pretrain/Loss (Raw)": 2.060089111328125, "Pretrain/Step": 6699, "Pretrain/Step Time": 8.483556922525167} +{"Pretrain/Learning Rate": 1.0727513036141326e-05, "Pretrain/Loss": 1.993999719619751, "Pretrain/Loss (Raw)": 1.9570645093917847, "Pretrain/Step": 6700, "Pretrain/Step Time": 8.483229776844382} +{"Pretrain/Learning Rate": 1.0720542750532584e-05, "Pretrain/Loss": 1.9938483238220215, "Pretrain/Loss (Raw)": 1.9313615560531616, "Pretrain/Step": 6701, "Pretrain/Step Time": 8.485365342348814} +{"Pretrain/Learning Rate": 1.0713574112054216e-05, "Pretrain/Loss": 1.9942642450332642, "Pretrain/Loss (Raw)": 2.00858473777771, "Pretrain/Step": 6702, "Pretrain/Step Time": 8.486323801800609} +{"Pretrain/Learning Rate": 1.0706607121510065e-05, "Pretrain/Loss": 1.9935258626937866, "Pretrain/Loss (Raw)": 1.8851490020751953, "Pretrain/Step": 6703, "Pretrain/Step Time": 8.487644273787737} +{"Pretrain/Learning Rate": 1.0699641779703747e-05, "Pretrain/Loss": 1.9936776161193848, "Pretrain/Loss (Raw)": 2.0488486289978027, "Pretrain/Step": 6704, "Pretrain/Step Time": 8.487256838008761} +{"Pretrain/Learning Rate": 1.0692678087438728e-05, "Pretrain/Loss": 1.9955716133117676, "Pretrain/Loss (Raw)": 2.2026610374450684, "Pretrain/Step": 6705, "Pretrain/Step Time": 8.485340997576714} +{"Pretrain/Learning Rate": 1.0685716045518262e-05, "Pretrain/Loss": 1.998631238937378, "Pretrain/Loss (Raw)": 2.2488322257995605, "Pretrain/Step": 6706, "Pretrain/Step Time": 8.478322014212608} +{"Pretrain/Learning Rate": 1.0678755654745418e-05, "Pretrain/Loss": 1.9977900981903076, "Pretrain/Loss (Raw)": 1.8879384994506836, "Pretrain/Step": 6707, "Pretrain/Step Time": 8.479286154732108} +{"Pretrain/Learning Rate": 1.0671796915923088e-05, "Pretrain/Loss": 1.9988033771514893, "Pretrain/Loss (Raw)": 2.0965890884399414, "Pretrain/Step": 6708, "Pretrain/Step Time": 8.47901257313788} +{"Pretrain/Learning Rate": 1.066483982985394e-05, "Pretrain/Loss": 1.998551607131958, "Pretrain/Loss (Raw)": 2.0809645652770996, "Pretrain/Step": 6709, "Pretrain/Step Time": 8.476772081106901} +{"Pretrain/Learning Rate": 1.0657884397340475e-05, "Pretrain/Loss": 1.9987685680389404, "Pretrain/Loss (Raw)": 2.0716018676757812, "Pretrain/Step": 6710, "Pretrain/Step Time": 8.478096954524517} +{"Pretrain/Learning Rate": 1.065093061918501e-05, "Pretrain/Loss": 2.0004217624664307, "Pretrain/Loss (Raw)": 1.8432389497756958, "Pretrain/Step": 6711, "Pretrain/Step Time": 8.478457601740956} +{"Pretrain/Learning Rate": 1.0643978496189663e-05, "Pretrain/Loss": 2.001922607421875, "Pretrain/Loss (Raw)": 2.1755309104919434, "Pretrain/Step": 6712, "Pretrain/Step Time": 8.476629069074988} +{"Pretrain/Learning Rate": 1.063702802915634e-05, "Pretrain/Loss": 2.0032827854156494, "Pretrain/Loss (Raw)": 2.0590033531188965, "Pretrain/Step": 6713, "Pretrain/Step Time": 8.477297857403755} +{"Pretrain/Learning Rate": 1.06300792188868e-05, "Pretrain/Loss": 2.004903793334961, "Pretrain/Loss (Raw)": 2.06970477104187, "Pretrain/Step": 6714, "Pretrain/Step Time": 8.47726090811193} +{"Pretrain/Learning Rate": 1.062313206618256e-05, "Pretrain/Loss": 2.006551742553711, "Pretrain/Loss (Raw)": 2.146012783050537, "Pretrain/Step": 6715, "Pretrain/Step Time": 8.47821431979537} +{"Pretrain/Learning Rate": 1.0616186571844982e-05, "Pretrain/Loss": 2.0066921710968018, "Pretrain/Loss (Raw)": 1.9649786949157715, "Pretrain/Step": 6716, "Pretrain/Step Time": 8.476498443633318} +{"Pretrain/Learning Rate": 1.0609242736675232e-05, "Pretrain/Loss": 2.0065042972564697, "Pretrain/Loss (Raw)": 2.01145339012146, "Pretrain/Step": 6717, "Pretrain/Step Time": 8.475323045626283} +{"Pretrain/Learning Rate": 1.0602300561474271e-05, "Pretrain/Loss": 2.0060620307922363, "Pretrain/Loss (Raw)": 1.9011313915252686, "Pretrain/Step": 6718, "Pretrain/Step Time": 8.476561518386006} +{"Pretrain/Learning Rate": 1.0595360047042893e-05, "Pretrain/Loss": 2.0059335231781006, "Pretrain/Loss (Raw)": 2.0878851413726807, "Pretrain/Step": 6719, "Pretrain/Step Time": 8.475813975557685} +{"Pretrain/Learning Rate": 1.058842119418166e-05, "Pretrain/Loss": 2.0054051876068115, "Pretrain/Loss (Raw)": 1.9354321956634521, "Pretrain/Step": 6720, "Pretrain/Step Time": 8.474366001784801} +{"Pretrain/Learning Rate": 1.0581484003690981e-05, "Pretrain/Loss": 2.0046658515930176, "Pretrain/Loss (Raw)": 1.9371875524520874, "Pretrain/Step": 6721, "Pretrain/Step Time": 8.471674729138613} +{"Pretrain/Learning Rate": 1.0574548476371051e-05, "Pretrain/Loss": 2.007702112197876, "Pretrain/Loss (Raw)": 2.131791114807129, "Pretrain/Step": 6722, "Pretrain/Step Time": 8.473696947097778} +{"Pretrain/Learning Rate": 1.0567614613021886e-05, "Pretrain/Loss": 2.0097129344940186, "Pretrain/Loss (Raw)": 2.0538647174835205, "Pretrain/Step": 6723, "Pretrain/Step Time": 8.475372824817896} +{"Pretrain/Learning Rate": 1.0560682414443315e-05, "Pretrain/Loss": 2.0105326175689697, "Pretrain/Loss (Raw)": 2.1188864707946777, "Pretrain/Step": 6724, "Pretrain/Step Time": 8.473546801134944} +{"Pretrain/Learning Rate": 1.0553751881434943e-05, "Pretrain/Loss": 2.0138118267059326, "Pretrain/Loss (Raw)": 2.191199541091919, "Pretrain/Step": 6725, "Pretrain/Step Time": 8.472350556403399} +{"Pretrain/Learning Rate": 1.0546823014796214e-05, "Pretrain/Loss": 2.012835741043091, "Pretrain/Loss (Raw)": 1.9969996213912964, "Pretrain/Step": 6726, "Pretrain/Step Time": 8.473929887637496} +{"Pretrain/Learning Rate": 1.053989581532637e-05, "Pretrain/Loss": 2.012392520904541, "Pretrain/Loss (Raw)": 1.7884544134140015, "Pretrain/Step": 6727, "Pretrain/Step Time": 8.47574357315898} +{"Pretrain/Learning Rate": 1.0532970283824473e-05, "Pretrain/Loss": 2.0132482051849365, "Pretrain/Loss (Raw)": 2.100273847579956, "Pretrain/Step": 6728, "Pretrain/Step Time": 8.471613207831979} +{"Pretrain/Learning Rate": 1.0526046421089358e-05, "Pretrain/Loss": 2.013583183288574, "Pretrain/Loss (Raw)": 2.057778835296631, "Pretrain/Step": 6729, "Pretrain/Step Time": 8.47417962178588} +{"Pretrain/Learning Rate": 1.0519124227919705e-05, "Pretrain/Loss": 2.012636184692383, "Pretrain/Loss (Raw)": 1.85410475730896, "Pretrain/Step": 6730, "Pretrain/Step Time": 8.472872450947762} +{"Pretrain/Learning Rate": 1.051220370511399e-05, "Pretrain/Loss": 2.012326955795288, "Pretrain/Loss (Raw)": 1.9305157661437988, "Pretrain/Step": 6731, "Pretrain/Step Time": 8.47595415636897} +{"Pretrain/Learning Rate": 1.050528485347048e-05, "Pretrain/Loss": 2.0125274658203125, "Pretrain/Loss (Raw)": 1.9852409362792969, "Pretrain/Step": 6732, "Pretrain/Step Time": 8.477762307971716} +{"Pretrain/Learning Rate": 1.0498367673787265e-05, "Pretrain/Loss": 2.011653423309326, "Pretrain/Loss (Raw)": 1.861172080039978, "Pretrain/Step": 6733, "Pretrain/Step Time": 8.477665662765503} +{"Pretrain/Learning Rate": 1.0491452166862245e-05, "Pretrain/Loss": 2.012385606765747, "Pretrain/Loss (Raw)": 2.078080654144287, "Pretrain/Step": 6734, "Pretrain/Step Time": 8.477520925924182} +{"Pretrain/Learning Rate": 1.0484538333493128e-05, "Pretrain/Loss": 2.014085531234741, "Pretrain/Loss (Raw)": 2.1209030151367188, "Pretrain/Step": 6735, "Pretrain/Step Time": 8.47937954775989} +{"Pretrain/Learning Rate": 1.0477626174477404e-05, "Pretrain/Loss": 2.0119099617004395, "Pretrain/Loss (Raw)": 1.9678417444229126, "Pretrain/Step": 6736, "Pretrain/Step Time": 8.478058002889156} +{"Pretrain/Learning Rate": 1.0470715690612395e-05, "Pretrain/Loss": 2.0142641067504883, "Pretrain/Loss (Raw)": 2.086986541748047, "Pretrain/Step": 6737, "Pretrain/Step Time": 8.476280251517892} +{"Pretrain/Learning Rate": 1.046380688269523e-05, "Pretrain/Loss": 2.013701915740967, "Pretrain/Loss (Raw)": 1.8302807807922363, "Pretrain/Step": 6738, "Pretrain/Step Time": 8.478914910927415} +{"Pretrain/Learning Rate": 1.0456899751522827e-05, "Pretrain/Loss": 2.0134658813476562, "Pretrain/Loss (Raw)": 2.026366710662842, "Pretrain/Step": 6739, "Pretrain/Step Time": 8.475171217694879} +{"Pretrain/Learning Rate": 1.0449994297891938e-05, "Pretrain/Loss": 2.0148749351501465, "Pretrain/Loss (Raw)": 1.9213886260986328, "Pretrain/Step": 6740, "Pretrain/Step Time": 8.475282607600093} +{"Pretrain/Learning Rate": 1.0443090522599085e-05, "Pretrain/Loss": 2.014016628265381, "Pretrain/Loss (Raw)": 1.909603238105774, "Pretrain/Step": 6741, "Pretrain/Step Time": 8.475694539025426} +{"Pretrain/Learning Rate": 1.0436188426440623e-05, "Pretrain/Loss": 2.0146918296813965, "Pretrain/Loss (Raw)": 2.1512043476104736, "Pretrain/Step": 6742, "Pretrain/Step Time": 8.476255841553211} +{"Pretrain/Learning Rate": 1.0429288010212713e-05, "Pretrain/Loss": 2.0162289142608643, "Pretrain/Loss (Raw)": 2.145496368408203, "Pretrain/Step": 6743, "Pretrain/Step Time": 8.476252529770136} +{"Pretrain/Learning Rate": 1.0422389274711306e-05, "Pretrain/Loss": 2.015449285507202, "Pretrain/Loss (Raw)": 2.0430054664611816, "Pretrain/Step": 6744, "Pretrain/Step Time": 8.474210053682327} +{"Pretrain/Learning Rate": 1.0415492220732182e-05, "Pretrain/Loss": 2.01780366897583, "Pretrain/Loss (Raw)": 2.004587173461914, "Pretrain/Step": 6745, "Pretrain/Step Time": 8.476274982094765} +{"Pretrain/Learning Rate": 1.0408596849070898e-05, "Pretrain/Loss": 2.018734931945801, "Pretrain/Loss (Raw)": 1.9483082294464111, "Pretrain/Step": 6746, "Pretrain/Step Time": 8.47740031965077} +{"Pretrain/Learning Rate": 1.0401703160522846e-05, "Pretrain/Loss": 2.0184314250946045, "Pretrain/Loss (Raw)": 2.062007427215576, "Pretrain/Step": 6747, "Pretrain/Step Time": 8.476791745051742} +{"Pretrain/Learning Rate": 1.0394811155883196e-05, "Pretrain/Loss": 2.0182831287384033, "Pretrain/Loss (Raw)": 1.9570744037628174, "Pretrain/Step": 6748, "Pretrain/Step Time": 8.478579910472035} +{"Pretrain/Learning Rate": 1.0387920835946949e-05, "Pretrain/Loss": 2.0189363956451416, "Pretrain/Loss (Raw)": 2.1102983951568604, "Pretrain/Step": 6749, "Pretrain/Step Time": 8.474025262519717} +{"Pretrain/Learning Rate": 1.0381032201508906e-05, "Pretrain/Loss": 2.01912260055542, "Pretrain/Loss (Raw)": 2.065643787384033, "Pretrain/Step": 6750, "Pretrain/Step Time": 8.474089704453945} +{"Pretrain/Learning Rate": 1.037414525336365e-05, "Pretrain/Loss": 2.0174765586853027, "Pretrain/Loss (Raw)": 2.003962516784668, "Pretrain/Step": 6751, "Pretrain/Step Time": 8.475597694516182} +{"Pretrain/Learning Rate": 1.0367259992305602e-05, "Pretrain/Loss": 2.0168955326080322, "Pretrain/Loss (Raw)": 2.0412585735321045, "Pretrain/Step": 6752, "Pretrain/Step Time": 8.475674172863364} +{"Pretrain/Learning Rate": 1.0360376419128973e-05, "Pretrain/Loss": 2.0175490379333496, "Pretrain/Loss (Raw)": 2.0663204193115234, "Pretrain/Step": 6753, "Pretrain/Step Time": 8.474916892126203} +{"Pretrain/Learning Rate": 1.0353494534627776e-05, "Pretrain/Loss": 2.017723560333252, "Pretrain/Loss (Raw)": 2.0105032920837402, "Pretrain/Step": 6754, "Pretrain/Step Time": 8.476373096928} +{"Pretrain/Learning Rate": 1.034661433959584e-05, "Pretrain/Loss": 2.017756938934326, "Pretrain/Loss (Raw)": 1.9081913232803345, "Pretrain/Step": 6755, "Pretrain/Step Time": 8.474047182127833} +{"Pretrain/Learning Rate": 1.0339735834826797e-05, "Pretrain/Loss": 2.015876293182373, "Pretrain/Loss (Raw)": 1.9022237062454224, "Pretrain/Step": 6756, "Pretrain/Step Time": 8.473248962312937} +{"Pretrain/Learning Rate": 1.0332859021114063e-05, "Pretrain/Loss": 2.0149779319763184, "Pretrain/Loss (Raw)": 1.964315414428711, "Pretrain/Step": 6757, "Pretrain/Step Time": 8.47200582921505} +{"Pretrain/Learning Rate": 1.0325983899250891e-05, "Pretrain/Loss": 2.0143027305603027, "Pretrain/Loss (Raw)": 1.990749478340149, "Pretrain/Step": 6758, "Pretrain/Step Time": 8.472022894769907} +{"Pretrain/Learning Rate": 1.0319110470030315e-05, "Pretrain/Loss": 2.0123205184936523, "Pretrain/Loss (Raw)": 1.7886320352554321, "Pretrain/Step": 6759, "Pretrain/Step Time": 8.474441649392247} +{"Pretrain/Learning Rate": 1.0312238734245191e-05, "Pretrain/Loss": 2.0132927894592285, "Pretrain/Loss (Raw)": 1.9614354372024536, "Pretrain/Step": 6760, "Pretrain/Step Time": 8.470302078872919} +{"Pretrain/Learning Rate": 1.0305368692688174e-05, "Pretrain/Loss": 2.012939691543579, "Pretrain/Loss (Raw)": 2.042789936065674, "Pretrain/Step": 6761, "Pretrain/Step Time": 8.471477901563048} +{"Pretrain/Learning Rate": 1.0298500346151708e-05, "Pretrain/Loss": 2.0106232166290283, "Pretrain/Loss (Raw)": 1.9420537948608398, "Pretrain/Step": 6762, "Pretrain/Step Time": 8.47132852487266} +{"Pretrain/Learning Rate": 1.0291633695428065e-05, "Pretrain/Loss": 2.0130083560943604, "Pretrain/Loss (Raw)": 2.0949041843414307, "Pretrain/Step": 6763, "Pretrain/Step Time": 8.469656012952328} +{"Pretrain/Learning Rate": 1.0284768741309301e-05, "Pretrain/Loss": 2.011427879333496, "Pretrain/Loss (Raw)": 1.8659957647323608, "Pretrain/Step": 6764, "Pretrain/Step Time": 8.468224823474884} +{"Pretrain/Learning Rate": 1.0277905484587289e-05, "Pretrain/Loss": 2.0103156566619873, "Pretrain/Loss (Raw)": 1.8787686824798584, "Pretrain/Step": 6765, "Pretrain/Step Time": 8.468995971605182} +{"Pretrain/Learning Rate": 1.0271043926053716e-05, "Pretrain/Loss": 2.0104727745056152, "Pretrain/Loss (Raw)": 2.1276564598083496, "Pretrain/Step": 6766, "Pretrain/Step Time": 8.467765733599663} +{"Pretrain/Learning Rate": 1.026418406650004e-05, "Pretrain/Loss": 2.008535146713257, "Pretrain/Loss (Raw)": 1.8668749332427979, "Pretrain/Step": 6767, "Pretrain/Step Time": 8.466755514964461} +{"Pretrain/Learning Rate": 1.0257325906717554e-05, "Pretrain/Loss": 2.0090672969818115, "Pretrain/Loss (Raw)": 2.169445753097534, "Pretrain/Step": 6768, "Pretrain/Step Time": 8.468705505132675} +{"Pretrain/Learning Rate": 1.0250469447497347e-05, "Pretrain/Loss": 2.007298231124878, "Pretrain/Loss (Raw)": 2.0212693214416504, "Pretrain/Step": 6769, "Pretrain/Step Time": 8.469189271330833} +{"Pretrain/Learning Rate": 1.0243614689630302e-05, "Pretrain/Loss": 2.006239414215088, "Pretrain/Loss (Raw)": 1.7595851421356201, "Pretrain/Step": 6770, "Pretrain/Step Time": 8.46459635719657} +{"Pretrain/Learning Rate": 1.0236761633907125e-05, "Pretrain/Loss": 2.00480318069458, "Pretrain/Loss (Raw)": 1.8796921968460083, "Pretrain/Step": 6771, "Pretrain/Step Time": 8.464622223749757} +{"Pretrain/Learning Rate": 1.02299102811183e-05, "Pretrain/Loss": 2.0063529014587402, "Pretrain/Loss (Raw)": 2.1276533603668213, "Pretrain/Step": 6772, "Pretrain/Step Time": 8.46086953021586} +{"Pretrain/Learning Rate": 1.022306063205413e-05, "Pretrain/Loss": 2.005425214767456, "Pretrain/Loss (Raw)": 1.7835379838943481, "Pretrain/Step": 6773, "Pretrain/Step Time": 8.461943803355098} +{"Pretrain/Learning Rate": 1.0216212687504725e-05, "Pretrain/Loss": 2.0037336349487305, "Pretrain/Loss (Raw)": 1.8776761293411255, "Pretrain/Step": 6774, "Pretrain/Step Time": 8.462172077968717} +{"Pretrain/Learning Rate": 1.0209366448259991e-05, "Pretrain/Loss": 2.0043351650238037, "Pretrain/Loss (Raw)": 2.065119743347168, "Pretrain/Step": 6775, "Pretrain/Step Time": 8.463380299508572} +{"Pretrain/Learning Rate": 1.020252191510964e-05, "Pretrain/Loss": 2.00691819190979, "Pretrain/Loss (Raw)": 2.096048355102539, "Pretrain/Step": 6776, "Pretrain/Step Time": 8.464729119092226} +{"Pretrain/Learning Rate": 1.019567908884319e-05, "Pretrain/Loss": 2.0071048736572266, "Pretrain/Loss (Raw)": 2.1212291717529297, "Pretrain/Step": 6777, "Pretrain/Step Time": 8.464785616844893} +{"Pretrain/Learning Rate": 1.018883797024995e-05, "Pretrain/Loss": 2.0054104328155518, "Pretrain/Loss (Raw)": 1.9021283388137817, "Pretrain/Step": 6778, "Pretrain/Step Time": 8.464184885844588} +{"Pretrain/Learning Rate": 1.0181998560119047e-05, "Pretrain/Loss": 2.0034122467041016, "Pretrain/Loss (Raw)": 1.8945149183273315, "Pretrain/Step": 6779, "Pretrain/Step Time": 8.464506028220057} +{"Pretrain/Learning Rate": 1.0175160859239408e-05, "Pretrain/Loss": 2.0047640800476074, "Pretrain/Loss (Raw)": 2.02485728263855, "Pretrain/Step": 6780, "Pretrain/Step Time": 8.464195415377617} +{"Pretrain/Learning Rate": 1.0168324868399748e-05, "Pretrain/Loss": 2.007197380065918, "Pretrain/Loss (Raw)": 2.138634204864502, "Pretrain/Step": 6781, "Pretrain/Step Time": 8.465390235185623} +{"Pretrain/Learning Rate": 1.0161490588388608e-05, "Pretrain/Loss": 2.0087318420410156, "Pretrain/Loss (Raw)": 2.1256494522094727, "Pretrain/Step": 6782, "Pretrain/Step Time": 8.46372769959271} +{"Pretrain/Learning Rate": 1.0154658019994307e-05, "Pretrain/Loss": 2.006077527999878, "Pretrain/Loss (Raw)": 1.8835033178329468, "Pretrain/Step": 6783, "Pretrain/Step Time": 8.463432420045137} +{"Pretrain/Learning Rate": 1.0147827164004986e-05, "Pretrain/Loss": 2.0037589073181152, "Pretrain/Loss (Raw)": 1.9980413913726807, "Pretrain/Step": 6784, "Pretrain/Step Time": 8.465719852596521} +{"Pretrain/Learning Rate": 1.0140998021208581e-05, "Pretrain/Loss": 2.006085157394409, "Pretrain/Loss (Raw)": 2.0630104541778564, "Pretrain/Step": 6785, "Pretrain/Step Time": 8.464724881574512} +{"Pretrain/Learning Rate": 1.0134170592392836e-05, "Pretrain/Loss": 2.006523370742798, "Pretrain/Loss (Raw)": 2.0706534385681152, "Pretrain/Step": 6786, "Pretrain/Step Time": 8.46530269831419} +{"Pretrain/Learning Rate": 1.0127344878345293e-05, "Pretrain/Loss": 2.009045124053955, "Pretrain/Loss (Raw)": 2.1118462085723877, "Pretrain/Step": 6787, "Pretrain/Step Time": 8.461435936391354} +{"Pretrain/Learning Rate": 1.0120520879853287e-05, "Pretrain/Loss": 2.008254289627075, "Pretrain/Loss (Raw)": 2.008165121078491, "Pretrain/Step": 6788, "Pretrain/Step Time": 8.46159409917891} +{"Pretrain/Learning Rate": 1.0113698597703967e-05, "Pretrain/Loss": 2.0095417499542236, "Pretrain/Loss (Raw)": 2.0368309020996094, "Pretrain/Step": 6789, "Pretrain/Step Time": 8.467217460274696} +{"Pretrain/Learning Rate": 1.010687803268428e-05, "Pretrain/Loss": 2.0135416984558105, "Pretrain/Loss (Raw)": 2.068843364715576, "Pretrain/Step": 6790, "Pretrain/Step Time": 8.465191116556525} +{"Pretrain/Learning Rate": 1.0100059185580981e-05, "Pretrain/Loss": 2.01330304145813, "Pretrain/Loss (Raw)": 1.9981253147125244, "Pretrain/Step": 6791, "Pretrain/Step Time": 8.467862280085683} +{"Pretrain/Learning Rate": 1.009324205718062e-05, "Pretrain/Loss": 2.012917995452881, "Pretrain/Loss (Raw)": 1.9927617311477661, "Pretrain/Step": 6792, "Pretrain/Step Time": 8.467023124918342} +{"Pretrain/Learning Rate": 1.0086426648269553e-05, "Pretrain/Loss": 2.012904644012451, "Pretrain/Loss (Raw)": 1.982918620109558, "Pretrain/Step": 6793, "Pretrain/Step Time": 8.46810831129551} +{"Pretrain/Learning Rate": 1.0079612959633928e-05, "Pretrain/Loss": 2.01358699798584, "Pretrain/Loss (Raw)": 2.241631507873535, "Pretrain/Step": 6794, "Pretrain/Step Time": 8.469623323529959} +{"Pretrain/Learning Rate": 1.00728009920597e-05, "Pretrain/Loss": 2.0140647888183594, "Pretrain/Loss (Raw)": 2.071139335632324, "Pretrain/Step": 6795, "Pretrain/Step Time": 8.469675149768591} +{"Pretrain/Learning Rate": 1.0065990746332643e-05, "Pretrain/Loss": 2.012075901031494, "Pretrain/Loss (Raw)": 1.7899377346038818, "Pretrain/Step": 6796, "Pretrain/Step Time": 8.46508857794106} +{"Pretrain/Learning Rate": 1.0059182223238296e-05, "Pretrain/Loss": 2.0104637145996094, "Pretrain/Loss (Raw)": 1.8111540079116821, "Pretrain/Step": 6797, "Pretrain/Step Time": 8.467233156785369} +{"Pretrain/Learning Rate": 1.0052375423562038e-05, "Pretrain/Loss": 2.008394718170166, "Pretrain/Loss (Raw)": 1.8172881603240967, "Pretrain/Step": 6798, "Pretrain/Step Time": 8.466106411069632} +{"Pretrain/Learning Rate": 1.0045570348089012e-05, "Pretrain/Loss": 2.0071935653686523, "Pretrain/Loss (Raw)": 1.8610674142837524, "Pretrain/Step": 6799, "Pretrain/Step Time": 8.468195414170623} +{"Pretrain/Learning Rate": 1.003876699760419e-05, "Pretrain/Loss": 2.0080456733703613, "Pretrain/Loss (Raw)": 2.114583969116211, "Pretrain/Step": 6800, "Pretrain/Step Time": 8.468023847788572} +{"Pretrain/Learning Rate": 1.003196537289234e-05, "Pretrain/Loss": 2.00748610496521, "Pretrain/Loss (Raw)": 1.936327576637268, "Pretrain/Step": 6801, "Pretrain/Step Time": 8.464886851608753} +{"Pretrain/Learning Rate": 1.0025165474738024e-05, "Pretrain/Loss": 2.006664991378784, "Pretrain/Loss (Raw)": 2.0068111419677734, "Pretrain/Step": 6802, "Pretrain/Step Time": 8.466214610263705} +{"Pretrain/Learning Rate": 1.0018367303925617e-05, "Pretrain/Loss": 2.0088376998901367, "Pretrain/Loss (Raw)": 2.2982590198516846, "Pretrain/Step": 6803, "Pretrain/Step Time": 8.464477144181728} +{"Pretrain/Learning Rate": 1.0011570861239264e-05, "Pretrain/Loss": 2.0070652961730957, "Pretrain/Loss (Raw)": 1.9772247076034546, "Pretrain/Step": 6804, "Pretrain/Step Time": 8.470830831676722} +{"Pretrain/Learning Rate": 1.0004776147462946e-05, "Pretrain/Loss": 2.007213830947876, "Pretrain/Loss (Raw)": 2.178504705429077, "Pretrain/Step": 6805, "Pretrain/Step Time": 8.468280643224716} +{"Pretrain/Learning Rate": 9.997983163380435e-06, "Pretrain/Loss": 2.0060858726501465, "Pretrain/Loss (Raw)": 1.910582184791565, "Pretrain/Step": 6806, "Pretrain/Step Time": 8.466257717460394} +{"Pretrain/Learning Rate": 9.991191909775289e-06, "Pretrain/Loss": 2.005143880844116, "Pretrain/Loss (Raw)": 1.945940613746643, "Pretrain/Step": 6807, "Pretrain/Step Time": 8.475462764501572} +{"Pretrain/Learning Rate": 9.98440238743089e-06, "Pretrain/Loss": 2.004887580871582, "Pretrain/Loss (Raw)": 1.9690433740615845, "Pretrain/Step": 6808, "Pretrain/Step Time": 8.469533834606409} +{"Pretrain/Learning Rate": 9.977614597130392e-06, "Pretrain/Loss": 2.00441837310791, "Pretrain/Loss (Raw)": 1.9132503271102905, "Pretrain/Step": 6809, "Pretrain/Step Time": 8.471125070005655} +{"Pretrain/Learning Rate": 9.97082853965677e-06, "Pretrain/Loss": 2.005096435546875, "Pretrain/Loss (Raw)": 2.0212395191192627, "Pretrain/Step": 6810, "Pretrain/Step Time": 8.468686990439892} +{"Pretrain/Learning Rate": 9.964044215792796e-06, "Pretrain/Loss": 2.00437331199646, "Pretrain/Loss (Raw)": 2.0648934841156006, "Pretrain/Step": 6811, "Pretrain/Step Time": 8.47378784045577} +{"Pretrain/Learning Rate": 9.957261626321046e-06, "Pretrain/Loss": 2.002699851989746, "Pretrain/Loss (Raw)": 1.757603406906128, "Pretrain/Step": 6812, "Pretrain/Step Time": 8.471778390929103} +{"Pretrain/Learning Rate": 9.950480772023871e-06, "Pretrain/Loss": 2.0031285285949707, "Pretrain/Loss (Raw)": 1.7513474225997925, "Pretrain/Step": 6813, "Pretrain/Step Time": 8.47073571011424} +{"Pretrain/Learning Rate": 9.943701653683449e-06, "Pretrain/Loss": 2.0054328441619873, "Pretrain/Loss (Raw)": 2.135505437850952, "Pretrain/Step": 6814, "Pretrain/Step Time": 8.47007699124515} +{"Pretrain/Learning Rate": 9.936924272081764e-06, "Pretrain/Loss": 2.003904342651367, "Pretrain/Loss (Raw)": 2.010291337966919, "Pretrain/Step": 6815, "Pretrain/Step Time": 8.469749942421913} +{"Pretrain/Learning Rate": 9.930148628000557e-06, "Pretrain/Loss": 2.004640579223633, "Pretrain/Loss (Raw)": 2.018127679824829, "Pretrain/Step": 6816, "Pretrain/Step Time": 8.471570154652} +{"Pretrain/Learning Rate": 9.92337472222141e-06, "Pretrain/Loss": 2.0040817260742188, "Pretrain/Loss (Raw)": 1.9551448822021484, "Pretrain/Step": 6817, "Pretrain/Step Time": 8.472129411995411} +{"Pretrain/Learning Rate": 9.916602555525692e-06, "Pretrain/Loss": 2.004300594329834, "Pretrain/Loss (Raw)": 1.9871490001678467, "Pretrain/Step": 6818, "Pretrain/Step Time": 8.467932118102908} +{"Pretrain/Learning Rate": 9.909832128694576e-06, "Pretrain/Loss": 2.0048093795776367, "Pretrain/Loss (Raw)": 2.0458364486694336, "Pretrain/Step": 6819, "Pretrain/Step Time": 8.474102357402444} +{"Pretrain/Learning Rate": 9.903063442509015e-06, "Pretrain/Loss": 2.0058441162109375, "Pretrain/Loss (Raw)": 2.0853850841522217, "Pretrain/Step": 6820, "Pretrain/Step Time": 8.469972375780344} +{"Pretrain/Learning Rate": 9.89629649774978e-06, "Pretrain/Loss": 2.0045742988586426, "Pretrain/Loss (Raw)": 2.0091822147369385, "Pretrain/Step": 6821, "Pretrain/Step Time": 8.4673644118011} +{"Pretrain/Learning Rate": 9.889531295197432e-06, "Pretrain/Loss": 2.004807949066162, "Pretrain/Loss (Raw)": 2.025360584259033, "Pretrain/Step": 6822, "Pretrain/Step Time": 8.469821771606803} +{"Pretrain/Learning Rate": 9.882767835632342e-06, "Pretrain/Loss": 2.004612445831299, "Pretrain/Loss (Raw)": 1.9835104942321777, "Pretrain/Step": 6823, "Pretrain/Step Time": 8.46817321330309} +{"Pretrain/Learning Rate": 9.87600611983468e-06, "Pretrain/Loss": 2.003016948699951, "Pretrain/Loss (Raw)": 1.9838348627090454, "Pretrain/Step": 6824, "Pretrain/Step Time": 8.467035941779613} +{"Pretrain/Learning Rate": 9.869246148584385e-06, "Pretrain/Loss": 2.0024795532226562, "Pretrain/Loss (Raw)": 1.939652442932129, "Pretrain/Step": 6825, "Pretrain/Step Time": 8.467159958556294} +{"Pretrain/Learning Rate": 9.862487922661231e-06, "Pretrain/Loss": 2.003485918045044, "Pretrain/Loss (Raw)": 2.0604093074798584, "Pretrain/Step": 6826, "Pretrain/Step Time": 8.468859089538455} +{"Pretrain/Learning Rate": 9.855731442844775e-06, "Pretrain/Loss": 2.003365993499756, "Pretrain/Loss (Raw)": 2.0447418689727783, "Pretrain/Step": 6827, "Pretrain/Step Time": 8.470800751820207} +{"Pretrain/Learning Rate": 9.848976709914376e-06, "Pretrain/Loss": 2.005218029022217, "Pretrain/Loss (Raw)": 2.1941263675689697, "Pretrain/Step": 6828, "Pretrain/Step Time": 8.467983840033412} +{"Pretrain/Learning Rate": 9.842223724649199e-06, "Pretrain/Loss": 2.006777763366699, "Pretrain/Loss (Raw)": 2.1310107707977295, "Pretrain/Step": 6829, "Pretrain/Step Time": 8.469840126112103} +{"Pretrain/Learning Rate": 9.835472487828176e-06, "Pretrain/Loss": 2.0067105293273926, "Pretrain/Loss (Raw)": 1.9999736547470093, "Pretrain/Step": 6830, "Pretrain/Step Time": 8.469606429338455} +{"Pretrain/Learning Rate": 9.828723000230084e-06, "Pretrain/Loss": 2.0072214603424072, "Pretrain/Loss (Raw)": 1.9505460262298584, "Pretrain/Step": 6831, "Pretrain/Step Time": 8.467889551073313} +{"Pretrain/Learning Rate": 9.821975262633453e-06, "Pretrain/Loss": 2.0077199935913086, "Pretrain/Loss (Raw)": 2.1126625537872314, "Pretrain/Step": 6832, "Pretrain/Step Time": 8.467613888904452} +{"Pretrain/Learning Rate": 9.815229275816643e-06, "Pretrain/Loss": 2.0070548057556152, "Pretrain/Loss (Raw)": 2.117515802383423, "Pretrain/Step": 6833, "Pretrain/Step Time": 8.470030834898353} +{"Pretrain/Learning Rate": 9.808485040557796e-06, "Pretrain/Loss": 2.0045762062072754, "Pretrain/Loss (Raw)": 1.931540846824646, "Pretrain/Step": 6834, "Pretrain/Step Time": 8.47010923922062} +{"Pretrain/Learning Rate": 9.801742557634872e-06, "Pretrain/Loss": 2.0041611194610596, "Pretrain/Loss (Raw)": 1.834842324256897, "Pretrain/Step": 6835, "Pretrain/Step Time": 8.467583924531937} +{"Pretrain/Learning Rate": 9.795001827825596e-06, "Pretrain/Loss": 2.0034828186035156, "Pretrain/Loss (Raw)": 2.009766101837158, "Pretrain/Step": 6836, "Pretrain/Step Time": 8.467845419421792} +{"Pretrain/Learning Rate": 9.788262851907512e-06, "Pretrain/Loss": 2.003704071044922, "Pretrain/Loss (Raw)": 2.1092703342437744, "Pretrain/Step": 6837, "Pretrain/Step Time": 8.471330581232905} +{"Pretrain/Learning Rate": 9.781525630657964e-06, "Pretrain/Loss": 2.002521514892578, "Pretrain/Loss (Raw)": 1.920241355895996, "Pretrain/Step": 6838, "Pretrain/Step Time": 8.471315111964941} +{"Pretrain/Learning Rate": 9.774790164854087e-06, "Pretrain/Loss": 2.004274845123291, "Pretrain/Loss (Raw)": 2.0676655769348145, "Pretrain/Step": 6839, "Pretrain/Step Time": 8.468455489724874} +{"Pretrain/Learning Rate": 9.76805645527282e-06, "Pretrain/Loss": 2.0029332637786865, "Pretrain/Loss (Raw)": 2.003824234008789, "Pretrain/Step": 6840, "Pretrain/Step Time": 8.473726132884622} +{"Pretrain/Learning Rate": 9.76132450269088e-06, "Pretrain/Loss": 1.9999796152114868, "Pretrain/Loss (Raw)": 1.6809196472167969, "Pretrain/Step": 6841, "Pretrain/Step Time": 8.472273230552673} +{"Pretrain/Learning Rate": 9.754594307884808e-06, "Pretrain/Loss": 1.9992892742156982, "Pretrain/Loss (Raw)": 1.9813241958618164, "Pretrain/Step": 6842, "Pretrain/Step Time": 8.473042618483305} +{"Pretrain/Learning Rate": 9.747865871630917e-06, "Pretrain/Loss": 1.9983861446380615, "Pretrain/Loss (Raw)": 2.0304362773895264, "Pretrain/Step": 6843, "Pretrain/Step Time": 8.476058388128877} +{"Pretrain/Learning Rate": 9.741139194705345e-06, "Pretrain/Loss": 1.9983868598937988, "Pretrain/Loss (Raw)": 1.9650641679763794, "Pretrain/Step": 6844, "Pretrain/Step Time": 8.484200498089194} +{"Pretrain/Learning Rate": 9.73441427788401e-06, "Pretrain/Loss": 1.9983799457550049, "Pretrain/Loss (Raw)": 2.010561466217041, "Pretrain/Step": 6845, "Pretrain/Step Time": 8.484038315713406} +{"Pretrain/Learning Rate": 9.727691121942614e-06, "Pretrain/Loss": 1.998536467552185, "Pretrain/Loss (Raw)": 1.9211820363998413, "Pretrain/Step": 6846, "Pretrain/Step Time": 8.482534732669592} +{"Pretrain/Learning Rate": 9.72096972765669e-06, "Pretrain/Loss": 1.9967291355133057, "Pretrain/Loss (Raw)": 1.856548547744751, "Pretrain/Step": 6847, "Pretrain/Step Time": 8.483241783455014} +{"Pretrain/Learning Rate": 9.71425009580153e-06, "Pretrain/Loss": 1.9964382648468018, "Pretrain/Loss (Raw)": 1.8981764316558838, "Pretrain/Step": 6848, "Pretrain/Step Time": 8.484015680849552} +{"Pretrain/Learning Rate": 9.70753222715225e-06, "Pretrain/Loss": 1.997659683227539, "Pretrain/Loss (Raw)": 2.093541383743286, "Pretrain/Step": 6849, "Pretrain/Step Time": 8.4853850081563} +{"Pretrain/Learning Rate": 9.70081612248376e-06, "Pretrain/Loss": 1.9975943565368652, "Pretrain/Loss (Raw)": 2.123415231704712, "Pretrain/Step": 6850, "Pretrain/Step Time": 8.480137163773179} +{"Pretrain/Learning Rate": 9.694101782570747e-06, "Pretrain/Loss": 1.995481252670288, "Pretrain/Loss (Raw)": 1.783405065536499, "Pretrain/Step": 6851, "Pretrain/Step Time": 8.48275457881391} +{"Pretrain/Learning Rate": 9.687389208187713e-06, "Pretrain/Loss": 1.993788242340088, "Pretrain/Loss (Raw)": 1.9021685123443604, "Pretrain/Step": 6852, "Pretrain/Step Time": 8.484041165560484} +{"Pretrain/Learning Rate": 9.680678400108955e-06, "Pretrain/Loss": 1.9927564859390259, "Pretrain/Loss (Raw)": 2.0591490268707275, "Pretrain/Step": 6853, "Pretrain/Step Time": 8.486256171017885} +{"Pretrain/Learning Rate": 9.673969359108559e-06, "Pretrain/Loss": 1.9933112859725952, "Pretrain/Loss (Raw)": 2.0680108070373535, "Pretrain/Step": 6854, "Pretrain/Step Time": 8.48303360491991} +{"Pretrain/Learning Rate": 9.66726208596041e-06, "Pretrain/Loss": 1.9959635734558105, "Pretrain/Loss (Raw)": 2.1279478073120117, "Pretrain/Step": 6855, "Pretrain/Step Time": 8.484427530318499} +{"Pretrain/Learning Rate": 9.660556581438201e-06, "Pretrain/Loss": 1.9949941635131836, "Pretrain/Loss (Raw)": 1.9761936664581299, "Pretrain/Step": 6856, "Pretrain/Step Time": 8.4839031919837} +{"Pretrain/Learning Rate": 9.653852846315391e-06, "Pretrain/Loss": 1.9954956769943237, "Pretrain/Loss (Raw)": 2.1219708919525146, "Pretrain/Step": 6857, "Pretrain/Step Time": 8.481374373659492} +{"Pretrain/Learning Rate": 9.647150881365264e-06, "Pretrain/Loss": 1.996032953262329, "Pretrain/Loss (Raw)": 1.92287015914917, "Pretrain/Step": 6858, "Pretrain/Step Time": 8.484071085229516} +{"Pretrain/Learning Rate": 9.640450687360882e-06, "Pretrain/Loss": 1.9969828128814697, "Pretrain/Loss (Raw)": 2.0521018505096436, "Pretrain/Step": 6859, "Pretrain/Step Time": 8.480699189007282} +{"Pretrain/Learning Rate": 9.633752265075122e-06, "Pretrain/Loss": 1.9975244998931885, "Pretrain/Loss (Raw)": 2.054579496383667, "Pretrain/Step": 6860, "Pretrain/Step Time": 8.483478801324964} +{"Pretrain/Learning Rate": 9.627055615280642e-06, "Pretrain/Loss": 2.0000908374786377, "Pretrain/Loss (Raw)": 2.189661979675293, "Pretrain/Step": 6861, "Pretrain/Step Time": 8.485541520640254} +{"Pretrain/Learning Rate": 9.620360738749888e-06, "Pretrain/Loss": 1.9984536170959473, "Pretrain/Loss (Raw)": 1.8685275316238403, "Pretrain/Step": 6862, "Pretrain/Step Time": 8.487876331433654} +{"Pretrain/Learning Rate": 9.613667636255116e-06, "Pretrain/Loss": 1.9984453916549683, "Pretrain/Loss (Raw)": 2.1198322772979736, "Pretrain/Step": 6863, "Pretrain/Step Time": 8.485819894820452} +{"Pretrain/Learning Rate": 9.606976308568386e-06, "Pretrain/Loss": 1.9972343444824219, "Pretrain/Loss (Raw)": 1.812839150428772, "Pretrain/Step": 6864, "Pretrain/Step Time": 8.4855674225837} +{"Pretrain/Learning Rate": 9.600286756461519e-06, "Pretrain/Loss": 1.9971282482147217, "Pretrain/Loss (Raw)": 2.0733983516693115, "Pretrain/Step": 6865, "Pretrain/Step Time": 8.48513494618237} +{"Pretrain/Learning Rate": 9.593598980706173e-06, "Pretrain/Loss": 1.998509407043457, "Pretrain/Loss (Raw)": 2.0070693492889404, "Pretrain/Step": 6866, "Pretrain/Step Time": 8.482661774381995} +{"Pretrain/Learning Rate": 9.586912982073763e-06, "Pretrain/Loss": 1.9965189695358276, "Pretrain/Loss (Raw)": 1.7715914249420166, "Pretrain/Step": 6867, "Pretrain/Step Time": 8.484835425391793} +{"Pretrain/Learning Rate": 9.580228761335519e-06, "Pretrain/Loss": 1.997236967086792, "Pretrain/Loss (Raw)": 2.0132808685302734, "Pretrain/Step": 6868, "Pretrain/Step Time": 8.483706595376134} +{"Pretrain/Learning Rate": 9.573546319262473e-06, "Pretrain/Loss": 1.9987061023712158, "Pretrain/Loss (Raw)": 2.0976672172546387, "Pretrain/Step": 6869, "Pretrain/Step Time": 8.486720990389585} +{"Pretrain/Learning Rate": 9.566865656625434e-06, "Pretrain/Loss": 1.9981553554534912, "Pretrain/Loss (Raw)": 2.080721139907837, "Pretrain/Step": 6870, "Pretrain/Step Time": 8.487255161628127} +{"Pretrain/Learning Rate": 9.56018677419503e-06, "Pretrain/Loss": 1.9946074485778809, "Pretrain/Loss (Raw)": 1.6913495063781738, "Pretrain/Step": 6871, "Pretrain/Step Time": 8.487319651991129} +{"Pretrain/Learning Rate": 9.553509672741645e-06, "Pretrain/Loss": 1.9944809675216675, "Pretrain/Loss (Raw)": 2.026811122894287, "Pretrain/Step": 6872, "Pretrain/Step Time": 8.488113867118955} +{"Pretrain/Learning Rate": 9.546834353035492e-06, "Pretrain/Loss": 1.9934513568878174, "Pretrain/Loss (Raw)": 1.8728119134902954, "Pretrain/Step": 6873, "Pretrain/Step Time": 8.487755263224244} +{"Pretrain/Learning Rate": 9.540160815846566e-06, "Pretrain/Loss": 1.9951376914978027, "Pretrain/Loss (Raw)": 2.164149045944214, "Pretrain/Step": 6874, "Pretrain/Step Time": 8.487654285505414} +{"Pretrain/Learning Rate": 9.533489061944655e-06, "Pretrain/Loss": 1.9955494403839111, "Pretrain/Loss (Raw)": 2.1147048473358154, "Pretrain/Step": 6875, "Pretrain/Step Time": 8.488605108112097} +{"Pretrain/Learning Rate": 9.526819092099348e-06, "Pretrain/Loss": 1.9969418048858643, "Pretrain/Loss (Raw)": 2.1353092193603516, "Pretrain/Step": 6876, "Pretrain/Step Time": 8.489653633907437} +{"Pretrain/Learning Rate": 9.520150907080028e-06, "Pretrain/Loss": 1.9957185983657837, "Pretrain/Loss (Raw)": 1.953725814819336, "Pretrain/Step": 6877, "Pretrain/Step Time": 8.490938164293766} +{"Pretrain/Learning Rate": 9.513484507655854e-06, "Pretrain/Loss": 1.99502432346344, "Pretrain/Loss (Raw)": 1.9767879247665405, "Pretrain/Step": 6878, "Pretrain/Step Time": 8.490790072828531} +{"Pretrain/Learning Rate": 9.506819894595798e-06, "Pretrain/Loss": 1.9930840730667114, "Pretrain/Loss (Raw)": 1.7555809020996094, "Pretrain/Step": 6879, "Pretrain/Step Time": 8.492003709077835} +{"Pretrain/Learning Rate": 9.500157068668632e-06, "Pretrain/Loss": 1.9929225444793701, "Pretrain/Loss (Raw)": 2.0206005573272705, "Pretrain/Step": 6880, "Pretrain/Step Time": 8.492630576714873} +{"Pretrain/Learning Rate": 9.493496030642893e-06, "Pretrain/Loss": 1.991085171699524, "Pretrain/Loss (Raw)": 1.831132173538208, "Pretrain/Step": 6881, "Pretrain/Step Time": 8.491856509819627} +{"Pretrain/Learning Rate": 9.486836781286945e-06, "Pretrain/Loss": 1.9914679527282715, "Pretrain/Loss (Raw)": 2.059511184692383, "Pretrain/Step": 6882, "Pretrain/Step Time": 8.492901641875505} +{"Pretrain/Learning Rate": 9.480179321368912e-06, "Pretrain/Loss": 1.9917691946029663, "Pretrain/Loss (Raw)": 1.9467424154281616, "Pretrain/Step": 6883, "Pretrain/Step Time": 8.493848254904151} +{"Pretrain/Learning Rate": 9.473523651656744e-06, "Pretrain/Loss": 1.9920554161071777, "Pretrain/Loss (Raw)": 1.9388576745986938, "Pretrain/Step": 6884, "Pretrain/Step Time": 8.494713125750422} +{"Pretrain/Learning Rate": 9.466869772918163e-06, "Pretrain/Loss": 1.9921393394470215, "Pretrain/Loss (Raw)": 1.9750661849975586, "Pretrain/Step": 6885, "Pretrain/Step Time": 8.493145709857345} +{"Pretrain/Learning Rate": 9.460217685920697e-06, "Pretrain/Loss": 1.9923951625823975, "Pretrain/Loss (Raw)": 2.023481607437134, "Pretrain/Step": 6886, "Pretrain/Step Time": 8.493007309734821} +{"Pretrain/Learning Rate": 9.45356739143167e-06, "Pretrain/Loss": 1.9932183027267456, "Pretrain/Loss (Raw)": 1.894003987312317, "Pretrain/Step": 6887, "Pretrain/Step Time": 8.490843368694186} +{"Pretrain/Learning Rate": 9.44691889021817e-06, "Pretrain/Loss": 1.9917352199554443, "Pretrain/Loss (Raw)": 1.7715771198272705, "Pretrain/Step": 6888, "Pretrain/Step Time": 8.490874694660306} +{"Pretrain/Learning Rate": 9.440272183047112e-06, "Pretrain/Loss": 1.9918344020843506, "Pretrain/Loss (Raw)": 2.0555121898651123, "Pretrain/Step": 6889, "Pretrain/Step Time": 8.489776996895671} +{"Pretrain/Learning Rate": 9.433627270685185e-06, "Pretrain/Loss": 1.9927395582199097, "Pretrain/Loss (Raw)": 2.0579018592834473, "Pretrain/Step": 6890, "Pretrain/Step Time": 8.491644831374288} +{"Pretrain/Learning Rate": 9.426984153898888e-06, "Pretrain/Loss": 1.9909613132476807, "Pretrain/Loss (Raw)": 1.8673022985458374, "Pretrain/Step": 6891, "Pretrain/Step Time": 8.4918272793293} +{"Pretrain/Learning Rate": 9.420342833454493e-06, "Pretrain/Loss": 1.99355149269104, "Pretrain/Loss (Raw)": 2.1975162029266357, "Pretrain/Step": 6892, "Pretrain/Step Time": 8.491257335990667} +{"Pretrain/Learning Rate": 9.413703310118085e-06, "Pretrain/Loss": 1.9947079420089722, "Pretrain/Loss (Raw)": 2.0267980098724365, "Pretrain/Step": 6893, "Pretrain/Step Time": 8.49307314492762} +{"Pretrain/Learning Rate": 9.407065584655516e-06, "Pretrain/Loss": 1.9932880401611328, "Pretrain/Loss (Raw)": 1.945932388305664, "Pretrain/Step": 6894, "Pretrain/Step Time": 8.495755393058062} +{"Pretrain/Learning Rate": 9.400429657832451e-06, "Pretrain/Loss": 1.9939168691635132, "Pretrain/Loss (Raw)": 1.947357177734375, "Pretrain/Step": 6895, "Pretrain/Step Time": 8.492374125868082} +{"Pretrain/Learning Rate": 9.393795530414354e-06, "Pretrain/Loss": 1.9923889636993408, "Pretrain/Loss (Raw)": 1.9738463163375854, "Pretrain/Step": 6896, "Pretrain/Step Time": 8.49183621071279} +{"Pretrain/Learning Rate": 9.387163203166447e-06, "Pretrain/Loss": 1.9922029972076416, "Pretrain/Loss (Raw)": 1.9974747896194458, "Pretrain/Step": 6897, "Pretrain/Step Time": 8.490082101896405} +{"Pretrain/Learning Rate": 9.380532676853776e-06, "Pretrain/Loss": 1.9946174621582031, "Pretrain/Loss (Raw)": 2.0686495304107666, "Pretrain/Step": 6898, "Pretrain/Step Time": 8.486979331821203} +{"Pretrain/Learning Rate": 9.373903952241183e-06, "Pretrain/Loss": 1.9944208860397339, "Pretrain/Loss (Raw)": 1.854537844657898, "Pretrain/Step": 6899, "Pretrain/Step Time": 8.485748313367367} +{"Pretrain/Learning Rate": 9.36727703009327e-06, "Pretrain/Loss": 1.9930055141448975, "Pretrain/Loss (Raw)": 1.9464789628982544, "Pretrain/Step": 6900, "Pretrain/Step Time": 8.48438723385334} +{"Pretrain/Learning Rate": 9.360651911174455e-06, "Pretrain/Loss": 1.9950358867645264, "Pretrain/Loss (Raw)": 2.0434083938598633, "Pretrain/Step": 6901, "Pretrain/Step Time": 8.486872266978025} +{"Pretrain/Learning Rate": 9.354028596248949e-06, "Pretrain/Loss": 1.9964489936828613, "Pretrain/Loss (Raw)": 2.058584451675415, "Pretrain/Step": 6902, "Pretrain/Step Time": 8.485709518194199} +{"Pretrain/Learning Rate": 9.347407086080754e-06, "Pretrain/Loss": 1.99667227268219, "Pretrain/Loss (Raw)": 2.0936853885650635, "Pretrain/Step": 6903, "Pretrain/Step Time": 8.485042721033096} +{"Pretrain/Learning Rate": 9.340787381433639e-06, "Pretrain/Loss": 1.9956445693969727, "Pretrain/Loss (Raw)": 1.964499592781067, "Pretrain/Step": 6904, "Pretrain/Step Time": 8.483094066381454} +{"Pretrain/Learning Rate": 9.3341694830712e-06, "Pretrain/Loss": 1.994251012802124, "Pretrain/Loss (Raw)": 1.9428446292877197, "Pretrain/Step": 6905, "Pretrain/Step Time": 8.48295283317566} +{"Pretrain/Learning Rate": 9.327553391756806e-06, "Pretrain/Loss": 1.9939563274383545, "Pretrain/Loss (Raw)": 1.8644077777862549, "Pretrain/Step": 6906, "Pretrain/Step Time": 8.486136605963111} +{"Pretrain/Learning Rate": 9.320939108253619e-06, "Pretrain/Loss": 1.9941496849060059, "Pretrain/Loss (Raw)": 1.9192761182785034, "Pretrain/Step": 6907, "Pretrain/Step Time": 8.48766971193254} +{"Pretrain/Learning Rate": 9.314326633324603e-06, "Pretrain/Loss": 1.9934813976287842, "Pretrain/Loss (Raw)": 1.939303994178772, "Pretrain/Step": 6908, "Pretrain/Step Time": 8.491766039282084} +{"Pretrain/Learning Rate": 9.307715967732491e-06, "Pretrain/Loss": 1.9914847612380981, "Pretrain/Loss (Raw)": 1.8830770254135132, "Pretrain/Step": 6909, "Pretrain/Step Time": 8.489072451367974} +{"Pretrain/Learning Rate": 9.301107112239827e-06, "Pretrain/Loss": 1.9904356002807617, "Pretrain/Loss (Raw)": 1.9913634061813354, "Pretrain/Step": 6910, "Pretrain/Step Time": 8.490503273904324} +{"Pretrain/Learning Rate": 9.29450006760894e-06, "Pretrain/Loss": 1.9911755323410034, "Pretrain/Loss (Raw)": 1.9782171249389648, "Pretrain/Step": 6911, "Pretrain/Step Time": 8.489021336659789} +{"Pretrain/Learning Rate": 9.287894834601951e-06, "Pretrain/Loss": 1.9919806718826294, "Pretrain/Loss (Raw)": 2.1010868549346924, "Pretrain/Step": 6912, "Pretrain/Step Time": 8.489222021773458} +{"Pretrain/Learning Rate": 9.28129141398078e-06, "Pretrain/Loss": 1.99244225025177, "Pretrain/Loss (Raw)": 2.1220884323120117, "Pretrain/Step": 6913, "Pretrain/Step Time": 8.486899668350816} +{"Pretrain/Learning Rate": 9.274689806507114e-06, "Pretrain/Loss": 1.9925177097320557, "Pretrain/Loss (Raw)": 2.080325126647949, "Pretrain/Step": 6914, "Pretrain/Step Time": 8.485115053132176} +{"Pretrain/Learning Rate": 9.26809001294246e-06, "Pretrain/Loss": 1.992018222808838, "Pretrain/Loss (Raw)": 2.0479016304016113, "Pretrain/Step": 6915, "Pretrain/Step Time": 8.488852128386497} +{"Pretrain/Learning Rate": 9.261492034048083e-06, "Pretrain/Loss": 1.992282748222351, "Pretrain/Loss (Raw)": 2.042032480239868, "Pretrain/Step": 6916, "Pretrain/Step Time": 8.486152965575457} +{"Pretrain/Learning Rate": 9.254895870585072e-06, "Pretrain/Loss": 1.9918599128723145, "Pretrain/Loss (Raw)": 1.982686161994934, "Pretrain/Step": 6917, "Pretrain/Step Time": 8.48088856600225} +{"Pretrain/Learning Rate": 9.24830152331429e-06, "Pretrain/Loss": 1.9910953044891357, "Pretrain/Loss (Raw)": 1.9710149765014648, "Pretrain/Step": 6918, "Pretrain/Step Time": 8.481128921732306} +{"Pretrain/Learning Rate": 9.241708992996397e-06, "Pretrain/Loss": 1.9902398586273193, "Pretrain/Loss (Raw)": 1.888600468635559, "Pretrain/Step": 6919, "Pretrain/Step Time": 8.482314901426435} +{"Pretrain/Learning Rate": 9.235118280391827e-06, "Pretrain/Loss": 1.9897853136062622, "Pretrain/Loss (Raw)": 1.9345738887786865, "Pretrain/Step": 6920, "Pretrain/Step Time": 8.477633154019713} +{"Pretrain/Learning Rate": 9.228529386260823e-06, "Pretrain/Loss": 1.989492416381836, "Pretrain/Loss (Raw)": 1.9454315900802612, "Pretrain/Step": 6921, "Pretrain/Step Time": 8.481243558228016} +{"Pretrain/Learning Rate": 9.221942311363413e-06, "Pretrain/Loss": 1.9865100383758545, "Pretrain/Loss (Raw)": 1.8599034547805786, "Pretrain/Step": 6922, "Pretrain/Step Time": 8.48084094375372} +{"Pretrain/Learning Rate": 9.215357056459412e-06, "Pretrain/Loss": 1.9853661060333252, "Pretrain/Loss (Raw)": 1.9247034788131714, "Pretrain/Step": 6923, "Pretrain/Step Time": 8.483110940083861} +{"Pretrain/Learning Rate": 9.208773622308434e-06, "Pretrain/Loss": 1.9874441623687744, "Pretrain/Loss (Raw)": 2.0559463500976562, "Pretrain/Step": 6924, "Pretrain/Step Time": 8.488603793084621} +{"Pretrain/Learning Rate": 9.202192009669863e-06, "Pretrain/Loss": 1.9898039102554321, "Pretrain/Loss (Raw)": 2.113196611404419, "Pretrain/Step": 6925, "Pretrain/Step Time": 8.486246278509498} +{"Pretrain/Learning Rate": 9.19561221930289e-06, "Pretrain/Loss": 1.9921460151672363, "Pretrain/Loss (Raw)": 2.1170766353607178, "Pretrain/Step": 6926, "Pretrain/Step Time": 8.486004946753383} +{"Pretrain/Learning Rate": 9.189034251966494e-06, "Pretrain/Loss": 1.9940379858016968, "Pretrain/Loss (Raw)": 2.1032347679138184, "Pretrain/Step": 6927, "Pretrain/Step Time": 8.488486787304282} +{"Pretrain/Learning Rate": 9.182458108419442e-06, "Pretrain/Loss": 1.99396550655365, "Pretrain/Loss (Raw)": 2.1053013801574707, "Pretrain/Step": 6928, "Pretrain/Step Time": 8.49166757427156} +{"Pretrain/Learning Rate": 9.175883789420295e-06, "Pretrain/Loss": 1.9946070909500122, "Pretrain/Loss (Raw)": 2.018444061279297, "Pretrain/Step": 6929, "Pretrain/Step Time": 8.490418910980225} +{"Pretrain/Learning Rate": 9.169311295727387e-06, "Pretrain/Loss": 1.9942373037338257, "Pretrain/Loss (Raw)": 1.959481120109558, "Pretrain/Step": 6930, "Pretrain/Step Time": 8.490998473018408} +{"Pretrain/Learning Rate": 9.162740628098861e-06, "Pretrain/Loss": 1.9903966188430786, "Pretrain/Loss (Raw)": 1.8066576719284058, "Pretrain/Step": 6931, "Pretrain/Step Time": 8.494574947282672} +{"Pretrain/Learning Rate": 9.156171787292633e-06, "Pretrain/Loss": 1.9913816452026367, "Pretrain/Loss (Raw)": 2.103308916091919, "Pretrain/Step": 6932, "Pretrain/Step Time": 8.4880506452173} +{"Pretrain/Learning Rate": 9.149604774066423e-06, "Pretrain/Loss": 1.9900565147399902, "Pretrain/Loss (Raw)": 2.0089004039764404, "Pretrain/Step": 6933, "Pretrain/Step Time": 8.489980077371001} +{"Pretrain/Learning Rate": 9.14303958917773e-06, "Pretrain/Loss": 1.9899179935455322, "Pretrain/Loss (Raw)": 1.8928323984146118, "Pretrain/Step": 6934, "Pretrain/Step Time": 8.49078468233347} +{"Pretrain/Learning Rate": 9.136476233383853e-06, "Pretrain/Loss": 1.9896621704101562, "Pretrain/Loss (Raw)": 1.9131982326507568, "Pretrain/Step": 6935, "Pretrain/Step Time": 8.48350360430777} +{"Pretrain/Learning Rate": 9.129914707441864e-06, "Pretrain/Loss": 1.9894970655441284, "Pretrain/Loss (Raw)": 1.9479053020477295, "Pretrain/Step": 6936, "Pretrain/Step Time": 8.485044764354825} +{"Pretrain/Learning Rate": 9.123355012108634e-06, "Pretrain/Loss": 1.9902725219726562, "Pretrain/Loss (Raw)": 2.012507677078247, "Pretrain/Step": 6937, "Pretrain/Step Time": 8.483089374378324} +{"Pretrain/Learning Rate": 9.116797148140823e-06, "Pretrain/Loss": 1.9886727333068848, "Pretrain/Loss (Raw)": 1.8164854049682617, "Pretrain/Step": 6938, "Pretrain/Step Time": 8.485120639204979} +{"Pretrain/Learning Rate": 9.110241116294883e-06, "Pretrain/Loss": 1.9885469675064087, "Pretrain/Loss (Raw)": 2.048783302307129, "Pretrain/Step": 6939, "Pretrain/Step Time": 8.483843967318535} +{"Pretrain/Learning Rate": 9.103686917327053e-06, "Pretrain/Loss": 1.9911980628967285, "Pretrain/Loss (Raw)": 2.0969483852386475, "Pretrain/Step": 6940, "Pretrain/Step Time": 8.487442066892982} +{"Pretrain/Learning Rate": 9.097134551993341e-06, "Pretrain/Loss": 1.9930956363677979, "Pretrain/Loss (Raw)": 1.9942395687103271, "Pretrain/Step": 6941, "Pretrain/Step Time": 8.482494818046689} +{"Pretrain/Learning Rate": 9.09058402104957e-06, "Pretrain/Loss": 1.9910094738006592, "Pretrain/Loss (Raw)": 1.8684654235839844, "Pretrain/Step": 6942, "Pretrain/Step Time": 8.488308031111956} +{"Pretrain/Learning Rate": 9.084035325251342e-06, "Pretrain/Loss": 1.99137544631958, "Pretrain/Loss (Raw)": 2.0571367740631104, "Pretrain/Step": 6943, "Pretrain/Step Time": 8.486201604828238} +{"Pretrain/Learning Rate": 9.077488465354044e-06, "Pretrain/Loss": 1.9915691614151, "Pretrain/Loss (Raw)": 2.0429110527038574, "Pretrain/Step": 6944, "Pretrain/Step Time": 8.483639102429152} +{"Pretrain/Learning Rate": 9.070943442112868e-06, "Pretrain/Loss": 1.989221215248108, "Pretrain/Loss (Raw)": 1.6546066999435425, "Pretrain/Step": 6945, "Pretrain/Step Time": 8.48444272018969} +{"Pretrain/Learning Rate": 9.064400256282757e-06, "Pretrain/Loss": 1.9896246194839478, "Pretrain/Loss (Raw)": 2.03879451751709, "Pretrain/Step": 6946, "Pretrain/Step Time": 8.484813325107098} +{"Pretrain/Learning Rate": 9.057858908618477e-06, "Pretrain/Loss": 1.989266037940979, "Pretrain/Loss (Raw)": 1.9999481439590454, "Pretrain/Step": 6947, "Pretrain/Step Time": 8.479372549802065} +{"Pretrain/Learning Rate": 9.051319399874577e-06, "Pretrain/Loss": 1.9871063232421875, "Pretrain/Loss (Raw)": 1.8089388608932495, "Pretrain/Step": 6948, "Pretrain/Step Time": 8.481791101396084} +{"Pretrain/Learning Rate": 9.044781730805373e-06, "Pretrain/Loss": 1.9876525402069092, "Pretrain/Loss (Raw)": 2.079094886779785, "Pretrain/Step": 6949, "Pretrain/Step Time": 8.484853867441416} +{"Pretrain/Learning Rate": 9.038245902164996e-06, "Pretrain/Loss": 1.9870028495788574, "Pretrain/Loss (Raw)": 1.942209243774414, "Pretrain/Step": 6950, "Pretrain/Step Time": 8.482158910483122} +{"Pretrain/Learning Rate": 9.03171191470734e-06, "Pretrain/Loss": 1.9881701469421387, "Pretrain/Loss (Raw)": 2.1329128742218018, "Pretrain/Step": 6951, "Pretrain/Step Time": 8.480079093948007} +{"Pretrain/Learning Rate": 9.025179769186098e-06, "Pretrain/Loss": 1.9885541200637817, "Pretrain/Loss (Raw)": 2.0329911708831787, "Pretrain/Step": 6952, "Pretrain/Step Time": 8.480121739208698} +{"Pretrain/Learning Rate": 9.01864946635476e-06, "Pretrain/Loss": 1.9864528179168701, "Pretrain/Loss (Raw)": 1.6706792116165161, "Pretrain/Step": 6953, "Pretrain/Step Time": 8.481405282393098} +{"Pretrain/Learning Rate": 9.012121006966584e-06, "Pretrain/Loss": 1.986128807067871, "Pretrain/Loss (Raw)": 2.0189499855041504, "Pretrain/Step": 6954, "Pretrain/Step Time": 8.481228208169341} +{"Pretrain/Learning Rate": 9.005594391774635e-06, "Pretrain/Loss": 1.9846413135528564, "Pretrain/Loss (Raw)": 1.854328989982605, "Pretrain/Step": 6955, "Pretrain/Step Time": 8.480132000520825} +{"Pretrain/Learning Rate": 8.99906962153176e-06, "Pretrain/Loss": 1.983156681060791, "Pretrain/Loss (Raw)": 2.004103899002075, "Pretrain/Step": 6956, "Pretrain/Step Time": 8.483061987906694} +{"Pretrain/Learning Rate": 8.992546696990576e-06, "Pretrain/Loss": 1.9827218055725098, "Pretrain/Loss (Raw)": 2.075333595275879, "Pretrain/Step": 6957, "Pretrain/Step Time": 8.479920990765095} +{"Pretrain/Learning Rate": 8.986025618903498e-06, "Pretrain/Loss": 1.9833343029022217, "Pretrain/Loss (Raw)": 2.0783822536468506, "Pretrain/Step": 6958, "Pretrain/Step Time": 8.482000757008791} +{"Pretrain/Learning Rate": 8.979506388022743e-06, "Pretrain/Loss": 1.9833717346191406, "Pretrain/Loss (Raw)": 1.9553453922271729, "Pretrain/Step": 6959, "Pretrain/Step Time": 8.484329767525196} +{"Pretrain/Learning Rate": 8.972989005100294e-06, "Pretrain/Loss": 1.9823276996612549, "Pretrain/Loss (Raw)": 1.9790191650390625, "Pretrain/Step": 6960, "Pretrain/Step Time": 8.485234033316374} +{"Pretrain/Learning Rate": 8.96647347088794e-06, "Pretrain/Loss": 1.9790489673614502, "Pretrain/Loss (Raw)": 1.697818636894226, "Pretrain/Step": 6961, "Pretrain/Step Time": 8.483283912763} +{"Pretrain/Learning Rate": 8.959959786137228e-06, "Pretrain/Loss": 1.980133295059204, "Pretrain/Loss (Raw)": 2.0703611373901367, "Pretrain/Step": 6962, "Pretrain/Step Time": 8.484126407653093} +{"Pretrain/Learning Rate": 8.953447951599517e-06, "Pretrain/Loss": 1.9836134910583496, "Pretrain/Loss (Raw)": 2.2802884578704834, "Pretrain/Step": 6963, "Pretrain/Step Time": 8.486118368804455} +{"Pretrain/Learning Rate": 8.946937968025956e-06, "Pretrain/Loss": 1.9841948747634888, "Pretrain/Loss (Raw)": 2.084195137023926, "Pretrain/Step": 6964, "Pretrain/Step Time": 8.48615156300366} +{"Pretrain/Learning Rate": 8.94042983616745e-06, "Pretrain/Loss": 1.9815574884414673, "Pretrain/Loss (Raw)": 1.7716741561889648, "Pretrain/Step": 6965, "Pretrain/Step Time": 8.483000751584768} +{"Pretrain/Learning Rate": 8.933923556774726e-06, "Pretrain/Loss": 1.9817869663238525, "Pretrain/Loss (Raw)": 1.9496314525604248, "Pretrain/Step": 6966, "Pretrain/Step Time": 8.4824512116611} +{"Pretrain/Learning Rate": 8.927419130598263e-06, "Pretrain/Loss": 1.9814780950546265, "Pretrain/Loss (Raw)": 2.0281245708465576, "Pretrain/Step": 6967, "Pretrain/Step Time": 8.484561674296856} +{"Pretrain/Learning Rate": 8.92091655838836e-06, "Pretrain/Loss": 1.981740951538086, "Pretrain/Loss (Raw)": 2.037463665008545, "Pretrain/Step": 6968, "Pretrain/Step Time": 8.478113749995828} +{"Pretrain/Learning Rate": 8.914415840895077e-06, "Pretrain/Loss": 1.9847664833068848, "Pretrain/Loss (Raw)": 2.0681841373443604, "Pretrain/Step": 6969, "Pretrain/Step Time": 8.481843493878841} +{"Pretrain/Learning Rate": 8.907916978868278e-06, "Pretrain/Loss": 1.9848527908325195, "Pretrain/Loss (Raw)": 1.9923748970031738, "Pretrain/Step": 6970, "Pretrain/Step Time": 8.482261111959815} +{"Pretrain/Learning Rate": 8.901419973057604e-06, "Pretrain/Loss": 1.9844061136245728, "Pretrain/Loss (Raw)": 1.9732608795166016, "Pretrain/Step": 6971, "Pretrain/Step Time": 8.480465658009052} +{"Pretrain/Learning Rate": 8.894924824212474e-06, "Pretrain/Loss": 1.9836511611938477, "Pretrain/Loss (Raw)": 1.8684319257736206, "Pretrain/Step": 6972, "Pretrain/Step Time": 8.474524023011327} +{"Pretrain/Learning Rate": 8.888431533082104e-06, "Pretrain/Loss": 1.9827600717544556, "Pretrain/Loss (Raw)": 1.8964991569519043, "Pretrain/Step": 6973, "Pretrain/Step Time": 8.47617058083415} +{"Pretrain/Learning Rate": 8.881940100415495e-06, "Pretrain/Loss": 1.9831218719482422, "Pretrain/Loss (Raw)": 1.9675132036209106, "Pretrain/Step": 6974, "Pretrain/Step Time": 8.476389968767762} +{"Pretrain/Learning Rate": 8.875450526961433e-06, "Pretrain/Loss": 1.984788417816162, "Pretrain/Loss (Raw)": 2.0698482990264893, "Pretrain/Step": 6975, "Pretrain/Step Time": 8.478918250650167} +{"Pretrain/Learning Rate": 8.868962813468484e-06, "Pretrain/Loss": 1.9862548112869263, "Pretrain/Loss (Raw)": 2.0858774185180664, "Pretrain/Step": 6976, "Pretrain/Step Time": 8.478048833087087} +{"Pretrain/Learning Rate": 8.862476960685016e-06, "Pretrain/Loss": 1.9847607612609863, "Pretrain/Loss (Raw)": 1.9023139476776123, "Pretrain/Step": 6977, "Pretrain/Step Time": 8.47934983111918} +{"Pretrain/Learning Rate": 8.855992969359148e-06, "Pretrain/Loss": 1.9843192100524902, "Pretrain/Loss (Raw)": 2.066873788833618, "Pretrain/Step": 6978, "Pretrain/Step Time": 8.48108310624957} +{"Pretrain/Learning Rate": 8.84951084023882e-06, "Pretrain/Loss": 1.98694908618927, "Pretrain/Loss (Raw)": 2.1200339794158936, "Pretrain/Step": 6979, "Pretrain/Step Time": 8.480036310851574} +{"Pretrain/Learning Rate": 8.843030574071747e-06, "Pretrain/Loss": 1.9886813163757324, "Pretrain/Loss (Raw)": 2.123906135559082, "Pretrain/Step": 6980, "Pretrain/Step Time": 8.47892994992435} +{"Pretrain/Learning Rate": 8.836552171605414e-06, "Pretrain/Loss": 1.9896471500396729, "Pretrain/Loss (Raw)": 2.182771682739258, "Pretrain/Step": 6981, "Pretrain/Step Time": 8.478784285485744} +{"Pretrain/Learning Rate": 8.830075633587115e-06, "Pretrain/Loss": 1.9890543222427368, "Pretrain/Loss (Raw)": 1.9921330213546753, "Pretrain/Step": 6982, "Pretrain/Step Time": 8.480605663731694} +{"Pretrain/Learning Rate": 8.8236009607639e-06, "Pretrain/Loss": 1.9873106479644775, "Pretrain/Loss (Raw)": 1.9047483205795288, "Pretrain/Step": 6983, "Pretrain/Step Time": 8.474604362621903} +{"Pretrain/Learning Rate": 8.817128153882628e-06, "Pretrain/Loss": 1.9871826171875, "Pretrain/Loss (Raw)": 1.9598026275634766, "Pretrain/Step": 6984, "Pretrain/Step Time": 8.473849840462208} +{"Pretrain/Learning Rate": 8.810657213689939e-06, "Pretrain/Loss": 1.9871207475662231, "Pretrain/Loss (Raw)": 2.114060401916504, "Pretrain/Step": 6985, "Pretrain/Step Time": 8.480734441429377} +{"Pretrain/Learning Rate": 8.80418814093225e-06, "Pretrain/Loss": 1.98727548122406, "Pretrain/Loss (Raw)": 1.9426711797714233, "Pretrain/Step": 6986, "Pretrain/Step Time": 8.479981353506446} +{"Pretrain/Learning Rate": 8.797720936355777e-06, "Pretrain/Loss": 1.988067388534546, "Pretrain/Loss (Raw)": 2.1534759998321533, "Pretrain/Step": 6987, "Pretrain/Step Time": 8.480942215770483} +{"Pretrain/Learning Rate": 8.791255600706488e-06, "Pretrain/Loss": 1.9873077869415283, "Pretrain/Loss (Raw)": 1.9573360681533813, "Pretrain/Step": 6988, "Pretrain/Step Time": 8.481617912650108} +{"Pretrain/Learning Rate": 8.784792134730174e-06, "Pretrain/Loss": 1.9866564273834229, "Pretrain/Loss (Raw)": 2.1062943935394287, "Pretrain/Step": 6989, "Pretrain/Step Time": 8.480589950457215} +{"Pretrain/Learning Rate": 8.778330539172386e-06, "Pretrain/Loss": 1.9874027967453003, "Pretrain/Loss (Raw)": 1.9640660285949707, "Pretrain/Step": 6990, "Pretrain/Step Time": 8.482933942228556} +{"Pretrain/Learning Rate": 8.77187081477847e-06, "Pretrain/Loss": 1.9878323078155518, "Pretrain/Loss (Raw)": 2.174801826477051, "Pretrain/Step": 6991, "Pretrain/Step Time": 8.481208365410566} +{"Pretrain/Learning Rate": 8.765412962293562e-06, "Pretrain/Loss": 1.9863348007202148, "Pretrain/Loss (Raw)": 1.6211621761322021, "Pretrain/Step": 6992, "Pretrain/Step Time": 8.482879446819425} +{"Pretrain/Learning Rate": 8.758956982462555e-06, "Pretrain/Loss": 1.9859485626220703, "Pretrain/Loss (Raw)": 2.02396821975708, "Pretrain/Step": 6993, "Pretrain/Step Time": 8.48330052383244} +{"Pretrain/Learning Rate": 8.752502876030153e-06, "Pretrain/Loss": 1.9846611022949219, "Pretrain/Loss (Raw)": 1.8422613143920898, "Pretrain/Step": 6994, "Pretrain/Step Time": 8.482939155772328} +{"Pretrain/Learning Rate": 8.746050643740833e-06, "Pretrain/Loss": 1.9865739345550537, "Pretrain/Loss (Raw)": 2.0164377689361572, "Pretrain/Step": 6995, "Pretrain/Step Time": 8.481079557910562} +{"Pretrain/Learning Rate": 8.73960028633886e-06, "Pretrain/Loss": 1.985715389251709, "Pretrain/Loss (Raw)": 1.9033969640731812, "Pretrain/Step": 6996, "Pretrain/Step Time": 8.481717213988304} +{"Pretrain/Learning Rate": 8.733151804568288e-06, "Pretrain/Loss": 1.9841878414154053, "Pretrain/Loss (Raw)": 1.9021347761154175, "Pretrain/Step": 6997, "Pretrain/Step Time": 8.479993795976043} +{"Pretrain/Learning Rate": 8.726705199172929e-06, "Pretrain/Loss": 1.9827547073364258, "Pretrain/Loss (Raw)": 1.8972667455673218, "Pretrain/Step": 6998, "Pretrain/Step Time": 8.479106049984694} +{"Pretrain/Learning Rate": 8.720260470896416e-06, "Pretrain/Loss": 1.984445571899414, "Pretrain/Loss (Raw)": 1.907800316810608, "Pretrain/Step": 6999, "Pretrain/Step Time": 8.477958450093865} +{"Pretrain/Learning Rate": 8.713817620482128e-06, "Pretrain/Loss": 1.9842681884765625, "Pretrain/Loss (Raw)": 2.004093885421753, "Pretrain/Step": 7000, "Pretrain/Step Time": 8.474374331533909} +{"Pretrain/Learning Rate": 8.707376648673254e-06, "Pretrain/Loss": 1.9860957860946655, "Pretrain/Loss (Raw)": 2.106750726699829, "Pretrain/Step": 7001, "Pretrain/Step Time": 8.476530466228724} +{"Pretrain/Learning Rate": 8.70093755621276e-06, "Pretrain/Loss": 1.984884262084961, "Pretrain/Loss (Raw)": 2.009068012237549, "Pretrain/Step": 7002, "Pretrain/Step Time": 8.475717548280954} +{"Pretrain/Learning Rate": 8.694500343843395e-06, "Pretrain/Loss": 1.9857959747314453, "Pretrain/Loss (Raw)": 2.231419324874878, "Pretrain/Step": 7003, "Pretrain/Step Time": 8.47768460586667} +{"Pretrain/Learning Rate": 8.68806501230768e-06, "Pretrain/Loss": 1.9846190214157104, "Pretrain/Loss (Raw)": 1.9846470355987549, "Pretrain/Step": 7004, "Pretrain/Step Time": 8.474192019551992} +{"Pretrain/Learning Rate": 8.681631562347933e-06, "Pretrain/Loss": 1.9847776889801025, "Pretrain/Loss (Raw)": 1.9740418195724487, "Pretrain/Step": 7005, "Pretrain/Step Time": 8.477956645190716} +{"Pretrain/Learning Rate": 8.675199994706252e-06, "Pretrain/Loss": 1.9847583770751953, "Pretrain/Loss (Raw)": 1.9743095636367798, "Pretrain/Step": 7006, "Pretrain/Step Time": 8.4785062558949} +{"Pretrain/Learning Rate": 8.668770310124514e-06, "Pretrain/Loss": 1.9885518550872803, "Pretrain/Loss (Raw)": 2.2411489486694336, "Pretrain/Step": 7007, "Pretrain/Step Time": 8.476216077804565} +{"Pretrain/Learning Rate": 8.662342509344387e-06, "Pretrain/Loss": 1.9885079860687256, "Pretrain/Loss (Raw)": 2.014979124069214, "Pretrain/Step": 7008, "Pretrain/Step Time": 8.475497771054506} +{"Pretrain/Learning Rate": 8.655916593107305e-06, "Pretrain/Loss": 1.9892593622207642, "Pretrain/Loss (Raw)": 1.927308201789856, "Pretrain/Step": 7009, "Pretrain/Step Time": 8.480507496744394} +{"Pretrain/Learning Rate": 8.649492562154499e-06, "Pretrain/Loss": 1.988820195198059, "Pretrain/Loss (Raw)": 2.0033066272735596, "Pretrain/Step": 7010, "Pretrain/Step Time": 8.477848164737225} +{"Pretrain/Learning Rate": 8.643070417226978e-06, "Pretrain/Loss": 1.990241527557373, "Pretrain/Loss (Raw)": 2.1286652088165283, "Pretrain/Step": 7011, "Pretrain/Step Time": 8.476918490603566} +{"Pretrain/Learning Rate": 8.63665015906554e-06, "Pretrain/Loss": 1.9895532131195068, "Pretrain/Loss (Raw)": 1.8507670164108276, "Pretrain/Step": 7012, "Pretrain/Step Time": 8.477683814242482} +{"Pretrain/Learning Rate": 8.630231788410762e-06, "Pretrain/Loss": 1.9894970655441284, "Pretrain/Loss (Raw)": 1.9678741693496704, "Pretrain/Step": 7013, "Pretrain/Step Time": 8.47956008464098} +{"Pretrain/Learning Rate": 8.623815306002986e-06, "Pretrain/Loss": 1.9881706237792969, "Pretrain/Loss (Raw)": 1.8536771535873413, "Pretrain/Step": 7014, "Pretrain/Step Time": 8.480324648320675} +{"Pretrain/Learning Rate": 8.617400712582369e-06, "Pretrain/Loss": 1.9897172451019287, "Pretrain/Loss (Raw)": 2.0919885635375977, "Pretrain/Step": 7015, "Pretrain/Step Time": 8.478320507332683} +{"Pretrain/Learning Rate": 8.610988008888813e-06, "Pretrain/Loss": 1.99233078956604, "Pretrain/Loss (Raw)": 2.1060965061187744, "Pretrain/Step": 7016, "Pretrain/Step Time": 8.47996542043984} +{"Pretrain/Learning Rate": 8.60457719566203e-06, "Pretrain/Loss": 1.993562936782837, "Pretrain/Loss (Raw)": 2.2132322788238525, "Pretrain/Step": 7017, "Pretrain/Step Time": 8.48374855145812} +{"Pretrain/Learning Rate": 8.598168273641508e-06, "Pretrain/Loss": 1.9932396411895752, "Pretrain/Loss (Raw)": 2.016538143157959, "Pretrain/Step": 7018, "Pretrain/Step Time": 8.481674592942} +{"Pretrain/Learning Rate": 8.591761243566517e-06, "Pretrain/Loss": 1.9952623844146729, "Pretrain/Loss (Raw)": 2.126211404800415, "Pretrain/Step": 7019, "Pretrain/Step Time": 8.480712888762355} +{"Pretrain/Learning Rate": 8.585356106176094e-06, "Pretrain/Loss": 1.9933539628982544, "Pretrain/Loss (Raw)": 1.9532302618026733, "Pretrain/Step": 7020, "Pretrain/Step Time": 8.484518997371197} +{"Pretrain/Learning Rate": 8.578952862209075e-06, "Pretrain/Loss": 1.9930334091186523, "Pretrain/Loss (Raw)": 1.985780954360962, "Pretrain/Step": 7021, "Pretrain/Step Time": 8.48574385792017} +{"Pretrain/Learning Rate": 8.572551512404073e-06, "Pretrain/Loss": 1.9941623210906982, "Pretrain/Loss (Raw)": 2.090407609939575, "Pretrain/Step": 7022, "Pretrain/Step Time": 8.483967443928123} +{"Pretrain/Learning Rate": 8.56615205749948e-06, "Pretrain/Loss": 1.994805932044983, "Pretrain/Loss (Raw)": 2.029754877090454, "Pretrain/Step": 7023, "Pretrain/Step Time": 8.487659737467766} +{"Pretrain/Learning Rate": 8.559754498233483e-06, "Pretrain/Loss": 1.9961659908294678, "Pretrain/Loss (Raw)": 2.1479334831237793, "Pretrain/Step": 7024, "Pretrain/Step Time": 8.486105857416987} +{"Pretrain/Learning Rate": 8.553358835344016e-06, "Pretrain/Loss": 1.996375322341919, "Pretrain/Loss (Raw)": 2.0242669582366943, "Pretrain/Step": 7025, "Pretrain/Step Time": 8.487151864916086} +{"Pretrain/Learning Rate": 8.546965069568827e-06, "Pretrain/Loss": 1.9966000318527222, "Pretrain/Loss (Raw)": 2.0974245071411133, "Pretrain/Step": 7026, "Pretrain/Step Time": 8.489779829978943} +{"Pretrain/Learning Rate": 8.540573201645438e-06, "Pretrain/Loss": 1.9984047412872314, "Pretrain/Loss (Raw)": 2.0855343341827393, "Pretrain/Step": 7027, "Pretrain/Step Time": 8.489505184814334} +{"Pretrain/Learning Rate": 8.534183232311143e-06, "Pretrain/Loss": 1.9987804889678955, "Pretrain/Loss (Raw)": 1.9945658445358276, "Pretrain/Step": 7028, "Pretrain/Step Time": 8.48993050865829} +{"Pretrain/Learning Rate": 8.527795162303037e-06, "Pretrain/Loss": 1.9981333017349243, "Pretrain/Loss (Raw)": 1.9605741500854492, "Pretrain/Step": 7029, "Pretrain/Step Time": 8.485057832673192} +{"Pretrain/Learning Rate": 8.52140899235796e-06, "Pretrain/Loss": 1.9980430603027344, "Pretrain/Loss (Raw)": 2.047030448913574, "Pretrain/Step": 7030, "Pretrain/Step Time": 8.485878761857748} +{"Pretrain/Learning Rate": 8.515024723212566e-06, "Pretrain/Loss": 1.9953534603118896, "Pretrain/Loss (Raw)": 1.7494134902954102, "Pretrain/Step": 7031, "Pretrain/Step Time": 8.482338525354862} +{"Pretrain/Learning Rate": 8.508642355603286e-06, "Pretrain/Loss": 1.9961881637573242, "Pretrain/Loss (Raw)": 2.0713539123535156, "Pretrain/Step": 7032, "Pretrain/Step Time": 8.48176977597177} +{"Pretrain/Learning Rate": 8.502261890266303e-06, "Pretrain/Loss": 1.997434377670288, "Pretrain/Loss (Raw)": 2.1023430824279785, "Pretrain/Step": 7033, "Pretrain/Step Time": 8.48550434783101} +{"Pretrain/Learning Rate": 8.495883327937614e-06, "Pretrain/Loss": 1.999722957611084, "Pretrain/Loss (Raw)": 2.157364845275879, "Pretrain/Step": 7034, "Pretrain/Step Time": 8.48586143180728} +{"Pretrain/Learning Rate": 8.489506669352994e-06, "Pretrain/Loss": 1.9987399578094482, "Pretrain/Loss (Raw)": 1.793440818786621, "Pretrain/Step": 7035, "Pretrain/Step Time": 8.484747866168618} +{"Pretrain/Learning Rate": 8.483131915247968e-06, "Pretrain/Loss": 1.9994453191757202, "Pretrain/Loss (Raw)": 2.029590606689453, "Pretrain/Step": 7036, "Pretrain/Step Time": 8.481996182352304} +{"Pretrain/Learning Rate": 8.476759066357873e-06, "Pretrain/Loss": 2.0007224082946777, "Pretrain/Loss (Raw)": 2.0465354919433594, "Pretrain/Step": 7037, "Pretrain/Step Time": 8.486344067379832} +{"Pretrain/Learning Rate": 8.470388123417811e-06, "Pretrain/Loss": 2.001038074493408, "Pretrain/Loss (Raw)": 2.0317630767822266, "Pretrain/Step": 7038, "Pretrain/Step Time": 8.486077692359686} +{"Pretrain/Learning Rate": 8.46401908716267e-06, "Pretrain/Loss": 2.0016281604766846, "Pretrain/Loss (Raw)": 2.0537588596343994, "Pretrain/Step": 7039, "Pretrain/Step Time": 8.485485738143325} +{"Pretrain/Learning Rate": 8.457651958327123e-06, "Pretrain/Loss": 1.9985780715942383, "Pretrain/Loss (Raw)": 1.7106714248657227, "Pretrain/Step": 7040, "Pretrain/Step Time": 8.486441208049655} +{"Pretrain/Learning Rate": 8.451286737645603e-06, "Pretrain/Loss": 1.9977129697799683, "Pretrain/Loss (Raw)": 2.01137113571167, "Pretrain/Step": 7041, "Pretrain/Step Time": 8.487332222983241} +{"Pretrain/Learning Rate": 8.444923425852342e-06, "Pretrain/Loss": 1.9969545602798462, "Pretrain/Loss (Raw)": 1.9832433462142944, "Pretrain/Step": 7042, "Pretrain/Step Time": 8.49211254529655} +{"Pretrain/Learning Rate": 8.438562023681346e-06, "Pretrain/Loss": 1.997401475906372, "Pretrain/Loss (Raw)": 2.1051206588745117, "Pretrain/Step": 7043, "Pretrain/Step Time": 8.488493628799915} +{"Pretrain/Learning Rate": 8.432202531866402e-06, "Pretrain/Loss": 1.9955261945724487, "Pretrain/Loss (Raw)": 1.8019688129425049, "Pretrain/Step": 7044, "Pretrain/Step Time": 8.489145785570145} +{"Pretrain/Learning Rate": 8.42584495114108e-06, "Pretrain/Loss": 1.9956103563308716, "Pretrain/Loss (Raw)": 1.993470549583435, "Pretrain/Step": 7045, "Pretrain/Step Time": 8.491303967311978} +{"Pretrain/Learning Rate": 8.419489282238708e-06, "Pretrain/Loss": 1.9941954612731934, "Pretrain/Loss (Raw)": 1.7899142503738403, "Pretrain/Step": 7046, "Pretrain/Step Time": 8.492966061457992} +{"Pretrain/Learning Rate": 8.413135525892425e-06, "Pretrain/Loss": 1.9957876205444336, "Pretrain/Loss (Raw)": 2.0923783779144287, "Pretrain/Step": 7047, "Pretrain/Step Time": 8.48829935863614} +{"Pretrain/Learning Rate": 8.406783682835135e-06, "Pretrain/Loss": 1.9966533184051514, "Pretrain/Loss (Raw)": 2.0454015731811523, "Pretrain/Step": 7048, "Pretrain/Step Time": 8.492669800296426} +{"Pretrain/Learning Rate": 8.400433753799508e-06, "Pretrain/Loss": 1.995660424232483, "Pretrain/Loss (Raw)": 1.8183332681655884, "Pretrain/Step": 7049, "Pretrain/Step Time": 8.487645467743278} +{"Pretrain/Learning Rate": 8.394085739518024e-06, "Pretrain/Loss": 1.997201919555664, "Pretrain/Loss (Raw)": 2.0572221279144287, "Pretrain/Step": 7050, "Pretrain/Step Time": 8.487366976216435} +{"Pretrain/Learning Rate": 8.387739640722902e-06, "Pretrain/Loss": 1.9962289333343506, "Pretrain/Loss (Raw)": 1.800163745880127, "Pretrain/Step": 7051, "Pretrain/Step Time": 8.484906757250428} +{"Pretrain/Learning Rate": 8.38139545814618e-06, "Pretrain/Loss": 1.9962489604949951, "Pretrain/Loss (Raw)": 2.058493137359619, "Pretrain/Step": 7052, "Pretrain/Step Time": 8.484005633741617} +{"Pretrain/Learning Rate": 8.375053192519647e-06, "Pretrain/Loss": 1.994635820388794, "Pretrain/Loss (Raw)": 1.9067316055297852, "Pretrain/Step": 7053, "Pretrain/Step Time": 8.487337224185467} +{"Pretrain/Learning Rate": 8.36871284457489e-06, "Pretrain/Loss": 1.9942669868469238, "Pretrain/Loss (Raw)": 2.0698482990264893, "Pretrain/Step": 7054, "Pretrain/Step Time": 8.49236842431128} +{"Pretrain/Learning Rate": 8.36237441504326e-06, "Pretrain/Loss": 1.9933662414550781, "Pretrain/Loss (Raw)": 1.9879286289215088, "Pretrain/Step": 7055, "Pretrain/Step Time": 8.488710150122643} +{"Pretrain/Learning Rate": 8.3560379046559e-06, "Pretrain/Loss": 1.993605136871338, "Pretrain/Loss (Raw)": 2.1358819007873535, "Pretrain/Step": 7056, "Pretrain/Step Time": 8.486018117517233} +{"Pretrain/Learning Rate": 8.34970331414371e-06, "Pretrain/Loss": 1.994432806968689, "Pretrain/Loss (Raw)": 2.1244044303894043, "Pretrain/Step": 7057, "Pretrain/Step Time": 8.488899586722255} +{"Pretrain/Learning Rate": 8.343370644237396e-06, "Pretrain/Loss": 1.9951977729797363, "Pretrain/Loss (Raw)": 2.057384967803955, "Pretrain/Step": 7058, "Pretrain/Step Time": 8.488507553935051} +{"Pretrain/Learning Rate": 8.337039895667423e-06, "Pretrain/Loss": 1.9954020977020264, "Pretrain/Loss (Raw)": 1.832822322845459, "Pretrain/Step": 7059, "Pretrain/Step Time": 8.485116764903069} +{"Pretrain/Learning Rate": 8.33071106916404e-06, "Pretrain/Loss": 1.9929550886154175, "Pretrain/Loss (Raw)": 1.7900842428207397, "Pretrain/Step": 7060, "Pretrain/Step Time": 8.484817188233137} +{"Pretrain/Learning Rate": 8.324384165457289e-06, "Pretrain/Loss": 1.9932293891906738, "Pretrain/Loss (Raw)": 2.044020414352417, "Pretrain/Step": 7061, "Pretrain/Step Time": 8.484398391097784} +{"Pretrain/Learning Rate": 8.318059185276955e-06, "Pretrain/Loss": 1.992842435836792, "Pretrain/Loss (Raw)": 1.8432995080947876, "Pretrain/Step": 7062, "Pretrain/Step Time": 8.487117579206824} +{"Pretrain/Learning Rate": 8.31173612935263e-06, "Pretrain/Loss": 1.9936509132385254, "Pretrain/Loss (Raw)": 2.016662120819092, "Pretrain/Step": 7063, "Pretrain/Step Time": 8.487500371411443} +{"Pretrain/Learning Rate": 8.305414998413685e-06, "Pretrain/Loss": 1.9947483539581299, "Pretrain/Loss (Raw)": 2.0883913040161133, "Pretrain/Step": 7064, "Pretrain/Step Time": 8.48688755556941} +{"Pretrain/Learning Rate": 8.29909579318925e-06, "Pretrain/Loss": 1.9946749210357666, "Pretrain/Loss (Raw)": 2.0031135082244873, "Pretrain/Step": 7065, "Pretrain/Step Time": 8.48544604331255} +{"Pretrain/Learning Rate": 8.29277851440825e-06, "Pretrain/Loss": 1.9950718879699707, "Pretrain/Loss (Raw)": 1.8672863245010376, "Pretrain/Step": 7066, "Pretrain/Step Time": 8.481888582929969} +{"Pretrain/Learning Rate": 8.286463162799368e-06, "Pretrain/Loss": 1.995755672454834, "Pretrain/Loss (Raw)": 2.1363017559051514, "Pretrain/Step": 7067, "Pretrain/Step Time": 8.48163602128625} +{"Pretrain/Learning Rate": 8.28014973909109e-06, "Pretrain/Loss": 1.9959406852722168, "Pretrain/Loss (Raw)": 2.1206371784210205, "Pretrain/Step": 7068, "Pretrain/Step Time": 8.478278482332826} +{"Pretrain/Learning Rate": 8.273838244011662e-06, "Pretrain/Loss": 1.9946321249008179, "Pretrain/Loss (Raw)": 1.8267548084259033, "Pretrain/Step": 7069, "Pretrain/Step Time": 8.481421446427703} +{"Pretrain/Learning Rate": 8.267528678289114e-06, "Pretrain/Loss": 1.994762659072876, "Pretrain/Loss (Raw)": 1.8851666450500488, "Pretrain/Step": 7070, "Pretrain/Step Time": 8.482426090165973} +{"Pretrain/Learning Rate": 8.261221042651262e-06, "Pretrain/Loss": 1.9925270080566406, "Pretrain/Loss (Raw)": 1.7709624767303467, "Pretrain/Step": 7071, "Pretrain/Step Time": 8.486727809533477} +{"Pretrain/Learning Rate": 8.254915337825673e-06, "Pretrain/Loss": 1.991976261138916, "Pretrain/Loss (Raw)": 1.972428321838379, "Pretrain/Step": 7072, "Pretrain/Step Time": 8.48610620945692} +{"Pretrain/Learning Rate": 8.248611564539713e-06, "Pretrain/Loss": 1.9949383735656738, "Pretrain/Loss (Raw)": 2.0337531566619873, "Pretrain/Step": 7073, "Pretrain/Step Time": 8.48593925125897} +{"Pretrain/Learning Rate": 8.242309723520523e-06, "Pretrain/Loss": 1.9951857328414917, "Pretrain/Loss (Raw)": 2.0704541206359863, "Pretrain/Step": 7074, "Pretrain/Step Time": 8.486876090988517} +{"Pretrain/Learning Rate": 8.236009815495019e-06, "Pretrain/Loss": 1.994849681854248, "Pretrain/Loss (Raw)": 1.95694100856781, "Pretrain/Step": 7075, "Pretrain/Step Time": 8.487730057910085} +{"Pretrain/Learning Rate": 8.229711841189889e-06, "Pretrain/Loss": 1.9965922832489014, "Pretrain/Loss (Raw)": 2.0319855213165283, "Pretrain/Step": 7076, "Pretrain/Step Time": 8.486690105870366} +{"Pretrain/Learning Rate": 8.223415801331612e-06, "Pretrain/Loss": 1.9976212978363037, "Pretrain/Loss (Raw)": 2.210805892944336, "Pretrain/Step": 7077, "Pretrain/Step Time": 8.484824813902378} +{"Pretrain/Learning Rate": 8.21712169664642e-06, "Pretrain/Loss": 1.9988749027252197, "Pretrain/Loss (Raw)": 2.1026782989501953, "Pretrain/Step": 7078, "Pretrain/Step Time": 8.481697138398886} +{"Pretrain/Learning Rate": 8.210829527860345e-06, "Pretrain/Loss": 1.9979795217514038, "Pretrain/Loss (Raw)": 2.0182931423187256, "Pretrain/Step": 7079, "Pretrain/Step Time": 8.481448139995337} +{"Pretrain/Learning Rate": 8.204539295699182e-06, "Pretrain/Loss": 1.9959503412246704, "Pretrain/Loss (Raw)": 1.7732676267623901, "Pretrain/Step": 7080, "Pretrain/Step Time": 8.482757035642862} +{"Pretrain/Learning Rate": 8.198251000888516e-06, "Pretrain/Loss": 1.9985170364379883, "Pretrain/Loss (Raw)": 1.999205470085144, "Pretrain/Step": 7081, "Pretrain/Step Time": 8.483714746311307} +{"Pretrain/Learning Rate": 8.191964644153685e-06, "Pretrain/Loss": 1.9994142055511475, "Pretrain/Loss (Raw)": 2.1337838172912598, "Pretrain/Step": 7082, "Pretrain/Step Time": 8.48123673722148} +{"Pretrain/Learning Rate": 8.185680226219832e-06, "Pretrain/Loss": 2.0008630752563477, "Pretrain/Loss (Raw)": 2.0397629737854004, "Pretrain/Step": 7083, "Pretrain/Step Time": 8.482248215004802} +{"Pretrain/Learning Rate": 8.179397747811852e-06, "Pretrain/Loss": 2.0014867782592773, "Pretrain/Loss (Raw)": 2.0839736461639404, "Pretrain/Step": 7084, "Pretrain/Step Time": 8.481816379353404} +{"Pretrain/Learning Rate": 8.173117209654427e-06, "Pretrain/Loss": 2.00262451171875, "Pretrain/Loss (Raw)": 2.220966339111328, "Pretrain/Step": 7085, "Pretrain/Step Time": 8.48596204444766} +{"Pretrain/Learning Rate": 8.16683861247202e-06, "Pretrain/Loss": 2.0024375915527344, "Pretrain/Loss (Raw)": 2.0544631481170654, "Pretrain/Step": 7086, "Pretrain/Step Time": 8.48450656235218} +{"Pretrain/Learning Rate": 8.160561956988869e-06, "Pretrain/Loss": 2.00178861618042, "Pretrain/Loss (Raw)": 1.872283697128296, "Pretrain/Step": 7087, "Pretrain/Step Time": 8.483323063701391} +{"Pretrain/Learning Rate": 8.154287243928974e-06, "Pretrain/Loss": 2.0019116401672363, "Pretrain/Loss (Raw)": 1.9947556257247925, "Pretrain/Step": 7088, "Pretrain/Step Time": 8.485776109620929} +{"Pretrain/Learning Rate": 8.148014474016121e-06, "Pretrain/Loss": 2.0025014877319336, "Pretrain/Loss (Raw)": 1.7733056545257568, "Pretrain/Step": 7089, "Pretrain/Step Time": 8.484239296987653} +{"Pretrain/Learning Rate": 8.141743647973882e-06, "Pretrain/Loss": 2.0024003982543945, "Pretrain/Loss (Raw)": 2.057422637939453, "Pretrain/Step": 7090, "Pretrain/Step Time": 8.487601909786463} +{"Pretrain/Learning Rate": 8.135474766525585e-06, "Pretrain/Loss": 1.999309778213501, "Pretrain/Loss (Raw)": 1.8847066164016724, "Pretrain/Step": 7091, "Pretrain/Step Time": 8.488064993172884} +{"Pretrain/Learning Rate": 8.129207830394356e-06, "Pretrain/Loss": 1.9983670711517334, "Pretrain/Loss (Raw)": 1.9635310173034668, "Pretrain/Step": 7092, "Pretrain/Step Time": 8.485443487763405} +{"Pretrain/Learning Rate": 8.122942840303067e-06, "Pretrain/Loss": 2.000825881958008, "Pretrain/Loss (Raw)": 2.086388111114502, "Pretrain/Step": 7093, "Pretrain/Step Time": 8.487607145681977} +{"Pretrain/Learning Rate": 8.116679796974388e-06, "Pretrain/Loss": 1.9994438886642456, "Pretrain/Loss (Raw)": 1.7727349996566772, "Pretrain/Step": 7094, "Pretrain/Step Time": 8.489381132647395} +{"Pretrain/Learning Rate": 8.110418701130765e-06, "Pretrain/Loss": 1.999106526374817, "Pretrain/Loss (Raw)": 1.9849516153335571, "Pretrain/Step": 7095, "Pretrain/Step Time": 8.488508375361562} +{"Pretrain/Learning Rate": 8.104159553494408e-06, "Pretrain/Loss": 1.9979982376098633, "Pretrain/Loss (Raw)": 1.8956084251403809, "Pretrain/Step": 7096, "Pretrain/Step Time": 8.49101342447102} +{"Pretrain/Learning Rate": 8.097902354787319e-06, "Pretrain/Loss": 1.9972866773605347, "Pretrain/Loss (Raw)": 1.9770859479904175, "Pretrain/Step": 7097, "Pretrain/Step Time": 8.49037423916161} +{"Pretrain/Learning Rate": 8.091647105731239e-06, "Pretrain/Loss": 1.9973870515823364, "Pretrain/Loss (Raw)": 2.0052220821380615, "Pretrain/Step": 7098, "Pretrain/Step Time": 8.488013066351414} +{"Pretrain/Learning Rate": 8.085393807047737e-06, "Pretrain/Loss": 1.9982713460922241, "Pretrain/Loss (Raw)": 2.0864455699920654, "Pretrain/Step": 7099, "Pretrain/Step Time": 8.487397342920303} +{"Pretrain/Learning Rate": 8.079142459458106e-06, "Pretrain/Loss": 1.998154640197754, "Pretrain/Loss (Raw)": 1.853509545326233, "Pretrain/Step": 7100, "Pretrain/Step Time": 8.485425647348166} +{"Pretrain/Learning Rate": 8.072893063683445e-06, "Pretrain/Loss": 1.9986670017242432, "Pretrain/Loss (Raw)": 1.9620656967163086, "Pretrain/Step": 7101, "Pretrain/Step Time": 8.487927682697773} +{"Pretrain/Learning Rate": 8.066645620444622e-06, "Pretrain/Loss": 1.99700927734375, "Pretrain/Loss (Raw)": 1.7553303241729736, "Pretrain/Step": 7102, "Pretrain/Step Time": 8.48894502222538} +{"Pretrain/Learning Rate": 8.060400130462285e-06, "Pretrain/Loss": 1.9969737529754639, "Pretrain/Loss (Raw)": 2.065305709838867, "Pretrain/Step": 7103, "Pretrain/Step Time": 8.485248748213053} +{"Pretrain/Learning Rate": 8.054156594456828e-06, "Pretrain/Loss": 1.9954004287719727, "Pretrain/Loss (Raw)": 1.8845170736312866, "Pretrain/Step": 7104, "Pretrain/Step Time": 8.487033944576979} +{"Pretrain/Learning Rate": 8.047915013148454e-06, "Pretrain/Loss": 1.9940686225891113, "Pretrain/Loss (Raw)": 1.7318164110183716, "Pretrain/Step": 7105, "Pretrain/Step Time": 8.490430761128664} +{"Pretrain/Learning Rate": 8.041675387257127e-06, "Pretrain/Loss": 1.9942666292190552, "Pretrain/Loss (Raw)": 2.092216968536377, "Pretrain/Step": 7106, "Pretrain/Step Time": 8.49155955389142} +{"Pretrain/Learning Rate": 8.035437717502584e-06, "Pretrain/Loss": 1.994315505027771, "Pretrain/Loss (Raw)": 2.1263046264648438, "Pretrain/Step": 7107, "Pretrain/Step Time": 8.488917024806142} +{"Pretrain/Learning Rate": 8.029202004604347e-06, "Pretrain/Loss": 1.9932537078857422, "Pretrain/Loss (Raw)": 1.9879956245422363, "Pretrain/Step": 7108, "Pretrain/Step Time": 8.489755649119616} +{"Pretrain/Learning Rate": 8.022968249281686e-06, "Pretrain/Loss": 1.9926388263702393, "Pretrain/Loss (Raw)": 2.1040618419647217, "Pretrain/Step": 7109, "Pretrain/Step Time": 8.487253475934267} +{"Pretrain/Learning Rate": 8.01673645225367e-06, "Pretrain/Loss": 1.99375581741333, "Pretrain/Loss (Raw)": 2.1351046562194824, "Pretrain/Step": 7110, "Pretrain/Step Time": 8.486627042293549} +{"Pretrain/Learning Rate": 8.010506614239139e-06, "Pretrain/Loss": 1.994511604309082, "Pretrain/Loss (Raw)": 2.0014939308166504, "Pretrain/Step": 7111, "Pretrain/Step Time": 8.48931890167296} +{"Pretrain/Learning Rate": 8.004278735956696e-06, "Pretrain/Loss": 1.9946637153625488, "Pretrain/Loss (Raw)": 1.9792758226394653, "Pretrain/Step": 7112, "Pretrain/Step Time": 8.493539117276669} +{"Pretrain/Learning Rate": 7.99805281812474e-06, "Pretrain/Loss": 1.99413001537323, "Pretrain/Loss (Raw)": 2.045736312866211, "Pretrain/Step": 7113, "Pretrain/Step Time": 8.484899451956153} +{"Pretrain/Learning Rate": 7.991828861461407e-06, "Pretrain/Loss": 1.9944629669189453, "Pretrain/Loss (Raw)": 1.9852924346923828, "Pretrain/Step": 7114, "Pretrain/Step Time": 8.486598482355475} +{"Pretrain/Learning Rate": 7.985606866684637e-06, "Pretrain/Loss": 1.9930928945541382, "Pretrain/Loss (Raw)": 1.9780958890914917, "Pretrain/Step": 7115, "Pretrain/Step Time": 8.486741302534938} +{"Pretrain/Learning Rate": 7.979386834512145e-06, "Pretrain/Loss": 1.9925960302352905, "Pretrain/Loss (Raw)": 1.893742561340332, "Pretrain/Step": 7116, "Pretrain/Step Time": 8.483218813315034} +{"Pretrain/Learning Rate": 7.97316876566139e-06, "Pretrain/Loss": 1.9908077716827393, "Pretrain/Loss (Raw)": 1.8773993253707886, "Pretrain/Step": 7117, "Pretrain/Step Time": 8.486687779426575} +{"Pretrain/Learning Rate": 7.966952660849636e-06, "Pretrain/Loss": 1.98978590965271, "Pretrain/Loss (Raw)": 1.833288311958313, "Pretrain/Step": 7118, "Pretrain/Step Time": 8.485505739226937} +{"Pretrain/Learning Rate": 7.960738520793914e-06, "Pretrain/Loss": 1.9871547222137451, "Pretrain/Loss (Raw)": 1.8379842042922974, "Pretrain/Step": 7119, "Pretrain/Step Time": 8.486129626631737} +{"Pretrain/Learning Rate": 7.954526346211008e-06, "Pretrain/Loss": 1.9903075695037842, "Pretrain/Loss (Raw)": 2.0247244834899902, "Pretrain/Step": 7120, "Pretrain/Step Time": 8.486101731657982} +{"Pretrain/Learning Rate": 7.948316137817497e-06, "Pretrain/Loss": 1.9906394481658936, "Pretrain/Loss (Raw)": 2.066458225250244, "Pretrain/Step": 7121, "Pretrain/Step Time": 8.490435184910893} +{"Pretrain/Learning Rate": 7.942107896329728e-06, "Pretrain/Loss": 1.9918845891952515, "Pretrain/Loss (Raw)": 2.0016417503356934, "Pretrain/Step": 7122, "Pretrain/Step Time": 8.490066349506378} +{"Pretrain/Learning Rate": 7.935901622463817e-06, "Pretrain/Loss": 1.9926087856292725, "Pretrain/Loss (Raw)": 2.1091275215148926, "Pretrain/Step": 7123, "Pretrain/Step Time": 8.489398166537285} +{"Pretrain/Learning Rate": 7.929697316935666e-06, "Pretrain/Loss": 1.993786334991455, "Pretrain/Loss (Raw)": 2.0541319847106934, "Pretrain/Step": 7124, "Pretrain/Step Time": 8.48859528824687} +{"Pretrain/Learning Rate": 7.923494980460924e-06, "Pretrain/Loss": 1.994499683380127, "Pretrain/Loss (Raw)": 1.993430733680725, "Pretrain/Step": 7125, "Pretrain/Step Time": 8.49011510796845} +{"Pretrain/Learning Rate": 7.917294613755034e-06, "Pretrain/Loss": 1.9951293468475342, "Pretrain/Loss (Raw)": 1.977877140045166, "Pretrain/Step": 7126, "Pretrain/Step Time": 8.489367444068193} +{"Pretrain/Learning Rate": 7.911096217533206e-06, "Pretrain/Loss": 1.9965307712554932, "Pretrain/Loss (Raw)": 2.087170362472534, "Pretrain/Step": 7127, "Pretrain/Step Time": 8.4880903493613} +{"Pretrain/Learning Rate": 7.904899792510426e-06, "Pretrain/Loss": 1.9975659847259521, "Pretrain/Loss (Raw)": 2.136601686477661, "Pretrain/Step": 7128, "Pretrain/Step Time": 8.496090948581696} +{"Pretrain/Learning Rate": 7.898705339401455e-06, "Pretrain/Loss": 1.9963388442993164, "Pretrain/Loss (Raw)": 1.9496768712997437, "Pretrain/Step": 7129, "Pretrain/Step Time": 8.493194848299026} +{"Pretrain/Learning Rate": 7.892512858920803e-06, "Pretrain/Loss": 1.9947556257247925, "Pretrain/Loss (Raw)": 1.8064281940460205, "Pretrain/Step": 7130, "Pretrain/Step Time": 8.496356571093202} +{"Pretrain/Learning Rate": 7.886322351782783e-06, "Pretrain/Loss": 1.9924166202545166, "Pretrain/Loss (Raw)": 1.9320034980773926, "Pretrain/Step": 7131, "Pretrain/Step Time": 8.491793140769005} +{"Pretrain/Learning Rate": 7.880133818701472e-06, "Pretrain/Loss": 1.9921774864196777, "Pretrain/Loss (Raw)": 1.9540555477142334, "Pretrain/Step": 7132, "Pretrain/Step Time": 8.492126317694783} +{"Pretrain/Learning Rate": 7.873947260390702e-06, "Pretrain/Loss": 1.992691993713379, "Pretrain/Loss (Raw)": 2.039900779724121, "Pretrain/Step": 7133, "Pretrain/Step Time": 8.489101994782686} +{"Pretrain/Learning Rate": 7.867762677564095e-06, "Pretrain/Loss": 1.9914846420288086, "Pretrain/Loss (Raw)": 1.8197669982910156, "Pretrain/Step": 7134, "Pretrain/Step Time": 8.492460018023849} +{"Pretrain/Learning Rate": 7.861580070935052e-06, "Pretrain/Loss": 1.9877433776855469, "Pretrain/Loss (Raw)": 1.7622737884521484, "Pretrain/Step": 7135, "Pretrain/Step Time": 8.493396731093526} +{"Pretrain/Learning Rate": 7.855399441216716e-06, "Pretrain/Loss": 1.9865164756774902, "Pretrain/Loss (Raw)": 1.857932448387146, "Pretrain/Step": 7136, "Pretrain/Step Time": 8.493426535278559} +{"Pretrain/Learning Rate": 7.84922078912203e-06, "Pretrain/Loss": 1.987521767616272, "Pretrain/Loss (Raw)": 2.055989980697632, "Pretrain/Step": 7137, "Pretrain/Step Time": 8.49075511470437} +{"Pretrain/Learning Rate": 7.843044115363698e-06, "Pretrain/Loss": 1.9870150089263916, "Pretrain/Loss (Raw)": 1.9384377002716064, "Pretrain/Step": 7138, "Pretrain/Step Time": 8.494975989684463} +{"Pretrain/Learning Rate": 7.8368694206542e-06, "Pretrain/Loss": 1.986268401145935, "Pretrain/Loss (Raw)": 2.0330817699432373, "Pretrain/Step": 7139, "Pretrain/Step Time": 8.494118435308337} +{"Pretrain/Learning Rate": 7.83069670570579e-06, "Pretrain/Loss": 1.9881012439727783, "Pretrain/Loss (Raw)": 2.085383892059326, "Pretrain/Step": 7140, "Pretrain/Step Time": 8.495221199467778} +{"Pretrain/Learning Rate": 7.824525971230472e-06, "Pretrain/Loss": 1.9877623319625854, "Pretrain/Loss (Raw)": 1.9244964122772217, "Pretrain/Step": 7141, "Pretrain/Step Time": 8.497559932991862} +{"Pretrain/Learning Rate": 7.818357217940048e-06, "Pretrain/Loss": 1.9865076541900635, "Pretrain/Loss (Raw)": 1.6930807828903198, "Pretrain/Step": 7142, "Pretrain/Step Time": 8.493845220655203} +{"Pretrain/Learning Rate": 7.81219044654608e-06, "Pretrain/Loss": 1.9865822792053223, "Pretrain/Loss (Raw)": 2.1015350818634033, "Pretrain/Step": 7143, "Pretrain/Step Time": 8.49373989738524} +{"Pretrain/Learning Rate": 7.806025657759904e-06, "Pretrain/Loss": 1.9867494106292725, "Pretrain/Loss (Raw)": 2.127490997314453, "Pretrain/Step": 7144, "Pretrain/Step Time": 8.495207684114575} +{"Pretrain/Learning Rate": 7.799862852292636e-06, "Pretrain/Loss": 1.9847514629364014, "Pretrain/Loss (Raw)": 1.9574929475784302, "Pretrain/Step": 7145, "Pretrain/Step Time": 8.49046828597784} +{"Pretrain/Learning Rate": 7.793702030855135e-06, "Pretrain/Loss": 1.9860107898712158, "Pretrain/Loss (Raw)": 2.1777238845825195, "Pretrain/Step": 7146, "Pretrain/Step Time": 8.491938434541225} +{"Pretrain/Learning Rate": 7.787543194158057e-06, "Pretrain/Loss": 1.9847207069396973, "Pretrain/Loss (Raw)": 1.96108877658844, "Pretrain/Step": 7147, "Pretrain/Step Time": 8.490170722827315} +{"Pretrain/Learning Rate": 7.78138634291183e-06, "Pretrain/Loss": 1.984062671661377, "Pretrain/Loss (Raw)": 1.8690011501312256, "Pretrain/Step": 7148, "Pretrain/Step Time": 8.48850885592401} +{"Pretrain/Learning Rate": 7.77523147782663e-06, "Pretrain/Loss": 1.9840936660766602, "Pretrain/Loss (Raw)": 1.989743709564209, "Pretrain/Step": 7149, "Pretrain/Step Time": 8.487899865955114} +{"Pretrain/Learning Rate": 7.769078599612434e-06, "Pretrain/Loss": 1.984014868736267, "Pretrain/Loss (Raw)": 2.0803258419036865, "Pretrain/Step": 7150, "Pretrain/Step Time": 8.487534845247865} +{"Pretrain/Learning Rate": 7.762927708978959e-06, "Pretrain/Loss": 1.9858450889587402, "Pretrain/Loss (Raw)": 2.2640388011932373, "Pretrain/Step": 7151, "Pretrain/Step Time": 8.483383676037192} +{"Pretrain/Learning Rate": 7.756778806635715e-06, "Pretrain/Loss": 1.9839813709259033, "Pretrain/Loss (Raw)": 1.9093681573867798, "Pretrain/Step": 7152, "Pretrain/Step Time": 8.483459211885929} +{"Pretrain/Learning Rate": 7.750631893291974e-06, "Pretrain/Loss": 1.983471393585205, "Pretrain/Loss (Raw)": 1.9589927196502686, "Pretrain/Step": 7153, "Pretrain/Step Time": 8.484932590276003} +{"Pretrain/Learning Rate": 7.744486969656784e-06, "Pretrain/Loss": 1.9843401908874512, "Pretrain/Loss (Raw)": 2.2086124420166016, "Pretrain/Step": 7154, "Pretrain/Step Time": 8.484288673847914} +{"Pretrain/Learning Rate": 7.738344036438958e-06, "Pretrain/Loss": 1.9812548160552979, "Pretrain/Loss (Raw)": 1.690611481666565, "Pretrain/Step": 7155, "Pretrain/Step Time": 8.485130304470658} +{"Pretrain/Learning Rate": 7.732203094347087e-06, "Pretrain/Loss": 1.9823273420333862, "Pretrain/Loss (Raw)": 2.1318559646606445, "Pretrain/Step": 7156, "Pretrain/Step Time": 8.484575318172574} +{"Pretrain/Learning Rate": 7.726064144089515e-06, "Pretrain/Loss": 1.9827415943145752, "Pretrain/Loss (Raw)": 2.0135998725891113, "Pretrain/Step": 7157, "Pretrain/Step Time": 8.487139968201518} +{"Pretrain/Learning Rate": 7.719927186374373e-06, "Pretrain/Loss": 1.982816219329834, "Pretrain/Loss (Raw)": 2.0565855503082275, "Pretrain/Step": 7158, "Pretrain/Step Time": 8.485651150345802} +{"Pretrain/Learning Rate": 7.713792221909558e-06, "Pretrain/Loss": 1.9836161136627197, "Pretrain/Loss (Raw)": 1.851800799369812, "Pretrain/Step": 7159, "Pretrain/Step Time": 8.488819297403097} +{"Pretrain/Learning Rate": 7.707659251402735e-06, "Pretrain/Loss": 1.9839210510253906, "Pretrain/Loss (Raw)": 2.1103813648223877, "Pretrain/Step": 7160, "Pretrain/Step Time": 8.487727293744683} +{"Pretrain/Learning Rate": 7.701528275561348e-06, "Pretrain/Loss": 1.9825522899627686, "Pretrain/Loss (Raw)": 1.92714262008667, "Pretrain/Step": 7161, "Pretrain/Step Time": 8.483381746336818} +{"Pretrain/Learning Rate": 7.695399295092587e-06, "Pretrain/Loss": 1.9827494621276855, "Pretrain/Loss (Raw)": 2.182605504989624, "Pretrain/Step": 7162, "Pretrain/Step Time": 8.482644936069846} +{"Pretrain/Learning Rate": 7.689272310703438e-06, "Pretrain/Loss": 1.9853543043136597, "Pretrain/Loss (Raw)": 2.1268560886383057, "Pretrain/Step": 7163, "Pretrain/Step Time": 8.481702748686075} +{"Pretrain/Learning Rate": 7.683147323100643e-06, "Pretrain/Loss": 1.9857357740402222, "Pretrain/Loss (Raw)": 2.07841157913208, "Pretrain/Step": 7164, "Pretrain/Step Time": 8.480412920936942} +{"Pretrain/Learning Rate": 7.677024332990725e-06, "Pretrain/Loss": 1.9863007068634033, "Pretrain/Loss (Raw)": 2.118849992752075, "Pretrain/Step": 7165, "Pretrain/Step Time": 8.47544227540493} +{"Pretrain/Learning Rate": 7.670903341079957e-06, "Pretrain/Loss": 1.9873032569885254, "Pretrain/Loss (Raw)": 2.1600968837738037, "Pretrain/Step": 7166, "Pretrain/Step Time": 8.48083446919918} +{"Pretrain/Learning Rate": 7.664784348074404e-06, "Pretrain/Loss": 1.9868943691253662, "Pretrain/Loss (Raw)": 2.001434087753296, "Pretrain/Step": 7167, "Pretrain/Step Time": 8.48170374147594} +{"Pretrain/Learning Rate": 7.65866735467988e-06, "Pretrain/Loss": 1.988844633102417, "Pretrain/Loss (Raw)": 1.960287094116211, "Pretrain/Step": 7168, "Pretrain/Step Time": 8.482461979612708} +{"Pretrain/Learning Rate": 7.652552361601981e-06, "Pretrain/Loss": 1.9884999990463257, "Pretrain/Loss (Raw)": 1.9672574996948242, "Pretrain/Step": 7169, "Pretrain/Step Time": 8.482638541609049} +{"Pretrain/Learning Rate": 7.64643936954607e-06, "Pretrain/Loss": 1.9879528284072876, "Pretrain/Loss (Raw)": 1.913196086883545, "Pretrain/Step": 7170, "Pretrain/Step Time": 8.48001491650939} +{"Pretrain/Learning Rate": 7.640328379217291e-06, "Pretrain/Loss": 1.9857032299041748, "Pretrain/Loss (Raw)": 1.8171908855438232, "Pretrain/Step": 7171, "Pretrain/Step Time": 8.479968389496207} +{"Pretrain/Learning Rate": 7.634219391320522e-06, "Pretrain/Loss": 1.9860255718231201, "Pretrain/Loss (Raw)": 1.8432259559631348, "Pretrain/Step": 7172, "Pretrain/Step Time": 8.48499096930027} +{"Pretrain/Learning Rate": 7.628112406560442e-06, "Pretrain/Loss": 1.9861936569213867, "Pretrain/Loss (Raw)": 2.014986753463745, "Pretrain/Step": 7173, "Pretrain/Step Time": 8.480746783316135} +{"Pretrain/Learning Rate": 7.622007425641492e-06, "Pretrain/Loss": 1.9877707958221436, "Pretrain/Loss (Raw)": 1.9917762279510498, "Pretrain/Step": 7174, "Pretrain/Step Time": 8.477108234539628} +{"Pretrain/Learning Rate": 7.615904449267877e-06, "Pretrain/Loss": 1.988814353942871, "Pretrain/Loss (Raw)": 2.22597074508667, "Pretrain/Step": 7175, "Pretrain/Step Time": 8.479864098131657} +{"Pretrain/Learning Rate": 7.609803478143576e-06, "Pretrain/Loss": 1.9874420166015625, "Pretrain/Loss (Raw)": 1.8697326183319092, "Pretrain/Step": 7176, "Pretrain/Step Time": 8.4782700445503} +{"Pretrain/Learning Rate": 7.603704512972343e-06, "Pretrain/Loss": 1.9892888069152832, "Pretrain/Loss (Raw)": 2.0547220706939697, "Pretrain/Step": 7177, "Pretrain/Step Time": 8.480640172958374} +{"Pretrain/Learning Rate": 7.59760755445767e-06, "Pretrain/Loss": 1.9884907007217407, "Pretrain/Loss (Raw)": 1.9550557136535645, "Pretrain/Step": 7178, "Pretrain/Step Time": 8.479969514533877} +{"Pretrain/Learning Rate": 7.59151260330285e-06, "Pretrain/Loss": 1.9886400699615479, "Pretrain/Loss (Raw)": 1.8193004131317139, "Pretrain/Step": 7179, "Pretrain/Step Time": 8.480724988505244} +{"Pretrain/Learning Rate": 7.585419660210935e-06, "Pretrain/Loss": 1.9891130924224854, "Pretrain/Loss (Raw)": 2.1190335750579834, "Pretrain/Step": 7180, "Pretrain/Step Time": 8.47506577335298} +{"Pretrain/Learning Rate": 7.579328725884749e-06, "Pretrain/Loss": 1.9908946752548218, "Pretrain/Loss (Raw)": 2.13478422164917, "Pretrain/Step": 7181, "Pretrain/Step Time": 8.473542807623744} +{"Pretrain/Learning Rate": 7.573239801026863e-06, "Pretrain/Loss": 1.991281509399414, "Pretrain/Loss (Raw)": 2.11934232711792, "Pretrain/Step": 7182, "Pretrain/Step Time": 8.468814639374614} +{"Pretrain/Learning Rate": 7.5671528863396515e-06, "Pretrain/Loss": 1.9915947914123535, "Pretrain/Loss (Raw)": 2.0280582904815674, "Pretrain/Step": 7183, "Pretrain/Step Time": 8.474137028679252} +{"Pretrain/Learning Rate": 7.561067982525222e-06, "Pretrain/Loss": 1.9907859563827515, "Pretrain/Loss (Raw)": 2.032320737838745, "Pretrain/Step": 7184, "Pretrain/Step Time": 8.473660388961434} +{"Pretrain/Learning Rate": 7.554985090285468e-06, "Pretrain/Loss": 1.9899547100067139, "Pretrain/Loss (Raw)": 2.0180165767669678, "Pretrain/Step": 7185, "Pretrain/Step Time": 8.47819298505783} +{"Pretrain/Learning Rate": 7.548904210322058e-06, "Pretrain/Loss": 1.9908677339553833, "Pretrain/Loss (Raw)": 2.174241781234741, "Pretrain/Step": 7186, "Pretrain/Step Time": 8.479022385552526} +{"Pretrain/Learning Rate": 7.542825343336418e-06, "Pretrain/Loss": 1.9916186332702637, "Pretrain/Loss (Raw)": 1.928965449333191, "Pretrain/Step": 7187, "Pretrain/Step Time": 8.478839477524161} +{"Pretrain/Learning Rate": 7.536748490029736e-06, "Pretrain/Loss": 1.9921634197235107, "Pretrain/Loss (Raw)": 1.8597793579101562, "Pretrain/Step": 7188, "Pretrain/Step Time": 8.48251729272306} +{"Pretrain/Learning Rate": 7.530673651102976e-06, "Pretrain/Loss": 1.9933956861495972, "Pretrain/Loss (Raw)": 2.2017822265625, "Pretrain/Step": 7189, "Pretrain/Step Time": 8.48011476173997} +{"Pretrain/Learning Rate": 7.5246008272568725e-06, "Pretrain/Loss": 1.995124340057373, "Pretrain/Loss (Raw)": 2.064546585083008, "Pretrain/Step": 7190, "Pretrain/Step Time": 8.479456592351198} +{"Pretrain/Learning Rate": 7.518530019191921e-06, "Pretrain/Loss": 1.9944708347320557, "Pretrain/Loss (Raw)": 1.93303382396698, "Pretrain/Step": 7191, "Pretrain/Step Time": 8.47870509326458} +{"Pretrain/Learning Rate": 7.512461227608397e-06, "Pretrain/Loss": 1.994140863418579, "Pretrain/Loss (Raw)": 2.046128988265991, "Pretrain/Step": 7192, "Pretrain/Step Time": 8.480498313903809} +{"Pretrain/Learning Rate": 7.506394453206317e-06, "Pretrain/Loss": 1.995341181755066, "Pretrain/Loss (Raw)": 2.1567859649658203, "Pretrain/Step": 7193, "Pretrain/Step Time": 8.483854871243238} +{"Pretrain/Learning Rate": 7.500329696685488e-06, "Pretrain/Loss": 1.9963030815124512, "Pretrain/Loss (Raw)": 1.990380883216858, "Pretrain/Step": 7194, "Pretrain/Step Time": 8.486039739102125} +{"Pretrain/Learning Rate": 7.49426695874548e-06, "Pretrain/Loss": 1.9957534074783325, "Pretrain/Loss (Raw)": 2.06596302986145, "Pretrain/Step": 7195, "Pretrain/Step Time": 8.486081076785922} +{"Pretrain/Learning Rate": 7.488206240085627e-06, "Pretrain/Loss": 1.995924949645996, "Pretrain/Loss (Raw)": 2.1425888538360596, "Pretrain/Step": 7196, "Pretrain/Step Time": 8.485010555014014} +{"Pretrain/Learning Rate": 7.482147541405035e-06, "Pretrain/Loss": 1.996598482131958, "Pretrain/Loss (Raw)": 1.9129700660705566, "Pretrain/Step": 7197, "Pretrain/Step Time": 8.48841148801148} +{"Pretrain/Learning Rate": 7.4760908634025624e-06, "Pretrain/Loss": 1.9956153631210327, "Pretrain/Loss (Raw)": 1.7593094110488892, "Pretrain/Step": 7198, "Pretrain/Step Time": 8.479779506102204} +{"Pretrain/Learning Rate": 7.4700362067768595e-06, "Pretrain/Loss": 1.9990801811218262, "Pretrain/Loss (Raw)": 2.214484691619873, "Pretrain/Step": 7199, "Pretrain/Step Time": 8.480798637494445} +{"Pretrain/Learning Rate": 7.46398357222631e-06, "Pretrain/Loss": 2.0004539489746094, "Pretrain/Loss (Raw)": 2.148237705230713, "Pretrain/Step": 7200, "Pretrain/Step Time": 8.479513956233859} +{"Pretrain/Learning Rate": 7.457932960449093e-06, "Pretrain/Loss": 1.9986028671264648, "Pretrain/Loss (Raw)": 1.7968484163284302, "Pretrain/Step": 7201, "Pretrain/Step Time": 8.48159639723599} +{"Pretrain/Learning Rate": 7.4518843721431446e-06, "Pretrain/Loss": 1.997440218925476, "Pretrain/Loss (Raw)": 1.9216127395629883, "Pretrain/Step": 7202, "Pretrain/Step Time": 8.484463045373559} +{"Pretrain/Learning Rate": 7.445837808006173e-06, "Pretrain/Loss": 1.999272346496582, "Pretrain/Loss (Raw)": 2.1914761066436768, "Pretrain/Step": 7203, "Pretrain/Step Time": 8.487779149785638} +{"Pretrain/Learning Rate": 7.439793268735635e-06, "Pretrain/Loss": 1.9998688697814941, "Pretrain/Loss (Raw)": 2.108320474624634, "Pretrain/Step": 7204, "Pretrain/Step Time": 8.48635902442038} +{"Pretrain/Learning Rate": 7.433750755028773e-06, "Pretrain/Loss": 2.000246286392212, "Pretrain/Loss (Raw)": 2.2591335773468018, "Pretrain/Step": 7205, "Pretrain/Step Time": 8.486736902967095} +{"Pretrain/Learning Rate": 7.4277102675825885e-06, "Pretrain/Loss": 1.9996689558029175, "Pretrain/Loss (Raw)": 2.028750419616699, "Pretrain/Step": 7206, "Pretrain/Step Time": 8.489883417263627} +{"Pretrain/Learning Rate": 7.4216718070938465e-06, "Pretrain/Loss": 2.0003280639648438, "Pretrain/Loss (Raw)": 2.102689504623413, "Pretrain/Step": 7207, "Pretrain/Step Time": 8.49334179237485} +{"Pretrain/Learning Rate": 7.415635374259094e-06, "Pretrain/Loss": 2.0029125213623047, "Pretrain/Loss (Raw)": 2.104072332382202, "Pretrain/Step": 7208, "Pretrain/Step Time": 8.489889305084944} +{"Pretrain/Learning Rate": 7.409600969774613e-06, "Pretrain/Loss": 2.003983497619629, "Pretrain/Loss (Raw)": 2.136286497116089, "Pretrain/Step": 7209, "Pretrain/Step Time": 8.490848693996668} +{"Pretrain/Learning Rate": 7.4035685943364795e-06, "Pretrain/Loss": 2.003376007080078, "Pretrain/Loss (Raw)": 2.056039333343506, "Pretrain/Step": 7210, "Pretrain/Step Time": 8.49292274005711} +{"Pretrain/Learning Rate": 7.397538248640526e-06, "Pretrain/Loss": 2.001828908920288, "Pretrain/Loss (Raw)": 1.841726541519165, "Pretrain/Step": 7211, "Pretrain/Step Time": 8.49157639592886} +{"Pretrain/Learning Rate": 7.391509933382345e-06, "Pretrain/Loss": 2.000894546508789, "Pretrain/Loss (Raw)": 1.9643583297729492, "Pretrain/Step": 7212, "Pretrain/Step Time": 8.491340978071094} +{"Pretrain/Learning Rate": 7.385483649257319e-06, "Pretrain/Loss": 1.9998559951782227, "Pretrain/Loss (Raw)": 2.088031768798828, "Pretrain/Step": 7213, "Pretrain/Step Time": 8.49252406321466} +{"Pretrain/Learning Rate": 7.3794593969605505e-06, "Pretrain/Loss": 1.999801516532898, "Pretrain/Loss (Raw)": 2.0474853515625, "Pretrain/Step": 7214, "Pretrain/Step Time": 8.494332406669855} +{"Pretrain/Learning Rate": 7.373437177186951e-06, "Pretrain/Loss": 2.0005550384521484, "Pretrain/Loss (Raw)": 1.968754529953003, "Pretrain/Step": 7215, "Pretrain/Step Time": 8.492798937484622} +{"Pretrain/Learning Rate": 7.367416990631188e-06, "Pretrain/Loss": 2.000807523727417, "Pretrain/Loss (Raw)": 2.027059555053711, "Pretrain/Step": 7216, "Pretrain/Step Time": 8.491048755124211} +{"Pretrain/Learning Rate": 7.361398837987668e-06, "Pretrain/Loss": 2.0028839111328125, "Pretrain/Loss (Raw)": 2.0390756130218506, "Pretrain/Step": 7217, "Pretrain/Step Time": 8.494977731257677} +{"Pretrain/Learning Rate": 7.355382719950593e-06, "Pretrain/Loss": 2.002063274383545, "Pretrain/Loss (Raw)": 1.9524081945419312, "Pretrain/Step": 7218, "Pretrain/Step Time": 8.490743279457092} +{"Pretrain/Learning Rate": 7.34936863721393e-06, "Pretrain/Loss": 2.0025792121887207, "Pretrain/Loss (Raw)": 1.9507344961166382, "Pretrain/Step": 7219, "Pretrain/Step Time": 8.495015541091561} +{"Pretrain/Learning Rate": 7.343356590471384e-06, "Pretrain/Loss": 2.0026168823242188, "Pretrain/Loss (Raw)": 1.9683419466018677, "Pretrain/Step": 7220, "Pretrain/Step Time": 8.495594434440136} +{"Pretrain/Learning Rate": 7.337346580416449e-06, "Pretrain/Loss": 2.002725601196289, "Pretrain/Loss (Raw)": 2.1003053188323975, "Pretrain/Step": 7221, "Pretrain/Step Time": 8.492920005694032} +{"Pretrain/Learning Rate": 7.33133860774238e-06, "Pretrain/Loss": 2.003964424133301, "Pretrain/Loss (Raw)": 1.9312933683395386, "Pretrain/Step": 7222, "Pretrain/Step Time": 8.492767402902246} +{"Pretrain/Learning Rate": 7.325332673142193e-06, "Pretrain/Loss": 2.003787040710449, "Pretrain/Loss (Raw)": 1.962258219718933, "Pretrain/Step": 7223, "Pretrain/Step Time": 8.491502678021789} +{"Pretrain/Learning Rate": 7.319328777308679e-06, "Pretrain/Loss": 2.0036423206329346, "Pretrain/Loss (Raw)": 1.8770872354507446, "Pretrain/Step": 7224, "Pretrain/Step Time": 8.49188338406384} +{"Pretrain/Learning Rate": 7.313326920934368e-06, "Pretrain/Loss": 2.0039944648742676, "Pretrain/Loss (Raw)": 2.022165298461914, "Pretrain/Step": 7225, "Pretrain/Step Time": 8.49042358994484} +{"Pretrain/Learning Rate": 7.3073271047115834e-06, "Pretrain/Loss": 2.0032219886779785, "Pretrain/Loss (Raw)": 1.9063252210617065, "Pretrain/Step": 7226, "Pretrain/Step Time": 8.491744181141257} +{"Pretrain/Learning Rate": 7.3013293293323985e-06, "Pretrain/Loss": 2.0020639896392822, "Pretrain/Loss (Raw)": 1.938236951828003, "Pretrain/Step": 7227, "Pretrain/Step Time": 8.491157924756408} +{"Pretrain/Learning Rate": 7.295333595488657e-06, "Pretrain/Loss": 2.0020482540130615, "Pretrain/Loss (Raw)": 1.8515105247497559, "Pretrain/Step": 7228, "Pretrain/Step Time": 8.490982301533222} +{"Pretrain/Learning Rate": 7.28933990387197e-06, "Pretrain/Loss": 2.000709056854248, "Pretrain/Loss (Raw)": 1.7906177043914795, "Pretrain/Step": 7229, "Pretrain/Step Time": 8.489055948331952} +{"Pretrain/Learning Rate": 7.283348255173691e-06, "Pretrain/Loss": 2.00369930267334, "Pretrain/Loss (Raw)": 2.138080358505249, "Pretrain/Step": 7230, "Pretrain/Step Time": 8.486567357555032} +{"Pretrain/Learning Rate": 7.277358650084967e-06, "Pretrain/Loss": 2.0035133361816406, "Pretrain/Loss (Raw)": 2.0414927005767822, "Pretrain/Step": 7231, "Pretrain/Step Time": 8.487308042123914} +{"Pretrain/Learning Rate": 7.271371089296702e-06, "Pretrain/Loss": 2.0041165351867676, "Pretrain/Loss (Raw)": 1.9617692232131958, "Pretrain/Step": 7232, "Pretrain/Step Time": 8.486080290749669} +{"Pretrain/Learning Rate": 7.2653855734995445e-06, "Pretrain/Loss": 2.0059332847595215, "Pretrain/Loss (Raw)": 1.9643466472625732, "Pretrain/Step": 7233, "Pretrain/Step Time": 8.481119316071272} +{"Pretrain/Learning Rate": 7.25940210338393e-06, "Pretrain/Loss": 2.006164073944092, "Pretrain/Loss (Raw)": 2.121741533279419, "Pretrain/Step": 7234, "Pretrain/Step Time": 8.483055045828223} +{"Pretrain/Learning Rate": 7.253420679640055e-06, "Pretrain/Loss": 2.00434947013855, "Pretrain/Loss (Raw)": 1.8940424919128418, "Pretrain/Step": 7235, "Pretrain/Step Time": 8.482651572674513} +{"Pretrain/Learning Rate": 7.247441302957858e-06, "Pretrain/Loss": 2.004124402999878, "Pretrain/Loss (Raw)": 1.9591995477676392, "Pretrain/Step": 7236, "Pretrain/Step Time": 8.484538933262229} +{"Pretrain/Learning Rate": 7.241463974027071e-06, "Pretrain/Loss": 2.0036401748657227, "Pretrain/Loss (Raw)": 2.042064666748047, "Pretrain/Step": 7237, "Pretrain/Step Time": 8.483971778303385} +{"Pretrain/Learning Rate": 7.2354886935371705e-06, "Pretrain/Loss": 2.003789186477661, "Pretrain/Loss (Raw)": 2.154191732406616, "Pretrain/Step": 7238, "Pretrain/Step Time": 8.487412130460143} +{"Pretrain/Learning Rate": 7.229515462177408e-06, "Pretrain/Loss": 2.0025064945220947, "Pretrain/Loss (Raw)": 1.8372974395751953, "Pretrain/Step": 7239, "Pretrain/Step Time": 8.486363837495446} +{"Pretrain/Learning Rate": 7.223544280636801e-06, "Pretrain/Loss": 2.0032033920288086, "Pretrain/Loss (Raw)": 2.0684654712677, "Pretrain/Step": 7240, "Pretrain/Step Time": 8.486046854406595} +{"Pretrain/Learning Rate": 7.217575149604105e-06, "Pretrain/Loss": 2.0023341178894043, "Pretrain/Loss (Raw)": 1.9344768524169922, "Pretrain/Step": 7241, "Pretrain/Step Time": 8.486229360103607} +{"Pretrain/Learning Rate": 7.211608069767867e-06, "Pretrain/Loss": 2.0027623176574707, "Pretrain/Loss (Raw)": 2.04010009765625, "Pretrain/Step": 7242, "Pretrain/Step Time": 8.484869653359056} +{"Pretrain/Learning Rate": 7.205643041816387e-06, "Pretrain/Loss": 2.0041046142578125, "Pretrain/Loss (Raw)": 2.1499345302581787, "Pretrain/Step": 7243, "Pretrain/Step Time": 8.485571945086122} +{"Pretrain/Learning Rate": 7.199680066437728e-06, "Pretrain/Loss": 2.004481315612793, "Pretrain/Loss (Raw)": 1.9419500827789307, "Pretrain/Step": 7244, "Pretrain/Step Time": 8.484691720455885} +{"Pretrain/Learning Rate": 7.193719144319727e-06, "Pretrain/Loss": 2.0060153007507324, "Pretrain/Loss (Raw)": 2.0737357139587402, "Pretrain/Step": 7245, "Pretrain/Step Time": 8.480740439146757} +{"Pretrain/Learning Rate": 7.187760276149955e-06, "Pretrain/Loss": 2.007688522338867, "Pretrain/Loss (Raw)": 2.047488212585449, "Pretrain/Step": 7246, "Pretrain/Step Time": 8.478569813072681} +{"Pretrain/Learning Rate": 7.181803462615777e-06, "Pretrain/Loss": 2.009586811065674, "Pretrain/Loss (Raw)": 2.080946445465088, "Pretrain/Step": 7247, "Pretrain/Step Time": 8.477920467033982} +{"Pretrain/Learning Rate": 7.175848704404309e-06, "Pretrain/Loss": 2.0104424953460693, "Pretrain/Loss (Raw)": 2.1342577934265137, "Pretrain/Step": 7248, "Pretrain/Step Time": 8.47739452123642} +{"Pretrain/Learning Rate": 7.1698960022024335e-06, "Pretrain/Loss": 2.009225368499756, "Pretrain/Loss (Raw)": 1.9106769561767578, "Pretrain/Step": 7249, "Pretrain/Step Time": 8.473754161968827} +{"Pretrain/Learning Rate": 7.163945356696783e-06, "Pretrain/Loss": 2.0090599060058594, "Pretrain/Loss (Raw)": 1.9804413318634033, "Pretrain/Step": 7250, "Pretrain/Step Time": 8.476973619312048} +{"Pretrain/Learning Rate": 7.157996768573774e-06, "Pretrain/Loss": 2.0083699226379395, "Pretrain/Loss (Raw)": 2.0208263397216797, "Pretrain/Step": 7251, "Pretrain/Step Time": 8.48090104199946} +{"Pretrain/Learning Rate": 7.152050238519561e-06, "Pretrain/Loss": 2.0075621604919434, "Pretrain/Loss (Raw)": 1.9507590532302856, "Pretrain/Step": 7252, "Pretrain/Step Time": 8.482462976127863} +{"Pretrain/Learning Rate": 7.146105767220082e-06, "Pretrain/Loss": 2.0085296630859375, "Pretrain/Loss (Raw)": 2.1172444820404053, "Pretrain/Step": 7253, "Pretrain/Step Time": 8.480948992073536} +{"Pretrain/Learning Rate": 7.140163355361027e-06, "Pretrain/Loss": 2.0094854831695557, "Pretrain/Loss (Raw)": 2.1002283096313477, "Pretrain/Step": 7254, "Pretrain/Step Time": 8.480443097651005} +{"Pretrain/Learning Rate": 7.134223003627852e-06, "Pretrain/Loss": 2.009255886077881, "Pretrain/Loss (Raw)": 2.057765483856201, "Pretrain/Step": 7255, "Pretrain/Step Time": 8.481835264712572} +{"Pretrain/Learning Rate": 7.128284712705782e-06, "Pretrain/Loss": 2.008511781692505, "Pretrain/Loss (Raw)": 2.0413641929626465, "Pretrain/Step": 7256, "Pretrain/Step Time": 8.47545925527811} +{"Pretrain/Learning Rate": 7.122348483279784e-06, "Pretrain/Loss": 2.0100932121276855, "Pretrain/Loss (Raw)": 2.1520938873291016, "Pretrain/Step": 7257, "Pretrain/Step Time": 8.478654397651553} +{"Pretrain/Learning Rate": 7.1164143160346055e-06, "Pretrain/Loss": 2.0122499465942383, "Pretrain/Loss (Raw)": 2.082505941390991, "Pretrain/Step": 7258, "Pretrain/Step Time": 8.477703236043453} +{"Pretrain/Learning Rate": 7.110482211654751e-06, "Pretrain/Loss": 2.0126233100891113, "Pretrain/Loss (Raw)": 1.9797790050506592, "Pretrain/Step": 7259, "Pretrain/Step Time": 8.47741243056953} +{"Pretrain/Learning Rate": 7.104552170824485e-06, "Pretrain/Loss": 2.0143749713897705, "Pretrain/Loss (Raw)": 2.178284168243408, "Pretrain/Step": 7260, "Pretrain/Step Time": 8.477289289236069} +{"Pretrain/Learning Rate": 7.0986241942278455e-06, "Pretrain/Loss": 2.01358962059021, "Pretrain/Loss (Raw)": 1.9393634796142578, "Pretrain/Step": 7261, "Pretrain/Step Time": 8.479363704100251} +{"Pretrain/Learning Rate": 7.092698282548607e-06, "Pretrain/Loss": 2.0168113708496094, "Pretrain/Loss (Raw)": 2.2321557998657227, "Pretrain/Step": 7262, "Pretrain/Step Time": 8.47740855999291} +{"Pretrain/Learning Rate": 7.086774436470328e-06, "Pretrain/Loss": 2.018674850463867, "Pretrain/Loss (Raw)": 2.0008108615875244, "Pretrain/Step": 7263, "Pretrain/Step Time": 8.479246312752366} +{"Pretrain/Learning Rate": 7.080852656676323e-06, "Pretrain/Loss": 2.0200116634368896, "Pretrain/Loss (Raw)": 2.029027223587036, "Pretrain/Step": 7264, "Pretrain/Step Time": 8.478105578571558} +{"Pretrain/Learning Rate": 7.074932943849677e-06, "Pretrain/Loss": 2.01859450340271, "Pretrain/Loss (Raw)": 1.8746097087860107, "Pretrain/Step": 7265, "Pretrain/Step Time": 8.480900477617979} +{"Pretrain/Learning Rate": 7.069015298673206e-06, "Pretrain/Loss": 2.019792318344116, "Pretrain/Loss (Raw)": 2.0917599201202393, "Pretrain/Step": 7266, "Pretrain/Step Time": 8.4758319593966} +{"Pretrain/Learning Rate": 7.063099721829528e-06, "Pretrain/Loss": 2.018360137939453, "Pretrain/Loss (Raw)": 1.849753975868225, "Pretrain/Step": 7267, "Pretrain/Step Time": 8.482133861631155} +{"Pretrain/Learning Rate": 7.057186214000985e-06, "Pretrain/Loss": 2.0161519050598145, "Pretrain/Loss (Raw)": 1.8027429580688477, "Pretrain/Step": 7268, "Pretrain/Step Time": 8.483811734244227} +{"Pretrain/Learning Rate": 7.0512747758697066e-06, "Pretrain/Loss": 2.014197826385498, "Pretrain/Loss (Raw)": 1.6743546724319458, "Pretrain/Step": 7269, "Pretrain/Step Time": 8.482551991939545} +{"Pretrain/Learning Rate": 7.045365408117574e-06, "Pretrain/Loss": 2.016655445098877, "Pretrain/Loss (Raw)": 2.0076403617858887, "Pretrain/Step": 7270, "Pretrain/Step Time": 8.485001288354397} +{"Pretrain/Learning Rate": 7.039458111426242e-06, "Pretrain/Loss": 2.015005111694336, "Pretrain/Loss (Raw)": 1.890299916267395, "Pretrain/Step": 7271, "Pretrain/Step Time": 8.487662987783551} +{"Pretrain/Learning Rate": 7.033552886477096e-06, "Pretrain/Loss": 2.014843463897705, "Pretrain/Loss (Raw)": 2.106799602508545, "Pretrain/Step": 7272, "Pretrain/Step Time": 8.48448882997036} +{"Pretrain/Learning Rate": 7.0276497339513105e-06, "Pretrain/Loss": 2.014838218688965, "Pretrain/Loss (Raw)": 1.9568653106689453, "Pretrain/Step": 7273, "Pretrain/Step Time": 8.48631731979549} +{"Pretrain/Learning Rate": 7.021748654529814e-06, "Pretrain/Loss": 2.013167381286621, "Pretrain/Loss (Raw)": 1.9638078212738037, "Pretrain/Step": 7274, "Pretrain/Step Time": 8.485822966322303} +{"Pretrain/Learning Rate": 7.015849648893288e-06, "Pretrain/Loss": 2.0125770568847656, "Pretrain/Loss (Raw)": 1.8855236768722534, "Pretrain/Step": 7275, "Pretrain/Step Time": 8.48693485558033} +{"Pretrain/Learning Rate": 7.009952717722191e-06, "Pretrain/Loss": 2.014949321746826, "Pretrain/Loss (Raw)": 2.1726772785186768, "Pretrain/Step": 7276, "Pretrain/Step Time": 8.484989831224084} +{"Pretrain/Learning Rate": 7.004057861696728e-06, "Pretrain/Loss": 2.0142219066619873, "Pretrain/Loss (Raw)": 1.896622896194458, "Pretrain/Step": 7277, "Pretrain/Step Time": 8.484394853934646} +{"Pretrain/Learning Rate": 6.998165081496863e-06, "Pretrain/Loss": 2.0139174461364746, "Pretrain/Loss (Raw)": 2.0413596630096436, "Pretrain/Step": 7278, "Pretrain/Step Time": 8.48433238454163} +{"Pretrain/Learning Rate": 6.992274377802327e-06, "Pretrain/Loss": 2.010964870452881, "Pretrain/Loss (Raw)": 1.886120319366455, "Pretrain/Step": 7279, "Pretrain/Step Time": 8.486878909170628} +{"Pretrain/Learning Rate": 6.986385751292615e-06, "Pretrain/Loss": 2.0118608474731445, "Pretrain/Loss (Raw)": 2.0240511894226074, "Pretrain/Step": 7280, "Pretrain/Step Time": 8.490194998681545} +{"Pretrain/Learning Rate": 6.980499202646981e-06, "Pretrain/Loss": 2.012673854827881, "Pretrain/Loss (Raw)": 2.0630362033843994, "Pretrain/Step": 7281, "Pretrain/Step Time": 8.489874105900526} +{"Pretrain/Learning Rate": 6.974614732544427e-06, "Pretrain/Loss": 2.0081098079681396, "Pretrain/Loss (Raw)": 1.6244391202926636, "Pretrain/Step": 7282, "Pretrain/Step Time": 8.492969386279583} +{"Pretrain/Learning Rate": 6.9687323416637335e-06, "Pretrain/Loss": 2.008903980255127, "Pretrain/Loss (Raw)": 1.792242407798767, "Pretrain/Step": 7283, "Pretrain/Step Time": 8.494934303686023} +{"Pretrain/Learning Rate": 6.962852030683423e-06, "Pretrain/Loss": 2.007333517074585, "Pretrain/Loss (Raw)": 1.930859923362732, "Pretrain/Step": 7284, "Pretrain/Step Time": 8.4947488643229} +{"Pretrain/Learning Rate": 6.95697380028179e-06, "Pretrain/Loss": 2.0063774585723877, "Pretrain/Loss (Raw)": 1.891206979751587, "Pretrain/Step": 7285, "Pretrain/Step Time": 8.493413710966706} +{"Pretrain/Learning Rate": 6.951097651136889e-06, "Pretrain/Loss": 2.00406551361084, "Pretrain/Loss (Raw)": 1.7606316804885864, "Pretrain/Step": 7286, "Pretrain/Step Time": 8.496532421559095} +{"Pretrain/Learning Rate": 6.9452235839265385e-06, "Pretrain/Loss": 2.0042836666107178, "Pretrain/Loss (Raw)": 1.8797703981399536, "Pretrain/Step": 7287, "Pretrain/Step Time": 8.495632139965892} +{"Pretrain/Learning Rate": 6.9393515993282976e-06, "Pretrain/Loss": 2.0035629272460938, "Pretrain/Loss (Raw)": 2.018097162246704, "Pretrain/Step": 7288, "Pretrain/Step Time": 8.497872499749064} +{"Pretrain/Learning Rate": 6.9334816980195005e-06, "Pretrain/Loss": 2.004157066345215, "Pretrain/Loss (Raw)": 2.00321364402771, "Pretrain/Step": 7289, "Pretrain/Step Time": 8.49817061983049} +{"Pretrain/Learning Rate": 6.927613880677239e-06, "Pretrain/Loss": 2.0027947425842285, "Pretrain/Loss (Raw)": 2.0082108974456787, "Pretrain/Step": 7290, "Pretrain/Step Time": 8.494130820035934} +{"Pretrain/Learning Rate": 6.921748147978368e-06, "Pretrain/Loss": 2.0023155212402344, "Pretrain/Loss (Raw)": 2.0655548572540283, "Pretrain/Step": 7291, "Pretrain/Step Time": 8.4984376039356} +{"Pretrain/Learning Rate": 6.915884500599501e-06, "Pretrain/Loss": 2.0016369819641113, "Pretrain/Loss (Raw)": 1.991540789604187, "Pretrain/Step": 7292, "Pretrain/Step Time": 8.49901189468801} +{"Pretrain/Learning Rate": 6.910022939216995e-06, "Pretrain/Loss": 2.000792980194092, "Pretrain/Loss (Raw)": 2.0107860565185547, "Pretrain/Step": 7293, "Pretrain/Step Time": 8.49830605275929} +{"Pretrain/Learning Rate": 6.904163464506985e-06, "Pretrain/Loss": 1.9988884925842285, "Pretrain/Loss (Raw)": 1.9163377285003662, "Pretrain/Step": 7294, "Pretrain/Step Time": 8.494246331974864} +{"Pretrain/Learning Rate": 6.8983060771453614e-06, "Pretrain/Loss": 1.9980924129486084, "Pretrain/Loss (Raw)": 1.8995438814163208, "Pretrain/Step": 7295, "Pretrain/Step Time": 8.495027860626578} +{"Pretrain/Learning Rate": 6.892450777807769e-06, "Pretrain/Loss": 1.998457908630371, "Pretrain/Loss (Raw)": 2.007071018218994, "Pretrain/Step": 7296, "Pretrain/Step Time": 8.49188781157136} +{"Pretrain/Learning Rate": 6.886597567169617e-06, "Pretrain/Loss": 1.9996249675750732, "Pretrain/Loss (Raw)": 2.116631507873535, "Pretrain/Step": 7297, "Pretrain/Step Time": 8.496120691299438} +{"Pretrain/Learning Rate": 6.880746445906075e-06, "Pretrain/Loss": 2.0009946823120117, "Pretrain/Loss (Raw)": 2.0885303020477295, "Pretrain/Step": 7298, "Pretrain/Step Time": 8.496195340529084} +{"Pretrain/Learning Rate": 6.874897414692058e-06, "Pretrain/Loss": 2.001755714416504, "Pretrain/Loss (Raw)": 1.914579153060913, "Pretrain/Step": 7299, "Pretrain/Step Time": 8.498902421444654} +{"Pretrain/Learning Rate": 6.869050474202263e-06, "Pretrain/Loss": 2.0046586990356445, "Pretrain/Loss (Raw)": 2.214818000793457, "Pretrain/Step": 7300, "Pretrain/Step Time": 8.494562087580562} +{"Pretrain/Learning Rate": 6.863205625111113e-06, "Pretrain/Loss": 2.004699230194092, "Pretrain/Loss (Raw)": 2.0201878547668457, "Pretrain/Step": 7301, "Pretrain/Step Time": 8.499180223792791} +{"Pretrain/Learning Rate": 6.857362868092823e-06, "Pretrain/Loss": 2.0044193267822266, "Pretrain/Loss (Raw)": 1.9559463262557983, "Pretrain/Step": 7302, "Pretrain/Step Time": 8.499908005818725} +{"Pretrain/Learning Rate": 6.851522203821359e-06, "Pretrain/Loss": 2.003190279006958, "Pretrain/Loss (Raw)": 2.0686707496643066, "Pretrain/Step": 7303, "Pretrain/Step Time": 8.500291980803013} +{"Pretrain/Learning Rate": 6.8456836329704205e-06, "Pretrain/Loss": 2.004492998123169, "Pretrain/Loss (Raw)": 2.0364599227905273, "Pretrain/Step": 7304, "Pretrain/Step Time": 8.498847445473075} +{"Pretrain/Learning Rate": 6.839847156213497e-06, "Pretrain/Loss": 2.004361629486084, "Pretrain/Loss (Raw)": 2.037916421890259, "Pretrain/Step": 7305, "Pretrain/Step Time": 8.49950553663075} +{"Pretrain/Learning Rate": 6.834012774223822e-06, "Pretrain/Loss": 2.0054850578308105, "Pretrain/Loss (Raw)": 2.0988354682922363, "Pretrain/Step": 7306, "Pretrain/Step Time": 8.498707555234432} +{"Pretrain/Learning Rate": 6.8281804876743875e-06, "Pretrain/Loss": 2.0066967010498047, "Pretrain/Loss (Raw)": 1.974395751953125, "Pretrain/Step": 7307, "Pretrain/Step Time": 8.50114606320858} +{"Pretrain/Learning Rate": 6.822350297237959e-06, "Pretrain/Loss": 2.0057480335235596, "Pretrain/Loss (Raw)": 1.997610330581665, "Pretrain/Step": 7308, "Pretrain/Step Time": 8.501874538138509} +{"Pretrain/Learning Rate": 6.816522203587025e-06, "Pretrain/Loss": 2.0032389163970947, "Pretrain/Loss (Raw)": 1.8136082887649536, "Pretrain/Step": 7309, "Pretrain/Step Time": 8.504931088536978} +{"Pretrain/Learning Rate": 6.810696207393865e-06, "Pretrain/Loss": 2.00262451171875, "Pretrain/Loss (Raw)": 2.0407137870788574, "Pretrain/Step": 7310, "Pretrain/Step Time": 8.507272601127625} +{"Pretrain/Learning Rate": 6.804872309330506e-06, "Pretrain/Loss": 2.0022706985473633, "Pretrain/Loss (Raw)": 1.9827624559402466, "Pretrain/Step": 7311, "Pretrain/Step Time": 8.50239266268909} +{"Pretrain/Learning Rate": 6.799050510068733e-06, "Pretrain/Loss": 2.002748727798462, "Pretrain/Loss (Raw)": 2.0934956073760986, "Pretrain/Step": 7312, "Pretrain/Step Time": 8.504678847268224} +{"Pretrain/Learning Rate": 6.793230810280094e-06, "Pretrain/Loss": 2.0026049613952637, "Pretrain/Loss (Raw)": 1.999637246131897, "Pretrain/Step": 7313, "Pretrain/Step Time": 8.501803018152714} +{"Pretrain/Learning Rate": 6.7874132106358734e-06, "Pretrain/Loss": 2.0005428791046143, "Pretrain/Loss (Raw)": 1.9103009700775146, "Pretrain/Step": 7314, "Pretrain/Step Time": 8.502141110599041} +{"Pretrain/Learning Rate": 6.781597711807141e-06, "Pretrain/Loss": 2.0033886432647705, "Pretrain/Loss (Raw)": 2.2931971549987793, "Pretrain/Step": 7315, "Pretrain/Step Time": 8.503077587112784} +{"Pretrain/Learning Rate": 6.775784314464717e-06, "Pretrain/Loss": 2.004660129547119, "Pretrain/Loss (Raw)": 2.02253794670105, "Pretrain/Step": 7316, "Pretrain/Step Time": 8.499791119247675} +{"Pretrain/Learning Rate": 6.76997301927916e-06, "Pretrain/Loss": 2.0046582221984863, "Pretrain/Loss (Raw)": 2.2015507221221924, "Pretrain/Step": 7317, "Pretrain/Step Time": 8.50083045475185} +{"Pretrain/Learning Rate": 6.764163826920808e-06, "Pretrain/Loss": 2.0051231384277344, "Pretrain/Loss (Raw)": 2.1240766048431396, "Pretrain/Step": 7318, "Pretrain/Step Time": 8.500657267868519} +{"Pretrain/Learning Rate": 6.75835673805976e-06, "Pretrain/Loss": 2.0028555393218994, "Pretrain/Loss (Raw)": 1.6427620649337769, "Pretrain/Step": 7319, "Pretrain/Step Time": 8.501030473038554} +{"Pretrain/Learning Rate": 6.752551753365843e-06, "Pretrain/Loss": 2.001988649368286, "Pretrain/Loss (Raw)": 1.9351533651351929, "Pretrain/Step": 7320, "Pretrain/Step Time": 8.497245743870735} +{"Pretrain/Learning Rate": 6.746748873508668e-06, "Pretrain/Loss": 2.0009825229644775, "Pretrain/Loss (Raw)": 2.027994155883789, "Pretrain/Step": 7321, "Pretrain/Step Time": 8.49939687922597} +{"Pretrain/Learning Rate": 6.740948099157596e-06, "Pretrain/Loss": 2.0015676021575928, "Pretrain/Loss (Raw)": 2.0652859210968018, "Pretrain/Step": 7322, "Pretrain/Step Time": 8.50217772088945} +{"Pretrain/Learning Rate": 6.7351494309817434e-06, "Pretrain/Loss": 2.000976085662842, "Pretrain/Loss (Raw)": 1.9902523756027222, "Pretrain/Step": 7323, "Pretrain/Step Time": 8.500534484162927} +{"Pretrain/Learning Rate": 6.729352869649994e-06, "Pretrain/Loss": 2.00009822845459, "Pretrain/Loss (Raw)": 2.030208110809326, "Pretrain/Step": 7324, "Pretrain/Step Time": 8.503733927384019} +{"Pretrain/Learning Rate": 6.723558415830963e-06, "Pretrain/Loss": 1.9990811347961426, "Pretrain/Loss (Raw)": 1.7827874422073364, "Pretrain/Step": 7325, "Pretrain/Step Time": 8.500965548679233} +{"Pretrain/Learning Rate": 6.717766070193043e-06, "Pretrain/Loss": 2.001434803009033, "Pretrain/Loss (Raw)": 2.0605645179748535, "Pretrain/Step": 7326, "Pretrain/Step Time": 8.500604460015893} +{"Pretrain/Learning Rate": 6.7119758334043856e-06, "Pretrain/Loss": 2.00003981590271, "Pretrain/Loss (Raw)": 2.0359487533569336, "Pretrain/Step": 7327, "Pretrain/Step Time": 8.49749232083559} +{"Pretrain/Learning Rate": 6.706187706132888e-06, "Pretrain/Loss": 1.9988102912902832, "Pretrain/Loss (Raw)": 1.9908543825149536, "Pretrain/Step": 7328, "Pretrain/Step Time": 8.504016088321805} +{"Pretrain/Learning Rate": 6.700401689046218e-06, "Pretrain/Loss": 1.9999101161956787, "Pretrain/Loss (Raw)": 1.9376078844070435, "Pretrain/Step": 7329, "Pretrain/Step Time": 8.499718457460403} +{"Pretrain/Learning Rate": 6.6946177828117716e-06, "Pretrain/Loss": 1.9988285303115845, "Pretrain/Loss (Raw)": 1.7831989526748657, "Pretrain/Step": 7330, "Pretrain/Step Time": 8.495552757754922} +{"Pretrain/Learning Rate": 6.688835988096734e-06, "Pretrain/Loss": 1.995508074760437, "Pretrain/Loss (Raw)": 1.7664309740066528, "Pretrain/Step": 7331, "Pretrain/Step Time": 8.494662808254361} +{"Pretrain/Learning Rate": 6.683056305568036e-06, "Pretrain/Loss": 1.9944603443145752, "Pretrain/Loss (Raw)": 1.974216103553772, "Pretrain/Step": 7332, "Pretrain/Step Time": 8.497037747874856} +{"Pretrain/Learning Rate": 6.6772787358923476e-06, "Pretrain/Loss": 1.9920203685760498, "Pretrain/Loss (Raw)": 1.9468199014663696, "Pretrain/Step": 7333, "Pretrain/Step Time": 8.495027655735612} +{"Pretrain/Learning Rate": 6.671503279736122e-06, "Pretrain/Loss": 1.9922966957092285, "Pretrain/Loss (Raw)": 2.064114809036255, "Pretrain/Step": 7334, "Pretrain/Step Time": 8.498107220977545} +{"Pretrain/Learning Rate": 6.665729937765555e-06, "Pretrain/Loss": 1.9902260303497314, "Pretrain/Loss (Raw)": 1.8376637697219849, "Pretrain/Step": 7335, "Pretrain/Step Time": 8.496985577046871} +{"Pretrain/Learning Rate": 6.659958710646591e-06, "Pretrain/Loss": 1.9880675077438354, "Pretrain/Loss (Raw)": 1.8277722597122192, "Pretrain/Step": 7336, "Pretrain/Step Time": 8.49898593313992} +{"Pretrain/Learning Rate": 6.654189599044947e-06, "Pretrain/Loss": 1.9875109195709229, "Pretrain/Loss (Raw)": 2.0650441646575928, "Pretrain/Step": 7337, "Pretrain/Step Time": 8.496821835637093} +{"Pretrain/Learning Rate": 6.648422603626081e-06, "Pretrain/Loss": 1.9847910404205322, "Pretrain/Loss (Raw)": 1.7078782320022583, "Pretrain/Step": 7338, "Pretrain/Step Time": 8.49765831977129} +{"Pretrain/Learning Rate": 6.64265772505522e-06, "Pretrain/Loss": 1.9860706329345703, "Pretrain/Loss (Raw)": 2.0055243968963623, "Pretrain/Step": 7339, "Pretrain/Step Time": 8.497240709140897} +{"Pretrain/Learning Rate": 6.636894963997348e-06, "Pretrain/Loss": 1.9866878986358643, "Pretrain/Loss (Raw)": 2.043374538421631, "Pretrain/Step": 7340, "Pretrain/Step Time": 8.497917145490646} +{"Pretrain/Learning Rate": 6.63113432111718e-06, "Pretrain/Loss": 1.9861328601837158, "Pretrain/Loss (Raw)": 2.0169827938079834, "Pretrain/Step": 7341, "Pretrain/Step Time": 8.492420058697462} +{"Pretrain/Learning Rate": 6.625375797079214e-06, "Pretrain/Loss": 1.9845521450042725, "Pretrain/Loss (Raw)": 1.8451483249664307, "Pretrain/Step": 7342, "Pretrain/Step Time": 8.491166019812226} +{"Pretrain/Learning Rate": 6.619619392547693e-06, "Pretrain/Loss": 1.9847009181976318, "Pretrain/Loss (Raw)": 1.9878073930740356, "Pretrain/Step": 7343, "Pretrain/Step Time": 8.493236288428307} +{"Pretrain/Learning Rate": 6.6138651081866144e-06, "Pretrain/Loss": 1.9842236042022705, "Pretrain/Loss (Raw)": 1.9659680128097534, "Pretrain/Step": 7344, "Pretrain/Step Time": 8.49205251596868} +{"Pretrain/Learning Rate": 6.608112944659742e-06, "Pretrain/Loss": 1.9848384857177734, "Pretrain/Loss (Raw)": 2.1177797317504883, "Pretrain/Step": 7345, "Pretrain/Step Time": 8.491093279793859} +{"Pretrain/Learning Rate": 6.602362902630571e-06, "Pretrain/Loss": 1.9840421676635742, "Pretrain/Loss (Raw)": 1.850481390953064, "Pretrain/Step": 7346, "Pretrain/Step Time": 8.491565208882093} +{"Pretrain/Learning Rate": 6.596614982762373e-06, "Pretrain/Loss": 1.9855589866638184, "Pretrain/Loss (Raw)": 2.1448814868927, "Pretrain/Step": 7347, "Pretrain/Step Time": 8.484210571274161} +{"Pretrain/Learning Rate": 6.590869185718168e-06, "Pretrain/Loss": 1.986402988433838, "Pretrain/Loss (Raw)": 2.0763750076293945, "Pretrain/Step": 7348, "Pretrain/Step Time": 8.486792486160994} +{"Pretrain/Learning Rate": 6.5851255121607415e-06, "Pretrain/Loss": 1.9862067699432373, "Pretrain/Loss (Raw)": 2.0751919746398926, "Pretrain/Step": 7349, "Pretrain/Step Time": 8.486187752336264} +{"Pretrain/Learning Rate": 6.579383962752611e-06, "Pretrain/Loss": 1.9857172966003418, "Pretrain/Loss (Raw)": 1.8686219453811646, "Pretrain/Step": 7350, "Pretrain/Step Time": 8.486323157325387} +{"Pretrain/Learning Rate": 6.5736445381560705e-06, "Pretrain/Loss": 1.984928846359253, "Pretrain/Loss (Raw)": 1.8613427877426147, "Pretrain/Step": 7351, "Pretrain/Step Time": 8.485583052039146} +{"Pretrain/Learning Rate": 6.567907239033153e-06, "Pretrain/Loss": 1.9852235317230225, "Pretrain/Loss (Raw)": 1.914823055267334, "Pretrain/Step": 7352, "Pretrain/Step Time": 8.487620793282986} +{"Pretrain/Learning Rate": 6.562172066045655e-06, "Pretrain/Loss": 1.9841341972351074, "Pretrain/Loss (Raw)": 1.8827186822891235, "Pretrain/Step": 7353, "Pretrain/Step Time": 8.486284172162414} +{"Pretrain/Learning Rate": 6.556439019855132e-06, "Pretrain/Loss": 1.986084222793579, "Pretrain/Loss (Raw)": 2.155918598175049, "Pretrain/Step": 7354, "Pretrain/Step Time": 8.488124808296561} +{"Pretrain/Learning Rate": 6.550708101122885e-06, "Pretrain/Loss": 1.9860702753067017, "Pretrain/Loss (Raw)": 1.9364640712738037, "Pretrain/Step": 7355, "Pretrain/Step Time": 8.48832069709897} +{"Pretrain/Learning Rate": 6.544979310509983e-06, "Pretrain/Loss": 1.9873758554458618, "Pretrain/Loss (Raw)": 2.018622398376465, "Pretrain/Step": 7356, "Pretrain/Step Time": 8.489478195086122} +{"Pretrain/Learning Rate": 6.539252648677224e-06, "Pretrain/Loss": 1.9887356758117676, "Pretrain/Loss (Raw)": 1.9646861553192139, "Pretrain/Step": 7357, "Pretrain/Step Time": 8.487730314955115} +{"Pretrain/Learning Rate": 6.533528116285184e-06, "Pretrain/Loss": 1.987836241722107, "Pretrain/Loss (Raw)": 2.022946834564209, "Pretrain/Step": 7358, "Pretrain/Step Time": 8.490410564467311} +{"Pretrain/Learning Rate": 6.527805713994189e-06, "Pretrain/Loss": 1.9886527061462402, "Pretrain/Loss (Raw)": 2.1460070610046387, "Pretrain/Step": 7359, "Pretrain/Step Time": 8.492966201156378} +{"Pretrain/Learning Rate": 6.52208544246431e-06, "Pretrain/Loss": 1.9890929460525513, "Pretrain/Loss (Raw)": 2.0181126594543457, "Pretrain/Step": 7360, "Pretrain/Step Time": 8.490964761003852} +{"Pretrain/Learning Rate": 6.5163673023553915e-06, "Pretrain/Loss": 1.9875288009643555, "Pretrain/Loss (Raw)": 1.764130711555481, "Pretrain/Step": 7361, "Pretrain/Step Time": 8.491892224177718} +{"Pretrain/Learning Rate": 6.5106512943269995e-06, "Pretrain/Loss": 1.9873046875, "Pretrain/Loss (Raw)": 2.0930533409118652, "Pretrain/Step": 7362, "Pretrain/Step Time": 8.490145940333605} +{"Pretrain/Learning Rate": 6.504937419038485e-06, "Pretrain/Loss": 1.9889395236968994, "Pretrain/Loss (Raw)": 2.10330867767334, "Pretrain/Step": 7363, "Pretrain/Step Time": 8.487833023071289} +{"Pretrain/Learning Rate": 6.49922567714894e-06, "Pretrain/Loss": 1.9887564182281494, "Pretrain/Loss (Raw)": 1.935746431350708, "Pretrain/Step": 7364, "Pretrain/Step Time": 8.487754056230187} +{"Pretrain/Learning Rate": 6.493516069317218e-06, "Pretrain/Loss": 1.9886200428009033, "Pretrain/Loss (Raw)": 2.024632453918457, "Pretrain/Step": 7365, "Pretrain/Step Time": 8.486377572640777} +{"Pretrain/Learning Rate": 6.487808596201905e-06, "Pretrain/Loss": 1.9883770942687988, "Pretrain/Loss (Raw)": 2.1230790615081787, "Pretrain/Step": 7366, "Pretrain/Step Time": 8.484443359076977} +{"Pretrain/Learning Rate": 6.482103258461372e-06, "Pretrain/Loss": 1.9897067546844482, "Pretrain/Loss (Raw)": 2.007497787475586, "Pretrain/Step": 7367, "Pretrain/Step Time": 8.488238282501698} +{"Pretrain/Learning Rate": 6.476400056753715e-06, "Pretrain/Loss": 1.9889941215515137, "Pretrain/Loss (Raw)": 1.97724187374115, "Pretrain/Step": 7368, "Pretrain/Step Time": 8.487481335178018} +{"Pretrain/Learning Rate": 6.470698991736801e-06, "Pretrain/Loss": 1.9895286560058594, "Pretrain/Loss (Raw)": 2.0029022693634033, "Pretrain/Step": 7369, "Pretrain/Step Time": 8.489605562761426} +{"Pretrain/Learning Rate": 6.4650000640682465e-06, "Pretrain/Loss": 1.988063097000122, "Pretrain/Loss (Raw)": 1.8525086641311646, "Pretrain/Step": 7370, "Pretrain/Step Time": 8.487155817449093} +{"Pretrain/Learning Rate": 6.459303274405429e-06, "Pretrain/Loss": 1.9863442182540894, "Pretrain/Loss (Raw)": 1.9299265146255493, "Pretrain/Step": 7371, "Pretrain/Step Time": 8.488146398216486} +{"Pretrain/Learning Rate": 6.453608623405455e-06, "Pretrain/Loss": 1.9858819246292114, "Pretrain/Loss (Raw)": 1.8827630281448364, "Pretrain/Step": 7372, "Pretrain/Step Time": 8.488494975492358} +{"Pretrain/Learning Rate": 6.44791611172521e-06, "Pretrain/Loss": 1.984192967414856, "Pretrain/Loss (Raw)": 1.8575630187988281, "Pretrain/Step": 7373, "Pretrain/Step Time": 8.488784620538354} +{"Pretrain/Learning Rate": 6.442225740021321e-06, "Pretrain/Loss": 1.9843876361846924, "Pretrain/Loss (Raw)": 2.0724103450775146, "Pretrain/Step": 7374, "Pretrain/Step Time": 8.491276290267706} +{"Pretrain/Learning Rate": 6.436537508950171e-06, "Pretrain/Loss": 1.9841500520706177, "Pretrain/Loss (Raw)": 2.0505316257476807, "Pretrain/Step": 7375, "Pretrain/Step Time": 8.492234028875828} +{"Pretrain/Learning Rate": 6.430851419167896e-06, "Pretrain/Loss": 1.9819700717926025, "Pretrain/Loss (Raw)": 1.8552130460739136, "Pretrain/Step": 7376, "Pretrain/Step Time": 8.493084572255611} +{"Pretrain/Learning Rate": 6.42516747133039e-06, "Pretrain/Loss": 1.9820715188980103, "Pretrain/Loss (Raw)": 1.9236607551574707, "Pretrain/Step": 7377, "Pretrain/Step Time": 8.49298956990242} +{"Pretrain/Learning Rate": 6.419485666093283e-06, "Pretrain/Loss": 1.9823691844940186, "Pretrain/Loss (Raw)": 2.018547534942627, "Pretrain/Step": 7378, "Pretrain/Step Time": 8.493083320558071} +{"Pretrain/Learning Rate": 6.413806004111975e-06, "Pretrain/Loss": 1.980499267578125, "Pretrain/Loss (Raw)": 1.7814761400222778, "Pretrain/Step": 7379, "Pretrain/Step Time": 8.492623288184404} +{"Pretrain/Learning Rate": 6.408128486041612e-06, "Pretrain/Loss": 1.9821841716766357, "Pretrain/Loss (Raw)": 2.1664273738861084, "Pretrain/Step": 7380, "Pretrain/Step Time": 8.491618549451232} +{"Pretrain/Learning Rate": 6.402453112537094e-06, "Pretrain/Loss": 1.9808777570724487, "Pretrain/Loss (Raw)": 1.9500223398208618, "Pretrain/Step": 7381, "Pretrain/Step Time": 8.491082621738315} +{"Pretrain/Learning Rate": 6.396779884253082e-06, "Pretrain/Loss": 1.979914903640747, "Pretrain/Loss (Raw)": 1.9769922494888306, "Pretrain/Step": 7382, "Pretrain/Step Time": 8.491348849609494} +{"Pretrain/Learning Rate": 6.391108801843965e-06, "Pretrain/Loss": 1.979477882385254, "Pretrain/Loss (Raw)": 2.001807689666748, "Pretrain/Step": 7383, "Pretrain/Step Time": 8.493904134258628} +{"Pretrain/Learning Rate": 6.385439865963916e-06, "Pretrain/Loss": 1.9799110889434814, "Pretrain/Loss (Raw)": 2.096818685531616, "Pretrain/Step": 7384, "Pretrain/Step Time": 8.49276045896113} +{"Pretrain/Learning Rate": 6.379773077266829e-06, "Pretrain/Loss": 1.9787153005599976, "Pretrain/Loss (Raw)": 1.9990431070327759, "Pretrain/Step": 7385, "Pretrain/Step Time": 8.492998335510492} +{"Pretrain/Learning Rate": 6.374108436406373e-06, "Pretrain/Loss": 1.9780443906784058, "Pretrain/Loss (Raw)": 1.9966316223144531, "Pretrain/Step": 7386, "Pretrain/Step Time": 8.492427622899413} +{"Pretrain/Learning Rate": 6.368445944035972e-06, "Pretrain/Loss": 1.9790475368499756, "Pretrain/Loss (Raw)": 2.1081838607788086, "Pretrain/Step": 7387, "Pretrain/Step Time": 8.491629673168063} +{"Pretrain/Learning Rate": 6.3627856008087764e-06, "Pretrain/Loss": 1.9774945974349976, "Pretrain/Loss (Raw)": 1.9794890880584717, "Pretrain/Step": 7388, "Pretrain/Step Time": 8.492641098797321} +{"Pretrain/Learning Rate": 6.357127407377711e-06, "Pretrain/Loss": 1.9789209365844727, "Pretrain/Loss (Raw)": 2.1219418048858643, "Pretrain/Step": 7389, "Pretrain/Step Time": 8.490292044356465} +{"Pretrain/Learning Rate": 6.3514713643954475e-06, "Pretrain/Loss": 1.9772746562957764, "Pretrain/Loss (Raw)": 2.0214476585388184, "Pretrain/Step": 7390, "Pretrain/Step Time": 8.487788412719965} +{"Pretrain/Learning Rate": 6.345817472514409e-06, "Pretrain/Loss": 1.9775002002716064, "Pretrain/Loss (Raw)": 2.0296552181243896, "Pretrain/Step": 7391, "Pretrain/Step Time": 8.489542184397578} +{"Pretrain/Learning Rate": 6.340165732386777e-06, "Pretrain/Loss": 1.9777252674102783, "Pretrain/Loss (Raw)": 2.0578534603118896, "Pretrain/Step": 7392, "Pretrain/Step Time": 8.490312337875366} +{"Pretrain/Learning Rate": 6.334516144664465e-06, "Pretrain/Loss": 1.979709506034851, "Pretrain/Loss (Raw)": 2.1285977363586426, "Pretrain/Step": 7393, "Pretrain/Step Time": 8.489558367058635} +{"Pretrain/Learning Rate": 6.328868709999153e-06, "Pretrain/Loss": 1.979767084121704, "Pretrain/Loss (Raw)": 2.099116325378418, "Pretrain/Step": 7394, "Pretrain/Step Time": 8.493398198857903} +{"Pretrain/Learning Rate": 6.323223429042275e-06, "Pretrain/Loss": 1.9806427955627441, "Pretrain/Loss (Raw)": 1.961848258972168, "Pretrain/Step": 7395, "Pretrain/Step Time": 8.486237874254584} +{"Pretrain/Learning Rate": 6.317580302445012e-06, "Pretrain/Loss": 1.9827594757080078, "Pretrain/Loss (Raw)": 2.073683023452759, "Pretrain/Step": 7396, "Pretrain/Step Time": 8.48198451846838} +{"Pretrain/Learning Rate": 6.311939330858293e-06, "Pretrain/Loss": 1.984890103340149, "Pretrain/Loss (Raw)": 1.947077989578247, "Pretrain/Step": 7397, "Pretrain/Step Time": 8.482315951958299} +{"Pretrain/Learning Rate": 6.3063005149328146e-06, "Pretrain/Loss": 1.984470009803772, "Pretrain/Loss (Raw)": 1.9538582563400269, "Pretrain/Step": 7398, "Pretrain/Step Time": 8.483680626377463} +{"Pretrain/Learning Rate": 6.300663855318995e-06, "Pretrain/Loss": 1.9832234382629395, "Pretrain/Loss (Raw)": 1.7307337522506714, "Pretrain/Step": 7399, "Pretrain/Step Time": 8.483364321291447} +{"Pretrain/Learning Rate": 6.295029352667034e-06, "Pretrain/Loss": 1.9824819564819336, "Pretrain/Loss (Raw)": 2.011892080307007, "Pretrain/Step": 7400, "Pretrain/Step Time": 8.490206327289343} +{"Pretrain/Learning Rate": 6.289397007626857e-06, "Pretrain/Loss": 1.9830266237258911, "Pretrain/Loss (Raw)": 2.0265908241271973, "Pretrain/Step": 7401, "Pretrain/Step Time": 8.487286757677794} +{"Pretrain/Learning Rate": 6.2837668208481606e-06, "Pretrain/Loss": 1.9826492071151733, "Pretrain/Loss (Raw)": 1.9154969453811646, "Pretrain/Step": 7402, "Pretrain/Step Time": 8.485816042870283} +{"Pretrain/Learning Rate": 6.27813879298039e-06, "Pretrain/Loss": 1.984436273574829, "Pretrain/Loss (Raw)": 2.114267587661743, "Pretrain/Step": 7403, "Pretrain/Step Time": 8.489302353933454} +{"Pretrain/Learning Rate": 6.272512924672724e-06, "Pretrain/Loss": 1.9837594032287598, "Pretrain/Loss (Raw)": 2.0860366821289062, "Pretrain/Step": 7404, "Pretrain/Step Time": 8.487090498209} +{"Pretrain/Learning Rate": 6.266889216574112e-06, "Pretrain/Loss": 1.9854121208190918, "Pretrain/Loss (Raw)": 2.1081740856170654, "Pretrain/Step": 7405, "Pretrain/Step Time": 8.486489407718182} +{"Pretrain/Learning Rate": 6.261267669333243e-06, "Pretrain/Loss": 1.9837918281555176, "Pretrain/Loss (Raw)": 1.8339601755142212, "Pretrain/Step": 7406, "Pretrain/Step Time": 8.49100936949253} +{"Pretrain/Learning Rate": 6.255648283598564e-06, "Pretrain/Loss": 1.9851386547088623, "Pretrain/Loss (Raw)": 2.0585150718688965, "Pretrain/Step": 7407, "Pretrain/Step Time": 8.489627884700894} +{"Pretrain/Learning Rate": 6.250031060018277e-06, "Pretrain/Loss": 1.9841644763946533, "Pretrain/Loss (Raw)": 1.899367332458496, "Pretrain/Step": 7408, "Pretrain/Step Time": 8.484909947961569} +{"Pretrain/Learning Rate": 6.244415999240311e-06, "Pretrain/Loss": 1.9825379848480225, "Pretrain/Loss (Raw)": 1.8548429012298584, "Pretrain/Step": 7409, "Pretrain/Step Time": 8.486903421580791} +{"Pretrain/Learning Rate": 6.238803101912366e-06, "Pretrain/Loss": 1.9856778383255005, "Pretrain/Loss (Raw)": 2.0263285636901855, "Pretrain/Step": 7410, "Pretrain/Step Time": 8.482539497315884} +{"Pretrain/Learning Rate": 6.23319236868189e-06, "Pretrain/Loss": 1.9869571924209595, "Pretrain/Loss (Raw)": 1.9559928178787231, "Pretrain/Step": 7411, "Pretrain/Step Time": 8.478542381897569} +{"Pretrain/Learning Rate": 6.22758380019608e-06, "Pretrain/Loss": 1.9875614643096924, "Pretrain/Loss (Raw)": 2.0082218647003174, "Pretrain/Step": 7412, "Pretrain/Step Time": 8.48012893088162} +{"Pretrain/Learning Rate": 6.221977397101889e-06, "Pretrain/Loss": 1.9880144596099854, "Pretrain/Loss (Raw)": 1.9491969347000122, "Pretrain/Step": 7413, "Pretrain/Step Time": 8.480756526812911} +{"Pretrain/Learning Rate": 6.216373160045999e-06, "Pretrain/Loss": 1.990463137626648, "Pretrain/Loss (Raw)": 2.074047565460205, "Pretrain/Step": 7414, "Pretrain/Step Time": 8.475494476035237} +{"Pretrain/Learning Rate": 6.210771089674864e-06, "Pretrain/Loss": 1.991459846496582, "Pretrain/Loss (Raw)": 2.007345199584961, "Pretrain/Step": 7415, "Pretrain/Step Time": 8.478220045566559} +{"Pretrain/Learning Rate": 6.205171186634689e-06, "Pretrain/Loss": 1.9907790422439575, "Pretrain/Loss (Raw)": 1.9309636354446411, "Pretrain/Step": 7416, "Pretrain/Step Time": 8.479223415255547} +{"Pretrain/Learning Rate": 6.199573451571403e-06, "Pretrain/Loss": 1.9901115894317627, "Pretrain/Loss (Raw)": 1.91778564453125, "Pretrain/Step": 7417, "Pretrain/Step Time": 8.48071645759046} +{"Pretrain/Learning Rate": 6.193977885130714e-06, "Pretrain/Loss": 1.9912327527999878, "Pretrain/Loss (Raw)": 2.15170955657959, "Pretrain/Step": 7418, "Pretrain/Step Time": 8.48070602491498} +{"Pretrain/Learning Rate": 6.188384487958074e-06, "Pretrain/Loss": 1.9903182983398438, "Pretrain/Loss (Raw)": 1.9485081434249878, "Pretrain/Step": 7419, "Pretrain/Step Time": 8.475944982841611} +{"Pretrain/Learning Rate": 6.182793260698666e-06, "Pretrain/Loss": 1.9908779859542847, "Pretrain/Loss (Raw)": 2.0631816387176514, "Pretrain/Step": 7420, "Pretrain/Step Time": 8.475952504202724} +{"Pretrain/Learning Rate": 6.1772042039974415e-06, "Pretrain/Loss": 1.9911625385284424, "Pretrain/Loss (Raw)": 2.047220230102539, "Pretrain/Step": 7421, "Pretrain/Step Time": 8.47758112847805} +{"Pretrain/Learning Rate": 6.171617318499098e-06, "Pretrain/Loss": 1.9883270263671875, "Pretrain/Loss (Raw)": 1.5533833503723145, "Pretrain/Step": 7422, "Pretrain/Step Time": 8.476537860929966} +{"Pretrain/Learning Rate": 6.166032604848079e-06, "Pretrain/Loss": 1.9881467819213867, "Pretrain/Loss (Raw)": 1.8764607906341553, "Pretrain/Step": 7423, "Pretrain/Step Time": 8.478285795077682} +{"Pretrain/Learning Rate": 6.160450063688589e-06, "Pretrain/Loss": 1.988699197769165, "Pretrain/Loss (Raw)": 2.077789783477783, "Pretrain/Step": 7424, "Pretrain/Step Time": 8.478143606334925} +{"Pretrain/Learning Rate": 6.154869695664556e-06, "Pretrain/Loss": 1.9875280857086182, "Pretrain/Loss (Raw)": 1.9667258262634277, "Pretrain/Step": 7425, "Pretrain/Step Time": 8.475793367251754} +{"Pretrain/Learning Rate": 6.1492915014196795e-06, "Pretrain/Loss": 1.9874629974365234, "Pretrain/Loss (Raw)": 2.0802042484283447, "Pretrain/Step": 7426, "Pretrain/Step Time": 8.478491129353642} +{"Pretrain/Learning Rate": 6.143715481597404e-06, "Pretrain/Loss": 1.9881267547607422, "Pretrain/Loss (Raw)": 1.9995399713516235, "Pretrain/Step": 7427, "Pretrain/Step Time": 8.474783709272742} +{"Pretrain/Learning Rate": 6.138141636840922e-06, "Pretrain/Loss": 1.983033537864685, "Pretrain/Loss (Raw)": 1.562880277633667, "Pretrain/Step": 7428, "Pretrain/Step Time": 8.472481109201908} +{"Pretrain/Learning Rate": 6.132569967793181e-06, "Pretrain/Loss": 1.9823672771453857, "Pretrain/Loss (Raw)": 1.9349004030227661, "Pretrain/Step": 7429, "Pretrain/Step Time": 8.471747716888785} +{"Pretrain/Learning Rate": 6.127000475096856e-06, "Pretrain/Loss": 1.9839508533477783, "Pretrain/Loss (Raw)": 2.1586520671844482, "Pretrain/Step": 7430, "Pretrain/Step Time": 8.470697646960616} +{"Pretrain/Learning Rate": 6.121433159394394e-06, "Pretrain/Loss": 1.9841971397399902, "Pretrain/Loss (Raw)": 2.1001884937286377, "Pretrain/Step": 7431, "Pretrain/Step Time": 8.472426611930132} +{"Pretrain/Learning Rate": 6.115868021327981e-06, "Pretrain/Loss": 1.984809398651123, "Pretrain/Loss (Raw)": 2.114854097366333, "Pretrain/Step": 7432, "Pretrain/Step Time": 8.47256021015346} +{"Pretrain/Learning Rate": 6.1103050615395644e-06, "Pretrain/Loss": 1.9852104187011719, "Pretrain/Loss (Raw)": 2.0892274379730225, "Pretrain/Step": 7433, "Pretrain/Step Time": 8.474321408197284} +{"Pretrain/Learning Rate": 6.104744280670813e-06, "Pretrain/Loss": 1.9842184782028198, "Pretrain/Loss (Raw)": 1.9718718528747559, "Pretrain/Step": 7434, "Pretrain/Step Time": 8.47614136710763} +{"Pretrain/Learning Rate": 6.099185679363176e-06, "Pretrain/Loss": 1.9848946332931519, "Pretrain/Loss (Raw)": 2.060940742492676, "Pretrain/Step": 7435, "Pretrain/Step Time": 8.473576840013266} +{"Pretrain/Learning Rate": 6.093629258257821e-06, "Pretrain/Loss": 1.984842300415039, "Pretrain/Loss (Raw)": 1.9909067153930664, "Pretrain/Step": 7436, "Pretrain/Step Time": 8.471636785194278} +{"Pretrain/Learning Rate": 6.0880750179956895e-06, "Pretrain/Loss": 1.9843757152557373, "Pretrain/Loss (Raw)": 1.753889560699463, "Pretrain/Step": 7437, "Pretrain/Step Time": 8.471010006964207} +{"Pretrain/Learning Rate": 6.082522959217454e-06, "Pretrain/Loss": 1.9836726188659668, "Pretrain/Loss (Raw)": 1.9507246017456055, "Pretrain/Step": 7438, "Pretrain/Step Time": 8.467087211087346} +{"Pretrain/Learning Rate": 6.0769730825635505e-06, "Pretrain/Loss": 1.9832558631896973, "Pretrain/Loss (Raw)": 1.929429531097412, "Pretrain/Step": 7439, "Pretrain/Step Time": 8.468445239588618} +{"Pretrain/Learning Rate": 6.07142538867416e-06, "Pretrain/Loss": 1.9833667278289795, "Pretrain/Loss (Raw)": 2.10768723487854, "Pretrain/Step": 7440, "Pretrain/Step Time": 8.471177814528346} +{"Pretrain/Learning Rate": 6.065879878189187e-06, "Pretrain/Loss": 1.9830862283706665, "Pretrain/Loss (Raw)": 1.9637166261672974, "Pretrain/Step": 7441, "Pretrain/Step Time": 8.471415761858225} +{"Pretrain/Learning Rate": 6.060336551748319e-06, "Pretrain/Loss": 1.9848418235778809, "Pretrain/Loss (Raw)": 2.1350150108337402, "Pretrain/Step": 7442, "Pretrain/Step Time": 8.470339871942997} +{"Pretrain/Learning Rate": 6.054795409990974e-06, "Pretrain/Loss": 1.9830996990203857, "Pretrain/Loss (Raw)": 2.0701963901519775, "Pretrain/Step": 7443, "Pretrain/Step Time": 8.467913001775742} +{"Pretrain/Learning Rate": 6.04925645355632e-06, "Pretrain/Loss": 1.9829521179199219, "Pretrain/Loss (Raw)": 2.0036683082580566, "Pretrain/Step": 7444, "Pretrain/Step Time": 8.469089802354574} +{"Pretrain/Learning Rate": 6.043719683083282e-06, "Pretrain/Loss": 1.9809339046478271, "Pretrain/Loss (Raw)": 1.9432108402252197, "Pretrain/Step": 7445, "Pretrain/Step Time": 8.465778566896915} +{"Pretrain/Learning Rate": 6.038185099210511e-06, "Pretrain/Loss": 1.9811331033706665, "Pretrain/Loss (Raw)": 2.149566411972046, "Pretrain/Step": 7446, "Pretrain/Step Time": 8.469617031514645} +{"Pretrain/Learning Rate": 6.032652702576424e-06, "Pretrain/Loss": 1.9829223155975342, "Pretrain/Loss (Raw)": 1.8717859983444214, "Pretrain/Step": 7447, "Pretrain/Step Time": 8.468712938949466} +{"Pretrain/Learning Rate": 6.027122493819182e-06, "Pretrain/Loss": 1.982276201248169, "Pretrain/Loss (Raw)": 1.8524489402770996, "Pretrain/Step": 7448, "Pretrain/Step Time": 8.470393190160394} +{"Pretrain/Learning Rate": 6.0215944735767e-06, "Pretrain/Loss": 1.9806017875671387, "Pretrain/Loss (Raw)": 1.813665509223938, "Pretrain/Step": 7449, "Pretrain/Step Time": 8.468672459945083} +{"Pretrain/Learning Rate": 6.016068642486619e-06, "Pretrain/Loss": 1.9799985885620117, "Pretrain/Loss (Raw)": 1.988072395324707, "Pretrain/Step": 7450, "Pretrain/Step Time": 8.466559702530503} +{"Pretrain/Learning Rate": 6.010545001186354e-06, "Pretrain/Loss": 1.9806787967681885, "Pretrain/Loss (Raw)": 2.0773348808288574, "Pretrain/Step": 7451, "Pretrain/Step Time": 8.46681559458375} +{"Pretrain/Learning Rate": 6.005023550313043e-06, "Pretrain/Loss": 1.9804468154907227, "Pretrain/Loss (Raw)": 2.0005054473876953, "Pretrain/Step": 7452, "Pretrain/Step Time": 8.46911035478115} +{"Pretrain/Learning Rate": 5.999504290503593e-06, "Pretrain/Loss": 1.9830548763275146, "Pretrain/Loss (Raw)": 2.116626739501953, "Pretrain/Step": 7453, "Pretrain/Step Time": 8.466792941093445} +{"Pretrain/Learning Rate": 5.9939872223946455e-06, "Pretrain/Loss": 1.9836093187332153, "Pretrain/Loss (Raw)": 2.1315176486968994, "Pretrain/Step": 7454, "Pretrain/Step Time": 8.467669131234288} +{"Pretrain/Learning Rate": 5.988472346622589e-06, "Pretrain/Loss": 1.9828811883926392, "Pretrain/Loss (Raw)": 1.9427579641342163, "Pretrain/Step": 7455, "Pretrain/Step Time": 8.4657127186656} +{"Pretrain/Learning Rate": 5.982959663823576e-06, "Pretrain/Loss": 1.9833436012268066, "Pretrain/Loss (Raw)": 2.0500614643096924, "Pretrain/Step": 7456, "Pretrain/Step Time": 8.45954318344593} +{"Pretrain/Learning Rate": 5.977449174633476e-06, "Pretrain/Loss": 1.9829412698745728, "Pretrain/Loss (Raw)": 1.8860962390899658, "Pretrain/Step": 7457, "Pretrain/Step Time": 8.46626634709537} +{"Pretrain/Learning Rate": 5.971940879687929e-06, "Pretrain/Loss": 1.9829400777816772, "Pretrain/Loss (Raw)": 1.7830427885055542, "Pretrain/Step": 7458, "Pretrain/Step Time": 8.468863544985652} +{"Pretrain/Learning Rate": 5.966434779622313e-06, "Pretrain/Loss": 1.9850282669067383, "Pretrain/Loss (Raw)": 2.03371000289917, "Pretrain/Step": 7459, "Pretrain/Step Time": 8.469157615676522} +{"Pretrain/Learning Rate": 5.9609308750717575e-06, "Pretrain/Loss": 1.9855471849441528, "Pretrain/Loss (Raw)": 2.040648937225342, "Pretrain/Step": 7460, "Pretrain/Step Time": 8.468006063252687} +{"Pretrain/Learning Rate": 5.95542916667114e-06, "Pretrain/Loss": 1.985252857208252, "Pretrain/Loss (Raw)": 1.9091365337371826, "Pretrain/Step": 7461, "Pretrain/Step Time": 8.469683516770601} +{"Pretrain/Learning Rate": 5.94992965505507e-06, "Pretrain/Loss": 1.985556960105896, "Pretrain/Loss (Raw)": 2.103039026260376, "Pretrain/Step": 7462, "Pretrain/Step Time": 8.46441432274878} +{"Pretrain/Learning Rate": 5.944432340857919e-06, "Pretrain/Loss": 1.9862494468688965, "Pretrain/Loss (Raw)": 1.9263125658035278, "Pretrain/Step": 7463, "Pretrain/Step Time": 8.464043382555246} +{"Pretrain/Learning Rate": 5.9389372247138e-06, "Pretrain/Loss": 1.9882715940475464, "Pretrain/Loss (Raw)": 2.0866081714630127, "Pretrain/Step": 7464, "Pretrain/Step Time": 8.464375438168645} +{"Pretrain/Learning Rate": 5.9334443072565745e-06, "Pretrain/Loss": 1.9899342060089111, "Pretrain/Loss (Raw)": 2.277841329574585, "Pretrain/Step": 7465, "Pretrain/Step Time": 8.463874645531178} +{"Pretrain/Learning Rate": 5.927953589119856e-06, "Pretrain/Loss": 1.9925215244293213, "Pretrain/Loss (Raw)": 2.0390636920928955, "Pretrain/Step": 7466, "Pretrain/Step Time": 8.462837815284729} +{"Pretrain/Learning Rate": 5.92246507093698e-06, "Pretrain/Loss": 1.9927510023117065, "Pretrain/Loss (Raw)": 2.0348961353302, "Pretrain/Step": 7467, "Pretrain/Step Time": 8.462236255407333} +{"Pretrain/Learning Rate": 5.916978753341063e-06, "Pretrain/Loss": 1.9930663108825684, "Pretrain/Loss (Raw)": 2.0837490558624268, "Pretrain/Step": 7468, "Pretrain/Step Time": 8.461823647841811} +{"Pretrain/Learning Rate": 5.911494636964931e-06, "Pretrain/Loss": 1.9919519424438477, "Pretrain/Loss (Raw)": 1.8743188381195068, "Pretrain/Step": 7469, "Pretrain/Step Time": 8.463416822254658} +{"Pretrain/Learning Rate": 5.906012722441184e-06, "Pretrain/Loss": 1.9932634830474854, "Pretrain/Loss (Raw)": 2.01304030418396, "Pretrain/Step": 7470, "Pretrain/Step Time": 8.461211180314422} +{"Pretrain/Learning Rate": 5.900533010402168e-06, "Pretrain/Loss": 1.9936859607696533, "Pretrain/Loss (Raw)": 2.041879892349243, "Pretrain/Step": 7471, "Pretrain/Step Time": 8.461495464667678} +{"Pretrain/Learning Rate": 5.895055501479952e-06, "Pretrain/Loss": 1.9936842918395996, "Pretrain/Loss (Raw)": 1.965757966041565, "Pretrain/Step": 7472, "Pretrain/Step Time": 8.459588108584285} +{"Pretrain/Learning Rate": 5.889580196306366e-06, "Pretrain/Loss": 1.9904752969741821, "Pretrain/Loss (Raw)": 1.707022786140442, "Pretrain/Step": 7473, "Pretrain/Step Time": 8.459762258455157} +{"Pretrain/Learning Rate": 5.884107095512992e-06, "Pretrain/Loss": 1.9907617568969727, "Pretrain/Loss (Raw)": 1.8871417045593262, "Pretrain/Step": 7474, "Pretrain/Step Time": 8.461247084662318} +{"Pretrain/Learning Rate": 5.878636199731144e-06, "Pretrain/Loss": 1.9897278547286987, "Pretrain/Loss (Raw)": 2.0125465393066406, "Pretrain/Step": 7475, "Pretrain/Step Time": 8.463901240378618} +{"Pretrain/Learning Rate": 5.873167509591893e-06, "Pretrain/Loss": 1.9885945320129395, "Pretrain/Loss (Raw)": 1.9313238859176636, "Pretrain/Step": 7476, "Pretrain/Step Time": 8.463476467877626} +{"Pretrain/Learning Rate": 5.8677010257260525e-06, "Pretrain/Loss": 1.987321376800537, "Pretrain/Loss (Raw)": 1.9122198820114136, "Pretrain/Step": 7477, "Pretrain/Step Time": 8.462065173313022} +{"Pretrain/Learning Rate": 5.862236748764169e-06, "Pretrain/Loss": 1.988513469696045, "Pretrain/Loss (Raw)": 2.0212130546569824, "Pretrain/Step": 7478, "Pretrain/Step Time": 8.457590084522963} +{"Pretrain/Learning Rate": 5.856774679336552e-06, "Pretrain/Loss": 1.9906864166259766, "Pretrain/Loss (Raw)": 2.139467716217041, "Pretrain/Step": 7479, "Pretrain/Step Time": 8.462073359638453} +{"Pretrain/Learning Rate": 5.8513148180732476e-06, "Pretrain/Loss": 1.9929146766662598, "Pretrain/Loss (Raw)": 2.2000603675842285, "Pretrain/Step": 7480, "Pretrain/Step Time": 8.459385273978114} +{"Pretrain/Learning Rate": 5.845857165604049e-06, "Pretrain/Loss": 1.9938788414001465, "Pretrain/Loss (Raw)": 2.006103992462158, "Pretrain/Step": 7481, "Pretrain/Step Time": 8.465436268597841} +{"Pretrain/Learning Rate": 5.840401722558503e-06, "Pretrain/Loss": 1.9920094013214111, "Pretrain/Loss (Raw)": 1.9166555404663086, "Pretrain/Step": 7482, "Pretrain/Step Time": 8.464516242966056} +{"Pretrain/Learning Rate": 5.834948489565878e-06, "Pretrain/Loss": 1.9930989742279053, "Pretrain/Loss (Raw)": 2.0759174823760986, "Pretrain/Step": 7483, "Pretrain/Step Time": 8.464658251032233} +{"Pretrain/Learning Rate": 5.829497467255218e-06, "Pretrain/Loss": 1.9931179285049438, "Pretrain/Loss (Raw)": 2.0210652351379395, "Pretrain/Step": 7484, "Pretrain/Step Time": 8.464092131704092} +{"Pretrain/Learning Rate": 5.82404865625528e-06, "Pretrain/Loss": 1.9948949813842773, "Pretrain/Loss (Raw)": 2.1921370029449463, "Pretrain/Step": 7485, "Pretrain/Step Time": 8.468528090044856} +{"Pretrain/Learning Rate": 5.818602057194589e-06, "Pretrain/Loss": 1.9954780340194702, "Pretrain/Loss (Raw)": 2.0975797176361084, "Pretrain/Step": 7486, "Pretrain/Step Time": 8.465440232306719} +{"Pretrain/Learning Rate": 5.813157670701419e-06, "Pretrain/Loss": 1.9953501224517822, "Pretrain/Loss (Raw)": 2.129628896713257, "Pretrain/Step": 7487, "Pretrain/Step Time": 8.46635558642447} +{"Pretrain/Learning Rate": 5.807715497403762e-06, "Pretrain/Loss": 1.995643973350525, "Pretrain/Loss (Raw)": 2.055741548538208, "Pretrain/Step": 7488, "Pretrain/Step Time": 8.46605876646936} +{"Pretrain/Learning Rate": 5.802275537929375e-06, "Pretrain/Loss": 1.9969706535339355, "Pretrain/Loss (Raw)": 1.93392813205719, "Pretrain/Step": 7489, "Pretrain/Step Time": 8.468118349090219} +{"Pretrain/Learning Rate": 5.79683779290576e-06, "Pretrain/Loss": 1.9976999759674072, "Pretrain/Loss (Raw)": 2.186406135559082, "Pretrain/Step": 7490, "Pretrain/Step Time": 8.4694909080863} +{"Pretrain/Learning Rate": 5.791402262960158e-06, "Pretrain/Loss": 1.9961938858032227, "Pretrain/Loss (Raw)": 1.9105297327041626, "Pretrain/Step": 7491, "Pretrain/Step Time": 8.475505992770195} +{"Pretrain/Learning Rate": 5.785968948719561e-06, "Pretrain/Loss": 1.996349811553955, "Pretrain/Loss (Raw)": 1.9557217359542847, "Pretrain/Step": 7492, "Pretrain/Step Time": 8.474751811474562} +{"Pretrain/Learning Rate": 5.780537850810686e-06, "Pretrain/Loss": 1.9975988864898682, "Pretrain/Loss (Raw)": 2.184494733810425, "Pretrain/Step": 7493, "Pretrain/Step Time": 8.47513591684401} +{"Pretrain/Learning Rate": 5.775108969860016e-06, "Pretrain/Loss": 1.9974141120910645, "Pretrain/Loss (Raw)": 2.099440336227417, "Pretrain/Step": 7494, "Pretrain/Step Time": 8.473658146336675} +{"Pretrain/Learning Rate": 5.76968230649377e-06, "Pretrain/Loss": 1.9976625442504883, "Pretrain/Loss (Raw)": 2.0392937660217285, "Pretrain/Step": 7495, "Pretrain/Step Time": 8.468874303624034} +{"Pretrain/Learning Rate": 5.764257861337913e-06, "Pretrain/Loss": 1.9987303018569946, "Pretrain/Loss (Raw)": 2.1139121055603027, "Pretrain/Step": 7496, "Pretrain/Step Time": 8.467753808945417} +{"Pretrain/Learning Rate": 5.758835635018151e-06, "Pretrain/Loss": 1.9992611408233643, "Pretrain/Loss (Raw)": 2.070838212966919, "Pretrain/Step": 7497, "Pretrain/Step Time": 8.469192702323198} +{"Pretrain/Learning Rate": 5.753415628159945e-06, "Pretrain/Loss": 2.0004539489746094, "Pretrain/Loss (Raw)": 2.0052108764648438, "Pretrain/Step": 7498, "Pretrain/Step Time": 8.473660444840789} +{"Pretrain/Learning Rate": 5.747997841388472e-06, "Pretrain/Loss": 2.001155376434326, "Pretrain/Loss (Raw)": 2.0196869373321533, "Pretrain/Step": 7499, "Pretrain/Step Time": 8.470106853172183} +{"Pretrain/Learning Rate": 5.742582275328692e-06, "Pretrain/Loss": 2.002469062805176, "Pretrain/Loss (Raw)": 2.0509283542633057, "Pretrain/Step": 7500, "Pretrain/Step Time": 8.472412249073386} +{"Pretrain/Learning Rate": 5.737168930605272e-06, "Pretrain/Loss": 2.0024566650390625, "Pretrain/Loss (Raw)": 1.8559883832931519, "Pretrain/Step": 7501, "Pretrain/Step Time": 8.471724387258291} +{"Pretrain/Learning Rate": 5.731757807842647e-06, "Pretrain/Loss": 2.0027878284454346, "Pretrain/Loss (Raw)": 2.11480450630188, "Pretrain/Step": 7502, "Pretrain/Step Time": 8.467571614310145} +{"Pretrain/Learning Rate": 5.726348907664994e-06, "Pretrain/Loss": 2.001612424850464, "Pretrain/Loss (Raw)": 1.900054931640625, "Pretrain/Step": 7503, "Pretrain/Step Time": 8.469532230868936} +{"Pretrain/Learning Rate": 5.7209422306962135e-06, "Pretrain/Loss": 2.002350330352783, "Pretrain/Loss (Raw)": 1.9496866464614868, "Pretrain/Step": 7504, "Pretrain/Step Time": 8.474404534325004} +{"Pretrain/Learning Rate": 5.715537777559971e-06, "Pretrain/Loss": 2.0026683807373047, "Pretrain/Loss (Raw)": 1.9643566608428955, "Pretrain/Step": 7505, "Pretrain/Step Time": 8.47427641786635} +{"Pretrain/Learning Rate": 5.7101355488796695e-06, "Pretrain/Loss": 2.0015034675598145, "Pretrain/Loss (Raw)": 1.8694252967834473, "Pretrain/Step": 7506, "Pretrain/Step Time": 8.472393611446023} +{"Pretrain/Learning Rate": 5.704735545278453e-06, "Pretrain/Loss": 2.002133846282959, "Pretrain/Loss (Raw)": 1.8621817827224731, "Pretrain/Step": 7507, "Pretrain/Step Time": 8.470897480845451} +{"Pretrain/Learning Rate": 5.69933776737922e-06, "Pretrain/Loss": 2.001331329345703, "Pretrain/Loss (Raw)": 2.063706159591675, "Pretrain/Step": 7508, "Pretrain/Step Time": 8.473732367157936} +{"Pretrain/Learning Rate": 5.693942215804585e-06, "Pretrain/Loss": 2.000142812728882, "Pretrain/Loss (Raw)": 1.7978981733322144, "Pretrain/Step": 7509, "Pretrain/Step Time": 8.470942897722125} +{"Pretrain/Learning Rate": 5.6885488911769285e-06, "Pretrain/Loss": 1.9999061822891235, "Pretrain/Loss (Raw)": 1.9466906785964966, "Pretrain/Step": 7510, "Pretrain/Step Time": 8.473084464669228} +{"Pretrain/Learning Rate": 5.683157794118371e-06, "Pretrain/Loss": 1.99979829788208, "Pretrain/Loss (Raw)": 1.9880160093307495, "Pretrain/Step": 7511, "Pretrain/Step Time": 8.470962882041931} +{"Pretrain/Learning Rate": 5.677768925250776e-06, "Pretrain/Loss": 1.9990346431732178, "Pretrain/Loss (Raw)": 1.9990407228469849, "Pretrain/Step": 7512, "Pretrain/Step Time": 8.470323687419295} +{"Pretrain/Learning Rate": 5.672382285195751e-06, "Pretrain/Loss": 1.9999855756759644, "Pretrain/Loss (Raw)": 2.1207656860351562, "Pretrain/Step": 7513, "Pretrain/Step Time": 8.467475857585669} +{"Pretrain/Learning Rate": 5.666997874574629e-06, "Pretrain/Loss": 2.0005059242248535, "Pretrain/Loss (Raw)": 2.06325364112854, "Pretrain/Step": 7514, "Pretrain/Step Time": 8.468328312039375} +{"Pretrain/Learning Rate": 5.66161569400851e-06, "Pretrain/Loss": 2.000795364379883, "Pretrain/Loss (Raw)": 2.145205020904541, "Pretrain/Step": 7515, "Pretrain/Step Time": 8.470869662240148} +{"Pretrain/Learning Rate": 5.656235744118224e-06, "Pretrain/Loss": 2.0011768341064453, "Pretrain/Loss (Raw)": 2.0283420085906982, "Pretrain/Step": 7516, "Pretrain/Step Time": 8.472234707325697} +{"Pretrain/Learning Rate": 5.6508580255243524e-06, "Pretrain/Loss": 1.9998315572738647, "Pretrain/Loss (Raw)": 1.9497442245483398, "Pretrain/Step": 7517, "Pretrain/Step Time": 8.470557928085327} +{"Pretrain/Learning Rate": 5.645482538847202e-06, "Pretrain/Loss": 1.998545527458191, "Pretrain/Loss (Raw)": 1.8568425178527832, "Pretrain/Step": 7518, "Pretrain/Step Time": 8.478090578690171} +{"Pretrain/Learning Rate": 5.640109284706849e-06, "Pretrain/Loss": 1.9985387325286865, "Pretrain/Loss (Raw)": 2.0287764072418213, "Pretrain/Step": 7519, "Pretrain/Step Time": 8.473098961636424} +{"Pretrain/Learning Rate": 5.634738263723075e-06, "Pretrain/Loss": 1.9978418350219727, "Pretrain/Loss (Raw)": 1.9686284065246582, "Pretrain/Step": 7520, "Pretrain/Step Time": 8.476329065859318} +{"Pretrain/Learning Rate": 5.6293694765154395e-06, "Pretrain/Loss": 1.9964781999588013, "Pretrain/Loss (Raw)": 1.9540683031082153, "Pretrain/Step": 7521, "Pretrain/Step Time": 8.475419655442238} +{"Pretrain/Learning Rate": 5.624002923703226e-06, "Pretrain/Loss": 1.9932161569595337, "Pretrain/Loss (Raw)": 1.6815787553787231, "Pretrain/Step": 7522, "Pretrain/Step Time": 8.474051667377353} +{"Pretrain/Learning Rate": 5.618638605905469e-06, "Pretrain/Loss": 1.993240475654602, "Pretrain/Loss (Raw)": 1.964955449104309, "Pretrain/Step": 7523, "Pretrain/Step Time": 8.476429717615247} +{"Pretrain/Learning Rate": 5.61327652374094e-06, "Pretrain/Loss": 1.9931066036224365, "Pretrain/Loss (Raw)": 2.0565526485443115, "Pretrain/Step": 7524, "Pretrain/Step Time": 8.476560590788722} +{"Pretrain/Learning Rate": 5.607916677828149e-06, "Pretrain/Loss": 1.9929225444793701, "Pretrain/Loss (Raw)": 1.923514485359192, "Pretrain/Step": 7525, "Pretrain/Step Time": 8.473392333835363} +{"Pretrain/Learning Rate": 5.602559068785352e-06, "Pretrain/Loss": 1.9919092655181885, "Pretrain/Loss (Raw)": 1.8241595029830933, "Pretrain/Step": 7526, "Pretrain/Step Time": 8.47212652117014} +{"Pretrain/Learning Rate": 5.597203697230549e-06, "Pretrain/Loss": 1.9953835010528564, "Pretrain/Loss (Raw)": 2.1754441261291504, "Pretrain/Step": 7527, "Pretrain/Step Time": 8.47332514077425} +{"Pretrain/Learning Rate": 5.591850563781481e-06, "Pretrain/Loss": 1.9951367378234863, "Pretrain/Loss (Raw)": 1.9802945852279663, "Pretrain/Step": 7528, "Pretrain/Step Time": 8.467957179993391} +{"Pretrain/Learning Rate": 5.586499669055637e-06, "Pretrain/Loss": 1.9945578575134277, "Pretrain/Loss (Raw)": 1.952497959136963, "Pretrain/Step": 7529, "Pretrain/Step Time": 8.468191210180521} +{"Pretrain/Learning Rate": 5.581151013670227e-06, "Pretrain/Loss": 1.9943127632141113, "Pretrain/Loss (Raw)": 1.884132742881775, "Pretrain/Step": 7530, "Pretrain/Step Time": 8.46826902590692} +{"Pretrain/Learning Rate": 5.5758045982422235e-06, "Pretrain/Loss": 1.9923808574676514, "Pretrain/Loss (Raw)": 1.8669720888137817, "Pretrain/Step": 7531, "Pretrain/Step Time": 8.467859426513314} +{"Pretrain/Learning Rate": 5.570460423388332e-06, "Pretrain/Loss": 1.9922921657562256, "Pretrain/Loss (Raw)": 2.0746843814849854, "Pretrain/Step": 7532, "Pretrain/Step Time": 8.469617260619998} +{"Pretrain/Learning Rate": 5.565118489725013e-06, "Pretrain/Loss": 1.9912919998168945, "Pretrain/Loss (Raw)": 1.980158805847168, "Pretrain/Step": 7533, "Pretrain/Step Time": 8.472463859245181} +{"Pretrain/Learning Rate": 5.559778797868437e-06, "Pretrain/Loss": 1.9938766956329346, "Pretrain/Loss (Raw)": 2.1647939682006836, "Pretrain/Step": 7534, "Pretrain/Step Time": 8.469998179003596} +{"Pretrain/Learning Rate": 5.554441348434553e-06, "Pretrain/Loss": 1.9938912391662598, "Pretrain/Loss (Raw)": 2.060391426086426, "Pretrain/Step": 7535, "Pretrain/Step Time": 8.470908623188734} +{"Pretrain/Learning Rate": 5.549106142039018e-06, "Pretrain/Loss": 1.9957160949707031, "Pretrain/Loss (Raw)": 2.132929801940918, "Pretrain/Step": 7536, "Pretrain/Step Time": 8.47402799129486} +{"Pretrain/Learning Rate": 5.543773179297254e-06, "Pretrain/Loss": 1.9970738887786865, "Pretrain/Loss (Raw)": 2.0286455154418945, "Pretrain/Step": 7537, "Pretrain/Step Time": 8.472590973600745} +{"Pretrain/Learning Rate": 5.538442460824417e-06, "Pretrain/Loss": 1.9966983795166016, "Pretrain/Loss (Raw)": 1.9782755374908447, "Pretrain/Step": 7538, "Pretrain/Step Time": 8.4713393189013} +{"Pretrain/Learning Rate": 5.5331139872354e-06, "Pretrain/Loss": 1.996520757675171, "Pretrain/Loss (Raw)": 1.9332505464553833, "Pretrain/Step": 7539, "Pretrain/Step Time": 8.475811013951898} +{"Pretrain/Learning Rate": 5.527787759144854e-06, "Pretrain/Loss": 1.9957528114318848, "Pretrain/Loss (Raw)": 1.9099197387695312, "Pretrain/Step": 7540, "Pretrain/Step Time": 8.475926829501987} +{"Pretrain/Learning Rate": 5.5224637771671385e-06, "Pretrain/Loss": 1.9949734210968018, "Pretrain/Loss (Raw)": 1.8494431972503662, "Pretrain/Step": 7541, "Pretrain/Step Time": 8.47836891002953} +{"Pretrain/Learning Rate": 5.517142041916382e-06, "Pretrain/Loss": 1.9932043552398682, "Pretrain/Loss (Raw)": 1.847598910331726, "Pretrain/Step": 7542, "Pretrain/Step Time": 8.47881137393415} +{"Pretrain/Learning Rate": 5.511822554006443e-06, "Pretrain/Loss": 1.9943311214447021, "Pretrain/Loss (Raw)": 2.1515793800354004, "Pretrain/Step": 7543, "Pretrain/Step Time": 8.477730365470052} +{"Pretrain/Learning Rate": 5.506505314050925e-06, "Pretrain/Loss": 1.9936678409576416, "Pretrain/Loss (Raw)": 1.846073031425476, "Pretrain/Step": 7544, "Pretrain/Step Time": 8.475136000663042} +{"Pretrain/Learning Rate": 5.5011903226631745e-06, "Pretrain/Loss": 1.9927626848220825, "Pretrain/Loss (Raw)": 1.8019089698791504, "Pretrain/Step": 7545, "Pretrain/Step Time": 8.475468896329403} +{"Pretrain/Learning Rate": 5.4958775804562625e-06, "Pretrain/Loss": 1.991260051727295, "Pretrain/Loss (Raw)": 1.959382176399231, "Pretrain/Step": 7546, "Pretrain/Step Time": 8.476089907810092} +{"Pretrain/Learning Rate": 5.490567088043016e-06, "Pretrain/Loss": 1.9912158250808716, "Pretrain/Loss (Raw)": 1.9428279399871826, "Pretrain/Step": 7547, "Pretrain/Step Time": 8.4780647251755} +{"Pretrain/Learning Rate": 5.485258846036001e-06, "Pretrain/Loss": 1.9902797937393188, "Pretrain/Loss (Raw)": 1.9433907270431519, "Pretrain/Step": 7548, "Pretrain/Step Time": 8.478487100452185} +{"Pretrain/Learning Rate": 5.479952855047527e-06, "Pretrain/Loss": 1.990356206893921, "Pretrain/Loss (Raw)": 2.0570034980773926, "Pretrain/Step": 7549, "Pretrain/Step Time": 8.4813188072294} +{"Pretrain/Learning Rate": 5.4746491156896225e-06, "Pretrain/Loss": 1.993163824081421, "Pretrain/Loss (Raw)": 1.9127445220947266, "Pretrain/Step": 7550, "Pretrain/Step Time": 8.48295795544982} +{"Pretrain/Learning Rate": 5.4693476285740815e-06, "Pretrain/Loss": 1.9923160076141357, "Pretrain/Loss (Raw)": 1.767940878868103, "Pretrain/Step": 7551, "Pretrain/Step Time": 8.479217242449522} +{"Pretrain/Learning Rate": 5.464048394312438e-06, "Pretrain/Loss": 1.9909591674804688, "Pretrain/Loss (Raw)": 1.9041242599487305, "Pretrain/Step": 7552, "Pretrain/Step Time": 8.481679843738675} +{"Pretrain/Learning Rate": 5.458751413515936e-06, "Pretrain/Loss": 1.991612434387207, "Pretrain/Loss (Raw)": 2.0503475666046143, "Pretrain/Step": 7553, "Pretrain/Step Time": 8.480669951066375} +{"Pretrain/Learning Rate": 5.453456686795591e-06, "Pretrain/Loss": 1.9912893772125244, "Pretrain/Loss (Raw)": 2.0388381481170654, "Pretrain/Step": 7554, "Pretrain/Step Time": 8.476339869201183} +{"Pretrain/Learning Rate": 5.448164214762158e-06, "Pretrain/Loss": 1.9913928508758545, "Pretrain/Loss (Raw)": 2.0127906799316406, "Pretrain/Step": 7555, "Pretrain/Step Time": 8.478285387158394} +{"Pretrain/Learning Rate": 5.442873998026102e-06, "Pretrain/Loss": 1.9948939085006714, "Pretrain/Loss (Raw)": 2.0110085010528564, "Pretrain/Step": 7556, "Pretrain/Step Time": 8.481486614793539} +{"Pretrain/Learning Rate": 5.437586037197659e-06, "Pretrain/Loss": 1.9954274892807007, "Pretrain/Loss (Raw)": 2.0032143592834473, "Pretrain/Step": 7557, "Pretrain/Step Time": 8.482922449707985} +{"Pretrain/Learning Rate": 5.432300332886791e-06, "Pretrain/Loss": 1.99454665184021, "Pretrain/Loss (Raw)": 2.0458824634552, "Pretrain/Step": 7558, "Pretrain/Step Time": 8.483021926134825} +{"Pretrain/Learning Rate": 5.427016885703207e-06, "Pretrain/Loss": 1.9938514232635498, "Pretrain/Loss (Raw)": 2.011214017868042, "Pretrain/Step": 7559, "Pretrain/Step Time": 8.47980709001422} +{"Pretrain/Learning Rate": 5.421735696256342e-06, "Pretrain/Loss": 1.993854284286499, "Pretrain/Loss (Raw)": 2.115217447280884, "Pretrain/Step": 7560, "Pretrain/Step Time": 8.48326376825571} +{"Pretrain/Learning Rate": 5.416456765155392e-06, "Pretrain/Loss": 1.9939415454864502, "Pretrain/Loss (Raw)": 2.1003875732421875, "Pretrain/Step": 7561, "Pretrain/Step Time": 8.480186009779572} +{"Pretrain/Learning Rate": 5.411180093009266e-06, "Pretrain/Loss": 1.9914778470993042, "Pretrain/Loss (Raw)": 1.656537413597107, "Pretrain/Step": 7562, "Pretrain/Step Time": 8.478236300870776} +{"Pretrain/Learning Rate": 5.4059056804266315e-06, "Pretrain/Loss": 1.9900178909301758, "Pretrain/Loss (Raw)": 1.874070167541504, "Pretrain/Step": 7563, "Pretrain/Step Time": 8.479440942406654} +{"Pretrain/Learning Rate": 5.400633528015891e-06, "Pretrain/Loss": 1.9880053997039795, "Pretrain/Loss (Raw)": 1.7333012819290161, "Pretrain/Step": 7564, "Pretrain/Step Time": 8.481969071552157} +{"Pretrain/Learning Rate": 5.395363636385186e-06, "Pretrain/Loss": 1.9888904094696045, "Pretrain/Loss (Raw)": 1.8671703338623047, "Pretrain/Step": 7565, "Pretrain/Step Time": 8.483001057058573} +{"Pretrain/Learning Rate": 5.390096006142404e-06, "Pretrain/Loss": 1.9892747402191162, "Pretrain/Loss (Raw)": 1.999899983406067, "Pretrain/Step": 7566, "Pretrain/Step Time": 8.484600054100156} +{"Pretrain/Learning Rate": 5.384830637895147e-06, "Pretrain/Loss": 1.9902782440185547, "Pretrain/Loss (Raw)": 2.05790376663208, "Pretrain/Step": 7567, "Pretrain/Step Time": 8.484708655625582} +{"Pretrain/Learning Rate": 5.37956753225079e-06, "Pretrain/Loss": 1.9899728298187256, "Pretrain/Loss (Raw)": 2.068588972091675, "Pretrain/Step": 7568, "Pretrain/Step Time": 8.479117942973971} +{"Pretrain/Learning Rate": 5.374306689816419e-06, "Pretrain/Loss": 1.989762783050537, "Pretrain/Loss (Raw)": 1.936819076538086, "Pretrain/Step": 7569, "Pretrain/Step Time": 8.474913015961647} +{"Pretrain/Learning Rate": 5.369048111198871e-06, "Pretrain/Loss": 1.990483045578003, "Pretrain/Loss (Raw)": 2.227205514907837, "Pretrain/Step": 7570, "Pretrain/Step Time": 8.478333257138729} +{"Pretrain/Learning Rate": 5.363791797004733e-06, "Pretrain/Loss": 1.9901156425476074, "Pretrain/Loss (Raw)": 2.023191452026367, "Pretrain/Step": 7571, "Pretrain/Step Time": 8.479237930849195} +{"Pretrain/Learning Rate": 5.3585377478403035e-06, "Pretrain/Loss": 1.9896671772003174, "Pretrain/Loss (Raw)": 1.946244239807129, "Pretrain/Step": 7572, "Pretrain/Step Time": 8.4825440607965} +{"Pretrain/Learning Rate": 5.353285964311642e-06, "Pretrain/Loss": 1.9911459684371948, "Pretrain/Loss (Raw)": 2.132509708404541, "Pretrain/Step": 7573, "Pretrain/Step Time": 8.483243150636554} +{"Pretrain/Learning Rate": 5.34803644702454e-06, "Pretrain/Loss": 1.9905931949615479, "Pretrain/Loss (Raw)": 2.078809976577759, "Pretrain/Step": 7574, "Pretrain/Step Time": 8.47761819884181} +{"Pretrain/Learning Rate": 5.342789196584527e-06, "Pretrain/Loss": 1.9908802509307861, "Pretrain/Loss (Raw)": 1.908522367477417, "Pretrain/Step": 7575, "Pretrain/Step Time": 8.480021389201283} +{"Pretrain/Learning Rate": 5.337544213596873e-06, "Pretrain/Loss": 1.9919450283050537, "Pretrain/Loss (Raw)": 1.9887371063232422, "Pretrain/Step": 7576, "Pretrain/Step Time": 8.478775143623352} +{"Pretrain/Learning Rate": 5.332301498666592e-06, "Pretrain/Loss": 1.9946147203445435, "Pretrain/Loss (Raw)": 2.1553843021392822, "Pretrain/Step": 7577, "Pretrain/Step Time": 8.478682717308402} +{"Pretrain/Learning Rate": 5.327061052398413e-06, "Pretrain/Loss": 1.9947874546051025, "Pretrain/Loss (Raw)": 2.0102009773254395, "Pretrain/Step": 7578, "Pretrain/Step Time": 8.479242160916328} +{"Pretrain/Learning Rate": 5.321822875396829e-06, "Pretrain/Loss": 1.99196457862854, "Pretrain/Loss (Raw)": 1.7160046100616455, "Pretrain/Step": 7579, "Pretrain/Step Time": 8.479294208809733} +{"Pretrain/Learning Rate": 5.31658696826606e-06, "Pretrain/Loss": 1.991896390914917, "Pretrain/Loss (Raw)": 1.991755485534668, "Pretrain/Step": 7580, "Pretrain/Step Time": 8.475796572864056} +{"Pretrain/Learning Rate": 5.311353331610067e-06, "Pretrain/Loss": 1.99200439453125, "Pretrain/Loss (Raw)": 2.130469799041748, "Pretrain/Step": 7581, "Pretrain/Step Time": 8.476660499349236} +{"Pretrain/Learning Rate": 5.306121966032557e-06, "Pretrain/Loss": 1.9907901287078857, "Pretrain/Loss (Raw)": 1.9760754108428955, "Pretrain/Step": 7582, "Pretrain/Step Time": 8.476958274841309} +{"Pretrain/Learning Rate": 5.300892872136947e-06, "Pretrain/Loss": 1.9903556108474731, "Pretrain/Loss (Raw)": 1.8871536254882812, "Pretrain/Step": 7583, "Pretrain/Step Time": 8.48165288567543} +{"Pretrain/Learning Rate": 5.295666050526432e-06, "Pretrain/Loss": 1.9875634908676147, "Pretrain/Loss (Raw)": 1.6926649808883667, "Pretrain/Step": 7584, "Pretrain/Step Time": 8.487545436248183} +{"Pretrain/Learning Rate": 5.290441501803903e-06, "Pretrain/Loss": 1.9897443056106567, "Pretrain/Loss (Raw)": 2.165243148803711, "Pretrain/Step": 7585, "Pretrain/Step Time": 8.479470867663622} +{"Pretrain/Learning Rate": 5.2852192265720216e-06, "Pretrain/Loss": 1.9906816482543945, "Pretrain/Loss (Raw)": 1.9030154943466187, "Pretrain/Step": 7586, "Pretrain/Step Time": 8.481641693040729} +{"Pretrain/Learning Rate": 5.279999225433182e-06, "Pretrain/Loss": 1.991170048713684, "Pretrain/Loss (Raw)": 2.0962343215942383, "Pretrain/Step": 7587, "Pretrain/Step Time": 8.477608257904649} +{"Pretrain/Learning Rate": 5.274781498989495e-06, "Pretrain/Loss": 1.9910153150558472, "Pretrain/Loss (Raw)": 2.0208282470703125, "Pretrain/Step": 7588, "Pretrain/Step Time": 8.48296313919127} +{"Pretrain/Learning Rate": 5.2695660478428305e-06, "Pretrain/Loss": 1.9931086301803589, "Pretrain/Loss (Raw)": 2.1771035194396973, "Pretrain/Step": 7589, "Pretrain/Step Time": 8.480634815990925} +{"Pretrain/Learning Rate": 5.264352872594786e-06, "Pretrain/Loss": 1.9937716722488403, "Pretrain/Loss (Raw)": 2.187901020050049, "Pretrain/Step": 7590, "Pretrain/Step Time": 8.483755588531494} +{"Pretrain/Learning Rate": 5.259141973846704e-06, "Pretrain/Loss": 1.994167447090149, "Pretrain/Loss (Raw)": 1.9769669771194458, "Pretrain/Step": 7591, "Pretrain/Step Time": 8.4816241171211} +{"Pretrain/Learning Rate": 5.253933352199664e-06, "Pretrain/Loss": 1.9936057329177856, "Pretrain/Loss (Raw)": 2.0146849155426025, "Pretrain/Step": 7592, "Pretrain/Step Time": 8.483591953292489} +{"Pretrain/Learning Rate": 5.248727008254467e-06, "Pretrain/Loss": 1.9900977611541748, "Pretrain/Loss (Raw)": 1.8288536071777344, "Pretrain/Step": 7593, "Pretrain/Step Time": 8.482365414500237} +{"Pretrain/Learning Rate": 5.243522942611667e-06, "Pretrain/Loss": 1.991395115852356, "Pretrain/Loss (Raw)": 2.2051148414611816, "Pretrain/Step": 7594, "Pretrain/Step Time": 8.481491385027766} +{"Pretrain/Learning Rate": 5.238321155871554e-06, "Pretrain/Loss": 1.9896941184997559, "Pretrain/Loss (Raw)": 1.8171571493148804, "Pretrain/Step": 7595, "Pretrain/Step Time": 8.486102433875203} +{"Pretrain/Learning Rate": 5.233121648634151e-06, "Pretrain/Loss": 1.988257884979248, "Pretrain/Loss (Raw)": 1.8999296426773071, "Pretrain/Step": 7596, "Pretrain/Step Time": 8.485727744176984} +{"Pretrain/Learning Rate": 5.2279244214992166e-06, "Pretrain/Loss": 1.986424207687378, "Pretrain/Loss (Raw)": 1.63961923122406, "Pretrain/Step": 7597, "Pretrain/Step Time": 8.489117359742522} +{"Pretrain/Learning Rate": 5.222729475066263e-06, "Pretrain/Loss": 1.9878008365631104, "Pretrain/Loss (Raw)": 2.1892244815826416, "Pretrain/Step": 7598, "Pretrain/Step Time": 8.489887807518244} +{"Pretrain/Learning Rate": 5.217536809934503e-06, "Pretrain/Loss": 1.9878642559051514, "Pretrain/Loss (Raw)": 2.050006151199341, "Pretrain/Step": 7599, "Pretrain/Step Time": 8.488559203222394} +{"Pretrain/Learning Rate": 5.212346426702922e-06, "Pretrain/Loss": 1.9888325929641724, "Pretrain/Loss (Raw)": 2.0896968841552734, "Pretrain/Step": 7600, "Pretrain/Step Time": 8.490486783906817} +{"Pretrain/Learning Rate": 5.207158325970235e-06, "Pretrain/Loss": 1.992079734802246, "Pretrain/Loss (Raw)": 2.1226747035980225, "Pretrain/Step": 7601, "Pretrain/Step Time": 8.488476319238544} +{"Pretrain/Learning Rate": 5.201972508334871e-06, "Pretrain/Loss": 1.99359929561615, "Pretrain/Loss (Raw)": 2.081638813018799, "Pretrain/Step": 7602, "Pretrain/Step Time": 8.488490890711546} +{"Pretrain/Learning Rate": 5.196788974395026e-06, "Pretrain/Loss": 1.9941658973693848, "Pretrain/Loss (Raw)": 2.08506441116333, "Pretrain/Step": 7603, "Pretrain/Step Time": 8.491701481863856} +{"Pretrain/Learning Rate": 5.1916077247486095e-06, "Pretrain/Loss": 1.9946223497390747, "Pretrain/Loss (Raw)": 1.9897493124008179, "Pretrain/Step": 7604, "Pretrain/Step Time": 8.490725276991725} +{"Pretrain/Learning Rate": 5.186428759993278e-06, "Pretrain/Loss": 1.9974393844604492, "Pretrain/Loss (Raw)": 2.2728159427642822, "Pretrain/Step": 7605, "Pretrain/Step Time": 8.492041377350688} +{"Pretrain/Learning Rate": 5.181252080726429e-06, "Pretrain/Loss": 1.9987852573394775, "Pretrain/Loss (Raw)": 2.193477153778076, "Pretrain/Step": 7606, "Pretrain/Step Time": 8.496264545246959} +{"Pretrain/Learning Rate": 5.176077687545186e-06, "Pretrain/Loss": 1.9971083402633667, "Pretrain/Loss (Raw)": 1.9248226881027222, "Pretrain/Step": 7607, "Pretrain/Step Time": 8.49404051154852} +{"Pretrain/Learning Rate": 5.1709055810464205e-06, "Pretrain/Loss": 1.995760440826416, "Pretrain/Loss (Raw)": 2.027503728866577, "Pretrain/Step": 7608, "Pretrain/Step Time": 8.492149256169796} +{"Pretrain/Learning Rate": 5.165735761826724e-06, "Pretrain/Loss": 1.9956636428833008, "Pretrain/Loss (Raw)": 1.9937328100204468, "Pretrain/Step": 7609, "Pretrain/Step Time": 8.490317542105913} +{"Pretrain/Learning Rate": 5.160568230482435e-06, "Pretrain/Loss": 1.9960694313049316, "Pretrain/Loss (Raw)": 1.9685853719711304, "Pretrain/Step": 7610, "Pretrain/Step Time": 8.490280589088798} +{"Pretrain/Learning Rate": 5.155402987609628e-06, "Pretrain/Loss": 1.9948058128356934, "Pretrain/Loss (Raw)": 1.9141826629638672, "Pretrain/Step": 7611, "Pretrain/Step Time": 8.489677673205733} +{"Pretrain/Learning Rate": 5.150240033804116e-06, "Pretrain/Loss": 1.9934699535369873, "Pretrain/Loss (Raw)": 1.8500850200653076, "Pretrain/Step": 7612, "Pretrain/Step Time": 8.488762686029077} +{"Pretrain/Learning Rate": 5.145079369661443e-06, "Pretrain/Loss": 1.9926676750183105, "Pretrain/Loss (Raw)": 2.0894558429718018, "Pretrain/Step": 7613, "Pretrain/Step Time": 8.487212434411049} +{"Pretrain/Learning Rate": 5.139920995776884e-06, "Pretrain/Loss": 1.9929752349853516, "Pretrain/Loss (Raw)": 2.136932134628296, "Pretrain/Step": 7614, "Pretrain/Step Time": 8.487332601100206} +{"Pretrain/Learning Rate": 5.134764912745457e-06, "Pretrain/Loss": 1.9918209314346313, "Pretrain/Loss (Raw)": 1.9818741083145142, "Pretrain/Step": 7615, "Pretrain/Step Time": 8.48445064947009} +{"Pretrain/Learning Rate": 5.1296111211619146e-06, "Pretrain/Loss": 1.9903171062469482, "Pretrain/Loss (Raw)": 1.863237738609314, "Pretrain/Step": 7616, "Pretrain/Step Time": 8.486749392002821} +{"Pretrain/Learning Rate": 5.1244596216207555e-06, "Pretrain/Loss": 1.9920454025268555, "Pretrain/Loss (Raw)": 2.1551594734191895, "Pretrain/Step": 7617, "Pretrain/Step Time": 8.488789089024067} +{"Pretrain/Learning Rate": 5.1193104147161885e-06, "Pretrain/Loss": 1.990803599357605, "Pretrain/Loss (Raw)": 2.0274581909179688, "Pretrain/Step": 7618, "Pretrain/Step Time": 8.491803087294102} +{"Pretrain/Learning Rate": 5.114163501042182e-06, "Pretrain/Loss": 1.990860104560852, "Pretrain/Loss (Raw)": 1.917769432067871, "Pretrain/Step": 7619, "Pretrain/Step Time": 8.487391795963049} +{"Pretrain/Learning Rate": 5.109018881192423e-06, "Pretrain/Loss": 1.9921352863311768, "Pretrain/Loss (Raw)": 2.118945837020874, "Pretrain/Step": 7620, "Pretrain/Step Time": 8.486334782093763} +{"Pretrain/Learning Rate": 5.103876555760345e-06, "Pretrain/Loss": 1.9907948970794678, "Pretrain/Loss (Raw)": 2.0129144191741943, "Pretrain/Step": 7621, "Pretrain/Step Time": 8.487874019891024} +{"Pretrain/Learning Rate": 5.098736525339115e-06, "Pretrain/Loss": 1.9903531074523926, "Pretrain/Loss (Raw)": 2.0428874492645264, "Pretrain/Step": 7622, "Pretrain/Step Time": 8.486946161836386} +{"Pretrain/Learning Rate": 5.093598790521634e-06, "Pretrain/Loss": 1.9897656440734863, "Pretrain/Loss (Raw)": 1.9641175270080566, "Pretrain/Step": 7623, "Pretrain/Step Time": 8.48742781020701} +{"Pretrain/Learning Rate": 5.088463351900541e-06, "Pretrain/Loss": 1.9878379106521606, "Pretrain/Loss (Raw)": 1.86714506149292, "Pretrain/Step": 7624, "Pretrain/Step Time": 8.486547250300646} +{"Pretrain/Learning Rate": 5.0833302100681965e-06, "Pretrain/Loss": 1.9869003295898438, "Pretrain/Loss (Raw)": 1.950839638710022, "Pretrain/Step": 7625, "Pretrain/Step Time": 8.483002895489335} +{"Pretrain/Learning Rate": 5.078199365616715e-06, "Pretrain/Loss": 1.98567533493042, "Pretrain/Loss (Raw)": 1.848404049873352, "Pretrain/Step": 7626, "Pretrain/Step Time": 8.482642346993089} +{"Pretrain/Learning Rate": 5.073070819137934e-06, "Pretrain/Loss": 1.9874720573425293, "Pretrain/Loss (Raw)": 2.249680280685425, "Pretrain/Step": 7627, "Pretrain/Step Time": 8.482974596321583} +{"Pretrain/Learning Rate": 5.067944571223432e-06, "Pretrain/Loss": 1.9865387678146362, "Pretrain/Loss (Raw)": 1.931456446647644, "Pretrain/Step": 7628, "Pretrain/Step Time": 8.48204168304801} +{"Pretrain/Learning Rate": 5.062820622464526e-06, "Pretrain/Loss": 1.9879310131072998, "Pretrain/Loss (Raw)": 2.0342025756835938, "Pretrain/Step": 7629, "Pretrain/Step Time": 8.482832139357924} +{"Pretrain/Learning Rate": 5.057698973452249e-06, "Pretrain/Loss": 1.9848852157592773, "Pretrain/Loss (Raw)": 1.7249361276626587, "Pretrain/Step": 7630, "Pretrain/Step Time": 8.484570126980543} +{"Pretrain/Learning Rate": 5.052579624777384e-06, "Pretrain/Loss": 1.9864158630371094, "Pretrain/Loss (Raw)": 2.0959835052490234, "Pretrain/Step": 7631, "Pretrain/Step Time": 8.48154085315764} +{"Pretrain/Learning Rate": 5.047462577030451e-06, "Pretrain/Loss": 1.9868595600128174, "Pretrain/Loss (Raw)": 2.0064568519592285, "Pretrain/Step": 7632, "Pretrain/Step Time": 8.4805374071002} +{"Pretrain/Learning Rate": 5.042347830801705e-06, "Pretrain/Loss": 1.9866671562194824, "Pretrain/Loss (Raw)": 1.939743995666504, "Pretrain/Step": 7633, "Pretrain/Step Time": 8.482015704736114} +{"Pretrain/Learning Rate": 5.037235386681116e-06, "Pretrain/Loss": 1.9890024662017822, "Pretrain/Loss (Raw)": 2.1683437824249268, "Pretrain/Step": 7634, "Pretrain/Step Time": 8.479534596204758} +{"Pretrain/Learning Rate": 5.032125245258409e-06, "Pretrain/Loss": 1.9893364906311035, "Pretrain/Loss (Raw)": 1.904941201210022, "Pretrain/Step": 7635, "Pretrain/Step Time": 8.485240135341883} +{"Pretrain/Learning Rate": 5.027017407123047e-06, "Pretrain/Loss": 1.9884884357452393, "Pretrain/Loss (Raw)": 1.9551568031311035, "Pretrain/Step": 7636, "Pretrain/Step Time": 8.482625367119908} +{"Pretrain/Learning Rate": 5.021911872864199e-06, "Pretrain/Loss": 1.9893519878387451, "Pretrain/Loss (Raw)": 1.9084205627441406, "Pretrain/Step": 7637, "Pretrain/Step Time": 8.485458688810468} +{"Pretrain/Learning Rate": 5.016808643070798e-06, "Pretrain/Loss": 1.989858865737915, "Pretrain/Loss (Raw)": 2.0115840435028076, "Pretrain/Step": 7638, "Pretrain/Step Time": 8.485645206645131} +{"Pretrain/Learning Rate": 5.011707718331496e-06, "Pretrain/Loss": 1.9894524812698364, "Pretrain/Loss (Raw)": 1.9360017776489258, "Pretrain/Step": 7639, "Pretrain/Step Time": 8.487905351445079} +{"Pretrain/Learning Rate": 5.0066090992346905e-06, "Pretrain/Loss": 1.9902111291885376, "Pretrain/Loss (Raw)": 2.0961413383483887, "Pretrain/Step": 7640, "Pretrain/Step Time": 8.488446710631251} +{"Pretrain/Learning Rate": 5.001512786368492e-06, "Pretrain/Loss": 1.9901833534240723, "Pretrain/Loss (Raw)": 2.1172075271606445, "Pretrain/Step": 7641, "Pretrain/Step Time": 8.488127680495381} +{"Pretrain/Learning Rate": 4.996418780320766e-06, "Pretrain/Loss": 1.9893369674682617, "Pretrain/Loss (Raw)": 1.9549258947372437, "Pretrain/Step": 7642, "Pretrain/Step Time": 8.487348450347781} +{"Pretrain/Learning Rate": 4.991327081679106e-06, "Pretrain/Loss": 1.9894616603851318, "Pretrain/Loss (Raw)": 2.1611783504486084, "Pretrain/Step": 7643, "Pretrain/Step Time": 8.484039733186364} +{"Pretrain/Learning Rate": 4.986237691030835e-06, "Pretrain/Loss": 1.9878861904144287, "Pretrain/Loss (Raw)": 1.8266594409942627, "Pretrain/Step": 7644, "Pretrain/Step Time": 8.48698659427464} +{"Pretrain/Learning Rate": 4.981150608963017e-06, "Pretrain/Loss": 1.9876070022583008, "Pretrain/Loss (Raw)": 1.9140150547027588, "Pretrain/Step": 7645, "Pretrain/Step Time": 8.488171311095357} +{"Pretrain/Learning Rate": 4.9760658360624355e-06, "Pretrain/Loss": 1.9889318943023682, "Pretrain/Loss (Raw)": 2.0264174938201904, "Pretrain/Step": 7646, "Pretrain/Step Time": 8.482902627438307} +{"Pretrain/Learning Rate": 4.9709833729156246e-06, "Pretrain/Loss": 1.989531397819519, "Pretrain/Loss (Raw)": 2.105520486831665, "Pretrain/Step": 7647, "Pretrain/Step Time": 8.48301736265421} +{"Pretrain/Learning Rate": 4.965903220108842e-06, "Pretrain/Loss": 1.9894821643829346, "Pretrain/Loss (Raw)": 1.96231210231781, "Pretrain/Step": 7648, "Pretrain/Step Time": 8.482330296188593} +{"Pretrain/Learning Rate": 4.960825378228082e-06, "Pretrain/Loss": 1.9913039207458496, "Pretrain/Loss (Raw)": 2.187270402908325, "Pretrain/Step": 7649, "Pretrain/Step Time": 8.480263767763972} +{"Pretrain/Learning Rate": 4.9557498478590785e-06, "Pretrain/Loss": 1.9957380294799805, "Pretrain/Loss (Raw)": 2.2491490840911865, "Pretrain/Step": 7650, "Pretrain/Step Time": 8.48302298411727} +{"Pretrain/Learning Rate": 4.950676629587281e-06, "Pretrain/Loss": 1.9965543746948242, "Pretrain/Loss (Raw)": 2.06945538520813, "Pretrain/Step": 7651, "Pretrain/Step Time": 8.485490331426263} +{"Pretrain/Learning Rate": 4.945605723997896e-06, "Pretrain/Loss": 1.9965643882751465, "Pretrain/Loss (Raw)": 2.0578291416168213, "Pretrain/Step": 7652, "Pretrain/Step Time": 8.484364436939359} +{"Pretrain/Learning Rate": 4.9405371316758345e-06, "Pretrain/Loss": 1.9958975315093994, "Pretrain/Loss (Raw)": 1.8381483554840088, "Pretrain/Step": 7653, "Pretrain/Step Time": 8.485687255859375} +{"Pretrain/Learning Rate": 4.935470853205765e-06, "Pretrain/Loss": 1.9963188171386719, "Pretrain/Loss (Raw)": 1.8780839443206787, "Pretrain/Step": 7654, "Pretrain/Step Time": 8.490405714139342} +{"Pretrain/Learning Rate": 4.93040688917209e-06, "Pretrain/Loss": 1.9947574138641357, "Pretrain/Loss (Raw)": 1.9755942821502686, "Pretrain/Step": 7655, "Pretrain/Step Time": 8.487751260399818} +{"Pretrain/Learning Rate": 4.9253452401589185e-06, "Pretrain/Loss": 1.9950616359710693, "Pretrain/Loss (Raw)": 2.019240140914917, "Pretrain/Step": 7656, "Pretrain/Step Time": 8.488195080310106} +{"Pretrain/Learning Rate": 4.920285906750122e-06, "Pretrain/Loss": 1.9962081909179688, "Pretrain/Loss (Raw)": 2.0992398262023926, "Pretrain/Step": 7657, "Pretrain/Step Time": 8.49271397292614} +{"Pretrain/Learning Rate": 4.9152288895292855e-06, "Pretrain/Loss": 1.9962148666381836, "Pretrain/Loss (Raw)": 1.8849866390228271, "Pretrain/Step": 7658, "Pretrain/Step Time": 8.494619207456708} +{"Pretrain/Learning Rate": 4.910174189079742e-06, "Pretrain/Loss": 1.9977786540985107, "Pretrain/Loss (Raw)": 2.0671632289886475, "Pretrain/Step": 7659, "Pretrain/Step Time": 8.49089570529759} +{"Pretrain/Learning Rate": 4.9051218059845446e-06, "Pretrain/Loss": 1.9953420162200928, "Pretrain/Loss (Raw)": 1.762762427330017, "Pretrain/Step": 7660, "Pretrain/Step Time": 8.49103032425046} +{"Pretrain/Learning Rate": 4.900071740826489e-06, "Pretrain/Loss": 1.9960424900054932, "Pretrain/Loss (Raw)": 2.069840431213379, "Pretrain/Step": 7661, "Pretrain/Step Time": 8.487568035721779} +{"Pretrain/Learning Rate": 4.8950239941880914e-06, "Pretrain/Loss": 1.9962574243545532, "Pretrain/Loss (Raw)": 2.1922879219055176, "Pretrain/Step": 7662, "Pretrain/Step Time": 8.484433909878135} +{"Pretrain/Learning Rate": 4.88997856665161e-06, "Pretrain/Loss": 1.9952170848846436, "Pretrain/Loss (Raw)": 1.9272305965423584, "Pretrain/Step": 7663, "Pretrain/Step Time": 8.484533509239554} +{"Pretrain/Learning Rate": 4.884935458799031e-06, "Pretrain/Loss": 1.9936752319335938, "Pretrain/Loss (Raw)": 1.935586929321289, "Pretrain/Step": 7664, "Pretrain/Step Time": 8.483868725597858} +{"Pretrain/Learning Rate": 4.879894671212082e-06, "Pretrain/Loss": 1.9934093952178955, "Pretrain/Loss (Raw)": 1.9946130514144897, "Pretrain/Step": 7665, "Pretrain/Step Time": 8.485350962728262} +{"Pretrain/Learning Rate": 4.874856204472217e-06, "Pretrain/Loss": 1.9932639598846436, "Pretrain/Loss (Raw)": 1.9596580266952515, "Pretrain/Step": 7666, "Pretrain/Step Time": 8.489273419603705} +{"Pretrain/Learning Rate": 4.869820059160607e-06, "Pretrain/Loss": 1.9929672479629517, "Pretrain/Loss (Raw)": 1.8952741622924805, "Pretrain/Step": 7667, "Pretrain/Step Time": 8.486543091014028} +{"Pretrain/Learning Rate": 4.864786235858187e-06, "Pretrain/Loss": 1.9938580989837646, "Pretrain/Loss (Raw)": 2.023937463760376, "Pretrain/Step": 7668, "Pretrain/Step Time": 8.486862072721124} +{"Pretrain/Learning Rate": 4.859754735145594e-06, "Pretrain/Loss": 1.996156930923462, "Pretrain/Loss (Raw)": 2.1436963081359863, "Pretrain/Step": 7669, "Pretrain/Step Time": 8.483531441539526} +{"Pretrain/Learning Rate": 4.854725557603215e-06, "Pretrain/Loss": 1.9974148273468018, "Pretrain/Loss (Raw)": 2.008607864379883, "Pretrain/Step": 7670, "Pretrain/Step Time": 8.485598418861628} +{"Pretrain/Learning Rate": 4.8496987038111674e-06, "Pretrain/Loss": 1.9973227977752686, "Pretrain/Loss (Raw)": 2.139796733856201, "Pretrain/Step": 7671, "Pretrain/Step Time": 8.485037058591843} +{"Pretrain/Learning Rate": 4.844674174349287e-06, "Pretrain/Loss": 1.9988007545471191, "Pretrain/Loss (Raw)": 2.035249948501587, "Pretrain/Step": 7672, "Pretrain/Step Time": 8.490923691540956} +{"Pretrain/Learning Rate": 4.83965196979716e-06, "Pretrain/Loss": 1.9989594221115112, "Pretrain/Loss (Raw)": 1.8222235441207886, "Pretrain/Step": 7673, "Pretrain/Step Time": 8.4881956204772} +{"Pretrain/Learning Rate": 4.83463209073409e-06, "Pretrain/Loss": 2.0005555152893066, "Pretrain/Loss (Raw)": 2.1636927127838135, "Pretrain/Step": 7674, "Pretrain/Step Time": 8.488860143348575} +{"Pretrain/Learning Rate": 4.829614537739124e-06, "Pretrain/Loss": 1.9999600648880005, "Pretrain/Loss (Raw)": 1.8666191101074219, "Pretrain/Step": 7675, "Pretrain/Step Time": 8.486019352450967} +{"Pretrain/Learning Rate": 4.824599311391031e-06, "Pretrain/Loss": 2.000763177871704, "Pretrain/Loss (Raw)": 2.0461597442626953, "Pretrain/Step": 7676, "Pretrain/Step Time": 8.484942698851228} +{"Pretrain/Learning Rate": 4.819586412268326e-06, "Pretrain/Loss": 2.0013222694396973, "Pretrain/Loss (Raw)": 2.1285998821258545, "Pretrain/Step": 7677, "Pretrain/Step Time": 8.48156957142055} +{"Pretrain/Learning Rate": 4.814575840949228e-06, "Pretrain/Loss": 2.002528190612793, "Pretrain/Loss (Raw)": 2.0671069622039795, "Pretrain/Step": 7678, "Pretrain/Step Time": 8.478563336655498} +{"Pretrain/Learning Rate": 4.809567598011714e-06, "Pretrain/Loss": 2.0032389163970947, "Pretrain/Loss (Raw)": 1.8588987588882446, "Pretrain/Step": 7679, "Pretrain/Step Time": 8.481670944020152} +{"Pretrain/Learning Rate": 4.8045616840334816e-06, "Pretrain/Loss": 2.0037853717803955, "Pretrain/Loss (Raw)": 1.974062204360962, "Pretrain/Step": 7680, "Pretrain/Step Time": 8.478243574500084} +{"Pretrain/Learning Rate": 4.799558099591961e-06, "Pretrain/Loss": 2.0038323402404785, "Pretrain/Loss (Raw)": 2.0563671588897705, "Pretrain/Step": 7681, "Pretrain/Step Time": 8.481480948626995} +{"Pretrain/Learning Rate": 4.794556845264322e-06, "Pretrain/Loss": 2.00443172454834, "Pretrain/Loss (Raw)": 2.1155519485473633, "Pretrain/Step": 7682, "Pretrain/Step Time": 8.481098728254437} +{"Pretrain/Learning Rate": 4.789557921627444e-06, "Pretrain/Loss": 2.003937005996704, "Pretrain/Loss (Raw)": 1.9494671821594238, "Pretrain/Step": 7683, "Pretrain/Step Time": 8.485658917576075} +{"Pretrain/Learning Rate": 4.7845613292579585e-06, "Pretrain/Loss": 2.0026469230651855, "Pretrain/Loss (Raw)": 1.8458824157714844, "Pretrain/Step": 7684, "Pretrain/Step Time": 8.48525544628501} +{"Pretrain/Learning Rate": 4.779567068732224e-06, "Pretrain/Loss": 2.0011448860168457, "Pretrain/Loss (Raw)": 1.8109376430511475, "Pretrain/Step": 7685, "Pretrain/Step Time": 8.486042201519012} +{"Pretrain/Learning Rate": 4.7745751406263165e-06, "Pretrain/Loss": 2.001500129699707, "Pretrain/Loss (Raw)": 2.0913803577423096, "Pretrain/Step": 7686, "Pretrain/Step Time": 8.488300539553165} +{"Pretrain/Learning Rate": 4.769585545516065e-06, "Pretrain/Loss": 1.999803900718689, "Pretrain/Loss (Raw)": 1.7940874099731445, "Pretrain/Step": 7687, "Pretrain/Step Time": 8.488004978746176} +{"Pretrain/Learning Rate": 4.764598283977004e-06, "Pretrain/Loss": 2.00046443939209, "Pretrain/Loss (Raw)": 2.199730157852173, "Pretrain/Step": 7688, "Pretrain/Step Time": 8.487109199166298} +{"Pretrain/Learning Rate": 4.759613356584422e-06, "Pretrain/Loss": 1.9993107318878174, "Pretrain/Loss (Raw)": 1.9527336359024048, "Pretrain/Step": 7689, "Pretrain/Step Time": 8.489184148609638} +{"Pretrain/Learning Rate": 4.754630763913323e-06, "Pretrain/Loss": 2.0026776790618896, "Pretrain/Loss (Raw)": 2.087505578994751, "Pretrain/Step": 7690, "Pretrain/Step Time": 8.49005808122456} +{"Pretrain/Learning Rate": 4.749650506538453e-06, "Pretrain/Loss": 2.0025813579559326, "Pretrain/Loss (Raw)": 1.8617607355117798, "Pretrain/Step": 7691, "Pretrain/Step Time": 8.48848282545805} +{"Pretrain/Learning Rate": 4.7446725850342875e-06, "Pretrain/Loss": 2.0053958892822266, "Pretrain/Loss (Raw)": 2.093564748764038, "Pretrain/Step": 7692, "Pretrain/Step Time": 8.486668264493346} +{"Pretrain/Learning Rate": 4.739696999975013e-06, "Pretrain/Loss": 2.0060081481933594, "Pretrain/Loss (Raw)": 1.9455162286758423, "Pretrain/Step": 7693, "Pretrain/Step Time": 8.483412463217974} +{"Pretrain/Learning Rate": 4.734723751934572e-06, "Pretrain/Loss": 2.005215883255005, "Pretrain/Loss (Raw)": 1.8985142707824707, "Pretrain/Step": 7694, "Pretrain/Step Time": 8.482509285211563} +{"Pretrain/Learning Rate": 4.729752841486623e-06, "Pretrain/Loss": 2.0043158531188965, "Pretrain/Loss (Raw)": 1.942702054977417, "Pretrain/Step": 7695, "Pretrain/Step Time": 8.482593966647983} +{"Pretrain/Learning Rate": 4.72478426920456e-06, "Pretrain/Loss": 2.001831531524658, "Pretrain/Loss (Raw)": 1.7505906820297241, "Pretrain/Step": 7696, "Pretrain/Step Time": 8.485962729901075} +{"Pretrain/Learning Rate": 4.719818035661508e-06, "Pretrain/Loss": 2.0014383792877197, "Pretrain/Loss (Raw)": 1.8864644765853882, "Pretrain/Step": 7697, "Pretrain/Step Time": 8.489159427583218} +{"Pretrain/Learning Rate": 4.714854141430322e-06, "Pretrain/Loss": 2.0002737045288086, "Pretrain/Loss (Raw)": 2.078155755996704, "Pretrain/Step": 7698, "Pretrain/Step Time": 8.486969904974103} +{"Pretrain/Learning Rate": 4.709892587083578e-06, "Pretrain/Loss": 1.9997010231018066, "Pretrain/Loss (Raw)": 1.9498956203460693, "Pretrain/Step": 7699, "Pretrain/Step Time": 8.485835943371058} +{"Pretrain/Learning Rate": 4.704933373193593e-06, "Pretrain/Loss": 1.998740792274475, "Pretrain/Loss (Raw)": 1.823323130607605, "Pretrain/Step": 7700, "Pretrain/Step Time": 8.485676802694798} +{"Pretrain/Learning Rate": 4.699976500332418e-06, "Pretrain/Loss": 1.9971551895141602, "Pretrain/Loss (Raw)": 1.9295432567596436, "Pretrain/Step": 7701, "Pretrain/Step Time": 8.487090220674872} +{"Pretrain/Learning Rate": 4.695021969071811e-06, "Pretrain/Loss": 1.9967135190963745, "Pretrain/Loss (Raw)": 2.022287130355835, "Pretrain/Step": 7702, "Pretrain/Step Time": 8.48770871013403} +{"Pretrain/Learning Rate": 4.690069779983294e-06, "Pretrain/Loss": 1.9979294538497925, "Pretrain/Loss (Raw)": 2.0641605854034424, "Pretrain/Step": 7703, "Pretrain/Step Time": 8.486046949401498} +{"Pretrain/Learning Rate": 4.685119933638082e-06, "Pretrain/Loss": 1.999123454093933, "Pretrain/Loss (Raw)": 2.141556739807129, "Pretrain/Step": 7704, "Pretrain/Step Time": 8.48734775930643} +{"Pretrain/Learning Rate": 4.680172430607146e-06, "Pretrain/Loss": 1.998929500579834, "Pretrain/Loss (Raw)": 2.1305618286132812, "Pretrain/Step": 7705, "Pretrain/Step Time": 8.486379308626056} +{"Pretrain/Learning Rate": 4.675227271461182e-06, "Pretrain/Loss": 1.9977226257324219, "Pretrain/Loss (Raw)": 1.8557212352752686, "Pretrain/Step": 7706, "Pretrain/Step Time": 8.48668447509408} +{"Pretrain/Learning Rate": 4.670284456770607e-06, "Pretrain/Loss": 1.9991791248321533, "Pretrain/Loss (Raw)": 1.902444839477539, "Pretrain/Step": 7707, "Pretrain/Step Time": 8.488295873627067} +{"Pretrain/Learning Rate": 4.665343987105583e-06, "Pretrain/Loss": 1.9981110095977783, "Pretrain/Loss (Raw)": 1.8550294637680054, "Pretrain/Step": 7708, "Pretrain/Step Time": 8.488392719998956} +{"Pretrain/Learning Rate": 4.660405863035977e-06, "Pretrain/Loss": 1.9966464042663574, "Pretrain/Loss (Raw)": 1.9429941177368164, "Pretrain/Step": 7709, "Pretrain/Step Time": 8.487909378483891} +{"Pretrain/Learning Rate": 4.655470085131408e-06, "Pretrain/Loss": 1.9978795051574707, "Pretrain/Loss (Raw)": 2.1339175701141357, "Pretrain/Step": 7710, "Pretrain/Step Time": 8.489249808713794} +{"Pretrain/Learning Rate": 4.650536653961215e-06, "Pretrain/Loss": 1.9986847639083862, "Pretrain/Loss (Raw)": 1.9902288913726807, "Pretrain/Step": 7711, "Pretrain/Step Time": 8.487134713679552} +{"Pretrain/Learning Rate": 4.645605570094466e-06, "Pretrain/Loss": 2.0014891624450684, "Pretrain/Loss (Raw)": 2.0516316890716553, "Pretrain/Step": 7712, "Pretrain/Step Time": 8.48182942532003} +{"Pretrain/Learning Rate": 4.640676834099969e-06, "Pretrain/Loss": 1.999701738357544, "Pretrain/Loss (Raw)": 1.936455249786377, "Pretrain/Step": 7713, "Pretrain/Step Time": 8.490070134401321} +{"Pretrain/Learning Rate": 4.635750446546239e-06, "Pretrain/Loss": 2.0002970695495605, "Pretrain/Loss (Raw)": 1.9792343378067017, "Pretrain/Step": 7714, "Pretrain/Step Time": 8.488262131810188} +{"Pretrain/Learning Rate": 4.630826408001537e-06, "Pretrain/Loss": 1.9983625411987305, "Pretrain/Loss (Raw)": 1.8485898971557617, "Pretrain/Step": 7715, "Pretrain/Step Time": 8.490653902292252} +{"Pretrain/Learning Rate": 4.62590471903385e-06, "Pretrain/Loss": 1.998522162437439, "Pretrain/Loss (Raw)": 2.041269302368164, "Pretrain/Step": 7716, "Pretrain/Step Time": 8.484708597883582} +{"Pretrain/Learning Rate": 4.620985380210901e-06, "Pretrain/Loss": 1.9966471195220947, "Pretrain/Loss (Raw)": 1.9370841979980469, "Pretrain/Step": 7717, "Pretrain/Step Time": 8.487804647535086} +{"Pretrain/Learning Rate": 4.61606839210012e-06, "Pretrain/Loss": 1.9937565326690674, "Pretrain/Loss (Raw)": 1.8179081678390503, "Pretrain/Step": 7718, "Pretrain/Step Time": 8.485526574775577} +{"Pretrain/Learning Rate": 4.611153755268688e-06, "Pretrain/Loss": 1.9936341047286987, "Pretrain/Loss (Raw)": 1.9612947702407837, "Pretrain/Step": 7719, "Pretrain/Step Time": 8.488659696653485} +{"Pretrain/Learning Rate": 4.606241470283512e-06, "Pretrain/Loss": 1.99497389793396, "Pretrain/Loss (Raw)": 2.1861894130706787, "Pretrain/Step": 7720, "Pretrain/Step Time": 8.487452311441302} +{"Pretrain/Learning Rate": 4.601331537711207e-06, "Pretrain/Loss": 1.9964063167572021, "Pretrain/Loss (Raw)": 2.012186050415039, "Pretrain/Step": 7721, "Pretrain/Step Time": 8.488844741135836} +{"Pretrain/Learning Rate": 4.59642395811814e-06, "Pretrain/Loss": 1.9946701526641846, "Pretrain/Loss (Raw)": 1.9829003810882568, "Pretrain/Step": 7722, "Pretrain/Step Time": 8.490550942718983} +{"Pretrain/Learning Rate": 4.591518732070402e-06, "Pretrain/Loss": 1.9972895383834839, "Pretrain/Loss (Raw)": 2.1524360179901123, "Pretrain/Step": 7723, "Pretrain/Step Time": 8.488396937027574} +{"Pretrain/Learning Rate": 4.586615860133811e-06, "Pretrain/Loss": 1.9978532791137695, "Pretrain/Loss (Raw)": 1.9720845222473145, "Pretrain/Step": 7724, "Pretrain/Step Time": 8.488719176501036} +{"Pretrain/Learning Rate": 4.581715342873899e-06, "Pretrain/Loss": 2.000394344329834, "Pretrain/Loss (Raw)": 1.9648610353469849, "Pretrain/Step": 7725, "Pretrain/Step Time": 8.482751490548253} +{"Pretrain/Learning Rate": 4.57681718085595e-06, "Pretrain/Loss": 1.9997872114181519, "Pretrain/Loss (Raw)": 2.111525058746338, "Pretrain/Step": 7726, "Pretrain/Step Time": 8.481723628938198} +{"Pretrain/Learning Rate": 4.571921374644958e-06, "Pretrain/Loss": 2.000093460083008, "Pretrain/Loss (Raw)": 2.0891964435577393, "Pretrain/Step": 7727, "Pretrain/Step Time": 8.482722641900182} +{"Pretrain/Learning Rate": 4.5670279248056585e-06, "Pretrain/Loss": 1.9988986253738403, "Pretrain/Loss (Raw)": 1.9367789030075073, "Pretrain/Step": 7728, "Pretrain/Step Time": 8.481474537402391} +{"Pretrain/Learning Rate": 4.562136831902514e-06, "Pretrain/Loss": 1.9980902671813965, "Pretrain/Loss (Raw)": 2.019193172454834, "Pretrain/Step": 7729, "Pretrain/Step Time": 8.486341185867786} +{"Pretrain/Learning Rate": 4.557248096499697e-06, "Pretrain/Loss": 1.997381329536438, "Pretrain/Loss (Raw)": 1.9909167289733887, "Pretrain/Step": 7730, "Pretrain/Step Time": 8.486342199146748} +{"Pretrain/Learning Rate": 4.552361719161127e-06, "Pretrain/Loss": 1.995538353919983, "Pretrain/Loss (Raw)": 1.849151372909546, "Pretrain/Step": 7731, "Pretrain/Step Time": 8.482802925631404} +{"Pretrain/Learning Rate": 4.547477700450448e-06, "Pretrain/Loss": 1.9963459968566895, "Pretrain/Loss (Raw)": 2.093122720718384, "Pretrain/Step": 7732, "Pretrain/Step Time": 8.483574759215117} +{"Pretrain/Learning Rate": 4.542596040931029e-06, "Pretrain/Loss": 1.9937033653259277, "Pretrain/Loss (Raw)": 1.934548020362854, "Pretrain/Step": 7733, "Pretrain/Step Time": 8.482960846275091} +{"Pretrain/Learning Rate": 4.537716741165973e-06, "Pretrain/Loss": 1.9932016134262085, "Pretrain/Loss (Raw)": 2.129258155822754, "Pretrain/Step": 7734, "Pretrain/Step Time": 8.480328373610973} +{"Pretrain/Learning Rate": 4.532839801718095e-06, "Pretrain/Loss": 1.9939758777618408, "Pretrain/Loss (Raw)": 2.0239312648773193, "Pretrain/Step": 7735, "Pretrain/Step Time": 8.47828190587461} +{"Pretrain/Learning Rate": 4.527965223149957e-06, "Pretrain/Loss": 1.9934663772583008, "Pretrain/Loss (Raw)": 1.9622881412506104, "Pretrain/Step": 7736, "Pretrain/Step Time": 8.480717562139034} +{"Pretrain/Learning Rate": 4.523093006023832e-06, "Pretrain/Loss": 1.9954397678375244, "Pretrain/Loss (Raw)": 2.24633526802063, "Pretrain/Step": 7737, "Pretrain/Step Time": 8.481880078092217} +{"Pretrain/Learning Rate": 4.518223150901732e-06, "Pretrain/Loss": 1.9966869354248047, "Pretrain/Loss (Raw)": 2.12821888923645, "Pretrain/Step": 7738, "Pretrain/Step Time": 8.481885006651282} +{"Pretrain/Learning Rate": 4.513355658345392e-06, "Pretrain/Loss": 1.997471570968628, "Pretrain/Loss (Raw)": 2.014617919921875, "Pretrain/Step": 7739, "Pretrain/Step Time": 8.481119845062494} +{"Pretrain/Learning Rate": 4.508490528916287e-06, "Pretrain/Loss": 1.9962680339813232, "Pretrain/Loss (Raw)": 1.6960176229476929, "Pretrain/Step": 7740, "Pretrain/Step Time": 8.484033493325114} +{"Pretrain/Learning Rate": 4.503627763175589e-06, "Pretrain/Loss": 1.996356725692749, "Pretrain/Loss (Raw)": 2.1008052825927734, "Pretrain/Step": 7741, "Pretrain/Step Time": 8.480946594849229} +{"Pretrain/Learning Rate": 4.498767361684228e-06, "Pretrain/Loss": 1.9956278800964355, "Pretrain/Loss (Raw)": 2.0436599254608154, "Pretrain/Step": 7742, "Pretrain/Step Time": 8.480446288362145} +{"Pretrain/Learning Rate": 4.493909325002846e-06, "Pretrain/Loss": 1.9943300485610962, "Pretrain/Loss (Raw)": 1.8157405853271484, "Pretrain/Step": 7743, "Pretrain/Step Time": 8.485745195299387} +{"Pretrain/Learning Rate": 4.489053653691816e-06, "Pretrain/Loss": 1.9943256378173828, "Pretrain/Loss (Raw)": 1.8626880645751953, "Pretrain/Step": 7744, "Pretrain/Step Time": 8.486315226182342} +{"Pretrain/Learning Rate": 4.484200348311246e-06, "Pretrain/Loss": 1.9929835796356201, "Pretrain/Loss (Raw)": 1.9833565950393677, "Pretrain/Step": 7745, "Pretrain/Step Time": 8.482118178158998} +{"Pretrain/Learning Rate": 4.4793494094209496e-06, "Pretrain/Loss": 1.9934560060501099, "Pretrain/Loss (Raw)": 2.0879478454589844, "Pretrain/Step": 7746, "Pretrain/Step Time": 8.478850765153766} +{"Pretrain/Learning Rate": 4.4745008375804866e-06, "Pretrain/Loss": 1.9941877126693726, "Pretrain/Loss (Raw)": 2.011422634124756, "Pretrain/Step": 7747, "Pretrain/Step Time": 8.480405285954475} +{"Pretrain/Learning Rate": 4.469654633349141e-06, "Pretrain/Loss": 1.9924988746643066, "Pretrain/Loss (Raw)": 1.9027695655822754, "Pretrain/Step": 7748, "Pretrain/Step Time": 8.480543673038483} +{"Pretrain/Learning Rate": 4.464810797285918e-06, "Pretrain/Loss": 1.991765022277832, "Pretrain/Loss (Raw)": 1.9189902544021606, "Pretrain/Step": 7749, "Pretrain/Step Time": 8.48256041109562} +{"Pretrain/Learning Rate": 4.459969329949559e-06, "Pretrain/Loss": 1.9900158643722534, "Pretrain/Loss (Raw)": 1.8189891576766968, "Pretrain/Step": 7750, "Pretrain/Step Time": 8.485705360770226} +{"Pretrain/Learning Rate": 4.455130231898513e-06, "Pretrain/Loss": 1.9906976222991943, "Pretrain/Loss (Raw)": 2.0513834953308105, "Pretrain/Step": 7751, "Pretrain/Step Time": 8.484988098964095} +{"Pretrain/Learning Rate": 4.45029350369098e-06, "Pretrain/Loss": 1.991844654083252, "Pretrain/Loss (Raw)": 2.0139784812927246, "Pretrain/Step": 7752, "Pretrain/Step Time": 8.488087875768542} +{"Pretrain/Learning Rate": 4.445459145884864e-06, "Pretrain/Loss": 1.993287205696106, "Pretrain/Loss (Raw)": 2.1354689598083496, "Pretrain/Step": 7753, "Pretrain/Step Time": 8.488766083493829} +{"Pretrain/Learning Rate": 4.4406271590378135e-06, "Pretrain/Loss": 1.9960349798202515, "Pretrain/Loss (Raw)": 2.200124979019165, "Pretrain/Step": 7754, "Pretrain/Step Time": 8.486490067094564} +{"Pretrain/Learning Rate": 4.435797543707201e-06, "Pretrain/Loss": 1.9944941997528076, "Pretrain/Loss (Raw)": 2.0524532794952393, "Pretrain/Step": 7755, "Pretrain/Step Time": 8.49180518090725} +{"Pretrain/Learning Rate": 4.430970300450107e-06, "Pretrain/Loss": 1.995483160018921, "Pretrain/Loss (Raw)": 2.058039665222168, "Pretrain/Step": 7756, "Pretrain/Step Time": 8.490282662212849} +{"Pretrain/Learning Rate": 4.426145429823361e-06, "Pretrain/Loss": 1.9972362518310547, "Pretrain/Loss (Raw)": 2.2585952281951904, "Pretrain/Step": 7757, "Pretrain/Step Time": 8.4874650798738} +{"Pretrain/Learning Rate": 4.421322932383512e-06, "Pretrain/Loss": 1.998605489730835, "Pretrain/Loss (Raw)": 1.9001883268356323, "Pretrain/Step": 7758, "Pretrain/Step Time": 8.488950420171022} +{"Pretrain/Learning Rate": 4.4165028086868285e-06, "Pretrain/Loss": 1.9989125728607178, "Pretrain/Loss (Raw)": 2.1353023052215576, "Pretrain/Step": 7759, "Pretrain/Step Time": 8.491585355252028} +{"Pretrain/Learning Rate": 4.411685059289314e-06, "Pretrain/Loss": 1.9982695579528809, "Pretrain/Loss (Raw)": 1.9241634607315063, "Pretrain/Step": 7760, "Pretrain/Step Time": 8.486953061074018} +{"Pretrain/Learning Rate": 4.4068696847466975e-06, "Pretrain/Loss": 1.9990360736846924, "Pretrain/Loss (Raw)": 2.037851095199585, "Pretrain/Step": 7761, "Pretrain/Step Time": 8.489069079980254} +{"Pretrain/Learning Rate": 4.40205668561442e-06, "Pretrain/Loss": 1.9968725442886353, "Pretrain/Loss (Raw)": 1.8914214372634888, "Pretrain/Step": 7762, "Pretrain/Step Time": 8.491126636043191} +{"Pretrain/Learning Rate": 4.397246062447666e-06, "Pretrain/Loss": 1.9963929653167725, "Pretrain/Loss (Raw)": 1.843559980392456, "Pretrain/Step": 7763, "Pretrain/Step Time": 8.485654044896364} +{"Pretrain/Learning Rate": 4.3924378158013365e-06, "Pretrain/Loss": 1.9968116283416748, "Pretrain/Loss (Raw)": 2.008737087249756, "Pretrain/Step": 7764, "Pretrain/Step Time": 8.485426461324096} +{"Pretrain/Learning Rate": 4.387631946230064e-06, "Pretrain/Loss": 1.996073842048645, "Pretrain/Loss (Raw)": 1.8139920234680176, "Pretrain/Step": 7765, "Pretrain/Step Time": 8.486493896692991} +{"Pretrain/Learning Rate": 4.38282845428821e-06, "Pretrain/Loss": 1.9965285062789917, "Pretrain/Loss (Raw)": 2.069770336151123, "Pretrain/Step": 7766, "Pretrain/Step Time": 8.48561709932983} +{"Pretrain/Learning Rate": 4.378027340529842e-06, "Pretrain/Loss": 1.9991700649261475, "Pretrain/Loss (Raw)": 2.274111747741699, "Pretrain/Step": 7767, "Pretrain/Step Time": 8.486376849934459} +{"Pretrain/Learning Rate": 4.373228605508772e-06, "Pretrain/Loss": 1.9987115859985352, "Pretrain/Loss (Raw)": 2.037468671798706, "Pretrain/Step": 7768, "Pretrain/Step Time": 8.487505408003926} +{"Pretrain/Learning Rate": 4.368432249778539e-06, "Pretrain/Loss": 1.999598741531372, "Pretrain/Loss (Raw)": 2.2307674884796143, "Pretrain/Step": 7769, "Pretrain/Step Time": 8.489143228158355} +{"Pretrain/Learning Rate": 4.363638273892393e-06, "Pretrain/Loss": 1.999557375907898, "Pretrain/Loss (Raw)": 1.9496302604675293, "Pretrain/Step": 7770, "Pretrain/Step Time": 8.488506795838475} +{"Pretrain/Learning Rate": 4.358846678403322e-06, "Pretrain/Loss": 1.998168706893921, "Pretrain/Loss (Raw)": 1.9834257364273071, "Pretrain/Step": 7771, "Pretrain/Step Time": 8.494497328996658} +{"Pretrain/Learning Rate": 4.354057463864028e-06, "Pretrain/Loss": 1.9985930919647217, "Pretrain/Loss (Raw)": 1.880993127822876, "Pretrain/Step": 7772, "Pretrain/Step Time": 8.490607310086489} +{"Pretrain/Learning Rate": 4.349270630826952e-06, "Pretrain/Loss": 1.9998526573181152, "Pretrain/Loss (Raw)": 2.0752346515655518, "Pretrain/Step": 7773, "Pretrain/Step Time": 8.492325242608786} +{"Pretrain/Learning Rate": 4.344486179844248e-06, "Pretrain/Loss": 1.9987215995788574, "Pretrain/Loss (Raw)": 1.881636142730713, "Pretrain/Step": 7774, "Pretrain/Step Time": 8.491916412487626} +{"Pretrain/Learning Rate": 4.339704111467807e-06, "Pretrain/Loss": 1.997869610786438, "Pretrain/Loss (Raw)": 1.9964596033096313, "Pretrain/Step": 7775, "Pretrain/Step Time": 8.493739603087306} +{"Pretrain/Learning Rate": 4.334924426249243e-06, "Pretrain/Loss": 1.9963254928588867, "Pretrain/Loss (Raw)": 1.7646689414978027, "Pretrain/Step": 7776, "Pretrain/Step Time": 8.491576498374343} +{"Pretrain/Learning Rate": 4.330147124739875e-06, "Pretrain/Loss": 1.9954609870910645, "Pretrain/Loss (Raw)": 2.076615333557129, "Pretrain/Step": 7777, "Pretrain/Step Time": 8.494898287579417} +{"Pretrain/Learning Rate": 4.325372207490774e-06, "Pretrain/Loss": 1.9928865432739258, "Pretrain/Loss (Raw)": 1.919629693031311, "Pretrain/Step": 7778, "Pretrain/Step Time": 8.491276977583766} +{"Pretrain/Learning Rate": 4.320599675052725e-06, "Pretrain/Loss": 1.9924933910369873, "Pretrain/Loss (Raw)": 2.019127607345581, "Pretrain/Step": 7779, "Pretrain/Step Time": 8.488678634166718} +{"Pretrain/Learning Rate": 4.315829527976234e-06, "Pretrain/Loss": 1.9909236431121826, "Pretrain/Loss (Raw)": 1.856888771057129, "Pretrain/Step": 7780, "Pretrain/Step Time": 8.490163000300527} +{"Pretrain/Learning Rate": 4.3110617668115386e-06, "Pretrain/Loss": 1.9933199882507324, "Pretrain/Loss (Raw)": 2.14490008354187, "Pretrain/Step": 7781, "Pretrain/Step Time": 8.491564754396677} +{"Pretrain/Learning Rate": 4.306296392108605e-06, "Pretrain/Loss": 1.9938101768493652, "Pretrain/Loss (Raw)": 1.940807819366455, "Pretrain/Step": 7782, "Pretrain/Step Time": 8.488888228312135} +{"Pretrain/Learning Rate": 4.301533404417102e-06, "Pretrain/Loss": 1.9919437170028687, "Pretrain/Loss (Raw)": 1.736692190170288, "Pretrain/Step": 7783, "Pretrain/Step Time": 8.489863405004144} +{"Pretrain/Learning Rate": 4.296772804286447e-06, "Pretrain/Loss": 1.9920802116394043, "Pretrain/Loss (Raw)": 2.0367085933685303, "Pretrain/Step": 7784, "Pretrain/Step Time": 8.490638302639127} +{"Pretrain/Learning Rate": 4.2920145922657805e-06, "Pretrain/Loss": 1.9897119998931885, "Pretrain/Loss (Raw)": 1.7961229085922241, "Pretrain/Step": 7785, "Pretrain/Step Time": 8.490222899243236} +{"Pretrain/Learning Rate": 4.2872587689039484e-06, "Pretrain/Loss": 1.9913908243179321, "Pretrain/Loss (Raw)": 2.099870443344116, "Pretrain/Step": 7786, "Pretrain/Step Time": 8.491349410265684} +{"Pretrain/Learning Rate": 4.282505334749542e-06, "Pretrain/Loss": 1.9911786317825317, "Pretrain/Loss (Raw)": 2.03999400138855, "Pretrain/Step": 7787, "Pretrain/Step Time": 8.492028022184968} +{"Pretrain/Learning Rate": 4.2777542903508605e-06, "Pretrain/Loss": 1.9937174320220947, "Pretrain/Loss (Raw)": 2.0877299308776855, "Pretrain/Step": 7788, "Pretrain/Step Time": 8.491549674421549} +{"Pretrain/Learning Rate": 4.273005636255939e-06, "Pretrain/Loss": 1.9939837455749512, "Pretrain/Loss (Raw)": 2.103935718536377, "Pretrain/Step": 7789, "Pretrain/Step Time": 8.490145785734057} +{"Pretrain/Learning Rate": 4.268259373012535e-06, "Pretrain/Loss": 1.9931831359863281, "Pretrain/Loss (Raw)": 2.0897977352142334, "Pretrain/Step": 7790, "Pretrain/Step Time": 8.491972556337714} +{"Pretrain/Learning Rate": 4.263515501168122e-06, "Pretrain/Loss": 1.9933810234069824, "Pretrain/Loss (Raw)": 1.9525694847106934, "Pretrain/Step": 7791, "Pretrain/Step Time": 8.490041332319379} +{"Pretrain/Learning Rate": 4.2587740212699175e-06, "Pretrain/Loss": 1.994083046913147, "Pretrain/Loss (Raw)": 2.025437116622925, "Pretrain/Step": 7792, "Pretrain/Step Time": 8.491240153089166} +{"Pretrain/Learning Rate": 4.2540349338648366e-06, "Pretrain/Loss": 1.9950921535491943, "Pretrain/Loss (Raw)": 2.123784065246582, "Pretrain/Step": 7793, "Pretrain/Step Time": 8.487675355747342} +{"Pretrain/Learning Rate": 4.249298239499533e-06, "Pretrain/Loss": 1.9968507289886475, "Pretrain/Loss (Raw)": 2.184762477874756, "Pretrain/Step": 7794, "Pretrain/Step Time": 8.487310091033578} +{"Pretrain/Learning Rate": 4.2445639387203865e-06, "Pretrain/Loss": 1.9983799457550049, "Pretrain/Loss (Raw)": 2.0910022258758545, "Pretrain/Step": 7795, "Pretrain/Step Time": 8.485785394906998} +{"Pretrain/Learning Rate": 4.239832032073493e-06, "Pretrain/Loss": 1.9965457916259766, "Pretrain/Loss (Raw)": 1.7891895771026611, "Pretrain/Step": 7796, "Pretrain/Step Time": 8.485305704176426} +{"Pretrain/Learning Rate": 4.235102520104681e-06, "Pretrain/Loss": 1.994736671447754, "Pretrain/Loss (Raw)": 1.9121156930923462, "Pretrain/Step": 7797, "Pretrain/Step Time": 8.486990803852677} +{"Pretrain/Learning Rate": 4.230375403359502e-06, "Pretrain/Loss": 1.9941456317901611, "Pretrain/Loss (Raw)": 1.9329478740692139, "Pretrain/Step": 7798, "Pretrain/Step Time": 8.486528862267733} +{"Pretrain/Learning Rate": 4.225650682383214e-06, "Pretrain/Loss": 1.9941306114196777, "Pretrain/Loss (Raw)": 2.13787841796875, "Pretrain/Step": 7799, "Pretrain/Step Time": 8.483253385871649} +{"Pretrain/Learning Rate": 4.220928357720822e-06, "Pretrain/Loss": 1.9937125444412231, "Pretrain/Loss (Raw)": 1.9817311763763428, "Pretrain/Step": 7800, "Pretrain/Step Time": 8.484077457338572} +{"Pretrain/Learning Rate": 4.216208429917046e-06, "Pretrain/Loss": 1.9950616359710693, "Pretrain/Loss (Raw)": 1.9949015378952026, "Pretrain/Step": 7801, "Pretrain/Step Time": 8.484089953824878} +{"Pretrain/Learning Rate": 4.211490899516315e-06, "Pretrain/Loss": 1.9935767650604248, "Pretrain/Loss (Raw)": 1.973638892173767, "Pretrain/Step": 7802, "Pretrain/Step Time": 8.488677814602852} +{"Pretrain/Learning Rate": 4.2067757670628126e-06, "Pretrain/Loss": 1.9940265417099, "Pretrain/Loss (Raw)": 1.9241943359375, "Pretrain/Step": 7803, "Pretrain/Step Time": 8.49151705391705} +{"Pretrain/Learning Rate": 4.2020630331004115e-06, "Pretrain/Loss": 1.9938209056854248, "Pretrain/Loss (Raw)": 2.019840717315674, "Pretrain/Step": 7804, "Pretrain/Step Time": 8.491106279194355} +{"Pretrain/Learning Rate": 4.1973526981727295e-06, "Pretrain/Loss": 1.9932799339294434, "Pretrain/Loss (Raw)": 2.059340715408325, "Pretrain/Step": 7805, "Pretrain/Step Time": 8.48889229632914} +{"Pretrain/Learning Rate": 4.192644762823106e-06, "Pretrain/Loss": 1.9920400381088257, "Pretrain/Loss (Raw)": 1.908403992652893, "Pretrain/Step": 7806, "Pretrain/Step Time": 8.490776918828487} +{"Pretrain/Learning Rate": 4.187939227594595e-06, "Pretrain/Loss": 1.994388461112976, "Pretrain/Loss (Raw)": 2.1595020294189453, "Pretrain/Step": 7807, "Pretrain/Step Time": 8.489447943866253} +{"Pretrain/Learning Rate": 4.183236093029985e-06, "Pretrain/Loss": 1.9952000379562378, "Pretrain/Loss (Raw)": 2.0779366493225098, "Pretrain/Step": 7808, "Pretrain/Step Time": 8.49033240787685} +{"Pretrain/Learning Rate": 4.17853535967177e-06, "Pretrain/Loss": 1.9949924945831299, "Pretrain/Loss (Raw)": 2.0297975540161133, "Pretrain/Step": 7809, "Pretrain/Step Time": 8.485976204276085} +{"Pretrain/Learning Rate": 4.173837028062186e-06, "Pretrain/Loss": 1.9940882921218872, "Pretrain/Loss (Raw)": 1.9998173713684082, "Pretrain/Step": 7810, "Pretrain/Step Time": 8.490506283938885} +{"Pretrain/Learning Rate": 4.169141098743182e-06, "Pretrain/Loss": 1.9948978424072266, "Pretrain/Loss (Raw)": 2.053096294403076, "Pretrain/Step": 7811, "Pretrain/Step Time": 8.486171444877982} +{"Pretrain/Learning Rate": 4.16444757225643e-06, "Pretrain/Loss": 1.9976423978805542, "Pretrain/Loss (Raw)": 2.197197437286377, "Pretrain/Step": 7812, "Pretrain/Step Time": 8.486218823119998} +{"Pretrain/Learning Rate": 4.159756449143337e-06, "Pretrain/Loss": 1.9983155727386475, "Pretrain/Loss (Raw)": 1.8970988988876343, "Pretrain/Step": 7813, "Pretrain/Step Time": 8.484606601297855} +{"Pretrain/Learning Rate": 4.155067729945005e-06, "Pretrain/Loss": 1.9981842041015625, "Pretrain/Loss (Raw)": 2.07456111907959, "Pretrain/Step": 7814, "Pretrain/Step Time": 8.48698827251792} +{"Pretrain/Learning Rate": 4.150381415202287e-06, "Pretrain/Loss": 1.999399185180664, "Pretrain/Loss (Raw)": 1.9496179819107056, "Pretrain/Step": 7815, "Pretrain/Step Time": 8.487922308966517} +{"Pretrain/Learning Rate": 4.145697505455745e-06, "Pretrain/Loss": 1.997936487197876, "Pretrain/Loss (Raw)": 2.0124850273132324, "Pretrain/Step": 7816, "Pretrain/Step Time": 8.49220758676529} +{"Pretrain/Learning Rate": 4.141016001245668e-06, "Pretrain/Loss": 1.9986329078674316, "Pretrain/Loss (Raw)": 2.041877508163452, "Pretrain/Step": 7817, "Pretrain/Step Time": 8.489301966503263} +{"Pretrain/Learning Rate": 4.13633690311207e-06, "Pretrain/Loss": 1.9981987476348877, "Pretrain/Loss (Raw)": 2.0319387912750244, "Pretrain/Step": 7818, "Pretrain/Step Time": 8.49186440743506} +{"Pretrain/Learning Rate": 4.131660211594671e-06, "Pretrain/Loss": 1.9992613792419434, "Pretrain/Loss (Raw)": 1.9977738857269287, "Pretrain/Step": 7819, "Pretrain/Step Time": 8.491846142336726} +{"Pretrain/Learning Rate": 4.12698592723294e-06, "Pretrain/Loss": 1.9993327856063843, "Pretrain/Loss (Raw)": 2.1027088165283203, "Pretrain/Step": 7820, "Pretrain/Step Time": 8.492787975817919} +{"Pretrain/Learning Rate": 4.122314050566043e-06, "Pretrain/Loss": 1.999985694885254, "Pretrain/Loss (Raw)": 2.029081344604492, "Pretrain/Step": 7821, "Pretrain/Step Time": 8.48963031731546} +{"Pretrain/Learning Rate": 4.1176445821328795e-06, "Pretrain/Loss": 1.998732089996338, "Pretrain/Loss (Raw)": 1.7380589246749878, "Pretrain/Step": 7822, "Pretrain/Step Time": 8.493740698322654} +{"Pretrain/Learning Rate": 4.1129775224720775e-06, "Pretrain/Loss": 2.0000112056732178, "Pretrain/Loss (Raw)": 2.106438159942627, "Pretrain/Step": 7823, "Pretrain/Step Time": 8.494312370195985} +{"Pretrain/Learning Rate": 4.108312872121983e-06, "Pretrain/Loss": 2.0020244121551514, "Pretrain/Loss (Raw)": 2.0082755088806152, "Pretrain/Step": 7824, "Pretrain/Step Time": 8.492298897355795} +{"Pretrain/Learning Rate": 4.103650631620651e-06, "Pretrain/Loss": 2.00344181060791, "Pretrain/Loss (Raw)": 2.0678818225860596, "Pretrain/Step": 7825, "Pretrain/Step Time": 8.491377850994468} +{"Pretrain/Learning Rate": 4.098990801505875e-06, "Pretrain/Loss": 2.002819776535034, "Pretrain/Loss (Raw)": 1.9985363483428955, "Pretrain/Step": 7826, "Pretrain/Step Time": 8.488614171743393} +{"Pretrain/Learning Rate": 4.094333382315166e-06, "Pretrain/Loss": 2.00460147857666, "Pretrain/Loss (Raw)": 2.177959442138672, "Pretrain/Step": 7827, "Pretrain/Step Time": 8.489904472604394} +{"Pretrain/Learning Rate": 4.0896783745857535e-06, "Pretrain/Loss": 2.0064430236816406, "Pretrain/Loss (Raw)": 2.059033155441284, "Pretrain/Step": 7828, "Pretrain/Step Time": 8.48640594817698} +{"Pretrain/Learning Rate": 4.085025778854598e-06, "Pretrain/Loss": 2.007518768310547, "Pretrain/Loss (Raw)": 2.0672409534454346, "Pretrain/Step": 7829, "Pretrain/Step Time": 8.487744573503733} +{"Pretrain/Learning Rate": 4.0803755956583644e-06, "Pretrain/Loss": 2.0064640045166016, "Pretrain/Loss (Raw)": 1.887277603149414, "Pretrain/Step": 7830, "Pretrain/Step Time": 8.489481927827} +{"Pretrain/Learning Rate": 4.0757278255334514e-06, "Pretrain/Loss": 2.0052449703216553, "Pretrain/Loss (Raw)": 1.908126711845398, "Pretrain/Step": 7831, "Pretrain/Step Time": 8.49065831117332} +{"Pretrain/Learning Rate": 4.071082469015982e-06, "Pretrain/Loss": 2.0048208236694336, "Pretrain/Loss (Raw)": 2.0872414112091064, "Pretrain/Step": 7832, "Pretrain/Step Time": 8.489978076890111} +{"Pretrain/Learning Rate": 4.066439526641796e-06, "Pretrain/Loss": 2.004957675933838, "Pretrain/Loss (Raw)": 2.148111343383789, "Pretrain/Step": 7833, "Pretrain/Step Time": 8.493213426321745} +{"Pretrain/Learning Rate": 4.061798998946459e-06, "Pretrain/Loss": 2.0058326721191406, "Pretrain/Loss (Raw)": 1.9677432775497437, "Pretrain/Step": 7834, "Pretrain/Step Time": 8.491595512256026} +{"Pretrain/Learning Rate": 4.057160886465244e-06, "Pretrain/Loss": 2.006502866744995, "Pretrain/Loss (Raw)": 1.988196849822998, "Pretrain/Step": 7835, "Pretrain/Step Time": 8.493143294006586} +{"Pretrain/Learning Rate": 4.052525189733167e-06, "Pretrain/Loss": 2.0078330039978027, "Pretrain/Loss (Raw)": 2.0252864360809326, "Pretrain/Step": 7836, "Pretrain/Step Time": 8.493300445377827} +{"Pretrain/Learning Rate": 4.04789190928494e-06, "Pretrain/Loss": 2.0079493522644043, "Pretrain/Loss (Raw)": 1.9578988552093506, "Pretrain/Step": 7837, "Pretrain/Step Time": 8.493712298572063} +{"Pretrain/Learning Rate": 4.04326104565502e-06, "Pretrain/Loss": 2.0047707557678223, "Pretrain/Loss (Raw)": 1.727062463760376, "Pretrain/Step": 7838, "Pretrain/Step Time": 8.491974975913763} +{"Pretrain/Learning Rate": 4.03863259937757e-06, "Pretrain/Loss": 2.0048952102661133, "Pretrain/Loss (Raw)": 2.00616455078125, "Pretrain/Step": 7839, "Pretrain/Step Time": 8.49153819680214} +{"Pretrain/Learning Rate": 4.034006570986492e-06, "Pretrain/Loss": 2.0041966438293457, "Pretrain/Loss (Raw)": 1.9621832370758057, "Pretrain/Step": 7840, "Pretrain/Step Time": 8.493831425905228} +{"Pretrain/Learning Rate": 4.029382961015385e-06, "Pretrain/Loss": 2.003628730773926, "Pretrain/Loss (Raw)": 1.863759160041809, "Pretrain/Step": 7841, "Pretrain/Step Time": 8.487848535180092} +{"Pretrain/Learning Rate": 4.024761769997578e-06, "Pretrain/Loss": 2.00339674949646, "Pretrain/Loss (Raw)": 1.9495489597320557, "Pretrain/Step": 7842, "Pretrain/Step Time": 8.484368689358234} +{"Pretrain/Learning Rate": 4.020142998466133e-06, "Pretrain/Loss": 2.0045151710510254, "Pretrain/Loss (Raw)": 1.9917713403701782, "Pretrain/Step": 7843, "Pretrain/Step Time": 8.482774820178747} +{"Pretrain/Learning Rate": 4.015526646953821e-06, "Pretrain/Loss": 2.0052807331085205, "Pretrain/Loss (Raw)": 2.1392598152160645, "Pretrain/Step": 7844, "Pretrain/Step Time": 8.483948215842247} +{"Pretrain/Learning Rate": 4.010912715993142e-06, "Pretrain/Loss": 2.0057249069213867, "Pretrain/Loss (Raw)": 1.9939053058624268, "Pretrain/Step": 7845, "Pretrain/Step Time": 8.482111172750592} +{"Pretrain/Learning Rate": 4.006301206116297e-06, "Pretrain/Loss": 2.0057952404022217, "Pretrain/Loss (Raw)": 1.826947569847107, "Pretrain/Step": 7846, "Pretrain/Step Time": 8.482665864750743} +{"Pretrain/Learning Rate": 4.0016921178552325e-06, "Pretrain/Loss": 2.006887435913086, "Pretrain/Loss (Raw)": 2.1010541915893555, "Pretrain/Step": 7847, "Pretrain/Step Time": 8.482225121930242} +{"Pretrain/Learning Rate": 3.9970854517416e-06, "Pretrain/Loss": 2.0067296028137207, "Pretrain/Loss (Raw)": 2.1659812927246094, "Pretrain/Step": 7848, "Pretrain/Step Time": 8.482221625745296} +{"Pretrain/Learning Rate": 3.992481208306781e-06, "Pretrain/Loss": 2.006747245788574, "Pretrain/Loss (Raw)": 2.0144755840301514, "Pretrain/Step": 7849, "Pretrain/Step Time": 8.48467979952693} +{"Pretrain/Learning Rate": 3.987879388081881e-06, "Pretrain/Loss": 2.007495403289795, "Pretrain/Loss (Raw)": 2.078681468963623, "Pretrain/Step": 7850, "Pretrain/Step Time": 8.484343094751239} +{"Pretrain/Learning Rate": 3.983279991597699e-06, "Pretrain/Loss": 2.0066118240356445, "Pretrain/Loss (Raw)": 2.039341688156128, "Pretrain/Step": 7851, "Pretrain/Step Time": 8.481999732553959} +{"Pretrain/Learning Rate": 3.978683019384785e-06, "Pretrain/Loss": 2.0062990188598633, "Pretrain/Loss (Raw)": 1.9320147037506104, "Pretrain/Step": 7852, "Pretrain/Step Time": 8.484457666054368} +{"Pretrain/Learning Rate": 3.974088471973406e-06, "Pretrain/Loss": 2.00396728515625, "Pretrain/Loss (Raw)": 1.6664025783538818, "Pretrain/Step": 7853, "Pretrain/Step Time": 8.487362368032336} +{"Pretrain/Learning Rate": 3.969496349893522e-06, "Pretrain/Loss": 2.0033984184265137, "Pretrain/Loss (Raw)": 2.0387399196624756, "Pretrain/Step": 7854, "Pretrain/Step Time": 8.489862192422152} +{"Pretrain/Learning Rate": 3.964906653674855e-06, "Pretrain/Loss": 2.004873275756836, "Pretrain/Loss (Raw)": 2.277954339981079, "Pretrain/Step": 7855, "Pretrain/Step Time": 8.486854635179043} +{"Pretrain/Learning Rate": 3.960319383846803e-06, "Pretrain/Loss": 2.0057482719421387, "Pretrain/Loss (Raw)": 2.0487873554229736, "Pretrain/Step": 7856, "Pretrain/Step Time": 8.486910125240684} +{"Pretrain/Learning Rate": 3.955734540938519e-06, "Pretrain/Loss": 2.0029687881469727, "Pretrain/Loss (Raw)": 1.663406491279602, "Pretrain/Step": 7857, "Pretrain/Step Time": 8.485155524685979} +{"Pretrain/Learning Rate": 3.951152125478858e-06, "Pretrain/Loss": 2.00270676612854, "Pretrain/Loss (Raw)": 1.9573935270309448, "Pretrain/Step": 7858, "Pretrain/Step Time": 8.483529891818762} +{"Pretrain/Learning Rate": 3.946572137996404e-06, "Pretrain/Loss": 2.003814458847046, "Pretrain/Loss (Raw)": 1.990915060043335, "Pretrain/Step": 7859, "Pretrain/Step Time": 8.481405846774578} +{"Pretrain/Learning Rate": 3.9419945790194534e-06, "Pretrain/Loss": 2.001438617706299, "Pretrain/Loss (Raw)": 1.7890416383743286, "Pretrain/Step": 7860, "Pretrain/Step Time": 8.480425782501698} +{"Pretrain/Learning Rate": 3.937419449076035e-06, "Pretrain/Loss": 2.002011775970459, "Pretrain/Loss (Raw)": 2.0078988075256348, "Pretrain/Step": 7861, "Pretrain/Step Time": 8.480856878682971} +{"Pretrain/Learning Rate": 3.932846748693875e-06, "Pretrain/Loss": 2.0015437602996826, "Pretrain/Loss (Raw)": 2.06935715675354, "Pretrain/Step": 7862, "Pretrain/Step Time": 8.485486581921577} +{"Pretrain/Learning Rate": 3.928276478400439e-06, "Pretrain/Loss": 2.001736640930176, "Pretrain/Loss (Raw)": 2.0486199855804443, "Pretrain/Step": 7863, "Pretrain/Step Time": 8.485596200451255} +{"Pretrain/Learning Rate": 3.923708638722906e-06, "Pretrain/Loss": 2.0038318634033203, "Pretrain/Loss (Raw)": 2.230456829071045, "Pretrain/Step": 7864, "Pretrain/Step Time": 8.483741333708167} +{"Pretrain/Learning Rate": 3.919143230188174e-06, "Pretrain/Loss": 2.0011682510375977, "Pretrain/Loss (Raw)": 1.9053765535354614, "Pretrain/Step": 7865, "Pretrain/Step Time": 8.481024274602532} +{"Pretrain/Learning Rate": 3.9145802533228695e-06, "Pretrain/Loss": 1.999741792678833, "Pretrain/Loss (Raw)": 1.9456572532653809, "Pretrain/Step": 7866, "Pretrain/Step Time": 8.482769396156073} +{"Pretrain/Learning Rate": 3.910019708653317e-06, "Pretrain/Loss": 1.9996211528778076, "Pretrain/Loss (Raw)": 1.9991836547851562, "Pretrain/Step": 7867, "Pretrain/Step Time": 8.483544873073697} +{"Pretrain/Learning Rate": 3.905461596705579e-06, "Pretrain/Loss": 2.0024359226226807, "Pretrain/Loss (Raw)": 2.0562870502471924, "Pretrain/Step": 7868, "Pretrain/Step Time": 8.481035761535168} +{"Pretrain/Learning Rate": 3.900905918005438e-06, "Pretrain/Loss": 2.002805709838867, "Pretrain/Loss (Raw)": 2.148136854171753, "Pretrain/Step": 7869, "Pretrain/Step Time": 8.486488651484251} +{"Pretrain/Learning Rate": 3.89635267307838e-06, "Pretrain/Loss": 2.003523111343384, "Pretrain/Loss (Raw)": 2.135502338409424, "Pretrain/Step": 7870, "Pretrain/Step Time": 8.487921828404069} +{"Pretrain/Learning Rate": 3.891801862449629e-06, "Pretrain/Loss": 2.005122184753418, "Pretrain/Loss (Raw)": 2.020425796508789, "Pretrain/Step": 7871, "Pretrain/Step Time": 8.481328040361404} +{"Pretrain/Learning Rate": 3.88725348664411e-06, "Pretrain/Loss": 2.005373954772949, "Pretrain/Loss (Raw)": 1.8948835134506226, "Pretrain/Step": 7872, "Pretrain/Step Time": 8.478434521704912} +{"Pretrain/Learning Rate": 3.882707546186481e-06, "Pretrain/Loss": 2.00563383102417, "Pretrain/Loss (Raw)": 2.0166378021240234, "Pretrain/Step": 7873, "Pretrain/Step Time": 8.478700356557965} +{"Pretrain/Learning Rate": 3.878164041601118e-06, "Pretrain/Loss": 2.0051262378692627, "Pretrain/Loss (Raw)": 2.0229992866516113, "Pretrain/Step": 7874, "Pretrain/Step Time": 8.478010276332498} +{"Pretrain/Learning Rate": 3.8736229734121085e-06, "Pretrain/Loss": 2.00557541847229, "Pretrain/Loss (Raw)": 2.068894386291504, "Pretrain/Step": 7875, "Pretrain/Step Time": 8.476416654884815} +{"Pretrain/Learning Rate": 3.86908434214327e-06, "Pretrain/Loss": 2.0061354637145996, "Pretrain/Loss (Raw)": 1.9744632244110107, "Pretrain/Step": 7876, "Pretrain/Step Time": 8.478386459872127} +{"Pretrain/Learning Rate": 3.8645481483181225e-06, "Pretrain/Loss": 2.0055036544799805, "Pretrain/Loss (Raw)": 1.838145136833191, "Pretrain/Step": 7877, "Pretrain/Step Time": 8.480984933674335} +{"Pretrain/Learning Rate": 3.860014392459918e-06, "Pretrain/Loss": 2.0079030990600586, "Pretrain/Loss (Raw)": 2.126112937927246, "Pretrain/Step": 7878, "Pretrain/Step Time": 8.477958993986249} +{"Pretrain/Learning Rate": 3.855483075091623e-06, "Pretrain/Loss": 2.008155345916748, "Pretrain/Loss (Raw)": 2.083646774291992, "Pretrain/Step": 7879, "Pretrain/Step Time": 8.481650298461318} +{"Pretrain/Learning Rate": 3.8509541967359254e-06, "Pretrain/Loss": 2.0062386989593506, "Pretrain/Loss (Raw)": 1.7686419486999512, "Pretrain/Step": 7880, "Pretrain/Step Time": 8.478495601564646} +{"Pretrain/Learning Rate": 3.8464277579152275e-06, "Pretrain/Loss": 2.0059707164764404, "Pretrain/Loss (Raw)": 2.1011719703674316, "Pretrain/Step": 7881, "Pretrain/Step Time": 8.47953275963664} +{"Pretrain/Learning Rate": 3.841903759151661e-06, "Pretrain/Loss": 2.004560708999634, "Pretrain/Loss (Raw)": 2.019653081893921, "Pretrain/Step": 7882, "Pretrain/Step Time": 8.485621863976121} +{"Pretrain/Learning Rate": 3.837382200967055e-06, "Pretrain/Loss": 2.003406286239624, "Pretrain/Loss (Raw)": 1.9046796560287476, "Pretrain/Step": 7883, "Pretrain/Step Time": 8.481831753626466} +{"Pretrain/Learning Rate": 3.832863083882974e-06, "Pretrain/Loss": 2.004145383834839, "Pretrain/Loss (Raw)": 2.1526386737823486, "Pretrain/Step": 7884, "Pretrain/Step Time": 8.484824147075415} +{"Pretrain/Learning Rate": 3.828346408420705e-06, "Pretrain/Loss": 2.0030903816223145, "Pretrain/Loss (Raw)": 2.1235737800598145, "Pretrain/Step": 7885, "Pretrain/Step Time": 8.485655372962356} +{"Pretrain/Learning Rate": 3.82383217510123e-06, "Pretrain/Loss": 2.00411057472229, "Pretrain/Loss (Raw)": 2.030764579772949, "Pretrain/Step": 7886, "Pretrain/Step Time": 8.485740439966321} +{"Pretrain/Learning Rate": 3.8193203844452795e-06, "Pretrain/Loss": 2.002087116241455, "Pretrain/Loss (Raw)": 1.8763015270233154, "Pretrain/Step": 7887, "Pretrain/Step Time": 8.489140277728438} +{"Pretrain/Learning Rate": 3.814811036973271e-06, "Pretrain/Loss": 2.0034971237182617, "Pretrain/Loss (Raw)": 2.1046504974365234, "Pretrain/Step": 7888, "Pretrain/Step Time": 8.489782402291894} +{"Pretrain/Learning Rate": 3.8103041332053668e-06, "Pretrain/Loss": 2.003207206726074, "Pretrain/Loss (Raw)": 2.0007240772247314, "Pretrain/Step": 7889, "Pretrain/Step Time": 8.485786136239767} +{"Pretrain/Learning Rate": 3.805799673661431e-06, "Pretrain/Loss": 2.0047497749328613, "Pretrain/Loss (Raw)": 2.088879346847534, "Pretrain/Step": 7890, "Pretrain/Step Time": 8.484350195154548} +{"Pretrain/Learning Rate": 3.8012976588610582e-06, "Pretrain/Loss": 2.004889965057373, "Pretrain/Loss (Raw)": 1.8615056276321411, "Pretrain/Step": 7891, "Pretrain/Step Time": 8.485963627696037} +{"Pretrain/Learning Rate": 3.7967980893235555e-06, "Pretrain/Loss": 2.005765676498413, "Pretrain/Loss (Raw)": 2.1208267211914062, "Pretrain/Step": 7892, "Pretrain/Step Time": 8.484891341999173} +{"Pretrain/Learning Rate": 3.7923009655679353e-06, "Pretrain/Loss": 2.0078392028808594, "Pretrain/Loss (Raw)": 2.079399585723877, "Pretrain/Step": 7893, "Pretrain/Step Time": 8.481813302263618} +{"Pretrain/Learning Rate": 3.7878062881129467e-06, "Pretrain/Loss": 2.006336212158203, "Pretrain/Loss (Raw)": 1.8774082660675049, "Pretrain/Step": 7894, "Pretrain/Step Time": 8.479025604203343} +{"Pretrain/Learning Rate": 3.783314057477047e-06, "Pretrain/Loss": 2.0038535594940186, "Pretrain/Loss (Raw)": 1.9563078880310059, "Pretrain/Step": 7895, "Pretrain/Step Time": 8.477451359853148} +{"Pretrain/Learning Rate": 3.7788242741784164e-06, "Pretrain/Loss": 2.0030765533447266, "Pretrain/Loss (Raw)": 1.938044548034668, "Pretrain/Step": 7896, "Pretrain/Step Time": 8.477745529264212} +{"Pretrain/Learning Rate": 3.7743369387349514e-06, "Pretrain/Loss": 2.00165057182312, "Pretrain/Loss (Raw)": 2.048215389251709, "Pretrain/Step": 7897, "Pretrain/Step Time": 8.478381117805839} +{"Pretrain/Learning Rate": 3.7698520516642576e-06, "Pretrain/Loss": 1.9987194538116455, "Pretrain/Loss (Raw)": 1.5744657516479492, "Pretrain/Step": 7898, "Pretrain/Step Time": 8.48587223701179} +{"Pretrain/Learning Rate": 3.7653696134836687e-06, "Pretrain/Loss": 1.9995020627975464, "Pretrain/Loss (Raw)": 2.0835795402526855, "Pretrain/Step": 7899, "Pretrain/Step Time": 8.480219580233097} +{"Pretrain/Learning Rate": 3.7608896247102315e-06, "Pretrain/Loss": 2.0009002685546875, "Pretrain/Loss (Raw)": 2.0599868297576904, "Pretrain/Step": 7900, "Pretrain/Step Time": 8.478602688759565} +{"Pretrain/Learning Rate": 3.7564120858607136e-06, "Pretrain/Loss": 2.000528335571289, "Pretrain/Loss (Raw)": 2.0276036262512207, "Pretrain/Step": 7901, "Pretrain/Step Time": 8.475396983325481} +{"Pretrain/Learning Rate": 3.7519369974515993e-06, "Pretrain/Loss": 2.002034902572632, "Pretrain/Loss (Raw)": 2.0744783878326416, "Pretrain/Step": 7902, "Pretrain/Step Time": 8.476634802296758} +{"Pretrain/Learning Rate": 3.747464359999081e-06, "Pretrain/Loss": 2.0025205612182617, "Pretrain/Loss (Raw)": 2.058598279953003, "Pretrain/Step": 7903, "Pretrain/Step Time": 8.475868474692106} +{"Pretrain/Learning Rate": 3.7429941740190877e-06, "Pretrain/Loss": 2.0056498050689697, "Pretrain/Loss (Raw)": 2.1652400493621826, "Pretrain/Step": 7904, "Pretrain/Step Time": 8.476560357958078} +{"Pretrain/Learning Rate": 3.7385264400272373e-06, "Pretrain/Loss": 2.0039806365966797, "Pretrain/Loss (Raw)": 1.862957239151001, "Pretrain/Step": 7905, "Pretrain/Step Time": 8.473779898136854} +{"Pretrain/Learning Rate": 3.734061158538893e-06, "Pretrain/Loss": 2.0053937435150146, "Pretrain/Loss (Raw)": 2.100501537322998, "Pretrain/Step": 7906, "Pretrain/Step Time": 8.473448794335127} +{"Pretrain/Learning Rate": 3.7295983300691174e-06, "Pretrain/Loss": 2.0054783821105957, "Pretrain/Loss (Raw)": 2.0299572944641113, "Pretrain/Step": 7907, "Pretrain/Step Time": 8.474835937842727} +{"Pretrain/Learning Rate": 3.725137955132707e-06, "Pretrain/Loss": 2.005898952484131, "Pretrain/Loss (Raw)": 1.9107307195663452, "Pretrain/Step": 7908, "Pretrain/Step Time": 8.474420318379998} +{"Pretrain/Learning Rate": 3.7206800342441534e-06, "Pretrain/Loss": 2.0026655197143555, "Pretrain/Loss (Raw)": 1.73102605342865, "Pretrain/Step": 7909, "Pretrain/Step Time": 8.47633838839829} +{"Pretrain/Learning Rate": 3.7162245679176784e-06, "Pretrain/Loss": 2.0030174255371094, "Pretrain/Loss (Raw)": 1.9858450889587402, "Pretrain/Step": 7910, "Pretrain/Step Time": 8.472427511587739} +{"Pretrain/Learning Rate": 3.711771556667218e-06, "Pretrain/Loss": 2.004262685775757, "Pretrain/Loss (Raw)": 1.896080732345581, "Pretrain/Step": 7911, "Pretrain/Step Time": 8.476024903357029} +{"Pretrain/Learning Rate": 3.707321001006428e-06, "Pretrain/Loss": 2.0039169788360596, "Pretrain/Loss (Raw)": 1.992488145828247, "Pretrain/Step": 7912, "Pretrain/Step Time": 8.4748564530164} +{"Pretrain/Learning Rate": 3.702872901448684e-06, "Pretrain/Loss": 2.004239559173584, "Pretrain/Loss (Raw)": 1.8373743295669556, "Pretrain/Step": 7913, "Pretrain/Step Time": 8.471386633813381} +{"Pretrain/Learning Rate": 3.698427258507062e-06, "Pretrain/Loss": 2.0040316581726074, "Pretrain/Loss (Raw)": 2.073294162750244, "Pretrain/Step": 7914, "Pretrain/Step Time": 8.47029272466898} +{"Pretrain/Learning Rate": 3.6939840726943675e-06, "Pretrain/Loss": 2.002136707305908, "Pretrain/Loss (Raw)": 1.7974416017532349, "Pretrain/Step": 7915, "Pretrain/Step Time": 8.476581310853362} +{"Pretrain/Learning Rate": 3.6895433445231247e-06, "Pretrain/Loss": 2.001849889755249, "Pretrain/Loss (Raw)": 2.051013231277466, "Pretrain/Step": 7916, "Pretrain/Step Time": 8.47499212063849} +{"Pretrain/Learning Rate": 3.6851050745055652e-06, "Pretrain/Loss": 2.0008931159973145, "Pretrain/Loss (Raw)": 1.981478214263916, "Pretrain/Step": 7917, "Pretrain/Step Time": 8.475430538877845} +{"Pretrain/Learning Rate": 3.680669263153655e-06, "Pretrain/Loss": 1.9994648694992065, "Pretrain/Loss (Raw)": 1.9069589376449585, "Pretrain/Step": 7918, "Pretrain/Step Time": 8.475568771362305} +{"Pretrain/Learning Rate": 3.6762359109790452e-06, "Pretrain/Loss": 2.0003433227539062, "Pretrain/Loss (Raw)": 2.065021276473999, "Pretrain/Step": 7919, "Pretrain/Step Time": 8.477355815470219} +{"Pretrain/Learning Rate": 3.6718050184931353e-06, "Pretrain/Loss": 2.0002262592315674, "Pretrain/Loss (Raw)": 2.0104472637176514, "Pretrain/Step": 7920, "Pretrain/Step Time": 8.478737961500883} +{"Pretrain/Learning Rate": 3.667376586207014e-06, "Pretrain/Loss": 1.999837875366211, "Pretrain/Loss (Raw)": 2.0740773677825928, "Pretrain/Step": 7921, "Pretrain/Step Time": 8.478345643728971} +{"Pretrain/Learning Rate": 3.662950614631508e-06, "Pretrain/Loss": 1.9980964660644531, "Pretrain/Loss (Raw)": 1.9618470668792725, "Pretrain/Step": 7922, "Pretrain/Step Time": 8.47589728422463} +{"Pretrain/Learning Rate": 3.6585271042771486e-06, "Pretrain/Loss": 1.9930704832077026, "Pretrain/Loss (Raw)": 1.4476885795593262, "Pretrain/Step": 7923, "Pretrain/Step Time": 8.477700820192695} +{"Pretrain/Learning Rate": 3.654106055654197e-06, "Pretrain/Loss": 1.994299292564392, "Pretrain/Loss (Raw)": 1.9464921951293945, "Pretrain/Step": 7924, "Pretrain/Step Time": 8.480068046599627} +{"Pretrain/Learning Rate": 3.6496874692726003e-06, "Pretrain/Loss": 1.9960829019546509, "Pretrain/Loss (Raw)": 2.1404001712799072, "Pretrain/Step": 7925, "Pretrain/Step Time": 8.477936146780849} +{"Pretrain/Learning Rate": 3.645271345642054e-06, "Pretrain/Loss": 1.997361660003662, "Pretrain/Loss (Raw)": 2.096620798110962, "Pretrain/Step": 7926, "Pretrain/Step Time": 8.479086987674236} +{"Pretrain/Learning Rate": 3.6408576852719533e-06, "Pretrain/Loss": 1.9963011741638184, "Pretrain/Loss (Raw)": 2.0021462440490723, "Pretrain/Step": 7927, "Pretrain/Step Time": 8.480918718501925} +{"Pretrain/Learning Rate": 3.6364464886714105e-06, "Pretrain/Loss": 1.996770977973938, "Pretrain/Loss (Raw)": 2.0418713092803955, "Pretrain/Step": 7928, "Pretrain/Step Time": 8.478415103629231} +{"Pretrain/Learning Rate": 3.632037756349266e-06, "Pretrain/Loss": 1.9969539642333984, "Pretrain/Loss (Raw)": 2.0183217525482178, "Pretrain/Step": 7929, "Pretrain/Step Time": 8.48157749325037} +{"Pretrain/Learning Rate": 3.6276314888140513e-06, "Pretrain/Loss": 1.9975905418395996, "Pretrain/Loss (Raw)": 2.0551042556762695, "Pretrain/Step": 7930, "Pretrain/Step Time": 8.482822956517339} +{"Pretrain/Learning Rate": 3.6232276865740323e-06, "Pretrain/Loss": 1.9979596138000488, "Pretrain/Loss (Raw)": 1.9714452028274536, "Pretrain/Step": 7931, "Pretrain/Step Time": 8.481081718578935} +{"Pretrain/Learning Rate": 3.618826350137186e-06, "Pretrain/Loss": 1.997912883758545, "Pretrain/Loss (Raw)": 2.013869524002075, "Pretrain/Step": 7932, "Pretrain/Step Time": 8.482503181323409} +{"Pretrain/Learning Rate": 3.6144274800112065e-06, "Pretrain/Loss": 1.9970226287841797, "Pretrain/Loss (Raw)": 1.945385456085205, "Pretrain/Step": 7933, "Pretrain/Step Time": 8.48544305190444} +{"Pretrain/Learning Rate": 3.6100310767035102e-06, "Pretrain/Loss": 1.9987884759902954, "Pretrain/Loss (Raw)": 2.134423017501831, "Pretrain/Step": 7934, "Pretrain/Step Time": 8.48755325563252} +{"Pretrain/Learning Rate": 3.605637140721205e-06, "Pretrain/Loss": 1.9974241256713867, "Pretrain/Loss (Raw)": 1.9848507642745972, "Pretrain/Step": 7935, "Pretrain/Step Time": 8.48479150235653} +{"Pretrain/Learning Rate": 3.6012456725711437e-06, "Pretrain/Loss": 1.9966518878936768, "Pretrain/Loss (Raw)": 1.9791145324707031, "Pretrain/Step": 7936, "Pretrain/Step Time": 8.486126845702529} +{"Pretrain/Learning Rate": 3.596856672759866e-06, "Pretrain/Loss": 1.995746374130249, "Pretrain/Loss (Raw)": 1.9138942956924438, "Pretrain/Step": 7937, "Pretrain/Step Time": 8.487658744677901} +{"Pretrain/Learning Rate": 3.5924701417936495e-06, "Pretrain/Loss": 1.994164228439331, "Pretrain/Loss (Raw)": 1.7972978353500366, "Pretrain/Step": 7938, "Pretrain/Step Time": 8.482722928747535} +{"Pretrain/Learning Rate": 3.588086080178482e-06, "Pretrain/Loss": 1.993229866027832, "Pretrain/Loss (Raw)": 1.933483600616455, "Pretrain/Step": 7939, "Pretrain/Step Time": 8.48290185071528} +{"Pretrain/Learning Rate": 3.5837044884200642e-06, "Pretrain/Loss": 1.9923627376556396, "Pretrain/Loss (Raw)": 2.0862247943878174, "Pretrain/Step": 7940, "Pretrain/Step Time": 8.48369413241744} +{"Pretrain/Learning Rate": 3.579325367023803e-06, "Pretrain/Loss": 1.9942388534545898, "Pretrain/Loss (Raw)": 2.1372299194335938, "Pretrain/Step": 7941, "Pretrain/Step Time": 8.481917917728424} +{"Pretrain/Learning Rate": 3.5749487164948303e-06, "Pretrain/Loss": 1.9934922456741333, "Pretrain/Loss (Raw)": 1.9789962768554688, "Pretrain/Step": 7942, "Pretrain/Step Time": 8.478261409327388} +{"Pretrain/Learning Rate": 3.570574537337998e-06, "Pretrain/Loss": 1.9927184581756592, "Pretrain/Loss (Raw)": 1.8505668640136719, "Pretrain/Step": 7943, "Pretrain/Step Time": 8.477799950167537} +{"Pretrain/Learning Rate": 3.5662028300578576e-06, "Pretrain/Loss": 1.9922006130218506, "Pretrain/Loss (Raw)": 1.9462246894836426, "Pretrain/Step": 7944, "Pretrain/Step Time": 8.474307244643569} +{"Pretrain/Learning Rate": 3.561833595158698e-06, "Pretrain/Loss": 1.991166114807129, "Pretrain/Loss (Raw)": 1.9094501733779907, "Pretrain/Step": 7945, "Pretrain/Step Time": 8.473620740696788} +{"Pretrain/Learning Rate": 3.5574668331444904e-06, "Pretrain/Loss": 1.9893929958343506, "Pretrain/Loss (Raw)": 1.8049709796905518, "Pretrain/Step": 7946, "Pretrain/Step Time": 8.474878385663033} +{"Pretrain/Learning Rate": 3.5531025445189494e-06, "Pretrain/Loss": 1.9895946979522705, "Pretrain/Loss (Raw)": 2.0235793590545654, "Pretrain/Step": 7947, "Pretrain/Step Time": 8.475070102140307} +{"Pretrain/Learning Rate": 3.5487407297854937e-06, "Pretrain/Loss": 1.989549994468689, "Pretrain/Loss (Raw)": 2.0970065593719482, "Pretrain/Step": 7948, "Pretrain/Step Time": 8.474294006824493} +{"Pretrain/Learning Rate": 3.544381389447254e-06, "Pretrain/Loss": 1.9880313873291016, "Pretrain/Loss (Raw)": 1.8346977233886719, "Pretrain/Step": 7949, "Pretrain/Step Time": 8.480271860957146} +{"Pretrain/Learning Rate": 3.5400245240070905e-06, "Pretrain/Loss": 1.9904298782348633, "Pretrain/Loss (Raw)": 2.045053005218506, "Pretrain/Step": 7950, "Pretrain/Step Time": 8.47633421421051} +{"Pretrain/Learning Rate": 3.5356701339675474e-06, "Pretrain/Loss": 1.9897468090057373, "Pretrain/Loss (Raw)": 2.019010543823242, "Pretrain/Step": 7951, "Pretrain/Step Time": 8.473998807370663} +{"Pretrain/Learning Rate": 3.531318219830912e-06, "Pretrain/Loss": 1.990147590637207, "Pretrain/Loss (Raw)": 2.0595805644989014, "Pretrain/Step": 7952, "Pretrain/Step Time": 8.47345620766282} +{"Pretrain/Learning Rate": 3.5269687820991824e-06, "Pretrain/Loss": 1.989085078239441, "Pretrain/Loss (Raw)": 1.9318791627883911, "Pretrain/Step": 7953, "Pretrain/Step Time": 8.474181719124317} +{"Pretrain/Learning Rate": 3.5226218212740497e-06, "Pretrain/Loss": 1.9893224239349365, "Pretrain/Loss (Raw)": 2.028914451599121, "Pretrain/Step": 7954, "Pretrain/Step Time": 8.473297275602818} +{"Pretrain/Learning Rate": 3.518277337856951e-06, "Pretrain/Loss": 1.9873058795928955, "Pretrain/Loss (Raw)": 1.919830560684204, "Pretrain/Step": 7955, "Pretrain/Step Time": 8.474263586103916} +{"Pretrain/Learning Rate": 3.5139353323490053e-06, "Pretrain/Loss": 1.9863576889038086, "Pretrain/Loss (Raw)": 1.9376726150512695, "Pretrain/Step": 7956, "Pretrain/Step Time": 8.477731812745333} +{"Pretrain/Learning Rate": 3.5095958052510675e-06, "Pretrain/Loss": 1.9855804443359375, "Pretrain/Loss (Raw)": 1.967750072479248, "Pretrain/Step": 7957, "Pretrain/Step Time": 8.47548171132803} +{"Pretrain/Learning Rate": 3.5052587570637006e-06, "Pretrain/Loss": 1.9858403205871582, "Pretrain/Loss (Raw)": 1.9205390214920044, "Pretrain/Step": 7958, "Pretrain/Step Time": 8.474010158330202} +{"Pretrain/Learning Rate": 3.500924188287183e-06, "Pretrain/Loss": 1.9874385595321655, "Pretrain/Loss (Raw)": 2.112704277038574, "Pretrain/Step": 7959, "Pretrain/Step Time": 8.472181918099523} +{"Pretrain/Learning Rate": 3.4965920994215056e-06, "Pretrain/Loss": 1.9865500926971436, "Pretrain/Loss (Raw)": 1.973527431488037, "Pretrain/Step": 7960, "Pretrain/Step Time": 8.47402018122375} +{"Pretrain/Learning Rate": 3.4922624909663774e-06, "Pretrain/Loss": 1.9835156202316284, "Pretrain/Loss (Raw)": 1.759691596031189, "Pretrain/Step": 7961, "Pretrain/Step Time": 8.47029734775424} +{"Pretrain/Learning Rate": 3.4879353634212076e-06, "Pretrain/Loss": 1.9838937520980835, "Pretrain/Loss (Raw)": 2.0161454677581787, "Pretrain/Step": 7962, "Pretrain/Step Time": 8.473837161436677} +{"Pretrain/Learning Rate": 3.4836107172851352e-06, "Pretrain/Loss": 1.983641266822815, "Pretrain/Loss (Raw)": 1.9558826684951782, "Pretrain/Step": 7963, "Pretrain/Step Time": 8.47244243323803} +{"Pretrain/Learning Rate": 3.479288553057003e-06, "Pretrain/Loss": 1.983612298965454, "Pretrain/Loss (Raw)": 2.021580457687378, "Pretrain/Step": 7964, "Pretrain/Step Time": 8.47318753413856} +{"Pretrain/Learning Rate": 3.4749688712353735e-06, "Pretrain/Loss": 1.9830079078674316, "Pretrain/Loss (Raw)": 1.8805309534072876, "Pretrain/Step": 7965, "Pretrain/Step Time": 8.476052679121494} +{"Pretrain/Learning Rate": 3.4706516723185256e-06, "Pretrain/Loss": 1.9852757453918457, "Pretrain/Loss (Raw)": 2.017345666885376, "Pretrain/Step": 7966, "Pretrain/Step Time": 8.479160191491246} +{"Pretrain/Learning Rate": 3.466336956804436e-06, "Pretrain/Loss": 1.9875068664550781, "Pretrain/Loss (Raw)": 2.2917513847351074, "Pretrain/Step": 7967, "Pretrain/Step Time": 8.477259997278452} +{"Pretrain/Learning Rate": 3.4620247251908127e-06, "Pretrain/Loss": 1.9879018068313599, "Pretrain/Loss (Raw)": 2.012732744216919, "Pretrain/Step": 7968, "Pretrain/Step Time": 8.477523444220424} +{"Pretrain/Learning Rate": 3.4577149779750713e-06, "Pretrain/Loss": 1.9895830154418945, "Pretrain/Loss (Raw)": 2.0789546966552734, "Pretrain/Step": 7969, "Pretrain/Step Time": 8.477106586098671} +{"Pretrain/Learning Rate": 3.4534077156543333e-06, "Pretrain/Loss": 1.9901752471923828, "Pretrain/Loss (Raw)": 2.0253655910491943, "Pretrain/Step": 7970, "Pretrain/Step Time": 8.47851611673832} +{"Pretrain/Learning Rate": 3.4491029387254486e-06, "Pretrain/Loss": 1.9905569553375244, "Pretrain/Loss (Raw)": 2.0406289100646973, "Pretrain/Step": 7971, "Pretrain/Step Time": 8.481440668925643} +{"Pretrain/Learning Rate": 3.444800647684959e-06, "Pretrain/Loss": 1.990068793296814, "Pretrain/Loss (Raw)": 2.0767526626586914, "Pretrain/Step": 7972, "Pretrain/Step Time": 8.478694394230843} +{"Pretrain/Learning Rate": 3.440500843029143e-06, "Pretrain/Loss": 1.990541934967041, "Pretrain/Loss (Raw)": 2.054497241973877, "Pretrain/Step": 7973, "Pretrain/Step Time": 8.481600489467382} +{"Pretrain/Learning Rate": 3.4362035252539754e-06, "Pretrain/Loss": 1.9913041591644287, "Pretrain/Loss (Raw)": 1.924514651298523, "Pretrain/Step": 7974, "Pretrain/Step Time": 8.481972437351942} +{"Pretrain/Learning Rate": 3.4319086948551544e-06, "Pretrain/Loss": 1.9886797666549683, "Pretrain/Loss (Raw)": 1.7651151418685913, "Pretrain/Step": 7975, "Pretrain/Step Time": 8.482308804988861} +{"Pretrain/Learning Rate": 3.427616352328089e-06, "Pretrain/Loss": 1.988337516784668, "Pretrain/Loss (Raw)": 2.1221702098846436, "Pretrain/Step": 7976, "Pretrain/Step Time": 8.482861917465925} +{"Pretrain/Learning Rate": 3.4233264981678947e-06, "Pretrain/Loss": 1.9873790740966797, "Pretrain/Loss (Raw)": 1.8918054103851318, "Pretrain/Step": 7977, "Pretrain/Step Time": 8.48128761164844} +{"Pretrain/Learning Rate": 3.4190391328694034e-06, "Pretrain/Loss": 1.987348198890686, "Pretrain/Loss (Raw)": 2.0747170448303223, "Pretrain/Step": 7978, "Pretrain/Step Time": 8.479079036042094} +{"Pretrain/Learning Rate": 3.4147542569271635e-06, "Pretrain/Loss": 1.986039161682129, "Pretrain/Loss (Raw)": 1.8717962503433228, "Pretrain/Step": 7979, "Pretrain/Step Time": 8.482868449762464} +{"Pretrain/Learning Rate": 3.4104718708354354e-06, "Pretrain/Loss": 1.9868431091308594, "Pretrain/Loss (Raw)": 2.0349175930023193, "Pretrain/Step": 7980, "Pretrain/Step Time": 8.477607956156135} +{"Pretrain/Learning Rate": 3.406191975088191e-06, "Pretrain/Loss": 1.9880917072296143, "Pretrain/Loss (Raw)": 1.8262193202972412, "Pretrain/Step": 7981, "Pretrain/Step Time": 8.479499584063888} +{"Pretrain/Learning Rate": 3.4019145701791184e-06, "Pretrain/Loss": 1.9874463081359863, "Pretrain/Loss (Raw)": 1.9561229944229126, "Pretrain/Step": 7982, "Pretrain/Step Time": 8.483642579987645} +{"Pretrain/Learning Rate": 3.397639656601606e-06, "Pretrain/Loss": 1.985948920249939, "Pretrain/Loss (Raw)": 2.086298942565918, "Pretrain/Step": 7983, "Pretrain/Step Time": 8.484239518642426} +{"Pretrain/Learning Rate": 3.3933672348487655e-06, "Pretrain/Loss": 1.9859730005264282, "Pretrain/Loss (Raw)": 2.0518698692321777, "Pretrain/Step": 7984, "Pretrain/Step Time": 8.480882057920098} +{"Pretrain/Learning Rate": 3.3890973054134217e-06, "Pretrain/Loss": 1.9888460636138916, "Pretrain/Loss (Raw)": 2.0311439037323, "Pretrain/Step": 7985, "Pretrain/Step Time": 8.480436846613884} +{"Pretrain/Learning Rate": 3.3848298687881143e-06, "Pretrain/Loss": 1.9902342557907104, "Pretrain/Loss (Raw)": 2.135091543197632, "Pretrain/Step": 7986, "Pretrain/Step Time": 8.479941789060831} +{"Pretrain/Learning Rate": 3.3805649254650825e-06, "Pretrain/Loss": 1.9901765584945679, "Pretrain/Loss (Raw)": 1.9835283756256104, "Pretrain/Step": 7987, "Pretrain/Step Time": 8.48159098252654} +{"Pretrain/Learning Rate": 3.376302475936291e-06, "Pretrain/Loss": 1.991617202758789, "Pretrain/Loss (Raw)": 1.9734500646591187, "Pretrain/Step": 7988, "Pretrain/Step Time": 8.486622892320156} +{"Pretrain/Learning Rate": 3.3720425206934055e-06, "Pretrain/Loss": 1.99123215675354, "Pretrain/Loss (Raw)": 1.9586076736450195, "Pretrain/Step": 7989, "Pretrain/Step Time": 8.486356168985367} +{"Pretrain/Learning Rate": 3.3677850602278156e-06, "Pretrain/Loss": 1.9913828372955322, "Pretrain/Loss (Raw)": 2.088650941848755, "Pretrain/Step": 7990, "Pretrain/Step Time": 8.482585936784744} +{"Pretrain/Learning Rate": 3.3635300950306174e-06, "Pretrain/Loss": 1.9912059307098389, "Pretrain/Loss (Raw)": 2.0259616374969482, "Pretrain/Step": 7991, "Pretrain/Step Time": 8.482981396839023} +{"Pretrain/Learning Rate": 3.3592776255926217e-06, "Pretrain/Loss": 1.9888561964035034, "Pretrain/Loss (Raw)": 1.9296997785568237, "Pretrain/Step": 7992, "Pretrain/Step Time": 8.487730810418725} +{"Pretrain/Learning Rate": 3.355027652404344e-06, "Pretrain/Loss": 1.9912002086639404, "Pretrain/Loss (Raw)": 2.2053956985473633, "Pretrain/Step": 7993, "Pretrain/Step Time": 8.486544717103243} +{"Pretrain/Learning Rate": 3.3507801759560198e-06, "Pretrain/Loss": 1.9915695190429688, "Pretrain/Loss (Raw)": 1.992945671081543, "Pretrain/Step": 7994, "Pretrain/Step Time": 8.488782346248627} +{"Pretrain/Learning Rate": 3.3465351967375936e-06, "Pretrain/Loss": 1.9909696578979492, "Pretrain/Loss (Raw)": 1.9223926067352295, "Pretrain/Step": 7995, "Pretrain/Step Time": 8.489733651280403} +{"Pretrain/Learning Rate": 3.3422927152387236e-06, "Pretrain/Loss": 1.989382266998291, "Pretrain/Loss (Raw)": 1.8531194925308228, "Pretrain/Step": 7996, "Pretrain/Step Time": 8.49132721312344} +{"Pretrain/Learning Rate": 3.338052731948782e-06, "Pretrain/Loss": 1.988107681274414, "Pretrain/Loss (Raw)": 1.9849745035171509, "Pretrain/Step": 7997, "Pretrain/Step Time": 8.485187198966742} +{"Pretrain/Learning Rate": 3.333815247356839e-06, "Pretrain/Loss": 1.9866816997528076, "Pretrain/Loss (Raw)": 1.9529787302017212, "Pretrain/Step": 7998, "Pretrain/Step Time": 8.486683884635568} +{"Pretrain/Learning Rate": 3.3295802619516954e-06, "Pretrain/Loss": 1.9852101802825928, "Pretrain/Loss (Raw)": 1.8320684432983398, "Pretrain/Step": 7999, "Pretrain/Step Time": 8.490043377503753} +{"Pretrain/Learning Rate": 3.3253477762218517e-06, "Pretrain/Loss": 1.9864463806152344, "Pretrain/Loss (Raw)": 2.0531270503997803, "Pretrain/Step": 8000, "Pretrain/Step Time": 8.49356460571289} +{"Pretrain/Learning Rate": 3.321117790655526e-06, "Pretrain/Loss": 1.9873063564300537, "Pretrain/Loss (Raw)": 2.1267056465148926, "Pretrain/Step": 8001, "Pretrain/Step Time": 8.492557529360056} +{"Pretrain/Learning Rate": 3.3168903057406497e-06, "Pretrain/Loss": 1.9879817962646484, "Pretrain/Loss (Raw)": 2.1094727516174316, "Pretrain/Step": 8002, "Pretrain/Step Time": 8.490890938788652} +{"Pretrain/Learning Rate": 3.31266532196485e-06, "Pretrain/Loss": 1.987790822982788, "Pretrain/Loss (Raw)": 2.044430732727051, "Pretrain/Step": 8003, "Pretrain/Step Time": 8.494916558265686} +{"Pretrain/Learning Rate": 3.3084428398154924e-06, "Pretrain/Loss": 1.9882593154907227, "Pretrain/Loss (Raw)": 2.0344531536102295, "Pretrain/Step": 8004, "Pretrain/Step Time": 8.49234333448112} +{"Pretrain/Learning Rate": 3.304222859779621e-06, "Pretrain/Loss": 1.9908292293548584, "Pretrain/Loss (Raw)": 2.167056083679199, "Pretrain/Step": 8005, "Pretrain/Step Time": 8.48754408955574} +{"Pretrain/Learning Rate": 3.3000053823440207e-06, "Pretrain/Loss": 1.9891586303710938, "Pretrain/Loss (Raw)": 1.9122912883758545, "Pretrain/Step": 8006, "Pretrain/Step Time": 8.489395650103688} +{"Pretrain/Learning Rate": 3.2957904079951725e-06, "Pretrain/Loss": 1.988433599472046, "Pretrain/Loss (Raw)": 1.9908368587493896, "Pretrain/Step": 8007, "Pretrain/Step Time": 8.484623769298196} +{"Pretrain/Learning Rate": 3.291577937219281e-06, "Pretrain/Loss": 1.9898443222045898, "Pretrain/Loss (Raw)": 1.9492329359054565, "Pretrain/Step": 8008, "Pretrain/Step Time": 8.487279884517193} +{"Pretrain/Learning Rate": 3.287367970502239e-06, "Pretrain/Loss": 1.9877201318740845, "Pretrain/Loss (Raw)": 1.829258918762207, "Pretrain/Step": 8009, "Pretrain/Step Time": 8.487735578790307} +{"Pretrain/Learning Rate": 3.283160508329669e-06, "Pretrain/Loss": 1.9876854419708252, "Pretrain/Loss (Raw)": 2.0152359008789062, "Pretrain/Step": 8010, "Pretrain/Step Time": 8.484241921454668} +{"Pretrain/Learning Rate": 3.2789555511869047e-06, "Pretrain/Loss": 1.9887709617614746, "Pretrain/Loss (Raw)": 2.043599843978882, "Pretrain/Step": 8011, "Pretrain/Step Time": 8.484350003302097} +{"Pretrain/Learning Rate": 3.274753099558983e-06, "Pretrain/Loss": 1.9860984086990356, "Pretrain/Loss (Raw)": 1.8105626106262207, "Pretrain/Step": 8012, "Pretrain/Step Time": 8.4817327670753} +{"Pretrain/Learning Rate": 3.2705531539306638e-06, "Pretrain/Loss": 1.9861018657684326, "Pretrain/Loss (Raw)": 2.124016284942627, "Pretrain/Step": 8013, "Pretrain/Step Time": 8.48318973556161} +{"Pretrain/Learning Rate": 3.2663557147863954e-06, "Pretrain/Loss": 1.9845902919769287, "Pretrain/Loss (Raw)": 1.8372795581817627, "Pretrain/Step": 8014, "Pretrain/Step Time": 8.483133260160685} +{"Pretrain/Learning Rate": 3.2621607826103572e-06, "Pretrain/Loss": 1.9841763973236084, "Pretrain/Loss (Raw)": 1.8233178853988647, "Pretrain/Step": 8015, "Pretrain/Step Time": 8.477452740073204} +{"Pretrain/Learning Rate": 3.2579683578864347e-06, "Pretrain/Loss": 1.9826312065124512, "Pretrain/Loss (Raw)": 1.9068870544433594, "Pretrain/Step": 8016, "Pretrain/Step Time": 8.477666903287172} +{"Pretrain/Learning Rate": 3.253778441098221e-06, "Pretrain/Loss": 1.9826958179473877, "Pretrain/Loss (Raw)": 2.0089833736419678, "Pretrain/Step": 8017, "Pretrain/Step Time": 8.478625273332} +{"Pretrain/Learning Rate": 3.2495910327290267e-06, "Pretrain/Loss": 1.9837137460708618, "Pretrain/Loss (Raw)": 2.2191803455352783, "Pretrain/Step": 8018, "Pretrain/Step Time": 8.481533845886588} +{"Pretrain/Learning Rate": 3.245406133261858e-06, "Pretrain/Loss": 1.9845027923583984, "Pretrain/Loss (Raw)": 1.9625062942504883, "Pretrain/Step": 8019, "Pretrain/Step Time": 8.47867607139051} +{"Pretrain/Learning Rate": 3.241223743179453e-06, "Pretrain/Loss": 1.9844186305999756, "Pretrain/Loss (Raw)": 2.1100590229034424, "Pretrain/Step": 8020, "Pretrain/Step Time": 8.48165319301188} +{"Pretrain/Learning Rate": 3.237043862964237e-06, "Pretrain/Loss": 1.984785795211792, "Pretrain/Loss (Raw)": 2.1263766288757324, "Pretrain/Step": 8021, "Pretrain/Step Time": 8.481789726763964} +{"Pretrain/Learning Rate": 3.2328664930983633e-06, "Pretrain/Loss": 1.985862374305725, "Pretrain/Loss (Raw)": 2.0152151584625244, "Pretrain/Step": 8022, "Pretrain/Step Time": 8.483968248590827} +{"Pretrain/Learning Rate": 3.228691634063688e-06, "Pretrain/Loss": 1.9866548776626587, "Pretrain/Loss (Raw)": 2.0577425956726074, "Pretrain/Step": 8023, "Pretrain/Step Time": 8.48495745100081} +{"Pretrain/Learning Rate": 3.22451928634179e-06, "Pretrain/Loss": 1.9872865676879883, "Pretrain/Loss (Raw)": 2.0189061164855957, "Pretrain/Step": 8024, "Pretrain/Step Time": 8.490334551781416} +{"Pretrain/Learning Rate": 3.2203494504139343e-06, "Pretrain/Loss": 1.986053466796875, "Pretrain/Loss (Raw)": 1.890382170677185, "Pretrain/Step": 8025, "Pretrain/Step Time": 8.489241415634751} +{"Pretrain/Learning Rate": 3.2161821267611137e-06, "Pretrain/Loss": 1.9911549091339111, "Pretrain/Loss (Raw)": 2.227445363998413, "Pretrain/Step": 8026, "Pretrain/Step Time": 8.483152026310563} +{"Pretrain/Learning Rate": 3.21201731586403e-06, "Pretrain/Loss": 1.9907045364379883, "Pretrain/Loss (Raw)": 2.0259344577789307, "Pretrain/Step": 8027, "Pretrain/Step Time": 8.487108740955591} +{"Pretrain/Learning Rate": 3.207855018203093e-06, "Pretrain/Loss": 1.9914205074310303, "Pretrain/Loss (Raw)": 2.1516330242156982, "Pretrain/Step": 8028, "Pretrain/Step Time": 8.487435752525926} +{"Pretrain/Learning Rate": 3.2036952342584274e-06, "Pretrain/Loss": 1.9921939373016357, "Pretrain/Loss (Raw)": 2.1266047954559326, "Pretrain/Step": 8029, "Pretrain/Step Time": 8.489162493497133} +{"Pretrain/Learning Rate": 3.1995379645098496e-06, "Pretrain/Loss": 1.9906299114227295, "Pretrain/Loss (Raw)": 1.8742704391479492, "Pretrain/Step": 8030, "Pretrain/Step Time": 8.488812506198883} +{"Pretrain/Learning Rate": 3.195383209436906e-06, "Pretrain/Loss": 1.9917114973068237, "Pretrain/Loss (Raw)": 2.1970441341400146, "Pretrain/Step": 8031, "Pretrain/Step Time": 8.487249365076423} +{"Pretrain/Learning Rate": 3.1912309695188463e-06, "Pretrain/Loss": 1.9909380674362183, "Pretrain/Loss (Raw)": 2.066257953643799, "Pretrain/Step": 8032, "Pretrain/Step Time": 8.48819949105382} +{"Pretrain/Learning Rate": 3.1870812452346328e-06, "Pretrain/Loss": 1.992425799369812, "Pretrain/Loss (Raw)": 2.0533721446990967, "Pretrain/Step": 8033, "Pretrain/Step Time": 8.488704700022936} +{"Pretrain/Learning Rate": 3.1829340370629347e-06, "Pretrain/Loss": 1.9914675951004028, "Pretrain/Loss (Raw)": 1.9778687953948975, "Pretrain/Step": 8034, "Pretrain/Step Time": 8.488624358549714} +{"Pretrain/Learning Rate": 3.178789345482125e-06, "Pretrain/Loss": 1.9911527633666992, "Pretrain/Loss (Raw)": 1.9896453619003296, "Pretrain/Step": 8035, "Pretrain/Step Time": 8.485668871551752} +{"Pretrain/Learning Rate": 3.1746471709702964e-06, "Pretrain/Loss": 1.9900197982788086, "Pretrain/Loss (Raw)": 1.765698790550232, "Pretrain/Step": 8036, "Pretrain/Step Time": 8.488973030820489} +{"Pretrain/Learning Rate": 3.17050751400525e-06, "Pretrain/Loss": 1.9929401874542236, "Pretrain/Loss (Raw)": 2.1048545837402344, "Pretrain/Step": 8037, "Pretrain/Step Time": 8.483504265546799} +{"Pretrain/Learning Rate": 3.1663703750644843e-06, "Pretrain/Loss": 1.9930943250656128, "Pretrain/Loss (Raw)": 2.005560874938965, "Pretrain/Step": 8038, "Pretrain/Step Time": 8.48561798967421} +{"Pretrain/Learning Rate": 3.162235754625226e-06, "Pretrain/Loss": 1.9933654069900513, "Pretrain/Loss (Raw)": 1.9307904243469238, "Pretrain/Step": 8039, "Pretrain/Step Time": 8.484465975314379} +{"Pretrain/Learning Rate": 3.1581036531644014e-06, "Pretrain/Loss": 1.9913761615753174, "Pretrain/Loss (Raw)": 1.7378664016723633, "Pretrain/Step": 8040, "Pretrain/Step Time": 8.485700204968452} +{"Pretrain/Learning Rate": 3.1539740711586415e-06, "Pretrain/Loss": 1.9915013313293457, "Pretrain/Loss (Raw)": 1.8533953428268433, "Pretrain/Step": 8041, "Pretrain/Step Time": 8.48660970106721} +{"Pretrain/Learning Rate": 3.1498470090842947e-06, "Pretrain/Loss": 1.9919403791427612, "Pretrain/Loss (Raw)": 2.1294925212860107, "Pretrain/Step": 8042, "Pretrain/Step Time": 8.486561415717006} +{"Pretrain/Learning Rate": 3.1457224674174167e-06, "Pretrain/Loss": 1.992846965789795, "Pretrain/Loss (Raw)": 1.9134843349456787, "Pretrain/Step": 8043, "Pretrain/Step Time": 8.482057221233845} +{"Pretrain/Learning Rate": 3.141600446633772e-06, "Pretrain/Loss": 1.9915025234222412, "Pretrain/Loss (Raw)": 1.878922700881958, "Pretrain/Step": 8044, "Pretrain/Step Time": 8.48221580311656} +{"Pretrain/Learning Rate": 3.1374809472088373e-06, "Pretrain/Loss": 1.9914767742156982, "Pretrain/Loss (Raw)": 1.9781858921051025, "Pretrain/Step": 8045, "Pretrain/Step Time": 8.485954383388162} +{"Pretrain/Learning Rate": 3.133363969617789e-06, "Pretrain/Loss": 1.991591453552246, "Pretrain/Loss (Raw)": 1.9216336011886597, "Pretrain/Step": 8046, "Pretrain/Step Time": 8.483220955356956} +{"Pretrain/Learning Rate": 3.1292495143355223e-06, "Pretrain/Loss": 1.9905338287353516, "Pretrain/Loss (Raw)": 1.9296338558197021, "Pretrain/Step": 8047, "Pretrain/Step Time": 8.484739877283573} +{"Pretrain/Learning Rate": 3.1251375818366375e-06, "Pretrain/Loss": 1.9904762506484985, "Pretrain/Loss (Raw)": 2.0030932426452637, "Pretrain/Step": 8048, "Pretrain/Step Time": 8.486111814156175} +{"Pretrain/Learning Rate": 3.121028172595447e-06, "Pretrain/Loss": 1.9902184009552002, "Pretrain/Loss (Raw)": 2.0410690307617188, "Pretrain/Step": 8049, "Pretrain/Step Time": 8.485631324350834} +{"Pretrain/Learning Rate": 3.116921287085972e-06, "Pretrain/Loss": 1.990203619003296, "Pretrain/Loss (Raw)": 1.9599794149398804, "Pretrain/Step": 8050, "Pretrain/Step Time": 8.48510529845953} +{"Pretrain/Learning Rate": 3.112816925781931e-06, "Pretrain/Loss": 1.995434045791626, "Pretrain/Loss (Raw)": 2.1171672344207764, "Pretrain/Step": 8051, "Pretrain/Step Time": 8.486262064427137} +{"Pretrain/Learning Rate": 3.1087150891567663e-06, "Pretrain/Loss": 1.995701551437378, "Pretrain/Loss (Raw)": 1.9807194471359253, "Pretrain/Step": 8052, "Pretrain/Step Time": 8.481674229726195} +{"Pretrain/Learning Rate": 3.1046157776836283e-06, "Pretrain/Loss": 1.9961377382278442, "Pretrain/Loss (Raw)": 2.1962473392486572, "Pretrain/Step": 8053, "Pretrain/Step Time": 8.482459336519241} +{"Pretrain/Learning Rate": 3.1005189918353606e-06, "Pretrain/Loss": 1.99552321434021, "Pretrain/Loss (Raw)": 2.0179524421691895, "Pretrain/Step": 8054, "Pretrain/Step Time": 8.480751929804683} +{"Pretrain/Learning Rate": 3.096424732084535e-06, "Pretrain/Loss": 1.9945688247680664, "Pretrain/Loss (Raw)": 1.8799808025360107, "Pretrain/Step": 8055, "Pretrain/Step Time": 8.483563143759966} +{"Pretrain/Learning Rate": 3.092332998903416e-06, "Pretrain/Loss": 1.9936604499816895, "Pretrain/Loss (Raw)": 1.9256116151809692, "Pretrain/Step": 8056, "Pretrain/Step Time": 8.479784673079848} +{"Pretrain/Learning Rate": 3.088243792763984e-06, "Pretrain/Loss": 1.9933726787567139, "Pretrain/Loss (Raw)": 1.9814612865447998, "Pretrain/Step": 8057, "Pretrain/Step Time": 8.480834038928151} +{"Pretrain/Learning Rate": 3.084157114137931e-06, "Pretrain/Loss": 1.9927910566329956, "Pretrain/Loss (Raw)": 1.9806797504425049, "Pretrain/Step": 8058, "Pretrain/Step Time": 8.475390374660492} +{"Pretrain/Learning Rate": 3.080072963496655e-06, "Pretrain/Loss": 1.9925389289855957, "Pretrain/Loss (Raw)": 1.939166784286499, "Pretrain/Step": 8059, "Pretrain/Step Time": 8.480307783931494} +{"Pretrain/Learning Rate": 3.075991341311257e-06, "Pretrain/Loss": 1.9933055639266968, "Pretrain/Loss (Raw)": 2.112004280090332, "Pretrain/Step": 8060, "Pretrain/Step Time": 8.478449270129204} +{"Pretrain/Learning Rate": 3.0719122480525607e-06, "Pretrain/Loss": 1.993452548980713, "Pretrain/Loss (Raw)": 1.9641973972320557, "Pretrain/Step": 8061, "Pretrain/Step Time": 8.47938658669591} +{"Pretrain/Learning Rate": 3.0678356841910753e-06, "Pretrain/Loss": 1.9926002025604248, "Pretrain/Loss (Raw)": 2.025326728820801, "Pretrain/Step": 8062, "Pretrain/Step Time": 8.475002355873585} +{"Pretrain/Learning Rate": 3.0637616501970336e-06, "Pretrain/Loss": 1.9939286708831787, "Pretrain/Loss (Raw)": 2.1548869609832764, "Pretrain/Step": 8063, "Pretrain/Step Time": 8.476780058816075} +{"Pretrain/Learning Rate": 3.0596901465403784e-06, "Pretrain/Loss": 1.9954332113265991, "Pretrain/Loss (Raw)": 2.171684980392456, "Pretrain/Step": 8064, "Pretrain/Step Time": 8.47963116131723} +{"Pretrain/Learning Rate": 3.0556211736907537e-06, "Pretrain/Loss": 1.9966224431991577, "Pretrain/Loss (Raw)": 2.0661308765411377, "Pretrain/Step": 8065, "Pretrain/Step Time": 8.476975111290812} +{"Pretrain/Learning Rate": 3.05155473211752e-06, "Pretrain/Loss": 1.9983205795288086, "Pretrain/Loss (Raw)": 2.0146753787994385, "Pretrain/Step": 8066, "Pretrain/Step Time": 8.479786133393645} +{"Pretrain/Learning Rate": 3.047490822289731e-06, "Pretrain/Loss": 1.9994068145751953, "Pretrain/Loss (Raw)": 2.0725061893463135, "Pretrain/Step": 8067, "Pretrain/Step Time": 8.479975024238229} +{"Pretrain/Learning Rate": 3.04342944467616e-06, "Pretrain/Loss": 1.9982208013534546, "Pretrain/Loss (Raw)": 1.9344215393066406, "Pretrain/Step": 8068, "Pretrain/Step Time": 8.481579193845391} +{"Pretrain/Learning Rate": 3.0393705997452863e-06, "Pretrain/Loss": 1.997678518295288, "Pretrain/Loss (Raw)": 2.0678131580352783, "Pretrain/Step": 8069, "Pretrain/Step Time": 8.481833362951875} +{"Pretrain/Learning Rate": 3.035314287965302e-06, "Pretrain/Loss": 1.9967601299285889, "Pretrain/Loss (Raw)": 1.8614510297775269, "Pretrain/Step": 8070, "Pretrain/Step Time": 8.482718953862786} +{"Pretrain/Learning Rate": 3.0312605098040904e-06, "Pretrain/Loss": 1.9986815452575684, "Pretrain/Loss (Raw)": 2.09647798538208, "Pretrain/Step": 8071, "Pretrain/Step Time": 8.481697203591466} +{"Pretrain/Learning Rate": 3.027209265729264e-06, "Pretrain/Loss": 1.9986947774887085, "Pretrain/Loss (Raw)": 1.9479258060455322, "Pretrain/Step": 8072, "Pretrain/Step Time": 8.48094579204917} +{"Pretrain/Learning Rate": 3.0231605562081213e-06, "Pretrain/Loss": 1.9992241859436035, "Pretrain/Loss (Raw)": 1.977221131324768, "Pretrain/Step": 8073, "Pretrain/Step Time": 8.48355270177126} +{"Pretrain/Learning Rate": 3.0191143817076854e-06, "Pretrain/Loss": 2.0010085105895996, "Pretrain/Loss (Raw)": 2.033372163772583, "Pretrain/Step": 8074, "Pretrain/Step Time": 8.483148684725165} +{"Pretrain/Learning Rate": 3.015070742694681e-06, "Pretrain/Loss": 2.001802682876587, "Pretrain/Loss (Raw)": 2.1252331733703613, "Pretrain/Step": 8075, "Pretrain/Step Time": 8.484199661761522} +{"Pretrain/Learning Rate": 3.011029639635546e-06, "Pretrain/Loss": 2.001911163330078, "Pretrain/Loss (Raw)": 2.1109039783477783, "Pretrain/Step": 8076, "Pretrain/Step Time": 8.484969772398472} +{"Pretrain/Learning Rate": 3.0069910729964068e-06, "Pretrain/Loss": 2.0023317337036133, "Pretrain/Loss (Raw)": 1.8885140419006348, "Pretrain/Step": 8077, "Pretrain/Step Time": 8.482335396111012} +{"Pretrain/Learning Rate": 3.002955043243122e-06, "Pretrain/Loss": 2.002110242843628, "Pretrain/Loss (Raw)": 2.0166938304901123, "Pretrain/Step": 8078, "Pretrain/Step Time": 8.48277759924531} +{"Pretrain/Learning Rate": 2.998921550841241e-06, "Pretrain/Loss": 2.0028748512268066, "Pretrain/Loss (Raw)": 2.116884708404541, "Pretrain/Step": 8079, "Pretrain/Step Time": 8.48386463522911} +{"Pretrain/Learning Rate": 2.994890596256028e-06, "Pretrain/Loss": 2.0038201808929443, "Pretrain/Loss (Raw)": 2.180572986602783, "Pretrain/Step": 8080, "Pretrain/Step Time": 8.483270287513733} +{"Pretrain/Learning Rate": 2.99086217995245e-06, "Pretrain/Loss": 2.0035042762756348, "Pretrain/Loss (Raw)": 1.8914434909820557, "Pretrain/Step": 8081, "Pretrain/Step Time": 8.48465465568006} +{"Pretrain/Learning Rate": 2.9868363023951935e-06, "Pretrain/Loss": 2.0020556449890137, "Pretrain/Loss (Raw)": 1.8434900045394897, "Pretrain/Step": 8082, "Pretrain/Step Time": 8.484274117276073} +{"Pretrain/Learning Rate": 2.9828129640486257e-06, "Pretrain/Loss": 2.00156569480896, "Pretrain/Loss (Raw)": 1.857131838798523, "Pretrain/Step": 8083, "Pretrain/Step Time": 8.483086477965117} +{"Pretrain/Learning Rate": 2.9787921653768454e-06, "Pretrain/Loss": 2.000027656555176, "Pretrain/Loss (Raw)": 1.7408193349838257, "Pretrain/Step": 8084, "Pretrain/Step Time": 8.480907570570707} +{"Pretrain/Learning Rate": 2.97477390684365e-06, "Pretrain/Loss": 1.9986941814422607, "Pretrain/Loss (Raw)": 1.7970424890518188, "Pretrain/Step": 8085, "Pretrain/Step Time": 8.47974207624793} +{"Pretrain/Learning Rate": 2.970758188912551e-06, "Pretrain/Loss": 2.0015721321105957, "Pretrain/Loss (Raw)": 2.288926362991333, "Pretrain/Step": 8086, "Pretrain/Step Time": 8.478915840387344} +{"Pretrain/Learning Rate": 2.9667450120467453e-06, "Pretrain/Loss": 2.0016286373138428, "Pretrain/Loss (Raw)": 2.119919776916504, "Pretrain/Step": 8087, "Pretrain/Step Time": 8.478926561772823} +{"Pretrain/Learning Rate": 2.962734376709167e-06, "Pretrain/Loss": 2.002223491668701, "Pretrain/Loss (Raw)": 2.049649715423584, "Pretrain/Step": 8088, "Pretrain/Step Time": 8.477561881765723} +{"Pretrain/Learning Rate": 2.958726283362426e-06, "Pretrain/Loss": 2.0046300888061523, "Pretrain/Loss (Raw)": 2.0677523612976074, "Pretrain/Step": 8089, "Pretrain/Step Time": 8.481552371755242} +{"Pretrain/Learning Rate": 2.954720732468866e-06, "Pretrain/Loss": 2.0035834312438965, "Pretrain/Loss (Raw)": 1.8821886777877808, "Pretrain/Step": 8090, "Pretrain/Step Time": 8.476111808791757} +{"Pretrain/Learning Rate": 2.9507177244905205e-06, "Pretrain/Loss": 2.0042290687561035, "Pretrain/Loss (Raw)": 2.0385169982910156, "Pretrain/Step": 8091, "Pretrain/Step Time": 8.477452725172043} +{"Pretrain/Learning Rate": 2.9467172598891395e-06, "Pretrain/Loss": 2.005197525024414, "Pretrain/Loss (Raw)": 2.145563840866089, "Pretrain/Step": 8092, "Pretrain/Step Time": 8.47678136266768} +{"Pretrain/Learning Rate": 2.942719339126171e-06, "Pretrain/Loss": 2.005871057510376, "Pretrain/Loss (Raw)": 1.966723918914795, "Pretrain/Step": 8093, "Pretrain/Step Time": 8.473647467792034} +{"Pretrain/Learning Rate": 2.9387239626627734e-06, "Pretrain/Loss": 2.005438804626465, "Pretrain/Loss (Raw)": 1.9620230197906494, "Pretrain/Step": 8094, "Pretrain/Step Time": 8.469367280602455} +{"Pretrain/Learning Rate": 2.934731130959814e-06, "Pretrain/Loss": 2.0023765563964844, "Pretrain/Loss (Raw)": 1.8997949361801147, "Pretrain/Step": 8095, "Pretrain/Step Time": 8.473547153174877} +{"Pretrain/Learning Rate": 2.930740844477867e-06, "Pretrain/Loss": 2.003386974334717, "Pretrain/Loss (Raw)": 2.1420629024505615, "Pretrain/Step": 8096, "Pretrain/Step Time": 8.470475478097796} +{"Pretrain/Learning Rate": 2.92675310367721e-06, "Pretrain/Loss": 2.00115704536438, "Pretrain/Loss (Raw)": 1.793515682220459, "Pretrain/Step": 8097, "Pretrain/Step Time": 8.470719490200281} +{"Pretrain/Learning Rate": 2.9227679090178205e-06, "Pretrain/Loss": 2.0013160705566406, "Pretrain/Loss (Raw)": 2.045684814453125, "Pretrain/Step": 8098, "Pretrain/Step Time": 8.472360977903008} +{"Pretrain/Learning Rate": 2.9187852609593946e-06, "Pretrain/Loss": 2.0017902851104736, "Pretrain/Loss (Raw)": 2.101372241973877, "Pretrain/Step": 8099, "Pretrain/Step Time": 8.47079742886126} +{"Pretrain/Learning Rate": 2.9148051599613314e-06, "Pretrain/Loss": 2.0029702186584473, "Pretrain/Loss (Raw)": 2.227795124053955, "Pretrain/Step": 8100, "Pretrain/Step Time": 8.475375154986978} +{"Pretrain/Learning Rate": 2.910827606482727e-06, "Pretrain/Loss": 2.003520965576172, "Pretrain/Loss (Raw)": 2.1249654293060303, "Pretrain/Step": 8101, "Pretrain/Step Time": 8.472336204722524} +{"Pretrain/Learning Rate": 2.906852600982404e-06, "Pretrain/Loss": 2.001077651977539, "Pretrain/Loss (Raw)": 1.6117802858352661, "Pretrain/Step": 8102, "Pretrain/Step Time": 8.475799046456814} +{"Pretrain/Learning Rate": 2.9028801439188625e-06, "Pretrain/Loss": 2.0017173290252686, "Pretrain/Loss (Raw)": 1.8469794988632202, "Pretrain/Step": 8103, "Pretrain/Step Time": 8.472109032794833} +{"Pretrain/Learning Rate": 2.8989102357503376e-06, "Pretrain/Loss": 1.9998818635940552, "Pretrain/Loss (Raw)": 1.8872374296188354, "Pretrain/Step": 8104, "Pretrain/Step Time": 8.468551242724061} +{"Pretrain/Learning Rate": 2.8949428769347446e-06, "Pretrain/Loss": 2.0018529891967773, "Pretrain/Loss (Raw)": 2.1441116333007812, "Pretrain/Step": 8105, "Pretrain/Step Time": 8.468943171203136} +{"Pretrain/Learning Rate": 2.8909780679297225e-06, "Pretrain/Loss": 2.0008773803710938, "Pretrain/Loss (Raw)": 1.9498412609100342, "Pretrain/Step": 8106, "Pretrain/Step Time": 8.472088765352964} +{"Pretrain/Learning Rate": 2.887015809192611e-06, "Pretrain/Loss": 2.0009398460388184, "Pretrain/Loss (Raw)": 1.8797794580459595, "Pretrain/Step": 8107, "Pretrain/Step Time": 8.468458173796535} +{"Pretrain/Learning Rate": 2.883056101180459e-06, "Pretrain/Loss": 2.002009153366089, "Pretrain/Loss (Raw)": 2.1717967987060547, "Pretrain/Step": 8108, "Pretrain/Step Time": 8.469702586531639} +{"Pretrain/Learning Rate": 2.879098944350009e-06, "Pretrain/Loss": 2.0018117427825928, "Pretrain/Loss (Raw)": 1.8009588718414307, "Pretrain/Step": 8109, "Pretrain/Step Time": 8.465990342199802} +{"Pretrain/Learning Rate": 2.8751443391577203e-06, "Pretrain/Loss": 2.0026533603668213, "Pretrain/Loss (Raw)": 2.0638442039489746, "Pretrain/Step": 8110, "Pretrain/Step Time": 8.459671342745423} +{"Pretrain/Learning Rate": 2.8711922860597593e-06, "Pretrain/Loss": 2.001739740371704, "Pretrain/Loss (Raw)": 1.9693764448165894, "Pretrain/Step": 8111, "Pretrain/Step Time": 8.460013929754496} +{"Pretrain/Learning Rate": 2.8672427855119894e-06, "Pretrain/Loss": 2.00173020362854, "Pretrain/Loss (Raw)": 2.0506505966186523, "Pretrain/Step": 8112, "Pretrain/Step Time": 8.46983703225851} +{"Pretrain/Learning Rate": 2.8632958379699927e-06, "Pretrain/Loss": 2.0014097690582275, "Pretrain/Loss (Raw)": 1.990109920501709, "Pretrain/Step": 8113, "Pretrain/Step Time": 8.468457052484155} +{"Pretrain/Learning Rate": 2.8593514438890354e-06, "Pretrain/Loss": 1.9988367557525635, "Pretrain/Loss (Raw)": 1.8057283163070679, "Pretrain/Step": 8114, "Pretrain/Step Time": 8.469218090176582} +{"Pretrain/Learning Rate": 2.8554096037241103e-06, "Pretrain/Loss": 1.9995719194412231, "Pretrain/Loss (Raw)": 2.077650308609009, "Pretrain/Step": 8115, "Pretrain/Step Time": 8.468256533145905} +{"Pretrain/Learning Rate": 2.8514703179299024e-06, "Pretrain/Loss": 1.9995629787445068, "Pretrain/Loss (Raw)": 1.972311019897461, "Pretrain/Step": 8116, "Pretrain/Step Time": 8.468717748299241} +{"Pretrain/Learning Rate": 2.8475335869608127e-06, "Pretrain/Loss": 1.998307704925537, "Pretrain/Loss (Raw)": 1.7979148626327515, "Pretrain/Step": 8117, "Pretrain/Step Time": 8.47025502473116} +{"Pretrain/Learning Rate": 2.843599411270942e-06, "Pretrain/Loss": 1.9975624084472656, "Pretrain/Loss (Raw)": 1.9932788610458374, "Pretrain/Step": 8118, "Pretrain/Step Time": 8.469201741740108} +{"Pretrain/Learning Rate": 2.8396677913140877e-06, "Pretrain/Loss": 1.9978127479553223, "Pretrain/Loss (Raw)": 2.0579910278320312, "Pretrain/Step": 8119, "Pretrain/Step Time": 8.47114328108728} +{"Pretrain/Learning Rate": 2.8357387275437657e-06, "Pretrain/Loss": 1.9982240200042725, "Pretrain/Loss (Raw)": 1.9823428392410278, "Pretrain/Step": 8120, "Pretrain/Step Time": 8.467801174148917} +{"Pretrain/Learning Rate": 2.831812220413199e-06, "Pretrain/Loss": 1.9964784383773804, "Pretrain/Loss (Raw)": 1.9819597005844116, "Pretrain/Step": 8121, "Pretrain/Step Time": 8.468159781768918} +{"Pretrain/Learning Rate": 2.827888270375295e-06, "Pretrain/Loss": 1.996370553970337, "Pretrain/Loss (Raw)": 1.97914719581604, "Pretrain/Step": 8122, "Pretrain/Step Time": 8.46486784145236} +{"Pretrain/Learning Rate": 2.823966877882689e-06, "Pretrain/Loss": 1.997888207435608, "Pretrain/Loss (Raw)": 2.116628885269165, "Pretrain/Step": 8123, "Pretrain/Step Time": 8.46551319397986} +{"Pretrain/Learning Rate": 2.8200480433877158e-06, "Pretrain/Loss": 2.0001380443573, "Pretrain/Loss (Raw)": 2.141120195388794, "Pretrain/Step": 8124, "Pretrain/Step Time": 8.464329477399588} +{"Pretrain/Learning Rate": 2.8161317673424005e-06, "Pretrain/Loss": 2.0022499561309814, "Pretrain/Loss (Raw)": 2.2553064823150635, "Pretrain/Step": 8125, "Pretrain/Step Time": 8.464851301163435} +{"Pretrain/Learning Rate": 2.8122180501984895e-06, "Pretrain/Loss": 2.0031380653381348, "Pretrain/Loss (Raw)": 2.066626787185669, "Pretrain/Step": 8126, "Pretrain/Step Time": 8.462390944361687} +{"Pretrain/Learning Rate": 2.8083068924074308e-06, "Pretrain/Loss": 2.0039727687835693, "Pretrain/Loss (Raw)": 1.9389203786849976, "Pretrain/Step": 8127, "Pretrain/Step Time": 8.460542572662234} +{"Pretrain/Learning Rate": 2.804398294420371e-06, "Pretrain/Loss": 2.004207134246826, "Pretrain/Loss (Raw)": 2.083132266998291, "Pretrain/Step": 8128, "Pretrain/Step Time": 8.459569552913308} +{"Pretrain/Learning Rate": 2.8004922566881753e-06, "Pretrain/Loss": 2.0035533905029297, "Pretrain/Loss (Raw)": 2.043010711669922, "Pretrain/Step": 8129, "Pretrain/Step Time": 8.460956387221813} +{"Pretrain/Learning Rate": 2.7965887796613884e-06, "Pretrain/Loss": 2.0038323402404785, "Pretrain/Loss (Raw)": 2.145200729370117, "Pretrain/Step": 8130, "Pretrain/Step Time": 8.464393127709627} +{"Pretrain/Learning Rate": 2.792687863790286e-06, "Pretrain/Loss": 2.0044310092926025, "Pretrain/Loss (Raw)": 2.1210389137268066, "Pretrain/Step": 8131, "Pretrain/Step Time": 8.459671650081873} +{"Pretrain/Learning Rate": 2.7887895095248308e-06, "Pretrain/Loss": 2.0037732124328613, "Pretrain/Loss (Raw)": 1.9502718448638916, "Pretrain/Step": 8132, "Pretrain/Step Time": 8.46051418967545} +{"Pretrain/Learning Rate": 2.7848937173147017e-06, "Pretrain/Loss": 2.0013484954833984, "Pretrain/Loss (Raw)": 1.8566972017288208, "Pretrain/Step": 8133, "Pretrain/Step Time": 8.46072050370276} +{"Pretrain/Learning Rate": 2.781000487609281e-06, "Pretrain/Loss": 2.0016493797302246, "Pretrain/Loss (Raw)": 1.9508030414581299, "Pretrain/Step": 8134, "Pretrain/Step Time": 8.458691615611315} +{"Pretrain/Learning Rate": 2.77710982085764e-06, "Pretrain/Loss": 2.0024027824401855, "Pretrain/Loss (Raw)": 2.0872678756713867, "Pretrain/Step": 8135, "Pretrain/Step Time": 8.462364114820957} +{"Pretrain/Learning Rate": 2.773221717508573e-06, "Pretrain/Loss": 2.002164125442505, "Pretrain/Loss (Raw)": 1.9186984300613403, "Pretrain/Step": 8136, "Pretrain/Step Time": 8.459473256021738} +{"Pretrain/Learning Rate": 2.769336178010573e-06, "Pretrain/Loss": 2.003706455230713, "Pretrain/Loss (Raw)": 2.0266499519348145, "Pretrain/Step": 8137, "Pretrain/Step Time": 8.460097718983889} +{"Pretrain/Learning Rate": 2.7654532028118297e-06, "Pretrain/Loss": 2.0029351711273193, "Pretrain/Loss (Raw)": 1.9165244102478027, "Pretrain/Step": 8138, "Pretrain/Step Time": 8.45776641741395} +{"Pretrain/Learning Rate": 2.7615727923602426e-06, "Pretrain/Loss": 2.002173900604248, "Pretrain/Loss (Raw)": 1.9461427927017212, "Pretrain/Step": 8139, "Pretrain/Step Time": 8.458053076639771} +{"Pretrain/Learning Rate": 2.757694947103426e-06, "Pretrain/Loss": 2.0044736862182617, "Pretrain/Loss (Raw)": 2.1049485206604004, "Pretrain/Step": 8140, "Pretrain/Step Time": 8.457592783495784} +{"Pretrain/Learning Rate": 2.7538196674886746e-06, "Pretrain/Loss": 2.0026845932006836, "Pretrain/Loss (Raw)": 1.8949998617172241, "Pretrain/Step": 8141, "Pretrain/Step Time": 8.459169618785381} +{"Pretrain/Learning Rate": 2.7499469539630092e-06, "Pretrain/Loss": 2.004232883453369, "Pretrain/Loss (Raw)": 2.0354490280151367, "Pretrain/Step": 8142, "Pretrain/Step Time": 8.456270460039377} +{"Pretrain/Learning Rate": 2.746076806973141e-06, "Pretrain/Loss": 2.006549835205078, "Pretrain/Loss (Raw)": 2.119903326034546, "Pretrain/Step": 8143, "Pretrain/Step Time": 8.46126190572977} +{"Pretrain/Learning Rate": 2.742209226965492e-06, "Pretrain/Loss": 2.0085930824279785, "Pretrain/Loss (Raw)": 2.1684505939483643, "Pretrain/Step": 8144, "Pretrain/Step Time": 8.464134253561497} +{"Pretrain/Learning Rate": 2.738344214386193e-06, "Pretrain/Loss": 2.008383274078369, "Pretrain/Loss (Raw)": 1.982098937034607, "Pretrain/Step": 8145, "Pretrain/Step Time": 8.465214371681213} +{"Pretrain/Learning Rate": 2.7344817696810603e-06, "Pretrain/Loss": 2.0076332092285156, "Pretrain/Loss (Raw)": 2.123195171356201, "Pretrain/Step": 8146, "Pretrain/Step Time": 8.462059516459703} +{"Pretrain/Learning Rate": 2.7306218932956317e-06, "Pretrain/Loss": 2.0065553188323975, "Pretrain/Loss (Raw)": 1.824516773223877, "Pretrain/Step": 8147, "Pretrain/Step Time": 8.463952062651515} +{"Pretrain/Learning Rate": 2.72676458567514e-06, "Pretrain/Loss": 2.0057010650634766, "Pretrain/Loss (Raw)": 2.0007190704345703, "Pretrain/Step": 8148, "Pretrain/Step Time": 8.461692100390792} +{"Pretrain/Learning Rate": 2.7229098472645263e-06, "Pretrain/Loss": 2.0045528411865234, "Pretrain/Loss (Raw)": 1.9794156551361084, "Pretrain/Step": 8149, "Pretrain/Step Time": 8.463122425600886} +{"Pretrain/Learning Rate": 2.7190576785084408e-06, "Pretrain/Loss": 2.002608299255371, "Pretrain/Loss (Raw)": 1.7663021087646484, "Pretrain/Step": 8150, "Pretrain/Step Time": 8.464581582695246} +{"Pretrain/Learning Rate": 2.7152080798512144e-06, "Pretrain/Loss": 2.0024499893188477, "Pretrain/Loss (Raw)": 2.0374865531921387, "Pretrain/Step": 8151, "Pretrain/Step Time": 8.461653742939234} +{"Pretrain/Learning Rate": 2.711361051736905e-06, "Pretrain/Loss": 2.0004971027374268, "Pretrain/Loss (Raw)": 1.7689520120620728, "Pretrain/Step": 8152, "Pretrain/Step Time": 8.459587771445513} +{"Pretrain/Learning Rate": 2.707516594609269e-06, "Pretrain/Loss": 2.001878261566162, "Pretrain/Loss (Raw)": 2.0671544075012207, "Pretrain/Step": 8153, "Pretrain/Step Time": 8.45888895355165} +{"Pretrain/Learning Rate": 2.7036747089117575e-06, "Pretrain/Loss": 2.0007095336914062, "Pretrain/Loss (Raw)": 2.0778329372406006, "Pretrain/Step": 8154, "Pretrain/Step Time": 8.456634951755404} +{"Pretrain/Learning Rate": 2.69983539508753e-06, "Pretrain/Loss": 1.999218463897705, "Pretrain/Loss (Raw)": 1.8350889682769775, "Pretrain/Step": 8155, "Pretrain/Step Time": 8.456070862710476} +{"Pretrain/Learning Rate": 2.6959986535794597e-06, "Pretrain/Loss": 1.9982144832611084, "Pretrain/Loss (Raw)": 2.0231151580810547, "Pretrain/Step": 8156, "Pretrain/Step Time": 8.458476496860385} +{"Pretrain/Learning Rate": 2.692164484830101e-06, "Pretrain/Loss": 1.9980744123458862, "Pretrain/Loss (Raw)": 2.1086673736572266, "Pretrain/Step": 8157, "Pretrain/Step Time": 8.459984386339784} +{"Pretrain/Learning Rate": 2.6883328892817307e-06, "Pretrain/Loss": 1.998520016670227, "Pretrain/Loss (Raw)": 1.9313064813613892, "Pretrain/Step": 8158, "Pretrain/Step Time": 8.459696454927325} +{"Pretrain/Learning Rate": 2.6845038673763173e-06, "Pretrain/Loss": 1.9971940517425537, "Pretrain/Loss (Raw)": 2.027322769165039, "Pretrain/Step": 8159, "Pretrain/Step Time": 8.459450662136078} +{"Pretrain/Learning Rate": 2.680677419555544e-06, "Pretrain/Loss": 1.9971957206726074, "Pretrain/Loss (Raw)": 2.066481113433838, "Pretrain/Step": 8160, "Pretrain/Step Time": 8.458702376112342} +{"Pretrain/Learning Rate": 2.676853546260791e-06, "Pretrain/Loss": 1.9981704950332642, "Pretrain/Loss (Raw)": 2.1781513690948486, "Pretrain/Step": 8161, "Pretrain/Step Time": 8.459352727979422} +{"Pretrain/Learning Rate": 2.67303224793313e-06, "Pretrain/Loss": 1.997972011566162, "Pretrain/Loss (Raw)": 1.9524556398391724, "Pretrain/Step": 8162, "Pretrain/Step Time": 8.46096415258944} +{"Pretrain/Learning Rate": 2.669213525013356e-06, "Pretrain/Loss": 1.999305248260498, "Pretrain/Loss (Raw)": 2.1602978706359863, "Pretrain/Step": 8163, "Pretrain/Step Time": 8.463502673432231} +{"Pretrain/Learning Rate": 2.6653973779419528e-06, "Pretrain/Loss": 2.0019712448120117, "Pretrain/Loss (Raw)": 2.106945276260376, "Pretrain/Step": 8164, "Pretrain/Step Time": 8.460797803476453} +{"Pretrain/Learning Rate": 2.6615838071591125e-06, "Pretrain/Loss": 2.0007379055023193, "Pretrain/Loss (Raw)": 1.9469873905181885, "Pretrain/Step": 8165, "Pretrain/Step Time": 8.46337521634996} +{"Pretrain/Learning Rate": 2.6577728131047337e-06, "Pretrain/Loss": 2.0001473426818848, "Pretrain/Loss (Raw)": 1.92997145652771, "Pretrain/Step": 8166, "Pretrain/Step Time": 8.460839956998825} +{"Pretrain/Learning Rate": 2.6539643962184057e-06, "Pretrain/Loss": 2.001129627227783, "Pretrain/Loss (Raw)": 2.05649733543396, "Pretrain/Step": 8167, "Pretrain/Step Time": 8.45779606886208} +{"Pretrain/Learning Rate": 2.6501585569394333e-06, "Pretrain/Loss": 2.002878427505493, "Pretrain/Loss (Raw)": 1.961742639541626, "Pretrain/Step": 8168, "Pretrain/Step Time": 8.456533055752516} +{"Pretrain/Learning Rate": 2.646355295706815e-06, "Pretrain/Loss": 2.005324363708496, "Pretrain/Loss (Raw)": 2.166465997695923, "Pretrain/Step": 8169, "Pretrain/Step Time": 8.462375670671463} +{"Pretrain/Learning Rate": 2.642554612959261e-06, "Pretrain/Loss": 2.004899024963379, "Pretrain/Loss (Raw)": 2.075049877166748, "Pretrain/Step": 8170, "Pretrain/Step Time": 8.45848941989243} +{"Pretrain/Learning Rate": 2.6387565091351735e-06, "Pretrain/Loss": 2.005399703979492, "Pretrain/Loss (Raw)": 1.977573037147522, "Pretrain/Step": 8171, "Pretrain/Step Time": 8.456723196431994} +{"Pretrain/Learning Rate": 2.6349609846726688e-06, "Pretrain/Loss": 2.0058610439300537, "Pretrain/Loss (Raw)": 1.9379844665527344, "Pretrain/Step": 8172, "Pretrain/Step Time": 8.454133249819279} +{"Pretrain/Learning Rate": 2.631168040009549e-06, "Pretrain/Loss": 2.006762742996216, "Pretrain/Loss (Raw)": 2.0936007499694824, "Pretrain/Step": 8173, "Pretrain/Step Time": 8.455265406519175} +{"Pretrain/Learning Rate": 2.627377675583337e-06, "Pretrain/Loss": 2.007504940032959, "Pretrain/Loss (Raw)": 2.0166232585906982, "Pretrain/Step": 8174, "Pretrain/Step Time": 8.461344627663493} +{"Pretrain/Learning Rate": 2.6235898918312434e-06, "Pretrain/Loss": 2.0096793174743652, "Pretrain/Loss (Raw)": 2.2079660892486572, "Pretrain/Step": 8175, "Pretrain/Step Time": 8.459211334586143} +{"Pretrain/Learning Rate": 2.6198046891902003e-06, "Pretrain/Loss": 2.0082497596740723, "Pretrain/Loss (Raw)": 1.8201080560684204, "Pretrain/Step": 8176, "Pretrain/Step Time": 8.455523803830147} +{"Pretrain/Learning Rate": 2.6160220680968155e-06, "Pretrain/Loss": 2.0089175701141357, "Pretrain/Loss (Raw)": 2.126558542251587, "Pretrain/Step": 8177, "Pretrain/Step Time": 8.458926057443023} +{"Pretrain/Learning Rate": 2.6122420289874216e-06, "Pretrain/Loss": 2.0099666118621826, "Pretrain/Loss (Raw)": 2.0942347049713135, "Pretrain/Step": 8178, "Pretrain/Step Time": 8.458834486082196} +{"Pretrain/Learning Rate": 2.608464572298039e-06, "Pretrain/Loss": 2.0098977088928223, "Pretrain/Loss (Raw)": 2.1083767414093018, "Pretrain/Step": 8179, "Pretrain/Step Time": 8.463376758620143} +{"Pretrain/Learning Rate": 2.6046896984643993e-06, "Pretrain/Loss": 2.009512424468994, "Pretrain/Loss (Raw)": 1.9314017295837402, "Pretrain/Step": 8180, "Pretrain/Step Time": 8.46618084795773} +{"Pretrain/Learning Rate": 2.6009174079219324e-06, "Pretrain/Loss": 2.009061336517334, "Pretrain/Loss (Raw)": 2.1384899616241455, "Pretrain/Step": 8181, "Pretrain/Step Time": 8.465771900489926} +{"Pretrain/Learning Rate": 2.597147701105779e-06, "Pretrain/Loss": 2.0093984603881836, "Pretrain/Loss (Raw)": 2.0611023902893066, "Pretrain/Step": 8182, "Pretrain/Step Time": 8.465949308127165} +{"Pretrain/Learning Rate": 2.5933805784507576e-06, "Pretrain/Loss": 2.0077929496765137, "Pretrain/Loss (Raw)": 1.6744803190231323, "Pretrain/Step": 8183, "Pretrain/Step Time": 8.462470952421427} +{"Pretrain/Learning Rate": 2.5896160403914126e-06, "Pretrain/Loss": 2.008833408355713, "Pretrain/Loss (Raw)": 2.0588018894195557, "Pretrain/Step": 8184, "Pretrain/Step Time": 8.465583303943276} +{"Pretrain/Learning Rate": 2.58585408736198e-06, "Pretrain/Loss": 2.0064830780029297, "Pretrain/Loss (Raw)": 1.6806175708770752, "Pretrain/Step": 8185, "Pretrain/Step Time": 8.464770631864667} +{"Pretrain/Learning Rate": 2.5820947197964103e-06, "Pretrain/Loss": 2.0065128803253174, "Pretrain/Loss (Raw)": 1.9844728708267212, "Pretrain/Step": 8186, "Pretrain/Step Time": 8.464980695396662} +{"Pretrain/Learning Rate": 2.5783379381283277e-06, "Pretrain/Loss": 2.0067763328552246, "Pretrain/Loss (Raw)": 1.9728927612304688, "Pretrain/Step": 8187, "Pretrain/Step Time": 8.460375374183059} +{"Pretrain/Learning Rate": 2.5745837427910923e-06, "Pretrain/Loss": 2.005788803100586, "Pretrain/Loss (Raw)": 1.9855834245681763, "Pretrain/Step": 8188, "Pretrain/Step Time": 8.462397625669837} +{"Pretrain/Learning Rate": 2.570832134217735e-06, "Pretrain/Loss": 2.003861665725708, "Pretrain/Loss (Raw)": 1.7175568342208862, "Pretrain/Step": 8189, "Pretrain/Step Time": 8.461694495752454} +{"Pretrain/Learning Rate": 2.5670831128410094e-06, "Pretrain/Loss": 2.005419969558716, "Pretrain/Loss (Raw)": 2.224782705307007, "Pretrain/Step": 8190, "Pretrain/Step Time": 8.464093936607242} +{"Pretrain/Learning Rate": 2.5633366790933615e-06, "Pretrain/Loss": 2.005034923553467, "Pretrain/Loss (Raw)": 2.1055941581726074, "Pretrain/Step": 8191, "Pretrain/Step Time": 8.467698300257325} +{"Pretrain/Learning Rate": 2.5595928334069487e-06, "Pretrain/Loss": 2.003229856491089, "Pretrain/Loss (Raw)": 1.9406331777572632, "Pretrain/Step": 8192, "Pretrain/Step Time": 8.46261491253972} +{"Pretrain/Learning Rate": 2.5558515762136137e-06, "Pretrain/Loss": 2.0020267963409424, "Pretrain/Loss (Raw)": 1.9121648073196411, "Pretrain/Step": 8193, "Pretrain/Step Time": 8.464375922456384} +{"Pretrain/Learning Rate": 2.552112907944909e-06, "Pretrain/Loss": 2.001371145248413, "Pretrain/Loss (Raw)": 1.930716633796692, "Pretrain/Step": 8194, "Pretrain/Step Time": 8.463836919516325} +{"Pretrain/Learning Rate": 2.5483768290320925e-06, "Pretrain/Loss": 2.0002834796905518, "Pretrain/Loss (Raw)": 1.9333062171936035, "Pretrain/Step": 8195, "Pretrain/Step Time": 8.462315622717142} +{"Pretrain/Learning Rate": 2.5446433399061194e-06, "Pretrain/Loss": 1.9991439580917358, "Pretrain/Loss (Raw)": 1.7885633707046509, "Pretrain/Step": 8196, "Pretrain/Step Time": 8.463991789147258} +{"Pretrain/Learning Rate": 2.5409124409976506e-06, "Pretrain/Loss": 1.9984620809555054, "Pretrain/Loss (Raw)": 1.98053777217865, "Pretrain/Step": 8197, "Pretrain/Step Time": 8.4652413520962} +{"Pretrain/Learning Rate": 2.537184132737033e-06, "Pretrain/Loss": 1.9979885816574097, "Pretrain/Loss (Raw)": 1.8008369207382202, "Pretrain/Step": 8198, "Pretrain/Step Time": 8.465031046420336} +{"Pretrain/Learning Rate": 2.533458415554335e-06, "Pretrain/Loss": 1.996724247932434, "Pretrain/Loss (Raw)": 1.934640645980835, "Pretrain/Step": 8199, "Pretrain/Step Time": 8.465885452926159} +{"Pretrain/Learning Rate": 2.5297352898793092e-06, "Pretrain/Loss": 1.998395323753357, "Pretrain/Loss (Raw)": 2.161827564239502, "Pretrain/Step": 8200, "Pretrain/Step Time": 8.463786613196135} +{"Pretrain/Learning Rate": 2.5260147561414234e-06, "Pretrain/Loss": 1.9990177154541016, "Pretrain/Loss (Raw)": 2.056893825531006, "Pretrain/Step": 8201, "Pretrain/Step Time": 8.46392765454948} +{"Pretrain/Learning Rate": 2.5222968147698365e-06, "Pretrain/Loss": 2.0000240802764893, "Pretrain/Loss (Raw)": 2.162156343460083, "Pretrain/Step": 8202, "Pretrain/Step Time": 8.459378462284803} +{"Pretrain/Learning Rate": 2.51858146619342e-06, "Pretrain/Loss": 1.9973303079605103, "Pretrain/Loss (Raw)": 1.7804499864578247, "Pretrain/Step": 8203, "Pretrain/Step Time": 8.45697153173387} +{"Pretrain/Learning Rate": 2.514868710840723e-06, "Pretrain/Loss": 1.9978110790252686, "Pretrain/Loss (Raw)": 2.172445297241211, "Pretrain/Step": 8204, "Pretrain/Step Time": 8.456912714987993} +{"Pretrain/Learning Rate": 2.511158549140025e-06, "Pretrain/Loss": 1.9993940591812134, "Pretrain/Loss (Raw)": 2.0911343097686768, "Pretrain/Step": 8205, "Pretrain/Step Time": 8.46112341992557} +{"Pretrain/Learning Rate": 2.50745098151928e-06, "Pretrain/Loss": 1.9994845390319824, "Pretrain/Loss (Raw)": 2.0282697677612305, "Pretrain/Step": 8206, "Pretrain/Step Time": 8.462954591959715} +{"Pretrain/Learning Rate": 2.5037460084061602e-06, "Pretrain/Loss": 1.9994268417358398, "Pretrain/Loss (Raw)": 2.109497308731079, "Pretrain/Step": 8207, "Pretrain/Step Time": 8.46144374459982} +{"Pretrain/Learning Rate": 2.5000436302280355e-06, "Pretrain/Loss": 1.9983704090118408, "Pretrain/Loss (Raw)": 2.0453381538391113, "Pretrain/Step": 8208, "Pretrain/Step Time": 8.46235852316022} +{"Pretrain/Learning Rate": 2.4963438474119694e-06, "Pretrain/Loss": 1.9988441467285156, "Pretrain/Loss (Raw)": 1.9520996809005737, "Pretrain/Step": 8209, "Pretrain/Step Time": 8.459836073219776} +{"Pretrain/Learning Rate": 2.4926466603847286e-06, "Pretrain/Loss": 1.9996140003204346, "Pretrain/Loss (Raw)": 1.942012906074524, "Pretrain/Step": 8210, "Pretrain/Step Time": 8.464726386591792} +{"Pretrain/Learning Rate": 2.488952069572789e-06, "Pretrain/Loss": 2.0006344318389893, "Pretrain/Loss (Raw)": 1.9877530336380005, "Pretrain/Step": 8211, "Pretrain/Step Time": 8.463623909279704} +{"Pretrain/Learning Rate": 2.4852600754023155e-06, "Pretrain/Loss": 2.002671957015991, "Pretrain/Loss (Raw)": 2.0016345977783203, "Pretrain/Step": 8212, "Pretrain/Step Time": 8.463742235675454} +{"Pretrain/Learning Rate": 2.481570678299186e-06, "Pretrain/Loss": 2.003939628601074, "Pretrain/Loss (Raw)": 1.9592998027801514, "Pretrain/Step": 8213, "Pretrain/Step Time": 8.46471899934113} +{"Pretrain/Learning Rate": 2.477883878688958e-06, "Pretrain/Loss": 2.0002880096435547, "Pretrain/Loss (Raw)": 1.8214987516403198, "Pretrain/Step": 8214, "Pretrain/Step Time": 8.472538920119405} +{"Pretrain/Learning Rate": 2.4741996769969134e-06, "Pretrain/Loss": 1.998969554901123, "Pretrain/Loss (Raw)": 1.9511840343475342, "Pretrain/Step": 8215, "Pretrain/Step Time": 8.472468599677086} +{"Pretrain/Learning Rate": 2.4705180736480176e-06, "Pretrain/Loss": 1.9995288848876953, "Pretrain/Loss (Raw)": 2.12123441696167, "Pretrain/Step": 8216, "Pretrain/Step Time": 8.471206979826093} +{"Pretrain/Learning Rate": 2.4668390690669452e-06, "Pretrain/Loss": 1.9985523223876953, "Pretrain/Loss (Raw)": 1.9427489042282104, "Pretrain/Step": 8217, "Pretrain/Step Time": 8.470466492697597} +{"Pretrain/Learning Rate": 2.4631626636780704e-06, "Pretrain/Loss": 1.9996378421783447, "Pretrain/Loss (Raw)": 2.0211293697357178, "Pretrain/Step": 8218, "Pretrain/Step Time": 8.473922548815608} +{"Pretrain/Learning Rate": 2.459488857905459e-06, "Pretrain/Loss": 2.000770330429077, "Pretrain/Loss (Raw)": 2.183485507965088, "Pretrain/Step": 8219, "Pretrain/Step Time": 8.470217047259212} +{"Pretrain/Learning Rate": 2.455817652172887e-06, "Pretrain/Loss": 1.9987307786941528, "Pretrain/Loss (Raw)": 1.8845124244689941, "Pretrain/Step": 8220, "Pretrain/Step Time": 8.472902985289693} +{"Pretrain/Learning Rate": 2.4521490469038316e-06, "Pretrain/Loss": 1.9997791051864624, "Pretrain/Loss (Raw)": 2.100904941558838, "Pretrain/Step": 8221, "Pretrain/Step Time": 8.474079651758075} +{"Pretrain/Learning Rate": 2.4484830425214543e-06, "Pretrain/Loss": 2.0013771057128906, "Pretrain/Loss (Raw)": 2.1665449142456055, "Pretrain/Step": 8222, "Pretrain/Step Time": 8.47616008669138} +{"Pretrain/Learning Rate": 2.444819639448631e-06, "Pretrain/Loss": 2.0010838508605957, "Pretrain/Loss (Raw)": 1.8622781038284302, "Pretrain/Step": 8223, "Pretrain/Step Time": 8.476494766771793} +{"Pretrain/Learning Rate": 2.441158838107943e-06, "Pretrain/Loss": 2.001270055770874, "Pretrain/Loss (Raw)": 2.165879011154175, "Pretrain/Step": 8224, "Pretrain/Step Time": 8.479263730347157} +{"Pretrain/Learning Rate": 2.4375006389216497e-06, "Pretrain/Loss": 2.0026557445526123, "Pretrain/Loss (Raw)": 1.9708982706069946, "Pretrain/Step": 8225, "Pretrain/Step Time": 8.478292109444737} +{"Pretrain/Learning Rate": 2.4338450423117306e-06, "Pretrain/Loss": 2.0011816024780273, "Pretrain/Loss (Raw)": 1.8569706678390503, "Pretrain/Step": 8226, "Pretrain/Step Time": 8.477111352607608} +{"Pretrain/Learning Rate": 2.430192048699853e-06, "Pretrain/Loss": 2.0006392002105713, "Pretrain/Loss (Raw)": 2.031963586807251, "Pretrain/Step": 8227, "Pretrain/Step Time": 8.47627610526979} +{"Pretrain/Learning Rate": 2.426541658507392e-06, "Pretrain/Loss": 1.9978852272033691, "Pretrain/Loss (Raw)": 1.875291347503662, "Pretrain/Step": 8228, "Pretrain/Step Time": 8.475749924778938} +{"Pretrain/Learning Rate": 2.422893872155421e-06, "Pretrain/Loss": 1.9973738193511963, "Pretrain/Loss (Raw)": 2.059511423110962, "Pretrain/Step": 8229, "Pretrain/Step Time": 8.478001229465008} +{"Pretrain/Learning Rate": 2.4192486900647043e-06, "Pretrain/Loss": 2.0020458698272705, "Pretrain/Loss (Raw)": 2.2097957134246826, "Pretrain/Step": 8230, "Pretrain/Step Time": 8.477952994406223} +{"Pretrain/Learning Rate": 2.415606112655716e-06, "Pretrain/Loss": 2.004450798034668, "Pretrain/Loss (Raw)": 2.1548147201538086, "Pretrain/Step": 8231, "Pretrain/Step Time": 8.481126522645354} +{"Pretrain/Learning Rate": 2.411966140348626e-06, "Pretrain/Loss": 2.0065016746520996, "Pretrain/Loss (Raw)": 2.149744987487793, "Pretrain/Step": 8232, "Pretrain/Step Time": 8.483835015445948} +{"Pretrain/Learning Rate": 2.4083287735633036e-06, "Pretrain/Loss": 2.004173517227173, "Pretrain/Loss (Raw)": 1.846125841140747, "Pretrain/Step": 8233, "Pretrain/Step Time": 8.486525729298592} +{"Pretrain/Learning Rate": 2.404694012719322e-06, "Pretrain/Loss": 2.003800868988037, "Pretrain/Loss (Raw)": 1.9021357297897339, "Pretrain/Step": 8234, "Pretrain/Step Time": 8.483654560521245} +{"Pretrain/Learning Rate": 2.4010618582359424e-06, "Pretrain/Loss": 2.0034852027893066, "Pretrain/Loss (Raw)": 1.8393652439117432, "Pretrain/Step": 8235, "Pretrain/Step Time": 8.485602525994182} +{"Pretrain/Learning Rate": 2.397432310532133e-06, "Pretrain/Loss": 2.0015769004821777, "Pretrain/Loss (Raw)": 1.927500605583191, "Pretrain/Step": 8236, "Pretrain/Step Time": 8.488041166216135} +{"Pretrain/Learning Rate": 2.3938053700265694e-06, "Pretrain/Loss": 2.003535270690918, "Pretrain/Loss (Raw)": 2.0516602993011475, "Pretrain/Step": 8237, "Pretrain/Step Time": 8.488890506327152} +{"Pretrain/Learning Rate": 2.3901810371376066e-06, "Pretrain/Loss": 2.0030903816223145, "Pretrain/Loss (Raw)": 2.0069098472595215, "Pretrain/Step": 8238, "Pretrain/Step Time": 8.494066070765257} +{"Pretrain/Learning Rate": 2.386559312283318e-06, "Pretrain/Loss": 2.0027310848236084, "Pretrain/Loss (Raw)": 1.9233888387680054, "Pretrain/Step": 8239, "Pretrain/Step Time": 8.49631772376597} +{"Pretrain/Learning Rate": 2.3829401958814694e-06, "Pretrain/Loss": 2.0005922317504883, "Pretrain/Loss (Raw)": 1.776850938796997, "Pretrain/Step": 8240, "Pretrain/Step Time": 8.489117359742522} +{"Pretrain/Learning Rate": 2.379323688349516e-06, "Pretrain/Loss": 2.0023679733276367, "Pretrain/Loss (Raw)": 2.217419147491455, "Pretrain/Step": 8241, "Pretrain/Step Time": 8.490959394723177} +{"Pretrain/Learning Rate": 2.3757097901046244e-06, "Pretrain/Loss": 2.002711534500122, "Pretrain/Loss (Raw)": 1.8496935367584229, "Pretrain/Step": 8242, "Pretrain/Step Time": 8.491538567468524} +{"Pretrain/Learning Rate": 2.3720985015636577e-06, "Pretrain/Loss": 2.002647876739502, "Pretrain/Loss (Raw)": 2.0695033073425293, "Pretrain/Step": 8243, "Pretrain/Step Time": 8.49409201554954} +{"Pretrain/Learning Rate": 2.3684898231431802e-06, "Pretrain/Loss": 2.0026345252990723, "Pretrain/Loss (Raw)": 1.9705939292907715, "Pretrain/Step": 8244, "Pretrain/Step Time": 8.489069925621152} +{"Pretrain/Learning Rate": 2.3648837552594505e-06, "Pretrain/Loss": 2.004669427871704, "Pretrain/Loss (Raw)": 2.0583994388580322, "Pretrain/Step": 8245, "Pretrain/Step Time": 8.489007327705622} +{"Pretrain/Learning Rate": 2.3612802983284193e-06, "Pretrain/Loss": 2.003864049911499, "Pretrain/Loss (Raw)": 1.890201210975647, "Pretrain/Step": 8246, "Pretrain/Step Time": 8.491629995405674} +{"Pretrain/Learning Rate": 2.3576794527657516e-06, "Pretrain/Loss": 2.003365993499756, "Pretrain/Loss (Raw)": 1.9942302703857422, "Pretrain/Step": 8247, "Pretrain/Step Time": 8.491343174129725} +{"Pretrain/Learning Rate": 2.3540812189868005e-06, "Pretrain/Loss": 2.003777027130127, "Pretrain/Loss (Raw)": 2.034949541091919, "Pretrain/Step": 8248, "Pretrain/Step Time": 8.493001319468021} +{"Pretrain/Learning Rate": 2.3504855974066236e-06, "Pretrain/Loss": 2.003365993499756, "Pretrain/Loss (Raw)": 1.9293694496154785, "Pretrain/Step": 8249, "Pretrain/Step Time": 8.492282954975963} +{"Pretrain/Learning Rate": 2.346892588439981e-06, "Pretrain/Loss": 2.002140998840332, "Pretrain/Loss (Raw)": 1.8223042488098145, "Pretrain/Step": 8250, "Pretrain/Step Time": 8.491941502317786} +{"Pretrain/Learning Rate": 2.3433021925013092e-06, "Pretrain/Loss": 2.00091552734375, "Pretrain/Loss (Raw)": 1.9598039388656616, "Pretrain/Step": 8251, "Pretrain/Step Time": 8.493470083922148} +{"Pretrain/Learning Rate": 2.3397144100047673e-06, "Pretrain/Loss": 1.9993287324905396, "Pretrain/Loss (Raw)": 1.9379897117614746, "Pretrain/Step": 8252, "Pretrain/Step Time": 8.492448091506958} +{"Pretrain/Learning Rate": 2.3361292413642043e-06, "Pretrain/Loss": 1.9980241060256958, "Pretrain/Loss (Raw)": 2.0883264541625977, "Pretrain/Step": 8253, "Pretrain/Step Time": 8.493069460615516} +{"Pretrain/Learning Rate": 2.3325466869931756e-06, "Pretrain/Loss": 1.9971283674240112, "Pretrain/Loss (Raw)": 1.9519675970077515, "Pretrain/Step": 8254, "Pretrain/Step Time": 8.495834765955806} +{"Pretrain/Learning Rate": 2.3289667473049143e-06, "Pretrain/Loss": 1.9963843822479248, "Pretrain/Loss (Raw)": 1.8436858654022217, "Pretrain/Step": 8255, "Pretrain/Step Time": 8.500061996281147} +{"Pretrain/Learning Rate": 2.325389422712379e-06, "Pretrain/Loss": 1.994704008102417, "Pretrain/Loss (Raw)": 1.8680503368377686, "Pretrain/Step": 8256, "Pretrain/Step Time": 8.499566104263067} +{"Pretrain/Learning Rate": 2.321814713628198e-06, "Pretrain/Loss": 1.9958915710449219, "Pretrain/Loss (Raw)": 2.1950109004974365, "Pretrain/Step": 8257, "Pretrain/Step Time": 8.50015171058476} +{"Pretrain/Learning Rate": 2.3182426204647197e-06, "Pretrain/Loss": 1.9945738315582275, "Pretrain/Loss (Raw)": 1.9765303134918213, "Pretrain/Step": 8258, "Pretrain/Step Time": 8.497949933633208} +{"Pretrain/Learning Rate": 2.3146731436339857e-06, "Pretrain/Loss": 1.9941651821136475, "Pretrain/Loss (Raw)": 2.068739652633667, "Pretrain/Step": 8259, "Pretrain/Step Time": 8.501450382173061} +{"Pretrain/Learning Rate": 2.3111062835477315e-06, "Pretrain/Loss": 1.995234489440918, "Pretrain/Loss (Raw)": 2.08716082572937, "Pretrain/Step": 8260, "Pretrain/Step Time": 8.502019293606281} +{"Pretrain/Learning Rate": 2.3075420406173997e-06, "Pretrain/Loss": 1.9970964193344116, "Pretrain/Loss (Raw)": 2.0950024127960205, "Pretrain/Step": 8261, "Pretrain/Step Time": 8.502795396372676} +{"Pretrain/Learning Rate": 2.3039804152541146e-06, "Pretrain/Loss": 1.9976953268051147, "Pretrain/Loss (Raw)": 2.0274710655212402, "Pretrain/Step": 8262, "Pretrain/Step Time": 8.50650231167674} +{"Pretrain/Learning Rate": 2.300421407868711e-06, "Pretrain/Loss": 1.998011589050293, "Pretrain/Loss (Raw)": 2.1277568340301514, "Pretrain/Step": 8263, "Pretrain/Step Time": 8.504347069188952} +{"Pretrain/Learning Rate": 2.2968650188717218e-06, "Pretrain/Loss": 1.9983789920806885, "Pretrain/Loss (Raw)": 1.9657279253005981, "Pretrain/Step": 8264, "Pretrain/Step Time": 8.507023461163044} +{"Pretrain/Learning Rate": 2.2933112486733716e-06, "Pretrain/Loss": 1.9984657764434814, "Pretrain/Loss (Raw)": 2.037743091583252, "Pretrain/Step": 8265, "Pretrain/Step Time": 8.508713303133845} +{"Pretrain/Learning Rate": 2.2897600976835963e-06, "Pretrain/Loss": 1.9999696016311646, "Pretrain/Loss (Raw)": 2.1090190410614014, "Pretrain/Step": 8266, "Pretrain/Step Time": 8.507349569350481} +{"Pretrain/Learning Rate": 2.2862115663120076e-06, "Pretrain/Loss": 2.00050687789917, "Pretrain/Loss (Raw)": 2.0149080753326416, "Pretrain/Step": 8267, "Pretrain/Step Time": 8.507874576374888} +{"Pretrain/Learning Rate": 2.2826656549679332e-06, "Pretrain/Loss": 1.9991594552993774, "Pretrain/Loss (Raw)": 1.932494044303894, "Pretrain/Step": 8268, "Pretrain/Step Time": 8.50859111174941} +{"Pretrain/Learning Rate": 2.279122364060393e-06, "Pretrain/Loss": 1.99962317943573, "Pretrain/Loss (Raw)": 1.9543519020080566, "Pretrain/Step": 8269, "Pretrain/Step Time": 8.506152998656034} +{"Pretrain/Learning Rate": 2.275581693998108e-06, "Pretrain/Loss": 1.9985413551330566, "Pretrain/Loss (Raw)": 1.896971344947815, "Pretrain/Step": 8270, "Pretrain/Step Time": 8.508680827915668} +{"Pretrain/Learning Rate": 2.272043645189481e-06, "Pretrain/Loss": 1.9969427585601807, "Pretrain/Loss (Raw)": 1.915296196937561, "Pretrain/Step": 8271, "Pretrain/Step Time": 8.507226562127471} +{"Pretrain/Learning Rate": 2.268508218042639e-06, "Pretrain/Loss": 1.9953038692474365, "Pretrain/Loss (Raw)": 1.9586498737335205, "Pretrain/Step": 8272, "Pretrain/Step Time": 8.505586553364992} +{"Pretrain/Learning Rate": 2.264975412965381e-06, "Pretrain/Loss": 1.994861125946045, "Pretrain/Loss (Raw)": 1.9254233837127686, "Pretrain/Step": 8273, "Pretrain/Step Time": 8.50263792090118} +{"Pretrain/Learning Rate": 2.2614452303652195e-06, "Pretrain/Loss": 1.9937975406646729, "Pretrain/Loss (Raw)": 1.9870702028274536, "Pretrain/Step": 8274, "Pretrain/Step Time": 8.504858650267124} +{"Pretrain/Learning Rate": 2.257917670649359e-06, "Pretrain/Loss": 1.9953962564468384, "Pretrain/Loss (Raw)": 2.029148817062378, "Pretrain/Step": 8275, "Pretrain/Step Time": 8.503135427832603} +{"Pretrain/Learning Rate": 2.2543927342247086e-06, "Pretrain/Loss": 1.9941226243972778, "Pretrain/Loss (Raw)": 1.837697148323059, "Pretrain/Step": 8276, "Pretrain/Step Time": 8.507372107356787} +{"Pretrain/Learning Rate": 2.250870421497858e-06, "Pretrain/Loss": 1.993737816810608, "Pretrain/Loss (Raw)": 1.93015718460083, "Pretrain/Step": 8277, "Pretrain/Step Time": 8.50941170565784} +{"Pretrain/Learning Rate": 2.2473507328751086e-06, "Pretrain/Loss": 1.9950193166732788, "Pretrain/Loss (Raw)": 1.9303433895111084, "Pretrain/Step": 8278, "Pretrain/Step Time": 8.50771551206708} +{"Pretrain/Learning Rate": 2.24383366876246e-06, "Pretrain/Loss": 1.9941904544830322, "Pretrain/Loss (Raw)": 1.931393027305603, "Pretrain/Step": 8279, "Pretrain/Step Time": 8.508475366979837} +{"Pretrain/Learning Rate": 2.2403192295655962e-06, "Pretrain/Loss": 1.9965215921401978, "Pretrain/Loss (Raw)": 2.0673255920410156, "Pretrain/Step": 8280, "Pretrain/Step Time": 8.507589543238282} +{"Pretrain/Learning Rate": 2.236807415689912e-06, "Pretrain/Loss": 1.99563729763031, "Pretrain/Loss (Raw)": 1.953963279724121, "Pretrain/Step": 8281, "Pretrain/Step Time": 8.506096251308918} +{"Pretrain/Learning Rate": 2.2332982275405005e-06, "Pretrain/Loss": 1.9963968992233276, "Pretrain/Loss (Raw)": 2.1750705242156982, "Pretrain/Step": 8282, "Pretrain/Step Time": 8.50715021416545} +{"Pretrain/Learning Rate": 2.2297916655221297e-06, "Pretrain/Loss": 1.9976105690002441, "Pretrain/Loss (Raw)": 1.990435242652893, "Pretrain/Step": 8283, "Pretrain/Step Time": 8.505216993391514} +{"Pretrain/Learning Rate": 2.226287730039289e-06, "Pretrain/Loss": 1.9946396350860596, "Pretrain/Loss (Raw)": 1.642835259437561, "Pretrain/Step": 8284, "Pretrain/Step Time": 8.50427328236401} +{"Pretrain/Learning Rate": 2.2227864214961562e-06, "Pretrain/Loss": 1.9937173128128052, "Pretrain/Loss (Raw)": 1.9906132221221924, "Pretrain/Step": 8285, "Pretrain/Step Time": 8.504534745588899} +{"Pretrain/Learning Rate": 2.219287740296605e-06, "Pretrain/Loss": 1.9923908710479736, "Pretrain/Loss (Raw)": 1.7615125179290771, "Pretrain/Step": 8286, "Pretrain/Step Time": 8.501968557015061} +{"Pretrain/Learning Rate": 2.2157916868442125e-06, "Pretrain/Loss": 1.993072509765625, "Pretrain/Loss (Raw)": 2.1145949363708496, "Pretrain/Step": 8287, "Pretrain/Step Time": 8.506590634584427} +{"Pretrain/Learning Rate": 2.2122982615422365e-06, "Pretrain/Loss": 1.9928816556930542, "Pretrain/Loss (Raw)": 2.042024612426758, "Pretrain/Step": 8288, "Pretrain/Step Time": 8.505395766347647} +{"Pretrain/Learning Rate": 2.2088074647936524e-06, "Pretrain/Loss": 1.990761399269104, "Pretrain/Loss (Raw)": 1.9067624807357788, "Pretrain/Step": 8289, "Pretrain/Step Time": 8.506926806643605} +{"Pretrain/Learning Rate": 2.205319297001113e-06, "Pretrain/Loss": 1.9915473461151123, "Pretrain/Loss (Raw)": 2.0530595779418945, "Pretrain/Step": 8290, "Pretrain/Step Time": 8.506746487691998} +{"Pretrain/Learning Rate": 2.201833758566982e-06, "Pretrain/Loss": 1.990952491760254, "Pretrain/Loss (Raw)": 2.084165334701538, "Pretrain/Step": 8291, "Pretrain/Step Time": 8.504892148077488} +{"Pretrain/Learning Rate": 2.1983508498933185e-06, "Pretrain/Loss": 1.989701509475708, "Pretrain/Loss (Raw)": 1.9468026161193848, "Pretrain/Step": 8292, "Pretrain/Step Time": 8.507898578420281} +{"Pretrain/Learning Rate": 2.1948705713818683e-06, "Pretrain/Loss": 1.9907124042510986, "Pretrain/Loss (Raw)": 2.0763907432556152, "Pretrain/Step": 8293, "Pretrain/Step Time": 8.509936491027474} +{"Pretrain/Learning Rate": 2.191392923434085e-06, "Pretrain/Loss": 1.990992546081543, "Pretrain/Loss (Raw)": 1.9658429622650146, "Pretrain/Step": 8294, "Pretrain/Step Time": 8.510484796017408} +{"Pretrain/Learning Rate": 2.1879179064511117e-06, "Pretrain/Loss": 1.9908857345581055, "Pretrain/Loss (Raw)": 2.0428214073181152, "Pretrain/Step": 8295, "Pretrain/Step Time": 8.509936660528183} +{"Pretrain/Learning Rate": 2.184445520833789e-06, "Pretrain/Loss": 1.990457534790039, "Pretrain/Loss (Raw)": 1.9069178104400635, "Pretrain/Step": 8296, "Pretrain/Step Time": 8.509482869878411} +{"Pretrain/Learning Rate": 2.1809757669826653e-06, "Pretrain/Loss": 1.9895325899124146, "Pretrain/Loss (Raw)": 2.0480971336364746, "Pretrain/Step": 8297, "Pretrain/Step Time": 8.504284316673875} +{"Pretrain/Learning Rate": 2.1775086452979598e-06, "Pretrain/Loss": 1.9891533851623535, "Pretrain/Loss (Raw)": 2.026495933532715, "Pretrain/Step": 8298, "Pretrain/Step Time": 8.506984921172261} +{"Pretrain/Learning Rate": 2.1740441561796137e-06, "Pretrain/Loss": 1.9882011413574219, "Pretrain/Loss (Raw)": 1.8556830883026123, "Pretrain/Step": 8299, "Pretrain/Step Time": 8.50699270144105} +{"Pretrain/Learning Rate": 2.1705823000272518e-06, "Pretrain/Loss": 1.98765230178833, "Pretrain/Loss (Raw)": 1.8677268028259277, "Pretrain/Step": 8300, "Pretrain/Step Time": 8.509655375033617} +{"Pretrain/Learning Rate": 2.167123077240199e-06, "Pretrain/Loss": 1.9871469736099243, "Pretrain/Loss (Raw)": 2.0289230346679688, "Pretrain/Step": 8301, "Pretrain/Step Time": 8.507158476859331} +{"Pretrain/Learning Rate": 2.163666488217475e-06, "Pretrain/Loss": 1.9875032901763916, "Pretrain/Loss (Raw)": 2.062248468399048, "Pretrain/Step": 8302, "Pretrain/Step Time": 8.501599667593837} +{"Pretrain/Learning Rate": 2.1602125333578025e-06, "Pretrain/Loss": 1.9836845397949219, "Pretrain/Loss (Raw)": 1.7191708087921143, "Pretrain/Step": 8303, "Pretrain/Step Time": 8.501768734306097} +{"Pretrain/Learning Rate": 2.15676121305958e-06, "Pretrain/Loss": 1.9851088523864746, "Pretrain/Loss (Raw)": 2.0024025440216064, "Pretrain/Step": 8304, "Pretrain/Step Time": 8.501599982380867} +{"Pretrain/Learning Rate": 2.1533125277209326e-06, "Pretrain/Loss": 1.9834990501403809, "Pretrain/Loss (Raw)": 1.9205124378204346, "Pretrain/Step": 8305, "Pretrain/Step Time": 8.500487526878715} +{"Pretrain/Learning Rate": 2.149866477739648e-06, "Pretrain/Loss": 1.9838640689849854, "Pretrain/Loss (Raw)": 2.140953540802002, "Pretrain/Step": 8306, "Pretrain/Step Time": 8.501570284366608} +{"Pretrain/Learning Rate": 2.1464230635132366e-06, "Pretrain/Loss": 1.9845945835113525, "Pretrain/Loss (Raw)": 2.201894760131836, "Pretrain/Step": 8307, "Pretrain/Step Time": 8.495000343769789} +{"Pretrain/Learning Rate": 2.142982285438899e-06, "Pretrain/Loss": 1.985628366470337, "Pretrain/Loss (Raw)": 2.06370210647583, "Pretrain/Step": 8308, "Pretrain/Step Time": 8.495171437039971} +{"Pretrain/Learning Rate": 2.1395441439135163e-06, "Pretrain/Loss": 1.9836212396621704, "Pretrain/Loss (Raw)": 1.8815875053405762, "Pretrain/Step": 8309, "Pretrain/Step Time": 8.496259026229382} +{"Pretrain/Learning Rate": 2.136108639333684e-06, "Pretrain/Loss": 1.9825392961502075, "Pretrain/Loss (Raw)": 1.9226112365722656, "Pretrain/Step": 8310, "Pretrain/Step Time": 8.497634913772345} +{"Pretrain/Learning Rate": 2.1326757720956827e-06, "Pretrain/Loss": 1.985412836074829, "Pretrain/Loss (Raw)": 2.0423059463500977, "Pretrain/Step": 8311, "Pretrain/Step Time": 8.496985979378223} +{"Pretrain/Learning Rate": 2.129245542595498e-06, "Pretrain/Loss": 1.986383318901062, "Pretrain/Loss (Raw)": 2.1830132007598877, "Pretrain/Step": 8312, "Pretrain/Step Time": 8.494741812348366} +{"Pretrain/Learning Rate": 2.125817951228806e-06, "Pretrain/Loss": 1.9886524677276611, "Pretrain/Loss (Raw)": 1.971068263053894, "Pretrain/Step": 8313, "Pretrain/Step Time": 8.492592312395573} +{"Pretrain/Learning Rate": 2.1223929983909705e-06, "Pretrain/Loss": 1.9888978004455566, "Pretrain/Loss (Raw)": 2.015876054763794, "Pretrain/Step": 8314, "Pretrain/Step Time": 8.492279935628176} +{"Pretrain/Learning Rate": 2.118970684477062e-06, "Pretrain/Loss": 1.9895672798156738, "Pretrain/Loss (Raw)": 2.058596134185791, "Pretrain/Step": 8315, "Pretrain/Step Time": 8.492681734263897} +{"Pretrain/Learning Rate": 2.1155510098818445e-06, "Pretrain/Loss": 1.9893776178359985, "Pretrain/Loss (Raw)": 1.9612957239151, "Pretrain/Step": 8316, "Pretrain/Step Time": 8.492324098944664} +{"Pretrain/Learning Rate": 2.112133974999775e-06, "Pretrain/Loss": 1.991422176361084, "Pretrain/Loss (Raw)": 1.9792689085006714, "Pretrain/Step": 8317, "Pretrain/Step Time": 8.490579338744283} +{"Pretrain/Learning Rate": 2.108719580225013e-06, "Pretrain/Loss": 1.9884129762649536, "Pretrain/Loss (Raw)": 1.8395986557006836, "Pretrain/Step": 8318, "Pretrain/Step Time": 8.489373477175832} +{"Pretrain/Learning Rate": 2.1053078259513996e-06, "Pretrain/Loss": 1.9880526065826416, "Pretrain/Loss (Raw)": 2.059475898742676, "Pretrain/Step": 8319, "Pretrain/Step Time": 8.487483715638518} +{"Pretrain/Learning Rate": 2.101898712572484e-06, "Pretrain/Loss": 1.9884344339370728, "Pretrain/Loss (Raw)": 1.9894959926605225, "Pretrain/Step": 8320, "Pretrain/Step Time": 8.487474149093032} +{"Pretrain/Learning Rate": 2.098492240481506e-06, "Pretrain/Loss": 1.9892175197601318, "Pretrain/Loss (Raw)": 2.012410879135132, "Pretrain/Step": 8321, "Pretrain/Step Time": 8.48751119710505} +{"Pretrain/Learning Rate": 2.095088410071397e-06, "Pretrain/Loss": 1.989922285079956, "Pretrain/Loss (Raw)": 2.020925760269165, "Pretrain/Step": 8322, "Pretrain/Step Time": 8.486502550542355} +{"Pretrain/Learning Rate": 2.091687221734789e-06, "Pretrain/Loss": 1.990443468093872, "Pretrain/Loss (Raw)": 2.000014066696167, "Pretrain/Step": 8323, "Pretrain/Step Time": 8.48663106188178} +{"Pretrain/Learning Rate": 2.088288675864017e-06, "Pretrain/Loss": 1.9925280809402466, "Pretrain/Loss (Raw)": 2.0553863048553467, "Pretrain/Step": 8324, "Pretrain/Step Time": 8.482968147844076} +{"Pretrain/Learning Rate": 2.084892772851088e-06, "Pretrain/Loss": 1.9908612966537476, "Pretrain/Loss (Raw)": 1.767193078994751, "Pretrain/Step": 8325, "Pretrain/Step Time": 8.486779753118753} +{"Pretrain/Learning Rate": 2.0814995130877256e-06, "Pretrain/Loss": 1.9917939901351929, "Pretrain/Loss (Raw)": 1.9202085733413696, "Pretrain/Step": 8326, "Pretrain/Step Time": 8.484821697697043} +{"Pretrain/Learning Rate": 2.078108896965339e-06, "Pretrain/Loss": 1.9916415214538574, "Pretrain/Loss (Raw)": 1.9151372909545898, "Pretrain/Step": 8327, "Pretrain/Step Time": 8.487679181620479} +{"Pretrain/Learning Rate": 2.074720924875037e-06, "Pretrain/Loss": 1.9894468784332275, "Pretrain/Loss (Raw)": 1.880915880203247, "Pretrain/Step": 8328, "Pretrain/Step Time": 8.49040480516851} +{"Pretrain/Learning Rate": 2.071335597207624e-06, "Pretrain/Loss": 1.9885280132293701, "Pretrain/Loss (Raw)": 1.9392809867858887, "Pretrain/Step": 8329, "Pretrain/Step Time": 8.487642027437687} +{"Pretrain/Learning Rate": 2.067952914353588e-06, "Pretrain/Loss": 1.9852303266525269, "Pretrain/Loss (Raw)": 1.7400457859039307, "Pretrain/Step": 8330, "Pretrain/Step Time": 8.490298505872488} +{"Pretrain/Learning Rate": 2.0645728767031246e-06, "Pretrain/Loss": 1.9872915744781494, "Pretrain/Loss (Raw)": 2.044290065765381, "Pretrain/Step": 8331, "Pretrain/Step Time": 8.492797512561083} +{"Pretrain/Learning Rate": 2.0611954846461167e-06, "Pretrain/Loss": 1.9863685369491577, "Pretrain/Loss (Raw)": 2.0542938709259033, "Pretrain/Step": 8332, "Pretrain/Step Time": 8.492619020864367} +{"Pretrain/Learning Rate": 2.0578207385721526e-06, "Pretrain/Loss": 1.9864745140075684, "Pretrain/Loss (Raw)": 2.1047115325927734, "Pretrain/Step": 8333, "Pretrain/Step Time": 8.486901324242353} +{"Pretrain/Learning Rate": 2.054448638870507e-06, "Pretrain/Loss": 1.9879684448242188, "Pretrain/Loss (Raw)": 2.2194738388061523, "Pretrain/Step": 8334, "Pretrain/Step Time": 8.486119085922837} +{"Pretrain/Learning Rate": 2.0510791859301408e-06, "Pretrain/Loss": 1.9873828887939453, "Pretrain/Loss (Raw)": 2.034543991088867, "Pretrain/Step": 8335, "Pretrain/Step Time": 8.488763950765133} +{"Pretrain/Learning Rate": 2.047712380139727e-06, "Pretrain/Loss": 1.9877090454101562, "Pretrain/Loss (Raw)": 2.0870983600616455, "Pretrain/Step": 8336, "Pretrain/Step Time": 8.488130619749427} +{"Pretrain/Learning Rate": 2.0443482218876265e-06, "Pretrain/Loss": 1.9872429370880127, "Pretrain/Loss (Raw)": 1.8924301862716675, "Pretrain/Step": 8337, "Pretrain/Step Time": 8.48939348384738} +{"Pretrain/Learning Rate": 2.040986711561893e-06, "Pretrain/Loss": 1.9884731769561768, "Pretrain/Loss (Raw)": 2.099501132965088, "Pretrain/Step": 8338, "Pretrain/Step Time": 8.486577874049544} +{"Pretrain/Learning Rate": 2.0376278495502693e-06, "Pretrain/Loss": 1.9875414371490479, "Pretrain/Loss (Raw)": 1.8684866428375244, "Pretrain/Step": 8339, "Pretrain/Step Time": 8.488136360421777} +{"Pretrain/Learning Rate": 2.0342716362402094e-06, "Pretrain/Loss": 1.9871771335601807, "Pretrain/Loss (Raw)": 1.954999566078186, "Pretrain/Step": 8340, "Pretrain/Step Time": 8.491402756422758} +{"Pretrain/Learning Rate": 2.030918072018842e-06, "Pretrain/Loss": 1.9861805438995361, "Pretrain/Loss (Raw)": 1.831756353378296, "Pretrain/Step": 8341, "Pretrain/Step Time": 8.491091160103679} +{"Pretrain/Learning Rate": 2.027567157273e-06, "Pretrain/Loss": 1.984993815422058, "Pretrain/Loss (Raw)": 1.6695597171783447, "Pretrain/Step": 8342, "Pretrain/Step Time": 8.485341854393482} +{"Pretrain/Learning Rate": 2.0242188923892154e-06, "Pretrain/Loss": 1.9851657152175903, "Pretrain/Loss (Raw)": 1.9732035398483276, "Pretrain/Step": 8343, "Pretrain/Step Time": 8.486910689622164} +{"Pretrain/Learning Rate": 2.0208732777537072e-06, "Pretrain/Loss": 1.9851292371749878, "Pretrain/Loss (Raw)": 2.116562843322754, "Pretrain/Step": 8344, "Pretrain/Step Time": 8.486750250682235} +{"Pretrain/Learning Rate": 2.0175303137523943e-06, "Pretrain/Loss": 1.9865175485610962, "Pretrain/Loss (Raw)": 2.120460033416748, "Pretrain/Step": 8345, "Pretrain/Step Time": 8.482812333852053} +{"Pretrain/Learning Rate": 2.01419000077088e-06, "Pretrain/Loss": 1.9858992099761963, "Pretrain/Loss (Raw)": 1.9419829845428467, "Pretrain/Step": 8346, "Pretrain/Step Time": 8.484262637794018} +{"Pretrain/Learning Rate": 2.0108523391944717e-06, "Pretrain/Loss": 1.984619379043579, "Pretrain/Loss (Raw)": 2.0196735858917236, "Pretrain/Step": 8347, "Pretrain/Step Time": 8.483867907896638} +{"Pretrain/Learning Rate": 2.007517329408165e-06, "Pretrain/Loss": 1.9848405122756958, "Pretrain/Loss (Raw)": 1.9128010272979736, "Pretrain/Step": 8348, "Pretrain/Step Time": 8.481732830405235} +{"Pretrain/Learning Rate": 2.004184971796658e-06, "Pretrain/Loss": 1.9846758842468262, "Pretrain/Loss (Raw)": 2.0798423290252686, "Pretrain/Step": 8349, "Pretrain/Step Time": 8.481210080906749} +{"Pretrain/Learning Rate": 2.0008552667443335e-06, "Pretrain/Loss": 1.983203411102295, "Pretrain/Loss (Raw)": 1.978053092956543, "Pretrain/Step": 8350, "Pretrain/Step Time": 8.482282223179936} +{"Pretrain/Learning Rate": 1.997528214635269e-06, "Pretrain/Loss": 1.9854542016983032, "Pretrain/Loss (Raw)": 2.1503937244415283, "Pretrain/Step": 8351, "Pretrain/Step Time": 8.479176308959723} +{"Pretrain/Learning Rate": 1.9942038158532407e-06, "Pretrain/Loss": 1.9843189716339111, "Pretrain/Loss (Raw)": 2.02056884765625, "Pretrain/Step": 8352, "Pretrain/Step Time": 8.476358154788613} +{"Pretrain/Learning Rate": 1.990882070781719e-06, "Pretrain/Loss": 1.9852290153503418, "Pretrain/Loss (Raw)": 2.0873923301696777, "Pretrain/Step": 8353, "Pretrain/Step Time": 8.47860374674201} +{"Pretrain/Learning Rate": 1.9875629798038668e-06, "Pretrain/Loss": 1.9875214099884033, "Pretrain/Loss (Raw)": 2.1503756046295166, "Pretrain/Step": 8354, "Pretrain/Step Time": 8.478225644677877} +{"Pretrain/Learning Rate": 1.9842465433025343e-06, "Pretrain/Loss": 1.9880027770996094, "Pretrain/Loss (Raw)": 2.0935966968536377, "Pretrain/Step": 8355, "Pretrain/Step Time": 8.480878036469221} +{"Pretrain/Learning Rate": 1.9809327616602784e-06, "Pretrain/Loss": 1.9880220890045166, "Pretrain/Loss (Raw)": 1.8777589797973633, "Pretrain/Step": 8356, "Pretrain/Step Time": 8.480130661278963} +{"Pretrain/Learning Rate": 1.977621635259336e-06, "Pretrain/Loss": 1.988168716430664, "Pretrain/Loss (Raw)": 2.0782790184020996, "Pretrain/Step": 8357, "Pretrain/Step Time": 8.478919293731451} +{"Pretrain/Learning Rate": 1.9743131644816477e-06, "Pretrain/Loss": 1.9851953983306885, "Pretrain/Loss (Raw)": 1.8292070627212524, "Pretrain/Step": 8358, "Pretrain/Step Time": 8.479187021031976} +{"Pretrain/Learning Rate": 1.971007349708842e-06, "Pretrain/Loss": 1.9849737882614136, "Pretrain/Loss (Raw)": 2.1264536380767822, "Pretrain/Step": 8359, "Pretrain/Step Time": 8.480363432317972} +{"Pretrain/Learning Rate": 1.9677041913222476e-06, "Pretrain/Loss": 1.9846465587615967, "Pretrain/Loss (Raw)": 2.1078646183013916, "Pretrain/Step": 8360, "Pretrain/Step Time": 8.477540828287601} +{"Pretrain/Learning Rate": 1.964403689702882e-06, "Pretrain/Loss": 1.9884603023529053, "Pretrain/Loss (Raw)": 2.3342738151550293, "Pretrain/Step": 8361, "Pretrain/Step Time": 8.474443145096302} +{"Pretrain/Learning Rate": 1.9611058452314535e-06, "Pretrain/Loss": 1.9904038906097412, "Pretrain/Loss (Raw)": 2.1509010791778564, "Pretrain/Step": 8362, "Pretrain/Step Time": 8.473884848877788} +{"Pretrain/Learning Rate": 1.95781065828837e-06, "Pretrain/Loss": 1.9920411109924316, "Pretrain/Loss (Raw)": 2.048956871032715, "Pretrain/Step": 8363, "Pretrain/Step Time": 8.475401300936937} +{"Pretrain/Learning Rate": 1.9545181292537267e-06, "Pretrain/Loss": 1.9914606809616089, "Pretrain/Loss (Raw)": 1.853195309638977, "Pretrain/Step": 8364, "Pretrain/Step Time": 8.47477531246841} +{"Pretrain/Learning Rate": 1.9512282585073205e-06, "Pretrain/Loss": 1.9901459217071533, "Pretrain/Loss (Raw)": 1.8833779096603394, "Pretrain/Step": 8365, "Pretrain/Step Time": 8.474277511239052} +{"Pretrain/Learning Rate": 1.947941046428639e-06, "Pretrain/Loss": 1.987714171409607, "Pretrain/Loss (Raw)": 1.6956422328948975, "Pretrain/Step": 8366, "Pretrain/Step Time": 8.468965178355575} +{"Pretrain/Learning Rate": 1.9446564933968513e-06, "Pretrain/Loss": 1.9891177415847778, "Pretrain/Loss (Raw)": 2.1030404567718506, "Pretrain/Step": 8367, "Pretrain/Step Time": 8.467141030356288} +{"Pretrain/Learning Rate": 1.941374599790838e-06, "Pretrain/Loss": 1.99088454246521, "Pretrain/Loss (Raw)": 2.003007173538208, "Pretrain/Step": 8368, "Pretrain/Step Time": 8.467789413407445} +{"Pretrain/Learning Rate": 1.9380953659891563e-06, "Pretrain/Loss": 1.9901049137115479, "Pretrain/Loss (Raw)": 2.117628335952759, "Pretrain/Step": 8369, "Pretrain/Step Time": 8.464797612279654} +{"Pretrain/Learning Rate": 1.9348187923700772e-06, "Pretrain/Loss": 1.992527961730957, "Pretrain/Loss (Raw)": 2.1598317623138428, "Pretrain/Step": 8370, "Pretrain/Step Time": 8.463061792775989} +{"Pretrain/Learning Rate": 1.9315448793115395e-06, "Pretrain/Loss": 1.992026925086975, "Pretrain/Loss (Raw)": 2.0053858757019043, "Pretrain/Step": 8371, "Pretrain/Step Time": 8.45954555273056} +{"Pretrain/Learning Rate": 1.9282736271911935e-06, "Pretrain/Loss": 1.9921059608459473, "Pretrain/Loss (Raw)": 1.9807072877883911, "Pretrain/Step": 8372, "Pretrain/Step Time": 8.462336087599397} +{"Pretrain/Learning Rate": 1.925005036386382e-06, "Pretrain/Loss": 1.9911398887634277, "Pretrain/Loss (Raw)": 1.9347501993179321, "Pretrain/Step": 8373, "Pretrain/Step Time": 8.462004765868187} +{"Pretrain/Learning Rate": 1.921739107274123e-06, "Pretrain/Loss": 1.9926248788833618, "Pretrain/Loss (Raw)": 2.0802669525146484, "Pretrain/Step": 8374, "Pretrain/Step Time": 8.45949967391789} +{"Pretrain/Learning Rate": 1.9184758402311514e-06, "Pretrain/Loss": 1.9928290843963623, "Pretrain/Loss (Raw)": 2.0203733444213867, "Pretrain/Step": 8375, "Pretrain/Step Time": 8.457973849028349} +{"Pretrain/Learning Rate": 1.915215235633883e-06, "Pretrain/Loss": 1.9931399822235107, "Pretrain/Loss (Raw)": 2.0747318267822266, "Pretrain/Step": 8376, "Pretrain/Step Time": 8.455119395628572} +{"Pretrain/Learning Rate": 1.9119572938584184e-06, "Pretrain/Loss": 1.9942612648010254, "Pretrain/Loss (Raw)": 2.07289981842041, "Pretrain/Step": 8377, "Pretrain/Step Time": 8.456872161477804} +{"Pretrain/Learning Rate": 1.9087020152805698e-06, "Pretrain/Loss": 1.9969229698181152, "Pretrain/Loss (Raw)": 2.1630022525787354, "Pretrain/Step": 8378, "Pretrain/Step Time": 8.456251852214336} +{"Pretrain/Learning Rate": 1.9054494002758245e-06, "Pretrain/Loss": 1.9982472658157349, "Pretrain/Loss (Raw)": 2.1293282508850098, "Pretrain/Step": 8379, "Pretrain/Step Time": 8.454490330070257} +{"Pretrain/Learning Rate": 1.9021994492193773e-06, "Pretrain/Loss": 1.9982534646987915, "Pretrain/Loss (Raw)": 1.9387787580490112, "Pretrain/Step": 8380, "Pretrain/Step Time": 8.454762730747461} +{"Pretrain/Learning Rate": 1.8989521624861089e-06, "Pretrain/Loss": 1.998887062072754, "Pretrain/Loss (Raw)": 2.169430732727051, "Pretrain/Step": 8381, "Pretrain/Step Time": 8.454433662816882} +{"Pretrain/Learning Rate": 1.895707540450592e-06, "Pretrain/Loss": 1.9977068901062012, "Pretrain/Loss (Raw)": 1.8009003400802612, "Pretrain/Step": 8382, "Pretrain/Step Time": 8.454694161191583} +{"Pretrain/Learning Rate": 1.8924655834870853e-06, "Pretrain/Loss": 2.000620126724243, "Pretrain/Loss (Raw)": 2.2165822982788086, "Pretrain/Step": 8383, "Pretrain/Step Time": 8.453794812783599} +{"Pretrain/Learning Rate": 1.8892262919695563e-06, "Pretrain/Loss": 2.001893997192383, "Pretrain/Loss (Raw)": 2.0310773849487305, "Pretrain/Step": 8384, "Pretrain/Step Time": 8.452394254505634} +{"Pretrain/Learning Rate": 1.885989666271651e-06, "Pretrain/Loss": 2.001309871673584, "Pretrain/Loss (Raw)": 2.120262861251831, "Pretrain/Step": 8385, "Pretrain/Step Time": 8.45190628618002} +{"Pretrain/Learning Rate": 1.8827557067667146e-06, "Pretrain/Loss": 2.0014567375183105, "Pretrain/Loss (Raw)": 1.995314359664917, "Pretrain/Step": 8386, "Pretrain/Step Time": 8.450222454965115} +{"Pretrain/Learning Rate": 1.8795244138277878e-06, "Pretrain/Loss": 2.0022189617156982, "Pretrain/Loss (Raw)": 2.166325807571411, "Pretrain/Step": 8387, "Pretrain/Step Time": 8.448146501556039} +{"Pretrain/Learning Rate": 1.8762957878275893e-06, "Pretrain/Loss": 2.0018136501312256, "Pretrain/Loss (Raw)": 2.0352871417999268, "Pretrain/Step": 8388, "Pretrain/Step Time": 8.448436822742224} +{"Pretrain/Learning Rate": 1.8730698291385518e-06, "Pretrain/Loss": 2.0016021728515625, "Pretrain/Loss (Raw)": 2.0679104328155518, "Pretrain/Step": 8389, "Pretrain/Step Time": 8.448813928291202} +{"Pretrain/Learning Rate": 1.8698465381327774e-06, "Pretrain/Loss": 2.000035285949707, "Pretrain/Loss (Raw)": 1.8269108533859253, "Pretrain/Step": 8390, "Pretrain/Step Time": 8.444826953113079} +{"Pretrain/Learning Rate": 1.8666259151820769e-06, "Pretrain/Loss": 1.9974136352539062, "Pretrain/Loss (Raw)": 1.7921932935714722, "Pretrain/Step": 8391, "Pretrain/Step Time": 8.449009777978063} +{"Pretrain/Learning Rate": 1.8634079606579507e-06, "Pretrain/Loss": 1.9984087944030762, "Pretrain/Loss (Raw)": 2.09309720993042, "Pretrain/Step": 8392, "Pretrain/Step Time": 8.44668798521161} +{"Pretrain/Learning Rate": 1.8601926749315796e-06, "Pretrain/Loss": 1.9973448514938354, "Pretrain/Loss (Raw)": 1.9015705585479736, "Pretrain/Step": 8393, "Pretrain/Step Time": 8.444090874865651} +{"Pretrain/Learning Rate": 1.8569800583738556e-06, "Pretrain/Loss": 1.9947283267974854, "Pretrain/Loss (Raw)": 1.7741084098815918, "Pretrain/Step": 8394, "Pretrain/Step Time": 8.445135664194822} +{"Pretrain/Learning Rate": 1.8537701113553462e-06, "Pretrain/Loss": 1.9927948713302612, "Pretrain/Loss (Raw)": 1.7674299478530884, "Pretrain/Step": 8395, "Pretrain/Step Time": 8.44180921278894} +{"Pretrain/Learning Rate": 1.8505628342463193e-06, "Pretrain/Loss": 1.9926965236663818, "Pretrain/Loss (Raw)": 1.9199014902114868, "Pretrain/Step": 8396, "Pretrain/Step Time": 8.444813217967749} +{"Pretrain/Learning Rate": 1.84735822741674e-06, "Pretrain/Loss": 1.9934961795806885, "Pretrain/Loss (Raw)": 2.0566954612731934, "Pretrain/Step": 8397, "Pretrain/Step Time": 8.44313539005816} +{"Pretrain/Learning Rate": 1.8441562912362487e-06, "Pretrain/Loss": 1.994253396987915, "Pretrain/Loss (Raw)": 1.9938991069793701, "Pretrain/Step": 8398, "Pretrain/Step Time": 8.442196015268564} +{"Pretrain/Learning Rate": 1.8409570260741916e-06, "Pretrain/Loss": 1.9941109418869019, "Pretrain/Loss (Raw)": 1.8970838785171509, "Pretrain/Step": 8399, "Pretrain/Step Time": 8.441830705851316} +{"Pretrain/Learning Rate": 1.837760432299601e-06, "Pretrain/Loss": 1.994323968887329, "Pretrain/Loss (Raw)": 1.9858940839767456, "Pretrain/Step": 8400, "Pretrain/Step Time": 8.444378597661853} +{"Pretrain/Learning Rate": 1.8345665102812076e-06, "Pretrain/Loss": 1.99466872215271, "Pretrain/Loss (Raw)": 1.969556212425232, "Pretrain/Step": 8401, "Pretrain/Step Time": 8.445325456559658} +{"Pretrain/Learning Rate": 1.8313752603874246e-06, "Pretrain/Loss": 1.9948575496673584, "Pretrain/Loss (Raw)": 2.0112483501434326, "Pretrain/Step": 8402, "Pretrain/Step Time": 8.444078704342246} +{"Pretrain/Learning Rate": 1.8281866829863687e-06, "Pretrain/Loss": 1.995100498199463, "Pretrain/Loss (Raw)": 2.060238838195801, "Pretrain/Step": 8403, "Pretrain/Step Time": 8.443848231807351} +{"Pretrain/Learning Rate": 1.825000778445829e-06, "Pretrain/Loss": 1.9955182075500488, "Pretrain/Loss (Raw)": 1.891172170639038, "Pretrain/Step": 8404, "Pretrain/Step Time": 8.441543452441692} +{"Pretrain/Learning Rate": 1.8218175471333116e-06, "Pretrain/Loss": 1.9962550401687622, "Pretrain/Loss (Raw)": 2.024460554122925, "Pretrain/Step": 8405, "Pretrain/Step Time": 8.441466869786382} +{"Pretrain/Learning Rate": 1.8186369894159921e-06, "Pretrain/Loss": 1.9984604120254517, "Pretrain/Loss (Raw)": 2.2126293182373047, "Pretrain/Step": 8406, "Pretrain/Step Time": 8.445546690374613} +{"Pretrain/Learning Rate": 1.8154591056607467e-06, "Pretrain/Loss": 1.9995754957199097, "Pretrain/Loss (Raw)": 2.0741283893585205, "Pretrain/Step": 8407, "Pretrain/Step Time": 8.4438142683357} +{"Pretrain/Learning Rate": 1.8122838962341515e-06, "Pretrain/Loss": 1.9991509914398193, "Pretrain/Loss (Raw)": 2.0129756927490234, "Pretrain/Step": 8408, "Pretrain/Step Time": 8.44134484231472} +{"Pretrain/Learning Rate": 1.8091113615024553e-06, "Pretrain/Loss": 1.9989653825759888, "Pretrain/Loss (Raw)": 1.9302082061767578, "Pretrain/Step": 8409, "Pretrain/Step Time": 8.441063428297639} +{"Pretrain/Learning Rate": 1.8059415018316123e-06, "Pretrain/Loss": 1.9983277320861816, "Pretrain/Loss (Raw)": 2.093451976776123, "Pretrain/Step": 8410, "Pretrain/Step Time": 8.443212855607271} +{"Pretrain/Learning Rate": 1.8027743175872664e-06, "Pretrain/Loss": 1.9967330694198608, "Pretrain/Loss (Raw)": 1.7863380908966064, "Pretrain/Step": 8411, "Pretrain/Step Time": 8.442559411749244} +{"Pretrain/Learning Rate": 1.799609809134753e-06, "Pretrain/Loss": 1.9998136758804321, "Pretrain/Loss (Raw)": 2.0371434688568115, "Pretrain/Step": 8412, "Pretrain/Step Time": 8.443676315248013} +{"Pretrain/Learning Rate": 1.796447976839097e-06, "Pretrain/Loss": 1.999329686164856, "Pretrain/Loss (Raw)": 1.9286620616912842, "Pretrain/Step": 8413, "Pretrain/Step Time": 8.442089630290866} +{"Pretrain/Learning Rate": 1.7932888210650117e-06, "Pretrain/Loss": 2.000337839126587, "Pretrain/Loss (Raw)": 1.8905489444732666, "Pretrain/Step": 8414, "Pretrain/Step Time": 8.442859914153814} +{"Pretrain/Learning Rate": 1.7901323421769035e-06, "Pretrain/Loss": 1.9965482950210571, "Pretrain/Loss (Raw)": 1.6295313835144043, "Pretrain/Step": 8415, "Pretrain/Step Time": 8.439299434423447} +{"Pretrain/Learning Rate": 1.7869785405388723e-06, "Pretrain/Loss": 1.9958006143569946, "Pretrain/Loss (Raw)": 1.9463231563568115, "Pretrain/Step": 8416, "Pretrain/Step Time": 8.44081736728549} +{"Pretrain/Learning Rate": 1.783827416514708e-06, "Pretrain/Loss": 1.9967644214630127, "Pretrain/Loss (Raw)": 2.030139446258545, "Pretrain/Step": 8417, "Pretrain/Step Time": 8.438268549740314} +{"Pretrain/Learning Rate": 1.7806789704678973e-06, "Pretrain/Loss": 1.9960087537765503, "Pretrain/Loss (Raw)": 1.9563418626785278, "Pretrain/Step": 8418, "Pretrain/Step Time": 8.437151931226254} +{"Pretrain/Learning Rate": 1.7775332027616053e-06, "Pretrain/Loss": 1.9941182136535645, "Pretrain/Loss (Raw)": 1.8421578407287598, "Pretrain/Step": 8419, "Pretrain/Step Time": 8.436770252883434} +{"Pretrain/Learning Rate": 1.774390113758695e-06, "Pretrain/Loss": 1.993409514427185, "Pretrain/Loss (Raw)": 1.8560945987701416, "Pretrain/Step": 8420, "Pretrain/Step Time": 8.433636218309402} +{"Pretrain/Learning Rate": 1.7712497038217258e-06, "Pretrain/Loss": 1.993648886680603, "Pretrain/Loss (Raw)": 2.1070175170898438, "Pretrain/Step": 8421, "Pretrain/Step Time": 8.430631048977375} +{"Pretrain/Learning Rate": 1.7681119733129414e-06, "Pretrain/Loss": 1.9913195371627808, "Pretrain/Loss (Raw)": 1.6676945686340332, "Pretrain/Step": 8422, "Pretrain/Step Time": 8.432857532054186} +{"Pretrain/Learning Rate": 1.7649769225942747e-06, "Pretrain/Loss": 1.98870849609375, "Pretrain/Loss (Raw)": 1.7086156606674194, "Pretrain/Step": 8423, "Pretrain/Step Time": 8.434763660654426} +{"Pretrain/Learning Rate": 1.7618445520273558e-06, "Pretrain/Loss": 1.9895954132080078, "Pretrain/Loss (Raw)": 2.0204288959503174, "Pretrain/Step": 8424, "Pretrain/Step Time": 8.434137338772416} +{"Pretrain/Learning Rate": 1.7587148619735011e-06, "Pretrain/Loss": 1.9884130954742432, "Pretrain/Loss (Raw)": 1.8967748880386353, "Pretrain/Step": 8425, "Pretrain/Step Time": 8.43543835543096} +{"Pretrain/Learning Rate": 1.7555878527937164e-06, "Pretrain/Loss": 1.9875617027282715, "Pretrain/Loss (Raw)": 1.917523741722107, "Pretrain/Step": 8426, "Pretrain/Step Time": 8.435200406238437} +{"Pretrain/Learning Rate": 1.7524635248487048e-06, "Pretrain/Loss": 1.9877216815948486, "Pretrain/Loss (Raw)": 1.8761539459228516, "Pretrain/Step": 8427, "Pretrain/Step Time": 8.437175368890166} +{"Pretrain/Learning Rate": 1.7493418784988586e-06, "Pretrain/Loss": 1.989495038986206, "Pretrain/Loss (Raw)": 2.0947201251983643, "Pretrain/Step": 8428, "Pretrain/Step Time": 8.437142165377736} +{"Pretrain/Learning Rate": 1.7462229141042562e-06, "Pretrain/Loss": 1.9883811473846436, "Pretrain/Loss (Raw)": 1.8863379955291748, "Pretrain/Step": 8429, "Pretrain/Step Time": 8.440006444230676} +{"Pretrain/Learning Rate": 1.7431066320246658e-06, "Pretrain/Loss": 1.9886784553527832, "Pretrain/Loss (Raw)": 2.1003010272979736, "Pretrain/Step": 8430, "Pretrain/Step Time": 8.442099081352353} +{"Pretrain/Learning Rate": 1.7399930326195523e-06, "Pretrain/Loss": 1.991743803024292, "Pretrain/Loss (Raw)": 2.111537218093872, "Pretrain/Step": 8431, "Pretrain/Step Time": 8.442922577261925} +{"Pretrain/Learning Rate": 1.7368821162480703e-06, "Pretrain/Loss": 1.9918889999389648, "Pretrain/Loss (Raw)": 2.020986318588257, "Pretrain/Step": 8432, "Pretrain/Step Time": 8.441756252199411} +{"Pretrain/Learning Rate": 1.7337738832690603e-06, "Pretrain/Loss": 1.9939132928848267, "Pretrain/Loss (Raw)": 2.179641008377075, "Pretrain/Step": 8433, "Pretrain/Step Time": 8.442176641896367} +{"Pretrain/Learning Rate": 1.730668334041058e-06, "Pretrain/Loss": 1.992478370666504, "Pretrain/Loss (Raw)": 1.957274317741394, "Pretrain/Step": 8434, "Pretrain/Step Time": 8.439725814387202} +{"Pretrain/Learning Rate": 1.7275654689222847e-06, "Pretrain/Loss": 1.992231845855713, "Pretrain/Loss (Raw)": 2.1703338623046875, "Pretrain/Step": 8435, "Pretrain/Step Time": 8.442441588267684} +{"Pretrain/Learning Rate": 1.7244652882706546e-06, "Pretrain/Loss": 1.9924484491348267, "Pretrain/Loss (Raw)": 2.0914244651794434, "Pretrain/Step": 8436, "Pretrain/Step Time": 8.440268164500594} +{"Pretrain/Learning Rate": 1.7213677924437733e-06, "Pretrain/Loss": 1.9940561056137085, "Pretrain/Loss (Raw)": 2.0873539447784424, "Pretrain/Step": 8437, "Pretrain/Step Time": 8.43964833766222} +{"Pretrain/Learning Rate": 1.7182729817989436e-06, "Pretrain/Loss": 1.9949259757995605, "Pretrain/Loss (Raw)": 2.0339725017547607, "Pretrain/Step": 8438, "Pretrain/Step Time": 8.438448175787926} +{"Pretrain/Learning Rate": 1.7151808566931354e-06, "Pretrain/Loss": 1.9949606657028198, "Pretrain/Loss (Raw)": 2.046743154525757, "Pretrain/Step": 8439, "Pretrain/Step Time": 8.444577557966113} +{"Pretrain/Learning Rate": 1.7120914174830387e-06, "Pretrain/Loss": 1.9943960905075073, "Pretrain/Loss (Raw)": 2.1107351779937744, "Pretrain/Step": 8440, "Pretrain/Step Time": 8.443742809817195} +{"Pretrain/Learning Rate": 1.7090046645250101e-06, "Pretrain/Loss": 1.9948784112930298, "Pretrain/Loss (Raw)": 2.032824993133545, "Pretrain/Step": 8441, "Pretrain/Step Time": 8.447365270927548} +{"Pretrain/Learning Rate": 1.7059205981751065e-06, "Pretrain/Loss": 1.9944597482681274, "Pretrain/Loss (Raw)": 1.9622784852981567, "Pretrain/Step": 8442, "Pretrain/Step Time": 8.446828346699476} +{"Pretrain/Learning Rate": 1.7028392187890762e-06, "Pretrain/Loss": 1.991575002670288, "Pretrain/Loss (Raw)": 1.6893551349639893, "Pretrain/Step": 8443, "Pretrain/Step Time": 8.447989039123058} +{"Pretrain/Learning Rate": 1.699760526722355e-06, "Pretrain/Loss": 1.9906399250030518, "Pretrain/Loss (Raw)": 1.8415966033935547, "Pretrain/Step": 8444, "Pretrain/Step Time": 8.447360523045063} +{"Pretrain/Learning Rate": 1.6966845223300747e-06, "Pretrain/Loss": 1.9906527996063232, "Pretrain/Loss (Raw)": 1.980913519859314, "Pretrain/Step": 8445, "Pretrain/Step Time": 8.45285694859922} +{"Pretrain/Learning Rate": 1.6936112059670383e-06, "Pretrain/Loss": 1.989585041999817, "Pretrain/Loss (Raw)": 1.702929973602295, "Pretrain/Step": 8446, "Pretrain/Step Time": 8.45160567201674} +{"Pretrain/Learning Rate": 1.690540577987762e-06, "Pretrain/Loss": 1.9889522790908813, "Pretrain/Loss (Raw)": 1.978497862815857, "Pretrain/Step": 8447, "Pretrain/Step Time": 8.44952093809843} +{"Pretrain/Learning Rate": 1.6874726387464347e-06, "Pretrain/Loss": 1.990500569343567, "Pretrain/Loss (Raw)": 2.1876633167266846, "Pretrain/Step": 8448, "Pretrain/Step Time": 8.450553739443421} +{"Pretrain/Learning Rate": 1.684407388596948e-06, "Pretrain/Loss": 1.9898689985275269, "Pretrain/Loss (Raw)": 1.931580662727356, "Pretrain/Step": 8449, "Pretrain/Step Time": 8.450414143502712} +{"Pretrain/Learning Rate": 1.6813448278928807e-06, "Pretrain/Loss": 1.9892621040344238, "Pretrain/Loss (Raw)": 1.943237066268921, "Pretrain/Step": 8450, "Pretrain/Step Time": 8.453186614438891} +{"Pretrain/Learning Rate": 1.678284956987486e-06, "Pretrain/Loss": 1.9906584024429321, "Pretrain/Loss (Raw)": 2.1787476539611816, "Pretrain/Step": 8451, "Pretrain/Step Time": 8.457061836495996} +{"Pretrain/Learning Rate": 1.6752277762337288e-06, "Pretrain/Loss": 1.989804983139038, "Pretrain/Loss (Raw)": 1.9461302757263184, "Pretrain/Step": 8452, "Pretrain/Step Time": 8.458501497283578} +{"Pretrain/Learning Rate": 1.6721732859842466e-06, "Pretrain/Loss": 1.991302728652954, "Pretrain/Loss (Raw)": 1.958907127380371, "Pretrain/Step": 8453, "Pretrain/Step Time": 8.452412027865648} +{"Pretrain/Learning Rate": 1.6691214865913851e-06, "Pretrain/Loss": 1.9921016693115234, "Pretrain/Loss (Raw)": 2.022486448287964, "Pretrain/Step": 8454, "Pretrain/Step Time": 8.454611668363214} +{"Pretrain/Learning Rate": 1.6660723784071575e-06, "Pretrain/Loss": 1.992910623550415, "Pretrain/Loss (Raw)": 2.0186734199523926, "Pretrain/Step": 8455, "Pretrain/Step Time": 8.454220363870263} +{"Pretrain/Learning Rate": 1.6630259617832794e-06, "Pretrain/Loss": 1.9944742918014526, "Pretrain/Loss (Raw)": 2.081064462661743, "Pretrain/Step": 8456, "Pretrain/Step Time": 8.452291149646044} +{"Pretrain/Learning Rate": 1.6599822370711586e-06, "Pretrain/Loss": 1.9943180084228516, "Pretrain/Loss (Raw)": 1.919274926185608, "Pretrain/Step": 8457, "Pretrain/Step Time": 8.455655947327614} +{"Pretrain/Learning Rate": 1.6569412046218814e-06, "Pretrain/Loss": 1.9965442419052124, "Pretrain/Loss (Raw)": 2.0250089168548584, "Pretrain/Step": 8458, "Pretrain/Step Time": 8.45629782602191} +{"Pretrain/Learning Rate": 1.653902864786233e-06, "Pretrain/Loss": 1.9962527751922607, "Pretrain/Loss (Raw)": 2.0069901943206787, "Pretrain/Step": 8459, "Pretrain/Step Time": 8.45455332659185} +{"Pretrain/Learning Rate": 1.6508672179146894e-06, "Pretrain/Loss": 1.9948859214782715, "Pretrain/Loss (Raw)": 1.879321575164795, "Pretrain/Step": 8460, "Pretrain/Step Time": 8.45525243319571} +{"Pretrain/Learning Rate": 1.6478342643574008e-06, "Pretrain/Loss": 1.9944239854812622, "Pretrain/Loss (Raw)": 2.0455846786499023, "Pretrain/Step": 8461, "Pretrain/Step Time": 8.458249187096953} +{"Pretrain/Learning Rate": 1.644804004464226e-06, "Pretrain/Loss": 1.993545651435852, "Pretrain/Loss (Raw)": 2.107057571411133, "Pretrain/Step": 8462, "Pretrain/Step Time": 8.456383368000388} +{"Pretrain/Learning Rate": 1.6417764385846996e-06, "Pretrain/Loss": 1.994262456893921, "Pretrain/Loss (Raw)": 2.1262874603271484, "Pretrain/Step": 8463, "Pretrain/Step Time": 8.459379311650991} +{"Pretrain/Learning Rate": 1.638751567068053e-06, "Pretrain/Loss": 1.9928886890411377, "Pretrain/Loss (Raw)": 1.9112576246261597, "Pretrain/Step": 8464, "Pretrain/Step Time": 8.460332104936242} +{"Pretrain/Learning Rate": 1.6357293902632049e-06, "Pretrain/Loss": 1.993356704711914, "Pretrain/Loss (Raw)": 1.9523380994796753, "Pretrain/Step": 8465, "Pretrain/Step Time": 8.458619436249137} +{"Pretrain/Learning Rate": 1.632709908518762e-06, "Pretrain/Loss": 1.9936137199401855, "Pretrain/Loss (Raw)": 2.1324048042297363, "Pretrain/Step": 8466, "Pretrain/Step Time": 8.461201390251517} +{"Pretrain/Learning Rate": 1.629693122183018e-06, "Pretrain/Loss": 1.9942556619644165, "Pretrain/Loss (Raw)": 1.950656771659851, "Pretrain/Step": 8467, "Pretrain/Step Time": 8.461655024439096} +{"Pretrain/Learning Rate": 1.626679031603956e-06, "Pretrain/Loss": 1.994776725769043, "Pretrain/Loss (Raw)": 2.021674156188965, "Pretrain/Step": 8468, "Pretrain/Step Time": 8.456559803336859} +{"Pretrain/Learning Rate": 1.6236676371292558e-06, "Pretrain/Loss": 1.9967297315597534, "Pretrain/Loss (Raw)": 2.081754446029663, "Pretrain/Step": 8469, "Pretrain/Step Time": 8.460309822112322} +{"Pretrain/Learning Rate": 1.6206589391062787e-06, "Pretrain/Loss": 2.0002689361572266, "Pretrain/Loss (Raw)": 2.122584581375122, "Pretrain/Step": 8470, "Pretrain/Step Time": 8.458194237202406} +{"Pretrain/Learning Rate": 1.6176529378820832e-06, "Pretrain/Loss": 2.0013389587402344, "Pretrain/Loss (Raw)": 2.110164165496826, "Pretrain/Step": 8471, "Pretrain/Step Time": 8.458214892074466} +{"Pretrain/Learning Rate": 1.6146496338033973e-06, "Pretrain/Loss": 1.998092770576477, "Pretrain/Loss (Raw)": 1.7010506391525269, "Pretrain/Step": 8472, "Pretrain/Step Time": 8.461483554914594} +{"Pretrain/Learning Rate": 1.6116490272166607e-06, "Pretrain/Loss": 1.9981086254119873, "Pretrain/Loss (Raw)": 2.1224796772003174, "Pretrain/Step": 8473, "Pretrain/Step Time": 8.462989689782262} +{"Pretrain/Learning Rate": 1.6086511184679881e-06, "Pretrain/Loss": 1.997127890586853, "Pretrain/Loss (Raw)": 1.8164528608322144, "Pretrain/Step": 8474, "Pretrain/Step Time": 8.462519522756338} +{"Pretrain/Learning Rate": 1.605655907903189e-06, "Pretrain/Loss": 1.995771884918213, "Pretrain/Loss (Raw)": 1.8461017608642578, "Pretrain/Step": 8475, "Pretrain/Step Time": 8.464018100872636} +{"Pretrain/Learning Rate": 1.6026633958677622e-06, "Pretrain/Loss": 1.9954643249511719, "Pretrain/Loss (Raw)": 1.873426079750061, "Pretrain/Step": 8476, "Pretrain/Step Time": 8.46511179767549} +{"Pretrain/Learning Rate": 1.5996735827068871e-06, "Pretrain/Loss": 1.9945684671401978, "Pretrain/Loss (Raw)": 1.9651784896850586, "Pretrain/Step": 8477, "Pretrain/Step Time": 8.464529292657971} +{"Pretrain/Learning Rate": 1.5966864687654403e-06, "Pretrain/Loss": 1.993033766746521, "Pretrain/Loss (Raw)": 1.7816267013549805, "Pretrain/Step": 8478, "Pretrain/Step Time": 8.467022716999054} +{"Pretrain/Learning Rate": 1.5937020543879855e-06, "Pretrain/Loss": 1.989736795425415, "Pretrain/Loss (Raw)": 1.7283567190170288, "Pretrain/Step": 8479, "Pretrain/Step Time": 8.464919596910477} +{"Pretrain/Learning Rate": 1.590720339918772e-06, "Pretrain/Loss": 1.9879865646362305, "Pretrain/Loss (Raw)": 1.7965402603149414, "Pretrain/Step": 8480, "Pretrain/Step Time": 8.467772386968136} +{"Pretrain/Learning Rate": 1.5877413257017415e-06, "Pretrain/Loss": 1.9871242046356201, "Pretrain/Loss (Raw)": 1.977016568183899, "Pretrain/Step": 8481, "Pretrain/Step Time": 8.466918421909213} +{"Pretrain/Learning Rate": 1.5847650120805247e-06, "Pretrain/Loss": 1.9866743087768555, "Pretrain/Loss (Raw)": 2.0927822589874268, "Pretrain/Step": 8482, "Pretrain/Step Time": 8.468827893957496} +{"Pretrain/Learning Rate": 1.5817913993984302e-06, "Pretrain/Loss": 1.9875702857971191, "Pretrain/Loss (Raw)": 2.208306312561035, "Pretrain/Step": 8483, "Pretrain/Step Time": 8.467740567401052} +{"Pretrain/Learning Rate": 1.5788204879984696e-06, "Pretrain/Loss": 1.9869749546051025, "Pretrain/Loss (Raw)": 1.801535725593567, "Pretrain/Step": 8484, "Pretrain/Step Time": 8.465178281068802} +{"Pretrain/Learning Rate": 1.5758522782233358e-06, "Pretrain/Loss": 1.984323263168335, "Pretrain/Loss (Raw)": 1.7388818264007568, "Pretrain/Step": 8485, "Pretrain/Step Time": 8.46489853411913} +{"Pretrain/Learning Rate": 1.5728867704154077e-06, "Pretrain/Loss": 1.9859976768493652, "Pretrain/Loss (Raw)": 2.0435214042663574, "Pretrain/Step": 8486, "Pretrain/Step Time": 8.461948733776808} +{"Pretrain/Learning Rate": 1.569923964916764e-06, "Pretrain/Loss": 1.9852300882339478, "Pretrain/Loss (Raw)": 2.0282089710235596, "Pretrain/Step": 8487, "Pretrain/Step Time": 8.463428949937224} +{"Pretrain/Learning Rate": 1.5669638620691513e-06, "Pretrain/Loss": 1.984798789024353, "Pretrain/Loss (Raw)": 2.052647113800049, "Pretrain/Step": 8488, "Pretrain/Step Time": 8.465801576152444} +{"Pretrain/Learning Rate": 1.5640064622140265e-06, "Pretrain/Loss": 1.9798307418823242, "Pretrain/Loss (Raw)": 1.6983696222305298, "Pretrain/Step": 8489, "Pretrain/Step Time": 8.465140461921692} +{"Pretrain/Learning Rate": 1.5610517656925172e-06, "Pretrain/Loss": 1.9778721332550049, "Pretrain/Loss (Raw)": 1.9001846313476562, "Pretrain/Step": 8490, "Pretrain/Step Time": 8.467409163713455} +{"Pretrain/Learning Rate": 1.5580997728454477e-06, "Pretrain/Loss": 1.978026032447815, "Pretrain/Loss (Raw)": 2.068669080734253, "Pretrain/Step": 8491, "Pretrain/Step Time": 8.46576433815062} +{"Pretrain/Learning Rate": 1.5551504840133375e-06, "Pretrain/Loss": 1.9784733057022095, "Pretrain/Loss (Raw)": 1.9104384183883667, "Pretrain/Step": 8492, "Pretrain/Step Time": 8.467079475522041} +{"Pretrain/Learning Rate": 1.5522038995363751e-06, "Pretrain/Loss": 1.9786877632141113, "Pretrain/Loss (Raw)": 1.9108408689498901, "Pretrain/Step": 8493, "Pretrain/Step Time": 8.466483468189836} +{"Pretrain/Learning Rate": 1.5492600197544532e-06, "Pretrain/Loss": 1.9808094501495361, "Pretrain/Loss (Raw)": 1.967209815979004, "Pretrain/Step": 8494, "Pretrain/Step Time": 8.468306194990873} +{"Pretrain/Learning Rate": 1.546318845007147e-06, "Pretrain/Loss": 1.9803909063339233, "Pretrain/Loss (Raw)": 2.0494706630706787, "Pretrain/Step": 8495, "Pretrain/Step Time": 8.469547297805548} +{"Pretrain/Learning Rate": 1.5433803756337185e-06, "Pretrain/Loss": 1.9793598651885986, "Pretrain/Loss (Raw)": 1.871039628982544, "Pretrain/Step": 8496, "Pretrain/Step Time": 8.468505239114165} +{"Pretrain/Learning Rate": 1.5404446119731242e-06, "Pretrain/Loss": 1.9785964488983154, "Pretrain/Loss (Raw)": 2.019914388656616, "Pretrain/Step": 8497, "Pretrain/Step Time": 8.46917101368308} +{"Pretrain/Learning Rate": 1.5375115543639962e-06, "Pretrain/Loss": 1.9773006439208984, "Pretrain/Loss (Raw)": 1.993962049484253, "Pretrain/Step": 8498, "Pretrain/Step Time": 8.470108561217785} +{"Pretrain/Learning Rate": 1.5345812031446667e-06, "Pretrain/Loss": 1.9778461456298828, "Pretrain/Loss (Raw)": 2.0752017498016357, "Pretrain/Step": 8499, "Pretrain/Step Time": 8.473026094958186} +{"Pretrain/Learning Rate": 1.5316535586531483e-06, "Pretrain/Loss": 1.9785282611846924, "Pretrain/Loss (Raw)": 2.0680301189422607, "Pretrain/Step": 8500, "Pretrain/Step Time": 8.471538349986076} +{"Pretrain/Learning Rate": 1.5287286212271434e-06, "Pretrain/Loss": 1.9793353080749512, "Pretrain/Loss (Raw)": 2.0380594730377197, "Pretrain/Step": 8501, "Pretrain/Step Time": 8.472751196473837} +{"Pretrain/Learning Rate": 1.525806391204046e-06, "Pretrain/Loss": 1.9800280332565308, "Pretrain/Loss (Raw)": 2.168921947479248, "Pretrain/Step": 8502, "Pretrain/Step Time": 8.47485944069922} +{"Pretrain/Learning Rate": 1.5228868689209335e-06, "Pretrain/Loss": 1.979489803314209, "Pretrain/Loss (Raw)": 1.951475739479065, "Pretrain/Step": 8503, "Pretrain/Step Time": 8.476778911426663} +{"Pretrain/Learning Rate": 1.5199700547145674e-06, "Pretrain/Loss": 1.9783821105957031, "Pretrain/Loss (Raw)": 1.9329475164413452, "Pretrain/Step": 8504, "Pretrain/Step Time": 8.474216114729643} +{"Pretrain/Learning Rate": 1.5170559489214032e-06, "Pretrain/Loss": 1.9788333177566528, "Pretrain/Loss (Raw)": 2.130674362182617, "Pretrain/Step": 8505, "Pretrain/Step Time": 8.475003931671381} +{"Pretrain/Learning Rate": 1.514144551877586e-06, "Pretrain/Loss": 1.9777705669403076, "Pretrain/Loss (Raw)": 2.026947259902954, "Pretrain/Step": 8506, "Pretrain/Step Time": 8.476308850571513} +{"Pretrain/Learning Rate": 1.5112358639189388e-06, "Pretrain/Loss": 1.974916696548462, "Pretrain/Loss (Raw)": 1.7640464305877686, "Pretrain/Step": 8507, "Pretrain/Step Time": 8.474115703254938} +{"Pretrain/Learning Rate": 1.5083298853809852e-06, "Pretrain/Loss": 1.9746084213256836, "Pretrain/Loss (Raw)": 1.8993085622787476, "Pretrain/Step": 8508, "Pretrain/Step Time": 8.477490780875087} +{"Pretrain/Learning Rate": 1.5054266165989177e-06, "Pretrain/Loss": 1.9730162620544434, "Pretrain/Loss (Raw)": 1.9656420946121216, "Pretrain/Step": 8509, "Pretrain/Step Time": 8.479414157569408} +{"Pretrain/Learning Rate": 1.5025260579076328e-06, "Pretrain/Loss": 1.9750237464904785, "Pretrain/Loss (Raw)": 2.057849645614624, "Pretrain/Step": 8510, "Pretrain/Step Time": 8.478692043572664} +{"Pretrain/Learning Rate": 1.4996282096417125e-06, "Pretrain/Loss": 1.973555564880371, "Pretrain/Loss (Raw)": 2.0286545753479004, "Pretrain/Step": 8511, "Pretrain/Step Time": 8.476053858175874} +{"Pretrain/Learning Rate": 1.4967330721354172e-06, "Pretrain/Loss": 1.9735727310180664, "Pretrain/Loss (Raw)": 2.0332818031311035, "Pretrain/Step": 8512, "Pretrain/Step Time": 8.475772205740213} +{"Pretrain/Learning Rate": 1.4938406457227077e-06, "Pretrain/Loss": 1.9722790718078613, "Pretrain/Loss (Raw)": 1.954674243927002, "Pretrain/Step": 8513, "Pretrain/Step Time": 8.473169032484293} +{"Pretrain/Learning Rate": 1.4909509307372144e-06, "Pretrain/Loss": 1.9691431522369385, "Pretrain/Loss (Raw)": 1.593912124633789, "Pretrain/Step": 8514, "Pretrain/Step Time": 8.479289347305894} +{"Pretrain/Learning Rate": 1.4880639275122704e-06, "Pretrain/Loss": 1.9679288864135742, "Pretrain/Loss (Raw)": 2.0109148025512695, "Pretrain/Step": 8515, "Pretrain/Step Time": 8.479482205584645} +{"Pretrain/Learning Rate": 1.4851796363808872e-06, "Pretrain/Loss": 1.9671871662139893, "Pretrain/Loss (Raw)": 1.9403471946716309, "Pretrain/Step": 8516, "Pretrain/Step Time": 8.476537683978677} +{"Pretrain/Learning Rate": 1.4822980576757712e-06, "Pretrain/Loss": 1.9666810035705566, "Pretrain/Loss (Raw)": 2.0031192302703857, "Pretrain/Step": 8517, "Pretrain/Step Time": 8.476187968626618} +{"Pretrain/Learning Rate": 1.4794191917293142e-06, "Pretrain/Loss": 1.9668269157409668, "Pretrain/Loss (Raw)": 1.8455897569656372, "Pretrain/Step": 8518, "Pretrain/Step Time": 8.479784868657589} +{"Pretrain/Learning Rate": 1.4765430388735817e-06, "Pretrain/Loss": 1.968611240386963, "Pretrain/Loss (Raw)": 2.0205681324005127, "Pretrain/Step": 8519, "Pretrain/Step Time": 8.475534861907363} +{"Pretrain/Learning Rate": 1.4736695994403444e-06, "Pretrain/Loss": 1.966256856918335, "Pretrain/Loss (Raw)": 1.7917510271072388, "Pretrain/Step": 8520, "Pretrain/Step Time": 8.476959101855755} +{"Pretrain/Learning Rate": 1.4707988737610506e-06, "Pretrain/Loss": 1.9677143096923828, "Pretrain/Loss (Raw)": 2.088137626647949, "Pretrain/Step": 8521, "Pretrain/Step Time": 8.476809231564403} +{"Pretrain/Learning Rate": 1.4679308621668442e-06, "Pretrain/Loss": 1.9704570770263672, "Pretrain/Loss (Raw)": 2.125164747238159, "Pretrain/Step": 8522, "Pretrain/Step Time": 8.479694487527013} +{"Pretrain/Learning Rate": 1.4650655649885353e-06, "Pretrain/Loss": 1.9733498096466064, "Pretrain/Loss (Raw)": 2.137699842453003, "Pretrain/Step": 8523, "Pretrain/Step Time": 8.48001397587359} +{"Pretrain/Learning Rate": 1.4622029825566486e-06, "Pretrain/Loss": 1.9741520881652832, "Pretrain/Loss (Raw)": 2.0225915908813477, "Pretrain/Step": 8524, "Pretrain/Step Time": 8.477898122742772} +{"Pretrain/Learning Rate": 1.4593431152013725e-06, "Pretrain/Loss": 1.9742125272750854, "Pretrain/Loss (Raw)": 2.0644278526306152, "Pretrain/Step": 8525, "Pretrain/Step Time": 8.48294928483665} +{"Pretrain/Learning Rate": 1.4564859632525962e-06, "Pretrain/Loss": 1.9730963706970215, "Pretrain/Loss (Raw)": 1.8510432243347168, "Pretrain/Step": 8526, "Pretrain/Step Time": 8.481925778090954} +{"Pretrain/Learning Rate": 1.4536315270398864e-06, "Pretrain/Loss": 1.9727895259857178, "Pretrain/Loss (Raw)": 1.8577971458435059, "Pretrain/Step": 8527, "Pretrain/Step Time": 8.481490645557642} +{"Pretrain/Learning Rate": 1.4507798068925078e-06, "Pretrain/Loss": 1.9727797508239746, "Pretrain/Loss (Raw)": 1.9846367835998535, "Pretrain/Step": 8528, "Pretrain/Step Time": 8.479033160954714} +{"Pretrain/Learning Rate": 1.4479308031394078e-06, "Pretrain/Loss": 1.9721949100494385, "Pretrain/Loss (Raw)": 1.8947169780731201, "Pretrain/Step": 8529, "Pretrain/Step Time": 8.477315293624997} +{"Pretrain/Learning Rate": 1.4450845161092074e-06, "Pretrain/Loss": 1.9722013473510742, "Pretrain/Loss (Raw)": 2.01206111907959, "Pretrain/Step": 8530, "Pretrain/Step Time": 8.483073372393847} +{"Pretrain/Learning Rate": 1.44224094613023e-06, "Pretrain/Loss": 1.9710712432861328, "Pretrain/Loss (Raw)": 1.9156049489974976, "Pretrain/Step": 8531, "Pretrain/Step Time": 8.482597203925252} +{"Pretrain/Learning Rate": 1.4394000935304825e-06, "Pretrain/Loss": 1.971388816833496, "Pretrain/Loss (Raw)": 1.9318106174468994, "Pretrain/Step": 8532, "Pretrain/Step Time": 8.480442492291331} +{"Pretrain/Learning Rate": 1.4365619586376528e-06, "Pretrain/Loss": 1.9718903303146362, "Pretrain/Loss (Raw)": 2.0886480808258057, "Pretrain/Step": 8533, "Pretrain/Step Time": 8.482007641345263} +{"Pretrain/Learning Rate": 1.4337265417791235e-06, "Pretrain/Loss": 1.9705710411071777, "Pretrain/Loss (Raw)": 2.0437560081481934, "Pretrain/Step": 8534, "Pretrain/Step Time": 8.478224297985435} +{"Pretrain/Learning Rate": 1.4308938432819524e-06, "Pretrain/Loss": 1.970259189605713, "Pretrain/Loss (Raw)": 2.034226894378662, "Pretrain/Step": 8535, "Pretrain/Step Time": 8.47948713414371} +{"Pretrain/Learning Rate": 1.428063863472895e-06, "Pretrain/Loss": 1.9702800512313843, "Pretrain/Loss (Raw)": 2.0156302452087402, "Pretrain/Step": 8536, "Pretrain/Step Time": 8.48274103552103} +{"Pretrain/Learning Rate": 1.425236602678387e-06, "Pretrain/Loss": 1.9721239805221558, "Pretrain/Loss (Raw)": 2.16623854637146, "Pretrain/Step": 8537, "Pretrain/Step Time": 8.484721265733242} +{"Pretrain/Learning Rate": 1.4224120612245566e-06, "Pretrain/Loss": 1.9676836729049683, "Pretrain/Loss (Raw)": 1.5250842571258545, "Pretrain/Step": 8538, "Pretrain/Step Time": 8.485338306054473} +{"Pretrain/Learning Rate": 1.4195902394372045e-06, "Pretrain/Loss": 1.9685266017913818, "Pretrain/Loss (Raw)": 1.894244909286499, "Pretrain/Step": 8539, "Pretrain/Step Time": 8.48585281521082} +{"Pretrain/Learning Rate": 1.4167711376418313e-06, "Pretrain/Loss": 1.969618320465088, "Pretrain/Loss (Raw)": 2.176879405975342, "Pretrain/Step": 8540, "Pretrain/Step Time": 8.48521177843213} +{"Pretrain/Learning Rate": 1.4139547561636213e-06, "Pretrain/Loss": 1.9706311225891113, "Pretrain/Loss (Raw)": 2.0582940578460693, "Pretrain/Step": 8541, "Pretrain/Step Time": 8.484352195635438} +{"Pretrain/Learning Rate": 1.4111410953274424e-06, "Pretrain/Loss": 1.9705262184143066, "Pretrain/Loss (Raw)": 1.8771207332611084, "Pretrain/Step": 8542, "Pretrain/Step Time": 8.489088997244835} +{"Pretrain/Learning Rate": 1.4083301554578433e-06, "Pretrain/Loss": 1.9742028713226318, "Pretrain/Loss (Raw)": 2.100135326385498, "Pretrain/Step": 8543, "Pretrain/Step Time": 8.489296784624457} +{"Pretrain/Learning Rate": 1.405521936879073e-06, "Pretrain/Loss": 1.9743459224700928, "Pretrain/Loss (Raw)": 1.9646469354629517, "Pretrain/Step": 8544, "Pretrain/Step Time": 8.488346837460995} +{"Pretrain/Learning Rate": 1.402716439915061e-06, "Pretrain/Loss": 1.9749523401260376, "Pretrain/Loss (Raw)": 2.107762336730957, "Pretrain/Step": 8545, "Pretrain/Step Time": 8.489792389795184} +{"Pretrain/Learning Rate": 1.3999136648894074e-06, "Pretrain/Loss": 1.9756369590759277, "Pretrain/Loss (Raw)": 2.043954610824585, "Pretrain/Step": 8546, "Pretrain/Step Time": 8.489627297967672} +{"Pretrain/Learning Rate": 1.3971136121254225e-06, "Pretrain/Loss": 1.9776923656463623, "Pretrain/Loss (Raw)": 2.1052684783935547, "Pretrain/Step": 8547, "Pretrain/Step Time": 8.493222042918205} +{"Pretrain/Learning Rate": 1.3943162819460841e-06, "Pretrain/Loss": 1.9788557291030884, "Pretrain/Loss (Raw)": 2.0050048828125, "Pretrain/Step": 8548, "Pretrain/Step Time": 8.492224534973502} +{"Pretrain/Learning Rate": 1.3915216746740705e-06, "Pretrain/Loss": 1.977482557296753, "Pretrain/Loss (Raw)": 1.931239128112793, "Pretrain/Step": 8549, "Pretrain/Step Time": 8.494148703292012} +{"Pretrain/Learning Rate": 1.3887297906317375e-06, "Pretrain/Loss": 1.9812756776809692, "Pretrain/Loss (Raw)": 2.153226613998413, "Pretrain/Step": 8550, "Pretrain/Step Time": 8.492380665615201} +{"Pretrain/Learning Rate": 1.385940630141122e-06, "Pretrain/Loss": 1.9825996160507202, "Pretrain/Loss (Raw)": 1.8780843019485474, "Pretrain/Step": 8551, "Pretrain/Step Time": 8.491704722866416} +{"Pretrain/Learning Rate": 1.3831541935239556e-06, "Pretrain/Loss": 1.9827631711959839, "Pretrain/Loss (Raw)": 2.041343927383423, "Pretrain/Step": 8552, "Pretrain/Step Time": 8.493943681940436} +{"Pretrain/Learning Rate": 1.3803704811016532e-06, "Pretrain/Loss": 1.9824635982513428, "Pretrain/Loss (Raw)": 1.8584424257278442, "Pretrain/Step": 8553, "Pretrain/Step Time": 8.492257680743933} +{"Pretrain/Learning Rate": 1.3775894931953165e-06, "Pretrain/Loss": 1.9820551872253418, "Pretrain/Loss (Raw)": 1.8652417659759521, "Pretrain/Step": 8554, "Pretrain/Step Time": 8.492815520614386} +{"Pretrain/Learning Rate": 1.3748112301257332e-06, "Pretrain/Loss": 1.9824957847595215, "Pretrain/Loss (Raw)": 1.9325692653656006, "Pretrain/Step": 8555, "Pretrain/Step Time": 8.491313550621271} +{"Pretrain/Learning Rate": 1.3720356922133666e-06, "Pretrain/Loss": 1.9823949337005615, "Pretrain/Loss (Raw)": 2.0817956924438477, "Pretrain/Step": 8556, "Pretrain/Step Time": 8.493472507223487} +{"Pretrain/Learning Rate": 1.3692628797783852e-06, "Pretrain/Loss": 1.9810545444488525, "Pretrain/Loss (Raw)": 1.714777946472168, "Pretrain/Step": 8557, "Pretrain/Step Time": 8.49034309387207} +{"Pretrain/Learning Rate": 1.3664927931406225e-06, "Pretrain/Loss": 1.98056960105896, "Pretrain/Loss (Raw)": 2.038212537765503, "Pretrain/Step": 8558, "Pretrain/Step Time": 8.491487627848983} +{"Pretrain/Learning Rate": 1.3637254326196115e-06, "Pretrain/Loss": 1.979332447052002, "Pretrain/Loss (Raw)": 1.9531967639923096, "Pretrain/Step": 8559, "Pretrain/Step Time": 8.490380428731441} +{"Pretrain/Learning Rate": 1.3609607985345662e-06, "Pretrain/Loss": 1.9801232814788818, "Pretrain/Loss (Raw)": 2.1222002506256104, "Pretrain/Step": 8560, "Pretrain/Step Time": 8.490007381886244} +{"Pretrain/Learning Rate": 1.3581988912043847e-06, "Pretrain/Loss": 1.9801535606384277, "Pretrain/Loss (Raw)": 2.1835103034973145, "Pretrain/Step": 8561, "Pretrain/Step Time": 8.48828831128776} +{"Pretrain/Learning Rate": 1.3554397109476507e-06, "Pretrain/Loss": 1.9795360565185547, "Pretrain/Loss (Raw)": 1.8782352209091187, "Pretrain/Step": 8562, "Pretrain/Step Time": 8.492346683517098} +{"Pretrain/Learning Rate": 1.3526832580826376e-06, "Pretrain/Loss": 1.9780634641647339, "Pretrain/Loss (Raw)": 1.981848120689392, "Pretrain/Step": 8563, "Pretrain/Step Time": 8.491068191826344} +{"Pretrain/Learning Rate": 1.349929532927302e-06, "Pretrain/Loss": 1.9775841236114502, "Pretrain/Loss (Raw)": 2.0300817489624023, "Pretrain/Step": 8564, "Pretrain/Step Time": 8.492641257122159} +{"Pretrain/Learning Rate": 1.3471785357992816e-06, "Pretrain/Loss": 1.977489948272705, "Pretrain/Loss (Raw)": 2.0753042697906494, "Pretrain/Step": 8565, "Pretrain/Step Time": 8.492357378825545} +{"Pretrain/Learning Rate": 1.3444302670159088e-06, "Pretrain/Loss": 1.9765987396240234, "Pretrain/Loss (Raw)": 1.9198758602142334, "Pretrain/Step": 8566, "Pretrain/Step Time": 8.493444107472897} +{"Pretrain/Learning Rate": 1.341684726894188e-06, "Pretrain/Loss": 1.976752758026123, "Pretrain/Loss (Raw)": 2.0664753913879395, "Pretrain/Step": 8567, "Pretrain/Step Time": 8.488285614177585} +{"Pretrain/Learning Rate": 1.3389419157508216e-06, "Pretrain/Loss": 1.9732106924057007, "Pretrain/Loss (Raw)": 1.6573396921157837, "Pretrain/Step": 8568, "Pretrain/Step Time": 8.490459773689508} +{"Pretrain/Learning Rate": 1.336201833902187e-06, "Pretrain/Loss": 1.9725624322891235, "Pretrain/Loss (Raw)": 1.9498494863510132, "Pretrain/Step": 8569, "Pretrain/Step Time": 8.48645506799221} +{"Pretrain/Learning Rate": 1.3334644816643566e-06, "Pretrain/Loss": 1.971144676208496, "Pretrain/Loss (Raw)": 1.7808083295822144, "Pretrain/Step": 8570, "Pretrain/Step Time": 8.488972844555974} +{"Pretrain/Learning Rate": 1.330729859353086e-06, "Pretrain/Loss": 1.9740347862243652, "Pretrain/Loss (Raw)": 2.0592830181121826, "Pretrain/Step": 8571, "Pretrain/Step Time": 8.488391371443868} +{"Pretrain/Learning Rate": 1.3279979672838032e-06, "Pretrain/Loss": 1.9759724140167236, "Pretrain/Loss (Raw)": 2.0896124839782715, "Pretrain/Step": 8572, "Pretrain/Step Time": 8.487963620573282} +{"Pretrain/Learning Rate": 1.3252688057716373e-06, "Pretrain/Loss": 1.976747989654541, "Pretrain/Loss (Raw)": 2.0802106857299805, "Pretrain/Step": 8573, "Pretrain/Step Time": 8.48276500403881} +{"Pretrain/Learning Rate": 1.3225423751313942e-06, "Pretrain/Loss": 1.9785563945770264, "Pretrain/Loss (Raw)": 1.9343928098678589, "Pretrain/Step": 8574, "Pretrain/Step Time": 8.487410185858607} +{"Pretrain/Learning Rate": 1.3198186756775672e-06, "Pretrain/Loss": 1.978562831878662, "Pretrain/Loss (Raw)": 1.9793221950531006, "Pretrain/Step": 8575, "Pretrain/Step Time": 8.490834826603532} +{"Pretrain/Learning Rate": 1.317097707724338e-06, "Pretrain/Loss": 1.9763505458831787, "Pretrain/Loss (Raw)": 1.9045000076293945, "Pretrain/Step": 8576, "Pretrain/Step Time": 8.491330493241549} +{"Pretrain/Learning Rate": 1.3143794715855584e-06, "Pretrain/Loss": 1.9765260219573975, "Pretrain/Loss (Raw)": 1.9540215730667114, "Pretrain/Step": 8577, "Pretrain/Step Time": 8.491549152880907} +{"Pretrain/Learning Rate": 1.311663967574786e-06, "Pretrain/Loss": 1.9772238731384277, "Pretrain/Loss (Raw)": 2.0325629711151123, "Pretrain/Step": 8578, "Pretrain/Step Time": 8.48955300450325} +{"Pretrain/Learning Rate": 1.3089511960052508e-06, "Pretrain/Loss": 1.9770338535308838, "Pretrain/Loss (Raw)": 2.154432535171509, "Pretrain/Step": 8579, "Pretrain/Step Time": 8.484416646882892} +{"Pretrain/Learning Rate": 1.3062411571898692e-06, "Pretrain/Loss": 1.975825548171997, "Pretrain/Loss (Raw)": 1.791459321975708, "Pretrain/Step": 8580, "Pretrain/Step Time": 8.4834886752069} +{"Pretrain/Learning Rate": 1.303533851441241e-06, "Pretrain/Loss": 1.9758142232894897, "Pretrain/Loss (Raw)": 1.9574755430221558, "Pretrain/Step": 8581, "Pretrain/Step Time": 8.485415108501911} +{"Pretrain/Learning Rate": 1.3008292790716608e-06, "Pretrain/Loss": 1.9764777421951294, "Pretrain/Loss (Raw)": 2.107394218444824, "Pretrain/Step": 8582, "Pretrain/Step Time": 8.48287096247077} +{"Pretrain/Learning Rate": 1.2981274403930933e-06, "Pretrain/Loss": 1.9760777950286865, "Pretrain/Loss (Raw)": 1.9674923419952393, "Pretrain/Step": 8583, "Pretrain/Step Time": 8.479173934087157} +{"Pretrain/Learning Rate": 1.2954283357171943e-06, "Pretrain/Loss": 1.975682258605957, "Pretrain/Loss (Raw)": 2.030447006225586, "Pretrain/Step": 8584, "Pretrain/Step Time": 8.47948650084436} +{"Pretrain/Learning Rate": 1.2927319653553065e-06, "Pretrain/Loss": 1.9774008989334106, "Pretrain/Loss (Raw)": 2.139247417449951, "Pretrain/Step": 8585, "Pretrain/Step Time": 8.477067502215505} +{"Pretrain/Learning Rate": 1.2900383296184536e-06, "Pretrain/Loss": 1.9771729707717896, "Pretrain/Loss (Raw)": 1.9958409070968628, "Pretrain/Step": 8586, "Pretrain/Step Time": 8.477098377421498} +{"Pretrain/Learning Rate": 1.2873474288173538e-06, "Pretrain/Loss": 1.9744014739990234, "Pretrain/Loss (Raw)": 1.6522220373153687, "Pretrain/Step": 8587, "Pretrain/Step Time": 8.479135114699602} +{"Pretrain/Learning Rate": 1.2846592632623889e-06, "Pretrain/Loss": 1.9755442142486572, "Pretrain/Loss (Raw)": 2.025595188140869, "Pretrain/Step": 8588, "Pretrain/Step Time": 8.481271313503385} +{"Pretrain/Learning Rate": 1.2819738332636443e-06, "Pretrain/Loss": 1.973167896270752, "Pretrain/Loss (Raw)": 1.7414239645004272, "Pretrain/Step": 8589, "Pretrain/Step Time": 8.479298381134868} +{"Pretrain/Learning Rate": 1.2792911391308864e-06, "Pretrain/Loss": 1.9707467555999756, "Pretrain/Loss (Raw)": 1.7971612215042114, "Pretrain/Step": 8590, "Pretrain/Step Time": 8.481670651584864} +{"Pretrain/Learning Rate": 1.2766111811735564e-06, "Pretrain/Loss": 1.9695417881011963, "Pretrain/Loss (Raw)": 1.9720395803451538, "Pretrain/Step": 8591, "Pretrain/Step Time": 8.481659973040223} +{"Pretrain/Learning Rate": 1.2739339597007932e-06, "Pretrain/Loss": 1.9701619148254395, "Pretrain/Loss (Raw)": 1.9906532764434814, "Pretrain/Step": 8592, "Pretrain/Step Time": 8.481872817501426} +{"Pretrain/Learning Rate": 1.2712594750214052e-06, "Pretrain/Loss": 1.9709104299545288, "Pretrain/Loss (Raw)": 2.0481326580047607, "Pretrain/Step": 8593, "Pretrain/Step Time": 8.482276504859328} +{"Pretrain/Learning Rate": 1.2685877274438985e-06, "Pretrain/Loss": 1.9709341526031494, "Pretrain/Loss (Raw)": 2.1354434490203857, "Pretrain/Step": 8594, "Pretrain/Step Time": 8.480384893715382} +{"Pretrain/Learning Rate": 1.2659187172764597e-06, "Pretrain/Loss": 1.971917748451233, "Pretrain/Loss (Raw)": 2.076557159423828, "Pretrain/Step": 8595, "Pretrain/Step Time": 8.482778387144208} +{"Pretrain/Learning Rate": 1.263252444826954e-06, "Pretrain/Loss": 1.9724278450012207, "Pretrain/Loss (Raw)": 2.0869507789611816, "Pretrain/Step": 8596, "Pretrain/Step Time": 8.482669467106462} +{"Pretrain/Learning Rate": 1.2605889104029406e-06, "Pretrain/Loss": 1.971744418144226, "Pretrain/Loss (Raw)": 1.994294285774231, "Pretrain/Step": 8597, "Pretrain/Step Time": 8.48047155700624} +{"Pretrain/Learning Rate": 1.2579281143116518e-06, "Pretrain/Loss": 1.9707087278366089, "Pretrain/Loss (Raw)": 1.9900020360946655, "Pretrain/Step": 8598, "Pretrain/Step Time": 8.484872456640005} +{"Pretrain/Learning Rate": 1.2552700568600085e-06, "Pretrain/Loss": 1.971104383468628, "Pretrain/Loss (Raw)": 2.160820960998535, "Pretrain/Step": 8599, "Pretrain/Step Time": 8.480984684079885} +{"Pretrain/Learning Rate": 1.2526147383546239e-06, "Pretrain/Loss": 1.9736099243164062, "Pretrain/Loss (Raw)": 2.021756887435913, "Pretrain/Step": 8600, "Pretrain/Step Time": 8.481816688552499} +{"Pretrain/Learning Rate": 1.2499621591017807e-06, "Pretrain/Loss": 1.9721567630767822, "Pretrain/Loss (Raw)": 1.936475157737732, "Pretrain/Step": 8601, "Pretrain/Step Time": 8.478703156113625} +{"Pretrain/Learning Rate": 1.2473123194074565e-06, "Pretrain/Loss": 1.9725384712219238, "Pretrain/Loss (Raw)": 1.8653161525726318, "Pretrain/Step": 8602, "Pretrain/Step Time": 8.477206645533442} +{"Pretrain/Learning Rate": 1.2446652195773123e-06, "Pretrain/Loss": 1.9728124141693115, "Pretrain/Loss (Raw)": 1.8811616897583008, "Pretrain/Step": 8603, "Pretrain/Step Time": 8.483222678303719} +{"Pretrain/Learning Rate": 1.2420208599166844e-06, "Pretrain/Loss": 1.9737801551818848, "Pretrain/Loss (Raw)": 1.9972987174987793, "Pretrain/Step": 8604, "Pretrain/Step Time": 8.481716122478247} +{"Pretrain/Learning Rate": 1.2393792407306009e-06, "Pretrain/Loss": 1.9744596481323242, "Pretrain/Loss (Raw)": 2.052138328552246, "Pretrain/Step": 8605, "Pretrain/Step Time": 8.48163546435535} +{"Pretrain/Learning Rate": 1.236740362323774e-06, "Pretrain/Loss": 1.9766201972961426, "Pretrain/Loss (Raw)": 2.058192014694214, "Pretrain/Step": 8606, "Pretrain/Step Time": 8.479954026639462} +{"Pretrain/Learning Rate": 1.234104225000593e-06, "Pretrain/Loss": 1.9775004386901855, "Pretrain/Loss (Raw)": 1.8410325050354004, "Pretrain/Step": 8607, "Pretrain/Step Time": 8.485124669969082} +{"Pretrain/Learning Rate": 1.2314708290651427e-06, "Pretrain/Loss": 1.977736234664917, "Pretrain/Loss (Raw)": 1.8267134428024292, "Pretrain/Step": 8608, "Pretrain/Step Time": 8.484132647514343} +{"Pretrain/Learning Rate": 1.228840174821172e-06, "Pretrain/Loss": 1.9777495861053467, "Pretrain/Loss (Raw)": 1.978713035583496, "Pretrain/Step": 8609, "Pretrain/Step Time": 8.48518206179142} +{"Pretrain/Learning Rate": 1.2262122625721377e-06, "Pretrain/Loss": 1.9762613773345947, "Pretrain/Loss (Raw)": 1.9022983312606812, "Pretrain/Step": 8610, "Pretrain/Step Time": 8.484698720276356} +{"Pretrain/Learning Rate": 1.2235870926211619e-06, "Pretrain/Loss": 1.9744495153427124, "Pretrain/Loss (Raw)": 1.976396083831787, "Pretrain/Step": 8611, "Pretrain/Step Time": 8.481383945792913} +{"Pretrain/Learning Rate": 1.22096466527106e-06, "Pretrain/Loss": 1.9755041599273682, "Pretrain/Loss (Raw)": 1.9365235567092896, "Pretrain/Step": 8612, "Pretrain/Step Time": 8.484968073666096} +{"Pretrain/Learning Rate": 1.218344980824329e-06, "Pretrain/Loss": 1.978027105331421, "Pretrain/Loss (Raw)": 2.061824321746826, "Pretrain/Step": 8613, "Pretrain/Step Time": 8.48751931078732} +{"Pretrain/Learning Rate": 1.2157280395831473e-06, "Pretrain/Loss": 1.9778358936309814, "Pretrain/Loss (Raw)": 2.0190489292144775, "Pretrain/Step": 8614, "Pretrain/Step Time": 8.486161183565855} +{"Pretrain/Learning Rate": 1.2131138418493754e-06, "Pretrain/Loss": 1.976722240447998, "Pretrain/Loss (Raw)": 1.8856618404388428, "Pretrain/Step": 8615, "Pretrain/Step Time": 8.483478652313352} +{"Pretrain/Learning Rate": 1.2105023879245614e-06, "Pretrain/Loss": 1.9777870178222656, "Pretrain/Loss (Raw)": 2.1889240741729736, "Pretrain/Step": 8616, "Pretrain/Step Time": 8.481041017919779} +{"Pretrain/Learning Rate": 1.2078936781099392e-06, "Pretrain/Loss": 1.980672836303711, "Pretrain/Loss (Raw)": 2.0677602291107178, "Pretrain/Step": 8617, "Pretrain/Step Time": 8.482214540243149} +{"Pretrain/Learning Rate": 1.205287712706421e-06, "Pretrain/Loss": 1.9817759990692139, "Pretrain/Loss (Raw)": 2.041393518447876, "Pretrain/Step": 8618, "Pretrain/Step Time": 8.479569325223565} +{"Pretrain/Learning Rate": 1.2026844920146024e-06, "Pretrain/Loss": 1.9820282459259033, "Pretrain/Loss (Raw)": 2.1009538173675537, "Pretrain/Step": 8619, "Pretrain/Step Time": 8.480560375377536} +{"Pretrain/Learning Rate": 1.2000840163347627e-06, "Pretrain/Loss": 1.9828035831451416, "Pretrain/Loss (Raw)": 2.0096843242645264, "Pretrain/Step": 8620, "Pretrain/Step Time": 8.482247680425644} +{"Pretrain/Learning Rate": 1.19748628596687e-06, "Pretrain/Loss": 1.9841227531433105, "Pretrain/Loss (Raw)": 2.0796871185302734, "Pretrain/Step": 8621, "Pretrain/Step Time": 8.483466928824782} +{"Pretrain/Learning Rate": 1.1948913012105712e-06, "Pretrain/Loss": 1.9841136932373047, "Pretrain/Loss (Raw)": 1.966060996055603, "Pretrain/Step": 8622, "Pretrain/Step Time": 8.483219314366579} +{"Pretrain/Learning Rate": 1.1922990623651902e-06, "Pretrain/Loss": 1.9817832708358765, "Pretrain/Loss (Raw)": 1.7511783838272095, "Pretrain/Step": 8623, "Pretrain/Step Time": 8.488275373354554} +{"Pretrain/Learning Rate": 1.1897095697297522e-06, "Pretrain/Loss": 1.983327865600586, "Pretrain/Loss (Raw)": 2.068735361099243, "Pretrain/Step": 8624, "Pretrain/Step Time": 8.488606207072735} +{"Pretrain/Learning Rate": 1.187122823602943e-06, "Pretrain/Loss": 1.9829707145690918, "Pretrain/Loss (Raw)": 1.9742040634155273, "Pretrain/Step": 8625, "Pretrain/Step Time": 8.489217890426517} +{"Pretrain/Learning Rate": 1.1845388242831462e-06, "Pretrain/Loss": 1.9835319519042969, "Pretrain/Loss (Raw)": 2.065795421600342, "Pretrain/Step": 8626, "Pretrain/Step Time": 8.488821296021342} +{"Pretrain/Learning Rate": 1.181957572068429e-06, "Pretrain/Loss": 1.9831334352493286, "Pretrain/Loss (Raw)": 2.024202585220337, "Pretrain/Step": 8627, "Pretrain/Step Time": 8.48950830847025} +{"Pretrain/Learning Rate": 1.1793790672565335e-06, "Pretrain/Loss": 1.982024908065796, "Pretrain/Loss (Raw)": 1.9261385202407837, "Pretrain/Step": 8628, "Pretrain/Step Time": 8.487409461289644} +{"Pretrain/Learning Rate": 1.176803310144897e-06, "Pretrain/Loss": 1.982005000114441, "Pretrain/Loss (Raw)": 2.035508155822754, "Pretrain/Step": 8629, "Pretrain/Step Time": 8.486347626894712} +{"Pretrain/Learning Rate": 1.1742303010306211e-06, "Pretrain/Loss": 1.9792256355285645, "Pretrain/Loss (Raw)": 1.8131741285324097, "Pretrain/Step": 8630, "Pretrain/Step Time": 8.48489929176867} +{"Pretrain/Learning Rate": 1.1716600402105093e-06, "Pretrain/Loss": 1.975881814956665, "Pretrain/Loss (Raw)": 1.5234589576721191, "Pretrain/Step": 8631, "Pretrain/Step Time": 8.4837725777179} +{"Pretrain/Learning Rate": 1.1690925279810362e-06, "Pretrain/Loss": 1.976246953010559, "Pretrain/Loss (Raw)": 1.9796791076660156, "Pretrain/Step": 8632, "Pretrain/Step Time": 8.487674914300442} +{"Pretrain/Learning Rate": 1.1665277646383671e-06, "Pretrain/Loss": 1.9751533269882202, "Pretrain/Loss (Raw)": 1.9906911849975586, "Pretrain/Step": 8633, "Pretrain/Step Time": 8.485542377457023} +{"Pretrain/Learning Rate": 1.1639657504783462e-06, "Pretrain/Loss": 1.9751027822494507, "Pretrain/Loss (Raw)": 2.020479917526245, "Pretrain/Step": 8634, "Pretrain/Step Time": 8.482987653464079} +{"Pretrain/Learning Rate": 1.1614064857964985e-06, "Pretrain/Loss": 1.9764981269836426, "Pretrain/Loss (Raw)": 1.9426524639129639, "Pretrain/Step": 8635, "Pretrain/Step Time": 8.48521332629025} +{"Pretrain/Learning Rate": 1.158849970888032e-06, "Pretrain/Loss": 1.9782497882843018, "Pretrain/Loss (Raw)": 2.123525381088257, "Pretrain/Step": 8636, "Pretrain/Step Time": 8.485158767551184} +{"Pretrain/Learning Rate": 1.1562962060478439e-06, "Pretrain/Loss": 1.9784908294677734, "Pretrain/Loss (Raw)": 1.9965054988861084, "Pretrain/Step": 8637, "Pretrain/Step Time": 8.483690481632948} +{"Pretrain/Learning Rate": 1.15374519157051e-06, "Pretrain/Loss": 1.9787893295288086, "Pretrain/Loss (Raw)": 2.0960466861724854, "Pretrain/Step": 8638, "Pretrain/Step Time": 8.485111879184842} +{"Pretrain/Learning Rate": 1.151196927750292e-06, "Pretrain/Loss": 1.9783655405044556, "Pretrain/Loss (Raw)": 1.9744012355804443, "Pretrain/Step": 8639, "Pretrain/Step Time": 8.486404288560152} +{"Pretrain/Learning Rate": 1.1486514148811216e-06, "Pretrain/Loss": 1.976205587387085, "Pretrain/Loss (Raw)": 1.7568055391311646, "Pretrain/Step": 8640, "Pretrain/Step Time": 8.488671826198697} +{"Pretrain/Learning Rate": 1.1461086532566335e-06, "Pretrain/Loss": 1.9766533374786377, "Pretrain/Loss (Raw)": 2.011988878250122, "Pretrain/Step": 8641, "Pretrain/Step Time": 8.488576732575893} +{"Pretrain/Learning Rate": 1.143568643170126e-06, "Pretrain/Loss": 1.9792606830596924, "Pretrain/Loss (Raw)": 1.9276444911956787, "Pretrain/Step": 8642, "Pretrain/Step Time": 8.484892453998327} +{"Pretrain/Learning Rate": 1.1410313849145926e-06, "Pretrain/Loss": 1.980233907699585, "Pretrain/Loss (Raw)": 2.1354968547821045, "Pretrain/Step": 8643, "Pretrain/Step Time": 8.484273355454206} +{"Pretrain/Learning Rate": 1.1384968787827022e-06, "Pretrain/Loss": 1.9816009998321533, "Pretrain/Loss (Raw)": 2.1153337955474854, "Pretrain/Step": 8644, "Pretrain/Step Time": 8.486294999718666} +{"Pretrain/Learning Rate": 1.135965125066818e-06, "Pretrain/Loss": 1.9815244674682617, "Pretrain/Loss (Raw)": 1.9933197498321533, "Pretrain/Step": 8645, "Pretrain/Step Time": 8.484082400798798} +{"Pretrain/Learning Rate": 1.1334361240589647e-06, "Pretrain/Loss": 1.9824471473693848, "Pretrain/Loss (Raw)": 1.9637023210525513, "Pretrain/Step": 8646, "Pretrain/Step Time": 8.485113164409995} +{"Pretrain/Learning Rate": 1.1309098760508646e-06, "Pretrain/Loss": 1.9842472076416016, "Pretrain/Loss (Raw)": 2.2509632110595703, "Pretrain/Step": 8647, "Pretrain/Step Time": 8.483701009303331} +{"Pretrain/Learning Rate": 1.1283863813339263e-06, "Pretrain/Loss": 1.9867966175079346, "Pretrain/Loss (Raw)": 2.1180830001831055, "Pretrain/Step": 8648, "Pretrain/Step Time": 8.48671398870647} +{"Pretrain/Learning Rate": 1.1258656401992278e-06, "Pretrain/Loss": 1.985538363456726, "Pretrain/Loss (Raw)": 1.9270894527435303, "Pretrain/Step": 8649, "Pretrain/Step Time": 8.486772790551186} +{"Pretrain/Learning Rate": 1.1233476529375426e-06, "Pretrain/Loss": 1.983640432357788, "Pretrain/Loss (Raw)": 1.8822247982025146, "Pretrain/Step": 8650, "Pretrain/Step Time": 8.484448984265327} +{"Pretrain/Learning Rate": 1.12083241983931e-06, "Pretrain/Loss": 1.983696699142456, "Pretrain/Loss (Raw)": 2.1448984146118164, "Pretrain/Step": 8651, "Pretrain/Step Time": 8.48608330823481} +{"Pretrain/Learning Rate": 1.1183199411946649e-06, "Pretrain/Loss": 1.985435962677002, "Pretrain/Loss (Raw)": 2.2451999187469482, "Pretrain/Step": 8652, "Pretrain/Step Time": 8.48653732612729} +{"Pretrain/Learning Rate": 1.1158102172934254e-06, "Pretrain/Loss": 1.9854965209960938, "Pretrain/Loss (Raw)": 2.07220721244812, "Pretrain/Step": 8653, "Pretrain/Step Time": 8.481750624254346} +{"Pretrain/Learning Rate": 1.1133032484250821e-06, "Pretrain/Loss": 1.9861048460006714, "Pretrain/Loss (Raw)": 1.9289002418518066, "Pretrain/Step": 8654, "Pretrain/Step Time": 8.4842608589679} +{"Pretrain/Learning Rate": 1.1107990348788178e-06, "Pretrain/Loss": 1.9883005619049072, "Pretrain/Loss (Raw)": 2.1388356685638428, "Pretrain/Step": 8655, "Pretrain/Step Time": 8.482739739120007} +{"Pretrain/Learning Rate": 1.1082975769434845e-06, "Pretrain/Loss": 1.9882303476333618, "Pretrain/Loss (Raw)": 1.9756611585617065, "Pretrain/Step": 8656, "Pretrain/Step Time": 8.486787714064121} +{"Pretrain/Learning Rate": 1.1057988749076348e-06, "Pretrain/Loss": 1.9877933263778687, "Pretrain/Loss (Raw)": 1.838773250579834, "Pretrain/Step": 8657, "Pretrain/Step Time": 8.488935884088278} +{"Pretrain/Learning Rate": 1.1033029290594855e-06, "Pretrain/Loss": 1.9881089925765991, "Pretrain/Loss (Raw)": 2.052469253540039, "Pretrain/Step": 8658, "Pretrain/Step Time": 8.48369749262929} +{"Pretrain/Learning Rate": 1.100809739686945e-06, "Pretrain/Loss": 1.9888067245483398, "Pretrain/Loss (Raw)": 2.0049030780792236, "Pretrain/Step": 8659, "Pretrain/Step Time": 8.487107334658504} +{"Pretrain/Learning Rate": 1.0983193070776053e-06, "Pretrain/Loss": 1.9894235134124756, "Pretrain/Loss (Raw)": 2.010758876800537, "Pretrain/Step": 8660, "Pretrain/Step Time": 8.48956866376102} +{"Pretrain/Learning Rate": 1.095831631518729e-06, "Pretrain/Loss": 1.9886325597763062, "Pretrain/Loss (Raw)": 1.9874045848846436, "Pretrain/Step": 8661, "Pretrain/Step Time": 8.484946865588427} +{"Pretrain/Learning Rate": 1.0933467132972746e-06, "Pretrain/Loss": 1.9877315759658813, "Pretrain/Loss (Raw)": 1.9284484386444092, "Pretrain/Step": 8662, "Pretrain/Step Time": 8.48496613651514} +{"Pretrain/Learning Rate": 1.0908645526998745e-06, "Pretrain/Loss": 1.9865909814834595, "Pretrain/Loss (Raw)": 1.8882261514663696, "Pretrain/Step": 8663, "Pretrain/Step Time": 8.484753530472517} +{"Pretrain/Learning Rate": 1.0883851500128494e-06, "Pretrain/Loss": 1.9867722988128662, "Pretrain/Loss (Raw)": 2.0388379096984863, "Pretrain/Step": 8664, "Pretrain/Step Time": 8.482045825570822} +{"Pretrain/Learning Rate": 1.0859085055221902e-06, "Pretrain/Loss": 1.9842565059661865, "Pretrain/Loss (Raw)": 1.844220519065857, "Pretrain/Step": 8665, "Pretrain/Step Time": 8.483930509537458} +{"Pretrain/Learning Rate": 1.0834346195135874e-06, "Pretrain/Loss": 1.9890894889831543, "Pretrain/Loss (Raw)": 2.143714427947998, "Pretrain/Step": 8666, "Pretrain/Step Time": 8.478791892528534} +{"Pretrain/Learning Rate": 1.080963492272391e-06, "Pretrain/Loss": 1.988404393196106, "Pretrain/Loss (Raw)": 1.806544542312622, "Pretrain/Step": 8667, "Pretrain/Step Time": 8.479261811822653} +{"Pretrain/Learning Rate": 1.0784951240836505e-06, "Pretrain/Loss": 1.9881199598312378, "Pretrain/Loss (Raw)": 2.1404545307159424, "Pretrain/Step": 8668, "Pretrain/Step Time": 8.482237232849002} +{"Pretrain/Learning Rate": 1.076029515232091e-06, "Pretrain/Loss": 1.9884710311889648, "Pretrain/Loss (Raw)": 2.10324764251709, "Pretrain/Step": 8669, "Pretrain/Step Time": 8.482416430488229} +{"Pretrain/Learning Rate": 1.0735666660021182e-06, "Pretrain/Loss": 1.9902782440185547, "Pretrain/Loss (Raw)": 2.108455181121826, "Pretrain/Step": 8670, "Pretrain/Step Time": 8.479292714968324} +{"Pretrain/Learning Rate": 1.0711065766778272e-06, "Pretrain/Loss": 1.9897234439849854, "Pretrain/Loss (Raw)": 2.0291223526000977, "Pretrain/Step": 8671, "Pretrain/Step Time": 8.478744415566325} +{"Pretrain/Learning Rate": 1.06864924754298e-06, "Pretrain/Loss": 1.9903626441955566, "Pretrain/Loss (Raw)": 2.0464649200439453, "Pretrain/Step": 8672, "Pretrain/Step Time": 8.480365063995123} +{"Pretrain/Learning Rate": 1.0661946788810301e-06, "Pretrain/Loss": 1.9901996850967407, "Pretrain/Loss (Raw)": 2.0868825912475586, "Pretrain/Step": 8673, "Pretrain/Step Time": 8.480078542605042} +{"Pretrain/Learning Rate": 1.0637428709751178e-06, "Pretrain/Loss": 1.9899134635925293, "Pretrain/Loss (Raw)": 2.007319211959839, "Pretrain/Step": 8674, "Pretrain/Step Time": 8.479837788268924} +{"Pretrain/Learning Rate": 1.0612938241080506e-06, "Pretrain/Loss": 1.9869790077209473, "Pretrain/Loss (Raw)": 1.729647159576416, "Pretrain/Step": 8675, "Pretrain/Step Time": 8.47893463820219} +{"Pretrain/Learning Rate": 1.0588475385623297e-06, "Pretrain/Loss": 1.9875296354293823, "Pretrain/Loss (Raw)": 2.075490951538086, "Pretrain/Step": 8676, "Pretrain/Step Time": 8.479238770902157} +{"Pretrain/Learning Rate": 1.0564040146201299e-06, "Pretrain/Loss": 1.9887322187423706, "Pretrain/Loss (Raw)": 2.0851712226867676, "Pretrain/Step": 8677, "Pretrain/Step Time": 8.479421529918909} +{"Pretrain/Learning Rate": 1.0539632525633113e-06, "Pretrain/Loss": 1.9875279664993286, "Pretrain/Loss (Raw)": 1.999097466468811, "Pretrain/Step": 8678, "Pretrain/Step Time": 8.47955334186554} +{"Pretrain/Learning Rate": 1.0515252526734186e-06, "Pretrain/Loss": 1.9884631633758545, "Pretrain/Loss (Raw)": 1.9977864027023315, "Pretrain/Step": 8679, "Pretrain/Step Time": 8.480823064222932} +{"Pretrain/Learning Rate": 1.0490900152316713e-06, "Pretrain/Loss": 1.9891741275787354, "Pretrain/Loss (Raw)": 2.1323516368865967, "Pretrain/Step": 8680, "Pretrain/Step Time": 8.480619920417666} +{"Pretrain/Learning Rate": 1.046657540518975e-06, "Pretrain/Loss": 1.9916489124298096, "Pretrain/Loss (Raw)": 2.175210952758789, "Pretrain/Step": 8681, "Pretrain/Step Time": 8.48022897168994} +{"Pretrain/Learning Rate": 1.0442278288159136e-06, "Pretrain/Loss": 1.9929299354553223, "Pretrain/Loss (Raw)": 2.029207706451416, "Pretrain/Step": 8682, "Pretrain/Step Time": 8.48202807828784} +{"Pretrain/Learning Rate": 1.041800880402749e-06, "Pretrain/Loss": 1.9936083555221558, "Pretrain/Loss (Raw)": 2.0194144248962402, "Pretrain/Step": 8683, "Pretrain/Step Time": 8.48171991854906} +{"Pretrain/Learning Rate": 1.0393766955594382e-06, "Pretrain/Loss": 1.9937652349472046, "Pretrain/Loss (Raw)": 2.1018664836883545, "Pretrain/Step": 8684, "Pretrain/Step Time": 8.478764731436968} +{"Pretrain/Learning Rate": 1.0369552745656013e-06, "Pretrain/Loss": 1.9957793951034546, "Pretrain/Loss (Raw)": 1.972588062286377, "Pretrain/Step": 8685, "Pretrain/Step Time": 8.476899133995175} +{"Pretrain/Learning Rate": 1.0345366177005544e-06, "Pretrain/Loss": 1.994959831237793, "Pretrain/Loss (Raw)": 1.9333223104476929, "Pretrain/Step": 8686, "Pretrain/Step Time": 8.479787062853575} +{"Pretrain/Learning Rate": 1.0321207252432907e-06, "Pretrain/Loss": 1.9951624870300293, "Pretrain/Loss (Raw)": 1.979129433631897, "Pretrain/Step": 8687, "Pretrain/Step Time": 8.479656260460615} +{"Pretrain/Learning Rate": 1.0297075974724735e-06, "Pretrain/Loss": 1.994161605834961, "Pretrain/Loss (Raw)": 1.9941078424453735, "Pretrain/Step": 8688, "Pretrain/Step Time": 8.4812045507133} +{"Pretrain/Learning Rate": 1.0272972346664606e-06, "Pretrain/Loss": 1.9925661087036133, "Pretrain/Loss (Raw)": 1.9792765378952026, "Pretrain/Step": 8689, "Pretrain/Step Time": 8.481905620545149} +{"Pretrain/Learning Rate": 1.0248896371032907e-06, "Pretrain/Loss": 1.9923996925354004, "Pretrain/Loss (Raw)": 1.856937050819397, "Pretrain/Step": 8690, "Pretrain/Step Time": 8.483585277572274} +{"Pretrain/Learning Rate": 1.022484805060675e-06, "Pretrain/Loss": 1.9931766986846924, "Pretrain/Loss (Raw)": 2.081287384033203, "Pretrain/Step": 8691, "Pretrain/Step Time": 8.481027802452445} +{"Pretrain/Learning Rate": 1.020082738816011e-06, "Pretrain/Loss": 1.9933730363845825, "Pretrain/Loss (Raw)": 2.0552196502685547, "Pretrain/Step": 8692, "Pretrain/Step Time": 8.481881158426404} +{"Pretrain/Learning Rate": 1.0176834386463745e-06, "Pretrain/Loss": 1.9925888776779175, "Pretrain/Loss (Raw)": 1.9749248027801514, "Pretrain/Step": 8693, "Pretrain/Step Time": 8.48331736586988} +{"Pretrain/Learning Rate": 1.0152869048285246e-06, "Pretrain/Loss": 1.9942234754562378, "Pretrain/Loss (Raw)": 2.1291050910949707, "Pretrain/Step": 8694, "Pretrain/Step Time": 8.481978388503194} +{"Pretrain/Learning Rate": 1.0128931376389011e-06, "Pretrain/Loss": 1.9936566352844238, "Pretrain/Loss (Raw)": 1.9939229488372803, "Pretrain/Step": 8695, "Pretrain/Step Time": 8.484948042780161} +{"Pretrain/Learning Rate": 1.010502137353625e-06, "Pretrain/Loss": 1.9958314895629883, "Pretrain/Loss (Raw)": 1.935731291770935, "Pretrain/Step": 8696, "Pretrain/Step Time": 8.4833611715585} +{"Pretrain/Learning Rate": 1.0081139042485006e-06, "Pretrain/Loss": 1.9947664737701416, "Pretrain/Loss (Raw)": 1.8135285377502441, "Pretrain/Step": 8697, "Pretrain/Step Time": 8.484002653509378} +{"Pretrain/Learning Rate": 1.0057284385990018e-06, "Pretrain/Loss": 1.9962079524993896, "Pretrain/Loss (Raw)": 1.9653186798095703, "Pretrain/Step": 8698, "Pretrain/Step Time": 8.481365559622645} +{"Pretrain/Learning Rate": 1.0033457406802948e-06, "Pretrain/Loss": 1.993586540222168, "Pretrain/Loss (Raw)": 1.7237262725830078, "Pretrain/Step": 8699, "Pretrain/Step Time": 8.481655977666378} +{"Pretrain/Learning Rate": 1.0009658107672237e-06, "Pretrain/Loss": 1.9936227798461914, "Pretrain/Loss (Raw)": 2.094259023666382, "Pretrain/Step": 8700, "Pretrain/Step Time": 8.484583232551813} +{"Pretrain/Learning Rate": 9.985886491343132e-07, "Pretrain/Loss": 1.9932801723480225, "Pretrain/Loss (Raw)": 2.0363447666168213, "Pretrain/Step": 8701, "Pretrain/Step Time": 8.484733246266842} +{"Pretrain/Learning Rate": 9.962142560557692e-07, "Pretrain/Loss": 1.9932186603546143, "Pretrain/Loss (Raw)": 1.9265292882919312, "Pretrain/Step": 8702, "Pretrain/Step Time": 8.48503141850233} +{"Pretrain/Learning Rate": 9.93842631805475e-07, "Pretrain/Loss": 1.993157148361206, "Pretrain/Loss (Raw)": 1.971435308456421, "Pretrain/Step": 8703, "Pretrain/Step Time": 8.48431921750307} +{"Pretrain/Learning Rate": 9.914737766569953e-07, "Pretrain/Loss": 1.994018316268921, "Pretrain/Loss (Raw)": 2.014746904373169, "Pretrain/Step": 8704, "Pretrain/Step Time": 8.484754167497158} +{"Pretrain/Learning Rate": 9.891076908835783e-07, "Pretrain/Loss": 1.9945151805877686, "Pretrain/Loss (Raw)": 2.017629384994507, "Pretrain/Step": 8705, "Pretrain/Step Time": 8.487025871872902} +{"Pretrain/Learning Rate": 9.867443747581555e-07, "Pretrain/Loss": 1.9937245845794678, "Pretrain/Loss (Raw)": 1.9313480854034424, "Pretrain/Step": 8706, "Pretrain/Step Time": 8.487885173410177} +{"Pretrain/Learning Rate": 9.843838285533258e-07, "Pretrain/Loss": 1.9917280673980713, "Pretrain/Loss (Raw)": 1.898878574371338, "Pretrain/Step": 8707, "Pretrain/Step Time": 8.488360956311226} +{"Pretrain/Learning Rate": 9.820260525413849e-07, "Pretrain/Loss": 1.993821144104004, "Pretrain/Loss (Raw)": 2.0593717098236084, "Pretrain/Step": 8708, "Pretrain/Step Time": 8.487726662307978} +{"Pretrain/Learning Rate": 9.79671046994296e-07, "Pretrain/Loss": 1.993973731994629, "Pretrain/Loss (Raw)": 1.9770127534866333, "Pretrain/Step": 8709, "Pretrain/Step Time": 8.486103953793645} +{"Pretrain/Learning Rate": 9.773188121837085e-07, "Pretrain/Loss": 1.9932525157928467, "Pretrain/Loss (Raw)": 2.015082597732544, "Pretrain/Step": 8710, "Pretrain/Step Time": 8.486834108829498} +{"Pretrain/Learning Rate": 9.749693483809552e-07, "Pretrain/Loss": 1.994134545326233, "Pretrain/Loss (Raw)": 2.080378770828247, "Pretrain/Step": 8711, "Pretrain/Step Time": 8.489508222788572} +{"Pretrain/Learning Rate": 9.726226558570444e-07, "Pretrain/Loss": 1.9938640594482422, "Pretrain/Loss (Raw)": 1.9958440065383911, "Pretrain/Step": 8712, "Pretrain/Step Time": 8.489744605496526} +{"Pretrain/Learning Rate": 9.702787348826708e-07, "Pretrain/Loss": 1.9928613901138306, "Pretrain/Loss (Raw)": 2.0109074115753174, "Pretrain/Step": 8713, "Pretrain/Step Time": 8.487897025421262} +{"Pretrain/Learning Rate": 9.679375857281959e-07, "Pretrain/Loss": 1.9918758869171143, "Pretrain/Loss (Raw)": 1.8697031736373901, "Pretrain/Step": 8714, "Pretrain/Step Time": 8.486443880945444} +{"Pretrain/Learning Rate": 9.655992086636755e-07, "Pretrain/Loss": 1.9920151233673096, "Pretrain/Loss (Raw)": 1.6700098514556885, "Pretrain/Step": 8715, "Pretrain/Step Time": 8.486797865480185} +{"Pretrain/Learning Rate": 9.63263603958839e-07, "Pretrain/Loss": 1.9910354614257812, "Pretrain/Loss (Raw)": 1.9002156257629395, "Pretrain/Step": 8716, "Pretrain/Step Time": 8.4855831656605} +{"Pretrain/Learning Rate": 9.609307718831006e-07, "Pretrain/Loss": 1.9920026063919067, "Pretrain/Loss (Raw)": 1.8652151823043823, "Pretrain/Step": 8717, "Pretrain/Step Time": 8.487320499494672} +{"Pretrain/Learning Rate": 9.586007127055512e-07, "Pretrain/Loss": 1.9927785396575928, "Pretrain/Loss (Raw)": 1.8964749574661255, "Pretrain/Step": 8718, "Pretrain/Step Time": 8.48936970345676} +{"Pretrain/Learning Rate": 9.562734266949592e-07, "Pretrain/Loss": 1.9905641078948975, "Pretrain/Loss (Raw)": 1.6885995864868164, "Pretrain/Step": 8719, "Pretrain/Step Time": 8.483774928376079} +{"Pretrain/Learning Rate": 9.53948914119776e-07, "Pretrain/Loss": 1.9897758960723877, "Pretrain/Loss (Raw)": 1.8897565603256226, "Pretrain/Step": 8720, "Pretrain/Step Time": 8.484490493312478} +{"Pretrain/Learning Rate": 9.516271752481376e-07, "Pretrain/Loss": 1.990070104598999, "Pretrain/Loss (Raw)": 2.0858001708984375, "Pretrain/Step": 8721, "Pretrain/Step Time": 8.48758364096284} +{"Pretrain/Learning Rate": 9.493082103478517e-07, "Pretrain/Loss": 1.9895203113555908, "Pretrain/Loss (Raw)": 2.0650668144226074, "Pretrain/Step": 8722, "Pretrain/Step Time": 8.487123489379883} +{"Pretrain/Learning Rate": 9.469920196864158e-07, "Pretrain/Loss": 1.9908722639083862, "Pretrain/Loss (Raw)": 2.2496044635772705, "Pretrain/Step": 8723, "Pretrain/Step Time": 8.48397533595562} +{"Pretrain/Learning Rate": 9.446786035309934e-07, "Pretrain/Loss": 1.9899382591247559, "Pretrain/Loss (Raw)": 1.9674041271209717, "Pretrain/Step": 8724, "Pretrain/Step Time": 8.485087752342224} +{"Pretrain/Learning Rate": 9.423679621484438e-07, "Pretrain/Loss": 1.9896633625030518, "Pretrain/Loss (Raw)": 1.9591015577316284, "Pretrain/Step": 8725, "Pretrain/Step Time": 8.483570352196693} +{"Pretrain/Learning Rate": 9.400600958052924e-07, "Pretrain/Loss": 1.9911575317382812, "Pretrain/Loss (Raw)": 2.181277275085449, "Pretrain/Step": 8726, "Pretrain/Step Time": 8.48024646192789} +{"Pretrain/Learning Rate": 9.377550047677541e-07, "Pretrain/Loss": 1.9894195795059204, "Pretrain/Loss (Raw)": 1.9383357763290405, "Pretrain/Step": 8727, "Pretrain/Step Time": 8.484682332724333} +{"Pretrain/Learning Rate": 9.354526893017191e-07, "Pretrain/Loss": 1.9887759685516357, "Pretrain/Loss (Raw)": 1.9393994808197021, "Pretrain/Step": 8728, "Pretrain/Step Time": 8.482878398150206} +{"Pretrain/Learning Rate": 9.331531496727635e-07, "Pretrain/Loss": 1.9899001121520996, "Pretrain/Loss (Raw)": 2.080348491668701, "Pretrain/Step": 8729, "Pretrain/Step Time": 8.482886850833893} +{"Pretrain/Learning Rate": 9.308563861461311e-07, "Pretrain/Loss": 1.990694284439087, "Pretrain/Loss (Raw)": 1.9669915437698364, "Pretrain/Step": 8730, "Pretrain/Step Time": 8.483194947242737} +{"Pretrain/Learning Rate": 9.285623989867543e-07, "Pretrain/Loss": 1.992509365081787, "Pretrain/Loss (Raw)": 2.113464117050171, "Pretrain/Step": 8731, "Pretrain/Step Time": 8.478952541947365} +{"Pretrain/Learning Rate": 9.262711884592462e-07, "Pretrain/Loss": 1.9915679693222046, "Pretrain/Loss (Raw)": 1.8768014907836914, "Pretrain/Step": 8732, "Pretrain/Step Time": 8.477371698245406} +{"Pretrain/Learning Rate": 9.239827548278985e-07, "Pretrain/Loss": 1.9905776977539062, "Pretrain/Loss (Raw)": 1.9254014492034912, "Pretrain/Step": 8733, "Pretrain/Step Time": 8.480591889470816} +{"Pretrain/Learning Rate": 9.216970983566802e-07, "Pretrain/Loss": 1.990025520324707, "Pretrain/Loss (Raw)": 1.9875017404556274, "Pretrain/Step": 8734, "Pretrain/Step Time": 8.4787987601012} +{"Pretrain/Learning Rate": 9.194142193092392e-07, "Pretrain/Loss": 1.9920227527618408, "Pretrain/Loss (Raw)": 2.0966668128967285, "Pretrain/Step": 8735, "Pretrain/Step Time": 8.478619115427136} +{"Pretrain/Learning Rate": 9.171341179489034e-07, "Pretrain/Loss": 1.9939579963684082, "Pretrain/Loss (Raw)": 2.0744285583496094, "Pretrain/Step": 8736, "Pretrain/Step Time": 8.480721082538366} +{"Pretrain/Learning Rate": 9.148567945386849e-07, "Pretrain/Loss": 1.9922406673431396, "Pretrain/Loss (Raw)": 1.7589000463485718, "Pretrain/Step": 8737, "Pretrain/Step Time": 8.481751976534724} +{"Pretrain/Learning Rate": 9.125822493412678e-07, "Pretrain/Loss": 1.9933390617370605, "Pretrain/Loss (Raw)": 2.042893886566162, "Pretrain/Step": 8738, "Pretrain/Step Time": 8.483048565685749} +{"Pretrain/Learning Rate": 9.103104826190312e-07, "Pretrain/Loss": 1.9944424629211426, "Pretrain/Loss (Raw)": 2.1176421642303467, "Pretrain/Step": 8739, "Pretrain/Step Time": 8.48932341299951} +{"Pretrain/Learning Rate": 9.080414946340071e-07, "Pretrain/Loss": 1.9961955547332764, "Pretrain/Loss (Raw)": 2.1609082221984863, "Pretrain/Step": 8740, "Pretrain/Step Time": 8.487977050244808} +{"Pretrain/Learning Rate": 9.057752856479363e-07, "Pretrain/Loss": 1.9961419105529785, "Pretrain/Loss (Raw)": 2.054962158203125, "Pretrain/Step": 8741, "Pretrain/Step Time": 8.484826179221272} +{"Pretrain/Learning Rate": 9.03511855922215e-07, "Pretrain/Loss": 1.9958800077438354, "Pretrain/Loss (Raw)": 1.9855284690856934, "Pretrain/Step": 8742, "Pretrain/Step Time": 8.485906945541501} +{"Pretrain/Learning Rate": 9.012512057179345e-07, "Pretrain/Loss": 1.9966473579406738, "Pretrain/Loss (Raw)": 1.9838805198669434, "Pretrain/Step": 8743, "Pretrain/Step Time": 8.48584945499897} +{"Pretrain/Learning Rate": 8.989933352958558e-07, "Pretrain/Loss": 1.9963858127593994, "Pretrain/Loss (Raw)": 2.1554481983184814, "Pretrain/Step": 8744, "Pretrain/Step Time": 8.486076410859823} +{"Pretrain/Learning Rate": 8.967382449164314e-07, "Pretrain/Loss": 1.995666742324829, "Pretrain/Loss (Raw)": 1.9757031202316284, "Pretrain/Step": 8745, "Pretrain/Step Time": 8.484222255647182} +{"Pretrain/Learning Rate": 8.944859348397755e-07, "Pretrain/Loss": 1.9970788955688477, "Pretrain/Loss (Raw)": 2.222153902053833, "Pretrain/Step": 8746, "Pretrain/Step Time": 8.485868891701102} +{"Pretrain/Learning Rate": 8.922364053256971e-07, "Pretrain/Loss": 1.99711012840271, "Pretrain/Loss (Raw)": 2.104954242706299, "Pretrain/Step": 8747, "Pretrain/Step Time": 8.485772166401148} +{"Pretrain/Learning Rate": 8.899896566336746e-07, "Pretrain/Loss": 1.9972511529922485, "Pretrain/Loss (Raw)": 2.0277280807495117, "Pretrain/Step": 8748, "Pretrain/Step Time": 8.48246318474412} +{"Pretrain/Learning Rate": 8.877456890228758e-07, "Pretrain/Loss": 1.9969236850738525, "Pretrain/Loss (Raw)": 2.037773609161377, "Pretrain/Step": 8749, "Pretrain/Step Time": 8.482059184461832} +{"Pretrain/Learning Rate": 8.85504502752138e-07, "Pretrain/Loss": 1.9972745180130005, "Pretrain/Loss (Raw)": 2.0109708309173584, "Pretrain/Step": 8750, "Pretrain/Step Time": 8.481064012274146} +{"Pretrain/Learning Rate": 8.832660980799795e-07, "Pretrain/Loss": 1.9981435537338257, "Pretrain/Loss (Raw)": 1.862410545349121, "Pretrain/Step": 8751, "Pretrain/Step Time": 8.477763511240482} +{"Pretrain/Learning Rate": 8.81030475264602e-07, "Pretrain/Loss": 1.9982068538665771, "Pretrain/Loss (Raw)": 2.076842784881592, "Pretrain/Step": 8752, "Pretrain/Step Time": 8.477175744250417} +{"Pretrain/Learning Rate": 8.787976345638826e-07, "Pretrain/Loss": 1.9982409477233887, "Pretrain/Loss (Raw)": 1.978560447692871, "Pretrain/Step": 8753, "Pretrain/Step Time": 8.475759651511908} +{"Pretrain/Learning Rate": 8.76567576235382e-07, "Pretrain/Loss": 1.9971635341644287, "Pretrain/Loss (Raw)": 1.9278886318206787, "Pretrain/Step": 8754, "Pretrain/Step Time": 8.481418522074819} +{"Pretrain/Learning Rate": 8.743403005363332e-07, "Pretrain/Loss": 1.996814250946045, "Pretrain/Loss (Raw)": 1.979516863822937, "Pretrain/Step": 8755, "Pretrain/Step Time": 8.481083955615759} +{"Pretrain/Learning Rate": 8.721158077236503e-07, "Pretrain/Loss": 1.9977450370788574, "Pretrain/Loss (Raw)": 2.045250415802002, "Pretrain/Step": 8756, "Pretrain/Step Time": 8.482947964221239} +{"Pretrain/Learning Rate": 8.698940980539332e-07, "Pretrain/Loss": 1.9969693422317505, "Pretrain/Loss (Raw)": 1.9362388849258423, "Pretrain/Step": 8757, "Pretrain/Step Time": 8.481340790167451} +{"Pretrain/Learning Rate": 8.676751717834497e-07, "Pretrain/Loss": 1.9951666593551636, "Pretrain/Loss (Raw)": 1.582422137260437, "Pretrain/Step": 8758, "Pretrain/Step Time": 8.48444077372551} +{"Pretrain/Learning Rate": 8.65459029168153e-07, "Pretrain/Loss": 1.997600793838501, "Pretrain/Loss (Raw)": 1.8350286483764648, "Pretrain/Step": 8759, "Pretrain/Step Time": 8.483561560511589} +{"Pretrain/Learning Rate": 8.632456704636805e-07, "Pretrain/Loss": 1.9966318607330322, "Pretrain/Loss (Raw)": 1.855655312538147, "Pretrain/Step": 8760, "Pretrain/Step Time": 8.482027335092425} +{"Pretrain/Learning Rate": 8.610350959253332e-07, "Pretrain/Loss": 1.9957292079925537, "Pretrain/Loss (Raw)": 1.8751596212387085, "Pretrain/Step": 8761, "Pretrain/Step Time": 8.481521358713508} +{"Pretrain/Learning Rate": 8.588273058081048e-07, "Pretrain/Loss": 1.9936814308166504, "Pretrain/Loss (Raw)": 1.7583513259887695, "Pretrain/Step": 8762, "Pretrain/Step Time": 8.482229933142662} +{"Pretrain/Learning Rate": 8.566223003666635e-07, "Pretrain/Loss": 1.9932646751403809, "Pretrain/Loss (Raw)": 1.8893147706985474, "Pretrain/Step": 8763, "Pretrain/Step Time": 8.487039014697075} +{"Pretrain/Learning Rate": 8.544200798553559e-07, "Pretrain/Loss": 1.9924694299697876, "Pretrain/Loss (Raw)": 2.0217249393463135, "Pretrain/Step": 8764, "Pretrain/Step Time": 8.484200732782483} +{"Pretrain/Learning Rate": 8.522206445282038e-07, "Pretrain/Loss": 1.9932116270065308, "Pretrain/Loss (Raw)": 2.091519594192505, "Pretrain/Step": 8765, "Pretrain/Step Time": 8.48367672227323} +{"Pretrain/Learning Rate": 8.50023994638921e-07, "Pretrain/Loss": 1.9918054342269897, "Pretrain/Loss (Raw)": 1.916049599647522, "Pretrain/Step": 8766, "Pretrain/Step Time": 8.48342796601355} +{"Pretrain/Learning Rate": 8.47830130440877e-07, "Pretrain/Loss": 1.9930318593978882, "Pretrain/Loss (Raw)": 2.1313834190368652, "Pretrain/Step": 8767, "Pretrain/Step Time": 8.482173597440124} +{"Pretrain/Learning Rate": 8.456390521871415e-07, "Pretrain/Loss": 1.9944716691970825, "Pretrain/Loss (Raw)": 1.941100835800171, "Pretrain/Step": 8768, "Pretrain/Step Time": 8.482733234763145} +{"Pretrain/Learning Rate": 8.434507601304542e-07, "Pretrain/Loss": 1.9927994012832642, "Pretrain/Loss (Raw)": 1.797937273979187, "Pretrain/Step": 8769, "Pretrain/Step Time": 8.486441373825073} +{"Pretrain/Learning Rate": 8.412652545232324e-07, "Pretrain/Loss": 1.9942594766616821, "Pretrain/Loss (Raw)": 2.1145384311676025, "Pretrain/Step": 8770, "Pretrain/Step Time": 8.483956955373287} +{"Pretrain/Learning Rate": 8.390825356175747e-07, "Pretrain/Loss": 1.9934190511703491, "Pretrain/Loss (Raw)": 2.0279381275177, "Pretrain/Step": 8771, "Pretrain/Step Time": 8.486645985394716} +{"Pretrain/Learning Rate": 8.369026036652516e-07, "Pretrain/Loss": 1.9929132461547852, "Pretrain/Loss (Raw)": 2.050572156906128, "Pretrain/Step": 8772, "Pretrain/Step Time": 8.488373590633273} +{"Pretrain/Learning Rate": 8.347254589177234e-07, "Pretrain/Loss": 1.993999719619751, "Pretrain/Loss (Raw)": 2.132392406463623, "Pretrain/Step": 8773, "Pretrain/Step Time": 8.489797681570053} +{"Pretrain/Learning Rate": 8.32551101626125e-07, "Pretrain/Loss": 1.994152545928955, "Pretrain/Loss (Raw)": 1.9832686185836792, "Pretrain/Step": 8774, "Pretrain/Step Time": 8.484666028991342} +{"Pretrain/Learning Rate": 8.303795320412616e-07, "Pretrain/Loss": 1.9925248622894287, "Pretrain/Loss (Raw)": 2.0426290035247803, "Pretrain/Step": 8775, "Pretrain/Step Time": 8.488950913771987} +{"Pretrain/Learning Rate": 8.282107504136271e-07, "Pretrain/Loss": 1.9902465343475342, "Pretrain/Loss (Raw)": 1.8264464139938354, "Pretrain/Step": 8776, "Pretrain/Step Time": 8.485608153045177} +{"Pretrain/Learning Rate": 8.260447569933827e-07, "Pretrain/Loss": 1.9909851551055908, "Pretrain/Loss (Raw)": 2.0216357707977295, "Pretrain/Step": 8777, "Pretrain/Step Time": 8.481839906424284} +{"Pretrain/Learning Rate": 8.238815520303839e-07, "Pretrain/Loss": 1.9918932914733887, "Pretrain/Loss (Raw)": 1.998475193977356, "Pretrain/Step": 8778, "Pretrain/Step Time": 8.486325880512595} +{"Pretrain/Learning Rate": 8.217211357741505e-07, "Pretrain/Loss": 1.989803671836853, "Pretrain/Loss (Raw)": 1.877419114112854, "Pretrain/Step": 8779, "Pretrain/Step Time": 8.488600442185998} +{"Pretrain/Learning Rate": 8.195635084738862e-07, "Pretrain/Loss": 1.983280897140503, "Pretrain/Loss (Raw)": 1.4102778434753418, "Pretrain/Step": 8780, "Pretrain/Step Time": 8.48916944116354} +{"Pretrain/Learning Rate": 8.174086703784778e-07, "Pretrain/Loss": 1.9822757244110107, "Pretrain/Loss (Raw)": 1.9435415267944336, "Pretrain/Step": 8781, "Pretrain/Step Time": 8.489484889432788} +{"Pretrain/Learning Rate": 8.152566217364793e-07, "Pretrain/Loss": 1.9818577766418457, "Pretrain/Loss (Raw)": 1.8754041194915771, "Pretrain/Step": 8782, "Pretrain/Step Time": 8.488338578492403} +{"Pretrain/Learning Rate": 8.131073627961283e-07, "Pretrain/Loss": 1.9817187786102295, "Pretrain/Loss (Raw)": 2.1210572719573975, "Pretrain/Step": 8783, "Pretrain/Step Time": 8.485384531319141} +{"Pretrain/Learning Rate": 8.109608938053431e-07, "Pretrain/Loss": 1.9824812412261963, "Pretrain/Loss (Raw)": 2.073240280151367, "Pretrain/Step": 8784, "Pretrain/Step Time": 8.484678413718939} +{"Pretrain/Learning Rate": 8.088172150117202e-07, "Pretrain/Loss": 1.9835600852966309, "Pretrain/Loss (Raw)": 1.97686767578125, "Pretrain/Step": 8785, "Pretrain/Step Time": 8.48591679148376} +{"Pretrain/Learning Rate": 8.066763266625282e-07, "Pretrain/Loss": 1.983365535736084, "Pretrain/Loss (Raw)": 2.0275583267211914, "Pretrain/Step": 8786, "Pretrain/Step Time": 8.485167810693383} +{"Pretrain/Learning Rate": 8.045382290047227e-07, "Pretrain/Loss": 1.9822746515274048, "Pretrain/Loss (Raw)": 1.8652887344360352, "Pretrain/Step": 8787, "Pretrain/Step Time": 8.482158079743385} +{"Pretrain/Learning Rate": 8.024029222849283e-07, "Pretrain/Loss": 1.981955647468567, "Pretrain/Loss (Raw)": 1.969915509223938, "Pretrain/Step": 8788, "Pretrain/Step Time": 8.480696681886911} +{"Pretrain/Learning Rate": 8.002704067494509e-07, "Pretrain/Loss": 1.981579065322876, "Pretrain/Loss (Raw)": 1.9391859769821167, "Pretrain/Step": 8789, "Pretrain/Step Time": 8.483310092240572} +{"Pretrain/Learning Rate": 7.981406826442828e-07, "Pretrain/Loss": 1.9822373390197754, "Pretrain/Loss (Raw)": 2.012732744216919, "Pretrain/Step": 8790, "Pretrain/Step Time": 8.48394499719143} +{"Pretrain/Learning Rate": 7.960137502150772e-07, "Pretrain/Loss": 1.983462929725647, "Pretrain/Loss (Raw)": 2.045109272003174, "Pretrain/Step": 8791, "Pretrain/Step Time": 8.48299460299313} +{"Pretrain/Learning Rate": 7.938896097071824e-07, "Pretrain/Loss": 1.983088493347168, "Pretrain/Loss (Raw)": 1.9908937215805054, "Pretrain/Step": 8792, "Pretrain/Step Time": 8.48331774584949} +{"Pretrain/Learning Rate": 7.917682613656136e-07, "Pretrain/Loss": 1.9856882095336914, "Pretrain/Loss (Raw)": 2.1769886016845703, "Pretrain/Step": 8793, "Pretrain/Step Time": 8.47977800667286} +{"Pretrain/Learning Rate": 7.896497054350665e-07, "Pretrain/Loss": 1.9847160577774048, "Pretrain/Loss (Raw)": 2.019286870956421, "Pretrain/Step": 8794, "Pretrain/Step Time": 8.480695340782404} +{"Pretrain/Learning Rate": 7.875339421599182e-07, "Pretrain/Loss": 1.9858943223953247, "Pretrain/Loss (Raw)": 1.9573614597320557, "Pretrain/Step": 8795, "Pretrain/Step Time": 8.483658896759152} +{"Pretrain/Learning Rate": 7.854209717842231e-07, "Pretrain/Loss": 1.9843651056289673, "Pretrain/Loss (Raw)": 1.9447041749954224, "Pretrain/Step": 8796, "Pretrain/Step Time": 8.478001452982426} +{"Pretrain/Learning Rate": 7.833107945517087e-07, "Pretrain/Loss": 1.983286738395691, "Pretrain/Loss (Raw)": 1.965213656425476, "Pretrain/Step": 8797, "Pretrain/Step Time": 8.48020450770855} +{"Pretrain/Learning Rate": 7.81203410705783e-07, "Pretrain/Loss": 1.9833862781524658, "Pretrain/Loss (Raw)": 2.121199607849121, "Pretrain/Step": 8798, "Pretrain/Step Time": 8.4815557859838} +{"Pretrain/Learning Rate": 7.790988204895323e-07, "Pretrain/Loss": 1.983825922012329, "Pretrain/Loss (Raw)": 2.085416555404663, "Pretrain/Step": 8799, "Pretrain/Step Time": 8.48118682205677} +{"Pretrain/Learning Rate": 7.769970241457203e-07, "Pretrain/Loss": 1.9835885763168335, "Pretrain/Loss (Raw)": 2.016066789627075, "Pretrain/Step": 8800, "Pretrain/Step Time": 8.482803981751204} +{"Pretrain/Learning Rate": 7.748980219167895e-07, "Pretrain/Loss": 1.983965277671814, "Pretrain/Loss (Raw)": 2.1351001262664795, "Pretrain/Step": 8801, "Pretrain/Step Time": 8.480378922075033} +{"Pretrain/Learning Rate": 7.728018140448628e-07, "Pretrain/Loss": 1.9839131832122803, "Pretrain/Loss (Raw)": 2.000645399093628, "Pretrain/Step": 8802, "Pretrain/Step Time": 8.48331767693162} +{"Pretrain/Learning Rate": 7.707084007717274e-07, "Pretrain/Loss": 1.983161449432373, "Pretrain/Loss (Raw)": 1.6334261894226074, "Pretrain/Step": 8803, "Pretrain/Step Time": 8.482581021264195} +{"Pretrain/Learning Rate": 7.686177823388651e-07, "Pretrain/Loss": 1.983440637588501, "Pretrain/Loss (Raw)": 2.111227035522461, "Pretrain/Step": 8804, "Pretrain/Step Time": 8.485905351117253} +{"Pretrain/Learning Rate": 7.665299589874248e-07, "Pretrain/Loss": 1.982081413269043, "Pretrain/Loss (Raw)": 1.9111928939819336, "Pretrain/Step": 8805, "Pretrain/Step Time": 8.486879961565137} +{"Pretrain/Learning Rate": 7.644449309582385e-07, "Pretrain/Loss": 1.9832634925842285, "Pretrain/Loss (Raw)": 2.1503965854644775, "Pretrain/Step": 8806, "Pretrain/Step Time": 8.485444463789463} +{"Pretrain/Learning Rate": 7.623626984918142e-07, "Pretrain/Loss": 1.9835307598114014, "Pretrain/Loss (Raw)": 2.032001256942749, "Pretrain/Step": 8807, "Pretrain/Step Time": 8.484228007495403} +{"Pretrain/Learning Rate": 7.602832618283346e-07, "Pretrain/Loss": 1.9817533493041992, "Pretrain/Loss (Raw)": 1.9048677682876587, "Pretrain/Step": 8808, "Pretrain/Step Time": 8.48622496984899} +{"Pretrain/Learning Rate": 7.582066212076632e-07, "Pretrain/Loss": 1.9796857833862305, "Pretrain/Loss (Raw)": 1.9105377197265625, "Pretrain/Step": 8809, "Pretrain/Step Time": 8.48630646802485} +{"Pretrain/Learning Rate": 7.561327768693366e-07, "Pretrain/Loss": 1.9793952703475952, "Pretrain/Loss (Raw)": 1.9920413494110107, "Pretrain/Step": 8810, "Pretrain/Step Time": 8.482503866776824} +{"Pretrain/Learning Rate": 7.540617290525743e-07, "Pretrain/Loss": 1.9802520275115967, "Pretrain/Loss (Raw)": 2.1290581226348877, "Pretrain/Step": 8811, "Pretrain/Step Time": 8.482883187010884} +{"Pretrain/Learning Rate": 7.519934779962684e-07, "Pretrain/Loss": 1.9783363342285156, "Pretrain/Loss (Raw)": 1.8566646575927734, "Pretrain/Step": 8812, "Pretrain/Step Time": 8.483594972640276} +{"Pretrain/Learning Rate": 7.499280239389978e-07, "Pretrain/Loss": 1.9786934852600098, "Pretrain/Loss (Raw)": 2.018294334411621, "Pretrain/Step": 8813, "Pretrain/Step Time": 8.488120265305042} +{"Pretrain/Learning Rate": 7.478653671190078e-07, "Pretrain/Loss": 1.979315996170044, "Pretrain/Loss (Raw)": 2.0130181312561035, "Pretrain/Step": 8814, "Pretrain/Step Time": 8.485269833356142} +{"Pretrain/Learning Rate": 7.458055077742221e-07, "Pretrain/Loss": 1.9795360565185547, "Pretrain/Loss (Raw)": 2.007286548614502, "Pretrain/Step": 8815, "Pretrain/Step Time": 8.486051367595792} +{"Pretrain/Learning Rate": 7.437484461422478e-07, "Pretrain/Loss": 1.97792387008667, "Pretrain/Loss (Raw)": 1.7877620458602905, "Pretrain/Step": 8816, "Pretrain/Step Time": 8.486529314890504} +{"Pretrain/Learning Rate": 7.416941824603646e-07, "Pretrain/Loss": 1.977656364440918, "Pretrain/Loss (Raw)": 1.9450393915176392, "Pretrain/Step": 8817, "Pretrain/Step Time": 8.487254718318582} +{"Pretrain/Learning Rate": 7.396427169655384e-07, "Pretrain/Loss": 1.9777719974517822, "Pretrain/Loss (Raw)": 1.87172532081604, "Pretrain/Step": 8818, "Pretrain/Step Time": 8.483417317271233} +{"Pretrain/Learning Rate": 7.37594049894394e-07, "Pretrain/Loss": 1.9781420230865479, "Pretrain/Loss (Raw)": 2.128650426864624, "Pretrain/Step": 8819, "Pretrain/Step Time": 8.492134997621179} +{"Pretrain/Learning Rate": 7.355481814832505e-07, "Pretrain/Loss": 1.9774199724197388, "Pretrain/Loss (Raw)": 1.9627957344055176, "Pretrain/Step": 8820, "Pretrain/Step Time": 8.490431634709239} +{"Pretrain/Learning Rate": 7.335051119680969e-07, "Pretrain/Loss": 1.9777354001998901, "Pretrain/Loss (Raw)": 2.0152952671051025, "Pretrain/Step": 8821, "Pretrain/Step Time": 8.488060783594847} +{"Pretrain/Learning Rate": 7.314648415846004e-07, "Pretrain/Loss": 1.9753022193908691, "Pretrain/Loss (Raw)": 1.817649245262146, "Pretrain/Step": 8822, "Pretrain/Step Time": 8.488440122455359} +{"Pretrain/Learning Rate": 7.294273705681087e-07, "Pretrain/Loss": 1.9756618738174438, "Pretrain/Loss (Raw)": 2.0399675369262695, "Pretrain/Step": 8823, "Pretrain/Step Time": 8.485996451228857} +{"Pretrain/Learning Rate": 7.273926991536367e-07, "Pretrain/Loss": 1.9763357639312744, "Pretrain/Loss (Raw)": 2.0220112800598145, "Pretrain/Step": 8824, "Pretrain/Step Time": 8.485588351264596} +{"Pretrain/Learning Rate": 7.253608275758911e-07, "Pretrain/Loss": 1.9782655239105225, "Pretrain/Loss (Raw)": 2.060534715652466, "Pretrain/Step": 8825, "Pretrain/Step Time": 8.484948655590415} +{"Pretrain/Learning Rate": 7.233317560692426e-07, "Pretrain/Loss": 1.9788322448730469, "Pretrain/Loss (Raw)": 2.037867307662964, "Pretrain/Step": 8826, "Pretrain/Step Time": 8.488220438361168} +{"Pretrain/Learning Rate": 7.213054848677403e-07, "Pretrain/Loss": 1.9809527397155762, "Pretrain/Loss (Raw)": 1.995113492012024, "Pretrain/Step": 8827, "Pretrain/Step Time": 8.485831499099731} +{"Pretrain/Learning Rate": 7.192820142051221e-07, "Pretrain/Loss": 1.9801080226898193, "Pretrain/Loss (Raw)": 1.9861578941345215, "Pretrain/Step": 8828, "Pretrain/Step Time": 8.484311083331704} +{"Pretrain/Learning Rate": 7.172613443147902e-07, "Pretrain/Loss": 1.9802098274230957, "Pretrain/Loss (Raw)": 2.049362897872925, "Pretrain/Step": 8829, "Pretrain/Step Time": 8.48128898255527} +{"Pretrain/Learning Rate": 7.152434754298276e-07, "Pretrain/Loss": 1.9786994457244873, "Pretrain/Loss (Raw)": 1.7332074642181396, "Pretrain/Step": 8830, "Pretrain/Step Time": 8.480513477697968} +{"Pretrain/Learning Rate": 7.132284077829954e-07, "Pretrain/Loss": 1.9790432453155518, "Pretrain/Loss (Raw)": 2.015418291091919, "Pretrain/Step": 8831, "Pretrain/Step Time": 8.477821253240108} +{"Pretrain/Learning Rate": 7.112161416067325e-07, "Pretrain/Loss": 1.9801912307739258, "Pretrain/Loss (Raw)": 2.1617188453674316, "Pretrain/Step": 8832, "Pretrain/Step Time": 8.477331826463342} +{"Pretrain/Learning Rate": 7.092066771331507e-07, "Pretrain/Loss": 1.9803266525268555, "Pretrain/Loss (Raw)": 2.034942865371704, "Pretrain/Step": 8833, "Pretrain/Step Time": 8.478540755808353} +{"Pretrain/Learning Rate": 7.07200014594045e-07, "Pretrain/Loss": 1.9800827503204346, "Pretrain/Loss (Raw)": 1.9001359939575195, "Pretrain/Step": 8834, "Pretrain/Step Time": 8.477806009352207} +{"Pretrain/Learning Rate": 7.051961542208801e-07, "Pretrain/Loss": 1.9816150665283203, "Pretrain/Loss (Raw)": 2.0950076580047607, "Pretrain/Step": 8835, "Pretrain/Step Time": 8.48302979581058} +{"Pretrain/Learning Rate": 7.031950962447992e-07, "Pretrain/Loss": 1.9794740676879883, "Pretrain/Loss (Raw)": 1.7853256464004517, "Pretrain/Step": 8836, "Pretrain/Step Time": 8.484247168526053} +{"Pretrain/Learning Rate": 7.011968408966257e-07, "Pretrain/Loss": 1.9786808490753174, "Pretrain/Loss (Raw)": 1.8754853010177612, "Pretrain/Step": 8837, "Pretrain/Step Time": 8.486631006002426} +{"Pretrain/Learning Rate": 6.99201388406856e-07, "Pretrain/Loss": 1.9785664081573486, "Pretrain/Loss (Raw)": 2.0004425048828125, "Pretrain/Step": 8838, "Pretrain/Step Time": 8.487276123836637} +{"Pretrain/Learning Rate": 6.972087390056697e-07, "Pretrain/Loss": 1.9789180755615234, "Pretrain/Loss (Raw)": 2.1253693103790283, "Pretrain/Step": 8839, "Pretrain/Step Time": 8.484871653839946} +{"Pretrain/Learning Rate": 6.952188929229136e-07, "Pretrain/Loss": 1.9780783653259277, "Pretrain/Loss (Raw)": 1.8883895874023438, "Pretrain/Step": 8840, "Pretrain/Step Time": 8.485153641551733} +{"Pretrain/Learning Rate": 6.93231850388118e-07, "Pretrain/Loss": 1.9781150817871094, "Pretrain/Loss (Raw)": 2.0155935287475586, "Pretrain/Step": 8841, "Pretrain/Step Time": 8.485575970262289} +{"Pretrain/Learning Rate": 6.912476116304828e-07, "Pretrain/Loss": 1.9780899286270142, "Pretrain/Loss (Raw)": 1.866483449935913, "Pretrain/Step": 8842, "Pretrain/Step Time": 8.488864623010159} +{"Pretrain/Learning Rate": 6.892661768788944e-07, "Pretrain/Loss": 1.9799659252166748, "Pretrain/Loss (Raw)": 1.9101351499557495, "Pretrain/Step": 8843, "Pretrain/Step Time": 8.487837949767709} +{"Pretrain/Learning Rate": 6.872875463619088e-07, "Pretrain/Loss": 1.9802870750427246, "Pretrain/Loss (Raw)": 1.9413352012634277, "Pretrain/Step": 8844, "Pretrain/Step Time": 8.487129731103778} +{"Pretrain/Learning Rate": 6.853117203077658e-07, "Pretrain/Loss": 1.981411337852478, "Pretrain/Loss (Raw)": 2.0091185569763184, "Pretrain/Step": 8845, "Pretrain/Step Time": 8.486357059329748} +{"Pretrain/Learning Rate": 6.833386989443636e-07, "Pretrain/Loss": 1.9818180799484253, "Pretrain/Loss (Raw)": 1.9485342502593994, "Pretrain/Step": 8846, "Pretrain/Step Time": 8.485678980126977} +{"Pretrain/Learning Rate": 6.813684824993005e-07, "Pretrain/Loss": 1.98469877243042, "Pretrain/Loss (Raw)": 2.057328939437866, "Pretrain/Step": 8847, "Pretrain/Step Time": 8.48528292402625} +{"Pretrain/Learning Rate": 6.794010711998366e-07, "Pretrain/Loss": 1.9852304458618164, "Pretrain/Loss (Raw)": 1.9578150510787964, "Pretrain/Step": 8848, "Pretrain/Step Time": 8.486967535689473} +{"Pretrain/Learning Rate": 6.774364652729098e-07, "Pretrain/Loss": 1.985093116760254, "Pretrain/Loss (Raw)": 2.0682125091552734, "Pretrain/Step": 8849, "Pretrain/Step Time": 8.48351164162159} +{"Pretrain/Learning Rate": 6.754746649451444e-07, "Pretrain/Loss": 1.9858100414276123, "Pretrain/Loss (Raw)": 2.156830310821533, "Pretrain/Step": 8850, "Pretrain/Step Time": 8.485412668436766} +{"Pretrain/Learning Rate": 6.735156704428258e-07, "Pretrain/Loss": 1.9869883060455322, "Pretrain/Loss (Raw)": 2.400425910949707, "Pretrain/Step": 8851, "Pretrain/Step Time": 8.486587028950453} +{"Pretrain/Learning Rate": 6.715594819919236e-07, "Pretrain/Loss": 1.9880352020263672, "Pretrain/Loss (Raw)": 2.101402521133423, "Pretrain/Step": 8852, "Pretrain/Step Time": 8.4851557854563} +{"Pretrain/Learning Rate": 6.696060998180875e-07, "Pretrain/Loss": 1.9891571998596191, "Pretrain/Loss (Raw)": 2.102712392807007, "Pretrain/Step": 8853, "Pretrain/Step Time": 8.489071764051914} +{"Pretrain/Learning Rate": 6.676555241466347e-07, "Pretrain/Loss": 1.9872560501098633, "Pretrain/Loss (Raw)": 1.937949776649475, "Pretrain/Step": 8854, "Pretrain/Step Time": 8.49099699407816} +{"Pretrain/Learning Rate": 6.657077552025714e-07, "Pretrain/Loss": 1.9877744913101196, "Pretrain/Loss (Raw)": 2.004678249359131, "Pretrain/Step": 8855, "Pretrain/Step Time": 8.487913032993674} +{"Pretrain/Learning Rate": 6.637627932105623e-07, "Pretrain/Loss": 1.9866390228271484, "Pretrain/Loss (Raw)": 1.7940689325332642, "Pretrain/Step": 8856, "Pretrain/Step Time": 8.487382421270013} +{"Pretrain/Learning Rate": 6.618206383949638e-07, "Pretrain/Loss": 1.9866435527801514, "Pretrain/Loss (Raw)": 2.0809226036071777, "Pretrain/Step": 8857, "Pretrain/Step Time": 8.489880487322807} +{"Pretrain/Learning Rate": 6.598812909798052e-07, "Pretrain/Loss": 1.9857548475265503, "Pretrain/Loss (Raw)": 1.8532382249832153, "Pretrain/Step": 8858, "Pretrain/Step Time": 8.490108961239457} +{"Pretrain/Learning Rate": 6.579447511887826e-07, "Pretrain/Loss": 1.9857999086380005, "Pretrain/Loss (Raw)": 2.119239330291748, "Pretrain/Step": 8859, "Pretrain/Step Time": 8.486536709591746} +{"Pretrain/Learning Rate": 6.560110192452812e-07, "Pretrain/Loss": 1.9859390258789062, "Pretrain/Loss (Raw)": 1.8946027755737305, "Pretrain/Step": 8860, "Pretrain/Step Time": 8.48712576366961} +{"Pretrain/Learning Rate": 6.540800953723503e-07, "Pretrain/Loss": 1.9867504835128784, "Pretrain/Loss (Raw)": 2.029268264770508, "Pretrain/Step": 8861, "Pretrain/Step Time": 8.483543684706092} +{"Pretrain/Learning Rate": 6.521519797927256e-07, "Pretrain/Loss": 1.9869505167007446, "Pretrain/Loss (Raw)": 2.0131044387817383, "Pretrain/Step": 8862, "Pretrain/Step Time": 8.484891921281815} +{"Pretrain/Learning Rate": 6.502266727288126e-07, "Pretrain/Loss": 1.984562873840332, "Pretrain/Loss (Raw)": 1.7910553216934204, "Pretrain/Step": 8863, "Pretrain/Step Time": 8.48113713413477} +{"Pretrain/Learning Rate": 6.483041744026946e-07, "Pretrain/Loss": 1.9845967292785645, "Pretrain/Loss (Raw)": 2.0787546634674072, "Pretrain/Step": 8864, "Pretrain/Step Time": 8.478835437446833} +{"Pretrain/Learning Rate": 6.463844850361361e-07, "Pretrain/Loss": 1.9864425659179688, "Pretrain/Loss (Raw)": 1.9951810836791992, "Pretrain/Step": 8865, "Pretrain/Step Time": 8.482113465666771} +{"Pretrain/Learning Rate": 6.444676048505682e-07, "Pretrain/Loss": 1.9856404066085815, "Pretrain/Loss (Raw)": 1.9402000904083252, "Pretrain/Step": 8866, "Pretrain/Step Time": 8.479464141651988} +{"Pretrain/Learning Rate": 6.425535340671002e-07, "Pretrain/Loss": 1.9850246906280518, "Pretrain/Loss (Raw)": 2.0388424396514893, "Pretrain/Step": 8867, "Pretrain/Step Time": 8.478330364450812} +{"Pretrain/Learning Rate": 6.406422729065248e-07, "Pretrain/Loss": 1.9842063188552856, "Pretrain/Loss (Raw)": 2.0561535358428955, "Pretrain/Step": 8868, "Pretrain/Step Time": 8.47737242281437} +{"Pretrain/Learning Rate": 6.387338215893019e-07, "Pretrain/Loss": 1.9823510646820068, "Pretrain/Loss (Raw)": 1.8174854516983032, "Pretrain/Step": 8869, "Pretrain/Step Time": 8.479848098009825} +{"Pretrain/Learning Rate": 6.368281803355691e-07, "Pretrain/Loss": 1.9823867082595825, "Pretrain/Loss (Raw)": 1.9900866746902466, "Pretrain/Step": 8870, "Pretrain/Step Time": 8.478138156235218} +{"Pretrain/Learning Rate": 6.349253493651508e-07, "Pretrain/Loss": 1.9819446802139282, "Pretrain/Loss (Raw)": 1.9273018836975098, "Pretrain/Step": 8871, "Pretrain/Step Time": 8.47829126380384} +{"Pretrain/Learning Rate": 6.33025328897524e-07, "Pretrain/Loss": 1.9804272651672363, "Pretrain/Loss (Raw)": 1.9612152576446533, "Pretrain/Step": 8872, "Pretrain/Step Time": 8.477819748222828} +{"Pretrain/Learning Rate": 6.311281191518636e-07, "Pretrain/Loss": 1.9810099601745605, "Pretrain/Loss (Raw)": 2.050294876098633, "Pretrain/Step": 8873, "Pretrain/Step Time": 8.478225711733103} +{"Pretrain/Learning Rate": 6.292337203470139e-07, "Pretrain/Loss": 1.9780864715576172, "Pretrain/Loss (Raw)": 1.847941279411316, "Pretrain/Step": 8874, "Pretrain/Step Time": 8.480923315510154} +{"Pretrain/Learning Rate": 6.273421327014889e-07, "Pretrain/Loss": 1.9756057262420654, "Pretrain/Loss (Raw)": 1.7874243259429932, "Pretrain/Step": 8875, "Pretrain/Step Time": 8.478333294391632} +{"Pretrain/Learning Rate": 6.254533564334863e-07, "Pretrain/Loss": 1.9752662181854248, "Pretrain/Loss (Raw)": 1.9842725992202759, "Pretrain/Step": 8876, "Pretrain/Step Time": 8.479276418685913} +{"Pretrain/Learning Rate": 6.235673917608681e-07, "Pretrain/Loss": 1.9743798971176147, "Pretrain/Loss (Raw)": 1.924326777458191, "Pretrain/Step": 8877, "Pretrain/Step Time": 8.481781877577305} +{"Pretrain/Learning Rate": 6.216842389011852e-07, "Pretrain/Loss": 1.9741086959838867, "Pretrain/Loss (Raw)": 1.9762471914291382, "Pretrain/Step": 8878, "Pretrain/Step Time": 8.481911262497306} +{"Pretrain/Learning Rate": 6.198038980716608e-07, "Pretrain/Loss": 1.97524893283844, "Pretrain/Loss (Raw)": 2.008362293243408, "Pretrain/Step": 8879, "Pretrain/Step Time": 8.481845904141665} +{"Pretrain/Learning Rate": 6.179263694891857e-07, "Pretrain/Loss": 1.9744467735290527, "Pretrain/Loss (Raw)": 1.9741865396499634, "Pretrain/Step": 8880, "Pretrain/Step Time": 8.483297681435943} +{"Pretrain/Learning Rate": 6.160516533703392e-07, "Pretrain/Loss": 1.973418951034546, "Pretrain/Loss (Raw)": 1.8469963073730469, "Pretrain/Step": 8881, "Pretrain/Step Time": 8.483578206971288} +{"Pretrain/Learning Rate": 6.14179749931365e-07, "Pretrain/Loss": 1.9728975296020508, "Pretrain/Loss (Raw)": 1.861133337020874, "Pretrain/Step": 8882, "Pretrain/Step Time": 8.48192867450416} +{"Pretrain/Learning Rate": 6.12310659388185e-07, "Pretrain/Loss": 1.9728655815124512, "Pretrain/Loss (Raw)": 1.97544527053833, "Pretrain/Step": 8883, "Pretrain/Step Time": 8.48130495660007} +{"Pretrain/Learning Rate": 6.104443819563987e-07, "Pretrain/Loss": 1.9740219116210938, "Pretrain/Loss (Raw)": 2.1932501792907715, "Pretrain/Step": 8884, "Pretrain/Step Time": 8.481148600578308} +{"Pretrain/Learning Rate": 6.085809178512841e-07, "Pretrain/Loss": 1.9734828472137451, "Pretrain/Loss (Raw)": 1.8672372102737427, "Pretrain/Step": 8885, "Pretrain/Step Time": 8.481286995112896} +{"Pretrain/Learning Rate": 6.067202672877886e-07, "Pretrain/Loss": 1.9755699634552002, "Pretrain/Loss (Raw)": 1.8495579957962036, "Pretrain/Step": 8886, "Pretrain/Step Time": 8.485886627808213} +{"Pretrain/Learning Rate": 6.048624304805378e-07, "Pretrain/Loss": 1.9766627550125122, "Pretrain/Loss (Raw)": 1.9749149084091187, "Pretrain/Step": 8887, "Pretrain/Step Time": 8.486692629754543} +{"Pretrain/Learning Rate": 6.030074076438325e-07, "Pretrain/Loss": 1.977764368057251, "Pretrain/Loss (Raw)": 1.9966720342636108, "Pretrain/Step": 8888, "Pretrain/Step Time": 8.483865452930331} +{"Pretrain/Learning Rate": 6.011551989916486e-07, "Pretrain/Loss": 1.979353666305542, "Pretrain/Loss (Raw)": 2.078601121902466, "Pretrain/Step": 8889, "Pretrain/Step Time": 8.482403993606567} +{"Pretrain/Learning Rate": 5.993058047376376e-07, "Pretrain/Loss": 1.9818633794784546, "Pretrain/Loss (Raw)": 2.0795791149139404, "Pretrain/Step": 8890, "Pretrain/Step Time": 8.481817515566945} +{"Pretrain/Learning Rate": 5.974592250951316e-07, "Pretrain/Loss": 1.9823942184448242, "Pretrain/Loss (Raw)": 1.9572676420211792, "Pretrain/Step": 8891, "Pretrain/Step Time": 8.478639766573906} +{"Pretrain/Learning Rate": 5.956154602771241e-07, "Pretrain/Loss": 1.981766700744629, "Pretrain/Loss (Raw)": 1.9413937330245972, "Pretrain/Step": 8892, "Pretrain/Step Time": 8.47968428209424} +{"Pretrain/Learning Rate": 5.937745104962978e-07, "Pretrain/Loss": 1.9809370040893555, "Pretrain/Loss (Raw)": 1.985323429107666, "Pretrain/Step": 8893, "Pretrain/Step Time": 8.478423105552793} +{"Pretrain/Learning Rate": 5.919363759650049e-07, "Pretrain/Loss": 1.9811573028564453, "Pretrain/Loss (Raw)": 1.9442427158355713, "Pretrain/Step": 8894, "Pretrain/Step Time": 8.479192120954394} +{"Pretrain/Learning Rate": 5.90101056895273e-07, "Pretrain/Loss": 1.9806625843048096, "Pretrain/Loss (Raw)": 2.0680618286132812, "Pretrain/Step": 8895, "Pretrain/Step Time": 8.476695222780108} +{"Pretrain/Learning Rate": 5.882685534988053e-07, "Pretrain/Loss": 1.9809479713439941, "Pretrain/Loss (Raw)": 1.9776396751403809, "Pretrain/Step": 8896, "Pretrain/Step Time": 8.476243825629354} +{"Pretrain/Learning Rate": 5.864388659869823e-07, "Pretrain/Loss": 1.9810891151428223, "Pretrain/Loss (Raw)": 1.8159970045089722, "Pretrain/Step": 8897, "Pretrain/Step Time": 8.473920185118914} +{"Pretrain/Learning Rate": 5.846119945708578e-07, "Pretrain/Loss": 1.9809626340866089, "Pretrain/Loss (Raw)": 2.0983388423919678, "Pretrain/Step": 8898, "Pretrain/Step Time": 8.477221896871924} +{"Pretrain/Learning Rate": 5.827879394611574e-07, "Pretrain/Loss": 1.9820570945739746, "Pretrain/Loss (Raw)": 2.1680362224578857, "Pretrain/Step": 8899, "Pretrain/Step Time": 8.475598549470305} +{"Pretrain/Learning Rate": 5.80966700868285e-07, "Pretrain/Loss": 1.981337070465088, "Pretrain/Loss (Raw)": 1.9584161043167114, "Pretrain/Step": 8900, "Pretrain/Step Time": 8.476158011704683} +{"Pretrain/Learning Rate": 5.791482790023256e-07, "Pretrain/Loss": 1.9800686836242676, "Pretrain/Loss (Raw)": 1.970024585723877, "Pretrain/Step": 8901, "Pretrain/Step Time": 8.478955859318376} +{"Pretrain/Learning Rate": 5.773326740730306e-07, "Pretrain/Loss": 1.9816296100616455, "Pretrain/Loss (Raw)": 2.1830663681030273, "Pretrain/Step": 8902, "Pretrain/Step Time": 8.484741635620594} +{"Pretrain/Learning Rate": 5.75519886289827e-07, "Pretrain/Loss": 1.9808449745178223, "Pretrain/Loss (Raw)": 1.9421992301940918, "Pretrain/Step": 8903, "Pretrain/Step Time": 8.482471901923418} +{"Pretrain/Learning Rate": 5.737099158618225e-07, "Pretrain/Loss": 1.9812934398651123, "Pretrain/Loss (Raw)": 1.8838655948638916, "Pretrain/Step": 8904, "Pretrain/Step Time": 8.482942190021276} +{"Pretrain/Learning Rate": 5.719027629977947e-07, "Pretrain/Loss": 1.9816077947616577, "Pretrain/Loss (Raw)": 2.0618736743927, "Pretrain/Step": 8905, "Pretrain/Step Time": 8.48533844575286} +{"Pretrain/Learning Rate": 5.700984279061988e-07, "Pretrain/Loss": 1.9810839891433716, "Pretrain/Loss (Raw)": 1.931418538093567, "Pretrain/Step": 8906, "Pretrain/Step Time": 8.481564791873097} +{"Pretrain/Learning Rate": 5.68296910795163e-07, "Pretrain/Loss": 1.9810924530029297, "Pretrain/Loss (Raw)": 1.878499150276184, "Pretrain/Step": 8907, "Pretrain/Step Time": 8.47944450005889} +{"Pretrain/Learning Rate": 5.664982118724932e-07, "Pretrain/Loss": 1.9866456985473633, "Pretrain/Loss (Raw)": 2.121103048324585, "Pretrain/Step": 8908, "Pretrain/Step Time": 8.47650513611734} +{"Pretrain/Learning Rate": 5.647023313456706e-07, "Pretrain/Loss": 1.9870505332946777, "Pretrain/Loss (Raw)": 1.9953607320785522, "Pretrain/Step": 8909, "Pretrain/Step Time": 8.47992225177586} +{"Pretrain/Learning Rate": 5.629092694218435e-07, "Pretrain/Loss": 1.988215446472168, "Pretrain/Loss (Raw)": 2.0245065689086914, "Pretrain/Step": 8910, "Pretrain/Step Time": 8.479553937911987} +{"Pretrain/Learning Rate": 5.611190263078464e-07, "Pretrain/Loss": 1.9865251779556274, "Pretrain/Loss (Raw)": 1.9047110080718994, "Pretrain/Step": 8911, "Pretrain/Step Time": 8.483364520594478} +{"Pretrain/Learning Rate": 5.593316022101779e-07, "Pretrain/Loss": 1.985750436782837, "Pretrain/Loss (Raw)": 1.9740735292434692, "Pretrain/Step": 8912, "Pretrain/Step Time": 8.481678975746036} +{"Pretrain/Learning Rate": 5.575469973350262e-07, "Pretrain/Loss": 1.9844038486480713, "Pretrain/Loss (Raw)": 1.8044979572296143, "Pretrain/Step": 8913, "Pretrain/Step Time": 8.479716211557388} +{"Pretrain/Learning Rate": 5.557652118882345e-07, "Pretrain/Loss": 1.984520435333252, "Pretrain/Loss (Raw)": 2.04248046875, "Pretrain/Step": 8914, "Pretrain/Step Time": 8.481129484251142} +{"Pretrain/Learning Rate": 5.539862460753331e-07, "Pretrain/Loss": 1.9850718975067139, "Pretrain/Loss (Raw)": 1.9358813762664795, "Pretrain/Step": 8915, "Pretrain/Step Time": 8.484207652509212} +{"Pretrain/Learning Rate": 5.522101001015301e-07, "Pretrain/Loss": 1.985169768333435, "Pretrain/Loss (Raw)": 1.982440710067749, "Pretrain/Step": 8916, "Pretrain/Step Time": 8.484436927363276} +{"Pretrain/Learning Rate": 5.504367741717004e-07, "Pretrain/Loss": 1.9835803508758545, "Pretrain/Loss (Raw)": 1.735732078552246, "Pretrain/Step": 8917, "Pretrain/Step Time": 8.481896480545402} +{"Pretrain/Learning Rate": 5.48666268490397e-07, "Pretrain/Loss": 1.983610987663269, "Pretrain/Loss (Raw)": 2.016662836074829, "Pretrain/Step": 8918, "Pretrain/Step Time": 8.485888103023171} +{"Pretrain/Learning Rate": 5.468985832618456e-07, "Pretrain/Loss": 1.9836280345916748, "Pretrain/Loss (Raw)": 2.047283887863159, "Pretrain/Step": 8919, "Pretrain/Step Time": 8.487256390973926} +{"Pretrain/Learning Rate": 5.451337186899496e-07, "Pretrain/Loss": 1.9817208051681519, "Pretrain/Loss (Raw)": 1.7467752695083618, "Pretrain/Step": 8920, "Pretrain/Step Time": 8.489291792735457} +{"Pretrain/Learning Rate": 5.433716749782853e-07, "Pretrain/Loss": 1.9807220697402954, "Pretrain/Loss (Raw)": 2.049144744873047, "Pretrain/Step": 8921, "Pretrain/Step Time": 8.491976486518979} +{"Pretrain/Learning Rate": 5.416124523301036e-07, "Pretrain/Loss": 1.980286955833435, "Pretrain/Loss (Raw)": 1.9635939598083496, "Pretrain/Step": 8922, "Pretrain/Step Time": 8.493296686559916} +{"Pretrain/Learning Rate": 5.398560509483313e-07, "Pretrain/Loss": 1.9802114963531494, "Pretrain/Loss (Raw)": 1.9477086067199707, "Pretrain/Step": 8923, "Pretrain/Step Time": 8.491945156827569} +{"Pretrain/Learning Rate": 5.381024710355675e-07, "Pretrain/Loss": 1.981804370880127, "Pretrain/Loss (Raw)": 2.1485846042633057, "Pretrain/Step": 8924, "Pretrain/Step Time": 8.492440771311522} +{"Pretrain/Learning Rate": 5.363517127940864e-07, "Pretrain/Loss": 1.9824473857879639, "Pretrain/Loss (Raw)": 2.047529697418213, "Pretrain/Step": 8925, "Pretrain/Step Time": 8.492444371804595} +{"Pretrain/Learning Rate": 5.346037764258377e-07, "Pretrain/Loss": 1.9816386699676514, "Pretrain/Loss (Raw)": 2.017685651779175, "Pretrain/Step": 8926, "Pretrain/Step Time": 8.49118055216968} +{"Pretrain/Learning Rate": 5.328586621324461e-07, "Pretrain/Loss": 1.979949951171875, "Pretrain/Loss (Raw)": 1.8692623376846313, "Pretrain/Step": 8927, "Pretrain/Step Time": 8.493135180324316} +{"Pretrain/Learning Rate": 5.311163701152088e-07, "Pretrain/Loss": 1.9796833992004395, "Pretrain/Loss (Raw)": 1.981952428817749, "Pretrain/Step": 8928, "Pretrain/Step Time": 8.489720175042748} +{"Pretrain/Learning Rate": 5.293769005751015e-07, "Pretrain/Loss": 1.9794962406158447, "Pretrain/Loss (Raw)": 2.111130475997925, "Pretrain/Step": 8929, "Pretrain/Step Time": 8.49139292910695} +{"Pretrain/Learning Rate": 5.276402537127662e-07, "Pretrain/Loss": 1.9794867038726807, "Pretrain/Loss (Raw)": 1.9994333982467651, "Pretrain/Step": 8930, "Pretrain/Step Time": 8.490270419046283} +{"Pretrain/Learning Rate": 5.259064297285287e-07, "Pretrain/Loss": 1.9819271564483643, "Pretrain/Loss (Raw)": 1.9457966089248657, "Pretrain/Step": 8931, "Pretrain/Step Time": 8.490824623033404} +{"Pretrain/Learning Rate": 5.241754288223822e-07, "Pretrain/Loss": 1.979066014289856, "Pretrain/Loss (Raw)": 1.7449982166290283, "Pretrain/Step": 8932, "Pretrain/Step Time": 8.487809538841248} +{"Pretrain/Learning Rate": 5.224472511939998e-07, "Pretrain/Loss": 1.978278636932373, "Pretrain/Loss (Raw)": 1.8103982210159302, "Pretrain/Step": 8933, "Pretrain/Step Time": 8.486856080591679} +{"Pretrain/Learning Rate": 5.207218970427253e-07, "Pretrain/Loss": 1.9764467477798462, "Pretrain/Loss (Raw)": 1.9159256219863892, "Pretrain/Step": 8934, "Pretrain/Step Time": 8.488325975835323} +{"Pretrain/Learning Rate": 5.189993665675768e-07, "Pretrain/Loss": 1.9765191078186035, "Pretrain/Loss (Raw)": 2.0412564277648926, "Pretrain/Step": 8935, "Pretrain/Step Time": 8.489286869764328} +{"Pretrain/Learning Rate": 5.172796599672485e-07, "Pretrain/Loss": 1.9772653579711914, "Pretrain/Loss (Raw)": 2.0003936290740967, "Pretrain/Step": 8936, "Pretrain/Step Time": 8.487358245998621} +{"Pretrain/Learning Rate": 5.155627774401067e-07, "Pretrain/Loss": 1.978369951248169, "Pretrain/Loss (Raw)": 2.051914930343628, "Pretrain/Step": 8937, "Pretrain/Step Time": 8.49198666214943} +{"Pretrain/Learning Rate": 5.138487191841956e-07, "Pretrain/Loss": 1.978191614151001, "Pretrain/Loss (Raw)": 1.9692152738571167, "Pretrain/Step": 8938, "Pretrain/Step Time": 8.491907997056842} +{"Pretrain/Learning Rate": 5.121374853972294e-07, "Pretrain/Loss": 1.9782270193099976, "Pretrain/Loss (Raw)": 2.133603096008301, "Pretrain/Step": 8939, "Pretrain/Step Time": 8.495151685550809} +{"Pretrain/Learning Rate": 5.104290762766001e-07, "Pretrain/Loss": 1.9797066450119019, "Pretrain/Loss (Raw)": 2.0460543632507324, "Pretrain/Step": 8940, "Pretrain/Step Time": 8.495173620060086} +{"Pretrain/Learning Rate": 5.087234920193668e-07, "Pretrain/Loss": 1.9793864488601685, "Pretrain/Loss (Raw)": 1.9773142337799072, "Pretrain/Step": 8941, "Pretrain/Step Time": 8.491760736331344} +{"Pretrain/Learning Rate": 5.070207328222748e-07, "Pretrain/Loss": 1.9804925918579102, "Pretrain/Loss (Raw)": 2.15460205078125, "Pretrain/Step": 8942, "Pretrain/Step Time": 8.490033583715558} +{"Pretrain/Learning Rate": 5.053207988817338e-07, "Pretrain/Loss": 1.9809322357177734, "Pretrain/Loss (Raw)": 2.0635645389556885, "Pretrain/Step": 8943, "Pretrain/Step Time": 8.48902122490108} +{"Pretrain/Learning Rate": 5.036236903938285e-07, "Pretrain/Loss": 1.9835124015808105, "Pretrain/Loss (Raw)": 2.1180248260498047, "Pretrain/Step": 8944, "Pretrain/Step Time": 8.490789700299501} +{"Pretrain/Learning Rate": 5.019294075543246e-07, "Pretrain/Loss": 1.9844368696212769, "Pretrain/Loss (Raw)": 2.0633695125579834, "Pretrain/Step": 8945, "Pretrain/Step Time": 8.492318892851472} +{"Pretrain/Learning Rate": 5.002379505586518e-07, "Pretrain/Loss": 1.984384536743164, "Pretrain/Loss (Raw)": 1.8650182485580444, "Pretrain/Step": 8946, "Pretrain/Step Time": 8.491855880245566} +{"Pretrain/Learning Rate": 4.985493196019237e-07, "Pretrain/Loss": 1.9838109016418457, "Pretrain/Loss (Raw)": 2.055223226547241, "Pretrain/Step": 8947, "Pretrain/Step Time": 8.48712507262826} +{"Pretrain/Learning Rate": 4.968635148789174e-07, "Pretrain/Loss": 1.9821799993515015, "Pretrain/Loss (Raw)": 1.7540397644042969, "Pretrain/Step": 8948, "Pretrain/Step Time": 8.488214284181595} +{"Pretrain/Learning Rate": 4.951805365840972e-07, "Pretrain/Loss": 1.9817137718200684, "Pretrain/Loss (Raw)": 1.9556307792663574, "Pretrain/Step": 8949, "Pretrain/Step Time": 8.493087278679013} +{"Pretrain/Learning Rate": 4.93500384911591e-07, "Pretrain/Loss": 1.9832130670547485, "Pretrain/Loss (Raw)": 2.0095436573028564, "Pretrain/Step": 8950, "Pretrain/Step Time": 8.493702463805676} +{"Pretrain/Learning Rate": 4.918230600552021e-07, "Pretrain/Loss": 1.9821386337280273, "Pretrain/Loss (Raw)": 1.9024556875228882, "Pretrain/Step": 8951, "Pretrain/Step Time": 8.496177205815911} +{"Pretrain/Learning Rate": 4.90148562208409e-07, "Pretrain/Loss": 1.98262357711792, "Pretrain/Loss (Raw)": 2.0840818881988525, "Pretrain/Step": 8952, "Pretrain/Step Time": 8.495856845751405} +{"Pretrain/Learning Rate": 4.884768915643657e-07, "Pretrain/Loss": 1.9810341596603394, "Pretrain/Loss (Raw)": 1.857078194618225, "Pretrain/Step": 8953, "Pretrain/Step Time": 8.498370047658682} +{"Pretrain/Learning Rate": 4.86808048315901e-07, "Pretrain/Loss": 1.979170799255371, "Pretrain/Loss (Raw)": 1.799360752105713, "Pretrain/Step": 8954, "Pretrain/Step Time": 8.498350827023387} +{"Pretrain/Learning Rate": 4.85142032655514e-07, "Pretrain/Loss": 1.978034496307373, "Pretrain/Loss (Raw)": 1.8496721982955933, "Pretrain/Step": 8955, "Pretrain/Step Time": 8.500080766156316} +{"Pretrain/Learning Rate": 4.834788447753758e-07, "Pretrain/Loss": 1.9778821468353271, "Pretrain/Loss (Raw)": 1.96665620803833, "Pretrain/Step": 8956, "Pretrain/Step Time": 8.498540164902806} +{"Pretrain/Learning Rate": 4.818184848673385e-07, "Pretrain/Loss": 1.9772759675979614, "Pretrain/Loss (Raw)": 1.971767783164978, "Pretrain/Step": 8957, "Pretrain/Step Time": 8.502092264592648} +{"Pretrain/Learning Rate": 4.80160953122924e-07, "Pretrain/Loss": 1.9814181327819824, "Pretrain/Loss (Raw)": 2.263406991958618, "Pretrain/Step": 8958, "Pretrain/Step Time": 8.49894667416811} +{"Pretrain/Learning Rate": 4.785062497333265e-07, "Pretrain/Loss": 1.980887770652771, "Pretrain/Loss (Raw)": 1.9475330114364624, "Pretrain/Step": 8959, "Pretrain/Step Time": 8.49875794351101} +{"Pretrain/Learning Rate": 4.768543748894155e-07, "Pretrain/Loss": 1.9795243740081787, "Pretrain/Loss (Raw)": 1.987199068069458, "Pretrain/Step": 8960, "Pretrain/Step Time": 8.499830251559615} +{"Pretrain/Learning Rate": 4.752053287817332e-07, "Pretrain/Loss": 1.9797618389129639, "Pretrain/Loss (Raw)": 2.0653457641601562, "Pretrain/Step": 8961, "Pretrain/Step Time": 8.49657074175775} +{"Pretrain/Learning Rate": 4.735591116004967e-07, "Pretrain/Loss": 1.980710506439209, "Pretrain/Loss (Raw)": 2.0215675830841064, "Pretrain/Step": 8962, "Pretrain/Step Time": 8.497670646756887} +{"Pretrain/Learning Rate": 4.719157235355959e-07, "Pretrain/Loss": 1.9796860218048096, "Pretrain/Loss (Raw)": 1.9638646841049194, "Pretrain/Step": 8963, "Pretrain/Step Time": 8.49349313788116} +{"Pretrain/Learning Rate": 4.702751647765985e-07, "Pretrain/Loss": 1.9804630279541016, "Pretrain/Loss (Raw)": 1.884779930114746, "Pretrain/Step": 8964, "Pretrain/Step Time": 8.493144229054451} +{"Pretrain/Learning Rate": 4.686374355127421e-07, "Pretrain/Loss": 1.9812695980072021, "Pretrain/Loss (Raw)": 1.9787373542785645, "Pretrain/Step": 8965, "Pretrain/Step Time": 8.489142512902617} +{"Pretrain/Learning Rate": 4.670025359329366e-07, "Pretrain/Loss": 1.9806779623031616, "Pretrain/Loss (Raw)": 1.9247013330459595, "Pretrain/Step": 8966, "Pretrain/Step Time": 8.491299202665687} +{"Pretrain/Learning Rate": 4.653704662257674e-07, "Pretrain/Loss": 1.9804526567459106, "Pretrain/Loss (Raw)": 2.096540689468384, "Pretrain/Step": 8967, "Pretrain/Step Time": 8.492407910525799} +{"Pretrain/Learning Rate": 4.637412265794894e-07, "Pretrain/Loss": 1.982073187828064, "Pretrain/Loss (Raw)": 2.095810890197754, "Pretrain/Step": 8968, "Pretrain/Step Time": 8.492950076237321} +{"Pretrain/Learning Rate": 4.621148171820411e-07, "Pretrain/Loss": 1.979852318763733, "Pretrain/Loss (Raw)": 1.7313275337219238, "Pretrain/Step": 8969, "Pretrain/Step Time": 8.495392207056284} +{"Pretrain/Learning Rate": 4.6049123822102245e-07, "Pretrain/Loss": 1.9794270992279053, "Pretrain/Loss (Raw)": 1.8120481967926025, "Pretrain/Step": 8970, "Pretrain/Step Time": 8.493430454283953} +{"Pretrain/Learning Rate": 4.5887048988371986e-07, "Pretrain/Loss": 1.9802820682525635, "Pretrain/Loss (Raw)": 2.019582509994507, "Pretrain/Step": 8971, "Pretrain/Step Time": 8.492435147985816} +{"Pretrain/Learning Rate": 4.572525723570809e-07, "Pretrain/Loss": 1.980769395828247, "Pretrain/Loss (Raw)": 2.0037057399749756, "Pretrain/Step": 8972, "Pretrain/Step Time": 8.490129727870226} +{"Pretrain/Learning Rate": 4.5563748582773124e-07, "Pretrain/Loss": 1.9799405336380005, "Pretrain/Loss (Raw)": 1.9030238389968872, "Pretrain/Step": 8973, "Pretrain/Step Time": 8.488484492525458} +{"Pretrain/Learning Rate": 4.540252304819748e-07, "Pretrain/Loss": 1.9820833206176758, "Pretrain/Loss (Raw)": 2.2228150367736816, "Pretrain/Step": 8974, "Pretrain/Step Time": 8.485688876360655} +{"Pretrain/Learning Rate": 4.524158065057793e-07, "Pretrain/Loss": 1.9789787530899048, "Pretrain/Loss (Raw)": 1.6599360704421997, "Pretrain/Step": 8975, "Pretrain/Step Time": 8.486297471448779} +{"Pretrain/Learning Rate": 4.508092140847936e-07, "Pretrain/Loss": 1.9797366857528687, "Pretrain/Loss (Raw)": 2.0548317432403564, "Pretrain/Step": 8976, "Pretrain/Step Time": 8.482870109379292} +{"Pretrain/Learning Rate": 4.4920545340433886e-07, "Pretrain/Loss": 1.9795293807983398, "Pretrain/Loss (Raw)": 2.0416784286499023, "Pretrain/Step": 8977, "Pretrain/Step Time": 8.484622759744525} +{"Pretrain/Learning Rate": 4.4760452464940874e-07, "Pretrain/Loss": 1.977974772453308, "Pretrain/Loss (Raw)": 1.9578403234481812, "Pretrain/Step": 8978, "Pretrain/Step Time": 8.483009168878198} +{"Pretrain/Learning Rate": 4.4600642800466664e-07, "Pretrain/Loss": 1.9744462966918945, "Pretrain/Loss (Raw)": 1.9487922191619873, "Pretrain/Step": 8979, "Pretrain/Step Time": 8.484661726281047} +{"Pretrain/Learning Rate": 4.4441116365445125e-07, "Pretrain/Loss": 1.9729868173599243, "Pretrain/Loss (Raw)": 1.9145843982696533, "Pretrain/Step": 8980, "Pretrain/Step Time": 8.486509071663022} +{"Pretrain/Learning Rate": 4.4281873178278475e-07, "Pretrain/Loss": 1.972245693206787, "Pretrain/Loss (Raw)": 2.007843017578125, "Pretrain/Step": 8981, "Pretrain/Step Time": 8.481091853231192} +{"Pretrain/Learning Rate": 4.412291325733453e-07, "Pretrain/Loss": 1.973428726196289, "Pretrain/Loss (Raw)": 2.0893845558166504, "Pretrain/Step": 8982, "Pretrain/Step Time": 8.481200529262424} +{"Pretrain/Learning Rate": 4.3964236620949173e-07, "Pretrain/Loss": 1.973706603050232, "Pretrain/Loss (Raw)": 2.0402486324310303, "Pretrain/Step": 8983, "Pretrain/Step Time": 8.483763614669442} +{"Pretrain/Learning Rate": 4.3805843287426376e-07, "Pretrain/Loss": 1.9766860008239746, "Pretrain/Loss (Raw)": 2.1754162311553955, "Pretrain/Step": 8984, "Pretrain/Step Time": 8.48311435058713} +{"Pretrain/Learning Rate": 4.364773327503624e-07, "Pretrain/Loss": 1.9757020473480225, "Pretrain/Loss (Raw)": 1.954982042312622, "Pretrain/Step": 8985, "Pretrain/Step Time": 8.482241297140718} +{"Pretrain/Learning Rate": 4.3489906602016686e-07, "Pretrain/Loss": 1.977036714553833, "Pretrain/Loss (Raw)": 2.0240767002105713, "Pretrain/Step": 8986, "Pretrain/Step Time": 8.48468516021967} +{"Pretrain/Learning Rate": 4.333236328657342e-07, "Pretrain/Loss": 1.9750813245773315, "Pretrain/Loss (Raw)": 1.8689571619033813, "Pretrain/Step": 8987, "Pretrain/Step Time": 8.487256834283471} +{"Pretrain/Learning Rate": 4.3175103346878575e-07, "Pretrain/Loss": 1.974144697189331, "Pretrain/Loss (Raw)": 1.7747114896774292, "Pretrain/Step": 8988, "Pretrain/Step Time": 8.488898219540715} +{"Pretrain/Learning Rate": 4.301812680107209e-07, "Pretrain/Loss": 1.9743062257766724, "Pretrain/Loss (Raw)": 2.049947738647461, "Pretrain/Step": 8989, "Pretrain/Step Time": 8.488021979108453} +{"Pretrain/Learning Rate": 4.286143366726142e-07, "Pretrain/Loss": 1.9728050231933594, "Pretrain/Loss (Raw)": 1.820939064025879, "Pretrain/Step": 8990, "Pretrain/Step Time": 8.486134149134159} +{"Pretrain/Learning Rate": 4.2705023963520993e-07, "Pretrain/Loss": 1.973595380783081, "Pretrain/Loss (Raw)": 1.8922258615493774, "Pretrain/Step": 8991, "Pretrain/Step Time": 8.490341471508145} +{"Pretrain/Learning Rate": 4.254889770789222e-07, "Pretrain/Loss": 1.9734017848968506, "Pretrain/Loss (Raw)": 2.053969144821167, "Pretrain/Step": 8992, "Pretrain/Step Time": 8.488597020506859} +{"Pretrain/Learning Rate": 4.2393054918384855e-07, "Pretrain/Loss": 1.9731162786483765, "Pretrain/Loss (Raw)": 1.958632469177246, "Pretrain/Step": 8993, "Pretrain/Step Time": 8.485389057546854} +{"Pretrain/Learning Rate": 4.223749561297452e-07, "Pretrain/Loss": 1.9741384983062744, "Pretrain/Loss (Raw)": 2.0710556507110596, "Pretrain/Step": 8994, "Pretrain/Step Time": 8.485010365024209} +{"Pretrain/Learning Rate": 4.208221980960547e-07, "Pretrain/Loss": 1.9744584560394287, "Pretrain/Loss (Raw)": 2.0798020362854004, "Pretrain/Step": 8995, "Pretrain/Step Time": 8.481407150626183} +{"Pretrain/Learning Rate": 4.192722752618866e-07, "Pretrain/Loss": 1.9748879671096802, "Pretrain/Loss (Raw)": 2.1111245155334473, "Pretrain/Step": 8996, "Pretrain/Step Time": 8.480999406427145} +{"Pretrain/Learning Rate": 4.177251878060229e-07, "Pretrain/Loss": 1.9764142036437988, "Pretrain/Loss (Raw)": 2.012834310531616, "Pretrain/Step": 8997, "Pretrain/Step Time": 8.48083234205842} +{"Pretrain/Learning Rate": 4.1618093590692073e-07, "Pretrain/Loss": 1.9762036800384521, "Pretrain/Loss (Raw)": 1.9631551504135132, "Pretrain/Step": 8998, "Pretrain/Step Time": 8.483891846612096} +{"Pretrain/Learning Rate": 4.146395197427072e-07, "Pretrain/Loss": 1.9764559268951416, "Pretrain/Loss (Raw)": 1.9595881700515747, "Pretrain/Step": 8999, "Pretrain/Step Time": 8.482949828729033} +{"Pretrain/Learning Rate": 4.1310093949118443e-07, "Pretrain/Loss": 1.9758374691009521, "Pretrain/Loss (Raw)": 1.8820382356643677, "Pretrain/Step": 9000, "Pretrain/Step Time": 8.485552014783025} +{"Pretrain/Learning Rate": 4.115651953298272e-07, "Pretrain/Loss": 1.974689245223999, "Pretrain/Loss (Raw)": 1.9033269882202148, "Pretrain/Step": 9001, "Pretrain/Step Time": 8.486487235873938} +{"Pretrain/Learning Rate": 4.1003228743578814e-07, "Pretrain/Loss": 1.9748245477676392, "Pretrain/Loss (Raw)": 1.8652528524398804, "Pretrain/Step": 9002, "Pretrain/Step Time": 8.484032588079572} +{"Pretrain/Learning Rate": 4.0850221598587867e-07, "Pretrain/Loss": 1.9762213230133057, "Pretrain/Loss (Raw)": 1.9662216901779175, "Pretrain/Step": 9003, "Pretrain/Step Time": 8.489665284752846} +{"Pretrain/Learning Rate": 4.069749811565965e-07, "Pretrain/Loss": 1.974483609199524, "Pretrain/Loss (Raw)": 1.7618460655212402, "Pretrain/Step": 9004, "Pretrain/Step Time": 8.488533299416304} +{"Pretrain/Learning Rate": 4.05450583124109e-07, "Pretrain/Loss": 1.9754064083099365, "Pretrain/Loss (Raw)": 2.0424392223358154, "Pretrain/Step": 9005, "Pretrain/Step Time": 8.48496862873435} +{"Pretrain/Learning Rate": 4.039290220642533e-07, "Pretrain/Loss": 1.9765653610229492, "Pretrain/Loss (Raw)": 2.1245999336242676, "Pretrain/Step": 9006, "Pretrain/Step Time": 8.48443679139018} +{"Pretrain/Learning Rate": 4.024102981525446e-07, "Pretrain/Loss": 1.9768474102020264, "Pretrain/Loss (Raw)": 2.044450044631958, "Pretrain/Step": 9007, "Pretrain/Step Time": 8.481299629434943} +{"Pretrain/Learning Rate": 4.008944115641594e-07, "Pretrain/Loss": 1.9785230159759521, "Pretrain/Loss (Raw)": 2.1886794567108154, "Pretrain/Step": 9008, "Pretrain/Step Time": 8.48152270168066} +{"Pretrain/Learning Rate": 3.993813624739634e-07, "Pretrain/Loss": 1.979093074798584, "Pretrain/Loss (Raw)": 1.9199585914611816, "Pretrain/Step": 9009, "Pretrain/Step Time": 8.483419904485345} +{"Pretrain/Learning Rate": 3.978711510564781e-07, "Pretrain/Loss": 1.979050874710083, "Pretrain/Loss (Raw)": 1.8557237386703491, "Pretrain/Step": 9010, "Pretrain/Step Time": 8.479805642738938} +{"Pretrain/Learning Rate": 3.963637774859114e-07, "Pretrain/Loss": 1.9786829948425293, "Pretrain/Loss (Raw)": 1.9283770322799683, "Pretrain/Step": 9011, "Pretrain/Step Time": 8.4804622028023} +{"Pretrain/Learning Rate": 3.9485924193613523e-07, "Pretrain/Loss": 1.9779980182647705, "Pretrain/Loss (Raw)": 2.1055610179901123, "Pretrain/Step": 9012, "Pretrain/Step Time": 8.480582308024168} +{"Pretrain/Learning Rate": 3.933575445807025e-07, "Pretrain/Loss": 1.9804853200912476, "Pretrain/Loss (Raw)": 2.1856133937835693, "Pretrain/Step": 9013, "Pretrain/Step Time": 8.48168532550335} +{"Pretrain/Learning Rate": 3.9185868559282466e-07, "Pretrain/Loss": 1.983107089996338, "Pretrain/Loss (Raw)": 2.185148000717163, "Pretrain/Step": 9014, "Pretrain/Step Time": 8.477552197873592} +{"Pretrain/Learning Rate": 3.903626651454023e-07, "Pretrain/Loss": 1.9826087951660156, "Pretrain/Loss (Raw)": 1.9111287593841553, "Pretrain/Step": 9015, "Pretrain/Step Time": 8.477820007130504} +{"Pretrain/Learning Rate": 3.8886948341099737e-07, "Pretrain/Loss": 1.9827525615692139, "Pretrain/Loss (Raw)": 2.0150630474090576, "Pretrain/Step": 9016, "Pretrain/Step Time": 8.481358593329787} +{"Pretrain/Learning Rate": 3.873791405618471e-07, "Pretrain/Loss": 1.9827150106430054, "Pretrain/Loss (Raw)": 2.0738162994384766, "Pretrain/Step": 9017, "Pretrain/Step Time": 8.482878407463431} +{"Pretrain/Learning Rate": 3.8589163676986674e-07, "Pretrain/Loss": 1.9820375442504883, "Pretrain/Loss (Raw)": 1.992845892906189, "Pretrain/Step": 9018, "Pretrain/Step Time": 8.48408542945981} +{"Pretrain/Learning Rate": 3.844069722066329e-07, "Pretrain/Loss": 1.9818191528320312, "Pretrain/Loss (Raw)": 1.9293162822723389, "Pretrain/Step": 9019, "Pretrain/Step Time": 8.484938245266676} +{"Pretrain/Learning Rate": 3.8292514704340586e-07, "Pretrain/Loss": 1.9829550981521606, "Pretrain/Loss (Raw)": 2.0867929458618164, "Pretrain/Step": 9020, "Pretrain/Step Time": 8.486034171655774} +{"Pretrain/Learning Rate": 3.8144616145111277e-07, "Pretrain/Loss": 1.9828836917877197, "Pretrain/Loss (Raw)": 1.9762033224105835, "Pretrain/Step": 9021, "Pretrain/Step Time": 8.48842692002654} +{"Pretrain/Learning Rate": 3.799700156003505e-07, "Pretrain/Loss": 1.9840500354766846, "Pretrain/Loss (Raw)": 2.0935187339782715, "Pretrain/Step": 9022, "Pretrain/Step Time": 8.485299004241824} +{"Pretrain/Learning Rate": 3.784967096613995e-07, "Pretrain/Loss": 1.9823747873306274, "Pretrain/Loss (Raw)": 1.8536269664764404, "Pretrain/Step": 9023, "Pretrain/Step Time": 8.487099405378103} +{"Pretrain/Learning Rate": 3.7702624380419607e-07, "Pretrain/Loss": 1.982907772064209, "Pretrain/Loss (Raw)": 2.0458717346191406, "Pretrain/Step": 9024, "Pretrain/Step Time": 8.486122166737914} +{"Pretrain/Learning Rate": 3.755586181983628e-07, "Pretrain/Loss": 1.9838805198669434, "Pretrain/Loss (Raw)": 1.9405040740966797, "Pretrain/Step": 9025, "Pretrain/Step Time": 8.487179698422551} +{"Pretrain/Learning Rate": 3.7409383301319213e-07, "Pretrain/Loss": 1.9839469194412231, "Pretrain/Loss (Raw)": 2.106840133666992, "Pretrain/Step": 9026, "Pretrain/Step Time": 8.485798601061106} +{"Pretrain/Learning Rate": 3.726318884176433e-07, "Pretrain/Loss": 1.9825814962387085, "Pretrain/Loss (Raw)": 1.9932509660720825, "Pretrain/Step": 9027, "Pretrain/Step Time": 8.48421254567802} +{"Pretrain/Learning Rate": 3.711727845803481e-07, "Pretrain/Loss": 1.983351707458496, "Pretrain/Loss (Raw)": 2.0570130348205566, "Pretrain/Step": 9028, "Pretrain/Step Time": 8.486118238419294} +{"Pretrain/Learning Rate": 3.697165216696219e-07, "Pretrain/Loss": 1.9834849834442139, "Pretrain/Loss (Raw)": 1.987078070640564, "Pretrain/Step": 9029, "Pretrain/Step Time": 8.484109671786427} +{"Pretrain/Learning Rate": 3.682630998534359e-07, "Pretrain/Loss": 1.9810278415679932, "Pretrain/Loss (Raw)": 1.8685654401779175, "Pretrain/Step": 9030, "Pretrain/Step Time": 8.482640212401748} +{"Pretrain/Learning Rate": 3.668125192994448e-07, "Pretrain/Loss": 1.9819610118865967, "Pretrain/Loss (Raw)": 2.061635732650757, "Pretrain/Step": 9031, "Pretrain/Step Time": 8.480857083573937} +{"Pretrain/Learning Rate": 3.653647801749732e-07, "Pretrain/Loss": 1.9842782020568848, "Pretrain/Loss (Raw)": 2.180475950241089, "Pretrain/Step": 9032, "Pretrain/Step Time": 8.482290260493755} +{"Pretrain/Learning Rate": 3.63919882647018e-07, "Pretrain/Loss": 1.98095703125, "Pretrain/Loss (Raw)": 1.6367634534835815, "Pretrain/Step": 9033, "Pretrain/Step Time": 8.481300871819258} +{"Pretrain/Learning Rate": 3.6247782688224596e-07, "Pretrain/Loss": 1.981109619140625, "Pretrain/Loss (Raw)": 1.950945496559143, "Pretrain/Step": 9034, "Pretrain/Step Time": 8.482849700376391} +{"Pretrain/Learning Rate": 3.6103861304699895e-07, "Pretrain/Loss": 1.983015537261963, "Pretrain/Loss (Raw)": 2.1224472522735596, "Pretrain/Step": 9035, "Pretrain/Step Time": 8.484364584088326} +{"Pretrain/Learning Rate": 3.5960224130728857e-07, "Pretrain/Loss": 1.980170726776123, "Pretrain/Loss (Raw)": 1.7569783926010132, "Pretrain/Step": 9036, "Pretrain/Step Time": 8.487774109467864} +{"Pretrain/Learning Rate": 3.581687118287991e-07, "Pretrain/Loss": 1.9796584844589233, "Pretrain/Loss (Raw)": 1.9297902584075928, "Pretrain/Step": 9037, "Pretrain/Step Time": 8.485468665137887} +{"Pretrain/Learning Rate": 3.5673802477689257e-07, "Pretrain/Loss": 1.9771820306777954, "Pretrain/Loss (Raw)": 1.707502841949463, "Pretrain/Step": 9038, "Pretrain/Step Time": 8.486556090414524} +{"Pretrain/Learning Rate": 3.553101803165926e-07, "Pretrain/Loss": 1.9784860610961914, "Pretrain/Loss (Raw)": 2.071624517440796, "Pretrain/Step": 9039, "Pretrain/Step Time": 8.485674537718296} +{"Pretrain/Learning Rate": 3.538851786126035e-07, "Pretrain/Loss": 1.9796570539474487, "Pretrain/Loss (Raw)": 2.12398624420166, "Pretrain/Step": 9040, "Pretrain/Step Time": 8.48024802096188} +{"Pretrain/Learning Rate": 3.5246301982929387e-07, "Pretrain/Loss": 1.9814401865005493, "Pretrain/Loss (Raw)": 2.032731771469116, "Pretrain/Step": 9041, "Pretrain/Step Time": 8.48317439481616} +{"Pretrain/Learning Rate": 3.510437041307185e-07, "Pretrain/Loss": 1.981391429901123, "Pretrain/Loss (Raw)": 2.0362389087677, "Pretrain/Step": 9042, "Pretrain/Step Time": 8.48104359023273} +{"Pretrain/Learning Rate": 3.496272316805882e-07, "Pretrain/Loss": 1.9805560111999512, "Pretrain/Loss (Raw)": 1.828947901725769, "Pretrain/Step": 9043, "Pretrain/Step Time": 8.47934752330184} +{"Pretrain/Learning Rate": 3.4821360264229165e-07, "Pretrain/Loss": 1.9807592630386353, "Pretrain/Loss (Raw)": 2.008460760116577, "Pretrain/Step": 9044, "Pretrain/Step Time": 8.478828908875585} +{"Pretrain/Learning Rate": 3.4680281717889564e-07, "Pretrain/Loss": 1.9827090501785278, "Pretrain/Loss (Raw)": 1.9853018522262573, "Pretrain/Step": 9045, "Pretrain/Step Time": 8.481695065274835} +{"Pretrain/Learning Rate": 3.453948754531283e-07, "Pretrain/Loss": 1.9828875064849854, "Pretrain/Loss (Raw)": 2.039485216140747, "Pretrain/Step": 9046, "Pretrain/Step Time": 8.48237002082169} +{"Pretrain/Learning Rate": 3.439897776273987e-07, "Pretrain/Loss": 1.9796504974365234, "Pretrain/Loss (Raw)": 1.6329598426818848, "Pretrain/Step": 9047, "Pretrain/Step Time": 8.481900399550796} +{"Pretrain/Learning Rate": 3.4258752386378267e-07, "Pretrain/Loss": 1.9795138835906982, "Pretrain/Loss (Raw)": 1.729308009147644, "Pretrain/Step": 9048, "Pretrain/Step Time": 8.479240776970983} +{"Pretrain/Learning Rate": 3.4118811432403144e-07, "Pretrain/Loss": 1.9803909063339233, "Pretrain/Loss (Raw)": 2.161393880844116, "Pretrain/Step": 9049, "Pretrain/Step Time": 8.478734415024519} +{"Pretrain/Learning Rate": 3.397915491695686e-07, "Pretrain/Loss": 1.980926513671875, "Pretrain/Loss (Raw)": 2.0321357250213623, "Pretrain/Step": 9050, "Pretrain/Step Time": 8.477999093011022} +{"Pretrain/Learning Rate": 3.3839782856147916e-07, "Pretrain/Loss": 1.9801043272018433, "Pretrain/Loss (Raw)": 1.8424758911132812, "Pretrain/Step": 9051, "Pretrain/Step Time": 8.476794421672821} +{"Pretrain/Learning Rate": 3.370069526605374e-07, "Pretrain/Loss": 1.978817343711853, "Pretrain/Loss (Raw)": 1.983864665031433, "Pretrain/Step": 9052, "Pretrain/Step Time": 8.481312278658152} +{"Pretrain/Learning Rate": 3.3561892162717325e-07, "Pretrain/Loss": 1.9766699075698853, "Pretrain/Loss (Raw)": 1.7726471424102783, "Pretrain/Step": 9053, "Pretrain/Step Time": 8.479192780330777} +{"Pretrain/Learning Rate": 3.342337356215003e-07, "Pretrain/Loss": 1.9767215251922607, "Pretrain/Loss (Raw)": 2.024277687072754, "Pretrain/Step": 9054, "Pretrain/Step Time": 8.480933904647827} +{"Pretrain/Learning Rate": 3.328513948032991e-07, "Pretrain/Loss": 1.9787747859954834, "Pretrain/Loss (Raw)": 2.132097005844116, "Pretrain/Step": 9055, "Pretrain/Step Time": 8.479170471429825} +{"Pretrain/Learning Rate": 3.314718993320198e-07, "Pretrain/Loss": 1.9786405563354492, "Pretrain/Loss (Raw)": 1.964781403541565, "Pretrain/Step": 9056, "Pretrain/Step Time": 8.480932170525193} +{"Pretrain/Learning Rate": 3.3009524936678527e-07, "Pretrain/Loss": 1.9781770706176758, "Pretrain/Loss (Raw)": 2.0518007278442383, "Pretrain/Step": 9057, "Pretrain/Step Time": 8.480240162461996} +{"Pretrain/Learning Rate": 3.287214450663989e-07, "Pretrain/Loss": 1.9775716066360474, "Pretrain/Loss (Raw)": 1.9219237565994263, "Pretrain/Step": 9058, "Pretrain/Step Time": 8.482158239930868} +{"Pretrain/Learning Rate": 3.273504865893201e-07, "Pretrain/Loss": 1.978779673576355, "Pretrain/Loss (Raw)": 2.1004281044006348, "Pretrain/Step": 9059, "Pretrain/Step Time": 8.479264741763473} +{"Pretrain/Learning Rate": 3.259823740936946e-07, "Pretrain/Loss": 1.9799871444702148, "Pretrain/Loss (Raw)": 1.8995649814605713, "Pretrain/Step": 9060, "Pretrain/Step Time": 8.478864405304193} +{"Pretrain/Learning Rate": 3.2461710773732947e-07, "Pretrain/Loss": 1.9807605743408203, "Pretrain/Loss (Raw)": 1.9093817472457886, "Pretrain/Step": 9061, "Pretrain/Step Time": 8.483147021383047} +{"Pretrain/Learning Rate": 3.2325468767770984e-07, "Pretrain/Loss": 1.9809420108795166, "Pretrain/Loss (Raw)": 1.9391456842422485, "Pretrain/Step": 9062, "Pretrain/Step Time": 8.48550646007061} +{"Pretrain/Learning Rate": 3.218951140719906e-07, "Pretrain/Loss": 1.9809458255767822, "Pretrain/Loss (Raw)": 2.0417592525482178, "Pretrain/Step": 9063, "Pretrain/Step Time": 8.48324273340404} +{"Pretrain/Learning Rate": 3.2053838707699626e-07, "Pretrain/Loss": 1.981041431427002, "Pretrain/Loss (Raw)": 2.0126163959503174, "Pretrain/Step": 9064, "Pretrain/Step Time": 8.482868783175945} +{"Pretrain/Learning Rate": 3.191845068492266e-07, "Pretrain/Loss": 1.980594277381897, "Pretrain/Loss (Raw)": 1.9946931600570679, "Pretrain/Step": 9065, "Pretrain/Step Time": 8.479905877262354} +{"Pretrain/Learning Rate": 3.178334735448513e-07, "Pretrain/Loss": 1.978879451751709, "Pretrain/Loss (Raw)": 1.7497141361236572, "Pretrain/Step": 9066, "Pretrain/Step Time": 8.47919443435967} +{"Pretrain/Learning Rate": 3.164852873197094e-07, "Pretrain/Loss": 1.9774341583251953, "Pretrain/Loss (Raw)": 1.9486068487167358, "Pretrain/Step": 9067, "Pretrain/Step Time": 8.475192600861192} +{"Pretrain/Learning Rate": 3.151399483293155e-07, "Pretrain/Loss": 1.9764641523361206, "Pretrain/Loss (Raw)": 1.9218932390213013, "Pretrain/Step": 9068, "Pretrain/Step Time": 8.476347988471389} +{"Pretrain/Learning Rate": 3.1379745672885375e-07, "Pretrain/Loss": 1.9773694276809692, "Pretrain/Loss (Raw)": 2.093191385269165, "Pretrain/Step": 9069, "Pretrain/Step Time": 8.477634135633707} +{"Pretrain/Learning Rate": 3.1245781267318085e-07, "Pretrain/Loss": 1.975501298904419, "Pretrain/Loss (Raw)": 1.9154763221740723, "Pretrain/Step": 9070, "Pretrain/Step Time": 8.476777445524931} +{"Pretrain/Learning Rate": 3.111210163168232e-07, "Pretrain/Loss": 1.9734210968017578, "Pretrain/Loss (Raw)": 1.7972936630249023, "Pretrain/Step": 9071, "Pretrain/Step Time": 8.47552890330553} +{"Pretrain/Learning Rate": 3.097870678139797e-07, "Pretrain/Loss": 1.972720742225647, "Pretrain/Loss (Raw)": 2.0283777713775635, "Pretrain/Step": 9072, "Pretrain/Step Time": 8.476696921512485} +{"Pretrain/Learning Rate": 3.084559673185217e-07, "Pretrain/Loss": 1.9719250202178955, "Pretrain/Loss (Raw)": 1.9615248441696167, "Pretrain/Step": 9073, "Pretrain/Step Time": 8.472906827926636} +{"Pretrain/Learning Rate": 3.0712771498399017e-07, "Pretrain/Loss": 1.9712069034576416, "Pretrain/Loss (Raw)": 1.7731013298034668, "Pretrain/Step": 9074, "Pretrain/Step Time": 8.473435839638114} +{"Pretrain/Learning Rate": 3.058023109636016e-07, "Pretrain/Loss": 1.9689964056015015, "Pretrain/Loss (Raw)": 1.772282600402832, "Pretrain/Step": 9075, "Pretrain/Step Time": 8.474654575809836} +{"Pretrain/Learning Rate": 3.0447975541023356e-07, "Pretrain/Loss": 1.9704298973083496, "Pretrain/Loss (Raw)": 1.9375213384628296, "Pretrain/Step": 9076, "Pretrain/Step Time": 8.47538397461176} +{"Pretrain/Learning Rate": 3.031600484764502e-07, "Pretrain/Loss": 1.9700218439102173, "Pretrain/Loss (Raw)": 1.903408169746399, "Pretrain/Step": 9077, "Pretrain/Step Time": 8.471484918147326} +{"Pretrain/Learning Rate": 3.0184319031447696e-07, "Pretrain/Loss": 1.969433307647705, "Pretrain/Loss (Raw)": 1.934208869934082, "Pretrain/Step": 9078, "Pretrain/Step Time": 8.47079642675817} +{"Pretrain/Learning Rate": 3.00529181076209e-07, "Pretrain/Loss": 1.9696788787841797, "Pretrain/Loss (Raw)": 1.933883547782898, "Pretrain/Step": 9079, "Pretrain/Step Time": 8.468586787581444} +{"Pretrain/Learning Rate": 2.9921802091322224e-07, "Pretrain/Loss": 1.970566987991333, "Pretrain/Loss (Raw)": 2.1977450847625732, "Pretrain/Step": 9080, "Pretrain/Step Time": 8.467911103740335} +{"Pretrain/Learning Rate": 2.9790970997675695e-07, "Pretrain/Loss": 1.9728728532791138, "Pretrain/Loss (Raw)": 2.1522529125213623, "Pretrain/Step": 9081, "Pretrain/Step Time": 8.467958007007837} +{"Pretrain/Learning Rate": 2.966042484177228e-07, "Pretrain/Loss": 1.9746580123901367, "Pretrain/Loss (Raw)": 2.027850866317749, "Pretrain/Step": 9082, "Pretrain/Step Time": 8.467357713729143} +{"Pretrain/Learning Rate": 2.953016363867078e-07, "Pretrain/Loss": 1.9759148359298706, "Pretrain/Loss (Raw)": 2.0105485916137695, "Pretrain/Step": 9083, "Pretrain/Step Time": 8.467205533757806} +{"Pretrain/Learning Rate": 2.940018740339695e-07, "Pretrain/Loss": 1.9762811660766602, "Pretrain/Loss (Raw)": 2.0135464668273926, "Pretrain/Step": 9084, "Pretrain/Step Time": 8.469136903062463} +{"Pretrain/Learning Rate": 2.927049615094296e-07, "Pretrain/Loss": 1.9769115447998047, "Pretrain/Loss (Raw)": 2.052460193634033, "Pretrain/Step": 9085, "Pretrain/Step Time": 8.470239274203777} +{"Pretrain/Learning Rate": 2.9141089896269346e-07, "Pretrain/Loss": 1.975131869316101, "Pretrain/Loss (Raw)": 2.0356087684631348, "Pretrain/Step": 9086, "Pretrain/Step Time": 8.46888535283506} +{"Pretrain/Learning Rate": 2.90119686543025e-07, "Pretrain/Loss": 1.9768478870391846, "Pretrain/Loss (Raw)": 2.167182683944702, "Pretrain/Step": 9087, "Pretrain/Step Time": 8.472016837447882} +{"Pretrain/Learning Rate": 2.888313243993662e-07, "Pretrain/Loss": 1.9778915643692017, "Pretrain/Loss (Raw)": 2.120783567428589, "Pretrain/Step": 9088, "Pretrain/Step Time": 8.469458876177669} +{"Pretrain/Learning Rate": 2.875458126803315e-07, "Pretrain/Loss": 1.9774730205535889, "Pretrain/Loss (Raw)": 2.0117640495300293, "Pretrain/Step": 9089, "Pretrain/Step Time": 8.470532488077879} +{"Pretrain/Learning Rate": 2.8626315153420236e-07, "Pretrain/Loss": 1.9773699045181274, "Pretrain/Loss (Raw)": 2.0083842277526855, "Pretrain/Step": 9090, "Pretrain/Step Time": 8.468321066349745} +{"Pretrain/Learning Rate": 2.8498334110893256e-07, "Pretrain/Loss": 1.9781579971313477, "Pretrain/Loss (Raw)": 2.064727783203125, "Pretrain/Step": 9091, "Pretrain/Step Time": 8.473289718851447} +{"Pretrain/Learning Rate": 2.8370638155215123e-07, "Pretrain/Loss": 1.9790847301483154, "Pretrain/Loss (Raw)": 2.003425359725952, "Pretrain/Step": 9092, "Pretrain/Step Time": 8.472806075587869} +{"Pretrain/Learning Rate": 2.8243227301115173e-07, "Pretrain/Loss": 1.9787317514419556, "Pretrain/Loss (Raw)": 1.9335483312606812, "Pretrain/Step": 9093, "Pretrain/Step Time": 8.477186694741249} +{"Pretrain/Learning Rate": 2.8116101563290253e-07, "Pretrain/Loss": 1.9794398546218872, "Pretrain/Loss (Raw)": 2.01533579826355, "Pretrain/Step": 9094, "Pretrain/Step Time": 8.474788105115294} +{"Pretrain/Learning Rate": 2.7989260956404193e-07, "Pretrain/Loss": 1.9796016216278076, "Pretrain/Loss (Raw)": 2.1172499656677246, "Pretrain/Step": 9095, "Pretrain/Step Time": 8.476541209965944} +{"Pretrain/Learning Rate": 2.786270549508835e-07, "Pretrain/Loss": 1.9762221574783325, "Pretrain/Loss (Raw)": 1.66323983669281, "Pretrain/Step": 9096, "Pretrain/Step Time": 8.475659208372235} +{"Pretrain/Learning Rate": 2.7736435193940755e-07, "Pretrain/Loss": 1.9796346426010132, "Pretrain/Loss (Raw)": 2.1681220531463623, "Pretrain/Step": 9097, "Pretrain/Step Time": 8.476919542998075} +{"Pretrain/Learning Rate": 2.7610450067526436e-07, "Pretrain/Loss": 1.9825091361999512, "Pretrain/Loss (Raw)": 2.17997407913208, "Pretrain/Step": 9098, "Pretrain/Step Time": 8.475922985002398} +{"Pretrain/Learning Rate": 2.7484750130377655e-07, "Pretrain/Loss": 1.98279869556427, "Pretrain/Loss (Raw)": 2.0566470623016357, "Pretrain/Step": 9099, "Pretrain/Step Time": 8.477152056992054} +{"Pretrain/Learning Rate": 2.73593353969942e-07, "Pretrain/Loss": 1.9826960563659668, "Pretrain/Loss (Raw)": 1.9905716180801392, "Pretrain/Step": 9100, "Pretrain/Step Time": 8.477124309167266} +{"Pretrain/Learning Rate": 2.7234205881842554e-07, "Pretrain/Loss": 1.9833142757415771, "Pretrain/Loss (Raw)": 1.9821555614471436, "Pretrain/Step": 9101, "Pretrain/Step Time": 8.479309421032667} +{"Pretrain/Learning Rate": 2.7109361599356177e-07, "Pretrain/Loss": 1.9813472032546997, "Pretrain/Loss (Raw)": 1.9710330963134766, "Pretrain/Step": 9102, "Pretrain/Step Time": 8.480795476585627} +{"Pretrain/Learning Rate": 2.698480256393604e-07, "Pretrain/Loss": 1.9827537536621094, "Pretrain/Loss (Raw)": 1.8399626016616821, "Pretrain/Step": 9103, "Pretrain/Step Time": 8.482421403750777} +{"Pretrain/Learning Rate": 2.6860528789949544e-07, "Pretrain/Loss": 1.9824860095977783, "Pretrain/Loss (Raw)": 2.020573854446411, "Pretrain/Step": 9104, "Pretrain/Step Time": 8.486718717962503} +{"Pretrain/Learning Rate": 2.673654029173217e-07, "Pretrain/Loss": 1.9819775819778442, "Pretrain/Loss (Raw)": 1.9765934944152832, "Pretrain/Step": 9105, "Pretrain/Step Time": 8.485714729875326} +{"Pretrain/Learning Rate": 2.6612837083585527e-07, "Pretrain/Loss": 1.9821498394012451, "Pretrain/Loss (Raw)": 1.9799036979675293, "Pretrain/Step": 9106, "Pretrain/Step Time": 8.483365967869759} +{"Pretrain/Learning Rate": 2.648941917977904e-07, "Pretrain/Loss": 1.9821803569793701, "Pretrain/Loss (Raw)": 1.9526618719100952, "Pretrain/Step": 9107, "Pretrain/Step Time": 8.484282845631242} +{"Pretrain/Learning Rate": 2.6366286594549093e-07, "Pretrain/Loss": 1.9827529191970825, "Pretrain/Loss (Raw)": 1.9879063367843628, "Pretrain/Step": 9108, "Pretrain/Step Time": 8.483570018783212} +{"Pretrain/Learning Rate": 2.624343934209822e-07, "Pretrain/Loss": 1.982701301574707, "Pretrain/Loss (Raw)": 2.001225233078003, "Pretrain/Step": 9109, "Pretrain/Step Time": 8.485304910689592} +{"Pretrain/Learning Rate": 2.6120877436597577e-07, "Pretrain/Loss": 1.9812066555023193, "Pretrain/Loss (Raw)": 1.8980766534805298, "Pretrain/Step": 9110, "Pretrain/Step Time": 8.484194805845618} +{"Pretrain/Learning Rate": 2.59986008921842e-07, "Pretrain/Loss": 1.9797377586364746, "Pretrain/Loss (Raw)": 1.852223515510559, "Pretrain/Step": 9111, "Pretrain/Step Time": 8.48365068808198} +{"Pretrain/Learning Rate": 2.587660972296263e-07, "Pretrain/Loss": 1.9785841703414917, "Pretrain/Loss (Raw)": 2.0277657508850098, "Pretrain/Step": 9112, "Pretrain/Step Time": 8.485941031947732} +{"Pretrain/Learning Rate": 2.575490394300495e-07, "Pretrain/Loss": 1.9779670238494873, "Pretrain/Loss (Raw)": 1.8759723901748657, "Pretrain/Step": 9113, "Pretrain/Step Time": 8.48856070265174} +{"Pretrain/Learning Rate": 2.5633483566349645e-07, "Pretrain/Loss": 1.9779026508331299, "Pretrain/Loss (Raw)": 2.0158369541168213, "Pretrain/Step": 9114, "Pretrain/Step Time": 8.486550748348236} +{"Pretrain/Learning Rate": 2.551234860700219e-07, "Pretrain/Loss": 1.9777861833572388, "Pretrain/Loss (Raw)": 1.8540529012680054, "Pretrain/Step": 9115, "Pretrain/Step Time": 8.483424985781312} +{"Pretrain/Learning Rate": 2.5391499078935845e-07, "Pretrain/Loss": 1.9805271625518799, "Pretrain/Loss (Raw)": 2.1255598068237305, "Pretrain/Step": 9116, "Pretrain/Step Time": 8.484121514484286} +{"Pretrain/Learning Rate": 2.527093499609029e-07, "Pretrain/Loss": 1.9803069829940796, "Pretrain/Loss (Raw)": 2.021759271621704, "Pretrain/Step": 9117, "Pretrain/Step Time": 8.489040652289987} +{"Pretrain/Learning Rate": 2.515065637237302e-07, "Pretrain/Loss": 1.9815239906311035, "Pretrain/Loss (Raw)": 1.9767216444015503, "Pretrain/Step": 9118, "Pretrain/Step Time": 8.489627560600638} +{"Pretrain/Learning Rate": 2.5030663221657646e-07, "Pretrain/Loss": 1.9827628135681152, "Pretrain/Loss (Raw)": 2.0507898330688477, "Pretrain/Step": 9119, "Pretrain/Step Time": 8.486991984769702} +{"Pretrain/Learning Rate": 2.491095555778533e-07, "Pretrain/Loss": 1.982344388961792, "Pretrain/Loss (Raw)": 2.000422477722168, "Pretrain/Step": 9120, "Pretrain/Step Time": 8.486943405121565} +{"Pretrain/Learning Rate": 2.479153339456447e-07, "Pretrain/Loss": 1.9823884963989258, "Pretrain/Loss (Raw)": 1.9642605781555176, "Pretrain/Step": 9121, "Pretrain/Step Time": 8.48586723022163} +{"Pretrain/Learning Rate": 2.467239674577071e-07, "Pretrain/Loss": 1.981471061706543, "Pretrain/Loss (Raw)": 1.9536404609680176, "Pretrain/Step": 9122, "Pretrain/Step Time": 8.48629991710186} +{"Pretrain/Learning Rate": 2.4553545625145835e-07, "Pretrain/Loss": 1.981168270111084, "Pretrain/Loss (Raw)": 2.0410315990448, "Pretrain/Step": 9123, "Pretrain/Step Time": 8.486878765746951} +{"Pretrain/Learning Rate": 2.4434980046399713e-07, "Pretrain/Loss": 1.9807153940200806, "Pretrain/Loss (Raw)": 2.053166389465332, "Pretrain/Step": 9124, "Pretrain/Step Time": 8.49052900634706} +{"Pretrain/Learning Rate": 2.431670002320863e-07, "Pretrain/Loss": 1.9796605110168457, "Pretrain/Loss (Raw)": 1.8778111934661865, "Pretrain/Step": 9125, "Pretrain/Step Time": 8.490191336721182} +{"Pretrain/Learning Rate": 2.419870556921611e-07, "Pretrain/Loss": 1.9802742004394531, "Pretrain/Loss (Raw)": 2.0417094230651855, "Pretrain/Step": 9126, "Pretrain/Step Time": 8.489601574838161} +{"Pretrain/Learning Rate": 2.4080996698032934e-07, "Pretrain/Loss": 1.9809961318969727, "Pretrain/Loss (Raw)": 2.051992893218994, "Pretrain/Step": 9127, "Pretrain/Step Time": 8.487299285829067} +{"Pretrain/Learning Rate": 2.3963573423236573e-07, "Pretrain/Loss": 1.9821693897247314, "Pretrain/Loss (Raw)": 2.0322139263153076, "Pretrain/Step": 9128, "Pretrain/Step Time": 8.490130089223385} +{"Pretrain/Learning Rate": 2.384643575837203e-07, "Pretrain/Loss": 1.9835774898529053, "Pretrain/Loss (Raw)": 2.083547830581665, "Pretrain/Step": 9129, "Pretrain/Step Time": 8.492998883128166} +{"Pretrain/Learning Rate": 2.3729583716950998e-07, "Pretrain/Loss": 1.9855844974517822, "Pretrain/Loss (Raw)": 2.1221654415130615, "Pretrain/Step": 9130, "Pretrain/Step Time": 8.495648805052042} +{"Pretrain/Learning Rate": 2.3613017312451858e-07, "Pretrain/Loss": 1.9870917797088623, "Pretrain/Loss (Raw)": 2.1591460704803467, "Pretrain/Step": 9131, "Pretrain/Step Time": 8.48948367126286} +{"Pretrain/Learning Rate": 2.3496736558321354e-07, "Pretrain/Loss": 1.9887735843658447, "Pretrain/Loss (Raw)": 1.9771337509155273, "Pretrain/Step": 9132, "Pretrain/Step Time": 8.48887070082128} +{"Pretrain/Learning Rate": 2.3380741467971534e-07, "Pretrain/Loss": 1.987693190574646, "Pretrain/Loss (Raw)": 1.9041370153427124, "Pretrain/Step": 9133, "Pretrain/Step Time": 8.48853437229991} +{"Pretrain/Learning Rate": 2.3265032054783365e-07, "Pretrain/Loss": 1.9881327152252197, "Pretrain/Loss (Raw)": 2.180867910385132, "Pretrain/Step": 9134, "Pretrain/Step Time": 8.491445053368807} +{"Pretrain/Learning Rate": 2.3149608332103113e-07, "Pretrain/Loss": 1.9879157543182373, "Pretrain/Loss (Raw)": 2.016674518585205, "Pretrain/Step": 9135, "Pretrain/Step Time": 8.490198642015457} +{"Pretrain/Learning Rate": 2.303447031324485e-07, "Pretrain/Loss": 1.9865999221801758, "Pretrain/Loss (Raw)": 2.0202579498291016, "Pretrain/Step": 9136, "Pretrain/Step Time": 8.48865501396358} +{"Pretrain/Learning Rate": 2.2919618011490174e-07, "Pretrain/Loss": 1.9856083393096924, "Pretrain/Loss (Raw)": 1.7930225133895874, "Pretrain/Step": 9137, "Pretrain/Step Time": 8.488769315183163} +{"Pretrain/Learning Rate": 2.28050514400871e-07, "Pretrain/Loss": 1.9871344566345215, "Pretrain/Loss (Raw)": 2.051084041595459, "Pretrain/Step": 9138, "Pretrain/Step Time": 8.490746585652232} +{"Pretrain/Learning Rate": 2.269077061225089e-07, "Pretrain/Loss": 1.9862895011901855, "Pretrain/Loss (Raw)": 1.8202186822891235, "Pretrain/Step": 9139, "Pretrain/Step Time": 8.489746587350965} +{"Pretrain/Learning Rate": 2.2576775541163498e-07, "Pretrain/Loss": 1.9855070114135742, "Pretrain/Loss (Raw)": 2.0053892135620117, "Pretrain/Step": 9140, "Pretrain/Step Time": 8.491200506687164} +{"Pretrain/Learning Rate": 2.2463066239974684e-07, "Pretrain/Loss": 1.982619047164917, "Pretrain/Loss (Raw)": 1.8159635066986084, "Pretrain/Step": 9141, "Pretrain/Step Time": 8.491879733279347} +{"Pretrain/Learning Rate": 2.2349642721800346e-07, "Pretrain/Loss": 1.980835199356079, "Pretrain/Loss (Raw)": 1.95680570602417, "Pretrain/Step": 9142, "Pretrain/Step Time": 8.48958564735949} +{"Pretrain/Learning Rate": 2.2236504999723906e-07, "Pretrain/Loss": 1.982164740562439, "Pretrain/Loss (Raw)": 2.081320285797119, "Pretrain/Step": 9143, "Pretrain/Step Time": 8.488095298409462} +{"Pretrain/Learning Rate": 2.2123653086796038e-07, "Pretrain/Loss": 1.984163761138916, "Pretrain/Loss (Raw)": 2.2709271907806396, "Pretrain/Step": 9144, "Pretrain/Step Time": 8.491451362147927} +{"Pretrain/Learning Rate": 2.2011086996034103e-07, "Pretrain/Loss": 1.9827017784118652, "Pretrain/Loss (Raw)": 1.8866828680038452, "Pretrain/Step": 9145, "Pretrain/Step Time": 8.492050847038627} +{"Pretrain/Learning Rate": 2.1898806740422163e-07, "Pretrain/Loss": 1.982941746711731, "Pretrain/Loss (Raw)": 2.023573398590088, "Pretrain/Step": 9146, "Pretrain/Step Time": 8.493363758549094} +{"Pretrain/Learning Rate": 2.1786812332912076e-07, "Pretrain/Loss": 1.9835045337677002, "Pretrain/Loss (Raw)": 2.001343011856079, "Pretrain/Step": 9147, "Pretrain/Step Time": 8.492916287854314} +{"Pretrain/Learning Rate": 2.1675103786422402e-07, "Pretrain/Loss": 1.9844615459442139, "Pretrain/Loss (Raw)": 2.209312915802002, "Pretrain/Step": 9148, "Pretrain/Step Time": 8.489739967510104} +{"Pretrain/Learning Rate": 2.1563681113838387e-07, "Pretrain/Loss": 1.9849870204925537, "Pretrain/Loss (Raw)": 2.043440103530884, "Pretrain/Step": 9149, "Pretrain/Step Time": 8.488311504945159} +{"Pretrain/Learning Rate": 2.145254432801308e-07, "Pretrain/Loss": 1.983123540878296, "Pretrain/Loss (Raw)": 1.8549984693527222, "Pretrain/Step": 9150, "Pretrain/Step Time": 8.49113005399704} +{"Pretrain/Learning Rate": 2.1341693441765398e-07, "Pretrain/Loss": 1.9854384660720825, "Pretrain/Loss (Raw)": 2.1499438285827637, "Pretrain/Step": 9151, "Pretrain/Step Time": 8.491717515513301} +{"Pretrain/Learning Rate": 2.123112846788261e-07, "Pretrain/Loss": 1.9848301410675049, "Pretrain/Loss (Raw)": 1.9679930210113525, "Pretrain/Step": 9152, "Pretrain/Step Time": 8.49004140496254} +{"Pretrain/Learning Rate": 2.112084941911785e-07, "Pretrain/Loss": 1.9839911460876465, "Pretrain/Loss (Raw)": 1.8331161737442017, "Pretrain/Step": 9153, "Pretrain/Step Time": 8.489035684615374} +{"Pretrain/Learning Rate": 2.101085630819205e-07, "Pretrain/Loss": 1.9834907054901123, "Pretrain/Loss (Raw)": 2.042783498764038, "Pretrain/Step": 9154, "Pretrain/Step Time": 8.488462306559086} +{"Pretrain/Learning Rate": 2.0901149147792841e-07, "Pretrain/Loss": 1.9820606708526611, "Pretrain/Loss (Raw)": 1.8102161884307861, "Pretrain/Step": 9155, "Pretrain/Step Time": 8.490380683913827} +{"Pretrain/Learning Rate": 2.0791727950574823e-07, "Pretrain/Loss": 1.9808952808380127, "Pretrain/Loss (Raw)": 1.9078402519226074, "Pretrain/Step": 9156, "Pretrain/Step Time": 8.486073361709714} +{"Pretrain/Learning Rate": 2.0682592729159567e-07, "Pretrain/Loss": 1.9825775623321533, "Pretrain/Loss (Raw)": 2.2024009227752686, "Pretrain/Step": 9157, "Pretrain/Step Time": 8.487287739291787} +{"Pretrain/Learning Rate": 2.0573743496136167e-07, "Pretrain/Loss": 1.984027624130249, "Pretrain/Loss (Raw)": 2.054192066192627, "Pretrain/Step": 9158, "Pretrain/Step Time": 8.483058664947748} +{"Pretrain/Learning Rate": 2.0465180264060135e-07, "Pretrain/Loss": 1.9840545654296875, "Pretrain/Loss (Raw)": 2.0650861263275146, "Pretrain/Step": 9159, "Pretrain/Step Time": 8.487811502069235} +{"Pretrain/Learning Rate": 2.0356903045453958e-07, "Pretrain/Loss": 1.9833714962005615, "Pretrain/Loss (Raw)": 2.09303879737854, "Pretrain/Step": 9160, "Pretrain/Step Time": 8.487527402117848} +{"Pretrain/Learning Rate": 2.0248911852807916e-07, "Pretrain/Loss": 1.9872463941574097, "Pretrain/Loss (Raw)": 2.132732629776001, "Pretrain/Step": 9161, "Pretrain/Step Time": 8.488613719120622} +{"Pretrain/Learning Rate": 2.0141206698578163e-07, "Pretrain/Loss": 1.9869716167449951, "Pretrain/Loss (Raw)": 1.915798306465149, "Pretrain/Step": 9162, "Pretrain/Step Time": 8.486792542040348} +{"Pretrain/Learning Rate": 2.0033787595188925e-07, "Pretrain/Loss": 1.9851224422454834, "Pretrain/Loss (Raw)": 1.8857358694076538, "Pretrain/Step": 9163, "Pretrain/Step Time": 8.485798807814717} +{"Pretrain/Learning Rate": 1.9926654555030566e-07, "Pretrain/Loss": 1.9868817329406738, "Pretrain/Loss (Raw)": 1.9821727275848389, "Pretrain/Step": 9164, "Pretrain/Step Time": 8.48380065523088} +{"Pretrain/Learning Rate": 1.981980759046126e-07, "Pretrain/Loss": 1.987494945526123, "Pretrain/Loss (Raw)": 2.0082597732543945, "Pretrain/Step": 9165, "Pretrain/Step Time": 8.483191965147853} +{"Pretrain/Learning Rate": 1.9713246713805588e-07, "Pretrain/Loss": 1.9900063276290894, "Pretrain/Loss (Raw)": 2.029000759124756, "Pretrain/Step": 9166, "Pretrain/Step Time": 8.484608491882682} +{"Pretrain/Learning Rate": 1.960697193735511e-07, "Pretrain/Loss": 1.990032434463501, "Pretrain/Loss (Raw)": 2.0749475955963135, "Pretrain/Step": 9167, "Pretrain/Step Time": 8.486494788900018} +{"Pretrain/Learning Rate": 1.9500983273368633e-07, "Pretrain/Loss": 1.9884827136993408, "Pretrain/Loss (Raw)": 1.9256387948989868, "Pretrain/Step": 9168, "Pretrain/Step Time": 8.488826034590602} +{"Pretrain/Learning Rate": 1.9395280734072208e-07, "Pretrain/Loss": 1.9874507188796997, "Pretrain/Loss (Raw)": 1.900614857673645, "Pretrain/Step": 9169, "Pretrain/Step Time": 8.489435410127044} +{"Pretrain/Learning Rate": 1.9289864331658303e-07, "Pretrain/Loss": 1.98757004737854, "Pretrain/Loss (Raw)": 2.0515224933624268, "Pretrain/Step": 9170, "Pretrain/Step Time": 8.492870388552547} +{"Pretrain/Learning Rate": 1.9184734078286914e-07, "Pretrain/Loss": 1.9884960651397705, "Pretrain/Loss (Raw)": 1.9474798440933228, "Pretrain/Step": 9171, "Pretrain/Step Time": 8.490944240242243} +{"Pretrain/Learning Rate": 1.9079889986084453e-07, "Pretrain/Loss": 1.9881187677383423, "Pretrain/Loss (Raw)": 1.960166573524475, "Pretrain/Step": 9172, "Pretrain/Step Time": 8.49021977931261} +{"Pretrain/Learning Rate": 1.8975332067145134e-07, "Pretrain/Loss": 1.987233281135559, "Pretrain/Loss (Raw)": 1.871939778327942, "Pretrain/Step": 9173, "Pretrain/Step Time": 8.48741813749075} +{"Pretrain/Learning Rate": 1.8871060333529033e-07, "Pretrain/Loss": 1.9876952171325684, "Pretrain/Loss (Raw)": 2.0986361503601074, "Pretrain/Step": 9174, "Pretrain/Step Time": 8.481214355677366} +{"Pretrain/Learning Rate": 1.8767074797264306e-07, "Pretrain/Loss": 1.9904911518096924, "Pretrain/Loss (Raw)": 1.990831971168518, "Pretrain/Step": 9175, "Pretrain/Step Time": 8.479385692626238} +{"Pretrain/Learning Rate": 1.8663375470345523e-07, "Pretrain/Loss": 1.9903581142425537, "Pretrain/Loss (Raw)": 1.7122882604599, "Pretrain/Step": 9176, "Pretrain/Step Time": 8.48097231797874} +{"Pretrain/Learning Rate": 1.8559962364734507e-07, "Pretrain/Loss": 1.9899699687957764, "Pretrain/Loss (Raw)": 2.1116738319396973, "Pretrain/Step": 9177, "Pretrain/Step Time": 8.48306386731565} +{"Pretrain/Learning Rate": 1.845683549235977e-07, "Pretrain/Loss": 1.9910941123962402, "Pretrain/Loss (Raw)": 2.1760647296905518, "Pretrain/Step": 9178, "Pretrain/Step Time": 8.481844529509544} +{"Pretrain/Learning Rate": 1.8353994865116797e-07, "Pretrain/Loss": 1.9922418594360352, "Pretrain/Loss (Raw)": 1.9893605709075928, "Pretrain/Step": 9179, "Pretrain/Step Time": 8.48235910013318} +{"Pretrain/Learning Rate": 1.8251440494868598e-07, "Pretrain/Loss": 1.9923725128173828, "Pretrain/Loss (Raw)": 2.000591993331909, "Pretrain/Step": 9180, "Pretrain/Step Time": 8.482480302453041} +{"Pretrain/Learning Rate": 1.8149172393444603e-07, "Pretrain/Loss": 1.993882179260254, "Pretrain/Loss (Raw)": 1.965864658355713, "Pretrain/Step": 9181, "Pretrain/Step Time": 8.481682550162077} +{"Pretrain/Learning Rate": 1.8047190572641204e-07, "Pretrain/Loss": 1.9938712120056152, "Pretrain/Loss (Raw)": 2.022923707962036, "Pretrain/Step": 9182, "Pretrain/Step Time": 8.483984308317304} +{"Pretrain/Learning Rate": 1.794549504422205e-07, "Pretrain/Loss": 1.994063138961792, "Pretrain/Loss (Raw)": 2.15664005279541, "Pretrain/Step": 9183, "Pretrain/Step Time": 8.482682274654508} +{"Pretrain/Learning Rate": 1.7844085819918032e-07, "Pretrain/Loss": 1.9949095249176025, "Pretrain/Loss (Raw)": 2.0731284618377686, "Pretrain/Step": 9184, "Pretrain/Step Time": 8.480886505916715} +{"Pretrain/Learning Rate": 1.7742962911426464e-07, "Pretrain/Loss": 1.9955565929412842, "Pretrain/Loss (Raw)": 2.1346068382263184, "Pretrain/Step": 9185, "Pretrain/Step Time": 8.48269309103489} +{"Pretrain/Learning Rate": 1.7642126330411624e-07, "Pretrain/Loss": 1.9963425397872925, "Pretrain/Loss (Raw)": 2.0225486755371094, "Pretrain/Step": 9186, "Pretrain/Step Time": 8.48075757548213} +{"Pretrain/Learning Rate": 1.7541576088505318e-07, "Pretrain/Loss": 1.9950602054595947, "Pretrain/Loss (Raw)": 1.936267375946045, "Pretrain/Step": 9187, "Pretrain/Step Time": 8.479705411940813} +{"Pretrain/Learning Rate": 1.7441312197305494e-07, "Pretrain/Loss": 1.9947558641433716, "Pretrain/Loss (Raw)": 1.8606072664260864, "Pretrain/Step": 9188, "Pretrain/Step Time": 8.482231482863426} +{"Pretrain/Learning Rate": 1.7341334668378172e-07, "Pretrain/Loss": 1.9958149194717407, "Pretrain/Loss (Raw)": 2.0449419021606445, "Pretrain/Step": 9189, "Pretrain/Step Time": 8.476573131978512} +{"Pretrain/Learning Rate": 1.7241643513255247e-07, "Pretrain/Loss": 1.9965475797653198, "Pretrain/Loss (Raw)": 2.032925844192505, "Pretrain/Step": 9190, "Pretrain/Step Time": 8.47359573841095} +{"Pretrain/Learning Rate": 1.7142238743436401e-07, "Pretrain/Loss": 1.996190071105957, "Pretrain/Loss (Raw)": 1.996018886566162, "Pretrain/Step": 9191, "Pretrain/Step Time": 8.477523621171713} +{"Pretrain/Learning Rate": 1.7043120370387744e-07, "Pretrain/Loss": 1.9955964088439941, "Pretrain/Loss (Raw)": 1.9366109371185303, "Pretrain/Step": 9192, "Pretrain/Step Time": 8.479038367047906} +{"Pretrain/Learning Rate": 1.694428840554263e-07, "Pretrain/Loss": 1.995523452758789, "Pretrain/Loss (Raw)": 1.9853477478027344, "Pretrain/Step": 9193, "Pretrain/Step Time": 8.47905389405787} +{"Pretrain/Learning Rate": 1.6845742860301382e-07, "Pretrain/Loss": 1.9976147413253784, "Pretrain/Loss (Raw)": 2.0174124240875244, "Pretrain/Step": 9194, "Pretrain/Step Time": 8.482174342498183} +{"Pretrain/Learning Rate": 1.6747483746030746e-07, "Pretrain/Loss": 1.9977757930755615, "Pretrain/Loss (Raw)": 1.969213843345642, "Pretrain/Step": 9195, "Pretrain/Step Time": 8.48283707909286} +{"Pretrain/Learning Rate": 1.664951107406526e-07, "Pretrain/Loss": 1.9976755380630493, "Pretrain/Loss (Raw)": 1.9090605974197388, "Pretrain/Step": 9196, "Pretrain/Step Time": 8.483571473509073} +{"Pretrain/Learning Rate": 1.6551824855705888e-07, "Pretrain/Loss": 1.996025562286377, "Pretrain/Loss (Raw)": 1.8819894790649414, "Pretrain/Step": 9197, "Pretrain/Step Time": 8.482700997963548} +{"Pretrain/Learning Rate": 1.645442510222084e-07, "Pretrain/Loss": 1.9954122304916382, "Pretrain/Loss (Raw)": 1.8369847536087036, "Pretrain/Step": 9198, "Pretrain/Step Time": 8.484730442985892} +{"Pretrain/Learning Rate": 1.635731182484529e-07, "Pretrain/Loss": 1.998530387878418, "Pretrain/Loss (Raw)": 2.19640851020813, "Pretrain/Step": 9199, "Pretrain/Step Time": 8.4872629288584} +{"Pretrain/Learning Rate": 1.626048503478056e-07, "Pretrain/Loss": 1.9970558881759644, "Pretrain/Loss (Raw)": 1.8396377563476562, "Pretrain/Step": 9200, "Pretrain/Step Time": 8.483293768018484} +{"Pretrain/Learning Rate": 1.6163944743196323e-07, "Pretrain/Loss": 1.9948675632476807, "Pretrain/Loss (Raw)": 1.68143892288208, "Pretrain/Step": 9201, "Pretrain/Step Time": 8.486796846613288} +{"Pretrain/Learning Rate": 1.6067690961228398e-07, "Pretrain/Loss": 1.9950199127197266, "Pretrain/Loss (Raw)": 1.7925968170166016, "Pretrain/Step": 9202, "Pretrain/Step Time": 8.487341990694404} +{"Pretrain/Learning Rate": 1.5971723699979013e-07, "Pretrain/Loss": 1.9962711334228516, "Pretrain/Loss (Raw)": 1.9324262142181396, "Pretrain/Step": 9203, "Pretrain/Step Time": 8.482923405244946} +{"Pretrain/Learning Rate": 1.5876042970518478e-07, "Pretrain/Loss": 1.9958654642105103, "Pretrain/Loss (Raw)": 1.8855828046798706, "Pretrain/Step": 9204, "Pretrain/Step Time": 8.481285402551293} +{"Pretrain/Learning Rate": 1.5780648783883523e-07, "Pretrain/Loss": 1.9955761432647705, "Pretrain/Loss (Raw)": 1.8663865327835083, "Pretrain/Step": 9205, "Pretrain/Step Time": 8.48048403672874} +{"Pretrain/Learning Rate": 1.5685541151077566e-07, "Pretrain/Loss": 1.99629545211792, "Pretrain/Loss (Raw)": 2.0262861251831055, "Pretrain/Step": 9206, "Pretrain/Step Time": 8.48304914869368} +{"Pretrain/Learning Rate": 1.5590720083071275e-07, "Pretrain/Loss": 1.9972598552703857, "Pretrain/Loss (Raw)": 2.0573525428771973, "Pretrain/Step": 9207, "Pretrain/Step Time": 8.481234140694141} +{"Pretrain/Learning Rate": 1.549618559080257e-07, "Pretrain/Loss": 1.996130347251892, "Pretrain/Loss (Raw)": 2.0531463623046875, "Pretrain/Step": 9208, "Pretrain/Step Time": 8.482232159003615} +{"Pretrain/Learning Rate": 1.5401937685175781e-07, "Pretrain/Loss": 1.9951996803283691, "Pretrain/Loss (Raw)": 2.0331146717071533, "Pretrain/Step": 9209, "Pretrain/Step Time": 8.482365932315588} +{"Pretrain/Learning Rate": 1.5307976377062216e-07, "Pretrain/Loss": 1.992525339126587, "Pretrain/Loss (Raw)": 1.6855461597442627, "Pretrain/Step": 9210, "Pretrain/Step Time": 8.481805199757218} +{"Pretrain/Learning Rate": 1.5214301677300425e-07, "Pretrain/Loss": 1.9908466339111328, "Pretrain/Loss (Raw)": 1.7956714630126953, "Pretrain/Step": 9211, "Pretrain/Step Time": 8.4847744833678} +{"Pretrain/Learning Rate": 1.512091359669565e-07, "Pretrain/Loss": 1.9912114143371582, "Pretrain/Loss (Raw)": 2.060234308242798, "Pretrain/Step": 9212, "Pretrain/Step Time": 8.483740352094173} +{"Pretrain/Learning Rate": 1.502781214602039e-07, "Pretrain/Loss": 1.990915298461914, "Pretrain/Loss (Raw)": 2.014575958251953, "Pretrain/Step": 9213, "Pretrain/Step Time": 8.480972718447447} +{"Pretrain/Learning Rate": 1.4934997336013557e-07, "Pretrain/Loss": 1.9905141592025757, "Pretrain/Loss (Raw)": 1.984248399734497, "Pretrain/Step": 9214, "Pretrain/Step Time": 8.482226176187396} +{"Pretrain/Learning Rate": 1.484246917738158e-07, "Pretrain/Loss": 1.9861805438995361, "Pretrain/Loss (Raw)": 1.6124886274337769, "Pretrain/Step": 9215, "Pretrain/Step Time": 8.482788752764463} +{"Pretrain/Learning Rate": 1.4750227680797312e-07, "Pretrain/Loss": 1.9829440116882324, "Pretrain/Loss (Raw)": 1.7064895629882812, "Pretrain/Step": 9216, "Pretrain/Step Time": 8.485404381528497} +{"Pretrain/Learning Rate": 1.4658272856900857e-07, "Pretrain/Loss": 1.98361074924469, "Pretrain/Loss (Raw)": 2.0971240997314453, "Pretrain/Step": 9217, "Pretrain/Step Time": 8.485609358176589} +{"Pretrain/Learning Rate": 1.4566604716299282e-07, "Pretrain/Loss": 1.9848302602767944, "Pretrain/Loss (Raw)": 2.1644766330718994, "Pretrain/Step": 9218, "Pretrain/Step Time": 8.486952193081379} +{"Pretrain/Learning Rate": 1.447522326956663e-07, "Pretrain/Loss": 1.9850034713745117, "Pretrain/Loss (Raw)": 2.0869007110595703, "Pretrain/Step": 9219, "Pretrain/Step Time": 8.482318377122283} +{"Pretrain/Learning Rate": 1.4384128527243356e-07, "Pretrain/Loss": 1.9840087890625, "Pretrain/Loss (Raw)": 1.8761065006256104, "Pretrain/Step": 9220, "Pretrain/Step Time": 8.482231387868524} +{"Pretrain/Learning Rate": 1.4293320499837171e-07, "Pretrain/Loss": 1.984853982925415, "Pretrain/Loss (Raw)": 2.041734457015991, "Pretrain/Step": 9221, "Pretrain/Step Time": 8.479892950505018} +{"Pretrain/Learning Rate": 1.4202799197823025e-07, "Pretrain/Loss": 1.9851058721542358, "Pretrain/Loss (Raw)": 2.047572135925293, "Pretrain/Step": 9222, "Pretrain/Step Time": 8.482285492122173} +{"Pretrain/Learning Rate": 1.4112564631642568e-07, "Pretrain/Loss": 1.985633373260498, "Pretrain/Loss (Raw)": 2.18476939201355, "Pretrain/Step": 9223, "Pretrain/Step Time": 8.484076553955674} +{"Pretrain/Learning Rate": 1.4022616811704137e-07, "Pretrain/Loss": 1.9890018701553345, "Pretrain/Loss (Raw)": 2.094420909881592, "Pretrain/Step": 9224, "Pretrain/Step Time": 8.483250042423606} +{"Pretrain/Learning Rate": 1.3932955748383049e-07, "Pretrain/Loss": 1.9871697425842285, "Pretrain/Loss (Raw)": 1.933605670928955, "Pretrain/Step": 9225, "Pretrain/Step Time": 8.482244063168764} +{"Pretrain/Learning Rate": 1.3843581452022137e-07, "Pretrain/Loss": 1.9872478246688843, "Pretrain/Loss (Raw)": 2.1899538040161133, "Pretrain/Step": 9226, "Pretrain/Step Time": 8.484875559806824} +{"Pretrain/Learning Rate": 1.3754493932930102e-07, "Pretrain/Loss": 1.9870662689208984, "Pretrain/Loss (Raw)": 2.033426523208618, "Pretrain/Step": 9227, "Pretrain/Step Time": 8.484414830803871} +{"Pretrain/Learning Rate": 1.3665693201383723e-07, "Pretrain/Loss": 1.988298773765564, "Pretrain/Loss (Raw)": 2.148322820663452, "Pretrain/Step": 9228, "Pretrain/Step Time": 8.483964832499623} +{"Pretrain/Learning Rate": 1.3577179267625638e-07, "Pretrain/Loss": 1.9865520000457764, "Pretrain/Loss (Raw)": 1.7585772275924683, "Pretrain/Step": 9229, "Pretrain/Step Time": 8.482525564730167} +{"Pretrain/Learning Rate": 1.3488952141866294e-07, "Pretrain/Loss": 1.9837946891784668, "Pretrain/Loss (Raw)": 1.618086814880371, "Pretrain/Step": 9230, "Pretrain/Step Time": 8.482778063043952} +{"Pretrain/Learning Rate": 1.3401011834282552e-07, "Pretrain/Loss": 1.9840986728668213, "Pretrain/Loss (Raw)": 1.8788772821426392, "Pretrain/Step": 9231, "Pretrain/Step Time": 8.482076942920685} +{"Pretrain/Learning Rate": 1.3313358355017959e-07, "Pretrain/Loss": 1.9833256006240845, "Pretrain/Loss (Raw)": 1.9216111898422241, "Pretrain/Step": 9232, "Pretrain/Step Time": 8.481122279539704} +{"Pretrain/Learning Rate": 1.3225991714183872e-07, "Pretrain/Loss": 1.9833558797836304, "Pretrain/Loss (Raw)": 1.9804751873016357, "Pretrain/Step": 9233, "Pretrain/Step Time": 8.483361441642046} +{"Pretrain/Learning Rate": 1.3138911921857788e-07, "Pretrain/Loss": 1.9840387105941772, "Pretrain/Loss (Raw)": 2.0673043727874756, "Pretrain/Step": 9234, "Pretrain/Step Time": 8.485359797254205} +{"Pretrain/Learning Rate": 1.3052118988083894e-07, "Pretrain/Loss": 1.9837894439697266, "Pretrain/Loss (Raw)": 1.9207544326782227, "Pretrain/Step": 9235, "Pretrain/Step Time": 8.481100419536233} +{"Pretrain/Learning Rate": 1.296561292287446e-07, "Pretrain/Loss": 1.9822736978530884, "Pretrain/Loss (Raw)": 1.7938892841339111, "Pretrain/Step": 9236, "Pretrain/Step Time": 8.48346133902669} +{"Pretrain/Learning Rate": 1.2879393736207336e-07, "Pretrain/Loss": 1.9818487167358398, "Pretrain/Loss (Raw)": 1.9468249082565308, "Pretrain/Step": 9237, "Pretrain/Step Time": 8.483913470059633} +{"Pretrain/Learning Rate": 1.2793461438028176e-07, "Pretrain/Loss": 1.9829281568527222, "Pretrain/Loss (Raw)": 2.036247491836548, "Pretrain/Step": 9238, "Pretrain/Step Time": 8.483945859596133} +{"Pretrain/Learning Rate": 1.270781603824933e-07, "Pretrain/Loss": 1.9835206270217896, "Pretrain/Loss (Raw)": 1.9280681610107422, "Pretrain/Step": 9239, "Pretrain/Step Time": 8.481974061578512} +{"Pretrain/Learning Rate": 1.2622457546749567e-07, "Pretrain/Loss": 1.9838316440582275, "Pretrain/Loss (Raw)": 2.0675852298736572, "Pretrain/Step": 9240, "Pretrain/Step Time": 8.483586410060525} +{"Pretrain/Learning Rate": 1.2537385973375448e-07, "Pretrain/Loss": 1.9859813451766968, "Pretrain/Loss (Raw)": 2.1511189937591553, "Pretrain/Step": 9241, "Pretrain/Step Time": 8.48213461600244} +{"Pretrain/Learning Rate": 1.2452601327939406e-07, "Pretrain/Loss": 1.986131191253662, "Pretrain/Loss (Raw)": 2.035008192062378, "Pretrain/Step": 9242, "Pretrain/Step Time": 8.485474506393075} +{"Pretrain/Learning Rate": 1.236810362022195e-07, "Pretrain/Loss": 1.987167239189148, "Pretrain/Loss (Raw)": 1.9866816997528076, "Pretrain/Step": 9243, "Pretrain/Step Time": 8.487751558423042} +{"Pretrain/Learning Rate": 1.228389285996917e-07, "Pretrain/Loss": 1.9859154224395752, "Pretrain/Loss (Raw)": 1.96532142162323, "Pretrain/Step": 9244, "Pretrain/Step Time": 8.484138235449791} +{"Pretrain/Learning Rate": 1.2199969056895523e-07, "Pretrain/Loss": 1.984311580657959, "Pretrain/Loss (Raw)": 1.8164805173873901, "Pretrain/Step": 9245, "Pretrain/Step Time": 8.480944391340017} +{"Pretrain/Learning Rate": 1.2116332220680758e-07, "Pretrain/Loss": 1.9830436706542969, "Pretrain/Loss (Raw)": 1.8144147396087646, "Pretrain/Step": 9246, "Pretrain/Step Time": 8.482010189443827} +{"Pretrain/Learning Rate": 1.2032982360973e-07, "Pretrain/Loss": 1.984017014503479, "Pretrain/Loss (Raw)": 2.175384759902954, "Pretrain/Step": 9247, "Pretrain/Step Time": 8.48352025821805} +{"Pretrain/Learning Rate": 1.1949919487386218e-07, "Pretrain/Loss": 1.9835646152496338, "Pretrain/Loss (Raw)": 1.9425108432769775, "Pretrain/Step": 9248, "Pretrain/Step Time": 8.484567638486624} +{"Pretrain/Learning Rate": 1.1867143609502195e-07, "Pretrain/Loss": 1.9820717573165894, "Pretrain/Loss (Raw)": 1.7731809616088867, "Pretrain/Step": 9249, "Pretrain/Step Time": 8.48475300334394} +{"Pretrain/Learning Rate": 1.1784654736868572e-07, "Pretrain/Loss": 1.9821370840072632, "Pretrain/Loss (Raw)": 1.9620029926300049, "Pretrain/Step": 9250, "Pretrain/Step Time": 8.486187521368265} +{"Pretrain/Learning Rate": 1.1702452879000514e-07, "Pretrain/Loss": 1.981827974319458, "Pretrain/Loss (Raw)": 2.001473903656006, "Pretrain/Step": 9251, "Pretrain/Step Time": 8.48580783046782} +{"Pretrain/Learning Rate": 1.1620538045380158e-07, "Pretrain/Loss": 1.9816868305206299, "Pretrain/Loss (Raw)": 2.035086154937744, "Pretrain/Step": 9252, "Pretrain/Step Time": 8.480843102559447} +{"Pretrain/Learning Rate": 1.1538910245456058e-07, "Pretrain/Loss": 1.9820760488510132, "Pretrain/Loss (Raw)": 1.9276374578475952, "Pretrain/Step": 9253, "Pretrain/Step Time": 8.48152614198625} +{"Pretrain/Learning Rate": 1.1457569488644294e-07, "Pretrain/Loss": 1.9809439182281494, "Pretrain/Loss (Raw)": 1.896769642829895, "Pretrain/Step": 9254, "Pretrain/Step Time": 8.48060031235218} +{"Pretrain/Learning Rate": 1.1376515784327634e-07, "Pretrain/Loss": 1.9794859886169434, "Pretrain/Loss (Raw)": 1.8654121160507202, "Pretrain/Step": 9255, "Pretrain/Step Time": 8.481611849740148} +{"Pretrain/Learning Rate": 1.1295749141854994e-07, "Pretrain/Loss": 1.9776582717895508, "Pretrain/Loss (Raw)": 1.798257827758789, "Pretrain/Step": 9256, "Pretrain/Step Time": 8.480739748105407} +{"Pretrain/Learning Rate": 1.1215269570543085e-07, "Pretrain/Loss": 1.9763144254684448, "Pretrain/Loss (Raw)": 1.911536455154419, "Pretrain/Step": 9257, "Pretrain/Step Time": 8.479256941005588} +{"Pretrain/Learning Rate": 1.1135077079675315e-07, "Pretrain/Loss": 1.9755886793136597, "Pretrain/Loss (Raw)": 2.0292632579803467, "Pretrain/Step": 9258, "Pretrain/Step Time": 8.475186610594392} +{"Pretrain/Learning Rate": 1.1055171678501785e-07, "Pretrain/Loss": 1.9743602275848389, "Pretrain/Loss (Raw)": 2.0019102096557617, "Pretrain/Step": 9259, "Pretrain/Step Time": 8.479384617879987} +{"Pretrain/Learning Rate": 1.0975553376239566e-07, "Pretrain/Loss": 1.9751542806625366, "Pretrain/Loss (Raw)": 2.0787580013275146, "Pretrain/Step": 9260, "Pretrain/Step Time": 8.481840683147311} +{"Pretrain/Learning Rate": 1.0896222182072424e-07, "Pretrain/Loss": 1.97610604763031, "Pretrain/Loss (Raw)": 2.0259742736816406, "Pretrain/Step": 9261, "Pretrain/Step Time": 8.482215883210301} +{"Pretrain/Learning Rate": 1.0817178105151371e-07, "Pretrain/Loss": 1.9744536876678467, "Pretrain/Loss (Raw)": 1.9693598747253418, "Pretrain/Step": 9262, "Pretrain/Step Time": 8.483576282858849} +{"Pretrain/Learning Rate": 1.0738421154594114e-07, "Pretrain/Loss": 1.9744601249694824, "Pretrain/Loss (Raw)": 2.017514705657959, "Pretrain/Step": 9263, "Pretrain/Step Time": 8.48294923081994} +{"Pretrain/Learning Rate": 1.0659951339485053e-07, "Pretrain/Loss": 1.9734044075012207, "Pretrain/Loss (Raw)": 1.88512122631073, "Pretrain/Step": 9264, "Pretrain/Step Time": 8.485032089054585} +{"Pretrain/Learning Rate": 1.0581768668875836e-07, "Pretrain/Loss": 1.9718877077102661, "Pretrain/Loss (Raw)": 1.5988917350769043, "Pretrain/Step": 9265, "Pretrain/Step Time": 8.484386270865798} +{"Pretrain/Learning Rate": 1.0503873151785082e-07, "Pretrain/Loss": 1.9711086750030518, "Pretrain/Loss (Raw)": 1.95135498046875, "Pretrain/Step": 9266, "Pretrain/Step Time": 8.485005542635918} +{"Pretrain/Learning Rate": 1.0426264797197272e-07, "Pretrain/Loss": 1.9729905128479004, "Pretrain/Loss (Raw)": 2.0610995292663574, "Pretrain/Step": 9267, "Pretrain/Step Time": 8.48263512738049} +{"Pretrain/Learning Rate": 1.0348943614064965e-07, "Pretrain/Loss": 1.9714150428771973, "Pretrain/Loss (Raw)": 1.803720474243164, "Pretrain/Step": 9268, "Pretrain/Step Time": 8.480081206187606} +{"Pretrain/Learning Rate": 1.027190961130714e-07, "Pretrain/Loss": 1.9723633527755737, "Pretrain/Loss (Raw)": 1.9373501539230347, "Pretrain/Step": 9269, "Pretrain/Step Time": 8.477903122082353} +{"Pretrain/Learning Rate": 1.0195162797809743e-07, "Pretrain/Loss": 1.97343909740448, "Pretrain/Loss (Raw)": 2.0944907665252686, "Pretrain/Step": 9270, "Pretrain/Step Time": 8.476619556546211} +{"Pretrain/Learning Rate": 1.0118703182425137e-07, "Pretrain/Loss": 1.9725239276885986, "Pretrain/Loss (Raw)": 1.9642064571380615, "Pretrain/Step": 9271, "Pretrain/Step Time": 8.478353075683117} +{"Pretrain/Learning Rate": 1.0042530773973213e-07, "Pretrain/Loss": 1.9713351726531982, "Pretrain/Loss (Raw)": 2.118750810623169, "Pretrain/Step": 9272, "Pretrain/Step Time": 8.475418034940958} +{"Pretrain/Learning Rate": 9.966645581240274e-08, "Pretrain/Loss": 1.9700466394424438, "Pretrain/Loss (Raw)": 1.721758246421814, "Pretrain/Step": 9273, "Pretrain/Step Time": 8.474997533485293} +{"Pretrain/Learning Rate": 9.891047612979876e-08, "Pretrain/Loss": 1.9697468280792236, "Pretrain/Loss (Raw)": 1.9851901531219482, "Pretrain/Step": 9274, "Pretrain/Step Time": 8.47769045829773} +{"Pretrain/Learning Rate": 9.815736877911985e-08, "Pretrain/Loss": 1.9677125215530396, "Pretrain/Loss (Raw)": 1.7409541606903076, "Pretrain/Step": 9275, "Pretrain/Step Time": 8.47431792318821} +{"Pretrain/Learning Rate": 9.740713384723543e-08, "Pretrain/Loss": 1.9653199911117554, "Pretrain/Loss (Raw)": 1.9030559062957764, "Pretrain/Step": 9276, "Pretrain/Step Time": 8.476924000307918} +{"Pretrain/Learning Rate": 9.665977142068738e-08, "Pretrain/Loss": 1.9650684595108032, "Pretrain/Loss (Raw)": 2.0112478733062744, "Pretrain/Step": 9277, "Pretrain/Step Time": 8.476663794368505} +{"Pretrain/Learning Rate": 9.591528158568453e-08, "Pretrain/Loss": 1.967771053314209, "Pretrain/Loss (Raw)": 2.200927495956421, "Pretrain/Step": 9278, "Pretrain/Step Time": 8.4759138841182} +{"Pretrain/Learning Rate": 9.51736644281026e-08, "Pretrain/Loss": 1.9668723344802856, "Pretrain/Loss (Raw)": 2.0349156856536865, "Pretrain/Step": 9279, "Pretrain/Step Time": 8.476115617901087} +{"Pretrain/Learning Rate": 9.443492003348431e-08, "Pretrain/Loss": 1.9665887355804443, "Pretrain/Loss (Raw)": 1.9317054748535156, "Pretrain/Step": 9280, "Pretrain/Step Time": 8.477359915152192} +{"Pretrain/Learning Rate": 9.369904848704758e-08, "Pretrain/Loss": 1.9677585363388062, "Pretrain/Loss (Raw)": 1.9828412532806396, "Pretrain/Step": 9281, "Pretrain/Step Time": 8.479362113401294} +{"Pretrain/Learning Rate": 9.296604987366898e-08, "Pretrain/Loss": 1.9681960344314575, "Pretrain/Loss (Raw)": 2.0987792015075684, "Pretrain/Step": 9282, "Pretrain/Step Time": 8.481304347515106} +{"Pretrain/Learning Rate": 9.223592427790584e-08, "Pretrain/Loss": 1.9699004888534546, "Pretrain/Loss (Raw)": 2.0283901691436768, "Pretrain/Step": 9283, "Pretrain/Step Time": 8.482466876506805} +{"Pretrain/Learning Rate": 9.150867178397693e-08, "Pretrain/Loss": 1.9719855785369873, "Pretrain/Loss (Raw)": 2.174727439880371, "Pretrain/Step": 9284, "Pretrain/Step Time": 8.482820093631744} +{"Pretrain/Learning Rate": 9.078429247576791e-08, "Pretrain/Loss": 1.9709312915802002, "Pretrain/Loss (Raw)": 2.067436456680298, "Pretrain/Step": 9285, "Pretrain/Step Time": 8.48181233741343} +{"Pretrain/Learning Rate": 9.006278643683696e-08, "Pretrain/Loss": 1.970414400100708, "Pretrain/Loss (Raw)": 1.9880378246307373, "Pretrain/Step": 9286, "Pretrain/Step Time": 8.484761474654078} +{"Pretrain/Learning Rate": 8.934415375041195e-08, "Pretrain/Loss": 1.9690158367156982, "Pretrain/Loss (Raw)": 1.8860691785812378, "Pretrain/Step": 9287, "Pretrain/Step Time": 8.484072411432862} +{"Pretrain/Learning Rate": 8.86283944993821e-08, "Pretrain/Loss": 1.9678627252578735, "Pretrain/Loss (Raw)": 1.9454548358917236, "Pretrain/Step": 9288, "Pretrain/Step Time": 8.481222864240408} +{"Pretrain/Learning Rate": 8.791550876631193e-08, "Pretrain/Loss": 1.9669032096862793, "Pretrain/Loss (Raw)": 2.0099117755889893, "Pretrain/Step": 9289, "Pretrain/Step Time": 8.482941014692187} +{"Pretrain/Learning Rate": 8.720549663343291e-08, "Pretrain/Loss": 1.9679877758026123, "Pretrain/Loss (Raw)": 2.0546112060546875, "Pretrain/Step": 9290, "Pretrain/Step Time": 8.480996087193489} +{"Pretrain/Learning Rate": 8.649835818264618e-08, "Pretrain/Loss": 1.9699537754058838, "Pretrain/Loss (Raw)": 2.1373980045318604, "Pretrain/Step": 9291, "Pretrain/Step Time": 8.484481498599052} +{"Pretrain/Learning Rate": 8.579409349551981e-08, "Pretrain/Loss": 1.9699366092681885, "Pretrain/Loss (Raw)": 1.979958415031433, "Pretrain/Step": 9292, "Pretrain/Step Time": 8.482304606586695} +{"Pretrain/Learning Rate": 8.509270265328884e-08, "Pretrain/Loss": 1.9726474285125732, "Pretrain/Loss (Raw)": 2.355264663696289, "Pretrain/Step": 9293, "Pretrain/Step Time": 8.483718790113926} +{"Pretrain/Learning Rate": 8.439418573685797e-08, "Pretrain/Loss": 1.9702715873718262, "Pretrain/Loss (Raw)": 1.7248938083648682, "Pretrain/Step": 9294, "Pretrain/Step Time": 8.485650980845094} +{"Pretrain/Learning Rate": 8.369854282680168e-08, "Pretrain/Loss": 1.9687527418136597, "Pretrain/Loss (Raw)": 1.8805208206176758, "Pretrain/Step": 9295, "Pretrain/Step Time": 8.482010452076793} +{"Pretrain/Learning Rate": 8.300577400336407e-08, "Pretrain/Loss": 1.968717098236084, "Pretrain/Loss (Raw)": 1.9210788011550903, "Pretrain/Step": 9296, "Pretrain/Step Time": 8.482336761429906} +{"Pretrain/Learning Rate": 8.231587934645068e-08, "Pretrain/Loss": 1.969125509262085, "Pretrain/Loss (Raw)": 1.9528950452804565, "Pretrain/Step": 9297, "Pretrain/Step Time": 8.483953300863504} +{"Pretrain/Learning Rate": 8.162885893564786e-08, "Pretrain/Loss": 1.9690171480178833, "Pretrain/Loss (Raw)": 2.037649154663086, "Pretrain/Step": 9298, "Pretrain/Step Time": 8.480675600469112} +{"Pretrain/Learning Rate": 8.0944712850195e-08, "Pretrain/Loss": 1.9694432020187378, "Pretrain/Loss (Raw)": 2.0020198822021484, "Pretrain/Step": 9299, "Pretrain/Step Time": 8.482276685535908} +{"Pretrain/Learning Rate": 8.026344116901507e-08, "Pretrain/Loss": 1.970837116241455, "Pretrain/Loss (Raw)": 2.1385767459869385, "Pretrain/Step": 9300, "Pretrain/Step Time": 8.48318994231522} +{"Pretrain/Learning Rate": 7.958504397068966e-08, "Pretrain/Loss": 1.9702250957489014, "Pretrain/Loss (Raw)": 1.7936128377914429, "Pretrain/Step": 9301, "Pretrain/Step Time": 8.4877656288445} +{"Pretrain/Learning Rate": 7.890952133347007e-08, "Pretrain/Loss": 1.969102382659912, "Pretrain/Loss (Raw)": 1.9549334049224854, "Pretrain/Step": 9302, "Pretrain/Step Time": 8.48824418708682} +{"Pretrain/Learning Rate": 7.823687333528008e-08, "Pretrain/Loss": 1.969148874282837, "Pretrain/Loss (Raw)": 1.9967734813690186, "Pretrain/Step": 9303, "Pretrain/Step Time": 8.492644742131233} +{"Pretrain/Learning Rate": 7.756710005371037e-08, "Pretrain/Loss": 1.9702904224395752, "Pretrain/Loss (Raw)": 1.8584221601486206, "Pretrain/Step": 9304, "Pretrain/Step Time": 8.489675940945745} +{"Pretrain/Learning Rate": 7.690020156601585e-08, "Pretrain/Loss": 1.9703139066696167, "Pretrain/Loss (Raw)": 2.1146657466888428, "Pretrain/Step": 9305, "Pretrain/Step Time": 8.48742507956922} +{"Pretrain/Learning Rate": 7.623617794912386e-08, "Pretrain/Loss": 1.9683451652526855, "Pretrain/Loss (Raw)": 1.9240587949752808, "Pretrain/Step": 9306, "Pretrain/Step Time": 8.493550226092339} +{"Pretrain/Learning Rate": 7.557502927963145e-08, "Pretrain/Loss": 1.967357873916626, "Pretrain/Loss (Raw)": 1.8630080223083496, "Pretrain/Step": 9307, "Pretrain/Step Time": 8.49230494350195} +{"Pretrain/Learning Rate": 7.491675563379985e-08, "Pretrain/Loss": 1.967360258102417, "Pretrain/Loss (Raw)": 2.00089693069458, "Pretrain/Step": 9308, "Pretrain/Step Time": 8.48880628682673} +{"Pretrain/Learning Rate": 7.426135708756e-08, "Pretrain/Loss": 1.9674910306930542, "Pretrain/Loss (Raw)": 1.982603669166565, "Pretrain/Step": 9309, "Pretrain/Step Time": 8.491352301090956} +{"Pretrain/Learning Rate": 7.360883371651528e-08, "Pretrain/Loss": 1.9680359363555908, "Pretrain/Loss (Raw)": 2.0926520824432373, "Pretrain/Step": 9310, "Pretrain/Step Time": 8.485764360055327} +{"Pretrain/Learning Rate": 7.295918559593051e-08, "Pretrain/Loss": 1.9671130180358887, "Pretrain/Loss (Raw)": 2.038503885269165, "Pretrain/Step": 9311, "Pretrain/Step Time": 8.488562164828181} +{"Pretrain/Learning Rate": 7.231241280074297e-08, "Pretrain/Loss": 1.967015027999878, "Pretrain/Loss (Raw)": 2.0605993270874023, "Pretrain/Step": 9312, "Pretrain/Step Time": 8.486736496910453} +{"Pretrain/Learning Rate": 7.166851540555963e-08, "Pretrain/Loss": 1.9681037664413452, "Pretrain/Loss (Raw)": 2.2739672660827637, "Pretrain/Step": 9313, "Pretrain/Step Time": 8.485050674527884} +{"Pretrain/Learning Rate": 7.102749348465165e-08, "Pretrain/Loss": 1.9681594371795654, "Pretrain/Loss (Raw)": 2.029672384262085, "Pretrain/Step": 9314, "Pretrain/Step Time": 8.487504160031676} +{"Pretrain/Learning Rate": 7.038934711196265e-08, "Pretrain/Loss": 1.9693303108215332, "Pretrain/Loss (Raw)": 2.086138963699341, "Pretrain/Step": 9315, "Pretrain/Step Time": 8.490990601480007} +{"Pretrain/Learning Rate": 6.975407636110043e-08, "Pretrain/Loss": 1.9710111618041992, "Pretrain/Loss (Raw)": 2.0757429599761963, "Pretrain/Step": 9316, "Pretrain/Step Time": 8.488834589719772} +{"Pretrain/Learning Rate": 6.912168130534525e-08, "Pretrain/Loss": 1.9698959589004517, "Pretrain/Loss (Raw)": 1.902212381362915, "Pretrain/Step": 9317, "Pretrain/Step Time": 8.487623322755098} +{"Pretrain/Learning Rate": 6.84921620176443e-08, "Pretrain/Loss": 1.968695878982544, "Pretrain/Loss (Raw)": 1.8792963027954102, "Pretrain/Step": 9318, "Pretrain/Step Time": 8.48859640955925} +{"Pretrain/Learning Rate": 6.786551857060896e-08, "Pretrain/Loss": 1.966484546661377, "Pretrain/Loss (Raw)": 1.712974190711975, "Pretrain/Step": 9319, "Pretrain/Step Time": 8.486698528751731} +{"Pretrain/Learning Rate": 6.724175103652308e-08, "Pretrain/Loss": 1.9677554368972778, "Pretrain/Loss (Raw)": 2.099295139312744, "Pretrain/Step": 9320, "Pretrain/Step Time": 8.484458828344941} +{"Pretrain/Learning Rate": 6.66208594873402e-08, "Pretrain/Loss": 1.9677090644836426, "Pretrain/Loss (Raw)": 1.979408621788025, "Pretrain/Step": 9321, "Pretrain/Step Time": 8.483211634680629} +{"Pretrain/Learning Rate": 6.600284399468082e-08, "Pretrain/Loss": 1.9660893678665161, "Pretrain/Loss (Raw)": 1.8100844621658325, "Pretrain/Step": 9322, "Pretrain/Step Time": 8.479676453396678} +{"Pretrain/Learning Rate": 6.538770462982957e-08, "Pretrain/Loss": 1.9659299850463867, "Pretrain/Loss (Raw)": 1.948830008506775, "Pretrain/Step": 9323, "Pretrain/Step Time": 8.485733913257718} +{"Pretrain/Learning Rate": 6.47754414637436e-08, "Pretrain/Loss": 1.9659924507141113, "Pretrain/Loss (Raw)": 1.9170434474945068, "Pretrain/Step": 9324, "Pretrain/Step Time": 8.485575802624226} +{"Pretrain/Learning Rate": 6.416605456704694e-08, "Pretrain/Loss": 1.9660840034484863, "Pretrain/Loss (Raw)": 1.893725037574768, "Pretrain/Step": 9325, "Pretrain/Step Time": 8.486182415857911} +{"Pretrain/Learning Rate": 6.355954401003339e-08, "Pretrain/Loss": 1.9673621654510498, "Pretrain/Loss (Raw)": 2.000584125518799, "Pretrain/Step": 9326, "Pretrain/Step Time": 8.486030476167798} +{"Pretrain/Learning Rate": 6.295590986266642e-08, "Pretrain/Loss": 1.9660849571228027, "Pretrain/Loss (Raw)": 2.0329182147979736, "Pretrain/Step": 9327, "Pretrain/Step Time": 8.48303690366447} +{"Pretrain/Learning Rate": 6.235515219456811e-08, "Pretrain/Loss": 1.968935251235962, "Pretrain/Loss (Raw)": 2.20447039604187, "Pretrain/Step": 9328, "Pretrain/Step Time": 8.482286067679524} +{"Pretrain/Learning Rate": 6.175727107504137e-08, "Pretrain/Loss": 1.9712224006652832, "Pretrain/Loss (Raw)": 1.9742062091827393, "Pretrain/Step": 9329, "Pretrain/Step Time": 8.482501881197095} +{"Pretrain/Learning Rate": 6.116226657304769e-08, "Pretrain/Loss": 1.972450613975525, "Pretrain/Loss (Raw)": 1.9497979879379272, "Pretrain/Step": 9330, "Pretrain/Step Time": 8.484057219699025} +{"Pretrain/Learning Rate": 6.057013875722107e-08, "Pretrain/Loss": 1.9735270738601685, "Pretrain/Loss (Raw)": 2.070219039916992, "Pretrain/Step": 9331, "Pretrain/Step Time": 8.487382946535945} +{"Pretrain/Learning Rate": 5.998088769586795e-08, "Pretrain/Loss": 1.9733068943023682, "Pretrain/Loss (Raw)": 1.8573967218399048, "Pretrain/Step": 9332, "Pretrain/Step Time": 8.490204757079482} +{"Pretrain/Learning Rate": 5.939451345695346e-08, "Pretrain/Loss": 1.9760186672210693, "Pretrain/Loss (Raw)": 2.2134952545166016, "Pretrain/Step": 9333, "Pretrain/Step Time": 8.490020629018545} +{"Pretrain/Learning Rate": 5.88110161081179e-08, "Pretrain/Loss": 1.9772014617919922, "Pretrain/Loss (Raw)": 2.177678108215332, "Pretrain/Step": 9334, "Pretrain/Step Time": 8.487000895664096} +{"Pretrain/Learning Rate": 5.823039571666578e-08, "Pretrain/Loss": 1.9766738414764404, "Pretrain/Loss (Raw)": 1.9898273944854736, "Pretrain/Step": 9335, "Pretrain/Step Time": 8.489678896963596} +{"Pretrain/Learning Rate": 5.765265234957129e-08, "Pretrain/Loss": 1.9761731624603271, "Pretrain/Loss (Raw)": 1.989057183265686, "Pretrain/Step": 9336, "Pretrain/Step Time": 8.491229562088847} +{"Pretrain/Learning Rate": 5.7077786073478356e-08, "Pretrain/Loss": 1.9766643047332764, "Pretrain/Loss (Raw)": 2.0959722995758057, "Pretrain/Step": 9337, "Pretrain/Step Time": 8.489918941631913} +{"Pretrain/Learning Rate": 5.650579695469782e-08, "Pretrain/Loss": 1.979374885559082, "Pretrain/Loss (Raw)": 2.0324885845184326, "Pretrain/Step": 9338, "Pretrain/Step Time": 8.488649517297745} +{"Pretrain/Learning Rate": 5.593668505921024e-08, "Pretrain/Loss": 1.9817423820495605, "Pretrain/Loss (Raw)": 2.098733901977539, "Pretrain/Step": 9339, "Pretrain/Step Time": 8.48824429512024} +{"Pretrain/Learning Rate": 5.537045045265754e-08, "Pretrain/Loss": 1.9804162979125977, "Pretrain/Loss (Raw)": 1.8904826641082764, "Pretrain/Step": 9340, "Pretrain/Step Time": 8.486916080117226} +{"Pretrain/Learning Rate": 5.480709320035693e-08, "Pretrain/Loss": 1.9807701110839844, "Pretrain/Loss (Raw)": 2.0598623752593994, "Pretrain/Step": 9341, "Pretrain/Step Time": 8.488021112978458} +{"Pretrain/Learning Rate": 5.424661336729253e-08, "Pretrain/Loss": 1.9818202257156372, "Pretrain/Loss (Raw)": 2.1186697483062744, "Pretrain/Step": 9342, "Pretrain/Step Time": 8.490631513297558} +{"Pretrain/Learning Rate": 5.3689011018115406e-08, "Pretrain/Loss": 1.984793782234192, "Pretrain/Loss (Raw)": 1.9931074380874634, "Pretrain/Step": 9343, "Pretrain/Step Time": 8.485382933169603} +{"Pretrain/Learning Rate": 5.3134286217143556e-08, "Pretrain/Loss": 1.9863696098327637, "Pretrain/Loss (Raw)": 1.9081916809082031, "Pretrain/Step": 9344, "Pretrain/Step Time": 8.485871765762568} +{"Pretrain/Learning Rate": 5.258243902836468e-08, "Pretrain/Loss": 1.9851295948028564, "Pretrain/Loss (Raw)": 1.938409686088562, "Pretrain/Step": 9345, "Pretrain/Step Time": 8.482824793085456} +{"Pretrain/Learning Rate": 5.203346951543342e-08, "Pretrain/Loss": 1.983318567276001, "Pretrain/Loss (Raw)": 1.9326478242874146, "Pretrain/Step": 9346, "Pretrain/Step Time": 8.48447809740901} +{"Pretrain/Learning Rate": 5.148737774167411e-08, "Pretrain/Loss": 1.9822449684143066, "Pretrain/Loss (Raw)": 1.9494966268539429, "Pretrain/Step": 9347, "Pretrain/Step Time": 8.484158935025334} +{"Pretrain/Learning Rate": 5.094416377008082e-08, "Pretrain/Loss": 1.983414888381958, "Pretrain/Loss (Raw)": 2.025852680206299, "Pretrain/Step": 9348, "Pretrain/Step Time": 8.483042668551207} +{"Pretrain/Learning Rate": 5.040382766330898e-08, "Pretrain/Loss": 1.9821215867996216, "Pretrain/Loss (Raw)": 1.87618088722229, "Pretrain/Step": 9349, "Pretrain/Step Time": 8.48913212493062} +{"Pretrain/Learning Rate": 4.9866369483686504e-08, "Pretrain/Loss": 1.9817497730255127, "Pretrain/Loss (Raw)": 1.9999946355819702, "Pretrain/Step": 9350, "Pretrain/Step Time": 8.486900929361582} +{"Pretrain/Learning Rate": 4.9331789293211026e-08, "Pretrain/Loss": 1.9804272651672363, "Pretrain/Loss (Raw)": 2.0154707431793213, "Pretrain/Step": 9351, "Pretrain/Step Time": 8.484870405867696} +{"Pretrain/Learning Rate": 4.880008715354434e-08, "Pretrain/Loss": 1.9799866676330566, "Pretrain/Loss (Raw)": 2.038025140762329, "Pretrain/Step": 9352, "Pretrain/Step Time": 8.485010029748082} +{"Pretrain/Learning Rate": 4.8271263126020705e-08, "Pretrain/Loss": 1.9804778099060059, "Pretrain/Loss (Raw)": 1.9964768886566162, "Pretrain/Step": 9353, "Pretrain/Step Time": 8.486112149432302} +{"Pretrain/Learning Rate": 4.7745317271638556e-08, "Pretrain/Loss": 1.9798765182495117, "Pretrain/Loss (Raw)": 2.112997055053711, "Pretrain/Step": 9354, "Pretrain/Step Time": 8.48144001699984} +{"Pretrain/Learning Rate": 4.722224965106603e-08, "Pretrain/Loss": 1.9790608882904053, "Pretrain/Loss (Raw)": 1.9290205240249634, "Pretrain/Step": 9355, "Pretrain/Step Time": 8.483264101669192} +{"Pretrain/Learning Rate": 4.670206032463542e-08, "Pretrain/Loss": 1.978662133216858, "Pretrain/Loss (Raw)": 2.09729266166687, "Pretrain/Step": 9356, "Pretrain/Step Time": 8.48626210540533} +{"Pretrain/Learning Rate": 4.618474935235429e-08, "Pretrain/Loss": 1.9814292192459106, "Pretrain/Loss (Raw)": 2.112753391265869, "Pretrain/Step": 9357, "Pretrain/Step Time": 8.486521290615201} +{"Pretrain/Learning Rate": 4.5670316793891555e-08, "Pretrain/Loss": 1.9848861694335938, "Pretrain/Loss (Raw)": 2.060574531555176, "Pretrain/Step": 9358, "Pretrain/Step Time": 8.487429643049836} +{"Pretrain/Learning Rate": 4.515876270859143e-08, "Pretrain/Loss": 1.9860862493515015, "Pretrain/Loss (Raw)": 2.0324885845184326, "Pretrain/Step": 9359, "Pretrain/Step Time": 8.486866543069482} +{"Pretrain/Learning Rate": 4.4650087155453936e-08, "Pretrain/Loss": 1.9864803552627563, "Pretrain/Loss (Raw)": 1.9720577001571655, "Pretrain/Step": 9360, "Pretrain/Step Time": 8.48560051061213} +{"Pretrain/Learning Rate": 4.414429019316268e-08, "Pretrain/Loss": 1.9866752624511719, "Pretrain/Loss (Raw)": 2.0054264068603516, "Pretrain/Step": 9361, "Pretrain/Step Time": 8.481187568977475} +{"Pretrain/Learning Rate": 4.3641371880057123e-08, "Pretrain/Loss": 1.9872453212738037, "Pretrain/Loss (Raw)": 2.140265941619873, "Pretrain/Step": 9362, "Pretrain/Step Time": 8.484463369473815} +{"Pretrain/Learning Rate": 4.3141332274146404e-08, "Pretrain/Loss": 1.9881372451782227, "Pretrain/Loss (Raw)": 2.034914493560791, "Pretrain/Step": 9363, "Pretrain/Step Time": 8.485029194504023} +{"Pretrain/Learning Rate": 4.2644171433114945e-08, "Pretrain/Loss": 1.9908769130706787, "Pretrain/Loss (Raw)": 2.1445820331573486, "Pretrain/Step": 9364, "Pretrain/Step Time": 8.48227946460247} +{"Pretrain/Learning Rate": 4.2149889414305756e-08, "Pretrain/Loss": 1.9912657737731934, "Pretrain/Loss (Raw)": 1.9965804815292358, "Pretrain/Step": 9365, "Pretrain/Step Time": 8.482811292633414} +{"Pretrain/Learning Rate": 4.165848627473712e-08, "Pretrain/Loss": 1.989760398864746, "Pretrain/Loss (Raw)": 1.843570351600647, "Pretrain/Step": 9366, "Pretrain/Step Time": 8.480150677263737} +{"Pretrain/Learning Rate": 4.1169962071091474e-08, "Pretrain/Loss": 1.9906806945800781, "Pretrain/Loss (Raw)": 2.0458600521087646, "Pretrain/Step": 9367, "Pretrain/Step Time": 8.481687294319272} +{"Pretrain/Learning Rate": 4.068431685971818e-08, "Pretrain/Loss": 1.9896016120910645, "Pretrain/Loss (Raw)": 1.9294761419296265, "Pretrain/Step": 9368, "Pretrain/Step Time": 8.479263646528125} +{"Pretrain/Learning Rate": 4.020155069663911e-08, "Pretrain/Loss": 1.988143801689148, "Pretrain/Loss (Raw)": 1.964512586593628, "Pretrain/Step": 9369, "Pretrain/Step Time": 8.477764951065183} +{"Pretrain/Learning Rate": 3.9721663637537485e-08, "Pretrain/Loss": 1.9872270822525024, "Pretrain/Loss (Raw)": 1.9176639318466187, "Pretrain/Step": 9370, "Pretrain/Step Time": 8.476029256358743} +{"Pretrain/Learning Rate": 3.924465573777458e-08, "Pretrain/Loss": 1.987038016319275, "Pretrain/Loss (Raw)": 1.9624899625778198, "Pretrain/Step": 9371, "Pretrain/Step Time": 8.474238906055689} +{"Pretrain/Learning Rate": 3.877052705236472e-08, "Pretrain/Loss": 1.9876327514648438, "Pretrain/Loss (Raw)": 2.041447162628174, "Pretrain/Step": 9372, "Pretrain/Step Time": 8.47708074748516} +{"Pretrain/Learning Rate": 3.829927763600305e-08, "Pretrain/Loss": 1.9889857769012451, "Pretrain/Loss (Raw)": 1.9896678924560547, "Pretrain/Step": 9373, "Pretrain/Step Time": 8.476320590823889} +{"Pretrain/Learning Rate": 3.783090754304885e-08, "Pretrain/Loss": 1.9912772178649902, "Pretrain/Loss (Raw)": 2.107722759246826, "Pretrain/Step": 9374, "Pretrain/Step Time": 8.474211189895868} +{"Pretrain/Learning Rate": 3.7365416827528364e-08, "Pretrain/Loss": 1.9899182319641113, "Pretrain/Loss (Raw)": 2.001429796218872, "Pretrain/Step": 9375, "Pretrain/Step Time": 8.47353820130229} +{"Pretrain/Learning Rate": 3.690280554313197e-08, "Pretrain/Loss": 1.991137981414795, "Pretrain/Loss (Raw)": 2.0986387729644775, "Pretrain/Step": 9376, "Pretrain/Step Time": 8.473030565306544} +{"Pretrain/Learning Rate": 3.644307374322531e-08, "Pretrain/Loss": 1.9927241802215576, "Pretrain/Loss (Raw)": 1.9762194156646729, "Pretrain/Step": 9377, "Pretrain/Step Time": 8.47058886475861} +{"Pretrain/Learning Rate": 3.598622148083819e-08, "Pretrain/Loss": 1.9934287071228027, "Pretrain/Loss (Raw)": 2.052175521850586, "Pretrain/Step": 9378, "Pretrain/Step Time": 8.471228452399373} +{"Pretrain/Learning Rate": 3.553224880866735e-08, "Pretrain/Loss": 1.9922614097595215, "Pretrain/Loss (Raw)": 1.8520625829696655, "Pretrain/Step": 9379, "Pretrain/Step Time": 8.47119122184813} +{"Pretrain/Learning Rate": 3.508115577907645e-08, "Pretrain/Loss": 1.9906976222991943, "Pretrain/Loss (Raw)": 1.8349100351333618, "Pretrain/Step": 9380, "Pretrain/Step Time": 8.472790855914354} +{"Pretrain/Learning Rate": 3.463294244410165e-08, "Pretrain/Loss": 1.990648865699768, "Pretrain/Loss (Raw)": 1.9213976860046387, "Pretrain/Step": 9381, "Pretrain/Step Time": 8.470065839588642} +{"Pretrain/Learning Rate": 3.418760885544325e-08, "Pretrain/Loss": 1.991776466369629, "Pretrain/Loss (Raw)": 2.0411157608032227, "Pretrain/Step": 9382, "Pretrain/Step Time": 8.470475470647216} +{"Pretrain/Learning Rate": 3.374515506447129e-08, "Pretrain/Loss": 1.9933624267578125, "Pretrain/Loss (Raw)": 2.06839919090271, "Pretrain/Step": 9383, "Pretrain/Step Time": 8.472084915265441} +{"Pretrain/Learning Rate": 3.330558112222271e-08, "Pretrain/Loss": 1.9948663711547852, "Pretrain/Loss (Raw)": 1.9907722473144531, "Pretrain/Step": 9384, "Pretrain/Step Time": 8.471665848046541} +{"Pretrain/Learning Rate": 3.2868887079401386e-08, "Pretrain/Loss": 1.9956843852996826, "Pretrain/Loss (Raw)": 2.016235589981079, "Pretrain/Step": 9385, "Pretrain/Step Time": 8.466852886602283} +{"Pretrain/Learning Rate": 3.2435072986378154e-08, "Pretrain/Loss": 1.9955706596374512, "Pretrain/Loss (Raw)": 2.0147199630737305, "Pretrain/Step": 9386, "Pretrain/Step Time": 8.469975644722581} +{"Pretrain/Learning Rate": 3.200413889319631e-08, "Pretrain/Loss": 1.9937834739685059, "Pretrain/Loss (Raw)": 1.773150086402893, "Pretrain/Step": 9387, "Pretrain/Step Time": 8.470802584663033} +{"Pretrain/Learning Rate": 3.157608484956332e-08, "Pretrain/Loss": 1.993330717086792, "Pretrain/Loss (Raw)": 2.0207958221435547, "Pretrain/Step": 9388, "Pretrain/Step Time": 8.4677222520113} +{"Pretrain/Learning Rate": 3.115091090485356e-08, "Pretrain/Loss": 1.9936387538909912, "Pretrain/Loss (Raw)": 2.0653929710388184, "Pretrain/Step": 9389, "Pretrain/Step Time": 8.468415791168809} +{"Pretrain/Learning Rate": 3.0728617108111147e-08, "Pretrain/Loss": 1.994274616241455, "Pretrain/Loss (Raw)": 2.0507709980010986, "Pretrain/Step": 9390, "Pretrain/Step Time": 8.465689903125167} +{"Pretrain/Learning Rate": 3.030920350804711e-08, "Pretrain/Loss": 1.9947024583816528, "Pretrain/Loss (Raw)": 2.072266101837158, "Pretrain/Step": 9391, "Pretrain/Step Time": 8.47040001116693} +{"Pretrain/Learning Rate": 2.98926701530422e-08, "Pretrain/Loss": 1.9957926273345947, "Pretrain/Loss (Raw)": 2.0246520042419434, "Pretrain/Step": 9392, "Pretrain/Step Time": 8.468305656686425} +{"Pretrain/Learning Rate": 2.947901709114409e-08, "Pretrain/Loss": 1.9990036487579346, "Pretrain/Loss (Raw)": 2.0099141597747803, "Pretrain/Step": 9393, "Pretrain/Step Time": 8.469590172171593} +{"Pretrain/Learning Rate": 2.9068244370064613e-08, "Pretrain/Loss": 1.9996864795684814, "Pretrain/Loss (Raw)": 2.0387752056121826, "Pretrain/Step": 9394, "Pretrain/Step Time": 8.465871741995215} +{"Pretrain/Learning Rate": 2.8660352037188088e-08, "Pretrain/Loss": 1.9992724657058716, "Pretrain/Loss (Raw)": 2.0080838203430176, "Pretrain/Step": 9395, "Pretrain/Step Time": 8.471188332885504} +{"Pretrain/Learning Rate": 2.8255340139565767e-08, "Pretrain/Loss": 2.001539707183838, "Pretrain/Loss (Raw)": 2.093933343887329, "Pretrain/Step": 9396, "Pretrain/Step Time": 8.470926174893975} +{"Pretrain/Learning Rate": 2.785320872391306e-08, "Pretrain/Loss": 2.0008788108825684, "Pretrain/Loss (Raw)": 1.8527382612228394, "Pretrain/Step": 9397, "Pretrain/Step Time": 8.476665429770947} +{"Pretrain/Learning Rate": 2.745395783661786e-08, "Pretrain/Loss": 2.000047206878662, "Pretrain/Loss (Raw)": 1.988067626953125, "Pretrain/Step": 9398, "Pretrain/Step Time": 8.476947944611311} +{"Pretrain/Learning Rate": 2.7057587523729445e-08, "Pretrain/Loss": 2.0001888275146484, "Pretrain/Loss (Raw)": 1.9823384284973145, "Pretrain/Step": 9399, "Pretrain/Step Time": 8.477500518783927} +{"Pretrain/Learning Rate": 2.6664097830975123e-08, "Pretrain/Loss": 1.9979548454284668, "Pretrain/Loss (Raw)": 1.8328008651733398, "Pretrain/Step": 9400, "Pretrain/Step Time": 8.4756610840559} +{"Pretrain/Learning Rate": 2.627348880374081e-08, "Pretrain/Loss": 2.0004730224609375, "Pretrain/Loss (Raw)": 2.044070243835449, "Pretrain/Step": 9401, "Pretrain/Step Time": 8.478349464014173} +{"Pretrain/Learning Rate": 2.5885760487082135e-08, "Pretrain/Loss": 2.0003395080566406, "Pretrain/Loss (Raw)": 1.96811842918396, "Pretrain/Step": 9402, "Pretrain/Step Time": 8.472824012860656} +{"Pretrain/Learning Rate": 2.550091292572443e-08, "Pretrain/Loss": 2.0028228759765625, "Pretrain/Loss (Raw)": 2.0588173866271973, "Pretrain/Step": 9403, "Pretrain/Step Time": 8.472725233063102} +{"Pretrain/Learning Rate": 2.5118946164059963e-08, "Pretrain/Loss": 2.0040812492370605, "Pretrain/Loss (Raw)": 2.0641374588012695, "Pretrain/Step": 9404, "Pretrain/Step Time": 8.471964355558157} +{"Pretrain/Learning Rate": 2.4739860246150716e-08, "Pretrain/Loss": 2.003178358078003, "Pretrain/Loss (Raw)": 1.8956570625305176, "Pretrain/Step": 9405, "Pretrain/Step Time": 8.472351722419262} +{"Pretrain/Learning Rate": 2.4363655215717264e-08, "Pretrain/Loss": 2.0013551712036133, "Pretrain/Loss (Raw)": 1.9675767421722412, "Pretrain/Step": 9406, "Pretrain/Step Time": 8.472753955051303} +{"Pretrain/Learning Rate": 2.3990331116161e-08, "Pretrain/Loss": 2.001169204711914, "Pretrain/Loss (Raw)": 2.0111083984375, "Pretrain/Step": 9407, "Pretrain/Step Time": 8.47255470789969} +{"Pretrain/Learning Rate": 2.361988799054471e-08, "Pretrain/Loss": 2.000746965408325, "Pretrain/Loss (Raw)": 1.877644658088684, "Pretrain/Step": 9408, "Pretrain/Step Time": 8.4724250882864} +{"Pretrain/Learning Rate": 2.3252325881595316e-08, "Pretrain/Loss": 2.0016469955444336, "Pretrain/Loss (Raw)": 2.098055839538574, "Pretrain/Step": 9409, "Pretrain/Step Time": 8.471771758049726} +{"Pretrain/Learning Rate": 2.288764483171224e-08, "Pretrain/Loss": 2.002697229385376, "Pretrain/Loss (Raw)": 2.233206272125244, "Pretrain/Step": 9410, "Pretrain/Step Time": 8.468051820993423} +{"Pretrain/Learning Rate": 2.2525844882964607e-08, "Pretrain/Loss": 2.0032753944396973, "Pretrain/Loss (Raw)": 2.102389335632324, "Pretrain/Step": 9411, "Pretrain/Step Time": 8.468478927388787} +{"Pretrain/Learning Rate": 2.2166926077080153e-08, "Pretrain/Loss": 2.0026230812072754, "Pretrain/Loss (Raw)": 2.091235399246216, "Pretrain/Step": 9412, "Pretrain/Step Time": 8.46935355104506} +{"Pretrain/Learning Rate": 2.181088845546464e-08, "Pretrain/Loss": 2.002983570098877, "Pretrain/Loss (Raw)": 2.1135761737823486, "Pretrain/Step": 9413, "Pretrain/Step Time": 8.468180116266012} +{"Pretrain/Learning Rate": 2.1457732059182443e-08, "Pretrain/Loss": 2.0023229122161865, "Pretrain/Loss (Raw)": 1.9034947156906128, "Pretrain/Step": 9414, "Pretrain/Step Time": 8.468080170452595} +{"Pretrain/Learning Rate": 2.1107456928975978e-08, "Pretrain/Loss": 2.003675937652588, "Pretrain/Loss (Raw)": 2.0592169761657715, "Pretrain/Step": 9415, "Pretrain/Step Time": 8.46915458329022} +{"Pretrain/Learning Rate": 2.0760063105243475e-08, "Pretrain/Loss": 2.005150318145752, "Pretrain/Loss (Raw)": 2.1341991424560547, "Pretrain/Step": 9416, "Pretrain/Step Time": 8.47175713442266} +{"Pretrain/Learning Rate": 2.041555062806122e-08, "Pretrain/Loss": 2.004812717437744, "Pretrain/Loss (Raw)": 1.9667034149169922, "Pretrain/Step": 9417, "Pretrain/Step Time": 8.469354527071118} +{"Pretrain/Learning Rate": 2.0073919537166864e-08, "Pretrain/Loss": 2.0062999725341797, "Pretrain/Loss (Raw)": 2.2449827194213867, "Pretrain/Step": 9418, "Pretrain/Step Time": 8.469518216326833} +{"Pretrain/Learning Rate": 1.9735169871964997e-08, "Pretrain/Loss": 2.0045228004455566, "Pretrain/Loss (Raw)": 1.9099136590957642, "Pretrain/Step": 9419, "Pretrain/Step Time": 8.46750364638865} +{"Pretrain/Learning Rate": 1.9399301671535473e-08, "Pretrain/Loss": 2.005392074584961, "Pretrain/Loss (Raw)": 2.091217517852783, "Pretrain/Step": 9420, "Pretrain/Step Time": 8.468543892726302} +{"Pretrain/Learning Rate": 1.9066314974613974e-08, "Pretrain/Loss": 2.00392484664917, "Pretrain/Loss (Raw)": 2.1674580574035645, "Pretrain/Step": 9421, "Pretrain/Step Time": 8.468776220455766} +{"Pretrain/Learning Rate": 1.873620981961699e-08, "Pretrain/Loss": 2.0059707164764404, "Pretrain/Loss (Raw)": 1.9867678880691528, "Pretrain/Step": 9422, "Pretrain/Step Time": 8.466226182878017} +{"Pretrain/Learning Rate": 1.840898624461962e-08, "Pretrain/Loss": 2.006892204284668, "Pretrain/Loss (Raw)": 1.998494029045105, "Pretrain/Step": 9423, "Pretrain/Step Time": 8.466341450810432} +{"Pretrain/Learning Rate": 1.808464428736667e-08, "Pretrain/Loss": 2.007014274597168, "Pretrain/Loss (Raw)": 1.9366730451583862, "Pretrain/Step": 9424, "Pretrain/Step Time": 8.467072801664472} +{"Pretrain/Learning Rate": 1.7763183985269883e-08, "Pretrain/Loss": 2.0069680213928223, "Pretrain/Loss (Raw)": 1.946973204612732, "Pretrain/Step": 9425, "Pretrain/Step Time": 8.463500078767538} +{"Pretrain/Learning Rate": 1.744460537540793e-08, "Pretrain/Loss": 2.006619453430176, "Pretrain/Loss (Raw)": 1.9930682182312012, "Pretrain/Step": 9426, "Pretrain/Step Time": 8.466135857626796} +{"Pretrain/Learning Rate": 1.7128908494534745e-08, "Pretrain/Loss": 2.0070948600769043, "Pretrain/Loss (Raw)": 2.0628435611724854, "Pretrain/Step": 9427, "Pretrain/Step Time": 8.466007675975561} +{"Pretrain/Learning Rate": 1.681609337906287e-08, "Pretrain/Loss": 2.00543212890625, "Pretrain/Loss (Raw)": 1.9257465600967407, "Pretrain/Step": 9428, "Pretrain/Step Time": 8.466722035780549} +{"Pretrain/Learning Rate": 1.6506160065071775e-08, "Pretrain/Loss": 2.007617950439453, "Pretrain/Loss (Raw)": 2.0733911991119385, "Pretrain/Step": 9429, "Pretrain/Step Time": 8.462080512195826} +{"Pretrain/Learning Rate": 1.6199108588316193e-08, "Pretrain/Loss": 2.0090088844299316, "Pretrain/Loss (Raw)": 2.1329898834228516, "Pretrain/Step": 9430, "Pretrain/Step Time": 8.461792195215821} +{"Pretrain/Learning Rate": 1.5894938984215013e-08, "Pretrain/Loss": 2.0106029510498047, "Pretrain/Loss (Raw)": 2.200829029083252, "Pretrain/Step": 9431, "Pretrain/Step Time": 8.46278372220695} +{"Pretrain/Learning Rate": 1.5593651287851285e-08, "Pretrain/Loss": 2.01218581199646, "Pretrain/Loss (Raw)": 2.0610108375549316, "Pretrain/Step": 9432, "Pretrain/Step Time": 8.466761071234941} +{"Pretrain/Learning Rate": 1.529524553398054e-08, "Pretrain/Loss": 2.0096123218536377, "Pretrain/Loss (Raw)": 1.7852691411972046, "Pretrain/Step": 9433, "Pretrain/Step Time": 8.46716270595789} +{"Pretrain/Learning Rate": 1.4999721757022467e-08, "Pretrain/Loss": 2.0099740028381348, "Pretrain/Loss (Raw)": 1.9703387022018433, "Pretrain/Step": 9434, "Pretrain/Step Time": 8.464179925620556} +{"Pretrain/Learning Rate": 1.4707079991066464e-08, "Pretrain/Loss": 2.0112266540527344, "Pretrain/Loss (Raw)": 2.023339033126831, "Pretrain/Step": 9435, "Pretrain/Step Time": 8.463677914813161} +{"Pretrain/Learning Rate": 1.4417320269868861e-08, "Pretrain/Loss": 2.010664939880371, "Pretrain/Loss (Raw)": 1.929000735282898, "Pretrain/Step": 9436, "Pretrain/Step Time": 8.465469691902399} +{"Pretrain/Learning Rate": 1.4130442626850149e-08, "Pretrain/Loss": 2.0115761756896973, "Pretrain/Loss (Raw)": 2.0992445945739746, "Pretrain/Step": 9437, "Pretrain/Step Time": 8.464855330064893} +{"Pretrain/Learning Rate": 1.3846447095106074e-08, "Pretrain/Loss": 2.012006998062134, "Pretrain/Loss (Raw)": 2.147800922393799, "Pretrain/Step": 9438, "Pretrain/Step Time": 8.465649209916592} +{"Pretrain/Learning Rate": 1.3565333707393769e-08, "Pretrain/Loss": 2.0110466480255127, "Pretrain/Loss (Raw)": 1.9155889749526978, "Pretrain/Step": 9439, "Pretrain/Step Time": 8.466247463598847} +{"Pretrain/Learning Rate": 1.3287102496140069e-08, "Pretrain/Loss": 2.0098047256469727, "Pretrain/Loss (Raw)": 1.9016340970993042, "Pretrain/Step": 9440, "Pretrain/Step Time": 8.468934839591384} +{"Pretrain/Learning Rate": 1.3011753493438749e-08, "Pretrain/Loss": 2.006936550140381, "Pretrain/Loss (Raw)": 1.9068565368652344, "Pretrain/Step": 9441, "Pretrain/Step Time": 8.46719821728766} +{"Pretrain/Learning Rate": 1.2739286731047739e-08, "Pretrain/Loss": 2.006680965423584, "Pretrain/Loss (Raw)": 1.9969218969345093, "Pretrain/Step": 9442, "Pretrain/Step Time": 8.462848730385303} +{"Pretrain/Learning Rate": 1.2469702240400227e-08, "Pretrain/Loss": 2.006404161453247, "Pretrain/Loss (Raw)": 2.050723075866699, "Pretrain/Step": 9443, "Pretrain/Step Time": 8.464686440303922} +{"Pretrain/Learning Rate": 1.2203000052590785e-08, "Pretrain/Loss": 2.0053248405456543, "Pretrain/Loss (Raw)": 1.9375680685043335, "Pretrain/Step": 9444, "Pretrain/Step Time": 8.465128036215901} +{"Pretrain/Learning Rate": 1.1939180198386468e-08, "Pretrain/Loss": 2.005847454071045, "Pretrain/Loss (Raw)": 1.9691287279129028, "Pretrain/Step": 9445, "Pretrain/Step Time": 8.464875331148505} +{"Pretrain/Learning Rate": 1.1678242708212939e-08, "Pretrain/Loss": 2.0068471431732178, "Pretrain/Loss (Raw)": 2.007266044616699, "Pretrain/Step": 9446, "Pretrain/Step Time": 8.46640295907855} +{"Pretrain/Learning Rate": 1.1420187612173894e-08, "Pretrain/Loss": 2.0078842639923096, "Pretrain/Loss (Raw)": 1.845712661743164, "Pretrain/Step": 9447, "Pretrain/Step Time": 8.46705518849194} +{"Pretrain/Learning Rate": 1.1165014940037189e-08, "Pretrain/Loss": 2.007622718811035, "Pretrain/Loss (Raw)": 2.0658042430877686, "Pretrain/Step": 9448, "Pretrain/Step Time": 8.467744698747993} +{"Pretrain/Learning Rate": 1.091272472123206e-08, "Pretrain/Loss": 2.0085244178771973, "Pretrain/Loss (Raw)": 2.094862937927246, "Pretrain/Step": 9449, "Pretrain/Step Time": 8.466800887137651} +{"Pretrain/Learning Rate": 1.0663316984860228e-08, "Pretrain/Loss": 2.0108184814453125, "Pretrain/Loss (Raw)": 2.1037049293518066, "Pretrain/Step": 9450, "Pretrain/Step Time": 8.472677022218704} +{"Pretrain/Learning Rate": 1.0416791759695899e-08, "Pretrain/Loss": 2.011458158493042, "Pretrain/Loss (Raw)": 2.0306897163391113, "Pretrain/Step": 9451, "Pretrain/Step Time": 8.468496959656477} +{"Pretrain/Learning Rate": 1.0173149074171883e-08, "Pretrain/Loss": 2.0118179321289062, "Pretrain/Loss (Raw)": 1.96311354637146, "Pretrain/Step": 9452, "Pretrain/Step Time": 8.46737595461309} +{"Pretrain/Learning Rate": 9.932388956393479e-09, "Pretrain/Loss": 2.0119740962982178, "Pretrain/Loss (Raw)": 1.9137111902236938, "Pretrain/Step": 9453, "Pretrain/Step Time": 8.466533832252026} +{"Pretrain/Learning Rate": 9.694511434130139e-09, "Pretrain/Loss": 2.01003098487854, "Pretrain/Loss (Raw)": 1.7518678903579712, "Pretrain/Step": 9454, "Pretrain/Step Time": 8.46382861956954} +{"Pretrain/Learning Rate": 9.459516534823797e-09, "Pretrain/Loss": 2.0102481842041016, "Pretrain/Loss (Raw)": 2.060694694519043, "Pretrain/Step": 9455, "Pretrain/Step Time": 8.47115639783442} +{"Pretrain/Learning Rate": 9.227404285580555e-09, "Pretrain/Loss": 2.008340358734131, "Pretrain/Loss (Raw)": 1.9602978229522705, "Pretrain/Step": 9456, "Pretrain/Step Time": 8.47281215339899} +{"Pretrain/Learning Rate": 8.998174713173435e-09, "Pretrain/Loss": 2.0084033012390137, "Pretrain/Loss (Raw)": 1.9822393655776978, "Pretrain/Step": 9457, "Pretrain/Step Time": 8.470282424241304} +{"Pretrain/Learning Rate": 8.771827844042402e-09, "Pretrain/Loss": 2.0085983276367188, "Pretrain/Loss (Raw)": 1.974787950515747, "Pretrain/Step": 9458, "Pretrain/Step Time": 8.470952210947871} +{"Pretrain/Learning Rate": 8.548363704302676e-09, "Pretrain/Loss": 2.008298397064209, "Pretrain/Loss (Raw)": 2.0318095684051514, "Pretrain/Step": 9459, "Pretrain/Step Time": 8.46942232735455} +{"Pretrain/Learning Rate": 8.327782319722532e-09, "Pretrain/Loss": 2.007888078689575, "Pretrain/Loss (Raw)": 1.8048845529556274, "Pretrain/Step": 9460, "Pretrain/Step Time": 8.472357826307416} +{"Pretrain/Learning Rate": 8.11008371575106e-09, "Pretrain/Loss": 2.0056285858154297, "Pretrain/Loss (Raw)": 1.9242689609527588, "Pretrain/Step": 9461, "Pretrain/Step Time": 8.472441498190165} +{"Pretrain/Learning Rate": 7.895267917501504e-09, "Pretrain/Loss": 2.005838632583618, "Pretrain/Loss (Raw)": 2.2045812606811523, "Pretrain/Step": 9462, "Pretrain/Step Time": 8.472642913460732} +{"Pretrain/Learning Rate": 7.683334949745713e-09, "Pretrain/Loss": 2.0062673091888428, "Pretrain/Loss (Raw)": 2.0446910858154297, "Pretrain/Step": 9463, "Pretrain/Step Time": 8.470485189929605} +{"Pretrain/Learning Rate": 7.474284836936352e-09, "Pretrain/Loss": 2.004822254180908, "Pretrain/Loss (Raw)": 1.804068922996521, "Pretrain/Step": 9464, "Pretrain/Step Time": 8.467419557273388} +{"Pretrain/Learning Rate": 7.268117603187463e-09, "Pretrain/Loss": 2.003206968307495, "Pretrain/Loss (Raw)": 1.8892416954040527, "Pretrain/Step": 9465, "Pretrain/Step Time": 8.469266504049301} +{"Pretrain/Learning Rate": 7.064833272274474e-09, "Pretrain/Loss": 2.0024166107177734, "Pretrain/Loss (Raw)": 1.9313232898712158, "Pretrain/Step": 9466, "Pretrain/Step Time": 8.470126263797283} +{"Pretrain/Learning Rate": 6.864431867650845e-09, "Pretrain/Loss": 2.001534938812256, "Pretrain/Loss (Raw)": 1.9858524799346924, "Pretrain/Step": 9467, "Pretrain/Step Time": 8.46926261484623} +{"Pretrain/Learning Rate": 6.666913412434195e-09, "Pretrain/Loss": 2.001413345336914, "Pretrain/Loss (Raw)": 1.8749207258224487, "Pretrain/Step": 9468, "Pretrain/Step Time": 8.470276230946183} +{"Pretrain/Learning Rate": 6.4722779294035254e-09, "Pretrain/Loss": 2.0022315979003906, "Pretrain/Loss (Raw)": 2.164613962173462, "Pretrain/Step": 9469, "Pretrain/Step Time": 8.47081696614623} +{"Pretrain/Learning Rate": 6.280525441010321e-09, "Pretrain/Loss": 1.9998244047164917, "Pretrain/Loss (Raw)": 1.8105621337890625, "Pretrain/Step": 9470, "Pretrain/Step Time": 8.467508373782039} +{"Pretrain/Learning Rate": 6.091655969378552e-09, "Pretrain/Loss": 1.9997791051864624, "Pretrain/Loss (Raw)": 1.987296223640442, "Pretrain/Step": 9471, "Pretrain/Step Time": 8.472590336576104} +{"Pretrain/Learning Rate": 5.905669536290792e-09, "Pretrain/Loss": 2.000946044921875, "Pretrain/Loss (Raw)": 2.057577610015869, "Pretrain/Step": 9472, "Pretrain/Step Time": 8.469382861629128} +{"Pretrain/Learning Rate": 5.722566163199328e-09, "Pretrain/Loss": 1.9999009370803833, "Pretrain/Loss (Raw)": 1.8046214580535889, "Pretrain/Step": 9473, "Pretrain/Step Time": 8.470569416880608} +{"Pretrain/Learning Rate": 5.542345871226151e-09, "Pretrain/Loss": 1.999680519104004, "Pretrain/Loss (Raw)": 1.9044597148895264, "Pretrain/Step": 9474, "Pretrain/Step Time": 8.469884915277362} +{"Pretrain/Learning Rate": 5.365008681157413e-09, "Pretrain/Loss": 1.999169111251831, "Pretrain/Loss (Raw)": 1.8840148448944092, "Pretrain/Step": 9475, "Pretrain/Step Time": 8.471930099651217} +{"Pretrain/Learning Rate": 5.190554613454524e-09, "Pretrain/Loss": 1.9994263648986816, "Pretrain/Loss (Raw)": 2.0587708950042725, "Pretrain/Step": 9476, "Pretrain/Step Time": 8.473539369180799} +{"Pretrain/Learning Rate": 5.0189836882375e-09, "Pretrain/Loss": 2.000626564025879, "Pretrain/Loss (Raw)": 2.0298376083374023, "Pretrain/Step": 9477, "Pretrain/Step Time": 8.471436316147447} +{"Pretrain/Learning Rate": 4.850295925296067e-09, "Pretrain/Loss": 2.00042724609375, "Pretrain/Loss (Raw)": 1.974452018737793, "Pretrain/Step": 9478, "Pretrain/Step Time": 8.470882276073098} +{"Pretrain/Learning Rate": 4.684491344086883e-09, "Pretrain/Loss": 2.001349687576294, "Pretrain/Loss (Raw)": 2.1335530281066895, "Pretrain/Step": 9479, "Pretrain/Step Time": 8.467822955921292} +{"Pretrain/Learning Rate": 4.521569963739092e-09, "Pretrain/Loss": 2.00115966796875, "Pretrain/Loss (Raw)": 2.013688564300537, "Pretrain/Step": 9480, "Pretrain/Step Time": 8.467232998460531} +{"Pretrain/Learning Rate": 4.361531803045993e-09, "Pretrain/Loss": 2.0000123977661133, "Pretrain/Loss (Raw)": 1.8496413230895996, "Pretrain/Step": 9481, "Pretrain/Step Time": 8.466555792838335} +{"Pretrain/Learning Rate": 4.204376880465044e-09, "Pretrain/Loss": 1.9990309476852417, "Pretrain/Loss (Raw)": 1.9873807430267334, "Pretrain/Step": 9482, "Pretrain/Step Time": 8.467179683968425} +{"Pretrain/Learning Rate": 4.050105214123412e-09, "Pretrain/Loss": 1.999004602432251, "Pretrain/Loss (Raw)": 1.9256349802017212, "Pretrain/Step": 9483, "Pretrain/Step Time": 8.464792935177684} +{"Pretrain/Learning Rate": 3.898716821820747e-09, "Pretrain/Loss": 1.9975485801696777, "Pretrain/Loss (Raw)": 1.9109199047088623, "Pretrain/Step": 9484, "Pretrain/Step Time": 8.468871232122183} +{"Pretrain/Learning Rate": 3.750211721015306e-09, "Pretrain/Loss": 1.9964734315872192, "Pretrain/Loss (Raw)": 1.9751406908035278, "Pretrain/Step": 9485, "Pretrain/Step Time": 8.467982335016131} +{"Pretrain/Learning Rate": 3.6045899288378317e-09, "Pretrain/Loss": 1.9962925910949707, "Pretrain/Loss (Raw)": 2.0374343395233154, "Pretrain/Step": 9486, "Pretrain/Step Time": 8.464634453877807} +{"Pretrain/Learning Rate": 3.461851462088772e-09, "Pretrain/Loss": 1.9959847927093506, "Pretrain/Loss (Raw)": 1.9930802583694458, "Pretrain/Step": 9487, "Pretrain/Step Time": 8.464455461129546} +{"Pretrain/Learning Rate": 3.3219963372271844e-09, "Pretrain/Loss": 1.9962387084960938, "Pretrain/Loss (Raw)": 2.0045719146728516, "Pretrain/Step": 9488, "Pretrain/Step Time": 8.465290173888206} +{"Pretrain/Learning Rate": 3.185024570392936e-09, "Pretrain/Loss": 1.9963740110397339, "Pretrain/Loss (Raw)": 2.022747039794922, "Pretrain/Step": 9489, "Pretrain/Step Time": 8.467788700014353} +{"Pretrain/Learning Rate": 3.050936177378949e-09, "Pretrain/Loss": 1.9954426288604736, "Pretrain/Loss (Raw)": 2.0210444927215576, "Pretrain/Step": 9490, "Pretrain/Step Time": 8.465572392567992} +{"Pretrain/Learning Rate": 2.9197311736561816e-09, "Pretrain/Loss": 1.9959871768951416, "Pretrain/Loss (Raw)": 2.1046035289764404, "Pretrain/Step": 9491, "Pretrain/Step Time": 8.466746209189296} +{"Pretrain/Learning Rate": 2.7914095743569736e-09, "Pretrain/Loss": 1.9961140155792236, "Pretrain/Loss (Raw)": 2.160839319229126, "Pretrain/Step": 9492, "Pretrain/Step Time": 8.46896268427372} +{"Pretrain/Learning Rate": 2.665971394283373e-09, "Pretrain/Loss": 1.9941139221191406, "Pretrain/Loss (Raw)": 1.740548014640808, "Pretrain/Step": 9493, "Pretrain/Step Time": 8.468645671382546} +{"Pretrain/Learning Rate": 2.5434166479071376e-09, "Pretrain/Loss": 1.9950745105743408, "Pretrain/Loss (Raw)": 1.966543436050415, "Pretrain/Step": 9494, "Pretrain/Step Time": 8.471624426543713} +{"Pretrain/Learning Rate": 2.4237453493641816e-09, "Pretrain/Loss": 1.9937490224838257, "Pretrain/Loss (Raw)": 1.876180648803711, "Pretrain/Step": 9495, "Pretrain/Step Time": 8.472624935209751} +{"Pretrain/Learning Rate": 2.3069575124545773e-09, "Pretrain/Loss": 1.9937609434127808, "Pretrain/Loss (Raw)": 1.9310115575790405, "Pretrain/Step": 9496, "Pretrain/Step Time": 8.471215741708875} +{"Pretrain/Learning Rate": 2.1930531506536565e-09, "Pretrain/Loss": 1.9938361644744873, "Pretrain/Loss (Raw)": 1.9741402864456177, "Pretrain/Step": 9497, "Pretrain/Step Time": 8.471758872270584} +{"Pretrain/Learning Rate": 2.0820322770981337e-09, "Pretrain/Loss": 1.9938297271728516, "Pretrain/Loss (Raw)": 1.9168329238891602, "Pretrain/Step": 9498, "Pretrain/Step Time": 8.470848115161061} +{"Pretrain/Learning Rate": 1.973894904597207e-09, "Pretrain/Loss": 1.9925312995910645, "Pretrain/Loss (Raw)": 1.7962900400161743, "Pretrain/Step": 9499, "Pretrain/Step Time": 8.474565712735057} +{"Pretrain/Learning Rate": 1.8686410456214553e-09, "Pretrain/Loss": 1.992936372756958, "Pretrain/Loss (Raw)": 2.0933094024658203, "Pretrain/Step": 9500, "Pretrain/Step Time": 8.473462412133813} +{"Pretrain/Learning Rate": 1.7662707123139443e-09, "Pretrain/Loss": 1.9921691417694092, "Pretrain/Loss (Raw)": 1.891451120376587, "Pretrain/Step": 9501, "Pretrain/Step Time": 8.476892985403538} +{"Pretrain/Learning Rate": 1.6667839164818954e-09, "Pretrain/Loss": 1.9908549785614014, "Pretrain/Loss (Raw)": 1.9395227432250977, "Pretrain/Step": 9502, "Pretrain/Step Time": 8.476759446784854} +{"Pretrain/Learning Rate": 1.5701806695994636e-09, "Pretrain/Loss": 1.990549921989441, "Pretrain/Loss (Raw)": 1.96237051486969, "Pretrain/Step": 9503, "Pretrain/Step Time": 8.475611466914415} +{"Pretrain/Learning Rate": 1.4764609828132881e-09, "Pretrain/Loss": 1.9889357089996338, "Pretrain/Loss (Raw)": 1.8920198678970337, "Pretrain/Step": 9504, "Pretrain/Step Time": 8.479686055332422} +{"Pretrain/Learning Rate": 1.3856248669313899e-09, "Pretrain/Loss": 1.9896399974822998, "Pretrain/Loss (Raw)": 2.066368341445923, "Pretrain/Step": 9505, "Pretrain/Step Time": 8.480545364320278} +{"Pretrain/Learning Rate": 1.2976723324342744e-09, "Pretrain/Loss": 1.9885722398757935, "Pretrain/Loss (Raw)": 1.915503740310669, "Pretrain/Step": 9506, "Pretrain/Step Time": 8.480630986392498} +{"Pretrain/Learning Rate": 1.212603389463829e-09, "Pretrain/Loss": 1.9873892068862915, "Pretrain/Loss (Raw)": 1.7006301879882812, "Pretrain/Step": 9507, "Pretrain/Step Time": 8.48235746845603} +{"Pretrain/Learning Rate": 1.1304180478344251e-09, "Pretrain/Loss": 1.9881629943847656, "Pretrain/Loss (Raw)": 1.933969497680664, "Pretrain/Step": 9508, "Pretrain/Step Time": 8.481728350743651} +{"Pretrain/Learning Rate": 1.0511163170273674e-09, "Pretrain/Loss": 1.9889838695526123, "Pretrain/Loss (Raw)": 2.026459217071533, "Pretrain/Step": 9509, "Pretrain/Step Time": 8.485653337091208} +{"Pretrain/Learning Rate": 9.746982061881183e-10, "Pretrain/Loss": 1.9877326488494873, "Pretrain/Loss (Raw)": 1.8809632062911987, "Pretrain/Step": 9510, "Pretrain/Step Time": 8.48452329263091} +{"Pretrain/Learning Rate": 9.011637241318483e-10, "Pretrain/Loss": 1.9870080947875977, "Pretrain/Loss (Raw)": 1.9756386280059814, "Pretrain/Step": 9511, "Pretrain/Step Time": 8.484152242541313} +{"Pretrain/Learning Rate": 8.305128793406613e-10, "Pretrain/Loss": 1.9869420528411865, "Pretrain/Loss (Raw)": 1.9823246002197266, "Pretrain/Step": 9512, "Pretrain/Step Time": 8.481363805010915} +{"Pretrain/Learning Rate": 7.627456799635946e-10, "Pretrain/Loss": 1.9868154525756836, "Pretrain/Loss (Raw)": 2.000035047531128, "Pretrain/Step": 9513, "Pretrain/Step Time": 8.484043415635824} +{"Pretrain/Learning Rate": 6.978621338193936e-10, "Pretrain/Loss": 1.98748779296875, "Pretrain/Loss (Raw)": 2.100797176361084, "Pretrain/Step": 9514, "Pretrain/Step Time": 8.485888490453362} +{"Pretrain/Learning Rate": 6.358622483937371e-10, "Pretrain/Loss": 1.9894611835479736, "Pretrain/Loss (Raw)": 2.0257277488708496, "Pretrain/Step": 9515, "Pretrain/Step Time": 8.484606068581343} +{"Pretrain/Learning Rate": 5.767460308336859e-10, "Pretrain/Loss": 1.9896371364593506, "Pretrain/Loss (Raw)": 2.043323040008545, "Pretrain/Step": 9516, "Pretrain/Step Time": 8.48321201466024} +{"Pretrain/Learning Rate": 5.205134879615603e-10, "Pretrain/Loss": 1.9899554252624512, "Pretrain/Loss (Raw)": 2.106123447418213, "Pretrain/Step": 9517, "Pretrain/Step Time": 8.484977342188358} +{"Pretrain/Learning Rate": 4.671646262610629e-10, "Pretrain/Loss": 1.9881463050842285, "Pretrain/Loss (Raw)": 1.8192185163497925, "Pretrain/Step": 9518, "Pretrain/Step Time": 8.48253090493381} +{"Pretrain/Learning Rate": 4.1669945188838044e-10, "Pretrain/Loss": 1.9878652095794678, "Pretrain/Loss (Raw)": 2.036280870437622, "Pretrain/Step": 9519, "Pretrain/Step Time": 8.482478521764278} +{"Pretrain/Learning Rate": 3.69117970663857e-10, "Pretrain/Loss": 1.988189458847046, "Pretrain/Loss (Raw)": 2.0661497116088867, "Pretrain/Step": 9520, "Pretrain/Step Time": 8.485489934682846} +{"Pretrain/Learning Rate": 3.244201880775455e-10, "Pretrain/Loss": 1.9892184734344482, "Pretrain/Loss (Raw)": 2.1416351795196533, "Pretrain/Step": 9521, "Pretrain/Step Time": 8.484390623867512} +{"Pretrain/Learning Rate": 2.826061092836563e-10, "Pretrain/Loss": 1.989269495010376, "Pretrain/Loss (Raw)": 2.0453107357025146, "Pretrain/Step": 9522, "Pretrain/Step Time": 8.484703661873937} +{"Pretrain/Learning Rate": 2.4367573910333283e-10, "Pretrain/Loss": 1.9889918565750122, "Pretrain/Loss (Raw)": 1.9725385904312134, "Pretrain/Step": 9523, "Pretrain/Step Time": 8.483842421323061} +{"Pretrain/Learning Rate": 2.0762908203297849e-10, "Pretrain/Loss": 1.9902920722961426, "Pretrain/Loss (Raw)": 2.260366201400757, "Pretrain/Step": 9524, "Pretrain/Step Time": 8.483608551323414} +{"Pretrain/Learning Rate": 1.7446614222482728e-10, "Pretrain/Loss": 1.992185115814209, "Pretrain/Loss (Raw)": 2.0950374603271484, "Pretrain/Step": 9525, "Pretrain/Step Time": 8.479226741939783} +{"Pretrain/Learning Rate": 1.441869235063731e-10, "Pretrain/Loss": 1.991256594657898, "Pretrain/Loss (Raw)": 1.8692318201065063, "Pretrain/Step": 9526, "Pretrain/Step Time": 8.479421630501747} +{"Pretrain/Learning Rate": 1.1679142936926734e-10, "Pretrain/Loss": 1.9923946857452393, "Pretrain/Loss (Raw)": 2.128023147583008, "Pretrain/Step": 9527, "Pretrain/Step Time": 8.476879704743624} +{"Pretrain/Learning Rate": 9.227966297764567e-11, "Pretrain/Loss": 1.9947748184204102, "Pretrain/Loss (Raw)": 2.13743257522583, "Pretrain/Step": 9528, "Pretrain/Step Time": 8.479732345789671} +{"Pretrain/Learning Rate": 7.06516271542501e-11, "Pretrain/Loss": 1.9947656393051147, "Pretrain/Loss (Raw)": 2.0428922176361084, "Pretrain/Step": 9529, "Pretrain/Step Time": 8.480660693719983} +{"Pretrain/Learning Rate": 5.19073243943069e-11, "Pretrain/Loss": 1.9932332038879395, "Pretrain/Loss (Raw)": 1.7719755172729492, "Pretrain/Step": 9530, "Pretrain/Step Time": 8.48270857334137} +{"Pretrain/Learning Rate": 3.604675686275094e-11, "Pretrain/Loss": 1.9929800033569336, "Pretrain/Loss (Raw)": 2.0264017581939697, "Pretrain/Step": 9531, "Pretrain/Step Time": 8.48471126332879} +{"Pretrain/Learning Rate": 2.3069926388674667e-11, "Pretrain/Loss": 1.9928693771362305, "Pretrain/Loss (Raw)": 2.049984931945801, "Pretrain/Step": 9532, "Pretrain/Step Time": 8.482989812269807} +{"Pretrain/Learning Rate": 1.2976834468103605e-11, "Pretrain/Loss": 1.9944789409637451, "Pretrain/Loss (Raw)": 2.1016921997070312, "Pretrain/Step": 9533, "Pretrain/Step Time": 8.483408655971289} +{"Pretrain/Learning Rate": 5.767482261220814e-12, "Pretrain/Loss": 1.9939295053482056, "Pretrain/Loss (Raw)": 1.8972389698028564, "Pretrain/Step": 9534, "Pretrain/Step Time": 8.480945171788335} +{"Pretrain/Learning Rate": 1.4418706062446774e-12, "Pretrain/Loss": 1.993626594543457, "Pretrain/Loss (Raw)": 1.9723374843597412, "Pretrain/Step": 9535, "Pretrain/Step Time": 8.483976250514388} +{"Pretrain/Learning Rate": 0.0, "Pretrain/Loss": 1.9940903186798096, "Pretrain/Loss (Raw)": 1.9370023012161255, "Pretrain/Step": 9536, "Pretrain/Step Time": 8.486040618270636} diff --git a/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/run-metrics.jsonl b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/run-metrics.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0d2ec51d5e922a3c9fe341184f819617bf4cd7d8 --- /dev/null +++ b/obelics+phi3-3b-continue-training-hq-35-run1+stage-pretrain+x7/run-metrics.jsonl @@ -0,0 +1 @@ +{"hparams": {"dataset": {"align_stage_components": ["download/llava-laion-cc-sbu-558k/chat.json", "download/llava-laion-cc-sbu-558k"], "dataset_id": "obelics", "dataset_resampled": true, "dataset_root_dir": "/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/datacomp/datacomp_hq_single_pkl_pil:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/OBELICS/obelics_hq_35_single_pkl_pil:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/synthdog-en/synthdog_single_pkl_pil/", "finetune_stage_components": ["/fsx-training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/llava/llava_v1_5_mix665k.json", "/fsx-training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/llava/data"], "max_num_images": 6, "min_num_images": 1, "train_num_samples": 2441408, "type": "obelics", "workers": 4}, "model": {"align_epochs": 1, "align_global_batch_size": 256, "align_learning_rate": 0.001, "align_lr_scheduler_type": "linear-warmup+cosine-decay", "align_max_grad_norm": 1.0, "align_max_steps": null, "align_per_device_batch_size": 16, "align_train_strategy": "fsdp-shard-grad-op", "align_warmup_ratio": 0.03, "align_weight_decay": 0.0, "arch_specifier": "no-align+avgpool", "enable_gradient_checkpointing": true, "enable_mixed_precision_training": true, "finetune_epochs": 1, "finetune_global_batch_size": 128, "finetune_learning_rate": 2e-05, "finetune_lr_scheduler_type": "linear-warmup+cosine-decay", "finetune_max_grad_norm": 1.0, "finetune_max_steps": null, "finetune_per_device_batch_size": 16, "finetune_train_strategy": "fsdp-full-shard", "finetune_warmup_ratio": 0.03, "finetune_weight_decay": 0.1, "image_resize_strategy": "resize-naive", "llm_backbone_id": "phi3-3b", "llm_max_length": 4096, "model_id": "phi3-3b-continue-training-hq_35", "pretrain_epochs": 1, "pretrain_global_batch_size": 256, "pretrain_learning_rate": 5e-05, "pretrain_lr_scheduler_type": "linear-warmup+cosine-decay", "pretrain_max_grad_norm": 1.0, "pretrain_max_steps": 9536, "pretrain_per_device_batch_size": 8, "pretrain_train_strategy": "fsdp-full-shard", "pretrain_warmup_ratio": 0.03, "pretrain_weight_decay": 0.01, "reduce_in_full_precision": false, "type": "one-stage+7b", "vision_backbone_id": "siglip-vit-so400m-384px"}, "mount_path": "/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/models", "pretrained_checkpoint": null, "run_id": "obelics+phi3-3b-continue-training-hq_35+stage-pretrain+x7", "run_root_dir": "/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/checkpoints/mllm_pretrain_checkpoints", "seed": 7, "stage": "pretrain", "trackers": ["jsonl", "wandb"], "wandb_entity": null, "wandb_project": "mmpretrain"}, "run_id": "obelics+phi3-3b-continue-training-hq_35+stage-pretrain+x7"}