| { | |
| "best_metric": 0.705236508994004, | |
| "best_model_checkpoint": "bert-finetuned-emoDetect\\checkpoint-10890", | |
| "epoch": 16.0, | |
| "global_step": 11616, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.612603305785123e-07, | |
| "loss": 0.6578, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.12597717674543985, | |
| "eval_f1": 0.6247395563961993, | |
| "eval_loss": 0.5872672200202942, | |
| "eval_roc_auc": 0.6941023793178698, | |
| "eval_runtime": 27.1522, | |
| "eval_samples_per_second": 409.874, | |
| "eval_steps_per_second": 25.633, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.225206611570248e-07, | |
| "loss": 0.6015, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.13747865935843293, | |
| "eval_f1": 0.676137544871173, | |
| "eval_loss": 0.5408967733383179, | |
| "eval_roc_auc": 0.7271664269226527, | |
| "eval_runtime": 27.4171, | |
| "eval_samples_per_second": 405.914, | |
| "eval_steps_per_second": 25.386, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 7.837809917355371e-07, | |
| "loss": 0.5649, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 7.450413223140496e-07, | |
| "loss": 0.5421, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.15338305328421242, | |
| "eval_f1": 0.6897526886106239, | |
| "eval_loss": 0.5212533473968506, | |
| "eval_roc_auc": 0.7365039148221721, | |
| "eval_runtime": 26.9702, | |
| "eval_samples_per_second": 412.641, | |
| "eval_steps_per_second": 25.806, | |
| "step": 2178 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 7.063016528925619e-07, | |
| "loss": 0.5299, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.15509030460957857, | |
| "eval_f1": 0.6938252626184985, | |
| "eval_loss": 0.511451005935669, | |
| "eval_roc_auc": 0.7391141519446084, | |
| "eval_runtime": 27.2486, | |
| "eval_samples_per_second": 408.424, | |
| "eval_steps_per_second": 25.543, | |
| "step": 2904 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 6.675619834710743e-07, | |
| "loss": 0.5197, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 6.288223140495868e-07, | |
| "loss": 0.5132, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.1585048072603109, | |
| "eval_f1": 0.6966020395824096, | |
| "eval_loss": 0.5062695145606995, | |
| "eval_roc_auc": 0.7411277519246361, | |
| "eval_runtime": 29.3114, | |
| "eval_samples_per_second": 379.681, | |
| "eval_steps_per_second": 23.745, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 5.900826446280991e-07, | |
| "loss": 0.5037, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.15940336058945098, | |
| "eval_f1": 0.6980239056608819, | |
| "eval_loss": 0.503739058971405, | |
| "eval_roc_auc": 0.7418482524921964, | |
| "eval_runtime": 29.5823, | |
| "eval_samples_per_second": 376.205, | |
| "eval_steps_per_second": 23.528, | |
| "step": 4356 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 5.513429752066116e-07, | |
| "loss": 0.5067, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 5.126033057851239e-07, | |
| "loss": 0.5029, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.16129032258064516, | |
| "eval_f1": 0.6980136185986543, | |
| "eval_loss": 0.5011261105537415, | |
| "eval_roc_auc": 0.7423068479571919, | |
| "eval_runtime": 29.397, | |
| "eval_samples_per_second": 378.576, | |
| "eval_steps_per_second": 23.676, | |
| "step": 5082 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 4.738636363636363e-07, | |
| "loss": 0.4959, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.16299757390601133, | |
| "eval_f1": 0.6987288021715176, | |
| "eval_loss": 0.4990156292915344, | |
| "eval_roc_auc": 0.7429793617183864, | |
| "eval_runtime": 29.4059, | |
| "eval_samples_per_second": 378.462, | |
| "eval_steps_per_second": 23.669, | |
| "step": 5808 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 4.3512396694214875e-07, | |
| "loss": 0.4925, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 3.963842975206612e-07, | |
| "loss": 0.4929, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.16686135322131368, | |
| "eval_f1": 0.7020867801675829, | |
| "eval_loss": 0.49795523285865784, | |
| "eval_roc_auc": 0.7451727394313618, | |
| "eval_runtime": 29.5261, | |
| "eval_samples_per_second": 376.92, | |
| "eval_steps_per_second": 23.572, | |
| "step": 6534 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 3.5764462809917355e-07, | |
| "loss": 0.4895, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.170275855872046, | |
| "eval_f1": 0.7031296013707065, | |
| "eval_loss": 0.4975072145462036, | |
| "eval_roc_auc": 0.7464022235943039, | |
| "eval_runtime": 29.7087, | |
| "eval_samples_per_second": 374.603, | |
| "eval_steps_per_second": 23.427, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 3.1890495867768593e-07, | |
| "loss": 0.4878, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.16982657920747596, | |
| "eval_f1": 0.7027403498432938, | |
| "eval_loss": 0.4964962601661682, | |
| "eval_roc_auc": 0.7461229684036625, | |
| "eval_runtime": 29.456, | |
| "eval_samples_per_second": 377.818, | |
| "eval_steps_per_second": 23.628, | |
| "step": 7986 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 2.801652892561983e-07, | |
| "loss": 0.4859, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 2.4142561983471074e-07, | |
| "loss": 0.4836, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.17144397519992813, | |
| "eval_f1": 0.7041074712796865, | |
| "eval_loss": 0.49592188000679016, | |
| "eval_roc_auc": 0.7468192187307751, | |
| "eval_runtime": 29.7723, | |
| "eval_samples_per_second": 373.804, | |
| "eval_steps_per_second": 23.377, | |
| "step": 8712 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 2.0268595041322314e-07, | |
| "loss": 0.4846, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.1711744092011861, | |
| "eval_f1": 0.7041892162758068, | |
| "eval_loss": 0.4953349828720093, | |
| "eval_roc_auc": 0.747152289680829, | |
| "eval_runtime": 28.7423, | |
| "eval_samples_per_second": 387.2, | |
| "eval_steps_per_second": 24.215, | |
| "step": 9438 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 1.6394628099173552e-07, | |
| "loss": 0.4809, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 1.2520661157024792e-07, | |
| "loss": 0.4798, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.17180339653158416, | |
| "eval_f1": 0.7049645957514902, | |
| "eval_loss": 0.49510398507118225, | |
| "eval_roc_auc": 0.7476226777348743, | |
| "eval_runtime": 29.5268, | |
| "eval_samples_per_second": 376.912, | |
| "eval_steps_per_second": 23.572, | |
| "step": 10164 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 8.646694214876032e-08, | |
| "loss": 0.4837, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.17315122652529427, | |
| "eval_f1": 0.705236508994004, | |
| "eval_loss": 0.49506452679634094, | |
| "eval_roc_auc": 0.7477827050997783, | |
| "eval_runtime": 29.4306, | |
| "eval_samples_per_second": 378.144, | |
| "eval_steps_per_second": 23.649, | |
| "step": 10890 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 4.772727272727273e-08, | |
| "loss": 0.4764, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 8.987603305785124e-09, | |
| "loss": 0.4803, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.17297151585946627, | |
| "eval_f1": 0.7051639311475847, | |
| "eval_loss": 0.49504488706588745, | |
| "eval_roc_auc": 0.7477833242237542, | |
| "eval_runtime": 29.3196, | |
| "eval_samples_per_second": 379.575, | |
| "eval_steps_per_second": 23.738, | |
| "step": 11616 | |
| } | |
| ], | |
| "max_steps": 11616, | |
| "num_train_epochs": 16, | |
| "total_flos": 1.221953566113792e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |