| { | |
| "best_metric": 0.6732447131282889, | |
| "best_model_checkpoint": "bart-large/checkpoint-12845", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 12845, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.967886337096146e-05, | |
| "loss": 2.0273, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.9354482937589206e-05, | |
| "loss": 1.4983, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.903140002595043e-05, | |
| "loss": 1.4727, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.870701959257818e-05, | |
| "loss": 1.3945, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.8383287920072665e-05, | |
| "loss": 1.1685, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6847405112316034, | |
| "eval_f1_macro": 0.4296023125768376, | |
| "eval_f1_micro": 0.6847405112316034, | |
| "eval_f1_weighted": 0.6471198955620663, | |
| "eval_loss": 1.258675456047058, | |
| "eval_macro_fpr": 0.03310536835500512, | |
| "eval_macro_sensitivity": 0.47197476920519743, | |
| "eval_macro_specificity": 0.9759825618150952, | |
| "eval_precision": 0.6359796796355663, | |
| "eval_precision_macro": 0.4175869918662546, | |
| "eval_recall": 0.6847405112316034, | |
| "eval_recall_macro": 0.47197476920519743, | |
| "eval_runtime": 166.2079, | |
| "eval_samples_per_second": 7.767, | |
| "eval_steps_per_second": 3.887, | |
| "eval_weighted_fpr": 0.03183916138621607, | |
| "eval_weighted_sensitivity": 0.6847405112316034, | |
| "eval_weighted_specificity": 0.9549979159948256, | |
| "step": 2569 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.80589074867004e-05, | |
| "loss": 1.2814, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.7734527053328146e-05, | |
| "loss": 1.2579, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.741079538082263e-05, | |
| "loss": 1.246, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.708641494745037e-05, | |
| "loss": 1.0685, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.676203451407811e-05, | |
| "loss": 1.1965, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6638264910921766, | |
| "eval_f1_macro": 0.3954707529203812, | |
| "eval_f1_micro": 0.6638264910921766, | |
| "eval_f1_weighted": 0.6467821848395333, | |
| "eval_loss": 1.1623183488845825, | |
| "eval_macro_fpr": 0.03422706134984445, | |
| "eval_macro_sensitivity": 0.4261017849773373, | |
| "eval_macro_specificity": 0.9752839802406176, | |
| "eval_precision": 0.6943370263824146, | |
| "eval_precision_macro": 0.45636498568634104, | |
| "eval_recall": 0.6638264910921766, | |
| "eval_recall_macro": 0.4261017849773373, | |
| "eval_runtime": 320.2013, | |
| "eval_samples_per_second": 4.032, | |
| "eval_steps_per_second": 2.017, | |
| "eval_weighted_fpr": 0.03490990990990991, | |
| "eval_weighted_sensitivity": 0.6638264910921766, | |
| "eval_weighted_specificity": 0.9654332125170877, | |
| "step": 5138 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.643765408070585e-05, | |
| "loss": 1.0697, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.611327364733359e-05, | |
| "loss": 1.1042, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.578954197482808e-05, | |
| "loss": 1.124, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.546516154145582e-05, | |
| "loss": 1.1449, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 4.514078110808356e-05, | |
| "loss": 1.189, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7234701781564679, | |
| "eval_f1_macro": 0.5196282925085354, | |
| "eval_f1_micro": 0.7234701781564679, | |
| "eval_f1_weighted": 0.7031290239201134, | |
| "eval_loss": 1.357356309890747, | |
| "eval_macro_fpr": 0.027073020005110214, | |
| "eval_macro_sensitivity": 0.5527845991176076, | |
| "eval_macro_specificity": 0.9790845865453512, | |
| "eval_precision": 0.7219921821470505, | |
| "eval_precision_macro": 0.5413306235947684, | |
| "eval_recall": 0.7234701781564679, | |
| "eval_recall_macro": 0.5527845991176076, | |
| "eval_runtime": 290.3268, | |
| "eval_samples_per_second": 4.447, | |
| "eval_steps_per_second": 2.225, | |
| "eval_weighted_fpr": 0.026576341844710787, | |
| "eval_weighted_sensitivity": 0.7234701781564679, | |
| "eval_weighted_specificity": 0.9627986200238022, | |
| "step": 7707 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.481704943557805e-05, | |
| "loss": 0.9829, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 4.4492669002205786e-05, | |
| "loss": 0.9172, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 4.416828856883353e-05, | |
| "loss": 0.9911, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 4.384390813546127e-05, | |
| "loss": 0.9934, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 4.351952770208901e-05, | |
| "loss": 1.0127, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7668474051123161, | |
| "eval_f1_macro": 0.6233324855492023, | |
| "eval_f1_micro": 0.7668474051123161, | |
| "eval_f1_weighted": 0.7569127961671379, | |
| "eval_loss": 1.4684507846832275, | |
| "eval_macro_fpr": 0.022371017412255348, | |
| "eval_macro_sensitivity": 0.6201844239757082, | |
| "eval_macro_specificity": 0.9821444214871504, | |
| "eval_precision": 0.7584494799967734, | |
| "eval_precision_macro": 0.6670503035550461, | |
| "eval_recall": 0.7668474051123161, | |
| "eval_recall_macro": 0.6201844239757082, | |
| "eval_runtime": 296.0277, | |
| "eval_samples_per_second": 4.361, | |
| "eval_steps_per_second": 2.182, | |
| "eval_weighted_fpr": 0.021255561047948592, | |
| "eval_weighted_sensitivity": 0.7668474051123161, | |
| "eval_weighted_specificity": 0.9653189171949409, | |
| "step": 10276 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 4.3196444790450244e-05, | |
| "loss": 0.9926, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 4.287206435707798e-05, | |
| "loss": 1.1046, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.2547683923705725e-05, | |
| "loss": 0.8572, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 4.222330349033346e-05, | |
| "loss": 0.8623, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 4.1898923056961206e-05, | |
| "loss": 1.0205, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7668474051123161, | |
| "eval_f1_macro": 0.6732447131282889, | |
| "eval_f1_micro": 0.7668474051123161, | |
| "eval_f1_weighted": 0.7643097206437405, | |
| "eval_loss": 1.4232454299926758, | |
| "eval_macro_fpr": 0.021536303183803004, | |
| "eval_macro_sensitivity": 0.6871530786461169, | |
| "eval_macro_specificity": 0.9827017397959152, | |
| "eval_precision": 0.7710604143740172, | |
| "eval_precision_macro": 0.6764905863857386, | |
| "eval_recall": 0.7668474051123161, | |
| "eval_recall_macro": 0.6871530786461169, | |
| "eval_runtime": 288.8657, | |
| "eval_samples_per_second": 4.469, | |
| "eval_steps_per_second": 2.236, | |
| "eval_weighted_fpr": 0.021255561047948592, | |
| "eval_weighted_sensitivity": 0.7668474051123161, | |
| "eval_weighted_specificity": 0.9736786918264111, | |
| "step": 12845 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 77070, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.792050610033664e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |