| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1080, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.5473, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.8120419393156919, | |
| "eval_loss": 0.7750807404518127, | |
| "eval_pearson": 0.8115414805311705, | |
| "eval_runtime": 10.8984, | |
| "eval_samples_per_second": 137.634, | |
| "eval_spearmanr": 0.8125423981002132, | |
| "eval_steps_per_second": 17.25, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6954, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.8145095741908042, | |
| "eval_loss": 0.8717353343963623, | |
| "eval_pearson": 0.8159860577723805, | |
| "eval_runtime": 10.909, | |
| "eval_samples_per_second": 137.502, | |
| "eval_spearmanr": 0.8130330906092277, | |
| "eval_steps_per_second": 17.234, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4828, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.8237743551253471, | |
| "eval_loss": 0.789396345615387, | |
| "eval_pearson": 0.825608960477892, | |
| "eval_runtime": 10.9264, | |
| "eval_samples_per_second": 137.282, | |
| "eval_spearmanr": 0.8219397497728022, | |
| "eval_steps_per_second": 17.206, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1080, | |
| "total_flos": 3067148834731008.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 0.0337, | |
| "train_samples_per_second": 511700.934, | |
| "train_steps_per_second": 32042.501 | |
| } | |
| ], | |
| "max_steps": 1080, | |
| "num_train_epochs": 3, | |
| "total_flos": 3067148834731008.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |