| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2894736842105265, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006578947368421052, | |
| "grad_norm": 61.44523239135742, | |
| "learning_rate": 4.9934210526315795e-05, | |
| "loss": 5.7871, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.342105263157895e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.973684210526316, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0263157894736844e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.2894736842105265, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7105263157894737e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 760, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 7727673338757120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |