| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1101, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22706630336058128, | |
| "grad_norm": 1.8386303186416626, | |
| "learning_rate": 3.869209809264305e-05, | |
| "loss": 1.3775, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.45413260672116257, | |
| "grad_norm": 1.83552885055542, | |
| "learning_rate": 2.7338782924613986e-05, | |
| "loss": 1.3109, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6811989100817438, | |
| "grad_norm": 1.9307498931884766, | |
| "learning_rate": 1.5985467756584924e-05, | |
| "loss": 1.2712, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9082652134423251, | |
| "grad_norm": 2.483839511871338, | |
| "learning_rate": 4.6321525885558584e-06, | |
| "loss": 1.2495, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1101, | |
| "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": 2395969014988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |