| { | |
| "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": 1.1174, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.8815940360468737, | |
| "eval_loss": 0.5000496506690979, | |
| "eval_pearson": 0.8832304460348288, | |
| "eval_runtime": 15.5329, | |
| "eval_samples_per_second": 96.569, | |
| "eval_spearmanr": 0.8799576260589187, | |
| "eval_steps_per_second": 12.103, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.3835, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.8901405153644659, | |
| "eval_loss": 0.4672209620475769, | |
| "eval_pearson": 0.8914800693934992, | |
| "eval_runtime": 15.3324, | |
| "eval_samples_per_second": 97.832, | |
| "eval_spearmanr": 0.8888009613354327, | |
| "eval_steps_per_second": 12.262, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2388, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.8911934607933856, | |
| "eval_loss": 0.48608845472335815, | |
| "eval_pearson": 0.8925961944446151, | |
| "eval_runtime": 15.3291, | |
| "eval_samples_per_second": 97.853, | |
| "eval_spearmanr": 0.8897907271421561, | |
| "eval_steps_per_second": 12.264, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1080, | |
| "total_flos": 4537835628033024.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 0.0413, | |
| "train_samples_per_second": 417771.136, | |
| "train_steps_per_second": 26160.656 | |
| } | |
| ], | |
| "max_steps": 1080, | |
| "num_train_epochs": 3, | |
| "total_flos": 4537835628033024.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |