| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006814077884910225, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001362815576982045, | |
| "eval_loss": 3.762300968170166, | |
| "eval_runtime": 357.6618, | |
| "eval_samples_per_second": 8.639, | |
| "eval_steps_per_second": 4.32, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006814077884910225, | |
| "grad_norm": 19.308378219604492, | |
| "learning_rate": 5e-05, | |
| "loss": 15.076, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001362815576982045, | |
| "grad_norm": 9.135622024536133, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6618, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001362815576982045, | |
| "eval_loss": 3.3052594661712646, | |
| "eval_runtime": 358.4211, | |
| "eval_samples_per_second": 8.621, | |
| "eval_steps_per_second": 4.311, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020442233654730676, | |
| "grad_norm": 4.848336696624756, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 12.9069, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00272563115396409, | |
| "grad_norm": 3.2571258544921875, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 12.3206, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00272563115396409, | |
| "eval_loss": 3.0396130084991455, | |
| "eval_runtime": 358.6997, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 4.307, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034070389424551125, | |
| "grad_norm": 4.436225414276123, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 12.14, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004088446730946135, | |
| "grad_norm": 3.1982760429382324, | |
| "learning_rate": 5e-05, | |
| "loss": 12.1189, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004088446730946135, | |
| "eval_loss": 3.024545907974243, | |
| "eval_runtime": 359.0717, | |
| "eval_samples_per_second": 8.606, | |
| "eval_steps_per_second": 4.303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004769854519437157, | |
| "grad_norm": 11.857263565063477, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 12.2151, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00545126230792818, | |
| "grad_norm": 7.0431671142578125, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 12.2395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00545126230792818, | |
| "eval_loss": 3.022294282913208, | |
| "eval_runtime": 359.7414, | |
| "eval_samples_per_second": 8.59, | |
| "eval_steps_per_second": 4.295, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006132670096419202, | |
| "grad_norm": 4.540308475494385, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 12.2358, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006814077884910225, | |
| "grad_norm": 12.071662902832031, | |
| "learning_rate": 0.0, | |
| "loss": 12.1334, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006814077884910225, | |
| "eval_loss": 3.0158936977386475, | |
| "eval_runtime": 359.7398, | |
| "eval_samples_per_second": 8.59, | |
| "eval_steps_per_second": 4.295, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.75344288006144e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |