| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7657554177195803, | |
| "eval_steps": 5000, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03828777088597902, | |
| "grad_norm": 471.1349792480469, | |
| "learning_rate": 3e-06, | |
| "loss": 205.1221, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07657554177195804, | |
| "grad_norm": 344.47088623046875, | |
| "learning_rate": 6e-06, | |
| "loss": 45.0922, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11486331265793706, | |
| "grad_norm": 309.480224609375, | |
| "learning_rate": 9e-06, | |
| "loss": 38.0229, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.15315108354391607, | |
| "grad_norm": 564.2250366210938, | |
| "learning_rate": 1.2e-05, | |
| "loss": 33.9726, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.19143885442989508, | |
| "grad_norm": 283.4784851074219, | |
| "learning_rate": 1.5e-05, | |
| "loss": 29.991, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.22972662531587412, | |
| "grad_norm": 330.930419921875, | |
| "learning_rate": 1.8e-05, | |
| "loss": 30.7885, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.26801439620185313, | |
| "grad_norm": 342.97344970703125, | |
| "learning_rate": 2.1e-05, | |
| "loss": 25.1332, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.30630216708783214, | |
| "grad_norm": 231.11172485351562, | |
| "learning_rate": 2.4e-05, | |
| "loss": 21.5112, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.34458993797381116, | |
| "grad_norm": 706.323974609375, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 19.5362, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.38287770885979017, | |
| "grad_norm": 205.98391723632812, | |
| "learning_rate": 3e-05, | |
| "loss": 18.0186, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.38287770885979017, | |
| "eval_loss": 52.25505447387695, | |
| "eval_runtime": 7.8963, | |
| "eval_samples_per_second": 1470.058, | |
| "eval_steps_per_second": 183.757, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.4211654797457692, | |
| "grad_norm": 237.13412475585938, | |
| "learning_rate": 2.9997949574887035e-05, | |
| "loss": 16.9354, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.45945325063174824, | |
| "grad_norm": 117.44111633300781, | |
| "learning_rate": 2.999179886011389e-05, | |
| "loss": 16.263, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.49774102151772726, | |
| "grad_norm": 419.0275573730469, | |
| "learning_rate": 2.9981549537224573e-05, | |
| "loss": 15.3433, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.5360287924037063, | |
| "grad_norm": 305.9416809082031, | |
| "learning_rate": 2.9967204408281618e-05, | |
| "loss": 13.5674, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.5743165632896853, | |
| "grad_norm": 373.90185546875, | |
| "learning_rate": 2.994876739510005e-05, | |
| "loss": 13.2024, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.6126043341756643, | |
| "grad_norm": 142.22088623046875, | |
| "learning_rate": 2.9926243538175172e-05, | |
| "loss": 13.7021, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.6508921050616433, | |
| "grad_norm": 134.59779357910156, | |
| "learning_rate": 2.9899638995304575e-05, | |
| "loss": 13.2536, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.6891798759476223, | |
| "grad_norm": 289.6990966796875, | |
| "learning_rate": 2.9868961039904628e-05, | |
| "loss": 13.1385, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.7274676468336013, | |
| "grad_norm": 529.670166015625, | |
| "learning_rate": 2.9834218059022027e-05, | |
| "loss": 12.3703, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.7657554177195803, | |
| "grad_norm": 162.87234497070312, | |
| "learning_rate": 2.9795419551040836e-05, | |
| "loss": 12.2421, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.7657554177195803, | |
| "eval_loss": 34.264163970947266, | |
| "eval_runtime": 7.8743, | |
| "eval_samples_per_second": 1474.162, | |
| "eval_steps_per_second": 184.27, | |
| "step": 10000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |