| { | |
| "best_metric": 0.4374756335282651, | |
| "best_model_checkpoint": "./results/checkpoint-2724", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 2724, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_auc_pr": 0.3741202821573497, | |
| "eval_auc_roc": 0.5344017094017094, | |
| "eval_loss": 0.6598178148269653, | |
| "eval_runtime": 64.1274, | |
| "eval_samples_per_second": 1.575, | |
| "eval_steps_per_second": 0.795, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 2.729569673538208, | |
| "learning_rate": 3.2701908957415565e-05, | |
| "loss": 0.7137, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_auc_pr": 0.3336610256770358, | |
| "eval_auc_roc": 0.43162393162393164, | |
| "eval_loss": 0.6951384544372559, | |
| "eval_runtime": 63.851, | |
| "eval_samples_per_second": 1.582, | |
| "eval_steps_per_second": 0.799, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 4.023996829986572, | |
| "learning_rate": 2.535976505139501e-05, | |
| "loss": 0.6916, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_auc_pr": 0.3415869066362487, | |
| "eval_auc_roc": 0.4920940170940171, | |
| "eval_loss": 0.653586208820343, | |
| "eval_runtime": 63.8711, | |
| "eval_samples_per_second": 1.581, | |
| "eval_steps_per_second": 0.798, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "grad_norm": 3.374420642852783, | |
| "learning_rate": 1.801762114537445e-05, | |
| "loss": 0.7041, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_auc_pr": 0.3571268522434573, | |
| "eval_auc_roc": 0.5004273504273504, | |
| "eval_loss": 0.6515412330627441, | |
| "eval_runtime": 63.7749, | |
| "eval_samples_per_second": 1.584, | |
| "eval_steps_per_second": 0.8, | |
| "step": 1816 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "grad_norm": 2.160428285598755, | |
| "learning_rate": 1.0675477239353893e-05, | |
| "loss": 0.6616, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_auc_pr": 0.39159998056113526, | |
| "eval_auc_roc": 0.5651709401709402, | |
| "eval_loss": 0.6515726447105408, | |
| "eval_runtime": 63.9137, | |
| "eval_samples_per_second": 1.58, | |
| "eval_steps_per_second": 0.798, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "grad_norm": 1.967381477355957, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.6673, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_auc_pr": 0.4374756335282651, | |
| "eval_auc_roc": 0.6269230769230769, | |
| "eval_loss": 0.6512559652328491, | |
| "eval_runtime": 63.8923, | |
| "eval_samples_per_second": 1.581, | |
| "eval_steps_per_second": 0.798, | |
| "step": 2724 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2724, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 1.4298345882353664e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |