| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994672349493873, | |
| "eval_steps": 500, | |
| "global_step": 469, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21310602024507191, | |
| "grad_norm": 3.0930368900299072, | |
| "learning_rate": 7.092198581560284e-05, | |
| "loss": 2.0066, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.42621204049014383, | |
| "grad_norm": 1.5248420238494873, | |
| "learning_rate": 9.533965244865718e-05, | |
| "loss": 1.2202, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6393180607352158, | |
| "grad_norm": 1.2673641443252563, | |
| "learning_rate": 8.744075829383887e-05, | |
| "loss": 1.1874, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8524240809802877, | |
| "grad_norm": 1.1734017133712769, | |
| "learning_rate": 7.954186413902054e-05, | |
| "loss": 1.1678, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1407, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.933418373416223e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |