diff --git a/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/latest-checkpoint.pt b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/latest-checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..087af42248fc3e7560b3e0346e9b7ff13a7357fc --- /dev/null +++ b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/latest-checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f723545efea813af0c97f8c6bb242c272b5d3cb3a3dc50f0fc63857280ecf2f3 +size 15336322587 diff --git a/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/step-005000-epoch-00-loss=2.0400.pt b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/step-005000-epoch-00-loss=2.0400.pt new file mode 100644 index 0000000000000000000000000000000000000000..13e136b1b5a9d3513c6b29ee5a6c659c71d98d2a --- /dev/null +++ b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/step-005000-epoch-00-loss=2.0400.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c9634bd09a03a46d8d1538f80a2409eafd85c76d59a000743f6c4b76044479 +size 15336322587 diff --git a/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/step-009537-epoch-00-loss=2.0459.pt b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/step-009537-epoch-00-loss=2.0459.pt new file mode 100644 index 0000000000000000000000000000000000000000..087af42248fc3e7560b3e0346e9b7ff13a7357fc --- /dev/null +++ b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/checkpoints/step-009537-epoch-00-loss=2.0459.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f723545efea813af0c97f8c6bb242c272b5d3cb3a3dc50f0fc63857280ecf2f3 +size 15336322587 diff --git a/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/config.json b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/config.json new file mode 100644 index 0000000000000000000000000000000000000000..3bdc1d692f0a3d5ece541be8aefe966064bb3cbd --- /dev/null +++ b/obelics+phi3-3b-continue-training-dfn+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:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/OBELICS/obelics_dfn_single_pkl:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/synthdog-en/synthdog_single_pkl/", + "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": 2441407, + "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-dfn", + "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": 9537, + "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-dfn+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-dfn+stage-pretrain+x7/config.yaml b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..051ecd1e12b014b04585b0b5f0c31448add6c43e --- /dev/null +++ b/obelics+phi3-3b-continue-training-dfn+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:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/OBELICS/obelics_dfn_single_pkl:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/synthdog-en/synthdog_single_pkl/ + 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: 2441407 + 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-dfn + 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: 9537 + 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-dfn+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-dfn+stage-pretrain+x7/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7.jsonl b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c60ccfe3da9fc73795623cc517a14163c4dcf55b --- /dev/null +++ b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7.jsonl @@ -0,0 +1,9537 @@ +{"Pretrain/Learning Rate": 1.7482517482517484e-07, "Pretrain/Loss": 3.458899974822998, "Pretrain/Loss (Raw)": 3.458899974822998, "Pretrain/Step": 1, "Pretrain/Step Time": 13.411020994186401} +{"Pretrain/Learning Rate": 3.496503496503497e-07, "Pretrain/Loss": 3.582157850265503, "Pretrain/Loss (Raw)": 3.705415725708008, "Pretrain/Step": 2, "Pretrain/Step Time": 10.888911962509155} +{"Pretrain/Learning Rate": 5.244755244755246e-07, "Pretrain/Loss": 3.885371685028076, "Pretrain/Loss (Raw)": 4.491799354553223, "Pretrain/Step": 3, "Pretrain/Step Time": 10.072221994400024} +{"Pretrain/Learning Rate": 6.993006993006994e-07, "Pretrain/Loss": 3.8177781105041504, "Pretrain/Loss (Raw)": 3.614997625350952, "Pretrain/Step": 4, "Pretrain/Step Time": 9.660086691379547} +{"Pretrain/Learning Rate": 8.741258741258743e-07, "Pretrain/Loss": 3.7235000133514404, "Pretrain/Loss (Raw)": 3.346386432647705, "Pretrain/Step": 5, "Pretrain/Step Time": 9.394013690948487} +{"Pretrain/Learning Rate": 1.0489510489510491e-06, "Pretrain/Loss": 3.6605184078216553, "Pretrain/Loss (Raw)": 3.3456108570098877, "Pretrain/Step": 6, "Pretrain/Step Time": 9.270890553792318} +{"Pretrain/Learning Rate": 1.2237762237762238e-06, "Pretrain/Loss": 3.713258743286133, "Pretrain/Loss (Raw)": 4.029700756072998, "Pretrain/Step": 7, "Pretrain/Step Time": 9.142678226743426} +{"Pretrain/Learning Rate": 1.3986013986013987e-06, "Pretrain/Loss": 3.7490057945251465, "Pretrain/Loss (Raw)": 3.999235153198242, "Pretrain/Step": 8, "Pretrain/Step Time": 9.049579411745071} +{"Pretrain/Learning Rate": 1.5734265734265736e-06, "Pretrain/Loss": 3.6808133125305176, "Pretrain/Loss (Raw)": 3.135270833969116, "Pretrain/Step": 9, "Pretrain/Step Time": 9.002247863345676} +{"Pretrain/Learning Rate": 1.7482517482517485e-06, "Pretrain/Loss": 3.675827741622925, "Pretrain/Loss (Raw)": 3.630958080291748, "Pretrain/Step": 10, "Pretrain/Step Time": 8.93379819393158} +{"Pretrain/Learning Rate": 1.9230769230769234e-06, "Pretrain/Loss": 3.6309916973114014, "Pretrain/Loss (Raw)": 3.1826319694519043, "Pretrain/Step": 11, "Pretrain/Step Time": 8.896971659226852} +{"Pretrain/Learning Rate": 2.0979020979020983e-06, "Pretrain/Loss": 3.564743757247925, "Pretrain/Loss (Raw)": 2.83601975440979, "Pretrain/Step": 12, "Pretrain/Step Time": 8.859821995099386} +{"Pretrain/Learning Rate": 2.2727272727272728e-06, "Pretrain/Loss": 3.5092484951019287, "Pretrain/Loss (Raw)": 2.8433029651641846, "Pretrain/Step": 13, "Pretrain/Step Time": 8.85286388030419} +{"Pretrain/Learning Rate": 2.4475524475524477e-06, "Pretrain/Loss": 3.4717447757720947, "Pretrain/Loss (Raw)": 2.9841949939727783, "Pretrain/Step": 14, "Pretrain/Step Time": 8.857121535709926} +{"Pretrain/Learning Rate": 2.6223776223776225e-06, "Pretrain/Loss": 3.4285013675689697, "Pretrain/Loss (Raw)": 2.823094129562378, "Pretrain/Step": 15, "Pretrain/Step Time": 8.865568065643311} +{"Pretrain/Learning Rate": 2.7972027972027974e-06, "Pretrain/Loss": 3.4187605381011963, "Pretrain/Loss (Raw)": 3.272648572921753, "Pretrain/Step": 16, "Pretrain/Step Time": 8.838981330394745} +{"Pretrain/Learning Rate": 2.9720279720279723e-06, "Pretrain/Loss": 3.383307933807373, "Pretrain/Loss (Raw)": 2.8160669803619385, "Pretrain/Step": 17, "Pretrain/Step Time": 8.805194097406725} +{"Pretrain/Learning Rate": 3.1468531468531472e-06, "Pretrain/Loss": 3.3410117626190186, "Pretrain/Loss (Raw)": 2.621973991394043, "Pretrain/Step": 18, "Pretrain/Step Time": 8.79072814517551} +{"Pretrain/Learning Rate": 3.3216783216783217e-06, "Pretrain/Loss": 3.308288335800171, "Pretrain/Loss (Raw)": 2.719268798828125, "Pretrain/Step": 19, "Pretrain/Step Time": 8.757946428499723} +{"Pretrain/Learning Rate": 3.496503496503497e-06, "Pretrain/Loss": 3.3090744018554688, "Pretrain/Loss (Raw)": 3.324005365371704, "Pretrain/Step": 20, "Pretrain/Step Time": 8.735656142234802} +{"Pretrain/Learning Rate": 3.6713286713286715e-06, "Pretrain/Loss": 3.282766819000244, "Pretrain/Loss (Raw)": 2.756619930267334, "Pretrain/Step": 21, "Pretrain/Step Time": 8.71490656761896} +{"Pretrain/Learning Rate": 3.846153846153847e-06, "Pretrain/Loss": 3.249319314956665, "Pretrain/Loss (Raw)": 2.5469167232513428, "Pretrain/Step": 22, "Pretrain/Step Time": 8.695616191083735} +{"Pretrain/Learning Rate": 4.020979020979021e-06, "Pretrain/Loss": 3.2278664112091064, "Pretrain/Loss (Raw)": 2.7559072971343994, "Pretrain/Step": 23, "Pretrain/Step Time": 8.677234753318455} +{"Pretrain/Learning Rate": 4.195804195804197e-06, "Pretrain/Loss": 3.203381061553955, "Pretrain/Loss (Raw)": 2.640216827392578, "Pretrain/Step": 24, "Pretrain/Step Time": 8.664979100227356} +{"Pretrain/Learning Rate": 4.370629370629371e-06, "Pretrain/Loss": 3.184279680252075, "Pretrain/Loss (Raw)": 2.7258548736572266, "Pretrain/Step": 25, "Pretrain/Step Time": 8.649038009643554} +{"Pretrain/Learning Rate": 4.5454545454545455e-06, "Pretrain/Loss": 3.1635966300964355, "Pretrain/Loss (Raw)": 2.646512746810913, "Pretrain/Step": 26, "Pretrain/Step Time": 8.630837055353018} +{"Pretrain/Learning Rate": 4.72027972027972e-06, "Pretrain/Loss": 3.136096477508545, "Pretrain/Loss (Raw)": 2.421096086502075, "Pretrain/Step": 27, "Pretrain/Step Time": 8.627105598096493} +{"Pretrain/Learning Rate": 4.895104895104895e-06, "Pretrain/Loss": 3.1069321632385254, "Pretrain/Loss (Raw)": 2.3194918632507324, "Pretrain/Step": 28, "Pretrain/Step Time": 8.615981706551143} +{"Pretrain/Learning Rate": 5.06993006993007e-06, "Pretrain/Loss": 3.1006181240081787, "Pretrain/Loss (Raw)": 2.9238297939300537, "Pretrain/Step": 29, "Pretrain/Step Time": 8.63180185186452} +{"Pretrain/Learning Rate": 5.244755244755245e-06, "Pretrain/Loss": 3.078004837036133, "Pretrain/Loss (Raw)": 2.422213315963745, "Pretrain/Step": 30, "Pretrain/Step Time": 8.633006914456685} +{"Pretrain/Learning Rate": 5.419580419580419e-06, "Pretrain/Loss": 3.05204701423645, "Pretrain/Loss (Raw)": 2.2733142375946045, "Pretrain/Step": 31, "Pretrain/Step Time": 8.631234553552442} +{"Pretrain/Learning Rate": 5.594405594405595e-06, "Pretrain/Loss": 3.0263543128967285, "Pretrain/Loss (Raw)": 2.22988224029541, "Pretrain/Step": 32, "Pretrain/Step Time": 8.624132163822651} +{"Pretrain/Learning Rate": 5.76923076923077e-06, "Pretrain/Loss": 3.016242742538452, "Pretrain/Loss (Raw)": 2.69266939163208, "Pretrain/Step": 33, "Pretrain/Step Time": 8.616115967432657} +{"Pretrain/Learning Rate": 5.944055944055945e-06, "Pretrain/Loss": 3.000154733657837, "Pretrain/Loss (Raw)": 2.4692418575286865, "Pretrain/Step": 34, "Pretrain/Step Time": 8.606184973436243} +{"Pretrain/Learning Rate": 6.1188811188811196e-06, "Pretrain/Loss": 2.9807686805725098, "Pretrain/Loss (Raw)": 2.3216543197631836, "Pretrain/Step": 35, "Pretrain/Step Time": 8.595040804999215} +{"Pretrain/Learning Rate": 6.2937062937062944e-06, "Pretrain/Loss": 2.9615962505340576, "Pretrain/Loss (Raw)": 2.2905523777008057, "Pretrain/Step": 36, "Pretrain/Step Time": 8.586331566174826} +{"Pretrain/Learning Rate": 6.468531468531469e-06, "Pretrain/Loss": 2.9435014724731445, "Pretrain/Loss (Raw)": 2.292095184326172, "Pretrain/Step": 37, "Pretrain/Step Time": 8.582550145484305} +{"Pretrain/Learning Rate": 6.643356643356643e-06, "Pretrain/Loss": 2.9272685050964355, "Pretrain/Loss (Raw)": 2.3266420364379883, "Pretrain/Step": 38, "Pretrain/Step Time": 8.573498387085763} +{"Pretrain/Learning Rate": 6.818181818181818e-06, "Pretrain/Loss": 2.9198920726776123, "Pretrain/Loss (Raw)": 2.6395976543426514, "Pretrain/Step": 39, "Pretrain/Step Time": 8.571827607277113} +{"Pretrain/Learning Rate": 6.993006993006994e-06, "Pretrain/Loss": 2.9071788787841797, "Pretrain/Loss (Raw)": 2.4113636016845703, "Pretrain/Step": 40, "Pretrain/Step Time": 8.567232346534729} +{"Pretrain/Learning Rate": 7.167832167832168e-06, "Pretrain/Loss": 2.893641471862793, "Pretrain/Loss (Raw)": 2.3521485328674316, "Pretrain/Step": 41, "Pretrain/Step Time": 8.560540501664324} +{"Pretrain/Learning Rate": 7.342657342657343e-06, "Pretrain/Loss": 2.8850958347320557, "Pretrain/Loss (Raw)": 2.534721612930298, "Pretrain/Step": 42, "Pretrain/Step Time": 8.553744849704561} +{"Pretrain/Learning Rate": 7.517482517482517e-06, "Pretrain/Loss": 2.874415636062622, "Pretrain/Loss (Raw)": 2.425842046737671, "Pretrain/Step": 43, "Pretrain/Step Time": 8.545591836751894} +{"Pretrain/Learning Rate": 7.692307692307694e-06, "Pretrain/Loss": 2.862849235534668, "Pretrain/Loss (Raw)": 2.3654990196228027, "Pretrain/Step": 44, "Pretrain/Step Time": 8.544987125830216} +{"Pretrain/Learning Rate": 7.867132867132867e-06, "Pretrain/Loss": 2.852407455444336, "Pretrain/Loss (Raw)": 2.3929736614227295, "Pretrain/Step": 45, "Pretrain/Step Time": 8.55472542974684} +{"Pretrain/Learning Rate": 8.041958041958042e-06, "Pretrain/Loss": 2.844529151916504, "Pretrain/Loss (Raw)": 2.4900074005126953, "Pretrain/Step": 46, "Pretrain/Step Time": 8.568736345871635} +{"Pretrain/Learning Rate": 8.216783216783217e-06, "Pretrain/Loss": 2.8304760456085205, "Pretrain/Loss (Raw)": 2.184035062789917, "Pretrain/Step": 47, "Pretrain/Step Time": 8.565402061381238} +{"Pretrain/Learning Rate": 8.391608391608393e-06, "Pretrain/Loss": 2.8269031047821045, "Pretrain/Loss (Raw)": 2.658964157104492, "Pretrain/Step": 48, "Pretrain/Step Time": 8.569782674312592} +{"Pretrain/Learning Rate": 8.566433566433566e-06, "Pretrain/Loss": 2.820570945739746, "Pretrain/Loss (Raw)": 2.516632080078125, "Pretrain/Step": 49, "Pretrain/Step Time": 8.567453841773832} +{"Pretrain/Learning Rate": 8.741258741258741e-06, "Pretrain/Loss": 2.820909261703491, "Pretrain/Loss (Raw)": 2.837491035461426, "Pretrain/Step": 50, "Pretrain/Step Time": 8.563882737159728} +{"Pretrain/Learning Rate": 8.916083916083918e-06, "Pretrain/Loss": 2.816201686859131, "Pretrain/Loss (Raw)": 2.5808236598968506, "Pretrain/Step": 51, "Pretrain/Step Time": 8.559049746569466} +{"Pretrain/Learning Rate": 9.090909090909091e-06, "Pretrain/Loss": 2.810429096221924, "Pretrain/Loss (Raw)": 2.5160133838653564, "Pretrain/Step": 52, "Pretrain/Step Time": 8.55395147892145} +{"Pretrain/Learning Rate": 9.265734265734266e-06, "Pretrain/Loss": 2.7995147705078125, "Pretrain/Loss (Raw)": 2.231981039047241, "Pretrain/Step": 53, "Pretrain/Step Time": 8.553123100748602} +{"Pretrain/Learning Rate": 9.44055944055944e-06, "Pretrain/Loss": 2.7916247844696045, "Pretrain/Loss (Raw)": 2.37345814704895, "Pretrain/Step": 54, "Pretrain/Step Time": 8.557181375998038} +{"Pretrain/Learning Rate": 9.615384615384616e-06, "Pretrain/Loss": 2.7817177772521973, "Pretrain/Loss (Raw)": 2.246731996536255, "Pretrain/Step": 55, "Pretrain/Step Time": 8.552045067873868} +{"Pretrain/Learning Rate": 9.79020979020979e-06, "Pretrain/Loss": 2.771303653717041, "Pretrain/Loss (Raw)": 2.1985273361206055, "Pretrain/Step": 56, "Pretrain/Step Time": 8.548445143869944} +{"Pretrain/Learning Rate": 9.965034965034966e-06, "Pretrain/Loss": 2.76322865486145, "Pretrain/Loss (Raw)": 2.3110361099243164, "Pretrain/Step": 57, "Pretrain/Step Time": 8.546270065140305} +{"Pretrain/Learning Rate": 1.013986013986014e-05, "Pretrain/Loss": 2.756321907043457, "Pretrain/Loss (Raw)": 2.3626415729522705, "Pretrain/Step": 58, "Pretrain/Step Time": 8.541129979594} +{"Pretrain/Learning Rate": 1.0314685314685315e-05, "Pretrain/Loss": 2.7510414123535156, "Pretrain/Loss (Raw)": 2.4447684288024902, "Pretrain/Step": 59, "Pretrain/Step Time": 8.54054809828936} +{"Pretrain/Learning Rate": 1.048951048951049e-05, "Pretrain/Loss": 2.743488311767578, "Pretrain/Loss (Raw)": 2.2978391647338867, "Pretrain/Step": 60, "Pretrain/Step Time": 8.54903178215027} +{"Pretrain/Learning Rate": 1.0664335664335665e-05, "Pretrain/Loss": 2.740777015686035, "Pretrain/Loss (Raw)": 2.5781302452087402, "Pretrain/Step": 61, "Pretrain/Step Time": 8.547616368434468} +{"Pretrain/Learning Rate": 1.0839160839160838e-05, "Pretrain/Loss": 2.733933448791504, "Pretrain/Loss (Raw)": 2.3164632320404053, "Pretrain/Step": 62, "Pretrain/Step Time": 8.553107038620979} +{"Pretrain/Learning Rate": 1.1013986013986015e-05, "Pretrain/Loss": 2.7275683879852295, "Pretrain/Loss (Raw)": 2.3329060077667236, "Pretrain/Step": 63, "Pretrain/Step Time": 8.557034746048943} +{"Pretrain/Learning Rate": 1.118881118881119e-05, "Pretrain/Loss": 2.724966049194336, "Pretrain/Loss (Raw)": 2.561034917831421, "Pretrain/Step": 64, "Pretrain/Step Time": 8.55274448171258} +{"Pretrain/Learning Rate": 1.1363636363636365e-05, "Pretrain/Loss": 2.7160427570343018, "Pretrain/Loss (Raw)": 2.1449661254882812, "Pretrain/Step": 65, "Pretrain/Step Time": 8.547624074495756} +{"Pretrain/Learning Rate": 1.153846153846154e-05, "Pretrain/Loss": 2.710069179534912, "Pretrain/Loss (Raw)": 2.321784734725952, "Pretrain/Step": 66, "Pretrain/Step Time": 8.544414433566006} +{"Pretrain/Learning Rate": 1.1713286713286714e-05, "Pretrain/Loss": 2.7043473720550537, "Pretrain/Loss (Raw)": 2.3267078399658203, "Pretrain/Step": 67, "Pretrain/Step Time": 8.539870692722833} +{"Pretrain/Learning Rate": 1.188811188811189e-05, "Pretrain/Loss": 2.698174476623535, "Pretrain/Loss (Raw)": 2.284574031829834, "Pretrain/Step": 68, "Pretrain/Step Time": 8.536200579474954} +{"Pretrain/Learning Rate": 1.2062937062937063e-05, "Pretrain/Loss": 2.69114351272583, "Pretrain/Loss (Raw)": 2.2130415439605713, "Pretrain/Step": 69, "Pretrain/Step Time": 8.530942115230836} +{"Pretrain/Learning Rate": 1.2237762237762239e-05, "Pretrain/Loss": 2.685957670211792, "Pretrain/Loss (Raw)": 2.328144073486328, "Pretrain/Step": 70, "Pretrain/Step Time": 8.532046164785113} +{"Pretrain/Learning Rate": 1.2412587412587414e-05, "Pretrain/Loss": 2.679701089859009, "Pretrain/Loss (Raw)": 2.2417449951171875, "Pretrain/Step": 71, "Pretrain/Step Time": 8.526175240395775} +{"Pretrain/Learning Rate": 1.2587412587412589e-05, "Pretrain/Loss": 2.676841974258423, "Pretrain/Loss (Raw)": 2.47383713722229, "Pretrain/Step": 72, "Pretrain/Step Time": 8.642710351281696} +{"Pretrain/Learning Rate": 1.2762237762237764e-05, "Pretrain/Loss": 2.675366163253784, "Pretrain/Loss (Raw)": 2.5691208839416504, "Pretrain/Step": 73, "Pretrain/Step Time": 8.639569987989452} +{"Pretrain/Learning Rate": 1.2937062937062939e-05, "Pretrain/Loss": 2.6686220169067383, "Pretrain/Loss (Raw)": 2.1762852668762207, "Pretrain/Step": 74, "Pretrain/Step Time": 8.637019621359336} +{"Pretrain/Learning Rate": 1.3111888111888112e-05, "Pretrain/Loss": 2.665731191635132, "Pretrain/Loss (Raw)": 2.451812505722046, "Pretrain/Step": 75, "Pretrain/Step Time": 8.63769250869751} +{"Pretrain/Learning Rate": 1.3286713286713287e-05, "Pretrain/Loss": 2.6641926765441895, "Pretrain/Loss (Raw)": 2.548811912536621, "Pretrain/Step": 76, "Pretrain/Step Time": 8.659208605163975} +{"Pretrain/Learning Rate": 1.3461538461538462e-05, "Pretrain/Loss": 2.661609649658203, "Pretrain/Loss (Raw)": 2.465291738510132, "Pretrain/Step": 77, "Pretrain/Step Time": 8.655043521484771} +{"Pretrain/Learning Rate": 1.3636363636363637e-05, "Pretrain/Loss": 2.658095598220825, "Pretrain/Loss (Raw)": 2.3875136375427246, "Pretrain/Step": 78, "Pretrain/Step Time": 8.67332349373744} +{"Pretrain/Learning Rate": 1.381118881118881e-05, "Pretrain/Loss": 2.6537182331085205, "Pretrain/Loss (Raw)": 2.312274217605591, "Pretrain/Step": 79, "Pretrain/Step Time": 8.670736273632773} +{"Pretrain/Learning Rate": 1.3986013986013988e-05, "Pretrain/Loss": 2.6518771648406982, "Pretrain/Loss (Raw)": 2.506438732147217, "Pretrain/Step": 80, "Pretrain/Step Time": 8.676882115006446} +{"Pretrain/Learning Rate": 1.4160839160839163e-05, "Pretrain/Loss": 2.6455764770507812, "Pretrain/Loss (Raw)": 2.1415107250213623, "Pretrain/Step": 81, "Pretrain/Step Time": 8.684677806901343} +{"Pretrain/Learning Rate": 1.4335664335664336e-05, "Pretrain/Loss": 2.640848159790039, "Pretrain/Loss (Raw)": 2.2578694820404053, "Pretrain/Step": 82, "Pretrain/Step Time": 8.692633791667658} +{"Pretrain/Learning Rate": 1.4510489510489511e-05, "Pretrain/Loss": 2.6396634578704834, "Pretrain/Loss (Raw)": 2.5425286293029785, "Pretrain/Step": 83, "Pretrain/Step Time": 8.68714529347707} +{"Pretrain/Learning Rate": 1.4685314685314686e-05, "Pretrain/Loss": 2.6348495483398438, "Pretrain/Loss (Raw)": 2.235278844833374, "Pretrain/Step": 84, "Pretrain/Step Time": 8.683036724726358} +{"Pretrain/Learning Rate": 1.486013986013986e-05, "Pretrain/Loss": 2.6343345642089844, "Pretrain/Loss (Raw)": 2.591088056564331, "Pretrain/Step": 85, "Pretrain/Step Time": 8.678919590220731} +{"Pretrain/Learning Rate": 1.5034965034965034e-05, "Pretrain/Loss": 2.6326982975006104, "Pretrain/Loss (Raw)": 2.493612766265869, "Pretrain/Step": 86, "Pretrain/Step Time": 8.67706905963809} +{"Pretrain/Learning Rate": 1.5209790209790212e-05, "Pretrain/Loss": 2.630164861679077, "Pretrain/Loss (Raw)": 2.4122908115386963, "Pretrain/Step": 87, "Pretrain/Step Time": 8.689129788300086} +{"Pretrain/Learning Rate": 1.5384615384615387e-05, "Pretrain/Loss": 2.6309115886688232, "Pretrain/Loss (Raw)": 2.6958539485931396, "Pretrain/Step": 88, "Pretrain/Step Time": 8.684900665825063} +{"Pretrain/Learning Rate": 1.555944055944056e-05, "Pretrain/Loss": 2.6287291049957275, "Pretrain/Loss (Raw)": 2.4366917610168457, "Pretrain/Step": 89, "Pretrain/Step Time": 8.680549546573939} +{"Pretrain/Learning Rate": 1.5734265734265734e-05, "Pretrain/Loss": 2.6249024868011475, "Pretrain/Loss (Raw)": 2.2843098640441895, "Pretrain/Step": 90, "Pretrain/Step Time": 8.692381082640754} +{"Pretrain/Learning Rate": 1.590909090909091e-05, "Pretrain/Loss": 2.624656915664673, "Pretrain/Loss (Raw)": 2.602559804916382, "Pretrain/Step": 91, "Pretrain/Step Time": 8.69660300212902} +{"Pretrain/Learning Rate": 1.6083916083916083e-05, "Pretrain/Loss": 2.619428873062134, "Pretrain/Loss (Raw)": 2.143674850463867, "Pretrain/Step": 92, "Pretrain/Step Time": 8.701513220434604} +{"Pretrain/Learning Rate": 1.625874125874126e-05, "Pretrain/Loss": 2.6155545711517334, "Pretrain/Loss (Raw)": 2.259126663208008, "Pretrain/Step": 93, "Pretrain/Step Time": 8.700862482029905} +{"Pretrain/Learning Rate": 1.6433566433566433e-05, "Pretrain/Loss": 2.6135141849517822, "Pretrain/Loss (Raw)": 2.423766851425171, "Pretrain/Step": 94, "Pretrain/Step Time": 8.718686220493723} +{"Pretrain/Learning Rate": 1.660839160839161e-05, "Pretrain/Loss": 2.6103885173797607, "Pretrain/Loss (Raw)": 2.3165841102600098, "Pretrain/Step": 95, "Pretrain/Step Time": 8.720339524118524} +{"Pretrain/Learning Rate": 1.6783216783216786e-05, "Pretrain/Loss": 2.60728120803833, "Pretrain/Loss (Raw)": 2.3120779991149902, "Pretrain/Step": 96, "Pretrain/Step Time": 8.714902333915234} +{"Pretrain/Learning Rate": 1.695804195804196e-05, "Pretrain/Loss": 2.6049513816833496, "Pretrain/Loss (Raw)": 2.381309747695923, "Pretrain/Step": 97, "Pretrain/Step Time": 8.724770069122314} +{"Pretrain/Learning Rate": 1.7132867132867133e-05, "Pretrain/Loss": 2.6015961170196533, "Pretrain/Loss (Raw)": 2.2761213779449463, "Pretrain/Step": 98, "Pretrain/Step Time": 8.723631399018425} +{"Pretrain/Learning Rate": 1.730769230769231e-05, "Pretrain/Loss": 2.598905563354492, "Pretrain/Loss (Raw)": 2.335221529006958, "Pretrain/Step": 99, "Pretrain/Step Time": 8.72042707000116} +{"Pretrain/Learning Rate": 1.7482517482517483e-05, "Pretrain/Loss": 2.5945587158203125, "Pretrain/Loss (Raw)": 2.1642372608184814, "Pretrain/Step": 100, "Pretrain/Step Time": 8.721858081817627} +{"Pretrain/Learning Rate": 1.7657342657342656e-05, "Pretrain/Loss": 2.589625597000122, "Pretrain/Loss (Raw)": 2.096284866333008, "Pretrain/Step": 101, "Pretrain/Step Time": 8.718369316346575} +{"Pretrain/Learning Rate": 1.7832167832167836e-05, "Pretrain/Loss": 2.5873398780822754, "Pretrain/Loss (Raw)": 2.356491804122925, "Pretrain/Step": 102, "Pretrain/Step Time": 8.715385226642384} +{"Pretrain/Learning Rate": 1.800699300699301e-05, "Pretrain/Loss": 2.5854392051696777, "Pretrain/Loss (Raw)": 2.391575336456299, "Pretrain/Step": 103, "Pretrain/Step Time": 8.718485302138097} +{"Pretrain/Learning Rate": 1.8181818181818182e-05, "Pretrain/Loss": 2.5837783813476562, "Pretrain/Loss (Raw)": 2.412700891494751, "Pretrain/Step": 104, "Pretrain/Step Time": 8.723528809272326} +{"Pretrain/Learning Rate": 1.835664335664336e-05, "Pretrain/Loss": 2.5807301998138428, "Pretrain/Loss (Raw)": 2.263719320297241, "Pretrain/Step": 105, "Pretrain/Step Time": 8.719774128141857} +{"Pretrain/Learning Rate": 1.8531468531468532e-05, "Pretrain/Loss": 2.5795657634735107, "Pretrain/Loss (Raw)": 2.4573185443878174, "Pretrain/Step": 106, "Pretrain/Step Time": 8.720752644089034} +{"Pretrain/Learning Rate": 1.8706293706293705e-05, "Pretrain/Loss": 2.578392267227173, "Pretrain/Loss (Raw)": 2.453988790512085, "Pretrain/Step": 107, "Pretrain/Step Time": 8.720228128344099} +{"Pretrain/Learning Rate": 1.888111888111888e-05, "Pretrain/Loss": 2.5763919353485107, "Pretrain/Loss (Raw)": 2.3623721599578857, "Pretrain/Step": 108, "Pretrain/Step Time": 8.73096196077488} +{"Pretrain/Learning Rate": 1.9055944055944055e-05, "Pretrain/Loss": 2.574367046356201, "Pretrain/Loss (Raw)": 2.3556785583496094, "Pretrain/Step": 109, "Pretrain/Step Time": 8.728679296073564} +{"Pretrain/Learning Rate": 1.923076923076923e-05, "Pretrain/Loss": 2.571911573410034, "Pretrain/Loss (Raw)": 2.3042640686035156, "Pretrain/Step": 110, "Pretrain/Step Time": 8.72537037676031} +{"Pretrain/Learning Rate": 1.9405594405594408e-05, "Pretrain/Loss": 2.5715088844299316, "Pretrain/Loss (Raw)": 2.5271859169006348, "Pretrain/Step": 111, "Pretrain/Step Time": 8.726922984595772} +{"Pretrain/Learning Rate": 1.958041958041958e-05, "Pretrain/Loss": 2.5717175006866455, "Pretrain/Loss (Raw)": 2.594902992248535, "Pretrain/Step": 112, "Pretrain/Step Time": 8.72289676964283} +{"Pretrain/Learning Rate": 1.9755244755244758e-05, "Pretrain/Loss": 2.56904935836792, "Pretrain/Loss (Raw)": 2.27021861076355, "Pretrain/Step": 113, "Pretrain/Step Time": 8.723856573611235} +{"Pretrain/Learning Rate": 1.993006993006993e-05, "Pretrain/Loss": 2.5705461502075195, "Pretrain/Loss (Raw)": 2.739678382873535, "Pretrain/Step": 114, "Pretrain/Step Time": 8.728464645251893} +{"Pretrain/Learning Rate": 2.0104895104895104e-05, "Pretrain/Loss": 2.5671815872192383, "Pretrain/Loss (Raw)": 2.1836533546447754, "Pretrain/Step": 115, "Pretrain/Step Time": 8.725041932645052} +{"Pretrain/Learning Rate": 2.027972027972028e-05, "Pretrain/Loss": 2.565453290939331, "Pretrain/Loss (Raw)": 2.366685628890991, "Pretrain/Step": 116, "Pretrain/Step Time": 8.722465550077372} +{"Pretrain/Learning Rate": 2.0454545454545457e-05, "Pretrain/Loss": 2.5630486011505127, "Pretrain/Loss (Raw)": 2.2840752601623535, "Pretrain/Step": 117, "Pretrain/Step Time": 8.716728624115643} +{"Pretrain/Learning Rate": 2.062937062937063e-05, "Pretrain/Loss": 2.5606629848480225, "Pretrain/Loss (Raw)": 2.2815630435943604, "Pretrain/Step": 118, "Pretrain/Step Time": 8.715504902904316} +{"Pretrain/Learning Rate": 2.0804195804195807e-05, "Pretrain/Loss": 2.55751633644104, "Pretrain/Loss (Raw)": 2.186189889907837, "Pretrain/Step": 119, "Pretrain/Step Time": 8.712460760308915} +{"Pretrain/Learning Rate": 2.097902097902098e-05, "Pretrain/Loss": 2.554487705230713, "Pretrain/Loss (Raw)": 2.194072723388672, "Pretrain/Step": 120, "Pretrain/Step Time": 8.718645467360814} +{"Pretrain/Learning Rate": 2.1153846153846154e-05, "Pretrain/Loss": 2.552989959716797, "Pretrain/Loss (Raw)": 2.3732972145080566, "Pretrain/Step": 121, "Pretrain/Step Time": 8.71677463113769} +{"Pretrain/Learning Rate": 2.132867132867133e-05, "Pretrain/Loss": 2.550028085708618, "Pretrain/Loss (Raw)": 2.191647529602051, "Pretrain/Step": 122, "Pretrain/Step Time": 8.71905442339475} +{"Pretrain/Learning Rate": 2.1503496503496503e-05, "Pretrain/Loss": 2.5479016304016113, "Pretrain/Loss (Raw)": 2.2884392738342285, "Pretrain/Step": 123, "Pretrain/Step Time": 8.719441634852712} +{"Pretrain/Learning Rate": 2.1678321678321677e-05, "Pretrain/Loss": 2.545869827270508, "Pretrain/Loss (Raw)": 2.295990228652954, "Pretrain/Step": 124, "Pretrain/Step Time": 8.724253437211436} +{"Pretrain/Learning Rate": 2.1853146853146857e-05, "Pretrain/Loss": 2.543896198272705, "Pretrain/Loss (Raw)": 2.2991411685943604, "Pretrain/Step": 125, "Pretrain/Step Time": 8.741379039764404} +{"Pretrain/Learning Rate": 2.202797202797203e-05, "Pretrain/Loss": 2.5407347679138184, "Pretrain/Loss (Raw)": 2.145530939102173, "Pretrain/Step": 126, "Pretrain/Step Time": 8.739540942131526} +{"Pretrain/Learning Rate": 2.2202797202797203e-05, "Pretrain/Loss": 2.5394766330718994, "Pretrain/Loss (Raw)": 2.3809661865234375, "Pretrain/Step": 127, "Pretrain/Step Time": 8.740207413050133} +{"Pretrain/Learning Rate": 2.237762237762238e-05, "Pretrain/Loss": 2.5369343757629395, "Pretrain/Loss (Raw)": 2.214083433151245, "Pretrain/Step": 128, "Pretrain/Step Time": 8.741422943770885} +{"Pretrain/Learning Rate": 2.2552447552447553e-05, "Pretrain/Loss": 2.529633045196533, "Pretrain/Loss (Raw)": 2.524362087249756, "Pretrain/Step": 129, "Pretrain/Step Time": 8.700805017724633} +{"Pretrain/Learning Rate": 2.272727272727273e-05, "Pretrain/Loss": 2.5189647674560547, "Pretrain/Loss (Raw)": 2.3398537635803223, "Pretrain/Step": 130, "Pretrain/Step Time": 8.702339453622699} +{"Pretrain/Learning Rate": 2.2902097902097902e-05, "Pretrain/Loss": 2.50241756439209, "Pretrain/Loss (Raw)": 2.3737637996673584, "Pretrain/Step": 131, "Pretrain/Step Time": 8.711615029722452} +{"Pretrain/Learning Rate": 2.307692307692308e-05, "Pretrain/Loss": 2.4910683631896973, "Pretrain/Loss (Raw)": 2.1622812747955322, "Pretrain/Step": 132, "Pretrain/Step Time": 8.710576655343175} +{"Pretrain/Learning Rate": 2.3251748251748252e-05, "Pretrain/Loss": 2.4835686683654785, "Pretrain/Loss (Raw)": 2.3864402770996094, "Pretrain/Step": 133, "Pretrain/Step Time": 8.709988951683044} +{"Pretrain/Learning Rate": 2.342657342657343e-05, "Pretrain/Loss": 2.4756088256835938, "Pretrain/Loss (Raw)": 2.326733350753784, "Pretrain/Step": 134, "Pretrain/Step Time": 8.712104056030512} +{"Pretrain/Learning Rate": 2.3601398601398602e-05, "Pretrain/Loss": 2.463813543319702, "Pretrain/Loss (Raw)": 2.5199027061462402, "Pretrain/Step": 135, "Pretrain/Step Time": 8.712368309497833} +{"Pretrain/Learning Rate": 2.377622377622378e-05, "Pretrain/Loss": 2.449295997619629, "Pretrain/Loss (Raw)": 2.1409919261932373, "Pretrain/Step": 136, "Pretrain/Step Time": 8.72172350436449} +{"Pretrain/Learning Rate": 2.3951048951048952e-05, "Pretrain/Loss": 2.4436419010162354, "Pretrain/Loss (Raw)": 2.411557674407959, "Pretrain/Step": 137, "Pretrain/Step Time": 8.723231125622988} +{"Pretrain/Learning Rate": 2.4125874125874125e-05, "Pretrain/Loss": 2.4331841468811035, "Pretrain/Loss (Raw)": 2.292354106903076, "Pretrain/Step": 138, "Pretrain/Step Time": 8.737822322174907} +{"Pretrain/Learning Rate": 2.43006993006993e-05, "Pretrain/Loss": 2.426870822906494, "Pretrain/Loss (Raw)": 2.3745346069335938, "Pretrain/Step": 139, "Pretrain/Step Time": 8.74287985637784} +{"Pretrain/Learning Rate": 2.4475524475524478e-05, "Pretrain/Loss": 2.4226088523864746, "Pretrain/Loss (Raw)": 2.290471315383911, "Pretrain/Step": 140, "Pretrain/Step Time": 8.742320451885462} +{"Pretrain/Learning Rate": 2.465034965034965e-05, "Pretrain/Loss": 2.41804838180542, "Pretrain/Loss (Raw)": 2.2595579624176025, "Pretrain/Step": 141, "Pretrain/Step Time": 8.749942116439342} +{"Pretrain/Learning Rate": 2.4825174825174828e-05, "Pretrain/Loss": 2.411867618560791, "Pretrain/Loss (Raw)": 2.193084955215454, "Pretrain/Step": 142, "Pretrain/Step Time": 8.747390273958445} +{"Pretrain/Learning Rate": 2.5e-05, "Pretrain/Loss": 2.406989812850952, "Pretrain/Loss (Raw)": 2.1987226009368896, "Pretrain/Step": 143, "Pretrain/Step Time": 8.74430288374424} +{"Pretrain/Learning Rate": 2.5174825174825178e-05, "Pretrain/Loss": 2.400595188140869, "Pretrain/Loss (Raw)": 2.4541409015655518, "Pretrain/Step": 144, "Pretrain/Step Time": 8.745851555839181} +{"Pretrain/Learning Rate": 2.534965034965035e-05, "Pretrain/Loss": 2.3976845741271973, "Pretrain/Loss (Raw)": 2.443491220474243, "Pretrain/Step": 145, "Pretrain/Step Time": 8.7509486079216} +{"Pretrain/Learning Rate": 2.5524475524475528e-05, "Pretrain/Loss": 2.3935861587524414, "Pretrain/Loss (Raw)": 2.097362518310547, "Pretrain/Step": 146, "Pretrain/Step Time": 8.748340282589197} +{"Pretrain/Learning Rate": 2.5699300699300697e-05, "Pretrain/Loss": 2.389572858810425, "Pretrain/Loss (Raw)": 2.2056045532226562, "Pretrain/Step": 147, "Pretrain/Step Time": 8.74829382635653} +{"Pretrain/Learning Rate": 2.5874125874125877e-05, "Pretrain/Loss": 2.381276845932007, "Pretrain/Loss (Raw)": 2.262080192565918, "Pretrain/Step": 148, "Pretrain/Step Time": 8.748719265684485} +{"Pretrain/Learning Rate": 2.6048951048951047e-05, "Pretrain/Loss": 2.3762123584747314, "Pretrain/Loss (Raw)": 2.1083905696868896, "Pretrain/Step": 149, "Pretrain/Step Time": 8.752336081117392} +{"Pretrain/Learning Rate": 2.6223776223776224e-05, "Pretrain/Loss": 2.373161554336548, "Pretrain/Loss (Raw)": 2.15641713142395, "Pretrain/Step": 150, "Pretrain/Step Time": 8.75338146649301} +{"Pretrain/Learning Rate": 2.6398601398601404e-05, "Pretrain/Loss": 2.3683815002441406, "Pretrain/Loss (Raw)": 2.144059896469116, "Pretrain/Step": 151, "Pretrain/Step Time": 8.76092098094523} +{"Pretrain/Learning Rate": 2.6573426573426574e-05, "Pretrain/Loss": 2.3644251823425293, "Pretrain/Loss (Raw)": 2.1338002681732178, "Pretrain/Step": 152, "Pretrain/Step Time": 8.75905836187303} +{"Pretrain/Learning Rate": 2.674825174825175e-05, "Pretrain/Loss": 2.3615589141845703, "Pretrain/Loss (Raw)": 2.358975887298584, "Pretrain/Step": 153, "Pretrain/Step Time": 8.765169398859143} +{"Pretrain/Learning Rate": 2.6923076923076923e-05, "Pretrain/Loss": 2.3586349487304688, "Pretrain/Loss (Raw)": 2.2722344398498535, "Pretrain/Step": 154, "Pretrain/Step Time": 8.76890654861927} +{"Pretrain/Learning Rate": 2.70979020979021e-05, "Pretrain/Loss": 2.3580832481384277, "Pretrain/Loss (Raw)": 2.350475788116455, "Pretrain/Step": 155, "Pretrain/Step Time": 8.773469353094697} +{"Pretrain/Learning Rate": 2.7272727272727273e-05, "Pretrain/Loss": 2.356548309326172, "Pretrain/Loss (Raw)": 2.12300443649292, "Pretrain/Step": 156, "Pretrain/Step Time": 8.776771483942866} +{"Pretrain/Learning Rate": 2.744755244755245e-05, "Pretrain/Loss": 2.3509113788604736, "Pretrain/Loss (Raw)": 2.2023394107818604, "Pretrain/Step": 157, "Pretrain/Step Time": 8.784110931679606} +{"Pretrain/Learning Rate": 2.762237762237762e-05, "Pretrain/Loss": 2.349987506866455, "Pretrain/Loss (Raw)": 2.303943634033203, "Pretrain/Step": 158, "Pretrain/Step Time": 8.781189234927297} +{"Pretrain/Learning Rate": 2.77972027972028e-05, "Pretrain/Loss": 2.3499631881713867, "Pretrain/Loss (Raw)": 2.270205020904541, "Pretrain/Step": 159, "Pretrain/Step Time": 8.78255096450448} +{"Pretrain/Learning Rate": 2.7972027972027976e-05, "Pretrain/Loss": 2.3513903617858887, "Pretrain/Loss (Raw)": 2.4125545024871826, "Pretrain/Step": 160, "Pretrain/Step Time": 8.78139502927661} +{"Pretrain/Learning Rate": 2.8146853146853146e-05, "Pretrain/Loss": 2.3482179641723633, "Pretrain/Loss (Raw)": 2.286602020263672, "Pretrain/Step": 161, "Pretrain/Step Time": 8.784749088808894} +{"Pretrain/Learning Rate": 2.8321678321678326e-05, "Pretrain/Loss": 2.3467893600463867, "Pretrain/Loss (Raw)": 2.286358594894409, "Pretrain/Step": 162, "Pretrain/Step Time": 8.785720255225897} +{"Pretrain/Learning Rate": 2.8496503496503496e-05, "Pretrain/Loss": 2.3462986946105957, "Pretrain/Loss (Raw)": 2.258862257003784, "Pretrain/Step": 163, "Pretrain/Step Time": 8.786426877602935} +{"Pretrain/Learning Rate": 2.8671328671328672e-05, "Pretrain/Loss": 2.344855308532715, "Pretrain/Loss (Raw)": 2.105778932571411, "Pretrain/Step": 164, "Pretrain/Step Time": 8.78636852838099} +{"Pretrain/Learning Rate": 2.8846153846153845e-05, "Pretrain/Loss": 2.34243106842041, "Pretrain/Loss (Raw)": 1.9818447828292847, "Pretrain/Step": 165, "Pretrain/Step Time": 8.786356152966619} +{"Pretrain/Learning Rate": 2.9020979020979022e-05, "Pretrain/Loss": 2.3409106731414795, "Pretrain/Loss (Raw)": 2.132002830505371, "Pretrain/Step": 166, "Pretrain/Step Time": 8.79797793738544} +{"Pretrain/Learning Rate": 2.91958041958042e-05, "Pretrain/Loss": 2.337594985961914, "Pretrain/Loss (Raw)": 2.2152061462402344, "Pretrain/Step": 167, "Pretrain/Step Time": 8.79745758883655} +{"Pretrain/Learning Rate": 2.9370629370629372e-05, "Pretrain/Loss": 2.3357620239257812, "Pretrain/Loss (Raw)": 2.1767160892486572, "Pretrain/Step": 168, "Pretrain/Step Time": 8.80032773129642} +{"Pretrain/Learning Rate": 2.954545454545455e-05, "Pretrain/Loss": 2.336393356323242, "Pretrain/Loss (Raw)": 2.4329771995544434, "Pretrain/Step": 169, "Pretrain/Step Time": 8.806094663217664} +{"Pretrain/Learning Rate": 2.972027972027972e-05, "Pretrain/Loss": 2.3340184688568115, "Pretrain/Loss (Raw)": 2.2307403087615967, "Pretrain/Step": 170, "Pretrain/Step Time": 8.806457743048668} +{"Pretrain/Learning Rate": 2.9895104895104898e-05, "Pretrain/Loss": 2.3328781127929688, "Pretrain/Loss (Raw)": 2.2798779010772705, "Pretrain/Step": 171, "Pretrain/Step Time": 8.81475985608995} +{"Pretrain/Learning Rate": 3.0069930069930068e-05, "Pretrain/Loss": 2.332150459289551, "Pretrain/Loss (Raw)": 2.2723236083984375, "Pretrain/Step": 172, "Pretrain/Step Time": 8.819260984659195} +{"Pretrain/Learning Rate": 3.0244755244755245e-05, "Pretrain/Loss": 2.330430746078491, "Pretrain/Loss (Raw)": 2.1728951930999756, "Pretrain/Step": 173, "Pretrain/Step Time": 8.817458041012287} +{"Pretrain/Learning Rate": 3.0419580419580425e-05, "Pretrain/Loss": 2.3280375003814697, "Pretrain/Loss (Raw)": 2.183655261993408, "Pretrain/Step": 174, "Pretrain/Step Time": 8.81388378329575} +{"Pretrain/Learning Rate": 3.0594405594405594e-05, "Pretrain/Loss": 2.328427791595459, "Pretrain/Loss (Raw)": 2.2340197563171387, "Pretrain/Step": 175, "Pretrain/Step Time": 8.818648053333163} +{"Pretrain/Learning Rate": 3.0769230769230774e-05, "Pretrain/Loss": 2.325956344604492, "Pretrain/Loss (Raw)": 2.3425939083099365, "Pretrain/Step": 176, "Pretrain/Step Time": 8.81650173664093} +{"Pretrain/Learning Rate": 3.094405594405594e-05, "Pretrain/Loss": 2.324655532836914, "Pretrain/Loss (Raw)": 2.350111722946167, "Pretrain/Step": 177, "Pretrain/Step Time": 8.815749542787671} +{"Pretrain/Learning Rate": 3.111888111888112e-05, "Pretrain/Loss": 2.3200716972351074, "Pretrain/Loss (Raw)": 2.250783920288086, "Pretrain/Step": 178, "Pretrain/Step Time": 8.814322685822845} +{"Pretrain/Learning Rate": 3.1293706293706294e-05, "Pretrain/Loss": 2.3179216384887695, "Pretrain/Loss (Raw)": 2.305593967437744, "Pretrain/Step": 179, "Pretrain/Step Time": 8.81536154448986} +{"Pretrain/Learning Rate": 3.146853146853147e-05, "Pretrain/Loss": 2.3161768913269043, "Pretrain/Loss (Raw)": 2.292719841003418, "Pretrain/Step": 180, "Pretrain/Step Time": 8.827464308589697} +{"Pretrain/Learning Rate": 3.164335664335665e-05, "Pretrain/Loss": 2.315983772277832, "Pretrain/Loss (Raw)": 2.2072432041168213, "Pretrain/Step": 181, "Pretrain/Step Time": 8.825831631198525} +{"Pretrain/Learning Rate": 3.181818181818182e-05, "Pretrain/Loss": 2.3144829273223877, "Pretrain/Loss (Raw)": 2.1813387870788574, "Pretrain/Step": 182, "Pretrain/Step Time": 8.822146655991673} +{"Pretrain/Learning Rate": 3.1993006993006994e-05, "Pretrain/Loss": 2.31532621383667, "Pretrain/Loss (Raw)": 2.3546650409698486, "Pretrain/Step": 183, "Pretrain/Step Time": 8.827280979603529} +{"Pretrain/Learning Rate": 3.216783216783217e-05, "Pretrain/Loss": 2.313650131225586, "Pretrain/Loss (Raw)": 1.9840174913406372, "Pretrain/Step": 184, "Pretrain/Step Time": 8.830639963969588} +{"Pretrain/Learning Rate": 3.234265734265735e-05, "Pretrain/Loss": 2.31178879737854, "Pretrain/Loss (Raw)": 2.072789192199707, "Pretrain/Step": 185, "Pretrain/Step Time": 8.834395043551922} +{"Pretrain/Learning Rate": 3.251748251748252e-05, "Pretrain/Loss": 2.310401439666748, "Pretrain/Loss (Raw)": 2.1850688457489014, "Pretrain/Step": 186, "Pretrain/Step Time": 8.843690894544125} +{"Pretrain/Learning Rate": 3.269230769230769e-05, "Pretrain/Loss": 2.310059070587158, "Pretrain/Loss (Raw)": 2.4009034633636475, "Pretrain/Step": 187, "Pretrain/Step Time": 8.842052379623055} +{"Pretrain/Learning Rate": 3.2867132867132866e-05, "Pretrain/Loss": 2.3095083236694336, "Pretrain/Loss (Raw)": 2.2273573875427246, "Pretrain/Step": 188, "Pretrain/Step Time": 8.842477848753333} +{"Pretrain/Learning Rate": 3.3041958041958046e-05, "Pretrain/Loss": 2.307162284851074, "Pretrain/Loss (Raw)": 2.277862310409546, "Pretrain/Step": 189, "Pretrain/Step Time": 8.843293368816376} +{"Pretrain/Learning Rate": 3.321678321678322e-05, "Pretrain/Loss": 2.306379795074463, "Pretrain/Loss (Raw)": 2.216277837753296, "Pretrain/Step": 190, "Pretrain/Step Time": 8.842634929344058} +{"Pretrain/Learning Rate": 3.339160839160839e-05, "Pretrain/Loss": 2.3047313690185547, "Pretrain/Loss (Raw)": 2.1219241619110107, "Pretrain/Step": 191, "Pretrain/Step Time": 8.841777116060257} +{"Pretrain/Learning Rate": 3.356643356643357e-05, "Pretrain/Loss": 2.302187919616699, "Pretrain/Loss (Raw)": 2.2354559898376465, "Pretrain/Step": 192, "Pretrain/Step Time": 8.841753894463181} +{"Pretrain/Learning Rate": 3.374125874125874e-05, "Pretrain/Loss": 2.3028340339660645, "Pretrain/Loss (Raw)": 2.2276859283447266, "Pretrain/Step": 193, "Pretrain/Step Time": 8.85424080863595} +{"Pretrain/Learning Rate": 3.391608391608392e-05, "Pretrain/Loss": 2.303004264831543, "Pretrain/Loss (Raw)": 2.3435826301574707, "Pretrain/Step": 194, "Pretrain/Step Time": 8.854027822613716} +{"Pretrain/Learning Rate": 3.409090909090909e-05, "Pretrain/Loss": 2.3009493350982666, "Pretrain/Loss (Raw)": 2.0636518001556396, "Pretrain/Step": 195, "Pretrain/Step Time": 8.856072412803769} +{"Pretrain/Learning Rate": 3.4265734265734265e-05, "Pretrain/Loss": 2.3009207248687744, "Pretrain/Loss (Raw)": 2.280930519104004, "Pretrain/Step": 196, "Pretrain/Step Time": 8.861466562375426} +{"Pretrain/Learning Rate": 3.4440559440559445e-05, "Pretrain/Loss": 2.301279067993164, "Pretrain/Loss (Raw)": 2.2588894367218018, "Pretrain/Step": 197, "Pretrain/Step Time": 8.863106535747647} +{"Pretrain/Learning Rate": 3.461538461538462e-05, "Pretrain/Loss": 2.299816131591797, "Pretrain/Loss (Raw)": 2.140885591506958, "Pretrain/Step": 198, "Pretrain/Step Time": 8.867116561159492} +{"Pretrain/Learning Rate": 3.479020979020979e-05, "Pretrain/Loss": 2.299921989440918, "Pretrain/Loss (Raw)": 2.255326509475708, "Pretrain/Step": 199, "Pretrain/Step Time": 8.87008748948574} +{"Pretrain/Learning Rate": 3.4965034965034965e-05, "Pretrain/Loss": 2.2971670627593994, "Pretrain/Loss (Raw)": 2.1211862564086914, "Pretrain/Step": 200, "Pretrain/Step Time": 8.805547745898366} +{"Pretrain/Learning Rate": 3.5139860139860145e-05, "Pretrain/Loss": 2.2947001457214355, "Pretrain/Loss (Raw)": 2.25335431098938, "Pretrain/Step": 201, "Pretrain/Step Time": 8.821600863710046} +{"Pretrain/Learning Rate": 3.531468531468531e-05, "Pretrain/Loss": 2.2939577102661133, "Pretrain/Loss (Raw)": 2.0812792778015137, "Pretrain/Step": 202, "Pretrain/Step Time": 8.820135664194822} +{"Pretrain/Learning Rate": 3.548951048951049e-05, "Pretrain/Loss": 2.291391372680664, "Pretrain/Loss (Raw)": 2.1232798099517822, "Pretrain/Step": 203, "Pretrain/Step Time": 8.828115072101355} +{"Pretrain/Learning Rate": 3.566433566433567e-05, "Pretrain/Loss": 2.2889909744262695, "Pretrain/Loss (Raw)": 2.2415997982025146, "Pretrain/Step": 204, "Pretrain/Step Time": 8.815011948347092} +{"Pretrain/Learning Rate": 3.583916083916084e-05, "Pretrain/Loss": 2.288358688354492, "Pretrain/Loss (Raw)": 2.3843255043029785, "Pretrain/Step": 205, "Pretrain/Step Time": 8.813861016184092} +{"Pretrain/Learning Rate": 3.601398601398602e-05, "Pretrain/Loss": 2.28714919090271, "Pretrain/Loss (Raw)": 2.2327070236206055, "Pretrain/Step": 206, "Pretrain/Step Time": 8.803725147619843} +{"Pretrain/Learning Rate": 3.618881118881119e-05, "Pretrain/Loss": 2.286444664001465, "Pretrain/Loss (Raw)": 2.222097635269165, "Pretrain/Step": 207, "Pretrain/Step Time": 8.80245372094214} +{"Pretrain/Learning Rate": 3.6363636363636364e-05, "Pretrain/Loss": 2.2842390537261963, "Pretrain/Loss (Raw)": 2.2241108417510986, "Pretrain/Step": 208, "Pretrain/Step Time": 8.797112854197621} +{"Pretrain/Learning Rate": 3.653846153846154e-05, "Pretrain/Loss": 2.2844457626342773, "Pretrain/Loss (Raw)": 2.1679558753967285, "Pretrain/Step": 209, "Pretrain/Step Time": 8.793989095836878} +{"Pretrain/Learning Rate": 3.671328671328672e-05, "Pretrain/Loss": 2.284945487976074, "Pretrain/Loss (Raw)": 2.321855068206787, "Pretrain/Step": 210, "Pretrain/Step Time": 8.79203899204731} +{"Pretrain/Learning Rate": 3.688811188811189e-05, "Pretrain/Loss": 2.283128261566162, "Pretrain/Loss (Raw)": 2.3099043369293213, "Pretrain/Step": 211, "Pretrain/Step Time": 8.799095675349236} +{"Pretrain/Learning Rate": 3.7062937062937064e-05, "Pretrain/Loss": 2.281229019165039, "Pretrain/Loss (Raw)": 1.9922199249267578, "Pretrain/Step": 212, "Pretrain/Step Time": 8.80340875685215} +{"Pretrain/Learning Rate": 3.7237762237762244e-05, "Pretrain/Loss": 2.2787113189697266, "Pretrain/Loss (Raw)": 2.2688040733337402, "Pretrain/Step": 213, "Pretrain/Step Time": 8.811633314937353} +{"Pretrain/Learning Rate": 3.741258741258741e-05, "Pretrain/Loss": 2.2777512073516846, "Pretrain/Loss (Raw)": 2.3707096576690674, "Pretrain/Step": 214, "Pretrain/Step Time": 8.811878982931376} +{"Pretrain/Learning Rate": 3.758741258741259e-05, "Pretrain/Loss": 2.2770438194274902, "Pretrain/Loss (Raw)": 2.3217661380767822, "Pretrain/Step": 215, "Pretrain/Step Time": 8.800229836255312} +{"Pretrain/Learning Rate": 3.776223776223776e-05, "Pretrain/Loss": 2.274333953857422, "Pretrain/Loss (Raw)": 2.3489882946014404, "Pretrain/Step": 216, "Pretrain/Step Time": 8.816633053123951} +{"Pretrain/Learning Rate": 3.7937062937062936e-05, "Pretrain/Loss": 2.2720823287963867, "Pretrain/Loss (Raw)": 2.148463487625122, "Pretrain/Step": 217, "Pretrain/Step Time": 8.819007959216833} +{"Pretrain/Learning Rate": 3.811188811188811e-05, "Pretrain/Loss": 2.271265983581543, "Pretrain/Loss (Raw)": 2.1798291206359863, "Pretrain/Step": 218, "Pretrain/Step Time": 8.81014851666987} +{"Pretrain/Learning Rate": 3.828671328671329e-05, "Pretrain/Loss": 2.2667593955993652, "Pretrain/Loss (Raw)": 2.025707483291626, "Pretrain/Step": 219, "Pretrain/Step Time": 8.815176604315639} +{"Pretrain/Learning Rate": 3.846153846153846e-05, "Pretrain/Loss": 2.2667059898376465, "Pretrain/Loss (Raw)": 2.13683819770813, "Pretrain/Step": 220, "Pretrain/Step Time": 8.810570707544684} +{"Pretrain/Learning Rate": 3.8636363636363636e-05, "Pretrain/Loss": 2.266672372817993, "Pretrain/Loss (Raw)": 2.254838466644287, "Pretrain/Step": 221, "Pretrain/Step Time": 8.810920866206288} +{"Pretrain/Learning Rate": 3.8811188811188816e-05, "Pretrain/Loss": 2.26564884185791, "Pretrain/Loss (Raw)": 2.2927463054656982, "Pretrain/Step": 222, "Pretrain/Step Time": 8.802242087200284} +{"Pretrain/Learning Rate": 3.898601398601399e-05, "Pretrain/Loss": 2.264237880706787, "Pretrain/Loss (Raw)": 2.13596248626709, "Pretrain/Step": 223, "Pretrain/Step Time": 8.802098331972957} +{"Pretrain/Learning Rate": 3.916083916083916e-05, "Pretrain/Loss": 2.263477087020874, "Pretrain/Loss (Raw)": 2.214711904525757, "Pretrain/Step": 224, "Pretrain/Step Time": 8.806701326742768} +{"Pretrain/Learning Rate": 3.9335664335664336e-05, "Pretrain/Loss": 2.2623131275177, "Pretrain/Loss (Raw)": 2.2323086261749268, "Pretrain/Step": 225, "Pretrain/Step Time": 8.802181182429194} +{"Pretrain/Learning Rate": 3.9510489510489516e-05, "Pretrain/Loss": 2.2618508338928223, "Pretrain/Loss (Raw)": 2.216947555541992, "Pretrain/Step": 226, "Pretrain/Step Time": 8.801864081993699} +{"Pretrain/Learning Rate": 3.968531468531469e-05, "Pretrain/Loss": 2.26129150390625, "Pretrain/Loss (Raw)": 2.263643503189087, "Pretrain/Step": 227, "Pretrain/Step Time": 8.800243755802512} +{"Pretrain/Learning Rate": 3.986013986013986e-05, "Pretrain/Loss": 2.261552333831787, "Pretrain/Loss (Raw)": 2.1976394653320312, "Pretrain/Step": 228, "Pretrain/Step Time": 8.79927851445973} +{"Pretrain/Learning Rate": 4.0034965034965035e-05, "Pretrain/Loss": 2.2632272243499756, "Pretrain/Loss (Raw)": 2.3106467723846436, "Pretrain/Step": 229, "Pretrain/Step Time": 8.804290963336825} +{"Pretrain/Learning Rate": 4.020979020979021e-05, "Pretrain/Loss": 2.26155424118042, "Pretrain/Loss (Raw)": 2.142357349395752, "Pretrain/Step": 230, "Pretrain/Step Time": 8.80881499685347} +{"Pretrain/Learning Rate": 4.038461538461539e-05, "Pretrain/Loss": 2.260401725769043, "Pretrain/Loss (Raw)": 2.2440683841705322, "Pretrain/Step": 231, "Pretrain/Step Time": 8.806771237403154} +{"Pretrain/Learning Rate": 4.055944055944056e-05, "Pretrain/Loss": 2.2594032287597656, "Pretrain/Loss (Raw)": 2.2848689556121826, "Pretrain/Step": 232, "Pretrain/Step Time": 8.801957625895739} +{"Pretrain/Learning Rate": 4.0734265734265735e-05, "Pretrain/Loss": 2.2590179443359375, "Pretrain/Loss (Raw)": 2.2144200801849365, "Pretrain/Step": 233, "Pretrain/Step Time": 8.805146435275674} +{"Pretrain/Learning Rate": 4.0909090909090915e-05, "Pretrain/Loss": 2.25789213180542, "Pretrain/Loss (Raw)": 2.3131885528564453, "Pretrain/Step": 234, "Pretrain/Step Time": 8.802816305309534} +{"Pretrain/Learning Rate": 4.108391608391609e-05, "Pretrain/Loss": 2.25634765625, "Pretrain/Loss (Raw)": 2.256304979324341, "Pretrain/Step": 235, "Pretrain/Step Time": 8.802132772281766} +{"Pretrain/Learning Rate": 4.125874125874126e-05, "Pretrain/Loss": 2.2566189765930176, "Pretrain/Loss (Raw)": 2.3971099853515625, "Pretrain/Step": 236, "Pretrain/Step Time": 8.795312790200114} +{"Pretrain/Learning Rate": 4.1433566433566434e-05, "Pretrain/Loss": 2.2567224502563477, "Pretrain/Loss (Raw)": 2.368922472000122, "Pretrain/Step": 237, "Pretrain/Step Time": 8.795082289725542} +{"Pretrain/Learning Rate": 4.1608391608391614e-05, "Pretrain/Loss": 2.256251335144043, "Pretrain/Loss (Raw)": 2.2439897060394287, "Pretrain/Step": 238, "Pretrain/Step Time": 8.796060306951404} +{"Pretrain/Learning Rate": 4.178321678321678e-05, "Pretrain/Loss": 2.254955291748047, "Pretrain/Loss (Raw)": 2.36128830909729, "Pretrain/Step": 239, "Pretrain/Step Time": 8.796699551865458} +{"Pretrain/Learning Rate": 4.195804195804196e-05, "Pretrain/Loss": 2.251178741455078, "Pretrain/Loss (Raw)": 2.1114821434020996, "Pretrain/Step": 240, "Pretrain/Step Time": 8.797781681641936} +{"Pretrain/Learning Rate": 4.213286713286714e-05, "Pretrain/Loss": 2.251250982284546, "Pretrain/Loss (Raw)": 2.279470443725586, "Pretrain/Step": 241, "Pretrain/Step Time": 8.794977072626352} +{"Pretrain/Learning Rate": 4.230769230769231e-05, "Pretrain/Loss": 2.246953248977661, "Pretrain/Loss (Raw)": 2.1895759105682373, "Pretrain/Step": 242, "Pretrain/Step Time": 8.789270663633943} +{"Pretrain/Learning Rate": 4.248251748251749e-05, "Pretrain/Loss": 2.2461771965026855, "Pretrain/Loss (Raw)": 2.0842854976654053, "Pretrain/Step": 243, "Pretrain/Step Time": 8.800914688035846} +{"Pretrain/Learning Rate": 4.265734265734266e-05, "Pretrain/Loss": 2.245043992996216, "Pretrain/Loss (Raw)": 2.2216711044311523, "Pretrain/Step": 244, "Pretrain/Step Time": 8.800840273499489} +{"Pretrain/Learning Rate": 4.2832167832167833e-05, "Pretrain/Loss": 2.2445874214172363, "Pretrain/Loss (Raw)": 2.2256197929382324, "Pretrain/Step": 245, "Pretrain/Step Time": 8.808109551668167} +{"Pretrain/Learning Rate": 4.300699300699301e-05, "Pretrain/Loss": 2.2448818683624268, "Pretrain/Loss (Raw)": 2.319251537322998, "Pretrain/Step": 246, "Pretrain/Step Time": 8.810488358139992} +{"Pretrain/Learning Rate": 4.318181818181819e-05, "Pretrain/Loss": 2.2459774017333984, "Pretrain/Loss (Raw)": 2.326448917388916, "Pretrain/Step": 247, "Pretrain/Step Time": 8.812964303418994} +{"Pretrain/Learning Rate": 4.335664335664335e-05, "Pretrain/Loss": 2.2465076446533203, "Pretrain/Loss (Raw)": 2.2618982791900635, "Pretrain/Step": 248, "Pretrain/Step Time": 8.807770578190684} +{"Pretrain/Learning Rate": 4.353146853146853e-05, "Pretrain/Loss": 2.2452168464660645, "Pretrain/Loss (Raw)": 2.2080936431884766, "Pretrain/Step": 249, "Pretrain/Step Time": 8.813829125836492} +{"Pretrain/Learning Rate": 4.370629370629371e-05, "Pretrain/Loss": 2.245713710784912, "Pretrain/Loss (Raw)": 2.2552266120910645, "Pretrain/Step": 250, "Pretrain/Step Time": 8.811035171151161} +{"Pretrain/Learning Rate": 4.388111888111888e-05, "Pretrain/Loss": 2.245203971862793, "Pretrain/Loss (Raw)": 2.2232112884521484, "Pretrain/Step": 251, "Pretrain/Step Time": 8.811742220073938} +{"Pretrain/Learning Rate": 4.405594405594406e-05, "Pretrain/Loss": 2.244204044342041, "Pretrain/Loss (Raw)": 2.16800856590271, "Pretrain/Step": 252, "Pretrain/Step Time": 8.80386035144329} +{"Pretrain/Learning Rate": 4.423076923076923e-05, "Pretrain/Loss": 2.242513656616211, "Pretrain/Loss (Raw)": 2.0827476978302, "Pretrain/Step": 253, "Pretrain/Step Time": 8.788151655346155} +{"Pretrain/Learning Rate": 4.4405594405594406e-05, "Pretrain/Loss": 2.2429046630859375, "Pretrain/Loss (Raw)": 2.1955997943878174, "Pretrain/Step": 254, "Pretrain/Step Time": 8.78725766018033} +{"Pretrain/Learning Rate": 4.458041958041958e-05, "Pretrain/Loss": 2.2421927452087402, "Pretrain/Loss (Raw)": 2.2898504734039307, "Pretrain/Step": 255, "Pretrain/Step Time": 8.787303261458874} +{"Pretrain/Learning Rate": 4.475524475524476e-05, "Pretrain/Loss": 2.242600679397583, "Pretrain/Loss (Raw)": 2.266268014907837, "Pretrain/Step": 256, "Pretrain/Step Time": 8.785437323153019} +{"Pretrain/Learning Rate": 4.493006993006993e-05, "Pretrain/Loss": 2.2411210536956787, "Pretrain/Loss (Raw)": 2.3349854946136475, "Pretrain/Step": 257, "Pretrain/Step Time": 8.79347219131887} +{"Pretrain/Learning Rate": 4.5104895104895105e-05, "Pretrain/Loss": 2.2393360137939453, "Pretrain/Loss (Raw)": 2.1113600730895996, "Pretrain/Step": 258, "Pretrain/Step Time": 8.793575186282396} +{"Pretrain/Learning Rate": 4.5279720279720285e-05, "Pretrain/Loss": 2.237743854522705, "Pretrain/Loss (Raw)": 2.169990301132202, "Pretrain/Step": 259, "Pretrain/Step Time": 8.784777734428644} +{"Pretrain/Learning Rate": 4.545454545454546e-05, "Pretrain/Loss": 2.2386975288391113, "Pretrain/Loss (Raw)": 2.2843267917633057, "Pretrain/Step": 260, "Pretrain/Step Time": 8.790314564481378} +{"Pretrain/Learning Rate": 4.562937062937063e-05, "Pretrain/Loss": 2.2380173206329346, "Pretrain/Loss (Raw)": 2.2993853092193604, "Pretrain/Step": 261, "Pretrain/Step Time": 8.792811380699277} +{"Pretrain/Learning Rate": 4.5804195804195805e-05, "Pretrain/Loss": 2.2386441230773926, "Pretrain/Loss (Raw)": 2.4069745540618896, "Pretrain/Step": 262, "Pretrain/Step Time": 8.795060258358717} +{"Pretrain/Learning Rate": 4.597902097902098e-05, "Pretrain/Loss": 2.2359700202941895, "Pretrain/Loss (Raw)": 2.177640914916992, "Pretrain/Step": 263, "Pretrain/Step Time": 8.795925445854664} +{"Pretrain/Learning Rate": 4.615384615384616e-05, "Pretrain/Loss": 2.236443281173706, "Pretrain/Loss (Raw)": 2.201525926589966, "Pretrain/Step": 264, "Pretrain/Step Time": 8.799646673724055} +{"Pretrain/Learning Rate": 4.632867132867133e-05, "Pretrain/Loss": 2.233654022216797, "Pretrain/Loss (Raw)": 2.0545434951782227, "Pretrain/Step": 265, "Pretrain/Step Time": 8.795186508446932} +{"Pretrain/Learning Rate": 4.6503496503496505e-05, "Pretrain/Loss": 2.2336764335632324, "Pretrain/Loss (Raw)": 2.2952301502227783, "Pretrain/Step": 266, "Pretrain/Step Time": 8.784576525911689} +{"Pretrain/Learning Rate": 4.667832167832168e-05, "Pretrain/Loss": 2.2315261363983154, "Pretrain/Loss (Raw)": 2.0992934703826904, "Pretrain/Step": 267, "Pretrain/Step Time": 8.78107169829309} +{"Pretrain/Learning Rate": 4.685314685314686e-05, "Pretrain/Loss": 2.2305679321289062, "Pretrain/Loss (Raw)": 2.167827844619751, "Pretrain/Step": 268, "Pretrain/Step Time": 8.780569355934858} +{"Pretrain/Learning Rate": 4.702797202797203e-05, "Pretrain/Loss": 2.2301840782165527, "Pretrain/Loss (Raw)": 2.210407018661499, "Pretrain/Step": 269, "Pretrain/Step Time": 8.772335598245263} +{"Pretrain/Learning Rate": 4.7202797202797204e-05, "Pretrain/Loss": 2.231665849685669, "Pretrain/Loss (Raw)": 2.3827598094940186, "Pretrain/Step": 270, "Pretrain/Step Time": 8.770421143621206} +{"Pretrain/Learning Rate": 4.7377622377622384e-05, "Pretrain/Loss": 2.232072591781616, "Pretrain/Loss (Raw)": 2.2507920265197754, "Pretrain/Step": 271, "Pretrain/Step Time": 8.770225211977959} +{"Pretrain/Learning Rate": 4.755244755244756e-05, "Pretrain/Loss": 2.2295989990234375, "Pretrain/Loss (Raw)": 2.1374945640563965, "Pretrain/Step": 272, "Pretrain/Step Time": 8.771694108843803} +{"Pretrain/Learning Rate": 4.772727272727273e-05, "Pretrain/Loss": 2.227416515350342, "Pretrain/Loss (Raw)": 2.164133310317993, "Pretrain/Step": 273, "Pretrain/Step Time": 8.76896557584405} +{"Pretrain/Learning Rate": 4.7902097902097904e-05, "Pretrain/Loss": 2.229257583618164, "Pretrain/Loss (Raw)": 2.3330376148223877, "Pretrain/Step": 274, "Pretrain/Step Time": 8.76948095113039} +{"Pretrain/Learning Rate": 4.8076923076923084e-05, "Pretrain/Loss": 2.227538585662842, "Pretrain/Loss (Raw)": 1.9855575561523438, "Pretrain/Step": 275, "Pretrain/Step Time": 8.776097133755684} +{"Pretrain/Learning Rate": 4.825174825174825e-05, "Pretrain/Loss": 2.226458787918091, "Pretrain/Loss (Raw)": 2.123897075653076, "Pretrain/Step": 276, "Pretrain/Step Time": 8.780443418771029} +{"Pretrain/Learning Rate": 4.842657342657343e-05, "Pretrain/Loss": 2.226914882659912, "Pretrain/Loss (Raw)": 2.166748046875, "Pretrain/Step": 277, "Pretrain/Step Time": 8.77719940058887} +{"Pretrain/Learning Rate": 4.86013986013986e-05, "Pretrain/Loss": 2.227768898010254, "Pretrain/Loss (Raw)": 2.2657666206359863, "Pretrain/Step": 278, "Pretrain/Step Time": 8.78790226764977} +{"Pretrain/Learning Rate": 4.8776223776223776e-05, "Pretrain/Loss": 2.229180097579956, "Pretrain/Loss (Raw)": 2.324669361114502, "Pretrain/Step": 279, "Pretrain/Step Time": 8.782144498080015} +{"Pretrain/Learning Rate": 4.8951048951048956e-05, "Pretrain/Loss": 2.2292940616607666, "Pretrain/Loss (Raw)": 2.1483922004699707, "Pretrain/Step": 280, "Pretrain/Step Time": 8.791529331356287} +{"Pretrain/Learning Rate": 4.912587412587413e-05, "Pretrain/Loss": 2.2300796508789062, "Pretrain/Loss (Raw)": 2.4595303535461426, "Pretrain/Step": 281, "Pretrain/Step Time": 8.788646087050438} +{"Pretrain/Learning Rate": 4.93006993006993e-05, "Pretrain/Loss": 2.2287516593933105, "Pretrain/Loss (Raw)": 2.102238416671753, "Pretrain/Step": 282, "Pretrain/Step Time": 8.797286273911595} +{"Pretrain/Learning Rate": 4.9475524475524476e-05, "Pretrain/Loss": 2.228205680847168, "Pretrain/Loss (Raw)": 2.2805991172790527, "Pretrain/Step": 283, "Pretrain/Step Time": 8.791848599910736} +{"Pretrain/Learning Rate": 4.9650349650349656e-05, "Pretrain/Loss": 2.2293927669525146, "Pretrain/Loss (Raw)": 2.2749452590942383, "Pretrain/Step": 284, "Pretrain/Step Time": 8.79195362702012} +{"Pretrain/Learning Rate": 4.982517482517482e-05, "Pretrain/Loss": 2.2295029163360596, "Pretrain/Loss (Raw)": 2.2164509296417236, "Pretrain/Step": 285, "Pretrain/Step Time": 8.778704082593322} +{"Pretrain/Learning Rate": 5e-05, "Pretrain/Loss": 2.2306530475616455, "Pretrain/Loss (Raw)": 2.451145648956299, "Pretrain/Step": 286, "Pretrain/Step Time": 8.786645840853453} +{"Pretrain/Learning Rate": 4.9999998558441094e-05, "Pretrain/Loss": 2.231091260910034, "Pretrain/Loss (Raw)": 2.3263120651245117, "Pretrain/Step": 287, "Pretrain/Step Time": 8.78376574255526} +{"Pretrain/Learning Rate": 4.999999423376456e-05, "Pretrain/Loss": 2.229681968688965, "Pretrain/Loss (Raw)": 2.232147693634033, "Pretrain/Step": 288, "Pretrain/Step Time": 8.785758264362812} +{"Pretrain/Learning Rate": 4.9999987025970884e-05, "Pretrain/Loss": 2.22999906539917, "Pretrain/Loss (Raw)": 2.327177047729492, "Pretrain/Step": 289, "Pretrain/Step Time": 8.78569607436657} +{"Pretrain/Learning Rate": 4.99999769350609e-05, "Pretrain/Loss": 2.2307024002075195, "Pretrain/Loss (Raw)": 2.3764126300811768, "Pretrain/Step": 290, "Pretrain/Step Time": 8.79041020013392} +{"Pretrain/Learning Rate": 4.999996396103577e-05, "Pretrain/Loss": 2.2301454544067383, "Pretrain/Loss (Raw)": 2.1875505447387695, "Pretrain/Step": 291, "Pretrain/Step Time": 8.793729377910495} +{"Pretrain/Learning Rate": 4.999994810389699e-05, "Pretrain/Loss": 2.2308804988861084, "Pretrain/Loss (Raw)": 2.1998891830444336, "Pretrain/Step": 292, "Pretrain/Step Time": 8.79215645417571} +{"Pretrain/Learning Rate": 4.999992936364639e-05, "Pretrain/Loss": 2.2322800159454346, "Pretrain/Loss (Raw)": 2.1609745025634766, "Pretrain/Step": 293, "Pretrain/Step Time": 8.79559488594532} +{"Pretrain/Learning Rate": 4.9999907740286136e-05, "Pretrain/Loss": 2.2330117225646973, "Pretrain/Loss (Raw)": 2.225654125213623, "Pretrain/Step": 294, "Pretrain/Step Time": 8.794392189010978} +{"Pretrain/Learning Rate": 4.9999883233818724e-05, "Pretrain/Loss": 2.2346413135528564, "Pretrain/Loss (Raw)": 2.4237964153289795, "Pretrain/Step": 295, "Pretrain/Step Time": 8.79358983784914} +{"Pretrain/Learning Rate": 4.999985584424696e-05, "Pretrain/Loss": 2.235535144805908, "Pretrain/Loss (Raw)": 2.291151285171509, "Pretrain/Step": 296, "Pretrain/Step Time": 8.798702865839005} +{"Pretrain/Learning Rate": 4.999982557157403e-05, "Pretrain/Loss": 2.2331204414367676, "Pretrain/Loss (Raw)": 2.1238627433776855, "Pretrain/Step": 297, "Pretrain/Step Time": 8.795992797240615} +{"Pretrain/Learning Rate": 4.9999792415803405e-05, "Pretrain/Loss": 2.232576847076416, "Pretrain/Loss (Raw)": 2.1611454486846924, "Pretrain/Step": 298, "Pretrain/Step Time": 8.800147911533713} +{"Pretrain/Learning Rate": 4.999975637693892e-05, "Pretrain/Loss": 2.2336840629577637, "Pretrain/Loss (Raw)": 2.421619415283203, "Pretrain/Step": 299, "Pretrain/Step Time": 8.793035235255957} +{"Pretrain/Learning Rate": 4.999971745498472e-05, "Pretrain/Loss": 2.2339694499969482, "Pretrain/Loss (Raw)": 2.3088583946228027, "Pretrain/Step": 300, "Pretrain/Step Time": 8.788132743909955} +{"Pretrain/Learning Rate": 4.999967564994531e-05, "Pretrain/Loss": 2.2351298332214355, "Pretrain/Loss (Raw)": 2.3214306831359863, "Pretrain/Step": 301, "Pretrain/Step Time": 8.797724897041917} +{"Pretrain/Learning Rate": 4.999963096182549e-05, "Pretrain/Loss": 2.2354021072387695, "Pretrain/Loss (Raw)": 2.218506097793579, "Pretrain/Step": 302, "Pretrain/Step Time": 8.795826928690076} +{"Pretrain/Learning Rate": 4.9999583390630435e-05, "Pretrain/Loss": 2.234175443649292, "Pretrain/Loss (Raw)": 2.0770132541656494, "Pretrain/Step": 303, "Pretrain/Step Time": 8.792261341586709} +{"Pretrain/Learning Rate": 4.999953293636562e-05, "Pretrain/Loss": 2.2328672409057617, "Pretrain/Loss (Raw)": 2.175137758255005, "Pretrain/Step": 304, "Pretrain/Step Time": 8.792399909347296} +{"Pretrain/Learning Rate": 4.9999479599036856e-05, "Pretrain/Loss": 2.2315313816070557, "Pretrain/Loss (Raw)": 2.1791093349456787, "Pretrain/Step": 305, "Pretrain/Step Time": 8.792754143476486} +{"Pretrain/Learning Rate": 4.9999423378650315e-05, "Pretrain/Loss": 2.2310104370117188, "Pretrain/Loss (Raw)": 2.1840829849243164, "Pretrain/Step": 306, "Pretrain/Step Time": 8.795458301901817} +{"Pretrain/Learning Rate": 4.9999364275212466e-05, "Pretrain/Loss": 2.231049060821533, "Pretrain/Loss (Raw)": 2.310577154159546, "Pretrain/Step": 307, "Pretrain/Step Time": 8.80263557843864} +{"Pretrain/Learning Rate": 4.9999302288730126e-05, "Pretrain/Loss": 2.2287797927856445, "Pretrain/Loss (Raw)": 2.0022361278533936, "Pretrain/Step": 308, "Pretrain/Step Time": 8.789696725085378} +{"Pretrain/Learning Rate": 4.9999237419210445e-05, "Pretrain/Loss": 2.230729579925537, "Pretrain/Loss (Raw)": 2.4568185806274414, "Pretrain/Step": 309, "Pretrain/Step Time": 8.799434874206781} +{"Pretrain/Learning Rate": 4.99991696666609e-05, "Pretrain/Loss": 2.2305386066436768, "Pretrain/Loss (Raw)": 2.1569037437438965, "Pretrain/Step": 310, "Pretrain/Step Time": 8.801261868327856} +{"Pretrain/Learning Rate": 4.999909903108932e-05, "Pretrain/Loss": 2.2305898666381836, "Pretrain/Loss (Raw)": 2.361210823059082, "Pretrain/Step": 311, "Pretrain/Step Time": 8.800332337617874} +{"Pretrain/Learning Rate": 4.999902551250384e-05, "Pretrain/Loss": 2.2326879501342773, "Pretrain/Loss (Raw)": 2.252591133117676, "Pretrain/Step": 312, "Pretrain/Step Time": 8.801462206989527} +{"Pretrain/Learning Rate": 4.999894911091293e-05, "Pretrain/Loss": 2.2350480556488037, "Pretrain/Loss (Raw)": 2.3748531341552734, "Pretrain/Step": 313, "Pretrain/Step Time": 8.798611523583531} +{"Pretrain/Learning Rate": 4.999886982632541e-05, "Pretrain/Loss": 2.2395739555358887, "Pretrain/Loss (Raw)": 2.764402151107788, "Pretrain/Step": 314, "Pretrain/Step Time": 8.796173570677638} +{"Pretrain/Learning Rate": 4.999878765875042e-05, "Pretrain/Loss": 2.2375543117523193, "Pretrain/Loss (Raw)": 2.1423983573913574, "Pretrain/Step": 315, "Pretrain/Step Time": 8.798900283873081} +{"Pretrain/Learning Rate": 4.999870260819745e-05, "Pretrain/Loss": 2.237736701965332, "Pretrain/Loss (Raw)": 2.25069260597229, "Pretrain/Step": 316, "Pretrain/Step Time": 8.791483012959361} +{"Pretrain/Learning Rate": 4.999861467467629e-05, "Pretrain/Loss": 2.2383627891540527, "Pretrain/Loss (Raw)": 2.3580117225646973, "Pretrain/Step": 317, "Pretrain/Step Time": 8.791114626452327} +{"Pretrain/Learning Rate": 4.9998523858197094e-05, "Pretrain/Loss": 2.239346981048584, "Pretrain/Loss (Raw)": 2.342273712158203, "Pretrain/Step": 318, "Pretrain/Step Time": 8.794931245967746} +{"Pretrain/Learning Rate": 4.999843015877032e-05, "Pretrain/Loss": 2.240424871444702, "Pretrain/Loss (Raw)": 2.259880542755127, "Pretrain/Step": 319, "Pretrain/Step Time": 8.791672898456454} +{"Pretrain/Learning Rate": 4.99983335764068e-05, "Pretrain/Loss": 2.2421045303344727, "Pretrain/Loss (Raw)": 2.450451135635376, "Pretrain/Step": 320, "Pretrain/Step Time": 8.797656515613198} +{"Pretrain/Learning Rate": 4.999823411111765e-05, "Pretrain/Loss": 2.242727756500244, "Pretrain/Loss (Raw)": 2.30743145942688, "Pretrain/Step": 321, "Pretrain/Step Time": 8.78639293462038} +{"Pretrain/Learning Rate": 4.999813176291433e-05, "Pretrain/Loss": 2.241973876953125, "Pretrain/Loss (Raw)": 2.2470998764038086, "Pretrain/Step": 322, "Pretrain/Step Time": 8.79583191499114} +{"Pretrain/Learning Rate": 4.999802653180868e-05, "Pretrain/Loss": 2.243354320526123, "Pretrain/Loss (Raw)": 2.2403664588928223, "Pretrain/Step": 323, "Pretrain/Step Time": 8.796747526153922} +{"Pretrain/Learning Rate": 4.9997918417812805e-05, "Pretrain/Loss": 2.24295973777771, "Pretrain/Loss (Raw)": 2.2304177284240723, "Pretrain/Step": 324, "Pretrain/Step Time": 8.794062096625566} +{"Pretrain/Learning Rate": 4.999780742093919e-05, "Pretrain/Loss": 2.2440919876098633, "Pretrain/Loss (Raw)": 2.4038100242614746, "Pretrain/Step": 325, "Pretrain/Step Time": 8.797228710725904} +{"Pretrain/Learning Rate": 4.999769354120063e-05, "Pretrain/Loss": 2.2446956634521484, "Pretrain/Loss (Raw)": 2.2181742191314697, "Pretrain/Step": 326, "Pretrain/Step Time": 8.795703019946814} +{"Pretrain/Learning Rate": 4.9997576778610254e-05, "Pretrain/Loss": 2.2454795837402344, "Pretrain/Loss (Raw)": 2.3556289672851562, "Pretrain/Step": 327, "Pretrain/Step Time": 8.794935666024685} +{"Pretrain/Learning Rate": 4.999745713318154e-05, "Pretrain/Loss": 2.2460904121398926, "Pretrain/Loss (Raw)": 2.1994030475616455, "Pretrain/Step": 328, "Pretrain/Step Time": 8.803427912294865} +{"Pretrain/Learning Rate": 4.999733460492826e-05, "Pretrain/Loss": 2.2461657524108887, "Pretrain/Loss (Raw)": 2.2629592418670654, "Pretrain/Step": 329, "Pretrain/Step Time": 8.786120375618339} +{"Pretrain/Learning Rate": 4.999720919386457e-05, "Pretrain/Loss": 2.246778964996338, "Pretrain/Loss (Raw)": 2.159804105758667, "Pretrain/Step": 330, "Pretrain/Step Time": 8.792866591364145} +{"Pretrain/Learning Rate": 4.999708090000493e-05, "Pretrain/Loss": 2.2480649948120117, "Pretrain/Loss (Raw)": 2.287907361984253, "Pretrain/Step": 331, "Pretrain/Step Time": 8.787932220846415} +{"Pretrain/Learning Rate": 4.999694972336413e-05, "Pretrain/Loss": 2.24765682220459, "Pretrain/Loss (Raw)": 2.1893272399902344, "Pretrain/Step": 332, "Pretrain/Step Time": 8.790500532835722} +{"Pretrain/Learning Rate": 4.9996815663957296e-05, "Pretrain/Loss": 2.246885299682617, "Pretrain/Loss (Raw)": 2.285600185394287, "Pretrain/Step": 333, "Pretrain/Step Time": 8.795130046084523} +{"Pretrain/Learning Rate": 4.9996678721799893e-05, "Pretrain/Loss": 2.246967315673828, "Pretrain/Loss (Raw)": 2.2432072162628174, "Pretrain/Step": 334, "Pretrain/Step Time": 8.791954079642892} +{"Pretrain/Learning Rate": 4.999653889690771e-05, "Pretrain/Loss": 2.2473902702331543, "Pretrain/Loss (Raw)": 2.276200294494629, "Pretrain/Step": 335, "Pretrain/Step Time": 8.794291663914919} +{"Pretrain/Learning Rate": 4.9996396189296865e-05, "Pretrain/Loss": 2.246441125869751, "Pretrain/Loss (Raw)": 2.1026344299316406, "Pretrain/Step": 336, "Pretrain/Step Time": 8.8036636300385} +{"Pretrain/Learning Rate": 4.999625059898384e-05, "Pretrain/Loss": 2.246812343597412, "Pretrain/Loss (Raw)": 2.215482711791992, "Pretrain/Step": 337, "Pretrain/Step Time": 8.80156565271318} +{"Pretrain/Learning Rate": 4.99961021259854e-05, "Pretrain/Loss": 2.2464492321014404, "Pretrain/Loss (Raw)": 2.2753758430480957, "Pretrain/Step": 338, "Pretrain/Step Time": 8.796112854033709} +{"Pretrain/Learning Rate": 4.999595077031868e-05, "Pretrain/Loss": 2.2456626892089844, "Pretrain/Loss (Raw)": 2.209195852279663, "Pretrain/Step": 339, "Pretrain/Step Time": 8.798952596262097} +{"Pretrain/Learning Rate": 4.9995796532001136e-05, "Pretrain/Loss": 2.2458865642547607, "Pretrain/Loss (Raw)": 2.0209004878997803, "Pretrain/Step": 340, "Pretrain/Step Time": 8.797082243487239} +{"Pretrain/Learning Rate": 4.999563941105054e-05, "Pretrain/Loss": 2.2442541122436523, "Pretrain/Loss (Raw)": 2.059866428375244, "Pretrain/Step": 341, "Pretrain/Step Time": 8.793943645432591} +{"Pretrain/Learning Rate": 4.9995479407485035e-05, "Pretrain/Loss": 2.245661973953247, "Pretrain/Loss (Raw)": 2.550916910171509, "Pretrain/Step": 342, "Pretrain/Step Time": 8.802854670211673} +{"Pretrain/Learning Rate": 4.9995316521323066e-05, "Pretrain/Loss": 2.2443900108337402, "Pretrain/Loss (Raw)": 2.15895938873291, "Pretrain/Step": 343, "Pretrain/Step Time": 8.806219162419438} +{"Pretrain/Learning Rate": 4.99951507525834e-05, "Pretrain/Loss": 2.243650436401367, "Pretrain/Loss (Raw)": 2.254290819168091, "Pretrain/Step": 344, "Pretrain/Step Time": 8.789500143378973} +{"Pretrain/Learning Rate": 4.999498210128518e-05, "Pretrain/Loss": 2.24459171295166, "Pretrain/Loss (Raw)": 2.2689690589904785, "Pretrain/Step": 345, "Pretrain/Step Time": 8.794713478535414} +{"Pretrain/Learning Rate": 4.9994810567447834e-05, "Pretrain/Loss": 2.2451674938201904, "Pretrain/Loss (Raw)": 2.253512382507324, "Pretrain/Step": 346, "Pretrain/Step Time": 8.793555088341236} +{"Pretrain/Learning Rate": 4.9994636151091165e-05, "Pretrain/Loss": 2.2476494312286377, "Pretrain/Loss (Raw)": 2.3433988094329834, "Pretrain/Step": 347, "Pretrain/Step Time": 8.785332987084985} +{"Pretrain/Learning Rate": 4.999445885223527e-05, "Pretrain/Loss": 2.2484517097473145, "Pretrain/Loss (Raw)": 2.2395360469818115, "Pretrain/Step": 348, "Pretrain/Step Time": 8.782061088830233} +{"Pretrain/Learning Rate": 4.99942786709006e-05, "Pretrain/Loss": 2.2476651668548584, "Pretrain/Loss (Raw)": 2.154162883758545, "Pretrain/Step": 349, "Pretrain/Step Time": 8.786597969010472} +{"Pretrain/Learning Rate": 4.999409560710794e-05, "Pretrain/Loss": 2.2478837966918945, "Pretrain/Loss (Raw)": 2.3207409381866455, "Pretrain/Step": 350, "Pretrain/Step Time": 8.781903019174933} +{"Pretrain/Learning Rate": 4.99939096608784e-05, "Pretrain/Loss": 2.2485885620117188, "Pretrain/Loss (Raw)": 2.2261569499969482, "Pretrain/Step": 351, "Pretrain/Step Time": 8.777460968121886} +{"Pretrain/Learning Rate": 4.999372083223343e-05, "Pretrain/Loss": 2.250831127166748, "Pretrain/Loss (Raw)": 2.5017313957214355, "Pretrain/Step": 352, "Pretrain/Step Time": 8.777010889723897} +{"Pretrain/Learning Rate": 4.999352912119478e-05, "Pretrain/Loss": 2.249080181121826, "Pretrain/Loss (Raw)": 2.0082216262817383, "Pretrain/Step": 353, "Pretrain/Step Time": 8.777379978448153} +{"Pretrain/Learning Rate": 4.999333452778459e-05, "Pretrain/Loss": 2.2497482299804688, "Pretrain/Loss (Raw)": 2.3024370670318604, "Pretrain/Step": 354, "Pretrain/Step Time": 8.77623145468533} +{"Pretrain/Learning Rate": 4.999313705202529e-05, "Pretrain/Loss": 2.249605655670166, "Pretrain/Loss (Raw)": 2.2454049587249756, "Pretrain/Step": 355, "Pretrain/Step Time": 8.779071286320686} +{"Pretrain/Learning Rate": 4.999293669393965e-05, "Pretrain/Loss": 2.2489752769470215, "Pretrain/Loss (Raw)": 2.116952896118164, "Pretrain/Step": 356, "Pretrain/Step Time": 8.778450028970838} +{"Pretrain/Learning Rate": 4.999273345355078e-05, "Pretrain/Loss": 2.247279167175293, "Pretrain/Loss (Raw)": 2.0935301780700684, "Pretrain/Step": 357, "Pretrain/Step Time": 8.778189679607749} +{"Pretrain/Learning Rate": 4.9992527330882125e-05, "Pretrain/Loss": 2.248047351837158, "Pretrain/Loss (Raw)": 2.2407002449035645, "Pretrain/Step": 358, "Pretrain/Step Time": 8.78054434992373} +{"Pretrain/Learning Rate": 4.999231832595744e-05, "Pretrain/Loss": 2.2484869956970215, "Pretrain/Loss (Raw)": 2.300339937210083, "Pretrain/Step": 359, "Pretrain/Step Time": 8.782449338585138} +{"Pretrain/Learning Rate": 4.9992106438800846e-05, "Pretrain/Loss": 2.2487053871154785, "Pretrain/Loss (Raw)": 2.3128018379211426, "Pretrain/Step": 360, "Pretrain/Step Time": 8.784981219097972} +{"Pretrain/Learning Rate": 4.999189166943677e-05, "Pretrain/Loss": 2.2486228942871094, "Pretrain/Loss (Raw)": 2.203857183456421, "Pretrain/Step": 361, "Pretrain/Step Time": 8.784355506300926} +{"Pretrain/Learning Rate": 4.999167401788998e-05, "Pretrain/Loss": 2.2472314834594727, "Pretrain/Loss (Raw)": 2.135091543197632, "Pretrain/Step": 362, "Pretrain/Step Time": 8.78716185502708} +{"Pretrain/Learning Rate": 4.9991453484185577e-05, "Pretrain/Loss": 2.2465429306030273, "Pretrain/Loss (Raw)": 2.1681859493255615, "Pretrain/Step": 363, "Pretrain/Step Time": 8.794832540675998} +{"Pretrain/Learning Rate": 4.999123006834899e-05, "Pretrain/Loss": 2.2457075119018555, "Pretrain/Loss (Raw)": 2.290172576904297, "Pretrain/Step": 364, "Pretrain/Step Time": 8.790524326264858} +{"Pretrain/Learning Rate": 4.9991003770405994e-05, "Pretrain/Loss": 2.2463393211364746, "Pretrain/Loss (Raw)": 2.449795722961426, "Pretrain/Step": 365, "Pretrain/Step Time": 8.793122557923198} +{"Pretrain/Learning Rate": 4.999077459038268e-05, "Pretrain/Loss": 2.2453269958496094, "Pretrain/Loss (Raw)": 2.1144275665283203, "Pretrain/Step": 366, "Pretrain/Step Time": 8.792256755754352} +{"Pretrain/Learning Rate": 4.9990542528305484e-05, "Pretrain/Loss": 2.244985818862915, "Pretrain/Loss (Raw)": 2.317601442337036, "Pretrain/Step": 367, "Pretrain/Step Time": 8.794153980910778} +{"Pretrain/Learning Rate": 4.999030758420116e-05, "Pretrain/Loss": 2.2459206581115723, "Pretrain/Loss (Raw)": 2.2311177253723145, "Pretrain/Step": 368, "Pretrain/Step Time": 8.794373149052262} +{"Pretrain/Learning Rate": 4.999006975809681e-05, "Pretrain/Loss": 2.2461090087890625, "Pretrain/Loss (Raw)": 2.3035972118377686, "Pretrain/Step": 369, "Pretrain/Step Time": 8.796856507658958} +{"Pretrain/Learning Rate": 4.998982905001986e-05, "Pretrain/Loss": 2.2454774379730225, "Pretrain/Loss (Raw)": 2.108743906021118, "Pretrain/Step": 370, "Pretrain/Step Time": 8.79832480289042} +{"Pretrain/Learning Rate": 4.998958545999806e-05, "Pretrain/Loss": 2.2456274032592773, "Pretrain/Loss (Raw)": 2.103466272354126, "Pretrain/Step": 371, "Pretrain/Step Time": 8.795591652393341} +{"Pretrain/Learning Rate": 4.998933898805951e-05, "Pretrain/Loss": 2.246695041656494, "Pretrain/Loss (Raw)": 2.358363151550293, "Pretrain/Step": 372, "Pretrain/Step Time": 8.794399093836546} +{"Pretrain/Learning Rate": 4.9989089634232645e-05, "Pretrain/Loss": 2.2461929321289062, "Pretrain/Loss (Raw)": 2.1613190174102783, "Pretrain/Step": 373, "Pretrain/Step Time": 8.796545384451747} +{"Pretrain/Learning Rate": 4.9988837398546206e-05, "Pretrain/Loss": 2.2449676990509033, "Pretrain/Loss (Raw)": 2.1624228954315186, "Pretrain/Step": 374, "Pretrain/Step Time": 8.796098841354251} +{"Pretrain/Learning Rate": 4.9988582281029284e-05, "Pretrain/Loss": 2.2443690299987793, "Pretrain/Loss (Raw)": 2.249833583831787, "Pretrain/Step": 375, "Pretrain/Step Time": 8.798428878188133} +{"Pretrain/Learning Rate": 4.998832428171131e-05, "Pretrain/Loss": 2.244807243347168, "Pretrain/Loss (Raw)": 2.3179709911346436, "Pretrain/Step": 376, "Pretrain/Step Time": 8.798372132703662} +{"Pretrain/Learning Rate": 4.998806340062202e-05, "Pretrain/Loss": 2.244866371154785, "Pretrain/Loss (Raw)": 2.215649127960205, "Pretrain/Step": 377, "Pretrain/Step Time": 8.790816953405738} +{"Pretrain/Learning Rate": 4.998779963779152e-05, "Pretrain/Loss": 2.244504928588867, "Pretrain/Loss (Raw)": 2.2089908123016357, "Pretrain/Step": 378, "Pretrain/Step Time": 8.795104704797268} +{"Pretrain/Learning Rate": 4.998753299325021e-05, "Pretrain/Loss": 2.243577718734741, "Pretrain/Loss (Raw)": 2.104504108428955, "Pretrain/Step": 379, "Pretrain/Step Time": 8.790859401226044} +{"Pretrain/Learning Rate": 4.998726346702886e-05, "Pretrain/Loss": 2.2451953887939453, "Pretrain/Loss (Raw)": 2.37510085105896, "Pretrain/Step": 380, "Pretrain/Step Time": 8.790709003806114} +{"Pretrain/Learning Rate": 4.998699105915854e-05, "Pretrain/Loss": 2.2457361221313477, "Pretrain/Loss (Raw)": 2.1519687175750732, "Pretrain/Step": 381, "Pretrain/Step Time": 8.796020790934563} +{"Pretrain/Learning Rate": 4.9986715769670665e-05, "Pretrain/Loss": 2.2449264526367188, "Pretrain/Loss (Raw)": 2.091933488845825, "Pretrain/Step": 382, "Pretrain/Step Time": 8.796258606016636} +{"Pretrain/Learning Rate": 4.998643759859699e-05, "Pretrain/Loss": 2.2441201210021973, "Pretrain/Loss (Raw)": 2.18662691116333, "Pretrain/Step": 383, "Pretrain/Step Time": 8.793046049773693} +{"Pretrain/Learning Rate": 4.998615654596959e-05, "Pretrain/Loss": 2.2428219318389893, "Pretrain/Loss (Raw)": 2.1001176834106445, "Pretrain/Step": 384, "Pretrain/Step Time": 8.795999769121408} +{"Pretrain/Learning Rate": 4.9985872611820885e-05, "Pretrain/Loss": 2.241734027862549, "Pretrain/Loss (Raw)": 2.195758104324341, "Pretrain/Step": 385, "Pretrain/Step Time": 8.790978625416756} +{"Pretrain/Learning Rate": 4.9985585796183605e-05, "Pretrain/Loss": 2.2419137954711914, "Pretrain/Loss (Raw)": 2.134340524673462, "Pretrain/Step": 386, "Pretrain/Step Time": 8.791585121303797} +{"Pretrain/Learning Rate": 4.998529609909084e-05, "Pretrain/Loss": 2.2434229850769043, "Pretrain/Loss (Raw)": 2.3631739616394043, "Pretrain/Step": 387, "Pretrain/Step Time": 8.794118547812104} +{"Pretrain/Learning Rate": 4.998500352057599e-05, "Pretrain/Loss": 2.2428646087646484, "Pretrain/Loss (Raw)": 2.212860584259033, "Pretrain/Step": 388, "Pretrain/Step Time": 8.798716189339757} +{"Pretrain/Learning Rate": 4.9984708060672805e-05, "Pretrain/Loss": 2.243600845336914, "Pretrain/Loss (Raw)": 2.393618106842041, "Pretrain/Step": 389, "Pretrain/Step Time": 8.801152968779206} +{"Pretrain/Learning Rate": 4.9984409719415345e-05, "Pretrain/Loss": 2.2427926063537598, "Pretrain/Loss (Raw)": 2.303520917892456, "Pretrain/Step": 390, "Pretrain/Step Time": 8.797305615618825} +{"Pretrain/Learning Rate": 4.9984108496838034e-05, "Pretrain/Loss": 2.242856502532959, "Pretrain/Loss (Raw)": 2.185814619064331, "Pretrain/Step": 391, "Pretrain/Step Time": 8.798951191827655} +{"Pretrain/Learning Rate": 4.99838043929756e-05, "Pretrain/Loss": 2.2424399852752686, "Pretrain/Loss (Raw)": 2.1482057571411133, "Pretrain/Step": 392, "Pretrain/Step Time": 8.786668218672276} +{"Pretrain/Learning Rate": 4.9983497407863114e-05, "Pretrain/Loss": 2.2445197105407715, "Pretrain/Loss (Raw)": 2.3207695484161377, "Pretrain/Step": 393, "Pretrain/Step Time": 8.794679882004857} +{"Pretrain/Learning Rate": 4.9983187541535984e-05, "Pretrain/Loss": 2.2430577278137207, "Pretrain/Loss (Raw)": 2.108079433441162, "Pretrain/Step": 394, "Pretrain/Step Time": 8.792264182120562} +{"Pretrain/Learning Rate": 4.998287479402994e-05, "Pretrain/Loss": 2.243562936782837, "Pretrain/Loss (Raw)": 2.163963794708252, "Pretrain/Step": 395, "Pretrain/Step Time": 8.791000969707966} +{"Pretrain/Learning Rate": 4.998255916538106e-05, "Pretrain/Loss": 2.245206356048584, "Pretrain/Loss (Raw)": 2.378171920776367, "Pretrain/Step": 396, "Pretrain/Step Time": 8.793746080249548} +{"Pretrain/Learning Rate": 4.998224065562572e-05, "Pretrain/Loss": 2.2456250190734863, "Pretrain/Loss (Raw)": 2.264007329940796, "Pretrain/Step": 397, "Pretrain/Step Time": 8.791539570316672} +{"Pretrain/Learning Rate": 4.998191926480068e-05, "Pretrain/Loss": 2.24357533454895, "Pretrain/Loss (Raw)": 2.1203982830047607, "Pretrain/Step": 398, "Pretrain/Step Time": 8.791689783334732} +{"Pretrain/Learning Rate": 4.998159499294299e-05, "Pretrain/Loss": 2.2440104484558105, "Pretrain/Loss (Raw)": 2.3065059185028076, "Pretrain/Step": 399, "Pretrain/Step Time": 8.801790464669466} +{"Pretrain/Learning Rate": 4.998126784009005e-05, "Pretrain/Loss": 2.2442054748535156, "Pretrain/Loss (Raw)": 2.1624505519866943, "Pretrain/Step": 400, "Pretrain/Step Time": 8.79991134442389} +{"Pretrain/Learning Rate": 4.998093780627958e-05, "Pretrain/Loss": 2.245297431945801, "Pretrain/Loss (Raw)": 2.3039045333862305, "Pretrain/Step": 401, "Pretrain/Step Time": 8.80063602514565} +{"Pretrain/Learning Rate": 4.9980604891549656e-05, "Pretrain/Loss": 2.2455220222473145, "Pretrain/Loss (Raw)": 2.3617658615112305, "Pretrain/Step": 402, "Pretrain/Step Time": 8.805362977087498} +{"Pretrain/Learning Rate": 4.998026909593865e-05, "Pretrain/Loss": 2.2488389015197754, "Pretrain/Loss (Raw)": 2.4101200103759766, "Pretrain/Step": 403, "Pretrain/Step Time": 8.801967337727547} +{"Pretrain/Learning Rate": 4.997993041948531e-05, "Pretrain/Loss": 2.2489709854125977, "Pretrain/Loss (Raw)": 2.140803098678589, "Pretrain/Step": 404, "Pretrain/Step Time": 8.804379228502512} +{"Pretrain/Learning Rate": 4.997958886222869e-05, "Pretrain/Loss": 2.2494864463806152, "Pretrain/Loss (Raw)": 2.2327394485473633, "Pretrain/Step": 405, "Pretrain/Step Time": 8.80363729223609} +{"Pretrain/Learning Rate": 4.9979244424208165e-05, "Pretrain/Loss": 2.2494125366210938, "Pretrain/Loss (Raw)": 2.256326198577881, "Pretrain/Step": 406, "Pretrain/Step Time": 8.80332144536078} +{"Pretrain/Learning Rate": 4.997889710546347e-05, "Pretrain/Loss": 2.2483584880828857, "Pretrain/Loss (Raw)": 2.1897237300872803, "Pretrain/Step": 407, "Pretrain/Step Time": 8.802053401246667} +{"Pretrain/Learning Rate": 4.9978546906034655e-05, "Pretrain/Loss": 2.249422073364258, "Pretrain/Loss (Raw)": 2.284562349319458, "Pretrain/Step": 408, "Pretrain/Step Time": 8.795066459104419} +{"Pretrain/Learning Rate": 4.997819382596212e-05, "Pretrain/Loss": 2.246631145477295, "Pretrain/Loss (Raw)": 2.1022701263427734, "Pretrain/Step": 409, "Pretrain/Step Time": 8.796544518321753} +{"Pretrain/Learning Rate": 4.997783786528656e-05, "Pretrain/Loss": 2.2485949993133545, "Pretrain/Loss (Raw)": 2.3536179065704346, "Pretrain/Step": 410, "Pretrain/Step Time": 8.786958683282137} +{"Pretrain/Learning Rate": 4.997747902404904e-05, "Pretrain/Loss": 2.246011257171631, "Pretrain/Loss (Raw)": 1.9498828649520874, "Pretrain/Step": 411, "Pretrain/Step Time": 8.792208606377244} +{"Pretrain/Learning Rate": 4.997711730229094e-05, "Pretrain/Loss": 2.2435407638549805, "Pretrain/Loss (Raw)": 1.9587111473083496, "Pretrain/Step": 412, "Pretrain/Step Time": 8.792290430516005} +{"Pretrain/Learning Rate": 4.9976752700053975e-05, "Pretrain/Loss": 2.242102861404419, "Pretrain/Loss (Raw)": 2.0324156284332275, "Pretrain/Step": 413, "Pretrain/Step Time": 8.795966984704137} +{"Pretrain/Learning Rate": 4.9976385217380195e-05, "Pretrain/Loss": 2.2398359775543213, "Pretrain/Loss (Raw)": 2.16096830368042, "Pretrain/Step": 414, "Pretrain/Step Time": 8.797794600948691} +{"Pretrain/Learning Rate": 4.997601485431198e-05, "Pretrain/Loss": 2.241509437561035, "Pretrain/Loss (Raw)": 2.540508270263672, "Pretrain/Step": 415, "Pretrain/Step Time": 8.797071581706405} +{"Pretrain/Learning Rate": 4.997564161089204e-05, "Pretrain/Loss": 2.2419486045837402, "Pretrain/Loss (Raw)": 2.2883646488189697, "Pretrain/Step": 416, "Pretrain/Step Time": 8.795157412067056} +{"Pretrain/Learning Rate": 4.9975265487163424e-05, "Pretrain/Loss": 2.2399964332580566, "Pretrain/Loss (Raw)": 2.0773019790649414, "Pretrain/Step": 417, "Pretrain/Step Time": 8.802025889977813} +{"Pretrain/Learning Rate": 4.997488648316951e-05, "Pretrain/Loss": 2.2392501831054688, "Pretrain/Loss (Raw)": 2.2809059619903564, "Pretrain/Step": 418, "Pretrain/Step Time": 8.798302754759789} +{"Pretrain/Learning Rate": 4.997450459895399e-05, "Pretrain/Loss": 2.2407379150390625, "Pretrain/Loss (Raw)": 2.3779850006103516, "Pretrain/Step": 419, "Pretrain/Step Time": 8.799981009215117} +{"Pretrain/Learning Rate": 4.997411983456092e-05, "Pretrain/Loss": 2.240939140319824, "Pretrain/Loss (Raw)": 2.225620746612549, "Pretrain/Step": 420, "Pretrain/Step Time": 8.808557152748108} +{"Pretrain/Learning Rate": 4.9973732190034674e-05, "Pretrain/Loss": 2.2409985065460205, "Pretrain/Loss (Raw)": 2.1685984134674072, "Pretrain/Step": 421, "Pretrain/Step Time": 8.806097256019711} +{"Pretrain/Learning Rate": 4.9973341665419946e-05, "Pretrain/Loss": 2.2400660514831543, "Pretrain/Loss (Raw)": 2.106299877166748, "Pretrain/Step": 422, "Pretrain/Step Time": 8.803186131641269} +{"Pretrain/Learning Rate": 4.997294826076178e-05, "Pretrain/Loss": 2.2360854148864746, "Pretrain/Loss (Raw)": 1.9142508506774902, "Pretrain/Step": 423, "Pretrain/Step Time": 8.803377717733383} +{"Pretrain/Learning Rate": 4.9972551976105545e-05, "Pretrain/Loss": 2.2360520362854004, "Pretrain/Loss (Raw)": 2.2869043350219727, "Pretrain/Step": 424, "Pretrain/Step Time": 8.79508357308805} +{"Pretrain/Learning Rate": 4.9972152811496945e-05, "Pretrain/Loss": 2.236605405807495, "Pretrain/Loss (Raw)": 2.1946768760681152, "Pretrain/Step": 425, "Pretrain/Step Time": 8.794405056163669} +{"Pretrain/Learning Rate": 4.9971750766982e-05, "Pretrain/Loss": 2.2365407943725586, "Pretrain/Loss (Raw)": 2.152906656265259, "Pretrain/Step": 426, "Pretrain/Step Time": 8.791438981890678} +{"Pretrain/Learning Rate": 4.9971345842607095e-05, "Pretrain/Loss": 2.235196113586426, "Pretrain/Loss (Raw)": 2.2494699954986572, "Pretrain/Step": 427, "Pretrain/Step Time": 8.800223011523485} +{"Pretrain/Learning Rate": 4.997093803841891e-05, "Pretrain/Loss": 2.233515739440918, "Pretrain/Loss (Raw)": 2.0937607288360596, "Pretrain/Step": 428, "Pretrain/Step Time": 8.798462357372046} +{"Pretrain/Learning Rate": 4.997052735446449e-05, "Pretrain/Loss": 2.233428716659546, "Pretrain/Loss (Raw)": 2.310302257537842, "Pretrain/Step": 429, "Pretrain/Step Time": 8.787604419514537} +{"Pretrain/Learning Rate": 4.997011379079119e-05, "Pretrain/Loss": 2.2333617210388184, "Pretrain/Loss (Raw)": 2.2099411487579346, "Pretrain/Step": 430, "Pretrain/Step Time": 8.789406875148416} +{"Pretrain/Learning Rate": 4.996969734744671e-05, "Pretrain/Loss": 2.2345542907714844, "Pretrain/Loss (Raw)": 2.229668378829956, "Pretrain/Step": 431, "Pretrain/Step Time": 8.797974899411201} +{"Pretrain/Learning Rate": 4.996927802447906e-05, "Pretrain/Loss": 2.2347536087036133, "Pretrain/Loss (Raw)": 2.200658082962036, "Pretrain/Step": 432, "Pretrain/Step Time": 8.797068065032363} +{"Pretrain/Learning Rate": 4.9968855821936613e-05, "Pretrain/Loss": 2.23538875579834, "Pretrain/Loss (Raw)": 2.260399103164673, "Pretrain/Step": 433, "Pretrain/Step Time": 8.795962983742356} +{"Pretrain/Learning Rate": 4.9968430739868056e-05, "Pretrain/Loss": 2.2349815368652344, "Pretrain/Loss (Raw)": 2.1319468021392822, "Pretrain/Step": 434, "Pretrain/Step Time": 8.798545572906733} +{"Pretrain/Learning Rate": 4.9968002778322406e-05, "Pretrain/Loss": 2.233835458755493, "Pretrain/Loss (Raw)": 2.16388201713562, "Pretrain/Step": 435, "Pretrain/Step Time": 8.797279281541705} +{"Pretrain/Learning Rate": 4.9967571937349034e-05, "Pretrain/Loss": 2.2351436614990234, "Pretrain/Loss (Raw)": 2.169691562652588, "Pretrain/Step": 436, "Pretrain/Step Time": 8.797354681417346} +{"Pretrain/Learning Rate": 4.996713821699761e-05, "Pretrain/Loss": 2.2333076000213623, "Pretrain/Loss (Raw)": 2.221784830093384, "Pretrain/Step": 437, "Pretrain/Step Time": 8.792868046090007} +{"Pretrain/Learning Rate": 4.9966701617318154e-05, "Pretrain/Loss": 2.23433780670166, "Pretrain/Loss (Raw)": 2.288762092590332, "Pretrain/Step": 438, "Pretrain/Step Time": 8.796379912644625} +{"Pretrain/Learning Rate": 4.996626213836103e-05, "Pretrain/Loss": 2.2313458919525146, "Pretrain/Loss (Raw)": 1.978263020515442, "Pretrain/Step": 439, "Pretrain/Step Time": 8.793571908026934} +{"Pretrain/Learning Rate": 4.99658197801769e-05, "Pretrain/Loss": 2.231081008911133, "Pretrain/Loss (Raw)": 2.2186801433563232, "Pretrain/Step": 440, "Pretrain/Step Time": 8.791046023368835} +{"Pretrain/Learning Rate": 4.99653745428168e-05, "Pretrain/Loss": 2.2295165061950684, "Pretrain/Loss (Raw)": 2.174586057662964, "Pretrain/Step": 441, "Pretrain/Step Time": 8.789738975465298} +{"Pretrain/Learning Rate": 4.9964926426332056e-05, "Pretrain/Loss": 2.223536968231201, "Pretrain/Loss (Raw)": 1.9990392923355103, "Pretrain/Step": 442, "Pretrain/Step Time": 8.796306286007166} +{"Pretrain/Learning Rate": 4.9964475430774364e-05, "Pretrain/Loss": 2.2252821922302246, "Pretrain/Loss (Raw)": 2.3657734394073486, "Pretrain/Step": 443, "Pretrain/Step Time": 8.795781368389726} +{"Pretrain/Learning Rate": 4.996402155619573e-05, "Pretrain/Loss": 2.2227866649627686, "Pretrain/Loss (Raw)": 1.9312727451324463, "Pretrain/Step": 444, "Pretrain/Step Time": 8.799536876380444} +{"Pretrain/Learning Rate": 4.9963564802648494e-05, "Pretrain/Loss": 2.22209095954895, "Pretrain/Loss (Raw)": 2.2689456939697266, "Pretrain/Step": 445, "Pretrain/Step Time": 8.798123389482498} +{"Pretrain/Learning Rate": 4.9963105170185334e-05, "Pretrain/Loss": 2.2205920219421387, "Pretrain/Loss (Raw)": 2.1504437923431396, "Pretrain/Step": 446, "Pretrain/Step Time": 8.795965315774083} +{"Pretrain/Learning Rate": 4.9962642658859255e-05, "Pretrain/Loss": 2.2205405235290527, "Pretrain/Loss (Raw)": 2.253293991088867, "Pretrain/Step": 447, "Pretrain/Step Time": 8.800305807963014} +{"Pretrain/Learning Rate": 4.99621772687236e-05, "Pretrain/Loss": 2.2179689407348633, "Pretrain/Loss (Raw)": 2.1212666034698486, "Pretrain/Step": 448, "Pretrain/Step Time": 8.79822683148086} +{"Pretrain/Learning Rate": 4.996170899983203e-05, "Pretrain/Loss": 2.2152209281921387, "Pretrain/Loss (Raw)": 1.9556580781936646, "Pretrain/Step": 449, "Pretrain/Step Time": 8.809354599565268} +{"Pretrain/Learning Rate": 4.9961237852238554e-05, "Pretrain/Loss": 2.2143146991729736, "Pretrain/Loss (Raw)": 2.1311309337615967, "Pretrain/Step": 450, "Pretrain/Step Time": 8.8040432613343} +{"Pretrain/Learning Rate": 4.996076382599752e-05, "Pretrain/Loss": 2.2127089500427246, "Pretrain/Loss (Raw)": 2.0348470211029053, "Pretrain/Step": 451, "Pretrain/Step Time": 8.8068024571985} +{"Pretrain/Learning Rate": 4.996028692116357e-05, "Pretrain/Loss": 2.212352752685547, "Pretrain/Loss (Raw)": 2.184804916381836, "Pretrain/Step": 452, "Pretrain/Step Time": 8.811653412878513} +{"Pretrain/Learning Rate": 4.995980713779172e-05, "Pretrain/Loss": 2.2095513343811035, "Pretrain/Loss (Raw)": 2.0452358722686768, "Pretrain/Step": 453, "Pretrain/Step Time": 8.812649877741933} +{"Pretrain/Learning Rate": 4.9959324475937297e-05, "Pretrain/Loss": 2.2097058296203613, "Pretrain/Loss (Raw)": 2.2379581928253174, "Pretrain/Step": 454, "Pretrain/Step Time": 8.809170961380005} +{"Pretrain/Learning Rate": 4.995883893565596e-05, "Pretrain/Loss": 2.2077579498291016, "Pretrain/Loss (Raw)": 2.106271743774414, "Pretrain/Step": 455, "Pretrain/Step Time": 8.808426665142179} +{"Pretrain/Learning Rate": 4.995835051700371e-05, "Pretrain/Loss": 2.2064738273620605, "Pretrain/Loss (Raw)": 2.035034656524658, "Pretrain/Step": 456, "Pretrain/Step Time": 8.802834164351225} +{"Pretrain/Learning Rate": 4.995785922003687e-05, "Pretrain/Loss": 2.2055981159210205, "Pretrain/Loss (Raw)": 2.1508800983428955, "Pretrain/Step": 457, "Pretrain/Step Time": 8.807403119280934} +{"Pretrain/Learning Rate": 4.9957365044812097e-05, "Pretrain/Loss": 2.205904006958008, "Pretrain/Loss (Raw)": 2.198937177658081, "Pretrain/Step": 458, "Pretrain/Step Time": 8.802964953705668} +{"Pretrain/Learning Rate": 4.995686799138639e-05, "Pretrain/Loss": 2.204160690307617, "Pretrain/Loss (Raw)": 2.0647895336151123, "Pretrain/Step": 459, "Pretrain/Step Time": 8.797583218663931} +{"Pretrain/Learning Rate": 4.995636805981706e-05, "Pretrain/Loss": 2.2040133476257324, "Pretrain/Loss (Raw)": 2.1704747676849365, "Pretrain/Step": 460, "Pretrain/Step Time": 8.799054956063628} +{"Pretrain/Learning Rate": 4.9955865250161774e-05, "Pretrain/Loss": 2.2029404640197754, "Pretrain/Loss (Raw)": 2.1482455730438232, "Pretrain/Step": 461, "Pretrain/Step Time": 8.796240076422691} +{"Pretrain/Learning Rate": 4.9955359562478504e-05, "Pretrain/Loss": 2.201618194580078, "Pretrain/Loss (Raw)": 2.0739693641662598, "Pretrain/Step": 462, "Pretrain/Step Time": 8.798159696161747} +{"Pretrain/Learning Rate": 4.995485099682558e-05, "Pretrain/Loss": 2.201753854751587, "Pretrain/Loss (Raw)": 2.2935726642608643, "Pretrain/Step": 463, "Pretrain/Step Time": 8.800805812701583} +{"Pretrain/Learning Rate": 4.995433955326165e-05, "Pretrain/Loss": 2.202747106552124, "Pretrain/Loss (Raw)": 2.2297520637512207, "Pretrain/Step": 464, "Pretrain/Step Time": 8.791052674874663} +{"Pretrain/Learning Rate": 4.995382523184569e-05, "Pretrain/Loss": 2.202601671218872, "Pretrain/Loss (Raw)": 2.196868658065796, "Pretrain/Step": 465, "Pretrain/Step Time": 8.796078039333224} +{"Pretrain/Learning Rate": 4.9953308032637016e-05, "Pretrain/Loss": 2.2005727291107178, "Pretrain/Loss (Raw)": 2.015688180923462, "Pretrain/Step": 466, "Pretrain/Step Time": 8.799205360934138} +{"Pretrain/Learning Rate": 4.995278795569528e-05, "Pretrain/Loss": 2.203583002090454, "Pretrain/Loss (Raw)": 2.5945239067077637, "Pretrain/Step": 467, "Pretrain/Step Time": 8.791134770959616} +{"Pretrain/Learning Rate": 4.995226500108046e-05, "Pretrain/Loss": 2.205197334289551, "Pretrain/Loss (Raw)": 2.2275290489196777, "Pretrain/Step": 468, "Pretrain/Step Time": 8.791334809735417} +{"Pretrain/Learning Rate": 4.995173916885285e-05, "Pretrain/Loss": 2.2090415954589844, "Pretrain/Loss (Raw)": 2.5519320964813232, "Pretrain/Step": 469, "Pretrain/Step Time": 8.790389005094767} +{"Pretrain/Learning Rate": 4.9951210459073105e-05, "Pretrain/Loss": 2.206007957458496, "Pretrain/Loss (Raw)": 2.1626064777374268, "Pretrain/Step": 470, "Pretrain/Step Time": 8.792248766869307} +{"Pretrain/Learning Rate": 4.99506788718022e-05, "Pretrain/Loss": 2.2069954872131348, "Pretrain/Loss (Raw)": 2.285341501235962, "Pretrain/Step": 471, "Pretrain/Step Time": 8.791242944076657} +{"Pretrain/Learning Rate": 4.995014440710144e-05, "Pretrain/Loss": 2.207396984100342, "Pretrain/Loss (Raw)": 2.3056962490081787, "Pretrain/Step": 472, "Pretrain/Step Time": 8.79371970333159} +{"Pretrain/Learning Rate": 4.9949607065032445e-05, "Pretrain/Loss": 2.207246780395508, "Pretrain/Loss (Raw)": 2.249757766723633, "Pretrain/Step": 473, "Pretrain/Step Time": 8.792051337659359} +{"Pretrain/Learning Rate": 4.99490668456572e-05, "Pretrain/Loss": 2.2075119018554688, "Pretrain/Loss (Raw)": 2.287426233291626, "Pretrain/Step": 474, "Pretrain/Step Time": 8.793815029785037} +{"Pretrain/Learning Rate": 4.994852374903801e-05, "Pretrain/Loss": 2.2073333263397217, "Pretrain/Loss (Raw)": 2.320557117462158, "Pretrain/Step": 475, "Pretrain/Step Time": 8.794844347983599} +{"Pretrain/Learning Rate": 4.99479777752375e-05, "Pretrain/Loss": 2.2076010704040527, "Pretrain/Loss (Raw)": 2.2738184928894043, "Pretrain/Step": 476, "Pretrain/Step Time": 8.796668142080307} +{"Pretrain/Learning Rate": 4.994742892431863e-05, "Pretrain/Loss": 2.206906795501709, "Pretrain/Loss (Raw)": 2.0652763843536377, "Pretrain/Step": 477, "Pretrain/Step Time": 8.79936296492815} +{"Pretrain/Learning Rate": 4.99468771963447e-05, "Pretrain/Loss": 2.205571174621582, "Pretrain/Loss (Raw)": 2.14978289604187, "Pretrain/Step": 478, "Pretrain/Step Time": 8.795937338843942} +{"Pretrain/Learning Rate": 4.994632259137935e-05, "Pretrain/Loss": 2.204983711242676, "Pretrain/Loss (Raw)": 2.150942087173462, "Pretrain/Step": 479, "Pretrain/Step Time": 8.800676578655839} +{"Pretrain/Learning Rate": 4.9945765109486506e-05, "Pretrain/Loss": 2.2025060653686523, "Pretrain/Loss (Raw)": 2.1846418380737305, "Pretrain/Step": 480, "Pretrain/Step Time": 8.798872841522098} +{"Pretrain/Learning Rate": 4.99452047507305e-05, "Pretrain/Loss": 2.204023838043213, "Pretrain/Loss (Raw)": 2.202483892440796, "Pretrain/Step": 481, "Pretrain/Step Time": 8.799386952072382} +{"Pretrain/Learning Rate": 4.994464151517593e-05, "Pretrain/Loss": 2.203519821166992, "Pretrain/Loss (Raw)": 2.237917900085449, "Pretrain/Step": 482, "Pretrain/Step Time": 8.80020533874631} +{"Pretrain/Learning Rate": 4.994407540288775e-05, "Pretrain/Loss": 2.2028610706329346, "Pretrain/Loss (Raw)": 2.1610829830169678, "Pretrain/Step": 483, "Pretrain/Step Time": 8.800120091065764} +{"Pretrain/Learning Rate": 4.994350641393126e-05, "Pretrain/Loss": 2.2041962146759033, "Pretrain/Loss (Raw)": 2.287853956222534, "Pretrain/Step": 484, "Pretrain/Step Time": 8.808589985594153} +{"Pretrain/Learning Rate": 4.9942934548372077e-05, "Pretrain/Loss": 2.2051587104797363, "Pretrain/Loss (Raw)": 2.2167303562164307, "Pretrain/Step": 485, "Pretrain/Step Time": 8.804581759497523} +{"Pretrain/Learning Rate": 4.994235980627614e-05, "Pretrain/Loss": 2.2066049575805664, "Pretrain/Loss (Raw)": 2.4258055686950684, "Pretrain/Step": 486, "Pretrain/Step Time": 8.798167796805501} +{"Pretrain/Learning Rate": 4.9941782187709746e-05, "Pretrain/Loss": 2.2053494453430176, "Pretrain/Loss (Raw)": 2.1396217346191406, "Pretrain/Step": 487, "Pretrain/Step Time": 8.793069537729025} +{"Pretrain/Learning Rate": 4.994120169273949e-05, "Pretrain/Loss": 2.2039260864257812, "Pretrain/Loss (Raw)": 2.130624771118164, "Pretrain/Step": 488, "Pretrain/Step Time": 8.7965665217489} +{"Pretrain/Learning Rate": 4.9940618321432344e-05, "Pretrain/Loss": 2.2044615745544434, "Pretrain/Loss (Raw)": 2.272400140762329, "Pretrain/Step": 489, "Pretrain/Step Time": 8.79357922077179} +{"Pretrain/Learning Rate": 4.994003207385556e-05, "Pretrain/Loss": 2.2039215564727783, "Pretrain/Loss (Raw)": 2.065981149673462, "Pretrain/Step": 490, "Pretrain/Step Time": 8.787966320291162} +{"Pretrain/Learning Rate": 4.9939442950076755e-05, "Pretrain/Loss": 2.2031662464141846, "Pretrain/Loss (Raw)": 2.0714941024780273, "Pretrain/Step": 491, "Pretrain/Step Time": 8.783155461773276} +{"Pretrain/Learning Rate": 4.9938850950163864e-05, "Pretrain/Loss": 2.200261116027832, "Pretrain/Loss (Raw)": 1.9183181524276733, "Pretrain/Step": 492, "Pretrain/Step Time": 8.804274810478091} +{"Pretrain/Learning Rate": 4.9938256074185174e-05, "Pretrain/Loss": 2.196432113647461, "Pretrain/Loss (Raw)": 1.9596893787384033, "Pretrain/Step": 493, "Pretrain/Step Time": 8.803486688062549} +{"Pretrain/Learning Rate": 4.993765832220928e-05, "Pretrain/Loss": 2.1963229179382324, "Pretrain/Loss (Raw)": 2.1004467010498047, "Pretrain/Step": 494, "Pretrain/Step Time": 8.803974211215973} +{"Pretrain/Learning Rate": 4.993705769430511e-05, "Pretrain/Loss": 2.1961467266082764, "Pretrain/Loss (Raw)": 2.295034408569336, "Pretrain/Step": 495, "Pretrain/Step Time": 8.799203474074602} +{"Pretrain/Learning Rate": 4.9936454190541945e-05, "Pretrain/Loss": 2.1958508491516113, "Pretrain/Loss (Raw)": 2.1932668685913086, "Pretrain/Step": 496, "Pretrain/Step Time": 8.799760863184929} +{"Pretrain/Learning Rate": 4.993584781098939e-05, "Pretrain/Loss": 2.1939802169799805, "Pretrain/Loss (Raw)": 2.0641732215881348, "Pretrain/Step": 497, "Pretrain/Step Time": 8.799821516498923} +{"Pretrain/Learning Rate": 4.993523855571735e-05, "Pretrain/Loss": 2.196849822998047, "Pretrain/Loss (Raw)": 2.4760544300079346, "Pretrain/Step": 498, "Pretrain/Step Time": 8.80418524518609} +{"Pretrain/Learning Rate": 4.99346264247961e-05, "Pretrain/Loss": 2.1986751556396484, "Pretrain/Loss (Raw)": 2.337064027786255, "Pretrain/Step": 499, "Pretrain/Step Time": 8.796117717400193} +{"Pretrain/Learning Rate": 4.993401141829625e-05, "Pretrain/Loss": 2.196856737136841, "Pretrain/Loss (Raw)": 2.125624895095825, "Pretrain/Step": 500, "Pretrain/Step Time": 8.800143156200647} +{"Pretrain/Learning Rate": 4.99333935362887e-05, "Pretrain/Loss": 2.1973586082458496, "Pretrain/Loss (Raw)": 2.225551128387451, "Pretrain/Step": 501, "Pretrain/Step Time": 8.793885869905353} +{"Pretrain/Learning Rate": 4.993277277884471e-05, "Pretrain/Loss": 2.1975345611572266, "Pretrain/Loss (Raw)": 2.1849448680877686, "Pretrain/Step": 502, "Pretrain/Step Time": 8.795156959444284} +{"Pretrain/Learning Rate": 4.993214914603588e-05, "Pretrain/Loss": 2.197493076324463, "Pretrain/Loss (Raw)": 2.2445380687713623, "Pretrain/Step": 503, "Pretrain/Step Time": 8.792704632505774} +{"Pretrain/Learning Rate": 4.993152263793414e-05, "Pretrain/Loss": 2.196485996246338, "Pretrain/Loss (Raw)": 2.189075231552124, "Pretrain/Step": 504, "Pretrain/Step Time": 8.791447687894106} +{"Pretrain/Learning Rate": 4.993089325461171e-05, "Pretrain/Loss": 2.196234703063965, "Pretrain/Loss (Raw)": 2.1834609508514404, "Pretrain/Step": 505, "Pretrain/Step Time": 8.8009413164109} +{"Pretrain/Learning Rate": 4.99302609961412e-05, "Pretrain/Loss": 2.1963272094726562, "Pretrain/Loss (Raw)": 2.2208499908447266, "Pretrain/Step": 506, "Pretrain/Step Time": 8.796708069741726} +{"Pretrain/Learning Rate": 4.9929625862595516e-05, "Pretrain/Loss": 2.1955533027648926, "Pretrain/Loss (Raw)": 2.005441188812256, "Pretrain/Step": 507, "Pretrain/Step Time": 8.801740545779467} +{"Pretrain/Learning Rate": 4.9928987854047905e-05, "Pretrain/Loss": 2.194923162460327, "Pretrain/Loss (Raw)": 2.2944250106811523, "Pretrain/Step": 508, "Pretrain/Step Time": 8.80454975552857} +{"Pretrain/Learning Rate": 4.992834697057195e-05, "Pretrain/Loss": 2.195348024368286, "Pretrain/Loss (Raw)": 2.2063448429107666, "Pretrain/Step": 509, "Pretrain/Step Time": 8.793810687959194} +{"Pretrain/Learning Rate": 4.992770321224155e-05, "Pretrain/Loss": 2.1973705291748047, "Pretrain/Loss (Raw)": 2.350857734680176, "Pretrain/Step": 510, "Pretrain/Step Time": 8.796160496771336} +{"Pretrain/Learning Rate": 4.992705657913095e-05, "Pretrain/Loss": 2.1980199813842773, "Pretrain/Loss (Raw)": 2.269699811935425, "Pretrain/Step": 511, "Pretrain/Step Time": 8.79777749069035} +{"Pretrain/Learning Rate": 4.9926407071314736e-05, "Pretrain/Loss": 2.1984548568725586, "Pretrain/Loss (Raw)": 2.1557822227478027, "Pretrain/Step": 512, "Pretrain/Step Time": 8.800725392997265} +{"Pretrain/Learning Rate": 4.9925754688867796e-05, "Pretrain/Loss": 2.196664810180664, "Pretrain/Loss (Raw)": 1.9666423797607422, "Pretrain/Step": 513, "Pretrain/Step Time": 8.799366539344192} +{"Pretrain/Learning Rate": 4.992509943186537e-05, "Pretrain/Loss": 2.19899845123291, "Pretrain/Loss (Raw)": 2.433065891265869, "Pretrain/Step": 514, "Pretrain/Step Time": 8.805364461615682} +{"Pretrain/Learning Rate": 4.992444130038302e-05, "Pretrain/Loss": 2.1975479125976562, "Pretrain/Loss (Raw)": 2.177485227584839, "Pretrain/Step": 515, "Pretrain/Step Time": 8.802185911685228} +{"Pretrain/Learning Rate": 4.992378029449666e-05, "Pretrain/Loss": 2.1991357803344727, "Pretrain/Loss (Raw)": 2.4161252975463867, "Pretrain/Step": 516, "Pretrain/Step Time": 8.792381383478642} +{"Pretrain/Learning Rate": 4.9923116414282514e-05, "Pretrain/Loss": 2.1966075897216797, "Pretrain/Loss (Raw)": 2.069991111755371, "Pretrain/Step": 517, "Pretrain/Step Time": 8.790618984028697} +{"Pretrain/Learning Rate": 4.992244965981714e-05, "Pretrain/Loss": 2.1955456733703613, "Pretrain/Loss (Raw)": 2.1676058769226074, "Pretrain/Step": 518, "Pretrain/Step Time": 8.788304569199681} +{"Pretrain/Learning Rate": 4.9921780031177425e-05, "Pretrain/Loss": 2.1957147121429443, "Pretrain/Loss (Raw)": 2.2074508666992188, "Pretrain/Step": 519, "Pretrain/Step Time": 8.788094099611044} +{"Pretrain/Learning Rate": 4.992110752844061e-05, "Pretrain/Loss": 2.1962087154388428, "Pretrain/Loss (Raw)": 2.211451530456543, "Pretrain/Step": 520, "Pretrain/Step Time": 8.794851519167423} +{"Pretrain/Learning Rate": 4.992043215168424e-05, "Pretrain/Loss": 2.1934566497802734, "Pretrain/Loss (Raw)": 1.9685040712356567, "Pretrain/Step": 521, "Pretrain/Step Time": 8.787156101316214} +{"Pretrain/Learning Rate": 4.99197539009862e-05, "Pretrain/Loss": 2.193643093109131, "Pretrain/Loss (Raw)": 2.1319451332092285, "Pretrain/Step": 522, "Pretrain/Step Time": 8.791520856320858} +{"Pretrain/Learning Rate": 4.9919072776424726e-05, "Pretrain/Loss": 2.194453239440918, "Pretrain/Loss (Raw)": 2.2676429748535156, "Pretrain/Step": 523, "Pretrain/Step Time": 8.794873367995024} +{"Pretrain/Learning Rate": 4.9918388778078347e-05, "Pretrain/Loss": 2.1926698684692383, "Pretrain/Loss (Raw)": 2.149930238723755, "Pretrain/Step": 524, "Pretrain/Step Time": 8.79560725018382} +{"Pretrain/Learning Rate": 4.991770190602596e-05, "Pretrain/Loss": 2.1924729347229004, "Pretrain/Loss (Raw)": 2.2387654781341553, "Pretrain/Step": 525, "Pretrain/Step Time": 8.795418463647366} +{"Pretrain/Learning Rate": 4.991701216034677e-05, "Pretrain/Loss": 2.1934502124786377, "Pretrain/Loss (Raw)": 2.2455155849456787, "Pretrain/Step": 526, "Pretrain/Step Time": 8.797831863164902} +{"Pretrain/Learning Rate": 4.9916319541120324e-05, "Pretrain/Loss": 2.193206787109375, "Pretrain/Loss (Raw)": 2.2753374576568604, "Pretrain/Step": 527, "Pretrain/Step Time": 8.799308769404888} +{"Pretrain/Learning Rate": 4.99156240484265e-05, "Pretrain/Loss": 2.1936402320861816, "Pretrain/Loss (Raw)": 2.2179105281829834, "Pretrain/Step": 528, "Pretrain/Step Time": 8.798470739275217} +{"Pretrain/Learning Rate": 4.9914925682345504e-05, "Pretrain/Loss": 2.1938109397888184, "Pretrain/Loss (Raw)": 2.325798511505127, "Pretrain/Step": 529, "Pretrain/Step Time": 8.796696728095412} +{"Pretrain/Learning Rate": 4.991422444295788e-05, "Pretrain/Loss": 2.192967653274536, "Pretrain/Loss (Raw)": 2.253786325454712, "Pretrain/Step": 530, "Pretrain/Step Time": 8.795344293117523} +{"Pretrain/Learning Rate": 4.9913520330344486e-05, "Pretrain/Loss": 2.19157338142395, "Pretrain/Loss (Raw)": 2.231672525405884, "Pretrain/Step": 531, "Pretrain/Step Time": 8.795942047610879} +{"Pretrain/Learning Rate": 4.991281334458654e-05, "Pretrain/Loss": 2.191272497177124, "Pretrain/Loss (Raw)": 2.1022799015045166, "Pretrain/Step": 532, "Pretrain/Step Time": 8.788372935727239} +{"Pretrain/Learning Rate": 4.991210348576556e-05, "Pretrain/Loss": 2.1900172233581543, "Pretrain/Loss (Raw)": 2.0720560550689697, "Pretrain/Step": 533, "Pretrain/Step Time": 8.792434874922037} +{"Pretrain/Learning Rate": 4.991139075396342e-05, "Pretrain/Loss": 2.188584804534912, "Pretrain/Loss (Raw)": 2.072988748550415, "Pretrain/Step": 534, "Pretrain/Step Time": 8.786465952172875} +{"Pretrain/Learning Rate": 4.991067514926231e-05, "Pretrain/Loss": 2.1886627674102783, "Pretrain/Loss (Raw)": 2.1997077465057373, "Pretrain/Step": 535, "Pretrain/Step Time": 8.788955621421337} +{"Pretrain/Learning Rate": 4.990995667174476e-05, "Pretrain/Loss": 2.18789005279541, "Pretrain/Loss (Raw)": 2.1856632232666016, "Pretrain/Step": 536, "Pretrain/Step Time": 8.790034666657448} +{"Pretrain/Learning Rate": 4.990923532149362e-05, "Pretrain/Loss": 2.188037395477295, "Pretrain/Loss (Raw)": 2.1211228370666504, "Pretrain/Step": 537, "Pretrain/Step Time": 8.790417704731226} +{"Pretrain/Learning Rate": 4.990851109859209e-05, "Pretrain/Loss": 2.1874632835388184, "Pretrain/Loss (Raw)": 2.2801079750061035, "Pretrain/Step": 538, "Pretrain/Step Time": 8.791537737473845} +{"Pretrain/Learning Rate": 4.9907784003123695e-05, "Pretrain/Loss": 2.189943790435791, "Pretrain/Loss (Raw)": 2.267427682876587, "Pretrain/Step": 539, "Pretrain/Step Time": 8.786252930760384} +{"Pretrain/Learning Rate": 4.9907054035172273e-05, "Pretrain/Loss": 2.1921777725219727, "Pretrain/Loss (Raw)": 2.244662284851074, "Pretrain/Step": 540, "Pretrain/Step Time": 8.782096741721034} +{"Pretrain/Learning Rate": 4.9906321194822014e-05, "Pretrain/Loss": 2.1935036182403564, "Pretrain/Loss (Raw)": 2.2020909786224365, "Pretrain/Step": 541, "Pretrain/Step Time": 8.791154170408845} +{"Pretrain/Learning Rate": 4.9905585482157436e-05, "Pretrain/Loss": 2.191640615463257, "Pretrain/Loss (Raw)": 1.9225159883499146, "Pretrain/Step": 542, "Pretrain/Step Time": 8.781796488910913} +{"Pretrain/Learning Rate": 4.990484689726338e-05, "Pretrain/Loss": 2.1901018619537354, "Pretrain/Loss (Raw)": 2.3435564041137695, "Pretrain/Step": 543, "Pretrain/Step Time": 8.788640707731247} +{"Pretrain/Learning Rate": 4.990410544022502e-05, "Pretrain/Loss": 2.1891889572143555, "Pretrain/Loss (Raw)": 2.1715142726898193, "Pretrain/Step": 544, "Pretrain/Step Time": 8.793101090937853} +{"Pretrain/Learning Rate": 4.9903361111127864e-05, "Pretrain/Loss": 2.190030097961426, "Pretrain/Loss (Raw)": 2.1849822998046875, "Pretrain/Step": 545, "Pretrain/Step Time": 8.784779895097017} +{"Pretrain/Learning Rate": 4.990261391005777e-05, "Pretrain/Loss": 2.190018653869629, "Pretrain/Loss (Raw)": 2.2794036865234375, "Pretrain/Step": 546, "Pretrain/Step Time": 8.782432470470667} +{"Pretrain/Learning Rate": 4.9901863837100886e-05, "Pretrain/Loss": 2.1874747276306152, "Pretrain/Loss (Raw)": 2.0523645877838135, "Pretrain/Step": 547, "Pretrain/Step Time": 8.782339381054044} +{"Pretrain/Learning Rate": 4.9901110892343724e-05, "Pretrain/Loss": 2.187946081161499, "Pretrain/Loss (Raw)": 2.2859561443328857, "Pretrain/Step": 548, "Pretrain/Step Time": 8.786727456375957} +{"Pretrain/Learning Rate": 4.9900355075873116e-05, "Pretrain/Loss": 2.1883859634399414, "Pretrain/Loss (Raw)": 2.224879503250122, "Pretrain/Step": 549, "Pretrain/Step Time": 8.78379999473691} +{"Pretrain/Learning Rate": 4.989959638777623e-05, "Pretrain/Loss": 2.18821120262146, "Pretrain/Loss (Raw)": 2.0839765071868896, "Pretrain/Step": 550, "Pretrain/Step Time": 8.781400375068188} +{"Pretrain/Learning Rate": 4.989883482814056e-05, "Pretrain/Loss": 2.190113067626953, "Pretrain/Loss (Raw)": 2.1576831340789795, "Pretrain/Step": 551, "Pretrain/Step Time": 8.786602614447474} +{"Pretrain/Learning Rate": 4.989807039705392e-05, "Pretrain/Loss": 2.1893930435180664, "Pretrain/Loss (Raw)": 2.194715976715088, "Pretrain/Step": 552, "Pretrain/Step Time": 8.788873573765159} +{"Pretrain/Learning Rate": 4.989730309460449e-05, "Pretrain/Loss": 2.1888182163238525, "Pretrain/Loss (Raw)": 2.1211061477661133, "Pretrain/Step": 553, "Pretrain/Step Time": 8.791233437135816} +{"Pretrain/Learning Rate": 4.989653292088074e-05, "Pretrain/Loss": 2.1898698806762695, "Pretrain/Loss (Raw)": 2.2875404357910156, "Pretrain/Step": 554, "Pretrain/Step Time": 8.790784697979689} +{"Pretrain/Learning Rate": 4.9895759875971495e-05, "Pretrain/Loss": 2.1901144981384277, "Pretrain/Loss (Raw)": 2.2807846069335938, "Pretrain/Step": 555, "Pretrain/Step Time": 8.791417378932238} +{"Pretrain/Learning Rate": 4.9894983959965915e-05, "Pretrain/Loss": 2.192030429840088, "Pretrain/Loss (Raw)": 2.338980197906494, "Pretrain/Step": 556, "Pretrain/Step Time": 8.792172385379672} +{"Pretrain/Learning Rate": 4.989420517295347e-05, "Pretrain/Loss": 2.190920352935791, "Pretrain/Loss (Raw)": 2.168200731277466, "Pretrain/Step": 557, "Pretrain/Step Time": 8.79216237179935} +{"Pretrain/Learning Rate": 4.9893423515023986e-05, "Pretrain/Loss": 2.191342830657959, "Pretrain/Loss (Raw)": 2.2640271186828613, "Pretrain/Step": 558, "Pretrain/Step Time": 8.794170776382089} +{"Pretrain/Learning Rate": 4.9892638986267594e-05, "Pretrain/Loss": 2.189295768737793, "Pretrain/Loss (Raw)": 1.9676421880722046, "Pretrain/Step": 559, "Pretrain/Step Time": 8.78404899686575} +{"Pretrain/Learning Rate": 4.989185158677478e-05, "Pretrain/Loss": 2.188988208770752, "Pretrain/Loss (Raw)": 2.161318063735962, "Pretrain/Step": 560, "Pretrain/Step Time": 8.783705417066813} +{"Pretrain/Learning Rate": 4.9891061316636346e-05, "Pretrain/Loss": 2.188807964324951, "Pretrain/Loss (Raw)": 2.2373206615448, "Pretrain/Step": 561, "Pretrain/Step Time": 8.787581650540233} +{"Pretrain/Learning Rate": 4.9890268175943425e-05, "Pretrain/Loss": 2.188955307006836, "Pretrain/Loss (Raw)": 2.1507794857025146, "Pretrain/Step": 562, "Pretrain/Step Time": 8.783748347312212} +{"Pretrain/Learning Rate": 4.9889472164787496e-05, "Pretrain/Loss": 2.188498020172119, "Pretrain/Loss (Raw)": 2.1053617000579834, "Pretrain/Step": 563, "Pretrain/Step Time": 8.792236967012286} +{"Pretrain/Learning Rate": 4.9888673283260355e-05, "Pretrain/Loss": 2.1889970302581787, "Pretrain/Loss (Raw)": 2.2335617542266846, "Pretrain/Step": 564, "Pretrain/Step Time": 8.793881505727768} +{"Pretrain/Learning Rate": 4.9887871531454134e-05, "Pretrain/Loss": 2.1888070106506348, "Pretrain/Loss (Raw)": 2.1974756717681885, "Pretrain/Step": 565, "Pretrain/Step Time": 8.79623687081039} +{"Pretrain/Learning Rate": 4.988706690946129e-05, "Pretrain/Loss": 2.187563419342041, "Pretrain/Loss (Raw)": 2.1295831203460693, "Pretrain/Step": 566, "Pretrain/Step Time": 8.792894722893834} +{"Pretrain/Learning Rate": 4.9886259417374616e-05, "Pretrain/Loss": 2.189640998840332, "Pretrain/Loss (Raw)": 2.244205951690674, "Pretrain/Step": 567, "Pretrain/Step Time": 8.792652813717723} +{"Pretrain/Learning Rate": 4.988544905528724e-05, "Pretrain/Loss": 2.1887950897216797, "Pretrain/Loss (Raw)": 2.1103737354278564, "Pretrain/Step": 568, "Pretrain/Step Time": 8.793370317667723} +{"Pretrain/Learning Rate": 4.9884635823292615e-05, "Pretrain/Loss": 2.190016746520996, "Pretrain/Loss (Raw)": 2.33099102973938, "Pretrain/Step": 569, "Pretrain/Step Time": 8.796565955504775} +{"Pretrain/Learning Rate": 4.988381972148452e-05, "Pretrain/Loss": 2.1915464401245117, "Pretrain/Loss (Raw)": 2.194807529449463, "Pretrain/Step": 570, "Pretrain/Step Time": 8.797772528603673} +{"Pretrain/Learning Rate": 4.9883000749957086e-05, "Pretrain/Loss": 2.1909141540527344, "Pretrain/Loss (Raw)": 2.2848775386810303, "Pretrain/Step": 571, "Pretrain/Step Time": 8.795385079458356} +{"Pretrain/Learning Rate": 4.988217890880475e-05, "Pretrain/Loss": 2.1936984062194824, "Pretrain/Loss (Raw)": 2.2876152992248535, "Pretrain/Step": 572, "Pretrain/Step Time": 8.795900400727987} +{"Pretrain/Learning Rate": 4.98813541981223e-05, "Pretrain/Loss": 2.1912503242492676, "Pretrain/Loss (Raw)": 1.9556139707565308, "Pretrain/Step": 573, "Pretrain/Step Time": 8.805471235886216} +{"Pretrain/Learning Rate": 4.988052661800483e-05, "Pretrain/Loss": 2.1913530826568604, "Pretrain/Loss (Raw)": 2.163600206375122, "Pretrain/Step": 574, "Pretrain/Step Time": 8.80262840911746} +{"Pretrain/Learning Rate": 4.98796961685478e-05, "Pretrain/Loss": 2.1914219856262207, "Pretrain/Loss (Raw)": 2.2620902061462402, "Pretrain/Step": 575, "Pretrain/Step Time": 8.799106441438198} +{"Pretrain/Learning Rate": 4.987886284984695e-05, "Pretrain/Loss": 2.1923232078552246, "Pretrain/Loss (Raw)": 2.2366409301757812, "Pretrain/Step": 576, "Pretrain/Step Time": 8.79844000004232} +{"Pretrain/Learning Rate": 4.987802666199842e-05, "Pretrain/Loss": 2.1936683654785156, "Pretrain/Loss (Raw)": 2.1278486251831055, "Pretrain/Step": 577, "Pretrain/Step Time": 8.80073694512248} +{"Pretrain/Learning Rate": 4.987718760509863e-05, "Pretrain/Loss": 2.1942076683044434, "Pretrain/Loss (Raw)": 2.200166940689087, "Pretrain/Step": 578, "Pretrain/Step Time": 8.79888734780252} +{"Pretrain/Learning Rate": 4.987634567924433e-05, "Pretrain/Loss": 2.1955454349517822, "Pretrain/Loss (Raw)": 2.2060658931732178, "Pretrain/Step": 579, "Pretrain/Step Time": 8.796820567920804} +{"Pretrain/Learning Rate": 4.9875500884532634e-05, "Pretrain/Loss": 2.195075511932373, "Pretrain/Loss (Raw)": 2.1246581077575684, "Pretrain/Step": 580, "Pretrain/Step Time": 8.790091682225466} +{"Pretrain/Learning Rate": 4.987465322106095e-05, "Pretrain/Loss": 2.195887565612793, "Pretrain/Loss (Raw)": 2.149170398712158, "Pretrain/Step": 581, "Pretrain/Step Time": 8.790162093937397} +{"Pretrain/Learning Rate": 4.987380268892705e-05, "Pretrain/Loss": 2.195772647857666, "Pretrain/Loss (Raw)": 2.2232565879821777, "Pretrain/Step": 582, "Pretrain/Step Time": 8.788365822285414} +{"Pretrain/Learning Rate": 4.987294928822901e-05, "Pretrain/Loss": 2.1972131729125977, "Pretrain/Loss (Raw)": 2.2906405925750732, "Pretrain/Step": 583, "Pretrain/Step Time": 8.789345055818558} +{"Pretrain/Learning Rate": 4.9872093019065255e-05, "Pretrain/Loss": 2.197923183441162, "Pretrain/Loss (Raw)": 2.1259267330169678, "Pretrain/Step": 584, "Pretrain/Step Time": 8.795226901769638} +{"Pretrain/Learning Rate": 4.987123388153453e-05, "Pretrain/Loss": 2.1972978115081787, "Pretrain/Loss (Raw)": 2.0708391666412354, "Pretrain/Step": 585, "Pretrain/Step Time": 8.794186968356371} +{"Pretrain/Learning Rate": 4.9870371875735916e-05, "Pretrain/Loss": 2.197551727294922, "Pretrain/Loss (Raw)": 2.2314341068267822, "Pretrain/Step": 586, "Pretrain/Step Time": 8.79601314663887} +{"Pretrain/Learning Rate": 4.986950700176882e-05, "Pretrain/Loss": 2.1965579986572266, "Pretrain/Loss (Raw)": 1.9375991821289062, "Pretrain/Step": 587, "Pretrain/Step Time": 8.803497519344091} +{"Pretrain/Learning Rate": 4.9868639259732996e-05, "Pretrain/Loss": 2.1969714164733887, "Pretrain/Loss (Raw)": 2.2233846187591553, "Pretrain/Step": 588, "Pretrain/Step Time": 8.796703455969691} +{"Pretrain/Learning Rate": 4.986776864972851e-05, "Pretrain/Loss": 2.196065902709961, "Pretrain/Loss (Raw)": 2.0323386192321777, "Pretrain/Step": 589, "Pretrain/Step Time": 8.796917552128434} +{"Pretrain/Learning Rate": 4.9866895171855756e-05, "Pretrain/Loss": 2.197747230529785, "Pretrain/Loss (Raw)": 2.289156436920166, "Pretrain/Step": 590, "Pretrain/Step Time": 8.802741693332791} +{"Pretrain/Learning Rate": 4.9866018826215475e-05, "Pretrain/Loss": 2.195801258087158, "Pretrain/Loss (Raw)": 2.0445337295532227, "Pretrain/Step": 591, "Pretrain/Step Time": 8.798673069104552} +{"Pretrain/Learning Rate": 4.9865139612908736e-05, "Pretrain/Loss": 2.1956138610839844, "Pretrain/Loss (Raw)": 2.2057297229766846, "Pretrain/Step": 592, "Pretrain/Step Time": 8.800828412175179} +{"Pretrain/Learning Rate": 4.9864257532036924e-05, "Pretrain/Loss": 2.1950602531433105, "Pretrain/Loss (Raw)": 2.1260178089141846, "Pretrain/Step": 593, "Pretrain/Step Time": 8.797411860898137} +{"Pretrain/Learning Rate": 4.9863372583701765e-05, "Pretrain/Loss": 2.1965713500976562, "Pretrain/Loss (Raw)": 2.209125280380249, "Pretrain/Step": 594, "Pretrain/Step Time": 8.79845161177218} +{"Pretrain/Learning Rate": 4.9862484768005324e-05, "Pretrain/Loss": 2.193211793899536, "Pretrain/Loss (Raw)": 2.164484739303589, "Pretrain/Step": 595, "Pretrain/Step Time": 8.800898099318147} +{"Pretrain/Learning Rate": 4.986159408504999e-05, "Pretrain/Loss": 2.1927413940429688, "Pretrain/Loss (Raw)": 2.1673054695129395, "Pretrain/Step": 596, "Pretrain/Step Time": 8.799159493297338} +{"Pretrain/Learning Rate": 4.986070053493846e-05, "Pretrain/Loss": 2.1902146339416504, "Pretrain/Loss (Raw)": 2.2285008430480957, "Pretrain/Step": 597, "Pretrain/Step Time": 8.79749563895166} +{"Pretrain/Learning Rate": 4.985980411777381e-05, "Pretrain/Loss": 2.189368724822998, "Pretrain/Loss (Raw)": 2.054335832595825, "Pretrain/Step": 598, "Pretrain/Step Time": 8.798219764605165} +{"Pretrain/Learning Rate": 4.9858904833659404e-05, "Pretrain/Loss": 2.1888985633850098, "Pretrain/Loss (Raw)": 2.225167989730835, "Pretrain/Step": 599, "Pretrain/Step Time": 8.796421555802226} +{"Pretrain/Learning Rate": 4.985800268269895e-05, "Pretrain/Loss": 2.18764591217041, "Pretrain/Loss (Raw)": 2.145369291305542, "Pretrain/Step": 600, "Pretrain/Step Time": 8.794813022017479} +{"Pretrain/Learning Rate": 4.9857097664996486e-05, "Pretrain/Loss": 2.1864075660705566, "Pretrain/Loss (Raw)": 2.0912582874298096, "Pretrain/Step": 601, "Pretrain/Step Time": 8.79516433365643} +{"Pretrain/Learning Rate": 4.98561897806564e-05, "Pretrain/Loss": 2.184323787689209, "Pretrain/Loss (Raw)": 2.0207059383392334, "Pretrain/Step": 602, "Pretrain/Step Time": 8.794208755716681} +{"Pretrain/Learning Rate": 4.985527902978337e-05, "Pretrain/Loss": 2.18265438079834, "Pretrain/Loss (Raw)": 2.1068832874298096, "Pretrain/Step": 603, "Pretrain/Step Time": 8.793607385829091} +{"Pretrain/Learning Rate": 4.985436541248245e-05, "Pretrain/Loss": 2.1818044185638428, "Pretrain/Loss (Raw)": 2.165005683898926, "Pretrain/Step": 604, "Pretrain/Step Time": 8.803187454119325} +{"Pretrain/Learning Rate": 4.985344892885899e-05, "Pretrain/Loss": 2.1818466186523438, "Pretrain/Loss (Raw)": 2.0706679821014404, "Pretrain/Step": 605, "Pretrain/Step Time": 8.796736123040318} +{"Pretrain/Learning Rate": 4.985252957901869e-05, "Pretrain/Loss": 2.1825242042541504, "Pretrain/Loss (Raw)": 2.236499547958374, "Pretrain/Step": 606, "Pretrain/Step Time": 8.798559373244643} +{"Pretrain/Learning Rate": 4.985160736306756e-05, "Pretrain/Loss": 2.1836471557617188, "Pretrain/Loss (Raw)": 2.2947030067443848, "Pretrain/Step": 607, "Pretrain/Step Time": 8.79744759015739} +{"Pretrain/Learning Rate": 4.985068228111198e-05, "Pretrain/Loss": 2.1841909885406494, "Pretrain/Loss (Raw)": 2.254258155822754, "Pretrain/Step": 608, "Pretrain/Step Time": 8.79719883017242} +{"Pretrain/Learning Rate": 4.984975433325861e-05, "Pretrain/Loss": 2.1818621158599854, "Pretrain/Loss (Raw)": 1.9043705463409424, "Pretrain/Step": 609, "Pretrain/Step Time": 8.789221229031682} +{"Pretrain/Learning Rate": 4.9848823519614475e-05, "Pretrain/Loss": 2.181565523147583, "Pretrain/Loss (Raw)": 2.1999666690826416, "Pretrain/Step": 610, "Pretrain/Step Time": 8.79236257635057} +{"Pretrain/Learning Rate": 4.9847889840286924e-05, "Pretrain/Loss": 2.182451009750366, "Pretrain/Loss (Raw)": 2.2744107246398926, "Pretrain/Step": 611, "Pretrain/Step Time": 8.803370932117105} +{"Pretrain/Learning Rate": 4.984695329538362e-05, "Pretrain/Loss": 2.181948184967041, "Pretrain/Loss (Raw)": 2.2235045433044434, "Pretrain/Step": 612, "Pretrain/Step Time": 8.793542681261897} +{"Pretrain/Learning Rate": 4.984601388501258e-05, "Pretrain/Loss": 2.1831161975860596, "Pretrain/Loss (Raw)": 2.3662309646606445, "Pretrain/Step": 613, "Pretrain/Step Time": 8.795623615384102} +{"Pretrain/Learning Rate": 4.9845071609282145e-05, "Pretrain/Loss": 2.181370973587036, "Pretrain/Loss (Raw)": 2.202420711517334, "Pretrain/Step": 614, "Pretrain/Step Time": 8.79512346163392} +{"Pretrain/Learning Rate": 4.984412646830098e-05, "Pretrain/Loss": 2.1819615364074707, "Pretrain/Loss (Raw)": 2.215221881866455, "Pretrain/Step": 615, "Pretrain/Step Time": 8.794407334178686} +{"Pretrain/Learning Rate": 4.9843178462178084e-05, "Pretrain/Loss": 2.1826729774475098, "Pretrain/Loss (Raw)": 2.221681594848633, "Pretrain/Step": 616, "Pretrain/Step Time": 8.788607306778431} +{"Pretrain/Learning Rate": 4.984222759102277e-05, "Pretrain/Loss": 2.1811368465423584, "Pretrain/Loss (Raw)": 2.0757687091827393, "Pretrain/Step": 617, "Pretrain/Step Time": 8.789056802168489} +{"Pretrain/Learning Rate": 4.984127385494472e-05, "Pretrain/Loss": 2.1817190647125244, "Pretrain/Loss (Raw)": 2.140519380569458, "Pretrain/Step": 618, "Pretrain/Step Time": 8.794899957254529} +{"Pretrain/Learning Rate": 4.984031725405392e-05, "Pretrain/Loss": 2.1825757026672363, "Pretrain/Loss (Raw)": 2.1811094284057617, "Pretrain/Step": 619, "Pretrain/Step Time": 8.789620034396648} +{"Pretrain/Learning Rate": 4.983935778846067e-05, "Pretrain/Loss": 2.184190273284912, "Pretrain/Loss (Raw)": 2.1250171661376953, "Pretrain/Step": 620, "Pretrain/Step Time": 8.775746693834662} +{"Pretrain/Learning Rate": 4.9838395458275636e-05, "Pretrain/Loss": 2.184762477874756, "Pretrain/Loss (Raw)": 2.032904624938965, "Pretrain/Step": 621, "Pretrain/Step Time": 8.77415726147592} +{"Pretrain/Learning Rate": 4.98374302636098e-05, "Pretrain/Loss": 2.186723232269287, "Pretrain/Loss (Raw)": 2.3514580726623535, "Pretrain/Step": 622, "Pretrain/Step Time": 8.7796965315938} +{"Pretrain/Learning Rate": 4.983646220457446e-05, "Pretrain/Loss": 2.185706615447998, "Pretrain/Loss (Raw)": 2.1649138927459717, "Pretrain/Step": 623, "Pretrain/Step Time": 8.782031828537583} +{"Pretrain/Learning Rate": 4.9835491281281274e-05, "Pretrain/Loss": 2.185523509979248, "Pretrain/Loss (Raw)": 2.1698174476623535, "Pretrain/Step": 624, "Pretrain/Step Time": 8.780036125332117} +{"Pretrain/Learning Rate": 4.9834517493842196e-05, "Pretrain/Loss": 2.1857662200927734, "Pretrain/Loss (Raw)": 2.0952279567718506, "Pretrain/Step": 625, "Pretrain/Step Time": 8.781492553651333} +{"Pretrain/Learning Rate": 4.983354084236954e-05, "Pretrain/Loss": 2.1841702461242676, "Pretrain/Loss (Raw)": 2.2718002796173096, "Pretrain/Step": 626, "Pretrain/Step Time": 8.7782870400697} +{"Pretrain/Learning Rate": 4.983256132697594e-05, "Pretrain/Loss": 2.1830997467041016, "Pretrain/Loss (Raw)": 2.2000083923339844, "Pretrain/Step": 627, "Pretrain/Step Time": 8.78008297458291} +{"Pretrain/Learning Rate": 4.983157894777435e-05, "Pretrain/Loss": 2.183180332183838, "Pretrain/Loss (Raw)": 2.1359481811523438, "Pretrain/Step": 628, "Pretrain/Step Time": 8.779914962127805} +{"Pretrain/Learning Rate": 4.983059370487806e-05, "Pretrain/Loss": 2.183215618133545, "Pretrain/Loss (Raw)": 2.230062246322632, "Pretrain/Step": 629, "Pretrain/Step Time": 8.786238331347704} +{"Pretrain/Learning Rate": 4.9829605598400705e-05, "Pretrain/Loss": 2.1823275089263916, "Pretrain/Loss (Raw)": 2.071275472640991, "Pretrain/Step": 630, "Pretrain/Step Time": 8.784145433455706} +{"Pretrain/Learning Rate": 4.982861462845623e-05, "Pretrain/Loss": 2.1808626651763916, "Pretrain/Loss (Raw)": 2.057035207748413, "Pretrain/Step": 631, "Pretrain/Step Time": 8.781903283670545} +{"Pretrain/Learning Rate": 4.982762079515892e-05, "Pretrain/Loss": 2.1801304817199707, "Pretrain/Loss (Raw)": 2.0953686237335205, "Pretrain/Step": 632, "Pretrain/Step Time": 8.784661184996367} +{"Pretrain/Learning Rate": 4.982662409862339e-05, "Pretrain/Loss": 2.180225133895874, "Pretrain/Loss (Raw)": 2.195563316345215, "Pretrain/Step": 633, "Pretrain/Step Time": 8.77519205212593} +{"Pretrain/Learning Rate": 4.9825624538964576e-05, "Pretrain/Loss": 2.17877459526062, "Pretrain/Loss (Raw)": 2.035188674926758, "Pretrain/Step": 634, "Pretrain/Step Time": 8.778887068852782} +{"Pretrain/Learning Rate": 4.982462211629776e-05, "Pretrain/Loss": 2.179685115814209, "Pretrain/Loss (Raw)": 2.1219677925109863, "Pretrain/Step": 635, "Pretrain/Step Time": 8.776374010369182} +{"Pretrain/Learning Rate": 4.9823616830738546e-05, "Pretrain/Loss": 2.1787352561950684, "Pretrain/Loss (Raw)": 2.172853708267212, "Pretrain/Step": 636, "Pretrain/Step Time": 8.782217072322965} +{"Pretrain/Learning Rate": 4.9822608682402866e-05, "Pretrain/Loss": 2.177438735961914, "Pretrain/Loss (Raw)": 2.040372371673584, "Pretrain/Step": 637, "Pretrain/Step Time": 8.786035181954503} +{"Pretrain/Learning Rate": 4.9821597671406984e-05, "Pretrain/Loss": 2.175663948059082, "Pretrain/Loss (Raw)": 2.123682975769043, "Pretrain/Step": 638, "Pretrain/Step Time": 8.786393985152245} +{"Pretrain/Learning Rate": 4.982058379786749e-05, "Pretrain/Loss": 2.174948215484619, "Pretrain/Loss (Raw)": 2.1780927181243896, "Pretrain/Step": 639, "Pretrain/Step Time": 8.788165574893355} +{"Pretrain/Learning Rate": 4.9819567061901327e-05, "Pretrain/Loss": 2.176166534423828, "Pretrain/Loss (Raw)": 2.3117055892944336, "Pretrain/Step": 640, "Pretrain/Step Time": 8.789831398054957} +{"Pretrain/Learning Rate": 4.981854746362573e-05, "Pretrain/Loss": 2.178314208984375, "Pretrain/Loss (Raw)": 2.24157452583313, "Pretrain/Step": 641, "Pretrain/Step Time": 8.789529534056783} +{"Pretrain/Learning Rate": 4.981752500315829e-05, "Pretrain/Loss": 2.175812244415283, "Pretrain/Loss (Raw)": 2.112811326980591, "Pretrain/Step": 642, "Pretrain/Step Time": 8.785004820674658} +{"Pretrain/Learning Rate": 4.981649968061692e-05, "Pretrain/Loss": 2.1748945713043213, "Pretrain/Loss (Raw)": 2.0600180625915527, "Pretrain/Step": 643, "Pretrain/Step Time": 8.785237288102508} +{"Pretrain/Learning Rate": 4.981547149611987e-05, "Pretrain/Loss": 2.173436164855957, "Pretrain/Loss (Raw)": 2.2294564247131348, "Pretrain/Step": 644, "Pretrain/Step Time": 8.788719547912478} +{"Pretrain/Learning Rate": 4.9814440449785715e-05, "Pretrain/Loss": 2.174156665802002, "Pretrain/Loss (Raw)": 2.162209987640381, "Pretrain/Step": 645, "Pretrain/Step Time": 8.787577169016004} +{"Pretrain/Learning Rate": 4.9813406541733355e-05, "Pretrain/Loss": 2.1744422912597656, "Pretrain/Loss (Raw)": 2.2041890621185303, "Pretrain/Step": 646, "Pretrain/Step Time": 8.787295497953892} +{"Pretrain/Learning Rate": 4.981236977208203e-05, "Pretrain/Loss": 2.174009323120117, "Pretrain/Loss (Raw)": 2.152012348175049, "Pretrain/Step": 647, "Pretrain/Step Time": 8.789782559499145} +{"Pretrain/Learning Rate": 4.98113301409513e-05, "Pretrain/Loss": 2.1734132766723633, "Pretrain/Loss (Raw)": 2.1351847648620605, "Pretrain/Step": 648, "Pretrain/Step Time": 8.786444630473852} +{"Pretrain/Learning Rate": 4.981028764846106e-05, "Pretrain/Loss": 2.1751067638397217, "Pretrain/Loss (Raw)": 2.1852543354034424, "Pretrain/Step": 649, "Pretrain/Step Time": 8.786959769204259} +{"Pretrain/Learning Rate": 4.980924229473155e-05, "Pretrain/Loss": 2.1752424240112305, "Pretrain/Loss (Raw)": 2.1492881774902344, "Pretrain/Step": 650, "Pretrain/Step Time": 8.784997442737222} +{"Pretrain/Learning Rate": 4.980819407988331e-05, "Pretrain/Loss": 2.175771713256836, "Pretrain/Loss (Raw)": 2.3353891372680664, "Pretrain/Step": 651, "Pretrain/Step Time": 8.786737797781825} +{"Pretrain/Learning Rate": 4.980714300403723e-05, "Pretrain/Loss": 2.1751914024353027, "Pretrain/Loss (Raw)": 2.075706720352173, "Pretrain/Step": 652, "Pretrain/Step Time": 8.784868543967605} +{"Pretrain/Learning Rate": 4.9806089067314515e-05, "Pretrain/Loss": 2.1738460063934326, "Pretrain/Loss (Raw)": 2.066521406173706, "Pretrain/Step": 653, "Pretrain/Step Time": 8.786664759740233} +{"Pretrain/Learning Rate": 4.980503226983673e-05, "Pretrain/Loss": 2.1730146408081055, "Pretrain/Loss (Raw)": 2.139085292816162, "Pretrain/Step": 654, "Pretrain/Step Time": 8.786797178909183} +{"Pretrain/Learning Rate": 4.980397261172573e-05, "Pretrain/Loss": 2.171424627304077, "Pretrain/Loss (Raw)": 2.071812391281128, "Pretrain/Step": 655, "Pretrain/Step Time": 8.775431171059608} +{"Pretrain/Learning Rate": 4.9802910093103725e-05, "Pretrain/Loss": 2.1705522537231445, "Pretrain/Loss (Raw)": 2.1062769889831543, "Pretrain/Step": 656, "Pretrain/Step Time": 8.776518618687987} +{"Pretrain/Learning Rate": 4.980184471409326e-05, "Pretrain/Loss": 2.169605016708374, "Pretrain/Loss (Raw)": 2.204535961151123, "Pretrain/Step": 657, "Pretrain/Step Time": 8.777799259871244} +{"Pretrain/Learning Rate": 4.980077647481719e-05, "Pretrain/Loss": 2.167609691619873, "Pretrain/Loss (Raw)": 1.998365044593811, "Pretrain/Step": 658, "Pretrain/Step Time": 8.782956471666694} +{"Pretrain/Learning Rate": 4.979970537539871e-05, "Pretrain/Loss": 2.1672534942626953, "Pretrain/Loss (Raw)": 2.1860809326171875, "Pretrain/Step": 659, "Pretrain/Step Time": 8.778292583301663} +{"Pretrain/Learning Rate": 4.979863141596135e-05, "Pretrain/Loss": 2.1681442260742188, "Pretrain/Loss (Raw)": 2.216320276260376, "Pretrain/Step": 660, "Pretrain/Step Time": 8.782966062426567} +{"Pretrain/Learning Rate": 4.979755459662896e-05, "Pretrain/Loss": 2.1674959659576416, "Pretrain/Loss (Raw)": 1.9890494346618652, "Pretrain/Step": 661, "Pretrain/Step Time": 8.78783692792058} +{"Pretrain/Learning Rate": 4.979647491752572e-05, "Pretrain/Loss": 2.1691036224365234, "Pretrain/Loss (Raw)": 2.278775453567505, "Pretrain/Step": 662, "Pretrain/Step Time": 8.78087991848588} +{"Pretrain/Learning Rate": 4.979539237877615e-05, "Pretrain/Loss": 2.1690447330474854, "Pretrain/Loss (Raw)": 2.192182779312134, "Pretrain/Step": 663, "Pretrain/Step Time": 8.785749413073063} +{"Pretrain/Learning Rate": 4.979430698050509e-05, "Pretrain/Loss": 2.1690845489501953, "Pretrain/Loss (Raw)": 2.190765857696533, "Pretrain/Step": 664, "Pretrain/Step Time": 8.783826787024736} +{"Pretrain/Learning Rate": 4.979321872283772e-05, "Pretrain/Loss": 2.1691179275512695, "Pretrain/Loss (Raw)": 2.1253833770751953, "Pretrain/Step": 665, "Pretrain/Step Time": 8.785460028797388} +{"Pretrain/Learning Rate": 4.979212760589953e-05, "Pretrain/Loss": 2.1686973571777344, "Pretrain/Loss (Raw)": 2.2262704372406006, "Pretrain/Step": 666, "Pretrain/Step Time": 8.784360110759735} +{"Pretrain/Learning Rate": 4.9791033629816364e-05, "Pretrain/Loss": 2.1682379245758057, "Pretrain/Loss (Raw)": 2.2086308002471924, "Pretrain/Step": 667, "Pretrain/Step Time": 8.785438150167465} +{"Pretrain/Learning Rate": 4.978993679471438e-05, "Pretrain/Loss": 2.167403221130371, "Pretrain/Loss (Raw)": 2.137807607650757, "Pretrain/Step": 668, "Pretrain/Step Time": 8.78875277005136} +{"Pretrain/Learning Rate": 4.978883710072008e-05, "Pretrain/Loss": 2.1667568683624268, "Pretrain/Loss (Raw)": 2.1193602085113525, "Pretrain/Step": 669, "Pretrain/Step Time": 8.785156112164259} +{"Pretrain/Learning Rate": 4.978773454796026e-05, "Pretrain/Loss": 2.167975425720215, "Pretrain/Loss (Raw)": 2.0785140991210938, "Pretrain/Step": 670, "Pretrain/Step Time": 8.786532867699862} +{"Pretrain/Learning Rate": 4.9786629136562095e-05, "Pretrain/Loss": 2.1669793128967285, "Pretrain/Loss (Raw)": 2.216038942337036, "Pretrain/Step": 671, "Pretrain/Step Time": 8.786571929231286} +{"Pretrain/Learning Rate": 4.978552086665306e-05, "Pretrain/Loss": 2.166306257247925, "Pretrain/Loss (Raw)": 2.0853636264801025, "Pretrain/Step": 672, "Pretrain/Step Time": 8.793609591200948} +{"Pretrain/Learning Rate": 4.9784409738360973e-05, "Pretrain/Loss": 2.1650638580322266, "Pretrain/Loss (Raw)": 2.025930404663086, "Pretrain/Step": 673, "Pretrain/Step Time": 8.793298410251737} +{"Pretrain/Learning Rate": 4.978329575181395e-05, "Pretrain/Loss": 2.16464900970459, "Pretrain/Loss (Raw)": 2.226310968399048, "Pretrain/Step": 674, "Pretrain/Step Time": 8.795463731512427} +{"Pretrain/Learning Rate": 4.978217890714049e-05, "Pretrain/Loss": 2.165226936340332, "Pretrain/Loss (Raw)": 2.1263749599456787, "Pretrain/Step": 675, "Pretrain/Step Time": 8.7900874260813} +{"Pretrain/Learning Rate": 4.978105920446938e-05, "Pretrain/Loss": 2.1647329330444336, "Pretrain/Loss (Raw)": 2.222689151763916, "Pretrain/Step": 676, "Pretrain/Step Time": 8.790016392245889} +{"Pretrain/Learning Rate": 4.977993664392975e-05, "Pretrain/Loss": 2.1633048057556152, "Pretrain/Loss (Raw)": 2.0420854091644287, "Pretrain/Step": 677, "Pretrain/Step Time": 8.793086027726531} +{"Pretrain/Learning Rate": 4.9778811225651056e-05, "Pretrain/Loss": 2.1633174419403076, "Pretrain/Loss (Raw)": 2.0855939388275146, "Pretrain/Step": 678, "Pretrain/Step Time": 8.78889269568026} +{"Pretrain/Learning Rate": 4.9777682949763096e-05, "Pretrain/Loss": 2.163891077041626, "Pretrain/Loss (Raw)": 2.2311291694641113, "Pretrain/Step": 679, "Pretrain/Step Time": 8.78817398659885} +{"Pretrain/Learning Rate": 4.9776551816395975e-05, "Pretrain/Loss": 2.163965940475464, "Pretrain/Loss (Raw)": 2.2042698860168457, "Pretrain/Step": 680, "Pretrain/Step Time": 8.791107131168246} +{"Pretrain/Learning Rate": 4.977541782568015e-05, "Pretrain/Loss": 2.163224935531616, "Pretrain/Loss (Raw)": 2.0262701511383057, "Pretrain/Step": 681, "Pretrain/Step Time": 8.78859661333263} +{"Pretrain/Learning Rate": 4.97742809777464e-05, "Pretrain/Loss": 2.1611406803131104, "Pretrain/Loss (Raw)": 2.0207440853118896, "Pretrain/Step": 682, "Pretrain/Step Time": 8.791206086054444} +{"Pretrain/Learning Rate": 4.9773141272725824e-05, "Pretrain/Loss": 2.158087730407715, "Pretrain/Loss (Raw)": 1.8900258541107178, "Pretrain/Step": 683, "Pretrain/Step Time": 8.785271657630801} +{"Pretrain/Learning Rate": 4.9771998710749864e-05, "Pretrain/Loss": 2.156789779663086, "Pretrain/Loss (Raw)": 2.172802686691284, "Pretrain/Step": 684, "Pretrain/Step Time": 8.790227930992842} +{"Pretrain/Learning Rate": 4.977085329195028e-05, "Pretrain/Loss": 2.156672477722168, "Pretrain/Loss (Raw)": 2.153221607208252, "Pretrain/Step": 685, "Pretrain/Step Time": 8.790267342701554} +{"Pretrain/Learning Rate": 4.9769705016459164e-05, "Pretrain/Loss": 2.154409885406494, "Pretrain/Loss (Raw)": 1.9744194746017456, "Pretrain/Step": 686, "Pretrain/Step Time": 8.791034733876586} +{"Pretrain/Learning Rate": 4.976855388440896e-05, "Pretrain/Loss": 2.155123710632324, "Pretrain/Loss (Raw)": 2.059030532836914, "Pretrain/Step": 687, "Pretrain/Step Time": 8.794771810993552} +{"Pretrain/Learning Rate": 4.97673998959324e-05, "Pretrain/Loss": 2.154849052429199, "Pretrain/Loss (Raw)": 2.12614107131958, "Pretrain/Step": 688, "Pretrain/Step Time": 8.796208966523409} +{"Pretrain/Learning Rate": 4.976624305116259e-05, "Pretrain/Loss": 2.1533427238464355, "Pretrain/Loss (Raw)": 2.0445289611816406, "Pretrain/Step": 689, "Pretrain/Step Time": 8.801051689311862} +{"Pretrain/Learning Rate": 4.9765083350232913e-05, "Pretrain/Loss": 2.1540205478668213, "Pretrain/Loss (Raw)": 2.23751163482666, "Pretrain/Step": 690, "Pretrain/Step Time": 8.801983386278152} +{"Pretrain/Learning Rate": 4.976392079327713e-05, "Pretrain/Loss": 2.1541366577148438, "Pretrain/Loss (Raw)": 2.1202521324157715, "Pretrain/Step": 691, "Pretrain/Step Time": 8.78488796018064} +{"Pretrain/Learning Rate": 4.976275538042932e-05, "Pretrain/Loss": 2.1520304679870605, "Pretrain/Loss (Raw)": 1.9639530181884766, "Pretrain/Step": 692, "Pretrain/Step Time": 8.791477665305138} +{"Pretrain/Learning Rate": 4.976158711182386e-05, "Pretrain/Loss": 2.1508448123931885, "Pretrain/Loss (Raw)": 2.045715570449829, "Pretrain/Step": 693, "Pretrain/Step Time": 8.7854198589921} +{"Pretrain/Learning Rate": 4.9760415987595496e-05, "Pretrain/Loss": 2.151146650314331, "Pretrain/Loss (Raw)": 2.1681928634643555, "Pretrain/Step": 694, "Pretrain/Step Time": 8.784349782392383} +{"Pretrain/Learning Rate": 4.9759242007879295e-05, "Pretrain/Loss": 2.1506896018981934, "Pretrain/Loss (Raw)": 2.1857492923736572, "Pretrain/Step": 695, "Pretrain/Step Time": 8.78471776098013} +{"Pretrain/Learning Rate": 4.975806517281062e-05, "Pretrain/Loss": 2.1509363651275635, "Pretrain/Loss (Raw)": 2.141904592514038, "Pretrain/Step": 696, "Pretrain/Step Time": 8.791802782565355} +{"Pretrain/Learning Rate": 4.975688548252522e-05, "Pretrain/Loss": 2.1486053466796875, "Pretrain/Loss (Raw)": 2.0326380729675293, "Pretrain/Step": 697, "Pretrain/Step Time": 8.789211343973875} +{"Pretrain/Learning Rate": 4.9755702937159124e-05, "Pretrain/Loss": 2.1481003761291504, "Pretrain/Loss (Raw)": 2.1301934719085693, "Pretrain/Step": 698, "Pretrain/Step Time": 8.778809757903218} +{"Pretrain/Learning Rate": 4.975451753684871e-05, "Pretrain/Loss": 2.1466116905212402, "Pretrain/Loss (Raw)": 2.0943362712860107, "Pretrain/Step": 699, "Pretrain/Step Time": 8.78312543220818} +{"Pretrain/Learning Rate": 4.975332928173069e-05, "Pretrain/Loss": 2.1450858116149902, "Pretrain/Loss (Raw)": 2.09224534034729, "Pretrain/Step": 700, "Pretrain/Step Time": 8.784222582355142} +{"Pretrain/Learning Rate": 4.975213817194209e-05, "Pretrain/Loss": 2.145211696624756, "Pretrain/Loss (Raw)": 1.9717622995376587, "Pretrain/Step": 701, "Pretrain/Step Time": 8.781748475506902} +{"Pretrain/Learning Rate": 4.975094420762029e-05, "Pretrain/Loss": 2.144604444503784, "Pretrain/Loss (Raw)": 2.085848569869995, "Pretrain/Step": 702, "Pretrain/Step Time": 8.786254044622183} +{"Pretrain/Learning Rate": 4.9749747388902964e-05, "Pretrain/Loss": 2.1423592567443848, "Pretrain/Loss (Raw)": 1.9747276306152344, "Pretrain/Step": 703, "Pretrain/Step Time": 8.793186506256461} +{"Pretrain/Learning Rate": 4.974854771592815e-05, "Pretrain/Loss": 2.1408395767211914, "Pretrain/Loss (Raw)": 2.0421059131622314, "Pretrain/Step": 704, "Pretrain/Step Time": 8.7922931779176} +{"Pretrain/Learning Rate": 4.974734518883419e-05, "Pretrain/Loss": 2.1421706676483154, "Pretrain/Loss (Raw)": 2.2982470989227295, "Pretrain/Step": 705, "Pretrain/Step Time": 8.780412185937166} +{"Pretrain/Learning Rate": 4.974613980775977e-05, "Pretrain/Loss": 2.1420633792877197, "Pretrain/Loss (Raw)": 2.18642520904541, "Pretrain/Step": 706, "Pretrain/Step Time": 8.778444664552808} +{"Pretrain/Learning Rate": 4.974493157284391e-05, "Pretrain/Loss": 2.1404807567596436, "Pretrain/Loss (Raw)": 2.0035080909729004, "Pretrain/Step": 707, "Pretrain/Step Time": 8.784126026555896} +{"Pretrain/Learning Rate": 4.974372048422593e-05, "Pretrain/Loss": 2.140516519546509, "Pretrain/Loss (Raw)": 2.129211664199829, "Pretrain/Step": 708, "Pretrain/Step Time": 8.785318780690432} +{"Pretrain/Learning Rate": 4.974250654204551e-05, "Pretrain/Loss": 2.1423444747924805, "Pretrain/Loss (Raw)": 2.383159637451172, "Pretrain/Step": 709, "Pretrain/Step Time": 8.778742915019393} +{"Pretrain/Learning Rate": 4.974128974644264e-05, "Pretrain/Loss": 2.1421499252319336, "Pretrain/Loss (Raw)": 2.198350667953491, "Pretrain/Step": 710, "Pretrain/Step Time": 8.787574354559183} +{"Pretrain/Learning Rate": 4.9740070097557656e-05, "Pretrain/Loss": 2.1408040523529053, "Pretrain/Loss (Raw)": 2.118377685546875, "Pretrain/Step": 711, "Pretrain/Step Time": 8.796471986919641} +{"Pretrain/Learning Rate": 4.973884759553121e-05, "Pretrain/Loss": 2.14095139503479, "Pretrain/Loss (Raw)": 2.1447629928588867, "Pretrain/Step": 712, "Pretrain/Step Time": 8.784221861511469} +{"Pretrain/Learning Rate": 4.973762224050428e-05, "Pretrain/Loss": 2.142848491668701, "Pretrain/Loss (Raw)": 2.313688278198242, "Pretrain/Step": 713, "Pretrain/Step Time": 8.781039910390973} +{"Pretrain/Learning Rate": 4.973639403261819e-05, "Pretrain/Loss": 2.143580436706543, "Pretrain/Loss (Raw)": 2.325124979019165, "Pretrain/Step": 714, "Pretrain/Step Time": 8.784181440249085} +{"Pretrain/Learning Rate": 4.9735162972014584e-05, "Pretrain/Loss": 2.144768238067627, "Pretrain/Loss (Raw)": 2.0896151065826416, "Pretrain/Step": 715, "Pretrain/Step Time": 8.777726527303457} +{"Pretrain/Learning Rate": 4.9733929058835425e-05, "Pretrain/Loss": 2.1441516876220703, "Pretrain/Loss (Raw)": 2.144507646560669, "Pretrain/Step": 716, "Pretrain/Step Time": 8.779283566400409} +{"Pretrain/Learning Rate": 4.973269229322301e-05, "Pretrain/Loss": 2.1449031829833984, "Pretrain/Loss (Raw)": 2.128498077392578, "Pretrain/Step": 717, "Pretrain/Step Time": 8.787976643070579} +{"Pretrain/Learning Rate": 4.973145267531998e-05, "Pretrain/Loss": 2.1462674140930176, "Pretrain/Loss (Raw)": 2.46378493309021, "Pretrain/Step": 718, "Pretrain/Step Time": 8.781561197713017} +{"Pretrain/Learning Rate": 4.973021020526929e-05, "Pretrain/Loss": 2.147045612335205, "Pretrain/Loss (Raw)": 2.144144296646118, "Pretrain/Step": 719, "Pretrain/Step Time": 8.784861942753196} +{"Pretrain/Learning Rate": 4.972896488321422e-05, "Pretrain/Loss": 2.14656925201416, "Pretrain/Loss (Raw)": 2.144761800765991, "Pretrain/Step": 720, "Pretrain/Step Time": 8.782186269760132} +{"Pretrain/Learning Rate": 4.97277167092984e-05, "Pretrain/Loss": 2.1437745094299316, "Pretrain/Loss (Raw)": 1.7682650089263916, "Pretrain/Step": 721, "Pretrain/Step Time": 8.78695515356958} +{"Pretrain/Learning Rate": 4.972646568366577e-05, "Pretrain/Loss": 2.142571449279785, "Pretrain/Loss (Raw)": 2.055147409439087, "Pretrain/Step": 722, "Pretrain/Step Time": 8.786842362955213} +{"Pretrain/Learning Rate": 4.9725211806460604e-05, "Pretrain/Loss": 2.142690658569336, "Pretrain/Loss (Raw)": 2.1797637939453125, "Pretrain/Step": 723, "Pretrain/Step Time": 8.784294916316867} +{"Pretrain/Learning Rate": 4.97239550778275e-05, "Pretrain/Loss": 2.1432597637176514, "Pretrain/Loss (Raw)": 2.240140914916992, "Pretrain/Step": 724, "Pretrain/Step Time": 8.79647322371602} +{"Pretrain/Learning Rate": 4.972269549791139e-05, "Pretrain/Loss": 2.141329050064087, "Pretrain/Loss (Raw)": 1.9813458919525146, "Pretrain/Step": 725, "Pretrain/Step Time": 8.794301880523562} +{"Pretrain/Learning Rate": 4.9721433066857535e-05, "Pretrain/Loss": 2.1420888900756836, "Pretrain/Loss (Raw)": 2.151616334915161, "Pretrain/Step": 726, "Pretrain/Step Time": 8.781920975074172} +{"Pretrain/Learning Rate": 4.9720167784811535e-05, "Pretrain/Loss": 2.141509532928467, "Pretrain/Loss (Raw)": 2.1510214805603027, "Pretrain/Step": 727, "Pretrain/Step Time": 8.784338656812906} +{"Pretrain/Learning Rate": 4.97188996519193e-05, "Pretrain/Loss": 2.143136501312256, "Pretrain/Loss (Raw)": 2.35361647605896, "Pretrain/Step": 728, "Pretrain/Step Time": 8.785449692979455} +{"Pretrain/Learning Rate": 4.971762866832708e-05, "Pretrain/Loss": 2.143364906311035, "Pretrain/Loss (Raw)": 2.120502233505249, "Pretrain/Step": 729, "Pretrain/Step Time": 8.780841775238514} +{"Pretrain/Learning Rate": 4.971635483418144e-05, "Pretrain/Loss": 2.1437301635742188, "Pretrain/Loss (Raw)": 2.0674357414245605, "Pretrain/Step": 730, "Pretrain/Step Time": 8.779291551560163} +{"Pretrain/Learning Rate": 4.97150781496293e-05, "Pretrain/Loss": 2.1443493366241455, "Pretrain/Loss (Raw)": 2.1861329078674316, "Pretrain/Step": 731, "Pretrain/Step Time": 8.787850582972169} +{"Pretrain/Learning Rate": 4.971379861481789e-05, "Pretrain/Loss": 2.1452760696411133, "Pretrain/Loss (Raw)": 2.283660411834717, "Pretrain/Step": 732, "Pretrain/Step Time": 8.77855601720512} +{"Pretrain/Learning Rate": 4.9712516229894756e-05, "Pretrain/Loss": 2.1453371047973633, "Pretrain/Loss (Raw)": 2.078437328338623, "Pretrain/Step": 733, "Pretrain/Step Time": 8.777653032913804} +{"Pretrain/Learning Rate": 4.971123099500781e-05, "Pretrain/Loss": 2.1448912620544434, "Pretrain/Loss (Raw)": 2.179457187652588, "Pretrain/Step": 734, "Pretrain/Step Time": 8.783226871863008} +{"Pretrain/Learning Rate": 4.970994291030526e-05, "Pretrain/Loss": 2.1431241035461426, "Pretrain/Loss (Raw)": 2.0685043334960938, "Pretrain/Step": 735, "Pretrain/Step Time": 8.780369192361832} +{"Pretrain/Learning Rate": 4.970865197593566e-05, "Pretrain/Loss": 2.141752243041992, "Pretrain/Loss (Raw)": 2.078666925430298, "Pretrain/Step": 736, "Pretrain/Step Time": 8.783221328631043} +{"Pretrain/Learning Rate": 4.9707358192047885e-05, "Pretrain/Loss": 2.144211769104004, "Pretrain/Loss (Raw)": 2.219176769256592, "Pretrain/Step": 737, "Pretrain/Step Time": 8.782732553780079} +{"Pretrain/Learning Rate": 4.970606155879113e-05, "Pretrain/Loss": 2.142759084701538, "Pretrain/Loss (Raw)": 2.0140411853790283, "Pretrain/Step": 738, "Pretrain/Step Time": 8.785386610776186} +{"Pretrain/Learning Rate": 4.970476207631494e-05, "Pretrain/Loss": 2.1422219276428223, "Pretrain/Loss (Raw)": 2.205650806427002, "Pretrain/Step": 739, "Pretrain/Step Time": 8.775494212284684} +{"Pretrain/Learning Rate": 4.970345974476918e-05, "Pretrain/Loss": 2.142181634902954, "Pretrain/Loss (Raw)": 2.2183587551116943, "Pretrain/Step": 740, "Pretrain/Step Time": 8.776719288900495} +{"Pretrain/Learning Rate": 4.970215456430403e-05, "Pretrain/Loss": 2.140315294265747, "Pretrain/Loss (Raw)": 2.127312183380127, "Pretrain/Step": 741, "Pretrain/Step Time": 8.77499027736485} +{"Pretrain/Learning Rate": 4.970084653507001e-05, "Pretrain/Loss": 2.1411938667297363, "Pretrain/Loss (Raw)": 2.3148562908172607, "Pretrain/Step": 742, "Pretrain/Step Time": 8.781377086415887} +{"Pretrain/Learning Rate": 4.969953565721799e-05, "Pretrain/Loss": 2.1402125358581543, "Pretrain/Loss (Raw)": 2.08963680267334, "Pretrain/Step": 743, "Pretrain/Step Time": 8.782097460702062} +{"Pretrain/Learning Rate": 4.969822193089911e-05, "Pretrain/Loss": 2.1395387649536133, "Pretrain/Loss (Raw)": 2.135471820831299, "Pretrain/Step": 744, "Pretrain/Step Time": 8.780318558216095} +{"Pretrain/Learning Rate": 4.969690535626491e-05, "Pretrain/Loss": 2.1406283378601074, "Pretrain/Loss (Raw)": 2.215200185775757, "Pretrain/Step": 745, "Pretrain/Step Time": 8.780160600319505} +{"Pretrain/Learning Rate": 4.96955859334672e-05, "Pretrain/Loss": 2.139951705932617, "Pretrain/Loss (Raw)": 2.0539305210113525, "Pretrain/Step": 746, "Pretrain/Step Time": 8.786737121641636} +{"Pretrain/Learning Rate": 4.9694263662658156e-05, "Pretrain/Loss": 2.137655019760132, "Pretrain/Loss (Raw)": 1.8871022462844849, "Pretrain/Step": 747, "Pretrain/Step Time": 8.789501475170255} +{"Pretrain/Learning Rate": 4.9692938543990265e-05, "Pretrain/Loss": 2.1382133960723877, "Pretrain/Loss (Raw)": 2.1965057849884033, "Pretrain/Step": 748, "Pretrain/Step Time": 8.783710008487105} +{"Pretrain/Learning Rate": 4.969161057761634e-05, "Pretrain/Loss": 2.13887882232666, "Pretrain/Loss (Raw)": 2.1180853843688965, "Pretrain/Step": 749, "Pretrain/Step Time": 8.792500054463744} +{"Pretrain/Learning Rate": 4.969027976368954e-05, "Pretrain/Loss": 2.1368327140808105, "Pretrain/Loss (Raw)": 2.089543342590332, "Pretrain/Step": 750, "Pretrain/Step Time": 8.792696064338088} +{"Pretrain/Learning Rate": 4.968894610236332e-05, "Pretrain/Loss": 2.1371660232543945, "Pretrain/Loss (Raw)": 2.207594156265259, "Pretrain/Step": 751, "Pretrain/Step Time": 8.787481309846044} +{"Pretrain/Learning Rate": 4.968760959379151e-05, "Pretrain/Loss": 2.1380887031555176, "Pretrain/Loss (Raw)": 2.2879021167755127, "Pretrain/Step": 752, "Pretrain/Step Time": 8.793764736503363} +{"Pretrain/Learning Rate": 4.968627023812822e-05, "Pretrain/Loss": 2.1393613815307617, "Pretrain/Loss (Raw)": 2.2581636905670166, "Pretrain/Step": 753, "Pretrain/Step Time": 8.789827842265368} +{"Pretrain/Learning Rate": 4.968492803552793e-05, "Pretrain/Loss": 2.13811993598938, "Pretrain/Loss (Raw)": 2.112874746322632, "Pretrain/Step": 754, "Pretrain/Step Time": 8.793688636273146} +{"Pretrain/Learning Rate": 4.968358298614541e-05, "Pretrain/Loss": 2.136899948120117, "Pretrain/Loss (Raw)": 2.0438525676727295, "Pretrain/Step": 755, "Pretrain/Step Time": 8.791389221325517} +{"Pretrain/Learning Rate": 4.968223509013579e-05, "Pretrain/Loss": 2.1372241973876953, "Pretrain/Loss (Raw)": 2.17747163772583, "Pretrain/Step": 756, "Pretrain/Step Time": 8.790629122406244} +{"Pretrain/Learning Rate": 4.968088434765452e-05, "Pretrain/Loss": 2.1365249156951904, "Pretrain/Loss (Raw)": 2.140531063079834, "Pretrain/Step": 757, "Pretrain/Step Time": 8.786391688510776} +{"Pretrain/Learning Rate": 4.967953075885736e-05, "Pretrain/Loss": 2.136808156967163, "Pretrain/Loss (Raw)": 2.1075210571289062, "Pretrain/Step": 758, "Pretrain/Step Time": 8.78261117823422} +{"Pretrain/Learning Rate": 4.9678174323900415e-05, "Pretrain/Loss": 2.138594627380371, "Pretrain/Loss (Raw)": 2.285710096359253, "Pretrain/Step": 759, "Pretrain/Step Time": 8.789422776550055} +{"Pretrain/Learning Rate": 4.9676815042940125e-05, "Pretrain/Loss": 2.138904094696045, "Pretrain/Loss (Raw)": 2.1349899768829346, "Pretrain/Step": 760, "Pretrain/Step Time": 8.79118663072586} +{"Pretrain/Learning Rate": 4.967545291613325e-05, "Pretrain/Loss": 2.1379871368408203, "Pretrain/Loss (Raw)": 2.078167676925659, "Pretrain/Step": 761, "Pretrain/Step Time": 8.79354696907103} +{"Pretrain/Learning Rate": 4.967408794363686e-05, "Pretrain/Loss": 2.138803482055664, "Pretrain/Loss (Raw)": 2.1396982669830322, "Pretrain/Step": 762, "Pretrain/Step Time": 8.790944496169686} +{"Pretrain/Learning Rate": 4.9672720125608384e-05, "Pretrain/Loss": 2.139343738555908, "Pretrain/Loss (Raw)": 2.191112756729126, "Pretrain/Step": 763, "Pretrain/Step Time": 8.797974525019526} +{"Pretrain/Learning Rate": 4.9671349462205565e-05, "Pretrain/Loss": 2.139056444168091, "Pretrain/Loss (Raw)": 2.136075019836426, "Pretrain/Step": 764, "Pretrain/Step Time": 8.79098161123693} +{"Pretrain/Learning Rate": 4.966997595358647e-05, "Pretrain/Loss": 2.1397290229797363, "Pretrain/Loss (Raw)": 2.126462697982788, "Pretrain/Step": 765, "Pretrain/Step Time": 8.790509989485145} +{"Pretrain/Learning Rate": 4.966859959990949e-05, "Pretrain/Loss": 2.1376516819000244, "Pretrain/Loss (Raw)": 1.8577831983566284, "Pretrain/Step": 766, "Pretrain/Step Time": 8.796865804120898} +{"Pretrain/Learning Rate": 4.966722040133337e-05, "Pretrain/Loss": 2.1364212036132812, "Pretrain/Loss (Raw)": 2.020599603652954, "Pretrain/Step": 767, "Pretrain/Step Time": 8.79438210837543} +{"Pretrain/Learning Rate": 4.9665838358017156e-05, "Pretrain/Loss": 2.1355185508728027, "Pretrain/Loss (Raw)": 2.1961822509765625, "Pretrain/Step": 768, "Pretrain/Step Time": 8.792390536516905} +{"Pretrain/Learning Rate": 4.966445347012023e-05, "Pretrain/Loss": 2.1353297233581543, "Pretrain/Loss (Raw)": 2.217376708984375, "Pretrain/Step": 769, "Pretrain/Step Time": 8.792651070281863} +{"Pretrain/Learning Rate": 4.9663065737802316e-05, "Pretrain/Loss": 2.1356420516967773, "Pretrain/Loss (Raw)": 2.152808904647827, "Pretrain/Step": 770, "Pretrain/Step Time": 8.794951662421227} +{"Pretrain/Learning Rate": 4.9661675161223435e-05, "Pretrain/Loss": 2.136993885040283, "Pretrain/Loss (Raw)": 2.233039617538452, "Pretrain/Step": 771, "Pretrain/Step Time": 8.798222780227661} +{"Pretrain/Learning Rate": 4.966028174054397e-05, "Pretrain/Loss": 2.136240243911743, "Pretrain/Loss (Raw)": 2.1329903602600098, "Pretrain/Step": 772, "Pretrain/Step Time": 8.795801974833012} +{"Pretrain/Learning Rate": 4.965888547592461e-05, "Pretrain/Loss": 2.13525128364563, "Pretrain/Loss (Raw)": 2.0356245040893555, "Pretrain/Step": 773, "Pretrain/Step Time": 8.795503173023462} +{"Pretrain/Learning Rate": 4.965748636752638e-05, "Pretrain/Loss": 2.1359362602233887, "Pretrain/Loss (Raw)": 2.291867971420288, "Pretrain/Step": 774, "Pretrain/Step Time": 8.802682718262076} +{"Pretrain/Learning Rate": 4.965608441551063e-05, "Pretrain/Loss": 2.135601043701172, "Pretrain/Loss (Raw)": 2.1091225147247314, "Pretrain/Step": 775, "Pretrain/Step Time": 8.797612989321351} +{"Pretrain/Learning Rate": 4.965467962003905e-05, "Pretrain/Loss": 2.136864423751831, "Pretrain/Loss (Raw)": 2.2968599796295166, "Pretrain/Step": 776, "Pretrain/Step Time": 8.796424364671111} +{"Pretrain/Learning Rate": 4.965327198127363e-05, "Pretrain/Loss": 2.136986255645752, "Pretrain/Loss (Raw)": 2.2008843421936035, "Pretrain/Step": 777, "Pretrain/Step Time": 8.79559881426394} +{"Pretrain/Learning Rate": 4.965186149937672e-05, "Pretrain/Loss": 2.136413097381592, "Pretrain/Loss (Raw)": 2.075897693634033, "Pretrain/Step": 778, "Pretrain/Step Time": 8.794409008696675} +{"Pretrain/Learning Rate": 4.9650448174510986e-05, "Pretrain/Loss": 2.135138988494873, "Pretrain/Loss (Raw)": 2.1723058223724365, "Pretrain/Step": 779, "Pretrain/Step Time": 8.792184676975012} +{"Pretrain/Learning Rate": 4.9649032006839404e-05, "Pretrain/Loss": 2.1344518661499023, "Pretrain/Loss (Raw)": 1.9877500534057617, "Pretrain/Step": 780, "Pretrain/Step Time": 8.79149635322392} +{"Pretrain/Learning Rate": 4.964761299652529e-05, "Pretrain/Loss": 2.1347832679748535, "Pretrain/Loss (Raw)": 2.108978748321533, "Pretrain/Step": 781, "Pretrain/Step Time": 8.800470134243369} +{"Pretrain/Learning Rate": 4.9646191143732324e-05, "Pretrain/Loss": 2.1367971897125244, "Pretrain/Loss (Raw)": 2.3968429565429688, "Pretrain/Step": 782, "Pretrain/Step Time": 8.79717330634594} +{"Pretrain/Learning Rate": 4.9644766448624444e-05, "Pretrain/Loss": 2.136455535888672, "Pretrain/Loss (Raw)": 2.0280866622924805, "Pretrain/Step": 783, "Pretrain/Step Time": 8.800020955502987} +{"Pretrain/Learning Rate": 4.9643338911365964e-05, "Pretrain/Loss": 2.1374049186706543, "Pretrain/Loss (Raw)": 2.2278013229370117, "Pretrain/Step": 784, "Pretrain/Step Time": 8.798700468614697} +{"Pretrain/Learning Rate": 4.9641908532121525e-05, "Pretrain/Loss": 2.1355745792388916, "Pretrain/Loss (Raw)": 1.9702446460723877, "Pretrain/Step": 785, "Pretrain/Step Time": 8.79737708158791} +{"Pretrain/Learning Rate": 4.964047531105608e-05, "Pretrain/Loss": 2.1369917392730713, "Pretrain/Loss (Raw)": 2.1797730922698975, "Pretrain/Step": 786, "Pretrain/Step Time": 8.790117051452398} +{"Pretrain/Learning Rate": 4.963903924833491e-05, "Pretrain/Loss": 2.1357827186584473, "Pretrain/Loss (Raw)": 2.0313212871551514, "Pretrain/Step": 787, "Pretrain/Step Time": 8.794558824971318} +{"Pretrain/Learning Rate": 4.963760034412363e-05, "Pretrain/Loss": 2.1337661743164062, "Pretrain/Loss (Raw)": 1.9581938982009888, "Pretrain/Step": 788, "Pretrain/Step Time": 8.80359991453588} +{"Pretrain/Learning Rate": 4.9636158598588185e-05, "Pretrain/Loss": 2.135437488555908, "Pretrain/Loss (Raw)": 2.202998399734497, "Pretrain/Step": 789, "Pretrain/Step Time": 8.79805271141231} +{"Pretrain/Learning Rate": 4.9634714011894836e-05, "Pretrain/Loss": 2.1357131004333496, "Pretrain/Loss (Raw)": 2.314020872116089, "Pretrain/Step": 790, "Pretrain/Step Time": 8.802457774057984} +{"Pretrain/Learning Rate": 4.963326658421019e-05, "Pretrain/Loss": 2.1353485584259033, "Pretrain/Loss (Raw)": 2.145540952682495, "Pretrain/Step": 791, "Pretrain/Step Time": 8.799636261537671} +{"Pretrain/Learning Rate": 4.9631816315701165e-05, "Pretrain/Loss": 2.137049674987793, "Pretrain/Loss (Raw)": 2.4085075855255127, "Pretrain/Step": 792, "Pretrain/Step Time": 8.800540119409561} +{"Pretrain/Learning Rate": 4.9630363206535e-05, "Pretrain/Loss": 2.1380980014801025, "Pretrain/Loss (Raw)": 2.259568929672241, "Pretrain/Step": 793, "Pretrain/Step Time": 8.801570335403085} +{"Pretrain/Learning Rate": 4.962890725687931e-05, "Pretrain/Loss": 2.1377933025360107, "Pretrain/Loss (Raw)": 2.1872599124908447, "Pretrain/Step": 794, "Pretrain/Step Time": 8.801962487399578} +{"Pretrain/Learning Rate": 4.962744846690196e-05, "Pretrain/Loss": 2.1377763748168945, "Pretrain/Loss (Raw)": 2.2064478397369385, "Pretrain/Step": 795, "Pretrain/Step Time": 8.802802244201303} +{"Pretrain/Learning Rate": 4.962598683677122e-05, "Pretrain/Loss": 2.138990640640259, "Pretrain/Loss (Raw)": 2.2932345867156982, "Pretrain/Step": 796, "Pretrain/Step Time": 8.808150613680482} +{"Pretrain/Learning Rate": 4.9624522366655625e-05, "Pretrain/Loss": 2.1374313831329346, "Pretrain/Loss (Raw)": 1.9198253154754639, "Pretrain/Step": 797, "Pretrain/Step Time": 8.802254658192396} +{"Pretrain/Learning Rate": 4.962305505672408e-05, "Pretrain/Loss": 2.1371030807495117, "Pretrain/Loss (Raw)": 2.036468505859375, "Pretrain/Step": 798, "Pretrain/Step Time": 8.800210680812597} +{"Pretrain/Learning Rate": 4.96215849071458e-05, "Pretrain/Loss": 2.135681629180908, "Pretrain/Loss (Raw)": 2.034088373184204, "Pretrain/Step": 799, "Pretrain/Step Time": 8.801252573728561} +{"Pretrain/Learning Rate": 4.962011191809033e-05, "Pretrain/Loss": 2.1368303298950195, "Pretrain/Loss (Raw)": 2.2324137687683105, "Pretrain/Step": 800, "Pretrain/Step Time": 8.791745502501726} +{"Pretrain/Learning Rate": 4.961863608972753e-05, "Pretrain/Loss": 2.137545585632324, "Pretrain/Loss (Raw)": 2.1174752712249756, "Pretrain/Step": 801, "Pretrain/Step Time": 8.79142297245562} +{"Pretrain/Learning Rate": 4.961715742222762e-05, "Pretrain/Loss": 2.13577938079834, "Pretrain/Loss (Raw)": 2.0002124309539795, "Pretrain/Step": 802, "Pretrain/Step Time": 8.79642559029162} +{"Pretrain/Learning Rate": 4.961567591576112e-05, "Pretrain/Loss": 2.1339406967163086, "Pretrain/Loss (Raw)": 1.8910505771636963, "Pretrain/Step": 803, "Pretrain/Step Time": 8.798703787848353} +{"Pretrain/Learning Rate": 4.961419157049887e-05, "Pretrain/Loss": 2.133087635040283, "Pretrain/Loss (Raw)": 2.11346435546875, "Pretrain/Step": 804, "Pretrain/Step Time": 8.794676953926682} +{"Pretrain/Learning Rate": 4.9612704386612066e-05, "Pretrain/Loss": 2.1311163902282715, "Pretrain/Loss (Raw)": 1.7897940874099731, "Pretrain/Step": 805, "Pretrain/Step Time": 8.794872442260385} +{"Pretrain/Learning Rate": 4.9611214364272206e-05, "Pretrain/Loss": 2.130215644836426, "Pretrain/Loss (Raw)": 1.970260500907898, "Pretrain/Step": 806, "Pretrain/Step Time": 8.799230067059398} +{"Pretrain/Learning Rate": 4.960972150365114e-05, "Pretrain/Loss": 2.129333257675171, "Pretrain/Loss (Raw)": 2.1182236671447754, "Pretrain/Step": 807, "Pretrain/Step Time": 8.79528795927763} +{"Pretrain/Learning Rate": 4.960822580492103e-05, "Pretrain/Loss": 2.1294398307800293, "Pretrain/Loss (Raw)": 2.217881917953491, "Pretrain/Step": 808, "Pretrain/Step Time": 8.790025722235441} +{"Pretrain/Learning Rate": 4.960672726825436e-05, "Pretrain/Loss": 2.1300806999206543, "Pretrain/Loss (Raw)": 2.108304500579834, "Pretrain/Step": 809, "Pretrain/Step Time": 8.803063226863742} +{"Pretrain/Learning Rate": 4.960522589382395e-05, "Pretrain/Loss": 2.131190776824951, "Pretrain/Loss (Raw)": 2.1628472805023193, "Pretrain/Step": 810, "Pretrain/Step Time": 8.800225164741278} +{"Pretrain/Learning Rate": 4.960372168180294e-05, "Pretrain/Loss": 2.1325387954711914, "Pretrain/Loss (Raw)": 2.0625603199005127, "Pretrain/Step": 811, "Pretrain/Step Time": 8.798633076250553} +{"Pretrain/Learning Rate": 4.9602214632364816e-05, "Pretrain/Loss": 2.1323039531707764, "Pretrain/Loss (Raw)": 2.1427440643310547, "Pretrain/Step": 812, "Pretrain/Step Time": 8.795894594863057} +{"Pretrain/Learning Rate": 4.9600704745683367e-05, "Pretrain/Loss": 2.1320323944091797, "Pretrain/Loss (Raw)": 2.1184990406036377, "Pretrain/Step": 813, "Pretrain/Step Time": 8.797334041446447} +{"Pretrain/Learning Rate": 4.959919202193273e-05, "Pretrain/Loss": 2.1337032318115234, "Pretrain/Loss (Raw)": 2.1882641315460205, "Pretrain/Step": 814, "Pretrain/Step Time": 8.795474400743842} +{"Pretrain/Learning Rate": 4.959767646128735e-05, "Pretrain/Loss": 2.1340672969818115, "Pretrain/Loss (Raw)": 2.105644941329956, "Pretrain/Step": 815, "Pretrain/Step Time": 8.793308295309544} +{"Pretrain/Learning Rate": 4.959615806392201e-05, "Pretrain/Loss": 2.133509635925293, "Pretrain/Loss (Raw)": 2.0547592639923096, "Pretrain/Step": 816, "Pretrain/Step Time": 8.79821927472949} +{"Pretrain/Learning Rate": 4.959463683001182e-05, "Pretrain/Loss": 2.134202480316162, "Pretrain/Loss (Raw)": 2.133225202560425, "Pretrain/Step": 817, "Pretrain/Step Time": 8.792286366224289} +{"Pretrain/Learning Rate": 4.959311275973223e-05, "Pretrain/Loss": 2.1349728107452393, "Pretrain/Loss (Raw)": 2.3360865116119385, "Pretrain/Step": 818, "Pretrain/Step Time": 8.791033988818526} +{"Pretrain/Learning Rate": 4.959158585325898e-05, "Pretrain/Loss": 2.1352462768554688, "Pretrain/Loss (Raw)": 2.15527081489563, "Pretrain/Step": 819, "Pretrain/Step Time": 8.796451304107904} +{"Pretrain/Learning Rate": 4.959005611076817e-05, "Pretrain/Loss": 2.1374568939208984, "Pretrain/Loss (Raw)": 2.2469098567962646, "Pretrain/Step": 820, "Pretrain/Step Time": 8.79352431371808} +{"Pretrain/Learning Rate": 4.9588523532436214e-05, "Pretrain/Loss": 2.1395421028137207, "Pretrain/Loss (Raw)": 2.3126320838928223, "Pretrain/Step": 821, "Pretrain/Step Time": 8.791958836838603} +{"Pretrain/Learning Rate": 4.9586988118439863e-05, "Pretrain/Loss": 2.1399474143981934, "Pretrain/Loss (Raw)": 2.2200539112091064, "Pretrain/Step": 822, "Pretrain/Step Time": 8.79479674808681} +{"Pretrain/Learning Rate": 4.958544986895619e-05, "Pretrain/Loss": 2.138969659805298, "Pretrain/Loss (Raw)": 2.0606093406677246, "Pretrain/Step": 823, "Pretrain/Step Time": 8.794603554531932} +{"Pretrain/Learning Rate": 4.958390878416258e-05, "Pretrain/Loss": 2.1402511596679688, "Pretrain/Loss (Raw)": 2.3059072494506836, "Pretrain/Step": 824, "Pretrain/Step Time": 8.790015755221248} +{"Pretrain/Learning Rate": 4.9582364864236765e-05, "Pretrain/Loss": 2.1395130157470703, "Pretrain/Loss (Raw)": 1.9381614923477173, "Pretrain/Step": 825, "Pretrain/Step Time": 8.796553129330277} +{"Pretrain/Learning Rate": 4.95808181093568e-05, "Pretrain/Loss": 2.140218496322632, "Pretrain/Loss (Raw)": 2.2205045223236084, "Pretrain/Step": 826, "Pretrain/Step Time": 8.796907618641853} +{"Pretrain/Learning Rate": 4.9579268519701063e-05, "Pretrain/Loss": 2.1401782035827637, "Pretrain/Loss (Raw)": 2.0892090797424316, "Pretrain/Step": 827, "Pretrain/Step Time": 8.792565269395709} +{"Pretrain/Learning Rate": 4.957771609544826e-05, "Pretrain/Loss": 2.141866683959961, "Pretrain/Loss (Raw)": 2.3083605766296387, "Pretrain/Step": 828, "Pretrain/Step Time": 8.79039910249412} +{"Pretrain/Learning Rate": 4.957616083677742e-05, "Pretrain/Loss": 2.1447789669036865, "Pretrain/Loss (Raw)": 2.344521999359131, "Pretrain/Step": 829, "Pretrain/Step Time": 8.786085540428758} +{"Pretrain/Learning Rate": 4.9574602743867916e-05, "Pretrain/Loss": 2.1448378562927246, "Pretrain/Loss (Raw)": 2.0933735370635986, "Pretrain/Step": 830, "Pretrain/Step Time": 8.788128230720758} +{"Pretrain/Learning Rate": 4.957304181689941e-05, "Pretrain/Loss": 2.146923065185547, "Pretrain/Loss (Raw)": 2.2416725158691406, "Pretrain/Step": 831, "Pretrain/Step Time": 8.782887874171138} +{"Pretrain/Learning Rate": 4.957147805605194e-05, "Pretrain/Loss": 2.148493766784668, "Pretrain/Loss (Raw)": 2.2431328296661377, "Pretrain/Step": 832, "Pretrain/Step Time": 8.78046878427267} +{"Pretrain/Learning Rate": 4.956991146150583e-05, "Pretrain/Loss": 2.147366523742676, "Pretrain/Loss (Raw)": 2.1539742946624756, "Pretrain/Step": 833, "Pretrain/Step Time": 8.784232946112752} +{"Pretrain/Learning Rate": 4.9568342033441755e-05, "Pretrain/Loss": 2.146024703979492, "Pretrain/Loss (Raw)": 2.014655590057373, "Pretrain/Step": 834, "Pretrain/Step Time": 8.789631303399801} +{"Pretrain/Learning Rate": 4.956676977204071e-05, "Pretrain/Loss": 2.147221088409424, "Pretrain/Loss (Raw)": 2.156658172607422, "Pretrain/Step": 835, "Pretrain/Step Time": 8.783144084736705} +{"Pretrain/Learning Rate": 4.9565194677484e-05, "Pretrain/Loss": 2.1465272903442383, "Pretrain/Loss (Raw)": 2.0403926372528076, "Pretrain/Step": 836, "Pretrain/Step Time": 8.781176023185253} +{"Pretrain/Learning Rate": 4.95636167499533e-05, "Pretrain/Loss": 2.1438634395599365, "Pretrain/Loss (Raw)": 2.0421876907348633, "Pretrain/Step": 837, "Pretrain/Step Time": 8.786726148799062} +{"Pretrain/Learning Rate": 4.9562035989630564e-05, "Pretrain/Loss": 2.1434288024902344, "Pretrain/Loss (Raw)": 2.1427009105682373, "Pretrain/Step": 838, "Pretrain/Step Time": 8.788104601204395} +{"Pretrain/Learning Rate": 4.95604523966981e-05, "Pretrain/Loss": 2.143561363220215, "Pretrain/Loss (Raw)": 2.1353673934936523, "Pretrain/Step": 839, "Pretrain/Step Time": 8.777373688295484} +{"Pretrain/Learning Rate": 4.9558865971338524e-05, "Pretrain/Loss": 2.142754077911377, "Pretrain/Loss (Raw)": 2.0414280891418457, "Pretrain/Step": 840, "Pretrain/Step Time": 8.783651243895292} +{"Pretrain/Learning Rate": 4.9557276713734805e-05, "Pretrain/Loss": 2.142443895339966, "Pretrain/Loss (Raw)": 2.2739615440368652, "Pretrain/Step": 841, "Pretrain/Step Time": 8.786255694925785} +{"Pretrain/Learning Rate": 4.955568462407022e-05, "Pretrain/Loss": 2.1411213874816895, "Pretrain/Loss (Raw)": 2.155857563018799, "Pretrain/Step": 842, "Pretrain/Step Time": 8.781560726463795} +{"Pretrain/Learning Rate": 4.955408970252837e-05, "Pretrain/Loss": 2.140857696533203, "Pretrain/Loss (Raw)": 2.055860757827759, "Pretrain/Step": 843, "Pretrain/Step Time": 8.782049624249339} +{"Pretrain/Learning Rate": 4.955249194929319e-05, "Pretrain/Loss": 2.1416611671447754, "Pretrain/Loss (Raw)": 2.2473459243774414, "Pretrain/Step": 844, "Pretrain/Step Time": 8.78065893240273} +{"Pretrain/Learning Rate": 4.955089136454895e-05, "Pretrain/Loss": 2.142449378967285, "Pretrain/Loss (Raw)": 2.2293872833251953, "Pretrain/Step": 845, "Pretrain/Step Time": 8.779813069850206} +{"Pretrain/Learning Rate": 4.954928794848023e-05, "Pretrain/Loss": 2.1396946907043457, "Pretrain/Loss (Raw)": 2.1111786365509033, "Pretrain/Step": 846, "Pretrain/Step Time": 8.783477645367384} +{"Pretrain/Learning Rate": 4.954768170127194e-05, "Pretrain/Loss": 2.1407551765441895, "Pretrain/Loss (Raw)": 2.279914379119873, "Pretrain/Step": 847, "Pretrain/Step Time": 8.779897985979915} +{"Pretrain/Learning Rate": 4.9546072623109325e-05, "Pretrain/Loss": 2.1400694847106934, "Pretrain/Loss (Raw)": 2.0569827556610107, "Pretrain/Step": 848, "Pretrain/Step Time": 8.786365518346429} +{"Pretrain/Learning Rate": 4.954446071417795e-05, "Pretrain/Loss": 2.1423697471618652, "Pretrain/Loss (Raw)": 2.0627150535583496, "Pretrain/Step": 849, "Pretrain/Step Time": 8.780233701691031} +{"Pretrain/Learning Rate": 4.954284597466371e-05, "Pretrain/Loss": 2.1439597606658936, "Pretrain/Loss (Raw)": 2.2586586475372314, "Pretrain/Step": 850, "Pretrain/Step Time": 8.779516130685806} +{"Pretrain/Learning Rate": 4.954122840475281e-05, "Pretrain/Loss": 2.1428587436676025, "Pretrain/Loss (Raw)": 2.0388238430023193, "Pretrain/Step": 851, "Pretrain/Step Time": 8.778945684432983} +{"Pretrain/Learning Rate": 4.9539608004631825e-05, "Pretrain/Loss": 2.14271879196167, "Pretrain/Loss (Raw)": 2.222219228744507, "Pretrain/Step": 852, "Pretrain/Step Time": 8.775436073541641} +{"Pretrain/Learning Rate": 4.9537984774487606e-05, "Pretrain/Loss": 2.143998622894287, "Pretrain/Loss (Raw)": 2.145188093185425, "Pretrain/Step": 853, "Pretrain/Step Time": 8.775593839585781} +{"Pretrain/Learning Rate": 4.953635871450736e-05, "Pretrain/Loss": 2.144247055053711, "Pretrain/Loss (Raw)": 2.1834120750427246, "Pretrain/Step": 854, "Pretrain/Step Time": 8.776380728930235} +{"Pretrain/Learning Rate": 4.95347298248786e-05, "Pretrain/Loss": 2.143749713897705, "Pretrain/Loss (Raw)": 2.0873289108276367, "Pretrain/Step": 855, "Pretrain/Step Time": 8.780701404437423} +{"Pretrain/Learning Rate": 4.953309810578918e-05, "Pretrain/Loss": 2.1436121463775635, "Pretrain/Loss (Raw)": 2.336031675338745, "Pretrain/Step": 856, "Pretrain/Step Time": 8.78141912072897} +{"Pretrain/Learning Rate": 4.953146355742729e-05, "Pretrain/Loss": 2.1452643871307373, "Pretrain/Loss (Raw)": 2.3319902420043945, "Pretrain/Step": 857, "Pretrain/Step Time": 8.783521147444844} +{"Pretrain/Learning Rate": 4.952982617998143e-05, "Pretrain/Loss": 2.146730422973633, "Pretrain/Loss (Raw)": 2.2551016807556152, "Pretrain/Step": 858, "Pretrain/Step Time": 8.782724354416132} +{"Pretrain/Learning Rate": 4.952818597364043e-05, "Pretrain/Loss": 2.1450040340423584, "Pretrain/Loss (Raw)": 1.9651414155960083, "Pretrain/Step": 859, "Pretrain/Step Time": 8.784709949046373} +{"Pretrain/Learning Rate": 4.952654293859344e-05, "Pretrain/Loss": 2.1443986892700195, "Pretrain/Loss (Raw)": 2.2061593532562256, "Pretrain/Step": 860, "Pretrain/Step Time": 8.782713992521167} +{"Pretrain/Learning Rate": 4.952489707502993e-05, "Pretrain/Loss": 2.144345760345459, "Pretrain/Loss (Raw)": 2.0717074871063232, "Pretrain/Step": 861, "Pretrain/Step Time": 8.783912915736437} +{"Pretrain/Learning Rate": 4.952324838313974e-05, "Pretrain/Loss": 2.1445016860961914, "Pretrain/Loss (Raw)": 2.199371814727783, "Pretrain/Step": 862, "Pretrain/Step Time": 8.779492473229766} +{"Pretrain/Learning Rate": 4.9521596863112986e-05, "Pretrain/Loss": 2.146179676055908, "Pretrain/Loss (Raw)": 2.2833011150360107, "Pretrain/Step": 863, "Pretrain/Step Time": 8.783030496910214} +{"Pretrain/Learning Rate": 4.951994251514013e-05, "Pretrain/Loss": 2.1480298042297363, "Pretrain/Loss (Raw)": 2.3154730796813965, "Pretrain/Step": 864, "Pretrain/Step Time": 8.780274093151093} +{"Pretrain/Learning Rate": 4.9518285339411966e-05, "Pretrain/Loss": 2.1484246253967285, "Pretrain/Loss (Raw)": 2.2697393894195557, "Pretrain/Step": 865, "Pretrain/Step Time": 8.783659415319562} +{"Pretrain/Learning Rate": 4.9516625336119595e-05, "Pretrain/Loss": 2.1491146087646484, "Pretrain/Loss (Raw)": 2.1023573875427246, "Pretrain/Step": 866, "Pretrain/Step Time": 8.787426978349686} +{"Pretrain/Learning Rate": 4.951496250545446e-05, "Pretrain/Loss": 2.1483848094940186, "Pretrain/Loss (Raw)": 2.1122217178344727, "Pretrain/Step": 867, "Pretrain/Step Time": 8.788589362055063} +{"Pretrain/Learning Rate": 4.951329684760835e-05, "Pretrain/Loss": 2.1484534740448, "Pretrain/Loss (Raw)": 2.2271616458892822, "Pretrain/Step": 868, "Pretrain/Step Time": 8.787687527015805} +{"Pretrain/Learning Rate": 4.951162836277332e-05, "Pretrain/Loss": 2.1488256454467773, "Pretrain/Loss (Raw)": 2.174955129623413, "Pretrain/Step": 869, "Pretrain/Step Time": 8.786230776458979} +{"Pretrain/Learning Rate": 4.950995705114182e-05, "Pretrain/Loss": 2.147491931915283, "Pretrain/Loss (Raw)": 2.1441402435302734, "Pretrain/Step": 870, "Pretrain/Step Time": 8.78206154704094} +{"Pretrain/Learning Rate": 4.950828291290656e-05, "Pretrain/Loss": 2.148366928100586, "Pretrain/Loss (Raw)": 2.201615810394287, "Pretrain/Step": 871, "Pretrain/Step Time": 8.782073453068733} +{"Pretrain/Learning Rate": 4.950660594826064e-05, "Pretrain/Loss": 2.1482014656066895, "Pretrain/Loss (Raw)": 2.114309549331665, "Pretrain/Step": 872, "Pretrain/Step Time": 8.781258333474398} +{"Pretrain/Learning Rate": 4.9504926157397436e-05, "Pretrain/Loss": 2.147441864013672, "Pretrain/Loss (Raw)": 2.1179654598236084, "Pretrain/Step": 873, "Pretrain/Step Time": 8.792364386841655} +{"Pretrain/Learning Rate": 4.950324354051068e-05, "Pretrain/Loss": 2.147909164428711, "Pretrain/Loss (Raw)": 2.113745927810669, "Pretrain/Step": 874, "Pretrain/Step Time": 8.779493859037757} +{"Pretrain/Learning Rate": 4.950155809779442e-05, "Pretrain/Loss": 2.1495907306671143, "Pretrain/Loss (Raw)": 2.1023545265197754, "Pretrain/Step": 875, "Pretrain/Step Time": 8.788982037454844} +{"Pretrain/Learning Rate": 4.9499869829443026e-05, "Pretrain/Loss": 2.148097515106201, "Pretrain/Loss (Raw)": 2.0053324699401855, "Pretrain/Step": 876, "Pretrain/Step Time": 8.788100235164165} +{"Pretrain/Learning Rate": 4.9498178735651184e-05, "Pretrain/Loss": 2.1483654975891113, "Pretrain/Loss (Raw)": 2.152413845062256, "Pretrain/Step": 877, "Pretrain/Step Time": 8.780160922557116} +{"Pretrain/Learning Rate": 4.949648481661394e-05, "Pretrain/Loss": 2.1485939025878906, "Pretrain/Loss (Raw)": 2.1187517642974854, "Pretrain/Step": 878, "Pretrain/Step Time": 8.775142008438706} +{"Pretrain/Learning Rate": 4.949478807252663e-05, "Pretrain/Loss": 2.149468421936035, "Pretrain/Loss (Raw)": 2.3195438385009766, "Pretrain/Step": 879, "Pretrain/Step Time": 8.77823256701231} +{"Pretrain/Learning Rate": 4.949308850358494e-05, "Pretrain/Loss": 2.148421287536621, "Pretrain/Loss (Raw)": 2.15390944480896, "Pretrain/Step": 880, "Pretrain/Step Time": 8.787059623748064} +{"Pretrain/Learning Rate": 4.949138610998487e-05, "Pretrain/Loss": 2.148362159729004, "Pretrain/Loss (Raw)": 2.2505459785461426, "Pretrain/Step": 881, "Pretrain/Step Time": 8.787184417247772} +{"Pretrain/Learning Rate": 4.9489680891922746e-05, "Pretrain/Loss": 2.1485133171081543, "Pretrain/Loss (Raw)": 2.1322360038757324, "Pretrain/Step": 882, "Pretrain/Step Time": 8.786854300647974} +{"Pretrain/Learning Rate": 4.948797284959522e-05, "Pretrain/Loss": 2.148655891418457, "Pretrain/Loss (Raw)": 2.062126636505127, "Pretrain/Step": 883, "Pretrain/Step Time": 8.788051133975387} +{"Pretrain/Learning Rate": 4.948626198319928e-05, "Pretrain/Loss": 2.1486830711364746, "Pretrain/Loss (Raw)": 2.180947780609131, "Pretrain/Step": 884, "Pretrain/Step Time": 8.788865491747856} +{"Pretrain/Learning Rate": 4.948454829293222e-05, "Pretrain/Loss": 2.148599147796631, "Pretrain/Loss (Raw)": 2.1297943592071533, "Pretrain/Step": 885, "Pretrain/Step Time": 8.786622261628509} +{"Pretrain/Learning Rate": 4.9482831778991676e-05, "Pretrain/Loss": 2.148552417755127, "Pretrain/Loss (Raw)": 2.1015090942382812, "Pretrain/Step": 886, "Pretrain/Step Time": 8.787931783124804} +{"Pretrain/Learning Rate": 4.9481112441575605e-05, "Pretrain/Loss": 2.145699977874756, "Pretrain/Loss (Raw)": 1.9205876588821411, "Pretrain/Step": 887, "Pretrain/Step Time": 8.792779862880707} +{"Pretrain/Learning Rate": 4.947939028088229e-05, "Pretrain/Loss": 2.145537853240967, "Pretrain/Loss (Raw)": 2.114264726638794, "Pretrain/Step": 888, "Pretrain/Step Time": 8.787975354120135} +{"Pretrain/Learning Rate": 4.947766529711033e-05, "Pretrain/Loss": 2.146716833114624, "Pretrain/Loss (Raw)": 2.2290685176849365, "Pretrain/Step": 889, "Pretrain/Step Time": 8.78592730499804} +{"Pretrain/Learning Rate": 4.947593749045867e-05, "Pretrain/Loss": 2.146601676940918, "Pretrain/Loss (Raw)": 2.1249709129333496, "Pretrain/Step": 890, "Pretrain/Step Time": 8.785330848768353} +{"Pretrain/Learning Rate": 4.947420686112657e-05, "Pretrain/Loss": 2.1471757888793945, "Pretrain/Loss (Raw)": 2.26462459564209, "Pretrain/Step": 891, "Pretrain/Step Time": 8.776716578751802} +{"Pretrain/Learning Rate": 4.9472473409313605e-05, "Pretrain/Loss": 2.1478426456451416, "Pretrain/Loss (Raw)": 2.221390724182129, "Pretrain/Step": 892, "Pretrain/Step Time": 8.775992553681135} +{"Pretrain/Learning Rate": 4.947073713521968e-05, "Pretrain/Loss": 2.1491289138793945, "Pretrain/Loss (Raw)": 2.2911269664764404, "Pretrain/Step": 893, "Pretrain/Step Time": 8.77242549136281} +{"Pretrain/Learning Rate": 4.9468998039045046e-05, "Pretrain/Loss": 2.151794910430908, "Pretrain/Loss (Raw)": 2.199028253555298, "Pretrain/Step": 894, "Pretrain/Step Time": 8.778887560591102} +{"Pretrain/Learning Rate": 4.946725612099026e-05, "Pretrain/Loss": 2.1525144577026367, "Pretrain/Loss (Raw)": 2.112668514251709, "Pretrain/Step": 895, "Pretrain/Step Time": 8.778217082843184} +{"Pretrain/Learning Rate": 4.9465511381256204e-05, "Pretrain/Loss": 2.151106834411621, "Pretrain/Loss (Raw)": 2.0160083770751953, "Pretrain/Step": 896, "Pretrain/Step Time": 8.773581862449646} +{"Pretrain/Learning Rate": 4.946376382004408e-05, "Pretrain/Loss": 2.1508164405822754, "Pretrain/Loss (Raw)": 2.180218458175659, "Pretrain/Step": 897, "Pretrain/Step Time": 8.780356742441654} +{"Pretrain/Learning Rate": 4.9462013437555446e-05, "Pretrain/Loss": 2.150064468383789, "Pretrain/Loss (Raw)": 2.0565593242645264, "Pretrain/Step": 898, "Pretrain/Step Time": 8.775100154802203} +{"Pretrain/Learning Rate": 4.946026023399215e-05, "Pretrain/Loss": 2.1494693756103516, "Pretrain/Loss (Raw)": 2.1569008827209473, "Pretrain/Step": 899, "Pretrain/Step Time": 8.771077267825603} +{"Pretrain/Learning Rate": 4.9458504209556377e-05, "Pretrain/Loss": 2.1496996879577637, "Pretrain/Loss (Raw)": 2.162440776824951, "Pretrain/Step": 900, "Pretrain/Step Time": 8.770919069647789} +{"Pretrain/Learning Rate": 4.945674536445065e-05, "Pretrain/Loss": 2.1488702297210693, "Pretrain/Loss (Raw)": 1.9294546842575073, "Pretrain/Step": 901, "Pretrain/Step Time": 8.77982878498733} +{"Pretrain/Learning Rate": 4.945498369887781e-05, "Pretrain/Loss": 2.1475343704223633, "Pretrain/Loss (Raw)": 2.1208715438842773, "Pretrain/Step": 902, "Pretrain/Step Time": 8.771698215976357} +{"Pretrain/Learning Rate": 4.945321921304101e-05, "Pretrain/Loss": 2.1472930908203125, "Pretrain/Loss (Raw)": 2.078253984451294, "Pretrain/Step": 903, "Pretrain/Step Time": 8.775105567649007} +{"Pretrain/Learning Rate": 4.945145190714374e-05, "Pretrain/Loss": 2.1467061042785645, "Pretrain/Loss (Raw)": 2.2217087745666504, "Pretrain/Step": 904, "Pretrain/Step Time": 8.772323790937662} +{"Pretrain/Learning Rate": 4.944968178138982e-05, "Pretrain/Loss": 2.1448445320129395, "Pretrain/Loss (Raw)": 1.9625864028930664, "Pretrain/Step": 905, "Pretrain/Step Time": 8.776209646835923} +{"Pretrain/Learning Rate": 4.944790883598339e-05, "Pretrain/Loss": 2.1444194316864014, "Pretrain/Loss (Raw)": 2.0215044021606445, "Pretrain/Step": 906, "Pretrain/Step Time": 8.774673238396645} +{"Pretrain/Learning Rate": 4.9446133071128905e-05, "Pretrain/Loss": 2.14445161819458, "Pretrain/Loss (Raw)": 2.1764345169067383, "Pretrain/Step": 907, "Pretrain/Step Time": 8.773953599855304} +{"Pretrain/Learning Rate": 4.944435448703116e-05, "Pretrain/Loss": 2.14526629447937, "Pretrain/Loss (Raw)": 2.0920166969299316, "Pretrain/Step": 908, "Pretrain/Step Time": 8.779449626803398} +{"Pretrain/Learning Rate": 4.944257308389528e-05, "Pretrain/Loss": 2.1465024948120117, "Pretrain/Loss (Raw)": 2.2672417163848877, "Pretrain/Step": 909, "Pretrain/Step Time": 8.769181346520782} +{"Pretrain/Learning Rate": 4.944078886192668e-05, "Pretrain/Loss": 2.144707202911377, "Pretrain/Loss (Raw)": 2.1670145988464355, "Pretrain/Step": 910, "Pretrain/Step Time": 8.773320259526372} +{"Pretrain/Learning Rate": 4.943900182133116e-05, "Pretrain/Loss": 2.1456265449523926, "Pretrain/Loss (Raw)": 2.14577054977417, "Pretrain/Step": 911, "Pretrain/Step Time": 8.774975189939141} +{"Pretrain/Learning Rate": 4.943721196231477e-05, "Pretrain/Loss": 2.1448092460632324, "Pretrain/Loss (Raw)": 2.123199939727783, "Pretrain/Step": 912, "Pretrain/Step Time": 8.778475660830736} +{"Pretrain/Learning Rate": 4.943541928508395e-05, "Pretrain/Loss": 2.1460390090942383, "Pretrain/Loss (Raw)": 2.127638339996338, "Pretrain/Step": 913, "Pretrain/Step Time": 8.780968839302659} +{"Pretrain/Learning Rate": 4.9433623789845426e-05, "Pretrain/Loss": 2.1462199687957764, "Pretrain/Loss (Raw)": 2.2029366493225098, "Pretrain/Step": 914, "Pretrain/Step Time": 8.78229701705277} +{"Pretrain/Learning Rate": 4.943182547680629e-05, "Pretrain/Loss": 2.1465518474578857, "Pretrain/Loss (Raw)": 2.0738048553466797, "Pretrain/Step": 915, "Pretrain/Step Time": 8.78293327987194} +{"Pretrain/Learning Rate": 4.94300243461739e-05, "Pretrain/Loss": 2.146249771118164, "Pretrain/Loss (Raw)": 1.919517159461975, "Pretrain/Step": 916, "Pretrain/Step Time": 8.771976610645652} +{"Pretrain/Learning Rate": 4.9428220398155986e-05, "Pretrain/Loss": 2.1472580432891846, "Pretrain/Loss (Raw)": 2.3320515155792236, "Pretrain/Step": 917, "Pretrain/Step Time": 8.76931088231504} +{"Pretrain/Learning Rate": 4.94264136329606e-05, "Pretrain/Loss": 2.1441028118133545, "Pretrain/Loss (Raw)": 1.9101840257644653, "Pretrain/Step": 918, "Pretrain/Step Time": 8.772951303049922} +{"Pretrain/Learning Rate": 4.942460405079608e-05, "Pretrain/Loss": 2.1439218521118164, "Pretrain/Loss (Raw)": 2.122375249862671, "Pretrain/Step": 919, "Pretrain/Step Time": 8.77101613767445} +{"Pretrain/Learning Rate": 4.942279165187113e-05, "Pretrain/Loss": 2.1427762508392334, "Pretrain/Loss (Raw)": 2.2618401050567627, "Pretrain/Step": 920, "Pretrain/Step Time": 8.770594974979758} +{"Pretrain/Learning Rate": 4.9420976436394764e-05, "Pretrain/Loss": 2.1415724754333496, "Pretrain/Loss (Raw)": 2.105522394180298, "Pretrain/Step": 921, "Pretrain/Step Time": 8.766581360250711} +{"Pretrain/Learning Rate": 4.941915840457632e-05, "Pretrain/Loss": 2.1415586471557617, "Pretrain/Loss (Raw)": 2.1854658126831055, "Pretrain/Step": 922, "Pretrain/Step Time": 8.770913358777761} +{"Pretrain/Learning Rate": 4.941733755662545e-05, "Pretrain/Loss": 2.1410369873046875, "Pretrain/Loss (Raw)": 2.1396560668945312, "Pretrain/Step": 923, "Pretrain/Step Time": 8.768790101632476} +{"Pretrain/Learning Rate": 4.941551389275217e-05, "Pretrain/Loss": 2.1403560638427734, "Pretrain/Loss (Raw)": 2.206082820892334, "Pretrain/Step": 924, "Pretrain/Step Time": 8.76049849204719} +{"Pretrain/Learning Rate": 4.9413687413166777e-05, "Pretrain/Loss": 2.142059803009033, "Pretrain/Loss (Raw)": 2.137932538986206, "Pretrain/Step": 925, "Pretrain/Step Time": 8.765925835818052} +{"Pretrain/Learning Rate": 4.94118581180799e-05, "Pretrain/Loss": 2.1418404579162598, "Pretrain/Loss (Raw)": 2.008382558822632, "Pretrain/Step": 926, "Pretrain/Step Time": 8.766045283526182} +{"Pretrain/Learning Rate": 4.9410026007702525e-05, "Pretrain/Loss": 2.1429295539855957, "Pretrain/Loss (Raw)": 2.1734812259674072, "Pretrain/Step": 927, "Pretrain/Step Time": 8.764087401330471} +{"Pretrain/Learning Rate": 4.940819108224592e-05, "Pretrain/Loss": 2.1429624557495117, "Pretrain/Loss (Raw)": 2.2366368770599365, "Pretrain/Step": 928, "Pretrain/Step Time": 8.76547284424305} +{"Pretrain/Learning Rate": 4.940635334192171e-05, "Pretrain/Loss": 2.144200086593628, "Pretrain/Loss (Raw)": 2.275893449783325, "Pretrain/Step": 929, "Pretrain/Step Time": 8.773624021559954} +{"Pretrain/Learning Rate": 4.940451278694181e-05, "Pretrain/Loss": 2.1451048851013184, "Pretrain/Loss (Raw)": 2.1160361766815186, "Pretrain/Step": 930, "Pretrain/Step Time": 8.769303681328893} +{"Pretrain/Learning Rate": 4.9402669417518514e-05, "Pretrain/Loss": 2.1466617584228516, "Pretrain/Loss (Raw)": 2.090287446975708, "Pretrain/Step": 931, "Pretrain/Step Time": 8.771211985498667} +{"Pretrain/Learning Rate": 4.940082323386439e-05, "Pretrain/Loss": 2.1469600200653076, "Pretrain/Loss (Raw)": 2.1516635417938232, "Pretrain/Step": 932, "Pretrain/Step Time": 8.76796803995967} +{"Pretrain/Learning Rate": 4.939897423619234e-05, "Pretrain/Loss": 2.149888038635254, "Pretrain/Loss (Raw)": 2.164578676223755, "Pretrain/Step": 933, "Pretrain/Step Time": 8.768480721861124} +{"Pretrain/Learning Rate": 4.9397122424715624e-05, "Pretrain/Loss": 2.149644374847412, "Pretrain/Loss (Raw)": 1.939082145690918, "Pretrain/Step": 934, "Pretrain/Step Time": 8.76491479203105} +{"Pretrain/Learning Rate": 4.939526779964778e-05, "Pretrain/Loss": 2.1499876976013184, "Pretrain/Loss (Raw)": 2.162184476852417, "Pretrain/Step": 935, "Pretrain/Step Time": 8.764342702925205} +{"Pretrain/Learning Rate": 4.9393410361202694e-05, "Pretrain/Loss": 2.149796485900879, "Pretrain/Loss (Raw)": 2.1933765411376953, "Pretrain/Step": 936, "Pretrain/Step Time": 8.771638071164489} +{"Pretrain/Learning Rate": 4.9391550109594584e-05, "Pretrain/Loss": 2.1496634483337402, "Pretrain/Loss (Raw)": 2.091299533843994, "Pretrain/Step": 937, "Pretrain/Step Time": 8.757448125630617} +{"Pretrain/Learning Rate": 4.938968704503798e-05, "Pretrain/Loss": 2.1488330364227295, "Pretrain/Loss (Raw)": 2.05655837059021, "Pretrain/Step": 938, "Pretrain/Step Time": 8.761256825178862} +{"Pretrain/Learning Rate": 4.938782116774774e-05, "Pretrain/Loss": 2.150270700454712, "Pretrain/Loss (Raw)": 2.2465648651123047, "Pretrain/Step": 939, "Pretrain/Step Time": 8.764376992359757} +{"Pretrain/Learning Rate": 4.938595247793903e-05, "Pretrain/Loss": 2.150736093521118, "Pretrain/Loss (Raw)": 2.2023162841796875, "Pretrain/Step": 940, "Pretrain/Step Time": 8.76361184567213} +{"Pretrain/Learning Rate": 4.938408097582738e-05, "Pretrain/Loss": 2.1519320011138916, "Pretrain/Loss (Raw)": 2.271578550338745, "Pretrain/Step": 941, "Pretrain/Step Time": 8.763807833194733} +{"Pretrain/Learning Rate": 4.9382206661628615e-05, "Pretrain/Loss": 2.1533660888671875, "Pretrain/Loss (Raw)": 2.3718278408050537, "Pretrain/Step": 942, "Pretrain/Step Time": 8.770547814667225} +{"Pretrain/Learning Rate": 4.9380329535558887e-05, "Pretrain/Loss": 2.1535959243774414, "Pretrain/Loss (Raw)": 2.1350507736206055, "Pretrain/Step": 943, "Pretrain/Step Time": 8.770715031772852} +{"Pretrain/Learning Rate": 4.9378449597834664e-05, "Pretrain/Loss": 2.1547441482543945, "Pretrain/Loss (Raw)": 2.201753616333008, "Pretrain/Step": 944, "Pretrain/Step Time": 8.76585404202342} +{"Pretrain/Learning Rate": 4.937656684867276e-05, "Pretrain/Loss": 2.155050277709961, "Pretrain/Loss (Raw)": 2.172393560409546, "Pretrain/Step": 945, "Pretrain/Step Time": 8.765576999634504} +{"Pretrain/Learning Rate": 4.93746812882903e-05, "Pretrain/Loss": 2.153291702270508, "Pretrain/Loss (Raw)": 2.110987424850464, "Pretrain/Step": 946, "Pretrain/Step Time": 8.77014572918415} +{"Pretrain/Learning Rate": 4.937279291690474e-05, "Pretrain/Loss": 2.1542932987213135, "Pretrain/Loss (Raw)": 2.283473491668701, "Pretrain/Step": 947, "Pretrain/Step Time": 8.770316179841757} +{"Pretrain/Learning Rate": 4.9370901734733856e-05, "Pretrain/Loss": 2.1538524627685547, "Pretrain/Loss (Raw)": 2.1905012130737305, "Pretrain/Step": 948, "Pretrain/Step Time": 8.766579737886786} +{"Pretrain/Learning Rate": 4.936900774199573e-05, "Pretrain/Loss": 2.1526970863342285, "Pretrain/Loss (Raw)": 2.164738893508911, "Pretrain/Step": 949, "Pretrain/Step Time": 8.775181386619806} +{"Pretrain/Learning Rate": 4.936711093890881e-05, "Pretrain/Loss": 2.1527810096740723, "Pretrain/Loss (Raw)": 2.2307825088500977, "Pretrain/Step": 950, "Pretrain/Step Time": 8.775467654690146} +{"Pretrain/Learning Rate": 4.936521132569184e-05, "Pretrain/Loss": 2.1531739234924316, "Pretrain/Loss (Raw)": 2.1109349727630615, "Pretrain/Step": 951, "Pretrain/Step Time": 8.776210483163595} +{"Pretrain/Learning Rate": 4.936330890256388e-05, "Pretrain/Loss": 2.1529011726379395, "Pretrain/Loss (Raw)": 2.2709426879882812, "Pretrain/Step": 952, "Pretrain/Step Time": 8.776191329583526} +{"Pretrain/Learning Rate": 4.9361403669744336e-05, "Pretrain/Loss": 2.1542246341705322, "Pretrain/Loss (Raw)": 2.107605218887329, "Pretrain/Step": 953, "Pretrain/Step Time": 8.77357424609363} +{"Pretrain/Learning Rate": 4.935949562745293e-05, "Pretrain/Loss": 2.1532957553863525, "Pretrain/Loss (Raw)": 2.1016037464141846, "Pretrain/Step": 954, "Pretrain/Step Time": 8.772519744932652} +{"Pretrain/Learning Rate": 4.93575847759097e-05, "Pretrain/Loss": 2.153096914291382, "Pretrain/Loss (Raw)": 2.063753604888916, "Pretrain/Step": 955, "Pretrain/Step Time": 8.779487926512957} +{"Pretrain/Learning Rate": 4.9355671115335015e-05, "Pretrain/Loss": 2.1530251502990723, "Pretrain/Loss (Raw)": 2.299182891845703, "Pretrain/Step": 956, "Pretrain/Step Time": 8.778599280864} +{"Pretrain/Learning Rate": 4.935375464594957e-05, "Pretrain/Loss": 2.1509764194488525, "Pretrain/Loss (Raw)": 2.0822715759277344, "Pretrain/Step": 957, "Pretrain/Step Time": 8.785640556365252} +{"Pretrain/Learning Rate": 4.9351835367974375e-05, "Pretrain/Loss": 2.1514992713928223, "Pretrain/Loss (Raw)": 2.1603338718414307, "Pretrain/Step": 958, "Pretrain/Step Time": 8.776227729395032} +{"Pretrain/Learning Rate": 4.9349913281630786e-05, "Pretrain/Loss": 2.150883913040161, "Pretrain/Loss (Raw)": 2.162872791290283, "Pretrain/Step": 959, "Pretrain/Step Time": 8.780440583825111} +{"Pretrain/Learning Rate": 4.934798838714045e-05, "Pretrain/Loss": 2.151653289794922, "Pretrain/Loss (Raw)": 2.3415915966033936, "Pretrain/Step": 960, "Pretrain/Step Time": 8.785468814894557} +{"Pretrain/Learning Rate": 4.9346060684725364e-05, "Pretrain/Loss": 2.151188850402832, "Pretrain/Loss (Raw)": 2.0945563316345215, "Pretrain/Step": 961, "Pretrain/Step Time": 8.781828302890062} +{"Pretrain/Learning Rate": 4.934413017460784e-05, "Pretrain/Loss": 2.1519687175750732, "Pretrain/Loss (Raw)": 2.1144931316375732, "Pretrain/Step": 962, "Pretrain/Step Time": 8.777835933491588} +{"Pretrain/Learning Rate": 4.93421968570105e-05, "Pretrain/Loss": 2.152311325073242, "Pretrain/Loss (Raw)": 2.200502395629883, "Pretrain/Step": 963, "Pretrain/Step Time": 8.77748753502965} +{"Pretrain/Learning Rate": 4.934026073215633e-05, "Pretrain/Loss": 2.1542935371398926, "Pretrain/Loss (Raw)": 2.2941229343414307, "Pretrain/Step": 964, "Pretrain/Step Time": 8.789046792313457} +{"Pretrain/Learning Rate": 4.933832180026858e-05, "Pretrain/Loss": 2.154629707336426, "Pretrain/Loss (Raw)": 2.0851874351501465, "Pretrain/Step": 965, "Pretrain/Step Time": 8.786592097952962} +{"Pretrain/Learning Rate": 4.933638006157089e-05, "Pretrain/Loss": 2.1543564796447754, "Pretrain/Loss (Raw)": 2.1077146530151367, "Pretrain/Step": 966, "Pretrain/Step Time": 8.781796593219042} +{"Pretrain/Learning Rate": 4.933443551628717e-05, "Pretrain/Loss": 2.1550984382629395, "Pretrain/Loss (Raw)": 2.2303624153137207, "Pretrain/Step": 967, "Pretrain/Step Time": 8.78400082886219} +{"Pretrain/Learning Rate": 4.933248816464168e-05, "Pretrain/Loss": 2.155560255050659, "Pretrain/Loss (Raw)": 2.1005289554595947, "Pretrain/Step": 968, "Pretrain/Step Time": 8.787775034084916} +{"Pretrain/Learning Rate": 4.933053800685899e-05, "Pretrain/Loss": 2.153622627258301, "Pretrain/Loss (Raw)": 2.02596378326416, "Pretrain/Step": 969, "Pretrain/Step Time": 8.786525201052427} +{"Pretrain/Learning Rate": 4.932858504316401e-05, "Pretrain/Loss": 2.1529908180236816, "Pretrain/Loss (Raw)": 2.0749948024749756, "Pretrain/Step": 970, "Pretrain/Step Time": 8.786640593782067} +{"Pretrain/Learning Rate": 4.932662927378196e-05, "Pretrain/Loss": 2.1539957523345947, "Pretrain/Loss (Raw)": 2.1844799518585205, "Pretrain/Step": 971, "Pretrain/Step Time": 8.79697241447866} +{"Pretrain/Learning Rate": 4.93246706989384e-05, "Pretrain/Loss": 2.153393268585205, "Pretrain/Loss (Raw)": 2.1702353954315186, "Pretrain/Step": 972, "Pretrain/Step Time": 8.798089761286974} +{"Pretrain/Learning Rate": 4.932270931885918e-05, "Pretrain/Loss": 2.1525328159332275, "Pretrain/Loss (Raw)": 2.119237184524536, "Pretrain/Step": 973, "Pretrain/Step Time": 8.79042249917984} +{"Pretrain/Learning Rate": 4.9320745133770524e-05, "Pretrain/Loss": 2.152529001235962, "Pretrain/Loss (Raw)": 2.1106860637664795, "Pretrain/Step": 974, "Pretrain/Step Time": 8.78860991448164} +{"Pretrain/Learning Rate": 4.931877814389893e-05, "Pretrain/Loss": 2.1512255668640137, "Pretrain/Loss (Raw)": 2.113070249557495, "Pretrain/Step": 975, "Pretrain/Step Time": 8.794185485690832} +{"Pretrain/Learning Rate": 4.931680834947124e-05, "Pretrain/Loss": 2.1518301963806152, "Pretrain/Loss (Raw)": 2.1343672275543213, "Pretrain/Step": 976, "Pretrain/Step Time": 8.788953218609095} +{"Pretrain/Learning Rate": 4.9314835750714635e-05, "Pretrain/Loss": 2.1556499004364014, "Pretrain/Loss (Raw)": 2.551651954650879, "Pretrain/Step": 977, "Pretrain/Step Time": 8.787153229117393} +{"Pretrain/Learning Rate": 4.9312860347856595e-05, "Pretrain/Loss": 2.154313564300537, "Pretrain/Loss (Raw)": 2.0876333713531494, "Pretrain/Step": 978, "Pretrain/Step Time": 8.793094795197248} +{"Pretrain/Learning Rate": 4.931088214112494e-05, "Pretrain/Loss": 2.156627655029297, "Pretrain/Loss (Raw)": 2.3350048065185547, "Pretrain/Step": 979, "Pretrain/Step Time": 8.79768443480134} +{"Pretrain/Learning Rate": 4.930890113074779e-05, "Pretrain/Loss": 2.156005620956421, "Pretrain/Loss (Raw)": 2.142605781555176, "Pretrain/Step": 980, "Pretrain/Step Time": 8.790874702855945} +{"Pretrain/Learning Rate": 4.930691731695362e-05, "Pretrain/Loss": 2.1548895835876465, "Pretrain/Loss (Raw)": 2.0023081302642822, "Pretrain/Step": 981, "Pretrain/Step Time": 8.795313080772758} +{"Pretrain/Learning Rate": 4.9304930699971194e-05, "Pretrain/Loss": 2.153780460357666, "Pretrain/Loss (Raw)": 2.0414769649505615, "Pretrain/Step": 982, "Pretrain/Step Time": 8.795318966731429} +{"Pretrain/Learning Rate": 4.9302941280029645e-05, "Pretrain/Loss": 2.1547579765319824, "Pretrain/Loss (Raw)": 2.2124269008636475, "Pretrain/Step": 983, "Pretrain/Step Time": 8.78950915671885} +{"Pretrain/Learning Rate": 4.930094905735838e-05, "Pretrain/Loss": 2.1539649963378906, "Pretrain/Loss (Raw)": 2.2345399856567383, "Pretrain/Step": 984, "Pretrain/Step Time": 8.79049182869494} +{"Pretrain/Learning Rate": 4.929895403218717e-05, "Pretrain/Loss": 2.1527628898620605, "Pretrain/Loss (Raw)": 2.1781036853790283, "Pretrain/Step": 985, "Pretrain/Step Time": 8.790488449856639} +{"Pretrain/Learning Rate": 4.929695620474607e-05, "Pretrain/Loss": 2.1518759727478027, "Pretrain/Loss (Raw)": 2.1415796279907227, "Pretrain/Step": 986, "Pretrain/Step Time": 8.797466045245528} +{"Pretrain/Learning Rate": 4.9294955575265494e-05, "Pretrain/Loss": 2.1522226333618164, "Pretrain/Loss (Raw)": 2.0095202922821045, "Pretrain/Step": 987, "Pretrain/Step Time": 8.785377597436309} +{"Pretrain/Learning Rate": 4.929295214397616e-05, "Pretrain/Loss": 2.1508498191833496, "Pretrain/Loss (Raw)": 2.0304605960845947, "Pretrain/Step": 988, "Pretrain/Step Time": 8.791925802826881} +{"Pretrain/Learning Rate": 4.929094591110911e-05, "Pretrain/Loss": 2.1507930755615234, "Pretrain/Loss (Raw)": 2.0644116401672363, "Pretrain/Step": 989, "Pretrain/Step Time": 8.789452947676182} +{"Pretrain/Learning Rate": 4.928893687689572e-05, "Pretrain/Loss": 2.149667739868164, "Pretrain/Loss (Raw)": 2.055321216583252, "Pretrain/Step": 990, "Pretrain/Step Time": 8.78946073167026} +{"Pretrain/Learning Rate": 4.928692504156767e-05, "Pretrain/Loss": 2.148564338684082, "Pretrain/Loss (Raw)": 2.1420741081237793, "Pretrain/Step": 991, "Pretrain/Step Time": 8.792248856276274} +{"Pretrain/Learning Rate": 4.928491040535699e-05, "Pretrain/Loss": 2.1463093757629395, "Pretrain/Loss (Raw)": 2.0268383026123047, "Pretrain/Step": 992, "Pretrain/Step Time": 8.790299916639924} +{"Pretrain/Learning Rate": 4.9282892968495995e-05, "Pretrain/Loss": 2.144193649291992, "Pretrain/Loss (Raw)": 1.9989221096038818, "Pretrain/Step": 993, "Pretrain/Step Time": 8.790888270363212} +{"Pretrain/Learning Rate": 4.928087273121737e-05, "Pretrain/Loss": 2.1434383392333984, "Pretrain/Loss (Raw)": 2.0057058334350586, "Pretrain/Step": 994, "Pretrain/Step Time": 8.784081256017089} +{"Pretrain/Learning Rate": 4.9278849693754076e-05, "Pretrain/Loss": 2.1433939933776855, "Pretrain/Loss (Raw)": 2.106518507003784, "Pretrain/Step": 995, "Pretrain/Step Time": 8.782832035794854} +{"Pretrain/Learning Rate": 4.927682385633944e-05, "Pretrain/Loss": 2.1429898738861084, "Pretrain/Loss (Raw)": 2.175448417663574, "Pretrain/Step": 996, "Pretrain/Step Time": 8.783305272459984} +{"Pretrain/Learning Rate": 4.927479521920707e-05, "Pretrain/Loss": 2.142568826675415, "Pretrain/Loss (Raw)": 2.1210484504699707, "Pretrain/Step": 997, "Pretrain/Step Time": 8.787283226847649} +{"Pretrain/Learning Rate": 4.927276378259094e-05, "Pretrain/Loss": 2.1435604095458984, "Pretrain/Loss (Raw)": 2.27107572555542, "Pretrain/Step": 998, "Pretrain/Step Time": 8.790045047178864} +{"Pretrain/Learning Rate": 4.9270729546725305e-05, "Pretrain/Loss": 2.1429219245910645, "Pretrain/Loss (Raw)": 2.1199023723602295, "Pretrain/Step": 999, "Pretrain/Step Time": 8.789833206683397} +{"Pretrain/Learning Rate": 4.9268692511844774e-05, "Pretrain/Loss": 2.142570734024048, "Pretrain/Loss (Raw)": 2.069331169128418, "Pretrain/Step": 1000, "Pretrain/Step Time": 8.793733820319176} +{"Pretrain/Learning Rate": 4.926665267818426e-05, "Pretrain/Loss": 2.1431028842926025, "Pretrain/Loss (Raw)": 2.1860909461975098, "Pretrain/Step": 1001, "Pretrain/Step Time": 8.782850734889507} +{"Pretrain/Learning Rate": 4.926461004597901e-05, "Pretrain/Loss": 2.144407272338867, "Pretrain/Loss (Raw)": 2.280721664428711, "Pretrain/Step": 1002, "Pretrain/Step Time": 8.788878556340933} +{"Pretrain/Learning Rate": 4.92625646154646e-05, "Pretrain/Loss": 2.145359516143799, "Pretrain/Loss (Raw)": 2.224229335784912, "Pretrain/Step": 1003, "Pretrain/Step Time": 8.775862611830235} +{"Pretrain/Learning Rate": 4.926051638687691e-05, "Pretrain/Loss": 2.1472854614257812, "Pretrain/Loss (Raw)": 2.25184965133667, "Pretrain/Step": 1004, "Pretrain/Step Time": 8.77539236471057} +{"Pretrain/Learning Rate": 4.925846536045215e-05, "Pretrain/Loss": 2.1472229957580566, "Pretrain/Loss (Raw)": 2.144406795501709, "Pretrain/Step": 1005, "Pretrain/Step Time": 8.786714160814881} +{"Pretrain/Learning Rate": 4.925641153642684e-05, "Pretrain/Loss": 2.1472327709198, "Pretrain/Loss (Raw)": 2.1200132369995117, "Pretrain/Step": 1006, "Pretrain/Step Time": 8.788412543013692} +{"Pretrain/Learning Rate": 4.925435491503787e-05, "Pretrain/Loss": 2.1466736793518066, "Pretrain/Loss (Raw)": 2.247969627380371, "Pretrain/Step": 1007, "Pretrain/Step Time": 8.788481317460537} +{"Pretrain/Learning Rate": 4.9252295496522395e-05, "Pretrain/Loss": 2.145467758178711, "Pretrain/Loss (Raw)": 1.9995763301849365, "Pretrain/Step": 1008, "Pretrain/Step Time": 8.776740184053779} +{"Pretrain/Learning Rate": 4.925023328111792e-05, "Pretrain/Loss": 2.144742965698242, "Pretrain/Loss (Raw)": 2.15775465965271, "Pretrain/Step": 1009, "Pretrain/Step Time": 8.7812740188092} +{"Pretrain/Learning Rate": 4.924816826906227e-05, "Pretrain/Loss": 2.143171787261963, "Pretrain/Loss (Raw)": 1.931144118309021, "Pretrain/Step": 1010, "Pretrain/Step Time": 8.775177326053381} +{"Pretrain/Learning Rate": 4.92461004605936e-05, "Pretrain/Loss": 2.1450538635253906, "Pretrain/Loss (Raw)": 2.3030343055725098, "Pretrain/Step": 1011, "Pretrain/Step Time": 8.774588495492935} +{"Pretrain/Learning Rate": 4.924402985595037e-05, "Pretrain/Loss": 2.1446478366851807, "Pretrain/Loss (Raw)": 2.1289525032043457, "Pretrain/Step": 1012, "Pretrain/Step Time": 8.778753194957972} +{"Pretrain/Learning Rate": 4.924195645537138e-05, "Pretrain/Loss": 2.144280433654785, "Pretrain/Loss (Raw)": 2.0827648639678955, "Pretrain/Step": 1013, "Pretrain/Step Time": 8.780536429956555} +{"Pretrain/Learning Rate": 4.923988025909574e-05, "Pretrain/Loss": 2.142848491668701, "Pretrain/Loss (Raw)": 1.9182286262512207, "Pretrain/Step": 1014, "Pretrain/Step Time": 8.7800402212888} +{"Pretrain/Learning Rate": 4.923780126736288e-05, "Pretrain/Loss": 2.1439595222473145, "Pretrain/Loss (Raw)": 2.062833309173584, "Pretrain/Step": 1015, "Pretrain/Step Time": 8.773163124918938} +{"Pretrain/Learning Rate": 4.923571948041257e-05, "Pretrain/Loss": 2.143838882446289, "Pretrain/Loss (Raw)": 2.098796844482422, "Pretrain/Step": 1016, "Pretrain/Step Time": 8.777701230719686} +{"Pretrain/Learning Rate": 4.923363489848489e-05, "Pretrain/Loss": 2.144437313079834, "Pretrain/Loss (Raw)": 2.305696487426758, "Pretrain/Step": 1017, "Pretrain/Step Time": 8.780286010354757} +{"Pretrain/Learning Rate": 4.923154752182023e-05, "Pretrain/Loss": 2.1457059383392334, "Pretrain/Loss (Raw)": 2.2873237133026123, "Pretrain/Step": 1018, "Pretrain/Step Time": 8.77858373709023} +{"Pretrain/Learning Rate": 4.922945735065934e-05, "Pretrain/Loss": 2.145594596862793, "Pretrain/Loss (Raw)": 2.250378131866455, "Pretrain/Step": 1019, "Pretrain/Step Time": 8.783787492662668} +{"Pretrain/Learning Rate": 4.9227364385243246e-05, "Pretrain/Loss": 2.1437478065490723, "Pretrain/Loss (Raw)": 1.98496675491333, "Pretrain/Step": 1020, "Pretrain/Step Time": 8.784610137343407} +{"Pretrain/Learning Rate": 4.922526862581333e-05, "Pretrain/Loss": 2.1424176692962646, "Pretrain/Loss (Raw)": 2.120908498764038, "Pretrain/Step": 1021, "Pretrain/Step Time": 8.78976340033114} +{"Pretrain/Learning Rate": 4.922317007261129e-05, "Pretrain/Loss": 2.14133882522583, "Pretrain/Loss (Raw)": 2.0609524250030518, "Pretrain/Step": 1022, "Pretrain/Step Time": 8.776221873238683} +{"Pretrain/Learning Rate": 4.922106872587913e-05, "Pretrain/Loss": 2.141047716140747, "Pretrain/Loss (Raw)": 2.0753676891326904, "Pretrain/Step": 1023, "Pretrain/Step Time": 8.778746396303177} +{"Pretrain/Learning Rate": 4.921896458585919e-05, "Pretrain/Loss": 2.14176082611084, "Pretrain/Loss (Raw)": 2.107316493988037, "Pretrain/Step": 1024, "Pretrain/Step Time": 8.776040581986308} +{"Pretrain/Learning Rate": 4.9216857652794125e-05, "Pretrain/Loss": 2.140446662902832, "Pretrain/Loss (Raw)": 2.0119974613189697, "Pretrain/Step": 1025, "Pretrain/Step Time": 8.774359418079257} +{"Pretrain/Learning Rate": 4.921474792692692e-05, "Pretrain/Loss": 2.1399035453796387, "Pretrain/Loss (Raw)": 1.9870375394821167, "Pretrain/Step": 1026, "Pretrain/Step Time": 8.775845838710666} +{"Pretrain/Learning Rate": 4.921263540850089e-05, "Pretrain/Loss": 2.1388444900512695, "Pretrain/Loss (Raw)": 2.021354913711548, "Pretrain/Step": 1027, "Pretrain/Step Time": 8.788645388558507} +{"Pretrain/Learning Rate": 4.921052009775965e-05, "Pretrain/Loss": 2.138176441192627, "Pretrain/Loss (Raw)": 2.076889753341675, "Pretrain/Step": 1028, "Pretrain/Step Time": 8.78833425976336} +{"Pretrain/Learning Rate": 4.9208401994947144e-05, "Pretrain/Loss": 2.1403884887695312, "Pretrain/Loss (Raw)": 2.2126266956329346, "Pretrain/Step": 1029, "Pretrain/Step Time": 8.783770272508264} +{"Pretrain/Learning Rate": 4.920628110030765e-05, "Pretrain/Loss": 2.140514612197876, "Pretrain/Loss (Raw)": 2.1369998455047607, "Pretrain/Step": 1030, "Pretrain/Step Time": 8.786677949130535} +{"Pretrain/Learning Rate": 4.920415741408575e-05, "Pretrain/Loss": 2.14162015914917, "Pretrain/Loss (Raw)": 2.2197892665863037, "Pretrain/Step": 1031, "Pretrain/Step Time": 8.783743929117918} +{"Pretrain/Learning Rate": 4.920203093652637e-05, "Pretrain/Loss": 2.141043186187744, "Pretrain/Loss (Raw)": 2.147850513458252, "Pretrain/Step": 1032, "Pretrain/Step Time": 8.785697590559721} +{"Pretrain/Learning Rate": 4.919990166787474e-05, "Pretrain/Loss": 2.1426444053649902, "Pretrain/Loss (Raw)": 2.167513608932495, "Pretrain/Step": 1033, "Pretrain/Step Time": 8.783362669870257} +{"Pretrain/Learning Rate": 4.919776960837641e-05, "Pretrain/Loss": 2.143167734146118, "Pretrain/Loss (Raw)": 2.0885093212127686, "Pretrain/Step": 1034, "Pretrain/Step Time": 8.79230297729373} +{"Pretrain/Learning Rate": 4.9195634758277264e-05, "Pretrain/Loss": 2.1416139602661133, "Pretrain/Loss (Raw)": 1.9775692224502563, "Pretrain/Step": 1035, "Pretrain/Step Time": 8.792702483013272} +{"Pretrain/Learning Rate": 4.919349711782351e-05, "Pretrain/Loss": 2.143270492553711, "Pretrain/Loss (Raw)": 2.3040237426757812, "Pretrain/Step": 1036, "Pretrain/Step Time": 8.78889661282301} +{"Pretrain/Learning Rate": 4.919135668726167e-05, "Pretrain/Loss": 2.1408393383026123, "Pretrain/Loss (Raw)": 1.956080675125122, "Pretrain/Step": 1037, "Pretrain/Step Time": 8.789338221773505} +{"Pretrain/Learning Rate": 4.9189213466838565e-05, "Pretrain/Loss": 2.13973331451416, "Pretrain/Loss (Raw)": 2.0254104137420654, "Pretrain/Step": 1038, "Pretrain/Step Time": 8.79398693703115} +{"Pretrain/Learning Rate": 4.91870674568014e-05, "Pretrain/Loss": 2.1393916606903076, "Pretrain/Loss (Raw)": 2.102060079574585, "Pretrain/Step": 1039, "Pretrain/Step Time": 8.787695119157434} +{"Pretrain/Learning Rate": 4.9184918657397625e-05, "Pretrain/Loss": 2.1413891315460205, "Pretrain/Loss (Raw)": 2.378889560699463, "Pretrain/Step": 1040, "Pretrain/Step Time": 8.784030137583613} +{"Pretrain/Learning Rate": 4.918276706887508e-05, "Pretrain/Loss": 2.139641284942627, "Pretrain/Loss (Raw)": 1.903884768486023, "Pretrain/Step": 1041, "Pretrain/Step Time": 8.78328320197761} +{"Pretrain/Learning Rate": 4.918061269148187e-05, "Pretrain/Loss": 2.13964581489563, "Pretrain/Loss (Raw)": 2.203540325164795, "Pretrain/Step": 1042, "Pretrain/Step Time": 8.791778277605772} +{"Pretrain/Learning Rate": 4.9178455525466484e-05, "Pretrain/Loss": 2.1398863792419434, "Pretrain/Loss (Raw)": 2.104599952697754, "Pretrain/Step": 1043, "Pretrain/Step Time": 8.788110131397843} +{"Pretrain/Learning Rate": 4.9176295571077655e-05, "Pretrain/Loss": 2.142155170440674, "Pretrain/Loss (Raw)": 2.209913492202759, "Pretrain/Step": 1044, "Pretrain/Step Time": 8.786726461723447} +{"Pretrain/Learning Rate": 4.917413282856451e-05, "Pretrain/Loss": 2.140080451965332, "Pretrain/Loss (Raw)": 2.066497802734375, "Pretrain/Step": 1045, "Pretrain/Step Time": 8.792375950142741} +{"Pretrain/Learning Rate": 4.917196729817645e-05, "Pretrain/Loss": 2.1409213542938232, "Pretrain/Loss (Raw)": 2.0177905559539795, "Pretrain/Step": 1046, "Pretrain/Step Time": 8.786817671731114} +{"Pretrain/Learning Rate": 4.9169798980163215e-05, "Pretrain/Loss": 2.140789031982422, "Pretrain/Loss (Raw)": 2.1054532527923584, "Pretrain/Step": 1047, "Pretrain/Step Time": 8.790873505175114} +{"Pretrain/Learning Rate": 4.916762787477487e-05, "Pretrain/Loss": 2.139401912689209, "Pretrain/Loss (Raw)": 2.084287643432617, "Pretrain/Step": 1048, "Pretrain/Step Time": 8.792501702904701} +{"Pretrain/Learning Rate": 4.91654539822618e-05, "Pretrain/Loss": 2.1403441429138184, "Pretrain/Loss (Raw)": 2.2261478900909424, "Pretrain/Step": 1049, "Pretrain/Step Time": 8.798297507688403} +{"Pretrain/Learning Rate": 4.916327730287471e-05, "Pretrain/Loss": 2.1400997638702393, "Pretrain/Loss (Raw)": 2.154176950454712, "Pretrain/Step": 1050, "Pretrain/Step Time": 8.791934415698051} +{"Pretrain/Learning Rate": 4.916109783686461e-05, "Pretrain/Loss": 2.1406002044677734, "Pretrain/Loss (Raw)": 2.2037386894226074, "Pretrain/Step": 1051, "Pretrain/Step Time": 8.795017123222351} +{"Pretrain/Learning Rate": 4.915891558448287e-05, "Pretrain/Loss": 2.139249324798584, "Pretrain/Loss (Raw)": 2.0331296920776367, "Pretrain/Step": 1052, "Pretrain/Step Time": 8.802870333194733} +{"Pretrain/Learning Rate": 4.915673054598113e-05, "Pretrain/Loss": 2.141385078430176, "Pretrain/Loss (Raw)": 2.4113075733184814, "Pretrain/Step": 1053, "Pretrain/Step Time": 8.794137883931398} +{"Pretrain/Learning Rate": 4.91545427216114e-05, "Pretrain/Loss": 2.1410634517669678, "Pretrain/Loss (Raw)": 1.9672267436981201, "Pretrain/Step": 1054, "Pretrain/Step Time": 8.799990814179182} +{"Pretrain/Learning Rate": 4.915235211162599e-05, "Pretrain/Loss": 2.141179323196411, "Pretrain/Loss (Raw)": 2.188314437866211, "Pretrain/Step": 1055, "Pretrain/Step Time": 8.798744613304734} +{"Pretrain/Learning Rate": 4.9150158716277516e-05, "Pretrain/Loss": 2.1397511959075928, "Pretrain/Loss (Raw)": 2.053849697113037, "Pretrain/Step": 1056, "Pretrain/Step Time": 8.802496541291475} +{"Pretrain/Learning Rate": 4.9147962535818935e-05, "Pretrain/Loss": 2.1389288902282715, "Pretrain/Loss (Raw)": 2.1706345081329346, "Pretrain/Step": 1057, "Pretrain/Step Time": 8.793254373595119} +{"Pretrain/Learning Rate": 4.9145763570503536e-05, "Pretrain/Loss": 2.138690948486328, "Pretrain/Loss (Raw)": 2.0855698585510254, "Pretrain/Step": 1058, "Pretrain/Step Time": 8.794821674004197} +{"Pretrain/Learning Rate": 4.914356182058491e-05, "Pretrain/Loss": 2.1388778686523438, "Pretrain/Loss (Raw)": 2.114206552505493, "Pretrain/Step": 1059, "Pretrain/Step Time": 8.797698710113764} +{"Pretrain/Learning Rate": 4.914135728631695e-05, "Pretrain/Loss": 2.138381004333496, "Pretrain/Loss (Raw)": 2.088083267211914, "Pretrain/Step": 1060, "Pretrain/Step Time": 8.796231912449002} +{"Pretrain/Learning Rate": 4.913914996795391e-05, "Pretrain/Loss": 2.139150857925415, "Pretrain/Loss (Raw)": 2.2631030082702637, "Pretrain/Step": 1061, "Pretrain/Step Time": 8.79557859711349} +{"Pretrain/Learning Rate": 4.9136939865750357e-05, "Pretrain/Loss": 2.1396431922912598, "Pretrain/Loss (Raw)": 2.0021109580993652, "Pretrain/Step": 1062, "Pretrain/Step Time": 8.79709193110466} +{"Pretrain/Learning Rate": 4.913472697996116e-05, "Pretrain/Loss": 2.139559030532837, "Pretrain/Loss (Raw)": 2.1514148712158203, "Pretrain/Step": 1063, "Pretrain/Step Time": 8.802925879135728} +{"Pretrain/Learning Rate": 4.913251131084152e-05, "Pretrain/Loss": 2.1402058601379395, "Pretrain/Loss (Raw)": 2.2761452198028564, "Pretrain/Step": 1064, "Pretrain/Step Time": 8.800115905702114} +{"Pretrain/Learning Rate": 4.9130292858646966e-05, "Pretrain/Loss": 2.139160633087158, "Pretrain/Loss (Raw)": 1.9575245380401611, "Pretrain/Step": 1065, "Pretrain/Step Time": 8.804116129875183} +{"Pretrain/Learning Rate": 4.912807162363332e-05, "Pretrain/Loss": 2.1394591331481934, "Pretrain/Loss (Raw)": 2.0947887897491455, "Pretrain/Step": 1066, "Pretrain/Step Time": 8.804153757169843} +{"Pretrain/Learning Rate": 4.912584760605677e-05, "Pretrain/Loss": 2.1386568546295166, "Pretrain/Loss (Raw)": 2.1438708305358887, "Pretrain/Step": 1067, "Pretrain/Step Time": 8.801666870713234} +{"Pretrain/Learning Rate": 4.9123620806173785e-05, "Pretrain/Loss": 2.138408660888672, "Pretrain/Loss (Raw)": 2.170548915863037, "Pretrain/Step": 1068, "Pretrain/Step Time": 8.801766358315945} +{"Pretrain/Learning Rate": 4.9121391224241174e-05, "Pretrain/Loss": 2.1383423805236816, "Pretrain/Loss (Raw)": 2.263071298599243, "Pretrain/Step": 1069, "Pretrain/Step Time": 8.811254046857357} +{"Pretrain/Learning Rate": 4.9119158860516066e-05, "Pretrain/Loss": 2.1364235877990723, "Pretrain/Loss (Raw)": 2.1262569427490234, "Pretrain/Step": 1070, "Pretrain/Step Time": 8.803066849708557} +{"Pretrain/Learning Rate": 4.9116923715255905e-05, "Pretrain/Loss": 2.136431932449341, "Pretrain/Loss (Raw)": 2.136096954345703, "Pretrain/Step": 1071, "Pretrain/Step Time": 8.805963998660445} +{"Pretrain/Learning Rate": 4.9114685788718454e-05, "Pretrain/Loss": 2.1362533569335938, "Pretrain/Loss (Raw)": 2.1788759231567383, "Pretrain/Step": 1072, "Pretrain/Step Time": 8.805579891428351} +{"Pretrain/Learning Rate": 4.9112445081161813e-05, "Pretrain/Loss": 2.1347718238830566, "Pretrain/Loss (Raw)": 1.9827781915664673, "Pretrain/Step": 1073, "Pretrain/Step Time": 8.80566587112844} +{"Pretrain/Learning Rate": 4.9110201592844376e-05, "Pretrain/Loss": 2.1362509727478027, "Pretrain/Loss (Raw)": 2.300294876098633, "Pretrain/Step": 1074, "Pretrain/Step Time": 8.801622413098812} +{"Pretrain/Learning Rate": 4.910795532402489e-05, "Pretrain/Loss": 2.134823799133301, "Pretrain/Loss (Raw)": 2.1008236408233643, "Pretrain/Step": 1075, "Pretrain/Step Time": 8.798146691173315} +{"Pretrain/Learning Rate": 4.910570627496239e-05, "Pretrain/Loss": 2.135819911956787, "Pretrain/Loss (Raw)": 2.317981243133545, "Pretrain/Step": 1076, "Pretrain/Step Time": 8.803429070860147} +{"Pretrain/Learning Rate": 4.9103454445916256e-05, "Pretrain/Loss": 2.136462450027466, "Pretrain/Loss (Raw)": 2.2469775676727295, "Pretrain/Step": 1077, "Pretrain/Step Time": 8.800117632374167} +{"Pretrain/Learning Rate": 4.910119983714616e-05, "Pretrain/Loss": 2.136296272277832, "Pretrain/Loss (Raw)": 2.209507942199707, "Pretrain/Step": 1078, "Pretrain/Step Time": 8.795778144150972} +{"Pretrain/Learning Rate": 4.909894244891214e-05, "Pretrain/Loss": 2.1351735591888428, "Pretrain/Loss (Raw)": 1.967247486114502, "Pretrain/Step": 1079, "Pretrain/Step Time": 8.79603928886354} +{"Pretrain/Learning Rate": 4.909668228147453e-05, "Pretrain/Loss": 2.1326403617858887, "Pretrain/Loss (Raw)": 1.9466733932495117, "Pretrain/Step": 1080, "Pretrain/Step Time": 8.796667044982314} +{"Pretrain/Learning Rate": 4.9094419335093966e-05, "Pretrain/Loss": 2.131552219390869, "Pretrain/Loss (Raw)": 1.968357801437378, "Pretrain/Step": 1081, "Pretrain/Step Time": 8.792354011908174} +{"Pretrain/Learning Rate": 4.909215361003142e-05, "Pretrain/Loss": 2.131741523742676, "Pretrain/Loss (Raw)": 2.1258113384246826, "Pretrain/Step": 1082, "Pretrain/Step Time": 8.790992168709636} +{"Pretrain/Learning Rate": 4.90898851065482e-05, "Pretrain/Loss": 2.1319096088409424, "Pretrain/Loss (Raw)": 2.085266590118408, "Pretrain/Step": 1083, "Pretrain/Step Time": 8.798860803246498} +{"Pretrain/Learning Rate": 4.908761382490591e-05, "Pretrain/Loss": 2.1303725242614746, "Pretrain/Loss (Raw)": 2.1024293899536133, "Pretrain/Step": 1084, "Pretrain/Step Time": 8.799663130193949} +{"Pretrain/Learning Rate": 4.908533976536649e-05, "Pretrain/Loss": 2.1301589012145996, "Pretrain/Loss (Raw)": 2.054928779602051, "Pretrain/Step": 1085, "Pretrain/Step Time": 8.791797382757068} +{"Pretrain/Learning Rate": 4.90830629281922e-05, "Pretrain/Loss": 2.1303229331970215, "Pretrain/Loss (Raw)": 2.181359052658081, "Pretrain/Step": 1086, "Pretrain/Step Time": 8.794738542288542} +{"Pretrain/Learning Rate": 4.908078331364561e-05, "Pretrain/Loss": 2.1295995712280273, "Pretrain/Loss (Raw)": 2.070260524749756, "Pretrain/Step": 1087, "Pretrain/Step Time": 8.79345589876175} +{"Pretrain/Learning Rate": 4.907850092198961e-05, "Pretrain/Loss": 2.1280174255371094, "Pretrain/Loss (Raw)": 2.139052152633667, "Pretrain/Step": 1088, "Pretrain/Step Time": 8.790081022307277} +{"Pretrain/Learning Rate": 4.9076215753487425e-05, "Pretrain/Loss": 2.127807140350342, "Pretrain/Loss (Raw)": 2.0676510334014893, "Pretrain/Step": 1089, "Pretrain/Step Time": 8.789615422487259} +{"Pretrain/Learning Rate": 4.9073927808402585e-05, "Pretrain/Loss": 2.127183437347412, "Pretrain/Loss (Raw)": 2.034663677215576, "Pretrain/Step": 1090, "Pretrain/Step Time": 8.798798909410834} +{"Pretrain/Learning Rate": 4.907163708699896e-05, "Pretrain/Loss": 2.1266322135925293, "Pretrain/Loss (Raw)": 2.1299564838409424, "Pretrain/Step": 1091, "Pretrain/Step Time": 8.795874705538154} +{"Pretrain/Learning Rate": 4.9069343589540704e-05, "Pretrain/Loss": 2.1243538856506348, "Pretrain/Loss (Raw)": 2.0024876594543457, "Pretrain/Step": 1092, "Pretrain/Step Time": 8.788775326684117} +{"Pretrain/Learning Rate": 4.906704731629233e-05, "Pretrain/Loss": 2.124558687210083, "Pretrain/Loss (Raw)": 2.1114044189453125, "Pretrain/Step": 1093, "Pretrain/Step Time": 8.787167491391301} +{"Pretrain/Learning Rate": 4.9064748267518656e-05, "Pretrain/Loss": 2.1249942779541016, "Pretrain/Loss (Raw)": 2.163499593734741, "Pretrain/Step": 1094, "Pretrain/Step Time": 8.7874475736171} +{"Pretrain/Learning Rate": 4.9062446443484813e-05, "Pretrain/Loss": 2.124558925628662, "Pretrain/Loss (Raw)": 2.1746156215667725, "Pretrain/Step": 1095, "Pretrain/Step Time": 8.787316914647818} +{"Pretrain/Learning Rate": 4.9060141844456267e-05, "Pretrain/Loss": 2.123164653778076, "Pretrain/Loss (Raw)": 1.922058343887329, "Pretrain/Step": 1096, "Pretrain/Step Time": 8.77866774611175} +{"Pretrain/Learning Rate": 4.905783447069878e-05, "Pretrain/Loss": 2.1241087913513184, "Pretrain/Loss (Raw)": 2.1467998027801514, "Pretrain/Step": 1097, "Pretrain/Step Time": 8.776488535106182} +{"Pretrain/Learning Rate": 4.905552432247846e-05, "Pretrain/Loss": 2.1233184337615967, "Pretrain/Loss (Raw)": 1.9738376140594482, "Pretrain/Step": 1098, "Pretrain/Step Time": 8.788849733769894} +{"Pretrain/Learning Rate": 4.905321140006172e-05, "Pretrain/Loss": 2.123539924621582, "Pretrain/Loss (Raw)": 2.2128515243530273, "Pretrain/Step": 1099, "Pretrain/Step Time": 8.778578599914908} +{"Pretrain/Learning Rate": 4.90508957037153e-05, "Pretrain/Loss": 2.1230573654174805, "Pretrain/Loss (Raw)": 2.1084659099578857, "Pretrain/Step": 1100, "Pretrain/Step Time": 8.780164713039994} +{"Pretrain/Learning Rate": 4.9048577233706264e-05, "Pretrain/Loss": 2.1233773231506348, "Pretrain/Loss (Raw)": 2.160183906555176, "Pretrain/Step": 1101, "Pretrain/Step Time": 8.783912794664502} +{"Pretrain/Learning Rate": 4.9046255990301965e-05, "Pretrain/Loss": 2.1229934692382812, "Pretrain/Loss (Raw)": 2.061537265777588, "Pretrain/Step": 1102, "Pretrain/Step Time": 8.783377457410097} +{"Pretrain/Learning Rate": 4.904393197377012e-05, "Pretrain/Loss": 2.1234374046325684, "Pretrain/Loss (Raw)": 2.169914960861206, "Pretrain/Step": 1103, "Pretrain/Step Time": 8.778706258162856} +{"Pretrain/Learning Rate": 4.9041605184378746e-05, "Pretrain/Loss": 2.1220688819885254, "Pretrain/Loss (Raw)": 1.9591741561889648, "Pretrain/Step": 1104, "Pretrain/Step Time": 8.78210180811584} +{"Pretrain/Learning Rate": 4.903927562239617e-05, "Pretrain/Loss": 2.1183266639709473, "Pretrain/Loss (Raw)": 2.0726382732391357, "Pretrain/Step": 1105, "Pretrain/Step Time": 8.788274737074971} +{"Pretrain/Learning Rate": 4.9036943288091066e-05, "Pretrain/Loss": 2.118743896484375, "Pretrain/Loss (Raw)": 2.1410391330718994, "Pretrain/Step": 1106, "Pretrain/Step Time": 8.778818245977163} +{"Pretrain/Learning Rate": 4.903460818173238e-05, "Pretrain/Loss": 2.1177916526794434, "Pretrain/Loss (Raw)": 2.2131357192993164, "Pretrain/Step": 1107, "Pretrain/Step Time": 8.776058416813612} +{"Pretrain/Learning Rate": 4.9032270303589435e-05, "Pretrain/Loss": 2.1168744564056396, "Pretrain/Loss (Raw)": 2.0251994132995605, "Pretrain/Step": 1108, "Pretrain/Step Time": 8.776895612478256} +{"Pretrain/Learning Rate": 4.9029929653931826e-05, "Pretrain/Loss": 2.1186540126800537, "Pretrain/Loss (Raw)": 2.230102300643921, "Pretrain/Step": 1109, "Pretrain/Step Time": 8.772604817524552} +{"Pretrain/Learning Rate": 4.90275862330295e-05, "Pretrain/Loss": 2.1181416511535645, "Pretrain/Loss (Raw)": 1.9759182929992676, "Pretrain/Step": 1110, "Pretrain/Step Time": 8.773322535678744} +{"Pretrain/Learning Rate": 4.902524004115271e-05, "Pretrain/Loss": 2.1148507595062256, "Pretrain/Loss (Raw)": 1.79117751121521, "Pretrain/Step": 1111, "Pretrain/Step Time": 8.772012675181031} +{"Pretrain/Learning Rate": 4.902289107857202e-05, "Pretrain/Loss": 2.1141693592071533, "Pretrain/Loss (Raw)": 2.14731502532959, "Pretrain/Step": 1112, "Pretrain/Step Time": 8.781102288514376} +{"Pretrain/Learning Rate": 4.9020539345558335e-05, "Pretrain/Loss": 2.1128594875335693, "Pretrain/Loss (Raw)": 2.0104308128356934, "Pretrain/Step": 1113, "Pretrain/Step Time": 8.778854688629508} +{"Pretrain/Learning Rate": 4.9018184842382866e-05, "Pretrain/Loss": 2.1131534576416016, "Pretrain/Loss (Raw)": 2.1792047023773193, "Pretrain/Step": 1114, "Pretrain/Step Time": 8.774211870506406} +{"Pretrain/Learning Rate": 4.901582756931715e-05, "Pretrain/Loss": 2.1148667335510254, "Pretrain/Loss (Raw)": 2.228832483291626, "Pretrain/Step": 1115, "Pretrain/Step Time": 8.777197984978557} +{"Pretrain/Learning Rate": 4.901346752663302e-05, "Pretrain/Loss": 2.1149487495422363, "Pretrain/Loss (Raw)": 2.040952205657959, "Pretrain/Step": 1116, "Pretrain/Step Time": 8.774091655388474} +{"Pretrain/Learning Rate": 4.9011104714602666e-05, "Pretrain/Loss": 2.1148488521575928, "Pretrain/Loss (Raw)": 2.051625967025757, "Pretrain/Step": 1117, "Pretrain/Step Time": 8.773490782827139} +{"Pretrain/Learning Rate": 4.900873913349857e-05, "Pretrain/Loss": 2.1145100593566895, "Pretrain/Loss (Raw)": 2.0119388103485107, "Pretrain/Step": 1118, "Pretrain/Step Time": 8.77639027312398} +{"Pretrain/Learning Rate": 4.9006370783593544e-05, "Pretrain/Loss": 2.114595413208008, "Pretrain/Loss (Raw)": 2.153026819229126, "Pretrain/Step": 1119, "Pretrain/Step Time": 8.778930818662047} +{"Pretrain/Learning Rate": 4.900399966516073e-05, "Pretrain/Loss": 2.115401029586792, "Pretrain/Loss (Raw)": 2.129941463470459, "Pretrain/Step": 1120, "Pretrain/Step Time": 8.781862173229456} +{"Pretrain/Learning Rate": 4.900162577847355e-05, "Pretrain/Loss": 2.117526054382324, "Pretrain/Loss (Raw)": 2.2709217071533203, "Pretrain/Step": 1121, "Pretrain/Step Time": 8.779987093061209} +{"Pretrain/Learning Rate": 4.899924912380579e-05, "Pretrain/Loss": 2.117802143096924, "Pretrain/Loss (Raw)": 2.041067361831665, "Pretrain/Step": 1122, "Pretrain/Step Time": 8.782858407124877} +{"Pretrain/Learning Rate": 4.899686970143153e-05, "Pretrain/Loss": 2.117961883544922, "Pretrain/Loss (Raw)": 2.126940965652466, "Pretrain/Step": 1123, "Pretrain/Step Time": 8.782387996092439} +{"Pretrain/Learning Rate": 4.8994487511625184e-05, "Pretrain/Loss": 2.1185286045074463, "Pretrain/Loss (Raw)": 2.247993230819702, "Pretrain/Step": 1124, "Pretrain/Step Time": 8.780546290799975} +{"Pretrain/Learning Rate": 4.899210255466147e-05, "Pretrain/Loss": 2.118882417678833, "Pretrain/Loss (Raw)": 2.166348457336426, "Pretrain/Step": 1125, "Pretrain/Step Time": 8.777770871296525} +{"Pretrain/Learning Rate": 4.898971483081543e-05, "Pretrain/Loss": 2.1178581714630127, "Pretrain/Loss (Raw)": 2.1399669647216797, "Pretrain/Step": 1126, "Pretrain/Step Time": 8.787775112316012} +{"Pretrain/Learning Rate": 4.898732434036244e-05, "Pretrain/Loss": 2.118394613265991, "Pretrain/Loss (Raw)": 2.18858003616333, "Pretrain/Step": 1127, "Pretrain/Step Time": 8.788252670317888} +{"Pretrain/Learning Rate": 4.898493108357817e-05, "Pretrain/Loss": 2.11881160736084, "Pretrain/Loss (Raw)": 2.1226985454559326, "Pretrain/Step": 1128, "Pretrain/Step Time": 8.78988147340715} +{"Pretrain/Learning Rate": 4.898253506073863e-05, "Pretrain/Loss": 2.1171884536743164, "Pretrain/Loss (Raw)": 1.978301763534546, "Pretrain/Step": 1129, "Pretrain/Step Time": 8.79256733506918} +{"Pretrain/Learning Rate": 4.8980136272120136e-05, "Pretrain/Loss": 2.1168928146362305, "Pretrain/Loss (Raw)": 2.242912769317627, "Pretrain/Step": 1130, "Pretrain/Step Time": 8.791182903572917} +{"Pretrain/Learning Rate": 4.8977734717999326e-05, "Pretrain/Loss": 2.1144137382507324, "Pretrain/Loss (Raw)": 1.9068938493728638, "Pretrain/Step": 1131, "Pretrain/Step Time": 8.792619990184903} +{"Pretrain/Learning Rate": 4.8975330398653164e-05, "Pretrain/Loss": 2.114182472229004, "Pretrain/Loss (Raw)": 2.222238779067993, "Pretrain/Step": 1132, "Pretrain/Step Time": 8.794016223400831} +{"Pretrain/Learning Rate": 4.8972923314358934e-05, "Pretrain/Loss": 2.1133079528808594, "Pretrain/Loss (Raw)": 2.0324764251708984, "Pretrain/Step": 1133, "Pretrain/Step Time": 8.78544888459146} +{"Pretrain/Learning Rate": 4.8970513465394206e-05, "Pretrain/Loss": 2.1118621826171875, "Pretrain/Loss (Raw)": 1.934942364692688, "Pretrain/Step": 1134, "Pretrain/Step Time": 8.786768862977624} +{"Pretrain/Learning Rate": 4.896810085203692e-05, "Pretrain/Loss": 2.1113219261169434, "Pretrain/Loss (Raw)": 2.178845167160034, "Pretrain/Step": 1135, "Pretrain/Step Time": 8.787571163848042} +{"Pretrain/Learning Rate": 4.896568547456531e-05, "Pretrain/Loss": 2.1138482093811035, "Pretrain/Loss (Raw)": 2.3229215145111084, "Pretrain/Step": 1136, "Pretrain/Step Time": 8.786520197987556} +{"Pretrain/Learning Rate": 4.896326733325791e-05, "Pretrain/Loss": 2.1134541034698486, "Pretrain/Loss (Raw)": 2.107311487197876, "Pretrain/Step": 1137, "Pretrain/Step Time": 8.786662423983216} +{"Pretrain/Learning Rate": 4.8960846428393615e-05, "Pretrain/Loss": 2.116577386856079, "Pretrain/Loss (Raw)": 2.3309102058410645, "Pretrain/Step": 1138, "Pretrain/Step Time": 8.785026809200644} +{"Pretrain/Learning Rate": 4.8958422760251585e-05, "Pretrain/Loss": 2.1155643463134766, "Pretrain/Loss (Raw)": 2.1733906269073486, "Pretrain/Step": 1139, "Pretrain/Step Time": 8.785135859623551} +{"Pretrain/Learning Rate": 4.8955996329111364e-05, "Pretrain/Loss": 2.116220712661743, "Pretrain/Loss (Raw)": 2.212949514389038, "Pretrain/Step": 1140, "Pretrain/Step Time": 8.778563987463713} +{"Pretrain/Learning Rate": 4.895356713525275e-05, "Pretrain/Loss": 2.115859031677246, "Pretrain/Loss (Raw)": 2.036468029022217, "Pretrain/Step": 1141, "Pretrain/Step Time": 8.788858758285642} +{"Pretrain/Learning Rate": 4.895113517895591e-05, "Pretrain/Loss": 2.11708402633667, "Pretrain/Loss (Raw)": 2.075042247772217, "Pretrain/Step": 1142, "Pretrain/Step Time": 8.79016998410225} +{"Pretrain/Learning Rate": 4.8948700460501294e-05, "Pretrain/Loss": 2.1192760467529297, "Pretrain/Loss (Raw)": 2.3434324264526367, "Pretrain/Step": 1143, "Pretrain/Step Time": 8.788167433813214} +{"Pretrain/Learning Rate": 4.8946262980169686e-05, "Pretrain/Loss": 2.1190567016601562, "Pretrain/Loss (Raw)": 2.070683002471924, "Pretrain/Step": 1144, "Pretrain/Step Time": 8.786292590200901} +{"Pretrain/Learning Rate": 4.894382273824221e-05, "Pretrain/Loss": 2.118213653564453, "Pretrain/Loss (Raw)": 2.197801113128662, "Pretrain/Step": 1145, "Pretrain/Step Time": 8.786586213856936} +{"Pretrain/Learning Rate": 4.894137973500025e-05, "Pretrain/Loss": 2.1177234649658203, "Pretrain/Loss (Raw)": 2.2245571613311768, "Pretrain/Step": 1146, "Pretrain/Step Time": 8.787147523835301} +{"Pretrain/Learning Rate": 4.893893397072558e-05, "Pretrain/Loss": 2.1180129051208496, "Pretrain/Loss (Raw)": 2.287445068359375, "Pretrain/Step": 1147, "Pretrain/Step Time": 8.788671484217048} +{"Pretrain/Learning Rate": 4.893648544570022e-05, "Pretrain/Loss": 2.119480848312378, "Pretrain/Loss (Raw)": 2.172854423522949, "Pretrain/Step": 1148, "Pretrain/Step Time": 8.785717561841011} +{"Pretrain/Learning Rate": 4.893403416020658e-05, "Pretrain/Loss": 2.119184970855713, "Pretrain/Loss (Raw)": 2.0830297470092773, "Pretrain/Step": 1149, "Pretrain/Step Time": 8.788817262277007} +{"Pretrain/Learning Rate": 4.893158011452734e-05, "Pretrain/Loss": 2.119055986404419, "Pretrain/Loss (Raw)": 2.0444605350494385, "Pretrain/Step": 1150, "Pretrain/Step Time": 8.786333398893476} +{"Pretrain/Learning Rate": 4.8929123308945505e-05, "Pretrain/Loss": 2.1198172569274902, "Pretrain/Loss (Raw)": 2.1728291511535645, "Pretrain/Step": 1151, "Pretrain/Step Time": 8.79087357595563} +{"Pretrain/Learning Rate": 4.8926663743744414e-05, "Pretrain/Loss": 2.118623971939087, "Pretrain/Loss (Raw)": 1.954558253288269, "Pretrain/Step": 1152, "Pretrain/Step Time": 8.79080168530345} +{"Pretrain/Learning Rate": 4.892420141920772e-05, "Pretrain/Loss": 2.1180520057678223, "Pretrain/Loss (Raw)": 1.938793420791626, "Pretrain/Step": 1153, "Pretrain/Step Time": 8.788262853398919} +{"Pretrain/Learning Rate": 4.8921736335619385e-05, "Pretrain/Loss": 2.1188650131225586, "Pretrain/Loss (Raw)": 2.0910911560058594, "Pretrain/Step": 1154, "Pretrain/Step Time": 8.790884491056204} +{"Pretrain/Learning Rate": 4.8919268493263684e-05, "Pretrain/Loss": 2.1184091567993164, "Pretrain/Loss (Raw)": 1.9630107879638672, "Pretrain/Step": 1155, "Pretrain/Step Time": 8.78128475137055} +{"Pretrain/Learning Rate": 4.891679789242524e-05, "Pretrain/Loss": 2.119126558303833, "Pretrain/Loss (Raw)": 2.168712615966797, "Pretrain/Step": 1156, "Pretrain/Step Time": 8.782943794503808} +{"Pretrain/Learning Rate": 4.891432453338895e-05, "Pretrain/Loss": 2.1193645000457764, "Pretrain/Loss (Raw)": 2.2430953979492188, "Pretrain/Step": 1157, "Pretrain/Step Time": 8.77823313511908} +{"Pretrain/Learning Rate": 4.8911848416440075e-05, "Pretrain/Loss": 2.1207969188690186, "Pretrain/Loss (Raw)": 2.3203420639038086, "Pretrain/Step": 1158, "Pretrain/Step Time": 8.785026416182518} +{"Pretrain/Learning Rate": 4.890936954186416e-05, "Pretrain/Loss": 2.119464874267578, "Pretrain/Loss (Raw)": 2.0493154525756836, "Pretrain/Step": 1159, "Pretrain/Step Time": 8.787235610187054} +{"Pretrain/Learning Rate": 4.890688790994709e-05, "Pretrain/Loss": 2.119473457336426, "Pretrain/Loss (Raw)": 2.1489012241363525, "Pretrain/Step": 1160, "Pretrain/Step Time": 8.784238889813423} +{"Pretrain/Learning Rate": 4.890440352097505e-05, "Pretrain/Loss": 2.1203370094299316, "Pretrain/Loss (Raw)": 2.2780909538269043, "Pretrain/Step": 1161, "Pretrain/Step Time": 8.792678052559495} +{"Pretrain/Learning Rate": 4.8901916375234556e-05, "Pretrain/Loss": 2.1204991340637207, "Pretrain/Loss (Raw)": 2.1092512607574463, "Pretrain/Step": 1162, "Pretrain/Step Time": 8.782902145758271} +{"Pretrain/Learning Rate": 4.889942647301243e-05, "Pretrain/Loss": 2.121011257171631, "Pretrain/Loss (Raw)": 2.0431156158447266, "Pretrain/Step": 1163, "Pretrain/Step Time": 8.787562601268291} +{"Pretrain/Learning Rate": 4.8896933814595834e-05, "Pretrain/Loss": 2.119032859802246, "Pretrain/Loss (Raw)": 2.0507712364196777, "Pretrain/Step": 1164, "Pretrain/Step Time": 8.78827310912311} +{"Pretrain/Learning Rate": 4.8894438400272224e-05, "Pretrain/Loss": 2.1211190223693848, "Pretrain/Loss (Raw)": 2.223109245300293, "Pretrain/Step": 1165, "Pretrain/Step Time": 8.786838194355369} +{"Pretrain/Learning Rate": 4.889194023032938e-05, "Pretrain/Loss": 2.12215518951416, "Pretrain/Loss (Raw)": 2.1580731868743896, "Pretrain/Step": 1166, "Pretrain/Step Time": 8.780326098203659} +{"Pretrain/Learning Rate": 4.8889439305055406e-05, "Pretrain/Loss": 2.1214823722839355, "Pretrain/Loss (Raw)": 2.0159499645233154, "Pretrain/Step": 1167, "Pretrain/Step Time": 8.786594590172172} +{"Pretrain/Learning Rate": 4.8886935624738715e-05, "Pretrain/Loss": 2.1194534301757812, "Pretrain/Loss (Raw)": 2.119147300720215, "Pretrain/Step": 1168, "Pretrain/Step Time": 8.794056192040443} +{"Pretrain/Learning Rate": 4.888442918966806e-05, "Pretrain/Loss": 2.1213696002960205, "Pretrain/Loss (Raw)": 2.149158477783203, "Pretrain/Step": 1169, "Pretrain/Step Time": 8.790830856189132} +{"Pretrain/Learning Rate": 4.888192000013248e-05, "Pretrain/Loss": 2.1210947036743164, "Pretrain/Loss (Raw)": 2.168354034423828, "Pretrain/Step": 1170, "Pretrain/Step Time": 8.78646656498313} +{"Pretrain/Learning Rate": 4.887940805642135e-05, "Pretrain/Loss": 2.1212220191955566, "Pretrain/Loss (Raw)": 2.1208994388580322, "Pretrain/Step": 1171, "Pretrain/Step Time": 8.788288943469524} +{"Pretrain/Learning Rate": 4.887689335882436e-05, "Pretrain/Loss": 2.1195781230926514, "Pretrain/Loss (Raw)": 1.999512791633606, "Pretrain/Step": 1172, "Pretrain/Step Time": 8.790793312713504} +{"Pretrain/Learning Rate": 4.8874375907631506e-05, "Pretrain/Loss": 2.120011806488037, "Pretrain/Loss (Raw)": 2.122002601623535, "Pretrain/Step": 1173, "Pretrain/Step Time": 8.78707816824317} +{"Pretrain/Learning Rate": 4.887185570313314e-05, "Pretrain/Loss": 2.119236469268799, "Pretrain/Loss (Raw)": 1.9185333251953125, "Pretrain/Step": 1174, "Pretrain/Step Time": 8.788333216682076} +{"Pretrain/Learning Rate": 4.886933274561988e-05, "Pretrain/Loss": 2.119882106781006, "Pretrain/Loss (Raw)": 2.188119888305664, "Pretrain/Step": 1175, "Pretrain/Step Time": 8.791600590571761} +{"Pretrain/Learning Rate": 4.886680703538269e-05, "Pretrain/Loss": 2.120291233062744, "Pretrain/Loss (Raw)": 2.1366512775421143, "Pretrain/Step": 1176, "Pretrain/Step Time": 8.789931857958436} +{"Pretrain/Learning Rate": 4.886427857271284e-05, "Pretrain/Loss": 2.1195836067199707, "Pretrain/Loss (Raw)": 2.1355419158935547, "Pretrain/Step": 1177, "Pretrain/Step Time": 8.781254261732101} +{"Pretrain/Learning Rate": 4.886174735790194e-05, "Pretrain/Loss": 2.1186599731445312, "Pretrain/Loss (Raw)": 2.035964012145996, "Pretrain/Step": 1178, "Pretrain/Step Time": 8.785017827525735} +{"Pretrain/Learning Rate": 4.88592133912419e-05, "Pretrain/Loss": 2.1181559562683105, "Pretrain/Loss (Raw)": 2.1392171382904053, "Pretrain/Step": 1179, "Pretrain/Step Time": 8.784572783857584} +{"Pretrain/Learning Rate": 4.885667667302494e-05, "Pretrain/Loss": 2.1189074516296387, "Pretrain/Loss (Raw)": 2.1293091773986816, "Pretrain/Step": 1180, "Pretrain/Step Time": 8.779065603390336} +{"Pretrain/Learning Rate": 4.88541372035436e-05, "Pretrain/Loss": 2.1149444580078125, "Pretrain/Loss (Raw)": 1.904061198234558, "Pretrain/Step": 1181, "Pretrain/Step Time": 8.78104055300355} +{"Pretrain/Learning Rate": 4.885159498309077e-05, "Pretrain/Loss": 2.1165356636047363, "Pretrain/Loss (Raw)": 2.170884609222412, "Pretrain/Step": 1182, "Pretrain/Step Time": 8.78986220434308} +{"Pretrain/Learning Rate": 4.884905001195961e-05, "Pretrain/Loss": 2.115556478500366, "Pretrain/Loss (Raw)": 2.062999725341797, "Pretrain/Step": 1183, "Pretrain/Step Time": 8.785570131614804} +{"Pretrain/Learning Rate": 4.884650229044361e-05, "Pretrain/Loss": 2.1164088249206543, "Pretrain/Loss (Raw)": 2.1629481315612793, "Pretrain/Step": 1184, "Pretrain/Step Time": 8.78240062482655} +{"Pretrain/Learning Rate": 4.884395181883661e-05, "Pretrain/Loss": 2.115879774093628, "Pretrain/Loss (Raw)": 2.1028971672058105, "Pretrain/Step": 1185, "Pretrain/Step Time": 8.789871139451861} +{"Pretrain/Learning Rate": 4.8841398597432725e-05, "Pretrain/Loss": 2.1192398071289062, "Pretrain/Loss (Raw)": 2.5156726837158203, "Pretrain/Step": 1186, "Pretrain/Step Time": 8.78687541000545} +{"Pretrain/Learning Rate": 4.883884262652641e-05, "Pretrain/Loss": 2.1178817749023438, "Pretrain/Loss (Raw)": 1.9403783082962036, "Pretrain/Step": 1187, "Pretrain/Step Time": 8.780710900202394} +{"Pretrain/Learning Rate": 4.883628390641243e-05, "Pretrain/Loss": 2.118473529815674, "Pretrain/Loss (Raw)": 2.163815498352051, "Pretrain/Step": 1188, "Pretrain/Step Time": 8.779324725270271} +{"Pretrain/Learning Rate": 4.883372243738588e-05, "Pretrain/Loss": 2.1163525581359863, "Pretrain/Loss (Raw)": 1.9916025400161743, "Pretrain/Step": 1189, "Pretrain/Step Time": 8.792352981865406} +{"Pretrain/Learning Rate": 4.883115821974213e-05, "Pretrain/Loss": 2.117377758026123, "Pretrain/Loss (Raw)": 2.1333577632904053, "Pretrain/Step": 1190, "Pretrain/Step Time": 8.790289772674441} +{"Pretrain/Learning Rate": 4.8828591253776937e-05, "Pretrain/Loss": 2.1184301376342773, "Pretrain/Loss (Raw)": 2.2860989570617676, "Pretrain/Step": 1191, "Pretrain/Step Time": 8.78569227643311} +{"Pretrain/Learning Rate": 4.88260215397863e-05, "Pretrain/Loss": 2.1171112060546875, "Pretrain/Loss (Raw)": 2.107327938079834, "Pretrain/Step": 1192, "Pretrain/Step Time": 8.782759020105004} +{"Pretrain/Learning Rate": 4.882344907806659e-05, "Pretrain/Loss": 2.1180005073547363, "Pretrain/Loss (Raw)": 2.071377992630005, "Pretrain/Step": 1193, "Pretrain/Step Time": 8.778459949418902} +{"Pretrain/Learning Rate": 4.882087386891448e-05, "Pretrain/Loss": 2.1189732551574707, "Pretrain/Loss (Raw)": 2.21931791305542, "Pretrain/Step": 1194, "Pretrain/Step Time": 8.775932459160686} +{"Pretrain/Learning Rate": 4.8818295912626955e-05, "Pretrain/Loss": 2.1172659397125244, "Pretrain/Loss (Raw)": 1.9252989292144775, "Pretrain/Step": 1195, "Pretrain/Step Time": 8.773235009983182} +{"Pretrain/Learning Rate": 4.88157152095013e-05, "Pretrain/Loss": 2.116626262664795, "Pretrain/Loss (Raw)": 2.0886926651000977, "Pretrain/Step": 1196, "Pretrain/Step Time": 8.773337533697486} +{"Pretrain/Learning Rate": 4.881313175983515e-05, "Pretrain/Loss": 2.115342855453491, "Pretrain/Loss (Raw)": 2.098792791366577, "Pretrain/Step": 1197, "Pretrain/Step Time": 8.769324166700244} +{"Pretrain/Learning Rate": 4.881054556392642e-05, "Pretrain/Loss": 2.114394187927246, "Pretrain/Loss (Raw)": 2.0048062801361084, "Pretrain/Step": 1198, "Pretrain/Step Time": 8.771757818758488} +{"Pretrain/Learning Rate": 4.8807956622073394e-05, "Pretrain/Loss": 2.1142349243164062, "Pretrain/Loss (Raw)": 2.1157374382019043, "Pretrain/Step": 1199, "Pretrain/Step Time": 8.770216116681695} +{"Pretrain/Learning Rate": 4.880536493457461e-05, "Pretrain/Loss": 2.113833427429199, "Pretrain/Loss (Raw)": 2.1274755001068115, "Pretrain/Step": 1200, "Pretrain/Step Time": 8.773980725556612} +{"Pretrain/Learning Rate": 4.880277050172897e-05, "Pretrain/Loss": 2.115508556365967, "Pretrain/Loss (Raw)": 2.1971757411956787, "Pretrain/Step": 1201, "Pretrain/Step Time": 8.77646279707551} +{"Pretrain/Learning Rate": 4.880017332383567e-05, "Pretrain/Loss": 2.1133551597595215, "Pretrain/Loss (Raw)": 2.0246548652648926, "Pretrain/Step": 1202, "Pretrain/Step Time": 8.77591260895133} +{"Pretrain/Learning Rate": 4.879757340119425e-05, "Pretrain/Loss": 2.1140382289886475, "Pretrain/Loss (Raw)": 2.1882755756378174, "Pretrain/Step": 1203, "Pretrain/Step Time": 8.78872750326991} +{"Pretrain/Learning Rate": 4.879497073410451e-05, "Pretrain/Loss": 2.112738609313965, "Pretrain/Loss (Raw)": 2.1516480445861816, "Pretrain/Step": 1204, "Pretrain/Step Time": 8.782564988359809} +{"Pretrain/Learning Rate": 4.8792365322866626e-05, "Pretrain/Loss": 2.1118311882019043, "Pretrain/Loss (Raw)": 2.1308088302612305, "Pretrain/Step": 1205, "Pretrain/Step Time": 8.784510808065534} +{"Pretrain/Learning Rate": 4.878975716778106e-05, "Pretrain/Loss": 2.1114954948425293, "Pretrain/Loss (Raw)": 2.166532039642334, "Pretrain/Step": 1206, "Pretrain/Step Time": 8.785157985985279} +{"Pretrain/Learning Rate": 4.878714626914859e-05, "Pretrain/Loss": 2.1115126609802246, "Pretrain/Loss (Raw)": 1.9694396257400513, "Pretrain/Step": 1207, "Pretrain/Step Time": 8.790684094652534} +{"Pretrain/Learning Rate": 4.878453262727033e-05, "Pretrain/Loss": 2.1136715412139893, "Pretrain/Loss (Raw)": 2.2230124473571777, "Pretrain/Step": 1208, "Pretrain/Step Time": 8.785628663375974} +{"Pretrain/Learning Rate": 4.878191624244769e-05, "Pretrain/Loss": 2.1146178245544434, "Pretrain/Loss (Raw)": 2.0895166397094727, "Pretrain/Step": 1209, "Pretrain/Step Time": 8.784609800204635} +{"Pretrain/Learning Rate": 4.8779297114982406e-05, "Pretrain/Loss": 2.1138675212860107, "Pretrain/Loss (Raw)": 2.0297691822052, "Pretrain/Step": 1210, "Pretrain/Step Time": 8.790873562917113} +{"Pretrain/Learning Rate": 4.877667524517652e-05, "Pretrain/Loss": 2.113694667816162, "Pretrain/Loss (Raw)": 2.063098430633545, "Pretrain/Step": 1211, "Pretrain/Step Time": 8.777222590520978} +{"Pretrain/Learning Rate": 4.877405063333241e-05, "Pretrain/Loss": 2.1143198013305664, "Pretrain/Loss (Raw)": 2.1824705600738525, "Pretrain/Step": 1212, "Pretrain/Step Time": 8.781313238665462} +{"Pretrain/Learning Rate": 4.877142327975276e-05, "Pretrain/Loss": 2.114776611328125, "Pretrain/Loss (Raw)": 2.1133995056152344, "Pretrain/Step": 1213, "Pretrain/Step Time": 8.781863871961832} +{"Pretrain/Learning Rate": 4.8768793184740556e-05, "Pretrain/Loss": 2.1145358085632324, "Pretrain/Loss (Raw)": 2.1505117416381836, "Pretrain/Step": 1214, "Pretrain/Step Time": 8.781987614929676} +{"Pretrain/Learning Rate": 4.8766160348599125e-05, "Pretrain/Loss": 2.1127514839172363, "Pretrain/Loss (Raw)": 1.841894268989563, "Pretrain/Step": 1215, "Pretrain/Step Time": 8.783807130530477} +{"Pretrain/Learning Rate": 4.876352477163209e-05, "Pretrain/Loss": 2.1125521659851074, "Pretrain/Loss (Raw)": 2.1135363578796387, "Pretrain/Step": 1216, "Pretrain/Step Time": 8.783323295414448} +{"Pretrain/Learning Rate": 4.8760886454143394e-05, "Pretrain/Loss": 2.1119933128356934, "Pretrain/Loss (Raw)": 1.9961507320404053, "Pretrain/Step": 1217, "Pretrain/Step Time": 8.792119715362787} +{"Pretrain/Learning Rate": 4.875824539643731e-05, "Pretrain/Loss": 2.114325523376465, "Pretrain/Loss (Raw)": 2.3331644535064697, "Pretrain/Step": 1218, "Pretrain/Step Time": 8.781450353562832} +{"Pretrain/Learning Rate": 4.8755601598818427e-05, "Pretrain/Loss": 2.11458420753479, "Pretrain/Loss (Raw)": 2.1630499362945557, "Pretrain/Step": 1219, "Pretrain/Step Time": 8.78790020942688} +{"Pretrain/Learning Rate": 4.875295506159161e-05, "Pretrain/Loss": 2.1147263050079346, "Pretrain/Loss (Raw)": 2.0207040309906006, "Pretrain/Step": 1220, "Pretrain/Step Time": 8.784734623506665} +{"Pretrain/Learning Rate": 4.87503057850621e-05, "Pretrain/Loss": 2.1146414279937744, "Pretrain/Loss (Raw)": 2.1005287170410156, "Pretrain/Step": 1221, "Pretrain/Step Time": 8.791437143459916} +{"Pretrain/Learning Rate": 4.874765376953541e-05, "Pretrain/Loss": 2.1144189834594727, "Pretrain/Loss (Raw)": 2.1349971294403076, "Pretrain/Step": 1222, "Pretrain/Step Time": 8.789732789620757} +{"Pretrain/Learning Rate": 4.874499901531737e-05, "Pretrain/Loss": 2.1141934394836426, "Pretrain/Loss (Raw)": 2.1457858085632324, "Pretrain/Step": 1223, "Pretrain/Step Time": 8.793693378567696} +{"Pretrain/Learning Rate": 4.874234152271418e-05, "Pretrain/Loss": 2.115929126739502, "Pretrain/Loss (Raw)": 2.1441962718963623, "Pretrain/Step": 1224, "Pretrain/Step Time": 8.799314878880978} +{"Pretrain/Learning Rate": 4.8739681292032266e-05, "Pretrain/Loss": 2.1165692806243896, "Pretrain/Loss (Raw)": 2.228769302368164, "Pretrain/Step": 1225, "Pretrain/Step Time": 8.800489852204919} +{"Pretrain/Learning Rate": 4.8737018323578445e-05, "Pretrain/Loss": 2.118290901184082, "Pretrain/Loss (Raw)": 2.1942200660705566, "Pretrain/Step": 1226, "Pretrain/Step Time": 8.790420157834888} +{"Pretrain/Learning Rate": 4.873435261765982e-05, "Pretrain/Loss": 2.117936372756958, "Pretrain/Loss (Raw)": 2.1674258708953857, "Pretrain/Step": 1227, "Pretrain/Step Time": 8.792501118034124} +{"Pretrain/Learning Rate": 4.873168417458381e-05, "Pretrain/Loss": 2.116990566253662, "Pretrain/Loss (Raw)": 1.9874275922775269, "Pretrain/Step": 1228, "Pretrain/Step Time": 8.794827803969383} +{"Pretrain/Learning Rate": 4.8729012994658166e-05, "Pretrain/Loss": 2.1162869930267334, "Pretrain/Loss (Raw)": 2.070117235183716, "Pretrain/Step": 1229, "Pretrain/Step Time": 8.789186174049973} +{"Pretrain/Learning Rate": 4.8726339078190914e-05, "Pretrain/Loss": 2.116379737854004, "Pretrain/Loss (Raw)": 2.073397636413574, "Pretrain/Step": 1230, "Pretrain/Step Time": 8.793417289853096} +{"Pretrain/Learning Rate": 4.872366242549044e-05, "Pretrain/Loss": 2.115635395050049, "Pretrain/Loss (Raw)": 2.0746443271636963, "Pretrain/Step": 1231, "Pretrain/Step Time": 8.795375609770417} +{"Pretrain/Learning Rate": 4.872098303686543e-05, "Pretrain/Loss": 2.1162092685699463, "Pretrain/Loss (Raw)": 2.032627820968628, "Pretrain/Step": 1232, "Pretrain/Step Time": 8.793430518358946} +{"Pretrain/Learning Rate": 4.871830091262488e-05, "Pretrain/Loss": 2.1178317070007324, "Pretrain/Loss (Raw)": 2.280336856842041, "Pretrain/Step": 1233, "Pretrain/Step Time": 8.790918957442045} +{"Pretrain/Learning Rate": 4.8715616053078095e-05, "Pretrain/Loss": 2.1193063259124756, "Pretrain/Loss (Raw)": 2.329784870147705, "Pretrain/Step": 1234, "Pretrain/Step Time": 8.795147923752666} +{"Pretrain/Learning Rate": 4.871292845853472e-05, "Pretrain/Loss": 2.1185765266418457, "Pretrain/Loss (Raw)": 2.1196746826171875, "Pretrain/Step": 1235, "Pretrain/Step Time": 8.795529402792454} +{"Pretrain/Learning Rate": 4.87102381293047e-05, "Pretrain/Loss": 2.1195411682128906, "Pretrain/Loss (Raw)": 2.1487152576446533, "Pretrain/Step": 1236, "Pretrain/Step Time": 8.79256622493267} +{"Pretrain/Learning Rate": 4.870754506569829e-05, "Pretrain/Loss": 2.118462085723877, "Pretrain/Loss (Raw)": 2.0919809341430664, "Pretrain/Step": 1237, "Pretrain/Step Time": 8.793508395552635} +{"Pretrain/Learning Rate": 4.870484926802606e-05, "Pretrain/Loss": 2.1195974349975586, "Pretrain/Loss (Raw)": 2.121246337890625, "Pretrain/Step": 1238, "Pretrain/Step Time": 8.792439954355359} +{"Pretrain/Learning Rate": 4.8702150736598925e-05, "Pretrain/Loss": 2.121320962905884, "Pretrain/Loss (Raw)": 2.011775016784668, "Pretrain/Step": 1239, "Pretrain/Step Time": 8.803893506526947} +{"Pretrain/Learning Rate": 4.8699449471728075e-05, "Pretrain/Loss": 2.120767831802368, "Pretrain/Loss (Raw)": 2.0764968395233154, "Pretrain/Step": 1240, "Pretrain/Step Time": 8.795064570382237} +{"Pretrain/Learning Rate": 4.869674547372504e-05, "Pretrain/Loss": 2.1211018562316895, "Pretrain/Loss (Raw)": 2.0532174110412598, "Pretrain/Step": 1241, "Pretrain/Step Time": 8.796047750860453} +{"Pretrain/Learning Rate": 4.8694038742901646e-05, "Pretrain/Loss": 2.1189942359924316, "Pretrain/Loss (Raw)": 1.9094040393829346, "Pretrain/Step": 1242, "Pretrain/Step Time": 8.797623751685023} +{"Pretrain/Learning Rate": 4.869132927957007e-05, "Pretrain/Loss": 2.117593288421631, "Pretrain/Loss (Raw)": 2.0495288372039795, "Pretrain/Step": 1243, "Pretrain/Step Time": 8.797924609854817} +{"Pretrain/Learning Rate": 4.868861708404275e-05, "Pretrain/Loss": 2.1184258460998535, "Pretrain/Loss (Raw)": 2.1475114822387695, "Pretrain/Step": 1244, "Pretrain/Step Time": 8.798144813627005} +{"Pretrain/Learning Rate": 4.868590215663248e-05, "Pretrain/Loss": 2.119919776916504, "Pretrain/Loss (Raw)": 2.24283504486084, "Pretrain/Step": 1245, "Pretrain/Step Time": 8.798858720809221} +{"Pretrain/Learning Rate": 4.8683184497652366e-05, "Pretrain/Loss": 2.1201372146606445, "Pretrain/Loss (Raw)": 2.039788246154785, "Pretrain/Step": 1246, "Pretrain/Step Time": 8.797097902745008} +{"Pretrain/Learning Rate": 4.868046410741582e-05, "Pretrain/Loss": 2.1201391220092773, "Pretrain/Loss (Raw)": 2.153247117996216, "Pretrain/Step": 1247, "Pretrain/Step Time": 8.79724894464016} +{"Pretrain/Learning Rate": 4.867774098623657e-05, "Pretrain/Loss": 2.120307445526123, "Pretrain/Loss (Raw)": 2.151479959487915, "Pretrain/Step": 1248, "Pretrain/Step Time": 8.796590419486165} +{"Pretrain/Learning Rate": 4.8675015134428654e-05, "Pretrain/Loss": 2.1201834678649902, "Pretrain/Loss (Raw)": 2.255098581314087, "Pretrain/Step": 1249, "Pretrain/Step Time": 8.802282465621829} +{"Pretrain/Learning Rate": 4.867228655230643e-05, "Pretrain/Loss": 2.120969772338867, "Pretrain/Loss (Raw)": 2.141716718673706, "Pretrain/Step": 1250, "Pretrain/Step Time": 8.799743846058846} +{"Pretrain/Learning Rate": 4.866955524018457e-05, "Pretrain/Loss": 2.121370792388916, "Pretrain/Loss (Raw)": 2.178220272064209, "Pretrain/Step": 1251, "Pretrain/Step Time": 8.798180609941483} +{"Pretrain/Learning Rate": 4.866682119837807e-05, "Pretrain/Loss": 2.121715545654297, "Pretrain/Loss (Raw)": 2.292149782180786, "Pretrain/Step": 1252, "Pretrain/Step Time": 8.799492189660668} +{"Pretrain/Learning Rate": 4.866408442720223e-05, "Pretrain/Loss": 2.1206345558166504, "Pretrain/Loss (Raw)": 2.0279908180236816, "Pretrain/Step": 1253, "Pretrain/Step Time": 8.804506033658981} +{"Pretrain/Learning Rate": 4.8661344926972666e-05, "Pretrain/Loss": 2.120732307434082, "Pretrain/Loss (Raw)": 2.1524667739868164, "Pretrain/Step": 1254, "Pretrain/Step Time": 8.790460370481014} +{"Pretrain/Learning Rate": 4.8658602698005294e-05, "Pretrain/Loss": 2.1201305389404297, "Pretrain/Loss (Raw)": 2.1115715503692627, "Pretrain/Step": 1255, "Pretrain/Step Time": 8.792577749118209} +{"Pretrain/Learning Rate": 4.8655857740616395e-05, "Pretrain/Loss": 2.121181011199951, "Pretrain/Loss (Raw)": 2.2571535110473633, "Pretrain/Step": 1256, "Pretrain/Step Time": 8.795103263109922} +{"Pretrain/Learning Rate": 4.8653110055122496e-05, "Pretrain/Loss": 2.1216254234313965, "Pretrain/Loss (Raw)": 2.0351834297180176, "Pretrain/Step": 1257, "Pretrain/Step Time": 8.792799163609743} +{"Pretrain/Learning Rate": 4.8650359641840495e-05, "Pretrain/Loss": 2.1215524673461914, "Pretrain/Loss (Raw)": 2.233588933944702, "Pretrain/Step": 1258, "Pretrain/Step Time": 8.793107960373163} +{"Pretrain/Learning Rate": 4.864760650108758e-05, "Pretrain/Loss": 2.1228907108306885, "Pretrain/Loss (Raw)": 2.0781760215759277, "Pretrain/Step": 1259, "Pretrain/Step Time": 8.796875588595867} +{"Pretrain/Learning Rate": 4.864485063318125e-05, "Pretrain/Loss": 2.122138738632202, "Pretrain/Loss (Raw)": 2.1259846687316895, "Pretrain/Step": 1260, "Pretrain/Step Time": 8.80471831932664} +{"Pretrain/Learning Rate": 4.864209203843932e-05, "Pretrain/Loss": 2.124083995819092, "Pretrain/Loss (Raw)": 2.2814524173736572, "Pretrain/Step": 1261, "Pretrain/Step Time": 8.801275797188282} +{"Pretrain/Learning Rate": 4.8639330717179946e-05, "Pretrain/Loss": 2.124612331390381, "Pretrain/Loss (Raw)": 2.0025737285614014, "Pretrain/Step": 1262, "Pretrain/Step Time": 8.800061825662851} +{"Pretrain/Learning Rate": 4.863656666972154e-05, "Pretrain/Loss": 2.124577045440674, "Pretrain/Loss (Raw)": 2.1743414402008057, "Pretrain/Step": 1263, "Pretrain/Step Time": 8.805500341579318} +{"Pretrain/Learning Rate": 4.86337998963829e-05, "Pretrain/Loss": 2.1220898628234863, "Pretrain/Loss (Raw)": 2.004560947418213, "Pretrain/Step": 1264, "Pretrain/Step Time": 8.80672780610621} +{"Pretrain/Learning Rate": 4.863103039748309e-05, "Pretrain/Loss": 2.1211624145507812, "Pretrain/Loss (Raw)": 1.9886001348495483, "Pretrain/Step": 1265, "Pretrain/Step Time": 8.802477626129985} +{"Pretrain/Learning Rate": 4.86282581733415e-05, "Pretrain/Loss": 2.119619846343994, "Pretrain/Loss (Raw)": 2.1334621906280518, "Pretrain/Step": 1266, "Pretrain/Step Time": 8.805193465203047} +{"Pretrain/Learning Rate": 4.8625483224277835e-05, "Pretrain/Loss": 2.1185030937194824, "Pretrain/Loss (Raw)": 2.030416250228882, "Pretrain/Step": 1267, "Pretrain/Step Time": 8.804088868200779} +{"Pretrain/Learning Rate": 4.8622705550612126e-05, "Pretrain/Loss": 2.116764545440674, "Pretrain/Loss (Raw)": 1.9904478788375854, "Pretrain/Step": 1268, "Pretrain/Step Time": 8.805354172363877} +{"Pretrain/Learning Rate": 4.861992515266469e-05, "Pretrain/Loss": 2.116434097290039, "Pretrain/Loss (Raw)": 1.9941599369049072, "Pretrain/Step": 1269, "Pretrain/Step Time": 8.794580908492208} +{"Pretrain/Learning Rate": 4.8617142030756194e-05, "Pretrain/Loss": 2.1175336837768555, "Pretrain/Loss (Raw)": 2.215806722640991, "Pretrain/Step": 1270, "Pretrain/Step Time": 8.800745781511068} +{"Pretrain/Learning Rate": 4.8614356185207575e-05, "Pretrain/Loss": 2.1159961223602295, "Pretrain/Loss (Raw)": 2.1466267108917236, "Pretrain/Step": 1271, "Pretrain/Step Time": 8.80088759586215} +{"Pretrain/Learning Rate": 4.861156761634014e-05, "Pretrain/Loss": 2.117936611175537, "Pretrain/Loss (Raw)": 2.3190529346466064, "Pretrain/Step": 1272, "Pretrain/Step Time": 8.801077319309115} +{"Pretrain/Learning Rate": 4.860877632447546e-05, "Pretrain/Loss": 2.118075132369995, "Pretrain/Loss (Raw)": 2.2155230045318604, "Pretrain/Step": 1273, "Pretrain/Step Time": 8.797810696065426} +{"Pretrain/Learning Rate": 4.8605982309935446e-05, "Pretrain/Loss": 2.116469383239746, "Pretrain/Loss (Raw)": 2.019016981124878, "Pretrain/Step": 1274, "Pretrain/Step Time": 8.811885623261333} +{"Pretrain/Learning Rate": 4.860318557304232e-05, "Pretrain/Loss": 2.1157240867614746, "Pretrain/Loss (Raw)": 2.192051410675049, "Pretrain/Step": 1275, "Pretrain/Step Time": 8.810077022761106} +{"Pretrain/Learning Rate": 4.860038611411861e-05, "Pretrain/Loss": 2.1139473915100098, "Pretrain/Loss (Raw)": 1.945443868637085, "Pretrain/Step": 1276, "Pretrain/Step Time": 8.815158125013113} +{"Pretrain/Learning Rate": 4.8597583933487165e-05, "Pretrain/Loss": 2.1151680946350098, "Pretrain/Loss (Raw)": 2.239295482635498, "Pretrain/Step": 1277, "Pretrain/Step Time": 8.810904037207365} +{"Pretrain/Learning Rate": 4.859477903147115e-05, "Pretrain/Loss": 2.116133689880371, "Pretrain/Loss (Raw)": 2.168044328689575, "Pretrain/Step": 1278, "Pretrain/Step Time": 8.811654139310122} +{"Pretrain/Learning Rate": 4.8591971408394034e-05, "Pretrain/Loss": 2.1161394119262695, "Pretrain/Loss (Raw)": 2.173560380935669, "Pretrain/Step": 1279, "Pretrain/Step Time": 8.805699441581964} +{"Pretrain/Learning Rate": 4.85891610645796e-05, "Pretrain/Loss": 2.116800308227539, "Pretrain/Loss (Raw)": 2.039142370223999, "Pretrain/Step": 1280, "Pretrain/Step Time": 8.805351577699184} +{"Pretrain/Learning Rate": 4.8586348000351956e-05, "Pretrain/Loss": 2.1187686920166016, "Pretrain/Loss (Raw)": 2.1907410621643066, "Pretrain/Step": 1281, "Pretrain/Step Time": 8.815385902300477} +{"Pretrain/Learning Rate": 4.8583532216035524e-05, "Pretrain/Loss": 2.1193203926086426, "Pretrain/Loss (Raw)": 2.1617250442504883, "Pretrain/Step": 1282, "Pretrain/Step Time": 8.809436239302158} +{"Pretrain/Learning Rate": 4.858071371195502e-05, "Pretrain/Loss": 2.1211087703704834, "Pretrain/Loss (Raw)": 2.19191837310791, "Pretrain/Step": 1283, "Pretrain/Step Time": 8.806833412498236} +{"Pretrain/Learning Rate": 4.8577892488435504e-05, "Pretrain/Loss": 2.121074676513672, "Pretrain/Loss (Raw)": 2.1643178462982178, "Pretrain/Step": 1284, "Pretrain/Step Time": 8.805186197161674} +{"Pretrain/Learning Rate": 4.8575068545802316e-05, "Pretrain/Loss": 2.121631145477295, "Pretrain/Loss (Raw)": 2.314368724822998, "Pretrain/Step": 1285, "Pretrain/Step Time": 8.804460845887661} +{"Pretrain/Learning Rate": 4.8572241884381145e-05, "Pretrain/Loss": 2.1194980144500732, "Pretrain/Loss (Raw)": 2.047295331954956, "Pretrain/Step": 1286, "Pretrain/Step Time": 8.798028921708465} +{"Pretrain/Learning Rate": 4.856941250449795e-05, "Pretrain/Loss": 2.120394468307495, "Pretrain/Loss (Raw)": 2.164060592651367, "Pretrain/Step": 1287, "Pretrain/Step Time": 8.795647891238332} +{"Pretrain/Learning Rate": 4.8566580406479045e-05, "Pretrain/Loss": 2.119946002960205, "Pretrain/Loss (Raw)": 2.09147572517395, "Pretrain/Step": 1288, "Pretrain/Step Time": 8.805290890857577} +{"Pretrain/Learning Rate": 4.856374559065104e-05, "Pretrain/Loss": 2.118821859359741, "Pretrain/Loss (Raw)": 2.1342077255249023, "Pretrain/Step": 1289, "Pretrain/Step Time": 8.79480422846973} +{"Pretrain/Learning Rate": 4.856090805734086e-05, "Pretrain/Loss": 2.11969256401062, "Pretrain/Loss (Raw)": 2.2207229137420654, "Pretrain/Step": 1290, "Pretrain/Step Time": 8.800571985542774} +{"Pretrain/Learning Rate": 4.855806780687574e-05, "Pretrain/Loss": 2.12026309967041, "Pretrain/Loss (Raw)": 2.116123914718628, "Pretrain/Step": 1291, "Pretrain/Step Time": 8.796352261677384} +{"Pretrain/Learning Rate": 4.8555224839583236e-05, "Pretrain/Loss": 2.119723320007324, "Pretrain/Loss (Raw)": 1.981688141822815, "Pretrain/Step": 1292, "Pretrain/Step Time": 8.802975304424763} +{"Pretrain/Learning Rate": 4.8552379155791194e-05, "Pretrain/Loss": 2.120023250579834, "Pretrain/Loss (Raw)": 2.2615063190460205, "Pretrain/Step": 1293, "Pretrain/Step Time": 8.805655866861343} +{"Pretrain/Learning Rate": 4.854953075582782e-05, "Pretrain/Loss": 2.1204752922058105, "Pretrain/Loss (Raw)": 2.2159268856048584, "Pretrain/Step": 1294, "Pretrain/Step Time": 8.807878132909536} +{"Pretrain/Learning Rate": 4.854667964002158e-05, "Pretrain/Loss": 2.121525526046753, "Pretrain/Loss (Raw)": 2.150364875793457, "Pretrain/Step": 1295, "Pretrain/Step Time": 8.801329581066966} +{"Pretrain/Learning Rate": 4.8543825808701294e-05, "Pretrain/Loss": 2.121506690979004, "Pretrain/Loss (Raw)": 2.116757869720459, "Pretrain/Step": 1296, "Pretrain/Step Time": 8.800492491573095} +{"Pretrain/Learning Rate": 4.854096926219607e-05, "Pretrain/Loss": 2.119476795196533, "Pretrain/Loss (Raw)": 1.889335036277771, "Pretrain/Step": 1297, "Pretrain/Step Time": 8.804003586992621} +{"Pretrain/Learning Rate": 4.853811000083535e-05, "Pretrain/Loss": 2.118607997894287, "Pretrain/Loss (Raw)": 2.0571722984313965, "Pretrain/Step": 1298, "Pretrain/Step Time": 8.798912988975644} +{"Pretrain/Learning Rate": 4.8535248024948854e-05, "Pretrain/Loss": 2.1195616722106934, "Pretrain/Loss (Raw)": 2.242945432662964, "Pretrain/Step": 1299, "Pretrain/Step Time": 8.802087966352701} +{"Pretrain/Learning Rate": 4.853238333486666e-05, "Pretrain/Loss": 2.121151924133301, "Pretrain/Loss (Raw)": 2.2030599117279053, "Pretrain/Step": 1300, "Pretrain/Step Time": 8.799222566187382} +{"Pretrain/Learning Rate": 4.852951593091914e-05, "Pretrain/Loss": 2.121706962585449, "Pretrain/Loss (Raw)": 2.193045139312744, "Pretrain/Step": 1301, "Pretrain/Step Time": 8.801333682611585} +{"Pretrain/Learning Rate": 4.852664581343696e-05, "Pretrain/Loss": 2.1237173080444336, "Pretrain/Loss (Raw)": 2.1758792400360107, "Pretrain/Step": 1302, "Pretrain/Step Time": 8.799323024228215} +{"Pretrain/Learning Rate": 4.852377298275113e-05, "Pretrain/Loss": 2.1237568855285645, "Pretrain/Loss (Raw)": 2.1931800842285156, "Pretrain/Step": 1303, "Pretrain/Step Time": 8.801635254174471} +{"Pretrain/Learning Rate": 4.852089743919295e-05, "Pretrain/Loss": 2.124204397201538, "Pretrain/Loss (Raw)": 2.193899154663086, "Pretrain/Step": 1304, "Pretrain/Step Time": 8.802116725593805} +{"Pretrain/Learning Rate": 4.851801918309403e-05, "Pretrain/Loss": 2.1234850883483887, "Pretrain/Loss (Raw)": 2.0434696674346924, "Pretrain/Step": 1305, "Pretrain/Step Time": 8.803693113848567} +{"Pretrain/Learning Rate": 4.8515138214786335e-05, "Pretrain/Loss": 2.1236062049865723, "Pretrain/Loss (Raw)": 2.0514748096466064, "Pretrain/Step": 1306, "Pretrain/Step Time": 8.80555764771998} +{"Pretrain/Learning Rate": 4.851225453460209e-05, "Pretrain/Loss": 2.123514413833618, "Pretrain/Loss (Raw)": 2.1274843215942383, "Pretrain/Step": 1307, "Pretrain/Step Time": 8.803122671321034} +{"Pretrain/Learning Rate": 4.850936814287386e-05, "Pretrain/Loss": 2.1238646507263184, "Pretrain/Loss (Raw)": 2.1741437911987305, "Pretrain/Step": 1308, "Pretrain/Step Time": 8.803878648206592} +{"Pretrain/Learning Rate": 4.85064790399345e-05, "Pretrain/Loss": 2.1255664825439453, "Pretrain/Loss (Raw)": 2.1218814849853516, "Pretrain/Step": 1309, "Pretrain/Step Time": 8.807187300175428} +{"Pretrain/Learning Rate": 4.850358722611723e-05, "Pretrain/Loss": 2.1248583793640137, "Pretrain/Loss (Raw)": 2.0802533626556396, "Pretrain/Step": 1310, "Pretrain/Step Time": 8.801007896661758} +{"Pretrain/Learning Rate": 4.850069270175552e-05, "Pretrain/Loss": 2.125243663787842, "Pretrain/Loss (Raw)": 2.1123249530792236, "Pretrain/Step": 1311, "Pretrain/Step Time": 8.801976753398776} +{"Pretrain/Learning Rate": 4.849779546718319e-05, "Pretrain/Loss": 2.1260623931884766, "Pretrain/Loss (Raw)": 2.2677090167999268, "Pretrain/Step": 1312, "Pretrain/Step Time": 8.800072090700269} +{"Pretrain/Learning Rate": 4.8494895522734364e-05, "Pretrain/Loss": 2.1266469955444336, "Pretrain/Loss (Raw)": 2.1777477264404297, "Pretrain/Step": 1313, "Pretrain/Step Time": 8.796766072511673} +{"Pretrain/Learning Rate": 4.849199286874347e-05, "Pretrain/Loss": 2.1226072311401367, "Pretrain/Loss (Raw)": 1.9985980987548828, "Pretrain/Step": 1314, "Pretrain/Step Time": 8.798877583816648} +{"Pretrain/Learning Rate": 4.8489087505545266e-05, "Pretrain/Loss": 2.124678611755371, "Pretrain/Loss (Raw)": 2.2055232524871826, "Pretrain/Step": 1315, "Pretrain/Step Time": 8.799404429271817} +{"Pretrain/Learning Rate": 4.84861794334748e-05, "Pretrain/Loss": 2.1240153312683105, "Pretrain/Loss (Raw)": 2.07890248298645, "Pretrain/Step": 1316, "Pretrain/Step Time": 8.800544157624245} +{"Pretrain/Learning Rate": 4.848326865286746e-05, "Pretrain/Loss": 2.126577377319336, "Pretrain/Loss (Raw)": 2.3195512294769287, "Pretrain/Step": 1317, "Pretrain/Step Time": 8.795169591903687} +{"Pretrain/Learning Rate": 4.848035516405892e-05, "Pretrain/Loss": 2.125663995742798, "Pretrain/Loss (Raw)": 2.016439437866211, "Pretrain/Step": 1318, "Pretrain/Step Time": 8.793564705178142} +{"Pretrain/Learning Rate": 4.847743896738517e-05, "Pretrain/Loss": 2.1247220039367676, "Pretrain/Loss (Raw)": 2.1655139923095703, "Pretrain/Step": 1319, "Pretrain/Step Time": 8.797039004042745} +{"Pretrain/Learning Rate": 4.847452006318254e-05, "Pretrain/Loss": 2.125483274459839, "Pretrain/Loss (Raw)": 2.204763650894165, "Pretrain/Step": 1320, "Pretrain/Step Time": 8.79780637845397} +{"Pretrain/Learning Rate": 4.8471598451787635e-05, "Pretrain/Loss": 2.1252360343933105, "Pretrain/Loss (Raw)": 2.039766788482666, "Pretrain/Step": 1321, "Pretrain/Step Time": 8.800798185169697} +{"Pretrain/Learning Rate": 4.8468674133537395e-05, "Pretrain/Loss": 2.123687744140625, "Pretrain/Loss (Raw)": 2.0211222171783447, "Pretrain/Step": 1322, "Pretrain/Step Time": 8.801734996959567} +{"Pretrain/Learning Rate": 4.846574710876907e-05, "Pretrain/Loss": 2.126007556915283, "Pretrain/Loss (Raw)": 2.222243070602417, "Pretrain/Step": 1323, "Pretrain/Step Time": 8.80248217470944} +{"Pretrain/Learning Rate": 4.846281737782021e-05, "Pretrain/Loss": 2.126985549926758, "Pretrain/Loss (Raw)": 2.2138588428497314, "Pretrain/Step": 1324, "Pretrain/Step Time": 8.813984028995037} +{"Pretrain/Learning Rate": 4.845988494102869e-05, "Pretrain/Loss": 2.12734055519104, "Pretrain/Loss (Raw)": 2.144231081008911, "Pretrain/Step": 1325, "Pretrain/Step Time": 8.805741528049111} +{"Pretrain/Learning Rate": 4.845694979873269e-05, "Pretrain/Loss": 2.1276321411132812, "Pretrain/Loss (Raw)": 2.0421011447906494, "Pretrain/Step": 1326, "Pretrain/Step Time": 8.803580611944199} +{"Pretrain/Learning Rate": 4.845401195127071e-05, "Pretrain/Loss": 2.1284096240997314, "Pretrain/Loss (Raw)": 2.215287208557129, "Pretrain/Step": 1327, "Pretrain/Step Time": 8.810326298698783} +{"Pretrain/Learning Rate": 4.845107139898155e-05, "Pretrain/Loss": 2.1283040046691895, "Pretrain/Loss (Raw)": 2.1139509677886963, "Pretrain/Step": 1328, "Pretrain/Step Time": 8.807241696864367} +{"Pretrain/Learning Rate": 4.8448128142204334e-05, "Pretrain/Loss": 2.1279656887054443, "Pretrain/Loss (Raw)": 2.1538820266723633, "Pretrain/Step": 1329, "Pretrain/Step Time": 8.805945115163922} +{"Pretrain/Learning Rate": 4.8445182181278494e-05, "Pretrain/Loss": 2.128243923187256, "Pretrain/Loss (Raw)": 2.060255527496338, "Pretrain/Step": 1330, "Pretrain/Step Time": 8.805343775078654} +{"Pretrain/Learning Rate": 4.8442233516543756e-05, "Pretrain/Loss": 2.1276040077209473, "Pretrain/Loss (Raw)": 2.1063942909240723, "Pretrain/Step": 1331, "Pretrain/Step Time": 8.797060675919056} +{"Pretrain/Learning Rate": 4.8439282148340195e-05, "Pretrain/Loss": 2.1276750564575195, "Pretrain/Loss (Raw)": 2.160703182220459, "Pretrain/Step": 1332, "Pretrain/Step Time": 8.804619029164314} +{"Pretrain/Learning Rate": 4.843632807700816e-05, "Pretrain/Loss": 2.127739906311035, "Pretrain/Loss (Raw)": 2.139146089553833, "Pretrain/Step": 1333, "Pretrain/Step Time": 8.800334338098764} +{"Pretrain/Learning Rate": 4.843337130288834e-05, "Pretrain/Loss": 2.127004384994507, "Pretrain/Loss (Raw)": 2.0723607540130615, "Pretrain/Step": 1334, "Pretrain/Step Time": 8.801029905676842} +{"Pretrain/Learning Rate": 4.843041182632172e-05, "Pretrain/Loss": 2.128770112991333, "Pretrain/Loss (Raw)": 2.1954691410064697, "Pretrain/Step": 1335, "Pretrain/Step Time": 8.800273487344384} +{"Pretrain/Learning Rate": 4.84274496476496e-05, "Pretrain/Loss": 2.127951145172119, "Pretrain/Loss (Raw)": 2.1181929111480713, "Pretrain/Step": 1336, "Pretrain/Step Time": 8.80001556687057} +{"Pretrain/Learning Rate": 4.84244847672136e-05, "Pretrain/Loss": 2.1273810863494873, "Pretrain/Loss (Raw)": 2.016545534133911, "Pretrain/Step": 1337, "Pretrain/Step Time": 8.80294319987297} +{"Pretrain/Learning Rate": 4.842151718535563e-05, "Pretrain/Loss": 2.1263933181762695, "Pretrain/Loss (Raw)": 1.903314232826233, "Pretrain/Step": 1338, "Pretrain/Step Time": 8.809236550703645} +{"Pretrain/Learning Rate": 4.841854690241793e-05, "Pretrain/Loss": 2.126786231994629, "Pretrain/Loss (Raw)": 2.1133975982666016, "Pretrain/Step": 1339, "Pretrain/Step Time": 8.809988779947162} +{"Pretrain/Learning Rate": 4.841557391874304e-05, "Pretrain/Loss": 2.1249918937683105, "Pretrain/Loss (Raw)": 1.952798843383789, "Pretrain/Step": 1340, "Pretrain/Step Time": 8.811692263931036} +{"Pretrain/Learning Rate": 4.8412598234673845e-05, "Pretrain/Loss": 2.124570369720459, "Pretrain/Loss (Raw)": 2.0594632625579834, "Pretrain/Step": 1341, "Pretrain/Step Time": 8.8087815400213} +{"Pretrain/Learning Rate": 4.840961985055349e-05, "Pretrain/Loss": 2.1241204738616943, "Pretrain/Loss (Raw)": 2.092886447906494, "Pretrain/Step": 1342, "Pretrain/Step Time": 8.808660756796598} +{"Pretrain/Learning Rate": 4.8406638766725464e-05, "Pretrain/Loss": 2.1268763542175293, "Pretrain/Loss (Raw)": 2.1946637630462646, "Pretrain/Step": 1343, "Pretrain/Step Time": 8.803895991295576} +{"Pretrain/Learning Rate": 4.840365498353357e-05, "Pretrain/Loss": 2.1271262168884277, "Pretrain/Loss (Raw)": 2.1454975605010986, "Pretrain/Step": 1344, "Pretrain/Step Time": 8.804809605702758} +{"Pretrain/Learning Rate": 4.840066850132189e-05, "Pretrain/Loss": 2.127195358276367, "Pretrain/Loss (Raw)": 2.005030870437622, "Pretrain/Step": 1345, "Pretrain/Step Time": 8.796322748064995} +{"Pretrain/Learning Rate": 4.839767932043485e-05, "Pretrain/Loss": 2.127380847930908, "Pretrain/Loss (Raw)": 2.3568830490112305, "Pretrain/Step": 1346, "Pretrain/Step Time": 8.806746987625957} +{"Pretrain/Learning Rate": 4.839468744121718e-05, "Pretrain/Loss": 2.1274845600128174, "Pretrain/Loss (Raw)": 2.1763226985931396, "Pretrain/Step": 1347, "Pretrain/Step Time": 8.800893120467663} +{"Pretrain/Learning Rate": 4.8391692864013916e-05, "Pretrain/Loss": 2.128882646560669, "Pretrain/Loss (Raw)": 2.199676513671875, "Pretrain/Step": 1348, "Pretrain/Step Time": 8.803360363468528} +{"Pretrain/Learning Rate": 4.838869558917041e-05, "Pretrain/Loss": 2.128755569458008, "Pretrain/Loss (Raw)": 2.084254741668701, "Pretrain/Step": 1349, "Pretrain/Step Time": 8.806497799232602} +{"Pretrain/Learning Rate": 4.838569561703231e-05, "Pretrain/Loss": 2.1284608840942383, "Pretrain/Loss (Raw)": 2.0972585678100586, "Pretrain/Step": 1350, "Pretrain/Step Time": 8.802762130275369} +{"Pretrain/Learning Rate": 4.83826929479456e-05, "Pretrain/Loss": 2.1287341117858887, "Pretrain/Loss (Raw)": 2.180769920349121, "Pretrain/Step": 1351, "Pretrain/Step Time": 8.800842739641666} +{"Pretrain/Learning Rate": 4.837968758225655e-05, "Pretrain/Loss": 2.1292364597320557, "Pretrain/Loss (Raw)": 2.208505868911743, "Pretrain/Step": 1352, "Pretrain/Step Time": 8.79592839628458} +{"Pretrain/Learning Rate": 4.837667952031176e-05, "Pretrain/Loss": 2.128194570541382, "Pretrain/Loss (Raw)": 2.0954251289367676, "Pretrain/Step": 1353, "Pretrain/Step Time": 8.805776050314307} +{"Pretrain/Learning Rate": 4.8373668762458144e-05, "Pretrain/Loss": 2.1280813217163086, "Pretrain/Loss (Raw)": 2.179701805114746, "Pretrain/Step": 1354, "Pretrain/Step Time": 8.801561614498496} +{"Pretrain/Learning Rate": 4.8370655309042896e-05, "Pretrain/Loss": 2.1265580654144287, "Pretrain/Loss (Raw)": 1.9724363088607788, "Pretrain/Step": 1355, "Pretrain/Step Time": 8.804622938856483} +{"Pretrain/Learning Rate": 4.8367639160413553e-05, "Pretrain/Loss": 2.1278982162475586, "Pretrain/Loss (Raw)": 2.1589908599853516, "Pretrain/Step": 1356, "Pretrain/Step Time": 8.80239762738347} +{"Pretrain/Learning Rate": 4.8364620316917956e-05, "Pretrain/Loss": 2.127828598022461, "Pretrain/Loss (Raw)": 2.061228036880493, "Pretrain/Step": 1357, "Pretrain/Step Time": 8.804994786158204} +{"Pretrain/Learning Rate": 4.836159877890424e-05, "Pretrain/Loss": 2.1280176639556885, "Pretrain/Loss (Raw)": 2.097576141357422, "Pretrain/Step": 1358, "Pretrain/Step Time": 8.801163416355848} +{"Pretrain/Learning Rate": 4.835857454672087e-05, "Pretrain/Loss": 2.1285715103149414, "Pretrain/Loss (Raw)": 2.1455166339874268, "Pretrain/Step": 1359, "Pretrain/Step Time": 8.805078085511923} +{"Pretrain/Learning Rate": 4.835554762071661e-05, "Pretrain/Loss": 2.1298344135284424, "Pretrain/Loss (Raw)": 2.1942925453186035, "Pretrain/Step": 1360, "Pretrain/Step Time": 8.805297259241343} +{"Pretrain/Learning Rate": 4.8352518001240555e-05, "Pretrain/Loss": 2.130667209625244, "Pretrain/Loss (Raw)": 2.3869433403015137, "Pretrain/Step": 1361, "Pretrain/Step Time": 8.80120357312262} +{"Pretrain/Learning Rate": 4.834948568864207e-05, "Pretrain/Loss": 2.130204200744629, "Pretrain/Loss (Raw)": 2.27054500579834, "Pretrain/Step": 1362, "Pretrain/Step Time": 8.799068046733737} +{"Pretrain/Learning Rate": 4.8346450683270875e-05, "Pretrain/Loss": 2.1286678314208984, "Pretrain/Loss (Raw)": 1.9229792356491089, "Pretrain/Step": 1363, "Pretrain/Step Time": 8.800892688333988} +{"Pretrain/Learning Rate": 4.8343412985476974e-05, "Pretrain/Loss": 2.1286416053771973, "Pretrain/Loss (Raw)": 2.1454007625579834, "Pretrain/Step": 1364, "Pretrain/Step Time": 8.80300409719348} +{"Pretrain/Learning Rate": 4.83403725956107e-05, "Pretrain/Loss": 2.1283679008483887, "Pretrain/Loss (Raw)": 2.0568981170654297, "Pretrain/Step": 1365, "Pretrain/Step Time": 8.804480848833919} +{"Pretrain/Learning Rate": 4.8337329514022664e-05, "Pretrain/Loss": 2.12823748588562, "Pretrain/Loss (Raw)": 2.1045732498168945, "Pretrain/Step": 1366, "Pretrain/Step Time": 8.804180320352316} +{"Pretrain/Learning Rate": 4.833428374106382e-05, "Pretrain/Loss": 2.128021240234375, "Pretrain/Loss (Raw)": 1.9840682744979858, "Pretrain/Step": 1367, "Pretrain/Step Time": 8.803436510264874} +{"Pretrain/Learning Rate": 4.833123527708542e-05, "Pretrain/Loss": 2.128328800201416, "Pretrain/Loss (Raw)": 2.115891933441162, "Pretrain/Step": 1368, "Pretrain/Step Time": 8.800379689782858} +{"Pretrain/Learning Rate": 4.832818412243904e-05, "Pretrain/Loss": 2.1285741329193115, "Pretrain/Loss (Raw)": 2.0846164226531982, "Pretrain/Step": 1369, "Pretrain/Step Time": 8.80212900787592} +{"Pretrain/Learning Rate": 4.8325130277476526e-05, "Pretrain/Loss": 2.1295742988586426, "Pretrain/Loss (Raw)": 2.037424325942993, "Pretrain/Step": 1370, "Pretrain/Step Time": 8.802559608593583} +{"Pretrain/Learning Rate": 4.832207374255008e-05, "Pretrain/Loss": 2.1302437782287598, "Pretrain/Loss (Raw)": 2.1351914405822754, "Pretrain/Step": 1371, "Pretrain/Step Time": 8.800074312835932} +{"Pretrain/Learning Rate": 4.8319014518012195e-05, "Pretrain/Loss": 2.1295289993286133, "Pretrain/Loss (Raw)": 2.056060552597046, "Pretrain/Step": 1372, "Pretrain/Step Time": 8.7980425208807} +{"Pretrain/Learning Rate": 4.831595260421567e-05, "Pretrain/Loss": 2.128495693206787, "Pretrain/Loss (Raw)": 2.1105496883392334, "Pretrain/Step": 1373, "Pretrain/Step Time": 8.797445302829146} +{"Pretrain/Learning Rate": 4.8312888001513624e-05, "Pretrain/Loss": 2.128772258758545, "Pretrain/Loss (Raw)": 2.075209856033325, "Pretrain/Step": 1374, "Pretrain/Step Time": 8.808467557653785} +{"Pretrain/Learning Rate": 4.830982071025948e-05, "Pretrain/Loss": 2.128889799118042, "Pretrain/Loss (Raw)": 2.168273448944092, "Pretrain/Step": 1375, "Pretrain/Step Time": 8.798321014270186} +{"Pretrain/Learning Rate": 4.830675073080697e-05, "Pretrain/Loss": 2.1281144618988037, "Pretrain/Loss (Raw)": 2.0522656440734863, "Pretrain/Step": 1376, "Pretrain/Step Time": 8.812100743874907} +{"Pretrain/Learning Rate": 4.830367806351015e-05, "Pretrain/Loss": 2.1279067993164062, "Pretrain/Loss (Raw)": 2.228466033935547, "Pretrain/Step": 1377, "Pretrain/Step Time": 8.808600271120667} +{"Pretrain/Learning Rate": 4.830060270872335e-05, "Pretrain/Loss": 2.1267354488372803, "Pretrain/Loss (Raw)": 1.991817831993103, "Pretrain/Step": 1378, "Pretrain/Step Time": 8.805441740900278} +{"Pretrain/Learning Rate": 4.8297524666801265e-05, "Pretrain/Loss": 2.128453254699707, "Pretrain/Loss (Raw)": 2.398073673248291, "Pretrain/Step": 1379, "Pretrain/Step Time": 8.805686904117465} +{"Pretrain/Learning Rate": 4.829444393809884e-05, "Pretrain/Loss": 2.1274547576904297, "Pretrain/Loss (Raw)": 2.164346218109131, "Pretrain/Step": 1380, "Pretrain/Step Time": 8.805804569274187} +{"Pretrain/Learning Rate": 4.829136052297138e-05, "Pretrain/Loss": 2.1266801357269287, "Pretrain/Loss (Raw)": 1.928850769996643, "Pretrain/Step": 1381, "Pretrain/Step Time": 8.809589276090264} +{"Pretrain/Learning Rate": 4.828827442177447e-05, "Pretrain/Loss": 2.1271142959594727, "Pretrain/Loss (Raw)": 2.208035707473755, "Pretrain/Step": 1382, "Pretrain/Step Time": 8.80983686260879} +{"Pretrain/Learning Rate": 4.8285185634864024e-05, "Pretrain/Loss": 2.130150556564331, "Pretrain/Loss (Raw)": 2.5002048015594482, "Pretrain/Step": 1383, "Pretrain/Step Time": 8.807063231244683} +{"Pretrain/Learning Rate": 4.8282094162596235e-05, "Pretrain/Loss": 2.1271955966949463, "Pretrain/Loss (Raw)": 1.8789411783218384, "Pretrain/Step": 1384, "Pretrain/Step Time": 8.811039112508297} +{"Pretrain/Learning Rate": 4.8279000005327644e-05, "Pretrain/Loss": 2.128054618835449, "Pretrain/Loss (Raw)": 2.1451072692871094, "Pretrain/Step": 1385, "Pretrain/Step Time": 8.81267317570746} +{"Pretrain/Learning Rate": 4.827590316341508e-05, "Pretrain/Loss": 2.1267316341400146, "Pretrain/Loss (Raw)": 2.0642802715301514, "Pretrain/Step": 1386, "Pretrain/Step Time": 8.815763691440225} +{"Pretrain/Learning Rate": 4.827280363721568e-05, "Pretrain/Loss": 2.1267993450164795, "Pretrain/Loss (Raw)": 2.0868403911590576, "Pretrain/Step": 1387, "Pretrain/Step Time": 8.821852250024676} +{"Pretrain/Learning Rate": 4.82697014270869e-05, "Pretrain/Loss": 2.1270265579223633, "Pretrain/Loss (Raw)": 2.1550886631011963, "Pretrain/Step": 1388, "Pretrain/Step Time": 8.823514088988304} +{"Pretrain/Learning Rate": 4.8266596533386505e-05, "Pretrain/Loss": 2.125756025314331, "Pretrain/Loss (Raw)": 2.118788242340088, "Pretrain/Step": 1389, "Pretrain/Step Time": 8.824358841404319} +{"Pretrain/Learning Rate": 4.8263488956472555e-05, "Pretrain/Loss": 2.126145362854004, "Pretrain/Loss (Raw)": 2.052410840988159, "Pretrain/Step": 1390, "Pretrain/Step Time": 8.82908184081316} +{"Pretrain/Learning Rate": 4.826037869670345e-05, "Pretrain/Loss": 2.125959873199463, "Pretrain/Loss (Raw)": 2.1505863666534424, "Pretrain/Step": 1391, "Pretrain/Step Time": 8.822121297940612} +{"Pretrain/Learning Rate": 4.8257265754437854e-05, "Pretrain/Loss": 2.126274585723877, "Pretrain/Loss (Raw)": 2.044853448867798, "Pretrain/Step": 1392, "Pretrain/Step Time": 8.819676633924246} +{"Pretrain/Learning Rate": 4.825415013003478e-05, "Pretrain/Loss": 2.128329277038574, "Pretrain/Loss (Raw)": 2.2516191005706787, "Pretrain/Step": 1393, "Pretrain/Step Time": 8.820552464574575} +{"Pretrain/Learning Rate": 4.8251031823853546e-05, "Pretrain/Loss": 2.128335475921631, "Pretrain/Loss (Raw)": 2.1342339515686035, "Pretrain/Step": 1394, "Pretrain/Step Time": 8.830480888485909} +{"Pretrain/Learning Rate": 4.824791083625375e-05, "Pretrain/Loss": 2.129178285598755, "Pretrain/Loss (Raw)": 2.1383025646209717, "Pretrain/Step": 1395, "Pretrain/Step Time": 8.834949089214206} +{"Pretrain/Learning Rate": 4.8244787167595335e-05, "Pretrain/Loss": 2.1305618286132812, "Pretrain/Loss (Raw)": 2.1675312519073486, "Pretrain/Step": 1396, "Pretrain/Step Time": 8.840789640322328} +{"Pretrain/Learning Rate": 4.824166081823853e-05, "Pretrain/Loss": 2.131098747253418, "Pretrain/Loss (Raw)": 2.062887668609619, "Pretrain/Step": 1397, "Pretrain/Step Time": 8.841391488909721} +{"Pretrain/Learning Rate": 4.823853178854387e-05, "Pretrain/Loss": 2.1295413970947266, "Pretrain/Loss (Raw)": 2.016481637954712, "Pretrain/Step": 1398, "Pretrain/Step Time": 8.839658163487911} +{"Pretrain/Learning Rate": 4.8235400078872234e-05, "Pretrain/Loss": 2.127669334411621, "Pretrain/Loss (Raw)": 1.906975507736206, "Pretrain/Step": 1399, "Pretrain/Step Time": 8.837173573672771} +{"Pretrain/Learning Rate": 4.823226568958477e-05, "Pretrain/Loss": 2.1279492378234863, "Pretrain/Loss (Raw)": 2.3549132347106934, "Pretrain/Step": 1400, "Pretrain/Step Time": 8.8335515037179} +{"Pretrain/Learning Rate": 4.822912862104295e-05, "Pretrain/Loss": 2.1263513565063477, "Pretrain/Loss (Raw)": 2.0109786987304688, "Pretrain/Step": 1401, "Pretrain/Step Time": 8.848013080656528} +{"Pretrain/Learning Rate": 4.8225988873608554e-05, "Pretrain/Loss": 2.12795352935791, "Pretrain/Loss (Raw)": 2.2240853309631348, "Pretrain/Step": 1402, "Pretrain/Step Time": 8.833920175209641} +{"Pretrain/Learning Rate": 4.8222846447643686e-05, "Pretrain/Loss": 2.1261186599731445, "Pretrain/Loss (Raw)": 1.9572257995605469, "Pretrain/Step": 1403, "Pretrain/Step Time": 8.836644308641553} +{"Pretrain/Learning Rate": 4.8219701343510727e-05, "Pretrain/Loss": 2.1285650730133057, "Pretrain/Loss (Raw)": 2.2585701942443848, "Pretrain/Step": 1404, "Pretrain/Step Time": 8.836376048624516} +{"Pretrain/Learning Rate": 4.8216553561572395e-05, "Pretrain/Loss": 2.127962589263916, "Pretrain/Loss (Raw)": 2.162172555923462, "Pretrain/Step": 1405, "Pretrain/Step Time": 8.83428055420518} +{"Pretrain/Learning Rate": 4.821340310219171e-05, "Pretrain/Loss": 2.127448320388794, "Pretrain/Loss (Raw)": 2.102200984954834, "Pretrain/Step": 1406, "Pretrain/Step Time": 8.83606688119471} +{"Pretrain/Learning Rate": 4.8210249965732e-05, "Pretrain/Loss": 2.126534938812256, "Pretrain/Loss (Raw)": 2.0566658973693848, "Pretrain/Step": 1407, "Pretrain/Step Time": 8.835643399506807} +{"Pretrain/Learning Rate": 4.8207094152556886e-05, "Pretrain/Loss": 2.1280922889709473, "Pretrain/Loss (Raw)": 2.2384538650512695, "Pretrain/Step": 1408, "Pretrain/Step Time": 8.836749663576484} +{"Pretrain/Learning Rate": 4.820393566303032e-05, "Pretrain/Loss": 2.1283376216888428, "Pretrain/Loss (Raw)": 2.2221810817718506, "Pretrain/Step": 1409, "Pretrain/Step Time": 8.832486866042018} +{"Pretrain/Learning Rate": 4.8200774497516555e-05, "Pretrain/Loss": 2.1277379989624023, "Pretrain/Loss (Raw)": 2.0849509239196777, "Pretrain/Step": 1410, "Pretrain/Step Time": 8.840779341757298} +{"Pretrain/Learning Rate": 4.8197610656380144e-05, "Pretrain/Loss": 2.126316785812378, "Pretrain/Loss (Raw)": 2.010021924972534, "Pretrain/Step": 1411, "Pretrain/Step Time": 8.840450903400779} +{"Pretrain/Learning Rate": 4.8194444139985965e-05, "Pretrain/Loss": 2.1263628005981445, "Pretrain/Loss (Raw)": 2.1701810359954834, "Pretrain/Step": 1412, "Pretrain/Step Time": 8.84717377834022} +{"Pretrain/Learning Rate": 4.81912749486992e-05, "Pretrain/Loss": 2.125570297241211, "Pretrain/Loss (Raw)": 2.212956190109253, "Pretrain/Step": 1413, "Pretrain/Step Time": 8.847563661634922} +{"Pretrain/Learning Rate": 4.818810308288531e-05, "Pretrain/Loss": 2.125424861907959, "Pretrain/Loss (Raw)": 2.028696060180664, "Pretrain/Step": 1414, "Pretrain/Step Time": 8.846403421834111} +{"Pretrain/Learning Rate": 4.818492854291012e-05, "Pretrain/Loss": 2.125692367553711, "Pretrain/Loss (Raw)": 2.1982955932617188, "Pretrain/Step": 1415, "Pretrain/Step Time": 8.849374383687973} +{"Pretrain/Learning Rate": 4.818175132913971e-05, "Pretrain/Loss": 2.126105308532715, "Pretrain/Loss (Raw)": 2.144298553466797, "Pretrain/Step": 1416, "Pretrain/Step Time": 8.846379524096847} +{"Pretrain/Learning Rate": 4.817857144194051e-05, "Pretrain/Loss": 2.126473903656006, "Pretrain/Loss (Raw)": 2.181432008743286, "Pretrain/Step": 1417, "Pretrain/Step Time": 8.856116877868772} +{"Pretrain/Learning Rate": 4.817538888167923e-05, "Pretrain/Loss": 2.1257667541503906, "Pretrain/Loss (Raw)": 2.13018536567688, "Pretrain/Step": 1418, "Pretrain/Step Time": 8.853808032348752} +{"Pretrain/Learning Rate": 4.817220364872289e-05, "Pretrain/Loss": 2.125220775604248, "Pretrain/Loss (Raw)": 2.046254873275757, "Pretrain/Step": 1419, "Pretrain/Step Time": 8.852513493970037} +{"Pretrain/Learning Rate": 4.816901574343884e-05, "Pretrain/Loss": 2.1266794204711914, "Pretrain/Loss (Raw)": 2.1683502197265625, "Pretrain/Step": 1420, "Pretrain/Step Time": 8.843640964478254} +{"Pretrain/Learning Rate": 4.816582516619471e-05, "Pretrain/Loss": 2.1268553733825684, "Pretrain/Loss (Raw)": 2.2840633392333984, "Pretrain/Step": 1421, "Pretrain/Step Time": 8.84142504259944} +{"Pretrain/Learning Rate": 4.816263191735847e-05, "Pretrain/Loss": 2.124666690826416, "Pretrain/Loss (Raw)": 1.935770869255066, "Pretrain/Step": 1422, "Pretrain/Step Time": 8.841949980705976} +{"Pretrain/Learning Rate": 4.8159435997298375e-05, "Pretrain/Loss": 2.1240711212158203, "Pretrain/Loss (Raw)": 2.0741324424743652, "Pretrain/Step": 1423, "Pretrain/Step Time": 8.847850186750293} +{"Pretrain/Learning Rate": 4.8156237406382975e-05, "Pretrain/Loss": 2.1229491233825684, "Pretrain/Loss (Raw)": 1.9731202125549316, "Pretrain/Step": 1424, "Pretrain/Step Time": 8.846614938229322} +{"Pretrain/Learning Rate": 4.815303614498118e-05, "Pretrain/Loss": 2.12573504447937, "Pretrain/Loss (Raw)": 2.2459583282470703, "Pretrain/Step": 1425, "Pretrain/Step Time": 8.847287258133292} +{"Pretrain/Learning Rate": 4.814983221346214e-05, "Pretrain/Loss": 2.1267917156219482, "Pretrain/Loss (Raw)": 2.1923985481262207, "Pretrain/Step": 1426, "Pretrain/Step Time": 8.85331954434514} +{"Pretrain/Learning Rate": 4.814662561219537e-05, "Pretrain/Loss": 2.125056266784668, "Pretrain/Loss (Raw)": 2.0208380222320557, "Pretrain/Step": 1427, "Pretrain/Step Time": 8.852275483310223} +{"Pretrain/Learning Rate": 4.814341634155066e-05, "Pretrain/Loss": 2.1247072219848633, "Pretrain/Loss (Raw)": 2.1583681106567383, "Pretrain/Step": 1428, "Pretrain/Step Time": 8.853434475138783} +{"Pretrain/Learning Rate": 4.8140204401898134e-05, "Pretrain/Loss": 2.123851776123047, "Pretrain/Loss (Raw)": 2.0835468769073486, "Pretrain/Step": 1429, "Pretrain/Step Time": 8.8517657071352} +{"Pretrain/Learning Rate": 4.813698979360819e-05, "Pretrain/Loss": 2.1233818531036377, "Pretrain/Loss (Raw)": 2.1157407760620117, "Pretrain/Step": 1430, "Pretrain/Step Time": 8.862744120880961} +{"Pretrain/Learning Rate": 4.813377251705156e-05, "Pretrain/Loss": 2.1221120357513428, "Pretrain/Loss (Raw)": 2.0306384563446045, "Pretrain/Step": 1431, "Pretrain/Step Time": 8.848839525133371} +{"Pretrain/Learning Rate": 4.8130552572599265e-05, "Pretrain/Loss": 2.121058940887451, "Pretrain/Loss (Raw)": 2.0591046810150146, "Pretrain/Step": 1432, "Pretrain/Step Time": 8.856333766132593} +{"Pretrain/Learning Rate": 4.8127329960622656e-05, "Pretrain/Loss": 2.121943950653076, "Pretrain/Loss (Raw)": 2.156738042831421, "Pretrain/Step": 1433, "Pretrain/Step Time": 8.858259866014123} +{"Pretrain/Learning Rate": 4.8124104681493375e-05, "Pretrain/Loss": 2.122807502746582, "Pretrain/Loss (Raw)": 2.1619961261749268, "Pretrain/Step": 1434, "Pretrain/Step Time": 8.857485953718424} +{"Pretrain/Learning Rate": 4.8120876735583384e-05, "Pretrain/Loss": 2.1223645210266113, "Pretrain/Loss (Raw)": 2.070795774459839, "Pretrain/Step": 1435, "Pretrain/Step Time": 8.860723331570625} +{"Pretrain/Learning Rate": 4.811764612326493e-05, "Pretrain/Loss": 2.1230459213256836, "Pretrain/Loss (Raw)": 2.2613744735717773, "Pretrain/Step": 1436, "Pretrain/Step Time": 8.861628098413348} +{"Pretrain/Learning Rate": 4.8114412844910595e-05, "Pretrain/Loss": 2.123762369155884, "Pretrain/Loss (Raw)": 2.2135744094848633, "Pretrain/Step": 1437, "Pretrain/Step Time": 8.86583610996604} +{"Pretrain/Learning Rate": 4.8111176900893254e-05, "Pretrain/Loss": 2.125664710998535, "Pretrain/Loss (Raw)": 2.3237857818603516, "Pretrain/Step": 1438, "Pretrain/Step Time": 8.85973303578794} +{"Pretrain/Learning Rate": 4.810793829158609e-05, "Pretrain/Loss": 2.1253528594970703, "Pretrain/Loss (Raw)": 2.0723884105682373, "Pretrain/Step": 1439, "Pretrain/Step Time": 8.860699927434325} +{"Pretrain/Learning Rate": 4.8104697017362595e-05, "Pretrain/Loss": 2.1240718364715576, "Pretrain/Loss (Raw)": 2.103731632232666, "Pretrain/Step": 1440, "Pretrain/Step Time": 8.869917515665293} +{"Pretrain/Learning Rate": 4.8101453078596565e-05, "Pretrain/Loss": 2.1244428157806396, "Pretrain/Loss (Raw)": 2.225238561630249, "Pretrain/Step": 1441, "Pretrain/Step Time": 8.86569469794631} +{"Pretrain/Learning Rate": 4.809820647566211e-05, "Pretrain/Loss": 2.124587059020996, "Pretrain/Loss (Raw)": 2.0170438289642334, "Pretrain/Step": 1442, "Pretrain/Step Time": 8.864136150106788} +{"Pretrain/Learning Rate": 4.8094957208933635e-05, "Pretrain/Loss": 2.1242244243621826, "Pretrain/Loss (Raw)": 2.159118175506592, "Pretrain/Step": 1443, "Pretrain/Step Time": 8.864383831620216} +{"Pretrain/Learning Rate": 4.809170527878587e-05, "Pretrain/Loss": 2.123843193054199, "Pretrain/Loss (Raw)": 2.0301127433776855, "Pretrain/Step": 1444, "Pretrain/Step Time": 8.873351659625769} +{"Pretrain/Learning Rate": 4.808845068559384e-05, "Pretrain/Loss": 2.121567726135254, "Pretrain/Loss (Raw)": 2.0282979011535645, "Pretrain/Step": 1445, "Pretrain/Step Time": 8.86783817410469} +{"Pretrain/Learning Rate": 4.808519342973289e-05, "Pretrain/Loss": 2.1226158142089844, "Pretrain/Loss (Raw)": 2.1506083011627197, "Pretrain/Step": 1446, "Pretrain/Step Time": 8.870694002136588} +{"Pretrain/Learning Rate": 4.808193351157865e-05, "Pretrain/Loss": 2.1236021518707275, "Pretrain/Loss (Raw)": 2.291748523712158, "Pretrain/Step": 1447, "Pretrain/Step Time": 8.866876317188144} +{"Pretrain/Learning Rate": 4.8078670931507064e-05, "Pretrain/Loss": 2.1227540969848633, "Pretrain/Loss (Raw)": 2.096233367919922, "Pretrain/Step": 1448, "Pretrain/Step Time": 8.869440665468574} +{"Pretrain/Learning Rate": 4.80754056898944e-05, "Pretrain/Loss": 2.12337589263916, "Pretrain/Loss (Raw)": 2.1193125247955322, "Pretrain/Step": 1449, "Pretrain/Step Time": 8.868306461721659} +{"Pretrain/Learning Rate": 4.807213778711722e-05, "Pretrain/Loss": 2.124025344848633, "Pretrain/Loss (Raw)": 2.104266405105591, "Pretrain/Step": 1450, "Pretrain/Step Time": 8.871115515008569} +{"Pretrain/Learning Rate": 4.8068867223552384e-05, "Pretrain/Loss": 2.1233010292053223, "Pretrain/Loss (Raw)": 2.1295411586761475, "Pretrain/Step": 1451, "Pretrain/Step Time": 8.872524870559573} +{"Pretrain/Learning Rate": 4.8065593999577086e-05, "Pretrain/Loss": 2.1242167949676514, "Pretrain/Loss (Raw)": 2.3310582637786865, "Pretrain/Step": 1452, "Pretrain/Step Time": 8.86941034719348} +{"Pretrain/Learning Rate": 4.806231811556879e-05, "Pretrain/Loss": 2.1243886947631836, "Pretrain/Loss (Raw)": 2.16623592376709, "Pretrain/Step": 1453, "Pretrain/Step Time": 8.868356900289655} +{"Pretrain/Learning Rate": 4.80590395719053e-05, "Pretrain/Loss": 2.126277446746826, "Pretrain/Loss (Raw)": 2.2838878631591797, "Pretrain/Step": 1454, "Pretrain/Step Time": 8.870676318183541} +{"Pretrain/Learning Rate": 4.805575836896471e-05, "Pretrain/Loss": 2.1253063678741455, "Pretrain/Loss (Raw)": 2.090965747833252, "Pretrain/Step": 1455, "Pretrain/Step Time": 8.861666455864906} +{"Pretrain/Learning Rate": 4.805247450712542e-05, "Pretrain/Loss": 2.125486373901367, "Pretrain/Loss (Raw)": 2.1369943618774414, "Pretrain/Step": 1456, "Pretrain/Step Time": 8.860559731721878} +{"Pretrain/Learning Rate": 4.804918798676614e-05, "Pretrain/Loss": 2.124452590942383, "Pretrain/Loss (Raw)": 2.0215585231781006, "Pretrain/Step": 1457, "Pretrain/Step Time": 8.864228196442127} +{"Pretrain/Learning Rate": 4.804589880826589e-05, "Pretrain/Loss": 2.125214099884033, "Pretrain/Loss (Raw)": 2.1577181816101074, "Pretrain/Step": 1458, "Pretrain/Step Time": 8.864372557029128} +{"Pretrain/Learning Rate": 4.8042606972004e-05, "Pretrain/Loss": 2.1249334812164307, "Pretrain/Loss (Raw)": 2.0704684257507324, "Pretrain/Step": 1459, "Pretrain/Step Time": 8.862335791811347} +{"Pretrain/Learning Rate": 4.803931247836009e-05, "Pretrain/Loss": 2.1244750022888184, "Pretrain/Loss (Raw)": 2.1020090579986572, "Pretrain/Step": 1460, "Pretrain/Step Time": 8.858699079602957} +{"Pretrain/Learning Rate": 4.80360153277141e-05, "Pretrain/Loss": 2.12323260307312, "Pretrain/Loss (Raw)": 1.9801554679870605, "Pretrain/Step": 1461, "Pretrain/Step Time": 8.86574962735176} +{"Pretrain/Learning Rate": 4.8032715520446275e-05, "Pretrain/Loss": 2.12353515625, "Pretrain/Loss (Raw)": 2.1110610961914062, "Pretrain/Step": 1462, "Pretrain/Step Time": 8.867723774164915} +{"Pretrain/Learning Rate": 4.802941305693716e-05, "Pretrain/Loss": 2.1223511695861816, "Pretrain/Loss (Raw)": 2.0439529418945312, "Pretrain/Step": 1463, "Pretrain/Step Time": 8.871359370648861} +{"Pretrain/Learning Rate": 4.802610793756761e-05, "Pretrain/Loss": 2.122767925262451, "Pretrain/Loss (Raw)": 2.1715526580810547, "Pretrain/Step": 1464, "Pretrain/Step Time": 8.871175352483988} +{"Pretrain/Learning Rate": 4.8022800162718794e-05, "Pretrain/Loss": 2.1231751441955566, "Pretrain/Loss (Raw)": 2.068619966506958, "Pretrain/Step": 1465, "Pretrain/Step Time": 8.881313847377896} +{"Pretrain/Learning Rate": 4.801948973277218e-05, "Pretrain/Loss": 2.1261887550354004, "Pretrain/Loss (Raw)": 2.2890512943267822, "Pretrain/Step": 1466, "Pretrain/Step Time": 8.870936453342438} +{"Pretrain/Learning Rate": 4.8016176648109534e-05, "Pretrain/Loss": 2.1268808841705322, "Pretrain/Loss (Raw)": 2.2020111083984375, "Pretrain/Step": 1467, "Pretrain/Step Time": 8.869094353169203} +{"Pretrain/Learning Rate": 4.801286090911295e-05, "Pretrain/Loss": 2.1281838417053223, "Pretrain/Loss (Raw)": 2.1195671558380127, "Pretrain/Step": 1468, "Pretrain/Step Time": 8.867326717823744} +{"Pretrain/Learning Rate": 4.80095425161648e-05, "Pretrain/Loss": 2.1290106773376465, "Pretrain/Loss (Raw)": 2.1653242111206055, "Pretrain/Step": 1469, "Pretrain/Step Time": 8.869734112173319} +{"Pretrain/Learning Rate": 4.800622146964777e-05, "Pretrain/Loss": 2.130336284637451, "Pretrain/Loss (Raw)": 2.2625627517700195, "Pretrain/Step": 1470, "Pretrain/Step Time": 8.87401075847447} +{"Pretrain/Learning Rate": 4.8002897769944885e-05, "Pretrain/Loss": 2.128188133239746, "Pretrain/Loss (Raw)": 1.919685959815979, "Pretrain/Step": 1471, "Pretrain/Step Time": 8.8789326492697} +{"Pretrain/Learning Rate": 4.799957141743944e-05, "Pretrain/Loss": 2.128495216369629, "Pretrain/Loss (Raw)": 2.184798240661621, "Pretrain/Step": 1472, "Pretrain/Step Time": 8.878897512331605} +{"Pretrain/Learning Rate": 4.799624241251502e-05, "Pretrain/Loss": 2.129621982574463, "Pretrain/Loss (Raw)": 2.1492557525634766, "Pretrain/Step": 1473, "Pretrain/Step Time": 8.885720336809754} +{"Pretrain/Learning Rate": 4.7992910755555584e-05, "Pretrain/Loss": 2.1282012462615967, "Pretrain/Loss (Raw)": 2.1750404834747314, "Pretrain/Step": 1474, "Pretrain/Step Time": 8.876850116997957} +{"Pretrain/Learning Rate": 4.798957644694533e-05, "Pretrain/Loss": 2.1290857791900635, "Pretrain/Loss (Raw)": 2.2895283699035645, "Pretrain/Step": 1475, "Pretrain/Step Time": 8.878043176606297} +{"Pretrain/Learning Rate": 4.7986239487068785e-05, "Pretrain/Loss": 2.129700183868408, "Pretrain/Loss (Raw)": 2.2783408164978027, "Pretrain/Step": 1476, "Pretrain/Step Time": 8.886120239272714} +{"Pretrain/Learning Rate": 4.798289987631079e-05, "Pretrain/Loss": 2.130155563354492, "Pretrain/Loss (Raw)": 2.1425373554229736, "Pretrain/Step": 1477, "Pretrain/Step Time": 8.875506725162268} +{"Pretrain/Learning Rate": 4.797955761505648e-05, "Pretrain/Loss": 2.131394386291504, "Pretrain/Loss (Raw)": 2.2558321952819824, "Pretrain/Step": 1478, "Pretrain/Step Time": 8.884304882958531} +{"Pretrain/Learning Rate": 4.7976212703691306e-05, "Pretrain/Loss": 2.1317367553710938, "Pretrain/Loss (Raw)": 2.2245678901672363, "Pretrain/Step": 1479, "Pretrain/Step Time": 8.884620418772101} +{"Pretrain/Learning Rate": 4.797286514260101e-05, "Pretrain/Loss": 2.130882740020752, "Pretrain/Loss (Raw)": 2.099212884902954, "Pretrain/Step": 1480, "Pretrain/Step Time": 8.889758702367544} +{"Pretrain/Learning Rate": 4.7969514932171665e-05, "Pretrain/Loss": 2.129884719848633, "Pretrain/Loss (Raw)": 1.967674732208252, "Pretrain/Step": 1481, "Pretrain/Step Time": 8.88315911591053} +{"Pretrain/Learning Rate": 4.796616207278961e-05, "Pretrain/Loss": 2.1299750804901123, "Pretrain/Loss (Raw)": 2.191269874572754, "Pretrain/Step": 1482, "Pretrain/Step Time": 8.890314692631364} +{"Pretrain/Learning Rate": 4.796280656484153e-05, "Pretrain/Loss": 2.1309006214141846, "Pretrain/Loss (Raw)": 2.0908820629119873, "Pretrain/Step": 1483, "Pretrain/Step Time": 8.886659070849419} +{"Pretrain/Learning Rate": 4.795944840871439e-05, "Pretrain/Loss": 2.1304378509521484, "Pretrain/Loss (Raw)": 2.099766969680786, "Pretrain/Step": 1484, "Pretrain/Step Time": 8.884465020149946} +{"Pretrain/Learning Rate": 4.7956087604795474e-05, "Pretrain/Loss": 2.1313159465789795, "Pretrain/Loss (Raw)": 2.173628568649292, "Pretrain/Step": 1485, "Pretrain/Step Time": 8.886017311364412} +{"Pretrain/Learning Rate": 4.7952724153472366e-05, "Pretrain/Loss": 2.1307010650634766, "Pretrain/Loss (Raw)": 2.0188839435577393, "Pretrain/Step": 1486, "Pretrain/Step Time": 8.887970559298992} +{"Pretrain/Learning Rate": 4.7949358055132945e-05, "Pretrain/Loss": 2.132563352584839, "Pretrain/Loss (Raw)": 2.3838791847229004, "Pretrain/Step": 1487, "Pretrain/Step Time": 8.882061645388603} +{"Pretrain/Learning Rate": 4.7945989310165415e-05, "Pretrain/Loss": 2.1318366527557373, "Pretrain/Loss (Raw)": 2.1012771129608154, "Pretrain/Step": 1488, "Pretrain/Step Time": 8.882695097476244} +{"Pretrain/Learning Rate": 4.794261791895828e-05, "Pretrain/Loss": 2.1289682388305664, "Pretrain/Loss (Raw)": 2.019768476486206, "Pretrain/Step": 1489, "Pretrain/Step Time": 8.888139443472028} +{"Pretrain/Learning Rate": 4.793924388190033e-05, "Pretrain/Loss": 2.1272165775299072, "Pretrain/Loss (Raw)": 2.0463733673095703, "Pretrain/Step": 1490, "Pretrain/Step Time": 8.886487612500787} +{"Pretrain/Learning Rate": 4.793586719938068e-05, "Pretrain/Loss": 2.127122640609741, "Pretrain/Loss (Raw)": 1.9109225273132324, "Pretrain/Step": 1491, "Pretrain/Step Time": 8.888325773179531} +{"Pretrain/Learning Rate": 4.7932487871788746e-05, "Pretrain/Loss": 2.127260684967041, "Pretrain/Loss (Raw)": 2.163078546524048, "Pretrain/Step": 1492, "Pretrain/Step Time": 8.88694004714489} +{"Pretrain/Learning Rate": 4.792910589951426e-05, "Pretrain/Loss": 2.1262283325195312, "Pretrain/Loss (Raw)": 1.9247461557388306, "Pretrain/Step": 1493, "Pretrain/Step Time": 8.890493234619498} +{"Pretrain/Learning Rate": 4.792572128294722e-05, "Pretrain/Loss": 2.124903678894043, "Pretrain/Loss (Raw)": 1.9350306987762451, "Pretrain/Step": 1494, "Pretrain/Step Time": 8.892403183504939} +{"Pretrain/Learning Rate": 4.792233402247799e-05, "Pretrain/Loss": 2.1251964569091797, "Pretrain/Loss (Raw)": 2.021566867828369, "Pretrain/Step": 1495, "Pretrain/Step Time": 8.8909807857126} +{"Pretrain/Learning Rate": 4.791894411849718e-05, "Pretrain/Loss": 2.1262919902801514, "Pretrain/Loss (Raw)": 2.256094455718994, "Pretrain/Step": 1496, "Pretrain/Step Time": 8.89170022122562} +{"Pretrain/Learning Rate": 4.7915551571395726e-05, "Pretrain/Loss": 2.1271488666534424, "Pretrain/Loss (Raw)": 2.1943037509918213, "Pretrain/Step": 1497, "Pretrain/Step Time": 8.889075266197324} +{"Pretrain/Learning Rate": 4.79121563815649e-05, "Pretrain/Loss": 2.1271042823791504, "Pretrain/Loss (Raw)": 2.0317132472991943, "Pretrain/Step": 1498, "Pretrain/Step Time": 8.890439638867974} +{"Pretrain/Learning Rate": 4.790875854939622e-05, "Pretrain/Loss": 2.126051664352417, "Pretrain/Loss (Raw)": 2.0004425048828125, "Pretrain/Step": 1499, "Pretrain/Step Time": 8.89710932224989} +{"Pretrain/Learning Rate": 4.790535807528156e-05, "Pretrain/Loss": 2.1259756088256836, "Pretrain/Loss (Raw)": 2.046334743499756, "Pretrain/Step": 1500, "Pretrain/Step Time": 8.899173060432076} +{"Pretrain/Learning Rate": 4.7901954959613076e-05, "Pretrain/Loss": 2.125790596008301, "Pretrain/Loss (Raw)": 2.0868825912475586, "Pretrain/Step": 1501, "Pretrain/Step Time": 8.903074065223336} +{"Pretrain/Learning Rate": 4.789854920278323e-05, "Pretrain/Loss": 2.125606060028076, "Pretrain/Loss (Raw)": 2.0515739917755127, "Pretrain/Step": 1502, "Pretrain/Step Time": 8.897294364869595} +{"Pretrain/Learning Rate": 4.789514080518478e-05, "Pretrain/Loss": 2.1251680850982666, "Pretrain/Loss (Raw)": 2.112231969833374, "Pretrain/Step": 1503, "Pretrain/Step Time": 8.898208167403936} +{"Pretrain/Learning Rate": 4.789172976721081e-05, "Pretrain/Loss": 2.125094413757324, "Pretrain/Loss (Raw)": 2.042816400527954, "Pretrain/Step": 1504, "Pretrain/Step Time": 8.890878841280937} +{"Pretrain/Learning Rate": 4.7888316089254705e-05, "Pretrain/Loss": 2.1232616901397705, "Pretrain/Loss (Raw)": 1.993874430656433, "Pretrain/Step": 1505, "Pretrain/Step Time": 8.88970797508955} +{"Pretrain/Learning Rate": 4.7884899771710126e-05, "Pretrain/Loss": 2.124412775039673, "Pretrain/Loss (Raw)": 2.139183759689331, "Pretrain/Step": 1506, "Pretrain/Step Time": 8.893079467117786} +{"Pretrain/Learning Rate": 4.788148081497106e-05, "Pretrain/Loss": 2.1225242614746094, "Pretrain/Loss (Raw)": 2.1563100814819336, "Pretrain/Step": 1507, "Pretrain/Step Time": 8.895374972373247} +{"Pretrain/Learning Rate": 4.787805921943181e-05, "Pretrain/Loss": 2.1228199005126953, "Pretrain/Loss (Raw)": 2.2021992206573486, "Pretrain/Step": 1508, "Pretrain/Step Time": 8.899209797382355} +{"Pretrain/Learning Rate": 4.787463498548698e-05, "Pretrain/Loss": 2.121997833251953, "Pretrain/Loss (Raw)": 1.823644757270813, "Pretrain/Step": 1509, "Pretrain/Step Time": 8.89226509258151} +{"Pretrain/Learning Rate": 4.787120811353144e-05, "Pretrain/Loss": 2.1221628189086914, "Pretrain/Loss (Raw)": 2.229156494140625, "Pretrain/Step": 1510, "Pretrain/Step Time": 8.897081661969423} +{"Pretrain/Learning Rate": 4.786777860396041e-05, "Pretrain/Loss": 2.1197471618652344, "Pretrain/Loss (Raw)": 2.190962076187134, "Pretrain/Step": 1511, "Pretrain/Step Time": 8.899513773620129} +{"Pretrain/Learning Rate": 4.78643464571694e-05, "Pretrain/Loss": 2.1203458309173584, "Pretrain/Loss (Raw)": 1.9555919170379639, "Pretrain/Step": 1512, "Pretrain/Step Time": 8.89575537852943} +{"Pretrain/Learning Rate": 4.786091167355421e-05, "Pretrain/Loss": 2.120628833770752, "Pretrain/Loss (Raw)": 2.181342363357544, "Pretrain/Step": 1513, "Pretrain/Step Time": 8.897308088839054} +{"Pretrain/Learning Rate": 4.785747425351097e-05, "Pretrain/Loss": 2.121330976486206, "Pretrain/Loss (Raw)": 2.154151678085327, "Pretrain/Step": 1514, "Pretrain/Step Time": 8.89732533507049} +{"Pretrain/Learning Rate": 4.785403419743608e-05, "Pretrain/Loss": 2.1209731101989746, "Pretrain/Loss (Raw)": 2.04103684425354, "Pretrain/Step": 1515, "Pretrain/Step Time": 8.89504263177514} +{"Pretrain/Learning Rate": 4.785059150572628e-05, "Pretrain/Loss": 2.1205625534057617, "Pretrain/Loss (Raw)": 2.1025476455688477, "Pretrain/Step": 1516, "Pretrain/Step Time": 8.882376227527857} +{"Pretrain/Learning Rate": 4.784714617877859e-05, "Pretrain/Loss": 2.122021436691284, "Pretrain/Loss (Raw)": 2.3055224418640137, "Pretrain/Step": 1517, "Pretrain/Step Time": 8.89164405874908} +{"Pretrain/Learning Rate": 4.784369821699035e-05, "Pretrain/Loss": 2.121396064758301, "Pretrain/Loss (Raw)": 1.972366213798523, "Pretrain/Step": 1518, "Pretrain/Step Time": 8.88290853612125} +{"Pretrain/Learning Rate": 4.784024762075918e-05, "Pretrain/Loss": 2.120769500732422, "Pretrain/Loss (Raw)": 2.070383310317993, "Pretrain/Step": 1519, "Pretrain/Step Time": 8.884373741224408} +{"Pretrain/Learning Rate": 4.7836794390483035e-05, "Pretrain/Loss": 2.121666193008423, "Pretrain/Loss (Raw)": 2.159611701965332, "Pretrain/Step": 1520, "Pretrain/Step Time": 8.883119232952595} +{"Pretrain/Learning Rate": 4.7833338526560145e-05, "Pretrain/Loss": 2.1203579902648926, "Pretrain/Loss (Raw)": 2.0841829776763916, "Pretrain/Step": 1521, "Pretrain/Step Time": 8.891599357128143} +{"Pretrain/Learning Rate": 4.782988002938907e-05, "Pretrain/Loss": 2.1203315258026123, "Pretrain/Loss (Raw)": 2.130840301513672, "Pretrain/Step": 1522, "Pretrain/Step Time": 8.87917205132544} +{"Pretrain/Learning Rate": 4.782641889936864e-05, "Pretrain/Loss": 2.120016574859619, "Pretrain/Loss (Raw)": 2.097961187362671, "Pretrain/Step": 1523, "Pretrain/Step Time": 8.881553497165442} +{"Pretrain/Learning Rate": 4.782295513689803e-05, "Pretrain/Loss": 2.122403383255005, "Pretrain/Loss (Raw)": 2.473080635070801, "Pretrain/Step": 1524, "Pretrain/Step Time": 8.883519819006324} +{"Pretrain/Learning Rate": 4.7819488742376686e-05, "Pretrain/Loss": 2.122438430786133, "Pretrain/Loss (Raw)": 2.0673673152923584, "Pretrain/Step": 1525, "Pretrain/Step Time": 8.883790465071797} +{"Pretrain/Learning Rate": 4.7816019716204375e-05, "Pretrain/Loss": 2.1236138343811035, "Pretrain/Loss (Raw)": 2.166940689086914, "Pretrain/Step": 1526, "Pretrain/Step Time": 8.877958407625556} +{"Pretrain/Learning Rate": 4.781254805878115e-05, "Pretrain/Loss": 2.125852584838867, "Pretrain/Loss (Raw)": 2.1935081481933594, "Pretrain/Step": 1527, "Pretrain/Step Time": 8.882871195673943} +{"Pretrain/Learning Rate": 4.780907377050739e-05, "Pretrain/Loss": 2.122913360595703, "Pretrain/Loss (Raw)": 1.9786922931671143, "Pretrain/Step": 1528, "Pretrain/Step Time": 8.886933874338865} +{"Pretrain/Learning Rate": 4.780559685178376e-05, "Pretrain/Loss": 2.1235857009887695, "Pretrain/Loss (Raw)": 2.097046136856079, "Pretrain/Step": 1529, "Pretrain/Step Time": 8.873856401070952} +{"Pretrain/Learning Rate": 4.780211730301124e-05, "Pretrain/Loss": 2.124690532684326, "Pretrain/Loss (Raw)": 2.3655121326446533, "Pretrain/Step": 1530, "Pretrain/Step Time": 8.874727385118604} +{"Pretrain/Learning Rate": 4.779863512459111e-05, "Pretrain/Loss": 2.1263551712036133, "Pretrain/Loss (Raw)": 2.1703040599823, "Pretrain/Step": 1531, "Pretrain/Step Time": 8.87101611867547} +{"Pretrain/Learning Rate": 4.779515031692494e-05, "Pretrain/Loss": 2.125859498977661, "Pretrain/Loss (Raw)": 2.1951215267181396, "Pretrain/Step": 1532, "Pretrain/Step Time": 8.87471329048276} +{"Pretrain/Learning Rate": 4.7791662880414625e-05, "Pretrain/Loss": 2.1245856285095215, "Pretrain/Loss (Raw)": 1.9991053342819214, "Pretrain/Step": 1533, "Pretrain/Step Time": 8.875881042331457} +{"Pretrain/Learning Rate": 4.778817281546235e-05, "Pretrain/Loss": 2.124262571334839, "Pretrain/Loss (Raw)": 2.060845136642456, "Pretrain/Step": 1534, "Pretrain/Step Time": 8.872693629935384} +{"Pretrain/Learning Rate": 4.7784680122470605e-05, "Pretrain/Loss": 2.1249728202819824, "Pretrain/Loss (Raw)": 2.1475703716278076, "Pretrain/Step": 1535, "Pretrain/Step Time": 8.871644463390112} +{"Pretrain/Learning Rate": 4.778118480184218e-05, "Pretrain/Loss": 2.124572277069092, "Pretrain/Loss (Raw)": 2.1871862411499023, "Pretrain/Step": 1536, "Pretrain/Step Time": 8.88410483673215} +{"Pretrain/Learning Rate": 4.777768685398017e-05, "Pretrain/Loss": 2.1230924129486084, "Pretrain/Loss (Raw)": 2.0327775478363037, "Pretrain/Step": 1537, "Pretrain/Step Time": 8.875475382432342} +{"Pretrain/Learning Rate": 4.777418627928799e-05, "Pretrain/Loss": 2.122105598449707, "Pretrain/Loss (Raw)": 1.9586597681045532, "Pretrain/Step": 1538, "Pretrain/Step Time": 8.874184608459473} +{"Pretrain/Learning Rate": 4.777068307816932e-05, "Pretrain/Loss": 2.120424270629883, "Pretrain/Loss (Raw)": 1.794765591621399, "Pretrain/Step": 1539, "Pretrain/Step Time": 8.874713741242886} +{"Pretrain/Learning Rate": 4.776717725102819e-05, "Pretrain/Loss": 2.1199910640716553, "Pretrain/Loss (Raw)": 2.114752769470215, "Pretrain/Step": 1540, "Pretrain/Step Time": 8.87670323997736} +{"Pretrain/Learning Rate": 4.77636687982689e-05, "Pretrain/Loss": 2.1192188262939453, "Pretrain/Loss (Raw)": 2.1141114234924316, "Pretrain/Step": 1541, "Pretrain/Step Time": 8.876559184864163} +{"Pretrain/Learning Rate": 4.776015772029605e-05, "Pretrain/Loss": 2.1196532249450684, "Pretrain/Loss (Raw)": 2.0843088626861572, "Pretrain/Step": 1542, "Pretrain/Step Time": 8.877082712948322} +{"Pretrain/Learning Rate": 4.7756644017514564e-05, "Pretrain/Loss": 2.1185965538024902, "Pretrain/Loss (Raw)": 2.0630381107330322, "Pretrain/Step": 1543, "Pretrain/Step Time": 8.875392146408558} +{"Pretrain/Learning Rate": 4.775312769032966e-05, "Pretrain/Loss": 2.117549419403076, "Pretrain/Loss (Raw)": 2.010260820388794, "Pretrain/Step": 1544, "Pretrain/Step Time": 8.879646899178624} +{"Pretrain/Learning Rate": 4.774960873914685e-05, "Pretrain/Loss": 2.114928960800171, "Pretrain/Loss (Raw)": 1.8460018634796143, "Pretrain/Step": 1545, "Pretrain/Step Time": 8.8741455078125} +{"Pretrain/Learning Rate": 4.774608716437196e-05, "Pretrain/Loss": 2.114805221557617, "Pretrain/Loss (Raw)": 2.1143441200256348, "Pretrain/Step": 1546, "Pretrain/Step Time": 8.876045871526003} +{"Pretrain/Learning Rate": 4.7742562966411117e-05, "Pretrain/Loss": 2.115504741668701, "Pretrain/Loss (Raw)": 2.1357944011688232, "Pretrain/Step": 1547, "Pretrain/Step Time": 8.875355692580342} +{"Pretrain/Learning Rate": 4.7739036145670744e-05, "Pretrain/Loss": 2.1150741577148438, "Pretrain/Loss (Raw)": 2.113262891769409, "Pretrain/Step": 1548, "Pretrain/Step Time": 8.877259377390146} +{"Pretrain/Learning Rate": 4.773550670255758e-05, "Pretrain/Loss": 2.1139822006225586, "Pretrain/Loss (Raw)": 2.144256114959717, "Pretrain/Step": 1549, "Pretrain/Step Time": 8.877007512375712} +{"Pretrain/Learning Rate": 4.773197463747865e-05, "Pretrain/Loss": 2.1156210899353027, "Pretrain/Loss (Raw)": 2.145564317703247, "Pretrain/Step": 1550, "Pretrain/Step Time": 8.87306640483439} +{"Pretrain/Learning Rate": 4.772843995084128e-05, "Pretrain/Loss": 2.1165597438812256, "Pretrain/Loss (Raw)": 2.1942975521087646, "Pretrain/Step": 1551, "Pretrain/Step Time": 8.872070301324129} +{"Pretrain/Learning Rate": 4.7724902643053116e-05, "Pretrain/Loss": 2.1174564361572266, "Pretrain/Loss (Raw)": 2.0878875255584717, "Pretrain/Step": 1552, "Pretrain/Step Time": 8.876888347789645} +{"Pretrain/Learning Rate": 4.77213627145221e-05, "Pretrain/Loss": 2.115931749343872, "Pretrain/Loss (Raw)": 2.050790309906006, "Pretrain/Step": 1553, "Pretrain/Step Time": 8.883065739646554} +{"Pretrain/Learning Rate": 4.771782016565647e-05, "Pretrain/Loss": 2.11820125579834, "Pretrain/Loss (Raw)": 2.4828977584838867, "Pretrain/Step": 1554, "Pretrain/Step Time": 8.87828990072012} +{"Pretrain/Learning Rate": 4.771427499686477e-05, "Pretrain/Loss": 2.1181483268737793, "Pretrain/Loss (Raw)": 2.0140414237976074, "Pretrain/Step": 1555, "Pretrain/Step Time": 8.886270180344582} +{"Pretrain/Learning Rate": 4.771072720855584e-05, "Pretrain/Loss": 2.118161678314209, "Pretrain/Loss (Raw)": 2.1600747108459473, "Pretrain/Step": 1556, "Pretrain/Step Time": 8.884466530755162} +{"Pretrain/Learning Rate": 4.770717680113883e-05, "Pretrain/Loss": 2.1180543899536133, "Pretrain/Loss (Raw)": 2.069819450378418, "Pretrain/Step": 1557, "Pretrain/Step Time": 8.883746867999434} +{"Pretrain/Learning Rate": 4.770362377502319e-05, "Pretrain/Loss": 2.117908000946045, "Pretrain/Loss (Raw)": 2.097027540206909, "Pretrain/Step": 1558, "Pretrain/Step Time": 8.883265752345324} +{"Pretrain/Learning Rate": 4.770006813061868e-05, "Pretrain/Loss": 2.1189234256744385, "Pretrain/Loss (Raw)": 2.160621166229248, "Pretrain/Step": 1559, "Pretrain/Step Time": 8.889501061290503} +{"Pretrain/Learning Rate": 4.769650986833535e-05, "Pretrain/Loss": 2.118178367614746, "Pretrain/Loss (Raw)": 1.9637240171432495, "Pretrain/Step": 1560, "Pretrain/Step Time": 8.885811265558004} +{"Pretrain/Learning Rate": 4.769294898858354e-05, "Pretrain/Loss": 2.118234872817993, "Pretrain/Loss (Raw)": 2.163966655731201, "Pretrain/Step": 1561, "Pretrain/Step Time": 8.885070180520415} +{"Pretrain/Learning Rate": 4.768938549177393e-05, "Pretrain/Loss": 2.1174614429473877, "Pretrain/Loss (Raw)": 2.0630042552948, "Pretrain/Step": 1562, "Pretrain/Step Time": 8.886646907776594} +{"Pretrain/Learning Rate": 4.768581937831746e-05, "Pretrain/Loss": 2.117927312850952, "Pretrain/Loss (Raw)": 2.1304118633270264, "Pretrain/Step": 1563, "Pretrain/Step Time": 8.88659912161529} +{"Pretrain/Learning Rate": 4.768225064862541e-05, "Pretrain/Loss": 2.1174356937408447, "Pretrain/Loss (Raw)": 2.1984639167785645, "Pretrain/Step": 1564, "Pretrain/Step Time": 8.884435638785362} +{"Pretrain/Learning Rate": 4.767867930310933e-05, "Pretrain/Loss": 2.117222309112549, "Pretrain/Loss (Raw)": 2.1862401962280273, "Pretrain/Step": 1565, "Pretrain/Step Time": 8.87698694691062} +{"Pretrain/Learning Rate": 4.7675105342181084e-05, "Pretrain/Loss": 2.1161906719207764, "Pretrain/Loss (Raw)": 2.19175386428833, "Pretrain/Step": 1566, "Pretrain/Step Time": 8.883424155414104} +{"Pretrain/Learning Rate": 4.767152876625285e-05, "Pretrain/Loss": 2.116652488708496, "Pretrain/Loss (Raw)": 2.131516695022583, "Pretrain/Step": 1567, "Pretrain/Step Time": 8.88198765926063} +{"Pretrain/Learning Rate": 4.766794957573708e-05, "Pretrain/Loss": 2.1170618534088135, "Pretrain/Loss (Raw)": 2.1561052799224854, "Pretrain/Step": 1568, "Pretrain/Step Time": 8.873566877096891} +{"Pretrain/Learning Rate": 4.766436777104655e-05, "Pretrain/Loss": 2.1174206733703613, "Pretrain/Loss (Raw)": 2.2711706161499023, "Pretrain/Step": 1569, "Pretrain/Step Time": 8.878314634785056} +{"Pretrain/Learning Rate": 4.766078335259433e-05, "Pretrain/Loss": 2.1182522773742676, "Pretrain/Loss (Raw)": 2.123518705368042, "Pretrain/Step": 1570, "Pretrain/Step Time": 8.8837705347687} +{"Pretrain/Learning Rate": 4.76571963207938e-05, "Pretrain/Loss": 2.1185760498046875, "Pretrain/Loss (Raw)": 2.2005081176757812, "Pretrain/Step": 1571, "Pretrain/Step Time": 8.883048072457314} +{"Pretrain/Learning Rate": 4.765360667605861e-05, "Pretrain/Loss": 2.1209867000579834, "Pretrain/Loss (Raw)": 2.338696002960205, "Pretrain/Step": 1572, "Pretrain/Step Time": 8.873455891385674} +{"Pretrain/Learning Rate": 4.765001441880276e-05, "Pretrain/Loss": 2.121426582336426, "Pretrain/Loss (Raw)": 2.0846195220947266, "Pretrain/Step": 1573, "Pretrain/Step Time": 8.871177585795522} +{"Pretrain/Learning Rate": 4.764641954944052e-05, "Pretrain/Loss": 2.1210575103759766, "Pretrain/Loss (Raw)": 2.1033434867858887, "Pretrain/Step": 1574, "Pretrain/Step Time": 8.880173930898309} +{"Pretrain/Learning Rate": 4.764282206838646e-05, "Pretrain/Loss": 2.120131254196167, "Pretrain/Loss (Raw)": 2.1731953620910645, "Pretrain/Step": 1575, "Pretrain/Step Time": 8.88144208304584} +{"Pretrain/Learning Rate": 4.763922197605547e-05, "Pretrain/Loss": 2.1201138496398926, "Pretrain/Loss (Raw)": 2.094001293182373, "Pretrain/Step": 1576, "Pretrain/Step Time": 8.883090682327747} +{"Pretrain/Learning Rate": 4.763561927286271e-05, "Pretrain/Loss": 2.1192290782928467, "Pretrain/Loss (Raw)": 2.0060653686523438, "Pretrain/Step": 1577, "Pretrain/Step Time": 8.884378613904119} +{"Pretrain/Learning Rate": 4.7632013959223684e-05, "Pretrain/Loss": 2.1186490058898926, "Pretrain/Loss (Raw)": 2.030022382736206, "Pretrain/Step": 1578, "Pretrain/Step Time": 8.884163482114673} +{"Pretrain/Learning Rate": 4.7628406035554156e-05, "Pretrain/Loss": 2.119147777557373, "Pretrain/Loss (Raw)": 2.1933727264404297, "Pretrain/Step": 1579, "Pretrain/Step Time": 8.883902652189136} +{"Pretrain/Learning Rate": 4.762479550227022e-05, "Pretrain/Loss": 2.118382692337036, "Pretrain/Loss (Raw)": 2.233146905899048, "Pretrain/Step": 1580, "Pretrain/Step Time": 8.87429204583168} +{"Pretrain/Learning Rate": 4.762118235978825e-05, "Pretrain/Loss": 2.117131233215332, "Pretrain/Loss (Raw)": 2.0060176849365234, "Pretrain/Step": 1581, "Pretrain/Step Time": 8.880104973912239} +{"Pretrain/Learning Rate": 4.7617566608524946e-05, "Pretrain/Loss": 2.118121385574341, "Pretrain/Loss (Raw)": 2.4106547832489014, "Pretrain/Step": 1582, "Pretrain/Step Time": 8.879232481122017} +{"Pretrain/Learning Rate": 4.761394824889727e-05, "Pretrain/Loss": 2.1182007789611816, "Pretrain/Loss (Raw)": 2.101109266281128, "Pretrain/Step": 1583, "Pretrain/Step Time": 8.88330153748393} +{"Pretrain/Learning Rate": 4.761032728132253e-05, "Pretrain/Loss": 2.1179299354553223, "Pretrain/Loss (Raw)": 2.102351665496826, "Pretrain/Step": 1584, "Pretrain/Step Time": 8.88677098043263} +{"Pretrain/Learning Rate": 4.76067037062183e-05, "Pretrain/Loss": 2.1185009479522705, "Pretrain/Loss (Raw)": 2.0946335792541504, "Pretrain/Step": 1585, "Pretrain/Step Time": 8.881385711953044} +{"Pretrain/Learning Rate": 4.7603077524002474e-05, "Pretrain/Loss": 2.1183810234069824, "Pretrain/Loss (Raw)": 2.1423473358154297, "Pretrain/Step": 1586, "Pretrain/Step Time": 8.88537684082985} +{"Pretrain/Learning Rate": 4.759944873509324e-05, "Pretrain/Loss": 2.119267463684082, "Pretrain/Loss (Raw)": 2.18394136428833, "Pretrain/Step": 1587, "Pretrain/Step Time": 8.889405371621251} +{"Pretrain/Learning Rate": 4.7595817339909086e-05, "Pretrain/Loss": 2.1211001873016357, "Pretrain/Loss (Raw)": 2.336604595184326, "Pretrain/Step": 1588, "Pretrain/Step Time": 8.885862704366446} +{"Pretrain/Learning Rate": 4.75921833388688e-05, "Pretrain/Loss": 2.1217050552368164, "Pretrain/Loss (Raw)": 2.057586669921875, "Pretrain/Step": 1589, "Pretrain/Step Time": 8.888416280969977} +{"Pretrain/Learning Rate": 4.758854673239147e-05, "Pretrain/Loss": 2.1222667694091797, "Pretrain/Loss (Raw)": 2.1829323768615723, "Pretrain/Step": 1590, "Pretrain/Step Time": 8.890367690473795} +{"Pretrain/Learning Rate": 4.7584907520896495e-05, "Pretrain/Loss": 2.1222360134124756, "Pretrain/Loss (Raw)": 2.0400285720825195, "Pretrain/Step": 1591, "Pretrain/Step Time": 8.886836601421237} +{"Pretrain/Learning Rate": 4.7581265704803554e-05, "Pretrain/Loss": 2.1218440532684326, "Pretrain/Loss (Raw)": 2.1213784217834473, "Pretrain/Step": 1592, "Pretrain/Step Time": 8.887283373624086} +{"Pretrain/Learning Rate": 4.757762128453266e-05, "Pretrain/Loss": 2.122992992401123, "Pretrain/Loss (Raw)": 2.2156834602355957, "Pretrain/Step": 1593, "Pretrain/Step Time": 8.883180119097233} +{"Pretrain/Learning Rate": 4.757397426050408e-05, "Pretrain/Loss": 2.121283531188965, "Pretrain/Loss (Raw)": 2.0702550411224365, "Pretrain/Step": 1594, "Pretrain/Step Time": 8.881396373733878} +{"Pretrain/Learning Rate": 4.757032463313842e-05, "Pretrain/Loss": 2.1215577125549316, "Pretrain/Loss (Raw)": 2.2371134757995605, "Pretrain/Step": 1595, "Pretrain/Step Time": 8.881414588540792} +{"Pretrain/Learning Rate": 4.756667240285656e-05, "Pretrain/Loss": 2.120934009552002, "Pretrain/Loss (Raw)": 2.0397379398345947, "Pretrain/Step": 1596, "Pretrain/Step Time": 8.875081999227405} +{"Pretrain/Learning Rate": 4.756301757007971e-05, "Pretrain/Loss": 2.1206798553466797, "Pretrain/Loss (Raw)": 2.1327943801879883, "Pretrain/Step": 1597, "Pretrain/Step Time": 8.888803780078888} +{"Pretrain/Learning Rate": 4.755936013522935e-05, "Pretrain/Loss": 2.1209805011749268, "Pretrain/Loss (Raw)": 2.3010525703430176, "Pretrain/Step": 1598, "Pretrain/Step Time": 8.884872378781438} +{"Pretrain/Learning Rate": 4.7555700098727276e-05, "Pretrain/Loss": 2.122347831726074, "Pretrain/Loss (Raw)": 2.0946524143218994, "Pretrain/Step": 1599, "Pretrain/Step Time": 8.881201403215528} +{"Pretrain/Learning Rate": 4.755203746099558e-05, "Pretrain/Loss": 2.1220059394836426, "Pretrain/Loss (Raw)": 2.1410765647888184, "Pretrain/Step": 1600, "Pretrain/Step Time": 8.886129952967167} +{"Pretrain/Learning Rate": 4.754837222245666e-05, "Pretrain/Loss": 2.12172794342041, "Pretrain/Loss (Raw)": 2.1136622428894043, "Pretrain/Step": 1601, "Pretrain/Step Time": 8.879282493144274} +{"Pretrain/Learning Rate": 4.75447043835332e-05, "Pretrain/Loss": 2.1204071044921875, "Pretrain/Loss (Raw)": 2.005951166152954, "Pretrain/Step": 1602, "Pretrain/Step Time": 8.877959681674838} +{"Pretrain/Learning Rate": 4.75410339446482e-05, "Pretrain/Loss": 2.11968731880188, "Pretrain/Loss (Raw)": 2.1974098682403564, "Pretrain/Step": 1603, "Pretrain/Step Time": 8.882506174966693} +{"Pretrain/Learning Rate": 4.753736090622494e-05, "Pretrain/Loss": 2.1177480220794678, "Pretrain/Loss (Raw)": 2.030122756958008, "Pretrain/Step": 1604, "Pretrain/Step Time": 8.878735007718205} +{"Pretrain/Learning Rate": 4.753368526868703e-05, "Pretrain/Loss": 2.117453098297119, "Pretrain/Loss (Raw)": 2.1047873497009277, "Pretrain/Step": 1605, "Pretrain/Step Time": 8.885006388649344} +{"Pretrain/Learning Rate": 4.753000703245834e-05, "Pretrain/Loss": 2.1167855262756348, "Pretrain/Loss (Raw)": 2.170363187789917, "Pretrain/Step": 1606, "Pretrain/Step Time": 8.879819443449378} +{"Pretrain/Learning Rate": 4.752632619796309e-05, "Pretrain/Loss": 2.1163554191589355, "Pretrain/Loss (Raw)": 2.1695287227630615, "Pretrain/Step": 1607, "Pretrain/Step Time": 8.883819995447993} +{"Pretrain/Learning Rate": 4.752264276562575e-05, "Pretrain/Loss": 2.115389823913574, "Pretrain/Loss (Raw)": 1.9756298065185547, "Pretrain/Step": 1608, "Pretrain/Step Time": 8.87697197496891} +{"Pretrain/Learning Rate": 4.751895673587111e-05, "Pretrain/Loss": 2.117537498474121, "Pretrain/Loss (Raw)": 2.24257230758667, "Pretrain/Step": 1609, "Pretrain/Step Time": 8.875472974032164} +{"Pretrain/Learning Rate": 4.751526810912427e-05, "Pretrain/Loss": 2.117741107940674, "Pretrain/Loss (Raw)": 2.217345714569092, "Pretrain/Step": 1610, "Pretrain/Step Time": 8.871734013780951} +{"Pretrain/Learning Rate": 4.751157688581062e-05, "Pretrain/Loss": 2.117250442504883, "Pretrain/Loss (Raw)": 2.0280356407165527, "Pretrain/Step": 1611, "Pretrain/Step Time": 8.882390469312668} +{"Pretrain/Learning Rate": 4.750788306635584e-05, "Pretrain/Loss": 2.116671085357666, "Pretrain/Loss (Raw)": 2.025620937347412, "Pretrain/Step": 1612, "Pretrain/Step Time": 8.882856335490942} +{"Pretrain/Learning Rate": 4.7504186651185926e-05, "Pretrain/Loss": 2.115821361541748, "Pretrain/Loss (Raw)": 2.0648550987243652, "Pretrain/Step": 1613, "Pretrain/Step Time": 8.883885065093637} +{"Pretrain/Learning Rate": 4.7500487640727165e-05, "Pretrain/Loss": 2.115600824356079, "Pretrain/Loss (Raw)": 1.9907026290893555, "Pretrain/Step": 1614, "Pretrain/Step Time": 8.881049789488316} +{"Pretrain/Learning Rate": 4.7496786035406144e-05, "Pretrain/Loss": 2.113969326019287, "Pretrain/Loss (Raw)": 2.1749916076660156, "Pretrain/Step": 1615, "Pretrain/Step Time": 8.884763916954398} +{"Pretrain/Learning Rate": 4.749308183564974e-05, "Pretrain/Loss": 2.11452579498291, "Pretrain/Loss (Raw)": 2.1725244522094727, "Pretrain/Step": 1616, "Pretrain/Step Time": 8.885101769119501} +{"Pretrain/Learning Rate": 4.748937504188517e-05, "Pretrain/Loss": 2.1157572269439697, "Pretrain/Loss (Raw)": 2.1773874759674072, "Pretrain/Step": 1617, "Pretrain/Step Time": 8.879693133756518} +{"Pretrain/Learning Rate": 4.748566565453988e-05, "Pretrain/Loss": 2.1170496940612793, "Pretrain/Loss (Raw)": 2.2118215560913086, "Pretrain/Step": 1618, "Pretrain/Step Time": 8.890916710719466} +{"Pretrain/Learning Rate": 4.748195367404167e-05, "Pretrain/Loss": 2.1180427074432373, "Pretrain/Loss (Raw)": 2.038025140762329, "Pretrain/Step": 1619, "Pretrain/Step Time": 8.882802931591868} +{"Pretrain/Learning Rate": 4.747823910081863e-05, "Pretrain/Loss": 2.119274616241455, "Pretrain/Loss (Raw)": 2.320782423019409, "Pretrain/Step": 1620, "Pretrain/Step Time": 8.881645374000072} +{"Pretrain/Learning Rate": 4.747452193529913e-05, "Pretrain/Loss": 2.1239800453186035, "Pretrain/Loss (Raw)": 2.5270326137542725, "Pretrain/Step": 1621, "Pretrain/Step Time": 8.879519674926996} +{"Pretrain/Learning Rate": 4.747080217791187e-05, "Pretrain/Loss": 2.1253230571746826, "Pretrain/Loss (Raw)": 2.1069257259368896, "Pretrain/Step": 1622, "Pretrain/Step Time": 8.87730272859335} +{"Pretrain/Learning Rate": 4.7467079829085804e-05, "Pretrain/Loss": 2.12477707862854, "Pretrain/Loss (Raw)": 1.9516942501068115, "Pretrain/Step": 1623, "Pretrain/Step Time": 8.877468563616276} +{"Pretrain/Learning Rate": 4.746335488925022e-05, "Pretrain/Loss": 2.1222891807556152, "Pretrain/Loss (Raw)": 1.9376308917999268, "Pretrain/Step": 1624, "Pretrain/Step Time": 8.878904949873686} +{"Pretrain/Learning Rate": 4.7459627358834716e-05, "Pretrain/Loss": 2.120305061340332, "Pretrain/Loss (Raw)": 1.9403328895568848, "Pretrain/Step": 1625, "Pretrain/Step Time": 8.876843716949224} +{"Pretrain/Learning Rate": 4.7455897238269134e-05, "Pretrain/Loss": 2.1218748092651367, "Pretrain/Loss (Raw)": 2.232649803161621, "Pretrain/Step": 1626, "Pretrain/Step Time": 8.873351354151964} +{"Pretrain/Learning Rate": 4.745216452798368e-05, "Pretrain/Loss": 2.122419834136963, "Pretrain/Loss (Raw)": 2.070202589035034, "Pretrain/Step": 1627, "Pretrain/Step Time": 8.875229666009545} +{"Pretrain/Learning Rate": 4.744842922840881e-05, "Pretrain/Loss": 2.1220102310180664, "Pretrain/Loss (Raw)": 1.993906021118164, "Pretrain/Step": 1628, "Pretrain/Step Time": 8.880407620221376} +{"Pretrain/Learning Rate": 4.74446913399753e-05, "Pretrain/Loss": 2.123373031616211, "Pretrain/Loss (Raw)": 2.261327028274536, "Pretrain/Step": 1629, "Pretrain/Step Time": 8.885782139375806} +{"Pretrain/Learning Rate": 4.744095086311422e-05, "Pretrain/Loss": 2.124105930328369, "Pretrain/Loss (Raw)": 2.145411491394043, "Pretrain/Step": 1630, "Pretrain/Step Time": 8.87905278429389} +{"Pretrain/Learning Rate": 4.743720779825694e-05, "Pretrain/Loss": 2.124081611633301, "Pretrain/Loss (Raw)": 2.1091034412384033, "Pretrain/Step": 1631, "Pretrain/Step Time": 8.884981952607632} +{"Pretrain/Learning Rate": 4.743346214583514e-05, "Pretrain/Loss": 2.1252689361572266, "Pretrain/Loss (Raw)": 2.1947731971740723, "Pretrain/Step": 1632, "Pretrain/Step Time": 8.880438124760985} +{"Pretrain/Learning Rate": 4.742971390628076e-05, "Pretrain/Loss": 2.1258537769317627, "Pretrain/Loss (Raw)": 2.0687379837036133, "Pretrain/Step": 1633, "Pretrain/Step Time": 8.880640719085932} +{"Pretrain/Learning Rate": 4.742596308002609e-05, "Pretrain/Loss": 2.126784324645996, "Pretrain/Loss (Raw)": 2.2582943439483643, "Pretrain/Step": 1634, "Pretrain/Step Time": 8.884244088083506} +{"Pretrain/Learning Rate": 4.742220966750368e-05, "Pretrain/Loss": 2.126566171646118, "Pretrain/Loss (Raw)": 2.1283984184265137, "Pretrain/Step": 1635, "Pretrain/Step Time": 8.885898917913437} +{"Pretrain/Learning Rate": 4.7418453669146404e-05, "Pretrain/Loss": 2.1252331733703613, "Pretrain/Loss (Raw)": 2.0315592288970947, "Pretrain/Step": 1636, "Pretrain/Step Time": 8.887791771441698} +{"Pretrain/Learning Rate": 4.74146950853874e-05, "Pretrain/Loss": 2.1268720626831055, "Pretrain/Loss (Raw)": 2.033444881439209, "Pretrain/Step": 1637, "Pretrain/Step Time": 8.887914502993226} +{"Pretrain/Learning Rate": 4.741093391666014e-05, "Pretrain/Loss": 2.1268391609191895, "Pretrain/Loss (Raw)": 2.224932909011841, "Pretrain/Step": 1638, "Pretrain/Step Time": 8.88146567903459} +{"Pretrain/Learning Rate": 4.7407170163398375e-05, "Pretrain/Loss": 2.1261274814605713, "Pretrain/Loss (Raw)": 2.099874973297119, "Pretrain/Step": 1639, "Pretrain/Step Time": 8.881362307816744} +{"Pretrain/Learning Rate": 4.740340382603616e-05, "Pretrain/Loss": 2.1261799335479736, "Pretrain/Loss (Raw)": 1.962318778038025, "Pretrain/Step": 1640, "Pretrain/Step Time": 8.873585991561413} +{"Pretrain/Learning Rate": 4.739963490500785e-05, "Pretrain/Loss": 2.125563859939575, "Pretrain/Loss (Raw)": 2.1024744510650635, "Pretrain/Step": 1641, "Pretrain/Step Time": 8.880113035440445} +{"Pretrain/Learning Rate": 4.7395863400748096e-05, "Pretrain/Loss": 2.125338077545166, "Pretrain/Loss (Raw)": 2.125227689743042, "Pretrain/Step": 1642, "Pretrain/Step Time": 8.874122699722648} +{"Pretrain/Learning Rate": 4.7392089313691835e-05, "Pretrain/Loss": 2.126535177230835, "Pretrain/Loss (Raw)": 2.194276809692383, "Pretrain/Step": 1643, "Pretrain/Step Time": 8.872478345409036} +{"Pretrain/Learning Rate": 4.738831264427432e-05, "Pretrain/Loss": 2.127591371536255, "Pretrain/Loss (Raw)": 2.237739324569702, "Pretrain/Step": 1644, "Pretrain/Step Time": 8.875650009140372} +{"Pretrain/Learning Rate": 4.73845333929311e-05, "Pretrain/Loss": 2.125239849090576, "Pretrain/Loss (Raw)": 2.004533052444458, "Pretrain/Step": 1645, "Pretrain/Step Time": 8.871216477826238} +{"Pretrain/Learning Rate": 4.738075156009801e-05, "Pretrain/Loss": 2.126969814300537, "Pretrain/Loss (Raw)": 2.193772315979004, "Pretrain/Step": 1646, "Pretrain/Step Time": 8.874842355027795} +{"Pretrain/Learning Rate": 4.737696714621118e-05, "Pretrain/Loss": 2.126418113708496, "Pretrain/Loss (Raw)": 1.99979829788208, "Pretrain/Step": 1647, "Pretrain/Step Time": 8.872023552656174} +{"Pretrain/Learning Rate": 4.7373180151707065e-05, "Pretrain/Loss": 2.1274049282073975, "Pretrain/Loss (Raw)": 2.285905599594116, "Pretrain/Step": 1648, "Pretrain/Step Time": 8.873225010931492} +{"Pretrain/Learning Rate": 4.7369390577022385e-05, "Pretrain/Loss": 2.1282317638397217, "Pretrain/Loss (Raw)": 2.190032482147217, "Pretrain/Step": 1649, "Pretrain/Step Time": 8.871660666540265} +{"Pretrain/Learning Rate": 4.736559842259417e-05, "Pretrain/Loss": 2.128480911254883, "Pretrain/Loss (Raw)": 2.1627070903778076, "Pretrain/Step": 1650, "Pretrain/Step Time": 8.871334619820118} +{"Pretrain/Learning Rate": 4.736180368885976e-05, "Pretrain/Loss": 2.1287283897399902, "Pretrain/Loss (Raw)": 2.1296463012695312, "Pretrain/Step": 1651, "Pretrain/Step Time": 8.871512999758124} +{"Pretrain/Learning Rate": 4.735800637625678e-05, "Pretrain/Loss": 2.125486135482788, "Pretrain/Loss (Raw)": 2.0580837726593018, "Pretrain/Step": 1652, "Pretrain/Step Time": 8.866156497970223} +{"Pretrain/Learning Rate": 4.735420648522314e-05, "Pretrain/Loss": 2.124734401702881, "Pretrain/Loss (Raw)": 1.9711405038833618, "Pretrain/Step": 1653, "Pretrain/Step Time": 8.866417808458209} +{"Pretrain/Learning Rate": 4.7350404016197083e-05, "Pretrain/Loss": 2.1234538555145264, "Pretrain/Loss (Raw)": 2.0030481815338135, "Pretrain/Step": 1654, "Pretrain/Step Time": 8.866636399179697} +{"Pretrain/Learning Rate": 4.734659896961711e-05, "Pretrain/Loss": 2.124476909637451, "Pretrain/Loss (Raw)": 2.3244545459747314, "Pretrain/Step": 1655, "Pretrain/Step Time": 8.861741378903389} +{"Pretrain/Learning Rate": 4.734279134592204e-05, "Pretrain/Loss": 2.1281979084014893, "Pretrain/Loss (Raw)": 2.454984426498413, "Pretrain/Step": 1656, "Pretrain/Step Time": 8.867243083193898} +{"Pretrain/Learning Rate": 4.7338981145550994e-05, "Pretrain/Loss": 2.128298759460449, "Pretrain/Loss (Raw)": 2.1099352836608887, "Pretrain/Step": 1657, "Pretrain/Step Time": 8.867327531799674} +{"Pretrain/Learning Rate": 4.7335168368943374e-05, "Pretrain/Loss": 2.127270221710205, "Pretrain/Loss (Raw)": 2.233860969543457, "Pretrain/Step": 1658, "Pretrain/Step Time": 8.869625119492412} +{"Pretrain/Learning Rate": 4.733135301653889e-05, "Pretrain/Loss": 2.1266214847564697, "Pretrain/Loss (Raw)": 2.0872726440429688, "Pretrain/Step": 1659, "Pretrain/Step Time": 8.871294051408768} +{"Pretrain/Learning Rate": 4.732753508877755e-05, "Pretrain/Loss": 2.1258373260498047, "Pretrain/Loss (Raw)": 2.094731569290161, "Pretrain/Step": 1660, "Pretrain/Step Time": 8.868008565157652} +{"Pretrain/Learning Rate": 4.732371458609966e-05, "Pretrain/Loss": 2.1262340545654297, "Pretrain/Loss (Raw)": 2.0498716831207275, "Pretrain/Step": 1661, "Pretrain/Step Time": 8.869048845022917} +{"Pretrain/Learning Rate": 4.73198915089458e-05, "Pretrain/Loss": 2.126660108566284, "Pretrain/Loss (Raw)": 2.1153929233551025, "Pretrain/Step": 1662, "Pretrain/Step Time": 8.86956924200058} +{"Pretrain/Learning Rate": 4.731606585775689e-05, "Pretrain/Loss": 2.125852108001709, "Pretrain/Loss (Raw)": 2.0441646575927734, "Pretrain/Step": 1663, "Pretrain/Step Time": 8.869474612176418} +{"Pretrain/Learning Rate": 4.731223763297409e-05, "Pretrain/Loss": 2.124738931655884, "Pretrain/Loss (Raw)": 2.0446996688842773, "Pretrain/Step": 1664, "Pretrain/Step Time": 8.864135069772601} +{"Pretrain/Learning Rate": 4.730840683503892e-05, "Pretrain/Loss": 2.1268064975738525, "Pretrain/Loss (Raw)": 2.297435998916626, "Pretrain/Step": 1665, "Pretrain/Step Time": 8.86855155788362} +{"Pretrain/Learning Rate": 4.730457346439315e-05, "Pretrain/Loss": 2.1277503967285156, "Pretrain/Loss (Raw)": 2.079463481903076, "Pretrain/Step": 1666, "Pretrain/Step Time": 8.874752717092633} +{"Pretrain/Learning Rate": 4.7300737521478863e-05, "Pretrain/Loss": 2.1300430297851562, "Pretrain/Loss (Raw)": 2.0882320404052734, "Pretrain/Step": 1667, "Pretrain/Step Time": 8.875029867514968} +{"Pretrain/Learning Rate": 4.729689900673845e-05, "Pretrain/Loss": 2.130253791809082, "Pretrain/Loss (Raw)": 2.141709566116333, "Pretrain/Step": 1668, "Pretrain/Step Time": 8.875367995351553} +{"Pretrain/Learning Rate": 4.729305792061457e-05, "Pretrain/Loss": 2.1298301219940186, "Pretrain/Loss (Raw)": 2.0598883628845215, "Pretrain/Step": 1669, "Pretrain/Step Time": 8.878599096089602} +{"Pretrain/Learning Rate": 4.72892142635502e-05, "Pretrain/Loss": 2.129145383834839, "Pretrain/Loss (Raw)": 1.9966752529144287, "Pretrain/Step": 1670, "Pretrain/Step Time": 8.876262227073312} +{"Pretrain/Learning Rate": 4.728536803598862e-05, "Pretrain/Loss": 2.130399703979492, "Pretrain/Loss (Raw)": 2.2235982418060303, "Pretrain/Step": 1671, "Pretrain/Step Time": 8.876586774364114} +{"Pretrain/Learning Rate": 4.728151923837337e-05, "Pretrain/Loss": 2.1304190158843994, "Pretrain/Loss (Raw)": 2.012723207473755, "Pretrain/Step": 1672, "Pretrain/Step Time": 8.880223339423537} +{"Pretrain/Learning Rate": 4.727766787114835e-05, "Pretrain/Loss": 2.134049415588379, "Pretrain/Loss (Raw)": 2.3107221126556396, "Pretrain/Step": 1673, "Pretrain/Step Time": 8.878406843170524} +{"Pretrain/Learning Rate": 4.727381393475767e-05, "Pretrain/Loss": 2.1328697204589844, "Pretrain/Loss (Raw)": 1.9633023738861084, "Pretrain/Step": 1674, "Pretrain/Step Time": 8.87925230897963} +{"Pretrain/Learning Rate": 4.726995742964583e-05, "Pretrain/Loss": 2.131404161453247, "Pretrain/Loss (Raw)": 1.9482128620147705, "Pretrain/Step": 1675, "Pretrain/Step Time": 8.879446480423212} +{"Pretrain/Learning Rate": 4.726609835625755e-05, "Pretrain/Loss": 2.1320528984069824, "Pretrain/Loss (Raw)": 2.196307897567749, "Pretrain/Step": 1676, "Pretrain/Step Time": 8.880611130967736} +{"Pretrain/Learning Rate": 4.726223671503789e-05, "Pretrain/Loss": 2.1316962242126465, "Pretrain/Loss (Raw)": 2.098605155944824, "Pretrain/Step": 1677, "Pretrain/Step Time": 8.882846340537071} +{"Pretrain/Learning Rate": 4.725837250643218e-05, "Pretrain/Loss": 2.131326198577881, "Pretrain/Loss (Raw)": 2.0981802940368652, "Pretrain/Step": 1678, "Pretrain/Step Time": 8.884823333472013} +{"Pretrain/Learning Rate": 4.7254505730886075e-05, "Pretrain/Loss": 2.1320741176605225, "Pretrain/Loss (Raw)": 2.2900497913360596, "Pretrain/Step": 1679, "Pretrain/Step Time": 8.882444106042385} +{"Pretrain/Learning Rate": 4.725063638884551e-05, "Pretrain/Loss": 2.131556749343872, "Pretrain/Loss (Raw)": 2.0216684341430664, "Pretrain/Step": 1680, "Pretrain/Step Time": 8.877586174756289} +{"Pretrain/Learning Rate": 4.724676448075669e-05, "Pretrain/Loss": 2.1317508220672607, "Pretrain/Loss (Raw)": 2.0756287574768066, "Pretrain/Step": 1681, "Pretrain/Step Time": 8.87720824033022} +{"Pretrain/Learning Rate": 4.724289000706617e-05, "Pretrain/Loss": 2.1283183097839355, "Pretrain/Loss (Raw)": 2.043539047241211, "Pretrain/Step": 1682, "Pretrain/Step Time": 8.881853701546788} +{"Pretrain/Learning Rate": 4.723901296822076e-05, "Pretrain/Loss": 2.127333641052246, "Pretrain/Loss (Raw)": 1.8879706859588623, "Pretrain/Step": 1683, "Pretrain/Step Time": 8.872566428035498} +{"Pretrain/Learning Rate": 4.723513336466759e-05, "Pretrain/Loss": 2.1269922256469727, "Pretrain/Loss (Raw)": 2.1164000034332275, "Pretrain/Step": 1684, "Pretrain/Step Time": 8.874728977680206} +{"Pretrain/Learning Rate": 4.723125119685405e-05, "Pretrain/Loss": 2.125993490219116, "Pretrain/Loss (Raw)": 1.9419662952423096, "Pretrain/Step": 1685, "Pretrain/Step Time": 8.875162271782756} +{"Pretrain/Learning Rate": 4.722736646522788e-05, "Pretrain/Loss": 2.1260437965393066, "Pretrain/Loss (Raw)": 2.1034750938415527, "Pretrain/Step": 1686, "Pretrain/Step Time": 8.869606642052531} +{"Pretrain/Learning Rate": 4.722347917023706e-05, "Pretrain/Loss": 2.1258039474487305, "Pretrain/Loss (Raw)": 2.12994384765625, "Pretrain/Step": 1687, "Pretrain/Step Time": 8.877256963402033} +{"Pretrain/Learning Rate": 4.72195893123299e-05, "Pretrain/Loss": 2.1266896724700928, "Pretrain/Loss (Raw)": 2.0770792961120605, "Pretrain/Step": 1688, "Pretrain/Step Time": 8.875013118609786} +{"Pretrain/Learning Rate": 4.7215696891955006e-05, "Pretrain/Loss": 2.126798629760742, "Pretrain/Loss (Raw)": 2.1779050827026367, "Pretrain/Step": 1689, "Pretrain/Step Time": 8.871783962473273} +{"Pretrain/Learning Rate": 4.721180190956126e-05, "Pretrain/Loss": 2.12857723236084, "Pretrain/Loss (Raw)": 2.2906737327575684, "Pretrain/Step": 1690, "Pretrain/Step Time": 8.872866408899426} +{"Pretrain/Learning Rate": 4.7207904365597855e-05, "Pretrain/Loss": 2.128767967224121, "Pretrain/Loss (Raw)": 2.1547961235046387, "Pretrain/Step": 1691, "Pretrain/Step Time": 8.87281426973641} +{"Pretrain/Learning Rate": 4.720400426051427e-05, "Pretrain/Loss": 2.1273279190063477, "Pretrain/Loss (Raw)": 2.014157772064209, "Pretrain/Step": 1692, "Pretrain/Step Time": 8.874628799036145} +{"Pretrain/Learning Rate": 4.720010159476028e-05, "Pretrain/Loss": 2.1267051696777344, "Pretrain/Loss (Raw)": 2.1065220832824707, "Pretrain/Step": 1693, "Pretrain/Step Time": 8.877496525645256} +{"Pretrain/Learning Rate": 4.719619636878597e-05, "Pretrain/Loss": 2.1255664825439453, "Pretrain/Loss (Raw)": 2.0460011959075928, "Pretrain/Step": 1694, "Pretrain/Step Time": 8.87115572206676} +{"Pretrain/Learning Rate": 4.71922885830417e-05, "Pretrain/Loss": 2.125699996948242, "Pretrain/Loss (Raw)": 2.148646116256714, "Pretrain/Step": 1695, "Pretrain/Step Time": 8.879929438233376} +{"Pretrain/Learning Rate": 4.718837823797814e-05, "Pretrain/Loss": 2.1252684593200684, "Pretrain/Loss (Raw)": 2.1008293628692627, "Pretrain/Step": 1696, "Pretrain/Step Time": 8.880102755501866} +{"Pretrain/Learning Rate": 4.7184465334046246e-05, "Pretrain/Loss": 2.1251702308654785, "Pretrain/Loss (Raw)": 2.2585842609405518, "Pretrain/Step": 1697, "Pretrain/Step Time": 8.875156013295054} +{"Pretrain/Learning Rate": 4.718054987169727e-05, "Pretrain/Loss": 2.1247949600219727, "Pretrain/Loss (Raw)": 2.075526475906372, "Pretrain/Step": 1698, "Pretrain/Step Time": 8.873637346550822} +{"Pretrain/Learning Rate": 4.717663185138276e-05, "Pretrain/Loss": 2.123647689819336, "Pretrain/Loss (Raw)": 2.0536229610443115, "Pretrain/Step": 1699, "Pretrain/Step Time": 8.875288667157292} +{"Pretrain/Learning Rate": 4.7172711273554576e-05, "Pretrain/Loss": 2.1220741271972656, "Pretrain/Loss (Raw)": 2.137291193008423, "Pretrain/Step": 1700, "Pretrain/Step Time": 8.876882566139102} +{"Pretrain/Learning Rate": 4.7168788138664845e-05, "Pretrain/Loss": 2.122696876525879, "Pretrain/Loss (Raw)": 2.164318084716797, "Pretrain/Step": 1701, "Pretrain/Step Time": 8.878951013088226} +{"Pretrain/Learning Rate": 4.7164862447165995e-05, "Pretrain/Loss": 2.120673418045044, "Pretrain/Loss (Raw)": 1.8443689346313477, "Pretrain/Step": 1702, "Pretrain/Step Time": 8.875372391194105} +{"Pretrain/Learning Rate": 4.716093419951077e-05, "Pretrain/Loss": 2.119678497314453, "Pretrain/Loss (Raw)": 2.0458362102508545, "Pretrain/Step": 1703, "Pretrain/Step Time": 8.878191087394953} +{"Pretrain/Learning Rate": 4.7157003396152184e-05, "Pretrain/Loss": 2.119828462600708, "Pretrain/Loss (Raw)": 2.113184928894043, "Pretrain/Step": 1704, "Pretrain/Step Time": 8.879189137369394} +{"Pretrain/Learning Rate": 4.715307003754356e-05, "Pretrain/Loss": 2.120802402496338, "Pretrain/Loss (Raw)": 2.130722761154175, "Pretrain/Step": 1705, "Pretrain/Step Time": 8.87758389301598} +{"Pretrain/Learning Rate": 4.714913412413851e-05, "Pretrain/Loss": 2.1214804649353027, "Pretrain/Loss (Raw)": 2.1168248653411865, "Pretrain/Step": 1706, "Pretrain/Step Time": 8.8799764867872} +{"Pretrain/Learning Rate": 4.714519565639095e-05, "Pretrain/Loss": 2.1207847595214844, "Pretrain/Loss (Raw)": 2.1043410301208496, "Pretrain/Step": 1707, "Pretrain/Step Time": 8.881460309028625} +{"Pretrain/Learning Rate": 4.714125463475506e-05, "Pretrain/Loss": 2.121412754058838, "Pretrain/Loss (Raw)": 2.313538074493408, "Pretrain/Step": 1708, "Pretrain/Step Time": 8.881029173731804} +{"Pretrain/Learning Rate": 4.713731105968536e-05, "Pretrain/Loss": 2.122443199157715, "Pretrain/Loss (Raw)": 2.137885332107544, "Pretrain/Step": 1709, "Pretrain/Step Time": 8.888842331245542} +{"Pretrain/Learning Rate": 4.7133364931636644e-05, "Pretrain/Loss": 2.1202101707458496, "Pretrain/Loss (Raw)": 2.124826431274414, "Pretrain/Step": 1710, "Pretrain/Step Time": 8.884460899978876} +{"Pretrain/Learning Rate": 4.712941625106398e-05, "Pretrain/Loss": 2.118171215057373, "Pretrain/Loss (Raw)": 1.840161919593811, "Pretrain/Step": 1711, "Pretrain/Step Time": 8.884875778108835} +{"Pretrain/Learning Rate": 4.7125465018422755e-05, "Pretrain/Loss": 2.118337631225586, "Pretrain/Loss (Raw)": 2.123622179031372, "Pretrain/Step": 1712, "Pretrain/Step Time": 8.882930137217045} +{"Pretrain/Learning Rate": 4.7121511234168644e-05, "Pretrain/Loss": 2.119810104370117, "Pretrain/Loss (Raw)": 2.2831196784973145, "Pretrain/Step": 1713, "Pretrain/Step Time": 8.888071972876787} +{"Pretrain/Learning Rate": 4.711755489875762e-05, "Pretrain/Loss": 2.1207399368286133, "Pretrain/Loss (Raw)": 2.261359691619873, "Pretrain/Step": 1714, "Pretrain/Step Time": 8.884258400648832} +{"Pretrain/Learning Rate": 4.711359601264594e-05, "Pretrain/Loss": 2.120342254638672, "Pretrain/Loss (Raw)": 2.1330413818359375, "Pretrain/Step": 1715, "Pretrain/Step Time": 8.88461478613317} +{"Pretrain/Learning Rate": 4.7109634576290175e-05, "Pretrain/Loss": 2.1191835403442383, "Pretrain/Loss (Raw)": 2.188274621963501, "Pretrain/Step": 1716, "Pretrain/Step Time": 8.891917338594794} +{"Pretrain/Learning Rate": 4.710567059014716e-05, "Pretrain/Loss": 2.1194510459899902, "Pretrain/Loss (Raw)": 2.091827630996704, "Pretrain/Step": 1717, "Pretrain/Step Time": 8.881047450006008} +{"Pretrain/Learning Rate": 4.710170405467405e-05, "Pretrain/Loss": 2.119887351989746, "Pretrain/Loss (Raw)": 2.238814115524292, "Pretrain/Step": 1718, "Pretrain/Step Time": 8.881533773615956} +{"Pretrain/Learning Rate": 4.709773497032828e-05, "Pretrain/Loss": 2.1202080249786377, "Pretrain/Loss (Raw)": 2.0810699462890625, "Pretrain/Step": 1719, "Pretrain/Step Time": 8.874622117727995} +{"Pretrain/Learning Rate": 4.7093763337567585e-05, "Pretrain/Loss": 2.1201651096343994, "Pretrain/Loss (Raw)": 2.1158671379089355, "Pretrain/Step": 1720, "Pretrain/Step Time": 8.881150539964437} +{"Pretrain/Learning Rate": 4.708978915685e-05, "Pretrain/Loss": 2.119424343109131, "Pretrain/Loss (Raw)": 2.1208786964416504, "Pretrain/Step": 1721, "Pretrain/Step Time": 8.871697099879384} +{"Pretrain/Learning Rate": 4.708581242863382e-05, "Pretrain/Loss": 2.1207423210144043, "Pretrain/Loss (Raw)": 2.238966703414917, "Pretrain/Step": 1722, "Pretrain/Step Time": 8.873626098036766} +{"Pretrain/Learning Rate": 4.7081833153377694e-05, "Pretrain/Loss": 2.120377540588379, "Pretrain/Loss (Raw)": 2.190399169921875, "Pretrain/Step": 1723, "Pretrain/Step Time": 8.876306172460318} +{"Pretrain/Learning Rate": 4.707785133154051e-05, "Pretrain/Loss": 2.121870517730713, "Pretrain/Loss (Raw)": 2.230854034423828, "Pretrain/Step": 1724, "Pretrain/Step Time": 8.87925778515637} +{"Pretrain/Learning Rate": 4.707386696358148e-05, "Pretrain/Loss": 2.1216769218444824, "Pretrain/Loss (Raw)": 2.1080093383789062, "Pretrain/Step": 1725, "Pretrain/Step Time": 8.867588156834245} +{"Pretrain/Learning Rate": 4.7069880049960104e-05, "Pretrain/Loss": 2.1195731163024902, "Pretrain/Loss (Raw)": 2.031745433807373, "Pretrain/Step": 1726, "Pretrain/Step Time": 8.86942028440535} +{"Pretrain/Learning Rate": 4.7065890591136154e-05, "Pretrain/Loss": 2.1176161766052246, "Pretrain/Loss (Raw)": 1.8442071676254272, "Pretrain/Step": 1727, "Pretrain/Step Time": 8.870823977515101} +{"Pretrain/Learning Rate": 4.706189858756972e-05, "Pretrain/Loss": 2.116860866546631, "Pretrain/Loss (Raw)": 2.0443496704101562, "Pretrain/Step": 1728, "Pretrain/Step Time": 8.866979472339153} +{"Pretrain/Learning Rate": 4.705790403972119e-05, "Pretrain/Loss": 2.117257833480835, "Pretrain/Loss (Raw)": 2.1644952297210693, "Pretrain/Step": 1729, "Pretrain/Step Time": 8.863082990050316} +{"Pretrain/Learning Rate": 4.705390694805122e-05, "Pretrain/Loss": 2.118690013885498, "Pretrain/Loss (Raw)": 2.1892905235290527, "Pretrain/Step": 1730, "Pretrain/Step Time": 8.871098645031452} +{"Pretrain/Learning Rate": 4.704990731302078e-05, "Pretrain/Loss": 2.118039131164551, "Pretrain/Loss (Raw)": 2.114063262939453, "Pretrain/Step": 1731, "Pretrain/Step Time": 8.868643397465348} +{"Pretrain/Learning Rate": 4.7045905135091126e-05, "Pretrain/Loss": 2.1185302734375, "Pretrain/Loss (Raw)": 2.0930025577545166, "Pretrain/Step": 1732, "Pretrain/Step Time": 8.867707662284374} +{"Pretrain/Learning Rate": 4.704190041472381e-05, "Pretrain/Loss": 2.119638204574585, "Pretrain/Loss (Raw)": 2.246598243713379, "Pretrain/Step": 1733, "Pretrain/Step Time": 8.865560570731759} +{"Pretrain/Learning Rate": 4.703789315238067e-05, "Pretrain/Loss": 2.1183829307556152, "Pretrain/Loss (Raw)": 2.0096817016601562, "Pretrain/Step": 1734, "Pretrain/Step Time": 8.864417344331741} +{"Pretrain/Learning Rate": 4.703388334852385e-05, "Pretrain/Loss": 2.118637800216675, "Pretrain/Loss (Raw)": 2.202172040939331, "Pretrain/Step": 1735, "Pretrain/Step Time": 8.862628370523453} +{"Pretrain/Learning Rate": 4.7029871003615776e-05, "Pretrain/Loss": 2.121457576751709, "Pretrain/Loss (Raw)": 2.336564302444458, "Pretrain/Step": 1736, "Pretrain/Step Time": 8.865686990320683} +{"Pretrain/Learning Rate": 4.7025856118119164e-05, "Pretrain/Loss": 2.1216225624084473, "Pretrain/Loss (Raw)": 2.2636709213256836, "Pretrain/Step": 1737, "Pretrain/Step Time": 8.866752838715911} +{"Pretrain/Learning Rate": 4.7021838692497046e-05, "Pretrain/Loss": 2.1196560859680176, "Pretrain/Loss (Raw)": 1.9656543731689453, "Pretrain/Step": 1738, "Pretrain/Step Time": 8.864571891725063} +{"Pretrain/Learning Rate": 4.70178187272127e-05, "Pretrain/Loss": 2.119739055633545, "Pretrain/Loss (Raw)": 2.0386548042297363, "Pretrain/Step": 1739, "Pretrain/Step Time": 8.86162725277245} +{"Pretrain/Learning Rate": 4.701379622272977e-05, "Pretrain/Loss": 2.120515823364258, "Pretrain/Loss (Raw)": 2.1250245571136475, "Pretrain/Step": 1740, "Pretrain/Step Time": 8.865204311907291} +{"Pretrain/Learning Rate": 4.700977117951211e-05, "Pretrain/Loss": 2.121220111846924, "Pretrain/Loss (Raw)": 2.155029535293579, "Pretrain/Step": 1741, "Pretrain/Step Time": 8.86903491616249} +{"Pretrain/Learning Rate": 4.700574359802393e-05, "Pretrain/Loss": 2.122387170791626, "Pretrain/Loss (Raw)": 2.1400582790374756, "Pretrain/Step": 1742, "Pretrain/Step Time": 8.868245707824826} +{"Pretrain/Learning Rate": 4.700171347872971e-05, "Pretrain/Loss": 2.1222872734069824, "Pretrain/Loss (Raw)": 2.1621952056884766, "Pretrain/Step": 1743, "Pretrain/Step Time": 8.870019495487213} +{"Pretrain/Learning Rate": 4.699768082209421e-05, "Pretrain/Loss": 2.1208181381225586, "Pretrain/Loss (Raw)": 1.984501600265503, "Pretrain/Step": 1744, "Pretrain/Step Time": 8.865911986678839} +{"Pretrain/Learning Rate": 4.69936456285825e-05, "Pretrain/Loss": 2.119565725326538, "Pretrain/Loss (Raw)": 2.017075300216675, "Pretrain/Step": 1745, "Pretrain/Step Time": 8.868905019015074} +{"Pretrain/Learning Rate": 4.698960789865994e-05, "Pretrain/Loss": 2.119642734527588, "Pretrain/Loss (Raw)": 2.221681594848633, "Pretrain/Step": 1746, "Pretrain/Step Time": 8.867380794137716} +{"Pretrain/Learning Rate": 4.698556763279218e-05, "Pretrain/Loss": 2.1197867393493652, "Pretrain/Loss (Raw)": 2.056464910507202, "Pretrain/Step": 1747, "Pretrain/Step Time": 8.875105729326606} +{"Pretrain/Learning Rate": 4.698152483144516e-05, "Pretrain/Loss": 2.117039203643799, "Pretrain/Loss (Raw)": 1.9690628051757812, "Pretrain/Step": 1748, "Pretrain/Step Time": 8.878174567595124} +{"Pretrain/Learning Rate": 4.697747949508512e-05, "Pretrain/Loss": 2.1138548851013184, "Pretrain/Loss (Raw)": 2.119440793991089, "Pretrain/Step": 1749, "Pretrain/Step Time": 8.878371074795723} +{"Pretrain/Learning Rate": 4.697343162417858e-05, "Pretrain/Loss": 2.113034725189209, "Pretrain/Loss (Raw)": 2.001959800720215, "Pretrain/Step": 1750, "Pretrain/Step Time": 8.879192030057311} +{"Pretrain/Learning Rate": 4.696938121919235e-05, "Pretrain/Loss": 2.1125802993774414, "Pretrain/Loss (Raw)": 1.8935538530349731, "Pretrain/Step": 1751, "Pretrain/Step Time": 8.873682778328657} +{"Pretrain/Learning Rate": 4.696532828059358e-05, "Pretrain/Loss": 2.1143531799316406, "Pretrain/Loss (Raw)": 2.1645350456237793, "Pretrain/Step": 1752, "Pretrain/Step Time": 8.872740318998694} +{"Pretrain/Learning Rate": 4.6961272808849634e-05, "Pretrain/Loss": 2.116762638092041, "Pretrain/Loss (Raw)": 2.248739242553711, "Pretrain/Step": 1753, "Pretrain/Step Time": 8.874696323648095} +{"Pretrain/Learning Rate": 4.6957214804428217e-05, "Pretrain/Loss": 2.1180953979492188, "Pretrain/Loss (Raw)": 2.4032814502716064, "Pretrain/Step": 1754, "Pretrain/Step Time": 8.881835112348199} +{"Pretrain/Learning Rate": 4.695315426779734e-05, "Pretrain/Loss": 2.1181273460388184, "Pretrain/Loss (Raw)": 2.0742409229278564, "Pretrain/Step": 1755, "Pretrain/Step Time": 8.877258351072669} +{"Pretrain/Learning Rate": 4.694909119942526e-05, "Pretrain/Loss": 2.118732452392578, "Pretrain/Loss (Raw)": 2.0713751316070557, "Pretrain/Step": 1756, "Pretrain/Step Time": 8.877342542633414} +{"Pretrain/Learning Rate": 4.694502559978055e-05, "Pretrain/Loss": 2.1174333095550537, "Pretrain/Loss (Raw)": 2.0950515270233154, "Pretrain/Step": 1757, "Pretrain/Step Time": 8.875957710668445} +{"Pretrain/Learning Rate": 4.694095746933208e-05, "Pretrain/Loss": 2.117276668548584, "Pretrain/Loss (Raw)": 2.1253535747528076, "Pretrain/Step": 1758, "Pretrain/Step Time": 8.879528652876616} +{"Pretrain/Learning Rate": 4.6936886808549004e-05, "Pretrain/Loss": 2.1171441078186035, "Pretrain/Loss (Raw)": 2.0921456813812256, "Pretrain/Step": 1759, "Pretrain/Step Time": 8.874654591083527} +{"Pretrain/Learning Rate": 4.693281361790077e-05, "Pretrain/Loss": 2.1163644790649414, "Pretrain/Loss (Raw)": 2.0949575901031494, "Pretrain/Step": 1760, "Pretrain/Step Time": 8.872720582410693} +{"Pretrain/Learning Rate": 4.6928737897857124e-05, "Pretrain/Loss": 2.1186115741729736, "Pretrain/Loss (Raw)": 2.3563668727874756, "Pretrain/Step": 1761, "Pretrain/Step Time": 8.87217446230352} +{"Pretrain/Learning Rate": 4.692465964888809e-05, "Pretrain/Loss": 2.1166224479675293, "Pretrain/Loss (Raw)": 2.003710985183716, "Pretrain/Step": 1762, "Pretrain/Step Time": 8.876726526767015} +{"Pretrain/Learning Rate": 4.692057887146399e-05, "Pretrain/Loss": 2.1155214309692383, "Pretrain/Loss (Raw)": 1.9874558448791504, "Pretrain/Step": 1763, "Pretrain/Step Time": 8.872726660221815} +{"Pretrain/Learning Rate": 4.691649556605545e-05, "Pretrain/Loss": 2.1153268814086914, "Pretrain/Loss (Raw)": 2.0066728591918945, "Pretrain/Step": 1764, "Pretrain/Step Time": 8.872505264356732} +{"Pretrain/Learning Rate": 4.691240973313337e-05, "Pretrain/Loss": 2.1169562339782715, "Pretrain/Loss (Raw)": 2.2419607639312744, "Pretrain/Step": 1765, "Pretrain/Step Time": 8.869767779484391} +{"Pretrain/Learning Rate": 4.690832137316893e-05, "Pretrain/Loss": 2.1164937019348145, "Pretrain/Loss (Raw)": 2.1657721996307373, "Pretrain/Step": 1766, "Pretrain/Step Time": 8.872863629832864} +{"Pretrain/Learning Rate": 4.690423048663364e-05, "Pretrain/Loss": 2.116206169128418, "Pretrain/Loss (Raw)": 2.0630695819854736, "Pretrain/Step": 1767, "Pretrain/Step Time": 8.873131366446614} +{"Pretrain/Learning Rate": 4.690013707399928e-05, "Pretrain/Loss": 2.1179871559143066, "Pretrain/Loss (Raw)": 2.190253257751465, "Pretrain/Step": 1768, "Pretrain/Step Time": 8.874587362632155} +{"Pretrain/Learning Rate": 4.689604113573791e-05, "Pretrain/Loss": 2.1200132369995117, "Pretrain/Loss (Raw)": 2.361834764480591, "Pretrain/Step": 1769, "Pretrain/Step Time": 8.871800588443875} +{"Pretrain/Learning Rate": 4.68919426723219e-05, "Pretrain/Loss": 2.120467185974121, "Pretrain/Loss (Raw)": 2.183351755142212, "Pretrain/Step": 1770, "Pretrain/Step Time": 8.872481284663081} +{"Pretrain/Learning Rate": 4.6887841684223905e-05, "Pretrain/Loss": 2.119668960571289, "Pretrain/Loss (Raw)": 2.092062473297119, "Pretrain/Step": 1771, "Pretrain/Step Time": 8.880221327766776} +{"Pretrain/Learning Rate": 4.688373817191687e-05, "Pretrain/Loss": 2.1179988384246826, "Pretrain/Loss (Raw)": 2.0239834785461426, "Pretrain/Step": 1772, "Pretrain/Step Time": 8.87995420768857} +{"Pretrain/Learning Rate": 4.687963213587402e-05, "Pretrain/Loss": 2.118856191635132, "Pretrain/Loss (Raw)": 2.114278554916382, "Pretrain/Step": 1773, "Pretrain/Step Time": 8.880684142932296} +{"Pretrain/Learning Rate": 4.6875523576568895e-05, "Pretrain/Loss": 2.118316173553467, "Pretrain/Loss (Raw)": 2.1246485710144043, "Pretrain/Step": 1774, "Pretrain/Step Time": 8.88218517228961} +{"Pretrain/Learning Rate": 4.6871412494475316e-05, "Pretrain/Loss": 2.11922287940979, "Pretrain/Loss (Raw)": 2.115847587585449, "Pretrain/Step": 1775, "Pretrain/Step Time": 8.881967209279537} +{"Pretrain/Learning Rate": 4.6867298890067377e-05, "Pretrain/Loss": 2.117518663406372, "Pretrain/Loss (Raw)": 2.0677731037139893, "Pretrain/Step": 1776, "Pretrain/Step Time": 8.880858547985554} +{"Pretrain/Learning Rate": 4.68631827638195e-05, "Pretrain/Loss": 2.1155295372009277, "Pretrain/Loss (Raw)": 1.9354065656661987, "Pretrain/Step": 1777, "Pretrain/Step Time": 8.877853959798813} +{"Pretrain/Learning Rate": 4.6859064116206356e-05, "Pretrain/Loss": 2.1145803928375244, "Pretrain/Loss (Raw)": 2.041236162185669, "Pretrain/Step": 1778, "Pretrain/Step Time": 8.882000835612416} +{"Pretrain/Learning Rate": 4.685494294770294e-05, "Pretrain/Loss": 2.1145992279052734, "Pretrain/Loss (Raw)": 2.132045269012451, "Pretrain/Step": 1779, "Pretrain/Step Time": 8.882338436320424} +{"Pretrain/Learning Rate": 4.685081925878452e-05, "Pretrain/Loss": 2.1143269538879395, "Pretrain/Loss (Raw)": 2.0232584476470947, "Pretrain/Step": 1780, "Pretrain/Step Time": 8.883824087679386} +{"Pretrain/Learning Rate": 4.684669304992665e-05, "Pretrain/Loss": 2.1162593364715576, "Pretrain/Loss (Raw)": 2.2184629440307617, "Pretrain/Step": 1781, "Pretrain/Step Time": 8.882162040099502} +{"Pretrain/Learning Rate": 4.6842564321605196e-05, "Pretrain/Loss": 2.117821216583252, "Pretrain/Loss (Raw)": 2.202955484390259, "Pretrain/Step": 1782, "Pretrain/Step Time": 8.882536107674241} +{"Pretrain/Learning Rate": 4.683843307429631e-05, "Pretrain/Loss": 2.1191577911376953, "Pretrain/Loss (Raw)": 2.495521068572998, "Pretrain/Step": 1783, "Pretrain/Step Time": 8.884843917563558} +{"Pretrain/Learning Rate": 4.68342993084764e-05, "Pretrain/Loss": 2.116548538208008, "Pretrain/Loss (Raw)": 2.12101674079895, "Pretrain/Step": 1784, "Pretrain/Step Time": 8.877018935978413} +{"Pretrain/Learning Rate": 4.683016302462221e-05, "Pretrain/Loss": 2.1168718338012695, "Pretrain/Loss (Raw)": 2.151348352432251, "Pretrain/Step": 1785, "Pretrain/Step Time": 8.889684995636344} +{"Pretrain/Learning Rate": 4.682602422321076e-05, "Pretrain/Loss": 2.1149511337280273, "Pretrain/Loss (Raw)": 1.9880014657974243, "Pretrain/Step": 1786, "Pretrain/Step Time": 8.88459106720984} +{"Pretrain/Learning Rate": 4.6821882904719344e-05, "Pretrain/Loss": 2.11590838432312, "Pretrain/Loss (Raw)": 2.2097949981689453, "Pretrain/Step": 1787, "Pretrain/Step Time": 8.888919914141297} +{"Pretrain/Learning Rate": 4.6817739069625563e-05, "Pretrain/Loss": 2.11724853515625, "Pretrain/Loss (Raw)": 2.2662506103515625, "Pretrain/Step": 1788, "Pretrain/Step Time": 8.88713970221579} +{"Pretrain/Learning Rate": 4.681359271840731e-05, "Pretrain/Loss": 2.1176648139953613, "Pretrain/Loss (Raw)": 2.103159189224243, "Pretrain/Step": 1789, "Pretrain/Step Time": 8.887641021981835} +{"Pretrain/Learning Rate": 4.6809443851542744e-05, "Pretrain/Loss": 2.117309808731079, "Pretrain/Loss (Raw)": 2.06996750831604, "Pretrain/Step": 1790, "Pretrain/Step Time": 8.888391861692071} +{"Pretrain/Learning Rate": 4.680529246951035e-05, "Pretrain/Loss": 2.1177725791931152, "Pretrain/Loss (Raw)": 2.1033730506896973, "Pretrain/Step": 1791, "Pretrain/Step Time": 8.893553346395493} +{"Pretrain/Learning Rate": 4.6801138572788885e-05, "Pretrain/Loss": 2.1180036067962646, "Pretrain/Loss (Raw)": 2.0742998123168945, "Pretrain/Step": 1792, "Pretrain/Step Time": 8.888462740927935} +{"Pretrain/Learning Rate": 4.679698216185738e-05, "Pretrain/Loss": 2.1158907413482666, "Pretrain/Loss (Raw)": 2.0269734859466553, "Pretrain/Step": 1793, "Pretrain/Step Time": 8.887765536084771} +{"Pretrain/Learning Rate": 4.6792823237195185e-05, "Pretrain/Loss": 2.115720272064209, "Pretrain/Loss (Raw)": 2.0576705932617188, "Pretrain/Step": 1794, "Pretrain/Step Time": 8.876689974218607} +{"Pretrain/Learning Rate": 4.678866179928193e-05, "Pretrain/Loss": 2.115736484527588, "Pretrain/Loss (Raw)": 2.0903003215789795, "Pretrain/Step": 1795, "Pretrain/Step Time": 8.88218273036182} +{"Pretrain/Learning Rate": 4.6784497848597516e-05, "Pretrain/Loss": 2.113872528076172, "Pretrain/Loss (Raw)": 1.9031264781951904, "Pretrain/Step": 1796, "Pretrain/Step Time": 8.876036962494254} +{"Pretrain/Learning Rate": 4.678033138562216e-05, "Pretrain/Loss": 2.1137704849243164, "Pretrain/Loss (Raw)": 2.0468459129333496, "Pretrain/Step": 1797, "Pretrain/Step Time": 8.875682348385453} +{"Pretrain/Learning Rate": 4.6776162410836354e-05, "Pretrain/Loss": 2.1148829460144043, "Pretrain/Loss (Raw)": 2.139019012451172, "Pretrain/Step": 1798, "Pretrain/Step Time": 8.881358228623867} +{"Pretrain/Learning Rate": 4.677199092472089e-05, "Pretrain/Loss": 2.114163398742676, "Pretrain/Loss (Raw)": 2.1315271854400635, "Pretrain/Step": 1799, "Pretrain/Step Time": 8.88337891921401} +{"Pretrain/Learning Rate": 4.6767816927756834e-05, "Pretrain/Loss": 2.1138792037963867, "Pretrain/Loss (Raw)": 1.9763450622558594, "Pretrain/Step": 1800, "Pretrain/Step Time": 8.872006818652153} +{"Pretrain/Learning Rate": 4.6763640420425566e-05, "Pretrain/Loss": 2.1117730140686035, "Pretrain/Loss (Raw)": 2.041151762008667, "Pretrain/Step": 1801, "Pretrain/Step Time": 8.870983211323619} +{"Pretrain/Learning Rate": 4.675946140320873e-05, "Pretrain/Loss": 2.1131396293640137, "Pretrain/Loss (Raw)": 2.138204336166382, "Pretrain/Step": 1802, "Pretrain/Step Time": 8.869311122223735} +{"Pretrain/Learning Rate": 4.6755279876588256e-05, "Pretrain/Loss": 2.1150293350219727, "Pretrain/Loss (Raw)": 2.190098285675049, "Pretrain/Step": 1803, "Pretrain/Step Time": 8.869659742340446} +{"Pretrain/Learning Rate": 4.67510958410464e-05, "Pretrain/Loss": 2.1135871410369873, "Pretrain/Loss (Raw)": 2.0116851329803467, "Pretrain/Step": 1804, "Pretrain/Step Time": 8.867761900648475} +{"Pretrain/Learning Rate": 4.6746909297065685e-05, "Pretrain/Loss": 2.1120734214782715, "Pretrain/Loss (Raw)": 1.9048444032669067, "Pretrain/Step": 1805, "Pretrain/Step Time": 8.870449980720878} +{"Pretrain/Learning Rate": 4.674272024512891e-05, "Pretrain/Loss": 2.1138365268707275, "Pretrain/Loss (Raw)": 2.3238680362701416, "Pretrain/Step": 1806, "Pretrain/Step Time": 8.872526425868273} +{"Pretrain/Learning Rate": 4.6738528685719185e-05, "Pretrain/Loss": 2.114001750946045, "Pretrain/Loss (Raw)": 2.3112025260925293, "Pretrain/Step": 1807, "Pretrain/Step Time": 8.870518937706947} +{"Pretrain/Learning Rate": 4.673433461931989e-05, "Pretrain/Loss": 2.1147964000701904, "Pretrain/Loss (Raw)": 2.1233901977539062, "Pretrain/Step": 1808, "Pretrain/Step Time": 8.874402731657028} +{"Pretrain/Learning Rate": 4.6730138046414714e-05, "Pretrain/Loss": 2.1161012649536133, "Pretrain/Loss (Raw)": 2.2426443099975586, "Pretrain/Step": 1809, "Pretrain/Step Time": 8.866391446441412} +{"Pretrain/Learning Rate": 4.672593896748763e-05, "Pretrain/Loss": 2.117213249206543, "Pretrain/Loss (Raw)": 2.185891628265381, "Pretrain/Step": 1810, "Pretrain/Step Time": 8.865022912621498} +{"Pretrain/Learning Rate": 4.6721737383022876e-05, "Pretrain/Loss": 2.118673324584961, "Pretrain/Loss (Raw)": 2.074850082397461, "Pretrain/Step": 1811, "Pretrain/Step Time": 8.86712751723826} +{"Pretrain/Learning Rate": 4.671753329350502e-05, "Pretrain/Loss": 2.1167588233947754, "Pretrain/Loss (Raw)": 1.8713480234146118, "Pretrain/Step": 1812, "Pretrain/Step Time": 8.866141568869352} +{"Pretrain/Learning Rate": 4.671332669941888e-05, "Pretrain/Loss": 2.1185765266418457, "Pretrain/Loss (Raw)": 2.1746509075164795, "Pretrain/Step": 1813, "Pretrain/Step Time": 8.865724455565214} +{"Pretrain/Learning Rate": 4.6709117601249596e-05, "Pretrain/Loss": 2.1169071197509766, "Pretrain/Loss (Raw)": 1.8897651433944702, "Pretrain/Step": 1814, "Pretrain/Step Time": 8.872943935915828} +{"Pretrain/Learning Rate": 4.6704905999482575e-05, "Pretrain/Loss": 2.1163687705993652, "Pretrain/Loss (Raw)": 2.061051607131958, "Pretrain/Step": 1815, "Pretrain/Step Time": 8.860047915950418} +{"Pretrain/Learning Rate": 4.670069189460351e-05, "Pretrain/Loss": 2.1163792610168457, "Pretrain/Loss (Raw)": 2.0783872604370117, "Pretrain/Step": 1816, "Pretrain/Step Time": 8.864186868071556} +{"Pretrain/Learning Rate": 4.6696475287098396e-05, "Pretrain/Loss": 2.115602493286133, "Pretrain/Loss (Raw)": 2.0785114765167236, "Pretrain/Step": 1817, "Pretrain/Step Time": 8.867379520088434} +{"Pretrain/Learning Rate": 4.669225617745352e-05, "Pretrain/Loss": 2.112870931625366, "Pretrain/Loss (Raw)": 1.941025972366333, "Pretrain/Step": 1818, "Pretrain/Step Time": 8.86686777509749} +{"Pretrain/Learning Rate": 4.668803456615545e-05, "Pretrain/Loss": 2.112858533859253, "Pretrain/Loss (Raw)": 2.153191089630127, "Pretrain/Step": 1819, "Pretrain/Step Time": 8.863362740725279} +{"Pretrain/Learning Rate": 4.668381045369102e-05, "Pretrain/Loss": 2.1133298873901367, "Pretrain/Loss (Raw)": 2.0744943618774414, "Pretrain/Step": 1820, "Pretrain/Step Time": 8.868861217051744} +{"Pretrain/Learning Rate": 4.6679583840547405e-05, "Pretrain/Loss": 2.111398696899414, "Pretrain/Loss (Raw)": 1.8593246936798096, "Pretrain/Step": 1821, "Pretrain/Step Time": 8.87347306124866} +{"Pretrain/Learning Rate": 4.667535472721203e-05, "Pretrain/Loss": 2.112761974334717, "Pretrain/Loss (Raw)": 2.2205193042755127, "Pretrain/Step": 1822, "Pretrain/Step Time": 8.870288470759988} +{"Pretrain/Learning Rate": 4.66711231141726e-05, "Pretrain/Loss": 2.1127231121063232, "Pretrain/Loss (Raw)": 2.1436567306518555, "Pretrain/Step": 1823, "Pretrain/Step Time": 8.867752430960536} +{"Pretrain/Learning Rate": 4.6666889001917136e-05, "Pretrain/Loss": 2.112347364425659, "Pretrain/Loss (Raw)": 2.052746534347534, "Pretrain/Step": 1824, "Pretrain/Step Time": 8.866044471040368} +{"Pretrain/Learning Rate": 4.666265239093393e-05, "Pretrain/Loss": 2.111896514892578, "Pretrain/Loss (Raw)": 2.200871706008911, "Pretrain/Step": 1825, "Pretrain/Step Time": 8.866817113012075} +{"Pretrain/Learning Rate": 4.665841328171158e-05, "Pretrain/Loss": 2.111407518386841, "Pretrain/Loss (Raw)": 2.012932300567627, "Pretrain/Step": 1826, "Pretrain/Step Time": 8.863166518509388} +{"Pretrain/Learning Rate": 4.665417167473894e-05, "Pretrain/Loss": 2.111732006072998, "Pretrain/Loss (Raw)": 2.095123529434204, "Pretrain/Step": 1827, "Pretrain/Step Time": 8.866203112527728} +{"Pretrain/Learning Rate": 4.66499275705052e-05, "Pretrain/Loss": 2.1104655265808105, "Pretrain/Loss (Raw)": 1.9752296209335327, "Pretrain/Step": 1828, "Pretrain/Step Time": 8.863803742453456} +{"Pretrain/Learning Rate": 4.6645680969499795e-05, "Pretrain/Loss": 2.1105518341064453, "Pretrain/Loss (Raw)": 2.1753475666046143, "Pretrain/Step": 1829, "Pretrain/Step Time": 8.876631386578083} +{"Pretrain/Learning Rate": 4.664143187221245e-05, "Pretrain/Loss": 2.1117382049560547, "Pretrain/Loss (Raw)": 1.9962165355682373, "Pretrain/Step": 1830, "Pretrain/Step Time": 8.876482324674726} +{"Pretrain/Learning Rate": 4.6637180279133216e-05, "Pretrain/Loss": 2.111217737197876, "Pretrain/Loss (Raw)": 1.97923743724823, "Pretrain/Step": 1831, "Pretrain/Step Time": 8.873384431004524} +{"Pretrain/Learning Rate": 4.6632926190752385e-05, "Pretrain/Loss": 2.110894203186035, "Pretrain/Loss (Raw)": 2.0717737674713135, "Pretrain/Step": 1832, "Pretrain/Step Time": 8.873604442924261} +{"Pretrain/Learning Rate": 4.662866960756057e-05, "Pretrain/Loss": 2.1104917526245117, "Pretrain/Loss (Raw)": 2.079207420349121, "Pretrain/Step": 1833, "Pretrain/Step Time": 8.873738585039973} +{"Pretrain/Learning Rate": 4.662441053004866e-05, "Pretrain/Loss": 2.1099207401275635, "Pretrain/Loss (Raw)": 2.0437307357788086, "Pretrain/Step": 1834, "Pretrain/Step Time": 8.8700100928545} +{"Pretrain/Learning Rate": 4.6620148958707833e-05, "Pretrain/Loss": 2.109679698944092, "Pretrain/Loss (Raw)": 2.073467493057251, "Pretrain/Step": 1835, "Pretrain/Step Time": 8.870556166395545} +{"Pretrain/Learning Rate": 4.661588489402955e-05, "Pretrain/Loss": 2.1095643043518066, "Pretrain/Loss (Raw)": 2.2987709045410156, "Pretrain/Step": 1836, "Pretrain/Step Time": 8.870398584753275} +{"Pretrain/Learning Rate": 4.661161833650556e-05, "Pretrain/Loss": 2.110361337661743, "Pretrain/Loss (Raw)": 2.239919424057007, "Pretrain/Step": 1837, "Pretrain/Step Time": 8.864793751388788} +{"Pretrain/Learning Rate": 4.660734928662791e-05, "Pretrain/Loss": 2.11099910736084, "Pretrain/Loss (Raw)": 2.206475257873535, "Pretrain/Step": 1838, "Pretrain/Step Time": 8.869345227256417} +{"Pretrain/Learning Rate": 4.660307774488892e-05, "Pretrain/Loss": 2.114738941192627, "Pretrain/Loss (Raw)": 2.3188345432281494, "Pretrain/Step": 1839, "Pretrain/Step Time": 8.86811899393797} +{"Pretrain/Learning Rate": 4.65988037117812e-05, "Pretrain/Loss": 2.1150827407836914, "Pretrain/Loss (Raw)": 2.167621612548828, "Pretrain/Step": 1840, "Pretrain/Step Time": 8.868110759183764} +{"Pretrain/Learning Rate": 4.659452718779768e-05, "Pretrain/Loss": 2.113563060760498, "Pretrain/Loss (Raw)": 2.0886270999908447, "Pretrain/Step": 1841, "Pretrain/Step Time": 8.866992868483067} +{"Pretrain/Learning Rate": 4.6590248173431505e-05, "Pretrain/Loss": 2.112011432647705, "Pretrain/Loss (Raw)": 2.062727451324463, "Pretrain/Step": 1842, "Pretrain/Step Time": 8.869238102808595} +{"Pretrain/Learning Rate": 4.6585966669176186e-05, "Pretrain/Loss": 2.1124558448791504, "Pretrain/Loss (Raw)": 2.189952850341797, "Pretrain/Step": 1843, "Pretrain/Step Time": 8.862389497458935} +{"Pretrain/Learning Rate": 4.658168267552547e-05, "Pretrain/Loss": 2.1114540100097656, "Pretrain/Loss (Raw)": 2.0600388050079346, "Pretrain/Step": 1844, "Pretrain/Step Time": 8.866597129032016} +{"Pretrain/Learning Rate": 4.657739619297342e-05, "Pretrain/Loss": 2.110994815826416, "Pretrain/Loss (Raw)": 2.033034324645996, "Pretrain/Step": 1845, "Pretrain/Step Time": 8.873659839853644} +{"Pretrain/Learning Rate": 4.657310722201436e-05, "Pretrain/Loss": 2.10882568359375, "Pretrain/Loss (Raw)": 1.9611427783966064, "Pretrain/Step": 1846, "Pretrain/Step Time": 8.87346912175417} +{"Pretrain/Learning Rate": 4.6568815763142914e-05, "Pretrain/Loss": 2.1096396446228027, "Pretrain/Loss (Raw)": 2.185295581817627, "Pretrain/Step": 1847, "Pretrain/Step Time": 8.877665461972356} +{"Pretrain/Learning Rate": 4.6564521816854e-05, "Pretrain/Loss": 2.1097686290740967, "Pretrain/Loss (Raw)": 2.1323695182800293, "Pretrain/Step": 1848, "Pretrain/Step Time": 8.87323234602809} +{"Pretrain/Learning Rate": 4.656022538364282e-05, "Pretrain/Loss": 2.109009265899658, "Pretrain/Loss (Raw)": 2.023702383041382, "Pretrain/Step": 1849, "Pretrain/Step Time": 8.877112140879035} +{"Pretrain/Learning Rate": 4.655592646400485e-05, "Pretrain/Loss": 2.1076154708862305, "Pretrain/Loss (Raw)": 2.060520648956299, "Pretrain/Step": 1850, "Pretrain/Step Time": 8.877091994509101} +{"Pretrain/Learning Rate": 4.6551625058435866e-05, "Pretrain/Loss": 2.1069016456604004, "Pretrain/Loss (Raw)": 2.0990264415740967, "Pretrain/Step": 1851, "Pretrain/Step Time": 8.883170427754521} +{"Pretrain/Learning Rate": 4.654732116743194e-05, "Pretrain/Loss": 2.1066958904266357, "Pretrain/Loss (Raw)": 2.2045400142669678, "Pretrain/Step": 1852, "Pretrain/Step Time": 8.880288995802402} +{"Pretrain/Learning Rate": 4.654301479148938e-05, "Pretrain/Loss": 2.106433868408203, "Pretrain/Loss (Raw)": 2.074477195739746, "Pretrain/Step": 1853, "Pretrain/Step Time": 8.879543032497168} +{"Pretrain/Learning Rate": 4.653870593110485e-05, "Pretrain/Loss": 2.107565402984619, "Pretrain/Loss (Raw)": 2.1765706539154053, "Pretrain/Step": 1854, "Pretrain/Step Time": 8.880510032176971} +{"Pretrain/Learning Rate": 4.6534394586775254e-05, "Pretrain/Loss": 2.109621047973633, "Pretrain/Loss (Raw)": 2.1073267459869385, "Pretrain/Step": 1855, "Pretrain/Step Time": 8.87818405404687} +{"Pretrain/Learning Rate": 4.653008075899781e-05, "Pretrain/Loss": 2.1107635498046875, "Pretrain/Loss (Raw)": 2.1905908584594727, "Pretrain/Step": 1856, "Pretrain/Step Time": 8.8854975476861} +{"Pretrain/Learning Rate": 4.652576444826999e-05, "Pretrain/Loss": 2.110147476196289, "Pretrain/Loss (Raw)": 2.085632801055908, "Pretrain/Step": 1857, "Pretrain/Step Time": 8.889129055663943} +{"Pretrain/Learning Rate": 4.652144565508959e-05, "Pretrain/Loss": 2.1086981296539307, "Pretrain/Loss (Raw)": 2.003789186477661, "Pretrain/Step": 1858, "Pretrain/Step Time": 8.879975076764822} +{"Pretrain/Learning Rate": 4.6517124379954655e-05, "Pretrain/Loss": 2.108288288116455, "Pretrain/Loss (Raw)": 2.0616044998168945, "Pretrain/Step": 1859, "Pretrain/Step Time": 8.893226249143481} +{"Pretrain/Learning Rate": 4.651280062336355e-05, "Pretrain/Loss": 2.1086413860321045, "Pretrain/Loss (Raw)": 2.1381986141204834, "Pretrain/Step": 1860, "Pretrain/Step Time": 8.888331271708012} +{"Pretrain/Learning Rate": 4.65084743858149e-05, "Pretrain/Loss": 2.107783794403076, "Pretrain/Loss (Raw)": 2.136805772781372, "Pretrain/Step": 1861, "Pretrain/Step Time": 8.889681747183204} +{"Pretrain/Learning Rate": 4.6504145667807644e-05, "Pretrain/Loss": 2.1075854301452637, "Pretrain/Loss (Raw)": 1.9842966794967651, "Pretrain/Step": 1862, "Pretrain/Step Time": 8.889478422701359} +{"Pretrain/Learning Rate": 4.649981446984097e-05, "Pretrain/Loss": 2.107342004776001, "Pretrain/Loss (Raw)": 2.171013355255127, "Pretrain/Step": 1863, "Pretrain/Step Time": 8.885201189666986} +{"Pretrain/Learning Rate": 4.649548079241438e-05, "Pretrain/Loss": 2.106302261352539, "Pretrain/Loss (Raw)": 2.2034802436828613, "Pretrain/Step": 1864, "Pretrain/Step Time": 8.885454462841153} +{"Pretrain/Learning Rate": 4.649114463602766e-05, "Pretrain/Loss": 2.1051201820373535, "Pretrain/Loss (Raw)": 2.1123571395874023, "Pretrain/Step": 1865, "Pretrain/Step Time": 8.883394030854106} +{"Pretrain/Learning Rate": 4.648680600118087e-05, "Pretrain/Loss": 2.1064209938049316, "Pretrain/Loss (Raw)": 2.132194995880127, "Pretrain/Step": 1866, "Pretrain/Step Time": 8.884665803983808} +{"Pretrain/Learning Rate": 4.6482464888374365e-05, "Pretrain/Loss": 2.108114242553711, "Pretrain/Loss (Raw)": 2.2553584575653076, "Pretrain/Step": 1867, "Pretrain/Step Time": 8.881450828164816} +{"Pretrain/Learning Rate": 4.6478121298108776e-05, "Pretrain/Loss": 2.108314037322998, "Pretrain/Loss (Raw)": 2.1506214141845703, "Pretrain/Step": 1868, "Pretrain/Step Time": 8.883319625630975} +{"Pretrain/Learning Rate": 4.647377523088503e-05, "Pretrain/Loss": 2.1072936058044434, "Pretrain/Loss (Raw)": 2.0243871212005615, "Pretrain/Step": 1869, "Pretrain/Step Time": 8.880230644717813} +{"Pretrain/Learning Rate": 4.6469426687204346e-05, "Pretrain/Loss": 2.1081578731536865, "Pretrain/Loss (Raw)": 2.2506918907165527, "Pretrain/Step": 1870, "Pretrain/Step Time": 8.887074183672667} +{"Pretrain/Learning Rate": 4.646507566756819e-05, "Pretrain/Loss": 2.108522653579712, "Pretrain/Loss (Raw)": 2.2088801860809326, "Pretrain/Step": 1871, "Pretrain/Step Time": 8.881115475669503} +{"Pretrain/Learning Rate": 4.646072217247838e-05, "Pretrain/Loss": 2.1102631092071533, "Pretrain/Loss (Raw)": 2.207294464111328, "Pretrain/Step": 1872, "Pretrain/Step Time": 8.881334502249956} +{"Pretrain/Learning Rate": 4.645636620243695e-05, "Pretrain/Loss": 2.1105477809906006, "Pretrain/Loss (Raw)": 2.0534873008728027, "Pretrain/Step": 1873, "Pretrain/Step Time": 8.880003962665796} +{"Pretrain/Learning Rate": 4.645200775794628e-05, "Pretrain/Loss": 2.10959529876709, "Pretrain/Loss (Raw)": 2.0998027324676514, "Pretrain/Step": 1874, "Pretrain/Step Time": 8.878484588116407} +{"Pretrain/Learning Rate": 4.6447646839508975e-05, "Pretrain/Loss": 2.1112794876098633, "Pretrain/Loss (Raw)": 2.271996259689331, "Pretrain/Step": 1875, "Pretrain/Step Time": 8.874411150813103} +{"Pretrain/Learning Rate": 4.6443283447627974e-05, "Pretrain/Loss": 2.111971139907837, "Pretrain/Loss (Raw)": 2.0576391220092773, "Pretrain/Step": 1876, "Pretrain/Step Time": 8.873590162023902} +{"Pretrain/Learning Rate": 4.643891758280649e-05, "Pretrain/Loss": 2.1133971214294434, "Pretrain/Loss (Raw)": 2.3019254207611084, "Pretrain/Step": 1877, "Pretrain/Step Time": 8.871878260746598} +{"Pretrain/Learning Rate": 4.6434549245548e-05, "Pretrain/Loss": 2.113475799560547, "Pretrain/Loss (Raw)": 2.0120809078216553, "Pretrain/Step": 1878, "Pretrain/Step Time": 8.874491453170776} +{"Pretrain/Learning Rate": 4.643017843635629e-05, "Pretrain/Loss": 2.1156117916107178, "Pretrain/Loss (Raw)": 2.1669251918792725, "Pretrain/Step": 1879, "Pretrain/Step Time": 8.871416380628943} +{"Pretrain/Learning Rate": 4.6425805155735416e-05, "Pretrain/Loss": 2.115811347961426, "Pretrain/Loss (Raw)": 2.190089464187622, "Pretrain/Step": 1880, "Pretrain/Step Time": 8.869703376665711} +{"Pretrain/Learning Rate": 4.642142940418973e-05, "Pretrain/Loss": 2.114205837249756, "Pretrain/Loss (Raw)": 2.043238401412964, "Pretrain/Step": 1881, "Pretrain/Step Time": 8.876213867217302} +{"Pretrain/Learning Rate": 4.641705118222387e-05, "Pretrain/Loss": 2.1110918521881104, "Pretrain/Loss (Raw)": 2.004704236984253, "Pretrain/Step": 1882, "Pretrain/Step Time": 8.871776835992932} +{"Pretrain/Learning Rate": 4.6412670490342747e-05, "Pretrain/Loss": 2.1111416816711426, "Pretrain/Loss (Raw)": 2.0806050300598145, "Pretrain/Step": 1883, "Pretrain/Step Time": 8.873487738892436} +{"Pretrain/Learning Rate": 4.6408287329051556e-05, "Pretrain/Loss": 2.1102986335754395, "Pretrain/Loss (Raw)": 1.9634592533111572, "Pretrain/Step": 1884, "Pretrain/Step Time": 8.866912592202425} +{"Pretrain/Learning Rate": 4.64039016988558e-05, "Pretrain/Loss": 2.1101064682006836, "Pretrain/Loss (Raw)": 2.070453405380249, "Pretrain/Step": 1885, "Pretrain/Step Time": 8.863166464492679} +{"Pretrain/Learning Rate": 4.639951360026123e-05, "Pretrain/Loss": 2.1111831665039062, "Pretrain/Loss (Raw)": 2.263154983520508, "Pretrain/Step": 1886, "Pretrain/Step Time": 8.859179491177201} +{"Pretrain/Learning Rate": 4.639512303377393e-05, "Pretrain/Loss": 2.1120476722717285, "Pretrain/Loss (Raw)": 2.20279860496521, "Pretrain/Step": 1887, "Pretrain/Step Time": 8.862307893112302} +{"Pretrain/Learning Rate": 4.639072999990022e-05, "Pretrain/Loss": 2.1106507778167725, "Pretrain/Loss (Raw)": 1.9161815643310547, "Pretrain/Step": 1888, "Pretrain/Step Time": 8.861209265887737} +{"Pretrain/Learning Rate": 4.6386334499146724e-05, "Pretrain/Loss": 2.1091103553771973, "Pretrain/Loss (Raw)": 2.1591970920562744, "Pretrain/Step": 1889, "Pretrain/Step Time": 8.873805928975344} +{"Pretrain/Learning Rate": 4.638193653202035e-05, "Pretrain/Loss": 2.1085598468780518, "Pretrain/Loss (Raw)": 1.9332420825958252, "Pretrain/Step": 1890, "Pretrain/Step Time": 8.86822783574462} +{"Pretrain/Learning Rate": 4.6377536099028315e-05, "Pretrain/Loss": 2.1089158058166504, "Pretrain/Loss (Raw)": 2.033008098602295, "Pretrain/Step": 1891, "Pretrain/Step Time": 8.872121142223477} +{"Pretrain/Learning Rate": 4.637313320067808e-05, "Pretrain/Loss": 2.110936164855957, "Pretrain/Loss (Raw)": 2.265305757522583, "Pretrain/Step": 1892, "Pretrain/Step Time": 8.869703140109777} +{"Pretrain/Learning Rate": 4.636872783747741e-05, "Pretrain/Loss": 2.110795497894287, "Pretrain/Loss (Raw)": 2.223933458328247, "Pretrain/Step": 1893, "Pretrain/Step Time": 8.875224998220801} +{"Pretrain/Learning Rate": 4.636432000993435e-05, "Pretrain/Loss": 2.1100621223449707, "Pretrain/Loss (Raw)": 2.0718774795532227, "Pretrain/Step": 1894, "Pretrain/Step Time": 8.871458038687706} +{"Pretrain/Learning Rate": 4.635990971855724e-05, "Pretrain/Loss": 2.1098878383636475, "Pretrain/Loss (Raw)": 2.040778398513794, "Pretrain/Step": 1895, "Pretrain/Step Time": 8.875906009227037} +{"Pretrain/Learning Rate": 4.6355496963854684e-05, "Pretrain/Loss": 2.1073012351989746, "Pretrain/Loss (Raw)": 1.8591599464416504, "Pretrain/Step": 1896, "Pretrain/Step Time": 8.880142787471414} +{"Pretrain/Learning Rate": 4.635108174633559e-05, "Pretrain/Loss": 2.104552745819092, "Pretrain/Loss (Raw)": 2.010061502456665, "Pretrain/Step": 1897, "Pretrain/Step Time": 8.87499737739563} +{"Pretrain/Learning Rate": 4.634666406650914e-05, "Pretrain/Loss": 2.1039116382598877, "Pretrain/Loss (Raw)": 2.1012704372406006, "Pretrain/Step": 1898, "Pretrain/Step Time": 8.875713761895895} +{"Pretrain/Learning Rate": 4.63422439248848e-05, "Pretrain/Loss": 2.103196382522583, "Pretrain/Loss (Raw)": 2.000497579574585, "Pretrain/Step": 1899, "Pretrain/Step Time": 8.869730681180954} +{"Pretrain/Learning Rate": 4.633782132197232e-05, "Pretrain/Loss": 2.104310989379883, "Pretrain/Loss (Raw)": 2.1666674613952637, "Pretrain/Step": 1900, "Pretrain/Step Time": 8.868195451796055} +{"Pretrain/Learning Rate": 4.633339625828173e-05, "Pretrain/Loss": 2.104780673980713, "Pretrain/Loss (Raw)": 2.1744155883789062, "Pretrain/Step": 1901, "Pretrain/Step Time": 8.86730301938951} +{"Pretrain/Learning Rate": 4.632896873432338e-05, "Pretrain/Loss": 2.105186939239502, "Pretrain/Loss (Raw)": 2.1766340732574463, "Pretrain/Step": 1902, "Pretrain/Step Time": 8.86576765961945} +{"Pretrain/Learning Rate": 4.632453875060784e-05, "Pretrain/Loss": 2.1047627925872803, "Pretrain/Loss (Raw)": 2.061544418334961, "Pretrain/Step": 1903, "Pretrain/Step Time": 8.865034705027938} +{"Pretrain/Learning Rate": 4.6320106307646e-05, "Pretrain/Loss": 2.1055660247802734, "Pretrain/Loss (Raw)": 2.170614719390869, "Pretrain/Step": 1904, "Pretrain/Step Time": 8.880054848268628} +{"Pretrain/Learning Rate": 4.6315671405949046e-05, "Pretrain/Loss": 2.107503890991211, "Pretrain/Loss (Raw)": 2.1834285259246826, "Pretrain/Step": 1905, "Pretrain/Step Time": 8.87731871381402} +{"Pretrain/Learning Rate": 4.631123404602842e-05, "Pretrain/Loss": 2.108457326889038, "Pretrain/Loss (Raw)": 2.163300037384033, "Pretrain/Step": 1906, "Pretrain/Step Time": 8.879921790212393} +{"Pretrain/Learning Rate": 4.630679422839585e-05, "Pretrain/Loss": 2.1094791889190674, "Pretrain/Loss (Raw)": 2.2628180980682373, "Pretrain/Step": 1907, "Pretrain/Step Time": 8.8744340762496} +{"Pretrain/Learning Rate": 4.6302351953563385e-05, "Pretrain/Loss": 2.113020420074463, "Pretrain/Loss (Raw)": 2.4765663146972656, "Pretrain/Step": 1908, "Pretrain/Step Time": 8.872500825673342} +{"Pretrain/Learning Rate": 4.629790722204331e-05, "Pretrain/Loss": 2.1135802268981934, "Pretrain/Loss (Raw)": 2.290100336074829, "Pretrain/Step": 1909, "Pretrain/Step Time": 8.872161673381925} +{"Pretrain/Learning Rate": 4.629346003434821e-05, "Pretrain/Loss": 2.112708568572998, "Pretrain/Loss (Raw)": 2.091369152069092, "Pretrain/Step": 1910, "Pretrain/Step Time": 8.876158058643341} +{"Pretrain/Learning Rate": 4.628901039099096e-05, "Pretrain/Loss": 2.109036684036255, "Pretrain/Loss (Raw)": 2.0255167484283447, "Pretrain/Step": 1911, "Pretrain/Step Time": 8.879435252398252} +{"Pretrain/Learning Rate": 4.6284558292484724e-05, "Pretrain/Loss": 2.110135078430176, "Pretrain/Loss (Raw)": 2.26162052154541, "Pretrain/Step": 1912, "Pretrain/Step Time": 8.879565829411149} +{"Pretrain/Learning Rate": 4.628010373934292e-05, "Pretrain/Loss": 2.1115145683288574, "Pretrain/Loss (Raw)": 2.3279314041137695, "Pretrain/Step": 1913, "Pretrain/Step Time": 8.86897217668593} +{"Pretrain/Learning Rate": 4.627564673207928e-05, "Pretrain/Loss": 2.113067865371704, "Pretrain/Loss (Raw)": 2.1868062019348145, "Pretrain/Step": 1914, "Pretrain/Step Time": 8.873664122074842} +{"Pretrain/Learning Rate": 4.62711872712078e-05, "Pretrain/Loss": 2.1126744747161865, "Pretrain/Loss (Raw)": 2.1594436168670654, "Pretrain/Step": 1915, "Pretrain/Step Time": 8.86595089174807} +{"Pretrain/Learning Rate": 4.626672535724278e-05, "Pretrain/Loss": 2.1122007369995117, "Pretrain/Loss (Raw)": 2.205620765686035, "Pretrain/Step": 1916, "Pretrain/Step Time": 8.87116856686771} +{"Pretrain/Learning Rate": 4.626226099069878e-05, "Pretrain/Loss": 2.110841751098633, "Pretrain/Loss (Raw)": 1.9292229413986206, "Pretrain/Step": 1917, "Pretrain/Step Time": 8.867860399186611} +{"Pretrain/Learning Rate": 4.625779417209065e-05, "Pretrain/Loss": 2.1115286350250244, "Pretrain/Loss (Raw)": 2.1578664779663086, "Pretrain/Step": 1918, "Pretrain/Step Time": 8.87008672207594} +{"Pretrain/Learning Rate": 4.625332490193352e-05, "Pretrain/Loss": 2.111572265625, "Pretrain/Loss (Raw)": 2.1089653968811035, "Pretrain/Step": 1919, "Pretrain/Step Time": 8.866883102804422} +{"Pretrain/Learning Rate": 4.624885318074282e-05, "Pretrain/Loss": 2.1123709678649902, "Pretrain/Loss (Raw)": 2.176565647125244, "Pretrain/Step": 1920, "Pretrain/Step Time": 8.866394151002169} +{"Pretrain/Learning Rate": 4.624437900903424e-05, "Pretrain/Loss": 2.1115822792053223, "Pretrain/Loss (Raw)": 1.9260209798812866, "Pretrain/Step": 1921, "Pretrain/Step Time": 8.872405100613832} +{"Pretrain/Learning Rate": 4.623990238732376e-05, "Pretrain/Loss": 2.112044334411621, "Pretrain/Loss (Raw)": 2.1167893409729004, "Pretrain/Step": 1922, "Pretrain/Step Time": 8.879009392112494} +{"Pretrain/Learning Rate": 4.6235423316127655e-05, "Pretrain/Loss": 2.111835479736328, "Pretrain/Loss (Raw)": 2.063580274581909, "Pretrain/Step": 1923, "Pretrain/Step Time": 8.881877146661282} +{"Pretrain/Learning Rate": 4.623094179596248e-05, "Pretrain/Loss": 2.1132779121398926, "Pretrain/Loss (Raw)": 2.0877649784088135, "Pretrain/Step": 1924, "Pretrain/Step Time": 8.878909481689334} +{"Pretrain/Learning Rate": 4.622645782734504e-05, "Pretrain/Loss": 2.116086721420288, "Pretrain/Loss (Raw)": 2.4063425064086914, "Pretrain/Step": 1925, "Pretrain/Step Time": 8.878462010994554} +{"Pretrain/Learning Rate": 4.6221971410792466e-05, "Pretrain/Loss": 2.115022659301758, "Pretrain/Loss (Raw)": 2.0027992725372314, "Pretrain/Step": 1926, "Pretrain/Step Time": 8.875659011304379} +{"Pretrain/Learning Rate": 4.621748254682214e-05, "Pretrain/Loss": 2.116061210632324, "Pretrain/Loss (Raw)": 2.2645041942596436, "Pretrain/Step": 1927, "Pretrain/Step Time": 8.876270581036806} +{"Pretrain/Learning Rate": 4.621299123595176e-05, "Pretrain/Loss": 2.1163532733917236, "Pretrain/Loss (Raw)": 2.0137126445770264, "Pretrain/Step": 1928, "Pretrain/Step Time": 8.875185191631317} +{"Pretrain/Learning Rate": 4.620849747869926e-05, "Pretrain/Loss": 2.1166582107543945, "Pretrain/Loss (Raw)": 2.080166816711426, "Pretrain/Step": 1929, "Pretrain/Step Time": 8.884620822966099} +{"Pretrain/Learning Rate": 4.6204001275582904e-05, "Pretrain/Loss": 2.116508960723877, "Pretrain/Loss (Raw)": 2.119122266769409, "Pretrain/Step": 1930, "Pretrain/Step Time": 8.881722941994667} +{"Pretrain/Learning Rate": 4.61995026271212e-05, "Pretrain/Loss": 2.1145949363708496, "Pretrain/Loss (Raw)": 1.9451104402542114, "Pretrain/Step": 1931, "Pretrain/Step Time": 8.885438553988934} +{"Pretrain/Learning Rate": 4.619500153383296e-05, "Pretrain/Loss": 2.1154491901397705, "Pretrain/Loss (Raw)": 2.1210145950317383, "Pretrain/Step": 1932, "Pretrain/Step Time": 8.887158276513219} +{"Pretrain/Learning Rate": 4.619049799623726e-05, "Pretrain/Loss": 2.1170690059661865, "Pretrain/Loss (Raw)": 2.1121773719787598, "Pretrain/Step": 1933, "Pretrain/Step Time": 8.885534143075347} +{"Pretrain/Learning Rate": 4.618599201485349e-05, "Pretrain/Loss": 2.1156015396118164, "Pretrain/Loss (Raw)": 2.136024236679077, "Pretrain/Step": 1934, "Pretrain/Step Time": 8.894731029868126} +{"Pretrain/Learning Rate": 4.618148359020128e-05, "Pretrain/Loss": 2.114584445953369, "Pretrain/Loss (Raw)": 2.1810238361358643, "Pretrain/Step": 1935, "Pretrain/Step Time": 8.89340548031032} +{"Pretrain/Learning Rate": 4.617697272280057e-05, "Pretrain/Loss": 2.1141209602355957, "Pretrain/Loss (Raw)": 2.064072608947754, "Pretrain/Step": 1936, "Pretrain/Step Time": 8.88938308507204} +{"Pretrain/Learning Rate": 4.6172459413171586e-05, "Pretrain/Loss": 2.1138088703155518, "Pretrain/Loss (Raw)": 2.2027008533477783, "Pretrain/Step": 1937, "Pretrain/Step Time": 8.887617126107216} +{"Pretrain/Learning Rate": 4.616794366183481e-05, "Pretrain/Loss": 2.114034652709961, "Pretrain/Loss (Raw)": 2.214801073074341, "Pretrain/Step": 1938, "Pretrain/Step Time": 8.886804413050413} +{"Pretrain/Learning Rate": 4.616342546931102e-05, "Pretrain/Loss": 2.112974166870117, "Pretrain/Loss (Raw)": 1.9391158819198608, "Pretrain/Step": 1939, "Pretrain/Step Time": 8.88404064066708} +{"Pretrain/Learning Rate": 4.6158904836121286e-05, "Pretrain/Loss": 2.1140551567077637, "Pretrain/Loss (Raw)": 2.0097057819366455, "Pretrain/Step": 1940, "Pretrain/Step Time": 8.887912245467305} +{"Pretrain/Learning Rate": 4.6154381762786936e-05, "Pretrain/Loss": 2.114548444747925, "Pretrain/Loss (Raw)": 2.237778663635254, "Pretrain/Step": 1941, "Pretrain/Step Time": 8.889496488496661} +{"Pretrain/Learning Rate": 4.6149856249829606e-05, "Pretrain/Loss": 2.1173043251037598, "Pretrain/Loss (Raw)": 2.2424798011779785, "Pretrain/Step": 1942, "Pretrain/Step Time": 8.880880063399673} +{"Pretrain/Learning Rate": 4.6145328297771183e-05, "Pretrain/Loss": 2.1176936626434326, "Pretrain/Loss (Raw)": 2.110928773880005, "Pretrain/Step": 1943, "Pretrain/Step Time": 8.882855733856559} +{"Pretrain/Learning Rate": 4.614079790713387e-05, "Pretrain/Loss": 2.117738962173462, "Pretrain/Loss (Raw)": 2.0841832160949707, "Pretrain/Step": 1944, "Pretrain/Step Time": 8.880131529644132} +{"Pretrain/Learning Rate": 4.613626507844012e-05, "Pretrain/Loss": 2.1177191734313965, "Pretrain/Loss (Raw)": 2.0759775638580322, "Pretrain/Step": 1945, "Pretrain/Step Time": 8.886324694380164} +{"Pretrain/Learning Rate": 4.613172981221268e-05, "Pretrain/Loss": 2.119638442993164, "Pretrain/Loss (Raw)": 2.186692953109741, "Pretrain/Step": 1946, "Pretrain/Step Time": 8.877803832292557} +{"Pretrain/Learning Rate": 4.612719210897459e-05, "Pretrain/Loss": 2.119398593902588, "Pretrain/Loss (Raw)": 2.122481107711792, "Pretrain/Step": 1947, "Pretrain/Step Time": 8.88392780162394} +{"Pretrain/Learning Rate": 4.612265196924914e-05, "Pretrain/Loss": 2.1193130016326904, "Pretrain/Loss (Raw)": 2.063538074493408, "Pretrain/Step": 1948, "Pretrain/Step Time": 8.87772260978818} +{"Pretrain/Learning Rate": 4.611810939355995e-05, "Pretrain/Loss": 2.1219658851623535, "Pretrain/Loss (Raw)": 2.198869228363037, "Pretrain/Step": 1949, "Pretrain/Step Time": 8.877033526077867} +{"Pretrain/Learning Rate": 4.611356438243085e-05, "Pretrain/Loss": 2.120959520339966, "Pretrain/Loss (Raw)": 2.0917179584503174, "Pretrain/Step": 1950, "Pretrain/Step Time": 8.879356713965535} +{"Pretrain/Learning Rate": 4.610901693638603e-05, "Pretrain/Loss": 2.120576858520508, "Pretrain/Loss (Raw)": 2.0946836471557617, "Pretrain/Step": 1951, "Pretrain/Step Time": 8.874506261199713} +{"Pretrain/Learning Rate": 4.610446705594991e-05, "Pretrain/Loss": 2.1208908557891846, "Pretrain/Loss (Raw)": 2.0929338932037354, "Pretrain/Step": 1952, "Pretrain/Step Time": 8.883380306884646} +{"Pretrain/Learning Rate": 4.6099914741647196e-05, "Pretrain/Loss": 2.1206655502319336, "Pretrain/Loss (Raw)": 2.172055244445801, "Pretrain/Step": 1953, "Pretrain/Step Time": 8.885519782081246} +{"Pretrain/Learning Rate": 4.609535999400289e-05, "Pretrain/Loss": 2.1214816570281982, "Pretrain/Loss (Raw)": 2.1173863410949707, "Pretrain/Step": 1954, "Pretrain/Step Time": 8.884526608511806} +{"Pretrain/Learning Rate": 4.6090802813542255e-05, "Pretrain/Loss": 2.1206600666046143, "Pretrain/Loss (Raw)": 1.9899523258209229, "Pretrain/Step": 1955, "Pretrain/Step Time": 8.881326725706458} +{"Pretrain/Learning Rate": 4.608624320079087e-05, "Pretrain/Loss": 2.12131404876709, "Pretrain/Loss (Raw)": 2.058926820755005, "Pretrain/Step": 1956, "Pretrain/Step Time": 8.891738567501307} +{"Pretrain/Learning Rate": 4.608168115627455e-05, "Pretrain/Loss": 2.1207051277160645, "Pretrain/Loss (Raw)": 2.097412109375, "Pretrain/Step": 1957, "Pretrain/Step Time": 8.876552609726787} +{"Pretrain/Learning Rate": 4.607711668051942e-05, "Pretrain/Loss": 2.121685266494751, "Pretrain/Loss (Raw)": 2.1216821670532227, "Pretrain/Step": 1958, "Pretrain/Step Time": 8.873794227838516} +{"Pretrain/Learning Rate": 4.6072549774051874e-05, "Pretrain/Loss": 2.1225857734680176, "Pretrain/Loss (Raw)": 2.0944881439208984, "Pretrain/Step": 1959, "Pretrain/Step Time": 8.873821847140789} +{"Pretrain/Learning Rate": 4.60679804373986e-05, "Pretrain/Loss": 2.123216152191162, "Pretrain/Loss (Raw)": 2.1524734497070312, "Pretrain/Step": 1960, "Pretrain/Step Time": 8.870778882876039} +{"Pretrain/Learning Rate": 4.606340867108653e-05, "Pretrain/Loss": 2.1254208087921143, "Pretrain/Loss (Raw)": 2.361424684524536, "Pretrain/Step": 1961, "Pretrain/Step Time": 8.871963456273079} +{"Pretrain/Learning Rate": 4.605883447564293e-05, "Pretrain/Loss": 2.1255619525909424, "Pretrain/Loss (Raw)": 2.0617871284484863, "Pretrain/Step": 1962, "Pretrain/Step Time": 8.87152299657464} +{"Pretrain/Learning Rate": 4.6054257851595303e-05, "Pretrain/Loss": 2.1253294944763184, "Pretrain/Loss (Raw)": 2.043719530105591, "Pretrain/Step": 1963, "Pretrain/Step Time": 8.869296411052346} +{"Pretrain/Learning Rate": 4.604967879947145e-05, "Pretrain/Loss": 2.1234793663024902, "Pretrain/Loss (Raw)": 2.061936855316162, "Pretrain/Step": 1964, "Pretrain/Step Time": 8.87883760407567} +{"Pretrain/Learning Rate": 4.6045097319799447e-05, "Pretrain/Loss": 2.123569965362549, "Pretrain/Loss (Raw)": 2.2515017986297607, "Pretrain/Step": 1965, "Pretrain/Step Time": 8.873607804998755} +{"Pretrain/Learning Rate": 4.6040513413107655e-05, "Pretrain/Loss": 2.122933864593506, "Pretrain/Loss (Raw)": 2.1250691413879395, "Pretrain/Step": 1966, "Pretrain/Step Time": 8.87632129713893} +{"Pretrain/Learning Rate": 4.603592707992471e-05, "Pretrain/Loss": 2.1211628913879395, "Pretrain/Loss (Raw)": 2.0921754837036133, "Pretrain/Step": 1967, "Pretrain/Step Time": 8.87207330390811} +{"Pretrain/Learning Rate": 4.6031338320779534e-05, "Pretrain/Loss": 2.1195600032806396, "Pretrain/Loss (Raw)": 1.9624269008636475, "Pretrain/Step": 1968, "Pretrain/Step Time": 8.878314808011055} +{"Pretrain/Learning Rate": 4.602674713620131e-05, "Pretrain/Loss": 2.1187024116516113, "Pretrain/Loss (Raw)": 1.9788577556610107, "Pretrain/Step": 1969, "Pretrain/Step Time": 8.872172908857465} +{"Pretrain/Learning Rate": 4.6022153526719536e-05, "Pretrain/Loss": 2.1201400756835938, "Pretrain/Loss (Raw)": 2.246730327606201, "Pretrain/Step": 1970, "Pretrain/Step Time": 8.874069074168801} +{"Pretrain/Learning Rate": 4.601755749286395e-05, "Pretrain/Loss": 2.1203863620758057, "Pretrain/Loss (Raw)": 2.2214906215667725, "Pretrain/Step": 1971, "Pretrain/Step Time": 8.875318536534905} +{"Pretrain/Learning Rate": 4.6012959035164596e-05, "Pretrain/Loss": 2.1215310096740723, "Pretrain/Loss (Raw)": 2.206559419631958, "Pretrain/Step": 1972, "Pretrain/Step Time": 8.872049232944846} +{"Pretrain/Learning Rate": 4.6008358154151794e-05, "Pretrain/Loss": 2.122711658477783, "Pretrain/Loss (Raw)": 2.184159755706787, "Pretrain/Step": 1973, "Pretrain/Step Time": 8.86568851955235} +{"Pretrain/Learning Rate": 4.600375485035613e-05, "Pretrain/Loss": 2.123415470123291, "Pretrain/Loss (Raw)": 2.051241159439087, "Pretrain/Step": 1974, "Pretrain/Step Time": 8.86910250224173} +{"Pretrain/Learning Rate": 4.599914912430849e-05, "Pretrain/Loss": 2.1230034828186035, "Pretrain/Loss (Raw)": 2.132558584213257, "Pretrain/Step": 1975, "Pretrain/Step Time": 8.868023704737425} +{"Pretrain/Learning Rate": 4.5994540976540013e-05, "Pretrain/Loss": 2.123493194580078, "Pretrain/Loss (Raw)": 2.195066213607788, "Pretrain/Step": 1976, "Pretrain/Step Time": 8.870122006163001} +{"Pretrain/Learning Rate": 4.598993040758215e-05, "Pretrain/Loss": 2.125133991241455, "Pretrain/Loss (Raw)": 2.2336933612823486, "Pretrain/Step": 1977, "Pretrain/Step Time": 8.86880387365818} +{"Pretrain/Learning Rate": 4.59853174179666e-05, "Pretrain/Loss": 2.1242990493774414, "Pretrain/Loss (Raw)": 1.9536668062210083, "Pretrain/Step": 1978, "Pretrain/Step Time": 8.867046024650335} +{"Pretrain/Learning Rate": 4.5980702008225365e-05, "Pretrain/Loss": 2.123107671737671, "Pretrain/Loss (Raw)": 1.9465103149414062, "Pretrain/Step": 1979, "Pretrain/Step Time": 8.861500892788172} +{"Pretrain/Learning Rate": 4.59760841788907e-05, "Pretrain/Loss": 2.1228089332580566, "Pretrain/Loss (Raw)": 2.166325807571411, "Pretrain/Step": 1980, "Pretrain/Step Time": 8.868154037743807} +{"Pretrain/Learning Rate": 4.597146393049517e-05, "Pretrain/Loss": 2.1221065521240234, "Pretrain/Loss (Raw)": 1.9845571517944336, "Pretrain/Step": 1981, "Pretrain/Step Time": 8.872424099594355} +{"Pretrain/Learning Rate": 4.59668412635716e-05, "Pretrain/Loss": 2.122368335723877, "Pretrain/Loss (Raw)": 2.2100706100463867, "Pretrain/Step": 1982, "Pretrain/Step Time": 8.871172033250332} +{"Pretrain/Learning Rate": 4.5962216178653095e-05, "Pretrain/Loss": 2.122603416442871, "Pretrain/Loss (Raw)": 2.1374623775482178, "Pretrain/Step": 1983, "Pretrain/Step Time": 8.87858765013516} +{"Pretrain/Learning Rate": 4.5957588676273046e-05, "Pretrain/Loss": 2.122645616531372, "Pretrain/Loss (Raw)": 2.195964813232422, "Pretrain/Step": 1984, "Pretrain/Step Time": 8.867663614451885} +{"Pretrain/Learning Rate": 4.595295875696511e-05, "Pretrain/Loss": 2.1213104724884033, "Pretrain/Loss (Raw)": 1.9147204160690308, "Pretrain/Step": 1985, "Pretrain/Step Time": 8.869559789076447} +{"Pretrain/Learning Rate": 4.5948326421263244e-05, "Pretrain/Loss": 2.1225528717041016, "Pretrain/Loss (Raw)": 2.162818193435669, "Pretrain/Step": 1986, "Pretrain/Step Time": 8.877295071259141} +{"Pretrain/Learning Rate": 4.5943691669701654e-05, "Pretrain/Loss": 2.1216464042663574, "Pretrain/Loss (Raw)": 1.9455922842025757, "Pretrain/Step": 1987, "Pretrain/Step Time": 8.865020044147968} +{"Pretrain/Learning Rate": 4.593905450281486e-05, "Pretrain/Loss": 2.1214523315429688, "Pretrain/Loss (Raw)": 2.1133580207824707, "Pretrain/Step": 1988, "Pretrain/Step Time": 8.870449038222432} +{"Pretrain/Learning Rate": 4.593441492113763e-05, "Pretrain/Loss": 2.1207189559936523, "Pretrain/Loss (Raw)": 2.0429229736328125, "Pretrain/Step": 1989, "Pretrain/Step Time": 8.86610876582563} +{"Pretrain/Learning Rate": 4.5929772925205014e-05, "Pretrain/Loss": 2.12182354927063, "Pretrain/Loss (Raw)": 2.1256866455078125, "Pretrain/Step": 1990, "Pretrain/Step Time": 8.869134103879333} +{"Pretrain/Learning Rate": 4.592512851555237e-05, "Pretrain/Loss": 2.121814727783203, "Pretrain/Loss (Raw)": 2.169903516769409, "Pretrain/Step": 1991, "Pretrain/Step Time": 8.87220037356019} +{"Pretrain/Learning Rate": 4.592048169271531e-05, "Pretrain/Loss": 2.1210250854492188, "Pretrain/Loss (Raw)": 2.102388858795166, "Pretrain/Step": 1992, "Pretrain/Step Time": 8.870700662955642} +{"Pretrain/Learning Rate": 4.591583245722971e-05, "Pretrain/Loss": 2.120466709136963, "Pretrain/Loss (Raw)": 2.040853500366211, "Pretrain/Step": 1993, "Pretrain/Step Time": 8.86940448358655} +{"Pretrain/Learning Rate": 4.591118080963176e-05, "Pretrain/Loss": 2.119751453399658, "Pretrain/Loss (Raw)": 2.040661573410034, "Pretrain/Step": 1994, "Pretrain/Step Time": 8.875042097643018} +{"Pretrain/Learning Rate": 4.590652675045789e-05, "Pretrain/Loss": 2.1213862895965576, "Pretrain/Loss (Raw)": 2.464616537094116, "Pretrain/Step": 1995, "Pretrain/Step Time": 8.873473770916462} +{"Pretrain/Learning Rate": 4.5901870280244855e-05, "Pretrain/Loss": 2.1208808422088623, "Pretrain/Loss (Raw)": 2.0859310626983643, "Pretrain/Step": 1996, "Pretrain/Step Time": 8.873674193397164} +{"Pretrain/Learning Rate": 4.589721139952964e-05, "Pretrain/Loss": 2.122152805328369, "Pretrain/Loss (Raw)": 2.187191963195801, "Pretrain/Step": 1997, "Pretrain/Step Time": 8.872918849810958} +{"Pretrain/Learning Rate": 4.589255010884953e-05, "Pretrain/Loss": 2.1200790405273438, "Pretrain/Loss (Raw)": 1.985265851020813, "Pretrain/Step": 1998, "Pretrain/Step Time": 8.873446745797992} +{"Pretrain/Learning Rate": 4.58878864087421e-05, "Pretrain/Loss": 2.11991548538208, "Pretrain/Loss (Raw)": 2.187945604324341, "Pretrain/Step": 1999, "Pretrain/Step Time": 8.874064333736897} +{"Pretrain/Learning Rate": 4.5883220299745176e-05, "Pretrain/Loss": 2.1178081035614014, "Pretrain/Loss (Raw)": 1.9375659227371216, "Pretrain/Step": 2000, "Pretrain/Step Time": 8.876435516402125} +{"Pretrain/Learning Rate": 4.587855178239689e-05, "Pretrain/Loss": 2.1180200576782227, "Pretrain/Loss (Raw)": 2.0805823802948, "Pretrain/Step": 2001, "Pretrain/Step Time": 8.87490113452077} +{"Pretrain/Learning Rate": 4.587388085723562e-05, "Pretrain/Loss": 2.117758274078369, "Pretrain/Loss (Raw)": 2.0662968158721924, "Pretrain/Step": 2002, "Pretrain/Step Time": 8.871305713430047} +{"Pretrain/Learning Rate": 4.586920752480006e-05, "Pretrain/Loss": 2.116382598876953, "Pretrain/Loss (Raw)": 2.0959057807922363, "Pretrain/Step": 2003, "Pretrain/Step Time": 8.875282600522041} +{"Pretrain/Learning Rate": 4.5864531785629136e-05, "Pretrain/Loss": 2.116215705871582, "Pretrain/Loss (Raw)": 2.0363051891326904, "Pretrain/Step": 2004, "Pretrain/Step Time": 8.879962986335158} +{"Pretrain/Learning Rate": 4.5859853640262104e-05, "Pretrain/Loss": 2.1152002811431885, "Pretrain/Loss (Raw)": 2.1719162464141846, "Pretrain/Step": 2005, "Pretrain/Step Time": 8.88667649962008} +{"Pretrain/Learning Rate": 4.5855173089238445e-05, "Pretrain/Loss": 2.116137981414795, "Pretrain/Loss (Raw)": 2.132108211517334, "Pretrain/Step": 2006, "Pretrain/Step Time": 8.892427353188396} +{"Pretrain/Learning Rate": 4.5850490133097957e-05, "Pretrain/Loss": 2.1154837608337402, "Pretrain/Loss (Raw)": 2.08318829536438, "Pretrain/Step": 2007, "Pretrain/Step Time": 8.891493529081345} +{"Pretrain/Learning Rate": 4.584580477238069e-05, "Pretrain/Loss": 2.1165361404418945, "Pretrain/Loss (Raw)": 2.3248188495635986, "Pretrain/Step": 2008, "Pretrain/Step Time": 8.89492368325591} +{"Pretrain/Learning Rate": 4.5841117007627e-05, "Pretrain/Loss": 2.117281198501587, "Pretrain/Loss (Raw)": 2.138578176498413, "Pretrain/Step": 2009, "Pretrain/Step Time": 8.89511325955391} +{"Pretrain/Learning Rate": 4.583642683937748e-05, "Pretrain/Loss": 2.1189467906951904, "Pretrain/Loss (Raw)": 2.2179245948791504, "Pretrain/Step": 2010, "Pretrain/Step Time": 8.892384756356478} +{"Pretrain/Learning Rate": 4.583173426817304e-05, "Pretrain/Loss": 2.118896245956421, "Pretrain/Loss (Raw)": 2.07412052154541, "Pretrain/Step": 2011, "Pretrain/Step Time": 8.889259848743677} +{"Pretrain/Learning Rate": 4.5827039294554833e-05, "Pretrain/Loss": 2.118720531463623, "Pretrain/Loss (Raw)": 1.940967321395874, "Pretrain/Step": 2012, "Pretrain/Step Time": 8.888240283355117} +{"Pretrain/Learning Rate": 4.582234191906432e-05, "Pretrain/Loss": 2.1198041439056396, "Pretrain/Loss (Raw)": 2.2091598510742188, "Pretrain/Step": 2013, "Pretrain/Step Time": 8.892610156908631} +{"Pretrain/Learning Rate": 4.581764214224322e-05, "Pretrain/Loss": 2.118725299835205, "Pretrain/Loss (Raw)": 2.125061511993408, "Pretrain/Step": 2014, "Pretrain/Step Time": 8.891487434506416} +{"Pretrain/Learning Rate": 4.581293996463353e-05, "Pretrain/Loss": 2.1168978214263916, "Pretrain/Loss (Raw)": 1.968888282775879, "Pretrain/Step": 2015, "Pretrain/Step Time": 8.890018586069345} +{"Pretrain/Learning Rate": 4.580823538677753e-05, "Pretrain/Loss": 2.1180636882781982, "Pretrain/Loss (Raw)": 2.0654282569885254, "Pretrain/Step": 2016, "Pretrain/Step Time": 8.891248870640993} +{"Pretrain/Learning Rate": 4.580352840921777e-05, "Pretrain/Loss": 2.117500066757202, "Pretrain/Loss (Raw)": 2.08703351020813, "Pretrain/Step": 2017, "Pretrain/Step Time": 8.890522202476859} +{"Pretrain/Learning Rate": 4.579881903249709e-05, "Pretrain/Loss": 2.1196460723876953, "Pretrain/Loss (Raw)": 2.20792818069458, "Pretrain/Step": 2018, "Pretrain/Step Time": 8.88531244173646} +{"Pretrain/Learning Rate": 4.5794107257158595e-05, "Pretrain/Loss": 2.1214027404785156, "Pretrain/Loss (Raw)": 2.2578396797180176, "Pretrain/Step": 2019, "Pretrain/Step Time": 8.883060552179813} +{"Pretrain/Learning Rate": 4.578939308374566e-05, "Pretrain/Loss": 2.1185874938964844, "Pretrain/Loss (Raw)": 1.9049787521362305, "Pretrain/Step": 2020, "Pretrain/Step Time": 8.880526402965188} +{"Pretrain/Learning Rate": 4.578467651280195e-05, "Pretrain/Loss": 2.1172432899475098, "Pretrain/Loss (Raw)": 2.0518639087677, "Pretrain/Step": 2021, "Pretrain/Step Time": 8.879625825211406} +{"Pretrain/Learning Rate": 4.57799575448714e-05, "Pretrain/Loss": 2.117551326751709, "Pretrain/Loss (Raw)": 2.1113133430480957, "Pretrain/Step": 2022, "Pretrain/Step Time": 8.882127555087209} +{"Pretrain/Learning Rate": 4.5775236180498235e-05, "Pretrain/Loss": 2.117755889892578, "Pretrain/Loss (Raw)": 2.0669636726379395, "Pretrain/Step": 2023, "Pretrain/Step Time": 8.875239480286837} +{"Pretrain/Learning Rate": 4.5770512420226934e-05, "Pretrain/Loss": 2.118579864501953, "Pretrain/Loss (Raw)": 1.9646552801132202, "Pretrain/Step": 2024, "Pretrain/Step Time": 8.879606543108821} +{"Pretrain/Learning Rate": 4.5765786264602274e-05, "Pretrain/Loss": 2.12009596824646, "Pretrain/Loss (Raw)": 2.2040913105010986, "Pretrain/Step": 2025, "Pretrain/Step Time": 8.879220569506288} +{"Pretrain/Learning Rate": 4.5761057714169284e-05, "Pretrain/Loss": 2.119579315185547, "Pretrain/Loss (Raw)": 2.0351479053497314, "Pretrain/Step": 2026, "Pretrain/Step Time": 8.884990014135838} +{"Pretrain/Learning Rate": 4.575632676947329e-05, "Pretrain/Loss": 2.1195361614227295, "Pretrain/Loss (Raw)": 1.9949719905853271, "Pretrain/Step": 2027, "Pretrain/Step Time": 8.87673713825643} +{"Pretrain/Learning Rate": 4.575159343105988e-05, "Pretrain/Loss": 2.1198232173919678, "Pretrain/Loss (Raw)": 2.2034103870391846, "Pretrain/Step": 2028, "Pretrain/Step Time": 8.882702261209488} +{"Pretrain/Learning Rate": 4.5746857699474946e-05, "Pretrain/Loss": 2.118546962738037, "Pretrain/Loss (Raw)": 2.0110573768615723, "Pretrain/Step": 2029, "Pretrain/Step Time": 8.880331158638} +{"Pretrain/Learning Rate": 4.574211957526461e-05, "Pretrain/Loss": 2.1186115741729736, "Pretrain/Loss (Raw)": 2.184921979904175, "Pretrain/Step": 2030, "Pretrain/Step Time": 8.879334384575486} +{"Pretrain/Learning Rate": 4.57373790589753e-05, "Pretrain/Loss": 2.118269443511963, "Pretrain/Loss (Raw)": 2.017714023590088, "Pretrain/Step": 2031, "Pretrain/Step Time": 8.887494392693043} +{"Pretrain/Learning Rate": 4.573263615115372e-05, "Pretrain/Loss": 2.119502544403076, "Pretrain/Loss (Raw)": 2.328484535217285, "Pretrain/Step": 2032, "Pretrain/Step Time": 8.874773483723402} +{"Pretrain/Learning Rate": 4.572789085234686e-05, "Pretrain/Loss": 2.119185209274292, "Pretrain/Loss (Raw)": 2.14279842376709, "Pretrain/Step": 2033, "Pretrain/Step Time": 8.873801566660404} +{"Pretrain/Learning Rate": 4.5723143163101934e-05, "Pretrain/Loss": 2.119269609451294, "Pretrain/Loss (Raw)": 2.1741151809692383, "Pretrain/Step": 2034, "Pretrain/Step Time": 8.869551932439208} +{"Pretrain/Learning Rate": 4.571839308396649e-05, "Pretrain/Loss": 2.118384838104248, "Pretrain/Loss (Raw)": 2.149538278579712, "Pretrain/Step": 2035, "Pretrain/Step Time": 8.874828957021236} +{"Pretrain/Learning Rate": 4.571364061548834e-05, "Pretrain/Loss": 2.1157572269439697, "Pretrain/Loss (Raw)": 2.140249729156494, "Pretrain/Step": 2036, "Pretrain/Step Time": 8.870436580851674} +{"Pretrain/Learning Rate": 4.5708885758215543e-05, "Pretrain/Loss": 2.114996910095215, "Pretrain/Loss (Raw)": 2.192755937576294, "Pretrain/Step": 2037, "Pretrain/Step Time": 8.87410500086844} +{"Pretrain/Learning Rate": 4.570412851269645e-05, "Pretrain/Loss": 2.1132562160491943, "Pretrain/Loss (Raw)": 1.8685905933380127, "Pretrain/Step": 2038, "Pretrain/Step Time": 8.86994069069624} +{"Pretrain/Learning Rate": 4.56993688794797e-05, "Pretrain/Loss": 2.1130211353302, "Pretrain/Loss (Raw)": 1.995408058166504, "Pretrain/Step": 2039, "Pretrain/Step Time": 8.873446475714445} +{"Pretrain/Learning Rate": 4.5694606859114196e-05, "Pretrain/Loss": 2.112318515777588, "Pretrain/Loss (Raw)": 2.171684503555298, "Pretrain/Step": 2040, "Pretrain/Step Time": 8.871521206572652} +{"Pretrain/Learning Rate": 4.5689842452149114e-05, "Pretrain/Loss": 2.1113169193267822, "Pretrain/Loss (Raw)": 2.1997296810150146, "Pretrain/Step": 2041, "Pretrain/Step Time": 8.874394536018372} +{"Pretrain/Learning Rate": 4.56850756591339e-05, "Pretrain/Loss": 2.1104164123535156, "Pretrain/Loss (Raw)": 2.0715596675872803, "Pretrain/Step": 2042, "Pretrain/Step Time": 8.87064821086824} +{"Pretrain/Learning Rate": 4.56803064806183e-05, "Pretrain/Loss": 2.110586643218994, "Pretrain/Loss (Raw)": 2.1812126636505127, "Pretrain/Step": 2043, "Pretrain/Step Time": 8.871941713616252} +{"Pretrain/Learning Rate": 4.567553491715229e-05, "Pretrain/Loss": 2.107712507247925, "Pretrain/Loss (Raw)": 1.8377223014831543, "Pretrain/Step": 2044, "Pretrain/Step Time": 8.864536156877875} +{"Pretrain/Learning Rate": 4.567076096928618e-05, "Pretrain/Loss": 2.1087253093719482, "Pretrain/Loss (Raw)": 2.0588736534118652, "Pretrain/Step": 2045, "Pretrain/Step Time": 8.869779096916318} +{"Pretrain/Learning Rate": 4.566598463757051e-05, "Pretrain/Loss": 2.1072964668273926, "Pretrain/Loss (Raw)": 1.9749712944030762, "Pretrain/Step": 2046, "Pretrain/Step Time": 8.876006180420518} +{"Pretrain/Learning Rate": 4.56612059225561e-05, "Pretrain/Loss": 2.1071982383728027, "Pretrain/Loss (Raw)": 2.0963780879974365, "Pretrain/Step": 2047, "Pretrain/Step Time": 8.874741163104773} +{"Pretrain/Learning Rate": 4.565642482479408e-05, "Pretrain/Loss": 2.107194423675537, "Pretrain/Loss (Raw)": 2.176109790802002, "Pretrain/Step": 2048, "Pretrain/Step Time": 8.873106338083744} +{"Pretrain/Learning Rate": 4.565164134483581e-05, "Pretrain/Loss": 2.1081855297088623, "Pretrain/Loss (Raw)": 2.0528640747070312, "Pretrain/Step": 2049, "Pretrain/Step Time": 8.86526164226234} +{"Pretrain/Learning Rate": 4.5646855483232935e-05, "Pretrain/Loss": 2.108259677886963, "Pretrain/Loss (Raw)": 2.1262943744659424, "Pretrain/Step": 2050, "Pretrain/Step Time": 8.863655870780349} +{"Pretrain/Learning Rate": 4.56420672405374e-05, "Pretrain/Loss": 2.1071701049804688, "Pretrain/Loss (Raw)": 1.9240877628326416, "Pretrain/Step": 2051, "Pretrain/Step Time": 8.857632577419281} +{"Pretrain/Learning Rate": 4.563727661730141e-05, "Pretrain/Loss": 2.1078739166259766, "Pretrain/Loss (Raw)": 2.177872657775879, "Pretrain/Step": 2052, "Pretrain/Step Time": 8.858178976923227} +{"Pretrain/Learning Rate": 4.563248361407743e-05, "Pretrain/Loss": 2.1056642532348633, "Pretrain/Loss (Raw)": 2.123476266860962, "Pretrain/Step": 2053, "Pretrain/Step Time": 8.8561908043921} +{"Pretrain/Learning Rate": 4.562768823141821e-05, "Pretrain/Loss": 2.1070919036865234, "Pretrain/Loss (Raw)": 2.185563325881958, "Pretrain/Step": 2054, "Pretrain/Step Time": 8.862550470978022} +{"Pretrain/Learning Rate": 4.562289046987679e-05, "Pretrain/Loss": 2.1078901290893555, "Pretrain/Loss (Raw)": 2.3666532039642334, "Pretrain/Step": 2055, "Pretrain/Step Time": 8.859554514288902} +{"Pretrain/Learning Rate": 4.561809033000646e-05, "Pretrain/Loss": 2.1090025901794434, "Pretrain/Loss (Raw)": 2.1561355590820312, "Pretrain/Step": 2056, "Pretrain/Step Time": 8.868901507928967} +{"Pretrain/Learning Rate": 4.5613287812360796e-05, "Pretrain/Loss": 2.1089391708374023, "Pretrain/Loss (Raw)": 2.0720419883728027, "Pretrain/Step": 2057, "Pretrain/Step Time": 8.861388998106122} +{"Pretrain/Learning Rate": 4.560848291749365e-05, "Pretrain/Loss": 2.1085450649261475, "Pretrain/Loss (Raw)": 2.0686733722686768, "Pretrain/Step": 2058, "Pretrain/Step Time": 8.867238219827414} +{"Pretrain/Learning Rate": 4.560367564595914e-05, "Pretrain/Loss": 2.10927152633667, "Pretrain/Loss (Raw)": 2.038079261779785, "Pretrain/Step": 2059, "Pretrain/Step Time": 8.860719133168459} +{"Pretrain/Learning Rate": 4.559886599831167e-05, "Pretrain/Loss": 2.1088337898254395, "Pretrain/Loss (Raw)": 2.0650131702423096, "Pretrain/Step": 2060, "Pretrain/Step Time": 8.859086342155933} +{"Pretrain/Learning Rate": 4.559405397510591e-05, "Pretrain/Loss": 2.107435464859009, "Pretrain/Loss (Raw)": 1.933190941810608, "Pretrain/Step": 2061, "Pretrain/Step Time": 8.866395553573966} +{"Pretrain/Learning Rate": 4.55892395768968e-05, "Pretrain/Loss": 2.106846809387207, "Pretrain/Loss (Raw)": 2.0606849193573, "Pretrain/Step": 2062, "Pretrain/Step Time": 8.855456251651049} +{"Pretrain/Learning Rate": 4.5584422804239566e-05, "Pretrain/Loss": 2.1062850952148438, "Pretrain/Loss (Raw)": 2.10910701751709, "Pretrain/Step": 2063, "Pretrain/Step Time": 8.85915051959455} +{"Pretrain/Learning Rate": 4.55796036576897e-05, "Pretrain/Loss": 2.107438564300537, "Pretrain/Loss (Raw)": 2.211711883544922, "Pretrain/Step": 2064, "Pretrain/Step Time": 8.858327658846974} +{"Pretrain/Learning Rate": 4.557478213780295e-05, "Pretrain/Loss": 2.1073668003082275, "Pretrain/Loss (Raw)": 2.1935222148895264, "Pretrain/Step": 2065, "Pretrain/Step Time": 8.863589813932776} +{"Pretrain/Learning Rate": 4.556995824513539e-05, "Pretrain/Loss": 2.1063289642333984, "Pretrain/Loss (Raw)": 2.081972599029541, "Pretrain/Step": 2066, "Pretrain/Step Time": 8.862434394657612} +{"Pretrain/Learning Rate": 4.5565131980243305e-05, "Pretrain/Loss": 2.108701467514038, "Pretrain/Loss (Raw)": 2.2427656650543213, "Pretrain/Step": 2067, "Pretrain/Step Time": 8.863333325833082} +{"Pretrain/Learning Rate": 4.55603033436833e-05, "Pretrain/Loss": 2.1104114055633545, "Pretrain/Loss (Raw)": 2.228609085083008, "Pretrain/Step": 2068, "Pretrain/Step Time": 8.856919566169381} +{"Pretrain/Learning Rate": 4.555547233601223e-05, "Pretrain/Loss": 2.1100215911865234, "Pretrain/Loss (Raw)": 2.18784761428833, "Pretrain/Step": 2069, "Pretrain/Step Time": 8.859722411260009} +{"Pretrain/Learning Rate": 4.555063895778723e-05, "Pretrain/Loss": 2.1101841926574707, "Pretrain/Loss (Raw)": 2.2633278369903564, "Pretrain/Step": 2070, "Pretrain/Step Time": 8.868939280509949} +{"Pretrain/Learning Rate": 4.5545803209565704e-05, "Pretrain/Loss": 2.1115379333496094, "Pretrain/Loss (Raw)": 2.2841999530792236, "Pretrain/Step": 2071, "Pretrain/Step Time": 8.874647177755833} +{"Pretrain/Learning Rate": 4.554096509190534e-05, "Pretrain/Loss": 2.111266613006592, "Pretrain/Loss (Raw)": 2.0494754314422607, "Pretrain/Step": 2072, "Pretrain/Step Time": 8.870485035702586} +{"Pretrain/Learning Rate": 4.5536124605364085e-05, "Pretrain/Loss": 2.109600067138672, "Pretrain/Loss (Raw)": 1.8626227378845215, "Pretrain/Step": 2073, "Pretrain/Step Time": 8.8611204251647} +{"Pretrain/Learning Rate": 4.553128175050018e-05, "Pretrain/Loss": 2.1075165271759033, "Pretrain/Loss (Raw)": 1.919995903968811, "Pretrain/Step": 2074, "Pretrain/Step Time": 8.866295075044036} +{"Pretrain/Learning Rate": 4.552643652787211e-05, "Pretrain/Loss": 2.1070823669433594, "Pretrain/Loss (Raw)": 2.066896677017212, "Pretrain/Step": 2075, "Pretrain/Step Time": 8.8599495831877} +{"Pretrain/Learning Rate": 4.552158893803865e-05, "Pretrain/Loss": 2.106675148010254, "Pretrain/Loss (Raw)": 2.011437177658081, "Pretrain/Step": 2076, "Pretrain/Step Time": 8.868773579597473} +{"Pretrain/Learning Rate": 4.551673898155886e-05, "Pretrain/Loss": 2.105825901031494, "Pretrain/Loss (Raw)": 2.0901803970336914, "Pretrain/Step": 2077, "Pretrain/Step Time": 8.86225683055818} +{"Pretrain/Learning Rate": 4.5511886658992055e-05, "Pretrain/Loss": 2.1054506301879883, "Pretrain/Loss (Raw)": 2.04365873336792, "Pretrain/Step": 2078, "Pretrain/Step Time": 8.8653613217175} +{"Pretrain/Learning Rate": 4.550703197089782e-05, "Pretrain/Loss": 2.105764389038086, "Pretrain/Loss (Raw)": 2.13484525680542, "Pretrain/Step": 2079, "Pretrain/Step Time": 8.878930864855647} +{"Pretrain/Learning Rate": 4.550217491783603e-05, "Pretrain/Loss": 2.106637716293335, "Pretrain/Loss (Raw)": 2.204744577407837, "Pretrain/Step": 2080, "Pretrain/Step Time": 8.875816117972136} +{"Pretrain/Learning Rate": 4.549731550036682e-05, "Pretrain/Loss": 2.1080379486083984, "Pretrain/Loss (Raw)": 2.3512766361236572, "Pretrain/Step": 2081, "Pretrain/Step Time": 8.875248581171036} +{"Pretrain/Learning Rate": 4.5492453719050596e-05, "Pretrain/Loss": 2.1086864471435547, "Pretrain/Loss (Raw)": 2.200382709503174, "Pretrain/Step": 2082, "Pretrain/Step Time": 8.877076530829072} +{"Pretrain/Learning Rate": 4.5487589574448046e-05, "Pretrain/Loss": 2.1094393730163574, "Pretrain/Loss (Raw)": 2.086301803588867, "Pretrain/Step": 2083, "Pretrain/Step Time": 8.876938899978995} +{"Pretrain/Learning Rate": 4.5482723067120124e-05, "Pretrain/Loss": 2.109449863433838, "Pretrain/Loss (Raw)": 2.0602922439575195, "Pretrain/Step": 2084, "Pretrain/Step Time": 8.867631644010544} +{"Pretrain/Learning Rate": 4.547785419762807e-05, "Pretrain/Loss": 2.1092324256896973, "Pretrain/Loss (Raw)": 2.0695748329162598, "Pretrain/Step": 2085, "Pretrain/Step Time": 8.871248042210937} +{"Pretrain/Learning Rate": 4.547298296653336e-05, "Pretrain/Loss": 2.109555721282959, "Pretrain/Loss (Raw)": 2.1630992889404297, "Pretrain/Step": 2086, "Pretrain/Step Time": 8.877068094909191} +{"Pretrain/Learning Rate": 4.5468109374397796e-05, "Pretrain/Loss": 2.1105263233184814, "Pretrain/Loss (Raw)": 2.218705654144287, "Pretrain/Step": 2087, "Pretrain/Step Time": 8.88262957893312} +{"Pretrain/Learning Rate": 4.54632334217834e-05, "Pretrain/Loss": 2.110790252685547, "Pretrain/Loss (Raw)": 2.186265230178833, "Pretrain/Step": 2088, "Pretrain/Step Time": 8.878696221858263} +{"Pretrain/Learning Rate": 4.545835510925251e-05, "Pretrain/Loss": 2.1085305213928223, "Pretrain/Loss (Raw)": 2.0722005367279053, "Pretrain/Step": 2089, "Pretrain/Step Time": 8.880735764279962} +{"Pretrain/Learning Rate": 4.5453474437367695e-05, "Pretrain/Loss": 2.1088223457336426, "Pretrain/Loss (Raw)": 2.099081516265869, "Pretrain/Step": 2090, "Pretrain/Step Time": 8.879739539697766} +{"Pretrain/Learning Rate": 4.544859140669183e-05, "Pretrain/Loss": 2.1089091300964355, "Pretrain/Loss (Raw)": 2.0548434257507324, "Pretrain/Step": 2091, "Pretrain/Step Time": 8.880510685965419} +{"Pretrain/Learning Rate": 4.5443706017788054e-05, "Pretrain/Loss": 2.1092686653137207, "Pretrain/Loss (Raw)": 2.1079483032226562, "Pretrain/Step": 2092, "Pretrain/Step Time": 8.879369243979454} +{"Pretrain/Learning Rate": 4.5438818271219765e-05, "Pretrain/Loss": 2.108640432357788, "Pretrain/Loss (Raw)": 2.1711082458496094, "Pretrain/Step": 2093, "Pretrain/Step Time": 8.877664415165782} +{"Pretrain/Learning Rate": 4.5433928167550634e-05, "Pretrain/Loss": 2.1090826988220215, "Pretrain/Loss (Raw)": 2.181694746017456, "Pretrain/Step": 2094, "Pretrain/Step Time": 8.876706568524241} +{"Pretrain/Learning Rate": 4.542903570734463e-05, "Pretrain/Loss": 2.108187198638916, "Pretrain/Loss (Raw)": 1.9775094985961914, "Pretrain/Step": 2095, "Pretrain/Step Time": 8.878049002960324} +{"Pretrain/Learning Rate": 4.542414089116595e-05, "Pretrain/Loss": 2.108527183532715, "Pretrain/Loss (Raw)": 2.0059657096862793, "Pretrain/Step": 2096, "Pretrain/Step Time": 8.880209056660533} +{"Pretrain/Learning Rate": 4.541924371957911e-05, "Pretrain/Loss": 2.1125729084014893, "Pretrain/Loss (Raw)": 2.4967150688171387, "Pretrain/Step": 2097, "Pretrain/Step Time": 8.88333448022604} +{"Pretrain/Learning Rate": 4.5414344193148866e-05, "Pretrain/Loss": 2.1119508743286133, "Pretrain/Loss (Raw)": 2.167123317718506, "Pretrain/Step": 2098, "Pretrain/Step Time": 8.88139933720231} +{"Pretrain/Learning Rate": 4.540944231244025e-05, "Pretrain/Loss": 2.110461711883545, "Pretrain/Loss (Raw)": 2.0308609008789062, "Pretrain/Step": 2099, "Pretrain/Step Time": 8.88018019683659} +{"Pretrain/Learning Rate": 4.540453807801858e-05, "Pretrain/Loss": 2.1102371215820312, "Pretrain/Loss (Raw)": 2.1778178215026855, "Pretrain/Step": 2100, "Pretrain/Step Time": 8.882135873660445} +{"Pretrain/Learning Rate": 4.539963149044943e-05, "Pretrain/Loss": 2.1098792552948, "Pretrain/Loss (Raw)": 2.13835072517395, "Pretrain/Step": 2101, "Pretrain/Step Time": 8.882203716784716} +{"Pretrain/Learning Rate": 4.539472255029864e-05, "Pretrain/Loss": 2.1103391647338867, "Pretrain/Loss (Raw)": 2.110142707824707, "Pretrain/Step": 2102, "Pretrain/Step Time": 8.881393579766154} +{"Pretrain/Learning Rate": 4.538981125813235e-05, "Pretrain/Loss": 2.1070988178253174, "Pretrain/Loss (Raw)": 1.7177571058273315, "Pretrain/Step": 2103, "Pretrain/Step Time": 8.883961202576756} +{"Pretrain/Learning Rate": 4.538489761451694e-05, "Pretrain/Loss": 2.105653762817383, "Pretrain/Loss (Raw)": 2.010125160217285, "Pretrain/Step": 2104, "Pretrain/Step Time": 8.87959660962224} +{"Pretrain/Learning Rate": 4.537998162001909e-05, "Pretrain/Loss": 2.1016173362731934, "Pretrain/Loss (Raw)": 1.717025637626648, "Pretrain/Step": 2105, "Pretrain/Step Time": 8.88029532134533} +{"Pretrain/Learning Rate": 4.537506327520571e-05, "Pretrain/Loss": 2.1025052070617676, "Pretrain/Loss (Raw)": 2.0672874450683594, "Pretrain/Step": 2106, "Pretrain/Step Time": 8.880915779620409} +{"Pretrain/Learning Rate": 4.5370142580644036e-05, "Pretrain/Loss": 2.104672431945801, "Pretrain/Loss (Raw)": 2.223928689956665, "Pretrain/Step": 2107, "Pretrain/Step Time": 8.881246784701943} +{"Pretrain/Learning Rate": 4.536521953690153e-05, "Pretrain/Loss": 2.1025524139404297, "Pretrain/Loss (Raw)": 1.894945740699768, "Pretrain/Step": 2108, "Pretrain/Step Time": 8.885107025504112} +{"Pretrain/Learning Rate": 4.5360294144545946e-05, "Pretrain/Loss": 2.103698492050171, "Pretrain/Loss (Raw)": 2.1312708854675293, "Pretrain/Step": 2109, "Pretrain/Step Time": 8.878979234024882} +{"Pretrain/Learning Rate": 4.5355366404145294e-05, "Pretrain/Loss": 2.1029069423675537, "Pretrain/Loss (Raw)": 2.1087582111358643, "Pretrain/Step": 2110, "Pretrain/Step Time": 8.87660107202828} +{"Pretrain/Learning Rate": 4.5350436316267876e-05, "Pretrain/Loss": 2.1021862030029297, "Pretrain/Loss (Raw)": 2.0451784133911133, "Pretrain/Step": 2111, "Pretrain/Step Time": 8.86721176840365} +{"Pretrain/Learning Rate": 4.534550388148224e-05, "Pretrain/Loss": 2.1006836891174316, "Pretrain/Loss (Raw)": 2.0036814212799072, "Pretrain/Step": 2112, "Pretrain/Step Time": 8.870974441990256} +{"Pretrain/Learning Rate": 4.5340569100357235e-05, "Pretrain/Loss": 2.1057863235473633, "Pretrain/Loss (Raw)": 2.5678436756134033, "Pretrain/Step": 2113, "Pretrain/Step Time": 8.86789726279676} +{"Pretrain/Learning Rate": 4.5335631973461944e-05, "Pretrain/Loss": 2.105710506439209, "Pretrain/Loss (Raw)": 2.153101682662964, "Pretrain/Step": 2114, "Pretrain/Step Time": 8.866455575451255} +{"Pretrain/Learning Rate": 4.5330692501365755e-05, "Pretrain/Loss": 2.105304718017578, "Pretrain/Loss (Raw)": 1.8936556577682495, "Pretrain/Step": 2115, "Pretrain/Step Time": 8.872902981936932} +{"Pretrain/Learning Rate": 4.532575068463831e-05, "Pretrain/Loss": 2.106626510620117, "Pretrain/Loss (Raw)": 2.282534599304199, "Pretrain/Step": 2116, "Pretrain/Step Time": 8.867676859721541} +{"Pretrain/Learning Rate": 4.532080652384951e-05, "Pretrain/Loss": 2.1061627864837646, "Pretrain/Loss (Raw)": 1.9835922718048096, "Pretrain/Step": 2117, "Pretrain/Step Time": 8.874255241826177} +{"Pretrain/Learning Rate": 4.5315860019569546e-05, "Pretrain/Loss": 2.1068224906921387, "Pretrain/Loss (Raw)": 2.210160732269287, "Pretrain/Step": 2118, "Pretrain/Step Time": 8.869141701608896} +{"Pretrain/Learning Rate": 4.531091117236888e-05, "Pretrain/Loss": 2.1048338413238525, "Pretrain/Loss (Raw)": 1.9153072834014893, "Pretrain/Step": 2119, "Pretrain/Step Time": 8.86567597463727} +{"Pretrain/Learning Rate": 4.530595998281822e-05, "Pretrain/Loss": 2.1043033599853516, "Pretrain/Loss (Raw)": 2.034484624862671, "Pretrain/Step": 2120, "Pretrain/Step Time": 8.865371504798532} +{"Pretrain/Learning Rate": 4.530100645148858e-05, "Pretrain/Loss": 2.1055259704589844, "Pretrain/Loss (Raw)": 2.197368621826172, "Pretrain/Step": 2121, "Pretrain/Step Time": 8.87388089299202} +{"Pretrain/Learning Rate": 4.529605057895121e-05, "Pretrain/Loss": 2.104259967803955, "Pretrain/Loss (Raw)": 1.878623366355896, "Pretrain/Step": 2122, "Pretrain/Step Time": 8.867686262354255} +{"Pretrain/Learning Rate": 4.529109236577764e-05, "Pretrain/Loss": 2.1017744541168213, "Pretrain/Loss (Raw)": 2.1464598178863525, "Pretrain/Step": 2123, "Pretrain/Step Time": 8.867308165878057} +{"Pretrain/Learning Rate": 4.5286131812539704e-05, "Pretrain/Loss": 2.101048469543457, "Pretrain/Loss (Raw)": 1.9930129051208496, "Pretrain/Step": 2124, "Pretrain/Step Time": 8.860230883583426} +{"Pretrain/Learning Rate": 4.5281168919809444e-05, "Pretrain/Loss": 2.1013174057006836, "Pretrain/Loss (Raw)": 2.2216343879699707, "Pretrain/Step": 2125, "Pretrain/Step Time": 8.863046890124679} +{"Pretrain/Learning Rate": 4.527620368815921e-05, "Pretrain/Loss": 2.1017284393310547, "Pretrain/Loss (Raw)": 2.0378291606903076, "Pretrain/Step": 2126, "Pretrain/Step Time": 8.853773018345237} +{"Pretrain/Learning Rate": 4.527123611816163e-05, "Pretrain/Loss": 2.1019954681396484, "Pretrain/Loss (Raw)": 2.2221524715423584, "Pretrain/Step": 2127, "Pretrain/Step Time": 8.855477785691619} +{"Pretrain/Learning Rate": 4.526626621038958e-05, "Pretrain/Loss": 2.103123664855957, "Pretrain/Loss (Raw)": 2.081960916519165, "Pretrain/Step": 2128, "Pretrain/Step Time": 8.855946945026517} +{"Pretrain/Learning Rate": 4.526129396541621e-05, "Pretrain/Loss": 2.102907180786133, "Pretrain/Loss (Raw)": 2.0528907775878906, "Pretrain/Step": 2129, "Pretrain/Step Time": 8.861037340015173} +{"Pretrain/Learning Rate": 4.525631938381495e-05, "Pretrain/Loss": 2.1041767597198486, "Pretrain/Loss (Raw)": 2.2287964820861816, "Pretrain/Step": 2130, "Pretrain/Step Time": 8.865104671567678} +{"Pretrain/Learning Rate": 4.5251342466159487e-05, "Pretrain/Loss": 2.1060009002685547, "Pretrain/Loss (Raw)": 2.329390525817871, "Pretrain/Step": 2131, "Pretrain/Step Time": 8.867582254111767} +{"Pretrain/Learning Rate": 4.524636321302378e-05, "Pretrain/Loss": 2.106773614883423, "Pretrain/Loss (Raw)": 2.13521146774292, "Pretrain/Step": 2132, "Pretrain/Step Time": 8.864558840170503} +{"Pretrain/Learning Rate": 4.524138162498206e-05, "Pretrain/Loss": 2.1055080890655518, "Pretrain/Loss (Raw)": 2.0099334716796875, "Pretrain/Step": 2133, "Pretrain/Step Time": 8.860935492441058} +{"Pretrain/Learning Rate": 4.5236397702608833e-05, "Pretrain/Loss": 2.105825185775757, "Pretrain/Loss (Raw)": 2.172713279724121, "Pretrain/Step": 2134, "Pretrain/Step Time": 8.850509259849787} +{"Pretrain/Learning Rate": 4.5231411446478865e-05, "Pretrain/Loss": 2.10671329498291, "Pretrain/Loss (Raw)": 2.1968445777893066, "Pretrain/Step": 2135, "Pretrain/Step Time": 8.851659774780273} +{"Pretrain/Learning Rate": 4.5226422857167207e-05, "Pretrain/Loss": 2.1035428047180176, "Pretrain/Loss (Raw)": 1.918997883796692, "Pretrain/Step": 2136, "Pretrain/Step Time": 8.859906801953912} +{"Pretrain/Learning Rate": 4.5221431935249144e-05, "Pretrain/Loss": 2.103175163269043, "Pretrain/Loss (Raw)": 2.0915048122406006, "Pretrain/Step": 2137, "Pretrain/Step Time": 8.852688001468778} +{"Pretrain/Learning Rate": 4.5216438681300265e-05, "Pretrain/Loss": 2.103877305984497, "Pretrain/Loss (Raw)": 2.3078229427337646, "Pretrain/Step": 2138, "Pretrain/Step Time": 8.858166415244341} +{"Pretrain/Learning Rate": 4.521144309589641e-05, "Pretrain/Loss": 2.104668617248535, "Pretrain/Loss (Raw)": 2.175393581390381, "Pretrain/Step": 2139, "Pretrain/Step Time": 8.85402307473123} +{"Pretrain/Learning Rate": 4.520644517961371e-05, "Pretrain/Loss": 2.1065163612365723, "Pretrain/Loss (Raw)": 2.1774609088897705, "Pretrain/Step": 2140, "Pretrain/Step Time": 8.860894639045} +{"Pretrain/Learning Rate": 4.520144493302853e-05, "Pretrain/Loss": 2.1033034324645996, "Pretrain/Loss (Raw)": 1.7979131937026978, "Pretrain/Step": 2141, "Pretrain/Step Time": 8.855653833597898} +{"Pretrain/Learning Rate": 4.519644235671752e-05, "Pretrain/Loss": 2.103503704071045, "Pretrain/Loss (Raw)": 2.150723934173584, "Pretrain/Step": 2142, "Pretrain/Step Time": 8.857720781117678} +{"Pretrain/Learning Rate": 4.519143745125762e-05, "Pretrain/Loss": 2.1040732860565186, "Pretrain/Loss (Raw)": 2.041792631149292, "Pretrain/Step": 2143, "Pretrain/Step Time": 8.870204718783498} +{"Pretrain/Learning Rate": 4.5186430217226004e-05, "Pretrain/Loss": 2.1051840782165527, "Pretrain/Loss (Raw)": 2.2075986862182617, "Pretrain/Step": 2144, "Pretrain/Step Time": 8.87358134612441} +{"Pretrain/Learning Rate": 4.518142065520013e-05, "Pretrain/Loss": 2.1037724018096924, "Pretrain/Loss (Raw)": 1.9063471555709839, "Pretrain/Step": 2145, "Pretrain/Step Time": 8.861701859161258} +{"Pretrain/Learning Rate": 4.5176408765757736e-05, "Pretrain/Loss": 2.101379871368408, "Pretrain/Loss (Raw)": 1.9016984701156616, "Pretrain/Step": 2146, "Pretrain/Step Time": 8.862673867493868} +{"Pretrain/Learning Rate": 4.5171394549476794e-05, "Pretrain/Loss": 2.100493907928467, "Pretrain/Loss (Raw)": 2.144425392150879, "Pretrain/Step": 2147, "Pretrain/Step Time": 8.86325098015368} +{"Pretrain/Learning Rate": 4.5166378006935595e-05, "Pretrain/Loss": 2.102536201477051, "Pretrain/Loss (Raw)": 2.1663920879364014, "Pretrain/Step": 2148, "Pretrain/Step Time": 8.864162970334291} +{"Pretrain/Learning Rate": 4.5161359138712655e-05, "Pretrain/Loss": 2.1029038429260254, "Pretrain/Loss (Raw)": 2.0989179611206055, "Pretrain/Step": 2149, "Pretrain/Step Time": 8.868756109848619} +{"Pretrain/Learning Rate": 4.5156337945386775e-05, "Pretrain/Loss": 2.102846384048462, "Pretrain/Loss (Raw)": 2.1039693355560303, "Pretrain/Step": 2150, "Pretrain/Step Time": 8.868074860423803} +{"Pretrain/Learning Rate": 4.515131442753703e-05, "Pretrain/Loss": 2.1033265590667725, "Pretrain/Loss (Raw)": 2.128429412841797, "Pretrain/Step": 2151, "Pretrain/Step Time": 8.871281363070011} +{"Pretrain/Learning Rate": 4.5146288585742737e-05, "Pretrain/Loss": 2.105442523956299, "Pretrain/Loss (Raw)": 2.2355000972747803, "Pretrain/Step": 2152, "Pretrain/Step Time": 8.870758963748813} +{"Pretrain/Learning Rate": 4.514126042058352e-05, "Pretrain/Loss": 2.1042795181274414, "Pretrain/Loss (Raw)": 2.055208206176758, "Pretrain/Step": 2153, "Pretrain/Step Time": 8.873682651668787} +{"Pretrain/Learning Rate": 4.513622993263924e-05, "Pretrain/Loss": 2.105545997619629, "Pretrain/Loss (Raw)": 2.197258234024048, "Pretrain/Step": 2154, "Pretrain/Step Time": 8.872101480141282} +{"Pretrain/Learning Rate": 4.5131197122490035e-05, "Pretrain/Loss": 2.1059374809265137, "Pretrain/Loss (Raw)": 2.045085906982422, "Pretrain/Step": 2155, "Pretrain/Step Time": 8.872201899066567} +{"Pretrain/Learning Rate": 4.512616199071632e-05, "Pretrain/Loss": 2.1049132347106934, "Pretrain/Loss (Raw)": 2.0722951889038086, "Pretrain/Step": 2156, "Pretrain/Step Time": 8.873853048309684} +{"Pretrain/Learning Rate": 4.512112453789877e-05, "Pretrain/Loss": 2.1044559478759766, "Pretrain/Loss (Raw)": 1.9525129795074463, "Pretrain/Step": 2157, "Pretrain/Step Time": 8.873920436948538} +{"Pretrain/Learning Rate": 4.5116084764618325e-05, "Pretrain/Loss": 2.1033177375793457, "Pretrain/Loss (Raw)": 2.0392558574676514, "Pretrain/Step": 2158, "Pretrain/Step Time": 8.87399110198021} +{"Pretrain/Learning Rate": 4.511104267145618e-05, "Pretrain/Loss": 2.105166435241699, "Pretrain/Loss (Raw)": 2.25433087348938, "Pretrain/Step": 2159, "Pretrain/Step Time": 8.870618870481849} +{"Pretrain/Learning Rate": 4.510599825899384e-05, "Pretrain/Loss": 2.1038336753845215, "Pretrain/Loss (Raw)": 2.157905101776123, "Pretrain/Step": 2160, "Pretrain/Step Time": 8.8769865706563} +{"Pretrain/Learning Rate": 4.510095152781304e-05, "Pretrain/Loss": 2.1026649475097656, "Pretrain/Loss (Raw)": 1.9931964874267578, "Pretrain/Step": 2161, "Pretrain/Step Time": 8.878268266096711} +{"Pretrain/Learning Rate": 4.509590247849579e-05, "Pretrain/Loss": 2.1020846366882324, "Pretrain/Loss (Raw)": 2.0998287200927734, "Pretrain/Step": 2162, "Pretrain/Step Time": 8.880511792376637} +{"Pretrain/Learning Rate": 4.509085111162437e-05, "Pretrain/Loss": 2.100851535797119, "Pretrain/Loss (Raw)": 1.9917314052581787, "Pretrain/Step": 2163, "Pretrain/Step Time": 8.879738695919514} +{"Pretrain/Learning Rate": 4.508579742778133e-05, "Pretrain/Loss": 2.1007556915283203, "Pretrain/Loss (Raw)": 2.1279735565185547, "Pretrain/Step": 2164, "Pretrain/Step Time": 8.87962781637907} +{"Pretrain/Learning Rate": 4.508074142754948e-05, "Pretrain/Loss": 2.099578380584717, "Pretrain/Loss (Raw)": 2.042039632797241, "Pretrain/Step": 2165, "Pretrain/Step Time": 8.875628059729934} +{"Pretrain/Learning Rate": 4.507568311151191e-05, "Pretrain/Loss": 2.10152006149292, "Pretrain/Loss (Raw)": 2.1171247959136963, "Pretrain/Step": 2166, "Pretrain/Step Time": 8.877490911632776} +{"Pretrain/Learning Rate": 4.5070622480251955e-05, "Pretrain/Loss": 2.1020140647888184, "Pretrain/Loss (Raw)": 2.0586700439453125, "Pretrain/Step": 2167, "Pretrain/Step Time": 8.879832295700908} +{"Pretrain/Learning Rate": 4.506555953435324e-05, "Pretrain/Loss": 2.10213041305542, "Pretrain/Loss (Raw)": 2.1865553855895996, "Pretrain/Step": 2168, "Pretrain/Step Time": 8.878638785332441} +{"Pretrain/Learning Rate": 4.5060494274399654e-05, "Pretrain/Loss": 2.101816177368164, "Pretrain/Loss (Raw)": 2.159494400024414, "Pretrain/Step": 2169, "Pretrain/Step Time": 8.877174498513341} +{"Pretrain/Learning Rate": 4.505542670097534e-05, "Pretrain/Loss": 2.102184772491455, "Pretrain/Loss (Raw)": 2.1187493801116943, "Pretrain/Step": 2170, "Pretrain/Step Time": 8.878752183169127} +{"Pretrain/Learning Rate": 4.505035681466472e-05, "Pretrain/Loss": 2.102260112762451, "Pretrain/Loss (Raw)": 2.190882444381714, "Pretrain/Step": 2171, "Pretrain/Step Time": 8.88117159716785} +{"Pretrain/Learning Rate": 4.504528461605247e-05, "Pretrain/Loss": 2.1033473014831543, "Pretrain/Loss (Raw)": 1.9768649339675903, "Pretrain/Step": 2172, "Pretrain/Step Time": 8.88312066346407} +{"Pretrain/Learning Rate": 4.5040210105723525e-05, "Pretrain/Loss": 2.1023459434509277, "Pretrain/Loss (Raw)": 1.9306919574737549, "Pretrain/Step": 2173, "Pretrain/Step Time": 8.881062949076295} +{"Pretrain/Learning Rate": 4.5035133284263134e-05, "Pretrain/Loss": 2.1040992736816406, "Pretrain/Loss (Raw)": 2.1993789672851562, "Pretrain/Step": 2174, "Pretrain/Step Time": 8.883741673082113} +{"Pretrain/Learning Rate": 4.5030054152256756e-05, "Pretrain/Loss": 2.104236125946045, "Pretrain/Loss (Raw)": 2.1139421463012695, "Pretrain/Step": 2175, "Pretrain/Step Time": 8.887529876083136} +{"Pretrain/Learning Rate": 4.502497271029015e-05, "Pretrain/Loss": 2.103611946105957, "Pretrain/Loss (Raw)": 2.0962095260620117, "Pretrain/Step": 2176, "Pretrain/Step Time": 8.888332031667233} +{"Pretrain/Learning Rate": 4.501988895894933e-05, "Pretrain/Loss": 2.1041502952575684, "Pretrain/Loss (Raw)": 2.12176513671875, "Pretrain/Step": 2177, "Pretrain/Step Time": 8.891321549192071} +{"Pretrain/Learning Rate": 4.501480289882058e-05, "Pretrain/Loss": 2.1054623126983643, "Pretrain/Loss (Raw)": 2.294224739074707, "Pretrain/Step": 2178, "Pretrain/Step Time": 8.889388494193554} +{"Pretrain/Learning Rate": 4.5009714530490455e-05, "Pretrain/Loss": 2.107840061187744, "Pretrain/Loss (Raw)": 2.228445291519165, "Pretrain/Step": 2179, "Pretrain/Step Time": 8.885725259780884} +{"Pretrain/Learning Rate": 4.5004623854545746e-05, "Pretrain/Loss": 2.1072311401367188, "Pretrain/Loss (Raw)": 2.0999324321746826, "Pretrain/Step": 2180, "Pretrain/Step Time": 8.888048436492682} +{"Pretrain/Learning Rate": 4.4999530871573556e-05, "Pretrain/Loss": 2.1065216064453125, "Pretrain/Loss (Raw)": 2.0326435565948486, "Pretrain/Step": 2181, "Pretrain/Step Time": 8.901127759367228} +{"Pretrain/Learning Rate": 4.499443558216123e-05, "Pretrain/Loss": 2.106172561645508, "Pretrain/Loss (Raw)": 2.140882968902588, "Pretrain/Step": 2182, "Pretrain/Step Time": 8.891426166519523} +{"Pretrain/Learning Rate": 4.498933798689638e-05, "Pretrain/Loss": 2.1049070358276367, "Pretrain/Loss (Raw)": 2.204690456390381, "Pretrain/Step": 2183, "Pretrain/Step Time": 8.893428212031722} +{"Pretrain/Learning Rate": 4.498423808636687e-05, "Pretrain/Loss": 2.1050615310668945, "Pretrain/Loss (Raw)": 2.1759016513824463, "Pretrain/Step": 2184, "Pretrain/Step Time": 8.883433962240815} +{"Pretrain/Learning Rate": 4.497913588116085e-05, "Pretrain/Loss": 2.103614568710327, "Pretrain/Loss (Raw)": 1.8868122100830078, "Pretrain/Step": 2185, "Pretrain/Step Time": 8.888184897601604} +{"Pretrain/Learning Rate": 4.497403137186674e-05, "Pretrain/Loss": 2.102553129196167, "Pretrain/Loss (Raw)": 1.9328093528747559, "Pretrain/Step": 2186, "Pretrain/Step Time": 8.882283806800842} +{"Pretrain/Learning Rate": 4.496892455907322e-05, "Pretrain/Loss": 2.1034631729125977, "Pretrain/Loss (Raw)": 2.1545815467834473, "Pretrain/Step": 2187, "Pretrain/Step Time": 8.883808957412839} +{"Pretrain/Learning Rate": 4.496381544336922e-05, "Pretrain/Loss": 2.1029675006866455, "Pretrain/Loss (Raw)": 2.0015487670898438, "Pretrain/Step": 2188, "Pretrain/Step Time": 8.887131955474615} +{"Pretrain/Learning Rate": 4.495870402534394e-05, "Pretrain/Loss": 2.1040163040161133, "Pretrain/Loss (Raw)": 2.0674538612365723, "Pretrain/Step": 2189, "Pretrain/Step Time": 8.875295942649245} +{"Pretrain/Learning Rate": 4.495359030558688e-05, "Pretrain/Loss": 2.1053667068481445, "Pretrain/Loss (Raw)": 2.233515977859497, "Pretrain/Step": 2190, "Pretrain/Step Time": 8.87961409240961} +{"Pretrain/Learning Rate": 4.494847428468775e-05, "Pretrain/Loss": 2.1054282188415527, "Pretrain/Loss (Raw)": 2.117006540298462, "Pretrain/Step": 2191, "Pretrain/Step Time": 8.880122419446707} +{"Pretrain/Learning Rate": 4.494335596323657e-05, "Pretrain/Loss": 2.105107069015503, "Pretrain/Loss (Raw)": 2.1705915927886963, "Pretrain/Step": 2192, "Pretrain/Step Time": 8.88489480316639} +{"Pretrain/Learning Rate": 4.49382353418236e-05, "Pretrain/Loss": 2.1046671867370605, "Pretrain/Loss (Raw)": 2.1372172832489014, "Pretrain/Step": 2193, "Pretrain/Step Time": 8.881073247641325} +{"Pretrain/Learning Rate": 4.493311242103938e-05, "Pretrain/Loss": 2.106372356414795, "Pretrain/Loss (Raw)": 2.3002219200134277, "Pretrain/Step": 2194, "Pretrain/Step Time": 8.880299631506205} +{"Pretrain/Learning Rate": 4.4927987201474707e-05, "Pretrain/Loss": 2.104487419128418, "Pretrain/Loss (Raw)": 2.001511812210083, "Pretrain/Step": 2195, "Pretrain/Step Time": 8.889560416340828} +{"Pretrain/Learning Rate": 4.492285968372065e-05, "Pretrain/Loss": 2.102339506149292, "Pretrain/Loss (Raw)": 1.9536606073379517, "Pretrain/Step": 2196, "Pretrain/Step Time": 8.890972906723619} +{"Pretrain/Learning Rate": 4.491772986836853e-05, "Pretrain/Loss": 2.1009483337402344, "Pretrain/Loss (Raw)": 2.009796619415283, "Pretrain/Step": 2197, "Pretrain/Step Time": 8.887978684157133} +{"Pretrain/Learning Rate": 4.4912597756009946e-05, "Pretrain/Loss": 2.100691318511963, "Pretrain/Loss (Raw)": 2.2304296493530273, "Pretrain/Step": 2198, "Pretrain/Step Time": 8.878349587321281} +{"Pretrain/Learning Rate": 4.490746334723677e-05, "Pretrain/Loss": 2.0983128547668457, "Pretrain/Loss (Raw)": 1.979724407196045, "Pretrain/Step": 2199, "Pretrain/Step Time": 8.874860554933548} +{"Pretrain/Learning Rate": 4.4902326642641095e-05, "Pretrain/Loss": 2.0974860191345215, "Pretrain/Loss (Raw)": 1.9436562061309814, "Pretrain/Step": 2200, "Pretrain/Step Time": 8.87786410190165} +{"Pretrain/Learning Rate": 4.489718764281534e-05, "Pretrain/Loss": 2.098761796951294, "Pretrain/Loss (Raw)": 2.0259158611297607, "Pretrain/Step": 2201, "Pretrain/Step Time": 8.883696114644408} +{"Pretrain/Learning Rate": 4.489204634835215e-05, "Pretrain/Loss": 2.100015878677368, "Pretrain/Loss (Raw)": 2.08052396774292, "Pretrain/Step": 2202, "Pretrain/Step Time": 8.881144801154733} +{"Pretrain/Learning Rate": 4.488690275984443e-05, "Pretrain/Loss": 2.1006124019622803, "Pretrain/Loss (Raw)": 2.143246650695801, "Pretrain/Step": 2203, "Pretrain/Step Time": 8.888743825256824} +{"Pretrain/Learning Rate": 4.488175687788538e-05, "Pretrain/Loss": 2.0992813110351562, "Pretrain/Loss (Raw)": 1.8410663604736328, "Pretrain/Step": 2204, "Pretrain/Step Time": 8.877595784142613} +{"Pretrain/Learning Rate": 4.4876608703068434e-05, "Pretrain/Loss": 2.098661422729492, "Pretrain/Loss (Raw)": 2.0108282566070557, "Pretrain/Step": 2205, "Pretrain/Step Time": 8.879729889333248} +{"Pretrain/Learning Rate": 4.487145823598732e-05, "Pretrain/Loss": 2.0987839698791504, "Pretrain/Loss (Raw)": 2.0593655109405518, "Pretrain/Step": 2206, "Pretrain/Step Time": 8.8781567979604} +{"Pretrain/Learning Rate": 4.4866305477236e-05, "Pretrain/Loss": 2.0976810455322266, "Pretrain/Loss (Raw)": 1.9936283826828003, "Pretrain/Step": 2207, "Pretrain/Step Time": 8.870397325605154} +{"Pretrain/Learning Rate": 4.486115042740872e-05, "Pretrain/Loss": 2.096561908721924, "Pretrain/Loss (Raw)": 2.0615041255950928, "Pretrain/Step": 2208, "Pretrain/Step Time": 8.864347474649549} +{"Pretrain/Learning Rate": 4.4855993087099984e-05, "Pretrain/Loss": 2.095834255218506, "Pretrain/Loss (Raw)": 2.2581467628479004, "Pretrain/Step": 2209, "Pretrain/Step Time": 8.862603785470128} +{"Pretrain/Learning Rate": 4.485083345690456e-05, "Pretrain/Loss": 2.0940988063812256, "Pretrain/Loss (Raw)": 1.9782471656799316, "Pretrain/Step": 2210, "Pretrain/Step Time": 8.859386282041669} +{"Pretrain/Learning Rate": 4.4845671537417486e-05, "Pretrain/Loss": 2.094513177871704, "Pretrain/Loss (Raw)": 2.139338493347168, "Pretrain/Step": 2211, "Pretrain/Step Time": 8.870373751968145} +{"Pretrain/Learning Rate": 4.484050732923405e-05, "Pretrain/Loss": 2.0946195125579834, "Pretrain/Loss (Raw)": 2.0739078521728516, "Pretrain/Step": 2212, "Pretrain/Step Time": 8.868940202519298} +{"Pretrain/Learning Rate": 4.483534083294982e-05, "Pretrain/Loss": 2.0963845252990723, "Pretrain/Loss (Raw)": 2.295506477355957, "Pretrain/Step": 2213, "Pretrain/Step Time": 8.872951839119196} +{"Pretrain/Learning Rate": 4.483017204916061e-05, "Pretrain/Loss": 2.096932888031006, "Pretrain/Loss (Raw)": 2.233289957046509, "Pretrain/Step": 2214, "Pretrain/Step Time": 8.866443261504173} +{"Pretrain/Learning Rate": 4.482500097846253e-05, "Pretrain/Loss": 2.097686767578125, "Pretrain/Loss (Raw)": 2.315185546875, "Pretrain/Step": 2215, "Pretrain/Step Time": 8.86579461954534} +{"Pretrain/Learning Rate": 4.4819827621451906e-05, "Pretrain/Loss": 2.0962860584259033, "Pretrain/Loss (Raw)": 2.006988763809204, "Pretrain/Step": 2216, "Pretrain/Step Time": 8.866821613162756} +{"Pretrain/Learning Rate": 4.481465197872538e-05, "Pretrain/Loss": 2.0960593223571777, "Pretrain/Loss (Raw)": 2.043166160583496, "Pretrain/Step": 2217, "Pretrain/Step Time": 8.861949536949396} +{"Pretrain/Learning Rate": 4.4809474050879806e-05, "Pretrain/Loss": 2.09580135345459, "Pretrain/Loss (Raw)": 2.066086530685425, "Pretrain/Step": 2218, "Pretrain/Step Time": 8.860334038734436} +{"Pretrain/Learning Rate": 4.4804293838512346e-05, "Pretrain/Loss": 2.0956921577453613, "Pretrain/Loss (Raw)": 2.040837526321411, "Pretrain/Step": 2219, "Pretrain/Step Time": 8.868135254830122} +{"Pretrain/Learning Rate": 4.47991113422204e-05, "Pretrain/Loss": 2.0952625274658203, "Pretrain/Loss (Raw)": 2.0529730319976807, "Pretrain/Step": 2220, "Pretrain/Step Time": 8.864206766709685} +{"Pretrain/Learning Rate": 4.479392656260163e-05, "Pretrain/Loss": 2.0955119132995605, "Pretrain/Loss (Raw)": 2.203062057495117, "Pretrain/Step": 2221, "Pretrain/Step Time": 8.86946278065443} +{"Pretrain/Learning Rate": 4.4788739500253986e-05, "Pretrain/Loss": 2.093543529510498, "Pretrain/Loss (Raw)": 1.9296939373016357, "Pretrain/Step": 2222, "Pretrain/Step Time": 8.869212202727795} +{"Pretrain/Learning Rate": 4.4783550155775647e-05, "Pretrain/Loss": 2.0951671600341797, "Pretrain/Loss (Raw)": 2.1853229999542236, "Pretrain/Step": 2223, "Pretrain/Step Time": 8.874573292210698} +{"Pretrain/Learning Rate": 4.4778358529765085e-05, "Pretrain/Loss": 2.0972800254821777, "Pretrain/Loss (Raw)": 2.276407480239868, "Pretrain/Step": 2224, "Pretrain/Step Time": 8.868441237136722} +{"Pretrain/Learning Rate": 4.477316462282102e-05, "Pretrain/Loss": 2.0920164585113525, "Pretrain/Loss (Raw)": 1.8230125904083252, "Pretrain/Step": 2225, "Pretrain/Step Time": 8.86623683385551} +{"Pretrain/Learning Rate": 4.476796843554243e-05, "Pretrain/Loss": 2.0917091369628906, "Pretrain/Loss (Raw)": 2.1277785301208496, "Pretrain/Step": 2226, "Pretrain/Step Time": 8.863959029316902} +{"Pretrain/Learning Rate": 4.4762769968528575e-05, "Pretrain/Loss": 2.0930235385894775, "Pretrain/Loss (Raw)": 2.1990950107574463, "Pretrain/Step": 2227, "Pretrain/Step Time": 8.878066284582019} +{"Pretrain/Learning Rate": 4.475756922237896e-05, "Pretrain/Loss": 2.092952013015747, "Pretrain/Loss (Raw)": 2.1686747074127197, "Pretrain/Step": 2228, "Pretrain/Step Time": 8.87133015692234} +{"Pretrain/Learning Rate": 4.4752366197693365e-05, "Pretrain/Loss": 2.092082977294922, "Pretrain/Loss (Raw)": 2.0271222591400146, "Pretrain/Step": 2229, "Pretrain/Step Time": 8.871966829523444} +{"Pretrain/Learning Rate": 4.474716089507182e-05, "Pretrain/Loss": 2.09226393699646, "Pretrain/Loss (Raw)": 2.1332898139953613, "Pretrain/Step": 2230, "Pretrain/Step Time": 8.868431782349944} +{"Pretrain/Learning Rate": 4.474195331511464e-05, "Pretrain/Loss": 2.094467878341675, "Pretrain/Loss (Raw)": 1.999875783920288, "Pretrain/Step": 2231, "Pretrain/Step Time": 8.871213160455227} +{"Pretrain/Learning Rate": 4.473674345842236e-05, "Pretrain/Loss": 2.093864917755127, "Pretrain/Loss (Raw)": 1.9329465627670288, "Pretrain/Step": 2232, "Pretrain/Step Time": 8.8722786847502} +{"Pretrain/Learning Rate": 4.4731531325595835e-05, "Pretrain/Loss": 2.0970239639282227, "Pretrain/Loss (Raw)": 2.121363878250122, "Pretrain/Step": 2233, "Pretrain/Step Time": 8.869801349937916} +{"Pretrain/Learning Rate": 4.472631691723613e-05, "Pretrain/Loss": 2.0967957973480225, "Pretrain/Loss (Raw)": 2.0380871295928955, "Pretrain/Step": 2234, "Pretrain/Step Time": 8.87684154510498} +{"Pretrain/Learning Rate": 4.4721100233944606e-05, "Pretrain/Loss": 2.096285820007324, "Pretrain/Loss (Raw)": 2.158684492111206, "Pretrain/Step": 2235, "Pretrain/Step Time": 8.875691825523973} +{"Pretrain/Learning Rate": 4.471588127632288e-05, "Pretrain/Loss": 2.098928928375244, "Pretrain/Loss (Raw)": 2.233250617980957, "Pretrain/Step": 2236, "Pretrain/Step Time": 8.871875617653131} +{"Pretrain/Learning Rate": 4.471066004497282e-05, "Pretrain/Loss": 2.0985798835754395, "Pretrain/Loss (Raw)": 2.0866143703460693, "Pretrain/Step": 2237, "Pretrain/Step Time": 8.879032069817185} +{"Pretrain/Learning Rate": 4.470543654049656e-05, "Pretrain/Loss": 2.0981850624084473, "Pretrain/Loss (Raw)": 2.0581870079040527, "Pretrain/Step": 2238, "Pretrain/Step Time": 8.88370162434876} +{"Pretrain/Learning Rate": 4.47002107634965e-05, "Pretrain/Loss": 2.097024440765381, "Pretrain/Loss (Raw)": 1.8966399431228638, "Pretrain/Step": 2239, "Pretrain/Step Time": 8.883925527334213} +{"Pretrain/Learning Rate": 4.469498271457531e-05, "Pretrain/Loss": 2.0985918045043945, "Pretrain/Loss (Raw)": 2.2042739391326904, "Pretrain/Step": 2240, "Pretrain/Step Time": 8.883281994611025} +{"Pretrain/Learning Rate": 4.468975239433591e-05, "Pretrain/Loss": 2.095525026321411, "Pretrain/Loss (Raw)": 2.175309419631958, "Pretrain/Step": 2241, "Pretrain/Step Time": 8.884334295988083} +{"Pretrain/Learning Rate": 4.468451980338148e-05, "Pretrain/Loss": 2.094581127166748, "Pretrain/Loss (Raw)": 2.032274007797241, "Pretrain/Step": 2242, "Pretrain/Step Time": 8.889768300577998} +{"Pretrain/Learning Rate": 4.467928494231547e-05, "Pretrain/Loss": 2.0971274375915527, "Pretrain/Loss (Raw)": 2.2195827960968018, "Pretrain/Step": 2243, "Pretrain/Step Time": 8.87888683192432} +{"Pretrain/Learning Rate": 4.4674047811741585e-05, "Pretrain/Loss": 2.0944602489471436, "Pretrain/Loss (Raw)": 1.9411412477493286, "Pretrain/Step": 2244, "Pretrain/Step Time": 8.886420091614127} +{"Pretrain/Learning Rate": 4.466880841226381e-05, "Pretrain/Loss": 2.0957844257354736, "Pretrain/Loss (Raw)": 2.1531052589416504, "Pretrain/Step": 2245, "Pretrain/Step Time": 8.882144447416067} +{"Pretrain/Learning Rate": 4.466356674448635e-05, "Pretrain/Loss": 2.094540596008301, "Pretrain/Loss (Raw)": 2.0509088039398193, "Pretrain/Step": 2246, "Pretrain/Step Time": 8.883960861712694} +{"Pretrain/Learning Rate": 4.4658322809013723e-05, "Pretrain/Loss": 2.0944643020629883, "Pretrain/Loss (Raw)": 1.9055736064910889, "Pretrain/Step": 2247, "Pretrain/Step Time": 8.888548785820603} +{"Pretrain/Learning Rate": 4.465307660645068e-05, "Pretrain/Loss": 2.0940818786621094, "Pretrain/Loss (Raw)": 1.9855244159698486, "Pretrain/Step": 2248, "Pretrain/Step Time": 8.888408923521638} +{"Pretrain/Learning Rate": 4.464782813740223e-05, "Pretrain/Loss": 2.0919244289398193, "Pretrain/Loss (Raw)": 1.921217441558838, "Pretrain/Step": 2249, "Pretrain/Step Time": 8.884280426427722} +{"Pretrain/Learning Rate": 4.464257740247366e-05, "Pretrain/Loss": 2.0933704376220703, "Pretrain/Loss (Raw)": 2.0636849403381348, "Pretrain/Step": 2250, "Pretrain/Step Time": 8.892239643260837} +{"Pretrain/Learning Rate": 4.4637324402270495e-05, "Pretrain/Loss": 2.0933008193969727, "Pretrain/Loss (Raw)": 2.137573480606079, "Pretrain/Step": 2251, "Pretrain/Step Time": 8.891030825674534} +{"Pretrain/Learning Rate": 4.463206913739856e-05, "Pretrain/Loss": 2.0928525924682617, "Pretrain/Loss (Raw)": 1.9356226921081543, "Pretrain/Step": 2252, "Pretrain/Step Time": 8.899206778034568} +{"Pretrain/Learning Rate": 4.462681160846389e-05, "Pretrain/Loss": 2.0916905403137207, "Pretrain/Loss (Raw)": 2.072911024093628, "Pretrain/Step": 2253, "Pretrain/Step Time": 8.895797234028578} +{"Pretrain/Learning Rate": 4.4621551816072835e-05, "Pretrain/Loss": 2.0923283100128174, "Pretrain/Loss (Raw)": 2.119462490081787, "Pretrain/Step": 2254, "Pretrain/Step Time": 8.899624576792121} +{"Pretrain/Learning Rate": 4.4616289760831954e-05, "Pretrain/Loss": 2.091174602508545, "Pretrain/Loss (Raw)": 2.07450532913208, "Pretrain/Step": 2255, "Pretrain/Step Time": 8.899126462638378} +{"Pretrain/Learning Rate": 4.46110254433481e-05, "Pretrain/Loss": 2.091279983520508, "Pretrain/Loss (Raw)": 2.095424175262451, "Pretrain/Step": 2256, "Pretrain/Step Time": 8.896199194714427} +{"Pretrain/Learning Rate": 4.4605758864228384e-05, "Pretrain/Loss": 2.0904276371002197, "Pretrain/Loss (Raw)": 1.9437956809997559, "Pretrain/Step": 2257, "Pretrain/Step Time": 8.895991140976548} +{"Pretrain/Learning Rate": 4.460049002408018e-05, "Pretrain/Loss": 2.08990740776062, "Pretrain/Loss (Raw)": 2.1621925830841064, "Pretrain/Step": 2258, "Pretrain/Step Time": 8.886855721473694} +{"Pretrain/Learning Rate": 4.45952189235111e-05, "Pretrain/Loss": 2.088789939880371, "Pretrain/Loss (Raw)": 2.1863605976104736, "Pretrain/Step": 2259, "Pretrain/Step Time": 8.888700559735298} +{"Pretrain/Learning Rate": 4.458994556312903e-05, "Pretrain/Loss": 2.0883936882019043, "Pretrain/Loss (Raw)": 2.084495782852173, "Pretrain/Step": 2260, "Pretrain/Step Time": 8.885997489094734} +{"Pretrain/Learning Rate": 4.458466994354214e-05, "Pretrain/Loss": 2.0901782512664795, "Pretrain/Loss (Raw)": 2.2383766174316406, "Pretrain/Step": 2261, "Pretrain/Step Time": 8.883045453578234} +{"Pretrain/Learning Rate": 4.457939206535882e-05, "Pretrain/Loss": 2.0915656089782715, "Pretrain/Loss (Raw)": 2.350295305252075, "Pretrain/Step": 2262, "Pretrain/Step Time": 8.886769741773605} +{"Pretrain/Learning Rate": 4.4574111929187744e-05, "Pretrain/Loss": 2.0897796154022217, "Pretrain/Loss (Raw)": 1.968212604522705, "Pretrain/Step": 2263, "Pretrain/Step Time": 8.885553503409028} +{"Pretrain/Learning Rate": 4.4568829535637844e-05, "Pretrain/Loss": 2.0901107788085938, "Pretrain/Loss (Raw)": 1.961394190788269, "Pretrain/Step": 2264, "Pretrain/Step Time": 8.884718976914883} +{"Pretrain/Learning Rate": 4.456354488531832e-05, "Pretrain/Loss": 2.089045286178589, "Pretrain/Loss (Raw)": 1.9551255702972412, "Pretrain/Step": 2265, "Pretrain/Step Time": 8.891065092757344} +{"Pretrain/Learning Rate": 4.4558257978838605e-05, "Pretrain/Loss": 2.0882880687713623, "Pretrain/Loss (Raw)": 2.210890769958496, "Pretrain/Step": 2266, "Pretrain/Step Time": 8.889718916267157} +{"Pretrain/Learning Rate": 4.455296881680842e-05, "Pretrain/Loss": 2.089447021484375, "Pretrain/Loss (Raw)": 2.3237383365631104, "Pretrain/Step": 2267, "Pretrain/Step Time": 8.890506768599153} +{"Pretrain/Learning Rate": 4.4547677399837726e-05, "Pretrain/Loss": 2.0885870456695557, "Pretrain/Loss (Raw)": 2.0673861503601074, "Pretrain/Step": 2268, "Pretrain/Step Time": 8.890498645603657} +{"Pretrain/Learning Rate": 4.4542383728536774e-05, "Pretrain/Loss": 2.0905075073242188, "Pretrain/Loss (Raw)": 2.043733596801758, "Pretrain/Step": 2269, "Pretrain/Step Time": 8.887899797409773} +{"Pretrain/Learning Rate": 4.453708780351604e-05, "Pretrain/Loss": 2.089731216430664, "Pretrain/Loss (Raw)": 2.051361083984375, "Pretrain/Step": 2270, "Pretrain/Step Time": 8.889616200700402} +{"Pretrain/Learning Rate": 4.4531789625386274e-05, "Pretrain/Loss": 2.091090202331543, "Pretrain/Loss (Raw)": 2.215759754180908, "Pretrain/Step": 2271, "Pretrain/Step Time": 8.874303180724382} +{"Pretrain/Learning Rate": 4.45264891947585e-05, "Pretrain/Loss": 2.0884687900543213, "Pretrain/Loss (Raw)": 1.8720334768295288, "Pretrain/Step": 2272, "Pretrain/Step Time": 8.872883163392544} +{"Pretrain/Learning Rate": 4.452118651224398e-05, "Pretrain/Loss": 2.0893914699554443, "Pretrain/Loss (Raw)": 2.024472713470459, "Pretrain/Step": 2273, "Pretrain/Step Time": 8.874377464875579} +{"Pretrain/Learning Rate": 4.451588157845424e-05, "Pretrain/Loss": 2.0910916328430176, "Pretrain/Loss (Raw)": 2.1192965507507324, "Pretrain/Step": 2274, "Pretrain/Step Time": 8.875864768400788} +{"Pretrain/Learning Rate": 4.451057439400108e-05, "Pretrain/Loss": 2.0889296531677246, "Pretrain/Loss (Raw)": 1.8676834106445312, "Pretrain/Step": 2275, "Pretrain/Step Time": 8.878953101113439} +{"Pretrain/Learning Rate": 4.450526495949653e-05, "Pretrain/Loss": 2.0867059230804443, "Pretrain/Loss (Raw)": 1.8817685842514038, "Pretrain/Step": 2276, "Pretrain/Step Time": 8.876316454261541} +{"Pretrain/Learning Rate": 4.449995327555293e-05, "Pretrain/Loss": 2.0848166942596436, "Pretrain/Loss (Raw)": 1.857099175453186, "Pretrain/Step": 2277, "Pretrain/Step Time": 8.867711409926414} +{"Pretrain/Learning Rate": 4.449463934278282e-05, "Pretrain/Loss": 2.084526538848877, "Pretrain/Loss (Raw)": 2.066840171813965, "Pretrain/Step": 2278, "Pretrain/Step Time": 8.875906474888325} +{"Pretrain/Learning Rate": 4.4489323161799045e-05, "Pretrain/Loss": 2.083432674407959, "Pretrain/Loss (Raw)": 1.988381266593933, "Pretrain/Step": 2279, "Pretrain/Step Time": 8.878783460706472} +{"Pretrain/Learning Rate": 4.4484004733214685e-05, "Pretrain/Loss": 2.082730531692505, "Pretrain/Loss (Raw)": 2.145655393600464, "Pretrain/Step": 2280, "Pretrain/Step Time": 8.87215188331902} +{"Pretrain/Learning Rate": 4.447868405764309e-05, "Pretrain/Loss": 2.0843780040740967, "Pretrain/Loss (Raw)": 2.266084671020508, "Pretrain/Step": 2281, "Pretrain/Step Time": 8.866994690150023} +{"Pretrain/Learning Rate": 4.4473361135697856e-05, "Pretrain/Loss": 2.0841784477233887, "Pretrain/Loss (Raw)": 2.1717207431793213, "Pretrain/Step": 2282, "Pretrain/Step Time": 8.868734985589981} +{"Pretrain/Learning Rate": 4.446803596799286e-05, "Pretrain/Loss": 2.084481716156006, "Pretrain/Loss (Raw)": 2.083878993988037, "Pretrain/Step": 2283, "Pretrain/Step Time": 8.870082760229707} +{"Pretrain/Learning Rate": 4.446270855514222e-05, "Pretrain/Loss": 2.083601951599121, "Pretrain/Loss (Raw)": 1.959716796875, "Pretrain/Step": 2284, "Pretrain/Step Time": 8.869325991719961} +{"Pretrain/Learning Rate": 4.445737889776031e-05, "Pretrain/Loss": 2.0855798721313477, "Pretrain/Loss (Raw)": 2.2056760787963867, "Pretrain/Step": 2285, "Pretrain/Step Time": 8.865025417879224} +{"Pretrain/Learning Rate": 4.44520469964618e-05, "Pretrain/Loss": 2.085891008377075, "Pretrain/Loss (Raw)": 2.0790698528289795, "Pretrain/Step": 2286, "Pretrain/Step Time": 8.869308020919561} +{"Pretrain/Learning Rate": 4.444671285186155e-05, "Pretrain/Loss": 2.0856103897094727, "Pretrain/Loss (Raw)": 2.2184042930603027, "Pretrain/Step": 2287, "Pretrain/Step Time": 8.870201090350747} +{"Pretrain/Learning Rate": 4.444137646457474e-05, "Pretrain/Loss": 2.085322141647339, "Pretrain/Loss (Raw)": 2.1209990978240967, "Pretrain/Step": 2288, "Pretrain/Step Time": 8.865495817735791} +{"Pretrain/Learning Rate": 4.4436037835216784e-05, "Pretrain/Loss": 2.0861339569091797, "Pretrain/Loss (Raw)": 2.0971243381500244, "Pretrain/Step": 2289, "Pretrain/Step Time": 8.866212792694569} +{"Pretrain/Learning Rate": 4.4430696964403366e-05, "Pretrain/Loss": 2.0850353240966797, "Pretrain/Loss (Raw)": 1.9591820240020752, "Pretrain/Step": 2290, "Pretrain/Step Time": 8.867177503183484} +{"Pretrain/Learning Rate": 4.4425353852750414e-05, "Pretrain/Loss": 2.087164878845215, "Pretrain/Loss (Raw)": 2.2643492221832275, "Pretrain/Step": 2291, "Pretrain/Step Time": 8.862524101510644} +{"Pretrain/Learning Rate": 4.4420008500874116e-05, "Pretrain/Loss": 2.0882766246795654, "Pretrain/Loss (Raw)": 2.2702620029449463, "Pretrain/Step": 2292, "Pretrain/Step Time": 8.862707242369652} +{"Pretrain/Learning Rate": 4.441466090939093e-05, "Pretrain/Loss": 2.0885705947875977, "Pretrain/Loss (Raw)": 2.0796444416046143, "Pretrain/Step": 2293, "Pretrain/Step Time": 8.863805655390024} +{"Pretrain/Learning Rate": 4.440931107891756e-05, "Pretrain/Loss": 2.0886406898498535, "Pretrain/Loss (Raw)": 2.1261239051818848, "Pretrain/Step": 2294, "Pretrain/Step Time": 8.8700255099684} +{"Pretrain/Learning Rate": 4.440395901007098e-05, "Pretrain/Loss": 2.089339256286621, "Pretrain/Loss (Raw)": 2.1480884552001953, "Pretrain/Step": 2295, "Pretrain/Step Time": 8.867603804916143} +{"Pretrain/Learning Rate": 4.4398604703468415e-05, "Pretrain/Loss": 2.088285207748413, "Pretrain/Loss (Raw)": 2.051643133163452, "Pretrain/Step": 2296, "Pretrain/Step Time": 8.87118330784142} +{"Pretrain/Learning Rate": 4.439324815972734e-05, "Pretrain/Loss": 2.0888025760650635, "Pretrain/Loss (Raw)": 2.225722312927246, "Pretrain/Step": 2297, "Pretrain/Step Time": 8.869680568575859} +{"Pretrain/Learning Rate": 4.438788937946551e-05, "Pretrain/Loss": 2.087855815887451, "Pretrain/Loss (Raw)": 1.9975780248641968, "Pretrain/Step": 2298, "Pretrain/Step Time": 8.87439813837409} +{"Pretrain/Learning Rate": 4.4382528363300916e-05, "Pretrain/Loss": 2.088623046875, "Pretrain/Loss (Raw)": 2.2890589237213135, "Pretrain/Step": 2299, "Pretrain/Step Time": 8.870818389579654} +{"Pretrain/Learning Rate": 4.437716511185181e-05, "Pretrain/Loss": 2.088672161102295, "Pretrain/Loss (Raw)": 1.9831643104553223, "Pretrain/Step": 2300, "Pretrain/Step Time": 8.872237470000982} +{"Pretrain/Learning Rate": 4.437179962573672e-05, "Pretrain/Loss": 2.090303897857666, "Pretrain/Loss (Raw)": 2.1395437717437744, "Pretrain/Step": 2301, "Pretrain/Step Time": 8.868187161162496} +{"Pretrain/Learning Rate": 4.436643190557441e-05, "Pretrain/Loss": 2.0892603397369385, "Pretrain/Loss (Raw)": 2.065805435180664, "Pretrain/Step": 2302, "Pretrain/Step Time": 8.86849725060165} +{"Pretrain/Learning Rate": 4.4361061951983925e-05, "Pretrain/Loss": 2.0881049633026123, "Pretrain/Loss (Raw)": 1.966042399406433, "Pretrain/Step": 2303, "Pretrain/Step Time": 8.867088882252574} +{"Pretrain/Learning Rate": 4.435568976558454e-05, "Pretrain/Loss": 2.0877418518066406, "Pretrain/Loss (Raw)": 2.049726963043213, "Pretrain/Step": 2304, "Pretrain/Step Time": 8.869771925732493} +{"Pretrain/Learning Rate": 4.4350315346995804e-05, "Pretrain/Loss": 2.0882461071014404, "Pretrain/Loss (Raw)": 2.186321973800659, "Pretrain/Step": 2305, "Pretrain/Step Time": 8.869744477793574} +{"Pretrain/Learning Rate": 4.434493869683752e-05, "Pretrain/Loss": 2.085681915283203, "Pretrain/Loss (Raw)": 1.9660176038742065, "Pretrain/Step": 2306, "Pretrain/Step Time": 8.870857454836369} +{"Pretrain/Learning Rate": 4.4339559815729746e-05, "Pretrain/Loss": 2.083909749984741, "Pretrain/Loss (Raw)": 2.0016019344329834, "Pretrain/Step": 2307, "Pretrain/Step Time": 8.8746467679739} +{"Pretrain/Learning Rate": 4.4334178704292805e-05, "Pretrain/Loss": 2.084000587463379, "Pretrain/Loss (Raw)": 2.1115713119506836, "Pretrain/Step": 2308, "Pretrain/Step Time": 8.871215166524053} +{"Pretrain/Learning Rate": 4.432879536314727e-05, "Pretrain/Loss": 2.085036277770996, "Pretrain/Loss (Raw)": 2.1652276515960693, "Pretrain/Step": 2309, "Pretrain/Step Time": 8.858161676675081} +{"Pretrain/Learning Rate": 4.4323409792913974e-05, "Pretrain/Loss": 2.085149049758911, "Pretrain/Loss (Raw)": 2.1552860736846924, "Pretrain/Step": 2310, "Pretrain/Step Time": 8.866279816254973} +{"Pretrain/Learning Rate": 4.431802199421401e-05, "Pretrain/Loss": 2.082597494125366, "Pretrain/Loss (Raw)": 1.878085732460022, "Pretrain/Step": 2311, "Pretrain/Step Time": 8.871246302500367} +{"Pretrain/Learning Rate": 4.431263196766872e-05, "Pretrain/Loss": 2.082671642303467, "Pretrain/Loss (Raw)": 2.1853952407836914, "Pretrain/Step": 2312, "Pretrain/Step Time": 8.877359539270401} +{"Pretrain/Learning Rate": 4.43072397138997e-05, "Pretrain/Loss": 2.084033489227295, "Pretrain/Loss (Raw)": 2.061150312423706, "Pretrain/Step": 2313, "Pretrain/Step Time": 8.869458481669426} +{"Pretrain/Learning Rate": 4.430184523352881e-05, "Pretrain/Loss": 2.0854244232177734, "Pretrain/Loss (Raw)": 2.1108551025390625, "Pretrain/Step": 2314, "Pretrain/Step Time": 8.87340778671205} +{"Pretrain/Learning Rate": 4.429644852717819e-05, "Pretrain/Loss": 2.0857656002044678, "Pretrain/Loss (Raw)": 2.1982316970825195, "Pretrain/Step": 2315, "Pretrain/Step Time": 8.875228805467486} +{"Pretrain/Learning Rate": 4.4291049595470193e-05, "Pretrain/Loss": 2.0868725776672363, "Pretrain/Loss (Raw)": 2.143249273300171, "Pretrain/Step": 2316, "Pretrain/Step Time": 8.871182776987553} +{"Pretrain/Learning Rate": 4.428564843902746e-05, "Pretrain/Loss": 2.086826801300049, "Pretrain/Loss (Raw)": 2.061607599258423, "Pretrain/Step": 2317, "Pretrain/Step Time": 8.879623340442777} +{"Pretrain/Learning Rate": 4.4280245058472866e-05, "Pretrain/Loss": 2.083065986633301, "Pretrain/Loss (Raw)": 1.7521244287490845, "Pretrain/Step": 2318, "Pretrain/Step Time": 8.874762831255794} +{"Pretrain/Learning Rate": 4.427483945442956e-05, "Pretrain/Loss": 2.084083318710327, "Pretrain/Loss (Raw)": 2.247208595275879, "Pretrain/Step": 2319, "Pretrain/Step Time": 8.877226075157523} +{"Pretrain/Learning Rate": 4.426943162752094e-05, "Pretrain/Loss": 2.0827901363372803, "Pretrain/Loss (Raw)": 2.005070686340332, "Pretrain/Step": 2320, "Pretrain/Step Time": 8.874867394566536} +{"Pretrain/Learning Rate": 4.426402157837067e-05, "Pretrain/Loss": 2.0824246406555176, "Pretrain/Loss (Raw)": 2.0904524326324463, "Pretrain/Step": 2321, "Pretrain/Step Time": 8.876492073759437} +{"Pretrain/Learning Rate": 4.425860930760265e-05, "Pretrain/Loss": 2.080988883972168, "Pretrain/Loss (Raw)": 2.116443395614624, "Pretrain/Step": 2322, "Pretrain/Step Time": 8.876478139311075} +{"Pretrain/Learning Rate": 4.4253194815841056e-05, "Pretrain/Loss": 2.0809831619262695, "Pretrain/Loss (Raw)": 2.000760316848755, "Pretrain/Step": 2323, "Pretrain/Step Time": 8.867318643257022} +{"Pretrain/Learning Rate": 4.424777810371032e-05, "Pretrain/Loss": 2.08248233795166, "Pretrain/Loss (Raw)": 2.1455585956573486, "Pretrain/Step": 2324, "Pretrain/Step Time": 8.872265879064798} +{"Pretrain/Learning Rate": 4.424235917183511e-05, "Pretrain/Loss": 2.0818257331848145, "Pretrain/Loss (Raw)": 1.925754427909851, "Pretrain/Step": 2325, "Pretrain/Step Time": 8.880107369273901} +{"Pretrain/Learning Rate": 4.4236938020840365e-05, "Pretrain/Loss": 2.081225633621216, "Pretrain/Loss (Raw)": 2.15362811088562, "Pretrain/Step": 2326, "Pretrain/Step Time": 8.880773233249784} +{"Pretrain/Learning Rate": 4.423151465135128e-05, "Pretrain/Loss": 2.0826539993286133, "Pretrain/Loss (Raw)": 2.1625468730926514, "Pretrain/Step": 2327, "Pretrain/Step Time": 8.879084864631295} +{"Pretrain/Learning Rate": 4.422608906399331e-05, "Pretrain/Loss": 2.0831727981567383, "Pretrain/Loss (Raw)": 2.0100760459899902, "Pretrain/Step": 2328, "Pretrain/Step Time": 8.88154454343021} +{"Pretrain/Learning Rate": 4.4220661259392146e-05, "Pretrain/Loss": 2.083771228790283, "Pretrain/Loss (Raw)": 2.1025028228759766, "Pretrain/Step": 2329, "Pretrain/Step Time": 8.877294771373272} +{"Pretrain/Learning Rate": 4.421523123817376e-05, "Pretrain/Loss": 2.0842719078063965, "Pretrain/Loss (Raw)": 2.1445975303649902, "Pretrain/Step": 2330, "Pretrain/Step Time": 8.877229686826468} +{"Pretrain/Learning Rate": 4.420979900096436e-05, "Pretrain/Loss": 2.0848634243011475, "Pretrain/Loss (Raw)": 2.2189579010009766, "Pretrain/Step": 2331, "Pretrain/Step Time": 8.881047932431102} +{"Pretrain/Learning Rate": 4.420436454839041e-05, "Pretrain/Loss": 2.0861144065856934, "Pretrain/Loss (Raw)": 2.0012223720550537, "Pretrain/Step": 2332, "Pretrain/Step Time": 8.883670702576637} +{"Pretrain/Learning Rate": 4.419892788107865e-05, "Pretrain/Loss": 2.0853800773620605, "Pretrain/Loss (Raw)": 1.9167840480804443, "Pretrain/Step": 2333, "Pretrain/Step Time": 8.882150448858738} +{"Pretrain/Learning Rate": 4.419348899965608e-05, "Pretrain/Loss": 2.086829900741577, "Pretrain/Loss (Raw)": 2.2449774742126465, "Pretrain/Step": 2334, "Pretrain/Step Time": 8.884559832513332} +{"Pretrain/Learning Rate": 4.4188047904749894e-05, "Pretrain/Loss": 2.0875210762023926, "Pretrain/Loss (Raw)": 2.08209228515625, "Pretrain/Step": 2335, "Pretrain/Step Time": 8.879851264879107} +{"Pretrain/Learning Rate": 4.418260459698761e-05, "Pretrain/Loss": 2.0870285034179688, "Pretrain/Loss (Raw)": 1.9984359741210938, "Pretrain/Step": 2336, "Pretrain/Step Time": 8.883768945932388} +{"Pretrain/Learning Rate": 4.417715907699698e-05, "Pretrain/Loss": 2.0854454040527344, "Pretrain/Loss (Raw)": 2.0555243492126465, "Pretrain/Step": 2337, "Pretrain/Step Time": 8.88297200948} +{"Pretrain/Learning Rate": 4.417171134540599e-05, "Pretrain/Loss": 2.085737705230713, "Pretrain/Loss (Raw)": 2.0156755447387695, "Pretrain/Step": 2338, "Pretrain/Step Time": 8.886792588979006} +{"Pretrain/Learning Rate": 4.416626140284291e-05, "Pretrain/Loss": 2.0856919288635254, "Pretrain/Loss (Raw)": 2.133450746536255, "Pretrain/Step": 2339, "Pretrain/Step Time": 8.880415888503194} +{"Pretrain/Learning Rate": 4.416080924993625e-05, "Pretrain/Loss": 2.0856199264526367, "Pretrain/Loss (Raw)": 2.064703941345215, "Pretrain/Step": 2340, "Pretrain/Step Time": 8.8859319165349} +{"Pretrain/Learning Rate": 4.415535488731478e-05, "Pretrain/Loss": 2.0841193199157715, "Pretrain/Loss (Raw)": 2.103424072265625, "Pretrain/Step": 2341, "Pretrain/Step Time": 8.882907465100288} +{"Pretrain/Learning Rate": 4.414989831560753e-05, "Pretrain/Loss": 2.084542989730835, "Pretrain/Loss (Raw)": 2.2875499725341797, "Pretrain/Step": 2342, "Pretrain/Step Time": 8.88201160915196} +{"Pretrain/Learning Rate": 4.4144439535443763e-05, "Pretrain/Loss": 2.0817227363586426, "Pretrain/Loss (Raw)": 1.9541715383529663, "Pretrain/Step": 2343, "Pretrain/Step Time": 8.880607713013887} +{"Pretrain/Learning Rate": 4.413897854745301e-05, "Pretrain/Loss": 2.081028699874878, "Pretrain/Loss (Raw)": 1.9181667566299438, "Pretrain/Step": 2344, "Pretrain/Step Time": 8.881547957658768} +{"Pretrain/Learning Rate": 4.413351535226507e-05, "Pretrain/Loss": 2.0815157890319824, "Pretrain/Loss (Raw)": 2.105489730834961, "Pretrain/Step": 2345, "Pretrain/Step Time": 8.88563534989953} +{"Pretrain/Learning Rate": 4.4128049950509984e-05, "Pretrain/Loss": 2.082101345062256, "Pretrain/Loss (Raw)": 2.1410744190216064, "Pretrain/Step": 2346, "Pretrain/Step Time": 8.88670265674591} +{"Pretrain/Learning Rate": 4.412258234281804e-05, "Pretrain/Loss": 2.0811712741851807, "Pretrain/Loss (Raw)": 1.9217565059661865, "Pretrain/Step": 2347, "Pretrain/Step Time": 8.888944257050753} +{"Pretrain/Learning Rate": 4.411711252981979e-05, "Pretrain/Loss": 2.081826686859131, "Pretrain/Loss (Raw)": 2.136869192123413, "Pretrain/Step": 2348, "Pretrain/Step Time": 8.885980412364006} +{"Pretrain/Learning Rate": 4.411164051214603e-05, "Pretrain/Loss": 2.080451726913452, "Pretrain/Loss (Raw)": 2.027064561843872, "Pretrain/Step": 2349, "Pretrain/Step Time": 8.880415227264166} +{"Pretrain/Learning Rate": 4.4106166290427846e-05, "Pretrain/Loss": 2.081160306930542, "Pretrain/Loss (Raw)": 2.0203895568847656, "Pretrain/Step": 2350, "Pretrain/Step Time": 8.879754131659865} +{"Pretrain/Learning Rate": 4.410068986529653e-05, "Pretrain/Loss": 2.0808281898498535, "Pretrain/Loss (Raw)": 2.142819881439209, "Pretrain/Step": 2351, "Pretrain/Step Time": 8.874751603230834} +{"Pretrain/Learning Rate": 4.409521123738365e-05, "Pretrain/Loss": 2.080390453338623, "Pretrain/Loss (Raw)": 2.220362663269043, "Pretrain/Step": 2352, "Pretrain/Step Time": 8.872929131612182} +{"Pretrain/Learning Rate": 4.4089730407321035e-05, "Pretrain/Loss": 2.083239793777466, "Pretrain/Loss (Raw)": 2.187746524810791, "Pretrain/Step": 2353, "Pretrain/Step Time": 8.872875111177564} +{"Pretrain/Learning Rate": 4.408424737574075e-05, "Pretrain/Loss": 2.0826215744018555, "Pretrain/Loss (Raw)": 2.0486648082733154, "Pretrain/Step": 2354, "Pretrain/Step Time": 8.88418723642826} +{"Pretrain/Learning Rate": 4.407876214327513e-05, "Pretrain/Loss": 2.081786632537842, "Pretrain/Loss (Raw)": 2.092210531234741, "Pretrain/Step": 2355, "Pretrain/Step Time": 8.87211480922997} +{"Pretrain/Learning Rate": 4.407327471055677e-05, "Pretrain/Loss": 2.0818753242492676, "Pretrain/Loss (Raw)": 2.180032730102539, "Pretrain/Step": 2356, "Pretrain/Step Time": 8.875501982867718} +{"Pretrain/Learning Rate": 4.406778507821848e-05, "Pretrain/Loss": 2.082226037979126, "Pretrain/Loss (Raw)": 2.0719940662384033, "Pretrain/Step": 2357, "Pretrain/Step Time": 8.871754493564367} +{"Pretrain/Learning Rate": 4.4062293246893374e-05, "Pretrain/Loss": 2.080981969833374, "Pretrain/Loss (Raw)": 1.9740569591522217, "Pretrain/Step": 2358, "Pretrain/Step Time": 8.87147862277925} +{"Pretrain/Learning Rate": 4.4056799217214774e-05, "Pretrain/Loss": 2.079866886138916, "Pretrain/Loss (Raw)": 1.8571667671203613, "Pretrain/Step": 2359, "Pretrain/Step Time": 8.863175220787525} +{"Pretrain/Learning Rate": 4.4051302989816304e-05, "Pretrain/Loss": 2.081662654876709, "Pretrain/Loss (Raw)": 2.162804365158081, "Pretrain/Step": 2360, "Pretrain/Step Time": 8.861571913585067} +{"Pretrain/Learning Rate": 4.404580456533179e-05, "Pretrain/Loss": 2.079709053039551, "Pretrain/Loss (Raw)": 1.8712786436080933, "Pretrain/Step": 2361, "Pretrain/Step Time": 8.875449100509286} +{"Pretrain/Learning Rate": 4.404030394439535e-05, "Pretrain/Loss": 2.080116033554077, "Pretrain/Loss (Raw)": 2.090195894241333, "Pretrain/Step": 2362, "Pretrain/Step Time": 8.866279359906912} +{"Pretrain/Learning Rate": 4.4034801127641336e-05, "Pretrain/Loss": 2.0785460472106934, "Pretrain/Loss (Raw)": 1.9577105045318604, "Pretrain/Step": 2363, "Pretrain/Step Time": 8.871720110997558} +{"Pretrain/Learning Rate": 4.4029296115704366e-05, "Pretrain/Loss": 2.0778050422668457, "Pretrain/Loss (Raw)": 2.1384031772613525, "Pretrain/Step": 2364, "Pretrain/Step Time": 8.867579696699977} +{"Pretrain/Learning Rate": 4.40237889092193e-05, "Pretrain/Loss": 2.0792317390441895, "Pretrain/Loss (Raw)": 2.269230842590332, "Pretrain/Step": 2365, "Pretrain/Step Time": 8.86137891560793} +{"Pretrain/Learning Rate": 4.401827950882125e-05, "Pretrain/Loss": 2.080538749694824, "Pretrain/Loss (Raw)": 2.225468397140503, "Pretrain/Step": 2366, "Pretrain/Step Time": 8.856306990608573} +{"Pretrain/Learning Rate": 4.4012767915145594e-05, "Pretrain/Loss": 2.0821807384490967, "Pretrain/Loss (Raw)": 2.1068270206451416, "Pretrain/Step": 2367, "Pretrain/Step Time": 8.859457537531853} +{"Pretrain/Learning Rate": 4.400725412882794e-05, "Pretrain/Loss": 2.082073926925659, "Pretrain/Loss (Raw)": 2.190610647201538, "Pretrain/Step": 2368, "Pretrain/Step Time": 8.863465650007129} +{"Pretrain/Learning Rate": 4.400173815050418e-05, "Pretrain/Loss": 2.0809669494628906, "Pretrain/Loss (Raw)": 2.0336225032806396, "Pretrain/Step": 2369, "Pretrain/Step Time": 8.87037610821426} +{"Pretrain/Learning Rate": 4.399621998081045e-05, "Pretrain/Loss": 2.080707550048828, "Pretrain/Loss (Raw)": 1.99907386302948, "Pretrain/Step": 2370, "Pretrain/Step Time": 8.860949613153934} +{"Pretrain/Learning Rate": 4.39906996203831e-05, "Pretrain/Loss": 2.079063892364502, "Pretrain/Loss (Raw)": 2.00917911529541, "Pretrain/Step": 2371, "Pretrain/Step Time": 8.86923536658287} +{"Pretrain/Learning Rate": 4.398517706985879e-05, "Pretrain/Loss": 2.0806875228881836, "Pretrain/Loss (Raw)": 2.1489713191986084, "Pretrain/Step": 2372, "Pretrain/Step Time": 8.862740628421307} +{"Pretrain/Learning Rate": 4.39796523298744e-05, "Pretrain/Loss": 2.0807063579559326, "Pretrain/Loss (Raw)": 2.1554996967315674, "Pretrain/Step": 2373, "Pretrain/Step Time": 8.865625202655792} +{"Pretrain/Learning Rate": 4.397412540106707e-05, "Pretrain/Loss": 2.081202745437622, "Pretrain/Loss (Raw)": 2.1144495010375977, "Pretrain/Step": 2374, "Pretrain/Step Time": 8.86597279086709} +{"Pretrain/Learning Rate": 4.396859628407418e-05, "Pretrain/Loss": 2.0821499824523926, "Pretrain/Loss (Raw)": 2.026834726333618, "Pretrain/Step": 2375, "Pretrain/Step Time": 8.863781305029988} +{"Pretrain/Learning Rate": 4.39630649795334e-05, "Pretrain/Loss": 2.083332061767578, "Pretrain/Loss (Raw)": 2.1368091106414795, "Pretrain/Step": 2376, "Pretrain/Step Time": 8.86681299842894} +{"Pretrain/Learning Rate": 4.3957531488082595e-05, "Pretrain/Loss": 2.0842831134796143, "Pretrain/Loss (Raw)": 2.042973518371582, "Pretrain/Step": 2377, "Pretrain/Step Time": 8.872151166200638} +{"Pretrain/Learning Rate": 4.395199581035994e-05, "Pretrain/Loss": 2.083643674850464, "Pretrain/Loss (Raw)": 1.981829047203064, "Pretrain/Step": 2378, "Pretrain/Step Time": 8.86876386962831} +{"Pretrain/Learning Rate": 4.3946457947003813e-05, "Pretrain/Loss": 2.0838117599487305, "Pretrain/Loss (Raw)": 2.1591053009033203, "Pretrain/Step": 2379, "Pretrain/Step Time": 8.869186686351895} +{"Pretrain/Learning Rate": 4.394091789865288e-05, "Pretrain/Loss": 2.0861196517944336, "Pretrain/Loss (Raw)": 2.231001138687134, "Pretrain/Step": 2380, "Pretrain/Step Time": 8.866587502881885} +{"Pretrain/Learning Rate": 4.393537566594605e-05, "Pretrain/Loss": 2.0857691764831543, "Pretrain/Loss (Raw)": 2.028073787689209, "Pretrain/Step": 2381, "Pretrain/Step Time": 8.86837668903172} +{"Pretrain/Learning Rate": 4.392983124952246e-05, "Pretrain/Loss": 2.0854263305664062, "Pretrain/Loss (Raw)": 2.075570583343506, "Pretrain/Step": 2382, "Pretrain/Step Time": 8.867180289700627} +{"Pretrain/Learning Rate": 4.392428465002154e-05, "Pretrain/Loss": 2.0860435962677, "Pretrain/Loss (Raw)": 2.1535191535949707, "Pretrain/Step": 2383, "Pretrain/Step Time": 8.866301229223609} +{"Pretrain/Learning Rate": 4.391873586808294e-05, "Pretrain/Loss": 2.086042642593384, "Pretrain/Loss (Raw)": 2.0952839851379395, "Pretrain/Step": 2384, "Pretrain/Step Time": 8.875347321853042} +{"Pretrain/Learning Rate": 4.391318490434656e-05, "Pretrain/Loss": 2.0885491371154785, "Pretrain/Loss (Raw)": 2.2646377086639404, "Pretrain/Step": 2385, "Pretrain/Step Time": 8.875044772401452} +{"Pretrain/Learning Rate": 4.3907631759452584e-05, "Pretrain/Loss": 2.089771270751953, "Pretrain/Loss (Raw)": 2.318608283996582, "Pretrain/Step": 2386, "Pretrain/Step Time": 8.879780871793628} +{"Pretrain/Learning Rate": 4.3902076434041416e-05, "Pretrain/Loss": 2.0884456634521484, "Pretrain/Loss (Raw)": 2.016719102859497, "Pretrain/Step": 2387, "Pretrain/Step Time": 8.873587355017662} +{"Pretrain/Learning Rate": 4.389651892875373e-05, "Pretrain/Loss": 2.087904930114746, "Pretrain/Loss (Raw)": 2.0152556896209717, "Pretrain/Step": 2388, "Pretrain/Step Time": 8.874910827726126} +{"Pretrain/Learning Rate": 4.389095924423043e-05, "Pretrain/Loss": 2.0857620239257812, "Pretrain/Loss (Raw)": 1.964104175567627, "Pretrain/Step": 2389, "Pretrain/Step Time": 8.874526312574744} +{"Pretrain/Learning Rate": 4.388539738111269e-05, "Pretrain/Loss": 2.083354949951172, "Pretrain/Loss (Raw)": 2.0421762466430664, "Pretrain/Step": 2390, "Pretrain/Step Time": 8.875308822840452} +{"Pretrain/Learning Rate": 4.387983334004194e-05, "Pretrain/Loss": 2.0846145153045654, "Pretrain/Loss (Raw)": 2.1294467449188232, "Pretrain/Step": 2391, "Pretrain/Step Time": 8.881111223250628} +{"Pretrain/Learning Rate": 4.387426712165984e-05, "Pretrain/Loss": 2.0867271423339844, "Pretrain/Loss (Raw)": 2.2318153381347656, "Pretrain/Step": 2392, "Pretrain/Step Time": 8.872557647526264} +{"Pretrain/Learning Rate": 4.3868698726608325e-05, "Pretrain/Loss": 2.087599277496338, "Pretrain/Loss (Raw)": 2.0667407512664795, "Pretrain/Step": 2393, "Pretrain/Step Time": 8.867251679301262} +{"Pretrain/Learning Rate": 4.3863128155529554e-05, "Pretrain/Loss": 2.086432695388794, "Pretrain/Loss (Raw)": 2.061563491821289, "Pretrain/Step": 2394, "Pretrain/Step Time": 8.870367001742125} +{"Pretrain/Learning Rate": 4.385755540906595e-05, "Pretrain/Loss": 2.084618091583252, "Pretrain/Loss (Raw)": 2.0914833545684814, "Pretrain/Step": 2395, "Pretrain/Step Time": 8.87313956208527} +{"Pretrain/Learning Rate": 4.385198048786021e-05, "Pretrain/Loss": 2.0844311714172363, "Pretrain/Loss (Raw)": 2.0434465408325195, "Pretrain/Step": 2396, "Pretrain/Step Time": 8.874932806938887} +{"Pretrain/Learning Rate": 4.384640339255525e-05, "Pretrain/Loss": 2.085970401763916, "Pretrain/Loss (Raw)": 2.2407689094543457, "Pretrain/Step": 2397, "Pretrain/Step Time": 8.873436955735087} +{"Pretrain/Learning Rate": 4.384082412379423e-05, "Pretrain/Loss": 2.0854663848876953, "Pretrain/Loss (Raw)": 1.9868313074111938, "Pretrain/Step": 2398, "Pretrain/Step Time": 8.87452433258295} +{"Pretrain/Learning Rate": 4.38352426822206e-05, "Pretrain/Loss": 2.085073947906494, "Pretrain/Loss (Raw)": 2.1655688285827637, "Pretrain/Step": 2399, "Pretrain/Step Time": 8.877834390848875} +{"Pretrain/Learning Rate": 4.3829659068478026e-05, "Pretrain/Loss": 2.0852482318878174, "Pretrain/Loss (Raw)": 1.8943018913269043, "Pretrain/Step": 2400, "Pretrain/Step Time": 8.87625632993877} +{"Pretrain/Learning Rate": 4.3824073283210445e-05, "Pretrain/Loss": 2.085667133331299, "Pretrain/Loss (Raw)": 2.078115224838257, "Pretrain/Step": 2401, "Pretrain/Step Time": 8.882088974118233} +{"Pretrain/Learning Rate": 4.381848532706202e-05, "Pretrain/Loss": 2.084073066711426, "Pretrain/Loss (Raw)": 1.9152345657348633, "Pretrain/Step": 2402, "Pretrain/Step Time": 8.88026368804276} +{"Pretrain/Learning Rate": 4.38128952006772e-05, "Pretrain/Loss": 2.085268974304199, "Pretrain/Loss (Raw)": 2.020751476287842, "Pretrain/Step": 2403, "Pretrain/Step Time": 8.877488244324923} +{"Pretrain/Learning Rate": 4.380730290470065e-05, "Pretrain/Loss": 2.087251663208008, "Pretrain/Loss (Raw)": 2.1355550289154053, "Pretrain/Step": 2404, "Pretrain/Step Time": 8.879323065280914} +{"Pretrain/Learning Rate": 4.380170843977731e-05, "Pretrain/Loss": 2.089202404022217, "Pretrain/Loss (Raw)": 2.106796979904175, "Pretrain/Step": 2405, "Pretrain/Step Time": 8.879926392808557} +{"Pretrain/Learning Rate": 4.3796111806552364e-05, "Pretrain/Loss": 2.0905184745788574, "Pretrain/Loss (Raw)": 2.2352962493896484, "Pretrain/Step": 2406, "Pretrain/Step Time": 8.87621619924903} +{"Pretrain/Learning Rate": 4.379051300567123e-05, "Pretrain/Loss": 2.0915653705596924, "Pretrain/Loss (Raw)": 2.1224019527435303, "Pretrain/Step": 2407, "Pretrain/Step Time": 8.87646291218698} +{"Pretrain/Learning Rate": 4.378491203777958e-05, "Pretrain/Loss": 2.090263605117798, "Pretrain/Loss (Raw)": 1.9790149927139282, "Pretrain/Step": 2408, "Pretrain/Step Time": 8.874379871413112} +{"Pretrain/Learning Rate": 4.377930890352337e-05, "Pretrain/Loss": 2.0896520614624023, "Pretrain/Loss (Raw)": 2.1878128051757812, "Pretrain/Step": 2409, "Pretrain/Step Time": 8.879856729879975} +{"Pretrain/Learning Rate": 4.3773703603548765e-05, "Pretrain/Loss": 2.0897092819213867, "Pretrain/Loss (Raw)": 2.179016590118408, "Pretrain/Step": 2410, "Pretrain/Step Time": 8.87548635341227} +{"Pretrain/Learning Rate": 4.3768096138502194e-05, "Pretrain/Loss": 2.0901412963867188, "Pretrain/Loss (Raw)": 2.1391963958740234, "Pretrain/Step": 2411, "Pretrain/Step Time": 8.879937203601003} +{"Pretrain/Learning Rate": 4.376248650903033e-05, "Pretrain/Loss": 2.0914390087127686, "Pretrain/Loss (Raw)": 2.1258323192596436, "Pretrain/Step": 2412, "Pretrain/Step Time": 8.87503401003778} +{"Pretrain/Learning Rate": 4.375687471578011e-05, "Pretrain/Loss": 2.0910484790802, "Pretrain/Loss (Raw)": 2.155672788619995, "Pretrain/Step": 2413, "Pretrain/Step Time": 8.880832416936755} +{"Pretrain/Learning Rate": 4.375126075939873e-05, "Pretrain/Loss": 2.0910797119140625, "Pretrain/Loss (Raw)": 2.0830960273742676, "Pretrain/Step": 2414, "Pretrain/Step Time": 8.874765312299132} +{"Pretrain/Learning Rate": 4.374564464053359e-05, "Pretrain/Loss": 2.0907435417175293, "Pretrain/Loss (Raw)": 2.1753580570220947, "Pretrain/Step": 2415, "Pretrain/Step Time": 8.873341290280223} +{"Pretrain/Learning Rate": 4.374002635983238e-05, "Pretrain/Loss": 2.089276075363159, "Pretrain/Loss (Raw)": 1.9331767559051514, "Pretrain/Step": 2416, "Pretrain/Step Time": 8.88224988244474} +{"Pretrain/Learning Rate": 4.373440591794301e-05, "Pretrain/Loss": 2.0891990661621094, "Pretrain/Loss (Raw)": 2.087282180786133, "Pretrain/Step": 2417, "Pretrain/Step Time": 8.882122123613954} +{"Pretrain/Learning Rate": 4.372878331551369e-05, "Pretrain/Loss": 2.0900864601135254, "Pretrain/Loss (Raw)": 2.0727319717407227, "Pretrain/Step": 2418, "Pretrain/Step Time": 8.883442277088761} +{"Pretrain/Learning Rate": 4.3723158553192813e-05, "Pretrain/Loss": 2.0890185832977295, "Pretrain/Loss (Raw)": 2.127685070037842, "Pretrain/Step": 2419, "Pretrain/Step Time": 8.883930515497923} +{"Pretrain/Learning Rate": 4.3717531631629075e-05, "Pretrain/Loss": 2.0882961750030518, "Pretrain/Loss (Raw)": 2.1777846813201904, "Pretrain/Step": 2420, "Pretrain/Step Time": 8.88786856085062} +{"Pretrain/Learning Rate": 4.371190255147138e-05, "Pretrain/Loss": 2.0891335010528564, "Pretrain/Loss (Raw)": 2.186826705932617, "Pretrain/Step": 2421, "Pretrain/Step Time": 8.885198928415775} +{"Pretrain/Learning Rate": 4.370627131336891e-05, "Pretrain/Loss": 2.089719772338867, "Pretrain/Loss (Raw)": 2.2011570930480957, "Pretrain/Step": 2422, "Pretrain/Step Time": 8.883412329480052} +{"Pretrain/Learning Rate": 4.370063791797109e-05, "Pretrain/Loss": 2.0902915000915527, "Pretrain/Loss (Raw)": 2.221257448196411, "Pretrain/Step": 2423, "Pretrain/Step Time": 8.877670573070645} +{"Pretrain/Learning Rate": 4.3695002365927584e-05, "Pretrain/Loss": 2.089319944381714, "Pretrain/Loss (Raw)": 1.927296757698059, "Pretrain/Step": 2424, "Pretrain/Step Time": 8.877313483506441} +{"Pretrain/Learning Rate": 4.368936465788831e-05, "Pretrain/Loss": 2.087820529937744, "Pretrain/Loss (Raw)": 2.033795118331909, "Pretrain/Step": 2425, "Pretrain/Step Time": 8.881465518847108} +{"Pretrain/Learning Rate": 4.3683724794503436e-05, "Pretrain/Loss": 2.0909180641174316, "Pretrain/Loss (Raw)": 2.394037961959839, "Pretrain/Step": 2426, "Pretrain/Step Time": 8.876588413491845} +{"Pretrain/Learning Rate": 4.367808277642338e-05, "Pretrain/Loss": 2.0902457237243652, "Pretrain/Loss (Raw)": 2.2030320167541504, "Pretrain/Step": 2427, "Pretrain/Step Time": 8.872958548367023} +{"Pretrain/Learning Rate": 4.3672438604298806e-05, "Pretrain/Loss": 2.0904927253723145, "Pretrain/Loss (Raw)": 2.014808416366577, "Pretrain/Step": 2428, "Pretrain/Step Time": 8.876247538253665} +{"Pretrain/Learning Rate": 4.3666792278780625e-05, "Pretrain/Loss": 2.0886425971984863, "Pretrain/Loss (Raw)": 1.902675747871399, "Pretrain/Step": 2429, "Pretrain/Step Time": 8.883142463862896} +{"Pretrain/Learning Rate": 4.366114380051999e-05, "Pretrain/Loss": 2.088505268096924, "Pretrain/Loss (Raw)": 2.04823637008667, "Pretrain/Step": 2430, "Pretrain/Step Time": 8.87173816561699} +{"Pretrain/Learning Rate": 4.365549317016832e-05, "Pretrain/Loss": 2.089367151260376, "Pretrain/Loss (Raw)": 2.076373338699341, "Pretrain/Step": 2431, "Pretrain/Step Time": 8.874793143942952} +{"Pretrain/Learning Rate": 4.364984038837727e-05, "Pretrain/Loss": 2.0907068252563477, "Pretrain/Loss (Raw)": 2.221210241317749, "Pretrain/Step": 2432, "Pretrain/Step Time": 8.872519005089998} +{"Pretrain/Learning Rate": 4.364418545579875e-05, "Pretrain/Loss": 2.0905885696411133, "Pretrain/Loss (Raw)": 2.1711931228637695, "Pretrain/Step": 2433, "Pretrain/Step Time": 8.87288705818355} +{"Pretrain/Learning Rate": 4.363852837308491e-05, "Pretrain/Loss": 2.0926060676574707, "Pretrain/Loss (Raw)": 2.2242209911346436, "Pretrain/Step": 2434, "Pretrain/Step Time": 8.870221856981516} +{"Pretrain/Learning Rate": 4.3632869140888144e-05, "Pretrain/Loss": 2.0927677154541016, "Pretrain/Loss (Raw)": 2.0223238468170166, "Pretrain/Step": 2435, "Pretrain/Step Time": 8.8716463111341} +{"Pretrain/Learning Rate": 4.362720775986111e-05, "Pretrain/Loss": 2.0919713973999023, "Pretrain/Loss (Raw)": 2.0096278190612793, "Pretrain/Step": 2436, "Pretrain/Step Time": 8.881291070953012} +{"Pretrain/Learning Rate": 4.362154423065671e-05, "Pretrain/Loss": 2.0910987854003906, "Pretrain/Loss (Raw)": 2.053551197052002, "Pretrain/Step": 2437, "Pretrain/Step Time": 8.88177053257823} +{"Pretrain/Learning Rate": 4.361587855392807e-05, "Pretrain/Loss": 2.0920331478118896, "Pretrain/Loss (Raw)": 2.274864435195923, "Pretrain/Step": 2438, "Pretrain/Step Time": 8.877830222249031} +{"Pretrain/Learning Rate": 4.3610210730328604e-05, "Pretrain/Loss": 2.093916654586792, "Pretrain/Loss (Raw)": 2.119178056716919, "Pretrain/Step": 2439, "Pretrain/Step Time": 8.872825572267175} +{"Pretrain/Learning Rate": 4.3604540760511935e-05, "Pretrain/Loss": 2.092841386795044, "Pretrain/Loss (Raw)": 2.0477664470672607, "Pretrain/Step": 2440, "Pretrain/Step Time": 8.869737520813942} +{"Pretrain/Learning Rate": 4.3598868645131964e-05, "Pretrain/Loss": 2.092538356781006, "Pretrain/Loss (Raw)": 2.0223569869995117, "Pretrain/Step": 2441, "Pretrain/Step Time": 8.87336840108037} +{"Pretrain/Learning Rate": 4.359319438484282e-05, "Pretrain/Loss": 2.0928778648376465, "Pretrain/Loss (Raw)": 2.154337167739868, "Pretrain/Step": 2442, "Pretrain/Step Time": 8.868943367153406} +{"Pretrain/Learning Rate": 4.358751798029887e-05, "Pretrain/Loss": 2.09171199798584, "Pretrain/Loss (Raw)": 2.0489673614501953, "Pretrain/Step": 2443, "Pretrain/Step Time": 8.870106142014265} +{"Pretrain/Learning Rate": 4.358183943215478e-05, "Pretrain/Loss": 2.091362476348877, "Pretrain/Loss (Raw)": 2.0985023975372314, "Pretrain/Step": 2444, "Pretrain/Step Time": 8.872892197221518} +{"Pretrain/Learning Rate": 4.3576158741065395e-05, "Pretrain/Loss": 2.0922727584838867, "Pretrain/Loss (Raw)": 2.1781392097473145, "Pretrain/Step": 2445, "Pretrain/Step Time": 8.866997918114066} +{"Pretrain/Learning Rate": 4.357047590768586e-05, "Pretrain/Loss": 2.0950615406036377, "Pretrain/Loss (Raw)": 2.109088182449341, "Pretrain/Step": 2446, "Pretrain/Step Time": 8.870372045785189} +{"Pretrain/Learning Rate": 4.356479093267153e-05, "Pretrain/Loss": 2.094095230102539, "Pretrain/Loss (Raw)": 2.1235384941101074, "Pretrain/Step": 2447, "Pretrain/Step Time": 8.86708565801382} +{"Pretrain/Learning Rate": 4.355910381667803e-05, "Pretrain/Loss": 2.0956239700317383, "Pretrain/Loss (Raw)": 2.2007319927215576, "Pretrain/Step": 2448, "Pretrain/Step Time": 8.867867710068822} +{"Pretrain/Learning Rate": 4.355341456036122e-05, "Pretrain/Loss": 2.095012664794922, "Pretrain/Loss (Raw)": 2.0122251510620117, "Pretrain/Step": 2449, "Pretrain/Step Time": 8.867475524544716} +{"Pretrain/Learning Rate": 4.354772316437722e-05, "Pretrain/Loss": 2.095055103302002, "Pretrain/Loss (Raw)": 2.121856689453125, "Pretrain/Step": 2450, "Pretrain/Step Time": 8.865283792838454} +{"Pretrain/Learning Rate": 4.354202962938239e-05, "Pretrain/Loss": 2.0954809188842773, "Pretrain/Loss (Raw)": 2.0552709102630615, "Pretrain/Step": 2451, "Pretrain/Step Time": 8.865053975954652} +{"Pretrain/Learning Rate": 4.353633395603332e-05, "Pretrain/Loss": 2.0951435565948486, "Pretrain/Loss (Raw)": 2.102374792098999, "Pretrain/Step": 2452, "Pretrain/Step Time": 8.868539027869701} +{"Pretrain/Learning Rate": 4.353063614498688e-05, "Pretrain/Loss": 2.096893310546875, "Pretrain/Loss (Raw)": 2.1497278213500977, "Pretrain/Step": 2453, "Pretrain/Step Time": 8.8663000036031} +{"Pretrain/Learning Rate": 4.352493619690016e-05, "Pretrain/Loss": 2.0970115661621094, "Pretrain/Loss (Raw)": 2.1687636375427246, "Pretrain/Step": 2454, "Pretrain/Step Time": 8.868750553578138} +{"Pretrain/Learning Rate": 4.351923411243049e-05, "Pretrain/Loss": 2.096194267272949, "Pretrain/Loss (Raw)": 2.0579402446746826, "Pretrain/Step": 2455, "Pretrain/Step Time": 8.866807784885168} +{"Pretrain/Learning Rate": 4.35135298922355e-05, "Pretrain/Loss": 2.097029447555542, "Pretrain/Loss (Raw)": 2.116969347000122, "Pretrain/Step": 2456, "Pretrain/Step Time": 8.869805423542857} +{"Pretrain/Learning Rate": 4.350782353697299e-05, "Pretrain/Loss": 2.09549617767334, "Pretrain/Loss (Raw)": 1.9062312841415405, "Pretrain/Step": 2457, "Pretrain/Step Time": 8.871293235570192} +{"Pretrain/Learning Rate": 4.350211504730106e-05, "Pretrain/Loss": 2.0957584381103516, "Pretrain/Loss (Raw)": 2.1781933307647705, "Pretrain/Step": 2458, "Pretrain/Step Time": 8.870100555941463} +{"Pretrain/Learning Rate": 4.3496404423878045e-05, "Pretrain/Loss": 2.095663070678711, "Pretrain/Loss (Raw)": 2.2067501544952393, "Pretrain/Step": 2459, "Pretrain/Step Time": 8.869306707754731} +{"Pretrain/Learning Rate": 4.349069166736251e-05, "Pretrain/Loss": 2.096280097961426, "Pretrain/Loss (Raw)": 2.0801780223846436, "Pretrain/Step": 2460, "Pretrain/Step Time": 8.867905599996448} +{"Pretrain/Learning Rate": 4.348497677841328e-05, "Pretrain/Loss": 2.0972776412963867, "Pretrain/Loss (Raw)": 2.0444772243499756, "Pretrain/Step": 2461, "Pretrain/Step Time": 8.876844853162766} +{"Pretrain/Learning Rate": 4.3479259757689427e-05, "Pretrain/Loss": 2.0966014862060547, "Pretrain/Loss (Raw)": 2.158440113067627, "Pretrain/Step": 2462, "Pretrain/Step Time": 8.871696274727583} +{"Pretrain/Learning Rate": 4.347354060585026e-05, "Pretrain/Loss": 2.097395420074463, "Pretrain/Loss (Raw)": 2.1837241649627686, "Pretrain/Step": 2463, "Pretrain/Step Time": 8.877584557980299} +{"Pretrain/Learning Rate": 4.346781932355533e-05, "Pretrain/Loss": 2.0973854064941406, "Pretrain/Loss (Raw)": 1.997153401374817, "Pretrain/Step": 2464, "Pretrain/Step Time": 8.875776555389166} +{"Pretrain/Learning Rate": 4.3462095911464465e-05, "Pretrain/Loss": 2.0976288318634033, "Pretrain/Loss (Raw)": 2.086670160293579, "Pretrain/Step": 2465, "Pretrain/Step Time": 8.877165662124753} +{"Pretrain/Learning Rate": 4.34563703702377e-05, "Pretrain/Loss": 2.099045753479004, "Pretrain/Loss (Raw)": 2.1970667839050293, "Pretrain/Step": 2466, "Pretrain/Step Time": 8.87758495286107} +{"Pretrain/Learning Rate": 4.3450642700535335e-05, "Pretrain/Loss": 2.0988717079162598, "Pretrain/Loss (Raw)": 2.1111538410186768, "Pretrain/Step": 2467, "Pretrain/Step Time": 8.880486628040671} +{"Pretrain/Learning Rate": 4.344491290301791e-05, "Pretrain/Loss": 2.097949504852295, "Pretrain/Loss (Raw)": 1.9466756582260132, "Pretrain/Step": 2468, "Pretrain/Step Time": 8.880422551184893} +{"Pretrain/Learning Rate": 4.3439180978346216e-05, "Pretrain/Loss": 2.0980277061462402, "Pretrain/Loss (Raw)": 2.1133995056152344, "Pretrain/Step": 2469, "Pretrain/Step Time": 8.883278610184789} +{"Pretrain/Learning Rate": 4.3433446927181274e-05, "Pretrain/Loss": 2.095991849899292, "Pretrain/Loss (Raw)": 2.026965379714966, "Pretrain/Step": 2470, "Pretrain/Step Time": 8.88249851949513} +{"Pretrain/Learning Rate": 4.342771075018438e-05, "Pretrain/Loss": 2.0972418785095215, "Pretrain/Loss (Raw)": 2.114182710647583, "Pretrain/Step": 2471, "Pretrain/Step Time": 8.885250905528665} +{"Pretrain/Learning Rate": 4.342197244801705e-05, "Pretrain/Loss": 2.098470687866211, "Pretrain/Loss (Raw)": 2.0754356384277344, "Pretrain/Step": 2472, "Pretrain/Step Time": 8.883913241326809} +{"Pretrain/Learning Rate": 4.341623202134105e-05, "Pretrain/Loss": 2.098050117492676, "Pretrain/Loss (Raw)": 2.0516650676727295, "Pretrain/Step": 2473, "Pretrain/Step Time": 8.880070248618722} +{"Pretrain/Learning Rate": 4.341048947081839e-05, "Pretrain/Loss": 2.097560405731201, "Pretrain/Loss (Raw)": 2.078406810760498, "Pretrain/Step": 2474, "Pretrain/Step Time": 8.882782677188516} +{"Pretrain/Learning Rate": 4.340474479711133e-05, "Pretrain/Loss": 2.098992347717285, "Pretrain/Loss (Raw)": 2.105020523071289, "Pretrain/Step": 2475, "Pretrain/Step Time": 8.877777552232146} +{"Pretrain/Learning Rate": 4.3398998000882375e-05, "Pretrain/Loss": 2.0969150066375732, "Pretrain/Loss (Raw)": 1.8709875345230103, "Pretrain/Step": 2476, "Pretrain/Step Time": 8.877212291583419} +{"Pretrain/Learning Rate": 4.339324908279427e-05, "Pretrain/Loss": 2.097891330718994, "Pretrain/Loss (Raw)": 2.1520283222198486, "Pretrain/Step": 2477, "Pretrain/Step Time": 8.880785575136542} +{"Pretrain/Learning Rate": 4.338749804351001e-05, "Pretrain/Loss": 2.098252773284912, "Pretrain/Loss (Raw)": 2.0666441917419434, "Pretrain/Step": 2478, "Pretrain/Step Time": 8.886263459920883} +{"Pretrain/Learning Rate": 4.338174488369283e-05, "Pretrain/Loss": 2.0952112674713135, "Pretrain/Loss (Raw)": 1.75352144241333, "Pretrain/Step": 2479, "Pretrain/Step Time": 8.885742008686066} +{"Pretrain/Learning Rate": 4.337598960400622e-05, "Pretrain/Loss": 2.096175193786621, "Pretrain/Loss (Raw)": 2.3437705039978027, "Pretrain/Step": 2480, "Pretrain/Step Time": 8.885121207684278} +{"Pretrain/Learning Rate": 4.337023220511389e-05, "Pretrain/Loss": 2.094968557357788, "Pretrain/Loss (Raw)": 2.033283233642578, "Pretrain/Step": 2481, "Pretrain/Step Time": 8.89099913649261} +{"Pretrain/Learning Rate": 4.336447268767982e-05, "Pretrain/Loss": 2.095961332321167, "Pretrain/Loss (Raw)": 2.1757404804229736, "Pretrain/Step": 2482, "Pretrain/Step Time": 8.884009949862957} +{"Pretrain/Learning Rate": 4.3358711052368224e-05, "Pretrain/Loss": 2.098970890045166, "Pretrain/Loss (Raw)": 2.4774346351623535, "Pretrain/Step": 2483, "Pretrain/Step Time": 8.885402001440525} +{"Pretrain/Learning Rate": 4.335294729984356e-05, "Pretrain/Loss": 2.0986342430114746, "Pretrain/Loss (Raw)": 2.1369504928588867, "Pretrain/Step": 2484, "Pretrain/Step Time": 8.884500678628683} +{"Pretrain/Learning Rate": 4.334718143077054e-05, "Pretrain/Loss": 2.098569631576538, "Pretrain/Loss (Raw)": 2.0637173652648926, "Pretrain/Step": 2485, "Pretrain/Step Time": 8.888791212812066} +{"Pretrain/Learning Rate": 4.334141344581408e-05, "Pretrain/Loss": 2.0996272563934326, "Pretrain/Loss (Raw)": 2.109428644180298, "Pretrain/Step": 2486, "Pretrain/Step Time": 8.888479152694345} +{"Pretrain/Learning Rate": 4.3335643345639414e-05, "Pretrain/Loss": 2.1014463901519775, "Pretrain/Loss (Raw)": 2.0899980068206787, "Pretrain/Step": 2487, "Pretrain/Step Time": 8.889931160956621} +{"Pretrain/Learning Rate": 4.332987113091195e-05, "Pretrain/Loss": 2.100297212600708, "Pretrain/Loss (Raw)": 2.015726089477539, "Pretrain/Step": 2488, "Pretrain/Step Time": 8.892649529501796} +{"Pretrain/Learning Rate": 4.332409680229737e-05, "Pretrain/Loss": 2.101179599761963, "Pretrain/Loss (Raw)": 1.9842253923416138, "Pretrain/Step": 2489, "Pretrain/Step Time": 8.88397592306137} +{"Pretrain/Learning Rate": 4.3318320360461616e-05, "Pretrain/Loss": 2.1006956100463867, "Pretrain/Loss (Raw)": 2.028265953063965, "Pretrain/Step": 2490, "Pretrain/Step Time": 8.884301306679845} +{"Pretrain/Learning Rate": 4.331254180607083e-05, "Pretrain/Loss": 2.1021745204925537, "Pretrain/Loss (Raw)": 2.146986484527588, "Pretrain/Step": 2491, "Pretrain/Step Time": 8.885331343859434} +{"Pretrain/Learning Rate": 4.330676113979143e-05, "Pretrain/Loss": 2.101745128631592, "Pretrain/Loss (Raw)": 2.0834550857543945, "Pretrain/Step": 2492, "Pretrain/Step Time": 8.885460242629051} +{"Pretrain/Learning Rate": 4.330097836229007e-05, "Pretrain/Loss": 2.09905743598938, "Pretrain/Loss (Raw)": 1.9251970052719116, "Pretrain/Step": 2493, "Pretrain/Step Time": 8.891458459198475} +{"Pretrain/Learning Rate": 4.3295193474233655e-05, "Pretrain/Loss": 2.097205400466919, "Pretrain/Loss (Raw)": 1.988406777381897, "Pretrain/Step": 2494, "Pretrain/Step Time": 8.891288308426738} +{"Pretrain/Learning Rate": 4.328940647628931e-05, "Pretrain/Loss": 2.0962882041931152, "Pretrain/Loss (Raw)": 1.9893959760665894, "Pretrain/Step": 2495, "Pretrain/Step Time": 8.890904635190964} +{"Pretrain/Learning Rate": 4.328361736912443e-05, "Pretrain/Loss": 2.094066619873047, "Pretrain/Loss (Raw)": 1.9062587022781372, "Pretrain/Step": 2496, "Pretrain/Step Time": 8.886875988915563} +{"Pretrain/Learning Rate": 4.3277826153406644e-05, "Pretrain/Loss": 2.0945920944213867, "Pretrain/Loss (Raw)": 2.100911855697632, "Pretrain/Step": 2497, "Pretrain/Step Time": 8.88445214368403} +{"Pretrain/Learning Rate": 4.327203282980382e-05, "Pretrain/Loss": 2.0955376625061035, "Pretrain/Loss (Raw)": 2.1200809478759766, "Pretrain/Step": 2498, "Pretrain/Step Time": 8.886721348389983} +{"Pretrain/Learning Rate": 4.326623739898406e-05, "Pretrain/Loss": 2.0964760780334473, "Pretrain/Loss (Raw)": 2.129314661026001, "Pretrain/Step": 2499, "Pretrain/Step Time": 8.88774761930108} +{"Pretrain/Learning Rate": 4.3260439861615734e-05, "Pretrain/Loss": 2.095155954360962, "Pretrain/Loss (Raw)": 1.9799963235855103, "Pretrain/Step": 2500, "Pretrain/Step Time": 8.887833824381232} +{"Pretrain/Learning Rate": 4.325464021836744e-05, "Pretrain/Loss": 2.0951766967773438, "Pretrain/Loss (Raw)": 2.158133029937744, "Pretrain/Step": 2501, "Pretrain/Step Time": 8.883634377270937} +{"Pretrain/Learning Rate": 4.3248838469908016e-05, "Pretrain/Loss": 2.0945816040039062, "Pretrain/Loss (Raw)": 2.0383031368255615, "Pretrain/Step": 2502, "Pretrain/Step Time": 8.8823745790869} +{"Pretrain/Learning Rate": 4.324303461690655e-05, "Pretrain/Loss": 2.094642400741577, "Pretrain/Loss (Raw)": 2.0346033573150635, "Pretrain/Step": 2503, "Pretrain/Step Time": 8.881501499563456} +{"Pretrain/Learning Rate": 4.3237228660032355e-05, "Pretrain/Loss": 2.094155788421631, "Pretrain/Loss (Raw)": 2.0745394229888916, "Pretrain/Step": 2504, "Pretrain/Step Time": 8.88136644475162} +{"Pretrain/Learning Rate": 4.323142059995503e-05, "Pretrain/Loss": 2.0959067344665527, "Pretrain/Loss (Raw)": 2.2670743465423584, "Pretrain/Step": 2505, "Pretrain/Step Time": 8.878887662664056} +{"Pretrain/Learning Rate": 4.3225610437344363e-05, "Pretrain/Loss": 2.0976948738098145, "Pretrain/Loss (Raw)": 2.210740566253662, "Pretrain/Step": 2506, "Pretrain/Step Time": 8.882031353190541} +{"Pretrain/Learning Rate": 4.321979817287043e-05, "Pretrain/Loss": 2.097644329071045, "Pretrain/Loss (Raw)": 2.1526060104370117, "Pretrain/Step": 2507, "Pretrain/Step Time": 8.879657287150621} +{"Pretrain/Learning Rate": 4.32139838072035e-05, "Pretrain/Loss": 2.096665859222412, "Pretrain/Loss (Raw)": 2.105740547180176, "Pretrain/Step": 2508, "Pretrain/Step Time": 8.88322795368731} +{"Pretrain/Learning Rate": 4.320816734101415e-05, "Pretrain/Loss": 2.100071907043457, "Pretrain/Loss (Raw)": 2.464078903198242, "Pretrain/Step": 2509, "Pretrain/Step Time": 8.877173209562898} +{"Pretrain/Learning Rate": 4.320234877497313e-05, "Pretrain/Loss": 2.1011204719543457, "Pretrain/Loss (Raw)": 2.2097830772399902, "Pretrain/Step": 2510, "Pretrain/Step Time": 8.882739931344986} +{"Pretrain/Learning Rate": 4.319652810975148e-05, "Pretrain/Loss": 2.1010313034057617, "Pretrain/Loss (Raw)": 2.1420791149139404, "Pretrain/Step": 2511, "Pretrain/Step Time": 8.884275488555431} +{"Pretrain/Learning Rate": 4.319070534602047e-05, "Pretrain/Loss": 2.1009554862976074, "Pretrain/Loss (Raw)": 2.085618257522583, "Pretrain/Step": 2512, "Pretrain/Step Time": 8.879894295707345} +{"Pretrain/Learning Rate": 4.318488048445158e-05, "Pretrain/Loss": 2.098968505859375, "Pretrain/Loss (Raw)": 2.010256767272949, "Pretrain/Step": 2513, "Pretrain/Step Time": 8.878425853326917} +{"Pretrain/Learning Rate": 4.317905352571661e-05, "Pretrain/Loss": 2.097568988800049, "Pretrain/Loss (Raw)": 2.1395015716552734, "Pretrain/Step": 2514, "Pretrain/Step Time": 8.875293366611004} +{"Pretrain/Learning Rate": 4.317322447048751e-05, "Pretrain/Loss": 2.0967867374420166, "Pretrain/Loss (Raw)": 1.9165955781936646, "Pretrain/Step": 2515, "Pretrain/Step Time": 8.877438874915242} +{"Pretrain/Learning Rate": 4.316739331943653e-05, "Pretrain/Loss": 2.097433090209961, "Pretrain/Loss (Raw)": 2.0980024337768555, "Pretrain/Step": 2516, "Pretrain/Step Time": 8.87481389567256} +{"Pretrain/Learning Rate": 4.316156007323614e-05, "Pretrain/Loss": 2.0985403060913086, "Pretrain/Loss (Raw)": 2.105818510055542, "Pretrain/Step": 2517, "Pretrain/Step Time": 8.875905498862267} +{"Pretrain/Learning Rate": 4.315572473255908e-05, "Pretrain/Loss": 2.0993168354034424, "Pretrain/Loss (Raw)": 2.1415657997131348, "Pretrain/Step": 2518, "Pretrain/Step Time": 8.872374977916479} +{"Pretrain/Learning Rate": 4.3149887298078276e-05, "Pretrain/Loss": 2.0987088680267334, "Pretrain/Loss (Raw)": 2.051640510559082, "Pretrain/Step": 2519, "Pretrain/Step Time": 8.87489876896143} +{"Pretrain/Learning Rate": 4.314404777046694e-05, "Pretrain/Loss": 2.09668231010437, "Pretrain/Loss (Raw)": 1.9724096059799194, "Pretrain/Step": 2520, "Pretrain/Step Time": 8.874820170924067} +{"Pretrain/Learning Rate": 4.313820615039853e-05, "Pretrain/Loss": 2.0965330600738525, "Pretrain/Loss (Raw)": 2.0476233959198, "Pretrain/Step": 2521, "Pretrain/Step Time": 8.875945618376136} +{"Pretrain/Learning Rate": 4.313236243854671e-05, "Pretrain/Loss": 2.0973565578460693, "Pretrain/Loss (Raw)": 2.166987180709839, "Pretrain/Step": 2522, "Pretrain/Step Time": 8.868057260289788} +{"Pretrain/Learning Rate": 4.3126516635585414e-05, "Pretrain/Loss": 2.0980422496795654, "Pretrain/Loss (Raw)": 2.1792330741882324, "Pretrain/Step": 2523, "Pretrain/Step Time": 8.871135361492634} +{"Pretrain/Learning Rate": 4.312066874218881e-05, "Pretrain/Loss": 2.098510265350342, "Pretrain/Loss (Raw)": 2.1033682823181152, "Pretrain/Step": 2524, "Pretrain/Step Time": 8.865607559680939} +{"Pretrain/Learning Rate": 4.3114818759031284e-05, "Pretrain/Loss": 2.0977065563201904, "Pretrain/Loss (Raw)": 2.13788104057312, "Pretrain/Step": 2525, "Pretrain/Step Time": 8.867070311680436} +{"Pretrain/Learning Rate": 4.310896668678751e-05, "Pretrain/Loss": 2.098071575164795, "Pretrain/Loss (Raw)": 2.0335469245910645, "Pretrain/Step": 2526, "Pretrain/Step Time": 8.862462120130658} +{"Pretrain/Learning Rate": 4.3103112526132364e-05, "Pretrain/Loss": 2.098330497741699, "Pretrain/Loss (Raw)": 2.1987202167510986, "Pretrain/Step": 2527, "Pretrain/Step Time": 8.867098696529865} +{"Pretrain/Learning Rate": 4.3097256277740976e-05, "Pretrain/Loss": 2.099513053894043, "Pretrain/Loss (Raw)": 2.045670747756958, "Pretrain/Step": 2528, "Pretrain/Step Time": 8.871523901820183} +{"Pretrain/Learning Rate": 4.309139794228871e-05, "Pretrain/Loss": 2.099862575531006, "Pretrain/Loss (Raw)": 2.122833013534546, "Pretrain/Step": 2529, "Pretrain/Step Time": 8.867215637117624} +{"Pretrain/Learning Rate": 4.3085537520451196e-05, "Pretrain/Loss": 2.1017494201660156, "Pretrain/Loss (Raw)": 2.156787395477295, "Pretrain/Step": 2530, "Pretrain/Step Time": 8.86792772077024} +{"Pretrain/Learning Rate": 4.307967501290427e-05, "Pretrain/Loss": 2.1025595664978027, "Pretrain/Loss (Raw)": 2.124436140060425, "Pretrain/Step": 2531, "Pretrain/Step Time": 8.868653386831284} +{"Pretrain/Learning Rate": 4.307381042032402e-05, "Pretrain/Loss": 2.102713108062744, "Pretrain/Loss (Raw)": 2.1552188396453857, "Pretrain/Step": 2532, "Pretrain/Step Time": 8.868611197918653} +{"Pretrain/Learning Rate": 4.3067943743386796e-05, "Pretrain/Loss": 2.103210687637329, "Pretrain/Loss (Raw)": 2.170485734939575, "Pretrain/Step": 2533, "Pretrain/Step Time": 8.865143900737166} +{"Pretrain/Learning Rate": 4.3062074982769155e-05, "Pretrain/Loss": 2.1028475761413574, "Pretrain/Loss (Raw)": 2.188784122467041, "Pretrain/Step": 2534, "Pretrain/Step Time": 8.86945927515626} +{"Pretrain/Learning Rate": 4.305620413914792e-05, "Pretrain/Loss": 2.102879762649536, "Pretrain/Loss (Raw)": 2.1265411376953125, "Pretrain/Step": 2535, "Pretrain/Step Time": 8.870168797671795} +{"Pretrain/Learning Rate": 4.305033121320013e-05, "Pretrain/Loss": 2.104163646697998, "Pretrain/Loss (Raw)": 2.143364429473877, "Pretrain/Step": 2536, "Pretrain/Step Time": 8.872423179447651} +{"Pretrain/Learning Rate": 4.30444562056031e-05, "Pretrain/Loss": 2.104252815246582, "Pretrain/Loss (Raw)": 2.199246644973755, "Pretrain/Step": 2537, "Pretrain/Step Time": 8.875836437568069} +{"Pretrain/Learning Rate": 4.3038579117034347e-05, "Pretrain/Loss": 2.102954387664795, "Pretrain/Loss (Raw)": 2.0127782821655273, "Pretrain/Step": 2538, "Pretrain/Step Time": 8.873877750709653} +{"Pretrain/Learning Rate": 4.303269994817165e-05, "Pretrain/Loss": 2.1008100509643555, "Pretrain/Loss (Raw)": 1.8647137880325317, "Pretrain/Step": 2539, "Pretrain/Step Time": 8.878289191052318} +{"Pretrain/Learning Rate": 4.302681869969302e-05, "Pretrain/Loss": 2.100027084350586, "Pretrain/Loss (Raw)": 2.025629758834839, "Pretrain/Step": 2540, "Pretrain/Step Time": 8.874117275699973} +{"Pretrain/Learning Rate": 4.3020935372276716e-05, "Pretrain/Loss": 2.10097599029541, "Pretrain/Loss (Raw)": 2.2771201133728027, "Pretrain/Step": 2541, "Pretrain/Step Time": 8.871150568127632} +{"Pretrain/Learning Rate": 4.3015049966601224e-05, "Pretrain/Loss": 2.0987932682037354, "Pretrain/Loss (Raw)": 1.803726077079773, "Pretrain/Step": 2542, "Pretrain/Step Time": 8.872381186112761} +{"Pretrain/Learning Rate": 4.3009162483345275e-05, "Pretrain/Loss": 2.0977818965911865, "Pretrain/Loss (Raw)": 2.045907735824585, "Pretrain/Step": 2543, "Pretrain/Step Time": 8.883603427559137} +{"Pretrain/Learning Rate": 4.300327292318786e-05, "Pretrain/Loss": 2.0992496013641357, "Pretrain/Loss (Raw)": 2.121033191680908, "Pretrain/Step": 2544, "Pretrain/Step Time": 8.879640758037567} +{"Pretrain/Learning Rate": 4.299738128680817e-05, "Pretrain/Loss": 2.0983424186706543, "Pretrain/Loss (Raw)": 1.9711687564849854, "Pretrain/Step": 2545, "Pretrain/Step Time": 8.88131101988256} +{"Pretrain/Learning Rate": 4.299148757488567e-05, "Pretrain/Loss": 2.097984552383423, "Pretrain/Loss (Raw)": 2.0269248485565186, "Pretrain/Step": 2546, "Pretrain/Step Time": 8.87973128631711} +{"Pretrain/Learning Rate": 4.298559178810003e-05, "Pretrain/Loss": 2.0980381965637207, "Pretrain/Loss (Raw)": 2.1345388889312744, "Pretrain/Step": 2547, "Pretrain/Step Time": 8.88133518025279} +{"Pretrain/Learning Rate": 4.297969392713121e-05, "Pretrain/Loss": 2.097208023071289, "Pretrain/Loss (Raw)": 2.071532726287842, "Pretrain/Step": 2548, "Pretrain/Step Time": 8.87793736346066} +{"Pretrain/Learning Rate": 4.297379399265935e-05, "Pretrain/Loss": 2.095914125442505, "Pretrain/Loss (Raw)": 2.021191120147705, "Pretrain/Step": 2549, "Pretrain/Step Time": 8.882106645032763} +{"Pretrain/Learning Rate": 4.296789198536488e-05, "Pretrain/Loss": 2.0939579010009766, "Pretrain/Loss (Raw)": 1.9507923126220703, "Pretrain/Step": 2550, "Pretrain/Step Time": 8.883827095851302} +{"Pretrain/Learning Rate": 4.296198790592843e-05, "Pretrain/Loss": 2.0923891067504883, "Pretrain/Loss (Raw)": 2.0204269886016846, "Pretrain/Step": 2551, "Pretrain/Step Time": 8.879662143066525} +{"Pretrain/Learning Rate": 4.295608175503091e-05, "Pretrain/Loss": 2.0947909355163574, "Pretrain/Loss (Raw)": 2.2347500324249268, "Pretrain/Step": 2552, "Pretrain/Step Time": 8.886231509968638} +{"Pretrain/Learning Rate": 4.295017353335342e-05, "Pretrain/Loss": 2.095014810562134, "Pretrain/Loss (Raw)": 2.062450408935547, "Pretrain/Step": 2553, "Pretrain/Step Time": 8.88079196587205} +{"Pretrain/Learning Rate": 4.2944263241577334e-05, "Pretrain/Loss": 2.0924744606018066, "Pretrain/Loss (Raw)": 2.06882381439209, "Pretrain/Step": 2554, "Pretrain/Step Time": 8.882112432271242} +{"Pretrain/Learning Rate": 4.293835088038425e-05, "Pretrain/Loss": 2.091188430786133, "Pretrain/Loss (Raw)": 2.0384414196014404, "Pretrain/Step": 2555, "Pretrain/Step Time": 8.883722377941012} +{"Pretrain/Learning Rate": 4.2932436450456025e-05, "Pretrain/Loss": 2.092597484588623, "Pretrain/Loss (Raw)": 2.1951744556427, "Pretrain/Step": 2556, "Pretrain/Step Time": 8.881826052442193} +{"Pretrain/Learning Rate": 4.292651995247472e-05, "Pretrain/Loss": 2.094007968902588, "Pretrain/Loss (Raw)": 2.0832324028015137, "Pretrain/Step": 2557, "Pretrain/Step Time": 8.885422348976135} +{"Pretrain/Learning Rate": 4.292060138712266e-05, "Pretrain/Loss": 2.095154285430908, "Pretrain/Loss (Raw)": 2.1949706077575684, "Pretrain/Step": 2558, "Pretrain/Step Time": 8.88508383743465} +{"Pretrain/Learning Rate": 4.2914680755082414e-05, "Pretrain/Loss": 2.095625877380371, "Pretrain/Loss (Raw)": 2.136749267578125, "Pretrain/Step": 2559, "Pretrain/Step Time": 8.883850509300828} +{"Pretrain/Learning Rate": 4.2908758057036756e-05, "Pretrain/Loss": 2.094228982925415, "Pretrain/Loss (Raw)": 2.042371988296509, "Pretrain/Step": 2560, "Pretrain/Step Time": 8.88777587376535} +{"Pretrain/Learning Rate": 4.2902833293668744e-05, "Pretrain/Loss": 2.0939888954162598, "Pretrain/Loss (Raw)": 2.1404786109924316, "Pretrain/Step": 2561, "Pretrain/Step Time": 8.885283073410392} +{"Pretrain/Learning Rate": 4.2896906465661623e-05, "Pretrain/Loss": 2.0927019119262695, "Pretrain/Loss (Raw)": 2.059466600418091, "Pretrain/Step": 2562, "Pretrain/Step Time": 8.887403678148985} +{"Pretrain/Learning Rate": 4.289097757369892e-05, "Pretrain/Loss": 2.092252016067505, "Pretrain/Loss (Raw)": 1.9647419452667236, "Pretrain/Step": 2563, "Pretrain/Step Time": 8.883046383038163} +{"Pretrain/Learning Rate": 4.288504661846437e-05, "Pretrain/Loss": 2.095104217529297, "Pretrain/Loss (Raw)": 2.374728202819824, "Pretrain/Step": 2564, "Pretrain/Step Time": 8.875453876331449} +{"Pretrain/Learning Rate": 4.2879113600641976e-05, "Pretrain/Loss": 2.095733642578125, "Pretrain/Loss (Raw)": 2.134082317352295, "Pretrain/Step": 2565, "Pretrain/Step Time": 8.887723987922072} +{"Pretrain/Learning Rate": 4.287317852091595e-05, "Pretrain/Loss": 2.093843936920166, "Pretrain/Loss (Raw)": 2.0330026149749756, "Pretrain/Step": 2566, "Pretrain/Step Time": 8.885893220081925} +{"Pretrain/Learning Rate": 4.2867241379970754e-05, "Pretrain/Loss": 2.094165086746216, "Pretrain/Loss (Raw)": 2.160310983657837, "Pretrain/Step": 2567, "Pretrain/Step Time": 8.887204691767693} +{"Pretrain/Learning Rate": 4.2861302178491094e-05, "Pretrain/Loss": 2.095022439956665, "Pretrain/Loss (Raw)": 2.157499074935913, "Pretrain/Step": 2568, "Pretrain/Step Time": 8.882721584290266} +{"Pretrain/Learning Rate": 4.28553609171619e-05, "Pretrain/Loss": 2.09517240524292, "Pretrain/Loss (Raw)": 2.041541576385498, "Pretrain/Step": 2569, "Pretrain/Step Time": 8.885210840031505} +{"Pretrain/Learning Rate": 4.284941759666835e-05, "Pretrain/Loss": 2.0940136909484863, "Pretrain/Loss (Raw)": 2.006035804748535, "Pretrain/Step": 2570, "Pretrain/Step Time": 8.885804368183017} +{"Pretrain/Learning Rate": 4.2843472217695844e-05, "Pretrain/Loss": 2.0945143699645996, "Pretrain/Loss (Raw)": 2.113016128540039, "Pretrain/Step": 2571, "Pretrain/Step Time": 8.885085716843605} +{"Pretrain/Learning Rate": 4.283752478093005e-05, "Pretrain/Loss": 2.0950379371643066, "Pretrain/Loss (Raw)": 2.165558338165283, "Pretrain/Step": 2572, "Pretrain/Step Time": 8.887869810685515} +{"Pretrain/Learning Rate": 4.283157528705683e-05, "Pretrain/Loss": 2.0940215587615967, "Pretrain/Loss (Raw)": 2.0480258464813232, "Pretrain/Step": 2573, "Pretrain/Step Time": 8.886478776112199} +{"Pretrain/Learning Rate": 4.2825623736762344e-05, "Pretrain/Loss": 2.0933432579040527, "Pretrain/Loss (Raw)": 2.022261381149292, "Pretrain/Step": 2574, "Pretrain/Step Time": 8.887311032041907} +{"Pretrain/Learning Rate": 4.2819670130732926e-05, "Pretrain/Loss": 2.0943188667297363, "Pretrain/Loss (Raw)": 2.248441457748413, "Pretrain/Step": 2575, "Pretrain/Step Time": 8.884427186101675} +{"Pretrain/Learning Rate": 4.2813714469655176e-05, "Pretrain/Loss": 2.0946428775787354, "Pretrain/Loss (Raw)": 2.242175817489624, "Pretrain/Step": 2576, "Pretrain/Step Time": 8.882843874394894} +{"Pretrain/Learning Rate": 4.280775675421593e-05, "Pretrain/Loss": 2.093618392944336, "Pretrain/Loss (Raw)": 1.8811017274856567, "Pretrain/Step": 2577, "Pretrain/Step Time": 8.888994066044688} +{"Pretrain/Learning Rate": 4.280179698510226e-05, "Pretrain/Loss": 2.0941214561462402, "Pretrain/Loss (Raw)": 2.1862363815307617, "Pretrain/Step": 2578, "Pretrain/Step Time": 8.88828825391829} +{"Pretrain/Learning Rate": 4.279583516300148e-05, "Pretrain/Loss": 2.0941970348358154, "Pretrain/Loss (Raw)": 2.064943790435791, "Pretrain/Step": 2579, "Pretrain/Step Time": 8.887065641582012} +{"Pretrain/Learning Rate": 4.2789871288601136e-05, "Pretrain/Loss": 2.0924813747406006, "Pretrain/Loss (Raw)": 1.8827799558639526, "Pretrain/Step": 2580, "Pretrain/Step Time": 8.893520956858993} +{"Pretrain/Learning Rate": 4.2783905362589e-05, "Pretrain/Loss": 2.090291976928711, "Pretrain/Loss (Raw)": 1.8694909811019897, "Pretrain/Step": 2581, "Pretrain/Step Time": 8.88437238521874} +{"Pretrain/Learning Rate": 4.27779373856531e-05, "Pretrain/Loss": 2.0899877548217773, "Pretrain/Loss (Raw)": 2.129838466644287, "Pretrain/Step": 2582, "Pretrain/Step Time": 8.888483194634318} +{"Pretrain/Learning Rate": 4.277196735848169e-05, "Pretrain/Loss": 2.0900015830993652, "Pretrain/Loss (Raw)": 2.0597012042999268, "Pretrain/Step": 2583, "Pretrain/Step Time": 8.891950517892838} +{"Pretrain/Learning Rate": 4.2765995281763263e-05, "Pretrain/Loss": 2.0892953872680664, "Pretrain/Loss (Raw)": 2.0265839099884033, "Pretrain/Step": 2584, "Pretrain/Step Time": 8.885453503578901} +{"Pretrain/Learning Rate": 4.2760021156186534e-05, "Pretrain/Loss": 2.0918445587158203, "Pretrain/Loss (Raw)": 2.23248553276062, "Pretrain/Step": 2585, "Pretrain/Step Time": 8.884074857458472} +{"Pretrain/Learning Rate": 4.2754044982440486e-05, "Pretrain/Loss": 2.090343475341797, "Pretrain/Loss (Raw)": 1.9860891103744507, "Pretrain/Step": 2586, "Pretrain/Step Time": 8.886413076892495} +{"Pretrain/Learning Rate": 4.2748066761214305e-05, "Pretrain/Loss": 2.0884552001953125, "Pretrain/Loss (Raw)": 1.96503484249115, "Pretrain/Step": 2587, "Pretrain/Step Time": 8.89147754944861} +{"Pretrain/Learning Rate": 4.274208649319744e-05, "Pretrain/Loss": 2.0886850357055664, "Pretrain/Loss (Raw)": 2.109602689743042, "Pretrain/Step": 2588, "Pretrain/Step Time": 8.89048582687974} +{"Pretrain/Learning Rate": 4.273610417907955e-05, "Pretrain/Loss": 2.089616537094116, "Pretrain/Loss (Raw)": 2.163722276687622, "Pretrain/Step": 2589, "Pretrain/Step Time": 8.88115001656115} +{"Pretrain/Learning Rate": 4.2730119819550555e-05, "Pretrain/Loss": 2.0886921882629395, "Pretrain/Loss (Raw)": 2.040083169937134, "Pretrain/Step": 2590, "Pretrain/Step Time": 8.886199656873941} +{"Pretrain/Learning Rate": 4.2724133415300596e-05, "Pretrain/Loss": 2.088773727416992, "Pretrain/Loss (Raw)": 2.1941819190979004, "Pretrain/Step": 2591, "Pretrain/Step Time": 8.877264853566885} +{"Pretrain/Learning Rate": 4.271814496702005e-05, "Pretrain/Loss": 2.0855865478515625, "Pretrain/Loss (Raw)": 1.5892186164855957, "Pretrain/Step": 2592, "Pretrain/Step Time": 8.879088494926691} +{"Pretrain/Learning Rate": 4.2712154475399534e-05, "Pretrain/Loss": 2.0837106704711914, "Pretrain/Loss (Raw)": 1.8465371131896973, "Pretrain/Step": 2593, "Pretrain/Step Time": 8.880700754001737} +{"Pretrain/Learning Rate": 4.2706161941129906e-05, "Pretrain/Loss": 2.082587480545044, "Pretrain/Loss (Raw)": 2.053314208984375, "Pretrain/Step": 2594, "Pretrain/Step Time": 8.880818575620651} +{"Pretrain/Learning Rate": 4.270016736490225e-05, "Pretrain/Loss": 2.0822627544403076, "Pretrain/Loss (Raw)": 2.069584369659424, "Pretrain/Step": 2595, "Pretrain/Step Time": 8.87300773896277} +{"Pretrain/Learning Rate": 4.2694170747407886e-05, "Pretrain/Loss": 2.083616256713867, "Pretrain/Loss (Raw)": 2.119933843612671, "Pretrain/Step": 2596, "Pretrain/Step Time": 8.871536776423454} +{"Pretrain/Learning Rate": 4.268817208933837e-05, "Pretrain/Loss": 2.083402633666992, "Pretrain/Loss (Raw)": 2.0860180854797363, "Pretrain/Step": 2597, "Pretrain/Step Time": 8.86191312968731} +{"Pretrain/Learning Rate": 4.268217139138551e-05, "Pretrain/Loss": 2.08359956741333, "Pretrain/Loss (Raw)": 2.052199125289917, "Pretrain/Step": 2598, "Pretrain/Step Time": 8.86889566294849} +{"Pretrain/Learning Rate": 4.267616865424131e-05, "Pretrain/Loss": 2.0828728675842285, "Pretrain/Loss (Raw)": 2.0211644172668457, "Pretrain/Step": 2599, "Pretrain/Step Time": 8.866694018244743} +{"Pretrain/Learning Rate": 4.267016387859806e-05, "Pretrain/Loss": 2.0842947959899902, "Pretrain/Loss (Raw)": 2.2574377059936523, "Pretrain/Step": 2600, "Pretrain/Step Time": 8.864991832524538} +{"Pretrain/Learning Rate": 4.266415706514824e-05, "Pretrain/Loss": 2.0849335193634033, "Pretrain/Loss (Raw)": 2.1334192752838135, "Pretrain/Step": 2601, "Pretrain/Step Time": 8.87242404744029} +{"Pretrain/Learning Rate": 4.2658148214584585e-05, "Pretrain/Loss": 2.085421323776245, "Pretrain/Loss (Raw)": 2.140850067138672, "Pretrain/Step": 2602, "Pretrain/Step Time": 8.869826029986143} +{"Pretrain/Learning Rate": 4.265213732760008e-05, "Pretrain/Loss": 2.085224151611328, "Pretrain/Loss (Raw)": 2.0797817707061768, "Pretrain/Step": 2603, "Pretrain/Step Time": 8.863426832482219} +{"Pretrain/Learning Rate": 4.264612440488791e-05, "Pretrain/Loss": 2.086297035217285, "Pretrain/Loss (Raw)": 2.008329391479492, "Pretrain/Step": 2604, "Pretrain/Step Time": 8.865562738850713} +{"Pretrain/Learning Rate": 4.264010944714153e-05, "Pretrain/Loss": 2.087230682373047, "Pretrain/Loss (Raw)": 2.2715280055999756, "Pretrain/Step": 2605, "Pretrain/Step Time": 8.862258993089199} +{"Pretrain/Learning Rate": 4.263409245505461e-05, "Pretrain/Loss": 2.0895912647247314, "Pretrain/Loss (Raw)": 2.3687899112701416, "Pretrain/Step": 2606, "Pretrain/Step Time": 8.857194192707539} +{"Pretrain/Learning Rate": 4.262807342932105e-05, "Pretrain/Loss": 2.091418743133545, "Pretrain/Loss (Raw)": 1.9874521493911743, "Pretrain/Step": 2607, "Pretrain/Step Time": 8.860605819150805} +{"Pretrain/Learning Rate": 4.262205237063499e-05, "Pretrain/Loss": 2.090432643890381, "Pretrain/Loss (Raw)": 2.2175326347351074, "Pretrain/Step": 2608, "Pretrain/Step Time": 8.85712998919189} +{"Pretrain/Learning Rate": 4.2616029279690814e-05, "Pretrain/Loss": 2.0913586616516113, "Pretrain/Loss (Raw)": 2.1518101692199707, "Pretrain/Step": 2609, "Pretrain/Step Time": 8.867674631997943} +{"Pretrain/Learning Rate": 4.261000415718312e-05, "Pretrain/Loss": 2.0912346839904785, "Pretrain/Loss (Raw)": 2.159877300262451, "Pretrain/Step": 2610, "Pretrain/Step Time": 8.865707090124488} +{"Pretrain/Learning Rate": 4.260397700380679e-05, "Pretrain/Loss": 2.0889551639556885, "Pretrain/Loss (Raw)": 2.185683012008667, "Pretrain/Step": 2611, "Pretrain/Step Time": 8.862397154793143} +{"Pretrain/Learning Rate": 4.259794782025687e-05, "Pretrain/Loss": 2.089478015899658, "Pretrain/Loss (Raw)": 2.2038376331329346, "Pretrain/Step": 2612, "Pretrain/Step Time": 8.864133527502418} +{"Pretrain/Learning Rate": 4.2591916607228675e-05, "Pretrain/Loss": 2.086796760559082, "Pretrain/Loss (Raw)": 1.7205291986465454, "Pretrain/Step": 2613, "Pretrain/Step Time": 8.862081717699766} +{"Pretrain/Learning Rate": 4.2585883365417774e-05, "Pretrain/Loss": 2.085791826248169, "Pretrain/Loss (Raw)": 1.9807971715927124, "Pretrain/Step": 2614, "Pretrain/Step Time": 8.867589075118303} +{"Pretrain/Learning Rate": 4.2579848095519926e-05, "Pretrain/Loss": 2.086717367172241, "Pretrain/Loss (Raw)": 2.208481788635254, "Pretrain/Step": 2615, "Pretrain/Step Time": 8.86846394278109} +{"Pretrain/Learning Rate": 4.257381079823116e-05, "Pretrain/Loss": 2.0874414443969727, "Pretrain/Loss (Raw)": 2.108377695083618, "Pretrain/Step": 2616, "Pretrain/Step Time": 8.868592023849487} +{"Pretrain/Learning Rate": 4.2567771474247726e-05, "Pretrain/Loss": 2.088277578353882, "Pretrain/Loss (Raw)": 2.0912585258483887, "Pretrain/Step": 2617, "Pretrain/Step Time": 8.864857289940119} +{"Pretrain/Learning Rate": 4.2561730124266094e-05, "Pretrain/Loss": 2.089251756668091, "Pretrain/Loss (Raw)": 2.152980327606201, "Pretrain/Step": 2618, "Pretrain/Step Time": 8.871440010145307} +{"Pretrain/Learning Rate": 4.255568674898301e-05, "Pretrain/Loss": 2.0894618034362793, "Pretrain/Loss (Raw)": 2.1738429069519043, "Pretrain/Step": 2619, "Pretrain/Step Time": 8.876680485904217} +{"Pretrain/Learning Rate": 4.254964134909538e-05, "Pretrain/Loss": 2.0876245498657227, "Pretrain/Loss (Raw)": 1.8483189344406128, "Pretrain/Step": 2620, "Pretrain/Step Time": 8.877454236149788} +{"Pretrain/Learning Rate": 4.254359392530043e-05, "Pretrain/Loss": 2.088815212249756, "Pretrain/Loss (Raw)": 2.077608585357666, "Pretrain/Step": 2621, "Pretrain/Step Time": 8.873074682429433} +{"Pretrain/Learning Rate": 4.2537544478295556e-05, "Pretrain/Loss": 2.089794158935547, "Pretrain/Loss (Raw)": 2.1136868000030518, "Pretrain/Step": 2622, "Pretrain/Step Time": 8.873638203367591} +{"Pretrain/Learning Rate": 4.253149300877841e-05, "Pretrain/Loss": 2.0904932022094727, "Pretrain/Loss (Raw)": 2.0788493156433105, "Pretrain/Step": 2623, "Pretrain/Step Time": 8.870657708495855} +{"Pretrain/Learning Rate": 4.252543951744688e-05, "Pretrain/Loss": 2.091325521469116, "Pretrain/Loss (Raw)": 2.0128402709960938, "Pretrain/Step": 2624, "Pretrain/Step Time": 8.870448797941208} +{"Pretrain/Learning Rate": 4.251938400499909e-05, "Pretrain/Loss": 2.090038537979126, "Pretrain/Loss (Raw)": 1.9361685514450073, "Pretrain/Step": 2625, "Pretrain/Step Time": 8.87860631197691} +{"Pretrain/Learning Rate": 4.251332647213337e-05, "Pretrain/Loss": 2.090453863143921, "Pretrain/Loss (Raw)": 2.1732282638549805, "Pretrain/Step": 2626, "Pretrain/Step Time": 8.878480622544885} +{"Pretrain/Learning Rate": 4.250726691954832e-05, "Pretrain/Loss": 2.0895769596099854, "Pretrain/Loss (Raw)": 2.0170931816101074, "Pretrain/Step": 2627, "Pretrain/Step Time": 8.878444319590926} +{"Pretrain/Learning Rate": 4.250120534794275e-05, "Pretrain/Loss": 2.089825391769409, "Pretrain/Loss (Raw)": 2.011779546737671, "Pretrain/Step": 2628, "Pretrain/Step Time": 8.873231299221516} +{"Pretrain/Learning Rate": 4.249514175801572e-05, "Pretrain/Loss": 2.0897884368896484, "Pretrain/Loss (Raw)": 2.1534228324890137, "Pretrain/Step": 2629, "Pretrain/Step Time": 8.877952013164759} +{"Pretrain/Learning Rate": 4.248907615046649e-05, "Pretrain/Loss": 2.091841459274292, "Pretrain/Loss (Raw)": 2.3010730743408203, "Pretrain/Step": 2630, "Pretrain/Step Time": 8.88057349435985} +{"Pretrain/Learning Rate": 4.24830085259946e-05, "Pretrain/Loss": 2.0922861099243164, "Pretrain/Loss (Raw)": 2.091529130935669, "Pretrain/Step": 2631, "Pretrain/Step Time": 8.882739558815956} +{"Pretrain/Learning Rate": 4.247693888529978e-05, "Pretrain/Loss": 2.092660427093506, "Pretrain/Loss (Raw)": 2.1224210262298584, "Pretrain/Step": 2632, "Pretrain/Step Time": 8.889345915988088} +{"Pretrain/Learning Rate": 4.247086722908201e-05, "Pretrain/Loss": 2.0911757946014404, "Pretrain/Loss (Raw)": 2.077056884765625, "Pretrain/Step": 2633, "Pretrain/Step Time": 8.882976854220033} +{"Pretrain/Learning Rate": 4.24647935580415e-05, "Pretrain/Loss": 2.089984893798828, "Pretrain/Loss (Raw)": 2.0583088397979736, "Pretrain/Step": 2634, "Pretrain/Step Time": 8.876527477055788} +{"Pretrain/Learning Rate": 4.2458717872878715e-05, "Pretrain/Loss": 2.08876895904541, "Pretrain/Loss (Raw)": 1.9969745874404907, "Pretrain/Step": 2635, "Pretrain/Step Time": 8.877654753625393} +{"Pretrain/Learning Rate": 4.245264017429431e-05, "Pretrain/Loss": 2.089262008666992, "Pretrain/Loss (Raw)": 2.168827533721924, "Pretrain/Step": 2636, "Pretrain/Step Time": 8.869419373571873} +{"Pretrain/Learning Rate": 4.2446560462989203e-05, "Pretrain/Loss": 2.0836234092712402, "Pretrain/Loss (Raw)": 1.7423642873764038, "Pretrain/Step": 2637, "Pretrain/Step Time": 8.877599028870463} +{"Pretrain/Learning Rate": 4.244047873966452e-05, "Pretrain/Loss": 2.084059238433838, "Pretrain/Loss (Raw)": 2.2655460834503174, "Pretrain/Step": 2638, "Pretrain/Step Time": 8.870028024539351} +{"Pretrain/Learning Rate": 4.2434395005021666e-05, "Pretrain/Loss": 2.084972858428955, "Pretrain/Loss (Raw)": 2.2590065002441406, "Pretrain/Step": 2639, "Pretrain/Step Time": 8.866707960143685} +{"Pretrain/Learning Rate": 4.242830925976221e-05, "Pretrain/Loss": 2.083843469619751, "Pretrain/Loss (Raw)": 1.941096305847168, "Pretrain/Step": 2640, "Pretrain/Step Time": 8.873827191069722} +{"Pretrain/Learning Rate": 4.2422221504588016e-05, "Pretrain/Loss": 2.0830330848693848, "Pretrain/Loss (Raw)": 1.9065215587615967, "Pretrain/Step": 2641, "Pretrain/Step Time": 8.87558657117188} +{"Pretrain/Learning Rate": 4.2416131740201134e-05, "Pretrain/Loss": 2.081637382507324, "Pretrain/Loss (Raw)": 1.9608397483825684, "Pretrain/Step": 2642, "Pretrain/Step Time": 8.876902300864458} +{"Pretrain/Learning Rate": 4.241003996730388e-05, "Pretrain/Loss": 2.0831151008605957, "Pretrain/Loss (Raw)": 2.105757236480713, "Pretrain/Step": 2643, "Pretrain/Step Time": 8.873774508014321} +{"Pretrain/Learning Rate": 4.240394618659878e-05, "Pretrain/Loss": 2.083150863647461, "Pretrain/Loss (Raw)": 2.102557897567749, "Pretrain/Step": 2644, "Pretrain/Step Time": 8.87853767722845} +{"Pretrain/Learning Rate": 4.2397850398788586e-05, "Pretrain/Loss": 2.0819597244262695, "Pretrain/Loss (Raw)": 1.9533499479293823, "Pretrain/Step": 2645, "Pretrain/Step Time": 8.876097455620766} +{"Pretrain/Learning Rate": 4.239175260457631e-05, "Pretrain/Loss": 2.0814566612243652, "Pretrain/Loss (Raw)": 2.0772175788879395, "Pretrain/Step": 2646, "Pretrain/Step Time": 8.881621684879065} +{"Pretrain/Learning Rate": 4.2385652804665164e-05, "Pretrain/Loss": 2.0827689170837402, "Pretrain/Loss (Raw)": 2.219578504562378, "Pretrain/Step": 2647, "Pretrain/Step Time": 8.878358718007803} +{"Pretrain/Learning Rate": 4.237955099975862e-05, "Pretrain/Loss": 2.083272933959961, "Pretrain/Loss (Raw)": 2.0369012355804443, "Pretrain/Step": 2648, "Pretrain/Step Time": 8.880642730742693} +{"Pretrain/Learning Rate": 4.237344719056035e-05, "Pretrain/Loss": 2.082637310028076, "Pretrain/Loss (Raw)": 1.9662859439849854, "Pretrain/Step": 2649, "Pretrain/Step Time": 8.881391748785973} +{"Pretrain/Learning Rate": 4.236734137777429e-05, "Pretrain/Loss": 2.081472873687744, "Pretrain/Loss (Raw)": 2.0179243087768555, "Pretrain/Step": 2650, "Pretrain/Step Time": 8.887030178681016} +{"Pretrain/Learning Rate": 4.236123356210458e-05, "Pretrain/Loss": 2.0809459686279297, "Pretrain/Loss (Raw)": 2.111786127090454, "Pretrain/Step": 2651, "Pretrain/Step Time": 8.882092924788594} +{"Pretrain/Learning Rate": 4.235512374425561e-05, "Pretrain/Loss": 2.081216812133789, "Pretrain/Loss (Raw)": 2.13804030418396, "Pretrain/Step": 2652, "Pretrain/Step Time": 8.883350433781743} +{"Pretrain/Learning Rate": 4.234901192493199e-05, "Pretrain/Loss": 2.081954002380371, "Pretrain/Loss (Raw)": 2.2322630882263184, "Pretrain/Step": 2653, "Pretrain/Step Time": 8.88412350974977} +{"Pretrain/Learning Rate": 4.234289810483857e-05, "Pretrain/Loss": 2.081470489501953, "Pretrain/Loss (Raw)": 1.9716660976409912, "Pretrain/Step": 2654, "Pretrain/Step Time": 8.882723480463028} +{"Pretrain/Learning Rate": 4.233678228468041e-05, "Pretrain/Loss": 2.0812225341796875, "Pretrain/Loss (Raw)": 2.166948080062866, "Pretrain/Step": 2655, "Pretrain/Step Time": 8.879601441323757} +{"Pretrain/Learning Rate": 4.2330664465162826e-05, "Pretrain/Loss": 2.0802602767944336, "Pretrain/Loss (Raw)": 1.9225205183029175, "Pretrain/Step": 2656, "Pretrain/Step Time": 8.875769816339016} +{"Pretrain/Learning Rate": 4.232454464699135e-05, "Pretrain/Loss": 2.079801082611084, "Pretrain/Loss (Raw)": 2.0640461444854736, "Pretrain/Step": 2657, "Pretrain/Step Time": 8.884678803384304} +{"Pretrain/Learning Rate": 4.231842283087175e-05, "Pretrain/Loss": 2.078282356262207, "Pretrain/Loss (Raw)": 1.9623992443084717, "Pretrain/Step": 2658, "Pretrain/Step Time": 8.884901436045766} +{"Pretrain/Learning Rate": 4.231229901751002e-05, "Pretrain/Loss": 2.0783438682556152, "Pretrain/Loss (Raw)": 2.132298707962036, "Pretrain/Step": 2659, "Pretrain/Step Time": 8.885483058169484} +{"Pretrain/Learning Rate": 4.2306173207612394e-05, "Pretrain/Loss": 2.078892946243286, "Pretrain/Loss (Raw)": 2.225497245788574, "Pretrain/Step": 2660, "Pretrain/Step Time": 8.887436032295227} +{"Pretrain/Learning Rate": 4.230004540188533e-05, "Pretrain/Loss": 2.078479766845703, "Pretrain/Loss (Raw)": 2.1176161766052246, "Pretrain/Step": 2661, "Pretrain/Step Time": 8.892165454104543} +{"Pretrain/Learning Rate": 4.22939156010355e-05, "Pretrain/Loss": 2.0775227546691895, "Pretrain/Loss (Raw)": 2.0663223266601562, "Pretrain/Step": 2662, "Pretrain/Step Time": 8.889705399051309} +{"Pretrain/Learning Rate": 4.2287783805769824e-05, "Pretrain/Loss": 2.0767245292663574, "Pretrain/Loss (Raw)": 2.0243079662323, "Pretrain/Step": 2663, "Pretrain/Step Time": 8.886876309290528} +{"Pretrain/Learning Rate": 4.2281650016795466e-05, "Pretrain/Loss": 2.0753045082092285, "Pretrain/Loss (Raw)": 1.961618185043335, "Pretrain/Step": 2664, "Pretrain/Step Time": 8.891382897272706} +{"Pretrain/Learning Rate": 4.227551423481979e-05, "Pretrain/Loss": 2.0742568969726562, "Pretrain/Loss (Raw)": 2.0651543140411377, "Pretrain/Step": 2665, "Pretrain/Step Time": 8.88441171310842} +{"Pretrain/Learning Rate": 4.2269376460550414e-05, "Pretrain/Loss": 2.0726213455200195, "Pretrain/Loss (Raw)": 1.8034090995788574, "Pretrain/Step": 2666, "Pretrain/Step Time": 8.890100678429008} +{"Pretrain/Learning Rate": 4.226323669469516e-05, "Pretrain/Loss": 2.074449300765991, "Pretrain/Loss (Raw)": 2.0987050533294678, "Pretrain/Step": 2667, "Pretrain/Step Time": 8.88054297491908} +{"Pretrain/Learning Rate": 4.225709493796211e-05, "Pretrain/Loss": 2.075273275375366, "Pretrain/Loss (Raw)": 2.1310980319976807, "Pretrain/Step": 2668, "Pretrain/Step Time": 8.88409960642457} +{"Pretrain/Learning Rate": 4.225095119105956e-05, "Pretrain/Loss": 2.073657512664795, "Pretrain/Loss (Raw)": 2.070317268371582, "Pretrain/Step": 2669, "Pretrain/Step Time": 8.880197789520025} +{"Pretrain/Learning Rate": 4.224480545469603e-05, "Pretrain/Loss": 2.0771310329437256, "Pretrain/Loss (Raw)": 2.248361349105835, "Pretrain/Step": 2670, "Pretrain/Step Time": 8.886867612600327} +{"Pretrain/Learning Rate": 4.223865772958026e-05, "Pretrain/Loss": 2.078126907348633, "Pretrain/Loss (Raw)": 2.1733381748199463, "Pretrain/Step": 2671, "Pretrain/Step Time": 8.875193750485778} +{"Pretrain/Learning Rate": 4.223250801642126e-05, "Pretrain/Loss": 2.07719087600708, "Pretrain/Loss (Raw)": 2.001243829727173, "Pretrain/Step": 2672, "Pretrain/Step Time": 8.87130238302052} +{"Pretrain/Learning Rate": 4.222635631592823e-05, "Pretrain/Loss": 2.0785107612609863, "Pretrain/Loss (Raw)": 2.140103816986084, "Pretrain/Step": 2673, "Pretrain/Step Time": 8.869881486520171} +{"Pretrain/Learning Rate": 4.2220202628810614e-05, "Pretrain/Loss": 2.0789403915405273, "Pretrain/Loss (Raw)": 2.0819153785705566, "Pretrain/Step": 2674, "Pretrain/Step Time": 8.867678867653012} +{"Pretrain/Learning Rate": 4.2214046955778085e-05, "Pretrain/Loss": 2.0792078971862793, "Pretrain/Loss (Raw)": 2.168776035308838, "Pretrain/Step": 2675, "Pretrain/Step Time": 8.866410493850708} +{"Pretrain/Learning Rate": 4.2207889297540546e-05, "Pretrain/Loss": 2.079089641571045, "Pretrain/Loss (Raw)": 2.056392192840576, "Pretrain/Step": 2676, "Pretrain/Step Time": 8.870430413633585} +{"Pretrain/Learning Rate": 4.2201729654808136e-05, "Pretrain/Loss": 2.078559637069702, "Pretrain/Loss (Raw)": 1.953359603881836, "Pretrain/Step": 2677, "Pretrain/Step Time": 8.873570550233126} +{"Pretrain/Learning Rate": 4.21955680282912e-05, "Pretrain/Loss": 2.0778255462646484, "Pretrain/Loss (Raw)": 1.8568480014801025, "Pretrain/Step": 2678, "Pretrain/Step Time": 8.86777887120843} +{"Pretrain/Learning Rate": 4.218940441870033e-05, "Pretrain/Loss": 2.0783915519714355, "Pretrain/Loss (Raw)": 2.0928518772125244, "Pretrain/Step": 2679, "Pretrain/Step Time": 8.873008413240314} +{"Pretrain/Learning Rate": 4.218323882674634e-05, "Pretrain/Loss": 2.076744318008423, "Pretrain/Loss (Raw)": 2.0239100456237793, "Pretrain/Step": 2680, "Pretrain/Step Time": 8.86251256801188} +{"Pretrain/Learning Rate": 4.217707125314029e-05, "Pretrain/Loss": 2.077090263366699, "Pretrain/Loss (Raw)": 2.1067192554473877, "Pretrain/Step": 2681, "Pretrain/Step Time": 8.86591929756105} +{"Pretrain/Learning Rate": 4.217090169859343e-05, "Pretrain/Loss": 2.075310230255127, "Pretrain/Loss (Raw)": 1.8409875631332397, "Pretrain/Step": 2682, "Pretrain/Step Time": 8.862870814278722} +{"Pretrain/Learning Rate": 4.216473016381728e-05, "Pretrain/Loss": 2.0762405395507812, "Pretrain/Loss (Raw)": 2.157503366470337, "Pretrain/Step": 2683, "Pretrain/Step Time": 8.863483989611268} +{"Pretrain/Learning Rate": 4.215855664952356e-05, "Pretrain/Loss": 2.075568675994873, "Pretrain/Loss (Raw)": 2.109196901321411, "Pretrain/Step": 2684, "Pretrain/Step Time": 8.864705987274647} +{"Pretrain/Learning Rate": 4.215238115642424e-05, "Pretrain/Loss": 2.0761194229125977, "Pretrain/Loss (Raw)": 2.1537117958068848, "Pretrain/Step": 2685, "Pretrain/Step Time": 8.862141346558928} +{"Pretrain/Learning Rate": 4.2146203685231495e-05, "Pretrain/Loss": 2.0750951766967773, "Pretrain/Loss (Raw)": 2.0638837814331055, "Pretrain/Step": 2686, "Pretrain/Step Time": 8.867692401632667} +{"Pretrain/Learning Rate": 4.214002423665775e-05, "Pretrain/Loss": 2.0734474658966064, "Pretrain/Loss (Raw)": 1.9258326292037964, "Pretrain/Step": 2687, "Pretrain/Step Time": 8.865491146221757} +{"Pretrain/Learning Rate": 4.213384281141563e-05, "Pretrain/Loss": 2.0746006965637207, "Pretrain/Loss (Raw)": 2.190016984939575, "Pretrain/Step": 2688, "Pretrain/Step Time": 8.85836936533451} +{"Pretrain/Learning Rate": 4.212765941021804e-05, "Pretrain/Loss": 2.074951410293579, "Pretrain/Loss (Raw)": 2.1853649616241455, "Pretrain/Step": 2689, "Pretrain/Step Time": 8.863819969817996} +{"Pretrain/Learning Rate": 4.212147403377805e-05, "Pretrain/Loss": 2.073986530303955, "Pretrain/Loss (Raw)": 1.9359588623046875, "Pretrain/Step": 2690, "Pretrain/Step Time": 8.860833859071136} +{"Pretrain/Learning Rate": 4.2115286682808995e-05, "Pretrain/Loss": 2.0759425163269043, "Pretrain/Loss (Raw)": 2.2150981426239014, "Pretrain/Step": 2691, "Pretrain/Step Time": 8.859466139227152} +{"Pretrain/Learning Rate": 4.210909735802442e-05, "Pretrain/Loss": 2.07485294342041, "Pretrain/Loss (Raw)": 2.2352652549743652, "Pretrain/Step": 2692, "Pretrain/Step Time": 8.86603819206357} +{"Pretrain/Learning Rate": 4.210290606013812e-05, "Pretrain/Loss": 2.0741729736328125, "Pretrain/Loss (Raw)": 2.0470194816589355, "Pretrain/Step": 2693, "Pretrain/Step Time": 8.859436139464378} +{"Pretrain/Learning Rate": 4.209671278986412e-05, "Pretrain/Loss": 2.07490611076355, "Pretrain/Loss (Raw)": 2.1268672943115234, "Pretrain/Step": 2694, "Pretrain/Step Time": 8.863982355222106} +{"Pretrain/Learning Rate": 4.209051754791662e-05, "Pretrain/Loss": 2.0746850967407227, "Pretrain/Loss (Raw)": 2.132014036178589, "Pretrain/Step": 2695, "Pretrain/Step Time": 8.86413506232202} +{"Pretrain/Learning Rate": 4.208432033501011e-05, "Pretrain/Loss": 2.073723316192627, "Pretrain/Loss (Raw)": 2.03438663482666, "Pretrain/Step": 2696, "Pretrain/Step Time": 8.868188951164484} +{"Pretrain/Learning Rate": 4.2078121151859276e-05, "Pretrain/Loss": 2.0750203132629395, "Pretrain/Loss (Raw)": 2.207540512084961, "Pretrain/Step": 2697, "Pretrain/Step Time": 8.86490834504366} +{"Pretrain/Learning Rate": 4.2071919999179036e-05, "Pretrain/Loss": 2.074955701828003, "Pretrain/Loss (Raw)": 1.9977943897247314, "Pretrain/Step": 2698, "Pretrain/Step Time": 8.865932766348124} +{"Pretrain/Learning Rate": 4.206571687768454e-05, "Pretrain/Loss": 2.0746560096740723, "Pretrain/Loss (Raw)": 2.074659585952759, "Pretrain/Step": 2699, "Pretrain/Step Time": 8.861610604450107} +{"Pretrain/Learning Rate": 4.2059511788091146e-05, "Pretrain/Loss": 2.0729241371154785, "Pretrain/Loss (Raw)": 1.943876028060913, "Pretrain/Step": 2700, "Pretrain/Step Time": 8.864225743338466} +{"Pretrain/Learning Rate": 4.205330473111447e-05, "Pretrain/Loss": 2.0726046562194824, "Pretrain/Loss (Raw)": 2.0071020126342773, "Pretrain/Step": 2701, "Pretrain/Step Time": 8.865858554840088} +{"Pretrain/Learning Rate": 4.204709570747034e-05, "Pretrain/Loss": 2.0723750591278076, "Pretrain/Loss (Raw)": 1.9928799867630005, "Pretrain/Step": 2702, "Pretrain/Step Time": 8.871282059699297} +{"Pretrain/Learning Rate": 4.2040884717874804e-05, "Pretrain/Loss": 2.0711379051208496, "Pretrain/Loss (Raw)": 2.090090274810791, "Pretrain/Step": 2703, "Pretrain/Step Time": 8.870689112693071} +{"Pretrain/Learning Rate": 4.203467176304414e-05, "Pretrain/Loss": 2.0696661472320557, "Pretrain/Loss (Raw)": 2.0538196563720703, "Pretrain/Step": 2704, "Pretrain/Step Time": 8.874892067164183} +{"Pretrain/Learning Rate": 4.202845684369486e-05, "Pretrain/Loss": 2.071105480194092, "Pretrain/Loss (Raw)": 2.0653340816497803, "Pretrain/Step": 2705, "Pretrain/Step Time": 8.868086997419596} +{"Pretrain/Learning Rate": 4.202223996054369e-05, "Pretrain/Loss": 2.07110595703125, "Pretrain/Loss (Raw)": 2.1862876415252686, "Pretrain/Step": 2706, "Pretrain/Step Time": 8.867051096633077} +{"Pretrain/Learning Rate": 4.20160211143076e-05, "Pretrain/Loss": 2.0707147121429443, "Pretrain/Loss (Raw)": 2.0148491859436035, "Pretrain/Step": 2707, "Pretrain/Step Time": 8.878331493586302} +{"Pretrain/Learning Rate": 4.200980030570377e-05, "Pretrain/Loss": 2.072131633758545, "Pretrain/Loss (Raw)": 2.0641582012176514, "Pretrain/Step": 2708, "Pretrain/Step Time": 8.869488021358848} +{"Pretrain/Learning Rate": 4.2003577535449624e-05, "Pretrain/Loss": 2.0712575912475586, "Pretrain/Loss (Raw)": 1.7576055526733398, "Pretrain/Step": 2709, "Pretrain/Step Time": 8.876323586329818} +{"Pretrain/Learning Rate": 4.199735280426279e-05, "Pretrain/Loss": 2.071739435195923, "Pretrain/Loss (Raw)": 2.191521167755127, "Pretrain/Step": 2710, "Pretrain/Step Time": 8.869360556825995} +{"Pretrain/Learning Rate": 4.199112611286113e-05, "Pretrain/Loss": 2.070387363433838, "Pretrain/Loss (Raw)": 1.8866627216339111, "Pretrain/Step": 2711, "Pretrain/Step Time": 8.867733178660274} +{"Pretrain/Learning Rate": 4.1984897461962754e-05, "Pretrain/Loss": 2.0716652870178223, "Pretrain/Loss (Raw)": 2.190124034881592, "Pretrain/Step": 2712, "Pretrain/Step Time": 8.868514196947217} +{"Pretrain/Learning Rate": 4.197866685228596e-05, "Pretrain/Loss": 2.0712106227874756, "Pretrain/Loss (Raw)": 2.174299955368042, "Pretrain/Step": 2713, "Pretrain/Step Time": 8.869321271777153} +{"Pretrain/Learning Rate": 4.19724342845493e-05, "Pretrain/Loss": 2.069798707962036, "Pretrain/Loss (Raw)": 1.8053687810897827, "Pretrain/Step": 2714, "Pretrain/Step Time": 8.868811989203095} +{"Pretrain/Learning Rate": 4.1966199759471535e-05, "Pretrain/Loss": 2.0681562423706055, "Pretrain/Loss (Raw)": 1.7547909021377563, "Pretrain/Step": 2715, "Pretrain/Step Time": 8.864699266850948} +{"Pretrain/Learning Rate": 4.195996327777167e-05, "Pretrain/Loss": 2.0686731338500977, "Pretrain/Loss (Raw)": 2.1757469177246094, "Pretrain/Step": 2716, "Pretrain/Step Time": 8.864652274176478} +{"Pretrain/Learning Rate": 4.195372484016893e-05, "Pretrain/Loss": 2.0679681301116943, "Pretrain/Loss (Raw)": 2.0734810829162598, "Pretrain/Step": 2717, "Pretrain/Step Time": 8.869401670992374} +{"Pretrain/Learning Rate": 4.1947484447382746e-05, "Pretrain/Loss": 2.066148519515991, "Pretrain/Loss (Raw)": 1.8071866035461426, "Pretrain/Step": 2718, "Pretrain/Step Time": 8.866893757134676} +{"Pretrain/Learning Rate": 4.194124210013279e-05, "Pretrain/Loss": 2.065561532974243, "Pretrain/Loss (Raw)": 2.1190690994262695, "Pretrain/Step": 2719, "Pretrain/Step Time": 8.873758496716619} +{"Pretrain/Learning Rate": 4.1934997799138976e-05, "Pretrain/Loss": 2.0703556537628174, "Pretrain/Loss (Raw)": 2.2028543949127197, "Pretrain/Step": 2720, "Pretrain/Step Time": 8.869611345231533} +{"Pretrain/Learning Rate": 4.192875154512141e-05, "Pretrain/Loss": 2.0718135833740234, "Pretrain/Loss (Raw)": 2.0331413745880127, "Pretrain/Step": 2721, "Pretrain/Step Time": 8.86698011867702} +{"Pretrain/Learning Rate": 4.192250333880045e-05, "Pretrain/Loss": 2.073880195617676, "Pretrain/Loss (Raw)": 2.317854404449463, "Pretrain/Step": 2722, "Pretrain/Step Time": 8.87916175276041} +{"Pretrain/Learning Rate": 4.191625318089666e-05, "Pretrain/Loss": 2.074469566345215, "Pretrain/Loss (Raw)": 2.1450088024139404, "Pretrain/Step": 2723, "Pretrain/Step Time": 8.87905177474022} +{"Pretrain/Learning Rate": 4.191000107213084e-05, "Pretrain/Loss": 2.074258804321289, "Pretrain/Loss (Raw)": 2.092959403991699, "Pretrain/Step": 2724, "Pretrain/Step Time": 8.879102565348148} +{"Pretrain/Learning Rate": 4.190374701322401e-05, "Pretrain/Loss": 2.074151039123535, "Pretrain/Loss (Raw)": 2.072206735610962, "Pretrain/Step": 2725, "Pretrain/Step Time": 8.878216607496142} +{"Pretrain/Learning Rate": 4.1897491004897435e-05, "Pretrain/Loss": 2.074458122253418, "Pretrain/Loss (Raw)": 2.09151291847229, "Pretrain/Step": 2726, "Pretrain/Step Time": 8.87751848064363} +{"Pretrain/Learning Rate": 4.189123304787256e-05, "Pretrain/Loss": 2.0746099948883057, "Pretrain/Loss (Raw)": 2.040635824203491, "Pretrain/Step": 2727, "Pretrain/Step Time": 8.875753344967961} +{"Pretrain/Learning Rate": 4.1884973142871096e-05, "Pretrain/Loss": 2.074524402618408, "Pretrain/Loss (Raw)": 2.2464499473571777, "Pretrain/Step": 2728, "Pretrain/Step Time": 8.877110185101628} +{"Pretrain/Learning Rate": 4.187871129061498e-05, "Pretrain/Loss": 2.07493257522583, "Pretrain/Loss (Raw)": 2.185689687728882, "Pretrain/Step": 2729, "Pretrain/Step Time": 8.868176739662886} +{"Pretrain/Learning Rate": 4.187244749182633e-05, "Pretrain/Loss": 2.074110984802246, "Pretrain/Loss (Raw)": 2.035698652267456, "Pretrain/Step": 2730, "Pretrain/Step Time": 8.876608841121197} +{"Pretrain/Learning Rate": 4.1866181747227526e-05, "Pretrain/Loss": 2.0745575428009033, "Pretrain/Loss (Raw)": 2.1369175910949707, "Pretrain/Step": 2731, "Pretrain/Step Time": 8.880539011210203} +{"Pretrain/Learning Rate": 4.185991405754118e-05, "Pretrain/Loss": 2.074955463409424, "Pretrain/Loss (Raw)": 2.0592613220214844, "Pretrain/Step": 2732, "Pretrain/Step Time": 8.883567996323109} +{"Pretrain/Learning Rate": 4.185364442349008e-05, "Pretrain/Loss": 2.0739247798919678, "Pretrain/Loss (Raw)": 2.139594793319702, "Pretrain/Step": 2733, "Pretrain/Step Time": 8.886553084477782} +{"Pretrain/Learning Rate": 4.184737284579731e-05, "Pretrain/Loss": 2.0718932151794434, "Pretrain/Loss (Raw)": 2.108741283416748, "Pretrain/Step": 2734, "Pretrain/Step Time": 8.889779737219214} +{"Pretrain/Learning Rate": 4.18410993251861e-05, "Pretrain/Loss": 2.0726776123046875, "Pretrain/Loss (Raw)": 2.087904453277588, "Pretrain/Step": 2735, "Pretrain/Step Time": 8.886585671454668} +{"Pretrain/Learning Rate": 4.183482386237996e-05, "Pretrain/Loss": 2.0719711780548096, "Pretrain/Loss (Raw)": 2.127075433731079, "Pretrain/Step": 2736, "Pretrain/Step Time": 8.889805752784014} +{"Pretrain/Learning Rate": 4.182854645810261e-05, "Pretrain/Loss": 2.0722694396972656, "Pretrain/Loss (Raw)": 2.1899971961975098, "Pretrain/Step": 2737, "Pretrain/Step Time": 8.882856639102101} +{"Pretrain/Learning Rate": 4.182226711307798e-05, "Pretrain/Loss": 2.07211971282959, "Pretrain/Loss (Raw)": 2.1406943798065186, "Pretrain/Step": 2738, "Pretrain/Step Time": 8.88336249627173} +{"Pretrain/Learning Rate": 4.181598582803024e-05, "Pretrain/Loss": 2.071408987045288, "Pretrain/Loss (Raw)": 2.0947158336639404, "Pretrain/Step": 2739, "Pretrain/Step Time": 8.887931134551764} +{"Pretrain/Learning Rate": 4.1809702603683776e-05, "Pretrain/Loss": 2.070309638977051, "Pretrain/Loss (Raw)": 2.0631446838378906, "Pretrain/Step": 2740, "Pretrain/Step Time": 8.884443370625377} +{"Pretrain/Learning Rate": 4.1803417440763196e-05, "Pretrain/Loss": 2.0727367401123047, "Pretrain/Loss (Raw)": 2.0311596393585205, "Pretrain/Step": 2741, "Pretrain/Step Time": 8.888342330232263} +{"Pretrain/Learning Rate": 4.179713033999333e-05, "Pretrain/Loss": 2.0739033222198486, "Pretrain/Loss (Raw)": 2.130125045776367, "Pretrain/Step": 2742, "Pretrain/Step Time": 8.879058711230755} +{"Pretrain/Learning Rate": 4.1790841302099246e-05, "Pretrain/Loss": 2.07363224029541, "Pretrain/Loss (Raw)": 2.1737921237945557, "Pretrain/Step": 2743, "Pretrain/Step Time": 8.881404288113117} +{"Pretrain/Learning Rate": 4.1784550327806226e-05, "Pretrain/Loss": 2.075732707977295, "Pretrain/Loss (Raw)": 2.3772482872009277, "Pretrain/Step": 2744, "Pretrain/Step Time": 8.880893340334296} +{"Pretrain/Learning Rate": 4.177825741783977e-05, "Pretrain/Loss": 2.074758529663086, "Pretrain/Loss (Raw)": 1.9665594100952148, "Pretrain/Step": 2745, "Pretrain/Step Time": 8.890070661902428} +{"Pretrain/Learning Rate": 4.1771962572925606e-05, "Pretrain/Loss": 2.0747721195220947, "Pretrain/Loss (Raw)": 2.154733657836914, "Pretrain/Step": 2746, "Pretrain/Step Time": 8.884504895657301} +{"Pretrain/Learning Rate": 4.176566579378968e-05, "Pretrain/Loss": 2.073862075805664, "Pretrain/Loss (Raw)": 2.0573348999023438, "Pretrain/Step": 2747, "Pretrain/Step Time": 8.872746611014009} +{"Pretrain/Learning Rate": 4.175936708115818e-05, "Pretrain/Loss": 2.07488751411438, "Pretrain/Loss (Raw)": 1.9795880317687988, "Pretrain/Step": 2748, "Pretrain/Step Time": 8.877417251467705} +{"Pretrain/Learning Rate": 4.1753066435757494e-05, "Pretrain/Loss": 2.0759129524230957, "Pretrain/Loss (Raw)": 2.2088632583618164, "Pretrain/Step": 2749, "Pretrain/Step Time": 8.872234785929322} +{"Pretrain/Learning Rate": 4.1746763858314244e-05, "Pretrain/Loss": 2.0755810737609863, "Pretrain/Loss (Raw)": 2.071226119995117, "Pretrain/Step": 2750, "Pretrain/Step Time": 8.876729965209961} +{"Pretrain/Learning Rate": 4.174045934955527e-05, "Pretrain/Loss": 2.0760908126831055, "Pretrain/Loss (Raw)": 2.1440610885620117, "Pretrain/Step": 2751, "Pretrain/Step Time": 8.878318836912513} +{"Pretrain/Learning Rate": 4.173415291020764e-05, "Pretrain/Loss": 2.078313112258911, "Pretrain/Loss (Raw)": 2.297314167022705, "Pretrain/Step": 2752, "Pretrain/Step Time": 8.878253666684031} +{"Pretrain/Learning Rate": 4.172784454099865e-05, "Pretrain/Loss": 2.0795435905456543, "Pretrain/Loss (Raw)": 2.0936360359191895, "Pretrain/Step": 2753, "Pretrain/Step Time": 8.868818614631891} +{"Pretrain/Learning Rate": 4.172153424265579e-05, "Pretrain/Loss": 2.07800030708313, "Pretrain/Loss (Raw)": 1.9757128953933716, "Pretrain/Step": 2754, "Pretrain/Step Time": 8.872482717037201} +{"Pretrain/Learning Rate": 4.171522201590682e-05, "Pretrain/Loss": 2.0784683227539062, "Pretrain/Loss (Raw)": 2.076986074447632, "Pretrain/Step": 2755, "Pretrain/Step Time": 8.865278942510486} +{"Pretrain/Learning Rate": 4.170890786147967e-05, "Pretrain/Loss": 2.080110788345337, "Pretrain/Loss (Raw)": 2.2220242023468018, "Pretrain/Step": 2756, "Pretrain/Step Time": 8.867773029953241} +{"Pretrain/Learning Rate": 4.170259178010254e-05, "Pretrain/Loss": 2.0798683166503906, "Pretrain/Loss (Raw)": 2.1223905086517334, "Pretrain/Step": 2757, "Pretrain/Step Time": 8.862554110586643} +{"Pretrain/Learning Rate": 4.169627377250382e-05, "Pretrain/Loss": 2.0792417526245117, "Pretrain/Loss (Raw)": 2.220863103866577, "Pretrain/Step": 2758, "Pretrain/Step Time": 8.863123759627342} +{"Pretrain/Learning Rate": 4.1689953839412124e-05, "Pretrain/Loss": 2.079799175262451, "Pretrain/Loss (Raw)": 2.162896156311035, "Pretrain/Step": 2759, "Pretrain/Step Time": 8.868089554831386} +{"Pretrain/Learning Rate": 4.1683631981556314e-05, "Pretrain/Loss": 2.0793962478637695, "Pretrain/Loss (Raw)": 2.070850372314453, "Pretrain/Step": 2760, "Pretrain/Step Time": 8.857434274628758} +{"Pretrain/Learning Rate": 4.167730819966545e-05, "Pretrain/Loss": 2.078033447265625, "Pretrain/Loss (Raw)": 1.9026176929473877, "Pretrain/Step": 2761, "Pretrain/Step Time": 8.86345205642283} +{"Pretrain/Learning Rate": 4.167098249446881e-05, "Pretrain/Loss": 2.0810742378234863, "Pretrain/Loss (Raw)": 2.4475185871124268, "Pretrain/Step": 2762, "Pretrain/Step Time": 8.86053067445755} +{"Pretrain/Learning Rate": 4.166465486669592e-05, "Pretrain/Loss": 2.0821218490600586, "Pretrain/Loss (Raw)": 2.1310830116271973, "Pretrain/Step": 2763, "Pretrain/Step Time": 8.861276283860207} +{"Pretrain/Learning Rate": 4.16583253170765e-05, "Pretrain/Loss": 2.0816333293914795, "Pretrain/Loss (Raw)": 2.106262445449829, "Pretrain/Step": 2764, "Pretrain/Step Time": 8.868379382416606} +{"Pretrain/Learning Rate": 4.165199384634051e-05, "Pretrain/Loss": 2.085573673248291, "Pretrain/Loss (Raw)": 2.2467427253723145, "Pretrain/Step": 2765, "Pretrain/Step Time": 8.860677056014538} +{"Pretrain/Learning Rate": 4.164566045521812e-05, "Pretrain/Loss": 2.0858867168426514, "Pretrain/Loss (Raw)": 2.3056259155273438, "Pretrain/Step": 2766, "Pretrain/Step Time": 8.869051681831479} +{"Pretrain/Learning Rate": 4.163932514443973e-05, "Pretrain/Loss": 2.0847949981689453, "Pretrain/Loss (Raw)": 2.1192514896392822, "Pretrain/Step": 2767, "Pretrain/Step Time": 8.873255616053939} +{"Pretrain/Learning Rate": 4.163298791473596e-05, "Pretrain/Loss": 2.0867912769317627, "Pretrain/Loss (Raw)": 2.1966333389282227, "Pretrain/Step": 2768, "Pretrain/Step Time": 8.862619386985898} +{"Pretrain/Learning Rate": 4.1626648766837654e-05, "Pretrain/Loss": 2.087824821472168, "Pretrain/Loss (Raw)": 2.03883695602417, "Pretrain/Step": 2769, "Pretrain/Step Time": 8.86492408812046} +{"Pretrain/Learning Rate": 4.162030770147585e-05, "Pretrain/Loss": 2.0893821716308594, "Pretrain/Loss (Raw)": 2.160172939300537, "Pretrain/Step": 2770, "Pretrain/Step Time": 8.864794785156846} +{"Pretrain/Learning Rate": 4.161396471938185e-05, "Pretrain/Loss": 2.0884580612182617, "Pretrain/Loss (Raw)": 1.9874355792999268, "Pretrain/Step": 2771, "Pretrain/Step Time": 8.870932392776012} +{"Pretrain/Learning Rate": 4.1607619821287154e-05, "Pretrain/Loss": 2.0877914428710938, "Pretrain/Loss (Raw)": 2.0172364711761475, "Pretrain/Step": 2772, "Pretrain/Step Time": 8.868734622374177} +{"Pretrain/Learning Rate": 4.160127300792348e-05, "Pretrain/Loss": 2.0891504287719727, "Pretrain/Loss (Raw)": 2.127295732498169, "Pretrain/Step": 2773, "Pretrain/Step Time": 8.871930044144392} +{"Pretrain/Learning Rate": 4.159492428002277e-05, "Pretrain/Loss": 2.090526580810547, "Pretrain/Loss (Raw)": 2.2533626556396484, "Pretrain/Step": 2774, "Pretrain/Step Time": 8.865250950679183} +{"Pretrain/Learning Rate": 4.1588573638317195e-05, "Pretrain/Loss": 2.0897979736328125, "Pretrain/Loss (Raw)": 2.1263279914855957, "Pretrain/Step": 2775, "Pretrain/Step Time": 8.87087407335639} +{"Pretrain/Learning Rate": 4.158222108353915e-05, "Pretrain/Loss": 2.091107130050659, "Pretrain/Loss (Raw)": 2.204477071762085, "Pretrain/Step": 2776, "Pretrain/Step Time": 8.868445262312889} +{"Pretrain/Learning Rate": 4.1575866616421224e-05, "Pretrain/Loss": 2.0906317234039307, "Pretrain/Loss (Raw)": 1.9054471254348755, "Pretrain/Step": 2777, "Pretrain/Step Time": 8.871460678055882} +{"Pretrain/Learning Rate": 4.156951023769625e-05, "Pretrain/Loss": 2.091219425201416, "Pretrain/Loss (Raw)": 2.0931568145751953, "Pretrain/Step": 2778, "Pretrain/Step Time": 8.865330774337053} +{"Pretrain/Learning Rate": 4.156315194809728e-05, "Pretrain/Loss": 2.0914535522460938, "Pretrain/Loss (Raw)": 2.141740083694458, "Pretrain/Step": 2779, "Pretrain/Step Time": 8.86809740588069} +{"Pretrain/Learning Rate": 4.1556791748357584e-05, "Pretrain/Loss": 2.09177303314209, "Pretrain/Loss (Raw)": 2.178936004638672, "Pretrain/Step": 2780, "Pretrain/Step Time": 8.864498380571604} +{"Pretrain/Learning Rate": 4.155042963921064e-05, "Pretrain/Loss": 2.090696096420288, "Pretrain/Loss (Raw)": 2.0944364070892334, "Pretrain/Step": 2781, "Pretrain/Step Time": 8.863376436755061} +{"Pretrain/Learning Rate": 4.1544065621390165e-05, "Pretrain/Loss": 2.0914807319641113, "Pretrain/Loss (Raw)": 2.0720574855804443, "Pretrain/Step": 2782, "Pretrain/Step Time": 8.872702600434422} +{"Pretrain/Learning Rate": 4.153769969563008e-05, "Pretrain/Loss": 2.090883255004883, "Pretrain/Loss (Raw)": 2.090506076812744, "Pretrain/Step": 2783, "Pretrain/Step Time": 8.872269889339805} +{"Pretrain/Learning Rate": 4.1531331862664545e-05, "Pretrain/Loss": 2.0900394916534424, "Pretrain/Loss (Raw)": 1.8144986629486084, "Pretrain/Step": 2784, "Pretrain/Step Time": 8.877380773425102} +{"Pretrain/Learning Rate": 4.1524962123227914e-05, "Pretrain/Loss": 2.0905349254608154, "Pretrain/Loss (Raw)": 2.1274726390838623, "Pretrain/Step": 2785, "Pretrain/Step Time": 8.868364138528705} +{"Pretrain/Learning Rate": 4.151859047805479e-05, "Pretrain/Loss": 2.09097957611084, "Pretrain/Loss (Raw)": 2.019303798675537, "Pretrain/Step": 2786, "Pretrain/Step Time": 8.872962526977062} +{"Pretrain/Learning Rate": 4.151221692787997e-05, "Pretrain/Loss": 2.0891761779785156, "Pretrain/Loss (Raw)": 1.9014540910720825, "Pretrain/Step": 2787, "Pretrain/Step Time": 8.868304355069995} +{"Pretrain/Learning Rate": 4.1505841473438485e-05, "Pretrain/Loss": 2.0891032218933105, "Pretrain/Loss (Raw)": 2.216172218322754, "Pretrain/Step": 2788, "Pretrain/Step Time": 8.869131252169609} +{"Pretrain/Learning Rate": 4.149946411546558e-05, "Pretrain/Loss": 2.0899527072906494, "Pretrain/Loss (Raw)": 2.226348638534546, "Pretrain/Step": 2789, "Pretrain/Step Time": 8.865835562348366} +{"Pretrain/Learning Rate": 4.1493084854696726e-05, "Pretrain/Loss": 2.0901284217834473, "Pretrain/Loss (Raw)": 2.088792085647583, "Pretrain/Step": 2790, "Pretrain/Step Time": 8.871624052524567} +{"Pretrain/Learning Rate": 4.1486703691867616e-05, "Pretrain/Loss": 2.089836597442627, "Pretrain/Loss (Raw)": 1.9869742393493652, "Pretrain/Step": 2791, "Pretrain/Step Time": 8.867894943803549} +{"Pretrain/Learning Rate": 4.148032062771414e-05, "Pretrain/Loss": 2.0905866622924805, "Pretrain/Loss (Raw)": 2.0576491355895996, "Pretrain/Step": 2792, "Pretrain/Step Time": 8.86844352260232} +{"Pretrain/Learning Rate": 4.147393566297244e-05, "Pretrain/Loss": 2.0908279418945312, "Pretrain/Loss (Raw)": 2.09603214263916, "Pretrain/Step": 2793, "Pretrain/Step Time": 8.867931559681892} +{"Pretrain/Learning Rate": 4.1467548798378847e-05, "Pretrain/Loss": 2.094785213470459, "Pretrain/Loss (Raw)": 2.309913158416748, "Pretrain/Step": 2794, "Pretrain/Step Time": 8.866339720785618} +{"Pretrain/Learning Rate": 4.1461160034669925e-05, "Pretrain/Loss": 2.0933432579040527, "Pretrain/Loss (Raw)": 1.9141223430633545, "Pretrain/Step": 2795, "Pretrain/Step Time": 8.866359235718846} +{"Pretrain/Learning Rate": 4.145476937258247e-05, "Pretrain/Loss": 2.092808723449707, "Pretrain/Loss (Raw)": 2.0627121925354004, "Pretrain/Step": 2796, "Pretrain/Step Time": 8.865235853940248} +{"Pretrain/Learning Rate": 4.144837681285346e-05, "Pretrain/Loss": 2.0930137634277344, "Pretrain/Loss (Raw)": 2.096564769744873, "Pretrain/Step": 2797, "Pretrain/Step Time": 8.874213002622128} +{"Pretrain/Learning Rate": 4.1441982356220144e-05, "Pretrain/Loss": 2.09114933013916, "Pretrain/Loss (Raw)": 2.009721040725708, "Pretrain/Step": 2798, "Pretrain/Step Time": 8.866854576393962} +{"Pretrain/Learning Rate": 4.1435586003419935e-05, "Pretrain/Loss": 2.0885558128356934, "Pretrain/Loss (Raw)": 1.8413578271865845, "Pretrain/Step": 2799, "Pretrain/Step Time": 8.872248696163297} +{"Pretrain/Learning Rate": 4.1429187755190504e-05, "Pretrain/Loss": 2.0895590782165527, "Pretrain/Loss (Raw)": 2.1296396255493164, "Pretrain/Step": 2800, "Pretrain/Step Time": 8.870332881808281} +{"Pretrain/Learning Rate": 4.1422787612269726e-05, "Pretrain/Loss": 2.0902950763702393, "Pretrain/Loss (Raw)": 2.2343249320983887, "Pretrain/Step": 2801, "Pretrain/Step Time": 8.872701356187463} +{"Pretrain/Learning Rate": 4.1416385575395686e-05, "Pretrain/Loss": 2.09199857711792, "Pretrain/Loss (Raw)": 2.2999908924102783, "Pretrain/Step": 2802, "Pretrain/Step Time": 8.872684147208929} +{"Pretrain/Learning Rate": 4.140998164530672e-05, "Pretrain/Loss": 2.0896291732788086, "Pretrain/Loss (Raw)": 1.8654495477676392, "Pretrain/Step": 2803, "Pretrain/Step Time": 8.870443949475884} +{"Pretrain/Learning Rate": 4.140357582274133e-05, "Pretrain/Loss": 2.091634511947632, "Pretrain/Loss (Raw)": 2.313096046447754, "Pretrain/Step": 2804, "Pretrain/Step Time": 8.868611462414265} +{"Pretrain/Learning Rate": 4.1397168108438286e-05, "Pretrain/Loss": 2.091481924057007, "Pretrain/Loss (Raw)": 1.9338312149047852, "Pretrain/Step": 2805, "Pretrain/Step Time": 8.87583688646555} +{"Pretrain/Learning Rate": 4.139075850313655e-05, "Pretrain/Loss": 2.092498302459717, "Pretrain/Loss (Raw)": 1.9869427680969238, "Pretrain/Step": 2806, "Pretrain/Step Time": 8.880534324795008} +{"Pretrain/Learning Rate": 4.1384347007575305e-05, "Pretrain/Loss": 2.092677354812622, "Pretrain/Loss (Raw)": 2.1157708168029785, "Pretrain/Step": 2807, "Pretrain/Step Time": 8.878567039966583} +{"Pretrain/Learning Rate": 4.137793362249396e-05, "Pretrain/Loss": 2.092787742614746, "Pretrain/Loss (Raw)": 2.038032293319702, "Pretrain/Step": 2808, "Pretrain/Step Time": 8.88021077401936} +{"Pretrain/Learning Rate": 4.137151834863213e-05, "Pretrain/Loss": 2.091243028640747, "Pretrain/Loss (Raw)": 1.9090207815170288, "Pretrain/Step": 2809, "Pretrain/Step Time": 8.88182513974607} +{"Pretrain/Learning Rate": 4.136510118672966e-05, "Pretrain/Loss": 2.0922040939331055, "Pretrain/Loss (Raw)": 1.963990330696106, "Pretrain/Step": 2810, "Pretrain/Step Time": 8.883028738200665} +{"Pretrain/Learning Rate": 4.135868213752661e-05, "Pretrain/Loss": 2.0925180912017822, "Pretrain/Loss (Raw)": 2.197676181793213, "Pretrain/Step": 2811, "Pretrain/Step Time": 8.881057422608137} +{"Pretrain/Learning Rate": 4.135226120176325e-05, "Pretrain/Loss": 2.09289288520813, "Pretrain/Loss (Raw)": 2.1571805477142334, "Pretrain/Step": 2812, "Pretrain/Step Time": 8.881653429940343} +{"Pretrain/Learning Rate": 4.134583838018007e-05, "Pretrain/Loss": 2.0933117866516113, "Pretrain/Loss (Raw)": 2.2073206901550293, "Pretrain/Step": 2813, "Pretrain/Step Time": 8.876094149425626} +{"Pretrain/Learning Rate": 4.133941367351779e-05, "Pretrain/Loss": 2.0940968990325928, "Pretrain/Loss (Raw)": 2.1643893718719482, "Pretrain/Step": 2814, "Pretrain/Step Time": 8.880835702642798} +{"Pretrain/Learning Rate": 4.133298708251733e-05, "Pretrain/Loss": 2.095231771469116, "Pretrain/Loss (Raw)": 2.071106433868408, "Pretrain/Step": 2815, "Pretrain/Step Time": 8.885494379326701} +{"Pretrain/Learning Rate": 4.132655860791983e-05, "Pretrain/Loss": 2.0943455696105957, "Pretrain/Loss (Raw)": 2.0765769481658936, "Pretrain/Step": 2816, "Pretrain/Step Time": 8.885885016992688} +{"Pretrain/Learning Rate": 4.132012825046666e-05, "Pretrain/Loss": 2.0926709175109863, "Pretrain/Loss (Raw)": 1.9710017442703247, "Pretrain/Step": 2817, "Pretrain/Step Time": 8.88313578441739} +{"Pretrain/Learning Rate": 4.13136960108994e-05, "Pretrain/Loss": 2.094247817993164, "Pretrain/Loss (Raw)": 2.137803077697754, "Pretrain/Step": 2818, "Pretrain/Step Time": 8.88084153458476} +{"Pretrain/Learning Rate": 4.130726188995985e-05, "Pretrain/Loss": 2.0930674076080322, "Pretrain/Loss (Raw)": 2.0640017986297607, "Pretrain/Step": 2819, "Pretrain/Step Time": 8.88493798673153} +{"Pretrain/Learning Rate": 4.1300825888390006e-05, "Pretrain/Loss": 2.093559741973877, "Pretrain/Loss (Raw)": 2.2983145713806152, "Pretrain/Step": 2820, "Pretrain/Step Time": 8.889114363119006} +{"Pretrain/Learning Rate": 4.1294388006932114e-05, "Pretrain/Loss": 2.0927233695983887, "Pretrain/Loss (Raw)": 1.9399255514144897, "Pretrain/Step": 2821, "Pretrain/Step Time": 8.882134994491935} +{"Pretrain/Learning Rate": 4.128794824632861e-05, "Pretrain/Loss": 2.0914649963378906, "Pretrain/Loss (Raw)": 1.965782880783081, "Pretrain/Step": 2822, "Pretrain/Step Time": 8.882171895354986} +{"Pretrain/Learning Rate": 4.1281506607322167e-05, "Pretrain/Loss": 2.0918996334075928, "Pretrain/Loss (Raw)": 2.1876697540283203, "Pretrain/Step": 2823, "Pretrain/Step Time": 8.878803078085184} +{"Pretrain/Learning Rate": 4.1275063090655666e-05, "Pretrain/Loss": 2.092686176300049, "Pretrain/Loss (Raw)": 2.1350972652435303, "Pretrain/Step": 2824, "Pretrain/Step Time": 8.877437736839056} +{"Pretrain/Learning Rate": 4.126861769707219e-05, "Pretrain/Loss": 2.0915908813476562, "Pretrain/Loss (Raw)": 2.067307949066162, "Pretrain/Step": 2825, "Pretrain/Step Time": 8.874385202303529} +{"Pretrain/Learning Rate": 4.126217042731507e-05, "Pretrain/Loss": 2.0915937423706055, "Pretrain/Loss (Raw)": 1.9981952905654907, "Pretrain/Step": 2826, "Pretrain/Step Time": 8.874972760677338} +{"Pretrain/Learning Rate": 4.125572128212781e-05, "Pretrain/Loss": 2.0915091037750244, "Pretrain/Loss (Raw)": 2.0637965202331543, "Pretrain/Step": 2827, "Pretrain/Step Time": 8.882335379719734} +{"Pretrain/Learning Rate": 4.124927026225419e-05, "Pretrain/Loss": 2.094752311706543, "Pretrain/Loss (Raw)": 2.358997344970703, "Pretrain/Step": 2828, "Pretrain/Step Time": 8.876710001379251} +{"Pretrain/Learning Rate": 4.124281736843815e-05, "Pretrain/Loss": 2.094114303588867, "Pretrain/Loss (Raw)": 1.9254353046417236, "Pretrain/Step": 2829, "Pretrain/Step Time": 8.877246154472232} +{"Pretrain/Learning Rate": 4.1236362601423865e-05, "Pretrain/Loss": 2.0922811031341553, "Pretrain/Loss (Raw)": 1.7582341432571411, "Pretrain/Step": 2830, "Pretrain/Step Time": 8.871295345947146} +{"Pretrain/Learning Rate": 4.122990596195574e-05, "Pretrain/Loss": 2.092236042022705, "Pretrain/Loss (Raw)": 2.0843310356140137, "Pretrain/Step": 2831, "Pretrain/Step Time": 8.876358987763524} +{"Pretrain/Learning Rate": 4.122344745077838e-05, "Pretrain/Loss": 2.0921730995178223, "Pretrain/Loss (Raw)": 2.0457870960235596, "Pretrain/Step": 2832, "Pretrain/Step Time": 8.866584978997707} +{"Pretrain/Learning Rate": 4.121698706863662e-05, "Pretrain/Loss": 2.0919668674468994, "Pretrain/Loss (Raw)": 2.0389223098754883, "Pretrain/Step": 2833, "Pretrain/Step Time": 8.866318898275495} +{"Pretrain/Learning Rate": 4.121052481627549e-05, "Pretrain/Loss": 2.0912375450134277, "Pretrain/Loss (Raw)": 2.0929198265075684, "Pretrain/Step": 2834, "Pretrain/Step Time": 8.876600788906217} +{"Pretrain/Learning Rate": 4.120406069444025e-05, "Pretrain/Loss": 2.0911307334899902, "Pretrain/Loss (Raw)": 2.0011534690856934, "Pretrain/Step": 2835, "Pretrain/Step Time": 8.864896604791284} +{"Pretrain/Learning Rate": 4.119759470387637e-05, "Pretrain/Loss": 2.090677261352539, "Pretrain/Loss (Raw)": 2.0061686038970947, "Pretrain/Step": 2836, "Pretrain/Step Time": 8.870964720845222} +{"Pretrain/Learning Rate": 4.1191126845329554e-05, "Pretrain/Loss": 2.0944910049438477, "Pretrain/Loss (Raw)": 2.245730400085449, "Pretrain/Step": 2837, "Pretrain/Step Time": 8.86637044325471} +{"Pretrain/Learning Rate": 4.118465711954569e-05, "Pretrain/Loss": 2.0928473472595215, "Pretrain/Loss (Raw)": 1.9811466932296753, "Pretrain/Step": 2838, "Pretrain/Step Time": 8.869009349495173} +{"Pretrain/Learning Rate": 4.1178185527270905e-05, "Pretrain/Loss": 2.0956006050109863, "Pretrain/Loss (Raw)": 2.2390449047088623, "Pretrain/Step": 2839, "Pretrain/Step Time": 8.871763104572892} +{"Pretrain/Learning Rate": 4.1171712069251534e-05, "Pretrain/Loss": 2.0957956314086914, "Pretrain/Loss (Raw)": 2.2151033878326416, "Pretrain/Step": 2840, "Pretrain/Step Time": 8.869894592091441} +{"Pretrain/Learning Rate": 4.116523674623412e-05, "Pretrain/Loss": 2.094881534576416, "Pretrain/Loss (Raw)": 2.0573339462280273, "Pretrain/Step": 2841, "Pretrain/Step Time": 8.872223263606429} +{"Pretrain/Learning Rate": 4.115875955896543e-05, "Pretrain/Loss": 2.0983314514160156, "Pretrain/Loss (Raw)": 2.2469465732574463, "Pretrain/Step": 2842, "Pretrain/Step Time": 8.878402339294553} +{"Pretrain/Learning Rate": 4.115228050819244e-05, "Pretrain/Loss": 2.1014492511749268, "Pretrain/Loss (Raw)": 2.1538608074188232, "Pretrain/Step": 2843, "Pretrain/Step Time": 8.868353996425867} +{"Pretrain/Learning Rate": 4.114579959466235e-05, "Pretrain/Loss": 2.0998363494873047, "Pretrain/Loss (Raw)": 1.9693158864974976, "Pretrain/Step": 2844, "Pretrain/Step Time": 8.874382132664323} +{"Pretrain/Learning Rate": 4.113931681912257e-05, "Pretrain/Loss": 2.1002612113952637, "Pretrain/Loss (Raw)": 2.127837657928467, "Pretrain/Step": 2845, "Pretrain/Step Time": 8.86754685640335} +{"Pretrain/Learning Rate": 4.113283218232073e-05, "Pretrain/Loss": 2.103346347808838, "Pretrain/Loss (Raw)": 2.202066421508789, "Pretrain/Step": 2846, "Pretrain/Step Time": 8.871510116383433} +{"Pretrain/Learning Rate": 4.112634568500466e-05, "Pretrain/Loss": 2.101322889328003, "Pretrain/Loss (Raw)": 1.860076665878296, "Pretrain/Step": 2847, "Pretrain/Step Time": 8.869667638093233} +{"Pretrain/Learning Rate": 4.111985732792242e-05, "Pretrain/Loss": 2.1008312702178955, "Pretrain/Loss (Raw)": 2.1399424076080322, "Pretrain/Step": 2848, "Pretrain/Step Time": 8.870921166613698} +{"Pretrain/Learning Rate": 4.111336711182226e-05, "Pretrain/Loss": 2.1004045009613037, "Pretrain/Loss (Raw)": 1.9785255193710327, "Pretrain/Step": 2849, "Pretrain/Step Time": 8.882435882464051} +{"Pretrain/Learning Rate": 4.110687503745269e-05, "Pretrain/Loss": 2.0982327461242676, "Pretrain/Loss (Raw)": 2.0398752689361572, "Pretrain/Step": 2850, "Pretrain/Step Time": 8.865440681576729} +{"Pretrain/Learning Rate": 4.1100381105562394e-05, "Pretrain/Loss": 2.0959794521331787, "Pretrain/Loss (Raw)": 1.8565540313720703, "Pretrain/Step": 2851, "Pretrain/Step Time": 8.870168404653668} +{"Pretrain/Learning Rate": 4.109388531690027e-05, "Pretrain/Loss": 2.096876859664917, "Pretrain/Loss (Raw)": 2.2078452110290527, "Pretrain/Step": 2852, "Pretrain/Step Time": 8.868570949882269} +{"Pretrain/Learning Rate": 4.108738767221546e-05, "Pretrain/Loss": 2.0973572731018066, "Pretrain/Loss (Raw)": 2.133720874786377, "Pretrain/Step": 2853, "Pretrain/Step Time": 8.871463373303413} +{"Pretrain/Learning Rate": 4.108088817225729e-05, "Pretrain/Loss": 2.0985794067382812, "Pretrain/Loss (Raw)": 2.2479071617126465, "Pretrain/Step": 2854, "Pretrain/Step Time": 8.868670456111431} +{"Pretrain/Learning Rate": 4.1074386817775334e-05, "Pretrain/Loss": 2.0994739532470703, "Pretrain/Loss (Raw)": 2.155160903930664, "Pretrain/Step": 2855, "Pretrain/Step Time": 8.863845953717828} +{"Pretrain/Learning Rate": 4.106788360951934e-05, "Pretrain/Loss": 2.0985167026519775, "Pretrain/Loss (Raw)": 2.123896598815918, "Pretrain/Step": 2856, "Pretrain/Step Time": 8.86317365989089} +{"Pretrain/Learning Rate": 4.106137854823929e-05, "Pretrain/Loss": 2.097886562347412, "Pretrain/Loss (Raw)": 2.1050477027893066, "Pretrain/Step": 2857, "Pretrain/Step Time": 8.873985391110182} +{"Pretrain/Learning Rate": 4.1054871634685385e-05, "Pretrain/Loss": 2.0994205474853516, "Pretrain/Loss (Raw)": 2.232046127319336, "Pretrain/Step": 2858, "Pretrain/Step Time": 8.86897174268961} +{"Pretrain/Learning Rate": 4.104836286960802e-05, "Pretrain/Loss": 2.099587917327881, "Pretrain/Loss (Raw)": 2.1583383083343506, "Pretrain/Step": 2859, "Pretrain/Step Time": 8.8689756821841} +{"Pretrain/Learning Rate": 4.1041852253757836e-05, "Pretrain/Loss": 2.0997848510742188, "Pretrain/Loss (Raw)": 2.0844969749450684, "Pretrain/Step": 2860, "Pretrain/Step Time": 8.867533847689629} +{"Pretrain/Learning Rate": 4.103533978788566e-05, "Pretrain/Loss": 2.099799871444702, "Pretrain/Loss (Raw)": 2.141486167907715, "Pretrain/Step": 2861, "Pretrain/Step Time": 8.872591523453593} +{"Pretrain/Learning Rate": 4.1028825472742536e-05, "Pretrain/Loss": 2.100306987762451, "Pretrain/Loss (Raw)": 2.173675298690796, "Pretrain/Step": 2862, "Pretrain/Step Time": 8.866642497479916} +{"Pretrain/Learning Rate": 4.1022309309079734e-05, "Pretrain/Loss": 2.1007883548736572, "Pretrain/Loss (Raw)": 2.1495068073272705, "Pretrain/Step": 2863, "Pretrain/Step Time": 8.866267329081893} +{"Pretrain/Learning Rate": 4.1015791297648716e-05, "Pretrain/Loss": 2.1015026569366455, "Pretrain/Loss (Raw)": 2.2185068130493164, "Pretrain/Step": 2864, "Pretrain/Step Time": 8.86936641857028} +{"Pretrain/Learning Rate": 4.100927143920118e-05, "Pretrain/Loss": 2.1004421710968018, "Pretrain/Loss (Raw)": 2.054260492324829, "Pretrain/Step": 2865, "Pretrain/Step Time": 8.865785224363208} +{"Pretrain/Learning Rate": 4.100274973448902e-05, "Pretrain/Loss": 2.101606845855713, "Pretrain/Loss (Raw)": 2.289778709411621, "Pretrain/Step": 2866, "Pretrain/Step Time": 8.86975327692926} +{"Pretrain/Learning Rate": 4.099622618426436e-05, "Pretrain/Loss": 2.100128173828125, "Pretrain/Loss (Raw)": 1.9054396152496338, "Pretrain/Step": 2867, "Pretrain/Step Time": 8.867133989930153} +{"Pretrain/Learning Rate": 4.098970078927951e-05, "Pretrain/Loss": 2.0991291999816895, "Pretrain/Loss (Raw)": 1.935280203819275, "Pretrain/Step": 2868, "Pretrain/Step Time": 8.871424036100507} +{"Pretrain/Learning Rate": 4.0983173550287026e-05, "Pretrain/Loss": 2.0984673500061035, "Pretrain/Loss (Raw)": 1.9464340209960938, "Pretrain/Step": 2869, "Pretrain/Step Time": 8.86802632175386} +{"Pretrain/Learning Rate": 4.0976644468039646e-05, "Pretrain/Loss": 2.0990772247314453, "Pretrain/Loss (Raw)": 2.2081775665283203, "Pretrain/Step": 2870, "Pretrain/Step Time": 8.868183366954327} +{"Pretrain/Learning Rate": 4.097011354329035e-05, "Pretrain/Loss": 2.0989489555358887, "Pretrain/Loss (Raw)": 2.1573636531829834, "Pretrain/Step": 2871, "Pretrain/Step Time": 8.864367319270968} +{"Pretrain/Learning Rate": 4.096358077679231e-05, "Pretrain/Loss": 2.0964765548706055, "Pretrain/Loss (Raw)": 2.060786247253418, "Pretrain/Step": 2872, "Pretrain/Step Time": 8.87087376229465} +{"Pretrain/Learning Rate": 4.0957046169298895e-05, "Pretrain/Loss": 2.0991106033325195, "Pretrain/Loss (Raw)": 2.3037264347076416, "Pretrain/Step": 2873, "Pretrain/Step Time": 8.867665754631162} +{"Pretrain/Learning Rate": 4.095050972156374e-05, "Pretrain/Loss": 2.0989983081817627, "Pretrain/Loss (Raw)": 2.1403591632843018, "Pretrain/Step": 2874, "Pretrain/Step Time": 8.867712805047631} +{"Pretrain/Learning Rate": 4.0943971434340633e-05, "Pretrain/Loss": 2.098018169403076, "Pretrain/Loss (Raw)": 1.931859016418457, "Pretrain/Step": 2875, "Pretrain/Step Time": 8.873313967138529} +{"Pretrain/Learning Rate": 4.093743130838361e-05, "Pretrain/Loss": 2.0987205505371094, "Pretrain/Loss (Raw)": 2.0695066452026367, "Pretrain/Step": 2876, "Pretrain/Step Time": 8.869986919686198} +{"Pretrain/Learning Rate": 4.093088934444692e-05, "Pretrain/Loss": 2.0987472534179688, "Pretrain/Loss (Raw)": 2.2122652530670166, "Pretrain/Step": 2877, "Pretrain/Step Time": 8.872748050838709} +{"Pretrain/Learning Rate": 4.092434554328499e-05, "Pretrain/Loss": 2.100897789001465, "Pretrain/Loss (Raw)": 2.3464982509613037, "Pretrain/Step": 2878, "Pretrain/Step Time": 8.870181171223521} +{"Pretrain/Learning Rate": 4.09177999056525e-05, "Pretrain/Loss": 2.1028144359588623, "Pretrain/Loss (Raw)": 2.3894059658050537, "Pretrain/Step": 2879, "Pretrain/Step Time": 8.872992195189} +{"Pretrain/Learning Rate": 4.0911252432304316e-05, "Pretrain/Loss": 2.099762439727783, "Pretrain/Loss (Raw)": 1.9066697359085083, "Pretrain/Step": 2880, "Pretrain/Step Time": 8.875579502433538} +{"Pretrain/Learning Rate": 4.0904703123995516e-05, "Pretrain/Loss": 2.0963587760925293, "Pretrain/Loss (Raw)": 1.6579549312591553, "Pretrain/Step": 2881, "Pretrain/Step Time": 8.877706797793508} +{"Pretrain/Learning Rate": 4.0898151981481416e-05, "Pretrain/Loss": 2.097947835922241, "Pretrain/Loss (Raw)": 2.1791234016418457, "Pretrain/Step": 2882, "Pretrain/Step Time": 8.876586241647601} +{"Pretrain/Learning Rate": 4.089159900551752e-05, "Pretrain/Loss": 2.099410057067871, "Pretrain/Loss (Raw)": 2.264119863510132, "Pretrain/Step": 2883, "Pretrain/Step Time": 8.878172880038619} +{"Pretrain/Learning Rate": 4.0885044196859537e-05, "Pretrain/Loss": 2.0990004539489746, "Pretrain/Loss (Raw)": 2.1696183681488037, "Pretrain/Step": 2884, "Pretrain/Step Time": 8.885207479819655} +{"Pretrain/Learning Rate": 4.08784875562634e-05, "Pretrain/Loss": 2.097479820251465, "Pretrain/Loss (Raw)": 1.9277257919311523, "Pretrain/Step": 2885, "Pretrain/Step Time": 8.886153154075146} +{"Pretrain/Learning Rate": 4.087192908448526e-05, "Pretrain/Loss": 2.0957112312316895, "Pretrain/Loss (Raw)": 1.9945043325424194, "Pretrain/Step": 2886, "Pretrain/Step Time": 8.882646018639207} +{"Pretrain/Learning Rate": 4.086536878228147e-05, "Pretrain/Loss": 2.096179485321045, "Pretrain/Loss (Raw)": 2.222853899002075, "Pretrain/Step": 2887, "Pretrain/Step Time": 8.88641307130456} +{"Pretrain/Learning Rate": 4.0858806650408586e-05, "Pretrain/Loss": 2.0962436199188232, "Pretrain/Loss (Raw)": 2.0790388584136963, "Pretrain/Step": 2888, "Pretrain/Step Time": 8.889861013740301} +{"Pretrain/Learning Rate": 4.08522426896234e-05, "Pretrain/Loss": 2.0982723236083984, "Pretrain/Loss (Raw)": 2.1622872352600098, "Pretrain/Step": 2889, "Pretrain/Step Time": 8.88488855957985} +{"Pretrain/Learning Rate": 4.0845676900682884e-05, "Pretrain/Loss": 2.0970189571380615, "Pretrain/Loss (Raw)": 2.28708553314209, "Pretrain/Step": 2890, "Pretrain/Step Time": 8.89028124511242} +{"Pretrain/Learning Rate": 4.0839109284344235e-05, "Pretrain/Loss": 2.0969595909118652, "Pretrain/Loss (Raw)": 2.1234898567199707, "Pretrain/Step": 2891, "Pretrain/Step Time": 8.8942033611238} +{"Pretrain/Learning Rate": 4.083253984136487e-05, "Pretrain/Loss": 2.0984654426574707, "Pretrain/Loss (Raw)": 2.299037218093872, "Pretrain/Step": 2892, "Pretrain/Step Time": 8.889072420075536} +{"Pretrain/Learning Rate": 4.0825968572502404e-05, "Pretrain/Loss": 2.0966176986694336, "Pretrain/Loss (Raw)": 2.0102038383483887, "Pretrain/Step": 2893, "Pretrain/Step Time": 8.888935362920165} +{"Pretrain/Learning Rate": 4.081939547851467e-05, "Pretrain/Loss": 2.0946969985961914, "Pretrain/Loss (Raw)": 2.0597946643829346, "Pretrain/Step": 2894, "Pretrain/Step Time": 8.893999556079507} +{"Pretrain/Learning Rate": 4.0812820560159705e-05, "Pretrain/Loss": 2.093761444091797, "Pretrain/Loss (Raw)": 1.9994618892669678, "Pretrain/Step": 2895, "Pretrain/Step Time": 8.89055734500289} +{"Pretrain/Learning Rate": 4.0806243818195765e-05, "Pretrain/Loss": 2.0933518409729004, "Pretrain/Loss (Raw)": 2.144244909286499, "Pretrain/Step": 2896, "Pretrain/Step Time": 8.890516001731157} +{"Pretrain/Learning Rate": 4.07996652533813e-05, "Pretrain/Loss": 2.0938796997070312, "Pretrain/Loss (Raw)": 2.106391668319702, "Pretrain/Step": 2897, "Pretrain/Step Time": 8.886334570124745} +{"Pretrain/Learning Rate": 4.0793084866474986e-05, "Pretrain/Loss": 2.0928196907043457, "Pretrain/Loss (Raw)": 2.0244860649108887, "Pretrain/Step": 2898, "Pretrain/Step Time": 8.8950972892344} +{"Pretrain/Learning Rate": 4.078650265823571e-05, "Pretrain/Loss": 2.0923330783843994, "Pretrain/Loss (Raw)": 1.925152063369751, "Pretrain/Step": 2899, "Pretrain/Step Time": 8.890019750222564} +{"Pretrain/Learning Rate": 4.077991862942256e-05, "Pretrain/Loss": 2.091628074645996, "Pretrain/Loss (Raw)": 1.9269764423370361, "Pretrain/Step": 2900, "Pretrain/Step Time": 8.887789322063327} +{"Pretrain/Learning Rate": 4.0773332780794834e-05, "Pretrain/Loss": 2.0907974243164062, "Pretrain/Loss (Raw)": 2.0210111141204834, "Pretrain/Step": 2901, "Pretrain/Step Time": 8.883631873875856} +{"Pretrain/Learning Rate": 4.076674511311205e-05, "Pretrain/Loss": 2.089895725250244, "Pretrain/Loss (Raw)": 2.137939453125, "Pretrain/Step": 2902, "Pretrain/Step Time": 8.891476279124618} +{"Pretrain/Learning Rate": 4.0760155627133924e-05, "Pretrain/Loss": 2.0888214111328125, "Pretrain/Loss (Raw)": 1.9888145923614502, "Pretrain/Step": 2903, "Pretrain/Step Time": 8.883216600865126} +{"Pretrain/Learning Rate": 4.075356432362037e-05, "Pretrain/Loss": 2.0876457691192627, "Pretrain/Loss (Raw)": 2.053982973098755, "Pretrain/Step": 2904, "Pretrain/Step Time": 8.88291092775762} +{"Pretrain/Learning Rate": 4.074697120333156e-05, "Pretrain/Loss": 2.089569568634033, "Pretrain/Loss (Raw)": 2.151681900024414, "Pretrain/Step": 2905, "Pretrain/Step Time": 8.881218194961548} +{"Pretrain/Learning Rate": 4.0740376267027836e-05, "Pretrain/Loss": 2.0882253646850586, "Pretrain/Loss (Raw)": 1.9211039543151855, "Pretrain/Step": 2906, "Pretrain/Step Time": 8.880963891744614} +{"Pretrain/Learning Rate": 4.0733779515469736e-05, "Pretrain/Loss": 2.088528633117676, "Pretrain/Loss (Raw)": 2.180555820465088, "Pretrain/Step": 2907, "Pretrain/Step Time": 8.877021392807364} +{"Pretrain/Learning Rate": 4.072718094941805e-05, "Pretrain/Loss": 2.089064598083496, "Pretrain/Loss (Raw)": 2.2475717067718506, "Pretrain/Step": 2908, "Pretrain/Step Time": 8.876458581537008} +{"Pretrain/Learning Rate": 4.0720580569633746e-05, "Pretrain/Loss": 2.0890650749206543, "Pretrain/Loss (Raw)": 2.094496011734009, "Pretrain/Step": 2909, "Pretrain/Step Time": 8.889688579365611} +{"Pretrain/Learning Rate": 4.0713978376878016e-05, "Pretrain/Loss": 2.0893545150756836, "Pretrain/Loss (Raw)": 2.1090869903564453, "Pretrain/Step": 2910, "Pretrain/Step Time": 8.881900927051902} +{"Pretrain/Learning Rate": 4.070737437191224e-05, "Pretrain/Loss": 2.0890512466430664, "Pretrain/Loss (Raw)": 2.0516583919525146, "Pretrain/Step": 2911, "Pretrain/Step Time": 8.883098987862468} +{"Pretrain/Learning Rate": 4.0700768555498045e-05, "Pretrain/Loss": 2.0913233757019043, "Pretrain/Loss (Raw)": 2.1053507328033447, "Pretrain/Step": 2912, "Pretrain/Step Time": 8.880415074527264} +{"Pretrain/Learning Rate": 4.069416092839724e-05, "Pretrain/Loss": 2.092233896255493, "Pretrain/Loss (Raw)": 2.2440242767333984, "Pretrain/Step": 2913, "Pretrain/Step Time": 8.886810274794698} +{"Pretrain/Learning Rate": 4.068755149137184e-05, "Pretrain/Loss": 2.0933310985565186, "Pretrain/Loss (Raw)": 2.159754514694214, "Pretrain/Step": 2914, "Pretrain/Step Time": 8.879143157973886} +{"Pretrain/Learning Rate": 4.0680940245184076e-05, "Pretrain/Loss": 2.0946879386901855, "Pretrain/Loss (Raw)": 2.0751113891601562, "Pretrain/Step": 2915, "Pretrain/Step Time": 8.879730634391308} +{"Pretrain/Learning Rate": 4.06743271905964e-05, "Pretrain/Loss": 2.0937600135803223, "Pretrain/Loss (Raw)": 2.097403049468994, "Pretrain/Step": 2916, "Pretrain/Step Time": 8.877612827345729} +{"Pretrain/Learning Rate": 4.066771232837144e-05, "Pretrain/Loss": 2.0925984382629395, "Pretrain/Loss (Raw)": 2.07765793800354, "Pretrain/Step": 2917, "Pretrain/Step Time": 8.885807450860739} +{"Pretrain/Learning Rate": 4.066109565927208e-05, "Pretrain/Loss": 2.092327117919922, "Pretrain/Loss (Raw)": 2.0541067123413086, "Pretrain/Step": 2918, "Pretrain/Step Time": 8.87187609449029} +{"Pretrain/Learning Rate": 4.0654477184061356e-05, "Pretrain/Loss": 2.093071699142456, "Pretrain/Loss (Raw)": 2.08225154876709, "Pretrain/Step": 2919, "Pretrain/Step Time": 8.877058709040284} +{"Pretrain/Learning Rate": 4.064785690350257e-05, "Pretrain/Loss": 2.093674898147583, "Pretrain/Loss (Raw)": 2.134861707687378, "Pretrain/Step": 2920, "Pretrain/Step Time": 8.870711214840412} +{"Pretrain/Learning Rate": 4.064123481835919e-05, "Pretrain/Loss": 2.0948095321655273, "Pretrain/Loss (Raw)": 2.2412805557250977, "Pretrain/Step": 2921, "Pretrain/Step Time": 8.874933267012239} +{"Pretrain/Learning Rate": 4.0634610929394893e-05, "Pretrain/Loss": 2.093240737915039, "Pretrain/Loss (Raw)": 2.1091079711914062, "Pretrain/Step": 2922, "Pretrain/Step Time": 8.872305642813444} +{"Pretrain/Learning Rate": 4.06279852373736e-05, "Pretrain/Loss": 2.0941343307495117, "Pretrain/Loss (Raw)": 2.0284817218780518, "Pretrain/Step": 2923, "Pretrain/Step Time": 8.872313918545842} +{"Pretrain/Learning Rate": 4.0621357743059415e-05, "Pretrain/Loss": 2.094491720199585, "Pretrain/Loss (Raw)": 2.108480453491211, "Pretrain/Step": 2924, "Pretrain/Step Time": 8.881919857114553} +{"Pretrain/Learning Rate": 4.061472844721664e-05, "Pretrain/Loss": 2.0946006774902344, "Pretrain/Loss (Raw)": 2.110495090484619, "Pretrain/Step": 2925, "Pretrain/Step Time": 8.875914063304663} +{"Pretrain/Learning Rate": 4.06080973506098e-05, "Pretrain/Loss": 2.095036029815674, "Pretrain/Loss (Raw)": 2.0654666423797607, "Pretrain/Step": 2926, "Pretrain/Step Time": 8.877795323729515} +{"Pretrain/Learning Rate": 4.0601464454003624e-05, "Pretrain/Loss": 2.0983481407165527, "Pretrain/Loss (Raw)": 2.265256404876709, "Pretrain/Step": 2927, "Pretrain/Step Time": 8.869767477735877} +{"Pretrain/Learning Rate": 4.059482975816305e-05, "Pretrain/Loss": 2.0983150005340576, "Pretrain/Loss (Raw)": 2.12542986869812, "Pretrain/Step": 2928, "Pretrain/Step Time": 8.874579478055239} +{"Pretrain/Learning Rate": 4.058819326385322e-05, "Pretrain/Loss": 2.0956976413726807, "Pretrain/Loss (Raw)": 1.899279236793518, "Pretrain/Step": 2929, "Pretrain/Step Time": 8.869922436773777} +{"Pretrain/Learning Rate": 4.05815549718395e-05, "Pretrain/Loss": 2.093137741088867, "Pretrain/Loss (Raw)": 1.9723682403564453, "Pretrain/Step": 2930, "Pretrain/Step Time": 8.874085824936628} +{"Pretrain/Learning Rate": 4.057491488288743e-05, "Pretrain/Loss": 2.094053268432617, "Pretrain/Loss (Raw)": 1.9826098680496216, "Pretrain/Step": 2931, "Pretrain/Step Time": 8.873224997892976} +{"Pretrain/Learning Rate": 4.0568272997762785e-05, "Pretrain/Loss": 2.0924134254455566, "Pretrain/Loss (Raw)": 2.103205680847168, "Pretrain/Step": 2932, "Pretrain/Step Time": 8.879553658887744} +{"Pretrain/Learning Rate": 4.056162931723154e-05, "Pretrain/Loss": 2.0946149826049805, "Pretrain/Loss (Raw)": 2.2155895233154297, "Pretrain/Step": 2933, "Pretrain/Step Time": 8.867458438500762} +{"Pretrain/Learning Rate": 4.055498384205987e-05, "Pretrain/Loss": 2.096555709838867, "Pretrain/Loss (Raw)": 2.235400438308716, "Pretrain/Step": 2934, "Pretrain/Step Time": 8.866749553009868} +{"Pretrain/Learning Rate": 4.054833657301417e-05, "Pretrain/Loss": 2.0960965156555176, "Pretrain/Loss (Raw)": 2.0569989681243896, "Pretrain/Step": 2935, "Pretrain/Step Time": 8.865437161177397} +{"Pretrain/Learning Rate": 4.054168751086102e-05, "Pretrain/Loss": 2.096710205078125, "Pretrain/Loss (Raw)": 2.1165502071380615, "Pretrain/Step": 2936, "Pretrain/Step Time": 8.86931686848402} +{"Pretrain/Learning Rate": 4.053503665636724e-05, "Pretrain/Loss": 2.096611976623535, "Pretrain/Loss (Raw)": 1.8964523077011108, "Pretrain/Step": 2937, "Pretrain/Step Time": 8.86311481706798} +{"Pretrain/Learning Rate": 4.052838401029984e-05, "Pretrain/Loss": 2.098470687866211, "Pretrain/Loss (Raw)": 2.2019450664520264, "Pretrain/Step": 2938, "Pretrain/Step Time": 8.86623302474618} +{"Pretrain/Learning Rate": 4.0521729573426006e-05, "Pretrain/Loss": 2.098482608795166, "Pretrain/Loss (Raw)": 2.1991569995880127, "Pretrain/Step": 2939, "Pretrain/Step Time": 8.872580731287599} +{"Pretrain/Learning Rate": 4.051507334651318e-05, "Pretrain/Loss": 2.099453926086426, "Pretrain/Loss (Raw)": 2.2815423011779785, "Pretrain/Step": 2940, "Pretrain/Step Time": 8.868701968342066} +{"Pretrain/Learning Rate": 4.050841533032899e-05, "Pretrain/Loss": 2.0985641479492188, "Pretrain/Loss (Raw)": 2.093402862548828, "Pretrain/Step": 2941, "Pretrain/Step Time": 8.876716924831271} +{"Pretrain/Learning Rate": 4.050175552564127e-05, "Pretrain/Loss": 2.0983924865722656, "Pretrain/Loss (Raw)": 2.1424291133880615, "Pretrain/Step": 2942, "Pretrain/Step Time": 8.873606430366635} +{"Pretrain/Learning Rate": 4.049509393321805e-05, "Pretrain/Loss": 2.0959649085998535, "Pretrain/Loss (Raw)": 1.760372519493103, "Pretrain/Step": 2943, "Pretrain/Step Time": 8.86595301143825} +{"Pretrain/Learning Rate": 4.0488430553827585e-05, "Pretrain/Loss": 2.095150947570801, "Pretrain/Loss (Raw)": 1.9723955392837524, "Pretrain/Step": 2944, "Pretrain/Step Time": 8.870107555761933} +{"Pretrain/Learning Rate": 4.0481765388238324e-05, "Pretrain/Loss": 2.09605073928833, "Pretrain/Loss (Raw)": 2.0861570835113525, "Pretrain/Step": 2945, "Pretrain/Step Time": 8.866235686466098} +{"Pretrain/Learning Rate": 4.047509843721893e-05, "Pretrain/Loss": 2.0935115814208984, "Pretrain/Loss (Raw)": 1.812782883644104, "Pretrain/Step": 2946, "Pretrain/Step Time": 8.866829868406057} +{"Pretrain/Learning Rate": 4.0468429701538253e-05, "Pretrain/Loss": 2.0926883220672607, "Pretrain/Loss (Raw)": 1.9586219787597656, "Pretrain/Step": 2947, "Pretrain/Step Time": 8.873843297362328} +{"Pretrain/Learning Rate": 4.046175918196538e-05, "Pretrain/Loss": 2.0922629833221436, "Pretrain/Loss (Raw)": 2.2439000606536865, "Pretrain/Step": 2948, "Pretrain/Step Time": 8.863624773919582} +{"Pretrain/Learning Rate": 4.045508687926958e-05, "Pretrain/Loss": 2.0930845737457275, "Pretrain/Loss (Raw)": 2.0450692176818848, "Pretrain/Step": 2949, "Pretrain/Step Time": 8.870381817221642} +{"Pretrain/Learning Rate": 4.044841279422034e-05, "Pretrain/Loss": 2.094043016433716, "Pretrain/Loss (Raw)": 2.0884625911712646, "Pretrain/Step": 2950, "Pretrain/Step Time": 8.864826630800962} +{"Pretrain/Learning Rate": 4.044173692758733e-05, "Pretrain/Loss": 2.092921018600464, "Pretrain/Loss (Raw)": 2.0440707206726074, "Pretrain/Step": 2951, "Pretrain/Step Time": 8.87216497771442} +{"Pretrain/Learning Rate": 4.043505928014045e-05, "Pretrain/Loss": 2.0904741287231445, "Pretrain/Loss (Raw)": 1.8218886852264404, "Pretrain/Step": 2952, "Pretrain/Step Time": 8.871713561937213} +{"Pretrain/Learning Rate": 4.0428379852649816e-05, "Pretrain/Loss": 2.089803457260132, "Pretrain/Loss (Raw)": 1.9814664125442505, "Pretrain/Step": 2953, "Pretrain/Step Time": 8.875514602288604} +{"Pretrain/Learning Rate": 4.042169864588571e-05, "Pretrain/Loss": 2.09066104888916, "Pretrain/Loss (Raw)": 2.1079626083374023, "Pretrain/Step": 2954, "Pretrain/Step Time": 8.873667938634753} +{"Pretrain/Learning Rate": 4.041501566061865e-05, "Pretrain/Loss": 2.0914554595947266, "Pretrain/Loss (Raw)": 2.1654865741729736, "Pretrain/Step": 2955, "Pretrain/Step Time": 8.869408629834652} +{"Pretrain/Learning Rate": 4.040833089761934e-05, "Pretrain/Loss": 2.0894949436187744, "Pretrain/Loss (Raw)": 2.1080570220947266, "Pretrain/Step": 2956, "Pretrain/Step Time": 8.87098952755332} +{"Pretrain/Learning Rate": 4.040164435765871e-05, "Pretrain/Loss": 2.093228816986084, "Pretrain/Loss (Raw)": 2.4033615589141846, "Pretrain/Step": 2957, "Pretrain/Step Time": 8.882573699578643} +{"Pretrain/Learning Rate": 4.039495604150787e-05, "Pretrain/Loss": 2.0952696800231934, "Pretrain/Loss (Raw)": 2.019484043121338, "Pretrain/Step": 2958, "Pretrain/Step Time": 8.879845649003983} +{"Pretrain/Learning Rate": 4.0388265949938165e-05, "Pretrain/Loss": 2.0962061882019043, "Pretrain/Loss (Raw)": 2.2041659355163574, "Pretrain/Step": 2959, "Pretrain/Step Time": 8.878101808950305} +{"Pretrain/Learning Rate": 4.038157408372111e-05, "Pretrain/Loss": 2.095545768737793, "Pretrain/Loss (Raw)": 1.9612538814544678, "Pretrain/Step": 2960, "Pretrain/Step Time": 8.878471763804555} +{"Pretrain/Learning Rate": 4.037488044362846e-05, "Pretrain/Loss": 2.0952515602111816, "Pretrain/Loss (Raw)": 2.0012712478637695, "Pretrain/Step": 2961, "Pretrain/Step Time": 8.880267400294542} +{"Pretrain/Learning Rate": 4.036818503043214e-05, "Pretrain/Loss": 2.0969631671905518, "Pretrain/Loss (Raw)": 2.312006950378418, "Pretrain/Step": 2962, "Pretrain/Step Time": 8.871420470997691} +{"Pretrain/Learning Rate": 4.0361487844904314e-05, "Pretrain/Loss": 2.094430685043335, "Pretrain/Loss (Raw)": 1.6770076751708984, "Pretrain/Step": 2963, "Pretrain/Step Time": 8.879654094576836} +{"Pretrain/Learning Rate": 4.035478888781732e-05, "Pretrain/Loss": 2.0953710079193115, "Pretrain/Loss (Raw)": 2.1265199184417725, "Pretrain/Step": 2964, "Pretrain/Step Time": 8.877718994393945} +{"Pretrain/Learning Rate": 4.034808815994372e-05, "Pretrain/Loss": 2.0930371284484863, "Pretrain/Loss (Raw)": 1.947026014328003, "Pretrain/Step": 2965, "Pretrain/Step Time": 8.882886121049523} +{"Pretrain/Learning Rate": 4.0341385662056265e-05, "Pretrain/Loss": 2.094728469848633, "Pretrain/Loss (Raw)": 2.197598695755005, "Pretrain/Step": 2966, "Pretrain/Step Time": 8.881358206272125} +{"Pretrain/Learning Rate": 4.033468139492793e-05, "Pretrain/Loss": 2.0913028717041016, "Pretrain/Loss (Raw)": 1.8005759716033936, "Pretrain/Step": 2967, "Pretrain/Step Time": 8.884860454127192} +{"Pretrain/Learning Rate": 4.032797535933187e-05, "Pretrain/Loss": 2.0922415256500244, "Pretrain/Loss (Raw)": 2.3352808952331543, "Pretrain/Step": 2968, "Pretrain/Step Time": 8.88674245774746} +{"Pretrain/Learning Rate": 4.032126755604147e-05, "Pretrain/Loss": 2.0915379524230957, "Pretrain/Loss (Raw)": 1.9672603607177734, "Pretrain/Step": 2969, "Pretrain/Step Time": 8.882295355200768} +{"Pretrain/Learning Rate": 4.03145579858303e-05, "Pretrain/Loss": 2.090730667114258, "Pretrain/Loss (Raw)": 2.1435868740081787, "Pretrain/Step": 2970, "Pretrain/Step Time": 8.875642275437713} +{"Pretrain/Learning Rate": 4.0307846649472134e-05, "Pretrain/Loss": 2.0888588428497314, "Pretrain/Loss (Raw)": 1.9142920970916748, "Pretrain/Step": 2971, "Pretrain/Step Time": 8.882846293970942} +{"Pretrain/Learning Rate": 4.030113354774096e-05, "Pretrain/Loss": 2.0899362564086914, "Pretrain/Loss (Raw)": 2.1072161197662354, "Pretrain/Step": 2972, "Pretrain/Step Time": 8.88708944618702} +{"Pretrain/Learning Rate": 4.029441868141096e-05, "Pretrain/Loss": 2.0902442932128906, "Pretrain/Loss (Raw)": 2.1672940254211426, "Pretrain/Step": 2973, "Pretrain/Step Time": 8.89114068634808} +{"Pretrain/Learning Rate": 4.0287702051256535e-05, "Pretrain/Loss": 2.0884270668029785, "Pretrain/Loss (Raw)": 1.9694221019744873, "Pretrain/Step": 2974, "Pretrain/Step Time": 8.888592395931482} +{"Pretrain/Learning Rate": 4.0280983658052276e-05, "Pretrain/Loss": 2.089204788208008, "Pretrain/Loss (Raw)": 1.9596320390701294, "Pretrain/Step": 2975, "Pretrain/Step Time": 8.885679565370083} +{"Pretrain/Learning Rate": 4.0274263502572966e-05, "Pretrain/Loss": 2.088766098022461, "Pretrain/Loss (Raw)": 2.08380389213562, "Pretrain/Step": 2976, "Pretrain/Step Time": 8.885262405499816} +{"Pretrain/Learning Rate": 4.026754158559362e-05, "Pretrain/Loss": 2.0900943279266357, "Pretrain/Loss (Raw)": 2.148545980453491, "Pretrain/Step": 2977, "Pretrain/Step Time": 8.886544961482286} +{"Pretrain/Learning Rate": 4.026081790788943e-05, "Pretrain/Loss": 2.088405132293701, "Pretrain/Loss (Raw)": 1.8236253261566162, "Pretrain/Step": 2978, "Pretrain/Step Time": 8.889533510431647} +{"Pretrain/Learning Rate": 4.025409247023581e-05, "Pretrain/Loss": 2.0901408195495605, "Pretrain/Loss (Raw)": 2.078772783279419, "Pretrain/Step": 2979, "Pretrain/Step Time": 8.886526178568602} +{"Pretrain/Learning Rate": 4.0247365273408366e-05, "Pretrain/Loss": 2.089280366897583, "Pretrain/Loss (Raw)": 2.097677707672119, "Pretrain/Step": 2980, "Pretrain/Step Time": 8.8863943554461} +{"Pretrain/Learning Rate": 4.024063631818291e-05, "Pretrain/Loss": 2.0885910987854004, "Pretrain/Loss (Raw)": 2.045517921447754, "Pretrain/Step": 2981, "Pretrain/Step Time": 8.88937670364976} +{"Pretrain/Learning Rate": 4.023390560533546e-05, "Pretrain/Loss": 2.087975025177002, "Pretrain/Loss (Raw)": 2.1690144538879395, "Pretrain/Step": 2982, "Pretrain/Step Time": 8.887570425868034} +{"Pretrain/Learning Rate": 4.022717313564223e-05, "Pretrain/Loss": 2.088007926940918, "Pretrain/Loss (Raw)": 2.159372329711914, "Pretrain/Step": 2983, "Pretrain/Step Time": 8.889296848326921} +{"Pretrain/Learning Rate": 4.0220438909879644e-05, "Pretrain/Loss": 2.0885119438171387, "Pretrain/Loss (Raw)": 2.1884286403656006, "Pretrain/Step": 2984, "Pretrain/Step Time": 8.88999223895371} +{"Pretrain/Learning Rate": 4.0213702928824315e-05, "Pretrain/Loss": 2.088977336883545, "Pretrain/Loss (Raw)": 2.164634943008423, "Pretrain/Step": 2985, "Pretrain/Step Time": 8.888384625315666} +{"Pretrain/Learning Rate": 4.0206965193253075e-05, "Pretrain/Loss": 2.0876944065093994, "Pretrain/Loss (Raw)": 2.0677990913391113, "Pretrain/Step": 2986, "Pretrain/Step Time": 8.882377775385976} +{"Pretrain/Learning Rate": 4.0200225703942964e-05, "Pretrain/Loss": 2.087620258331299, "Pretrain/Loss (Raw)": 2.148876905441284, "Pretrain/Step": 2987, "Pretrain/Step Time": 8.88099487312138} +{"Pretrain/Learning Rate": 4.0193484461671185e-05, "Pretrain/Loss": 2.086979866027832, "Pretrain/Loss (Raw)": 2.0024917125701904, "Pretrain/Step": 2988, "Pretrain/Step Time": 8.874887309968472} +{"Pretrain/Learning Rate": 4.0186741467215186e-05, "Pretrain/Loss": 2.0868544578552246, "Pretrain/Loss (Raw)": 2.125438690185547, "Pretrain/Step": 2989, "Pretrain/Step Time": 8.873381527140737} +{"Pretrain/Learning Rate": 4.017999672135261e-05, "Pretrain/Loss": 2.0861430168151855, "Pretrain/Loss (Raw)": 2.0826168060302734, "Pretrain/Step": 2990, "Pretrain/Step Time": 8.87233910895884} +{"Pretrain/Learning Rate": 4.017325022486127e-05, "Pretrain/Loss": 2.086099147796631, "Pretrain/Loss (Raw)": 2.1438894271850586, "Pretrain/Step": 2991, "Pretrain/Step Time": 8.870359562337399} +{"Pretrain/Learning Rate": 4.0166501978519225e-05, "Pretrain/Loss": 2.0843803882598877, "Pretrain/Loss (Raw)": 1.9985194206237793, "Pretrain/Step": 2992, "Pretrain/Step Time": 8.878401273861527} +{"Pretrain/Learning Rate": 4.015975198310469e-05, "Pretrain/Loss": 2.0826714038848877, "Pretrain/Loss (Raw)": 1.8355214595794678, "Pretrain/Step": 2993, "Pretrain/Step Time": 8.875975729897618} +{"Pretrain/Learning Rate": 4.0153000239396136e-05, "Pretrain/Loss": 2.0821056365966797, "Pretrain/Loss (Raw)": 2.217366933822632, "Pretrain/Step": 2994, "Pretrain/Step Time": 8.874013271182775} +{"Pretrain/Learning Rate": 4.014624674817218e-05, "Pretrain/Loss": 2.083404064178467, "Pretrain/Loss (Raw)": 2.0715911388397217, "Pretrain/Step": 2995, "Pretrain/Step Time": 8.872526420280337} +{"Pretrain/Learning Rate": 4.0139491510211684e-05, "Pretrain/Loss": 2.085543632507324, "Pretrain/Loss (Raw)": 2.2091856002807617, "Pretrain/Step": 2996, "Pretrain/Step Time": 8.870284743607044} +{"Pretrain/Learning Rate": 4.0132734526293685e-05, "Pretrain/Loss": 2.0859315395355225, "Pretrain/Loss (Raw)": 1.9960589408874512, "Pretrain/Step": 2997, "Pretrain/Step Time": 8.87007811293006} +{"Pretrain/Learning Rate": 4.012597579719743e-05, "Pretrain/Loss": 2.0855908393859863, "Pretrain/Loss (Raw)": 2.164555788040161, "Pretrain/Step": 2998, "Pretrain/Step Time": 8.871199890971184} +{"Pretrain/Learning Rate": 4.011921532370238e-05, "Pretrain/Loss": 2.0861330032348633, "Pretrain/Loss (Raw)": 2.2267796993255615, "Pretrain/Step": 2999, "Pretrain/Step Time": 8.881098303943872} +{"Pretrain/Learning Rate": 4.0112453106588164e-05, "Pretrain/Loss": 2.0871684551239014, "Pretrain/Loss (Raw)": 2.1933257579803467, "Pretrain/Step": 3000, "Pretrain/Step Time": 8.873292258009315} +{"Pretrain/Learning Rate": 4.010568914663465e-05, "Pretrain/Loss": 2.0867714881896973, "Pretrain/Loss (Raw)": 2.2529408931732178, "Pretrain/Step": 3001, "Pretrain/Step Time": 8.87298121675849} +{"Pretrain/Learning Rate": 4.0098923444621885e-05, "Pretrain/Loss": 2.086235761642456, "Pretrain/Loss (Raw)": 2.0717661380767822, "Pretrain/Step": 3002, "Pretrain/Step Time": 8.874013353139162} +{"Pretrain/Learning Rate": 4.0092156001330115e-05, "Pretrain/Loss": 2.08809757232666, "Pretrain/Loss (Raw)": 2.1701529026031494, "Pretrain/Step": 3003, "Pretrain/Step Time": 8.873151920735836} +{"Pretrain/Learning Rate": 4.00853868175398e-05, "Pretrain/Loss": 2.088866710662842, "Pretrain/Loss (Raw)": 2.167941093444824, "Pretrain/Step": 3004, "Pretrain/Step Time": 8.871280837804079} +{"Pretrain/Learning Rate": 4.007861589403159e-05, "Pretrain/Loss": 2.0889267921447754, "Pretrain/Loss (Raw)": 2.2199671268463135, "Pretrain/Step": 3005, "Pretrain/Step Time": 8.870987134054303} +{"Pretrain/Learning Rate": 4.0071843231586345e-05, "Pretrain/Loss": 2.085318088531494, "Pretrain/Loss (Raw)": 1.8846138715744019, "Pretrain/Step": 3006, "Pretrain/Step Time": 8.865832474082708} +{"Pretrain/Learning Rate": 4.006506883098512e-05, "Pretrain/Loss": 2.0833513736724854, "Pretrain/Loss (Raw)": 2.137653350830078, "Pretrain/Step": 3007, "Pretrain/Step Time": 8.87147636897862} +{"Pretrain/Learning Rate": 4.005829269300917e-05, "Pretrain/Loss": 2.0834245681762695, "Pretrain/Loss (Raw)": 1.916031837463379, "Pretrain/Step": 3008, "Pretrain/Step Time": 8.872024942189455} +{"Pretrain/Learning Rate": 4.005151481843994e-05, "Pretrain/Loss": 2.085632085800171, "Pretrain/Loss (Raw)": 1.9405205249786377, "Pretrain/Step": 3009, "Pretrain/Step Time": 8.869359847158194} +{"Pretrain/Learning Rate": 4.0044735208059104e-05, "Pretrain/Loss": 2.086611032485962, "Pretrain/Loss (Raw)": 2.3044307231903076, "Pretrain/Step": 3010, "Pretrain/Step Time": 8.865256890654564} +{"Pretrain/Learning Rate": 4.0037953862648504e-05, "Pretrain/Loss": 2.085392475128174, "Pretrain/Loss (Raw)": 2.1081340312957764, "Pretrain/Step": 3011, "Pretrain/Step Time": 8.867485340684652} +{"Pretrain/Learning Rate": 4.003117078299021e-05, "Pretrain/Loss": 2.0861964225769043, "Pretrain/Loss (Raw)": 2.2725257873535156, "Pretrain/Step": 3012, "Pretrain/Step Time": 8.863011809065938} +{"Pretrain/Learning Rate": 4.002438596986647e-05, "Pretrain/Loss": 2.089169979095459, "Pretrain/Loss (Raw)": 2.308332920074463, "Pretrain/Step": 3013, "Pretrain/Step Time": 8.864996865391731} +{"Pretrain/Learning Rate": 4.001759942405974e-05, "Pretrain/Loss": 2.090643882751465, "Pretrain/Loss (Raw)": 2.183183431625366, "Pretrain/Step": 3014, "Pretrain/Step Time": 8.872011449187994} +{"Pretrain/Learning Rate": 4.001081114635268e-05, "Pretrain/Loss": 2.0874810218811035, "Pretrain/Loss (Raw)": 1.8179923295974731, "Pretrain/Step": 3015, "Pretrain/Step Time": 8.859165113419294} +{"Pretrain/Learning Rate": 4.000402113752815e-05, "Pretrain/Loss": 2.0864579677581787, "Pretrain/Loss (Raw)": 1.948103666305542, "Pretrain/Step": 3016, "Pretrain/Step Time": 8.861730728298426} +{"Pretrain/Learning Rate": 3.9997229398369194e-05, "Pretrain/Loss": 2.0856871604919434, "Pretrain/Loss (Raw)": 2.063624382019043, "Pretrain/Step": 3017, "Pretrain/Step Time": 8.866513257846236} +{"Pretrain/Learning Rate": 3.999043592965908e-05, "Pretrain/Loss": 2.083920955657959, "Pretrain/Loss (Raw)": 2.061016321182251, "Pretrain/Step": 3018, "Pretrain/Step Time": 8.866249203681946} +{"Pretrain/Learning Rate": 3.998364073218126e-05, "Pretrain/Loss": 2.081960678100586, "Pretrain/Loss (Raw)": 1.8725674152374268, "Pretrain/Step": 3019, "Pretrain/Step Time": 8.85965164937079} +{"Pretrain/Learning Rate": 3.997684380671938e-05, "Pretrain/Loss": 2.079766273498535, "Pretrain/Loss (Raw)": 2.0181477069854736, "Pretrain/Step": 3020, "Pretrain/Step Time": 8.86082149296999} +{"Pretrain/Learning Rate": 3.9970045154057304e-05, "Pretrain/Loss": 2.0799989700317383, "Pretrain/Loss (Raw)": 2.039992570877075, "Pretrain/Step": 3021, "Pretrain/Step Time": 8.861092548817396} +{"Pretrain/Learning Rate": 3.996324477497907e-05, "Pretrain/Loss": 2.0798699855804443, "Pretrain/Loss (Raw)": 2.043287515640259, "Pretrain/Step": 3022, "Pretrain/Step Time": 8.859547834843397} +{"Pretrain/Learning Rate": 3.9956442670268946e-05, "Pretrain/Loss": 2.0799665451049805, "Pretrain/Loss (Raw)": 2.0118188858032227, "Pretrain/Step": 3023, "Pretrain/Step Time": 8.862457897514105} +{"Pretrain/Learning Rate": 3.9949638840711376e-05, "Pretrain/Loss": 2.079608917236328, "Pretrain/Loss (Raw)": 2.0984485149383545, "Pretrain/Step": 3024, "Pretrain/Step Time": 8.86619763635099} +{"Pretrain/Learning Rate": 3.9942833287091006e-05, "Pretrain/Loss": 2.078892707824707, "Pretrain/Loss (Raw)": 2.014746904373169, "Pretrain/Step": 3025, "Pretrain/Step Time": 8.864994263276458} +{"Pretrain/Learning Rate": 3.9936026010192696e-05, "Pretrain/Loss": 2.078165054321289, "Pretrain/Loss (Raw)": 1.9313431978225708, "Pretrain/Step": 3026, "Pretrain/Step Time": 8.859630620107055} +{"Pretrain/Learning Rate": 3.9929217010801476e-05, "Pretrain/Loss": 2.079331159591675, "Pretrain/Loss (Raw)": 2.0744192600250244, "Pretrain/Step": 3027, "Pretrain/Step Time": 8.857561767101288} +{"Pretrain/Learning Rate": 3.992240628970261e-05, "Pretrain/Loss": 2.0803656578063965, "Pretrain/Loss (Raw)": 2.059385299682617, "Pretrain/Step": 3028, "Pretrain/Step Time": 8.857579477131367} +{"Pretrain/Learning Rate": 3.991559384768153e-05, "Pretrain/Loss": 2.079763889312744, "Pretrain/Loss (Raw)": 1.94400954246521, "Pretrain/Step": 3029, "Pretrain/Step Time": 8.863967316225171} +{"Pretrain/Learning Rate": 3.9908779685523885e-05, "Pretrain/Loss": 2.079493522644043, "Pretrain/Loss (Raw)": 2.1033225059509277, "Pretrain/Step": 3030, "Pretrain/Step Time": 8.859571876004338} +{"Pretrain/Learning Rate": 3.9901963804015516e-05, "Pretrain/Loss": 2.08018159866333, "Pretrain/Loss (Raw)": 2.076895236968994, "Pretrain/Step": 3031, "Pretrain/Step Time": 8.865230295807123} +{"Pretrain/Learning Rate": 3.9895146203942457e-05, "Pretrain/Loss": 2.082106828689575, "Pretrain/Loss (Raw)": 2.300382375717163, "Pretrain/Step": 3032, "Pretrain/Step Time": 8.868566809222102} +{"Pretrain/Learning Rate": 3.988832688609095e-05, "Pretrain/Loss": 2.084773063659668, "Pretrain/Loss (Raw)": 2.4929733276367188, "Pretrain/Step": 3033, "Pretrain/Step Time": 8.862907083705068} +{"Pretrain/Learning Rate": 3.988150585124743e-05, "Pretrain/Loss": 2.084563732147217, "Pretrain/Loss (Raw)": 1.89427649974823, "Pretrain/Step": 3034, "Pretrain/Step Time": 8.87033155746758} +{"Pretrain/Learning Rate": 3.987468310019853e-05, "Pretrain/Loss": 2.084834337234497, "Pretrain/Loss (Raw)": 2.2152230739593506, "Pretrain/Step": 3035, "Pretrain/Step Time": 8.870795419439673} +{"Pretrain/Learning Rate": 3.986785863373109e-05, "Pretrain/Loss": 2.083035469055176, "Pretrain/Loss (Raw)": 2.017322301864624, "Pretrain/Step": 3036, "Pretrain/Step Time": 8.87276929244399} +{"Pretrain/Learning Rate": 3.9861032452632124e-05, "Pretrain/Loss": 2.082810878753662, "Pretrain/Loss (Raw)": 2.0657594203948975, "Pretrain/Step": 3037, "Pretrain/Step Time": 8.857769763097167} +{"Pretrain/Learning Rate": 3.985420455768887e-05, "Pretrain/Loss": 2.0827391147613525, "Pretrain/Loss (Raw)": 2.099886894226074, "Pretrain/Step": 3038, "Pretrain/Step Time": 8.869638646021485} +{"Pretrain/Learning Rate": 3.9847374949688756e-05, "Pretrain/Loss": 2.082195281982422, "Pretrain/Loss (Raw)": 1.9820407629013062, "Pretrain/Step": 3039, "Pretrain/Step Time": 8.86993862874806} +{"Pretrain/Learning Rate": 3.98405436294194e-05, "Pretrain/Loss": 2.0807223320007324, "Pretrain/Loss (Raw)": 1.9168299436569214, "Pretrain/Step": 3040, "Pretrain/Step Time": 8.87343381345272} +{"Pretrain/Learning Rate": 3.9833710597668614e-05, "Pretrain/Loss": 2.0779263973236084, "Pretrain/Loss (Raw)": 1.8861383199691772, "Pretrain/Step": 3041, "Pretrain/Step Time": 8.865315916016698} +{"Pretrain/Learning Rate": 3.9826875855224435e-05, "Pretrain/Loss": 2.0770325660705566, "Pretrain/Loss (Raw)": 2.0453543663024902, "Pretrain/Step": 3042, "Pretrain/Step Time": 8.872921731323004} +{"Pretrain/Learning Rate": 3.9820039402875055e-05, "Pretrain/Loss": 2.0774617195129395, "Pretrain/Loss (Raw)": 2.1300439834594727, "Pretrain/Step": 3043, "Pretrain/Step Time": 8.87181212566793} +{"Pretrain/Learning Rate": 3.98132012414089e-05, "Pretrain/Loss": 2.077725887298584, "Pretrain/Loss (Raw)": 2.1312005519866943, "Pretrain/Step": 3044, "Pretrain/Step Time": 8.871705261990428} +{"Pretrain/Learning Rate": 3.9806361371614576e-05, "Pretrain/Loss": 2.0773613452911377, "Pretrain/Loss (Raw)": 2.030991315841675, "Pretrain/Step": 3045, "Pretrain/Step Time": 8.865861946716905} +{"Pretrain/Learning Rate": 3.979951979428089e-05, "Pretrain/Loss": 2.078813076019287, "Pretrain/Loss (Raw)": 2.2399251461029053, "Pretrain/Step": 3046, "Pretrain/Step Time": 8.866159884259105} +{"Pretrain/Learning Rate": 3.9792676510196835e-05, "Pretrain/Loss": 2.0784194469451904, "Pretrain/Loss (Raw)": 2.031871795654297, "Pretrain/Step": 3047, "Pretrain/Step Time": 8.867099029943347} +{"Pretrain/Learning Rate": 3.978583152015163e-05, "Pretrain/Loss": 2.0770769119262695, "Pretrain/Loss (Raw)": 1.9630179405212402, "Pretrain/Step": 3048, "Pretrain/Step Time": 8.867835454642773} +{"Pretrain/Learning Rate": 3.977898482493466e-05, "Pretrain/Loss": 2.076808452606201, "Pretrain/Loss (Raw)": 2.2068958282470703, "Pretrain/Step": 3049, "Pretrain/Step Time": 8.863429607823491} +{"Pretrain/Learning Rate": 3.977213642533552e-05, "Pretrain/Loss": 2.0762834548950195, "Pretrain/Loss (Raw)": 2.041912794113159, "Pretrain/Step": 3050, "Pretrain/Step Time": 8.863179231062531} +{"Pretrain/Learning Rate": 3.976528632214399e-05, "Pretrain/Loss": 2.0771267414093018, "Pretrain/Loss (Raw)": 2.1364376544952393, "Pretrain/Step": 3051, "Pretrain/Step Time": 8.862485717982054} +{"Pretrain/Learning Rate": 3.975843451615007e-05, "Pretrain/Loss": 2.078387975692749, "Pretrain/Loss (Raw)": 2.2699215412139893, "Pretrain/Step": 3052, "Pretrain/Step Time": 8.855484697967768} +{"Pretrain/Learning Rate": 3.9751581008143946e-05, "Pretrain/Loss": 2.076632499694824, "Pretrain/Loss (Raw)": 1.8858081102371216, "Pretrain/Step": 3053, "Pretrain/Step Time": 8.85396515391767} +{"Pretrain/Learning Rate": 3.9744725798915974e-05, "Pretrain/Loss": 2.0770516395568848, "Pretrain/Loss (Raw)": 2.119112014770508, "Pretrain/Step": 3054, "Pretrain/Step Time": 8.863054253160954} +{"Pretrain/Learning Rate": 3.973786888925675e-05, "Pretrain/Loss": 2.0748095512390137, "Pretrain/Loss (Raw)": 1.9782471656799316, "Pretrain/Step": 3055, "Pretrain/Step Time": 8.863701172173023} +{"Pretrain/Learning Rate": 3.973101027995704e-05, "Pretrain/Loss": 2.075660228729248, "Pretrain/Loss (Raw)": 2.2343404293060303, "Pretrain/Step": 3056, "Pretrain/Step Time": 8.858975572511554} +{"Pretrain/Learning Rate": 3.9724149971807814e-05, "Pretrain/Loss": 2.077838182449341, "Pretrain/Loss (Raw)": 2.1780312061309814, "Pretrain/Step": 3057, "Pretrain/Step Time": 8.859032621607184} +{"Pretrain/Learning Rate": 3.9717287965600224e-05, "Pretrain/Loss": 2.0772454738616943, "Pretrain/Loss (Raw)": 1.8965067863464355, "Pretrain/Step": 3058, "Pretrain/Step Time": 8.852029349654913} +{"Pretrain/Learning Rate": 3.971042426212563e-05, "Pretrain/Loss": 2.076237440109253, "Pretrain/Loss (Raw)": 1.8535888195037842, "Pretrain/Step": 3059, "Pretrain/Step Time": 8.866448417305946} +{"Pretrain/Learning Rate": 3.970355886217561e-05, "Pretrain/Loss": 2.074993371963501, "Pretrain/Loss (Raw)": 1.943955898284912, "Pretrain/Step": 3060, "Pretrain/Step Time": 8.864334343001246} +{"Pretrain/Learning Rate": 3.9696691766541884e-05, "Pretrain/Loss": 2.0738613605499268, "Pretrain/Loss (Raw)": 2.070700168609619, "Pretrain/Step": 3061, "Pretrain/Step Time": 8.87102155201137} +{"Pretrain/Learning Rate": 3.968982297601641e-05, "Pretrain/Loss": 2.074601650238037, "Pretrain/Loss (Raw)": 2.3301496505737305, "Pretrain/Step": 3062, "Pretrain/Step Time": 8.86747356876731} +{"Pretrain/Learning Rate": 3.9682952491391326e-05, "Pretrain/Loss": 2.0753753185272217, "Pretrain/Loss (Raw)": 2.156041145324707, "Pretrain/Step": 3063, "Pretrain/Step Time": 8.869835374876857} +{"Pretrain/Learning Rate": 3.967608031345898e-05, "Pretrain/Loss": 2.075315475463867, "Pretrain/Loss (Raw)": 2.108900308609009, "Pretrain/Step": 3064, "Pretrain/Step Time": 8.865555115044117} +{"Pretrain/Learning Rate": 3.96692064430119e-05, "Pretrain/Loss": 2.0765225887298584, "Pretrain/Loss (Raw)": 2.050936698913574, "Pretrain/Step": 3065, "Pretrain/Step Time": 8.864084983244538} +{"Pretrain/Learning Rate": 3.96623308808428e-05, "Pretrain/Loss": 2.075510025024414, "Pretrain/Loss (Raw)": 2.0723519325256348, "Pretrain/Step": 3066, "Pretrain/Step Time": 8.86108254827559} +{"Pretrain/Learning Rate": 3.965545362774461e-05, "Pretrain/Loss": 2.0743889808654785, "Pretrain/Loss (Raw)": 2.0556414127349854, "Pretrain/Step": 3067, "Pretrain/Step Time": 8.855182813480496} +{"Pretrain/Learning Rate": 3.964857468451045e-05, "Pretrain/Loss": 2.0726211071014404, "Pretrain/Loss (Raw)": 2.0552728176116943, "Pretrain/Step": 3068, "Pretrain/Step Time": 8.872241538017988} +{"Pretrain/Learning Rate": 3.9641694051933644e-05, "Pretrain/Loss": 2.072927951812744, "Pretrain/Loss (Raw)": 2.132699728012085, "Pretrain/Step": 3069, "Pretrain/Step Time": 8.871507558971643} +{"Pretrain/Learning Rate": 3.963481173080767e-05, "Pretrain/Loss": 2.073362350463867, "Pretrain/Loss (Raw)": 2.1980316638946533, "Pretrain/Step": 3070, "Pretrain/Step Time": 8.86464610695839} +{"Pretrain/Learning Rate": 3.962792772192626e-05, "Pretrain/Loss": 2.075413703918457, "Pretrain/Loss (Raw)": 2.0229499340057373, "Pretrain/Step": 3071, "Pretrain/Step Time": 8.868282420560718} +{"Pretrain/Learning Rate": 3.962104202608329e-05, "Pretrain/Loss": 2.0777039527893066, "Pretrain/Loss (Raw)": 2.265531539916992, "Pretrain/Step": 3072, "Pretrain/Step Time": 8.867645578458905} +{"Pretrain/Learning Rate": 3.9614154644072854e-05, "Pretrain/Loss": 2.0769548416137695, "Pretrain/Loss (Raw)": 1.9902682304382324, "Pretrain/Step": 3073, "Pretrain/Step Time": 8.866713635623455} +{"Pretrain/Learning Rate": 3.960726557668924e-05, "Pretrain/Loss": 2.078324317932129, "Pretrain/Loss (Raw)": 1.9880547523498535, "Pretrain/Step": 3074, "Pretrain/Step Time": 8.875942341983318} +{"Pretrain/Learning Rate": 3.960037482472694e-05, "Pretrain/Loss": 2.078538656234741, "Pretrain/Loss (Raw)": 1.9860683679580688, "Pretrain/Step": 3075, "Pretrain/Step Time": 8.868807541206479} +{"Pretrain/Learning Rate": 3.95934823889806e-05, "Pretrain/Loss": 2.0775961875915527, "Pretrain/Loss (Raw)": 2.123257637023926, "Pretrain/Step": 3076, "Pretrain/Step Time": 8.871487833559513} +{"Pretrain/Learning Rate": 3.9586588270245115e-05, "Pretrain/Loss": 2.078293561935425, "Pretrain/Loss (Raw)": 2.1343469619750977, "Pretrain/Step": 3077, "Pretrain/Step Time": 8.871655758470297} +{"Pretrain/Learning Rate": 3.957969246931553e-05, "Pretrain/Loss": 2.079099655151367, "Pretrain/Loss (Raw)": 2.191650867462158, "Pretrain/Step": 3078, "Pretrain/Step Time": 8.876773437485099} +{"Pretrain/Learning Rate": 3.95727949869871e-05, "Pretrain/Loss": 2.080009698867798, "Pretrain/Loss (Raw)": 2.1605589389801025, "Pretrain/Step": 3079, "Pretrain/Step Time": 8.87406549602747} +{"Pretrain/Learning Rate": 3.95658958240553e-05, "Pretrain/Loss": 2.081266403198242, "Pretrain/Loss (Raw)": 1.9827412366867065, "Pretrain/Step": 3080, "Pretrain/Step Time": 8.872978894039989} +{"Pretrain/Learning Rate": 3.955899498131575e-05, "Pretrain/Loss": 2.0830166339874268, "Pretrain/Loss (Raw)": 2.2054784297943115, "Pretrain/Step": 3081, "Pretrain/Step Time": 8.870981162413955} +{"Pretrain/Learning Rate": 3.9552092459564294e-05, "Pretrain/Loss": 2.0825133323669434, "Pretrain/Loss (Raw)": 2.043550729751587, "Pretrain/Step": 3082, "Pretrain/Step Time": 8.882209230214357} +{"Pretrain/Learning Rate": 3.9545188259596966e-05, "Pretrain/Loss": 2.081319570541382, "Pretrain/Loss (Raw)": 2.0126872062683105, "Pretrain/Step": 3083, "Pretrain/Step Time": 8.879694880917668} +{"Pretrain/Learning Rate": 3.953828238220998e-05, "Pretrain/Loss": 2.0808675289154053, "Pretrain/Loss (Raw)": 2.0501840114593506, "Pretrain/Step": 3084, "Pretrain/Step Time": 8.879122987389565} +{"Pretrain/Learning Rate": 3.9531374828199774e-05, "Pretrain/Loss": 2.078141212463379, "Pretrain/Loss (Raw)": 2.054400682449341, "Pretrain/Step": 3085, "Pretrain/Step Time": 8.86660630069673} +{"Pretrain/Learning Rate": 3.952446559836295e-05, "Pretrain/Loss": 2.0793099403381348, "Pretrain/Loss (Raw)": 2.1691057682037354, "Pretrain/Step": 3086, "Pretrain/Step Time": 8.865753190591931} +{"Pretrain/Learning Rate": 3.95175546934963e-05, "Pretrain/Loss": 2.0794456005096436, "Pretrain/Loss (Raw)": 2.221524715423584, "Pretrain/Step": 3087, "Pretrain/Step Time": 8.863681642338634} +{"Pretrain/Learning Rate": 3.951064211439684e-05, "Pretrain/Loss": 2.0809245109558105, "Pretrain/Loss (Raw)": 2.1505355834960938, "Pretrain/Step": 3088, "Pretrain/Step Time": 8.863097451627254} +{"Pretrain/Learning Rate": 3.9503727861861756e-05, "Pretrain/Loss": 2.081118106842041, "Pretrain/Loss (Raw)": 2.0260746479034424, "Pretrain/Step": 3089, "Pretrain/Step Time": 8.864978848025203} +{"Pretrain/Learning Rate": 3.9496811936688425e-05, "Pretrain/Loss": 2.079002618789673, "Pretrain/Loss (Raw)": 2.0412111282348633, "Pretrain/Step": 3090, "Pretrain/Step Time": 8.869707910344005} +{"Pretrain/Learning Rate": 3.9489894339674435e-05, "Pretrain/Loss": 2.0823941230773926, "Pretrain/Loss (Raw)": 2.1111199855804443, "Pretrain/Step": 3091, "Pretrain/Step Time": 8.869788251817226} +{"Pretrain/Learning Rate": 3.948297507161756e-05, "Pretrain/Loss": 2.081845283508301, "Pretrain/Loss (Raw)": 2.0562572479248047, "Pretrain/Step": 3092, "Pretrain/Step Time": 8.865178084000945} +{"Pretrain/Learning Rate": 3.947605413331574e-05, "Pretrain/Loss": 2.083911657333374, "Pretrain/Loss (Raw)": 2.2115328311920166, "Pretrain/Step": 3093, "Pretrain/Step Time": 8.861895641312003} +{"Pretrain/Learning Rate": 3.946913152556715e-05, "Pretrain/Loss": 2.0838541984558105, "Pretrain/Loss (Raw)": 2.190239667892456, "Pretrain/Step": 3094, "Pretrain/Step Time": 8.857601325958967} +{"Pretrain/Learning Rate": 3.946220724917013e-05, "Pretrain/Loss": 2.085024833679199, "Pretrain/Loss (Raw)": 1.9504179954528809, "Pretrain/Step": 3095, "Pretrain/Step Time": 8.854373464360833} +{"Pretrain/Learning Rate": 3.945528130492322e-05, "Pretrain/Loss": 2.0829110145568848, "Pretrain/Loss (Raw)": 2.0646889209747314, "Pretrain/Step": 3096, "Pretrain/Step Time": 8.851570991799235} +{"Pretrain/Learning Rate": 3.944835369362516e-05, "Pretrain/Loss": 2.084017276763916, "Pretrain/Loss (Raw)": 2.1088850498199463, "Pretrain/Step": 3097, "Pretrain/Step Time": 8.868013836443424} +{"Pretrain/Learning Rate": 3.9441424416074866e-05, "Pretrain/Loss": 2.0841307640075684, "Pretrain/Loss (Raw)": 2.158130407333374, "Pretrain/Step": 3098, "Pretrain/Step Time": 8.867815373465419} +{"Pretrain/Learning Rate": 3.9434493473071456e-05, "Pretrain/Loss": 2.085162401199341, "Pretrain/Loss (Raw)": 2.0463294982910156, "Pretrain/Step": 3099, "Pretrain/Step Time": 8.864946257323027} +{"Pretrain/Learning Rate": 3.9427560865414246e-05, "Pretrain/Loss": 2.08473539352417, "Pretrain/Loss (Raw)": 2.0525567531585693, "Pretrain/Step": 3100, "Pretrain/Step Time": 8.857890965417027} +{"Pretrain/Learning Rate": 3.942062659390273e-05, "Pretrain/Loss": 2.08367919921875, "Pretrain/Loss (Raw)": 2.032092809677124, "Pretrain/Step": 3101, "Pretrain/Step Time": 8.859357491135597} +{"Pretrain/Learning Rate": 3.94136906593366e-05, "Pretrain/Loss": 2.0855655670166016, "Pretrain/Loss (Raw)": 2.210883617401123, "Pretrain/Step": 3102, "Pretrain/Step Time": 8.855441564694047} +{"Pretrain/Learning Rate": 3.940675306251574e-05, "Pretrain/Loss": 2.0852296352386475, "Pretrain/Loss (Raw)": 1.9166311025619507, "Pretrain/Step": 3103, "Pretrain/Step Time": 8.856507627293468} +{"Pretrain/Learning Rate": 3.939981380424024e-05, "Pretrain/Loss": 2.0861315727233887, "Pretrain/Loss (Raw)": 2.19923996925354, "Pretrain/Step": 3104, "Pretrain/Step Time": 8.86543338932097} +{"Pretrain/Learning Rate": 3.939287288531035e-05, "Pretrain/Loss": 2.086193084716797, "Pretrain/Loss (Raw)": 2.156419515609741, "Pretrain/Step": 3105, "Pretrain/Step Time": 8.855688916519284} +{"Pretrain/Learning Rate": 3.938593030652654e-05, "Pretrain/Loss": 2.08834171295166, "Pretrain/Loss (Raw)": 2.0986759662628174, "Pretrain/Step": 3106, "Pretrain/Step Time": 8.860195092856884} +{"Pretrain/Learning Rate": 3.937898606868946e-05, "Pretrain/Loss": 2.0888161659240723, "Pretrain/Loss (Raw)": 2.1394708156585693, "Pretrain/Step": 3107, "Pretrain/Step Time": 8.861012732610106} +{"Pretrain/Learning Rate": 3.9372040172599956e-05, "Pretrain/Loss": 2.089423656463623, "Pretrain/Loss (Raw)": 2.1754462718963623, "Pretrain/Step": 3108, "Pretrain/Step Time": 8.862203722819686} +{"Pretrain/Learning Rate": 3.936509261905905e-05, "Pretrain/Loss": 2.089965343475342, "Pretrain/Loss (Raw)": 2.1148722171783447, "Pretrain/Step": 3109, "Pretrain/Step Time": 8.8615384940058} +{"Pretrain/Learning Rate": 3.935814340886797e-05, "Pretrain/Loss": 2.088822364807129, "Pretrain/Loss (Raw)": 2.022716522216797, "Pretrain/Step": 3110, "Pretrain/Step Time": 8.859130198135972} +{"Pretrain/Learning Rate": 3.935119254282814e-05, "Pretrain/Loss": 2.0895299911499023, "Pretrain/Loss (Raw)": 2.2499351501464844, "Pretrain/Step": 3111, "Pretrain/Step Time": 8.859157018363476} +{"Pretrain/Learning Rate": 3.934424002174115e-05, "Pretrain/Loss": 2.0880823135375977, "Pretrain/Loss (Raw)": 2.0031185150146484, "Pretrain/Step": 3112, "Pretrain/Step Time": 8.870989702641964} +{"Pretrain/Learning Rate": 3.9337285846408826e-05, "Pretrain/Loss": 2.086639404296875, "Pretrain/Loss (Raw)": 1.979935646057129, "Pretrain/Step": 3113, "Pretrain/Step Time": 8.864547289907932} +{"Pretrain/Learning Rate": 3.9330330017633126e-05, "Pretrain/Loss": 2.0879733562469482, "Pretrain/Loss (Raw)": 2.23856258392334, "Pretrain/Step": 3114, "Pretrain/Step Time": 8.868851613253355} +{"Pretrain/Learning Rate": 3.932337253621624e-05, "Pretrain/Loss": 2.088050365447998, "Pretrain/Loss (Raw)": 2.1587376594543457, "Pretrain/Step": 3115, "Pretrain/Step Time": 8.87379052117467} +{"Pretrain/Learning Rate": 3.9316413402960553e-05, "Pretrain/Loss": 2.0898332595825195, "Pretrain/Loss (Raw)": 2.230696201324463, "Pretrain/Step": 3116, "Pretrain/Step Time": 8.87660708092153} +{"Pretrain/Learning Rate": 3.93094526186686e-05, "Pretrain/Loss": 2.090064525604248, "Pretrain/Loss (Raw)": 2.1550333499908447, "Pretrain/Step": 3117, "Pretrain/Step Time": 8.872726248577237} +{"Pretrain/Learning Rate": 3.930249018414315e-05, "Pretrain/Loss": 2.090925693511963, "Pretrain/Loss (Raw)": 2.1928303241729736, "Pretrain/Step": 3118, "Pretrain/Step Time": 8.876406867057085} +{"Pretrain/Learning Rate": 3.9295526100187126e-05, "Pretrain/Loss": 2.091465711593628, "Pretrain/Loss (Raw)": 2.2130253314971924, "Pretrain/Step": 3119, "Pretrain/Step Time": 8.883027235046029} +{"Pretrain/Learning Rate": 3.928856036760368e-05, "Pretrain/Loss": 2.0923538208007812, "Pretrain/Loss (Raw)": 2.1121745109558105, "Pretrain/Step": 3120, "Pretrain/Step Time": 8.87245294637978} +{"Pretrain/Learning Rate": 3.9281592987196115e-05, "Pretrain/Loss": 2.094511032104492, "Pretrain/Loss (Raw)": 2.1116714477539062, "Pretrain/Step": 3121, "Pretrain/Step Time": 8.87194101139903} +{"Pretrain/Learning Rate": 3.9274623959767945e-05, "Pretrain/Loss": 2.0933587551116943, "Pretrain/Loss (Raw)": 2.0698745250701904, "Pretrain/Step": 3122, "Pretrain/Step Time": 8.871088802814484} +{"Pretrain/Learning Rate": 3.9267653286122886e-05, "Pretrain/Loss": 2.093252658843994, "Pretrain/Loss (Raw)": 2.0580027103424072, "Pretrain/Step": 3123, "Pretrain/Step Time": 8.871594782918692} +{"Pretrain/Learning Rate": 3.9260680967064814e-05, "Pretrain/Loss": 2.09293794631958, "Pretrain/Loss (Raw)": 2.1689233779907227, "Pretrain/Step": 3124, "Pretrain/Step Time": 8.868614679202437} +{"Pretrain/Learning Rate": 3.9253707003397814e-05, "Pretrain/Loss": 2.0926966667175293, "Pretrain/Loss (Raw)": 1.9651724100112915, "Pretrain/Step": 3125, "Pretrain/Step Time": 8.87492711097002} +{"Pretrain/Learning Rate": 3.924673139592616e-05, "Pretrain/Loss": 2.090418815612793, "Pretrain/Loss (Raw)": 1.8729947805404663, "Pretrain/Step": 3126, "Pretrain/Step Time": 8.875608153641224} +{"Pretrain/Learning Rate": 3.9239754145454304e-05, "Pretrain/Loss": 2.0882680416107178, "Pretrain/Loss (Raw)": 1.951461672782898, "Pretrain/Step": 3127, "Pretrain/Step Time": 8.864306585863233} +{"Pretrain/Learning Rate": 3.92327752527869e-05, "Pretrain/Loss": 2.0885491371154785, "Pretrain/Loss (Raw)": 2.2293319702148438, "Pretrain/Step": 3128, "Pretrain/Step Time": 8.864215573295951} +{"Pretrain/Learning Rate": 3.922579471872879e-05, "Pretrain/Loss": 2.0870089530944824, "Pretrain/Loss (Raw)": 2.0557827949523926, "Pretrain/Step": 3129, "Pretrain/Step Time": 8.857766289263964} +{"Pretrain/Learning Rate": 3.9218812544085004e-05, "Pretrain/Loss": 2.0870394706726074, "Pretrain/Loss (Raw)": 2.0756499767303467, "Pretrain/Step": 3130, "Pretrain/Step Time": 8.861839145421982} +{"Pretrain/Learning Rate": 3.921182872966075e-05, "Pretrain/Loss": 2.0869669914245605, "Pretrain/Loss (Raw)": 2.1608939170837402, "Pretrain/Step": 3131, "Pretrain/Step Time": 8.857332035899162} +{"Pretrain/Learning Rate": 3.920484327626144e-05, "Pretrain/Loss": 2.0875048637390137, "Pretrain/Loss (Raw)": 2.236769199371338, "Pretrain/Step": 3132, "Pretrain/Step Time": 8.854868745431304} +{"Pretrain/Learning Rate": 3.919785618469266e-05, "Pretrain/Loss": 2.086355209350586, "Pretrain/Loss (Raw)": 2.07283353805542, "Pretrain/Step": 3133, "Pretrain/Step Time": 8.866502705961466} +{"Pretrain/Learning Rate": 3.9190867455760213e-05, "Pretrain/Loss": 2.0880959033966064, "Pretrain/Loss (Raw)": 2.107398271560669, "Pretrain/Step": 3134, "Pretrain/Step Time": 8.86744007281959} +{"Pretrain/Learning Rate": 3.918387709027005e-05, "Pretrain/Loss": 2.0886881351470947, "Pretrain/Loss (Raw)": 2.213486433029175, "Pretrain/Step": 3135, "Pretrain/Step Time": 8.86598457954824} +{"Pretrain/Learning Rate": 3.917688508902835e-05, "Pretrain/Loss": 2.088642120361328, "Pretrain/Loss (Raw)": 1.9101135730743408, "Pretrain/Step": 3136, "Pretrain/Step Time": 8.863707158714533} +{"Pretrain/Learning Rate": 3.916989145284146e-05, "Pretrain/Loss": 2.089235782623291, "Pretrain/Loss (Raw)": 2.0165293216705322, "Pretrain/Step": 3137, "Pretrain/Step Time": 8.859068982303143} +{"Pretrain/Learning Rate": 3.9162896182515915e-05, "Pretrain/Loss": 2.087824821472168, "Pretrain/Loss (Raw)": 2.1238415241241455, "Pretrain/Step": 3138, "Pretrain/Step Time": 8.8566461391747} +{"Pretrain/Learning Rate": 3.9155899278858445e-05, "Pretrain/Loss": 2.088218927383423, "Pretrain/Loss (Raw)": 2.158581018447876, "Pretrain/Step": 3139, "Pretrain/Step Time": 8.858828037977219} +{"Pretrain/Learning Rate": 3.914890074267597e-05, "Pretrain/Loss": 2.0848374366760254, "Pretrain/Loss (Raw)": 1.8396753072738647, "Pretrain/Step": 3140, "Pretrain/Step Time": 8.859163058921695} +{"Pretrain/Learning Rate": 3.914190057477558e-05, "Pretrain/Loss": 2.0837595462799072, "Pretrain/Loss (Raw)": 2.1703786849975586, "Pretrain/Step": 3141, "Pretrain/Step Time": 8.869771923869848} +{"Pretrain/Learning Rate": 3.913489877596458e-05, "Pretrain/Loss": 2.082671642303467, "Pretrain/Loss (Raw)": 2.043940782546997, "Pretrain/Step": 3142, "Pretrain/Step Time": 8.862456256523728} +{"Pretrain/Learning Rate": 3.912789534705045e-05, "Pretrain/Loss": 2.0855045318603516, "Pretrain/Loss (Raw)": 2.180586576461792, "Pretrain/Step": 3143, "Pretrain/Step Time": 8.870621049776673} +{"Pretrain/Learning Rate": 3.912089028884085e-05, "Pretrain/Loss": 2.0860965251922607, "Pretrain/Loss (Raw)": 2.023872137069702, "Pretrain/Step": 3144, "Pretrain/Step Time": 8.866725677624345} +{"Pretrain/Learning Rate": 3.9113883602143645e-05, "Pretrain/Loss": 2.084717273712158, "Pretrain/Loss (Raw)": 1.8870744705200195, "Pretrain/Step": 3145, "Pretrain/Step Time": 8.866858761757612} +{"Pretrain/Learning Rate": 3.910687528776688e-05, "Pretrain/Loss": 2.085376262664795, "Pretrain/Loss (Raw)": 2.1453802585601807, "Pretrain/Step": 3146, "Pretrain/Step Time": 8.865063732489944} +{"Pretrain/Learning Rate": 3.9099865346518786e-05, "Pretrain/Loss": 2.0870108604431152, "Pretrain/Loss (Raw)": 2.081777572631836, "Pretrain/Step": 3147, "Pretrain/Step Time": 8.867204176262021} +{"Pretrain/Learning Rate": 3.909285377920777e-05, "Pretrain/Loss": 2.088042736053467, "Pretrain/Loss (Raw)": 2.15023136138916, "Pretrain/Step": 3148, "Pretrain/Step Time": 8.867119705304503} +{"Pretrain/Learning Rate": 3.908584058664245e-05, "Pretrain/Loss": 2.0891425609588623, "Pretrain/Loss (Raw)": 2.180786371231079, "Pretrain/Step": 3149, "Pretrain/Step Time": 8.882352164015174} +{"Pretrain/Learning Rate": 3.907882576963162e-05, "Pretrain/Loss": 2.0904393196105957, "Pretrain/Loss (Raw)": 2.2092654705047607, "Pretrain/Step": 3150, "Pretrain/Step Time": 8.869149137288332} +{"Pretrain/Learning Rate": 3.907180932898427e-05, "Pretrain/Loss": 2.0908846855163574, "Pretrain/Loss (Raw)": 2.0688390731811523, "Pretrain/Step": 3151, "Pretrain/Step Time": 8.871340814977884} +{"Pretrain/Learning Rate": 3.9064791265509546e-05, "Pretrain/Loss": 2.090129852294922, "Pretrain/Loss (Raw)": 2.0017971992492676, "Pretrain/Step": 3152, "Pretrain/Step Time": 8.873565820977092} +{"Pretrain/Learning Rate": 3.905777158001682e-05, "Pretrain/Loss": 2.0885043144226074, "Pretrain/Loss (Raw)": 1.8067123889923096, "Pretrain/Step": 3153, "Pretrain/Step Time": 8.874684879556298} +{"Pretrain/Learning Rate": 3.905075027331564e-05, "Pretrain/Loss": 2.089977741241455, "Pretrain/Loss (Raw)": 2.1199100017547607, "Pretrain/Step": 3154, "Pretrain/Step Time": 8.87056215107441} +{"Pretrain/Learning Rate": 3.9043727346215726e-05, "Pretrain/Loss": 2.090888738632202, "Pretrain/Loss (Raw)": 2.191047191619873, "Pretrain/Step": 3155, "Pretrain/Step Time": 8.869718331843615} +{"Pretrain/Learning Rate": 3.9036702799527e-05, "Pretrain/Loss": 2.089855909347534, "Pretrain/Loss (Raw)": 1.9271870851516724, "Pretrain/Step": 3156, "Pretrain/Step Time": 8.88495040498674} +{"Pretrain/Learning Rate": 3.902967663405956e-05, "Pretrain/Loss": 2.091581106185913, "Pretrain/Loss (Raw)": 2.1648435592651367, "Pretrain/Step": 3157, "Pretrain/Step Time": 8.879426309838891} +{"Pretrain/Learning Rate": 3.90226488506237e-05, "Pretrain/Loss": 2.0918869972229004, "Pretrain/Loss (Raw)": 2.1424782276153564, "Pretrain/Step": 3158, "Pretrain/Step Time": 8.883049372583628} +{"Pretrain/Learning Rate": 3.9015619450029904e-05, "Pretrain/Loss": 2.0928986072540283, "Pretrain/Loss (Raw)": 2.2063779830932617, "Pretrain/Step": 3159, "Pretrain/Step Time": 8.876093020662665} +{"Pretrain/Learning Rate": 3.9008588433088825e-05, "Pretrain/Loss": 2.0908467769622803, "Pretrain/Loss (Raw)": 2.037717580795288, "Pretrain/Step": 3160, "Pretrain/Step Time": 8.874191235750914} +{"Pretrain/Learning Rate": 3.900155580061132e-05, "Pretrain/Loss": 2.0865871906280518, "Pretrain/Loss (Raw)": 1.9477734565734863, "Pretrain/Step": 3161, "Pretrain/Step Time": 8.8756014816463} +{"Pretrain/Learning Rate": 3.899452155340842e-05, "Pretrain/Loss": 2.0869455337524414, "Pretrain/Loss (Raw)": 1.9401085376739502, "Pretrain/Step": 3162, "Pretrain/Step Time": 8.869609402492642} +{"Pretrain/Learning Rate": 3.898748569229135e-05, "Pretrain/Loss": 2.0857319831848145, "Pretrain/Loss (Raw)": 2.0599172115325928, "Pretrain/Step": 3163, "Pretrain/Step Time": 8.875828607007861} +{"Pretrain/Learning Rate": 3.898044821807152e-05, "Pretrain/Loss": 2.0855088233947754, "Pretrain/Loss (Raw)": 1.988763451576233, "Pretrain/Step": 3164, "Pretrain/Step Time": 8.87801525555551} +{"Pretrain/Learning Rate": 3.897340913156052e-05, "Pretrain/Loss": 2.086376667022705, "Pretrain/Loss (Raw)": 2.1768648624420166, "Pretrain/Step": 3165, "Pretrain/Step Time": 8.87918795645237} +{"Pretrain/Learning Rate": 3.896636843357014e-05, "Pretrain/Loss": 2.084590435028076, "Pretrain/Loss (Raw)": 1.8712241649627686, "Pretrain/Step": 3166, "Pretrain/Step Time": 8.87203442491591} +{"Pretrain/Learning Rate": 3.895932612491233e-05, "Pretrain/Loss": 2.084900140762329, "Pretrain/Loss (Raw)": 2.0216968059539795, "Pretrain/Step": 3167, "Pretrain/Step Time": 8.869591023772955} +{"Pretrain/Learning Rate": 3.895228220639926e-05, "Pretrain/Loss": 2.0854263305664062, "Pretrain/Loss (Raw)": 1.98415207862854, "Pretrain/Step": 3168, "Pretrain/Step Time": 8.872179923579097} +{"Pretrain/Learning Rate": 3.8945236678843266e-05, "Pretrain/Loss": 2.0869030952453613, "Pretrain/Loss (Raw)": 2.0751969814300537, "Pretrain/Step": 3169, "Pretrain/Step Time": 8.869948253035545} +{"Pretrain/Learning Rate": 3.893818954305686e-05, "Pretrain/Loss": 2.0865657329559326, "Pretrain/Loss (Raw)": 2.002143621444702, "Pretrain/Step": 3170, "Pretrain/Step Time": 8.86528210900724} +{"Pretrain/Learning Rate": 3.893114079985276e-05, "Pretrain/Loss": 2.0858559608459473, "Pretrain/Loss (Raw)": 2.039194107055664, "Pretrain/Step": 3171, "Pretrain/Step Time": 8.868595488369465} +{"Pretrain/Learning Rate": 3.892409045004385e-05, "Pretrain/Loss": 2.085944175720215, "Pretrain/Loss (Raw)": 2.142493724822998, "Pretrain/Step": 3172, "Pretrain/Step Time": 8.871074728667736} +{"Pretrain/Learning Rate": 3.891703849444322e-05, "Pretrain/Loss": 2.0852906703948975, "Pretrain/Loss (Raw)": 1.947365403175354, "Pretrain/Step": 3173, "Pretrain/Step Time": 8.871238980442286} +{"Pretrain/Learning Rate": 3.890998493386414e-05, "Pretrain/Loss": 2.085014820098877, "Pretrain/Loss (Raw)": 2.204615592956543, "Pretrain/Step": 3174, "Pretrain/Step Time": 8.879717387259007} +{"Pretrain/Learning Rate": 3.890292976912005e-05, "Pretrain/Loss": 2.0861284732818604, "Pretrain/Loss (Raw)": 2.174409866333008, "Pretrain/Step": 3175, "Pretrain/Step Time": 8.875314453616738} +{"Pretrain/Learning Rate": 3.889587300102457e-05, "Pretrain/Loss": 2.0879428386688232, "Pretrain/Loss (Raw)": 2.195232629776001, "Pretrain/Step": 3176, "Pretrain/Step Time": 8.877258237451315} +{"Pretrain/Learning Rate": 3.8888814630391556e-05, "Pretrain/Loss": 2.0869808197021484, "Pretrain/Loss (Raw)": 2.083784580230713, "Pretrain/Step": 3177, "Pretrain/Step Time": 8.875433340668678} +{"Pretrain/Learning Rate": 3.8881754658034986e-05, "Pretrain/Loss": 2.087613821029663, "Pretrain/Loss (Raw)": 2.1229097843170166, "Pretrain/Step": 3178, "Pretrain/Step Time": 8.876502580940723} +{"Pretrain/Learning Rate": 3.8874693084769055e-05, "Pretrain/Loss": 2.0868964195251465, "Pretrain/Loss (Raw)": 2.044614553451538, "Pretrain/Step": 3179, "Pretrain/Step Time": 8.888075735419989} +{"Pretrain/Learning Rate": 3.8867629911408135e-05, "Pretrain/Loss": 2.0852644443511963, "Pretrain/Loss (Raw)": 2.061044692993164, "Pretrain/Step": 3180, "Pretrain/Step Time": 8.884642411023378} +{"Pretrain/Learning Rate": 3.886056513876679e-05, "Pretrain/Loss": 2.087421417236328, "Pretrain/Loss (Raw)": 2.1619203090667725, "Pretrain/Step": 3181, "Pretrain/Step Time": 8.888337487354875} +{"Pretrain/Learning Rate": 3.885349876765976e-05, "Pretrain/Loss": 2.0881173610687256, "Pretrain/Loss (Raw)": 2.20816707611084, "Pretrain/Step": 3182, "Pretrain/Step Time": 8.878030240535736} +{"Pretrain/Learning Rate": 3.884643079890197e-05, "Pretrain/Loss": 2.0897722244262695, "Pretrain/Loss (Raw)": 2.1900978088378906, "Pretrain/Step": 3183, "Pretrain/Step Time": 8.882527381181717} +{"Pretrain/Learning Rate": 3.883936123330853e-05, "Pretrain/Loss": 2.088808059692383, "Pretrain/Loss (Raw)": 2.1108946800231934, "Pretrain/Step": 3184, "Pretrain/Step Time": 8.880265535786748} +{"Pretrain/Learning Rate": 3.883229007169474e-05, "Pretrain/Loss": 2.08728289604187, "Pretrain/Loss (Raw)": 1.9828338623046875, "Pretrain/Step": 3185, "Pretrain/Step Time": 8.8792516682297} +{"Pretrain/Learning Rate": 3.8825217314876084e-05, "Pretrain/Loss": 2.0877108573913574, "Pretrain/Loss (Raw)": 1.951253890991211, "Pretrain/Step": 3186, "Pretrain/Step Time": 8.881979711353779} +{"Pretrain/Learning Rate": 3.881814296366822e-05, "Pretrain/Loss": 2.089449405670166, "Pretrain/Loss (Raw)": 2.0761754512786865, "Pretrain/Step": 3187, "Pretrain/Step Time": 8.874481078237295} +{"Pretrain/Learning Rate": 3.881106701888699e-05, "Pretrain/Loss": 2.0905327796936035, "Pretrain/Loss (Raw)": 2.0825986862182617, "Pretrain/Step": 3188, "Pretrain/Step Time": 8.87529026158154} +{"Pretrain/Learning Rate": 3.880398948134845e-05, "Pretrain/Loss": 2.0900816917419434, "Pretrain/Loss (Raw)": 2.012965202331543, "Pretrain/Step": 3189, "Pretrain/Step Time": 8.879788966849446} +{"Pretrain/Learning Rate": 3.879691035186878e-05, "Pretrain/Loss": 2.0873847007751465, "Pretrain/Loss (Raw)": 1.9849474430084229, "Pretrain/Step": 3190, "Pretrain/Step Time": 8.878692423924804} +{"Pretrain/Learning Rate": 3.8789829631264394e-05, "Pretrain/Loss": 2.0867161750793457, "Pretrain/Loss (Raw)": 2.070460796356201, "Pretrain/Step": 3191, "Pretrain/Step Time": 8.876357559114695} +{"Pretrain/Learning Rate": 3.878274732035188e-05, "Pretrain/Loss": 2.086747169494629, "Pretrain/Loss (Raw)": 2.112825393676758, "Pretrain/Step": 3192, "Pretrain/Step Time": 8.878617433831096} +{"Pretrain/Learning Rate": 3.8775663419948e-05, "Pretrain/Loss": 2.086932420730591, "Pretrain/Loss (Raw)": 2.0746853351593018, "Pretrain/Step": 3193, "Pretrain/Step Time": 8.880336243659258} +{"Pretrain/Learning Rate": 3.87685779308697e-05, "Pretrain/Loss": 2.086627244949341, "Pretrain/Loss (Raw)": 2.0332632064819336, "Pretrain/Step": 3194, "Pretrain/Step Time": 8.886624187231064} +{"Pretrain/Learning Rate": 3.8761490853934115e-05, "Pretrain/Loss": 2.086613655090332, "Pretrain/Loss (Raw)": 2.0539307594299316, "Pretrain/Step": 3195, "Pretrain/Step Time": 8.889122486114502} +{"Pretrain/Learning Rate": 3.875440218995856e-05, "Pretrain/Loss": 2.0869216918945312, "Pretrain/Loss (Raw)": 2.0946788787841797, "Pretrain/Step": 3196, "Pretrain/Step Time": 8.875304514542222} +{"Pretrain/Learning Rate": 3.874731193976052e-05, "Pretrain/Loss": 2.0866241455078125, "Pretrain/Loss (Raw)": 2.094648599624634, "Pretrain/Step": 3197, "Pretrain/Step Time": 8.872360229492188} +{"Pretrain/Learning Rate": 3.87402201041577e-05, "Pretrain/Loss": 2.0843875408172607, "Pretrain/Loss (Raw)": 1.9117146730422974, "Pretrain/Step": 3198, "Pretrain/Step Time": 8.873193034902215} +{"Pretrain/Learning Rate": 3.8733126683967946e-05, "Pretrain/Loss": 2.0858068466186523, "Pretrain/Loss (Raw)": 2.2046313285827637, "Pretrain/Step": 3199, "Pretrain/Step Time": 8.871307902038097} +{"Pretrain/Learning Rate": 3.872603168000931e-05, "Pretrain/Loss": 2.083763599395752, "Pretrain/Loss (Raw)": 2.0039820671081543, "Pretrain/Step": 3200, "Pretrain/Step Time": 8.873777186498046} +{"Pretrain/Learning Rate": 3.871893509310003e-05, "Pretrain/Loss": 2.084630012512207, "Pretrain/Loss (Raw)": 2.1011688709259033, "Pretrain/Step": 3201, "Pretrain/Step Time": 8.873998476192355} +{"Pretrain/Learning Rate": 3.87118369240585e-05, "Pretrain/Loss": 2.084644317626953, "Pretrain/Loss (Raw)": 1.9899051189422607, "Pretrain/Step": 3202, "Pretrain/Step Time": 8.866138760000467} +{"Pretrain/Learning Rate": 3.870473717370333e-05, "Pretrain/Loss": 2.0856127738952637, "Pretrain/Loss (Raw)": 2.110048770904541, "Pretrain/Step": 3203, "Pretrain/Step Time": 8.872524619102478} +{"Pretrain/Learning Rate": 3.869763584285328e-05, "Pretrain/Loss": 2.0849409103393555, "Pretrain/Loss (Raw)": 2.037224054336548, "Pretrain/Step": 3204, "Pretrain/Step Time": 8.867499377578497} +{"Pretrain/Learning Rate": 3.869053293232733e-05, "Pretrain/Loss": 2.0854830741882324, "Pretrain/Loss (Raw)": 2.203733444213867, "Pretrain/Step": 3205, "Pretrain/Step Time": 8.863274259492755} +{"Pretrain/Learning Rate": 3.8683428442944604e-05, "Pretrain/Loss": 2.0839996337890625, "Pretrain/Loss (Raw)": 2.001796245574951, "Pretrain/Step": 3206, "Pretrain/Step Time": 8.858998637646437} +{"Pretrain/Learning Rate": 3.8676322375524435e-05, "Pretrain/Loss": 2.0825600624084473, "Pretrain/Loss (Raw)": 1.9762778282165527, "Pretrain/Step": 3207, "Pretrain/Step Time": 8.851965611800551} +{"Pretrain/Learning Rate": 3.866921473088632e-05, "Pretrain/Loss": 2.0833778381347656, "Pretrain/Loss (Raw)": 2.087404727935791, "Pretrain/Step": 3208, "Pretrain/Step Time": 8.864841271191835} +{"Pretrain/Learning Rate": 3.866210550984996e-05, "Pretrain/Loss": 2.0812430381774902, "Pretrain/Loss (Raw)": 1.9322459697723389, "Pretrain/Step": 3209, "Pretrain/Step Time": 8.867340836673975} +{"Pretrain/Learning Rate": 3.86549947132352e-05, "Pretrain/Loss": 2.080327272415161, "Pretrain/Loss (Raw)": 1.9263180494308472, "Pretrain/Step": 3210, "Pretrain/Step Time": 8.856766302138567} +{"Pretrain/Learning Rate": 3.8647882341862115e-05, "Pretrain/Loss": 2.0812594890594482, "Pretrain/Loss (Raw)": 2.132023811340332, "Pretrain/Step": 3211, "Pretrain/Step Time": 8.859611295163631} +{"Pretrain/Learning Rate": 3.864076839655093e-05, "Pretrain/Loss": 2.080814838409424, "Pretrain/Loss (Raw)": 1.9932419061660767, "Pretrain/Step": 3212, "Pretrain/Step Time": 8.857998605817556} +{"Pretrain/Learning Rate": 3.863365287812205e-05, "Pretrain/Loss": 2.081348180770874, "Pretrain/Loss (Raw)": 2.1226930618286133, "Pretrain/Step": 3213, "Pretrain/Step Time": 8.855732103809714} +{"Pretrain/Learning Rate": 3.862653578739608e-05, "Pretrain/Loss": 2.0825304985046387, "Pretrain/Loss (Raw)": 2.3204309940338135, "Pretrain/Step": 3214, "Pretrain/Step Time": 8.85409346781671} +{"Pretrain/Learning Rate": 3.861941712519379e-05, "Pretrain/Loss": 2.080876350402832, "Pretrain/Loss (Raw)": 2.009819507598877, "Pretrain/Step": 3215, "Pretrain/Step Time": 8.856214424595237} +{"Pretrain/Learning Rate": 3.8612296892336144e-05, "Pretrain/Loss": 2.0807409286499023, "Pretrain/Loss (Raw)": 2.1331746578216553, "Pretrain/Step": 3216, "Pretrain/Step Time": 8.856102608144283} +{"Pretrain/Learning Rate": 3.8605175089644274e-05, "Pretrain/Loss": 2.0820963382720947, "Pretrain/Loss (Raw)": 2.1995902061462402, "Pretrain/Step": 3217, "Pretrain/Step Time": 8.859817761927843} +{"Pretrain/Learning Rate": 3.859805171793951e-05, "Pretrain/Loss": 2.0833611488342285, "Pretrain/Loss (Raw)": 2.2030820846557617, "Pretrain/Step": 3218, "Pretrain/Step Time": 8.854474917054176} +{"Pretrain/Learning Rate": 3.8590926778043335e-05, "Pretrain/Loss": 2.0828542709350586, "Pretrain/Loss (Raw)": 2.0462844371795654, "Pretrain/Step": 3219, "Pretrain/Step Time": 8.848904905840755} +{"Pretrain/Learning Rate": 3.858380027077745e-05, "Pretrain/Loss": 2.083796501159668, "Pretrain/Loss (Raw)": 2.1768205165863037, "Pretrain/Step": 3220, "Pretrain/Step Time": 8.844686256721616} +{"Pretrain/Learning Rate": 3.8576672196963705e-05, "Pretrain/Loss": 2.08327579498291, "Pretrain/Loss (Raw)": 2.1449053287506104, "Pretrain/Step": 3221, "Pretrain/Step Time": 8.844102008268237} +{"Pretrain/Learning Rate": 3.856954255742414e-05, "Pretrain/Loss": 2.0836591720581055, "Pretrain/Loss (Raw)": 2.239307165145874, "Pretrain/Step": 3222, "Pretrain/Step Time": 8.851637739688158} +{"Pretrain/Learning Rate": 3.8562411352980996e-05, "Pretrain/Loss": 2.0845797061920166, "Pretrain/Loss (Raw)": 2.068242311477661, "Pretrain/Step": 3223, "Pretrain/Step Time": 8.848310723900795} +{"Pretrain/Learning Rate": 3.8555278584456664e-05, "Pretrain/Loss": 2.0857977867126465, "Pretrain/Loss (Raw)": 2.2206122875213623, "Pretrain/Step": 3224, "Pretrain/Step Time": 8.850474627688527} +{"Pretrain/Learning Rate": 3.854814425267373e-05, "Pretrain/Loss": 2.085879325866699, "Pretrain/Loss (Raw)": 2.119309425354004, "Pretrain/Step": 3225, "Pretrain/Step Time": 8.835118353366852} +{"Pretrain/Learning Rate": 3.8541008358454956e-05, "Pretrain/Loss": 2.0850448608398438, "Pretrain/Loss (Raw)": 2.0512919425964355, "Pretrain/Step": 3226, "Pretrain/Step Time": 8.836969112977386} +{"Pretrain/Learning Rate": 3.853387090262329e-05, "Pretrain/Loss": 2.0839650630950928, "Pretrain/Loss (Raw)": 1.9081462621688843, "Pretrain/Step": 3227, "Pretrain/Step Time": 8.831451784819365} +{"Pretrain/Learning Rate": 3.852673188600187e-05, "Pretrain/Loss": 2.084152936935425, "Pretrain/Loss (Raw)": 2.076608419418335, "Pretrain/Step": 3228, "Pretrain/Step Time": 8.838044326752424} +{"Pretrain/Learning Rate": 3.851959130941398e-05, "Pretrain/Loss": 2.0827035903930664, "Pretrain/Loss (Raw)": 1.846587896347046, "Pretrain/Step": 3229, "Pretrain/Step Time": 8.834146345034242} +{"Pretrain/Learning Rate": 3.851244917368311e-05, "Pretrain/Loss": 2.082012176513672, "Pretrain/Loss (Raw)": 2.1223535537719727, "Pretrain/Step": 3230, "Pretrain/Step Time": 8.835118221119046} +{"Pretrain/Learning Rate": 3.8505305479632934e-05, "Pretrain/Loss": 2.084146499633789, "Pretrain/Loss (Raw)": 2.1898281574249268, "Pretrain/Step": 3231, "Pretrain/Step Time": 8.831171948462725} +{"Pretrain/Learning Rate": 3.8498160228087284e-05, "Pretrain/Loss": 2.08150053024292, "Pretrain/Loss (Raw)": 1.8605743646621704, "Pretrain/Step": 3232, "Pretrain/Step Time": 8.831347398459911} +{"Pretrain/Learning Rate": 3.8491013419870204e-05, "Pretrain/Loss": 2.080043315887451, "Pretrain/Loss (Raw)": 1.9698843955993652, "Pretrain/Step": 3233, "Pretrain/Step Time": 8.833806963637471} +{"Pretrain/Learning Rate": 3.848386505580588e-05, "Pretrain/Loss": 2.078308343887329, "Pretrain/Loss (Raw)": 1.8765960931777954, "Pretrain/Step": 3234, "Pretrain/Step Time": 8.830540111288428} +{"Pretrain/Learning Rate": 3.84767151367187e-05, "Pretrain/Loss": 2.0772910118103027, "Pretrain/Loss (Raw)": 2.0092570781707764, "Pretrain/Step": 3235, "Pretrain/Step Time": 8.826547967270017} +{"Pretrain/Learning Rate": 3.846956366343322e-05, "Pretrain/Loss": 2.076687812805176, "Pretrain/Loss (Raw)": 2.098254680633545, "Pretrain/Step": 3236, "Pretrain/Step Time": 8.82462745718658} +{"Pretrain/Learning Rate": 3.8462410636774196e-05, "Pretrain/Loss": 2.0781455039978027, "Pretrain/Loss (Raw)": 2.3014485836029053, "Pretrain/Step": 3237, "Pretrain/Step Time": 8.825625015422702} +{"Pretrain/Learning Rate": 3.845525605756653e-05, "Pretrain/Loss": 2.079162836074829, "Pretrain/Loss (Raw)": 2.1529250144958496, "Pretrain/Step": 3238, "Pretrain/Step Time": 8.825908411294222} +{"Pretrain/Learning Rate": 3.844809992663534e-05, "Pretrain/Loss": 2.077869415283203, "Pretrain/Loss (Raw)": 2.0843725204467773, "Pretrain/Step": 3239, "Pretrain/Step Time": 8.826328849419951} +{"Pretrain/Learning Rate": 3.844094224480589e-05, "Pretrain/Loss": 2.0799314975738525, "Pretrain/Loss (Raw)": 2.2670860290527344, "Pretrain/Step": 3240, "Pretrain/Step Time": 8.824259014800191} +{"Pretrain/Learning Rate": 3.843378301290366e-05, "Pretrain/Loss": 2.0815181732177734, "Pretrain/Loss (Raw)": 2.183008909225464, "Pretrain/Step": 3241, "Pretrain/Step Time": 8.821312479674816} +{"Pretrain/Learning Rate": 3.8426622231754255e-05, "Pretrain/Loss": 2.080746650695801, "Pretrain/Loss (Raw)": 2.139806032180786, "Pretrain/Step": 3242, "Pretrain/Step Time": 8.825343180447817} +{"Pretrain/Learning Rate": 3.8419459902183515e-05, "Pretrain/Loss": 2.0812764167785645, "Pretrain/Loss (Raw)": 2.226550817489624, "Pretrain/Step": 3243, "Pretrain/Step Time": 8.818136977031827} +{"Pretrain/Learning Rate": 3.841229602501742e-05, "Pretrain/Loss": 2.079537868499756, "Pretrain/Loss (Raw)": 2.0081753730773926, "Pretrain/Step": 3244, "Pretrain/Step Time": 8.823072452098131} +{"Pretrain/Learning Rate": 3.840513060108214e-05, "Pretrain/Loss": 2.078770160675049, "Pretrain/Loss (Raw)": 2.0567455291748047, "Pretrain/Step": 3245, "Pretrain/Step Time": 8.820648849010468} +{"Pretrain/Learning Rate": 3.8397963631204046e-05, "Pretrain/Loss": 2.0776233673095703, "Pretrain/Loss (Raw)": 2.0460479259490967, "Pretrain/Step": 3246, "Pretrain/Step Time": 8.815007345750928} +{"Pretrain/Learning Rate": 3.8390795116209645e-05, "Pretrain/Loss": 2.0759010314941406, "Pretrain/Loss (Raw)": 1.992584466934204, "Pretrain/Step": 3247, "Pretrain/Step Time": 8.81795242242515} +{"Pretrain/Learning Rate": 3.8383625056925654e-05, "Pretrain/Loss": 2.073910713195801, "Pretrain/Loss (Raw)": 1.8573745489120483, "Pretrain/Step": 3248, "Pretrain/Step Time": 8.818186163902283} +{"Pretrain/Learning Rate": 3.837645345417895e-05, "Pretrain/Loss": 2.072781562805176, "Pretrain/Loss (Raw)": 1.9671534299850464, "Pretrain/Step": 3249, "Pretrain/Step Time": 8.818063467741013} +{"Pretrain/Learning Rate": 3.836928030879661e-05, "Pretrain/Loss": 2.0717859268188477, "Pretrain/Loss (Raw)": 1.9424645900726318, "Pretrain/Step": 3250, "Pretrain/Step Time": 8.81804333999753} +{"Pretrain/Learning Rate": 3.8362105621605866e-05, "Pretrain/Loss": 2.0709056854248047, "Pretrain/Loss (Raw)": 1.9453283548355103, "Pretrain/Step": 3251, "Pretrain/Step Time": 8.819618226960301} +{"Pretrain/Learning Rate": 3.835492939343413e-05, "Pretrain/Loss": 2.072030544281006, "Pretrain/Loss (Raw)": 2.312885284423828, "Pretrain/Step": 3252, "Pretrain/Step Time": 8.819462105631828} +{"Pretrain/Learning Rate": 3.834775162510901e-05, "Pretrain/Loss": 2.0733838081359863, "Pretrain/Loss (Raw)": 2.1383984088897705, "Pretrain/Step": 3253, "Pretrain/Step Time": 8.810528084635735} +{"Pretrain/Learning Rate": 3.834057231745828e-05, "Pretrain/Loss": 2.075103521347046, "Pretrain/Loss (Raw)": 2.093116521835327, "Pretrain/Step": 3254, "Pretrain/Step Time": 8.821628265082836} +{"Pretrain/Learning Rate": 3.8333391471309884e-05, "Pretrain/Loss": 2.0761497020721436, "Pretrain/Loss (Raw)": 2.0853774547576904, "Pretrain/Step": 3255, "Pretrain/Step Time": 8.820202585309744} +{"Pretrain/Learning Rate": 3.8326209087491955e-05, "Pretrain/Loss": 2.0742740631103516, "Pretrain/Loss (Raw)": 1.9892603158950806, "Pretrain/Step": 3256, "Pretrain/Step Time": 8.82564259879291} +{"Pretrain/Learning Rate": 3.8319025166832794e-05, "Pretrain/Loss": 2.0754480361938477, "Pretrain/Loss (Raw)": 2.2060580253601074, "Pretrain/Step": 3257, "Pretrain/Step Time": 8.826337065547705} +{"Pretrain/Learning Rate": 3.83118397101609e-05, "Pretrain/Loss": 2.075671672821045, "Pretrain/Loss (Raw)": 2.104255199432373, "Pretrain/Step": 3258, "Pretrain/Step Time": 8.820539135485888} +{"Pretrain/Learning Rate": 3.830465271830491e-05, "Pretrain/Loss": 2.0757217407226562, "Pretrain/Loss (Raw)": 2.1673128604888916, "Pretrain/Step": 3259, "Pretrain/Step Time": 8.823774799704552} +{"Pretrain/Learning Rate": 3.829746419209369e-05, "Pretrain/Loss": 2.075778007507324, "Pretrain/Loss (Raw)": 2.2439441680908203, "Pretrain/Step": 3260, "Pretrain/Step Time": 8.82692202553153} +{"Pretrain/Learning Rate": 3.829027413235623e-05, "Pretrain/Loss": 2.0754244327545166, "Pretrain/Loss (Raw)": 2.027592897415161, "Pretrain/Step": 3261, "Pretrain/Step Time": 8.814524695277214} +{"Pretrain/Learning Rate": 3.8283082539921735e-05, "Pretrain/Loss": 2.074942111968994, "Pretrain/Loss (Raw)": 2.045637607574463, "Pretrain/Step": 3262, "Pretrain/Step Time": 8.83101492933929} +{"Pretrain/Learning Rate": 3.827588941561956e-05, "Pretrain/Loss": 2.073967933654785, "Pretrain/Loss (Raw)": 2.0888149738311768, "Pretrain/Step": 3263, "Pretrain/Step Time": 8.820907587185502} +{"Pretrain/Learning Rate": 3.826869476027927e-05, "Pretrain/Loss": 2.075528621673584, "Pretrain/Loss (Raw)": 2.1098532676696777, "Pretrain/Step": 3264, "Pretrain/Step Time": 8.821614973247051} +{"Pretrain/Learning Rate": 3.826149857473057e-05, "Pretrain/Loss": 2.0774729251861572, "Pretrain/Loss (Raw)": 2.2654223442077637, "Pretrain/Step": 3265, "Pretrain/Step Time": 8.83071487210691} +{"Pretrain/Learning Rate": 3.825430085980337e-05, "Pretrain/Loss": 2.0779666900634766, "Pretrain/Loss (Raw)": 2.1870265007019043, "Pretrain/Step": 3266, "Pretrain/Step Time": 8.832556866109371} +{"Pretrain/Learning Rate": 3.8247101616327726e-05, "Pretrain/Loss": 2.078256368637085, "Pretrain/Loss (Raw)": 2.1956710815429688, "Pretrain/Step": 3267, "Pretrain/Step Time": 8.827165381982923} +{"Pretrain/Learning Rate": 3.823990084513391e-05, "Pretrain/Loss": 2.0819003582000732, "Pretrain/Loss (Raw)": 2.3061165809631348, "Pretrain/Step": 3268, "Pretrain/Step Time": 8.825591649860144} +{"Pretrain/Learning Rate": 3.8232698547052345e-05, "Pretrain/Loss": 2.0818867683410645, "Pretrain/Loss (Raw)": 2.168654680252075, "Pretrain/Step": 3269, "Pretrain/Step Time": 8.811751246452332} +{"Pretrain/Learning Rate": 3.8225494722913624e-05, "Pretrain/Loss": 2.0829010009765625, "Pretrain/Loss (Raw)": 2.173758029937744, "Pretrain/Step": 3270, "Pretrain/Step Time": 8.819107027724385} +{"Pretrain/Learning Rate": 3.821828937354853e-05, "Pretrain/Loss": 2.0816712379455566, "Pretrain/Loss (Raw)": 2.023169994354248, "Pretrain/Step": 3271, "Pretrain/Step Time": 8.810619801282883} +{"Pretrain/Learning Rate": 3.821108249978802e-05, "Pretrain/Loss": 2.080962657928467, "Pretrain/Loss (Raw)": 1.9331488609313965, "Pretrain/Step": 3272, "Pretrain/Step Time": 8.808475892990828} +{"Pretrain/Learning Rate": 3.8203874102463235e-05, "Pretrain/Loss": 2.0861802101135254, "Pretrain/Loss (Raw)": 2.554961919784546, "Pretrain/Step": 3273, "Pretrain/Step Time": 8.807972211390734} +{"Pretrain/Learning Rate": 3.819666418240545e-05, "Pretrain/Loss": 2.085909366607666, "Pretrain/Loss (Raw)": 2.110692262649536, "Pretrain/Step": 3274, "Pretrain/Step Time": 8.807243790477514} +{"Pretrain/Learning Rate": 3.818945274044618e-05, "Pretrain/Loss": 2.086740016937256, "Pretrain/Loss (Raw)": 2.1881024837493896, "Pretrain/Step": 3275, "Pretrain/Step Time": 8.804247345775366} +{"Pretrain/Learning Rate": 3.8182239777417066e-05, "Pretrain/Loss": 2.087340831756592, "Pretrain/Loss (Raw)": 2.227130889892578, "Pretrain/Step": 3276, "Pretrain/Step Time": 8.811541767790914} +{"Pretrain/Learning Rate": 3.817502529414994e-05, "Pretrain/Loss": 2.085542678833008, "Pretrain/Loss (Raw)": 1.9506328105926514, "Pretrain/Step": 3277, "Pretrain/Step Time": 8.799447355791926} +{"Pretrain/Learning Rate": 3.816780929147682e-05, "Pretrain/Loss": 2.0852155685424805, "Pretrain/Loss (Raw)": 2.1673948764801025, "Pretrain/Step": 3278, "Pretrain/Step Time": 8.799976896494627} +{"Pretrain/Learning Rate": 3.816059177022988e-05, "Pretrain/Loss": 2.0857653617858887, "Pretrain/Loss (Raw)": 2.1391994953155518, "Pretrain/Step": 3279, "Pretrain/Step Time": 8.796878721565008} +{"Pretrain/Learning Rate": 3.8153372731241486e-05, "Pretrain/Loss": 2.08534836769104, "Pretrain/Loss (Raw)": 1.9484142065048218, "Pretrain/Step": 3280, "Pretrain/Step Time": 8.801636492833495} +{"Pretrain/Learning Rate": 3.814615217534416e-05, "Pretrain/Loss": 2.0886831283569336, "Pretrain/Loss (Raw)": 2.2335503101348877, "Pretrain/Step": 3281, "Pretrain/Step Time": 8.799012448638678} +{"Pretrain/Learning Rate": 3.813893010337063e-05, "Pretrain/Loss": 2.0885043144226074, "Pretrain/Loss (Raw)": 2.097055673599243, "Pretrain/Step": 3282, "Pretrain/Step Time": 8.797744492068887} +{"Pretrain/Learning Rate": 3.813170651615376e-05, "Pretrain/Loss": 2.088162660598755, "Pretrain/Loss (Raw)": 2.1472907066345215, "Pretrain/Step": 3283, "Pretrain/Step Time": 8.801629850640893} +{"Pretrain/Learning Rate": 3.8124481414526613e-05, "Pretrain/Loss": 2.089535713195801, "Pretrain/Loss (Raw)": 2.1029412746429443, "Pretrain/Step": 3284, "Pretrain/Step Time": 8.788756055757403} +{"Pretrain/Learning Rate": 3.811725479932243e-05, "Pretrain/Loss": 2.088582992553711, "Pretrain/Loss (Raw)": 2.042912721633911, "Pretrain/Step": 3285, "Pretrain/Step Time": 8.789270082488656} +{"Pretrain/Learning Rate": 3.8110026671374615e-05, "Pretrain/Loss": 2.0869879722595215, "Pretrain/Loss (Raw)": 1.9383201599121094, "Pretrain/Step": 3286, "Pretrain/Step Time": 8.785603679716587} +{"Pretrain/Learning Rate": 3.810279703151674e-05, "Pretrain/Loss": 2.0844836235046387, "Pretrain/Loss (Raw)": 1.8858023881912231, "Pretrain/Step": 3287, "Pretrain/Step Time": 8.787260133773088} +{"Pretrain/Learning Rate": 3.809556588058258e-05, "Pretrain/Loss": 2.0855982303619385, "Pretrain/Loss (Raw)": 2.1803958415985107, "Pretrain/Step": 3288, "Pretrain/Step Time": 8.784760596230626} +{"Pretrain/Learning Rate": 3.8088333219406046e-05, "Pretrain/Loss": 2.085216999053955, "Pretrain/Loss (Raw)": 1.8989908695220947, "Pretrain/Step": 3289, "Pretrain/Step Time": 8.786541137844324} +{"Pretrain/Learning Rate": 3.808109904882126e-05, "Pretrain/Loss": 2.08689546585083, "Pretrain/Loss (Raw)": 2.154930830001831, "Pretrain/Step": 3290, "Pretrain/Step Time": 8.796656183898449} +{"Pretrain/Learning Rate": 3.807386336966248e-05, "Pretrain/Loss": 2.086087226867676, "Pretrain/Loss (Raw)": 1.956460952758789, "Pretrain/Step": 3291, "Pretrain/Step Time": 8.78927124850452} +{"Pretrain/Learning Rate": 3.8066626182764174e-05, "Pretrain/Loss": 2.0856361389160156, "Pretrain/Loss (Raw)": 1.9310110807418823, "Pretrain/Step": 3292, "Pretrain/Step Time": 8.79090222530067} +{"Pretrain/Learning Rate": 3.805938748896097e-05, "Pretrain/Loss": 2.0826282501220703, "Pretrain/Loss (Raw)": 1.791873812675476, "Pretrain/Step": 3293, "Pretrain/Step Time": 8.796156831085682} +{"Pretrain/Learning Rate": 3.805214728908765e-05, "Pretrain/Loss": 2.084336280822754, "Pretrain/Loss (Raw)": 2.089855670928955, "Pretrain/Step": 3294, "Pretrain/Step Time": 8.790614059194922} +{"Pretrain/Learning Rate": 3.804490558397922e-05, "Pretrain/Loss": 2.0839829444885254, "Pretrain/Loss (Raw)": 1.9764882326126099, "Pretrain/Step": 3295, "Pretrain/Step Time": 8.79049309156835} +{"Pretrain/Learning Rate": 3.803766237447079e-05, "Pretrain/Loss": 2.084625244140625, "Pretrain/Loss (Raw)": 2.0663561820983887, "Pretrain/Step": 3296, "Pretrain/Step Time": 8.780292430892587} +{"Pretrain/Learning Rate": 3.803041766139771e-05, "Pretrain/Loss": 2.0865302085876465, "Pretrain/Loss (Raw)": 2.3190054893493652, "Pretrain/Step": 3297, "Pretrain/Step Time": 8.787756346166134} +{"Pretrain/Learning Rate": 3.8023171445595464e-05, "Pretrain/Loss": 2.0879530906677246, "Pretrain/Loss (Raw)": 2.184316873550415, "Pretrain/Step": 3298, "Pretrain/Step Time": 8.785231951624155} +{"Pretrain/Learning Rate": 3.8015923727899714e-05, "Pretrain/Loss": 2.089160919189453, "Pretrain/Loss (Raw)": 2.1937782764434814, "Pretrain/Step": 3299, "Pretrain/Step Time": 8.78974675014615} +{"Pretrain/Learning Rate": 3.8008674509146304e-05, "Pretrain/Loss": 2.0873255729675293, "Pretrain/Loss (Raw)": 1.9075592756271362, "Pretrain/Step": 3300, "Pretrain/Step Time": 8.789568243548274} +{"Pretrain/Learning Rate": 3.800142379017127e-05, "Pretrain/Loss": 2.0882906913757324, "Pretrain/Loss (Raw)": 2.0709002017974854, "Pretrain/Step": 3301, "Pretrain/Step Time": 8.788392217829823} +{"Pretrain/Learning Rate": 3.799417157181076e-05, "Pretrain/Loss": 2.0862603187561035, "Pretrain/Loss (Raw)": 1.9447147846221924, "Pretrain/Step": 3302, "Pretrain/Step Time": 8.780543766915798} +{"Pretrain/Learning Rate": 3.798691785490115e-05, "Pretrain/Loss": 2.085836410522461, "Pretrain/Loss (Raw)": 2.120194673538208, "Pretrain/Step": 3303, "Pretrain/Step Time": 8.77813434228301} +{"Pretrain/Learning Rate": 3.797966264027899e-05, "Pretrain/Loss": 2.084078311920166, "Pretrain/Loss (Raw)": 1.970149040222168, "Pretrain/Step": 3304, "Pretrain/Step Time": 8.787101591005921} +{"Pretrain/Learning Rate": 3.7972405928780974e-05, "Pretrain/Loss": 2.08516526222229, "Pretrain/Loss (Raw)": 2.2229349613189697, "Pretrain/Step": 3305, "Pretrain/Step Time": 8.787472993135452} +{"Pretrain/Learning Rate": 3.796514772124396e-05, "Pretrain/Loss": 2.085716485977173, "Pretrain/Loss (Raw)": 2.193471670150757, "Pretrain/Step": 3306, "Pretrain/Step Time": 8.789039019495249} +{"Pretrain/Learning Rate": 3.795788801850504e-05, "Pretrain/Loss": 2.0857112407684326, "Pretrain/Loss (Raw)": 2.0439538955688477, "Pretrain/Step": 3307, "Pretrain/Step Time": 8.783770315349102} +{"Pretrain/Learning Rate": 3.7950626821401405e-05, "Pretrain/Loss": 2.0872082710266113, "Pretrain/Loss (Raw)": 2.2526516914367676, "Pretrain/Step": 3308, "Pretrain/Step Time": 8.787243170663714} +{"Pretrain/Learning Rate": 3.794336413077045e-05, "Pretrain/Loss": 2.086832284927368, "Pretrain/Loss (Raw)": 2.1137871742248535, "Pretrain/Step": 3309, "Pretrain/Step Time": 8.783692656084895} +{"Pretrain/Learning Rate": 3.793609994744977e-05, "Pretrain/Loss": 2.084012508392334, "Pretrain/Loss (Raw)": 1.8472356796264648, "Pretrain/Step": 3310, "Pretrain/Step Time": 8.783493030816317} +{"Pretrain/Learning Rate": 3.792883427227707e-05, "Pretrain/Loss": 2.0843873023986816, "Pretrain/Loss (Raw)": 2.2380855083465576, "Pretrain/Step": 3311, "Pretrain/Step Time": 8.788859885185957} +{"Pretrain/Learning Rate": 3.7921567106090297e-05, "Pretrain/Loss": 2.0842251777648926, "Pretrain/Loss (Raw)": 2.0901272296905518, "Pretrain/Step": 3312, "Pretrain/Step Time": 8.788426246494055} +{"Pretrain/Learning Rate": 3.79142984497275e-05, "Pretrain/Loss": 2.0844287872314453, "Pretrain/Loss (Raw)": 2.008881092071533, "Pretrain/Step": 3313, "Pretrain/Step Time": 8.792304541915655} +{"Pretrain/Learning Rate": 3.790702830402696e-05, "Pretrain/Loss": 2.0860207080841064, "Pretrain/Loss (Raw)": 2.1550471782684326, "Pretrain/Step": 3314, "Pretrain/Step Time": 8.793358512222767} +{"Pretrain/Learning Rate": 3.7899756669827094e-05, "Pretrain/Loss": 2.0865259170532227, "Pretrain/Loss (Raw)": 2.1408441066741943, "Pretrain/Step": 3315, "Pretrain/Step Time": 8.789532667025924} +{"Pretrain/Learning Rate": 3.789248354796651e-05, "Pretrain/Loss": 2.0862720012664795, "Pretrain/Loss (Raw)": 2.050086498260498, "Pretrain/Step": 3316, "Pretrain/Step Time": 8.784868493676186} +{"Pretrain/Learning Rate": 3.788520893928396e-05, "Pretrain/Loss": 2.085738182067871, "Pretrain/Loss (Raw)": 1.944656491279602, "Pretrain/Step": 3317, "Pretrain/Step Time": 8.7726767975837} +{"Pretrain/Learning Rate": 3.78779328446184e-05, "Pretrain/Loss": 2.0860483646392822, "Pretrain/Loss (Raw)": 2.0246336460113525, "Pretrain/Step": 3318, "Pretrain/Step Time": 8.785315373912454} +{"Pretrain/Learning Rate": 3.7870655264808954e-05, "Pretrain/Loss": 2.0868232250213623, "Pretrain/Loss (Raw)": 2.1696577072143555, "Pretrain/Step": 3319, "Pretrain/Step Time": 8.782606052234769} +{"Pretrain/Learning Rate": 3.786337620069488e-05, "Pretrain/Loss": 2.08835506439209, "Pretrain/Loss (Raw)": 2.3088767528533936, "Pretrain/Step": 3320, "Pretrain/Step Time": 8.7826043702662} +{"Pretrain/Learning Rate": 3.7856095653115655e-05, "Pretrain/Loss": 2.0896735191345215, "Pretrain/Loss (Raw)": 2.2434728145599365, "Pretrain/Step": 3321, "Pretrain/Step Time": 8.786993436515331} +{"Pretrain/Learning Rate": 3.7848813622910894e-05, "Pretrain/Loss": 2.088970184326172, "Pretrain/Loss (Raw)": 1.9432268142700195, "Pretrain/Step": 3322, "Pretrain/Step Time": 8.778324410319328} +{"Pretrain/Learning Rate": 3.784153011092041e-05, "Pretrain/Loss": 2.0907247066497803, "Pretrain/Loss (Raw)": 2.2785251140594482, "Pretrain/Step": 3323, "Pretrain/Step Time": 8.783441061154008} +{"Pretrain/Learning Rate": 3.7834245117984155e-05, "Pretrain/Loss": 2.0914206504821777, "Pretrain/Loss (Raw)": 2.1837143898010254, "Pretrain/Step": 3324, "Pretrain/Step Time": 8.776957109570503} +{"Pretrain/Learning Rate": 3.782695864494228e-05, "Pretrain/Loss": 2.0905990600585938, "Pretrain/Loss (Raw)": 1.9894835948944092, "Pretrain/Step": 3325, "Pretrain/Step Time": 8.782969627529383} +{"Pretrain/Learning Rate": 3.781967069263509e-05, "Pretrain/Loss": 2.0917611122131348, "Pretrain/Loss (Raw)": 2.0604562759399414, "Pretrain/Step": 3326, "Pretrain/Step Time": 8.782295601442456} +{"Pretrain/Learning Rate": 3.781238126190306e-05, "Pretrain/Loss": 2.090620994567871, "Pretrain/Loss (Raw)": 2.058732271194458, "Pretrain/Step": 3327, "Pretrain/Step Time": 8.781674470752478} +{"Pretrain/Learning Rate": 3.780509035358686e-05, "Pretrain/Loss": 2.0902485847473145, "Pretrain/Loss (Raw)": 1.9562783241271973, "Pretrain/Step": 3328, "Pretrain/Step Time": 8.77781175263226} +{"Pretrain/Learning Rate": 3.77977979685273e-05, "Pretrain/Loss": 2.091034173965454, "Pretrain/Loss (Raw)": 2.2017405033111572, "Pretrain/Step": 3329, "Pretrain/Step Time": 8.780847931280732} +{"Pretrain/Learning Rate": 3.7790504107565366e-05, "Pretrain/Loss": 2.091400623321533, "Pretrain/Loss (Raw)": 2.0368118286132812, "Pretrain/Step": 3330, "Pretrain/Step Time": 8.782939694821835} +{"Pretrain/Learning Rate": 3.7783208771542237e-05, "Pretrain/Loss": 2.091409683227539, "Pretrain/Loss (Raw)": 2.111217737197876, "Pretrain/Step": 3331, "Pretrain/Step Time": 8.775117054581642} +{"Pretrain/Learning Rate": 3.7775911961299225e-05, "Pretrain/Loss": 2.0928072929382324, "Pretrain/Loss (Raw)": 2.216089963912964, "Pretrain/Step": 3332, "Pretrain/Step Time": 8.774216644465923} +{"Pretrain/Learning Rate": 3.776861367767785e-05, "Pretrain/Loss": 2.09205961227417, "Pretrain/Loss (Raw)": 2.1080589294433594, "Pretrain/Step": 3333, "Pretrain/Step Time": 8.773457223549485} +{"Pretrain/Learning Rate": 3.776131392151978e-05, "Pretrain/Loss": 2.090325117111206, "Pretrain/Loss (Raw)": 1.7797738313674927, "Pretrain/Step": 3334, "Pretrain/Step Time": 8.777315342798829} +{"Pretrain/Learning Rate": 3.775401269366685e-05, "Pretrain/Loss": 2.0900516510009766, "Pretrain/Loss (Raw)": 1.941271424293518, "Pretrain/Step": 3335, "Pretrain/Step Time": 8.779140286147594} +{"Pretrain/Learning Rate": 3.7746709994961085e-05, "Pretrain/Loss": 2.0902762413024902, "Pretrain/Loss (Raw)": 2.116145372390747, "Pretrain/Step": 3336, "Pretrain/Step Time": 8.773147931322455} +{"Pretrain/Learning Rate": 3.7739405826244645e-05, "Pretrain/Loss": 2.0917444229125977, "Pretrain/Loss (Raw)": 2.1201820373535156, "Pretrain/Step": 3337, "Pretrain/Step Time": 8.770242273807526} +{"Pretrain/Learning Rate": 3.773210018835991e-05, "Pretrain/Loss": 2.092442512512207, "Pretrain/Loss (Raw)": 2.0156705379486084, "Pretrain/Step": 3338, "Pretrain/Step Time": 8.778219506144524} +{"Pretrain/Learning Rate": 3.772479308214937e-05, "Pretrain/Loss": 2.0901358127593994, "Pretrain/Loss (Raw)": 1.8367815017700195, "Pretrain/Step": 3339, "Pretrain/Step Time": 8.783935077488422} +{"Pretrain/Learning Rate": 3.771748450845575e-05, "Pretrain/Loss": 2.090406894683838, "Pretrain/Loss (Raw)": 2.0279388427734375, "Pretrain/Step": 3340, "Pretrain/Step Time": 8.7811198849231} +{"Pretrain/Learning Rate": 3.771017446812187e-05, "Pretrain/Loss": 2.0894298553466797, "Pretrain/Loss (Raw)": 1.9976181983947754, "Pretrain/Step": 3341, "Pretrain/Step Time": 8.785106683149934} +{"Pretrain/Learning Rate": 3.770286296199079e-05, "Pretrain/Loss": 2.088564395904541, "Pretrain/Loss (Raw)": 2.2096283435821533, "Pretrain/Step": 3342, "Pretrain/Step Time": 8.786474423483014} +{"Pretrain/Learning Rate": 3.7695549990905694e-05, "Pretrain/Loss": 2.0887081623077393, "Pretrain/Loss (Raw)": 2.0282504558563232, "Pretrain/Step": 3343, "Pretrain/Step Time": 8.78573464602232} +{"Pretrain/Learning Rate": 3.768823555570995e-05, "Pretrain/Loss": 2.0874242782592773, "Pretrain/Loss (Raw)": 1.9688199758529663, "Pretrain/Step": 3344, "Pretrain/Step Time": 8.793936148285866} +{"Pretrain/Learning Rate": 3.768091965724709e-05, "Pretrain/Loss": 2.084289073944092, "Pretrain/Loss (Raw)": 1.798284888267517, "Pretrain/Step": 3345, "Pretrain/Step Time": 8.784493217244744} +{"Pretrain/Learning Rate": 3.767360229636082e-05, "Pretrain/Loss": 2.082360029220581, "Pretrain/Loss (Raw)": 1.9561614990234375, "Pretrain/Step": 3346, "Pretrain/Step Time": 8.795704273506999} +{"Pretrain/Learning Rate": 3.7666283473895014e-05, "Pretrain/Loss": 2.082982063293457, "Pretrain/Loss (Raw)": 2.1259217262268066, "Pretrain/Step": 3347, "Pretrain/Step Time": 8.795184249058366} +{"Pretrain/Learning Rate": 3.765896319069372e-05, "Pretrain/Loss": 2.081549644470215, "Pretrain/Loss (Raw)": 1.9934804439544678, "Pretrain/Step": 3348, "Pretrain/Step Time": 8.794302502647042} +{"Pretrain/Learning Rate": 3.7651641447601126e-05, "Pretrain/Loss": 2.0799970626831055, "Pretrain/Loss (Raw)": 1.9461575746536255, "Pretrain/Step": 3349, "Pretrain/Step Time": 8.794626530259848} +{"Pretrain/Learning Rate": 3.764431824546163e-05, "Pretrain/Loss": 2.0802063941955566, "Pretrain/Loss (Raw)": 2.266103982925415, "Pretrain/Step": 3350, "Pretrain/Step Time": 8.792939087375998} +{"Pretrain/Learning Rate": 3.7636993585119775e-05, "Pretrain/Loss": 2.0799925327301025, "Pretrain/Loss (Raw)": 2.040879726409912, "Pretrain/Step": 3351, "Pretrain/Step Time": 8.792363854125142} +{"Pretrain/Learning Rate": 3.762966746742027e-05, "Pretrain/Loss": 2.0802369117736816, "Pretrain/Loss (Raw)": 2.2518832683563232, "Pretrain/Step": 3352, "Pretrain/Step Time": 8.794351756572723} +{"Pretrain/Learning Rate": 3.7622339893208e-05, "Pretrain/Loss": 2.0797462463378906, "Pretrain/Loss (Raw)": 2.056511878967285, "Pretrain/Step": 3353, "Pretrain/Step Time": 8.800712993368506} +{"Pretrain/Learning Rate": 3.761501086332802e-05, "Pretrain/Loss": 2.081512212753296, "Pretrain/Loss (Raw)": 2.277308940887451, "Pretrain/Step": 3354, "Pretrain/Step Time": 8.798267552629113} +{"Pretrain/Learning Rate": 3.760768037862553e-05, "Pretrain/Loss": 2.083369731903076, "Pretrain/Loss (Raw)": 2.145949602127075, "Pretrain/Step": 3355, "Pretrain/Step Time": 8.806070104241371} +{"Pretrain/Learning Rate": 3.760034843994594e-05, "Pretrain/Loss": 2.083733081817627, "Pretrain/Loss (Raw)": 2.1231000423431396, "Pretrain/Step": 3356, "Pretrain/Step Time": 8.79873107559979} +{"Pretrain/Learning Rate": 3.7593015048134794e-05, "Pretrain/Loss": 2.085926055908203, "Pretrain/Loss (Raw)": 2.1273140907287598, "Pretrain/Step": 3357, "Pretrain/Step Time": 8.797412736341357} +{"Pretrain/Learning Rate": 3.758568020403781e-05, "Pretrain/Loss": 2.085491180419922, "Pretrain/Loss (Raw)": 2.066641330718994, "Pretrain/Step": 3358, "Pretrain/Step Time": 8.798034755513072} +{"Pretrain/Learning Rate": 3.757834390850088e-05, "Pretrain/Loss": 2.083906650543213, "Pretrain/Loss (Raw)": 1.9870282411575317, "Pretrain/Step": 3359, "Pretrain/Step Time": 8.800392750650644} +{"Pretrain/Learning Rate": 3.7571006162370056e-05, "Pretrain/Loss": 2.08571195602417, "Pretrain/Loss (Raw)": 2.0916390419006348, "Pretrain/Step": 3360, "Pretrain/Step Time": 8.807218616828322} +{"Pretrain/Learning Rate": 3.7563666966491564e-05, "Pretrain/Loss": 2.0871646404266357, "Pretrain/Loss (Raw)": 2.1558573246002197, "Pretrain/Step": 3361, "Pretrain/Step Time": 8.800740744918585} +{"Pretrain/Learning Rate": 3.7556326321711796e-05, "Pretrain/Loss": 2.0887672901153564, "Pretrain/Loss (Raw)": 2.081713914871216, "Pretrain/Step": 3362, "Pretrain/Step Time": 8.80228115618229} +{"Pretrain/Learning Rate": 3.7548984228877313e-05, "Pretrain/Loss": 2.0897889137268066, "Pretrain/Loss (Raw)": 2.14005970954895, "Pretrain/Step": 3363, "Pretrain/Step Time": 8.803764756768942} +{"Pretrain/Learning Rate": 3.754164068883484e-05, "Pretrain/Loss": 2.089641571044922, "Pretrain/Loss (Raw)": 2.079361915588379, "Pretrain/Step": 3364, "Pretrain/Step Time": 8.801921002566814} +{"Pretrain/Learning Rate": 3.7534295702431254e-05, "Pretrain/Loss": 2.0870633125305176, "Pretrain/Loss (Raw)": 1.971436619758606, "Pretrain/Step": 3365, "Pretrain/Step Time": 8.798728873953223} +{"Pretrain/Learning Rate": 3.7526949270513635e-05, "Pretrain/Loss": 2.085214614868164, "Pretrain/Loss (Raw)": 1.9162864685058594, "Pretrain/Step": 3366, "Pretrain/Step Time": 8.803685080260038} +{"Pretrain/Learning Rate": 3.751960139392919e-05, "Pretrain/Loss": 2.085202693939209, "Pretrain/Loss (Raw)": 2.0828781127929688, "Pretrain/Step": 3367, "Pretrain/Step Time": 8.805031169205904} +{"Pretrain/Learning Rate": 3.7512252073525325e-05, "Pretrain/Loss": 2.0831708908081055, "Pretrain/Loss (Raw)": 2.00698184967041, "Pretrain/Step": 3368, "Pretrain/Step Time": 8.793407201766968} +{"Pretrain/Learning Rate": 3.7504901310149574e-05, "Pretrain/Loss": 2.0840868949890137, "Pretrain/Loss (Raw)": 2.3002853393554688, "Pretrain/Step": 3369, "Pretrain/Step Time": 8.800326224416494} +{"Pretrain/Learning Rate": 3.74975491046497e-05, "Pretrain/Loss": 2.0842812061309814, "Pretrain/Loss (Raw)": 2.1646509170532227, "Pretrain/Step": 3370, "Pretrain/Step Time": 8.797890696674585} +{"Pretrain/Learning Rate": 3.7490195457873555e-05, "Pretrain/Loss": 2.0827207565307617, "Pretrain/Loss (Raw)": 2.026839017868042, "Pretrain/Step": 3371, "Pretrain/Step Time": 8.796262808144093} +{"Pretrain/Learning Rate": 3.748284037066922e-05, "Pretrain/Loss": 2.083731174468994, "Pretrain/Loss (Raw)": 2.137515068054199, "Pretrain/Step": 3372, "Pretrain/Step Time": 8.795140236616135} +{"Pretrain/Learning Rate": 3.7475483843884916e-05, "Pretrain/Loss": 2.083162784576416, "Pretrain/Loss (Raw)": 1.9839632511138916, "Pretrain/Step": 3373, "Pretrain/Step Time": 8.795980963855982} +{"Pretrain/Learning Rate": 3.746812587836903e-05, "Pretrain/Loss": 2.0841264724731445, "Pretrain/Loss (Raw)": 2.1694228649139404, "Pretrain/Step": 3374, "Pretrain/Step Time": 8.800660729408264} +{"Pretrain/Learning Rate": 3.746076647497011e-05, "Pretrain/Loss": 2.0845260620117188, "Pretrain/Loss (Raw)": 2.0437026023864746, "Pretrain/Step": 3375, "Pretrain/Step Time": 8.792797271162271} +{"Pretrain/Learning Rate": 3.7453405634536894e-05, "Pretrain/Loss": 2.0863397121429443, "Pretrain/Loss (Raw)": 2.0895330905914307, "Pretrain/Step": 3376, "Pretrain/Step Time": 8.792763208970428} +{"Pretrain/Learning Rate": 3.744604335791825e-05, "Pretrain/Loss": 2.0876243114471436, "Pretrain/Loss (Raw)": 2.1315858364105225, "Pretrain/Step": 3377, "Pretrain/Step Time": 8.794215032830834} +{"Pretrain/Learning Rate": 3.743867964596324e-05, "Pretrain/Loss": 2.089413642883301, "Pretrain/Loss (Raw)": 2.1715030670166016, "Pretrain/Step": 3378, "Pretrain/Step Time": 8.795228874310851} +{"Pretrain/Learning Rate": 3.743131449952107e-05, "Pretrain/Loss": 2.0907795429229736, "Pretrain/Loss (Raw)": 2.120168447494507, "Pretrain/Step": 3379, "Pretrain/Step Time": 8.794131744652987} +{"Pretrain/Learning Rate": 3.7423947919441147e-05, "Pretrain/Loss": 2.089081287384033, "Pretrain/Loss (Raw)": 2.0955090522766113, "Pretrain/Step": 3380, "Pretrain/Step Time": 8.791337365284562} +{"Pretrain/Learning Rate": 3.7416579906573e-05, "Pretrain/Loss": 2.0891082286834717, "Pretrain/Loss (Raw)": 2.1418426036834717, "Pretrain/Step": 3381, "Pretrain/Step Time": 8.794064596295357} +{"Pretrain/Learning Rate": 3.7409210461766355e-05, "Pretrain/Loss": 2.089480400085449, "Pretrain/Loss (Raw)": 2.1407737731933594, "Pretrain/Step": 3382, "Pretrain/Step Time": 8.79322462156415} +{"Pretrain/Learning Rate": 3.740183958587108e-05, "Pretrain/Loss": 2.0888967514038086, "Pretrain/Loss (Raw)": 2.0106329917907715, "Pretrain/Step": 3383, "Pretrain/Step Time": 8.795011956244707} +{"Pretrain/Learning Rate": 3.7394467279737224e-05, "Pretrain/Loss": 2.090252637863159, "Pretrain/Loss (Raw)": 2.1628239154815674, "Pretrain/Step": 3384, "Pretrain/Step Time": 8.794302735477686} +{"Pretrain/Learning Rate": 3.7387093544215003e-05, "Pretrain/Loss": 2.090080499649048, "Pretrain/Loss (Raw)": 2.1840102672576904, "Pretrain/Step": 3385, "Pretrain/Step Time": 8.797838421538472} +{"Pretrain/Learning Rate": 3.7379718380154777e-05, "Pretrain/Loss": 2.089247703552246, "Pretrain/Loss (Raw)": 1.9976884126663208, "Pretrain/Step": 3386, "Pretrain/Step Time": 8.79908418469131} +{"Pretrain/Learning Rate": 3.737234178840709e-05, "Pretrain/Loss": 2.0878069400787354, "Pretrain/Loss (Raw)": 1.982884168624878, "Pretrain/Step": 3387, "Pretrain/Step Time": 8.798661399632692} +{"Pretrain/Learning Rate": 3.736496376982266e-05, "Pretrain/Loss": 2.0861258506774902, "Pretrain/Loss (Raw)": 2.0287559032440186, "Pretrain/Step": 3388, "Pretrain/Step Time": 8.802130281925201} +{"Pretrain/Learning Rate": 3.7357584325252336e-05, "Pretrain/Loss": 2.086357593536377, "Pretrain/Loss (Raw)": 2.057283639907837, "Pretrain/Step": 3389, "Pretrain/Step Time": 8.808937929570675} +{"Pretrain/Learning Rate": 3.7350203455547155e-05, "Pretrain/Loss": 2.0882668495178223, "Pretrain/Loss (Raw)": 2.2899880409240723, "Pretrain/Step": 3390, "Pretrain/Step Time": 8.792425334453583} +{"Pretrain/Learning Rate": 3.7342821161558316e-05, "Pretrain/Loss": 2.08864164352417, "Pretrain/Loss (Raw)": 2.1368141174316406, "Pretrain/Step": 3391, "Pretrain/Step Time": 8.800572173669934} +{"Pretrain/Learning Rate": 3.7335437444137175e-05, "Pretrain/Loss": 2.0857348442077637, "Pretrain/Loss (Raw)": 1.7377541065216064, "Pretrain/Step": 3392, "Pretrain/Step Time": 8.804698716849089} +{"Pretrain/Learning Rate": 3.732805230413527e-05, "Pretrain/Loss": 2.0850305557250977, "Pretrain/Loss (Raw)": 2.175293445587158, "Pretrain/Step": 3393, "Pretrain/Step Time": 8.799100948497653} +{"Pretrain/Learning Rate": 3.732066574240428e-05, "Pretrain/Loss": 2.083505153656006, "Pretrain/Loss (Raw)": 1.9917906522750854, "Pretrain/Step": 3394, "Pretrain/Step Time": 8.79955406486988} +{"Pretrain/Learning Rate": 3.731327775979605e-05, "Pretrain/Loss": 2.0832598209381104, "Pretrain/Loss (Raw)": 2.164254665374756, "Pretrain/Step": 3395, "Pretrain/Step Time": 8.799155360087752} +{"Pretrain/Learning Rate": 3.730588835716262e-05, "Pretrain/Loss": 2.0823259353637695, "Pretrain/Loss (Raw)": 2.186568260192871, "Pretrain/Step": 3396, "Pretrain/Step Time": 8.803228445351124} +{"Pretrain/Learning Rate": 3.729849753535615e-05, "Pretrain/Loss": 2.0801334381103516, "Pretrain/Loss (Raw)": 1.8880075216293335, "Pretrain/Step": 3397, "Pretrain/Step Time": 8.803309818729758} +{"Pretrain/Learning Rate": 3.7291105295229004e-05, "Pretrain/Loss": 2.0791473388671875, "Pretrain/Loss (Raw)": 2.047544002532959, "Pretrain/Step": 3398, "Pretrain/Step Time": 8.800037601962686} +{"Pretrain/Learning Rate": 3.728371163763366e-05, "Pretrain/Loss": 2.079409122467041, "Pretrain/Loss (Raw)": 2.0566909313201904, "Pretrain/Step": 3399, "Pretrain/Step Time": 8.803112462162971} +{"Pretrain/Learning Rate": 3.727631656342282e-05, "Pretrain/Loss": 2.0812864303588867, "Pretrain/Loss (Raw)": 2.1734557151794434, "Pretrain/Step": 3400, "Pretrain/Step Time": 8.808590970933437} +{"Pretrain/Learning Rate": 3.7268920073449296e-05, "Pretrain/Loss": 2.077810764312744, "Pretrain/Loss (Raw)": 2.110060691833496, "Pretrain/Step": 3401, "Pretrain/Step Time": 8.806864568963647} +{"Pretrain/Learning Rate": 3.72615221685661e-05, "Pretrain/Loss": 2.078145980834961, "Pretrain/Loss (Raw)": 2.153596878051758, "Pretrain/Step": 3402, "Pretrain/Step Time": 8.808608185499907} +{"Pretrain/Learning Rate": 3.725412284962639e-05, "Pretrain/Loss": 2.078115701675415, "Pretrain/Loss (Raw)": 2.1842257976531982, "Pretrain/Step": 3403, "Pretrain/Step Time": 8.810656107962132} +{"Pretrain/Learning Rate": 3.724672211748349e-05, "Pretrain/Loss": 2.0775108337402344, "Pretrain/Loss (Raw)": 2.149705648422241, "Pretrain/Step": 3404, "Pretrain/Step Time": 8.799983294680715} +{"Pretrain/Learning Rate": 3.723931997299089e-05, "Pretrain/Loss": 2.078251600265503, "Pretrain/Loss (Raw)": 2.0454652309417725, "Pretrain/Step": 3405, "Pretrain/Step Time": 8.800630116835237} +{"Pretrain/Learning Rate": 3.723191641700223e-05, "Pretrain/Loss": 2.077385425567627, "Pretrain/Loss (Raw)": 2.0565450191497803, "Pretrain/Step": 3406, "Pretrain/Step Time": 8.801519764587283} +{"Pretrain/Learning Rate": 3.7224511450371334e-05, "Pretrain/Loss": 2.077317237854004, "Pretrain/Loss (Raw)": 2.1304478645324707, "Pretrain/Step": 3407, "Pretrain/Step Time": 8.801996160298586} +{"Pretrain/Learning Rate": 3.721710507395218e-05, "Pretrain/Loss": 2.078596830368042, "Pretrain/Loss (Raw)": 2.1121931076049805, "Pretrain/Step": 3408, "Pretrain/Step Time": 8.791394852101803} +{"Pretrain/Learning Rate": 3.720969728859889e-05, "Pretrain/Loss": 2.07686185836792, "Pretrain/Loss (Raw)": 2.011460542678833, "Pretrain/Step": 3409, "Pretrain/Step Time": 8.795117808505893} +{"Pretrain/Learning Rate": 3.720228809516578e-05, "Pretrain/Loss": 2.077376365661621, "Pretrain/Loss (Raw)": 2.1629512310028076, "Pretrain/Step": 3410, "Pretrain/Step Time": 8.8022186961025} +{"Pretrain/Learning Rate": 3.719487749450731e-05, "Pretrain/Loss": 2.0769400596618652, "Pretrain/Loss (Raw)": 2.091434955596924, "Pretrain/Step": 3411, "Pretrain/Step Time": 8.79788395576179} +{"Pretrain/Learning Rate": 3.718746548747809e-05, "Pretrain/Loss": 2.075467109680176, "Pretrain/Loss (Raw)": 1.9143754243850708, "Pretrain/Step": 3412, "Pretrain/Step Time": 8.800021637231112} +{"Pretrain/Learning Rate": 3.7180052074932934e-05, "Pretrain/Loss": 2.0763626098632812, "Pretrain/Loss (Raw)": 2.15755558013916, "Pretrain/Step": 3413, "Pretrain/Step Time": 8.798012904822826} +{"Pretrain/Learning Rate": 3.7172637257726774e-05, "Pretrain/Loss": 2.0784082412719727, "Pretrain/Loss (Raw)": 2.2001538276672363, "Pretrain/Step": 3414, "Pretrain/Step Time": 8.802538182586432} +{"Pretrain/Learning Rate": 3.716522103671473e-05, "Pretrain/Loss": 2.079929828643799, "Pretrain/Loss (Raw)": 2.0805654525756836, "Pretrain/Step": 3415, "Pretrain/Step Time": 8.801073085516691} +{"Pretrain/Learning Rate": 3.715780341275207e-05, "Pretrain/Loss": 2.0790247917175293, "Pretrain/Loss (Raw)": 2.0645644664764404, "Pretrain/Step": 3416, "Pretrain/Step Time": 8.802258035168052} +{"Pretrain/Learning Rate": 3.715038438669423e-05, "Pretrain/Loss": 2.079249858856201, "Pretrain/Loss (Raw)": 1.9277926683425903, "Pretrain/Step": 3417, "Pretrain/Step Time": 8.804518971592188} +{"Pretrain/Learning Rate": 3.7142963959396806e-05, "Pretrain/Loss": 2.0775790214538574, "Pretrain/Loss (Raw)": 1.9410820007324219, "Pretrain/Step": 3418, "Pretrain/Step Time": 8.795063210651278} +{"Pretrain/Learning Rate": 3.713554213171556e-05, "Pretrain/Loss": 2.0788631439208984, "Pretrain/Loss (Raw)": 2.120811939239502, "Pretrain/Step": 3419, "Pretrain/Step Time": 8.796188328415155} +{"Pretrain/Learning Rate": 3.712811890450641e-05, "Pretrain/Loss": 2.079197406768799, "Pretrain/Loss (Raw)": 1.9737788438796997, "Pretrain/Step": 3420, "Pretrain/Step Time": 8.795797903090715} +{"Pretrain/Learning Rate": 3.712069427862544e-05, "Pretrain/Loss": 2.0804195404052734, "Pretrain/Loss (Raw)": 1.9483133554458618, "Pretrain/Step": 3421, "Pretrain/Step Time": 8.795073881745338} +{"Pretrain/Learning Rate": 3.711326825492889e-05, "Pretrain/Loss": 2.0802431106567383, "Pretrain/Loss (Raw)": 2.0672712326049805, "Pretrain/Step": 3422, "Pretrain/Step Time": 8.798553036525846} +{"Pretrain/Learning Rate": 3.7105840834273164e-05, "Pretrain/Loss": 2.0821690559387207, "Pretrain/Loss (Raw)": 2.2230279445648193, "Pretrain/Step": 3423, "Pretrain/Step Time": 8.797710549086332} +{"Pretrain/Learning Rate": 3.7098412017514835e-05, "Pretrain/Loss": 2.0818538665771484, "Pretrain/Loss (Raw)": 2.0260119438171387, "Pretrain/Step": 3424, "Pretrain/Step Time": 8.79768710769713} +{"Pretrain/Learning Rate": 3.7090981805510615e-05, "Pretrain/Loss": 2.0802202224731445, "Pretrain/Loss (Raw)": 2.1098952293395996, "Pretrain/Step": 3425, "Pretrain/Step Time": 8.80016134865582} +{"Pretrain/Learning Rate": 3.7083550199117403e-05, "Pretrain/Loss": 2.0791015625, "Pretrain/Loss (Raw)": 2.041104555130005, "Pretrain/Step": 3426, "Pretrain/Step Time": 8.80007403343916} +{"Pretrain/Learning Rate": 3.707611719919224e-05, "Pretrain/Loss": 2.0790600776672363, "Pretrain/Loss (Raw)": 2.188462018966675, "Pretrain/Step": 3427, "Pretrain/Step Time": 8.793984092772007} +{"Pretrain/Learning Rate": 3.706868280659234e-05, "Pretrain/Loss": 2.0791239738464355, "Pretrain/Loss (Raw)": 1.9157689809799194, "Pretrain/Step": 3428, "Pretrain/Step Time": 8.79415544308722} +{"Pretrain/Learning Rate": 3.7061247022175064e-05, "Pretrain/Loss": 2.0799660682678223, "Pretrain/Loss (Raw)": 2.178678274154663, "Pretrain/Step": 3429, "Pretrain/Step Time": 8.795295301824808} +{"Pretrain/Learning Rate": 3.705380984679795e-05, "Pretrain/Loss": 2.080758571624756, "Pretrain/Loss (Raw)": 2.0461528301239014, "Pretrain/Step": 3430, "Pretrain/Step Time": 8.796250250190496} +{"Pretrain/Learning Rate": 3.704637128131868e-05, "Pretrain/Loss": 2.0802547931671143, "Pretrain/Loss (Raw)": 2.055703639984131, "Pretrain/Step": 3431, "Pretrain/Step Time": 8.796761147677898} +{"Pretrain/Learning Rate": 3.7038931326595115e-05, "Pretrain/Loss": 2.080857992172241, "Pretrain/Loss (Raw)": 2.0473709106445312, "Pretrain/Step": 3432, "Pretrain/Step Time": 8.791926903650165} +{"Pretrain/Learning Rate": 3.703148998348526e-05, "Pretrain/Loss": 2.080911874771118, "Pretrain/Loss (Raw)": 2.229809522628784, "Pretrain/Step": 3433, "Pretrain/Step Time": 8.791189048439264} +{"Pretrain/Learning Rate": 3.702404725284728e-05, "Pretrain/Loss": 2.0803308486938477, "Pretrain/Loss (Raw)": 2.1191136837005615, "Pretrain/Step": 3434, "Pretrain/Step Time": 8.792730996385217} +{"Pretrain/Learning Rate": 3.7016603135539524e-05, "Pretrain/Loss": 2.0799803733825684, "Pretrain/Loss (Raw)": 1.9991097450256348, "Pretrain/Step": 3435, "Pretrain/Step Time": 8.787608113139868} +{"Pretrain/Learning Rate": 3.700915763242046e-05, "Pretrain/Loss": 2.078216075897217, "Pretrain/Loss (Raw)": 2.02681827545166, "Pretrain/Step": 3436, "Pretrain/Step Time": 8.785894582048059} +{"Pretrain/Learning Rate": 3.700171074434876e-05, "Pretrain/Loss": 2.078591823577881, "Pretrain/Loss (Raw)": 2.161868095397949, "Pretrain/Step": 3437, "Pretrain/Step Time": 8.787794632837176} +{"Pretrain/Learning Rate": 3.699426247218321e-05, "Pretrain/Loss": 2.07908034324646, "Pretrain/Loss (Raw)": 1.9097397327423096, "Pretrain/Step": 3438, "Pretrain/Step Time": 8.791644025593996} +{"Pretrain/Learning Rate": 3.69868128167828e-05, "Pretrain/Loss": 2.076350212097168, "Pretrain/Loss (Raw)": 1.8886640071868896, "Pretrain/Step": 3439, "Pretrain/Step Time": 8.785585332661867} +{"Pretrain/Learning Rate": 3.697936177900665e-05, "Pretrain/Loss": 2.0761587619781494, "Pretrain/Loss (Raw)": 2.065613031387329, "Pretrain/Step": 3440, "Pretrain/Step Time": 8.78975410759449} +{"Pretrain/Learning Rate": 3.697190935971405e-05, "Pretrain/Loss": 2.0795929431915283, "Pretrain/Loss (Raw)": 2.4484684467315674, "Pretrain/Step": 3441, "Pretrain/Step Time": 8.785398408770561} +{"Pretrain/Learning Rate": 3.696445555976445e-05, "Pretrain/Loss": 2.080345630645752, "Pretrain/Loss (Raw)": 2.2513604164123535, "Pretrain/Step": 3442, "Pretrain/Step Time": 8.783928772434592} +{"Pretrain/Learning Rate": 3.695700038001746e-05, "Pretrain/Loss": 2.079622745513916, "Pretrain/Loss (Raw)": 2.048332452774048, "Pretrain/Step": 3443, "Pretrain/Step Time": 8.782148273661733} +{"Pretrain/Learning Rate": 3.694954382133284e-05, "Pretrain/Loss": 2.0809195041656494, "Pretrain/Loss (Raw)": 2.2160935401916504, "Pretrain/Step": 3444, "Pretrain/Step Time": 8.782293822616339} +{"Pretrain/Learning Rate": 3.694208588457051e-05, "Pretrain/Loss": 2.081760883331299, "Pretrain/Loss (Raw)": 2.0523271560668945, "Pretrain/Step": 3445, "Pretrain/Step Time": 8.789542058482766} +{"Pretrain/Learning Rate": 3.693462657059058e-05, "Pretrain/Loss": 2.0805444717407227, "Pretrain/Loss (Raw)": 1.8689430952072144, "Pretrain/Step": 3446, "Pretrain/Step Time": 8.774863658472896} +{"Pretrain/Learning Rate": 3.6927165880253266e-05, "Pretrain/Loss": 2.08074688911438, "Pretrain/Loss (Raw)": 2.1955621242523193, "Pretrain/Step": 3447, "Pretrain/Step Time": 8.78250640258193} +{"Pretrain/Learning Rate": 3.691970381441898e-05, "Pretrain/Loss": 2.0778603553771973, "Pretrain/Loss (Raw)": 1.9394205808639526, "Pretrain/Step": 3448, "Pretrain/Step Time": 8.782537505030632} +{"Pretrain/Learning Rate": 3.691224037394828e-05, "Pretrain/Loss": 2.076988697052002, "Pretrain/Loss (Raw)": 2.1318843364715576, "Pretrain/Step": 3449, "Pretrain/Step Time": 8.782928630709648} +{"Pretrain/Learning Rate": 3.69047755597019e-05, "Pretrain/Loss": 2.0776686668395996, "Pretrain/Loss (Raw)": 2.0302631855010986, "Pretrain/Step": 3450, "Pretrain/Step Time": 8.787805872038007} +{"Pretrain/Learning Rate": 3.68973093725407e-05, "Pretrain/Loss": 2.0763678550720215, "Pretrain/Loss (Raw)": 2.1120407581329346, "Pretrain/Step": 3451, "Pretrain/Step Time": 8.78044030815363} +{"Pretrain/Learning Rate": 3.688984181332572e-05, "Pretrain/Loss": 2.0756096839904785, "Pretrain/Loss (Raw)": 2.0866682529449463, "Pretrain/Step": 3452, "Pretrain/Step Time": 8.79358527250588} +{"Pretrain/Learning Rate": 3.688237288291815e-05, "Pretrain/Loss": 2.0770182609558105, "Pretrain/Loss (Raw)": 2.169747829437256, "Pretrain/Step": 3453, "Pretrain/Step Time": 8.784994004294276} +{"Pretrain/Learning Rate": 3.687490258217935e-05, "Pretrain/Loss": 2.07619309425354, "Pretrain/Loss (Raw)": 1.9548351764678955, "Pretrain/Step": 3454, "Pretrain/Step Time": 8.782418014481664} +{"Pretrain/Learning Rate": 3.6867430911970824e-05, "Pretrain/Loss": 2.075618267059326, "Pretrain/Loss (Raw)": 1.985156536102295, "Pretrain/Step": 3455, "Pretrain/Step Time": 8.788483452051878} +{"Pretrain/Learning Rate": 3.6859957873154256e-05, "Pretrain/Loss": 2.0765087604522705, "Pretrain/Loss (Raw)": 2.0702688694000244, "Pretrain/Step": 3456, "Pretrain/Step Time": 8.794451715424657} +{"Pretrain/Learning Rate": 3.6852483466591447e-05, "Pretrain/Loss": 2.076673984527588, "Pretrain/Loss (Raw)": 2.2229084968566895, "Pretrain/Step": 3457, "Pretrain/Step Time": 8.79312496073544} +{"Pretrain/Learning Rate": 3.6845007693144404e-05, "Pretrain/Loss": 2.0772790908813477, "Pretrain/Loss (Raw)": 2.114239454269409, "Pretrain/Step": 3458, "Pretrain/Step Time": 8.790264841169119} +{"Pretrain/Learning Rate": 3.683753055367526e-05, "Pretrain/Loss": 2.07643461227417, "Pretrain/Loss (Raw)": 2.003124713897705, "Pretrain/Step": 3459, "Pretrain/Step Time": 8.791044998914003} +{"Pretrain/Learning Rate": 3.68300520490463e-05, "Pretrain/Loss": 2.076390027999878, "Pretrain/Loss (Raw)": 2.2104082107543945, "Pretrain/Step": 3460, "Pretrain/Step Time": 8.801009934395552} +{"Pretrain/Learning Rate": 3.682257218012e-05, "Pretrain/Loss": 2.0764992237091064, "Pretrain/Loss (Raw)": 2.122023344039917, "Pretrain/Step": 3461, "Pretrain/Step Time": 8.798021724447608} +{"Pretrain/Learning Rate": 3.6815090947758966e-05, "Pretrain/Loss": 2.0782039165496826, "Pretrain/Loss (Raw)": 1.9979655742645264, "Pretrain/Step": 3462, "Pretrain/Step Time": 8.800601890310645} +{"Pretrain/Learning Rate": 3.6807608352825975e-05, "Pretrain/Loss": 2.0814743041992188, "Pretrain/Loss (Raw)": 2.3598780632019043, "Pretrain/Step": 3463, "Pretrain/Step Time": 8.798721758648753} +{"Pretrain/Learning Rate": 3.680012439618394e-05, "Pretrain/Loss": 2.0821309089660645, "Pretrain/Loss (Raw)": 2.2002124786376953, "Pretrain/Step": 3464, "Pretrain/Step Time": 8.79472329840064} +{"Pretrain/Learning Rate": 3.679263907869596e-05, "Pretrain/Loss": 2.081866979598999, "Pretrain/Loss (Raw)": 2.0863876342773438, "Pretrain/Step": 3465, "Pretrain/Step Time": 8.795714277774096} +{"Pretrain/Learning Rate": 3.678515240122527e-05, "Pretrain/Loss": 2.0808074474334717, "Pretrain/Loss (Raw)": 1.8800363540649414, "Pretrain/Step": 3466, "Pretrain/Step Time": 8.78745094127953} +{"Pretrain/Learning Rate": 3.677766436463527e-05, "Pretrain/Loss": 2.0820693969726562, "Pretrain/Loss (Raw)": 1.9983302354812622, "Pretrain/Step": 3467, "Pretrain/Step Time": 8.796709211543202} +{"Pretrain/Learning Rate": 3.677017496978952e-05, "Pretrain/Loss": 2.082249164581299, "Pretrain/Loss (Raw)": 2.0509727001190186, "Pretrain/Step": 3468, "Pretrain/Step Time": 8.796963598579168} +{"Pretrain/Learning Rate": 3.6762684217551735e-05, "Pretrain/Loss": 2.0834879875183105, "Pretrain/Loss (Raw)": 2.1561527252197266, "Pretrain/Step": 3469, "Pretrain/Step Time": 8.799140755087137} +{"Pretrain/Learning Rate": 3.675519210878577e-05, "Pretrain/Loss": 2.0833356380462646, "Pretrain/Loss (Raw)": 2.190127372741699, "Pretrain/Step": 3470, "Pretrain/Step Time": 8.799178740009665} +{"Pretrain/Learning Rate": 3.6747698644355664e-05, "Pretrain/Loss": 2.0835020542144775, "Pretrain/Loss (Raw)": 2.0495638847351074, "Pretrain/Step": 3471, "Pretrain/Step Time": 8.805735271424055} +{"Pretrain/Learning Rate": 3.674020382512559e-05, "Pretrain/Loss": 2.0854744911193848, "Pretrain/Loss (Raw)": 2.221290111541748, "Pretrain/Step": 3472, "Pretrain/Step Time": 8.797508990392089} +{"Pretrain/Learning Rate": 3.673270765195989e-05, "Pretrain/Loss": 2.0886263847351074, "Pretrain/Loss (Raw)": 2.2017314434051514, "Pretrain/Step": 3473, "Pretrain/Step Time": 8.79964666441083} +{"Pretrain/Learning Rate": 3.672521012572307e-05, "Pretrain/Loss": 2.090080499649048, "Pretrain/Loss (Raw)": 2.142261028289795, "Pretrain/Step": 3474, "Pretrain/Step Time": 8.79952391423285} +{"Pretrain/Learning Rate": 3.671771124727975e-05, "Pretrain/Loss": 2.089737892150879, "Pretrain/Loss (Raw)": 2.082103729248047, "Pretrain/Step": 3475, "Pretrain/Step Time": 8.796743484213948} +{"Pretrain/Learning Rate": 3.671021101749476e-05, "Pretrain/Loss": 2.091470956802368, "Pretrain/Loss (Raw)": 2.215301036834717, "Pretrain/Step": 3476, "Pretrain/Step Time": 8.798671999946237} +{"Pretrain/Learning Rate": 3.670270943723305e-05, "Pretrain/Loss": 2.0922369956970215, "Pretrain/Loss (Raw)": 2.04423451423645, "Pretrain/Step": 3477, "Pretrain/Step Time": 8.800557041540742} +{"Pretrain/Learning Rate": 3.669520650735975e-05, "Pretrain/Loss": 2.090014934539795, "Pretrain/Loss (Raw)": 1.9816733598709106, "Pretrain/Step": 3478, "Pretrain/Step Time": 8.797671899199486} +{"Pretrain/Learning Rate": 3.668770222874012e-05, "Pretrain/Loss": 2.0889596939086914, "Pretrain/Loss (Raw)": 1.905785322189331, "Pretrain/Step": 3479, "Pretrain/Step Time": 8.798685014247894} +{"Pretrain/Learning Rate": 3.6680196602239596e-05, "Pretrain/Loss": 2.08402156829834, "Pretrain/Loss (Raw)": 1.6197922229766846, "Pretrain/Step": 3480, "Pretrain/Step Time": 8.799147501587868} +{"Pretrain/Learning Rate": 3.667268962872376e-05, "Pretrain/Loss": 2.084275722503662, "Pretrain/Loss (Raw)": 2.08904767036438, "Pretrain/Step": 3481, "Pretrain/Step Time": 8.801443802192807} +{"Pretrain/Learning Rate": 3.666518130905836e-05, "Pretrain/Loss": 2.0836846828460693, "Pretrain/Loss (Raw)": 2.2016680240631104, "Pretrain/Step": 3482, "Pretrain/Step Time": 8.802706561982632} +{"Pretrain/Learning Rate": 3.665767164410928e-05, "Pretrain/Loss": 2.08182954788208, "Pretrain/Loss (Raw)": 1.9084689617156982, "Pretrain/Step": 3483, "Pretrain/Step Time": 8.796826601028442} +{"Pretrain/Learning Rate": 3.665016063474257e-05, "Pretrain/Loss": 2.0809507369995117, "Pretrain/Loss (Raw)": 2.010629653930664, "Pretrain/Step": 3484, "Pretrain/Step Time": 8.798251217231154} +{"Pretrain/Learning Rate": 3.664264828182444e-05, "Pretrain/Loss": 2.0795912742614746, "Pretrain/Loss (Raw)": 1.953332781791687, "Pretrain/Step": 3485, "Pretrain/Step Time": 8.799093348905444} +{"Pretrain/Learning Rate": 3.663513458622124e-05, "Pretrain/Loss": 2.0790538787841797, "Pretrain/Loss (Raw)": 1.9978328943252563, "Pretrain/Step": 3486, "Pretrain/Step Time": 8.800284823402762} +{"Pretrain/Learning Rate": 3.662761954879951e-05, "Pretrain/Loss": 2.0788261890411377, "Pretrain/Loss (Raw)": 1.9578971862792969, "Pretrain/Step": 3487, "Pretrain/Step Time": 8.80130634456873} +{"Pretrain/Learning Rate": 3.662010317042589e-05, "Pretrain/Loss": 2.079653263092041, "Pretrain/Loss (Raw)": 2.197455406188965, "Pretrain/Step": 3488, "Pretrain/Step Time": 8.78608700633049} +{"Pretrain/Learning Rate": 3.661258545196722e-05, "Pretrain/Loss": 2.077256917953491, "Pretrain/Loss (Raw)": 1.849157691001892, "Pretrain/Step": 3489, "Pretrain/Step Time": 8.786637170240283} +{"Pretrain/Learning Rate": 3.6605066394290476e-05, "Pretrain/Loss": 2.076206684112549, "Pretrain/Loss (Raw)": 1.947281837463379, "Pretrain/Step": 3490, "Pretrain/Step Time": 8.782525921240449} +{"Pretrain/Learning Rate": 3.659754599826279e-05, "Pretrain/Loss": 2.075540781021118, "Pretrain/Loss (Raw)": 2.0548107624053955, "Pretrain/Step": 3491, "Pretrain/Step Time": 8.783724840730429} +{"Pretrain/Learning Rate": 3.659002426475145e-05, "Pretrain/Loss": 2.0755977630615234, "Pretrain/Loss (Raw)": 2.0866618156433105, "Pretrain/Step": 3492, "Pretrain/Step Time": 8.784884540364146} +{"Pretrain/Learning Rate": 3.65825011946239e-05, "Pretrain/Loss": 2.076542615890503, "Pretrain/Loss (Raw)": 2.092393159866333, "Pretrain/Step": 3493, "Pretrain/Step Time": 8.78471321798861} +{"Pretrain/Learning Rate": 3.6574976788747725e-05, "Pretrain/Loss": 2.076782703399658, "Pretrain/Loss (Raw)": 1.9470232725143433, "Pretrain/Step": 3494, "Pretrain/Step Time": 8.77813489176333} +{"Pretrain/Learning Rate": 3.6567451047990696e-05, "Pretrain/Loss": 2.077040433883667, "Pretrain/Loss (Raw)": 2.115882158279419, "Pretrain/Step": 3495, "Pretrain/Step Time": 8.78769363835454} +{"Pretrain/Learning Rate": 3.6559923973220695e-05, "Pretrain/Loss": 2.0784506797790527, "Pretrain/Loss (Raw)": 2.1874499320983887, "Pretrain/Step": 3496, "Pretrain/Step Time": 8.7881396766752} +{"Pretrain/Learning Rate": 3.65523955653058e-05, "Pretrain/Loss": 2.0769925117492676, "Pretrain/Loss (Raw)": 2.1136698722839355, "Pretrain/Step": 3497, "Pretrain/Step Time": 8.785406420007348} +{"Pretrain/Learning Rate": 3.65448658251142e-05, "Pretrain/Loss": 2.0768814086914062, "Pretrain/Loss (Raw)": 2.150435447692871, "Pretrain/Step": 3498, "Pretrain/Step Time": 8.7902936283499} +{"Pretrain/Learning Rate": 3.653733475351428e-05, "Pretrain/Loss": 2.0762743949890137, "Pretrain/Loss (Raw)": 1.9491217136383057, "Pretrain/Step": 3499, "Pretrain/Step Time": 8.79078633338213} +{"Pretrain/Learning Rate": 3.6529802351374545e-05, "Pretrain/Loss": 2.07332706451416, "Pretrain/Loss (Raw)": 1.7602753639221191, "Pretrain/Step": 3500, "Pretrain/Step Time": 8.785756075754762} +{"Pretrain/Learning Rate": 3.652226861956368e-05, "Pretrain/Loss": 2.07287335395813, "Pretrain/Loss (Raw)": 1.9258712530136108, "Pretrain/Step": 3501, "Pretrain/Step Time": 8.791567789390683} +{"Pretrain/Learning Rate": 3.65147335589505e-05, "Pretrain/Loss": 2.0717854499816895, "Pretrain/Loss (Raw)": 2.03019642829895, "Pretrain/Step": 3502, "Pretrain/Step Time": 8.788705529645085} +{"Pretrain/Learning Rate": 3.650719717040398e-05, "Pretrain/Loss": 2.0702638626098633, "Pretrain/Loss (Raw)": 1.8489198684692383, "Pretrain/Step": 3503, "Pretrain/Step Time": 8.793584823608398} +{"Pretrain/Learning Rate": 3.649965945479326e-05, "Pretrain/Loss": 2.07018780708313, "Pretrain/Loss (Raw)": 2.079782724380493, "Pretrain/Step": 3504, "Pretrain/Step Time": 8.790723310783505} +{"Pretrain/Learning Rate": 3.649212041298763e-05, "Pretrain/Loss": 2.0698719024658203, "Pretrain/Loss (Raw)": 2.091151475906372, "Pretrain/Step": 3505, "Pretrain/Step Time": 8.793651290237904} +{"Pretrain/Learning Rate": 3.648458004585652e-05, "Pretrain/Loss": 2.069300651550293, "Pretrain/Loss (Raw)": 2.0984199047088623, "Pretrain/Step": 3506, "Pretrain/Step Time": 8.790032837539911} +{"Pretrain/Learning Rate": 3.647703835426952e-05, "Pretrain/Loss": 2.069080352783203, "Pretrain/Loss (Raw)": 2.0919110774993896, "Pretrain/Step": 3507, "Pretrain/Step Time": 8.79077398404479} +{"Pretrain/Learning Rate": 3.646949533909637e-05, "Pretrain/Loss": 2.0677473545074463, "Pretrain/Loss (Raw)": 1.924896478652954, "Pretrain/Step": 3508, "Pretrain/Step Time": 8.795191459357738} +{"Pretrain/Learning Rate": 3.646195100120698e-05, "Pretrain/Loss": 2.067892074584961, "Pretrain/Loss (Raw)": 2.160386085510254, "Pretrain/Step": 3509, "Pretrain/Step Time": 8.793293161317706} +{"Pretrain/Learning Rate": 3.645440534147139e-05, "Pretrain/Loss": 2.0660033226013184, "Pretrain/Loss (Raw)": 1.8990354537963867, "Pretrain/Step": 3510, "Pretrain/Step Time": 8.786831425502896} +{"Pretrain/Learning Rate": 3.644685836075979e-05, "Pretrain/Loss": 2.0659918785095215, "Pretrain/Loss (Raw)": 2.0091586112976074, "Pretrain/Step": 3511, "Pretrain/Step Time": 8.788856193423271} +{"Pretrain/Learning Rate": 3.643931005994255e-05, "Pretrain/Loss": 2.0644900798797607, "Pretrain/Loss (Raw)": 1.9705736637115479, "Pretrain/Step": 3512, "Pretrain/Step Time": 8.783990992233157} +{"Pretrain/Learning Rate": 3.643176043989018e-05, "Pretrain/Loss": 2.0646142959594727, "Pretrain/Loss (Raw)": 2.1999402046203613, "Pretrain/Step": 3513, "Pretrain/Step Time": 8.786258794367313} +{"Pretrain/Learning Rate": 3.6424209501473314e-05, "Pretrain/Loss": 2.0669169425964355, "Pretrain/Loss (Raw)": 2.2924294471740723, "Pretrain/Step": 3514, "Pretrain/Step Time": 8.784171489998698} +{"Pretrain/Learning Rate": 3.641665724556278e-05, "Pretrain/Loss": 2.0673575401306152, "Pretrain/Loss (Raw)": 2.0392420291900635, "Pretrain/Step": 3515, "Pretrain/Step Time": 8.78625787422061} +{"Pretrain/Learning Rate": 3.6409103673029535e-05, "Pretrain/Loss": 2.0679125785827637, "Pretrain/Loss (Raw)": 2.099818468093872, "Pretrain/Step": 3516, "Pretrain/Step Time": 8.782657220959663} +{"Pretrain/Learning Rate": 3.64015487847447e-05, "Pretrain/Loss": 2.0677642822265625, "Pretrain/Loss (Raw)": 2.0382728576660156, "Pretrain/Step": 3517, "Pretrain/Step Time": 8.778017580509186} +{"Pretrain/Learning Rate": 3.6393992581579526e-05, "Pretrain/Loss": 2.0650081634521484, "Pretrain/Loss (Raw)": 1.9372389316558838, "Pretrain/Step": 3518, "Pretrain/Step Time": 8.777254512533545} +{"Pretrain/Learning Rate": 3.638643506440544e-05, "Pretrain/Loss": 2.0638866424560547, "Pretrain/Loss (Raw)": 1.9932719469070435, "Pretrain/Step": 3519, "Pretrain/Step Time": 8.779563272371888} +{"Pretrain/Learning Rate": 3.6378876234094014e-05, "Pretrain/Loss": 2.0670084953308105, "Pretrain/Loss (Raw)": 2.1373462677001953, "Pretrain/Step": 3520, "Pretrain/Step Time": 8.774100190028548} +{"Pretrain/Learning Rate": 3.6371316091516955e-05, "Pretrain/Loss": 2.064004898071289, "Pretrain/Loss (Raw)": 1.790819764137268, "Pretrain/Step": 3521, "Pretrain/Step Time": 8.771538276225328} +{"Pretrain/Learning Rate": 3.636375463754614e-05, "Pretrain/Loss": 2.066208839416504, "Pretrain/Loss (Raw)": 2.273909091949463, "Pretrain/Step": 3522, "Pretrain/Step Time": 8.772853892296553} +{"Pretrain/Learning Rate": 3.6356191873053594e-05, "Pretrain/Loss": 2.065234422683716, "Pretrain/Loss (Raw)": 2.0395028591156006, "Pretrain/Step": 3523, "Pretrain/Step Time": 8.782829195261002} +{"Pretrain/Learning Rate": 3.634862779891148e-05, "Pretrain/Loss": 2.0635409355163574, "Pretrain/Loss (Raw)": 1.9698046445846558, "Pretrain/Step": 3524, "Pretrain/Step Time": 8.775741703808308} +{"Pretrain/Learning Rate": 3.634106241599215e-05, "Pretrain/Loss": 2.0645253658294678, "Pretrain/Loss (Raw)": 2.0140249729156494, "Pretrain/Step": 3525, "Pretrain/Step Time": 8.77876308746636} +{"Pretrain/Learning Rate": 3.633349572516805e-05, "Pretrain/Loss": 2.0648112297058105, "Pretrain/Loss (Raw)": 2.084118604660034, "Pretrain/Step": 3526, "Pretrain/Step Time": 8.778612785041332} +{"Pretrain/Learning Rate": 3.632592772731182e-05, "Pretrain/Loss": 2.0647311210632324, "Pretrain/Loss (Raw)": 2.046471357345581, "Pretrain/Step": 3527, "Pretrain/Step Time": 8.781554399058223} +{"Pretrain/Learning Rate": 3.631835842329624e-05, "Pretrain/Loss": 2.0646820068359375, "Pretrain/Loss (Raw)": 2.1671276092529297, "Pretrain/Step": 3528, "Pretrain/Step Time": 8.776405619457364} +{"Pretrain/Learning Rate": 3.6310787813994226e-05, "Pretrain/Loss": 2.06596040725708, "Pretrain/Loss (Raw)": 2.2736921310424805, "Pretrain/Step": 3529, "Pretrain/Step Time": 8.77911701053381} +{"Pretrain/Learning Rate": 3.6303215900278864e-05, "Pretrain/Loss": 2.0661723613739014, "Pretrain/Loss (Raw)": 2.1807470321655273, "Pretrain/Step": 3530, "Pretrain/Step Time": 8.78502774424851} +{"Pretrain/Learning Rate": 3.629564268302338e-05, "Pretrain/Loss": 2.067849636077881, "Pretrain/Loss (Raw)": 2.398912191390991, "Pretrain/Step": 3531, "Pretrain/Step Time": 8.783935278654099} +{"Pretrain/Learning Rate": 3.6288068163101156e-05, "Pretrain/Loss": 2.06881046295166, "Pretrain/Loss (Raw)": 2.272684335708618, "Pretrain/Step": 3532, "Pretrain/Step Time": 8.787851050496101} +{"Pretrain/Learning Rate": 3.628049234138572e-05, "Pretrain/Loss": 2.070370674133301, "Pretrain/Loss (Raw)": 2.245168447494507, "Pretrain/Step": 3533, "Pretrain/Step Time": 8.785020131617785} +{"Pretrain/Learning Rate": 3.6272915218750755e-05, "Pretrain/Loss": 2.0716357231140137, "Pretrain/Loss (Raw)": 2.2185046672821045, "Pretrain/Step": 3534, "Pretrain/Step Time": 8.785042379051447} +{"Pretrain/Learning Rate": 3.6265336796070083e-05, "Pretrain/Loss": 2.0703625679016113, "Pretrain/Loss (Raw)": 1.9674582481384277, "Pretrain/Step": 3535, "Pretrain/Step Time": 8.782958898693323} +{"Pretrain/Learning Rate": 3.62577570742177e-05, "Pretrain/Loss": 2.069406270980835, "Pretrain/Loss (Raw)": 1.9898083209991455, "Pretrain/Step": 3536, "Pretrain/Step Time": 8.78209649771452} +{"Pretrain/Learning Rate": 3.625017605406771e-05, "Pretrain/Loss": 2.070371150970459, "Pretrain/Loss (Raw)": 2.1349475383758545, "Pretrain/Step": 3537, "Pretrain/Step Time": 8.777454748749733} +{"Pretrain/Learning Rate": 3.624259373649441e-05, "Pretrain/Loss": 2.0706064701080322, "Pretrain/Loss (Raw)": 2.1930675506591797, "Pretrain/Step": 3538, "Pretrain/Step Time": 8.782686710357666} +{"Pretrain/Learning Rate": 3.6235010122372214e-05, "Pretrain/Loss": 2.070786952972412, "Pretrain/Loss (Raw)": 2.1145312786102295, "Pretrain/Step": 3539, "Pretrain/Step Time": 8.783071277663112} +{"Pretrain/Learning Rate": 3.6227425212575725e-05, "Pretrain/Loss": 2.0724875926971436, "Pretrain/Loss (Raw)": 2.1320719718933105, "Pretrain/Step": 3540, "Pretrain/Step Time": 8.780500393360853} +{"Pretrain/Learning Rate": 3.621983900797964e-05, "Pretrain/Loss": 2.0762994289398193, "Pretrain/Loss (Raw)": 2.6454732418060303, "Pretrain/Step": 3541, "Pretrain/Step Time": 8.784744951874018} +{"Pretrain/Learning Rate": 3.621225150945886e-05, "Pretrain/Loss": 2.0745012760162354, "Pretrain/Loss (Raw)": 1.9699841737747192, "Pretrain/Step": 3542, "Pretrain/Step Time": 8.781409319490194} +{"Pretrain/Learning Rate": 3.620466271788841e-05, "Pretrain/Loss": 2.073589324951172, "Pretrain/Loss (Raw)": 1.963834285736084, "Pretrain/Step": 3543, "Pretrain/Step Time": 8.780645551159978} +{"Pretrain/Learning Rate": 3.6197072634143436e-05, "Pretrain/Loss": 2.073573589324951, "Pretrain/Loss (Raw)": 2.0625431537628174, "Pretrain/Step": 3544, "Pretrain/Step Time": 8.784352174028754} +{"Pretrain/Learning Rate": 3.61894812590993e-05, "Pretrain/Loss": 2.0749380588531494, "Pretrain/Loss (Raw)": 2.1024560928344727, "Pretrain/Step": 3545, "Pretrain/Step Time": 8.78237028233707} +{"Pretrain/Learning Rate": 3.6181888593631454e-05, "Pretrain/Loss": 2.0742452144622803, "Pretrain/Loss (Raw)": 1.8523908853530884, "Pretrain/Step": 3546, "Pretrain/Step Time": 8.785370465368032} +{"Pretrain/Learning Rate": 3.6174294638615524e-05, "Pretrain/Loss": 2.0730953216552734, "Pretrain/Loss (Raw)": 1.9736342430114746, "Pretrain/Step": 3547, "Pretrain/Step Time": 8.789309296756983} +{"Pretrain/Learning Rate": 3.616669939492728e-05, "Pretrain/Loss": 2.0740270614624023, "Pretrain/Loss (Raw)": 2.093064308166504, "Pretrain/Step": 3548, "Pretrain/Step Time": 8.789954479783773} +{"Pretrain/Learning Rate": 3.615910286344265e-05, "Pretrain/Loss": 2.0751566886901855, "Pretrain/Loss (Raw)": 2.092910051345825, "Pretrain/Step": 3549, "Pretrain/Step Time": 8.786102918908} +{"Pretrain/Learning Rate": 3.615150504503768e-05, "Pretrain/Loss": 2.0747923851013184, "Pretrain/Loss (Raw)": 2.0206475257873535, "Pretrain/Step": 3550, "Pretrain/Step Time": 8.787079568952322} +{"Pretrain/Learning Rate": 3.6143905940588616e-05, "Pretrain/Loss": 2.0730628967285156, "Pretrain/Loss (Raw)": 2.0016191005706787, "Pretrain/Step": 3551, "Pretrain/Step Time": 8.786366259679198} +{"Pretrain/Learning Rate": 3.613630555097179e-05, "Pretrain/Loss": 2.0737085342407227, "Pretrain/Loss (Raw)": 2.1086435317993164, "Pretrain/Step": 3552, "Pretrain/Step Time": 8.78871370665729} +{"Pretrain/Learning Rate": 3.6128703877063755e-05, "Pretrain/Loss": 2.0704963207244873, "Pretrain/Loss (Raw)": 1.6987522840499878, "Pretrain/Step": 3553, "Pretrain/Step Time": 8.779674677178264} +{"Pretrain/Learning Rate": 3.6121100919741126e-05, "Pretrain/Loss": 2.07053804397583, "Pretrain/Loss (Raw)": 2.046414852142334, "Pretrain/Step": 3554, "Pretrain/Step Time": 8.784503525123} +{"Pretrain/Learning Rate": 3.611349667988074e-05, "Pretrain/Loss": 2.0653700828552246, "Pretrain/Loss (Raw)": 1.526983380317688, "Pretrain/Step": 3555, "Pretrain/Step Time": 8.786060655489564} +{"Pretrain/Learning Rate": 3.6105891158359563e-05, "Pretrain/Loss": 2.066347599029541, "Pretrain/Loss (Raw)": 2.040894031524658, "Pretrain/Step": 3556, "Pretrain/Step Time": 8.785503381863236} +{"Pretrain/Learning Rate": 3.6098284356054666e-05, "Pretrain/Loss": 2.065239191055298, "Pretrain/Loss (Raw)": 2.036794900894165, "Pretrain/Step": 3557, "Pretrain/Step Time": 8.787530314177275} +{"Pretrain/Learning Rate": 3.609067627384333e-05, "Pretrain/Loss": 2.0648608207702637, "Pretrain/Loss (Raw)": 1.9977260828018188, "Pretrain/Step": 3558, "Pretrain/Step Time": 8.784913258627057} +{"Pretrain/Learning Rate": 3.608306691260295e-05, "Pretrain/Loss": 2.065605640411377, "Pretrain/Loss (Raw)": 2.1510367393493652, "Pretrain/Step": 3559, "Pretrain/Step Time": 8.799697767943144} +{"Pretrain/Learning Rate": 3.607545627321106e-05, "Pretrain/Loss": 2.0658984184265137, "Pretrain/Loss (Raw)": 2.084860324859619, "Pretrain/Step": 3560, "Pretrain/Step Time": 8.791658433154225} +{"Pretrain/Learning Rate": 3.606784435654536e-05, "Pretrain/Loss": 2.065464496612549, "Pretrain/Loss (Raw)": 2.1742632389068604, "Pretrain/Step": 3561, "Pretrain/Step Time": 8.795816265046597} +{"Pretrain/Learning Rate": 3.6060231163483704e-05, "Pretrain/Loss": 2.0639519691467285, "Pretrain/Loss (Raw)": 1.925498127937317, "Pretrain/Step": 3562, "Pretrain/Step Time": 8.791169203817844} +{"Pretrain/Learning Rate": 3.6052616694904066e-05, "Pretrain/Loss": 2.065058708190918, "Pretrain/Loss (Raw)": 2.1407594680786133, "Pretrain/Step": 3563, "Pretrain/Step Time": 8.795098278671503} +{"Pretrain/Learning Rate": 3.60450009516846e-05, "Pretrain/Loss": 2.066751480102539, "Pretrain/Loss (Raw)": 2.2435295581817627, "Pretrain/Step": 3564, "Pretrain/Step Time": 8.796296060085297} +{"Pretrain/Learning Rate": 3.603738393470357e-05, "Pretrain/Loss": 2.0663580894470215, "Pretrain/Loss (Raw)": 2.1115121841430664, "Pretrain/Step": 3565, "Pretrain/Step Time": 8.7997817825526} +{"Pretrain/Learning Rate": 3.6029765644839416e-05, "Pretrain/Loss": 2.06811261177063, "Pretrain/Loss (Raw)": 2.1343259811401367, "Pretrain/Step": 3566, "Pretrain/Step Time": 8.79375321045518} +{"Pretrain/Learning Rate": 3.602214608297071e-05, "Pretrain/Loss": 2.069612741470337, "Pretrain/Loss (Raw)": 2.08066987991333, "Pretrain/Step": 3567, "Pretrain/Step Time": 8.793899726122618} +{"Pretrain/Learning Rate": 3.601452524997619e-05, "Pretrain/Loss": 2.069136142730713, "Pretrain/Loss (Raw)": 2.004607677459717, "Pretrain/Step": 3568, "Pretrain/Step Time": 8.790516586974263} +{"Pretrain/Learning Rate": 3.600690314673471e-05, "Pretrain/Loss": 2.0655460357666016, "Pretrain/Loss (Raw)": 1.988944411277771, "Pretrain/Step": 3569, "Pretrain/Step Time": 8.797844810411334} +{"Pretrain/Learning Rate": 3.599927977412529e-05, "Pretrain/Loss": 2.0626585483551025, "Pretrain/Loss (Raw)": 1.8817331790924072, "Pretrain/Step": 3570, "Pretrain/Step Time": 8.795233840122819} +{"Pretrain/Learning Rate": 3.59916551330271e-05, "Pretrain/Loss": 2.062242031097412, "Pretrain/Loss (Raw)": 1.9950062036514282, "Pretrain/Step": 3571, "Pretrain/Step Time": 8.794622441753745} +{"Pretrain/Learning Rate": 3.598402922431944e-05, "Pretrain/Loss": 2.0611205101013184, "Pretrain/Loss (Raw)": 2.0725786685943604, "Pretrain/Step": 3572, "Pretrain/Step Time": 8.798132918775082} +{"Pretrain/Learning Rate": 3.5976402048881786e-05, "Pretrain/Loss": 2.0611157417297363, "Pretrain/Loss (Raw)": 2.051685094833374, "Pretrain/Step": 3573, "Pretrain/Step Time": 8.791551200672984} +{"Pretrain/Learning Rate": 3.596877360759371e-05, "Pretrain/Loss": 2.0612447261810303, "Pretrain/Loss (Raw)": 1.8854687213897705, "Pretrain/Step": 3574, "Pretrain/Step Time": 8.794560948386788} +{"Pretrain/Learning Rate": 3.5961143901334984e-05, "Pretrain/Loss": 2.060715675354004, "Pretrain/Loss (Raw)": 2.1278274059295654, "Pretrain/Step": 3575, "Pretrain/Step Time": 8.791524410247803} +{"Pretrain/Learning Rate": 3.5953512930985486e-05, "Pretrain/Loss": 2.061838150024414, "Pretrain/Loss (Raw)": 2.0831217765808105, "Pretrain/Step": 3576, "Pretrain/Step Time": 8.795582933351398} +{"Pretrain/Learning Rate": 3.594588069742527e-05, "Pretrain/Loss": 2.0611870288848877, "Pretrain/Loss (Raw)": 2.048525094985962, "Pretrain/Step": 3577, "Pretrain/Step Time": 8.79133740067482} +{"Pretrain/Learning Rate": 3.5938247201534505e-05, "Pretrain/Loss": 2.0607078075408936, "Pretrain/Loss (Raw)": 1.968912959098816, "Pretrain/Step": 3578, "Pretrain/Step Time": 8.788033612072468} +{"Pretrain/Learning Rate": 3.5930612444193535e-05, "Pretrain/Loss": 2.0594065189361572, "Pretrain/Loss (Raw)": 1.9454944133758545, "Pretrain/Step": 3579, "Pretrain/Step Time": 8.799283089116216} +{"Pretrain/Learning Rate": 3.592297642628283e-05, "Pretrain/Loss": 2.058979034423828, "Pretrain/Loss (Raw)": 2.031956434249878, "Pretrain/Step": 3580, "Pretrain/Step Time": 8.789988545700908} +{"Pretrain/Learning Rate": 3.5915339148683005e-05, "Pretrain/Loss": 2.0571982860565186, "Pretrain/Loss (Raw)": 1.9417895078659058, "Pretrain/Step": 3581, "Pretrain/Step Time": 8.791563048958778} +{"Pretrain/Learning Rate": 3.590770061227484e-05, "Pretrain/Loss": 2.0566511154174805, "Pretrain/Loss (Raw)": 1.8848239183425903, "Pretrain/Step": 3582, "Pretrain/Step Time": 8.798308830708265} +{"Pretrain/Learning Rate": 3.590006081793925e-05, "Pretrain/Loss": 2.0575332641601562, "Pretrain/Loss (Raw)": 2.0980565547943115, "Pretrain/Step": 3583, "Pretrain/Step Time": 8.792276034131646} +{"Pretrain/Learning Rate": 3.589241976655727e-05, "Pretrain/Loss": 2.0579445362091064, "Pretrain/Loss (Raw)": 2.1229355335235596, "Pretrain/Step": 3584, "Pretrain/Step Time": 8.784355141222477} +{"Pretrain/Learning Rate": 3.588477745901013e-05, "Pretrain/Loss": 2.0576162338256836, "Pretrain/Loss (Raw)": 2.180870532989502, "Pretrain/Step": 3585, "Pretrain/Step Time": 8.782814670354128} +{"Pretrain/Learning Rate": 3.587713389617916e-05, "Pretrain/Loss": 2.0576674938201904, "Pretrain/Loss (Raw)": 2.1207892894744873, "Pretrain/Step": 3586, "Pretrain/Step Time": 8.790248604491353} +{"Pretrain/Learning Rate": 3.5869489078945845e-05, "Pretrain/Loss": 2.057781219482422, "Pretrain/Loss (Raw)": 2.0176889896392822, "Pretrain/Step": 3587, "Pretrain/Step Time": 8.785524660721421} +{"Pretrain/Learning Rate": 3.586184300819184e-05, "Pretrain/Loss": 2.0555579662323, "Pretrain/Loss (Raw)": 1.9258266687393188, "Pretrain/Step": 3588, "Pretrain/Step Time": 8.778035728260875} +{"Pretrain/Learning Rate": 3.585419568479891e-05, "Pretrain/Loss": 2.0542798042297363, "Pretrain/Loss (Raw)": 1.9584094285964966, "Pretrain/Step": 3589, "Pretrain/Step Time": 8.78128314204514} +{"Pretrain/Learning Rate": 3.584654710964899e-05, "Pretrain/Loss": 2.0552713871002197, "Pretrain/Loss (Raw)": 2.124891519546509, "Pretrain/Step": 3590, "Pretrain/Step Time": 8.775815770030022} +{"Pretrain/Learning Rate": 3.583889728362414e-05, "Pretrain/Loss": 2.0540771484375, "Pretrain/Loss (Raw)": 2.2070302963256836, "Pretrain/Step": 3591, "Pretrain/Step Time": 8.778263840824366} +{"Pretrain/Learning Rate": 3.583124620760659e-05, "Pretrain/Loss": 2.0531859397888184, "Pretrain/Loss (Raw)": 2.086115598678589, "Pretrain/Step": 3592, "Pretrain/Step Time": 8.776445265859365} +{"Pretrain/Learning Rate": 3.582359388247869e-05, "Pretrain/Loss": 2.0526819229125977, "Pretrain/Loss (Raw)": 2.021879196166992, "Pretrain/Step": 3593, "Pretrain/Step Time": 8.784587766975164} +{"Pretrain/Learning Rate": 3.581594030912294e-05, "Pretrain/Loss": 2.0548689365386963, "Pretrain/Loss (Raw)": 2.1599855422973633, "Pretrain/Step": 3594, "Pretrain/Step Time": 8.78521298058331} +{"Pretrain/Learning Rate": 3.580828548842198e-05, "Pretrain/Loss": 2.056122064590454, "Pretrain/Loss (Raw)": 2.158738613128662, "Pretrain/Step": 3595, "Pretrain/Step Time": 8.771647587418556} +{"Pretrain/Learning Rate": 3.5800629421258606e-05, "Pretrain/Loss": 2.056035041809082, "Pretrain/Loss (Raw)": 2.0398051738739014, "Pretrain/Step": 3596, "Pretrain/Step Time": 8.771685747429729} +{"Pretrain/Learning Rate": 3.579297210851576e-05, "Pretrain/Loss": 2.054795265197754, "Pretrain/Loss (Raw)": 1.9974608421325684, "Pretrain/Step": 3597, "Pretrain/Step Time": 8.772733498364687} +{"Pretrain/Learning Rate": 3.5785313551076505e-05, "Pretrain/Loss": 2.0526680946350098, "Pretrain/Loss (Raw)": 1.9178836345672607, "Pretrain/Step": 3598, "Pretrain/Step Time": 8.77429499477148} +{"Pretrain/Learning Rate": 3.577765374982408e-05, "Pretrain/Loss": 2.0528945922851562, "Pretrain/Loss (Raw)": 2.078554391860962, "Pretrain/Step": 3599, "Pretrain/Step Time": 8.76621576026082} +{"Pretrain/Learning Rate": 3.576999270564183e-05, "Pretrain/Loss": 2.0512795448303223, "Pretrain/Loss (Raw)": 2.014561414718628, "Pretrain/Step": 3600, "Pretrain/Step Time": 8.766305919736624} +{"Pretrain/Learning Rate": 3.5762330419413273e-05, "Pretrain/Loss": 2.0506012439727783, "Pretrain/Loss (Raw)": 2.114899158477783, "Pretrain/Step": 3601, "Pretrain/Step Time": 8.77558414824307} +{"Pretrain/Learning Rate": 3.575466689202206e-05, "Pretrain/Loss": 2.0495808124542236, "Pretrain/Loss (Raw)": 2.0116467475891113, "Pretrain/Step": 3602, "Pretrain/Step Time": 8.763558328151703} +{"Pretrain/Learning Rate": 3.5747002124351986e-05, "Pretrain/Loss": 2.049636125564575, "Pretrain/Loss (Raw)": 2.089168071746826, "Pretrain/Step": 3603, "Pretrain/Step Time": 8.768114911392331} +{"Pretrain/Learning Rate": 3.573933611728698e-05, "Pretrain/Loss": 2.0482263565063477, "Pretrain/Loss (Raw)": 2.034841299057007, "Pretrain/Step": 3604, "Pretrain/Step Time": 8.770027112215757} +{"Pretrain/Learning Rate": 3.573166887171113e-05, "Pretrain/Loss": 2.0494256019592285, "Pretrain/Loss (Raw)": 2.1977787017822266, "Pretrain/Step": 3605, "Pretrain/Step Time": 8.767770387232304} +{"Pretrain/Learning Rate": 3.5724000388508655e-05, "Pretrain/Loss": 2.05061411857605, "Pretrain/Loss (Raw)": 2.1337738037109375, "Pretrain/Step": 3606, "Pretrain/Step Time": 8.764083694666624} +{"Pretrain/Learning Rate": 3.571633066856392e-05, "Pretrain/Loss": 2.0528416633605957, "Pretrain/Loss (Raw)": 2.190946102142334, "Pretrain/Step": 3607, "Pretrain/Step Time": 8.772436752915382} +{"Pretrain/Learning Rate": 3.570865971276144e-05, "Pretrain/Loss": 2.0585784912109375, "Pretrain/Loss (Raw)": 2.3540592193603516, "Pretrain/Step": 3608, "Pretrain/Step Time": 8.768796415999532} +{"Pretrain/Learning Rate": 3.570098752198586e-05, "Pretrain/Loss": 2.057220697402954, "Pretrain/Loss (Raw)": 1.9152756929397583, "Pretrain/Step": 3609, "Pretrain/Step Time": 8.763022907078266} +{"Pretrain/Learning Rate": 3.569331409712198e-05, "Pretrain/Loss": 2.0555825233459473, "Pretrain/Loss (Raw)": 1.9919849634170532, "Pretrain/Step": 3610, "Pretrain/Step Time": 8.764868848025799} +{"Pretrain/Learning Rate": 3.568563943905472e-05, "Pretrain/Loss": 2.0573878288269043, "Pretrain/Loss (Raw)": 2.1395435333251953, "Pretrain/Step": 3611, "Pretrain/Step Time": 8.769446620717645} +{"Pretrain/Learning Rate": 3.5677963548669175e-05, "Pretrain/Loss": 2.056483745574951, "Pretrain/Loss (Raw)": 1.8949178457260132, "Pretrain/Step": 3612, "Pretrain/Step Time": 8.769877672195435} +{"Pretrain/Learning Rate": 3.567028642685055e-05, "Pretrain/Loss": 2.056142807006836, "Pretrain/Loss (Raw)": 1.9096781015396118, "Pretrain/Step": 3613, "Pretrain/Step Time": 8.770236467942595} +{"Pretrain/Learning Rate": 3.566260807448422e-05, "Pretrain/Loss": 2.0574915409088135, "Pretrain/Loss (Raw)": 2.170459508895874, "Pretrain/Step": 3614, "Pretrain/Step Time": 8.773887129500508} +{"Pretrain/Learning Rate": 3.565492849245568e-05, "Pretrain/Loss": 2.0578160285949707, "Pretrain/Loss (Raw)": 1.9994128942489624, "Pretrain/Step": 3615, "Pretrain/Step Time": 8.771964076906443} +{"Pretrain/Learning Rate": 3.564724768165058e-05, "Pretrain/Loss": 2.0557503700256348, "Pretrain/Loss (Raw)": 1.9330894947052002, "Pretrain/Step": 3616, "Pretrain/Step Time": 8.77240632660687} +{"Pretrain/Learning Rate": 3.5639565642954705e-05, "Pretrain/Loss": 2.0582833290100098, "Pretrain/Loss (Raw)": 2.173372745513916, "Pretrain/Step": 3617, "Pretrain/Step Time": 8.773703571408987} +{"Pretrain/Learning Rate": 3.563188237725399e-05, "Pretrain/Loss": 2.0585379600524902, "Pretrain/Loss (Raw)": 1.9798682928085327, "Pretrain/Step": 3618, "Pretrain/Step Time": 8.776324616745114} +{"Pretrain/Learning Rate": 3.562419788543449e-05, "Pretrain/Loss": 2.058791399002075, "Pretrain/Loss (Raw)": 2.087254285812378, "Pretrain/Step": 3619, "Pretrain/Step Time": 8.773561472073197} +{"Pretrain/Learning Rate": 3.561651216838243e-05, "Pretrain/Loss": 2.057119607925415, "Pretrain/Loss (Raw)": 1.8726564645767212, "Pretrain/Step": 3620, "Pretrain/Step Time": 8.775640286505222} +{"Pretrain/Learning Rate": 3.560882522698417e-05, "Pretrain/Loss": 2.057677745819092, "Pretrain/Loss (Raw)": 2.1638662815093994, "Pretrain/Step": 3621, "Pretrain/Step Time": 8.775955187156796} +{"Pretrain/Learning Rate": 3.560113706212618e-05, "Pretrain/Loss": 2.0574891567230225, "Pretrain/Loss (Raw)": 1.9228492975234985, "Pretrain/Step": 3622, "Pretrain/Step Time": 8.77795246988535} +{"Pretrain/Learning Rate": 3.559344767469512e-05, "Pretrain/Loss": 2.057474136352539, "Pretrain/Loss (Raw)": 2.113969326019287, "Pretrain/Step": 3623, "Pretrain/Step Time": 8.771263862028718} +{"Pretrain/Learning Rate": 3.5585757065577755e-05, "Pretrain/Loss": 2.0547454357147217, "Pretrain/Loss (Raw)": 1.8381702899932861, "Pretrain/Step": 3624, "Pretrain/Step Time": 8.77457812987268} +{"Pretrain/Learning Rate": 3.557806523566099e-05, "Pretrain/Loss": 2.054405927658081, "Pretrain/Loss (Raw)": 2.0702364444732666, "Pretrain/Step": 3625, "Pretrain/Step Time": 8.774870492517948} +{"Pretrain/Learning Rate": 3.557037218583191e-05, "Pretrain/Loss": 2.0535011291503906, "Pretrain/Loss (Raw)": 2.0345890522003174, "Pretrain/Step": 3626, "Pretrain/Step Time": 8.764955591410398} +{"Pretrain/Learning Rate": 3.5562677916977704e-05, "Pretrain/Loss": 2.0534026622772217, "Pretrain/Loss (Raw)": 1.9365392923355103, "Pretrain/Step": 3627, "Pretrain/Step Time": 8.763529850170016} +{"Pretrain/Learning Rate": 3.55549824299857e-05, "Pretrain/Loss": 2.0564146041870117, "Pretrain/Loss (Raw)": 2.145817995071411, "Pretrain/Step": 3628, "Pretrain/Step Time": 8.766752677038312} +{"Pretrain/Learning Rate": 3.554728572574339e-05, "Pretrain/Loss": 2.0586256980895996, "Pretrain/Loss (Raw)": 2.208868980407715, "Pretrain/Step": 3629, "Pretrain/Step Time": 8.771357471123338} +{"Pretrain/Learning Rate": 3.5539587805138385e-05, "Pretrain/Loss": 2.0559139251708984, "Pretrain/Loss (Raw)": 1.6830880641937256, "Pretrain/Step": 3630, "Pretrain/Step Time": 8.769946595653892} +{"Pretrain/Learning Rate": 3.5531888669058455e-05, "Pretrain/Loss": 2.058515787124634, "Pretrain/Loss (Raw)": 2.1819565296173096, "Pretrain/Step": 3631, "Pretrain/Step Time": 8.768678680062294} +{"Pretrain/Learning Rate": 3.552418831839149e-05, "Pretrain/Loss": 2.057501792907715, "Pretrain/Loss (Raw)": 1.9500088691711426, "Pretrain/Step": 3632, "Pretrain/Step Time": 8.770691012963653} +{"Pretrain/Learning Rate": 3.551648675402554e-05, "Pretrain/Loss": 2.055494546890259, "Pretrain/Loss (Raw)": 1.8342106342315674, "Pretrain/Step": 3633, "Pretrain/Step Time": 8.763303687795997} +{"Pretrain/Learning Rate": 3.550878397684878e-05, "Pretrain/Loss": 2.055332899093628, "Pretrain/Loss (Raw)": 2.07771897315979, "Pretrain/Step": 3634, "Pretrain/Step Time": 8.763575237244368} +{"Pretrain/Learning Rate": 3.5501079987749535e-05, "Pretrain/Loss": 2.0550026893615723, "Pretrain/Loss (Raw)": 2.049663543701172, "Pretrain/Step": 3635, "Pretrain/Step Time": 8.760572161525488} +{"Pretrain/Learning Rate": 3.549337478761626e-05, "Pretrain/Loss": 2.0555992126464844, "Pretrain/Loss (Raw)": 2.0012331008911133, "Pretrain/Step": 3636, "Pretrain/Step Time": 8.769321706146002} +{"Pretrain/Learning Rate": 3.548566837733756e-05, "Pretrain/Loss": 2.054422616958618, "Pretrain/Loss (Raw)": 2.0097851753234863, "Pretrain/Step": 3637, "Pretrain/Step Time": 8.769209779798985} +{"Pretrain/Learning Rate": 3.547796075780218e-05, "Pretrain/Loss": 2.0558230876922607, "Pretrain/Loss (Raw)": 2.0782930850982666, "Pretrain/Step": 3638, "Pretrain/Step Time": 8.76802502758801} +{"Pretrain/Learning Rate": 3.547025192989898e-05, "Pretrain/Loss": 2.057751178741455, "Pretrain/Loss (Raw)": 2.255946159362793, "Pretrain/Step": 3639, "Pretrain/Step Time": 8.770377270877361} +{"Pretrain/Learning Rate": 3.546254189451699e-05, "Pretrain/Loss": 2.0584492683410645, "Pretrain/Loss (Raw)": 2.059945821762085, "Pretrain/Step": 3640, "Pretrain/Step Time": 8.772029258310795} +{"Pretrain/Learning Rate": 3.5454830652545374e-05, "Pretrain/Loss": 2.057985782623291, "Pretrain/Loss (Raw)": 2.140626907348633, "Pretrain/Step": 3641, "Pretrain/Step Time": 8.763659659773111} +{"Pretrain/Learning Rate": 3.544711820487343e-05, "Pretrain/Loss": 2.0564234256744385, "Pretrain/Loss (Raw)": 2.0924437046051025, "Pretrain/Step": 3642, "Pretrain/Step Time": 8.768970608711243} +{"Pretrain/Learning Rate": 3.543940455239057e-05, "Pretrain/Loss": 2.056671380996704, "Pretrain/Loss (Raw)": 2.0709683895111084, "Pretrain/Step": 3643, "Pretrain/Step Time": 8.77034243196249} +{"Pretrain/Learning Rate": 3.543168969598639e-05, "Pretrain/Loss": 2.0576205253601074, "Pretrain/Loss (Raw)": 2.221301794052124, "Pretrain/Step": 3644, "Pretrain/Step Time": 8.768842402845621} +{"Pretrain/Learning Rate": 3.54239736365506e-05, "Pretrain/Loss": 2.0583529472351074, "Pretrain/Loss (Raw)": 2.132007122039795, "Pretrain/Step": 3645, "Pretrain/Step Time": 8.769271841272712} +{"Pretrain/Learning Rate": 3.541625637497306e-05, "Pretrain/Loss": 2.06032133102417, "Pretrain/Loss (Raw)": 2.1892340183258057, "Pretrain/Step": 3646, "Pretrain/Step Time": 8.774618381634355} +{"Pretrain/Learning Rate": 3.540853791214373e-05, "Pretrain/Loss": 2.0612244606018066, "Pretrain/Loss (Raw)": 2.1088674068450928, "Pretrain/Step": 3647, "Pretrain/Step Time": 8.76938377507031} +{"Pretrain/Learning Rate": 3.5400818248952786e-05, "Pretrain/Loss": 2.05981707572937, "Pretrain/Loss (Raw)": 1.9572128057479858, "Pretrain/Step": 3648, "Pretrain/Step Time": 8.768621979281306} +{"Pretrain/Learning Rate": 3.539309738629045e-05, "Pretrain/Loss": 2.0629186630249023, "Pretrain/Loss (Raw)": 2.1877920627593994, "Pretrain/Step": 3649, "Pretrain/Step Time": 8.766429536044598} +{"Pretrain/Learning Rate": 3.5385375325047166e-05, "Pretrain/Loss": 2.0628747940063477, "Pretrain/Loss (Raw)": 2.268292188644409, "Pretrain/Step": 3650, "Pretrain/Step Time": 8.772662810981274} +{"Pretrain/Learning Rate": 3.537765206611345e-05, "Pretrain/Loss": 2.06371808052063, "Pretrain/Loss (Raw)": 2.1474533081054688, "Pretrain/Step": 3651, "Pretrain/Step Time": 8.766433987766504} +{"Pretrain/Learning Rate": 3.536992761038001e-05, "Pretrain/Loss": 2.065458059310913, "Pretrain/Loss (Raw)": 2.1925370693206787, "Pretrain/Step": 3652, "Pretrain/Step Time": 8.773854220286012} +{"Pretrain/Learning Rate": 3.536220195873764e-05, "Pretrain/Loss": 2.0654211044311523, "Pretrain/Loss (Raw)": 2.0092484951019287, "Pretrain/Step": 3653, "Pretrain/Step Time": 8.775918265804648} +{"Pretrain/Learning Rate": 3.535447511207731e-05, "Pretrain/Loss": 2.0659847259521484, "Pretrain/Loss (Raw)": 2.156284809112549, "Pretrain/Step": 3654, "Pretrain/Step Time": 8.772807735949755} +{"Pretrain/Learning Rate": 3.534674707129013e-05, "Pretrain/Loss": 2.0664424896240234, "Pretrain/Loss (Raw)": 2.1050591468811035, "Pretrain/Step": 3655, "Pretrain/Step Time": 8.771770851686597} +{"Pretrain/Learning Rate": 3.5339017837267316e-05, "Pretrain/Loss": 2.067166328430176, "Pretrain/Loss (Raw)": 2.2598118782043457, "Pretrain/Step": 3656, "Pretrain/Step Time": 8.773367432877421} +{"Pretrain/Learning Rate": 3.5331287410900246e-05, "Pretrain/Loss": 2.0662529468536377, "Pretrain/Loss (Raw)": 2.1567540168762207, "Pretrain/Step": 3657, "Pretrain/Step Time": 8.776150530204177} +{"Pretrain/Learning Rate": 3.532355579308043e-05, "Pretrain/Loss": 2.0646941661834717, "Pretrain/Loss (Raw)": 1.9812368154525757, "Pretrain/Step": 3658, "Pretrain/Step Time": 8.76751533150673} +{"Pretrain/Learning Rate": 3.531582298469952e-05, "Pretrain/Loss": 2.05985426902771, "Pretrain/Loss (Raw)": 1.7794057130813599, "Pretrain/Step": 3659, "Pretrain/Step Time": 8.764784075319767} +{"Pretrain/Learning Rate": 3.530808898664928e-05, "Pretrain/Loss": 2.0579590797424316, "Pretrain/Loss (Raw)": 2.0301003456115723, "Pretrain/Step": 3660, "Pretrain/Step Time": 8.7704345472157} +{"Pretrain/Learning Rate": 3.530035379982166e-05, "Pretrain/Loss": 2.0576791763305664, "Pretrain/Loss (Raw)": 2.209320545196533, "Pretrain/Step": 3661, "Pretrain/Step Time": 8.76767517067492} +{"Pretrain/Learning Rate": 3.5292617425108694e-05, "Pretrain/Loss": 2.0571231842041016, "Pretrain/Loss (Raw)": 2.1473309993743896, "Pretrain/Step": 3662, "Pretrain/Step Time": 8.771783592179418} +{"Pretrain/Learning Rate": 3.5284879863402585e-05, "Pretrain/Loss": 2.057361602783203, "Pretrain/Loss (Raw)": 1.998001217842102, "Pretrain/Step": 3663, "Pretrain/Step Time": 8.776630628854036} +{"Pretrain/Learning Rate": 3.527714111559567e-05, "Pretrain/Loss": 2.058157444000244, "Pretrain/Loss (Raw)": 2.091679811477661, "Pretrain/Step": 3664, "Pretrain/Step Time": 8.776895387098193} +{"Pretrain/Learning Rate": 3.526940118258041e-05, "Pretrain/Loss": 2.058103322982788, "Pretrain/Loss (Raw)": 2.127992868423462, "Pretrain/Step": 3665, "Pretrain/Step Time": 8.781046459451318} +{"Pretrain/Learning Rate": 3.526166006524942e-05, "Pretrain/Loss": 2.0573348999023438, "Pretrain/Loss (Raw)": 2.0947093963623047, "Pretrain/Step": 3666, "Pretrain/Step Time": 8.766772197559476} +{"Pretrain/Learning Rate": 3.525391776449544e-05, "Pretrain/Loss": 2.0567190647125244, "Pretrain/Loss (Raw)": 2.03572678565979, "Pretrain/Step": 3667, "Pretrain/Step Time": 8.775291815400124} +{"Pretrain/Learning Rate": 3.5246174281211344e-05, "Pretrain/Loss": 2.055424213409424, "Pretrain/Loss (Raw)": 1.9663337469100952, "Pretrain/Step": 3668, "Pretrain/Step Time": 8.774637183174491} +{"Pretrain/Learning Rate": 3.523842961629014e-05, "Pretrain/Loss": 2.0504069328308105, "Pretrain/Loss (Raw)": 2.0032567977905273, "Pretrain/Step": 3669, "Pretrain/Step Time": 8.772614676505327} +{"Pretrain/Learning Rate": 3.5230683770624987e-05, "Pretrain/Loss": 2.05216646194458, "Pretrain/Loss (Raw)": 2.195173501968384, "Pretrain/Step": 3670, "Pretrain/Step Time": 8.770635932683945} +{"Pretrain/Learning Rate": 3.522293674510918e-05, "Pretrain/Loss": 2.0528299808502197, "Pretrain/Loss (Raw)": 2.0487921237945557, "Pretrain/Step": 3671, "Pretrain/Step Time": 8.778634281829} +{"Pretrain/Learning Rate": 3.5215188540636134e-05, "Pretrain/Loss": 2.054291248321533, "Pretrain/Loss (Raw)": 2.2496085166931152, "Pretrain/Step": 3672, "Pretrain/Step Time": 8.773876756429672} +{"Pretrain/Learning Rate": 3.520743915809941e-05, "Pretrain/Loss": 2.0555198192596436, "Pretrain/Loss (Raw)": 2.2596793174743652, "Pretrain/Step": 3673, "Pretrain/Step Time": 8.773608503863215} +{"Pretrain/Learning Rate": 3.51996885983927e-05, "Pretrain/Loss": 2.0566883087158203, "Pretrain/Loss (Raw)": 2.0019795894622803, "Pretrain/Step": 3674, "Pretrain/Step Time": 8.77851628139615} +{"Pretrain/Learning Rate": 3.519193686240984e-05, "Pretrain/Loss": 2.056433916091919, "Pretrain/Loss (Raw)": 1.9410768747329712, "Pretrain/Step": 3675, "Pretrain/Step Time": 8.777328809723258} +{"Pretrain/Learning Rate": 3.51841839510448e-05, "Pretrain/Loss": 2.0556557178497314, "Pretrain/Loss (Raw)": 1.9934643507003784, "Pretrain/Step": 3676, "Pretrain/Step Time": 8.774295821785927} +{"Pretrain/Learning Rate": 3.517642986519167e-05, "Pretrain/Loss": 2.053882122039795, "Pretrain/Loss (Raw)": 1.8658784627914429, "Pretrain/Step": 3677, "Pretrain/Step Time": 8.776873353868723} +{"Pretrain/Learning Rate": 3.51686746057447e-05, "Pretrain/Loss": 2.053316593170166, "Pretrain/Loss (Raw)": 1.948266625404358, "Pretrain/Step": 3678, "Pretrain/Step Time": 8.774554749950767} +{"Pretrain/Learning Rate": 3.516091817359825e-05, "Pretrain/Loss": 2.0530552864074707, "Pretrain/Loss (Raw)": 1.96815824508667, "Pretrain/Step": 3679, "Pretrain/Step Time": 8.779635993763804} +{"Pretrain/Learning Rate": 3.515316056964684e-05, "Pretrain/Loss": 2.052351474761963, "Pretrain/Loss (Raw)": 2.0185413360595703, "Pretrain/Step": 3680, "Pretrain/Step Time": 8.776392946019769} +{"Pretrain/Learning Rate": 3.5145401794785116e-05, "Pretrain/Loss": 2.055044174194336, "Pretrain/Loss (Raw)": 2.0434229373931885, "Pretrain/Step": 3681, "Pretrain/Step Time": 8.780504610389471} +{"Pretrain/Learning Rate": 3.5137641849907844e-05, "Pretrain/Loss": 2.055931568145752, "Pretrain/Loss (Raw)": 2.1600286960601807, "Pretrain/Step": 3682, "Pretrain/Step Time": 8.777385419234633} +{"Pretrain/Learning Rate": 3.5129880735909945e-05, "Pretrain/Loss": 2.0598602294921875, "Pretrain/Loss (Raw)": 2.029844045639038, "Pretrain/Step": 3683, "Pretrain/Step Time": 8.776059655472636} +{"Pretrain/Learning Rate": 3.512211845368647e-05, "Pretrain/Loss": 2.060237407684326, "Pretrain/Loss (Raw)": 2.0891947746276855, "Pretrain/Step": 3684, "Pretrain/Step Time": 8.775361912325025} +{"Pretrain/Learning Rate": 3.511435500413259e-05, "Pretrain/Loss": 2.059943437576294, "Pretrain/Loss (Raw)": 1.9991259574890137, "Pretrain/Step": 3685, "Pretrain/Step Time": 8.782822767272592} +{"Pretrain/Learning Rate": 3.510659038814364e-05, "Pretrain/Loss": 2.0606956481933594, "Pretrain/Loss (Raw)": 2.094003677368164, "Pretrain/Step": 3686, "Pretrain/Step Time": 8.786429764702916} +{"Pretrain/Learning Rate": 3.509882460661506e-05, "Pretrain/Loss": 2.059630870819092, "Pretrain/Loss (Raw)": 2.014742136001587, "Pretrain/Step": 3687, "Pretrain/Step Time": 8.773911986500025} +{"Pretrain/Learning Rate": 3.5091057660442434e-05, "Pretrain/Loss": 2.058711051940918, "Pretrain/Loss (Raw)": 1.9671311378479004, "Pretrain/Step": 3688, "Pretrain/Step Time": 8.782236749306321} +{"Pretrain/Learning Rate": 3.5083289550521495e-05, "Pretrain/Loss": 2.0589072704315186, "Pretrain/Loss (Raw)": 2.199389934539795, "Pretrain/Step": 3689, "Pretrain/Step Time": 8.780448742210865} +{"Pretrain/Learning Rate": 3.507552027774809e-05, "Pretrain/Loss": 2.059598445892334, "Pretrain/Loss (Raw)": 2.013958215713501, "Pretrain/Step": 3690, "Pretrain/Step Time": 8.778845593333244} +{"Pretrain/Learning Rate": 3.5067749843018205e-05, "Pretrain/Loss": 2.05911922454834, "Pretrain/Loss (Raw)": 2.0794410705566406, "Pretrain/Step": 3691, "Pretrain/Step Time": 8.78652417846024} +{"Pretrain/Learning Rate": 3.5059978247227965e-05, "Pretrain/Loss": 2.05843448638916, "Pretrain/Loss (Raw)": 2.1558759212493896, "Pretrain/Step": 3692, "Pretrain/Step Time": 8.782744629308581} +{"Pretrain/Learning Rate": 3.505220549127364e-05, "Pretrain/Loss": 2.0584728717803955, "Pretrain/Loss (Raw)": 2.1164350509643555, "Pretrain/Step": 3693, "Pretrain/Step Time": 8.778394293040037} +{"Pretrain/Learning Rate": 3.50444315760516e-05, "Pretrain/Loss": 2.058126926422119, "Pretrain/Loss (Raw)": 2.090054750442505, "Pretrain/Step": 3694, "Pretrain/Step Time": 8.783159160986543} +{"Pretrain/Learning Rate": 3.503665650245838e-05, "Pretrain/Loss": 2.057791233062744, "Pretrain/Loss (Raw)": 2.0376598834991455, "Pretrain/Step": 3695, "Pretrain/Step Time": 8.782071022316813} +{"Pretrain/Learning Rate": 3.502888027139065e-05, "Pretrain/Loss": 2.0589425563812256, "Pretrain/Loss (Raw)": 2.1519813537597656, "Pretrain/Step": 3696, "Pretrain/Step Time": 8.783549789339304} +{"Pretrain/Learning Rate": 3.502110288374517e-05, "Pretrain/Loss": 2.0601701736450195, "Pretrain/Loss (Raw)": 2.146080493927002, "Pretrain/Step": 3697, "Pretrain/Step Time": 8.77698514238} +{"Pretrain/Learning Rate": 3.50133243404189e-05, "Pretrain/Loss": 2.0615153312683105, "Pretrain/Loss (Raw)": 2.0539438724517822, "Pretrain/Step": 3698, "Pretrain/Step Time": 8.779365867376328} +{"Pretrain/Learning Rate": 3.5005544642308874e-05, "Pretrain/Loss": 2.0613579750061035, "Pretrain/Loss (Raw)": 1.9748420715332031, "Pretrain/Step": 3699, "Pretrain/Step Time": 8.782296970486641} +{"Pretrain/Learning Rate": 3.49977637903123e-05, "Pretrain/Loss": 2.0610604286193848, "Pretrain/Loss (Raw)": 2.0344836711883545, "Pretrain/Step": 3700, "Pretrain/Step Time": 8.775999676436186} +{"Pretrain/Learning Rate": 3.4989981785326485e-05, "Pretrain/Loss": 2.060621738433838, "Pretrain/Loss (Raw)": 1.9955533742904663, "Pretrain/Step": 3701, "Pretrain/Step Time": 8.77982298657298} +{"Pretrain/Learning Rate": 3.498219862824891e-05, "Pretrain/Loss": 2.0625128746032715, "Pretrain/Loss (Raw)": 2.127546787261963, "Pretrain/Step": 3702, "Pretrain/Step Time": 8.77703383937478} +{"Pretrain/Learning Rate": 3.497441431997714e-05, "Pretrain/Loss": 2.0624008178710938, "Pretrain/Loss (Raw)": 2.1134700775146484, "Pretrain/Step": 3703, "Pretrain/Step Time": 8.776944192126393} +{"Pretrain/Learning Rate": 3.4966628861408914e-05, "Pretrain/Loss": 2.062497854232788, "Pretrain/Loss (Raw)": 2.095524311065674, "Pretrain/Step": 3704, "Pretrain/Step Time": 8.780870018526912} +{"Pretrain/Learning Rate": 3.495884225344208e-05, "Pretrain/Loss": 2.062502384185791, "Pretrain/Loss (Raw)": 2.0491387844085693, "Pretrain/Step": 3705, "Pretrain/Step Time": 8.780617071315646} +{"Pretrain/Learning Rate": 3.495105449697463e-05, "Pretrain/Loss": 2.061385154724121, "Pretrain/Loss (Raw)": 1.825891375541687, "Pretrain/Step": 3706, "Pretrain/Step Time": 8.787621412426233} +{"Pretrain/Learning Rate": 3.494326559290469e-05, "Pretrain/Loss": 2.0618441104888916, "Pretrain/Loss (Raw)": 2.0042366981506348, "Pretrain/Step": 3707, "Pretrain/Step Time": 8.777173902839422} +{"Pretrain/Learning Rate": 3.4935475542130505e-05, "Pretrain/Loss": 2.0620148181915283, "Pretrain/Loss (Raw)": 2.053800344467163, "Pretrain/Step": 3708, "Pretrain/Step Time": 8.773598274216056} +{"Pretrain/Learning Rate": 3.492768434555046e-05, "Pretrain/Loss": 2.0622146129608154, "Pretrain/Loss (Raw)": 1.9673881530761719, "Pretrain/Step": 3709, "Pretrain/Step Time": 8.770412208512425} +{"Pretrain/Learning Rate": 3.4919892004063084e-05, "Pretrain/Loss": 2.0641965866088867, "Pretrain/Loss (Raw)": 2.1385152339935303, "Pretrain/Step": 3710, "Pretrain/Step Time": 8.767869522795081} +{"Pretrain/Learning Rate": 3.491209851856701e-05, "Pretrain/Loss": 2.0637640953063965, "Pretrain/Loss (Raw)": 2.0426650047302246, "Pretrain/Step": 3711, "Pretrain/Step Time": 8.771997770294547} +{"Pretrain/Learning Rate": 3.490430388996103e-05, "Pretrain/Loss": 2.06365966796875, "Pretrain/Loss (Raw)": 2.109588384628296, "Pretrain/Step": 3712, "Pretrain/Step Time": 8.774130867794156} +{"Pretrain/Learning Rate": 3.4896508119144056e-05, "Pretrain/Loss": 2.0635008811950684, "Pretrain/Loss (Raw)": 2.1605613231658936, "Pretrain/Step": 3713, "Pretrain/Step Time": 8.77450137771666} +{"Pretrain/Learning Rate": 3.4888711207015124e-05, "Pretrain/Loss": 2.063530445098877, "Pretrain/Loss (Raw)": 2.124563694000244, "Pretrain/Step": 3714, "Pretrain/Step Time": 8.76989377848804} +{"Pretrain/Learning Rate": 3.488091315447343e-05, "Pretrain/Loss": 2.063805341720581, "Pretrain/Loss (Raw)": 2.052854061126709, "Pretrain/Step": 3715, "Pretrain/Step Time": 8.773112934082747} +{"Pretrain/Learning Rate": 3.487311396241826e-05, "Pretrain/Loss": 2.065281629562378, "Pretrain/Loss (Raw)": 2.114798069000244, "Pretrain/Step": 3716, "Pretrain/Step Time": 8.773451602086425} +{"Pretrain/Learning Rate": 3.486531363174908e-05, "Pretrain/Loss": 2.065990447998047, "Pretrain/Loss (Raw)": 2.0491671562194824, "Pretrain/Step": 3717, "Pretrain/Step Time": 8.771241491660476} +{"Pretrain/Learning Rate": 3.4857512163365424e-05, "Pretrain/Loss": 2.0638017654418945, "Pretrain/Loss (Raw)": 1.844704270362854, "Pretrain/Step": 3718, "Pretrain/Step Time": 8.779568407684565} +{"Pretrain/Learning Rate": 3.484970955816703e-05, "Pretrain/Loss": 2.0613832473754883, "Pretrain/Loss (Raw)": 1.8974741697311401, "Pretrain/Step": 3719, "Pretrain/Step Time": 8.778377991169691} +{"Pretrain/Learning Rate": 3.484190581705371e-05, "Pretrain/Loss": 2.0594751834869385, "Pretrain/Loss (Raw)": 1.8418703079223633, "Pretrain/Step": 3720, "Pretrain/Step Time": 8.777990620583296} +{"Pretrain/Learning Rate": 3.483410094092543e-05, "Pretrain/Loss": 2.0582218170166016, "Pretrain/Loss (Raw)": 1.8614507913589478, "Pretrain/Step": 3721, "Pretrain/Step Time": 8.77039885520935} +{"Pretrain/Learning Rate": 3.48262949306823e-05, "Pretrain/Loss": 2.0576796531677246, "Pretrain/Loss (Raw)": 2.090576171875, "Pretrain/Step": 3722, "Pretrain/Step Time": 8.77190306223929} +{"Pretrain/Learning Rate": 3.481848778722453e-05, "Pretrain/Loss": 2.056628704071045, "Pretrain/Loss (Raw)": 2.024228572845459, "Pretrain/Step": 3723, "Pretrain/Step Time": 8.77302111312747} +{"Pretrain/Learning Rate": 3.4810679511452484e-05, "Pretrain/Loss": 2.058053731918335, "Pretrain/Loss (Raw)": 2.2222321033477783, "Pretrain/Step": 3724, "Pretrain/Step Time": 8.771850941702724} +{"Pretrain/Learning Rate": 3.480287010426664e-05, "Pretrain/Loss": 2.057162046432495, "Pretrain/Loss (Raw)": 1.883311152458191, "Pretrain/Step": 3725, "Pretrain/Step Time": 8.768513275310397} +{"Pretrain/Learning Rate": 3.479505956656764e-05, "Pretrain/Loss": 2.059389114379883, "Pretrain/Loss (Raw)": 2.202958583831787, "Pretrain/Step": 3726, "Pretrain/Step Time": 8.77604078501463} +{"Pretrain/Learning Rate": 3.47872478992562e-05, "Pretrain/Loss": 2.0593504905700684, "Pretrain/Loss (Raw)": 2.0735878944396973, "Pretrain/Step": 3727, "Pretrain/Step Time": 8.774991629645228} +{"Pretrain/Learning Rate": 3.477943510323322e-05, "Pretrain/Loss": 2.059499740600586, "Pretrain/Loss (Raw)": 2.033653736114502, "Pretrain/Step": 3728, "Pretrain/Step Time": 8.77799616381526} +{"Pretrain/Learning Rate": 3.4771621179399696e-05, "Pretrain/Loss": 2.0587799549102783, "Pretrain/Loss (Raw)": 2.0227789878845215, "Pretrain/Step": 3729, "Pretrain/Step Time": 8.770202649757266} +{"Pretrain/Learning Rate": 3.476380612865679e-05, "Pretrain/Loss": 2.0598082542419434, "Pretrain/Loss (Raw)": 2.1432647705078125, "Pretrain/Step": 3730, "Pretrain/Step Time": 8.778510097414255} +{"Pretrain/Learning Rate": 3.475598995190572e-05, "Pretrain/Loss": 2.0585451126098633, "Pretrain/Loss (Raw)": 1.927509069442749, "Pretrain/Step": 3731, "Pretrain/Step Time": 8.774241337552667} +{"Pretrain/Learning Rate": 3.4748172650047945e-05, "Pretrain/Loss": 2.057126045227051, "Pretrain/Loss (Raw)": 1.853173851966858, "Pretrain/Step": 3732, "Pretrain/Step Time": 8.774481780827045} +{"Pretrain/Learning Rate": 3.474035422398496e-05, "Pretrain/Loss": 2.057150363922119, "Pretrain/Loss (Raw)": 2.200895309448242, "Pretrain/Step": 3733, "Pretrain/Step Time": 8.784784825518727} +{"Pretrain/Learning Rate": 3.473253467461842e-05, "Pretrain/Loss": 2.0563712120056152, "Pretrain/Loss (Raw)": 2.0340425968170166, "Pretrain/Step": 3734, "Pretrain/Step Time": 8.78538078814745} +{"Pretrain/Learning Rate": 3.4724714002850125e-05, "Pretrain/Loss": 2.0556955337524414, "Pretrain/Loss (Raw)": 2.1044914722442627, "Pretrain/Step": 3735, "Pretrain/Step Time": 8.781768713146448} +{"Pretrain/Learning Rate": 3.471689220958198e-05, "Pretrain/Loss": 2.053112745285034, "Pretrain/Loss (Raw)": 2.023437738418579, "Pretrain/Step": 3736, "Pretrain/Step Time": 8.781957536935806} +{"Pretrain/Learning Rate": 3.470906929571605e-05, "Pretrain/Loss": 2.054356098175049, "Pretrain/Loss (Raw)": 2.0744237899780273, "Pretrain/Step": 3737, "Pretrain/Step Time": 8.7799954097718} +{"Pretrain/Learning Rate": 3.470124526215449e-05, "Pretrain/Loss": 2.055490493774414, "Pretrain/Loss (Raw)": 2.137187957763672, "Pretrain/Step": 3738, "Pretrain/Step Time": 8.779955077916384} +{"Pretrain/Learning Rate": 3.469342010979962e-05, "Pretrain/Loss": 2.0549232959747314, "Pretrain/Loss (Raw)": 2.066943645477295, "Pretrain/Step": 3739, "Pretrain/Step Time": 8.774093134328723} +{"Pretrain/Learning Rate": 3.4685593839553856e-05, "Pretrain/Loss": 2.056041717529297, "Pretrain/Loss (Raw)": 2.0380992889404297, "Pretrain/Step": 3740, "Pretrain/Step Time": 8.781537832692266} +{"Pretrain/Learning Rate": 3.467776645231978e-05, "Pretrain/Loss": 2.0576930046081543, "Pretrain/Loss (Raw)": 2.121014356613159, "Pretrain/Step": 3741, "Pretrain/Step Time": 8.778523467481136} +{"Pretrain/Learning Rate": 3.466993794900007e-05, "Pretrain/Loss": 2.0547056198120117, "Pretrain/Loss (Raw)": 1.7881096601486206, "Pretrain/Step": 3742, "Pretrain/Step Time": 8.778648605570197} +{"Pretrain/Learning Rate": 3.466210833049755e-05, "Pretrain/Loss": 2.053907871246338, "Pretrain/Loss (Raw)": 1.8972793817520142, "Pretrain/Step": 3743, "Pretrain/Step Time": 8.779403802007437} +{"Pretrain/Learning Rate": 3.465427759771516e-05, "Pretrain/Loss": 2.055152416229248, "Pretrain/Loss (Raw)": 2.0923736095428467, "Pretrain/Step": 3744, "Pretrain/Step Time": 8.780506644397974} +{"Pretrain/Learning Rate": 3.464644575155599e-05, "Pretrain/Loss": 2.0549302101135254, "Pretrain/Loss (Raw)": 2.144927978515625, "Pretrain/Step": 3745, "Pretrain/Step Time": 8.782866232097149} +{"Pretrain/Learning Rate": 3.463861279292324e-05, "Pretrain/Loss": 2.054982900619507, "Pretrain/Loss (Raw)": 1.9866338968276978, "Pretrain/Step": 3746, "Pretrain/Step Time": 8.783070968464017} +{"Pretrain/Learning Rate": 3.4630778722720244e-05, "Pretrain/Loss": 2.053967237472534, "Pretrain/Loss (Raw)": 1.9572440385818481, "Pretrain/Step": 3747, "Pretrain/Step Time": 8.784859104081988} +{"Pretrain/Learning Rate": 3.462294354185046e-05, "Pretrain/Loss": 2.055581569671631, "Pretrain/Loss (Raw)": 2.0792956352233887, "Pretrain/Step": 3748, "Pretrain/Step Time": 8.79286320693791} +{"Pretrain/Learning Rate": 3.4615107251217496e-05, "Pretrain/Loss": 2.053884744644165, "Pretrain/Loss (Raw)": 1.9466667175292969, "Pretrain/Step": 3749, "Pretrain/Step Time": 8.790954297408462} +{"Pretrain/Learning Rate": 3.460726985172504e-05, "Pretrain/Loss": 2.055318832397461, "Pretrain/Loss (Raw)": 2.106414556503296, "Pretrain/Step": 3750, "Pretrain/Step Time": 8.792890068143606} +{"Pretrain/Learning Rate": 3.4599431344276966e-05, "Pretrain/Loss": 2.055128574371338, "Pretrain/Loss (Raw)": 2.0896382331848145, "Pretrain/Step": 3751, "Pretrain/Step Time": 8.791647242382169} +{"Pretrain/Learning Rate": 3.459159172977723e-05, "Pretrain/Loss": 2.0546581745147705, "Pretrain/Loss (Raw)": 1.7779501676559448, "Pretrain/Step": 3752, "Pretrain/Step Time": 8.792392957955599} +{"Pretrain/Learning Rate": 3.4583751009129936e-05, "Pretrain/Loss": 2.053727388381958, "Pretrain/Loss (Raw)": 1.951067328453064, "Pretrain/Step": 3753, "Pretrain/Step Time": 8.789618948474526} +{"Pretrain/Learning Rate": 3.457590918323932e-05, "Pretrain/Loss": 2.054629325866699, "Pretrain/Loss (Raw)": 2.1500391960144043, "Pretrain/Step": 3754, "Pretrain/Step Time": 8.790775150060654} +{"Pretrain/Learning Rate": 3.4568066253009736e-05, "Pretrain/Loss": 2.0561399459838867, "Pretrain/Loss (Raw)": 2.1298983097076416, "Pretrain/Step": 3755, "Pretrain/Step Time": 8.804199237376451} +{"Pretrain/Learning Rate": 3.456022221934566e-05, "Pretrain/Loss": 2.055631399154663, "Pretrain/Loss (Raw)": 2.0807480812072754, "Pretrain/Step": 3756, "Pretrain/Step Time": 8.799838056787848} +{"Pretrain/Learning Rate": 3.455237708315171e-05, "Pretrain/Loss": 2.0543997287750244, "Pretrain/Loss (Raw)": 2.0511863231658936, "Pretrain/Step": 3757, "Pretrain/Step Time": 8.79235377162695} +{"Pretrain/Learning Rate": 3.454453084533262e-05, "Pretrain/Loss": 2.0581624507904053, "Pretrain/Loss (Raw)": 2.164752960205078, "Pretrain/Step": 3758, "Pretrain/Step Time": 8.793106539174914} +{"Pretrain/Learning Rate": 3.453668350679327e-05, "Pretrain/Loss": 2.0568196773529053, "Pretrain/Loss (Raw)": 2.0100600719451904, "Pretrain/Step": 3759, "Pretrain/Step Time": 8.791529031470418} +{"Pretrain/Learning Rate": 3.4528835068438625e-05, "Pretrain/Loss": 2.05747389793396, "Pretrain/Loss (Raw)": 2.033756732940674, "Pretrain/Step": 3760, "Pretrain/Step Time": 8.790670549497008} +{"Pretrain/Learning Rate": 3.452098553117382e-05, "Pretrain/Loss": 2.0577492713928223, "Pretrain/Loss (Raw)": 1.8694642782211304, "Pretrain/Step": 3761, "Pretrain/Step Time": 8.79453899152577} +{"Pretrain/Learning Rate": 3.4513134895904105e-05, "Pretrain/Loss": 2.0586910247802734, "Pretrain/Loss (Raw)": 2.1982316970825195, "Pretrain/Step": 3762, "Pretrain/Step Time": 8.797111729159951} +{"Pretrain/Learning Rate": 3.450528316353484e-05, "Pretrain/Loss": 2.0575923919677734, "Pretrain/Loss (Raw)": 1.909055233001709, "Pretrain/Step": 3763, "Pretrain/Step Time": 8.797391893342137} +{"Pretrain/Learning Rate": 3.4497430334971534e-05, "Pretrain/Loss": 2.057976722717285, "Pretrain/Loss (Raw)": 2.050457715988159, "Pretrain/Step": 3764, "Pretrain/Step Time": 8.79224244877696} +{"Pretrain/Learning Rate": 3.448957641111981e-05, "Pretrain/Loss": 2.057654857635498, "Pretrain/Loss (Raw)": 1.9685769081115723, "Pretrain/Step": 3765, "Pretrain/Step Time": 8.793537074699998} +{"Pretrain/Learning Rate": 3.4481721392885414e-05, "Pretrain/Loss": 2.056962013244629, "Pretrain/Loss (Raw)": 1.989610195159912, "Pretrain/Step": 3766, "Pretrain/Step Time": 8.797490464523435} +{"Pretrain/Learning Rate": 3.447386528117423e-05, "Pretrain/Loss": 2.056166887283325, "Pretrain/Loss (Raw)": 2.1541554927825928, "Pretrain/Step": 3767, "Pretrain/Step Time": 8.796486441046} +{"Pretrain/Learning Rate": 3.446600807689226e-05, "Pretrain/Loss": 2.056168794631958, "Pretrain/Loss (Raw)": 2.060206651687622, "Pretrain/Step": 3768, "Pretrain/Step Time": 8.793462168425322} +{"Pretrain/Learning Rate": 3.4458149780945636e-05, "Pretrain/Loss": 2.0553767681121826, "Pretrain/Loss (Raw)": 2.0392348766326904, "Pretrain/Step": 3769, "Pretrain/Step Time": 8.807762132957578} +{"Pretrain/Learning Rate": 3.4450290394240606e-05, "Pretrain/Loss": 2.0567615032196045, "Pretrain/Loss (Raw)": 2.2696733474731445, "Pretrain/Step": 3770, "Pretrain/Step Time": 8.800855932757258} +{"Pretrain/Learning Rate": 3.444242991768356e-05, "Pretrain/Loss": 2.0572524070739746, "Pretrain/Loss (Raw)": 2.133824586868286, "Pretrain/Step": 3771, "Pretrain/Step Time": 8.793035300448537} +{"Pretrain/Learning Rate": 3.4434568352181e-05, "Pretrain/Loss": 2.0566446781158447, "Pretrain/Loss (Raw)": 2.1435060501098633, "Pretrain/Step": 3772, "Pretrain/Step Time": 8.796287240460515} +{"Pretrain/Learning Rate": 3.442670569863956e-05, "Pretrain/Loss": 2.055164337158203, "Pretrain/Loss (Raw)": 1.9425081014633179, "Pretrain/Step": 3773, "Pretrain/Step Time": 8.7943677008152} +{"Pretrain/Learning Rate": 3.4418841957965995e-05, "Pretrain/Loss": 2.053630828857422, "Pretrain/Loss (Raw)": 1.9929499626159668, "Pretrain/Step": 3774, "Pretrain/Step Time": 8.793879482895136} +{"Pretrain/Learning Rate": 3.44109771310672e-05, "Pretrain/Loss": 2.0523293018341064, "Pretrain/Loss (Raw)": 1.942280888557434, "Pretrain/Step": 3775, "Pretrain/Step Time": 8.793427551165223} +{"Pretrain/Learning Rate": 3.440311121885018e-05, "Pretrain/Loss": 2.053074359893799, "Pretrain/Loss (Raw)": 2.052572011947632, "Pretrain/Step": 3776, "Pretrain/Step Time": 8.802261013537645} +{"Pretrain/Learning Rate": 3.4395244222222054e-05, "Pretrain/Loss": 2.051846981048584, "Pretrain/Loss (Raw)": 2.0307106971740723, "Pretrain/Step": 3777, "Pretrain/Step Time": 8.805836092680693} +{"Pretrain/Learning Rate": 3.43873761420901e-05, "Pretrain/Loss": 2.052142858505249, "Pretrain/Loss (Raw)": 2.306135654449463, "Pretrain/Step": 3778, "Pretrain/Step Time": 8.799738597124815} +{"Pretrain/Learning Rate": 3.4379506979361694e-05, "Pretrain/Loss": 2.0523219108581543, "Pretrain/Loss (Raw)": 2.170367479324341, "Pretrain/Step": 3779, "Pretrain/Step Time": 8.800216043367982} +{"Pretrain/Learning Rate": 3.437163673494434e-05, "Pretrain/Loss": 2.0504393577575684, "Pretrain/Loss (Raw)": 1.9515990018844604, "Pretrain/Step": 3780, "Pretrain/Step Time": 8.802612511441112} +{"Pretrain/Learning Rate": 3.436376540974568e-05, "Pretrain/Loss": 2.050912380218506, "Pretrain/Loss (Raw)": 2.0697739124298096, "Pretrain/Step": 3781, "Pretrain/Step Time": 8.800428543239832} +{"Pretrain/Learning Rate": 3.4355893004673476e-05, "Pretrain/Loss": 2.050154209136963, "Pretrain/Loss (Raw)": 2.059243679046631, "Pretrain/Step": 3782, "Pretrain/Step Time": 8.805229909718037} +{"Pretrain/Learning Rate": 3.4348019520635587e-05, "Pretrain/Loss": 2.0488715171813965, "Pretrain/Loss (Raw)": 1.94087815284729, "Pretrain/Step": 3783, "Pretrain/Step Time": 8.811702186241746} +{"Pretrain/Learning Rate": 3.434014495854006e-05, "Pretrain/Loss": 2.0479321479797363, "Pretrain/Loss (Raw)": 2.139563798904419, "Pretrain/Step": 3784, "Pretrain/Step Time": 8.82020490244031} +{"Pretrain/Learning Rate": 3.4332269319294984e-05, "Pretrain/Loss": 2.048429489135742, "Pretrain/Loss (Raw)": 2.2204079627990723, "Pretrain/Step": 3785, "Pretrain/Step Time": 8.812332233414054} +{"Pretrain/Learning Rate": 3.432439260380865e-05, "Pretrain/Loss": 2.0477676391601562, "Pretrain/Loss (Raw)": 1.8965409994125366, "Pretrain/Step": 3786, "Pretrain/Step Time": 8.809735601767898} +{"Pretrain/Learning Rate": 3.4316514812989406e-05, "Pretrain/Loss": 2.048954486846924, "Pretrain/Loss (Raw)": 1.9312981367111206, "Pretrain/Step": 3787, "Pretrain/Step Time": 8.812667036429048} +{"Pretrain/Learning Rate": 3.4308635947745796e-05, "Pretrain/Loss": 2.049454927444458, "Pretrain/Loss (Raw)": 2.0941855907440186, "Pretrain/Step": 3788, "Pretrain/Step Time": 8.806602215394378} +{"Pretrain/Learning Rate": 3.43007560089864e-05, "Pretrain/Loss": 2.0485739707946777, "Pretrain/Loss (Raw)": 2.096531867980957, "Pretrain/Step": 3789, "Pretrain/Step Time": 8.819336304441094} +{"Pretrain/Learning Rate": 3.429287499762001e-05, "Pretrain/Loss": 2.0490012168884277, "Pretrain/Loss (Raw)": 2.2020111083984375, "Pretrain/Step": 3790, "Pretrain/Step Time": 8.822997599840164} +{"Pretrain/Learning Rate": 3.428499291455548e-05, "Pretrain/Loss": 2.049994707107544, "Pretrain/Loss (Raw)": 2.1252059936523438, "Pretrain/Step": 3791, "Pretrain/Step Time": 8.816785221919417} +{"Pretrain/Learning Rate": 3.427710976070182e-05, "Pretrain/Loss": 2.050767421722412, "Pretrain/Loss (Raw)": 2.1905741691589355, "Pretrain/Step": 3792, "Pretrain/Step Time": 8.814971063286066} +{"Pretrain/Learning Rate": 3.426922553696814e-05, "Pretrain/Loss": 2.0500950813293457, "Pretrain/Loss (Raw)": 2.041929244995117, "Pretrain/Step": 3793, "Pretrain/Step Time": 8.811900924891233} +{"Pretrain/Learning Rate": 3.426134024426371e-05, "Pretrain/Loss": 2.049912452697754, "Pretrain/Loss (Raw)": 2.071319580078125, "Pretrain/Step": 3794, "Pretrain/Step Time": 8.812628293409944} +{"Pretrain/Learning Rate": 3.425345388349786e-05, "Pretrain/Loss": 2.049826145172119, "Pretrain/Loss (Raw)": 2.024667739868164, "Pretrain/Step": 3795, "Pretrain/Step Time": 8.805923737585545} +{"Pretrain/Learning Rate": 3.4245566455580116e-05, "Pretrain/Loss": 2.050443649291992, "Pretrain/Loss (Raw)": 2.045395612716675, "Pretrain/Step": 3796, "Pretrain/Step Time": 8.807816622778773} +{"Pretrain/Learning Rate": 3.423767796142008e-05, "Pretrain/Loss": 2.051102638244629, "Pretrain/Loss (Raw)": 2.0875895023345947, "Pretrain/Step": 3797, "Pretrain/Step Time": 8.813018212094903} +{"Pretrain/Learning Rate": 3.422978840192749e-05, "Pretrain/Loss": 2.050096035003662, "Pretrain/Loss (Raw)": 2.0663702487945557, "Pretrain/Step": 3798, "Pretrain/Step Time": 8.812207754701376} +{"Pretrain/Learning Rate": 3.4221897778012214e-05, "Pretrain/Loss": 2.049736976623535, "Pretrain/Loss (Raw)": 2.0028295516967773, "Pretrain/Step": 3799, "Pretrain/Step Time": 8.80928055010736} +{"Pretrain/Learning Rate": 3.421400609058423e-05, "Pretrain/Loss": 2.0481157302856445, "Pretrain/Loss (Raw)": 2.0420727729797363, "Pretrain/Step": 3800, "Pretrain/Step Time": 8.808571606874466} +{"Pretrain/Learning Rate": 3.420611334055365e-05, "Pretrain/Loss": 2.0472867488861084, "Pretrain/Loss (Raw)": 2.1535685062408447, "Pretrain/Step": 3801, "Pretrain/Step Time": 8.810182774439454} +{"Pretrain/Learning Rate": 3.4198219528830675e-05, "Pretrain/Loss": 2.0489325523376465, "Pretrain/Loss (Raw)": 2.2126431465148926, "Pretrain/Step": 3802, "Pretrain/Step Time": 8.7992510125041} +{"Pretrain/Learning Rate": 3.4190324656325704e-05, "Pretrain/Loss": 2.0512030124664307, "Pretrain/Loss (Raw)": 2.2316980361938477, "Pretrain/Step": 3803, "Pretrain/Step Time": 8.797499034553766} +{"Pretrain/Learning Rate": 3.418242872394919e-05, "Pretrain/Loss": 2.050673723220825, "Pretrain/Loss (Raw)": 1.9257258176803589, "Pretrain/Step": 3804, "Pretrain/Step Time": 8.802184836938977} +{"Pretrain/Learning Rate": 3.417453173261171e-05, "Pretrain/Loss": 2.0519819259643555, "Pretrain/Loss (Raw)": 2.0333290100097656, "Pretrain/Step": 3805, "Pretrain/Step Time": 8.79983041062951} +{"Pretrain/Learning Rate": 3.4166633683224015e-05, "Pretrain/Loss": 2.053173065185547, "Pretrain/Loss (Raw)": 2.1007301807403564, "Pretrain/Step": 3806, "Pretrain/Step Time": 8.799007629975677} +{"Pretrain/Learning Rate": 3.4158734576696915e-05, "Pretrain/Loss": 2.0550055503845215, "Pretrain/Loss (Raw)": 2.2026875019073486, "Pretrain/Step": 3807, "Pretrain/Step Time": 8.794802794232965} +{"Pretrain/Learning Rate": 3.4150834413941394e-05, "Pretrain/Loss": 2.055510997772217, "Pretrain/Loss (Raw)": 2.083235025405884, "Pretrain/Step": 3808, "Pretrain/Step Time": 8.795464213937521} +{"Pretrain/Learning Rate": 3.414293319586853e-05, "Pretrain/Loss": 2.0567455291748047, "Pretrain/Loss (Raw)": 2.201446056365967, "Pretrain/Step": 3809, "Pretrain/Step Time": 8.794305257499218} +{"Pretrain/Learning Rate": 3.4135030923389525e-05, "Pretrain/Loss": 2.0561039447784424, "Pretrain/Loss (Raw)": 2.0779294967651367, "Pretrain/Step": 3810, "Pretrain/Step Time": 8.796172335743904} +{"Pretrain/Learning Rate": 3.412712759741571e-05, "Pretrain/Loss": 2.056164503097534, "Pretrain/Loss (Raw)": 2.037578821182251, "Pretrain/Step": 3811, "Pretrain/Step Time": 8.801050454378128} +{"Pretrain/Learning Rate": 3.411922321885853e-05, "Pretrain/Loss": 2.0561890602111816, "Pretrain/Loss (Raw)": 2.0923540592193604, "Pretrain/Step": 3812, "Pretrain/Step Time": 8.798894861713052} +{"Pretrain/Learning Rate": 3.411131778862955e-05, "Pretrain/Loss": 2.0584232807159424, "Pretrain/Loss (Raw)": 2.285118341445923, "Pretrain/Step": 3813, "Pretrain/Step Time": 8.792570108547807} +{"Pretrain/Learning Rate": 3.4103411307640475e-05, "Pretrain/Loss": 2.05731201171875, "Pretrain/Loss (Raw)": 1.9517830610275269, "Pretrain/Step": 3814, "Pretrain/Step Time": 8.791796315461397} +{"Pretrain/Learning Rate": 3.409550377680311e-05, "Pretrain/Loss": 2.0586109161376953, "Pretrain/Loss (Raw)": 2.180967092514038, "Pretrain/Step": 3815, "Pretrain/Step Time": 8.79492580331862} +{"Pretrain/Learning Rate": 3.408759519702939e-05, "Pretrain/Loss": 2.0596184730529785, "Pretrain/Loss (Raw)": 2.096111536026001, "Pretrain/Step": 3816, "Pretrain/Step Time": 8.788027046248317} +{"Pretrain/Learning Rate": 3.407968556923137e-05, "Pretrain/Loss": 2.059760093688965, "Pretrain/Loss (Raw)": 2.217498540878296, "Pretrain/Step": 3817, "Pretrain/Step Time": 8.78760864958167} +{"Pretrain/Learning Rate": 3.407177489432123e-05, "Pretrain/Loss": 2.058523178100586, "Pretrain/Loss (Raw)": 1.8556463718414307, "Pretrain/Step": 3818, "Pretrain/Step Time": 8.79571065492928} +{"Pretrain/Learning Rate": 3.406386317321126e-05, "Pretrain/Loss": 2.0583510398864746, "Pretrain/Loss (Raw)": 2.057405948638916, "Pretrain/Step": 3819, "Pretrain/Step Time": 8.783067051321268} +{"Pretrain/Learning Rate": 3.4055950406813875e-05, "Pretrain/Loss": 2.056412935256958, "Pretrain/Loss (Raw)": 1.9077918529510498, "Pretrain/Step": 3820, "Pretrain/Step Time": 8.788482079282403} +{"Pretrain/Learning Rate": 3.404803659604162e-05, "Pretrain/Loss": 2.0574536323547363, "Pretrain/Loss (Raw)": 2.249652862548828, "Pretrain/Step": 3821, "Pretrain/Step Time": 8.789173198863864} +{"Pretrain/Learning Rate": 3.4040121741807146e-05, "Pretrain/Loss": 2.056859016418457, "Pretrain/Loss (Raw)": 2.0139670372009277, "Pretrain/Step": 3822, "Pretrain/Step Time": 8.788815945386887} +{"Pretrain/Learning Rate": 3.403220584502323e-05, "Pretrain/Loss": 2.0572738647460938, "Pretrain/Loss (Raw)": 2.0907280445098877, "Pretrain/Step": 3823, "Pretrain/Step Time": 8.787501100450754} +{"Pretrain/Learning Rate": 3.402428890660279e-05, "Pretrain/Loss": 2.0569539070129395, "Pretrain/Loss (Raw)": 2.1110076904296875, "Pretrain/Step": 3824, "Pretrain/Step Time": 8.788977412506938} +{"Pretrain/Learning Rate": 3.401637092745882e-05, "Pretrain/Loss": 2.0539355278015137, "Pretrain/Loss (Raw)": 1.7597501277923584, "Pretrain/Step": 3825, "Pretrain/Step Time": 8.789913181215525} +{"Pretrain/Learning Rate": 3.4008451908504457e-05, "Pretrain/Loss": 2.054525375366211, "Pretrain/Loss (Raw)": 2.129453182220459, "Pretrain/Step": 3826, "Pretrain/Step Time": 8.789730694144964} +{"Pretrain/Learning Rate": 3.400053185065298e-05, "Pretrain/Loss": 2.0555832386016846, "Pretrain/Loss (Raw)": 2.1102371215820312, "Pretrain/Step": 3827, "Pretrain/Step Time": 8.790381850674748} +{"Pretrain/Learning Rate": 3.399261075481776e-05, "Pretrain/Loss": 2.0561482906341553, "Pretrain/Loss (Raw)": 2.1068413257598877, "Pretrain/Step": 3828, "Pretrain/Step Time": 8.796044506132603} +{"Pretrain/Learning Rate": 3.39846886219123e-05, "Pretrain/Loss": 2.0567994117736816, "Pretrain/Loss (Raw)": 2.078861713409424, "Pretrain/Step": 3829, "Pretrain/Step Time": 8.795367123559117} +{"Pretrain/Learning Rate": 3.3976765452850194e-05, "Pretrain/Loss": 2.0568933486938477, "Pretrain/Loss (Raw)": 2.1395723819732666, "Pretrain/Step": 3830, "Pretrain/Step Time": 8.79849842004478} +{"Pretrain/Learning Rate": 3.3968841248545214e-05, "Pretrain/Loss": 2.0561704635620117, "Pretrain/Loss (Raw)": 2.0209248065948486, "Pretrain/Step": 3831, "Pretrain/Step Time": 8.797715386375785} +{"Pretrain/Learning Rate": 3.396091600991118e-05, "Pretrain/Loss": 2.0562219619750977, "Pretrain/Loss (Raw)": 2.1021440029144287, "Pretrain/Step": 3832, "Pretrain/Step Time": 8.795235618948936} +{"Pretrain/Learning Rate": 3.39529897378621e-05, "Pretrain/Loss": 2.0564441680908203, "Pretrain/Loss (Raw)": 2.0775790214538574, "Pretrain/Step": 3833, "Pretrain/Step Time": 8.793178593739867} +{"Pretrain/Learning Rate": 3.3945062433312055e-05, "Pretrain/Loss": 2.058595657348633, "Pretrain/Loss (Raw)": 2.101269483566284, "Pretrain/Step": 3834, "Pretrain/Step Time": 8.78794838488102} +{"Pretrain/Learning Rate": 3.3937134097175256e-05, "Pretrain/Loss": 2.0577282905578613, "Pretrain/Loss (Raw)": 1.8932349681854248, "Pretrain/Step": 3835, "Pretrain/Step Time": 8.789193032309413} +{"Pretrain/Learning Rate": 3.392920473036604e-05, "Pretrain/Loss": 2.057952404022217, "Pretrain/Loss (Raw)": 2.082474946975708, "Pretrain/Step": 3836, "Pretrain/Step Time": 8.79271848872304} +{"Pretrain/Learning Rate": 3.392127433379886e-05, "Pretrain/Loss": 2.05924654006958, "Pretrain/Loss (Raw)": 2.1330487728118896, "Pretrain/Step": 3837, "Pretrain/Step Time": 8.790851097553968} +{"Pretrain/Learning Rate": 3.391334290838829e-05, "Pretrain/Loss": 2.057189702987671, "Pretrain/Loss (Raw)": 1.8752330541610718, "Pretrain/Step": 3838, "Pretrain/Step Time": 8.790762627497315} +{"Pretrain/Learning Rate": 3.3905410455049e-05, "Pretrain/Loss": 2.05653715133667, "Pretrain/Loss (Raw)": 1.9591487646102905, "Pretrain/Step": 3839, "Pretrain/Step Time": 8.790569726377726} +{"Pretrain/Learning Rate": 3.389747697469583e-05, "Pretrain/Loss": 2.0556652545928955, "Pretrain/Loss (Raw)": 1.9979586601257324, "Pretrain/Step": 3840, "Pretrain/Step Time": 8.787554396316409} +{"Pretrain/Learning Rate": 3.388954246824367e-05, "Pretrain/Loss": 2.0540425777435303, "Pretrain/Loss (Raw)": 1.9528898000717163, "Pretrain/Step": 3841, "Pretrain/Step Time": 8.79224593192339} +{"Pretrain/Learning Rate": 3.3881606936607604e-05, "Pretrain/Loss": 2.0532922744750977, "Pretrain/Loss (Raw)": 2.0285375118255615, "Pretrain/Step": 3842, "Pretrain/Step Time": 8.793629502877593} +{"Pretrain/Learning Rate": 3.387367038070275e-05, "Pretrain/Loss": 2.053175687789917, "Pretrain/Loss (Raw)": 2.037890911102295, "Pretrain/Step": 3843, "Pretrain/Step Time": 8.798269383609295} +{"Pretrain/Learning Rate": 3.386573280144444e-05, "Pretrain/Loss": 2.0527937412261963, "Pretrain/Loss (Raw)": 2.0659327507019043, "Pretrain/Step": 3844, "Pretrain/Step Time": 8.798843320459127} +{"Pretrain/Learning Rate": 3.385779419974803e-05, "Pretrain/Loss": 2.0544066429138184, "Pretrain/Loss (Raw)": 2.2555923461914062, "Pretrain/Step": 3845, "Pretrain/Step Time": 8.802160903811455} +{"Pretrain/Learning Rate": 3.384985457652906e-05, "Pretrain/Loss": 2.0543060302734375, "Pretrain/Loss (Raw)": 1.8318294286727905, "Pretrain/Step": 3846, "Pretrain/Step Time": 8.795400686562061} +{"Pretrain/Learning Rate": 3.384191393270316e-05, "Pretrain/Loss": 2.055384397506714, "Pretrain/Loss (Raw)": 2.0355188846588135, "Pretrain/Step": 3847, "Pretrain/Step Time": 8.799813060089946} +{"Pretrain/Learning Rate": 3.383397226918607e-05, "Pretrain/Loss": 2.0569536685943604, "Pretrain/Loss (Raw)": 2.0427393913269043, "Pretrain/Step": 3848, "Pretrain/Step Time": 8.800177078694105} +{"Pretrain/Learning Rate": 3.382602958689369e-05, "Pretrain/Loss": 2.058259963989258, "Pretrain/Loss (Raw)": 2.028660297393799, "Pretrain/Step": 3849, "Pretrain/Step Time": 8.800886111333966} +{"Pretrain/Learning Rate": 3.381808588674197e-05, "Pretrain/Loss": 2.057096481323242, "Pretrain/Loss (Raw)": 1.9416128396987915, "Pretrain/Step": 3850, "Pretrain/Step Time": 8.801880791783333} +{"Pretrain/Learning Rate": 3.381014116964705e-05, "Pretrain/Loss": 2.057955026626587, "Pretrain/Loss (Raw)": 2.134145736694336, "Pretrain/Step": 3851, "Pretrain/Step Time": 8.798835581168532} +{"Pretrain/Learning Rate": 3.380219543652512e-05, "Pretrain/Loss": 2.057084083557129, "Pretrain/Loss (Raw)": 2.1107547283172607, "Pretrain/Step": 3852, "Pretrain/Step Time": 8.799518024548888} +{"Pretrain/Learning Rate": 3.379424868829254e-05, "Pretrain/Loss": 2.059218645095825, "Pretrain/Loss (Raw)": 2.1565327644348145, "Pretrain/Step": 3853, "Pretrain/Step Time": 8.795913640409708} +{"Pretrain/Learning Rate": 3.378630092586576e-05, "Pretrain/Loss": 2.0585358142852783, "Pretrain/Loss (Raw)": 2.1155450344085693, "Pretrain/Step": 3854, "Pretrain/Step Time": 8.783640405163169} +{"Pretrain/Learning Rate": 3.377835215016136e-05, "Pretrain/Loss": 2.0601918697357178, "Pretrain/Loss (Raw)": 2.2855682373046875, "Pretrain/Step": 3855, "Pretrain/Step Time": 8.798495220020413} +{"Pretrain/Learning Rate": 3.3770402362096024e-05, "Pretrain/Loss": 2.06088924407959, "Pretrain/Loss (Raw)": 2.122924566268921, "Pretrain/Step": 3856, "Pretrain/Step Time": 8.795546267181635} +{"Pretrain/Learning Rate": 3.3762451562586565e-05, "Pretrain/Loss": 2.060682535171509, "Pretrain/Loss (Raw)": 1.9963165521621704, "Pretrain/Step": 3857, "Pretrain/Step Time": 8.796974876895547} +{"Pretrain/Learning Rate": 3.3754499752549885e-05, "Pretrain/Loss": 2.0606589317321777, "Pretrain/Loss (Raw)": 2.1402556896209717, "Pretrain/Step": 3858, "Pretrain/Step Time": 8.794462317600846} +{"Pretrain/Learning Rate": 3.374654693290306e-05, "Pretrain/Loss": 2.0614144802093506, "Pretrain/Loss (Raw)": 2.0241963863372803, "Pretrain/Step": 3859, "Pretrain/Step Time": 8.79869837500155} +{"Pretrain/Learning Rate": 3.373859310456321e-05, "Pretrain/Loss": 2.06269907951355, "Pretrain/Loss (Raw)": 2.0176165103912354, "Pretrain/Step": 3860, "Pretrain/Step Time": 8.803242800757289} +{"Pretrain/Learning Rate": 3.373063826844764e-05, "Pretrain/Loss": 2.0624120235443115, "Pretrain/Loss (Raw)": 2.1641595363616943, "Pretrain/Step": 3861, "Pretrain/Step Time": 8.79527360573411} +{"Pretrain/Learning Rate": 3.3722682425473715e-05, "Pretrain/Loss": 2.062480926513672, "Pretrain/Loss (Raw)": 2.0428555011749268, "Pretrain/Step": 3862, "Pretrain/Step Time": 8.803900681436062} +{"Pretrain/Learning Rate": 3.371472557655896e-05, "Pretrain/Loss": 2.062837600708008, "Pretrain/Loss (Raw)": 2.1501681804656982, "Pretrain/Step": 3863, "Pretrain/Step Time": 8.801229104399681} +{"Pretrain/Learning Rate": 3.370676772262098e-05, "Pretrain/Loss": 2.0641536712646484, "Pretrain/Loss (Raw)": 2.1918790340423584, "Pretrain/Step": 3864, "Pretrain/Step Time": 8.800069950520992} +{"Pretrain/Learning Rate": 3.369880886457751e-05, "Pretrain/Loss": 2.0639543533325195, "Pretrain/Loss (Raw)": 2.048884391784668, "Pretrain/Step": 3865, "Pretrain/Step Time": 8.804047318175435} +{"Pretrain/Learning Rate": 3.369084900334643e-05, "Pretrain/Loss": 2.064657211303711, "Pretrain/Loss (Raw)": 2.227149486541748, "Pretrain/Step": 3866, "Pretrain/Step Time": 8.803003933280706} +{"Pretrain/Learning Rate": 3.368288813984568e-05, "Pretrain/Loss": 2.0630741119384766, "Pretrain/Loss (Raw)": 1.864312767982483, "Pretrain/Step": 3867, "Pretrain/Step Time": 8.803744688630104} +{"Pretrain/Learning Rate": 3.3674926274993356e-05, "Pretrain/Loss": 2.063822031021118, "Pretrain/Loss (Raw)": 2.1338422298431396, "Pretrain/Step": 3868, "Pretrain/Step Time": 8.79301005601883} +{"Pretrain/Learning Rate": 3.3666963409707655e-05, "Pretrain/Loss": 2.064272880554199, "Pretrain/Loss (Raw)": 2.1787188053131104, "Pretrain/Step": 3869, "Pretrain/Step Time": 8.80557894706726} +{"Pretrain/Learning Rate": 3.36589995449069e-05, "Pretrain/Loss": 2.068556547164917, "Pretrain/Loss (Raw)": 2.3364241123199463, "Pretrain/Step": 3870, "Pretrain/Step Time": 8.797938879579306} +{"Pretrain/Learning Rate": 3.36510346815095e-05, "Pretrain/Loss": 2.0688273906707764, "Pretrain/Loss (Raw)": 1.9319568872451782, "Pretrain/Step": 3871, "Pretrain/Step Time": 8.800112603232265} +{"Pretrain/Learning Rate": 3.3643068820434035e-05, "Pretrain/Loss": 2.0690248012542725, "Pretrain/Loss (Raw)": 2.117633581161499, "Pretrain/Step": 3872, "Pretrain/Step Time": 8.802810952067375} +{"Pretrain/Learning Rate": 3.363510196259913e-05, "Pretrain/Loss": 2.0691781044006348, "Pretrain/Loss (Raw)": 2.1645708084106445, "Pretrain/Step": 3873, "Pretrain/Step Time": 8.798494305461645} +{"Pretrain/Learning Rate": 3.362713410892359e-05, "Pretrain/Loss": 2.068953037261963, "Pretrain/Loss (Raw)": 1.9578231573104858, "Pretrain/Step": 3874, "Pretrain/Step Time": 8.79925812780857} +{"Pretrain/Learning Rate": 3.361916526032628e-05, "Pretrain/Loss": 2.0712242126464844, "Pretrain/Loss (Raw)": 2.2479248046875, "Pretrain/Step": 3875, "Pretrain/Step Time": 8.808579456061125} +{"Pretrain/Learning Rate": 3.361119541772622e-05, "Pretrain/Loss": 2.0703940391540527, "Pretrain/Loss (Raw)": 1.973052740097046, "Pretrain/Step": 3876, "Pretrain/Step Time": 8.797556418925524} +{"Pretrain/Learning Rate": 3.360322458204253e-05, "Pretrain/Loss": 2.072500228881836, "Pretrain/Loss (Raw)": 2.21624493598938, "Pretrain/Step": 3877, "Pretrain/Step Time": 8.805726820603013} +{"Pretrain/Learning Rate": 3.3595252754194445e-05, "Pretrain/Loss": 2.0718531608581543, "Pretrain/Loss (Raw)": 2.0235977172851562, "Pretrain/Step": 3878, "Pretrain/Step Time": 8.803258396685123} +{"Pretrain/Learning Rate": 3.3587279935101306e-05, "Pretrain/Loss": 2.0709612369537354, "Pretrain/Loss (Raw)": 1.9754856824874878, "Pretrain/Step": 3879, "Pretrain/Step Time": 8.800606338307261} +{"Pretrain/Learning Rate": 3.357930612568258e-05, "Pretrain/Loss": 2.0740504264831543, "Pretrain/Loss (Raw)": 2.173374891281128, "Pretrain/Step": 3880, "Pretrain/Step Time": 8.80233808979392} +{"Pretrain/Learning Rate": 3.3571331326857844e-05, "Pretrain/Loss": 2.075577974319458, "Pretrain/Loss (Raw)": 2.146568536758423, "Pretrain/Step": 3881, "Pretrain/Step Time": 8.801504300907254} +{"Pretrain/Learning Rate": 3.3563355539546795e-05, "Pretrain/Loss": 2.0764822959899902, "Pretrain/Loss (Raw)": 2.265805959701538, "Pretrain/Step": 3882, "Pretrain/Step Time": 8.80588429607451} +{"Pretrain/Learning Rate": 3.355537876466923e-05, "Pretrain/Loss": 2.0767364501953125, "Pretrain/Loss (Raw)": 2.1624131202697754, "Pretrain/Step": 3883, "Pretrain/Step Time": 8.794602205976844} +{"Pretrain/Learning Rate": 3.354740100314506e-05, "Pretrain/Loss": 2.0775139331817627, "Pretrain/Loss (Raw)": 2.1802637577056885, "Pretrain/Step": 3884, "Pretrain/Step Time": 8.798620406538248} +{"Pretrain/Learning Rate": 3.3539422255894345e-05, "Pretrain/Loss": 2.078348159790039, "Pretrain/Loss (Raw)": 2.15797758102417, "Pretrain/Step": 3885, "Pretrain/Step Time": 8.794380936771631} +{"Pretrain/Learning Rate": 3.353144252383721e-05, "Pretrain/Loss": 2.0784645080566406, "Pretrain/Loss (Raw)": 2.1796395778656006, "Pretrain/Step": 3886, "Pretrain/Step Time": 8.800212886184454} +{"Pretrain/Learning Rate": 3.3523461807893925e-05, "Pretrain/Loss": 2.0786635875701904, "Pretrain/Loss (Raw)": 2.0355541706085205, "Pretrain/Step": 3887, "Pretrain/Step Time": 8.799936791881919} +{"Pretrain/Learning Rate": 3.351548010898486e-05, "Pretrain/Loss": 2.079871654510498, "Pretrain/Loss (Raw)": 2.188365936279297, "Pretrain/Step": 3888, "Pretrain/Step Time": 8.800064085051417} +{"Pretrain/Learning Rate": 3.35074974280305e-05, "Pretrain/Loss": 2.0800881385803223, "Pretrain/Loss (Raw)": 1.8972039222717285, "Pretrain/Step": 3889, "Pretrain/Step Time": 8.804241321980953} +{"Pretrain/Learning Rate": 3.349951376595145e-05, "Pretrain/Loss": 2.079787254333496, "Pretrain/Loss (Raw)": 2.159702777862549, "Pretrain/Step": 3890, "Pretrain/Step Time": 8.8017644174397} +{"Pretrain/Learning Rate": 3.3491529123668425e-05, "Pretrain/Loss": 2.0811219215393066, "Pretrain/Loss (Raw)": 2.0798935890197754, "Pretrain/Step": 3891, "Pretrain/Step Time": 8.809964491054416} +{"Pretrain/Learning Rate": 3.348354350210224e-05, "Pretrain/Loss": 2.081639528274536, "Pretrain/Loss (Raw)": 2.116719961166382, "Pretrain/Step": 3892, "Pretrain/Step Time": 8.801345519721508} +{"Pretrain/Learning Rate": 3.347555690217385e-05, "Pretrain/Loss": 2.082352638244629, "Pretrain/Loss (Raw)": 2.059849739074707, "Pretrain/Step": 3893, "Pretrain/Step Time": 8.810928251594305} +{"Pretrain/Learning Rate": 3.34675693248043e-05, "Pretrain/Loss": 2.081681251525879, "Pretrain/Loss (Raw)": 1.9036531448364258, "Pretrain/Step": 3894, "Pretrain/Step Time": 8.803436717018485} +{"Pretrain/Learning Rate": 3.3459580770914744e-05, "Pretrain/Loss": 2.0813255310058594, "Pretrain/Loss (Raw)": 2.108640193939209, "Pretrain/Step": 3895, "Pretrain/Step Time": 8.80611914396286} +{"Pretrain/Learning Rate": 3.3451591241426486e-05, "Pretrain/Loss": 2.082430839538574, "Pretrain/Loss (Raw)": 2.20168399810791, "Pretrain/Step": 3896, "Pretrain/Step Time": 8.812433371320367} +{"Pretrain/Learning Rate": 3.3443600737260885e-05, "Pretrain/Loss": 2.08255934715271, "Pretrain/Loss (Raw)": 2.05568790435791, "Pretrain/Step": 3897, "Pretrain/Step Time": 8.801083147525787} +{"Pretrain/Learning Rate": 3.343560925933947e-05, "Pretrain/Loss": 2.081916332244873, "Pretrain/Loss (Raw)": 2.1873581409454346, "Pretrain/Step": 3898, "Pretrain/Step Time": 8.804034322500229} +{"Pretrain/Learning Rate": 3.342761680858385e-05, "Pretrain/Loss": 2.0807642936706543, "Pretrain/Loss (Raw)": 1.9863691329956055, "Pretrain/Step": 3899, "Pretrain/Step Time": 8.804851859807968} +{"Pretrain/Learning Rate": 3.3419623385915736e-05, "Pretrain/Loss": 2.0786311626434326, "Pretrain/Loss (Raw)": 1.8704726696014404, "Pretrain/Step": 3900, "Pretrain/Step Time": 8.80175893008709} +{"Pretrain/Learning Rate": 3.3411628992256984e-05, "Pretrain/Loss": 2.0800352096557617, "Pretrain/Loss (Raw)": 2.122234582901001, "Pretrain/Step": 3901, "Pretrain/Step Time": 8.802769364789128} +{"Pretrain/Learning Rate": 3.340363362852954e-05, "Pretrain/Loss": 2.0807199478149414, "Pretrain/Loss (Raw)": 2.080587148666382, "Pretrain/Step": 3902, "Pretrain/Step Time": 8.80035481415689} +{"Pretrain/Learning Rate": 3.339563729565547e-05, "Pretrain/Loss": 2.081988573074341, "Pretrain/Loss (Raw)": 2.1046478748321533, "Pretrain/Step": 3903, "Pretrain/Step Time": 8.804010665044188} +{"Pretrain/Learning Rate": 3.3387639994556934e-05, "Pretrain/Loss": 2.0821468830108643, "Pretrain/Loss (Raw)": 2.072855234146118, "Pretrain/Step": 3904, "Pretrain/Step Time": 8.79502477683127} +{"Pretrain/Learning Rate": 3.337964172615624e-05, "Pretrain/Loss": 2.082289695739746, "Pretrain/Loss (Raw)": 2.0489814281463623, "Pretrain/Step": 3905, "Pretrain/Step Time": 8.796310083940625} +{"Pretrain/Learning Rate": 3.337164249137577e-05, "Pretrain/Loss": 2.081216812133789, "Pretrain/Loss (Raw)": 2.1687989234924316, "Pretrain/Step": 3906, "Pretrain/Step Time": 8.794483685865998} +{"Pretrain/Learning Rate": 3.3363642291138046e-05, "Pretrain/Loss": 2.08132004737854, "Pretrain/Loss (Raw)": 2.1836137771606445, "Pretrain/Step": 3907, "Pretrain/Step Time": 8.794442949816585} +{"Pretrain/Learning Rate": 3.3355641126365676e-05, "Pretrain/Loss": 2.081070899963379, "Pretrain/Loss (Raw)": 1.9196889400482178, "Pretrain/Step": 3908, "Pretrain/Step Time": 8.786898421123624} +{"Pretrain/Learning Rate": 3.33476389979814e-05, "Pretrain/Loss": 2.078944206237793, "Pretrain/Loss (Raw)": 1.797548532485962, "Pretrain/Step": 3909, "Pretrain/Step Time": 8.786730818450451} +{"Pretrain/Learning Rate": 3.3339635906908064e-05, "Pretrain/Loss": 2.0815916061401367, "Pretrain/Loss (Raw)": 2.3981053829193115, "Pretrain/Step": 3910, "Pretrain/Step Time": 8.79146202839911} +{"Pretrain/Learning Rate": 3.3331631854068616e-05, "Pretrain/Loss": 2.083266019821167, "Pretrain/Loss (Raw)": 2.1552085876464844, "Pretrain/Step": 3911, "Pretrain/Step Time": 8.78253728710115} +{"Pretrain/Learning Rate": 3.3323626840386115e-05, "Pretrain/Loss": 2.0826239585876465, "Pretrain/Loss (Raw)": 2.0574123859405518, "Pretrain/Step": 3912, "Pretrain/Step Time": 8.776437623426318} +{"Pretrain/Learning Rate": 3.3315620866783755e-05, "Pretrain/Loss": 2.0824155807495117, "Pretrain/Loss (Raw)": 2.1937155723571777, "Pretrain/Step": 3913, "Pretrain/Step Time": 8.773145202547312} +{"Pretrain/Learning Rate": 3.33076139341848e-05, "Pretrain/Loss": 2.0843653678894043, "Pretrain/Loss (Raw)": 2.1460916996002197, "Pretrain/Step": 3914, "Pretrain/Step Time": 8.776186484843493} +{"Pretrain/Learning Rate": 3.329960604351267e-05, "Pretrain/Loss": 2.086364984512329, "Pretrain/Loss (Raw)": 2.1872732639312744, "Pretrain/Step": 3915, "Pretrain/Step Time": 8.77760523557663} +{"Pretrain/Learning Rate": 3.329159719569085e-05, "Pretrain/Loss": 2.0867128372192383, "Pretrain/Loss (Raw)": 2.138730049133301, "Pretrain/Step": 3916, "Pretrain/Step Time": 8.77547838166356} +{"Pretrain/Learning Rate": 3.328358739164299e-05, "Pretrain/Loss": 2.086686372756958, "Pretrain/Loss (Raw)": 2.093106508255005, "Pretrain/Step": 3917, "Pretrain/Step Time": 8.774116093292832} +{"Pretrain/Learning Rate": 3.327557663229278e-05, "Pretrain/Loss": 2.0868866443634033, "Pretrain/Loss (Raw)": 2.2276790142059326, "Pretrain/Step": 3918, "Pretrain/Step Time": 8.766805769875646} +{"Pretrain/Learning Rate": 3.326756491856409e-05, "Pretrain/Loss": 2.0861687660217285, "Pretrain/Loss (Raw)": 2.0332915782928467, "Pretrain/Step": 3919, "Pretrain/Step Time": 8.767193404957652} +{"Pretrain/Learning Rate": 3.325955225138085e-05, "Pretrain/Loss": 2.085111618041992, "Pretrain/Loss (Raw)": 2.0552847385406494, "Pretrain/Step": 3920, "Pretrain/Step Time": 8.770227888599038} +{"Pretrain/Learning Rate": 3.3251538631667125e-05, "Pretrain/Loss": 2.085019588470459, "Pretrain/Loss (Raw)": 2.0301101207733154, "Pretrain/Step": 3921, "Pretrain/Step Time": 8.769777538254857} +{"Pretrain/Learning Rate": 3.324352406034707e-05, "Pretrain/Loss": 2.085315465927124, "Pretrain/Loss (Raw)": 2.1092045307159424, "Pretrain/Step": 3922, "Pretrain/Step Time": 8.775110647082329} +{"Pretrain/Learning Rate": 3.3235508538344996e-05, "Pretrain/Loss": 2.084704875946045, "Pretrain/Loss (Raw)": 1.9465422630310059, "Pretrain/Step": 3923, "Pretrain/Step Time": 8.785257579758763} +{"Pretrain/Learning Rate": 3.322749206658526e-05, "Pretrain/Loss": 2.083693027496338, "Pretrain/Loss (Raw)": 1.9158498048782349, "Pretrain/Step": 3924, "Pretrain/Step Time": 8.782698461785913} +{"Pretrain/Learning Rate": 3.3219474645992366e-05, "Pretrain/Loss": 2.0826048851013184, "Pretrain/Loss (Raw)": 1.9483294486999512, "Pretrain/Step": 3925, "Pretrain/Step Time": 8.776839466765523} +{"Pretrain/Learning Rate": 3.3211456277490926e-05, "Pretrain/Loss": 2.082556962966919, "Pretrain/Loss (Raw)": 2.060218334197998, "Pretrain/Step": 3926, "Pretrain/Step Time": 8.782608106732368} +{"Pretrain/Learning Rate": 3.3203436962005655e-05, "Pretrain/Loss": 2.083073616027832, "Pretrain/Loss (Raw)": 2.068944215774536, "Pretrain/Step": 3927, "Pretrain/Step Time": 8.778611214831471} +{"Pretrain/Learning Rate": 3.3195416700461385e-05, "Pretrain/Loss": 2.0826468467712402, "Pretrain/Loss (Raw)": 1.9874871969223022, "Pretrain/Step": 3928, "Pretrain/Step Time": 8.779190363362432} +{"Pretrain/Learning Rate": 3.318739549378304e-05, "Pretrain/Loss": 2.0808217525482178, "Pretrain/Loss (Raw)": 1.9199334383010864, "Pretrain/Step": 3929, "Pretrain/Step Time": 8.777100337669253} +{"Pretrain/Learning Rate": 3.317937334289566e-05, "Pretrain/Loss": 2.0790886878967285, "Pretrain/Loss (Raw)": 1.990792155265808, "Pretrain/Step": 3930, "Pretrain/Step Time": 8.776526764035225} +{"Pretrain/Learning Rate": 3.317135024872442e-05, "Pretrain/Loss": 2.078118324279785, "Pretrain/Loss (Raw)": 2.1075186729431152, "Pretrain/Step": 3931, "Pretrain/Step Time": 8.779063547030091} +{"Pretrain/Learning Rate": 3.3163326212194546e-05, "Pretrain/Loss": 2.079789638519287, "Pretrain/Loss (Raw)": 2.1396517753601074, "Pretrain/Step": 3932, "Pretrain/Step Time": 8.777780041098595} +{"Pretrain/Learning Rate": 3.315530123423143e-05, "Pretrain/Loss": 2.0811638832092285, "Pretrain/Loss (Raw)": 2.2092273235321045, "Pretrain/Step": 3933, "Pretrain/Step Time": 8.775460127741098} +{"Pretrain/Learning Rate": 3.314727531576055e-05, "Pretrain/Loss": 2.080726385116577, "Pretrain/Loss (Raw)": 2.04473876953125, "Pretrain/Step": 3934, "Pretrain/Step Time": 8.776183819398284} +{"Pretrain/Learning Rate": 3.3139248457707495e-05, "Pretrain/Loss": 2.0796544551849365, "Pretrain/Loss (Raw)": 2.0654804706573486, "Pretrain/Step": 3935, "Pretrain/Step Time": 8.77580689266324} +{"Pretrain/Learning Rate": 3.313122066099794e-05, "Pretrain/Loss": 2.0800743103027344, "Pretrain/Loss (Raw)": 2.136984348297119, "Pretrain/Step": 3936, "Pretrain/Step Time": 8.777491984888911} +{"Pretrain/Learning Rate": 3.312319192655772e-05, "Pretrain/Loss": 2.080122709274292, "Pretrain/Loss (Raw)": 2.2076380252838135, "Pretrain/Step": 3937, "Pretrain/Step Time": 8.778084697201848} +{"Pretrain/Learning Rate": 3.311516225531271e-05, "Pretrain/Loss": 2.0792319774627686, "Pretrain/Loss (Raw)": 1.9639065265655518, "Pretrain/Step": 3938, "Pretrain/Step Time": 8.775566287338734} +{"Pretrain/Learning Rate": 3.3107131648188966e-05, "Pretrain/Loss": 2.0793490409851074, "Pretrain/Loss (Raw)": 2.0525543689727783, "Pretrain/Step": 3939, "Pretrain/Step Time": 8.78797186538577} +{"Pretrain/Learning Rate": 3.309910010611259e-05, "Pretrain/Loss": 2.0790207386016846, "Pretrain/Loss (Raw)": 2.050320625305176, "Pretrain/Step": 3940, "Pretrain/Step Time": 8.786055596545339} +{"Pretrain/Learning Rate": 3.3091067630009834e-05, "Pretrain/Loss": 2.077845573425293, "Pretrain/Loss (Raw)": 2.1347174644470215, "Pretrain/Step": 3941, "Pretrain/Step Time": 8.78555996157229} +{"Pretrain/Learning Rate": 3.3083034220807016e-05, "Pretrain/Loss": 2.0792417526245117, "Pretrain/Loss (Raw)": 2.130464792251587, "Pretrain/Step": 3942, "Pretrain/Step Time": 8.784497182816267} +{"Pretrain/Learning Rate": 3.307499987943062e-05, "Pretrain/Loss": 2.0789079666137695, "Pretrain/Loss (Raw)": 2.1382510662078857, "Pretrain/Step": 3943, "Pretrain/Step Time": 8.779572220519185} +{"Pretrain/Learning Rate": 3.3066964606807175e-05, "Pretrain/Loss": 2.080261707305908, "Pretrain/Loss (Raw)": 2.269416093826294, "Pretrain/Step": 3944, "Pretrain/Step Time": 8.778997173532844} +{"Pretrain/Learning Rate": 3.3058928403863364e-05, "Pretrain/Loss": 2.078747272491455, "Pretrain/Loss (Raw)": 2.023625135421753, "Pretrain/Step": 3945, "Pretrain/Step Time": 8.77921842224896} +{"Pretrain/Learning Rate": 3.305089127152596e-05, "Pretrain/Loss": 2.0800366401672363, "Pretrain/Loss (Raw)": 2.0206756591796875, "Pretrain/Step": 3946, "Pretrain/Step Time": 8.77240626886487} +{"Pretrain/Learning Rate": 3.304285321072183e-05, "Pretrain/Loss": 2.0805423259735107, "Pretrain/Loss (Raw)": 2.122166156768799, "Pretrain/Step": 3947, "Pretrain/Step Time": 8.777607699856162} +{"Pretrain/Learning Rate": 3.303481422237797e-05, "Pretrain/Loss": 2.081545352935791, "Pretrain/Loss (Raw)": 2.0361337661743164, "Pretrain/Step": 3948, "Pretrain/Step Time": 8.779899237677455} +{"Pretrain/Learning Rate": 3.3026774307421476e-05, "Pretrain/Loss": 2.0814695358276367, "Pretrain/Loss (Raw)": 2.240000009536743, "Pretrain/Step": 3949, "Pretrain/Step Time": 8.77860646136105} +{"Pretrain/Learning Rate": 3.301873346677954e-05, "Pretrain/Loss": 2.083026647567749, "Pretrain/Loss (Raw)": 2.213254451751709, "Pretrain/Step": 3950, "Pretrain/Step Time": 8.776173351332545} +{"Pretrain/Learning Rate": 3.301069170137948e-05, "Pretrain/Loss": 2.0837085247039795, "Pretrain/Loss (Raw)": 2.1780223846435547, "Pretrain/Step": 3951, "Pretrain/Step Time": 8.775152815505862} +{"Pretrain/Learning Rate": 3.3002649012148704e-05, "Pretrain/Loss": 2.0840582847595215, "Pretrain/Loss (Raw)": 2.1557745933532715, "Pretrain/Step": 3952, "Pretrain/Step Time": 8.771170841529965} +{"Pretrain/Learning Rate": 3.2994605400014736e-05, "Pretrain/Loss": 2.0850887298583984, "Pretrain/Loss (Raw)": 1.8916635513305664, "Pretrain/Step": 3953, "Pretrain/Step Time": 8.780287915840745} +{"Pretrain/Learning Rate": 3.29865608659052e-05, "Pretrain/Loss": 2.084113359451294, "Pretrain/Loss (Raw)": 2.00459623336792, "Pretrain/Step": 3954, "Pretrain/Step Time": 8.781044997274876} +{"Pretrain/Learning Rate": 3.297851541074782e-05, "Pretrain/Loss": 2.083906412124634, "Pretrain/Loss (Raw)": 2.083740472793579, "Pretrain/Step": 3955, "Pretrain/Step Time": 8.781653750687838} +{"Pretrain/Learning Rate": 3.297046903547046e-05, "Pretrain/Loss": 2.0836777687072754, "Pretrain/Loss (Raw)": 2.0775558948516846, "Pretrain/Step": 3956, "Pretrain/Step Time": 8.776973249390721} +{"Pretrain/Learning Rate": 3.296242174100105e-05, "Pretrain/Loss": 2.0848472118377686, "Pretrain/Loss (Raw)": 2.2285733222961426, "Pretrain/Step": 3957, "Pretrain/Step Time": 8.77642928250134} +{"Pretrain/Learning Rate": 3.2954373528267646e-05, "Pretrain/Loss": 2.083423137664795, "Pretrain/Loss (Raw)": 1.9572858810424805, "Pretrain/Step": 3958, "Pretrain/Step Time": 8.776624055579305} +{"Pretrain/Learning Rate": 3.29463243981984e-05, "Pretrain/Loss": 2.0839548110961914, "Pretrain/Loss (Raw)": 2.0889875888824463, "Pretrain/Step": 3959, "Pretrain/Step Time": 8.774162881076336} +{"Pretrain/Learning Rate": 3.2938274351721587e-05, "Pretrain/Loss": 2.083200693130493, "Pretrain/Loss (Raw)": 2.0056021213531494, "Pretrain/Step": 3960, "Pretrain/Step Time": 8.772803174331784} +{"Pretrain/Learning Rate": 3.2930223389765566e-05, "Pretrain/Loss": 2.083024501800537, "Pretrain/Loss (Raw)": 2.05501651763916, "Pretrain/Step": 3961, "Pretrain/Step Time": 8.776875287294388} +{"Pretrain/Learning Rate": 3.292217151325882e-05, "Pretrain/Loss": 2.082766056060791, "Pretrain/Loss (Raw)": 2.0682125091552734, "Pretrain/Step": 3962, "Pretrain/Step Time": 8.776681562885642} +{"Pretrain/Learning Rate": 3.2914118723129916e-05, "Pretrain/Loss": 2.083390951156616, "Pretrain/Loss (Raw)": 1.9732056856155396, "Pretrain/Step": 3963, "Pretrain/Step Time": 8.778127197176218} +{"Pretrain/Learning Rate": 3.2906065020307545e-05, "Pretrain/Loss": 2.0833654403686523, "Pretrain/Loss (Raw)": 2.079226493835449, "Pretrain/Step": 3964, "Pretrain/Step Time": 8.781726434826851} +{"Pretrain/Learning Rate": 3.289801040572051e-05, "Pretrain/Loss": 2.0818212032318115, "Pretrain/Loss (Raw)": 1.9353841543197632, "Pretrain/Step": 3965, "Pretrain/Step Time": 8.783980157226324} +{"Pretrain/Learning Rate": 3.288995488029769e-05, "Pretrain/Loss": 2.084796905517578, "Pretrain/Loss (Raw)": 2.2560982704162598, "Pretrain/Step": 3966, "Pretrain/Step Time": 8.78247200511396} +{"Pretrain/Learning Rate": 3.288189844496811e-05, "Pretrain/Loss": 2.0850653648376465, "Pretrain/Loss (Raw)": 1.9935425519943237, "Pretrain/Step": 3967, "Pretrain/Step Time": 8.779800210148096} +{"Pretrain/Learning Rate": 3.287384110066084e-05, "Pretrain/Loss": 2.0854198932647705, "Pretrain/Loss (Raw)": 2.043307065963745, "Pretrain/Step": 3968, "Pretrain/Step Time": 8.789212107658386} +{"Pretrain/Learning Rate": 3.286578284830513e-05, "Pretrain/Loss": 2.0868544578552246, "Pretrain/Loss (Raw)": 2.1365370750427246, "Pretrain/Step": 3969, "Pretrain/Step Time": 8.78767211176455} +{"Pretrain/Learning Rate": 3.2857723688830264e-05, "Pretrain/Loss": 2.0879313945770264, "Pretrain/Loss (Raw)": 2.1663663387298584, "Pretrain/Step": 3970, "Pretrain/Step Time": 8.78567891381681} +{"Pretrain/Learning Rate": 3.284966362316568e-05, "Pretrain/Loss": 2.087876796722412, "Pretrain/Loss (Raw)": 2.030914783477783, "Pretrain/Step": 3971, "Pretrain/Step Time": 8.784941021353006} +{"Pretrain/Learning Rate": 3.28416026522409e-05, "Pretrain/Loss": 2.087329864501953, "Pretrain/Loss (Raw)": 1.995927095413208, "Pretrain/Step": 3972, "Pretrain/Step Time": 8.784431874752045} +{"Pretrain/Learning Rate": 3.283354077698555e-05, "Pretrain/Loss": 2.0846118927001953, "Pretrain/Loss (Raw)": 1.9077098369598389, "Pretrain/Step": 3973, "Pretrain/Step Time": 8.781603373587132} +{"Pretrain/Learning Rate": 3.2825477998329366e-05, "Pretrain/Loss": 2.0872673988342285, "Pretrain/Loss (Raw)": 2.1717350482940674, "Pretrain/Step": 3974, "Pretrain/Step Time": 8.792591428384185} +{"Pretrain/Learning Rate": 3.281741431720219e-05, "Pretrain/Loss": 2.0871472358703613, "Pretrain/Loss (Raw)": 2.0201077461242676, "Pretrain/Step": 3975, "Pretrain/Step Time": 8.785988615825772} +{"Pretrain/Learning Rate": 3.280934973453395e-05, "Pretrain/Loss": 2.0883467197418213, "Pretrain/Loss (Raw)": 2.196287155151367, "Pretrain/Step": 3976, "Pretrain/Step Time": 8.794801220297813} +{"Pretrain/Learning Rate": 3.28012842512547e-05, "Pretrain/Loss": 2.0885066986083984, "Pretrain/Loss (Raw)": 2.049149751663208, "Pretrain/Step": 3977, "Pretrain/Step Time": 8.794000139459968} +{"Pretrain/Learning Rate": 3.279321786829459e-05, "Pretrain/Loss": 2.0891659259796143, "Pretrain/Loss (Raw)": 2.0259780883789062, "Pretrain/Step": 3978, "Pretrain/Step Time": 8.787859819829464} +{"Pretrain/Learning Rate": 3.278515058658387e-05, "Pretrain/Loss": 2.0878403186798096, "Pretrain/Loss (Raw)": 1.9644566774368286, "Pretrain/Step": 3979, "Pretrain/Step Time": 8.786374000832438} +{"Pretrain/Learning Rate": 3.27770824070529e-05, "Pretrain/Loss": 2.0880556106567383, "Pretrain/Loss (Raw)": 2.1383445262908936, "Pretrain/Step": 3980, "Pretrain/Step Time": 8.787969717755914} +{"Pretrain/Learning Rate": 3.276901333063215e-05, "Pretrain/Loss": 2.087648868560791, "Pretrain/Loss (Raw)": 2.1044461727142334, "Pretrain/Step": 3981, "Pretrain/Step Time": 8.7976033706218} +{"Pretrain/Learning Rate": 3.276094335825217e-05, "Pretrain/Loss": 2.0870680809020996, "Pretrain/Loss (Raw)": 2.041195869445801, "Pretrain/Step": 3982, "Pretrain/Step Time": 8.798649093136191} +{"Pretrain/Learning Rate": 3.2752872490843626e-05, "Pretrain/Loss": 2.0865297317504883, "Pretrain/Loss (Raw)": 2.216658115386963, "Pretrain/Step": 3983, "Pretrain/Step Time": 8.789336018264294} +{"Pretrain/Learning Rate": 3.274480072933729e-05, "Pretrain/Loss": 2.087284803390503, "Pretrain/Loss (Raw)": 2.219572067260742, "Pretrain/Step": 3984, "Pretrain/Step Time": 8.795147977769375} +{"Pretrain/Learning Rate": 3.273672807466405e-05, "Pretrain/Loss": 2.0871315002441406, "Pretrain/Loss (Raw)": 1.9767142534255981, "Pretrain/Step": 3985, "Pretrain/Step Time": 8.791398400440812} +{"Pretrain/Learning Rate": 3.272865452775487e-05, "Pretrain/Loss": 2.085327386856079, "Pretrain/Loss (Raw)": 1.9093093872070312, "Pretrain/Step": 3986, "Pretrain/Step Time": 8.789474740624428} +{"Pretrain/Learning Rate": 3.272058008954083e-05, "Pretrain/Loss": 2.0869827270507812, "Pretrain/Loss (Raw)": 2.236081838607788, "Pretrain/Step": 3987, "Pretrain/Step Time": 8.789114523679018} +{"Pretrain/Learning Rate": 3.271250476095311e-05, "Pretrain/Loss": 2.0875916481018066, "Pretrain/Loss (Raw)": 2.095567226409912, "Pretrain/Step": 3988, "Pretrain/Step Time": 8.793849492445588} +{"Pretrain/Learning Rate": 3.2704428542923e-05, "Pretrain/Loss": 2.085987091064453, "Pretrain/Loss (Raw)": 1.9587984085083008, "Pretrain/Step": 3989, "Pretrain/Step Time": 8.791051249951124} +{"Pretrain/Learning Rate": 3.269635143638188e-05, "Pretrain/Loss": 2.0870413780212402, "Pretrain/Loss (Raw)": 2.1777682304382324, "Pretrain/Step": 3990, "Pretrain/Step Time": 8.782827774062753} +{"Pretrain/Learning Rate": 3.2688273442261255e-05, "Pretrain/Loss": 2.0863730907440186, "Pretrain/Loss (Raw)": 2.0646450519561768, "Pretrain/Step": 3991, "Pretrain/Step Time": 8.783898958936334} +{"Pretrain/Learning Rate": 3.26801945614927e-05, "Pretrain/Loss": 2.0853281021118164, "Pretrain/Loss (Raw)": 2.058120012283325, "Pretrain/Step": 3992, "Pretrain/Step Time": 8.785054566338658} +{"Pretrain/Learning Rate": 3.2672114795007926e-05, "Pretrain/Loss": 2.087219715118408, "Pretrain/Loss (Raw)": 2.2910356521606445, "Pretrain/Step": 3993, "Pretrain/Step Time": 8.781895458698273} +{"Pretrain/Learning Rate": 3.266403414373872e-05, "Pretrain/Loss": 2.085496187210083, "Pretrain/Loss (Raw)": 2.006516218185425, "Pretrain/Step": 3994, "Pretrain/Step Time": 8.780429441481829} +{"Pretrain/Learning Rate": 3.265595260861698e-05, "Pretrain/Loss": 2.086728096008301, "Pretrain/Loss (Raw)": 2.0219833850860596, "Pretrain/Step": 3995, "Pretrain/Step Time": 8.790173502638936} +{"Pretrain/Learning Rate": 3.264787019057471e-05, "Pretrain/Loss": 2.0856971740722656, "Pretrain/Loss (Raw)": 2.001882314682007, "Pretrain/Step": 3996, "Pretrain/Step Time": 8.787108631804585} +{"Pretrain/Learning Rate": 3.2639786890544014e-05, "Pretrain/Loss": 2.0853731632232666, "Pretrain/Loss (Raw)": 2.137263298034668, "Pretrain/Step": 3997, "Pretrain/Step Time": 8.782253760844469} +{"Pretrain/Learning Rate": 3.263170270945709e-05, "Pretrain/Loss": 2.083738327026367, "Pretrain/Loss (Raw)": 2.1271753311157227, "Pretrain/Step": 3998, "Pretrain/Step Time": 8.790212534368038} +{"Pretrain/Learning Rate": 3.262361764824625e-05, "Pretrain/Loss": 2.0844101905822754, "Pretrain/Loss (Raw)": 2.017951726913452, "Pretrain/Step": 3999, "Pretrain/Step Time": 8.787503140047193} +{"Pretrain/Learning Rate": 3.26155317078439e-05, "Pretrain/Loss": 2.0824153423309326, "Pretrain/Loss (Raw)": 1.8622841835021973, "Pretrain/Step": 4000, "Pretrain/Step Time": 8.780363041907549} +{"Pretrain/Learning Rate": 3.260744488918254e-05, "Pretrain/Loss": 2.081984043121338, "Pretrain/Loss (Raw)": 2.1093862056732178, "Pretrain/Step": 4001, "Pretrain/Step Time": 8.789860408753157} +{"Pretrain/Learning Rate": 3.25993571931948e-05, "Pretrain/Loss": 2.084583044052124, "Pretrain/Loss (Raw)": 2.290475845336914, "Pretrain/Step": 4002, "Pretrain/Step Time": 8.789459008723497} +{"Pretrain/Learning Rate": 3.259126862081337e-05, "Pretrain/Loss": 2.081881523132324, "Pretrain/Loss (Raw)": 1.902147650718689, "Pretrain/Step": 4003, "Pretrain/Step Time": 8.783044485375285} +{"Pretrain/Learning Rate": 3.258317917297108e-05, "Pretrain/Loss": 2.0824785232543945, "Pretrain/Loss (Raw)": 2.049424886703491, "Pretrain/Step": 4004, "Pretrain/Step Time": 8.786180602386594} +{"Pretrain/Learning Rate": 3.2575088850600826e-05, "Pretrain/Loss": 2.0799479484558105, "Pretrain/Loss (Raw)": 1.8923505544662476, "Pretrain/Step": 4005, "Pretrain/Step Time": 8.779452146962285} +{"Pretrain/Learning Rate": 3.2566997654635634e-05, "Pretrain/Loss": 2.079317569732666, "Pretrain/Loss (Raw)": 1.9428985118865967, "Pretrain/Step": 4006, "Pretrain/Step Time": 8.780557749792933} +{"Pretrain/Learning Rate": 3.2558905586008616e-05, "Pretrain/Loss": 2.079373359680176, "Pretrain/Loss (Raw)": 1.9826414585113525, "Pretrain/Step": 4007, "Pretrain/Step Time": 8.777867687866092} +{"Pretrain/Learning Rate": 3.2550812645652985e-05, "Pretrain/Loss": 2.0780959129333496, "Pretrain/Loss (Raw)": 2.0098438262939453, "Pretrain/Step": 4008, "Pretrain/Step Time": 8.770955691114068} +{"Pretrain/Learning Rate": 3.2542718834502056e-05, "Pretrain/Loss": 2.078165054321289, "Pretrain/Loss (Raw)": 2.1554651260375977, "Pretrain/Step": 4009, "Pretrain/Step Time": 8.782654292881489} +{"Pretrain/Learning Rate": 3.253462415348926e-05, "Pretrain/Loss": 2.0766546726226807, "Pretrain/Loss (Raw)": 2.0724380016326904, "Pretrain/Step": 4010, "Pretrain/Step Time": 8.77750831283629} +{"Pretrain/Learning Rate": 3.252652860354809e-05, "Pretrain/Loss": 2.0751442909240723, "Pretrain/Loss (Raw)": 1.9690884351730347, "Pretrain/Step": 4011, "Pretrain/Step Time": 8.779635202139616} +{"Pretrain/Learning Rate": 3.2518432185612184e-05, "Pretrain/Loss": 2.0736565589904785, "Pretrain/Loss (Raw)": 1.9898419380187988, "Pretrain/Step": 4012, "Pretrain/Step Time": 8.780850764364004} +{"Pretrain/Learning Rate": 3.2510334900615254e-05, "Pretrain/Loss": 2.0728635787963867, "Pretrain/Loss (Raw)": 2.0564496517181396, "Pretrain/Step": 4013, "Pretrain/Step Time": 8.783291840925813} +{"Pretrain/Learning Rate": 3.25022367494911e-05, "Pretrain/Loss": 2.071099281311035, "Pretrain/Loss (Raw)": 1.9538233280181885, "Pretrain/Step": 4014, "Pretrain/Step Time": 8.781028313562274} +{"Pretrain/Learning Rate": 3.2494137733173666e-05, "Pretrain/Loss": 2.073967456817627, "Pretrain/Loss (Raw)": 2.402705430984497, "Pretrain/Step": 4015, "Pretrain/Step Time": 8.781852601096034} +{"Pretrain/Learning Rate": 3.2486037852596946e-05, "Pretrain/Loss": 2.071287155151367, "Pretrain/Loss (Raw)": 1.8452553749084473, "Pretrain/Step": 4016, "Pretrain/Step Time": 8.782710721716285} +{"Pretrain/Learning Rate": 3.247793710869507e-05, "Pretrain/Loss": 2.073885917663574, "Pretrain/Loss (Raw)": 2.229865312576294, "Pretrain/Step": 4017, "Pretrain/Step Time": 8.77707283385098} +{"Pretrain/Learning Rate": 3.2469835502402246e-05, "Pretrain/Loss": 2.0740714073181152, "Pretrain/Loss (Raw)": 2.1834514141082764, "Pretrain/Step": 4018, "Pretrain/Step Time": 8.775282815098763} +{"Pretrain/Learning Rate": 3.2461733034652794e-05, "Pretrain/Loss": 2.07385516166687, "Pretrain/Loss (Raw)": 2.052225351333618, "Pretrain/Step": 4019, "Pretrain/Step Time": 8.776429938152432} +{"Pretrain/Learning Rate": 3.245362970638113e-05, "Pretrain/Loss": 2.0726518630981445, "Pretrain/Loss (Raw)": 1.9626504182815552, "Pretrain/Step": 4020, "Pretrain/Step Time": 8.782242760062218} +{"Pretrain/Learning Rate": 3.244552551852176e-05, "Pretrain/Loss": 2.07064151763916, "Pretrain/Loss (Raw)": 1.802539587020874, "Pretrain/Step": 4021, "Pretrain/Step Time": 8.775039084255695} +{"Pretrain/Learning Rate": 3.24374204720093e-05, "Pretrain/Loss": 2.070974349975586, "Pretrain/Loss (Raw)": 1.9462536573410034, "Pretrain/Step": 4022, "Pretrain/Step Time": 8.785434929654002} +{"Pretrain/Learning Rate": 3.242931456777848e-05, "Pretrain/Loss": 2.0689187049865723, "Pretrain/Loss (Raw)": 1.8455302715301514, "Pretrain/Step": 4023, "Pretrain/Step Time": 8.780947698280215} +{"Pretrain/Learning Rate": 3.242120780676408e-05, "Pretrain/Loss": 2.0673909187316895, "Pretrain/Loss (Raw)": 2.006129264831543, "Pretrain/Step": 4024, "Pretrain/Step Time": 8.778597433120012} +{"Pretrain/Learning Rate": 3.2413100189901036e-05, "Pretrain/Loss": 2.0703611373901367, "Pretrain/Loss (Raw)": 2.4358747005462646, "Pretrain/Step": 4025, "Pretrain/Step Time": 8.776485783979297} +{"Pretrain/Learning Rate": 3.2404991718124346e-05, "Pretrain/Loss": 2.0679969787597656, "Pretrain/Loss (Raw)": 1.8847413063049316, "Pretrain/Step": 4026, "Pretrain/Step Time": 8.78354817815125} +{"Pretrain/Learning Rate": 3.239688239236911e-05, "Pretrain/Loss": 2.0684702396392822, "Pretrain/Loss (Raw)": 2.046963930130005, "Pretrain/Step": 4027, "Pretrain/Step Time": 8.783693401142955} +{"Pretrain/Learning Rate": 3.238877221357054e-05, "Pretrain/Loss": 2.071369171142578, "Pretrain/Loss (Raw)": 2.2415363788604736, "Pretrain/Step": 4028, "Pretrain/Step Time": 8.785152230411768} +{"Pretrain/Learning Rate": 3.2380661182663956e-05, "Pretrain/Loss": 2.0694282054901123, "Pretrain/Loss (Raw)": 1.8737578392028809, "Pretrain/Step": 4029, "Pretrain/Step Time": 8.791670577600598} +{"Pretrain/Learning Rate": 3.237254930058474e-05, "Pretrain/Loss": 2.068760395050049, "Pretrain/Loss (Raw)": 1.995116114616394, "Pretrain/Step": 4030, "Pretrain/Step Time": 8.789560103788972} +{"Pretrain/Learning Rate": 3.236443656826839e-05, "Pretrain/Loss": 2.067559242248535, "Pretrain/Loss (Raw)": 1.9509062767028809, "Pretrain/Step": 4031, "Pretrain/Step Time": 8.788466177880764} +{"Pretrain/Learning Rate": 3.235632298665052e-05, "Pretrain/Loss": 2.0681395530700684, "Pretrain/Loss (Raw)": 2.147104024887085, "Pretrain/Step": 4032, "Pretrain/Step Time": 8.789873944595456} +{"Pretrain/Learning Rate": 3.234820855666681e-05, "Pretrain/Loss": 2.0691490173339844, "Pretrain/Loss (Raw)": 2.1782310009002686, "Pretrain/Step": 4033, "Pretrain/Step Time": 8.785109778866172} +{"Pretrain/Learning Rate": 3.234009327925308e-05, "Pretrain/Loss": 2.067800283432007, "Pretrain/Loss (Raw)": 1.9961453676223755, "Pretrain/Step": 4034, "Pretrain/Step Time": 8.785499040037394} +{"Pretrain/Learning Rate": 3.23319771553452e-05, "Pretrain/Loss": 2.067146062850952, "Pretrain/Loss (Raw)": 2.0998990535736084, "Pretrain/Step": 4035, "Pretrain/Step Time": 8.784521954134107} +{"Pretrain/Learning Rate": 3.232386018587916e-05, "Pretrain/Loss": 2.0693211555480957, "Pretrain/Loss (Raw)": 2.1980550289154053, "Pretrain/Step": 4036, "Pretrain/Step Time": 8.7977160718292} +{"Pretrain/Learning Rate": 3.2315742371791046e-05, "Pretrain/Loss": 2.071985960006714, "Pretrain/Loss (Raw)": 2.1386704444885254, "Pretrain/Step": 4037, "Pretrain/Step Time": 8.803946593776345} +{"Pretrain/Learning Rate": 3.230762371401705e-05, "Pretrain/Loss": 2.0691564083099365, "Pretrain/Loss (Raw)": 2.0359177589416504, "Pretrain/Step": 4038, "Pretrain/Step Time": 8.79432182945311} +{"Pretrain/Learning Rate": 3.2299504213493464e-05, "Pretrain/Loss": 2.067739486694336, "Pretrain/Loss (Raw)": 1.973860502243042, "Pretrain/Step": 4039, "Pretrain/Step Time": 8.791367389261723} +{"Pretrain/Learning Rate": 3.229138387115665e-05, "Pretrain/Loss": 2.0680837631225586, "Pretrain/Loss (Raw)": 2.101456642150879, "Pretrain/Step": 4040, "Pretrain/Step Time": 8.790015770122409} +{"Pretrain/Learning Rate": 3.228326268794309e-05, "Pretrain/Loss": 2.0676231384277344, "Pretrain/Loss (Raw)": 2.134766101837158, "Pretrain/Step": 4041, "Pretrain/Step Time": 8.792519396170974} +{"Pretrain/Learning Rate": 3.227514066478936e-05, "Pretrain/Loss": 2.0661816596984863, "Pretrain/Loss (Raw)": 1.961585283279419, "Pretrain/Step": 4042, "Pretrain/Step Time": 8.789365397766232} +{"Pretrain/Learning Rate": 3.226701780263212e-05, "Pretrain/Loss": 2.065462589263916, "Pretrain/Loss (Raw)": 2.095236301422119, "Pretrain/Step": 4043, "Pretrain/Step Time": 8.786060310900211} +{"Pretrain/Learning Rate": 3.225889410240815e-05, "Pretrain/Loss": 2.063472270965576, "Pretrain/Loss (Raw)": 1.8839654922485352, "Pretrain/Step": 4044, "Pretrain/Step Time": 8.79232395812869} +{"Pretrain/Learning Rate": 3.2250769565054305e-05, "Pretrain/Loss": 2.064483642578125, "Pretrain/Loss (Raw)": 2.222552537918091, "Pretrain/Step": 4045, "Pretrain/Step Time": 8.78246996179223} +{"Pretrain/Learning Rate": 3.2242644191507545e-05, "Pretrain/Loss": 2.0627734661102295, "Pretrain/Loss (Raw)": 2.0087623596191406, "Pretrain/Step": 4046, "Pretrain/Step Time": 8.789727941155434} +{"Pretrain/Learning Rate": 3.223451798270493e-05, "Pretrain/Loss": 2.0622501373291016, "Pretrain/Loss (Raw)": 1.9663485288619995, "Pretrain/Step": 4047, "Pretrain/Step Time": 8.79050356335938} +{"Pretrain/Learning Rate": 3.222639093958361e-05, "Pretrain/Loss": 2.062682867050171, "Pretrain/Loss (Raw)": 2.110640287399292, "Pretrain/Step": 4048, "Pretrain/Step Time": 8.796200571581721} +{"Pretrain/Learning Rate": 3.2218263063080836e-05, "Pretrain/Loss": 2.062145233154297, "Pretrain/Loss (Raw)": 1.9612890481948853, "Pretrain/Step": 4049, "Pretrain/Step Time": 8.798622189089656} +{"Pretrain/Learning Rate": 3.221013435413395e-05, "Pretrain/Loss": 2.0618085861206055, "Pretrain/Loss (Raw)": 2.066101312637329, "Pretrain/Step": 4050, "Pretrain/Step Time": 8.797575000673532} +{"Pretrain/Learning Rate": 3.220200481368039e-05, "Pretrain/Loss": 2.0608932971954346, "Pretrain/Loss (Raw)": 1.8294168710708618, "Pretrain/Step": 4051, "Pretrain/Step Time": 8.790099918842316} +{"Pretrain/Learning Rate": 3.219387444265771e-05, "Pretrain/Loss": 2.06274151802063, "Pretrain/Loss (Raw)": 2.152413845062256, "Pretrain/Step": 4052, "Pretrain/Step Time": 8.790370151400566} +{"Pretrain/Learning Rate": 3.2185743242003524e-05, "Pretrain/Loss": 2.063225746154785, "Pretrain/Loss (Raw)": 2.010322332382202, "Pretrain/Step": 4053, "Pretrain/Step Time": 8.795938881114125} +{"Pretrain/Learning Rate": 3.217761121265557e-05, "Pretrain/Loss": 2.063152313232422, "Pretrain/Loss (Raw)": 2.0507900714874268, "Pretrain/Step": 4054, "Pretrain/Step Time": 8.791732059791684} +{"Pretrain/Learning Rate": 3.2169478355551665e-05, "Pretrain/Loss": 2.0638351440429688, "Pretrain/Loss (Raw)": 2.1563830375671387, "Pretrain/Step": 4055, "Pretrain/Step Time": 8.793343802914023} +{"Pretrain/Learning Rate": 3.216134467162973e-05, "Pretrain/Loss": 2.06415057182312, "Pretrain/Loss (Raw)": 2.027846574783325, "Pretrain/Step": 4056, "Pretrain/Step Time": 8.792925011366606} +{"Pretrain/Learning Rate": 3.215321016182779e-05, "Pretrain/Loss": 2.0652294158935547, "Pretrain/Loss (Raw)": 2.0580334663391113, "Pretrain/Step": 4057, "Pretrain/Step Time": 8.79131669178605} +{"Pretrain/Learning Rate": 3.2145074827083946e-05, "Pretrain/Loss": 2.0669126510620117, "Pretrain/Loss (Raw)": 2.2062182426452637, "Pretrain/Step": 4058, "Pretrain/Step Time": 8.79576026648283} +{"Pretrain/Learning Rate": 3.21369386683364e-05, "Pretrain/Loss": 2.0677003860473633, "Pretrain/Loss (Raw)": 2.208383560180664, "Pretrain/Step": 4059, "Pretrain/Step Time": 8.801591046154499} +{"Pretrain/Learning Rate": 3.212880168652346e-05, "Pretrain/Loss": 2.0674984455108643, "Pretrain/Loss (Raw)": 2.1137802600860596, "Pretrain/Step": 4060, "Pretrain/Step Time": 8.793486312031746} +{"Pretrain/Learning Rate": 3.2120663882583514e-05, "Pretrain/Loss": 2.066882848739624, "Pretrain/Loss (Raw)": 2.1304373741149902, "Pretrain/Step": 4061, "Pretrain/Step Time": 8.7979134041816} +{"Pretrain/Learning Rate": 3.2112525257455064e-05, "Pretrain/Loss": 2.0665555000305176, "Pretrain/Loss (Raw)": 2.002840757369995, "Pretrain/Step": 4062, "Pretrain/Step Time": 8.801718655973673} +{"Pretrain/Learning Rate": 3.210438581207667e-05, "Pretrain/Loss": 2.066476345062256, "Pretrain/Loss (Raw)": 2.0553739070892334, "Pretrain/Step": 4063, "Pretrain/Step Time": 8.803157977759838} +{"Pretrain/Learning Rate": 3.209624554738704e-05, "Pretrain/Loss": 2.0656216144561768, "Pretrain/Loss (Raw)": 2.0275521278381348, "Pretrain/Step": 4064, "Pretrain/Step Time": 8.800758332014084} +{"Pretrain/Learning Rate": 3.208810446432493e-05, "Pretrain/Loss": 2.0655503273010254, "Pretrain/Loss (Raw)": 2.1985158920288086, "Pretrain/Step": 4065, "Pretrain/Step Time": 8.801144298166037} +{"Pretrain/Learning Rate": 3.207996256382922e-05, "Pretrain/Loss": 2.0663819313049316, "Pretrain/Loss (Raw)": 2.070322036743164, "Pretrain/Step": 4066, "Pretrain/Step Time": 8.816490639001131} +{"Pretrain/Learning Rate": 3.207181984683886e-05, "Pretrain/Loss": 2.066901206970215, "Pretrain/Loss (Raw)": 2.119046688079834, "Pretrain/Step": 4067, "Pretrain/Step Time": 8.796728363260627} +{"Pretrain/Learning Rate": 3.2063676314292914e-05, "Pretrain/Loss": 2.067143201828003, "Pretrain/Loss (Raw)": 2.0813040733337402, "Pretrain/Step": 4068, "Pretrain/Step Time": 8.801352934911847} +{"Pretrain/Learning Rate": 3.205553196713052e-05, "Pretrain/Loss": 2.066831588745117, "Pretrain/Loss (Raw)": 2.0948212146759033, "Pretrain/Step": 4069, "Pretrain/Step Time": 8.80039986781776} +{"Pretrain/Learning Rate": 3.204738680629094e-05, "Pretrain/Loss": 2.065558910369873, "Pretrain/Loss (Raw)": 1.9675410985946655, "Pretrain/Step": 4070, "Pretrain/Step Time": 8.802509985864162} +{"Pretrain/Learning Rate": 3.2039240832713516e-05, "Pretrain/Loss": 2.0647828578948975, "Pretrain/Loss (Raw)": 2.0389485359191895, "Pretrain/Step": 4071, "Pretrain/Step Time": 8.80256911739707} +{"Pretrain/Learning Rate": 3.203109404733765e-05, "Pretrain/Loss": 2.063509941101074, "Pretrain/Loss (Raw)": 2.1064722537994385, "Pretrain/Step": 4072, "Pretrain/Step Time": 8.804813995957375} +{"Pretrain/Learning Rate": 3.20229464511029e-05, "Pretrain/Loss": 2.0634961128234863, "Pretrain/Loss (Raw)": 2.0218727588653564, "Pretrain/Step": 4073, "Pretrain/Step Time": 8.81497385725379} +{"Pretrain/Learning Rate": 3.2014798044948866e-05, "Pretrain/Loss": 2.062734365463257, "Pretrain/Loss (Raw)": 1.923163890838623, "Pretrain/Step": 4074, "Pretrain/Step Time": 8.814582483842969} +{"Pretrain/Learning Rate": 3.2006648829815265e-05, "Pretrain/Loss": 2.0645251274108887, "Pretrain/Loss (Raw)": 2.3513858318328857, "Pretrain/Step": 4075, "Pretrain/Step Time": 8.810532107949257} +{"Pretrain/Learning Rate": 3.1998498806641907e-05, "Pretrain/Loss": 2.0627877712249756, "Pretrain/Loss (Raw)": 1.8137458562850952, "Pretrain/Step": 4076, "Pretrain/Step Time": 8.80965143442154} +{"Pretrain/Learning Rate": 3.19903479763687e-05, "Pretrain/Loss": 2.0619709491729736, "Pretrain/Loss (Raw)": 2.1354453563690186, "Pretrain/Step": 4077, "Pretrain/Step Time": 8.811107117682695} +{"Pretrain/Learning Rate": 3.19821963399356e-05, "Pretrain/Loss": 2.0623040199279785, "Pretrain/Loss (Raw)": 2.2558600902557373, "Pretrain/Step": 4078, "Pretrain/Step Time": 8.813808737322688} +{"Pretrain/Learning Rate": 3.1974043898282744e-05, "Pretrain/Loss": 2.062130928039551, "Pretrain/Loss (Raw)": 2.155876874923706, "Pretrain/Step": 4079, "Pretrain/Step Time": 8.819333562627435} +{"Pretrain/Learning Rate": 3.196589065235026e-05, "Pretrain/Loss": 2.062016010284424, "Pretrain/Loss (Raw)": 2.1410746574401855, "Pretrain/Step": 4080, "Pretrain/Step Time": 8.818075116723776} +{"Pretrain/Learning Rate": 3.195773660307846e-05, "Pretrain/Loss": 2.0628771781921387, "Pretrain/Loss (Raw)": 2.0018811225891113, "Pretrain/Step": 4081, "Pretrain/Step Time": 8.808380607515574} +{"Pretrain/Learning Rate": 3.1949581751407676e-05, "Pretrain/Loss": 2.0612635612487793, "Pretrain/Loss (Raw)": 1.7980493307113647, "Pretrain/Step": 4082, "Pretrain/Step Time": 8.80941447429359} +{"Pretrain/Learning Rate": 3.1941426098278383e-05, "Pretrain/Loss": 2.062333345413208, "Pretrain/Loss (Raw)": 2.2207019329071045, "Pretrain/Step": 4083, "Pretrain/Step Time": 8.808468159288168} +{"Pretrain/Learning Rate": 3.193326964463112e-05, "Pretrain/Loss": 2.061269998550415, "Pretrain/Loss (Raw)": 1.9414374828338623, "Pretrain/Step": 4084, "Pretrain/Step Time": 8.812358839437366} +{"Pretrain/Learning Rate": 3.192511239140653e-05, "Pretrain/Loss": 2.060455322265625, "Pretrain/Loss (Raw)": 2.1242778301239014, "Pretrain/Step": 4085, "Pretrain/Step Time": 8.806337939575315} +{"Pretrain/Learning Rate": 3.1916954339545355e-05, "Pretrain/Loss": 2.061879873275757, "Pretrain/Loss (Raw)": 2.1396353244781494, "Pretrain/Step": 4086, "Pretrain/Step Time": 8.81182493083179} +{"Pretrain/Learning Rate": 3.19087954899884e-05, "Pretrain/Loss": 2.0613651275634766, "Pretrain/Loss (Raw)": 2.0230987071990967, "Pretrain/Step": 4087, "Pretrain/Step Time": 8.813480930402875} +{"Pretrain/Learning Rate": 3.190063584367661e-05, "Pretrain/Loss": 2.0618910789489746, "Pretrain/Loss (Raw)": 2.072932004928589, "Pretrain/Step": 4088, "Pretrain/Step Time": 8.805749053135514} +{"Pretrain/Learning Rate": 3.1892475401550956e-05, "Pretrain/Loss": 2.06085205078125, "Pretrain/Loss (Raw)": 1.9220373630523682, "Pretrain/Step": 4089, "Pretrain/Step Time": 8.804885648190975} +{"Pretrain/Learning Rate": 3.1884314164552576e-05, "Pretrain/Loss": 2.060220718383789, "Pretrain/Loss (Raw)": 1.9873888492584229, "Pretrain/Step": 4090, "Pretrain/Step Time": 8.813473092392087} +{"Pretrain/Learning Rate": 3.187615213362264e-05, "Pretrain/Loss": 2.0610318183898926, "Pretrain/Loss (Raw)": 2.0770301818847656, "Pretrain/Step": 4091, "Pretrain/Step Time": 8.811643172055483} +{"Pretrain/Learning Rate": 3.186798930970244e-05, "Pretrain/Loss": 2.0612101554870605, "Pretrain/Loss (Raw)": 2.1020331382751465, "Pretrain/Step": 4092, "Pretrain/Step Time": 8.804974475875497} +{"Pretrain/Learning Rate": 3.185982569373335e-05, "Pretrain/Loss": 2.062368631362915, "Pretrain/Loss (Raw)": 2.0836875438690186, "Pretrain/Step": 4093, "Pretrain/Step Time": 8.812161784619093} +{"Pretrain/Learning Rate": 3.185166128665684e-05, "Pretrain/Loss": 2.0608437061309814, "Pretrain/Loss (Raw)": 2.060914993286133, "Pretrain/Step": 4094, "Pretrain/Step Time": 8.819009531289339} +{"Pretrain/Learning Rate": 3.184349608941446e-05, "Pretrain/Loss": 2.0602359771728516, "Pretrain/Loss (Raw)": 1.9157471656799316, "Pretrain/Step": 4095, "Pretrain/Step Time": 8.818480536341667} +{"Pretrain/Learning Rate": 3.183533010294787e-05, "Pretrain/Loss": 2.0602383613586426, "Pretrain/Loss (Raw)": 2.043593168258667, "Pretrain/Step": 4096, "Pretrain/Step Time": 8.816347654908895} +{"Pretrain/Learning Rate": 3.18271633281988e-05, "Pretrain/Loss": 2.0607900619506836, "Pretrain/Loss (Raw)": 2.207183361053467, "Pretrain/Step": 4097, "Pretrain/Step Time": 8.812809187918901} +{"Pretrain/Learning Rate": 3.181899576610908e-05, "Pretrain/Loss": 2.0604960918426514, "Pretrain/Loss (Raw)": 2.1287105083465576, "Pretrain/Step": 4098, "Pretrain/Step Time": 8.81534201093018} +{"Pretrain/Learning Rate": 3.1810827417620634e-05, "Pretrain/Loss": 2.0603511333465576, "Pretrain/Loss (Raw)": 2.012390613555908, "Pretrain/Step": 4099, "Pretrain/Step Time": 8.81545152142644} +{"Pretrain/Learning Rate": 3.1802658283675486e-05, "Pretrain/Loss": 2.062948703765869, "Pretrain/Loss (Raw)": 2.3284201622009277, "Pretrain/Step": 4100, "Pretrain/Step Time": 8.815069019794464} +{"Pretrain/Learning Rate": 3.179448836521573e-05, "Pretrain/Loss": 2.0650925636291504, "Pretrain/Loss (Raw)": 2.182096242904663, "Pretrain/Step": 4101, "Pretrain/Step Time": 8.821098351851106} +{"Pretrain/Learning Rate": 3.178631766318355e-05, "Pretrain/Loss": 2.0637738704681396, "Pretrain/Loss (Raw)": 2.0029497146606445, "Pretrain/Step": 4102, "Pretrain/Step Time": 8.80772060342133} +{"Pretrain/Learning Rate": 3.177814617852124e-05, "Pretrain/Loss": 2.0649445056915283, "Pretrain/Loss (Raw)": 2.169952154159546, "Pretrain/Step": 4103, "Pretrain/Step Time": 8.814398797228932} +{"Pretrain/Learning Rate": 3.176997391217117e-05, "Pretrain/Loss": 2.0647568702697754, "Pretrain/Loss (Raw)": 2.1722469329833984, "Pretrain/Step": 4104, "Pretrain/Step Time": 8.802335426211357} +{"Pretrain/Learning Rate": 3.176180086507582e-05, "Pretrain/Loss": 2.0653514862060547, "Pretrain/Loss (Raw)": 2.1252999305725098, "Pretrain/Step": 4105, "Pretrain/Step Time": 8.801788123324513} +{"Pretrain/Learning Rate": 3.175362703817773e-05, "Pretrain/Loss": 2.0656630992889404, "Pretrain/Loss (Raw)": 2.065849781036377, "Pretrain/Step": 4106, "Pretrain/Step Time": 8.805543832480907} +{"Pretrain/Learning Rate": 3.1745452432419534e-05, "Pretrain/Loss": 2.0698609352111816, "Pretrain/Loss (Raw)": 2.501786470413208, "Pretrain/Step": 4107, "Pretrain/Step Time": 8.80349911749363} +{"Pretrain/Learning Rate": 3.1737277048743984e-05, "Pretrain/Loss": 2.069153308868408, "Pretrain/Loss (Raw)": 2.04777193069458, "Pretrain/Step": 4108, "Pretrain/Step Time": 8.804845290258527} +{"Pretrain/Learning Rate": 3.17291008880939e-05, "Pretrain/Loss": 2.0691256523132324, "Pretrain/Loss (Raw)": 2.1009013652801514, "Pretrain/Step": 4109, "Pretrain/Step Time": 8.808899028226733} +{"Pretrain/Learning Rate": 3.172092395141219e-05, "Pretrain/Loss": 2.0688676834106445, "Pretrain/Loss (Raw)": 2.008180618286133, "Pretrain/Step": 4110, "Pretrain/Step Time": 8.808622684329748} +{"Pretrain/Learning Rate": 3.171274623964186e-05, "Pretrain/Loss": 2.0684587955474854, "Pretrain/Loss (Raw)": 2.1643264293670654, "Pretrain/Step": 4111, "Pretrain/Step Time": 8.807413628324866} +{"Pretrain/Learning Rate": 3.170456775372601e-05, "Pretrain/Loss": 2.067375659942627, "Pretrain/Loss (Raw)": 2.080909013748169, "Pretrain/Step": 4112, "Pretrain/Step Time": 8.804004745557904} +{"Pretrain/Learning Rate": 3.1696388494607804e-05, "Pretrain/Loss": 2.065622329711914, "Pretrain/Loss (Raw)": 1.7522903680801392, "Pretrain/Step": 4113, "Pretrain/Step Time": 8.803740922361612} +{"Pretrain/Learning Rate": 3.168820846323053e-05, "Pretrain/Loss": 2.0658531188964844, "Pretrain/Loss (Raw)": 1.9388290643692017, "Pretrain/Step": 4114, "Pretrain/Step Time": 8.803974444046617} +{"Pretrain/Learning Rate": 3.1680027660537524e-05, "Pretrain/Loss": 2.0658373832702637, "Pretrain/Loss (Raw)": 2.2340848445892334, "Pretrain/Step": 4115, "Pretrain/Step Time": 8.815048959106207} +{"Pretrain/Learning Rate": 3.167184608747227e-05, "Pretrain/Loss": 2.065732955932617, "Pretrain/Loss (Raw)": 2.0822081565856934, "Pretrain/Step": 4116, "Pretrain/Step Time": 8.801696246489882} +{"Pretrain/Learning Rate": 3.1663663744978276e-05, "Pretrain/Loss": 2.0669121742248535, "Pretrain/Loss (Raw)": 2.1097302436828613, "Pretrain/Step": 4117, "Pretrain/Step Time": 8.802184579893947} +{"Pretrain/Learning Rate": 3.165548063399919e-05, "Pretrain/Loss": 2.066159725189209, "Pretrain/Loss (Raw)": 2.081486701965332, "Pretrain/Step": 4118, "Pretrain/Step Time": 8.801696034148335} +{"Pretrain/Learning Rate": 3.1647296755478694e-05, "Pretrain/Loss": 2.0663251876831055, "Pretrain/Loss (Raw)": 2.0857832431793213, "Pretrain/Step": 4119, "Pretrain/Step Time": 8.80054465122521} +{"Pretrain/Learning Rate": 3.163911211036063e-05, "Pretrain/Loss": 2.0667648315429688, "Pretrain/Loss (Raw)": 2.1143946647644043, "Pretrain/Step": 4120, "Pretrain/Step Time": 8.79969858750701} +{"Pretrain/Learning Rate": 3.163092669958887e-05, "Pretrain/Loss": 2.064922332763672, "Pretrain/Loss (Raw)": 2.055222749710083, "Pretrain/Step": 4121, "Pretrain/Step Time": 8.798184776678681} +{"Pretrain/Learning Rate": 3.16227405241074e-05, "Pretrain/Loss": 2.0639090538024902, "Pretrain/Loss (Raw)": 1.876825213432312, "Pretrain/Step": 4122, "Pretrain/Step Time": 8.79906084947288} +{"Pretrain/Learning Rate": 3.161455358486028e-05, "Pretrain/Loss": 2.0633296966552734, "Pretrain/Loss (Raw)": 1.9477888345718384, "Pretrain/Step": 4123, "Pretrain/Step Time": 8.79737894795835} +{"Pretrain/Learning Rate": 3.160636588279167e-05, "Pretrain/Loss": 2.0638790130615234, "Pretrain/Loss (Raw)": 2.0722057819366455, "Pretrain/Step": 4124, "Pretrain/Step Time": 8.800545213744044} +{"Pretrain/Learning Rate": 3.159817741884582e-05, "Pretrain/Loss": 2.0616064071655273, "Pretrain/Loss (Raw)": 1.8464103937149048, "Pretrain/Step": 4125, "Pretrain/Step Time": 8.797177152708173} +{"Pretrain/Learning Rate": 3.1589988193967056e-05, "Pretrain/Loss": 2.060445547103882, "Pretrain/Loss (Raw)": 1.9785640239715576, "Pretrain/Step": 4126, "Pretrain/Step Time": 8.792190263047814} +{"Pretrain/Learning Rate": 3.15817982090998e-05, "Pretrain/Loss": 2.059803009033203, "Pretrain/Loss (Raw)": 1.9356948137283325, "Pretrain/Step": 4127, "Pretrain/Step Time": 8.793940061703324} +{"Pretrain/Learning Rate": 3.157360746518857e-05, "Pretrain/Loss": 2.0599546432495117, "Pretrain/Loss (Raw)": 1.8816981315612793, "Pretrain/Step": 4128, "Pretrain/Step Time": 8.79712831787765} +{"Pretrain/Learning Rate": 3.1565415963177944e-05, "Pretrain/Loss": 2.060049295425415, "Pretrain/Loss (Raw)": 2.1215004920959473, "Pretrain/Step": 4129, "Pretrain/Step Time": 8.790270259603858} +{"Pretrain/Learning Rate": 3.1557223704012606e-05, "Pretrain/Loss": 2.059251308441162, "Pretrain/Loss (Raw)": 2.1883468627929688, "Pretrain/Step": 4130, "Pretrain/Step Time": 8.78895816206932} +{"Pretrain/Learning Rate": 3.154903068863734e-05, "Pretrain/Loss": 2.0587968826293945, "Pretrain/Loss (Raw)": 1.8439503908157349, "Pretrain/Step": 4131, "Pretrain/Step Time": 8.791572688147426} +{"Pretrain/Learning Rate": 3.154083691799699e-05, "Pretrain/Loss": 2.0594053268432617, "Pretrain/Loss (Raw)": 2.1273281574249268, "Pretrain/Step": 4132, "Pretrain/Step Time": 8.79092071019113} +{"Pretrain/Learning Rate": 3.1532642393036506e-05, "Pretrain/Loss": 2.0612845420837402, "Pretrain/Loss (Raw)": 2.1329073905944824, "Pretrain/Step": 4133, "Pretrain/Step Time": 8.79307066462934} +{"Pretrain/Learning Rate": 3.1524447114700914e-05, "Pretrain/Loss": 2.0630974769592285, "Pretrain/Loss (Raw)": 2.174929141998291, "Pretrain/Step": 4134, "Pretrain/Step Time": 8.793761556968093} +{"Pretrain/Learning Rate": 3.151625108393534e-05, "Pretrain/Loss": 2.0624704360961914, "Pretrain/Loss (Raw)": 1.902390718460083, "Pretrain/Step": 4135, "Pretrain/Step Time": 8.794109679758549} +{"Pretrain/Learning Rate": 3.150805430168499e-05, "Pretrain/Loss": 2.062331438064575, "Pretrain/Loss (Raw)": 1.9920319318771362, "Pretrain/Step": 4136, "Pretrain/Step Time": 8.796014849096537} +{"Pretrain/Learning Rate": 3.149985676889515e-05, "Pretrain/Loss": 2.061173915863037, "Pretrain/Loss (Raw)": 2.00734543800354, "Pretrain/Step": 4137, "Pretrain/Step Time": 8.793447874486446} +{"Pretrain/Learning Rate": 3.14916584865112e-05, "Pretrain/Loss": 2.061690092086792, "Pretrain/Loss (Raw)": 2.1384832859039307, "Pretrain/Step": 4138, "Pretrain/Step Time": 8.792765060439706} +{"Pretrain/Learning Rate": 3.1483459455478603e-05, "Pretrain/Loss": 2.0624289512634277, "Pretrain/Loss (Raw)": 2.06365704536438, "Pretrain/Step": 4139, "Pretrain/Step Time": 8.795207057148218} +{"Pretrain/Learning Rate": 3.147525967674291e-05, "Pretrain/Loss": 2.061662197113037, "Pretrain/Loss (Raw)": 1.891672968864441, "Pretrain/Step": 4140, "Pretrain/Step Time": 8.798018595203757} +{"Pretrain/Learning Rate": 3.146705915124976e-05, "Pretrain/Loss": 2.062399387359619, "Pretrain/Loss (Raw)": 2.150830030441284, "Pretrain/Step": 4141, "Pretrain/Step Time": 8.798053324222565} +{"Pretrain/Learning Rate": 3.145885787994487e-05, "Pretrain/Loss": 2.064523935317993, "Pretrain/Loss (Raw)": 2.2257869243621826, "Pretrain/Step": 4142, "Pretrain/Step Time": 8.793340658769011} +{"Pretrain/Learning Rate": 3.1450655863774056e-05, "Pretrain/Loss": 2.061101198196411, "Pretrain/Loss (Raw)": 1.9645615816116333, "Pretrain/Step": 4143, "Pretrain/Step Time": 8.792054738849401} +{"Pretrain/Learning Rate": 3.144245310368321e-05, "Pretrain/Loss": 2.062747001647949, "Pretrain/Loss (Raw)": 2.055943489074707, "Pretrain/Step": 4144, "Pretrain/Step Time": 8.797768007963896} +{"Pretrain/Learning Rate": 3.1434249600618315e-05, "Pretrain/Loss": 2.061028003692627, "Pretrain/Loss (Raw)": 2.0098299980163574, "Pretrain/Step": 4145, "Pretrain/Step Time": 8.796896686777472} +{"Pretrain/Learning Rate": 3.142604535552544e-05, "Pretrain/Loss": 2.0594677925109863, "Pretrain/Loss (Raw)": 1.9837507009506226, "Pretrain/Step": 4146, "Pretrain/Step Time": 8.800765715539455} +{"Pretrain/Learning Rate": 3.1417840369350735e-05, "Pretrain/Loss": 2.0608408451080322, "Pretrain/Loss (Raw)": 2.227970838546753, "Pretrain/Step": 4147, "Pretrain/Step Time": 8.794910162687302} +{"Pretrain/Learning Rate": 3.140963464304043e-05, "Pretrain/Loss": 2.0616750717163086, "Pretrain/Loss (Raw)": 2.0694215297698975, "Pretrain/Step": 4148, "Pretrain/Step Time": 8.79842822253704} +{"Pretrain/Learning Rate": 3.140142817754086e-05, "Pretrain/Loss": 2.062448501586914, "Pretrain/Loss (Raw)": 1.901535987854004, "Pretrain/Step": 4149, "Pretrain/Step Time": 8.795090587809682} +{"Pretrain/Learning Rate": 3.1393220973798425e-05, "Pretrain/Loss": 2.0631589889526367, "Pretrain/Loss (Raw)": 2.037193536758423, "Pretrain/Step": 4150, "Pretrain/Step Time": 8.785681391134858} +{"Pretrain/Learning Rate": 3.1385013032759623e-05, "Pretrain/Loss": 2.0650391578674316, "Pretrain/Loss (Raw)": 2.0861856937408447, "Pretrain/Step": 4151, "Pretrain/Step Time": 8.792831877246499} +{"Pretrain/Learning Rate": 3.137680435537104e-05, "Pretrain/Loss": 2.065178871154785, "Pretrain/Loss (Raw)": 2.0240137577056885, "Pretrain/Step": 4152, "Pretrain/Step Time": 8.790542664006352} +{"Pretrain/Learning Rate": 3.136859494257931e-05, "Pretrain/Loss": 2.063957691192627, "Pretrain/Loss (Raw)": 2.279585361480713, "Pretrain/Step": 4153, "Pretrain/Step Time": 8.795519668608904} +{"Pretrain/Learning Rate": 3.136038479533122e-05, "Pretrain/Loss": 2.0656347274780273, "Pretrain/Loss (Raw)": 2.0994114875793457, "Pretrain/Step": 4154, "Pretrain/Step Time": 8.78776447288692} +{"Pretrain/Learning Rate": 3.135217391457358e-05, "Pretrain/Loss": 2.064275026321411, "Pretrain/Loss (Raw)": 1.8728903532028198, "Pretrain/Step": 4155, "Pretrain/Step Time": 8.792013306170702} +{"Pretrain/Learning Rate": 3.1343962301253305e-05, "Pretrain/Loss": 2.0619568824768066, "Pretrain/Loss (Raw)": 1.9448283910751343, "Pretrain/Step": 4156, "Pretrain/Step Time": 8.78847922384739} +{"Pretrain/Learning Rate": 3.133574995631741e-05, "Pretrain/Loss": 2.063030481338501, "Pretrain/Loss (Raw)": 2.011183977127075, "Pretrain/Step": 4157, "Pretrain/Step Time": 8.782977504655719} +{"Pretrain/Learning Rate": 3.132753688071297e-05, "Pretrain/Loss": 2.0639560222625732, "Pretrain/Loss (Raw)": 2.113577127456665, "Pretrain/Step": 4158, "Pretrain/Step Time": 8.790772097185254} +{"Pretrain/Learning Rate": 3.1319323075387165e-05, "Pretrain/Loss": 2.0647032260894775, "Pretrain/Loss (Raw)": 2.0465617179870605, "Pretrain/Step": 4159, "Pretrain/Step Time": 8.786041371524334} +{"Pretrain/Learning Rate": 3.131110854128724e-05, "Pretrain/Loss": 2.063868761062622, "Pretrain/Loss (Raw)": 2.0403053760528564, "Pretrain/Step": 4160, "Pretrain/Step Time": 8.784496381878853} +{"Pretrain/Learning Rate": 3.130289327936055e-05, "Pretrain/Loss": 2.061785936355591, "Pretrain/Loss (Raw)": 1.9116017818450928, "Pretrain/Step": 4161, "Pretrain/Step Time": 8.786855725571513} +{"Pretrain/Learning Rate": 3.1294677290554494e-05, "Pretrain/Loss": 2.062875270843506, "Pretrain/Loss (Raw)": 2.135598659515381, "Pretrain/Step": 4162, "Pretrain/Step Time": 8.785578267648816} +{"Pretrain/Learning Rate": 3.128646057581659e-05, "Pretrain/Loss": 2.0619542598724365, "Pretrain/Loss (Raw)": 1.982008934020996, "Pretrain/Step": 4163, "Pretrain/Step Time": 8.78409818932414} +{"Pretrain/Learning Rate": 3.1278243136094436e-05, "Pretrain/Loss": 2.061217784881592, "Pretrain/Loss (Raw)": 2.1038026809692383, "Pretrain/Step": 4164, "Pretrain/Step Time": 8.77346439100802} +{"Pretrain/Learning Rate": 3.1270024972335706e-05, "Pretrain/Loss": 2.061744213104248, "Pretrain/Loss (Raw)": 2.2060303688049316, "Pretrain/Step": 4165, "Pretrain/Step Time": 8.764617277309299} +{"Pretrain/Learning Rate": 3.1261806085488144e-05, "Pretrain/Loss": 2.062955617904663, "Pretrain/Loss (Raw)": 2.1909501552581787, "Pretrain/Step": 4166, "Pretrain/Step Time": 8.77724171616137} +{"Pretrain/Learning Rate": 3.1253586476499594e-05, "Pretrain/Loss": 2.063431739807129, "Pretrain/Loss (Raw)": 2.0348122119903564, "Pretrain/Step": 4167, "Pretrain/Step Time": 8.777400314807892} +{"Pretrain/Learning Rate": 3.124536614631799e-05, "Pretrain/Loss": 2.060668706893921, "Pretrain/Loss (Raw)": 1.7478071451187134, "Pretrain/Step": 4168, "Pretrain/Step Time": 8.778888763859868} +{"Pretrain/Learning Rate": 3.123714509589133e-05, "Pretrain/Loss": 2.0583252906799316, "Pretrain/Loss (Raw)": 1.8347920179367065, "Pretrain/Step": 4169, "Pretrain/Step Time": 8.78310327604413} +{"Pretrain/Learning Rate": 3.122892332616771e-05, "Pretrain/Loss": 2.0601911544799805, "Pretrain/Loss (Raw)": 2.200423240661621, "Pretrain/Step": 4170, "Pretrain/Step Time": 8.787375889718533} +{"Pretrain/Learning Rate": 3.12207008380953e-05, "Pretrain/Loss": 2.05928635597229, "Pretrain/Loss (Raw)": 1.9794200658798218, "Pretrain/Step": 4171, "Pretrain/Step Time": 8.789030013605952} +{"Pretrain/Learning Rate": 3.121247763262235e-05, "Pretrain/Loss": 2.0615339279174805, "Pretrain/Loss (Raw)": 2.1716692447662354, "Pretrain/Step": 4172, "Pretrain/Step Time": 8.78495667874813} +{"Pretrain/Learning Rate": 3.120425371069721e-05, "Pretrain/Loss": 2.059706687927246, "Pretrain/Loss (Raw)": 1.9886648654937744, "Pretrain/Step": 4173, "Pretrain/Step Time": 8.799453001469374} +{"Pretrain/Learning Rate": 3.119602907326829e-05, "Pretrain/Loss": 2.0618810653686523, "Pretrain/Loss (Raw)": 2.287043809890747, "Pretrain/Step": 4174, "Pretrain/Step Time": 8.791976196691394} +{"Pretrain/Learning Rate": 3.118780372128411e-05, "Pretrain/Loss": 2.0615718364715576, "Pretrain/Loss (Raw)": 1.9268134832382202, "Pretrain/Step": 4175, "Pretrain/Step Time": 8.794159203767776} +{"Pretrain/Learning Rate": 3.1179577655693245e-05, "Pretrain/Loss": 2.061201572418213, "Pretrain/Loss (Raw)": 2.0632712841033936, "Pretrain/Step": 4176, "Pretrain/Step Time": 8.789082201197743} +{"Pretrain/Learning Rate": 3.1171350877444365e-05, "Pretrain/Loss": 2.0606768131256104, "Pretrain/Loss (Raw)": 1.8940767049789429, "Pretrain/Step": 4177, "Pretrain/Step Time": 8.79036514274776} +{"Pretrain/Learning Rate": 3.116312338748623e-05, "Pretrain/Loss": 2.0633366107940674, "Pretrain/Loss (Raw)": 2.406562328338623, "Pretrain/Step": 4178, "Pretrain/Step Time": 8.78771322965622} +{"Pretrain/Learning Rate": 3.115489518676765e-05, "Pretrain/Loss": 2.062748908996582, "Pretrain/Loss (Raw)": 1.7541782855987549, "Pretrain/Step": 4179, "Pretrain/Step Time": 8.78414035961032} +{"Pretrain/Learning Rate": 3.1146666276237554e-05, "Pretrain/Loss": 2.062033176422119, "Pretrain/Loss (Raw)": 2.0608153343200684, "Pretrain/Step": 4180, "Pretrain/Step Time": 8.79479057341814} +{"Pretrain/Learning Rate": 3.113843665684495e-05, "Pretrain/Loss": 2.063450813293457, "Pretrain/Loss (Raw)": 2.191801071166992, "Pretrain/Step": 4181, "Pretrain/Step Time": 8.78961070254445} +{"Pretrain/Learning Rate": 3.1130206329538905e-05, "Pretrain/Loss": 2.0642733573913574, "Pretrain/Loss (Raw)": 2.15602445602417, "Pretrain/Step": 4182, "Pretrain/Step Time": 8.789378562942147} +{"Pretrain/Learning Rate": 3.112197529526857e-05, "Pretrain/Loss": 2.063119649887085, "Pretrain/Loss (Raw)": 2.0087337493896484, "Pretrain/Step": 4183, "Pretrain/Step Time": 8.790302388370037} +{"Pretrain/Learning Rate": 3.11137435549832e-05, "Pretrain/Loss": 2.063676357269287, "Pretrain/Loss (Raw)": 2.0991013050079346, "Pretrain/Step": 4184, "Pretrain/Step Time": 8.791944714263082} +{"Pretrain/Learning Rate": 3.110551110963212e-05, "Pretrain/Loss": 2.063462018966675, "Pretrain/Loss (Raw)": 2.0306060314178467, "Pretrain/Step": 4185, "Pretrain/Step Time": 8.798517690971494} +{"Pretrain/Learning Rate": 3.109727796016472e-05, "Pretrain/Loss": 2.062549114227295, "Pretrain/Loss (Raw)": 2.089359760284424, "Pretrain/Step": 4186, "Pretrain/Step Time": 8.796558495610952} +{"Pretrain/Learning Rate": 3.10890441075305e-05, "Pretrain/Loss": 2.061338186264038, "Pretrain/Loss (Raw)": 2.053375005722046, "Pretrain/Step": 4187, "Pretrain/Step Time": 8.799073711037636} +{"Pretrain/Learning Rate": 3.108080955267902e-05, "Pretrain/Loss": 2.061685085296631, "Pretrain/Loss (Raw)": 2.1581995487213135, "Pretrain/Step": 4188, "Pretrain/Step Time": 8.800755962729454} +{"Pretrain/Learning Rate": 3.107257429655993e-05, "Pretrain/Loss": 2.061044931411743, "Pretrain/Loss (Raw)": 2.0485029220581055, "Pretrain/Step": 4189, "Pretrain/Step Time": 8.80380305275321} +{"Pretrain/Learning Rate": 3.1064338340122953e-05, "Pretrain/Loss": 2.060789108276367, "Pretrain/Loss (Raw)": 1.97005295753479, "Pretrain/Step": 4190, "Pretrain/Step Time": 8.802420085296035} +{"Pretrain/Learning Rate": 3.105610168431791e-05, "Pretrain/Loss": 2.058396816253662, "Pretrain/Loss (Raw)": 1.7491799592971802, "Pretrain/Step": 4191, "Pretrain/Step Time": 8.801854284480214} +{"Pretrain/Learning Rate": 3.1047864330094675e-05, "Pretrain/Loss": 2.0579638481140137, "Pretrain/Loss (Raw)": 1.97213613986969, "Pretrain/Step": 4192, "Pretrain/Step Time": 8.804320422932506} +{"Pretrain/Learning Rate": 3.1039626278403234e-05, "Pretrain/Loss": 2.0554873943328857, "Pretrain/Loss (Raw)": 1.8815498352050781, "Pretrain/Step": 4193, "Pretrain/Step Time": 8.801978038623929} +{"Pretrain/Learning Rate": 3.1031387530193626e-05, "Pretrain/Loss": 2.053849935531616, "Pretrain/Loss (Raw)": 1.8607059717178345, "Pretrain/Step": 4194, "Pretrain/Step Time": 8.794013997539878} +{"Pretrain/Learning Rate": 3.1023148086415984e-05, "Pretrain/Loss": 2.0550642013549805, "Pretrain/Loss (Raw)": 2.274477005004883, "Pretrain/Step": 4195, "Pretrain/Step Time": 8.798448700457811} +{"Pretrain/Learning Rate": 3.101490794802053e-05, "Pretrain/Loss": 2.0539941787719727, "Pretrain/Loss (Raw)": 1.9443570375442505, "Pretrain/Step": 4196, "Pretrain/Step Time": 8.796920521184802} +{"Pretrain/Learning Rate": 3.100666711595754e-05, "Pretrain/Loss": 2.05410099029541, "Pretrain/Loss (Raw)": 2.108501672744751, "Pretrain/Step": 4197, "Pretrain/Step Time": 8.798058008775115} +{"Pretrain/Learning Rate": 3.09984255911774e-05, "Pretrain/Loss": 2.0545287132263184, "Pretrain/Loss (Raw)": 2.022249698638916, "Pretrain/Step": 4198, "Pretrain/Step Time": 8.794729236513376} +{"Pretrain/Learning Rate": 3.099018337463056e-05, "Pretrain/Loss": 2.0537545680999756, "Pretrain/Loss (Raw)": 1.9398826360702515, "Pretrain/Step": 4199, "Pretrain/Step Time": 8.798099247738719} +{"Pretrain/Learning Rate": 3.0981940467267547e-05, "Pretrain/Loss": 2.053408622741699, "Pretrain/Loss (Raw)": 2.0622053146362305, "Pretrain/Step": 4200, "Pretrain/Step Time": 8.801334558054805} +{"Pretrain/Learning Rate": 3.097369687003896e-05, "Pretrain/Loss": 2.0560216903686523, "Pretrain/Loss (Raw)": 2.3563408851623535, "Pretrain/Step": 4201, "Pretrain/Step Time": 8.790586275979877} +{"Pretrain/Learning Rate": 3.096545258389551e-05, "Pretrain/Loss": 2.0574111938476562, "Pretrain/Loss (Raw)": 2.1010119915008545, "Pretrain/Step": 4202, "Pretrain/Step Time": 8.789876457303762} +{"Pretrain/Learning Rate": 3.0957207609787945e-05, "Pretrain/Loss": 2.0555291175842285, "Pretrain/Loss (Raw)": 2.110466480255127, "Pretrain/Step": 4203, "Pretrain/Step Time": 8.793108006939292} +{"Pretrain/Learning Rate": 3.094896194866714e-05, "Pretrain/Loss": 2.0572755336761475, "Pretrain/Loss (Raw)": 2.037302255630493, "Pretrain/Step": 4204, "Pretrain/Step Time": 8.790025452151895} +{"Pretrain/Learning Rate": 3.094071560148401e-05, "Pretrain/Loss": 2.055990695953369, "Pretrain/Loss (Raw)": 1.9709779024124146, "Pretrain/Step": 4205, "Pretrain/Step Time": 8.789936397224665} +{"Pretrain/Learning Rate": 3.093246856918956e-05, "Pretrain/Loss": 2.056673049926758, "Pretrain/Loss (Raw)": 2.343177318572998, "Pretrain/Step": 4206, "Pretrain/Step Time": 8.785376081243157} +{"Pretrain/Learning Rate": 3.092422085273488e-05, "Pretrain/Loss": 2.0555877685546875, "Pretrain/Loss (Raw)": 2.0169761180877686, "Pretrain/Step": 4207, "Pretrain/Step Time": 8.788590298965573} +{"Pretrain/Learning Rate": 3.091597245307114e-05, "Pretrain/Loss": 2.055253505706787, "Pretrain/Loss (Raw)": 2.0982887744903564, "Pretrain/Step": 4208, "Pretrain/Step Time": 8.790526455268264} +{"Pretrain/Learning Rate": 3.0907723371149575e-05, "Pretrain/Loss": 2.055610179901123, "Pretrain/Loss (Raw)": 2.0475547313690186, "Pretrain/Step": 4209, "Pretrain/Step Time": 8.794794745743275} +{"Pretrain/Learning Rate": 3.0899473607921513e-05, "Pretrain/Loss": 2.0569801330566406, "Pretrain/Loss (Raw)": 1.9733856916427612, "Pretrain/Step": 4210, "Pretrain/Step Time": 8.794723931699991} +{"Pretrain/Learning Rate": 3.0891223164338354e-05, "Pretrain/Loss": 2.0546045303344727, "Pretrain/Loss (Raw)": 1.9166395664215088, "Pretrain/Step": 4211, "Pretrain/Step Time": 8.792209247127175} +{"Pretrain/Learning Rate": 3.0882972041351585e-05, "Pretrain/Loss": 2.0539278984069824, "Pretrain/Loss (Raw)": 1.8548346757888794, "Pretrain/Step": 4212, "Pretrain/Step Time": 8.79108551889658} +{"Pretrain/Learning Rate": 3.0874720239912744e-05, "Pretrain/Loss": 2.0533907413482666, "Pretrain/Loss (Raw)": 2.055506467819214, "Pretrain/Step": 4213, "Pretrain/Step Time": 8.799167238175869} +{"Pretrain/Learning Rate": 3.0866467760973495e-05, "Pretrain/Loss": 2.0525145530700684, "Pretrain/Loss (Raw)": 2.027494192123413, "Pretrain/Step": 4214, "Pretrain/Step Time": 8.802392061799765} +{"Pretrain/Learning Rate": 3.0858214605485545e-05, "Pretrain/Loss": 2.051593780517578, "Pretrain/Loss (Raw)": 1.9052209854125977, "Pretrain/Step": 4215, "Pretrain/Step Time": 8.801455803215504} +{"Pretrain/Learning Rate": 3.0849960774400667e-05, "Pretrain/Loss": 2.0518078804016113, "Pretrain/Loss (Raw)": 2.1003406047821045, "Pretrain/Step": 4216, "Pretrain/Step Time": 8.805270971730351} +{"Pretrain/Learning Rate": 3.0841706268670756e-05, "Pretrain/Loss": 2.052394390106201, "Pretrain/Loss (Raw)": 1.9971550703048706, "Pretrain/Step": 4217, "Pretrain/Step Time": 8.806144526228309} +{"Pretrain/Learning Rate": 3.083345108924775e-05, "Pretrain/Loss": 2.0505828857421875, "Pretrain/Loss (Raw)": 1.7554941177368164, "Pretrain/Step": 4218, "Pretrain/Step Time": 8.797800280153751} +{"Pretrain/Learning Rate": 3.082519523708368e-05, "Pretrain/Loss": 2.048828125, "Pretrain/Loss (Raw)": 1.8524224758148193, "Pretrain/Step": 4219, "Pretrain/Step Time": 8.80006886832416} +{"Pretrain/Learning Rate": 3.081693871313064e-05, "Pretrain/Loss": 2.048403739929199, "Pretrain/Loss (Raw)": 2.0476906299591064, "Pretrain/Step": 4220, "Pretrain/Step Time": 8.803563052788377} +{"Pretrain/Learning Rate": 3.080868151834082e-05, "Pretrain/Loss": 2.048891544342041, "Pretrain/Loss (Raw)": 2.1461222171783447, "Pretrain/Step": 4221, "Pretrain/Step Time": 8.797368286177516} +{"Pretrain/Learning Rate": 3.080042365366648e-05, "Pretrain/Loss": 2.047882556915283, "Pretrain/Loss (Raw)": 1.9317739009857178, "Pretrain/Step": 4222, "Pretrain/Step Time": 8.791301535442472} +{"Pretrain/Learning Rate": 3.079216512005994e-05, "Pretrain/Loss": 2.0491690635681152, "Pretrain/Loss (Raw)": 2.0804479122161865, "Pretrain/Step": 4223, "Pretrain/Step Time": 8.793589897453785} +{"Pretrain/Learning Rate": 3.078390591847363e-05, "Pretrain/Loss": 2.050191879272461, "Pretrain/Loss (Raw)": 2.1745150089263916, "Pretrain/Step": 4224, "Pretrain/Step Time": 8.791042005643249} +{"Pretrain/Learning Rate": 3.077564604986004e-05, "Pretrain/Loss": 2.0485007762908936, "Pretrain/Loss (Raw)": 1.990693211555481, "Pretrain/Step": 4225, "Pretrain/Step Time": 8.79503014869988} +{"Pretrain/Learning Rate": 3.076738551517173e-05, "Pretrain/Loss": 2.046088695526123, "Pretrain/Loss (Raw)": 1.8199808597564697, "Pretrain/Step": 4226, "Pretrain/Step Time": 8.794793514534831} +{"Pretrain/Learning Rate": 3.0759124315361344e-05, "Pretrain/Loss": 2.04797101020813, "Pretrain/Loss (Raw)": 2.253302812576294, "Pretrain/Step": 4227, "Pretrain/Step Time": 8.791604539379478} +{"Pretrain/Learning Rate": 3.07508624513816e-05, "Pretrain/Loss": 2.044503688812256, "Pretrain/Loss (Raw)": 1.8846231698989868, "Pretrain/Step": 4228, "Pretrain/Step Time": 8.795878140255809} +{"Pretrain/Learning Rate": 3.0742599924185306e-05, "Pretrain/Loss": 2.0431103706359863, "Pretrain/Loss (Raw)": 2.003708839416504, "Pretrain/Step": 4229, "Pretrain/Step Time": 8.792003212496638} +{"Pretrain/Learning Rate": 3.073433673472533e-05, "Pretrain/Loss": 2.0432088375091553, "Pretrain/Loss (Raw)": 2.0155837535858154, "Pretrain/Step": 4230, "Pretrain/Step Time": 8.799050904810429} +{"Pretrain/Learning Rate": 3.072607288395461e-05, "Pretrain/Loss": 2.0443549156188965, "Pretrain/Loss (Raw)": 2.3166580200195312, "Pretrain/Step": 4231, "Pretrain/Step Time": 8.795182598754764} +{"Pretrain/Learning Rate": 3.071780837282619e-05, "Pretrain/Loss": 2.0418972969055176, "Pretrain/Loss (Raw)": 1.8576745986938477, "Pretrain/Step": 4232, "Pretrain/Step Time": 8.797773806378245} +{"Pretrain/Learning Rate": 3.0709543202293164e-05, "Pretrain/Loss": 2.041718006134033, "Pretrain/Loss (Raw)": 2.1023216247558594, "Pretrain/Step": 4233, "Pretrain/Step Time": 8.805715767666698} +{"Pretrain/Learning Rate": 3.070127737330871e-05, "Pretrain/Loss": 2.041353702545166, "Pretrain/Loss (Raw)": 2.0192370414733887, "Pretrain/Step": 4234, "Pretrain/Step Time": 8.807219203561544} +{"Pretrain/Learning Rate": 3.069301088682609e-05, "Pretrain/Loss": 2.0362610816955566, "Pretrain/Loss (Raw)": 1.8499252796173096, "Pretrain/Step": 4235, "Pretrain/Step Time": 8.80981570482254} +{"Pretrain/Learning Rate": 3.068474374379863e-05, "Pretrain/Loss": 2.0354652404785156, "Pretrain/Loss (Raw)": 1.9459307193756104, "Pretrain/Step": 4236, "Pretrain/Step Time": 8.806106293573976} +{"Pretrain/Learning Rate": 3.067647594517972e-05, "Pretrain/Loss": 2.0346546173095703, "Pretrain/Loss (Raw)": 1.99709153175354, "Pretrain/Step": 4237, "Pretrain/Step Time": 8.798895126208663} +{"Pretrain/Learning Rate": 3.0668207491922866e-05, "Pretrain/Loss": 2.0341081619262695, "Pretrain/Loss (Raw)": 1.9382754564285278, "Pretrain/Step": 4238, "Pretrain/Step Time": 8.800405219197273} +{"Pretrain/Learning Rate": 3.0659938384981616e-05, "Pretrain/Loss": 2.032515048980713, "Pretrain/Loss (Raw)": 1.9603986740112305, "Pretrain/Step": 4239, "Pretrain/Step Time": 8.79776943847537} +{"Pretrain/Learning Rate": 3.0651668625309594e-05, "Pretrain/Loss": 2.0331406593322754, "Pretrain/Loss (Raw)": 2.1609888076782227, "Pretrain/Step": 4240, "Pretrain/Step Time": 8.795652261003852} +{"Pretrain/Learning Rate": 3.0643398213860525e-05, "Pretrain/Loss": 2.0333664417266846, "Pretrain/Loss (Raw)": 1.78117835521698, "Pretrain/Step": 4241, "Pretrain/Step Time": 8.800823267549276} +{"Pretrain/Learning Rate": 3.0635127151588175e-05, "Pretrain/Loss": 2.035067081451416, "Pretrain/Loss (Raw)": 2.156527280807495, "Pretrain/Step": 4242, "Pretrain/Step Time": 8.798255866393447} +{"Pretrain/Learning Rate": 3.0626855439446405e-05, "Pretrain/Loss": 2.0334439277648926, "Pretrain/Loss (Raw)": 2.0262975692749023, "Pretrain/Step": 4243, "Pretrain/Step Time": 8.788444600999355} +{"Pretrain/Learning Rate": 3.061858307838915e-05, "Pretrain/Loss": 2.034147262573242, "Pretrain/Loss (Raw)": 2.172246217727661, "Pretrain/Step": 4244, "Pretrain/Step Time": 8.789127919822931} +{"Pretrain/Learning Rate": 3.061031006937043e-05, "Pretrain/Loss": 2.034186840057373, "Pretrain/Loss (Raw)": 2.114802122116089, "Pretrain/Step": 4245, "Pretrain/Step Time": 8.788196004927158} +{"Pretrain/Learning Rate": 3.060203641334431e-05, "Pretrain/Loss": 2.0327706336975098, "Pretrain/Loss (Raw)": 1.9001846313476562, "Pretrain/Step": 4246, "Pretrain/Step Time": 8.795308006927371} +{"Pretrain/Learning Rate": 3.059376211126495e-05, "Pretrain/Loss": 2.032750129699707, "Pretrain/Loss (Raw)": 2.083170175552368, "Pretrain/Step": 4247, "Pretrain/Step Time": 8.793115943670273} +{"Pretrain/Learning Rate": 3.058548716408658e-05, "Pretrain/Loss": 2.0310282707214355, "Pretrain/Loss (Raw)": 1.8940337896347046, "Pretrain/Step": 4248, "Pretrain/Step Time": 8.795067118480802} +{"Pretrain/Learning Rate": 3.057721157276352e-05, "Pretrain/Loss": 2.029688835144043, "Pretrain/Loss (Raw)": 1.8837381601333618, "Pretrain/Step": 4249, "Pretrain/Step Time": 8.796672102063894} +{"Pretrain/Learning Rate": 3.056893533825014e-05, "Pretrain/Loss": 2.030822277069092, "Pretrain/Loss (Raw)": 2.0219104290008545, "Pretrain/Step": 4250, "Pretrain/Step Time": 8.8026277218014} +{"Pretrain/Learning Rate": 3.056065846150089e-05, "Pretrain/Loss": 2.0320167541503906, "Pretrain/Loss (Raw)": 2.10071063041687, "Pretrain/Step": 4251, "Pretrain/Step Time": 8.793481977656484} +{"Pretrain/Learning Rate": 3.0552380943470306e-05, "Pretrain/Loss": 2.0325851440429688, "Pretrain/Loss (Raw)": 2.1449246406555176, "Pretrain/Step": 4252, "Pretrain/Step Time": 8.795624980702996} +{"Pretrain/Learning Rate": 3.054410278511299e-05, "Pretrain/Loss": 2.035581350326538, "Pretrain/Loss (Raw)": 2.2299349308013916, "Pretrain/Step": 4253, "Pretrain/Step Time": 8.795537689700723} +{"Pretrain/Learning Rate": 3.053582398738362e-05, "Pretrain/Loss": 2.0350255966186523, "Pretrain/Loss (Raw)": 1.9074509143829346, "Pretrain/Step": 4254, "Pretrain/Step Time": 8.7941365968436} +{"Pretrain/Learning Rate": 3.052754455123693e-05, "Pretrain/Loss": 2.035933256149292, "Pretrain/Loss (Raw)": 2.051851511001587, "Pretrain/Step": 4255, "Pretrain/Step Time": 8.793137578293681} +{"Pretrain/Learning Rate": 3.051926447762776e-05, "Pretrain/Loss": 2.03886079788208, "Pretrain/Loss (Raw)": 2.256418228149414, "Pretrain/Step": 4256, "Pretrain/Step Time": 8.794743191450834} +{"Pretrain/Learning Rate": 3.0510983767511007e-05, "Pretrain/Loss": 2.038438558578491, "Pretrain/Loss (Raw)": 2.0674679279327393, "Pretrain/Step": 4257, "Pretrain/Step Time": 8.806049920618534} +{"Pretrain/Learning Rate": 3.050270242184164e-05, "Pretrain/Loss": 2.037341833114624, "Pretrain/Loss (Raw)": 2.0479652881622314, "Pretrain/Step": 4258, "Pretrain/Step Time": 8.80929691158235} +{"Pretrain/Learning Rate": 3.049442044157469e-05, "Pretrain/Loss": 2.039830207824707, "Pretrain/Loss (Raw)": 2.1624510288238525, "Pretrain/Step": 4259, "Pretrain/Step Time": 8.80517897196114} +{"Pretrain/Learning Rate": 3.0486137827665296e-05, "Pretrain/Loss": 2.0388827323913574, "Pretrain/Loss (Raw)": 2.006047010421753, "Pretrain/Step": 4260, "Pretrain/Step Time": 8.803987680003047} +{"Pretrain/Learning Rate": 3.0477854581068626e-05, "Pretrain/Loss": 2.038604736328125, "Pretrain/Loss (Raw)": 2.097348213195801, "Pretrain/Step": 4261, "Pretrain/Step Time": 8.809264186769724} +{"Pretrain/Learning Rate": 3.0469570702739958e-05, "Pretrain/Loss": 2.038316249847412, "Pretrain/Loss (Raw)": 2.138023853302002, "Pretrain/Step": 4262, "Pretrain/Step Time": 8.805926343426108} +{"Pretrain/Learning Rate": 3.0461286193634626e-05, "Pretrain/Loss": 2.039708375930786, "Pretrain/Loss (Raw)": 2.080552101135254, "Pretrain/Step": 4263, "Pretrain/Step Time": 8.80975461192429} +{"Pretrain/Learning Rate": 3.045300105470803e-05, "Pretrain/Loss": 2.039970874786377, "Pretrain/Loss (Raw)": 2.025644063949585, "Pretrain/Step": 4264, "Pretrain/Step Time": 8.812338799238205} +{"Pretrain/Learning Rate": 3.0444715286915658e-05, "Pretrain/Loss": 2.040402412414551, "Pretrain/Loss (Raw)": 2.062587022781372, "Pretrain/Step": 4265, "Pretrain/Step Time": 8.812300423160195} +{"Pretrain/Learning Rate": 3.0436428891213063e-05, "Pretrain/Loss": 2.03947114944458, "Pretrain/Loss (Raw)": 2.0192711353302, "Pretrain/Step": 4266, "Pretrain/Step Time": 8.812460975721478} +{"Pretrain/Learning Rate": 3.0428141868555875e-05, "Pretrain/Loss": 2.0393221378326416, "Pretrain/Loss (Raw)": 2.0445783138275146, "Pretrain/Step": 4267, "Pretrain/Step Time": 8.808759482577443} +{"Pretrain/Learning Rate": 3.0419854219899786e-05, "Pretrain/Loss": 2.040530204772949, "Pretrain/Loss (Raw)": 2.046315908432007, "Pretrain/Step": 4268, "Pretrain/Step Time": 8.806725900620222} +{"Pretrain/Learning Rate": 3.041156594620057e-05, "Pretrain/Loss": 2.039816379547119, "Pretrain/Loss (Raw)": 2.0594515800476074, "Pretrain/Step": 4269, "Pretrain/Step Time": 8.802480148151517} +{"Pretrain/Learning Rate": 3.0403277048414063e-05, "Pretrain/Loss": 2.0384914875030518, "Pretrain/Loss (Raw)": 2.0562098026275635, "Pretrain/Step": 4270, "Pretrain/Step Time": 8.808453632518649} +{"Pretrain/Learning Rate": 3.0394987527496192e-05, "Pretrain/Loss": 2.040095806121826, "Pretrain/Loss (Raw)": 2.16989803314209, "Pretrain/Step": 4271, "Pretrain/Step Time": 8.80663225799799} +{"Pretrain/Learning Rate": 3.0386697384402935e-05, "Pretrain/Loss": 2.0387659072875977, "Pretrain/Loss (Raw)": 1.885715126991272, "Pretrain/Step": 4272, "Pretrain/Step Time": 8.806909024715424} +{"Pretrain/Learning Rate": 3.0378406620090354e-05, "Pretrain/Loss": 2.0385172367095947, "Pretrain/Loss (Raw)": 1.9780255556106567, "Pretrain/Step": 4273, "Pretrain/Step Time": 8.811447212472558} +{"Pretrain/Learning Rate": 3.0370115235514574e-05, "Pretrain/Loss": 2.0382742881774902, "Pretrain/Loss (Raw)": 1.9526349306106567, "Pretrain/Step": 4274, "Pretrain/Step Time": 8.811857283115387} +{"Pretrain/Learning Rate": 3.036182323163181e-05, "Pretrain/Loss": 2.0372469425201416, "Pretrain/Loss (Raw)": 2.096463918685913, "Pretrain/Step": 4275, "Pretrain/Step Time": 8.808023827150464} +{"Pretrain/Learning Rate": 3.0353530609398313e-05, "Pretrain/Loss": 2.037614345550537, "Pretrain/Loss (Raw)": 2.116443634033203, "Pretrain/Step": 4276, "Pretrain/Step Time": 8.799094796180725} +{"Pretrain/Learning Rate": 3.0345237369770448e-05, "Pretrain/Loss": 2.037036418914795, "Pretrain/Loss (Raw)": 1.8275738954544067, "Pretrain/Step": 4277, "Pretrain/Step Time": 8.80447307229042} +{"Pretrain/Learning Rate": 3.0336943513704613e-05, "Pretrain/Loss": 2.0383222103118896, "Pretrain/Loss (Raw)": 2.2017951011657715, "Pretrain/Step": 4278, "Pretrain/Step Time": 8.802549893036485} +{"Pretrain/Learning Rate": 3.0328649042157315e-05, "Pretrain/Loss": 2.0379998683929443, "Pretrain/Loss (Raw)": 2.0449092388153076, "Pretrain/Step": 4279, "Pretrain/Step Time": 8.806546308100224} +{"Pretrain/Learning Rate": 3.0320353956085095e-05, "Pretrain/Loss": 2.0378637313842773, "Pretrain/Loss (Raw)": 2.0065953731536865, "Pretrain/Step": 4280, "Pretrain/Step Time": 8.80745030939579} +{"Pretrain/Learning Rate": 3.0312058256444587e-05, "Pretrain/Loss": 2.0376126766204834, "Pretrain/Loss (Raw)": 2.2474441528320312, "Pretrain/Step": 4281, "Pretrain/Step Time": 8.802664497867227} +{"Pretrain/Learning Rate": 3.0303761944192488e-05, "Pretrain/Loss": 2.037036180496216, "Pretrain/Loss (Raw)": 2.0256261825561523, "Pretrain/Step": 4282, "Pretrain/Step Time": 8.805874526500702} +{"Pretrain/Learning Rate": 3.0295465020285567e-05, "Pretrain/Loss": 2.039180278778076, "Pretrain/Loss (Raw)": 2.147329568862915, "Pretrain/Step": 4283, "Pretrain/Step Time": 8.80202803015709} +{"Pretrain/Learning Rate": 3.0287167485680672e-05, "Pretrain/Loss": 2.0401558876037598, "Pretrain/Loss (Raw)": 2.069707155227661, "Pretrain/Step": 4284, "Pretrain/Step Time": 8.803977595642209} +{"Pretrain/Learning Rate": 3.0278869341334702e-05, "Pretrain/Loss": 2.04060697555542, "Pretrain/Loss (Raw)": 2.068927764892578, "Pretrain/Step": 4285, "Pretrain/Step Time": 8.802220759913325} +{"Pretrain/Learning Rate": 3.0270570588204655e-05, "Pretrain/Loss": 2.039778709411621, "Pretrain/Loss (Raw)": 2.0075249671936035, "Pretrain/Step": 4286, "Pretrain/Step Time": 8.801946764811873} +{"Pretrain/Learning Rate": 3.0262271227247563e-05, "Pretrain/Loss": 2.040109395980835, "Pretrain/Loss (Raw)": 2.088918447494507, "Pretrain/Step": 4287, "Pretrain/Step Time": 8.802191361784935} +{"Pretrain/Learning Rate": 3.025397125942056e-05, "Pretrain/Loss": 2.0382156372070312, "Pretrain/Loss (Raw)": 1.7978748083114624, "Pretrain/Step": 4288, "Pretrain/Step Time": 8.804671596735716} +{"Pretrain/Learning Rate": 3.0245670685680833e-05, "Pretrain/Loss": 2.038764476776123, "Pretrain/Loss (Raw)": 1.9818695783615112, "Pretrain/Step": 4289, "Pretrain/Step Time": 8.806357610970736} +{"Pretrain/Learning Rate": 3.0237369506985646e-05, "Pretrain/Loss": 2.037517547607422, "Pretrain/Loss (Raw)": 1.9760092496871948, "Pretrain/Step": 4290, "Pretrain/Step Time": 8.811550060287118} +{"Pretrain/Learning Rate": 3.022906772429232e-05, "Pretrain/Loss": 2.0382285118103027, "Pretrain/Loss (Raw)": 2.0730016231536865, "Pretrain/Step": 4291, "Pretrain/Step Time": 8.812771961092949} +{"Pretrain/Learning Rate": 3.0220765338558278e-05, "Pretrain/Loss": 2.036402463912964, "Pretrain/Loss (Raw)": 1.8700724840164185, "Pretrain/Step": 4292, "Pretrain/Step Time": 8.809598132967949} +{"Pretrain/Learning Rate": 3.021246235074096e-05, "Pretrain/Loss": 2.035115957260132, "Pretrain/Loss (Raw)": 2.041358709335327, "Pretrain/Step": 4293, "Pretrain/Step Time": 8.81986203044653} +{"Pretrain/Learning Rate": 3.0204158761797936e-05, "Pretrain/Loss": 2.0349795818328857, "Pretrain/Loss (Raw)": 2.1734793186187744, "Pretrain/Step": 4294, "Pretrain/Step Time": 8.811598455533385} +{"Pretrain/Learning Rate": 3.0195854572686793e-05, "Pretrain/Loss": 2.034014940261841, "Pretrain/Loss (Raw)": 1.9113572835922241, "Pretrain/Step": 4295, "Pretrain/Step Time": 8.816162066534162} +{"Pretrain/Learning Rate": 3.0187549784365214e-05, "Pretrain/Loss": 2.036409378051758, "Pretrain/Loss (Raw)": 2.054290771484375, "Pretrain/Step": 4296, "Pretrain/Step Time": 8.81264995597303} +{"Pretrain/Learning Rate": 3.0179244397790956e-05, "Pretrain/Loss": 2.039109230041504, "Pretrain/Loss (Raw)": 2.1803648471832275, "Pretrain/Step": 4297, "Pretrain/Step Time": 8.812908021733165} +{"Pretrain/Learning Rate": 3.017093841392183e-05, "Pretrain/Loss": 2.0390729904174805, "Pretrain/Loss (Raw)": 2.195783853530884, "Pretrain/Step": 4298, "Pretrain/Step Time": 8.809811538085341} +{"Pretrain/Learning Rate": 3.0162631833715715e-05, "Pretrain/Loss": 2.0392355918884277, "Pretrain/Loss (Raw)": 2.0002548694610596, "Pretrain/Step": 4299, "Pretrain/Step Time": 8.808715419843793} +{"Pretrain/Learning Rate": 3.0154324658130572e-05, "Pretrain/Loss": 2.0404927730560303, "Pretrain/Loss (Raw)": 2.332566738128662, "Pretrain/Step": 4300, "Pretrain/Step Time": 8.806517334654927} +{"Pretrain/Learning Rate": 3.0146016888124423e-05, "Pretrain/Loss": 2.041407585144043, "Pretrain/Loss (Raw)": 2.105760097503662, "Pretrain/Step": 4301, "Pretrain/Step Time": 8.804711433127522} +{"Pretrain/Learning Rate": 3.013770852465535e-05, "Pretrain/Loss": 2.038818836212158, "Pretrain/Loss (Raw)": 1.9556794166564941, "Pretrain/Step": 4302, "Pretrain/Step Time": 8.80342474207282} +{"Pretrain/Learning Rate": 3.0129399568681533e-05, "Pretrain/Loss": 2.039508819580078, "Pretrain/Loss (Raw)": 2.015150547027588, "Pretrain/Step": 4303, "Pretrain/Step Time": 8.807828785851598} +{"Pretrain/Learning Rate": 3.0121090021161175e-05, "Pretrain/Loss": 2.039216995239258, "Pretrain/Loss (Raw)": 2.0259182453155518, "Pretrain/Step": 4304, "Pretrain/Step Time": 8.80891178175807} +{"Pretrain/Learning Rate": 3.0112779883052593e-05, "Pretrain/Loss": 2.0384714603424072, "Pretrain/Loss (Raw)": 1.7986246347427368, "Pretrain/Step": 4305, "Pretrain/Step Time": 8.810349002480507} +{"Pretrain/Learning Rate": 3.010446915531414e-05, "Pretrain/Loss": 2.0348615646362305, "Pretrain/Loss (Raw)": 1.944501280784607, "Pretrain/Step": 4306, "Pretrain/Step Time": 8.808617873117328} +{"Pretrain/Learning Rate": 3.0096157838904247e-05, "Pretrain/Loss": 2.037257194519043, "Pretrain/Loss (Raw)": 2.060819149017334, "Pretrain/Step": 4307, "Pretrain/Step Time": 8.80974780768156} +{"Pretrain/Learning Rate": 3.0087845934781424e-05, "Pretrain/Loss": 2.037396192550659, "Pretrain/Loss (Raw)": 2.078617572784424, "Pretrain/Step": 4308, "Pretrain/Step Time": 8.810760628432035} +{"Pretrain/Learning Rate": 3.0079533443904227e-05, "Pretrain/Loss": 2.0374696254730225, "Pretrain/Loss (Raw)": 2.201193332672119, "Pretrain/Step": 4309, "Pretrain/Step Time": 8.808742156252265} +{"Pretrain/Learning Rate": 3.0071220367231306e-05, "Pretrain/Loss": 2.036407470703125, "Pretrain/Loss (Raw)": 2.020045518875122, "Pretrain/Step": 4310, "Pretrain/Step Time": 8.812065655365586} +{"Pretrain/Learning Rate": 3.006290670572135e-05, "Pretrain/Loss": 2.0373263359069824, "Pretrain/Loss (Raw)": 2.1263678073883057, "Pretrain/Step": 4311, "Pretrain/Step Time": 8.813322512432933} +{"Pretrain/Learning Rate": 3.0054592460333137e-05, "Pretrain/Loss": 2.037126302719116, "Pretrain/Loss (Raw)": 2.0735085010528564, "Pretrain/Step": 4312, "Pretrain/Step Time": 8.814054932445288} +{"Pretrain/Learning Rate": 3.00462776320255e-05, "Pretrain/Loss": 2.037907600402832, "Pretrain/Loss (Raw)": 2.130584239959717, "Pretrain/Step": 4313, "Pretrain/Step Time": 8.810013396665454} +{"Pretrain/Learning Rate": 3.0037962221757354e-05, "Pretrain/Loss": 2.0381758213043213, "Pretrain/Loss (Raw)": 2.1237034797668457, "Pretrain/Step": 4314, "Pretrain/Step Time": 8.815218115225434} +{"Pretrain/Learning Rate": 3.0029646230487657e-05, "Pretrain/Loss": 2.037914991378784, "Pretrain/Loss (Raw)": 2.019987106323242, "Pretrain/Step": 4315, "Pretrain/Step Time": 8.803682941943407} +{"Pretrain/Learning Rate": 3.002132965917547e-05, "Pretrain/Loss": 2.0391499996185303, "Pretrain/Loss (Raw)": 2.3162989616394043, "Pretrain/Step": 4316, "Pretrain/Step Time": 8.804255230352283} +{"Pretrain/Learning Rate": 3.001301250877987e-05, "Pretrain/Loss": 2.0401859283447266, "Pretrain/Loss (Raw)": 2.1810972690582275, "Pretrain/Step": 4317, "Pretrain/Step Time": 8.799798231571913} +{"Pretrain/Learning Rate": 3.000469478026005e-05, "Pretrain/Loss": 2.0409531593322754, "Pretrain/Loss (Raw)": 2.0682685375213623, "Pretrain/Step": 4318, "Pretrain/Step Time": 8.797639973461628} +{"Pretrain/Learning Rate": 2.9996376474575244e-05, "Pretrain/Loss": 2.043256998062134, "Pretrain/Loss (Raw)": 2.0440640449523926, "Pretrain/Step": 4319, "Pretrain/Step Time": 8.796116389334202} +{"Pretrain/Learning Rate": 2.9988057592684766e-05, "Pretrain/Loss": 2.042496681213379, "Pretrain/Loss (Raw)": 1.874841332435608, "Pretrain/Step": 4320, "Pretrain/Step Time": 8.79635040462017} +{"Pretrain/Learning Rate": 2.9979738135547973e-05, "Pretrain/Loss": 2.0448200702667236, "Pretrain/Loss (Raw)": 2.178915500640869, "Pretrain/Step": 4321, "Pretrain/Step Time": 8.79976099357009} +{"Pretrain/Learning Rate": 2.9971418104124322e-05, "Pretrain/Loss": 2.0459775924682617, "Pretrain/Loss (Raw)": 2.0088493824005127, "Pretrain/Step": 4322, "Pretrain/Step Time": 8.792349832132459} +{"Pretrain/Learning Rate": 2.9963097499373312e-05, "Pretrain/Loss": 2.0442042350769043, "Pretrain/Loss (Raw)": 2.0474934577941895, "Pretrain/Step": 4323, "Pretrain/Step Time": 8.789007952436805} +{"Pretrain/Learning Rate": 2.9954776322254495e-05, "Pretrain/Loss": 2.0457441806793213, "Pretrain/Loss (Raw)": 2.1414759159088135, "Pretrain/Step": 4324, "Pretrain/Step Time": 8.787049878388643} +{"Pretrain/Learning Rate": 2.994645457372754e-05, "Pretrain/Loss": 2.044414758682251, "Pretrain/Loss (Raw)": 1.9383395910263062, "Pretrain/Step": 4325, "Pretrain/Step Time": 8.784064186736941} +{"Pretrain/Learning Rate": 2.9938132254752126e-05, "Pretrain/Loss": 2.04396390914917, "Pretrain/Loss (Raw)": 1.964544653892517, "Pretrain/Step": 4326, "Pretrain/Step Time": 8.788760881870985} +{"Pretrain/Learning Rate": 2.9929809366288035e-05, "Pretrain/Loss": 2.0452957153320312, "Pretrain/Loss (Raw)": 2.1103649139404297, "Pretrain/Step": 4327, "Pretrain/Step Time": 8.785358237102628} +{"Pretrain/Learning Rate": 2.99214859092951e-05, "Pretrain/Loss": 2.0451040267944336, "Pretrain/Loss (Raw)": 2.0376594066619873, "Pretrain/Step": 4328, "Pretrain/Step Time": 8.780026962980628} +{"Pretrain/Learning Rate": 2.9913161884733215e-05, "Pretrain/Loss": 2.0433225631713867, "Pretrain/Loss (Raw)": 2.1283040046691895, "Pretrain/Step": 4329, "Pretrain/Step Time": 8.786652339622378} +{"Pretrain/Learning Rate": 2.9904837293562348e-05, "Pretrain/Loss": 2.043302059173584, "Pretrain/Loss (Raw)": 2.098416566848755, "Pretrain/Step": 4330, "Pretrain/Step Time": 8.78754834830761} +{"Pretrain/Learning Rate": 2.989651213674254e-05, "Pretrain/Loss": 2.0422773361206055, "Pretrain/Loss (Raw)": 1.9792770147323608, "Pretrain/Step": 4331, "Pretrain/Step Time": 8.78624825924635} +{"Pretrain/Learning Rate": 2.988818641523387e-05, "Pretrain/Loss": 2.044156551361084, "Pretrain/Loss (Raw)": 2.2778427600860596, "Pretrain/Step": 4332, "Pretrain/Step Time": 8.786882204934955} +{"Pretrain/Learning Rate": 2.9879860129996517e-05, "Pretrain/Loss": 2.046058416366577, "Pretrain/Loss (Raw)": 2.214419364929199, "Pretrain/Step": 4333, "Pretrain/Step Time": 8.789978748187423} +{"Pretrain/Learning Rate": 2.9871533281990692e-05, "Pretrain/Loss": 2.043649196624756, "Pretrain/Loss (Raw)": 2.0348055362701416, "Pretrain/Step": 4334, "Pretrain/Step Time": 8.791208952665329} +{"Pretrain/Learning Rate": 2.9863205872176703e-05, "Pretrain/Loss": 2.045485496520996, "Pretrain/Loss (Raw)": 2.2520227432250977, "Pretrain/Step": 4335, "Pretrain/Step Time": 8.781744360923767} +{"Pretrain/Learning Rate": 2.9854877901514884e-05, "Pretrain/Loss": 2.0457205772399902, "Pretrain/Loss (Raw)": 2.1283769607543945, "Pretrain/Step": 4336, "Pretrain/Step Time": 8.795304929837584} +{"Pretrain/Learning Rate": 2.9846549370965672e-05, "Pretrain/Loss": 2.0460305213928223, "Pretrain/Loss (Raw)": 2.087219476699829, "Pretrain/Step": 4337, "Pretrain/Step Time": 8.787665650248528} +{"Pretrain/Learning Rate": 2.9838220281489553e-05, "Pretrain/Loss": 2.045966625213623, "Pretrain/Loss (Raw)": 1.965201497077942, "Pretrain/Step": 4338, "Pretrain/Step Time": 8.788779688999057} +{"Pretrain/Learning Rate": 2.9829890634047068e-05, "Pretrain/Loss": 2.047024726867676, "Pretrain/Loss (Raw)": 2.0520708560943604, "Pretrain/Step": 4339, "Pretrain/Step Time": 8.787447018548846} +{"Pretrain/Learning Rate": 2.9821560429598844e-05, "Pretrain/Loss": 2.0481784343719482, "Pretrain/Loss (Raw)": 2.0025241374969482, "Pretrain/Step": 4340, "Pretrain/Step Time": 8.783786626532674} +{"Pretrain/Learning Rate": 2.9813229669105546e-05, "Pretrain/Loss": 2.048713207244873, "Pretrain/Loss (Raw)": 2.1239912509918213, "Pretrain/Step": 4341, "Pretrain/Step Time": 8.779437378048897} +{"Pretrain/Learning Rate": 2.9804898353527928e-05, "Pretrain/Loss": 2.049375534057617, "Pretrain/Loss (Raw)": 2.1122424602508545, "Pretrain/Step": 4342, "Pretrain/Step Time": 8.769635951146483} +{"Pretrain/Learning Rate": 2.9796566483826777e-05, "Pretrain/Loss": 2.052551507949829, "Pretrain/Loss (Raw)": 2.3117337226867676, "Pretrain/Step": 4343, "Pretrain/Step Time": 8.783672897145152} +{"Pretrain/Learning Rate": 2.9788234060962988e-05, "Pretrain/Loss": 2.0542070865631104, "Pretrain/Loss (Raw)": 2.3122692108154297, "Pretrain/Step": 4344, "Pretrain/Step Time": 8.783554835245013} +{"Pretrain/Learning Rate": 2.9779901085897478e-05, "Pretrain/Loss": 2.054107189178467, "Pretrain/Loss (Raw)": 1.9843701124191284, "Pretrain/Step": 4345, "Pretrain/Step Time": 8.784578619524837} +{"Pretrain/Learning Rate": 2.9771567559591257e-05, "Pretrain/Loss": 2.0557703971862793, "Pretrain/Loss (Raw)": 1.9683725833892822, "Pretrain/Step": 4346, "Pretrain/Step Time": 8.790374806150794} +{"Pretrain/Learning Rate": 2.9763233483005383e-05, "Pretrain/Loss": 2.055651903152466, "Pretrain/Loss (Raw)": 1.837263584136963, "Pretrain/Step": 4347, "Pretrain/Step Time": 8.785483092069626} +{"Pretrain/Learning Rate": 2.975489885710097e-05, "Pretrain/Loss": 2.0551815032958984, "Pretrain/Loss (Raw)": 1.9874554872512817, "Pretrain/Step": 4348, "Pretrain/Step Time": 8.784630132839084} +{"Pretrain/Learning Rate": 2.9746563682839225e-05, "Pretrain/Loss": 2.0555260181427, "Pretrain/Loss (Raw)": 2.190234899520874, "Pretrain/Step": 4349, "Pretrain/Step Time": 8.784917866811156} +{"Pretrain/Learning Rate": 2.9738227961181374e-05, "Pretrain/Loss": 2.0563621520996094, "Pretrain/Loss (Raw)": 2.038811445236206, "Pretrain/Step": 4350, "Pretrain/Step Time": 8.793565006926656} +{"Pretrain/Learning Rate": 2.972989169308876e-05, "Pretrain/Loss": 2.0556464195251465, "Pretrain/Loss (Raw)": 1.9888319969177246, "Pretrain/Step": 4351, "Pretrain/Step Time": 8.787704797461629} +{"Pretrain/Learning Rate": 2.9721554879522743e-05, "Pretrain/Loss": 2.054457902908325, "Pretrain/Loss (Raw)": 2.0223817825317383, "Pretrain/Step": 4352, "Pretrain/Step Time": 8.788363857194781} +{"Pretrain/Learning Rate": 2.9713217521444774e-05, "Pretrain/Loss": 2.0558087825775146, "Pretrain/Loss (Raw)": 2.163600206375122, "Pretrain/Step": 4353, "Pretrain/Step Time": 8.790357414633036} +{"Pretrain/Learning Rate": 2.9704879619816346e-05, "Pretrain/Loss": 2.0581579208374023, "Pretrain/Loss (Raw)": 2.120673418045044, "Pretrain/Step": 4354, "Pretrain/Step Time": 8.786147709935904} +{"Pretrain/Learning Rate": 2.969654117559903e-05, "Pretrain/Loss": 2.05873966217041, "Pretrain/Loss (Raw)": 2.3277511596679688, "Pretrain/Step": 4355, "Pretrain/Step Time": 8.784056359902024} +{"Pretrain/Learning Rate": 2.9688202189754456e-05, "Pretrain/Loss": 2.060765266418457, "Pretrain/Loss (Raw)": 2.143897771835327, "Pretrain/Step": 4356, "Pretrain/Step Time": 8.782029269263148} +{"Pretrain/Learning Rate": 2.9679862663244317e-05, "Pretrain/Loss": 2.061110496520996, "Pretrain/Loss (Raw)": 2.0479469299316406, "Pretrain/Step": 4357, "Pretrain/Step Time": 8.781386997550726} +{"Pretrain/Learning Rate": 2.9671522597030355e-05, "Pretrain/Loss": 2.0619711875915527, "Pretrain/Loss (Raw)": 2.125699043273926, "Pretrain/Step": 4358, "Pretrain/Step Time": 8.775489754974842} +{"Pretrain/Learning Rate": 2.9663181992074402e-05, "Pretrain/Loss": 2.060572862625122, "Pretrain/Loss (Raw)": 2.1376967430114746, "Pretrain/Step": 4359, "Pretrain/Step Time": 8.780177420005202} +{"Pretrain/Learning Rate": 2.9654840849338322e-05, "Pretrain/Loss": 2.0605881214141846, "Pretrain/Loss (Raw)": 1.8596197366714478, "Pretrain/Step": 4360, "Pretrain/Step Time": 8.784440563991666} +{"Pretrain/Learning Rate": 2.964649916978407e-05, "Pretrain/Loss": 2.060197591781616, "Pretrain/Loss (Raw)": 2.052337408065796, "Pretrain/Step": 4361, "Pretrain/Step Time": 8.776366654783487} +{"Pretrain/Learning Rate": 2.963815695437363e-05, "Pretrain/Loss": 2.0624260902404785, "Pretrain/Loss (Raw)": 2.3044776916503906, "Pretrain/Step": 4362, "Pretrain/Step Time": 8.772954806685448} +{"Pretrain/Learning Rate": 2.962981420406908e-05, "Pretrain/Loss": 2.0651278495788574, "Pretrain/Loss (Raw)": 2.195763111114502, "Pretrain/Step": 4363, "Pretrain/Step Time": 8.772582869976759} +{"Pretrain/Learning Rate": 2.9621470919832538e-05, "Pretrain/Loss": 2.064948081970215, "Pretrain/Loss (Raw)": 1.9228954315185547, "Pretrain/Step": 4364, "Pretrain/Step Time": 8.788446420803666} +{"Pretrain/Learning Rate": 2.9613127102626187e-05, "Pretrain/Loss": 2.068032741546631, "Pretrain/Loss (Raw)": 2.3919527530670166, "Pretrain/Step": 4365, "Pretrain/Step Time": 8.782749556005001} +{"Pretrain/Learning Rate": 2.9604782753412292e-05, "Pretrain/Loss": 2.0684590339660645, "Pretrain/Loss (Raw)": 1.9928263425827026, "Pretrain/Step": 4366, "Pretrain/Step Time": 8.789069946855307} +{"Pretrain/Learning Rate": 2.9596437873153137e-05, "Pretrain/Loss": 2.0697455406188965, "Pretrain/Loss (Raw)": 2.125098943710327, "Pretrain/Step": 4367, "Pretrain/Step Time": 8.788198063150048} +{"Pretrain/Learning Rate": 2.9588092462811122e-05, "Pretrain/Loss": 2.0679244995117188, "Pretrain/Loss (Raw)": 1.927897334098816, "Pretrain/Step": 4368, "Pretrain/Step Time": 8.790921155363321} +{"Pretrain/Learning Rate": 2.957974652334865e-05, "Pretrain/Loss": 2.069521903991699, "Pretrain/Loss (Raw)": 1.9856350421905518, "Pretrain/Step": 4369, "Pretrain/Step Time": 8.788250645622611} +{"Pretrain/Learning Rate": 2.9571400055728242e-05, "Pretrain/Loss": 2.069983720779419, "Pretrain/Loss (Raw)": 2.2156336307525635, "Pretrain/Step": 4370, "Pretrain/Step Time": 8.788570996373892} +{"Pretrain/Learning Rate": 2.9563053060912426e-05, "Pretrain/Loss": 2.068479061126709, "Pretrain/Loss (Raw)": 1.8336920738220215, "Pretrain/Step": 4371, "Pretrain/Step Time": 8.797417242079973} +{"Pretrain/Learning Rate": 2.9554705539863842e-05, "Pretrain/Loss": 2.067030906677246, "Pretrain/Loss (Raw)": 1.9868665933609009, "Pretrain/Step": 4372, "Pretrain/Step Time": 8.798087198287249} +{"Pretrain/Learning Rate": 2.954635749354514e-05, "Pretrain/Loss": 2.066913366317749, "Pretrain/Loss (Raw)": 2.099782943725586, "Pretrain/Step": 4373, "Pretrain/Step Time": 8.798255858942866} +{"Pretrain/Learning Rate": 2.953800892291908e-05, "Pretrain/Loss": 2.0689804553985596, "Pretrain/Loss (Raw)": 2.1647703647613525, "Pretrain/Step": 4374, "Pretrain/Step Time": 8.795168681070209} +{"Pretrain/Learning Rate": 2.9529659828948442e-05, "Pretrain/Loss": 2.069589138031006, "Pretrain/Loss (Raw)": 2.1610872745513916, "Pretrain/Step": 4375, "Pretrain/Step Time": 8.79672460258007} +{"Pretrain/Learning Rate": 2.9521310212596087e-05, "Pretrain/Loss": 2.0708208084106445, "Pretrain/Loss (Raw)": 2.051654100418091, "Pretrain/Step": 4376, "Pretrain/Step Time": 8.796404052525759} +{"Pretrain/Learning Rate": 2.951296007482493e-05, "Pretrain/Loss": 2.0715830326080322, "Pretrain/Loss (Raw)": 1.9813261032104492, "Pretrain/Step": 4377, "Pretrain/Step Time": 8.792812624946237} +{"Pretrain/Learning Rate": 2.9504609416597956e-05, "Pretrain/Loss": 2.0717875957489014, "Pretrain/Loss (Raw)": 2.04809832572937, "Pretrain/Step": 4378, "Pretrain/Step Time": 8.787285273894668} +{"Pretrain/Learning Rate": 2.9496258238878198e-05, "Pretrain/Loss": 2.0713858604431152, "Pretrain/Loss (Raw)": 2.049290418624878, "Pretrain/Step": 4379, "Pretrain/Step Time": 8.796477383002639} +{"Pretrain/Learning Rate": 2.9487906542628753e-05, "Pretrain/Loss": 2.0709919929504395, "Pretrain/Loss (Raw)": 2.094508409500122, "Pretrain/Step": 4380, "Pretrain/Step Time": 8.791949797421694} +{"Pretrain/Learning Rate": 2.9479554328812775e-05, "Pretrain/Loss": 2.0693931579589844, "Pretrain/Loss (Raw)": 2.025308847427368, "Pretrain/Step": 4381, "Pretrain/Step Time": 8.7913997489959} +{"Pretrain/Learning Rate": 2.9471201598393482e-05, "Pretrain/Loss": 2.0697054862976074, "Pretrain/Loss (Raw)": 1.9473785161972046, "Pretrain/Step": 4382, "Pretrain/Step Time": 8.795877827331424} +{"Pretrain/Learning Rate": 2.946284835233416e-05, "Pretrain/Loss": 2.0695862770080566, "Pretrain/Loss (Raw)": 2.036625385284424, "Pretrain/Step": 4383, "Pretrain/Step Time": 8.798438476398587} +{"Pretrain/Learning Rate": 2.945449459159813e-05, "Pretrain/Loss": 2.06964111328125, "Pretrain/Loss (Raw)": 2.2634341716766357, "Pretrain/Step": 4384, "Pretrain/Step Time": 8.797294065356255} +{"Pretrain/Learning Rate": 2.9446140317148795e-05, "Pretrain/Loss": 2.0697174072265625, "Pretrain/Loss (Raw)": 2.0772457122802734, "Pretrain/Step": 4385, "Pretrain/Step Time": 8.786836929619312} +{"Pretrain/Learning Rate": 2.9437785529949606e-05, "Pretrain/Loss": 2.0697193145751953, "Pretrain/Loss (Raw)": 2.04817271232605, "Pretrain/Step": 4386, "Pretrain/Step Time": 8.789635229855776} +{"Pretrain/Learning Rate": 2.9429430230964084e-05, "Pretrain/Loss": 2.0692341327667236, "Pretrain/Loss (Raw)": 2.100351095199585, "Pretrain/Step": 4387, "Pretrain/Step Time": 8.786161115393043} +{"Pretrain/Learning Rate": 2.9421074421155787e-05, "Pretrain/Loss": 2.070526123046875, "Pretrain/Loss (Raw)": 2.1714353561401367, "Pretrain/Step": 4388, "Pretrain/Step Time": 8.7873466424644} +{"Pretrain/Learning Rate": 2.9412718101488364e-05, "Pretrain/Loss": 2.0702152252197266, "Pretrain/Loss (Raw)": 2.0575640201568604, "Pretrain/Step": 4389, "Pretrain/Step Time": 8.786787711083889} +{"Pretrain/Learning Rate": 2.9404361272925497e-05, "Pretrain/Loss": 2.0673093795776367, "Pretrain/Loss (Raw)": 1.7660506963729858, "Pretrain/Step": 4390, "Pretrain/Step Time": 8.792484192177653} +{"Pretrain/Learning Rate": 2.939600393643092e-05, "Pretrain/Loss": 2.0671937465667725, "Pretrain/Loss (Raw)": 2.065772771835327, "Pretrain/Step": 4391, "Pretrain/Step Time": 8.792254373431206} +{"Pretrain/Learning Rate": 2.9387646092968468e-05, "Pretrain/Loss": 2.0683417320251465, "Pretrain/Loss (Raw)": 2.1725690364837646, "Pretrain/Step": 4392, "Pretrain/Step Time": 8.798619113862514} +{"Pretrain/Learning Rate": 2.9379287743501983e-05, "Pretrain/Loss": 2.068909168243408, "Pretrain/Loss (Raw)": 2.1352484226226807, "Pretrain/Step": 4393, "Pretrain/Step Time": 8.791457787156105} +{"Pretrain/Learning Rate": 2.9370928888995407e-05, "Pretrain/Loss": 2.068737268447876, "Pretrain/Loss (Raw)": 1.99725341796875, "Pretrain/Step": 4394, "Pretrain/Step Time": 8.79481945745647} +{"Pretrain/Learning Rate": 2.936256953041271e-05, "Pretrain/Loss": 2.0696582794189453, "Pretrain/Loss (Raw)": 2.1624464988708496, "Pretrain/Step": 4395, "Pretrain/Step Time": 8.795541301369667} +{"Pretrain/Learning Rate": 2.935420966871795e-05, "Pretrain/Loss": 2.0696308612823486, "Pretrain/Loss (Raw)": 2.0428171157836914, "Pretrain/Step": 4396, "Pretrain/Step Time": 8.793034138157964} +{"Pretrain/Learning Rate": 2.9345849304875195e-05, "Pretrain/Loss": 2.070187568664551, "Pretrain/Loss (Raw)": 2.130703926086426, "Pretrain/Step": 4397, "Pretrain/Step Time": 8.794129647314548} +{"Pretrain/Learning Rate": 2.9337488439848633e-05, "Pretrain/Loss": 2.0721471309661865, "Pretrain/Loss (Raw)": 2.3070340156555176, "Pretrain/Step": 4398, "Pretrain/Step Time": 8.788230581209064} +{"Pretrain/Learning Rate": 2.9329127074602458e-05, "Pretrain/Loss": 2.070916175842285, "Pretrain/Loss (Raw)": 2.012371301651001, "Pretrain/Step": 4399, "Pretrain/Step Time": 8.795789793133736} +{"Pretrain/Learning Rate": 2.9320765210100952e-05, "Pretrain/Loss": 2.071265697479248, "Pretrain/Loss (Raw)": 1.9304507970809937, "Pretrain/Step": 4400, "Pretrain/Step Time": 8.794760325923562} +{"Pretrain/Learning Rate": 2.931240284730844e-05, "Pretrain/Loss": 2.0717854499816895, "Pretrain/Loss (Raw)": 2.0445430278778076, "Pretrain/Step": 4401, "Pretrain/Step Time": 8.79099433682859} +{"Pretrain/Learning Rate": 2.9304039987189313e-05, "Pretrain/Loss": 2.0728135108947754, "Pretrain/Loss (Raw)": 2.084207773208618, "Pretrain/Step": 4402, "Pretrain/Step Time": 8.791393158957362} +{"Pretrain/Learning Rate": 2.9295676630708013e-05, "Pretrain/Loss": 2.072439670562744, "Pretrain/Loss (Raw)": 2.048596143722534, "Pretrain/Step": 4403, "Pretrain/Step Time": 8.795799342915416} +{"Pretrain/Learning Rate": 2.9287312778829047e-05, "Pretrain/Loss": 2.0724825859069824, "Pretrain/Loss (Raw)": 2.121964454650879, "Pretrain/Step": 4404, "Pretrain/Step Time": 8.795475604012609} +{"Pretrain/Learning Rate": 2.9278948432516968e-05, "Pretrain/Loss": 2.0748987197875977, "Pretrain/Loss (Raw)": 2.1368441581726074, "Pretrain/Step": 4405, "Pretrain/Step Time": 8.793234970420599} +{"Pretrain/Learning Rate": 2.9270583592736385e-05, "Pretrain/Loss": 2.0746097564697266, "Pretrain/Loss (Raw)": 2.1647865772247314, "Pretrain/Step": 4406, "Pretrain/Step Time": 8.801347376778722} +{"Pretrain/Learning Rate": 2.9262218260451984e-05, "Pretrain/Loss": 2.074341297149658, "Pretrain/Loss (Raw)": 2.0105695724487305, "Pretrain/Step": 4407, "Pretrain/Step Time": 8.78991630487144} +{"Pretrain/Learning Rate": 2.9253852436628483e-05, "Pretrain/Loss": 2.075777053833008, "Pretrain/Loss (Raw)": 2.1903555393218994, "Pretrain/Step": 4408, "Pretrain/Step Time": 8.789958123117685} +{"Pretrain/Learning Rate": 2.924548612223068e-05, "Pretrain/Loss": 2.072946548461914, "Pretrain/Loss (Raw)": 1.8851524591445923, "Pretrain/Step": 4409, "Pretrain/Step Time": 8.792736195027828} +{"Pretrain/Learning Rate": 2.923711931822341e-05, "Pretrain/Loss": 2.0712687969207764, "Pretrain/Loss (Raw)": 1.8108470439910889, "Pretrain/Step": 4410, "Pretrain/Step Time": 8.791159795597196} +{"Pretrain/Learning Rate": 2.9228752025571575e-05, "Pretrain/Loss": 2.0706048011779785, "Pretrain/Loss (Raw)": 2.0623443126678467, "Pretrain/Step": 4411, "Pretrain/Step Time": 8.791681988164783} +{"Pretrain/Learning Rate": 2.922038424524013e-05, "Pretrain/Loss": 2.0694491863250732, "Pretrain/Loss (Raw)": 1.9217950105667114, "Pretrain/Step": 4412, "Pretrain/Step Time": 8.7950923666358} +{"Pretrain/Learning Rate": 2.9212015978194083e-05, "Pretrain/Loss": 2.0686357021331787, "Pretrain/Loss (Raw)": 1.9647971391677856, "Pretrain/Step": 4413, "Pretrain/Step Time": 8.79958826303482} +{"Pretrain/Learning Rate": 2.920364722539851e-05, "Pretrain/Loss": 2.069779396057129, "Pretrain/Loss (Raw)": 2.1539204120635986, "Pretrain/Step": 4414, "Pretrain/Step Time": 8.79276162572205} +{"Pretrain/Learning Rate": 2.9195277987818533e-05, "Pretrain/Loss": 2.070906162261963, "Pretrain/Loss (Raw)": 2.233150005340576, "Pretrain/Step": 4415, "Pretrain/Step Time": 8.792638136073947} +{"Pretrain/Learning Rate": 2.918690826641932e-05, "Pretrain/Loss": 2.0743255615234375, "Pretrain/Loss (Raw)": 2.2355587482452393, "Pretrain/Step": 4416, "Pretrain/Step Time": 8.795424090698361} +{"Pretrain/Learning Rate": 2.917853806216613e-05, "Pretrain/Loss": 2.0749170780181885, "Pretrain/Loss (Raw)": 2.057595729827881, "Pretrain/Step": 4417, "Pretrain/Step Time": 8.79858379997313} +{"Pretrain/Learning Rate": 2.9170167376024228e-05, "Pretrain/Loss": 2.0743298530578613, "Pretrain/Loss (Raw)": 1.900822401046753, "Pretrain/Step": 4418, "Pretrain/Step Time": 8.792631326243281} +{"Pretrain/Learning Rate": 2.9161796208958974e-05, "Pretrain/Loss": 2.073662757873535, "Pretrain/Loss (Raw)": 1.9876363277435303, "Pretrain/Step": 4419, "Pretrain/Step Time": 8.790528073906898} +{"Pretrain/Learning Rate": 2.9153424561935782e-05, "Pretrain/Loss": 2.0760676860809326, "Pretrain/Loss (Raw)": 2.1778926849365234, "Pretrain/Step": 4420, "Pretrain/Step Time": 8.793459128588438} +{"Pretrain/Learning Rate": 2.914505243592009e-05, "Pretrain/Loss": 2.075939178466797, "Pretrain/Loss (Raw)": 2.0249269008636475, "Pretrain/Step": 4421, "Pretrain/Step Time": 8.78446102514863} +{"Pretrain/Learning Rate": 2.913667983187742e-05, "Pretrain/Loss": 2.0729942321777344, "Pretrain/Loss (Raw)": 1.7965006828308105, "Pretrain/Step": 4422, "Pretrain/Step Time": 8.784718502312899} +{"Pretrain/Learning Rate": 2.9128306750773338e-05, "Pretrain/Loss": 2.0746371746063232, "Pretrain/Loss (Raw)": 2.121657133102417, "Pretrain/Step": 4423, "Pretrain/Step Time": 8.781869215890765} +{"Pretrain/Learning Rate": 2.911993319357347e-05, "Pretrain/Loss": 2.0752735137939453, "Pretrain/Loss (Raw)": 2.135782241821289, "Pretrain/Step": 4424, "Pretrain/Step Time": 8.788735199719667} +{"Pretrain/Learning Rate": 2.911155916124349e-05, "Pretrain/Loss": 2.0740184783935547, "Pretrain/Loss (Raw)": 2.019700050354004, "Pretrain/Step": 4425, "Pretrain/Step Time": 8.783664220944047} +{"Pretrain/Learning Rate": 2.910318465474914e-05, "Pretrain/Loss": 2.0739998817443848, "Pretrain/Loss (Raw)": 2.1933705806732178, "Pretrain/Step": 4426, "Pretrain/Step Time": 8.787616537883878} +{"Pretrain/Learning Rate": 2.9094809675056188e-05, "Pretrain/Loss": 2.0742077827453613, "Pretrain/Loss (Raw)": 2.0269112586975098, "Pretrain/Step": 4427, "Pretrain/Step Time": 8.798356993123889} +{"Pretrain/Learning Rate": 2.9086434223130504e-05, "Pretrain/Loss": 2.073662757873535, "Pretrain/Loss (Raw)": 2.262800455093384, "Pretrain/Step": 4428, "Pretrain/Step Time": 8.797713274136186} +{"Pretrain/Learning Rate": 2.9078058299937962e-05, "Pretrain/Loss": 2.075305938720703, "Pretrain/Loss (Raw)": 2.316041946411133, "Pretrain/Step": 4429, "Pretrain/Step Time": 8.788913706317544} +{"Pretrain/Learning Rate": 2.9069681906444518e-05, "Pretrain/Loss": 2.075291156768799, "Pretrain/Loss (Raw)": 1.9537935256958008, "Pretrain/Step": 4430, "Pretrain/Step Time": 8.792329996824265} +{"Pretrain/Learning Rate": 2.906130504361619e-05, "Pretrain/Loss": 2.075357437133789, "Pretrain/Loss (Raw)": 2.0236575603485107, "Pretrain/Step": 4431, "Pretrain/Step Time": 8.788514405488968} +{"Pretrain/Learning Rate": 2.9052927712419013e-05, "Pretrain/Loss": 2.075003147125244, "Pretrain/Loss (Raw)": 1.98056960105896, "Pretrain/Step": 4432, "Pretrain/Step Time": 8.787254124879837} +{"Pretrain/Learning Rate": 2.9044549913819124e-05, "Pretrain/Loss": 2.0769202709198, "Pretrain/Loss (Raw)": 2.044017791748047, "Pretrain/Step": 4433, "Pretrain/Step Time": 8.781747443601489} +{"Pretrain/Learning Rate": 2.9036171648782672e-05, "Pretrain/Loss": 2.078361749649048, "Pretrain/Loss (Raw)": 2.1289868354797363, "Pretrain/Step": 4434, "Pretrain/Step Time": 8.78281668946147} +{"Pretrain/Learning Rate": 2.9027792918275894e-05, "Pretrain/Loss": 2.079197883605957, "Pretrain/Loss (Raw)": 2.1678411960601807, "Pretrain/Step": 4435, "Pretrain/Step Time": 8.790497614070773} +{"Pretrain/Learning Rate": 2.9019413723265053e-05, "Pretrain/Loss": 2.077988624572754, "Pretrain/Loss (Raw)": 1.9238592386245728, "Pretrain/Step": 4436, "Pretrain/Step Time": 8.777916505932808} +{"Pretrain/Learning Rate": 2.9011034064716485e-05, "Pretrain/Loss": 2.0751333236694336, "Pretrain/Loss (Raw)": 1.8357232809066772, "Pretrain/Step": 4437, "Pretrain/Step Time": 8.779975224286318} +{"Pretrain/Learning Rate": 2.9002653943596564e-05, "Pretrain/Loss": 2.073720932006836, "Pretrain/Loss (Raw)": 1.8392484188079834, "Pretrain/Step": 4438, "Pretrain/Step Time": 8.78293894045055} +{"Pretrain/Learning Rate": 2.8994273360871734e-05, "Pretrain/Loss": 2.0735764503479004, "Pretrain/Loss (Raw)": 2.107854127883911, "Pretrain/Step": 4439, "Pretrain/Step Time": 8.779452539980412} +{"Pretrain/Learning Rate": 2.898589231750847e-05, "Pretrain/Loss": 2.074457883834839, "Pretrain/Loss (Raw)": 2.1863632202148438, "Pretrain/Step": 4440, "Pretrain/Step Time": 8.778115905821323} +{"Pretrain/Learning Rate": 2.897751081447333e-05, "Pretrain/Loss": 2.0737667083740234, "Pretrain/Loss (Raw)": 2.0421078205108643, "Pretrain/Step": 4441, "Pretrain/Step Time": 8.77731180563569} +{"Pretrain/Learning Rate": 2.8969128852732896e-05, "Pretrain/Loss": 2.072864532470703, "Pretrain/Loss (Raw)": 2.0082039833068848, "Pretrain/Step": 4442, "Pretrain/Step Time": 8.784429848194122} +{"Pretrain/Learning Rate": 2.896074643325382e-05, "Pretrain/Loss": 2.0732240676879883, "Pretrain/Loss (Raw)": 2.066028356552124, "Pretrain/Step": 4443, "Pretrain/Step Time": 8.783767811954021} +{"Pretrain/Learning Rate": 2.8952363557002798e-05, "Pretrain/Loss": 2.0695948600769043, "Pretrain/Loss (Raw)": 1.8517383337020874, "Pretrain/Step": 4444, "Pretrain/Step Time": 8.786057457327843} +{"Pretrain/Learning Rate": 2.89439802249466e-05, "Pretrain/Loss": 2.0686941146850586, "Pretrain/Loss (Raw)": 2.0658392906188965, "Pretrain/Step": 4445, "Pretrain/Step Time": 8.788705874234438} +{"Pretrain/Learning Rate": 2.8935596438052003e-05, "Pretrain/Loss": 2.0686049461364746, "Pretrain/Loss (Raw)": 2.0568289756774902, "Pretrain/Step": 4446, "Pretrain/Step Time": 8.786504415795207} +{"Pretrain/Learning Rate": 2.8927212197285885e-05, "Pretrain/Loss": 2.0687637329101562, "Pretrain/Loss (Raw)": 2.06437611579895, "Pretrain/Step": 4447, "Pretrain/Step Time": 8.78596386499703} +{"Pretrain/Learning Rate": 2.8918827503615154e-05, "Pretrain/Loss": 2.0696563720703125, "Pretrain/Loss (Raw)": 1.9891186952590942, "Pretrain/Step": 4448, "Pretrain/Step Time": 8.78657628968358} +{"Pretrain/Learning Rate": 2.891044235800676e-05, "Pretrain/Loss": 2.0691473484039307, "Pretrain/Loss (Raw)": 2.1137547492980957, "Pretrain/Step": 4449, "Pretrain/Step Time": 8.791576094925404} +{"Pretrain/Learning Rate": 2.8902056761427744e-05, "Pretrain/Loss": 2.06937575340271, "Pretrain/Loss (Raw)": 2.0380752086639404, "Pretrain/Step": 4450, "Pretrain/Step Time": 8.792066374793649} +{"Pretrain/Learning Rate": 2.889367071484514e-05, "Pretrain/Loss": 2.069398880004883, "Pretrain/Loss (Raw)": 2.0504415035247803, "Pretrain/Step": 4451, "Pretrain/Step Time": 8.791329504922032} +{"Pretrain/Learning Rate": 2.888528421922608e-05, "Pretrain/Loss": 2.068103790283203, "Pretrain/Loss (Raw)": 1.9757437705993652, "Pretrain/Step": 4452, "Pretrain/Step Time": 8.796573251485825} +{"Pretrain/Learning Rate": 2.8876897275537744e-05, "Pretrain/Loss": 2.0674333572387695, "Pretrain/Loss (Raw)": 1.8525115251541138, "Pretrain/Step": 4453, "Pretrain/Step Time": 8.797553328797221} +{"Pretrain/Learning Rate": 2.8868509884747348e-05, "Pretrain/Loss": 2.068542003631592, "Pretrain/Loss (Raw)": 2.1064624786376953, "Pretrain/Step": 4454, "Pretrain/Step Time": 8.794983057305217} +{"Pretrain/Learning Rate": 2.8860122047822154e-05, "Pretrain/Loss": 2.068408966064453, "Pretrain/Loss (Raw)": 2.0933265686035156, "Pretrain/Step": 4455, "Pretrain/Step Time": 8.794476917013526} +{"Pretrain/Learning Rate": 2.88517337657295e-05, "Pretrain/Loss": 2.0691428184509277, "Pretrain/Loss (Raw)": 2.1315701007843018, "Pretrain/Step": 4456, "Pretrain/Step Time": 8.806493448093534} +{"Pretrain/Learning Rate": 2.8843345039436758e-05, "Pretrain/Loss": 2.0678439140319824, "Pretrain/Loss (Raw)": 1.9620362520217896, "Pretrain/Step": 4457, "Pretrain/Step Time": 8.802236892282963} +{"Pretrain/Learning Rate": 2.8834955869911356e-05, "Pretrain/Loss": 2.069084405899048, "Pretrain/Loss (Raw)": 2.257209539413452, "Pretrain/Step": 4458, "Pretrain/Step Time": 8.799643551930785} +{"Pretrain/Learning Rate": 2.8826566258120768e-05, "Pretrain/Loss": 2.070018768310547, "Pretrain/Loss (Raw)": 2.0989017486572266, "Pretrain/Step": 4459, "Pretrain/Step Time": 8.800113629549742} +{"Pretrain/Learning Rate": 2.8818176205032533e-05, "Pretrain/Loss": 2.0703439712524414, "Pretrain/Loss (Raw)": 2.319448232650757, "Pretrain/Step": 4460, "Pretrain/Step Time": 8.79919378273189} +{"Pretrain/Learning Rate": 2.8809785711614228e-05, "Pretrain/Loss": 2.0704710483551025, "Pretrain/Loss (Raw)": 2.2307021617889404, "Pretrain/Step": 4461, "Pretrain/Step Time": 8.795991465449333} +{"Pretrain/Learning Rate": 2.8801394778833475e-05, "Pretrain/Loss": 2.0719776153564453, "Pretrain/Loss (Raw)": 2.2276368141174316, "Pretrain/Step": 4462, "Pretrain/Step Time": 8.796054728329182} +{"Pretrain/Learning Rate": 2.879300340765797e-05, "Pretrain/Loss": 2.07094669342041, "Pretrain/Loss (Raw)": 2.120060920715332, "Pretrain/Step": 4463, "Pretrain/Step Time": 8.797337187454104} +{"Pretrain/Learning Rate": 2.8784611599055435e-05, "Pretrain/Loss": 2.0696873664855957, "Pretrain/Loss (Raw)": 1.967190146446228, "Pretrain/Step": 4464, "Pretrain/Step Time": 8.78488453105092} +{"Pretrain/Learning Rate": 2.8776219353993662e-05, "Pretrain/Loss": 2.0691471099853516, "Pretrain/Loss (Raw)": 2.0180671215057373, "Pretrain/Step": 4465, "Pretrain/Step Time": 8.792502215132117} +{"Pretrain/Learning Rate": 2.8767826673440467e-05, "Pretrain/Loss": 2.070013999938965, "Pretrain/Loss (Raw)": 2.0761635303497314, "Pretrain/Step": 4466, "Pretrain/Step Time": 8.787872970104218} +{"Pretrain/Learning Rate": 2.8759433558363758e-05, "Pretrain/Loss": 2.0704503059387207, "Pretrain/Loss (Raw)": 2.107883930206299, "Pretrain/Step": 4467, "Pretrain/Step Time": 8.791026692837477} +{"Pretrain/Learning Rate": 2.875104000973145e-05, "Pretrain/Loss": 2.0706183910369873, "Pretrain/Loss (Raw)": 2.0240590572357178, "Pretrain/Step": 4468, "Pretrain/Step Time": 8.791743068024516} +{"Pretrain/Learning Rate": 2.874264602851154e-05, "Pretrain/Loss": 2.0702874660491943, "Pretrain/Loss (Raw)": 2.081629514694214, "Pretrain/Step": 4469, "Pretrain/Step Time": 8.793496394529939} +{"Pretrain/Learning Rate": 2.8734251615672043e-05, "Pretrain/Loss": 2.070000648498535, "Pretrain/Loss (Raw)": 2.075528860092163, "Pretrain/Step": 4470, "Pretrain/Step Time": 8.793830208480358} +{"Pretrain/Learning Rate": 2.8725856772181058e-05, "Pretrain/Loss": 2.067924976348877, "Pretrain/Loss (Raw)": 2.0460474491119385, "Pretrain/Step": 4471, "Pretrain/Step Time": 8.78325079381466} +{"Pretrain/Learning Rate": 2.8717461499006714e-05, "Pretrain/Loss": 2.066422939300537, "Pretrain/Loss (Raw)": 2.1200387477874756, "Pretrain/Step": 4472, "Pretrain/Step Time": 8.784913264214993} +{"Pretrain/Learning Rate": 2.8709065797117198e-05, "Pretrain/Loss": 2.0668821334838867, "Pretrain/Loss (Raw)": 2.04313063621521, "Pretrain/Step": 4473, "Pretrain/Step Time": 8.78285039588809} +{"Pretrain/Learning Rate": 2.8700669667480732e-05, "Pretrain/Loss": 2.066002368927002, "Pretrain/Loss (Raw)": 1.8557522296905518, "Pretrain/Step": 4474, "Pretrain/Step Time": 8.779325280338526} +{"Pretrain/Learning Rate": 2.86922731110656e-05, "Pretrain/Loss": 2.066526174545288, "Pretrain/Loss (Raw)": 1.9043188095092773, "Pretrain/Step": 4475, "Pretrain/Step Time": 8.78595756739378} +{"Pretrain/Learning Rate": 2.8683876128840138e-05, "Pretrain/Loss": 2.0678188800811768, "Pretrain/Loss (Raw)": 2.152912139892578, "Pretrain/Step": 4476, "Pretrain/Step Time": 8.783393695950508} +{"Pretrain/Learning Rate": 2.8675478721772715e-05, "Pretrain/Loss": 2.0672049522399902, "Pretrain/Loss (Raw)": 2.1116697788238525, "Pretrain/Step": 4477, "Pretrain/Step Time": 8.795063890516758} +{"Pretrain/Learning Rate": 2.866708089083177e-05, "Pretrain/Loss": 2.06666898727417, "Pretrain/Loss (Raw)": 1.9702028036117554, "Pretrain/Step": 4478, "Pretrain/Step Time": 8.787027969956398} +{"Pretrain/Learning Rate": 2.865868263698578e-05, "Pretrain/Loss": 2.0661723613739014, "Pretrain/Loss (Raw)": 1.925275206565857, "Pretrain/Step": 4479, "Pretrain/Step Time": 8.790796825662255} +{"Pretrain/Learning Rate": 2.8650283961203267e-05, "Pretrain/Loss": 2.0667545795440674, "Pretrain/Loss (Raw)": 2.0968902111053467, "Pretrain/Step": 4480, "Pretrain/Step Time": 8.78825144097209} +{"Pretrain/Learning Rate": 2.86418848644528e-05, "Pretrain/Loss": 2.066002368927002, "Pretrain/Loss (Raw)": 2.067328929901123, "Pretrain/Step": 4481, "Pretrain/Step Time": 8.781872306019068} +{"Pretrain/Learning Rate": 2.8633485347703015e-05, "Pretrain/Loss": 2.065552234649658, "Pretrain/Loss (Raw)": 2.0630552768707275, "Pretrain/Step": 4482, "Pretrain/Step Time": 8.782378612086177} +{"Pretrain/Learning Rate": 2.8625085411922575e-05, "Pretrain/Loss": 2.0629405975341797, "Pretrain/Loss (Raw)": 1.993472933769226, "Pretrain/Step": 4483, "Pretrain/Step Time": 8.782138420268893} +{"Pretrain/Learning Rate": 2.861668505808021e-05, "Pretrain/Loss": 2.0632104873657227, "Pretrain/Loss (Raw)": 2.1784024238586426, "Pretrain/Step": 4484, "Pretrain/Step Time": 8.79278427734971} +{"Pretrain/Learning Rate": 2.8608284287144675e-05, "Pretrain/Loss": 2.0635128021240234, "Pretrain/Loss (Raw)": 2.086681365966797, "Pretrain/Step": 4485, "Pretrain/Step Time": 8.792530519887805} +{"Pretrain/Learning Rate": 2.85998831000848e-05, "Pretrain/Loss": 2.063157796859741, "Pretrain/Loss (Raw)": 2.080259323120117, "Pretrain/Step": 4486, "Pretrain/Step Time": 8.795852676033974} +{"Pretrain/Learning Rate": 2.8591481497869433e-05, "Pretrain/Loss": 2.0625123977661133, "Pretrain/Loss (Raw)": 2.055081844329834, "Pretrain/Step": 4487, "Pretrain/Step Time": 8.795932162553072} +{"Pretrain/Learning Rate": 2.8583079481467507e-05, "Pretrain/Loss": 2.0641348361968994, "Pretrain/Loss (Raw)": 2.0672872066497803, "Pretrain/Step": 4488, "Pretrain/Step Time": 8.790350442752242} +{"Pretrain/Learning Rate": 2.857467705184797e-05, "Pretrain/Loss": 2.064553737640381, "Pretrain/Loss (Raw)": 2.1059327125549316, "Pretrain/Step": 4489, "Pretrain/Step Time": 8.789354925975204} +{"Pretrain/Learning Rate": 2.856627420997982e-05, "Pretrain/Loss": 2.0625085830688477, "Pretrain/Loss (Raw)": 2.0427281856536865, "Pretrain/Step": 4490, "Pretrain/Step Time": 8.790618672966957} +{"Pretrain/Learning Rate": 2.8557870956832132e-05, "Pretrain/Loss": 2.062195301055908, "Pretrain/Loss (Raw)": 2.155639410018921, "Pretrain/Step": 4491, "Pretrain/Step Time": 8.79774478264153} +{"Pretrain/Learning Rate": 2.8549467293374e-05, "Pretrain/Loss": 2.062101364135742, "Pretrain/Loss (Raw)": 1.9108633995056152, "Pretrain/Step": 4492, "Pretrain/Step Time": 8.783844277262688} +{"Pretrain/Learning Rate": 2.854106322057457e-05, "Pretrain/Loss": 2.059969902038574, "Pretrain/Loss (Raw)": 2.1191446781158447, "Pretrain/Step": 4493, "Pretrain/Step Time": 8.784580007195473} +{"Pretrain/Learning Rate": 2.8532658739403046e-05, "Pretrain/Loss": 2.060533285140991, "Pretrain/Loss (Raw)": 2.0649373531341553, "Pretrain/Step": 4494, "Pretrain/Step Time": 8.783201774582267} +{"Pretrain/Learning Rate": 2.852425385082867e-05, "Pretrain/Loss": 2.058790445327759, "Pretrain/Loss (Raw)": 1.9020156860351562, "Pretrain/Step": 4495, "Pretrain/Step Time": 8.78449940867722} +{"Pretrain/Learning Rate": 2.851584855582073e-05, "Pretrain/Loss": 2.0602633953094482, "Pretrain/Loss (Raw)": 2.1164445877075195, "Pretrain/Step": 4496, "Pretrain/Step Time": 8.782961351796985} +{"Pretrain/Learning Rate": 2.8507442855348577e-05, "Pretrain/Loss": 2.0592539310455322, "Pretrain/Loss (Raw)": 1.8564167022705078, "Pretrain/Step": 4497, "Pretrain/Step Time": 8.783570390194654} +{"Pretrain/Learning Rate": 2.8499036750381576e-05, "Pretrain/Loss": 2.0580575466156006, "Pretrain/Loss (Raw)": 2.062486171722412, "Pretrain/Step": 4498, "Pretrain/Step Time": 8.791005406528711} +{"Pretrain/Learning Rate": 2.849063024188917e-05, "Pretrain/Loss": 2.057744264602661, "Pretrain/Loss (Raw)": 1.7936029434204102, "Pretrain/Step": 4499, "Pretrain/Step Time": 8.78116700053215} +{"Pretrain/Learning Rate": 2.8482223330840836e-05, "Pretrain/Loss": 2.0586318969726562, "Pretrain/Loss (Raw)": 2.100478172302246, "Pretrain/Step": 4500, "Pretrain/Step Time": 8.781563257798553} +{"Pretrain/Learning Rate": 2.84738160182061e-05, "Pretrain/Loss": 2.056241035461426, "Pretrain/Loss (Raw)": 1.7937411069869995, "Pretrain/Step": 4501, "Pretrain/Step Time": 8.782946363091469} +{"Pretrain/Learning Rate": 2.8465408304954533e-05, "Pretrain/Loss": 2.055267810821533, "Pretrain/Loss (Raw)": 2.0402064323425293, "Pretrain/Step": 4502, "Pretrain/Step Time": 8.782778650522232} +{"Pretrain/Learning Rate": 2.8457000192055748e-05, "Pretrain/Loss": 2.0551650524139404, "Pretrain/Loss (Raw)": 2.1479544639587402, "Pretrain/Step": 4503, "Pretrain/Step Time": 8.778762785717845} +{"Pretrain/Learning Rate": 2.8448591680479415e-05, "Pretrain/Loss": 2.055453062057495, "Pretrain/Loss (Raw)": 2.0885205268859863, "Pretrain/Step": 4504, "Pretrain/Step Time": 8.781955195590854} +{"Pretrain/Learning Rate": 2.8440182771195235e-05, "Pretrain/Loss": 2.0557186603546143, "Pretrain/Loss (Raw)": 2.015305519104004, "Pretrain/Step": 4505, "Pretrain/Step Time": 8.793890073895454} +{"Pretrain/Learning Rate": 2.8431773465172972e-05, "Pretrain/Loss": 2.055682897567749, "Pretrain/Loss (Raw)": 2.043517589569092, "Pretrain/Step": 4506, "Pretrain/Step Time": 8.791913729161024} +{"Pretrain/Learning Rate": 2.8423363763382415e-05, "Pretrain/Loss": 2.0536551475524902, "Pretrain/Loss (Raw)": 1.7897350788116455, "Pretrain/Step": 4507, "Pretrain/Step Time": 8.785658011212945} +{"Pretrain/Learning Rate": 2.8414953666793426e-05, "Pretrain/Loss": 2.053969144821167, "Pretrain/Loss (Raw)": 2.1347098350524902, "Pretrain/Step": 4508, "Pretrain/Step Time": 8.790305057540536} +{"Pretrain/Learning Rate": 2.8406543176375882e-05, "Pretrain/Loss": 2.054593563079834, "Pretrain/Loss (Raw)": 2.1052207946777344, "Pretrain/Step": 4509, "Pretrain/Step Time": 8.788107115775347} +{"Pretrain/Learning Rate": 2.839813229309973e-05, "Pretrain/Loss": 2.055368661880493, "Pretrain/Loss (Raw)": 2.0465822219848633, "Pretrain/Step": 4510, "Pretrain/Step Time": 8.7830003015697} +{"Pretrain/Learning Rate": 2.8389721017934945e-05, "Pretrain/Loss": 2.0544776916503906, "Pretrain/Loss (Raw)": 1.9226164817810059, "Pretrain/Step": 4511, "Pretrain/Step Time": 8.780814316123724} +{"Pretrain/Learning Rate": 2.8381309351851564e-05, "Pretrain/Loss": 2.0543298721313477, "Pretrain/Loss (Raw)": 2.244500160217285, "Pretrain/Step": 4512, "Pretrain/Step Time": 8.78439985960722} +{"Pretrain/Learning Rate": 2.837289729581965e-05, "Pretrain/Loss": 2.0551199913024902, "Pretrain/Loss (Raw)": 2.178359270095825, "Pretrain/Step": 4513, "Pretrain/Step Time": 8.78190878033638} +{"Pretrain/Learning Rate": 2.8364484850809337e-05, "Pretrain/Loss": 2.054366111755371, "Pretrain/Loss (Raw)": 1.9516730308532715, "Pretrain/Step": 4514, "Pretrain/Step Time": 8.778384946286678} +{"Pretrain/Learning Rate": 2.835607201779077e-05, "Pretrain/Loss": 2.0542492866516113, "Pretrain/Loss (Raw)": 2.0854132175445557, "Pretrain/Step": 4515, "Pretrain/Step Time": 8.779520133510232} +{"Pretrain/Learning Rate": 2.834765879773416e-05, "Pretrain/Loss": 2.054647922515869, "Pretrain/Loss (Raw)": 2.222463607788086, "Pretrain/Step": 4516, "Pretrain/Step Time": 8.786408767104149} +{"Pretrain/Learning Rate": 2.833924519160977e-05, "Pretrain/Loss": 2.0545358657836914, "Pretrain/Loss (Raw)": 2.0432348251342773, "Pretrain/Step": 4517, "Pretrain/Step Time": 8.779826331883669} +{"Pretrain/Learning Rate": 2.8330831200387885e-05, "Pretrain/Loss": 2.0555739402770996, "Pretrain/Loss (Raw)": 1.8989074230194092, "Pretrain/Step": 4518, "Pretrain/Step Time": 8.775888189673424} +{"Pretrain/Learning Rate": 2.8322416825038855e-05, "Pretrain/Loss": 2.0559113025665283, "Pretrain/Loss (Raw)": 2.1089799404144287, "Pretrain/Step": 4519, "Pretrain/Step Time": 8.773515589535236} +{"Pretrain/Learning Rate": 2.831400206653305e-05, "Pretrain/Loss": 2.0544018745422363, "Pretrain/Loss (Raw)": 1.9793628454208374, "Pretrain/Step": 4520, "Pretrain/Step Time": 8.768828492611647} +{"Pretrain/Learning Rate": 2.830558692584092e-05, "Pretrain/Loss": 2.054126262664795, "Pretrain/Loss (Raw)": 2.0999410152435303, "Pretrain/Step": 4521, "Pretrain/Step Time": 8.769654907286167} +{"Pretrain/Learning Rate": 2.8297171403932928e-05, "Pretrain/Loss": 2.0528202056884766, "Pretrain/Loss (Raw)": 1.8300647735595703, "Pretrain/Step": 4522, "Pretrain/Step Time": 8.765199104323983} +{"Pretrain/Learning Rate": 2.8288755501779597e-05, "Pretrain/Loss": 2.052769184112549, "Pretrain/Loss (Raw)": 2.155937671661377, "Pretrain/Step": 4523, "Pretrain/Step Time": 8.771842263638973} +{"Pretrain/Learning Rate": 2.8280339220351475e-05, "Pretrain/Loss": 2.051072120666504, "Pretrain/Loss (Raw)": 1.8255852460861206, "Pretrain/Step": 4524, "Pretrain/Step Time": 8.77037563920021} +{"Pretrain/Learning Rate": 2.8271922560619184e-05, "Pretrain/Loss": 2.0504117012023926, "Pretrain/Loss (Raw)": 2.0461935997009277, "Pretrain/Step": 4525, "Pretrain/Step Time": 8.770072849467397} +{"Pretrain/Learning Rate": 2.8263505523553357e-05, "Pretrain/Loss": 2.0489118099212646, "Pretrain/Loss (Raw)": 2.1150240898132324, "Pretrain/Step": 4526, "Pretrain/Step Time": 8.77347213216126} +{"Pretrain/Learning Rate": 2.8255088110124705e-05, "Pretrain/Loss": 2.0480666160583496, "Pretrain/Loss (Raw)": 1.9041935205459595, "Pretrain/Step": 4527, "Pretrain/Step Time": 8.774512372910976} +{"Pretrain/Learning Rate": 2.8246670321303947e-05, "Pretrain/Loss": 2.0484228134155273, "Pretrain/Loss (Raw)": 1.9760305881500244, "Pretrain/Step": 4528, "Pretrain/Step Time": 8.774681091308594} +{"Pretrain/Learning Rate": 2.8238252158061873e-05, "Pretrain/Loss": 2.049229383468628, "Pretrain/Loss (Raw)": 2.1477956771850586, "Pretrain/Step": 4529, "Pretrain/Step Time": 8.774365190416574} +{"Pretrain/Learning Rate": 2.8229833621369295e-05, "Pretrain/Loss": 2.047574520111084, "Pretrain/Loss (Raw)": 1.8724019527435303, "Pretrain/Step": 4530, "Pretrain/Step Time": 8.775694692507386} +{"Pretrain/Learning Rate": 2.822141471219709e-05, "Pretrain/Loss": 2.0494887828826904, "Pretrain/Loss (Raw)": 2.2936105728149414, "Pretrain/Step": 4531, "Pretrain/Step Time": 8.772528871893883} +{"Pretrain/Learning Rate": 2.8212995431516163e-05, "Pretrain/Loss": 2.0496020317077637, "Pretrain/Loss (Raw)": 2.136470317840576, "Pretrain/Step": 4532, "Pretrain/Step Time": 8.77344030700624} +{"Pretrain/Learning Rate": 2.820457578029746e-05, "Pretrain/Loss": 2.0502729415893555, "Pretrain/Loss (Raw)": 2.222710609436035, "Pretrain/Step": 4533, "Pretrain/Step Time": 8.78289183974266} +{"Pretrain/Learning Rate": 2.8196155759511977e-05, "Pretrain/Loss": 2.0497186183929443, "Pretrain/Loss (Raw)": 2.093827486038208, "Pretrain/Step": 4534, "Pretrain/Step Time": 8.774612566456199} +{"Pretrain/Learning Rate": 2.8187735370130745e-05, "Pretrain/Loss": 2.050650119781494, "Pretrain/Loss (Raw)": 2.1297929286956787, "Pretrain/Step": 4535, "Pretrain/Step Time": 8.780415853485465} +{"Pretrain/Learning Rate": 2.8179314613124858e-05, "Pretrain/Loss": 2.0494790077209473, "Pretrain/Loss (Raw)": 2.0404767990112305, "Pretrain/Step": 4536, "Pretrain/Step Time": 8.781242167577147} +{"Pretrain/Learning Rate": 2.817089348946542e-05, "Pretrain/Loss": 2.0495810508728027, "Pretrain/Loss (Raw)": 1.898206114768982, "Pretrain/Step": 4537, "Pretrain/Step Time": 8.781552167609334} +{"Pretrain/Learning Rate": 2.8162472000123613e-05, "Pretrain/Loss": 2.0525498390197754, "Pretrain/Loss (Raw)": 2.1908297538757324, "Pretrain/Step": 4538, "Pretrain/Step Time": 8.780907440930605} +{"Pretrain/Learning Rate": 2.8154050146070627e-05, "Pretrain/Loss": 2.052769184112549, "Pretrain/Loss (Raw)": 2.0904219150543213, "Pretrain/Step": 4539, "Pretrain/Step Time": 8.784220458939672} +{"Pretrain/Learning Rate": 2.814562792827772e-05, "Pretrain/Loss": 2.053325653076172, "Pretrain/Loss (Raw)": 1.9930517673492432, "Pretrain/Step": 4540, "Pretrain/Step Time": 8.77906327880919} +{"Pretrain/Learning Rate": 2.8137205347716165e-05, "Pretrain/Loss": 2.0537257194519043, "Pretrain/Loss (Raw)": 2.015993356704712, "Pretrain/Step": 4541, "Pretrain/Step Time": 8.775835905224085} +{"Pretrain/Learning Rate": 2.8128782405357312e-05, "Pretrain/Loss": 2.0525333881378174, "Pretrain/Loss (Raw)": 2.0012969970703125, "Pretrain/Step": 4542, "Pretrain/Step Time": 8.777560381218791} +{"Pretrain/Learning Rate": 2.812035910217254e-05, "Pretrain/Loss": 2.0519700050354004, "Pretrain/Loss (Raw)": 2.1610536575317383, "Pretrain/Step": 4543, "Pretrain/Step Time": 8.785073734819889} +{"Pretrain/Learning Rate": 2.811193543913324e-05, "Pretrain/Loss": 2.0502355098724365, "Pretrain/Loss (Raw)": 2.013533592224121, "Pretrain/Step": 4544, "Pretrain/Step Time": 8.783146645873785} +{"Pretrain/Learning Rate": 2.8103511417210886e-05, "Pretrain/Loss": 2.0504636764526367, "Pretrain/Loss (Raw)": 2.0867786407470703, "Pretrain/Step": 4545, "Pretrain/Step Time": 8.777443690225482} +{"Pretrain/Learning Rate": 2.809508703737697e-05, "Pretrain/Loss": 2.05203914642334, "Pretrain/Loss (Raw)": 2.1024863719940186, "Pretrain/Step": 4546, "Pretrain/Step Time": 8.778582522645593} +{"Pretrain/Learning Rate": 2.808666230060304e-05, "Pretrain/Loss": 2.0528829097747803, "Pretrain/Loss (Raw)": 2.0956592559814453, "Pretrain/Step": 4547, "Pretrain/Step Time": 8.783871423453093} +{"Pretrain/Learning Rate": 2.8078237207860658e-05, "Pretrain/Loss": 2.053792953491211, "Pretrain/Loss (Raw)": 2.2943708896636963, "Pretrain/Step": 4548, "Pretrain/Step Time": 8.78165965154767} +{"Pretrain/Learning Rate": 2.806981176012146e-05, "Pretrain/Loss": 2.054471015930176, "Pretrain/Loss (Raw)": 2.1117300987243652, "Pretrain/Step": 4549, "Pretrain/Step Time": 8.78408364392817} +{"Pretrain/Learning Rate": 2.80613859583571e-05, "Pretrain/Loss": 2.0575108528137207, "Pretrain/Loss (Raw)": 2.185595750808716, "Pretrain/Step": 4550, "Pretrain/Step Time": 8.785116469487548} +{"Pretrain/Learning Rate": 2.8052959803539298e-05, "Pretrain/Loss": 2.0570735931396484, "Pretrain/Loss (Raw)": 2.06565523147583, "Pretrain/Step": 4551, "Pretrain/Step Time": 8.785522786900401} +{"Pretrain/Learning Rate": 2.8044533296639774e-05, "Pretrain/Loss": 2.055708408355713, "Pretrain/Loss (Raw)": 1.9610838890075684, "Pretrain/Step": 4552, "Pretrain/Step Time": 8.779695766046643} +{"Pretrain/Learning Rate": 2.8036106438630327e-05, "Pretrain/Loss": 2.0548043251037598, "Pretrain/Loss (Raw)": 1.9039677381515503, "Pretrain/Step": 4553, "Pretrain/Step Time": 8.78174209035933} +{"Pretrain/Learning Rate": 2.802767923048278e-05, "Pretrain/Loss": 2.053351402282715, "Pretrain/Loss (Raw)": 2.007394790649414, "Pretrain/Step": 4554, "Pretrain/Step Time": 8.780331809073687} +{"Pretrain/Learning Rate": 2.8019251673168993e-05, "Pretrain/Loss": 2.0531373023986816, "Pretrain/Loss (Raw)": 1.999516248703003, "Pretrain/Step": 4555, "Pretrain/Step Time": 8.771038126200438} +{"Pretrain/Learning Rate": 2.8010823767660887e-05, "Pretrain/Loss": 2.052011013031006, "Pretrain/Loss (Raw)": 2.118621349334717, "Pretrain/Step": 4556, "Pretrain/Step Time": 8.771436113864183} +{"Pretrain/Learning Rate": 2.8002395514930385e-05, "Pretrain/Loss": 2.0501484870910645, "Pretrain/Loss (Raw)": 2.0776443481445312, "Pretrain/Step": 4557, "Pretrain/Step Time": 8.770683068782091} +{"Pretrain/Learning Rate": 2.7993966915949493e-05, "Pretrain/Loss": 2.0508298873901367, "Pretrain/Loss (Raw)": 2.0409820079803467, "Pretrain/Step": 4558, "Pretrain/Step Time": 8.775845885276794} +{"Pretrain/Learning Rate": 2.7985537971690216e-05, "Pretrain/Loss": 2.051974296569824, "Pretrain/Loss (Raw)": 2.1701760292053223, "Pretrain/Step": 4559, "Pretrain/Step Time": 8.776481818407774} +{"Pretrain/Learning Rate": 2.7977108683124647e-05, "Pretrain/Loss": 2.0524840354919434, "Pretrain/Loss (Raw)": 2.045814037322998, "Pretrain/Step": 4560, "Pretrain/Step Time": 8.77498110383749} +{"Pretrain/Learning Rate": 2.7968679051224868e-05, "Pretrain/Loss": 2.0540759563446045, "Pretrain/Loss (Raw)": 2.2477686405181885, "Pretrain/Step": 4561, "Pretrain/Step Time": 8.786922454833984} +{"Pretrain/Learning Rate": 2.796024907696303e-05, "Pretrain/Loss": 2.053804397583008, "Pretrain/Loss (Raw)": 2.0942211151123047, "Pretrain/Step": 4562, "Pretrain/Step Time": 8.785065917298198} +{"Pretrain/Learning Rate": 2.795181876131132e-05, "Pretrain/Loss": 2.0532290935516357, "Pretrain/Loss (Raw)": 2.0942211151123047, "Pretrain/Step": 4563, "Pretrain/Step Time": 8.78279117308557} +{"Pretrain/Learning Rate": 2.7943388105241968e-05, "Pretrain/Loss": 2.0543341636657715, "Pretrain/Loss (Raw)": 2.065275192260742, "Pretrain/Step": 4564, "Pretrain/Step Time": 8.784613065421581} +{"Pretrain/Learning Rate": 2.793495710972722e-05, "Pretrain/Loss": 2.053255558013916, "Pretrain/Loss (Raw)": 1.6976721286773682, "Pretrain/Step": 4565, "Pretrain/Step Time": 8.786839958280325} +{"Pretrain/Learning Rate": 2.79265257757394e-05, "Pretrain/Loss": 2.054985761642456, "Pretrain/Loss (Raw)": 2.060709238052368, "Pretrain/Step": 4566, "Pretrain/Step Time": 8.777279010042548} +{"Pretrain/Learning Rate": 2.7918094104250826e-05, "Pretrain/Loss": 2.0540218353271484, "Pretrain/Loss (Raw)": 1.984498143196106, "Pretrain/Step": 4567, "Pretrain/Step Time": 8.776918850839138} +{"Pretrain/Learning Rate": 2.7909662096233897e-05, "Pretrain/Loss": 2.053476333618164, "Pretrain/Loss (Raw)": 2.116546154022217, "Pretrain/Step": 4568, "Pretrain/Step Time": 8.778297275304794} +{"Pretrain/Learning Rate": 2.7901229752661018e-05, "Pretrain/Loss": 2.0539727210998535, "Pretrain/Loss (Raw)": 2.105630874633789, "Pretrain/Step": 4569, "Pretrain/Step Time": 8.77717967517674} +{"Pretrain/Learning Rate": 2.7892797074504656e-05, "Pretrain/Loss": 2.054034948348999, "Pretrain/Loss (Raw)": 2.016164541244507, "Pretrain/Step": 4570, "Pretrain/Step Time": 8.766778191551566} +{"Pretrain/Learning Rate": 2.78843640627373e-05, "Pretrain/Loss": 2.054675579071045, "Pretrain/Loss (Raw)": 2.148057222366333, "Pretrain/Step": 4571, "Pretrain/Step Time": 8.767300184816122} +{"Pretrain/Learning Rate": 2.7875930718331496e-05, "Pretrain/Loss": 2.0566446781158447, "Pretrain/Loss (Raw)": 2.1037635803222656, "Pretrain/Step": 4572, "Pretrain/Step Time": 8.769748073071241} +{"Pretrain/Learning Rate": 2.786749704225981e-05, "Pretrain/Loss": 2.057943820953369, "Pretrain/Loss (Raw)": 2.232109785079956, "Pretrain/Step": 4573, "Pretrain/Step Time": 8.76868811622262} +{"Pretrain/Learning Rate": 2.785906303549485e-05, "Pretrain/Loss": 2.058929443359375, "Pretrain/Loss (Raw)": 2.1829848289489746, "Pretrain/Step": 4574, "Pretrain/Step Time": 8.771785596385598} +{"Pretrain/Learning Rate": 2.7850628699009268e-05, "Pretrain/Loss": 2.059015989303589, "Pretrain/Loss (Raw)": 2.07548189163208, "Pretrain/Step": 4575, "Pretrain/Step Time": 8.77065765671432} +{"Pretrain/Learning Rate": 2.7842194033775747e-05, "Pretrain/Loss": 2.0611233711242676, "Pretrain/Loss (Raw)": 2.2588624954223633, "Pretrain/Step": 4576, "Pretrain/Step Time": 8.778614668175578} +{"Pretrain/Learning Rate": 2.7833759040767027e-05, "Pretrain/Loss": 2.061302900314331, "Pretrain/Loss (Raw)": 2.1367270946502686, "Pretrain/Step": 4577, "Pretrain/Step Time": 8.768522903323174} +{"Pretrain/Learning Rate": 2.7825323720955853e-05, "Pretrain/Loss": 2.061479330062866, "Pretrain/Loss (Raw)": 2.0606606006622314, "Pretrain/Step": 4578, "Pretrain/Step Time": 8.766988599672914} +{"Pretrain/Learning Rate": 2.781688807531504e-05, "Pretrain/Loss": 2.0610952377319336, "Pretrain/Loss (Raw)": 2.001269578933716, "Pretrain/Step": 4579, "Pretrain/Step Time": 8.777717610821128} +{"Pretrain/Learning Rate": 2.7808452104817412e-05, "Pretrain/Loss": 2.062710762023926, "Pretrain/Loss (Raw)": 2.182565212249756, "Pretrain/Step": 4580, "Pretrain/Step Time": 8.77383304387331} +{"Pretrain/Learning Rate": 2.7800015810435865e-05, "Pretrain/Loss": 2.0639877319335938, "Pretrain/Loss (Raw)": 2.0159239768981934, "Pretrain/Step": 4581, "Pretrain/Step Time": 8.774699166417122} +{"Pretrain/Learning Rate": 2.779157919314329e-05, "Pretrain/Loss": 2.061068058013916, "Pretrain/Loss (Raw)": 1.7327409982681274, "Pretrain/Step": 4582, "Pretrain/Step Time": 8.78510689176619} +{"Pretrain/Learning Rate": 2.7783142253912647e-05, "Pretrain/Loss": 2.0607213973999023, "Pretrain/Loss (Raw)": 2.048973321914673, "Pretrain/Step": 4583, "Pretrain/Step Time": 8.784459801390767} +{"Pretrain/Learning Rate": 2.7774704993716937e-05, "Pretrain/Loss": 2.060001850128174, "Pretrain/Loss (Raw)": 2.0394575595855713, "Pretrain/Step": 4584, "Pretrain/Step Time": 8.773176362738013} +{"Pretrain/Learning Rate": 2.776626741352916e-05, "Pretrain/Loss": 2.0605359077453613, "Pretrain/Loss (Raw)": 2.0304036140441895, "Pretrain/Step": 4585, "Pretrain/Step Time": 8.773550746962428} +{"Pretrain/Learning Rate": 2.7757829514322397e-05, "Pretrain/Loss": 2.058928966522217, "Pretrain/Loss (Raw)": 2.0515172481536865, "Pretrain/Step": 4586, "Pretrain/Step Time": 8.778132982552052} +{"Pretrain/Learning Rate": 2.774939129706974e-05, "Pretrain/Loss": 2.0587618350982666, "Pretrain/Loss (Raw)": 2.077522039413452, "Pretrain/Step": 4587, "Pretrain/Step Time": 8.778785962611437} +{"Pretrain/Learning Rate": 2.7740952762744322e-05, "Pretrain/Loss": 2.056987762451172, "Pretrain/Loss (Raw)": 2.092362403869629, "Pretrain/Step": 4588, "Pretrain/Step Time": 8.775205722078681} +{"Pretrain/Learning Rate": 2.7732513912319314e-05, "Pretrain/Loss": 2.0548086166381836, "Pretrain/Loss (Raw)": 1.9517624378204346, "Pretrain/Step": 4589, "Pretrain/Step Time": 8.782352432608604} +{"Pretrain/Learning Rate": 2.7724074746767926e-05, "Pretrain/Loss": 2.0539865493774414, "Pretrain/Loss (Raw)": 2.122431993484497, "Pretrain/Step": 4590, "Pretrain/Step Time": 8.786191243678331} +{"Pretrain/Learning Rate": 2.77156352670634e-05, "Pretrain/Loss": 2.0555613040924072, "Pretrain/Loss (Raw)": 2.321603298187256, "Pretrain/Step": 4591, "Pretrain/Step Time": 8.784327721223235} +{"Pretrain/Learning Rate": 2.770719547417902e-05, "Pretrain/Loss": 2.055086851119995, "Pretrain/Loss (Raw)": 1.9064759016036987, "Pretrain/Step": 4592, "Pretrain/Step Time": 8.787833619862795} +{"Pretrain/Learning Rate": 2.76987553690881e-05, "Pretrain/Loss": 2.0565295219421387, "Pretrain/Loss (Raw)": 2.2027039527893066, "Pretrain/Step": 4593, "Pretrain/Step Time": 8.783472426235676} +{"Pretrain/Learning Rate": 2.7690314952764e-05, "Pretrain/Loss": 2.057274341583252, "Pretrain/Loss (Raw)": 2.17153263092041, "Pretrain/Step": 4594, "Pretrain/Step Time": 8.788072016090155} +{"Pretrain/Learning Rate": 2.7681874226180093e-05, "Pretrain/Loss": 2.058201313018799, "Pretrain/Loss (Raw)": 2.22653865814209, "Pretrain/Step": 4595, "Pretrain/Step Time": 8.793293420225382} +{"Pretrain/Learning Rate": 2.7673433190309823e-05, "Pretrain/Loss": 2.056924819946289, "Pretrain/Loss (Raw)": 1.8606550693511963, "Pretrain/Step": 4596, "Pretrain/Step Time": 8.80037421733141} +{"Pretrain/Learning Rate": 2.766499184612663e-05, "Pretrain/Loss": 2.057583808898926, "Pretrain/Loss (Raw)": 2.165975332260132, "Pretrain/Step": 4597, "Pretrain/Step Time": 8.795936109498143} +{"Pretrain/Learning Rate": 2.7656550194604026e-05, "Pretrain/Loss": 2.056887149810791, "Pretrain/Loss (Raw)": 1.9863791465759277, "Pretrain/Step": 4598, "Pretrain/Step Time": 8.797596953809261} +{"Pretrain/Learning Rate": 2.7648108236715536e-05, "Pretrain/Loss": 2.0565052032470703, "Pretrain/Loss (Raw)": 1.9971026182174683, "Pretrain/Step": 4599, "Pretrain/Step Time": 8.793218187987804} +{"Pretrain/Learning Rate": 2.7639665973434725e-05, "Pretrain/Loss": 2.0597782135009766, "Pretrain/Loss (Raw)": 2.5390071868896484, "Pretrain/Step": 4600, "Pretrain/Step Time": 8.797264898195863} +{"Pretrain/Learning Rate": 2.7631223405735196e-05, "Pretrain/Loss": 2.0592763423919678, "Pretrain/Loss (Raw)": 1.978894591331482, "Pretrain/Step": 4601, "Pretrain/Step Time": 8.797374965623021} +{"Pretrain/Learning Rate": 2.7622780534590582e-05, "Pretrain/Loss": 2.0600411891937256, "Pretrain/Loss (Raw)": 1.9536467790603638, "Pretrain/Step": 4602, "Pretrain/Step Time": 8.792616317048669} +{"Pretrain/Learning Rate": 2.7614337360974558e-05, "Pretrain/Loss": 2.0608553886413574, "Pretrain/Loss (Raw)": 2.0085361003875732, "Pretrain/Step": 4603, "Pretrain/Step Time": 8.794798094779253} +{"Pretrain/Learning Rate": 2.760589388586083e-05, "Pretrain/Loss": 2.0603623390197754, "Pretrain/Loss (Raw)": 2.089806079864502, "Pretrain/Step": 4604, "Pretrain/Step Time": 8.794798854738474} +{"Pretrain/Learning Rate": 2.7597450110223145e-05, "Pretrain/Loss": 2.056915283203125, "Pretrain/Loss (Raw)": 1.6704623699188232, "Pretrain/Step": 4605, "Pretrain/Step Time": 8.783868094906211} +{"Pretrain/Learning Rate": 2.7589006035035264e-05, "Pretrain/Loss": 2.0578231811523438, "Pretrain/Loss (Raw)": 2.086404800415039, "Pretrain/Step": 4606, "Pretrain/Step Time": 8.782549498602748} +{"Pretrain/Learning Rate": 2.7580561661271014e-05, "Pretrain/Loss": 2.059659481048584, "Pretrain/Loss (Raw)": 2.1603024005889893, "Pretrain/Step": 4607, "Pretrain/Step Time": 8.787057410925627} +{"Pretrain/Learning Rate": 2.7572116989904228e-05, "Pretrain/Loss": 2.0595335960388184, "Pretrain/Loss (Raw)": 2.080808401107788, "Pretrain/Step": 4608, "Pretrain/Step Time": 8.788037342950702} +{"Pretrain/Learning Rate": 2.7563672021908797e-05, "Pretrain/Loss": 2.0599403381347656, "Pretrain/Loss (Raw)": 2.1193747520446777, "Pretrain/Step": 4609, "Pretrain/Step Time": 8.787084255367517} +{"Pretrain/Learning Rate": 2.7555226758258624e-05, "Pretrain/Loss": 2.0647945404052734, "Pretrain/Loss (Raw)": 2.6844053268432617, "Pretrain/Step": 4610, "Pretrain/Step Time": 8.799016566947103} +{"Pretrain/Learning Rate": 2.7546781199927667e-05, "Pretrain/Loss": 2.065451145172119, "Pretrain/Loss (Raw)": 2.0774877071380615, "Pretrain/Step": 4611, "Pretrain/Step Time": 8.79974195919931} +{"Pretrain/Learning Rate": 2.7538335347889892e-05, "Pretrain/Loss": 2.0630836486816406, "Pretrain/Loss (Raw)": 1.8753961324691772, "Pretrain/Step": 4612, "Pretrain/Step Time": 8.788530517369509} +{"Pretrain/Learning Rate": 2.752988920311933e-05, "Pretrain/Loss": 2.0626277923583984, "Pretrain/Loss (Raw)": 2.0283286571502686, "Pretrain/Step": 4613, "Pretrain/Step Time": 8.786922929808497} +{"Pretrain/Learning Rate": 2.7521442766590027e-05, "Pretrain/Loss": 2.0629382133483887, "Pretrain/Loss (Raw)": 2.1199891567230225, "Pretrain/Step": 4614, "Pretrain/Step Time": 8.787986161187291} +{"Pretrain/Learning Rate": 2.7512996039276055e-05, "Pretrain/Loss": 2.0624895095825195, "Pretrain/Loss (Raw)": 1.997623324394226, "Pretrain/Step": 4615, "Pretrain/Step Time": 8.783017620444298} +{"Pretrain/Learning Rate": 2.7504549022151543e-05, "Pretrain/Loss": 2.0620858669281006, "Pretrain/Loss (Raw)": 2.0156331062316895, "Pretrain/Step": 4616, "Pretrain/Step Time": 8.78450065292418} +{"Pretrain/Learning Rate": 2.749610171619063e-05, "Pretrain/Loss": 2.062784433364868, "Pretrain/Loss (Raw)": 2.1953701972961426, "Pretrain/Step": 4617, "Pretrain/Step Time": 8.792083121836185} +{"Pretrain/Learning Rate": 2.748765412236751e-05, "Pretrain/Loss": 2.0630674362182617, "Pretrain/Loss (Raw)": 2.0789554119110107, "Pretrain/Step": 4618, "Pretrain/Step Time": 8.791142689064145} +{"Pretrain/Learning Rate": 2.747920624165639e-05, "Pretrain/Loss": 2.061161518096924, "Pretrain/Loss (Raw)": 1.911648154258728, "Pretrain/Step": 4619, "Pretrain/Step Time": 8.78628284484148} +{"Pretrain/Learning Rate": 2.7470758075031533e-05, "Pretrain/Loss": 2.062828779220581, "Pretrain/Loss (Raw)": 2.1242902278900146, "Pretrain/Step": 4620, "Pretrain/Step Time": 8.786988396197557} +{"Pretrain/Learning Rate": 2.7462309623467204e-05, "Pretrain/Loss": 2.0624263286590576, "Pretrain/Loss (Raw)": 2.0676212310791016, "Pretrain/Step": 4621, "Pretrain/Step Time": 8.792656607925892} +{"Pretrain/Learning Rate": 2.7453860887937732e-05, "Pretrain/Loss": 2.063180685043335, "Pretrain/Loss (Raw)": 2.161520004272461, "Pretrain/Step": 4622, "Pretrain/Step Time": 8.787875337526202} +{"Pretrain/Learning Rate": 2.7445411869417453e-05, "Pretrain/Loss": 2.064197540283203, "Pretrain/Loss (Raw)": 2.0321438312530518, "Pretrain/Step": 4623, "Pretrain/Step Time": 8.78937510587275} +{"Pretrain/Learning Rate": 2.7436962568880752e-05, "Pretrain/Loss": 2.0615692138671875, "Pretrain/Loss (Raw)": 1.7800140380859375, "Pretrain/Step": 4624, "Pretrain/Step Time": 8.794606182724237} +{"Pretrain/Learning Rate": 2.7428512987302053e-05, "Pretrain/Loss": 2.063908100128174, "Pretrain/Loss (Raw)": 2.1558167934417725, "Pretrain/Step": 4625, "Pretrain/Step Time": 8.793063517659903} +{"Pretrain/Learning Rate": 2.7420063125655787e-05, "Pretrain/Loss": 2.0641238689422607, "Pretrain/Loss (Raw)": 2.0901098251342773, "Pretrain/Step": 4626, "Pretrain/Step Time": 8.787743648514152} +{"Pretrain/Learning Rate": 2.741161298491644e-05, "Pretrain/Loss": 2.0661110877990723, "Pretrain/Loss (Raw)": 2.0479605197906494, "Pretrain/Step": 4627, "Pretrain/Step Time": 8.785220846533775} +{"Pretrain/Learning Rate": 2.7403162566058517e-05, "Pretrain/Loss": 2.0641870498657227, "Pretrain/Loss (Raw)": 1.8542091846466064, "Pretrain/Step": 4628, "Pretrain/Step Time": 8.792054489254951} +{"Pretrain/Learning Rate": 2.7394711870056567e-05, "Pretrain/Loss": 2.0662477016448975, "Pretrain/Loss (Raw)": 2.0574848651885986, "Pretrain/Step": 4629, "Pretrain/Step Time": 8.790026785805821} +{"Pretrain/Learning Rate": 2.7386260897885156e-05, "Pretrain/Loss": 2.065121650695801, "Pretrain/Loss (Raw)": 1.8960959911346436, "Pretrain/Step": 4630, "Pretrain/Step Time": 8.787277482450008} +{"Pretrain/Learning Rate": 2.73778096505189e-05, "Pretrain/Loss": 2.0662953853607178, "Pretrain/Loss (Raw)": 2.2981929779052734, "Pretrain/Step": 4631, "Pretrain/Step Time": 8.788658075034618} +{"Pretrain/Learning Rate": 2.7369358128932422e-05, "Pretrain/Loss": 2.0661702156066895, "Pretrain/Loss (Raw)": 2.07246470451355, "Pretrain/Step": 4632, "Pretrain/Step Time": 8.79641248844564} +{"Pretrain/Learning Rate": 2.7360906334100407e-05, "Pretrain/Loss": 2.0674920082092285, "Pretrain/Loss (Raw)": 2.184523105621338, "Pretrain/Step": 4633, "Pretrain/Step Time": 8.78341101296246} +{"Pretrain/Learning Rate": 2.7352454266997545e-05, "Pretrain/Loss": 2.067735195159912, "Pretrain/Loss (Raw)": 2.074644088745117, "Pretrain/Step": 4634, "Pretrain/Step Time": 8.786171982064843} +{"Pretrain/Learning Rate": 2.734400192859857e-05, "Pretrain/Loss": 2.069704532623291, "Pretrain/Loss (Raw)": 2.0418167114257812, "Pretrain/Step": 4635, "Pretrain/Step Time": 8.7908496260643} +{"Pretrain/Learning Rate": 2.7335549319878252e-05, "Pretrain/Loss": 2.067943572998047, "Pretrain/Loss (Raw)": 1.9092997312545776, "Pretrain/Step": 4636, "Pretrain/Step Time": 8.78807757049799} +{"Pretrain/Learning Rate": 2.7327096441811383e-05, "Pretrain/Loss": 2.0693066120147705, "Pretrain/Loss (Raw)": 2.2796812057495117, "Pretrain/Step": 4637, "Pretrain/Step Time": 8.789110207930207} +{"Pretrain/Learning Rate": 2.7318643295372776e-05, "Pretrain/Loss": 2.070199728012085, "Pretrain/Loss (Raw)": 2.160900831222534, "Pretrain/Step": 4638, "Pretrain/Step Time": 8.796253757551312} +{"Pretrain/Learning Rate": 2.7310189881537307e-05, "Pretrain/Loss": 2.0711898803710938, "Pretrain/Loss (Raw)": 2.0493602752685547, "Pretrain/Step": 4639, "Pretrain/Step Time": 8.796097612008452} +{"Pretrain/Learning Rate": 2.7301736201279858e-05, "Pretrain/Loss": 2.0700228214263916, "Pretrain/Loss (Raw)": 2.0951149463653564, "Pretrain/Step": 4640, "Pretrain/Step Time": 8.791231045499444} +{"Pretrain/Learning Rate": 2.7293282255575335e-05, "Pretrain/Loss": 2.067899703979492, "Pretrain/Loss (Raw)": 1.906611442565918, "Pretrain/Step": 4641, "Pretrain/Step Time": 8.794494858011603} +{"Pretrain/Learning Rate": 2.7284828045398703e-05, "Pretrain/Loss": 2.0696427822113037, "Pretrain/Loss (Raw)": 2.1747822761535645, "Pretrain/Step": 4642, "Pretrain/Step Time": 8.790007721632719} +{"Pretrain/Learning Rate": 2.7276373571724927e-05, "Pretrain/Loss": 2.0697057247161865, "Pretrain/Loss (Raw)": 2.0934600830078125, "Pretrain/Step": 4643, "Pretrain/Step Time": 8.789492391049862} +{"Pretrain/Learning Rate": 2.7267918835529033e-05, "Pretrain/Loss": 2.06903338432312, "Pretrain/Loss (Raw)": 2.1364238262176514, "Pretrain/Step": 4644, "Pretrain/Step Time": 8.785331090912223} +{"Pretrain/Learning Rate": 2.725946383778605e-05, "Pretrain/Loss": 2.0703439712524414, "Pretrain/Loss (Raw)": 2.210965156555176, "Pretrain/Step": 4645, "Pretrain/Step Time": 8.790552970021963} +{"Pretrain/Learning Rate": 2.7251008579471044e-05, "Pretrain/Loss": 2.072450876235962, "Pretrain/Loss (Raw)": 2.1686062812805176, "Pretrain/Step": 4646, "Pretrain/Step Time": 8.791143717244267} +{"Pretrain/Learning Rate": 2.7242553061559123e-05, "Pretrain/Loss": 2.072617769241333, "Pretrain/Loss (Raw)": 2.130357265472412, "Pretrain/Step": 4647, "Pretrain/Step Time": 8.79451484233141} +{"Pretrain/Learning Rate": 2.7234097285025424e-05, "Pretrain/Loss": 2.0732016563415527, "Pretrain/Loss (Raw)": 2.0540692806243896, "Pretrain/Step": 4648, "Pretrain/Step Time": 8.791358456015587} +{"Pretrain/Learning Rate": 2.7225641250845085e-05, "Pretrain/Loss": 2.0719571113586426, "Pretrain/Loss (Raw)": 1.9406647682189941, "Pretrain/Step": 4649, "Pretrain/Step Time": 8.791443724185228} +{"Pretrain/Learning Rate": 2.7217184959993326e-05, "Pretrain/Loss": 2.073819637298584, "Pretrain/Loss (Raw)": 2.0684635639190674, "Pretrain/Step": 4650, "Pretrain/Step Time": 8.798102194443345} +{"Pretrain/Learning Rate": 2.7208728413445332e-05, "Pretrain/Loss": 2.0729260444641113, "Pretrain/Loss (Raw)": 2.0415472984313965, "Pretrain/Step": 4651, "Pretrain/Step Time": 8.790880173444748} +{"Pretrain/Learning Rate": 2.720027161217638e-05, "Pretrain/Loss": 2.075652599334717, "Pretrain/Loss (Raw)": 2.174597978591919, "Pretrain/Step": 4652, "Pretrain/Step Time": 8.792912920936942} +{"Pretrain/Learning Rate": 2.7191814557161736e-05, "Pretrain/Loss": 2.0751662254333496, "Pretrain/Loss (Raw)": 1.9839508533477783, "Pretrain/Step": 4653, "Pretrain/Step Time": 8.804676925763488} +{"Pretrain/Learning Rate": 2.7183357249376712e-05, "Pretrain/Loss": 2.074448347091675, "Pretrain/Loss (Raw)": 2.023099422454834, "Pretrain/Step": 4654, "Pretrain/Step Time": 8.801041716709733} +{"Pretrain/Learning Rate": 2.7174899689796636e-05, "Pretrain/Loss": 2.0742805004119873, "Pretrain/Loss (Raw)": 1.8827317953109741, "Pretrain/Step": 4655, "Pretrain/Step Time": 8.793542439118028} +{"Pretrain/Learning Rate": 2.7166441879396887e-05, "Pretrain/Loss": 2.0733213424682617, "Pretrain/Loss (Raw)": 1.8532534837722778, "Pretrain/Step": 4656, "Pretrain/Step Time": 8.79233142733574} +{"Pretrain/Learning Rate": 2.7157983819152848e-05, "Pretrain/Loss": 2.0713047981262207, "Pretrain/Loss (Raw)": 1.8897069692611694, "Pretrain/Step": 4657, "Pretrain/Step Time": 8.792610885575414} +{"Pretrain/Learning Rate": 2.714952551003994e-05, "Pretrain/Loss": 2.0734152793884277, "Pretrain/Loss (Raw)": 2.142526626586914, "Pretrain/Step": 4658, "Pretrain/Step Time": 8.78911828622222} +{"Pretrain/Learning Rate": 2.714106695303363e-05, "Pretrain/Loss": 2.0713977813720703, "Pretrain/Loss (Raw)": 2.0353708267211914, "Pretrain/Step": 4659, "Pretrain/Step Time": 8.79600701853633} +{"Pretrain/Learning Rate": 2.7132608149109383e-05, "Pretrain/Loss": 2.071122169494629, "Pretrain/Loss (Raw)": 2.101191759109497, "Pretrain/Step": 4660, "Pretrain/Step Time": 8.800183130428195} +{"Pretrain/Learning Rate": 2.7124149099242724e-05, "Pretrain/Loss": 2.0697569847106934, "Pretrain/Loss (Raw)": 2.0479724407196045, "Pretrain/Step": 4661, "Pretrain/Step Time": 8.78855138272047} +{"Pretrain/Learning Rate": 2.7115689804409174e-05, "Pretrain/Loss": 2.0694117546081543, "Pretrain/Loss (Raw)": 2.0496153831481934, "Pretrain/Step": 4662, "Pretrain/Step Time": 8.790399808436632} +{"Pretrain/Learning Rate": 2.710723026558431e-05, "Pretrain/Loss": 2.068204402923584, "Pretrain/Loss (Raw)": 1.9752511978149414, "Pretrain/Step": 4663, "Pretrain/Step Time": 8.788910560309887} +{"Pretrain/Learning Rate": 2.709877048374371e-05, "Pretrain/Loss": 2.0687367916107178, "Pretrain/Loss (Raw)": 2.1086370944976807, "Pretrain/Step": 4664, "Pretrain/Step Time": 8.786827873438597} +{"Pretrain/Learning Rate": 2.709031045986302e-05, "Pretrain/Loss": 2.06946063041687, "Pretrain/Loss (Raw)": 1.9908674955368042, "Pretrain/Step": 4665, "Pretrain/Step Time": 8.78920809365809} +{"Pretrain/Learning Rate": 2.708185019491788e-05, "Pretrain/Loss": 2.0696983337402344, "Pretrain/Loss (Raw)": 2.221221685409546, "Pretrain/Step": 4666, "Pretrain/Step Time": 8.788476832211018} +{"Pretrain/Learning Rate": 2.707338968988396e-05, "Pretrain/Loss": 2.0675036907196045, "Pretrain/Loss (Raw)": 1.8095295429229736, "Pretrain/Step": 4667, "Pretrain/Step Time": 8.791747968643904} +{"Pretrain/Learning Rate": 2.7064928945736974e-05, "Pretrain/Loss": 2.0673248767852783, "Pretrain/Loss (Raw)": 1.970165729522705, "Pretrain/Step": 4668, "Pretrain/Step Time": 8.792357673868537} +{"Pretrain/Learning Rate": 2.7056467963452646e-05, "Pretrain/Loss": 2.0676522254943848, "Pretrain/Loss (Raw)": 2.057887315750122, "Pretrain/Step": 4669, "Pretrain/Step Time": 8.795090978965163} +{"Pretrain/Learning Rate": 2.704800674400675e-05, "Pretrain/Loss": 2.0685415267944336, "Pretrain/Loss (Raw)": 2.1151046752929688, "Pretrain/Step": 4670, "Pretrain/Step Time": 8.793557487428188} +{"Pretrain/Learning Rate": 2.703954528837506e-05, "Pretrain/Loss": 2.0675222873687744, "Pretrain/Loss (Raw)": 2.0306015014648438, "Pretrain/Step": 4671, "Pretrain/Step Time": 8.787969831377268} +{"Pretrain/Learning Rate": 2.7031083597533402e-05, "Pretrain/Loss": 2.0677549839019775, "Pretrain/Loss (Raw)": 2.0433366298675537, "Pretrain/Step": 4672, "Pretrain/Step Time": 8.792133463546634} +{"Pretrain/Learning Rate": 2.702262167245761e-05, "Pretrain/Loss": 2.0683109760284424, "Pretrain/Loss (Raw)": 2.157954692840576, "Pretrain/Step": 4673, "Pretrain/Step Time": 8.792207410559058} +{"Pretrain/Learning Rate": 2.7014159514123555e-05, "Pretrain/Loss": 2.067664623260498, "Pretrain/Loss (Raw)": 2.019733190536499, "Pretrain/Step": 4674, "Pretrain/Step Time": 8.803461534902453} +{"Pretrain/Learning Rate": 2.7005697123507134e-05, "Pretrain/Loss": 2.0682990550994873, "Pretrain/Loss (Raw)": 2.176877498626709, "Pretrain/Step": 4675, "Pretrain/Step Time": 8.795581160113215} +{"Pretrain/Learning Rate": 2.6997234501584267e-05, "Pretrain/Loss": 2.067387104034424, "Pretrain/Loss (Raw)": 2.1776394844055176, "Pretrain/Step": 4676, "Pretrain/Step Time": 8.800268590450287} +{"Pretrain/Learning Rate": 2.6988771649330906e-05, "Pretrain/Loss": 2.0674805641174316, "Pretrain/Loss (Raw)": 2.12369966506958, "Pretrain/Step": 4677, "Pretrain/Step Time": 8.797864481806755} +{"Pretrain/Learning Rate": 2.6980308567723035e-05, "Pretrain/Loss": 2.0657119750976562, "Pretrain/Loss (Raw)": 1.9591962099075317, "Pretrain/Step": 4678, "Pretrain/Step Time": 8.791622933000326} +{"Pretrain/Learning Rate": 2.697184525773664e-05, "Pretrain/Loss": 2.0665969848632812, "Pretrain/Loss (Raw)": 2.178973913192749, "Pretrain/Step": 4679, "Pretrain/Step Time": 8.789977315813303} +{"Pretrain/Learning Rate": 2.6963381720347764e-05, "Pretrain/Loss": 2.067802667617798, "Pretrain/Loss (Raw)": 2.1153814792633057, "Pretrain/Step": 4680, "Pretrain/Step Time": 8.793428240343928} +{"Pretrain/Learning Rate": 2.6954917956532455e-05, "Pretrain/Loss": 2.06610107421875, "Pretrain/Loss (Raw)": 1.6861624717712402, "Pretrain/Step": 4681, "Pretrain/Step Time": 8.799680765718222} +{"Pretrain/Learning Rate": 2.6946453967266792e-05, "Pretrain/Loss": 2.0677833557128906, "Pretrain/Loss (Raw)": 2.2227418422698975, "Pretrain/Step": 4682, "Pretrain/Step Time": 8.796137440949678} +{"Pretrain/Learning Rate": 2.693798975352689e-05, "Pretrain/Loss": 2.069286823272705, "Pretrain/Loss (Raw)": 2.1919713020324707, "Pretrain/Step": 4683, "Pretrain/Step Time": 8.800123803317547} +{"Pretrain/Learning Rate": 2.6929525316288874e-05, "Pretrain/Loss": 2.0687732696533203, "Pretrain/Loss (Raw)": 2.052844762802124, "Pretrain/Step": 4684, "Pretrain/Step Time": 8.803240086883307} +{"Pretrain/Learning Rate": 2.692106065652891e-05, "Pretrain/Loss": 2.0697948932647705, "Pretrain/Loss (Raw)": 2.2084357738494873, "Pretrain/Step": 4685, "Pretrain/Step Time": 8.806728508323431} +{"Pretrain/Learning Rate": 2.6912595775223175e-05, "Pretrain/Loss": 2.0668935775756836, "Pretrain/Loss (Raw)": 1.6695764064788818, "Pretrain/Step": 4686, "Pretrain/Step Time": 8.801858762279153} +{"Pretrain/Learning Rate": 2.6904130673347887e-05, "Pretrain/Loss": 2.066875457763672, "Pretrain/Loss (Raw)": 2.1678640842437744, "Pretrain/Step": 4687, "Pretrain/Step Time": 8.797852555289865} +{"Pretrain/Learning Rate": 2.6895665351879274e-05, "Pretrain/Loss": 2.066404342651367, "Pretrain/Loss (Raw)": 1.9855196475982666, "Pretrain/Step": 4688, "Pretrain/Step Time": 8.80550248362124} +{"Pretrain/Learning Rate": 2.68871998117936e-05, "Pretrain/Loss": 2.065725088119507, "Pretrain/Loss (Raw)": 2.160830020904541, "Pretrain/Step": 4689, "Pretrain/Step Time": 8.797539347782731} +{"Pretrain/Learning Rate": 2.687873405406715e-05, "Pretrain/Loss": 2.0650181770324707, "Pretrain/Loss (Raw)": 2.0037598609924316, "Pretrain/Step": 4690, "Pretrain/Step Time": 8.800429571419954} +{"Pretrain/Learning Rate": 2.6870268079676237e-05, "Pretrain/Loss": 2.064241409301758, "Pretrain/Loss (Raw)": 1.9947679042816162, "Pretrain/Step": 4691, "Pretrain/Step Time": 8.792247831821442} +{"Pretrain/Learning Rate": 2.6861801889597193e-05, "Pretrain/Loss": 2.0656769275665283, "Pretrain/Loss (Raw)": 2.2490367889404297, "Pretrain/Step": 4692, "Pretrain/Step Time": 8.798596547916532} +{"Pretrain/Learning Rate": 2.685333548480639e-05, "Pretrain/Loss": 2.0699117183685303, "Pretrain/Loss (Raw)": 2.2397074699401855, "Pretrain/Step": 4693, "Pretrain/Step Time": 8.796463802456856} +{"Pretrain/Learning Rate": 2.68448688662802e-05, "Pretrain/Loss": 2.0713202953338623, "Pretrain/Loss (Raw)": 2.241020679473877, "Pretrain/Step": 4694, "Pretrain/Step Time": 8.798038262873888} +{"Pretrain/Learning Rate": 2.683640203499504e-05, "Pretrain/Loss": 2.0707762241363525, "Pretrain/Loss (Raw)": 1.9148675203323364, "Pretrain/Step": 4695, "Pretrain/Step Time": 8.80465573631227} +{"Pretrain/Learning Rate": 2.682793499192734e-05, "Pretrain/Loss": 2.0709826946258545, "Pretrain/Loss (Raw)": 2.142948865890503, "Pretrain/Step": 4696, "Pretrain/Step Time": 8.801827490329742} +{"Pretrain/Learning Rate": 2.6819467738053572e-05, "Pretrain/Loss": 2.0712480545043945, "Pretrain/Loss (Raw)": 2.13961124420166, "Pretrain/Step": 4697, "Pretrain/Step Time": 8.803250024095178} +{"Pretrain/Learning Rate": 2.6811000274350205e-05, "Pretrain/Loss": 2.07157301902771, "Pretrain/Loss (Raw)": 2.0577590465545654, "Pretrain/Step": 4698, "Pretrain/Step Time": 8.801963834092021} +{"Pretrain/Learning Rate": 2.680253260179375e-05, "Pretrain/Loss": 2.0684399604797363, "Pretrain/Loss (Raw)": 1.7470570802688599, "Pretrain/Step": 4699, "Pretrain/Step Time": 8.8074219673872} +{"Pretrain/Learning Rate": 2.6794064721360752e-05, "Pretrain/Loss": 2.0684423446655273, "Pretrain/Loss (Raw)": 2.104015588760376, "Pretrain/Step": 4700, "Pretrain/Step Time": 8.802986711263657} +{"Pretrain/Learning Rate": 2.6785596634027745e-05, "Pretrain/Loss": 2.0674381256103516, "Pretrain/Loss (Raw)": 2.1035776138305664, "Pretrain/Step": 4701, "Pretrain/Step Time": 8.798536105081439} +{"Pretrain/Learning Rate": 2.677712834077133e-05, "Pretrain/Loss": 2.067882537841797, "Pretrain/Loss (Raw)": 2.2398681640625, "Pretrain/Step": 4702, "Pretrain/Step Time": 8.801657164469361} +{"Pretrain/Learning Rate": 2.676865984256809e-05, "Pretrain/Loss": 2.0668652057647705, "Pretrain/Loss (Raw)": 1.945281744003296, "Pretrain/Step": 4703, "Pretrain/Step Time": 8.809509132057428} +{"Pretrain/Learning Rate": 2.6760191140394668e-05, "Pretrain/Loss": 2.0635485649108887, "Pretrain/Loss (Raw)": 1.8343310356140137, "Pretrain/Step": 4704, "Pretrain/Step Time": 8.804698443040252} +{"Pretrain/Learning Rate": 2.675172223522771e-05, "Pretrain/Loss": 2.0629210472106934, "Pretrain/Loss (Raw)": 2.056401014328003, "Pretrain/Step": 4705, "Pretrain/Step Time": 8.803846530616283} +{"Pretrain/Learning Rate": 2.6743253128043887e-05, "Pretrain/Loss": 2.0620498657226562, "Pretrain/Loss (Raw)": 1.949134111404419, "Pretrain/Step": 4706, "Pretrain/Step Time": 8.807115627452731} +{"Pretrain/Learning Rate": 2.6734783819819903e-05, "Pretrain/Loss": 2.062133312225342, "Pretrain/Loss (Raw)": 2.0119669437408447, "Pretrain/Step": 4707, "Pretrain/Step Time": 8.800539849326015} +{"Pretrain/Learning Rate": 2.6726314311532467e-05, "Pretrain/Loss": 2.0608952045440674, "Pretrain/Loss (Raw)": 2.0240962505340576, "Pretrain/Step": 4708, "Pretrain/Step Time": 8.797711262479424} +{"Pretrain/Learning Rate": 2.671784460415834e-05, "Pretrain/Loss": 2.061981678009033, "Pretrain/Loss (Raw)": 2.154993772506714, "Pretrain/Step": 4709, "Pretrain/Step Time": 8.799948662519455} +{"Pretrain/Learning Rate": 2.6709374698674267e-05, "Pretrain/Loss": 2.0637271404266357, "Pretrain/Loss (Raw)": 1.9561659097671509, "Pretrain/Step": 4710, "Pretrain/Step Time": 8.790114471688867} +{"Pretrain/Learning Rate": 2.670090459605706e-05, "Pretrain/Loss": 2.0620975494384766, "Pretrain/Loss (Raw)": 1.8403804302215576, "Pretrain/Step": 4711, "Pretrain/Step Time": 8.798526929691434} +{"Pretrain/Learning Rate": 2.6692434297283514e-05, "Pretrain/Loss": 2.061070442199707, "Pretrain/Loss (Raw)": 1.907977819442749, "Pretrain/Step": 4712, "Pretrain/Step Time": 8.795948393642902} +{"Pretrain/Learning Rate": 2.6683963803330468e-05, "Pretrain/Loss": 2.061960458755493, "Pretrain/Loss (Raw)": 2.1443369388580322, "Pretrain/Step": 4713, "Pretrain/Step Time": 8.79751057550311} +{"Pretrain/Learning Rate": 2.6675493115174786e-05, "Pretrain/Loss": 2.0623435974121094, "Pretrain/Loss (Raw)": 2.1005237102508545, "Pretrain/Step": 4714, "Pretrain/Step Time": 8.799002610147} +{"Pretrain/Learning Rate": 2.6667022233793342e-05, "Pretrain/Loss": 2.062483072280884, "Pretrain/Loss (Raw)": 2.095411777496338, "Pretrain/Step": 4715, "Pretrain/Step Time": 8.796198133379221} +{"Pretrain/Learning Rate": 2.6658551160163036e-05, "Pretrain/Loss": 2.062079906463623, "Pretrain/Loss (Raw)": 2.040736675262451, "Pretrain/Step": 4716, "Pretrain/Step Time": 8.802012590691447} +{"Pretrain/Learning Rate": 2.6650079895260798e-05, "Pretrain/Loss": 2.0624425411224365, "Pretrain/Loss (Raw)": 1.9981881380081177, "Pretrain/Step": 4717, "Pretrain/Step Time": 8.793628834187984} +{"Pretrain/Learning Rate": 2.664160844006357e-05, "Pretrain/Loss": 2.0628108978271484, "Pretrain/Loss (Raw)": 2.169597864151001, "Pretrain/Step": 4718, "Pretrain/Step Time": 8.792762285098433} +{"Pretrain/Learning Rate": 2.6633136795548326e-05, "Pretrain/Loss": 2.0590267181396484, "Pretrain/Loss (Raw)": 1.837184190750122, "Pretrain/Step": 4719, "Pretrain/Step Time": 8.795309610664845} +{"Pretrain/Learning Rate": 2.662466496269204e-05, "Pretrain/Loss": 2.060431957244873, "Pretrain/Loss (Raw)": 2.0863535404205322, "Pretrain/Step": 4720, "Pretrain/Step Time": 8.791764840483665} +{"Pretrain/Learning Rate": 2.661619294247174e-05, "Pretrain/Loss": 2.0598316192626953, "Pretrain/Loss (Raw)": 2.1259067058563232, "Pretrain/Step": 4721, "Pretrain/Step Time": 8.789901478216052} +{"Pretrain/Learning Rate": 2.6607720735864454e-05, "Pretrain/Loss": 2.057042121887207, "Pretrain/Loss (Raw)": 1.8144575357437134, "Pretrain/Step": 4722, "Pretrain/Step Time": 8.78715575300157} +{"Pretrain/Learning Rate": 2.6599248343847244e-05, "Pretrain/Loss": 2.0567760467529297, "Pretrain/Loss (Raw)": 2.1924638748168945, "Pretrain/Step": 4723, "Pretrain/Step Time": 8.780074367299676} +{"Pretrain/Learning Rate": 2.6590775767397174e-05, "Pretrain/Loss": 2.058582305908203, "Pretrain/Loss (Raw)": 2.0918734073638916, "Pretrain/Step": 4724, "Pretrain/Step Time": 8.778190612792969} +{"Pretrain/Learning Rate": 2.6582303007491345e-05, "Pretrain/Loss": 2.059845447540283, "Pretrain/Loss (Raw)": 2.3276734352111816, "Pretrain/Step": 4725, "Pretrain/Step Time": 8.782043749466538} +{"Pretrain/Learning Rate": 2.6573830065106874e-05, "Pretrain/Loss": 2.0604054927825928, "Pretrain/Loss (Raw)": 2.0580453872680664, "Pretrain/Step": 4726, "Pretrain/Step Time": 8.779234325513244} +{"Pretrain/Learning Rate": 2.6565356941220908e-05, "Pretrain/Loss": 2.0609850883483887, "Pretrain/Loss (Raw)": 2.07130765914917, "Pretrain/Step": 4727, "Pretrain/Step Time": 8.787325076758862} +{"Pretrain/Learning Rate": 2.6556883636810605e-05, "Pretrain/Loss": 2.056662082672119, "Pretrain/Loss (Raw)": 1.9856367111206055, "Pretrain/Step": 4728, "Pretrain/Step Time": 8.78186360001564} +{"Pretrain/Learning Rate": 2.6548410152853142e-05, "Pretrain/Loss": 2.0583558082580566, "Pretrain/Loss (Raw)": 2.1956915855407715, "Pretrain/Step": 4729, "Pretrain/Step Time": 8.779136035591364} +{"Pretrain/Learning Rate": 2.6539936490325725e-05, "Pretrain/Loss": 2.057378053665161, "Pretrain/Loss (Raw)": 1.828492522239685, "Pretrain/Step": 4730, "Pretrain/Step Time": 8.785235581919551} +{"Pretrain/Learning Rate": 2.6531462650205575e-05, "Pretrain/Loss": 2.056821346282959, "Pretrain/Loss (Raw)": 1.9372889995574951, "Pretrain/Step": 4731, "Pretrain/Step Time": 8.778211623430252} +{"Pretrain/Learning Rate": 2.6522988633469938e-05, "Pretrain/Loss": 2.057149648666382, "Pretrain/Loss (Raw)": 2.1318182945251465, "Pretrain/Step": 4732, "Pretrain/Step Time": 8.7816669549793} +{"Pretrain/Learning Rate": 2.6514514441096066e-05, "Pretrain/Loss": 2.059802770614624, "Pretrain/Loss (Raw)": 2.0100855827331543, "Pretrain/Step": 4733, "Pretrain/Step Time": 8.77856227569282} +{"Pretrain/Learning Rate": 2.650604007406126e-05, "Pretrain/Loss": 2.060187339782715, "Pretrain/Loss (Raw)": 2.135613441467285, "Pretrain/Step": 4734, "Pretrain/Step Time": 8.78500504232943} +{"Pretrain/Learning Rate": 2.6497565533342816e-05, "Pretrain/Loss": 2.058992385864258, "Pretrain/Loss (Raw)": 2.00732159614563, "Pretrain/Step": 4735, "Pretrain/Step Time": 8.780034424737096} +{"Pretrain/Learning Rate": 2.6489090819918057e-05, "Pretrain/Loss": 2.059413194656372, "Pretrain/Loss (Raw)": 2.134692907333374, "Pretrain/Step": 4736, "Pretrain/Step Time": 8.783050378784537} +{"Pretrain/Learning Rate": 2.6480615934764323e-05, "Pretrain/Loss": 2.058582067489624, "Pretrain/Loss (Raw)": 2.013009786605835, "Pretrain/Step": 4737, "Pretrain/Step Time": 8.787427572533488} +{"Pretrain/Learning Rate": 2.6472140878858994e-05, "Pretrain/Loss": 2.0536251068115234, "Pretrain/Loss (Raw)": 2.049931526184082, "Pretrain/Step": 4738, "Pretrain/Step Time": 8.779280673712492} +{"Pretrain/Learning Rate": 2.646366565317943e-05, "Pretrain/Loss": 2.0535550117492676, "Pretrain/Loss (Raw)": 2.0684797763824463, "Pretrain/Step": 4739, "Pretrain/Step Time": 8.777900386601686} +{"Pretrain/Learning Rate": 2.6455190258703056e-05, "Pretrain/Loss": 2.0540263652801514, "Pretrain/Loss (Raw)": 1.9357413053512573, "Pretrain/Step": 4740, "Pretrain/Step Time": 8.777489827945828} +{"Pretrain/Learning Rate": 2.644671469640728e-05, "Pretrain/Loss": 2.0522403717041016, "Pretrain/Loss (Raw)": 1.7997469902038574, "Pretrain/Step": 4741, "Pretrain/Step Time": 8.780614139512181} +{"Pretrain/Learning Rate": 2.6438238967269546e-05, "Pretrain/Loss": 2.050769090652466, "Pretrain/Loss (Raw)": 1.931627631187439, "Pretrain/Step": 4742, "Pretrain/Step Time": 8.773556627333164} +{"Pretrain/Learning Rate": 2.6429763072267317e-05, "Pretrain/Loss": 2.0514135360717773, "Pretrain/Loss (Raw)": 2.0801141262054443, "Pretrain/Step": 4743, "Pretrain/Step Time": 8.775628561154008} +{"Pretrain/Learning Rate": 2.642128701237807e-05, "Pretrain/Loss": 2.050471067428589, "Pretrain/Loss (Raw)": 1.8949885368347168, "Pretrain/Step": 4744, "Pretrain/Step Time": 8.775134224444628} +{"Pretrain/Learning Rate": 2.641281078857932e-05, "Pretrain/Loss": 2.0491552352905273, "Pretrain/Loss (Raw)": 2.0269718170166016, "Pretrain/Step": 4745, "Pretrain/Step Time": 8.780167326331139} +{"Pretrain/Learning Rate": 2.6404334401848558e-05, "Pretrain/Loss": 2.0500359535217285, "Pretrain/Loss (Raw)": 2.1916558742523193, "Pretrain/Step": 4746, "Pretrain/Step Time": 8.781029811128974} +{"Pretrain/Learning Rate": 2.6395857853163346e-05, "Pretrain/Loss": 2.0513863563537598, "Pretrain/Loss (Raw)": 2.0845351219177246, "Pretrain/Step": 4747, "Pretrain/Step Time": 8.782728157937527} +{"Pretrain/Learning Rate": 2.6387381143501217e-05, "Pretrain/Loss": 2.051288366317749, "Pretrain/Loss (Raw)": 2.111722230911255, "Pretrain/Step": 4748, "Pretrain/Step Time": 8.789569918066263} +{"Pretrain/Learning Rate": 2.6378904273839765e-05, "Pretrain/Loss": 2.0518252849578857, "Pretrain/Loss (Raw)": 2.1363601684570312, "Pretrain/Step": 4749, "Pretrain/Step Time": 8.7843326497823} +{"Pretrain/Learning Rate": 2.6370427245156574e-05, "Pretrain/Loss": 2.0521440505981445, "Pretrain/Loss (Raw)": 2.2023441791534424, "Pretrain/Step": 4750, "Pretrain/Step Time": 8.781516471877694} +{"Pretrain/Learning Rate": 2.6361950058429257e-05, "Pretrain/Loss": 2.053032398223877, "Pretrain/Loss (Raw)": 2.145834445953369, "Pretrain/Step": 4751, "Pretrain/Step Time": 8.783621922135353} +{"Pretrain/Learning Rate": 2.635347271463544e-05, "Pretrain/Loss": 2.0549535751342773, "Pretrain/Loss (Raw)": 2.025933265686035, "Pretrain/Step": 4752, "Pretrain/Step Time": 8.792970985174179} +{"Pretrain/Learning Rate": 2.6344995214752772e-05, "Pretrain/Loss": 2.0534801483154297, "Pretrain/Loss (Raw)": 1.967186689376831, "Pretrain/Step": 4753, "Pretrain/Step Time": 8.792407874017954} +{"Pretrain/Learning Rate": 2.6336517559758915e-05, "Pretrain/Loss": 2.0533080101013184, "Pretrain/Loss (Raw)": 2.0680761337280273, "Pretrain/Step": 4754, "Pretrain/Step Time": 8.79363708756864} +{"Pretrain/Learning Rate": 2.632803975063156e-05, "Pretrain/Loss": 2.0535151958465576, "Pretrain/Loss (Raw)": 2.0744919776916504, "Pretrain/Step": 4755, "Pretrain/Step Time": 8.792989114299417} +{"Pretrain/Learning Rate": 2.6319561788348402e-05, "Pretrain/Loss": 2.0548574924468994, "Pretrain/Loss (Raw)": 2.0260233879089355, "Pretrain/Step": 4756, "Pretrain/Step Time": 8.785780744627118} +{"Pretrain/Learning Rate": 2.6311083673887154e-05, "Pretrain/Loss": 2.0558528900146484, "Pretrain/Loss (Raw)": 2.18487811088562, "Pretrain/Step": 4757, "Pretrain/Step Time": 8.784198254346848} +{"Pretrain/Learning Rate": 2.6302605408225572e-05, "Pretrain/Loss": 2.0560073852539062, "Pretrain/Loss (Raw)": 1.9158670902252197, "Pretrain/Step": 4758, "Pretrain/Step Time": 8.784264849498868} +{"Pretrain/Learning Rate": 2.6294126992341382e-05, "Pretrain/Loss": 2.054436206817627, "Pretrain/Loss (Raw)": 2.097095251083374, "Pretrain/Step": 4759, "Pretrain/Step Time": 8.795238021761179} +{"Pretrain/Learning Rate": 2.628564842721238e-05, "Pretrain/Loss": 2.0548512935638428, "Pretrain/Loss (Raw)": 2.1255943775177, "Pretrain/Step": 4760, "Pretrain/Step Time": 8.783394472673535} +{"Pretrain/Learning Rate": 2.6277169713816337e-05, "Pretrain/Loss": 2.0525801181793213, "Pretrain/Loss (Raw)": 1.8938276767730713, "Pretrain/Step": 4761, "Pretrain/Step Time": 8.78906256519258} +{"Pretrain/Learning Rate": 2.6268690853131067e-05, "Pretrain/Loss": 2.0517873764038086, "Pretrain/Loss (Raw)": 1.9731813669204712, "Pretrain/Step": 4762, "Pretrain/Step Time": 8.787385553121567} +{"Pretrain/Learning Rate": 2.6260211846134387e-05, "Pretrain/Loss": 2.0521860122680664, "Pretrain/Loss (Raw)": 2.0928215980529785, "Pretrain/Step": 4763, "Pretrain/Step Time": 8.785403698682785} +{"Pretrain/Learning Rate": 2.6251732693804144e-05, "Pretrain/Loss": 2.054424524307251, "Pretrain/Loss (Raw)": 2.195834159851074, "Pretrain/Step": 4764, "Pretrain/Step Time": 8.78812750428915} +{"Pretrain/Learning Rate": 2.6243253397118178e-05, "Pretrain/Loss": 2.053328514099121, "Pretrain/Loss (Raw)": 2.1393957138061523, "Pretrain/Step": 4765, "Pretrain/Step Time": 8.787175487726927} +{"Pretrain/Learning Rate": 2.6234773957054383e-05, "Pretrain/Loss": 2.051731586456299, "Pretrain/Loss (Raw)": 1.9564889669418335, "Pretrain/Step": 4766, "Pretrain/Step Time": 8.793616767972708} +{"Pretrain/Learning Rate": 2.6226294374590638e-05, "Pretrain/Loss": 2.0521740913391113, "Pretrain/Loss (Raw)": 2.1060194969177246, "Pretrain/Step": 4767, "Pretrain/Step Time": 8.794176554307342} +{"Pretrain/Learning Rate": 2.6217814650704835e-05, "Pretrain/Loss": 2.0519261360168457, "Pretrain/Loss (Raw)": 2.0633485317230225, "Pretrain/Step": 4768, "Pretrain/Step Time": 8.792393490672112} +{"Pretrain/Learning Rate": 2.620933478637492e-05, "Pretrain/Loss": 2.0529189109802246, "Pretrain/Loss (Raw)": 2.03371262550354, "Pretrain/Step": 4769, "Pretrain/Step Time": 8.794071519747376} +{"Pretrain/Learning Rate": 2.620085478257881e-05, "Pretrain/Loss": 2.0520694255828857, "Pretrain/Loss (Raw)": 2.066049337387085, "Pretrain/Step": 4770, "Pretrain/Step Time": 8.795205106958747} +{"Pretrain/Learning Rate": 2.6192374640294477e-05, "Pretrain/Loss": 2.0521750450134277, "Pretrain/Loss (Raw)": 2.106955051422119, "Pretrain/Step": 4771, "Pretrain/Step Time": 8.798124959692359} +{"Pretrain/Learning Rate": 2.618389436049987e-05, "Pretrain/Loss": 2.051783561706543, "Pretrain/Loss (Raw)": 2.086329936981201, "Pretrain/Step": 4772, "Pretrain/Step Time": 8.794551590457559} +{"Pretrain/Learning Rate": 2.6175413944172995e-05, "Pretrain/Loss": 2.0502841472625732, "Pretrain/Loss (Raw)": 2.0190348625183105, "Pretrain/Step": 4773, "Pretrain/Step Time": 8.794298194348812} +{"Pretrain/Learning Rate": 2.6166933392291843e-05, "Pretrain/Loss": 2.049675941467285, "Pretrain/Loss (Raw)": 2.0907700061798096, "Pretrain/Step": 4774, "Pretrain/Step Time": 8.79321693815291} +{"Pretrain/Learning Rate": 2.6158452705834434e-05, "Pretrain/Loss": 2.0489978790283203, "Pretrain/Loss (Raw)": 2.0435521602630615, "Pretrain/Step": 4775, "Pretrain/Step Time": 8.7939110416919} +{"Pretrain/Learning Rate": 2.6149971885778795e-05, "Pretrain/Loss": 2.046978712081909, "Pretrain/Loss (Raw)": 1.7955915927886963, "Pretrain/Step": 4776, "Pretrain/Step Time": 8.79764425009489} +{"Pretrain/Learning Rate": 2.6141490933102987e-05, "Pretrain/Loss": 2.048032522201538, "Pretrain/Loss (Raw)": 2.0755863189697266, "Pretrain/Step": 4777, "Pretrain/Step Time": 8.797157138586044} +{"Pretrain/Learning Rate": 2.6133009848785062e-05, "Pretrain/Loss": 2.0479981899261475, "Pretrain/Loss (Raw)": 2.064056158065796, "Pretrain/Step": 4778, "Pretrain/Step Time": 8.793998623266816} +{"Pretrain/Learning Rate": 2.6124528633803103e-05, "Pretrain/Loss": 2.0485050678253174, "Pretrain/Loss (Raw)": 2.1064541339874268, "Pretrain/Step": 4779, "Pretrain/Step Time": 8.794596783816814} +{"Pretrain/Learning Rate": 2.61160472891352e-05, "Pretrain/Loss": 2.047945499420166, "Pretrain/Loss (Raw)": 2.1029365062713623, "Pretrain/Step": 4780, "Pretrain/Step Time": 8.798665402457118} +{"Pretrain/Learning Rate": 2.6107565815759473e-05, "Pretrain/Loss": 2.0486721992492676, "Pretrain/Loss (Raw)": 2.076979398727417, "Pretrain/Step": 4781, "Pretrain/Step Time": 8.78903253749013} +{"Pretrain/Learning Rate": 2.6099084214654034e-05, "Pretrain/Loss": 2.048506021499634, "Pretrain/Loss (Raw)": 2.0018439292907715, "Pretrain/Step": 4782, "Pretrain/Step Time": 8.790813315659761} +{"Pretrain/Learning Rate": 2.6090602486797017e-05, "Pretrain/Loss": 2.050950765609741, "Pretrain/Loss (Raw)": 2.195664644241333, "Pretrain/Step": 4783, "Pretrain/Step Time": 8.792743535712361} +{"Pretrain/Learning Rate": 2.608212063316659e-05, "Pretrain/Loss": 2.0519590377807617, "Pretrain/Loss (Raw)": 1.9822942018508911, "Pretrain/Step": 4784, "Pretrain/Step Time": 8.78869466856122} +{"Pretrain/Learning Rate": 2.6073638654740908e-05, "Pretrain/Loss": 2.0538673400878906, "Pretrain/Loss (Raw)": 2.133953809738159, "Pretrain/Step": 4785, "Pretrain/Step Time": 8.789481338113546} +{"Pretrain/Learning Rate": 2.606515655249816e-05, "Pretrain/Loss": 2.0533366203308105, "Pretrain/Loss (Raw)": 2.07462739944458, "Pretrain/Step": 4786, "Pretrain/Step Time": 8.785971818491817} +{"Pretrain/Learning Rate": 2.6056674327416537e-05, "Pretrain/Loss": 2.054657220840454, "Pretrain/Loss (Raw)": 2.2043991088867188, "Pretrain/Step": 4787, "Pretrain/Step Time": 8.7871263474226} +{"Pretrain/Learning Rate": 2.604819198047425e-05, "Pretrain/Loss": 2.056164503097534, "Pretrain/Loss (Raw)": 2.294130563735962, "Pretrain/Step": 4788, "Pretrain/Step Time": 8.782137053087354} +{"Pretrain/Learning Rate": 2.6039709512649522e-05, "Pretrain/Loss": 2.0560333728790283, "Pretrain/Loss (Raw)": 2.0311925411224365, "Pretrain/Step": 4789, "Pretrain/Step Time": 8.787861030548811} +{"Pretrain/Learning Rate": 2.60312269249206e-05, "Pretrain/Loss": 2.056358575820923, "Pretrain/Loss (Raw)": 2.091219663619995, "Pretrain/Step": 4790, "Pretrain/Step Time": 8.788530621677637} +{"Pretrain/Learning Rate": 2.602274421826573e-05, "Pretrain/Loss": 2.057518482208252, "Pretrain/Loss (Raw)": 2.1237127780914307, "Pretrain/Step": 4791, "Pretrain/Step Time": 8.78293089941144} +{"Pretrain/Learning Rate": 2.6014261393663176e-05, "Pretrain/Loss": 2.057460069656372, "Pretrain/Loss (Raw)": 2.101145029067993, "Pretrain/Step": 4792, "Pretrain/Step Time": 8.78538804128766} +{"Pretrain/Learning Rate": 2.600577845209122e-05, "Pretrain/Loss": 2.0585477352142334, "Pretrain/Loss (Raw)": 2.1301069259643555, "Pretrain/Step": 4793, "Pretrain/Step Time": 8.78334291651845} +{"Pretrain/Learning Rate": 2.599729539452815e-05, "Pretrain/Loss": 2.0555613040924072, "Pretrain/Loss (Raw)": 1.8389593362808228, "Pretrain/Step": 4794, "Pretrain/Step Time": 8.790016524493694} +{"Pretrain/Learning Rate": 2.598881222195228e-05, "Pretrain/Loss": 2.0580382347106934, "Pretrain/Loss (Raw)": 2.1265854835510254, "Pretrain/Step": 4795, "Pretrain/Step Time": 8.779911905527115} +{"Pretrain/Learning Rate": 2.5980328935341918e-05, "Pretrain/Loss": 2.058962345123291, "Pretrain/Loss (Raw)": 2.0884392261505127, "Pretrain/Step": 4796, "Pretrain/Step Time": 8.781738391146064} +{"Pretrain/Learning Rate": 2.597184553567541e-05, "Pretrain/Loss": 2.058652400970459, "Pretrain/Loss (Raw)": 2.018239974975586, "Pretrain/Step": 4797, "Pretrain/Step Time": 8.789331559091806} +{"Pretrain/Learning Rate": 2.5963362023931092e-05, "Pretrain/Loss": 2.058342456817627, "Pretrain/Loss (Raw)": 2.0754332542419434, "Pretrain/Step": 4798, "Pretrain/Step Time": 8.794576501473784} +{"Pretrain/Learning Rate": 2.595487840108733e-05, "Pretrain/Loss": 2.060209274291992, "Pretrain/Loss (Raw)": 2.2695415019989014, "Pretrain/Step": 4799, "Pretrain/Step Time": 8.791202398017049} +{"Pretrain/Learning Rate": 2.5946394668122485e-05, "Pretrain/Loss": 2.0605404376983643, "Pretrain/Loss (Raw)": 2.085709571838379, "Pretrain/Step": 4800, "Pretrain/Step Time": 8.791497146710753} +{"Pretrain/Learning Rate": 2.5937910826014955e-05, "Pretrain/Loss": 2.059225082397461, "Pretrain/Loss (Raw)": 1.989583134651184, "Pretrain/Step": 4801, "Pretrain/Step Time": 8.795316983014345} +{"Pretrain/Learning Rate": 2.5929426875743123e-05, "Pretrain/Loss": 2.0593101978302, "Pretrain/Loss (Raw)": 2.0306408405303955, "Pretrain/Step": 4802, "Pretrain/Step Time": 8.786792753264308} +{"Pretrain/Learning Rate": 2.592094281828541e-05, "Pretrain/Loss": 2.0599372386932373, "Pretrain/Loss (Raw)": 2.257150888442993, "Pretrain/Step": 4803, "Pretrain/Step Time": 8.789887934923172} +{"Pretrain/Learning Rate": 2.5912458654620226e-05, "Pretrain/Loss": 2.058964490890503, "Pretrain/Loss (Raw)": 2.053117275238037, "Pretrain/Step": 4804, "Pretrain/Step Time": 8.792272489517927} +{"Pretrain/Learning Rate": 2.5903974385726014e-05, "Pretrain/Loss": 2.057765245437622, "Pretrain/Loss (Raw)": 1.9702128171920776, "Pretrain/Step": 4805, "Pretrain/Step Time": 8.791717013344169} +{"Pretrain/Learning Rate": 2.589549001258121e-05, "Pretrain/Loss": 2.0568881034851074, "Pretrain/Loss (Raw)": 1.8468904495239258, "Pretrain/Step": 4806, "Pretrain/Step Time": 8.793952563777566} +{"Pretrain/Learning Rate": 2.5887005536164288e-05, "Pretrain/Loss": 2.056494951248169, "Pretrain/Loss (Raw)": 2.128650665283203, "Pretrain/Step": 4807, "Pretrain/Step Time": 8.795395471155643} +{"Pretrain/Learning Rate": 2.58785209574537e-05, "Pretrain/Loss": 2.05527925491333, "Pretrain/Loss (Raw)": 1.9597793817520142, "Pretrain/Step": 4808, "Pretrain/Step Time": 8.796741344034672} +{"Pretrain/Learning Rate": 2.587003627742794e-05, "Pretrain/Loss": 2.057795524597168, "Pretrain/Loss (Raw)": 2.008248805999756, "Pretrain/Step": 4809, "Pretrain/Step Time": 8.790179502218962} +{"Pretrain/Learning Rate": 2.5861551497065496e-05, "Pretrain/Loss": 2.056870937347412, "Pretrain/Loss (Raw)": 2.1043882369995117, "Pretrain/Step": 4810, "Pretrain/Step Time": 8.789672020822763} +{"Pretrain/Learning Rate": 2.5853066617344868e-05, "Pretrain/Loss": 2.055233955383301, "Pretrain/Loss (Raw)": 1.9824410676956177, "Pretrain/Step": 4811, "Pretrain/Step Time": 8.791286008432508} +{"Pretrain/Learning Rate": 2.5844581639244586e-05, "Pretrain/Loss": 2.056658983230591, "Pretrain/Loss (Raw)": 2.235250949859619, "Pretrain/Step": 4812, "Pretrain/Step Time": 8.789397755637765} +{"Pretrain/Learning Rate": 2.583609656374316e-05, "Pretrain/Loss": 2.0558104515075684, "Pretrain/Loss (Raw)": 2.0998122692108154, "Pretrain/Step": 4813, "Pretrain/Step Time": 8.789946258068085} +{"Pretrain/Learning Rate": 2.5827611391819152e-05, "Pretrain/Loss": 2.0584897994995117, "Pretrain/Loss (Raw)": 2.0125300884246826, "Pretrain/Step": 4814, "Pretrain/Step Time": 8.79252290725708} +{"Pretrain/Learning Rate": 2.581912612445108e-05, "Pretrain/Loss": 2.057157516479492, "Pretrain/Loss (Raw)": 1.997314691543579, "Pretrain/Step": 4815, "Pretrain/Step Time": 8.792583722621202} +{"Pretrain/Learning Rate": 2.5810640762617538e-05, "Pretrain/Loss": 2.0568296909332275, "Pretrain/Loss (Raw)": 1.9435861110687256, "Pretrain/Step": 4816, "Pretrain/Step Time": 8.783169774338603} +{"Pretrain/Learning Rate": 2.5802155307297077e-05, "Pretrain/Loss": 2.05521821975708, "Pretrain/Loss (Raw)": 1.9545477628707886, "Pretrain/Step": 4817, "Pretrain/Step Time": 8.783809242770076} +{"Pretrain/Learning Rate": 2.5793669759468292e-05, "Pretrain/Loss": 2.054905652999878, "Pretrain/Loss (Raw)": 1.9637612104415894, "Pretrain/Step": 4818, "Pretrain/Step Time": 8.786244129762053} +{"Pretrain/Learning Rate": 2.578518412010976e-05, "Pretrain/Loss": 2.05552339553833, "Pretrain/Loss (Raw)": 2.0738394260406494, "Pretrain/Step": 4819, "Pretrain/Step Time": 8.791079277172685} +{"Pretrain/Learning Rate": 2.577669839020011e-05, "Pretrain/Loss": 2.053452968597412, "Pretrain/Loss (Raw)": 1.9840419292449951, "Pretrain/Step": 4820, "Pretrain/Step Time": 8.784858888015151} +{"Pretrain/Learning Rate": 2.576821257071793e-05, "Pretrain/Loss": 2.051290988922119, "Pretrain/Loss (Raw)": 1.9629693031311035, "Pretrain/Step": 4821, "Pretrain/Step Time": 8.783135309815407} +{"Pretrain/Learning Rate": 2.5759726662641865e-05, "Pretrain/Loss": 2.0503413677215576, "Pretrain/Loss (Raw)": 2.1194584369659424, "Pretrain/Step": 4822, "Pretrain/Step Time": 8.78399521112442} +{"Pretrain/Learning Rate": 2.5751240666950532e-05, "Pretrain/Loss": 2.051591396331787, "Pretrain/Loss (Raw)": 2.0748414993286133, "Pretrain/Step": 4823, "Pretrain/Step Time": 8.791344096884131} +{"Pretrain/Learning Rate": 2.5742754584622592e-05, "Pretrain/Loss": 2.0489230155944824, "Pretrain/Loss (Raw)": 1.8014317750930786, "Pretrain/Step": 4824, "Pretrain/Step Time": 8.790832594037056} +{"Pretrain/Learning Rate": 2.5734268416636697e-05, "Pretrain/Loss": 2.047638416290283, "Pretrain/Loss (Raw)": 1.9751921892166138, "Pretrain/Step": 4825, "Pretrain/Step Time": 8.792381012812257} +{"Pretrain/Learning Rate": 2.5725782163971495e-05, "Pretrain/Loss": 2.0475080013275146, "Pretrain/Loss (Raw)": 2.041067361831665, "Pretrain/Step": 4826, "Pretrain/Step Time": 8.79678906314075} +{"Pretrain/Learning Rate": 2.5717295827605686e-05, "Pretrain/Loss": 2.050936698913574, "Pretrain/Loss (Raw)": 2.185910940170288, "Pretrain/Step": 4827, "Pretrain/Step Time": 8.789062855765224} +{"Pretrain/Learning Rate": 2.5708809408517937e-05, "Pretrain/Loss": 2.051060199737549, "Pretrain/Loss (Raw)": 2.1198182106018066, "Pretrain/Step": 4828, "Pretrain/Step Time": 8.792116101831198} +{"Pretrain/Learning Rate": 2.5700322907686946e-05, "Pretrain/Loss": 2.0499014854431152, "Pretrain/Loss (Raw)": 1.9552794694900513, "Pretrain/Step": 4829, "Pretrain/Step Time": 8.801026115193963} +{"Pretrain/Learning Rate": 2.5691836326091414e-05, "Pretrain/Loss": 2.0488178730010986, "Pretrain/Loss (Raw)": 2.101168394088745, "Pretrain/Step": 4830, "Pretrain/Step Time": 8.796372964978218} +{"Pretrain/Learning Rate": 2.5683349664710067e-05, "Pretrain/Loss": 2.0496368408203125, "Pretrain/Loss (Raw)": 2.050100803375244, "Pretrain/Step": 4831, "Pretrain/Step Time": 8.790412161499262} +{"Pretrain/Learning Rate": 2.5674862924521605e-05, "Pretrain/Loss": 2.051813840866089, "Pretrain/Loss (Raw)": 2.1130056381225586, "Pretrain/Step": 4832, "Pretrain/Step Time": 8.782821133732796} +{"Pretrain/Learning Rate": 2.566637610650478e-05, "Pretrain/Loss": 2.049984931945801, "Pretrain/Loss (Raw)": 1.822258472442627, "Pretrain/Step": 4833, "Pretrain/Step Time": 8.79047616571188} +{"Pretrain/Learning Rate": 2.565788921163832e-05, "Pretrain/Loss": 2.05112886428833, "Pretrain/Loss (Raw)": 2.095592975616455, "Pretrain/Step": 4834, "Pretrain/Step Time": 8.788178039714694} +{"Pretrain/Learning Rate": 2.5649402240900972e-05, "Pretrain/Loss": 2.051741361618042, "Pretrain/Loss (Raw)": 2.0903432369232178, "Pretrain/Step": 4835, "Pretrain/Step Time": 8.786926604807377} +{"Pretrain/Learning Rate": 2.5640915195271504e-05, "Pretrain/Loss": 2.052539348602295, "Pretrain/Loss (Raw)": 2.126241445541382, "Pretrain/Step": 4836, "Pretrain/Step Time": 8.786122838035226} +{"Pretrain/Learning Rate": 2.563242807572867e-05, "Pretrain/Loss": 2.053055763244629, "Pretrain/Loss (Raw)": 2.2210922241210938, "Pretrain/Step": 4837, "Pretrain/Step Time": 8.79390567354858} +{"Pretrain/Learning Rate": 2.5623940883251256e-05, "Pretrain/Loss": 2.0537776947021484, "Pretrain/Loss (Raw)": 2.0485897064208984, "Pretrain/Step": 4838, "Pretrain/Step Time": 8.793242180719972} +{"Pretrain/Learning Rate": 2.561545361881803e-05, "Pretrain/Loss": 2.0562915802001953, "Pretrain/Loss (Raw)": 2.1621546745300293, "Pretrain/Step": 4839, "Pretrain/Step Time": 8.788746561855078} +{"Pretrain/Learning Rate": 2.5606966283407803e-05, "Pretrain/Loss": 2.057182788848877, "Pretrain/Loss (Raw)": 2.022057294845581, "Pretrain/Step": 4840, "Pretrain/Step Time": 8.790656555444002} +{"Pretrain/Learning Rate": 2.5598478877999356e-05, "Pretrain/Loss": 2.054793357849121, "Pretrain/Loss (Raw)": 1.8384722471237183, "Pretrain/Step": 4841, "Pretrain/Step Time": 8.789265440776944} +{"Pretrain/Learning Rate": 2.558999140357151e-05, "Pretrain/Loss": 2.0541417598724365, "Pretrain/Loss (Raw)": 2.0171406269073486, "Pretrain/Step": 4842, "Pretrain/Step Time": 8.786159353330731} +{"Pretrain/Learning Rate": 2.5581503861103073e-05, "Pretrain/Loss": 2.0533576011657715, "Pretrain/Loss (Raw)": 1.995011806488037, "Pretrain/Step": 4843, "Pretrain/Step Time": 8.78757580369711} +{"Pretrain/Learning Rate": 2.5573016251572872e-05, "Pretrain/Loss": 2.054220676422119, "Pretrain/Loss (Raw)": 2.151252031326294, "Pretrain/Step": 4844, "Pretrain/Step Time": 8.790585761889815} +{"Pretrain/Learning Rate": 2.5564528575959733e-05, "Pretrain/Loss": 2.0544705390930176, "Pretrain/Loss (Raw)": 2.0301413536071777, "Pretrain/Step": 4845, "Pretrain/Step Time": 8.791280107572675} +{"Pretrain/Learning Rate": 2.55560408352425e-05, "Pretrain/Loss": 2.051970958709717, "Pretrain/Loss (Raw)": 1.8496925830841064, "Pretrain/Step": 4846, "Pretrain/Step Time": 8.787576166912913} +{"Pretrain/Learning Rate": 2.5547553030400016e-05, "Pretrain/Loss": 2.0541892051696777, "Pretrain/Loss (Raw)": 2.121084690093994, "Pretrain/Step": 4847, "Pretrain/Step Time": 8.791391268372536} +{"Pretrain/Learning Rate": 2.5539065162411143e-05, "Pretrain/Loss": 2.053325891494751, "Pretrain/Loss (Raw)": 1.9758821725845337, "Pretrain/Step": 4848, "Pretrain/Step Time": 8.792742881923914} +{"Pretrain/Learning Rate": 2.5530577232254733e-05, "Pretrain/Loss": 2.0520753860473633, "Pretrain/Loss (Raw)": 1.9657931327819824, "Pretrain/Step": 4849, "Pretrain/Step Time": 8.792918629944324} +{"Pretrain/Learning Rate": 2.5522089240909652e-05, "Pretrain/Loss": 2.0538482666015625, "Pretrain/Loss (Raw)": 2.0414109230041504, "Pretrain/Step": 4850, "Pretrain/Step Time": 8.792205972597003} +{"Pretrain/Learning Rate": 2.5513601189354786e-05, "Pretrain/Loss": 2.0523481369018555, "Pretrain/Loss (Raw)": 2.000422716140747, "Pretrain/Step": 4851, "Pretrain/Step Time": 8.808053445070982} +{"Pretrain/Learning Rate": 2.5505113078569004e-05, "Pretrain/Loss": 2.0528221130371094, "Pretrain/Loss (Raw)": 2.1525509357452393, "Pretrain/Step": 4852, "Pretrain/Step Time": 8.80150630325079} +{"Pretrain/Learning Rate": 2.5496624909531207e-05, "Pretrain/Loss": 2.0498104095458984, "Pretrain/Loss (Raw)": 1.94217050075531, "Pretrain/Step": 4853, "Pretrain/Step Time": 8.798846527934074} +{"Pretrain/Learning Rate": 2.548813668322028e-05, "Pretrain/Loss": 2.0488522052764893, "Pretrain/Loss (Raw)": 1.9354075193405151, "Pretrain/Step": 4854, "Pretrain/Step Time": 8.804641557857394} +{"Pretrain/Learning Rate": 2.5479648400615136e-05, "Pretrain/Loss": 2.048886299133301, "Pretrain/Loss (Raw)": 2.0756726264953613, "Pretrain/Step": 4855, "Pretrain/Step Time": 8.795694101601839} +{"Pretrain/Learning Rate": 2.547116006269467e-05, "Pretrain/Loss": 2.0506458282470703, "Pretrain/Loss (Raw)": 2.2108800411224365, "Pretrain/Step": 4856, "Pretrain/Step Time": 8.793695924803615} +{"Pretrain/Learning Rate": 2.5462671670437816e-05, "Pretrain/Loss": 2.048689365386963, "Pretrain/Loss (Raw)": 1.9452295303344727, "Pretrain/Step": 4857, "Pretrain/Step Time": 8.80754409916699} +{"Pretrain/Learning Rate": 2.545418322482348e-05, "Pretrain/Loss": 2.0518085956573486, "Pretrain/Loss (Raw)": 2.227753162384033, "Pretrain/Step": 4858, "Pretrain/Step Time": 8.802363060414791} +{"Pretrain/Learning Rate": 2.5445694726830593e-05, "Pretrain/Loss": 2.052152395248413, "Pretrain/Loss (Raw)": 1.9813055992126465, "Pretrain/Step": 4859, "Pretrain/Step Time": 8.805565698072314} +{"Pretrain/Learning Rate": 2.543720617743809e-05, "Pretrain/Loss": 2.0517115592956543, "Pretrain/Loss (Raw)": 2.0753774642944336, "Pretrain/Step": 4860, "Pretrain/Step Time": 8.806763008236885} +{"Pretrain/Learning Rate": 2.5428717577624915e-05, "Pretrain/Loss": 2.0507445335388184, "Pretrain/Loss (Raw)": 1.8863120079040527, "Pretrain/Step": 4861, "Pretrain/Step Time": 8.806695522740483} +{"Pretrain/Learning Rate": 2.5420228928370005e-05, "Pretrain/Loss": 2.050147533416748, "Pretrain/Loss (Raw)": 2.0592143535614014, "Pretrain/Step": 4862, "Pretrain/Step Time": 8.798619961366057} +{"Pretrain/Learning Rate": 2.5411740230652315e-05, "Pretrain/Loss": 2.0504913330078125, "Pretrain/Loss (Raw)": 2.051297426223755, "Pretrain/Step": 4863, "Pretrain/Step Time": 8.799858309328556} +{"Pretrain/Learning Rate": 2.5403251485450795e-05, "Pretrain/Loss": 2.0490589141845703, "Pretrain/Loss (Raw)": 1.9513776302337646, "Pretrain/Step": 4864, "Pretrain/Step Time": 8.80293196067214} +{"Pretrain/Learning Rate": 2.5394762693744428e-05, "Pretrain/Loss": 2.0511789321899414, "Pretrain/Loss (Raw)": 2.284376621246338, "Pretrain/Step": 4865, "Pretrain/Step Time": 8.798876017332077} +{"Pretrain/Learning Rate": 2.538627385651216e-05, "Pretrain/Loss": 2.0520195960998535, "Pretrain/Loss (Raw)": 2.1575522422790527, "Pretrain/Step": 4866, "Pretrain/Step Time": 8.798380682244897} +{"Pretrain/Learning Rate": 2.5377784974732965e-05, "Pretrain/Loss": 2.0515527725219727, "Pretrain/Loss (Raw)": 2.008666515350342, "Pretrain/Step": 4867, "Pretrain/Step Time": 8.803113849833608} +{"Pretrain/Learning Rate": 2.536929604938584e-05, "Pretrain/Loss": 2.052093267440796, "Pretrain/Loss (Raw)": 2.004948854446411, "Pretrain/Step": 4868, "Pretrain/Step Time": 8.801348919048905} +{"Pretrain/Learning Rate": 2.5360807081449738e-05, "Pretrain/Loss": 2.0538973808288574, "Pretrain/Loss (Raw)": 2.0306894779205322, "Pretrain/Step": 4869, "Pretrain/Step Time": 8.799896759912372} +{"Pretrain/Learning Rate": 2.5352318071903675e-05, "Pretrain/Loss": 2.055264949798584, "Pretrain/Loss (Raw)": 2.1066601276397705, "Pretrain/Step": 4870, "Pretrain/Step Time": 8.799854833632708} +{"Pretrain/Learning Rate": 2.5343829021726618e-05, "Pretrain/Loss": 2.0540804862976074, "Pretrain/Loss (Raw)": 1.9285094738006592, "Pretrain/Step": 4871, "Pretrain/Step Time": 8.799140820279717} +{"Pretrain/Learning Rate": 2.533533993189759e-05, "Pretrain/Loss": 2.053864002227783, "Pretrain/Loss (Raw)": 1.867293357849121, "Pretrain/Step": 4872, "Pretrain/Step Time": 8.803722940385342} +{"Pretrain/Learning Rate": 2.5326850803395575e-05, "Pretrain/Loss": 2.053781032562256, "Pretrain/Loss (Raw)": 2.016340732574463, "Pretrain/Step": 4873, "Pretrain/Step Time": 8.7966063413769} +{"Pretrain/Learning Rate": 2.5318361637199594e-05, "Pretrain/Loss": 2.051835775375366, "Pretrain/Loss (Raw)": 1.942655086517334, "Pretrain/Step": 4874, "Pretrain/Step Time": 8.799476074054837} +{"Pretrain/Learning Rate": 2.5309872434288645e-05, "Pretrain/Loss": 2.0525379180908203, "Pretrain/Loss (Raw)": 2.1744096279144287, "Pretrain/Step": 4875, "Pretrain/Step Time": 8.79673932865262} +{"Pretrain/Learning Rate": 2.5301383195641742e-05, "Pretrain/Loss": 2.0518271923065186, "Pretrain/Loss (Raw)": 2.0207505226135254, "Pretrain/Step": 4876, "Pretrain/Step Time": 8.793261397629976} +{"Pretrain/Learning Rate": 2.5292893922237913e-05, "Pretrain/Loss": 2.050662040710449, "Pretrain/Loss (Raw)": 1.9872134923934937, "Pretrain/Step": 4877, "Pretrain/Step Time": 8.793640898540616} +{"Pretrain/Learning Rate": 2.5284404615056172e-05, "Pretrain/Loss": 2.05078125, "Pretrain/Loss (Raw)": 2.2176127433776855, "Pretrain/Step": 4878, "Pretrain/Step Time": 8.795992113649845} +{"Pretrain/Learning Rate": 2.5275915275075556e-05, "Pretrain/Loss": 2.0485639572143555, "Pretrain/Loss (Raw)": 1.8620338439941406, "Pretrain/Step": 4879, "Pretrain/Step Time": 8.802786480635405} +{"Pretrain/Learning Rate": 2.5267425903275088e-05, "Pretrain/Loss": 2.049461841583252, "Pretrain/Loss (Raw)": 2.140829086303711, "Pretrain/Step": 4880, "Pretrain/Step Time": 8.785383807495236} +{"Pretrain/Learning Rate": 2.5258936500633807e-05, "Pretrain/Loss": 2.049530029296875, "Pretrain/Loss (Raw)": 1.9759397506713867, "Pretrain/Step": 4881, "Pretrain/Step Time": 8.791378699243069} +{"Pretrain/Learning Rate": 2.5250447068130746e-05, "Pretrain/Loss": 2.048649549484253, "Pretrain/Loss (Raw)": 1.9553829431533813, "Pretrain/Step": 4882, "Pretrain/Step Time": 8.789580063894391} +{"Pretrain/Learning Rate": 2.5241957606744952e-05, "Pretrain/Loss": 2.0483012199401855, "Pretrain/Loss (Raw)": 2.0298943519592285, "Pretrain/Step": 4883, "Pretrain/Step Time": 8.792676767334342} +{"Pretrain/Learning Rate": 2.523346811745546e-05, "Pretrain/Loss": 2.048664093017578, "Pretrain/Loss (Raw)": 2.0724682807922363, "Pretrain/Step": 4884, "Pretrain/Step Time": 8.793791849166155} +{"Pretrain/Learning Rate": 2.5224978601241333e-05, "Pretrain/Loss": 2.0474867820739746, "Pretrain/Loss (Raw)": 2.034207820892334, "Pretrain/Step": 4885, "Pretrain/Step Time": 8.794515825808048} +{"Pretrain/Learning Rate": 2.5216489059081607e-05, "Pretrain/Loss": 2.0487217903137207, "Pretrain/Loss (Raw)": 2.073909044265747, "Pretrain/Step": 4886, "Pretrain/Step Time": 8.805294459685683} +{"Pretrain/Learning Rate": 2.5207999491955347e-05, "Pretrain/Loss": 2.0480847358703613, "Pretrain/Loss (Raw)": 2.015573263168335, "Pretrain/Step": 4887, "Pretrain/Step Time": 8.79200904816389} +{"Pretrain/Learning Rate": 2.51995099008416e-05, "Pretrain/Loss": 2.0476608276367188, "Pretrain/Loss (Raw)": 2.071309804916382, "Pretrain/Step": 4888, "Pretrain/Step Time": 8.801048835739493} +{"Pretrain/Learning Rate": 2.519102028671944e-05, "Pretrain/Loss": 2.0494186878204346, "Pretrain/Loss (Raw)": 2.1188461780548096, "Pretrain/Step": 4889, "Pretrain/Step Time": 8.79971350543201} +{"Pretrain/Learning Rate": 2.518253065056791e-05, "Pretrain/Loss": 2.0509305000305176, "Pretrain/Loss (Raw)": 2.166691303253174, "Pretrain/Step": 4890, "Pretrain/Step Time": 8.80299817956984} +{"Pretrain/Learning Rate": 2.5174040993366094e-05, "Pretrain/Loss": 2.051609516143799, "Pretrain/Loss (Raw)": 2.179734230041504, "Pretrain/Step": 4891, "Pretrain/Step Time": 8.80288759805262} +{"Pretrain/Learning Rate": 2.516555131609305e-05, "Pretrain/Loss": 2.0503993034362793, "Pretrain/Loss (Raw)": 2.0409128665924072, "Pretrain/Step": 4892, "Pretrain/Step Time": 8.799926660954952} +{"Pretrain/Learning Rate": 2.5157061619727844e-05, "Pretrain/Loss": 2.0493264198303223, "Pretrain/Loss (Raw)": 2.0021026134490967, "Pretrain/Step": 4893, "Pretrain/Step Time": 8.802750932052732} +{"Pretrain/Learning Rate": 2.514857190524955e-05, "Pretrain/Loss": 2.049750804901123, "Pretrain/Loss (Raw)": 2.0108120441436768, "Pretrain/Step": 4894, "Pretrain/Step Time": 8.794174222275615} +{"Pretrain/Learning Rate": 2.514008217363725e-05, "Pretrain/Loss": 2.049834728240967, "Pretrain/Loss (Raw)": 2.116755723953247, "Pretrain/Step": 4895, "Pretrain/Step Time": 8.792557917535305} +{"Pretrain/Learning Rate": 2.513159242587001e-05, "Pretrain/Loss": 2.049473285675049, "Pretrain/Loss (Raw)": 2.0170998573303223, "Pretrain/Step": 4896, "Pretrain/Step Time": 8.795468980446458} +{"Pretrain/Learning Rate": 2.5123102662926913e-05, "Pretrain/Loss": 2.0508127212524414, "Pretrain/Loss (Raw)": 2.2051315307617188, "Pretrain/Step": 4897, "Pretrain/Step Time": 8.797198681160808} +{"Pretrain/Learning Rate": 2.5114612885787037e-05, "Pretrain/Loss": 2.051875591278076, "Pretrain/Loss (Raw)": 2.2021193504333496, "Pretrain/Step": 4898, "Pretrain/Step Time": 8.799420483410358} +{"Pretrain/Learning Rate": 2.5106123095429456e-05, "Pretrain/Loss": 2.0517420768737793, "Pretrain/Loss (Raw)": 2.0898563861846924, "Pretrain/Step": 4899, "Pretrain/Step Time": 8.797553472220898} +{"Pretrain/Learning Rate": 2.5097633292833268e-05, "Pretrain/Loss": 2.0509767532348633, "Pretrain/Loss (Raw)": 1.9883495569229126, "Pretrain/Step": 4900, "Pretrain/Step Time": 8.802835317328572} +{"Pretrain/Learning Rate": 2.5089143478977546e-05, "Pretrain/Loss": 2.049741744995117, "Pretrain/Loss (Raw)": 1.860979676246643, "Pretrain/Step": 4901, "Pretrain/Step Time": 8.799825483933091} +{"Pretrain/Learning Rate": 2.5080653654841378e-05, "Pretrain/Loss": 2.049973964691162, "Pretrain/Loss (Raw)": 2.1204922199249268, "Pretrain/Step": 4902, "Pretrain/Step Time": 8.798261983320117} +{"Pretrain/Learning Rate": 2.507216382140385e-05, "Pretrain/Loss": 2.0506606101989746, "Pretrain/Loss (Raw)": 2.1314210891723633, "Pretrain/Step": 4903, "Pretrain/Step Time": 8.79340042360127} +{"Pretrain/Learning Rate": 2.5063673979644054e-05, "Pretrain/Loss": 2.0527548789978027, "Pretrain/Loss (Raw)": 2.063673973083496, "Pretrain/Step": 4904, "Pretrain/Step Time": 8.792476331815124} +{"Pretrain/Learning Rate": 2.5055184130541065e-05, "Pretrain/Loss": 2.049513816833496, "Pretrain/Loss (Raw)": 1.660733938217163, "Pretrain/Step": 4905, "Pretrain/Step Time": 8.793842032551765} +{"Pretrain/Learning Rate": 2.504669427507399e-05, "Pretrain/Loss": 2.048007011413574, "Pretrain/Loss (Raw)": 1.871170997619629, "Pretrain/Step": 4906, "Pretrain/Step Time": 8.795290119946003} +{"Pretrain/Learning Rate": 2.503820441422191e-05, "Pretrain/Loss": 2.046778678894043, "Pretrain/Loss (Raw)": 1.9492205381393433, "Pretrain/Step": 4907, "Pretrain/Step Time": 8.797652177512646} +{"Pretrain/Learning Rate": 2.5029714548963917e-05, "Pretrain/Loss": 2.045654773712158, "Pretrain/Loss (Raw)": 1.959089756011963, "Pretrain/Step": 4908, "Pretrain/Step Time": 8.79137966223061} +{"Pretrain/Learning Rate": 2.5021224680279105e-05, "Pretrain/Loss": 2.0454955101013184, "Pretrain/Loss (Raw)": 2.0565850734710693, "Pretrain/Step": 4909, "Pretrain/Step Time": 8.791953755542636} +{"Pretrain/Learning Rate": 2.5012734809146554e-05, "Pretrain/Loss": 2.0462701320648193, "Pretrain/Loss (Raw)": 2.101001501083374, "Pretrain/Step": 4910, "Pretrain/Step Time": 8.790148658677936} +{"Pretrain/Learning Rate": 2.5004244936545374e-05, "Pretrain/Loss": 2.0452444553375244, "Pretrain/Loss (Raw)": 2.0643627643585205, "Pretrain/Step": 4911, "Pretrain/Step Time": 8.794395482167602} +{"Pretrain/Learning Rate": 2.499575506345464e-05, "Pretrain/Loss": 2.0459752082824707, "Pretrain/Loss (Raw)": 2.0758469104766846, "Pretrain/Step": 4912, "Pretrain/Step Time": 8.797119157388806} +{"Pretrain/Learning Rate": 2.498726519085345e-05, "Pretrain/Loss": 2.0465145111083984, "Pretrain/Loss (Raw)": 2.2029683589935303, "Pretrain/Step": 4913, "Pretrain/Step Time": 8.795465750619769} +{"Pretrain/Learning Rate": 2.497877531972091e-05, "Pretrain/Loss": 2.045097589492798, "Pretrain/Loss (Raw)": 1.8932979106903076, "Pretrain/Step": 4914, "Pretrain/Step Time": 8.804611476138234} +{"Pretrain/Learning Rate": 2.497028545103609e-05, "Pretrain/Loss": 2.0433740615844727, "Pretrain/Loss (Raw)": 1.9837522506713867, "Pretrain/Step": 4915, "Pretrain/Step Time": 8.798082455992699} +{"Pretrain/Learning Rate": 2.49617955857781e-05, "Pretrain/Loss": 2.041466474533081, "Pretrain/Loss (Raw)": 2.0499660968780518, "Pretrain/Step": 4916, "Pretrain/Step Time": 8.796921553090215} +{"Pretrain/Learning Rate": 2.4953305724926017e-05, "Pretrain/Loss": 2.0411107540130615, "Pretrain/Loss (Raw)": 1.9856795072555542, "Pretrain/Step": 4917, "Pretrain/Step Time": 8.792368603870273} +{"Pretrain/Learning Rate": 2.494481586945894e-05, "Pretrain/Loss": 2.037829637527466, "Pretrain/Loss (Raw)": 1.6712347269058228, "Pretrain/Step": 4918, "Pretrain/Step Time": 8.801417278125882} +{"Pretrain/Learning Rate": 2.4936326020355955e-05, "Pretrain/Loss": 2.036970376968384, "Pretrain/Loss (Raw)": 2.0136959552764893, "Pretrain/Step": 4919, "Pretrain/Step Time": 8.803440174087882} +{"Pretrain/Learning Rate": 2.4927836178596156e-05, "Pretrain/Loss": 2.038208246231079, "Pretrain/Loss (Raw)": 2.259615898132324, "Pretrain/Step": 4920, "Pretrain/Step Time": 8.801261477172375} +{"Pretrain/Learning Rate": 2.4919346345158624e-05, "Pretrain/Loss": 2.03817081451416, "Pretrain/Loss (Raw)": 2.12532901763916, "Pretrain/Step": 4921, "Pretrain/Step Time": 8.798711558803916} +{"Pretrain/Learning Rate": 2.491085652102246e-05, "Pretrain/Loss": 2.039334774017334, "Pretrain/Loss (Raw)": 1.9879380464553833, "Pretrain/Step": 4922, "Pretrain/Step Time": 8.80090950615704} +{"Pretrain/Learning Rate": 2.4902366707166734e-05, "Pretrain/Loss": 2.0392465591430664, "Pretrain/Loss (Raw)": 2.1152687072753906, "Pretrain/Step": 4923, "Pretrain/Step Time": 8.809927524998784} +{"Pretrain/Learning Rate": 2.4893876904570554e-05, "Pretrain/Loss": 2.039695978164673, "Pretrain/Loss (Raw)": 2.145988941192627, "Pretrain/Step": 4924, "Pretrain/Step Time": 8.806758373975754} +{"Pretrain/Learning Rate": 2.488538711421297e-05, "Pretrain/Loss": 2.041184425354004, "Pretrain/Loss (Raw)": 2.208770513534546, "Pretrain/Step": 4925, "Pretrain/Step Time": 8.79966893978417} +{"Pretrain/Learning Rate": 2.4876897337073103e-05, "Pretrain/Loss": 2.040465831756592, "Pretrain/Loss (Raw)": 1.9834460020065308, "Pretrain/Step": 4926, "Pretrain/Step Time": 8.794770205393434} +{"Pretrain/Learning Rate": 2.4868407574129994e-05, "Pretrain/Loss": 2.0398168563842773, "Pretrain/Loss (Raw)": 2.1864497661590576, "Pretrain/Step": 4927, "Pretrain/Step Time": 8.793917315080762} +{"Pretrain/Learning Rate": 2.4859917826362764e-05, "Pretrain/Loss": 2.0411572456359863, "Pretrain/Loss (Raw)": 2.2572691440582275, "Pretrain/Step": 4928, "Pretrain/Step Time": 8.792350087314844} +{"Pretrain/Learning Rate": 2.485142809475045e-05, "Pretrain/Loss": 2.0401723384857178, "Pretrain/Loss (Raw)": 1.8635457754135132, "Pretrain/Step": 4929, "Pretrain/Step Time": 8.802013024687767} +{"Pretrain/Learning Rate": 2.4842938380272168e-05, "Pretrain/Loss": 2.039862632751465, "Pretrain/Loss (Raw)": 1.991006851196289, "Pretrain/Step": 4930, "Pretrain/Step Time": 8.798697588965297} +{"Pretrain/Learning Rate": 2.4834448683906957e-05, "Pretrain/Loss": 2.0384421348571777, "Pretrain/Loss (Raw)": 2.0752813816070557, "Pretrain/Step": 4931, "Pretrain/Step Time": 8.79584689065814} +{"Pretrain/Learning Rate": 2.482595900663392e-05, "Pretrain/Loss": 2.0387773513793945, "Pretrain/Loss (Raw)": 2.096035957336426, "Pretrain/Step": 4932, "Pretrain/Step Time": 8.790979137644172} +{"Pretrain/Learning Rate": 2.481746934943209e-05, "Pretrain/Loss": 2.039794921875, "Pretrain/Loss (Raw)": 2.100499391555786, "Pretrain/Step": 4933, "Pretrain/Step Time": 8.791886106133461} +{"Pretrain/Learning Rate": 2.480897971328056e-05, "Pretrain/Loss": 2.04030179977417, "Pretrain/Loss (Raw)": 1.911744475364685, "Pretrain/Step": 4934, "Pretrain/Step Time": 8.790695732459426} +{"Pretrain/Learning Rate": 2.4800490099158403e-05, "Pretrain/Loss": 2.039092540740967, "Pretrain/Loss (Raw)": 1.9738825559616089, "Pretrain/Step": 4935, "Pretrain/Step Time": 8.79045932367444} +{"Pretrain/Learning Rate": 2.4792000508044652e-05, "Pretrain/Loss": 2.0416805744171143, "Pretrain/Loss (Raw)": 2.2910373210906982, "Pretrain/Step": 4936, "Pretrain/Step Time": 8.797743935137987} +{"Pretrain/Learning Rate": 2.4783510940918396e-05, "Pretrain/Loss": 2.042623519897461, "Pretrain/Loss (Raw)": 2.1289660930633545, "Pretrain/Step": 4937, "Pretrain/Step Time": 8.797060437500477} +{"Pretrain/Learning Rate": 2.4775021398758666e-05, "Pretrain/Loss": 2.0428738594055176, "Pretrain/Loss (Raw)": 2.1363985538482666, "Pretrain/Step": 4938, "Pretrain/Step Time": 8.803192237392068} +{"Pretrain/Learning Rate": 2.4766531882544545e-05, "Pretrain/Loss": 2.0436887741088867, "Pretrain/Loss (Raw)": 2.086750030517578, "Pretrain/Step": 4939, "Pretrain/Step Time": 8.797964010387659} +{"Pretrain/Learning Rate": 2.475804239325505e-05, "Pretrain/Loss": 2.040675163269043, "Pretrain/Loss (Raw)": 1.8495084047317505, "Pretrain/Step": 4940, "Pretrain/Step Time": 8.801637602970004} +{"Pretrain/Learning Rate": 2.474955293186926e-05, "Pretrain/Loss": 2.0399017333984375, "Pretrain/Loss (Raw)": 2.000802755355835, "Pretrain/Step": 4941, "Pretrain/Step Time": 8.794677957892418} +{"Pretrain/Learning Rate": 2.4741063499366195e-05, "Pretrain/Loss": 2.039958953857422, "Pretrain/Loss (Raw)": 2.019906997680664, "Pretrain/Step": 4942, "Pretrain/Step Time": 8.78852883912623} +{"Pretrain/Learning Rate": 2.4732574096724918e-05, "Pretrain/Loss": 2.038060188293457, "Pretrain/Loss (Raw)": 1.7542575597763062, "Pretrain/Step": 4943, "Pretrain/Step Time": 8.79098809324205} +{"Pretrain/Learning Rate": 2.4724084724924446e-05, "Pretrain/Loss": 2.03934383392334, "Pretrain/Loss (Raw)": 2.1078691482543945, "Pretrain/Step": 4944, "Pretrain/Step Time": 8.797607621178031} +{"Pretrain/Learning Rate": 2.471559538494383e-05, "Pretrain/Loss": 2.0399670600891113, "Pretrain/Loss (Raw)": 2.0343236923217773, "Pretrain/Step": 4945, "Pretrain/Step Time": 8.791931418702006} +{"Pretrain/Learning Rate": 2.470710607776209e-05, "Pretrain/Loss": 2.0409023761749268, "Pretrain/Loss (Raw)": 2.0834827423095703, "Pretrain/Step": 4946, "Pretrain/Step Time": 8.79272242449224} +{"Pretrain/Learning Rate": 2.4698616804358263e-05, "Pretrain/Loss": 2.040327787399292, "Pretrain/Loss (Raw)": 2.0002923011779785, "Pretrain/Step": 4947, "Pretrain/Step Time": 8.789804877713323} +{"Pretrain/Learning Rate": 2.469012756571136e-05, "Pretrain/Loss": 2.041806221008301, "Pretrain/Loss (Raw)": 2.1732869148254395, "Pretrain/Step": 4948, "Pretrain/Step Time": 8.79179305396974} +{"Pretrain/Learning Rate": 2.4681638362800415e-05, "Pretrain/Loss": 2.042572021484375, "Pretrain/Loss (Raw)": 2.0610084533691406, "Pretrain/Step": 4949, "Pretrain/Step Time": 8.791389157995582} +{"Pretrain/Learning Rate": 2.4673149196604424e-05, "Pretrain/Loss": 2.0406131744384766, "Pretrain/Loss (Raw)": 1.8687204122543335, "Pretrain/Step": 4950, "Pretrain/Step Time": 8.804210729897022} +{"Pretrain/Learning Rate": 2.4664660068102416e-05, "Pretrain/Loss": 2.040855884552002, "Pretrain/Loss (Raw)": 2.105889320373535, "Pretrain/Step": 4951, "Pretrain/Step Time": 8.788702046498656} +{"Pretrain/Learning Rate": 2.465617097827338e-05, "Pretrain/Loss": 2.0412020683288574, "Pretrain/Loss (Raw)": 1.8457227945327759, "Pretrain/Step": 4952, "Pretrain/Step Time": 8.79491196013987} +{"Pretrain/Learning Rate": 2.4647681928096337e-05, "Pretrain/Loss": 2.0438289642333984, "Pretrain/Loss (Raw)": 2.311457633972168, "Pretrain/Step": 4953, "Pretrain/Step Time": 8.798451516777277} +{"Pretrain/Learning Rate": 2.4639192918550268e-05, "Pretrain/Loss": 2.044184923171997, "Pretrain/Loss (Raw)": 2.086634874343872, "Pretrain/Step": 4954, "Pretrain/Step Time": 8.791928304359317} +{"Pretrain/Learning Rate": 2.4630703950614176e-05, "Pretrain/Loss": 2.0430245399475098, "Pretrain/Loss (Raw)": 2.0373730659484863, "Pretrain/Step": 4955, "Pretrain/Step Time": 8.793376194313169} +{"Pretrain/Learning Rate": 2.462221502526704e-05, "Pretrain/Loss": 2.0431857109069824, "Pretrain/Loss (Raw)": 2.1404640674591064, "Pretrain/Step": 4956, "Pretrain/Step Time": 8.794066555798054} +{"Pretrain/Learning Rate": 2.461372614348785e-05, "Pretrain/Loss": 2.0445303916931152, "Pretrain/Loss (Raw)": 2.1273937225341797, "Pretrain/Step": 4957, "Pretrain/Step Time": 8.785901935771108} +{"Pretrain/Learning Rate": 2.460523730625558e-05, "Pretrain/Loss": 2.04202938079834, "Pretrain/Loss (Raw)": 1.7810474634170532, "Pretrain/Step": 4958, "Pretrain/Step Time": 8.796753572300076} +{"Pretrain/Learning Rate": 2.4596748514549208e-05, "Pretrain/Loss": 2.0421195030212402, "Pretrain/Loss (Raw)": 2.061631202697754, "Pretrain/Step": 4959, "Pretrain/Step Time": 8.795530559495091} +{"Pretrain/Learning Rate": 2.458825976934769e-05, "Pretrain/Loss": 2.0410304069519043, "Pretrain/Loss (Raw)": 1.9736121892929077, "Pretrain/Step": 4960, "Pretrain/Step Time": 8.799303052946925} +{"Pretrain/Learning Rate": 2.4579771071630004e-05, "Pretrain/Loss": 2.0436549186706543, "Pretrain/Loss (Raw)": 2.158177614212036, "Pretrain/Step": 4961, "Pretrain/Step Time": 8.801068160682917} +{"Pretrain/Learning Rate": 2.457128242237509e-05, "Pretrain/Loss": 2.040306568145752, "Pretrain/Loss (Raw)": 1.6670031547546387, "Pretrain/Step": 4962, "Pretrain/Step Time": 8.801374811679125} +{"Pretrain/Learning Rate": 2.4562793822561914e-05, "Pretrain/Loss": 2.0392184257507324, "Pretrain/Loss (Raw)": 1.9510453939437866, "Pretrain/Step": 4963, "Pretrain/Step Time": 8.803588861599565} +{"Pretrain/Learning Rate": 2.455430527316941e-05, "Pretrain/Loss": 2.037445068359375, "Pretrain/Loss (Raw)": 1.8992886543273926, "Pretrain/Step": 4964, "Pretrain/Step Time": 8.809789102524519} +{"Pretrain/Learning Rate": 2.4545816775176532e-05, "Pretrain/Loss": 2.0355112552642822, "Pretrain/Loss (Raw)": 1.9735631942749023, "Pretrain/Step": 4965, "Pretrain/Step Time": 8.796611975878477} +{"Pretrain/Learning Rate": 2.4537328329562186e-05, "Pretrain/Loss": 2.0361006259918213, "Pretrain/Loss (Raw)": 2.124021291732788, "Pretrain/Step": 4966, "Pretrain/Step Time": 8.797966999933124} +{"Pretrain/Learning Rate": 2.4528839937305336e-05, "Pretrain/Loss": 2.03428316116333, "Pretrain/Loss (Raw)": 1.9294888973236084, "Pretrain/Step": 4967, "Pretrain/Step Time": 8.796081401407719} +{"Pretrain/Learning Rate": 2.452035159938487e-05, "Pretrain/Loss": 2.03475284576416, "Pretrain/Loss (Raw)": 2.0821869373321533, "Pretrain/Step": 4968, "Pretrain/Step Time": 8.801356228068471} +{"Pretrain/Learning Rate": 2.4511863316779728e-05, "Pretrain/Loss": 2.0368099212646484, "Pretrain/Loss (Raw)": 2.1018056869506836, "Pretrain/Step": 4969, "Pretrain/Step Time": 8.801155431196094} +{"Pretrain/Learning Rate": 2.4503375090468795e-05, "Pretrain/Loss": 2.0357723236083984, "Pretrain/Loss (Raw)": 1.8842955827713013, "Pretrain/Step": 4970, "Pretrain/Step Time": 8.800515273585916} +{"Pretrain/Learning Rate": 2.4494886921431005e-05, "Pretrain/Loss": 2.0358729362487793, "Pretrain/Loss (Raw)": 2.0079236030578613, "Pretrain/Step": 4971, "Pretrain/Step Time": 8.806080034002662} +{"Pretrain/Learning Rate": 2.448639881064522e-05, "Pretrain/Loss": 2.035041570663452, "Pretrain/Loss (Raw)": 2.0448338985443115, "Pretrain/Step": 4972, "Pretrain/Step Time": 8.799289541319013} +{"Pretrain/Learning Rate": 2.4477910759090357e-05, "Pretrain/Loss": 2.034119129180908, "Pretrain/Loss (Raw)": 1.912033200263977, "Pretrain/Step": 4973, "Pretrain/Step Time": 8.798866061493754} +{"Pretrain/Learning Rate": 2.446942276774527e-05, "Pretrain/Loss": 2.0351920127868652, "Pretrain/Loss (Raw)": 1.9870141744613647, "Pretrain/Step": 4974, "Pretrain/Step Time": 8.800669008865952} +{"Pretrain/Learning Rate": 2.4460934837588856e-05, "Pretrain/Loss": 2.0352821350097656, "Pretrain/Loss (Raw)": 2.132678747177124, "Pretrain/Step": 4975, "Pretrain/Step Time": 8.793740471825004} +{"Pretrain/Learning Rate": 2.4452446969599986e-05, "Pretrain/Loss": 2.0371737480163574, "Pretrain/Loss (Raw)": 2.2180068492889404, "Pretrain/Step": 4976, "Pretrain/Step Time": 8.79269179329276} +{"Pretrain/Learning Rate": 2.44439591647575e-05, "Pretrain/Loss": 2.038194179534912, "Pretrain/Loss (Raw)": 2.096384048461914, "Pretrain/Step": 4977, "Pretrain/Step Time": 8.796656431630254} +{"Pretrain/Learning Rate": 2.4435471424040273e-05, "Pretrain/Loss": 2.0394980907440186, "Pretrain/Loss (Raw)": 2.2083208560943604, "Pretrain/Step": 4978, "Pretrain/Step Time": 8.808223120868206} +{"Pretrain/Learning Rate": 2.442698374842713e-05, "Pretrain/Loss": 2.0382003784179688, "Pretrain/Loss (Raw)": 1.8343137502670288, "Pretrain/Step": 4979, "Pretrain/Step Time": 8.795644460245967} +{"Pretrain/Learning Rate": 2.4418496138896936e-05, "Pretrain/Loss": 2.0391845703125, "Pretrain/Loss (Raw)": 2.2785232067108154, "Pretrain/Step": 4980, "Pretrain/Step Time": 8.795141942799091} +{"Pretrain/Learning Rate": 2.4410008596428492e-05, "Pretrain/Loss": 2.038834810256958, "Pretrain/Loss (Raw)": 1.8973969221115112, "Pretrain/Step": 4981, "Pretrain/Step Time": 8.79928625933826} +{"Pretrain/Learning Rate": 2.440152112200065e-05, "Pretrain/Loss": 2.0392637252807617, "Pretrain/Loss (Raw)": 1.990286111831665, "Pretrain/Step": 4982, "Pretrain/Step Time": 8.794046791270375} +{"Pretrain/Learning Rate": 2.4393033716592196e-05, "Pretrain/Loss": 2.040996789932251, "Pretrain/Loss (Raw)": 2.2975428104400635, "Pretrain/Step": 4983, "Pretrain/Step Time": 8.797779779881239} +{"Pretrain/Learning Rate": 2.4384546381181976e-05, "Pretrain/Loss": 2.0397872924804688, "Pretrain/Loss (Raw)": 2.0560641288757324, "Pretrain/Step": 4984, "Pretrain/Step Time": 8.79939729347825} +{"Pretrain/Learning Rate": 2.437605911674875e-05, "Pretrain/Loss": 2.040921211242676, "Pretrain/Loss (Raw)": 2.090355157852173, "Pretrain/Step": 4985, "Pretrain/Step Time": 8.793613342568278} +{"Pretrain/Learning Rate": 2.4367571924271335e-05, "Pretrain/Loss": 2.0418992042541504, "Pretrain/Loss (Raw)": 2.352932929992676, "Pretrain/Step": 4986, "Pretrain/Step Time": 8.792969876900315} +{"Pretrain/Learning Rate": 2.43590848047285e-05, "Pretrain/Loss": 2.0421037673950195, "Pretrain/Loss (Raw)": 2.0074820518493652, "Pretrain/Step": 4987, "Pretrain/Step Time": 8.789844185113907} +{"Pretrain/Learning Rate": 2.4350597759099034e-05, "Pretrain/Loss": 2.0424180030822754, "Pretrain/Loss (Raw)": 2.1156070232391357, "Pretrain/Step": 4988, "Pretrain/Step Time": 8.785709857940674} +{"Pretrain/Learning Rate": 2.4342110788361685e-05, "Pretrain/Loss": 2.0418198108673096, "Pretrain/Loss (Raw)": 1.8097548484802246, "Pretrain/Step": 4989, "Pretrain/Step Time": 8.794080957770348} +{"Pretrain/Learning Rate": 2.433362389349523e-05, "Pretrain/Loss": 2.0416207313537598, "Pretrain/Loss (Raw)": 2.033742904663086, "Pretrain/Step": 4990, "Pretrain/Step Time": 8.796138709411025} +{"Pretrain/Learning Rate": 2.4325137075478398e-05, "Pretrain/Loss": 2.0412135124206543, "Pretrain/Loss (Raw)": 1.9991929531097412, "Pretrain/Step": 4991, "Pretrain/Step Time": 8.794466091319919} +{"Pretrain/Learning Rate": 2.4316650335289942e-05, "Pretrain/Loss": 2.043229579925537, "Pretrain/Loss (Raw)": 2.2094101905822754, "Pretrain/Step": 4992, "Pretrain/Step Time": 8.79842115752399} +{"Pretrain/Learning Rate": 2.430816367390859e-05, "Pretrain/Loss": 2.038116216659546, "Pretrain/Loss (Raw)": 1.6298590898513794, "Pretrain/Step": 4993, "Pretrain/Step Time": 8.802433991804719} +{"Pretrain/Learning Rate": 2.429967709231306e-05, "Pretrain/Loss": 2.0364933013916016, "Pretrain/Loss (Raw)": 1.9498045444488525, "Pretrain/Step": 4994, "Pretrain/Step Time": 8.797328025102615} +{"Pretrain/Learning Rate": 2.429119059148207e-05, "Pretrain/Loss": 2.0360465049743652, "Pretrain/Loss (Raw)": 1.9514764547348022, "Pretrain/Step": 4995, "Pretrain/Step Time": 8.796686559915543} +{"Pretrain/Learning Rate": 2.4282704172394323e-05, "Pretrain/Loss": 2.037080764770508, "Pretrain/Loss (Raw)": 2.137328863143921, "Pretrain/Step": 4996, "Pretrain/Step Time": 8.800102127715945} +{"Pretrain/Learning Rate": 2.4274217836028507e-05, "Pretrain/Loss": 2.039104461669922, "Pretrain/Loss (Raw)": 2.289738416671753, "Pretrain/Step": 4997, "Pretrain/Step Time": 8.79873431660235} +{"Pretrain/Learning Rate": 2.4265731583363316e-05, "Pretrain/Loss": 2.0385239124298096, "Pretrain/Loss (Raw)": 2.0323452949523926, "Pretrain/Step": 4998, "Pretrain/Step Time": 8.801120445132256} +{"Pretrain/Learning Rate": 2.425724541537741e-05, "Pretrain/Loss": 2.0382914543151855, "Pretrain/Loss (Raw)": 1.8987733125686646, "Pretrain/Step": 4999, "Pretrain/Step Time": 8.801308574154973} +{"Pretrain/Learning Rate": 2.4248759333049474e-05, "Pretrain/Loss": 2.0396411418914795, "Pretrain/Loss (Raw)": 2.040039300918579, "Pretrain/Step": 5000, "Pretrain/Step Time": 8.808312777429819} +{"Pretrain/Learning Rate": 2.424027333735814e-05, "Pretrain/Loss": 2.039170980453491, "Pretrain/Loss (Raw)": 1.956162452697754, "Pretrain/Step": 5001, "Pretrain/Step Time": 9.313375370576978} +{"Pretrain/Learning Rate": 2.4231787429282073e-05, "Pretrain/Loss": 2.039250612258911, "Pretrain/Loss (Raw)": 1.9528417587280273, "Pretrain/Step": 5002, "Pretrain/Step Time": 9.311072945594788} +{"Pretrain/Learning Rate": 2.4223301609799895e-05, "Pretrain/Loss": 2.039048433303833, "Pretrain/Loss (Raw)": 2.1485393047332764, "Pretrain/Step": 5003, "Pretrain/Step Time": 9.309053182601929} +{"Pretrain/Learning Rate": 2.421481587989024e-05, "Pretrain/Loss": 2.039785861968994, "Pretrain/Loss (Raw)": 2.1151340007781982, "Pretrain/Step": 5004, "Pretrain/Step Time": 9.305424256250262} +{"Pretrain/Learning Rate": 2.4206330240531713e-05, "Pretrain/Loss": 2.0406875610351562, "Pretrain/Loss (Raw)": 2.1026666164398193, "Pretrain/Step": 5005, "Pretrain/Step Time": 9.30637102201581} +{"Pretrain/Learning Rate": 2.4197844692702925e-05, "Pretrain/Loss": 2.039616107940674, "Pretrain/Loss (Raw)": 2.080443859100342, "Pretrain/Step": 5006, "Pretrain/Step Time": 9.307753628119826} +{"Pretrain/Learning Rate": 2.4189359237382464e-05, "Pretrain/Loss": 2.041283369064331, "Pretrain/Loss (Raw)": 2.0754425525665283, "Pretrain/Step": 5007, "Pretrain/Step Time": 9.309785779565573} +{"Pretrain/Learning Rate": 2.4180873875548925e-05, "Pretrain/Loss": 2.0413098335266113, "Pretrain/Loss (Raw)": 2.1442017555236816, "Pretrain/Step": 5008, "Pretrain/Step Time": 9.312078446149826} +{"Pretrain/Learning Rate": 2.4172388608180857e-05, "Pretrain/Loss": 2.041769504547119, "Pretrain/Loss (Raw)": 2.0347740650177, "Pretrain/Step": 5009, "Pretrain/Step Time": 9.309469496831298} +{"Pretrain/Learning Rate": 2.4163903436256848e-05, "Pretrain/Loss": 2.042997360229492, "Pretrain/Loss (Raw)": 2.1125688552856445, "Pretrain/Step": 5010, "Pretrain/Step Time": 9.309676123782992} +{"Pretrain/Learning Rate": 2.4155418360755423e-05, "Pretrain/Loss": 2.04295015335083, "Pretrain/Loss (Raw)": 2.023829460144043, "Pretrain/Step": 5011, "Pretrain/Step Time": 9.305357526987791} +{"Pretrain/Learning Rate": 2.4146933382655145e-05, "Pretrain/Loss": 2.042369842529297, "Pretrain/Loss (Raw)": 1.9981786012649536, "Pretrain/Step": 5012, "Pretrain/Step Time": 9.303584450855851} +{"Pretrain/Learning Rate": 2.413844850293451e-05, "Pretrain/Loss": 2.0437464714050293, "Pretrain/Loss (Raw)": 2.2104625701904297, "Pretrain/Step": 5013, "Pretrain/Step Time": 9.303450929000974} +{"Pretrain/Learning Rate": 2.4129963722572074e-05, "Pretrain/Loss": 2.0430235862731934, "Pretrain/Loss (Raw)": 1.9813534021377563, "Pretrain/Step": 5014, "Pretrain/Step Time": 9.305375199764967} +{"Pretrain/Learning Rate": 2.41214790425463e-05, "Pretrain/Loss": 2.043581008911133, "Pretrain/Loss (Raw)": 2.086902379989624, "Pretrain/Step": 5015, "Pretrain/Step Time": 9.31572170369327} +{"Pretrain/Learning Rate": 2.4112994463835714e-05, "Pretrain/Loss": 2.044914722442627, "Pretrain/Loss (Raw)": 2.242051124572754, "Pretrain/Step": 5016, "Pretrain/Step Time": 9.307658730074763} +{"Pretrain/Learning Rate": 2.4104509987418793e-05, "Pretrain/Loss": 2.0439865589141846, "Pretrain/Loss (Raw)": 2.000058174133301, "Pretrain/Step": 5017, "Pretrain/Step Time": 9.30852372571826} +{"Pretrain/Learning Rate": 2.4096025614273988e-05, "Pretrain/Loss": 2.0438265800476074, "Pretrain/Loss (Raw)": 2.146207094192505, "Pretrain/Step": 5018, "Pretrain/Step Time": 9.30499822087586} +{"Pretrain/Learning Rate": 2.408754134537978e-05, "Pretrain/Loss": 2.0435311794281006, "Pretrain/Loss (Raw)": 2.14190936088562, "Pretrain/Step": 5019, "Pretrain/Step Time": 9.302138540893793} +{"Pretrain/Learning Rate": 2.407905718171459e-05, "Pretrain/Loss": 2.043792247772217, "Pretrain/Loss (Raw)": 2.0743446350097656, "Pretrain/Step": 5020, "Pretrain/Step Time": 9.316095737740397} +{"Pretrain/Learning Rate": 2.4070573124256883e-05, "Pretrain/Loss": 2.044193744659424, "Pretrain/Loss (Raw)": 2.053466558456421, "Pretrain/Step": 5021, "Pretrain/Step Time": 9.316989872604609} +{"Pretrain/Learning Rate": 2.4062089173985044e-05, "Pretrain/Loss": 2.0451512336730957, "Pretrain/Loss (Raw)": 2.1333532333374023, "Pretrain/Step": 5022, "Pretrain/Step Time": 9.316599430516362} +{"Pretrain/Learning Rate": 2.4053605331877517e-05, "Pretrain/Loss": 2.044839382171631, "Pretrain/Loss (Raw)": 2.076864004135132, "Pretrain/Step": 5023, "Pretrain/Step Time": 9.320765439420938} +{"Pretrain/Learning Rate": 2.404512159891267e-05, "Pretrain/Loss": 2.0433192253112793, "Pretrain/Loss (Raw)": 1.8225058317184448, "Pretrain/Step": 5024, "Pretrain/Step Time": 9.321701917797327} +{"Pretrain/Learning Rate": 2.4036637976068914e-05, "Pretrain/Loss": 2.0425429344177246, "Pretrain/Loss (Raw)": 2.105764150619507, "Pretrain/Step": 5025, "Pretrain/Step Time": 9.315538506954908} +{"Pretrain/Learning Rate": 2.4028154464324592e-05, "Pretrain/Loss": 2.039155960083008, "Pretrain/Loss (Raw)": 1.7685834169387817, "Pretrain/Step": 5026, "Pretrain/Step Time": 9.313524117693305} +{"Pretrain/Learning Rate": 2.4019671064658088e-05, "Pretrain/Loss": 2.0394363403320312, "Pretrain/Loss (Raw)": 2.1257877349853516, "Pretrain/Step": 5027, "Pretrain/Step Time": 9.31974183395505} +{"Pretrain/Learning Rate": 2.4011187778047727e-05, "Pretrain/Loss": 2.038607120513916, "Pretrain/Loss (Raw)": 1.8822001218795776, "Pretrain/Step": 5028, "Pretrain/Step Time": 9.318772472441196} +{"Pretrain/Learning Rate": 2.4002704605471857e-05, "Pretrain/Loss": 2.0412518978118896, "Pretrain/Loss (Raw)": 2.1994946002960205, "Pretrain/Step": 5029, "Pretrain/Step Time": 9.3229715321213} +{"Pretrain/Learning Rate": 2.3994221547908783e-05, "Pretrain/Loss": 2.0395283699035645, "Pretrain/Loss (Raw)": 1.8998758792877197, "Pretrain/Step": 5030, "Pretrain/Step Time": 9.323040483519435} +{"Pretrain/Learning Rate": 2.398573860633683e-05, "Pretrain/Loss": 2.039011001586914, "Pretrain/Loss (Raw)": 2.0652191638946533, "Pretrain/Step": 5031, "Pretrain/Step Time": 9.333614340052009} +{"Pretrain/Learning Rate": 2.3977255781734275e-05, "Pretrain/Loss": 2.0405774116516113, "Pretrain/Loss (Raw)": 2.2641873359680176, "Pretrain/Step": 5032, "Pretrain/Step Time": 9.329633561894298} +{"Pretrain/Learning Rate": 2.3968773075079404e-05, "Pretrain/Loss": 2.0434088706970215, "Pretrain/Loss (Raw)": 2.023132801055908, "Pretrain/Step": 5033, "Pretrain/Step Time": 9.325659925118089} +{"Pretrain/Learning Rate": 2.396029048735048e-05, "Pretrain/Loss": 2.044760227203369, "Pretrain/Loss (Raw)": 2.044151544570923, "Pretrain/Step": 5034, "Pretrain/Step Time": 9.334053035825491} +{"Pretrain/Learning Rate": 2.3951808019525758e-05, "Pretrain/Loss": 2.0453848838806152, "Pretrain/Loss (Raw)": 2.029179573059082, "Pretrain/Step": 5035, "Pretrain/Step Time": 9.328562159091234} +{"Pretrain/Learning Rate": 2.394332567258347e-05, "Pretrain/Loss": 2.0458884239196777, "Pretrain/Loss (Raw)": 2.0235631465911865, "Pretrain/Step": 5036, "Pretrain/Step Time": 9.330639224499464} +{"Pretrain/Learning Rate": 2.3934843447501852e-05, "Pretrain/Loss": 2.045623779296875, "Pretrain/Loss (Raw)": 2.022686243057251, "Pretrain/Step": 5037, "Pretrain/Step Time": 9.335865210741758} +{"Pretrain/Learning Rate": 2.3926361345259098e-05, "Pretrain/Loss": 2.0453920364379883, "Pretrain/Loss (Raw)": 2.071341037750244, "Pretrain/Step": 5038, "Pretrain/Step Time": 9.33687437698245} +{"Pretrain/Learning Rate": 2.391787936683342e-05, "Pretrain/Loss": 2.0454726219177246, "Pretrain/Loss (Raw)": 2.0746772289276123, "Pretrain/Step": 5039, "Pretrain/Step Time": 9.32872050628066} +{"Pretrain/Learning Rate": 2.390939751320299e-05, "Pretrain/Loss": 2.044499635696411, "Pretrain/Loss (Raw)": 1.9512948989868164, "Pretrain/Step": 5040, "Pretrain/Step Time": 9.326356656849384} +{"Pretrain/Learning Rate": 2.390091578534598e-05, "Pretrain/Loss": 2.0448923110961914, "Pretrain/Loss (Raw)": 2.253222703933716, "Pretrain/Step": 5041, "Pretrain/Step Time": 9.325944589450955} +{"Pretrain/Learning Rate": 2.3892434184240533e-05, "Pretrain/Loss": 2.0461387634277344, "Pretrain/Loss (Raw)": 2.0528388023376465, "Pretrain/Step": 5042, "Pretrain/Step Time": 9.325056035071611} +{"Pretrain/Learning Rate": 2.3883952710864804e-05, "Pretrain/Loss": 2.047720432281494, "Pretrain/Loss (Raw)": 2.1862375736236572, "Pretrain/Step": 5043, "Pretrain/Step Time": 9.331243075430393} +{"Pretrain/Learning Rate": 2.3875471366196903e-05, "Pretrain/Loss": 2.0471014976501465, "Pretrain/Loss (Raw)": 1.9707444906234741, "Pretrain/Step": 5044, "Pretrain/Step Time": 9.333243694156408} +{"Pretrain/Learning Rate": 2.3866990151214947e-05, "Pretrain/Loss": 2.047825336456299, "Pretrain/Loss (Raw)": 2.0783283710479736, "Pretrain/Step": 5045, "Pretrain/Step Time": 9.336745174601674} +{"Pretrain/Learning Rate": 2.3858509066897016e-05, "Pretrain/Loss": 2.051478862762451, "Pretrain/Loss (Raw)": 2.1388912200927734, "Pretrain/Step": 5046, "Pretrain/Step Time": 9.331315638497472} +{"Pretrain/Learning Rate": 2.385002811422121e-05, "Pretrain/Loss": 2.0495402812957764, "Pretrain/Loss (Raw)": 1.765536904335022, "Pretrain/Step": 5047, "Pretrain/Step Time": 9.331414559856057} +{"Pretrain/Learning Rate": 2.384154729416557e-05, "Pretrain/Loss": 2.046496629714966, "Pretrain/Loss (Raw)": 1.870048999786377, "Pretrain/Step": 5048, "Pretrain/Step Time": 9.34486024826765} +{"Pretrain/Learning Rate": 2.383306660770817e-05, "Pretrain/Loss": 2.0448639392852783, "Pretrain/Loss (Raw)": 1.916329026222229, "Pretrain/Step": 5049, "Pretrain/Step Time": 9.347500329837203} +{"Pretrain/Learning Rate": 2.382458605582701e-05, "Pretrain/Loss": 2.0454087257385254, "Pretrain/Loss (Raw)": 2.0576465129852295, "Pretrain/Step": 5050, "Pretrain/Step Time": 9.34233539365232} +{"Pretrain/Learning Rate": 2.3816105639500142e-05, "Pretrain/Loss": 2.044107437133789, "Pretrain/Loss (Raw)": 1.9487007856369019, "Pretrain/Step": 5051, "Pretrain/Step Time": 9.341859417036176} +{"Pretrain/Learning Rate": 2.3807625359705532e-05, "Pretrain/Loss": 2.04372501373291, "Pretrain/Loss (Raw)": 2.0970730781555176, "Pretrain/Step": 5052, "Pretrain/Step Time": 9.343757946044207} +{"Pretrain/Learning Rate": 2.37991452174212e-05, "Pretrain/Loss": 2.040444850921631, "Pretrain/Loss (Raw)": 1.7889149188995361, "Pretrain/Step": 5053, "Pretrain/Step Time": 9.344617258757353} +{"Pretrain/Learning Rate": 2.3790665213625087e-05, "Pretrain/Loss": 2.0382018089294434, "Pretrain/Loss (Raw)": 1.6963272094726562, "Pretrain/Step": 5054, "Pretrain/Step Time": 9.345103479921818} +{"Pretrain/Learning Rate": 2.3782185349295174e-05, "Pretrain/Loss": 2.0363636016845703, "Pretrain/Loss (Raw)": 1.9511460065841675, "Pretrain/Step": 5055, "Pretrain/Step Time": 9.34919967316091} +{"Pretrain/Learning Rate": 2.377370562540937e-05, "Pretrain/Loss": 2.034902572631836, "Pretrain/Loss (Raw)": 2.0702669620513916, "Pretrain/Step": 5056, "Pretrain/Step Time": 9.347110459581017} +{"Pretrain/Learning Rate": 2.3765226042945616e-05, "Pretrain/Loss": 2.0370492935180664, "Pretrain/Loss (Raw)": 2.1383330821990967, "Pretrain/Step": 5057, "Pretrain/Step Time": 9.334155125543475} +{"Pretrain/Learning Rate": 2.3756746602881824e-05, "Pretrain/Loss": 2.036992073059082, "Pretrain/Loss (Raw)": 1.983678936958313, "Pretrain/Step": 5058, "Pretrain/Step Time": 9.334061181172729} +{"Pretrain/Learning Rate": 2.3748267306195855e-05, "Pretrain/Loss": 2.0379631519317627, "Pretrain/Loss (Raw)": 2.199570417404175, "Pretrain/Step": 5059, "Pretrain/Step Time": 9.345167273655534} +{"Pretrain/Learning Rate": 2.373978815386562e-05, "Pretrain/Loss": 2.038360357284546, "Pretrain/Loss (Raw)": 2.1468732357025146, "Pretrain/Step": 5060, "Pretrain/Step Time": 9.346807008609176} +{"Pretrain/Learning Rate": 2.3731309146868932e-05, "Pretrain/Loss": 2.037733793258667, "Pretrain/Loss (Raw)": 2.0203211307525635, "Pretrain/Step": 5061, "Pretrain/Step Time": 9.34631073474884} +{"Pretrain/Learning Rate": 2.372283028618367e-05, "Pretrain/Loss": 2.0389461517333984, "Pretrain/Loss (Raw)": 2.0668997764587402, "Pretrain/Step": 5062, "Pretrain/Step Time": 9.345229130238295} +{"Pretrain/Learning Rate": 2.371435157278762e-05, "Pretrain/Loss": 2.039400100708008, "Pretrain/Loss (Raw)": 2.0319976806640625, "Pretrain/Step": 5063, "Pretrain/Step Time": 9.345449259504676} +{"Pretrain/Learning Rate": 2.370587300765862e-05, "Pretrain/Loss": 2.037562847137451, "Pretrain/Loss (Raw)": 2.0558717250823975, "Pretrain/Step": 5064, "Pretrain/Step Time": 9.33581224270165} +{"Pretrain/Learning Rate": 2.369739459177443e-05, "Pretrain/Loss": 2.036942958831787, "Pretrain/Loss (Raw)": 2.049607753753662, "Pretrain/Step": 5065, "Pretrain/Step Time": 9.336458867415786} +{"Pretrain/Learning Rate": 2.3688916326112848e-05, "Pretrain/Loss": 2.035202980041504, "Pretrain/Loss (Raw)": 1.9137239456176758, "Pretrain/Step": 5066, "Pretrain/Step Time": 9.330947594717145} +{"Pretrain/Learning Rate": 2.3680438211651597e-05, "Pretrain/Loss": 2.0347540378570557, "Pretrain/Loss (Raw)": 2.029249906539917, "Pretrain/Step": 5067, "Pretrain/Step Time": 9.334584636613727} +{"Pretrain/Learning Rate": 2.3671960249368448e-05, "Pretrain/Loss": 2.0360867977142334, "Pretrain/Loss (Raw)": 2.0200998783111572, "Pretrain/Step": 5068, "Pretrain/Step Time": 9.333249488845468} +{"Pretrain/Learning Rate": 2.3663482440241087e-05, "Pretrain/Loss": 2.035691261291504, "Pretrain/Loss (Raw)": 1.9501689672470093, "Pretrain/Step": 5069, "Pretrain/Step Time": 9.335241923108697} +{"Pretrain/Learning Rate": 2.3655004785247234e-05, "Pretrain/Loss": 2.036581516265869, "Pretrain/Loss (Raw)": 2.1338489055633545, "Pretrain/Step": 5070, "Pretrain/Step Time": 9.33707731962204} +{"Pretrain/Learning Rate": 2.3646527285364565e-05, "Pretrain/Loss": 2.037957191467285, "Pretrain/Loss (Raw)": 1.930393934249878, "Pretrain/Step": 5071, "Pretrain/Step Time": 9.333521077409387} +{"Pretrain/Learning Rate": 2.363804994157075e-05, "Pretrain/Loss": 2.0376710891723633, "Pretrain/Loss (Raw)": 2.0712108612060547, "Pretrain/Step": 5072, "Pretrain/Step Time": 9.33431643806398} +{"Pretrain/Learning Rate": 2.3629572754843428e-05, "Pretrain/Loss": 2.0386900901794434, "Pretrain/Loss (Raw)": 2.1647515296936035, "Pretrain/Step": 5073, "Pretrain/Step Time": 9.348831340670586} +{"Pretrain/Learning Rate": 2.3621095726160237e-05, "Pretrain/Loss": 2.0376429557800293, "Pretrain/Loss (Raw)": 1.949463129043579, "Pretrain/Step": 5074, "Pretrain/Step Time": 9.350140238180757} +{"Pretrain/Learning Rate": 2.3612618856498785e-05, "Pretrain/Loss": 2.0376243591308594, "Pretrain/Loss (Raw)": 1.997924566268921, "Pretrain/Step": 5075, "Pretrain/Step Time": 9.349633976817131} +{"Pretrain/Learning Rate": 2.3604142146836666e-05, "Pretrain/Loss": 2.0382988452911377, "Pretrain/Loss (Raw)": 2.2596118450164795, "Pretrain/Step": 5076, "Pretrain/Step Time": 9.351827085018158} +{"Pretrain/Learning Rate": 2.3595665598151444e-05, "Pretrain/Loss": 2.0379624366760254, "Pretrain/Loss (Raw)": 2.0179598331451416, "Pretrain/Step": 5077, "Pretrain/Step Time": 9.356240529567003} +{"Pretrain/Learning Rate": 2.3587189211420694e-05, "Pretrain/Loss": 2.039515972137451, "Pretrain/Loss (Raw)": 2.0675668716430664, "Pretrain/Step": 5078, "Pretrain/Step Time": 9.341319201514125} +{"Pretrain/Learning Rate": 2.3578712987621932e-05, "Pretrain/Loss": 2.0403900146484375, "Pretrain/Loss (Raw)": 2.2177698612213135, "Pretrain/Step": 5079, "Pretrain/Step Time": 9.350928710773587} +{"Pretrain/Learning Rate": 2.3570236927732692e-05, "Pretrain/Loss": 2.0411629676818848, "Pretrain/Loss (Raw)": 1.9446735382080078, "Pretrain/Step": 5080, "Pretrain/Step Time": 9.347656840458512} +{"Pretrain/Learning Rate": 2.3561761032730463e-05, "Pretrain/Loss": 2.0391483306884766, "Pretrain/Loss (Raw)": 2.0535829067230225, "Pretrain/Step": 5081, "Pretrain/Step Time": 9.346981722861528} +{"Pretrain/Learning Rate": 2.355328530359273e-05, "Pretrain/Loss": 2.0392515659332275, "Pretrain/Loss (Raw)": 2.099842071533203, "Pretrain/Step": 5082, "Pretrain/Step Time": 9.34968039020896} +{"Pretrain/Learning Rate": 2.3544809741296954e-05, "Pretrain/Loss": 2.0391461849212646, "Pretrain/Loss (Raw)": 2.023872137069702, "Pretrain/Step": 5083, "Pretrain/Step Time": 9.353368762880564} +{"Pretrain/Learning Rate": 2.3536334346820578e-05, "Pretrain/Loss": 2.038694143295288, "Pretrain/Loss (Raw)": 2.082585573196411, "Pretrain/Step": 5084, "Pretrain/Step Time": 9.35039946436882} +{"Pretrain/Learning Rate": 2.3527859121141012e-05, "Pretrain/Loss": 2.0367040634155273, "Pretrain/Loss (Raw)": 1.8727037906646729, "Pretrain/Step": 5085, "Pretrain/Step Time": 9.35255166888237} +{"Pretrain/Learning Rate": 2.351938406523568e-05, "Pretrain/Loss": 2.0386433601379395, "Pretrain/Loss (Raw)": 2.029249906539917, "Pretrain/Step": 5086, "Pretrain/Step Time": 9.340911328792572} +{"Pretrain/Learning Rate": 2.3510909180081946e-05, "Pretrain/Loss": 2.0383810997009277, "Pretrain/Loss (Raw)": 2.0280797481536865, "Pretrain/Step": 5087, "Pretrain/Step Time": 9.353394055739045} +{"Pretrain/Learning Rate": 2.350243446665719e-05, "Pretrain/Loss": 2.040174961090088, "Pretrain/Loss (Raw)": 2.2032363414764404, "Pretrain/Step": 5088, "Pretrain/Step Time": 9.352093879133463} +{"Pretrain/Learning Rate": 2.3493959925938746e-05, "Pretrain/Loss": 2.038745403289795, "Pretrain/Loss (Raw)": 1.975172519683838, "Pretrain/Step": 5089, "Pretrain/Step Time": 9.348852867260575} +{"Pretrain/Learning Rate": 2.348548555890394e-05, "Pretrain/Loss": 2.04325008392334, "Pretrain/Loss (Raw)": 2.2436089515686035, "Pretrain/Step": 5090, "Pretrain/Step Time": 9.345769053325057} +{"Pretrain/Learning Rate": 2.3477011366530068e-05, "Pretrain/Loss": 2.044417381286621, "Pretrain/Loss (Raw)": 2.100473642349243, "Pretrain/Step": 5091, "Pretrain/Step Time": 9.345757778733969} +{"Pretrain/Learning Rate": 2.3468537349794438e-05, "Pretrain/Loss": 2.0443997383117676, "Pretrain/Loss (Raw)": 1.8970364332199097, "Pretrain/Step": 5092, "Pretrain/Step Time": 9.342298021540046} +{"Pretrain/Learning Rate": 2.3460063509674278e-05, "Pretrain/Loss": 2.0456736087799072, "Pretrain/Loss (Raw)": 2.136586904525757, "Pretrain/Step": 5093, "Pretrain/Step Time": 9.345010947436094} +{"Pretrain/Learning Rate": 2.345158984714687e-05, "Pretrain/Loss": 2.045410633087158, "Pretrain/Loss (Raw)": 2.090358018875122, "Pretrain/Step": 5094, "Pretrain/Step Time": 9.345982981845737} +{"Pretrain/Learning Rate": 2.3443116363189398e-05, "Pretrain/Loss": 2.045747756958008, "Pretrain/Loss (Raw)": 1.972635269165039, "Pretrain/Step": 5095, "Pretrain/Step Time": 9.35344479419291} +{"Pretrain/Learning Rate": 2.3434643058779104e-05, "Pretrain/Loss": 2.0453734397888184, "Pretrain/Loss (Raw)": 2.0342817306518555, "Pretrain/Step": 5096, "Pretrain/Step Time": 9.34955919161439} +{"Pretrain/Learning Rate": 2.342616993489313e-05, "Pretrain/Loss": 2.0456976890563965, "Pretrain/Loss (Raw)": 2.143345832824707, "Pretrain/Step": 5097, "Pretrain/Step Time": 9.355687193572521} +{"Pretrain/Learning Rate": 2.3417696992508657e-05, "Pretrain/Loss": 2.047731399536133, "Pretrain/Loss (Raw)": 2.1445693969726562, "Pretrain/Step": 5098, "Pretrain/Step Time": 9.357002718374133} +{"Pretrain/Learning Rate": 2.3409224232602832e-05, "Pretrain/Loss": 2.0474140644073486, "Pretrain/Loss (Raw)": 1.967319369316101, "Pretrain/Step": 5099, "Pretrain/Step Time": 9.355139460414648} +{"Pretrain/Learning Rate": 2.340075165615276e-05, "Pretrain/Loss": 2.0475499629974365, "Pretrain/Loss (Raw)": 2.062220811843872, "Pretrain/Step": 5100, "Pretrain/Step Time": 9.35899979993701} +{"Pretrain/Learning Rate": 2.339227926413555e-05, "Pretrain/Loss": 2.049558162689209, "Pretrain/Loss (Raw)": 2.1690802574157715, "Pretrain/Step": 5101, "Pretrain/Step Time": 9.358888823539019} +{"Pretrain/Learning Rate": 2.3383807057528256e-05, "Pretrain/Loss": 2.0490262508392334, "Pretrain/Loss (Raw)": 1.9189242124557495, "Pretrain/Step": 5102, "Pretrain/Step Time": 9.358931053429842} +{"Pretrain/Learning Rate": 2.3375335037307965e-05, "Pretrain/Loss": 2.047886371612549, "Pretrain/Loss (Raw)": 1.9867709875106812, "Pretrain/Step": 5103, "Pretrain/Step Time": 9.361234275624156} +{"Pretrain/Learning Rate": 2.3366863204451677e-05, "Pretrain/Loss": 2.0458121299743652, "Pretrain/Loss (Raw)": 1.9525542259216309, "Pretrain/Step": 5104, "Pretrain/Step Time": 9.368700843304396} +{"Pretrain/Learning Rate": 2.3358391559936438e-05, "Pretrain/Loss": 2.045440673828125, "Pretrain/Loss (Raw)": 2.0488204956054688, "Pretrain/Step": 5105, "Pretrain/Step Time": 9.365140425041318} +{"Pretrain/Learning Rate": 2.33499201047392e-05, "Pretrain/Loss": 2.040994167327881, "Pretrain/Loss (Raw)": 1.6391701698303223, "Pretrain/Step": 5106, "Pretrain/Step Time": 9.358694968745112} +{"Pretrain/Learning Rate": 2.334144883983697e-05, "Pretrain/Loss": 2.0440711975097656, "Pretrain/Loss (Raw)": 2.2281596660614014, "Pretrain/Step": 5107, "Pretrain/Step Time": 9.35799934528768} +{"Pretrain/Learning Rate": 2.3332977766206657e-05, "Pretrain/Loss": 2.0423665046691895, "Pretrain/Loss (Raw)": 2.060303211212158, "Pretrain/Step": 5108, "Pretrain/Step Time": 9.361400913447142} +{"Pretrain/Learning Rate": 2.332450688482522e-05, "Pretrain/Loss": 2.044555187225342, "Pretrain/Loss (Raw)": 2.1775596141815186, "Pretrain/Step": 5109, "Pretrain/Step Time": 9.36493849568069} +{"Pretrain/Learning Rate": 2.3316036196669534e-05, "Pretrain/Loss": 2.0449769496917725, "Pretrain/Loss (Raw)": 2.044259786605835, "Pretrain/Step": 5110, "Pretrain/Step Time": 9.36268357373774} +{"Pretrain/Learning Rate": 2.3307565702716495e-05, "Pretrain/Loss": 2.0422143936157227, "Pretrain/Loss (Raw)": 1.943915843963623, "Pretrain/Step": 5111, "Pretrain/Step Time": 9.36682715266943} +{"Pretrain/Learning Rate": 2.3299095403942943e-05, "Pretrain/Loss": 2.042463779449463, "Pretrain/Loss (Raw)": 2.0880091190338135, "Pretrain/Step": 5112, "Pretrain/Step Time": 9.369716174900532} +{"Pretrain/Learning Rate": 2.3290625301325735e-05, "Pretrain/Loss": 2.041654586791992, "Pretrain/Loss (Raw)": 1.9867844581604004, "Pretrain/Step": 5113, "Pretrain/Step Time": 9.367992324754596} +{"Pretrain/Learning Rate": 2.3282155395841667e-05, "Pretrain/Loss": 2.0401718616485596, "Pretrain/Loss (Raw)": 2.163154125213623, "Pretrain/Step": 5114, "Pretrain/Step Time": 9.374766854569316} +{"Pretrain/Learning Rate": 2.327368568846754e-05, "Pretrain/Loss": 2.0383338928222656, "Pretrain/Loss (Raw)": 1.772208333015442, "Pretrain/Step": 5115, "Pretrain/Step Time": 9.373827040195465} +{"Pretrain/Learning Rate": 2.3265216180180106e-05, "Pretrain/Loss": 2.038039445877075, "Pretrain/Loss (Raw)": 2.077937602996826, "Pretrain/Step": 5116, "Pretrain/Step Time": 9.3740718588233} +{"Pretrain/Learning Rate": 2.325674687195612e-05, "Pretrain/Loss": 2.0403246879577637, "Pretrain/Loss (Raw)": 2.1022560596466064, "Pretrain/Step": 5117, "Pretrain/Step Time": 9.36637737043202} +{"Pretrain/Learning Rate": 2.32482777647723e-05, "Pretrain/Loss": 2.039891242980957, "Pretrain/Loss (Raw)": 1.9782352447509766, "Pretrain/Step": 5118, "Pretrain/Step Time": 9.36551302485168} +{"Pretrain/Learning Rate": 2.323980885960534e-05, "Pretrain/Loss": 2.039983034133911, "Pretrain/Loss (Raw)": 2.0109639167785645, "Pretrain/Step": 5119, "Pretrain/Step Time": 9.368776904419065} +{"Pretrain/Learning Rate": 2.3231340157431917e-05, "Pretrain/Loss": 2.039531707763672, "Pretrain/Loss (Raw)": 2.151660442352295, "Pretrain/Step": 5120, "Pretrain/Step Time": 9.358305798843503} +{"Pretrain/Learning Rate": 2.3222871659228685e-05, "Pretrain/Loss": 2.0413918495178223, "Pretrain/Loss (Raw)": 1.8679230213165283, "Pretrain/Step": 5121, "Pretrain/Step Time": 9.360850743949413} +{"Pretrain/Learning Rate": 2.3214403365972258e-05, "Pretrain/Loss": 2.0413434505462646, "Pretrain/Loss (Raw)": 1.9436297416687012, "Pretrain/Step": 5122, "Pretrain/Step Time": 9.3622741792351} +{"Pretrain/Learning Rate": 2.320593527863926e-05, "Pretrain/Loss": 2.0429067611694336, "Pretrain/Loss (Raw)": 2.151578903198242, "Pretrain/Step": 5123, "Pretrain/Step Time": 9.358357520774007} +{"Pretrain/Learning Rate": 2.319746739820625e-05, "Pretrain/Loss": 2.041072368621826, "Pretrain/Loss (Raw)": 1.902523398399353, "Pretrain/Step": 5124, "Pretrain/Step Time": 9.35452151298523} +{"Pretrain/Learning Rate": 2.3188999725649804e-05, "Pretrain/Loss": 2.039483070373535, "Pretrain/Loss (Raw)": 2.0863137245178223, "Pretrain/Step": 5125, "Pretrain/Step Time": 9.357672043144703} +{"Pretrain/Learning Rate": 2.3180532261946437e-05, "Pretrain/Loss": 2.039666175842285, "Pretrain/Loss (Raw)": 2.0557568073272705, "Pretrain/Step": 5126, "Pretrain/Step Time": 9.362857611849904} +{"Pretrain/Learning Rate": 2.3172065008072663e-05, "Pretrain/Loss": 2.041239023208618, "Pretrain/Loss (Raw)": 2.1001129150390625, "Pretrain/Step": 5127, "Pretrain/Step Time": 9.3635707013309} +{"Pretrain/Learning Rate": 2.3163597965004967e-05, "Pretrain/Loss": 2.042419910430908, "Pretrain/Loss (Raw)": 2.1911838054656982, "Pretrain/Step": 5128, "Pretrain/Step Time": 9.350785754621029} +{"Pretrain/Learning Rate": 2.315513113371981e-05, "Pretrain/Loss": 2.041407585144043, "Pretrain/Loss (Raw)": 1.8265831470489502, "Pretrain/Step": 5129, "Pretrain/Step Time": 8.842268673703074} +{"Pretrain/Learning Rate": 2.3146664515193616e-05, "Pretrain/Loss": 2.0423991680145264, "Pretrain/Loss (Raw)": 2.0797839164733887, "Pretrain/Step": 5130, "Pretrain/Step Time": 8.84133492037654} +{"Pretrain/Learning Rate": 2.3138198110402812e-05, "Pretrain/Loss": 2.040675401687622, "Pretrain/Loss (Raw)": 1.927886724472046, "Pretrain/Step": 5131, "Pretrain/Step Time": 8.841829730197787} +{"Pretrain/Learning Rate": 2.3129731920323765e-05, "Pretrain/Loss": 2.040747880935669, "Pretrain/Loss (Raw)": 2.1244289875030518, "Pretrain/Step": 5132, "Pretrain/Step Time": 8.842427978292108} +{"Pretrain/Learning Rate": 2.3121265945932862e-05, "Pretrain/Loss": 2.040708065032959, "Pretrain/Loss (Raw)": 2.097552537918091, "Pretrain/Step": 5133, "Pretrain/Step Time": 8.852348692715168} +{"Pretrain/Learning Rate": 2.3112800188206404e-05, "Pretrain/Loss": 2.041133403778076, "Pretrain/Loss (Raw)": 2.1348912715911865, "Pretrain/Step": 5134, "Pretrain/Step Time": 8.850786523893476} +{"Pretrain/Learning Rate": 2.310433464812074e-05, "Pretrain/Loss": 2.0421762466430664, "Pretrain/Loss (Raw)": 2.208949565887451, "Pretrain/Step": 5135, "Pretrain/Step Time": 8.837290359660983} +{"Pretrain/Learning Rate": 2.309586932665212e-05, "Pretrain/Loss": 2.0419423580169678, "Pretrain/Loss (Raw)": 2.114245653152466, "Pretrain/Step": 5136, "Pretrain/Step Time": 8.839885892346501} +{"Pretrain/Learning Rate": 2.3087404224776835e-05, "Pretrain/Loss": 2.0413501262664795, "Pretrain/Loss (Raw)": 1.9589663743972778, "Pretrain/Step": 5137, "Pretrain/Step Time": 8.837233545258641} +{"Pretrain/Learning Rate": 2.307893934347109e-05, "Pretrain/Loss": 2.0410919189453125, "Pretrain/Loss (Raw)": 2.079514741897583, "Pretrain/Step": 5138, "Pretrain/Step Time": 8.835003573447466} +{"Pretrain/Learning Rate": 2.3070474683711125e-05, "Pretrain/Loss": 2.0416252613067627, "Pretrain/Loss (Raw)": 2.0920889377593994, "Pretrain/Step": 5139, "Pretrain/Step Time": 8.840773390606046} +{"Pretrain/Learning Rate": 2.306201024647311e-05, "Pretrain/Loss": 2.040860652923584, "Pretrain/Loss (Raw)": 1.9003058671951294, "Pretrain/Step": 5140, "Pretrain/Step Time": 8.840821800753474} +{"Pretrain/Learning Rate": 2.3053546032733207e-05, "Pretrain/Loss": 2.03877329826355, "Pretrain/Loss (Raw)": 1.9433034658432007, "Pretrain/Step": 5141, "Pretrain/Step Time": 8.84247338399291} +{"Pretrain/Learning Rate": 2.3045082043467554e-05, "Pretrain/Loss": 2.039315700531006, "Pretrain/Loss (Raw)": 2.050757646560669, "Pretrain/Step": 5142, "Pretrain/Step Time": 8.82842111773789} +{"Pretrain/Learning Rate": 2.3036618279652232e-05, "Pretrain/Loss": 2.0403218269348145, "Pretrain/Loss (Raw)": 2.215726852416992, "Pretrain/Step": 5143, "Pretrain/Step Time": 8.821403594687581} +{"Pretrain/Learning Rate": 2.3028154742263362e-05, "Pretrain/Loss": 2.0372159481048584, "Pretrain/Loss (Raw)": 1.844457745552063, "Pretrain/Step": 5144, "Pretrain/Step Time": 8.826995005831122} +{"Pretrain/Learning Rate": 2.3019691432276964e-05, "Pretrain/Loss": 2.037437915802002, "Pretrain/Loss (Raw)": 2.028489828109741, "Pretrain/Step": 5145, "Pretrain/Step Time": 8.82726032473147} +{"Pretrain/Learning Rate": 2.3011228350669096e-05, "Pretrain/Loss": 2.036351203918457, "Pretrain/Loss (Raw)": 2.007098913192749, "Pretrain/Step": 5146, "Pretrain/Step Time": 8.827132740989327} +{"Pretrain/Learning Rate": 2.3002765498415728e-05, "Pretrain/Loss": 2.0357651710510254, "Pretrain/Loss (Raw)": 2.066892623901367, "Pretrain/Step": 5147, "Pretrain/Step Time": 8.827960593625903} +{"Pretrain/Learning Rate": 2.2994302876492875e-05, "Pretrain/Loss": 2.0325472354888916, "Pretrain/Loss (Raw)": 1.6624560356140137, "Pretrain/Step": 5148, "Pretrain/Step Time": 8.816737208515406} +{"Pretrain/Learning Rate": 2.2985840485876444e-05, "Pretrain/Loss": 2.030296802520752, "Pretrain/Loss (Raw)": 1.7654104232788086, "Pretrain/Step": 5149, "Pretrain/Step Time": 8.814429802820086} +{"Pretrain/Learning Rate": 2.2977378327542397e-05, "Pretrain/Loss": 2.0308351516723633, "Pretrain/Loss (Raw)": 2.202272653579712, "Pretrain/Step": 5150, "Pretrain/Step Time": 8.814820822328329} +{"Pretrain/Learning Rate": 2.2968916402466604e-05, "Pretrain/Loss": 2.0302820205688477, "Pretrain/Loss (Raw)": 2.006040573120117, "Pretrain/Step": 5151, "Pretrain/Step Time": 8.81417161040008} +{"Pretrain/Learning Rate": 2.2960454711624945e-05, "Pretrain/Loss": 2.0325098037719727, "Pretrain/Loss (Raw)": 2.1076579093933105, "Pretrain/Step": 5152, "Pretrain/Step Time": 8.816033629700541} +{"Pretrain/Learning Rate": 2.2951993255993252e-05, "Pretrain/Loss": 2.0337882041931152, "Pretrain/Loss (Raw)": 2.2694091796875, "Pretrain/Step": 5153, "Pretrain/Step Time": 8.814844477921724} +{"Pretrain/Learning Rate": 2.2943532036547356e-05, "Pretrain/Loss": 2.0356438159942627, "Pretrain/Loss (Raw)": 2.0061004161834717, "Pretrain/Step": 5154, "Pretrain/Step Time": 8.816046915948391} +{"Pretrain/Learning Rate": 2.293507105426303e-05, "Pretrain/Loss": 2.0355124473571777, "Pretrain/Loss (Raw)": 2.1089630126953125, "Pretrain/Step": 5155, "Pretrain/Step Time": 8.820744525641203} +{"Pretrain/Learning Rate": 2.2926610310116047e-05, "Pretrain/Loss": 2.0376434326171875, "Pretrain/Loss (Raw)": 2.1549761295318604, "Pretrain/Step": 5156, "Pretrain/Step Time": 8.8139891885221} +{"Pretrain/Learning Rate": 2.2918149805082127e-05, "Pretrain/Loss": 2.0362472534179688, "Pretrain/Loss (Raw)": 2.0208017826080322, "Pretrain/Step": 5157, "Pretrain/Step Time": 8.813367385417223} +{"Pretrain/Learning Rate": 2.2909689540136985e-05, "Pretrain/Loss": 2.0386435985565186, "Pretrain/Loss (Raw)": 2.2065863609313965, "Pretrain/Step": 5158, "Pretrain/Step Time": 8.814226627349854} +{"Pretrain/Learning Rate": 2.290122951625629e-05, "Pretrain/Loss": 2.0373358726501465, "Pretrain/Loss (Raw)": 1.8978493213653564, "Pretrain/Step": 5159, "Pretrain/Step Time": 8.812204267829657} +{"Pretrain/Learning Rate": 2.2892769734415703e-05, "Pretrain/Loss": 2.0349631309509277, "Pretrain/Loss (Raw)": 1.9604511260986328, "Pretrain/Step": 5160, "Pretrain/Step Time": 8.814852861687541} +{"Pretrain/Learning Rate": 2.2884310195590835e-05, "Pretrain/Loss": 2.0348002910614014, "Pretrain/Loss (Raw)": 2.0023069381713867, "Pretrain/Step": 5161, "Pretrain/Step Time": 8.816778345033526} +{"Pretrain/Learning Rate": 2.2875850900757288e-05, "Pretrain/Loss": 2.036025285720825, "Pretrain/Loss (Raw)": 2.200958490371704, "Pretrain/Step": 5162, "Pretrain/Step Time": 8.81772692501545} +{"Pretrain/Learning Rate": 2.2867391850890623e-05, "Pretrain/Loss": 2.0364789962768555, "Pretrain/Loss (Raw)": 2.0872557163238525, "Pretrain/Step": 5163, "Pretrain/Step Time": 8.819578561931849} +{"Pretrain/Learning Rate": 2.285893304696638e-05, "Pretrain/Loss": 2.037290573120117, "Pretrain/Loss (Raw)": 2.127446174621582, "Pretrain/Step": 5164, "Pretrain/Step Time": 8.816830191761255} +{"Pretrain/Learning Rate": 2.2850474489960065e-05, "Pretrain/Loss": 2.038358688354492, "Pretrain/Loss (Raw)": 2.1594088077545166, "Pretrain/Step": 5165, "Pretrain/Step Time": 8.80902050435543} +{"Pretrain/Learning Rate": 2.2842016180847165e-05, "Pretrain/Loss": 2.039252281188965, "Pretrain/Loss (Raw)": 2.1856985092163086, "Pretrain/Step": 5166, "Pretrain/Step Time": 8.814310308545828} +{"Pretrain/Learning Rate": 2.2833558120603122e-05, "Pretrain/Loss": 2.0381274223327637, "Pretrain/Loss (Raw)": 1.9306848049163818, "Pretrain/Step": 5167, "Pretrain/Step Time": 8.817560628056526} +{"Pretrain/Learning Rate": 2.282510031020337e-05, "Pretrain/Loss": 2.0390448570251465, "Pretrain/Loss (Raw)": 2.0687294006347656, "Pretrain/Step": 5168, "Pretrain/Step Time": 8.815860563889146} +{"Pretrain/Learning Rate": 2.2816642750623294e-05, "Pretrain/Loss": 2.0384442806243896, "Pretrain/Loss (Raw)": 2.176363229751587, "Pretrain/Step": 5169, "Pretrain/Step Time": 8.816165944561362} +{"Pretrain/Learning Rate": 2.280818544283827e-05, "Pretrain/Loss": 2.0379011631011963, "Pretrain/Loss (Raw)": 1.9833215475082397, "Pretrain/Step": 5170, "Pretrain/Step Time": 8.817343028262258} +{"Pretrain/Learning Rate": 2.279972838782362e-05, "Pretrain/Loss": 2.0383005142211914, "Pretrain/Loss (Raw)": 2.2373416423797607, "Pretrain/Step": 5171, "Pretrain/Step Time": 8.810680508613586} +{"Pretrain/Learning Rate": 2.279127158655467e-05, "Pretrain/Loss": 2.0378623008728027, "Pretrain/Loss (Raw)": 1.9146736860275269, "Pretrain/Step": 5172, "Pretrain/Step Time": 8.812507208436728} +{"Pretrain/Learning Rate": 2.2782815040006683e-05, "Pretrain/Loss": 2.0371387004852295, "Pretrain/Loss (Raw)": 1.9857105016708374, "Pretrain/Step": 5173, "Pretrain/Step Time": 8.808009581640363} +{"Pretrain/Learning Rate": 2.2774358749154917e-05, "Pretrain/Loss": 2.0363781452178955, "Pretrain/Loss (Raw)": 2.041513681411743, "Pretrain/Step": 5174, "Pretrain/Step Time": 8.80312574468553} +{"Pretrain/Learning Rate": 2.2765902714974585e-05, "Pretrain/Loss": 2.0384182929992676, "Pretrain/Loss (Raw)": 2.026707172393799, "Pretrain/Step": 5175, "Pretrain/Step Time": 8.805448466911912} +{"Pretrain/Learning Rate": 2.2757446938440886e-05, "Pretrain/Loss": 2.0405218601226807, "Pretrain/Loss (Raw)": 2.139272928237915, "Pretrain/Step": 5176, "Pretrain/Step Time": 8.796131905168295} +{"Pretrain/Learning Rate": 2.274899142052896e-05, "Pretrain/Loss": 2.0416100025177, "Pretrain/Loss (Raw)": 2.055619716644287, "Pretrain/Step": 5177, "Pretrain/Step Time": 8.796610845252872} +{"Pretrain/Learning Rate": 2.2740536162213967e-05, "Pretrain/Loss": 2.040667772293091, "Pretrain/Loss (Raw)": 1.9370461702346802, "Pretrain/Step": 5178, "Pretrain/Step Time": 8.795375501736999} +{"Pretrain/Learning Rate": 2.2732081164470973e-05, "Pretrain/Loss": 2.041935682296753, "Pretrain/Loss (Raw)": 2.1109890937805176, "Pretrain/Step": 5179, "Pretrain/Step Time": 8.788558445870876} +{"Pretrain/Learning Rate": 2.2723626428275072e-05, "Pretrain/Loss": 2.0413007736206055, "Pretrain/Loss (Raw)": 2.0157833099365234, "Pretrain/Step": 5180, "Pretrain/Step Time": 8.79124359600246} +{"Pretrain/Learning Rate": 2.2715171954601303e-05, "Pretrain/Loss": 2.041889190673828, "Pretrain/Loss (Raw)": 1.8642652034759521, "Pretrain/Step": 5181, "Pretrain/Step Time": 8.790026936680079} +{"Pretrain/Learning Rate": 2.2706717744424664e-05, "Pretrain/Loss": 2.0453169345855713, "Pretrain/Loss (Raw)": 2.1350855827331543, "Pretrain/Step": 5182, "Pretrain/Step Time": 8.792206693440676} +{"Pretrain/Learning Rate": 2.2698263798720148e-05, "Pretrain/Loss": 2.046372890472412, "Pretrain/Loss (Raw)": 2.086308717727661, "Pretrain/Step": 5183, "Pretrain/Step Time": 8.791971735656261} +{"Pretrain/Learning Rate": 2.268981011846269e-05, "Pretrain/Loss": 2.0455501079559326, "Pretrain/Loss (Raw)": 1.9649415016174316, "Pretrain/Step": 5184, "Pretrain/Step Time": 8.78750655055046} +{"Pretrain/Learning Rate": 2.2681356704627226e-05, "Pretrain/Loss": 2.0455329418182373, "Pretrain/Loss (Raw)": 2.136129140853882, "Pretrain/Step": 5185, "Pretrain/Step Time": 8.79706585034728} +{"Pretrain/Learning Rate": 2.267290355818862e-05, "Pretrain/Loss": 2.0453338623046875, "Pretrain/Loss (Raw)": 1.958199143409729, "Pretrain/Step": 5186, "Pretrain/Step Time": 8.798426633700728} +{"Pretrain/Learning Rate": 2.2664450680121754e-05, "Pretrain/Loss": 2.043686628341675, "Pretrain/Loss (Raw)": 1.9887410402297974, "Pretrain/Step": 5187, "Pretrain/Step Time": 8.791075691580772} +{"Pretrain/Learning Rate": 2.2655998071401424e-05, "Pretrain/Loss": 2.0438122749328613, "Pretrain/Loss (Raw)": 2.16296124458313, "Pretrain/Step": 5188, "Pretrain/Step Time": 8.792170237749815} +{"Pretrain/Learning Rate": 2.264754573300246e-05, "Pretrain/Loss": 2.0433149337768555, "Pretrain/Loss (Raw)": 1.9566470384597778, "Pretrain/Step": 5189, "Pretrain/Step Time": 8.79560412093997} +{"Pretrain/Learning Rate": 2.2639093665899592e-05, "Pretrain/Loss": 2.0425450801849365, "Pretrain/Loss (Raw)": 1.9683467149734497, "Pretrain/Step": 5190, "Pretrain/Step Time": 8.799176471307874} +{"Pretrain/Learning Rate": 2.263064187106758e-05, "Pretrain/Loss": 2.044081211090088, "Pretrain/Loss (Raw)": 2.228628635406494, "Pretrain/Step": 5191, "Pretrain/Step Time": 8.80152976512909} +{"Pretrain/Learning Rate": 2.2622190349481102e-05, "Pretrain/Loss": 2.0434072017669678, "Pretrain/Loss (Raw)": 1.9696004390716553, "Pretrain/Step": 5192, "Pretrain/Step Time": 8.805360786616802} +{"Pretrain/Learning Rate": 2.2613739102114846e-05, "Pretrain/Loss": 2.042196750640869, "Pretrain/Loss (Raw)": 1.8946479558944702, "Pretrain/Step": 5193, "Pretrain/Step Time": 8.80683035030961} +{"Pretrain/Learning Rate": 2.2605288129943435e-05, "Pretrain/Loss": 2.0428175926208496, "Pretrain/Loss (Raw)": 1.9932267665863037, "Pretrain/Step": 5194, "Pretrain/Step Time": 8.808258077129722} +{"Pretrain/Learning Rate": 2.2596837433941486e-05, "Pretrain/Loss": 2.043403387069702, "Pretrain/Loss (Raw)": 2.104222059249878, "Pretrain/Step": 5195, "Pretrain/Step Time": 8.805235542356968} +{"Pretrain/Learning Rate": 2.2588387015083566e-05, "Pretrain/Loss": 2.043667793273926, "Pretrain/Loss (Raw)": 2.053922414779663, "Pretrain/Step": 5196, "Pretrain/Step Time": 8.802155552431941} +{"Pretrain/Learning Rate": 2.257993687434422e-05, "Pretrain/Loss": 2.0447797775268555, "Pretrain/Loss (Raw)": 2.0925066471099854, "Pretrain/Step": 5197, "Pretrain/Step Time": 8.802907107397914} +{"Pretrain/Learning Rate": 2.2571487012697952e-05, "Pretrain/Loss": 2.0427072048187256, "Pretrain/Loss (Raw)": 1.8685760498046875, "Pretrain/Step": 5198, "Pretrain/Step Time": 8.81324896030128} +{"Pretrain/Learning Rate": 2.2563037431119254e-05, "Pretrain/Loss": 2.043179512023926, "Pretrain/Loss (Raw)": 1.990834355354309, "Pretrain/Step": 5199, "Pretrain/Step Time": 8.814501451328397} +{"Pretrain/Learning Rate": 2.2554588130582556e-05, "Pretrain/Loss": 2.044748544692993, "Pretrain/Loss (Raw)": 2.2720587253570557, "Pretrain/Step": 5200, "Pretrain/Step Time": 8.810028186067939} +{"Pretrain/Learning Rate": 2.254613911206228e-05, "Pretrain/Loss": 2.043977737426758, "Pretrain/Loss (Raw)": 2.0660746097564697, "Pretrain/Step": 5201, "Pretrain/Step Time": 8.80423436127603} +{"Pretrain/Learning Rate": 2.25376903765328e-05, "Pretrain/Loss": 2.045346260070801, "Pretrain/Loss (Raw)": 2.124631643295288, "Pretrain/Step": 5202, "Pretrain/Step Time": 8.799184853211045} +{"Pretrain/Learning Rate": 2.252924192496848e-05, "Pretrain/Loss": 2.044844388961792, "Pretrain/Loss (Raw)": 1.933719277381897, "Pretrain/Step": 5203, "Pretrain/Step Time": 8.800460234284401} +{"Pretrain/Learning Rate": 2.2520793758343614e-05, "Pretrain/Loss": 2.04317569732666, "Pretrain/Loss (Raw)": 2.045990467071533, "Pretrain/Step": 5204, "Pretrain/Step Time": 8.79913560114801} +{"Pretrain/Learning Rate": 2.2512345877632498e-05, "Pretrain/Loss": 2.040717601776123, "Pretrain/Loss (Raw)": 1.7033421993255615, "Pretrain/Step": 5205, "Pretrain/Step Time": 8.804994646459818} +{"Pretrain/Learning Rate": 2.2503898283809374e-05, "Pretrain/Loss": 2.04117488861084, "Pretrain/Loss (Raw)": 2.1261062622070312, "Pretrain/Step": 5206, "Pretrain/Step Time": 8.807777639478445} +{"Pretrain/Learning Rate": 2.2495450977848467e-05, "Pretrain/Loss": 2.040768623352051, "Pretrain/Loss (Raw)": 2.1657538414001465, "Pretrain/Step": 5207, "Pretrain/Step Time": 8.802869046106935} +{"Pretrain/Learning Rate": 2.248700396072395e-05, "Pretrain/Loss": 2.042076587677002, "Pretrain/Loss (Raw)": 2.1121249198913574, "Pretrain/Step": 5208, "Pretrain/Step Time": 8.805262811481953} +{"Pretrain/Learning Rate": 2.2478557233409986e-05, "Pretrain/Loss": 2.0426456928253174, "Pretrain/Loss (Raw)": 2.1263909339904785, "Pretrain/Step": 5209, "Pretrain/Step Time": 8.8004495408386} +{"Pretrain/Learning Rate": 2.2470110796880673e-05, "Pretrain/Loss": 2.042491912841797, "Pretrain/Loss (Raw)": 2.080185890197754, "Pretrain/Step": 5210, "Pretrain/Step Time": 8.802673023194075} +{"Pretrain/Learning Rate": 2.246166465211011e-05, "Pretrain/Loss": 2.0401124954223633, "Pretrain/Loss (Raw)": 1.7192859649658203, "Pretrain/Step": 5211, "Pretrain/Step Time": 8.803149981424212} +{"Pretrain/Learning Rate": 2.245321880007234e-05, "Pretrain/Loss": 2.0395126342773438, "Pretrain/Loss (Raw)": 2.0058043003082275, "Pretrain/Step": 5212, "Pretrain/Step Time": 8.802357355132699} +{"Pretrain/Learning Rate": 2.244477324174138e-05, "Pretrain/Loss": 2.038846969604492, "Pretrain/Loss (Raw)": 1.787497639656067, "Pretrain/Step": 5213, "Pretrain/Step Time": 8.801352433860302} +{"Pretrain/Learning Rate": 2.2436327978091205e-05, "Pretrain/Loss": 2.0383286476135254, "Pretrain/Loss (Raw)": 1.9629268646240234, "Pretrain/Step": 5214, "Pretrain/Step Time": 8.800910206511617} +{"Pretrain/Learning Rate": 2.2427883010095775e-05, "Pretrain/Loss": 2.0365183353424072, "Pretrain/Loss (Raw)": 1.7963309288024902, "Pretrain/Step": 5215, "Pretrain/Step Time": 8.795330023393035} +{"Pretrain/Learning Rate": 2.241943833872899e-05, "Pretrain/Loss": 2.0371971130371094, "Pretrain/Loss (Raw)": 2.2901153564453125, "Pretrain/Step": 5216, "Pretrain/Step Time": 8.795274954289198} +{"Pretrain/Learning Rate": 2.2410993964964745e-05, "Pretrain/Loss": 2.036405324935913, "Pretrain/Loss (Raw)": 1.8738373517990112, "Pretrain/Step": 5217, "Pretrain/Step Time": 8.78926177509129} +{"Pretrain/Learning Rate": 2.2402549889776864e-05, "Pretrain/Loss": 2.034982681274414, "Pretrain/Loss (Raw)": 2.0615296363830566, "Pretrain/Step": 5218, "Pretrain/Step Time": 8.802061539143324} +{"Pretrain/Learning Rate": 2.2394106114139183e-05, "Pretrain/Loss": 2.0342605113983154, "Pretrain/Loss (Raw)": 2.0080201625823975, "Pretrain/Step": 5219, "Pretrain/Step Time": 8.798717448487878} +{"Pretrain/Learning Rate": 2.2385662639025448e-05, "Pretrain/Loss": 2.0342226028442383, "Pretrain/Loss (Raw)": 1.8921869993209839, "Pretrain/Step": 5220, "Pretrain/Step Time": 8.797136813402176} +{"Pretrain/Learning Rate": 2.237721946540942e-05, "Pretrain/Loss": 2.0332884788513184, "Pretrain/Loss (Raw)": 2.016993522644043, "Pretrain/Step": 5221, "Pretrain/Step Time": 8.796601686626673} +{"Pretrain/Learning Rate": 2.2368776594264813e-05, "Pretrain/Loss": 2.0339150428771973, "Pretrain/Loss (Raw)": 2.17055344581604, "Pretrain/Step": 5222, "Pretrain/Step Time": 8.799948429688811} +{"Pretrain/Learning Rate": 2.2360334026565277e-05, "Pretrain/Loss": 2.035872220993042, "Pretrain/Loss (Raw)": 2.2231762409210205, "Pretrain/Step": 5223, "Pretrain/Step Time": 8.792827656492591} +{"Pretrain/Learning Rate": 2.2351891763284466e-05, "Pretrain/Loss": 2.0361952781677246, "Pretrain/Loss (Raw)": 2.0756382942199707, "Pretrain/Step": 5224, "Pretrain/Step Time": 8.790894845500588} +{"Pretrain/Learning Rate": 2.2343449805395973e-05, "Pretrain/Loss": 2.035259246826172, "Pretrain/Loss (Raw)": 2.0234975814819336, "Pretrain/Step": 5225, "Pretrain/Step Time": 8.787013653665781} +{"Pretrain/Learning Rate": 2.2335008153873375e-05, "Pretrain/Loss": 2.034299373626709, "Pretrain/Loss (Raw)": 2.0217220783233643, "Pretrain/Step": 5226, "Pretrain/Step Time": 8.789534334093332} +{"Pretrain/Learning Rate": 2.2326566809690176e-05, "Pretrain/Loss": 2.036334991455078, "Pretrain/Loss (Raw)": 2.227896213531494, "Pretrain/Step": 5227, "Pretrain/Step Time": 8.785958141088486} +{"Pretrain/Learning Rate": 2.2318125773819913e-05, "Pretrain/Loss": 2.03690767288208, "Pretrain/Loss (Raw)": 2.1355037689208984, "Pretrain/Step": 5228, "Pretrain/Step Time": 8.784239504486322} +{"Pretrain/Learning Rate": 2.2309685047236002e-05, "Pretrain/Loss": 2.0351674556732178, "Pretrain/Loss (Raw)": 1.9463454484939575, "Pretrain/Step": 5229, "Pretrain/Step Time": 8.785625211894512} +{"Pretrain/Learning Rate": 2.2301244630911904e-05, "Pretrain/Loss": 2.036146640777588, "Pretrain/Loss (Raw)": 2.0442709922790527, "Pretrain/Step": 5230, "Pretrain/Step Time": 8.785433050245047} +{"Pretrain/Learning Rate": 2.229280452582098e-05, "Pretrain/Loss": 2.036095142364502, "Pretrain/Loss (Raw)": 1.9801623821258545, "Pretrain/Step": 5231, "Pretrain/Step Time": 8.786413006484509} +{"Pretrain/Learning Rate": 2.2284364732936608e-05, "Pretrain/Loss": 2.036412239074707, "Pretrain/Loss (Raw)": 1.9931310415267944, "Pretrain/Step": 5232, "Pretrain/Step Time": 8.777201941236854} +{"Pretrain/Learning Rate": 2.2275925253232073e-05, "Pretrain/Loss": 2.03619647026062, "Pretrain/Loss (Raw)": 2.021221876144409, "Pretrain/Step": 5233, "Pretrain/Step Time": 8.788772398605943} +{"Pretrain/Learning Rate": 2.2267486087680695e-05, "Pretrain/Loss": 2.03916597366333, "Pretrain/Loss (Raw)": 2.0192794799804688, "Pretrain/Step": 5234, "Pretrain/Step Time": 8.784053731709719} +{"Pretrain/Learning Rate": 2.2259047237255684e-05, "Pretrain/Loss": 2.03727126121521, "Pretrain/Loss (Raw)": 1.9856292009353638, "Pretrain/Step": 5235, "Pretrain/Step Time": 8.782235944643617} +{"Pretrain/Learning Rate": 2.2250608702930266e-05, "Pretrain/Loss": 2.0363826751708984, "Pretrain/Loss (Raw)": 1.9465428590774536, "Pretrain/Step": 5236, "Pretrain/Step Time": 8.78162894770503} +{"Pretrain/Learning Rate": 2.2242170485677606e-05, "Pretrain/Loss": 2.0357918739318848, "Pretrain/Loss (Raw)": 2.1019387245178223, "Pretrain/Step": 5237, "Pretrain/Step Time": 8.776889067143202} +{"Pretrain/Learning Rate": 2.223373258647084e-05, "Pretrain/Loss": 2.0358638763427734, "Pretrain/Loss (Raw)": 2.053492784500122, "Pretrain/Step": 5238, "Pretrain/Step Time": 8.77888210117817} +{"Pretrain/Learning Rate": 2.222529500628307e-05, "Pretrain/Loss": 2.036618232727051, "Pretrain/Loss (Raw)": 2.040454864501953, "Pretrain/Step": 5239, "Pretrain/Step Time": 8.776850508525968} +{"Pretrain/Learning Rate": 2.2216857746087355e-05, "Pretrain/Loss": 2.036689281463623, "Pretrain/Loss (Raw)": 2.097099542617798, "Pretrain/Step": 5240, "Pretrain/Step Time": 8.777352821081877} +{"Pretrain/Learning Rate": 2.2208420806856718e-05, "Pretrain/Loss": 2.0373897552490234, "Pretrain/Loss (Raw)": 2.0764713287353516, "Pretrain/Step": 5241, "Pretrain/Step Time": 8.769836654886603} +{"Pretrain/Learning Rate": 2.2199984189564148e-05, "Pretrain/Loss": 2.0376596450805664, "Pretrain/Loss (Raw)": 2.197669267654419, "Pretrain/Step": 5242, "Pretrain/Step Time": 8.765641720965505} +{"Pretrain/Learning Rate": 2.2191547895182594e-05, "Pretrain/Loss": 2.0404820442199707, "Pretrain/Loss (Raw)": 2.133497476577759, "Pretrain/Step": 5243, "Pretrain/Step Time": 8.774346191436052} +{"Pretrain/Learning Rate": 2.2183111924684975e-05, "Pretrain/Loss": 2.042640209197998, "Pretrain/Loss (Raw)": 2.3541605472564697, "Pretrain/Step": 5244, "Pretrain/Step Time": 8.773934846743941} +{"Pretrain/Learning Rate": 2.2174676279044153e-05, "Pretrain/Loss": 2.0421743392944336, "Pretrain/Loss (Raw)": 2.042623281478882, "Pretrain/Step": 5245, "Pretrain/Step Time": 8.775144804269075} +{"Pretrain/Learning Rate": 2.2166240959232985e-05, "Pretrain/Loss": 2.0430407524108887, "Pretrain/Loss (Raw)": 2.0891342163085938, "Pretrain/Step": 5246, "Pretrain/Step Time": 8.777178721502423} +{"Pretrain/Learning Rate": 2.215780596622426e-05, "Pretrain/Loss": 2.043247699737549, "Pretrain/Loss (Raw)": 2.0374746322631836, "Pretrain/Step": 5247, "Pretrain/Step Time": 8.775477081537247} +{"Pretrain/Learning Rate": 2.2149371300990745e-05, "Pretrain/Loss": 2.041674852371216, "Pretrain/Loss (Raw)": 1.9503207206726074, "Pretrain/Step": 5248, "Pretrain/Step Time": 8.775811659172177} +{"Pretrain/Learning Rate": 2.214093696450516e-05, "Pretrain/Loss": 2.041884422302246, "Pretrain/Loss (Raw)": 1.8947478532791138, "Pretrain/Step": 5249, "Pretrain/Step Time": 8.771089423447847} +{"Pretrain/Learning Rate": 2.21325029577402e-05, "Pretrain/Loss": 2.0435516834259033, "Pretrain/Loss (Raw)": 2.1570520401000977, "Pretrain/Step": 5250, "Pretrain/Step Time": 8.776261707767844} +{"Pretrain/Learning Rate": 2.2124069281668507e-05, "Pretrain/Loss": 2.042623281478882, "Pretrain/Loss (Raw)": 2.0327517986297607, "Pretrain/Step": 5251, "Pretrain/Step Time": 8.777634298428893} +{"Pretrain/Learning Rate": 2.2115635937262706e-05, "Pretrain/Loss": 2.04306697845459, "Pretrain/Loss (Raw)": 1.9592968225479126, "Pretrain/Step": 5252, "Pretrain/Step Time": 8.781619813293219} +{"Pretrain/Learning Rate": 2.210720292549535e-05, "Pretrain/Loss": 2.0439724922180176, "Pretrain/Loss (Raw)": 2.2022464275360107, "Pretrain/Step": 5253, "Pretrain/Step Time": 8.781307805329561} +{"Pretrain/Learning Rate": 2.209877024733899e-05, "Pretrain/Loss": 2.043865442276001, "Pretrain/Loss (Raw)": 2.0420656204223633, "Pretrain/Step": 5254, "Pretrain/Step Time": 8.776566741988063} +{"Pretrain/Learning Rate": 2.209033790376611e-05, "Pretrain/Loss": 2.0411486625671387, "Pretrain/Loss (Raw)": 1.7523339986801147, "Pretrain/Step": 5255, "Pretrain/Step Time": 8.775688104331493} +{"Pretrain/Learning Rate": 2.2081905895749183e-05, "Pretrain/Loss": 2.0397770404815674, "Pretrain/Loss (Raw)": 2.0156188011169434, "Pretrain/Step": 5256, "Pretrain/Step Time": 8.77934119477868} +{"Pretrain/Learning Rate": 2.207347422426061e-05, "Pretrain/Loss": 2.0402402877807617, "Pretrain/Loss (Raw)": 1.885872721672058, "Pretrain/Step": 5257, "Pretrain/Step Time": 8.782206578180194} +{"Pretrain/Learning Rate": 2.206504289027279e-05, "Pretrain/Loss": 2.041107177734375, "Pretrain/Loss (Raw)": 2.190774440765381, "Pretrain/Step": 5258, "Pretrain/Step Time": 8.783765008673072} +{"Pretrain/Learning Rate": 2.2056611894758038e-05, "Pretrain/Loss": 2.0433449745178223, "Pretrain/Loss (Raw)": 2.2143139839172363, "Pretrain/Step": 5259, "Pretrain/Step Time": 8.786999078467488} +{"Pretrain/Learning Rate": 2.204818123868869e-05, "Pretrain/Loss": 2.041841983795166, "Pretrain/Loss (Raw)": 1.9320337772369385, "Pretrain/Step": 5260, "Pretrain/Step Time": 8.785321976989508} +{"Pretrain/Learning Rate": 2.203975092303697e-05, "Pretrain/Loss": 2.041116714477539, "Pretrain/Loss (Raw)": 2.0047109127044678, "Pretrain/Step": 5261, "Pretrain/Step Time": 8.783178515732288} +{"Pretrain/Learning Rate": 2.2031320948775135e-05, "Pretrain/Loss": 2.0404653549194336, "Pretrain/Loss (Raw)": 2.0515308380126953, "Pretrain/Step": 5262, "Pretrain/Step Time": 8.785484280437231} +{"Pretrain/Learning Rate": 2.2022891316875362e-05, "Pretrain/Loss": 2.0387039184570312, "Pretrain/Loss (Raw)": 1.9834760427474976, "Pretrain/Step": 5263, "Pretrain/Step Time": 8.790020378306508} +{"Pretrain/Learning Rate": 2.201446202830978e-05, "Pretrain/Loss": 2.03865909576416, "Pretrain/Loss (Raw)": 2.1085309982299805, "Pretrain/Step": 5264, "Pretrain/Step Time": 8.785495983436704} +{"Pretrain/Learning Rate": 2.2006033084050516e-05, "Pretrain/Loss": 2.0390782356262207, "Pretrain/Loss (Raw)": 2.0126073360443115, "Pretrain/Step": 5265, "Pretrain/Step Time": 8.788638917729259} +{"Pretrain/Learning Rate": 2.1997604485069614e-05, "Pretrain/Loss": 2.0395331382751465, "Pretrain/Loss (Raw)": 2.1377339363098145, "Pretrain/Step": 5266, "Pretrain/Step Time": 8.790360884740949} +{"Pretrain/Learning Rate": 2.1989176232339122e-05, "Pretrain/Loss": 2.0391225814819336, "Pretrain/Loss (Raw)": 2.039546489715576, "Pretrain/Step": 5267, "Pretrain/Step Time": 8.789607863873243} +{"Pretrain/Learning Rate": 2.1980748326831002e-05, "Pretrain/Loss": 2.0398077964782715, "Pretrain/Loss (Raw)": 1.9880210161209106, "Pretrain/Step": 5268, "Pretrain/Step Time": 8.79531591758132} +{"Pretrain/Learning Rate": 2.1972320769517226e-05, "Pretrain/Loss": 2.0390305519104004, "Pretrain/Loss (Raw)": 1.8437879085540771, "Pretrain/Step": 5269, "Pretrain/Step Time": 8.794850362464786} +{"Pretrain/Learning Rate": 2.1963893561369672e-05, "Pretrain/Loss": 2.0387611389160156, "Pretrain/Loss (Raw)": 2.0162973403930664, "Pretrain/Step": 5270, "Pretrain/Step Time": 8.798208026215434} +{"Pretrain/Learning Rate": 2.1955466703360232e-05, "Pretrain/Loss": 2.0376133918762207, "Pretrain/Loss (Raw)": 2.068793296813965, "Pretrain/Step": 5271, "Pretrain/Step Time": 8.7952551394701} +{"Pretrain/Learning Rate": 2.1947040196460704e-05, "Pretrain/Loss": 2.0405309200286865, "Pretrain/Loss (Raw)": 2.2178995609283447, "Pretrain/Step": 5272, "Pretrain/Step Time": 8.798861449584365} +{"Pretrain/Learning Rate": 2.1938614041642903e-05, "Pretrain/Loss": 2.041125774383545, "Pretrain/Loss (Raw)": 2.1046550273895264, "Pretrain/Step": 5273, "Pretrain/Step Time": 8.799745999276638} +{"Pretrain/Learning Rate": 2.1930188239878537e-05, "Pretrain/Loss": 2.0416088104248047, "Pretrain/Loss (Raw)": 2.0689432621002197, "Pretrain/Step": 5274, "Pretrain/Step Time": 8.797936782240868} +{"Pretrain/Learning Rate": 2.192176279213935e-05, "Pretrain/Loss": 2.0428199768066406, "Pretrain/Loss (Raw)": 2.221907377243042, "Pretrain/Step": 5275, "Pretrain/Step Time": 8.795344488695264} +{"Pretrain/Learning Rate": 2.191333769939696e-05, "Pretrain/Loss": 2.0459296703338623, "Pretrain/Loss (Raw)": 2.0604970455169678, "Pretrain/Step": 5276, "Pretrain/Step Time": 8.804154109209776} +{"Pretrain/Learning Rate": 2.1904912962623035e-05, "Pretrain/Loss": 2.047628164291382, "Pretrain/Loss (Raw)": 1.9828225374221802, "Pretrain/Step": 5277, "Pretrain/Step Time": 8.804188288748264} +{"Pretrain/Learning Rate": 2.1896488582789117e-05, "Pretrain/Loss": 2.046964168548584, "Pretrain/Loss (Raw)": 2.11727237701416, "Pretrain/Step": 5278, "Pretrain/Step Time": 8.80544618703425} +{"Pretrain/Learning Rate": 2.1888064560866765e-05, "Pretrain/Loss": 2.048471450805664, "Pretrain/Loss (Raw)": 2.1989693641662598, "Pretrain/Step": 5279, "Pretrain/Step Time": 8.801625963300467} +{"Pretrain/Learning Rate": 2.187964089782747e-05, "Pretrain/Loss": 2.0465621948242188, "Pretrain/Loss (Raw)": 1.8633038997650146, "Pretrain/Step": 5280, "Pretrain/Step Time": 8.801778549328446} +{"Pretrain/Learning Rate": 2.187121759464269e-05, "Pretrain/Loss": 2.0440473556518555, "Pretrain/Loss (Raw)": 1.9474900960922241, "Pretrain/Step": 5281, "Pretrain/Step Time": 8.802795028313994} +{"Pretrain/Learning Rate": 2.1862794652283837e-05, "Pretrain/Loss": 2.045351028442383, "Pretrain/Loss (Raw)": 2.1729483604431152, "Pretrain/Step": 5282, "Pretrain/Step Time": 8.803713059052825} +{"Pretrain/Learning Rate": 2.1854372071722297e-05, "Pretrain/Loss": 2.045593500137329, "Pretrain/Loss (Raw)": 2.1400039196014404, "Pretrain/Step": 5283, "Pretrain/Step Time": 8.802970277145505} +{"Pretrain/Learning Rate": 2.1845949853929382e-05, "Pretrain/Loss": 2.043869972229004, "Pretrain/Loss (Raw)": 1.9343611001968384, "Pretrain/Step": 5284, "Pretrain/Step Time": 8.803406132385135} +{"Pretrain/Learning Rate": 2.1837527999876396e-05, "Pretrain/Loss": 2.044102668762207, "Pretrain/Loss (Raw)": 2.0506176948547363, "Pretrain/Step": 5285, "Pretrain/Step Time": 8.799151178449392} +{"Pretrain/Learning Rate": 2.1829106510534585e-05, "Pretrain/Loss": 2.042790412902832, "Pretrain/Loss (Raw)": 2.0385828018188477, "Pretrain/Step": 5286, "Pretrain/Step Time": 8.801427286118269} +{"Pretrain/Learning Rate": 2.1820685386875155e-05, "Pretrain/Loss": 2.0448381900787354, "Pretrain/Loss (Raw)": 2.1599864959716797, "Pretrain/Step": 5287, "Pretrain/Step Time": 8.798125702887774} +{"Pretrain/Learning Rate": 2.1812264629869257e-05, "Pretrain/Loss": 2.044538974761963, "Pretrain/Loss (Raw)": 1.92215895652771, "Pretrain/Step": 5288, "Pretrain/Step Time": 8.79755812510848} +{"Pretrain/Learning Rate": 2.1803844240488036e-05, "Pretrain/Loss": 2.0451736450195312, "Pretrain/Loss (Raw)": 2.083540439605713, "Pretrain/Step": 5289, "Pretrain/Step Time": 8.795302156358957} +{"Pretrain/Learning Rate": 2.179542421970255e-05, "Pretrain/Loss": 2.0371153354644775, "Pretrain/Loss (Raw)": 1.169478416442871, "Pretrain/Step": 5290, "Pretrain/Step Time": 8.797367956489325} +{"Pretrain/Learning Rate": 2.1787004568483846e-05, "Pretrain/Loss": 2.037126064300537, "Pretrain/Loss (Raw)": 2.08862566947937, "Pretrain/Step": 5291, "Pretrain/Step Time": 8.797473894432187} +{"Pretrain/Learning Rate": 2.1778585287802914e-05, "Pretrain/Loss": 2.0360541343688965, "Pretrain/Loss (Raw)": 1.9902358055114746, "Pretrain/Step": 5292, "Pretrain/Step Time": 8.799774637445807} +{"Pretrain/Learning Rate": 2.1770166378630708e-05, "Pretrain/Loss": 2.0335865020751953, "Pretrain/Loss (Raw)": 1.843567132949829, "Pretrain/Step": 5293, "Pretrain/Step Time": 8.802253227680922} +{"Pretrain/Learning Rate": 2.1761747841938133e-05, "Pretrain/Loss": 2.033606767654419, "Pretrain/Loss (Raw)": 2.1882998943328857, "Pretrain/Step": 5294, "Pretrain/Step Time": 8.797702318057418} +{"Pretrain/Learning Rate": 2.175332967869606e-05, "Pretrain/Loss": 2.0345265865325928, "Pretrain/Loss (Raw)": 2.048414945602417, "Pretrain/Step": 5295, "Pretrain/Step Time": 8.798399835824966} +{"Pretrain/Learning Rate": 2.17449118898753e-05, "Pretrain/Loss": 2.0325231552124023, "Pretrain/Loss (Raw)": 1.8123167753219604, "Pretrain/Step": 5296, "Pretrain/Step Time": 8.80195595137775} +{"Pretrain/Learning Rate": 2.1736494476446646e-05, "Pretrain/Loss": 2.0325064659118652, "Pretrain/Loss (Raw)": 2.1742043495178223, "Pretrain/Step": 5297, "Pretrain/Step Time": 8.807516848668456} +{"Pretrain/Learning Rate": 2.172807743938082e-05, "Pretrain/Loss": 2.0328269004821777, "Pretrain/Loss (Raw)": 2.0243403911590576, "Pretrain/Step": 5298, "Pretrain/Step Time": 8.801624324172735} +{"Pretrain/Learning Rate": 2.171966077964853e-05, "Pretrain/Loss": 2.0311102867126465, "Pretrain/Loss (Raw)": 2.017608642578125, "Pretrain/Step": 5299, "Pretrain/Step Time": 8.804383497685194} +{"Pretrain/Learning Rate": 2.1711244498220412e-05, "Pretrain/Loss": 2.0313031673431396, "Pretrain/Loss (Raw)": 1.9393653869628906, "Pretrain/Step": 5300, "Pretrain/Step Time": 8.810924869030714} +{"Pretrain/Learning Rate": 2.170282859606708e-05, "Pretrain/Loss": 2.0318281650543213, "Pretrain/Loss (Raw)": 2.052905321121216, "Pretrain/Step": 5301, "Pretrain/Step Time": 8.811433603987098} +{"Pretrain/Learning Rate": 2.1694413074159082e-05, "Pretrain/Loss": 2.0338099002838135, "Pretrain/Loss (Raw)": 2.2951672077178955, "Pretrain/Step": 5302, "Pretrain/Step Time": 8.817682841792703} +{"Pretrain/Learning Rate": 2.1685997933466948e-05, "Pretrain/Loss": 2.035245895385742, "Pretrain/Loss (Raw)": 2.210528612136841, "Pretrain/Step": 5303, "Pretrain/Step Time": 8.81500145047903} +{"Pretrain/Learning Rate": 2.167758317496115e-05, "Pretrain/Loss": 2.0324220657348633, "Pretrain/Loss (Raw)": 1.777844786643982, "Pretrain/Step": 5304, "Pretrain/Step Time": 8.818720396608114} +{"Pretrain/Learning Rate": 2.1669168799612118e-05, "Pretrain/Loss": 2.032179832458496, "Pretrain/Loss (Raw)": 2.024587392807007, "Pretrain/Step": 5305, "Pretrain/Step Time": 8.8178976085037} +{"Pretrain/Learning Rate": 2.1660754808390235e-05, "Pretrain/Loss": 2.033717393875122, "Pretrain/Loss (Raw)": 2.1338448524475098, "Pretrain/Step": 5306, "Pretrain/Step Time": 8.815185220912099} +{"Pretrain/Learning Rate": 2.1652341202265838e-05, "Pretrain/Loss": 2.0319292545318604, "Pretrain/Loss (Raw)": 1.882099986076355, "Pretrain/Step": 5307, "Pretrain/Step Time": 8.8175193592906} +{"Pretrain/Learning Rate": 2.1643927982209233e-05, "Pretrain/Loss": 2.0321245193481445, "Pretrain/Loss (Raw)": 2.0408005714416504, "Pretrain/Step": 5308, "Pretrain/Step Time": 8.818559594452381} +{"Pretrain/Learning Rate": 2.1635515149190665e-05, "Pretrain/Loss": 2.0348258018493652, "Pretrain/Loss (Raw)": 2.2100377082824707, "Pretrain/Step": 5309, "Pretrain/Step Time": 8.813462501391768} +{"Pretrain/Learning Rate": 2.1627102704180353e-05, "Pretrain/Loss": 2.0339455604553223, "Pretrain/Loss (Raw)": 2.0224149227142334, "Pretrain/Step": 5310, "Pretrain/Step Time": 8.81383396871388} +{"Pretrain/Learning Rate": 2.1618690648148435e-05, "Pretrain/Loss": 2.033757209777832, "Pretrain/Loss (Raw)": 2.062194585800171, "Pretrain/Step": 5311, "Pretrain/Step Time": 8.815882746130228} +{"Pretrain/Learning Rate": 2.161027898206506e-05, "Pretrain/Loss": 2.0341100692749023, "Pretrain/Loss (Raw)": 2.010075807571411, "Pretrain/Step": 5312, "Pretrain/Step Time": 8.816060366109014} +{"Pretrain/Learning Rate": 2.160186770690027e-05, "Pretrain/Loss": 2.03446888923645, "Pretrain/Loss (Raw)": 2.182091474533081, "Pretrain/Step": 5313, "Pretrain/Step Time": 8.809495711699128} +{"Pretrain/Learning Rate": 2.1593456823624127e-05, "Pretrain/Loss": 2.0355923175811768, "Pretrain/Loss (Raw)": 2.1019861698150635, "Pretrain/Step": 5314, "Pretrain/Step Time": 8.807360630482435} +{"Pretrain/Learning Rate": 2.1585046333206573e-05, "Pretrain/Loss": 2.0367722511291504, "Pretrain/Loss (Raw)": 2.1397900581359863, "Pretrain/Step": 5315, "Pretrain/Step Time": 8.80534085817635} +{"Pretrain/Learning Rate": 2.157663623661759e-05, "Pretrain/Loss": 2.0354366302490234, "Pretrain/Loss (Raw)": 1.9920094013214111, "Pretrain/Step": 5316, "Pretrain/Step Time": 8.80409392528236} +{"Pretrain/Learning Rate": 2.156822653482703e-05, "Pretrain/Loss": 2.0357003211975098, "Pretrain/Loss (Raw)": 1.9903504848480225, "Pretrain/Step": 5317, "Pretrain/Step Time": 8.801557701081038} +{"Pretrain/Learning Rate": 2.155981722880477e-05, "Pretrain/Loss": 2.036362409591675, "Pretrain/Loss (Raw)": 2.0531086921691895, "Pretrain/Step": 5318, "Pretrain/Step Time": 8.80127526819706} +{"Pretrain/Learning Rate": 2.1551408319520588e-05, "Pretrain/Loss": 2.034841537475586, "Pretrain/Loss (Raw)": 2.033954620361328, "Pretrain/Step": 5319, "Pretrain/Step Time": 8.797010203823447} +{"Pretrain/Learning Rate": 2.1542999807944258e-05, "Pretrain/Loss": 2.035707712173462, "Pretrain/Loss (Raw)": 2.0804800987243652, "Pretrain/Step": 5320, "Pretrain/Step Time": 8.79460098221898} +{"Pretrain/Learning Rate": 2.1534591695045473e-05, "Pretrain/Loss": 2.0376009941101074, "Pretrain/Loss (Raw)": 2.1369876861572266, "Pretrain/Step": 5321, "Pretrain/Step Time": 8.793036837130785} +{"Pretrain/Learning Rate": 2.1526183981793908e-05, "Pretrain/Loss": 2.037266492843628, "Pretrain/Loss (Raw)": 1.9504148960113525, "Pretrain/Step": 5322, "Pretrain/Step Time": 8.791979959234595} +{"Pretrain/Learning Rate": 2.1517776669159166e-05, "Pretrain/Loss": 2.038424491882324, "Pretrain/Loss (Raw)": 2.252417802810669, "Pretrain/Step": 5323, "Pretrain/Step Time": 8.790911506861448} +{"Pretrain/Learning Rate": 2.150936975811084e-05, "Pretrain/Loss": 2.0386078357696533, "Pretrain/Loss (Raw)": 2.077418565750122, "Pretrain/Step": 5324, "Pretrain/Step Time": 8.799904745072126} +{"Pretrain/Learning Rate": 2.1500963249618433e-05, "Pretrain/Loss": 2.037201166152954, "Pretrain/Loss (Raw)": 1.912442922592163, "Pretrain/Step": 5325, "Pretrain/Step Time": 8.799933468922973} +{"Pretrain/Learning Rate": 2.149255714465144e-05, "Pretrain/Loss": 2.0369198322296143, "Pretrain/Loss (Raw)": 1.8325756788253784, "Pretrain/Step": 5326, "Pretrain/Step Time": 8.791289001703262} +{"Pretrain/Learning Rate": 2.1484151444179273e-05, "Pretrain/Loss": 2.0371198654174805, "Pretrain/Loss (Raw)": 2.016432285308838, "Pretrain/Step": 5327, "Pretrain/Step Time": 8.792907236143947} +{"Pretrain/Learning Rate": 2.147574614917134e-05, "Pretrain/Loss": 2.0346174240112305, "Pretrain/Loss (Raw)": 1.9517509937286377, "Pretrain/Step": 5328, "Pretrain/Step Time": 8.791193839162588} +{"Pretrain/Learning Rate": 2.146734126059696e-05, "Pretrain/Loss": 2.033932685852051, "Pretrain/Loss (Raw)": 1.9784247875213623, "Pretrain/Step": 5329, "Pretrain/Step Time": 8.785342739894986} +{"Pretrain/Learning Rate": 2.1458936779425438e-05, "Pretrain/Loss": 2.032492160797119, "Pretrain/Loss (Raw)": 1.9402416944503784, "Pretrain/Step": 5330, "Pretrain/Step Time": 8.788164442405105} +{"Pretrain/Learning Rate": 2.145053270662601e-05, "Pretrain/Loss": 2.033977508544922, "Pretrain/Loss (Raw)": 2.123823881149292, "Pretrain/Step": 5331, "Pretrain/Step Time": 8.789515506476164} +{"Pretrain/Learning Rate": 2.1442129043167874e-05, "Pretrain/Loss": 2.034001588821411, "Pretrain/Loss (Raw)": 2.049095869064331, "Pretrain/Step": 5332, "Pretrain/Step Time": 8.79355720244348} +{"Pretrain/Learning Rate": 2.1433725790020186e-05, "Pretrain/Loss": 2.0371832847595215, "Pretrain/Loss (Raw)": 2.110611915588379, "Pretrain/Step": 5333, "Pretrain/Step Time": 8.78618137538433} +{"Pretrain/Learning Rate": 2.1425322948152042e-05, "Pretrain/Loss": 2.03658127784729, "Pretrain/Loss (Raw)": 2.0490310192108154, "Pretrain/Step": 5334, "Pretrain/Step Time": 8.786864155903459} +{"Pretrain/Learning Rate": 2.14169205185325e-05, "Pretrain/Loss": 2.03566312789917, "Pretrain/Loss (Raw)": 2.048248529434204, "Pretrain/Step": 5335, "Pretrain/Step Time": 8.78702299669385} +{"Pretrain/Learning Rate": 2.140851850213057e-05, "Pretrain/Loss": 2.0334415435791016, "Pretrain/Loss (Raw)": 1.8277250528335571, "Pretrain/Step": 5336, "Pretrain/Step Time": 8.788449516519904} +{"Pretrain/Learning Rate": 2.1400116899915205e-05, "Pretrain/Loss": 2.0332870483398438, "Pretrain/Loss (Raw)": 2.106640338897705, "Pretrain/Step": 5337, "Pretrain/Step Time": 8.788169438019395} +{"Pretrain/Learning Rate": 2.1391715712855327e-05, "Pretrain/Loss": 2.0327632427215576, "Pretrain/Loss (Raw)": 2.0131380558013916, "Pretrain/Step": 5338, "Pretrain/Step Time": 8.785464843735099} +{"Pretrain/Learning Rate": 2.1383314941919795e-05, "Pretrain/Loss": 2.034972667694092, "Pretrain/Loss (Raw)": 2.002067804336548, "Pretrain/Step": 5339, "Pretrain/Step Time": 8.791310105472803} +{"Pretrain/Learning Rate": 2.1374914588077427e-05, "Pretrain/Loss": 2.0364582538604736, "Pretrain/Loss (Raw)": 2.1959774494171143, "Pretrain/Step": 5340, "Pretrain/Step Time": 8.793338529765606} +{"Pretrain/Learning Rate": 2.1366514652296987e-05, "Pretrain/Loss": 2.038853168487549, "Pretrain/Loss (Raw)": 2.0940499305725098, "Pretrain/Step": 5341, "Pretrain/Step Time": 8.793158018961549} +{"Pretrain/Learning Rate": 2.135811513554721e-05, "Pretrain/Loss": 2.0394718647003174, "Pretrain/Loss (Raw)": 2.0421323776245117, "Pretrain/Step": 5342, "Pretrain/Step Time": 8.796690165996552} +{"Pretrain/Learning Rate": 2.1349716038796742e-05, "Pretrain/Loss": 2.04317569732666, "Pretrain/Loss (Raw)": 2.270416736602783, "Pretrain/Step": 5343, "Pretrain/Step Time": 8.79126537963748} +{"Pretrain/Learning Rate": 2.1341317363014223e-05, "Pretrain/Loss": 2.0395803451538086, "Pretrain/Loss (Raw)": 1.8299087285995483, "Pretrain/Step": 5344, "Pretrain/Step Time": 8.79098479449749} +{"Pretrain/Learning Rate": 2.133291910916823e-05, "Pretrain/Loss": 2.0426928997039795, "Pretrain/Loss (Raw)": 2.272247314453125, "Pretrain/Step": 5345, "Pretrain/Step Time": 8.790195615962148} +{"Pretrain/Learning Rate": 2.1324521278227287e-05, "Pretrain/Loss": 2.0421996116638184, "Pretrain/Loss (Raw)": 1.9983861446380615, "Pretrain/Step": 5346, "Pretrain/Step Time": 8.780621590092778} +{"Pretrain/Learning Rate": 2.131612387115987e-05, "Pretrain/Loss": 2.042205572128296, "Pretrain/Loss (Raw)": 2.008770227432251, "Pretrain/Step": 5347, "Pretrain/Step Time": 8.788667097687721} +{"Pretrain/Learning Rate": 2.13077268889344e-05, "Pretrain/Loss": 2.0438005924224854, "Pretrain/Loss (Raw)": 2.0963551998138428, "Pretrain/Step": 5348, "Pretrain/Step Time": 8.792391017079353} +{"Pretrain/Learning Rate": 2.1299330332519273e-05, "Pretrain/Loss": 2.04429030418396, "Pretrain/Loss (Raw)": 2.0796878337860107, "Pretrain/Step": 5349, "Pretrain/Step Time": 8.791609851643443} +{"Pretrain/Learning Rate": 2.1290934202882805e-05, "Pretrain/Loss": 2.043694496154785, "Pretrain/Loss (Raw)": 2.0942838191986084, "Pretrain/Step": 5350, "Pretrain/Step Time": 8.791283467784524} +{"Pretrain/Learning Rate": 2.128253850099329e-05, "Pretrain/Loss": 2.0425186157226562, "Pretrain/Loss (Raw)": 2.0726706981658936, "Pretrain/Step": 5351, "Pretrain/Step Time": 8.790410123765469} +{"Pretrain/Learning Rate": 2.1274143227818938e-05, "Pretrain/Loss": 2.0434250831604004, "Pretrain/Loss (Raw)": 2.1916310787200928, "Pretrain/Step": 5352, "Pretrain/Step Time": 8.791540453210473} +{"Pretrain/Learning Rate": 2.126574838432796e-05, "Pretrain/Loss": 2.043530225753784, "Pretrain/Loss (Raw)": 2.036980152130127, "Pretrain/Step": 5353, "Pretrain/Step Time": 8.787977440282702} +{"Pretrain/Learning Rate": 2.1257353971488463e-05, "Pretrain/Loss": 2.0436763763427734, "Pretrain/Loss (Raw)": 2.0404374599456787, "Pretrain/Step": 5354, "Pretrain/Step Time": 8.793123742565513} +{"Pretrain/Learning Rate": 2.1248959990268554e-05, "Pretrain/Loss": 2.0416259765625, "Pretrain/Loss (Raw)": 1.96543550491333, "Pretrain/Step": 5355, "Pretrain/Step Time": 8.788586996495724} +{"Pretrain/Learning Rate": 2.1240566441636238e-05, "Pretrain/Loss": 2.0420398712158203, "Pretrain/Loss (Raw)": 2.188481569290161, "Pretrain/Step": 5356, "Pretrain/Step Time": 8.78910281509161} +{"Pretrain/Learning Rate": 2.1232173326559535e-05, "Pretrain/Loss": 2.0438263416290283, "Pretrain/Loss (Raw)": 2.1750235557556152, "Pretrain/Step": 5357, "Pretrain/Step Time": 8.79587753303349} +{"Pretrain/Learning Rate": 2.122378064600634e-05, "Pretrain/Loss": 2.041240692138672, "Pretrain/Loss (Raw)": 1.7132993936538696, "Pretrain/Step": 5358, "Pretrain/Step Time": 8.79681140370667} +{"Pretrain/Learning Rate": 2.121538840094457e-05, "Pretrain/Loss": 2.0413756370544434, "Pretrain/Loss (Raw)": 1.997430443763733, "Pretrain/Step": 5359, "Pretrain/Step Time": 8.79622009396553} +{"Pretrain/Learning Rate": 2.120699659234203e-05, "Pretrain/Loss": 2.0426554679870605, "Pretrain/Loss (Raw)": 2.1569664478302, "Pretrain/Step": 5360, "Pretrain/Step Time": 8.798042144626379} +{"Pretrain/Learning Rate": 2.1198605221166528e-05, "Pretrain/Loss": 2.042616367340088, "Pretrain/Loss (Raw)": 2.016202449798584, "Pretrain/Step": 5361, "Pretrain/Step Time": 8.79927665181458} +{"Pretrain/Learning Rate": 2.1190214288385778e-05, "Pretrain/Loss": 2.043867588043213, "Pretrain/Loss (Raw)": 2.1794369220733643, "Pretrain/Step": 5362, "Pretrain/Step Time": 8.796526504680514} +{"Pretrain/Learning Rate": 2.1181823794967472e-05, "Pretrain/Loss": 2.0440540313720703, "Pretrain/Loss (Raw)": 2.0094878673553467, "Pretrain/Step": 5363, "Pretrain/Step Time": 8.797617463395} +{"Pretrain/Learning Rate": 2.1173433741879234e-05, "Pretrain/Loss": 2.0449297428131104, "Pretrain/Loss (Raw)": 2.0586323738098145, "Pretrain/Step": 5364, "Pretrain/Step Time": 8.801194623112679} +{"Pretrain/Learning Rate": 2.116504413008865e-05, "Pretrain/Loss": 2.0444862842559814, "Pretrain/Loss (Raw)": 2.045196533203125, "Pretrain/Step": 5365, "Pretrain/Step Time": 8.799968341365457} +{"Pretrain/Learning Rate": 2.1156654960563248e-05, "Pretrain/Loss": 2.045807123184204, "Pretrain/Loss (Raw)": 2.2225594520568848, "Pretrain/Step": 5366, "Pretrain/Step Time": 8.79964485578239} +{"Pretrain/Learning Rate": 2.1148266234270508e-05, "Pretrain/Loss": 2.046720266342163, "Pretrain/Loss (Raw)": 2.157336473464966, "Pretrain/Step": 5367, "Pretrain/Step Time": 8.79438783787191} +{"Pretrain/Learning Rate": 2.1139877952177852e-05, "Pretrain/Loss": 2.0455377101898193, "Pretrain/Loss (Raw)": 1.9457169771194458, "Pretrain/Step": 5368, "Pretrain/Step Time": 8.799448570236564} +{"Pretrain/Learning Rate": 2.1131490115252668e-05, "Pretrain/Loss": 2.045747995376587, "Pretrain/Loss (Raw)": 2.103379726409912, "Pretrain/Step": 5369, "Pretrain/Step Time": 8.805453708395362} +{"Pretrain/Learning Rate": 2.1123102724462262e-05, "Pretrain/Loss": 2.0442662239074707, "Pretrain/Loss (Raw)": 2.008014440536499, "Pretrain/Step": 5370, "Pretrain/Step Time": 8.80453466065228} +{"Pretrain/Learning Rate": 2.1114715780773924e-05, "Pretrain/Loss": 2.044265031814575, "Pretrain/Loss (Raw)": 2.1333699226379395, "Pretrain/Step": 5371, "Pretrain/Step Time": 8.79493116401136} +{"Pretrain/Learning Rate": 2.110632928515487e-05, "Pretrain/Loss": 2.042428970336914, "Pretrain/Loss (Raw)": 2.119131088256836, "Pretrain/Step": 5372, "Pretrain/Step Time": 8.805132821202278} +{"Pretrain/Learning Rate": 2.1097943238572272e-05, "Pretrain/Loss": 2.0418310165405273, "Pretrain/Loss (Raw)": 1.96609628200531, "Pretrain/Step": 5373, "Pretrain/Step Time": 8.804956456646323} +{"Pretrain/Learning Rate": 2.108955764199324e-05, "Pretrain/Loss": 2.040238857269287, "Pretrain/Loss (Raw)": 1.8853236436843872, "Pretrain/Step": 5374, "Pretrain/Step Time": 8.802577236667275} +{"Pretrain/Learning Rate": 2.1081172496384855e-05, "Pretrain/Loss": 2.0389719009399414, "Pretrain/Loss (Raw)": 1.8753061294555664, "Pretrain/Step": 5375, "Pretrain/Step Time": 8.801358379423618} +{"Pretrain/Learning Rate": 2.107278780271412e-05, "Pretrain/Loss": 2.040606737136841, "Pretrain/Loss (Raw)": 2.1595897674560547, "Pretrain/Step": 5376, "Pretrain/Step Time": 8.809417532756925} +{"Pretrain/Learning Rate": 2.1064403561948003e-05, "Pretrain/Loss": 2.039248466491699, "Pretrain/Loss (Raw)": 1.720848560333252, "Pretrain/Step": 5377, "Pretrain/Step Time": 8.808229342103004} +{"Pretrain/Learning Rate": 2.105601977505341e-05, "Pretrain/Loss": 2.03865122795105, "Pretrain/Loss (Raw)": 2.080638885498047, "Pretrain/Step": 5378, "Pretrain/Step Time": 8.804879082366824} +{"Pretrain/Learning Rate": 2.1047636442997205e-05, "Pretrain/Loss": 2.037714719772339, "Pretrain/Loss (Raw)": 1.9128779172897339, "Pretrain/Step": 5379, "Pretrain/Step Time": 8.812233401462436} +{"Pretrain/Learning Rate": 2.1039253566746182e-05, "Pretrain/Loss": 2.038475275039673, "Pretrain/Loss (Raw)": 2.0566418170928955, "Pretrain/Step": 5380, "Pretrain/Step Time": 8.809570357203484} +{"Pretrain/Learning Rate": 2.1030871147267113e-05, "Pretrain/Loss": 2.039144277572632, "Pretrain/Loss (Raw)": 2.2878780364990234, "Pretrain/Step": 5381, "Pretrain/Step Time": 8.806893449276686} +{"Pretrain/Learning Rate": 2.1022489185526674e-05, "Pretrain/Loss": 2.0380890369415283, "Pretrain/Loss (Raw)": 1.9070160388946533, "Pretrain/Step": 5382, "Pretrain/Step Time": 8.808002898469567} +{"Pretrain/Learning Rate": 2.1014107682491534e-05, "Pretrain/Loss": 2.03983736038208, "Pretrain/Loss (Raw)": 1.976121425628662, "Pretrain/Step": 5383, "Pretrain/Step Time": 8.809873344376683} +{"Pretrain/Learning Rate": 2.1005726639128276e-05, "Pretrain/Loss": 2.0392563343048096, "Pretrain/Loss (Raw)": 1.9412201642990112, "Pretrain/Step": 5384, "Pretrain/Step Time": 8.81078701838851} +{"Pretrain/Learning Rate": 2.0997346056403438e-05, "Pretrain/Loss": 2.0416269302368164, "Pretrain/Loss (Raw)": 2.1893153190612793, "Pretrain/Step": 5385, "Pretrain/Step Time": 8.805130505934358} +{"Pretrain/Learning Rate": 2.0988965935283524e-05, "Pretrain/Loss": 2.0398221015930176, "Pretrain/Loss (Raw)": 1.959744930267334, "Pretrain/Step": 5386, "Pretrain/Step Time": 8.807083470746875} +{"Pretrain/Learning Rate": 2.098058627673495e-05, "Pretrain/Loss": 2.038433313369751, "Pretrain/Loss (Raw)": 2.036576271057129, "Pretrain/Step": 5387, "Pretrain/Step Time": 8.80515849776566} +{"Pretrain/Learning Rate": 2.097220708172411e-05, "Pretrain/Loss": 2.0402770042419434, "Pretrain/Loss (Raw)": 2.1680331230163574, "Pretrain/Step": 5388, "Pretrain/Step Time": 8.807520654052496} +{"Pretrain/Learning Rate": 2.0963828351217327e-05, "Pretrain/Loss": 2.0404300689697266, "Pretrain/Loss (Raw)": 2.0242810249328613, "Pretrain/Step": 5389, "Pretrain/Step Time": 8.80488145723939} +{"Pretrain/Learning Rate": 2.0955450086180882e-05, "Pretrain/Loss": 2.0423622131347656, "Pretrain/Loss (Raw)": 2.2988502979278564, "Pretrain/Step": 5390, "Pretrain/Step Time": 8.800940519198775} +{"Pretrain/Learning Rate": 2.094707228758099e-05, "Pretrain/Loss": 2.0423316955566406, "Pretrain/Loss (Raw)": 1.979550838470459, "Pretrain/Step": 5391, "Pretrain/Step Time": 8.800192216411233} +{"Pretrain/Learning Rate": 2.093869495638382e-05, "Pretrain/Loss": 2.0407042503356934, "Pretrain/Loss (Raw)": 1.9002187252044678, "Pretrain/Step": 5392, "Pretrain/Step Time": 8.804691459983587} +{"Pretrain/Learning Rate": 2.093031809355548e-05, "Pretrain/Loss": 2.0415868759155273, "Pretrain/Loss (Raw)": 2.1255693435668945, "Pretrain/Step": 5393, "Pretrain/Step Time": 8.800951700657606} +{"Pretrain/Learning Rate": 2.0921941700062047e-05, "Pretrain/Loss": 2.0415616035461426, "Pretrain/Loss (Raw)": 2.1345138549804688, "Pretrain/Step": 5394, "Pretrain/Step Time": 8.800123546272516} +{"Pretrain/Learning Rate": 2.0913565776869498e-05, "Pretrain/Loss": 2.0432512760162354, "Pretrain/Loss (Raw)": 2.255854845046997, "Pretrain/Step": 5395, "Pretrain/Step Time": 8.802506137639284} +{"Pretrain/Learning Rate": 2.0905190324943814e-05, "Pretrain/Loss": 2.0444788932800293, "Pretrain/Loss (Raw)": 2.145146608352661, "Pretrain/Step": 5396, "Pretrain/Step Time": 8.80404705926776} +{"Pretrain/Learning Rate": 2.089681534525086e-05, "Pretrain/Loss": 2.045170545578003, "Pretrain/Loss (Raw)": 1.9323053359985352, "Pretrain/Step": 5397, "Pretrain/Step Time": 8.802330687642097} +{"Pretrain/Learning Rate": 2.0888440838756515e-05, "Pretrain/Loss": 2.0458273887634277, "Pretrain/Loss (Raw)": 2.10040020942688, "Pretrain/Step": 5398, "Pretrain/Step Time": 8.80143653601408} +{"Pretrain/Learning Rate": 2.088006680642653e-05, "Pretrain/Loss": 2.045647621154785, "Pretrain/Loss (Raw)": 2.0457499027252197, "Pretrain/Step": 5399, "Pretrain/Step Time": 8.80638756789267} +{"Pretrain/Learning Rate": 2.087169324922667e-05, "Pretrain/Loss": 2.044496774673462, "Pretrain/Loss (Raw)": 2.0706021785736084, "Pretrain/Step": 5400, "Pretrain/Step Time": 8.797072852030396} +{"Pretrain/Learning Rate": 2.086332016812258e-05, "Pretrain/Loss": 2.043882369995117, "Pretrain/Loss (Raw)": 2.0259857177734375, "Pretrain/Step": 5401, "Pretrain/Step Time": 8.798157373443246} +{"Pretrain/Learning Rate": 2.085494756407992e-05, "Pretrain/Loss": 2.046287775039673, "Pretrain/Loss (Raw)": 2.3768746852874756, "Pretrain/Step": 5402, "Pretrain/Step Time": 8.8004489839077} +{"Pretrain/Learning Rate": 2.0846575438064227e-05, "Pretrain/Loss": 2.045112133026123, "Pretrain/Loss (Raw)": 2.071411609649658, "Pretrain/Step": 5403, "Pretrain/Step Time": 8.8041548486799} +{"Pretrain/Learning Rate": 2.0838203791041028e-05, "Pretrain/Loss": 2.0449163913726807, "Pretrain/Loss (Raw)": 2.035468101501465, "Pretrain/Step": 5404, "Pretrain/Step Time": 8.794726707041264} +{"Pretrain/Learning Rate": 2.0829832623975775e-05, "Pretrain/Loss": 2.0462377071380615, "Pretrain/Loss (Raw)": 2.1519181728363037, "Pretrain/Step": 5405, "Pretrain/Step Time": 8.7953638471663} +{"Pretrain/Learning Rate": 2.0821461937833884e-05, "Pretrain/Loss": 2.046535015106201, "Pretrain/Loss (Raw)": 2.1553685665130615, "Pretrain/Step": 5406, "Pretrain/Step Time": 8.794066775590181} +{"Pretrain/Learning Rate": 2.0813091733580685e-05, "Pretrain/Loss": 2.043924331665039, "Pretrain/Loss (Raw)": 1.8647691011428833, "Pretrain/Step": 5407, "Pretrain/Step Time": 8.797012142837048} +{"Pretrain/Learning Rate": 2.080472201218148e-05, "Pretrain/Loss": 2.0434255599975586, "Pretrain/Loss (Raw)": 1.7994613647460938, "Pretrain/Step": 5408, "Pretrain/Step Time": 8.794419534504414} +{"Pretrain/Learning Rate": 2.0796352774601495e-05, "Pretrain/Loss": 2.0430126190185547, "Pretrain/Loss (Raw)": 1.8946222066879272, "Pretrain/Step": 5409, "Pretrain/Step Time": 8.798738449811935} +{"Pretrain/Learning Rate": 2.0787984021805922e-05, "Pretrain/Loss": 2.042573928833008, "Pretrain/Loss (Raw)": 2.116811990737915, "Pretrain/Step": 5410, "Pretrain/Step Time": 8.801142420619726} +{"Pretrain/Learning Rate": 2.077961575475988e-05, "Pretrain/Loss": 2.0415570735931396, "Pretrain/Loss (Raw)": 2.009855270385742, "Pretrain/Step": 5411, "Pretrain/Step Time": 8.796780250966549} +{"Pretrain/Learning Rate": 2.0771247974428434e-05, "Pretrain/Loss": 2.0430827140808105, "Pretrain/Loss (Raw)": 2.129622459411621, "Pretrain/Step": 5412, "Pretrain/Step Time": 8.799136858433485} +{"Pretrain/Learning Rate": 2.07628806817766e-05, "Pretrain/Loss": 2.0433857440948486, "Pretrain/Loss (Raw)": 2.0894246101379395, "Pretrain/Step": 5413, "Pretrain/Step Time": 8.799093464389443} +{"Pretrain/Learning Rate": 2.0754513877769328e-05, "Pretrain/Loss": 2.042384624481201, "Pretrain/Loss (Raw)": 1.910446286201477, "Pretrain/Step": 5414, "Pretrain/Step Time": 8.799079969525337} +{"Pretrain/Learning Rate": 2.074614756337152e-05, "Pretrain/Loss": 2.040422201156616, "Pretrain/Loss (Raw)": 1.9087637662887573, "Pretrain/Step": 5415, "Pretrain/Step Time": 8.796549465507269} +{"Pretrain/Learning Rate": 2.073778173954803e-05, "Pretrain/Loss": 2.040238857269287, "Pretrain/Loss (Raw)": 1.898695945739746, "Pretrain/Step": 5416, "Pretrain/Step Time": 8.795659964904189} +{"Pretrain/Learning Rate": 2.072941640726362e-05, "Pretrain/Loss": 2.040184259414673, "Pretrain/Loss (Raw)": 2.0765511989593506, "Pretrain/Step": 5417, "Pretrain/Step Time": 8.809662440791726} +{"Pretrain/Learning Rate": 2.0721051567483045e-05, "Pretrain/Loss": 2.0478570461273193, "Pretrain/Loss (Raw)": 2.1516165733337402, "Pretrain/Step": 5418, "Pretrain/Step Time": 8.79824323579669} +{"Pretrain/Learning Rate": 2.071268722117096e-05, "Pretrain/Loss": 2.047550678253174, "Pretrain/Loss (Raw)": 2.049401044845581, "Pretrain/Step": 5419, "Pretrain/Step Time": 8.798474522307515} +{"Pretrain/Learning Rate": 2.0704323369291993e-05, "Pretrain/Loss": 2.049114227294922, "Pretrain/Loss (Raw)": 2.1903879642486572, "Pretrain/Step": 5420, "Pretrain/Step Time": 8.797230780124664} +{"Pretrain/Learning Rate": 2.069596001281069e-05, "Pretrain/Loss": 2.0510144233703613, "Pretrain/Loss (Raw)": 2.086780071258545, "Pretrain/Step": 5421, "Pretrain/Step Time": 8.795216053724289} +{"Pretrain/Learning Rate": 2.0687597152691567e-05, "Pretrain/Loss": 2.050611734390259, "Pretrain/Loss (Raw)": 2.1367666721343994, "Pretrain/Step": 5422, "Pretrain/Step Time": 8.797619329765439} +{"Pretrain/Learning Rate": 2.0679234789899054e-05, "Pretrain/Loss": 2.0513768196105957, "Pretrain/Loss (Raw)": 2.146345615386963, "Pretrain/Step": 5423, "Pretrain/Step Time": 8.794962650164962} +{"Pretrain/Learning Rate": 2.067087292539755e-05, "Pretrain/Loss": 2.0533502101898193, "Pretrain/Loss (Raw)": 2.064894437789917, "Pretrain/Step": 5424, "Pretrain/Step Time": 8.797208704054356} +{"Pretrain/Learning Rate": 2.0662511560151373e-05, "Pretrain/Loss": 2.052107572555542, "Pretrain/Loss (Raw)": 2.0151405334472656, "Pretrain/Step": 5425, "Pretrain/Step Time": 8.792334351688623} +{"Pretrain/Learning Rate": 2.0654150695124804e-05, "Pretrain/Loss": 2.051668643951416, "Pretrain/Loss (Raw)": 1.968174695968628, "Pretrain/Step": 5426, "Pretrain/Step Time": 8.792625285685062} +{"Pretrain/Learning Rate": 2.064579033128206e-05, "Pretrain/Loss": 2.0513381958007812, "Pretrain/Loss (Raw)": 1.9752893447875977, "Pretrain/Step": 5427, "Pretrain/Step Time": 8.788683345541358} +{"Pretrain/Learning Rate": 2.063743046958729e-05, "Pretrain/Loss": 2.0505757331848145, "Pretrain/Loss (Raw)": 1.841782569885254, "Pretrain/Step": 5428, "Pretrain/Step Time": 8.785178003832698} +{"Pretrain/Learning Rate": 2.0629071111004595e-05, "Pretrain/Loss": 2.050675868988037, "Pretrain/Loss (Raw)": 2.0657310485839844, "Pretrain/Step": 5429, "Pretrain/Step Time": 8.788177443668246} +{"Pretrain/Learning Rate": 2.0620712256498016e-05, "Pretrain/Loss": 2.0483596324920654, "Pretrain/Loss (Raw)": 1.9986850023269653, "Pretrain/Step": 5430, "Pretrain/Step Time": 8.782017657533288} +{"Pretrain/Learning Rate": 2.061235390703154e-05, "Pretrain/Loss": 2.049488067626953, "Pretrain/Loss (Raw)": 2.3549671173095703, "Pretrain/Step": 5431, "Pretrain/Step Time": 8.781014334410429} +{"Pretrain/Learning Rate": 2.0603996063569078e-05, "Pretrain/Loss": 2.0505471229553223, "Pretrain/Loss (Raw)": 1.913387417793274, "Pretrain/Step": 5432, "Pretrain/Step Time": 8.784382905811071} +{"Pretrain/Learning Rate": 2.0595638727074512e-05, "Pretrain/Loss": 2.0510854721069336, "Pretrain/Loss (Raw)": 2.0934982299804688, "Pretrain/Step": 5433, "Pretrain/Step Time": 8.783320724964142} +{"Pretrain/Learning Rate": 2.058728189851164e-05, "Pretrain/Loss": 2.0497498512268066, "Pretrain/Loss (Raw)": 1.9629021883010864, "Pretrain/Step": 5434, "Pretrain/Step Time": 8.782416455447674} +{"Pretrain/Learning Rate": 2.0578925578844216e-05, "Pretrain/Loss": 2.0501370429992676, "Pretrain/Loss (Raw)": 1.9316387176513672, "Pretrain/Step": 5435, "Pretrain/Step Time": 8.78593179769814} +{"Pretrain/Learning Rate": 2.0570569769035915e-05, "Pretrain/Loss": 2.049489974975586, "Pretrain/Loss (Raw)": 1.9579975605010986, "Pretrain/Step": 5436, "Pretrain/Step Time": 8.784427797421813} +{"Pretrain/Learning Rate": 2.0562214470050396e-05, "Pretrain/Loss": 2.0489919185638428, "Pretrain/Loss (Raw)": 2.1462883949279785, "Pretrain/Step": 5437, "Pretrain/Step Time": 8.784559512510896} +{"Pretrain/Learning Rate": 2.0553859682851204e-05, "Pretrain/Loss": 2.047441005706787, "Pretrain/Loss (Raw)": 1.823906660079956, "Pretrain/Step": 5438, "Pretrain/Step Time": 8.78243045322597} +{"Pretrain/Learning Rate": 2.0545505408401878e-05, "Pretrain/Loss": 2.044959545135498, "Pretrain/Loss (Raw)": 1.7445405721664429, "Pretrain/Step": 5439, "Pretrain/Step Time": 8.79423832334578} +{"Pretrain/Learning Rate": 2.053715164766584e-05, "Pretrain/Loss": 2.043945550918579, "Pretrain/Loss (Raw)": 1.8802759647369385, "Pretrain/Step": 5440, "Pretrain/Step Time": 8.792985146865249} +{"Pretrain/Learning Rate": 2.052879840160652e-05, "Pretrain/Loss": 2.043351173400879, "Pretrain/Loss (Raw)": 2.1060314178466797, "Pretrain/Step": 5441, "Pretrain/Step Time": 8.792311346158385} +{"Pretrain/Learning Rate": 2.052044567118722e-05, "Pretrain/Loss": 2.0438334941864014, "Pretrain/Loss (Raw)": 2.1637134552001953, "Pretrain/Step": 5442, "Pretrain/Step Time": 8.795952463522553} +{"Pretrain/Learning Rate": 2.0512093457371253e-05, "Pretrain/Loss": 2.0400428771972656, "Pretrain/Loss (Raw)": 1.6545618772506714, "Pretrain/Step": 5443, "Pretrain/Step Time": 8.796014754101634} +{"Pretrain/Learning Rate": 2.0503741761121804e-05, "Pretrain/Loss": 2.0401086807250977, "Pretrain/Loss (Raw)": 2.0004518032073975, "Pretrain/Step": 5444, "Pretrain/Step Time": 8.795119807124138} +{"Pretrain/Learning Rate": 2.049539058340205e-05, "Pretrain/Loss": 2.039982318878174, "Pretrain/Loss (Raw)": 1.974198579788208, "Pretrain/Step": 5445, "Pretrain/Step Time": 8.79334631189704} +{"Pretrain/Learning Rate": 2.0487039925175073e-05, "Pretrain/Loss": 2.0387449264526367, "Pretrain/Loss (Raw)": 1.894734501838684, "Pretrain/Step": 5446, "Pretrain/Step Time": 8.803346985951066} +{"Pretrain/Learning Rate": 2.0478689787403923e-05, "Pretrain/Loss": 2.03924560546875, "Pretrain/Loss (Raw)": 2.0980145931243896, "Pretrain/Step": 5447, "Pretrain/Step Time": 8.804118489846587} +{"Pretrain/Learning Rate": 2.0470340171051567e-05, "Pretrain/Loss": 2.0399529933929443, "Pretrain/Loss (Raw)": 2.1710262298583984, "Pretrain/Step": 5448, "Pretrain/Step Time": 8.79950487986207} +{"Pretrain/Learning Rate": 2.046199107708093e-05, "Pretrain/Loss": 2.0399136543273926, "Pretrain/Loss (Raw)": 2.131957530975342, "Pretrain/Step": 5449, "Pretrain/Step Time": 8.800774620845914} +{"Pretrain/Learning Rate": 2.0453642506454862e-05, "Pretrain/Loss": 2.040569305419922, "Pretrain/Loss (Raw)": 2.0343470573425293, "Pretrain/Step": 5450, "Pretrain/Step Time": 8.810088811442256} +{"Pretrain/Learning Rate": 2.044529446013617e-05, "Pretrain/Loss": 2.037909507751465, "Pretrain/Loss (Raw)": 1.9119700193405151, "Pretrain/Step": 5451, "Pretrain/Step Time": 8.808912361040711} +{"Pretrain/Learning Rate": 2.0436946939087576e-05, "Pretrain/Loss": 2.0365140438079834, "Pretrain/Loss (Raw)": 1.8987913131713867, "Pretrain/Step": 5452, "Pretrain/Step Time": 8.79947018623352} +{"Pretrain/Learning Rate": 2.042859994427177e-05, "Pretrain/Loss": 2.0375027656555176, "Pretrain/Loss (Raw)": 2.0389904975891113, "Pretrain/Step": 5453, "Pretrain/Step Time": 8.802941784262657} +{"Pretrain/Learning Rate": 2.042025347665135e-05, "Pretrain/Loss": 2.0392017364501953, "Pretrain/Loss (Raw)": 2.050060749053955, "Pretrain/Step": 5454, "Pretrain/Step Time": 8.799816461279988} +{"Pretrain/Learning Rate": 2.041190753718889e-05, "Pretrain/Loss": 2.040602684020996, "Pretrain/Loss (Raw)": 2.1957123279571533, "Pretrain/Step": 5455, "Pretrain/Step Time": 8.800844959914684} +{"Pretrain/Learning Rate": 2.0403562126846865e-05, "Pretrain/Loss": 2.040738105773926, "Pretrain/Loss (Raw)": 1.969130516052246, "Pretrain/Step": 5456, "Pretrain/Step Time": 8.805851951241493} +{"Pretrain/Learning Rate": 2.039521724658772e-05, "Pretrain/Loss": 2.0419936180114746, "Pretrain/Loss (Raw)": 2.1391329765319824, "Pretrain/Step": 5457, "Pretrain/Step Time": 8.809489691630006} +{"Pretrain/Learning Rate": 2.0386872897373816e-05, "Pretrain/Loss": 2.04331111907959, "Pretrain/Loss (Raw)": 2.108832597732544, "Pretrain/Step": 5458, "Pretrain/Step Time": 8.807805061340332} +{"Pretrain/Learning Rate": 2.037852908016747e-05, "Pretrain/Loss": 2.0412416458129883, "Pretrain/Loss (Raw)": 1.8589656352996826, "Pretrain/Step": 5459, "Pretrain/Step Time": 8.805277835577726} +{"Pretrain/Learning Rate": 2.0370185795930927e-05, "Pretrain/Loss": 2.0427072048187256, "Pretrain/Loss (Raw)": 2.2366721630096436, "Pretrain/Step": 5460, "Pretrain/Step Time": 8.80617867410183} +{"Pretrain/Learning Rate": 2.0361843045626378e-05, "Pretrain/Loss": 2.041968584060669, "Pretrain/Loss (Raw)": 2.016090154647827, "Pretrain/Step": 5461, "Pretrain/Step Time": 8.80470011383295} +{"Pretrain/Learning Rate": 2.035350083021594e-05, "Pretrain/Loss": 2.043806552886963, "Pretrain/Loss (Raw)": 2.284257173538208, "Pretrain/Step": 5462, "Pretrain/Step Time": 8.806853823363781} +{"Pretrain/Learning Rate": 2.0345159150661683e-05, "Pretrain/Loss": 2.042072296142578, "Pretrain/Loss (Raw)": 1.8262717723846436, "Pretrain/Step": 5463, "Pretrain/Step Time": 8.80746146850288} +{"Pretrain/Learning Rate": 2.0336818007925603e-05, "Pretrain/Loss": 2.0441150665283203, "Pretrain/Loss (Raw)": 2.089202404022217, "Pretrain/Step": 5464, "Pretrain/Step Time": 8.801497392356396} +{"Pretrain/Learning Rate": 2.032847740296965e-05, "Pretrain/Loss": 2.045759439468384, "Pretrain/Loss (Raw)": 2.3171513080596924, "Pretrain/Step": 5465, "Pretrain/Step Time": 8.802154049277306} +{"Pretrain/Learning Rate": 2.0320137336755692e-05, "Pretrain/Loss": 2.04599928855896, "Pretrain/Loss (Raw)": 2.0438060760498047, "Pretrain/Step": 5466, "Pretrain/Step Time": 8.80359560996294} +{"Pretrain/Learning Rate": 2.0311797810245543e-05, "Pretrain/Loss": 2.0461249351501465, "Pretrain/Loss (Raw)": 2.018160820007324, "Pretrain/Step": 5467, "Pretrain/Step Time": 8.796508263796568} +{"Pretrain/Learning Rate": 2.0303458824400974e-05, "Pretrain/Loss": 2.045017719268799, "Pretrain/Loss (Raw)": 2.0542550086975098, "Pretrain/Step": 5468, "Pretrain/Step Time": 8.79551798850298} +{"Pretrain/Learning Rate": 2.0295120380183657e-05, "Pretrain/Loss": 2.0438733100891113, "Pretrain/Loss (Raw)": 1.947567343711853, "Pretrain/Step": 5469, "Pretrain/Step Time": 8.798950392752886} +{"Pretrain/Learning Rate": 2.0286782478555232e-05, "Pretrain/Loss": 2.044217348098755, "Pretrain/Loss (Raw)": 2.086160898208618, "Pretrain/Step": 5470, "Pretrain/Step Time": 8.796234086155891} +{"Pretrain/Learning Rate": 2.027844512047726e-05, "Pretrain/Loss": 2.0417633056640625, "Pretrain/Loss (Raw)": 1.9563261270523071, "Pretrain/Step": 5471, "Pretrain/Step Time": 8.797406863421202} +{"Pretrain/Learning Rate": 2.027010830691124e-05, "Pretrain/Loss": 2.0449180603027344, "Pretrain/Loss (Raw)": 2.2337100505828857, "Pretrain/Step": 5472, "Pretrain/Step Time": 8.800401018932462} +{"Pretrain/Learning Rate": 2.0261772038818622e-05, "Pretrain/Loss": 2.0423669815063477, "Pretrain/Loss (Raw)": 1.9457229375839233, "Pretrain/Step": 5473, "Pretrain/Step Time": 8.802023086696863} +{"Pretrain/Learning Rate": 2.0253436317160784e-05, "Pretrain/Loss": 2.042109966278076, "Pretrain/Loss (Raw)": 1.965475082397461, "Pretrain/Step": 5474, "Pretrain/Step Time": 8.806737808510661} +{"Pretrain/Learning Rate": 2.0245101142899032e-05, "Pretrain/Loss": 2.042423725128174, "Pretrain/Loss (Raw)": 2.0488932132720947, "Pretrain/Step": 5475, "Pretrain/Step Time": 8.797996431589127} +{"Pretrain/Learning Rate": 2.0236766516994623e-05, "Pretrain/Loss": 2.042475700378418, "Pretrain/Loss (Raw)": 2.10300874710083, "Pretrain/Step": 5476, "Pretrain/Step Time": 8.797722591087222} +{"Pretrain/Learning Rate": 2.022843244040874e-05, "Pretrain/Loss": 2.0423569679260254, "Pretrain/Loss (Raw)": 2.064518928527832, "Pretrain/Step": 5477, "Pretrain/Step Time": 8.801339644938707} +{"Pretrain/Learning Rate": 2.0220098914102525e-05, "Pretrain/Loss": 2.0418436527252197, "Pretrain/Loss (Raw)": 2.0285565853118896, "Pretrain/Step": 5478, "Pretrain/Step Time": 8.799251176416874} +{"Pretrain/Learning Rate": 2.021176593903701e-05, "Pretrain/Loss": 2.039823055267334, "Pretrain/Loss (Raw)": 1.814039945602417, "Pretrain/Step": 5479, "Pretrain/Step Time": 8.802518518641591} +{"Pretrain/Learning Rate": 2.0203433516173225e-05, "Pretrain/Loss": 2.039607524871826, "Pretrain/Loss (Raw)": 2.164052724838257, "Pretrain/Step": 5480, "Pretrain/Step Time": 8.799980621784925} +{"Pretrain/Learning Rate": 2.0195101646472075e-05, "Pretrain/Loss": 2.0400400161743164, "Pretrain/Loss (Raw)": 2.0923752784729004, "Pretrain/Step": 5481, "Pretrain/Step Time": 8.802762685343623} +{"Pretrain/Learning Rate": 2.018677033089446e-05, "Pretrain/Loss": 2.0408682823181152, "Pretrain/Loss (Raw)": 2.1464178562164307, "Pretrain/Step": 5482, "Pretrain/Step Time": 8.799590468406677} +{"Pretrain/Learning Rate": 2.017843957040115e-05, "Pretrain/Loss": 2.042786121368408, "Pretrain/Loss (Raw)": 2.2109134197235107, "Pretrain/Step": 5483, "Pretrain/Step Time": 8.80296109803021} +{"Pretrain/Learning Rate": 2.0170109365952934e-05, "Pretrain/Loss": 2.0413260459899902, "Pretrain/Loss (Raw)": 2.0015785694122314, "Pretrain/Step": 5484, "Pretrain/Step Time": 8.802906572818756} +{"Pretrain/Learning Rate": 2.0161779718510443e-05, "Pretrain/Loss": 2.0397913455963135, "Pretrain/Loss (Raw)": 1.9786063432693481, "Pretrain/Step": 5485, "Pretrain/Step Time": 8.797715652734041} +{"Pretrain/Learning Rate": 2.015345062903433e-05, "Pretrain/Loss": 2.042876958847046, "Pretrain/Loss (Raw)": 2.108254909515381, "Pretrain/Step": 5486, "Pretrain/Step Time": 8.799189509823918} +{"Pretrain/Learning Rate": 2.014512209848512e-05, "Pretrain/Loss": 2.0420169830322266, "Pretrain/Loss (Raw)": 1.8873473405838013, "Pretrain/Step": 5487, "Pretrain/Step Time": 8.797700865194201} +{"Pretrain/Learning Rate": 2.013679412782331e-05, "Pretrain/Loss": 2.0410149097442627, "Pretrain/Loss (Raw)": 2.028709650039673, "Pretrain/Step": 5488, "Pretrain/Step Time": 8.800603033974767} +{"Pretrain/Learning Rate": 2.0128466718009313e-05, "Pretrain/Loss": 2.0418150424957275, "Pretrain/Loss (Raw)": 2.1186420917510986, "Pretrain/Step": 5489, "Pretrain/Step Time": 8.799047304317355} +{"Pretrain/Learning Rate": 2.0120139870003492e-05, "Pretrain/Loss": 2.041888475418091, "Pretrain/Loss (Raw)": 2.188804864883423, "Pretrain/Step": 5490, "Pretrain/Step Time": 8.803037913516164} +{"Pretrain/Learning Rate": 2.0111813584766134e-05, "Pretrain/Loss": 2.039809465408325, "Pretrain/Loss (Raw)": 1.7433662414550781, "Pretrain/Step": 5491, "Pretrain/Step Time": 8.80034606717527} +{"Pretrain/Learning Rate": 2.010348786325747e-05, "Pretrain/Loss": 2.0400962829589844, "Pretrain/Loss (Raw)": 2.0953469276428223, "Pretrain/Step": 5492, "Pretrain/Step Time": 8.807256983593106} +{"Pretrain/Learning Rate": 2.0095162706437655e-05, "Pretrain/Loss": 2.039034128189087, "Pretrain/Loss (Raw)": 1.9092531204223633, "Pretrain/Step": 5493, "Pretrain/Step Time": 8.806933837011456} +{"Pretrain/Learning Rate": 2.0086838115266794e-05, "Pretrain/Loss": 2.0383079051971436, "Pretrain/Loss (Raw)": 2.129591703414917, "Pretrain/Step": 5494, "Pretrain/Step Time": 8.807331746444106} +{"Pretrain/Learning Rate": 2.007851409070491e-05, "Pretrain/Loss": 2.0377373695373535, "Pretrain/Loss (Raw)": 2.084303617477417, "Pretrain/Step": 5495, "Pretrain/Step Time": 8.817653281614184} +{"Pretrain/Learning Rate": 2.007019063371197e-05, "Pretrain/Loss": 2.038721799850464, "Pretrain/Loss (Raw)": 2.071751117706299, "Pretrain/Step": 5496, "Pretrain/Step Time": 8.808926021680236} +{"Pretrain/Learning Rate": 2.006186774524788e-05, "Pretrain/Loss": 2.039076089859009, "Pretrain/Loss (Raw)": 2.1487157344818115, "Pretrain/Step": 5497, "Pretrain/Step Time": 8.80939363501966} +{"Pretrain/Learning Rate": 2.005354542627247e-05, "Pretrain/Loss": 2.0398240089416504, "Pretrain/Loss (Raw)": 2.103738307952881, "Pretrain/Step": 5498, "Pretrain/Step Time": 8.810271333903074} +{"Pretrain/Learning Rate": 2.0045223677745507e-05, "Pretrain/Loss": 2.039226531982422, "Pretrain/Loss (Raw)": 2.056896924972534, "Pretrain/Step": 5499, "Pretrain/Step Time": 8.815125754103065} +{"Pretrain/Learning Rate": 2.0036902500626704e-05, "Pretrain/Loss": 2.039165735244751, "Pretrain/Loss (Raw)": 2.1113593578338623, "Pretrain/Step": 5500, "Pretrain/Step Time": 8.807980997487903} +{"Pretrain/Learning Rate": 2.002858189587568e-05, "Pretrain/Loss": 2.0401828289031982, "Pretrain/Loss (Raw)": 2.0962653160095215, "Pretrain/Step": 5501, "Pretrain/Step Time": 8.807609366253018} +{"Pretrain/Learning Rate": 2.002026186445203e-05, "Pretrain/Loss": 2.0410470962524414, "Pretrain/Loss (Raw)": 1.9959748983383179, "Pretrain/Step": 5502, "Pretrain/Step Time": 8.814452715218067} +{"Pretrain/Learning Rate": 2.0011942407315236e-05, "Pretrain/Loss": 2.0408935546875, "Pretrain/Loss (Raw)": 1.85565984249115, "Pretrain/Step": 5503, "Pretrain/Step Time": 8.813027264550328} +{"Pretrain/Learning Rate": 2.0003623525424758e-05, "Pretrain/Loss": 2.039417266845703, "Pretrain/Loss (Raw)": 1.9706230163574219, "Pretrain/Step": 5504, "Pretrain/Step Time": 8.806456429883838} +{"Pretrain/Learning Rate": 1.9995305219739952e-05, "Pretrain/Loss": 2.0433316230773926, "Pretrain/Loss (Raw)": 2.2218761444091797, "Pretrain/Step": 5505, "Pretrain/Step Time": 8.806905414909124} +{"Pretrain/Learning Rate": 1.9986987491220137e-05, "Pretrain/Loss": 2.043856143951416, "Pretrain/Loss (Raw)": 2.1477534770965576, "Pretrain/Step": 5506, "Pretrain/Step Time": 8.805896814912558} +{"Pretrain/Learning Rate": 1.997867034082454e-05, "Pretrain/Loss": 2.0447912216186523, "Pretrain/Loss (Raw)": 2.0325989723205566, "Pretrain/Step": 5507, "Pretrain/Step Time": 8.798892434686422} +{"Pretrain/Learning Rate": 1.997035376951234e-05, "Pretrain/Loss": 2.045353412628174, "Pretrain/Loss (Raw)": 2.128594398498535, "Pretrain/Step": 5508, "Pretrain/Step Time": 8.800149012356997} +{"Pretrain/Learning Rate": 1.996203777824265e-05, "Pretrain/Loss": 2.0448760986328125, "Pretrain/Loss (Raw)": 2.226761817932129, "Pretrain/Step": 5509, "Pretrain/Step Time": 8.802160726860166} +{"Pretrain/Learning Rate": 1.99537223679745e-05, "Pretrain/Loss": 2.043950080871582, "Pretrain/Loss (Raw)": 1.788487195968628, "Pretrain/Step": 5510, "Pretrain/Step Time": 8.805739222094417} +{"Pretrain/Learning Rate": 1.994540753966687e-05, "Pretrain/Loss": 2.0457589626312256, "Pretrain/Loss (Raw)": 2.2076761722564697, "Pretrain/Step": 5511, "Pretrain/Step Time": 8.80058429390192} +{"Pretrain/Learning Rate": 1.9937093294278653e-05, "Pretrain/Loss": 2.046299695968628, "Pretrain/Loss (Raw)": 2.0104451179504395, "Pretrain/Step": 5512, "Pretrain/Step Time": 8.800878750160336} +{"Pretrain/Learning Rate": 1.99287796327687e-05, "Pretrain/Loss": 2.0461244583129883, "Pretrain/Loss (Raw)": 2.166886329650879, "Pretrain/Step": 5513, "Pretrain/Step Time": 8.80674234032631} +{"Pretrain/Learning Rate": 1.9920466556095772e-05, "Pretrain/Loss": 2.046985149383545, "Pretrain/Loss (Raw)": 2.0698888301849365, "Pretrain/Step": 5514, "Pretrain/Step Time": 8.801160207018256} +{"Pretrain/Learning Rate": 1.991215406521858e-05, "Pretrain/Loss": 2.046617269515991, "Pretrain/Loss (Raw)": 1.989499568939209, "Pretrain/Step": 5515, "Pretrain/Step Time": 8.802925705909729} +{"Pretrain/Learning Rate": 1.9903842161095752e-05, "Pretrain/Loss": 2.0463290214538574, "Pretrain/Loss (Raw)": 2.1311111450195312, "Pretrain/Step": 5516, "Pretrain/Step Time": 8.804664181545377} +{"Pretrain/Learning Rate": 1.9895530844685865e-05, "Pretrain/Loss": 2.0460727214813232, "Pretrain/Loss (Raw)": 1.991478681564331, "Pretrain/Step": 5517, "Pretrain/Step Time": 8.80228172801435} +{"Pretrain/Learning Rate": 1.988722011694741e-05, "Pretrain/Loss": 2.0427494049072266, "Pretrain/Loss (Raw)": 1.8734909296035767, "Pretrain/Step": 5518, "Pretrain/Step Time": 8.803638005629182} +{"Pretrain/Learning Rate": 1.987890997883883e-05, "Pretrain/Loss": 2.0430331230163574, "Pretrain/Loss (Raw)": 2.0158445835113525, "Pretrain/Step": 5519, "Pretrain/Step Time": 8.80468318797648} +{"Pretrain/Learning Rate": 1.987060043131847e-05, "Pretrain/Loss": 2.045271635055542, "Pretrain/Loss (Raw)": 2.1867640018463135, "Pretrain/Step": 5520, "Pretrain/Step Time": 8.799641976132989} +{"Pretrain/Learning Rate": 1.9862291475344654e-05, "Pretrain/Loss": 2.043807029724121, "Pretrain/Loss (Raw)": 1.938096523284912, "Pretrain/Step": 5521, "Pretrain/Step Time": 8.80569827184081} +{"Pretrain/Learning Rate": 1.985398311187558e-05, "Pretrain/Loss": 2.0432848930358887, "Pretrain/Loss (Raw)": 2.067678928375244, "Pretrain/Step": 5522, "Pretrain/Step Time": 8.806353641673923} +{"Pretrain/Learning Rate": 1.9845675341869437e-05, "Pretrain/Loss": 2.040351152420044, "Pretrain/Loss (Raw)": 1.8803435564041138, "Pretrain/Step": 5523, "Pretrain/Step Time": 8.800176976248622} +{"Pretrain/Learning Rate": 1.9837368166284284e-05, "Pretrain/Loss": 2.0389275550842285, "Pretrain/Loss (Raw)": 1.9629231691360474, "Pretrain/Step": 5524, "Pretrain/Step Time": 8.801801731809974} +{"Pretrain/Learning Rate": 1.982906158607818e-05, "Pretrain/Loss": 2.0405330657958984, "Pretrain/Loss (Raw)": 2.1377925872802734, "Pretrain/Step": 5525, "Pretrain/Step Time": 8.803569046780467} +{"Pretrain/Learning Rate": 1.982075560220904e-05, "Pretrain/Loss": 2.0387072563171387, "Pretrain/Loss (Raw)": 1.8667073249816895, "Pretrain/Step": 5526, "Pretrain/Step Time": 8.80476121045649} +{"Pretrain/Learning Rate": 1.981245021563479e-05, "Pretrain/Loss": 2.039377450942993, "Pretrain/Loss (Raw)": 2.131538152694702, "Pretrain/Step": 5527, "Pretrain/Step Time": 8.804209714755416} +{"Pretrain/Learning Rate": 1.9804145427313213e-05, "Pretrain/Loss": 2.0392391681671143, "Pretrain/Loss (Raw)": 2.052910804748535, "Pretrain/Step": 5528, "Pretrain/Step Time": 8.805116567760706} +{"Pretrain/Learning Rate": 1.9795841238202077e-05, "Pretrain/Loss": 2.041463851928711, "Pretrain/Loss (Raw)": 2.310743808746338, "Pretrain/Step": 5529, "Pretrain/Step Time": 8.800492033362389} +{"Pretrain/Learning Rate": 1.9787537649259043e-05, "Pretrain/Loss": 2.038814067840576, "Pretrain/Loss (Raw)": 2.0376970767974854, "Pretrain/Step": 5530, "Pretrain/Step Time": 8.800449404865503} +{"Pretrain/Learning Rate": 1.977923466144174e-05, "Pretrain/Loss": 2.0383236408233643, "Pretrain/Loss (Raw)": 2.008634090423584, "Pretrain/Step": 5531, "Pretrain/Step Time": 8.798607749864459} +{"Pretrain/Learning Rate": 1.977093227570768e-05, "Pretrain/Loss": 2.038706064224243, "Pretrain/Loss (Raw)": 2.0844008922576904, "Pretrain/Step": 5532, "Pretrain/Step Time": 8.802601916715503} +{"Pretrain/Learning Rate": 1.9762630493014366e-05, "Pretrain/Loss": 2.036850929260254, "Pretrain/Loss (Raw)": 1.9144673347473145, "Pretrain/Step": 5533, "Pretrain/Step Time": 8.802104491740465} +{"Pretrain/Learning Rate": 1.9754329314319176e-05, "Pretrain/Loss": 2.0371053218841553, "Pretrain/Loss (Raw)": 2.187944173812866, "Pretrain/Step": 5534, "Pretrain/Step Time": 8.799420714378357} +{"Pretrain/Learning Rate": 1.974602874057945e-05, "Pretrain/Loss": 2.038252830505371, "Pretrain/Loss (Raw)": 2.011669397354126, "Pretrain/Step": 5535, "Pretrain/Step Time": 8.805164663121104} +{"Pretrain/Learning Rate": 1.9737728772752446e-05, "Pretrain/Loss": 2.039553642272949, "Pretrain/Loss (Raw)": 1.965929388999939, "Pretrain/Step": 5536, "Pretrain/Step Time": 8.80449995957315} +{"Pretrain/Learning Rate": 1.9729429411795358e-05, "Pretrain/Loss": 2.040497064590454, "Pretrain/Loss (Raw)": 2.015410900115967, "Pretrain/Step": 5537, "Pretrain/Step Time": 8.799989750608802} +{"Pretrain/Learning Rate": 1.97211306586653e-05, "Pretrain/Loss": 2.0374069213867188, "Pretrain/Loss (Raw)": 1.7212885618209839, "Pretrain/Step": 5538, "Pretrain/Step Time": 8.800808154046535} +{"Pretrain/Learning Rate": 1.971283251431934e-05, "Pretrain/Loss": 2.038691997528076, "Pretrain/Loss (Raw)": 2.174325466156006, "Pretrain/Step": 5539, "Pretrain/Step Time": 8.793776776641607} +{"Pretrain/Learning Rate": 1.970453497971444e-05, "Pretrain/Loss": 2.038918972015381, "Pretrain/Loss (Raw)": 2.1586410999298096, "Pretrain/Step": 5540, "Pretrain/Step Time": 8.798082197085023} +{"Pretrain/Learning Rate": 1.969623805580752e-05, "Pretrain/Loss": 2.038417339324951, "Pretrain/Loss (Raw)": 2.0252492427825928, "Pretrain/Step": 5541, "Pretrain/Step Time": 8.803199546411633} +{"Pretrain/Learning Rate": 1.9687941743555422e-05, "Pretrain/Loss": 2.0399153232574463, "Pretrain/Loss (Raw)": 2.1021673679351807, "Pretrain/Step": 5542, "Pretrain/Step Time": 8.803022217005491} +{"Pretrain/Learning Rate": 1.9679646043914914e-05, "Pretrain/Loss": 2.0418410301208496, "Pretrain/Loss (Raw)": 2.1552517414093018, "Pretrain/Step": 5543, "Pretrain/Step Time": 8.800642058253288} +{"Pretrain/Learning Rate": 1.967135095784269e-05, "Pretrain/Loss": 2.04109787940979, "Pretrain/Loss (Raw)": 1.8035799264907837, "Pretrain/Step": 5544, "Pretrain/Step Time": 8.802197154611349} +{"Pretrain/Learning Rate": 1.966305648629539e-05, "Pretrain/Loss": 2.040600061416626, "Pretrain/Loss (Raw)": 2.0128262042999268, "Pretrain/Step": 5545, "Pretrain/Step Time": 8.795420115813613} +{"Pretrain/Learning Rate": 1.9654762630229558e-05, "Pretrain/Loss": 2.0400307178497314, "Pretrain/Loss (Raw)": 2.078754186630249, "Pretrain/Step": 5546, "Pretrain/Step Time": 8.79327899031341} +{"Pretrain/Learning Rate": 1.9646469390601692e-05, "Pretrain/Loss": 2.040792942047119, "Pretrain/Loss (Raw)": 2.1469509601593018, "Pretrain/Step": 5547, "Pretrain/Step Time": 8.79461114294827} +{"Pretrain/Learning Rate": 1.96381767683682e-05, "Pretrain/Loss": 2.0398740768432617, "Pretrain/Loss (Raw)": 2.072796106338501, "Pretrain/Step": 5548, "Pretrain/Step Time": 8.794826624915004} +{"Pretrain/Learning Rate": 1.9629884764485422e-05, "Pretrain/Loss": 2.0398435592651367, "Pretrain/Loss (Raw)": 2.08286452293396, "Pretrain/Step": 5549, "Pretrain/Step Time": 8.801967399194837} +{"Pretrain/Learning Rate": 1.962159337990965e-05, "Pretrain/Loss": 2.039572238922119, "Pretrain/Loss (Raw)": 2.1020407676696777, "Pretrain/Step": 5550, "Pretrain/Step Time": 8.799494301900268} +{"Pretrain/Learning Rate": 1.9613302615597064e-05, "Pretrain/Loss": 2.0380640029907227, "Pretrain/Loss (Raw)": 1.9532811641693115, "Pretrain/Step": 5551, "Pretrain/Step Time": 8.803091855719686} +{"Pretrain/Learning Rate": 1.960501247250381e-05, "Pretrain/Loss": 2.035120964050293, "Pretrain/Loss (Raw)": 1.6881957054138184, "Pretrain/Step": 5552, "Pretrain/Step Time": 8.805455058813095} +{"Pretrain/Learning Rate": 1.9596722951585936e-05, "Pretrain/Loss": 2.0343475341796875, "Pretrain/Loss (Raw)": 1.9161579608917236, "Pretrain/Step": 5553, "Pretrain/Step Time": 8.805216362699866} +{"Pretrain/Learning Rate": 1.9588434053799437e-05, "Pretrain/Loss": 2.0349135398864746, "Pretrain/Loss (Raw)": 2.0405986309051514, "Pretrain/Step": 5554, "Pretrain/Step Time": 8.80628945492208} +{"Pretrain/Learning Rate": 1.9580145780100216e-05, "Pretrain/Loss": 2.034250020980835, "Pretrain/Loss (Raw)": 1.8903529644012451, "Pretrain/Step": 5555, "Pretrain/Step Time": 8.805513076484203} +{"Pretrain/Learning Rate": 1.9571858131444128e-05, "Pretrain/Loss": 2.039130210876465, "Pretrain/Loss (Raw)": 2.466434955596924, "Pretrain/Step": 5556, "Pretrain/Step Time": 8.805052453652024} +{"Pretrain/Learning Rate": 1.9563571108786936e-05, "Pretrain/Loss": 2.0390443801879883, "Pretrain/Loss (Raw)": 2.0547995567321777, "Pretrain/Step": 5557, "Pretrain/Step Time": 8.802840411663055} +{"Pretrain/Learning Rate": 1.9555284713084345e-05, "Pretrain/Loss": 2.0381431579589844, "Pretrain/Loss (Raw)": 1.8832694292068481, "Pretrain/Step": 5558, "Pretrain/Step Time": 8.808232225477695} +{"Pretrain/Learning Rate": 1.954699894529197e-05, "Pretrain/Loss": 2.0365800857543945, "Pretrain/Loss (Raw)": 2.154893398284912, "Pretrain/Step": 5559, "Pretrain/Step Time": 8.808945378288627} +{"Pretrain/Learning Rate": 1.953871380636538e-05, "Pretrain/Loss": 2.039437770843506, "Pretrain/Loss (Raw)": 2.279209852218628, "Pretrain/Step": 5560, "Pretrain/Step Time": 8.80077420733869} +{"Pretrain/Learning Rate": 1.953042929726004e-05, "Pretrain/Loss": 2.04024600982666, "Pretrain/Loss (Raw)": 2.1969351768493652, "Pretrain/Step": 5561, "Pretrain/Step Time": 8.801437499001622} +{"Pretrain/Learning Rate": 1.952214541893138e-05, "Pretrain/Loss": 2.0408129692077637, "Pretrain/Loss (Raw)": 2.0354626178741455, "Pretrain/Step": 5562, "Pretrain/Step Time": 8.806789798662066} +{"Pretrain/Learning Rate": 1.9513862172334707e-05, "Pretrain/Loss": 2.0394115447998047, "Pretrain/Loss (Raw)": 1.752252221107483, "Pretrain/Step": 5563, "Pretrain/Step Time": 8.801759447902441} +{"Pretrain/Learning Rate": 1.9505579558425313e-05, "Pretrain/Loss": 2.040926218032837, "Pretrain/Loss (Raw)": 2.1519076824188232, "Pretrain/Step": 5564, "Pretrain/Step Time": 8.80142142996192} +{"Pretrain/Learning Rate": 1.9497297578158363e-05, "Pretrain/Loss": 2.0396692752838135, "Pretrain/Loss (Raw)": 1.9853986501693726, "Pretrain/Step": 5565, "Pretrain/Step Time": 8.80482217296958} +{"Pretrain/Learning Rate": 1.9489016232489e-05, "Pretrain/Loss": 2.040921688079834, "Pretrain/Loss (Raw)": 1.9841850996017456, "Pretrain/Step": 5566, "Pretrain/Step Time": 8.808646995574236} +{"Pretrain/Learning Rate": 1.9480735522372236e-05, "Pretrain/Loss": 2.0434963703155518, "Pretrain/Loss (Raw)": 2.0741078853607178, "Pretrain/Step": 5567, "Pretrain/Step Time": 8.790968764573336} +{"Pretrain/Learning Rate": 1.9472455448763077e-05, "Pretrain/Loss": 2.043445110321045, "Pretrain/Loss (Raw)": 1.8737350702285767, "Pretrain/Step": 5568, "Pretrain/Step Time": 8.804668717086315} +{"Pretrain/Learning Rate": 1.9464176012616386e-05, "Pretrain/Loss": 2.041166305541992, "Pretrain/Loss (Raw)": 1.8143606185913086, "Pretrain/Step": 5569, "Pretrain/Step Time": 8.803211756050587} +{"Pretrain/Learning Rate": 1.945589721488702e-05, "Pretrain/Loss": 2.0404486656188965, "Pretrain/Loss (Raw)": 2.0718235969543457, "Pretrain/Step": 5570, "Pretrain/Step Time": 8.803067388013005} +{"Pretrain/Learning Rate": 1.9447619056529697e-05, "Pretrain/Loss": 2.0435285568237305, "Pretrain/Loss (Raw)": 2.0487730503082275, "Pretrain/Step": 5571, "Pretrain/Step Time": 8.808189079165459} +{"Pretrain/Learning Rate": 1.9439341538499117e-05, "Pretrain/Loss": 2.0437300205230713, "Pretrain/Loss (Raw)": 2.0262653827667236, "Pretrain/Step": 5572, "Pretrain/Step Time": 8.809998504817486} +{"Pretrain/Learning Rate": 1.9431064661749866e-05, "Pretrain/Loss": 2.044057607650757, "Pretrain/Loss (Raw)": 2.016139268875122, "Pretrain/Step": 5573, "Pretrain/Step Time": 8.812272632494569} +{"Pretrain/Learning Rate": 1.9422788427236487e-05, "Pretrain/Loss": 2.0428872108459473, "Pretrain/Loss (Raw)": 1.7448861598968506, "Pretrain/Step": 5574, "Pretrain/Step Time": 8.80573664791882} +{"Pretrain/Learning Rate": 1.9414512835913422e-05, "Pretrain/Loss": 2.0435125827789307, "Pretrain/Loss (Raw)": 2.178086519241333, "Pretrain/Step": 5575, "Pretrain/Step Time": 8.807882342487574} +{"Pretrain/Learning Rate": 1.940623788873506e-05, "Pretrain/Loss": 2.042609214782715, "Pretrain/Loss (Raw)": 2.0553925037384033, "Pretrain/Step": 5576, "Pretrain/Step Time": 8.807198660448194} +{"Pretrain/Learning Rate": 1.9397963586655702e-05, "Pretrain/Loss": 2.041107416152954, "Pretrain/Loss (Raw)": 1.939738392829895, "Pretrain/Step": 5577, "Pretrain/Step Time": 8.804404398426414} +{"Pretrain/Learning Rate": 1.9389689930629585e-05, "Pretrain/Loss": 2.0418248176574707, "Pretrain/Loss (Raw)": 2.126171112060547, "Pretrain/Step": 5578, "Pretrain/Step Time": 8.803442632779479} +{"Pretrain/Learning Rate": 1.9381416921610855e-05, "Pretrain/Loss": 2.0410103797912598, "Pretrain/Loss (Raw)": 1.8077318668365479, "Pretrain/Step": 5579, "Pretrain/Step Time": 8.802460068836808} +{"Pretrain/Learning Rate": 1.9373144560553604e-05, "Pretrain/Loss": 2.0419414043426514, "Pretrain/Loss (Raw)": 2.0179572105407715, "Pretrain/Step": 5580, "Pretrain/Step Time": 8.801892127841711} +{"Pretrain/Learning Rate": 1.9364872848411837e-05, "Pretrain/Loss": 2.041965961456299, "Pretrain/Loss (Raw)": 2.0421302318573, "Pretrain/Step": 5581, "Pretrain/Step Time": 8.803388414904475} +{"Pretrain/Learning Rate": 1.9356601786139487e-05, "Pretrain/Loss": 2.042269229888916, "Pretrain/Loss (Raw)": 2.0888657569885254, "Pretrain/Step": 5582, "Pretrain/Step Time": 8.804571038112044} +{"Pretrain/Learning Rate": 1.934833137469041e-05, "Pretrain/Loss": 2.041971206665039, "Pretrain/Loss (Raw)": 2.157559394836426, "Pretrain/Step": 5583, "Pretrain/Step Time": 8.801358349621296} +{"Pretrain/Learning Rate": 1.9340061615018393e-05, "Pretrain/Loss": 2.043379545211792, "Pretrain/Loss (Raw)": 2.1494226455688477, "Pretrain/Step": 5584, "Pretrain/Step Time": 8.799884794279933} +{"Pretrain/Learning Rate": 1.9331792508077136e-05, "Pretrain/Loss": 2.0420784950256348, "Pretrain/Loss (Raw)": 1.972588062286377, "Pretrain/Step": 5585, "Pretrain/Step Time": 8.795202497392893} +{"Pretrain/Learning Rate": 1.9323524054820285e-05, "Pretrain/Loss": 2.0417702198028564, "Pretrain/Loss (Raw)": 2.0693984031677246, "Pretrain/Step": 5586, "Pretrain/Step Time": 8.793365143239498} +{"Pretrain/Learning Rate": 1.9315256256201382e-05, "Pretrain/Loss": 2.0438904762268066, "Pretrain/Loss (Raw)": 2.130321502685547, "Pretrain/Step": 5587, "Pretrain/Step Time": 8.794066831469536} +{"Pretrain/Learning Rate": 1.930698911317392e-05, "Pretrain/Loss": 2.043250560760498, "Pretrain/Loss (Raw)": 2.1548011302948, "Pretrain/Step": 5588, "Pretrain/Step Time": 8.794915430247784} +{"Pretrain/Learning Rate": 1.929872262669129e-05, "Pretrain/Loss": 2.043234348297119, "Pretrain/Loss (Raw)": 2.0140016078948975, "Pretrain/Step": 5589, "Pretrain/Step Time": 8.796106573194265} +{"Pretrain/Learning Rate": 1.9290456797706835e-05, "Pretrain/Loss": 2.0412955284118652, "Pretrain/Loss (Raw)": 2.0360560417175293, "Pretrain/Step": 5590, "Pretrain/Step Time": 8.795749831944704} +{"Pretrain/Learning Rate": 1.928219162717381e-05, "Pretrain/Loss": 2.0412368774414062, "Pretrain/Loss (Raw)": 1.8188031911849976, "Pretrain/Step": 5591, "Pretrain/Step Time": 8.789900656789541} +{"Pretrain/Learning Rate": 1.927392711604539e-05, "Pretrain/Loss": 2.041440486907959, "Pretrain/Loss (Raw)": 2.1152491569519043, "Pretrain/Step": 5592, "Pretrain/Step Time": 8.80117205530405} +{"Pretrain/Learning Rate": 1.926566326527468e-05, "Pretrain/Loss": 2.037484645843506, "Pretrain/Loss (Raw)": 1.8108114004135132, "Pretrain/Step": 5593, "Pretrain/Step Time": 8.803901851177216} +{"Pretrain/Learning Rate": 1.9257400075814697e-05, "Pretrain/Loss": 2.0378236770629883, "Pretrain/Loss (Raw)": 2.0871925354003906, "Pretrain/Step": 5594, "Pretrain/Step Time": 8.802412385120988} +{"Pretrain/Learning Rate": 1.92491375486184e-05, "Pretrain/Loss": 2.0383152961730957, "Pretrain/Loss (Raw)": 2.081088066101074, "Pretrain/Step": 5595, "Pretrain/Step Time": 8.806067461147904} +{"Pretrain/Learning Rate": 1.9240875684638658e-05, "Pretrain/Loss": 2.038987398147583, "Pretrain/Loss (Raw)": 2.140287160873413, "Pretrain/Step": 5596, "Pretrain/Step Time": 8.810451963916421} +{"Pretrain/Learning Rate": 1.9232614484828277e-05, "Pretrain/Loss": 2.0402450561523438, "Pretrain/Loss (Raw)": 2.108548879623413, "Pretrain/Step": 5597, "Pretrain/Step Time": 8.810389844700694} +{"Pretrain/Learning Rate": 1.922435395013996e-05, "Pretrain/Loss": 2.040320873260498, "Pretrain/Loss (Raw)": 2.0958447456359863, "Pretrain/Step": 5598, "Pretrain/Step Time": 8.81157205067575} +{"Pretrain/Learning Rate": 1.921609408152637e-05, "Pretrain/Loss": 2.0410008430480957, "Pretrain/Loss (Raw)": 2.0434021949768066, "Pretrain/Step": 5599, "Pretrain/Step Time": 8.810392981395125} +{"Pretrain/Learning Rate": 1.9207834879940058e-05, "Pretrain/Loss": 2.041527509689331, "Pretrain/Loss (Raw)": 2.301097869873047, "Pretrain/Step": 5600, "Pretrain/Step Time": 8.805833736434579} +{"Pretrain/Learning Rate": 1.919957634633353e-05, "Pretrain/Loss": 2.041639804840088, "Pretrain/Loss (Raw)": 1.960113286972046, "Pretrain/Step": 5601, "Pretrain/Step Time": 8.80644628405571} +{"Pretrain/Learning Rate": 1.9191318481659183e-05, "Pretrain/Loss": 2.0414748191833496, "Pretrain/Loss (Raw)": 1.9443418979644775, "Pretrain/Step": 5602, "Pretrain/Step Time": 8.808861024677753} +{"Pretrain/Learning Rate": 1.918306128686937e-05, "Pretrain/Loss": 2.041029214859009, "Pretrain/Loss (Raw)": 1.99185311794281, "Pretrain/Step": 5603, "Pretrain/Step Time": 8.811142107471824} +{"Pretrain/Learning Rate": 1.9174804762916324e-05, "Pretrain/Loss": 2.0390048027038574, "Pretrain/Loss (Raw)": 1.8438962697982788, "Pretrain/Step": 5604, "Pretrain/Step Time": 8.811444815248251} +{"Pretrain/Learning Rate": 1.916654891075226e-05, "Pretrain/Loss": 2.039006233215332, "Pretrain/Loss (Raw)": 2.0646939277648926, "Pretrain/Step": 5605, "Pretrain/Step Time": 8.8086554184556} +{"Pretrain/Learning Rate": 1.915829373132924e-05, "Pretrain/Loss": 2.038363456726074, "Pretrain/Loss (Raw)": 1.9462658166885376, "Pretrain/Step": 5606, "Pretrain/Step Time": 8.805286573246121} +{"Pretrain/Learning Rate": 1.9150039225599336e-05, "Pretrain/Loss": 2.039085626602173, "Pretrain/Loss (Raw)": 1.9064936637878418, "Pretrain/Step": 5607, "Pretrain/Step Time": 8.801498644053936} +{"Pretrain/Learning Rate": 1.914178539451446e-05, "Pretrain/Loss": 2.038586139678955, "Pretrain/Loss (Raw)": 2.100132465362549, "Pretrain/Step": 5608, "Pretrain/Step Time": 8.805976919829845} +{"Pretrain/Learning Rate": 1.913353223902651e-05, "Pretrain/Loss": 2.0354628562927246, "Pretrain/Loss (Raw)": 1.6925835609436035, "Pretrain/Step": 5609, "Pretrain/Step Time": 8.805287726223469} +{"Pretrain/Learning Rate": 1.912527976008725e-05, "Pretrain/Loss": 2.034792900085449, "Pretrain/Loss (Raw)": 2.0606515407562256, "Pretrain/Step": 5610, "Pretrain/Step Time": 8.808385269716382} +{"Pretrain/Learning Rate": 1.911702795864843e-05, "Pretrain/Loss": 2.0325374603271484, "Pretrain/Loss (Raw)": 1.922214150428772, "Pretrain/Step": 5611, "Pretrain/Step Time": 8.809136338531971} +{"Pretrain/Learning Rate": 1.9108776835661655e-05, "Pretrain/Loss": 2.032764434814453, "Pretrain/Loss (Raw)": 2.030653715133667, "Pretrain/Step": 5612, "Pretrain/Step Time": 8.809285348281264} +{"Pretrain/Learning Rate": 1.91005263920785e-05, "Pretrain/Loss": 2.033853769302368, "Pretrain/Loss (Raw)": 2.1180269718170166, "Pretrain/Step": 5613, "Pretrain/Step Time": 8.805013254284859} +{"Pretrain/Learning Rate": 1.9092276628850438e-05, "Pretrain/Loss": 2.0326366424560547, "Pretrain/Loss (Raw)": 1.9524509906768799, "Pretrain/Step": 5614, "Pretrain/Step Time": 8.805098444223404} +{"Pretrain/Learning Rate": 1.9084027546928872e-05, "Pretrain/Loss": 2.033726453781128, "Pretrain/Loss (Raw)": 2.026864528656006, "Pretrain/Step": 5615, "Pretrain/Step Time": 8.805097848176956} +{"Pretrain/Learning Rate": 1.907577914726513e-05, "Pretrain/Loss": 2.036708354949951, "Pretrain/Loss (Raw)": 2.410362482070923, "Pretrain/Step": 5616, "Pretrain/Step Time": 8.807239543646574} +{"Pretrain/Learning Rate": 1.906753143081045e-05, "Pretrain/Loss": 2.036388397216797, "Pretrain/Loss (Raw)": 2.0776941776275635, "Pretrain/Step": 5617, "Pretrain/Step Time": 8.795977097004652} +{"Pretrain/Learning Rate": 1.9059284398515997e-05, "Pretrain/Loss": 2.0348687171936035, "Pretrain/Loss (Raw)": 1.9942735433578491, "Pretrain/Step": 5618, "Pretrain/Step Time": 8.79651270993054} +{"Pretrain/Learning Rate": 1.9051038051332868e-05, "Pretrain/Loss": 2.0372776985168457, "Pretrain/Loss (Raw)": 2.0517494678497314, "Pretrain/Step": 5619, "Pretrain/Step Time": 8.80373653024435} +{"Pretrain/Learning Rate": 1.9042792390212054e-05, "Pretrain/Loss": 2.0376334190368652, "Pretrain/Loss (Raw)": 2.1408629417419434, "Pretrain/Step": 5620, "Pretrain/Step Time": 8.793372685089707} +{"Pretrain/Learning Rate": 1.9034547416104502e-05, "Pretrain/Loss": 2.03932523727417, "Pretrain/Loss (Raw)": 2.1258091926574707, "Pretrain/Step": 5621, "Pretrain/Step Time": 8.791340474039316} +{"Pretrain/Learning Rate": 1.9026303129961047e-05, "Pretrain/Loss": 2.0388758182525635, "Pretrain/Loss (Raw)": 2.0720527172088623, "Pretrain/Step": 5622, "Pretrain/Step Time": 8.790656998753548} +{"Pretrain/Learning Rate": 1.901805953273247e-05, "Pretrain/Loss": 2.0405192375183105, "Pretrain/Loss (Raw)": 2.29465913772583, "Pretrain/Step": 5623, "Pretrain/Step Time": 8.781372779980302} +{"Pretrain/Learning Rate": 1.900981662536945e-05, "Pretrain/Loss": 2.0391793251037598, "Pretrain/Loss (Raw)": 1.9002634286880493, "Pretrain/Step": 5624, "Pretrain/Step Time": 8.79141072370112} +{"Pretrain/Learning Rate": 1.9001574408822603e-05, "Pretrain/Loss": 2.037976026535034, "Pretrain/Loss (Raw)": 1.9946850538253784, "Pretrain/Step": 5625, "Pretrain/Step Time": 8.787451639771461} +{"Pretrain/Learning Rate": 1.899333288404246e-05, "Pretrain/Loss": 2.0366897583007812, "Pretrain/Loss (Raw)": 1.9390813112258911, "Pretrain/Step": 5626, "Pretrain/Step Time": 8.78497290238738} +{"Pretrain/Learning Rate": 1.8985092051979478e-05, "Pretrain/Loss": 2.0366923809051514, "Pretrain/Loss (Raw)": 2.0572357177734375, "Pretrain/Step": 5627, "Pretrain/Step Time": 8.785997340455651} +{"Pretrain/Learning Rate": 1.897685191358402e-05, "Pretrain/Loss": 2.036485195159912, "Pretrain/Loss (Raw)": 2.084857940673828, "Pretrain/Step": 5628, "Pretrain/Step Time": 8.786407880485058} +{"Pretrain/Learning Rate": 1.8968612469806387e-05, "Pretrain/Loss": 2.0374300479888916, "Pretrain/Loss (Raw)": 2.2171928882598877, "Pretrain/Step": 5629, "Pretrain/Step Time": 8.78981551155448} +{"Pretrain/Learning Rate": 1.8960373721596775e-05, "Pretrain/Loss": 2.036900043487549, "Pretrain/Loss (Raw)": 1.9281578063964844, "Pretrain/Step": 5630, "Pretrain/Step Time": 8.782477099448442} +{"Pretrain/Learning Rate": 1.8952135669905334e-05, "Pretrain/Loss": 2.0380804538726807, "Pretrain/Loss (Raw)": 2.0067384243011475, "Pretrain/Step": 5631, "Pretrain/Step Time": 8.796865597367287} +{"Pretrain/Learning Rate": 1.89438983156821e-05, "Pretrain/Loss": 2.039802074432373, "Pretrain/Loss (Raw)": 2.1909894943237305, "Pretrain/Step": 5632, "Pretrain/Step Time": 8.79278222285211} +{"Pretrain/Learning Rate": 1.8935661659877046e-05, "Pretrain/Loss": 2.0374345779418945, "Pretrain/Loss (Raw)": 1.9188305139541626, "Pretrain/Step": 5633, "Pretrain/Step Time": 8.793781589716673} +{"Pretrain/Learning Rate": 1.8927425703440076e-05, "Pretrain/Loss": 2.0371763706207275, "Pretrain/Loss (Raw)": 2.114715814590454, "Pretrain/Step": 5634, "Pretrain/Step Time": 8.794305343180895} +{"Pretrain/Learning Rate": 1.8919190447320982e-05, "Pretrain/Loss": 2.0377309322357178, "Pretrain/Loss (Raw)": 2.1035728454589844, "Pretrain/Step": 5635, "Pretrain/Step Time": 8.79820486344397} +{"Pretrain/Learning Rate": 1.8910955892469505e-05, "Pretrain/Loss": 2.039496421813965, "Pretrain/Loss (Raw)": 2.3545682430267334, "Pretrain/Step": 5636, "Pretrain/Step Time": 8.797543786466122} +{"Pretrain/Learning Rate": 1.890272203983528e-05, "Pretrain/Loss": 2.0376505851745605, "Pretrain/Loss (Raw)": 1.9904903173446655, "Pretrain/Step": 5637, "Pretrain/Step Time": 8.79662317223847} +{"Pretrain/Learning Rate": 1.8894488890367885e-05, "Pretrain/Loss": 2.0387625694274902, "Pretrain/Loss (Raw)": 1.930834412574768, "Pretrain/Step": 5638, "Pretrain/Step Time": 8.797440690919757} +{"Pretrain/Learning Rate": 1.8886256445016798e-05, "Pretrain/Loss": 2.0367937088012695, "Pretrain/Loss (Raw)": 1.9556411504745483, "Pretrain/Step": 5639, "Pretrain/Step Time": 8.799023298546672} +{"Pretrain/Learning Rate": 1.8878024704731433e-05, "Pretrain/Loss": 2.036510944366455, "Pretrain/Loss (Raw)": 1.9742711782455444, "Pretrain/Step": 5640, "Pretrain/Step Time": 8.797565318644047} +{"Pretrain/Learning Rate": 1.88697936704611e-05, "Pretrain/Loss": 2.034492015838623, "Pretrain/Loss (Raw)": 1.9084513187408447, "Pretrain/Step": 5641, "Pretrain/Step Time": 8.793697640299797} +{"Pretrain/Learning Rate": 1.8861563343155054e-05, "Pretrain/Loss": 2.0350914001464844, "Pretrain/Loss (Raw)": 2.146649122238159, "Pretrain/Step": 5642, "Pretrain/Step Time": 8.79900598153472} +{"Pretrain/Learning Rate": 1.8853333723762438e-05, "Pretrain/Loss": 2.0354599952697754, "Pretrain/Loss (Raw)": 2.036672353744507, "Pretrain/Step": 5643, "Pretrain/Step Time": 8.792999554425478} +{"Pretrain/Learning Rate": 1.884510481323236e-05, "Pretrain/Loss": 2.0345065593719482, "Pretrain/Loss (Raw)": 2.0090603828430176, "Pretrain/Step": 5644, "Pretrain/Step Time": 8.796038089320064} +{"Pretrain/Learning Rate": 1.8836876612513777e-05, "Pretrain/Loss": 2.0347518920898438, "Pretrain/Loss (Raw)": 2.022865056991577, "Pretrain/Step": 5645, "Pretrain/Step Time": 8.79681189544499} +{"Pretrain/Learning Rate": 1.882864912255564e-05, "Pretrain/Loss": 2.0363173484802246, "Pretrain/Loss (Raw)": 2.0738840103149414, "Pretrain/Step": 5646, "Pretrain/Step Time": 8.800173049792647} +{"Pretrain/Learning Rate": 1.882042234430675e-05, "Pretrain/Loss": 2.0366692543029785, "Pretrain/Loss (Raw)": 2.060901641845703, "Pretrain/Step": 5647, "Pretrain/Step Time": 8.794454883784056} +{"Pretrain/Learning Rate": 1.8812196278715895e-05, "Pretrain/Loss": 2.0363500118255615, "Pretrain/Loss (Raw)": 2.1458897590637207, "Pretrain/Step": 5648, "Pretrain/Step Time": 8.798309685662389} +{"Pretrain/Learning Rate": 1.8803970926731703e-05, "Pretrain/Loss": 2.0378575325012207, "Pretrain/Loss (Raw)": 2.1310510635375977, "Pretrain/Step": 5649, "Pretrain/Step Time": 8.799223195761442} +{"Pretrain/Learning Rate": 1.8795746289302798e-05, "Pretrain/Loss": 2.0384738445281982, "Pretrain/Loss (Raw)": 2.1465847492218018, "Pretrain/Step": 5650, "Pretrain/Step Time": 8.801056988537312} +{"Pretrain/Learning Rate": 1.878752236737765e-05, "Pretrain/Loss": 2.0410897731781006, "Pretrain/Loss (Raw)": 2.2151577472686768, "Pretrain/Step": 5651, "Pretrain/Step Time": 8.799300622195005} +{"Pretrain/Learning Rate": 1.8779299161904712e-05, "Pretrain/Loss": 2.042191982269287, "Pretrain/Loss (Raw)": 2.1040360927581787, "Pretrain/Step": 5652, "Pretrain/Step Time": 8.79814026132226} +{"Pretrain/Learning Rate": 1.87710766738323e-05, "Pretrain/Loss": 2.0415234565734863, "Pretrain/Loss (Raw)": 2.052189588546753, "Pretrain/Step": 5653, "Pretrain/Step Time": 8.798621702939272} +{"Pretrain/Learning Rate": 1.8762854904108677e-05, "Pretrain/Loss": 2.0439131259918213, "Pretrain/Loss (Raw)": 2.17261004447937, "Pretrain/Step": 5654, "Pretrain/Step Time": 8.79503482580185} +{"Pretrain/Learning Rate": 1.8754633853682016e-05, "Pretrain/Loss": 2.045206069946289, "Pretrain/Loss (Raw)": 2.297011613845825, "Pretrain/Step": 5655, "Pretrain/Step Time": 8.79623676277697} +{"Pretrain/Learning Rate": 1.874641352350041e-05, "Pretrain/Loss": 2.0456042289733887, "Pretrain/Loss (Raw)": 2.1039018630981445, "Pretrain/Step": 5656, "Pretrain/Step Time": 8.79692780598998} +{"Pretrain/Learning Rate": 1.8738193914511865e-05, "Pretrain/Loss": 2.0451014041900635, "Pretrain/Loss (Raw)": 2.2463736534118652, "Pretrain/Step": 5657, "Pretrain/Step Time": 8.795124463737011} +{"Pretrain/Learning Rate": 1.8729975027664303e-05, "Pretrain/Loss": 2.046098470687866, "Pretrain/Loss (Raw)": 2.1653170585632324, "Pretrain/Step": 5658, "Pretrain/Step Time": 8.796192351728678} +{"Pretrain/Learning Rate": 1.8721756863905566e-05, "Pretrain/Loss": 2.0462727546691895, "Pretrain/Loss (Raw)": 2.0309412479400635, "Pretrain/Step": 5659, "Pretrain/Step Time": 8.798617212101817} +{"Pretrain/Learning Rate": 1.8713539424183417e-05, "Pretrain/Loss": 2.0451507568359375, "Pretrain/Loss (Raw)": 1.9407992362976074, "Pretrain/Step": 5660, "Pretrain/Step Time": 8.794976525008678} +{"Pretrain/Learning Rate": 1.8705322709445515e-05, "Pretrain/Loss": 2.046302318572998, "Pretrain/Loss (Raw)": 2.061850070953369, "Pretrain/Step": 5661, "Pretrain/Step Time": 8.794747143983841} +{"Pretrain/Learning Rate": 1.8697106720639467e-05, "Pretrain/Loss": 2.0465450286865234, "Pretrain/Loss (Raw)": 2.2190146446228027, "Pretrain/Step": 5662, "Pretrain/Step Time": 8.796221416443586} +{"Pretrain/Learning Rate": 1.8688891458712765e-05, "Pretrain/Loss": 2.0477147102355957, "Pretrain/Loss (Raw)": 2.161421537399292, "Pretrain/Step": 5663, "Pretrain/Step Time": 8.789041409268975} +{"Pretrain/Learning Rate": 1.8680676924612847e-05, "Pretrain/Loss": 2.047420024871826, "Pretrain/Loss (Raw)": 1.9281831979751587, "Pretrain/Step": 5664, "Pretrain/Step Time": 8.788973877206445} +{"Pretrain/Learning Rate": 1.8672463119287037e-05, "Pretrain/Loss": 2.047266960144043, "Pretrain/Loss (Raw)": 1.9958306550979614, "Pretrain/Step": 5665, "Pretrain/Step Time": 8.791611190885305} +{"Pretrain/Learning Rate": 1.86642500436826e-05, "Pretrain/Loss": 2.0499563217163086, "Pretrain/Loss (Raw)": 2.0655462741851807, "Pretrain/Step": 5666, "Pretrain/Step Time": 8.786758203059435} +{"Pretrain/Learning Rate": 1.8656037698746704e-05, "Pretrain/Loss": 2.0485544204711914, "Pretrain/Loss (Raw)": 1.9948278665542603, "Pretrain/Step": 5667, "Pretrain/Step Time": 8.793776793405414} +{"Pretrain/Learning Rate": 1.8647826085426433e-05, "Pretrain/Loss": 2.0475001335144043, "Pretrain/Loss (Raw)": 2.0237228870391846, "Pretrain/Step": 5668, "Pretrain/Step Time": 8.786673219874501} +{"Pretrain/Learning Rate": 1.8639615204668786e-05, "Pretrain/Loss": 2.047499656677246, "Pretrain/Loss (Raw)": 2.025179147720337, "Pretrain/Step": 5669, "Pretrain/Step Time": 8.785439210012555} +{"Pretrain/Learning Rate": 1.863140505742069e-05, "Pretrain/Loss": 2.0456838607788086, "Pretrain/Loss (Raw)": 1.8697359561920166, "Pretrain/Step": 5670, "Pretrain/Step Time": 8.789785146713257} +{"Pretrain/Learning Rate": 1.862319564462897e-05, "Pretrain/Loss": 2.0445141792297363, "Pretrain/Loss (Raw)": 2.005575656890869, "Pretrain/Step": 5671, "Pretrain/Step Time": 8.788888569921255} +{"Pretrain/Learning Rate": 1.8614986967240382e-05, "Pretrain/Loss": 2.045747995376587, "Pretrain/Loss (Raw)": 1.9614828824996948, "Pretrain/Step": 5672, "Pretrain/Step Time": 8.789241909980774} +{"Pretrain/Learning Rate": 1.8606779026201577e-05, "Pretrain/Loss": 2.044929027557373, "Pretrain/Loss (Raw)": 1.9080111980438232, "Pretrain/Step": 5673, "Pretrain/Step Time": 8.783594535663724} +{"Pretrain/Learning Rate": 1.859857182245914e-05, "Pretrain/Loss": 2.045712471008301, "Pretrain/Loss (Raw)": 2.1789984703063965, "Pretrain/Step": 5674, "Pretrain/Step Time": 8.796539591625333} +{"Pretrain/Learning Rate": 1.859036535695957e-05, "Pretrain/Loss": 2.0451338291168213, "Pretrain/Loss (Raw)": 2.072902202606201, "Pretrain/Step": 5675, "Pretrain/Step Time": 8.79477216862142} +{"Pretrain/Learning Rate": 1.858215963064927e-05, "Pretrain/Loss": 2.04526948928833, "Pretrain/Loss (Raw)": 2.090143918991089, "Pretrain/Step": 5676, "Pretrain/Step Time": 8.794920291751623} +{"Pretrain/Learning Rate": 1.8573954644474562e-05, "Pretrain/Loss": 2.0445034503936768, "Pretrain/Loss (Raw)": 1.9848358631134033, "Pretrain/Step": 5677, "Pretrain/Step Time": 8.794742843136191} +{"Pretrain/Learning Rate": 1.8565750399381684e-05, "Pretrain/Loss": 2.041840076446533, "Pretrain/Loss (Raw)": 1.761121392250061, "Pretrain/Step": 5678, "Pretrain/Step Time": 8.795016197487712} +{"Pretrain/Learning Rate": 1.8557546896316793e-05, "Pretrain/Loss": 2.042238235473633, "Pretrain/Loss (Raw)": 2.0042595863342285, "Pretrain/Step": 5679, "Pretrain/Step Time": 8.792005451396108} +{"Pretrain/Learning Rate": 1.8549344136225946e-05, "Pretrain/Loss": 2.04548716545105, "Pretrain/Loss (Raw)": 2.1040310859680176, "Pretrain/Step": 5680, "Pretrain/Step Time": 8.784460075199604} +{"Pretrain/Learning Rate": 1.8541142120055136e-05, "Pretrain/Loss": 2.0452282428741455, "Pretrain/Loss (Raw)": 1.8830329179763794, "Pretrain/Step": 5681, "Pretrain/Step Time": 8.794719263911247} +{"Pretrain/Learning Rate": 1.8532940848750245e-05, "Pretrain/Loss": 2.0449652671813965, "Pretrain/Loss (Raw)": 2.006944417953491, "Pretrain/Step": 5682, "Pretrain/Step Time": 8.794770857319236} +{"Pretrain/Learning Rate": 1.8524740323257095e-05, "Pretrain/Loss": 2.0479273796081543, "Pretrain/Loss (Raw)": 2.269503116607666, "Pretrain/Step": 5683, "Pretrain/Step Time": 8.797953631728888} +{"Pretrain/Learning Rate": 1.85165405445214e-05, "Pretrain/Loss": 2.044340133666992, "Pretrain/Loss (Raw)": 2.0072414875030518, "Pretrain/Step": 5684, "Pretrain/Step Time": 8.796223921701312} +{"Pretrain/Learning Rate": 1.8508341513488804e-05, "Pretrain/Loss": 2.0435853004455566, "Pretrain/Loss (Raw)": 1.9582070112228394, "Pretrain/Step": 5685, "Pretrain/Step Time": 8.799573339521885} +{"Pretrain/Learning Rate": 1.8500143231104846e-05, "Pretrain/Loss": 2.0455260276794434, "Pretrain/Loss (Raw)": 2.1316730976104736, "Pretrain/Step": 5686, "Pretrain/Step Time": 8.7946752384305} +{"Pretrain/Learning Rate": 1.8491945698315014e-05, "Pretrain/Loss": 2.0432465076446533, "Pretrain/Loss (Raw)": 1.8631153106689453, "Pretrain/Step": 5687, "Pretrain/Step Time": 8.797226564958692} +{"Pretrain/Learning Rate": 1.8483748916064654e-05, "Pretrain/Loss": 2.0421485900878906, "Pretrain/Loss (Raw)": 2.138690948486328, "Pretrain/Step": 5688, "Pretrain/Step Time": 8.808721011504531} +{"Pretrain/Learning Rate": 1.8475552885299092e-05, "Pretrain/Loss": 2.0402886867523193, "Pretrain/Loss (Raw)": 1.9588439464569092, "Pretrain/Step": 5689, "Pretrain/Step Time": 8.804537864401937} +{"Pretrain/Learning Rate": 1.8467357606963496e-05, "Pretrain/Loss": 2.0390281677246094, "Pretrain/Loss (Raw)": 1.874123215675354, "Pretrain/Step": 5690, "Pretrain/Step Time": 8.800778564065695} +{"Pretrain/Learning Rate": 1.845916308200302e-05, "Pretrain/Loss": 2.0424046516418457, "Pretrain/Loss (Raw)": 2.1844546794891357, "Pretrain/Step": 5691, "Pretrain/Step Time": 8.805730288848281} +{"Pretrain/Learning Rate": 1.8450969311362666e-05, "Pretrain/Loss": 2.0421667098999023, "Pretrain/Loss (Raw)": 2.121458053588867, "Pretrain/Step": 5692, "Pretrain/Step Time": 8.804239891469479} +{"Pretrain/Learning Rate": 1.8442776295987403e-05, "Pretrain/Loss": 2.043544054031372, "Pretrain/Loss (Raw)": 2.161684036254883, "Pretrain/Step": 5693, "Pretrain/Step Time": 8.805717142298818} +{"Pretrain/Learning Rate": 1.843458403682206e-05, "Pretrain/Loss": 2.0451459884643555, "Pretrain/Loss (Raw)": 2.189221143722534, "Pretrain/Step": 5694, "Pretrain/Step Time": 8.805693238973618} +{"Pretrain/Learning Rate": 1.8426392534811445e-05, "Pretrain/Loss": 2.043682098388672, "Pretrain/Loss (Raw)": 1.8867168426513672, "Pretrain/Step": 5695, "Pretrain/Step Time": 8.810028027743101} +{"Pretrain/Learning Rate": 1.84182017909002e-05, "Pretrain/Loss": 2.04604172706604, "Pretrain/Loss (Raw)": 2.1757876873016357, "Pretrain/Step": 5696, "Pretrain/Step Time": 8.79946924559772} +{"Pretrain/Learning Rate": 1.841001180603295e-05, "Pretrain/Loss": 2.0458755493164062, "Pretrain/Loss (Raw)": 1.7930703163146973, "Pretrain/Step": 5697, "Pretrain/Step Time": 8.802796786651015} +{"Pretrain/Learning Rate": 1.8401822581154188e-05, "Pretrain/Loss": 2.045518398284912, "Pretrain/Loss (Raw)": 2.026129722595215, "Pretrain/Step": 5698, "Pretrain/Step Time": 8.805106993764639} +{"Pretrain/Learning Rate": 1.8393634117208343e-05, "Pretrain/Loss": 2.0456814765930176, "Pretrain/Loss (Raw)": 2.0696277618408203, "Pretrain/Step": 5699, "Pretrain/Step Time": 8.798951068893075} +{"Pretrain/Learning Rate": 1.838544641513973e-05, "Pretrain/Loss": 2.0452003479003906, "Pretrain/Loss (Raw)": 1.9646961688995361, "Pretrain/Step": 5700, "Pretrain/Step Time": 8.796157332137227} +{"Pretrain/Learning Rate": 1.8377259475892612e-05, "Pretrain/Loss": 2.0440988540649414, "Pretrain/Loss (Raw)": 1.8751450777053833, "Pretrain/Step": 5701, "Pretrain/Step Time": 8.7989699896425} +{"Pretrain/Learning Rate": 1.8369073300411137e-05, "Pretrain/Loss": 2.045949935913086, "Pretrain/Loss (Raw)": 1.9818195104599, "Pretrain/Step": 5702, "Pretrain/Step Time": 8.798705188557506} +{"Pretrain/Learning Rate": 1.836088788963938e-05, "Pretrain/Loss": 2.0448708534240723, "Pretrain/Loss (Raw)": 2.0399787425994873, "Pretrain/Step": 5703, "Pretrain/Step Time": 8.79651204496622} +{"Pretrain/Learning Rate": 1.8352703244521308e-05, "Pretrain/Loss": 2.0445494651794434, "Pretrain/Loss (Raw)": 2.0142555236816406, "Pretrain/Step": 5704, "Pretrain/Step Time": 8.804010424762964} +{"Pretrain/Learning Rate": 1.8344519366000828e-05, "Pretrain/Loss": 2.044851779937744, "Pretrain/Loss (Raw)": 1.9784108400344849, "Pretrain/Step": 5705, "Pretrain/Step Time": 8.80647080205381} +{"Pretrain/Learning Rate": 1.833633625502173e-05, "Pretrain/Loss": 2.043390989303589, "Pretrain/Loss (Raw)": 1.9392024278640747, "Pretrain/Step": 5706, "Pretrain/Step Time": 8.798904977738857} +{"Pretrain/Learning Rate": 1.832815391252774e-05, "Pretrain/Loss": 2.0441346168518066, "Pretrain/Loss (Raw)": 1.902918815612793, "Pretrain/Step": 5707, "Pretrain/Step Time": 8.800822515040636} +{"Pretrain/Learning Rate": 1.8319972339462478e-05, "Pretrain/Loss": 2.0436015129089355, "Pretrain/Loss (Raw)": 1.9497507810592651, "Pretrain/Step": 5708, "Pretrain/Step Time": 8.802864130586386} +{"Pretrain/Learning Rate": 1.8311791536769483e-05, "Pretrain/Loss": 2.0441675186157227, "Pretrain/Loss (Raw)": 2.1145589351654053, "Pretrain/Step": 5709, "Pretrain/Step Time": 8.802978513762355} +{"Pretrain/Learning Rate": 1.8303611505392205e-05, "Pretrain/Loss": 2.0416271686553955, "Pretrain/Loss (Raw)": 1.763695240020752, "Pretrain/Step": 5710, "Pretrain/Step Time": 8.80288315936923} +{"Pretrain/Learning Rate": 1.8295432246274e-05, "Pretrain/Loss": 2.0414061546325684, "Pretrain/Loss (Raw)": 2.129274845123291, "Pretrain/Step": 5711, "Pretrain/Step Time": 8.81204965338111} +{"Pretrain/Learning Rate": 1.828725376035814e-05, "Pretrain/Loss": 2.04044508934021, "Pretrain/Loss (Raw)": 2.0264058113098145, "Pretrain/Step": 5712, "Pretrain/Step Time": 8.808713153004646} +{"Pretrain/Learning Rate": 1.827907604858782e-05, "Pretrain/Loss": 2.0423731803894043, "Pretrain/Loss (Raw)": 2.219383955001831, "Pretrain/Step": 5713, "Pretrain/Step Time": 8.809314917773008} +{"Pretrain/Learning Rate": 1.8270899111906102e-05, "Pretrain/Loss": 2.0428366661071777, "Pretrain/Loss (Raw)": 2.128734588623047, "Pretrain/Step": 5714, "Pretrain/Step Time": 8.811779733747244} +{"Pretrain/Learning Rate": 1.826272295125602e-05, "Pretrain/Loss": 2.0405192375183105, "Pretrain/Loss (Raw)": 1.8336944580078125, "Pretrain/Step": 5715, "Pretrain/Step Time": 8.812654562294483} +{"Pretrain/Learning Rate": 1.8254547567580472e-05, "Pretrain/Loss": 2.040522813796997, "Pretrain/Loss (Raw)": 2.1552300453186035, "Pretrain/Step": 5716, "Pretrain/Step Time": 8.805279929190874} +{"Pretrain/Learning Rate": 1.824637296182228e-05, "Pretrain/Loss": 2.0408778190612793, "Pretrain/Loss (Raw)": 2.059429883956909, "Pretrain/Step": 5717, "Pretrain/Step Time": 8.802734561264515} +{"Pretrain/Learning Rate": 1.8238199134924185e-05, "Pretrain/Loss": 2.0405397415161133, "Pretrain/Loss (Raw)": 1.9928131103515625, "Pretrain/Step": 5718, "Pretrain/Step Time": 8.80355286411941} +{"Pretrain/Learning Rate": 1.8230026087828824e-05, "Pretrain/Loss": 2.0422873497009277, "Pretrain/Loss (Raw)": 2.042468547821045, "Pretrain/Step": 5719, "Pretrain/Step Time": 8.806522343307734} +{"Pretrain/Learning Rate": 1.8221853821478763e-05, "Pretrain/Loss": 2.041799306869507, "Pretrain/Loss (Raw)": 2.052788496017456, "Pretrain/Step": 5720, "Pretrain/Step Time": 8.80224602855742} +{"Pretrain/Learning Rate": 1.821368233681645e-05, "Pretrain/Loss": 2.0442440509796143, "Pretrain/Loss (Raw)": 2.1237497329711914, "Pretrain/Step": 5721, "Pretrain/Step Time": 8.79743274860084} +{"Pretrain/Learning Rate": 1.820551163478428e-05, "Pretrain/Loss": 2.0430612564086914, "Pretrain/Loss (Raw)": 1.93576180934906, "Pretrain/Step": 5722, "Pretrain/Step Time": 8.795822747051716} +{"Pretrain/Learning Rate": 1.8197341716324516e-05, "Pretrain/Loss": 2.043757915496826, "Pretrain/Loss (Raw)": 2.170304536819458, "Pretrain/Step": 5723, "Pretrain/Step Time": 8.79414201527834} +{"Pretrain/Learning Rate": 1.8189172582379365e-05, "Pretrain/Loss": 2.042750358581543, "Pretrain/Loss (Raw)": 2.0113213062286377, "Pretrain/Step": 5724, "Pretrain/Step Time": 8.790801217779517} +{"Pretrain/Learning Rate": 1.818100423389092e-05, "Pretrain/Loss": 2.0426180362701416, "Pretrain/Loss (Raw)": 2.0915913581848145, "Pretrain/Step": 5725, "Pretrain/Step Time": 8.790747171267867} +{"Pretrain/Learning Rate": 1.817283667180121e-05, "Pretrain/Loss": 2.041857957839966, "Pretrain/Loss (Raw)": 1.998555302619934, "Pretrain/Step": 5726, "Pretrain/Step Time": 8.788577204570174} +{"Pretrain/Learning Rate": 1.8164669897052134e-05, "Pretrain/Loss": 2.042941093444824, "Pretrain/Loss (Raw)": 2.182065486907959, "Pretrain/Step": 5727, "Pretrain/Step Time": 8.791384890675545} +{"Pretrain/Learning Rate": 1.8156503910585544e-05, "Pretrain/Loss": 2.0416371822357178, "Pretrain/Loss (Raw)": 2.1341729164123535, "Pretrain/Step": 5728, "Pretrain/Step Time": 8.796318197622895} +{"Pretrain/Learning Rate": 1.814833871334316e-05, "Pretrain/Loss": 2.0421478748321533, "Pretrain/Loss (Raw)": 2.025479793548584, "Pretrain/Step": 5729, "Pretrain/Step Time": 8.797116849571466} +{"Pretrain/Learning Rate": 1.8140174306266655e-05, "Pretrain/Loss": 2.044839382171631, "Pretrain/Loss (Raw)": 2.28885817527771, "Pretrain/Step": 5730, "Pretrain/Step Time": 8.794365415349603} +{"Pretrain/Learning Rate": 1.8132010690297557e-05, "Pretrain/Loss": 2.0441393852233887, "Pretrain/Loss (Raw)": 1.9022647142410278, "Pretrain/Step": 5731, "Pretrain/Step Time": 8.792180117219687} +{"Pretrain/Learning Rate": 1.8123847866377367e-05, "Pretrain/Loss": 2.045231819152832, "Pretrain/Loss (Raw)": 1.9837325811386108, "Pretrain/Step": 5732, "Pretrain/Step Time": 8.790851805359125} +{"Pretrain/Learning Rate": 1.8115685835447423e-05, "Pretrain/Loss": 2.0442047119140625, "Pretrain/Loss (Raw)": 1.9332008361816406, "Pretrain/Step": 5733, "Pretrain/Step Time": 8.797925466671586} +{"Pretrain/Learning Rate": 1.810752459844905e-05, "Pretrain/Loss": 2.047800064086914, "Pretrain/Loss (Raw)": 2.406482696533203, "Pretrain/Step": 5734, "Pretrain/Step Time": 8.799559427425265} +{"Pretrain/Learning Rate": 1.8099364156323396e-05, "Pretrain/Loss": 2.050752639770508, "Pretrain/Loss (Raw)": 2.2844324111938477, "Pretrain/Step": 5735, "Pretrain/Step Time": 8.800552064552903} +{"Pretrain/Learning Rate": 1.8091204510011607e-05, "Pretrain/Loss": 2.048088550567627, "Pretrain/Loss (Raw)": 1.759121298789978, "Pretrain/Step": 5736, "Pretrain/Step Time": 8.801750265061855} +{"Pretrain/Learning Rate": 1.8083045660454655e-05, "Pretrain/Loss": 2.050727605819702, "Pretrain/Loss (Raw)": 2.030390977859497, "Pretrain/Step": 5737, "Pretrain/Step Time": 8.798081636428833} +{"Pretrain/Learning Rate": 1.8074887608593477e-05, "Pretrain/Loss": 2.0499155521392822, "Pretrain/Loss (Raw)": 1.9566915035247803, "Pretrain/Step": 5738, "Pretrain/Step Time": 8.795367063954473} +{"Pretrain/Learning Rate": 1.8066730355368888e-05, "Pretrain/Loss": 2.0527267456054688, "Pretrain/Loss (Raw)": 2.2820491790771484, "Pretrain/Step": 5739, "Pretrain/Step Time": 8.794358840212226} +{"Pretrain/Learning Rate": 1.805857390172163e-05, "Pretrain/Loss": 2.0505504608154297, "Pretrain/Loss (Raw)": 1.7521064281463623, "Pretrain/Step": 5740, "Pretrain/Step Time": 8.79556218907237} +{"Pretrain/Learning Rate": 1.8050418248592334e-05, "Pretrain/Loss": 2.0510048866271973, "Pretrain/Loss (Raw)": 2.1761715412139893, "Pretrain/Step": 5741, "Pretrain/Step Time": 8.79711340367794} +{"Pretrain/Learning Rate": 1.8042263396921554e-05, "Pretrain/Loss": 2.0521883964538574, "Pretrain/Loss (Raw)": 2.1039366722106934, "Pretrain/Step": 5742, "Pretrain/Step Time": 8.794744573533535} +{"Pretrain/Learning Rate": 1.803410934764974e-05, "Pretrain/Loss": 2.050814390182495, "Pretrain/Loss (Raw)": 1.8510105609893799, "Pretrain/Step": 5743, "Pretrain/Step Time": 8.793369824066758} +{"Pretrain/Learning Rate": 1.8025956101717272e-05, "Pretrain/Loss": 2.0491280555725098, "Pretrain/Loss (Raw)": 2.1944899559020996, "Pretrain/Step": 5744, "Pretrain/Step Time": 8.801435114815831} +{"Pretrain/Learning Rate": 1.80178036600644e-05, "Pretrain/Loss": 2.0501856803894043, "Pretrain/Loss (Raw)": 2.213057041168213, "Pretrain/Step": 5745, "Pretrain/Step Time": 8.80248798802495} +{"Pretrain/Learning Rate": 1.8009652023631318e-05, "Pretrain/Loss": 2.0526275634765625, "Pretrain/Loss (Raw)": 2.306858777999878, "Pretrain/Step": 5746, "Pretrain/Step Time": 8.798879524692893} +{"Pretrain/Learning Rate": 1.8001501193358096e-05, "Pretrain/Loss": 2.051349401473999, "Pretrain/Loss (Raw)": 1.8881462812423706, "Pretrain/Step": 5747, "Pretrain/Step Time": 8.796489475294948} +{"Pretrain/Learning Rate": 1.799335117018474e-05, "Pretrain/Loss": 2.0502519607543945, "Pretrain/Loss (Raw)": 2.0004117488861084, "Pretrain/Step": 5748, "Pretrain/Step Time": 8.798280427232385} +{"Pretrain/Learning Rate": 1.798520195505114e-05, "Pretrain/Loss": 2.0501999855041504, "Pretrain/Loss (Raw)": 2.1191420555114746, "Pretrain/Step": 5749, "Pretrain/Step Time": 8.799200097098947} +{"Pretrain/Learning Rate": 1.7977053548897112e-05, "Pretrain/Loss": 2.050966739654541, "Pretrain/Loss (Raw)": 2.1702053546905518, "Pretrain/Step": 5750, "Pretrain/Step Time": 8.802337680011988} +{"Pretrain/Learning Rate": 1.7968905952662354e-05, "Pretrain/Loss": 2.0497403144836426, "Pretrain/Loss (Raw)": 2.137662172317505, "Pretrain/Step": 5751, "Pretrain/Step Time": 8.805873833596706} +{"Pretrain/Learning Rate": 1.79607591672865e-05, "Pretrain/Loss": 2.051237106323242, "Pretrain/Loss (Raw)": 2.091846227645874, "Pretrain/Step": 5752, "Pretrain/Step Time": 8.792311793193221} +{"Pretrain/Learning Rate": 1.7952613193709063e-05, "Pretrain/Loss": 2.050379991531372, "Pretrain/Loss (Raw)": 1.8849766254425049, "Pretrain/Step": 5753, "Pretrain/Step Time": 8.79714479483664} +{"Pretrain/Learning Rate": 1.7944468032869486e-05, "Pretrain/Loss": 2.0503792762756348, "Pretrain/Loss (Raw)": 1.9390015602111816, "Pretrain/Step": 5754, "Pretrain/Step Time": 8.7986571919173} +{"Pretrain/Learning Rate": 1.7936323685707095e-05, "Pretrain/Loss": 2.0510776042938232, "Pretrain/Loss (Raw)": 2.146623134613037, "Pretrain/Step": 5755, "Pretrain/Step Time": 8.79962476156652} +{"Pretrain/Learning Rate": 1.7928180153161146e-05, "Pretrain/Loss": 2.0508837699890137, "Pretrain/Loss (Raw)": 2.0600502490997314, "Pretrain/Step": 5756, "Pretrain/Step Time": 8.799915295094252} +{"Pretrain/Learning Rate": 1.792003743617079e-05, "Pretrain/Loss": 2.0486159324645996, "Pretrain/Loss (Raw)": 1.926895260810852, "Pretrain/Step": 5757, "Pretrain/Step Time": 8.797958990558982} +{"Pretrain/Learning Rate": 1.7911895535675067e-05, "Pretrain/Loss": 2.0495946407318115, "Pretrain/Loss (Raw)": 2.0534400939941406, "Pretrain/Step": 5758, "Pretrain/Step Time": 8.799365544691682} +{"Pretrain/Learning Rate": 1.7903754452612964e-05, "Pretrain/Loss": 2.048983097076416, "Pretrain/Loss (Raw)": 1.928475260734558, "Pretrain/Step": 5759, "Pretrain/Step Time": 8.791419425979257} +{"Pretrain/Learning Rate": 1.7895614187923326e-05, "Pretrain/Loss": 2.049801826477051, "Pretrain/Loss (Raw)": 2.2957887649536133, "Pretrain/Step": 5760, "Pretrain/Step Time": 8.79055373556912} +{"Pretrain/Learning Rate": 1.7887474742544945e-05, "Pretrain/Loss": 2.0505423545837402, "Pretrain/Loss (Raw)": 2.01359486579895, "Pretrain/Step": 5761, "Pretrain/Step Time": 8.795197216793895} +{"Pretrain/Learning Rate": 1.7879336117416485e-05, "Pretrain/Loss": 2.05117130279541, "Pretrain/Loss (Raw)": 2.1952593326568604, "Pretrain/Step": 5762, "Pretrain/Step Time": 8.79237948358059} +{"Pretrain/Learning Rate": 1.7871198313476544e-05, "Pretrain/Loss": 2.0507726669311523, "Pretrain/Loss (Raw)": 2.052546262741089, "Pretrain/Step": 5763, "Pretrain/Step Time": 8.79241850040853} +{"Pretrain/Learning Rate": 1.78630613316636e-05, "Pretrain/Loss": 2.048867702484131, "Pretrain/Loss (Raw)": 2.1107101440429688, "Pretrain/Step": 5764, "Pretrain/Step Time": 8.792958475649357} +{"Pretrain/Learning Rate": 1.785492517291606e-05, "Pretrain/Loss": 2.048893928527832, "Pretrain/Loss (Raw)": 1.9938400983810425, "Pretrain/Step": 5765, "Pretrain/Step Time": 8.790620984509587} +{"Pretrain/Learning Rate": 1.784678983817221e-05, "Pretrain/Loss": 2.049999713897705, "Pretrain/Loss (Raw)": 2.072356700897217, "Pretrain/Step": 5766, "Pretrain/Step Time": 8.793927306309342} +{"Pretrain/Learning Rate": 1.783865532837027e-05, "Pretrain/Loss": 2.050994873046875, "Pretrain/Loss (Raw)": 2.0830516815185547, "Pretrain/Step": 5767, "Pretrain/Step Time": 8.794896213337779} +{"Pretrain/Learning Rate": 1.7830521644448334e-05, "Pretrain/Loss": 2.0502376556396484, "Pretrain/Loss (Raw)": 1.877346396446228, "Pretrain/Step": 5768, "Pretrain/Step Time": 8.796402065083385} +{"Pretrain/Learning Rate": 1.7822388787344434e-05, "Pretrain/Loss": 2.052394390106201, "Pretrain/Loss (Raw)": 2.1844871044158936, "Pretrain/Step": 5769, "Pretrain/Step Time": 8.795081462711096} +{"Pretrain/Learning Rate": 1.781425675799648e-05, "Pretrain/Loss": 2.051501750946045, "Pretrain/Loss (Raw)": 2.0323944091796875, "Pretrain/Step": 5770, "Pretrain/Step Time": 8.800015149638057} +{"Pretrain/Learning Rate": 1.7806125557342303e-05, "Pretrain/Loss": 2.0492048263549805, "Pretrain/Loss (Raw)": 1.7426811456680298, "Pretrain/Step": 5771, "Pretrain/Step Time": 8.805914545431733} +{"Pretrain/Learning Rate": 1.7797995186319606e-05, "Pretrain/Loss": 2.0483851432800293, "Pretrain/Loss (Raw)": 1.9041303396224976, "Pretrain/Step": 5772, "Pretrain/Step Time": 8.797992737963796} +{"Pretrain/Learning Rate": 1.778986564586606e-05, "Pretrain/Loss": 2.0461602210998535, "Pretrain/Loss (Raw)": 1.7380834817886353, "Pretrain/Step": 5773, "Pretrain/Step Time": 8.794166563078761} +{"Pretrain/Learning Rate": 1.778173693691917e-05, "Pretrain/Loss": 2.0463857650756836, "Pretrain/Loss (Raw)": 2.1027731895446777, "Pretrain/Step": 5774, "Pretrain/Step Time": 8.800554050132632} +{"Pretrain/Learning Rate": 1.77736090604164e-05, "Pretrain/Loss": 2.046271800994873, "Pretrain/Loss (Raw)": 2.0463006496429443, "Pretrain/Step": 5775, "Pretrain/Step Time": 8.802264481782913} +{"Pretrain/Learning Rate": 1.7765482017295077e-05, "Pretrain/Loss": 2.0458567142486572, "Pretrain/Loss (Raw)": 2.0927419662475586, "Pretrain/Step": 5776, "Pretrain/Step Time": 8.799942433834076} +{"Pretrain/Learning Rate": 1.7757355808492468e-05, "Pretrain/Loss": 2.045271873474121, "Pretrain/Loss (Raw)": 2.056215763092041, "Pretrain/Step": 5777, "Pretrain/Step Time": 8.803672801703215} +{"Pretrain/Learning Rate": 1.77492304349457e-05, "Pretrain/Loss": 2.043506145477295, "Pretrain/Loss (Raw)": 1.9205288887023926, "Pretrain/Step": 5778, "Pretrain/Step Time": 8.801539201289415} +{"Pretrain/Learning Rate": 1.7741105897591865e-05, "Pretrain/Loss": 2.0433287620544434, "Pretrain/Loss (Raw)": 2.1925032138824463, "Pretrain/Step": 5779, "Pretrain/Step Time": 8.804330687969923} +{"Pretrain/Learning Rate": 1.7732982197367888e-05, "Pretrain/Loss": 2.042226552963257, "Pretrain/Loss (Raw)": 1.9629348516464233, "Pretrain/Step": 5780, "Pretrain/Step Time": 8.797030810266733} +{"Pretrain/Learning Rate": 1.7724859335210654e-05, "Pretrain/Loss": 2.042430877685547, "Pretrain/Loss (Raw)": 2.0783305168151855, "Pretrain/Step": 5781, "Pretrain/Step Time": 8.804314685985446} +{"Pretrain/Learning Rate": 1.771673731205692e-05, "Pretrain/Loss": 2.0407443046569824, "Pretrain/Loss (Raw)": 1.956735610961914, "Pretrain/Step": 5782, "Pretrain/Step Time": 8.805548863485456} +{"Pretrain/Learning Rate": 1.770861612884336e-05, "Pretrain/Loss": 2.037858009338379, "Pretrain/Loss (Raw)": 1.9275742769241333, "Pretrain/Step": 5783, "Pretrain/Step Time": 8.803782837465405} +{"Pretrain/Learning Rate": 1.7700495786506545e-05, "Pretrain/Loss": 2.0365567207336426, "Pretrain/Loss (Raw)": 1.937329888343811, "Pretrain/Step": 5784, "Pretrain/Step Time": 8.807174330577254} +{"Pretrain/Learning Rate": 1.7692376285982953e-05, "Pretrain/Loss": 2.0368411540985107, "Pretrain/Loss (Raw)": 2.2827670574188232, "Pretrain/Step": 5785, "Pretrain/Step Time": 8.810263935476542} +{"Pretrain/Learning Rate": 1.768425762820896e-05, "Pretrain/Loss": 2.036686658859253, "Pretrain/Loss (Raw)": 2.1455373764038086, "Pretrain/Step": 5786, "Pretrain/Step Time": 8.809855379164219} +{"Pretrain/Learning Rate": 1.7676139814120857e-05, "Pretrain/Loss": 2.0368733406066895, "Pretrain/Loss (Raw)": 2.0548319816589355, "Pretrain/Step": 5787, "Pretrain/Step Time": 8.805719017982483} +{"Pretrain/Learning Rate": 1.7668022844654812e-05, "Pretrain/Loss": 2.037632465362549, "Pretrain/Loss (Raw)": 2.037997245788574, "Pretrain/Step": 5788, "Pretrain/Step Time": 8.810113295912743} +{"Pretrain/Learning Rate": 1.765990672074693e-05, "Pretrain/Loss": 2.0389082431793213, "Pretrain/Loss (Raw)": 2.2251391410827637, "Pretrain/Step": 5789, "Pretrain/Step Time": 8.812653914093971} +{"Pretrain/Learning Rate": 1.7651791443333187e-05, "Pretrain/Loss": 2.0378851890563965, "Pretrain/Loss (Raw)": 2.0880796909332275, "Pretrain/Step": 5790, "Pretrain/Step Time": 8.809141922742128} +{"Pretrain/Learning Rate": 1.764367701334949e-05, "Pretrain/Loss": 2.036768674850464, "Pretrain/Loss (Raw)": 2.018508195877075, "Pretrain/Step": 5791, "Pretrain/Step Time": 8.814858455210924} +{"Pretrain/Learning Rate": 1.7635563431731612e-05, "Pretrain/Loss": 2.0372095108032227, "Pretrain/Loss (Raw)": 1.9846035242080688, "Pretrain/Step": 5792, "Pretrain/Step Time": 8.813168900087476} +{"Pretrain/Learning Rate": 1.762745069941527e-05, "Pretrain/Loss": 2.037760019302368, "Pretrain/Loss (Raw)": 2.066295623779297, "Pretrain/Step": 5793, "Pretrain/Step Time": 8.815417787060142} +{"Pretrain/Learning Rate": 1.7619338817336046e-05, "Pretrain/Loss": 2.0374491214752197, "Pretrain/Loss (Raw)": 2.0257370471954346, "Pretrain/Step": 5794, "Pretrain/Step Time": 8.820096192881465} +{"Pretrain/Learning Rate": 1.7611227786429457e-05, "Pretrain/Loss": 2.0373268127441406, "Pretrain/Loss (Raw)": 1.9792076349258423, "Pretrain/Step": 5795, "Pretrain/Step Time": 8.814738819375634} +{"Pretrain/Learning Rate": 1.7603117607630893e-05, "Pretrain/Loss": 2.0383615493774414, "Pretrain/Loss (Raw)": 2.156122922897339, "Pretrain/Step": 5796, "Pretrain/Step Time": 8.818214586004615} +{"Pretrain/Learning Rate": 1.7595008281875657e-05, "Pretrain/Loss": 2.0402450561523438, "Pretrain/Loss (Raw)": 2.26628041267395, "Pretrain/Step": 5797, "Pretrain/Step Time": 8.81539874151349} +{"Pretrain/Learning Rate": 1.7586899810098967e-05, "Pretrain/Loss": 2.042327642440796, "Pretrain/Loss (Raw)": 2.1363258361816406, "Pretrain/Step": 5798, "Pretrain/Step Time": 8.810808893293142} +{"Pretrain/Learning Rate": 1.757879219323592e-05, "Pretrain/Loss": 2.0434722900390625, "Pretrain/Loss (Raw)": 2.1520955562591553, "Pretrain/Step": 5799, "Pretrain/Step Time": 8.812988368794322} +{"Pretrain/Learning Rate": 1.757068543222153e-05, "Pretrain/Loss": 2.0475053787231445, "Pretrain/Loss (Raw)": 2.4777116775512695, "Pretrain/Step": 5800, "Pretrain/Step Time": 8.812157932668924} +{"Pretrain/Learning Rate": 1.7562579527990696e-05, "Pretrain/Loss": 2.048311948776245, "Pretrain/Loss (Raw)": 2.0112404823303223, "Pretrain/Step": 5801, "Pretrain/Step Time": 8.824134789407253} +{"Pretrain/Learning Rate": 1.7554474481478245e-05, "Pretrain/Loss": 2.0475778579711914, "Pretrain/Loss (Raw)": 2.085023880004883, "Pretrain/Step": 5802, "Pretrain/Step Time": 8.814571987837553} +{"Pretrain/Learning Rate": 1.7546370293618875e-05, "Pretrain/Loss": 2.0477824211120605, "Pretrain/Loss (Raw)": 2.0991203784942627, "Pretrain/Step": 5803, "Pretrain/Step Time": 8.81401390209794} +{"Pretrain/Learning Rate": 1.7538266965347212e-05, "Pretrain/Loss": 2.045663595199585, "Pretrain/Loss (Raw)": 1.8189045190811157, "Pretrain/Step": 5804, "Pretrain/Step Time": 8.815287843346596} +{"Pretrain/Learning Rate": 1.7530164497597757e-05, "Pretrain/Loss": 2.0460643768310547, "Pretrain/Loss (Raw)": 2.036156177520752, "Pretrain/Step": 5805, "Pretrain/Step Time": 8.813427340239286} +{"Pretrain/Learning Rate": 1.7522062891304936e-05, "Pretrain/Loss": 2.047147274017334, "Pretrain/Loss (Raw)": 1.8997225761413574, "Pretrain/Step": 5806, "Pretrain/Step Time": 8.813380420207977} +{"Pretrain/Learning Rate": 1.7513962147403057e-05, "Pretrain/Loss": 2.0477852821350098, "Pretrain/Loss (Raw)": 2.0859451293945312, "Pretrain/Step": 5807, "Pretrain/Step Time": 8.813692839816213} +{"Pretrain/Learning Rate": 1.750586226682634e-05, "Pretrain/Loss": 2.045830726623535, "Pretrain/Loss (Raw)": 1.8538068532943726, "Pretrain/Step": 5808, "Pretrain/Step Time": 8.813663739711046} +{"Pretrain/Learning Rate": 1.74977632505089e-05, "Pretrain/Loss": 2.046635866165161, "Pretrain/Loss (Raw)": 1.9861111640930176, "Pretrain/Step": 5809, "Pretrain/Step Time": 8.810282673686743} +{"Pretrain/Learning Rate": 1.7489665099384755e-05, "Pretrain/Loss": 2.0469493865966797, "Pretrain/Loss (Raw)": 2.047084093093872, "Pretrain/Step": 5810, "Pretrain/Step Time": 8.809365950524807} +{"Pretrain/Learning Rate": 1.7481567814387815e-05, "Pretrain/Loss": 2.044875383377075, "Pretrain/Loss (Raw)": 2.0040266513824463, "Pretrain/Step": 5811, "Pretrain/Step Time": 8.806545754894614} +{"Pretrain/Learning Rate": 1.7473471396451913e-05, "Pretrain/Loss": 2.045393943786621, "Pretrain/Loss (Raw)": 2.0736119747161865, "Pretrain/Step": 5812, "Pretrain/Step Time": 8.81017973460257} +{"Pretrain/Learning Rate": 1.746537584651074e-05, "Pretrain/Loss": 2.046495199203491, "Pretrain/Loss (Raw)": 2.099163770675659, "Pretrain/Step": 5813, "Pretrain/Step Time": 8.806657746434212} +{"Pretrain/Learning Rate": 1.7457281165497947e-05, "Pretrain/Loss": 2.045459747314453, "Pretrain/Loss (Raw)": 1.999144196510315, "Pretrain/Step": 5814, "Pretrain/Step Time": 8.809410097077489} +{"Pretrain/Learning Rate": 1.7449187354347014e-05, "Pretrain/Loss": 2.0458900928497314, "Pretrain/Loss (Raw)": 1.9181981086730957, "Pretrain/Step": 5815, "Pretrain/Step Time": 8.807959081605077} +{"Pretrain/Learning Rate": 1.7441094413991393e-05, "Pretrain/Loss": 2.0455517768859863, "Pretrain/Loss (Raw)": 2.095388889312744, "Pretrain/Step": 5816, "Pretrain/Step Time": 8.80073924548924} +{"Pretrain/Learning Rate": 1.7433002345364368e-05, "Pretrain/Loss": 2.045778512954712, "Pretrain/Loss (Raw)": 1.9878733158111572, "Pretrain/Step": 5817, "Pretrain/Step Time": 8.803186168894172} +{"Pretrain/Learning Rate": 1.7424911149399183e-05, "Pretrain/Loss": 2.047224283218384, "Pretrain/Loss (Raw)": 2.059174060821533, "Pretrain/Step": 5818, "Pretrain/Step Time": 8.805179804563522} +{"Pretrain/Learning Rate": 1.7416820827028926e-05, "Pretrain/Loss": 2.046049118041992, "Pretrain/Loss (Raw)": 2.0340137481689453, "Pretrain/Step": 5819, "Pretrain/Step Time": 8.801528414711356} +{"Pretrain/Learning Rate": 1.7408731379186638e-05, "Pretrain/Loss": 2.0453004837036133, "Pretrain/Loss (Raw)": 2.0256495475769043, "Pretrain/Step": 5820, "Pretrain/Step Time": 8.801728570833802} +{"Pretrain/Learning Rate": 1.740064280680521e-05, "Pretrain/Loss": 2.043839693069458, "Pretrain/Loss (Raw)": 1.9746941328048706, "Pretrain/Step": 5821, "Pretrain/Step Time": 8.797903470695019} +{"Pretrain/Learning Rate": 1.7392555110817467e-05, "Pretrain/Loss": 2.042180299758911, "Pretrain/Loss (Raw)": 1.976822853088379, "Pretrain/Step": 5822, "Pretrain/Step Time": 8.794467130675912} +{"Pretrain/Learning Rate": 1.738446829215611e-05, "Pretrain/Loss": 2.043309211730957, "Pretrain/Loss (Raw)": 2.031237840652466, "Pretrain/Step": 5823, "Pretrain/Step Time": 8.792557818815112} +{"Pretrain/Learning Rate": 1.737638235175376e-05, "Pretrain/Loss": 2.042525291442871, "Pretrain/Loss (Raw)": 2.075434923171997, "Pretrain/Step": 5824, "Pretrain/Step Time": 8.793694946914911} +{"Pretrain/Learning Rate": 1.736829729054292e-05, "Pretrain/Loss": 2.0449676513671875, "Pretrain/Loss (Raw)": 2.105696678161621, "Pretrain/Step": 5825, "Pretrain/Step Time": 8.792927220463753} +{"Pretrain/Learning Rate": 1.7360213109456e-05, "Pretrain/Loss": 2.045821189880371, "Pretrain/Loss (Raw)": 2.1353609561920166, "Pretrain/Step": 5826, "Pretrain/Step Time": 8.790102427825332} +{"Pretrain/Learning Rate": 1.73521298094253e-05, "Pretrain/Loss": 2.0460739135742188, "Pretrain/Loss (Raw)": 2.1019694805145264, "Pretrain/Step": 5827, "Pretrain/Step Time": 8.794153966009617} +{"Pretrain/Learning Rate": 1.734404739138303e-05, "Pretrain/Loss": 2.046427011489868, "Pretrain/Loss (Raw)": 2.0098888874053955, "Pretrain/Step": 5828, "Pretrain/Step Time": 8.793056707829237} +{"Pretrain/Learning Rate": 1.733596585626129e-05, "Pretrain/Loss": 2.047153949737549, "Pretrain/Loss (Raw)": 1.9682254791259766, "Pretrain/Step": 5829, "Pretrain/Step Time": 8.79187361896038} +{"Pretrain/Learning Rate": 1.7327885204992083e-05, "Pretrain/Loss": 2.0480802059173584, "Pretrain/Loss (Raw)": 2.1003713607788086, "Pretrain/Step": 5830, "Pretrain/Step Time": 8.792685015127063} +{"Pretrain/Learning Rate": 1.7319805438507303e-05, "Pretrain/Loss": 2.0481739044189453, "Pretrain/Loss (Raw)": 2.05198335647583, "Pretrain/Step": 5831, "Pretrain/Step Time": 8.791859321296215} +{"Pretrain/Learning Rate": 1.7311726557738754e-05, "Pretrain/Loss": 2.046175479888916, "Pretrain/Loss (Raw)": 1.7584251165390015, "Pretrain/Step": 5832, "Pretrain/Step Time": 8.78545163758099} +{"Pretrain/Learning Rate": 1.7303648563618125e-05, "Pretrain/Loss": 2.0473833084106445, "Pretrain/Loss (Raw)": 2.1330301761627197, "Pretrain/Step": 5833, "Pretrain/Step Time": 8.787299744784832} +{"Pretrain/Learning Rate": 1.7295571457077015e-05, "Pretrain/Loss": 2.049497604370117, "Pretrain/Loss (Raw)": 2.2098422050476074, "Pretrain/Step": 5834, "Pretrain/Step Time": 8.787977335974574} +{"Pretrain/Learning Rate": 1.72874952390469e-05, "Pretrain/Loss": 2.049772262573242, "Pretrain/Loss (Raw)": 1.938071608543396, "Pretrain/Step": 5835, "Pretrain/Step Time": 8.788557855412364} +{"Pretrain/Learning Rate": 1.7279419910459182e-05, "Pretrain/Loss": 2.0494134426116943, "Pretrain/Loss (Raw)": 1.9038108587265015, "Pretrain/Step": 5836, "Pretrain/Step Time": 8.786871479824185} +{"Pretrain/Learning Rate": 1.727134547224514e-05, "Pretrain/Loss": 2.0452239513397217, "Pretrain/Loss (Raw)": 1.5782995223999023, "Pretrain/Step": 5837, "Pretrain/Step Time": 8.795449022203684} +{"Pretrain/Learning Rate": 1.726327192533595e-05, "Pretrain/Loss": 2.0469493865966797, "Pretrain/Loss (Raw)": 1.984555721282959, "Pretrain/Step": 5838, "Pretrain/Step Time": 8.794966071844101} +{"Pretrain/Learning Rate": 1.7255199270662708e-05, "Pretrain/Loss": 2.0451858043670654, "Pretrain/Loss (Raw)": 1.903537631034851, "Pretrain/Step": 5839, "Pretrain/Step Time": 8.788031961768866} +{"Pretrain/Learning Rate": 1.7247127509156377e-05, "Pretrain/Loss": 2.045504570007324, "Pretrain/Loss (Raw)": 2.0672178268432617, "Pretrain/Step": 5840, "Pretrain/Step Time": 8.78998700901866} +{"Pretrain/Learning Rate": 1.7239056641747836e-05, "Pretrain/Loss": 2.0415737628936768, "Pretrain/Loss (Raw)": 1.7162456512451172, "Pretrain/Step": 5841, "Pretrain/Step Time": 8.790862444788218} +{"Pretrain/Learning Rate": 1.723098666936785e-05, "Pretrain/Loss": 2.040982723236084, "Pretrain/Loss (Raw)": 2.053058624267578, "Pretrain/Step": 5842, "Pretrain/Step Time": 8.793415633961558} +{"Pretrain/Learning Rate": 1.7222917592947096e-05, "Pretrain/Loss": 2.043947219848633, "Pretrain/Loss (Raw)": 2.2131502628326416, "Pretrain/Step": 5843, "Pretrain/Step Time": 8.793198069557548} +{"Pretrain/Learning Rate": 1.7214849413416128e-05, "Pretrain/Loss": 2.0430991649627686, "Pretrain/Loss (Raw)": 2.0466649532318115, "Pretrain/Step": 5844, "Pretrain/Step Time": 8.797802187502384} +{"Pretrain/Learning Rate": 1.7206782131705414e-05, "Pretrain/Loss": 2.042980194091797, "Pretrain/Loss (Raw)": 2.0442049503326416, "Pretrain/Step": 5845, "Pretrain/Step Time": 8.798768933862448} +{"Pretrain/Learning Rate": 1.7198715748745304e-05, "Pretrain/Loss": 2.0416619777679443, "Pretrain/Loss (Raw)": 1.8240998983383179, "Pretrain/Step": 5846, "Pretrain/Step Time": 8.795855794101954} +{"Pretrain/Learning Rate": 1.7190650265466056e-05, "Pretrain/Loss": 2.0424628257751465, "Pretrain/Loss (Raw)": 2.14497447013855, "Pretrain/Step": 5847, "Pretrain/Step Time": 8.79537401907146} +{"Pretrain/Learning Rate": 1.7182585682797815e-05, "Pretrain/Loss": 2.0434794425964355, "Pretrain/Loss (Raw)": 2.1828854084014893, "Pretrain/Step": 5848, "Pretrain/Step Time": 8.795901704579592} +{"Pretrain/Learning Rate": 1.7174522001670633e-05, "Pretrain/Loss": 2.0432605743408203, "Pretrain/Loss (Raw)": 2.09576153755188, "Pretrain/Step": 5849, "Pretrain/Step Time": 8.799971615895629} +{"Pretrain/Learning Rate": 1.7166459223014448e-05, "Pretrain/Loss": 2.0440733432769775, "Pretrain/Loss (Raw)": 2.039796829223633, "Pretrain/Step": 5850, "Pretrain/Step Time": 8.805645758286119} +{"Pretrain/Learning Rate": 1.71583973477591e-05, "Pretrain/Loss": 2.0444021224975586, "Pretrain/Loss (Raw)": 2.212397813796997, "Pretrain/Step": 5851, "Pretrain/Step Time": 8.80592718347907} +{"Pretrain/Learning Rate": 1.7150336376834315e-05, "Pretrain/Loss": 2.044095516204834, "Pretrain/Loss (Raw)": 1.9720799922943115, "Pretrain/Step": 5852, "Pretrain/Step Time": 8.804391384124756} +{"Pretrain/Learning Rate": 1.714227631116974e-05, "Pretrain/Loss": 2.042210578918457, "Pretrain/Loss (Raw)": 1.850317120552063, "Pretrain/Step": 5853, "Pretrain/Step Time": 8.801052790135145} +{"Pretrain/Learning Rate": 1.7134217151694872e-05, "Pretrain/Loss": 2.0431320667266846, "Pretrain/Loss (Raw)": 2.116497755050659, "Pretrain/Step": 5854, "Pretrain/Step Time": 8.803744273260236} +{"Pretrain/Learning Rate": 1.7126158899339164e-05, "Pretrain/Loss": 2.042005777359009, "Pretrain/Loss (Raw)": 2.0378925800323486, "Pretrain/Step": 5855, "Pretrain/Step Time": 8.804339976981282} +{"Pretrain/Learning Rate": 1.7118101555031895e-05, "Pretrain/Loss": 2.041327953338623, "Pretrain/Loss (Raw)": 2.0473995208740234, "Pretrain/Step": 5856, "Pretrain/Step Time": 8.801809530705214} +{"Pretrain/Learning Rate": 1.7110045119702314e-05, "Pretrain/Loss": 2.0400850772857666, "Pretrain/Loss (Raw)": 1.866415023803711, "Pretrain/Step": 5857, "Pretrain/Step Time": 8.803428897634149} +{"Pretrain/Learning Rate": 1.7101989594279495e-05, "Pretrain/Loss": 2.038686752319336, "Pretrain/Loss (Raw)": 2.109884738922119, "Pretrain/Step": 5858, "Pretrain/Step Time": 8.797489985823631} +{"Pretrain/Learning Rate": 1.7093934979692465e-05, "Pretrain/Loss": 2.0375349521636963, "Pretrain/Loss (Raw)": 1.754823923110962, "Pretrain/Step": 5859, "Pretrain/Step Time": 8.807394348084927} +{"Pretrain/Learning Rate": 1.7085881276870093e-05, "Pretrain/Loss": 2.0375537872314453, "Pretrain/Loss (Raw)": 1.9861270189285278, "Pretrain/Step": 5860, "Pretrain/Step Time": 8.810374356806278} +{"Pretrain/Learning Rate": 1.70778284867412e-05, "Pretrain/Loss": 2.0374755859375, "Pretrain/Loss (Raw)": 1.9231945276260376, "Pretrain/Step": 5861, "Pretrain/Step Time": 8.801756447181106} +{"Pretrain/Learning Rate": 1.706977661023444e-05, "Pretrain/Loss": 2.0336742401123047, "Pretrain/Loss (Raw)": 1.9198962450027466, "Pretrain/Step": 5862, "Pretrain/Step Time": 8.803120901808143} +{"Pretrain/Learning Rate": 1.7061725648278423e-05, "Pretrain/Loss": 2.032109260559082, "Pretrain/Loss (Raw)": 2.08410906791687, "Pretrain/Step": 5863, "Pretrain/Step Time": 8.80146947875619} +{"Pretrain/Learning Rate": 1.7053675601801606e-05, "Pretrain/Loss": 2.0327813625335693, "Pretrain/Loss (Raw)": 1.8451626300811768, "Pretrain/Step": 5864, "Pretrain/Step Time": 8.800465470179915} +{"Pretrain/Learning Rate": 1.7045626471732363e-05, "Pretrain/Loss": 2.031440496444702, "Pretrain/Loss (Raw)": 1.858778715133667, "Pretrain/Step": 5865, "Pretrain/Step Time": 8.801804717630148} +{"Pretrain/Learning Rate": 1.7037578258998956e-05, "Pretrain/Loss": 2.0321907997131348, "Pretrain/Loss (Raw)": 2.0527350902557373, "Pretrain/Step": 5866, "Pretrain/Step Time": 8.804953632876277} +{"Pretrain/Learning Rate": 1.702953096452955e-05, "Pretrain/Loss": 2.030322551727295, "Pretrain/Loss (Raw)": 2.042912721633911, "Pretrain/Step": 5867, "Pretrain/Step Time": 8.805174365639687} +{"Pretrain/Learning Rate": 1.702148458925218e-05, "Pretrain/Loss": 2.0315845012664795, "Pretrain/Loss (Raw)": 1.9136489629745483, "Pretrain/Step": 5868, "Pretrain/Step Time": 8.801535399630666} +{"Pretrain/Learning Rate": 1.7013439134094815e-05, "Pretrain/Loss": 2.0291295051574707, "Pretrain/Loss (Raw)": 1.8619236946105957, "Pretrain/Step": 5869, "Pretrain/Step Time": 8.80346623621881} +{"Pretrain/Learning Rate": 1.7005394599985273e-05, "Pretrain/Loss": 2.0280051231384277, "Pretrain/Loss (Raw)": 1.960025429725647, "Pretrain/Step": 5870, "Pretrain/Step Time": 8.801783107221127} +{"Pretrain/Learning Rate": 1.6997350987851308e-05, "Pretrain/Loss": 2.0301461219787598, "Pretrain/Loss (Raw)": 2.1250360012054443, "Pretrain/Step": 5871, "Pretrain/Step Time": 8.802070837467909} +{"Pretrain/Learning Rate": 1.6989308298620526e-05, "Pretrain/Loss": 2.029304027557373, "Pretrain/Loss (Raw)": 2.0866878032684326, "Pretrain/Step": 5872, "Pretrain/Step Time": 8.790222577750683} +{"Pretrain/Learning Rate": 1.6981266533220467e-05, "Pretrain/Loss": 2.028247594833374, "Pretrain/Loss (Raw)": 2.077843189239502, "Pretrain/Step": 5873, "Pretrain/Step Time": 8.799296477809548} +{"Pretrain/Learning Rate": 1.6973225692578533e-05, "Pretrain/Loss": 2.0276427268981934, "Pretrain/Loss (Raw)": 2.229450225830078, "Pretrain/Step": 5874, "Pretrain/Step Time": 8.802850227802992} +{"Pretrain/Learning Rate": 1.6965185777622037e-05, "Pretrain/Loss": 2.028459072113037, "Pretrain/Loss (Raw)": 1.9926246404647827, "Pretrain/Step": 5875, "Pretrain/Step Time": 8.799990369006991} +{"Pretrain/Learning Rate": 1.6957146789278175e-05, "Pretrain/Loss": 2.0288867950439453, "Pretrain/Loss (Raw)": 2.0551726818084717, "Pretrain/Step": 5876, "Pretrain/Step Time": 8.799767388030887} +{"Pretrain/Learning Rate": 1.694910872847405e-05, "Pretrain/Loss": 2.029618740081787, "Pretrain/Loss (Raw)": 2.2128372192382812, "Pretrain/Step": 5877, "Pretrain/Step Time": 8.800671888515353} +{"Pretrain/Learning Rate": 1.694107159613664e-05, "Pretrain/Loss": 2.026066303253174, "Pretrain/Loss (Raw)": 1.7155144214630127, "Pretrain/Step": 5878, "Pretrain/Step Time": 8.800337797030807} +{"Pretrain/Learning Rate": 1.6933035393192824e-05, "Pretrain/Loss": 2.0267534255981445, "Pretrain/Loss (Raw)": 2.225552558898926, "Pretrain/Step": 5879, "Pretrain/Step Time": 8.79842372611165} +{"Pretrain/Learning Rate": 1.6925000120569385e-05, "Pretrain/Loss": 2.026221752166748, "Pretrain/Loss (Raw)": 2.0238027572631836, "Pretrain/Step": 5880, "Pretrain/Step Time": 8.809828048571944} +{"Pretrain/Learning Rate": 1.6916965779192983e-05, "Pretrain/Loss": 2.0272343158721924, "Pretrain/Loss (Raw)": 2.014585494995117, "Pretrain/Step": 5881, "Pretrain/Step Time": 8.804078912362456} +{"Pretrain/Learning Rate": 1.6908932369990176e-05, "Pretrain/Loss": 2.028468608856201, "Pretrain/Loss (Raw)": 2.0970184803009033, "Pretrain/Step": 5882, "Pretrain/Step Time": 8.807286158204079} +{"Pretrain/Learning Rate": 1.6900899893887408e-05, "Pretrain/Loss": 2.026909828186035, "Pretrain/Loss (Raw)": 1.9470860958099365, "Pretrain/Step": 5883, "Pretrain/Step Time": 8.804402500391006} +{"Pretrain/Learning Rate": 1.6892868351811036e-05, "Pretrain/Loss": 2.028139114379883, "Pretrain/Loss (Raw)": 2.2174181938171387, "Pretrain/Step": 5884, "Pretrain/Step Time": 8.803543405607343} +{"Pretrain/Learning Rate": 1.6884837744687284e-05, "Pretrain/Loss": 2.0326881408691406, "Pretrain/Loss (Raw)": 2.509136199951172, "Pretrain/Step": 5885, "Pretrain/Step Time": 8.801451517269015} +{"Pretrain/Learning Rate": 1.687680807344229e-05, "Pretrain/Loss": 2.0327067375183105, "Pretrain/Loss (Raw)": 2.0558390617370605, "Pretrain/Step": 5886, "Pretrain/Step Time": 8.800722559913993} +{"Pretrain/Learning Rate": 1.6868779339002056e-05, "Pretrain/Loss": 2.0317230224609375, "Pretrain/Loss (Raw)": 1.8025357723236084, "Pretrain/Step": 5887, "Pretrain/Step Time": 8.802932731807232} +{"Pretrain/Learning Rate": 1.6860751542292515e-05, "Pretrain/Loss": 2.0290651321411133, "Pretrain/Loss (Raw)": 1.9555978775024414, "Pretrain/Step": 5888, "Pretrain/Step Time": 8.803180938586593} +{"Pretrain/Learning Rate": 1.685272468423945e-05, "Pretrain/Loss": 2.028090238571167, "Pretrain/Loss (Raw)": 1.8887923955917358, "Pretrain/Step": 5889, "Pretrain/Step Time": 8.804128382354975} +{"Pretrain/Learning Rate": 1.6844698765768575e-05, "Pretrain/Loss": 2.0275931358337402, "Pretrain/Loss (Raw)": 2.1316378116607666, "Pretrain/Step": 5890, "Pretrain/Step Time": 8.809580689296126} +{"Pretrain/Learning Rate": 1.6836673787805456e-05, "Pretrain/Loss": 2.027343988418579, "Pretrain/Loss (Raw)": 2.020679235458374, "Pretrain/Step": 5891, "Pretrain/Step Time": 8.80938103236258} +{"Pretrain/Learning Rate": 1.6828649751275592e-05, "Pretrain/Loss": 2.026798963546753, "Pretrain/Loss (Raw)": 2.0409412384033203, "Pretrain/Step": 5892, "Pretrain/Step Time": 8.80896496027708} +{"Pretrain/Learning Rate": 1.682062665710434e-05, "Pretrain/Loss": 2.0271389484405518, "Pretrain/Loss (Raw)": 2.037339448928833, "Pretrain/Step": 5893, "Pretrain/Step Time": 8.812123328447342} +{"Pretrain/Learning Rate": 1.6812604506216966e-05, "Pretrain/Loss": 2.0274264812469482, "Pretrain/Loss (Raw)": 2.109187126159668, "Pretrain/Step": 5894, "Pretrain/Step Time": 8.814259085804224} +{"Pretrain/Learning Rate": 1.6804583299538614e-05, "Pretrain/Loss": 2.0273284912109375, "Pretrain/Loss (Raw)": 2.0705058574676514, "Pretrain/Step": 5895, "Pretrain/Step Time": 8.81531093083322} +{"Pretrain/Learning Rate": 1.6796563037994347e-05, "Pretrain/Loss": 2.0274338722229004, "Pretrain/Loss (Raw)": 1.8908238410949707, "Pretrain/Step": 5896, "Pretrain/Step Time": 8.812648870050907} +{"Pretrain/Learning Rate": 1.678854372250907e-05, "Pretrain/Loss": 2.026682138442993, "Pretrain/Loss (Raw)": 2.0882408618927, "Pretrain/Step": 5897, "Pretrain/Step Time": 8.812933012843132} +{"Pretrain/Learning Rate": 1.6780525354007644e-05, "Pretrain/Loss": 2.027132511138916, "Pretrain/Loss (Raw)": 2.0900683403015137, "Pretrain/Step": 5898, "Pretrain/Step Time": 8.80596848577261} +{"Pretrain/Learning Rate": 1.6772507933414744e-05, "Pretrain/Loss": 2.0298256874084473, "Pretrain/Loss (Raw)": 2.087435483932495, "Pretrain/Step": 5899, "Pretrain/Step Time": 8.80242889560759} +{"Pretrain/Learning Rate": 1.6764491461655017e-05, "Pretrain/Loss": 2.0323386192321777, "Pretrain/Loss (Raw)": 2.2257800102233887, "Pretrain/Step": 5900, "Pretrain/Step Time": 8.803056620061398} +{"Pretrain/Learning Rate": 1.6756475939652927e-05, "Pretrain/Loss": 2.0363807678222656, "Pretrain/Loss (Raw)": 2.255441904067993, "Pretrain/Step": 5901, "Pretrain/Step Time": 8.80771704018116} +{"Pretrain/Learning Rate": 1.674846136833289e-05, "Pretrain/Loss": 2.0389060974121094, "Pretrain/Loss (Raw)": 2.4260523319244385, "Pretrain/Step": 5902, "Pretrain/Step Time": 8.798705399036407} +{"Pretrain/Learning Rate": 1.6740447748619156e-05, "Pretrain/Loss": 2.038928508758545, "Pretrain/Loss (Raw)": 2.049149513244629, "Pretrain/Step": 5903, "Pretrain/Step Time": 8.79865805990994} +{"Pretrain/Learning Rate": 1.6732435081435924e-05, "Pretrain/Loss": 2.0376152992248535, "Pretrain/Loss (Raw)": 1.9246371984481812, "Pretrain/Step": 5904, "Pretrain/Step Time": 8.803585734218359} +{"Pretrain/Learning Rate": 1.6724423367707226e-05, "Pretrain/Loss": 2.037686347961426, "Pretrain/Loss (Raw)": 2.065297842025757, "Pretrain/Step": 5905, "Pretrain/Step Time": 8.791910881176591} +{"Pretrain/Learning Rate": 1.6716412608357024e-05, "Pretrain/Loss": 2.0383262634277344, "Pretrain/Loss (Raw)": 2.0024478435516357, "Pretrain/Step": 5906, "Pretrain/Step Time": 8.796066073700786} +{"Pretrain/Learning Rate": 1.670840280430915e-05, "Pretrain/Loss": 2.0358967781066895, "Pretrain/Loss (Raw)": 1.8815490007400513, "Pretrain/Step": 5907, "Pretrain/Step Time": 8.796259930357337} +{"Pretrain/Learning Rate": 1.6700393956487342e-05, "Pretrain/Loss": 2.0355305671691895, "Pretrain/Loss (Raw)": 1.9160404205322266, "Pretrain/Step": 5908, "Pretrain/Step Time": 8.80468918941915} +{"Pretrain/Learning Rate": 1.6692386065815203e-05, "Pretrain/Loss": 2.0348877906799316, "Pretrain/Loss (Raw)": 1.9960685968399048, "Pretrain/Step": 5909, "Pretrain/Step Time": 8.796805262565613} +{"Pretrain/Learning Rate": 1.668437913321626e-05, "Pretrain/Loss": 2.0353264808654785, "Pretrain/Loss (Raw)": 2.012864828109741, "Pretrain/Step": 5910, "Pretrain/Step Time": 8.797254230827093} +{"Pretrain/Learning Rate": 1.667637315961389e-05, "Pretrain/Loss": 2.0362792015075684, "Pretrain/Loss (Raw)": 2.0495243072509766, "Pretrain/Step": 5911, "Pretrain/Step Time": 8.79732863418758} +{"Pretrain/Learning Rate": 1.6668368145931397e-05, "Pretrain/Loss": 2.040228843688965, "Pretrain/Loss (Raw)": 2.4429142475128174, "Pretrain/Step": 5912, "Pretrain/Step Time": 8.796722635626793} +{"Pretrain/Learning Rate": 1.6660364093091945e-05, "Pretrain/Loss": 2.0336904525756836, "Pretrain/Loss (Raw)": 1.4458407163619995, "Pretrain/Step": 5913, "Pretrain/Step Time": 8.795734260231256} +{"Pretrain/Learning Rate": 1.6652361002018608e-05, "Pretrain/Loss": 2.033379554748535, "Pretrain/Loss (Raw)": 2.105750322341919, "Pretrain/Step": 5914, "Pretrain/Step Time": 8.797265600413084} +{"Pretrain/Learning Rate": 1.664435887363433e-05, "Pretrain/Loss": 2.034357786178589, "Pretrain/Loss (Raw)": 2.1800456047058105, "Pretrain/Step": 5915, "Pretrain/Step Time": 8.80748437717557} +{"Pretrain/Learning Rate": 1.6636357708861966e-05, "Pretrain/Loss": 2.035381317138672, "Pretrain/Loss (Raw)": 2.1689889430999756, "Pretrain/Step": 5916, "Pretrain/Step Time": 8.80154306255281} +{"Pretrain/Learning Rate": 1.6628357508624234e-05, "Pretrain/Loss": 2.0327768325805664, "Pretrain/Loss (Raw)": 1.8917919397354126, "Pretrain/Step": 5917, "Pretrain/Step Time": 8.79887717962265} +{"Pretrain/Learning Rate": 1.662035827384377e-05, "Pretrain/Loss": 2.0316030979156494, "Pretrain/Loss (Raw)": 1.9378283023834229, "Pretrain/Step": 5918, "Pretrain/Step Time": 8.799550687894225} +{"Pretrain/Learning Rate": 1.661236000544307e-05, "Pretrain/Loss": 2.0307979583740234, "Pretrain/Loss (Raw)": 1.9154536724090576, "Pretrain/Step": 5919, "Pretrain/Step Time": 8.795293312519789} +{"Pretrain/Learning Rate": 1.660436270434454e-05, "Pretrain/Loss": 2.0306992530822754, "Pretrain/Loss (Raw)": 1.9719659090042114, "Pretrain/Step": 5920, "Pretrain/Step Time": 8.797401886433363} +{"Pretrain/Learning Rate": 1.6596366371470466e-05, "Pretrain/Loss": 2.031954765319824, "Pretrain/Loss (Raw)": 2.2270216941833496, "Pretrain/Step": 5921, "Pretrain/Step Time": 8.79361466318369} +{"Pretrain/Learning Rate": 1.658837100774302e-05, "Pretrain/Loss": 2.031670093536377, "Pretrain/Loss (Raw)": 1.9892953634262085, "Pretrain/Step": 5922, "Pretrain/Step Time": 8.792543085291982} +{"Pretrain/Learning Rate": 1.658037661408427e-05, "Pretrain/Loss": 2.032553195953369, "Pretrain/Loss (Raw)": 2.0922417640686035, "Pretrain/Step": 5923, "Pretrain/Step Time": 8.799155566841364} +{"Pretrain/Learning Rate": 1.657238319141616e-05, "Pretrain/Loss": 2.031526565551758, "Pretrain/Loss (Raw)": 2.0246944427490234, "Pretrain/Step": 5924, "Pretrain/Step Time": 8.799124360084534} +{"Pretrain/Learning Rate": 1.656439074066053e-05, "Pretrain/Loss": 2.029900074005127, "Pretrain/Loss (Raw)": 2.0580928325653076, "Pretrain/Step": 5925, "Pretrain/Step Time": 8.794140174984932} +{"Pretrain/Learning Rate": 1.655639926273911e-05, "Pretrain/Loss": 2.029953956604004, "Pretrain/Loss (Raw)": 2.1432242393493652, "Pretrain/Step": 5926, "Pretrain/Step Time": 8.799098454415798} +{"Pretrain/Learning Rate": 1.654840875857352e-05, "Pretrain/Loss": 2.0275096893310547, "Pretrain/Loss (Raw)": 1.839210033416748, "Pretrain/Step": 5927, "Pretrain/Step Time": 8.798788083717227} +{"Pretrain/Learning Rate": 1.654041922908525e-05, "Pretrain/Loss": 2.023658275604248, "Pretrain/Loss (Raw)": 1.9847676753997803, "Pretrain/Step": 5928, "Pretrain/Step Time": 8.796319426968694} +{"Pretrain/Learning Rate": 1.6532430675195705e-05, "Pretrain/Loss": 2.0251853466033936, "Pretrain/Loss (Raw)": 2.206709623336792, "Pretrain/Step": 5929, "Pretrain/Step Time": 8.787290500476956} +{"Pretrain/Learning Rate": 1.652444309782615e-05, "Pretrain/Loss": 2.0262527465820312, "Pretrain/Loss (Raw)": 2.221635103225708, "Pretrain/Step": 5930, "Pretrain/Step Time": 8.798930142074823} +{"Pretrain/Learning Rate": 1.651645649789776e-05, "Pretrain/Loss": 2.0241212844848633, "Pretrain/Loss (Raw)": 1.8262940645217896, "Pretrain/Step": 5931, "Pretrain/Step Time": 8.799434281885624} +{"Pretrain/Learning Rate": 1.6508470876331577e-05, "Pretrain/Loss": 2.0254154205322266, "Pretrain/Loss (Raw)": 1.9845644235610962, "Pretrain/Step": 5932, "Pretrain/Step Time": 8.797877579927444} +{"Pretrain/Learning Rate": 1.650048623404855e-05, "Pretrain/Loss": 2.02547025680542, "Pretrain/Loss (Raw)": 2.043164014816284, "Pretrain/Step": 5933, "Pretrain/Step Time": 8.799849428236485} +{"Pretrain/Learning Rate": 1.6492502571969498e-05, "Pretrain/Loss": 2.026860237121582, "Pretrain/Loss (Raw)": 2.077609062194824, "Pretrain/Step": 5934, "Pretrain/Step Time": 8.799392422661185} +{"Pretrain/Learning Rate": 1.6484519891015143e-05, "Pretrain/Loss": 2.0256853103637695, "Pretrain/Loss (Raw)": 1.9355852603912354, "Pretrain/Step": 5935, "Pretrain/Step Time": 8.804325936362147} +{"Pretrain/Learning Rate": 1.647653819210607e-05, "Pretrain/Loss": 2.028146743774414, "Pretrain/Loss (Raw)": 2.1688756942749023, "Pretrain/Step": 5936, "Pretrain/Step Time": 8.80464736931026} +{"Pretrain/Learning Rate": 1.6468557476162793e-05, "Pretrain/Loss": 2.0289618968963623, "Pretrain/Loss (Raw)": 2.090456008911133, "Pretrain/Step": 5937, "Pretrain/Step Time": 8.81108339689672} +{"Pretrain/Learning Rate": 1.6460577744105654e-05, "Pretrain/Loss": 2.0289392471313477, "Pretrain/Loss (Raw)": 2.0441603660583496, "Pretrain/Step": 5938, "Pretrain/Step Time": 8.810048021376133} +{"Pretrain/Learning Rate": 1.6452598996854943e-05, "Pretrain/Loss": 2.03106689453125, "Pretrain/Loss (Raw)": 2.2763874530792236, "Pretrain/Step": 5939, "Pretrain/Step Time": 8.809518048539758} +{"Pretrain/Learning Rate": 1.6444621235330777e-05, "Pretrain/Loss": 2.0306904315948486, "Pretrain/Loss (Raw)": 2.025407075881958, "Pretrain/Step": 5940, "Pretrain/Step Time": 8.809422127902508} +{"Pretrain/Learning Rate": 1.6436644460453217e-05, "Pretrain/Loss": 2.0319108963012695, "Pretrain/Loss (Raw)": 2.2553930282592773, "Pretrain/Step": 5941, "Pretrain/Step Time": 8.807484259828925} +{"Pretrain/Learning Rate": 1.642866867314216e-05, "Pretrain/Loss": 2.036196708679199, "Pretrain/Loss (Raw)": 2.547732353210449, "Pretrain/Step": 5942, "Pretrain/Step Time": 8.8077974896878} +{"Pretrain/Learning Rate": 1.642069387431743e-05, "Pretrain/Loss": 2.0370144844055176, "Pretrain/Loss (Raw)": 2.0228490829467773, "Pretrain/Step": 5943, "Pretrain/Step Time": 8.808730065822601} +{"Pretrain/Learning Rate": 1.64127200648987e-05, "Pretrain/Loss": 2.033958911895752, "Pretrain/Loss (Raw)": 1.7043107748031616, "Pretrain/Step": 5944, "Pretrain/Step Time": 8.804671565070748} +{"Pretrain/Learning Rate": 1.6404747245805567e-05, "Pretrain/Loss": 2.0340347290039062, "Pretrain/Loss (Raw)": 1.9975873231887817, "Pretrain/Step": 5945, "Pretrain/Step Time": 8.807461140677333} +{"Pretrain/Learning Rate": 1.6396775417957478e-05, "Pretrain/Loss": 2.0344772338867188, "Pretrain/Loss (Raw)": 2.1157801151275635, "Pretrain/Step": 5946, "Pretrain/Step Time": 8.808122348040342} +{"Pretrain/Learning Rate": 1.6388804582273788e-05, "Pretrain/Loss": 2.033217668533325, "Pretrain/Loss (Raw)": 1.8727967739105225, "Pretrain/Step": 5947, "Pretrain/Step Time": 8.806582299992442} +{"Pretrain/Learning Rate": 1.6380834739673727e-05, "Pretrain/Loss": 2.0330348014831543, "Pretrain/Loss (Raw)": 2.002255439758301, "Pretrain/Step": 5948, "Pretrain/Step Time": 8.804240576922894} +{"Pretrain/Learning Rate": 1.6372865891076426e-05, "Pretrain/Loss": 2.0351476669311523, "Pretrain/Loss (Raw)": 2.2451326847076416, "Pretrain/Step": 5949, "Pretrain/Step Time": 8.804401190951467} +{"Pretrain/Learning Rate": 1.6364898037400876e-05, "Pretrain/Loss": 2.036350727081299, "Pretrain/Loss (Raw)": 2.13081693649292, "Pretrain/Step": 5950, "Pretrain/Step Time": 8.810044512152672} +{"Pretrain/Learning Rate": 1.6356931179565978e-05, "Pretrain/Loss": 2.037440299987793, "Pretrain/Loss (Raw)": 2.17069411277771, "Pretrain/Step": 5951, "Pretrain/Step Time": 8.813368329778314} +{"Pretrain/Learning Rate": 1.63489653184905e-05, "Pretrain/Loss": 2.037721872329712, "Pretrain/Loss (Raw)": 2.1114823818206787, "Pretrain/Step": 5952, "Pretrain/Step Time": 8.811782045289874} +{"Pretrain/Learning Rate": 1.6341000455093115e-05, "Pretrain/Loss": 2.036604404449463, "Pretrain/Loss (Raw)": 1.962664008140564, "Pretrain/Step": 5953, "Pretrain/Step Time": 8.814226737245917} +{"Pretrain/Learning Rate": 1.633303659029235e-05, "Pretrain/Loss": 2.036947727203369, "Pretrain/Loss (Raw)": 2.1793100833892822, "Pretrain/Step": 5954, "Pretrain/Step Time": 8.81575970351696} +{"Pretrain/Learning Rate": 1.6325073725006654e-05, "Pretrain/Loss": 2.035645008087158, "Pretrain/Loss (Raw)": 1.935220718383789, "Pretrain/Step": 5955, "Pretrain/Step Time": 8.813998021185398} +{"Pretrain/Learning Rate": 1.6317111860154328e-05, "Pretrain/Loss": 2.035209894180298, "Pretrain/Loss (Raw)": 1.9541858434677124, "Pretrain/Step": 5956, "Pretrain/Step Time": 8.814127312973142} +{"Pretrain/Learning Rate": 1.6309150996653582e-05, "Pretrain/Loss": 2.0342092514038086, "Pretrain/Loss (Raw)": 1.8401458263397217, "Pretrain/Step": 5957, "Pretrain/Step Time": 8.8130068089813} +{"Pretrain/Learning Rate": 1.630119113542249e-05, "Pretrain/Loss": 2.032834768295288, "Pretrain/Loss (Raw)": 1.9244303703308105, "Pretrain/Step": 5958, "Pretrain/Step Time": 8.810368001461029} +{"Pretrain/Learning Rate": 1.629323227737903e-05, "Pretrain/Loss": 2.0325863361358643, "Pretrain/Loss (Raw)": 2.020171642303467, "Pretrain/Step": 5959, "Pretrain/Step Time": 8.813340047374368} +{"Pretrain/Learning Rate": 1.628527442344105e-05, "Pretrain/Loss": 2.035006523132324, "Pretrain/Loss (Raw)": 2.0682380199432373, "Pretrain/Step": 5960, "Pretrain/Step Time": 8.818485090509057} +{"Pretrain/Learning Rate": 1.6277317574526284e-05, "Pretrain/Loss": 2.0352039337158203, "Pretrain/Loss (Raw)": 2.1583051681518555, "Pretrain/Step": 5961, "Pretrain/Step Time": 8.816539717838168} +{"Pretrain/Learning Rate": 1.626936173155237e-05, "Pretrain/Loss": 2.0353777408599854, "Pretrain/Loss (Raw)": 2.232058048248291, "Pretrain/Step": 5962, "Pretrain/Step Time": 8.817597540095448} +{"Pretrain/Learning Rate": 1.626140689543679e-05, "Pretrain/Loss": 2.0360279083251953, "Pretrain/Loss (Raw)": 2.021296501159668, "Pretrain/Step": 5963, "Pretrain/Step Time": 8.816580606624484} +{"Pretrain/Learning Rate": 1.6253453067096954e-05, "Pretrain/Loss": 2.037849187850952, "Pretrain/Loss (Raw)": 2.136934995651245, "Pretrain/Step": 5964, "Pretrain/Step Time": 8.819721208885312} +{"Pretrain/Learning Rate": 1.6245500247450114e-05, "Pretrain/Loss": 2.044548988342285, "Pretrain/Loss (Raw)": 2.4358997344970703, "Pretrain/Step": 5965, "Pretrain/Step Time": 8.807051118463278} +{"Pretrain/Learning Rate": 1.6237548437413448e-05, "Pretrain/Loss": 2.0439889430999756, "Pretrain/Loss (Raw)": 1.912857174873352, "Pretrain/Step": 5966, "Pretrain/Step Time": 8.811569392681122} +{"Pretrain/Learning Rate": 1.622959763790398e-05, "Pretrain/Loss": 2.0467185974121094, "Pretrain/Loss (Raw)": 2.252939462661743, "Pretrain/Step": 5967, "Pretrain/Step Time": 8.810199815779924} +{"Pretrain/Learning Rate": 1.6221647849838645e-05, "Pretrain/Loss": 2.043348789215088, "Pretrain/Loss (Raw)": 1.6358575820922852, "Pretrain/Step": 5968, "Pretrain/Step Time": 8.812526194378734} +{"Pretrain/Learning Rate": 1.621369907413424e-05, "Pretrain/Loss": 2.045788288116455, "Pretrain/Loss (Raw)": 2.0285072326660156, "Pretrain/Step": 5969, "Pretrain/Step Time": 8.811026103794575} +{"Pretrain/Learning Rate": 1.6205751311707463e-05, "Pretrain/Loss": 2.0468266010284424, "Pretrain/Loss (Raw)": 2.185995578765869, "Pretrain/Step": 5970, "Pretrain/Step Time": 8.80998176522553} +{"Pretrain/Learning Rate": 1.6197804563474882e-05, "Pretrain/Loss": 2.040635824203491, "Pretrain/Loss (Raw)": 1.4206997156143188, "Pretrain/Step": 5971, "Pretrain/Step Time": 8.808924628421664} +{"Pretrain/Learning Rate": 1.6189858830352962e-05, "Pretrain/Loss": 2.041846752166748, "Pretrain/Loss (Raw)": 2.201692819595337, "Pretrain/Step": 5972, "Pretrain/Step Time": 8.817479014396667} +{"Pretrain/Learning Rate": 1.618191411325803e-05, "Pretrain/Loss": 2.0411794185638428, "Pretrain/Loss (Raw)": 1.9587599039077759, "Pretrain/Step": 5973, "Pretrain/Step Time": 8.816407222300768} +{"Pretrain/Learning Rate": 1.617397041310632e-05, "Pretrain/Loss": 2.042013645172119, "Pretrain/Loss (Raw)": 1.9308817386627197, "Pretrain/Step": 5974, "Pretrain/Step Time": 8.818265410140157} +{"Pretrain/Learning Rate": 1.6166027730813926e-05, "Pretrain/Loss": 2.0428555011749268, "Pretrain/Loss (Raw)": 2.2527267932891846, "Pretrain/Step": 5975, "Pretrain/Step Time": 8.819260826334357} +{"Pretrain/Learning Rate": 1.6158086067296844e-05, "Pretrain/Loss": 2.0417683124542236, "Pretrain/Loss (Raw)": 2.0437467098236084, "Pretrain/Step": 5976, "Pretrain/Step Time": 8.813143214210868} +{"Pretrain/Learning Rate": 1.615014542347094e-05, "Pretrain/Loss": 2.041956901550293, "Pretrain/Loss (Raw)": 2.1198856830596924, "Pretrain/Step": 5977, "Pretrain/Step Time": 8.813753440976143} +{"Pretrain/Learning Rate": 1.6142205800251968e-05, "Pretrain/Loss": 2.041926383972168, "Pretrain/Loss (Raw)": 2.035896062850952, "Pretrain/Step": 5978, "Pretrain/Step Time": 8.808245088905096} +{"Pretrain/Learning Rate": 1.6134267198555563e-05, "Pretrain/Loss": 2.041198253631592, "Pretrain/Loss (Raw)": 2.1191823482513428, "Pretrain/Step": 5979, "Pretrain/Step Time": 8.807401085272431} +{"Pretrain/Learning Rate": 1.612632961929725e-05, "Pretrain/Loss": 2.042701482772827, "Pretrain/Loss (Raw)": 2.164517879486084, "Pretrain/Step": 5980, "Pretrain/Step Time": 8.808696527034044} +{"Pretrain/Learning Rate": 1.6118393063392402e-05, "Pretrain/Loss": 2.0442938804626465, "Pretrain/Loss (Raw)": 2.0541181564331055, "Pretrain/Step": 5981, "Pretrain/Step Time": 8.813265010714531} +{"Pretrain/Learning Rate": 1.6110457531756334e-05, "Pretrain/Loss": 2.0436410903930664, "Pretrain/Loss (Raw)": 2.0329644680023193, "Pretrain/Step": 5982, "Pretrain/Step Time": 8.812818478792906} +{"Pretrain/Learning Rate": 1.6102523025304178e-05, "Pretrain/Loss": 2.042351007461548, "Pretrain/Loss (Raw)": 1.8727591037750244, "Pretrain/Step": 5983, "Pretrain/Step Time": 8.810438914224505} +{"Pretrain/Learning Rate": 1.6094589544951006e-05, "Pretrain/Loss": 2.0436182022094727, "Pretrain/Loss (Raw)": 2.2096052169799805, "Pretrain/Step": 5984, "Pretrain/Step Time": 8.813020460307598} +{"Pretrain/Learning Rate": 1.6086657091611718e-05, "Pretrain/Loss": 2.0458755493164062, "Pretrain/Loss (Raw)": 2.1553432941436768, "Pretrain/Step": 5985, "Pretrain/Step Time": 8.810010867193341} +{"Pretrain/Learning Rate": 1.607872566620115e-05, "Pretrain/Loss": 2.045837879180908, "Pretrain/Loss (Raw)": 2.1050891876220703, "Pretrain/Step": 5986, "Pretrain/Step Time": 8.817658875137568} +{"Pretrain/Learning Rate": 1.6070795269633964e-05, "Pretrain/Loss": 2.0489401817321777, "Pretrain/Loss (Raw)": 2.1518800258636475, "Pretrain/Step": 5987, "Pretrain/Step Time": 8.808805514127016} +{"Pretrain/Learning Rate": 1.6062865902824754e-05, "Pretrain/Loss": 2.0496058464050293, "Pretrain/Loss (Raw)": 2.071377992630005, "Pretrain/Step": 5988, "Pretrain/Step Time": 8.810378475114703} +{"Pretrain/Learning Rate": 1.605493756668795e-05, "Pretrain/Loss": 2.0517475605010986, "Pretrain/Loss (Raw)": 2.1972906589508057, "Pretrain/Step": 5989, "Pretrain/Step Time": 8.812183713540435} +{"Pretrain/Learning Rate": 1.6047010262137908e-05, "Pretrain/Loss": 2.0542263984680176, "Pretrain/Loss (Raw)": 2.237184524536133, "Pretrain/Step": 5990, "Pretrain/Step Time": 8.810026962310076} +{"Pretrain/Learning Rate": 1.603908399008882e-05, "Pretrain/Loss": 2.054734706878662, "Pretrain/Loss (Raw)": 2.149174928665161, "Pretrain/Step": 5991, "Pretrain/Step Time": 8.80976726859808} +{"Pretrain/Learning Rate": 1.60311587514548e-05, "Pretrain/Loss": 2.0562214851379395, "Pretrain/Loss (Raw)": 2.0354902744293213, "Pretrain/Step": 5992, "Pretrain/Step Time": 8.806692715734243} +{"Pretrain/Learning Rate": 1.6023234547149808e-05, "Pretrain/Loss": 2.0569143295288086, "Pretrain/Loss (Raw)": 1.9474602937698364, "Pretrain/Step": 5993, "Pretrain/Step Time": 8.811573376879096} +{"Pretrain/Learning Rate": 1.6015311378087714e-05, "Pretrain/Loss": 2.057659149169922, "Pretrain/Loss (Raw)": 2.148068428039551, "Pretrain/Step": 5994, "Pretrain/Step Time": 8.806423362344503} +{"Pretrain/Learning Rate": 1.600738924518224e-05, "Pretrain/Loss": 2.0567800998687744, "Pretrain/Loss (Raw)": 1.9303841590881348, "Pretrain/Step": 5995, "Pretrain/Step Time": 8.808535067364573} +{"Pretrain/Learning Rate": 1.5999468149347024e-05, "Pretrain/Loss": 2.057854652404785, "Pretrain/Loss (Raw)": 2.0512006282806396, "Pretrain/Step": 5996, "Pretrain/Step Time": 8.808576809242368} +{"Pretrain/Learning Rate": 1.5991548091495546e-05, "Pretrain/Loss": 2.0589418411254883, "Pretrain/Loss (Raw)": 2.0010805130004883, "Pretrain/Step": 5997, "Pretrain/Step Time": 8.808222534134984} +{"Pretrain/Learning Rate": 1.5983629072541196e-05, "Pretrain/Loss": 2.0568931102752686, "Pretrain/Loss (Raw)": 1.6977933645248413, "Pretrain/Step": 5998, "Pretrain/Step Time": 8.81064324080944} +{"Pretrain/Learning Rate": 1.597571109339722e-05, "Pretrain/Loss": 2.057034969329834, "Pretrain/Loss (Raw)": 2.1431760787963867, "Pretrain/Step": 5999, "Pretrain/Step Time": 8.811037372797728} +{"Pretrain/Learning Rate": 1.5967794154976773e-05, "Pretrain/Loss": 2.0571017265319824, "Pretrain/Loss (Raw)": 2.0952694416046143, "Pretrain/Step": 6000, "Pretrain/Step Time": 8.810070268809795} +{"Pretrain/Learning Rate": 1.5959878258192863e-05, "Pretrain/Loss": 2.0560832023620605, "Pretrain/Loss (Raw)": 1.9474326372146606, "Pretrain/Step": 6001, "Pretrain/Step Time": 8.810518251731992} +{"Pretrain/Learning Rate": 1.5951963403958382e-05, "Pretrain/Loss": 2.0546422004699707, "Pretrain/Loss (Raw)": 2.045006275177002, "Pretrain/Step": 6002, "Pretrain/Step Time": 8.810155045241117} +{"Pretrain/Learning Rate": 1.5944049593186127e-05, "Pretrain/Loss": 2.0567851066589355, "Pretrain/Loss (Raw)": 2.2669363021850586, "Pretrain/Step": 6003, "Pretrain/Step Time": 8.818642327561975} +{"Pretrain/Learning Rate": 1.5936136826788745e-05, "Pretrain/Loss": 2.056480884552002, "Pretrain/Loss (Raw)": 2.0162363052368164, "Pretrain/Step": 6004, "Pretrain/Step Time": 8.817764265462756} +{"Pretrain/Learning Rate": 1.5928225105678774e-05, "Pretrain/Loss": 2.0552897453308105, "Pretrain/Loss (Raw)": 2.060349941253662, "Pretrain/Step": 6005, "Pretrain/Step Time": 8.817823151126504} +{"Pretrain/Learning Rate": 1.592031443076863e-05, "Pretrain/Loss": 2.0591773986816406, "Pretrain/Loss (Raw)": 2.213134288787842, "Pretrain/Step": 6006, "Pretrain/Step Time": 8.817453738301992} +{"Pretrain/Learning Rate": 1.591240480297061e-05, "Pretrain/Loss": 2.0555765628814697, "Pretrain/Loss (Raw)": 1.7646559476852417, "Pretrain/Step": 6007, "Pretrain/Step Time": 8.81682855822146} +{"Pretrain/Learning Rate": 1.590449622319689e-05, "Pretrain/Loss": 2.0512547492980957, "Pretrain/Loss (Raw)": 1.4706376791000366, "Pretrain/Step": 6008, "Pretrain/Step Time": 8.808690067380667} +{"Pretrain/Learning Rate": 1.589658869235953e-05, "Pretrain/Loss": 2.050558090209961, "Pretrain/Loss (Raw)": 1.9253846406936646, "Pretrain/Step": 6009, "Pretrain/Step Time": 8.818650603294373} +{"Pretrain/Learning Rate": 1.588868221137045e-05, "Pretrain/Loss": 2.049715518951416, "Pretrain/Loss (Raw)": 1.9891818761825562, "Pretrain/Step": 6010, "Pretrain/Step Time": 8.8135080691427} +{"Pretrain/Learning Rate": 1.588077678114148e-05, "Pretrain/Loss": 2.0475850105285645, "Pretrain/Loss (Raw)": 1.6743470430374146, "Pretrain/Step": 6011, "Pretrain/Step Time": 8.816391196101904} +{"Pretrain/Learning Rate": 1.5872872402584296e-05, "Pretrain/Loss": 2.0467629432678223, "Pretrain/Loss (Raw)": 2.112208127975464, "Pretrain/Step": 6012, "Pretrain/Step Time": 8.813719695433974} +{"Pretrain/Learning Rate": 1.586496907661048e-05, "Pretrain/Loss": 2.0436511039733887, "Pretrain/Loss (Raw)": 2.1108057498931885, "Pretrain/Step": 6013, "Pretrain/Step Time": 8.818550610914826} +{"Pretrain/Learning Rate": 1.5857066804131472e-05, "Pretrain/Loss": 2.043987274169922, "Pretrain/Loss (Raw)": 2.0988831520080566, "Pretrain/Step": 6014, "Pretrain/Step Time": 8.817968996241689} +{"Pretrain/Learning Rate": 1.5849165586058608e-05, "Pretrain/Loss": 2.0453555583953857, "Pretrain/Loss (Raw)": 1.9776841402053833, "Pretrain/Step": 6015, "Pretrain/Step Time": 8.811596339568496} +{"Pretrain/Learning Rate": 1.5841265423303084e-05, "Pretrain/Loss": 2.0457100868225098, "Pretrain/Loss (Raw)": 2.0009493827819824, "Pretrain/Step": 6016, "Pretrain/Step Time": 8.82376892119646} +{"Pretrain/Learning Rate": 1.5833366316775994e-05, "Pretrain/Loss": 2.0463216304779053, "Pretrain/Loss (Raw)": 1.9670957326889038, "Pretrain/Step": 6017, "Pretrain/Step Time": 8.8163161277771} +{"Pretrain/Learning Rate": 1.582546826738829e-05, "Pretrain/Loss": 2.0454702377319336, "Pretrain/Loss (Raw)": 2.022681474685669, "Pretrain/Step": 6018, "Pretrain/Step Time": 8.81528745032847} +{"Pretrain/Learning Rate": 1.581757127605082e-05, "Pretrain/Loss": 2.04472017288208, "Pretrain/Loss (Raw)": 1.9246302843093872, "Pretrain/Step": 6019, "Pretrain/Step Time": 8.818754011765122} +{"Pretrain/Learning Rate": 1.5809675343674295e-05, "Pretrain/Loss": 2.047386646270752, "Pretrain/Loss (Raw)": 2.382263422012329, "Pretrain/Step": 6020, "Pretrain/Step Time": 8.814521653577685} +{"Pretrain/Learning Rate": 1.5801780471169324e-05, "Pretrain/Loss": 2.0485825538635254, "Pretrain/Loss (Raw)": 2.190399169921875, "Pretrain/Step": 6021, "Pretrain/Step Time": 8.814397122710943} +{"Pretrain/Learning Rate": 1.579388665944636e-05, "Pretrain/Loss": 2.046579360961914, "Pretrain/Loss (Raw)": 1.8527957201004028, "Pretrain/Step": 6022, "Pretrain/Step Time": 8.802772752940655} +{"Pretrain/Learning Rate": 1.578599390941578e-05, "Pretrain/Loss": 2.045501232147217, "Pretrain/Loss (Raw)": 1.9325344562530518, "Pretrain/Step": 6023, "Pretrain/Step Time": 8.802658449858427} +{"Pretrain/Learning Rate": 1.577810222198779e-05, "Pretrain/Loss": 2.0485405921936035, "Pretrain/Loss (Raw)": 2.279853343963623, "Pretrain/Step": 6024, "Pretrain/Step Time": 8.801539167761803} +{"Pretrain/Learning Rate": 1.577021159807252e-05, "Pretrain/Loss": 2.0464072227478027, "Pretrain/Loss (Raw)": 1.8151471614837646, "Pretrain/Step": 6025, "Pretrain/Step Time": 8.80414524115622} +{"Pretrain/Learning Rate": 1.5762322038579925e-05, "Pretrain/Loss": 2.046576976776123, "Pretrain/Loss (Raw)": 2.1118276119232178, "Pretrain/Step": 6026, "Pretrain/Step Time": 8.805642427876592} +{"Pretrain/Learning Rate": 1.5754433544419893e-05, "Pretrain/Loss": 2.046424388885498, "Pretrain/Loss (Raw)": 2.0679092407226562, "Pretrain/Step": 6027, "Pretrain/Step Time": 8.80725897476077} +{"Pretrain/Learning Rate": 1.574654611650214e-05, "Pretrain/Loss": 2.0443873405456543, "Pretrain/Loss (Raw)": 1.9650123119354248, "Pretrain/Step": 6028, "Pretrain/Step Time": 8.807670019567013} +{"Pretrain/Learning Rate": 1.5738659755736308e-05, "Pretrain/Loss": 2.0448477268218994, "Pretrain/Loss (Raw)": 2.3143696784973145, "Pretrain/Step": 6029, "Pretrain/Step Time": 8.798608738929033} +{"Pretrain/Learning Rate": 1.5730774463031862e-05, "Pretrain/Loss": 2.038297176361084, "Pretrain/Loss (Raw)": 1.5875691175460815, "Pretrain/Step": 6030, "Pretrain/Step Time": 8.81286940164864} +{"Pretrain/Learning Rate": 1.572289023929819e-05, "Pretrain/Loss": 2.0383996963500977, "Pretrain/Loss (Raw)": 2.0623013973236084, "Pretrain/Step": 6031, "Pretrain/Step Time": 8.811488522216678} +{"Pretrain/Learning Rate": 1.5715007085444523e-05, "Pretrain/Loss": 2.0397868156433105, "Pretrain/Loss (Raw)": 2.102133274078369, "Pretrain/Step": 6032, "Pretrain/Step Time": 8.81051254272461} +{"Pretrain/Learning Rate": 1.5707125002379996e-05, "Pretrain/Loss": 2.0391976833343506, "Pretrain/Loss (Raw)": 1.9899306297302246, "Pretrain/Step": 6033, "Pretrain/Step Time": 8.815588330850005} +{"Pretrain/Learning Rate": 1.56992439910136e-05, "Pretrain/Loss": 2.040536403656006, "Pretrain/Loss (Raw)": 2.173800468444824, "Pretrain/Step": 6034, "Pretrain/Step Time": 8.814973330125213} +{"Pretrain/Learning Rate": 1.569136405225422e-05, "Pretrain/Loss": 2.042536497116089, "Pretrain/Loss (Raw)": 2.137544631958008, "Pretrain/Step": 6035, "Pretrain/Step Time": 8.815049685537815} +{"Pretrain/Learning Rate": 1.5683485187010593e-05, "Pretrain/Loss": 2.043898820877075, "Pretrain/Loss (Raw)": 2.0904269218444824, "Pretrain/Step": 6036, "Pretrain/Step Time": 8.805460905656219} +{"Pretrain/Learning Rate": 1.5675607396191366e-05, "Pretrain/Loss": 2.044506549835205, "Pretrain/Loss (Raw)": 2.073857307434082, "Pretrain/Step": 6037, "Pretrain/Step Time": 8.814581796526909} +{"Pretrain/Learning Rate": 1.5667730680705022e-05, "Pretrain/Loss": 2.044367551803589, "Pretrain/Loss (Raw)": 1.9950703382492065, "Pretrain/Step": 6038, "Pretrain/Step Time": 8.813641015440226} +{"Pretrain/Learning Rate": 1.5659855041459955e-05, "Pretrain/Loss": 2.0439860820770264, "Pretrain/Loss (Raw)": 2.000709056854248, "Pretrain/Step": 6039, "Pretrain/Step Time": 8.812426641583443} +{"Pretrain/Learning Rate": 1.5651980479364416e-05, "Pretrain/Loss": 2.040898084640503, "Pretrain/Loss (Raw)": 2.0476460456848145, "Pretrain/Step": 6040, "Pretrain/Step Time": 8.808451296761632} +{"Pretrain/Learning Rate": 1.564410699532654e-05, "Pretrain/Loss": 2.0452582836151123, "Pretrain/Loss (Raw)": 2.00394868850708, "Pretrain/Step": 6041, "Pretrain/Step Time": 8.810890205204487} +{"Pretrain/Learning Rate": 1.5636234590254324e-05, "Pretrain/Loss": 2.043682098388672, "Pretrain/Loss (Raw)": 1.9039913415908813, "Pretrain/Step": 6042, "Pretrain/Step Time": 8.810125360265374} +{"Pretrain/Learning Rate": 1.5628363265055664e-05, "Pretrain/Loss": 2.042658567428589, "Pretrain/Loss (Raw)": 2.049039602279663, "Pretrain/Step": 6043, "Pretrain/Step Time": 8.798686472699046} +{"Pretrain/Learning Rate": 1.5620493020638315e-05, "Pretrain/Loss": 2.0430808067321777, "Pretrain/Loss (Raw)": 2.223006248474121, "Pretrain/Step": 6044, "Pretrain/Step Time": 8.802611708641052} +{"Pretrain/Learning Rate": 1.5612623857909904e-05, "Pretrain/Loss": 2.046085834503174, "Pretrain/Loss (Raw)": 2.2764604091644287, "Pretrain/Step": 6045, "Pretrain/Step Time": 8.808830140158534} +{"Pretrain/Learning Rate": 1.5604755777777948e-05, "Pretrain/Loss": 2.0461602210998535, "Pretrain/Loss (Raw)": 1.9473598003387451, "Pretrain/Step": 6046, "Pretrain/Step Time": 8.808953246101737} +{"Pretrain/Learning Rate": 1.5596888781149827e-05, "Pretrain/Loss": 2.0466434955596924, "Pretrain/Loss (Raw)": 1.9773024320602417, "Pretrain/Step": 6047, "Pretrain/Step Time": 8.80814515426755} +{"Pretrain/Learning Rate": 1.55890228689328e-05, "Pretrain/Loss": 2.0450587272644043, "Pretrain/Loss (Raw)": 1.7691218852996826, "Pretrain/Step": 6048, "Pretrain/Step Time": 8.815187064930797} +{"Pretrain/Learning Rate": 1.5581158042034e-05, "Pretrain/Loss": 2.0433106422424316, "Pretrain/Loss (Raw)": 2.0032730102539062, "Pretrain/Step": 6049, "Pretrain/Step Time": 8.819367416203022} +{"Pretrain/Learning Rate": 1.557329430136044e-05, "Pretrain/Loss": 2.0422353744506836, "Pretrain/Loss (Raw)": 1.8516418933868408, "Pretrain/Step": 6050, "Pretrain/Step Time": 8.815474886447191} +{"Pretrain/Learning Rate": 1.5565431647819e-05, "Pretrain/Loss": 2.041926860809326, "Pretrain/Loss (Raw)": 2.0527570247650146, "Pretrain/Step": 6051, "Pretrain/Step Time": 8.812305165454745} +{"Pretrain/Learning Rate": 1.555757008231644e-05, "Pretrain/Loss": 2.042205572128296, "Pretrain/Loss (Raw)": 2.060359239578247, "Pretrain/Step": 6052, "Pretrain/Step Time": 8.815535003319383} +{"Pretrain/Learning Rate": 1.5549709605759393e-05, "Pretrain/Loss": 2.0413732528686523, "Pretrain/Loss (Raw)": 1.9515734910964966, "Pretrain/Step": 6053, "Pretrain/Step Time": 8.816218830645084} +{"Pretrain/Learning Rate": 1.5541850219054366e-05, "Pretrain/Loss": 2.0413804054260254, "Pretrain/Loss (Raw)": 2.1441450119018555, "Pretrain/Step": 6054, "Pretrain/Step Time": 8.809695461764932} +{"Pretrain/Learning Rate": 1.5533991923107737e-05, "Pretrain/Loss": 2.0444202423095703, "Pretrain/Loss (Raw)": 2.22829270362854, "Pretrain/Step": 6055, "Pretrain/Step Time": 8.812134049832821} +{"Pretrain/Learning Rate": 1.552613471882577e-05, "Pretrain/Loss": 2.0445518493652344, "Pretrain/Loss (Raw)": 2.001633882522583, "Pretrain/Step": 6056, "Pretrain/Step Time": 8.814190942794085} +{"Pretrain/Learning Rate": 1.5518278607114585e-05, "Pretrain/Loss": 2.041581630706787, "Pretrain/Loss (Raw)": 1.8265043497085571, "Pretrain/Step": 6057, "Pretrain/Step Time": 8.812260301783681} +{"Pretrain/Learning Rate": 1.5510423588880194e-05, "Pretrain/Loss": 2.041278839111328, "Pretrain/Loss (Raw)": 2.182877779006958, "Pretrain/Step": 6058, "Pretrain/Step Time": 8.79622302018106} +{"Pretrain/Learning Rate": 1.5502569665028465e-05, "Pretrain/Loss": 2.043771505355835, "Pretrain/Loss (Raw)": 2.1453495025634766, "Pretrain/Step": 6059, "Pretrain/Step Time": 8.805671410635114} +{"Pretrain/Learning Rate": 1.549471683646516e-05, "Pretrain/Loss": 2.0466394424438477, "Pretrain/Loss (Raw)": 2.351656436920166, "Pretrain/Step": 6060, "Pretrain/Step Time": 8.804425491020083} +{"Pretrain/Learning Rate": 1.54868651040959e-05, "Pretrain/Loss": 2.0457358360290527, "Pretrain/Loss (Raw)": 1.9275124073028564, "Pretrain/Step": 6061, "Pretrain/Step Time": 8.79921093955636} +{"Pretrain/Learning Rate": 1.5479014468826184e-05, "Pretrain/Loss": 2.0458078384399414, "Pretrain/Loss (Raw)": 2.086843490600586, "Pretrain/Step": 6062, "Pretrain/Step Time": 8.803362127393484} +{"Pretrain/Learning Rate": 1.547116493156138e-05, "Pretrain/Loss": 2.0469107627868652, "Pretrain/Loss (Raw)": 2.0767569541931152, "Pretrain/Step": 6063, "Pretrain/Step Time": 8.801266971975565} +{"Pretrain/Learning Rate": 1.5463316493206748e-05, "Pretrain/Loss": 2.0462775230407715, "Pretrain/Loss (Raw)": 2.0878210067749023, "Pretrain/Step": 6064, "Pretrain/Step Time": 8.80092915892601} +{"Pretrain/Learning Rate": 1.545546915466738e-05, "Pretrain/Loss": 2.045367479324341, "Pretrain/Loss (Raw)": 1.9739558696746826, "Pretrain/Step": 6065, "Pretrain/Step Time": 8.79360537417233} +{"Pretrain/Learning Rate": 1.54476229168483e-05, "Pretrain/Loss": 2.044421672821045, "Pretrain/Loss (Raw)": 1.9231204986572266, "Pretrain/Step": 6066, "Pretrain/Step Time": 8.7986228056252} +{"Pretrain/Learning Rate": 1.543977778065434e-05, "Pretrain/Loss": 2.041872024536133, "Pretrain/Loss (Raw)": 1.9500237703323364, "Pretrain/Step": 6067, "Pretrain/Step Time": 8.80266747996211} +{"Pretrain/Learning Rate": 1.5431933746990276e-05, "Pretrain/Loss": 2.041353464126587, "Pretrain/Loss (Raw)": 1.959023118019104, "Pretrain/Step": 6068, "Pretrain/Step Time": 8.796945057809353} +{"Pretrain/Learning Rate": 1.542409081676068e-05, "Pretrain/Loss": 2.039715051651001, "Pretrain/Loss (Raw)": 2.0456717014312744, "Pretrain/Step": 6069, "Pretrain/Step Time": 8.798935562372208} +{"Pretrain/Learning Rate": 1.541624899087007e-05, "Pretrain/Loss": 2.0355286598205566, "Pretrain/Loss (Raw)": 2.0118680000305176, "Pretrain/Step": 6070, "Pretrain/Step Time": 8.795335829257965} +{"Pretrain/Learning Rate": 1.5408408270222773e-05, "Pretrain/Loss": 2.036564826965332, "Pretrain/Loss (Raw)": 2.1555044651031494, "Pretrain/Step": 6071, "Pretrain/Step Time": 8.79402114637196} +{"Pretrain/Learning Rate": 1.5400568655723043e-05, "Pretrain/Loss": 2.0381174087524414, "Pretrain/Loss (Raw)": 1.903048038482666, "Pretrain/Step": 6072, "Pretrain/Step Time": 8.792826535180211} +{"Pretrain/Learning Rate": 1.5392730148274965e-05, "Pretrain/Loss": 2.039271116256714, "Pretrain/Loss (Raw)": 2.1452314853668213, "Pretrain/Step": 6073, "Pretrain/Step Time": 8.798264130949974} +{"Pretrain/Learning Rate": 1.5384892748782513e-05, "Pretrain/Loss": 2.039661169052124, "Pretrain/Loss (Raw)": 2.1657092571258545, "Pretrain/Step": 6074, "Pretrain/Step Time": 8.795536583289504} +{"Pretrain/Learning Rate": 1.5377056458149542e-05, "Pretrain/Loss": 2.0415120124816895, "Pretrain/Loss (Raw)": 2.1097233295440674, "Pretrain/Step": 6075, "Pretrain/Step Time": 8.797263195738196} +{"Pretrain/Learning Rate": 1.5369221277279765e-05, "Pretrain/Loss": 2.0410776138305664, "Pretrain/Loss (Raw)": 1.946639060974121, "Pretrain/Step": 6076, "Pretrain/Step Time": 8.796965464949608} +{"Pretrain/Learning Rate": 1.5361387207076766e-05, "Pretrain/Loss": 2.039834499359131, "Pretrain/Loss (Raw)": 2.086031198501587, "Pretrain/Step": 6077, "Pretrain/Step Time": 8.798535525798798} +{"Pretrain/Learning Rate": 1.5353554248444022e-05, "Pretrain/Loss": 2.0396270751953125, "Pretrain/Loss (Raw)": 2.104248285293579, "Pretrain/Step": 6078, "Pretrain/Step Time": 8.793383223935962} +{"Pretrain/Learning Rate": 1.5345722402284852e-05, "Pretrain/Loss": 2.0400190353393555, "Pretrain/Loss (Raw)": 2.2209010124206543, "Pretrain/Step": 6079, "Pretrain/Step Time": 8.790974715724587} +{"Pretrain/Learning Rate": 1.5337891669502468e-05, "Pretrain/Loss": 2.040921926498413, "Pretrain/Loss (Raw)": 2.227008104324341, "Pretrain/Step": 6080, "Pretrain/Step Time": 8.795061642304063} +{"Pretrain/Learning Rate": 1.5330062050999945e-05, "Pretrain/Loss": 2.041813850402832, "Pretrain/Loss (Raw)": 2.076838731765747, "Pretrain/Step": 6081, "Pretrain/Step Time": 8.791276978328824} +{"Pretrain/Learning Rate": 1.5322233547680235e-05, "Pretrain/Loss": 2.039921760559082, "Pretrain/Loss (Raw)": 1.9371387958526611, "Pretrain/Step": 6082, "Pretrain/Step Time": 8.786600416526198} +{"Pretrain/Learning Rate": 1.531440616044615e-05, "Pretrain/Loss": 2.042074203491211, "Pretrain/Loss (Raw)": 2.2107114791870117, "Pretrain/Step": 6083, "Pretrain/Step Time": 8.787294711917639} +{"Pretrain/Learning Rate": 1.530657989020039e-05, "Pretrain/Loss": 2.0439834594726562, "Pretrain/Loss (Raw)": 2.198580265045166, "Pretrain/Step": 6084, "Pretrain/Step Time": 8.7898128349334} +{"Pretrain/Learning Rate": 1.5298754737845515e-05, "Pretrain/Loss": 2.046748161315918, "Pretrain/Loss (Raw)": 2.194035053253174, "Pretrain/Step": 6085, "Pretrain/Step Time": 8.788263656198978} +{"Pretrain/Learning Rate": 1.5290930704283953e-05, "Pretrain/Loss": 2.0443990230560303, "Pretrain/Loss (Raw)": 1.6237242221832275, "Pretrain/Step": 6086, "Pretrain/Step Time": 8.784207813441753} +{"Pretrain/Learning Rate": 1.5283107790418023e-05, "Pretrain/Loss": 2.0446717739105225, "Pretrain/Loss (Raw)": 2.0550947189331055, "Pretrain/Step": 6087, "Pretrain/Step Time": 8.783364137634635} +{"Pretrain/Learning Rate": 1.527528599714988e-05, "Pretrain/Loss": 2.045166254043579, "Pretrain/Loss (Raw)": 2.1315159797668457, "Pretrain/Step": 6088, "Pretrain/Step Time": 8.784798622131348} +{"Pretrain/Learning Rate": 1.5267465325381584e-05, "Pretrain/Loss": 2.0450589656829834, "Pretrain/Loss (Raw)": 2.1445724964141846, "Pretrain/Step": 6089, "Pretrain/Step Time": 8.782761642709374} +{"Pretrain/Learning Rate": 1.5259645776015047e-05, "Pretrain/Loss": 2.0441908836364746, "Pretrain/Loss (Raw)": 2.120945692062378, "Pretrain/Step": 6090, "Pretrain/Step Time": 8.783984508365393} +{"Pretrain/Learning Rate": 1.5251827349952058e-05, "Pretrain/Loss": 2.0440545082092285, "Pretrain/Loss (Raw)": 2.0038232803344727, "Pretrain/Step": 6091, "Pretrain/Step Time": 8.787938542664051} +{"Pretrain/Learning Rate": 1.524401004809427e-05, "Pretrain/Loss": 2.042107582092285, "Pretrain/Loss (Raw)": 1.887770652770996, "Pretrain/Step": 6092, "Pretrain/Step Time": 8.78397891484201} +{"Pretrain/Learning Rate": 1.5236193871343224e-05, "Pretrain/Loss": 2.03796648979187, "Pretrain/Loss (Raw)": 1.9058321714401245, "Pretrain/Step": 6093, "Pretrain/Step Time": 8.782402539625764} +{"Pretrain/Learning Rate": 1.5228378820600303e-05, "Pretrain/Loss": 2.0372400283813477, "Pretrain/Loss (Raw)": 1.8198294639587402, "Pretrain/Step": 6094, "Pretrain/Step Time": 8.78669816814363} +{"Pretrain/Learning Rate": 1.5220564896766784e-05, "Pretrain/Loss": 2.036496162414551, "Pretrain/Loss (Raw)": 2.1577420234680176, "Pretrain/Step": 6095, "Pretrain/Step Time": 8.785960733890533} +{"Pretrain/Learning Rate": 1.52127521007438e-05, "Pretrain/Loss": 2.039489984512329, "Pretrain/Loss (Raw)": 2.019076347351074, "Pretrain/Step": 6096, "Pretrain/Step Time": 8.789262384176254} +{"Pretrain/Learning Rate": 1.5204940433432368e-05, "Pretrain/Loss": 2.0399699211120605, "Pretrain/Loss (Raw)": 2.0899345874786377, "Pretrain/Step": 6097, "Pretrain/Step Time": 8.79777361266315} +{"Pretrain/Learning Rate": 1.5197129895733354e-05, "Pretrain/Loss": 2.0397427082061768, "Pretrain/Loss (Raw)": 2.156923294067383, "Pretrain/Step": 6098, "Pretrain/Step Time": 8.794584184885025} +{"Pretrain/Learning Rate": 1.518932048854752e-05, "Pretrain/Loss": 2.0449113845825195, "Pretrain/Loss (Raw)": 2.0822694301605225, "Pretrain/Step": 6099, "Pretrain/Step Time": 8.794105326756835} +{"Pretrain/Learning Rate": 1.5181512212775472e-05, "Pretrain/Loss": 2.043123245239258, "Pretrain/Loss (Raw)": 1.9728151559829712, "Pretrain/Step": 6100, "Pretrain/Step Time": 8.77964398637414} +{"Pretrain/Learning Rate": 1.5173705069317706e-05, "Pretrain/Loss": 2.046485424041748, "Pretrain/Loss (Raw)": 2.3891475200653076, "Pretrain/Step": 6101, "Pretrain/Step Time": 8.789685120806098} +{"Pretrain/Learning Rate": 1.5165899059074567e-05, "Pretrain/Loss": 2.0466833114624023, "Pretrain/Loss (Raw)": 1.9561874866485596, "Pretrain/Step": 6102, "Pretrain/Step Time": 8.786380920559168} +{"Pretrain/Learning Rate": 1.5158094182946298e-05, "Pretrain/Loss": 2.0459060668945312, "Pretrain/Loss (Raw)": 2.1532206535339355, "Pretrain/Step": 6103, "Pretrain/Step Time": 8.787275740876794} +{"Pretrain/Learning Rate": 1.5150290441832976e-05, "Pretrain/Loss": 2.0450897216796875, "Pretrain/Loss (Raw)": 1.939258337020874, "Pretrain/Step": 6104, "Pretrain/Step Time": 8.787933887913823} +{"Pretrain/Learning Rate": 1.5142487836634587e-05, "Pretrain/Loss": 2.0446665287017822, "Pretrain/Loss (Raw)": 2.0657355785369873, "Pretrain/Step": 6105, "Pretrain/Step Time": 8.787721145898104} +{"Pretrain/Learning Rate": 1.5134686368250932e-05, "Pretrain/Loss": 2.046046733856201, "Pretrain/Loss (Raw)": 2.212570905685425, "Pretrain/Step": 6106, "Pretrain/Step Time": 8.786768624559045} +{"Pretrain/Learning Rate": 1.512688603758175e-05, "Pretrain/Loss": 2.043886184692383, "Pretrain/Loss (Raw)": 1.8425997495651245, "Pretrain/Step": 6107, "Pretrain/Step Time": 8.784788701683283} +{"Pretrain/Learning Rate": 1.5119086845526576e-05, "Pretrain/Loss": 2.0434422492980957, "Pretrain/Loss (Raw)": 2.107745409011841, "Pretrain/Step": 6108, "Pretrain/Step Time": 8.78764632716775} +{"Pretrain/Learning Rate": 1.5111288792984884e-05, "Pretrain/Loss": 2.043273448944092, "Pretrain/Loss (Raw)": 2.0324816703796387, "Pretrain/Step": 6109, "Pretrain/Step Time": 8.781522573903203} +{"Pretrain/Learning Rate": 1.5103491880855953e-05, "Pretrain/Loss": 2.0434536933898926, "Pretrain/Loss (Raw)": 2.056015968322754, "Pretrain/Step": 6110, "Pretrain/Step Time": 8.78696720302105} +{"Pretrain/Learning Rate": 1.5095696110038981e-05, "Pretrain/Loss": 2.043710708618164, "Pretrain/Loss (Raw)": 1.9056891202926636, "Pretrain/Step": 6111, "Pretrain/Step Time": 8.786904564127326} +{"Pretrain/Learning Rate": 1.5087901481432993e-05, "Pretrain/Loss": 2.041656255722046, "Pretrain/Loss (Raw)": 1.9466197490692139, "Pretrain/Step": 6112, "Pretrain/Step Time": 8.789711389690638} +{"Pretrain/Learning Rate": 1.5080107995936929e-05, "Pretrain/Loss": 2.0411787033081055, "Pretrain/Loss (Raw)": 2.0942180156707764, "Pretrain/Step": 6113, "Pretrain/Step Time": 8.793217174708843} +{"Pretrain/Learning Rate": 1.5072315654449543e-05, "Pretrain/Loss": 2.0400516986846924, "Pretrain/Loss (Raw)": 1.960828423500061, "Pretrain/Step": 6114, "Pretrain/Step Time": 8.784505700692534} +{"Pretrain/Learning Rate": 1.5064524457869506e-05, "Pretrain/Loss": 2.0387141704559326, "Pretrain/Loss (Raw)": 1.9806705713272095, "Pretrain/Step": 6115, "Pretrain/Step Time": 8.791205702349544} +{"Pretrain/Learning Rate": 1.5056734407095316e-05, "Pretrain/Loss": 2.0388717651367188, "Pretrain/Loss (Raw)": 2.091592311859131, "Pretrain/Step": 6116, "Pretrain/Step Time": 8.787838090211153} +{"Pretrain/Learning Rate": 1.5048945503025375e-05, "Pretrain/Loss": 2.0386264324188232, "Pretrain/Loss (Raw)": 2.1658778190612793, "Pretrain/Step": 6117, "Pretrain/Step Time": 8.786042096093297} +{"Pretrain/Learning Rate": 1.5041157746557924e-05, "Pretrain/Loss": 2.0376534461975098, "Pretrain/Loss (Raw)": 2.1126296520233154, "Pretrain/Step": 6118, "Pretrain/Step Time": 8.783721866086125} +{"Pretrain/Learning Rate": 1.5033371138591095e-05, "Pretrain/Loss": 2.0372815132141113, "Pretrain/Loss (Raw)": 2.1015586853027344, "Pretrain/Step": 6119, "Pretrain/Step Time": 8.790958957746625} +{"Pretrain/Learning Rate": 1.5025585680022866e-05, "Pretrain/Loss": 2.038026809692383, "Pretrain/Loss (Raw)": 2.1308889389038086, "Pretrain/Step": 6120, "Pretrain/Step Time": 8.793972695246339} +{"Pretrain/Learning Rate": 1.50178013717511e-05, "Pretrain/Loss": 2.0377025604248047, "Pretrain/Loss (Raw)": 1.9059627056121826, "Pretrain/Step": 6121, "Pretrain/Step Time": 8.789407286792994} +{"Pretrain/Learning Rate": 1.5010018214673515e-05, "Pretrain/Loss": 2.0369060039520264, "Pretrain/Loss (Raw)": 2.0461158752441406, "Pretrain/Step": 6122, "Pretrain/Step Time": 8.784583415836096} +{"Pretrain/Learning Rate": 1.5002236209687709e-05, "Pretrain/Loss": 2.039215326309204, "Pretrain/Loss (Raw)": 2.2259745597839355, "Pretrain/Step": 6123, "Pretrain/Step Time": 8.788338350132108} +{"Pretrain/Learning Rate": 1.4994455357691128e-05, "Pretrain/Loss": 2.040722131729126, "Pretrain/Loss (Raw)": 2.2440743446350098, "Pretrain/Step": 6124, "Pretrain/Step Time": 8.78756993636489} +{"Pretrain/Learning Rate": 1.4986675659581103e-05, "Pretrain/Loss": 2.043473720550537, "Pretrain/Loss (Raw)": 2.3532602787017822, "Pretrain/Step": 6125, "Pretrain/Step Time": 8.784564623609185} +{"Pretrain/Learning Rate": 1.4978897116254832e-05, "Pretrain/Loss": 2.045785665512085, "Pretrain/Loss (Raw)": 1.9937267303466797, "Pretrain/Step": 6126, "Pretrain/Step Time": 8.789098987355828} +{"Pretrain/Learning Rate": 1.4971119728609359e-05, "Pretrain/Loss": 2.045356512069702, "Pretrain/Loss (Raw)": 2.088271141052246, "Pretrain/Step": 6127, "Pretrain/Step Time": 8.793813612312078} +{"Pretrain/Learning Rate": 1.4963343497541621e-05, "Pretrain/Loss": 2.045088291168213, "Pretrain/Loss (Raw)": 2.0609283447265625, "Pretrain/Step": 6128, "Pretrain/Step Time": 8.79307247698307} +{"Pretrain/Learning Rate": 1.4955568423948402e-05, "Pretrain/Loss": 2.0456557273864746, "Pretrain/Loss (Raw)": 2.020042896270752, "Pretrain/Step": 6129, "Pretrain/Step Time": 8.786151647567749} +{"Pretrain/Learning Rate": 1.494779450872637e-05, "Pretrain/Loss": 2.0461251735687256, "Pretrain/Loss (Raw)": 2.105102777481079, "Pretrain/Step": 6130, "Pretrain/Step Time": 8.78713395819068} +{"Pretrain/Learning Rate": 1.4940021752772034e-05, "Pretrain/Loss": 2.044755458831787, "Pretrain/Loss (Raw)": 2.091625690460205, "Pretrain/Step": 6131, "Pretrain/Step Time": 8.778150534257293} +{"Pretrain/Learning Rate": 1.4932250156981803e-05, "Pretrain/Loss": 2.0439939498901367, "Pretrain/Loss (Raw)": 1.9187495708465576, "Pretrain/Step": 6132, "Pretrain/Step Time": 8.777751557528973} +{"Pretrain/Learning Rate": 1.4924479722251916e-05, "Pretrain/Loss": 2.044942617416382, "Pretrain/Loss (Raw)": 2.1817924976348877, "Pretrain/Step": 6133, "Pretrain/Step Time": 8.7848592530936} +{"Pretrain/Learning Rate": 1.4916710449478511e-05, "Pretrain/Loss": 2.043452262878418, "Pretrain/Loss (Raw)": 2.022364616394043, "Pretrain/Step": 6134, "Pretrain/Step Time": 8.783107101917267} +{"Pretrain/Learning Rate": 1.4908942339557564e-05, "Pretrain/Loss": 2.046398639678955, "Pretrain/Loss (Raw)": 2.1418237686157227, "Pretrain/Step": 6135, "Pretrain/Step Time": 8.78393767401576} +{"Pretrain/Learning Rate": 1.4901175393384944e-05, "Pretrain/Loss": 2.0502822399139404, "Pretrain/Loss (Raw)": 1.9676928520202637, "Pretrain/Step": 6136, "Pretrain/Step Time": 8.782777918502688} +{"Pretrain/Learning Rate": 1.4893409611856362e-05, "Pretrain/Loss": 2.050778388977051, "Pretrain/Loss (Raw)": 1.9889072179794312, "Pretrain/Step": 6137, "Pretrain/Step Time": 8.785368975251913} +{"Pretrain/Learning Rate": 1.488564499586741e-05, "Pretrain/Loss": 2.0506558418273926, "Pretrain/Loss (Raw)": 1.9735010862350464, "Pretrain/Step": 6138, "Pretrain/Step Time": 8.787077188491821} +{"Pretrain/Learning Rate": 1.4877881546313532e-05, "Pretrain/Loss": 2.054363250732422, "Pretrain/Loss (Raw)": 2.1489076614379883, "Pretrain/Step": 6139, "Pretrain/Step Time": 8.782308096066117} +{"Pretrain/Learning Rate": 1.4870119264090057e-05, "Pretrain/Loss": 2.0537109375, "Pretrain/Loss (Raw)": 2.0287046432495117, "Pretrain/Step": 6140, "Pretrain/Step Time": 8.78808506205678} +{"Pretrain/Learning Rate": 1.4862358150092157e-05, "Pretrain/Loss": 2.0525691509246826, "Pretrain/Loss (Raw)": 1.964638590812683, "Pretrain/Step": 6141, "Pretrain/Step Time": 8.785414818674326} +{"Pretrain/Learning Rate": 1.485459820521489e-05, "Pretrain/Loss": 2.0530996322631836, "Pretrain/Loss (Raw)": 2.1667768955230713, "Pretrain/Step": 6142, "Pretrain/Step Time": 8.78762237727642} +{"Pretrain/Learning Rate": 1.484683943035316e-05, "Pretrain/Loss": 2.055220365524292, "Pretrain/Loss (Raw)": 2.2491707801818848, "Pretrain/Step": 6143, "Pretrain/Step Time": 8.789892436936498} +{"Pretrain/Learning Rate": 1.4839081826401755e-05, "Pretrain/Loss": 2.053781509399414, "Pretrain/Loss (Raw)": 1.8167364597320557, "Pretrain/Step": 6144, "Pretrain/Step Time": 8.785805301740766} +{"Pretrain/Learning Rate": 1.4831325394255307e-05, "Pretrain/Loss": 2.0550026893615723, "Pretrain/Loss (Raw)": 2.1234161853790283, "Pretrain/Step": 6145, "Pretrain/Step Time": 8.790488921105862} +{"Pretrain/Learning Rate": 1.4823570134808342e-05, "Pretrain/Loss": 2.0553371906280518, "Pretrain/Loss (Raw)": 2.0655155181884766, "Pretrain/Step": 6146, "Pretrain/Step Time": 8.790544908493757} +{"Pretrain/Learning Rate": 1.4815816048955208e-05, "Pretrain/Loss": 2.0563576221466064, "Pretrain/Loss (Raw)": 2.055258274078369, "Pretrain/Step": 6147, "Pretrain/Step Time": 8.78531569428742} +{"Pretrain/Learning Rate": 1.4808063137590172e-05, "Pretrain/Loss": 2.0510549545288086, "Pretrain/Loss (Raw)": 1.7035197019577026, "Pretrain/Step": 6148, "Pretrain/Step Time": 8.789343440905213} +{"Pretrain/Learning Rate": 1.4800311401607304e-05, "Pretrain/Loss": 2.050368309020996, "Pretrain/Loss (Raw)": 2.1025078296661377, "Pretrain/Step": 6149, "Pretrain/Step Time": 8.789790095761418} +{"Pretrain/Learning Rate": 1.4792560841900604e-05, "Pretrain/Loss": 2.0515623092651367, "Pretrain/Loss (Raw)": 2.005631446838379, "Pretrain/Step": 6150, "Pretrain/Step Time": 8.791066206991673} +{"Pretrain/Learning Rate": 1.4784811459363873e-05, "Pretrain/Loss": 2.05137300491333, "Pretrain/Loss (Raw)": 1.9083073139190674, "Pretrain/Step": 6151, "Pretrain/Step Time": 8.78946878388524} +{"Pretrain/Learning Rate": 1.4777063254890833e-05, "Pretrain/Loss": 2.047621488571167, "Pretrain/Loss (Raw)": 1.7996234893798828, "Pretrain/Step": 6152, "Pretrain/Step Time": 8.792815636843443} +{"Pretrain/Learning Rate": 1.4769316229375012e-05, "Pretrain/Loss": 2.0470285415649414, "Pretrain/Loss (Raw)": 1.7392845153808594, "Pretrain/Step": 6153, "Pretrain/Step Time": 8.793189622461796} +{"Pretrain/Learning Rate": 1.4761570383709871e-05, "Pretrain/Loss": 2.046299695968628, "Pretrain/Loss (Raw)": 2.01851487159729, "Pretrain/Step": 6154, "Pretrain/Step Time": 8.791148081421852} +{"Pretrain/Learning Rate": 1.4753825718788667e-05, "Pretrain/Loss": 2.0458555221557617, "Pretrain/Loss (Raw)": 2.0110669136047363, "Pretrain/Step": 6155, "Pretrain/Step Time": 8.791366204619408} +{"Pretrain/Learning Rate": 1.4746082235504572e-05, "Pretrain/Loss": 2.04671049118042, "Pretrain/Loss (Raw)": 2.074441909790039, "Pretrain/Step": 6156, "Pretrain/Step Time": 8.790936261415482} +{"Pretrain/Learning Rate": 1.4738339934750584e-05, "Pretrain/Loss": 2.043705463409424, "Pretrain/Loss (Raw)": 1.9297178983688354, "Pretrain/Step": 6157, "Pretrain/Step Time": 8.798703951761127} +{"Pretrain/Learning Rate": 1.4730598817419593e-05, "Pretrain/Loss": 2.046095132827759, "Pretrain/Loss (Raw)": 1.8934506177902222, "Pretrain/Step": 6158, "Pretrain/Step Time": 8.785121044144034} +{"Pretrain/Learning Rate": 1.4722858884404333e-05, "Pretrain/Loss": 2.0465166568756104, "Pretrain/Loss (Raw)": 2.116255283355713, "Pretrain/Step": 6159, "Pretrain/Step Time": 8.79122068732977} +{"Pretrain/Learning Rate": 1.4715120136597421e-05, "Pretrain/Loss": 2.0454678535461426, "Pretrain/Loss (Raw)": 1.9678716659545898, "Pretrain/Step": 6160, "Pretrain/Step Time": 8.787000689655542} +{"Pretrain/Learning Rate": 1.4707382574891312e-05, "Pretrain/Loss": 2.045135259628296, "Pretrain/Loss (Raw)": 1.9473636150360107, "Pretrain/Step": 6161, "Pretrain/Step Time": 8.786919180303812} +{"Pretrain/Learning Rate": 1.4699646200178353e-05, "Pretrain/Loss": 2.0428779125213623, "Pretrain/Loss (Raw)": 1.8848756551742554, "Pretrain/Step": 6162, "Pretrain/Step Time": 8.782421715557575} +{"Pretrain/Learning Rate": 1.469191101335072e-05, "Pretrain/Loss": 2.041635036468506, "Pretrain/Loss (Raw)": 1.9784573316574097, "Pretrain/Step": 6163, "Pretrain/Step Time": 8.784656081348658} +{"Pretrain/Learning Rate": 1.4684177015300491e-05, "Pretrain/Loss": 2.0431392192840576, "Pretrain/Loss (Raw)": 2.282966136932373, "Pretrain/Step": 6164, "Pretrain/Step Time": 8.790690995752811} +{"Pretrain/Learning Rate": 1.467644420691957e-05, "Pretrain/Loss": 2.0415024757385254, "Pretrain/Loss (Raw)": 1.8643732070922852, "Pretrain/Step": 6165, "Pretrain/Step Time": 8.781992632895708} +{"Pretrain/Learning Rate": 1.4668712589099753e-05, "Pretrain/Loss": 2.040590286254883, "Pretrain/Loss (Raw)": 1.8782835006713867, "Pretrain/Step": 6166, "Pretrain/Step Time": 8.781481290236115} +{"Pretrain/Learning Rate": 1.466098216273269e-05, "Pretrain/Loss": 2.0418286323547363, "Pretrain/Loss (Raw)": 2.1592371463775635, "Pretrain/Step": 6167, "Pretrain/Step Time": 8.78187102638185} +{"Pretrain/Learning Rate": 1.465325292870987e-05, "Pretrain/Loss": 2.0441393852233887, "Pretrain/Loss (Raw)": 2.3433997631073, "Pretrain/Step": 6168, "Pretrain/Step Time": 8.78392280638218} +{"Pretrain/Learning Rate": 1.464552488792269e-05, "Pretrain/Loss": 2.0446863174438477, "Pretrain/Loss (Raw)": 2.073976755142212, "Pretrain/Step": 6169, "Pretrain/Step Time": 8.781704813241959} +{"Pretrain/Learning Rate": 1.4637798041262363e-05, "Pretrain/Loss": 2.0450520515441895, "Pretrain/Loss (Raw)": 1.9507858753204346, "Pretrain/Step": 6170, "Pretrain/Step Time": 8.777575081214309} +{"Pretrain/Learning Rate": 1.4630072389620003e-05, "Pretrain/Loss": 2.0450892448425293, "Pretrain/Loss (Raw)": 2.053830623626709, "Pretrain/Step": 6171, "Pretrain/Step Time": 8.779163314029574} +{"Pretrain/Learning Rate": 1.462234793388655e-05, "Pretrain/Loss": 2.042895793914795, "Pretrain/Loss (Raw)": 1.9422173500061035, "Pretrain/Step": 6172, "Pretrain/Step Time": 8.779766710475087} +{"Pretrain/Learning Rate": 1.4614624674952842e-05, "Pretrain/Loss": 2.0402064323425293, "Pretrain/Loss (Raw)": 1.9322479963302612, "Pretrain/Step": 6173, "Pretrain/Step Time": 8.773946708068252} +{"Pretrain/Learning Rate": 1.460690261370955e-05, "Pretrain/Loss": 2.0414395332336426, "Pretrain/Loss (Raw)": 2.105147123336792, "Pretrain/Step": 6174, "Pretrain/Step Time": 8.773973517119884} +{"Pretrain/Learning Rate": 1.4599181751047225e-05, "Pretrain/Loss": 2.0417633056640625, "Pretrain/Loss (Raw)": 2.0187737941741943, "Pretrain/Step": 6175, "Pretrain/Step Time": 8.77962108142674} +{"Pretrain/Learning Rate": 1.4591462087856262e-05, "Pretrain/Loss": 2.044480562210083, "Pretrain/Loss (Raw)": 2.116912603378296, "Pretrain/Step": 6176, "Pretrain/Step Time": 8.772954380139709} +{"Pretrain/Learning Rate": 1.4583743625026958e-05, "Pretrain/Loss": 2.0451080799102783, "Pretrain/Loss (Raw)": 2.0835938453674316, "Pretrain/Step": 6177, "Pretrain/Step Time": 8.766753917559981} +{"Pretrain/Learning Rate": 1.4576026363449402e-05, "Pretrain/Loss": 2.04612398147583, "Pretrain/Loss (Raw)": 1.9816992282867432, "Pretrain/Step": 6178, "Pretrain/Step Time": 8.776186743751168} +{"Pretrain/Learning Rate": 1.4568310304013613e-05, "Pretrain/Loss": 2.045278787612915, "Pretrain/Loss (Raw)": 1.9445666074752808, "Pretrain/Step": 6179, "Pretrain/Step Time": 8.773803615942597} +{"Pretrain/Learning Rate": 1.4560595447609427e-05, "Pretrain/Loss": 2.044590950012207, "Pretrain/Loss (Raw)": 1.9723314046859741, "Pretrain/Step": 6180, "Pretrain/Step Time": 8.771336454898119} +{"Pretrain/Learning Rate": 1.4552881795126588e-05, "Pretrain/Loss": 2.0449209213256836, "Pretrain/Loss (Raw)": 1.993789792060852, "Pretrain/Step": 6181, "Pretrain/Step Time": 8.77580190449953} +{"Pretrain/Learning Rate": 1.4545169347454627e-05, "Pretrain/Loss": 2.043822765350342, "Pretrain/Loss (Raw)": 2.0035839080810547, "Pretrain/Step": 6182, "Pretrain/Step Time": 8.781247114762664} +{"Pretrain/Learning Rate": 1.453745810548301e-05, "Pretrain/Loss": 2.0451760292053223, "Pretrain/Loss (Raw)": 2.4015252590179443, "Pretrain/Step": 6183, "Pretrain/Step Time": 8.780096597969532} +{"Pretrain/Learning Rate": 1.452974807010103e-05, "Pretrain/Loss": 2.0448691844940186, "Pretrain/Loss (Raw)": 1.962342381477356, "Pretrain/Step": 6184, "Pretrain/Step Time": 8.778428165242076} +{"Pretrain/Learning Rate": 1.4522039242197835e-05, "Pretrain/Loss": 2.045846700668335, "Pretrain/Loss (Raw)": 1.9516159296035767, "Pretrain/Step": 6185, "Pretrain/Step Time": 8.779394805431366} +{"Pretrain/Learning Rate": 1.4514331622662441e-05, "Pretrain/Loss": 2.0441970825195312, "Pretrain/Loss (Raw)": 1.9717421531677246, "Pretrain/Step": 6186, "Pretrain/Step Time": 8.788917899131775} +{"Pretrain/Learning Rate": 1.4506625212383743e-05, "Pretrain/Loss": 2.0438332557678223, "Pretrain/Loss (Raw)": 2.098785161972046, "Pretrain/Step": 6187, "Pretrain/Step Time": 8.778677264228463} +{"Pretrain/Learning Rate": 1.4498920012250472e-05, "Pretrain/Loss": 2.041369676589966, "Pretrain/Loss (Raw)": 2.0363008975982666, "Pretrain/Step": 6188, "Pretrain/Step Time": 8.778974425047636} +{"Pretrain/Learning Rate": 1.449121602315123e-05, "Pretrain/Loss": 2.041867971420288, "Pretrain/Loss (Raw)": 1.9913060665130615, "Pretrain/Step": 6189, "Pretrain/Step Time": 8.7805645018816} +{"Pretrain/Learning Rate": 1.4483513245974461e-05, "Pretrain/Loss": 2.041628360748291, "Pretrain/Loss (Raw)": 2.0561935901641846, "Pretrain/Step": 6190, "Pretrain/Step Time": 8.77742911875248} +{"Pretrain/Learning Rate": 1.4475811681608515e-05, "Pretrain/Loss": 2.0415053367614746, "Pretrain/Loss (Raw)": 2.0609774589538574, "Pretrain/Step": 6191, "Pretrain/Step Time": 8.77216867916286} +{"Pretrain/Learning Rate": 1.4468111330941556e-05, "Pretrain/Loss": 2.0411202907562256, "Pretrain/Loss (Raw)": 2.038546562194824, "Pretrain/Step": 6192, "Pretrain/Step Time": 8.777854407206178} +{"Pretrain/Learning Rate": 1.4460412194861624e-05, "Pretrain/Loss": 2.0399961471557617, "Pretrain/Loss (Raw)": 1.8300412893295288, "Pretrain/Step": 6193, "Pretrain/Step Time": 8.781884411349893} +{"Pretrain/Learning Rate": 1.4452714274256612e-05, "Pretrain/Loss": 2.0411086082458496, "Pretrain/Loss (Raw)": 2.065542459487915, "Pretrain/Step": 6194, "Pretrain/Step Time": 8.781210169196129} +{"Pretrain/Learning Rate": 1.4445017570014303e-05, "Pretrain/Loss": 2.0416951179504395, "Pretrain/Loss (Raw)": 2.0250630378723145, "Pretrain/Step": 6195, "Pretrain/Step Time": 8.779034273698926} +{"Pretrain/Learning Rate": 1.4437322083022304e-05, "Pretrain/Loss": 2.0408530235290527, "Pretrain/Loss (Raw)": 1.851260781288147, "Pretrain/Step": 6196, "Pretrain/Step Time": 8.784086471423507} +{"Pretrain/Learning Rate": 1.4429627814168095e-05, "Pretrain/Loss": 2.0420899391174316, "Pretrain/Loss (Raw)": 2.203991413116455, "Pretrain/Step": 6197, "Pretrain/Step Time": 8.783889673650265} +{"Pretrain/Learning Rate": 1.4421934764339004e-05, "Pretrain/Loss": 2.0424046516418457, "Pretrain/Loss (Raw)": 2.052175283432007, "Pretrain/Step": 6198, "Pretrain/Step Time": 8.788608185946941} +{"Pretrain/Learning Rate": 1.4414242934422251e-05, "Pretrain/Loss": 2.040802001953125, "Pretrain/Loss (Raw)": 1.950360894203186, "Pretrain/Step": 6199, "Pretrain/Step Time": 8.787146842107177} +{"Pretrain/Learning Rate": 1.440655232530489e-05, "Pretrain/Loss": 2.041862726211548, "Pretrain/Loss (Raw)": 2.0388145446777344, "Pretrain/Step": 6200, "Pretrain/Step Time": 8.790578193962574} +{"Pretrain/Learning Rate": 1.4398862937873825e-05, "Pretrain/Loss": 2.039912700653076, "Pretrain/Loss (Raw)": 1.8955954313278198, "Pretrain/Step": 6201, "Pretrain/Step Time": 8.784374859184027} +{"Pretrain/Learning Rate": 1.4391174773015836e-05, "Pretrain/Loss": 2.038313388824463, "Pretrain/Loss (Raw)": 1.9610341787338257, "Pretrain/Step": 6202, "Pretrain/Step Time": 8.781536208465695} +{"Pretrain/Learning Rate": 1.4383487831617571e-05, "Pretrain/Loss": 2.0377044677734375, "Pretrain/Loss (Raw)": 2.031766653060913, "Pretrain/Step": 6203, "Pretrain/Step Time": 8.786049049347639} +{"Pretrain/Learning Rate": 1.4375802114565515e-05, "Pretrain/Loss": 2.037815570831299, "Pretrain/Loss (Raw)": 1.9608573913574219, "Pretrain/Step": 6204, "Pretrain/Step Time": 8.789983352646232} +{"Pretrain/Learning Rate": 1.4368117622746025e-05, "Pretrain/Loss": 2.0375542640686035, "Pretrain/Loss (Raw)": 2.052582263946533, "Pretrain/Step": 6205, "Pretrain/Step Time": 8.786817412823439} +{"Pretrain/Learning Rate": 1.4360434357045294e-05, "Pretrain/Loss": 2.0369203090667725, "Pretrain/Loss (Raw)": 2.02310848236084, "Pretrain/Step": 6206, "Pretrain/Step Time": 8.787556855008006} +{"Pretrain/Learning Rate": 1.4352752318349421e-05, "Pretrain/Loss": 2.034797430038452, "Pretrain/Loss (Raw)": 1.9491645097732544, "Pretrain/Step": 6207, "Pretrain/Step Time": 8.7971484195441} +{"Pretrain/Learning Rate": 1.4345071507544326e-05, "Pretrain/Loss": 2.033102035522461, "Pretrain/Loss (Raw)": 2.0099997520446777, "Pretrain/Step": 6208, "Pretrain/Step Time": 8.791389280930161} +{"Pretrain/Learning Rate": 1.4337391925515777e-05, "Pretrain/Loss": 2.033278465270996, "Pretrain/Loss (Raw)": 2.099402666091919, "Pretrain/Step": 6209, "Pretrain/Step Time": 8.791680367663503} +{"Pretrain/Learning Rate": 1.432971357314945e-05, "Pretrain/Loss": 2.034209728240967, "Pretrain/Loss (Raw)": 2.0563669204711914, "Pretrain/Step": 6210, "Pretrain/Step Time": 8.795583849772811} +{"Pretrain/Learning Rate": 1.4322036451330828e-05, "Pretrain/Loss": 2.032632350921631, "Pretrain/Loss (Raw)": 2.0088024139404297, "Pretrain/Step": 6211, "Pretrain/Step Time": 8.796649310737848} +{"Pretrain/Learning Rate": 1.4314360560945284e-05, "Pretrain/Loss": 2.03222918510437, "Pretrain/Loss (Raw)": 2.1469616889953613, "Pretrain/Step": 6212, "Pretrain/Step Time": 8.794373638927937} +{"Pretrain/Learning Rate": 1.430668590287802e-05, "Pretrain/Loss": 2.0304155349731445, "Pretrain/Loss (Raw)": 1.9619313478469849, "Pretrain/Step": 6213, "Pretrain/Step Time": 8.792681641876698} +{"Pretrain/Learning Rate": 1.4299012478014146e-05, "Pretrain/Loss": 2.0365614891052246, "Pretrain/Loss (Raw)": 2.4103970527648926, "Pretrain/Step": 6214, "Pretrain/Step Time": 8.792337123304605} +{"Pretrain/Learning Rate": 1.4291340287238558e-05, "Pretrain/Loss": 2.0369982719421387, "Pretrain/Loss (Raw)": 2.1109864711761475, "Pretrain/Step": 6215, "Pretrain/Step Time": 8.804493479430676} +{"Pretrain/Learning Rate": 1.4283669331436078e-05, "Pretrain/Loss": 2.036099672317505, "Pretrain/Loss (Raw)": 2.0164992809295654, "Pretrain/Step": 6216, "Pretrain/Step Time": 8.7970633469522} +{"Pretrain/Learning Rate": 1.4275999611491342e-05, "Pretrain/Loss": 2.036499500274658, "Pretrain/Loss (Raw)": 2.1957576274871826, "Pretrain/Step": 6217, "Pretrain/Step Time": 8.800329389050603} +{"Pretrain/Learning Rate": 1.4268331128288881e-05, "Pretrain/Loss": 2.036776065826416, "Pretrain/Loss (Raw)": 2.1563103199005127, "Pretrain/Step": 6218, "Pretrain/Step Time": 8.80374682508409} +{"Pretrain/Learning Rate": 1.4260663882713022e-05, "Pretrain/Loss": 2.0373613834381104, "Pretrain/Loss (Raw)": 2.078770875930786, "Pretrain/Step": 6219, "Pretrain/Step Time": 8.798722695559263} +{"Pretrain/Learning Rate": 1.4252997875648021e-05, "Pretrain/Loss": 2.037966728210449, "Pretrain/Loss (Raw)": 1.9652665853500366, "Pretrain/Step": 6220, "Pretrain/Step Time": 8.799192132428288} +{"Pretrain/Learning Rate": 1.4245333107977937e-05, "Pretrain/Loss": 2.038261890411377, "Pretrain/Loss (Raw)": 1.943597435951233, "Pretrain/Step": 6221, "Pretrain/Step Time": 8.801733350381255} +{"Pretrain/Learning Rate": 1.4237669580586736e-05, "Pretrain/Loss": 2.041144609451294, "Pretrain/Loss (Raw)": 2.1888134479522705, "Pretrain/Step": 6222, "Pretrain/Step Time": 8.795741273090243} +{"Pretrain/Learning Rate": 1.4230007294358173e-05, "Pretrain/Loss": 2.041229248046875, "Pretrain/Loss (Raw)": 2.168586492538452, "Pretrain/Step": 6223, "Pretrain/Step Time": 8.80088360607624} +{"Pretrain/Learning Rate": 1.4222346250175928e-05, "Pretrain/Loss": 2.041036605834961, "Pretrain/Loss (Raw)": 1.9943801164627075, "Pretrain/Step": 6224, "Pretrain/Step Time": 8.792519913986325} +{"Pretrain/Learning Rate": 1.4214686448923498e-05, "Pretrain/Loss": 2.040257692337036, "Pretrain/Loss (Raw)": 1.9902719259262085, "Pretrain/Step": 6225, "Pretrain/Step Time": 8.790181772783399} +{"Pretrain/Learning Rate": 1.420702789148425e-05, "Pretrain/Loss": 2.0391616821289062, "Pretrain/Loss (Raw)": 2.0166454315185547, "Pretrain/Step": 6226, "Pretrain/Step Time": 8.790624836459756} +{"Pretrain/Learning Rate": 1.4199370578741395e-05, "Pretrain/Loss": 2.0397791862487793, "Pretrain/Loss (Raw)": 2.161292552947998, "Pretrain/Step": 6227, "Pretrain/Step Time": 8.793990556150675} +{"Pretrain/Learning Rate": 1.419171451157803e-05, "Pretrain/Loss": 2.0401854515075684, "Pretrain/Loss (Raw)": 2.0248191356658936, "Pretrain/Step": 6228, "Pretrain/Step Time": 8.801152901723981} +{"Pretrain/Learning Rate": 1.4184059690877075e-05, "Pretrain/Loss": 2.037240982055664, "Pretrain/Loss (Raw)": 2.0122597217559814, "Pretrain/Step": 6229, "Pretrain/Step Time": 8.790265321731567} +{"Pretrain/Learning Rate": 1.4176406117521324e-05, "Pretrain/Loss": 2.035521984100342, "Pretrain/Loss (Raw)": 1.7361706495285034, "Pretrain/Step": 6230, "Pretrain/Step Time": 8.794051475822926} +{"Pretrain/Learning Rate": 1.4168753792393414e-05, "Pretrain/Loss": 2.034543037414551, "Pretrain/Loss (Raw)": 2.0279009342193604, "Pretrain/Step": 6231, "Pretrain/Step Time": 8.792165761813521} +{"Pretrain/Learning Rate": 1.4161102716375863e-05, "Pretrain/Loss": 2.034846305847168, "Pretrain/Loss (Raw)": 1.9780699014663696, "Pretrain/Step": 6232, "Pretrain/Step Time": 8.793967423960567} +{"Pretrain/Learning Rate": 1.4153452890351022e-05, "Pretrain/Loss": 2.033618450164795, "Pretrain/Loss (Raw)": 1.9085856676101685, "Pretrain/Step": 6233, "Pretrain/Step Time": 8.79085485637188} +{"Pretrain/Learning Rate": 1.41458043152011e-05, "Pretrain/Loss": 2.0320017337799072, "Pretrain/Loss (Raw)": 2.005629777908325, "Pretrain/Step": 6234, "Pretrain/Step Time": 8.793001366779208} +{"Pretrain/Learning Rate": 1.4138156991808165e-05, "Pretrain/Loss": 2.0316872596740723, "Pretrain/Loss (Raw)": 1.802344799041748, "Pretrain/Step": 6235, "Pretrain/Step Time": 8.803248876705766} +{"Pretrain/Learning Rate": 1.4130510921054157e-05, "Pretrain/Loss": 2.0291662216186523, "Pretrain/Loss (Raw)": 1.785041332244873, "Pretrain/Step": 6236, "Pretrain/Step Time": 8.799331173300743} +{"Pretrain/Learning Rate": 1.4122866103820854e-05, "Pretrain/Loss": 2.0308570861816406, "Pretrain/Loss (Raw)": 2.2489020824432373, "Pretrain/Step": 6237, "Pretrain/Step Time": 8.801501983776689} +{"Pretrain/Learning Rate": 1.411522254098988e-05, "Pretrain/Loss": 2.030222177505493, "Pretrain/Loss (Raw)": 1.9747645854949951, "Pretrain/Step": 6238, "Pretrain/Step Time": 8.79903120175004} +{"Pretrain/Learning Rate": 1.4107580233442725e-05, "Pretrain/Loss": 2.0321667194366455, "Pretrain/Loss (Raw)": 2.154599189758301, "Pretrain/Step": 6239, "Pretrain/Step Time": 8.798673655837774} +{"Pretrain/Learning Rate": 1.4099939182060755e-05, "Pretrain/Loss": 2.033079147338867, "Pretrain/Loss (Raw)": 2.0633785724639893, "Pretrain/Step": 6240, "Pretrain/Step Time": 8.796744225546718} +{"Pretrain/Learning Rate": 1.409229938772516e-05, "Pretrain/Loss": 2.0323166847229004, "Pretrain/Loss (Raw)": 1.996639370918274, "Pretrain/Step": 6241, "Pretrain/Step Time": 8.803105702623725} +{"Pretrain/Learning Rate": 1.4084660851316999e-05, "Pretrain/Loss": 2.031893730163574, "Pretrain/Loss (Raw)": 1.906689167022705, "Pretrain/Step": 6242, "Pretrain/Step Time": 8.80661972053349} +{"Pretrain/Learning Rate": 1.4077023573717174e-05, "Pretrain/Loss": 2.0290169715881348, "Pretrain/Loss (Raw)": 1.6124674081802368, "Pretrain/Step": 6243, "Pretrain/Step Time": 8.80289314314723} +{"Pretrain/Learning Rate": 1.4069387555806473e-05, "Pretrain/Loss": 2.0288491249084473, "Pretrain/Loss (Raw)": 2.070082664489746, "Pretrain/Step": 6244, "Pretrain/Step Time": 8.800656391307712} +{"Pretrain/Learning Rate": 1.4061752798465503e-05, "Pretrain/Loss": 2.027402400970459, "Pretrain/Loss (Raw)": 1.9807170629501343, "Pretrain/Step": 6245, "Pretrain/Step Time": 8.802047170698643} +{"Pretrain/Learning Rate": 1.4054119302574741e-05, "Pretrain/Loss": 2.027538299560547, "Pretrain/Loss (Raw)": 2.1300251483917236, "Pretrain/Step": 6246, "Pretrain/Step Time": 8.804621500894427} +{"Pretrain/Learning Rate": 1.4046487069014513e-05, "Pretrain/Loss": 2.0278477668762207, "Pretrain/Loss (Raw)": 2.1411335468292236, "Pretrain/Step": 6247, "Pretrain/Step Time": 8.798312690109015} +{"Pretrain/Learning Rate": 1.403885609866502e-05, "Pretrain/Loss": 2.028545379638672, "Pretrain/Loss (Raw)": 2.220189094543457, "Pretrain/Step": 6248, "Pretrain/Step Time": 8.794112840667367} +{"Pretrain/Learning Rate": 1.4031226392406293e-05, "Pretrain/Loss": 2.0296387672424316, "Pretrain/Loss (Raw)": 2.0459184646606445, "Pretrain/Step": 6249, "Pretrain/Step Time": 8.792732425034046} +{"Pretrain/Learning Rate": 1.4023597951118217e-05, "Pretrain/Loss": 2.0296640396118164, "Pretrain/Loss (Raw)": 2.0493972301483154, "Pretrain/Step": 6250, "Pretrain/Step Time": 8.792556466534734} +{"Pretrain/Learning Rate": 1.4015970775680554e-05, "Pretrain/Loss": 2.0290417671203613, "Pretrain/Loss (Raw)": 2.146303176879883, "Pretrain/Step": 6251, "Pretrain/Step Time": 8.786243349313736} +{"Pretrain/Learning Rate": 1.4008344866972902e-05, "Pretrain/Loss": 2.0268778800964355, "Pretrain/Loss (Raw)": 1.967085361480713, "Pretrain/Step": 6252, "Pretrain/Step Time": 8.788479885086417} +{"Pretrain/Learning Rate": 1.4000720225874714e-05, "Pretrain/Loss": 2.023916006088257, "Pretrain/Loss (Raw)": 1.974136233329773, "Pretrain/Step": 6253, "Pretrain/Step Time": 8.791544457897544} +{"Pretrain/Learning Rate": 1.399309685326529e-05, "Pretrain/Loss": 2.024548292160034, "Pretrain/Loss (Raw)": 2.0746686458587646, "Pretrain/Step": 6254, "Pretrain/Step Time": 8.78534403629601} +{"Pretrain/Learning Rate": 1.3985474750023821e-05, "Pretrain/Loss": 2.025552272796631, "Pretrain/Loss (Raw)": 2.2167954444885254, "Pretrain/Step": 6255, "Pretrain/Step Time": 8.782813103869557} +{"Pretrain/Learning Rate": 1.3977853917029287e-05, "Pretrain/Loss": 2.028144121170044, "Pretrain/Loss (Raw)": 2.3926496505737305, "Pretrain/Step": 6256, "Pretrain/Step Time": 8.794310707598925} +{"Pretrain/Learning Rate": 1.3970234355160588e-05, "Pretrain/Loss": 2.0290064811706543, "Pretrain/Loss (Raw)": 2.1304662227630615, "Pretrain/Step": 6257, "Pretrain/Step Time": 8.790266200900078} +{"Pretrain/Learning Rate": 1.3962616065296428e-05, "Pretrain/Loss": 2.02848219871521, "Pretrain/Loss (Raw)": 2.0379717350006104, "Pretrain/Step": 6258, "Pretrain/Step Time": 8.788360446691513} +{"Pretrain/Learning Rate": 1.395499904831541e-05, "Pretrain/Loss": 2.0276541709899902, "Pretrain/Loss (Raw)": 1.9856406450271606, "Pretrain/Step": 6259, "Pretrain/Step Time": 8.78841445967555} +{"Pretrain/Learning Rate": 1.394738330509593e-05, "Pretrain/Loss": 2.0279276371002197, "Pretrain/Loss (Raw)": 1.9537262916564941, "Pretrain/Step": 6260, "Pretrain/Step Time": 8.78983285650611} +{"Pretrain/Learning Rate": 1.3939768836516299e-05, "Pretrain/Loss": 2.0285608768463135, "Pretrain/Loss (Raw)": 2.262852907180786, "Pretrain/Step": 6261, "Pretrain/Step Time": 8.783183369785547} +{"Pretrain/Learning Rate": 1.393215564345463e-05, "Pretrain/Loss": 2.0287556648254395, "Pretrain/Loss (Raw)": 2.04730486869812, "Pretrain/Step": 6262, "Pretrain/Step Time": 8.782169068232179} +{"Pretrain/Learning Rate": 1.3924543726788953e-05, "Pretrain/Loss": 2.026184558868408, "Pretrain/Loss (Raw)": 1.812721610069275, "Pretrain/Step": 6263, "Pretrain/Step Time": 8.786048801615834} +{"Pretrain/Learning Rate": 1.3916933087397055e-05, "Pretrain/Loss": 2.0249876976013184, "Pretrain/Loss (Raw)": 1.8144794702529907, "Pretrain/Step": 6264, "Pretrain/Step Time": 8.785748519003391} +{"Pretrain/Learning Rate": 1.3909323726156672e-05, "Pretrain/Loss": 2.02494740486145, "Pretrain/Loss (Raw)": 1.9837690591812134, "Pretrain/Step": 6265, "Pretrain/Step Time": 8.778450105339289} +{"Pretrain/Learning Rate": 1.3901715643945337e-05, "Pretrain/Loss": 2.0262889862060547, "Pretrain/Loss (Raw)": 2.1452412605285645, "Pretrain/Step": 6266, "Pretrain/Step Time": 8.781891234219074} +{"Pretrain/Learning Rate": 1.3894108841640452e-05, "Pretrain/Loss": 2.0257556438446045, "Pretrain/Loss (Raw)": 2.080627918243408, "Pretrain/Step": 6267, "Pretrain/Step Time": 8.784408684819937} +{"Pretrain/Learning Rate": 1.3886503320119256e-05, "Pretrain/Loss": 2.024825096130371, "Pretrain/Loss (Raw)": 1.9095799922943115, "Pretrain/Step": 6268, "Pretrain/Step Time": 8.781470799818635} +{"Pretrain/Learning Rate": 1.3878899080258878e-05, "Pretrain/Loss": 2.0260744094848633, "Pretrain/Loss (Raw)": 2.124530076980591, "Pretrain/Step": 6269, "Pretrain/Step Time": 8.778427010402083} +{"Pretrain/Learning Rate": 1.3871296122936261e-05, "Pretrain/Loss": 2.025224208831787, "Pretrain/Loss (Raw)": 2.0579893589019775, "Pretrain/Step": 6270, "Pretrain/Step Time": 8.783110002055764} +{"Pretrain/Learning Rate": 1.3863694449028214e-05, "Pretrain/Loss": 2.023679256439209, "Pretrain/Loss (Raw)": 2.0514121055603027, "Pretrain/Step": 6271, "Pretrain/Step Time": 8.781966220587492} +{"Pretrain/Learning Rate": 1.3856094059411392e-05, "Pretrain/Loss": 2.02537202835083, "Pretrain/Loss (Raw)": 2.033406972885132, "Pretrain/Step": 6272, "Pretrain/Step Time": 8.783227996900678} +{"Pretrain/Learning Rate": 1.3848494954962324e-05, "Pretrain/Loss": 2.024362564086914, "Pretrain/Loss (Raw)": 1.994235634803772, "Pretrain/Step": 6273, "Pretrain/Step Time": 8.780885370448232} +{"Pretrain/Learning Rate": 1.3840897136557366e-05, "Pretrain/Loss": 2.02376389503479, "Pretrain/Loss (Raw)": 1.9888497591018677, "Pretrain/Step": 6274, "Pretrain/Step Time": 8.781881298869848} +{"Pretrain/Learning Rate": 1.383330060507273e-05, "Pretrain/Loss": 2.023405075073242, "Pretrain/Loss (Raw)": 2.00934100151062, "Pretrain/Step": 6275, "Pretrain/Step Time": 8.782247269526124} +{"Pretrain/Learning Rate": 1.382570536138448e-05, "Pretrain/Loss": 2.026944875717163, "Pretrain/Loss (Raw)": 2.1566009521484375, "Pretrain/Step": 6276, "Pretrain/Step Time": 8.782695017755032} +{"Pretrain/Learning Rate": 1.3818111406368555e-05, "Pretrain/Loss": 2.0274205207824707, "Pretrain/Loss (Raw)": 2.1633810997009277, "Pretrain/Step": 6277, "Pretrain/Step Time": 8.783968567848206} +{"Pretrain/Learning Rate": 1.381051874090071e-05, "Pretrain/Loss": 2.027538299560547, "Pretrain/Loss (Raw)": 2.020728826522827, "Pretrain/Step": 6278, "Pretrain/Step Time": 8.786571558564901} +{"Pretrain/Learning Rate": 1.3802927365856571e-05, "Pretrain/Loss": 2.0306971073150635, "Pretrain/Loss (Raw)": 2.3126351833343506, "Pretrain/Step": 6279, "Pretrain/Step Time": 8.788532571867108} +{"Pretrain/Learning Rate": 1.3795337282111604e-05, "Pretrain/Loss": 2.0331690311431885, "Pretrain/Loss (Raw)": 2.116025447845459, "Pretrain/Step": 6280, "Pretrain/Step Time": 8.786575147882104} +{"Pretrain/Learning Rate": 1.3787748490541144e-05, "Pretrain/Loss": 2.0355308055877686, "Pretrain/Loss (Raw)": 2.0415782928466797, "Pretrain/Step": 6281, "Pretrain/Step Time": 8.790100384503603} +{"Pretrain/Learning Rate": 1.3780160992020364e-05, "Pretrain/Loss": 2.0355682373046875, "Pretrain/Loss (Raw)": 2.0233025550842285, "Pretrain/Step": 6282, "Pretrain/Step Time": 8.789580933749676} +{"Pretrain/Learning Rate": 1.3772574787424291e-05, "Pretrain/Loss": 2.0341153144836426, "Pretrain/Loss (Raw)": 1.8251359462738037, "Pretrain/Step": 6283, "Pretrain/Step Time": 8.790865268558264} +{"Pretrain/Learning Rate": 1.3764989877627785e-05, "Pretrain/Loss": 2.035051107406616, "Pretrain/Loss (Raw)": 2.194199323654175, "Pretrain/Step": 6284, "Pretrain/Step Time": 8.791401190683246} +{"Pretrain/Learning Rate": 1.3757406263505602e-05, "Pretrain/Loss": 2.0353403091430664, "Pretrain/Loss (Raw)": 1.966745138168335, "Pretrain/Step": 6285, "Pretrain/Step Time": 8.800642397254705} +{"Pretrain/Learning Rate": 1.37498239459323e-05, "Pretrain/Loss": 2.035680055618286, "Pretrain/Loss (Raw)": 1.9369304180145264, "Pretrain/Step": 6286, "Pretrain/Step Time": 8.79808828420937} +{"Pretrain/Learning Rate": 1.3742242925782317e-05, "Pretrain/Loss": 2.0355045795440674, "Pretrain/Loss (Raw)": 2.0937840938568115, "Pretrain/Step": 6287, "Pretrain/Step Time": 8.794913837686181} +{"Pretrain/Learning Rate": 1.3734663203929916e-05, "Pretrain/Loss": 2.0356922149658203, "Pretrain/Loss (Raw)": 1.9918636083602905, "Pretrain/Step": 6288, "Pretrain/Step Time": 8.79899582080543} +{"Pretrain/Learning Rate": 1.372708478124925e-05, "Pretrain/Loss": 2.0365262031555176, "Pretrain/Loss (Raw)": 2.054171085357666, "Pretrain/Step": 6289, "Pretrain/Step Time": 8.795507607981563} +{"Pretrain/Learning Rate": 1.3719507658614284e-05, "Pretrain/Loss": 2.0383236408233643, "Pretrain/Loss (Raw)": 2.1149308681488037, "Pretrain/Step": 6290, "Pretrain/Step Time": 8.795768026262522} +{"Pretrain/Learning Rate": 1.3711931836898842e-05, "Pretrain/Loss": 2.0396647453308105, "Pretrain/Loss (Raw)": 2.150132894515991, "Pretrain/Step": 6291, "Pretrain/Step Time": 8.796781118959188} +{"Pretrain/Learning Rate": 1.3704357316976623e-05, "Pretrain/Loss": 2.0379586219787598, "Pretrain/Loss (Raw)": 2.0645482540130615, "Pretrain/Step": 6292, "Pretrain/Step Time": 8.79748061299324} +{"Pretrain/Learning Rate": 1.3696784099721143e-05, "Pretrain/Loss": 2.0400137901306152, "Pretrain/Loss (Raw)": 2.1274571418762207, "Pretrain/Step": 6293, "Pretrain/Step Time": 8.800997355952859} +{"Pretrain/Learning Rate": 1.3689212186005784e-05, "Pretrain/Loss": 2.044057846069336, "Pretrain/Loss (Raw)": 2.3959100246429443, "Pretrain/Step": 6294, "Pretrain/Step Time": 8.8026626072824} +{"Pretrain/Learning Rate": 1.3681641576703763e-05, "Pretrain/Loss": 2.042515993118286, "Pretrain/Loss (Raw)": 1.9618805646896362, "Pretrain/Step": 6295, "Pretrain/Step Time": 8.807021534070373} +{"Pretrain/Learning Rate": 1.3674072272688182e-05, "Pretrain/Loss": 2.0416817665100098, "Pretrain/Loss (Raw)": 2.2366178035736084, "Pretrain/Step": 6296, "Pretrain/Step Time": 8.804858276620507} +{"Pretrain/Learning Rate": 1.3666504274831954e-05, "Pretrain/Loss": 2.0432231426239014, "Pretrain/Loss (Raw)": 2.2712666988372803, "Pretrain/Step": 6297, "Pretrain/Step Time": 8.804223960265517} +{"Pretrain/Learning Rate": 1.3658937584007859e-05, "Pretrain/Loss": 2.0429649353027344, "Pretrain/Loss (Raw)": 1.917731761932373, "Pretrain/Step": 6298, "Pretrain/Step Time": 8.805417934432626} +{"Pretrain/Learning Rate": 1.3651372201088508e-05, "Pretrain/Loss": 2.0434341430664062, "Pretrain/Loss (Raw)": 2.1139001846313477, "Pretrain/Step": 6299, "Pretrain/Step Time": 8.815259670838714} +{"Pretrain/Learning Rate": 1.3643808126946417e-05, "Pretrain/Loss": 2.0422682762145996, "Pretrain/Loss (Raw)": 1.7929943799972534, "Pretrain/Step": 6300, "Pretrain/Step Time": 8.812149181962013} +{"Pretrain/Learning Rate": 1.3636245362453865e-05, "Pretrain/Loss": 2.044849395751953, "Pretrain/Loss (Raw)": 2.262637138366699, "Pretrain/Step": 6301, "Pretrain/Step Time": 8.810642020776868} +{"Pretrain/Learning Rate": 1.3628683908483054e-05, "Pretrain/Loss": 2.0447072982788086, "Pretrain/Loss (Raw)": 2.08695650100708, "Pretrain/Step": 6302, "Pretrain/Step Time": 8.809764811769128} +{"Pretrain/Learning Rate": 1.3621123765905985e-05, "Pretrain/Loss": 2.044245719909668, "Pretrain/Loss (Raw)": 1.9596595764160156, "Pretrain/Step": 6303, "Pretrain/Step Time": 8.80309633165598} +{"Pretrain/Learning Rate": 1.3613564935594565e-05, "Pretrain/Loss": 2.0431880950927734, "Pretrain/Loss (Raw)": 1.981552004814148, "Pretrain/Step": 6304, "Pretrain/Step Time": 8.803894808515906} +{"Pretrain/Learning Rate": 1.3606007418420472e-05, "Pretrain/Loss": 2.0427355766296387, "Pretrain/Loss (Raw)": 2.0256898403167725, "Pretrain/Step": 6305, "Pretrain/Step Time": 8.805324809625745} +{"Pretrain/Learning Rate": 1.3598451215255303e-05, "Pretrain/Loss": 2.0441911220550537, "Pretrain/Loss (Raw)": 2.1680095195770264, "Pretrain/Step": 6306, "Pretrain/Step Time": 8.80025783367455} +{"Pretrain/Learning Rate": 1.3590896326970465e-05, "Pretrain/Loss": 2.0449976921081543, "Pretrain/Loss (Raw)": 2.047811269760132, "Pretrain/Step": 6307, "Pretrain/Step Time": 8.802824465557933} +{"Pretrain/Learning Rate": 1.3583342754437226e-05, "Pretrain/Loss": 2.047144889831543, "Pretrain/Loss (Raw)": 2.247157096862793, "Pretrain/Step": 6308, "Pretrain/Step Time": 8.80476007424295} +{"Pretrain/Learning Rate": 1.3575790498526687e-05, "Pretrain/Loss": 2.050795555114746, "Pretrain/Loss (Raw)": 2.461056709289551, "Pretrain/Step": 6309, "Pretrain/Step Time": 8.804652916267514} +{"Pretrain/Learning Rate": 1.356823956010983e-05, "Pretrain/Loss": 2.0515851974487305, "Pretrain/Loss (Raw)": 2.1046969890594482, "Pretrain/Step": 6310, "Pretrain/Step Time": 8.799672525376081} +{"Pretrain/Learning Rate": 1.3560689940057453e-05, "Pretrain/Loss": 2.0477354526519775, "Pretrain/Loss (Raw)": 1.9087271690368652, "Pretrain/Step": 6311, "Pretrain/Step Time": 8.798239950090647} +{"Pretrain/Learning Rate": 1.3553141639240218e-05, "Pretrain/Loss": 2.0476765632629395, "Pretrain/Loss (Raw)": 1.9548170566558838, "Pretrain/Step": 6312, "Pretrain/Step Time": 8.800910744816065} +{"Pretrain/Learning Rate": 1.354559465852862e-05, "Pretrain/Loss": 2.048574447631836, "Pretrain/Loss (Raw)": 2.0665488243103027, "Pretrain/Step": 6313, "Pretrain/Step Time": 8.79802361689508} +{"Pretrain/Learning Rate": 1.353804899879303e-05, "Pretrain/Loss": 2.0487117767333984, "Pretrain/Loss (Raw)": 1.989318609237671, "Pretrain/Step": 6314, "Pretrain/Step Time": 8.798737654462457} +{"Pretrain/Learning Rate": 1.3530504660903637e-05, "Pretrain/Loss": 2.0495402812957764, "Pretrain/Loss (Raw)": 2.2048416137695312, "Pretrain/Step": 6315, "Pretrain/Step Time": 8.7972562443465} +{"Pretrain/Learning Rate": 1.3522961645730498e-05, "Pretrain/Loss": 2.050374984741211, "Pretrain/Loss (Raw)": 2.1431338787078857, "Pretrain/Step": 6316, "Pretrain/Step Time": 8.80144403129816} +{"Pretrain/Learning Rate": 1.3515419954143489e-05, "Pretrain/Loss": 2.0506768226623535, "Pretrain/Loss (Raw)": 2.0299572944641113, "Pretrain/Step": 6317, "Pretrain/Step Time": 8.805699346587062} +{"Pretrain/Learning Rate": 1.3507879587012378e-05, "Pretrain/Loss": 2.050370931625366, "Pretrain/Loss (Raw)": 2.0170187950134277, "Pretrain/Step": 6318, "Pretrain/Step Time": 8.804636355489492} +{"Pretrain/Learning Rate": 1.3500340545206747e-05, "Pretrain/Loss": 2.049844264984131, "Pretrain/Loss (Raw)": 1.9935766458511353, "Pretrain/Step": 6319, "Pretrain/Step Time": 8.804849993437529} +{"Pretrain/Learning Rate": 1.3492802829596035e-05, "Pretrain/Loss": 2.0488243103027344, "Pretrain/Loss (Raw)": 1.9079595804214478, "Pretrain/Step": 6320, "Pretrain/Step Time": 8.811038546264172} +{"Pretrain/Learning Rate": 1.348526644104951e-05, "Pretrain/Loss": 2.051754951477051, "Pretrain/Loss (Raw)": 2.205197334289551, "Pretrain/Step": 6321, "Pretrain/Step Time": 8.800158835947514} +{"Pretrain/Learning Rate": 1.3477731380436332e-05, "Pretrain/Loss": 2.0525662899017334, "Pretrain/Loss (Raw)": 2.1693811416625977, "Pretrain/Step": 6322, "Pretrain/Step Time": 8.800727356225252} +{"Pretrain/Learning Rate": 1.3470197648625463e-05, "Pretrain/Loss": 2.0512731075286865, "Pretrain/Loss (Raw)": 1.85953688621521, "Pretrain/Step": 6323, "Pretrain/Step Time": 8.80093913897872} +{"Pretrain/Learning Rate": 1.3462665246485734e-05, "Pretrain/Loss": 2.052797317504883, "Pretrain/Loss (Raw)": 2.0463812351226807, "Pretrain/Step": 6324, "Pretrain/Step Time": 8.800311705097556} +{"Pretrain/Learning Rate": 1.3455134174885802e-05, "Pretrain/Loss": 2.0510895252227783, "Pretrain/Loss (Raw)": 1.985363483428955, "Pretrain/Step": 6325, "Pretrain/Step Time": 8.80035837367177} +{"Pretrain/Learning Rate": 1.3447604434694207e-05, "Pretrain/Loss": 2.0501527786254883, "Pretrain/Loss (Raw)": 1.9322937726974487, "Pretrain/Step": 6326, "Pretrain/Step Time": 8.795934544876218} +{"Pretrain/Learning Rate": 1.3440076026779309e-05, "Pretrain/Loss": 2.0505757331848145, "Pretrain/Loss (Raw)": 2.0044989585876465, "Pretrain/Step": 6327, "Pretrain/Step Time": 8.799575785174966} +{"Pretrain/Learning Rate": 1.3432548952009313e-05, "Pretrain/Loss": 2.0505452156066895, "Pretrain/Loss (Raw)": 2.0348904132843018, "Pretrain/Step": 6328, "Pretrain/Step Time": 8.796871740370989} +{"Pretrain/Learning Rate": 1.3425023211252272e-05, "Pretrain/Loss": 2.0502078533172607, "Pretrain/Loss (Raw)": 1.852423071861267, "Pretrain/Step": 6329, "Pretrain/Step Time": 8.796657234430313} +{"Pretrain/Learning Rate": 1.3417498805376105e-05, "Pretrain/Loss": 2.0501275062561035, "Pretrain/Loss (Raw)": 1.9507503509521484, "Pretrain/Step": 6330, "Pretrain/Step Time": 8.806022001430392} +{"Pretrain/Learning Rate": 1.3409975735248556e-05, "Pretrain/Loss": 2.0510480403900146, "Pretrain/Loss (Raw)": 2.1495885848999023, "Pretrain/Step": 6331, "Pretrain/Step Time": 8.803722068667412} +{"Pretrain/Learning Rate": 1.3402454001737209e-05, "Pretrain/Loss": 2.0528321266174316, "Pretrain/Loss (Raw)": 2.1892218589782715, "Pretrain/Step": 6332, "Pretrain/Step Time": 8.802909329533577} +{"Pretrain/Learning Rate": 1.3394933605709525e-05, "Pretrain/Loss": 2.0524120330810547, "Pretrain/Loss (Raw)": 1.9988017082214355, "Pretrain/Step": 6333, "Pretrain/Step Time": 8.803193658590317} +{"Pretrain/Learning Rate": 1.3387414548032783e-05, "Pretrain/Loss": 2.0537455081939697, "Pretrain/Loss (Raw)": 2.19380784034729, "Pretrain/Step": 6334, "Pretrain/Step Time": 8.802123446017504} +{"Pretrain/Learning Rate": 1.3379896829574115e-05, "Pretrain/Loss": 2.056182861328125, "Pretrain/Loss (Raw)": 2.2611372470855713, "Pretrain/Step": 6335, "Pretrain/Step Time": 8.792094208300114} +{"Pretrain/Learning Rate": 1.337238045120049e-05, "Pretrain/Loss": 2.057258129119873, "Pretrain/Loss (Raw)": 2.147643566131592, "Pretrain/Step": 6336, "Pretrain/Step Time": 8.79476622492075} +{"Pretrain/Learning Rate": 1.3364865413778755e-05, "Pretrain/Loss": 2.056809425354004, "Pretrain/Loss (Raw)": 2.0419604778289795, "Pretrain/Step": 6337, "Pretrain/Step Time": 8.797945892438293} +{"Pretrain/Learning Rate": 1.3357351718175564e-05, "Pretrain/Loss": 2.0569798946380615, "Pretrain/Loss (Raw)": 2.078185558319092, "Pretrain/Step": 6338, "Pretrain/Step Time": 8.800269573926926} +{"Pretrain/Learning Rate": 1.3349839365257438e-05, "Pretrain/Loss": 2.0578370094299316, "Pretrain/Loss (Raw)": 2.118506908416748, "Pretrain/Step": 6339, "Pretrain/Step Time": 8.796653317287564} +{"Pretrain/Learning Rate": 1.3342328355890721e-05, "Pretrain/Loss": 2.058431625366211, "Pretrain/Loss (Raw)": 2.2230846881866455, "Pretrain/Step": 6340, "Pretrain/Step Time": 8.797905806452036} +{"Pretrain/Learning Rate": 1.3334818690941652e-05, "Pretrain/Loss": 2.056532859802246, "Pretrain/Loss (Raw)": 1.718900203704834, "Pretrain/Step": 6341, "Pretrain/Step Time": 8.805288968607783} +{"Pretrain/Learning Rate": 1.332731037127624e-05, "Pretrain/Loss": 2.0551834106445312, "Pretrain/Loss (Raw)": 2.2376396656036377, "Pretrain/Step": 6342, "Pretrain/Step Time": 8.804939549416304} +{"Pretrain/Learning Rate": 1.3319803397760408e-05, "Pretrain/Loss": 2.0553693771362305, "Pretrain/Loss (Raw)": 2.1347897052764893, "Pretrain/Step": 6343, "Pretrain/Step Time": 8.793173367157578} +{"Pretrain/Learning Rate": 1.331229777125988e-05, "Pretrain/Loss": 2.0532636642456055, "Pretrain/Loss (Raw)": 1.7469582557678223, "Pretrain/Step": 6344, "Pretrain/Step Time": 8.795585628598928} +{"Pretrain/Learning Rate": 1.3304793492640263e-05, "Pretrain/Loss": 2.051422357559204, "Pretrain/Loss (Raw)": 1.96010160446167, "Pretrain/Step": 6345, "Pretrain/Step Time": 8.796522499993443} +{"Pretrain/Learning Rate": 1.329729056276695e-05, "Pretrain/Loss": 2.051274061203003, "Pretrain/Loss (Raw)": 2.1373229026794434, "Pretrain/Step": 6346, "Pretrain/Step Time": 8.794774696230888} +{"Pretrain/Learning Rate": 1.328978898250525e-05, "Pretrain/Loss": 2.0511491298675537, "Pretrain/Loss (Raw)": 2.062765121459961, "Pretrain/Step": 6347, "Pretrain/Step Time": 8.794286334887147} +{"Pretrain/Learning Rate": 1.3282288752720262e-05, "Pretrain/Loss": 2.051096200942993, "Pretrain/Loss (Raw)": 1.958506464958191, "Pretrain/Step": 6348, "Pretrain/Step Time": 8.804176541045308} +{"Pretrain/Learning Rate": 1.3274789874276949e-05, "Pretrain/Loss": 2.050457000732422, "Pretrain/Loss (Raw)": 1.861778974533081, "Pretrain/Step": 6349, "Pretrain/Step Time": 8.799273470416665} +{"Pretrain/Learning Rate": 1.3267292348040111e-05, "Pretrain/Loss": 2.0487122535705566, "Pretrain/Loss (Raw)": 1.9654972553253174, "Pretrain/Step": 6350, "Pretrain/Step Time": 8.801205188035965} +{"Pretrain/Learning Rate": 1.3259796174874411e-05, "Pretrain/Loss": 2.0475339889526367, "Pretrain/Loss (Raw)": 2.0177361965179443, "Pretrain/Step": 6351, "Pretrain/Step Time": 8.799742065370083} +{"Pretrain/Learning Rate": 1.3252301355644341e-05, "Pretrain/Loss": 2.047886848449707, "Pretrain/Loss (Raw)": 2.0395588874816895, "Pretrain/Step": 6352, "Pretrain/Step Time": 8.802620192989707} +{"Pretrain/Learning Rate": 1.324480789121424e-05, "Pretrain/Loss": 2.046678304672241, "Pretrain/Loss (Raw)": 1.8355836868286133, "Pretrain/Step": 6353, "Pretrain/Step Time": 8.798018859699368} +{"Pretrain/Learning Rate": 1.323731578244827e-05, "Pretrain/Loss": 2.0463714599609375, "Pretrain/Loss (Raw)": 1.9773725271224976, "Pretrain/Step": 6354, "Pretrain/Step Time": 8.799626713618636} +{"Pretrain/Learning Rate": 1.3229825030210482e-05, "Pretrain/Loss": 2.0458598136901855, "Pretrain/Loss (Raw)": 2.0957937240600586, "Pretrain/Step": 6355, "Pretrain/Step Time": 8.796716466546059} +{"Pretrain/Learning Rate": 1.3222335635364736e-05, "Pretrain/Loss": 2.046656608581543, "Pretrain/Loss (Raw)": 2.1267879009246826, "Pretrain/Step": 6356, "Pretrain/Step Time": 8.801764426752925} +{"Pretrain/Learning Rate": 1.3214847598774744e-05, "Pretrain/Loss": 2.0466203689575195, "Pretrain/Loss (Raw)": 2.007654905319214, "Pretrain/Step": 6357, "Pretrain/Step Time": 8.804126039147377} +{"Pretrain/Learning Rate": 1.3207360921304046e-05, "Pretrain/Loss": 2.0473852157592773, "Pretrain/Loss (Raw)": 1.8340498208999634, "Pretrain/Step": 6358, "Pretrain/Step Time": 8.800585882738233} +{"Pretrain/Learning Rate": 1.319987560381607e-05, "Pretrain/Loss": 2.048039436340332, "Pretrain/Loss (Raw)": 2.1116461753845215, "Pretrain/Step": 6359, "Pretrain/Step Time": 8.799530634656549} +{"Pretrain/Learning Rate": 1.319239164717404e-05, "Pretrain/Loss": 2.0487163066864014, "Pretrain/Loss (Raw)": 2.0647060871124268, "Pretrain/Step": 6360, "Pretrain/Step Time": 8.79752797074616} +{"Pretrain/Learning Rate": 1.3184909052241046e-05, "Pretrain/Loss": 2.050549030303955, "Pretrain/Loss (Raw)": 2.143214702606201, "Pretrain/Step": 6361, "Pretrain/Step Time": 8.798809798434377} +{"Pretrain/Learning Rate": 1.3177427819880002e-05, "Pretrain/Loss": 2.0520362854003906, "Pretrain/Loss (Raw)": 2.1959750652313232, "Pretrain/Step": 6362, "Pretrain/Step Time": 8.800235563889146} +{"Pretrain/Learning Rate": 1.3169947950953704e-05, "Pretrain/Loss": 2.054008960723877, "Pretrain/Loss (Raw)": 2.0548434257507324, "Pretrain/Step": 6363, "Pretrain/Step Time": 8.7931073512882} +{"Pretrain/Learning Rate": 1.3162469446324755e-05, "Pretrain/Loss": 2.0556745529174805, "Pretrain/Loss (Raw)": 1.998232126235962, "Pretrain/Step": 6364, "Pretrain/Step Time": 8.793164603412151} +{"Pretrain/Learning Rate": 1.3154992306855607e-05, "Pretrain/Loss": 2.053821325302124, "Pretrain/Loss (Raw)": 2.0116987228393555, "Pretrain/Step": 6365, "Pretrain/Step Time": 8.798311157152057} +{"Pretrain/Learning Rate": 1.3147516533408552e-05, "Pretrain/Loss": 2.0555973052978516, "Pretrain/Loss (Raw)": 2.2020795345306396, "Pretrain/Step": 6366, "Pretrain/Step Time": 8.793554656207561} +{"Pretrain/Learning Rate": 1.3140042126845753e-05, "Pretrain/Loss": 2.0555572509765625, "Pretrain/Loss (Raw)": 2.149487018585205, "Pretrain/Step": 6367, "Pretrain/Step Time": 8.796377927064896} +{"Pretrain/Learning Rate": 1.3132569088029179e-05, "Pretrain/Loss": 2.0551204681396484, "Pretrain/Loss (Raw)": 2.007469415664673, "Pretrain/Step": 6368, "Pretrain/Step Time": 8.794338593259454} +{"Pretrain/Learning Rate": 1.312509741782066e-05, "Pretrain/Loss": 2.0571043491363525, "Pretrain/Loss (Raw)": 2.250572443008423, "Pretrain/Step": 6369, "Pretrain/Step Time": 8.78336282633245} +{"Pretrain/Learning Rate": 1.3117627117081854e-05, "Pretrain/Loss": 2.058854579925537, "Pretrain/Loss (Raw)": 2.1307125091552734, "Pretrain/Step": 6370, "Pretrain/Step Time": 8.791657345369458} +{"Pretrain/Learning Rate": 1.3110158186674293e-05, "Pretrain/Loss": 2.0620651245117188, "Pretrain/Loss (Raw)": 2.023425579071045, "Pretrain/Step": 6371, "Pretrain/Step Time": 8.788137126713991} +{"Pretrain/Learning Rate": 1.3102690627459314e-05, "Pretrain/Loss": 2.061884880065918, "Pretrain/Loss (Raw)": 2.046997308731079, "Pretrain/Step": 6372, "Pretrain/Step Time": 8.792503636330366} +{"Pretrain/Learning Rate": 1.30952244402981e-05, "Pretrain/Loss": 2.062833309173584, "Pretrain/Loss (Raw)": 2.102135419845581, "Pretrain/Step": 6373, "Pretrain/Step Time": 8.791053049266338} +{"Pretrain/Learning Rate": 1.3087759626051716e-05, "Pretrain/Loss": 2.062936782836914, "Pretrain/Loss (Raw)": 2.143279790878296, "Pretrain/Step": 6374, "Pretrain/Step Time": 8.794208256527781} +{"Pretrain/Learning Rate": 1.308029618558102e-05, "Pretrain/Loss": 2.0618834495544434, "Pretrain/Loss (Raw)": 2.0062897205352783, "Pretrain/Step": 6375, "Pretrain/Step Time": 8.795796172693372} +{"Pretrain/Learning Rate": 1.3072834119746741e-05, "Pretrain/Loss": 2.0603995323181152, "Pretrain/Loss (Raw)": 2.030255079269409, "Pretrain/Step": 6376, "Pretrain/Step Time": 8.797099940478802} +{"Pretrain/Learning Rate": 1.3065373429409419e-05, "Pretrain/Loss": 2.0614492893218994, "Pretrain/Loss (Raw)": 2.1802921295166016, "Pretrain/Step": 6377, "Pretrain/Step Time": 8.805609656497836} +{"Pretrain/Learning Rate": 1.3057914115429482e-05, "Pretrain/Loss": 2.062566041946411, "Pretrain/Loss (Raw)": 2.1923367977142334, "Pretrain/Step": 6378, "Pretrain/Step Time": 8.807026030495763} +{"Pretrain/Learning Rate": 1.3050456178667165e-05, "Pretrain/Loss": 2.0588791370391846, "Pretrain/Loss (Raw)": 1.6743791103363037, "Pretrain/Step": 6379, "Pretrain/Step Time": 8.811399925500154} +{"Pretrain/Learning Rate": 1.3042999619982546e-05, "Pretrain/Loss": 2.0606980323791504, "Pretrain/Loss (Raw)": 2.1998989582061768, "Pretrain/Step": 6380, "Pretrain/Step Time": 8.812211589887738} +{"Pretrain/Learning Rate": 1.3035544440235548e-05, "Pretrain/Loss": 2.062617778778076, "Pretrain/Loss (Raw)": 2.2198398113250732, "Pretrain/Step": 6381, "Pretrain/Step Time": 8.808809529989958} +{"Pretrain/Learning Rate": 1.3028090640285958e-05, "Pretrain/Loss": 2.062080144882202, "Pretrain/Loss (Raw)": 2.0058915615081787, "Pretrain/Step": 6382, "Pretrain/Step Time": 8.812141168862581} +{"Pretrain/Learning Rate": 1.3020638220993353e-05, "Pretrain/Loss": 2.061366081237793, "Pretrain/Loss (Raw)": 2.1253626346588135, "Pretrain/Step": 6383, "Pretrain/Step Time": 8.810609076172113} +{"Pretrain/Learning Rate": 1.3013187183217206e-05, "Pretrain/Loss": 2.058530330657959, "Pretrain/Loss (Raw)": 2.029662847518921, "Pretrain/Step": 6384, "Pretrain/Step Time": 8.812145441770554} +{"Pretrain/Learning Rate": 1.3005737527816786e-05, "Pretrain/Loss": 2.058173179626465, "Pretrain/Loss (Raw)": 2.0847723484039307, "Pretrain/Step": 6385, "Pretrain/Step Time": 8.81602575816214} +{"Pretrain/Learning Rate": 1.2998289255651253e-05, "Pretrain/Loss": 2.0583279132843018, "Pretrain/Loss (Raw)": 2.0577847957611084, "Pretrain/Step": 6386, "Pretrain/Step Time": 8.816263237968087} +{"Pretrain/Learning Rate": 1.2990842367579539e-05, "Pretrain/Loss": 2.0592458248138428, "Pretrain/Loss (Raw)": 2.1031386852264404, "Pretrain/Step": 6387, "Pretrain/Step Time": 8.816643862053752} +{"Pretrain/Learning Rate": 1.2983396864460482e-05, "Pretrain/Loss": 2.0594699382781982, "Pretrain/Loss (Raw)": 1.982405185699463, "Pretrain/Step": 6388, "Pretrain/Step Time": 8.81384869478643} +{"Pretrain/Learning Rate": 1.2975952747152709e-05, "Pretrain/Loss": 2.057504653930664, "Pretrain/Loss (Raw)": 2.0112762451171875, "Pretrain/Step": 6389, "Pretrain/Step Time": 8.814479505643249} +{"Pretrain/Learning Rate": 1.2968510016514749e-05, "Pretrain/Loss": 2.0567712783813477, "Pretrain/Loss (Raw)": 1.9534450769424438, "Pretrain/Step": 6390, "Pretrain/Step Time": 8.814217865467072} +{"Pretrain/Learning Rate": 1.2961068673404886e-05, "Pretrain/Loss": 2.0587730407714844, "Pretrain/Loss (Raw)": 2.0689454078674316, "Pretrain/Step": 6391, "Pretrain/Step Time": 8.81736958026886} +{"Pretrain/Learning Rate": 1.295362871868132e-05, "Pretrain/Loss": 2.0606398582458496, "Pretrain/Loss (Raw)": 2.0534310340881348, "Pretrain/Step": 6392, "Pretrain/Step Time": 8.817629471421242} +{"Pretrain/Learning Rate": 1.2946190153202059e-05, "Pretrain/Loss": 2.0618724822998047, "Pretrain/Loss (Raw)": 2.1415598392486572, "Pretrain/Step": 6393, "Pretrain/Step Time": 8.815702496096492} +{"Pretrain/Learning Rate": 1.2938752977824947e-05, "Pretrain/Loss": 2.061636447906494, "Pretrain/Loss (Raw)": 2.11500883102417, "Pretrain/Step": 6394, "Pretrain/Step Time": 8.814040901139379} +{"Pretrain/Learning Rate": 1.2931317193407665e-05, "Pretrain/Loss": 2.060842752456665, "Pretrain/Loss (Raw)": 1.9790598154067993, "Pretrain/Step": 6395, "Pretrain/Step Time": 8.814946997910738} +{"Pretrain/Learning Rate": 1.2923882800807768e-05, "Pretrain/Loss": 2.061732530593872, "Pretrain/Loss (Raw)": 2.0234687328338623, "Pretrain/Step": 6396, "Pretrain/Step Time": 8.814517701044679} +{"Pretrain/Learning Rate": 1.2916449800882607e-05, "Pretrain/Loss": 2.062188148498535, "Pretrain/Loss (Raw)": 2.1828489303588867, "Pretrain/Step": 6397, "Pretrain/Step Time": 8.816865671426058} +{"Pretrain/Learning Rate": 1.2909018194489397e-05, "Pretrain/Loss": 2.0608620643615723, "Pretrain/Loss (Raw)": 1.8882372379302979, "Pretrain/Step": 6398, "Pretrain/Step Time": 8.81510086916387} +{"Pretrain/Learning Rate": 1.2901587982485172e-05, "Pretrain/Loss": 2.0619256496429443, "Pretrain/Loss (Raw)": 2.18755841255188, "Pretrain/Step": 6399, "Pretrain/Step Time": 8.817358501255512} +{"Pretrain/Learning Rate": 1.289415916572684e-05, "Pretrain/Loss": 2.0630855560302734, "Pretrain/Loss (Raw)": 2.181885242462158, "Pretrain/Step": 6400, "Pretrain/Step Time": 8.809231206774712} +{"Pretrain/Learning Rate": 1.2886731745071117e-05, "Pretrain/Loss": 2.0623764991760254, "Pretrain/Loss (Raw)": 1.9034589529037476, "Pretrain/Step": 6401, "Pretrain/Step Time": 8.813981253653765} +{"Pretrain/Learning Rate": 1.287930572137457e-05, "Pretrain/Loss": 2.0622448921203613, "Pretrain/Loss (Raw)": 1.9719818830490112, "Pretrain/Step": 6402, "Pretrain/Step Time": 8.80927773565054} +{"Pretrain/Learning Rate": 1.2871881095493592e-05, "Pretrain/Loss": 2.061858654022217, "Pretrain/Loss (Raw)": 1.9599344730377197, "Pretrain/Step": 6403, "Pretrain/Step Time": 8.807772736996412} +{"Pretrain/Learning Rate": 1.2864457868284446e-05, "Pretrain/Loss": 2.0601038932800293, "Pretrain/Loss (Raw)": 1.9319827556610107, "Pretrain/Step": 6404, "Pretrain/Step Time": 8.810680398717523} +{"Pretrain/Learning Rate": 1.2857036040603205e-05, "Pretrain/Loss": 2.058469295501709, "Pretrain/Loss (Raw)": 1.954136848449707, "Pretrain/Step": 6405, "Pretrain/Step Time": 8.811833444982767} +{"Pretrain/Learning Rate": 1.2849615613305782e-05, "Pretrain/Loss": 2.0589470863342285, "Pretrain/Loss (Raw)": 2.081899642944336, "Pretrain/Step": 6406, "Pretrain/Step Time": 8.806419309228659} +{"Pretrain/Learning Rate": 1.2842196587247935e-05, "Pretrain/Loss": 2.057185649871826, "Pretrain/Loss (Raw)": 2.08719539642334, "Pretrain/Step": 6407, "Pretrain/Step Time": 8.807876912876964} +{"Pretrain/Learning Rate": 1.2834778963285276e-05, "Pretrain/Loss": 2.057291030883789, "Pretrain/Loss (Raw)": 2.1294946670532227, "Pretrain/Step": 6408, "Pretrain/Step Time": 8.806854186579585} +{"Pretrain/Learning Rate": 1.282736274227323e-05, "Pretrain/Loss": 2.0574498176574707, "Pretrain/Loss (Raw)": 2.061899185180664, "Pretrain/Step": 6409, "Pretrain/Step Time": 8.804079281166196} +{"Pretrain/Learning Rate": 1.2819947925067071e-05, "Pretrain/Loss": 2.0574231147766113, "Pretrain/Loss (Raw)": 2.0198752880096436, "Pretrain/Step": 6410, "Pretrain/Step Time": 8.802848346531391} +{"Pretrain/Learning Rate": 1.2812534512521906e-05, "Pretrain/Loss": 2.0609984397888184, "Pretrain/Loss (Raw)": 2.2827813625335693, "Pretrain/Step": 6411, "Pretrain/Step Time": 8.801154784858227} +{"Pretrain/Learning Rate": 1.2805122505492697e-05, "Pretrain/Loss": 2.060108184814453, "Pretrain/Loss (Raw)": 2.08026123046875, "Pretrain/Step": 6412, "Pretrain/Step Time": 8.799260651692748} +{"Pretrain/Learning Rate": 1.2797711904834226e-05, "Pretrain/Loss": 2.0599937438964844, "Pretrain/Loss (Raw)": 1.9520676136016846, "Pretrain/Step": 6413, "Pretrain/Step Time": 8.795128993690014} +{"Pretrain/Learning Rate": 1.279030271140111e-05, "Pretrain/Loss": 2.057753086090088, "Pretrain/Loss (Raw)": 1.6501387357711792, "Pretrain/Step": 6414, "Pretrain/Step Time": 8.802623694762588} +{"Pretrain/Learning Rate": 1.2782894926047822e-05, "Pretrain/Loss": 2.058851480484009, "Pretrain/Loss (Raw)": 2.234393358230591, "Pretrain/Step": 6415, "Pretrain/Step Time": 8.800509482622147} +{"Pretrain/Learning Rate": 1.2775488549628667e-05, "Pretrain/Loss": 2.0600879192352295, "Pretrain/Loss (Raw)": 2.15012526512146, "Pretrain/Step": 6416, "Pretrain/Step Time": 8.798549165949225} +{"Pretrain/Learning Rate": 1.2768083582997772e-05, "Pretrain/Loss": 2.060048818588257, "Pretrain/Loss (Raw)": 2.0491456985473633, "Pretrain/Step": 6417, "Pretrain/Step Time": 8.796315535902977} +{"Pretrain/Learning Rate": 1.2760680027009109e-05, "Pretrain/Loss": 2.0571627616882324, "Pretrain/Loss (Raw)": 1.7455475330352783, "Pretrain/Step": 6418, "Pretrain/Step Time": 8.798150649294257} +{"Pretrain/Learning Rate": 1.2753277882516507e-05, "Pretrain/Loss": 2.0568432807922363, "Pretrain/Loss (Raw)": 2.10921049118042, "Pretrain/Step": 6419, "Pretrain/Step Time": 8.793207559734583} +{"Pretrain/Learning Rate": 1.2745877150373612e-05, "Pretrain/Loss": 2.0580215454101562, "Pretrain/Loss (Raw)": 2.215362071990967, "Pretrain/Step": 6420, "Pretrain/Step Time": 8.798561051487923} +{"Pretrain/Learning Rate": 1.2738477831433904e-05, "Pretrain/Loss": 2.057644844055176, "Pretrain/Loss (Raw)": 2.0792579650878906, "Pretrain/Step": 6421, "Pretrain/Step Time": 8.794491995126009} +{"Pretrain/Learning Rate": 1.2731079926550701e-05, "Pretrain/Loss": 2.054504871368408, "Pretrain/Loss (Raw)": 1.9939905405044556, "Pretrain/Step": 6422, "Pretrain/Step Time": 8.793116871267557} +{"Pretrain/Learning Rate": 1.2723683436577195e-05, "Pretrain/Loss": 2.054368257522583, "Pretrain/Loss (Raw)": 1.9443947076797485, "Pretrain/Step": 6423, "Pretrain/Step Time": 8.790826985612512} +{"Pretrain/Learning Rate": 1.271628836236634e-05, "Pretrain/Loss": 2.0528430938720703, "Pretrain/Loss (Raw)": 2.041400194168091, "Pretrain/Step": 6424, "Pretrain/Step Time": 8.789184277877212} +{"Pretrain/Learning Rate": 1.2708894704771007e-05, "Pretrain/Loss": 2.05047607421875, "Pretrain/Loss (Raw)": 1.9682623147964478, "Pretrain/Step": 6425, "Pretrain/Step Time": 8.787944562733173} +{"Pretrain/Learning Rate": 1.2701502464643844e-05, "Pretrain/Loss": 2.0501961708068848, "Pretrain/Loss (Raw)": 1.881949782371521, "Pretrain/Step": 6426, "Pretrain/Step Time": 8.7913822196424} +{"Pretrain/Learning Rate": 1.2694111642837386e-05, "Pretrain/Loss": 2.049424171447754, "Pretrain/Loss (Raw)": 2.015065908432007, "Pretrain/Step": 6427, "Pretrain/Step Time": 8.786030162125826} +{"Pretrain/Learning Rate": 1.2686722240203946e-05, "Pretrain/Loss": 2.051786422729492, "Pretrain/Loss (Raw)": 2.0953588485717773, "Pretrain/Step": 6428, "Pretrain/Step Time": 8.781942524015903} +{"Pretrain/Learning Rate": 1.2679334257595727e-05, "Pretrain/Loss": 2.0493292808532715, "Pretrain/Loss (Raw)": 1.9481196403503418, "Pretrain/Step": 6429, "Pretrain/Step Time": 8.790755145251751} +{"Pretrain/Learning Rate": 1.2671947695864727e-05, "Pretrain/Loss": 2.0493030548095703, "Pretrain/Loss (Raw)": 2.0836124420166016, "Pretrain/Step": 6430, "Pretrain/Step Time": 8.796143546700478} +{"Pretrain/Learning Rate": 1.266456255586283e-05, "Pretrain/Loss": 2.0493295192718506, "Pretrain/Loss (Raw)": 1.9630224704742432, "Pretrain/Step": 6431, "Pretrain/Step Time": 8.799136495217681} +{"Pretrain/Learning Rate": 1.2657178838441686e-05, "Pretrain/Loss": 2.0503716468811035, "Pretrain/Loss (Raw)": 2.1149702072143555, "Pretrain/Step": 6432, "Pretrain/Step Time": 8.796419560909271} +{"Pretrain/Learning Rate": 1.2649796544452852e-05, "Pretrain/Loss": 2.0493054389953613, "Pretrain/Loss (Raw)": 1.8891767263412476, "Pretrain/Step": 6433, "Pretrain/Step Time": 8.79958252236247} +{"Pretrain/Learning Rate": 1.2642415674747673e-05, "Pretrain/Loss": 2.0466909408569336, "Pretrain/Loss (Raw)": 1.8333698511123657, "Pretrain/Step": 6434, "Pretrain/Step Time": 8.80139241181314} +{"Pretrain/Learning Rate": 1.263503623017735e-05, "Pretrain/Loss": 2.0471673011779785, "Pretrain/Loss (Raw)": 2.1087961196899414, "Pretrain/Step": 6435, "Pretrain/Step Time": 8.796129202470183} +{"Pretrain/Learning Rate": 1.2627658211592907e-05, "Pretrain/Loss": 2.046375274658203, "Pretrain/Loss (Raw)": 2.1457691192626953, "Pretrain/Step": 6436, "Pretrain/Step Time": 8.793714072555304} +{"Pretrain/Learning Rate": 1.262028161984523e-05, "Pretrain/Loss": 2.041165828704834, "Pretrain/Loss (Raw)": 1.7942497730255127, "Pretrain/Step": 6437, "Pretrain/Step Time": 8.794893318787217} +{"Pretrain/Learning Rate": 1.2612906455785006e-05, "Pretrain/Loss": 2.0401687622070312, "Pretrain/Loss (Raw)": 1.9771007299423218, "Pretrain/Step": 6438, "Pretrain/Step Time": 8.79372251778841} +{"Pretrain/Learning Rate": 1.2605532720262785e-05, "Pretrain/Loss": 2.0410988330841064, "Pretrain/Loss (Raw)": 2.0277597904205322, "Pretrain/Step": 6439, "Pretrain/Step Time": 8.793379474431276} +{"Pretrain/Learning Rate": 1.2598160414128924e-05, "Pretrain/Loss": 2.0425899028778076, "Pretrain/Loss (Raw)": 2.145678758621216, "Pretrain/Step": 6440, "Pretrain/Step Time": 8.79065771959722} +{"Pretrain/Learning Rate": 1.2590789538233652e-05, "Pretrain/Loss": 2.042776584625244, "Pretrain/Loss (Raw)": 2.0904436111450195, "Pretrain/Step": 6441, "Pretrain/Step Time": 8.796125462278724} +{"Pretrain/Learning Rate": 1.2583420093427006e-05, "Pretrain/Loss": 2.043083667755127, "Pretrain/Loss (Raw)": 2.0285909175872803, "Pretrain/Step": 6442, "Pretrain/Step Time": 8.785749660804868} +{"Pretrain/Learning Rate": 1.2576052080558864e-05, "Pretrain/Loss": 2.0416059494018555, "Pretrain/Loss (Raw)": 2.0157105922698975, "Pretrain/Step": 6443, "Pretrain/Step Time": 8.790934346616268} +{"Pretrain/Learning Rate": 1.2568685500478927e-05, "Pretrain/Loss": 2.0380403995513916, "Pretrain/Loss (Raw)": 1.6867536306381226, "Pretrain/Step": 6444, "Pretrain/Step Time": 8.787627266719937} +{"Pretrain/Learning Rate": 1.256132035403677e-05, "Pretrain/Loss": 2.036444664001465, "Pretrain/Loss (Raw)": 1.8257231712341309, "Pretrain/Step": 6445, "Pretrain/Step Time": 8.789394810795784} +{"Pretrain/Learning Rate": 1.255395664208176e-05, "Pretrain/Loss": 2.0370097160339355, "Pretrain/Loss (Raw)": 2.0893354415893555, "Pretrain/Step": 6446, "Pretrain/Step Time": 8.791124030947685} +{"Pretrain/Learning Rate": 1.2546594365463119e-05, "Pretrain/Loss": 2.037883758544922, "Pretrain/Loss (Raw)": 2.1054255962371826, "Pretrain/Step": 6447, "Pretrain/Step Time": 8.799492351710796} +{"Pretrain/Learning Rate": 1.2539233525029886e-05, "Pretrain/Loss": 2.0390396118164062, "Pretrain/Loss (Raw)": 2.0559210777282715, "Pretrain/Step": 6448, "Pretrain/Step Time": 8.79159925505519} +{"Pretrain/Learning Rate": 1.2531874121630973e-05, "Pretrain/Loss": 2.036916494369507, "Pretrain/Loss (Raw)": 1.93343985080719, "Pretrain/Step": 6449, "Pretrain/Step Time": 8.796002635732293} +{"Pretrain/Learning Rate": 1.2524516156115088e-05, "Pretrain/Loss": 2.037019968032837, "Pretrain/Loss (Raw)": 2.182617664337158, "Pretrain/Step": 6450, "Pretrain/Step Time": 8.789069131016731} +{"Pretrain/Learning Rate": 1.2517159629330783e-05, "Pretrain/Loss": 2.0368757247924805, "Pretrain/Loss (Raw)": 1.8411107063293457, "Pretrain/Step": 6451, "Pretrain/Step Time": 8.790334088727832} +{"Pretrain/Learning Rate": 1.2509804542126444e-05, "Pretrain/Loss": 2.036292552947998, "Pretrain/Loss (Raw)": 1.9717059135437012, "Pretrain/Step": 6452, "Pretrain/Step Time": 8.792027847841382} +{"Pretrain/Learning Rate": 1.250245089535031e-05, "Pretrain/Loss": 2.03548002243042, "Pretrain/Loss (Raw)": 1.8813642263412476, "Pretrain/Step": 6453, "Pretrain/Step Time": 8.791602797806263} +{"Pretrain/Learning Rate": 1.2495098689850429e-05, "Pretrain/Loss": 2.036402702331543, "Pretrain/Loss (Raw)": 2.0504133701324463, "Pretrain/Step": 6454, "Pretrain/Step Time": 8.793269330635667} +{"Pretrain/Learning Rate": 1.2487747926474683e-05, "Pretrain/Loss": 2.037609577178955, "Pretrain/Loss (Raw)": 2.158945322036743, "Pretrain/Step": 6455, "Pretrain/Step Time": 8.788680866360664} +{"Pretrain/Learning Rate": 1.2480398606070815e-05, "Pretrain/Loss": 2.0377254486083984, "Pretrain/Loss (Raw)": 2.0497243404388428, "Pretrain/Step": 6456, "Pretrain/Step Time": 8.799352863803506} +{"Pretrain/Learning Rate": 1.2473050729486371e-05, "Pretrain/Loss": 2.038323402404785, "Pretrain/Loss (Raw)": 1.9289591312408447, "Pretrain/Step": 6457, "Pretrain/Step Time": 8.798021571710706} +{"Pretrain/Learning Rate": 1.246570429756875e-05, "Pretrain/Loss": 2.040461778640747, "Pretrain/Loss (Raw)": 2.224468469619751, "Pretrain/Step": 6458, "Pretrain/Step Time": 8.79002090729773} +{"Pretrain/Learning Rate": 1.245835931116516e-05, "Pretrain/Loss": 2.0396981239318848, "Pretrain/Loss (Raw)": 2.0518689155578613, "Pretrain/Step": 6459, "Pretrain/Step Time": 8.792049197480083} +{"Pretrain/Learning Rate": 1.2451015771122684e-05, "Pretrain/Loss": 2.0385451316833496, "Pretrain/Loss (Raw)": 2.041597366333008, "Pretrain/Step": 6460, "Pretrain/Step Time": 8.791884867474437} +{"Pretrain/Learning Rate": 1.2443673678288204e-05, "Pretrain/Loss": 2.038956642150879, "Pretrain/Loss (Raw)": 2.0515310764312744, "Pretrain/Step": 6461, "Pretrain/Step Time": 8.797325406223536} +{"Pretrain/Learning Rate": 1.243633303350844e-05, "Pretrain/Loss": 2.0373706817626953, "Pretrain/Loss (Raw)": 1.990770936012268, "Pretrain/Step": 6462, "Pretrain/Step Time": 8.798982962965965} +{"Pretrain/Learning Rate": 1.2428993837629943e-05, "Pretrain/Loss": 2.035522222518921, "Pretrain/Loss (Raw)": 2.024533748626709, "Pretrain/Step": 6463, "Pretrain/Step Time": 8.807830965146422} +{"Pretrain/Learning Rate": 1.2421656091499123e-05, "Pretrain/Loss": 2.033262014389038, "Pretrain/Loss (Raw)": 1.8583300113677979, "Pretrain/Step": 6464, "Pretrain/Step Time": 8.80706356652081} +{"Pretrain/Learning Rate": 1.2414319795962196e-05, "Pretrain/Loss": 2.0340018272399902, "Pretrain/Loss (Raw)": 2.136650800704956, "Pretrain/Step": 6465, "Pretrain/Step Time": 8.802223829552531} +{"Pretrain/Learning Rate": 1.240698495186521e-05, "Pretrain/Loss": 2.0343775749206543, "Pretrain/Loss (Raw)": 2.126277208328247, "Pretrain/Step": 6466, "Pretrain/Step Time": 8.798879120498896} +{"Pretrain/Learning Rate": 1.2399651560054056e-05, "Pretrain/Loss": 2.031036853790283, "Pretrain/Loss (Raw)": 1.6908870935440063, "Pretrain/Step": 6467, "Pretrain/Step Time": 8.801151404157281} +{"Pretrain/Learning Rate": 1.2392319621374476e-05, "Pretrain/Loss": 2.0295491218566895, "Pretrain/Loss (Raw)": 2.032680034637451, "Pretrain/Step": 6468, "Pretrain/Step Time": 8.799055591225624} +{"Pretrain/Learning Rate": 1.2384989136671987e-05, "Pretrain/Loss": 2.0328078269958496, "Pretrain/Loss (Raw)": 2.1360433101654053, "Pretrain/Step": 6469, "Pretrain/Step Time": 8.795006535947323} +{"Pretrain/Learning Rate": 1.2377660106792005e-05, "Pretrain/Loss": 2.033296585083008, "Pretrain/Loss (Raw)": 2.3001840114593506, "Pretrain/Step": 6470, "Pretrain/Step Time": 8.80822174064815} +{"Pretrain/Learning Rate": 1.2370332532579726e-05, "Pretrain/Loss": 2.033134937286377, "Pretrain/Loss (Raw)": 2.114060878753662, "Pretrain/Step": 6471, "Pretrain/Step Time": 8.805921921506524} +{"Pretrain/Learning Rate": 1.2363006414880236e-05, "Pretrain/Loss": 2.0364959239959717, "Pretrain/Loss (Raw)": 2.177178144454956, "Pretrain/Step": 6472, "Pretrain/Step Time": 8.810007244348526} +{"Pretrain/Learning Rate": 1.235568175453837e-05, "Pretrain/Loss": 2.0365219116210938, "Pretrain/Loss (Raw)": 1.9634435176849365, "Pretrain/Step": 6473, "Pretrain/Step Time": 8.80865079909563} +{"Pretrain/Learning Rate": 1.2348358552398878e-05, "Pretrain/Loss": 2.0372262001037598, "Pretrain/Loss (Raw)": 2.2274487018585205, "Pretrain/Step": 6474, "Pretrain/Step Time": 8.804182317107916} +{"Pretrain/Learning Rate": 1.2341036809306292e-05, "Pretrain/Loss": 2.0366082191467285, "Pretrain/Loss (Raw)": 1.9836716651916504, "Pretrain/Step": 6475, "Pretrain/Step Time": 8.804941724985838} +{"Pretrain/Learning Rate": 1.2333716526104993e-05, "Pretrain/Loss": 2.035954475402832, "Pretrain/Loss (Raw)": 1.8748087882995605, "Pretrain/Step": 6476, "Pretrain/Step Time": 8.8000120613724} +{"Pretrain/Learning Rate": 1.2326397703639181e-05, "Pretrain/Loss": 2.0386524200439453, "Pretrain/Loss (Raw)": 2.2071540355682373, "Pretrain/Step": 6477, "Pretrain/Step Time": 8.811893489211798} +{"Pretrain/Learning Rate": 1.2319080342752918e-05, "Pretrain/Loss": 2.039039134979248, "Pretrain/Loss (Raw)": 2.014979839324951, "Pretrain/Step": 6478, "Pretrain/Step Time": 8.808022152632475} +{"Pretrain/Learning Rate": 1.2311764444290061e-05, "Pretrain/Loss": 2.041485071182251, "Pretrain/Loss (Raw)": 2.3308253288269043, "Pretrain/Step": 6479, "Pretrain/Step Time": 8.805977128446102} +{"Pretrain/Learning Rate": 1.2304450009094317e-05, "Pretrain/Loss": 2.041184425354004, "Pretrain/Loss (Raw)": 2.0010738372802734, "Pretrain/Step": 6480, "Pretrain/Step Time": 8.810465384274721} +{"Pretrain/Learning Rate": 1.2297137038009213e-05, "Pretrain/Loss": 2.0419530868530273, "Pretrain/Loss (Raw)": 1.9339840412139893, "Pretrain/Step": 6481, "Pretrain/Step Time": 8.812704212963581} +{"Pretrain/Learning Rate": 1.2289825531878133e-05, "Pretrain/Loss": 2.0434155464172363, "Pretrain/Loss (Raw)": 2.164551258087158, "Pretrain/Step": 6482, "Pretrain/Step Time": 8.80972489528358} +{"Pretrain/Learning Rate": 1.2282515491544264e-05, "Pretrain/Loss": 2.0439720153808594, "Pretrain/Loss (Raw)": 2.166996955871582, "Pretrain/Step": 6483, "Pretrain/Step Time": 8.807120338082314} +{"Pretrain/Learning Rate": 1.2275206917850635e-05, "Pretrain/Loss": 2.0445470809936523, "Pretrain/Loss (Raw)": 2.2004470825195312, "Pretrain/Step": 6484, "Pretrain/Step Time": 8.80774899572134} +{"Pretrain/Learning Rate": 1.22678998116401e-05, "Pretrain/Loss": 2.0450472831726074, "Pretrain/Loss (Raw)": 2.071676254272461, "Pretrain/Step": 6485, "Pretrain/Step Time": 8.807137705385685} +{"Pretrain/Learning Rate": 1.2260594173755358e-05, "Pretrain/Loss": 2.0466864109039307, "Pretrain/Loss (Raw)": 2.0438392162323, "Pretrain/Step": 6486, "Pretrain/Step Time": 8.806445507332683} +{"Pretrain/Learning Rate": 1.2253290005038929e-05, "Pretrain/Loss": 2.04540753364563, "Pretrain/Loss (Raw)": 1.9479414224624634, "Pretrain/Step": 6487, "Pretrain/Step Time": 8.807630315423012} +{"Pretrain/Learning Rate": 1.2245987306333162e-05, "Pretrain/Loss": 2.046433925628662, "Pretrain/Loss (Raw)": 2.196091890335083, "Pretrain/Step": 6488, "Pretrain/Step Time": 8.807556631043553} +{"Pretrain/Learning Rate": 1.2238686078480227e-05, "Pretrain/Loss": 2.0451548099517822, "Pretrain/Loss (Raw)": 1.9795068502426147, "Pretrain/Step": 6489, "Pretrain/Step Time": 8.808109063655138} +{"Pretrain/Learning Rate": 1.2231386322322155e-05, "Pretrain/Loss": 2.044067859649658, "Pretrain/Loss (Raw)": 2.0568487644195557, "Pretrain/Step": 6490, "Pretrain/Step Time": 8.805629570037127} +{"Pretrain/Learning Rate": 1.2224088038700782e-05, "Pretrain/Loss": 2.04310941696167, "Pretrain/Loss (Raw)": 1.9321569204330444, "Pretrain/Step": 6491, "Pretrain/Step Time": 8.806230541318655} +{"Pretrain/Learning Rate": 1.2216791228457778e-05, "Pretrain/Loss": 2.0406861305236816, "Pretrain/Loss (Raw)": 1.6880382299423218, "Pretrain/Step": 6492, "Pretrain/Step Time": 8.805963438004255} +{"Pretrain/Learning Rate": 1.2209495892434635e-05, "Pretrain/Loss": 2.0409297943115234, "Pretrain/Loss (Raw)": 2.042894124984741, "Pretrain/Step": 6493, "Pretrain/Step Time": 8.799927586689591} +{"Pretrain/Learning Rate": 1.2202202031472707e-05, "Pretrain/Loss": 2.039506435394287, "Pretrain/Loss (Raw)": 2.019895553588867, "Pretrain/Step": 6494, "Pretrain/Step Time": 8.806866666302085} +{"Pretrain/Learning Rate": 1.2194909646413147e-05, "Pretrain/Loss": 2.038714647293091, "Pretrain/Loss (Raw)": 2.048121452331543, "Pretrain/Step": 6495, "Pretrain/Step Time": 8.805025136098266} +{"Pretrain/Learning Rate": 1.2187618738096934e-05, "Pretrain/Loss": 2.040370464324951, "Pretrain/Loss (Raw)": 2.2194228172302246, "Pretrain/Step": 6496, "Pretrain/Step Time": 8.804357569664717} +{"Pretrain/Learning Rate": 1.2180329307364916e-05, "Pretrain/Loss": 2.038569450378418, "Pretrain/Loss (Raw)": 2.020062208175659, "Pretrain/Step": 6497, "Pretrain/Step Time": 8.812247265130281} +{"Pretrain/Learning Rate": 1.2173041355057727e-05, "Pretrain/Loss": 2.038339614868164, "Pretrain/Loss (Raw)": 2.101271867752075, "Pretrain/Step": 6498, "Pretrain/Step Time": 8.804933127015829} +{"Pretrain/Learning Rate": 1.216575488201585e-05, "Pretrain/Loss": 2.0389647483825684, "Pretrain/Loss (Raw)": 2.1034367084503174, "Pretrain/Step": 6499, "Pretrain/Step Time": 8.806654885411263} +{"Pretrain/Learning Rate": 1.215846988907959e-05, "Pretrain/Loss": 2.0386404991149902, "Pretrain/Loss (Raw)": 2.00549054145813, "Pretrain/Step": 6500, "Pretrain/Step Time": 8.801756860688329} +{"Pretrain/Learning Rate": 1.2151186377089105e-05, "Pretrain/Loss": 2.0388259887695312, "Pretrain/Loss (Raw)": 2.1258597373962402, "Pretrain/Step": 6501, "Pretrain/Step Time": 8.805488679558039} +{"Pretrain/Learning Rate": 1.214390434688435e-05, "Pretrain/Loss": 2.038923740386963, "Pretrain/Loss (Raw)": 2.15582013130188, "Pretrain/Step": 6502, "Pretrain/Step Time": 8.801488406956196} +{"Pretrain/Learning Rate": 1.2136623799305127e-05, "Pretrain/Loss": 2.039656639099121, "Pretrain/Loss (Raw)": 2.1000888347625732, "Pretrain/Step": 6503, "Pretrain/Step Time": 8.801204992458224} +{"Pretrain/Learning Rate": 1.212934473519105e-05, "Pretrain/Loss": 2.0397486686706543, "Pretrain/Loss (Raw)": 2.0420422554016113, "Pretrain/Step": 6504, "Pretrain/Step Time": 8.803480060771108} +{"Pretrain/Learning Rate": 1.2122067155381598e-05, "Pretrain/Loss": 2.0390965938568115, "Pretrain/Loss (Raw)": 2.0968470573425293, "Pretrain/Step": 6505, "Pretrain/Step Time": 8.797534244135022} +{"Pretrain/Learning Rate": 1.2114791060716043e-05, "Pretrain/Loss": 2.037236452102661, "Pretrain/Loss (Raw)": 1.9542189836502075, "Pretrain/Step": 6506, "Pretrain/Step Time": 8.797419590875506} +{"Pretrain/Learning Rate": 1.2107516452033502e-05, "Pretrain/Loss": 2.0396552085876465, "Pretrain/Loss (Raw)": 1.9839714765548706, "Pretrain/Step": 6507, "Pretrain/Step Time": 8.794141074642539} +{"Pretrain/Learning Rate": 1.2100243330172905e-05, "Pretrain/Loss": 2.0388872623443604, "Pretrain/Loss (Raw)": 2.1016101837158203, "Pretrain/Step": 6508, "Pretrain/Step Time": 8.79432095773518} +{"Pretrain/Learning Rate": 1.2092971695973052e-05, "Pretrain/Loss": 2.036386013031006, "Pretrain/Loss (Raw)": 1.8996851444244385, "Pretrain/Step": 6509, "Pretrain/Step Time": 8.796275930479169} +{"Pretrain/Learning Rate": 1.2085701550272502e-05, "Pretrain/Loss": 2.036428451538086, "Pretrain/Loss (Raw)": 2.01131534576416, "Pretrain/Step": 6510, "Pretrain/Step Time": 8.79692878946662} +{"Pretrain/Learning Rate": 1.2078432893909714e-05, "Pretrain/Loss": 2.0366313457489014, "Pretrain/Loss (Raw)": 2.1513402462005615, "Pretrain/Step": 6511, "Pretrain/Step Time": 8.803253201767802} +{"Pretrain/Learning Rate": 1.2071165727722925e-05, "Pretrain/Loss": 2.0363051891326904, "Pretrain/Loss (Raw)": 1.9879310131072998, "Pretrain/Step": 6512, "Pretrain/Step Time": 8.790338898077607} +{"Pretrain/Learning Rate": 1.2063900052550246e-05, "Pretrain/Loss": 2.0357632637023926, "Pretrain/Loss (Raw)": 2.0153911113739014, "Pretrain/Step": 6513, "Pretrain/Step Time": 8.788737758994102} +{"Pretrain/Learning Rate": 1.2056635869229549e-05, "Pretrain/Loss": 2.0367515087127686, "Pretrain/Loss (Raw)": 2.1842827796936035, "Pretrain/Step": 6514, "Pretrain/Step Time": 8.788897344842553} +{"Pretrain/Learning Rate": 1.2049373178598606e-05, "Pretrain/Loss": 2.037134885787964, "Pretrain/Loss (Raw)": 2.1521859169006348, "Pretrain/Step": 6515, "Pretrain/Step Time": 8.78850656375289} +{"Pretrain/Learning Rate": 1.2042111981494968e-05, "Pretrain/Loss": 2.037559986114502, "Pretrain/Loss (Raw)": 2.0368261337280273, "Pretrain/Step": 6516, "Pretrain/Step Time": 8.789308615028858} +{"Pretrain/Learning Rate": 1.2034852278756042e-05, "Pretrain/Loss": 2.0372095108032227, "Pretrain/Loss (Raw)": 1.9663976430892944, "Pretrain/Step": 6517, "Pretrain/Step Time": 8.790357578545809} +{"Pretrain/Learning Rate": 1.2027594071219033e-05, "Pretrain/Loss": 2.036762237548828, "Pretrain/Loss (Raw)": 1.8962419033050537, "Pretrain/Step": 6518, "Pretrain/Step Time": 8.791214996948838} +{"Pretrain/Learning Rate": 1.2020337359721015e-05, "Pretrain/Loss": 2.0367355346679688, "Pretrain/Loss (Raw)": 2.0654900074005127, "Pretrain/Step": 6519, "Pretrain/Step Time": 8.789058309048414} +{"Pretrain/Learning Rate": 1.2013082145098852e-05, "Pretrain/Loss": 2.0367746353149414, "Pretrain/Loss (Raw)": 2.0584514141082764, "Pretrain/Step": 6520, "Pretrain/Step Time": 8.786480939015746} +{"Pretrain/Learning Rate": 1.2005828428189256e-05, "Pretrain/Loss": 2.0355374813079834, "Pretrain/Loss (Raw)": 1.9832245111465454, "Pretrain/Step": 6521, "Pretrain/Step Time": 8.786057822406292} +{"Pretrain/Learning Rate": 1.1998576209828743e-05, "Pretrain/Loss": 2.036083936691284, "Pretrain/Loss (Raw)": 2.1849210262298584, "Pretrain/Step": 6522, "Pretrain/Step Time": 8.78979454189539} +{"Pretrain/Learning Rate": 1.19913254908537e-05, "Pretrain/Loss": 2.0362415313720703, "Pretrain/Loss (Raw)": 1.9992560148239136, "Pretrain/Step": 6523, "Pretrain/Step Time": 8.786191763356328} +{"Pretrain/Learning Rate": 1.1984076272100297e-05, "Pretrain/Loss": 2.036003589630127, "Pretrain/Loss (Raw)": 1.9930013418197632, "Pretrain/Step": 6524, "Pretrain/Step Time": 8.785366114228964} +{"Pretrain/Learning Rate": 1.1976828554404552e-05, "Pretrain/Loss": 2.0345871448516846, "Pretrain/Loss (Raw)": 2.001539945602417, "Pretrain/Step": 6525, "Pretrain/Step Time": 8.789990786463022} +{"Pretrain/Learning Rate": 1.1969582338602295e-05, "Pretrain/Loss": 2.0340962409973145, "Pretrain/Loss (Raw)": 1.8254075050354004, "Pretrain/Step": 6526, "Pretrain/Step Time": 8.793571898713708} +{"Pretrain/Learning Rate": 1.1962337625529215e-05, "Pretrain/Loss": 2.034102439880371, "Pretrain/Loss (Raw)": 2.1883339881896973, "Pretrain/Step": 6527, "Pretrain/Step Time": 8.7872408144176} +{"Pretrain/Learning Rate": 1.1955094416020795e-05, "Pretrain/Loss": 2.0324044227600098, "Pretrain/Loss (Raw)": 1.9645583629608154, "Pretrain/Step": 6528, "Pretrain/Step Time": 8.792059514671564} +{"Pretrain/Learning Rate": 1.1947852710912355e-05, "Pretrain/Loss": 2.0340471267700195, "Pretrain/Loss (Raw)": 2.113708257675171, "Pretrain/Step": 6529, "Pretrain/Step Time": 8.784435205161572} +{"Pretrain/Learning Rate": 1.1940612511039038e-05, "Pretrain/Loss": 2.0343728065490723, "Pretrain/Loss (Raw)": 2.013676881790161, "Pretrain/Step": 6530, "Pretrain/Step Time": 8.784851085394621} +{"Pretrain/Learning Rate": 1.1933373817235832e-05, "Pretrain/Loss": 2.0366158485412598, "Pretrain/Loss (Raw)": 2.2470293045043945, "Pretrain/Step": 6531, "Pretrain/Step Time": 8.78464313223958} +{"Pretrain/Learning Rate": 1.1926136630337528e-05, "Pretrain/Loss": 2.0379977226257324, "Pretrain/Loss (Raw)": 2.108900785446167, "Pretrain/Step": 6532, "Pretrain/Step Time": 8.780551765114069} +{"Pretrain/Learning Rate": 1.1918900951178755e-05, "Pretrain/Loss": 2.037248134613037, "Pretrain/Loss (Raw)": 1.8581421375274658, "Pretrain/Step": 6533, "Pretrain/Step Time": 8.780387276783586} +{"Pretrain/Learning Rate": 1.1911666780593955e-05, "Pretrain/Loss": 2.0346643924713135, "Pretrain/Loss (Raw)": 1.7512104511260986, "Pretrain/Step": 6534, "Pretrain/Step Time": 8.786749213933945} +{"Pretrain/Learning Rate": 1.1904434119417426e-05, "Pretrain/Loss": 2.0344505310058594, "Pretrain/Loss (Raw)": 2.0598015785217285, "Pretrain/Step": 6535, "Pretrain/Step Time": 8.783497275784612} +{"Pretrain/Learning Rate": 1.1897202968483263e-05, "Pretrain/Loss": 2.0331263542175293, "Pretrain/Loss (Raw)": 1.9599988460540771, "Pretrain/Step": 6536, "Pretrain/Step Time": 8.781733708456159} +{"Pretrain/Learning Rate": 1.1889973328625384e-05, "Pretrain/Loss": 2.0341176986694336, "Pretrain/Loss (Raw)": 2.1888396739959717, "Pretrain/Step": 6537, "Pretrain/Step Time": 8.785616913810372} +{"Pretrain/Learning Rate": 1.1882745200677569e-05, "Pretrain/Loss": 2.035327434539795, "Pretrain/Loss (Raw)": 2.1746866703033447, "Pretrain/Step": 6538, "Pretrain/Step Time": 8.786416120827198} +{"Pretrain/Learning Rate": 1.1875518585473389e-05, "Pretrain/Loss": 2.0331437587738037, "Pretrain/Loss (Raw)": 2.003282070159912, "Pretrain/Step": 6539, "Pretrain/Step Time": 8.787855101749301} +{"Pretrain/Learning Rate": 1.1868293483846247e-05, "Pretrain/Loss": 2.0320749282836914, "Pretrain/Loss (Raw)": 1.9434723854064941, "Pretrain/Step": 6540, "Pretrain/Step Time": 8.789152916520834} +{"Pretrain/Learning Rate": 1.186106989662937e-05, "Pretrain/Loss": 2.0328640937805176, "Pretrain/Loss (Raw)": 2.053074836730957, "Pretrain/Step": 6541, "Pretrain/Step Time": 8.787427989766002} +{"Pretrain/Learning Rate": 1.1853847824655836e-05, "Pretrain/Loss": 2.0366358757019043, "Pretrain/Loss (Raw)": 2.1328885555267334, "Pretrain/Step": 6542, "Pretrain/Step Time": 8.784019738435745} +{"Pretrain/Learning Rate": 1.184662726875852e-05, "Pretrain/Loss": 2.034773826599121, "Pretrain/Loss (Raw)": 1.996084213256836, "Pretrain/Step": 6543, "Pretrain/Step Time": 8.785532798618078} +{"Pretrain/Learning Rate": 1.1839408229770124e-05, "Pretrain/Loss": 2.0297744274139404, "Pretrain/Loss (Raw)": 1.5101712942123413, "Pretrain/Step": 6544, "Pretrain/Step Time": 8.790425987914205} +{"Pretrain/Learning Rate": 1.183219070852318e-05, "Pretrain/Loss": 2.028886556625366, "Pretrain/Loss (Raw)": 1.9355171918869019, "Pretrain/Step": 6545, "Pretrain/Step Time": 8.794863866642118} +{"Pretrain/Learning Rate": 1.1824974705850058e-05, "Pretrain/Loss": 2.0319600105285645, "Pretrain/Loss (Raw)": 2.1389479637145996, "Pretrain/Step": 6546, "Pretrain/Step Time": 8.792890967801213} +{"Pretrain/Learning Rate": 1.1817760222582938e-05, "Pretrain/Loss": 2.0330300331115723, "Pretrain/Loss (Raw)": 2.246197462081909, "Pretrain/Step": 6547, "Pretrain/Step Time": 8.793539000675082} +{"Pretrain/Learning Rate": 1.1810547259553826e-05, "Pretrain/Loss": 2.0314106941223145, "Pretrain/Loss (Raw)": 2.0080699920654297, "Pretrain/Step": 6548, "Pretrain/Step Time": 8.78070466965437} +{"Pretrain/Learning Rate": 1.1803335817594544e-05, "Pretrain/Loss": 2.0315117835998535, "Pretrain/Loss (Raw)": 2.0921969413757324, "Pretrain/Step": 6549, "Pretrain/Step Time": 8.78271435201168} +{"Pretrain/Learning Rate": 1.179612589753678e-05, "Pretrain/Loss": 2.031733751296997, "Pretrain/Loss (Raw)": 2.022402048110962, "Pretrain/Step": 6550, "Pretrain/Step Time": 8.787629809230566} +{"Pretrain/Learning Rate": 1.1788917500211976e-05, "Pretrain/Loss": 2.032198429107666, "Pretrain/Loss (Raw)": 2.0038623809814453, "Pretrain/Step": 6551, "Pretrain/Step Time": 8.78681781515479} +{"Pretrain/Learning Rate": 1.178171062645147e-05, "Pretrain/Loss": 2.032046318054199, "Pretrain/Loss (Raw)": 2.0219156742095947, "Pretrain/Step": 6552, "Pretrain/Step Time": 8.795494621619582} +{"Pretrain/Learning Rate": 1.177450527708637e-05, "Pretrain/Loss": 2.029801368713379, "Pretrain/Loss (Raw)": 1.6809496879577637, "Pretrain/Step": 6553, "Pretrain/Step Time": 8.797275679185987} +{"Pretrain/Learning Rate": 1.1767301452947663e-05, "Pretrain/Loss": 2.0321035385131836, "Pretrain/Loss (Raw)": 2.1766035556793213, "Pretrain/Step": 6554, "Pretrain/Step Time": 8.798174833878875} +{"Pretrain/Learning Rate": 1.1760099154866086e-05, "Pretrain/Loss": 2.0313167572021484, "Pretrain/Loss (Raw)": 1.9143543243408203, "Pretrain/Step": 6555, "Pretrain/Step Time": 8.794906552881002} +{"Pretrain/Learning Rate": 1.1752898383672273e-05, "Pretrain/Loss": 2.030684471130371, "Pretrain/Loss (Raw)": 2.014432668685913, "Pretrain/Step": 6556, "Pretrain/Step Time": 8.802970182150602} +{"Pretrain/Learning Rate": 1.1745699140196632e-05, "Pretrain/Loss": 2.031184434890747, "Pretrain/Loss (Raw)": 2.012119770050049, "Pretrain/Step": 6557, "Pretrain/Step Time": 8.796299777925014} +{"Pretrain/Learning Rate": 1.1738501425269441e-05, "Pretrain/Loss": 2.0304253101348877, "Pretrain/Loss (Raw)": 1.9864400625228882, "Pretrain/Step": 6558, "Pretrain/Step Time": 8.79273384809494} +{"Pretrain/Learning Rate": 1.1731305239720735e-05, "Pretrain/Loss": 2.029817581176758, "Pretrain/Loss (Raw)": 1.8852280378341675, "Pretrain/Step": 6559, "Pretrain/Step Time": 8.796220978721976} +{"Pretrain/Learning Rate": 1.1724110584380444e-05, "Pretrain/Loss": 2.0296478271484375, "Pretrain/Loss (Raw)": 2.0932328701019287, "Pretrain/Step": 6560, "Pretrain/Step Time": 8.797438533976674} +{"Pretrain/Learning Rate": 1.1716917460078278e-05, "Pretrain/Loss": 2.0314323902130127, "Pretrain/Loss (Raw)": 2.11761212348938, "Pretrain/Step": 6561, "Pretrain/Step Time": 8.793558841571212} +{"Pretrain/Learning Rate": 1.1709725867643784e-05, "Pretrain/Loss": 2.033949375152588, "Pretrain/Loss (Raw)": 2.1555256843566895, "Pretrain/Step": 6562, "Pretrain/Step Time": 8.796661524102092} +{"Pretrain/Learning Rate": 1.1702535807906318e-05, "Pretrain/Loss": 2.0336952209472656, "Pretrain/Loss (Raw)": 2.0762858390808105, "Pretrain/Step": 6563, "Pretrain/Step Time": 8.79726985655725} +{"Pretrain/Learning Rate": 1.1695347281695093e-05, "Pretrain/Loss": 2.0333948135375977, "Pretrain/Loss (Raw)": 2.107320785522461, "Pretrain/Step": 6564, "Pretrain/Step Time": 8.79744841530919} +{"Pretrain/Learning Rate": 1.1688160289839111e-05, "Pretrain/Loss": 2.035922050476074, "Pretrain/Loss (Raw)": 2.1177141666412354, "Pretrain/Step": 6565, "Pretrain/Step Time": 8.796914333477616} +{"Pretrain/Learning Rate": 1.1680974833167214e-05, "Pretrain/Loss": 2.035665988922119, "Pretrain/Loss (Raw)": 1.9443480968475342, "Pretrain/Step": 6566, "Pretrain/Step Time": 8.799821896478534} +{"Pretrain/Learning Rate": 1.1673790912508051e-05, "Pretrain/Loss": 2.0365099906921387, "Pretrain/Loss (Raw)": 2.135763168334961, "Pretrain/Step": 6567, "Pretrain/Step Time": 8.798845876008272} +{"Pretrain/Learning Rate": 1.1666608528690123e-05, "Pretrain/Loss": 2.0354886054992676, "Pretrain/Loss (Raw)": 2.0149500370025635, "Pretrain/Step": 6568, "Pretrain/Step Time": 8.800964815542102} +{"Pretrain/Learning Rate": 1.165942768254173e-05, "Pretrain/Loss": 2.036773681640625, "Pretrain/Loss (Raw)": 2.254965305328369, "Pretrain/Step": 6569, "Pretrain/Step Time": 8.799579938873649} +{"Pretrain/Learning Rate": 1.1652248374890999e-05, "Pretrain/Loss": 2.037689685821533, "Pretrain/Loss (Raw)": 2.1458184719085693, "Pretrain/Step": 6570, "Pretrain/Step Time": 8.801880029961467} +{"Pretrain/Learning Rate": 1.164507060656587e-05, "Pretrain/Loss": 2.0369343757629395, "Pretrain/Loss (Raw)": 1.9190207719802856, "Pretrain/Step": 6571, "Pretrain/Step Time": 8.806413672864437} +{"Pretrain/Learning Rate": 1.163789437839414e-05, "Pretrain/Loss": 2.039355516433716, "Pretrain/Loss (Raw)": 1.9966814517974854, "Pretrain/Step": 6572, "Pretrain/Step Time": 8.808031149208546} +{"Pretrain/Learning Rate": 1.1630719691203395e-05, "Pretrain/Loss": 2.039273262023926, "Pretrain/Loss (Raw)": 1.815198540687561, "Pretrain/Step": 6573, "Pretrain/Step Time": 8.80495279096067} +{"Pretrain/Learning Rate": 1.1623546545821054e-05, "Pretrain/Loss": 2.0399022102355957, "Pretrain/Loss (Raw)": 2.1698248386383057, "Pretrain/Step": 6574, "Pretrain/Step Time": 8.802959930151701} +{"Pretrain/Learning Rate": 1.1616374943074349e-05, "Pretrain/Loss": 2.039551258087158, "Pretrain/Loss (Raw)": 2.0604934692382812, "Pretrain/Step": 6575, "Pretrain/Step Time": 8.79643165320158} +{"Pretrain/Learning Rate": 1.1609204883790359e-05, "Pretrain/Loss": 2.0390028953552246, "Pretrain/Loss (Raw)": 1.985774278640747, "Pretrain/Step": 6576, "Pretrain/Step Time": 8.803051270544529} +{"Pretrain/Learning Rate": 1.1602036368795963e-05, "Pretrain/Loss": 2.0406103134155273, "Pretrain/Loss (Raw)": 2.1391639709472656, "Pretrain/Step": 6577, "Pretrain/Step Time": 8.79784912802279} +{"Pretrain/Learning Rate": 1.1594869398917854e-05, "Pretrain/Loss": 2.039011001586914, "Pretrain/Loss (Raw)": 1.9778926372528076, "Pretrain/Step": 6578, "Pretrain/Step Time": 8.802819604054093} +{"Pretrain/Learning Rate": 1.1587703974982584e-05, "Pretrain/Loss": 2.041529655456543, "Pretrain/Loss (Raw)": 2.163517951965332, "Pretrain/Step": 6579, "Pretrain/Step Time": 8.802543371915817} +{"Pretrain/Learning Rate": 1.1580540097816491e-05, "Pretrain/Loss": 2.0431246757507324, "Pretrain/Loss (Raw)": 2.175872564315796, "Pretrain/Step": 6580, "Pretrain/Step Time": 8.796282213181257} +{"Pretrain/Learning Rate": 1.157337776824575e-05, "Pretrain/Loss": 2.043515205383301, "Pretrain/Loss (Raw)": 1.931322693824768, "Pretrain/Step": 6581, "Pretrain/Step Time": 8.795782485976815} +{"Pretrain/Learning Rate": 1.1566216987096343e-05, "Pretrain/Loss": 2.043613910675049, "Pretrain/Loss (Raw)": 2.063034772872925, "Pretrain/Step": 6582, "Pretrain/Step Time": 8.796094801276922} +{"Pretrain/Learning Rate": 1.1559057755194105e-05, "Pretrain/Loss": 2.0394084453582764, "Pretrain/Loss (Raw)": 1.6206674575805664, "Pretrain/Step": 6583, "Pretrain/Step Time": 8.807721257209778} +{"Pretrain/Learning Rate": 1.1551900073364663e-05, "Pretrain/Loss": 2.040595531463623, "Pretrain/Loss (Raw)": 2.2016518115997314, "Pretrain/Step": 6584, "Pretrain/Step Time": 8.792752381414175} +{"Pretrain/Learning Rate": 1.1544743942433473e-05, "Pretrain/Loss": 2.0402140617370605, "Pretrain/Loss (Raw)": 1.8801509141921997, "Pretrain/Step": 6585, "Pretrain/Step Time": 8.795824974775314} +{"Pretrain/Learning Rate": 1.1537589363225806e-05, "Pretrain/Loss": 2.0379185676574707, "Pretrain/Loss (Raw)": 1.9306570291519165, "Pretrain/Step": 6586, "Pretrain/Step Time": 8.801574999466538} +{"Pretrain/Learning Rate": 1.153043633656678e-05, "Pretrain/Loss": 2.0376696586608887, "Pretrain/Loss (Raw)": 2.0200231075286865, "Pretrain/Step": 6587, "Pretrain/Step Time": 8.796107551082969} +{"Pretrain/Learning Rate": 1.1523284863281306e-05, "Pretrain/Loss": 2.036635398864746, "Pretrain/Loss (Raw)": 1.9091989994049072, "Pretrain/Step": 6588, "Pretrain/Step Time": 8.79951304756105} +{"Pretrain/Learning Rate": 1.1516134944194126e-05, "Pretrain/Loss": 2.0367016792297363, "Pretrain/Loss (Raw)": 2.059986114501953, "Pretrain/Step": 6589, "Pretrain/Step Time": 8.794454066082835} +{"Pretrain/Learning Rate": 1.1508986580129794e-05, "Pretrain/Loss": 2.037328004837036, "Pretrain/Loss (Raw)": 2.0709526538848877, "Pretrain/Step": 6590, "Pretrain/Step Time": 8.800369258970022} +{"Pretrain/Learning Rate": 1.1501839771912718e-05, "Pretrain/Loss": 2.0372238159179688, "Pretrain/Loss (Raw)": 2.01119065284729, "Pretrain/Step": 6591, "Pretrain/Step Time": 8.791856996715069} +{"Pretrain/Learning Rate": 1.1494694520367068e-05, "Pretrain/Loss": 2.0376124382019043, "Pretrain/Loss (Raw)": 1.9080873727798462, "Pretrain/Step": 6592, "Pretrain/Step Time": 8.791111214086413} +{"Pretrain/Learning Rate": 1.1487550826316893e-05, "Pretrain/Loss": 2.035428047180176, "Pretrain/Loss (Raw)": 1.8570324182510376, "Pretrain/Step": 6593, "Pretrain/Step Time": 8.797608507797122} +{"Pretrain/Learning Rate": 1.1480408690586022e-05, "Pretrain/Loss": 2.033876895904541, "Pretrain/Loss (Raw)": 1.9277446269989014, "Pretrain/Step": 6594, "Pretrain/Step Time": 8.797580916434526} +{"Pretrain/Learning Rate": 1.1473268113998146e-05, "Pretrain/Loss": 2.035830497741699, "Pretrain/Loss (Raw)": 1.9409599304199219, "Pretrain/Step": 6595, "Pretrain/Step Time": 8.795543486252427} +{"Pretrain/Learning Rate": 1.146612909737671e-05, "Pretrain/Loss": 2.035125255584717, "Pretrain/Loss (Raw)": 1.9423844814300537, "Pretrain/Step": 6596, "Pretrain/Step Time": 8.796070452779531} +{"Pretrain/Learning Rate": 1.145899164154505e-05, "Pretrain/Loss": 2.034822463989258, "Pretrain/Loss (Raw)": 2.0972797870635986, "Pretrain/Step": 6597, "Pretrain/Step Time": 8.800798490643501} +{"Pretrain/Learning Rate": 1.1451855747326273e-05, "Pretrain/Loss": 2.033087730407715, "Pretrain/Loss (Raw)": 2.0781447887420654, "Pretrain/Step": 6598, "Pretrain/Step Time": 8.787145957350731} +{"Pretrain/Learning Rate": 1.1444721415543349e-05, "Pretrain/Loss": 2.030994415283203, "Pretrain/Loss (Raw)": 1.8461195230484009, "Pretrain/Step": 6599, "Pretrain/Step Time": 8.793017508462071} +{"Pretrain/Learning Rate": 1.143758864701901e-05, "Pretrain/Loss": 2.029956579208374, "Pretrain/Loss (Raw)": 2.0443339347839355, "Pretrain/Step": 6600, "Pretrain/Step Time": 8.793688928708434} +{"Pretrain/Learning Rate": 1.1430457442575863e-05, "Pretrain/Loss": 2.0317277908325195, "Pretrain/Loss (Raw)": 2.190155029296875, "Pretrain/Step": 6601, "Pretrain/Step Time": 8.790612015873194} +{"Pretrain/Learning Rate": 1.1423327803036308e-05, "Pretrain/Loss": 2.030505657196045, "Pretrain/Loss (Raw)": 2.0710322856903076, "Pretrain/Step": 6602, "Pretrain/Step Time": 8.795482810586691} +{"Pretrain/Learning Rate": 1.1416199729222565e-05, "Pretrain/Loss": 2.030064105987549, "Pretrain/Loss (Raw)": 1.927176594734192, "Pretrain/Step": 6603, "Pretrain/Step Time": 8.79895207285881} +{"Pretrain/Learning Rate": 1.1409073221956668e-05, "Pretrain/Loss": 2.030787944793701, "Pretrain/Loss (Raw)": 1.9674296379089355, "Pretrain/Step": 6604, "Pretrain/Step Time": 8.799732815474272} +{"Pretrain/Learning Rate": 1.14019482820605e-05, "Pretrain/Loss": 2.029757022857666, "Pretrain/Loss (Raw)": 2.075234889984131, "Pretrain/Step": 6605, "Pretrain/Step Time": 8.78735720179975} +{"Pretrain/Learning Rate": 1.1394824910355731e-05, "Pretrain/Loss": 2.0298967361450195, "Pretrain/Loss (Raw)": 2.0328023433685303, "Pretrain/Step": 6606, "Pretrain/Step Time": 8.790007930248976} +{"Pretrain/Learning Rate": 1.1387703107663864e-05, "Pretrain/Loss": 2.026671886444092, "Pretrain/Loss (Raw)": 1.9180642366409302, "Pretrain/Step": 6607, "Pretrain/Step Time": 8.794102482497692} +{"Pretrain/Learning Rate": 1.1380582874806209e-05, "Pretrain/Loss": 2.0270397663116455, "Pretrain/Loss (Raw)": 2.0481669902801514, "Pretrain/Step": 6608, "Pretrain/Step Time": 8.786967933177948} +{"Pretrain/Learning Rate": 1.1373464212603923e-05, "Pretrain/Loss": 2.0261118412017822, "Pretrain/Loss (Raw)": 1.8152161836624146, "Pretrain/Step": 6609, "Pretrain/Step Time": 8.784061074256897} +{"Pretrain/Learning Rate": 1.1366347121877955e-05, "Pretrain/Loss": 2.0252890586853027, "Pretrain/Loss (Raw)": 2.0592195987701416, "Pretrain/Step": 6610, "Pretrain/Step Time": 8.787262240424752} +{"Pretrain/Learning Rate": 1.1359231603449078e-05, "Pretrain/Loss": 2.0238795280456543, "Pretrain/Loss (Raw)": 1.9865989685058594, "Pretrain/Step": 6611, "Pretrain/Step Time": 8.788753198459744} +{"Pretrain/Learning Rate": 1.1352117658137884e-05, "Pretrain/Loss": 2.021850109100342, "Pretrain/Loss (Raw)": 1.9406907558441162, "Pretrain/Step": 6612, "Pretrain/Step Time": 8.773897368460894} +{"Pretrain/Learning Rate": 1.1345005286764798e-05, "Pretrain/Loss": 2.0226569175720215, "Pretrain/Loss (Raw)": 2.174940824508667, "Pretrain/Step": 6613, "Pretrain/Step Time": 8.775747068226337} +{"Pretrain/Learning Rate": 1.133789449015005e-05, "Pretrain/Loss": 2.0252718925476074, "Pretrain/Loss (Raw)": 2.378537178039551, "Pretrain/Step": 6614, "Pretrain/Step Time": 8.77516856789589} +{"Pretrain/Learning Rate": 1.1330785269113686e-05, "Pretrain/Loss": 2.027465581893921, "Pretrain/Loss (Raw)": 2.228757858276367, "Pretrain/Step": 6615, "Pretrain/Step Time": 8.776511685922742} +{"Pretrain/Learning Rate": 1.1323677624475567e-05, "Pretrain/Loss": 2.028003215789795, "Pretrain/Loss (Raw)": 2.2648825645446777, "Pretrain/Step": 6616, "Pretrain/Step Time": 8.772732133045793} +{"Pretrain/Learning Rate": 1.13165715570554e-05, "Pretrain/Loss": 2.0256314277648926, "Pretrain/Loss (Raw)": 1.675937294960022, "Pretrain/Step": 6617, "Pretrain/Step Time": 8.777240755036473} +{"Pretrain/Learning Rate": 1.1309467067672678e-05, "Pretrain/Loss": 2.0263404846191406, "Pretrain/Loss (Raw)": 2.147613048553467, "Pretrain/Step": 6618, "Pretrain/Step Time": 8.77805263735354} +{"Pretrain/Learning Rate": 1.1302364157146716e-05, "Pretrain/Loss": 2.0275073051452637, "Pretrain/Loss (Raw)": 2.0815203189849854, "Pretrain/Step": 6619, "Pretrain/Step Time": 8.775699185207486} +{"Pretrain/Learning Rate": 1.1295262826296677e-05, "Pretrain/Loss": 2.03092360496521, "Pretrain/Loss (Raw)": 2.12530517578125, "Pretrain/Step": 6620, "Pretrain/Step Time": 8.78166976571083} +{"Pretrain/Learning Rate": 1.1288163075941505e-05, "Pretrain/Loss": 2.0310373306274414, "Pretrain/Loss (Raw)": 2.0574707984924316, "Pretrain/Step": 6621, "Pretrain/Step Time": 8.780310098081827} +{"Pretrain/Learning Rate": 1.128106490689998e-05, "Pretrain/Loss": 2.03164005279541, "Pretrain/Loss (Raw)": 2.096996545791626, "Pretrain/Step": 6622, "Pretrain/Step Time": 8.779113095253706} +{"Pretrain/Learning Rate": 1.1273968319990685e-05, "Pretrain/Loss": 2.032165050506592, "Pretrain/Loss (Raw)": 2.1153626441955566, "Pretrain/Step": 6623, "Pretrain/Step Time": 8.775704625993967} +{"Pretrain/Learning Rate": 1.1266873316032053e-05, "Pretrain/Loss": 2.0306243896484375, "Pretrain/Loss (Raw)": 2.022202730178833, "Pretrain/Step": 6624, "Pretrain/Step Time": 8.776419170200825} +{"Pretrain/Learning Rate": 1.1259779895842304e-05, "Pretrain/Loss": 2.030531167984009, "Pretrain/Loss (Raw)": 2.0081162452697754, "Pretrain/Step": 6625, "Pretrain/Step Time": 8.78003496862948} +{"Pretrain/Learning Rate": 1.1252688060239481e-05, "Pretrain/Loss": 2.0298705101013184, "Pretrain/Loss (Raw)": 2.0167150497436523, "Pretrain/Step": 6626, "Pretrain/Step Time": 8.776196444407105} +{"Pretrain/Learning Rate": 1.1245597810041441e-05, "Pretrain/Loss": 2.0290603637695312, "Pretrain/Loss (Raw)": 1.999765396118164, "Pretrain/Step": 6627, "Pretrain/Step Time": 8.779827514663339} +{"Pretrain/Learning Rate": 1.1238509146065887e-05, "Pretrain/Loss": 2.0300233364105225, "Pretrain/Loss (Raw)": 2.1287245750427246, "Pretrain/Step": 6628, "Pretrain/Step Time": 8.782493822276592} +{"Pretrain/Learning Rate": 1.1231422069130302e-05, "Pretrain/Loss": 2.029407024383545, "Pretrain/Loss (Raw)": 2.046954393386841, "Pretrain/Step": 6629, "Pretrain/Step Time": 8.78229896351695} +{"Pretrain/Learning Rate": 1.1224336580052005e-05, "Pretrain/Loss": 2.0277867317199707, "Pretrain/Loss (Raw)": 1.948429822921753, "Pretrain/Step": 6630, "Pretrain/Step Time": 8.783307395875454} +{"Pretrain/Learning Rate": 1.1217252679648116e-05, "Pretrain/Loss": 2.0283303260803223, "Pretrain/Loss (Raw)": 2.169708490371704, "Pretrain/Step": 6631, "Pretrain/Step Time": 8.78531170450151} +{"Pretrain/Learning Rate": 1.1210170368735615e-05, "Pretrain/Loss": 2.0284905433654785, "Pretrain/Loss (Raw)": 2.0625011920928955, "Pretrain/Step": 6632, "Pretrain/Step Time": 8.78498500213027} +{"Pretrain/Learning Rate": 1.1203089648131227e-05, "Pretrain/Loss": 2.0285279750823975, "Pretrain/Loss (Raw)": 2.1016645431518555, "Pretrain/Step": 6633, "Pretrain/Step Time": 8.785219660028815} +{"Pretrain/Learning Rate": 1.1196010518651562e-05, "Pretrain/Loss": 2.0282928943634033, "Pretrain/Loss (Raw)": 1.9241188764572144, "Pretrain/Step": 6634, "Pretrain/Step Time": 8.788655031472445} +{"Pretrain/Learning Rate": 1.1188932981113004e-05, "Pretrain/Loss": 2.0288944244384766, "Pretrain/Loss (Raw)": 2.0609917640686035, "Pretrain/Step": 6635, "Pretrain/Step Time": 8.788437113165855} +{"Pretrain/Learning Rate": 1.1181857036331792e-05, "Pretrain/Loss": 2.0301175117492676, "Pretrain/Loss (Raw)": 2.258150100708008, "Pretrain/Step": 6636, "Pretrain/Step Time": 8.790847731754184} +{"Pretrain/Learning Rate": 1.1174782685123918e-05, "Pretrain/Loss": 2.029989242553711, "Pretrain/Loss (Raw)": 1.8832364082336426, "Pretrain/Step": 6637, "Pretrain/Step Time": 8.791347671300173} +{"Pretrain/Learning Rate": 1.1167709928305265e-05, "Pretrain/Loss": 2.0304250717163086, "Pretrain/Loss (Raw)": 2.0671560764312744, "Pretrain/Step": 6638, "Pretrain/Step Time": 8.789281791076064} +{"Pretrain/Learning Rate": 1.1160638766691473e-05, "Pretrain/Loss": 2.03035306930542, "Pretrain/Loss (Raw)": 2.142099618911743, "Pretrain/Step": 6639, "Pretrain/Step Time": 8.78985846415162} +{"Pretrain/Learning Rate": 1.1153569201098046e-05, "Pretrain/Loss": 2.0318565368652344, "Pretrain/Loss (Raw)": 2.1803548336029053, "Pretrain/Step": 6640, "Pretrain/Step Time": 8.790427697822452} +{"Pretrain/Learning Rate": 1.114650123234025e-05, "Pretrain/Loss": 2.0318281650543213, "Pretrain/Loss (Raw)": 2.011773109436035, "Pretrain/Step": 6641, "Pretrain/Step Time": 8.791188053786755} +{"Pretrain/Learning Rate": 1.1139434861233223e-05, "Pretrain/Loss": 2.0287160873413086, "Pretrain/Loss (Raw)": 1.7859606742858887, "Pretrain/Step": 6642, "Pretrain/Step Time": 8.791617812588811} +{"Pretrain/Learning Rate": 1.1132370088591879e-05, "Pretrain/Loss": 2.028573989868164, "Pretrain/Loss (Raw)": 2.133986473083496, "Pretrain/Step": 6643, "Pretrain/Step Time": 8.795546470209956} +{"Pretrain/Learning Rate": 1.1125306915230963e-05, "Pretrain/Loss": 2.029569387435913, "Pretrain/Loss (Raw)": 2.16422438621521, "Pretrain/Step": 6644, "Pretrain/Step Time": 8.79605945199728} +{"Pretrain/Learning Rate": 1.1118245341965022e-05, "Pretrain/Loss": 2.0298306941986084, "Pretrain/Loss (Raw)": 1.9998619556427002, "Pretrain/Step": 6645, "Pretrain/Step Time": 8.793703822419047} +{"Pretrain/Learning Rate": 1.1111185369608454e-05, "Pretrain/Loss": 2.0310401916503906, "Pretrain/Loss (Raw)": 2.0510661602020264, "Pretrain/Step": 6646, "Pretrain/Step Time": 8.794643959030509} +{"Pretrain/Learning Rate": 1.110412699897543e-05, "Pretrain/Loss": 2.0276646614074707, "Pretrain/Loss (Raw)": 1.6334072351455688, "Pretrain/Step": 6647, "Pretrain/Step Time": 8.797974918037653} +{"Pretrain/Learning Rate": 1.1097070230879965e-05, "Pretrain/Loss": 2.0276565551757812, "Pretrain/Loss (Raw)": 2.057410717010498, "Pretrain/Step": 6648, "Pretrain/Step Time": 8.799143135547638} +{"Pretrain/Learning Rate": 1.1090015066135865e-05, "Pretrain/Loss": 2.0281946659088135, "Pretrain/Loss (Raw)": 2.0521037578582764, "Pretrain/Step": 6649, "Pretrain/Step Time": 8.799984835088253} +{"Pretrain/Learning Rate": 1.108296150555678e-05, "Pretrain/Loss": 2.0276918411254883, "Pretrain/Loss (Raw)": 2.1205809116363525, "Pretrain/Step": 6650, "Pretrain/Step Time": 8.797358011826873} +{"Pretrain/Learning Rate": 1.1075909549956154e-05, "Pretrain/Loss": 2.030031204223633, "Pretrain/Loss (Raw)": 2.2986953258514404, "Pretrain/Step": 6651, "Pretrain/Step Time": 8.798723397776484} +{"Pretrain/Learning Rate": 1.106885920014725e-05, "Pretrain/Loss": 2.029076099395752, "Pretrain/Loss (Raw)": 1.8706976175308228, "Pretrain/Step": 6652, "Pretrain/Step Time": 8.798436239361763} +{"Pretrain/Learning Rate": 1.1061810456943142e-05, "Pretrain/Loss": 2.027941942214966, "Pretrain/Loss (Raw)": 1.856397032737732, "Pretrain/Step": 6653, "Pretrain/Step Time": 8.79541128873825} +{"Pretrain/Learning Rate": 1.1054763321156738e-05, "Pretrain/Loss": 2.0291543006896973, "Pretrain/Loss (Raw)": 1.9806194305419922, "Pretrain/Step": 6654, "Pretrain/Step Time": 8.795239076018333} +{"Pretrain/Learning Rate": 1.1047717793600743e-05, "Pretrain/Loss": 2.0292792320251465, "Pretrain/Loss (Raw)": 2.2042860984802246, "Pretrain/Step": 6655, "Pretrain/Step Time": 8.796128114685416} +{"Pretrain/Learning Rate": 1.1040673875087673e-05, "Pretrain/Loss": 2.029569625854492, "Pretrain/Loss (Raw)": 2.0017402172088623, "Pretrain/Step": 6656, "Pretrain/Step Time": 8.789698285982013} +{"Pretrain/Learning Rate": 1.1033631566429863e-05, "Pretrain/Loss": 2.0294880867004395, "Pretrain/Loss (Raw)": 2.1032521724700928, "Pretrain/Step": 6657, "Pretrain/Step Time": 8.799053519964218} +{"Pretrain/Learning Rate": 1.1026590868439482e-05, "Pretrain/Loss": 2.030020236968994, "Pretrain/Loss (Raw)": 2.0818257331848145, "Pretrain/Step": 6658, "Pretrain/Step Time": 8.797575730830431} +{"Pretrain/Learning Rate": 1.1019551781928489e-05, "Pretrain/Loss": 2.0281753540039062, "Pretrain/Loss (Raw)": 2.0108585357666016, "Pretrain/Step": 6659, "Pretrain/Step Time": 8.799612930044532} +{"Pretrain/Learning Rate": 1.1012514307708648e-05, "Pretrain/Loss": 2.0265004634857178, "Pretrain/Loss (Raw)": 1.8945144414901733, "Pretrain/Step": 6660, "Pretrain/Step Time": 8.798182720318437} +{"Pretrain/Learning Rate": 1.1005478446591582e-05, "Pretrain/Loss": 2.0266315937042236, "Pretrain/Loss (Raw)": 1.8749520778656006, "Pretrain/Step": 6661, "Pretrain/Step Time": 8.805196292698383} +{"Pretrain/Learning Rate": 1.0998444199388686e-05, "Pretrain/Loss": 2.0286929607391357, "Pretrain/Loss (Raw)": 2.0150671005249023, "Pretrain/Step": 6662, "Pretrain/Step Time": 8.79872021637857} +{"Pretrain/Learning Rate": 1.099141156691118e-05, "Pretrain/Loss": 2.028696060180664, "Pretrain/Loss (Raw)": 2.060190439224243, "Pretrain/Step": 6663, "Pretrain/Step Time": 8.802839655429125} +{"Pretrain/Learning Rate": 1.0984380549970095e-05, "Pretrain/Loss": 2.0288443565368652, "Pretrain/Loss (Raw)": 1.9789459705352783, "Pretrain/Step": 6664, "Pretrain/Step Time": 8.811986580491066} +{"Pretrain/Learning Rate": 1.0977351149376297e-05, "Pretrain/Loss": 2.0279719829559326, "Pretrain/Loss (Raw)": 2.0771920680999756, "Pretrain/Step": 6665, "Pretrain/Step Time": 8.808534149080515} +{"Pretrain/Learning Rate": 1.0970323365940444e-05, "Pretrain/Loss": 2.0269737243652344, "Pretrain/Loss (Raw)": 2.046922445297241, "Pretrain/Step": 6666, "Pretrain/Step Time": 8.810128502547741} +{"Pretrain/Learning Rate": 1.0963297200473007e-05, "Pretrain/Loss": 2.0273051261901855, "Pretrain/Loss (Raw)": 2.0456793308258057, "Pretrain/Step": 6667, "Pretrain/Step Time": 8.807098207995296} +{"Pretrain/Learning Rate": 1.0956272653784271e-05, "Pretrain/Loss": 2.027366876602173, "Pretrain/Loss (Raw)": 1.9513845443725586, "Pretrain/Step": 6668, "Pretrain/Step Time": 8.817435182631016} +{"Pretrain/Learning Rate": 1.094924972668436e-05, "Pretrain/Loss": 2.0272276401519775, "Pretrain/Loss (Raw)": 2.035273790359497, "Pretrain/Step": 6669, "Pretrain/Step Time": 8.81047048047185} +{"Pretrain/Learning Rate": 1.0942228419983177e-05, "Pretrain/Loss": 2.025643825531006, "Pretrain/Loss (Raw)": 1.9301429986953735, "Pretrain/Step": 6670, "Pretrain/Step Time": 8.80998370796442} +{"Pretrain/Learning Rate": 1.093520873449046e-05, "Pretrain/Loss": 2.0253958702087402, "Pretrain/Loss (Raw)": 1.964338779449463, "Pretrain/Step": 6671, "Pretrain/Step Time": 8.806903121992946} +{"Pretrain/Learning Rate": 1.0928190671015734e-05, "Pretrain/Loss": 2.03021502494812, "Pretrain/Loss (Raw)": 2.1270158290863037, "Pretrain/Step": 6672, "Pretrain/Step Time": 8.803404921665788} +{"Pretrain/Learning Rate": 1.0921174230368378e-05, "Pretrain/Loss": 2.031923770904541, "Pretrain/Loss (Raw)": 2.154266834259033, "Pretrain/Step": 6673, "Pretrain/Step Time": 8.806004228070378} +{"Pretrain/Learning Rate": 1.0914159413357553e-05, "Pretrain/Loss": 2.031137704849243, "Pretrain/Loss (Raw)": 2.038313150405884, "Pretrain/Step": 6674, "Pretrain/Step Time": 8.80650519579649} +{"Pretrain/Learning Rate": 1.0907146220792236e-05, "Pretrain/Loss": 2.029116630554199, "Pretrain/Loss (Raw)": 1.987492561340332, "Pretrain/Step": 6675, "Pretrain/Step Time": 8.80739581771195} +{"Pretrain/Learning Rate": 1.0900134653481217e-05, "Pretrain/Loss": 2.0282459259033203, "Pretrain/Loss (Raw)": 1.8966376781463623, "Pretrain/Step": 6676, "Pretrain/Step Time": 8.817949544638395} +{"Pretrain/Learning Rate": 1.089312471223313e-05, "Pretrain/Loss": 2.0266544818878174, "Pretrain/Loss (Raw)": 1.8885005712509155, "Pretrain/Step": 6677, "Pretrain/Step Time": 8.816063461825252} +{"Pretrain/Learning Rate": 1.0886116397856355e-05, "Pretrain/Loss": 2.026729106903076, "Pretrain/Loss (Raw)": 2.0319466590881348, "Pretrain/Step": 6678, "Pretrain/Step Time": 8.809503495693207} +{"Pretrain/Learning Rate": 1.0879109711159156e-05, "Pretrain/Loss": 2.028099775314331, "Pretrain/Loss (Raw)": 2.1792917251586914, "Pretrain/Step": 6679, "Pretrain/Step Time": 8.81377342902124} +{"Pretrain/Learning Rate": 1.0872104652949552e-05, "Pretrain/Loss": 2.0287022590637207, "Pretrain/Loss (Raw)": 2.099008083343506, "Pretrain/Step": 6680, "Pretrain/Step Time": 8.810789229348302} +{"Pretrain/Learning Rate": 1.0865101224035432e-05, "Pretrain/Loss": 2.0327258110046387, "Pretrain/Loss (Raw)": 2.1960043907165527, "Pretrain/Step": 6681, "Pretrain/Step Time": 8.810861397534609} +{"Pretrain/Learning Rate": 1.0858099425224427e-05, "Pretrain/Loss": 2.030665636062622, "Pretrain/Loss (Raw)": 1.912898302078247, "Pretrain/Step": 6682, "Pretrain/Step Time": 8.818108577281237} +{"Pretrain/Learning Rate": 1.0851099257324043e-05, "Pretrain/Loss": 2.0327272415161133, "Pretrain/Loss (Raw)": 2.1782329082489014, "Pretrain/Step": 6683, "Pretrain/Step Time": 8.814131094142795} +{"Pretrain/Learning Rate": 1.0844100721141564e-05, "Pretrain/Loss": 2.032412052154541, "Pretrain/Loss (Raw)": 1.9740982055664062, "Pretrain/Step": 6684, "Pretrain/Step Time": 8.810736751183867} +{"Pretrain/Learning Rate": 1.0837103817484096e-05, "Pretrain/Loss": 2.0322558879852295, "Pretrain/Loss (Raw)": 1.9921306371688843, "Pretrain/Step": 6685, "Pretrain/Step Time": 8.809865625575185} +{"Pretrain/Learning Rate": 1.0830108547158544e-05, "Pretrain/Loss": 2.0336203575134277, "Pretrain/Loss (Raw)": 2.1610701084136963, "Pretrain/Step": 6686, "Pretrain/Step Time": 8.811856204643846} +{"Pretrain/Learning Rate": 1.0823114910971654e-05, "Pretrain/Loss": 2.034181594848633, "Pretrain/Loss (Raw)": 1.9570642709732056, "Pretrain/Step": 6687, "Pretrain/Step Time": 8.805072033777833} +{"Pretrain/Learning Rate": 1.0816122909729957e-05, "Pretrain/Loss": 2.0335071086883545, "Pretrain/Loss (Raw)": 2.006890296936035, "Pretrain/Step": 6688, "Pretrain/Step Time": 8.809479651972651} +{"Pretrain/Learning Rate": 1.0809132544239803e-05, "Pretrain/Loss": 2.033097505569458, "Pretrain/Loss (Raw)": 2.0652074813842773, "Pretrain/Step": 6689, "Pretrain/Step Time": 8.808362336829305} +{"Pretrain/Learning Rate": 1.0802143815307342e-05, "Pretrain/Loss": 2.033132791519165, "Pretrain/Loss (Raw)": 2.1600539684295654, "Pretrain/Step": 6690, "Pretrain/Step Time": 8.799393506720662} +{"Pretrain/Learning Rate": 1.079515672373857e-05, "Pretrain/Loss": 2.033078670501709, "Pretrain/Loss (Raw)": 2.0693347454071045, "Pretrain/Step": 6691, "Pretrain/Step Time": 8.799559785053134} +{"Pretrain/Learning Rate": 1.078817127033926e-05, "Pretrain/Loss": 2.03079891204834, "Pretrain/Loss (Raw)": 1.8155250549316406, "Pretrain/Step": 6692, "Pretrain/Step Time": 8.8017443921417} +{"Pretrain/Learning Rate": 1.0781187455915007e-05, "Pretrain/Loss": 2.0312535762786865, "Pretrain/Loss (Raw)": 2.1759328842163086, "Pretrain/Step": 6693, "Pretrain/Step Time": 8.798959128558636} +{"Pretrain/Learning Rate": 1.0774205281271208e-05, "Pretrain/Loss": 2.033255100250244, "Pretrain/Loss (Raw)": 2.20051646232605, "Pretrain/Step": 6694, "Pretrain/Step Time": 8.800357706844807} +{"Pretrain/Learning Rate": 1.0767224747213101e-05, "Pretrain/Loss": 2.0311477184295654, "Pretrain/Loss (Raw)": 1.8660163879394531, "Pretrain/Step": 6695, "Pretrain/Step Time": 8.803987886756659} +{"Pretrain/Learning Rate": 1.07602458545457e-05, "Pretrain/Loss": 2.0328145027160645, "Pretrain/Loss (Raw)": 2.2282958030700684, "Pretrain/Step": 6696, "Pretrain/Step Time": 8.806962858885527} +{"Pretrain/Learning Rate": 1.0753268604073849e-05, "Pretrain/Loss": 2.03134822845459, "Pretrain/Loss (Raw)": 2.0672802925109863, "Pretrain/Step": 6697, "Pretrain/Step Time": 8.804503256455064} +{"Pretrain/Learning Rate": 1.0746292996602187e-05, "Pretrain/Loss": 2.031351089477539, "Pretrain/Loss (Raw)": 2.1462059020996094, "Pretrain/Step": 6698, "Pretrain/Step Time": 8.803947949782014} +{"Pretrain/Learning Rate": 1.0739319032935192e-05, "Pretrain/Loss": 2.0360169410705566, "Pretrain/Loss (Raw)": 2.5162529945373535, "Pretrain/Step": 6699, "Pretrain/Step Time": 8.796374959871173} +{"Pretrain/Learning Rate": 1.0732346713877123e-05, "Pretrain/Loss": 2.0359153747558594, "Pretrain/Loss (Raw)": 1.9836723804473877, "Pretrain/Step": 6700, "Pretrain/Step Time": 8.79576113447547} +{"Pretrain/Learning Rate": 1.0725376040232052e-05, "Pretrain/Loss": 2.0372607707977295, "Pretrain/Loss (Raw)": 1.9874221086502075, "Pretrain/Step": 6701, "Pretrain/Step Time": 8.793739968910813} +{"Pretrain/Learning Rate": 1.071840701280389e-05, "Pretrain/Loss": 2.034156322479248, "Pretrain/Loss (Raw)": 1.772428035736084, "Pretrain/Step": 6702, "Pretrain/Step Time": 8.791748102754354} +{"Pretrain/Learning Rate": 1.071143963239633e-05, "Pretrain/Loss": 2.0327024459838867, "Pretrain/Loss (Raw)": 1.874393343925476, "Pretrain/Step": 6703, "Pretrain/Step Time": 8.806655909866095} +{"Pretrain/Learning Rate": 1.0704473899812881e-05, "Pretrain/Loss": 2.0337390899658203, "Pretrain/Loss (Raw)": 2.118472099304199, "Pretrain/Step": 6704, "Pretrain/Step Time": 8.79474320821464} +{"Pretrain/Learning Rate": 1.0697509815856858e-05, "Pretrain/Loss": 2.0352072715759277, "Pretrain/Loss (Raw)": 2.327096700668335, "Pretrain/Step": 6705, "Pretrain/Step Time": 8.796332526952028} +{"Pretrain/Learning Rate": 1.0690547381331403e-05, "Pretrain/Loss": 2.036393165588379, "Pretrain/Loss (Raw)": 2.129713535308838, "Pretrain/Step": 6706, "Pretrain/Step Time": 8.792174885049462} +{"Pretrain/Learning Rate": 1.0683586597039456e-05, "Pretrain/Loss": 2.0368776321411133, "Pretrain/Loss (Raw)": 2.2255139350891113, "Pretrain/Step": 6707, "Pretrain/Step Time": 8.797375109046698} +{"Pretrain/Learning Rate": 1.0676627463783762e-05, "Pretrain/Loss": 2.03678560256958, "Pretrain/Loss (Raw)": 2.1640751361846924, "Pretrain/Step": 6708, "Pretrain/Step Time": 8.798192014917731} +{"Pretrain/Learning Rate": 1.0669669982366873e-05, "Pretrain/Loss": 2.0376524925231934, "Pretrain/Loss (Raw)": 2.042313575744629, "Pretrain/Step": 6709, "Pretrain/Step Time": 8.799439579248428} +{"Pretrain/Learning Rate": 1.0662714153591177e-05, "Pretrain/Loss": 2.036980628967285, "Pretrain/Loss (Raw)": 1.9770251512527466, "Pretrain/Step": 6710, "Pretrain/Step Time": 8.800167117267847} +{"Pretrain/Learning Rate": 1.0655759978258847e-05, "Pretrain/Loss": 2.0405068397521973, "Pretrain/Loss (Raw)": 2.0720114707946777, "Pretrain/Step": 6711, "Pretrain/Step Time": 8.7968611381948} +{"Pretrain/Learning Rate": 1.0648807457171867e-05, "Pretrain/Loss": 2.0393314361572266, "Pretrain/Loss (Raw)": 2.0512046813964844, "Pretrain/Step": 6712, "Pretrain/Step Time": 8.797161307185888} +{"Pretrain/Learning Rate": 1.0641856591132027e-05, "Pretrain/Loss": 2.0412187576293945, "Pretrain/Loss (Raw)": 2.1217360496520996, "Pretrain/Step": 6713, "Pretrain/Step Time": 8.795988347381353} +{"Pretrain/Learning Rate": 1.063490738094095e-05, "Pretrain/Loss": 2.0420703887939453, "Pretrain/Loss (Raw)": 2.0396828651428223, "Pretrain/Step": 6714, "Pretrain/Step Time": 8.7970454338938} +{"Pretrain/Learning Rate": 1.0627959827400047e-05, "Pretrain/Loss": 2.042759418487549, "Pretrain/Loss (Raw)": 2.1081833839416504, "Pretrain/Step": 6715, "Pretrain/Step Time": 8.795741189271212} +{"Pretrain/Learning Rate": 1.0621013931310541e-05, "Pretrain/Loss": 2.0438005924224854, "Pretrain/Loss (Raw)": 2.042484998703003, "Pretrain/Step": 6716, "Pretrain/Step Time": 8.791825598105788} +{"Pretrain/Learning Rate": 1.0614069693473452e-05, "Pretrain/Loss": 2.043712854385376, "Pretrain/Loss (Raw)": 2.048773765563965, "Pretrain/Step": 6717, "Pretrain/Step Time": 8.802070273086429} +{"Pretrain/Learning Rate": 1.0607127114689655e-05, "Pretrain/Loss": 2.043699264526367, "Pretrain/Loss (Raw)": 2.0691897869110107, "Pretrain/Step": 6718, "Pretrain/Step Time": 8.79783601872623} +{"Pretrain/Learning Rate": 1.0600186195759762e-05, "Pretrain/Loss": 2.0435633659362793, "Pretrain/Loss (Raw)": 1.9937636852264404, "Pretrain/Step": 6719, "Pretrain/Step Time": 8.796859428286552} +{"Pretrain/Learning Rate": 1.0593246937484261e-05, "Pretrain/Loss": 2.0434622764587402, "Pretrain/Loss (Raw)": 1.8951503038406372, "Pretrain/Step": 6720, "Pretrain/Step Time": 8.799970611929893} +{"Pretrain/Learning Rate": 1.05863093406634e-05, "Pretrain/Loss": 2.0456385612487793, "Pretrain/Loss (Raw)": 2.1356406211853027, "Pretrain/Step": 6721, "Pretrain/Step Time": 8.796399319544435} +{"Pretrain/Learning Rate": 1.0579373406097284e-05, "Pretrain/Loss": 2.0457468032836914, "Pretrain/Loss (Raw)": 1.9415841102600098, "Pretrain/Step": 6722, "Pretrain/Step Time": 8.798336416482925} +{"Pretrain/Learning Rate": 1.057243913458576e-05, "Pretrain/Loss": 2.0467782020568848, "Pretrain/Loss (Raw)": 2.072948455810547, "Pretrain/Step": 6723, "Pretrain/Step Time": 8.80059801414609} +{"Pretrain/Learning Rate": 1.0565506526928548e-05, "Pretrain/Loss": 2.048693895339966, "Pretrain/Loss (Raw)": 2.1876187324523926, "Pretrain/Step": 6724, "Pretrain/Step Time": 8.797597721219063} +{"Pretrain/Learning Rate": 1.0558575583925143e-05, "Pretrain/Loss": 2.049833297729492, "Pretrain/Loss (Raw)": 2.2431461811065674, "Pretrain/Step": 6725, "Pretrain/Step Time": 8.797665800899267} +{"Pretrain/Learning Rate": 1.0551646306374851e-05, "Pretrain/Loss": 2.049330711364746, "Pretrain/Loss (Raw)": 2.0137743949890137, "Pretrain/Step": 6726, "Pretrain/Step Time": 8.798666151240468} +{"Pretrain/Learning Rate": 1.0544718695076783e-05, "Pretrain/Loss": 2.0524473190307617, "Pretrain/Loss (Raw)": 2.2450613975524902, "Pretrain/Step": 6727, "Pretrain/Step Time": 8.79891737923026} +{"Pretrain/Learning Rate": 1.0537792750829875e-05, "Pretrain/Loss": 2.051778793334961, "Pretrain/Loss (Raw)": 1.9587751626968384, "Pretrain/Step": 6728, "Pretrain/Step Time": 8.795455863699317} +{"Pretrain/Learning Rate": 1.053086847443286e-05, "Pretrain/Loss": 2.0515313148498535, "Pretrain/Loss (Raw)": 2.15846586227417, "Pretrain/Step": 6729, "Pretrain/Step Time": 8.79995890893042} +{"Pretrain/Learning Rate": 1.052394586668427e-05, "Pretrain/Loss": 2.0511059761047363, "Pretrain/Loss (Raw)": 2.016605854034424, "Pretrain/Step": 6730, "Pretrain/Step Time": 8.795903412625194} +{"Pretrain/Learning Rate": 1.0517024928382449e-05, "Pretrain/Loss": 2.050968647003174, "Pretrain/Loss (Raw)": 1.9095767736434937, "Pretrain/Step": 6731, "Pretrain/Step Time": 8.791228961199522} +{"Pretrain/Learning Rate": 1.0510105660325567e-05, "Pretrain/Loss": 2.050755500793457, "Pretrain/Loss (Raw)": 1.9401772022247314, "Pretrain/Step": 6732, "Pretrain/Step Time": 8.797978324815631} +{"Pretrain/Learning Rate": 1.0503188063311578e-05, "Pretrain/Loss": 2.049590587615967, "Pretrain/Loss (Raw)": 1.9261289834976196, "Pretrain/Step": 6733, "Pretrain/Step Time": 8.799097310751677} +{"Pretrain/Learning Rate": 1.0496272138138255e-05, "Pretrain/Loss": 2.05019474029541, "Pretrain/Loss (Raw)": 2.1100776195526123, "Pretrain/Step": 6734, "Pretrain/Step Time": 8.79843189008534} +{"Pretrain/Learning Rate": 1.0489357885603162e-05, "Pretrain/Loss": 2.05134916305542, "Pretrain/Loss (Raw)": 2.065859317779541, "Pretrain/Step": 6735, "Pretrain/Step Time": 8.795976294204593} +{"Pretrain/Learning Rate": 1.0482445306503705e-05, "Pretrain/Loss": 2.0507571697235107, "Pretrain/Loss (Raw)": 1.9723891019821167, "Pretrain/Step": 6736, "Pretrain/Step Time": 8.798918990418315} +{"Pretrain/Learning Rate": 1.0475534401637063e-05, "Pretrain/Loss": 2.053159475326538, "Pretrain/Loss (Raw)": 2.1227312088012695, "Pretrain/Step": 6737, "Pretrain/Step Time": 8.798640288412571} +{"Pretrain/Learning Rate": 1.0468625171800233e-05, "Pretrain/Loss": 2.0534281730651855, "Pretrain/Loss (Raw)": 2.0936038494110107, "Pretrain/Step": 6738, "Pretrain/Step Time": 8.79612098634243} +{"Pretrain/Learning Rate": 1.0461717617790017e-05, "Pretrain/Loss": 2.053382158279419, "Pretrain/Loss (Raw)": 1.980698585510254, "Pretrain/Step": 6739, "Pretrain/Step Time": 8.798751248046756} +{"Pretrain/Learning Rate": 1.045481174040304e-05, "Pretrain/Loss": 2.0536298751831055, "Pretrain/Loss (Raw)": 1.9723820686340332, "Pretrain/Step": 6740, "Pretrain/Step Time": 8.803742108866572} +{"Pretrain/Learning Rate": 1.044790754043571e-05, "Pretrain/Loss": 2.0493786334991455, "Pretrain/Loss (Raw)": 1.6308183670043945, "Pretrain/Step": 6741, "Pretrain/Step Time": 8.808242315426469} +{"Pretrain/Learning Rate": 1.044100501868425e-05, "Pretrain/Loss": 2.0460197925567627, "Pretrain/Loss (Raw)": 1.948585033416748, "Pretrain/Step": 6742, "Pretrain/Step Time": 8.80872362665832} +{"Pretrain/Learning Rate": 1.0434104175944701e-05, "Pretrain/Loss": 2.043945550918579, "Pretrain/Loss (Raw)": 1.9632574319839478, "Pretrain/Step": 6743, "Pretrain/Step Time": 8.810513854026794} +{"Pretrain/Learning Rate": 1.0427205013012894e-05, "Pretrain/Loss": 2.0428714752197266, "Pretrain/Loss (Raw)": 2.1274001598358154, "Pretrain/Step": 6744, "Pretrain/Step Time": 8.81651183962822} +{"Pretrain/Learning Rate": 1.0420307530684478e-05, "Pretrain/Loss": 2.0454301834106445, "Pretrain/Loss (Raw)": 2.0034801959991455, "Pretrain/Step": 6745, "Pretrain/Step Time": 8.812164921313524} +{"Pretrain/Learning Rate": 1.0413411729754887e-05, "Pretrain/Loss": 2.044656276702881, "Pretrain/Loss (Raw)": 2.048518419265747, "Pretrain/Step": 6746, "Pretrain/Step Time": 8.810806905850768} +{"Pretrain/Learning Rate": 1.0406517611019401e-05, "Pretrain/Loss": 2.0428645610809326, "Pretrain/Loss (Raw)": 1.852186918258667, "Pretrain/Step": 6747, "Pretrain/Step Time": 8.81323996372521} +{"Pretrain/Learning Rate": 1.039962517527307e-05, "Pretrain/Loss": 2.0414505004882812, "Pretrain/Loss (Raw)": 1.9443063735961914, "Pretrain/Step": 6748, "Pretrain/Step Time": 8.809055965393782} +{"Pretrain/Learning Rate": 1.0392734423310762e-05, "Pretrain/Loss": 2.0408029556274414, "Pretrain/Loss (Raw)": 1.9746073484420776, "Pretrain/Step": 6749, "Pretrain/Step Time": 8.809904530644417} +{"Pretrain/Learning Rate": 1.0385845355927144e-05, "Pretrain/Loss": 2.0402708053588867, "Pretrain/Loss (Raw)": 2.0288708209991455, "Pretrain/Step": 6750, "Pretrain/Step Time": 8.811289750039577} +{"Pretrain/Learning Rate": 1.0378957973916712e-05, "Pretrain/Loss": 2.040408134460449, "Pretrain/Loss (Raw)": 2.1329245567321777, "Pretrain/Step": 6751, "Pretrain/Step Time": 8.812201803550124} +{"Pretrain/Learning Rate": 1.0372072278073744e-05, "Pretrain/Loss": 2.0407025814056396, "Pretrain/Loss (Raw)": 2.059907913208008, "Pretrain/Step": 6752, "Pretrain/Step Time": 8.809003215283155} +{"Pretrain/Learning Rate": 1.036518826919233e-05, "Pretrain/Loss": 2.041469097137451, "Pretrain/Loss (Raw)": 2.106243371963501, "Pretrain/Step": 6753, "Pretrain/Step Time": 8.800258731469512} +{"Pretrain/Learning Rate": 1.0358305948066355e-05, "Pretrain/Loss": 2.042682647705078, "Pretrain/Loss (Raw)": 2.1720101833343506, "Pretrain/Step": 6754, "Pretrain/Step Time": 8.812909122556448} +{"Pretrain/Learning Rate": 1.0351425315489543e-05, "Pretrain/Loss": 2.0433578491210938, "Pretrain/Loss (Raw)": 2.086207628250122, "Pretrain/Step": 6755, "Pretrain/Step Time": 8.807986246421933} +{"Pretrain/Learning Rate": 1.034454637225539e-05, "Pretrain/Loss": 2.0429840087890625, "Pretrain/Loss (Raw)": 2.0808465480804443, "Pretrain/Step": 6756, "Pretrain/Step Time": 8.805496541783214} +{"Pretrain/Learning Rate": 1.0337669119157208e-05, "Pretrain/Loss": 2.0440452098846436, "Pretrain/Loss (Raw)": 2.182825803756714, "Pretrain/Step": 6757, "Pretrain/Step Time": 8.80443238466978} +{"Pretrain/Learning Rate": 1.0330793556988106e-05, "Pretrain/Loss": 2.044463634490967, "Pretrain/Loss (Raw)": 2.0019567012786865, "Pretrain/Step": 6758, "Pretrain/Step Time": 8.80395700968802} +{"Pretrain/Learning Rate": 1.032391968654103e-05, "Pretrain/Loss": 2.044135093688965, "Pretrain/Loss (Raw)": 2.1276628971099854, "Pretrain/Step": 6759, "Pretrain/Step Time": 8.801906364038587} +{"Pretrain/Learning Rate": 1.0317047508608677e-05, "Pretrain/Loss": 2.043765068054199, "Pretrain/Loss (Raw)": 2.0151567459106445, "Pretrain/Step": 6760, "Pretrain/Step Time": 8.7990379948169} +{"Pretrain/Learning Rate": 1.03101770239836e-05, "Pretrain/Loss": 2.043064832687378, "Pretrain/Loss (Raw)": 2.0120387077331543, "Pretrain/Step": 6761, "Pretrain/Step Time": 8.799366367980838} +{"Pretrain/Learning Rate": 1.0303308233458123e-05, "Pretrain/Loss": 2.0437631607055664, "Pretrain/Loss (Raw)": 2.013485908508301, "Pretrain/Step": 6762, "Pretrain/Step Time": 8.80258926562965} +{"Pretrain/Learning Rate": 1.029644113782441e-05, "Pretrain/Loss": 2.0443737506866455, "Pretrain/Loss (Raw)": 2.1391401290893555, "Pretrain/Step": 6763, "Pretrain/Step Time": 8.800753202289343} +{"Pretrain/Learning Rate": 1.0289575737874372e-05, "Pretrain/Loss": 2.042898654937744, "Pretrain/Loss (Raw)": 2.069368600845337, "Pretrain/Step": 6764, "Pretrain/Step Time": 8.798604538664222} +{"Pretrain/Learning Rate": 1.0282712034399785e-05, "Pretrain/Loss": 2.04532527923584, "Pretrain/Loss (Raw)": 2.19382643699646, "Pretrain/Step": 6765, "Pretrain/Step Time": 8.801927233114839} +{"Pretrain/Learning Rate": 1.0275850028192192e-05, "Pretrain/Loss": 2.0446672439575195, "Pretrain/Loss (Raw)": 1.9829108715057373, "Pretrain/Step": 6766, "Pretrain/Step Time": 8.801482267677784} +{"Pretrain/Learning Rate": 1.026898972004297e-05, "Pretrain/Loss": 2.042572021484375, "Pretrain/Loss (Raw)": 1.8739445209503174, "Pretrain/Step": 6767, "Pretrain/Step Time": 8.79935498163104} +{"Pretrain/Learning Rate": 1.0262131110743254e-05, "Pretrain/Loss": 2.0403614044189453, "Pretrain/Loss (Raw)": 1.8973947763442993, "Pretrain/Step": 6768, "Pretrain/Step Time": 8.799377048388124} +{"Pretrain/Learning Rate": 1.0255274201084031e-05, "Pretrain/Loss": 2.0395541191101074, "Pretrain/Loss (Raw)": 1.908427357673645, "Pretrain/Step": 6769, "Pretrain/Step Time": 8.796912277117372} +{"Pretrain/Learning Rate": 1.0248418991856068e-05, "Pretrain/Loss": 2.042625904083252, "Pretrain/Loss (Raw)": 2.179147481918335, "Pretrain/Step": 6770, "Pretrain/Step Time": 8.79820560477674} +{"Pretrain/Learning Rate": 1.0241565483849939e-05, "Pretrain/Loss": 2.041754722595215, "Pretrain/Loss (Raw)": 2.0224709510803223, "Pretrain/Step": 6771, "Pretrain/Step Time": 8.797162968665361} +{"Pretrain/Learning Rate": 1.0234713677856011e-05, "Pretrain/Loss": 2.0413365364074707, "Pretrain/Loss (Raw)": 2.1107189655303955, "Pretrain/Step": 6772, "Pretrain/Step Time": 8.797999123111367} +{"Pretrain/Learning Rate": 1.022786357466449e-05, "Pretrain/Loss": 2.043973207473755, "Pretrain/Loss (Raw)": 2.337341785430908, "Pretrain/Step": 6773, "Pretrain/Step Time": 8.799955138936639} +{"Pretrain/Learning Rate": 1.022101517506535e-05, "Pretrain/Loss": 2.0439233779907227, "Pretrain/Loss (Raw)": 2.0447022914886475, "Pretrain/Step": 6774, "Pretrain/Step Time": 8.801406534388661} +{"Pretrain/Learning Rate": 1.021416847984838e-05, "Pretrain/Loss": 2.0455408096313477, "Pretrain/Loss (Raw)": 1.8404300212860107, "Pretrain/Step": 6775, "Pretrain/Step Time": 8.792760776355863} +{"Pretrain/Learning Rate": 1.0207323489803164e-05, "Pretrain/Loss": 2.045208692550659, "Pretrain/Loss (Raw)": 2.014896869659424, "Pretrain/Step": 6776, "Pretrain/Step Time": 8.796087255701423} +{"Pretrain/Learning Rate": 1.0200480205719118e-05, "Pretrain/Loss": 2.0448508262634277, "Pretrain/Loss (Raw)": 2.006300687789917, "Pretrain/Step": 6777, "Pretrain/Step Time": 8.794253068044782} +{"Pretrain/Learning Rate": 1.0193638628385433e-05, "Pretrain/Loss": 2.044215202331543, "Pretrain/Loss (Raw)": 2.039203643798828, "Pretrain/Step": 6778, "Pretrain/Step Time": 8.795898983255029} +{"Pretrain/Learning Rate": 1.0186798758591112e-05, "Pretrain/Loss": 2.0428614616394043, "Pretrain/Loss (Raw)": 2.125432252883911, "Pretrain/Step": 6779, "Pretrain/Step Time": 8.797176346182823} +{"Pretrain/Learning Rate": 1.017996059712495e-05, "Pretrain/Loss": 2.043529987335205, "Pretrain/Loss (Raw)": 1.9562650918960571, "Pretrain/Step": 6780, "Pretrain/Step Time": 8.800347866490483} +{"Pretrain/Learning Rate": 1.0173124144775576e-05, "Pretrain/Loss": 2.044631004333496, "Pretrain/Loss (Raw)": 1.9973177909851074, "Pretrain/Step": 6781, "Pretrain/Step Time": 8.798072040081024} +{"Pretrain/Learning Rate": 1.0166289402331391e-05, "Pretrain/Loss": 2.046358585357666, "Pretrain/Loss (Raw)": 2.20175838470459, "Pretrain/Step": 6782, "Pretrain/Step Time": 8.791244937106967} +{"Pretrain/Learning Rate": 1.0159456370580604e-05, "Pretrain/Loss": 2.0446853637695312, "Pretrain/Loss (Raw)": 1.990111231803894, "Pretrain/Step": 6783, "Pretrain/Step Time": 8.797538304701447} +{"Pretrain/Learning Rate": 1.0152625050311247e-05, "Pretrain/Loss": 2.044628143310547, "Pretrain/Loss (Raw)": 1.994425892829895, "Pretrain/Step": 6784, "Pretrain/Step Time": 8.800458332523704} +{"Pretrain/Learning Rate": 1.0145795442311132e-05, "Pretrain/Loss": 2.044066905975342, "Pretrain/Loss (Raw)": 2.0314080715179443, "Pretrain/Step": 6785, "Pretrain/Step Time": 8.796835919842124} +{"Pretrain/Learning Rate": 1.0138967547367882e-05, "Pretrain/Loss": 2.044356346130371, "Pretrain/Loss (Raw)": 2.1188504695892334, "Pretrain/Step": 6786, "Pretrain/Step Time": 8.801966030150652} +{"Pretrain/Learning Rate": 1.0132141366268913e-05, "Pretrain/Loss": 2.0433292388916016, "Pretrain/Loss (Raw)": 1.8794200420379639, "Pretrain/Step": 6787, "Pretrain/Step Time": 8.798837535083294} +{"Pretrain/Learning Rate": 1.012531689980147e-05, "Pretrain/Loss": 2.043860673904419, "Pretrain/Loss (Raw)": 1.9625200033187866, "Pretrain/Step": 6788, "Pretrain/Step Time": 8.800675731152296} +{"Pretrain/Learning Rate": 1.0118494148752575e-05, "Pretrain/Loss": 2.0437850952148438, "Pretrain/Loss (Raw)": 1.8652667999267578, "Pretrain/Step": 6789, "Pretrain/Step Time": 8.797474978491664} +{"Pretrain/Learning Rate": 1.0111673113909056e-05, "Pretrain/Loss": 2.0437774658203125, "Pretrain/Loss (Raw)": 2.014113426208496, "Pretrain/Step": 6790, "Pretrain/Step Time": 8.797303758561611} +{"Pretrain/Learning Rate": 1.0104853796057546e-05, "Pretrain/Loss": 2.044332981109619, "Pretrain/Loss (Raw)": 2.1312835216522217, "Pretrain/Step": 6791, "Pretrain/Step Time": 8.79598169401288} +{"Pretrain/Learning Rate": 1.009803619598449e-05, "Pretrain/Loss": 2.044257164001465, "Pretrain/Loss (Raw)": 1.9692251682281494, "Pretrain/Step": 6792, "Pretrain/Step Time": 8.7899687923491} +{"Pretrain/Learning Rate": 1.0091220314476119e-05, "Pretrain/Loss": 2.043854236602783, "Pretrain/Loss (Raw)": 2.0256574153900146, "Pretrain/Step": 6793, "Pretrain/Step Time": 8.786590810865164} +{"Pretrain/Learning Rate": 1.0084406152318473e-05, "Pretrain/Loss": 2.0435571670532227, "Pretrain/Loss (Raw)": 2.008880853652954, "Pretrain/Step": 6794, "Pretrain/Step Time": 8.787248859182} +{"Pretrain/Learning Rate": 1.007759371029739e-05, "Pretrain/Loss": 2.043745517730713, "Pretrain/Loss (Raw)": 2.069786548614502, "Pretrain/Step": 6795, "Pretrain/Step Time": 8.78849982470274} +{"Pretrain/Learning Rate": 1.0070782989198521e-05, "Pretrain/Loss": 2.044724941253662, "Pretrain/Loss (Raw)": 2.0767602920532227, "Pretrain/Step": 6796, "Pretrain/Step Time": 8.790864316746593} +{"Pretrain/Learning Rate": 1.006397398980731e-05, "Pretrain/Loss": 2.044919967651367, "Pretrain/Loss (Raw)": 2.0602495670318604, "Pretrain/Step": 6797, "Pretrain/Step Time": 8.787530921399593} +{"Pretrain/Learning Rate": 1.0057166712908996e-05, "Pretrain/Loss": 2.0454111099243164, "Pretrain/Loss (Raw)": 1.9929783344268799, "Pretrain/Step": 6798, "Pretrain/Step Time": 8.789023507386446} +{"Pretrain/Learning Rate": 1.0050361159288625e-05, "Pretrain/Loss": 2.0457944869995117, "Pretrain/Loss (Raw)": 2.013444662094116, "Pretrain/Step": 6799, "Pretrain/Step Time": 8.790764605626464} +{"Pretrain/Learning Rate": 1.0043557329731065e-05, "Pretrain/Loss": 2.0453338623046875, "Pretrain/Loss (Raw)": 2.0680224895477295, "Pretrain/Step": 6800, "Pretrain/Step Time": 8.796702470630407} +{"Pretrain/Learning Rate": 1.0036755225020933e-05, "Pretrain/Loss": 2.0437746047973633, "Pretrain/Loss (Raw)": 1.954696536064148, "Pretrain/Step": 6801, "Pretrain/Step Time": 8.789892066270113} +{"Pretrain/Learning Rate": 1.0029954845942707e-05, "Pretrain/Loss": 2.044259786605835, "Pretrain/Loss (Raw)": 2.1003973484039307, "Pretrain/Step": 6802, "Pretrain/Step Time": 8.792980808764696} +{"Pretrain/Learning Rate": 1.0023156193280622e-05, "Pretrain/Loss": 2.0450825691223145, "Pretrain/Loss (Raw)": 2.0928468704223633, "Pretrain/Step": 6803, "Pretrain/Step Time": 8.795017572119832} +{"Pretrain/Learning Rate": 1.0016359267818754e-05, "Pretrain/Loss": 2.0469770431518555, "Pretrain/Loss (Raw)": 2.139094114303589, "Pretrain/Step": 6804, "Pretrain/Step Time": 8.786695424467325} +{"Pretrain/Learning Rate": 1.0009564070340924e-05, "Pretrain/Loss": 2.0483949184417725, "Pretrain/Loss (Raw)": 2.0699989795684814, "Pretrain/Step": 6805, "Pretrain/Step Time": 8.789326125755906} +{"Pretrain/Learning Rate": 1.0002770601630809e-05, "Pretrain/Loss": 2.048497438430786, "Pretrain/Loss (Raw)": 2.0450732707977295, "Pretrain/Step": 6806, "Pretrain/Step Time": 8.79400205053389} +{"Pretrain/Learning Rate": 9.99597886247185e-06, "Pretrain/Loss": 2.046267509460449, "Pretrain/Loss (Raw)": 1.8938531875610352, "Pretrain/Step": 6807, "Pretrain/Step Time": 8.787872314453125} +{"Pretrain/Learning Rate": 9.98918885364733e-06, "Pretrain/Loss": 2.0452990531921387, "Pretrain/Loss (Raw)": 1.9750641584396362, "Pretrain/Step": 6808, "Pretrain/Step Time": 8.783953931182623} +{"Pretrain/Learning Rate": 9.982400575940262e-06, "Pretrain/Loss": 2.043856143951416, "Pretrain/Loss (Raw)": 2.0113205909729004, "Pretrain/Step": 6809, "Pretrain/Step Time": 8.784039802849293} +{"Pretrain/Learning Rate": 9.975614030133537e-06, "Pretrain/Loss": 2.046251058578491, "Pretrain/Loss (Raw)": 2.2194066047668457, "Pretrain/Step": 6810, "Pretrain/Step Time": 8.780191119760275} +{"Pretrain/Learning Rate": 9.968829217009802e-06, "Pretrain/Loss": 2.0441689491271973, "Pretrain/Loss (Raw)": 1.9117770195007324, "Pretrain/Step": 6811, "Pretrain/Step Time": 8.784560991451144} +{"Pretrain/Learning Rate": 9.962046137351505e-06, "Pretrain/Loss": 2.0448479652404785, "Pretrain/Loss (Raw)": 2.0609641075134277, "Pretrain/Step": 6812, "Pretrain/Step Time": 8.781478889286518} +{"Pretrain/Learning Rate": 9.955264791940902e-06, "Pretrain/Loss": 2.0417890548706055, "Pretrain/Loss (Raw)": 1.600628137588501, "Pretrain/Step": 6813, "Pretrain/Step Time": 8.786421455442905} +{"Pretrain/Learning Rate": 9.948485181560066e-06, "Pretrain/Loss": 2.0414180755615234, "Pretrain/Loss (Raw)": 2.113568067550659, "Pretrain/Step": 6814, "Pretrain/Step Time": 8.788069231435657} +{"Pretrain/Learning Rate": 9.941707306990843e-06, "Pretrain/Loss": 2.0419507026672363, "Pretrain/Loss (Raw)": 2.0252270698547363, "Pretrain/Step": 6815, "Pretrain/Step Time": 8.790296584367752} +{"Pretrain/Learning Rate": 9.934931169014891e-06, "Pretrain/Loss": 2.040853500366211, "Pretrain/Loss (Raw)": 1.866423487663269, "Pretrain/Step": 6816, "Pretrain/Step Time": 8.784345397725701} +{"Pretrain/Learning Rate": 9.928156768413657e-06, "Pretrain/Loss": 2.0395312309265137, "Pretrain/Loss (Raw)": 1.8959909677505493, "Pretrain/Step": 6817, "Pretrain/Step Time": 8.793656770139933} +{"Pretrain/Learning Rate": 9.921384105968415e-06, "Pretrain/Loss": 2.0394434928894043, "Pretrain/Loss (Raw)": 2.148801326751709, "Pretrain/Step": 6818, "Pretrain/Step Time": 8.792136080563068} +{"Pretrain/Learning Rate": 9.914613182460208e-06, "Pretrain/Loss": 2.040365219116211, "Pretrain/Loss (Raw)": 2.187364101409912, "Pretrain/Step": 6819, "Pretrain/Step Time": 8.7950727250427} +{"Pretrain/Learning Rate": 9.907843998669895e-06, "Pretrain/Loss": 2.0406653881073, "Pretrain/Loss (Raw)": 1.853921890258789, "Pretrain/Step": 6820, "Pretrain/Step Time": 8.795297008007765} +{"Pretrain/Learning Rate": 9.90107655537812e-06, "Pretrain/Loss": 2.0395236015319824, "Pretrain/Loss (Raw)": 2.0298030376434326, "Pretrain/Step": 6821, "Pretrain/Step Time": 8.802620775997639} +{"Pretrain/Learning Rate": 9.894310853365354e-06, "Pretrain/Loss": 2.0377674102783203, "Pretrain/Loss (Raw)": 1.9757039546966553, "Pretrain/Step": 6822, "Pretrain/Step Time": 8.79886974580586} +{"Pretrain/Learning Rate": 9.887546893411839e-06, "Pretrain/Loss": 2.038196086883545, "Pretrain/Loss (Raw)": 1.920894742012024, "Pretrain/Step": 6823, "Pretrain/Step Time": 8.795750375837088} +{"Pretrain/Learning Rate": 9.880784676297622e-06, "Pretrain/Loss": 2.037623167037964, "Pretrain/Loss (Raw)": 2.1549575328826904, "Pretrain/Step": 6824, "Pretrain/Step Time": 8.791557487100363} +{"Pretrain/Learning Rate": 9.874024202802567e-06, "Pretrain/Loss": 2.03741455078125, "Pretrain/Loss (Raw)": 2.0405561923980713, "Pretrain/Step": 6825, "Pretrain/Step Time": 8.803305042907596} +{"Pretrain/Learning Rate": 9.867265473706319e-06, "Pretrain/Loss": 2.038270950317383, "Pretrain/Loss (Raw)": 2.2558305263519287, "Pretrain/Step": 6826, "Pretrain/Step Time": 8.80257678590715} +{"Pretrain/Learning Rate": 9.860508489788323e-06, "Pretrain/Loss": 2.0343985557556152, "Pretrain/Loss (Raw)": 2.0206050872802734, "Pretrain/Step": 6827, "Pretrain/Step Time": 8.801449056714773} +{"Pretrain/Learning Rate": 9.853753251827818e-06, "Pretrain/Loss": 2.035670757293701, "Pretrain/Loss (Raw)": 2.1465060710906982, "Pretrain/Step": 6828, "Pretrain/Step Time": 8.805953117087483} +{"Pretrain/Learning Rate": 9.84699976060387e-06, "Pretrain/Loss": 2.036255359649658, "Pretrain/Loss (Raw)": 2.0622496604919434, "Pretrain/Step": 6829, "Pretrain/Step Time": 8.805726436898112} +{"Pretrain/Learning Rate": 9.840248016895311e-06, "Pretrain/Loss": 2.0382542610168457, "Pretrain/Loss (Raw)": 2.0282864570617676, "Pretrain/Step": 6830, "Pretrain/Step Time": 8.808552214875817} +{"Pretrain/Learning Rate": 9.833498021480789e-06, "Pretrain/Loss": 2.0406651496887207, "Pretrain/Loss (Raw)": 2.182992458343506, "Pretrain/Step": 6831, "Pretrain/Step Time": 8.796908481046557} +{"Pretrain/Learning Rate": 9.82674977513873e-06, "Pretrain/Loss": 2.040447950363159, "Pretrain/Loss (Raw)": 2.0906574726104736, "Pretrain/Step": 6832, "Pretrain/Step Time": 8.797325357794762} +{"Pretrain/Learning Rate": 9.820003278647396e-06, "Pretrain/Loss": 2.0381970405578613, "Pretrain/Loss (Raw)": 2.0389902591705322, "Pretrain/Step": 6833, "Pretrain/Step Time": 8.802629586309195} +{"Pretrain/Learning Rate": 9.813258532784813e-06, "Pretrain/Loss": 2.038301944732666, "Pretrain/Loss (Raw)": 2.1431338787078857, "Pretrain/Step": 6834, "Pretrain/Step Time": 8.804903969168663} +{"Pretrain/Learning Rate": 9.80651553832882e-06, "Pretrain/Loss": 2.036907911300659, "Pretrain/Loss (Raw)": 2.0470874309539795, "Pretrain/Step": 6835, "Pretrain/Step Time": 8.800798434764147} +{"Pretrain/Learning Rate": 9.79977429605704e-06, "Pretrain/Loss": 2.037260055541992, "Pretrain/Loss (Raw)": 2.2091586589813232, "Pretrain/Step": 6836, "Pretrain/Step Time": 8.805767897516489} +{"Pretrain/Learning Rate": 9.793034806746922e-06, "Pretrain/Loss": 2.0387351512908936, "Pretrain/Loss (Raw)": 2.231130838394165, "Pretrain/Step": 6837, "Pretrain/Step Time": 8.804592408239841} +{"Pretrain/Learning Rate": 9.786297071175687e-06, "Pretrain/Loss": 2.039034605026245, "Pretrain/Loss (Raw)": 2.0153398513793945, "Pretrain/Step": 6838, "Pretrain/Step Time": 8.810945224016905} +{"Pretrain/Learning Rate": 9.779561090120366e-06, "Pretrain/Loss": 2.040081024169922, "Pretrain/Loss (Raw)": 2.2059521675109863, "Pretrain/Step": 6839, "Pretrain/Step Time": 8.803824922069907} +{"Pretrain/Learning Rate": 9.77282686435777e-06, "Pretrain/Loss": 2.040653944015503, "Pretrain/Loss (Raw)": 2.1245343685150146, "Pretrain/Step": 6840, "Pretrain/Step Time": 8.803967216983438} +{"Pretrain/Learning Rate": 9.766094394664551e-06, "Pretrain/Loss": 2.0369598865509033, "Pretrain/Loss (Raw)": 1.6489020586013794, "Pretrain/Step": 6841, "Pretrain/Step Time": 8.802976774051785} +{"Pretrain/Learning Rate": 9.759363681817093e-06, "Pretrain/Loss": 2.0360658168792725, "Pretrain/Loss (Raw)": 1.9252489805221558, "Pretrain/Step": 6842, "Pretrain/Step Time": 8.798114659264684} +{"Pretrain/Learning Rate": 9.752634726591642e-06, "Pretrain/Loss": 2.035148859024048, "Pretrain/Loss (Raw)": 1.990805983543396, "Pretrain/Step": 6843, "Pretrain/Step Time": 8.800589891150594} +{"Pretrain/Learning Rate": 9.745907529764189e-06, "Pretrain/Loss": 2.0329103469848633, "Pretrain/Loss (Raw)": 1.75594961643219, "Pretrain/Step": 6844, "Pretrain/Step Time": 8.80640677176416} +{"Pretrain/Learning Rate": 9.739182092110583e-06, "Pretrain/Loss": 2.0332226753234863, "Pretrain/Loss (Raw)": 2.0887510776519775, "Pretrain/Step": 6845, "Pretrain/Step Time": 8.802068008109927} +{"Pretrain/Learning Rate": 9.732458414406387e-06, "Pretrain/Loss": 2.03240966796875, "Pretrain/Loss (Raw)": 1.9651402235031128, "Pretrain/Step": 6846, "Pretrain/Step Time": 8.800823358818889} +{"Pretrain/Learning Rate": 9.72573649742704e-06, "Pretrain/Loss": 2.0334081649780273, "Pretrain/Loss (Raw)": 2.1215641498565674, "Pretrain/Step": 6847, "Pretrain/Step Time": 8.80296553298831} +{"Pretrain/Learning Rate": 9.719016341947726e-06, "Pretrain/Loss": 2.0340628623962402, "Pretrain/Loss (Raw)": 1.9789665937423706, "Pretrain/Step": 6848, "Pretrain/Step Time": 8.802198611199856} +{"Pretrain/Learning Rate": 9.712297948743473e-06, "Pretrain/Loss": 2.0335326194763184, "Pretrain/Loss (Raw)": 2.067734956741333, "Pretrain/Step": 6849, "Pretrain/Step Time": 8.799457497894764} +{"Pretrain/Learning Rate": 9.705581318589038e-06, "Pretrain/Loss": 2.034493923187256, "Pretrain/Loss (Raw)": 2.0646419525146484, "Pretrain/Step": 6850, "Pretrain/Step Time": 8.795685226097703} +{"Pretrain/Learning Rate": 9.698866452259048e-06, "Pretrain/Loss": 2.032413959503174, "Pretrain/Loss (Raw)": 1.8066960573196411, "Pretrain/Step": 6851, "Pretrain/Step Time": 8.796106439083815} +{"Pretrain/Learning Rate": 9.692153350527877e-06, "Pretrain/Loss": 2.0310935974121094, "Pretrain/Loss (Raw)": 2.0186164379119873, "Pretrain/Step": 6852, "Pretrain/Step Time": 8.802092438563704} +{"Pretrain/Learning Rate": 9.685442014169715e-06, "Pretrain/Loss": 2.027510166168213, "Pretrain/Loss (Raw)": 1.7844966650009155, "Pretrain/Step": 6853, "Pretrain/Step Time": 8.79571839980781} +{"Pretrain/Learning Rate": 9.678732443958535e-06, "Pretrain/Loss": 2.0271904468536377, "Pretrain/Loss (Raw)": 1.9728378057479858, "Pretrain/Step": 6854, "Pretrain/Step Time": 8.79556636698544} +{"Pretrain/Learning Rate": 9.672024640668134e-06, "Pretrain/Loss": 2.025890827178955, "Pretrain/Loss (Raw)": 2.0786967277526855, "Pretrain/Step": 6855, "Pretrain/Step Time": 8.790181210264564} +{"Pretrain/Learning Rate": 9.665318605072082e-06, "Pretrain/Loss": 2.0276994705200195, "Pretrain/Loss (Raw)": 2.1903138160705566, "Pretrain/Step": 6856, "Pretrain/Step Time": 8.796265885233879} +{"Pretrain/Learning Rate": 9.658614337943748e-06, "Pretrain/Loss": 2.025698661804199, "Pretrain/Loss (Raw)": 1.902353286743164, "Pretrain/Step": 6857, "Pretrain/Step Time": 8.794410156086087} +{"Pretrain/Learning Rate": 9.651911840056287e-06, "Pretrain/Loss": 2.0244381427764893, "Pretrain/Loss (Raw)": 1.855261206626892, "Pretrain/Step": 6858, "Pretrain/Step Time": 8.797305591404438} +{"Pretrain/Learning Rate": 9.645211112182687e-06, "Pretrain/Loss": 2.025585174560547, "Pretrain/Loss (Raw)": 2.0563788414001465, "Pretrain/Step": 6859, "Pretrain/Step Time": 8.79800783470273} +{"Pretrain/Learning Rate": 9.638512155095694e-06, "Pretrain/Loss": 2.0259225368499756, "Pretrain/Loss (Raw)": 1.9833673238754272, "Pretrain/Step": 6860, "Pretrain/Step Time": 8.791314383968711} +{"Pretrain/Learning Rate": 9.631814969567866e-06, "Pretrain/Loss": 2.0272696018218994, "Pretrain/Loss (Raw)": 2.0985584259033203, "Pretrain/Step": 6861, "Pretrain/Step Time": 8.797772975638509} +{"Pretrain/Learning Rate": 9.625119556371542e-06, "Pretrain/Loss": 2.0263917446136475, "Pretrain/Loss (Raw)": 1.9977171421051025, "Pretrain/Step": 6862, "Pretrain/Step Time": 8.800337344408035} +{"Pretrain/Learning Rate": 9.618425916278891e-06, "Pretrain/Loss": 2.0272743701934814, "Pretrain/Loss (Raw)": 2.1788313388824463, "Pretrain/Step": 6863, "Pretrain/Step Time": 8.797391012310982} +{"Pretrain/Learning Rate": 9.611734050061844e-06, "Pretrain/Loss": 2.025125026702881, "Pretrain/Loss (Raw)": 1.6972767114639282, "Pretrain/Step": 6864, "Pretrain/Step Time": 8.800280094146729} +{"Pretrain/Learning Rate": 9.605043958492127e-06, "Pretrain/Loss": 2.025820255279541, "Pretrain/Loss (Raw)": 2.2117066383361816, "Pretrain/Step": 6865, "Pretrain/Step Time": 8.801263272762299} +{"Pretrain/Learning Rate": 9.598355642341294e-06, "Pretrain/Loss": 2.0261266231536865, "Pretrain/Loss (Raw)": 2.1328072547912598, "Pretrain/Step": 6866, "Pretrain/Step Time": 8.801658034324646} +{"Pretrain/Learning Rate": 9.591669102380666e-06, "Pretrain/Loss": 2.0272514820098877, "Pretrain/Loss (Raw)": 2.1246883869171143, "Pretrain/Step": 6867, "Pretrain/Step Time": 8.811339944601059} +{"Pretrain/Learning Rate": 9.584984339381362e-06, "Pretrain/Loss": 2.0282046794891357, "Pretrain/Loss (Raw)": 2.0943946838378906, "Pretrain/Step": 6868, "Pretrain/Step Time": 8.807344026863575} +{"Pretrain/Learning Rate": 9.578301354114291e-06, "Pretrain/Loss": 2.0313076972961426, "Pretrain/Loss (Raw)": 2.028000593185425, "Pretrain/Step": 6869, "Pretrain/Step Time": 8.800151886418462} +{"Pretrain/Learning Rate": 9.571620147350188e-06, "Pretrain/Loss": 2.0325193405151367, "Pretrain/Loss (Raw)": 2.1036834716796875, "Pretrain/Step": 6870, "Pretrain/Step Time": 8.801162345334888} +{"Pretrain/Learning Rate": 9.56494071985955e-06, "Pretrain/Loss": 2.03143310546875, "Pretrain/Loss (Raw)": 1.824225664138794, "Pretrain/Step": 6871, "Pretrain/Step Time": 8.800267361104488} +{"Pretrain/Learning Rate": 9.558263072412679e-06, "Pretrain/Loss": 2.0313096046447754, "Pretrain/Loss (Raw)": 2.111563205718994, "Pretrain/Step": 6872, "Pretrain/Step Time": 8.799371710047126} +{"Pretrain/Learning Rate": 9.551587205779666e-06, "Pretrain/Loss": 2.0313620567321777, "Pretrain/Loss (Raw)": 2.010223865509033, "Pretrain/Step": 6873, "Pretrain/Step Time": 8.802606360986829} +{"Pretrain/Learning Rate": 9.544913120730423e-06, "Pretrain/Loss": 2.032510757446289, "Pretrain/Loss (Raw)": 2.1955418586730957, "Pretrain/Step": 6874, "Pretrain/Step Time": 8.811963835731149} +{"Pretrain/Learning Rate": 9.538240818034624e-06, "Pretrain/Loss": 2.0348029136657715, "Pretrain/Loss (Raw)": 2.1455817222595215, "Pretrain/Step": 6875, "Pretrain/Step Time": 8.8057732116431} +{"Pretrain/Learning Rate": 9.531570298461754e-06, "Pretrain/Loss": 2.0361104011535645, "Pretrain/Loss (Raw)": 2.1116743087768555, "Pretrain/Step": 6876, "Pretrain/Step Time": 8.803421026095748} +{"Pretrain/Learning Rate": 9.524901562781074e-06, "Pretrain/Loss": 2.0364162921905518, "Pretrain/Loss (Raw)": 2.013768196105957, "Pretrain/Step": 6877, "Pretrain/Step Time": 8.808941071853042} +{"Pretrain/Learning Rate": 9.518234611761678e-06, "Pretrain/Loss": 2.035904884338379, "Pretrain/Loss (Raw)": 1.9634063243865967, "Pretrain/Step": 6878, "Pretrain/Step Time": 8.804530231282115} +{"Pretrain/Learning Rate": 9.511569446172419e-06, "Pretrain/Loss": 2.0345818996429443, "Pretrain/Loss (Raw)": 1.9635756015777588, "Pretrain/Step": 6879, "Pretrain/Step Time": 8.80517547763884} +{"Pretrain/Learning Rate": 9.504906066781954e-06, "Pretrain/Loss": 2.0350406169891357, "Pretrain/Loss (Raw)": 2.1186137199401855, "Pretrain/Step": 6880, "Pretrain/Step Time": 8.808196583762765} +{"Pretrain/Learning Rate": 9.49824447435873e-06, "Pretrain/Loss": 2.034515857696533, "Pretrain/Loss (Raw)": 2.039078950881958, "Pretrain/Step": 6881, "Pretrain/Step Time": 8.806512668728828} +{"Pretrain/Learning Rate": 9.491584669671008e-06, "Pretrain/Loss": 2.034653425216675, "Pretrain/Loss (Raw)": 2.189612627029419, "Pretrain/Step": 6882, "Pretrain/Step Time": 8.796499690040946} +{"Pretrain/Learning Rate": 9.484926653486819e-06, "Pretrain/Loss": 2.0342376232147217, "Pretrain/Loss (Raw)": 2.0329809188842773, "Pretrain/Step": 6883, "Pretrain/Step Time": 8.797400860115886} +{"Pretrain/Learning Rate": 9.478270426574002e-06, "Pretrain/Loss": 2.0333609580993652, "Pretrain/Loss (Raw)": 1.9686644077301025, "Pretrain/Step": 6884, "Pretrain/Step Time": 8.798137992620468} +{"Pretrain/Learning Rate": 9.471615989700167e-06, "Pretrain/Loss": 2.0327281951904297, "Pretrain/Loss (Raw)": 2.1018104553222656, "Pretrain/Step": 6885, "Pretrain/Step Time": 8.796165443956852} +{"Pretrain/Learning Rate": 9.464963343632766e-06, "Pretrain/Loss": 2.0315792560577393, "Pretrain/Loss (Raw)": 1.8549026250839233, "Pretrain/Step": 6886, "Pretrain/Step Time": 8.795884983614087} +{"Pretrain/Learning Rate": 9.458312489138979e-06, "Pretrain/Loss": 2.0323681831359863, "Pretrain/Loss (Raw)": 2.228646755218506, "Pretrain/Step": 6887, "Pretrain/Step Time": 8.796364752575755} +{"Pretrain/Learning Rate": 9.451663426985838e-06, "Pretrain/Loss": 2.0305471420288086, "Pretrain/Loss (Raw)": 1.7820520401000977, "Pretrain/Step": 6888, "Pretrain/Step Time": 8.815391859039664} +{"Pretrain/Learning Rate": 9.44501615794013e-06, "Pretrain/Loss": 2.030527353286743, "Pretrain/Loss (Raw)": 2.009514570236206, "Pretrain/Step": 6889, "Pretrain/Step Time": 8.813234644010663} +{"Pretrain/Learning Rate": 9.438370682768473e-06, "Pretrain/Loss": 2.030583620071411, "Pretrain/Loss (Raw)": 2.02067494392395, "Pretrain/Step": 6890, "Pretrain/Step Time": 8.807323679327965} +{"Pretrain/Learning Rate": 9.43172700223722e-06, "Pretrain/Loss": 2.0302681922912598, "Pretrain/Loss (Raw)": 2.098745822906494, "Pretrain/Step": 6891, "Pretrain/Step Time": 8.809002794325352} +{"Pretrain/Learning Rate": 9.425085117112577e-06, "Pretrain/Loss": 2.02938175201416, "Pretrain/Loss (Raw)": 1.9559240341186523, "Pretrain/Step": 6892, "Pretrain/Step Time": 8.805776907131076} +{"Pretrain/Learning Rate": 9.41844502816051e-06, "Pretrain/Loss": 2.0283336639404297, "Pretrain/Loss (Raw)": 2.059701681137085, "Pretrain/Step": 6893, "Pretrain/Step Time": 8.804054506123066} +{"Pretrain/Learning Rate": 9.411806736146788e-06, "Pretrain/Loss": 2.0298595428466797, "Pretrain/Loss (Raw)": 2.178208112716675, "Pretrain/Step": 6894, "Pretrain/Step Time": 8.80779823474586} +{"Pretrain/Learning Rate": 9.405170241836955e-06, "Pretrain/Loss": 2.031747579574585, "Pretrain/Loss (Raw)": 2.1155893802642822, "Pretrain/Step": 6895, "Pretrain/Step Time": 8.803400829434395} +{"Pretrain/Learning Rate": 9.398535545996386e-06, "Pretrain/Loss": 2.0350422859191895, "Pretrain/Loss (Raw)": 2.3191490173339844, "Pretrain/Step": 6896, "Pretrain/Step Time": 8.80585323087871} +{"Pretrain/Learning Rate": 9.391902649390214e-06, "Pretrain/Loss": 2.0364904403686523, "Pretrain/Loss (Raw)": 2.0937838554382324, "Pretrain/Step": 6897, "Pretrain/Step Time": 8.804848374798894} +{"Pretrain/Learning Rate": 9.385271552783375e-06, "Pretrain/Loss": 2.0349860191345215, "Pretrain/Loss (Raw)": 1.9865573644638062, "Pretrain/Step": 6898, "Pretrain/Step Time": 8.805726189166307} +{"Pretrain/Learning Rate": 9.378642256940589e-06, "Pretrain/Loss": 2.034508228302002, "Pretrain/Loss (Raw)": 1.9613337516784668, "Pretrain/Step": 6899, "Pretrain/Step Time": 8.804985186085105} +{"Pretrain/Learning Rate": 9.372014762626401e-06, "Pretrain/Loss": 2.032824993133545, "Pretrain/Loss (Raw)": 1.8952786922454834, "Pretrain/Step": 6900, "Pretrain/Step Time": 8.800441451370716} +{"Pretrain/Learning Rate": 9.36538907060511e-06, "Pretrain/Loss": 2.03341007232666, "Pretrain/Loss (Raw)": 2.412203788757324, "Pretrain/Step": 6901, "Pretrain/Step Time": 8.801182949915528} +{"Pretrain/Learning Rate": 9.358765181640825e-06, "Pretrain/Loss": 2.033743381500244, "Pretrain/Loss (Raw)": 2.0873708724975586, "Pretrain/Step": 6902, "Pretrain/Step Time": 8.805507251992822} +{"Pretrain/Learning Rate": 9.352143096497435e-06, "Pretrain/Loss": 2.0339515209198, "Pretrain/Loss (Raw)": 1.8670859336853027, "Pretrain/Step": 6903, "Pretrain/Step Time": 8.806585321202874} +{"Pretrain/Learning Rate": 9.345522815938645e-06, "Pretrain/Loss": 2.035051107406616, "Pretrain/Loss (Raw)": 2.1556408405303955, "Pretrain/Step": 6904, "Pretrain/Step Time": 8.8083726298064} +{"Pretrain/Learning Rate": 9.33890434072793e-06, "Pretrain/Loss": 2.0353169441223145, "Pretrain/Loss (Raw)": 2.0403335094451904, "Pretrain/Step": 6905, "Pretrain/Step Time": 8.806909779086709} +{"Pretrain/Learning Rate": 9.332287671628556e-06, "Pretrain/Loss": 2.0353472232818604, "Pretrain/Loss (Raw)": 2.0430755615234375, "Pretrain/Step": 6906, "Pretrain/Step Time": 8.805696830153465} +{"Pretrain/Learning Rate": 9.325672809403606e-06, "Pretrain/Loss": 2.0349748134613037, "Pretrain/Loss (Raw)": 2.0777506828308105, "Pretrain/Step": 6907, "Pretrain/Step Time": 8.8055807556957} +{"Pretrain/Learning Rate": 9.319059754815926e-06, "Pretrain/Loss": 2.0351436138153076, "Pretrain/Loss (Raw)": 1.9778954982757568, "Pretrain/Step": 6908, "Pretrain/Step Time": 8.80215573683381} +{"Pretrain/Learning Rate": 9.312448508628169e-06, "Pretrain/Loss": 2.035001754760742, "Pretrain/Loss (Raw)": 1.9791206121444702, "Pretrain/Step": 6909, "Pretrain/Step Time": 8.80247888341546} +{"Pretrain/Learning Rate": 9.30583907160276e-06, "Pretrain/Loss": 2.033059597015381, "Pretrain/Loss (Raw)": 1.9531798362731934, "Pretrain/Step": 6910, "Pretrain/Step Time": 8.809577099978924} +{"Pretrain/Learning Rate": 9.299231444501953e-06, "Pretrain/Loss": 2.033637046813965, "Pretrain/Loss (Raw)": 2.0640337467193604, "Pretrain/Step": 6911, "Pretrain/Step Time": 8.804413724690676} +{"Pretrain/Learning Rate": 9.29262562808776e-06, "Pretrain/Loss": 2.034775733947754, "Pretrain/Loss (Raw)": 2.1401634216308594, "Pretrain/Step": 6912, "Pretrain/Step Time": 8.805153340101242} +{"Pretrain/Learning Rate": 9.286021623121993e-06, "Pretrain/Loss": 2.0355312824249268, "Pretrain/Loss (Raw)": 2.128129243850708, "Pretrain/Step": 6913, "Pretrain/Step Time": 8.800530679523945} +{"Pretrain/Learning Rate": 9.279419430366255e-06, "Pretrain/Loss": 2.0350406169891357, "Pretrain/Loss (Raw)": 2.056048631668091, "Pretrain/Step": 6914, "Pretrain/Step Time": 8.799654705449939} +{"Pretrain/Learning Rate": 9.272819050581952e-06, "Pretrain/Loss": 2.0366506576538086, "Pretrain/Loss (Raw)": 2.0854742527008057, "Pretrain/Step": 6915, "Pretrain/Step Time": 8.80058721266687} +{"Pretrain/Learning Rate": 9.266220484530263e-06, "Pretrain/Loss": 2.037691593170166, "Pretrain/Loss (Raw)": 2.0958189964294434, "Pretrain/Step": 6916, "Pretrain/Step Time": 8.79828535951674} +{"Pretrain/Learning Rate": 9.259623732972173e-06, "Pretrain/Loss": 2.0382704734802246, "Pretrain/Loss (Raw)": 1.9393199682235718, "Pretrain/Step": 6917, "Pretrain/Step Time": 8.802720747888088} +{"Pretrain/Learning Rate": 9.25302879666843e-06, "Pretrain/Loss": 2.038414239883423, "Pretrain/Loss (Raw)": 2.0325393676757812, "Pretrain/Step": 6918, "Pretrain/Step Time": 8.802180854603648} +{"Pretrain/Learning Rate": 9.246435676379623e-06, "Pretrain/Loss": 2.037940502166748, "Pretrain/Loss (Raw)": 2.0706541538238525, "Pretrain/Step": 6919, "Pretrain/Step Time": 8.803745547309518} +{"Pretrain/Learning Rate": 9.239844372866083e-06, "Pretrain/Loss": 2.0370898246765137, "Pretrain/Loss (Raw)": 1.8603042364120483, "Pretrain/Step": 6920, "Pretrain/Step Time": 8.803835064172745} +{"Pretrain/Learning Rate": 9.233254886887958e-06, "Pretrain/Loss": 2.0374488830566406, "Pretrain/Loss (Raw)": 2.0716261863708496, "Pretrain/Step": 6921, "Pretrain/Step Time": 8.805186061188579} +{"Pretrain/Learning Rate": 9.226667219205163e-06, "Pretrain/Loss": 2.038933753967285, "Pretrain/Loss (Raw)": 2.1989693641662598, "Pretrain/Step": 6922, "Pretrain/Step Time": 8.80478037148714} +{"Pretrain/Learning Rate": 9.220081370577441e-06, "Pretrain/Loss": 2.0386714935302734, "Pretrain/Loss (Raw)": 2.03621506690979, "Pretrain/Step": 6923, "Pretrain/Step Time": 8.80868350341916} +{"Pretrain/Learning Rate": 9.21349734176429e-06, "Pretrain/Loss": 2.0395092964172363, "Pretrain/Loss (Raw)": 2.1839752197265625, "Pretrain/Step": 6924, "Pretrain/Step Time": 8.800709143280983} +{"Pretrain/Learning Rate": 9.206915133525016e-06, "Pretrain/Loss": 2.0395636558532715, "Pretrain/Loss (Raw)": 2.067201614379883, "Pretrain/Step": 6925, "Pretrain/Step Time": 8.802377611398697} +{"Pretrain/Learning Rate": 9.2003347466187e-06, "Pretrain/Loss": 2.0408525466918945, "Pretrain/Loss (Raw)": 2.15798282623291, "Pretrain/Step": 6926, "Pretrain/Step Time": 8.80037535354495} +{"Pretrain/Learning Rate": 9.193756181804248e-06, "Pretrain/Loss": 2.040776252746582, "Pretrain/Loss (Raw)": 2.0036535263061523, "Pretrain/Step": 6927, "Pretrain/Step Time": 8.805304830893874} +{"Pretrain/Learning Rate": 9.1871794398403e-06, "Pretrain/Loss": 2.0403599739074707, "Pretrain/Loss (Raw)": 2.0147407054901123, "Pretrain/Step": 6928, "Pretrain/Step Time": 8.799729436635971} +{"Pretrain/Learning Rate": 9.180604521485337e-06, "Pretrain/Loss": 2.041510820388794, "Pretrain/Loss (Raw)": 2.1020162105560303, "Pretrain/Step": 6929, "Pretrain/Step Time": 8.799439596012235} +{"Pretrain/Learning Rate": 9.174031427497595e-06, "Pretrain/Loss": 2.039379119873047, "Pretrain/Loss (Raw)": 1.827518105506897, "Pretrain/Step": 6930, "Pretrain/Step Time": 8.799141423776746} +{"Pretrain/Learning Rate": 9.167460158635141e-06, "Pretrain/Loss": 2.039442539215088, "Pretrain/Loss (Raw)": 2.100994110107422, "Pretrain/Step": 6931, "Pretrain/Step Time": 8.803149545565248} +{"Pretrain/Learning Rate": 9.16089071565577e-06, "Pretrain/Loss": 2.03848934173584, "Pretrain/Loss (Raw)": 2.017096996307373, "Pretrain/Step": 6932, "Pretrain/Step Time": 8.801276298239827} +{"Pretrain/Learning Rate": 9.154323099317128e-06, "Pretrain/Loss": 2.0383174419403076, "Pretrain/Loss (Raw)": 2.0479652881622314, "Pretrain/Step": 6933, "Pretrain/Step Time": 8.801649099215865} +{"Pretrain/Learning Rate": 9.147757310376612e-06, "Pretrain/Loss": 2.03667950630188, "Pretrain/Loss (Raw)": 1.8354231119155884, "Pretrain/Step": 6934, "Pretrain/Step Time": 8.79835718870163} +{"Pretrain/Learning Rate": 9.14119334959142e-06, "Pretrain/Loss": 2.0380563735961914, "Pretrain/Loss (Raw)": 2.070096969604492, "Pretrain/Step": 6935, "Pretrain/Step Time": 8.806332318112254} +{"Pretrain/Learning Rate": 9.134631217718534e-06, "Pretrain/Loss": 2.038814067840576, "Pretrain/Loss (Raw)": 2.072054147720337, "Pretrain/Step": 6936, "Pretrain/Step Time": 8.80627240613103} +{"Pretrain/Learning Rate": 9.128070915514744e-06, "Pretrain/Loss": 2.0393896102905273, "Pretrain/Loss (Raw)": 2.0849874019622803, "Pretrain/Step": 6937, "Pretrain/Step Time": 8.806435646489263} +{"Pretrain/Learning Rate": 9.121512443736607e-06, "Pretrain/Loss": 2.0363636016845703, "Pretrain/Loss (Raw)": 1.8320871591567993, "Pretrain/Step": 6938, "Pretrain/Step Time": 8.800643991678953} +{"Pretrain/Learning Rate": 9.114955803140476e-06, "Pretrain/Loss": 2.03816556930542, "Pretrain/Loss (Raw)": 2.1424310207366943, "Pretrain/Step": 6939, "Pretrain/Step Time": 8.802864484488964} +{"Pretrain/Learning Rate": 9.108400994482485e-06, "Pretrain/Loss": 2.037898540496826, "Pretrain/Loss (Raw)": 2.026745557785034, "Pretrain/Step": 6940, "Pretrain/Step Time": 8.8121234215796} +{"Pretrain/Learning Rate": 9.101848018518586e-06, "Pretrain/Loss": 2.0402212142944336, "Pretrain/Loss (Raw)": 1.897940993309021, "Pretrain/Step": 6941, "Pretrain/Step Time": 8.80708740092814} +{"Pretrain/Learning Rate": 9.09529687600449e-06, "Pretrain/Loss": 2.038827896118164, "Pretrain/Loss (Raw)": 1.93523108959198, "Pretrain/Step": 6942, "Pretrain/Step Time": 8.80545987188816} +{"Pretrain/Learning Rate": 9.0887475676957e-06, "Pretrain/Loss": 2.0377631187438965, "Pretrain/Loss (Raw)": 1.888912558555603, "Pretrain/Step": 6943, "Pretrain/Step Time": 8.80477124080062} +{"Pretrain/Learning Rate": 9.082200094347506e-06, "Pretrain/Loss": 2.038811683654785, "Pretrain/Loss (Raw)": 2.0006728172302246, "Pretrain/Step": 6944, "Pretrain/Step Time": 8.803718723356724} +{"Pretrain/Learning Rate": 9.075654456715016e-06, "Pretrain/Loss": 2.0378499031066895, "Pretrain/Loss (Raw)": 1.7728705406188965, "Pretrain/Step": 6945, "Pretrain/Step Time": 8.802057856693864} +{"Pretrain/Learning Rate": 9.069110655553093e-06, "Pretrain/Loss": 2.0367813110351562, "Pretrain/Loss (Raw)": 2.0120177268981934, "Pretrain/Step": 6946, "Pretrain/Step Time": 8.813961144536734} +{"Pretrain/Learning Rate": 9.062568691616389e-06, "Pretrain/Loss": 2.036635398864746, "Pretrain/Loss (Raw)": 2.1686952114105225, "Pretrain/Step": 6947, "Pretrain/Step Time": 8.810394637286663} +{"Pretrain/Learning Rate": 9.056028565659369e-06, "Pretrain/Loss": 2.037937641143799, "Pretrain/Loss (Raw)": 2.020596981048584, "Pretrain/Step": 6948, "Pretrain/Step Time": 8.809600487351418} +{"Pretrain/Learning Rate": 9.049490278436269e-06, "Pretrain/Loss": 2.037896156311035, "Pretrain/Loss (Raw)": 2.0244922637939453, "Pretrain/Step": 6949, "Pretrain/Step Time": 8.802554681897163} +{"Pretrain/Learning Rate": 9.04295383070111e-06, "Pretrain/Loss": 2.0387730598449707, "Pretrain/Loss (Raw)": 2.087967872619629, "Pretrain/Step": 6950, "Pretrain/Step Time": 8.801418920978904} +{"Pretrain/Learning Rate": 9.036419223207699e-06, "Pretrain/Loss": 2.041431427001953, "Pretrain/Loss (Raw)": 2.261148691177368, "Pretrain/Step": 6951, "Pretrain/Step Time": 8.803535494953394} +{"Pretrain/Learning Rate": 9.029886456709652e-06, "Pretrain/Loss": 2.0406768321990967, "Pretrain/Loss (Raw)": 2.058377742767334, "Pretrain/Step": 6952, "Pretrain/Step Time": 8.807700859382749} +{"Pretrain/Learning Rate": 9.023355531960353e-06, "Pretrain/Loss": 2.0390849113464355, "Pretrain/Loss (Raw)": 1.8368167877197266, "Pretrain/Step": 6953, "Pretrain/Step Time": 8.795507861301303} +{"Pretrain/Learning Rate": 9.016826449712981e-06, "Pretrain/Loss": 2.0376667976379395, "Pretrain/Loss (Raw)": 2.074282646179199, "Pretrain/Step": 6954, "Pretrain/Step Time": 8.799233864992857} +{"Pretrain/Learning Rate": 9.010299210720487e-06, "Pretrain/Loss": 2.037139892578125, "Pretrain/Loss (Raw)": 1.953163981437683, "Pretrain/Step": 6955, "Pretrain/Step Time": 8.802193971350789} +{"Pretrain/Learning Rate": 9.003773815735644e-06, "Pretrain/Loss": 2.036360740661621, "Pretrain/Loss (Raw)": 2.0467777252197266, "Pretrain/Step": 6956, "Pretrain/Step Time": 8.797703983262181} +{"Pretrain/Learning Rate": 8.997250265510984e-06, "Pretrain/Loss": 2.0368127822875977, "Pretrain/Loss (Raw)": 2.120121955871582, "Pretrain/Step": 6957, "Pretrain/Step Time": 8.795748991891742} +{"Pretrain/Learning Rate": 8.990728560798827e-06, "Pretrain/Loss": 2.037285327911377, "Pretrain/Loss (Raw)": 2.0887386798858643, "Pretrain/Step": 6958, "Pretrain/Step Time": 8.794823985546827} +{"Pretrain/Learning Rate": 8.984208702351281e-06, "Pretrain/Loss": 2.03580641746521, "Pretrain/Loss (Raw)": 1.9937118291854858, "Pretrain/Step": 6959, "Pretrain/Step Time": 8.793277848511934} +{"Pretrain/Learning Rate": 8.977690690920269e-06, "Pretrain/Loss": 2.036137819290161, "Pretrain/Loss (Raw)": 2.1330747604370117, "Pretrain/Step": 6960, "Pretrain/Step Time": 8.80471278168261} +{"Pretrain/Learning Rate": 8.971174527257464e-06, "Pretrain/Loss": 2.035303831100464, "Pretrain/Loss (Raw)": 1.9322404861450195, "Pretrain/Step": 6961, "Pretrain/Step Time": 8.79922598041594} +{"Pretrain/Learning Rate": 8.964660212114343e-06, "Pretrain/Loss": 2.033374309539795, "Pretrain/Loss (Raw)": 1.8961851596832275, "Pretrain/Step": 6962, "Pretrain/Step Time": 8.798258390277624} +{"Pretrain/Learning Rate": 8.958147746242157e-06, "Pretrain/Loss": 2.032827854156494, "Pretrain/Loss (Raw)": 1.9770946502685547, "Pretrain/Step": 6963, "Pretrain/Step Time": 8.800803858786821} +{"Pretrain/Learning Rate": 8.951637130391976e-06, "Pretrain/Loss": 2.031999111175537, "Pretrain/Loss (Raw)": 2.1030774116516113, "Pretrain/Step": 6964, "Pretrain/Step Time": 8.796241842210293} +{"Pretrain/Learning Rate": 8.945128365314622e-06, "Pretrain/Loss": 2.028501033782959, "Pretrain/Loss (Raw)": 1.7833878993988037, "Pretrain/Step": 6965, "Pretrain/Step Time": 8.795354442670941} +{"Pretrain/Learning Rate": 8.938621451760718e-06, "Pretrain/Loss": 2.0284738540649414, "Pretrain/Loss (Raw)": 2.011852264404297, "Pretrain/Step": 6966, "Pretrain/Step Time": 8.78647300414741} +{"Pretrain/Learning Rate": 8.932116390480663e-06, "Pretrain/Loss": 2.025998115539551, "Pretrain/Loss (Raw)": 1.8890712261199951, "Pretrain/Step": 6967, "Pretrain/Step Time": 8.79456321336329} +{"Pretrain/Learning Rate": 8.925613182224678e-06, "Pretrain/Loss": 2.0254366397857666, "Pretrain/Loss (Raw)": 2.052666187286377, "Pretrain/Step": 6968, "Pretrain/Step Time": 8.797642353922129} +{"Pretrain/Learning Rate": 8.919111827742708e-06, "Pretrain/Loss": 2.0301976203918457, "Pretrain/Loss (Raw)": 2.2583343982696533, "Pretrain/Step": 6969, "Pretrain/Step Time": 8.795545598492026} +{"Pretrain/Learning Rate": 8.912612327784547e-06, "Pretrain/Loss": 2.030399799346924, "Pretrain/Loss (Raw)": 1.9511306285858154, "Pretrain/Step": 6970, "Pretrain/Step Time": 8.802975438535213} +{"Pretrain/Learning Rate": 8.906114683099732e-06, "Pretrain/Loss": 2.0313994884490967, "Pretrain/Loss (Raw)": 2.1187353134155273, "Pretrain/Step": 6971, "Pretrain/Step Time": 8.799758428707719} +{"Pretrain/Learning Rate": 8.899618894437622e-06, "Pretrain/Loss": 2.03415584564209, "Pretrain/Loss (Raw)": 2.1087746620178223, "Pretrain/Step": 6972, "Pretrain/Step Time": 8.79731827788055} +{"Pretrain/Learning Rate": 8.893124962547311e-06, "Pretrain/Loss": 2.0328407287597656, "Pretrain/Loss (Raw)": 1.920419692993164, "Pretrain/Step": 6973, "Pretrain/Step Time": 8.791846185922623} +{"Pretrain/Learning Rate": 8.88663288817774e-06, "Pretrain/Loss": 2.033672332763672, "Pretrain/Loss (Raw)": 2.0715672969818115, "Pretrain/Step": 6974, "Pretrain/Step Time": 8.80119394697249} +{"Pretrain/Learning Rate": 8.880142672077582e-06, "Pretrain/Loss": 2.033255100250244, "Pretrain/Loss (Raw)": 2.068178653717041, "Pretrain/Step": 6975, "Pretrain/Step Time": 8.797744767740369} +{"Pretrain/Learning Rate": 8.873654314995348e-06, "Pretrain/Loss": 2.03436279296875, "Pretrain/Loss (Raw)": 2.120737314224243, "Pretrain/Step": 6976, "Pretrain/Step Time": 8.797017626464367} +{"Pretrain/Learning Rate": 8.86716781767927e-06, "Pretrain/Loss": 2.0345752239227295, "Pretrain/Loss (Raw)": 2.094942331314087, "Pretrain/Step": 6977, "Pretrain/Step Time": 8.801462601870298} +{"Pretrain/Learning Rate": 8.86068318087743e-06, "Pretrain/Loss": 2.035539388656616, "Pretrain/Loss (Raw)": 2.1880557537078857, "Pretrain/Step": 6978, "Pretrain/Step Time": 8.805112948641181} +{"Pretrain/Learning Rate": 8.854200405337657e-06, "Pretrain/Loss": 2.0369396209716797, "Pretrain/Loss (Raw)": 1.9859201908111572, "Pretrain/Step": 6979, "Pretrain/Step Time": 8.80051738396287} +{"Pretrain/Learning Rate": 8.847719491807572e-06, "Pretrain/Loss": 2.0375709533691406, "Pretrain/Loss (Raw)": 2.099416494369507, "Pretrain/Step": 6980, "Pretrain/Step Time": 8.796420697122812} +{"Pretrain/Learning Rate": 8.841240441034579e-06, "Pretrain/Loss": 2.038384199142456, "Pretrain/Loss (Raw)": 1.888588309288025, "Pretrain/Step": 6981, "Pretrain/Step Time": 8.807440415024757} +{"Pretrain/Learning Rate": 8.83476325376589e-06, "Pretrain/Loss": 2.0394668579101562, "Pretrain/Loss (Raw)": 2.1114132404327393, "Pretrain/Step": 6982, "Pretrain/Step Time": 8.808100601658225} +{"Pretrain/Learning Rate": 8.828287930748477e-06, "Pretrain/Loss": 2.037950038909912, "Pretrain/Loss (Raw)": 1.8845478296279907, "Pretrain/Step": 6983, "Pretrain/Step Time": 8.812870804220438} +{"Pretrain/Learning Rate": 8.821814472729104e-06, "Pretrain/Loss": 2.03535795211792, "Pretrain/Loss (Raw)": 1.858516812324524, "Pretrain/Step": 6984, "Pretrain/Step Time": 8.802894372493029} +{"Pretrain/Learning Rate": 8.815342880454311e-06, "Pretrain/Loss": 2.0364632606506348, "Pretrain/Loss (Raw)": 2.0438737869262695, "Pretrain/Step": 6985, "Pretrain/Step Time": 8.804121615365148} +{"Pretrain/Learning Rate": 8.80887315467045e-06, "Pretrain/Loss": 2.038560152053833, "Pretrain/Loss (Raw)": 2.1236438751220703, "Pretrain/Step": 6986, "Pretrain/Step Time": 8.801793303340673} +{"Pretrain/Learning Rate": 8.80240529612363e-06, "Pretrain/Loss": 2.0389249324798584, "Pretrain/Loss (Raw)": 2.103083372116089, "Pretrain/Step": 6987, "Pretrain/Step Time": 8.806307643651962} +{"Pretrain/Learning Rate": 8.79593930555975e-06, "Pretrain/Loss": 2.039547920227051, "Pretrain/Loss (Raw)": 2.063106060028076, "Pretrain/Step": 6988, "Pretrain/Step Time": 8.806240698322654} +{"Pretrain/Learning Rate": 8.789475183724514e-06, "Pretrain/Loss": 2.0381526947021484, "Pretrain/Loss (Raw)": 1.9199495315551758, "Pretrain/Step": 6989, "Pretrain/Step Time": 8.799547692760825} +{"Pretrain/Learning Rate": 8.783012931363385e-06, "Pretrain/Loss": 2.038611888885498, "Pretrain/Loss (Raw)": 2.056488037109375, "Pretrain/Step": 6990, "Pretrain/Step Time": 8.801665598526597} +{"Pretrain/Learning Rate": 8.776552549221623e-06, "Pretrain/Loss": 2.03774356842041, "Pretrain/Loss (Raw)": 2.067704677581787, "Pretrain/Step": 6991, "Pretrain/Step Time": 8.804652022197843} +{"Pretrain/Learning Rate": 8.770094038044257e-06, "Pretrain/Loss": 2.0385966300964355, "Pretrain/Loss (Raw)": 1.806451678276062, "Pretrain/Step": 6992, "Pretrain/Step Time": 8.801456674933434} +{"Pretrain/Learning Rate": 8.763637398576135e-06, "Pretrain/Loss": 2.03763484954834, "Pretrain/Loss (Raw)": 2.08860445022583, "Pretrain/Step": 6993, "Pretrain/Step Time": 8.802527328953147} +{"Pretrain/Learning Rate": 8.757182631561859e-06, "Pretrain/Loss": 2.0367624759674072, "Pretrain/Loss (Raw)": 2.0211658477783203, "Pretrain/Step": 6994, "Pretrain/Step Time": 8.804207073524594} +{"Pretrain/Learning Rate": 8.750729737745819e-06, "Pretrain/Loss": 2.035249948501587, "Pretrain/Loss (Raw)": 1.931074619293213, "Pretrain/Step": 6995, "Pretrain/Step Time": 8.791804913431406} +{"Pretrain/Learning Rate": 8.744278717872185e-06, "Pretrain/Loss": 2.0351829528808594, "Pretrain/Loss (Raw)": 2.0858168601989746, "Pretrain/Step": 6996, "Pretrain/Step Time": 8.79100332222879} +{"Pretrain/Learning Rate": 8.73782957268494e-06, "Pretrain/Loss": 2.0350117683410645, "Pretrain/Loss (Raw)": 2.0060737133026123, "Pretrain/Step": 6997, "Pretrain/Step Time": 8.793693125247955} +{"Pretrain/Learning Rate": 8.731382302927813e-06, "Pretrain/Loss": 2.0345513820648193, "Pretrain/Loss (Raw)": 2.044768810272217, "Pretrain/Step": 6998, "Pretrain/Step Time": 8.798168098554015} +{"Pretrain/Learning Rate": 8.724936909344342e-06, "Pretrain/Loss": 2.036933183670044, "Pretrain/Loss (Raw)": 2.1290833950042725, "Pretrain/Step": 6999, "Pretrain/Step Time": 8.795839665457606} +{"Pretrain/Learning Rate": 8.718493392677829e-06, "Pretrain/Loss": 2.0365116596221924, "Pretrain/Loss (Raw)": 2.0576162338256836, "Pretrain/Step": 7000, "Pretrain/Step Time": 8.793909266591072} +{"Pretrain/Learning Rate": 8.712051753671389e-06, "Pretrain/Loss": 2.037360191345215, "Pretrain/Loss (Raw)": 2.118825674057007, "Pretrain/Step": 7001, "Pretrain/Step Time": 8.790463663637638} +{"Pretrain/Learning Rate": 8.705611993067892e-06, "Pretrain/Loss": 2.035841464996338, "Pretrain/Loss (Raw)": 2.0011394023895264, "Pretrain/Step": 7002, "Pretrain/Step Time": 8.804090987890959} +{"Pretrain/Learning Rate": 8.699174111609998e-06, "Pretrain/Loss": 2.035466432571411, "Pretrain/Loss (Raw)": 2.097618579864502, "Pretrain/Step": 7003, "Pretrain/Step Time": 8.8042212408036} +{"Pretrain/Learning Rate": 8.692738110040152e-06, "Pretrain/Loss": 2.0337467193603516, "Pretrain/Loss (Raw)": 1.891518473625183, "Pretrain/Step": 7004, "Pretrain/Step Time": 8.805473094806075} +{"Pretrain/Learning Rate": 8.686303989100596e-06, "Pretrain/Loss": 2.033872127532959, "Pretrain/Loss (Raw)": 2.02982497215271, "Pretrain/Step": 7005, "Pretrain/Step Time": 8.80216353200376} +{"Pretrain/Learning Rate": 8.679871749533338e-06, "Pretrain/Loss": 2.0347752571105957, "Pretrain/Loss (Raw)": 2.0789833068847656, "Pretrain/Step": 7006, "Pretrain/Step Time": 8.803504213690758} +{"Pretrain/Learning Rate": 8.673441392080173e-06, "Pretrain/Loss": 2.0350828170776367, "Pretrain/Loss (Raw)": 2.0029797554016113, "Pretrain/Step": 7007, "Pretrain/Step Time": 8.801097018644214} +{"Pretrain/Learning Rate": 8.667012917482673e-06, "Pretrain/Loss": 2.034757137298584, "Pretrain/Loss (Raw)": 2.076913356781006, "Pretrain/Step": 7008, "Pretrain/Step Time": 8.801959758624434} +{"Pretrain/Learning Rate": 8.66058632648222e-06, "Pretrain/Loss": 2.034590244293213, "Pretrain/Loss (Raw)": 2.017719268798828, "Pretrain/Step": 7009, "Pretrain/Step Time": 8.801261946558952} +{"Pretrain/Learning Rate": 8.654161619819931e-06, "Pretrain/Loss": 2.0322532653808594, "Pretrain/Loss (Raw)": 1.8904868364334106, "Pretrain/Step": 7010, "Pretrain/Step Time": 8.804066894575953} +{"Pretrain/Learning Rate": 8.647738798236757e-06, "Pretrain/Loss": 2.032512664794922, "Pretrain/Loss (Raw)": 2.0661890506744385, "Pretrain/Step": 7011, "Pretrain/Step Time": 8.803384425118566} +{"Pretrain/Learning Rate": 8.641317862473392e-06, "Pretrain/Loss": 2.0328171253204346, "Pretrain/Loss (Raw)": 2.007624626159668, "Pretrain/Step": 7012, "Pretrain/Step Time": 8.803943146020174} +{"Pretrain/Learning Rate": 8.634898813270348e-06, "Pretrain/Loss": 2.0315303802490234, "Pretrain/Loss (Raw)": 1.93711256980896, "Pretrain/Step": 7013, "Pretrain/Step Time": 8.805289624258876} +{"Pretrain/Learning Rate": 8.628481651367876e-06, "Pretrain/Loss": 2.034738540649414, "Pretrain/Loss (Raw)": 2.265517473220825, "Pretrain/Step": 7014, "Pretrain/Step Time": 8.806351909413934} +{"Pretrain/Learning Rate": 8.622066377506049e-06, "Pretrain/Loss": 2.0339901447296143, "Pretrain/Loss (Raw)": 2.1328847408294678, "Pretrain/Step": 7015, "Pretrain/Step Time": 8.804201729595661} +{"Pretrain/Learning Rate": 8.615652992424697e-06, "Pretrain/Loss": 2.0380859375, "Pretrain/Loss (Raw)": 2.306307792663574, "Pretrain/Step": 7016, "Pretrain/Step Time": 8.785080017521977} +{"Pretrain/Learning Rate": 8.609241496863463e-06, "Pretrain/Loss": 2.0371129512786865, "Pretrain/Loss (Raw)": 1.8849643468856812, "Pretrain/Step": 7017, "Pretrain/Step Time": 8.803467417135835} +{"Pretrain/Learning Rate": 8.602831891561718e-06, "Pretrain/Loss": 2.0371670722961426, "Pretrain/Loss (Raw)": 2.02760648727417, "Pretrain/Step": 7018, "Pretrain/Step Time": 8.80098219960928} +{"Pretrain/Learning Rate": 8.596424177258677e-06, "Pretrain/Loss": 2.037203788757324, "Pretrain/Loss (Raw)": 2.1034772396087646, "Pretrain/Step": 7019, "Pretrain/Step Time": 8.80204677209258} +{"Pretrain/Learning Rate": 8.590018354693293e-06, "Pretrain/Loss": 2.0370841026306152, "Pretrain/Loss (Raw)": 1.9405577182769775, "Pretrain/Step": 7020, "Pretrain/Step Time": 8.806259667500854} +{"Pretrain/Learning Rate": 8.583614424604322e-06, "Pretrain/Loss": 2.0368893146514893, "Pretrain/Loss (Raw)": 2.0347864627838135, "Pretrain/Step": 7021, "Pretrain/Step Time": 8.803424606099725} +{"Pretrain/Learning Rate": 8.57721238773028e-06, "Pretrain/Loss": 2.0360984802246094, "Pretrain/Loss (Raw)": 2.076964855194092, "Pretrain/Step": 7022, "Pretrain/Step Time": 8.80141887255013} +{"Pretrain/Learning Rate": 8.570812244809504e-06, "Pretrain/Loss": 2.036916494369507, "Pretrain/Loss (Raw)": 2.2203123569488525, "Pretrain/Step": 7023, "Pretrain/Step Time": 8.805559791624546} +{"Pretrain/Learning Rate": 8.564413996580073e-06, "Pretrain/Loss": 2.033627510070801, "Pretrain/Loss (Raw)": 1.89815092086792, "Pretrain/Step": 7024, "Pretrain/Step Time": 8.804079299792647} +{"Pretrain/Learning Rate": 8.55801764377987e-06, "Pretrain/Loss": 2.0337703227996826, "Pretrain/Loss (Raw)": 2.1120693683624268, "Pretrain/Step": 7025, "Pretrain/Step Time": 8.805138599127531} +{"Pretrain/Learning Rate": 8.551623187146537e-06, "Pretrain/Loss": 2.034243583679199, "Pretrain/Loss (Raw)": 2.0471367835998535, "Pretrain/Step": 7026, "Pretrain/Step Time": 8.802784599363804} +{"Pretrain/Learning Rate": 8.545230627417539e-06, "Pretrain/Loss": 2.03467059135437, "Pretrain/Loss (Raw)": 2.016000747680664, "Pretrain/Step": 7027, "Pretrain/Step Time": 8.798669997602701} +{"Pretrain/Learning Rate": 8.538839965330079e-06, "Pretrain/Loss": 2.0364718437194824, "Pretrain/Loss (Raw)": 2.125822067260742, "Pretrain/Step": 7028, "Pretrain/Step Time": 8.801938289776444} +{"Pretrain/Learning Rate": 8.532451201621156e-06, "Pretrain/Loss": 2.033390522003174, "Pretrain/Loss (Raw)": 2.017798900604248, "Pretrain/Step": 7029, "Pretrain/Step Time": 8.801911721006036} +{"Pretrain/Learning Rate": 8.526064337027565e-06, "Pretrain/Loss": 2.035245895385742, "Pretrain/Loss (Raw)": 2.3248307704925537, "Pretrain/Step": 7030, "Pretrain/Step Time": 8.798487983644009} +{"Pretrain/Learning Rate": 8.519679372285861e-06, "Pretrain/Loss": 2.0358481407165527, "Pretrain/Loss (Raw)": 1.9442330598831177, "Pretrain/Step": 7031, "Pretrain/Step Time": 8.80249447003007} +{"Pretrain/Learning Rate": 8.51329630813239e-06, "Pretrain/Loss": 2.0354599952697754, "Pretrain/Loss (Raw)": 2.1059322357177734, "Pretrain/Step": 7032, "Pretrain/Step Time": 8.799236187711358} +{"Pretrain/Learning Rate": 8.506915145303268e-06, "Pretrain/Loss": 2.035015821456909, "Pretrain/Loss (Raw)": 1.983471155166626, "Pretrain/Step": 7033, "Pretrain/Step Time": 8.800402194261551} +{"Pretrain/Learning Rate": 8.50053588453442e-06, "Pretrain/Loss": 2.035029411315918, "Pretrain/Loss (Raw)": 2.0448009967803955, "Pretrain/Step": 7034, "Pretrain/Step Time": 8.803270747885108} +{"Pretrain/Learning Rate": 8.49415852656152e-06, "Pretrain/Loss": 2.0340733528137207, "Pretrain/Loss (Raw)": 1.955378532409668, "Pretrain/Step": 7035, "Pretrain/Step Time": 8.799709731712937} +{"Pretrain/Learning Rate": 8.487783072120036e-06, "Pretrain/Loss": 2.034362316131592, "Pretrain/Loss (Raw)": 2.014871120452881, "Pretrain/Step": 7036, "Pretrain/Step Time": 8.799706963822246} +{"Pretrain/Learning Rate": 8.48140952194521e-06, "Pretrain/Loss": 2.035569190979004, "Pretrain/Loss (Raw)": 2.1336467266082764, "Pretrain/Step": 7037, "Pretrain/Step Time": 8.803339434787631} +{"Pretrain/Learning Rate": 8.475037876772085e-06, "Pretrain/Loss": 2.036327362060547, "Pretrain/Loss (Raw)": 2.050187349319458, "Pretrain/Step": 7038, "Pretrain/Step Time": 8.797842625528574} +{"Pretrain/Learning Rate": 8.468668137335459e-06, "Pretrain/Loss": 2.0365662574768066, "Pretrain/Loss (Raw)": 2.0946545600891113, "Pretrain/Step": 7039, "Pretrain/Step Time": 8.79891448840499} +{"Pretrain/Learning Rate": 8.462300304369921e-06, "Pretrain/Loss": 2.033878803253174, "Pretrain/Loss (Raw)": 1.796142816543579, "Pretrain/Step": 7040, "Pretrain/Step Time": 8.800538528710604} +{"Pretrain/Learning Rate": 8.455934378609834e-06, "Pretrain/Loss": 2.033194065093994, "Pretrain/Loss (Raw)": 2.040478229522705, "Pretrain/Step": 7041, "Pretrain/Step Time": 8.800636652857065} +{"Pretrain/Learning Rate": 8.449570360789358e-06, "Pretrain/Loss": 2.033705234527588, "Pretrain/Loss (Raw)": 2.1214966773986816, "Pretrain/Step": 7042, "Pretrain/Step Time": 8.798865860328078} +{"Pretrain/Learning Rate": 8.443208251642417e-06, "Pretrain/Loss": 2.0327188968658447, "Pretrain/Loss (Raw)": 1.9592214822769165, "Pretrain/Step": 7043, "Pretrain/Step Time": 8.798858478665352} +{"Pretrain/Learning Rate": 8.436848051902721e-06, "Pretrain/Loss": 2.0334486961364746, "Pretrain/Loss (Raw)": 2.1892170906066895, "Pretrain/Step": 7044, "Pretrain/Step Time": 8.799986645579338} +{"Pretrain/Learning Rate": 8.430489762303745e-06, "Pretrain/Loss": 2.0355868339538574, "Pretrain/Loss (Raw)": 2.2130095958709717, "Pretrain/Step": 7045, "Pretrain/Step Time": 8.798511123284698} +{"Pretrain/Learning Rate": 8.424133383578778e-06, "Pretrain/Loss": 2.034607410430908, "Pretrain/Loss (Raw)": 1.9071664810180664, "Pretrain/Step": 7046, "Pretrain/Step Time": 8.799507800489664} +{"Pretrain/Learning Rate": 8.417778916460856e-06, "Pretrain/Loss": 2.035149097442627, "Pretrain/Loss (Raw)": 2.1400182247161865, "Pretrain/Step": 7047, "Pretrain/Step Time": 8.794706206768751} +{"Pretrain/Learning Rate": 8.411426361682806e-06, "Pretrain/Loss": 2.0366201400756836, "Pretrain/Loss (Raw)": 2.0485939979553223, "Pretrain/Step": 7048, "Pretrain/Step Time": 8.796147610992193} +{"Pretrain/Learning Rate": 8.40507571997723e-06, "Pretrain/Loss": 2.0351362228393555, "Pretrain/Loss (Raw)": 1.8816590309143066, "Pretrain/Step": 7049, "Pretrain/Step Time": 8.797991866245866} +{"Pretrain/Learning Rate": 8.398726992076534e-06, "Pretrain/Loss": 2.0331966876983643, "Pretrain/Loss (Raw)": 1.9507142305374146, "Pretrain/Step": 7050, "Pretrain/Step Time": 8.79532764852047} +{"Pretrain/Learning Rate": 8.392380178712852e-06, "Pretrain/Loss": 2.0325028896331787, "Pretrain/Loss (Raw)": 1.9473952054977417, "Pretrain/Step": 7051, "Pretrain/Step Time": 8.790949407964945} +{"Pretrain/Learning Rate": 8.386035280618156e-06, "Pretrain/Loss": 2.032266855239868, "Pretrain/Loss (Raw)": 2.153763771057129, "Pretrain/Step": 7052, "Pretrain/Step Time": 8.794776778668165} +{"Pretrain/Learning Rate": 8.37969229852415e-06, "Pretrain/Loss": 2.0319364070892334, "Pretrain/Loss (Raw)": 2.0249173641204834, "Pretrain/Step": 7053, "Pretrain/Step Time": 8.795370653271675} +{"Pretrain/Learning Rate": 8.373351233162362e-06, "Pretrain/Loss": 2.0298702716827393, "Pretrain/Loss (Raw)": 1.8935158252716064, "Pretrain/Step": 7054, "Pretrain/Step Time": 8.798805547878146} +{"Pretrain/Learning Rate": 8.367012085264042e-06, "Pretrain/Loss": 2.0311734676361084, "Pretrain/Loss (Raw)": 2.170457124710083, "Pretrain/Step": 7055, "Pretrain/Step Time": 8.798105873167515} +{"Pretrain/Learning Rate": 8.360674855560274e-06, "Pretrain/Loss": 2.0302393436431885, "Pretrain/Loss (Raw)": 1.8951789140701294, "Pretrain/Step": 7056, "Pretrain/Step Time": 8.795302484184504} +{"Pretrain/Learning Rate": 8.354339544781878e-06, "Pretrain/Loss": 2.0303924083709717, "Pretrain/Loss (Raw)": 2.1216070652008057, "Pretrain/Step": 7057, "Pretrain/Step Time": 8.797585623338819} +{"Pretrain/Learning Rate": 8.348006153659502e-06, "Pretrain/Loss": 2.030482769012451, "Pretrain/Loss (Raw)": 1.8390997648239136, "Pretrain/Step": 7058, "Pretrain/Step Time": 8.793960858136415} +{"Pretrain/Learning Rate": 8.341674682923503e-06, "Pretrain/Loss": 2.028873920440674, "Pretrain/Loss (Raw)": 1.8950645923614502, "Pretrain/Step": 7059, "Pretrain/Step Time": 8.787548556923866} +{"Pretrain/Learning Rate": 8.335345133304088e-06, "Pretrain/Loss": 2.028580665588379, "Pretrain/Loss (Raw)": 1.9795258045196533, "Pretrain/Step": 7060, "Pretrain/Step Time": 8.798467056825757} +{"Pretrain/Learning Rate": 8.329017505531195e-06, "Pretrain/Loss": 2.028653383255005, "Pretrain/Loss (Raw)": 2.0572872161865234, "Pretrain/Step": 7061, "Pretrain/Step Time": 8.796631241217256} +{"Pretrain/Learning Rate": 8.322691800334562e-06, "Pretrain/Loss": 2.029587984085083, "Pretrain/Loss (Raw)": 1.9550601243972778, "Pretrain/Step": 7062, "Pretrain/Step Time": 8.798886267468333} +{"Pretrain/Learning Rate": 8.316368018443688e-06, "Pretrain/Loss": 2.029362201690674, "Pretrain/Loss (Raw)": 2.0411946773529053, "Pretrain/Step": 7063, "Pretrain/Step Time": 8.795620201155543} +{"Pretrain/Learning Rate": 8.310046160587878e-06, "Pretrain/Loss": 2.028257369995117, "Pretrain/Loss (Raw)": 1.930646538734436, "Pretrain/Step": 7064, "Pretrain/Step Time": 8.800060288980603} +{"Pretrain/Learning Rate": 8.303726227496191e-06, "Pretrain/Loss": 2.0306029319763184, "Pretrain/Loss (Raw)": 2.385185718536377, "Pretrain/Step": 7065, "Pretrain/Step Time": 8.796798564493656} +{"Pretrain/Learning Rate": 8.297408219897471e-06, "Pretrain/Loss": 2.0328657627105713, "Pretrain/Loss (Raw)": 2.1217517852783203, "Pretrain/Step": 7066, "Pretrain/Step Time": 8.806781651452184} +{"Pretrain/Learning Rate": 8.291092138520332e-06, "Pretrain/Loss": 2.034000873565674, "Pretrain/Loss (Raw)": 2.2877209186553955, "Pretrain/Step": 7067, "Pretrain/Step Time": 8.801708158105612} +{"Pretrain/Learning Rate": 8.28477798409319e-06, "Pretrain/Loss": 2.033560037612915, "Pretrain/Loss (Raw)": 1.9703127145767212, "Pretrain/Step": 7068, "Pretrain/Step Time": 8.796906922012568} +{"Pretrain/Learning Rate": 8.278465757344214e-06, "Pretrain/Loss": 2.034681797027588, "Pretrain/Loss (Raw)": 2.041553020477295, "Pretrain/Step": 7069, "Pretrain/Step Time": 8.79620311036706} +{"Pretrain/Learning Rate": 8.272155459001366e-06, "Pretrain/Loss": 2.037931442260742, "Pretrain/Loss (Raw)": 2.3511502742767334, "Pretrain/Step": 7070, "Pretrain/Step Time": 8.79376471415162} +{"Pretrain/Learning Rate": 8.265847089792362e-06, "Pretrain/Loss": 2.03853702545166, "Pretrain/Loss (Raw)": 1.966444730758667, "Pretrain/Step": 7071, "Pretrain/Step Time": 8.795835642144084} +{"Pretrain/Learning Rate": 8.259540650444736e-06, "Pretrain/Loss": 2.039156436920166, "Pretrain/Loss (Raw)": 2.079955816268921, "Pretrain/Step": 7072, "Pretrain/Step Time": 8.799234284088016} +{"Pretrain/Learning Rate": 8.253236141685764e-06, "Pretrain/Loss": 2.040160894393921, "Pretrain/Loss (Raw)": 1.9014346599578857, "Pretrain/Step": 7073, "Pretrain/Step Time": 8.79222035780549} +{"Pretrain/Learning Rate": 8.246933564242506e-06, "Pretrain/Loss": 2.0397725105285645, "Pretrain/Loss (Raw)": 1.9623148441314697, "Pretrain/Step": 7074, "Pretrain/Step Time": 8.784105598926544} +{"Pretrain/Learning Rate": 8.240632918841823e-06, "Pretrain/Loss": 2.0391831398010254, "Pretrain/Loss (Raw)": 2.0932371616363525, "Pretrain/Step": 7075, "Pretrain/Step Time": 8.789760207757354} +{"Pretrain/Learning Rate": 8.234334206210323e-06, "Pretrain/Loss": 2.0398130416870117, "Pretrain/Loss (Raw)": 2.1012439727783203, "Pretrain/Step": 7076, "Pretrain/Step Time": 8.788343088701367} +{"Pretrain/Learning Rate": 8.228037427074403e-06, "Pretrain/Loss": 2.0383288860321045, "Pretrain/Loss (Raw)": 1.8345216512680054, "Pretrain/Step": 7077, "Pretrain/Step Time": 8.790972732007504} +{"Pretrain/Learning Rate": 8.221742582160233e-06, "Pretrain/Loss": 2.037942886352539, "Pretrain/Loss (Raw)": 2.038539409637451, "Pretrain/Step": 7078, "Pretrain/Step Time": 8.792784806340933} +{"Pretrain/Learning Rate": 8.215449672193776e-06, "Pretrain/Loss": 2.03585147857666, "Pretrain/Loss (Raw)": 1.9934512376785278, "Pretrain/Step": 7079, "Pretrain/Step Time": 8.794062621891499} +{"Pretrain/Learning Rate": 8.209158697900757e-06, "Pretrain/Loss": 2.0337696075439453, "Pretrain/Loss (Raw)": 1.7919119596481323, "Pretrain/Step": 7080, "Pretrain/Step Time": 8.791260063648224} +{"Pretrain/Learning Rate": 8.202869660006676e-06, "Pretrain/Loss": 2.038691997528076, "Pretrain/Loss (Raw)": 2.4668846130371094, "Pretrain/Step": 7081, "Pretrain/Step Time": 8.799000211060047} +{"Pretrain/Learning Rate": 8.19658255923681e-06, "Pretrain/Loss": 2.0390214920043945, "Pretrain/Loss (Raw)": 2.1164777278900146, "Pretrain/Step": 7082, "Pretrain/Step Time": 8.795044695958495} +{"Pretrain/Learning Rate": 8.19029739631623e-06, "Pretrain/Loss": 2.03904128074646, "Pretrain/Loss (Raw)": 1.9556822776794434, "Pretrain/Step": 7083, "Pretrain/Step Time": 8.795000314712524} +{"Pretrain/Learning Rate": 8.184014171969765e-06, "Pretrain/Loss": 2.0394091606140137, "Pretrain/Loss (Raw)": 2.093858242034912, "Pretrain/Step": 7084, "Pretrain/Step Time": 8.799983393400908} +{"Pretrain/Learning Rate": 8.177732886922023e-06, "Pretrain/Loss": 2.0395150184631348, "Pretrain/Loss (Raw)": 2.1336653232574463, "Pretrain/Step": 7085, "Pretrain/Step Time": 8.800031399354339} +{"Pretrain/Learning Rate": 8.17145354189739e-06, "Pretrain/Loss": 2.0398454666137695, "Pretrain/Loss (Raw)": 2.131035089492798, "Pretrain/Step": 7086, "Pretrain/Step Time": 8.80293401144445} +{"Pretrain/Learning Rate": 8.16517613762004e-06, "Pretrain/Loss": 2.0403876304626465, "Pretrain/Loss (Raw)": 2.063129425048828, "Pretrain/Step": 7087, "Pretrain/Step Time": 8.802207192406058} +{"Pretrain/Learning Rate": 8.158900674813904e-06, "Pretrain/Loss": 2.0391123294830322, "Pretrain/Loss (Raw)": 1.9698200225830078, "Pretrain/Step": 7088, "Pretrain/Step Time": 8.797739926725626} +{"Pretrain/Learning Rate": 8.1526271542027e-06, "Pretrain/Loss": 2.0401904582977295, "Pretrain/Loss (Raw)": 2.0702574253082275, "Pretrain/Step": 7089, "Pretrain/Step Time": 8.794002883136272} +{"Pretrain/Learning Rate": 8.146355576509915e-06, "Pretrain/Loss": 2.0417561531066895, "Pretrain/Loss (Raw)": 2.0965986251831055, "Pretrain/Step": 7090, "Pretrain/Step Time": 8.800990723073483} +{"Pretrain/Learning Rate": 8.140085942458828e-06, "Pretrain/Loss": 2.042250633239746, "Pretrain/Loss (Raw)": 2.0403730869293213, "Pretrain/Step": 7091, "Pretrain/Step Time": 8.79736065864563} +{"Pretrain/Learning Rate": 8.133818252772476e-06, "Pretrain/Loss": 2.0421948432922363, "Pretrain/Loss (Raw)": 2.0959250926971436, "Pretrain/Step": 7092, "Pretrain/Step Time": 8.79621759802103} +{"Pretrain/Learning Rate": 8.12755250817368e-06, "Pretrain/Loss": 2.0434794425964355, "Pretrain/Loss (Raw)": 1.9478524923324585, "Pretrain/Step": 7093, "Pretrain/Step Time": 8.80021831765771} +{"Pretrain/Learning Rate": 8.121288709385025e-06, "Pretrain/Loss": 2.042661190032959, "Pretrain/Loss (Raw)": 1.9070781469345093, "Pretrain/Step": 7094, "Pretrain/Step Time": 8.805028965696692} +{"Pretrain/Learning Rate": 8.11502685712891e-06, "Pretrain/Loss": 2.0424458980560303, "Pretrain/Loss (Raw)": 1.8615031242370605, "Pretrain/Step": 7095, "Pretrain/Step Time": 8.807333575561643} +{"Pretrain/Learning Rate": 8.108766952127445e-06, "Pretrain/Loss": 2.042442798614502, "Pretrain/Loss (Raw)": 2.0522971153259277, "Pretrain/Step": 7096, "Pretrain/Step Time": 8.803575739264488} +{"Pretrain/Learning Rate": 8.102508995102576e-06, "Pretrain/Loss": 2.040173053741455, "Pretrain/Loss (Raw)": 1.9678319692611694, "Pretrain/Step": 7097, "Pretrain/Step Time": 8.805225437507033} +{"Pretrain/Learning Rate": 8.096252986775985e-06, "Pretrain/Loss": 2.0405781269073486, "Pretrain/Loss (Raw)": 2.0029587745666504, "Pretrain/Step": 7098, "Pretrain/Step Time": 8.800128355622292} +{"Pretrain/Learning Rate": 8.089998927869172e-06, "Pretrain/Loss": 2.0408332347869873, "Pretrain/Loss (Raw)": 2.15136981010437, "Pretrain/Step": 7099, "Pretrain/Step Time": 8.801281824707985} +{"Pretrain/Learning Rate": 8.083746819103346e-06, "Pretrain/Loss": 2.0395026206970215, "Pretrain/Loss (Raw)": 1.9384819269180298, "Pretrain/Step": 7100, "Pretrain/Step Time": 8.797277111560106} +{"Pretrain/Learning Rate": 8.077496661199557e-06, "Pretrain/Loss": 2.0382931232452393, "Pretrain/Loss (Raw)": 1.7655901908874512, "Pretrain/Step": 7101, "Pretrain/Step Time": 8.800863932818174} +{"Pretrain/Learning Rate": 8.071248454878596e-06, "Pretrain/Loss": 2.0360498428344727, "Pretrain/Loss (Raw)": 1.7844280004501343, "Pretrain/Step": 7102, "Pretrain/Step Time": 8.798932161182165} +{"Pretrain/Learning Rate": 8.065002200861033e-06, "Pretrain/Loss": 2.037210702896118, "Pretrain/Loss (Raw)": 2.216764450073242, "Pretrain/Step": 7103, "Pretrain/Step Time": 8.797544641420245} +{"Pretrain/Learning Rate": 8.058757899867209e-06, "Pretrain/Loss": 2.036182165145874, "Pretrain/Loss (Raw)": 1.9890828132629395, "Pretrain/Step": 7104, "Pretrain/Step Time": 8.79897610284388} +{"Pretrain/Learning Rate": 8.052515552617262e-06, "Pretrain/Loss": 2.031597375869751, "Pretrain/Loss (Raw)": 1.5081027746200562, "Pretrain/Step": 7105, "Pretrain/Step Time": 8.799252046272159} +{"Pretrain/Learning Rate": 8.04627515983108e-06, "Pretrain/Loss": 2.0317413806915283, "Pretrain/Loss (Raw)": 2.2064907550811768, "Pretrain/Step": 7106, "Pretrain/Step Time": 8.796713888645172} +{"Pretrain/Learning Rate": 8.040036722228336e-06, "Pretrain/Loss": 2.0324783325195312, "Pretrain/Loss (Raw)": 2.0802419185638428, "Pretrain/Step": 7107, "Pretrain/Step Time": 8.79665131866932} +{"Pretrain/Learning Rate": 8.033800240528466e-06, "Pretrain/Loss": 2.0341646671295166, "Pretrain/Loss (Raw)": 2.315282106399536, "Pretrain/Step": 7108, "Pretrain/Step Time": 8.797136783599854} +{"Pretrain/Learning Rate": 8.027565715450707e-06, "Pretrain/Loss": 2.0345191955566406, "Pretrain/Loss (Raw)": 1.933932900428772, "Pretrain/Step": 7109, "Pretrain/Step Time": 8.793759563937783} +{"Pretrain/Learning Rate": 8.02133314771405e-06, "Pretrain/Loss": 2.033482551574707, "Pretrain/Loss (Raw)": 1.978735327720642, "Pretrain/Step": 7110, "Pretrain/Step Time": 8.795601151883602} +{"Pretrain/Learning Rate": 8.015102538037255e-06, "Pretrain/Loss": 2.0348873138427734, "Pretrain/Loss (Raw)": 2.0643486976623535, "Pretrain/Step": 7111, "Pretrain/Step Time": 8.792085856199265} +{"Pretrain/Learning Rate": 8.008873887138868e-06, "Pretrain/Loss": 2.0353450775146484, "Pretrain/Loss (Raw)": 1.9171029329299927, "Pretrain/Step": 7112, "Pretrain/Step Time": 8.80008216202259} +{"Pretrain/Learning Rate": 8.002647195737214e-06, "Pretrain/Loss": 2.0360519886016846, "Pretrain/Loss (Raw)": 2.1343815326690674, "Pretrain/Step": 7113, "Pretrain/Step Time": 8.797963814809918} +{"Pretrain/Learning Rate": 7.996422464550382e-06, "Pretrain/Loss": 2.0352721214294434, "Pretrain/Loss (Raw)": 2.023803472518921, "Pretrain/Step": 7114, "Pretrain/Step Time": 8.79714141599834} +{"Pretrain/Learning Rate": 7.990199694296224e-06, "Pretrain/Loss": 2.034172773361206, "Pretrain/Loss (Raw)": 1.9623585939407349, "Pretrain/Step": 7115, "Pretrain/Step Time": 8.79333745315671} +{"Pretrain/Learning Rate": 7.9839788856924e-06, "Pretrain/Loss": 2.0344436168670654, "Pretrain/Loss (Raw)": 2.097810983657837, "Pretrain/Step": 7116, "Pretrain/Step Time": 8.794054217636585} +{"Pretrain/Learning Rate": 7.977760039456313e-06, "Pretrain/Loss": 2.034053325653076, "Pretrain/Loss (Raw)": 1.8699798583984375, "Pretrain/Step": 7117, "Pretrain/Step Time": 8.798309572041035} +{"Pretrain/Learning Rate": 7.97154315630515e-06, "Pretrain/Loss": 2.0336391925811768, "Pretrain/Loss (Raw)": 2.003476858139038, "Pretrain/Step": 7118, "Pretrain/Step Time": 8.790522329509258} +{"Pretrain/Learning Rate": 7.965328236955862e-06, "Pretrain/Loss": 2.0331883430480957, "Pretrain/Loss (Raw)": 2.009999990463257, "Pretrain/Step": 7119, "Pretrain/Step Time": 8.794719211757183} +{"Pretrain/Learning Rate": 7.959115282125198e-06, "Pretrain/Loss": 2.0356686115264893, "Pretrain/Loss (Raw)": 2.1239094734191895, "Pretrain/Step": 7120, "Pretrain/Step Time": 8.793061815202236} +{"Pretrain/Learning Rate": 7.952904292529661e-06, "Pretrain/Loss": 2.0353708267211914, "Pretrain/Loss (Raw)": 2.0505011081695557, "Pretrain/Step": 7121, "Pretrain/Step Time": 8.791484370827675} +{"Pretrain/Learning Rate": 7.946695268885531e-06, "Pretrain/Loss": 2.0356578826904297, "Pretrain/Loss (Raw)": 2.0579278469085693, "Pretrain/Step": 7122, "Pretrain/Step Time": 8.789230953902006} +{"Pretrain/Learning Rate": 7.94048821190885e-06, "Pretrain/Loss": 2.0379600524902344, "Pretrain/Loss (Raw)": 2.2257208824157715, "Pretrain/Step": 7123, "Pretrain/Step Time": 8.794421112164855} +{"Pretrain/Learning Rate": 7.934283122315464e-06, "Pretrain/Loss": 2.0381274223327637, "Pretrain/Loss (Raw)": 2.1072654724121094, "Pretrain/Step": 7124, "Pretrain/Step Time": 8.792176822200418} +{"Pretrain/Learning Rate": 7.928080000820968e-06, "Pretrain/Loss": 2.03715443611145, "Pretrain/Loss (Raw)": 1.8815151453018188, "Pretrain/Step": 7125, "Pretrain/Step Time": 8.796794535592198} +{"Pretrain/Learning Rate": 7.921878848140727e-06, "Pretrain/Loss": 2.037182569503784, "Pretrain/Loss (Raw)": 2.0483758449554443, "Pretrain/Step": 7126, "Pretrain/Step Time": 8.795631941407919} +{"Pretrain/Learning Rate": 7.915679664989887e-06, "Pretrain/Loss": 2.036985158920288, "Pretrain/Loss (Raw)": 2.103818893432617, "Pretrain/Step": 7127, "Pretrain/Step Time": 8.792741596698761} +{"Pretrain/Learning Rate": 7.909482452083378e-06, "Pretrain/Loss": 2.0370516777038574, "Pretrain/Loss (Raw)": 2.066110849380493, "Pretrain/Step": 7128, "Pretrain/Step Time": 8.797959135845304} +{"Pretrain/Learning Rate": 7.903287210135888e-06, "Pretrain/Loss": 2.0355334281921387, "Pretrain/Loss (Raw)": 1.9245051145553589, "Pretrain/Step": 7129, "Pretrain/Step Time": 8.796174483373761} +{"Pretrain/Learning Rate": 7.897093939861877e-06, "Pretrain/Loss": 2.0351972579956055, "Pretrain/Loss (Raw)": 1.9580910205841064, "Pretrain/Step": 7130, "Pretrain/Step Time": 8.775348147377372} +{"Pretrain/Learning Rate": 7.890902641975576e-06, "Pretrain/Loss": 2.033841371536255, "Pretrain/Loss (Raw)": 1.924080729484558, "Pretrain/Step": 7131, "Pretrain/Step Time": 8.775494115427136} +{"Pretrain/Learning Rate": 7.884713317191011e-06, "Pretrain/Loss": 2.0359103679656982, "Pretrain/Loss (Raw)": 2.156331777572632, "Pretrain/Step": 7132, "Pretrain/Step Time": 8.772996664047241} +{"Pretrain/Learning Rate": 7.878525966221958e-06, "Pretrain/Loss": 2.0362467765808105, "Pretrain/Loss (Raw)": 2.072899341583252, "Pretrain/Step": 7133, "Pretrain/Step Time": 8.778716087341309} +{"Pretrain/Learning Rate": 7.87234058978197e-06, "Pretrain/Loss": 2.0362370014190674, "Pretrain/Loss (Raw)": 2.0777223110198975, "Pretrain/Step": 7134, "Pretrain/Step Time": 8.779158724471927} +{"Pretrain/Learning Rate": 7.866157188584364e-06, "Pretrain/Loss": 2.0350942611694336, "Pretrain/Loss (Raw)": 1.8567100763320923, "Pretrain/Step": 7135, "Pretrain/Step Time": 8.78001818433404} +{"Pretrain/Learning Rate": 7.859975763342264e-06, "Pretrain/Loss": 2.033586263656616, "Pretrain/Loss (Raw)": 1.8838969469070435, "Pretrain/Step": 7136, "Pretrain/Step Time": 8.777280384674668} +{"Pretrain/Learning Rate": 7.85379631476851e-06, "Pretrain/Loss": 2.0348265171051025, "Pretrain/Loss (Raw)": 2.176473617553711, "Pretrain/Step": 7137, "Pretrain/Step Time": 8.789793737232685} +{"Pretrain/Learning Rate": 7.847618843575769e-06, "Pretrain/Loss": 2.0361523628234863, "Pretrain/Loss (Raw)": 2.060213088989258, "Pretrain/Step": 7138, "Pretrain/Step Time": 8.784883147105575} +{"Pretrain/Learning Rate": 7.84144335047644e-06, "Pretrain/Loss": 2.0354814529418945, "Pretrain/Loss (Raw)": 1.9803252220153809, "Pretrain/Step": 7139, "Pretrain/Step Time": 8.78771549090743} +{"Pretrain/Learning Rate": 7.835269836182733e-06, "Pretrain/Loss": 2.0360875129699707, "Pretrain/Loss (Raw)": 2.085176706314087, "Pretrain/Step": 7140, "Pretrain/Step Time": 8.799667967483401} +{"Pretrain/Learning Rate": 7.829098301406576e-06, "Pretrain/Loss": 2.0363550186157227, "Pretrain/Loss (Raw)": 1.9713419675827026, "Pretrain/Step": 7141, "Pretrain/Step Time": 8.798264717683196} +{"Pretrain/Learning Rate": 7.82292874685972e-06, "Pretrain/Loss": 2.0328235626220703, "Pretrain/Loss (Raw)": 1.8134781122207642, "Pretrain/Step": 7142, "Pretrain/Step Time": 8.796534890308976} +{"Pretrain/Learning Rate": 7.816761173253665e-06, "Pretrain/Loss": 2.032006025314331, "Pretrain/Loss (Raw)": 2.0282554626464844, "Pretrain/Step": 7143, "Pretrain/Step Time": 8.803394485265017} +{"Pretrain/Learning Rate": 7.810595581299681e-06, "Pretrain/Loss": 2.029946804046631, "Pretrain/Loss (Raw)": 2.042734146118164, "Pretrain/Step": 7144, "Pretrain/Step Time": 8.803829552605748} +{"Pretrain/Learning Rate": 7.804431971708807e-06, "Pretrain/Loss": 2.0325207710266113, "Pretrain/Loss (Raw)": 2.2144277095794678, "Pretrain/Step": 7145, "Pretrain/Step Time": 8.788705360144377} +{"Pretrain/Learning Rate": 7.798270345191871e-06, "Pretrain/Loss": 2.0332155227661133, "Pretrain/Loss (Raw)": 2.1165313720703125, "Pretrain/Step": 7146, "Pretrain/Step Time": 8.790138486772776} +{"Pretrain/Learning Rate": 7.792110702459456e-06, "Pretrain/Loss": 2.033161163330078, "Pretrain/Loss (Raw)": 2.096545457839966, "Pretrain/Step": 7147, "Pretrain/Step Time": 8.785893350839615} +{"Pretrain/Learning Rate": 7.785953044221924e-06, "Pretrain/Loss": 2.0319788455963135, "Pretrain/Loss (Raw)": 1.7891818284988403, "Pretrain/Step": 7148, "Pretrain/Step Time": 8.785901689901948} +{"Pretrain/Learning Rate": 7.779797371189394e-06, "Pretrain/Loss": 2.032938003540039, "Pretrain/Loss (Raw)": 2.1575825214385986, "Pretrain/Step": 7149, "Pretrain/Step Time": 8.784863043576479} +{"Pretrain/Learning Rate": 7.77364368407178e-06, "Pretrain/Loss": 2.034468173980713, "Pretrain/Loss (Raw)": 2.272806406021118, "Pretrain/Step": 7150, "Pretrain/Step Time": 8.786490699276328} +{"Pretrain/Learning Rate": 7.767491983578751e-06, "Pretrain/Loss": 2.0341758728027344, "Pretrain/Loss (Raw)": 2.1829144954681396, "Pretrain/Step": 7151, "Pretrain/Step Time": 8.791967647150159} +{"Pretrain/Learning Rate": 7.76134227041975e-06, "Pretrain/Loss": 2.0357511043548584, "Pretrain/Loss (Raw)": 2.099778652191162, "Pretrain/Step": 7152, "Pretrain/Step Time": 8.788663214072585} +{"Pretrain/Learning Rate": 7.755194545303982e-06, "Pretrain/Loss": 2.034761428833008, "Pretrain/Loss (Raw)": 1.9853897094726562, "Pretrain/Step": 7153, "Pretrain/Step Time": 8.79294516518712} +{"Pretrain/Learning Rate": 7.749048808940445e-06, "Pretrain/Loss": 2.034546375274658, "Pretrain/Loss (Raw)": 2.019641160964966, "Pretrain/Step": 7154, "Pretrain/Step Time": 8.78923113271594} +{"Pretrain/Learning Rate": 7.742905062037891e-06, "Pretrain/Loss": 2.032587766647339, "Pretrain/Loss (Raw)": 1.7652761936187744, "Pretrain/Step": 7155, "Pretrain/Step Time": 8.802067171782255} +{"Pretrain/Learning Rate": 7.736763305304834e-06, "Pretrain/Loss": 2.0336265563964844, "Pretrain/Loss (Raw)": 2.2588000297546387, "Pretrain/Step": 7156, "Pretrain/Step Time": 8.801531234756112} +{"Pretrain/Learning Rate": 7.730623539449588e-06, "Pretrain/Loss": 2.0332674980163574, "Pretrain/Loss (Raw)": 1.9718036651611328, "Pretrain/Step": 7157, "Pretrain/Step Time": 8.802553474903107} +{"Pretrain/Learning Rate": 7.724485765180212e-06, "Pretrain/Loss": 2.032101631164551, "Pretrain/Loss (Raw)": 2.1756272315979004, "Pretrain/Step": 7158, "Pretrain/Step Time": 8.796753093600273} +{"Pretrain/Learning Rate": 7.71834998320454e-06, "Pretrain/Loss": 2.0314431190490723, "Pretrain/Loss (Raw)": 1.859912633895874, "Pretrain/Step": 7159, "Pretrain/Step Time": 8.794958535581827} +{"Pretrain/Learning Rate": 7.712216194230177e-06, "Pretrain/Loss": 2.031482696533203, "Pretrain/Loss (Raw)": 2.1110215187072754, "Pretrain/Step": 7160, "Pretrain/Step Time": 8.794848553836346} +{"Pretrain/Learning Rate": 7.70608439896451e-06, "Pretrain/Loss": 2.031949758529663, "Pretrain/Loss (Raw)": 2.0432610511779785, "Pretrain/Step": 7161, "Pretrain/Step Time": 8.79675835557282} +{"Pretrain/Learning Rate": 7.699954598114684e-06, "Pretrain/Loss": 2.0311880111694336, "Pretrain/Loss (Raw)": 1.9473154544830322, "Pretrain/Step": 7162, "Pretrain/Step Time": 8.79156837798655} +{"Pretrain/Learning Rate": 7.693826792387613e-06, "Pretrain/Loss": 2.0313405990600586, "Pretrain/Loss (Raw)": 1.9748986959457397, "Pretrain/Step": 7163, "Pretrain/Step Time": 8.79327261634171} +{"Pretrain/Learning Rate": 7.68770098248998e-06, "Pretrain/Loss": 2.0310616493225098, "Pretrain/Loss (Raw)": 1.9791451692581177, "Pretrain/Step": 7164, "Pretrain/Step Time": 8.792969338595867} +{"Pretrain/Learning Rate": 7.681577169128251e-06, "Pretrain/Loss": 2.030017852783203, "Pretrain/Loss (Raw)": 2.000037908554077, "Pretrain/Step": 7165, "Pretrain/Step Time": 8.78921371139586} +{"Pretrain/Learning Rate": 7.675455353008653e-06, "Pretrain/Loss": 2.029996395111084, "Pretrain/Loss (Raw)": 2.047436475753784, "Pretrain/Step": 7166, "Pretrain/Step Time": 8.79876733571291} +{"Pretrain/Learning Rate": 7.669335534837183e-06, "Pretrain/Loss": 2.0294241905212402, "Pretrain/Loss (Raw)": 2.021430492401123, "Pretrain/Step": 7167, "Pretrain/Step Time": 8.79940391331911} +{"Pretrain/Learning Rate": 7.66321771531959e-06, "Pretrain/Loss": 2.0305986404418945, "Pretrain/Loss (Raw)": 1.9464761018753052, "Pretrain/Step": 7168, "Pretrain/Step Time": 8.795351607725024} +{"Pretrain/Learning Rate": 7.657101895161437e-06, "Pretrain/Loss": 2.0308921337127686, "Pretrain/Loss (Raw)": 2.0780303478240967, "Pretrain/Step": 7169, "Pretrain/Step Time": 8.800627697259188} +{"Pretrain/Learning Rate": 7.650988075068011e-06, "Pretrain/Loss": 2.0302977561950684, "Pretrain/Loss (Raw)": 2.0454351902008057, "Pretrain/Step": 7170, "Pretrain/Step Time": 8.799478340893984} +{"Pretrain/Learning Rate": 7.644876255744393e-06, "Pretrain/Loss": 2.030137062072754, "Pretrain/Loss (Raw)": 1.9386199712753296, "Pretrain/Step": 7171, "Pretrain/Step Time": 8.801576128229499} +{"Pretrain/Learning Rate": 7.63876643789542e-06, "Pretrain/Loss": 2.0298314094543457, "Pretrain/Loss (Raw)": 2.1501290798187256, "Pretrain/Step": 7172, "Pretrain/Step Time": 8.808150907978415} +{"Pretrain/Learning Rate": 7.632658622225713e-06, "Pretrain/Loss": 2.0277774333953857, "Pretrain/Loss (Raw)": 1.9500819444656372, "Pretrain/Step": 7173, "Pretrain/Step Time": 8.806223826482892} +{"Pretrain/Learning Rate": 7.626552809439655e-06, "Pretrain/Loss": 2.02874493598938, "Pretrain/Loss (Raw)": 2.031010627746582, "Pretrain/Step": 7174, "Pretrain/Step Time": 8.807228395715356} +{"Pretrain/Learning Rate": 7.620449000241395e-06, "Pretrain/Loss": 2.0279674530029297, "Pretrain/Loss (Raw)": 2.0405285358428955, "Pretrain/Step": 7175, "Pretrain/Step Time": 8.810350447893143} +{"Pretrain/Learning Rate": 7.614347195334839e-06, "Pretrain/Loss": 2.0280141830444336, "Pretrain/Loss (Raw)": 2.0545339584350586, "Pretrain/Step": 7176, "Pretrain/Step Time": 8.812077959999442} +{"Pretrain/Learning Rate": 7.6082473954237066e-06, "Pretrain/Loss": 2.029153823852539, "Pretrain/Loss (Raw)": 2.0275461673736572, "Pretrain/Step": 7177, "Pretrain/Step Time": 8.809558391571045} +{"Pretrain/Learning Rate": 7.602149601211422e-06, "Pretrain/Loss": 2.030327320098877, "Pretrain/Loss (Raw)": 2.10091495513916, "Pretrain/Step": 7178, "Pretrain/Step Time": 8.8117716871202} +{"Pretrain/Learning Rate": 7.596053813401233e-06, "Pretrain/Loss": 2.0316076278686523, "Pretrain/Loss (Raw)": 2.1113016605377197, "Pretrain/Step": 7179, "Pretrain/Step Time": 8.816686939448118} +{"Pretrain/Learning Rate": 7.589960032696122e-06, "Pretrain/Loss": 2.0302984714508057, "Pretrain/Loss (Raw)": 1.9861626625061035, "Pretrain/Step": 7180, "Pretrain/Step Time": 8.810984214767814} +{"Pretrain/Learning Rate": 7.583868259798874e-06, "Pretrain/Loss": 2.0311262607574463, "Pretrain/Loss (Raw)": 2.1308796405792236, "Pretrain/Step": 7181, "Pretrain/Step Time": 8.81023628078401} +{"Pretrain/Learning Rate": 7.5777784954119885e-06, "Pretrain/Loss": 2.0330281257629395, "Pretrain/Loss (Raw)": 2.1369435787200928, "Pretrain/Step": 7182, "Pretrain/Step Time": 8.806087365373969} +{"Pretrain/Learning Rate": 7.5716907402377915e-06, "Pretrain/Loss": 2.0319952964782715, "Pretrain/Loss (Raw)": 2.0382707118988037, "Pretrain/Step": 7183, "Pretrain/Step Time": 8.806294849142432} +{"Pretrain/Learning Rate": 7.565604994978337e-06, "Pretrain/Loss": 2.0341711044311523, "Pretrain/Loss (Raw)": 2.1736929416656494, "Pretrain/Step": 7184, "Pretrain/Step Time": 8.80809841118753} +{"Pretrain/Learning Rate": 7.559521260335483e-06, "Pretrain/Loss": 2.0330698490142822, "Pretrain/Loss (Raw)": 1.9806158542633057, "Pretrain/Step": 7185, "Pretrain/Step Time": 8.809639617800713} +{"Pretrain/Learning Rate": 7.553439537010803e-06, "Pretrain/Loss": 2.0370025634765625, "Pretrain/Loss (Raw)": 2.3425204753875732, "Pretrain/Step": 7186, "Pretrain/Step Time": 8.808664079755545} +{"Pretrain/Learning Rate": 7.547359825705696e-06, "Pretrain/Loss": 2.0386903285980225, "Pretrain/Loss (Raw)": 2.1110758781433105, "Pretrain/Step": 7187, "Pretrain/Step Time": 8.81789612956345} +{"Pretrain/Learning Rate": 7.541282127121291e-06, "Pretrain/Loss": 2.038724184036255, "Pretrain/Loss (Raw)": 1.9838569164276123, "Pretrain/Step": 7188, "Pretrain/Step Time": 8.808273181319237} +{"Pretrain/Learning Rate": 7.5352064419585e-06, "Pretrain/Loss": 2.0386154651641846, "Pretrain/Loss (Raw)": 2.043379306793213, "Pretrain/Step": 7189, "Pretrain/Step Time": 8.808962121605873} +{"Pretrain/Learning Rate": 7.529132770917993e-06, "Pretrain/Loss": 2.040745258331299, "Pretrain/Loss (Raw)": 2.2276670932769775, "Pretrain/Step": 7190, "Pretrain/Step Time": 8.805498333647847} +{"Pretrain/Learning Rate": 7.523061114700228e-06, "Pretrain/Loss": 2.040846586227417, "Pretrain/Loss (Raw)": 2.0541844367980957, "Pretrain/Step": 7191, "Pretrain/Step Time": 8.805669628083706} +{"Pretrain/Learning Rate": 7.516991474005408e-06, "Pretrain/Loss": 2.0421295166015625, "Pretrain/Loss (Raw)": 2.094855785369873, "Pretrain/Step": 7192, "Pretrain/Step Time": 8.803215583786368} +{"Pretrain/Learning Rate": 7.510923849533513e-06, "Pretrain/Loss": 2.0405197143554688, "Pretrain/Loss (Raw)": 2.1791329383850098, "Pretrain/Step": 7193, "Pretrain/Step Time": 8.810564974322915} +{"Pretrain/Learning Rate": 7.504858241984286e-06, "Pretrain/Loss": 2.0412912368774414, "Pretrain/Loss (Raw)": 2.2205142974853516, "Pretrain/Step": 7194, "Pretrain/Step Time": 8.79700810648501} +{"Pretrain/Learning Rate": 7.498794652057251e-06, "Pretrain/Loss": 2.0397653579711914, "Pretrain/Loss (Raw)": 2.092372417449951, "Pretrain/Step": 7195, "Pretrain/Step Time": 8.801736693829298} +{"Pretrain/Learning Rate": 7.492733080451686e-06, "Pretrain/Loss": 2.0402278900146484, "Pretrain/Loss (Raw)": 2.0295333862304688, "Pretrain/Step": 7196, "Pretrain/Step Time": 8.796773698180914} +{"Pretrain/Learning Rate": 7.486673527866633e-06, "Pretrain/Loss": 2.04154372215271, "Pretrain/Loss (Raw)": 2.209994077682495, "Pretrain/Step": 7197, "Pretrain/Step Time": 8.80589685216546} +{"Pretrain/Learning Rate": 7.4806159950009196e-06, "Pretrain/Loss": 2.038318395614624, "Pretrain/Loss (Raw)": 1.9382803440093994, "Pretrain/Step": 7198, "Pretrain/Step Time": 8.8071060013026} +{"Pretrain/Learning Rate": 7.474560482553125e-06, "Pretrain/Loss": 2.0391898155212402, "Pretrain/Loss (Raw)": 2.077993869781494, "Pretrain/Step": 7199, "Pretrain/Step Time": 8.804348161444068} +{"Pretrain/Learning Rate": 7.468506991221599e-06, "Pretrain/Loss": 2.0405592918395996, "Pretrain/Loss (Raw)": 2.2552554607391357, "Pretrain/Step": 7200, "Pretrain/Step Time": 8.806738771498203} +{"Pretrain/Learning Rate": 7.462455521704448e-06, "Pretrain/Loss": 2.0403549671173096, "Pretrain/Loss (Raw)": 1.875269889831543, "Pretrain/Step": 7201, "Pretrain/Step Time": 8.80755260400474} +{"Pretrain/Learning Rate": 7.4564060746995765e-06, "Pretrain/Loss": 2.038783311843872, "Pretrain/Loss (Raw)": 1.761154294013977, "Pretrain/Step": 7202, "Pretrain/Step Time": 8.805716846138239} +{"Pretrain/Learning Rate": 7.450358650904621e-06, "Pretrain/Loss": 2.0395278930664062, "Pretrain/Loss (Raw)": 2.1885621547698975, "Pretrain/Step": 7203, "Pretrain/Step Time": 8.804025003686547} +{"Pretrain/Learning Rate": 7.444313251017004e-06, "Pretrain/Loss": 2.0389585494995117, "Pretrain/Loss (Raw)": 2.0283591747283936, "Pretrain/Step": 7204, "Pretrain/Step Time": 8.799734339118004} +{"Pretrain/Learning Rate": 7.438269875733903e-06, "Pretrain/Loss": 2.0400309562683105, "Pretrain/Loss (Raw)": 1.9717884063720703, "Pretrain/Step": 7205, "Pretrain/Step Time": 8.798577778041363} +{"Pretrain/Learning Rate": 7.432228525752277e-06, "Pretrain/Loss": 2.0396552085876465, "Pretrain/Loss (Raw)": 1.990445613861084, "Pretrain/Step": 7206, "Pretrain/Step Time": 8.800159901380539} +{"Pretrain/Learning Rate": 7.426189201768844e-06, "Pretrain/Loss": 2.0401904582977295, "Pretrain/Loss (Raw)": 2.061952829360962, "Pretrain/Step": 7207, "Pretrain/Step Time": 8.796170715242624} +{"Pretrain/Learning Rate": 7.42015190448008e-06, "Pretrain/Loss": 2.0421841144561768, "Pretrain/Loss (Raw)": 2.0470848083496094, "Pretrain/Step": 7208, "Pretrain/Step Time": 8.797119500115514} +{"Pretrain/Learning Rate": 7.4141166345822274e-06, "Pretrain/Loss": 2.039146661758423, "Pretrain/Loss (Raw)": 2.078123092651367, "Pretrain/Step": 7209, "Pretrain/Step Time": 8.795702526345849} +{"Pretrain/Learning Rate": 7.408083392771323e-06, "Pretrain/Loss": 2.0387327671051025, "Pretrain/Loss (Raw)": 2.0634765625, "Pretrain/Step": 7210, "Pretrain/Step Time": 8.795915015041828} +{"Pretrain/Learning Rate": 7.402052179743135e-06, "Pretrain/Loss": 2.0393877029418945, "Pretrain/Loss (Raw)": 2.039505958557129, "Pretrain/Step": 7211, "Pretrain/Step Time": 8.793175622820854} +{"Pretrain/Learning Rate": 7.396022996193217e-06, "Pretrain/Loss": 2.039233684539795, "Pretrain/Loss (Raw)": 2.0741477012634277, "Pretrain/Step": 7212, "Pretrain/Step Time": 8.790788352489471} +{"Pretrain/Learning Rate": 7.389995842816871e-06, "Pretrain/Loss": 2.038125514984131, "Pretrain/Loss (Raw)": 1.9918255805969238, "Pretrain/Step": 7213, "Pretrain/Step Time": 8.789121517911553} +{"Pretrain/Learning Rate": 7.383970720309191e-06, "Pretrain/Loss": 2.0373759269714355, "Pretrain/Loss (Raw)": 2.035071849822998, "Pretrain/Step": 7214, "Pretrain/Step Time": 8.788696670904756} +{"Pretrain/Learning Rate": 7.37794762936502e-06, "Pretrain/Loss": 2.036513328552246, "Pretrain/Loss (Raw)": 1.9527525901794434, "Pretrain/Step": 7215, "Pretrain/Step Time": 8.795974815264344} +{"Pretrain/Learning Rate": 7.371926570678964e-06, "Pretrain/Loss": 2.034813165664673, "Pretrain/Loss (Raw)": 1.7521839141845703, "Pretrain/Step": 7216, "Pretrain/Step Time": 8.78942246362567} +{"Pretrain/Learning Rate": 7.365907544945397e-06, "Pretrain/Loss": 2.0346732139587402, "Pretrain/Loss (Raw)": 2.052321434020996, "Pretrain/Step": 7217, "Pretrain/Step Time": 8.795156147331} +{"Pretrain/Learning Rate": 7.359890552858478e-06, "Pretrain/Loss": 2.034691333770752, "Pretrain/Loss (Raw)": 2.098959445953369, "Pretrain/Step": 7218, "Pretrain/Step Time": 8.790083011612296} +{"Pretrain/Learning Rate": 7.353875595112092e-06, "Pretrain/Loss": 2.0343575477600098, "Pretrain/Loss (Raw)": 1.9976228475570679, "Pretrain/Step": 7219, "Pretrain/Step Time": 8.789917580783367} +{"Pretrain/Learning Rate": 7.347862672399927e-06, "Pretrain/Loss": 2.0325052738189697, "Pretrain/Loss (Raw)": 1.858835220336914, "Pretrain/Step": 7220, "Pretrain/Step Time": 8.792649827897549} +{"Pretrain/Learning Rate": 7.341851785415415e-06, "Pretrain/Loss": 2.032961130142212, "Pretrain/Loss (Raw)": 2.006225347518921, "Pretrain/Step": 7221, "Pretrain/Step Time": 8.790175165981054} +{"Pretrain/Learning Rate": 7.335842934851775e-06, "Pretrain/Loss": 2.033557176589966, "Pretrain/Loss (Raw)": 1.983344554901123, "Pretrain/Step": 7222, "Pretrain/Step Time": 8.793378407135606} +{"Pretrain/Learning Rate": 7.329836121401951e-06, "Pretrain/Loss": 2.034716844558716, "Pretrain/Loss (Raw)": 2.0099496841430664, "Pretrain/Step": 7223, "Pretrain/Step Time": 8.784034624695778} +{"Pretrain/Learning Rate": 7.323831345758697e-06, "Pretrain/Loss": 2.0337562561035156, "Pretrain/Loss (Raw)": 1.929361343383789, "Pretrain/Step": 7224, "Pretrain/Step Time": 8.787872372195125} +{"Pretrain/Learning Rate": 7.317828608614496e-06, "Pretrain/Loss": 2.035174608230591, "Pretrain/Loss (Raw)": 2.1493823528289795, "Pretrain/Step": 7225, "Pretrain/Step Time": 8.78917028941214} +{"Pretrain/Learning Rate": 7.311827910661639e-06, "Pretrain/Loss": 2.0369791984558105, "Pretrain/Loss (Raw)": 2.23394775390625, "Pretrain/Step": 7226, "Pretrain/Step Time": 8.79357635974884} +{"Pretrain/Learning Rate": 7.3058292525921195e-06, "Pretrain/Loss": 2.036562442779541, "Pretrain/Loss (Raw)": 2.097986936569214, "Pretrain/Step": 7227, "Pretrain/Step Time": 8.795694706961513} +{"Pretrain/Learning Rate": 7.299832635097756e-06, "Pretrain/Loss": 2.036128044128418, "Pretrain/Loss (Raw)": 1.8828943967819214, "Pretrain/Step": 7228, "Pretrain/Step Time": 8.794547004625201} +{"Pretrain/Learning Rate": 7.293838058870098e-06, "Pretrain/Loss": 2.0364999771118164, "Pretrain/Loss (Raw)": 1.8132047653198242, "Pretrain/Step": 7229, "Pretrain/Step Time": 8.799997655674815} +{"Pretrain/Learning Rate": 7.2878455246004704e-06, "Pretrain/Loss": 2.037529945373535, "Pretrain/Loss (Raw)": 1.9162569046020508, "Pretrain/Step": 7230, "Pretrain/Step Time": 8.790927125141025} +{"Pretrain/Learning Rate": 7.281855032979954e-06, "Pretrain/Loss": 2.0367825031280518, "Pretrain/Loss (Raw)": 2.121108055114746, "Pretrain/Step": 7231, "Pretrain/Step Time": 8.793057888746262} +{"Pretrain/Learning Rate": 7.275866584699409e-06, "Pretrain/Loss": 2.0368778705596924, "Pretrain/Loss (Raw)": 2.0012645721435547, "Pretrain/Step": 7232, "Pretrain/Step Time": 8.790942991152406} +{"Pretrain/Learning Rate": 7.269880180449451e-06, "Pretrain/Loss": 2.040070056915283, "Pretrain/Loss (Raw)": 1.9167102575302124, "Pretrain/Step": 7233, "Pretrain/Step Time": 8.789613395929337} +{"Pretrain/Learning Rate": 7.263895820920458e-06, "Pretrain/Loss": 2.039276599884033, "Pretrain/Loss (Raw)": 2.104945182800293, "Pretrain/Step": 7234, "Pretrain/Step Time": 8.789502965286374} +{"Pretrain/Learning Rate": 7.257913506802566e-06, "Pretrain/Loss": 2.03940486907959, "Pretrain/Loss (Raw)": 2.096675395965576, "Pretrain/Step": 7235, "Pretrain/Step Time": 8.791776146739721} +{"Pretrain/Learning Rate": 7.251933238785699e-06, "Pretrain/Loss": 2.0368430614471436, "Pretrain/Loss (Raw)": 1.9873378276824951, "Pretrain/Step": 7236, "Pretrain/Step Time": 8.795528877526522} +{"Pretrain/Learning Rate": 7.245955017559522e-06, "Pretrain/Loss": 2.03717041015625, "Pretrain/Loss (Raw)": 1.9758492708206177, "Pretrain/Step": 7237, "Pretrain/Step Time": 8.790114674717188} +{"Pretrain/Learning Rate": 7.2399788438134665e-06, "Pretrain/Loss": 2.037060260772705, "Pretrain/Loss (Raw)": 1.964613437652588, "Pretrain/Step": 7238, "Pretrain/Step Time": 8.791782729327679} +{"Pretrain/Learning Rate": 7.234004718236745e-06, "Pretrain/Loss": 2.037337303161621, "Pretrain/Loss (Raw)": 2.099821090698242, "Pretrain/Step": 7239, "Pretrain/Step Time": 8.792411601170897} +{"Pretrain/Learning Rate": 7.228032641518315e-06, "Pretrain/Loss": 2.038818836212158, "Pretrain/Loss (Raw)": 2.1067519187927246, "Pretrain/Step": 7240, "Pretrain/Step Time": 8.788671573624015} +{"Pretrain/Learning Rate": 7.222062614346906e-06, "Pretrain/Loss": 2.0370724201202393, "Pretrain/Loss (Raw)": 1.9108558893203735, "Pretrain/Step": 7241, "Pretrain/Step Time": 8.791619416326284} +{"Pretrain/Learning Rate": 7.216094637411e-06, "Pretrain/Loss": 2.037497043609619, "Pretrain/Loss (Raw)": 2.0781307220458984, "Pretrain/Step": 7242, "Pretrain/Step Time": 8.789514426141977} +{"Pretrain/Learning Rate": 7.21012871139887e-06, "Pretrain/Loss": 2.038926839828491, "Pretrain/Loss (Raw)": 2.145371198654175, "Pretrain/Step": 7243, "Pretrain/Step Time": 8.7918038982898} +{"Pretrain/Learning Rate": 7.204164836998523e-06, "Pretrain/Loss": 2.038388967514038, "Pretrain/Loss (Raw)": 2.0289599895477295, "Pretrain/Step": 7244, "Pretrain/Step Time": 8.787226524204016} +{"Pretrain/Learning Rate": 7.1982030148977474e-06, "Pretrain/Loss": 2.041177749633789, "Pretrain/Loss (Raw)": 2.226950168609619, "Pretrain/Step": 7245, "Pretrain/Step Time": 8.783751115202904} +{"Pretrain/Learning Rate": 7.192243245784075e-06, "Pretrain/Loss": 2.0415098667144775, "Pretrain/Loss (Raw)": 2.0459892749786377, "Pretrain/Step": 7246, "Pretrain/Step Time": 8.78927557170391} +{"Pretrain/Learning Rate": 7.186285530344833e-06, "Pretrain/Loss": 2.0408987998962402, "Pretrain/Loss (Raw)": 1.931792974472046, "Pretrain/Step": 7247, "Pretrain/Step Time": 8.781634146347642} +{"Pretrain/Learning Rate": 7.1803298692670825e-06, "Pretrain/Loss": 2.0415236949920654, "Pretrain/Loss (Raw)": 2.203874111175537, "Pretrain/Step": 7248, "Pretrain/Step Time": 8.788947753608227} +{"Pretrain/Learning Rate": 7.174376263237664e-06, "Pretrain/Loss": 2.042111873626709, "Pretrain/Loss (Raw)": 2.125808000564575, "Pretrain/Step": 7249, "Pretrain/Step Time": 8.78714202158153} +{"Pretrain/Learning Rate": 7.1684247129431616e-06, "Pretrain/Loss": 2.0422043800354004, "Pretrain/Loss (Raw)": 2.069770336151123, "Pretrain/Step": 7250, "Pretrain/Step Time": 8.789541825652122} +{"Pretrain/Learning Rate": 7.162475219069956e-06, "Pretrain/Loss": 2.0398108959198, "Pretrain/Loss (Raw)": 1.9193520545959473, "Pretrain/Step": 7251, "Pretrain/Step Time": 8.79193078354001} +{"Pretrain/Learning Rate": 7.1565277823041596e-06, "Pretrain/Loss": 2.038315773010254, "Pretrain/Loss (Raw)": 1.9158554077148438, "Pretrain/Step": 7252, "Pretrain/Step Time": 8.793811190873384} +{"Pretrain/Learning Rate": 7.1505824033316596e-06, "Pretrain/Loss": 2.038024425506592, "Pretrain/Loss (Raw)": 1.8442620038986206, "Pretrain/Step": 7253, "Pretrain/Step Time": 8.79324035719037} +{"Pretrain/Learning Rate": 7.1446390828381e-06, "Pretrain/Loss": 2.0380258560180664, "Pretrain/Loss (Raw)": 2.048530340194702, "Pretrain/Step": 7254, "Pretrain/Step Time": 8.789906086400151} +{"Pretrain/Learning Rate": 7.138697821508908e-06, "Pretrain/Loss": 2.0370068550109863, "Pretrain/Loss (Raw)": 1.9734110832214355, "Pretrain/Step": 7255, "Pretrain/Step Time": 8.7911485619843} +{"Pretrain/Learning Rate": 7.132758620029248e-06, "Pretrain/Loss": 2.0364766120910645, "Pretrain/Loss (Raw)": 1.9982271194458008, "Pretrain/Step": 7256, "Pretrain/Step Time": 8.788307616487145} +{"Pretrain/Learning Rate": 7.126821479084056e-06, "Pretrain/Loss": 2.0373635292053223, "Pretrain/Loss (Raw)": 2.038045644760132, "Pretrain/Step": 7257, "Pretrain/Step Time": 8.791426587849855} +{"Pretrain/Learning Rate": 7.120886399358023e-06, "Pretrain/Loss": 2.0385611057281494, "Pretrain/Loss (Raw)": 2.1113686561584473, "Pretrain/Step": 7258, "Pretrain/Step Time": 8.795535992830992} +{"Pretrain/Learning Rate": 7.114953381535627e-06, "Pretrain/Loss": 2.041609525680542, "Pretrain/Loss (Raw)": 2.31429123878479, "Pretrain/Step": 7259, "Pretrain/Step Time": 8.795660346746445} +{"Pretrain/Learning Rate": 7.109022426301087e-06, "Pretrain/Loss": 2.041050672531128, "Pretrain/Loss (Raw)": 2.0847764015197754, "Pretrain/Step": 7260, "Pretrain/Step Time": 8.800231792032719} +{"Pretrain/Learning Rate": 7.103093534338384e-06, "Pretrain/Loss": 2.0410075187683105, "Pretrain/Loss (Raw)": 2.0673716068267822, "Pretrain/Step": 7261, "Pretrain/Step Time": 8.794083947315812} +{"Pretrain/Learning Rate": 7.0971667063312624e-06, "Pretrain/Loss": 2.039642810821533, "Pretrain/Loss (Raw)": 1.9030581712722778, "Pretrain/Step": 7262, "Pretrain/Step Time": 8.794371591880918} +{"Pretrain/Learning Rate": 7.091241942963251e-06, "Pretrain/Loss": 2.0402541160583496, "Pretrain/Loss (Raw)": 1.934953212738037, "Pretrain/Step": 7263, "Pretrain/Step Time": 8.796158622950315} +{"Pretrain/Learning Rate": 7.0853192449175905e-06, "Pretrain/Loss": 2.0423696041107178, "Pretrain/Loss (Raw)": 2.1546924114227295, "Pretrain/Step": 7264, "Pretrain/Step Time": 8.795023191720247} +{"Pretrain/Learning Rate": 7.0793986128773415e-06, "Pretrain/Loss": 2.0411810874938965, "Pretrain/Loss (Raw)": 2.024338483810425, "Pretrain/Step": 7265, "Pretrain/Step Time": 8.79195049777627} +{"Pretrain/Learning Rate": 7.07348004752528e-06, "Pretrain/Loss": 2.0434787273406982, "Pretrain/Loss (Raw)": 2.3542988300323486, "Pretrain/Step": 7266, "Pretrain/Step Time": 8.79062807559967} +{"Pretrain/Learning Rate": 7.067563549543987e-06, "Pretrain/Loss": 2.0425057411193848, "Pretrain/Loss (Raw)": 1.8557816743850708, "Pretrain/Step": 7267, "Pretrain/Step Time": 8.7934977915138} +{"Pretrain/Learning Rate": 7.061649119615752e-06, "Pretrain/Loss": 2.0410749912261963, "Pretrain/Loss (Raw)": 1.9020336866378784, "Pretrain/Step": 7268, "Pretrain/Step Time": 8.78026138432324} +{"Pretrain/Learning Rate": 7.055736758422676e-06, "Pretrain/Loss": 2.0393080711364746, "Pretrain/Loss (Raw)": 1.7451566457748413, "Pretrain/Step": 7269, "Pretrain/Step Time": 8.781850531697273} +{"Pretrain/Learning Rate": 7.049826466646592e-06, "Pretrain/Loss": 2.0401840209960938, "Pretrain/Loss (Raw)": 1.9256256818771362, "Pretrain/Step": 7270, "Pretrain/Step Time": 8.783795351162553} +{"Pretrain/Learning Rate": 7.043918244969106e-06, "Pretrain/Loss": 2.0414834022521973, "Pretrain/Loss (Raw)": 2.1946020126342773, "Pretrain/Step": 7271, "Pretrain/Step Time": 8.778508797287941} +{"Pretrain/Learning Rate": 7.038012094071572e-06, "Pretrain/Loss": 2.043576955795288, "Pretrain/Loss (Raw)": 2.310676097869873, "Pretrain/Step": 7272, "Pretrain/Step Time": 8.785660004243255} +{"Pretrain/Learning Rate": 7.032108014635128e-06, "Pretrain/Loss": 2.0427353382110596, "Pretrain/Loss (Raw)": 2.106692314147949, "Pretrain/Step": 7273, "Pretrain/Step Time": 8.780148651450872} +{"Pretrain/Learning Rate": 7.026206007340658e-06, "Pretrain/Loss": 2.042283535003662, "Pretrain/Loss (Raw)": 2.058713674545288, "Pretrain/Step": 7274, "Pretrain/Step Time": 8.787273792549968} +{"Pretrain/Learning Rate": 7.020306072868804e-06, "Pretrain/Loss": 2.041600465774536, "Pretrain/Loss (Raw)": 2.00913143157959, "Pretrain/Step": 7275, "Pretrain/Step Time": 8.790759766474366} +{"Pretrain/Learning Rate": 7.014408211899973e-06, "Pretrain/Loss": 2.043048620223999, "Pretrain/Loss (Raw)": 1.9745235443115234, "Pretrain/Step": 7276, "Pretrain/Step Time": 8.787592984735966} +{"Pretrain/Learning Rate": 7.008512425114333e-06, "Pretrain/Loss": 2.0418829917907715, "Pretrain/Loss (Raw)": 2.0083720684051514, "Pretrain/Step": 7277, "Pretrain/Step Time": 8.787559965625405} +{"Pretrain/Learning Rate": 7.002618713191839e-06, "Pretrain/Loss": 2.040208101272583, "Pretrain/Loss (Raw)": 2.058454751968384, "Pretrain/Step": 7278, "Pretrain/Step Time": 8.78414110839367} +{"Pretrain/Learning Rate": 6.996727076812143e-06, "Pretrain/Loss": 2.038677215576172, "Pretrain/Loss (Raw)": 1.9869461059570312, "Pretrain/Step": 7279, "Pretrain/Step Time": 8.783666329458356} +{"Pretrain/Learning Rate": 6.990837516654722e-06, "Pretrain/Loss": 2.0382802486419678, "Pretrain/Loss (Raw)": 2.048980951309204, "Pretrain/Step": 7280, "Pretrain/Step Time": 8.785370571538806} +{"Pretrain/Learning Rate": 6.984950033398782e-06, "Pretrain/Loss": 2.037982225418091, "Pretrain/Loss (Raw)": 1.947219729423523, "Pretrain/Step": 7281, "Pretrain/Step Time": 8.780492635443807} +{"Pretrain/Learning Rate": 6.979064627723292e-06, "Pretrain/Loss": 2.035947322845459, "Pretrain/Loss (Raw)": 1.7591882944107056, "Pretrain/Step": 7282, "Pretrain/Step Time": 8.789001770317554} +{"Pretrain/Learning Rate": 6.97318130030698e-06, "Pretrain/Loss": 2.037724494934082, "Pretrain/Loss (Raw)": 1.992735743522644, "Pretrain/Step": 7283, "Pretrain/Step Time": 8.77968061901629} +{"Pretrain/Learning Rate": 6.967300051828355e-06, "Pretrain/Loss": 2.0363192558288574, "Pretrain/Loss (Raw)": 2.0789389610290527, "Pretrain/Step": 7284, "Pretrain/Step Time": 8.777411652728915} +{"Pretrain/Learning Rate": 6.961420882965661e-06, "Pretrain/Loss": 2.0358028411865234, "Pretrain/Loss (Raw)": 1.9056745767593384, "Pretrain/Step": 7285, "Pretrain/Step Time": 8.780792651697993} +{"Pretrain/Learning Rate": 6.9555437943969095e-06, "Pretrain/Loss": 2.0315566062927246, "Pretrain/Loss (Raw)": 1.63213312625885, "Pretrain/Step": 7286, "Pretrain/Step Time": 8.790079401805997} +{"Pretrain/Learning Rate": 6.949668786799867e-06, "Pretrain/Loss": 2.0320301055908203, "Pretrain/Loss (Raw)": 1.9205126762390137, "Pretrain/Step": 7287, "Pretrain/Step Time": 8.783772848546505} +{"Pretrain/Learning Rate": 6.943795860852087e-06, "Pretrain/Loss": 2.0302553176879883, "Pretrain/Loss (Raw)": 1.8838664293289185, "Pretrain/Step": 7288, "Pretrain/Step Time": 8.785280298441648} +{"Pretrain/Learning Rate": 6.937925017230848e-06, "Pretrain/Loss": 2.030085563659668, "Pretrain/Loss (Raw)": 2.021496057510376, "Pretrain/Step": 7289, "Pretrain/Step Time": 8.787819806486368} +{"Pretrain/Learning Rate": 6.932056256613209e-06, "Pretrain/Loss": 2.030792236328125, "Pretrain/Loss (Raw)": 2.037794589996338, "Pretrain/Step": 7290, "Pretrain/Step Time": 8.789601277559996} +{"Pretrain/Learning Rate": 6.926189579675977e-06, "Pretrain/Loss": 2.0291097164154053, "Pretrain/Loss (Raw)": 1.7595393657684326, "Pretrain/Step": 7291, "Pretrain/Step Time": 8.789356367662549} +{"Pretrain/Learning Rate": 6.920324987095733e-06, "Pretrain/Loss": 2.028900623321533, "Pretrain/Loss (Raw)": 1.9523826837539673, "Pretrain/Step": 7292, "Pretrain/Step Time": 8.788322357460856} +{"Pretrain/Learning Rate": 6.914462479548806e-06, "Pretrain/Loss": 2.029294967651367, "Pretrain/Loss (Raw)": 2.0505309104919434, "Pretrain/Step": 7293, "Pretrain/Step Time": 8.799987897276878} +{"Pretrain/Learning Rate": 6.908602057711289e-06, "Pretrain/Loss": 2.028245687484741, "Pretrain/Loss (Raw)": 1.9131159782409668, "Pretrain/Step": 7294, "Pretrain/Step Time": 8.788840189576149} +{"Pretrain/Learning Rate": 6.902743722259025e-06, "Pretrain/Loss": 2.029092311859131, "Pretrain/Loss (Raw)": 2.1297619342803955, "Pretrain/Step": 7295, "Pretrain/Step Time": 8.787128686904907} +{"Pretrain/Learning Rate": 6.8968874738676385e-06, "Pretrain/Loss": 2.0300447940826416, "Pretrain/Loss (Raw)": 2.0684256553649902, "Pretrain/Step": 7296, "Pretrain/Step Time": 8.786699080839753} +{"Pretrain/Learning Rate": 6.891033313212494e-06, "Pretrain/Loss": 2.0294833183288574, "Pretrain/Loss (Raw)": 2.0061705112457275, "Pretrain/Step": 7297, "Pretrain/Step Time": 8.788353618234396} +{"Pretrain/Learning Rate": 6.885181240968719e-06, "Pretrain/Loss": 2.0313973426818848, "Pretrain/Loss (Raw)": 2.290403366088867, "Pretrain/Step": 7298, "Pretrain/Step Time": 8.790372103452682} +{"Pretrain/Learning Rate": 6.879331257811195e-06, "Pretrain/Loss": 2.0319693088531494, "Pretrain/Loss (Raw)": 2.011855125427246, "Pretrain/Step": 7299, "Pretrain/Step Time": 8.789403451606631} +{"Pretrain/Learning Rate": 6.873483364414588e-06, "Pretrain/Loss": 2.0314292907714844, "Pretrain/Loss (Raw)": 2.080993175506592, "Pretrain/Step": 7300, "Pretrain/Step Time": 8.790476117283106} +{"Pretrain/Learning Rate": 6.867637561453291e-06, "Pretrain/Loss": 2.03224515914917, "Pretrain/Loss (Raw)": 2.054525852203369, "Pretrain/Step": 7301, "Pretrain/Step Time": 8.783236494287848} +{"Pretrain/Learning Rate": 6.861793849601475e-06, "Pretrain/Loss": 2.0333950519561768, "Pretrain/Loss (Raw)": 2.1781980991363525, "Pretrain/Step": 7302, "Pretrain/Step Time": 8.786868795752525} +{"Pretrain/Learning Rate": 6.855952229533055e-06, "Pretrain/Loss": 2.0341243743896484, "Pretrain/Loss (Raw)": 2.133873701095581, "Pretrain/Step": 7303, "Pretrain/Step Time": 8.786247916519642} +{"Pretrain/Learning Rate": 6.8501127019217346e-06, "Pretrain/Loss": 2.0345425605773926, "Pretrain/Loss (Raw)": 2.108071804046631, "Pretrain/Step": 7304, "Pretrain/Step Time": 8.781052943319082} +{"Pretrain/Learning Rate": 6.844275267440931e-06, "Pretrain/Loss": 2.034508228302002, "Pretrain/Loss (Raw)": 2.023160696029663, "Pretrain/Step": 7305, "Pretrain/Step Time": 8.785136112943292} +{"Pretrain/Learning Rate": 6.838439926763859e-06, "Pretrain/Loss": 2.034851312637329, "Pretrain/Loss (Raw)": 2.1448166370391846, "Pretrain/Step": 7306, "Pretrain/Step Time": 8.782677443698049} +{"Pretrain/Learning Rate": 6.832606680563472e-06, "Pretrain/Loss": 2.034785747528076, "Pretrain/Loss (Raw)": 2.10288667678833, "Pretrain/Step": 7307, "Pretrain/Step Time": 8.787744821980596} +{"Pretrain/Learning Rate": 6.8267755295125024e-06, "Pretrain/Loss": 2.0361194610595703, "Pretrain/Loss (Raw)": 2.1569151878356934, "Pretrain/Step": 7308, "Pretrain/Step Time": 8.783466959372163} +{"Pretrain/Learning Rate": 6.820946474283399e-06, "Pretrain/Loss": 2.032386302947998, "Pretrain/Loss (Raw)": 1.6530146598815918, "Pretrain/Step": 7309, "Pretrain/Step Time": 8.787697330117226} +{"Pretrain/Learning Rate": 6.815119515548418e-06, "Pretrain/Loss": 2.0331523418426514, "Pretrain/Loss (Raw)": 2.235015869140625, "Pretrain/Step": 7310, "Pretrain/Step Time": 8.78710880316794} +{"Pretrain/Learning Rate": 6.809294653979545e-06, "Pretrain/Loss": 2.0328569412231445, "Pretrain/Loss (Raw)": 2.0004148483276367, "Pretrain/Step": 7311, "Pretrain/Step Time": 8.786290030926466} +{"Pretrain/Learning Rate": 6.803471890248531e-06, "Pretrain/Loss": 2.031940460205078, "Pretrain/Loss (Raw)": 2.056413173675537, "Pretrain/Step": 7312, "Pretrain/Step Time": 8.785953272134066} +{"Pretrain/Learning Rate": 6.797651225026874e-06, "Pretrain/Loss": 2.033095359802246, "Pretrain/Loss (Raw)": 2.1284401416778564, "Pretrain/Step": 7313, "Pretrain/Step Time": 8.786904150620103} +{"Pretrain/Learning Rate": 6.791832658985859e-06, "Pretrain/Loss": 2.0318617820739746, "Pretrain/Loss (Raw)": 2.18463397026062, "Pretrain/Step": 7314, "Pretrain/Step Time": 8.793068908154964} +{"Pretrain/Learning Rate": 6.786016192796499e-06, "Pretrain/Loss": 2.0321640968322754, "Pretrain/Loss (Raw)": 2.14977765083313, "Pretrain/Step": 7315, "Pretrain/Step Time": 8.782821033149958} +{"Pretrain/Learning Rate": 6.7802018271295815e-06, "Pretrain/Loss": 2.0318007469177246, "Pretrain/Loss (Raw)": 1.9373260736465454, "Pretrain/Step": 7316, "Pretrain/Step Time": 8.785684706643224} +{"Pretrain/Learning Rate": 6.774389562655634e-06, "Pretrain/Loss": 2.031491756439209, "Pretrain/Loss (Raw)": 2.003829002380371, "Pretrain/Step": 7317, "Pretrain/Step Time": 8.782947946339846} +{"Pretrain/Learning Rate": 6.768579400044966e-06, "Pretrain/Loss": 2.0310721397399902, "Pretrain/Loss (Raw)": 2.1739649772644043, "Pretrain/Step": 7318, "Pretrain/Step Time": 8.787291575223207} +{"Pretrain/Learning Rate": 6.762771339967644e-06, "Pretrain/Loss": 2.0299899578094482, "Pretrain/Loss (Raw)": 1.9156476259231567, "Pretrain/Step": 7319, "Pretrain/Step Time": 8.786185186356306} +{"Pretrain/Learning Rate": 6.756965383093455e-06, "Pretrain/Loss": 2.0285136699676514, "Pretrain/Loss (Raw)": 1.9059034585952759, "Pretrain/Step": 7320, "Pretrain/Step Time": 8.785119401291013} +{"Pretrain/Learning Rate": 6.751161530091988e-06, "Pretrain/Loss": 2.0272233486175537, "Pretrain/Loss (Raw)": 2.0139734745025635, "Pretrain/Step": 7321, "Pretrain/Step Time": 8.790870344266295} +{"Pretrain/Learning Rate": 6.745359781632565e-06, "Pretrain/Loss": 2.0267791748046875, "Pretrain/Loss (Raw)": 2.16367769241333, "Pretrain/Step": 7322, "Pretrain/Step Time": 8.792418733239174} +{"Pretrain/Learning Rate": 6.739560138384271e-06, "Pretrain/Loss": 2.026534080505371, "Pretrain/Loss (Raw)": 2.0609779357910156, "Pretrain/Step": 7323, "Pretrain/Step Time": 8.790400644764304} +{"Pretrain/Learning Rate": 6.733762601015942e-06, "Pretrain/Loss": 2.028136730194092, "Pretrain/Loss (Raw)": 2.234691858291626, "Pretrain/Step": 7324, "Pretrain/Step Time": 8.79113712720573} +{"Pretrain/Learning Rate": 6.727967170196186e-06, "Pretrain/Loss": 2.0254993438720703, "Pretrain/Loss (Raw)": 1.8723816871643066, "Pretrain/Step": 7325, "Pretrain/Step Time": 8.784897616133094} +{"Pretrain/Learning Rate": 6.72217384659336e-06, "Pretrain/Loss": 2.027216911315918, "Pretrain/Loss (Raw)": 2.1581387519836426, "Pretrain/Step": 7326, "Pretrain/Step Time": 8.785362284630537} +{"Pretrain/Learning Rate": 6.7163826308755725e-06, "Pretrain/Loss": 2.026954174041748, "Pretrain/Loss (Raw)": 2.0443804264068604, "Pretrain/Step": 7327, "Pretrain/Step Time": 8.78668037801981} +{"Pretrain/Learning Rate": 6.7105935237106895e-06, "Pretrain/Loss": 2.0254197120666504, "Pretrain/Loss (Raw)": 2.0588555335998535, "Pretrain/Step": 7328, "Pretrain/Step Time": 8.786067755892873} +{"Pretrain/Learning Rate": 6.704806525766353e-06, "Pretrain/Loss": 2.026700019836426, "Pretrain/Loss (Raw)": 2.039113998413086, "Pretrain/Step": 7329, "Pretrain/Step Time": 8.787302572280169} +{"Pretrain/Learning Rate": 6.699021637709935e-06, "Pretrain/Loss": 2.0283098220825195, "Pretrain/Loss (Raw)": 1.9672319889068604, "Pretrain/Step": 7330, "Pretrain/Step Time": 8.788070779293776} +{"Pretrain/Learning Rate": 6.693238860208578e-06, "Pretrain/Loss": 2.027383327484131, "Pretrain/Loss (Raw)": 2.069967746734619, "Pretrain/Step": 7331, "Pretrain/Step Time": 8.786865582689643} +{"Pretrain/Learning Rate": 6.687458193929172e-06, "Pretrain/Loss": 2.0284061431884766, "Pretrain/Loss (Raw)": 2.1592860221862793, "Pretrain/Step": 7332, "Pretrain/Step Time": 8.790934992954135} +{"Pretrain/Learning Rate": 6.681679639538388e-06, "Pretrain/Loss": 2.0296437740325928, "Pretrain/Loss (Raw)": 2.1301968097686768, "Pretrain/Step": 7333, "Pretrain/Step Time": 8.789591446518898} +{"Pretrain/Learning Rate": 6.675903197702627e-06, "Pretrain/Loss": 2.031768560409546, "Pretrain/Loss (Raw)": 2.2624247074127197, "Pretrain/Step": 7334, "Pretrain/Step Time": 8.786416124552488} +{"Pretrain/Learning Rate": 6.6701288690880545e-06, "Pretrain/Loss": 2.030998706817627, "Pretrain/Loss (Raw)": 1.9634169340133667, "Pretrain/Step": 7335, "Pretrain/Step Time": 8.794086007401347} +{"Pretrain/Learning Rate": 6.664356654360588e-06, "Pretrain/Loss": 2.030330181121826, "Pretrain/Loss (Raw)": 1.961490511894226, "Pretrain/Step": 7336, "Pretrain/Step Time": 8.790358532220125} +{"Pretrain/Learning Rate": 6.658586554185916e-06, "Pretrain/Loss": 2.031139373779297, "Pretrain/Loss (Raw)": 2.1817123889923096, "Pretrain/Step": 7337, "Pretrain/Step Time": 8.78734871186316} +{"Pretrain/Learning Rate": 6.652818569229474e-06, "Pretrain/Loss": 2.02854585647583, "Pretrain/Loss (Raw)": 1.7315220832824707, "Pretrain/Step": 7338, "Pretrain/Step Time": 8.786344956606627} +{"Pretrain/Learning Rate": 6.647052700156447e-06, "Pretrain/Loss": 2.0286264419555664, "Pretrain/Loss (Raw)": 2.0498335361480713, "Pretrain/Step": 7339, "Pretrain/Step Time": 8.787618225440383} +{"Pretrain/Learning Rate": 6.6412889476317765e-06, "Pretrain/Loss": 2.028402090072632, "Pretrain/Loss (Raw)": 2.0453925132751465, "Pretrain/Step": 7340, "Pretrain/Step Time": 8.784388029947877} +{"Pretrain/Learning Rate": 6.635527312320183e-06, "Pretrain/Loss": 2.0293610095977783, "Pretrain/Loss (Raw)": 2.114569902420044, "Pretrain/Step": 7341, "Pretrain/Step Time": 8.785626282915473} +{"Pretrain/Learning Rate": 6.629767794886116e-06, "Pretrain/Loss": 2.0280470848083496, "Pretrain/Loss (Raw)": 1.8669047355651855, "Pretrain/Step": 7342, "Pretrain/Step Time": 8.79387846402824} +{"Pretrain/Learning Rate": 6.624010395993791e-06, "Pretrain/Loss": 2.0297484397888184, "Pretrain/Loss (Raw)": 2.17049503326416, "Pretrain/Step": 7343, "Pretrain/Step Time": 8.78553120791912} +{"Pretrain/Learning Rate": 6.618255116307171e-06, "Pretrain/Loss": 2.031806468963623, "Pretrain/Loss (Raw)": 2.0156266689300537, "Pretrain/Step": 7344, "Pretrain/Step Time": 8.792614046484232} +{"Pretrain/Learning Rate": 6.61250195649e-06, "Pretrain/Loss": 2.0328173637390137, "Pretrain/Loss (Raw)": 2.18172287940979, "Pretrain/Step": 7345, "Pretrain/Step Time": 8.789761561900377} +{"Pretrain/Learning Rate": 6.606750917205734e-06, "Pretrain/Loss": 2.0307772159576416, "Pretrain/Loss (Raw)": 1.837821125984192, "Pretrain/Step": 7346, "Pretrain/Step Time": 8.786681124940515} +{"Pretrain/Learning Rate": 6.601001999117634e-06, "Pretrain/Loss": 2.031341552734375, "Pretrain/Loss (Raw)": 2.0698723793029785, "Pretrain/Step": 7347, "Pretrain/Step Time": 8.789839370176196} +{"Pretrain/Learning Rate": 6.595255202888672e-06, "Pretrain/Loss": 2.032832145690918, "Pretrain/Loss (Raw)": 2.049633741378784, "Pretrain/Step": 7348, "Pretrain/Step Time": 8.788144439458847} +{"Pretrain/Learning Rate": 6.589510529181622e-06, "Pretrain/Loss": 2.032850503921509, "Pretrain/Loss (Raw)": 2.008563756942749, "Pretrain/Step": 7349, "Pretrain/Step Time": 8.802315633744001} +{"Pretrain/Learning Rate": 6.583767978658959e-06, "Pretrain/Loss": 2.0340185165405273, "Pretrain/Loss (Raw)": 2.132840394973755, "Pretrain/Step": 7350, "Pretrain/Step Time": 8.793893640860915} +{"Pretrain/Learning Rate": 6.578027551982957e-06, "Pretrain/Loss": 2.034040689468384, "Pretrain/Loss (Raw)": 2.0127902030944824, "Pretrain/Step": 7351, "Pretrain/Step Time": 8.793679339811206} +{"Pretrain/Learning Rate": 6.5722892498156165e-06, "Pretrain/Loss": 2.034071683883667, "Pretrain/Loss (Raw)": 1.9333059787750244, "Pretrain/Step": 7352, "Pretrain/Step Time": 8.79598475806415} +{"Pretrain/Learning Rate": 6.566553072818729e-06, "Pretrain/Loss": 2.032320499420166, "Pretrain/Loss (Raw)": 1.9252599477767944, "Pretrain/Step": 7353, "Pretrain/Step Time": 8.794494280591607} +{"Pretrain/Learning Rate": 6.560819021653791e-06, "Pretrain/Loss": 2.031430244445801, "Pretrain/Loss (Raw)": 2.119995355606079, "Pretrain/Step": 7354, "Pretrain/Step Time": 8.789056262001395} +{"Pretrain/Learning Rate": 6.555087096982096e-06, "Pretrain/Loss": 2.0297513008117676, "Pretrain/Loss (Raw)": 1.8830909729003906, "Pretrain/Step": 7355, "Pretrain/Step Time": 8.786412043496966} +{"Pretrain/Learning Rate": 6.549357299464673e-06, "Pretrain/Loss": 2.030975818634033, "Pretrain/Loss (Raw)": 2.0395917892456055, "Pretrain/Step": 7356, "Pretrain/Step Time": 8.794478498399258} +{"Pretrain/Learning Rate": 6.54362962976231e-06, "Pretrain/Loss": 2.0326149463653564, "Pretrain/Loss (Raw)": 2.023045301437378, "Pretrain/Step": 7357, "Pretrain/Step Time": 8.783359076827765} +{"Pretrain/Learning Rate": 6.5379040885355376e-06, "Pretrain/Loss": 2.0328664779663086, "Pretrain/Loss (Raw)": 1.948460578918457, "Pretrain/Step": 7358, "Pretrain/Step Time": 8.785294970497489} +{"Pretrain/Learning Rate": 6.532180676444663e-06, "Pretrain/Loss": 2.0322089195251465, "Pretrain/Loss (Raw)": 2.0369322299957275, "Pretrain/Step": 7359, "Pretrain/Step Time": 8.791279036551714} +{"Pretrain/Learning Rate": 6.52645939414975e-06, "Pretrain/Loss": 2.033039093017578, "Pretrain/Loss (Raw)": 2.107492685317993, "Pretrain/Step": 7360, "Pretrain/Step Time": 8.792450549080968} +{"Pretrain/Learning Rate": 6.5207402423105775e-06, "Pretrain/Loss": 2.0345962047576904, "Pretrain/Loss (Raw)": 2.116046667098999, "Pretrain/Step": 7361, "Pretrain/Step Time": 8.789393339306116} +{"Pretrain/Learning Rate": 6.515023221586722e-06, "Pretrain/Loss": 2.0350301265716553, "Pretrain/Loss (Raw)": 2.160475969314575, "Pretrain/Step": 7362, "Pretrain/Step Time": 8.789345297962427} +{"Pretrain/Learning Rate": 6.5093083326374954e-06, "Pretrain/Loss": 2.035198211669922, "Pretrain/Loss (Raw)": 2.118204355239868, "Pretrain/Step": 7363, "Pretrain/Step Time": 8.79321775957942} +{"Pretrain/Learning Rate": 6.50359557612196e-06, "Pretrain/Loss": 2.0374913215637207, "Pretrain/Loss (Raw)": 2.280852794647217, "Pretrain/Step": 7364, "Pretrain/Step Time": 8.795692536979914} +{"Pretrain/Learning Rate": 6.497884952698935e-06, "Pretrain/Loss": 2.038936138153076, "Pretrain/Loss (Raw)": 2.160778284072876, "Pretrain/Step": 7365, "Pretrain/Step Time": 8.792486084625125} +{"Pretrain/Learning Rate": 6.492176463027009e-06, "Pretrain/Loss": 2.039917469024658, "Pretrain/Loss (Raw)": 2.0902180671691895, "Pretrain/Step": 7366, "Pretrain/Step Time": 8.787392623722553} +{"Pretrain/Learning Rate": 6.486470107764505e-06, "Pretrain/Loss": 2.040170192718506, "Pretrain/Loss (Raw)": 2.1321802139282227, "Pretrain/Step": 7367, "Pretrain/Step Time": 8.792633341625333} +{"Pretrain/Learning Rate": 6.480765887569506e-06, "Pretrain/Loss": 2.040306806564331, "Pretrain/Loss (Raw)": 2.124211072921753, "Pretrain/Step": 7368, "Pretrain/Step Time": 8.790497619658709} +{"Pretrain/Learning Rate": 6.475063803099846e-06, "Pretrain/Loss": 2.0400478839874268, "Pretrain/Loss (Raw)": 1.8777369260787964, "Pretrain/Step": 7369, "Pretrain/Step Time": 8.786823568865657} +{"Pretrain/Learning Rate": 6.469363855013125e-06, "Pretrain/Loss": 2.0390477180480957, "Pretrain/Loss (Raw)": 1.9501124620437622, "Pretrain/Step": 7370, "Pretrain/Step Time": 8.788036938756704} +{"Pretrain/Learning Rate": 6.463666043966685e-06, "Pretrain/Loss": 2.0381906032562256, "Pretrain/Loss (Raw)": 2.0356390476226807, "Pretrain/Step": 7371, "Pretrain/Step Time": 8.797879775986075} +{"Pretrain/Learning Rate": 6.457970370617622e-06, "Pretrain/Loss": 2.038331985473633, "Pretrain/Loss (Raw)": 2.047074794769287, "Pretrain/Step": 7372, "Pretrain/Step Time": 8.796251902356744} +{"Pretrain/Learning Rate": 6.452276835622781e-06, "Pretrain/Loss": 2.037022590637207, "Pretrain/Loss (Raw)": 2.059368848800659, "Pretrain/Step": 7373, "Pretrain/Step Time": 8.798208171501756} +{"Pretrain/Learning Rate": 6.446585439638783e-06, "Pretrain/Loss": 2.0381126403808594, "Pretrain/Loss (Raw)": 2.185518503189087, "Pretrain/Step": 7374, "Pretrain/Step Time": 8.798399707302451} +{"Pretrain/Learning Rate": 6.440896183321979e-06, "Pretrain/Loss": 2.039078712463379, "Pretrain/Loss (Raw)": 2.055441379547119, "Pretrain/Step": 7375, "Pretrain/Step Time": 8.800852933898568} +{"Pretrain/Learning Rate": 6.435209067328479e-06, "Pretrain/Loss": 2.0366790294647217, "Pretrain/Loss (Raw)": 1.8966937065124512, "Pretrain/Step": 7376, "Pretrain/Step Time": 8.794513238593936} +{"Pretrain/Learning Rate": 6.429524092314143e-06, "Pretrain/Loss": 2.0372495651245117, "Pretrain/Loss (Raw)": 2.198820114135742, "Pretrain/Step": 7377, "Pretrain/Step Time": 8.796058824285865} +{"Pretrain/Learning Rate": 6.423841258934604e-06, "Pretrain/Loss": 2.036564350128174, "Pretrain/Loss (Raw)": 1.9820747375488281, "Pretrain/Step": 7378, "Pretrain/Step Time": 8.800533976405859} +{"Pretrain/Learning Rate": 6.418160567845224e-06, "Pretrain/Loss": 2.0353341102600098, "Pretrain/Loss (Raw)": 1.7619140148162842, "Pretrain/Step": 7379, "Pretrain/Step Time": 8.793917203322053} +{"Pretrain/Learning Rate": 6.412482019701127e-06, "Pretrain/Loss": 2.0361380577087402, "Pretrain/Loss (Raw)": 2.0187504291534424, "Pretrain/Step": 7380, "Pretrain/Step Time": 8.79778995551169} +{"Pretrain/Learning Rate": 6.4068056151571855e-06, "Pretrain/Loss": 2.038125514984131, "Pretrain/Loss (Raw)": 2.0986602306365967, "Pretrain/Step": 7381, "Pretrain/Step Time": 8.79488561116159} +{"Pretrain/Learning Rate": 6.40113135486804e-06, "Pretrain/Loss": 2.0386197566986084, "Pretrain/Loss (Raw)": 2.1117773056030273, "Pretrain/Step": 7382, "Pretrain/Step Time": 8.800105560570955} +{"Pretrain/Learning Rate": 6.395459239488069e-06, "Pretrain/Loss": 2.03804349899292, "Pretrain/Loss (Raw)": 1.8996424674987793, "Pretrain/Step": 7383, "Pretrain/Step Time": 8.805979553610086} +{"Pretrain/Learning Rate": 6.389789269671403e-06, "Pretrain/Loss": 2.0387415885925293, "Pretrain/Loss (Raw)": 2.087592124938965, "Pretrain/Step": 7384, "Pretrain/Step Time": 8.802307752892375} +{"Pretrain/Learning Rate": 6.384121446071928e-06, "Pretrain/Loss": 2.037951707839966, "Pretrain/Loss (Raw)": 1.9369361400604248, "Pretrain/Step": 7385, "Pretrain/Step Time": 8.808594753965735} +{"Pretrain/Learning Rate": 6.378455769343302e-06, "Pretrain/Loss": 2.0372507572174072, "Pretrain/Loss (Raw)": 2.021641731262207, "Pretrain/Step": 7386, "Pretrain/Step Time": 8.803003249689937} +{"Pretrain/Learning Rate": 6.372792240138891e-06, "Pretrain/Loss": 2.0353927612304688, "Pretrain/Loss (Raw)": 2.0764505863189697, "Pretrain/Step": 7387, "Pretrain/Step Time": 8.803858511149883} +{"Pretrain/Learning Rate": 6.3671308591118615e-06, "Pretrain/Loss": 2.035675287246704, "Pretrain/Loss (Raw)": 2.1209723949432373, "Pretrain/Step": 7388, "Pretrain/Step Time": 8.801625261083245} +{"Pretrain/Learning Rate": 6.361471626915091e-06, "Pretrain/Loss": 2.035698890686035, "Pretrain/Loss (Raw)": 2.0703866481781006, "Pretrain/Step": 7389, "Pretrain/Step Time": 8.800398200750351} +{"Pretrain/Learning Rate": 6.355814544201258e-06, "Pretrain/Loss": 2.0372555255889893, "Pretrain/Loss (Raw)": 2.1023192405700684, "Pretrain/Step": 7390, "Pretrain/Step Time": 8.801005899906158} +{"Pretrain/Learning Rate": 6.35015961162273e-06, "Pretrain/Loss": 2.039046287536621, "Pretrain/Loss (Raw)": 2.164128303527832, "Pretrain/Step": 7391, "Pretrain/Step Time": 8.799112018197775} +{"Pretrain/Learning Rate": 6.344506829831684e-06, "Pretrain/Loss": 2.03810453414917, "Pretrain/Loss (Raw)": 2.034182071685791, "Pretrain/Step": 7392, "Pretrain/Step Time": 8.808836659416556} +{"Pretrain/Learning Rate": 6.3388561994800115e-06, "Pretrain/Loss": 2.0384960174560547, "Pretrain/Loss (Raw)": 2.074442148208618, "Pretrain/Step": 7393, "Pretrain/Step Time": 8.803542690351605} +{"Pretrain/Learning Rate": 6.333207721219389e-06, "Pretrain/Loss": 2.035281181335449, "Pretrain/Loss (Raw)": 1.942805528640747, "Pretrain/Step": 7394, "Pretrain/Step Time": 8.806803023442626} +{"Pretrain/Learning Rate": 6.327561395701201e-06, "Pretrain/Loss": 2.0363636016845703, "Pretrain/Loss (Raw)": 1.9943490028381348, "Pretrain/Step": 7395, "Pretrain/Step Time": 8.800885584205389} +{"Pretrain/Learning Rate": 6.321917223576626e-06, "Pretrain/Loss": 2.038447618484497, "Pretrain/Loss (Raw)": 2.1687686443328857, "Pretrain/Step": 7396, "Pretrain/Step Time": 8.805299624800682} +{"Pretrain/Learning Rate": 6.316275205496572e-06, "Pretrain/Loss": 2.039931535720825, "Pretrain/Loss (Raw)": 1.9350842237472534, "Pretrain/Step": 7397, "Pretrain/Step Time": 8.804004188627005} +{"Pretrain/Learning Rate": 6.310635342111701e-06, "Pretrain/Loss": 2.0407087802886963, "Pretrain/Loss (Raw)": 2.0251495838165283, "Pretrain/Step": 7398, "Pretrain/Step Time": 8.803658416494727} +{"Pretrain/Learning Rate": 6.304997634072421e-06, "Pretrain/Loss": 2.038294792175293, "Pretrain/Loss (Raw)": 1.8855561017990112, "Pretrain/Step": 7399, "Pretrain/Step Time": 8.812156779691577} +{"Pretrain/Learning Rate": 6.299362082028909e-06, "Pretrain/Loss": 2.037446975708008, "Pretrain/Loss (Raw)": 2.202183961868286, "Pretrain/Step": 7400, "Pretrain/Step Time": 8.806820610538125} +{"Pretrain/Learning Rate": 6.293728686631095e-06, "Pretrain/Loss": 2.038032054901123, "Pretrain/Loss (Raw)": 2.1815919876098633, "Pretrain/Step": 7401, "Pretrain/Step Time": 8.811214661225677} +{"Pretrain/Learning Rate": 6.288097448528624e-06, "Pretrain/Loss": 2.0365982055664062, "Pretrain/Loss (Raw)": 1.8751808404922485, "Pretrain/Step": 7402, "Pretrain/Step Time": 8.809758983552456} +{"Pretrain/Learning Rate": 6.2824683683709335e-06, "Pretrain/Loss": 2.03709077835083, "Pretrain/Loss (Raw)": 2.0721864700317383, "Pretrain/Step": 7403, "Pretrain/Step Time": 8.807691207155585} +{"Pretrain/Learning Rate": 6.2768414468071915e-06, "Pretrain/Loss": 2.037600517272949, "Pretrain/Loss (Raw)": 2.039755344390869, "Pretrain/Step": 7404, "Pretrain/Step Time": 8.806371068581939} +{"Pretrain/Learning Rate": 6.27121668448632e-06, "Pretrain/Loss": 2.0391392707824707, "Pretrain/Loss (Raw)": 2.205364227294922, "Pretrain/Step": 7405, "Pretrain/Step Time": 8.808902621269226} +{"Pretrain/Learning Rate": 6.265594082056986e-06, "Pretrain/Loss": 2.0382843017578125, "Pretrain/Loss (Raw)": 1.9490104913711548, "Pretrain/Step": 7406, "Pretrain/Step Time": 8.82300603017211} +{"Pretrain/Learning Rate": 6.25997364016763e-06, "Pretrain/Loss": 2.038416862487793, "Pretrain/Loss (Raw)": 2.003868341445923, "Pretrain/Step": 7407, "Pretrain/Step Time": 8.814980620518327} +{"Pretrain/Learning Rate": 6.254355359466418e-06, "Pretrain/Loss": 2.0388131141662598, "Pretrain/Loss (Raw)": 2.0997464656829834, "Pretrain/Step": 7408, "Pretrain/Step Time": 8.81223145313561} +{"Pretrain/Learning Rate": 6.248739240601282e-06, "Pretrain/Loss": 2.0392911434173584, "Pretrain/Loss (Raw)": 2.0083911418914795, "Pretrain/Step": 7409, "Pretrain/Step Time": 8.81696006655693} +{"Pretrain/Learning Rate": 6.243125284219883e-06, "Pretrain/Loss": 2.0414986610412598, "Pretrain/Loss (Raw)": 2.0417568683624268, "Pretrain/Step": 7410, "Pretrain/Step Time": 8.808865435421467} +{"Pretrain/Learning Rate": 6.237513490969674e-06, "Pretrain/Loss": 2.041624069213867, "Pretrain/Loss (Raw)": 2.0088093280792236, "Pretrain/Step": 7411, "Pretrain/Step Time": 8.808055818080902} +{"Pretrain/Learning Rate": 6.231903861497817e-06, "Pretrain/Loss": 2.0422210693359375, "Pretrain/Loss (Raw)": 2.1553261280059814, "Pretrain/Step": 7412, "Pretrain/Step Time": 8.816059140488505} +{"Pretrain/Learning Rate": 6.226296396451245e-06, "Pretrain/Loss": 2.042198896408081, "Pretrain/Loss (Raw)": 1.9028342962265015, "Pretrain/Step": 7413, "Pretrain/Step Time": 8.808535046875477} +{"Pretrain/Learning Rate": 6.2206910964766325e-06, "Pretrain/Loss": 2.0447819232940674, "Pretrain/Loss (Raw)": 1.9627654552459717, "Pretrain/Step": 7414, "Pretrain/Step Time": 8.804898604750633} +{"Pretrain/Learning Rate": 6.21508796222042e-06, "Pretrain/Loss": 2.045236110687256, "Pretrain/Loss (Raw)": 1.9786309003829956, "Pretrain/Step": 7415, "Pretrain/Step Time": 8.806630373001099} +{"Pretrain/Learning Rate": 6.2094869943287805e-06, "Pretrain/Loss": 2.046163558959961, "Pretrain/Loss (Raw)": 2.0026094913482666, "Pretrain/Step": 7416, "Pretrain/Step Time": 8.80850249901414} +{"Pretrain/Learning Rate": 6.203888193447646e-06, "Pretrain/Loss": 2.046976327896118, "Pretrain/Loss (Raw)": 2.12553334236145, "Pretrain/Step": 7417, "Pretrain/Step Time": 8.806953340768814} +{"Pretrain/Learning Rate": 6.198291560222685e-06, "Pretrain/Loss": 2.0473594665527344, "Pretrain/Loss (Raw)": 2.086825370788574, "Pretrain/Step": 7418, "Pretrain/Step Time": 8.80210174061358} +{"Pretrain/Learning Rate": 6.192697095299349e-06, "Pretrain/Loss": 2.048943281173706, "Pretrain/Loss (Raw)": 1.9622515439987183, "Pretrain/Step": 7419, "Pretrain/Step Time": 8.803896827623248} +{"Pretrain/Learning Rate": 6.187104799322804e-06, "Pretrain/Loss": 2.0494771003723145, "Pretrain/Loss (Raw)": 2.020707130432129, "Pretrain/Step": 7420, "Pretrain/Step Time": 8.81469894014299} +{"Pretrain/Learning Rate": 6.1815146729379855e-06, "Pretrain/Loss": 2.0485856533050537, "Pretrain/Loss (Raw)": 1.9364579916000366, "Pretrain/Step": 7421, "Pretrain/Step Time": 8.80230288952589} +{"Pretrain/Learning Rate": 6.17592671678956e-06, "Pretrain/Loss": 2.0492000579833984, "Pretrain/Loss (Raw)": 1.991754174232483, "Pretrain/Step": 7422, "Pretrain/Step Time": 8.806477969512343} +{"Pretrain/Learning Rate": 6.170340931521976e-06, "Pretrain/Loss": 2.047733783721924, "Pretrain/Loss (Raw)": 1.942091703414917, "Pretrain/Step": 7423, "Pretrain/Step Time": 8.805346133187413} +{"Pretrain/Learning Rate": 6.164757317779404e-06, "Pretrain/Loss": 2.047365665435791, "Pretrain/Loss (Raw)": 2.0212783813476562, "Pretrain/Step": 7424, "Pretrain/Step Time": 8.809213913977146} +{"Pretrain/Learning Rate": 6.159175876205775e-06, "Pretrain/Loss": 2.0463078022003174, "Pretrain/Loss (Raw)": 1.8707667589187622, "Pretrain/Step": 7425, "Pretrain/Step Time": 8.801281932741404} +{"Pretrain/Learning Rate": 6.153596607444756e-06, "Pretrain/Loss": 2.044459342956543, "Pretrain/Loss (Raw)": 2.053816556930542, "Pretrain/Step": 7426, "Pretrain/Step Time": 8.801743987947702} +{"Pretrain/Learning Rate": 6.148019512139797e-06, "Pretrain/Loss": 2.0447726249694824, "Pretrain/Loss (Raw)": 2.0519628524780273, "Pretrain/Step": 7427, "Pretrain/Step Time": 8.805795542895794} +{"Pretrain/Learning Rate": 6.142444590934046e-06, "Pretrain/Loss": 2.0402579307556152, "Pretrain/Loss (Raw)": 1.5031144618988037, "Pretrain/Step": 7428, "Pretrain/Step Time": 8.799168480560184} +{"Pretrain/Learning Rate": 6.136871844470454e-06, "Pretrain/Loss": 2.0396530628204346, "Pretrain/Loss (Raw)": 1.9770945310592651, "Pretrain/Step": 7429, "Pretrain/Step Time": 8.801973290741444} +{"Pretrain/Learning Rate": 6.131301273391679e-06, "Pretrain/Loss": 2.0381879806518555, "Pretrain/Loss (Raw)": 1.9906461238861084, "Pretrain/Step": 7430, "Pretrain/Step Time": 8.79771545343101} +{"Pretrain/Learning Rate": 6.125732878340168e-06, "Pretrain/Loss": 2.038881778717041, "Pretrain/Loss (Raw)": 2.222670793533325, "Pretrain/Step": 7431, "Pretrain/Step Time": 8.799077780917287} +{"Pretrain/Learning Rate": 6.120166659958065e-06, "Pretrain/Loss": 2.0378994941711426, "Pretrain/Loss (Raw)": 1.9823553562164307, "Pretrain/Step": 7432, "Pretrain/Step Time": 8.799830950796604} +{"Pretrain/Learning Rate": 6.1146026188873134e-06, "Pretrain/Loss": 2.037271022796631, "Pretrain/Loss (Raw)": 1.9427189826965332, "Pretrain/Step": 7433, "Pretrain/Step Time": 8.796124514192343} +{"Pretrain/Learning Rate": 6.1090407557695735e-06, "Pretrain/Loss": 2.0342040061950684, "Pretrain/Loss (Raw)": 1.7522482872009277, "Pretrain/Step": 7434, "Pretrain/Step Time": 8.804714212194085} +{"Pretrain/Learning Rate": 6.103481071246284e-06, "Pretrain/Loss": 2.0340700149536133, "Pretrain/Loss (Raw)": 2.085726499557495, "Pretrain/Step": 7435, "Pretrain/Step Time": 8.795229176059365} +{"Pretrain/Learning Rate": 6.097923565958588e-06, "Pretrain/Loss": 2.034154176712036, "Pretrain/Loss (Raw)": 2.167689800262451, "Pretrain/Step": 7436, "Pretrain/Step Time": 8.795037833973765} +{"Pretrain/Learning Rate": 6.092368240547422e-06, "Pretrain/Loss": 2.0358147621154785, "Pretrain/Loss (Raw)": 1.8655766248703003, "Pretrain/Step": 7437, "Pretrain/Step Time": 8.792541578412056} +{"Pretrain/Learning Rate": 6.0868150956534445e-06, "Pretrain/Loss": 2.0358428955078125, "Pretrain/Loss (Raw)": 2.238600730895996, "Pretrain/Step": 7438, "Pretrain/Step Time": 8.796315720304847} +{"Pretrain/Learning Rate": 6.081264131917075e-06, "Pretrain/Loss": 2.0370986461639404, "Pretrain/Loss (Raw)": 2.161163091659546, "Pretrain/Step": 7439, "Pretrain/Step Time": 8.793554851785302} +{"Pretrain/Learning Rate": 6.075715349978464e-06, "Pretrain/Loss": 2.0362024307250977, "Pretrain/Loss (Raw)": 1.9416762590408325, "Pretrain/Step": 7440, "Pretrain/Step Time": 8.796726781874895} +{"Pretrain/Learning Rate": 6.070168750477534e-06, "Pretrain/Loss": 2.035942554473877, "Pretrain/Loss (Raw)": 2.0952091217041016, "Pretrain/Step": 7441, "Pretrain/Step Time": 8.794473426416516} +{"Pretrain/Learning Rate": 6.0646243340539584e-06, "Pretrain/Loss": 2.0347843170166016, "Pretrain/Loss (Raw)": 2.0363845825195312, "Pretrain/Step": 7442, "Pretrain/Step Time": 8.804900404065847} +{"Pretrain/Learning Rate": 6.059082101347119e-06, "Pretrain/Loss": 2.033734083175659, "Pretrain/Loss (Raw)": 2.0153441429138184, "Pretrain/Step": 7443, "Pretrain/Step Time": 8.805739849805832} +{"Pretrain/Learning Rate": 6.053542052996189e-06, "Pretrain/Loss": 2.0338635444641113, "Pretrain/Loss (Raw)": 1.9539076089859009, "Pretrain/Step": 7444, "Pretrain/Step Time": 8.80327725596726} +{"Pretrain/Learning Rate": 6.048004189640061e-06, "Pretrain/Loss": 2.0340559482574463, "Pretrain/Loss (Raw)": 2.0284411907196045, "Pretrain/Step": 7445, "Pretrain/Step Time": 8.807572469115257} +{"Pretrain/Learning Rate": 6.0424685119174095e-06, "Pretrain/Loss": 2.0327863693237305, "Pretrain/Loss (Raw)": 2.011441946029663, "Pretrain/Step": 7446, "Pretrain/Step Time": 8.807798326015472} +{"Pretrain/Learning Rate": 6.036935020466605e-06, "Pretrain/Loss": 2.034262180328369, "Pretrain/Loss (Raw)": 2.1045877933502197, "Pretrain/Step": 7447, "Pretrain/Step Time": 8.80654664337635} +{"Pretrain/Learning Rate": 6.031403715925818e-06, "Pretrain/Loss": 2.034681797027588, "Pretrain/Loss (Raw)": 1.959574580192566, "Pretrain/Step": 7448, "Pretrain/Step Time": 8.803595626726747} +{"Pretrain/Learning Rate": 6.025874598932937e-06, "Pretrain/Loss": 2.0336828231811523, "Pretrain/Loss (Raw)": 1.8861149549484253, "Pretrain/Step": 7449, "Pretrain/Step Time": 8.796083929017186} +{"Pretrain/Learning Rate": 6.020347670125606e-06, "Pretrain/Loss": 2.03251314163208, "Pretrain/Loss (Raw)": 2.013964891433716, "Pretrain/Step": 7450, "Pretrain/Step Time": 8.798166800290346} +{"Pretrain/Learning Rate": 6.014822930141212e-06, "Pretrain/Loss": 2.0330963134765625, "Pretrain/Loss (Raw)": 2.1356003284454346, "Pretrain/Step": 7451, "Pretrain/Step Time": 8.794122271239758} +{"Pretrain/Learning Rate": 6.0093003796169026e-06, "Pretrain/Loss": 2.0312771797180176, "Pretrain/Loss (Raw)": 2.0018835067749023, "Pretrain/Step": 7452, "Pretrain/Step Time": 8.79436849243939} +{"Pretrain/Learning Rate": 6.003780019189565e-06, "Pretrain/Loss": 2.031571388244629, "Pretrain/Loss (Raw)": 1.910028338432312, "Pretrain/Step": 7453, "Pretrain/Step Time": 8.792648658156395} +{"Pretrain/Learning Rate": 5.998261849495826e-06, "Pretrain/Loss": 2.031496047973633, "Pretrain/Loss (Raw)": 2.148475170135498, "Pretrain/Step": 7454, "Pretrain/Step Time": 8.790871413424611} +{"Pretrain/Learning Rate": 5.9927458711720615e-06, "Pretrain/Loss": 2.032276153564453, "Pretrain/Loss (Raw)": 2.144238233566284, "Pretrain/Step": 7455, "Pretrain/Step Time": 8.7908231690526} +{"Pretrain/Learning Rate": 5.9872320848544165e-06, "Pretrain/Loss": 2.0314929485321045, "Pretrain/Loss (Raw)": 1.9586118459701538, "Pretrain/Step": 7456, "Pretrain/Step Time": 8.795724591240287} +{"Pretrain/Learning Rate": 5.9817204911787576e-06, "Pretrain/Loss": 2.0309982299804688, "Pretrain/Loss (Raw)": 1.9758050441741943, "Pretrain/Step": 7457, "Pretrain/Step Time": 8.79492212459445} +{"Pretrain/Learning Rate": 5.976211090780712e-06, "Pretrain/Loss": 2.0306644439697266, "Pretrain/Loss (Raw)": 1.9245145320892334, "Pretrain/Step": 7458, "Pretrain/Step Time": 8.798363031819463} +{"Pretrain/Learning Rate": 5.970703884295636e-06, "Pretrain/Loss": 2.029778480529785, "Pretrain/Loss (Raw)": 1.9565579891204834, "Pretrain/Step": 7459, "Pretrain/Step Time": 8.796802008524537} +{"Pretrain/Learning Rate": 5.965198872358665e-06, "Pretrain/Loss": 2.0290138721466064, "Pretrain/Loss (Raw)": 2.0614030361175537, "Pretrain/Step": 7460, "Pretrain/Step Time": 8.794030031189322} +{"Pretrain/Learning Rate": 5.959696055604655e-06, "Pretrain/Loss": 2.0286993980407715, "Pretrain/Loss (Raw)": 2.089938163757324, "Pretrain/Step": 7461, "Pretrain/Step Time": 8.79911951906979} +{"Pretrain/Learning Rate": 5.9541954346682165e-06, "Pretrain/Loss": 2.0272836685180664, "Pretrain/Loss (Raw)": 2.081197500228882, "Pretrain/Step": 7462, "Pretrain/Step Time": 8.803006932139397} +{"Pretrain/Learning Rate": 5.948697010183701e-06, "Pretrain/Loss": 2.028026819229126, "Pretrain/Loss (Raw)": 2.058548927307129, "Pretrain/Step": 7463, "Pretrain/Step Time": 8.802922489121556} +{"Pretrain/Learning Rate": 5.943200782785227e-06, "Pretrain/Loss": 2.0291619300842285, "Pretrain/Loss (Raw)": 2.106804609298706, "Pretrain/Step": 7464, "Pretrain/Step Time": 8.80278923176229} +{"Pretrain/Learning Rate": 5.937706753106634e-06, "Pretrain/Loss": 2.0277915000915527, "Pretrain/Loss (Raw)": 2.0062737464904785, "Pretrain/Step": 7465, "Pretrain/Step Time": 8.803637858480215} +{"Pretrain/Learning Rate": 5.932214921781526e-06, "Pretrain/Loss": 2.031149387359619, "Pretrain/Loss (Raw)": 2.1613457202911377, "Pretrain/Step": 7466, "Pretrain/Step Time": 8.808195363730192} +{"Pretrain/Learning Rate": 5.9267252894432355e-06, "Pretrain/Loss": 2.031222105026245, "Pretrain/Loss (Raw)": 2.0591237545013428, "Pretrain/Step": 7467, "Pretrain/Step Time": 8.807180393487215} +{"Pretrain/Learning Rate": 5.921237856724867e-06, "Pretrain/Loss": 2.031094789505005, "Pretrain/Loss (Raw)": 2.0291054248809814, "Pretrain/Step": 7468, "Pretrain/Step Time": 8.807080363854766} +{"Pretrain/Learning Rate": 5.915752624259252e-06, "Pretrain/Loss": 2.029818534851074, "Pretrain/Loss (Raw)": 1.9512007236480713, "Pretrain/Step": 7469, "Pretrain/Step Time": 8.80591675080359} +{"Pretrain/Learning Rate": 5.910269592678971e-06, "Pretrain/Loss": 2.0307517051696777, "Pretrain/Loss (Raw)": 1.9863415956497192, "Pretrain/Step": 7470, "Pretrain/Step Time": 8.796519676223397} +{"Pretrain/Learning Rate": 5.904788762616348e-06, "Pretrain/Loss": 2.030088186264038, "Pretrain/Loss (Raw)": 2.085573196411133, "Pretrain/Step": 7471, "Pretrain/Step Time": 8.806367605924606} +{"Pretrain/Learning Rate": 5.899310134703479e-06, "Pretrain/Loss": 2.0304551124572754, "Pretrain/Loss (Raw)": 2.062598705291748, "Pretrain/Step": 7472, "Pretrain/Step Time": 8.799129309132695} +{"Pretrain/Learning Rate": 5.893833709572155e-06, "Pretrain/Loss": 2.02664852142334, "Pretrain/Loss (Raw)": 1.6944721937179565, "Pretrain/Step": 7473, "Pretrain/Step Time": 8.80244810692966} +{"Pretrain/Learning Rate": 5.88835948785397e-06, "Pretrain/Loss": 2.0274648666381836, "Pretrain/Loss (Raw)": 1.9423366785049438, "Pretrain/Step": 7474, "Pretrain/Step Time": 8.806461261585355} +{"Pretrain/Learning Rate": 5.882887470180215e-06, "Pretrain/Loss": 2.025810718536377, "Pretrain/Loss (Raw)": 1.8580995798110962, "Pretrain/Step": 7475, "Pretrain/Step Time": 8.801085649058223} +{"Pretrain/Learning Rate": 5.877417657181975e-06, "Pretrain/Loss": 2.0252647399902344, "Pretrain/Loss (Raw)": 1.9797667264938354, "Pretrain/Step": 7476, "Pretrain/Step Time": 8.804886994883418} +{"Pretrain/Learning Rate": 5.871950049490024e-06, "Pretrain/Loss": 2.0239410400390625, "Pretrain/Loss (Raw)": 1.8391178846359253, "Pretrain/Step": 7477, "Pretrain/Step Time": 8.790738107636571} +{"Pretrain/Learning Rate": 5.866484647734935e-06, "Pretrain/Loss": 2.0236692428588867, "Pretrain/Loss (Raw)": 2.098069190979004, "Pretrain/Step": 7478, "Pretrain/Step Time": 8.799448786303401} +{"Pretrain/Learning Rate": 5.861021452546997e-06, "Pretrain/Loss": 2.025970458984375, "Pretrain/Loss (Raw)": 2.307340383529663, "Pretrain/Step": 7479, "Pretrain/Step Time": 8.799322463572025} +{"Pretrain/Learning Rate": 5.855560464556253e-06, "Pretrain/Loss": 2.02768611907959, "Pretrain/Loss (Raw)": 2.1529476642608643, "Pretrain/Step": 7480, "Pretrain/Step Time": 8.796041950583458} +{"Pretrain/Learning Rate": 5.8501016843924785e-06, "Pretrain/Loss": 2.028627395629883, "Pretrain/Loss (Raw)": 2.045724630355835, "Pretrain/Step": 7481, "Pretrain/Step Time": 8.799026755616069} +{"Pretrain/Learning Rate": 5.844645112685215e-06, "Pretrain/Loss": 2.027052402496338, "Pretrain/Loss (Raw)": 1.918389916419983, "Pretrain/Step": 7482, "Pretrain/Step Time": 8.800224607810378} +{"Pretrain/Learning Rate": 5.839190750063756e-06, "Pretrain/Loss": 2.027980327606201, "Pretrain/Loss (Raw)": 2.0018465518951416, "Pretrain/Step": 7483, "Pretrain/Step Time": 8.801603687927127} +{"Pretrain/Learning Rate": 5.833738597157093e-06, "Pretrain/Loss": 2.027853488922119, "Pretrain/Loss (Raw)": 2.02340030670166, "Pretrain/Step": 7484, "Pretrain/Step Time": 8.796140568330884} +{"Pretrain/Learning Rate": 5.828288654594016e-06, "Pretrain/Loss": 2.0292205810546875, "Pretrain/Loss (Raw)": 2.197998046875, "Pretrain/Step": 7485, "Pretrain/Step Time": 8.809282438829541} +{"Pretrain/Learning Rate": 5.822840923003023e-06, "Pretrain/Loss": 2.030703067779541, "Pretrain/Loss (Raw)": 2.138209819793701, "Pretrain/Step": 7486, "Pretrain/Step Time": 8.804866028949618} +{"Pretrain/Learning Rate": 5.817395403012396e-06, "Pretrain/Loss": 2.030822277069092, "Pretrain/Loss (Raw)": 2.052189350128174, "Pretrain/Step": 7487, "Pretrain/Step Time": 8.805026281625032} +{"Pretrain/Learning Rate": 5.8119520952501085e-06, "Pretrain/Loss": 2.0318803787231445, "Pretrain/Loss (Raw)": 2.2429563999176025, "Pretrain/Step": 7488, "Pretrain/Step Time": 8.80349725857377} +{"Pretrain/Learning Rate": 5.806511000343931e-06, "Pretrain/Loss": 2.0301175117492676, "Pretrain/Loss (Raw)": 1.890389323234558, "Pretrain/Step": 7489, "Pretrain/Step Time": 8.803947761654854} +{"Pretrain/Learning Rate": 5.801072118921347e-06, "Pretrain/Loss": 2.0282998085021973, "Pretrain/Loss (Raw)": 1.9278202056884766, "Pretrain/Step": 7490, "Pretrain/Step Time": 8.803730899468064} +{"Pretrain/Learning Rate": 5.7956354516095935e-06, "Pretrain/Loss": 2.0270473957061768, "Pretrain/Loss (Raw)": 1.9578816890716553, "Pretrain/Step": 7491, "Pretrain/Step Time": 8.804345881566405} +{"Pretrain/Learning Rate": 5.790200999035647e-06, "Pretrain/Loss": 2.0246341228485107, "Pretrain/Loss (Raw)": 1.9719606637954712, "Pretrain/Step": 7492, "Pretrain/Step Time": 8.808604393154383} +{"Pretrain/Learning Rate": 5.784768761826248e-06, "Pretrain/Loss": 2.0243349075317383, "Pretrain/Loss (Raw)": 2.1224515438079834, "Pretrain/Step": 7493, "Pretrain/Step Time": 8.807983711361885} +{"Pretrain/Learning Rate": 5.779338740607859e-06, "Pretrain/Loss": 2.024691581726074, "Pretrain/Loss (Raw)": 2.1358933448791504, "Pretrain/Step": 7494, "Pretrain/Step Time": 8.811651829630136} +{"Pretrain/Learning Rate": 5.773910936006699e-06, "Pretrain/Loss": 2.0259804725646973, "Pretrain/Loss (Raw)": 2.2971694469451904, "Pretrain/Step": 7495, "Pretrain/Step Time": 8.807332582771778} +{"Pretrain/Learning Rate": 5.768485348648719e-06, "Pretrain/Loss": 2.023886203765869, "Pretrain/Loss (Raw)": 1.8561556339263916, "Pretrain/Step": 7496, "Pretrain/Step Time": 8.809903645887971} +{"Pretrain/Learning Rate": 5.763061979159637e-06, "Pretrain/Loss": 2.026376724243164, "Pretrain/Loss (Raw)": 2.1964991092681885, "Pretrain/Step": 7497, "Pretrain/Step Time": 8.810768701136112} +{"Pretrain/Learning Rate": 5.757640828164895e-06, "Pretrain/Loss": 2.0261054039001465, "Pretrain/Loss (Raw)": 1.915378451347351, "Pretrain/Step": 7498, "Pretrain/Step Time": 8.809517659246922} +{"Pretrain/Learning Rate": 5.7522218962896865e-06, "Pretrain/Loss": 2.0267012119293213, "Pretrain/Loss (Raw)": 2.111910343170166, "Pretrain/Step": 7499, "Pretrain/Step Time": 8.806119985878468} +{"Pretrain/Learning Rate": 5.746805184158941e-06, "Pretrain/Loss": 2.0262887477874756, "Pretrain/Loss (Raw)": 1.9942868947982788, "Pretrain/Step": 7500, "Pretrain/Step Time": 8.806927783414721} +{"Pretrain/Learning Rate": 5.74139069239735e-06, "Pretrain/Loss": 2.024857521057129, "Pretrain/Loss (Raw)": 1.8761451244354248, "Pretrain/Step": 7501, "Pretrain/Step Time": 8.808479588478804} +{"Pretrain/Learning Rate": 5.735978421629337e-06, "Pretrain/Loss": 2.0232110023498535, "Pretrain/Loss (Raw)": 1.9747892618179321, "Pretrain/Step": 7502, "Pretrain/Step Time": 8.806529758498073} +{"Pretrain/Learning Rate": 5.730568372479064e-06, "Pretrain/Loss": 2.022073745727539, "Pretrain/Loss (Raw)": 1.9098706245422363, "Pretrain/Step": 7503, "Pretrain/Step Time": 8.808001002296805} +{"Pretrain/Learning Rate": 5.725160545570443e-06, "Pretrain/Loss": 2.023409128189087, "Pretrain/Loss (Raw)": 2.0676283836364746, "Pretrain/Step": 7504, "Pretrain/Step Time": 8.805683808401227} +{"Pretrain/Learning Rate": 5.719754941527139e-06, "Pretrain/Loss": 2.021902084350586, "Pretrain/Loss (Raw)": 2.0059378147125244, "Pretrain/Step": 7505, "Pretrain/Step Time": 8.813931537792087} +{"Pretrain/Learning Rate": 5.7143515609725475e-06, "Pretrain/Loss": 2.0227463245391846, "Pretrain/Loss (Raw)": 2.090109348297119, "Pretrain/Step": 7506, "Pretrain/Step Time": 8.809487206861377} +{"Pretrain/Learning Rate": 5.7089504045298115e-06, "Pretrain/Loss": 2.0252041816711426, "Pretrain/Loss (Raw)": 2.0765414237976074, "Pretrain/Step": 7507, "Pretrain/Step Time": 8.806825933977962} +{"Pretrain/Learning Rate": 5.703551472821808e-06, "Pretrain/Loss": 2.026127338409424, "Pretrain/Loss (Raw)": 2.136883020401001, "Pretrain/Step": 7508, "Pretrain/Step Time": 8.803490582853556} +{"Pretrain/Learning Rate": 5.698154766471186e-06, "Pretrain/Loss": 2.0251708030700684, "Pretrain/Loss (Raw)": 1.9762300252914429, "Pretrain/Step": 7509, "Pretrain/Step Time": 8.806346919387579} +{"Pretrain/Learning Rate": 5.692760286100307e-06, "Pretrain/Loss": 2.0257487297058105, "Pretrain/Loss (Raw)": 2.1857657432556152, "Pretrain/Step": 7510, "Pretrain/Step Time": 8.803670084103942} +{"Pretrain/Learning Rate": 5.6873680323312916e-06, "Pretrain/Loss": 2.0276129245758057, "Pretrain/Loss (Raw)": 2.138249397277832, "Pretrain/Step": 7511, "Pretrain/Step Time": 8.8000118881464} +{"Pretrain/Learning Rate": 5.681978005785993e-06, "Pretrain/Loss": 2.0265135765075684, "Pretrain/Loss (Raw)": 1.946895956993103, "Pretrain/Step": 7512, "Pretrain/Step Time": 8.800357995554805} +{"Pretrain/Learning Rate": 5.676590207086035e-06, "Pretrain/Loss": 2.0282649993896484, "Pretrain/Loss (Raw)": 2.161083459854126, "Pretrain/Step": 7513, "Pretrain/Step Time": 8.791539061814547} +{"Pretrain/Learning Rate": 5.671204636852734e-06, "Pretrain/Loss": 2.028188467025757, "Pretrain/Loss (Raw)": 2.0118567943573, "Pretrain/Step": 7514, "Pretrain/Step Time": 8.804961366578937} +{"Pretrain/Learning Rate": 5.6658212957071995e-06, "Pretrain/Loss": 2.02822208404541, "Pretrain/Loss (Raw)": 2.0807700157165527, "Pretrain/Step": 7515, "Pretrain/Step Time": 8.802874840795994} +{"Pretrain/Learning Rate": 5.6604401842702545e-06, "Pretrain/Loss": 2.0270042419433594, "Pretrain/Loss (Raw)": 1.9650570154190063, "Pretrain/Step": 7516, "Pretrain/Step Time": 8.80373501777649} +{"Pretrain/Learning Rate": 5.6550613031624925e-06, "Pretrain/Loss": 2.027745485305786, "Pretrain/Loss (Raw)": 2.1652746200561523, "Pretrain/Step": 7517, "Pretrain/Step Time": 8.808389361947775} +{"Pretrain/Learning Rate": 5.649684653004203e-06, "Pretrain/Loss": 2.0263829231262207, "Pretrain/Loss (Raw)": 1.9279134273529053, "Pretrain/Step": 7518, "Pretrain/Step Time": 8.808948965743184} +{"Pretrain/Learning Rate": 5.644310234415467e-06, "Pretrain/Loss": 2.0262815952301025, "Pretrain/Loss (Raw)": 2.1511785984039307, "Pretrain/Step": 7519, "Pretrain/Step Time": 8.812524585053325} +{"Pretrain/Learning Rate": 5.638938048016082e-06, "Pretrain/Loss": 2.026488780975342, "Pretrain/Loss (Raw)": 2.0606961250305176, "Pretrain/Step": 7520, "Pretrain/Step Time": 8.811959700658917} +{"Pretrain/Learning Rate": 5.633568094425593e-06, "Pretrain/Loss": 2.0261919498443604, "Pretrain/Loss (Raw)": 2.0364630222320557, "Pretrain/Step": 7521, "Pretrain/Step Time": 8.8077680375427} +{"Pretrain/Learning Rate": 5.6282003742632846e-06, "Pretrain/Loss": 2.0318846702575684, "Pretrain/Loss (Raw)": 2.6714792251586914, "Pretrain/Step": 7522, "Pretrain/Step Time": 8.808956373482943} +{"Pretrain/Learning Rate": 5.622834888148188e-06, "Pretrain/Loss": 2.0305986404418945, "Pretrain/Loss (Raw)": 1.8296902179718018, "Pretrain/Step": 7523, "Pretrain/Step Time": 8.812140388414264} +{"Pretrain/Learning Rate": 5.617471636699098e-06, "Pretrain/Loss": 2.0304040908813477, "Pretrain/Loss (Raw)": 2.1438989639282227, "Pretrain/Step": 7524, "Pretrain/Step Time": 8.810503104701638} +{"Pretrain/Learning Rate": 5.612110620534497e-06, "Pretrain/Loss": 2.0299811363220215, "Pretrain/Loss (Raw)": 1.8809142112731934, "Pretrain/Step": 7525, "Pretrain/Step Time": 8.813539622351527} +{"Pretrain/Learning Rate": 5.606751840272664e-06, "Pretrain/Loss": 2.0294249057769775, "Pretrain/Loss (Raw)": 1.953978419303894, "Pretrain/Step": 7526, "Pretrain/Step Time": 8.814291244372725} +{"Pretrain/Learning Rate": 5.601395296531586e-06, "Pretrain/Loss": 2.03202486038208, "Pretrain/Loss (Raw)": 2.2183187007904053, "Pretrain/Step": 7527, "Pretrain/Step Time": 8.814113140106201} +{"Pretrain/Learning Rate": 5.596040989929027e-06, "Pretrain/Loss": 2.0313143730163574, "Pretrain/Loss (Raw)": 2.111283540725708, "Pretrain/Step": 7528, "Pretrain/Step Time": 8.812673503533006} +{"Pretrain/Learning Rate": 5.5906889210824405e-06, "Pretrain/Loss": 2.0298924446105957, "Pretrain/Loss (Raw)": 1.999557614326477, "Pretrain/Step": 7529, "Pretrain/Step Time": 8.808736043050885} +{"Pretrain/Learning Rate": 5.585339090609073e-06, "Pretrain/Loss": 2.0325586795806885, "Pretrain/Loss (Raw)": 2.2164666652679443, "Pretrain/Step": 7530, "Pretrain/Step Time": 8.808961775153875} +{"Pretrain/Learning Rate": 5.579991499125889e-06, "Pretrain/Loss": 2.0307087898254395, "Pretrain/Loss (Raw)": 1.83538818359375, "Pretrain/Step": 7531, "Pretrain/Step Time": 8.811311647295952} +{"Pretrain/Learning Rate": 5.574646147249596e-06, "Pretrain/Loss": 2.0306806564331055, "Pretrain/Loss (Raw)": 2.036162853240967, "Pretrain/Step": 7532, "Pretrain/Step Time": 8.811658661812544} +{"Pretrain/Learning Rate": 5.569303035596635e-06, "Pretrain/Loss": 2.029667377471924, "Pretrain/Loss (Raw)": 2.075639486312866, "Pretrain/Step": 7533, "Pretrain/Step Time": 8.811141103506088} +{"Pretrain/Learning Rate": 5.563962164783215e-06, "Pretrain/Loss": 2.030447006225586, "Pretrain/Loss (Raw)": 2.0488319396972656, "Pretrain/Step": 7534, "Pretrain/Step Time": 8.801275949925184} +{"Pretrain/Learning Rate": 5.558623535425267e-06, "Pretrain/Loss": 2.030839443206787, "Pretrain/Loss (Raw)": 2.0540990829467773, "Pretrain/Step": 7535, "Pretrain/Step Time": 8.80202778056264} +{"Pretrain/Learning Rate": 5.553287148138461e-06, "Pretrain/Loss": 2.0305895805358887, "Pretrain/Loss (Raw)": 2.0677685737609863, "Pretrain/Step": 7536, "Pretrain/Step Time": 8.811659475788474} +{"Pretrain/Learning Rate": 5.5479530035382115e-06, "Pretrain/Loss": 2.0301597118377686, "Pretrain/Loss (Raw)": 1.9533740282058716, "Pretrain/Step": 7537, "Pretrain/Step Time": 8.808494601398706} +{"Pretrain/Learning Rate": 5.542621102239686e-06, "Pretrain/Loss": 2.0304067134857178, "Pretrain/Loss (Raw)": 2.0733754634857178, "Pretrain/Step": 7538, "Pretrain/Step Time": 8.808651020750403} +{"Pretrain/Learning Rate": 5.537291444857787e-06, "Pretrain/Loss": 2.030522346496582, "Pretrain/Loss (Raw)": 2.0235981941223145, "Pretrain/Step": 7539, "Pretrain/Step Time": 8.808134153485298} +{"Pretrain/Learning Rate": 5.531964032007144e-06, "Pretrain/Loss": 2.02864670753479, "Pretrain/Loss (Raw)": 1.9152458906173706, "Pretrain/Step": 7540, "Pretrain/Step Time": 8.804466392844915} +{"Pretrain/Learning Rate": 5.526638864302144e-06, "Pretrain/Loss": 2.0288655757904053, "Pretrain/Loss (Raw)": 1.9308322668075562, "Pretrain/Step": 7541, "Pretrain/Step Time": 8.817754911258817} +{"Pretrain/Learning Rate": 5.521315942356914e-06, "Pretrain/Loss": 2.0298690795898438, "Pretrain/Loss (Raw)": 2.0912251472473145, "Pretrain/Step": 7542, "Pretrain/Step Time": 8.811670446768403} +{"Pretrain/Learning Rate": 5.5159952667853204e-06, "Pretrain/Loss": 2.031020164489746, "Pretrain/Loss (Raw)": 2.125950813293457, "Pretrain/Step": 7543, "Pretrain/Step Time": 8.817550571635365} +{"Pretrain/Learning Rate": 5.510676838200959e-06, "Pretrain/Loss": 2.0307016372680664, "Pretrain/Loss (Raw)": 1.9618505239486694, "Pretrain/Step": 7544, "Pretrain/Step Time": 8.812477612867951} +{"Pretrain/Learning Rate": 5.505360657217179e-06, "Pretrain/Loss": 2.028491258621216, "Pretrain/Loss (Raw)": 1.8426284790039062, "Pretrain/Step": 7545, "Pretrain/Step Time": 8.808493599295616} +{"Pretrain/Learning Rate": 5.5000467244470745e-06, "Pretrain/Loss": 2.029191017150879, "Pretrain/Loss (Raw)": 2.1763782501220703, "Pretrain/Step": 7546, "Pretrain/Step Time": 8.80745979771018} +{"Pretrain/Learning Rate": 5.494735040503468e-06, "Pretrain/Loss": 2.030909299850464, "Pretrain/Loss (Raw)": 2.182185411453247, "Pretrain/Step": 7547, "Pretrain/Step Time": 8.807406954467297} +{"Pretrain/Learning Rate": 5.48942560599893e-06, "Pretrain/Loss": 2.0325920581817627, "Pretrain/Loss (Raw)": 2.2361299991607666, "Pretrain/Step": 7548, "Pretrain/Step Time": 8.80619914457202} +{"Pretrain/Learning Rate": 5.4841184215457615e-06, "Pretrain/Loss": 2.0336527824401855, "Pretrain/Loss (Raw)": 2.072195291519165, "Pretrain/Step": 7549, "Pretrain/Step Time": 8.804262371733785} +{"Pretrain/Learning Rate": 5.478813487756024e-06, "Pretrain/Loss": 2.0344021320343018, "Pretrain/Loss (Raw)": 2.0876998901367188, "Pretrain/Step": 7550, "Pretrain/Step Time": 8.802916388958693} +{"Pretrain/Learning Rate": 5.473510805241502e-06, "Pretrain/Loss": 2.0343337059020996, "Pretrain/Loss (Raw)": 1.9333301782608032, "Pretrain/Step": 7551, "Pretrain/Step Time": 8.802287813276052} +{"Pretrain/Learning Rate": 5.468210374613727e-06, "Pretrain/Loss": 2.033825159072876, "Pretrain/Loss (Raw)": 1.9561736583709717, "Pretrain/Step": 7552, "Pretrain/Step Time": 8.799942970275879} +{"Pretrain/Learning Rate": 5.46291219648396e-06, "Pretrain/Loss": 2.03524112701416, "Pretrain/Loss (Raw)": 2.0520315170288086, "Pretrain/Step": 7553, "Pretrain/Step Time": 8.802464164793491} +{"Pretrain/Learning Rate": 5.457616271463234e-06, "Pretrain/Loss": 2.0341074466705322, "Pretrain/Loss (Raw)": 1.9086858034133911, "Pretrain/Step": 7554, "Pretrain/Step Time": 8.80286044999957} +{"Pretrain/Learning Rate": 5.452322600162274e-06, "Pretrain/Loss": 2.0346598625183105, "Pretrain/Loss (Raw)": 2.122655153274536, "Pretrain/Step": 7555, "Pretrain/Step Time": 8.802608644589782} +{"Pretrain/Learning Rate": 5.447031183191589e-06, "Pretrain/Loss": 2.038074493408203, "Pretrain/Loss (Raw)": 1.940199613571167, "Pretrain/Step": 7556, "Pretrain/Step Time": 8.807183362543583} +{"Pretrain/Learning Rate": 5.441742021161398e-06, "Pretrain/Loss": 2.0396018028259277, "Pretrain/Loss (Raw)": 2.172600507736206, "Pretrain/Step": 7557, "Pretrain/Step Time": 8.803804969415069} +{"Pretrain/Learning Rate": 5.436455114681693e-06, "Pretrain/Loss": 2.03849196434021, "Pretrain/Loss (Raw)": 1.8485703468322754, "Pretrain/Step": 7558, "Pretrain/Step Time": 8.802256057038903} +{"Pretrain/Learning Rate": 5.431170464362157e-06, "Pretrain/Loss": 2.036897897720337, "Pretrain/Loss (Raw)": 2.018634557723999, "Pretrain/Step": 7559, "Pretrain/Step Time": 8.80495561286807} +{"Pretrain/Learning Rate": 5.42588807081226e-06, "Pretrain/Loss": 2.0389387607574463, "Pretrain/Loss (Raw)": 2.2435965538024902, "Pretrain/Step": 7560, "Pretrain/Step Time": 8.803942179307342} +{"Pretrain/Learning Rate": 5.420607934641181e-06, "Pretrain/Loss": 2.0399582386016846, "Pretrain/Loss (Raw)": 2.07322359085083, "Pretrain/Step": 7561, "Pretrain/Step Time": 8.80539652518928} +{"Pretrain/Learning Rate": 5.415330056457871e-06, "Pretrain/Loss": 2.0434415340423584, "Pretrain/Loss (Raw)": 2.1981041431427, "Pretrain/Step": 7562, "Pretrain/Step Time": 8.797171916812658} +{"Pretrain/Learning Rate": 5.410054436870968e-06, "Pretrain/Loss": 2.0407776832580566, "Pretrain/Loss (Raw)": 1.7447503805160522, "Pretrain/Step": 7563, "Pretrain/Step Time": 8.809565538540483} +{"Pretrain/Learning Rate": 5.404781076488901e-06, "Pretrain/Loss": 2.039438247680664, "Pretrain/Loss (Raw)": 1.996263861656189, "Pretrain/Step": 7564, "Pretrain/Step Time": 8.812531793490052} +{"Pretrain/Learning Rate": 5.399509975919828e-06, "Pretrain/Loss": 2.0409536361694336, "Pretrain/Loss (Raw)": 2.0595076084136963, "Pretrain/Step": 7565, "Pretrain/Step Time": 8.812958505004644} +{"Pretrain/Learning Rate": 5.394241135771613e-06, "Pretrain/Loss": 2.0387678146362305, "Pretrain/Loss (Raw)": 1.958837866783142, "Pretrain/Step": 7566, "Pretrain/Step Time": 8.810092713683844} +{"Pretrain/Learning Rate": 5.388974556651902e-06, "Pretrain/Loss": 2.0383853912353516, "Pretrain/Loss (Raw)": 2.112194776535034, "Pretrain/Step": 7567, "Pretrain/Step Time": 8.817656863480806} +{"Pretrain/Learning Rate": 5.3837102391680465e-06, "Pretrain/Loss": 2.038862705230713, "Pretrain/Loss (Raw)": 2.0027618408203125, "Pretrain/Step": 7568, "Pretrain/Step Time": 8.810946663841605} +{"Pretrain/Learning Rate": 5.378448183927176e-06, "Pretrain/Loss": 2.0371737480163574, "Pretrain/Loss (Raw)": 1.879015564918518, "Pretrain/Step": 7569, "Pretrain/Step Time": 8.809522589668632} +{"Pretrain/Learning Rate": 5.373188391536108e-06, "Pretrain/Loss": 2.0380702018737793, "Pretrain/Loss (Raw)": 2.1511430740356445, "Pretrain/Step": 7570, "Pretrain/Step Time": 8.803149361163378} +{"Pretrain/Learning Rate": 5.3679308626014445e-06, "Pretrain/Loss": 2.0381689071655273, "Pretrain/Loss (Raw)": 2.027973175048828, "Pretrain/Step": 7571, "Pretrain/Step Time": 8.804530324414372} +{"Pretrain/Learning Rate": 5.362675597729505e-06, "Pretrain/Loss": 2.0387799739837646, "Pretrain/Loss (Raw)": 2.0321407318115234, "Pretrain/Step": 7572, "Pretrain/Step Time": 8.806521682068706} +{"Pretrain/Learning Rate": 5.357422597526349e-06, "Pretrain/Loss": 2.0394556522369385, "Pretrain/Loss (Raw)": 2.114924907684326, "Pretrain/Step": 7573, "Pretrain/Step Time": 8.802565108984709} +{"Pretrain/Learning Rate": 5.3521718625977715e-06, "Pretrain/Loss": 2.0403523445129395, "Pretrain/Loss (Raw)": 2.126211166381836, "Pretrain/Step": 7574, "Pretrain/Step Time": 8.798006134107709} +{"Pretrain/Learning Rate": 5.346923393549325e-06, "Pretrain/Loss": 2.039530038833618, "Pretrain/Loss (Raw)": 1.9993367195129395, "Pretrain/Step": 7575, "Pretrain/Step Time": 8.798923250287771} +{"Pretrain/Learning Rate": 5.34167719098628e-06, "Pretrain/Loss": 2.0409536361694336, "Pretrain/Loss (Raw)": 2.1418168544769287, "Pretrain/Step": 7576, "Pretrain/Step Time": 8.800239263102412} +{"Pretrain/Learning Rate": 5.336433255513656e-06, "Pretrain/Loss": 2.043529987335205, "Pretrain/Loss (Raw)": 2.215855360031128, "Pretrain/Step": 7577, "Pretrain/Step Time": 8.800839144736528} +{"Pretrain/Learning Rate": 5.331191587736198e-06, "Pretrain/Loss": 2.043506145477295, "Pretrain/Loss (Raw)": 2.0109364986419678, "Pretrain/Step": 7578, "Pretrain/Step Time": 8.802186952903867} +{"Pretrain/Learning Rate": 5.325952188258418e-06, "Pretrain/Loss": 2.0403685569763184, "Pretrain/Loss (Raw)": 1.7339756488800049, "Pretrain/Step": 7579, "Pretrain/Step Time": 8.805551648139954} +{"Pretrain/Learning Rate": 5.320715057684536e-06, "Pretrain/Loss": 2.040402412414551, "Pretrain/Loss (Raw)": 2.0062034130096436, "Pretrain/Step": 7580, "Pretrain/Step Time": 8.80700845271349} +{"Pretrain/Learning Rate": 5.315480196618527e-06, "Pretrain/Loss": 2.0420498847961426, "Pretrain/Loss (Raw)": 2.120919704437256, "Pretrain/Step": 7581, "Pretrain/Step Time": 8.809717044234276} +{"Pretrain/Learning Rate": 5.310247605664093e-06, "Pretrain/Loss": 2.041482448577881, "Pretrain/Loss (Raw)": 2.075826406478882, "Pretrain/Step": 7582, "Pretrain/Step Time": 8.809903157874942} +{"Pretrain/Learning Rate": 5.30501728542469e-06, "Pretrain/Loss": 2.0402884483337402, "Pretrain/Loss (Raw)": 1.9914097785949707, "Pretrain/Step": 7583, "Pretrain/Step Time": 8.809779873117805} +{"Pretrain/Learning Rate": 5.299789236503503e-06, "Pretrain/Loss": 2.0404186248779297, "Pretrain/Loss (Raw)": 1.9752918481826782, "Pretrain/Step": 7584, "Pretrain/Step Time": 8.804423708468676} +{"Pretrain/Learning Rate": 5.294563459503449e-06, "Pretrain/Loss": 2.041332960128784, "Pretrain/Loss (Raw)": 2.092824935913086, "Pretrain/Step": 7585, "Pretrain/Step Time": 8.807233551517129} +{"Pretrain/Learning Rate": 5.2893399550271835e-06, "Pretrain/Loss": 2.0422682762145996, "Pretrain/Loss (Raw)": 2.0442495346069336, "Pretrain/Step": 7586, "Pretrain/Step Time": 8.803931310772896} +{"Pretrain/Learning Rate": 5.2841187236771226e-06, "Pretrain/Loss": 2.0427722930908203, "Pretrain/Loss (Raw)": 2.021074056625366, "Pretrain/Step": 7587, "Pretrain/Step Time": 8.8062713034451} +{"Pretrain/Learning Rate": 5.278899766055395e-06, "Pretrain/Loss": 2.0431253910064697, "Pretrain/Loss (Raw)": 2.1065902709960938, "Pretrain/Step": 7588, "Pretrain/Step Time": 8.81336317770183} +{"Pretrain/Learning Rate": 5.273683082763875e-06, "Pretrain/Loss": 2.0422964096069336, "Pretrain/Loss (Raw)": 1.9838449954986572, "Pretrain/Step": 7589, "Pretrain/Step Time": 8.808286590501666} +{"Pretrain/Learning Rate": 5.26846867440417e-06, "Pretrain/Loss": 2.0416815280914307, "Pretrain/Loss (Raw)": 2.0024924278259277, "Pretrain/Step": 7590, "Pretrain/Step Time": 8.805717585608363} +{"Pretrain/Learning Rate": 5.263256541577641e-06, "Pretrain/Loss": 2.041701316833496, "Pretrain/Loss (Raw)": 2.0610694885253906, "Pretrain/Step": 7591, "Pretrain/Step Time": 8.800114702433348} +{"Pretrain/Learning Rate": 5.25804668488537e-06, "Pretrain/Loss": 2.0396618843078613, "Pretrain/Loss (Raw)": 1.8457728624343872, "Pretrain/Step": 7592, "Pretrain/Step Time": 8.809921843931079} +{"Pretrain/Learning Rate": 5.252839104928184e-06, "Pretrain/Loss": 2.0398364067077637, "Pretrain/Loss (Raw)": 2.028592824935913, "Pretrain/Step": 7593, "Pretrain/Step Time": 8.805563416332006} +{"Pretrain/Learning Rate": 5.247633802306637e-06, "Pretrain/Loss": 2.038745403289795, "Pretrain/Loss (Raw)": 2.021697521209717, "Pretrain/Step": 7594, "Pretrain/Step Time": 8.805712210014462} +{"Pretrain/Learning Rate": 5.242430777621049e-06, "Pretrain/Loss": 2.038249969482422, "Pretrain/Loss (Raw)": 1.995700478553772, "Pretrain/Step": 7595, "Pretrain/Step Time": 8.80625830590725} +{"Pretrain/Learning Rate": 5.2372300314714295e-06, "Pretrain/Loss": 2.0383005142211914, "Pretrain/Loss (Raw)": 2.035594940185547, "Pretrain/Step": 7596, "Pretrain/Step Time": 8.807120770215988} +{"Pretrain/Learning Rate": 5.232031564457576e-06, "Pretrain/Loss": 2.037386894226074, "Pretrain/Loss (Raw)": 1.8342252969741821, "Pretrain/Step": 7597, "Pretrain/Step Time": 8.810376705601811} +{"Pretrain/Learning Rate": 5.226835377178984e-06, "Pretrain/Loss": 2.037710666656494, "Pretrain/Loss (Raw)": 2.027801990509033, "Pretrain/Step": 7598, "Pretrain/Step Time": 8.809294167906046} +{"Pretrain/Learning Rate": 5.221641470234928e-06, "Pretrain/Loss": 2.039623260498047, "Pretrain/Loss (Raw)": 2.3303706645965576, "Pretrain/Step": 7599, "Pretrain/Step Time": 8.798739599063993} +{"Pretrain/Learning Rate": 5.216449844224358e-06, "Pretrain/Loss": 2.041224956512451, "Pretrain/Loss (Raw)": 2.267618179321289, "Pretrain/Step": 7600, "Pretrain/Step Time": 8.8131363093853} +{"Pretrain/Learning Rate": 5.211260499746026e-06, "Pretrain/Loss": 2.0442287921905518, "Pretrain/Loss (Raw)": 2.0789802074432373, "Pretrain/Step": 7601, "Pretrain/Step Time": 8.810342960059643} +{"Pretrain/Learning Rate": 5.206073437398371e-06, "Pretrain/Loss": 2.045212745666504, "Pretrain/Loss (Raw)": 2.0682895183563232, "Pretrain/Step": 7602, "Pretrain/Step Time": 8.80937130190432} +{"Pretrain/Learning Rate": 5.200888657779615e-06, "Pretrain/Loss": 2.047938585281372, "Pretrain/Loss (Raw)": 2.207000255584717, "Pretrain/Step": 7603, "Pretrain/Step Time": 8.813862830400467} +{"Pretrain/Learning Rate": 5.19570616148766e-06, "Pretrain/Loss": 2.0466113090515137, "Pretrain/Loss (Raw)": 1.8098727464675903, "Pretrain/Step": 7604, "Pretrain/Step Time": 8.809729374945164} +{"Pretrain/Learning Rate": 5.190525949120193e-06, "Pretrain/Loss": 2.047673463821411, "Pretrain/Loss (Raw)": 1.9750771522521973, "Pretrain/Step": 7605, "Pretrain/Step Time": 8.810829738155007} +{"Pretrain/Learning Rate": 5.18534802127463e-06, "Pretrain/Loss": 2.0463178157806396, "Pretrain/Loss (Raw)": 1.9245563745498657, "Pretrain/Step": 7606, "Pretrain/Step Time": 8.802366135641932} +{"Pretrain/Learning Rate": 5.1801723785480925e-06, "Pretrain/Loss": 2.0435891151428223, "Pretrain/Loss (Raw)": 1.9580403566360474, "Pretrain/Step": 7607, "Pretrain/Step Time": 8.812576033174992} +{"Pretrain/Learning Rate": 5.174999021537475e-06, "Pretrain/Loss": 2.043449878692627, "Pretrain/Loss (Raw)": 2.1351184844970703, "Pretrain/Step": 7608, "Pretrain/Step Time": 8.811206221580505} +{"Pretrain/Learning Rate": 5.169827950839384e-06, "Pretrain/Loss": 2.0437116622924805, "Pretrain/Loss (Raw)": 2.0792782306671143, "Pretrain/Step": 7609, "Pretrain/Step Time": 8.809063041582704} +{"Pretrain/Learning Rate": 5.164659167050187e-06, "Pretrain/Loss": 2.0437204837799072, "Pretrain/Loss (Raw)": 1.919509768486023, "Pretrain/Step": 7610, "Pretrain/Step Time": 8.806243862956762} +{"Pretrain/Learning Rate": 5.15949267076595e-06, "Pretrain/Loss": 2.043407440185547, "Pretrain/Loss (Raw)": 1.9617393016815186, "Pretrain/Step": 7611, "Pretrain/Step Time": 8.805572835728526} +{"Pretrain/Learning Rate": 5.1543284625825165e-06, "Pretrain/Loss": 2.044732093811035, "Pretrain/Loss (Raw)": 2.192986249923706, "Pretrain/Step": 7612, "Pretrain/Step Time": 8.804809048771858} +{"Pretrain/Learning Rate": 5.149166543095444e-06, "Pretrain/Loss": 2.0453920364379883, "Pretrain/Loss (Raw)": 2.2824795246124268, "Pretrain/Step": 7613, "Pretrain/Step Time": 8.796165235340595} +{"Pretrain/Learning Rate": 5.144006912900021e-06, "Pretrain/Loss": 2.044844150543213, "Pretrain/Loss (Raw)": 2.0680925846099854, "Pretrain/Step": 7614, "Pretrain/Step Time": 8.80704054236412} +{"Pretrain/Learning Rate": 5.138849572591281e-06, "Pretrain/Loss": 2.0450356006622314, "Pretrain/Loss (Raw)": 2.0766563415527344, "Pretrain/Step": 7615, "Pretrain/Step Time": 8.804041119292378} +{"Pretrain/Learning Rate": 5.133694522764002e-06, "Pretrain/Loss": 2.0419869422912598, "Pretrain/Loss (Raw)": 1.8527158498764038, "Pretrain/Step": 7616, "Pretrain/Step Time": 8.804684659466147} +{"Pretrain/Learning Rate": 5.128541764012687e-06, "Pretrain/Loss": 2.0437278747558594, "Pretrain/Loss (Raw)": 2.1132493019104004, "Pretrain/Step": 7617, "Pretrain/Step Time": 8.808546993881464} +{"Pretrain/Learning Rate": 5.123391296931571e-06, "Pretrain/Loss": 2.04417085647583, "Pretrain/Loss (Raw)": 1.984520435333252, "Pretrain/Step": 7618, "Pretrain/Step Time": 8.81339024193585} +{"Pretrain/Learning Rate": 5.118243122114625e-06, "Pretrain/Loss": 2.0447235107421875, "Pretrain/Loss (Raw)": 2.028616189956665, "Pretrain/Step": 7619, "Pretrain/Step Time": 8.813934462144971} +{"Pretrain/Learning Rate": 5.113097240155576e-06, "Pretrain/Loss": 2.0445756912231445, "Pretrain/Loss (Raw)": 1.9530696868896484, "Pretrain/Step": 7620, "Pretrain/Step Time": 8.809825729578733} +{"Pretrain/Learning Rate": 5.107953651647862e-06, "Pretrain/Loss": 2.0449886322021484, "Pretrain/Loss (Raw)": 2.1752798557281494, "Pretrain/Step": 7621, "Pretrain/Step Time": 8.81127367541194} +{"Pretrain/Learning Rate": 5.10281235718467e-06, "Pretrain/Loss": 2.043200731277466, "Pretrain/Loss (Raw)": 1.9070546627044678, "Pretrain/Step": 7622, "Pretrain/Step Time": 8.813702959567308} +{"Pretrain/Learning Rate": 5.097673357358907e-06, "Pretrain/Loss": 2.041189193725586, "Pretrain/Loss (Raw)": 2.0396666526794434, "Pretrain/Step": 7623, "Pretrain/Step Time": 8.809440752491355} +{"Pretrain/Learning Rate": 5.092536652763241e-06, "Pretrain/Loss": 2.0425801277160645, "Pretrain/Loss (Raw)": 2.034196615219116, "Pretrain/Step": 7624, "Pretrain/Step Time": 8.810551514849067} +{"Pretrain/Learning Rate": 5.087402243990056e-06, "Pretrain/Loss": 2.041013240814209, "Pretrain/Loss (Raw)": 1.9959666728973389, "Pretrain/Step": 7625, "Pretrain/Step Time": 8.808998161926866} +{"Pretrain/Learning Rate": 5.0822701316314755e-06, "Pretrain/Loss": 2.0416393280029297, "Pretrain/Loss (Raw)": 1.9955226182937622, "Pretrain/Step": 7626, "Pretrain/Step Time": 8.813001226633787} +{"Pretrain/Learning Rate": 5.0771403162793525e-06, "Pretrain/Loss": 2.041512966156006, "Pretrain/Loss (Raw)": 2.095707416534424, "Pretrain/Step": 7627, "Pretrain/Step Time": 8.801447626203299} +{"Pretrain/Learning Rate": 5.072012798525294e-06, "Pretrain/Loss": 2.0430262088775635, "Pretrain/Loss (Raw)": 2.1880059242248535, "Pretrain/Step": 7628, "Pretrain/Step Time": 8.806788951158524} +{"Pretrain/Learning Rate": 5.0668875789606245e-06, "Pretrain/Loss": 2.0447893142700195, "Pretrain/Loss (Raw)": 2.101793050765991, "Pretrain/Step": 7629, "Pretrain/Step Time": 8.804080877453089} +{"Pretrain/Learning Rate": 5.061764658176407e-06, "Pretrain/Loss": 2.044706344604492, "Pretrain/Loss (Raw)": 1.9641846418380737, "Pretrain/Step": 7630, "Pretrain/Step Time": 8.79925694130361} +{"Pretrain/Learning Rate": 5.056644036763433e-06, "Pretrain/Loss": 2.0461959838867188, "Pretrain/Loss (Raw)": 2.1005325317382812, "Pretrain/Step": 7631, "Pretrain/Step Time": 8.799900254234672} +{"Pretrain/Learning Rate": 5.051525715312253e-06, "Pretrain/Loss": 2.0443778038024902, "Pretrain/Loss (Raw)": 1.8348959684371948, "Pretrain/Step": 7632, "Pretrain/Step Time": 8.805445106700063} +{"Pretrain/Learning Rate": 5.046409694413129e-06, "Pretrain/Loss": 2.044325351715088, "Pretrain/Loss (Raw)": 1.9992245435714722, "Pretrain/Step": 7633, "Pretrain/Step Time": 8.798282569274306} +{"Pretrain/Learning Rate": 5.04129597465606e-06, "Pretrain/Loss": 2.0418167114257812, "Pretrain/Loss (Raw)": 1.7690318822860718, "Pretrain/Step": 7634, "Pretrain/Step Time": 8.794669568538666} +{"Pretrain/Learning Rate": 5.0361845566307825e-06, "Pretrain/Loss": 2.0414414405822754, "Pretrain/Loss (Raw)": 2.0284688472747803, "Pretrain/Step": 7635, "Pretrain/Step Time": 8.80462239868939} +{"Pretrain/Learning Rate": 5.0310754409267886e-06, "Pretrain/Loss": 2.0386390686035156, "Pretrain/Loss (Raw)": 1.7781985998153687, "Pretrain/Step": 7636, "Pretrain/Step Time": 8.808517288416624} +{"Pretrain/Learning Rate": 5.025968628133259e-06, "Pretrain/Loss": 2.040367603302002, "Pretrain/Loss (Raw)": 2.197512149810791, "Pretrain/Step": 7637, "Pretrain/Step Time": 8.804060282185674} +{"Pretrain/Learning Rate": 5.020864118839152e-06, "Pretrain/Loss": 2.039231300354004, "Pretrain/Loss (Raw)": 2.040306806564331, "Pretrain/Step": 7638, "Pretrain/Step Time": 8.803495420143008} +{"Pretrain/Learning Rate": 5.015761913633135e-06, "Pretrain/Loss": 2.0383126735687256, "Pretrain/Loss (Raw)": 2.020662546157837, "Pretrain/Step": 7639, "Pretrain/Step Time": 8.80273442901671} +{"Pretrain/Learning Rate": 5.010662013103637e-06, "Pretrain/Loss": 2.038982391357422, "Pretrain/Loss (Raw)": 2.0326173305511475, "Pretrain/Step": 7640, "Pretrain/Step Time": 8.80400980822742} +{"Pretrain/Learning Rate": 5.0055644178387735e-06, "Pretrain/Loss": 2.038299322128296, "Pretrain/Loss (Raw)": 2.073652744293213, "Pretrain/Step": 7641, "Pretrain/Step Time": 8.804023208096623} +{"Pretrain/Learning Rate": 5.0004691284264435e-06, "Pretrain/Loss": 2.0389597415924072, "Pretrain/Loss (Raw)": 2.0963923931121826, "Pretrain/Step": 7642, "Pretrain/Step Time": 8.80181854404509} +{"Pretrain/Learning Rate": 4.99537614545425e-06, "Pretrain/Loss": 2.038487434387207, "Pretrain/Loss (Raw)": 2.020319700241089, "Pretrain/Step": 7643, "Pretrain/Step Time": 8.801142195239663} +{"Pretrain/Learning Rate": 4.990285469509559e-06, "Pretrain/Loss": 2.040417194366455, "Pretrain/Loss (Raw)": 2.212045907974243, "Pretrain/Step": 7644, "Pretrain/Step Time": 8.797634404152632} +{"Pretrain/Learning Rate": 4.98519710117942e-06, "Pretrain/Loss": 2.040058135986328, "Pretrain/Loss (Raw)": 2.1193439960479736, "Pretrain/Step": 7645, "Pretrain/Step Time": 8.80268251337111} +{"Pretrain/Learning Rate": 4.980111041050667e-06, "Pretrain/Loss": 2.040416717529297, "Pretrain/Loss (Raw)": 1.9737979173660278, "Pretrain/Step": 7646, "Pretrain/Step Time": 8.798919590190053} +{"Pretrain/Learning Rate": 4.975027289709855e-06, "Pretrain/Loss": 2.0379250049591064, "Pretrain/Loss (Raw)": 1.8322393894195557, "Pretrain/Step": 7647, "Pretrain/Step Time": 8.796038383617997} +{"Pretrain/Learning Rate": 4.969945847743246e-06, "Pretrain/Loss": 2.0382726192474365, "Pretrain/Loss (Raw)": 2.1051933765411377, "Pretrain/Step": 7648, "Pretrain/Step Time": 8.795097690075636} +{"Pretrain/Learning Rate": 4.964866715736874e-06, "Pretrain/Loss": 2.0375754833221436, "Pretrain/Loss (Raw)": 1.947218894958496, "Pretrain/Step": 7649, "Pretrain/Step Time": 8.796074714511633} +{"Pretrain/Learning Rate": 4.959789894276473e-06, "Pretrain/Loss": 2.033217668533325, "Pretrain/Loss (Raw)": 2.1136856079101562, "Pretrain/Step": 7650, "Pretrain/Step Time": 8.799866432324052} +{"Pretrain/Learning Rate": 4.9547153839475476e-06, "Pretrain/Loss": 2.034245491027832, "Pretrain/Loss (Raw)": 1.9612252712249756, "Pretrain/Step": 7651, "Pretrain/Step Time": 8.797965614125133} +{"Pretrain/Learning Rate": 4.949643185335287e-06, "Pretrain/Loss": 2.034844398498535, "Pretrain/Loss (Raw)": 2.2205653190612793, "Pretrain/Step": 7652, "Pretrain/Step Time": 8.79791572317481} +{"Pretrain/Learning Rate": 4.944573299024663e-06, "Pretrain/Loss": 2.0357167720794678, "Pretrain/Loss (Raw)": 1.9925962686538696, "Pretrain/Step": 7653, "Pretrain/Step Time": 8.794305581599474} +{"Pretrain/Learning Rate": 4.939505725600341e-06, "Pretrain/Loss": 2.035735845565796, "Pretrain/Loss (Raw)": 1.9564317464828491, "Pretrain/Step": 7654, "Pretrain/Step Time": 8.792077315971255} +{"Pretrain/Learning Rate": 4.934440465646762e-06, "Pretrain/Loss": 2.034393072128296, "Pretrain/Loss (Raw)": 2.046442747116089, "Pretrain/Step": 7655, "Pretrain/Step Time": 8.784182926639915} +{"Pretrain/Learning Rate": 4.929377519748046e-06, "Pretrain/Loss": 2.0340051651000977, "Pretrain/Loss (Raw)": 2.0616424083709717, "Pretrain/Step": 7656, "Pretrain/Step Time": 8.786629658192396} +{"Pretrain/Learning Rate": 4.924316888488098e-06, "Pretrain/Loss": 2.0339488983154297, "Pretrain/Loss (Raw)": 1.9923516511917114, "Pretrain/Step": 7657, "Pretrain/Step Time": 8.787949431687593} +{"Pretrain/Learning Rate": 4.919258572450527e-06, "Pretrain/Loss": 2.0330703258514404, "Pretrain/Loss (Raw)": 2.1039977073669434, "Pretrain/Step": 7658, "Pretrain/Step Time": 8.781109781935811} +{"Pretrain/Learning Rate": 4.914202572218679e-06, "Pretrain/Loss": 2.03475284576416, "Pretrain/Loss (Raw)": 2.0507476329803467, "Pretrain/Step": 7659, "Pretrain/Step Time": 8.78160098940134} +{"Pretrain/Learning Rate": 4.909148888375631e-06, "Pretrain/Loss": 2.0340921878814697, "Pretrain/Loss (Raw)": 1.9516081809997559, "Pretrain/Step": 7660, "Pretrain/Step Time": 8.781894747167826} +{"Pretrain/Learning Rate": 4.904097521504214e-06, "Pretrain/Loss": 2.034515142440796, "Pretrain/Loss (Raw)": 2.129777431488037, "Pretrain/Step": 7661, "Pretrain/Step Time": 8.781157789751887} +{"Pretrain/Learning Rate": 4.899048472186962e-06, "Pretrain/Loss": 2.034879684448242, "Pretrain/Loss (Raw)": 2.0954973697662354, "Pretrain/Step": 7662, "Pretrain/Step Time": 8.778163822367787} +{"Pretrain/Learning Rate": 4.8940017410061625e-06, "Pretrain/Loss": 2.034402370452881, "Pretrain/Loss (Raw)": 1.9929734468460083, "Pretrain/Step": 7663, "Pretrain/Step Time": 8.783887619152665} +{"Pretrain/Learning Rate": 4.888957328543817e-06, "Pretrain/Loss": 2.033442974090576, "Pretrain/Loss (Raw)": 1.9450156688690186, "Pretrain/Step": 7664, "Pretrain/Step Time": 8.779091725125909} +{"Pretrain/Learning Rate": 4.8839152353816835e-06, "Pretrain/Loss": 2.0339279174804688, "Pretrain/Loss (Raw)": 2.015427589416504, "Pretrain/Step": 7665, "Pretrain/Step Time": 8.779032859951258} +{"Pretrain/Learning Rate": 4.8788754621012375e-06, "Pretrain/Loss": 2.032841205596924, "Pretrain/Loss (Raw)": 1.9342342615127563, "Pretrain/Step": 7666, "Pretrain/Step Time": 8.789611805230379} +{"Pretrain/Learning Rate": 4.873838009283685e-06, "Pretrain/Loss": 2.0323636531829834, "Pretrain/Loss (Raw)": 1.9625049829483032, "Pretrain/Step": 7667, "Pretrain/Step Time": 8.789905689656734} +{"Pretrain/Learning Rate": 4.868802877509965e-06, "Pretrain/Loss": 2.031857490539551, "Pretrain/Loss (Raw)": 1.8504688739776611, "Pretrain/Step": 7668, "Pretrain/Step Time": 8.787216287106276} +{"Pretrain/Learning Rate": 4.863770067360765e-06, "Pretrain/Loss": 2.0321688652038574, "Pretrain/Loss (Raw)": 1.9706521034240723, "Pretrain/Step": 7669, "Pretrain/Step Time": 8.777590546756983} +{"Pretrain/Learning Rate": 4.858739579416488e-06, "Pretrain/Loss": 2.031479597091675, "Pretrain/Loss (Raw)": 2.0030360221862793, "Pretrain/Step": 7670, "Pretrain/Step Time": 8.786478253081441} +{"Pretrain/Learning Rate": 4.85371141425727e-06, "Pretrain/Loss": 2.03187894821167, "Pretrain/Loss (Raw)": 2.1770637035369873, "Pretrain/Step": 7671, "Pretrain/Step Time": 8.782142125070095} +{"Pretrain/Learning Rate": 4.848685572462977e-06, "Pretrain/Loss": 2.030207633972168, "Pretrain/Loss (Raw)": 1.7479103803634644, "Pretrain/Step": 7672, "Pretrain/Step Time": 8.785899283364415} +{"Pretrain/Learning Rate": 4.843662054613227e-06, "Pretrain/Loss": 2.0292105674743652, "Pretrain/Loss (Raw)": 1.7150222063064575, "Pretrain/Step": 7673, "Pretrain/Step Time": 8.787067277356982} +{"Pretrain/Learning Rate": 4.838640861287347e-06, "Pretrain/Loss": 2.028200149536133, "Pretrain/Loss (Raw)": 2.047018051147461, "Pretrain/Step": 7674, "Pretrain/Step Time": 8.79110855422914} +{"Pretrain/Learning Rate": 4.833621993064408e-06, "Pretrain/Loss": 2.0273876190185547, "Pretrain/Loss (Raw)": 2.078202962875366, "Pretrain/Step": 7675, "Pretrain/Step Time": 8.78717291727662} +{"Pretrain/Learning Rate": 4.8286054505231994e-06, "Pretrain/Loss": 2.026557445526123, "Pretrain/Loss (Raw)": 2.1298775672912598, "Pretrain/Step": 7676, "Pretrain/Step Time": 8.780791845172644} +{"Pretrain/Learning Rate": 4.823591234242269e-06, "Pretrain/Loss": 2.0270681381225586, "Pretrain/Loss (Raw)": 2.137554407119751, "Pretrain/Step": 7677, "Pretrain/Step Time": 8.798400729894638} +{"Pretrain/Learning Rate": 4.818579344799873e-06, "Pretrain/Loss": 2.026400089263916, "Pretrain/Loss (Raw)": 2.0021650791168213, "Pretrain/Step": 7678, "Pretrain/Step Time": 8.793582696467638} +{"Pretrain/Learning Rate": 4.813569782774005e-06, "Pretrain/Loss": 2.0273337364196777, "Pretrain/Loss (Raw)": 2.0528464317321777, "Pretrain/Step": 7679, "Pretrain/Step Time": 8.799157030880451} +{"Pretrain/Learning Rate": 4.808562548742382e-06, "Pretrain/Loss": 2.0264875888824463, "Pretrain/Loss (Raw)": 1.847880482673645, "Pretrain/Step": 7680, "Pretrain/Step Time": 8.801809508353472} +{"Pretrain/Learning Rate": 4.803557643282486e-06, "Pretrain/Loss": 2.0246472358703613, "Pretrain/Loss (Raw)": 1.8164454698562622, "Pretrain/Step": 7681, "Pretrain/Step Time": 8.803240278735757} +{"Pretrain/Learning Rate": 4.798555066971478e-06, "Pretrain/Loss": 2.0259580612182617, "Pretrain/Loss (Raw)": 2.0764942169189453, "Pretrain/Step": 7682, "Pretrain/Step Time": 8.801682490855455} +{"Pretrain/Learning Rate": 4.793554820386298e-06, "Pretrain/Loss": 2.0252461433410645, "Pretrain/Loss (Raw)": 2.0315074920654297, "Pretrain/Step": 7683, "Pretrain/Step Time": 8.796116255223751} +{"Pretrain/Learning Rate": 4.788556904103586e-06, "Pretrain/Loss": 2.026914119720459, "Pretrain/Loss (Raw)": 2.1537230014801025, "Pretrain/Step": 7684, "Pretrain/Step Time": 8.796445317566395} +{"Pretrain/Learning Rate": 4.783561318699745e-06, "Pretrain/Loss": 2.0257620811462402, "Pretrain/Loss (Raw)": 2.0251083374023438, "Pretrain/Step": 7685, "Pretrain/Step Time": 8.798900038003922} +{"Pretrain/Learning Rate": 4.778568064750863e-06, "Pretrain/Loss": 2.0271387100219727, "Pretrain/Loss (Raw)": 2.0248043537139893, "Pretrain/Step": 7686, "Pretrain/Step Time": 8.800897190347314} +{"Pretrain/Learning Rate": 4.773577142832797e-06, "Pretrain/Loss": 2.027334451675415, "Pretrain/Loss (Raw)": 2.0436806678771973, "Pretrain/Step": 7687, "Pretrain/Step Time": 8.795979015529156} +{"Pretrain/Learning Rate": 4.768588553521136e-06, "Pretrain/Loss": 2.025568962097168, "Pretrain/Loss (Raw)": 2.017618417739868, "Pretrain/Step": 7688, "Pretrain/Step Time": 8.800997516140342} +{"Pretrain/Learning Rate": 4.763602297391167e-06, "Pretrain/Loss": 2.024893283843994, "Pretrain/Loss (Raw)": 1.9867278337478638, "Pretrain/Step": 7689, "Pretrain/Step Time": 8.803709702566266} +{"Pretrain/Learning Rate": 4.758618375017943e-06, "Pretrain/Loss": 2.0233960151672363, "Pretrain/Loss (Raw)": 2.00643253326416, "Pretrain/Step": 7690, "Pretrain/Step Time": 8.803768943995237} +{"Pretrain/Learning Rate": 4.753636786976223e-06, "Pretrain/Loss": 2.0212316513061523, "Pretrain/Loss (Raw)": 1.4677295684814453, "Pretrain/Step": 7691, "Pretrain/Step Time": 8.791395831853151} +{"Pretrain/Learning Rate": 4.748657533840525e-06, "Pretrain/Loss": 2.0220062732696533, "Pretrain/Loss (Raw)": 2.095426082611084, "Pretrain/Step": 7692, "Pretrain/Step Time": 8.803224246948957} +{"Pretrain/Learning Rate": 4.743680616185053e-06, "Pretrain/Loss": 2.0222136974334717, "Pretrain/Loss (Raw)": 2.0860681533813477, "Pretrain/Step": 7693, "Pretrain/Step Time": 8.80013496056199} +{"Pretrain/Learning Rate": 4.738706034583793e-06, "Pretrain/Loss": 2.0234014987945557, "Pretrain/Loss (Raw)": 2.1108484268188477, "Pretrain/Step": 7694, "Pretrain/Step Time": 8.803353253751993} +{"Pretrain/Learning Rate": 4.73373378961042e-06, "Pretrain/Loss": 2.023897647857666, "Pretrain/Loss (Raw)": 2.1756935119628906, "Pretrain/Step": 7695, "Pretrain/Step Time": 8.79465652629733} +{"Pretrain/Learning Rate": 4.728763881838375e-06, "Pretrain/Loss": 2.0244855880737305, "Pretrain/Loss (Raw)": 2.0780272483825684, "Pretrain/Step": 7696, "Pretrain/Step Time": 8.798776788637042} +{"Pretrain/Learning Rate": 4.723796311840789e-06, "Pretrain/Loss": 2.026376724243164, "Pretrain/Loss (Raw)": 2.121082067489624, "Pretrain/Step": 7697, "Pretrain/Step Time": 8.801087925210595} +{"Pretrain/Learning Rate": 4.7188310801905635e-06, "Pretrain/Loss": 2.024467945098877, "Pretrain/Loss (Raw)": 1.906826376914978, "Pretrain/Step": 7698, "Pretrain/Step Time": 8.793087679892778} +{"Pretrain/Learning Rate": 4.713868187460307e-06, "Pretrain/Loss": 2.0231902599334717, "Pretrain/Loss (Raw)": 1.8644315004348755, "Pretrain/Step": 7699, "Pretrain/Step Time": 8.794803876429796} +{"Pretrain/Learning Rate": 4.708907634222359e-06, "Pretrain/Loss": 2.023678779602051, "Pretrain/Loss (Raw)": 2.094691514968872, "Pretrain/Step": 7700, "Pretrain/Step Time": 8.793075904250145} +{"Pretrain/Learning Rate": 4.703949421048795e-06, "Pretrain/Loss": 2.022594928741455, "Pretrain/Loss (Raw)": 1.9761683940887451, "Pretrain/Step": 7701, "Pretrain/Step Time": 8.79382142610848} +{"Pretrain/Learning Rate": 4.698993548511427e-06, "Pretrain/Loss": 2.021850347518921, "Pretrain/Loss (Raw)": 2.0309009552001953, "Pretrain/Step": 7702, "Pretrain/Step Time": 8.800419079139829} +{"Pretrain/Learning Rate": 4.6940400171817835e-06, "Pretrain/Loss": 2.023381233215332, "Pretrain/Loss (Raw)": 2.1953065395355225, "Pretrain/Step": 7703, "Pretrain/Step Time": 8.799690626561642} +{"Pretrain/Learning Rate": 4.68908882763113e-06, "Pretrain/Loss": 2.022324562072754, "Pretrain/Loss (Raw)": 2.006547451019287, "Pretrain/Step": 7704, "Pretrain/Step Time": 8.79626015946269} +{"Pretrain/Learning Rate": 4.684139980430455e-06, "Pretrain/Loss": 2.019411325454712, "Pretrain/Loss (Raw)": 1.8429582118988037, "Pretrain/Step": 7705, "Pretrain/Step Time": 8.794972650706768} +{"Pretrain/Learning Rate": 4.679193476150495e-06, "Pretrain/Loss": 2.018612861633301, "Pretrain/Loss (Raw)": 1.9087245464324951, "Pretrain/Step": 7706, "Pretrain/Step Time": 8.79479624517262} +{"Pretrain/Learning Rate": 4.674249315361698e-06, "Pretrain/Loss": 2.0210790634155273, "Pretrain/Loss (Raw)": 2.049668312072754, "Pretrain/Step": 7707, "Pretrain/Step Time": 8.79556904733181} +{"Pretrain/Learning Rate": 4.669307498634251e-06, "Pretrain/Loss": 2.020663261413574, "Pretrain/Loss (Raw)": 1.9529680013656616, "Pretrain/Step": 7708, "Pretrain/Step Time": 8.794006986543536} +{"Pretrain/Learning Rate": 4.664368026538054e-06, "Pretrain/Loss": 2.0184144973754883, "Pretrain/Loss (Raw)": 1.8331072330474854, "Pretrain/Step": 7709, "Pretrain/Step Time": 8.797376785427332} +{"Pretrain/Learning Rate": 4.6594308996427694e-06, "Pretrain/Loss": 2.0184125900268555, "Pretrain/Loss (Raw)": 2.075572967529297, "Pretrain/Step": 7710, "Pretrain/Step Time": 8.799499610438943} +{"Pretrain/Learning Rate": 4.654496118517762e-06, "Pretrain/Loss": 2.017557382583618, "Pretrain/Loss (Raw)": 1.881934404373169, "Pretrain/Step": 7711, "Pretrain/Step Time": 8.798535641282797} +{"Pretrain/Learning Rate": 4.64956368373213e-06, "Pretrain/Loss": 2.0174617767333984, "Pretrain/Loss (Raw)": 1.9630582332611084, "Pretrain/Step": 7712, "Pretrain/Step Time": 8.796995878219604} +{"Pretrain/Learning Rate": 4.644633595854706e-06, "Pretrain/Loss": 2.016263484954834, "Pretrain/Loss (Raw)": 1.939447045326233, "Pretrain/Step": 7713, "Pretrain/Step Time": 8.80451574549079} +{"Pretrain/Learning Rate": 4.6397058554540575e-06, "Pretrain/Loss": 2.0166244506835938, "Pretrain/Loss (Raw)": 2.090480089187622, "Pretrain/Step": 7714, "Pretrain/Step Time": 8.80132957547903} +{"Pretrain/Learning Rate": 4.6347804630984735e-06, "Pretrain/Loss": 2.0165772438049316, "Pretrain/Loss (Raw)": 2.0150022506713867, "Pretrain/Step": 7715, "Pretrain/Step Time": 8.80200469121337} +{"Pretrain/Learning Rate": 4.629857419355968e-06, "Pretrain/Loss": 2.015378475189209, "Pretrain/Loss (Raw)": 1.9531666040420532, "Pretrain/Step": 7716, "Pretrain/Step Time": 8.799351308494806} +{"Pretrain/Learning Rate": 4.624936724794285e-06, "Pretrain/Loss": 2.015878677368164, "Pretrain/Loss (Raw)": 2.0478363037109375, "Pretrain/Step": 7717, "Pretrain/Step Time": 8.798745403066278} +{"Pretrain/Learning Rate": 4.620018379980917e-06, "Pretrain/Loss": 2.017867088317871, "Pretrain/Loss (Raw)": 2.2569925785064697, "Pretrain/Step": 7718, "Pretrain/Step Time": 8.799026928842068} +{"Pretrain/Learning Rate": 4.6151023854830635e-06, "Pretrain/Loss": 2.0181946754455566, "Pretrain/Loss (Raw)": 2.1030611991882324, "Pretrain/Step": 7719, "Pretrain/Step Time": 8.802092529833317} +{"Pretrain/Learning Rate": 4.610188741867657e-06, "Pretrain/Loss": 2.019968271255493, "Pretrain/Loss (Raw)": 2.072754144668579, "Pretrain/Step": 7720, "Pretrain/Step Time": 8.803484801203012} +{"Pretrain/Learning Rate": 4.6052774497013615e-06, "Pretrain/Loss": 2.020170211791992, "Pretrain/Loss (Raw)": 2.0544519424438477, "Pretrain/Step": 7721, "Pretrain/Step Time": 8.801616802811623} +{"Pretrain/Learning Rate": 4.600368509550584e-06, "Pretrain/Loss": 2.0201916694641113, "Pretrain/Loss (Raw)": 2.024442195892334, "Pretrain/Step": 7722, "Pretrain/Step Time": 8.799651397392154} +{"Pretrain/Learning Rate": 4.5954619219814254e-06, "Pretrain/Loss": 2.020328998565674, "Pretrain/Loss (Raw)": 2.0132803916931152, "Pretrain/Step": 7723, "Pretrain/Step Time": 8.80511274188757} +{"Pretrain/Learning Rate": 4.590557687559754e-06, "Pretrain/Loss": 2.0217511653900146, "Pretrain/Loss (Raw)": 2.217639446258545, "Pretrain/Step": 7724, "Pretrain/Step Time": 8.80770923383534} +{"Pretrain/Learning Rate": 4.585655806851136e-06, "Pretrain/Loss": 2.022745132446289, "Pretrain/Loss (Raw)": 1.9614496231079102, "Pretrain/Step": 7725, "Pretrain/Step Time": 8.80771497450769} +{"Pretrain/Learning Rate": 4.5807562804208975e-06, "Pretrain/Loss": 2.02225923538208, "Pretrain/Loss (Raw)": 1.9656120538711548, "Pretrain/Step": 7726, "Pretrain/Step Time": 8.814516706392169} +{"Pretrain/Learning Rate": 4.575859108834049e-06, "Pretrain/Loss": 2.019477367401123, "Pretrain/Loss (Raw)": 1.9742937088012695, "Pretrain/Step": 7727, "Pretrain/Step Time": 8.817921832203865} +{"Pretrain/Learning Rate": 4.570964292655372e-06, "Pretrain/Loss": 2.0172715187072754, "Pretrain/Loss (Raw)": 1.9852674007415771, "Pretrain/Step": 7728, "Pretrain/Step Time": 8.805265421047807} +{"Pretrain/Learning Rate": 4.56607183244937e-06, "Pretrain/Loss": 2.016559600830078, "Pretrain/Loss (Raw)": 1.9878461360931396, "Pretrain/Step": 7729, "Pretrain/Step Time": 8.803407538682222} +{"Pretrain/Learning Rate": 4.56118172878024e-06, "Pretrain/Loss": 2.0171971321105957, "Pretrain/Loss (Raw)": 2.149909734725952, "Pretrain/Step": 7730, "Pretrain/Step Time": 8.802618101239204} +{"Pretrain/Learning Rate": 4.556293982211951e-06, "Pretrain/Loss": 2.0164520740509033, "Pretrain/Loss (Raw)": 2.1116087436676025, "Pretrain/Step": 7731, "Pretrain/Step Time": 8.798271866515279} +{"Pretrain/Learning Rate": 4.551408593308165e-06, "Pretrain/Loss": 2.0186195373535156, "Pretrain/Loss (Raw)": 2.0873122215270996, "Pretrain/Step": 7732, "Pretrain/Step Time": 8.798341991379857} +{"Pretrain/Learning Rate": 4.5465255626323116e-06, "Pretrain/Loss": 2.0190978050231934, "Pretrain/Loss (Raw)": 2.036269187927246, "Pretrain/Step": 7733, "Pretrain/Step Time": 8.801308747380972} +{"Pretrain/Learning Rate": 4.541644890747495e-06, "Pretrain/Loss": 2.019498825073242, "Pretrain/Loss (Raw)": 1.975895881652832, "Pretrain/Step": 7734, "Pretrain/Step Time": 8.80299786478281} +{"Pretrain/Learning Rate": 4.536766578216603e-06, "Pretrain/Loss": 2.0212414264678955, "Pretrain/Loss (Raw)": 2.18113112449646, "Pretrain/Step": 7735, "Pretrain/Step Time": 8.791349781677127} +{"Pretrain/Learning Rate": 4.531890625602206e-06, "Pretrain/Loss": 2.021022319793701, "Pretrain/Loss (Raw)": 2.1070549488067627, "Pretrain/Step": 7736, "Pretrain/Step Time": 8.794662637636065} +{"Pretrain/Learning Rate": 4.5270170334666435e-06, "Pretrain/Loss": 2.021625280380249, "Pretrain/Loss (Raw)": 2.156473159790039, "Pretrain/Step": 7737, "Pretrain/Step Time": 8.797932486981153} +{"Pretrain/Learning Rate": 4.522145802371936e-06, "Pretrain/Loss": 2.0220115184783936, "Pretrain/Loss (Raw)": 1.9689475297927856, "Pretrain/Step": 7738, "Pretrain/Step Time": 8.797819605097175} +{"Pretrain/Learning Rate": 4.517276932879877e-06, "Pretrain/Loss": 2.022463798522949, "Pretrain/Loss (Raw)": 2.0196175575256348, "Pretrain/Step": 7739, "Pretrain/Step Time": 8.79970538802445} +{"Pretrain/Learning Rate": 4.512410425551958e-06, "Pretrain/Loss": 2.021056652069092, "Pretrain/Loss (Raw)": 2.0128839015960693, "Pretrain/Step": 7740, "Pretrain/Step Time": 8.799597518518567} +{"Pretrain/Learning Rate": 4.507546280949413e-06, "Pretrain/Loss": 2.0189332962036133, "Pretrain/Loss (Raw)": 2.010673761367798, "Pretrain/Step": 7741, "Pretrain/Step Time": 8.80605630762875} +{"Pretrain/Learning Rate": 4.502684499633183e-06, "Pretrain/Loss": 2.0177531242370605, "Pretrain/Loss (Raw)": 1.9170300960540771, "Pretrain/Step": 7742, "Pretrain/Step Time": 8.794260377064347} +{"Pretrain/Learning Rate": 4.4978250821639725e-06, "Pretrain/Loss": 2.0181634426116943, "Pretrain/Loss (Raw)": 2.129197359085083, "Pretrain/Step": 7743, "Pretrain/Step Time": 8.795556968078017} +{"Pretrain/Learning Rate": 4.492968029102182e-06, "Pretrain/Loss": 2.0190610885620117, "Pretrain/Loss (Raw)": 1.9675891399383545, "Pretrain/Step": 7744, "Pretrain/Step Time": 8.798225972801447} +{"Pretrain/Learning Rate": 4.488113341007951e-06, "Pretrain/Loss": 2.0165271759033203, "Pretrain/Loss (Raw)": 1.7889336347579956, "Pretrain/Step": 7745, "Pretrain/Step Time": 8.794459953904152} +{"Pretrain/Learning Rate": 4.48326101844114e-06, "Pretrain/Loss": 2.01729679107666, "Pretrain/Loss (Raw)": 2.0830111503601074, "Pretrain/Step": 7746, "Pretrain/Step Time": 8.793525986373425} +{"Pretrain/Learning Rate": 4.4784110619613514e-06, "Pretrain/Loss": 2.0180530548095703, "Pretrain/Loss (Raw)": 2.125430107116699, "Pretrain/Step": 7747, "Pretrain/Step Time": 8.785741928964853} +{"Pretrain/Learning Rate": 4.473563472127898e-06, "Pretrain/Loss": 2.019275188446045, "Pretrain/Loss (Raw)": 2.109496831893921, "Pretrain/Step": 7748, "Pretrain/Step Time": 8.79096938483417} +{"Pretrain/Learning Rate": 4.468718249499831e-06, "Pretrain/Loss": 2.0183234214782715, "Pretrain/Loss (Raw)": 2.053457498550415, "Pretrain/Step": 7749, "Pretrain/Step Time": 8.790355402976274} +{"Pretrain/Learning Rate": 4.463875394635916e-06, "Pretrain/Loss": 2.0199012756347656, "Pretrain/Loss (Raw)": 2.109009265899658, "Pretrain/Step": 7750, "Pretrain/Step Time": 8.787979347631335} +{"Pretrain/Learning Rate": 4.459034908094664e-06, "Pretrain/Loss": 2.01882004737854, "Pretrain/Loss (Raw)": 1.9012854099273682, "Pretrain/Step": 7751, "Pretrain/Step Time": 8.788515854626894} +{"Pretrain/Learning Rate": 4.454196790434301e-06, "Pretrain/Loss": 2.0187325477600098, "Pretrain/Loss (Raw)": 2.022993564605713, "Pretrain/Step": 7752, "Pretrain/Step Time": 8.783438365906477} +{"Pretrain/Learning Rate": 4.44936104221278e-06, "Pretrain/Loss": 2.0183613300323486, "Pretrain/Loss (Raw)": 1.9484485387802124, "Pretrain/Step": 7753, "Pretrain/Step Time": 8.785052699968219} +{"Pretrain/Learning Rate": 4.444527663987771e-06, "Pretrain/Loss": 2.01930570602417, "Pretrain/Loss (Raw)": 2.116400957107544, "Pretrain/Step": 7754, "Pretrain/Step Time": 8.781332524493337} +{"Pretrain/Learning Rate": 4.439696656316703e-06, "Pretrain/Loss": 2.0186588764190674, "Pretrain/Loss (Raw)": 2.0129144191741943, "Pretrain/Step": 7755, "Pretrain/Step Time": 8.799636343494058} +{"Pretrain/Learning Rate": 4.434868019756697e-06, "Pretrain/Loss": 2.018974542617798, "Pretrain/Loss (Raw)": 2.2284042835235596, "Pretrain/Step": 7756, "Pretrain/Step Time": 8.793052224442363} +{"Pretrain/Learning Rate": 4.430041754864617e-06, "Pretrain/Loss": 2.0211892127990723, "Pretrain/Loss (Raw)": 2.3852615356445312, "Pretrain/Step": 7757, "Pretrain/Step Time": 8.793165439739823} +{"Pretrain/Learning Rate": 4.4252178621970455e-06, "Pretrain/Loss": 2.021768093109131, "Pretrain/Loss (Raw)": 2.0382635593414307, "Pretrain/Step": 7758, "Pretrain/Step Time": 8.796321205794811} +{"Pretrain/Learning Rate": 4.420396342310309e-06, "Pretrain/Loss": 2.0212416648864746, "Pretrain/Loss (Raw)": 2.0331945419311523, "Pretrain/Step": 7759, "Pretrain/Step Time": 8.800659334287047} +{"Pretrain/Learning Rate": 4.41557719576044e-06, "Pretrain/Loss": 2.0237090587615967, "Pretrain/Loss (Raw)": 2.150695323944092, "Pretrain/Step": 7760, "Pretrain/Step Time": 8.79872520454228} +{"Pretrain/Learning Rate": 4.410760423103205e-06, "Pretrain/Loss": 2.0233376026153564, "Pretrain/Loss (Raw)": 1.9516959190368652, "Pretrain/Step": 7761, "Pretrain/Step Time": 8.796573840081692} +{"Pretrain/Learning Rate": 4.405946024894092e-06, "Pretrain/Loss": 2.025207996368408, "Pretrain/Loss (Raw)": 2.0084598064422607, "Pretrain/Step": 7762, "Pretrain/Step Time": 8.80025139823556} +{"Pretrain/Learning Rate": 4.401134001688337e-06, "Pretrain/Loss": 2.024834156036377, "Pretrain/Loss (Raw)": 1.9805971384048462, "Pretrain/Step": 7763, "Pretrain/Step Time": 8.809038670733571} +{"Pretrain/Learning Rate": 4.396324354040862e-06, "Pretrain/Loss": 2.026869773864746, "Pretrain/Loss (Raw)": 2.03875732421875, "Pretrain/Step": 7764, "Pretrain/Step Time": 8.803828157484531} +{"Pretrain/Learning Rate": 4.391517082506358e-06, "Pretrain/Loss": 2.0257136821746826, "Pretrain/Loss (Raw)": 2.049535036087036, "Pretrain/Step": 7765, "Pretrain/Step Time": 8.805372353643179} +{"Pretrain/Learning Rate": 4.386712187639205e-06, "Pretrain/Loss": 2.0248615741729736, "Pretrain/Loss (Raw)": 1.9312137365341187, "Pretrain/Step": 7766, "Pretrain/Step Time": 8.804867750033736} +{"Pretrain/Learning Rate": 4.38190966999355e-06, "Pretrain/Loss": 2.0248653888702393, "Pretrain/Loss (Raw)": 2.0211715698242188, "Pretrain/Step": 7767, "Pretrain/Step Time": 8.810438618063927} +{"Pretrain/Learning Rate": 4.377109530123217e-06, "Pretrain/Loss": 2.0245540142059326, "Pretrain/Loss (Raw)": 1.992751955986023, "Pretrain/Step": 7768, "Pretrain/Step Time": 8.808187959715724} +{"Pretrain/Learning Rate": 4.372311768581794e-06, "Pretrain/Loss": 2.024797201156616, "Pretrain/Loss (Raw)": 2.1047842502593994, "Pretrain/Step": 7769, "Pretrain/Step Time": 8.812876543030143} +{"Pretrain/Learning Rate": 4.367516385922574e-06, "Pretrain/Loss": 2.0222272872924805, "Pretrain/Loss (Raw)": 1.767421841621399, "Pretrain/Step": 7770, "Pretrain/Step Time": 8.800692806020379} +{"Pretrain/Learning Rate": 4.362723382698594e-06, "Pretrain/Loss": 2.0227856636047363, "Pretrain/Loss (Raw)": 2.091794729232788, "Pretrain/Step": 7771, "Pretrain/Step Time": 8.806207654997706} +{"Pretrain/Learning Rate": 4.357932759462599e-06, "Pretrain/Loss": 2.0203187465667725, "Pretrain/Loss (Raw)": 1.8962844610214233, "Pretrain/Step": 7772, "Pretrain/Step Time": 8.806663205847144} +{"Pretrain/Learning Rate": 4.35314451676706e-06, "Pretrain/Loss": 2.0194172859191895, "Pretrain/Loss (Raw)": 2.0039825439453125, "Pretrain/Step": 7773, "Pretrain/Step Time": 8.798081329092383} +{"Pretrain/Learning Rate": 4.348358655164203e-06, "Pretrain/Loss": 2.0207901000976562, "Pretrain/Loss (Raw)": 2.149496078491211, "Pretrain/Step": 7774, "Pretrain/Step Time": 8.799025062471628} +{"Pretrain/Learning Rate": 4.343575175205922e-06, "Pretrain/Loss": 2.021113872528076, "Pretrain/Loss (Raw)": 1.8737096786499023, "Pretrain/Step": 7775, "Pretrain/Step Time": 8.800512431189418} +{"Pretrain/Learning Rate": 4.338794077443897e-06, "Pretrain/Loss": 2.0193300247192383, "Pretrain/Loss (Raw)": 1.8768309354782104, "Pretrain/Step": 7776, "Pretrain/Step Time": 8.8024608977139} +{"Pretrain/Learning Rate": 4.334015362429491e-06, "Pretrain/Loss": 2.020634174346924, "Pretrain/Loss (Raw)": 2.1141674518585205, "Pretrain/Step": 7777, "Pretrain/Step Time": 8.804177602753043} +{"Pretrain/Learning Rate": 4.329239030713827e-06, "Pretrain/Loss": 2.019468069076538, "Pretrain/Loss (Raw)": 1.9644238948822021, "Pretrain/Step": 7778, "Pretrain/Step Time": 8.797148112207651} +{"Pretrain/Learning Rate": 4.3244650828477114e-06, "Pretrain/Loss": 2.0194296836853027, "Pretrain/Loss (Raw)": 1.9563125371932983, "Pretrain/Step": 7779, "Pretrain/Step Time": 8.797574209049344} +{"Pretrain/Learning Rate": 4.319693519381712e-06, "Pretrain/Loss": 2.0172653198242188, "Pretrain/Loss (Raw)": 1.9435158967971802, "Pretrain/Step": 7780, "Pretrain/Step Time": 8.799938390031457} +{"Pretrain/Learning Rate": 4.314924340866105e-06, "Pretrain/Loss": 2.0168633460998535, "Pretrain/Loss (Raw)": 1.9411410093307495, "Pretrain/Step": 7781, "Pretrain/Step Time": 8.797603093087673} +{"Pretrain/Learning Rate": 4.310157547850896e-06, "Pretrain/Loss": 2.0158376693725586, "Pretrain/Loss (Raw)": 1.825148582458496, "Pretrain/Step": 7782, "Pretrain/Step Time": 8.800795707851648} +{"Pretrain/Learning Rate": 4.3053931408858055e-06, "Pretrain/Loss": 2.0165534019470215, "Pretrain/Loss (Raw)": 2.1380558013916016, "Pretrain/Step": 7783, "Pretrain/Step Time": 8.804486457258463} +{"Pretrain/Learning Rate": 4.300631120520301e-06, "Pretrain/Loss": 2.0153560638427734, "Pretrain/Loss (Raw)": 1.9083812236785889, "Pretrain/Step": 7784, "Pretrain/Step Time": 8.80473186261952} +{"Pretrain/Learning Rate": 4.295871487303554e-06, "Pretrain/Loss": 2.0127875804901123, "Pretrain/Loss (Raw)": 1.6635934114456177, "Pretrain/Step": 7785, "Pretrain/Step Time": 8.806178279221058} +{"Pretrain/Learning Rate": 4.291114241784467e-06, "Pretrain/Loss": 2.011219024658203, "Pretrain/Loss (Raw)": 1.9031946659088135, "Pretrain/Step": 7786, "Pretrain/Step Time": 8.807442117482424} +{"Pretrain/Learning Rate": 4.286359384511662e-06, "Pretrain/Loss": 2.0113394260406494, "Pretrain/Loss (Raw)": 2.066187858581543, "Pretrain/Step": 7787, "Pretrain/Step Time": 8.81600021198392} +{"Pretrain/Learning Rate": 4.281606916033507e-06, "Pretrain/Loss": 2.012443780899048, "Pretrain/Loss (Raw)": 2.0929548740386963, "Pretrain/Step": 7788, "Pretrain/Step Time": 8.817952115088701} +{"Pretrain/Learning Rate": 4.276856836898072e-06, "Pretrain/Loss": 2.011934280395508, "Pretrain/Loss (Raw)": 2.0645503997802734, "Pretrain/Step": 7789, "Pretrain/Step Time": 8.817095262929797} +{"Pretrain/Learning Rate": 4.272109147653155e-06, "Pretrain/Loss": 2.010784864425659, "Pretrain/Loss (Raw)": 1.9484107494354248, "Pretrain/Step": 7790, "Pretrain/Step Time": 8.818081298843026} +{"Pretrain/Learning Rate": 4.267363848846278e-06, "Pretrain/Loss": 2.012448310852051, "Pretrain/Loss (Raw)": 2.2058730125427246, "Pretrain/Step": 7791, "Pretrain/Step Time": 8.817204909399152} +{"Pretrain/Learning Rate": 4.262620941024703e-06, "Pretrain/Loss": 2.013875961303711, "Pretrain/Loss (Raw)": 2.1277976036071777, "Pretrain/Step": 7792, "Pretrain/Step Time": 8.813221273943782} +{"Pretrain/Learning Rate": 4.2578804247353996e-06, "Pretrain/Loss": 2.015268564224243, "Pretrain/Loss (Raw)": 2.193629741668701, "Pretrain/Step": 7793, "Pretrain/Step Time": 8.813306150957942} +{"Pretrain/Learning Rate": 4.253142300525068e-06, "Pretrain/Loss": 2.0148937702178955, "Pretrain/Loss (Raw)": 1.8862820863723755, "Pretrain/Step": 7794, "Pretrain/Step Time": 8.804100327193737} +{"Pretrain/Learning Rate": 4.248406568940119e-06, "Pretrain/Loss": 2.014524459838867, "Pretrain/Loss (Raw)": 1.9152323007583618, "Pretrain/Step": 7795, "Pretrain/Step Time": 8.807660859078169} +{"Pretrain/Learning Rate": 4.243673230526715e-06, "Pretrain/Loss": 2.0153214931488037, "Pretrain/Loss (Raw)": 1.9524739980697632, "Pretrain/Step": 7796, "Pretrain/Step Time": 8.806582741439342} +{"Pretrain/Learning Rate": 4.238942285830724e-06, "Pretrain/Loss": 2.013566493988037, "Pretrain/Loss (Raw)": 1.7460103034973145, "Pretrain/Step": 7797, "Pretrain/Step Time": 8.805064937099814} +{"Pretrain/Learning Rate": 4.234213735397738e-06, "Pretrain/Loss": 2.014585494995117, "Pretrain/Loss (Raw)": 2.1334898471832275, "Pretrain/Step": 7798, "Pretrain/Step Time": 8.806592926383018} +{"Pretrain/Learning Rate": 4.229487579773067e-06, "Pretrain/Loss": 2.0142571926116943, "Pretrain/Loss (Raw)": 2.1350114345550537, "Pretrain/Step": 7799, "Pretrain/Step Time": 8.805745543912053} +{"Pretrain/Learning Rate": 4.22476381950177e-06, "Pretrain/Loss": 2.0153450965881348, "Pretrain/Loss (Raw)": 1.8871647119522095, "Pretrain/Step": 7800, "Pretrain/Step Time": 8.804651532322168} +{"Pretrain/Learning Rate": 4.220042455128603e-06, "Pretrain/Loss": 2.0194342136383057, "Pretrain/Loss (Raw)": 2.2384536266326904, "Pretrain/Step": 7801, "Pretrain/Step Time": 8.805160844698548} +{"Pretrain/Learning Rate": 4.215323487198061e-06, "Pretrain/Loss": 2.0199427604675293, "Pretrain/Loss (Raw)": 2.1121208667755127, "Pretrain/Step": 7802, "Pretrain/Step Time": 8.803789213299751} +{"Pretrain/Learning Rate": 4.210606916254348e-06, "Pretrain/Loss": 2.019866943359375, "Pretrain/Loss (Raw)": 2.0684971809387207, "Pretrain/Step": 7803, "Pretrain/Step Time": 8.806471357122064} +{"Pretrain/Learning Rate": 4.205892742841422e-06, "Pretrain/Loss": 2.018202304840088, "Pretrain/Loss (Raw)": 1.916788935661316, "Pretrain/Step": 7804, "Pretrain/Step Time": 8.810689304023981} +{"Pretrain/Learning Rate": 4.2011809675029154e-06, "Pretrain/Loss": 2.018141508102417, "Pretrain/Loss (Raw)": 2.1297621726989746, "Pretrain/Step": 7805, "Pretrain/Step Time": 8.796024397015572} +{"Pretrain/Learning Rate": 4.196471590782236e-06, "Pretrain/Loss": 2.0198802947998047, "Pretrain/Loss (Raw)": 2.224745512008667, "Pretrain/Step": 7806, "Pretrain/Step Time": 8.800379615277052} +{"Pretrain/Learning Rate": 4.191764613222474e-06, "Pretrain/Loss": 2.020991086959839, "Pretrain/Loss (Raw)": 2.1950035095214844, "Pretrain/Step": 7807, "Pretrain/Step Time": 8.799369599670172} +{"Pretrain/Learning Rate": 4.18706003536648e-06, "Pretrain/Loss": 2.0231833457946777, "Pretrain/Loss (Raw)": 2.1285250186920166, "Pretrain/Step": 7808, "Pretrain/Step Time": 8.800907410681248} +{"Pretrain/Learning Rate": 4.182357857756786e-06, "Pretrain/Loss": 2.0250813961029053, "Pretrain/Loss (Raw)": 2.059370279312134, "Pretrain/Step": 7809, "Pretrain/Step Time": 8.798180600628257} +{"Pretrain/Learning Rate": 4.1776580809356845e-06, "Pretrain/Loss": 2.0255746841430664, "Pretrain/Loss (Raw)": 2.1396381855010986, "Pretrain/Step": 7810, "Pretrain/Step Time": 8.798595750704408} +{"Pretrain/Learning Rate": 4.172960705445164e-06, "Pretrain/Loss": 2.0262703895568848, "Pretrain/Loss (Raw)": 2.1205685138702393, "Pretrain/Step": 7811, "Pretrain/Step Time": 8.799305917695165} +{"Pretrain/Learning Rate": 4.168265731826965e-06, "Pretrain/Loss": 2.025477409362793, "Pretrain/Loss (Raw)": 2.052198886871338, "Pretrain/Step": 7812, "Pretrain/Step Time": 8.799147123470902} +{"Pretrain/Learning Rate": 4.163573160622522e-06, "Pretrain/Loss": 2.0249319076538086, "Pretrain/Loss (Raw)": 1.9552918672561646, "Pretrain/Step": 7813, "Pretrain/Step Time": 8.796939332038164} +{"Pretrain/Learning Rate": 4.1588829923730005e-06, "Pretrain/Loss": 2.025001049041748, "Pretrain/Loss (Raw)": 2.0336592197418213, "Pretrain/Step": 7814, "Pretrain/Step Time": 8.798393581062555} +{"Pretrain/Learning Rate": 4.1541952276193095e-06, "Pretrain/Loss": 2.0241289138793945, "Pretrain/Loss (Raw)": 1.9320532083511353, "Pretrain/Step": 7815, "Pretrain/Step Time": 8.800691064447165} +{"Pretrain/Learning Rate": 4.149509866902043e-06, "Pretrain/Loss": 2.022061824798584, "Pretrain/Loss (Raw)": 1.7530038356781006, "Pretrain/Step": 7816, "Pretrain/Step Time": 8.798550993204117} +{"Pretrain/Learning Rate": 4.144826910761556e-06, "Pretrain/Loss": 2.0222907066345215, "Pretrain/Loss (Raw)": 2.016029119491577, "Pretrain/Step": 7817, "Pretrain/Step Time": 8.794665792956948} +{"Pretrain/Learning Rate": 4.140146359737895e-06, "Pretrain/Loss": 2.0257158279418945, "Pretrain/Loss (Raw)": 2.444854259490967, "Pretrain/Step": 7818, "Pretrain/Step Time": 8.799114597961307} +{"Pretrain/Learning Rate": 4.135468214370864e-06, "Pretrain/Loss": 2.029050350189209, "Pretrain/Loss (Raw)": 1.8945538997650146, "Pretrain/Step": 7819, "Pretrain/Step Time": 8.803594466298819} +{"Pretrain/Learning Rate": 4.130792475199943e-06, "Pretrain/Loss": 2.028320550918579, "Pretrain/Loss (Raw)": 2.0020289421081543, "Pretrain/Step": 7820, "Pretrain/Step Time": 8.789109801873565} +{"Pretrain/Learning Rate": 4.126119142764379e-06, "Pretrain/Loss": 2.028657913208008, "Pretrain/Loss (Raw)": 2.1292531490325928, "Pretrain/Step": 7821, "Pretrain/Step Time": 8.79479649849236} +{"Pretrain/Learning Rate": 4.121448217603116e-06, "Pretrain/Loss": 2.027170181274414, "Pretrain/Loss (Raw)": 1.920409917831421, "Pretrain/Step": 7822, "Pretrain/Step Time": 8.792297722771764} +{"Pretrain/Learning Rate": 4.116779700254828e-06, "Pretrain/Loss": 2.024644136428833, "Pretrain/Loss (Raw)": 1.8523532152175903, "Pretrain/Step": 7823, "Pretrain/Step Time": 8.796063907444477} +{"Pretrain/Learning Rate": 4.1121135912579044e-06, "Pretrain/Loss": 2.0241429805755615, "Pretrain/Loss (Raw)": 2.013885259628296, "Pretrain/Step": 7824, "Pretrain/Step Time": 8.79599536396563} +{"Pretrain/Learning Rate": 4.1074498911504725e-06, "Pretrain/Loss": 2.0236144065856934, "Pretrain/Loss (Raw)": 2.0534279346466064, "Pretrain/Step": 7825, "Pretrain/Step Time": 8.794313609600067} +{"Pretrain/Learning Rate": 4.102788600470369e-06, "Pretrain/Loss": 2.0236258506774902, "Pretrain/Loss (Raw)": 1.9082860946655273, "Pretrain/Step": 7826, "Pretrain/Step Time": 8.804250802844763} +{"Pretrain/Learning Rate": 4.098129719755156e-06, "Pretrain/Loss": 2.0247111320495605, "Pretrain/Loss (Raw)": 2.0033655166625977, "Pretrain/Step": 7827, "Pretrain/Step Time": 8.798785762861371} +{"Pretrain/Learning Rate": 4.093473249542109e-06, "Pretrain/Loss": 2.0249147415161133, "Pretrain/Loss (Raw)": 2.1207635402679443, "Pretrain/Step": 7828, "Pretrain/Step Time": 8.808037877082825} +{"Pretrain/Learning Rate": 4.0888191903682485e-06, "Pretrain/Loss": 2.0261974334716797, "Pretrain/Loss (Raw)": 2.1403298377990723, "Pretrain/Step": 7829, "Pretrain/Step Time": 8.808071902021766} +{"Pretrain/Learning Rate": 4.084167542770295e-06, "Pretrain/Loss": 2.024996042251587, "Pretrain/Loss (Raw)": 1.8771167993545532, "Pretrain/Step": 7830, "Pretrain/Step Time": 8.808167837560177} +{"Pretrain/Learning Rate": 4.079518307284699e-06, "Pretrain/Loss": 2.0235557556152344, "Pretrain/Loss (Raw)": 2.010937452316284, "Pretrain/Step": 7831, "Pretrain/Step Time": 8.805547893047333} +{"Pretrain/Learning Rate": 4.074871484447626e-06, "Pretrain/Loss": 2.022927761077881, "Pretrain/Loss (Raw)": 1.9262007474899292, "Pretrain/Step": 7832, "Pretrain/Step Time": 8.808144824579358} +{"Pretrain/Learning Rate": 4.070227074794983e-06, "Pretrain/Loss": 2.0252506732940674, "Pretrain/Loss (Raw)": 2.140270948410034, "Pretrain/Step": 7833, "Pretrain/Step Time": 8.806570002809167} +{"Pretrain/Learning Rate": 4.06558507886238e-06, "Pretrain/Loss": 2.0264439582824707, "Pretrain/Loss (Raw)": 2.0614516735076904, "Pretrain/Step": 7834, "Pretrain/Step Time": 8.817279083654284} +{"Pretrain/Learning Rate": 4.0609454971851476e-06, "Pretrain/Loss": 2.0263781547546387, "Pretrain/Loss (Raw)": 2.041231155395508, "Pretrain/Step": 7835, "Pretrain/Step Time": 8.813582517206669} +{"Pretrain/Learning Rate": 4.0563083302983444e-06, "Pretrain/Loss": 2.026601791381836, "Pretrain/Loss (Raw)": 1.9816460609436035, "Pretrain/Step": 7836, "Pretrain/Step Time": 8.818421602249146} +{"Pretrain/Learning Rate": 4.051673578736761e-06, "Pretrain/Loss": 2.0286388397216797, "Pretrain/Loss (Raw)": 2.0937881469726562, "Pretrain/Step": 7837, "Pretrain/Step Time": 8.811007229611278} +{"Pretrain/Learning Rate": 4.047041243034894e-06, "Pretrain/Loss": 2.0276477336883545, "Pretrain/Loss (Raw)": 1.9487484693527222, "Pretrain/Step": 7838, "Pretrain/Step Time": 8.813728408887982} +{"Pretrain/Learning Rate": 4.04241132372696e-06, "Pretrain/Loss": 2.0291972160339355, "Pretrain/Loss (Raw)": 2.080249786376953, "Pretrain/Step": 7839, "Pretrain/Step Time": 8.811172371730208} +{"Pretrain/Learning Rate": 4.037783821346905e-06, "Pretrain/Loss": 2.0291178226470947, "Pretrain/Loss (Raw)": 1.9529179334640503, "Pretrain/Step": 7840, "Pretrain/Step Time": 8.810907419770956} +{"Pretrain/Learning Rate": 4.033158736428402e-06, "Pretrain/Loss": 2.0286221504211426, "Pretrain/Loss (Raw)": 1.875977635383606, "Pretrain/Step": 7841, "Pretrain/Step Time": 8.808770895004272} +{"Pretrain/Learning Rate": 4.0285360695048316e-06, "Pretrain/Loss": 2.0282280445098877, "Pretrain/Loss (Raw)": 2.040041923522949, "Pretrain/Step": 7842, "Pretrain/Step Time": 8.807250956073403} +{"Pretrain/Learning Rate": 4.023915821109306e-06, "Pretrain/Loss": 2.029247283935547, "Pretrain/Loss (Raw)": 2.145482301712036, "Pretrain/Step": 7843, "Pretrain/Step Time": 8.803311945870519} +{"Pretrain/Learning Rate": 4.01929799177464e-06, "Pretrain/Loss": 2.0302093029022217, "Pretrain/Loss (Raw)": 2.076310873031616, "Pretrain/Step": 7844, "Pretrain/Step Time": 8.808249916881323} +{"Pretrain/Learning Rate": 4.014682582033407e-06, "Pretrain/Loss": 2.0309712886810303, "Pretrain/Loss (Raw)": 2.1453473567962646, "Pretrain/Step": 7845, "Pretrain/Step Time": 8.808752860873938} +{"Pretrain/Learning Rate": 4.010069592417853e-06, "Pretrain/Loss": 2.029486894607544, "Pretrain/Loss (Raw)": 2.066991090774536, "Pretrain/Step": 7846, "Pretrain/Step Time": 8.809402212500572} +{"Pretrain/Learning Rate": 4.00545902345999e-06, "Pretrain/Loss": 2.0299673080444336, "Pretrain/Loss (Raw)": 2.1645421981811523, "Pretrain/Step": 7847, "Pretrain/Step Time": 8.803815584629774} +{"Pretrain/Learning Rate": 4.000850875691514e-06, "Pretrain/Loss": 2.0289835929870605, "Pretrain/Loss (Raw)": 1.9468472003936768, "Pretrain/Step": 7848, "Pretrain/Step Time": 8.797651601955295} +{"Pretrain/Learning Rate": 3.9962451496438765e-06, "Pretrain/Loss": 2.0279743671417236, "Pretrain/Loss (Raw)": 1.9252936840057373, "Pretrain/Step": 7849, "Pretrain/Step Time": 8.80020498111844} +{"Pretrain/Learning Rate": 3.99164184584821e-06, "Pretrain/Loss": 2.029172897338867, "Pretrain/Loss (Raw)": 2.1778457164764404, "Pretrain/Step": 7850, "Pretrain/Step Time": 8.806571362540126} +{"Pretrain/Learning Rate": 3.987040964835409e-06, "Pretrain/Loss": 2.029369354248047, "Pretrain/Loss (Raw)": 2.0384397506713867, "Pretrain/Step": 7851, "Pretrain/Step Time": 8.799625849351287} +{"Pretrain/Learning Rate": 3.9824425071360525e-06, "Pretrain/Loss": 2.028106212615967, "Pretrain/Loss (Raw)": 2.0559279918670654, "Pretrain/Step": 7852, "Pretrain/Step Time": 8.799135442823172} +{"Pretrain/Learning Rate": 3.977846473280469e-06, "Pretrain/Loss": 2.0257530212402344, "Pretrain/Loss (Raw)": 1.6602537631988525, "Pretrain/Step": 7853, "Pretrain/Step Time": 8.79546052031219} +{"Pretrain/Learning Rate": 3.973252863798691e-06, "Pretrain/Loss": 2.026440382003784, "Pretrain/Loss (Raw)": 2.0535998344421387, "Pretrain/Step": 7854, "Pretrain/Step Time": 8.794832315295935} +{"Pretrain/Learning Rate": 3.968661679220468e-06, "Pretrain/Loss": 2.028005361557007, "Pretrain/Loss (Raw)": 2.174602746963501, "Pretrain/Step": 7855, "Pretrain/Step Time": 8.794361414387822} +{"Pretrain/Learning Rate": 3.964072920075296e-06, "Pretrain/Loss": 2.0283172130584717, "Pretrain/Loss (Raw)": 2.025197744369507, "Pretrain/Step": 7856, "Pretrain/Step Time": 8.797566069290042} +{"Pretrain/Learning Rate": 3.959486586892344e-06, "Pretrain/Loss": 2.0268936157226562, "Pretrain/Loss (Raw)": 1.8056094646453857, "Pretrain/Step": 7857, "Pretrain/Step Time": 8.798717379570007} +{"Pretrain/Learning Rate": 3.954902680200553e-06, "Pretrain/Loss": 2.0262527465820312, "Pretrain/Loss (Raw)": 2.067869186401367, "Pretrain/Step": 7858, "Pretrain/Step Time": 8.796527415513992} +{"Pretrain/Learning Rate": 3.950321200528548e-06, "Pretrain/Loss": 2.025801181793213, "Pretrain/Loss (Raw)": 2.0538415908813477, "Pretrain/Step": 7859, "Pretrain/Step Time": 8.80379931628704} +{"Pretrain/Learning Rate": 3.9457421484047015e-06, "Pretrain/Loss": 2.025991678237915, "Pretrain/Loss (Raw)": 2.1116864681243896, "Pretrain/Step": 7860, "Pretrain/Step Time": 8.807123990729451} +{"Pretrain/Learning Rate": 3.941165524357071e-06, "Pretrain/Loss": 2.0255680084228516, "Pretrain/Loss (Raw)": 1.982045292854309, "Pretrain/Step": 7861, "Pretrain/Step Time": 8.80172286555171} +{"Pretrain/Learning Rate": 3.936591328913472e-06, "Pretrain/Loss": 2.026074171066284, "Pretrain/Loss (Raw)": 2.040658950805664, "Pretrain/Step": 7862, "Pretrain/Step Time": 8.80706138536334} +{"Pretrain/Learning Rate": 3.932019562601405e-06, "Pretrain/Loss": 2.025655746459961, "Pretrain/Loss (Raw)": 2.1275572776794434, "Pretrain/Step": 7863, "Pretrain/Step Time": 8.807039149105549} +{"Pretrain/Learning Rate": 3.927450225948132e-06, "Pretrain/Loss": 2.0245113372802734, "Pretrain/Loss (Raw)": 1.9605774879455566, "Pretrain/Step": 7864, "Pretrain/Step Time": 8.804993271827698} +{"Pretrain/Learning Rate": 3.922883319480586e-06, "Pretrain/Loss": 2.023848533630371, "Pretrain/Loss (Raw)": 2.0716476440429688, "Pretrain/Step": 7865, "Pretrain/Step Time": 8.803148424252868} +{"Pretrain/Learning Rate": 3.9183188437254576e-06, "Pretrain/Loss": 2.024439811706543, "Pretrain/Loss (Raw)": 2.0446343421936035, "Pretrain/Step": 7866, "Pretrain/Step Time": 8.805924322456121} +{"Pretrain/Learning Rate": 3.9137567992091394e-06, "Pretrain/Loss": 2.025301933288574, "Pretrain/Loss (Raw)": 2.129995346069336, "Pretrain/Step": 7867, "Pretrain/Step Time": 8.804836856201291} +{"Pretrain/Learning Rate": 3.90919718645775e-06, "Pretrain/Loss": 2.0250658988952637, "Pretrain/Loss (Raw)": 1.9826347827911377, "Pretrain/Step": 7868, "Pretrain/Step Time": 8.803416879847646} +{"Pretrain/Learning Rate": 3.904640005997118e-06, "Pretrain/Loss": 2.026150703430176, "Pretrain/Loss (Raw)": 2.149566411972046, "Pretrain/Step": 7869, "Pretrain/Step Time": 8.805803587660193} +{"Pretrain/Learning Rate": 3.900085258352812e-06, "Pretrain/Loss": 2.027071237564087, "Pretrain/Loss (Raw)": 2.0348429679870605, "Pretrain/Step": 7870, "Pretrain/Step Time": 8.810250539332628} +{"Pretrain/Learning Rate": 3.895532944050098e-06, "Pretrain/Loss": 2.029423236846924, "Pretrain/Loss (Raw)": 2.430219888687134, "Pretrain/Step": 7871, "Pretrain/Step Time": 8.80744451470673} +{"Pretrain/Learning Rate": 3.890983063613976e-06, "Pretrain/Loss": 2.0291008949279785, "Pretrain/Loss (Raw)": 1.9263474941253662, "Pretrain/Step": 7872, "Pretrain/Step Time": 8.805734565481544} +{"Pretrain/Learning Rate": 3.886435617569148e-06, "Pretrain/Loss": 2.032869338989258, "Pretrain/Loss (Raw)": 2.2712950706481934, "Pretrain/Step": 7873, "Pretrain/Step Time": 8.808086216449738} +{"Pretrain/Learning Rate": 3.881890606440058e-06, "Pretrain/Loss": 2.034313201904297, "Pretrain/Loss (Raw)": 2.267850399017334, "Pretrain/Step": 7874, "Pretrain/Step Time": 8.806237088516355} +{"Pretrain/Learning Rate": 3.87734803075086e-06, "Pretrain/Loss": 2.0333805084228516, "Pretrain/Loss (Raw)": 2.0060606002807617, "Pretrain/Step": 7875, "Pretrain/Step Time": 8.810282984748483} +{"Pretrain/Learning Rate": 3.872807891025418e-06, "Pretrain/Loss": 2.033121109008789, "Pretrain/Loss (Raw)": 2.0762720108032227, "Pretrain/Step": 7876, "Pretrain/Step Time": 8.80026631243527} +{"Pretrain/Learning Rate": 3.868270187787318e-06, "Pretrain/Loss": 2.0330028533935547, "Pretrain/Loss (Raw)": 2.038336753845215, "Pretrain/Step": 7877, "Pretrain/Step Time": 8.802534149959683} +{"Pretrain/Learning Rate": 3.863734921559884e-06, "Pretrain/Loss": 2.0336756706237793, "Pretrain/Loss (Raw)": 2.1950924396514893, "Pretrain/Step": 7878, "Pretrain/Step Time": 8.802018446847796} +{"Pretrain/Learning Rate": 3.859202092866135e-06, "Pretrain/Loss": 2.0343384742736816, "Pretrain/Loss (Raw)": 1.9861358404159546, "Pretrain/Step": 7879, "Pretrain/Step Time": 8.809551233425736} +{"Pretrain/Learning Rate": 3.854671702228818e-06, "Pretrain/Loss": 2.03344988822937, "Pretrain/Loss (Raw)": 1.9092514514923096, "Pretrain/Step": 7880, "Pretrain/Step Time": 8.808971587568521} +{"Pretrain/Learning Rate": 3.850143750170395e-06, "Pretrain/Loss": 2.0329480171203613, "Pretrain/Loss (Raw)": 1.8841944932937622, "Pretrain/Step": 7881, "Pretrain/Step Time": 8.807899203151464} +{"Pretrain/Learning Rate": 3.8456182372130636e-06, "Pretrain/Loss": 2.0326650142669678, "Pretrain/Loss (Raw)": 2.0801854133605957, "Pretrain/Step": 7882, "Pretrain/Step Time": 8.810153480619192} +{"Pretrain/Learning Rate": 3.841095163878719e-06, "Pretrain/Loss": 2.031662940979004, "Pretrain/Loss (Raw)": 1.8846640586853027, "Pretrain/Step": 7883, "Pretrain/Step Time": 8.80710749514401} +{"Pretrain/Learning Rate": 3.836574530688983e-06, "Pretrain/Loss": 2.0313096046447754, "Pretrain/Loss (Raw)": 2.1831650733947754, "Pretrain/Step": 7884, "Pretrain/Step Time": 8.809482619166374} +{"Pretrain/Learning Rate": 3.832056338165193e-06, "Pretrain/Loss": 2.0287294387817383, "Pretrain/Loss (Raw)": 2.0550031661987305, "Pretrain/Step": 7885, "Pretrain/Step Time": 8.809504879638553} +{"Pretrain/Learning Rate": 3.827540586828418e-06, "Pretrain/Loss": 2.028327465057373, "Pretrain/Loss (Raw)": 1.9868279695510864, "Pretrain/Step": 7886, "Pretrain/Step Time": 8.810631189495325} +{"Pretrain/Learning Rate": 3.823027277199432e-06, "Pretrain/Loss": 2.027575969696045, "Pretrain/Loss (Raw)": 1.936984896659851, "Pretrain/Step": 7887, "Pretrain/Step Time": 8.805174117907882} +{"Pretrain/Learning Rate": 3.818516409798728e-06, "Pretrain/Loss": 2.026590347290039, "Pretrain/Loss (Raw)": 2.024513006210327, "Pretrain/Step": 7888, "Pretrain/Step Time": 8.801717542111874} +{"Pretrain/Learning Rate": 3.814007985146517e-06, "Pretrain/Loss": 2.026801109313965, "Pretrain/Loss (Raw)": 1.978703498840332, "Pretrain/Step": 7889, "Pretrain/Step Time": 8.801580976694822} +{"Pretrain/Learning Rate": 3.8095020037627467e-06, "Pretrain/Loss": 2.0273056030273438, "Pretrain/Loss (Raw)": 2.073028802871704, "Pretrain/Step": 7890, "Pretrain/Step Time": 8.805558428168297} +{"Pretrain/Learning Rate": 3.8049984661670477e-06, "Pretrain/Loss": 2.027240037918091, "Pretrain/Loss (Raw)": 1.9722050428390503, "Pretrain/Step": 7891, "Pretrain/Step Time": 8.789525160565972} +{"Pretrain/Learning Rate": 3.8004973728788057e-06, "Pretrain/Loss": 2.027538776397705, "Pretrain/Loss (Raw)": 2.0769851207733154, "Pretrain/Step": 7892, "Pretrain/Step Time": 8.789786526933312} +{"Pretrain/Learning Rate": 3.795998724417096e-06, "Pretrain/Loss": 2.027590274810791, "Pretrain/Loss (Raw)": 2.056137800216675, "Pretrain/Step": 7893, "Pretrain/Step Time": 8.789142994210124} +{"Pretrain/Learning Rate": 3.7915025213007354e-06, "Pretrain/Loss": 2.0289034843444824, "Pretrain/Loss (Raw)": 2.0993223190307617, "Pretrain/Step": 7894, "Pretrain/Step Time": 8.792946176603436} +{"Pretrain/Learning Rate": 3.7870087640482444e-06, "Pretrain/Loss": 2.0308220386505127, "Pretrain/Loss (Raw)": 2.266730546951294, "Pretrain/Step": 7895, "Pretrain/Step Time": 8.789259813725948} +{"Pretrain/Learning Rate": 3.782517453177853e-06, "Pretrain/Loss": 2.0311570167541504, "Pretrain/Loss (Raw)": 2.035632371902466, "Pretrain/Step": 7896, "Pretrain/Step Time": 8.791502378880978} +{"Pretrain/Learning Rate": 3.778028589207541e-06, "Pretrain/Loss": 2.0302894115448, "Pretrain/Loss (Raw)": 1.9937185049057007, "Pretrain/Step": 7897, "Pretrain/Step Time": 8.786922600120306} +{"Pretrain/Learning Rate": 3.773542172654962e-06, "Pretrain/Loss": 2.0303292274475098, "Pretrain/Loss (Raw)": 1.7725224494934082, "Pretrain/Step": 7898, "Pretrain/Step Time": 8.798655327409506} +{"Pretrain/Learning Rate": 3.769058204037526e-06, "Pretrain/Loss": 2.029395341873169, "Pretrain/Loss (Raw)": 1.9722579717636108, "Pretrain/Step": 7899, "Pretrain/Step Time": 8.795255474746227} +{"Pretrain/Learning Rate": 3.7645766838723395e-06, "Pretrain/Loss": 2.031075954437256, "Pretrain/Loss (Raw)": 2.1114139556884766, "Pretrain/Step": 7900, "Pretrain/Step Time": 8.799495873972774} +{"Pretrain/Learning Rate": 3.7600976126762415e-06, "Pretrain/Loss": 2.030425548553467, "Pretrain/Loss (Raw)": 1.9207050800323486, "Pretrain/Step": 7901, "Pretrain/Step Time": 8.801722139120102} +{"Pretrain/Learning Rate": 3.7556209909657635e-06, "Pretrain/Loss": 2.0292444229125977, "Pretrain/Loss (Raw)": 1.9983075857162476, "Pretrain/Step": 7902, "Pretrain/Step Time": 8.801762899383903} +{"Pretrain/Learning Rate": 3.751146819257187e-06, "Pretrain/Loss": 2.0296692848205566, "Pretrain/Loss (Raw)": 1.9281145334243774, "Pretrain/Step": 7903, "Pretrain/Step Time": 8.801113568246365} +{"Pretrain/Learning Rate": 3.7466750980664795e-06, "Pretrain/Loss": 2.031902551651001, "Pretrain/Loss (Raw)": 2.1626875400543213, "Pretrain/Step": 7904, "Pretrain/Step Time": 8.793972743675113} +{"Pretrain/Learning Rate": 3.7422058279093593e-06, "Pretrain/Loss": 2.0316290855407715, "Pretrain/Loss (Raw)": 2.079153537750244, "Pretrain/Step": 7905, "Pretrain/Step Time": 8.799010708928108} +{"Pretrain/Learning Rate": 3.737739009301222e-06, "Pretrain/Loss": 2.0328426361083984, "Pretrain/Loss (Raw)": 2.119793653488159, "Pretrain/Step": 7906, "Pretrain/Step Time": 8.798171615228057} +{"Pretrain/Learning Rate": 3.73327464275722e-06, "Pretrain/Loss": 2.033564567565918, "Pretrain/Loss (Raw)": 2.048682689666748, "Pretrain/Step": 7907, "Pretrain/Step Time": 8.802237153053284} +{"Pretrain/Learning Rate": 3.728812728792197e-06, "Pretrain/Loss": 2.032836437225342, "Pretrain/Loss (Raw)": 1.850332498550415, "Pretrain/Step": 7908, "Pretrain/Step Time": 8.799627700820565} +{"Pretrain/Learning Rate": 3.7243532679207242e-06, "Pretrain/Loss": 2.033190965652466, "Pretrain/Loss (Raw)": 1.9865113496780396, "Pretrain/Step": 7909, "Pretrain/Step Time": 8.803825652226806} +{"Pretrain/Learning Rate": 3.7198962606570826e-06, "Pretrain/Loss": 2.035149097442627, "Pretrain/Loss (Raw)": 2.0758087635040283, "Pretrain/Step": 7910, "Pretrain/Step Time": 8.800147218629718} +{"Pretrain/Learning Rate": 3.7154417075152826e-06, "Pretrain/Loss": 2.032857894897461, "Pretrain/Loss (Raw)": 1.844772219657898, "Pretrain/Step": 7911, "Pretrain/Step Time": 8.7973612267524} +{"Pretrain/Learning Rate": 3.7109896090090413e-06, "Pretrain/Loss": 2.0338568687438965, "Pretrain/Loss (Raw)": 2.0362627506256104, "Pretrain/Step": 7912, "Pretrain/Step Time": 8.80476202070713} +{"Pretrain/Learning Rate": 3.7065399656517953e-06, "Pretrain/Loss": 2.0358715057373047, "Pretrain/Loss (Raw)": 1.921434760093689, "Pretrain/Step": 7913, "Pretrain/Step Time": 8.802424067631364} +{"Pretrain/Learning Rate": 3.702092777956692e-06, "Pretrain/Loss": 2.037684679031372, "Pretrain/Loss (Raw)": 2.1352930068969727, "Pretrain/Step": 7914, "Pretrain/Step Time": 8.808743743225932} +{"Pretrain/Learning Rate": 3.6976480464366162e-06, "Pretrain/Loss": 2.035102367401123, "Pretrain/Loss (Raw)": 1.735629677772522, "Pretrain/Step": 7915, "Pretrain/Step Time": 8.801014717668295} +{"Pretrain/Learning Rate": 3.693205771604147e-06, "Pretrain/Loss": 2.034924268722534, "Pretrain/Loss (Raw)": 2.070183515548706, "Pretrain/Step": 7916, "Pretrain/Step Time": 8.800125127658248} +{"Pretrain/Learning Rate": 3.68876595397159e-06, "Pretrain/Loss": 2.0347962379455566, "Pretrain/Loss (Raw)": 2.048156499862671, "Pretrain/Step": 7917, "Pretrain/Step Time": 8.801718220114708} +{"Pretrain/Learning Rate": 3.6843285940509594e-06, "Pretrain/Loss": 2.0404062271118164, "Pretrain/Loss (Raw)": 2.6664931774139404, "Pretrain/Step": 7918, "Pretrain/Step Time": 8.79845185764134} +{"Pretrain/Learning Rate": 3.6798936923540027e-06, "Pretrain/Loss": 2.0383734703063965, "Pretrain/Loss (Raw)": 1.945697546005249, "Pretrain/Step": 7919, "Pretrain/Step Time": 8.803509049117565} +{"Pretrain/Learning Rate": 3.6754612493921675e-06, "Pretrain/Loss": 2.0395069122314453, "Pretrain/Loss (Raw)": 2.27286434173584, "Pretrain/Step": 7920, "Pretrain/Step Time": 8.807837661355734} +{"Pretrain/Learning Rate": 3.6710312656766276e-06, "Pretrain/Loss": 2.037416934967041, "Pretrain/Loss (Raw)": 1.926087737083435, "Pretrain/Step": 7921, "Pretrain/Step Time": 8.809951907023787} +{"Pretrain/Learning Rate": 3.6666037417182607e-06, "Pretrain/Loss": 2.038856267929077, "Pretrain/Loss (Raw)": 2.0705511569976807, "Pretrain/Step": 7922, "Pretrain/Step Time": 8.811074500903487} +{"Pretrain/Learning Rate": 3.6621786780276834e-06, "Pretrain/Loss": 2.034959316253662, "Pretrain/Loss (Raw)": 1.416399359703064, "Pretrain/Step": 7923, "Pretrain/Step Time": 8.808654235675931} +{"Pretrain/Learning Rate": 3.6577560751152096e-06, "Pretrain/Loss": 2.0348644256591797, "Pretrain/Loss (Raw)": 1.9403350353240967, "Pretrain/Step": 7924, "Pretrain/Step Time": 8.810472609475255} +{"Pretrain/Learning Rate": 3.65333593349087e-06, "Pretrain/Loss": 2.038139820098877, "Pretrain/Loss (Raw)": 2.165278673171997, "Pretrain/Step": 7925, "Pretrain/Step Time": 8.809920551255345} +{"Pretrain/Learning Rate": 3.6489182536644156e-06, "Pretrain/Loss": 2.035496711730957, "Pretrain/Loss (Raw)": 1.7951360940933228, "Pretrain/Step": 7926, "Pretrain/Step Time": 8.811712557449937} +{"Pretrain/Learning Rate": 3.644503036145322e-06, "Pretrain/Loss": 2.0344083309173584, "Pretrain/Loss (Raw)": 1.9957493543624878, "Pretrain/Step": 7927, "Pretrain/Step Time": 8.809882180765271} +{"Pretrain/Learning Rate": 3.6400902814427707e-06, "Pretrain/Loss": 2.034755229949951, "Pretrain/Loss (Raw)": 1.9315253496170044, "Pretrain/Step": 7928, "Pretrain/Step Time": 8.81195597909391} +{"Pretrain/Learning Rate": 3.6356799900656576e-06, "Pretrain/Loss": 2.032057046890259, "Pretrain/Loss (Raw)": 1.8930919170379639, "Pretrain/Step": 7929, "Pretrain/Step Time": 8.811850169673562} +{"Pretrain/Learning Rate": 3.6312721625225947e-06, "Pretrain/Loss": 2.0313096046447754, "Pretrain/Loss (Raw)": 2.0164761543273926, "Pretrain/Step": 7930, "Pretrain/Step Time": 8.816531149670482} +{"Pretrain/Learning Rate": 3.626866799321929e-06, "Pretrain/Loss": 2.030653953552246, "Pretrain/Loss (Raw)": 1.984548568725586, "Pretrain/Step": 7931, "Pretrain/Step Time": 8.818101175129414} +{"Pretrain/Learning Rate": 3.622463900971687e-06, "Pretrain/Loss": 2.0313167572021484, "Pretrain/Loss (Raw)": 2.0016469955444336, "Pretrain/Step": 7932, "Pretrain/Step Time": 8.81421510130167} +{"Pretrain/Learning Rate": 3.618063467979649e-06, "Pretrain/Loss": 2.0290534496307373, "Pretrain/Loss (Raw)": 1.8400403261184692, "Pretrain/Step": 7933, "Pretrain/Step Time": 8.818269910290837} +{"Pretrain/Learning Rate": 3.6136655008532807e-06, "Pretrain/Loss": 2.0273661613464355, "Pretrain/Loss (Raw)": 2.0087790489196777, "Pretrain/Step": 7934, "Pretrain/Step Time": 8.813947746530175} +{"Pretrain/Learning Rate": 3.6092700000997876e-06, "Pretrain/Loss": 2.0272574424743652, "Pretrain/Loss (Raw)": 2.181102752685547, "Pretrain/Step": 7935, "Pretrain/Step Time": 8.812116416171193} +{"Pretrain/Learning Rate": 3.6048769662260757e-06, "Pretrain/Loss": 2.0276293754577637, "Pretrain/Loss (Raw)": 2.176107168197632, "Pretrain/Step": 7936, "Pretrain/Step Time": 8.811956632882357} +{"Pretrain/Learning Rate": 3.600486399738762e-06, "Pretrain/Loss": 2.026775360107422, "Pretrain/Loss (Raw)": 1.9500632286071777, "Pretrain/Step": 7937, "Pretrain/Step Time": 8.81296762265265} +{"Pretrain/Learning Rate": 3.596098301144207e-06, "Pretrain/Loss": 2.0249457359313965, "Pretrain/Loss (Raw)": 1.9054633378982544, "Pretrain/Step": 7938, "Pretrain/Step Time": 8.811957808211446} +{"Pretrain/Learning Rate": 3.591712670948444e-06, "Pretrain/Loss": 2.024383068084717, "Pretrain/Loss (Raw)": 2.0485100746154785, "Pretrain/Step": 7939, "Pretrain/Step Time": 8.810247577726841} +{"Pretrain/Learning Rate": 3.5873295096572583e-06, "Pretrain/Loss": 2.0235774517059326, "Pretrain/Loss (Raw)": 1.9491162300109863, "Pretrain/Step": 7940, "Pretrain/Step Time": 8.809333307668567} +{"Pretrain/Learning Rate": 3.58294881777613e-06, "Pretrain/Loss": 2.0248231887817383, "Pretrain/Loss (Raw)": 2.114734172821045, "Pretrain/Step": 7941, "Pretrain/Step Time": 8.812134269624949} +{"Pretrain/Learning Rate": 3.578570595810274e-06, "Pretrain/Loss": 2.0253045558929443, "Pretrain/Loss (Raw)": 2.0952773094177246, "Pretrain/Step": 7942, "Pretrain/Step Time": 8.808043299242854} +{"Pretrain/Learning Rate": 3.5741948442645864e-06, "Pretrain/Loss": 2.0271692276000977, "Pretrain/Loss (Raw)": 2.170746088027954, "Pretrain/Step": 7943, "Pretrain/Step Time": 8.806136678904295} +{"Pretrain/Learning Rate": 3.569821563643719e-06, "Pretrain/Loss": 2.029916524887085, "Pretrain/Loss (Raw)": 2.1046359539031982, "Pretrain/Step": 7944, "Pretrain/Step Time": 8.808038517832756} +{"Pretrain/Learning Rate": 3.5654507544520016e-06, "Pretrain/Loss": 2.0310566425323486, "Pretrain/Loss (Raw)": 2.161972999572754, "Pretrain/Step": 7945, "Pretrain/Step Time": 8.805702414363623} +{"Pretrain/Learning Rate": 3.5610824171935205e-06, "Pretrain/Loss": 2.0274600982666016, "Pretrain/Loss (Raw)": 1.9845024347305298, "Pretrain/Step": 7946, "Pretrain/Step Time": 8.803756020963192} +{"Pretrain/Learning Rate": 3.5567165523720275e-06, "Pretrain/Loss": 2.0276408195495605, "Pretrain/Loss (Raw)": 1.9176846742630005, "Pretrain/Step": 7947, "Pretrain/Step Time": 8.802908034995198} +{"Pretrain/Learning Rate": 3.552353160491029e-06, "Pretrain/Loss": 2.0284669399261475, "Pretrain/Loss (Raw)": 2.1077890396118164, "Pretrain/Step": 7948, "Pretrain/Step Time": 8.81405202113092} +{"Pretrain/Learning Rate": 3.54799224205373e-06, "Pretrain/Loss": 2.027629852294922, "Pretrain/Loss (Raw)": 2.022080659866333, "Pretrain/Step": 7949, "Pretrain/Step Time": 8.809072898700833} +{"Pretrain/Learning Rate": 3.5436337975630536e-06, "Pretrain/Loss": 2.0279853343963623, "Pretrain/Loss (Raw)": 1.965907096862793, "Pretrain/Step": 7950, "Pretrain/Step Time": 8.809776386246085} +{"Pretrain/Learning Rate": 3.5392778275216227e-06, "Pretrain/Loss": 2.0285632610321045, "Pretrain/Loss (Raw)": 1.926324486732483, "Pretrain/Step": 7951, "Pretrain/Step Time": 8.805159153416753} +{"Pretrain/Learning Rate": 3.5349243324318076e-06, "Pretrain/Loss": 2.031588315963745, "Pretrain/Loss (Raw)": 2.401106357574463, "Pretrain/Step": 7952, "Pretrain/Step Time": 8.80471209809184} +{"Pretrain/Learning Rate": 3.5305733127956654e-06, "Pretrain/Loss": 2.0322208404541016, "Pretrain/Loss (Raw)": 2.1343801021575928, "Pretrain/Step": 7953, "Pretrain/Step Time": 8.807313734665513} +{"Pretrain/Learning Rate": 3.5262247691149747e-06, "Pretrain/Loss": 2.0341320037841797, "Pretrain/Loss (Raw)": 2.152932643890381, "Pretrain/Step": 7954, "Pretrain/Step Time": 8.79625317081809} +{"Pretrain/Learning Rate": 3.5218787018912263e-06, "Pretrain/Loss": 2.033116340637207, "Pretrain/Loss (Raw)": 1.8733594417572021, "Pretrain/Step": 7955, "Pretrain/Step Time": 8.809748392552137} +{"Pretrain/Learning Rate": 3.517535111625639e-06, "Pretrain/Loss": 2.033433437347412, "Pretrain/Loss (Raw)": 2.1613306999206543, "Pretrain/Step": 7956, "Pretrain/Step Time": 8.80105004273355} +{"Pretrain/Learning Rate": 3.5131939988191335e-06, "Pretrain/Loss": 2.0332255363464355, "Pretrain/Loss (Raw)": 2.1137030124664307, "Pretrain/Step": 7957, "Pretrain/Step Time": 8.798959758132696} +{"Pretrain/Learning Rate": 3.508855363972344e-06, "Pretrain/Loss": 2.03481125831604, "Pretrain/Loss (Raw)": 2.0801360607147217, "Pretrain/Step": 7958, "Pretrain/Step Time": 8.800193453207612} +{"Pretrain/Learning Rate": 3.5045192075856186e-06, "Pretrain/Loss": 2.0348715782165527, "Pretrain/Loss (Raw)": 2.018631935119629, "Pretrain/Step": 7959, "Pretrain/Step Time": 8.800140138715506} +{"Pretrain/Learning Rate": 3.5001855301590336e-06, "Pretrain/Loss": 2.035454750061035, "Pretrain/Loss (Raw)": 2.0008530616760254, "Pretrain/Step": 7960, "Pretrain/Step Time": 8.800009362399578} +{"Pretrain/Learning Rate": 3.495854332192361e-06, "Pretrain/Loss": 2.03240966796875, "Pretrain/Loss (Raw)": 1.750500202178955, "Pretrain/Step": 7961, "Pretrain/Step Time": 8.803439907729626} +{"Pretrain/Learning Rate": 3.491525614185101e-06, "Pretrain/Loss": 2.0317654609680176, "Pretrain/Loss (Raw)": 1.9789857864379883, "Pretrain/Step": 7962, "Pretrain/Step Time": 8.791461519896984} +{"Pretrain/Learning Rate": 3.4871993766364518e-06, "Pretrain/Loss": 2.0315818786621094, "Pretrain/Loss (Raw)": 2.017730951309204, "Pretrain/Step": 7963, "Pretrain/Step Time": 8.793355932459235} +{"Pretrain/Learning Rate": 3.482875620045348e-06, "Pretrain/Loss": 2.0313239097595215, "Pretrain/Loss (Raw)": 1.9486321210861206, "Pretrain/Step": 7964, "Pretrain/Step Time": 8.79081193357706} +{"Pretrain/Learning Rate": 3.4785543449104173e-06, "Pretrain/Loss": 2.0297956466674805, "Pretrain/Loss (Raw)": 1.8981701135635376, "Pretrain/Step": 7965, "Pretrain/Step Time": 8.796606350690126} +{"Pretrain/Learning Rate": 3.474235551730015e-06, "Pretrain/Loss": 2.030942440032959, "Pretrain/Loss (Raw)": 2.0955357551574707, "Pretrain/Step": 7966, "Pretrain/Step Time": 8.792245782911777} +{"Pretrain/Learning Rate": 3.4699192410021953e-06, "Pretrain/Loss": 2.030278444290161, "Pretrain/Loss (Raw)": 1.995253086090088, "Pretrain/Step": 7967, "Pretrain/Step Time": 8.79789979942143} +{"Pretrain/Learning Rate": 3.4656054132247483e-06, "Pretrain/Loss": 2.0307533740997314, "Pretrain/Loss (Raw)": 2.0137012004852295, "Pretrain/Step": 7968, "Pretrain/Step Time": 8.797662386670709} +{"Pretrain/Learning Rate": 3.4612940688951574e-06, "Pretrain/Loss": 2.031827926635742, "Pretrain/Loss (Raw)": 2.0135080814361572, "Pretrain/Step": 7969, "Pretrain/Step Time": 8.799883404746652} +{"Pretrain/Learning Rate": 3.456985208510627e-06, "Pretrain/Loss": 2.0341219902038574, "Pretrain/Loss (Raw)": 2.333702564239502, "Pretrain/Step": 7970, "Pretrain/Step Time": 8.800807368010283} +{"Pretrain/Learning Rate": 3.452678832568071e-06, "Pretrain/Loss": 2.0342843532562256, "Pretrain/Loss (Raw)": 2.166266441345215, "Pretrain/Step": 7971, "Pretrain/Step Time": 8.801177866756916} +{"Pretrain/Learning Rate": 3.448374941564139e-06, "Pretrain/Loss": 2.0348618030548096, "Pretrain/Loss (Raw)": 2.150223731994629, "Pretrain/Step": 7972, "Pretrain/Step Time": 8.796748124063015} +{"Pretrain/Learning Rate": 3.4440735359951515e-06, "Pretrain/Loss": 2.034191846847534, "Pretrain/Loss (Raw)": 2.059584379196167, "Pretrain/Step": 7973, "Pretrain/Step Time": 8.793731002137065} +{"Pretrain/Learning Rate": 3.439774616357183e-06, "Pretrain/Loss": 2.0341196060180664, "Pretrain/Loss (Raw)": 2.057772636413574, "Pretrain/Step": 7974, "Pretrain/Step Time": 8.796151891350746} +{"Pretrain/Learning Rate": 3.4354781831459985e-06, "Pretrain/Loss": 2.031217336654663, "Pretrain/Loss (Raw)": 1.7930411100387573, "Pretrain/Step": 7975, "Pretrain/Step Time": 8.798930512741208} +{"Pretrain/Learning Rate": 3.431184236857088e-06, "Pretrain/Loss": 2.032782793045044, "Pretrain/Loss (Raw)": 2.1472275257110596, "Pretrain/Step": 7976, "Pretrain/Step Time": 8.803637452423573} +{"Pretrain/Learning Rate": 3.426892777985646e-06, "Pretrain/Loss": 2.03340220451355, "Pretrain/Loss (Raw)": 2.0045740604400635, "Pretrain/Step": 7977, "Pretrain/Step Time": 8.802253011614084} +{"Pretrain/Learning Rate": 3.4226038070265837e-06, "Pretrain/Loss": 2.0325722694396973, "Pretrain/Loss (Raw)": 2.071608781814575, "Pretrain/Step": 7978, "Pretrain/Step Time": 8.79455016925931} +{"Pretrain/Learning Rate": 3.418317324474529e-06, "Pretrain/Loss": 2.0336923599243164, "Pretrain/Loss (Raw)": 2.1818313598632812, "Pretrain/Step": 7979, "Pretrain/Step Time": 8.796406080946326} +{"Pretrain/Learning Rate": 3.414033330823815e-06, "Pretrain/Loss": 2.0331130027770996, "Pretrain/Loss (Raw)": 1.981744647026062, "Pretrain/Step": 7980, "Pretrain/Step Time": 8.793583517894149} +{"Pretrain/Learning Rate": 3.409751826568497e-06, "Pretrain/Loss": 2.0353164672851562, "Pretrain/Loss (Raw)": 1.9422842264175415, "Pretrain/Step": 7981, "Pretrain/Step Time": 8.798580914735794} +{"Pretrain/Learning Rate": 3.405472812202326e-06, "Pretrain/Loss": 2.035095691680908, "Pretrain/Loss (Raw)": 2.0253512859344482, "Pretrain/Step": 7982, "Pretrain/Step Time": 8.795385519042611} +{"Pretrain/Learning Rate": 3.4011962882188024e-06, "Pretrain/Loss": 2.035195827484131, "Pretrain/Loss (Raw)": 2.1874091625213623, "Pretrain/Step": 7983, "Pretrain/Step Time": 8.800661962479353} +{"Pretrain/Learning Rate": 3.3969222551110845e-06, "Pretrain/Loss": 2.0353758335113525, "Pretrain/Loss (Raw)": 2.048248529434204, "Pretrain/Step": 7984, "Pretrain/Step Time": 8.796504504978657} +{"Pretrain/Learning Rate": 3.3926507133720973e-06, "Pretrain/Loss": 2.03924560546875, "Pretrain/Loss (Raw)": 2.300959348678589, "Pretrain/Step": 7985, "Pretrain/Step Time": 8.802541553974152} +{"Pretrain/Learning Rate": 3.3883816634944416e-06, "Pretrain/Loss": 2.040208339691162, "Pretrain/Loss (Raw)": 2.1910643577575684, "Pretrain/Step": 7986, "Pretrain/Step Time": 8.80269406735897} +{"Pretrain/Learning Rate": 3.384115105970459e-06, "Pretrain/Loss": 2.0404016971588135, "Pretrain/Loss (Raw)": 2.078620433807373, "Pretrain/Step": 7987, "Pretrain/Step Time": 8.797484820708632} +{"Pretrain/Learning Rate": 3.3798510412921702e-06, "Pretrain/Loss": 2.039757251739502, "Pretrain/Loss (Raw)": 2.0292038917541504, "Pretrain/Step": 7988, "Pretrain/Step Time": 8.795257763937116} +{"Pretrain/Learning Rate": 3.37558946995134e-06, "Pretrain/Loss": 2.039700984954834, "Pretrain/Loss (Raw)": 1.9748197793960571, "Pretrain/Step": 7989, "Pretrain/Step Time": 8.797052040696144} +{"Pretrain/Learning Rate": 3.371330392439434e-06, "Pretrain/Loss": 2.039813995361328, "Pretrain/Loss (Raw)": 2.055145740509033, "Pretrain/Step": 7990, "Pretrain/Step Time": 8.789280308410525} +{"Pretrain/Learning Rate": 3.36707380924762e-06, "Pretrain/Loss": 2.039391040802002, "Pretrain/Loss (Raw)": 2.073420524597168, "Pretrain/Step": 7991, "Pretrain/Step Time": 8.805826777592301} +{"Pretrain/Learning Rate": 3.362819720866789e-06, "Pretrain/Loss": 2.039172649383545, "Pretrain/Loss (Raw)": 1.9326249361038208, "Pretrain/Step": 7992, "Pretrain/Step Time": 8.804218910634518} +{"Pretrain/Learning Rate": 3.358568127787551e-06, "Pretrain/Loss": 2.0396947860717773, "Pretrain/Loss (Raw)": 2.138474464416504, "Pretrain/Step": 7993, "Pretrain/Step Time": 8.80334148928523} +{"Pretrain/Learning Rate": 3.3543190305002136e-06, "Pretrain/Loss": 2.0373826026916504, "Pretrain/Loss (Raw)": 1.748663306236267, "Pretrain/Step": 7994, "Pretrain/Step Time": 8.80440242215991} +{"Pretrain/Learning Rate": 3.350072429494805e-06, "Pretrain/Loss": 2.037677526473999, "Pretrain/Loss (Raw)": 2.1677472591400146, "Pretrain/Step": 7995, "Pretrain/Step Time": 8.804106878116727} +{"Pretrain/Learning Rate": 3.345828325261055e-06, "Pretrain/Loss": 2.038008689880371, "Pretrain/Loss (Raw)": 2.0250208377838135, "Pretrain/Step": 7996, "Pretrain/Step Time": 8.806399706751108} +{"Pretrain/Learning Rate": 3.341586718288425e-06, "Pretrain/Loss": 2.037506580352783, "Pretrain/Loss (Raw)": 2.0853097438812256, "Pretrain/Step": 7997, "Pretrain/Step Time": 8.794584037736058} +{"Pretrain/Learning Rate": 3.3373476090660745e-06, "Pretrain/Loss": 2.036374568939209, "Pretrain/Loss (Raw)": 1.889936089515686, "Pretrain/Step": 7998, "Pretrain/Step Time": 8.807691304013133} +{"Pretrain/Learning Rate": 3.333110998082875e-06, "Pretrain/Loss": 2.0336098670959473, "Pretrain/Loss (Raw)": 2.0763230323791504, "Pretrain/Step": 7999, "Pretrain/Step Time": 8.8074940610677} +{"Pretrain/Learning Rate": 3.3288768858274063e-06, "Pretrain/Loss": 2.0339059829711914, "Pretrain/Loss (Raw)": 1.9642952680587769, "Pretrain/Step": 8000, "Pretrain/Step Time": 8.811067005619407} +{"Pretrain/Learning Rate": 3.3246452727879797e-06, "Pretrain/Loss": 2.0334250926971436, "Pretrain/Loss (Raw)": 2.209704637527466, "Pretrain/Step": 8001, "Pretrain/Step Time": 8.80720304325223} +{"Pretrain/Learning Rate": 3.3204161594525967e-06, "Pretrain/Loss": 2.0315420627593994, "Pretrain/Loss (Raw)": 2.0268261432647705, "Pretrain/Step": 8002, "Pretrain/Step Time": 8.808516366407275} +{"Pretrain/Learning Rate": 3.3161895463089787e-06, "Pretrain/Loss": 2.030832290649414, "Pretrain/Loss (Raw)": 1.9151911735534668, "Pretrain/Step": 8003, "Pretrain/Step Time": 8.809921620413661} +{"Pretrain/Learning Rate": 3.311965433844555e-06, "Pretrain/Loss": 2.0295629501342773, "Pretrain/Loss (Raw)": 1.9138262271881104, "Pretrain/Step": 8004, "Pretrain/Step Time": 8.811247127130628} +{"Pretrain/Learning Rate": 3.3077438225464803e-06, "Pretrain/Loss": 2.030470132827759, "Pretrain/Loss (Raw)": 2.154442310333252, "Pretrain/Step": 8005, "Pretrain/Step Time": 8.814544575288892} +{"Pretrain/Learning Rate": 3.3035247129016065e-06, "Pretrain/Loss": 2.027318000793457, "Pretrain/Loss (Raw)": 1.7916275262832642, "Pretrain/Step": 8006, "Pretrain/Step Time": 8.814857823774219} +{"Pretrain/Learning Rate": 3.2993081053964982e-06, "Pretrain/Loss": 2.0259385108947754, "Pretrain/Loss (Raw)": 1.8095579147338867, "Pretrain/Step": 8007, "Pretrain/Step Time": 8.807638254016638} +{"Pretrain/Learning Rate": 3.295094000517432e-06, "Pretrain/Loss": 2.027080774307251, "Pretrain/Loss (Raw)": 2.0554699897766113, "Pretrain/Step": 8008, "Pretrain/Step Time": 8.808347946032882} +{"Pretrain/Learning Rate": 3.2908823987504085e-06, "Pretrain/Loss": 2.0287575721740723, "Pretrain/Loss (Raw)": 2.0988190174102783, "Pretrain/Step": 8009, "Pretrain/Step Time": 8.808382028713822} +{"Pretrain/Learning Rate": 3.286673300581122e-06, "Pretrain/Loss": 2.027456045150757, "Pretrain/Loss (Raw)": 1.913596749305725, "Pretrain/Step": 8010, "Pretrain/Step Time": 8.806825259700418} +{"Pretrain/Learning Rate": 3.2824667064949883e-06, "Pretrain/Loss": 2.029592275619507, "Pretrain/Loss (Raw)": 2.1580803394317627, "Pretrain/Step": 8011, "Pretrain/Step Time": 8.795644545927644} +{"Pretrain/Learning Rate": 3.2782626169771236e-06, "Pretrain/Loss": 2.0277609825134277, "Pretrain/Loss (Raw)": 1.9487816095352173, "Pretrain/Step": 8012, "Pretrain/Step Time": 8.802904553711414} +{"Pretrain/Learning Rate": 3.2740610325123823e-06, "Pretrain/Loss": 2.028517961502075, "Pretrain/Loss (Raw)": 2.151878833770752, "Pretrain/Step": 8013, "Pretrain/Step Time": 8.80158800072968} +{"Pretrain/Learning Rate": 3.2698619535852877e-06, "Pretrain/Loss": 2.027585744857788, "Pretrain/Loss (Raw)": 1.8675298690795898, "Pretrain/Step": 8014, "Pretrain/Step Time": 8.8034064527601} +{"Pretrain/Learning Rate": 3.2656653806801134e-06, "Pretrain/Loss": 2.02897310256958, "Pretrain/Loss (Raw)": 2.1145565509796143, "Pretrain/Step": 8015, "Pretrain/Step Time": 8.807059301063418} +{"Pretrain/Learning Rate": 3.261471314280817e-06, "Pretrain/Loss": 2.0286989212036133, "Pretrain/Loss (Raw)": 1.989392876625061, "Pretrain/Step": 8016, "Pretrain/Step Time": 8.8145374301821} +{"Pretrain/Learning Rate": 3.2572797548710897e-06, "Pretrain/Loss": 2.028052568435669, "Pretrain/Loss (Raw)": 1.8959827423095703, "Pretrain/Step": 8017, "Pretrain/Step Time": 8.813063835725188} +{"Pretrain/Learning Rate": 3.2530907029343165e-06, "Pretrain/Loss": 2.0280601978302, "Pretrain/Loss (Raw)": 2.074004650115967, "Pretrain/Step": 8018, "Pretrain/Step Time": 8.811311352998018} +{"Pretrain/Learning Rate": 3.2489041589535948e-06, "Pretrain/Loss": 2.02841854095459, "Pretrain/Loss (Raw)": 2.0180747509002686, "Pretrain/Step": 8019, "Pretrain/Step Time": 8.820824317634106} +{"Pretrain/Learning Rate": 3.244720123411743e-06, "Pretrain/Loss": 2.0273799896240234, "Pretrain/Loss (Raw)": 1.9440891742706299, "Pretrain/Step": 8020, "Pretrain/Step Time": 8.82223760895431} +{"Pretrain/Learning Rate": 3.2405385967912787e-06, "Pretrain/Loss": 2.026482343673706, "Pretrain/Loss (Raw)": 1.9412057399749756, "Pretrain/Step": 8021, "Pretrain/Step Time": 8.822206800803542} +{"Pretrain/Learning Rate": 3.2363595795744413e-06, "Pretrain/Loss": 2.026869773864746, "Pretrain/Loss (Raw)": 2.148918628692627, "Pretrain/Step": 8022, "Pretrain/Step Time": 8.823765465989709} +{"Pretrain/Learning Rate": 3.232183072243164e-06, "Pretrain/Loss": 2.022709608078003, "Pretrain/Loss (Raw)": 1.734217882156372, "Pretrain/Step": 8023, "Pretrain/Step Time": 8.820149075239897} +{"Pretrain/Learning Rate": 3.2280090752791175e-06, "Pretrain/Loss": 2.0222249031066895, "Pretrain/Loss (Raw)": 1.9736014604568481, "Pretrain/Step": 8024, "Pretrain/Step Time": 8.821063684299588} +{"Pretrain/Learning Rate": 3.2238375891636504e-06, "Pretrain/Loss": 2.021880865097046, "Pretrain/Loss (Raw)": 1.949687123298645, "Pretrain/Step": 8025, "Pretrain/Step Time": 8.819371635094285} +{"Pretrain/Learning Rate": 3.2196686143778467e-06, "Pretrain/Loss": 2.024463653564453, "Pretrain/Loss (Raw)": 2.1031265258789062, "Pretrain/Step": 8026, "Pretrain/Step Time": 8.81918115913868} +{"Pretrain/Learning Rate": 3.2155021514024857e-06, "Pretrain/Loss": 2.0251970291137695, "Pretrain/Loss (Raw)": 2.0661280155181885, "Pretrain/Step": 8027, "Pretrain/Step Time": 8.817813279107213} +{"Pretrain/Learning Rate": 3.211338200718081e-06, "Pretrain/Loss": 2.025506019592285, "Pretrain/Loss (Raw)": 2.150949239730835, "Pretrain/Step": 8028, "Pretrain/Step Time": 8.815988343209028} +{"Pretrain/Learning Rate": 3.2071767628048145e-06, "Pretrain/Loss": 2.0252161026000977, "Pretrain/Loss (Raw)": 1.8835787773132324, "Pretrain/Step": 8029, "Pretrain/Step Time": 8.814172757789493} +{"Pretrain/Learning Rate": 3.203017838142622e-06, "Pretrain/Loss": 2.025238037109375, "Pretrain/Loss (Raw)": 2.0011472702026367, "Pretrain/Step": 8030, "Pretrain/Step Time": 8.810291770845652} +{"Pretrain/Learning Rate": 3.198861427211122e-06, "Pretrain/Loss": 2.026142120361328, "Pretrain/Loss (Raw)": 2.0438387393951416, "Pretrain/Step": 8031, "Pretrain/Step Time": 8.810201784595847} +{"Pretrain/Learning Rate": 3.1947075304896516e-06, "Pretrain/Loss": 2.02604341506958, "Pretrain/Loss (Raw)": 2.1500256061553955, "Pretrain/Step": 8032, "Pretrain/Step Time": 8.81267373636365} +{"Pretrain/Learning Rate": 3.190556148457255e-06, "Pretrain/Loss": 2.027006149291992, "Pretrain/Loss (Raw)": 2.2023801803588867, "Pretrain/Step": 8033, "Pretrain/Step Time": 8.806730650365353} +{"Pretrain/Learning Rate": 3.1864072815926988e-06, "Pretrain/Loss": 2.0263185501098633, "Pretrain/Loss (Raw)": 2.03177547454834, "Pretrain/Step": 8034, "Pretrain/Step Time": 8.808944255113602} +{"Pretrain/Learning Rate": 3.1822609303744423e-06, "Pretrain/Loss": 2.0266313552856445, "Pretrain/Loss (Raw)": 2.088773250579834, "Pretrain/Step": 8035, "Pretrain/Step Time": 8.802275564521551} +{"Pretrain/Learning Rate": 3.178117095280664e-06, "Pretrain/Loss": 2.027977466583252, "Pretrain/Loss (Raw)": 2.0226311683654785, "Pretrain/Step": 8036, "Pretrain/Step Time": 8.804412242025137} +{"Pretrain/Learning Rate": 3.173975776789245e-06, "Pretrain/Loss": 2.0282139778137207, "Pretrain/Loss (Raw)": 2.016737937927246, "Pretrain/Step": 8037, "Pretrain/Step Time": 8.804206423461437} +{"Pretrain/Learning Rate": 3.1698369753777933e-06, "Pretrain/Loss": 2.0258564949035645, "Pretrain/Loss (Raw)": 1.7740459442138672, "Pretrain/Step": 8038, "Pretrain/Step Time": 8.804920038208365} +{"Pretrain/Learning Rate": 3.165700691523607e-06, "Pretrain/Loss": 2.0276296138763428, "Pretrain/Loss (Raw)": 2.071746826171875, "Pretrain/Step": 8039, "Pretrain/Step Time": 8.802988866344094} +{"Pretrain/Learning Rate": 3.1615669257037045e-06, "Pretrain/Loss": 2.0294647216796875, "Pretrain/Loss (Raw)": 2.271192789077759, "Pretrain/Step": 8040, "Pretrain/Step Time": 8.806815326213837} +{"Pretrain/Learning Rate": 3.1574356783948047e-06, "Pretrain/Loss": 2.02946400642395, "Pretrain/Loss (Raw)": 1.9213334321975708, "Pretrain/Step": 8041, "Pretrain/Step Time": 8.8082867115736} +{"Pretrain/Learning Rate": 3.1533069500733534e-06, "Pretrain/Loss": 2.0287418365478516, "Pretrain/Loss (Raw)": 2.0428147315979004, "Pretrain/Step": 8042, "Pretrain/Step Time": 8.80388941988349} +{"Pretrain/Learning Rate": 3.1491807412154905e-06, "Pretrain/Loss": 2.031710624694824, "Pretrain/Loss (Raw)": 2.115649938583374, "Pretrain/Step": 8043, "Pretrain/Step Time": 8.802221212536097} +{"Pretrain/Learning Rate": 3.145057052297068e-06, "Pretrain/Loss": 2.0314154624938965, "Pretrain/Loss (Raw)": 2.0324184894561768, "Pretrain/Step": 8044, "Pretrain/Step Time": 8.799537045881152} +{"Pretrain/Learning Rate": 3.140935883793644e-06, "Pretrain/Loss": 2.0296096801757812, "Pretrain/Loss (Raw)": 1.817010521888733, "Pretrain/Step": 8045, "Pretrain/Step Time": 8.799610942602158} +{"Pretrain/Learning Rate": 3.136817236180503e-06, "Pretrain/Loss": 2.024740219116211, "Pretrain/Loss (Raw)": 2.0432066917419434, "Pretrain/Step": 8046, "Pretrain/Step Time": 8.799526261165738} +{"Pretrain/Learning Rate": 3.1327011099326233e-06, "Pretrain/Loss": 2.0253489017486572, "Pretrain/Loss (Raw)": 2.0236260890960693, "Pretrain/Step": 8047, "Pretrain/Step Time": 8.793868953362107} +{"Pretrain/Learning Rate": 3.128587505524691e-06, "Pretrain/Loss": 2.023451328277588, "Pretrain/Loss (Raw)": 2.029956817626953, "Pretrain/Step": 8048, "Pretrain/Step Time": 8.790199959650636} +{"Pretrain/Learning Rate": 3.124476423431105e-06, "Pretrain/Loss": 2.023836612701416, "Pretrain/Loss (Raw)": 1.975428581237793, "Pretrain/Step": 8049, "Pretrain/Step Time": 8.7892479673028} +{"Pretrain/Learning Rate": 3.1203678641259836e-06, "Pretrain/Loss": 2.023097515106201, "Pretrain/Loss (Raw)": 1.9759199619293213, "Pretrain/Step": 8050, "Pretrain/Step Time": 8.788949793204665} +{"Pretrain/Learning Rate": 3.116261828083139e-06, "Pretrain/Loss": 2.028817653656006, "Pretrain/Loss (Raw)": 2.1486034393310547, "Pretrain/Step": 8051, "Pretrain/Step Time": 8.787095380946994} +{"Pretrain/Learning Rate": 3.112158315776104e-06, "Pretrain/Loss": 2.0292043685913086, "Pretrain/Loss (Raw)": 1.9898016452789307, "Pretrain/Step": 8052, "Pretrain/Step Time": 8.7859015930444} +{"Pretrain/Learning Rate": 3.108057327678102e-06, "Pretrain/Loss": 2.028062343597412, "Pretrain/Loss (Raw)": 2.019102096557617, "Pretrain/Step": 8053, "Pretrain/Step Time": 8.785794835537672} +{"Pretrain/Learning Rate": 3.1039588642620937e-06, "Pretrain/Loss": 2.0300588607788086, "Pretrain/Loss (Raw)": 2.0506787300109863, "Pretrain/Step": 8054, "Pretrain/Step Time": 8.786023389548063} +{"Pretrain/Learning Rate": 3.099862926000724e-06, "Pretrain/Loss": 2.031121253967285, "Pretrain/Loss (Raw)": 2.1317391395568848, "Pretrain/Step": 8055, "Pretrain/Step Time": 8.786430094391108} +{"Pretrain/Learning Rate": 3.0957695133663616e-06, "Pretrain/Loss": 2.0323166847229004, "Pretrain/Loss (Raw)": 2.0845675468444824, "Pretrain/Step": 8056, "Pretrain/Step Time": 8.789386842399836} +{"Pretrain/Learning Rate": 3.091678626831071e-06, "Pretrain/Loss": 2.034259796142578, "Pretrain/Loss (Raw)": 2.1417946815490723, "Pretrain/Step": 8057, "Pretrain/Step Time": 8.792719194665551} +{"Pretrain/Learning Rate": 3.0875902668666383e-06, "Pretrain/Loss": 2.0342023372650146, "Pretrain/Loss (Raw)": 2.009117603302002, "Pretrain/Step": 8058, "Pretrain/Step Time": 8.790509015321732} +{"Pretrain/Learning Rate": 3.0835044339445536e-06, "Pretrain/Loss": 2.0334632396698, "Pretrain/Loss (Raw)": 1.8899449110031128, "Pretrain/Step": 8059, "Pretrain/Step Time": 8.789245733991265} +{"Pretrain/Learning Rate": 3.079421128536003e-06, "Pretrain/Loss": 2.0331313610076904, "Pretrain/Loss (Raw)": 1.9591766595840454, "Pretrain/Step": 8060, "Pretrain/Step Time": 8.786151826381683} +{"Pretrain/Learning Rate": 3.075340351111908e-06, "Pretrain/Loss": 2.0340209007263184, "Pretrain/Loss (Raw)": 1.9539107084274292, "Pretrain/Step": 8061, "Pretrain/Step Time": 8.791445169597864} +{"Pretrain/Learning Rate": 3.071262102142877e-06, "Pretrain/Loss": 2.0351431369781494, "Pretrain/Loss (Raw)": 2.1523969173431396, "Pretrain/Step": 8062, "Pretrain/Step Time": 8.795219408348203} +{"Pretrain/Learning Rate": 3.0671863820992324e-06, "Pretrain/Loss": 2.0359046459198, "Pretrain/Loss (Raw)": 2.278595447540283, "Pretrain/Step": 8063, "Pretrain/Step Time": 8.79504338093102} +{"Pretrain/Learning Rate": 3.0631131914509977e-06, "Pretrain/Loss": 2.036329984664917, "Pretrain/Loss (Raw)": 2.2305357456207275, "Pretrain/Step": 8064, "Pretrain/Step Time": 8.787660343572497} +{"Pretrain/Learning Rate": 3.0590425306679327e-06, "Pretrain/Loss": 2.0386722087860107, "Pretrain/Loss (Raw)": 2.249889373779297, "Pretrain/Step": 8065, "Pretrain/Step Time": 8.792221551761031} +{"Pretrain/Learning Rate": 3.0549744002194597e-06, "Pretrain/Loss": 2.0392048358917236, "Pretrain/Loss (Raw)": 1.9736251831054688, "Pretrain/Step": 8066, "Pretrain/Step Time": 8.795496501028538} +{"Pretrain/Learning Rate": 3.0509088005747534e-06, "Pretrain/Loss": 2.0379066467285156, "Pretrain/Loss (Raw)": 1.8823262453079224, "Pretrain/Step": 8067, "Pretrain/Step Time": 8.79738081805408} +{"Pretrain/Learning Rate": 3.0468457322026663e-06, "Pretrain/Loss": 2.0384621620178223, "Pretrain/Loss (Raw)": 2.0202417373657227, "Pretrain/Step": 8068, "Pretrain/Step Time": 8.793765883892775} +{"Pretrain/Learning Rate": 3.0427851955717846e-06, "Pretrain/Loss": 2.0405378341674805, "Pretrain/Loss (Raw)": 2.380401134490967, "Pretrain/Step": 8069, "Pretrain/Step Time": 8.80090581253171} +{"Pretrain/Learning Rate": 3.0387271911503728e-06, "Pretrain/Loss": 2.0395383834838867, "Pretrain/Loss (Raw)": 1.9673439264297485, "Pretrain/Step": 8070, "Pretrain/Step Time": 8.802936032414436} +{"Pretrain/Learning Rate": 3.034671719406429e-06, "Pretrain/Loss": 2.0374505519866943, "Pretrain/Loss (Raw)": 1.9035178422927856, "Pretrain/Step": 8071, "Pretrain/Step Time": 8.80245833285153} +{"Pretrain/Learning Rate": 3.0306187808076423e-06, "Pretrain/Loss": 2.0368473529815674, "Pretrain/Loss (Raw)": 2.0274345874786377, "Pretrain/Step": 8072, "Pretrain/Step Time": 8.799553010612726} +{"Pretrain/Learning Rate": 3.0265683758214315e-06, "Pretrain/Loss": 2.0351316928863525, "Pretrain/Loss (Raw)": 1.9423589706420898, "Pretrain/Step": 8073, "Pretrain/Step Time": 8.800981054082513} +{"Pretrain/Learning Rate": 3.022520504914886e-06, "Pretrain/Loss": 2.0357041358947754, "Pretrain/Loss (Raw)": 2.057767152786255, "Pretrain/Step": 8074, "Pretrain/Step Time": 8.799900563433766} +{"Pretrain/Learning Rate": 3.0184751685548435e-06, "Pretrain/Loss": 2.036555767059326, "Pretrain/Loss (Raw)": 2.026700258255005, "Pretrain/Step": 8075, "Pretrain/Step Time": 8.794467149302363} +{"Pretrain/Learning Rate": 3.0144323672078256e-06, "Pretrain/Loss": 2.036115884780884, "Pretrain/Loss (Raw)": 2.051500082015991, "Pretrain/Step": 8076, "Pretrain/Step Time": 8.788898944854736} +{"Pretrain/Learning Rate": 3.0103921013400647e-06, "Pretrain/Loss": 2.0356850624084473, "Pretrain/Loss (Raw)": 1.9669239521026611, "Pretrain/Step": 8077, "Pretrain/Step Time": 8.789945747703314} +{"Pretrain/Learning Rate": 3.0063543714175024e-06, "Pretrain/Loss": 2.0373215675354004, "Pretrain/Loss (Raw)": 2.1753575801849365, "Pretrain/Step": 8078, "Pretrain/Step Time": 8.790117191150784} +{"Pretrain/Learning Rate": 3.0023191779057963e-06, "Pretrain/Loss": 2.0398097038269043, "Pretrain/Loss (Raw)": 2.2448487281799316, "Pretrain/Step": 8079, "Pretrain/Step Time": 8.798662608489394} +{"Pretrain/Learning Rate": 2.9982865212702965e-06, "Pretrain/Loss": 2.0376479625701904, "Pretrain/Loss (Raw)": 2.1243836879730225, "Pretrain/Step": 8080, "Pretrain/Step Time": 8.795563457533717} +{"Pretrain/Learning Rate": 2.994256401976073e-06, "Pretrain/Loss": 2.0358033180236816, "Pretrain/Loss (Raw)": 1.8982735872268677, "Pretrain/Step": 8081, "Pretrain/Step Time": 8.793467972427607} +{"Pretrain/Learning Rate": 2.9902288204878894e-06, "Pretrain/Loss": 2.034590244293213, "Pretrain/Loss (Raw)": 1.9976292848587036, "Pretrain/Step": 8082, "Pretrain/Step Time": 8.794538617134094} +{"Pretrain/Learning Rate": 2.9862037772702356e-06, "Pretrain/Loss": 2.0343215465545654, "Pretrain/Loss (Raw)": 1.8389981985092163, "Pretrain/Step": 8083, "Pretrain/Step Time": 8.789876377210021} +{"Pretrain/Learning Rate": 2.982181272787296e-06, "Pretrain/Loss": 2.0328969955444336, "Pretrain/Loss (Raw)": 1.979015827178955, "Pretrain/Step": 8084, "Pretrain/Step Time": 8.790986457839608} +{"Pretrain/Learning Rate": 2.9781613075029636e-06, "Pretrain/Loss": 2.0327188968658447, "Pretrain/Loss (Raw)": 2.09086275100708, "Pretrain/Step": 8085, "Pretrain/Step Time": 8.795854737982154} +{"Pretrain/Learning Rate": 2.9741438818808366e-06, "Pretrain/Loss": 2.032782554626465, "Pretrain/Loss (Raw)": 2.0883138179779053, "Pretrain/Step": 8086, "Pretrain/Step Time": 8.79118187353015} +{"Pretrain/Learning Rate": 2.9701289963842276e-06, "Pretrain/Loss": 2.0323781967163086, "Pretrain/Loss (Raw)": 1.9668391942977905, "Pretrain/Step": 8087, "Pretrain/Step Time": 8.794578762724996} +{"Pretrain/Learning Rate": 2.966116651476153e-06, "Pretrain/Loss": 2.0322744846343994, "Pretrain/Loss (Raw)": 1.9875982999801636, "Pretrain/Step": 8088, "Pretrain/Step Time": 8.795332957059145} +{"Pretrain/Learning Rate": 2.9621068476193335e-06, "Pretrain/Loss": 2.034484624862671, "Pretrain/Loss (Raw)": 2.033390998840332, "Pretrain/Step": 8089, "Pretrain/Step Time": 8.792203383520246} +{"Pretrain/Learning Rate": 2.958099585276192e-06, "Pretrain/Loss": 2.035773277282715, "Pretrain/Loss (Raw)": 2.1439223289489746, "Pretrain/Step": 8090, "Pretrain/Step Time": 8.78887014836073} +{"Pretrain/Learning Rate": 2.9540948649088767e-06, "Pretrain/Loss": 2.035672187805176, "Pretrain/Loss (Raw)": 2.004810333251953, "Pretrain/Step": 8091, "Pretrain/Step Time": 8.792719041928649} +{"Pretrain/Learning Rate": 2.950092686979225e-06, "Pretrain/Loss": 2.037402629852295, "Pretrain/Loss (Raw)": 2.1701061725616455, "Pretrain/Step": 8092, "Pretrain/Step Time": 8.793703159317374} +{"Pretrain/Learning Rate": 2.9460930519487865e-06, "Pretrain/Loss": 2.039403200149536, "Pretrain/Loss (Raw)": 2.1542694568634033, "Pretrain/Step": 8093, "Pretrain/Step Time": 8.798265120014548} +{"Pretrain/Learning Rate": 2.942095960278815e-06, "Pretrain/Loss": 2.0390219688415527, "Pretrain/Loss (Raw)": 2.0467162132263184, "Pretrain/Step": 8094, "Pretrain/Step Time": 8.800252068787813} +{"Pretrain/Learning Rate": 2.938101412430283e-06, "Pretrain/Loss": 2.038634777069092, "Pretrain/Loss (Raw)": 1.9456884860992432, "Pretrain/Step": 8095, "Pretrain/Step Time": 8.796334967017174} +{"Pretrain/Learning Rate": 2.9341094088638527e-06, "Pretrain/Loss": 2.0393598079681396, "Pretrain/Loss (Raw)": 2.10653018951416, "Pretrain/Step": 8096, "Pretrain/Step Time": 8.801606563851237} +{"Pretrain/Learning Rate": 2.9301199500399057e-06, "Pretrain/Loss": 2.0389974117279053, "Pretrain/Loss (Raw)": 1.9671086072921753, "Pretrain/Step": 8097, "Pretrain/Step Time": 8.790222557261586} +{"Pretrain/Learning Rate": 2.9261330364185184e-06, "Pretrain/Loss": 2.0366158485412598, "Pretrain/Loss (Raw)": 2.028834342956543, "Pretrain/Step": 8098, "Pretrain/Step Time": 8.803695913404226} +{"Pretrain/Learning Rate": 2.9221486684594873e-06, "Pretrain/Loss": 2.0358452796936035, "Pretrain/Loss (Raw)": 2.0676724910736084, "Pretrain/Step": 8099, "Pretrain/Step Time": 8.80482528731227} +{"Pretrain/Learning Rate": 2.9181668466223084e-06, "Pretrain/Loss": 2.0353164672851562, "Pretrain/Loss (Raw)": 2.08255672454834, "Pretrain/Step": 8100, "Pretrain/Step Time": 8.802816905081272} +{"Pretrain/Learning Rate": 2.914187571366175e-06, "Pretrain/Loss": 2.035771369934082, "Pretrain/Loss (Raw)": 2.1177685260772705, "Pretrain/Step": 8101, "Pretrain/Step Time": 8.806897843256593} +{"Pretrain/Learning Rate": 2.9102108431500076e-06, "Pretrain/Loss": 2.033886194229126, "Pretrain/Loss (Raw)": 1.8164883852005005, "Pretrain/Step": 8102, "Pretrain/Step Time": 8.811094496399164} +{"Pretrain/Learning Rate": 2.9062366624324154e-06, "Pretrain/Loss": 2.0355207920074463, "Pretrain/Loss (Raw)": 2.0022706985473633, "Pretrain/Step": 8103, "Pretrain/Step Time": 8.808326423168182} +{"Pretrain/Learning Rate": 2.9022650296717245e-06, "Pretrain/Loss": 2.0331497192382812, "Pretrain/Loss (Raw)": 1.8437317609786987, "Pretrain/Step": 8104, "Pretrain/Step Time": 8.799733912572265} +{"Pretrain/Learning Rate": 2.898295945325949e-06, "Pretrain/Loss": 2.033241033554077, "Pretrain/Loss (Raw)": 2.016261100769043, "Pretrain/Step": 8105, "Pretrain/Step Time": 8.80204595811665} +{"Pretrain/Learning Rate": 2.8943294098528447e-06, "Pretrain/Loss": 2.0330021381378174, "Pretrain/Loss (Raw)": 2.041029453277588, "Pretrain/Step": 8106, "Pretrain/Step Time": 8.806244861334562} +{"Pretrain/Learning Rate": 2.890365423709826e-06, "Pretrain/Loss": 2.031191349029541, "Pretrain/Loss (Raw)": 1.950059413909912, "Pretrain/Step": 8107, "Pretrain/Step Time": 8.80514669418335} +{"Pretrain/Learning Rate": 2.8864039873540583e-06, "Pretrain/Loss": 2.031644821166992, "Pretrain/Loss (Raw)": 2.0397698879241943, "Pretrain/Step": 8108, "Pretrain/Step Time": 8.808121981099248} +{"Pretrain/Learning Rate": 2.8824451012423786e-06, "Pretrain/Loss": 2.033803701400757, "Pretrain/Loss (Raw)": 2.2186245918273926, "Pretrain/Step": 8109, "Pretrain/Step Time": 8.804515574127436} +{"Pretrain/Learning Rate": 2.878488765831361e-06, "Pretrain/Loss": 2.0327885150909424, "Pretrain/Loss (Raw)": 1.8953977823257446, "Pretrain/Step": 8110, "Pretrain/Step Time": 8.801371483132243} +{"Pretrain/Learning Rate": 2.874534981577248e-06, "Pretrain/Loss": 2.0315921306610107, "Pretrain/Loss (Raw)": 2.034266710281372, "Pretrain/Step": 8111, "Pretrain/Step Time": 8.797167617827654} +{"Pretrain/Learning Rate": 2.870583748936026e-06, "Pretrain/Loss": 2.033111810684204, "Pretrain/Loss (Raw)": 2.24279522895813, "Pretrain/Step": 8112, "Pretrain/Step Time": 8.808683602139354} +{"Pretrain/Learning Rate": 2.8666350683633576e-06, "Pretrain/Loss": 2.0311903953552246, "Pretrain/Loss (Raw)": 2.0549778938293457, "Pretrain/Step": 8113, "Pretrain/Step Time": 8.801360135897994} +{"Pretrain/Learning Rate": 2.8626889403146395e-06, "Pretrain/Loss": 2.030059337615967, "Pretrain/Loss (Raw)": 2.0463156700134277, "Pretrain/Step": 8114, "Pretrain/Step Time": 8.806674437597394} +{"Pretrain/Learning Rate": 2.8587453652449386e-06, "Pretrain/Loss": 2.031311511993408, "Pretrain/Loss (Raw)": 2.2389068603515625, "Pretrain/Step": 8115, "Pretrain/Step Time": 8.805358245968819} +{"Pretrain/Learning Rate": 2.8548043436090577e-06, "Pretrain/Loss": 2.030334234237671, "Pretrain/Loss (Raw)": 1.9041231870651245, "Pretrain/Step": 8116, "Pretrain/Step Time": 8.809453409165144} +{"Pretrain/Learning Rate": 2.8508658758614944e-06, "Pretrain/Loss": 2.0298290252685547, "Pretrain/Loss (Raw)": 1.9101423025131226, "Pretrain/Step": 8117, "Pretrain/Step Time": 8.809044949710369} +{"Pretrain/Learning Rate": 2.846929962456446e-06, "Pretrain/Loss": 2.0293731689453125, "Pretrain/Loss (Raw)": 1.9967797994613647, "Pretrain/Step": 8118, "Pretrain/Step Time": 8.816472155973315} +{"Pretrain/Learning Rate": 2.8429966038478196e-06, "Pretrain/Loss": 2.0307908058166504, "Pretrain/Loss (Raw)": 2.2549126148223877, "Pretrain/Step": 8119, "Pretrain/Step Time": 8.800320740789175} +{"Pretrain/Learning Rate": 2.839065800489235e-06, "Pretrain/Loss": 2.031825065612793, "Pretrain/Loss (Raw)": 2.064990282058716, "Pretrain/Step": 8120, "Pretrain/Step Time": 8.802827585488558} +{"Pretrain/Learning Rate": 2.835137552834008e-06, "Pretrain/Loss": 2.0310444831848145, "Pretrain/Loss (Raw)": 2.0385348796844482, "Pretrain/Step": 8121, "Pretrain/Step Time": 8.804805997759104} +{"Pretrain/Learning Rate": 2.8312118613351644e-06, "Pretrain/Loss": 2.0346875190734863, "Pretrain/Loss (Raw)": 2.2149882316589355, "Pretrain/Step": 8122, "Pretrain/Step Time": 8.79898134432733} +{"Pretrain/Learning Rate": 2.8272887264454262e-06, "Pretrain/Loss": 2.033379554748535, "Pretrain/Loss (Raw)": 2.000338554382324, "Pretrain/Step": 8123, "Pretrain/Step Time": 8.799953373149037} +{"Pretrain/Learning Rate": 2.8233681486172393e-06, "Pretrain/Loss": 2.0334482192993164, "Pretrain/Loss (Raw)": 2.0338258743286133, "Pretrain/Step": 8124, "Pretrain/Step Time": 8.798146076500416} +{"Pretrain/Learning Rate": 2.8194501283027366e-06, "Pretrain/Loss": 2.0327775478363037, "Pretrain/Loss (Raw)": 1.9994163513183594, "Pretrain/Step": 8125, "Pretrain/Step Time": 8.802196267992258} +{"Pretrain/Learning Rate": 2.815534665953762e-06, "Pretrain/Loss": 2.0345287322998047, "Pretrain/Loss (Raw)": 2.1141116619110107, "Pretrain/Step": 8126, "Pretrain/Step Time": 8.791349602863193} +{"Pretrain/Learning Rate": 2.8116217620218626e-06, "Pretrain/Loss": 2.033564567565918, "Pretrain/Loss (Raw)": 1.9529184103012085, "Pretrain/Step": 8127, "Pretrain/Step Time": 8.791432749480009} +{"Pretrain/Learning Rate": 2.8077114169583e-06, "Pretrain/Loss": 2.0325183868408203, "Pretrain/Loss (Raw)": 1.8303791284561157, "Pretrain/Step": 8128, "Pretrain/Step Time": 8.786026215180755} +{"Pretrain/Learning Rate": 2.8038036312140333e-06, "Pretrain/Loss": 2.0311737060546875, "Pretrain/Loss (Raw)": 2.0375561714172363, "Pretrain/Step": 8129, "Pretrain/Step Time": 8.79180339537561} +{"Pretrain/Learning Rate": 2.79989840523972e-06, "Pretrain/Loss": 2.031468391418457, "Pretrain/Loss (Raw)": 2.064589023590088, "Pretrain/Step": 8130, "Pretrain/Step Time": 8.789706086739898} +{"Pretrain/Learning Rate": 2.795995739485732e-06, "Pretrain/Loss": 2.0328521728515625, "Pretrain/Loss (Raw)": 2.09232759475708, "Pretrain/Step": 8131, "Pretrain/Step Time": 8.790484676137567} +{"Pretrain/Learning Rate": 2.7920956344021475e-06, "Pretrain/Loss": 2.0348362922668457, "Pretrain/Loss (Raw)": 2.1677680015563965, "Pretrain/Step": 8132, "Pretrain/Step Time": 8.789709942415357} +{"Pretrain/Learning Rate": 2.78819809043874e-06, "Pretrain/Loss": 2.0334649085998535, "Pretrain/Loss (Raw)": 1.9788823127746582, "Pretrain/Step": 8133, "Pretrain/Step Time": 8.791374433785677} +{"Pretrain/Learning Rate": 2.7843031080449944e-06, "Pretrain/Loss": 2.0366764068603516, "Pretrain/Loss (Raw)": 2.202691078186035, "Pretrain/Step": 8134, "Pretrain/Step Time": 8.788198735564947} +{"Pretrain/Learning Rate": 2.780410687670096e-06, "Pretrain/Loss": 2.0381014347076416, "Pretrain/Loss (Raw)": 1.9920079708099365, "Pretrain/Step": 8135, "Pretrain/Step Time": 8.792442159727216} +{"Pretrain/Learning Rate": 2.776520829762941e-06, "Pretrain/Loss": 2.0375869274139404, "Pretrain/Loss (Raw)": 1.9895800352096558, "Pretrain/Step": 8136, "Pretrain/Step Time": 8.796003714203835} +{"Pretrain/Learning Rate": 2.7726335347721263e-06, "Pretrain/Loss": 2.0378594398498535, "Pretrain/Loss (Raw)": 2.1337225437164307, "Pretrain/Step": 8137, "Pretrain/Step Time": 8.797116423025727} +{"Pretrain/Learning Rate": 2.7687488031459484e-06, "Pretrain/Loss": 2.0371696949005127, "Pretrain/Loss (Raw)": 1.8253071308135986, "Pretrain/Step": 8138, "Pretrain/Step Time": 8.797388464212418} +{"Pretrain/Learning Rate": 2.7648666353324136e-06, "Pretrain/Loss": 2.0348477363586426, "Pretrain/Loss (Raw)": 1.86086106300354, "Pretrain/Step": 8139, "Pretrain/Step Time": 8.799089170992374} +{"Pretrain/Learning Rate": 2.7609870317792385e-06, "Pretrain/Loss": 2.0362653732299805, "Pretrain/Loss (Raw)": 2.1302638053894043, "Pretrain/Step": 8140, "Pretrain/Step Time": 8.799587106332183} +{"Pretrain/Learning Rate": 2.757109992933832e-06, "Pretrain/Loss": 2.035017490386963, "Pretrain/Loss (Raw)": 1.992119550704956, "Pretrain/Step": 8141, "Pretrain/Step Time": 8.800040405243635} +{"Pretrain/Learning Rate": 2.753235519243308e-06, "Pretrain/Loss": 2.0369720458984375, "Pretrain/Loss (Raw)": 2.117727041244507, "Pretrain/Step": 8142, "Pretrain/Step Time": 8.794671893119812} +{"Pretrain/Learning Rate": 2.7493636111544985e-06, "Pretrain/Loss": 2.035555362701416, "Pretrain/Loss (Raw)": 1.9332212209701538, "Pretrain/Step": 8143, "Pretrain/Step Time": 8.802098572254181} +{"Pretrain/Learning Rate": 2.745494269113927e-06, "Pretrain/Loss": 2.0374367237091064, "Pretrain/Loss (Raw)": 2.2301783561706543, "Pretrain/Step": 8144, "Pretrain/Step Time": 8.799571273848414} +{"Pretrain/Learning Rate": 2.741627493567822e-06, "Pretrain/Loss": 2.0376930236816406, "Pretrain/Loss (Raw)": 1.9288077354431152, "Pretrain/Step": 8145, "Pretrain/Step Time": 8.801006192341447} +{"Pretrain/Learning Rate": 2.7377632849621164e-06, "Pretrain/Loss": 2.0388360023498535, "Pretrain/Loss (Raw)": 2.220306873321533, "Pretrain/Step": 8146, "Pretrain/Step Time": 8.798513134941459} +{"Pretrain/Learning Rate": 2.7339016437424535e-06, "Pretrain/Loss": 2.0384812355041504, "Pretrain/Loss (Raw)": 1.9726711511611938, "Pretrain/Step": 8147, "Pretrain/Step Time": 8.791983041912317} +{"Pretrain/Learning Rate": 2.7300425703541773e-06, "Pretrain/Loss": 2.039616823196411, "Pretrain/Loss (Raw)": 2.0894367694854736, "Pretrain/Step": 8148, "Pretrain/Step Time": 8.791741237044334} +{"Pretrain/Learning Rate": 2.726186065242331e-06, "Pretrain/Loss": 2.0402755737304688, "Pretrain/Loss (Raw)": 2.025545835494995, "Pretrain/Step": 8149, "Pretrain/Step Time": 8.790600422769785} +{"Pretrain/Learning Rate": 2.7223321288516597e-06, "Pretrain/Loss": 2.038508415222168, "Pretrain/Loss (Raw)": 1.922705054283142, "Pretrain/Step": 8150, "Pretrain/Step Time": 8.786005590111017} +{"Pretrain/Learning Rate": 2.7184807616266323e-06, "Pretrain/Loss": 2.0414817333221436, "Pretrain/Loss (Raw)": 2.1148200035095215, "Pretrain/Step": 8151, "Pretrain/Step Time": 8.787004852667451} +{"Pretrain/Learning Rate": 2.714631964011388e-06, "Pretrain/Loss": 2.0410547256469727, "Pretrain/Loss (Raw)": 1.918900489807129, "Pretrain/Step": 8152, "Pretrain/Step Time": 8.790527256205678} +{"Pretrain/Learning Rate": 2.7107857364498027e-06, "Pretrain/Loss": 2.04172945022583, "Pretrain/Loss (Raw)": 2.03609561920166, "Pretrain/Step": 8153, "Pretrain/Step Time": 8.797843990847468} +{"Pretrain/Learning Rate": 2.7069420793854298e-06, "Pretrain/Loss": 2.042908191680908, "Pretrain/Loss (Raw)": 2.2539825439453125, "Pretrain/Step": 8154, "Pretrain/Step Time": 8.787464506924152} +{"Pretrain/Learning Rate": 2.7031009932615563e-06, "Pretrain/Loss": 2.0431876182556152, "Pretrain/Loss (Raw)": 2.101900339126587, "Pretrain/Step": 8155, "Pretrain/Step Time": 8.79609746672213} +{"Pretrain/Learning Rate": 2.6992624785211334e-06, "Pretrain/Loss": 2.041626453399658, "Pretrain/Loss (Raw)": 1.9511423110961914, "Pretrain/Step": 8156, "Pretrain/Step Time": 8.7958017103374} +{"Pretrain/Learning Rate": 2.6954265356068515e-06, "Pretrain/Loss": 2.043583393096924, "Pretrain/Loss (Raw)": 2.1340415477752686, "Pretrain/Step": 8157, "Pretrain/Step Time": 8.797327481210232} +{"Pretrain/Learning Rate": 2.691593164961084e-06, "Pretrain/Loss": 2.0428125858306885, "Pretrain/Loss (Raw)": 1.9024821519851685, "Pretrain/Step": 8158, "Pretrain/Step Time": 8.800162194296718} +{"Pretrain/Learning Rate": 2.6877623670259115e-06, "Pretrain/Loss": 2.0429043769836426, "Pretrain/Loss (Raw)": 2.0556037425994873, "Pretrain/Step": 8159, "Pretrain/Step Time": 8.803126621991396} +{"Pretrain/Learning Rate": 2.6839341422431165e-06, "Pretrain/Loss": 2.0421924591064453, "Pretrain/Loss (Raw)": 2.058896064758301, "Pretrain/Step": 8160, "Pretrain/Step Time": 8.805762929841876} +{"Pretrain/Learning Rate": 2.6801084910542008e-06, "Pretrain/Loss": 2.040243148803711, "Pretrain/Loss (Raw)": 1.9528695344924927, "Pretrain/Step": 8161, "Pretrain/Step Time": 8.806159559637308} +{"Pretrain/Learning Rate": 2.6762854139003452e-06, "Pretrain/Loss": 2.041482448577881, "Pretrain/Loss (Raw)": 2.190371513366699, "Pretrain/Step": 8162, "Pretrain/Step Time": 8.806539785116911} +{"Pretrain/Learning Rate": 2.6724649112224496e-06, "Pretrain/Loss": 2.0417728424072266, "Pretrain/Loss (Raw)": 2.125994920730591, "Pretrain/Step": 8163, "Pretrain/Step Time": 8.80882647074759} +{"Pretrain/Learning Rate": 2.6686469834611066e-06, "Pretrain/Loss": 2.0426478385925293, "Pretrain/Loss (Raw)": 2.1346020698547363, "Pretrain/Step": 8164, "Pretrain/Step Time": 8.80543322302401} +{"Pretrain/Learning Rate": 2.66483163105663e-06, "Pretrain/Loss": 2.043300151824951, "Pretrain/Loss (Raw)": 2.1002440452575684, "Pretrain/Step": 8165, "Pretrain/Step Time": 8.804119363427162} +{"Pretrain/Learning Rate": 2.6610188544490126e-06, "Pretrain/Loss": 2.0459342002868652, "Pretrain/Loss (Raw)": 2.1111812591552734, "Pretrain/Step": 8166, "Pretrain/Step Time": 8.804613558575511} +{"Pretrain/Learning Rate": 2.657208654077967e-06, "Pretrain/Loss": 2.0467751026153564, "Pretrain/Loss (Raw)": 2.1794097423553467, "Pretrain/Step": 8167, "Pretrain/Step Time": 8.804688725620508} +{"Pretrain/Learning Rate": 2.653401030382896e-06, "Pretrain/Loss": 2.045372486114502, "Pretrain/Loss (Raw)": 2.0916268825531006, "Pretrain/Step": 8168, "Pretrain/Step Time": 8.793517148122191} +{"Pretrain/Learning Rate": 2.649595983802927e-06, "Pretrain/Loss": 2.0481300354003906, "Pretrain/Loss (Raw)": 2.274315118789673, "Pretrain/Step": 8169, "Pretrain/Step Time": 8.792171197012067} +{"Pretrain/Learning Rate": 2.645793514776865e-06, "Pretrain/Loss": 2.0511436462402344, "Pretrain/Loss (Raw)": 2.428560733795166, "Pretrain/Step": 8170, "Pretrain/Step Time": 8.789802446961403} +{"Pretrain/Learning Rate": 2.64199362374323e-06, "Pretrain/Loss": 2.0509791374206543, "Pretrain/Loss (Raw)": 2.0945801734924316, "Pretrain/Step": 8171, "Pretrain/Step Time": 8.788881642743945} +{"Pretrain/Learning Rate": 2.6381963111402423e-06, "Pretrain/Loss": 2.052616596221924, "Pretrain/Loss (Raw)": 2.24204683303833, "Pretrain/Step": 8172, "Pretrain/Step Time": 8.796116694808006} +{"Pretrain/Learning Rate": 2.6344015774058345e-06, "Pretrain/Loss": 2.0541563034057617, "Pretrain/Loss (Raw)": 2.014082431793213, "Pretrain/Step": 8173, "Pretrain/Step Time": 8.798777541145682} +{"Pretrain/Learning Rate": 2.630609422977623e-06, "Pretrain/Loss": 2.053147315979004, "Pretrain/Loss (Raw)": 1.9140325784683228, "Pretrain/Step": 8174, "Pretrain/Step Time": 8.80230651050806} +{"Pretrain/Learning Rate": 2.6268198482929442e-06, "Pretrain/Loss": 2.0544872283935547, "Pretrain/Loss (Raw)": 2.1951448917388916, "Pretrain/Step": 8175, "Pretrain/Step Time": 8.803543636575341} +{"Pretrain/Learning Rate": 2.6230328537888204e-06, "Pretrain/Loss": 2.053361415863037, "Pretrain/Loss (Raw)": 1.8858695030212402, "Pretrain/Step": 8176, "Pretrain/Step Time": 8.804436285048723} +{"Pretrain/Learning Rate": 2.6192484399019947e-06, "Pretrain/Loss": 2.0547068119049072, "Pretrain/Loss (Raw)": 2.1476359367370605, "Pretrain/Step": 8177, "Pretrain/Step Time": 8.804489955306053} +{"Pretrain/Learning Rate": 2.615466607068903e-06, "Pretrain/Loss": 2.0563693046569824, "Pretrain/Loss (Raw)": 2.188713550567627, "Pretrain/Step": 8178, "Pretrain/Step Time": 8.806845447048545} +{"Pretrain/Learning Rate": 2.611687355725681e-06, "Pretrain/Loss": 2.0560173988342285, "Pretrain/Loss (Raw)": 2.103548049926758, "Pretrain/Step": 8179, "Pretrain/Step Time": 8.810163244605064} +{"Pretrain/Learning Rate": 2.6079106863081655e-06, "Pretrain/Loss": 2.0568580627441406, "Pretrain/Loss (Raw)": 2.0973899364471436, "Pretrain/Step": 8180, "Pretrain/Step Time": 8.81134400330484} +{"Pretrain/Learning Rate": 2.604136599251908e-06, "Pretrain/Loss": 2.058957576751709, "Pretrain/Loss (Raw)": 2.287842035293579, "Pretrain/Step": 8181, "Pretrain/Step Time": 8.809530198574066} +{"Pretrain/Learning Rate": 2.600365094992152e-06, "Pretrain/Loss": 2.058389663696289, "Pretrain/Loss (Raw)": 1.9780008792877197, "Pretrain/Step": 8182, "Pretrain/Step Time": 8.802538653835654} +{"Pretrain/Learning Rate": 2.596596173963839e-06, "Pretrain/Loss": 2.0580806732177734, "Pretrain/Loss (Raw)": 2.092207431793213, "Pretrain/Step": 8183, "Pretrain/Step Time": 8.808734046295285} +{"Pretrain/Learning Rate": 2.592829836601629e-06, "Pretrain/Loss": 2.0579655170440674, "Pretrain/Loss (Raw)": 2.069809675216675, "Pretrain/Step": 8184, "Pretrain/Step Time": 8.803282385692} +{"Pretrain/Learning Rate": 2.5890660833398667e-06, "Pretrain/Loss": 2.0547871589660645, "Pretrain/Loss (Raw)": 1.734992504119873, "Pretrain/Step": 8185, "Pretrain/Step Time": 8.7987305726856} +{"Pretrain/Learning Rate": 2.5853049146126076e-06, "Pretrain/Loss": 2.0547757148742676, "Pretrain/Loss (Raw)": 2.0076160430908203, "Pretrain/Step": 8186, "Pretrain/Step Time": 8.799331681802869} +{"Pretrain/Learning Rate": 2.581546330853604e-06, "Pretrain/Loss": 2.0568442344665527, "Pretrain/Loss (Raw)": 2.1547229290008545, "Pretrain/Step": 8187, "Pretrain/Step Time": 8.799291817471385} +{"Pretrain/Learning Rate": 2.5777903324963187e-06, "Pretrain/Loss": 2.057337522506714, "Pretrain/Loss (Raw)": 2.0223262310028076, "Pretrain/Step": 8188, "Pretrain/Step Time": 8.798386173322797} +{"Pretrain/Learning Rate": 2.574036919973913e-06, "Pretrain/Loss": 2.0546603202819824, "Pretrain/Loss (Raw)": 1.6112323999404907, "Pretrain/Step": 8189, "Pretrain/Step Time": 8.789215886965394} +{"Pretrain/Learning Rate": 2.5702860937192403e-06, "Pretrain/Loss": 2.0544800758361816, "Pretrain/Loss (Raw)": 2.1293435096740723, "Pretrain/Step": 8190, "Pretrain/Step Time": 8.801689388230443} +{"Pretrain/Learning Rate": 2.566537854164866e-06, "Pretrain/Loss": 2.052402973175049, "Pretrain/Loss (Raw)": 2.0127129554748535, "Pretrain/Step": 8191, "Pretrain/Step Time": 8.806244734674692} +{"Pretrain/Learning Rate": 2.5627922017430637e-06, "Pretrain/Loss": 2.0511655807495117, "Pretrain/Loss (Raw)": 2.072139024734497, "Pretrain/Step": 8192, "Pretrain/Step Time": 8.808652855455875} +{"Pretrain/Learning Rate": 2.559049136885783e-06, "Pretrain/Loss": 2.048139810562134, "Pretrain/Loss (Raw)": 1.8625962734222412, "Pretrain/Step": 8193, "Pretrain/Step Time": 8.806235872209072} +{"Pretrain/Learning Rate": 2.555308660024708e-06, "Pretrain/Loss": 2.0478219985961914, "Pretrain/Loss (Raw)": 1.9329442977905273, "Pretrain/Step": 8194, "Pretrain/Step Time": 8.805819010362029} +{"Pretrain/Learning Rate": 2.551570771591194e-06, "Pretrain/Loss": 2.0482230186462402, "Pretrain/Loss (Raw)": 1.9336750507354736, "Pretrain/Step": 8195, "Pretrain/Step Time": 8.805593157187104} +{"Pretrain/Learning Rate": 2.54783547201633e-06, "Pretrain/Loss": 2.048337459564209, "Pretrain/Loss (Raw)": 2.0348570346832275, "Pretrain/Step": 8196, "Pretrain/Step Time": 8.805980030447245} +{"Pretrain/Learning Rate": 2.5441027617308684e-06, "Pretrain/Loss": 2.044590950012207, "Pretrain/Loss (Raw)": 1.9008302688598633, "Pretrain/Step": 8197, "Pretrain/Step Time": 8.795994486659765} +{"Pretrain/Learning Rate": 2.540372641165295e-06, "Pretrain/Loss": 2.041499137878418, "Pretrain/Loss (Raw)": 1.5716251134872437, "Pretrain/Step": 8198, "Pretrain/Step Time": 8.797304093837738} +{"Pretrain/Learning Rate": 2.536645110749783e-06, "Pretrain/Loss": 2.041882038116455, "Pretrain/Loss (Raw)": 1.952511191368103, "Pretrain/Step": 8199, "Pretrain/Step Time": 8.795681308954954} +{"Pretrain/Learning Rate": 2.5329201709142074e-06, "Pretrain/Loss": 2.042079448699951, "Pretrain/Loss (Raw)": 2.052715539932251, "Pretrain/Step": 8200, "Pretrain/Step Time": 8.798093682155013} +{"Pretrain/Learning Rate": 2.5291978220881416e-06, "Pretrain/Loss": 2.0436906814575195, "Pretrain/Loss (Raw)": 2.148573398590088, "Pretrain/Step": 8201, "Pretrain/Step Time": 8.797350032255054} +{"Pretrain/Learning Rate": 2.525478064700873e-06, "Pretrain/Loss": 2.0437793731689453, "Pretrain/Loss (Raw)": 2.0691659450531006, "Pretrain/Step": 8202, "Pretrain/Step Time": 8.7968574706465} +{"Pretrain/Learning Rate": 2.5217608991813776e-06, "Pretrain/Loss": 2.0449609756469727, "Pretrain/Loss (Raw)": 2.1779143810272217, "Pretrain/Step": 8203, "Pretrain/Step Time": 8.798644632101059} +{"Pretrain/Learning Rate": 2.5180463259583344e-06, "Pretrain/Loss": 2.0446853637695312, "Pretrain/Loss (Raw)": 2.016244411468506, "Pretrain/Step": 8204, "Pretrain/Step Time": 8.805460084229708} +{"Pretrain/Learning Rate": 2.514334345460126e-06, "Pretrain/Loss": 2.0470309257507324, "Pretrain/Loss (Raw)": 2.2671213150024414, "Pretrain/Step": 8205, "Pretrain/Step Time": 8.805689232423902} +{"Pretrain/Learning Rate": 2.5106249581148406e-06, "Pretrain/Loss": 2.0457043647766113, "Pretrain/Loss (Raw)": 2.0055949687957764, "Pretrain/Step": 8206, "Pretrain/Step Time": 8.809905998408794} +{"Pretrain/Learning Rate": 2.5069181643502552e-06, "Pretrain/Loss": 2.04569935798645, "Pretrain/Loss (Raw)": 2.2441978454589844, "Pretrain/Step": 8207, "Pretrain/Step Time": 8.802373211830854} +{"Pretrain/Learning Rate": 2.503213964593862e-06, "Pretrain/Loss": 2.044009208679199, "Pretrain/Loss (Raw)": 1.908034324645996, "Pretrain/Step": 8208, "Pretrain/Step Time": 8.801875416189432} +{"Pretrain/Learning Rate": 2.4995123592728374e-06, "Pretrain/Loss": 2.0448904037475586, "Pretrain/Loss (Raw)": 2.0110788345336914, "Pretrain/Step": 8209, "Pretrain/Step Time": 8.79999216273427} +{"Pretrain/Learning Rate": 2.495813348814077e-06, "Pretrain/Loss": 2.0450077056884766, "Pretrain/Loss (Raw)": 2.0126426219940186, "Pretrain/Step": 8210, "Pretrain/Step Time": 8.802186822518706} +{"Pretrain/Learning Rate": 2.4921169336441645e-06, "Pretrain/Loss": 2.0465424060821533, "Pretrain/Loss (Raw)": 2.035444974899292, "Pretrain/Step": 8211, "Pretrain/Step Time": 8.802049135789275} +{"Pretrain/Learning Rate": 2.4884231141893864e-06, "Pretrain/Loss": 2.0483760833740234, "Pretrain/Loss (Raw)": 2.213719367980957, "Pretrain/Step": 8212, "Pretrain/Step Time": 8.801968043670058} +{"Pretrain/Learning Rate": 2.48473189087573e-06, "Pretrain/Loss": 2.046398878097534, "Pretrain/Loss (Raw)": 1.8377807140350342, "Pretrain/Step": 8213, "Pretrain/Step Time": 8.801697121933103} +{"Pretrain/Learning Rate": 2.4810432641288933e-06, "Pretrain/Loss": 2.0461246967315674, "Pretrain/Loss (Raw)": 2.053227424621582, "Pretrain/Step": 8214, "Pretrain/Step Time": 8.804013930261135} +{"Pretrain/Learning Rate": 2.4773572343742584e-06, "Pretrain/Loss": 2.046297073364258, "Pretrain/Loss (Raw)": 1.988917350769043, "Pretrain/Step": 8215, "Pretrain/Step Time": 8.806337272748351} +{"Pretrain/Learning Rate": 2.473673802036916e-06, "Pretrain/Loss": 2.0457990169525146, "Pretrain/Loss (Raw)": 1.9238213300704956, "Pretrain/Step": 8216, "Pretrain/Step Time": 8.807535080239177} +{"Pretrain/Learning Rate": 2.4699929675416565e-06, "Pretrain/Loss": 2.046905279159546, "Pretrain/Loss (Raw)": 2.1749958992004395, "Pretrain/Step": 8217, "Pretrain/Step Time": 8.807030050083995} +{"Pretrain/Learning Rate": 2.466314731312977e-06, "Pretrain/Loss": 2.0462756156921387, "Pretrain/Loss (Raw)": 2.063308000564575, "Pretrain/Step": 8218, "Pretrain/Step Time": 8.813237193971872} +{"Pretrain/Learning Rate": 2.4626390937750624e-06, "Pretrain/Loss": 2.0452206134796143, "Pretrain/Loss (Raw)": 1.8697810173034668, "Pretrain/Step": 8219, "Pretrain/Step Time": 8.808890329673886} +{"Pretrain/Learning Rate": 2.4589660553518108e-06, "Pretrain/Loss": 2.0426430702209473, "Pretrain/Loss (Raw)": 1.840171217918396, "Pretrain/Step": 8220, "Pretrain/Step Time": 8.810334896668792} +{"Pretrain/Learning Rate": 2.4552956164668018e-06, "Pretrain/Loss": 2.0427985191345215, "Pretrain/Loss (Raw)": 2.1742136478424072, "Pretrain/Step": 8221, "Pretrain/Step Time": 8.80282662436366} +{"Pretrain/Learning Rate": 2.4516277775433443e-06, "Pretrain/Loss": 2.0439350605010986, "Pretrain/Loss (Raw)": 2.192173480987549, "Pretrain/Step": 8222, "Pretrain/Step Time": 8.805838404223323} +{"Pretrain/Learning Rate": 2.4479625390044226e-06, "Pretrain/Loss": 2.0444252490997314, "Pretrain/Loss (Raw)": 2.008415460586548, "Pretrain/Step": 8223, "Pretrain/Step Time": 8.804933447390795} +{"Pretrain/Learning Rate": 2.444299901272723e-06, "Pretrain/Loss": 2.0441160202026367, "Pretrain/Loss (Raw)": 2.0669503211975098, "Pretrain/Step": 8224, "Pretrain/Step Time": 8.798652425408363} +{"Pretrain/Learning Rate": 2.4406398647706523e-06, "Pretrain/Loss": 2.045815944671631, "Pretrain/Loss (Raw)": 2.184718370437622, "Pretrain/Step": 8225, "Pretrain/Step Time": 8.796972211450338} +{"Pretrain/Learning Rate": 2.4369824299202926e-06, "Pretrain/Loss": 2.0459206104278564, "Pretrain/Loss (Raw)": 2.0422229766845703, "Pretrain/Step": 8226, "Pretrain/Step Time": 8.797297360375524} +{"Pretrain/Learning Rate": 2.433327597143442e-06, "Pretrain/Loss": 2.046454429626465, "Pretrain/Loss (Raw)": 2.135986089706421, "Pretrain/Step": 8227, "Pretrain/Step Time": 8.79630240611732} +{"Pretrain/Learning Rate": 2.4296753668615833e-06, "Pretrain/Loss": 2.0453898906707764, "Pretrain/Loss (Raw)": 1.9463046789169312, "Pretrain/Step": 8228, "Pretrain/Step Time": 8.797256471589208} +{"Pretrain/Learning Rate": 2.4260257394959213e-06, "Pretrain/Loss": 2.043771743774414, "Pretrain/Loss (Raw)": 1.9106471538543701, "Pretrain/Step": 8229, "Pretrain/Step Time": 8.798042420297861} +{"Pretrain/Learning Rate": 2.422378715467344e-06, "Pretrain/Loss": 2.0453927516937256, "Pretrain/Loss (Raw)": 2.02398681640625, "Pretrain/Step": 8230, "Pretrain/Step Time": 8.79466126486659} +{"Pretrain/Learning Rate": 2.4187342951964424e-06, "Pretrain/Loss": 2.0461812019348145, "Pretrain/Loss (Raw)": 2.1032140254974365, "Pretrain/Step": 8231, "Pretrain/Step Time": 8.795179300010204} +{"Pretrain/Learning Rate": 2.4150924791035035e-06, "Pretrain/Loss": 2.0469915866851807, "Pretrain/Loss (Raw)": 1.9474245309829712, "Pretrain/Step": 8232, "Pretrain/Step Time": 8.796264646574855} +{"Pretrain/Learning Rate": 2.411453267608535e-06, "Pretrain/Loss": 2.045684814453125, "Pretrain/Loss (Raw)": 1.8490216732025146, "Pretrain/Step": 8233, "Pretrain/Step Time": 8.803372122347355} +{"Pretrain/Learning Rate": 2.4078166611312044e-06, "Pretrain/Loss": 2.044313907623291, "Pretrain/Loss (Raw)": 1.8655145168304443, "Pretrain/Step": 8234, "Pretrain/Step Time": 8.798047076910734} +{"Pretrain/Learning Rate": 2.40418266009092e-06, "Pretrain/Loss": 2.0437121391296387, "Pretrain/Loss (Raw)": 1.8730385303497314, "Pretrain/Step": 8235, "Pretrain/Step Time": 8.80283896997571} +{"Pretrain/Learning Rate": 2.4005512649067612e-06, "Pretrain/Loss": 2.043302297592163, "Pretrain/Loss (Raw)": 1.9873298406600952, "Pretrain/Step": 8236, "Pretrain/Step Time": 8.805362720042467} +{"Pretrain/Learning Rate": 2.396922475997532e-06, "Pretrain/Loss": 2.042104721069336, "Pretrain/Loss (Raw)": 2.0653274059295654, "Pretrain/Step": 8237, "Pretrain/Step Time": 8.807108273729682} +{"Pretrain/Learning Rate": 2.393296293781702e-06, "Pretrain/Loss": 2.041598320007324, "Pretrain/Loss (Raw)": 1.8305702209472656, "Pretrain/Step": 8238, "Pretrain/Step Time": 8.806678246706724} +{"Pretrain/Learning Rate": 2.3896727186774744e-06, "Pretrain/Loss": 2.0406479835510254, "Pretrain/Loss (Raw)": 1.9126325845718384, "Pretrain/Step": 8239, "Pretrain/Step Time": 8.811514034867287} +{"Pretrain/Learning Rate": 2.386051751102733e-06, "Pretrain/Loss": 2.038256883621216, "Pretrain/Loss (Raw)": 1.9367332458496094, "Pretrain/Step": 8240, "Pretrain/Step Time": 8.801899855956435} +{"Pretrain/Learning Rate": 2.382433391475064e-06, "Pretrain/Loss": 2.0379421710968018, "Pretrain/Loss (Raw)": 2.0147037506103516, "Pretrain/Step": 8241, "Pretrain/Step Time": 8.802431738004088} +{"Pretrain/Learning Rate": 2.3788176402117502e-06, "Pretrain/Loss": 2.036787509918213, "Pretrain/Loss (Raw)": 1.8984938859939575, "Pretrain/Step": 8242, "Pretrain/Step Time": 8.80186857841909} +{"Pretrain/Learning Rate": 2.3752044977297827e-06, "Pretrain/Loss": 2.0356802940368652, "Pretrain/Loss (Raw)": 2.0972180366516113, "Pretrain/Step": 8243, "Pretrain/Step Time": 8.80580941773951} +{"Pretrain/Learning Rate": 2.371593964445845e-06, "Pretrain/Loss": 2.0356504917144775, "Pretrain/Loss (Raw)": 1.9002825021743774, "Pretrain/Step": 8244, "Pretrain/Step Time": 8.800895849242806} +{"Pretrain/Learning Rate": 2.367986040776321e-06, "Pretrain/Loss": 2.0371904373168945, "Pretrain/Loss (Raw)": 2.1072893142700195, "Pretrain/Step": 8245, "Pretrain/Step Time": 8.801245016977191} +{"Pretrain/Learning Rate": 2.3643807271372886e-06, "Pretrain/Loss": 2.0379638671875, "Pretrain/Loss (Raw)": 2.0957722663879395, "Pretrain/Step": 8246, "Pretrain/Step Time": 8.793296456336975} +{"Pretrain/Learning Rate": 2.360778023944535e-06, "Pretrain/Loss": 2.037475109100342, "Pretrain/Loss (Raw)": 2.19233775138855, "Pretrain/Step": 8247, "Pretrain/Step Time": 8.802880005910993} +{"Pretrain/Learning Rate": 2.3571779316135413e-06, "Pretrain/Loss": 2.037149429321289, "Pretrain/Loss (Raw)": 2.023282527923584, "Pretrain/Step": 8248, "Pretrain/Step Time": 8.804869597777724} +{"Pretrain/Learning Rate": 2.3535804505594837e-06, "Pretrain/Loss": 2.0365519523620605, "Pretrain/Loss (Raw)": 1.9620789289474487, "Pretrain/Step": 8249, "Pretrain/Step Time": 8.802633177489042} +{"Pretrain/Learning Rate": 2.3499855811972393e-06, "Pretrain/Loss": 2.0339932441711426, "Pretrain/Loss (Raw)": 1.8874605894088745, "Pretrain/Step": 8250, "Pretrain/Step Time": 8.810662183910608} +{"Pretrain/Learning Rate": 2.34639332394139e-06, "Pretrain/Loss": 2.0333874225616455, "Pretrain/Loss (Raw)": 1.9227938652038574, "Pretrain/Step": 8251, "Pretrain/Step Time": 8.810721430927515} +{"Pretrain/Learning Rate": 2.3428036792062124e-06, "Pretrain/Loss": 2.03169322013855, "Pretrain/Loss (Raw)": 1.8169726133346558, "Pretrain/Step": 8252, "Pretrain/Step Time": 8.812979711219668} +{"Pretrain/Learning Rate": 2.3392166474056758e-06, "Pretrain/Loss": 2.0320382118225098, "Pretrain/Loss (Raw)": 2.043553113937378, "Pretrain/Step": 8253, "Pretrain/Step Time": 8.813842823728919} +{"Pretrain/Learning Rate": 2.3356322289534547e-06, "Pretrain/Loss": 2.0322952270507812, "Pretrain/Loss (Raw)": 2.147050142288208, "Pretrain/Step": 8254, "Pretrain/Step Time": 8.808871764689684} +{"Pretrain/Learning Rate": 2.332050424262927e-06, "Pretrain/Loss": 2.0314087867736816, "Pretrain/Loss (Raw)": 1.83943772315979, "Pretrain/Step": 8255, "Pretrain/Step Time": 8.81355755776167} +{"Pretrain/Learning Rate": 2.3284712337471593e-06, "Pretrain/Loss": 2.0324463844299316, "Pretrain/Loss (Raw)": 1.9631813764572144, "Pretrain/Step": 8256, "Pretrain/Step Time": 8.810745503753424} +{"Pretrain/Learning Rate": 2.3248946578189186e-06, "Pretrain/Loss": 2.0321624279022217, "Pretrain/Loss (Raw)": 2.001201629638672, "Pretrain/Step": 8257, "Pretrain/Step Time": 8.814004605636} +{"Pretrain/Learning Rate": 2.321320696890672e-06, "Pretrain/Loss": 2.03122615814209, "Pretrain/Loss (Raw)": 1.9447746276855469, "Pretrain/Step": 8258, "Pretrain/Step Time": 8.813978811725974} +{"Pretrain/Learning Rate": 2.317749351374593e-06, "Pretrain/Loss": 2.031266212463379, "Pretrain/Loss (Raw)": 2.0974416732788086, "Pretrain/Step": 8259, "Pretrain/Step Time": 8.812870044261217} +{"Pretrain/Learning Rate": 2.3141806216825405e-06, "Pretrain/Loss": 2.0299596786499023, "Pretrain/Loss (Raw)": 2.0005221366882324, "Pretrain/Step": 8260, "Pretrain/Step Time": 8.810800796374679} +{"Pretrain/Learning Rate": 2.310614508226078e-06, "Pretrain/Loss": 2.0320425033569336, "Pretrain/Loss (Raw)": 2.245466470718384, "Pretrain/Step": 8261, "Pretrain/Step Time": 8.807581059634686} +{"Pretrain/Learning Rate": 2.3070510114164613e-06, "Pretrain/Loss": 2.0305354595184326, "Pretrain/Loss (Raw)": 2.0098230838775635, "Pretrain/Step": 8262, "Pretrain/Step Time": 8.808931374922395} +{"Pretrain/Learning Rate": 2.303490131664657e-06, "Pretrain/Loss": 2.0304489135742188, "Pretrain/Loss (Raw)": 1.9809374809265137, "Pretrain/Step": 8263, "Pretrain/Step Time": 8.8075482994318} +{"Pretrain/Learning Rate": 2.299931869381322e-06, "Pretrain/Loss": 2.027772903442383, "Pretrain/Loss (Raw)": 1.6470223665237427, "Pretrain/Step": 8264, "Pretrain/Step Time": 8.806698022410274} +{"Pretrain/Learning Rate": 2.2963762249768067e-06, "Pretrain/Loss": 2.026576519012451, "Pretrain/Loss (Raw)": 1.9806039333343506, "Pretrain/Step": 8265, "Pretrain/Step Time": 8.807162944227457} +{"Pretrain/Learning Rate": 2.2928231988611716e-06, "Pretrain/Loss": 2.0282983779907227, "Pretrain/Loss (Raw)": 2.045715093612671, "Pretrain/Step": 8266, "Pretrain/Step Time": 8.807781260460615} +{"Pretrain/Learning Rate": 2.289272791444166e-06, "Pretrain/Loss": 2.030552864074707, "Pretrain/Loss (Raw)": 2.149430513381958, "Pretrain/Step": 8267, "Pretrain/Step Time": 8.80686873756349} +{"Pretrain/Learning Rate": 2.285725003135239e-06, "Pretrain/Loss": 2.029715061187744, "Pretrain/Loss (Raw)": 2.023017644882202, "Pretrain/Step": 8268, "Pretrain/Step Time": 8.806696807965636} +{"Pretrain/Learning Rate": 2.2821798343435314e-06, "Pretrain/Loss": 2.030022144317627, "Pretrain/Loss (Raw)": 2.031425952911377, "Pretrain/Step": 8269, "Pretrain/Step Time": 8.806340657174587} +{"Pretrain/Learning Rate": 2.2786372854779e-06, "Pretrain/Loss": 2.0288660526275635, "Pretrain/Loss (Raw)": 1.9697458744049072, "Pretrain/Step": 8270, "Pretrain/Step Time": 8.808480337262154} +{"Pretrain/Learning Rate": 2.2750973569468843e-06, "Pretrain/Loss": 2.031487464904785, "Pretrain/Loss (Raw)": 2.268742084503174, "Pretrain/Step": 8271, "Pretrain/Step Time": 8.798575529828668} +{"Pretrain/Learning Rate": 2.2715600491587245e-06, "Pretrain/Loss": 2.028198003768921, "Pretrain/Loss (Raw)": 1.8091379404067993, "Pretrain/Step": 8272, "Pretrain/Step Time": 8.796282269060612} +{"Pretrain/Learning Rate": 2.268025362521353e-06, "Pretrain/Loss": 2.029515266418457, "Pretrain/Loss (Raw)": 2.0974221229553223, "Pretrain/Step": 8273, "Pretrain/Step Time": 8.798557806760073} +{"Pretrain/Learning Rate": 2.264493297442424e-06, "Pretrain/Loss": 2.0286693572998047, "Pretrain/Loss (Raw)": 2.1120505332946777, "Pretrain/Step": 8274, "Pretrain/Step Time": 8.797016054391861} +{"Pretrain/Learning Rate": 2.260963854329254e-06, "Pretrain/Loss": 2.03090763092041, "Pretrain/Loss (Raw)": 2.2591521739959717, "Pretrain/Step": 8275, "Pretrain/Step Time": 8.804731231182814} +{"Pretrain/Learning Rate": 2.2574370335888854e-06, "Pretrain/Loss": 2.0292093753814697, "Pretrain/Loss (Raw)": 1.872063159942627, "Pretrain/Step": 8276, "Pretrain/Step Time": 8.804610796272755} +{"Pretrain/Learning Rate": 2.2539128356280387e-06, "Pretrain/Loss": 2.02998948097229, "Pretrain/Loss (Raw)": 2.125380039215088, "Pretrain/Step": 8277, "Pretrain/Step Time": 8.803145166486502} +{"Pretrain/Learning Rate": 2.2503912608531576e-06, "Pretrain/Loss": 2.032686471939087, "Pretrain/Loss (Raw)": 2.267937183380127, "Pretrain/Step": 8278, "Pretrain/Step Time": 8.803341902792454} +{"Pretrain/Learning Rate": 2.2468723096703447e-06, "Pretrain/Loss": 2.0309057235717773, "Pretrain/Loss (Raw)": 1.8868807554244995, "Pretrain/Step": 8279, "Pretrain/Step Time": 8.8037124350667} +{"Pretrain/Learning Rate": 2.24335598248544e-06, "Pretrain/Loss": 2.0323634147644043, "Pretrain/Loss (Raw)": 2.105478286743164, "Pretrain/Step": 8280, "Pretrain/Step Time": 8.801312759518623} +{"Pretrain/Learning Rate": 2.239842279703952e-06, "Pretrain/Loss": 2.031726360321045, "Pretrain/Loss (Raw)": 1.9545812606811523, "Pretrain/Step": 8281, "Pretrain/Step Time": 8.794409709051251} +{"Pretrain/Learning Rate": 2.2363312017311094e-06, "Pretrain/Loss": 2.0295112133026123, "Pretrain/Loss (Raw)": 1.970445990562439, "Pretrain/Step": 8282, "Pretrain/Step Time": 8.799862494692206} +{"Pretrain/Learning Rate": 2.2328227489718106e-06, "Pretrain/Loss": 2.0286645889282227, "Pretrain/Loss (Raw)": 1.9934978485107422, "Pretrain/Step": 8283, "Pretrain/Step Time": 8.792450712993741} +{"Pretrain/Learning Rate": 2.229316921830679e-06, "Pretrain/Loss": 2.0277180671691895, "Pretrain/Loss (Raw)": 1.8300203084945679, "Pretrain/Step": 8284, "Pretrain/Step Time": 8.79208111949265} +{"Pretrain/Learning Rate": 2.2258137207120165e-06, "Pretrain/Loss": 2.0281808376312256, "Pretrain/Loss (Raw)": 2.193255662918091, "Pretrain/Step": 8285, "Pretrain/Step Time": 8.796255154535174} +{"Pretrain/Learning Rate": 2.222313146019833e-06, "Pretrain/Loss": 2.0296592712402344, "Pretrain/Loss (Raw)": 2.0917165279388428, "Pretrain/Step": 8286, "Pretrain/Step Time": 8.793870436027646} +{"Pretrain/Learning Rate": 2.2188151981578252e-06, "Pretrain/Loss": 2.0295825004577637, "Pretrain/Loss (Raw)": 2.045771598815918, "Pretrain/Step": 8287, "Pretrain/Step Time": 8.79018628038466} +{"Pretrain/Learning Rate": 2.215319877529404e-06, "Pretrain/Loss": 2.0295963287353516, "Pretrain/Loss (Raw)": 2.0606558322906494, "Pretrain/Step": 8288, "Pretrain/Step Time": 8.78404463455081} +{"Pretrain/Learning Rate": 2.211827184537657e-06, "Pretrain/Loss": 2.028978109359741, "Pretrain/Loss (Raw)": 1.8737725019454956, "Pretrain/Step": 8289, "Pretrain/Step Time": 8.791110957041383} +{"Pretrain/Learning Rate": 2.2083371195853796e-06, "Pretrain/Loss": 2.028782367706299, "Pretrain/Loss (Raw)": 2.165297508239746, "Pretrain/Step": 8290, "Pretrain/Step Time": 8.78784386627376} +{"Pretrain/Learning Rate": 2.204849683075061e-06, "Pretrain/Loss": 2.028398036956787, "Pretrain/Loss (Raw)": 2.076791286468506, "Pretrain/Step": 8291, "Pretrain/Step Time": 8.790181221440434} +{"Pretrain/Learning Rate": 2.2013648754088954e-06, "Pretrain/Loss": 2.0283966064453125, "Pretrain/Loss (Raw)": 2.134450912475586, "Pretrain/Step": 8292, "Pretrain/Step Time": 8.789925675839186} +{"Pretrain/Learning Rate": 2.1978826969887624e-06, "Pretrain/Loss": 2.0281248092651367, "Pretrain/Loss (Raw)": 2.0654215812683105, "Pretrain/Step": 8293, "Pretrain/Step Time": 8.79017305932939} +{"Pretrain/Learning Rate": 2.1944031482162425e-06, "Pretrain/Loss": 2.0280919075012207, "Pretrain/Loss (Raw)": 2.106999158859253, "Pretrain/Step": 8294, "Pretrain/Step Time": 8.79122705757618} +{"Pretrain/Learning Rate": 2.1909262294926126e-06, "Pretrain/Loss": 2.0278420448303223, "Pretrain/Loss (Raw)": 2.147430419921875, "Pretrain/Step": 8295, "Pretrain/Step Time": 8.789657896384597} +{"Pretrain/Learning Rate": 2.1874519412188545e-06, "Pretrain/Loss": 2.0269711017608643, "Pretrain/Loss (Raw)": 1.9801229238510132, "Pretrain/Step": 8296, "Pretrain/Step Time": 8.796089820563793} +{"Pretrain/Learning Rate": 2.1839802837956336e-06, "Pretrain/Loss": 2.0255818367004395, "Pretrain/Loss (Raw)": 2.0965144634246826, "Pretrain/Step": 8297, "Pretrain/Step Time": 8.796799451112747} +{"Pretrain/Learning Rate": 2.180511257623319e-06, "Pretrain/Loss": 2.0229363441467285, "Pretrain/Loss (Raw)": 2.089949369430542, "Pretrain/Step": 8298, "Pretrain/Step Time": 8.7988028395921} +{"Pretrain/Learning Rate": 2.1770448631019708e-06, "Pretrain/Loss": 2.021013021469116, "Pretrain/Loss (Raw)": 1.8483750820159912, "Pretrain/Step": 8299, "Pretrain/Step Time": 8.799958793446422} +{"Pretrain/Learning Rate": 2.1735811006313583e-06, "Pretrain/Loss": 2.019865036010742, "Pretrain/Loss (Raw)": 2.0950889587402344, "Pretrain/Step": 8300, "Pretrain/Step Time": 8.799699377268553} +{"Pretrain/Learning Rate": 2.170119970610937e-06, "Pretrain/Loss": 2.020200252532959, "Pretrain/Loss (Raw)": 2.0570058822631836, "Pretrain/Step": 8301, "Pretrain/Step Time": 8.79595241136849} +{"Pretrain/Learning Rate": 2.1666614734398573e-06, "Pretrain/Loss": 2.0219850540161133, "Pretrain/Loss (Raw)": 2.142463207244873, "Pretrain/Step": 8302, "Pretrain/Step Time": 8.79462737031281} +{"Pretrain/Learning Rate": 2.163205609516966e-06, "Pretrain/Loss": 2.018585205078125, "Pretrain/Loss (Raw)": 1.7599623203277588, "Pretrain/Step": 8303, "Pretrain/Step Time": 8.796000681817532} +{"Pretrain/Learning Rate": 2.1597523792408176e-06, "Pretrain/Loss": 2.0198752880096436, "Pretrain/Loss (Raw)": 2.051018714904785, "Pretrain/Step": 8304, "Pretrain/Step Time": 8.795427398756146} +{"Pretrain/Learning Rate": 2.156301783009654e-06, "Pretrain/Loss": 2.018157482147217, "Pretrain/Loss (Raw)": 1.9277660846710205, "Pretrain/Step": 8305, "Pretrain/Step Time": 8.799383137375116} +{"Pretrain/Learning Rate": 2.1528538212214066e-06, "Pretrain/Loss": 2.0175232887268066, "Pretrain/Loss (Raw)": 2.107515811920166, "Pretrain/Step": 8306, "Pretrain/Step Time": 8.794347701594234} +{"Pretrain/Learning Rate": 2.1494084942737193e-06, "Pretrain/Loss": 2.016082286834717, "Pretrain/Loss (Raw)": 1.9190936088562012, "Pretrain/Step": 8307, "Pretrain/Step Time": 8.796244386583567} +{"Pretrain/Learning Rate": 2.1459658025639208e-06, "Pretrain/Loss": 2.0166099071502686, "Pretrain/Loss (Raw)": 2.1649556159973145, "Pretrain/Step": 8308, "Pretrain/Step Time": 8.796179858967662} +{"Pretrain/Learning Rate": 2.142525746489038e-06, "Pretrain/Loss": 2.014775276184082, "Pretrain/Loss (Raw)": 2.052992105484009, "Pretrain/Step": 8309, "Pretrain/Step Time": 8.795744180679321} +{"Pretrain/Learning Rate": 2.1390883264457903e-06, "Pretrain/Loss": 2.014453649520874, "Pretrain/Loss (Raw)": 1.9368523359298706, "Pretrain/Step": 8310, "Pretrain/Step Time": 8.79345791041851} +{"Pretrain/Learning Rate": 2.135653542830604e-06, "Pretrain/Loss": 2.0145986080169678, "Pretrain/Loss (Raw)": 2.110745906829834, "Pretrain/Step": 8311, "Pretrain/Step Time": 8.791206369176507} +{"Pretrain/Learning Rate": 2.132221396039591e-06, "Pretrain/Loss": 2.0133252143859863, "Pretrain/Loss (Raw)": 1.9068324565887451, "Pretrain/Step": 8312, "Pretrain/Step Time": 8.791765986010432} +{"Pretrain/Learning Rate": 2.1287918864685645e-06, "Pretrain/Loss": 2.012993812561035, "Pretrain/Loss (Raw)": 1.6925561428070068, "Pretrain/Step": 8313, "Pretrain/Step Time": 8.790289599448442} +{"Pretrain/Learning Rate": 2.1253650145130254e-06, "Pretrain/Loss": 2.012651205062866, "Pretrain/Loss (Raw)": 1.9637681245803833, "Pretrain/Step": 8314, "Pretrain/Step Time": 8.79317551665008} +{"Pretrain/Learning Rate": 2.121940780568188e-06, "Pretrain/Loss": 2.011337995529175, "Pretrain/Loss (Raw)": 1.986636757850647, "Pretrain/Step": 8315, "Pretrain/Step Time": 8.794314617291093} +{"Pretrain/Learning Rate": 2.1185191850289386e-06, "Pretrain/Loss": 2.011172294616699, "Pretrain/Loss (Raw)": 2.0010972023010254, "Pretrain/Step": 8316, "Pretrain/Step Time": 8.79623118788004} +{"Pretrain/Learning Rate": 2.115100228289882e-06, "Pretrain/Loss": 2.015225410461426, "Pretrain/Loss (Raw)": 2.130025625228882, "Pretrain/Step": 8317, "Pretrain/Step Time": 8.796082442626357} +{"Pretrain/Learning Rate": 2.111683910745299e-06, "Pretrain/Loss": 2.014270067214966, "Pretrain/Loss (Raw)": 2.007080078125, "Pretrain/Step": 8318, "Pretrain/Step Time": 8.78715024702251} +{"Pretrain/Learning Rate": 2.108270232789192e-06, "Pretrain/Loss": 2.015650749206543, "Pretrain/Loss (Raw)": 2.1894125938415527, "Pretrain/Step": 8319, "Pretrain/Step Time": 8.78088585473597} +{"Pretrain/Learning Rate": 2.10485919481522e-06, "Pretrain/Loss": 2.0153307914733887, "Pretrain/Loss (Raw)": 2.031219244003296, "Pretrain/Step": 8320, "Pretrain/Step Time": 8.789558129385114} +{"Pretrain/Learning Rate": 2.101450797216775e-06, "Pretrain/Loss": 2.0173592567443848, "Pretrain/Loss (Raw)": 2.122241258621216, "Pretrain/Step": 8321, "Pretrain/Step Time": 8.788011526688933} +{"Pretrain/Learning Rate": 2.098045040386923e-06, "Pretrain/Loss": 2.018123149871826, "Pretrain/Loss (Raw)": 2.0306954383850098, "Pretrain/Step": 8322, "Pretrain/Step Time": 8.789449514821172} +{"Pretrain/Learning Rate": 2.0946419247184435e-06, "Pretrain/Loss": 2.0182859897613525, "Pretrain/Loss (Raw)": 1.9545400142669678, "Pretrain/Step": 8323, "Pretrain/Step Time": 8.79128690995276} +{"Pretrain/Learning Rate": 2.0912414506037814e-06, "Pretrain/Loss": 2.0177388191223145, "Pretrain/Loss (Raw)": 1.9648058414459229, "Pretrain/Step": 8324, "Pretrain/Step Time": 8.788207728415728} +{"Pretrain/Learning Rate": 2.087843618435109e-06, "Pretrain/Loss": 2.018265962600708, "Pretrain/Loss (Raw)": 1.9683030843734741, "Pretrain/Step": 8325, "Pretrain/Step Time": 8.789871044456959} +{"Pretrain/Learning Rate": 2.0844484286042744e-06, "Pretrain/Loss": 2.0228562355041504, "Pretrain/Loss (Raw)": 2.1591806411743164, "Pretrain/Step": 8326, "Pretrain/Step Time": 8.79602507315576} +{"Pretrain/Learning Rate": 2.0810558815028303e-06, "Pretrain/Loss": 2.0237841606140137, "Pretrain/Loss (Raw)": 2.0712733268737793, "Pretrain/Step": 8327, "Pretrain/Step Time": 8.79927559942007} +{"Pretrain/Learning Rate": 2.077665977522017e-06, "Pretrain/Loss": 2.0230584144592285, "Pretrain/Loss (Raw)": 1.9598294496536255, "Pretrain/Step": 8328, "Pretrain/Step Time": 8.795748803764582} +{"Pretrain/Learning Rate": 2.07427871705278e-06, "Pretrain/Loss": 2.024197578430176, "Pretrain/Loss (Raw)": 2.294417381286621, "Pretrain/Step": 8329, "Pretrain/Step Time": 8.800704253837466} +{"Pretrain/Learning Rate": 2.0708941004857485e-06, "Pretrain/Loss": 2.0201127529144287, "Pretrain/Loss (Raw)": 1.5462608337402344, "Pretrain/Step": 8330, "Pretrain/Step Time": 8.800557835027575} +{"Pretrain/Learning Rate": 2.0675121282112577e-06, "Pretrain/Loss": 2.019948720932007, "Pretrain/Loss (Raw)": 2.156937837600708, "Pretrain/Step": 8331, "Pretrain/Step Time": 8.802088249474764} +{"Pretrain/Learning Rate": 2.064132800619323e-06, "Pretrain/Loss": 2.018709659576416, "Pretrain/Loss (Raw)": 1.857650876045227, "Pretrain/Step": 8332, "Pretrain/Step Time": 8.794040113687515} +{"Pretrain/Learning Rate": 2.0607561180996772e-06, "Pretrain/Loss": 2.015920639038086, "Pretrain/Loss (Raw)": 1.9101159572601318, "Pretrain/Step": 8333, "Pretrain/Step Time": 8.796712009236217} +{"Pretrain/Learning Rate": 2.0573820810417283e-06, "Pretrain/Loss": 2.0160512924194336, "Pretrain/Loss (Raw)": 2.022348642349243, "Pretrain/Step": 8334, "Pretrain/Step Time": 8.790463155135512} +{"Pretrain/Learning Rate": 2.0540106898345874e-06, "Pretrain/Loss": 2.01454496383667, "Pretrain/Loss (Raw)": 2.051382064819336, "Pretrain/Step": 8335, "Pretrain/Step Time": 8.795097015798092} +{"Pretrain/Learning Rate": 2.0506419448670543e-06, "Pretrain/Loss": 2.016942024230957, "Pretrain/Loss (Raw)": 2.2148232460021973, "Pretrain/Step": 8336, "Pretrain/Step Time": 8.798314604908228} +{"Pretrain/Learning Rate": 2.047275846527638e-06, "Pretrain/Loss": 2.016930103302002, "Pretrain/Loss (Raw)": 2.0095906257629395, "Pretrain/Step": 8337, "Pretrain/Step Time": 8.801238529384136} +{"Pretrain/Learning Rate": 2.043912395204525e-06, "Pretrain/Loss": 2.017791509628296, "Pretrain/Loss (Raw)": 2.12287974357605, "Pretrain/Step": 8338, "Pretrain/Step Time": 8.80092386342585} +{"Pretrain/Learning Rate": 2.040551591285611e-06, "Pretrain/Loss": 2.01810884475708, "Pretrain/Loss (Raw)": 2.0760741233825684, "Pretrain/Step": 8339, "Pretrain/Step Time": 8.802474923431873} +{"Pretrain/Learning Rate": 2.0371934351584716e-06, "Pretrain/Loss": 2.0177481174468994, "Pretrain/Loss (Raw)": 2.167534112930298, "Pretrain/Step": 8340, "Pretrain/Step Time": 8.800370518118143} +{"Pretrain/Learning Rate": 2.0338379272103915e-06, "Pretrain/Loss": 2.0167367458343506, "Pretrain/Loss (Raw)": 1.7083204984664917, "Pretrain/Step": 8341, "Pretrain/Step Time": 8.799579244107008} +{"Pretrain/Learning Rate": 2.0304850678283415e-06, "Pretrain/Loss": 2.0155301094055176, "Pretrain/Loss (Raw)": 1.8987770080566406, "Pretrain/Step": 8342, "Pretrain/Step Time": 8.797746101394296} +{"Pretrain/Learning Rate": 2.027134857398991e-06, "Pretrain/Loss": 2.018319606781006, "Pretrain/Loss (Raw)": 2.345977544784546, "Pretrain/Step": 8343, "Pretrain/Step Time": 8.799362590536475} +{"Pretrain/Learning Rate": 2.023787296308696e-06, "Pretrain/Loss": 2.019631862640381, "Pretrain/Loss (Raw)": 2.0918045043945312, "Pretrain/Step": 8344, "Pretrain/Step Time": 8.796144686639309} +{"Pretrain/Learning Rate": 2.0204423849435216e-06, "Pretrain/Loss": 2.0185422897338867, "Pretrain/Loss (Raw)": 2.0355403423309326, "Pretrain/Step": 8345, "Pretrain/Step Time": 8.797751704230905} +{"Pretrain/Learning Rate": 2.017100123689214e-06, "Pretrain/Loss": 2.017575979232788, "Pretrain/Loss (Raw)": 1.9395889043807983, "Pretrain/Step": 8346, "Pretrain/Step Time": 8.801893694326282} +{"Pretrain/Learning Rate": 2.013760512931215e-06, "Pretrain/Loss": 2.019484519958496, "Pretrain/Loss (Raw)": 2.1140801906585693, "Pretrain/Step": 8347, "Pretrain/Step Time": 8.802635736763477} +{"Pretrain/Learning Rate": 2.0104235530546743e-06, "Pretrain/Loss": 2.020399570465088, "Pretrain/Loss (Raw)": 1.9573252201080322, "Pretrain/Step": 8348, "Pretrain/Step Time": 8.798508360981941} +{"Pretrain/Learning Rate": 2.0070892444444185e-06, "Pretrain/Loss": 2.0184714794158936, "Pretrain/Loss (Raw)": 1.9273900985717773, "Pretrain/Step": 8349, "Pretrain/Step Time": 8.795337241142988} +{"Pretrain/Learning Rate": 2.0037575874849753e-06, "Pretrain/Loss": 2.0167789459228516, "Pretrain/Loss (Raw)": 1.9755359888076782, "Pretrain/Step": 8350, "Pretrain/Step Time": 8.791711056604981} +{"Pretrain/Learning Rate": 2.0004285825605677e-06, "Pretrain/Loss": 2.0168118476867676, "Pretrain/Loss (Raw)": 2.0126242637634277, "Pretrain/Step": 8351, "Pretrain/Step Time": 8.794105596840382} +{"Pretrain/Learning Rate": 1.9971022300551174e-06, "Pretrain/Loss": 2.0154917240142822, "Pretrain/Loss (Raw)": 1.8979629278182983, "Pretrain/Step": 8352, "Pretrain/Step Time": 8.792828384786844} +{"Pretrain/Learning Rate": 1.9937785303522303e-06, "Pretrain/Loss": 2.0147128105163574, "Pretrain/Loss (Raw)": 2.0850088596343994, "Pretrain/Step": 8353, "Pretrain/Step Time": 8.811486855149269} +{"Pretrain/Learning Rate": 1.990457483835212e-06, "Pretrain/Loss": 2.0154128074645996, "Pretrain/Loss (Raw)": 2.131850004196167, "Pretrain/Step": 8354, "Pretrain/Step Time": 8.8002298027277} +{"Pretrain/Learning Rate": 1.9871390908870554e-06, "Pretrain/Loss": 2.0142464637756348, "Pretrain/Loss (Raw)": 1.9867076873779297, "Pretrain/Step": 8355, "Pretrain/Step Time": 8.80071877501905} +{"Pretrain/Learning Rate": 1.9838233518904655e-06, "Pretrain/Loss": 2.0149154663085938, "Pretrain/Loss (Raw)": 2.031926393508911, "Pretrain/Step": 8356, "Pretrain/Step Time": 8.796413619071245} +{"Pretrain/Learning Rate": 1.9805102672278226e-06, "Pretrain/Loss": 2.0163207054138184, "Pretrain/Loss (Raw)": 2.090507745742798, "Pretrain/Step": 8357, "Pretrain/Step Time": 8.794354928657413} +{"Pretrain/Learning Rate": 1.9771998372812044e-06, "Pretrain/Loss": 2.016842842102051, "Pretrain/Loss (Raw)": 2.090824604034424, "Pretrain/Step": 8358, "Pretrain/Step Time": 8.793982435017824} +{"Pretrain/Learning Rate": 1.9738920624323862e-06, "Pretrain/Loss": 2.0164713859558105, "Pretrain/Loss (Raw)": 2.0556435585021973, "Pretrain/Step": 8359, "Pretrain/Step Time": 8.796378992497921} +{"Pretrain/Learning Rate": 1.9705869430628465e-06, "Pretrain/Loss": 2.0178911685943604, "Pretrain/Loss (Raw)": 2.1292004585266113, "Pretrain/Step": 8360, "Pretrain/Step Time": 8.799730397760868} +{"Pretrain/Learning Rate": 1.96728447955373e-06, "Pretrain/Loss": 2.020432472229004, "Pretrain/Loss (Raw)": 2.1742868423461914, "Pretrain/Step": 8361, "Pretrain/Step Time": 8.791026078164577} +{"Pretrain/Learning Rate": 1.963984672285904e-06, "Pretrain/Loss": 2.019784927368164, "Pretrain/Loss (Raw)": 1.7826435565948486, "Pretrain/Step": 8362, "Pretrain/Step Time": 8.795720927417278} +{"Pretrain/Learning Rate": 1.960687521639912e-06, "Pretrain/Loss": 2.020094633102417, "Pretrain/Loss (Raw)": 1.9126622676849365, "Pretrain/Step": 8363, "Pretrain/Step Time": 8.792060134932399} +{"Pretrain/Learning Rate": 1.9573930279960073e-06, "Pretrain/Loss": 2.017949104309082, "Pretrain/Loss (Raw)": 1.7127342224121094, "Pretrain/Step": 8364, "Pretrain/Step Time": 8.786313412711024} +{"Pretrain/Learning Rate": 1.954101191734112e-06, "Pretrain/Loss": 2.018827438354492, "Pretrain/Loss (Raw)": 2.1777079105377197, "Pretrain/Step": 8365, "Pretrain/Step Time": 8.782853990793228} +{"Pretrain/Learning Rate": 1.9508120132338657e-06, "Pretrain/Loss": 2.0168159008026123, "Pretrain/Loss (Raw)": 1.57310950756073, "Pretrain/Step": 8366, "Pretrain/Step Time": 8.785328786820173} +{"Pretrain/Learning Rate": 1.9475254928745883e-06, "Pretrain/Loss": 2.0187883377075195, "Pretrain/Loss (Raw)": 2.165123224258423, "Pretrain/Step": 8367, "Pretrain/Step Time": 8.784765807911754} +{"Pretrain/Learning Rate": 1.9442416310353012e-06, "Pretrain/Loss": 2.0186009407043457, "Pretrain/Loss (Raw)": 1.9127120971679688, "Pretrain/Step": 8368, "Pretrain/Step Time": 8.78134954907} +{"Pretrain/Learning Rate": 1.940960428094704e-06, "Pretrain/Loss": 2.0193471908569336, "Pretrain/Loss (Raw)": 2.1102285385131836, "Pretrain/Step": 8369, "Pretrain/Step Time": 8.782421965152025} +{"Pretrain/Learning Rate": 1.937681884431214e-06, "Pretrain/Loss": 2.021456241607666, "Pretrain/Loss (Raw)": 2.168468952178955, "Pretrain/Step": 8370, "Pretrain/Step Time": 8.783274857327342} +{"Pretrain/Learning Rate": 1.9344060004229225e-06, "Pretrain/Loss": 2.0207901000976562, "Pretrain/Loss (Raw)": 2.011970043182373, "Pretrain/Step": 8371, "Pretrain/Step Time": 8.782426472753286} +{"Pretrain/Learning Rate": 1.9311327764476196e-06, "Pretrain/Loss": 2.0220630168914795, "Pretrain/Loss (Raw)": 2.0631983280181885, "Pretrain/Step": 8372, "Pretrain/Step Time": 8.779758783057332} +{"Pretrain/Learning Rate": 1.927862212882783e-06, "Pretrain/Loss": 2.022233486175537, "Pretrain/Loss (Raw)": 2.1291160583496094, "Pretrain/Step": 8373, "Pretrain/Step Time": 8.780300188809633} +{"Pretrain/Learning Rate": 1.9245943101056014e-06, "Pretrain/Loss": 2.022327423095703, "Pretrain/Loss (Raw)": 2.107792615890503, "Pretrain/Step": 8374, "Pretrain/Step Time": 8.787239814177155} +{"Pretrain/Learning Rate": 1.9213290684929386e-06, "Pretrain/Loss": 2.0208563804626465, "Pretrain/Loss (Raw)": 2.004028081893921, "Pretrain/Step": 8375, "Pretrain/Step Time": 8.776735024526715} +{"Pretrain/Learning Rate": 1.9180664884213577e-06, "Pretrain/Loss": 2.0218334197998047, "Pretrain/Loss (Raw)": 2.148355007171631, "Pretrain/Step": 8376, "Pretrain/Step Time": 8.777409685775638} +{"Pretrain/Learning Rate": 1.9148065702671108e-06, "Pretrain/Loss": 2.02125883102417, "Pretrain/Loss (Raw)": 1.8885250091552734, "Pretrain/Step": 8377, "Pretrain/Step Time": 8.775897597894073} +{"Pretrain/Learning Rate": 1.9115493144061555e-06, "Pretrain/Loss": 2.0219476222991943, "Pretrain/Loss (Raw)": 1.9756574630737305, "Pretrain/Step": 8378, "Pretrain/Step Time": 8.774033369496465} +{"Pretrain/Learning Rate": 1.9082947212141293e-06, "Pretrain/Loss": 2.022831439971924, "Pretrain/Loss (Raw)": 2.0358991622924805, "Pretrain/Step": 8379, "Pretrain/Step Time": 8.773858714848757} +{"Pretrain/Learning Rate": 1.9050427910663693e-06, "Pretrain/Loss": 2.0238425731658936, "Pretrain/Loss (Raw)": 1.946390986442566, "Pretrain/Step": 8380, "Pretrain/Step Time": 8.772086907178164} +{"Pretrain/Learning Rate": 1.901793524337897e-06, "Pretrain/Loss": 2.0227627754211426, "Pretrain/Loss (Raw)": 1.9053518772125244, "Pretrain/Step": 8381, "Pretrain/Step Time": 8.78962509892881} +{"Pretrain/Learning Rate": 1.8985469214034407e-06, "Pretrain/Loss": 2.020056962966919, "Pretrain/Loss (Raw)": 1.800702452659607, "Pretrain/Step": 8382, "Pretrain/Step Time": 8.790447996929288} +{"Pretrain/Learning Rate": 1.8953029826374119e-06, "Pretrain/Loss": 2.021003246307373, "Pretrain/Loss (Raw)": 1.960579752922058, "Pretrain/Step": 8383, "Pretrain/Step Time": 8.786449106410146} +{"Pretrain/Learning Rate": 1.8920617084139142e-06, "Pretrain/Loss": 2.0229828357696533, "Pretrain/Loss (Raw)": 2.2165374755859375, "Pretrain/Step": 8384, "Pretrain/Step Time": 8.790729997679591} +{"Pretrain/Learning Rate": 1.8888230991067457e-06, "Pretrain/Loss": 2.023207187652588, "Pretrain/Loss (Raw)": 2.029961109161377, "Pretrain/Step": 8385, "Pretrain/Step Time": 8.783631563186646} +{"Pretrain/Learning Rate": 1.885587155089405e-06, "Pretrain/Loss": 2.023468255996704, "Pretrain/Loss (Raw)": 1.978163480758667, "Pretrain/Step": 8386, "Pretrain/Step Time": 8.782424040138721} +{"Pretrain/Learning Rate": 1.8823538767350712e-06, "Pretrain/Loss": 2.0236029624938965, "Pretrain/Loss (Raw)": 2.1146950721740723, "Pretrain/Step": 8387, "Pretrain/Step Time": 8.779735086485744} +{"Pretrain/Learning Rate": 1.8791232644166212e-06, "Pretrain/Loss": 2.023683786392212, "Pretrain/Loss (Raw)": 2.0108420848846436, "Pretrain/Step": 8388, "Pretrain/Step Time": 8.783761750906706} +{"Pretrain/Learning Rate": 1.8758953185066264e-06, "Pretrain/Loss": 2.020801067352295, "Pretrain/Loss (Raw)": 1.8765102624893188, "Pretrain/Step": 8389, "Pretrain/Step Time": 8.780783852562308} +{"Pretrain/Learning Rate": 1.87267003937735e-06, "Pretrain/Loss": 2.019131660461426, "Pretrain/Loss (Raw)": 1.7961021661758423, "Pretrain/Step": 8390, "Pretrain/Step Time": 8.78228028677404} +{"Pretrain/Learning Rate": 1.8694474274007417e-06, "Pretrain/Loss": 2.021195888519287, "Pretrain/Loss (Raw)": 2.2451841831207275, "Pretrain/Step": 8391, "Pretrain/Step Time": 8.780393682420254} +{"Pretrain/Learning Rate": 1.8662274829484488e-06, "Pretrain/Loss": 2.0248031616210938, "Pretrain/Loss (Raw)": 2.1087417602539062, "Pretrain/Step": 8392, "Pretrain/Step Time": 8.784385288134217} +{"Pretrain/Learning Rate": 1.8630102063918158e-06, "Pretrain/Loss": 2.025268077850342, "Pretrain/Loss (Raw)": 2.0401084423065186, "Pretrain/Step": 8393, "Pretrain/Step Time": 8.781300408765674} +{"Pretrain/Learning Rate": 1.859795598101871e-06, "Pretrain/Loss": 2.0248594284057617, "Pretrain/Loss (Raw)": 1.9934223890304565, "Pretrain/Step": 8394, "Pretrain/Step Time": 8.784017400816083} +{"Pretrain/Learning Rate": 1.8565836584493374e-06, "Pretrain/Loss": 2.0228896141052246, "Pretrain/Loss (Raw)": 1.8972749710083008, "Pretrain/Step": 8395, "Pretrain/Step Time": 8.78753761947155} +{"Pretrain/Learning Rate": 1.8533743878046295e-06, "Pretrain/Loss": 2.022677421569824, "Pretrain/Loss (Raw)": 1.9958391189575195, "Pretrain/Step": 8396, "Pretrain/Step Time": 8.779964866116643} +{"Pretrain/Learning Rate": 1.8501677865378597e-06, "Pretrain/Loss": 2.024561882019043, "Pretrain/Loss (Raw)": 2.272649049758911, "Pretrain/Step": 8397, "Pretrain/Step Time": 8.783086251467466} +{"Pretrain/Learning Rate": 1.8469638550188267e-06, "Pretrain/Loss": 2.0261688232421875, "Pretrain/Loss (Raw)": 2.1754612922668457, "Pretrain/Step": 8398, "Pretrain/Step Time": 8.783561142161489} +{"Pretrain/Learning Rate": 1.8437625936170239e-06, "Pretrain/Loss": 2.0234122276306152, "Pretrain/Loss (Raw)": 1.915907859802246, "Pretrain/Step": 8399, "Pretrain/Step Time": 8.783911084756255} +{"Pretrain/Learning Rate": 1.8405640027016307e-06, "Pretrain/Loss": 2.0244739055633545, "Pretrain/Loss (Raw)": 1.944993019104004, "Pretrain/Step": 8400, "Pretrain/Step Time": 8.782372083514929} +{"Pretrain/Learning Rate": 1.8373680826415358e-06, "Pretrain/Loss": 2.024563789367676, "Pretrain/Loss (Raw)": 2.1089699268341064, "Pretrain/Step": 8401, "Pretrain/Step Time": 8.782221468165517} +{"Pretrain/Learning Rate": 1.8341748338052882e-06, "Pretrain/Loss": 2.0231642723083496, "Pretrain/Loss (Raw)": 1.9328722953796387, "Pretrain/Step": 8402, "Pretrain/Step Time": 8.786881733685732} +{"Pretrain/Learning Rate": 1.8309842565611663e-06, "Pretrain/Loss": 2.0206844806671143, "Pretrain/Loss (Raw)": 1.9417532682418823, "Pretrain/Step": 8403, "Pretrain/Step Time": 8.77624387666583} +{"Pretrain/Learning Rate": 1.8277963512771112e-06, "Pretrain/Loss": 2.021530866622925, "Pretrain/Loss (Raw)": 1.980397343635559, "Pretrain/Step": 8404, "Pretrain/Step Time": 8.779836531728506} +{"Pretrain/Learning Rate": 1.824611118320782e-06, "Pretrain/Loss": 2.0236401557922363, "Pretrain/Loss (Raw)": 2.39536452293396, "Pretrain/Step": 8405, "Pretrain/Step Time": 8.781102212145925} +{"Pretrain/Learning Rate": 1.8214285580594931e-06, "Pretrain/Loss": 2.0223283767700195, "Pretrain/Loss (Raw)": 2.100034475326538, "Pretrain/Step": 8406, "Pretrain/Step Time": 8.783580668270588} +{"Pretrain/Learning Rate": 1.8182486708602898e-06, "Pretrain/Loss": 2.024928569793701, "Pretrain/Loss (Raw)": 2.219719886779785, "Pretrain/Step": 8407, "Pretrain/Step Time": 8.784259648993611} +{"Pretrain/Learning Rate": 1.8150714570898868e-06, "Pretrain/Loss": 2.025290012359619, "Pretrain/Loss (Raw)": 2.1517345905303955, "Pretrain/Step": 8408, "Pretrain/Step Time": 8.780377630144358} +{"Pretrain/Learning Rate": 1.8118969171146915e-06, "Pretrain/Loss": 2.0256028175354004, "Pretrain/Loss (Raw)": 1.9946017265319824, "Pretrain/Step": 8409, "Pretrain/Step Time": 8.781531820073724} +{"Pretrain/Learning Rate": 1.8087250513008082e-06, "Pretrain/Loss": 2.0274510383605957, "Pretrain/Loss (Raw)": 2.206998348236084, "Pretrain/Step": 8410, "Pretrain/Step Time": 8.786539170891047} +{"Pretrain/Learning Rate": 1.8055558600140354e-06, "Pretrain/Loss": 2.0274369716644287, "Pretrain/Loss (Raw)": 1.9917325973510742, "Pretrain/Step": 8411, "Pretrain/Step Time": 8.78793997131288} +{"Pretrain/Learning Rate": 1.8023893436198592e-06, "Pretrain/Loss": 2.0290403366088867, "Pretrain/Loss (Raw)": 2.035233974456787, "Pretrain/Step": 8412, "Pretrain/Step Time": 8.787954438477755} +{"Pretrain/Learning Rate": 1.7992255024834509e-06, "Pretrain/Loss": 2.027512550354004, "Pretrain/Loss (Raw)": 1.9976990222930908, "Pretrain/Step": 8413, "Pretrain/Step Time": 8.787617083638906} +{"Pretrain/Learning Rate": 1.79606433696968e-06, "Pretrain/Loss": 2.028266429901123, "Pretrain/Loss (Raw)": 2.1882128715515137, "Pretrain/Step": 8414, "Pretrain/Step Time": 8.788025414571166} +{"Pretrain/Learning Rate": 1.792905847443116e-06, "Pretrain/Loss": 2.0246825218200684, "Pretrain/Loss (Raw)": 1.5870658159255981, "Pretrain/Step": 8415, "Pretrain/Step Time": 8.788343274965882} +{"Pretrain/Learning Rate": 1.7897500342680063e-06, "Pretrain/Loss": 2.023739814758301, "Pretrain/Loss (Raw)": 1.939974069595337, "Pretrain/Step": 8416, "Pretrain/Step Time": 8.786748563870788} +{"Pretrain/Learning Rate": 1.7865968978082903e-06, "Pretrain/Loss": 2.02573299407959, "Pretrain/Loss (Raw)": 2.128906011581421, "Pretrain/Step": 8417, "Pretrain/Step Time": 8.79493597522378} +{"Pretrain/Learning Rate": 1.7834464384276022e-06, "Pretrain/Loss": 2.023808002471924, "Pretrain/Loss (Raw)": 1.9188803434371948, "Pretrain/Step": 8418, "Pretrain/Step Time": 8.794097678735852} +{"Pretrain/Learning Rate": 1.7802986564892737e-06, "Pretrain/Loss": 2.022916793823242, "Pretrain/Loss (Raw)": 1.9627481698989868, "Pretrain/Step": 8419, "Pretrain/Step Time": 8.790516629815102} +{"Pretrain/Learning Rate": 1.7771535523563198e-06, "Pretrain/Loss": 2.022228479385376, "Pretrain/Loss (Raw)": 2.0463271141052246, "Pretrain/Step": 8420, "Pretrain/Step Time": 8.791563373059034} +{"Pretrain/Learning Rate": 1.7740111263914478e-06, "Pretrain/Loss": 2.022134304046631, "Pretrain/Loss (Raw)": 2.053363561630249, "Pretrain/Step": 8421, "Pretrain/Step Time": 8.790309567004442} +{"Pretrain/Learning Rate": 1.7708713789570536e-06, "Pretrain/Loss": 2.0201399326324463, "Pretrain/Loss (Raw)": 1.851696491241455, "Pretrain/Step": 8422, "Pretrain/Step Time": 8.787405092269182} +{"Pretrain/Learning Rate": 1.767734310415234e-06, "Pretrain/Loss": 2.01877498626709, "Pretrain/Loss (Raw)": 1.9727468490600586, "Pretrain/Step": 8423, "Pretrain/Step Time": 8.791198605671525} +{"Pretrain/Learning Rate": 1.7645999211277686e-06, "Pretrain/Loss": 2.0161776542663574, "Pretrain/Loss (Raw)": 1.6476389169692993, "Pretrain/Step": 8424, "Pretrain/Step Time": 8.787310745567083} +{"Pretrain/Learning Rate": 1.7614682114561298e-06, "Pretrain/Loss": 2.0149309635162354, "Pretrain/Loss (Raw)": 1.9369559288024902, "Pretrain/Step": 8425, "Pretrain/Step Time": 8.786163069307804} +{"Pretrain/Learning Rate": 1.7583391817614757e-06, "Pretrain/Loss": 2.013929605484009, "Pretrain/Loss (Raw)": 1.9617788791656494, "Pretrain/Step": 8426, "Pretrain/Step Time": 8.789272433146834} +{"Pretrain/Learning Rate": 1.7552128324046707e-06, "Pretrain/Loss": 2.0143442153930664, "Pretrain/Loss (Raw)": 1.9014506340026855, "Pretrain/Step": 8427, "Pretrain/Step Time": 8.797366900369525} +{"Pretrain/Learning Rate": 1.752089163746254e-06, "Pretrain/Loss": 2.01375150680542, "Pretrain/Loss (Raw)": 2.0192439556121826, "Pretrain/Step": 8428, "Pretrain/Step Time": 8.793507739901543} +{"Pretrain/Learning Rate": 1.7489681761464565e-06, "Pretrain/Loss": 2.0129847526550293, "Pretrain/Loss (Raw)": 1.9588563442230225, "Pretrain/Step": 8429, "Pretrain/Step Time": 8.792945671826601} +{"Pretrain/Learning Rate": 1.7458498699652186e-06, "Pretrain/Loss": 2.012721061706543, "Pretrain/Loss (Raw)": 2.108678102493286, "Pretrain/Step": 8430, "Pretrain/Step Time": 8.797257531434298} +{"Pretrain/Learning Rate": 1.7427342455621498e-06, "Pretrain/Loss": 2.014669895172119, "Pretrain/Loss (Raw)": 2.0094380378723145, "Pretrain/Step": 8431, "Pretrain/Step Time": 8.794873226433992} +{"Pretrain/Learning Rate": 1.7396213032965597e-06, "Pretrain/Loss": 2.015559196472168, "Pretrain/Loss (Raw)": 2.1648268699645996, "Pretrain/Step": 8432, "Pretrain/Step Time": 8.797016397118568} +{"Pretrain/Learning Rate": 1.7365110435274419e-06, "Pretrain/Loss": 2.0169577598571777, "Pretrain/Loss (Raw)": 2.1067819595336914, "Pretrain/Step": 8433, "Pretrain/Step Time": 8.790458602830768} +{"Pretrain/Learning Rate": 1.733403466613498e-06, "Pretrain/Loss": 2.0173652172088623, "Pretrain/Loss (Raw)": 2.1596827507019043, "Pretrain/Step": 8434, "Pretrain/Step Time": 8.796194341033697} +{"Pretrain/Learning Rate": 1.7302985729131e-06, "Pretrain/Loss": 2.0187854766845703, "Pretrain/Loss (Raw)": 2.100877523422241, "Pretrain/Step": 8435, "Pretrain/Step Time": 8.792480770498514} +{"Pretrain/Learning Rate": 1.7271963627843223e-06, "Pretrain/Loss": 2.0201473236083984, "Pretrain/Loss (Raw)": 2.339271068572998, "Pretrain/Step": 8436, "Pretrain/Step Time": 8.792446909472346} +{"Pretrain/Learning Rate": 1.7240968365849208e-06, "Pretrain/Loss": 2.019543170928955, "Pretrain/Loss (Raw)": 1.975662112236023, "Pretrain/Step": 8437, "Pretrain/Step Time": 8.800098940730095} +{"Pretrain/Learning Rate": 1.7209999946723564e-06, "Pretrain/Loss": 2.0204882621765137, "Pretrain/Loss (Raw)": 2.0578277111053467, "Pretrain/Step": 8438, "Pretrain/Step Time": 8.802202893421054} +{"Pretrain/Learning Rate": 1.717905837403766e-06, "Pretrain/Loss": 2.019491195678711, "Pretrain/Loss (Raw)": 1.9831366539001465, "Pretrain/Step": 8439, "Pretrain/Step Time": 8.807407481595874} +{"Pretrain/Learning Rate": 1.7148143651359833e-06, "Pretrain/Loss": 2.021008014678955, "Pretrain/Loss (Raw)": 2.1009883880615234, "Pretrain/Step": 8440, "Pretrain/Step Time": 8.805858811363578} +{"Pretrain/Learning Rate": 1.711725578225526e-06, "Pretrain/Loss": 2.023526668548584, "Pretrain/Loss (Raw)": 2.014941692352295, "Pretrain/Step": 8441, "Pretrain/Step Time": 8.813949201256037} +{"Pretrain/Learning Rate": 1.708639477028623e-06, "Pretrain/Loss": 2.026308059692383, "Pretrain/Loss (Raw)": 2.3197827339172363, "Pretrain/Step": 8442, "Pretrain/Step Time": 8.808652076870203} +{"Pretrain/Learning Rate": 1.705556061901159e-06, "Pretrain/Loss": 2.0263028144836426, "Pretrain/Loss (Raw)": 1.9859669208526611, "Pretrain/Step": 8443, "Pretrain/Step Time": 8.812212221324444} +{"Pretrain/Learning Rate": 1.7024753331987442e-06, "Pretrain/Loss": 2.027244806289673, "Pretrain/Loss (Raw)": 2.1216657161712646, "Pretrain/Step": 8444, "Pretrain/Step Time": 8.816023278981447} +{"Pretrain/Learning Rate": 1.699397291276647e-06, "Pretrain/Loss": 2.026594638824463, "Pretrain/Loss (Raw)": 2.0467965602874756, "Pretrain/Step": 8445, "Pretrain/Step Time": 8.813347421586514} +{"Pretrain/Learning Rate": 1.6963219364898613e-06, "Pretrain/Loss": 2.0276098251342773, "Pretrain/Loss (Raw)": 2.1370279788970947, "Pretrain/Step": 8446, "Pretrain/Step Time": 8.81666960194707} +{"Pretrain/Learning Rate": 1.6932492691930312e-06, "Pretrain/Loss": 2.0268266201019287, "Pretrain/Loss (Raw)": 2.0891788005828857, "Pretrain/Step": 8447, "Pretrain/Step Time": 8.815905444324017} +{"Pretrain/Learning Rate": 1.6901792897405233e-06, "Pretrain/Loss": 2.026230573654175, "Pretrain/Loss (Raw)": 1.9549161195755005, "Pretrain/Step": 8448, "Pretrain/Step Time": 8.809903336688876} +{"Pretrain/Learning Rate": 1.6871119984863765e-06, "Pretrain/Loss": 2.025343656539917, "Pretrain/Loss (Raw)": 2.0087029933929443, "Pretrain/Step": 8449, "Pretrain/Step Time": 8.80681648850441} +{"Pretrain/Learning Rate": 1.6840473957843355e-06, "Pretrain/Loss": 2.0258970260620117, "Pretrain/Loss (Raw)": 2.101522922515869, "Pretrain/Step": 8450, "Pretrain/Step Time": 8.803474273532629} +{"Pretrain/Learning Rate": 1.6809854819878096e-06, "Pretrain/Loss": 2.0268940925598145, "Pretrain/Loss (Raw)": 2.0821595191955566, "Pretrain/Step": 8451, "Pretrain/Step Time": 8.805017154663801} +{"Pretrain/Learning Rate": 1.6779262574499243e-06, "Pretrain/Loss": 2.0273189544677734, "Pretrain/Loss (Raw)": 2.0192060470581055, "Pretrain/Step": 8452, "Pretrain/Step Time": 8.808568084612489} +{"Pretrain/Learning Rate": 1.674869722523481e-06, "Pretrain/Loss": 2.0293359756469727, "Pretrain/Loss (Raw)": 2.22650146484375, "Pretrain/Step": 8453, "Pretrain/Step Time": 8.80573545023799} +{"Pretrain/Learning Rate": 1.6718158775609727e-06, "Pretrain/Loss": 2.0293757915496826, "Pretrain/Loss (Raw)": 2.164268970489502, "Pretrain/Step": 8454, "Pretrain/Step Time": 8.804628303274512} +{"Pretrain/Learning Rate": 1.6687647229145787e-06, "Pretrain/Loss": 2.029076099395752, "Pretrain/Loss (Raw)": 2.0328714847564697, "Pretrain/Step": 8455, "Pretrain/Step Time": 8.800933452323079} +{"Pretrain/Learning Rate": 1.6657162589361814e-06, "Pretrain/Loss": 2.0298826694488525, "Pretrain/Loss (Raw)": 2.063079595565796, "Pretrain/Step": 8456, "Pretrain/Step Time": 8.802731407806277} +{"Pretrain/Learning Rate": 1.6626704859773413e-06, "Pretrain/Loss": 2.028311252593994, "Pretrain/Loss (Raw)": 2.0933070182800293, "Pretrain/Step": 8457, "Pretrain/Step Time": 8.800146944820881} +{"Pretrain/Learning Rate": 1.6596274043893078e-06, "Pretrain/Loss": 2.0312376022338867, "Pretrain/Loss (Raw)": 1.9208306074142456, "Pretrain/Step": 8458, "Pretrain/Step Time": 8.805063378065825} +{"Pretrain/Learning Rate": 1.6565870145230228e-06, "Pretrain/Loss": 2.0300703048706055, "Pretrain/Loss (Raw)": 2.007495641708374, "Pretrain/Step": 8459, "Pretrain/Step Time": 8.809193313121796} +{"Pretrain/Learning Rate": 1.653549316729125e-06, "Pretrain/Loss": 2.0306828022003174, "Pretrain/Loss (Raw)": 1.9360663890838623, "Pretrain/Step": 8460, "Pretrain/Step Time": 8.805167213082314} +{"Pretrain/Learning Rate": 1.6505143113579314e-06, "Pretrain/Loss": 2.0322203636169434, "Pretrain/Loss (Raw)": 2.1069416999816895, "Pretrain/Step": 8461, "Pretrain/Step Time": 8.805176042020321} +{"Pretrain/Learning Rate": 1.6474819987594536e-06, "Pretrain/Loss": 2.033050298690796, "Pretrain/Loss (Raw)": 2.1285808086395264, "Pretrain/Step": 8462, "Pretrain/Step Time": 8.805574918165803} +{"Pretrain/Learning Rate": 1.64445237928339e-06, "Pretrain/Loss": 2.032710075378418, "Pretrain/Loss (Raw)": 2.007822036743164, "Pretrain/Step": 8463, "Pretrain/Step Time": 8.803858922794461} +{"Pretrain/Learning Rate": 1.6414254532791357e-06, "Pretrain/Loss": 2.0309276580810547, "Pretrain/Loss (Raw)": 1.9866605997085571, "Pretrain/Step": 8464, "Pretrain/Step Time": 8.801934842020273} +{"Pretrain/Learning Rate": 1.6384012210957672e-06, "Pretrain/Loss": 2.0308902263641357, "Pretrain/Loss (Raw)": 2.004803419113159, "Pretrain/Step": 8465, "Pretrain/Step Time": 8.799931729212403} +{"Pretrain/Learning Rate": 1.6353796830820529e-06, "Pretrain/Loss": 2.0325379371643066, "Pretrain/Loss (Raw)": 2.333799362182617, "Pretrain/Step": 8466, "Pretrain/Step Time": 8.803704952821136} +{"Pretrain/Learning Rate": 1.6323608395864498e-06, "Pretrain/Loss": 2.031723976135254, "Pretrain/Loss (Raw)": 1.9718819856643677, "Pretrain/Step": 8467, "Pretrain/Step Time": 8.794354623183608} +{"Pretrain/Learning Rate": 1.6293446909571075e-06, "Pretrain/Loss": 2.0313844680786133, "Pretrain/Loss (Raw)": 2.124087333679199, "Pretrain/Step": 8468, "Pretrain/Step Time": 8.79540903493762} +{"Pretrain/Learning Rate": 1.6263312375418643e-06, "Pretrain/Loss": 2.03439998626709, "Pretrain/Loss (Raw)": 2.0942914485931396, "Pretrain/Step": 8469, "Pretrain/Step Time": 8.795542072504759} +{"Pretrain/Learning Rate": 1.6233204796882368e-06, "Pretrain/Loss": 2.035360336303711, "Pretrain/Loss (Raw)": 2.021695137023926, "Pretrain/Step": 8470, "Pretrain/Step Time": 8.795038087293506} +{"Pretrain/Learning Rate": 1.6203124177434497e-06, "Pretrain/Loss": 2.0335464477539062, "Pretrain/Loss (Raw)": 2.11380672454834, "Pretrain/Step": 8471, "Pretrain/Step Time": 8.78859019652009} +{"Pretrain/Learning Rate": 1.6173070520544065e-06, "Pretrain/Loss": 2.032911539077759, "Pretrain/Loss (Raw)": 2.01052188873291, "Pretrain/Step": 8472, "Pretrain/Step Time": 8.792056411504745} +{"Pretrain/Learning Rate": 1.6143043829676934e-06, "Pretrain/Loss": 2.032438278198242, "Pretrain/Loss (Raw)": 1.974988579750061, "Pretrain/Step": 8473, "Pretrain/Step Time": 8.801363121718168} +{"Pretrain/Learning Rate": 1.611304410829595e-06, "Pretrain/Loss": 2.0326690673828125, "Pretrain/Loss (Raw)": 1.9691219329833984, "Pretrain/Step": 8474, "Pretrain/Step Time": 8.79418066330254} +{"Pretrain/Learning Rate": 1.6083071359860868e-06, "Pretrain/Loss": 2.0312743186950684, "Pretrain/Loss (Raw)": 1.935551404953003, "Pretrain/Step": 8475, "Pretrain/Step Time": 8.792542416602373} +{"Pretrain/Learning Rate": 1.6053125587828233e-06, "Pretrain/Loss": 2.0327000617980957, "Pretrain/Loss (Raw)": 2.139840841293335, "Pretrain/Step": 8476, "Pretrain/Step Time": 8.794086748734117} +{"Pretrain/Learning Rate": 1.6023206795651557e-06, "Pretrain/Loss": 2.0326521396636963, "Pretrain/Loss (Raw)": 1.9212449789047241, "Pretrain/Step": 8477, "Pretrain/Step Time": 8.800230843946338} +{"Pretrain/Learning Rate": 1.5993314986781166e-06, "Pretrain/Loss": 2.0328948497772217, "Pretrain/Loss (Raw)": 2.0065982341766357, "Pretrain/Step": 8478, "Pretrain/Step Time": 8.799081712961197} +{"Pretrain/Learning Rate": 1.5963450164664385e-06, "Pretrain/Loss": 2.0312767028808594, "Pretrain/Loss (Raw)": 1.8054630756378174, "Pretrain/Step": 8479, "Pretrain/Step Time": 8.797625629231334} +{"Pretrain/Learning Rate": 1.5933612332745373e-06, "Pretrain/Loss": 2.0325186252593994, "Pretrain/Loss (Raw)": 2.056952714920044, "Pretrain/Step": 8480, "Pretrain/Step Time": 8.811598725616932} +{"Pretrain/Learning Rate": 1.5903801494465131e-06, "Pretrain/Loss": 2.031841278076172, "Pretrain/Loss (Raw)": 1.998300552368164, "Pretrain/Step": 8481, "Pretrain/Step Time": 8.795147862285376} +{"Pretrain/Learning Rate": 1.5874017653261574e-06, "Pretrain/Loss": 2.032602310180664, "Pretrain/Loss (Raw)": 2.2292678356170654, "Pretrain/Step": 8482, "Pretrain/Step Time": 8.794074088335037} +{"Pretrain/Learning Rate": 1.5844260812569621e-06, "Pretrain/Loss": 2.033792495727539, "Pretrain/Loss (Raw)": 2.139024019241333, "Pretrain/Step": 8483, "Pretrain/Step Time": 8.794615937396884} +{"Pretrain/Learning Rate": 1.5814530975820806e-06, "Pretrain/Loss": 2.034545660018921, "Pretrain/Loss (Raw)": 2.128380298614502, "Pretrain/Step": 8484, "Pretrain/Step Time": 8.800536759197712} +{"Pretrain/Learning Rate": 1.578482814644383e-06, "Pretrain/Loss": 2.0321364402770996, "Pretrain/Loss (Raw)": 1.782128930091858, "Pretrain/Step": 8485, "Pretrain/Step Time": 8.802244270220399} +{"Pretrain/Learning Rate": 1.5755152327864093e-06, "Pretrain/Loss": 2.0322389602661133, "Pretrain/Loss (Raw)": 2.1039278507232666, "Pretrain/Step": 8486, "Pretrain/Step Time": 8.799933351576328} +{"Pretrain/Learning Rate": 1.572550352350405e-06, "Pretrain/Loss": 2.03181791305542, "Pretrain/Loss (Raw)": 2.001723051071167, "Pretrain/Step": 8487, "Pretrain/Step Time": 8.800012722611427} +{"Pretrain/Learning Rate": 1.5695881736782825e-06, "Pretrain/Loss": 2.030778408050537, "Pretrain/Loss (Raw)": 1.9961904287338257, "Pretrain/Step": 8488, "Pretrain/Step Time": 8.803044971078634} +{"Pretrain/Learning Rate": 1.5666286971116605e-06, "Pretrain/Loss": 2.0293667316436768, "Pretrain/Loss (Raw)": 1.993580937385559, "Pretrain/Step": 8489, "Pretrain/Step Time": 8.80504896119237} +{"Pretrain/Learning Rate": 1.5636719229918385e-06, "Pretrain/Loss": 2.030836582183838, "Pretrain/Loss (Raw)": 1.9707987308502197, "Pretrain/Step": 8490, "Pretrain/Step Time": 8.80521403439343} +{"Pretrain/Learning Rate": 1.5607178516598126e-06, "Pretrain/Loss": 2.0324392318725586, "Pretrain/Loss (Raw)": 2.1177616119384766, "Pretrain/Step": 8491, "Pretrain/Step Time": 8.806356655433774} +{"Pretrain/Learning Rate": 1.557766483456244e-06, "Pretrain/Loss": 2.0345029830932617, "Pretrain/Loss (Raw)": 1.9769299030303955, "Pretrain/Step": 8492, "Pretrain/Step Time": 8.80596617422998} +{"Pretrain/Learning Rate": 1.5548178187215128e-06, "Pretrain/Loss": 2.0323610305786133, "Pretrain/Loss (Raw)": 1.9035240411758423, "Pretrain/Step": 8493, "Pretrain/Step Time": 8.81118660978973} +{"Pretrain/Learning Rate": 1.5518718577956697e-06, "Pretrain/Loss": 2.036104679107666, "Pretrain/Loss (Raw)": 2.05230450630188, "Pretrain/Step": 8494, "Pretrain/Step Time": 8.817827029153705} +{"Pretrain/Learning Rate": 1.5489286010184539e-06, "Pretrain/Loss": 2.0342679023742676, "Pretrain/Loss (Raw)": 1.9299724102020264, "Pretrain/Step": 8495, "Pretrain/Step Time": 8.808503666892648} +{"Pretrain/Learning Rate": 1.545988048729291e-06, "Pretrain/Loss": 2.035353660583496, "Pretrain/Loss (Raw)": 2.0517234802246094, "Pretrain/Step": 8496, "Pretrain/Step Time": 8.808730499818921} +{"Pretrain/Learning Rate": 1.5430502012673126e-06, "Pretrain/Loss": 2.0339674949645996, "Pretrain/Loss (Raw)": 1.9327892065048218, "Pretrain/Step": 8497, "Pretrain/Step Time": 8.811441102996469} +{"Pretrain/Learning Rate": 1.5401150589713171e-06, "Pretrain/Loss": 2.0325863361358643, "Pretrain/Loss (Raw)": 1.9917035102844238, "Pretrain/Step": 8498, "Pretrain/Step Time": 8.810931727290154} +{"Pretrain/Learning Rate": 1.5371826221797975e-06, "Pretrain/Loss": 2.034013271331787, "Pretrain/Loss (Raw)": 2.1945836544036865, "Pretrain/Step": 8499, "Pretrain/Step Time": 8.807445522397757} +{"Pretrain/Learning Rate": 1.534252891230936e-06, "Pretrain/Loss": 2.032663345336914, "Pretrain/Loss (Raw)": 1.8904304504394531, "Pretrain/Step": 8500, "Pretrain/Step Time": 8.814822332933545} +{"Pretrain/Learning Rate": 1.5313258664626073e-06, "Pretrain/Loss": 2.031741142272949, "Pretrain/Loss (Raw)": 2.0110673904418945, "Pretrain/Step": 8501, "Pretrain/Step Time": 8.813548270612955} +{"Pretrain/Learning Rate": 1.5284015482123714e-06, "Pretrain/Loss": 2.0322346687316895, "Pretrain/Loss (Raw)": 2.1709842681884766, "Pretrain/Step": 8502, "Pretrain/Step Time": 8.812058161944151} +{"Pretrain/Learning Rate": 1.5254799368174672e-06, "Pretrain/Loss": 2.0329651832580566, "Pretrain/Loss (Raw)": 2.0975213050842285, "Pretrain/Step": 8503, "Pretrain/Step Time": 8.812957240268588} +{"Pretrain/Learning Rate": 1.5225610326148304e-06, "Pretrain/Loss": 2.031285285949707, "Pretrain/Loss (Raw)": 1.9333080053329468, "Pretrain/Step": 8504, "Pretrain/Step Time": 8.81199032254517} +{"Pretrain/Learning Rate": 1.5196448359410891e-06, "Pretrain/Loss": 2.0327870845794678, "Pretrain/Loss (Raw)": 2.0807526111602783, "Pretrain/Step": 8505, "Pretrain/Step Time": 8.819283543154597} +{"Pretrain/Learning Rate": 1.5167313471325468e-06, "Pretrain/Loss": 2.0335865020751953, "Pretrain/Loss (Raw)": 2.0779969692230225, "Pretrain/Step": 8506, "Pretrain/Step Time": 8.816493159160018} +{"Pretrain/Learning Rate": 1.513820566525201e-06, "Pretrain/Loss": 2.0335474014282227, "Pretrain/Loss (Raw)": 2.0309135913848877, "Pretrain/Step": 8507, "Pretrain/Step Time": 8.815252961590886} +{"Pretrain/Learning Rate": 1.510912494454736e-06, "Pretrain/Loss": 2.0345187187194824, "Pretrain/Loss (Raw)": 2.0707268714904785, "Pretrain/Step": 8508, "Pretrain/Step Time": 8.818517317995429} +{"Pretrain/Learning Rate": 1.5080071312565308e-06, "Pretrain/Loss": 2.0358657836914062, "Pretrain/Loss (Raw)": 2.077746629714966, "Pretrain/Step": 8509, "Pretrain/Step Time": 8.796430787071586} +{"Pretrain/Learning Rate": 1.5051044772656397e-06, "Pretrain/Loss": 2.037937879562378, "Pretrain/Loss (Raw)": 2.065941333770752, "Pretrain/Step": 8510, "Pretrain/Step Time": 8.800667403265834} +{"Pretrain/Learning Rate": 1.5022045328168088e-06, "Pretrain/Loss": 2.039022445678711, "Pretrain/Loss (Raw)": 2.09941029548645, "Pretrain/Step": 8511, "Pretrain/Step Time": 8.798017263412476} +{"Pretrain/Learning Rate": 1.4993072982444816e-06, "Pretrain/Loss": 2.0371999740600586, "Pretrain/Loss (Raw)": 1.9832507371902466, "Pretrain/Step": 8512, "Pretrain/Step Time": 8.796895913779736} +{"Pretrain/Learning Rate": 1.4964127738827744e-06, "Pretrain/Loss": 2.0373282432556152, "Pretrain/Loss (Raw)": 2.0463907718658447, "Pretrain/Step": 8513, "Pretrain/Step Time": 8.798248576000333} +{"Pretrain/Learning Rate": 1.4935209600654977e-06, "Pretrain/Loss": 2.0349550247192383, "Pretrain/Loss (Raw)": 1.6743766069412231, "Pretrain/Step": 8514, "Pretrain/Step Time": 8.804017568007112} +{"Pretrain/Learning Rate": 1.4906318571261484e-06, "Pretrain/Loss": 2.0348291397094727, "Pretrain/Loss (Raw)": 2.098592519760132, "Pretrain/Step": 8515, "Pretrain/Step Time": 8.802361231297255} +{"Pretrain/Learning Rate": 1.4877454653979162e-06, "Pretrain/Loss": 2.035066604614258, "Pretrain/Loss (Raw)": 2.041247606277466, "Pretrain/Step": 8516, "Pretrain/Step Time": 8.797077748924494} +{"Pretrain/Learning Rate": 1.4848617852136676e-06, "Pretrain/Loss": 2.0375874042510986, "Pretrain/Loss (Raw)": 2.199164628982544, "Pretrain/Step": 8517, "Pretrain/Step Time": 8.806983700022101} +{"Pretrain/Learning Rate": 1.4819808169059674e-06, "Pretrain/Loss": 2.041106700897217, "Pretrain/Loss (Raw)": 2.2465903759002686, "Pretrain/Step": 8518, "Pretrain/Step Time": 8.803695179522038} +{"Pretrain/Learning Rate": 1.4791025608070552e-06, "Pretrain/Loss": 2.038717031478882, "Pretrain/Loss (Raw)": 1.939297080039978, "Pretrain/Step": 8519, "Pretrain/Step Time": 8.804805271327496} +{"Pretrain/Learning Rate": 1.476227017248874e-06, "Pretrain/Loss": 2.037231206893921, "Pretrain/Loss (Raw)": 1.9185510873794556, "Pretrain/Step": 8520, "Pretrain/Step Time": 8.804407952353358} +{"Pretrain/Learning Rate": 1.4733541865630418e-06, "Pretrain/Loss": 2.0370397567749023, "Pretrain/Loss (Raw)": 2.01558518409729, "Pretrain/Step": 8521, "Pretrain/Step Time": 8.809321731328964} +{"Pretrain/Learning Rate": 1.4704840690808659e-06, "Pretrain/Loss": 2.038170337677002, "Pretrain/Loss (Raw)": 2.138169050216675, "Pretrain/Step": 8522, "Pretrain/Step Time": 8.804551877081394} +{"Pretrain/Learning Rate": 1.4676166651333367e-06, "Pretrain/Loss": 2.0386033058166504, "Pretrain/Loss (Raw)": 1.9527024030685425, "Pretrain/Step": 8523, "Pretrain/Step Time": 8.801048090681434} +{"Pretrain/Learning Rate": 1.4647519750511512e-06, "Pretrain/Loss": 2.040137529373169, "Pretrain/Loss (Raw)": 2.192192792892456, "Pretrain/Step": 8524, "Pretrain/Step Time": 8.80588736385107} +{"Pretrain/Learning Rate": 1.461889999164659e-06, "Pretrain/Loss": 2.036937713623047, "Pretrain/Loss (Raw)": 1.86306631565094, "Pretrain/Step": 8525, "Pretrain/Step Time": 8.804949535056949} +{"Pretrain/Learning Rate": 1.4590307378039348e-06, "Pretrain/Loss": 2.034759998321533, "Pretrain/Loss (Raw)": 1.8967031240463257, "Pretrain/Step": 8526, "Pretrain/Step Time": 8.802928490564227} +{"Pretrain/Learning Rate": 1.4561741912987093e-06, "Pretrain/Loss": 2.0352816581726074, "Pretrain/Loss (Raw)": 1.9827172756195068, "Pretrain/Step": 8527, "Pretrain/Step Time": 8.807288683950901} +{"Pretrain/Learning Rate": 1.4533203599784245e-06, "Pretrain/Loss": 2.0379419326782227, "Pretrain/Loss (Raw)": 2.285473346710205, "Pretrain/Step": 8528, "Pretrain/Step Time": 8.807521026581526} +{"Pretrain/Learning Rate": 1.4504692441721867e-06, "Pretrain/Loss": 2.0365588665008545, "Pretrain/Loss (Raw)": 1.9319571256637573, "Pretrain/Step": 8529, "Pretrain/Step Time": 8.807448642328382} +{"Pretrain/Learning Rate": 1.4476208442088052e-06, "Pretrain/Loss": 2.0372493267059326, "Pretrain/Loss (Raw)": 2.0212438106536865, "Pretrain/Step": 8530, "Pretrain/Step Time": 8.809437388554215} +{"Pretrain/Learning Rate": 1.4447751604167697e-06, "Pretrain/Loss": 2.0385994911193848, "Pretrain/Loss (Raw)": 2.114588737487793, "Pretrain/Step": 8531, "Pretrain/Step Time": 8.811578733846545} +{"Pretrain/Learning Rate": 1.4419321931242624e-06, "Pretrain/Loss": 2.038430690765381, "Pretrain/Loss (Raw)": 1.958778738975525, "Pretrain/Step": 8532, "Pretrain/Step Time": 8.80937853641808} +{"Pretrain/Learning Rate": 1.4390919426591404e-06, "Pretrain/Loss": 2.035391092300415, "Pretrain/Loss (Raw)": 2.006303548812866, "Pretrain/Step": 8533, "Pretrain/Step Time": 8.809870596975088} +{"Pretrain/Learning Rate": 1.4362544093489583e-06, "Pretrain/Loss": 2.036015510559082, "Pretrain/Loss (Raw)": 2.1799492835998535, "Pretrain/Step": 8534, "Pretrain/Step Time": 8.804473254829645} +{"Pretrain/Learning Rate": 1.4334195935209572e-06, "Pretrain/Loss": 2.0354113578796387, "Pretrain/Loss (Raw)": 2.1423909664154053, "Pretrain/Step": 8535, "Pretrain/Step Time": 8.806877981871367} +{"Pretrain/Learning Rate": 1.4305874955020559e-06, "Pretrain/Loss": 2.034640312194824, "Pretrain/Loss (Raw)": 2.0530643463134766, "Pretrain/Step": 8536, "Pretrain/Step Time": 8.811997743323445} +{"Pretrain/Learning Rate": 1.427758115618863e-06, "Pretrain/Loss": 2.0351674556732178, "Pretrain/Loss (Raw)": 2.0620551109313965, "Pretrain/Step": 8537, "Pretrain/Step Time": 8.81314212270081} +{"Pretrain/Learning Rate": 1.4249314541976866e-06, "Pretrain/Loss": 2.0329365730285645, "Pretrain/Loss (Raw)": 1.9214223623275757, "Pretrain/Step": 8538, "Pretrain/Step Time": 8.805011929944158} +{"Pretrain/Learning Rate": 1.422107511564502e-06, "Pretrain/Loss": 2.0324149131774902, "Pretrain/Loss (Raw)": 1.9249534606933594, "Pretrain/Step": 8539, "Pretrain/Step Time": 8.802388733252883} +{"Pretrain/Learning Rate": 1.4192862880449825e-06, "Pretrain/Loss": 2.033015012741089, "Pretrain/Loss (Raw)": 2.1120705604553223, "Pretrain/Step": 8540, "Pretrain/Step Time": 8.804899908602238} +{"Pretrain/Learning Rate": 1.4164677839644813e-06, "Pretrain/Loss": 2.0337882041931152, "Pretrain/Loss (Raw)": 2.0966949462890625, "Pretrain/Step": 8541, "Pretrain/Step Time": 8.798635264858603} +{"Pretrain/Learning Rate": 1.4136519996480469e-06, "Pretrain/Loss": 2.0301029682159424, "Pretrain/Loss (Raw)": 1.7164742946624756, "Pretrain/Step": 8542, "Pretrain/Step Time": 8.802909852936864} +{"Pretrain/Learning Rate": 1.4108389354204055e-06, "Pretrain/Loss": 2.033977508544922, "Pretrain/Loss (Raw)": 2.0830183029174805, "Pretrain/Step": 8543, "Pretrain/Step Time": 8.802695604041219} +{"Pretrain/Learning Rate": 1.4080285916059754e-06, "Pretrain/Loss": 2.0336079597473145, "Pretrain/Loss (Raw)": 1.8926581144332886, "Pretrain/Step": 8544, "Pretrain/Step Time": 8.809844383969903} +{"Pretrain/Learning Rate": 1.405220968528853e-06, "Pretrain/Loss": 2.0335021018981934, "Pretrain/Loss (Raw)": 2.115370512008667, "Pretrain/Step": 8545, "Pretrain/Step Time": 8.795927863568068} +{"Pretrain/Learning Rate": 1.402416066512835e-06, "Pretrain/Loss": 2.0349740982055664, "Pretrain/Loss (Raw)": 2.1072728633880615, "Pretrain/Step": 8546, "Pretrain/Step Time": 8.79914921708405} +{"Pretrain/Learning Rate": 1.3996138858813928e-06, "Pretrain/Loss": 2.035583972930908, "Pretrain/Loss (Raw)": 2.040821075439453, "Pretrain/Step": 8547, "Pretrain/Step Time": 8.799190079793334} +{"Pretrain/Learning Rate": 1.396814426957685e-06, "Pretrain/Loss": 2.0350208282470703, "Pretrain/Loss (Raw)": 1.974251389503479, "Pretrain/Step": 8548, "Pretrain/Step Time": 8.801338395103812} +{"Pretrain/Learning Rate": 1.394017690064553e-06, "Pretrain/Loss": 2.034119129180908, "Pretrain/Loss (Raw)": 1.937949299812317, "Pretrain/Step": 8549, "Pretrain/Step Time": 8.801620051264763} +{"Pretrain/Learning Rate": 1.3912236755245416e-06, "Pretrain/Loss": 2.0344133377075195, "Pretrain/Loss (Raw)": 1.8893311023712158, "Pretrain/Step": 8550, "Pretrain/Step Time": 8.802592970430851} +{"Pretrain/Learning Rate": 1.3884323836598655e-06, "Pretrain/Loss": 2.034191608428955, "Pretrain/Loss (Raw)": 1.944380760192871, "Pretrain/Step": 8551, "Pretrain/Step Time": 8.804032985121012} +{"Pretrain/Learning Rate": 1.3856438147924229e-06, "Pretrain/Loss": 2.0361039638519287, "Pretrain/Loss (Raw)": 1.892430067062378, "Pretrain/Step": 8552, "Pretrain/Step Time": 8.808158300817013} +{"Pretrain/Learning Rate": 1.3828579692438142e-06, "Pretrain/Loss": 2.036529302597046, "Pretrain/Loss (Raw)": 1.9913946390151978, "Pretrain/Step": 8553, "Pretrain/Step Time": 8.81019432656467} +{"Pretrain/Learning Rate": 1.3800748473353137e-06, "Pretrain/Loss": 2.037714719772339, "Pretrain/Loss (Raw)": 2.1135025024414062, "Pretrain/Step": 8554, "Pretrain/Step Time": 8.807529697194695} +{"Pretrain/Learning Rate": 1.377294449387881e-06, "Pretrain/Loss": 2.0376222133636475, "Pretrain/Loss (Raw)": 1.889604926109314, "Pretrain/Step": 8555, "Pretrain/Step Time": 8.800389129668474} +{"Pretrain/Learning Rate": 1.3745167757221622e-06, "Pretrain/Loss": 2.0370142459869385, "Pretrain/Loss (Raw)": 1.9414530992507935, "Pretrain/Step": 8556, "Pretrain/Step Time": 8.798264738172293} +{"Pretrain/Learning Rate": 1.3717418266585014e-06, "Pretrain/Loss": 2.0365660190582275, "Pretrain/Loss (Raw)": 1.9014801979064941, "Pretrain/Step": 8557, "Pretrain/Step Time": 8.805055245757103} +{"Pretrain/Learning Rate": 1.3689696025169118e-06, "Pretrain/Loss": 2.0365233421325684, "Pretrain/Loss (Raw)": 2.1031839847564697, "Pretrain/Step": 8558, "Pretrain/Step Time": 8.798286866396666} +{"Pretrain/Learning Rate": 1.366200103617099e-06, "Pretrain/Loss": 2.036133289337158, "Pretrain/Loss (Raw)": 1.9595363140106201, "Pretrain/Step": 8559, "Pretrain/Step Time": 8.80324262753129} +{"Pretrain/Learning Rate": 1.3634333302784546e-06, "Pretrain/Loss": 2.034341812133789, "Pretrain/Loss (Raw)": 1.9354963302612305, "Pretrain/Step": 8560, "Pretrain/Step Time": 8.800214570015669} +{"Pretrain/Learning Rate": 1.3606692828200623e-06, "Pretrain/Loss": 2.034522294998169, "Pretrain/Loss (Raw)": 2.129911184310913, "Pretrain/Step": 8561, "Pretrain/Step Time": 8.799171162769198} +{"Pretrain/Learning Rate": 1.3579079615606781e-06, "Pretrain/Loss": 2.0327649116516113, "Pretrain/Loss (Raw)": 1.9347459077835083, "Pretrain/Step": 8562, "Pretrain/Step Time": 8.800239318981767} +{"Pretrain/Learning Rate": 1.355149366818756e-06, "Pretrain/Loss": 2.0330450534820557, "Pretrain/Loss (Raw)": 2.136707305908203, "Pretrain/Step": 8563, "Pretrain/Step Time": 8.797505086287856} +{"Pretrain/Learning Rate": 1.3523934989124214e-06, "Pretrain/Loss": 2.0315380096435547, "Pretrain/Loss (Raw)": 2.1463937759399414, "Pretrain/Step": 8564, "Pretrain/Step Time": 8.802754331380129} +{"Pretrain/Learning Rate": 1.3496403581595042e-06, "Pretrain/Loss": 2.0320897102355957, "Pretrain/Loss (Raw)": 2.0462751388549805, "Pretrain/Step": 8565, "Pretrain/Step Time": 8.793682489544153} +{"Pretrain/Learning Rate": 1.3468899448775023e-06, "Pretrain/Loss": 2.0317816734313965, "Pretrain/Loss (Raw)": 2.018401622772217, "Pretrain/Step": 8566, "Pretrain/Step Time": 8.801301263272762} +{"Pretrain/Learning Rate": 1.3441422593836128e-06, "Pretrain/Loss": 2.0307579040527344, "Pretrain/Loss (Raw)": 1.8520894050598145, "Pretrain/Step": 8567, "Pretrain/Step Time": 8.79460466466844} +{"Pretrain/Learning Rate": 1.3413973019947013e-06, "Pretrain/Loss": 2.0302088260650635, "Pretrain/Loss (Raw)": 2.0306901931762695, "Pretrain/Step": 8568, "Pretrain/Step Time": 8.796896057203412} +{"Pretrain/Learning Rate": 1.3386550730273452e-06, "Pretrain/Loss": 2.03068208694458, "Pretrain/Loss (Raw)": 2.075542449951172, "Pretrain/Step": 8569, "Pretrain/Step Time": 8.797325136139989} +{"Pretrain/Learning Rate": 1.3359155727977745e-06, "Pretrain/Loss": 2.026789426803589, "Pretrain/Loss (Raw)": 1.8215008974075317, "Pretrain/Step": 8570, "Pretrain/Step Time": 8.797529995441437} +{"Pretrain/Learning Rate": 1.3331788016219315e-06, "Pretrain/Loss": 2.026137351989746, "Pretrain/Loss (Raw)": 1.9025115966796875, "Pretrain/Step": 8571, "Pretrain/Step Time": 8.793894324451685} +{"Pretrain/Learning Rate": 1.3304447598154274e-06, "Pretrain/Loss": 2.026489734649658, "Pretrain/Loss (Raw)": 2.166764259338379, "Pretrain/Step": 8572, "Pretrain/Step Time": 8.789674298837781} +{"Pretrain/Learning Rate": 1.3277134476935766e-06, "Pretrain/Loss": 2.0264976024627686, "Pretrain/Loss (Raw)": 2.047799587249756, "Pretrain/Step": 8573, "Pretrain/Step Time": 8.793034689500928} +{"Pretrain/Learning Rate": 1.324984865571352e-06, "Pretrain/Loss": 2.025160789489746, "Pretrain/Loss (Raw)": 1.965938687324524, "Pretrain/Step": 8574, "Pretrain/Step Time": 8.784954464063048} +{"Pretrain/Learning Rate": 1.3222590137634328e-06, "Pretrain/Loss": 2.0245542526245117, "Pretrain/Loss (Raw)": 2.011507272720337, "Pretrain/Step": 8575, "Pretrain/Step Time": 8.791072979569435} +{"Pretrain/Learning Rate": 1.319535892584181e-06, "Pretrain/Loss": 2.025279998779297, "Pretrain/Loss (Raw)": 2.047814130783081, "Pretrain/Step": 8576, "Pretrain/Step Time": 8.789140466600657} +{"Pretrain/Learning Rate": 1.3168155023476348e-06, "Pretrain/Loss": 2.025608777999878, "Pretrain/Loss (Raw)": 2.05080509185791, "Pretrain/Step": 8577, "Pretrain/Step Time": 8.794876918196678} +{"Pretrain/Learning Rate": 1.3140978433675206e-06, "Pretrain/Loss": 2.024484634399414, "Pretrain/Loss (Raw)": 1.9576125144958496, "Pretrain/Step": 8578, "Pretrain/Step Time": 8.794039446860552} +{"Pretrain/Learning Rate": 1.3113829159572572e-06, "Pretrain/Loss": 2.0249381065368652, "Pretrain/Loss (Raw)": 2.1402242183685303, "Pretrain/Step": 8579, "Pretrain/Step Time": 8.788869708776474} +{"Pretrain/Learning Rate": 1.3086707204299414e-06, "Pretrain/Loss": 2.0224485397338867, "Pretrain/Loss (Raw)": 1.700529932975769, "Pretrain/Step": 8580, "Pretrain/Step Time": 8.794809525832534} +{"Pretrain/Learning Rate": 1.3059612570983537e-06, "Pretrain/Loss": 2.0208287239074707, "Pretrain/Loss (Raw)": 2.0191853046417236, "Pretrain/Step": 8581, "Pretrain/Step Time": 8.8005311191082} +{"Pretrain/Learning Rate": 1.3032545262749635e-06, "Pretrain/Loss": 2.020557165145874, "Pretrain/Loss (Raw)": 2.12949275970459, "Pretrain/Step": 8582, "Pretrain/Step Time": 8.801162933930755} +{"Pretrain/Learning Rate": 1.3005505282719238e-06, "Pretrain/Loss": 2.0213165283203125, "Pretrain/Loss (Raw)": 2.13004469871521, "Pretrain/Step": 8583, "Pretrain/Step Time": 8.803709726780653} +{"Pretrain/Learning Rate": 1.297849263401074e-06, "Pretrain/Loss": 2.0208141803741455, "Pretrain/Loss (Raw)": 1.9987986087799072, "Pretrain/Step": 8584, "Pretrain/Step Time": 8.801700746640563} +{"Pretrain/Learning Rate": 1.2951507319739375e-06, "Pretrain/Loss": 2.020153522491455, "Pretrain/Loss (Raw)": 2.0087647438049316, "Pretrain/Step": 8585, "Pretrain/Step Time": 8.79912818968296} +{"Pretrain/Learning Rate": 1.2924549343017122e-06, "Pretrain/Loss": 2.021378755569458, "Pretrain/Loss (Raw)": 2.0776314735412598, "Pretrain/Step": 8586, "Pretrain/Step Time": 8.800369599834085} +{"Pretrain/Learning Rate": 1.289761870695305e-06, "Pretrain/Loss": 2.0187888145446777, "Pretrain/Loss (Raw)": 1.6759926080703735, "Pretrain/Step": 8587, "Pretrain/Step Time": 8.797987930476665} +{"Pretrain/Learning Rate": 1.2870715414652817e-06, "Pretrain/Loss": 2.020084857940674, "Pretrain/Loss (Raw)": 2.101963520050049, "Pretrain/Step": 8588, "Pretrain/Step Time": 8.798723163083196} +{"Pretrain/Learning Rate": 1.2843839469219104e-06, "Pretrain/Loss": 2.0204691886901855, "Pretrain/Loss (Raw)": 2.1561331748962402, "Pretrain/Step": 8589, "Pretrain/Step Time": 8.797723773866892} +{"Pretrain/Learning Rate": 1.2816990873751267e-06, "Pretrain/Loss": 2.0182671546936035, "Pretrain/Loss (Raw)": 1.8467050790786743, "Pretrain/Step": 8590, "Pretrain/Step Time": 8.799206444993615} +{"Pretrain/Learning Rate": 1.2790169631345744e-06, "Pretrain/Loss": 2.0160865783691406, "Pretrain/Loss (Raw)": 1.7287424802780151, "Pretrain/Step": 8591, "Pretrain/Step Time": 8.797551879659295} +{"Pretrain/Learning Rate": 1.2763375745095645e-06, "Pretrain/Loss": 2.015916109085083, "Pretrain/Loss (Raw)": 1.9648233652114868, "Pretrain/Step": 8592, "Pretrain/Step Time": 8.798603493720293} +{"Pretrain/Learning Rate": 1.2736609218090888e-06, "Pretrain/Loss": 2.0178823471069336, "Pretrain/Loss (Raw)": 2.2564873695373535, "Pretrain/Step": 8593, "Pretrain/Step Time": 8.802523296326399} +{"Pretrain/Learning Rate": 1.2709870053418421e-06, "Pretrain/Loss": 2.0159566402435303, "Pretrain/Loss (Raw)": 2.087310552597046, "Pretrain/Step": 8594, "Pretrain/Step Time": 8.797650529071689} +{"Pretrain/Learning Rate": 1.2683158254161887e-06, "Pretrain/Loss": 2.0177507400512695, "Pretrain/Loss (Raw)": 2.2015461921691895, "Pretrain/Step": 8595, "Pretrain/Step Time": 8.798374481499195} +{"Pretrain/Learning Rate": 1.2656473823401821e-06, "Pretrain/Loss": 2.0173258781433105, "Pretrain/Loss (Raw)": 2.0696632862091064, "Pretrain/Step": 8596, "Pretrain/Step Time": 8.79805776849389} +{"Pretrain/Learning Rate": 1.2629816764215542e-06, "Pretrain/Loss": 2.017566204071045, "Pretrain/Loss (Raw)": 2.125068426132202, "Pretrain/Step": 8597, "Pretrain/Step Time": 8.795479591935873} +{"Pretrain/Learning Rate": 1.2603187079677392e-06, "Pretrain/Loss": 2.018824338912964, "Pretrain/Loss (Raw)": 2.182736396789551, "Pretrain/Step": 8598, "Pretrain/Step Time": 8.80324630625546} +{"Pretrain/Learning Rate": 1.2576584772858307e-06, "Pretrain/Loss": 2.0186266899108887, "Pretrain/Loss (Raw)": 2.0884997844696045, "Pretrain/Step": 8599, "Pretrain/Step Time": 8.801869509741664} +{"Pretrain/Learning Rate": 1.2550009846826277e-06, "Pretrain/Loss": 2.0185132026672363, "Pretrain/Loss (Raw)": 1.9960075616836548, "Pretrain/Step": 8600, "Pretrain/Step Time": 8.800528222694993} +{"Pretrain/Learning Rate": 1.2523462304645961e-06, "Pretrain/Loss": 2.0203518867492676, "Pretrain/Loss (Raw)": 2.210320472717285, "Pretrain/Step": 8601, "Pretrain/Step Time": 8.79363115131855} +{"Pretrain/Learning Rate": 1.2496942149379048e-06, "Pretrain/Loss": 2.0217947959899902, "Pretrain/Loss (Raw)": 2.153822422027588, "Pretrain/Step": 8602, "Pretrain/Step Time": 8.801975179463625} +{"Pretrain/Learning Rate": 1.2470449384083927e-06, "Pretrain/Loss": 2.022794723510742, "Pretrain/Loss (Raw)": 2.0635571479797363, "Pretrain/Step": 8603, "Pretrain/Step Time": 8.80114546790719} +{"Pretrain/Learning Rate": 1.2443984011815845e-06, "Pretrain/Loss": 2.021331310272217, "Pretrain/Loss (Raw)": 1.9524872303009033, "Pretrain/Step": 8604, "Pretrain/Step Time": 8.798751164227724} +{"Pretrain/Learning Rate": 1.2417546035626864e-06, "Pretrain/Loss": 2.023000955581665, "Pretrain/Loss (Raw)": 2.1349871158599854, "Pretrain/Step": 8605, "Pretrain/Step Time": 8.798708649352193} +{"Pretrain/Learning Rate": 1.2391135458566072e-06, "Pretrain/Loss": 2.023402214050293, "Pretrain/Loss (Raw)": 2.05794095993042, "Pretrain/Step": 8606, "Pretrain/Step Time": 8.798156775534153} +{"Pretrain/Learning Rate": 1.236475228367917e-06, "Pretrain/Loss": 2.024834632873535, "Pretrain/Loss (Raw)": 1.9888250827789307, "Pretrain/Step": 8607, "Pretrain/Step Time": 8.80090164206922} +{"Pretrain/Learning Rate": 1.2338396514008839e-06, "Pretrain/Loss": 2.024836540222168, "Pretrain/Loss (Raw)": 2.0572214126586914, "Pretrain/Step": 8608, "Pretrain/Step Time": 8.791651332750916} +{"Pretrain/Learning Rate": 1.2312068152594447e-06, "Pretrain/Loss": 2.0256688594818115, "Pretrain/Loss (Raw)": 2.1048126220703125, "Pretrain/Step": 8609, "Pretrain/Step Time": 8.795262075960636} +{"Pretrain/Learning Rate": 1.228576720247246e-06, "Pretrain/Loss": 2.023441791534424, "Pretrain/Loss (Raw)": 1.944218635559082, "Pretrain/Step": 8610, "Pretrain/Step Time": 8.800415176898241} +{"Pretrain/Learning Rate": 1.2259493666675891e-06, "Pretrain/Loss": 2.0232791900634766, "Pretrain/Loss (Raw)": 2.1181981563568115, "Pretrain/Step": 8611, "Pretrain/Step Time": 8.797188775613904} +{"Pretrain/Learning Rate": 1.2233247548234795e-06, "Pretrain/Loss": 2.022007465362549, "Pretrain/Loss (Raw)": 1.96561861038208, "Pretrain/Step": 8612, "Pretrain/Step Time": 8.796683279797435} +{"Pretrain/Learning Rate": 1.2207028850175967e-06, "Pretrain/Loss": 2.0241804122924805, "Pretrain/Loss (Raw)": 2.060253858566284, "Pretrain/Step": 8613, "Pretrain/Step Time": 8.796221757307649} +{"Pretrain/Learning Rate": 1.2180837575523158e-06, "Pretrain/Loss": 2.0239224433898926, "Pretrain/Loss (Raw)": 2.0708906650543213, "Pretrain/Step": 8614, "Pretrain/Step Time": 8.799594951793551} +{"Pretrain/Learning Rate": 1.2154673727296728e-06, "Pretrain/Loss": 2.0240092277526855, "Pretrain/Loss (Raw)": 2.0128602981567383, "Pretrain/Step": 8615, "Pretrain/Step Time": 8.799906542524695} +{"Pretrain/Learning Rate": 1.21285373085141e-06, "Pretrain/Loss": 2.0246193408966064, "Pretrain/Loss (Raw)": 2.0742709636688232, "Pretrain/Step": 8616, "Pretrain/Step Time": 8.795169722288847} +{"Pretrain/Learning Rate": 1.2102428322189468e-06, "Pretrain/Loss": 2.025139331817627, "Pretrain/Loss (Raw)": 2.060117244720459, "Pretrain/Step": 8617, "Pretrain/Step Time": 8.803476434201002} +{"Pretrain/Learning Rate": 1.207634677133379e-06, "Pretrain/Loss": 2.026949882507324, "Pretrain/Loss (Raw)": 2.202587842941284, "Pretrain/Step": 8618, "Pretrain/Step Time": 8.796370591968298} +{"Pretrain/Learning Rate": 1.205029265895491e-06, "Pretrain/Loss": 2.025792121887207, "Pretrain/Loss (Raw)": 1.969544529914856, "Pretrain/Step": 8619, "Pretrain/Step Time": 8.795737816020846} +{"Pretrain/Learning Rate": 1.2024265988057588e-06, "Pretrain/Loss": 2.027576208114624, "Pretrain/Loss (Raw)": 2.2052929401397705, "Pretrain/Step": 8620, "Pretrain/Step Time": 8.795827344059944} +{"Pretrain/Learning Rate": 1.1998266761643256e-06, "Pretrain/Loss": 2.0284950733184814, "Pretrain/Loss (Raw)": 2.0211524963378906, "Pretrain/Step": 8621, "Pretrain/Step Time": 8.791431866586208} +{"Pretrain/Learning Rate": 1.1972294982710326e-06, "Pretrain/Loss": 2.027137041091919, "Pretrain/Loss (Raw)": 1.8784734010696411, "Pretrain/Step": 8622, "Pretrain/Step Time": 8.784844778478146} +{"Pretrain/Learning Rate": 1.1946350654253924e-06, "Pretrain/Loss": 2.0261995792388916, "Pretrain/Loss (Raw)": 1.8099576234817505, "Pretrain/Step": 8623, "Pretrain/Step Time": 8.789967864751816} +{"Pretrain/Learning Rate": 1.192043377926616e-06, "Pretrain/Loss": 2.0243844985961914, "Pretrain/Loss (Raw)": 1.8194363117218018, "Pretrain/Step": 8624, "Pretrain/Step Time": 8.797008523717523} +{"Pretrain/Learning Rate": 1.189454436073581e-06, "Pretrain/Loss": 2.0255837440490723, "Pretrain/Loss (Raw)": 2.0862531661987305, "Pretrain/Step": 8625, "Pretrain/Step Time": 8.792603634297848} +{"Pretrain/Learning Rate": 1.1868682401648595e-06, "Pretrain/Loss": 2.0266761779785156, "Pretrain/Loss (Raw)": 2.1315410137176514, "Pretrain/Step": 8626, "Pretrain/Step Time": 8.793024856597185} +{"Pretrain/Learning Rate": 1.184284790498702e-06, "Pretrain/Loss": 2.0249381065368652, "Pretrain/Loss (Raw)": 1.9721022844314575, "Pretrain/Step": 8627, "Pretrain/Step Time": 8.793983943760395} +{"Pretrain/Learning Rate": 1.1817040873730506e-06, "Pretrain/Loss": 2.0266809463500977, "Pretrain/Loss (Raw)": 2.1135408878326416, "Pretrain/Step": 8628, "Pretrain/Step Time": 8.788099322468042} +{"Pretrain/Learning Rate": 1.1791261310855172e-06, "Pretrain/Loss": 2.0264394283294678, "Pretrain/Loss (Raw)": 1.9801439046859741, "Pretrain/Step": 8629, "Pretrain/Step Time": 8.790562869980931} +{"Pretrain/Learning Rate": 1.1765509219334058e-06, "Pretrain/Loss": 2.024489164352417, "Pretrain/Loss (Raw)": 1.921351432800293, "Pretrain/Step": 8630, "Pretrain/Step Time": 8.798394141718745} +{"Pretrain/Learning Rate": 1.1739784602136983e-06, "Pretrain/Loss": 2.022505283355713, "Pretrain/Loss (Raw)": 1.8435781002044678, "Pretrain/Step": 8631, "Pretrain/Step Time": 8.799114253371954} +{"Pretrain/Learning Rate": 1.171408746223071e-06, "Pretrain/Loss": 2.022717237472534, "Pretrain/Loss (Raw)": 1.9604277610778809, "Pretrain/Step": 8632, "Pretrain/Step Time": 8.798171447589993} +{"Pretrain/Learning Rate": 1.1688417802578706e-06, "Pretrain/Loss": 2.02333664894104, "Pretrain/Loss (Raw)": 2.1600513458251953, "Pretrain/Step": 8633, "Pretrain/Step Time": 8.793790768831968} +{"Pretrain/Learning Rate": 1.1662775626141293e-06, "Pretrain/Loss": 2.023439884185791, "Pretrain/Loss (Raw)": 2.0911834239959717, "Pretrain/Step": 8634, "Pretrain/Step Time": 8.789824653416872} +{"Pretrain/Learning Rate": 1.1637160935875717e-06, "Pretrain/Loss": 2.0221314430236816, "Pretrain/Loss (Raw)": 1.8634793758392334, "Pretrain/Step": 8635, "Pretrain/Step Time": 8.792031437158585} +{"Pretrain/Learning Rate": 1.1611573734735925e-06, "Pretrain/Loss": 2.021249294281006, "Pretrain/Loss (Raw)": 1.9578101634979248, "Pretrain/Step": 8636, "Pretrain/Step Time": 8.789895547553897} +{"Pretrain/Learning Rate": 1.1586014025672775e-06, "Pretrain/Loss": 2.0217671394348145, "Pretrain/Loss (Raw)": 2.1440279483795166, "Pretrain/Step": 8637, "Pretrain/Step Time": 8.8019262496382} +{"Pretrain/Learning Rate": 1.1560481811633912e-06, "Pretrain/Loss": 2.021522045135498, "Pretrain/Loss (Raw)": 2.0345489978790283, "Pretrain/Step": 8638, "Pretrain/Step Time": 8.79726853966713} +{"Pretrain/Learning Rate": 1.1534977095563892e-06, "Pretrain/Loss": 2.020336627960205, "Pretrain/Loss (Raw)": 1.9476902484893799, "Pretrain/Step": 8639, "Pretrain/Step Time": 8.7999625261873} +{"Pretrain/Learning Rate": 1.1509499880403979e-06, "Pretrain/Loss": 2.021505355834961, "Pretrain/Loss (Raw)": 2.132850170135498, "Pretrain/Step": 8640, "Pretrain/Step Time": 8.79696866683662} +{"Pretrain/Learning Rate": 1.1484050169092347e-06, "Pretrain/Loss": 2.0212221145629883, "Pretrain/Loss (Raw)": 2.01011061668396, "Pretrain/Step": 8641, "Pretrain/Step Time": 8.795647265389562} +{"Pretrain/Learning Rate": 1.1458627964563928e-06, "Pretrain/Loss": 2.023927688598633, "Pretrain/Loss (Raw)": 2.0206847190856934, "Pretrain/Step": 8642, "Pretrain/Step Time": 8.792207632213831} +{"Pretrain/Learning Rate": 1.1433233269750627e-06, "Pretrain/Loss": 2.0246145725250244, "Pretrain/Loss (Raw)": 2.186537504196167, "Pretrain/Step": 8643, "Pretrain/Step Time": 8.794124802574515} +{"Pretrain/Learning Rate": 1.1407866087581043e-06, "Pretrain/Loss": 2.0237698554992676, "Pretrain/Loss (Raw)": 1.933120846748352, "Pretrain/Step": 8644, "Pretrain/Step Time": 8.806173261255026} +{"Pretrain/Learning Rate": 1.1382526420980588e-06, "Pretrain/Loss": 2.023576021194458, "Pretrain/Loss (Raw)": 2.174360513687134, "Pretrain/Step": 8645, "Pretrain/Step Time": 8.796679273247719} +{"Pretrain/Learning Rate": 1.135721427287159e-06, "Pretrain/Loss": 2.0217092037200928, "Pretrain/Loss (Raw)": 2.0076425075531006, "Pretrain/Step": 8646, "Pretrain/Step Time": 8.79815674200654} +{"Pretrain/Learning Rate": 1.1331929646173162e-06, "Pretrain/Loss": 2.023092269897461, "Pretrain/Loss (Raw)": 2.1163318157196045, "Pretrain/Step": 8647, "Pretrain/Step Time": 8.795793946832418} +{"Pretrain/Learning Rate": 1.1306672543801273e-06, "Pretrain/Loss": 2.024050712585449, "Pretrain/Loss (Raw)": 2.0412073135375977, "Pretrain/Step": 8648, "Pretrain/Step Time": 8.789229694753885} +{"Pretrain/Learning Rate": 1.1281442968668648e-06, "Pretrain/Loss": 2.024801254272461, "Pretrain/Loss (Raw)": 2.1116764545440674, "Pretrain/Step": 8649, "Pretrain/Step Time": 8.790912317112088} +{"Pretrain/Learning Rate": 1.125624092368488e-06, "Pretrain/Loss": 2.0231833457946777, "Pretrain/Loss (Raw)": 1.931060791015625, "Pretrain/Step": 8650, "Pretrain/Step Time": 8.79214364476502} +{"Pretrain/Learning Rate": 1.1231066411756475e-06, "Pretrain/Loss": 2.024486780166626, "Pretrain/Loss (Raw)": 2.119546890258789, "Pretrain/Step": 8651, "Pretrain/Step Time": 8.789358807727695} +{"Pretrain/Learning Rate": 1.1205919435786554e-06, "Pretrain/Loss": 2.0230093002319336, "Pretrain/Loss (Raw)": 2.003095865249634, "Pretrain/Step": 8652, "Pretrain/Step Time": 8.79684061743319} +{"Pretrain/Learning Rate": 1.1180799998675245e-06, "Pretrain/Loss": 2.0243353843688965, "Pretrain/Loss (Raw)": 2.0327720642089844, "Pretrain/Step": 8653, "Pretrain/Step Time": 8.794805333018303} +{"Pretrain/Learning Rate": 1.1155708103319395e-06, "Pretrain/Loss": 2.027975082397461, "Pretrain/Loss (Raw)": 2.36260986328125, "Pretrain/Step": 8654, "Pretrain/Step Time": 8.795297550037503} +{"Pretrain/Learning Rate": 1.1130643752612858e-06, "Pretrain/Loss": 2.0300629138946533, "Pretrain/Loss (Raw)": 2.249958038330078, "Pretrain/Step": 8655, "Pretrain/Step Time": 8.792830331251025} +{"Pretrain/Learning Rate": 1.1105606949445984e-06, "Pretrain/Loss": 2.028411626815796, "Pretrain/Loss (Raw)": 2.0741000175476074, "Pretrain/Step": 8656, "Pretrain/Step Time": 8.797876378521323} +{"Pretrain/Learning Rate": 1.1080597696706247e-06, "Pretrain/Loss": 2.0269722938537598, "Pretrain/Loss (Raw)": 1.747739553451538, "Pretrain/Step": 8657, "Pretrain/Step Time": 8.797324657440186} +{"Pretrain/Learning Rate": 1.1055615997277806e-06, "Pretrain/Loss": 2.027822971343994, "Pretrain/Loss (Raw)": 2.1301259994506836, "Pretrain/Step": 8658, "Pretrain/Step Time": 8.79054911620915} +{"Pretrain/Learning Rate": 1.1030661854041695e-06, "Pretrain/Loss": 2.0266060829162598, "Pretrain/Loss (Raw)": 1.958808422088623, "Pretrain/Step": 8659, "Pretrain/Step Time": 8.794317852705717} +{"Pretrain/Learning Rate": 1.1005735269875695e-06, "Pretrain/Loss": 2.0262255668640137, "Pretrain/Loss (Raw)": 1.910062551498413, "Pretrain/Step": 8660, "Pretrain/Step Time": 8.794036965817213} +{"Pretrain/Learning Rate": 1.0980836247654501e-06, "Pretrain/Loss": 2.025970935821533, "Pretrain/Loss (Raw)": 1.973739743232727, "Pretrain/Step": 8661, "Pretrain/Step Time": 8.792890449985862} +{"Pretrain/Learning Rate": 1.0955964790249546e-06, "Pretrain/Loss": 2.025909662246704, "Pretrain/Loss (Raw)": 2.1720991134643555, "Pretrain/Step": 8662, "Pretrain/Step Time": 8.799130899831653} +{"Pretrain/Learning Rate": 1.0931120900529169e-06, "Pretrain/Loss": 2.0239124298095703, "Pretrain/Loss (Raw)": 1.8867424726486206, "Pretrain/Step": 8663, "Pretrain/Step Time": 8.799150615930557} +{"Pretrain/Learning Rate": 1.0906304581358411e-06, "Pretrain/Loss": 2.0238566398620605, "Pretrain/Loss (Raw)": 2.045945167541504, "Pretrain/Step": 8664, "Pretrain/Step Time": 8.79971986822784} +{"Pretrain/Learning Rate": 1.0881515835599293e-06, "Pretrain/Loss": 2.0220987796783447, "Pretrain/Loss (Raw)": 1.8370305299758911, "Pretrain/Step": 8665, "Pretrain/Step Time": 8.802352331578732} +{"Pretrain/Learning Rate": 1.0856754666110553e-06, "Pretrain/Loss": 2.024646759033203, "Pretrain/Loss (Raw)": 2.2475502490997314, "Pretrain/Step": 8666, "Pretrain/Step Time": 8.80125667154789} +{"Pretrain/Learning Rate": 1.0832021075747711e-06, "Pretrain/Loss": 2.0253677368164062, "Pretrain/Loss (Raw)": 2.017212152481079, "Pretrain/Step": 8667, "Pretrain/Step Time": 8.802240666002035} +{"Pretrain/Learning Rate": 1.0807315067363184e-06, "Pretrain/Loss": 2.0235543251037598, "Pretrain/Loss (Raw)": 1.8799974918365479, "Pretrain/Step": 8668, "Pretrain/Step Time": 8.800881860777736} +{"Pretrain/Learning Rate": 1.0782636643806215e-06, "Pretrain/Loss": 2.022787094116211, "Pretrain/Loss (Raw)": 1.998458743095398, "Pretrain/Step": 8669, "Pretrain/Step Time": 8.79918248578906} +{"Pretrain/Learning Rate": 1.0757985807922838e-06, "Pretrain/Loss": 2.0258407592773438, "Pretrain/Loss (Raw)": 2.1073615550994873, "Pretrain/Step": 8670, "Pretrain/Step Time": 8.802248297259212} +{"Pretrain/Learning Rate": 1.073336256255586e-06, "Pretrain/Loss": 2.0241432189941406, "Pretrain/Loss (Raw)": 1.8657323122024536, "Pretrain/Step": 8671, "Pretrain/Step Time": 8.803315060213208} +{"Pretrain/Learning Rate": 1.0708766910544954e-06, "Pretrain/Loss": 2.0254011154174805, "Pretrain/Loss (Raw)": 2.053701639175415, "Pretrain/Step": 8672, "Pretrain/Step Time": 8.797699216753244} +{"Pretrain/Learning Rate": 1.0684198854726656e-06, "Pretrain/Loss": 2.025176525115967, "Pretrain/Loss (Raw)": 2.086580753326416, "Pretrain/Step": 8673, "Pretrain/Step Time": 8.799297211691737} +{"Pretrain/Learning Rate": 1.065965839793423e-06, "Pretrain/Loss": 2.0241949558258057, "Pretrain/Loss (Raw)": 1.9816462993621826, "Pretrain/Step": 8674, "Pretrain/Step Time": 8.799207048490644} +{"Pretrain/Learning Rate": 1.0635145542997772e-06, "Pretrain/Loss": 2.0233404636383057, "Pretrain/Loss (Raw)": 1.9314289093017578, "Pretrain/Step": 8675, "Pretrain/Step Time": 8.802563890814781} +{"Pretrain/Learning Rate": 1.0610660292744296e-06, "Pretrain/Loss": 2.0236623287200928, "Pretrain/Loss (Raw)": 2.015460729598999, "Pretrain/Step": 8676, "Pretrain/Step Time": 8.803512874990702} +{"Pretrain/Learning Rate": 1.0586202649997517e-06, "Pretrain/Loss": 2.0246996879577637, "Pretrain/Loss (Raw)": 2.0707221031188965, "Pretrain/Step": 8677, "Pretrain/Step Time": 8.80346511863172} +{"Pretrain/Learning Rate": 1.0561772617578014e-06, "Pretrain/Loss": 2.0253469944000244, "Pretrain/Loss (Raw)": 1.9721925258636475, "Pretrain/Step": 8678, "Pretrain/Step Time": 8.803881105035543} +{"Pretrain/Learning Rate": 1.0537370198303116e-06, "Pretrain/Loss": 2.0249409675598145, "Pretrain/Loss (Raw)": 1.8924174308776855, "Pretrain/Step": 8679, "Pretrain/Step Time": 8.802203109487891} +{"Pretrain/Learning Rate": 1.0512995394987096e-06, "Pretrain/Loss": 2.024811267852783, "Pretrain/Loss (Raw)": 1.8758325576782227, "Pretrain/Step": 8680, "Pretrain/Step Time": 8.799217322841287} +{"Pretrain/Learning Rate": 1.048864821044096e-06, "Pretrain/Loss": 2.0269272327423096, "Pretrain/Loss (Raw)": 2.262234687805176, "Pretrain/Step": 8681, "Pretrain/Step Time": 8.797286761924624} +{"Pretrain/Learning Rate": 1.0464328647472515e-06, "Pretrain/Loss": 2.0268917083740234, "Pretrain/Loss (Raw)": 2.1089203357696533, "Pretrain/Step": 8682, "Pretrain/Step Time": 8.797805309295654} +{"Pretrain/Learning Rate": 1.0440036708886407e-06, "Pretrain/Loss": 2.028393268585205, "Pretrain/Loss (Raw)": 2.0818331241607666, "Pretrain/Step": 8683, "Pretrain/Step Time": 8.798319237306714} +{"Pretrain/Learning Rate": 1.0415772397484119e-06, "Pretrain/Loss": 2.029440402984619, "Pretrain/Loss (Raw)": 2.0755109786987305, "Pretrain/Step": 8684, "Pretrain/Step Time": 8.798581909388304} +{"Pretrain/Learning Rate": 1.0391535716063938e-06, "Pretrain/Loss": 2.031795024871826, "Pretrain/Loss (Raw)": 2.202847480773926, "Pretrain/Step": 8685, "Pretrain/Step Time": 8.795419009402394} +{"Pretrain/Learning Rate": 1.0367326667420907e-06, "Pretrain/Loss": 2.031916618347168, "Pretrain/Loss (Raw)": 2.118736982345581, "Pretrain/Step": 8686, "Pretrain/Step Time": 8.798911472782493} +{"Pretrain/Learning Rate": 1.0343145254346931e-06, "Pretrain/Loss": 2.0335357189178467, "Pretrain/Loss (Raw)": 2.1667983531951904, "Pretrain/Step": 8687, "Pretrain/Step Time": 8.797302041202784} +{"Pretrain/Learning Rate": 1.031899147963078e-06, "Pretrain/Loss": 2.034498691558838, "Pretrain/Loss (Raw)": 2.058750629425049, "Pretrain/Step": 8688, "Pretrain/Step Time": 8.797299707308412} +{"Pretrain/Learning Rate": 1.0294865346057947e-06, "Pretrain/Loss": 2.033226728439331, "Pretrain/Loss (Raw)": 1.9670745134353638, "Pretrain/Step": 8689, "Pretrain/Step Time": 8.801242822781205} +{"Pretrain/Learning Rate": 1.0270766856410764e-06, "Pretrain/Loss": 2.0327134132385254, "Pretrain/Loss (Raw)": 1.8690646886825562, "Pretrain/Step": 8690, "Pretrain/Step Time": 8.804375935345888} +{"Pretrain/Learning Rate": 1.0246696013468338e-06, "Pretrain/Loss": 2.032522439956665, "Pretrain/Loss (Raw)": 2.1122677326202393, "Pretrain/Step": 8691, "Pretrain/Step Time": 8.805425364524126} +{"Pretrain/Learning Rate": 1.0222652820006785e-06, "Pretrain/Loss": 2.0318408012390137, "Pretrain/Loss (Raw)": 2.059152603149414, "Pretrain/Step": 8692, "Pretrain/Step Time": 8.800814481452107} +{"Pretrain/Learning Rate": 1.019863727879869e-06, "Pretrain/Loss": 2.0323026180267334, "Pretrain/Loss (Raw)": 2.105372667312622, "Pretrain/Step": 8693, "Pretrain/Step Time": 8.806226653978229} +{"Pretrain/Learning Rate": 1.0174649392613755e-06, "Pretrain/Loss": 2.03198504447937, "Pretrain/Loss (Raw)": 1.9777629375457764, "Pretrain/Step": 8694, "Pretrain/Step Time": 8.80277818068862} +{"Pretrain/Learning Rate": 1.0150689164218325e-06, "Pretrain/Loss": 2.033512830734253, "Pretrain/Loss (Raw)": 2.0476276874542236, "Pretrain/Step": 8695, "Pretrain/Step Time": 8.800747510045767} +{"Pretrain/Learning Rate": 1.0126756596375686e-06, "Pretrain/Loss": 2.0318238735198975, "Pretrain/Loss (Raw)": 1.8145207166671753, "Pretrain/Step": 8696, "Pretrain/Step Time": 8.80176410637796} +{"Pretrain/Learning Rate": 1.0102851691845716e-06, "Pretrain/Loss": 2.027857780456543, "Pretrain/Loss (Raw)": 1.5678924322128296, "Pretrain/Step": 8697, "Pretrain/Step Time": 8.799925988540053} +{"Pretrain/Learning Rate": 1.0078974453385375e-06, "Pretrain/Loss": 2.029709815979004, "Pretrain/Loss (Raw)": 2.0585145950317383, "Pretrain/Step": 8698, "Pretrain/Step Time": 8.798911293968558} +{"Pretrain/Learning Rate": 1.0055124883748213e-06, "Pretrain/Loss": 2.028054714202881, "Pretrain/Loss (Raw)": 1.6907172203063965, "Pretrain/Step": 8699, "Pretrain/Step Time": 8.79678813740611} +{"Pretrain/Learning Rate": 1.0031302985684777e-06, "Pretrain/Loss": 2.026827096939087, "Pretrain/Loss (Raw)": 2.0096073150634766, "Pretrain/Step": 8700, "Pretrain/Step Time": 8.801528541371226} +{"Pretrain/Learning Rate": 1.0007508761942176e-06, "Pretrain/Loss": 2.0267386436462402, "Pretrain/Loss (Raw)": 2.0364933013916016, "Pretrain/Step": 8701, "Pretrain/Step Time": 8.807400695979595} +{"Pretrain/Learning Rate": 9.983742215264575e-07, "Pretrain/Loss": 2.0263938903808594, "Pretrain/Loss (Raw)": 1.9217745065689087, "Pretrain/Step": 8702, "Pretrain/Step Time": 8.804094409570098} +{"Pretrain/Learning Rate": 9.96000334839281e-07, "Pretrain/Loss": 2.0251882076263428, "Pretrain/Loss (Raw)": 1.857210636138916, "Pretrain/Step": 8703, "Pretrain/Step Time": 8.800045374780893} +{"Pretrain/Learning Rate": 9.93629216406458e-07, "Pretrain/Loss": 2.025707960128784, "Pretrain/Loss (Raw)": 2.114328384399414, "Pretrain/Step": 8704, "Pretrain/Step Time": 8.802157577127218} +{"Pretrain/Learning Rate": 9.91260866501431e-07, "Pretrain/Loss": 2.026726245880127, "Pretrain/Loss (Raw)": 2.1811208724975586, "Pretrain/Step": 8705, "Pretrain/Step Time": 8.797456678003073} +{"Pretrain/Learning Rate": 9.888952853973371e-07, "Pretrain/Loss": 2.0278892517089844, "Pretrain/Loss (Raw)": 2.1065051555633545, "Pretrain/Step": 8706, "Pretrain/Step Time": 8.799575770273805} +{"Pretrain/Learning Rate": 9.86532473366983e-07, "Pretrain/Loss": 2.0263524055480957, "Pretrain/Loss (Raw)": 1.9435175657272339, "Pretrain/Step": 8707, "Pretrain/Step Time": 8.800718175247312} +{"Pretrain/Learning Rate": 9.841724306828587e-07, "Pretrain/Loss": 2.0309767723083496, "Pretrain/Loss (Raw)": 2.292449474334717, "Pretrain/Step": 8708, "Pretrain/Step Time": 8.799241308122873} +{"Pretrain/Learning Rate": 9.818151576171358e-07, "Pretrain/Loss": 2.03102445602417, "Pretrain/Loss (Raw)": 2.0252773761749268, "Pretrain/Step": 8709, "Pretrain/Step Time": 8.79374560713768} +{"Pretrain/Learning Rate": 9.794606544416662e-07, "Pretrain/Loss": 2.0326735973358154, "Pretrain/Loss (Raw)": 2.340592622756958, "Pretrain/Step": 8710, "Pretrain/Step Time": 8.787405272945762} +{"Pretrain/Learning Rate": 9.771089214279827e-07, "Pretrain/Loss": 2.031165838241577, "Pretrain/Loss (Raw)": 1.937027931213379, "Pretrain/Step": 8711, "Pretrain/Step Time": 8.78612306714058} +{"Pretrain/Learning Rate": 9.74759958847299e-07, "Pretrain/Loss": 2.0311756134033203, "Pretrain/Loss (Raw)": 2.0000834465026855, "Pretrain/Step": 8712, "Pretrain/Step Time": 8.785990990698338} +{"Pretrain/Learning Rate": 9.724137669705036e-07, "Pretrain/Loss": 2.031116008758545, "Pretrain/Loss (Raw)": 2.001098394393921, "Pretrain/Step": 8713, "Pretrain/Step Time": 8.78740388713777} +{"Pretrain/Learning Rate": 9.700703460681803e-07, "Pretrain/Loss": 2.0300943851470947, "Pretrain/Loss (Raw)": 1.9468729496002197, "Pretrain/Step": 8714, "Pretrain/Step Time": 8.780285315588117} +{"Pretrain/Learning Rate": 9.677296964105742e-07, "Pretrain/Loss": 2.0314557552337646, "Pretrain/Loss (Raw)": 1.8502641916275024, "Pretrain/Step": 8715, "Pretrain/Step Time": 8.785513561218977} +{"Pretrain/Learning Rate": 9.653918182676218e-07, "Pretrain/Loss": 2.03007435798645, "Pretrain/Loss (Raw)": 1.9251395463943481, "Pretrain/Step": 8716, "Pretrain/Step Time": 8.785194631665945} +{"Pretrain/Learning Rate": 9.630567119089412e-07, "Pretrain/Loss": 2.029778480529785, "Pretrain/Loss (Raw)": 2.1182568073272705, "Pretrain/Step": 8717, "Pretrain/Step Time": 8.784656256437302} +{"Pretrain/Learning Rate": 9.607243776038278e-07, "Pretrain/Loss": 2.0291686058044434, "Pretrain/Loss (Raw)": 1.7686429023742676, "Pretrain/Step": 8718, "Pretrain/Step Time": 8.788755115121603} +{"Pretrain/Learning Rate": 9.583948156212552e-07, "Pretrain/Loss": 2.03023099899292, "Pretrain/Loss (Raw)": 1.864738941192627, "Pretrain/Step": 8719, "Pretrain/Step Time": 8.79076536372304} +{"Pretrain/Learning Rate": 9.560680262298783e-07, "Pretrain/Loss": 2.030608892440796, "Pretrain/Loss (Raw)": 2.0131709575653076, "Pretrain/Step": 8720, "Pretrain/Step Time": 8.797934977337718} +{"Pretrain/Learning Rate": 9.537440096980377e-07, "Pretrain/Loss": 2.028992176055908, "Pretrain/Loss (Raw)": 2.0495731830596924, "Pretrain/Step": 8721, "Pretrain/Step Time": 8.792379094287753} +{"Pretrain/Learning Rate": 9.514227662937469e-07, "Pretrain/Loss": 2.0288519859313965, "Pretrain/Loss (Raw)": 2.0693607330322266, "Pretrain/Step": 8722, "Pretrain/Step Time": 8.799861151725054} +{"Pretrain/Learning Rate": 9.49104296284703e-07, "Pretrain/Loss": 2.0273044109344482, "Pretrain/Loss (Raw)": 2.0034379959106445, "Pretrain/Step": 8723, "Pretrain/Step Time": 8.798486899584532} +{"Pretrain/Learning Rate": 9.467885999382809e-07, "Pretrain/Loss": 2.0278613567352295, "Pretrain/Loss (Raw)": 2.1409568786621094, "Pretrain/Step": 8724, "Pretrain/Step Time": 8.799602562561631} +{"Pretrain/Learning Rate": 9.444756775215446e-07, "Pretrain/Loss": 2.027540683746338, "Pretrain/Loss (Raw)": 2.084031820297241, "Pretrain/Step": 8725, "Pretrain/Step Time": 8.803350137546659} +{"Pretrain/Learning Rate": 9.421655293012227e-07, "Pretrain/Loss": 2.0260400772094727, "Pretrain/Loss (Raw)": 1.9906468391418457, "Pretrain/Step": 8726, "Pretrain/Step Time": 8.79522554203868} +{"Pretrain/Learning Rate": 9.398581555437408e-07, "Pretrain/Loss": 2.0254859924316406, "Pretrain/Loss (Raw)": 2.017589569091797, "Pretrain/Step": 8727, "Pretrain/Step Time": 8.79760555922985} +{"Pretrain/Learning Rate": 9.375535565151861e-07, "Pretrain/Loss": 2.026789665222168, "Pretrain/Loss (Raw)": 2.162874937057495, "Pretrain/Step": 8728, "Pretrain/Step Time": 8.800755299627781} +{"Pretrain/Learning Rate": 9.352517324813431e-07, "Pretrain/Loss": 2.025186777114868, "Pretrain/Loss (Raw)": 2.0051429271698, "Pretrain/Step": 8729, "Pretrain/Step Time": 8.799294043332338} +{"Pretrain/Learning Rate": 9.329526837076691e-07, "Pretrain/Loss": 2.023422956466675, "Pretrain/Loss (Raw)": 1.9280651807785034, "Pretrain/Step": 8730, "Pretrain/Step Time": 8.794245122000575} +{"Pretrain/Learning Rate": 9.306564104592963e-07, "Pretrain/Loss": 2.022839307785034, "Pretrain/Loss (Raw)": 1.9888322353363037, "Pretrain/Step": 8731, "Pretrain/Step Time": 8.798938360065222} +{"Pretrain/Learning Rate": 9.283629130010463e-07, "Pretrain/Loss": 2.02462100982666, "Pretrain/Loss (Raw)": 2.1805686950683594, "Pretrain/Step": 8732, "Pretrain/Step Time": 8.799776030704379} +{"Pretrain/Learning Rate": 9.260721915974158e-07, "Pretrain/Loss": 2.0230140686035156, "Pretrain/Loss (Raw)": 1.929301381111145, "Pretrain/Step": 8733, "Pretrain/Step Time": 8.803471295163035} +{"Pretrain/Learning Rate": 9.237842465125768e-07, "Pretrain/Loss": 2.0241122245788574, "Pretrain/Loss (Raw)": 2.198526620864868, "Pretrain/Step": 8734, "Pretrain/Step Time": 8.79975308664143} +{"Pretrain/Learning Rate": 9.214990780103932e-07, "Pretrain/Loss": 2.0255465507507324, "Pretrain/Loss (Raw)": 2.1723806858062744, "Pretrain/Step": 8735, "Pretrain/Step Time": 8.801481440663338} +{"Pretrain/Learning Rate": 9.192166863543933e-07, "Pretrain/Loss": 2.0259289741516113, "Pretrain/Loss (Raw)": 2.1061720848083496, "Pretrain/Step": 8736, "Pretrain/Step Time": 8.797804852947593} +{"Pretrain/Learning Rate": 9.169370718078024e-07, "Pretrain/Loss": 2.0258266925811768, "Pretrain/Loss (Raw)": 2.0917201042175293, "Pretrain/Step": 8737, "Pretrain/Step Time": 8.803353203460574} +{"Pretrain/Learning Rate": 9.146602346335075e-07, "Pretrain/Loss": 2.0263683795928955, "Pretrain/Loss (Raw)": 2.013556480407715, "Pretrain/Step": 8738, "Pretrain/Step Time": 8.80053704045713} +{"Pretrain/Learning Rate": 9.123861750940904e-07, "Pretrain/Loss": 2.026735544204712, "Pretrain/Loss (Raw)": 2.1651952266693115, "Pretrain/Step": 8739, "Pretrain/Step Time": 8.804315827786922} +{"Pretrain/Learning Rate": 9.101148934518022e-07, "Pretrain/Loss": 2.0276260375976562, "Pretrain/Loss (Raw)": 2.079608917236328, "Pretrain/Step": 8740, "Pretrain/Step Time": 8.804857654497027} +{"Pretrain/Learning Rate": 9.078463899685835e-07, "Pretrain/Loss": 2.027745246887207, "Pretrain/Loss (Raw)": 2.0754921436309814, "Pretrain/Step": 8741, "Pretrain/Step Time": 8.801272727549076} +{"Pretrain/Learning Rate": 9.055806649060416e-07, "Pretrain/Loss": 2.0269999504089355, "Pretrain/Loss (Raw)": 1.975530743598938, "Pretrain/Step": 8742, "Pretrain/Step Time": 8.79550633765757} +{"Pretrain/Learning Rate": 9.033177185254732e-07, "Pretrain/Loss": 2.0269598960876465, "Pretrain/Loss (Raw)": 2.0077288150787354, "Pretrain/Step": 8743, "Pretrain/Step Time": 8.7938236258924} +{"Pretrain/Learning Rate": 9.010575510878555e-07, "Pretrain/Loss": 2.0279085636138916, "Pretrain/Loss (Raw)": 2.195697069168091, "Pretrain/Step": 8744, "Pretrain/Step Time": 8.795042725279927} +{"Pretrain/Learning Rate": 8.988001628538411e-07, "Pretrain/Loss": 2.0271286964416504, "Pretrain/Loss (Raw)": 1.9602837562561035, "Pretrain/Step": 8745, "Pretrain/Step Time": 8.784644728526473} +{"Pretrain/Learning Rate": 8.965455540837553e-07, "Pretrain/Loss": 2.0258750915527344, "Pretrain/Loss (Raw)": 2.0421085357666016, "Pretrain/Step": 8746, "Pretrain/Step Time": 8.792769625782967} +{"Pretrain/Learning Rate": 8.942937250376176e-07, "Pretrain/Loss": 2.026421308517456, "Pretrain/Loss (Raw)": 2.039475917816162, "Pretrain/Step": 8747, "Pretrain/Step Time": 8.796718899160624} +{"Pretrain/Learning Rate": 8.920446759751177e-07, "Pretrain/Loss": 2.02546763420105, "Pretrain/Loss (Raw)": 2.083211898803711, "Pretrain/Step": 8748, "Pretrain/Step Time": 8.798522448167205} +{"Pretrain/Learning Rate": 8.897984071556259e-07, "Pretrain/Loss": 2.026893138885498, "Pretrain/Loss (Raw)": 2.203641653060913, "Pretrain/Step": 8749, "Pretrain/Step Time": 8.803432568907738} +{"Pretrain/Learning Rate": 8.875549188381904e-07, "Pretrain/Loss": 2.0290281772613525, "Pretrain/Loss (Raw)": 2.1517510414123535, "Pretrain/Step": 8750, "Pretrain/Step Time": 8.804173218086362} +{"Pretrain/Learning Rate": 8.85314211281546e-07, "Pretrain/Loss": 2.030776023864746, "Pretrain/Loss (Raw)": 2.033679723739624, "Pretrain/Step": 8751, "Pretrain/Step Time": 8.804441569373012} +{"Pretrain/Learning Rate": 8.830762847440998e-07, "Pretrain/Loss": 2.0332000255584717, "Pretrain/Loss (Raw)": 2.129693031311035, "Pretrain/Step": 8752, "Pretrain/Step Time": 8.800065871328115} +{"Pretrain/Learning Rate": 8.808411394839372e-07, "Pretrain/Loss": 2.0320048332214355, "Pretrain/Loss (Raw)": 1.9332900047302246, "Pretrain/Step": 8753, "Pretrain/Step Time": 8.803256712853909} +{"Pretrain/Learning Rate": 8.786087757588269e-07, "Pretrain/Loss": 2.0308125019073486, "Pretrain/Loss (Raw)": 1.9789084196090698, "Pretrain/Step": 8754, "Pretrain/Step Time": 8.799651568755507} +{"Pretrain/Learning Rate": 8.763791938262184e-07, "Pretrain/Loss": 2.0313990116119385, "Pretrain/Loss (Raw)": 2.0471808910369873, "Pretrain/Step": 8755, "Pretrain/Step Time": 8.801143493503332} +{"Pretrain/Learning Rate": 8.741523939432339e-07, "Pretrain/Loss": 2.031980276107788, "Pretrain/Loss (Raw)": 2.1879396438598633, "Pretrain/Step": 8756, "Pretrain/Step Time": 8.801535971462727} +{"Pretrain/Learning Rate": 8.719283763666792e-07, "Pretrain/Loss": 2.0311474800109863, "Pretrain/Loss (Raw)": 1.8735458850860596, "Pretrain/Step": 8757, "Pretrain/Step Time": 8.800192929804325} +{"Pretrain/Learning Rate": 8.697071413530433e-07, "Pretrain/Loss": 2.029388427734375, "Pretrain/Loss (Raw)": 1.6962069272994995, "Pretrain/Step": 8758, "Pretrain/Step Time": 8.799877988174558} +{"Pretrain/Learning Rate": 8.674886891584827e-07, "Pretrain/Loss": 2.029942512512207, "Pretrain/Loss (Raw)": 1.9145063161849976, "Pretrain/Step": 8759, "Pretrain/Step Time": 8.800036408007145} +{"Pretrain/Learning Rate": 8.652730200388426e-07, "Pretrain/Loss": 2.0301787853240967, "Pretrain/Loss (Raw)": 1.9906513690948486, "Pretrain/Step": 8760, "Pretrain/Step Time": 8.80361619219184} +{"Pretrain/Learning Rate": 8.630601342496436e-07, "Pretrain/Loss": 2.0293755531311035, "Pretrain/Loss (Raw)": 2.057253122329712, "Pretrain/Step": 8761, "Pretrain/Step Time": 8.79974457807839} +{"Pretrain/Learning Rate": 8.608500320460899e-07, "Pretrain/Loss": 2.0287671089172363, "Pretrain/Loss (Raw)": 2.013282299041748, "Pretrain/Step": 8762, "Pretrain/Step Time": 8.807778857648373} +{"Pretrain/Learning Rate": 8.586427136830555e-07, "Pretrain/Loss": 2.0286641120910645, "Pretrain/Loss (Raw)": 1.8503085374832153, "Pretrain/Step": 8763, "Pretrain/Step Time": 8.809332503005862} +{"Pretrain/Learning Rate": 8.564381794151033e-07, "Pretrain/Loss": 2.0286619663238525, "Pretrain/Loss (Raw)": 1.9575334787368774, "Pretrain/Step": 8764, "Pretrain/Step Time": 8.808631805703044} +{"Pretrain/Learning Rate": 8.542364294964633e-07, "Pretrain/Loss": 2.0277347564697266, "Pretrain/Loss (Raw)": 2.025343179702759, "Pretrain/Step": 8765, "Pretrain/Step Time": 8.803010825067759} +{"Pretrain/Learning Rate": 8.52037464181063e-07, "Pretrain/Loss": 2.028362274169922, "Pretrain/Loss (Raw)": 2.114841938018799, "Pretrain/Step": 8766, "Pretrain/Step Time": 8.801322283223271} +{"Pretrain/Learning Rate": 8.498412837224884e-07, "Pretrain/Loss": 2.028566598892212, "Pretrain/Loss (Raw)": 1.973879337310791, "Pretrain/Step": 8767, "Pretrain/Step Time": 8.802868099883199} +{"Pretrain/Learning Rate": 8.476478883740175e-07, "Pretrain/Loss": 2.0267951488494873, "Pretrain/Loss (Raw)": 1.906090259552002, "Pretrain/Step": 8768, "Pretrain/Step Time": 8.80710405856371} +{"Pretrain/Learning Rate": 8.454572783885978e-07, "Pretrain/Loss": 2.024481773376465, "Pretrain/Loss (Raw)": 1.714005947113037, "Pretrain/Step": 8769, "Pretrain/Step Time": 8.80679733492434} +{"Pretrain/Learning Rate": 8.43269454018869e-07, "Pretrain/Loss": 2.025209426879883, "Pretrain/Loss (Raw)": 2.113816738128662, "Pretrain/Step": 8770, "Pretrain/Step Time": 8.804841140285134} +{"Pretrain/Learning Rate": 8.410844155171376e-07, "Pretrain/Loss": 2.025404691696167, "Pretrain/Loss (Raw)": 2.2115352153778076, "Pretrain/Step": 8771, "Pretrain/Step Time": 8.804025305435061} +{"Pretrain/Learning Rate": 8.389021631353911e-07, "Pretrain/Loss": 2.0248446464538574, "Pretrain/Loss (Raw)": 1.8614195585250854, "Pretrain/Step": 8772, "Pretrain/Step Time": 8.799033531919122} +{"Pretrain/Learning Rate": 8.367226971252945e-07, "Pretrain/Loss": 2.0236809253692627, "Pretrain/Loss (Raw)": 2.0254220962524414, "Pretrain/Step": 8773, "Pretrain/Step Time": 8.799491273239255} +{"Pretrain/Learning Rate": 8.345460177381998e-07, "Pretrain/Loss": 2.023711681365967, "Pretrain/Loss (Raw)": 2.0115954875946045, "Pretrain/Step": 8774, "Pretrain/Step Time": 8.800268871709704} +{"Pretrain/Learning Rate": 8.323721252251309e-07, "Pretrain/Loss": 2.023817539215088, "Pretrain/Loss (Raw)": 2.129863977432251, "Pretrain/Step": 8775, "Pretrain/Step Time": 8.802784601226449} +{"Pretrain/Learning Rate": 8.302010198367904e-07, "Pretrain/Loss": 2.0220210552215576, "Pretrain/Loss (Raw)": 1.8112587928771973, "Pretrain/Step": 8776, "Pretrain/Step Time": 8.806107761338353} +{"Pretrain/Learning Rate": 8.280327018235556e-07, "Pretrain/Loss": 2.02321195602417, "Pretrain/Loss (Raw)": 2.2641074657440186, "Pretrain/Step": 8777, "Pretrain/Step Time": 8.798651253804564} +{"Pretrain/Learning Rate": 8.258671714354987e-07, "Pretrain/Loss": 2.0228021144866943, "Pretrain/Loss (Raw)": 1.8786026239395142, "Pretrain/Step": 8778, "Pretrain/Step Time": 8.802207615226507} +{"Pretrain/Learning Rate": 8.23704428922345e-07, "Pretrain/Loss": 2.0209593772888184, "Pretrain/Loss (Raw)": 1.8836790323257446, "Pretrain/Step": 8779, "Pretrain/Step Time": 8.812581576406956} +{"Pretrain/Learning Rate": 8.215444745335227e-07, "Pretrain/Loss": 2.016787052154541, "Pretrain/Loss (Raw)": 1.469030737876892, "Pretrain/Step": 8780, "Pretrain/Step Time": 8.799430068582296} +{"Pretrain/Learning Rate": 8.193873085181214e-07, "Pretrain/Loss": 2.016090154647827, "Pretrain/Loss (Raw)": 1.9435901641845703, "Pretrain/Step": 8781, "Pretrain/Step Time": 8.797904431819916} +{"Pretrain/Learning Rate": 8.172329311249255e-07, "Pretrain/Loss": 2.013734817504883, "Pretrain/Loss (Raw)": 2.0610904693603516, "Pretrain/Step": 8782, "Pretrain/Step Time": 8.807011956349015} +{"Pretrain/Learning Rate": 8.150813426023751e-07, "Pretrain/Loss": 2.0129215717315674, "Pretrain/Loss (Raw)": 2.1458756923675537, "Pretrain/Step": 8783, "Pretrain/Step Time": 8.801420573145151} +{"Pretrain/Learning Rate": 8.129325431986079e-07, "Pretrain/Loss": 2.0124285221099854, "Pretrain/Loss (Raw)": 2.011002540588379, "Pretrain/Step": 8784, "Pretrain/Step Time": 8.797674024477601} +{"Pretrain/Learning Rate": 8.107865331614339e-07, "Pretrain/Loss": 2.0139315128326416, "Pretrain/Loss (Raw)": 1.9401063919067383, "Pretrain/Step": 8785, "Pretrain/Step Time": 8.801327746361494} +{"Pretrain/Learning Rate": 8.086433127383413e-07, "Pretrain/Loss": 2.0138487815856934, "Pretrain/Loss (Raw)": 2.119551181793213, "Pretrain/Step": 8786, "Pretrain/Step Time": 8.799002850428224} +{"Pretrain/Learning Rate": 8.065028821764909e-07, "Pretrain/Loss": 2.015170097351074, "Pretrain/Loss (Raw)": 2.127917528152466, "Pretrain/Step": 8787, "Pretrain/Step Time": 8.79332491196692} +{"Pretrain/Learning Rate": 8.043652417227349e-07, "Pretrain/Loss": 2.0166900157928467, "Pretrain/Loss (Raw)": 2.104616403579712, "Pretrain/Step": 8788, "Pretrain/Step Time": 8.795626550912857} +{"Pretrain/Learning Rate": 8.022303916235929e-07, "Pretrain/Loss": 2.0177013874053955, "Pretrain/Loss (Raw)": 2.1032164096832275, "Pretrain/Step": 8789, "Pretrain/Step Time": 8.80081151239574} +{"Pretrain/Learning Rate": 8.000983321252681e-07, "Pretrain/Loss": 2.0159921646118164, "Pretrain/Loss (Raw)": 1.9533054828643799, "Pretrain/Step": 8790, "Pretrain/Step Time": 8.795634465292096} +{"Pretrain/Learning Rate": 7.979690634736304e-07, "Pretrain/Loss": 2.0168821811676025, "Pretrain/Loss (Raw)": 2.0006628036499023, "Pretrain/Step": 8791, "Pretrain/Step Time": 8.792710537090898} +{"Pretrain/Learning Rate": 7.958425859142498e-07, "Pretrain/Loss": 2.017171621322632, "Pretrain/Loss (Raw)": 2.0830068588256836, "Pretrain/Step": 8792, "Pretrain/Step Time": 8.789453046396375} +{"Pretrain/Learning Rate": 7.937188996923556e-07, "Pretrain/Loss": 2.0186240673065186, "Pretrain/Loss (Raw)": 2.0229244232177734, "Pretrain/Step": 8793, "Pretrain/Step Time": 8.791618295013905} +{"Pretrain/Learning Rate": 7.915980050528599e-07, "Pretrain/Loss": 2.017116069793701, "Pretrain/Loss (Raw)": 2.054513692855835, "Pretrain/Step": 8794, "Pretrain/Step Time": 8.790174698457122} +{"Pretrain/Learning Rate": 7.894799022403532e-07, "Pretrain/Loss": 2.0176291465759277, "Pretrain/Loss (Raw)": 2.0829086303710938, "Pretrain/Step": 8795, "Pretrain/Step Time": 8.793701827526093} +{"Pretrain/Learning Rate": 7.873645914991123e-07, "Pretrain/Loss": 2.0218491554260254, "Pretrain/Loss (Raw)": 2.4201598167419434, "Pretrain/Step": 8796, "Pretrain/Step Time": 8.788984403014183} +{"Pretrain/Learning Rate": 7.852520730730812e-07, "Pretrain/Loss": 2.0233702659606934, "Pretrain/Loss (Raw)": 2.1931517124176025, "Pretrain/Step": 8797, "Pretrain/Step Time": 8.794555673375726} +{"Pretrain/Learning Rate": 7.831423472058785e-07, "Pretrain/Loss": 2.023491859436035, "Pretrain/Loss (Raw)": 2.1229283809661865, "Pretrain/Step": 8798, "Pretrain/Step Time": 8.787281759083271} +{"Pretrain/Learning Rate": 7.810354141408211e-07, "Pretrain/Loss": 2.0249714851379395, "Pretrain/Loss (Raw)": 2.055133819580078, "Pretrain/Step": 8799, "Pretrain/Step Time": 8.789420258253813} +{"Pretrain/Learning Rate": 7.789312741208809e-07, "Pretrain/Loss": 2.0247631072998047, "Pretrain/Loss (Raw)": 2.027008056640625, "Pretrain/Step": 8800, "Pretrain/Step Time": 8.794061647728086} +{"Pretrain/Learning Rate": 7.768299273887198e-07, "Pretrain/Loss": 2.024986982345581, "Pretrain/Loss (Raw)": 2.1152381896972656, "Pretrain/Step": 8801, "Pretrain/Step Time": 8.787692554295063} +{"Pretrain/Learning Rate": 7.747313741866713e-07, "Pretrain/Loss": 2.027024745941162, "Pretrain/Loss (Raw)": 2.242478847503662, "Pretrain/Step": 8802, "Pretrain/Step Time": 8.789154674857855} +{"Pretrain/Learning Rate": 7.726356147567559e-07, "Pretrain/Loss": 2.026848316192627, "Pretrain/Loss (Raw)": 1.9088466167449951, "Pretrain/Step": 8803, "Pretrain/Step Time": 8.786697536706924} +{"Pretrain/Learning Rate": 7.705426493406665e-07, "Pretrain/Loss": 2.0235595703125, "Pretrain/Loss (Raw)": 1.5945305824279785, "Pretrain/Step": 8804, "Pretrain/Step Time": 8.78667101264} +{"Pretrain/Learning Rate": 7.684524781797708e-07, "Pretrain/Loss": 2.0239832401275635, "Pretrain/Loss (Raw)": 2.124934673309326, "Pretrain/Step": 8805, "Pretrain/Step Time": 8.787743797525764} +{"Pretrain/Learning Rate": 7.663651015151152e-07, "Pretrain/Loss": 2.0232903957366943, "Pretrain/Loss (Raw)": 1.8835053443908691, "Pretrain/Step": 8806, "Pretrain/Step Time": 8.787638047710061} +{"Pretrain/Learning Rate": 7.64280519587432e-07, "Pretrain/Loss": 2.024301767349243, "Pretrain/Loss (Raw)": 2.021876096725464, "Pretrain/Step": 8807, "Pretrain/Step Time": 8.78864536434412} +{"Pretrain/Learning Rate": 7.621987326371205e-07, "Pretrain/Loss": 2.025852680206299, "Pretrain/Loss (Raw)": 2.074371099472046, "Pretrain/Step": 8808, "Pretrain/Step Time": 8.789926063269377} +{"Pretrain/Learning Rate": 7.601197409042665e-07, "Pretrain/Loss": 2.0248355865478516, "Pretrain/Loss (Raw)": 2.1320457458496094, "Pretrain/Step": 8809, "Pretrain/Step Time": 8.793271912261844} +{"Pretrain/Learning Rate": 7.5804354462862e-07, "Pretrain/Loss": 2.0246825218200684, "Pretrain/Loss (Raw)": 2.0892958641052246, "Pretrain/Step": 8810, "Pretrain/Step Time": 8.792685868218541} +{"Pretrain/Learning Rate": 7.55970144049628e-07, "Pretrain/Loss": 2.02482008934021, "Pretrain/Loss (Raw)": 2.0994415283203125, "Pretrain/Step": 8811, "Pretrain/Step Time": 8.790169768035412} +{"Pretrain/Learning Rate": 7.538995394063996e-07, "Pretrain/Loss": 2.0255441665649414, "Pretrain/Loss (Raw)": 2.16823148727417, "Pretrain/Step": 8812, "Pretrain/Step Time": 8.792477775365114} +{"Pretrain/Learning Rate": 7.518317309377298e-07, "Pretrain/Loss": 2.0239758491516113, "Pretrain/Loss (Raw)": 2.0020720958709717, "Pretrain/Step": 8813, "Pretrain/Step Time": 8.792757431045175} +{"Pretrain/Learning Rate": 7.497667188820834e-07, "Pretrain/Loss": 2.0231237411499023, "Pretrain/Loss (Raw)": 2.0096685886383057, "Pretrain/Step": 8814, "Pretrain/Step Time": 8.804705433547497} +{"Pretrain/Learning Rate": 7.477045034776087e-07, "Pretrain/Loss": 2.021846294403076, "Pretrain/Loss (Raw)": 2.0032689571380615, "Pretrain/Step": 8815, "Pretrain/Step Time": 8.793723694980145} +{"Pretrain/Learning Rate": 7.45645084962135e-07, "Pretrain/Loss": 2.021450996398926, "Pretrain/Loss (Raw)": 2.0081534385681152, "Pretrain/Step": 8816, "Pretrain/Step Time": 8.7990786395967} +{"Pretrain/Learning Rate": 7.435884635731582e-07, "Pretrain/Loss": 2.022052764892578, "Pretrain/Loss (Raw)": 2.044102668762207, "Pretrain/Step": 8817, "Pretrain/Step Time": 8.795285942032933} +{"Pretrain/Learning Rate": 7.415346395478584e-07, "Pretrain/Loss": 2.0250372886657715, "Pretrain/Loss (Raw)": 2.251102924346924, "Pretrain/Step": 8818, "Pretrain/Step Time": 8.79362997226417} +{"Pretrain/Learning Rate": 7.394836131230987e-07, "Pretrain/Loss": 2.024540424346924, "Pretrain/Loss (Raw)": 2.0486631393432617, "Pretrain/Step": 8819, "Pretrain/Step Time": 8.794636733829975} +{"Pretrain/Learning Rate": 7.37435384535401e-07, "Pretrain/Loss": 2.024704933166504, "Pretrain/Loss (Raw)": 2.08024525642395, "Pretrain/Step": 8820, "Pretrain/Step Time": 8.794022707268596} +{"Pretrain/Learning Rate": 7.353899540209902e-07, "Pretrain/Loss": 2.024322986602783, "Pretrain/Loss (Raw)": 2.056431293487549, "Pretrain/Step": 8821, "Pretrain/Step Time": 8.791409952566028} +{"Pretrain/Learning Rate": 7.333473218157416e-07, "Pretrain/Loss": 2.02534818649292, "Pretrain/Loss (Raw)": 2.1090009212493896, "Pretrain/Step": 8822, "Pretrain/Step Time": 8.796373564749956} +{"Pretrain/Learning Rate": 7.313074881552362e-07, "Pretrain/Loss": 2.027438163757324, "Pretrain/Loss (Raw)": 2.3151509761810303, "Pretrain/Step": 8823, "Pretrain/Step Time": 8.796062875539064} +{"Pretrain/Learning Rate": 7.292704532747024e-07, "Pretrain/Loss": 2.0296449661254883, "Pretrain/Loss (Raw)": 2.096996307373047, "Pretrain/Step": 8824, "Pretrain/Step Time": 8.794791035354137} +{"Pretrain/Learning Rate": 7.272362174090691e-07, "Pretrain/Loss": 2.0331668853759766, "Pretrain/Loss (Raw)": 2.018720865249634, "Pretrain/Step": 8825, "Pretrain/Step Time": 8.796752175316215} +{"Pretrain/Learning Rate": 7.252047807929347e-07, "Pretrain/Loss": 2.034829616546631, "Pretrain/Loss (Raw)": 2.2713284492492676, "Pretrain/Step": 8826, "Pretrain/Step Time": 8.797900388017297} +{"Pretrain/Learning Rate": 7.2317614366057e-07, "Pretrain/Loss": 2.036386013031006, "Pretrain/Loss (Raw)": 1.8899130821228027, "Pretrain/Step": 8827, "Pretrain/Step Time": 8.797543369233608} +{"Pretrain/Learning Rate": 7.211503062459268e-07, "Pretrain/Loss": 2.037179946899414, "Pretrain/Loss (Raw)": 2.111241102218628, "Pretrain/Step": 8828, "Pretrain/Step Time": 8.790903929620981} +{"Pretrain/Learning Rate": 7.191272687826378e-07, "Pretrain/Loss": 2.0369491577148438, "Pretrain/Loss (Raw)": 2.006964921951294, "Pretrain/Step": 8829, "Pretrain/Step Time": 8.797230569645762} +{"Pretrain/Learning Rate": 7.17107031504008e-07, "Pretrain/Loss": 2.036201238632202, "Pretrain/Loss (Raw)": 1.8260351419448853, "Pretrain/Step": 8830, "Pretrain/Step Time": 8.800250438973308} +{"Pretrain/Learning Rate": 7.150895946430203e-07, "Pretrain/Loss": 2.0371434688568115, "Pretrain/Loss (Raw)": 1.9778228998184204, "Pretrain/Step": 8831, "Pretrain/Step Time": 8.802418168634176} +{"Pretrain/Learning Rate": 7.130749584323304e-07, "Pretrain/Loss": 2.037047863006592, "Pretrain/Loss (Raw)": 2.1020760536193848, "Pretrain/Step": 8832, "Pretrain/Step Time": 8.798454472795129} +{"Pretrain/Learning Rate": 7.110631231042858e-07, "Pretrain/Loss": 2.0350840091705322, "Pretrain/Loss (Raw)": 1.9297610521316528, "Pretrain/Step": 8833, "Pretrain/Step Time": 8.807536469772458} +{"Pretrain/Learning Rate": 7.090540888908925e-07, "Pretrain/Loss": 2.0345633029937744, "Pretrain/Loss (Raw)": 2.039841651916504, "Pretrain/Step": 8834, "Pretrain/Step Time": 8.80434294603765} +{"Pretrain/Learning Rate": 7.070478560238458e-07, "Pretrain/Loss": 2.035867691040039, "Pretrain/Loss (Raw)": 2.1104958057403564, "Pretrain/Step": 8835, "Pretrain/Step Time": 8.80402535945177} +{"Pretrain/Learning Rate": 7.050444247345078e-07, "Pretrain/Loss": 2.0323286056518555, "Pretrain/Loss (Raw)": 1.839447259902954, "Pretrain/Step": 8836, "Pretrain/Step Time": 8.802642604336143} +{"Pretrain/Learning Rate": 7.030437952539326e-07, "Pretrain/Loss": 2.033609390258789, "Pretrain/Loss (Raw)": 2.1892192363739014, "Pretrain/Step": 8837, "Pretrain/Step Time": 8.8060133587569} +{"Pretrain/Learning Rate": 7.010459678128384e-07, "Pretrain/Loss": 2.0313289165496826, "Pretrain/Loss (Raw)": 2.0486738681793213, "Pretrain/Step": 8838, "Pretrain/Step Time": 8.805361507460475} +{"Pretrain/Learning Rate": 6.990509426416186e-07, "Pretrain/Loss": 2.0325231552124023, "Pretrain/Loss (Raw)": 2.0899012088775635, "Pretrain/Step": 8839, "Pretrain/Step Time": 8.80464711971581} +{"Pretrain/Learning Rate": 6.970587199703588e-07, "Pretrain/Loss": 2.0317037105560303, "Pretrain/Loss (Raw)": 1.8951762914657593, "Pretrain/Step": 8840, "Pretrain/Step Time": 8.803182154893875} +{"Pretrain/Learning Rate": 6.950693000288055e-07, "Pretrain/Loss": 2.032895088195801, "Pretrain/Loss (Raw)": 2.1536214351654053, "Pretrain/Step": 8841, "Pretrain/Step Time": 8.807986613363028} +{"Pretrain/Learning Rate": 6.930826830463922e-07, "Pretrain/Loss": 2.033895492553711, "Pretrain/Loss (Raw)": 2.074917793273926, "Pretrain/Step": 8842, "Pretrain/Step Time": 8.810403624549508} +{"Pretrain/Learning Rate": 6.910988692522158e-07, "Pretrain/Loss": 2.035346031188965, "Pretrain/Loss (Raw)": 2.0359387397766113, "Pretrain/Step": 8843, "Pretrain/Step Time": 8.805690683424473} +{"Pretrain/Learning Rate": 6.891178588750686e-07, "Pretrain/Loss": 2.0362563133239746, "Pretrain/Loss (Raw)": 2.0416300296783447, "Pretrain/Step": 8844, "Pretrain/Step Time": 8.804083358496428} +{"Pretrain/Learning Rate": 6.871396521434065e-07, "Pretrain/Loss": 2.034518241882324, "Pretrain/Loss (Raw)": 1.8957912921905518, "Pretrain/Step": 8845, "Pretrain/Step Time": 8.80747440084815} +{"Pretrain/Learning Rate": 6.851642492853666e-07, "Pretrain/Loss": 2.034951686859131, "Pretrain/Loss (Raw)": 1.8241208791732788, "Pretrain/Step": 8846, "Pretrain/Step Time": 8.803286839276552} +{"Pretrain/Learning Rate": 6.831916505287555e-07, "Pretrain/Loss": 2.035470962524414, "Pretrain/Loss (Raw)": 1.931233286857605, "Pretrain/Step": 8847, "Pretrain/Step Time": 8.800962327048182} +{"Pretrain/Learning Rate": 6.812218561010719e-07, "Pretrain/Loss": 2.035613536834717, "Pretrain/Loss (Raw)": 2.031409502029419, "Pretrain/Step": 8848, "Pretrain/Step Time": 8.792967891320586} +{"Pretrain/Learning Rate": 6.792548662294785e-07, "Pretrain/Loss": 2.0350987911224365, "Pretrain/Loss (Raw)": 1.9836839437484741, "Pretrain/Step": 8849, "Pretrain/Step Time": 8.79412984289229} +{"Pretrain/Learning Rate": 6.772906811408159e-07, "Pretrain/Loss": 2.0357418060302734, "Pretrain/Loss (Raw)": 2.1516594886779785, "Pretrain/Step": 8850, "Pretrain/Step Time": 8.792654750868678} +{"Pretrain/Learning Rate": 6.75329301061603e-07, "Pretrain/Loss": 2.036550760269165, "Pretrain/Loss (Raw)": 2.1069889068603516, "Pretrain/Step": 8851, "Pretrain/Step Time": 8.795004615560174} +{"Pretrain/Learning Rate": 6.733707262180394e-07, "Pretrain/Loss": 2.0367913246154785, "Pretrain/Loss (Raw)": 2.1717491149902344, "Pretrain/Step": 8852, "Pretrain/Step Time": 8.800405986607075} +{"Pretrain/Learning Rate": 6.714149568359945e-07, "Pretrain/Loss": 2.0378754138946533, "Pretrain/Loss (Raw)": 2.2227816581726074, "Pretrain/Step": 8853, "Pretrain/Step Time": 8.800814336165786} +{"Pretrain/Learning Rate": 6.694619931410156e-07, "Pretrain/Loss": 2.037675380706787, "Pretrain/Loss (Raw)": 1.9650509357452393, "Pretrain/Step": 8854, "Pretrain/Step Time": 8.803073653951287} +{"Pretrain/Learning Rate": 6.675118353583254e-07, "Pretrain/Loss": 2.037534713745117, "Pretrain/Loss (Raw)": 1.999596118927002, "Pretrain/Step": 8855, "Pretrain/Step Time": 8.799945566803217} +{"Pretrain/Learning Rate": 6.655644837128328e-07, "Pretrain/Loss": 2.0359013080596924, "Pretrain/Loss (Raw)": 1.9537831544876099, "Pretrain/Step": 8856, "Pretrain/Step Time": 8.80198360979557} +{"Pretrain/Learning Rate": 6.636199384291137e-07, "Pretrain/Loss": 2.035494327545166, "Pretrain/Loss (Raw)": 1.9530551433563232, "Pretrain/Step": 8857, "Pretrain/Step Time": 8.806371362879872} +{"Pretrain/Learning Rate": 6.616781997314164e-07, "Pretrain/Loss": 2.0353503227233887, "Pretrain/Loss (Raw)": 1.9096159934997559, "Pretrain/Step": 8858, "Pretrain/Step Time": 8.801138756796718} +{"Pretrain/Learning Rate": 6.597392678436731e-07, "Pretrain/Loss": 2.03840708732605, "Pretrain/Loss (Raw)": 2.380114793777466, "Pretrain/Step": 8859, "Pretrain/Step Time": 8.802143819630146} +{"Pretrain/Learning Rate": 6.578031429894993e-07, "Pretrain/Loss": 2.0378851890563965, "Pretrain/Loss (Raw)": 2.113788366317749, "Pretrain/Step": 8860, "Pretrain/Step Time": 8.80441871844232} +{"Pretrain/Learning Rate": 6.558698253921664e-07, "Pretrain/Loss": 2.0386340618133545, "Pretrain/Loss (Raw)": 2.025139331817627, "Pretrain/Step": 8861, "Pretrain/Step Time": 8.795100510120392} +{"Pretrain/Learning Rate": 6.539393152746404e-07, "Pretrain/Loss": 2.03787899017334, "Pretrain/Loss (Raw)": 2.1018776893615723, "Pretrain/Step": 8862, "Pretrain/Step Time": 8.802506979554892} +{"Pretrain/Learning Rate": 6.520116128595516e-07, "Pretrain/Loss": 2.0361952781677246, "Pretrain/Loss (Raw)": 1.9568687677383423, "Pretrain/Step": 8863, "Pretrain/Step Time": 8.798174737021327} +{"Pretrain/Learning Rate": 6.500867183692195e-07, "Pretrain/Loss": 2.035651206970215, "Pretrain/Loss (Raw)": 2.03651762008667, "Pretrain/Step": 8864, "Pretrain/Step Time": 8.8058149125427} +{"Pretrain/Learning Rate": 6.481646320256246e-07, "Pretrain/Loss": 2.0353424549102783, "Pretrain/Loss (Raw)": 2.0522074699401855, "Pretrain/Step": 8865, "Pretrain/Step Time": 8.796354107558727} +{"Pretrain/Learning Rate": 6.462453540504343e-07, "Pretrain/Loss": 2.0351946353912354, "Pretrain/Loss (Raw)": 1.994621992111206, "Pretrain/Step": 8866, "Pretrain/Step Time": 8.79406994394958} +{"Pretrain/Learning Rate": 6.443288846649881e-07, "Pretrain/Loss": 2.034297466278076, "Pretrain/Loss (Raw)": 2.0503456592559814, "Pretrain/Step": 8867, "Pretrain/Step Time": 8.794187657535076} +{"Pretrain/Learning Rate": 6.424152240903065e-07, "Pretrain/Loss": 2.0345163345336914, "Pretrain/Loss (Raw)": 2.107640027999878, "Pretrain/Step": 8868, "Pretrain/Step Time": 8.793447144329548} +{"Pretrain/Learning Rate": 6.405043725470738e-07, "Pretrain/Loss": 2.0337910652160645, "Pretrain/Loss (Raw)": 1.9826734066009521, "Pretrain/Step": 8869, "Pretrain/Step Time": 8.795216357335448} +{"Pretrain/Learning Rate": 6.385963302556641e-07, "Pretrain/Loss": 2.0342283248901367, "Pretrain/Loss (Raw)": 2.0315027236938477, "Pretrain/Step": 8870, "Pretrain/Step Time": 8.79660121910274} +{"Pretrain/Learning Rate": 6.366910974361206e-07, "Pretrain/Loss": 2.0324578285217285, "Pretrain/Loss (Raw)": 1.781125545501709, "Pretrain/Step": 8871, "Pretrain/Step Time": 8.804238079115748} +{"Pretrain/Learning Rate": 6.347886743081649e-07, "Pretrain/Loss": 2.031346321105957, "Pretrain/Loss (Raw)": 2.0533833503723145, "Pretrain/Step": 8872, "Pretrain/Step Time": 8.800841564312577} +{"Pretrain/Learning Rate": 6.328890610911881e-07, "Pretrain/Loss": 2.0319314002990723, "Pretrain/Loss (Raw)": 2.0351927280426025, "Pretrain/Step": 8873, "Pretrain/Step Time": 8.803407929837704} +{"Pretrain/Learning Rate": 6.309922580042676e-07, "Pretrain/Loss": 2.0315823554992676, "Pretrain/Loss (Raw)": 1.9974069595336914, "Pretrain/Step": 8874, "Pretrain/Step Time": 8.799401635304093} +{"Pretrain/Learning Rate": 6.290982652661509e-07, "Pretrain/Loss": 2.0315823554992676, "Pretrain/Loss (Raw)": 2.039466142654419, "Pretrain/Step": 8875, "Pretrain/Step Time": 8.797160303220153} +{"Pretrain/Learning Rate": 6.272070830952631e-07, "Pretrain/Loss": 2.031066656112671, "Pretrain/Loss (Raw)": 2.017244338989258, "Pretrain/Step": 8876, "Pretrain/Step Time": 8.797417171299458} +{"Pretrain/Learning Rate": 6.253187117096992e-07, "Pretrain/Loss": 2.0302696228027344, "Pretrain/Loss (Raw)": 2.101602792739868, "Pretrain/Step": 8877, "Pretrain/Step Time": 8.792551819235086} +{"Pretrain/Learning Rate": 6.234331513272435e-07, "Pretrain/Loss": 2.0290255546569824, "Pretrain/Loss (Raw)": 1.9925193786621094, "Pretrain/Step": 8878, "Pretrain/Step Time": 8.795914568006992} +{"Pretrain/Learning Rate": 6.215504021653412e-07, "Pretrain/Loss": 2.029839038848877, "Pretrain/Loss (Raw)": 2.1378204822540283, "Pretrain/Step": 8879, "Pretrain/Step Time": 8.792068995535374} +{"Pretrain/Learning Rate": 6.196704644411189e-07, "Pretrain/Loss": 2.0296645164489746, "Pretrain/Loss (Raw)": 2.107325315475464, "Pretrain/Step": 8880, "Pretrain/Step Time": 8.788185520097613} +{"Pretrain/Learning Rate": 6.177933383713835e-07, "Pretrain/Loss": 2.031391143798828, "Pretrain/Loss (Raw)": 2.154282569885254, "Pretrain/Step": 8881, "Pretrain/Step Time": 8.792116239666939} +{"Pretrain/Learning Rate": 6.159190241726148e-07, "Pretrain/Loss": 2.0319437980651855, "Pretrain/Loss (Raw)": 2.049651861190796, "Pretrain/Step": 8882, "Pretrain/Step Time": 8.792517172172666} +{"Pretrain/Learning Rate": 6.140475220609676e-07, "Pretrain/Loss": 2.032332420349121, "Pretrain/Loss (Raw)": 2.0969529151916504, "Pretrain/Step": 8883, "Pretrain/Step Time": 8.793380232527852} +{"Pretrain/Learning Rate": 6.121788322522637e-07, "Pretrain/Loss": 2.0315604209899902, "Pretrain/Loss (Raw)": 2.089128017425537, "Pretrain/Step": 8884, "Pretrain/Step Time": 8.792430045083165} +{"Pretrain/Learning Rate": 6.103129549620223e-07, "Pretrain/Loss": 2.0310122966766357, "Pretrain/Loss (Raw)": 1.8033732175827026, "Pretrain/Step": 8885, "Pretrain/Step Time": 8.795880306512117} +{"Pretrain/Learning Rate": 6.084498904054187e-07, "Pretrain/Loss": 2.0341410636901855, "Pretrain/Loss (Raw)": 2.0967180728912354, "Pretrain/Step": 8886, "Pretrain/Step Time": 8.788751415908337} +{"Pretrain/Learning Rate": 6.065896387973086e-07, "Pretrain/Loss": 2.0348849296569824, "Pretrain/Loss (Raw)": 2.0096871852874756, "Pretrain/Step": 8887, "Pretrain/Step Time": 8.787108566612005} +{"Pretrain/Learning Rate": 6.04732200352226e-07, "Pretrain/Loss": 2.0356931686401367, "Pretrain/Loss (Raw)": 2.094101667404175, "Pretrain/Step": 8888, "Pretrain/Step Time": 8.781015440821648} +{"Pretrain/Learning Rate": 6.028775752843801e-07, "Pretrain/Loss": 2.0351176261901855, "Pretrain/Loss (Raw)": 1.9836175441741943, "Pretrain/Step": 8889, "Pretrain/Step Time": 8.787261970341206} +{"Pretrain/Learning Rate": 6.010257638076583e-07, "Pretrain/Loss": 2.0348927974700928, "Pretrain/Loss (Raw)": 1.9844717979431152, "Pretrain/Step": 8890, "Pretrain/Step Time": 8.78286849334836} +{"Pretrain/Learning Rate": 5.991767661356145e-07, "Pretrain/Loss": 2.036011219024658, "Pretrain/Loss (Raw)": 1.9934687614440918, "Pretrain/Step": 8891, "Pretrain/Step Time": 8.78037222288549} +{"Pretrain/Learning Rate": 5.973305824814867e-07, "Pretrain/Loss": 2.036708354949951, "Pretrain/Loss (Raw)": 2.046797752380371, "Pretrain/Step": 8892, "Pretrain/Step Time": 8.78387158177793} +{"Pretrain/Learning Rate": 5.954872130581851e-07, "Pretrain/Loss": 2.036620616912842, "Pretrain/Loss (Raw)": 2.0140767097473145, "Pretrain/Step": 8893, "Pretrain/Step Time": 8.779049029573798} +{"Pretrain/Learning Rate": 5.936466580782979e-07, "Pretrain/Loss": 2.036626100540161, "Pretrain/Loss (Raw)": 2.1155574321746826, "Pretrain/Step": 8894, "Pretrain/Step Time": 8.779911316931248} +{"Pretrain/Learning Rate": 5.918089177540858e-07, "Pretrain/Loss": 2.037396192550659, "Pretrain/Loss (Raw)": 2.072453260421753, "Pretrain/Step": 8895, "Pretrain/Step Time": 8.778425846248865} +{"Pretrain/Learning Rate": 5.899739922974795e-07, "Pretrain/Loss": 2.0386240482330322, "Pretrain/Loss (Raw)": 2.0632669925689697, "Pretrain/Step": 8896, "Pretrain/Step Time": 8.77884772606194} +{"Pretrain/Learning Rate": 5.881418819200985e-07, "Pretrain/Loss": 2.03995680809021, "Pretrain/Loss (Raw)": 1.8845784664154053, "Pretrain/Step": 8897, "Pretrain/Step Time": 8.779778825119138} +{"Pretrain/Learning Rate": 5.863125868332292e-07, "Pretrain/Loss": 2.039949893951416, "Pretrain/Loss (Raw)": 2.1129117012023926, "Pretrain/Step": 8898, "Pretrain/Step Time": 8.7803302295506} +{"Pretrain/Learning Rate": 5.844861072478336e-07, "Pretrain/Loss": 2.039231777191162, "Pretrain/Loss (Raw)": 2.1196506023406982, "Pretrain/Step": 8899, "Pretrain/Step Time": 8.782817358151078} +{"Pretrain/Learning Rate": 5.826624433745486e-07, "Pretrain/Loss": 2.0403101444244385, "Pretrain/Loss (Raw)": 1.9994478225708008, "Pretrain/Step": 8900, "Pretrain/Step Time": 8.786186654120684} +{"Pretrain/Learning Rate": 5.808415954236924e-07, "Pretrain/Loss": 2.0392327308654785, "Pretrain/Loss (Raw)": 1.8875113725662231, "Pretrain/Step": 8901, "Pretrain/Step Time": 8.785516511648893} +{"Pretrain/Learning Rate": 5.790235636052438e-07, "Pretrain/Loss": 2.039682626724243, "Pretrain/Loss (Raw)": 2.0691816806793213, "Pretrain/Step": 8902, "Pretrain/Step Time": 8.784484043717384} +{"Pretrain/Learning Rate": 5.772083481288771e-07, "Pretrain/Loss": 2.0388331413269043, "Pretrain/Loss (Raw)": 2.0211424827575684, "Pretrain/Step": 8903, "Pretrain/Step Time": 8.785694411024451} +{"Pretrain/Learning Rate": 5.753959492039246e-07, "Pretrain/Loss": 2.0401668548583984, "Pretrain/Loss (Raw)": 1.9819490909576416, "Pretrain/Step": 8904, "Pretrain/Step Time": 8.78756151534617} +{"Pretrain/Learning Rate": 5.73586367039411e-07, "Pretrain/Loss": 2.038783073425293, "Pretrain/Loss (Raw)": 2.08701753616333, "Pretrain/Step": 8905, "Pretrain/Step Time": 8.787819344550371} +{"Pretrain/Learning Rate": 5.717796018440108e-07, "Pretrain/Loss": 2.0386691093444824, "Pretrain/Loss (Raw)": 1.863982081413269, "Pretrain/Step": 8906, "Pretrain/Step Time": 8.786758756265044} +{"Pretrain/Learning Rate": 5.69975653826102e-07, "Pretrain/Loss": 2.039322853088379, "Pretrain/Loss (Raw)": 1.967375636100769, "Pretrain/Step": 8907, "Pretrain/Step Time": 8.781305193901062} +{"Pretrain/Learning Rate": 5.681745231937124e-07, "Pretrain/Loss": 2.0440149307250977, "Pretrain/Loss (Raw)": 2.0696096420288086, "Pretrain/Step": 8908, "Pretrain/Step Time": 8.78131222166121} +{"Pretrain/Learning Rate": 5.663762101545706e-07, "Pretrain/Loss": 2.043282985687256, "Pretrain/Loss (Raw)": 1.8498879671096802, "Pretrain/Step": 8909, "Pretrain/Step Time": 8.788947155699134} +{"Pretrain/Learning Rate": 5.645807149160548e-07, "Pretrain/Loss": 2.0435400009155273, "Pretrain/Loss (Raw)": 2.093982696533203, "Pretrain/Step": 8910, "Pretrain/Step Time": 8.779332142323256} +{"Pretrain/Learning Rate": 5.627880376852357e-07, "Pretrain/Loss": 2.041210174560547, "Pretrain/Loss (Raw)": 1.847700834274292, "Pretrain/Step": 8911, "Pretrain/Step Time": 8.779107907786965} +{"Pretrain/Learning Rate": 5.609981786688534e-07, "Pretrain/Loss": 2.041288375854492, "Pretrain/Loss (Raw)": 2.021015167236328, "Pretrain/Step": 8912, "Pretrain/Step Time": 8.777263151481748} +{"Pretrain/Learning Rate": 5.592111380733206e-07, "Pretrain/Loss": 2.043527126312256, "Pretrain/Loss (Raw)": 2.226642608642578, "Pretrain/Step": 8913, "Pretrain/Step Time": 8.771100329235196} +{"Pretrain/Learning Rate": 5.574269161047252e-07, "Pretrain/Loss": 2.0428576469421387, "Pretrain/Loss (Raw)": 2.0338518619537354, "Pretrain/Step": 8914, "Pretrain/Step Time": 8.785362428054214} +{"Pretrain/Learning Rate": 5.556455129688387e-07, "Pretrain/Loss": 2.0427677631378174, "Pretrain/Loss (Raw)": 2.116401433944702, "Pretrain/Step": 8915, "Pretrain/Step Time": 8.783481061458588} +{"Pretrain/Learning Rate": 5.538669288710968e-07, "Pretrain/Loss": 2.043898582458496, "Pretrain/Loss (Raw)": 2.249384641647339, "Pretrain/Step": 8916, "Pretrain/Step Time": 8.783907124772668} +{"Pretrain/Learning Rate": 5.520911640166132e-07, "Pretrain/Loss": 2.0407838821411133, "Pretrain/Loss (Raw)": 1.704542875289917, "Pretrain/Step": 8917, "Pretrain/Step Time": 8.782891113311052} +{"Pretrain/Learning Rate": 5.503182186101796e-07, "Pretrain/Loss": 2.041024684906006, "Pretrain/Loss (Raw)": 1.9840916395187378, "Pretrain/Step": 8918, "Pretrain/Step Time": 8.785263888537884} +{"Pretrain/Learning Rate": 5.485480928562603e-07, "Pretrain/Loss": 2.0415616035461426, "Pretrain/Loss (Raw)": 2.0694284439086914, "Pretrain/Step": 8919, "Pretrain/Step Time": 8.790014751255512} +{"Pretrain/Learning Rate": 5.467807869589919e-07, "Pretrain/Loss": 2.0385379791259766, "Pretrain/Loss (Raw)": 1.695951223373413, "Pretrain/Step": 8920, "Pretrain/Step Time": 8.791210437193513} +{"Pretrain/Learning Rate": 5.45016301122192e-07, "Pretrain/Loss": 2.0369491577148438, "Pretrain/Loss (Raw)": 1.8195565938949585, "Pretrain/Step": 8921, "Pretrain/Step Time": 8.794075367972255} +{"Pretrain/Learning Rate": 5.432546355493479e-07, "Pretrain/Loss": 2.034635066986084, "Pretrain/Loss (Raw)": 1.7583110332489014, "Pretrain/Step": 8922, "Pretrain/Step Time": 8.796529876068234} +{"Pretrain/Learning Rate": 5.414957904436219e-07, "Pretrain/Loss": 2.0344536304473877, "Pretrain/Loss (Raw)": 2.0596818923950195, "Pretrain/Step": 8923, "Pretrain/Step Time": 8.793464982882142} +{"Pretrain/Learning Rate": 5.397397660078573e-07, "Pretrain/Loss": 2.0315418243408203, "Pretrain/Loss (Raw)": 2.0474724769592285, "Pretrain/Step": 8924, "Pretrain/Step Time": 8.798150269314647} +{"Pretrain/Learning Rate": 5.37986562444559e-07, "Pretrain/Loss": 2.0297210216522217, "Pretrain/Loss (Raw)": 1.960081696510315, "Pretrain/Step": 8925, "Pretrain/Step Time": 8.79595523327589} +{"Pretrain/Learning Rate": 5.362361799559207e-07, "Pretrain/Loss": 2.030433416366577, "Pretrain/Loss (Raw)": 2.2140960693359375, "Pretrain/Step": 8926, "Pretrain/Step Time": 8.79635601863265} +{"Pretrain/Learning Rate": 5.344886187438031e-07, "Pretrain/Loss": 2.029892921447754, "Pretrain/Loss (Raw)": 1.9859585762023926, "Pretrain/Step": 8927, "Pretrain/Step Time": 8.793891426175833} +{"Pretrain/Learning Rate": 5.327438790097449e-07, "Pretrain/Loss": 2.0299689769744873, "Pretrain/Loss (Raw)": 2.0367560386657715, "Pretrain/Step": 8928, "Pretrain/Step Time": 8.787508897483349} +{"Pretrain/Learning Rate": 5.310019609549521e-07, "Pretrain/Loss": 2.0293149948120117, "Pretrain/Loss (Raw)": 2.0315425395965576, "Pretrain/Step": 8929, "Pretrain/Step Time": 8.795641954988241} +{"Pretrain/Learning Rate": 5.292628647803194e-07, "Pretrain/Loss": 2.0274312496185303, "Pretrain/Loss (Raw)": 2.0013349056243896, "Pretrain/Step": 8930, "Pretrain/Step Time": 8.794464269652963} +{"Pretrain/Learning Rate": 5.27526590686403e-07, "Pretrain/Loss": 2.027053117752075, "Pretrain/Loss (Raw)": 1.8604340553283691, "Pretrain/Step": 8931, "Pretrain/Step Time": 8.793267376720905} +{"Pretrain/Learning Rate": 5.257931388734344e-07, "Pretrain/Loss": 2.0289337635040283, "Pretrain/Loss (Raw)": 1.835270881652832, "Pretrain/Step": 8932, "Pretrain/Step Time": 8.796575514599681} +{"Pretrain/Learning Rate": 5.240625095413287e-07, "Pretrain/Loss": 2.0283727645874023, "Pretrain/Loss (Raw)": 2.0531206130981445, "Pretrain/Step": 8933, "Pretrain/Step Time": 8.796572228893638} +{"Pretrain/Learning Rate": 5.223347028896708e-07, "Pretrain/Loss": 2.0311050415039062, "Pretrain/Loss (Raw)": 2.2332277297973633, "Pretrain/Step": 8934, "Pretrain/Step Time": 8.79840742237866} +{"Pretrain/Learning Rate": 5.206097191177151e-07, "Pretrain/Loss": 2.031661033630371, "Pretrain/Loss (Raw)": 2.0930590629577637, "Pretrain/Step": 8935, "Pretrain/Step Time": 8.800887139514089} +{"Pretrain/Learning Rate": 5.188875584243996e-07, "Pretrain/Loss": 2.0308172702789307, "Pretrain/Loss (Raw)": 1.966357946395874, "Pretrain/Step": 8936, "Pretrain/Step Time": 8.791878497228026} +{"Pretrain/Learning Rate": 5.171682210083268e-07, "Pretrain/Loss": 2.031369686126709, "Pretrain/Loss (Raw)": 2.202772855758667, "Pretrain/Step": 8937, "Pretrain/Step Time": 8.795721463859081} +{"Pretrain/Learning Rate": 5.15451707067785e-07, "Pretrain/Loss": 2.031125545501709, "Pretrain/Loss (Raw)": 2.0580427646636963, "Pretrain/Step": 8938, "Pretrain/Step Time": 8.791367338970304} +{"Pretrain/Learning Rate": 5.137380168007244e-07, "Pretrain/Loss": 2.0321197509765625, "Pretrain/Loss (Raw)": 2.22666335105896, "Pretrain/Step": 8939, "Pretrain/Step Time": 8.799027763307095} +{"Pretrain/Learning Rate": 5.120271504047813e-07, "Pretrain/Loss": 2.032041072845459, "Pretrain/Loss (Raw)": 2.1581826210021973, "Pretrain/Step": 8940, "Pretrain/Step Time": 8.796749275177717} +{"Pretrain/Learning Rate": 5.103191080772535e-07, "Pretrain/Loss": 2.0319020748138428, "Pretrain/Loss (Raw)": 1.984290361404419, "Pretrain/Step": 8941, "Pretrain/Step Time": 8.793806720525026} +{"Pretrain/Learning Rate": 5.086138900151333e-07, "Pretrain/Loss": 2.0323519706726074, "Pretrain/Loss (Raw)": 2.0672354698181152, "Pretrain/Step": 8942, "Pretrain/Step Time": 8.786490077152848} +{"Pretrain/Learning Rate": 5.069114964150606e-07, "Pretrain/Loss": 2.0324063301086426, "Pretrain/Loss (Raw)": 2.010225772857666, "Pretrain/Step": 8943, "Pretrain/Step Time": 8.786564338952303} +{"Pretrain/Learning Rate": 5.052119274733702e-07, "Pretrain/Loss": 2.0312790870666504, "Pretrain/Loss (Raw)": 1.863903284072876, "Pretrain/Step": 8944, "Pretrain/Step Time": 8.787443201988935} +{"Pretrain/Learning Rate": 5.035151833860635e-07, "Pretrain/Loss": 2.030850410461426, "Pretrain/Loss (Raw)": 1.9891843795776367, "Pretrain/Step": 8945, "Pretrain/Step Time": 8.787609729915857} +{"Pretrain/Learning Rate": 5.018212643488202e-07, "Pretrain/Loss": 2.0297207832336426, "Pretrain/Loss (Raw)": 2.106510877609253, "Pretrain/Step": 8946, "Pretrain/Step Time": 8.786610092967749} +{"Pretrain/Learning Rate": 5.001301705569838e-07, "Pretrain/Loss": 2.029081344604492, "Pretrain/Loss (Raw)": 1.9668190479278564, "Pretrain/Step": 8947, "Pretrain/Step Time": 8.787434112280607} +{"Pretrain/Learning Rate": 4.984419022055848e-07, "Pretrain/Loss": 2.0278444290161133, "Pretrain/Loss (Raw)": 1.9219664335250854, "Pretrain/Step": 8948, "Pretrain/Step Time": 8.790032228454947} +{"Pretrain/Learning Rate": 4.967564594893198e-07, "Pretrain/Loss": 2.0271458625793457, "Pretrain/Loss (Raw)": 1.966977596282959, "Pretrain/Step": 8949, "Pretrain/Step Time": 8.800652468577027} +{"Pretrain/Learning Rate": 4.95073842602567e-07, "Pretrain/Loss": 2.0266294479370117, "Pretrain/Loss (Raw)": 2.042893171310425, "Pretrain/Step": 8950, "Pretrain/Step Time": 8.788061704486609} +{"Pretrain/Learning Rate": 4.933940517393626e-07, "Pretrain/Loss": 2.0246706008911133, "Pretrain/Loss (Raw)": 2.064425468444824, "Pretrain/Step": 8951, "Pretrain/Step Time": 8.80002468265593} +{"Pretrain/Learning Rate": 4.917170870934407e-07, "Pretrain/Loss": 2.0232832431793213, "Pretrain/Loss (Raw)": 1.9194214344024658, "Pretrain/Step": 8952, "Pretrain/Step Time": 8.799231125041842} +{"Pretrain/Learning Rate": 4.900429488581909e-07, "Pretrain/Loss": 2.0232791900634766, "Pretrain/Loss (Raw)": 2.0181939601898193, "Pretrain/Step": 8953, "Pretrain/Step Time": 8.793434884399176} +{"Pretrain/Learning Rate": 4.883716372266811e-07, "Pretrain/Loss": 2.0212268829345703, "Pretrain/Loss (Raw)": 2.0086536407470703, "Pretrain/Step": 8954, "Pretrain/Step Time": 8.793094981461763} +{"Pretrain/Learning Rate": 4.867031523916571e-07, "Pretrain/Loss": 2.021725654602051, "Pretrain/Loss (Raw)": 1.9537335634231567, "Pretrain/Step": 8955, "Pretrain/Step Time": 8.79597932845354} +{"Pretrain/Learning Rate": 4.850374945455344e-07, "Pretrain/Loss": 2.022228240966797, "Pretrain/Loss (Raw)": 2.175614595413208, "Pretrain/Step": 8956, "Pretrain/Step Time": 8.804041923955083} +{"Pretrain/Learning Rate": 4.833746638804093e-07, "Pretrain/Loss": 2.022907257080078, "Pretrain/Loss (Raw)": 2.093867778778076, "Pretrain/Step": 8957, "Pretrain/Step Time": 8.791046515107155} +{"Pretrain/Learning Rate": 4.817146605880424e-07, "Pretrain/Loss": 2.0248312950134277, "Pretrain/Loss (Raw)": 2.0722668170928955, "Pretrain/Step": 8958, "Pretrain/Step Time": 8.788880735635757} +{"Pretrain/Learning Rate": 4.800574848598749e-07, "Pretrain/Loss": 2.0239758491516113, "Pretrain/Loss (Raw)": 1.8683429956436157, "Pretrain/Step": 8959, "Pretrain/Step Time": 8.78851180896163} +{"Pretrain/Learning Rate": 4.784031368870206e-07, "Pretrain/Loss": 2.0235395431518555, "Pretrain/Loss (Raw)": 2.046243906021118, "Pretrain/Step": 8960, "Pretrain/Step Time": 8.790903083980083} +{"Pretrain/Learning Rate": 4.7675161686026595e-07, "Pretrain/Loss": 2.0237066745758057, "Pretrain/Loss (Raw)": 1.9511440992355347, "Pretrain/Step": 8961, "Pretrain/Step Time": 8.782625937834382} +{"Pretrain/Learning Rate": 4.751029249700695e-07, "Pretrain/Loss": 2.0238795280456543, "Pretrain/Loss (Raw)": 2.061964750289917, "Pretrain/Step": 8962, "Pretrain/Step Time": 8.782963206991553} +{"Pretrain/Learning Rate": 4.734570614065709e-07, "Pretrain/Loss": 2.0237720012664795, "Pretrain/Loss (Raw)": 2.0967233180999756, "Pretrain/Step": 8963, "Pretrain/Step Time": 8.791300928220153} +{"Pretrain/Learning Rate": 4.718140263595794e-07, "Pretrain/Loss": 2.0262019634246826, "Pretrain/Loss (Raw)": 2.1505000591278076, "Pretrain/Step": 8964, "Pretrain/Step Time": 8.789637338370085} +{"Pretrain/Learning Rate": 4.701738200185712e-07, "Pretrain/Loss": 2.026200294494629, "Pretrain/Loss (Raw)": 2.1890156269073486, "Pretrain/Step": 8965, "Pretrain/Step Time": 8.783245522528887} +{"Pretrain/Learning Rate": 4.6853644257270624e-07, "Pretrain/Loss": 2.026794910430908, "Pretrain/Loss (Raw)": 2.124741554260254, "Pretrain/Step": 8966, "Pretrain/Step Time": 8.792057501152158} +{"Pretrain/Learning Rate": 4.6690189421081943e-07, "Pretrain/Loss": 2.0266597270965576, "Pretrain/Loss (Raw)": 2.072612762451172, "Pretrain/Step": 8967, "Pretrain/Step Time": 8.791331438347697} +{"Pretrain/Learning Rate": 4.6527017512140723e-07, "Pretrain/Loss": 2.0271975994110107, "Pretrain/Loss (Raw)": 1.9640345573425293, "Pretrain/Step": 8968, "Pretrain/Step Time": 8.798240350559354} +{"Pretrain/Learning Rate": 4.6364128549264976e-07, "Pretrain/Loss": 2.026242256164551, "Pretrain/Loss (Raw)": 2.0313384532928467, "Pretrain/Step": 8969, "Pretrain/Step Time": 8.793081557378173} +{"Pretrain/Learning Rate": 4.6201522551239664e-07, "Pretrain/Loss": 2.0247080326080322, "Pretrain/Loss (Raw)": 1.8785358667373657, "Pretrain/Step": 8970, "Pretrain/Step Time": 8.795120354741812} +{"Pretrain/Learning Rate": 4.603919953681757e-07, "Pretrain/Loss": 2.0253593921661377, "Pretrain/Loss (Raw)": 2.11930251121521, "Pretrain/Step": 8971, "Pretrain/Step Time": 8.790911551564932} +{"Pretrain/Learning Rate": 4.587715952471872e-07, "Pretrain/Loss": 2.0235443115234375, "Pretrain/Loss (Raw)": 1.8093167543411255, "Pretrain/Step": 8972, "Pretrain/Step Time": 8.793088138103485} +{"Pretrain/Learning Rate": 4.5715402533629826e-07, "Pretrain/Loss": 2.0242247581481934, "Pretrain/Loss (Raw)": 1.9828743934631348, "Pretrain/Step": 8973, "Pretrain/Step Time": 8.790729166939855} +{"Pretrain/Learning Rate": 4.5553928582205417e-07, "Pretrain/Loss": 2.0252652168273926, "Pretrain/Loss (Raw)": 1.9573136568069458, "Pretrain/Step": 8974, "Pretrain/Step Time": 8.78820737451315} +{"Pretrain/Learning Rate": 4.539273768906782e-07, "Pretrain/Loss": 2.0289413928985596, "Pretrain/Loss (Raw)": 2.4017670154571533, "Pretrain/Step": 8975, "Pretrain/Step Time": 8.788928788155317} +{"Pretrain/Learning Rate": 4.523182987280633e-07, "Pretrain/Loss": 2.0294852256774902, "Pretrain/Loss (Raw)": 2.1010403633117676, "Pretrain/Step": 8976, "Pretrain/Step Time": 8.787966012954712} +{"Pretrain/Learning Rate": 4.507120515197749e-07, "Pretrain/Loss": 2.0297741889953613, "Pretrain/Loss (Raw)": 2.0206756591796875, "Pretrain/Step": 8977, "Pretrain/Step Time": 8.79017823934555} +{"Pretrain/Learning Rate": 4.49108635451051e-07, "Pretrain/Loss": 2.0275497436523438, "Pretrain/Loss (Raw)": 1.866932988166809, "Pretrain/Step": 8978, "Pretrain/Step Time": 8.78338485583663} +{"Pretrain/Learning Rate": 4.475080507068102e-07, "Pretrain/Loss": 2.0275309085845947, "Pretrain/Loss (Raw)": 2.1045634746551514, "Pretrain/Step": 8979, "Pretrain/Step Time": 8.783574091270566} +{"Pretrain/Learning Rate": 4.4591029747163283e-07, "Pretrain/Loss": 2.0255331993103027, "Pretrain/Loss (Raw)": 1.916035771369934, "Pretrain/Step": 8980, "Pretrain/Step Time": 8.782027212902904} +{"Pretrain/Learning Rate": 4.443153759297852e-07, "Pretrain/Loss": 2.023529052734375, "Pretrain/Loss (Raw)": 1.9662648439407349, "Pretrain/Step": 8981, "Pretrain/Step Time": 8.781532362103462} +{"Pretrain/Learning Rate": 4.427232862651953e-07, "Pretrain/Loss": 2.024252414703369, "Pretrain/Loss (Raw)": 2.0576443672180176, "Pretrain/Step": 8982, "Pretrain/Step Time": 8.783338500186801} +{"Pretrain/Learning Rate": 4.4113402866147734e-07, "Pretrain/Loss": 2.0244252681732178, "Pretrain/Loss (Raw)": 2.021693468093872, "Pretrain/Step": 8983, "Pretrain/Step Time": 8.789936807006598} +{"Pretrain/Learning Rate": 4.395476033019069e-07, "Pretrain/Loss": 2.0251622200012207, "Pretrain/Loss (Raw)": 2.0481209754943848, "Pretrain/Step": 8984, "Pretrain/Step Time": 8.786707360297441} +{"Pretrain/Learning Rate": 4.3796401036944043e-07, "Pretrain/Loss": 2.0275535583496094, "Pretrain/Loss (Raw)": 2.259159564971924, "Pretrain/Step": 8985, "Pretrain/Step Time": 8.780569968745112} +{"Pretrain/Learning Rate": 4.3638325004670135e-07, "Pretrain/Loss": 2.0289418697357178, "Pretrain/Loss (Raw)": 2.087318181991577, "Pretrain/Step": 8986, "Pretrain/Step Time": 8.781640641391277} +{"Pretrain/Learning Rate": 4.3480532251599647e-07, "Pretrain/Loss": 2.0267295837402344, "Pretrain/Loss (Raw)": 2.0969157218933105, "Pretrain/Step": 8987, "Pretrain/Step Time": 8.779301339760423} +{"Pretrain/Learning Rate": 4.3323022795929425e-07, "Pretrain/Loss": 2.025599718093872, "Pretrain/Loss (Raw)": 1.9692059755325317, "Pretrain/Step": 8988, "Pretrain/Step Time": 8.7797761131078} +{"Pretrain/Learning Rate": 4.316579665582465e-07, "Pretrain/Loss": 2.025501251220703, "Pretrain/Loss (Raw)": 2.0125298500061035, "Pretrain/Step": 8989, "Pretrain/Step Time": 8.780792500823736} +{"Pretrain/Learning Rate": 4.300885384941694e-07, "Pretrain/Loss": 2.02298641204834, "Pretrain/Loss (Raw)": 1.779952883720398, "Pretrain/Step": 8990, "Pretrain/Step Time": 8.775923842564225} +{"Pretrain/Learning Rate": 4.285219439480653e-07, "Pretrain/Loss": 2.023766040802002, "Pretrain/Loss (Raw)": 2.0566861629486084, "Pretrain/Step": 8991, "Pretrain/Step Time": 8.779615189880133} +{"Pretrain/Learning Rate": 4.2695818310058975e-07, "Pretrain/Loss": 2.02374267578125, "Pretrain/Loss (Raw)": 2.033514976501465, "Pretrain/Step": 8992, "Pretrain/Step Time": 8.779840959236026} +{"Pretrain/Learning Rate": 4.253972561320901e-07, "Pretrain/Loss": 2.022991418838501, "Pretrain/Loss (Raw)": 1.9560582637786865, "Pretrain/Step": 8993, "Pretrain/Step Time": 8.781318672001362} +{"Pretrain/Learning Rate": 4.23839163222578e-07, "Pretrain/Loss": 2.023280620574951, "Pretrain/Loss (Raw)": 2.031627893447876, "Pretrain/Step": 8994, "Pretrain/Step Time": 8.781501015648246} +{"Pretrain/Learning Rate": 4.222839045517402e-07, "Pretrain/Loss": 2.023956775665283, "Pretrain/Loss (Raw)": 2.1368987560272217, "Pretrain/Step": 8995, "Pretrain/Step Time": 8.783271634951234} +{"Pretrain/Learning Rate": 4.2073148029893593e-07, "Pretrain/Loss": 2.0230178833007812, "Pretrain/Loss (Raw)": 1.9874532222747803, "Pretrain/Step": 8996, "Pretrain/Step Time": 8.784024627879262} +{"Pretrain/Learning Rate": 4.191818906431999e-07, "Pretrain/Loss": 2.0215611457824707, "Pretrain/Loss (Raw)": 1.7962102890014648, "Pretrain/Step": 8997, "Pretrain/Step Time": 8.784600326791406} +{"Pretrain/Learning Rate": 4.176351357632363e-07, "Pretrain/Loss": 2.0220203399658203, "Pretrain/Loss (Raw)": 2.0902905464172363, "Pretrain/Step": 8998, "Pretrain/Step Time": 8.78924272581935} +{"Pretrain/Learning Rate": 4.160912158374247e-07, "Pretrain/Loss": 2.023789167404175, "Pretrain/Loss (Raw)": 2.0075173377990723, "Pretrain/Step": 8999, "Pretrain/Step Time": 8.786984227597713} +{"Pretrain/Learning Rate": 4.1455013104381714e-07, "Pretrain/Loss": 2.0219545364379883, "Pretrain/Loss (Raw)": 1.8185908794403076, "Pretrain/Step": 9000, "Pretrain/Step Time": 8.788967223837972} +{"Pretrain/Learning Rate": 4.1301188156013803e-07, "Pretrain/Loss": 2.0210671424865723, "Pretrain/Loss (Raw)": 1.9215610027313232, "Pretrain/Step": 9001, "Pretrain/Step Time": 8.78726507537067} +{"Pretrain/Learning Rate": 4.1147646756378997e-07, "Pretrain/Loss": 2.02299165725708, "Pretrain/Loss (Raw)": 2.2437829971313477, "Pretrain/Step": 9002, "Pretrain/Step Time": 8.789231657981873} +{"Pretrain/Learning Rate": 4.099438892318369e-07, "Pretrain/Loss": 2.023465394973755, "Pretrain/Loss (Raw)": 2.100090742111206, "Pretrain/Step": 9003, "Pretrain/Step Time": 8.786165101453662} +{"Pretrain/Learning Rate": 4.084141467410263e-07, "Pretrain/Loss": 2.0227560997009277, "Pretrain/Loss (Raw)": 1.9264503717422485, "Pretrain/Step": 9004, "Pretrain/Step Time": 8.787089535966516} +{"Pretrain/Learning Rate": 4.0688724026777814e-07, "Pretrain/Loss": 2.023068428039551, "Pretrain/Loss (Raw)": 2.1415698528289795, "Pretrain/Step": 9005, "Pretrain/Step Time": 8.794300498440862} +{"Pretrain/Learning Rate": 4.0536316998817937e-07, "Pretrain/Loss": 2.0237789154052734, "Pretrain/Loss (Raw)": 2.0834555625915527, "Pretrain/Step": 9006, "Pretrain/Step Time": 8.787951786071062} +{"Pretrain/Learning Rate": 4.038419360779921e-07, "Pretrain/Loss": 2.021514654159546, "Pretrain/Loss (Raw)": 1.8480134010314941, "Pretrain/Step": 9007, "Pretrain/Step Time": 8.789570013061166} +{"Pretrain/Learning Rate": 4.023235387126567e-07, "Pretrain/Loss": 2.021477222442627, "Pretrain/Loss (Raw)": 2.10253643989563, "Pretrain/Step": 9008, "Pretrain/Step Time": 8.790617356076837} +{"Pretrain/Learning Rate": 4.008079780672774e-07, "Pretrain/Loss": 2.0197372436523438, "Pretrain/Loss (Raw)": 1.931563138961792, "Pretrain/Step": 9009, "Pretrain/Step Time": 8.793826261535287} +{"Pretrain/Learning Rate": 3.992952543166367e-07, "Pretrain/Loss": 2.018446445465088, "Pretrain/Loss (Raw)": 1.8844505548477173, "Pretrain/Step": 9010, "Pretrain/Step Time": 8.794052362442017} +{"Pretrain/Learning Rate": 3.977853676351867e-07, "Pretrain/Loss": 2.0184826850891113, "Pretrain/Loss (Raw)": 2.101588726043701, "Pretrain/Step": 9011, "Pretrain/Step Time": 8.791872488334775} +{"Pretrain/Learning Rate": 3.9627831819706305e-07, "Pretrain/Loss": 2.0180044174194336, "Pretrain/Loss (Raw)": 2.0278890132904053, "Pretrain/Step": 9012, "Pretrain/Step Time": 8.795786088332534} +{"Pretrain/Learning Rate": 3.947741061760574e-07, "Pretrain/Loss": 2.020998239517212, "Pretrain/Loss (Raw)": 2.1865949630737305, "Pretrain/Step": 9013, "Pretrain/Step Time": 8.795025639235973} +{"Pretrain/Learning Rate": 3.932727317456475e-07, "Pretrain/Loss": 2.0216221809387207, "Pretrain/Loss (Raw)": 2.1765828132629395, "Pretrain/Step": 9014, "Pretrain/Step Time": 8.791803665459156} +{"Pretrain/Learning Rate": 3.9177419507897274e-07, "Pretrain/Loss": 2.022830009460449, "Pretrain/Loss (Raw)": 2.1642632484436035, "Pretrain/Step": 9015, "Pretrain/Step Time": 8.793956091627479} +{"Pretrain/Learning Rate": 3.902784963488587e-07, "Pretrain/Loss": 2.0221235752105713, "Pretrain/Loss (Raw)": 2.003687620162964, "Pretrain/Step": 9016, "Pretrain/Step Time": 8.799794672057033} +{"Pretrain/Learning Rate": 3.887856357277925e-07, "Pretrain/Loss": 2.0224924087524414, "Pretrain/Loss (Raw)": 2.0308098793029785, "Pretrain/Step": 9017, "Pretrain/Step Time": 8.797666175290942} +{"Pretrain/Learning Rate": 3.872956133879391e-07, "Pretrain/Loss": 2.0224502086639404, "Pretrain/Loss (Raw)": 1.9791276454925537, "Pretrain/Step": 9018, "Pretrain/Step Time": 8.795287886634469} +{"Pretrain/Learning Rate": 3.858084295011333e-07, "Pretrain/Loss": 2.022402286529541, "Pretrain/Loss (Raw)": 1.9873112440109253, "Pretrain/Step": 9019, "Pretrain/Step Time": 8.796597596257925} +{"Pretrain/Learning Rate": 3.843240842388879e-07, "Pretrain/Loss": 2.021623134613037, "Pretrain/Loss (Raw)": 1.9470462799072266, "Pretrain/Step": 9020, "Pretrain/Step Time": 8.792348384857178} +{"Pretrain/Learning Rate": 3.8284257777237984e-07, "Pretrain/Loss": 2.0208024978637695, "Pretrain/Loss (Raw)": 1.909045696258545, "Pretrain/Step": 9021, "Pretrain/Step Time": 8.79720818810165} +{"Pretrain/Learning Rate": 3.8136391027246696e-07, "Pretrain/Loss": 2.0196328163146973, "Pretrain/Loss (Raw)": 1.965835690498352, "Pretrain/Step": 9022, "Pretrain/Step Time": 8.796966692432761} +{"Pretrain/Learning Rate": 3.7988808190967116e-07, "Pretrain/Loss": 2.0202813148498535, "Pretrain/Loss (Raw)": 2.1554675102233887, "Pretrain/Step": 9023, "Pretrain/Step Time": 8.794755494222045} +{"Pretrain/Learning Rate": 3.7841509285420076e-07, "Pretrain/Loss": 2.021080493927002, "Pretrain/Loss (Raw)": 2.165558099746704, "Pretrain/Step": 9024, "Pretrain/Step Time": 8.797919727861881} +{"Pretrain/Learning Rate": 3.769449432759198e-07, "Pretrain/Loss": 2.023956298828125, "Pretrain/Loss (Raw)": 2.2526679039001465, "Pretrain/Step": 9025, "Pretrain/Step Time": 8.79482040181756} +{"Pretrain/Learning Rate": 3.7547763334437603e-07, "Pretrain/Loss": 2.0232901573181152, "Pretrain/Loss (Raw)": 2.027677297592163, "Pretrain/Step": 9026, "Pretrain/Step Time": 8.795036481693387} +{"Pretrain/Learning Rate": 3.740131632287841e-07, "Pretrain/Loss": 2.0224609375, "Pretrain/Loss (Raw)": 2.0135061740875244, "Pretrain/Step": 9027, "Pretrain/Step Time": 8.79745415225625} +{"Pretrain/Learning Rate": 3.725515330980395e-07, "Pretrain/Loss": 2.0230236053466797, "Pretrain/Loss (Raw)": 2.0714690685272217, "Pretrain/Step": 9028, "Pretrain/Step Time": 8.792725007981062} +{"Pretrain/Learning Rate": 3.71092743120699e-07, "Pretrain/Loss": 2.025495767593384, "Pretrain/Loss (Raw)": 2.2039425373077393, "Pretrain/Step": 9029, "Pretrain/Step Time": 8.792741684243083} +{"Pretrain/Learning Rate": 3.6963679346499746e-07, "Pretrain/Loss": 2.024745464324951, "Pretrain/Loss (Raw)": 1.973134160041809, "Pretrain/Step": 9030, "Pretrain/Step Time": 8.796270668506622} +{"Pretrain/Learning Rate": 3.681836842988423e-07, "Pretrain/Loss": 2.026144027709961, "Pretrain/Loss (Raw)": 2.2001869678497314, "Pretrain/Step": 9031, "Pretrain/Step Time": 8.795484088361263} +{"Pretrain/Learning Rate": 3.6673341578981614e-07, "Pretrain/Loss": 2.0278539657592773, "Pretrain/Loss (Raw)": 2.2007851600646973, "Pretrain/Step": 9032, "Pretrain/Step Time": 8.79218002781272} +{"Pretrain/Learning Rate": 3.6528598810516567e-07, "Pretrain/Loss": 2.0260939598083496, "Pretrain/Loss (Raw)": 1.8617185354232788, "Pretrain/Step": 9033, "Pretrain/Step Time": 8.792643735185266} +{"Pretrain/Learning Rate": 3.6384140141181853e-07, "Pretrain/Loss": 2.027810573577881, "Pretrain/Loss (Raw)": 2.0837440490722656, "Pretrain/Step": 9034, "Pretrain/Step Time": 8.800593176856637} +{"Pretrain/Learning Rate": 3.6239965587637203e-07, "Pretrain/Loss": 2.0291008949279785, "Pretrain/Loss (Raw)": 2.132514715194702, "Pretrain/Step": 9035, "Pretrain/Step Time": 8.796185225248337} +{"Pretrain/Learning Rate": 3.609607516650931e-07, "Pretrain/Loss": 2.026548385620117, "Pretrain/Loss (Raw)": 1.7428892850875854, "Pretrain/Step": 9036, "Pretrain/Step Time": 8.798282211646438} +{"Pretrain/Learning Rate": 3.5952468894392133e-07, "Pretrain/Loss": 2.0289969444274902, "Pretrain/Loss (Raw)": 2.1633381843566895, "Pretrain/Step": 9037, "Pretrain/Step Time": 8.795648466795683} +{"Pretrain/Learning Rate": 3.5809146787847415e-07, "Pretrain/Loss": 2.0276994705200195, "Pretrain/Loss (Raw)": 1.9278799295425415, "Pretrain/Step": 9038, "Pretrain/Step Time": 8.798715947195888} +{"Pretrain/Learning Rate": 3.5666108863403327e-07, "Pretrain/Loss": 2.030428886413574, "Pretrain/Loss (Raw)": 2.197096109390259, "Pretrain/Step": 9039, "Pretrain/Step Time": 8.796373372897506} +{"Pretrain/Learning Rate": 3.552335513755611e-07, "Pretrain/Loss": 2.0302062034606934, "Pretrain/Loss (Raw)": 1.9924652576446533, "Pretrain/Step": 9040, "Pretrain/Step Time": 8.796605966985226} +{"Pretrain/Learning Rate": 3.538088562676817e-07, "Pretrain/Loss": 2.0292022228240967, "Pretrain/Loss (Raw)": 2.098145008087158, "Pretrain/Step": 9041, "Pretrain/Step Time": 8.806830644607544} +{"Pretrain/Learning Rate": 3.523870034747051e-07, "Pretrain/Loss": 2.0302939414978027, "Pretrain/Loss (Raw)": 2.173610210418701, "Pretrain/Step": 9042, "Pretrain/Step Time": 8.79408996924758} +{"Pretrain/Learning Rate": 3.50967993160603e-07, "Pretrain/Loss": 2.02847957611084, "Pretrain/Loss (Raw)": 1.8841743469238281, "Pretrain/Step": 9043, "Pretrain/Step Time": 8.798170670866966} +{"Pretrain/Learning Rate": 3.4955182548901955e-07, "Pretrain/Loss": 2.027423858642578, "Pretrain/Loss (Raw)": 2.1142427921295166, "Pretrain/Step": 9044, "Pretrain/Step Time": 8.800647178664804} +{"Pretrain/Learning Rate": 3.4813850062327956e-07, "Pretrain/Loss": 2.0299160480499268, "Pretrain/Loss (Raw)": 2.0235416889190674, "Pretrain/Step": 9045, "Pretrain/Step Time": 8.800216544419527} +{"Pretrain/Learning Rate": 3.467280187263694e-07, "Pretrain/Loss": 2.0309479236602783, "Pretrain/Loss (Raw)": 2.1161675453186035, "Pretrain/Step": 9046, "Pretrain/Step Time": 8.797915149480104} +{"Pretrain/Learning Rate": 3.4532037996095334e-07, "Pretrain/Loss": 2.028075933456421, "Pretrain/Loss (Raw)": 1.7018131017684937, "Pretrain/Step": 9047, "Pretrain/Step Time": 8.801864514127374} +{"Pretrain/Learning Rate": 3.4391558448936825e-07, "Pretrain/Loss": 2.03078031539917, "Pretrain/Loss (Raw)": 2.0421087741851807, "Pretrain/Step": 9048, "Pretrain/Step Time": 8.80044973269105} +{"Pretrain/Learning Rate": 3.4251363247362054e-07, "Pretrain/Loss": 2.031859874725342, "Pretrain/Loss (Raw)": 1.9577460289001465, "Pretrain/Step": 9049, "Pretrain/Step Time": 8.790235925465822} +{"Pretrain/Learning Rate": 3.4111452407539214e-07, "Pretrain/Loss": 2.0338892936706543, "Pretrain/Loss (Raw)": 2.018059730529785, "Pretrain/Step": 9050, "Pretrain/Step Time": 8.789481401443481} +{"Pretrain/Learning Rate": 3.397182594560344e-07, "Pretrain/Loss": 2.0356669425964355, "Pretrain/Loss (Raw)": 2.2872507572174072, "Pretrain/Step": 9051, "Pretrain/Step Time": 8.794180933386087} +{"Pretrain/Learning Rate": 3.3832483877656584e-07, "Pretrain/Loss": 2.035903215408325, "Pretrain/Loss (Raw)": 2.077685594558716, "Pretrain/Step": 9052, "Pretrain/Step Time": 8.794851291924715} +{"Pretrain/Learning Rate": 3.369342621976884e-07, "Pretrain/Loss": 2.0361506938934326, "Pretrain/Loss (Raw)": 1.9917774200439453, "Pretrain/Step": 9053, "Pretrain/Step Time": 8.792197074741125} +{"Pretrain/Learning Rate": 3.355465298797711e-07, "Pretrain/Loss": 2.03293776512146, "Pretrain/Loss (Raw)": 1.802838683128357, "Pretrain/Step": 9054, "Pretrain/Step Time": 8.792518485337496} +{"Pretrain/Learning Rate": 3.3416164198284694e-07, "Pretrain/Loss": 2.033339262008667, "Pretrain/Loss (Raw)": 2.037343740463257, "Pretrain/Step": 9055, "Pretrain/Step Time": 8.803042490035295} +{"Pretrain/Learning Rate": 3.327795986666327e-07, "Pretrain/Loss": 2.033587694168091, "Pretrain/Loss (Raw)": 2.0685505867004395, "Pretrain/Step": 9056, "Pretrain/Step Time": 8.802672766149044} +{"Pretrain/Learning Rate": 3.3140040009051186e-07, "Pretrain/Loss": 2.0330007076263428, "Pretrain/Loss (Raw)": 1.956411361694336, "Pretrain/Step": 9057, "Pretrain/Step Time": 8.801398186013103} +{"Pretrain/Learning Rate": 3.300240464135379e-07, "Pretrain/Loss": 2.0338797569274902, "Pretrain/Loss (Raw)": 2.1138570308685303, "Pretrain/Step": 9058, "Pretrain/Step Time": 8.800418583676219} +{"Pretrain/Learning Rate": 3.286505377944393e-07, "Pretrain/Loss": 2.034440517425537, "Pretrain/Loss (Raw)": 1.932196021080017, "Pretrain/Step": 9059, "Pretrain/Step Time": 8.801508637145162} +{"Pretrain/Learning Rate": 3.2727987439161724e-07, "Pretrain/Loss": 2.0357398986816406, "Pretrain/Loss (Raw)": 2.0016026496887207, "Pretrain/Step": 9060, "Pretrain/Step Time": 8.7951486017555} +{"Pretrain/Learning Rate": 3.2591205636313957e-07, "Pretrain/Loss": 2.0352306365966797, "Pretrain/Loss (Raw)": 1.9879558086395264, "Pretrain/Step": 9061, "Pretrain/Step Time": 8.796270793303847} +{"Pretrain/Learning Rate": 3.2454708386675525e-07, "Pretrain/Loss": 2.0348963737487793, "Pretrain/Loss (Raw)": 2.190412998199463, "Pretrain/Step": 9062, "Pretrain/Step Time": 8.802768157795072} +{"Pretrain/Learning Rate": 3.2318495705987437e-07, "Pretrain/Loss": 2.0354321002960205, "Pretrain/Loss (Raw)": 2.161640167236328, "Pretrain/Step": 9063, "Pretrain/Step Time": 8.796209242194891} +{"Pretrain/Learning Rate": 3.218256760995825e-07, "Pretrain/Loss": 2.034865617752075, "Pretrain/Loss (Raw)": 1.8938592672348022, "Pretrain/Step": 9064, "Pretrain/Step Time": 8.796965582296252} +{"Pretrain/Learning Rate": 3.20469241142643e-07, "Pretrain/Loss": 2.0327274799346924, "Pretrain/Loss (Raw)": 1.9290812015533447, "Pretrain/Step": 9065, "Pretrain/Step Time": 8.801508003845811} +{"Pretrain/Learning Rate": 3.1911565234548633e-07, "Pretrain/Loss": 2.0312604904174805, "Pretrain/Loss (Raw)": 1.8702731132507324, "Pretrain/Step": 9066, "Pretrain/Step Time": 8.803636422380805} +{"Pretrain/Learning Rate": 3.177649098642099e-07, "Pretrain/Loss": 2.0297417640686035, "Pretrain/Loss (Raw)": 2.032287120819092, "Pretrain/Step": 9067, "Pretrain/Step Time": 8.798016300424933} +{"Pretrain/Learning Rate": 3.1641701385459186e-07, "Pretrain/Loss": 2.0297765731811523, "Pretrain/Loss (Raw)": 2.162590503692627, "Pretrain/Step": 9068, "Pretrain/Step Time": 8.798361467197537} +{"Pretrain/Learning Rate": 3.150719644720773e-07, "Pretrain/Loss": 2.028928279876709, "Pretrain/Loss (Raw)": 1.8757517337799072, "Pretrain/Step": 9069, "Pretrain/Step Time": 8.803478555753827} +{"Pretrain/Learning Rate": 3.1372976187178105e-07, "Pretrain/Loss": 2.028818368911743, "Pretrain/Loss (Raw)": 2.053154706954956, "Pretrain/Step": 9070, "Pretrain/Step Time": 8.795664688572288} +{"Pretrain/Learning Rate": 3.123904062084959e-07, "Pretrain/Loss": 2.0273303985595703, "Pretrain/Loss (Raw)": 1.8197530508041382, "Pretrain/Step": 9071, "Pretrain/Step Time": 8.799756985157728} +{"Pretrain/Learning Rate": 3.110538976366789e-07, "Pretrain/Loss": 2.0286312103271484, "Pretrain/Loss (Raw)": 2.0304312705993652, "Pretrain/Step": 9072, "Pretrain/Step Time": 8.79408011212945} +{"Pretrain/Learning Rate": 3.0972023631046786e-07, "Pretrain/Loss": 2.029298782348633, "Pretrain/Loss (Raw)": 2.0745902061462402, "Pretrain/Step": 9073, "Pretrain/Step Time": 8.800225106999278} +{"Pretrain/Learning Rate": 3.083894223836592e-07, "Pretrain/Loss": 2.029168128967285, "Pretrain/Loss (Raw)": 2.089823007583618, "Pretrain/Step": 9074, "Pretrain/Step Time": 8.797490771859884} +{"Pretrain/Learning Rate": 3.070614560097357e-07, "Pretrain/Loss": 2.028829574584961, "Pretrain/Loss (Raw)": 1.9234601259231567, "Pretrain/Step": 9075, "Pretrain/Step Time": 8.795699529349804} +{"Pretrain/Learning Rate": 3.0573633734184146e-07, "Pretrain/Loss": 2.0295519828796387, "Pretrain/Loss (Raw)": 2.014444351196289, "Pretrain/Step": 9076, "Pretrain/Step Time": 8.808091789484024} +{"Pretrain/Learning Rate": 3.044140665327988e-07, "Pretrain/Loss": 2.0306732654571533, "Pretrain/Loss (Raw)": 2.1105005741119385, "Pretrain/Step": 9077, "Pretrain/Step Time": 8.799033952876925} +{"Pretrain/Learning Rate": 3.0309464373509125e-07, "Pretrain/Loss": 2.0294172763824463, "Pretrain/Loss (Raw)": 1.8821308612823486, "Pretrain/Step": 9078, "Pretrain/Step Time": 8.799741998314857} +{"Pretrain/Learning Rate": 3.017780691008859e-07, "Pretrain/Loss": 2.0254759788513184, "Pretrain/Loss (Raw)": 1.5599217414855957, "Pretrain/Step": 9079, "Pretrain/Step Time": 8.791209153831005} +{"Pretrain/Learning Rate": 3.00464342782017e-07, "Pretrain/Loss": 2.025193929672241, "Pretrain/Loss (Raw)": 1.8833402395248413, "Pretrain/Step": 9080, "Pretrain/Step Time": 8.792433459311724} +{"Pretrain/Learning Rate": 2.9915346492998817e-07, "Pretrain/Loss": 2.0244996547698975, "Pretrain/Loss (Raw)": 1.929298996925354, "Pretrain/Step": 9081, "Pretrain/Step Time": 8.79026854224503} +{"Pretrain/Learning Rate": 2.9784543569597314e-07, "Pretrain/Loss": 2.024531602859497, "Pretrain/Loss (Raw)": 2.0127761363983154, "Pretrain/Step": 9082, "Pretrain/Step Time": 8.791231252253056} +{"Pretrain/Learning Rate": 2.9654025523082607e-07, "Pretrain/Loss": 2.0243029594421387, "Pretrain/Loss (Raw)": 1.9244612455368042, "Pretrain/Step": 9083, "Pretrain/Step Time": 8.790145056322217} +{"Pretrain/Learning Rate": 2.9523792368506275e-07, "Pretrain/Loss": 2.022576332092285, "Pretrain/Loss (Raw)": 1.9545801877975464, "Pretrain/Step": 9084, "Pretrain/Step Time": 8.78550761565566} +{"Pretrain/Learning Rate": 2.9393844120887415e-07, "Pretrain/Loss": 2.0207483768463135, "Pretrain/Loss (Raw)": 1.8599121570587158, "Pretrain/Step": 9085, "Pretrain/Step Time": 8.788530498743057} +{"Pretrain/Learning Rate": 2.926418079521237e-07, "Pretrain/Loss": 2.0205612182617188, "Pretrain/Loss (Raw)": 2.048318386077881, "Pretrain/Step": 9086, "Pretrain/Step Time": 8.789696728810668} +{"Pretrain/Learning Rate": 2.913480240643446e-07, "Pretrain/Loss": 2.0231831073760986, "Pretrain/Loss (Raw)": 2.203946352005005, "Pretrain/Step": 9087, "Pretrain/Step Time": 8.791942801326513} +{"Pretrain/Learning Rate": 2.900570896947424e-07, "Pretrain/Loss": 2.0259737968444824, "Pretrain/Loss (Raw)": 2.4034299850463867, "Pretrain/Step": 9088, "Pretrain/Step Time": 8.791082620620728} +{"Pretrain/Learning Rate": 2.8876900499219263e-07, "Pretrain/Loss": 2.0275585651397705, "Pretrain/Loss (Raw)": 2.1540024280548096, "Pretrain/Step": 9089, "Pretrain/Step Time": 8.79518928565085} +{"Pretrain/Learning Rate": 2.8748377010524574e-07, "Pretrain/Loss": 2.0260870456695557, "Pretrain/Loss (Raw)": 1.873613715171814, "Pretrain/Step": 9090, "Pretrain/Step Time": 8.800225084647536} +{"Pretrain/Learning Rate": 2.8620138518211934e-07, "Pretrain/Loss": 2.026130437850952, "Pretrain/Loss (Raw)": 2.1022684574127197, "Pretrain/Step": 9091, "Pretrain/Step Time": 8.79579907655716} +{"Pretrain/Learning Rate": 2.849218503707035e-07, "Pretrain/Loss": 2.0237603187561035, "Pretrain/Loss (Raw)": 1.8471128940582275, "Pretrain/Step": 9092, "Pretrain/Step Time": 8.794899301603436} +{"Pretrain/Learning Rate": 2.836451658185607e-07, "Pretrain/Loss": 2.023205280303955, "Pretrain/Loss (Raw)": 2.1180057525634766, "Pretrain/Step": 9093, "Pretrain/Step Time": 8.799498107284307} +{"Pretrain/Learning Rate": 2.82371331672926e-07, "Pretrain/Loss": 2.0236473083496094, "Pretrain/Loss (Raw)": 2.1813266277313232, "Pretrain/Step": 9094, "Pretrain/Step Time": 8.791285706683993} +{"Pretrain/Learning Rate": 2.8110034808070396e-07, "Pretrain/Loss": 2.023712158203125, "Pretrain/Loss (Raw)": 2.0809073448181152, "Pretrain/Step": 9095, "Pretrain/Step Time": 8.799686474725604} +{"Pretrain/Learning Rate": 2.7983221518846634e-07, "Pretrain/Loss": 2.0238890647888184, "Pretrain/Loss (Raw)": 1.9866697788238525, "Pretrain/Step": 9096, "Pretrain/Step Time": 8.793848847970366} +{"Pretrain/Learning Rate": 2.7856693314246287e-07, "Pretrain/Loss": 2.02309250831604, "Pretrain/Loss (Raw)": 1.9293628931045532, "Pretrain/Step": 9097, "Pretrain/Step Time": 8.795307720080018} +{"Pretrain/Learning Rate": 2.773045020886156e-07, "Pretrain/Loss": 2.023097276687622, "Pretrain/Loss (Raw)": 1.8791613578796387, "Pretrain/Step": 9098, "Pretrain/Step Time": 8.794109918177128} +{"Pretrain/Learning Rate": 2.760449221725081e-07, "Pretrain/Loss": 2.0225670337677, "Pretrain/Loss (Raw)": 2.051438093185425, "Pretrain/Step": 9099, "Pretrain/Step Time": 8.798440765589476} +{"Pretrain/Learning Rate": 2.74788193539402e-07, "Pretrain/Loss": 2.0236151218414307, "Pretrain/Loss (Raw)": 1.9434585571289062, "Pretrain/Step": 9100, "Pretrain/Step Time": 8.799088740721345} +{"Pretrain/Learning Rate": 2.7353431633423134e-07, "Pretrain/Loss": 2.023599147796631, "Pretrain/Loss (Raw)": 1.9808356761932373, "Pretrain/Step": 9101, "Pretrain/Step Time": 8.79980694130063} +{"Pretrain/Learning Rate": 2.722832907015971e-07, "Pretrain/Loss": 2.023146390914917, "Pretrain/Loss (Raw)": 1.8993558883666992, "Pretrain/Step": 9102, "Pretrain/Step Time": 8.80361494794488} +{"Pretrain/Learning Rate": 2.710351167857783e-07, "Pretrain/Loss": 2.019307851791382, "Pretrain/Loss (Raw)": 1.9104456901550293, "Pretrain/Step": 9103, "Pretrain/Step Time": 8.804296508431435} +{"Pretrain/Learning Rate": 2.6978979473071264e-07, "Pretrain/Loss": 2.018299102783203, "Pretrain/Loss (Raw)": 1.9719338417053223, "Pretrain/Step": 9104, "Pretrain/Step Time": 8.804923152551055} +{"Pretrain/Learning Rate": 2.6854732468002133e-07, "Pretrain/Loss": 2.015810012817383, "Pretrain/Loss (Raw)": 1.7020468711853027, "Pretrain/Step": 9105, "Pretrain/Step Time": 8.806949563324451} +{"Pretrain/Learning Rate": 2.6730770677699245e-07, "Pretrain/Loss": 2.017498731613159, "Pretrain/Loss (Raw)": 2.0830936431884766, "Pretrain/Step": 9106, "Pretrain/Step Time": 8.81075426377356} +{"Pretrain/Learning Rate": 2.6607094116458123e-07, "Pretrain/Loss": 2.017528533935547, "Pretrain/Loss (Raw)": 2.1083831787109375, "Pretrain/Step": 9107, "Pretrain/Step Time": 8.809572337195277} +{"Pretrain/Learning Rate": 2.6483702798542066e-07, "Pretrain/Loss": 2.019756555557251, "Pretrain/Loss (Raw)": 2.2012085914611816, "Pretrain/Step": 9108, "Pretrain/Step Time": 8.810693066567183} +{"Pretrain/Learning Rate": 2.636059673818081e-07, "Pretrain/Loss": 2.0206124782562256, "Pretrain/Loss (Raw)": 2.0758306980133057, "Pretrain/Step": 9109, "Pretrain/Step Time": 8.807571694254875} +{"Pretrain/Learning Rate": 2.623777594957216e-07, "Pretrain/Loss": 2.019479990005493, "Pretrain/Loss (Raw)": 1.9126806259155273, "Pretrain/Step": 9110, "Pretrain/Step Time": 8.804886313155293} +{"Pretrain/Learning Rate": 2.6115240446879517e-07, "Pretrain/Loss": 2.018662452697754, "Pretrain/Loss (Raw)": 1.9170422554016113, "Pretrain/Step": 9111, "Pretrain/Step Time": 8.80218705534935} +{"Pretrain/Learning Rate": 2.599299024423491e-07, "Pretrain/Loss": 2.018930435180664, "Pretrain/Loss (Raw)": 2.0824267864227295, "Pretrain/Step": 9112, "Pretrain/Step Time": 8.799182454124093} +{"Pretrain/Learning Rate": 2.587102535573621e-07, "Pretrain/Loss": 2.0164308547973633, "Pretrain/Loss (Raw)": 1.93921959400177, "Pretrain/Step": 9113, "Pretrain/Step Time": 8.79926597699523} +{"Pretrain/Learning Rate": 2.5749345795449687e-07, "Pretrain/Loss": 2.0161776542663574, "Pretrain/Loss (Raw)": 2.0549023151397705, "Pretrain/Step": 9114, "Pretrain/Step Time": 8.799312254413962} +{"Pretrain/Learning Rate": 2.562795157740744e-07, "Pretrain/Loss": 2.014983892440796, "Pretrain/Loss (Raw)": 1.9441218376159668, "Pretrain/Step": 9115, "Pretrain/Step Time": 8.79938667267561} +{"Pretrain/Learning Rate": 2.5506842715609656e-07, "Pretrain/Loss": 2.0129551887512207, "Pretrain/Loss (Raw)": 1.7095459699630737, "Pretrain/Step": 9116, "Pretrain/Step Time": 8.800046157091856} +{"Pretrain/Learning Rate": 2.5386019224022673e-07, "Pretrain/Loss": 2.0138704776763916, "Pretrain/Loss (Raw)": 2.129662036895752, "Pretrain/Step": 9117, "Pretrain/Step Time": 8.79984413832426} +{"Pretrain/Learning Rate": 2.526548111658117e-07, "Pretrain/Loss": 2.016446352005005, "Pretrain/Loss (Raw)": 2.109670877456665, "Pretrain/Step": 9118, "Pretrain/Step Time": 8.80028822273016} +{"Pretrain/Learning Rate": 2.514522840718542e-07, "Pretrain/Loss": 2.0171561241149902, "Pretrain/Loss (Raw)": 2.1475203037261963, "Pretrain/Step": 9119, "Pretrain/Step Time": 8.807362606748939} +{"Pretrain/Learning Rate": 2.502526110970377e-07, "Pretrain/Loss": 2.017711639404297, "Pretrain/Loss (Raw)": 2.1046531200408936, "Pretrain/Step": 9120, "Pretrain/Step Time": 8.796651065349579} +{"Pretrain/Learning Rate": 2.490557923797154e-07, "Pretrain/Loss": 2.019169807434082, "Pretrain/Loss (Raw)": 2.1426703929901123, "Pretrain/Step": 9121, "Pretrain/Step Time": 8.803510533645749} +{"Pretrain/Learning Rate": 2.478618280579104e-07, "Pretrain/Loss": 2.019498825073242, "Pretrain/Loss (Raw)": 2.0737600326538086, "Pretrain/Step": 9122, "Pretrain/Step Time": 8.803285628557205} +{"Pretrain/Learning Rate": 2.466707182693151e-07, "Pretrain/Loss": 2.017761707305908, "Pretrain/Loss (Raw)": 1.9145421981811523, "Pretrain/Step": 9123, "Pretrain/Step Time": 8.800288053229451} +{"Pretrain/Learning Rate": 2.45482463151292e-07, "Pretrain/Loss": 2.0186264514923096, "Pretrain/Loss (Raw)": 2.0981333255767822, "Pretrain/Step": 9124, "Pretrain/Step Time": 8.796543749049306} +{"Pretrain/Learning Rate": 2.442970628408814e-07, "Pretrain/Loss": 2.019969940185547, "Pretrain/Loss (Raw)": 1.9681791067123413, "Pretrain/Step": 9125, "Pretrain/Step Time": 8.797122918069363} +{"Pretrain/Learning Rate": 2.4311451747478233e-07, "Pretrain/Loss": 2.0197415351867676, "Pretrain/Loss (Raw)": 2.0610740184783936, "Pretrain/Step": 9126, "Pretrain/Step Time": 8.80087823048234} +{"Pretrain/Learning Rate": 2.4193482718937733e-07, "Pretrain/Loss": 2.0207157135009766, "Pretrain/Loss (Raw)": 2.1322152614593506, "Pretrain/Step": 9127, "Pretrain/Step Time": 8.794340375810862} +{"Pretrain/Learning Rate": 2.4075799212071317e-07, "Pretrain/Loss": 2.0232343673706055, "Pretrain/Loss (Raw)": 2.1409881114959717, "Pretrain/Step": 9128, "Pretrain/Step Time": 8.801345009356737} +{"Pretrain/Learning Rate": 2.395840124045062e-07, "Pretrain/Loss": 2.024101734161377, "Pretrain/Loss (Raw)": 2.0325703620910645, "Pretrain/Step": 9129, "Pretrain/Step Time": 8.804126929491758} +{"Pretrain/Learning Rate": 2.384128881761455e-07, "Pretrain/Loss": 2.0236096382141113, "Pretrain/Loss (Raw)": 2.180760145187378, "Pretrain/Step": 9130, "Pretrain/Step Time": 8.803393436595798} +{"Pretrain/Learning Rate": 2.3724461957068956e-07, "Pretrain/Loss": 2.0234460830688477, "Pretrain/Loss (Raw)": 2.0791869163513184, "Pretrain/Step": 9131, "Pretrain/Step Time": 8.803507152944803} +{"Pretrain/Learning Rate": 2.360792067228723e-07, "Pretrain/Loss": 2.02406644821167, "Pretrain/Loss (Raw)": 2.005850076675415, "Pretrain/Step": 9132, "Pretrain/Step Time": 8.800472835078835} +{"Pretrain/Learning Rate": 2.349166497670918e-07, "Pretrain/Loss": 2.023733139038086, "Pretrain/Loss (Raw)": 2.098924398422241, "Pretrain/Step": 9133, "Pretrain/Step Time": 8.798665123060346} +{"Pretrain/Learning Rate": 2.337569488374186e-07, "Pretrain/Loss": 2.024132490158081, "Pretrain/Loss (Raw)": 2.134565830230713, "Pretrain/Step": 9134, "Pretrain/Step Time": 8.799364641308784} +{"Pretrain/Learning Rate": 2.3260010406759846e-07, "Pretrain/Loss": 2.025546073913574, "Pretrain/Loss (Raw)": 2.028942108154297, "Pretrain/Step": 9135, "Pretrain/Step Time": 8.80405731126666} +{"Pretrain/Learning Rate": 2.3144611559104134e-07, "Pretrain/Loss": 2.024305820465088, "Pretrain/Loss (Raw)": 1.9437798261642456, "Pretrain/Step": 9136, "Pretrain/Step Time": 8.803495302796364} +{"Pretrain/Learning Rate": 2.3029498354083245e-07, "Pretrain/Loss": 2.02504825592041, "Pretrain/Loss (Raw)": 2.0266008377075195, "Pretrain/Step": 9137, "Pretrain/Step Time": 8.803320562466979} +{"Pretrain/Learning Rate": 2.2914670804972394e-07, "Pretrain/Loss": 2.024301052093506, "Pretrain/Loss (Raw)": 1.7888137102127075, "Pretrain/Step": 9138, "Pretrain/Step Time": 8.800486328080297} +{"Pretrain/Learning Rate": 2.2800128925014042e-07, "Pretrain/Loss": 2.0219039916992188, "Pretrain/Loss (Raw)": 1.7947660684585571, "Pretrain/Step": 9139, "Pretrain/Step Time": 8.803683208301663} +{"Pretrain/Learning Rate": 2.26858727274179e-07, "Pretrain/Loss": 2.0220234394073486, "Pretrain/Loss (Raw)": 2.0431671142578125, "Pretrain/Step": 9140, "Pretrain/Step Time": 8.809602158144116} +{"Pretrain/Learning Rate": 2.2571902225360374e-07, "Pretrain/Loss": 2.0186667442321777, "Pretrain/Loss (Raw)": 1.7569458484649658, "Pretrain/Step": 9141, "Pretrain/Step Time": 8.805167512968183} +{"Pretrain/Learning Rate": 2.2458217431984842e-07, "Pretrain/Loss": 2.018400192260742, "Pretrain/Loss (Raw)": 2.142489194869995, "Pretrain/Step": 9142, "Pretrain/Step Time": 8.806696133688092} +{"Pretrain/Learning Rate": 2.2344818360402476e-07, "Pretrain/Loss": 2.019296646118164, "Pretrain/Loss (Raw)": 2.27899432182312, "Pretrain/Step": 9143, "Pretrain/Step Time": 8.804146211594343} +{"Pretrain/Learning Rate": 2.2231705023690875e-07, "Pretrain/Loss": 2.01975679397583, "Pretrain/Loss (Raw)": 2.0625922679901123, "Pretrain/Step": 9144, "Pretrain/Step Time": 8.799983309581876} +{"Pretrain/Learning Rate": 2.2118877434894325e-07, "Pretrain/Loss": 2.020076274871826, "Pretrain/Loss (Raw)": 2.0716969966888428, "Pretrain/Step": 9145, "Pretrain/Step Time": 8.80354392528534} +{"Pretrain/Learning Rate": 2.2006335607025196e-07, "Pretrain/Loss": 2.020193099975586, "Pretrain/Loss (Raw)": 1.994064211845398, "Pretrain/Step": 9146, "Pretrain/Step Time": 8.803969522938132} +{"Pretrain/Learning Rate": 2.1894079553062276e-07, "Pretrain/Loss": 2.021017074584961, "Pretrain/Loss (Raw)": 2.0928053855895996, "Pretrain/Step": 9147, "Pretrain/Step Time": 8.803410965949297} +{"Pretrain/Learning Rate": 2.1782109285951034e-07, "Pretrain/Loss": 2.0212278366088867, "Pretrain/Loss (Raw)": 1.9739867448806763, "Pretrain/Step": 9148, "Pretrain/Step Time": 8.81408891826868} +{"Pretrain/Learning Rate": 2.167042481860504e-07, "Pretrain/Loss": 2.022965908050537, "Pretrain/Loss (Raw)": 2.131547689437866, "Pretrain/Step": 9149, "Pretrain/Step Time": 8.806350655853748} +{"Pretrain/Learning Rate": 2.1559026163903427e-07, "Pretrain/Loss": 2.0205435752868652, "Pretrain/Loss (Raw)": 1.6557719707489014, "Pretrain/Step": 9150, "Pretrain/Step Time": 8.810765439644456} +{"Pretrain/Learning Rate": 2.1447913334694258e-07, "Pretrain/Loss": 2.0200140476226807, "Pretrain/Loss (Raw)": 2.087692975997925, "Pretrain/Step": 9151, "Pretrain/Step Time": 8.811500640586019} +{"Pretrain/Learning Rate": 2.1337086343790613e-07, "Pretrain/Loss": 2.020840644836426, "Pretrain/Loss (Raw)": 2.271357774734497, "Pretrain/Step": 9152, "Pretrain/Step Time": 8.807988056913018} +{"Pretrain/Learning Rate": 2.1226545203974212e-07, "Pretrain/Loss": 2.0179691314697266, "Pretrain/Loss (Raw)": 1.8851218223571777, "Pretrain/Step": 9153, "Pretrain/Step Time": 8.81079688668251} +{"Pretrain/Learning Rate": 2.1116289927992917e-07, "Pretrain/Loss": 2.016922950744629, "Pretrain/Loss (Raw)": 1.8937252759933472, "Pretrain/Step": 9154, "Pretrain/Step Time": 8.810355888679624} +{"Pretrain/Learning Rate": 2.1006320528562107e-07, "Pretrain/Loss": 2.017611026763916, "Pretrain/Loss (Raw)": 2.1015737056732178, "Pretrain/Step": 9155, "Pretrain/Step Time": 8.814254453405738} +{"Pretrain/Learning Rate": 2.0896637018363863e-07, "Pretrain/Loss": 2.01824951171875, "Pretrain/Loss (Raw)": 2.1532397270202637, "Pretrain/Step": 9156, "Pretrain/Step Time": 8.809379434213042} +{"Pretrain/Learning Rate": 2.0787239410047232e-07, "Pretrain/Loss": 2.017096519470215, "Pretrain/Loss (Raw)": 2.056330919265747, "Pretrain/Step": 9157, "Pretrain/Step Time": 8.809040874242783} +{"Pretrain/Learning Rate": 2.0678127716228236e-07, "Pretrain/Loss": 2.017707347869873, "Pretrain/Loss (Raw)": 2.0513224601745605, "Pretrain/Step": 9158, "Pretrain/Step Time": 8.809444708749652} +{"Pretrain/Learning Rate": 2.056930194949097e-07, "Pretrain/Loss": 2.0161681175231934, "Pretrain/Loss (Raw)": 2.0031816959381104, "Pretrain/Step": 9159, "Pretrain/Step Time": 8.810953978449106} +{"Pretrain/Learning Rate": 2.0460762122385125e-07, "Pretrain/Loss": 2.0165467262268066, "Pretrain/Loss (Raw)": 2.2492263317108154, "Pretrain/Step": 9160, "Pretrain/Step Time": 8.80977519787848} +{"Pretrain/Learning Rate": 2.035250824742818e-07, "Pretrain/Loss": 2.019008159637451, "Pretrain/Loss (Raw)": 2.1768100261688232, "Pretrain/Step": 9161, "Pretrain/Step Time": 8.812548507004976} +{"Pretrain/Learning Rate": 2.02445403371046e-07, "Pretrain/Loss": 2.0184812545776367, "Pretrain/Loss (Raw)": 2.0163159370422363, "Pretrain/Step": 9162, "Pretrain/Step Time": 8.809636358171701} +{"Pretrain/Learning Rate": 2.0136858403865534e-07, "Pretrain/Loss": 2.01715087890625, "Pretrain/Loss (Raw)": 1.962207555770874, "Pretrain/Step": 9163, "Pretrain/Step Time": 8.810451885685325} +{"Pretrain/Learning Rate": 2.00294624601291e-07, "Pretrain/Loss": 2.020444393157959, "Pretrain/Loss (Raw)": 2.16445255279541, "Pretrain/Step": 9164, "Pretrain/Step Time": 8.808944964781404} +{"Pretrain/Learning Rate": 1.9922352518281505e-07, "Pretrain/Loss": 2.019993305206299, "Pretrain/Loss (Raw)": 2.105621099472046, "Pretrain/Step": 9165, "Pretrain/Step Time": 8.809071721509099} +{"Pretrain/Learning Rate": 1.9815528590674537e-07, "Pretrain/Loss": 2.0225136280059814, "Pretrain/Loss (Raw)": 2.250457763671875, "Pretrain/Step": 9166, "Pretrain/Step Time": 8.810811255127192} +{"Pretrain/Learning Rate": 1.9708990689627783e-07, "Pretrain/Loss": 2.021418571472168, "Pretrain/Loss (Raw)": 2.056917667388916, "Pretrain/Step": 9167, "Pretrain/Step Time": 8.817566361278296} +{"Pretrain/Learning Rate": 1.9602738827427802e-07, "Pretrain/Loss": 2.0226268768310547, "Pretrain/Loss (Raw)": 2.1471426486968994, "Pretrain/Step": 9168, "Pretrain/Step Time": 8.81847888045013} +{"Pretrain/Learning Rate": 1.9496773016327852e-07, "Pretrain/Loss": 2.0216894149780273, "Pretrain/Loss (Raw)": 1.9781707525253296, "Pretrain/Step": 9169, "Pretrain/Step Time": 8.821323171257973} +{"Pretrain/Learning Rate": 1.9391093268548988e-07, "Pretrain/Loss": 2.0194852352142334, "Pretrain/Loss (Raw)": 1.8914344310760498, "Pretrain/Step": 9170, "Pretrain/Step Time": 8.822689957916737} +{"Pretrain/Learning Rate": 1.9285699596277852e-07, "Pretrain/Loss": 2.020681858062744, "Pretrain/Loss (Raw)": 2.03737211227417, "Pretrain/Step": 9171, "Pretrain/Step Time": 8.820680763572454} +{"Pretrain/Learning Rate": 1.918059201166944e-07, "Pretrain/Loss": 2.020827293395996, "Pretrain/Loss (Raw)": 2.1328554153442383, "Pretrain/Step": 9172, "Pretrain/Step Time": 8.815222879871726} +{"Pretrain/Learning Rate": 1.9075770526845172e-07, "Pretrain/Loss": 2.021294116973877, "Pretrain/Loss (Raw)": 2.0832910537719727, "Pretrain/Step": 9173, "Pretrain/Step Time": 8.813671274110675} +{"Pretrain/Learning Rate": 1.8971235153893708e-07, "Pretrain/Loss": 2.0217623710632324, "Pretrain/Loss (Raw)": 2.1760828495025635, "Pretrain/Step": 9174, "Pretrain/Step Time": 8.810985526069999} +{"Pretrain/Learning Rate": 1.8866985904870127e-07, "Pretrain/Loss": 2.025364875793457, "Pretrain/Loss (Raw)": 2.1629269123077393, "Pretrain/Step": 9175, "Pretrain/Step Time": 8.801085893064737} +{"Pretrain/Learning Rate": 1.8763022791797314e-07, "Pretrain/Loss": 2.02425217628479, "Pretrain/Loss (Raw)": 1.8997046947479248, "Pretrain/Step": 9176, "Pretrain/Step Time": 8.808041907846928} +{"Pretrain/Learning Rate": 1.8659345826664844e-07, "Pretrain/Loss": 2.026113510131836, "Pretrain/Loss (Raw)": 2.196007251739502, "Pretrain/Step": 9177, "Pretrain/Step Time": 8.809662381187081} +{"Pretrain/Learning Rate": 1.8555955021428984e-07, "Pretrain/Loss": 2.0250654220581055, "Pretrain/Loss (Raw)": 1.8839061260223389, "Pretrain/Step": 9178, "Pretrain/Step Time": 8.81069390848279} +{"Pretrain/Learning Rate": 1.8452850388013255e-07, "Pretrain/Loss": 2.0243053436279297, "Pretrain/Loss (Raw)": 2.1899337768554688, "Pretrain/Step": 9179, "Pretrain/Step Time": 8.803902016952634} +{"Pretrain/Learning Rate": 1.8350031938308144e-07, "Pretrain/Loss": 2.024628162384033, "Pretrain/Loss (Raw)": 2.119040012359619, "Pretrain/Step": 9180, "Pretrain/Step Time": 8.809246802702546} +{"Pretrain/Learning Rate": 1.8247499684171666e-07, "Pretrain/Loss": 2.0260815620422363, "Pretrain/Loss (Raw)": 2.17777419090271, "Pretrain/Step": 9181, "Pretrain/Step Time": 8.811843687668443} +{"Pretrain/Learning Rate": 1.8145253637427695e-07, "Pretrain/Loss": 2.0286245346069336, "Pretrain/Loss (Raw)": 2.128389596939087, "Pretrain/Step": 9182, "Pretrain/Step Time": 8.813053969293833} +{"Pretrain/Learning Rate": 1.8043293809867635e-07, "Pretrain/Loss": 2.0282959938049316, "Pretrain/Loss (Raw)": 1.9952666759490967, "Pretrain/Step": 9183, "Pretrain/Step Time": 8.800757868215442} +{"Pretrain/Learning Rate": 1.7941620213250688e-07, "Pretrain/Loss": 2.0283613204956055, "Pretrain/Loss (Raw)": 2.076918363571167, "Pretrain/Step": 9184, "Pretrain/Step Time": 8.80154424905777} +{"Pretrain/Learning Rate": 1.7840232859301919e-07, "Pretrain/Loss": 2.029531717300415, "Pretrain/Loss (Raw)": 2.106210708618164, "Pretrain/Step": 9185, "Pretrain/Step Time": 8.797535315155983} +{"Pretrain/Learning Rate": 1.7739131759713924e-07, "Pretrain/Loss": 2.028923988342285, "Pretrain/Loss (Raw)": 2.0360488891601562, "Pretrain/Step": 9186, "Pretrain/Step Time": 8.805470006540418} +{"Pretrain/Learning Rate": 1.7638316926145702e-07, "Pretrain/Loss": 2.027661085128784, "Pretrain/Loss (Raw)": 1.7705785036087036, "Pretrain/Step": 9187, "Pretrain/Step Time": 8.803019907325506} +{"Pretrain/Learning Rate": 1.7537788370224351e-07, "Pretrain/Loss": 2.028109073638916, "Pretrain/Loss (Raw)": 2.058912754058838, "Pretrain/Step": 9188, "Pretrain/Step Time": 8.806754730641842} +{"Pretrain/Learning Rate": 1.7437546103542814e-07, "Pretrain/Loss": 2.02803111076355, "Pretrain/Loss (Raw)": 1.9779852628707886, "Pretrain/Step": 9189, "Pretrain/Step Time": 8.804758151993155} +{"Pretrain/Learning Rate": 1.7337590137661842e-07, "Pretrain/Loss": 2.0260372161865234, "Pretrain/Loss (Raw)": 1.935221791267395, "Pretrain/Step": 9190, "Pretrain/Step Time": 8.806139193475246} +{"Pretrain/Learning Rate": 1.7237920484108327e-07, "Pretrain/Loss": 2.023771047592163, "Pretrain/Loss (Raw)": 1.8715455532073975, "Pretrain/Step": 9191, "Pretrain/Step Time": 8.806588668376207} +{"Pretrain/Learning Rate": 1.7138537154377243e-07, "Pretrain/Loss": 2.0249059200286865, "Pretrain/Loss (Raw)": 2.0391292572021484, "Pretrain/Step": 9192, "Pretrain/Step Time": 8.810551479458809} +{"Pretrain/Learning Rate": 1.70394401599297e-07, "Pretrain/Loss": 2.0260071754455566, "Pretrain/Loss (Raw)": 2.0700464248657227, "Pretrain/Step": 9193, "Pretrain/Step Time": 8.800440717488527} +{"Pretrain/Learning Rate": 1.6940629512194052e-07, "Pretrain/Loss": 2.0305113792419434, "Pretrain/Loss (Raw)": 2.446798324584961, "Pretrain/Step": 9194, "Pretrain/Step Time": 8.799948023632169} +{"Pretrain/Learning Rate": 1.6842105222565352e-07, "Pretrain/Loss": 2.0328989028930664, "Pretrain/Loss (Raw)": 2.3379015922546387, "Pretrain/Step": 9195, "Pretrain/Step Time": 8.798606667667627} +{"Pretrain/Learning Rate": 1.6743867302406458e-07, "Pretrain/Loss": 2.0296382904052734, "Pretrain/Loss (Raw)": 1.7452291250228882, "Pretrain/Step": 9196, "Pretrain/Step Time": 8.801078263670206} +{"Pretrain/Learning Rate": 1.6645915763045804e-07, "Pretrain/Loss": 2.0305569171905518, "Pretrain/Loss (Raw)": 1.9933316707611084, "Pretrain/Step": 9197, "Pretrain/Step Time": 8.799744997173548} +{"Pretrain/Learning Rate": 1.654825061578047e-07, "Pretrain/Loss": 2.0303051471710205, "Pretrain/Loss (Raw)": 2.0209310054779053, "Pretrain/Step": 9198, "Pretrain/Step Time": 8.803282778710127} +{"Pretrain/Learning Rate": 1.6450871871873108e-07, "Pretrain/Loss": 2.0328516960144043, "Pretrain/Loss (Raw)": 2.145719528198242, "Pretrain/Step": 9199, "Pretrain/Step Time": 8.801486754789948} +{"Pretrain/Learning Rate": 1.6353779542554182e-07, "Pretrain/Loss": 2.031430721282959, "Pretrain/Loss (Raw)": 1.8485409021377563, "Pretrain/Step": 9200, "Pretrain/Step Time": 8.8037703409791} +{"Pretrain/Learning Rate": 1.6256973639020569e-07, "Pretrain/Loss": 2.029829502105713, "Pretrain/Loss (Raw)": 1.8696244955062866, "Pretrain/Step": 9201, "Pretrain/Step Time": 8.804218841716647} +{"Pretrain/Learning Rate": 1.6160454172436667e-07, "Pretrain/Loss": 2.0303990840911865, "Pretrain/Loss (Raw)": 2.162738800048828, "Pretrain/Step": 9202, "Pretrain/Step Time": 8.802334491163492} +{"Pretrain/Learning Rate": 1.60642211539333e-07, "Pretrain/Loss": 2.032088041305542, "Pretrain/Loss (Raw)": 2.1396586894989014, "Pretrain/Step": 9203, "Pretrain/Step Time": 8.80102702230215} +{"Pretrain/Learning Rate": 1.5968274594608812e-07, "Pretrain/Loss": 2.031240940093994, "Pretrain/Loss (Raw)": 1.9060012102127075, "Pretrain/Step": 9204, "Pretrain/Step Time": 8.791084319353104} +{"Pretrain/Learning Rate": 1.587261450552796e-07, "Pretrain/Loss": 2.0305392742156982, "Pretrain/Loss (Raw)": 2.0206856727600098, "Pretrain/Step": 9205, "Pretrain/Step Time": 8.787858676165342} +{"Pretrain/Learning Rate": 1.5777240897722757e-07, "Pretrain/Loss": 2.0312600135803223, "Pretrain/Loss (Raw)": 1.9743891954421997, "Pretrain/Step": 9206, "Pretrain/Step Time": 8.790763774886727} +{"Pretrain/Learning Rate": 1.5682153782192177e-07, "Pretrain/Loss": 2.0344293117523193, "Pretrain/Loss (Raw)": 1.965586543083191, "Pretrain/Step": 9207, "Pretrain/Step Time": 8.78995356708765} +{"Pretrain/Learning Rate": 1.5587353169902175e-07, "Pretrain/Loss": 2.035093307495117, "Pretrain/Loss (Raw)": 1.9683409929275513, "Pretrain/Step": 9208, "Pretrain/Step Time": 8.792158069089055} +{"Pretrain/Learning Rate": 1.5492839071785392e-07, "Pretrain/Loss": 2.035367250442505, "Pretrain/Loss (Raw)": 1.9643582105636597, "Pretrain/Step": 9209, "Pretrain/Step Time": 8.795077787712216} +{"Pretrain/Learning Rate": 1.5398611498742e-07, "Pretrain/Loss": 2.035506010055542, "Pretrain/Loss (Raw)": 2.0305275917053223, "Pretrain/Step": 9210, "Pretrain/Step Time": 8.79501193575561} +{"Pretrain/Learning Rate": 1.5304670461638582e-07, "Pretrain/Loss": 2.0361757278442383, "Pretrain/Loss (Raw)": 2.010206699371338, "Pretrain/Step": 9211, "Pretrain/Step Time": 8.794164825230837} +{"Pretrain/Learning Rate": 1.521101597130842e-07, "Pretrain/Loss": 2.0379014015197754, "Pretrain/Loss (Raw)": 2.175471782684326, "Pretrain/Step": 9212, "Pretrain/Step Time": 8.80927561596036} +{"Pretrain/Learning Rate": 1.5117648038553144e-07, "Pretrain/Loss": 2.040357828140259, "Pretrain/Loss (Raw)": 2.1743199825286865, "Pretrain/Step": 9213, "Pretrain/Step Time": 8.803900316357613} +{"Pretrain/Learning Rate": 1.502456667413943e-07, "Pretrain/Loss": 2.038198947906494, "Pretrain/Loss (Raw)": 1.7719894647598267, "Pretrain/Step": 9214, "Pretrain/Step Time": 8.804801441729069} +{"Pretrain/Learning Rate": 1.493177188880257e-07, "Pretrain/Loss": 2.035555839538574, "Pretrain/Loss (Raw)": 1.8656120300292969, "Pretrain/Step": 9215, "Pretrain/Step Time": 8.804121945053339} +{"Pretrain/Learning Rate": 1.4839263693243732e-07, "Pretrain/Loss": 2.0331544876098633, "Pretrain/Loss (Raw)": 2.0960872173309326, "Pretrain/Step": 9216, "Pretrain/Step Time": 8.80705944262445} +{"Pretrain/Learning Rate": 1.4747042098131326e-07, "Pretrain/Loss": 2.031277656555176, "Pretrain/Loss (Raw)": 1.9137380123138428, "Pretrain/Step": 9217, "Pretrain/Step Time": 8.805421836674213} +{"Pretrain/Learning Rate": 1.4655107114101007e-07, "Pretrain/Loss": 2.0334534645080566, "Pretrain/Loss (Raw)": 2.152095317840576, "Pretrain/Step": 9218, "Pretrain/Step Time": 8.803922951221466} +{"Pretrain/Learning Rate": 1.4563458751755132e-07, "Pretrain/Loss": 2.032837390899658, "Pretrain/Loss (Raw)": 2.023456335067749, "Pretrain/Step": 9219, "Pretrain/Step Time": 8.805581538006663} +{"Pretrain/Learning Rate": 1.4472097021662745e-07, "Pretrain/Loss": 2.0333123207092285, "Pretrain/Loss (Raw)": 1.9078782796859741, "Pretrain/Step": 9220, "Pretrain/Step Time": 8.80453928746283} +{"Pretrain/Learning Rate": 1.4381021934360417e-07, "Pretrain/Loss": 2.0328450202941895, "Pretrain/Loss (Raw)": 2.058206558227539, "Pretrain/Step": 9221, "Pretrain/Step Time": 8.803432630375028} +{"Pretrain/Learning Rate": 1.4290233500351414e-07, "Pretrain/Loss": 2.0323486328125, "Pretrain/Loss (Raw)": 2.1177899837493896, "Pretrain/Step": 9222, "Pretrain/Step Time": 8.8049097917974} +{"Pretrain/Learning Rate": 1.4199731730105693e-07, "Pretrain/Loss": 2.0329384803771973, "Pretrain/Loss (Raw)": 2.156381368637085, "Pretrain/Step": 9223, "Pretrain/Step Time": 8.798150217160583} +{"Pretrain/Learning Rate": 1.4109516634060182e-07, "Pretrain/Loss": 2.0339341163635254, "Pretrain/Loss (Raw)": 2.1141273975372314, "Pretrain/Step": 9224, "Pretrain/Step Time": 8.79820398055017} +{"Pretrain/Learning Rate": 1.401958822261934e-07, "Pretrain/Loss": 2.0337588787078857, "Pretrain/Loss (Raw)": 1.9069362878799438, "Pretrain/Step": 9225, "Pretrain/Step Time": 8.79705568216741} +{"Pretrain/Learning Rate": 1.3929946506153758e-07, "Pretrain/Loss": 2.03520131111145, "Pretrain/Loss (Raw)": 2.0637834072113037, "Pretrain/Step": 9226, "Pretrain/Step Time": 8.802693417295814} +{"Pretrain/Learning Rate": 1.3840591495001554e-07, "Pretrain/Loss": 2.035848379135132, "Pretrain/Loss (Raw)": 2.134268283843994, "Pretrain/Step": 9227, "Pretrain/Step Time": 8.799374820664525} +{"Pretrain/Learning Rate": 1.375152319946754e-07, "Pretrain/Loss": 2.036797285079956, "Pretrain/Loss (Raw)": 2.0649337768554688, "Pretrain/Step": 9228, "Pretrain/Step Time": 8.802269570529461} +{"Pretrain/Learning Rate": 1.3662741629823506e-07, "Pretrain/Loss": 2.037811279296875, "Pretrain/Loss (Raw)": 2.1105964183807373, "Pretrain/Step": 9229, "Pretrain/Step Time": 8.802489258348942} +{"Pretrain/Learning Rate": 1.357424679630792e-07, "Pretrain/Loss": 2.0397114753723145, "Pretrain/Loss (Raw)": 2.1426143646240234, "Pretrain/Step": 9230, "Pretrain/Step Time": 8.800889499485493} +{"Pretrain/Learning Rate": 1.348603870912679e-07, "Pretrain/Loss": 2.039242744445801, "Pretrain/Loss (Raw)": 1.850447416305542, "Pretrain/Step": 9231, "Pretrain/Step Time": 8.797275530174375} +{"Pretrain/Learning Rate": 1.3398117378452534e-07, "Pretrain/Loss": 2.041640043258667, "Pretrain/Loss (Raw)": 2.278801918029785, "Pretrain/Step": 9232, "Pretrain/Step Time": 8.799043208360672} +{"Pretrain/Learning Rate": 1.331048281442454e-07, "Pretrain/Loss": 2.0454978942871094, "Pretrain/Loss (Raw)": 2.195840358734131, "Pretrain/Step": 9233, "Pretrain/Step Time": 8.80409157089889} +{"Pretrain/Learning Rate": 1.322313502714917e-07, "Pretrain/Loss": 2.0456643104553223, "Pretrain/Loss (Raw)": 2.104382276535034, "Pretrain/Step": 9234, "Pretrain/Step Time": 8.79965265840292} +{"Pretrain/Learning Rate": 1.3136074026700307e-07, "Pretrain/Loss": 2.0437440872192383, "Pretrain/Loss (Raw)": 1.8626002073287964, "Pretrain/Step": 9235, "Pretrain/Step Time": 8.803753986954689} +{"Pretrain/Learning Rate": 1.30492998231177e-07, "Pretrain/Loss": 2.042656183242798, "Pretrain/Loss (Raw)": 2.06196928024292, "Pretrain/Step": 9236, "Pretrain/Step Time": 8.797823127359152} +{"Pretrain/Learning Rate": 1.296281242640862e-07, "Pretrain/Loss": 2.0434279441833496, "Pretrain/Loss (Raw)": 2.174574613571167, "Pretrain/Step": 9237, "Pretrain/Step Time": 8.802138453349471} +{"Pretrain/Learning Rate": 1.2876611846547593e-07, "Pretrain/Loss": 2.0441737174987793, "Pretrain/Loss (Raw)": 2.0081536769866943, "Pretrain/Step": 9238, "Pretrain/Step Time": 8.801482347771525} +{"Pretrain/Learning Rate": 1.2790698093474995e-07, "Pretrain/Loss": 2.044158935546875, "Pretrain/Loss (Raw)": 1.915152907371521, "Pretrain/Step": 9239, "Pretrain/Step Time": 8.79731896147132} +{"Pretrain/Learning Rate": 1.270507117709957e-07, "Pretrain/Loss": 2.045397996902466, "Pretrain/Loss (Raw)": 2.2410430908203125, "Pretrain/Step": 9240, "Pretrain/Step Time": 8.799657303839922} +{"Pretrain/Learning Rate": 1.2619731107295917e-07, "Pretrain/Loss": 2.0461039543151855, "Pretrain/Loss (Raw)": 2.029564142227173, "Pretrain/Step": 9241, "Pretrain/Step Time": 8.80934438481927} +{"Pretrain/Learning Rate": 1.2534677893905334e-07, "Pretrain/Loss": 2.04689359664917, "Pretrain/Loss (Raw)": 2.1559641361236572, "Pretrain/Step": 9242, "Pretrain/Step Time": 8.80853970721364} +{"Pretrain/Learning Rate": 1.244991154673747e-07, "Pretrain/Loss": 2.04799222946167, "Pretrain/Loss (Raw)": 2.084770679473877, "Pretrain/Step": 9243, "Pretrain/Step Time": 8.808536972850561} +{"Pretrain/Learning Rate": 1.2365432075567007e-07, "Pretrain/Loss": 2.05055570602417, "Pretrain/Loss (Raw)": 2.0376839637756348, "Pretrain/Step": 9244, "Pretrain/Step Time": 8.811798861250281} +{"Pretrain/Learning Rate": 1.228123949013754e-07, "Pretrain/Loss": 2.049623966217041, "Pretrain/Loss (Raw)": 2.0103683471679688, "Pretrain/Step": 9245, "Pretrain/Step Time": 8.813441216945648} +{"Pretrain/Learning Rate": 1.2197333800157973e-07, "Pretrain/Loss": 2.049396514892578, "Pretrain/Loss (Raw)": 2.0805346965789795, "Pretrain/Step": 9246, "Pretrain/Step Time": 8.814032696187496} +{"Pretrain/Learning Rate": 1.2113715015304728e-07, "Pretrain/Loss": 2.0494492053985596, "Pretrain/Loss (Raw)": 2.1542999744415283, "Pretrain/Step": 9247, "Pretrain/Step Time": 8.805317878723145} +{"Pretrain/Learning Rate": 1.2030383145221203e-07, "Pretrain/Loss": 2.048804759979248, "Pretrain/Loss (Raw)": 2.0221786499023438, "Pretrain/Step": 9248, "Pretrain/Step Time": 8.81271143630147} +{"Pretrain/Learning Rate": 1.1947338199517489e-07, "Pretrain/Loss": 2.0459647178649902, "Pretrain/Loss (Raw)": 1.7791540622711182, "Pretrain/Step": 9249, "Pretrain/Step Time": 8.807608837261796} +{"Pretrain/Learning Rate": 1.1864580187770647e-07, "Pretrain/Loss": 2.0453546047210693, "Pretrain/Loss (Raw)": 1.9956302642822266, "Pretrain/Step": 9250, "Pretrain/Step Time": 8.808307614177465} +{"Pretrain/Learning Rate": 1.1782109119524986e-07, "Pretrain/Loss": 2.045788288116455, "Pretrain/Loss (Raw)": 1.9700385332107544, "Pretrain/Step": 9251, "Pretrain/Step Time": 8.805778915062547} +{"Pretrain/Learning Rate": 1.169992500429179e-07, "Pretrain/Loss": 2.046513557434082, "Pretrain/Loss (Raw)": 2.1910083293914795, "Pretrain/Step": 9252, "Pretrain/Step Time": 8.810925463214517} +{"Pretrain/Learning Rate": 1.1618027851548197e-07, "Pretrain/Loss": 2.048175573348999, "Pretrain/Loss (Raw)": 2.180901050567627, "Pretrain/Step": 9253, "Pretrain/Step Time": 8.80962498486042} +{"Pretrain/Learning Rate": 1.1536417670739152e-07, "Pretrain/Loss": 2.0450401306152344, "Pretrain/Loss (Raw)": 1.659705400466919, "Pretrain/Step": 9254, "Pretrain/Step Time": 8.80575936101377} +{"Pretrain/Learning Rate": 1.1455094471276573e-07, "Pretrain/Loss": 2.043234348297119, "Pretrain/Loss (Raw)": 1.901094675064087, "Pretrain/Step": 9255, "Pretrain/Step Time": 8.805956127122045} +{"Pretrain/Learning Rate": 1.1374058262539067e-07, "Pretrain/Loss": 2.041585922241211, "Pretrain/Loss (Raw)": 1.9300053119659424, "Pretrain/Step": 9256, "Pretrain/Step Time": 8.799701299518347} +{"Pretrain/Learning Rate": 1.1293309053871659e-07, "Pretrain/Loss": 2.042440176010132, "Pretrain/Loss (Raw)": 2.1419179439544678, "Pretrain/Step": 9257, "Pretrain/Step Time": 8.796399062499404} +{"Pretrain/Learning Rate": 1.1212846854587177e-07, "Pretrain/Loss": 2.041386127471924, "Pretrain/Loss (Raw)": 2.0458390712738037, "Pretrain/Step": 9258, "Pretrain/Step Time": 8.797885168343782} +{"Pretrain/Learning Rate": 1.113267167396459e-07, "Pretrain/Loss": 2.0408942699432373, "Pretrain/Loss (Raw)": 2.016235828399658, "Pretrain/Step": 9259, "Pretrain/Step Time": 8.800433404743671} +{"Pretrain/Learning Rate": 1.1052783521250387e-07, "Pretrain/Loss": 2.0417964458465576, "Pretrain/Loss (Raw)": 2.1213316917419434, "Pretrain/Step": 9260, "Pretrain/Step Time": 8.801039541140199} +{"Pretrain/Learning Rate": 1.0973182405657479e-07, "Pretrain/Loss": 2.0433287620544434, "Pretrain/Loss (Raw)": 2.295055627822876, "Pretrain/Step": 9261, "Pretrain/Step Time": 8.796042580157518} +{"Pretrain/Learning Rate": 1.089386833636602e-07, "Pretrain/Loss": 2.042027473449707, "Pretrain/Loss (Raw)": 1.9679611921310425, "Pretrain/Step": 9262, "Pretrain/Step Time": 8.80829175747931} +{"Pretrain/Learning Rate": 1.0814841322522585e-07, "Pretrain/Loss": 2.0416173934936523, "Pretrain/Loss (Raw)": 1.9764604568481445, "Pretrain/Step": 9263, "Pretrain/Step Time": 8.801247203722596} +{"Pretrain/Learning Rate": 1.0736101373240992e-07, "Pretrain/Loss": 2.042093276977539, "Pretrain/Loss (Raw)": 2.004720687866211, "Pretrain/Step": 9264, "Pretrain/Step Time": 8.802410194650292} +{"Pretrain/Learning Rate": 1.0657648497601757e-07, "Pretrain/Loss": 2.0395843982696533, "Pretrain/Loss (Raw)": 1.7054710388183594, "Pretrain/Step": 9265, "Pretrain/Step Time": 8.79878630116582} +{"Pretrain/Learning Rate": 1.0579482704653199e-07, "Pretrain/Loss": 2.0426979064941406, "Pretrain/Loss (Raw)": 2.1873180866241455, "Pretrain/Step": 9266, "Pretrain/Step Time": 8.80285706743598} +{"Pretrain/Learning Rate": 1.0501604003408938e-07, "Pretrain/Loss": 2.044771194458008, "Pretrain/Loss (Raw)": 2.0601489543914795, "Pretrain/Step": 9267, "Pretrain/Step Time": 8.797875167801976} +{"Pretrain/Learning Rate": 1.042401240285068e-07, "Pretrain/Loss": 2.0440750122070312, "Pretrain/Loss (Raw)": 1.9540581703186035, "Pretrain/Step": 9268, "Pretrain/Step Time": 8.796134831383824} +{"Pretrain/Learning Rate": 1.0346707911926268e-07, "Pretrain/Loss": 2.0468575954437256, "Pretrain/Loss (Raw)": 2.113128900527954, "Pretrain/Step": 9269, "Pretrain/Step Time": 8.796590104699135} +{"Pretrain/Learning Rate": 1.0269690539551625e-07, "Pretrain/Loss": 2.0461089611053467, "Pretrain/Loss (Raw)": 2.0466558933258057, "Pretrain/Step": 9270, "Pretrain/Step Time": 8.794272201135755} +{"Pretrain/Learning Rate": 1.0192960294607978e-07, "Pretrain/Loss": 2.0432698726654053, "Pretrain/Loss (Raw)": 1.9156080484390259, "Pretrain/Step": 9271, "Pretrain/Step Time": 8.795789692550898} +{"Pretrain/Learning Rate": 1.011651718594464e-07, "Pretrain/Loss": 2.0444960594177246, "Pretrain/Loss (Raw)": 2.219540596008301, "Pretrain/Step": 9272, "Pretrain/Step Time": 8.798069838434458} +{"Pretrain/Learning Rate": 1.0040361222377059e-07, "Pretrain/Loss": 2.0436959266662598, "Pretrain/Loss (Raw)": 1.9692999124526978, "Pretrain/Step": 9273, "Pretrain/Step Time": 8.794902689754963} +{"Pretrain/Learning Rate": 9.964492412688209e-08, "Pretrain/Loss": 2.045703887939453, "Pretrain/Loss (Raw)": 2.251079797744751, "Pretrain/Step": 9274, "Pretrain/Step Time": 8.795064413920045} +{"Pretrain/Learning Rate": 9.88891076562748e-08, "Pretrain/Loss": 2.0451395511627197, "Pretrain/Loss (Raw)": 2.0205471515655518, "Pretrain/Step": 9275, "Pretrain/Step Time": 8.801221918314695} +{"Pretrain/Learning Rate": 9.813616289911509e-08, "Pretrain/Loss": 2.0466277599334717, "Pretrain/Loss (Raw)": 2.1644814014434814, "Pretrain/Step": 9276, "Pretrain/Step Time": 8.7905531860888} +{"Pretrain/Learning Rate": 9.738608994223352e-08, "Pretrain/Loss": 2.0458860397338867, "Pretrain/Loss (Raw)": 2.036597728729248, "Pretrain/Step": 9277, "Pretrain/Step Time": 8.795258168131113} +{"Pretrain/Learning Rate": 9.663888887213313e-08, "Pretrain/Loss": 2.049643039703369, "Pretrain/Loss (Raw)": 2.1367032527923584, "Pretrain/Step": 9278, "Pretrain/Step Time": 8.792508946731687} +{"Pretrain/Learning Rate": 9.589455977498385e-08, "Pretrain/Loss": 2.050710439682007, "Pretrain/Loss (Raw)": 2.224285840988159, "Pretrain/Step": 9279, "Pretrain/Step Time": 8.791431734338403} +{"Pretrain/Learning Rate": 9.515310273662814e-08, "Pretrain/Loss": 2.0479114055633545, "Pretrain/Loss (Raw)": 1.9130879640579224, "Pretrain/Step": 9280, "Pretrain/Step Time": 8.791341457515955} +{"Pretrain/Learning Rate": 9.441451784256706e-08, "Pretrain/Loss": 2.0491342544555664, "Pretrain/Loss (Raw)": 2.04164981842041, "Pretrain/Step": 9281, "Pretrain/Step Time": 8.79114243760705} +{"Pretrain/Learning Rate": 9.3678805177988e-08, "Pretrain/Loss": 2.050666093826294, "Pretrain/Loss (Raw)": 2.0898022651672363, "Pretrain/Step": 9282, "Pretrain/Step Time": 8.793486714363098} +{"Pretrain/Learning Rate": 9.294596482772866e-08, "Pretrain/Loss": 2.050116539001465, "Pretrain/Loss (Raw)": 2.031219244003296, "Pretrain/Step": 9283, "Pretrain/Step Time": 8.796547511592507} +{"Pretrain/Learning Rate": 9.221599687630755e-08, "Pretrain/Loss": 2.0485188961029053, "Pretrain/Loss (Raw)": 1.948743224143982, "Pretrain/Step": 9284, "Pretrain/Step Time": 8.798501048237085} +{"Pretrain/Learning Rate": 9.148890140790733e-08, "Pretrain/Loss": 2.047999382019043, "Pretrain/Loss (Raw)": 1.9898498058319092, "Pretrain/Step": 9285, "Pretrain/Step Time": 8.798506485298276} +{"Pretrain/Learning Rate": 9.076467850638037e-08, "Pretrain/Loss": 2.0464634895324707, "Pretrain/Loss (Raw)": 1.8547070026397705, "Pretrain/Step": 9286, "Pretrain/Step Time": 8.795373138040304} +{"Pretrain/Learning Rate": 9.004332825524597e-08, "Pretrain/Loss": 2.046072483062744, "Pretrain/Loss (Raw)": 1.953128695487976, "Pretrain/Step": 9287, "Pretrain/Step Time": 8.793631251901388} +{"Pretrain/Learning Rate": 8.932485073769592e-08, "Pretrain/Loss": 2.0440287590026855, "Pretrain/Loss (Raw)": 1.9876145124435425, "Pretrain/Step": 9288, "Pretrain/Step Time": 8.796205999329686} +{"Pretrain/Learning Rate": 8.860924603658338e-08, "Pretrain/Loss": 2.043600559234619, "Pretrain/Loss (Raw)": 2.1220338344573975, "Pretrain/Step": 9289, "Pretrain/Step Time": 8.79474264383316} +{"Pretrain/Learning Rate": 8.789651423444234e-08, "Pretrain/Loss": 2.0432748794555664, "Pretrain/Loss (Raw)": 1.97464120388031, "Pretrain/Step": 9290, "Pretrain/Step Time": 8.794036341831088} +{"Pretrain/Learning Rate": 8.718665541346261e-08, "Pretrain/Loss": 2.0429887771606445, "Pretrain/Loss (Raw)": 1.9255638122558594, "Pretrain/Step": 9291, "Pretrain/Step Time": 8.79630895331502} +{"Pretrain/Learning Rate": 8.647966965551202e-08, "Pretrain/Loss": 2.0417656898498535, "Pretrain/Loss (Raw)": 2.0078890323638916, "Pretrain/Step": 9292, "Pretrain/Step Time": 8.798179449513555} +{"Pretrain/Learning Rate": 8.577555704212259e-08, "Pretrain/Loss": 2.0412750244140625, "Pretrain/Loss (Raw)": 2.0428638458251953, "Pretrain/Step": 9293, "Pretrain/Step Time": 8.794522508978844} +{"Pretrain/Learning Rate": 8.507431765449603e-08, "Pretrain/Loss": 2.032872438430786, "Pretrain/Loss (Raw)": 1.1748933792114258, "Pretrain/Step": 9294, "Pretrain/Step Time": 8.790031293407083} +{"Pretrain/Learning Rate": 8.437595157350098e-08, "Pretrain/Loss": 2.032148599624634, "Pretrain/Loss (Raw)": 1.9642682075500488, "Pretrain/Step": 9295, "Pretrain/Step Time": 8.790620109066367} +{"Pretrain/Learning Rate": 8.368045887967858e-08, "Pretrain/Loss": 2.030193328857422, "Pretrain/Loss (Raw)": 1.8968549966812134, "Pretrain/Step": 9296, "Pretrain/Step Time": 8.787976080551744} +{"Pretrain/Learning Rate": 8.298783965323409e-08, "Pretrain/Loss": 2.0327765941619873, "Pretrain/Loss (Raw)": 2.3088324069976807, "Pretrain/Step": 9297, "Pretrain/Step Time": 8.783720415085554} +{"Pretrain/Learning Rate": 8.22980939740453e-08, "Pretrain/Loss": 2.0341978073120117, "Pretrain/Loss (Raw)": 2.073364496231079, "Pretrain/Step": 9298, "Pretrain/Step Time": 8.78096086345613} +{"Pretrain/Learning Rate": 8.161122192165693e-08, "Pretrain/Loss": 2.032602548599243, "Pretrain/Loss (Raw)": 1.833174705505371, "Pretrain/Step": 9299, "Pretrain/Step Time": 8.785735616460443} +{"Pretrain/Learning Rate": 8.092722357528059e-08, "Pretrain/Loss": 2.0326755046844482, "Pretrain/Loss (Raw)": 2.1421916484832764, "Pretrain/Step": 9300, "Pretrain/Step Time": 8.783387256786227} +{"Pretrain/Learning Rate": 8.024609901380042e-08, "Pretrain/Loss": 2.0306055545806885, "Pretrain/Loss (Raw)": 1.818334937095642, "Pretrain/Step": 9301, "Pretrain/Step Time": 8.78686260804534} +{"Pretrain/Learning Rate": 7.956784831576469e-08, "Pretrain/Loss": 2.0298237800598145, "Pretrain/Loss (Raw)": 2.075991630554199, "Pretrain/Step": 9302, "Pretrain/Step Time": 8.788431126624346} +{"Pretrain/Learning Rate": 7.889247155939417e-08, "Pretrain/Loss": 2.029632091522217, "Pretrain/Loss (Raw)": 2.1384291648864746, "Pretrain/Step": 9303, "Pretrain/Step Time": 8.790735442191362} +{"Pretrain/Learning Rate": 7.821996882257654e-08, "Pretrain/Loss": 2.031144142150879, "Pretrain/Loss (Raw)": 2.09323787689209, "Pretrain/Step": 9304, "Pretrain/Step Time": 8.795946184545755} +{"Pretrain/Learning Rate": 7.755034018286644e-08, "Pretrain/Loss": 2.0302343368530273, "Pretrain/Loss (Raw)": 2.0795347690582275, "Pretrain/Step": 9305, "Pretrain/Step Time": 8.795367430895567} +{"Pretrain/Learning Rate": 7.688358571748821e-08, "Pretrain/Loss": 2.0306105613708496, "Pretrain/Loss (Raw)": 1.9320523738861084, "Pretrain/Step": 9306, "Pretrain/Step Time": 8.79221241734922} +{"Pretrain/Learning Rate": 7.621970550333868e-08, "Pretrain/Loss": 2.0273044109344482, "Pretrain/Loss (Raw)": 1.766770362854004, "Pretrain/Step": 9307, "Pretrain/Step Time": 8.793005282059312} +{"Pretrain/Learning Rate": 7.555869961697881e-08, "Pretrain/Loss": 2.02683687210083, "Pretrain/Loss (Raw)": 2.0592029094696045, "Pretrain/Step": 9308, "Pretrain/Step Time": 8.792907362803817} +{"Pretrain/Learning Rate": 7.490056813463375e-08, "Pretrain/Loss": 2.025364398956299, "Pretrain/Loss (Raw)": 1.9893149137496948, "Pretrain/Step": 9309, "Pretrain/Step Time": 8.790640892460942} +{"Pretrain/Learning Rate": 7.424531113220945e-08, "Pretrain/Loss": 2.0242152214050293, "Pretrain/Loss (Raw)": 1.9812525510787964, "Pretrain/Step": 9310, "Pretrain/Step Time": 8.7903744392097} +{"Pretrain/Learning Rate": 7.359292868526769e-08, "Pretrain/Loss": 2.0240135192871094, "Pretrain/Loss (Raw)": 1.969473123550415, "Pretrain/Step": 9311, "Pretrain/Step Time": 8.792692005634308} +{"Pretrain/Learning Rate": 7.294342086904827e-08, "Pretrain/Loss": 2.0237696170806885, "Pretrain/Loss (Raw)": 2.045681953430176, "Pretrain/Step": 9312, "Pretrain/Step Time": 8.803042216226459} +{"Pretrain/Learning Rate": 7.229678775845238e-08, "Pretrain/Loss": 2.0241682529449463, "Pretrain/Loss (Raw)": 2.1572296619415283, "Pretrain/Step": 9313, "Pretrain/Step Time": 8.802084421738982} +{"Pretrain/Learning Rate": 7.165302942805374e-08, "Pretrain/Loss": 2.024806022644043, "Pretrain/Loss (Raw)": 2.1177070140838623, "Pretrain/Step": 9314, "Pretrain/Step Time": 8.798120703548193} +{"Pretrain/Learning Rate": 7.101214595209571e-08, "Pretrain/Loss": 2.0270862579345703, "Pretrain/Loss (Raw)": 2.0624654293060303, "Pretrain/Step": 9315, "Pretrain/Step Time": 8.80210068449378} +{"Pretrain/Learning Rate": 7.037413740448306e-08, "Pretrain/Loss": 2.029026985168457, "Pretrain/Loss (Raw)": 2.307302713394165, "Pretrain/Step": 9316, "Pretrain/Step Time": 8.79799641855061} +{"Pretrain/Learning Rate": 6.973900385880138e-08, "Pretrain/Loss": 2.0284485816955566, "Pretrain/Loss (Raw)": 1.9039697647094727, "Pretrain/Step": 9317, "Pretrain/Step Time": 8.797689758241177} +{"Pretrain/Learning Rate": 6.910674538828931e-08, "Pretrain/Loss": 2.029348373413086, "Pretrain/Loss (Raw)": 2.050372362136841, "Pretrain/Step": 9318, "Pretrain/Step Time": 8.78878545947373} +{"Pretrain/Learning Rate": 6.847736206586908e-08, "Pretrain/Loss": 2.028346538543701, "Pretrain/Loss (Raw)": 1.743330955505371, "Pretrain/Step": 9319, "Pretrain/Step Time": 8.797907808795571} +{"Pretrain/Learning Rate": 6.785085396411872e-08, "Pretrain/Loss": 2.0298655033111572, "Pretrain/Loss (Raw)": 2.2335433959960938, "Pretrain/Step": 9320, "Pretrain/Step Time": 8.795043930411339} +{"Pretrain/Learning Rate": 6.722722115529156e-08, "Pretrain/Loss": 2.0300803184509277, "Pretrain/Loss (Raw)": 2.097541570663452, "Pretrain/Step": 9321, "Pretrain/Step Time": 8.795723296701908} +{"Pretrain/Learning Rate": 6.660646371130785e-08, "Pretrain/Loss": 2.027284622192383, "Pretrain/Loss (Raw)": 2.0889530181884766, "Pretrain/Step": 9322, "Pretrain/Step Time": 8.80096123367548} +{"Pretrain/Learning Rate": 6.598858170375755e-08, "Pretrain/Loss": 2.025195360183716, "Pretrain/Loss (Raw)": 2.0704734325408936, "Pretrain/Step": 9323, "Pretrain/Step Time": 8.800315916538239} +{"Pretrain/Learning Rate": 6.537357520389753e-08, "Pretrain/Loss": 2.026669502258301, "Pretrain/Loss (Raw)": 1.9339460134506226, "Pretrain/Step": 9324, "Pretrain/Step Time": 8.79750949703157} +{"Pretrain/Learning Rate": 6.476144428265163e-08, "Pretrain/Loss": 2.0254416465759277, "Pretrain/Loss (Raw)": 1.8361178636550903, "Pretrain/Step": 9325, "Pretrain/Step Time": 8.80227761156857} +{"Pretrain/Learning Rate": 6.415218901061614e-08, "Pretrain/Loss": 2.0264780521392822, "Pretrain/Loss (Raw)": 2.153592586517334, "Pretrain/Step": 9326, "Pretrain/Step Time": 8.797987081110477} +{"Pretrain/Learning Rate": 6.354580945805156e-08, "Pretrain/Loss": 2.026223659515381, "Pretrain/Loss (Raw)": 2.113173484802246, "Pretrain/Step": 9327, "Pretrain/Step Time": 8.79754095338285} +{"Pretrain/Learning Rate": 6.294230569488802e-08, "Pretrain/Loss": 2.0291900634765625, "Pretrain/Loss (Raw)": 2.2282278537750244, "Pretrain/Step": 9328, "Pretrain/Step Time": 8.799785524606705} +{"Pretrain/Learning Rate": 6.234167779072542e-08, "Pretrain/Loss": 2.033428907394409, "Pretrain/Loss (Raw)": 2.4121954441070557, "Pretrain/Step": 9329, "Pretrain/Step Time": 8.800249436870217} +{"Pretrain/Learning Rate": 6.174392581483057e-08, "Pretrain/Loss": 2.0335752964019775, "Pretrain/Loss (Raw)": 2.1814727783203125, "Pretrain/Step": 9330, "Pretrain/Step Time": 8.801420237869024} +{"Pretrain/Learning Rate": 6.114904983613722e-08, "Pretrain/Loss": 2.0325682163238525, "Pretrain/Loss (Raw)": 2.0107834339141846, "Pretrain/Step": 9331, "Pretrain/Step Time": 8.804578324779868} +{"Pretrain/Learning Rate": 6.055704992325162e-08, "Pretrain/Loss": 2.0325095653533936, "Pretrain/Loss (Raw)": 1.898471474647522, "Pretrain/Step": 9332, "Pretrain/Step Time": 8.800297189503908} +{"Pretrain/Learning Rate": 5.99679261444469e-08, "Pretrain/Loss": 2.0331718921661377, "Pretrain/Loss (Raw)": 2.1054630279541016, "Pretrain/Step": 9333, "Pretrain/Step Time": 8.811408426612616} +{"Pretrain/Learning Rate": 5.938167856766319e-08, "Pretrain/Loss": 2.0366969108581543, "Pretrain/Loss (Raw)": 2.4256181716918945, "Pretrain/Step": 9334, "Pretrain/Step Time": 8.80655644647777} +{"Pretrain/Learning Rate": 5.87983072605075e-08, "Pretrain/Loss": 2.0381102561950684, "Pretrain/Loss (Raw)": 2.146512985229492, "Pretrain/Step": 9335, "Pretrain/Step Time": 8.805745473131537} +{"Pretrain/Learning Rate": 5.821781229025658e-08, "Pretrain/Loss": 2.0398130416870117, "Pretrain/Loss (Raw)": 2.186250686645508, "Pretrain/Step": 9336, "Pretrain/Step Time": 8.805758832022548} +{"Pretrain/Learning Rate": 5.764019372385687e-08, "Pretrain/Loss": 2.0412614345550537, "Pretrain/Loss (Raw)": 2.1497609615325928, "Pretrain/Step": 9337, "Pretrain/Step Time": 8.803712068125606} +{"Pretrain/Learning Rate": 5.706545162792454e-08, "Pretrain/Loss": 2.0418813228607178, "Pretrain/Loss (Raw)": 2.1098854541778564, "Pretrain/Step": 9338, "Pretrain/Step Time": 8.800726408138871} +{"Pretrain/Learning Rate": 5.649358606873989e-08, "Pretrain/Loss": 2.042057752609253, "Pretrain/Loss (Raw)": 2.032769203186035, "Pretrain/Step": 9339, "Pretrain/Step Time": 8.804068885743618} +{"Pretrain/Learning Rate": 5.5924597112250176e-08, "Pretrain/Loss": 2.040971279144287, "Pretrain/Loss (Raw)": 2.036407709121704, "Pretrain/Step": 9340, "Pretrain/Step Time": 8.786918146535754} +{"Pretrain/Learning Rate": 5.5358484824077905e-08, "Pretrain/Loss": 2.0395283699035645, "Pretrain/Loss (Raw)": 1.989628791809082, "Pretrain/Step": 9341, "Pretrain/Step Time": 8.799028780311346} +{"Pretrain/Learning Rate": 5.479524926950696e-08, "Pretrain/Loss": 2.042903184890747, "Pretrain/Loss (Raw)": 2.203965187072754, "Pretrain/Step": 9342, "Pretrain/Step Time": 8.797177197411656} +{"Pretrain/Learning Rate": 5.4234890513490954e-08, "Pretrain/Loss": 2.0449819564819336, "Pretrain/Loss (Raw)": 2.1317288875579834, "Pretrain/Step": 9343, "Pretrain/Step Time": 8.795829929411411} +{"Pretrain/Learning Rate": 5.367740862065873e-08, "Pretrain/Loss": 2.0449137687683105, "Pretrain/Loss (Raw)": 2.087317705154419, "Pretrain/Step": 9344, "Pretrain/Step Time": 8.796133168041706} +{"Pretrain/Learning Rate": 5.3122803655300533e-08, "Pretrain/Loss": 2.0456161499023438, "Pretrain/Loss (Raw)": 2.003650426864624, "Pretrain/Step": 9345, "Pretrain/Step Time": 8.794183066114783} +{"Pretrain/Learning Rate": 5.257107568137076e-08, "Pretrain/Loss": 2.0431363582611084, "Pretrain/Loss (Raw)": 1.834668755531311, "Pretrain/Step": 9346, "Pretrain/Step Time": 8.794347021728754} +{"Pretrain/Learning Rate": 5.2022224762501845e-08, "Pretrain/Loss": 2.0424540042877197, "Pretrain/Loss (Raw)": 1.9361369609832764, "Pretrain/Step": 9347, "Pretrain/Step Time": 8.794826570898294} +{"Pretrain/Learning Rate": 5.147625096199038e-08, "Pretrain/Loss": 2.043276309967041, "Pretrain/Loss (Raw)": 2.0131123065948486, "Pretrain/Step": 9348, "Pretrain/Step Time": 8.793339513242245} +{"Pretrain/Learning Rate": 5.0933154342797105e-08, "Pretrain/Loss": 2.0433664321899414, "Pretrain/Loss (Raw)": 2.069765329360962, "Pretrain/Step": 9349, "Pretrain/Step Time": 8.79336910136044} +{"Pretrain/Learning Rate": 5.039293496755526e-08, "Pretrain/Loss": 2.0414395332336426, "Pretrain/Loss (Raw)": 1.8711391687393188, "Pretrain/Step": 9350, "Pretrain/Step Time": 8.790590301156044} +{"Pretrain/Learning Rate": 4.9855592898567784e-08, "Pretrain/Loss": 2.0409927368164062, "Pretrain/Loss (Raw)": 2.0992205142974854, "Pretrain/Step": 9351, "Pretrain/Step Time": 8.790665466338396} +{"Pretrain/Learning Rate": 4.9321128197804543e-08, "Pretrain/Loss": 2.041628360748291, "Pretrain/Loss (Raw)": 2.195466995239258, "Pretrain/Step": 9352, "Pretrain/Step Time": 8.790823360905051} +{"Pretrain/Learning Rate": 4.8789540926896806e-08, "Pretrain/Loss": 2.043515682220459, "Pretrain/Loss (Raw)": 2.1484885215759277, "Pretrain/Step": 9353, "Pretrain/Step Time": 8.796646354719996} +{"Pretrain/Learning Rate": 4.826083114715385e-08, "Pretrain/Loss": 2.0423974990844727, "Pretrain/Loss (Raw)": 1.9206758737564087, "Pretrain/Step": 9354, "Pretrain/Step Time": 8.79454574175179} +{"Pretrain/Learning Rate": 4.7734998919549135e-08, "Pretrain/Loss": 2.0407588481903076, "Pretrain/Loss (Raw)": 1.9245063066482544, "Pretrain/Step": 9355, "Pretrain/Step Time": 8.791360668838024} +{"Pretrain/Learning Rate": 4.7212044304723035e-08, "Pretrain/Loss": 2.0415196418762207, "Pretrain/Loss (Raw)": 2.1623117923736572, "Pretrain/Step": 9356, "Pretrain/Step Time": 8.795922623947263} +{"Pretrain/Learning Rate": 4.6691967362985645e-08, "Pretrain/Loss": 2.0416338443756104, "Pretrain/Loss (Raw)": 2.1252310276031494, "Pretrain/Step": 9357, "Pretrain/Step Time": 8.794168012216687} +{"Pretrain/Learning Rate": 4.6174768154316764e-08, "Pretrain/Loss": 2.0403151512145996, "Pretrain/Loss (Raw)": 1.9738038778305054, "Pretrain/Step": 9358, "Pretrain/Step Time": 8.794194664806128} +{"Pretrain/Learning Rate": 4.566044673835479e-08, "Pretrain/Loss": 2.042149305343628, "Pretrain/Loss (Raw)": 2.085249185562134, "Pretrain/Step": 9359, "Pretrain/Step Time": 8.796982793137431} +{"Pretrain/Learning Rate": 4.514900317442172e-08, "Pretrain/Loss": 2.0409834384918213, "Pretrain/Loss (Raw)": 2.1295628547668457, "Pretrain/Step": 9360, "Pretrain/Step Time": 8.79590293392539} +{"Pretrain/Learning Rate": 4.464043752149816e-08, "Pretrain/Loss": 2.0399155616760254, "Pretrain/Loss (Raw)": 2.0591418743133545, "Pretrain/Step": 9361, "Pretrain/Step Time": 8.796593245118856} +{"Pretrain/Learning Rate": 4.413474983823163e-08, "Pretrain/Loss": 2.0395734310150146, "Pretrain/Loss (Raw)": 2.060598611831665, "Pretrain/Step": 9362, "Pretrain/Step Time": 8.796969428658485} +{"Pretrain/Learning Rate": 4.363194018293937e-08, "Pretrain/Loss": 2.040689468383789, "Pretrain/Loss (Raw)": 2.005445957183838, "Pretrain/Step": 9363, "Pretrain/Step Time": 8.795021193102002} +{"Pretrain/Learning Rate": 4.313200861361388e-08, "Pretrain/Loss": 2.04060697555542, "Pretrain/Loss (Raw)": 2.05141282081604, "Pretrain/Step": 9364, "Pretrain/Step Time": 8.798824483528733} +{"Pretrain/Learning Rate": 4.2634955187900727e-08, "Pretrain/Loss": 2.0405778884887695, "Pretrain/Loss (Raw)": 2.1708285808563232, "Pretrain/Step": 9365, "Pretrain/Step Time": 8.79158529639244} +{"Pretrain/Learning Rate": 4.2140779963131815e-08, "Pretrain/Loss": 2.0414481163024902, "Pretrain/Loss (Raw)": 2.119551181793213, "Pretrain/Step": 9366, "Pretrain/Step Time": 8.792539460584521} +{"Pretrain/Learning Rate": 4.164948299629212e-08, "Pretrain/Loss": 2.041893243789673, "Pretrain/Loss (Raw)": 1.9721441268920898, "Pretrain/Step": 9367, "Pretrain/Step Time": 8.791716787964106} +{"Pretrain/Learning Rate": 4.1161064344041875e-08, "Pretrain/Loss": 2.040365695953369, "Pretrain/Loss (Raw)": 2.045534610748291, "Pretrain/Step": 9368, "Pretrain/Step Time": 8.799837917089462} +{"Pretrain/Learning Rate": 4.0675524062708245e-08, "Pretrain/Loss": 2.0393967628479004, "Pretrain/Loss (Raw)": 1.9055395126342773, "Pretrain/Step": 9369, "Pretrain/Step Time": 8.789268020540476} +{"Pretrain/Learning Rate": 4.019286220828255e-08, "Pretrain/Loss": 2.0379257202148438, "Pretrain/Loss (Raw)": 1.9676331281661987, "Pretrain/Step": 9370, "Pretrain/Step Time": 8.789494257420301} +{"Pretrain/Learning Rate": 3.971307883643416e-08, "Pretrain/Loss": 2.037754774093628, "Pretrain/Loss (Raw)": 2.062908887863159, "Pretrain/Step": 9371, "Pretrain/Step Time": 8.78852016478777} +{"Pretrain/Learning Rate": 3.923617400248825e-08, "Pretrain/Loss": 2.038820505142212, "Pretrain/Loss (Raw)": 2.1740896701812744, "Pretrain/Step": 9372, "Pretrain/Step Time": 8.782958595082164} +{"Pretrain/Learning Rate": 3.876214776144527e-08, "Pretrain/Loss": 2.039689064025879, "Pretrain/Loss (Raw)": 2.12155818939209, "Pretrain/Step": 9373, "Pretrain/Step Time": 8.779507797211409} +{"Pretrain/Learning Rate": 3.8291000167972604e-08, "Pretrain/Loss": 2.0384137630462646, "Pretrain/Loss (Raw)": 1.9172842502593994, "Pretrain/Step": 9374, "Pretrain/Step Time": 8.779905289411545} +{"Pretrain/Learning Rate": 3.782273127640734e-08, "Pretrain/Loss": 2.037843704223633, "Pretrain/Loss (Raw)": 2.081362247467041, "Pretrain/Step": 9375, "Pretrain/Step Time": 8.792481541633606} +{"Pretrain/Learning Rate": 3.735734114074796e-08, "Pretrain/Loss": 2.036865711212158, "Pretrain/Loss (Raw)": 1.8969850540161133, "Pretrain/Step": 9376, "Pretrain/Step Time": 8.789244219660759} +{"Pretrain/Learning Rate": 3.6894829814668185e-08, "Pretrain/Loss": 2.038381576538086, "Pretrain/Loss (Raw)": 1.9731576442718506, "Pretrain/Step": 9377, "Pretrain/Step Time": 8.786974409595132} +{"Pretrain/Learning Rate": 3.643519735150869e-08, "Pretrain/Loss": 2.0396671295166016, "Pretrain/Loss (Raw)": 2.1601974964141846, "Pretrain/Step": 9378, "Pretrain/Step Time": 8.786343874409795} +{"Pretrain/Learning Rate": 3.5978443804274286e-08, "Pretrain/Loss": 2.0377464294433594, "Pretrain/Loss (Raw)": 1.7241865396499634, "Pretrain/Step": 9379, "Pretrain/Step Time": 8.793042419478297} +{"Pretrain/Learning Rate": 3.552456922563674e-08, "Pretrain/Loss": 2.034921646118164, "Pretrain/Loss (Raw)": 1.8294264078140259, "Pretrain/Step": 9380, "Pretrain/Step Time": 8.789154035970569} +{"Pretrain/Learning Rate": 3.5073573667945836e-08, "Pretrain/Loss": 2.0335092544555664, "Pretrain/Loss (Raw)": 2.0000874996185303, "Pretrain/Step": 9381, "Pretrain/Step Time": 8.789225729182363} +{"Pretrain/Learning Rate": 3.46254571832072e-08, "Pretrain/Loss": 2.0355043411254883, "Pretrain/Loss (Raw)": 1.9150958061218262, "Pretrain/Step": 9382, "Pretrain/Step Time": 8.792125556617975} +{"Pretrain/Learning Rate": 3.418021982310171e-08, "Pretrain/Loss": 2.037824869155884, "Pretrain/Loss (Raw)": 2.1981277465820312, "Pretrain/Step": 9383, "Pretrain/Step Time": 8.792164778336883} +{"Pretrain/Learning Rate": 3.3737861638977184e-08, "Pretrain/Loss": 2.036999225616455, "Pretrain/Loss (Raw)": 1.824367880821228, "Pretrain/Step": 9384, "Pretrain/Step Time": 8.793538501486182} +{"Pretrain/Learning Rate": 3.3298382681845595e-08, "Pretrain/Loss": 2.0373692512512207, "Pretrain/Loss (Raw)": 2.189228057861328, "Pretrain/Step": 9385, "Pretrain/Step Time": 8.791072610765696} +{"Pretrain/Learning Rate": 3.28617830023914e-08, "Pretrain/Loss": 2.0363993644714355, "Pretrain/Loss (Raw)": 1.9217031002044678, "Pretrain/Step": 9386, "Pretrain/Step Time": 8.79087795689702} +{"Pretrain/Learning Rate": 3.242806265096876e-08, "Pretrain/Loss": 2.035764217376709, "Pretrain/Loss (Raw)": 1.9349536895751953, "Pretrain/Step": 9387, "Pretrain/Step Time": 8.790133710950613} +{"Pretrain/Learning Rate": 3.199722167759045e-08, "Pretrain/Loss": 2.0345847606658936, "Pretrain/Loss (Raw)": 1.9703609943389893, "Pretrain/Step": 9388, "Pretrain/Step Time": 8.788274483755231} +{"Pretrain/Learning Rate": 3.15692601319445e-08, "Pretrain/Loss": 2.0311901569366455, "Pretrain/Loss (Raw)": 1.860519289970398, "Pretrain/Step": 9389, "Pretrain/Step Time": 8.798011975362897} +{"Pretrain/Learning Rate": 3.114417806338865e-08, "Pretrain/Loss": 2.03143048286438, "Pretrain/Loss (Raw)": 1.9987437725067139, "Pretrain/Step": 9390, "Pretrain/Step Time": 8.782040974125266} +{"Pretrain/Learning Rate": 3.072197552094203e-08, "Pretrain/Loss": 2.0347251892089844, "Pretrain/Loss (Raw)": 2.3981926441192627, "Pretrain/Step": 9391, "Pretrain/Step Time": 8.78855549544096} +{"Pretrain/Learning Rate": 3.0302652553296226e-08, "Pretrain/Loss": 2.0332257747650146, "Pretrain/Loss (Raw)": 1.812789797782898, "Pretrain/Step": 9392, "Pretrain/Step Time": 8.79339324682951} +{"Pretrain/Learning Rate": 2.98862092088098e-08, "Pretrain/Loss": 2.035731077194214, "Pretrain/Loss (Raw)": 2.026125192642212, "Pretrain/Step": 9393, "Pretrain/Step Time": 8.7905607316643} +{"Pretrain/Learning Rate": 2.947264553551099e-08, "Pretrain/Loss": 2.035125494003296, "Pretrain/Loss (Raw)": 2.1098155975341797, "Pretrain/Step": 9394, "Pretrain/Step Time": 8.787973023951054} +{"Pretrain/Learning Rate": 2.9061961581089424e-08, "Pretrain/Loss": 2.0343587398529053, "Pretrain/Loss (Raw)": 1.9620012044906616, "Pretrain/Step": 9395, "Pretrain/Step Time": 8.791459321975708} +{"Pretrain/Learning Rate": 2.8654157392909997e-08, "Pretrain/Loss": 2.0354087352752686, "Pretrain/Loss (Raw)": 2.0884737968444824, "Pretrain/Step": 9396, "Pretrain/Step Time": 8.793651724234223} +{"Pretrain/Learning Rate": 2.824923301800175e-08, "Pretrain/Loss": 2.035370111465454, "Pretrain/Loss (Raw)": 2.108165740966797, "Pretrain/Step": 9397, "Pretrain/Step Time": 8.79302672855556} +{"Pretrain/Learning Rate": 2.7847188503063447e-08, "Pretrain/Loss": 2.034803867340088, "Pretrain/Loss (Raw)": 1.9741865396499634, "Pretrain/Step": 9398, "Pretrain/Step Time": 8.794193817302585} +{"Pretrain/Learning Rate": 2.7448023894457997e-08, "Pretrain/Loss": 2.0362370014190674, "Pretrain/Loss (Raw)": 2.0990500450134277, "Pretrain/Step": 9399, "Pretrain/Step Time": 8.794625481590629} +{"Pretrain/Learning Rate": 2.7051739238223572e-08, "Pretrain/Loss": 2.0340123176574707, "Pretrain/Loss (Raw)": 1.9347894191741943, "Pretrain/Step": 9400, "Pretrain/Step Time": 8.793849548324943} +{"Pretrain/Learning Rate": 2.6658334580056954e-08, "Pretrain/Loss": 2.035262107849121, "Pretrain/Loss (Raw)": 2.129246473312378, "Pretrain/Step": 9401, "Pretrain/Step Time": 8.79173251800239} +{"Pretrain/Learning Rate": 2.626780996533018e-08, "Pretrain/Loss": 2.0332117080688477, "Pretrain/Loss (Raw)": 1.9886608123779297, "Pretrain/Step": 9402, "Pretrain/Step Time": 8.791595568880439} +{"Pretrain/Learning Rate": 2.588016543907945e-08, "Pretrain/Loss": 2.034189224243164, "Pretrain/Loss (Raw)": 2.1456775665283203, "Pretrain/Step": 9403, "Pretrain/Step Time": 8.78425076417625} +{"Pretrain/Learning Rate": 2.549540104601067e-08, "Pretrain/Loss": 2.0337185859680176, "Pretrain/Loss (Raw)": 2.104250907897949, "Pretrain/Step": 9404, "Pretrain/Step Time": 8.79448546282947} +{"Pretrain/Learning Rate": 2.5113516830493898e-08, "Pretrain/Loss": 2.0323727130889893, "Pretrain/Loss (Raw)": 1.8642724752426147, "Pretrain/Step": 9405, "Pretrain/Step Time": 8.789406657218933} +{"Pretrain/Learning Rate": 2.4734512836574465e-08, "Pretrain/Loss": 2.0303969383239746, "Pretrain/Loss (Raw)": 1.8838578462600708, "Pretrain/Step": 9406, "Pretrain/Step Time": 8.791261866688728} +{"Pretrain/Learning Rate": 2.4358389107956292e-08, "Pretrain/Loss": 2.0289716720581055, "Pretrain/Loss (Raw)": 2.0418050289154053, "Pretrain/Step": 9407, "Pretrain/Step Time": 8.793687615543604} +{"Pretrain/Learning Rate": 2.3985145688018575e-08, "Pretrain/Loss": 2.0281176567077637, "Pretrain/Loss (Raw)": 1.8038105964660645, "Pretrain/Step": 9408, "Pretrain/Step Time": 8.796645993366838} +{"Pretrain/Learning Rate": 2.361478261980743e-08, "Pretrain/Loss": 2.027256965637207, "Pretrain/Loss (Raw)": 1.9314316511154175, "Pretrain/Step": 9409, "Pretrain/Step Time": 8.793599491938949} +{"Pretrain/Learning Rate": 2.324729994602759e-08, "Pretrain/Loss": 2.028085470199585, "Pretrain/Loss (Raw)": 2.195873975753784, "Pretrain/Step": 9410, "Pretrain/Step Time": 8.789969036355615} +{"Pretrain/Learning Rate": 2.288269770906737e-08, "Pretrain/Loss": 2.028919219970703, "Pretrain/Loss (Raw)": 2.1379523277282715, "Pretrain/Step": 9411, "Pretrain/Step Time": 8.790492905303836} +{"Pretrain/Learning Rate": 2.2520975950968137e-08, "Pretrain/Loss": 2.0300235748291016, "Pretrain/Loss (Raw)": 2.090092658996582, "Pretrain/Step": 9412, "Pretrain/Step Time": 8.788772692903876} +{"Pretrain/Learning Rate": 2.2162134713446524e-08, "Pretrain/Loss": 2.030677318572998, "Pretrain/Loss (Raw)": 2.0735397338867188, "Pretrain/Step": 9413, "Pretrain/Step Time": 8.791059255599976} +{"Pretrain/Learning Rate": 2.1806174037888872e-08, "Pretrain/Loss": 2.030956983566284, "Pretrain/Loss (Raw)": 1.8904985189437866, "Pretrain/Step": 9414, "Pretrain/Step Time": 8.795757248997688} +{"Pretrain/Learning Rate": 2.1453093965342896e-08, "Pretrain/Loss": 2.030852794647217, "Pretrain/Loss (Raw)": 1.9397966861724854, "Pretrain/Step": 9415, "Pretrain/Step Time": 8.796709010377526} +{"Pretrain/Learning Rate": 2.110289453653158e-08, "Pretrain/Loss": 2.032135248184204, "Pretrain/Loss (Raw)": 2.1517536640167236, "Pretrain/Step": 9416, "Pretrain/Step Time": 8.792898071929812} +{"Pretrain/Learning Rate": 2.0755575791836513e-08, "Pretrain/Loss": 2.0321927070617676, "Pretrain/Loss (Raw)": 2.129412889480591, "Pretrain/Step": 9417, "Pretrain/Step Time": 8.792735008522868} +{"Pretrain/Learning Rate": 2.041113777131731e-08, "Pretrain/Loss": 2.0349249839782715, "Pretrain/Loss (Raw)": 2.324370861053467, "Pretrain/Step": 9418, "Pretrain/Step Time": 8.795803423970938} +{"Pretrain/Learning Rate": 2.0069580514689435e-08, "Pretrain/Loss": 2.034999132156372, "Pretrain/Loss (Raw)": 1.9350405931472778, "Pretrain/Step": 9419, "Pretrain/Step Time": 8.791714671999216} +{"Pretrain/Learning Rate": 1.9730904061349143e-08, "Pretrain/Loss": 2.034907817840576, "Pretrain/Loss (Raw)": 1.9962084293365479, "Pretrain/Step": 9420, "Pretrain/Step Time": 8.790233440697193} +{"Pretrain/Learning Rate": 1.939510845035131e-08, "Pretrain/Loss": 2.0358898639678955, "Pretrain/Loss (Raw)": 2.168553590774536, "Pretrain/Step": 9421, "Pretrain/Step Time": 8.797000411897898} +{"Pretrain/Learning Rate": 1.9062193720423284e-08, "Pretrain/Loss": 2.043107032775879, "Pretrain/Loss (Raw)": 2.098710775375366, "Pretrain/Step": 9422, "Pretrain/Step Time": 8.799768649041653} +{"Pretrain/Learning Rate": 1.8732159909956583e-08, "Pretrain/Loss": 2.0431394577026367, "Pretrain/Loss (Raw)": 1.9684334993362427, "Pretrain/Step": 9423, "Pretrain/Step Time": 8.796253399923444} +{"Pretrain/Learning Rate": 1.8405007057012425e-08, "Pretrain/Loss": 2.043174982070923, "Pretrain/Loss (Raw)": 1.9013665914535522, "Pretrain/Step": 9424, "Pretrain/Step Time": 8.799021849408746} +{"Pretrain/Learning Rate": 1.8080735199318966e-08, "Pretrain/Loss": 2.0407700538635254, "Pretrain/Loss (Raw)": 2.0009918212890625, "Pretrain/Step": 9425, "Pretrain/Step Time": 8.805151510983706} +{"Pretrain/Learning Rate": 1.775934437427684e-08, "Pretrain/Loss": 2.041100263595581, "Pretrain/Loss (Raw)": 2.1156277656555176, "Pretrain/Step": 9426, "Pretrain/Step Time": 8.806188579648733} +{"Pretrain/Learning Rate": 1.7440834618945302e-08, "Pretrain/Loss": 2.0437731742858887, "Pretrain/Loss (Raw)": 2.175347328186035, "Pretrain/Step": 9427, "Pretrain/Step Time": 8.804935108870268} +{"Pretrain/Learning Rate": 1.7125205970058843e-08, "Pretrain/Loss": 2.042600154876709, "Pretrain/Loss (Raw)": 1.9920262098312378, "Pretrain/Step": 9428, "Pretrain/Step Time": 8.810660948976874} +{"Pretrain/Learning Rate": 1.681245846401336e-08, "Pretrain/Loss": 2.045172929763794, "Pretrain/Loss (Raw)": 2.1476621627807617, "Pretrain/Step": 9429, "Pretrain/Step Time": 8.804416397586465} +{"Pretrain/Learning Rate": 1.650259213688554e-08, "Pretrain/Loss": 2.0451455116271973, "Pretrain/Loss (Raw)": 2.0724472999572754, "Pretrain/Step": 9430, "Pretrain/Step Time": 8.804504906758666} +{"Pretrain/Learning Rate": 1.6195607024399593e-08, "Pretrain/Loss": 2.044367790222168, "Pretrain/Loss (Raw)": 2.038905620574951, "Pretrain/Step": 9431, "Pretrain/Step Time": 8.805467270314693} +{"Pretrain/Learning Rate": 1.5891503161968857e-08, "Pretrain/Loss": 2.043663740158081, "Pretrain/Loss (Raw)": 2.0030980110168457, "Pretrain/Step": 9432, "Pretrain/Step Time": 8.804009044542909} +{"Pretrain/Learning Rate": 1.559028058465417e-08, "Pretrain/Loss": 2.041393280029297, "Pretrain/Loss (Raw)": 1.788948655128479, "Pretrain/Step": 9433, "Pretrain/Step Time": 8.803126836195588} +{"Pretrain/Learning Rate": 1.5291939327202742e-08, "Pretrain/Loss": 2.0428895950317383, "Pretrain/Loss (Raw)": 2.123582601547241, "Pretrain/Step": 9434, "Pretrain/Step Time": 8.805060053244233} +{"Pretrain/Learning Rate": 1.499647942401483e-08, "Pretrain/Loss": 2.0456905364990234, "Pretrain/Loss (Raw)": 2.1252682209014893, "Pretrain/Step": 9435, "Pretrain/Step Time": 8.808314917609096} +{"Pretrain/Learning Rate": 1.4703900909165957e-08, "Pretrain/Loss": 2.045454978942871, "Pretrain/Loss (Raw)": 2.0290465354919434, "Pretrain/Step": 9436, "Pretrain/Step Time": 8.804802507162094} +{"Pretrain/Learning Rate": 1.4414203816398574e-08, "Pretrain/Loss": 2.0470852851867676, "Pretrain/Loss (Raw)": 2.1980090141296387, "Pretrain/Step": 9437, "Pretrain/Step Time": 8.805031364783645} +{"Pretrain/Learning Rate": 1.4127388179119294e-08, "Pretrain/Loss": 2.048363208770752, "Pretrain/Loss (Raw)": 2.14483380317688, "Pretrain/Step": 9438, "Pretrain/Step Time": 8.809922058135271} +{"Pretrain/Learning Rate": 1.3843454030409986e-08, "Pretrain/Loss": 2.0493507385253906, "Pretrain/Loss (Raw)": 2.095867395401001, "Pretrain/Step": 9439, "Pretrain/Step Time": 8.812524450942874} +{"Pretrain/Learning Rate": 1.3562401403008352e-08, "Pretrain/Loss": 2.04844331741333, "Pretrain/Loss (Raw)": 1.9294917583465576, "Pretrain/Step": 9440, "Pretrain/Step Time": 8.804840670898557} +{"Pretrain/Learning Rate": 1.3284230329332902e-08, "Pretrain/Loss": 2.0483853816986084, "Pretrain/Loss (Raw)": 2.149855613708496, "Pretrain/Step": 9441, "Pretrain/Step Time": 8.807015728205442} +{"Pretrain/Learning Rate": 1.3008940841460759e-08, "Pretrain/Loss": 2.0481772422790527, "Pretrain/Loss (Raw)": 2.091062068939209, "Pretrain/Step": 9442, "Pretrain/Step Time": 8.806836050003767} +{"Pretrain/Learning Rate": 1.2736532971141523e-08, "Pretrain/Loss": 2.0470006465911865, "Pretrain/Loss (Raw)": 1.9118746519088745, "Pretrain/Step": 9443, "Pretrain/Step Time": 8.805422473698854} +{"Pretrain/Learning Rate": 1.2467006749788956e-08, "Pretrain/Loss": 2.045037269592285, "Pretrain/Loss (Raw)": 2.0559942722320557, "Pretrain/Step": 9444, "Pretrain/Step Time": 8.805215986445546} +{"Pretrain/Learning Rate": 1.2200362208483751e-08, "Pretrain/Loss": 2.0460329055786133, "Pretrain/Loss (Raw)": 2.031388998031616, "Pretrain/Step": 9445, "Pretrain/Step Time": 8.80534683354199} +{"Pretrain/Learning Rate": 1.1936599377981861e-08, "Pretrain/Loss": 2.04551362991333, "Pretrain/Loss (Raw)": 1.983917236328125, "Pretrain/Step": 9446, "Pretrain/Step Time": 8.808256594464183} +{"Pretrain/Learning Rate": 1.1675718288697845e-08, "Pretrain/Loss": 2.044921398162842, "Pretrain/Loss (Raw)": 1.6675342321395874, "Pretrain/Step": 9447, "Pretrain/Step Time": 8.800976276397705} +{"Pretrain/Learning Rate": 1.1417718970718749e-08, "Pretrain/Loss": 2.0425734519958496, "Pretrain/Loss (Raw)": 1.9329859018325806, "Pretrain/Step": 9448, "Pretrain/Step Time": 8.800907600671053} +{"Pretrain/Learning Rate": 1.1162601453798549e-08, "Pretrain/Loss": 2.040989398956299, "Pretrain/Loss (Raw)": 1.8947819471359253, "Pretrain/Step": 9449, "Pretrain/Step Time": 8.801428167149425} +{"Pretrain/Learning Rate": 1.0910365767358155e-08, "Pretrain/Loss": 2.041745185852051, "Pretrain/Loss (Raw)": 2.18570613861084, "Pretrain/Step": 9450, "Pretrain/Step Time": 8.796405740082264} +{"Pretrain/Learning Rate": 1.0661011940488186e-08, "Pretrain/Loss": 2.041144847869873, "Pretrain/Loss (Raw)": 1.993612289428711, "Pretrain/Step": 9451, "Pretrain/Step Time": 8.796755829825997} +{"Pretrain/Learning Rate": 1.0414540001943418e-08, "Pretrain/Loss": 2.042494297027588, "Pretrain/Loss (Raw)": 2.1066958904266357, "Pretrain/Step": 9452, "Pretrain/Step Time": 8.798748197034001} +{"Pretrain/Learning Rate": 1.017094998014556e-08, "Pretrain/Loss": 2.044342279434204, "Pretrain/Loss (Raw)": 2.0726516246795654, "Pretrain/Step": 9453, "Pretrain/Step Time": 8.799470225349069} +{"Pretrain/Learning Rate": 9.93024190319436e-09, "Pretrain/Loss": 2.0432636737823486, "Pretrain/Loss (Raw)": 2.015538454055786, "Pretrain/Step": 9454, "Pretrain/Step Time": 8.799208277836442} +{"Pretrain/Learning Rate": 9.692415798842614e-09, "Pretrain/Loss": 2.043869972229004, "Pretrain/Loss (Raw)": 2.190742254257202, "Pretrain/Step": 9455, "Pretrain/Step Time": 8.800570338964462} +{"Pretrain/Learning Rate": 9.457471694518383e-09, "Pretrain/Loss": 2.0424180030822754, "Pretrain/Loss (Raw)": 2.0423965454101562, "Pretrain/Step": 9456, "Pretrain/Step Time": 8.805658495053649} +{"Pretrain/Learning Rate": 9.225409617319436e-09, "Pretrain/Loss": 2.040530204772949, "Pretrain/Loss (Raw)": 2.1705551147460938, "Pretrain/Step": 9457, "Pretrain/Step Time": 8.799351872876287} +{"Pretrain/Learning Rate": 8.996229594007699e-09, "Pretrain/Loss": 2.040858268737793, "Pretrain/Loss (Raw)": 2.223491907119751, "Pretrain/Step": 9458, "Pretrain/Step Time": 8.80103436857462} +{"Pretrain/Learning Rate": 8.769931651009255e-09, "Pretrain/Loss": 2.0410876274108887, "Pretrain/Loss (Raw)": 2.0401461124420166, "Pretrain/Step": 9459, "Pretrain/Step Time": 8.802211847156286} +{"Pretrain/Learning Rate": 8.546515814425449e-09, "Pretrain/Loss": 2.042381763458252, "Pretrain/Loss (Raw)": 2.0640952587127686, "Pretrain/Step": 9460, "Pretrain/Step Time": 8.803730918094516} +{"Pretrain/Learning Rate": 8.325982110024554e-09, "Pretrain/Loss": 2.0433268547058105, "Pretrain/Loss (Raw)": 2.226426362991333, "Pretrain/Step": 9461, "Pretrain/Step Time": 8.793809475377202} +{"Pretrain/Learning Rate": 8.108330563233458e-09, "Pretrain/Loss": 2.0393881797790527, "Pretrain/Loss (Raw)": 1.9214794635772705, "Pretrain/Step": 9462, "Pretrain/Step Time": 8.79535466618836} +{"Pretrain/Learning Rate": 7.893561199154297e-09, "Pretrain/Loss": 2.039350986480713, "Pretrain/Loss (Raw)": 2.1417267322540283, "Pretrain/Step": 9463, "Pretrain/Step Time": 8.796484800055623} +{"Pretrain/Learning Rate": 7.681674042558928e-09, "Pretrain/Loss": 2.038412570953369, "Pretrain/Loss (Raw)": 2.0661723613739014, "Pretrain/Step": 9464, "Pretrain/Step Time": 8.791580852121115} +{"Pretrain/Learning Rate": 7.472669117877807e-09, "Pretrain/Loss": 2.0399484634399414, "Pretrain/Loss (Raw)": 2.346334934234619, "Pretrain/Step": 9465, "Pretrain/Step Time": 8.794402904808521} +{"Pretrain/Learning Rate": 7.266546449219424e-09, "Pretrain/Loss": 2.037580966949463, "Pretrain/Loss (Raw)": 1.8068522214889526, "Pretrain/Step": 9466, "Pretrain/Step Time": 8.796131495386362} +{"Pretrain/Learning Rate": 7.0633060603508825e-09, "Pretrain/Loss": 2.036391019821167, "Pretrain/Loss (Raw)": 1.8804560899734497, "Pretrain/Step": 9467, "Pretrain/Step Time": 8.798647271469235} +{"Pretrain/Learning Rate": 6.862947974711764e-09, "Pretrain/Loss": 2.037365674972534, "Pretrain/Loss (Raw)": 2.1611757278442383, "Pretrain/Step": 9468, "Pretrain/Step Time": 8.800459379330277} +{"Pretrain/Learning Rate": 6.665472215411361e-09, "Pretrain/Loss": 2.0382566452026367, "Pretrain/Loss (Raw)": 2.103640079498291, "Pretrain/Step": 9469, "Pretrain/Step Time": 8.791970636695623} +{"Pretrain/Learning Rate": 6.470878805220348e-09, "Pretrain/Loss": 2.0367846488952637, "Pretrain/Loss (Raw)": 2.015587329864502, "Pretrain/Step": 9470, "Pretrain/Step Time": 8.79278364032507} +{"Pretrain/Learning Rate": 6.279167766579108e-09, "Pretrain/Loss": 2.034456491470337, "Pretrain/Loss (Raw)": 1.833709955215454, "Pretrain/Step": 9471, "Pretrain/Step Time": 8.79498279467225} +{"Pretrain/Learning Rate": 6.090339121600508e-09, "Pretrain/Loss": 2.0341968536376953, "Pretrain/Loss (Raw)": 2.05409574508667, "Pretrain/Step": 9472, "Pretrain/Step Time": 8.792997544631362} +{"Pretrain/Learning Rate": 5.904392892058796e-09, "Pretrain/Loss": 2.035712957382202, "Pretrain/Loss (Raw)": 2.197680711746216, "Pretrain/Step": 9473, "Pretrain/Step Time": 8.79454799182713} +{"Pretrain/Learning Rate": 5.721329099400707e-09, "Pretrain/Loss": 2.0377893447875977, "Pretrain/Loss (Raw)": 2.1004765033721924, "Pretrain/Step": 9474, "Pretrain/Step Time": 8.80014661885798} +{"Pretrain/Learning Rate": 5.54114776473158e-09, "Pretrain/Loss": 2.0376272201538086, "Pretrain/Loss (Raw)": 1.9153567552566528, "Pretrain/Step": 9475, "Pretrain/Step Time": 8.794608399271965} +{"Pretrain/Learning Rate": 5.363848908837565e-09, "Pretrain/Loss": 2.0380759239196777, "Pretrain/Loss (Raw)": 2.0705580711364746, "Pretrain/Step": 9476, "Pretrain/Step Time": 8.795350482687354} +{"Pretrain/Learning Rate": 5.1894325521634205e-09, "Pretrain/Loss": 2.0371592044830322, "Pretrain/Loss (Raw)": 1.9524186849594116, "Pretrain/Step": 9477, "Pretrain/Step Time": 8.796590274199843} +{"Pretrain/Learning Rate": 5.01789871482361e-09, "Pretrain/Loss": 2.039593458175659, "Pretrain/Loss (Raw)": 2.182734489440918, "Pretrain/Step": 9478, "Pretrain/Step Time": 8.798530470579863} +{"Pretrain/Learning Rate": 4.849247416599534e-09, "Pretrain/Loss": 2.039308547973633, "Pretrain/Loss (Raw)": 2.0627379417419434, "Pretrain/Step": 9479, "Pretrain/Step Time": 8.798508061096072} +{"Pretrain/Learning Rate": 4.683478676939523e-09, "Pretrain/Loss": 2.0369668006896973, "Pretrain/Loss (Raw)": 1.895749807357788, "Pretrain/Step": 9480, "Pretrain/Step Time": 8.798385493457317} +{"Pretrain/Learning Rate": 4.520592514964395e-09, "Pretrain/Loss": 2.035510301589966, "Pretrain/Loss (Raw)": 1.9620428085327148, "Pretrain/Step": 9481, "Pretrain/Step Time": 8.80033976957202} +{"Pretrain/Learning Rate": 4.360588949456345e-09, "Pretrain/Loss": 2.0364885330200195, "Pretrain/Loss (Raw)": 2.045888662338257, "Pretrain/Step": 9482, "Pretrain/Step Time": 8.793078573420644} +{"Pretrain/Learning Rate": 4.203467998867283e-09, "Pretrain/Loss": 2.039243698120117, "Pretrain/Loss (Raw)": 2.277153730392456, "Pretrain/Step": 9483, "Pretrain/Step Time": 8.796891864389181} +{"Pretrain/Learning Rate": 4.049229681321598e-09, "Pretrain/Loss": 2.0392885208129883, "Pretrain/Loss (Raw)": 2.1680572032928467, "Pretrain/Step": 9484, "Pretrain/Step Time": 8.792064752429724} +{"Pretrain/Learning Rate": 3.897874014599512e-09, "Pretrain/Loss": 2.039308547973633, "Pretrain/Loss (Raw)": 2.127769947052002, "Pretrain/Step": 9485, "Pretrain/Step Time": 8.795983664691448} +{"Pretrain/Learning Rate": 3.749401016162058e-09, "Pretrain/Loss": 2.0410590171813965, "Pretrain/Loss (Raw)": 2.197878360748291, "Pretrain/Step": 9486, "Pretrain/Step Time": 8.799150887876749} +{"Pretrain/Learning Rate": 3.603810703131649e-09, "Pretrain/Loss": 2.040764331817627, "Pretrain/Loss (Raw)": 2.0475716590881348, "Pretrain/Step": 9487, "Pretrain/Step Time": 8.798686552792788} +{"Pretrain/Learning Rate": 3.4611030922948595e-09, "Pretrain/Loss": 2.0382089614868164, "Pretrain/Loss (Raw)": 1.8024399280548096, "Pretrain/Step": 9488, "Pretrain/Step Time": 8.803436078131199} +{"Pretrain/Learning Rate": 3.3212782001107444e-09, "Pretrain/Loss": 2.0360300540924072, "Pretrain/Loss (Raw)": 1.7802292108535767, "Pretrain/Step": 9489, "Pretrain/Step Time": 8.795969977974892} +{"Pretrain/Learning Rate": 3.1843360427052937e-09, "Pretrain/Loss": 2.0359184741973877, "Pretrain/Loss (Raw)": 2.0463435649871826, "Pretrain/Step": 9490, "Pretrain/Step Time": 8.797242138534784} +{"Pretrain/Learning Rate": 3.0502766358714297e-09, "Pretrain/Loss": 2.035996437072754, "Pretrain/Loss (Raw)": 2.0154194831848145, "Pretrain/Step": 9491, "Pretrain/Step Time": 8.795931454747915} +{"Pretrain/Learning Rate": 2.919099995069008e-09, "Pretrain/Loss": 2.0370583534240723, "Pretrain/Loss (Raw)": 2.187321901321411, "Pretrain/Step": 9492, "Pretrain/Step Time": 8.79901447892189} +{"Pretrain/Learning Rate": 2.790806135427593e-09, "Pretrain/Loss": 2.035233974456787, "Pretrain/Loss (Raw)": 1.9373109340667725, "Pretrain/Step": 9493, "Pretrain/Step Time": 8.800724862143397} +{"Pretrain/Learning Rate": 2.665395071740906e-09, "Pretrain/Loss": 2.0337882041931152, "Pretrain/Loss (Raw)": 1.934490442276001, "Pretrain/Step": 9494, "Pretrain/Step Time": 8.799177777022123} +{"Pretrain/Learning Rate": 2.5428668184696024e-09, "Pretrain/Loss": 2.033411979675293, "Pretrain/Loss (Raw)": 1.9239957332611084, "Pretrain/Step": 9495, "Pretrain/Step Time": 8.801178945228457} +{"Pretrain/Learning Rate": 2.423221389749597e-09, "Pretrain/Loss": 2.03279447555542, "Pretrain/Loss (Raw)": 1.9665058851242065, "Pretrain/Step": 9496, "Pretrain/Step Time": 8.797003667801619} +{"Pretrain/Learning Rate": 2.306458799372635e-09, "Pretrain/Loss": 2.0343117713928223, "Pretrain/Loss (Raw)": 2.099740982055664, "Pretrain/Step": 9497, "Pretrain/Step Time": 8.795191308483481} +{"Pretrain/Learning Rate": 2.192579060811273e-09, "Pretrain/Loss": 2.034902811050415, "Pretrain/Loss (Raw)": 2.0433075428009033, "Pretrain/Step": 9498, "Pretrain/Step Time": 8.801983477547765} +{"Pretrain/Learning Rate": 2.081582187193898e-09, "Pretrain/Loss": 2.0341193675994873, "Pretrain/Loss (Raw)": 1.9626295566558838, "Pretrain/Step": 9499, "Pretrain/Step Time": 8.801539994776249} +{"Pretrain/Learning Rate": 1.9734681913213815e-09, "Pretrain/Loss": 2.0326340198516846, "Pretrain/Loss (Raw)": 1.9839378595352173, "Pretrain/Step": 9500, "Pretrain/Step Time": 8.802037945017219} +{"Pretrain/Learning Rate": 1.868237085664304e-09, "Pretrain/Loss": 2.031446933746338, "Pretrain/Loss (Raw)": 1.9696115255355835, "Pretrain/Step": 9501, "Pretrain/Step Time": 8.806094778701663} +{"Pretrain/Learning Rate": 1.7658888823574027e-09, "Pretrain/Loss": 2.032212018966675, "Pretrain/Loss (Raw)": 2.0152299404144287, "Pretrain/Step": 9502, "Pretrain/Step Time": 8.80783823505044} +{"Pretrain/Learning Rate": 1.6664235932051243e-09, "Pretrain/Loss": 2.0308425426483154, "Pretrain/Loss (Raw)": 1.9060784578323364, "Pretrain/Step": 9503, "Pretrain/Step Time": 8.800365813076496} +{"Pretrain/Learning Rate": 1.5698412296760723e-09, "Pretrain/Loss": 2.0315160751342773, "Pretrain/Loss (Raw)": 1.9832022190093994, "Pretrain/Step": 9504, "Pretrain/Step Time": 8.800565361976624} +{"Pretrain/Learning Rate": 1.4761418029085593e-09, "Pretrain/Loss": 2.0308494567871094, "Pretrain/Loss (Raw)": 1.8878101110458374, "Pretrain/Step": 9505, "Pretrain/Step Time": 8.804664084687829} +{"Pretrain/Learning Rate": 1.3853253237078311e-09, "Pretrain/Loss": 2.0310351848602295, "Pretrain/Loss (Raw)": 2.183987617492676, "Pretrain/Step": 9506, "Pretrain/Step Time": 8.805920820683241} +{"Pretrain/Learning Rate": 1.2973918025516174e-09, "Pretrain/Loss": 2.0318169593811035, "Pretrain/Loss (Raw)": 1.824236273765564, "Pretrain/Step": 9507, "Pretrain/Step Time": 8.806643741205335} +{"Pretrain/Learning Rate": 1.2123412495762544e-09, "Pretrain/Loss": 2.0334715843200684, "Pretrain/Loss (Raw)": 2.041198492050171, "Pretrain/Step": 9508, "Pretrain/Step Time": 8.807543443515897} +{"Pretrain/Learning Rate": 1.1301736745905623e-09, "Pretrain/Loss": 2.032299518585205, "Pretrain/Loss (Raw)": 1.850092887878418, "Pretrain/Step": 9509, "Pretrain/Step Time": 8.810100989416242} +{"Pretrain/Learning Rate": 1.050889087075846e-09, "Pretrain/Loss": 2.031893491744995, "Pretrain/Loss (Raw)": 1.863112211227417, "Pretrain/Step": 9510, "Pretrain/Step Time": 8.802895268425345} +{"Pretrain/Learning Rate": 9.744874961664652e-10, "Pretrain/Loss": 2.02964186668396, "Pretrain/Loss (Raw)": 1.9099245071411133, "Pretrain/Step": 9511, "Pretrain/Step Time": 8.817235020920634} +{"Pretrain/Learning Rate": 9.00968910683142e-10, "Pretrain/Loss": 2.032641649246216, "Pretrain/Loss (Raw)": 2.2083377838134766, "Pretrain/Step": 9512, "Pretrain/Step Time": 8.811781868338585} +{"Pretrain/Learning Rate": 8.303333390968782e-10, "Pretrain/Loss": 2.0322928428649902, "Pretrain/Loss (Raw)": 2.1445610523223877, "Pretrain/Step": 9513, "Pretrain/Step Time": 8.820789014920592} +{"Pretrain/Learning Rate": 7.625807895567106e-10, "Pretrain/Loss": 2.0319864749908447, "Pretrain/Loss (Raw)": 1.8825180530548096, "Pretrain/Step": 9514, "Pretrain/Step Time": 8.817999057471752} +{"Pretrain/Learning Rate": 6.977112698758337e-10, "Pretrain/Loss": 2.033841371536255, "Pretrain/Loss (Raw)": 2.172390937805176, "Pretrain/Step": 9515, "Pretrain/Step Time": 8.820306293666363} +{"Pretrain/Learning Rate": 6.357247875371508e-10, "Pretrain/Loss": 2.0346641540527344, "Pretrain/Loss (Raw)": 2.075667142868042, "Pretrain/Step": 9516, "Pretrain/Step Time": 8.82425006851554} +{"Pretrain/Learning Rate": 5.766213496877226e-10, "Pretrain/Loss": 2.034921646118164, "Pretrain/Loss (Raw)": 1.893455982208252, "Pretrain/Step": 9517, "Pretrain/Step Time": 8.817637158557773} +{"Pretrain/Learning Rate": 5.20400963141543e-10, "Pretrain/Loss": 2.034613609313965, "Pretrain/Loss (Raw)": 1.9593509435653687, "Pretrain/Step": 9518, "Pretrain/Step Time": 8.819167094305158} +{"Pretrain/Learning Rate": 4.670636343850899e-10, "Pretrain/Loss": 2.0320842266082764, "Pretrain/Loss (Raw)": 2.0744266510009766, "Pretrain/Step": 9519, "Pretrain/Step Time": 8.816350042819977} +{"Pretrain/Learning Rate": 4.1660936956899874e-10, "Pretrain/Loss": 2.03452467918396, "Pretrain/Loss (Raw)": 2.125164747238159, "Pretrain/Step": 9520, "Pretrain/Step Time": 8.817344710230827} +{"Pretrain/Learning Rate": 3.6903817451083846e-10, "Pretrain/Loss": 2.035407304763794, "Pretrain/Loss (Raw)": 2.1391091346740723, "Pretrain/Step": 9521, "Pretrain/Step Time": 8.814966086298227} +{"Pretrain/Learning Rate": 3.2435005469788615e-10, "Pretrain/Loss": 2.035639762878418, "Pretrain/Loss (Raw)": 2.1395516395568848, "Pretrain/Step": 9522, "Pretrain/Step Time": 8.814074655994773} +{"Pretrain/Learning Rate": 2.825450152815767e-10, "Pretrain/Loss": 2.0351295471191406, "Pretrain/Loss (Raw)": 1.8966716527938843, "Pretrain/Step": 9523, "Pretrain/Step Time": 8.813080241903663} +{"Pretrain/Learning Rate": 2.436230610858292e-10, "Pretrain/Loss": 2.034750461578369, "Pretrain/Loss (Raw)": 2.039949893951416, "Pretrain/Step": 9524, "Pretrain/Step Time": 8.801234332844615} +{"Pretrain/Learning Rate": 2.075841965987202e-10, "Pretrain/Loss": 2.034256935119629, "Pretrain/Loss (Raw)": 2.0450234413146973, "Pretrain/Step": 9525, "Pretrain/Step Time": 8.809842182323337} +{"Pretrain/Learning Rate": 1.7442842597525933e-10, "Pretrain/Loss": 2.034273147583008, "Pretrain/Loss (Raw)": 1.9762722253799438, "Pretrain/Step": 9526, "Pretrain/Step Time": 8.80776509642601} +{"Pretrain/Learning Rate": 1.4415575304016494e-10, "Pretrain/Loss": 2.0344226360321045, "Pretrain/Loss (Raw)": 2.118173837661743, "Pretrain/Step": 9527, "Pretrain/Step Time": 8.806756421923637} +{"Pretrain/Learning Rate": 1.1676618128231288e-10, "Pretrain/Loss": 2.035858154296875, "Pretrain/Loss (Raw)": 2.1185190677642822, "Pretrain/Step": 9528, "Pretrain/Step Time": 8.807094521820545} +{"Pretrain/Learning Rate": 9.225971386583876e-11, "Pretrain/Loss": 2.036039352416992, "Pretrain/Loss (Raw)": 2.1524391174316406, "Pretrain/Step": 9529, "Pretrain/Step Time": 8.805582029744983} +{"Pretrain/Learning Rate": 7.063635361070908e-11, "Pretrain/Loss": 2.035533905029297, "Pretrain/Loss (Raw)": 1.9239829778671265, "Pretrain/Step": 9530, "Pretrain/Step Time": 8.807332821190357} +{"Pretrain/Learning Rate": 5.189610301492564e-11, "Pretrain/Loss": 2.0333058834075928, "Pretrain/Loss (Raw)": 1.8604786396026611, "Pretrain/Step": 9531, "Pretrain/Step Time": 8.80598272755742} +{"Pretrain/Learning Rate": 3.6038964235096675e-11, "Pretrain/Loss": 2.033280372619629, "Pretrain/Loss (Raw)": 2.100994825363159, "Pretrain/Step": 9532, "Pretrain/Step Time": 8.803296701982617} +{"Pretrain/Learning Rate": 2.3064939105865713e-11, "Pretrain/Loss": 2.0353810787200928, "Pretrain/Loss (Raw)": 2.133148670196533, "Pretrain/Step": 9533, "Pretrain/Step Time": 8.803786151111126} +{"Pretrain/Learning Rate": 1.2974029120482733e-11, "Pretrain/Loss": 2.037405014038086, "Pretrain/Loss (Raw)": 2.14294171333313, "Pretrain/Step": 9534, "Pretrain/Step Time": 8.801662590354681} +{"Pretrain/Learning Rate": 5.766235441906353e-12, "Pretrain/Loss": 2.036248207092285, "Pretrain/Loss (Raw)": 1.893734097480774, "Pretrain/Step": 9535, "Pretrain/Step Time": 8.805599393323064} +{"Pretrain/Learning Rate": 1.4415589028038411e-12, "Pretrain/Loss": 2.036794424057007, "Pretrain/Loss (Raw)": 1.8737273216247559, "Pretrain/Step": 9536, "Pretrain/Step Time": 8.799024496227503} +{"Pretrain/Learning Rate": 0.0, "Pretrain/Loss": 2.037688732147217, "Pretrain/Loss (Raw)": 2.0458993911743164, "Pretrain/Step": 9537, "Pretrain/Step Time": 8.80154668726027} diff --git a/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/run-metrics.jsonl b/obelics+phi3-3b-continue-training-dfn+stage-pretrain+x7/run-metrics.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..79619836bbbc7f597d797d244d8167cd2761ff7d --- /dev/null +++ b/obelics+phi3-3b-continue-training-dfn+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:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/OBELICS/obelics_dfn_single_pkl:/fsx-Training/shopqa-training-fsx-prod-us-east-1/home/wzwang/data/synthdog-en/synthdog_single_pkl/", "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": 2441407, "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-dfn", "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": 9537, "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-dfn+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-dfn+stage-pretrain+x7"}