| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.2234506756067276, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.0322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.1784297227859497, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1032, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.40786346793174744, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0438, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.3481805622577667, | |
| "learning_rate": 0.0, | |
| "loss": 0.0325, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 6, | |
| "total_flos": 43469958021120.0, | |
| "train_loss": 0.04801289985577265, | |
| "train_runtime": 6.6043, | |
| "train_samples_per_second": 2.271, | |
| "train_steps_per_second": 0.909 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 43469958021120.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |