| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 4314, | |
| "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": 1.0727, | |
| "step": 1438 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.8213591113451347, | |
| "eval_loss": 0.7718442678451538, | |
| "eval_pearson": 0.818709053341712, | |
| "eval_runtime": 32.7792, | |
| "eval_samples_per_second": 45.761, | |
| "eval_spearmanr": 0.8240091693485575, | |
| "eval_steps_per_second": 5.735, | |
| "step": 1438 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.4619, | |
| "step": 2876 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.8486223143978786, | |
| "eval_loss": 0.7704320549964905, | |
| "eval_pearson": 0.847231018036828, | |
| "eval_runtime": 32.6549, | |
| "eval_samples_per_second": 45.935, | |
| "eval_spearmanr": 0.8500136107589293, | |
| "eval_steps_per_second": 5.757, | |
| "step": 2876 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2401, | |
| "step": 4314 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.8543492000039965, | |
| "eval_loss": 0.625028669834137, | |
| "eval_pearson": 0.8554314862950724, | |
| "eval_runtime": 32.627, | |
| "eval_samples_per_second": 45.974, | |
| "eval_spearmanr": 0.8532669137129205, | |
| "eval_steps_per_second": 5.762, | |
| "step": 4314 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 4314, | |
| "total_flos": 1.0789946557756416e+16, | |
| "train_loss": 0.5915702214990438, | |
| "train_runtime": 1352.1371, | |
| "train_samples_per_second": 12.755, | |
| "train_steps_per_second": 3.191 | |
| } | |
| ], | |
| "max_steps": 4314, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.0789946557756416e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |