| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01937984496124031, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007751937984496124, | |
| "grad_norm": 8.48913288116455, | |
| "learning_rate": 1e-05, | |
| "loss": 4.7095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015503875968992248, | |
| "grad_norm": 7.711472511291504, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002325581395348837, | |
| "grad_norm": 7.3934855461120605, | |
| "learning_rate": 1.9906859460363307e-05, | |
| "loss": 4.2592, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0031007751937984496, | |
| "grad_norm": 7.414181709289551, | |
| "learning_rate": 1.9629172873477995e-05, | |
| "loss": 4.7613, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003875968992248062, | |
| "grad_norm": 8.253118515014648, | |
| "learning_rate": 1.917211301505453e-05, | |
| "loss": 4.6254, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004651162790697674, | |
| "grad_norm": 7.263385772705078, | |
| "learning_rate": 1.8544194045464888e-05, | |
| "loss": 4.5289, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005426356589147287, | |
| "grad_norm": 8.016865730285645, | |
| "learning_rate": 1.77571129070442e-05, | |
| "loss": 4.2601, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006201550387596899, | |
| "grad_norm": 8.323400497436523, | |
| "learning_rate": 1.6825531432186545e-05, | |
| "loss": 3.7434, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0069767441860465115, | |
| "grad_norm": 7.544571399688721, | |
| "learning_rate": 1.5766803221148676e-05, | |
| "loss": 4.1809, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007751937984496124, | |
| "grad_norm": 9.398632049560547, | |
| "learning_rate": 1.4600650377311523e-05, | |
| "loss": 4.3367, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008527131782945736, | |
| "grad_norm": 6.982254981994629, | |
| "learning_rate": 1.3348796121709862e-05, | |
| "loss": 4.1018, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009302325581395349, | |
| "grad_norm": 7.524163246154785, | |
| "learning_rate": 1.2034560130526341e-05, | |
| "loss": 4.3482, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010077519379844961, | |
| "grad_norm": 9.047621726989746, | |
| "learning_rate": 1.0682424133646712e-05, | |
| "loss": 4.5547, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010852713178294573, | |
| "grad_norm": 8.568410873413086, | |
| "learning_rate": 9.317575866353293e-06, | |
| "loss": 4.2696, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011627906976744186, | |
| "grad_norm": 7.767399787902832, | |
| "learning_rate": 7.965439869473664e-06, | |
| "loss": 4.0424, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012403100775193798, | |
| "grad_norm": 8.221578598022461, | |
| "learning_rate": 6.651203878290139e-06, | |
| "loss": 4.2511, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01317829457364341, | |
| "grad_norm": 7.685263633728027, | |
| "learning_rate": 5.399349622688479e-06, | |
| "loss": 4.3515, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013953488372093023, | |
| "grad_norm": 7.456569671630859, | |
| "learning_rate": 4.2331967788513295e-06, | |
| "loss": 4.0519, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014728682170542635, | |
| "grad_norm": 8.316213607788086, | |
| "learning_rate": 3.174468567813461e-06, | |
| "loss": 4.018, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015503875968992248, | |
| "grad_norm": 8.131329536437988, | |
| "learning_rate": 2.2428870929558012e-06, | |
| "loss": 4.3308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01627906976744186, | |
| "grad_norm": 6.1296563148498535, | |
| "learning_rate": 1.4558059545351144e-06, | |
| "loss": 4.0145, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017054263565891473, | |
| "grad_norm": 8.936922073364258, | |
| "learning_rate": 8.278869849454718e-07, | |
| "loss": 3.8954, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017829457364341085, | |
| "grad_norm": 6.99735164642334, | |
| "learning_rate": 3.708271265220087e-07, | |
| "loss": 3.7881, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018604651162790697, | |
| "grad_norm": 8.808905601501465, | |
| "learning_rate": 9.314053963669245e-08, | |
| "loss": 4.3049, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01937984496124031, | |
| "grad_norm": 6.519270420074463, | |
| "learning_rate": 0.0, | |
| "loss": 4.0326, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01937984496124031, | |
| "eval_loss": 4.119612693786621, | |
| "eval_runtime": 2052.9641, | |
| "eval_samples_per_second": 1.266, | |
| "eval_steps_per_second": 1.266, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4985332118323200.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |