| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 96, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 0.8482029438018799, | |
| "learning_rate": 0.0001780324790952092, | |
| "loss": 2.5431, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 0.5920950770378113, | |
| "learning_rate": 0.00010506491688387127, | |
| "loss": 1.2115, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.34375, | |
| "grad_norm": 0.9038103222846985, | |
| "learning_rate": 2.869468883687798e-05, | |
| "loss": 1.1095, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 96, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 833988260265984.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |