| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 36.04340744018555, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.1212, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.8775720604589583, | |
| "eval_loss": 0.5732272267341614, | |
| "eval_pearson": 0.8789818053039898, | |
| "eval_runtime": 6.5665, | |
| "eval_samples_per_second": 228.431, | |
| "eval_spearmanr": 0.8761623156139267, | |
| "eval_steps_per_second": 28.63, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 15.674260139465332, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.4308, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.8794983049402647, | |
| "eval_loss": 0.5606899261474609, | |
| "eval_pearson": 0.881313245175558, | |
| "eval_runtime": 6.5051, | |
| "eval_samples_per_second": 230.59, | |
| "eval_spearmanr": 0.8776833647049715, | |
| "eval_steps_per_second": 28.901, | |
| "step": 720 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1080, | |
| "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": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3025223752022016.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |