| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.4285714285714286, | |
| "eval_steps": 300, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 1.1057740449905396, | |
| "learning_rate": 2.3845381526104417e-05, | |
| "loss": 1.8757, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.731731116771698, | |
| "learning_rate": 2.2590361445783133e-05, | |
| "loss": 0.8572, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.8941469192504883, | |
| "learning_rate": 2.1335341365461846e-05, | |
| "loss": 0.7303, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.8464439511299133, | |
| "learning_rate": 2.0080321285140562e-05, | |
| "loss": 0.6042, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7973920309248000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |