| { | |
| "best_metric": 0.49603304266929626, | |
| "best_model_checkpoint": "MD_SL_best_model/checkpoint-5276", | |
| "epoch": 2.0, | |
| "global_step": 5276, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.936820823856457e-05, | |
| "loss": 1.0828, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.873641647712914e-05, | |
| "loss": 0.7086, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.8104624715693708e-05, | |
| "loss": 0.669, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.747283295425828e-05, | |
| "loss": 0.6264, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.6841041192822848e-05, | |
| "loss": 0.5951, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_balanced accuracy": 0.6598598463994036, | |
| "eval_f1": 0.6477315522294683, | |
| "eval_loss": 0.5617039799690247, | |
| "eval_precision": 0.6664522794774816, | |
| "eval_recall": 0.6598598463994036, | |
| "eval_runtime": 177.7279, | |
| "eval_samples_per_second": 59.366, | |
| "eval_steps_per_second": 3.714, | |
| "step": 2638 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.6209249431387417e-05, | |
| "loss": 0.5066, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.5577457669951985e-05, | |
| "loss": 0.475, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.4945665908516554e-05, | |
| "loss": 0.4635, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 1.4313874147081124e-05, | |
| "loss": 0.4546, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.3682082385645691e-05, | |
| "loss": 0.4428, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_balanced accuracy": 0.7034186400261718, | |
| "eval_f1": 0.6980022981890632, | |
| "eval_loss": 0.49603304266929626, | |
| "eval_precision": 0.7144313872416078, | |
| "eval_recall": 0.7034186400261718, | |
| "eval_runtime": 177.7105, | |
| "eval_samples_per_second": 59.372, | |
| "eval_steps_per_second": 3.714, | |
| "step": 5276 | |
| } | |
| ], | |
| "max_steps": 15828, | |
| "num_train_epochs": 6, | |
| "total_flos": 1.11816441335808e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |