| { | |
| "best_metric": 0.9909600298841987, | |
| "best_model_checkpoint": "/home/shared/dt01/temutauro/ccasimiro/berta/src/finetuning/pos/roberta-base-ca-cased-pos/checkpoint-1230", | |
| "epoch": 9.99878197320341, | |
| "global_step": 4100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9902717208990272, | |
| "eval_f1": 0.9884402778815269, | |
| "eval_loss": 0.04564520716667175, | |
| "eval_precision": 0.9881081282903335, | |
| "eval_recall": 0.9887726508499907, | |
| "eval_runtime": 13.2852, | |
| "eval_samples_per_second": 128.639, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.390243902439025e-05, | |
| "loss": 0.1804, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9918077649676018, | |
| "eval_f1": 0.9899899152130878, | |
| "eval_loss": 0.036869727075099945, | |
| "eval_precision": 0.9896941861767671, | |
| "eval_recall": 0.9902858210349337, | |
| "eval_runtime": 13.3317, | |
| "eval_samples_per_second": 128.191, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.780487804878049e-05, | |
| "loss": 0.0303, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.992355091015025, | |
| "eval_f1": 0.9909600298841987, | |
| "eval_loss": 0.03579937666654587, | |
| "eval_precision": 0.9907749766573296, | |
| "eval_recall": 0.9911451522510741, | |
| "eval_runtime": 13.2482, | |
| "eval_samples_per_second": 128.999, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 3.170731707317073e-05, | |
| "loss": 0.0194, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9921079115097371, | |
| "eval_f1": 0.9907175675170894, | |
| "eval_loss": 0.037922825664281845, | |
| "eval_precision": 0.9904955745602569, | |
| "eval_recall": 0.9909396600037362, | |
| "eval_runtime": 13.1871, | |
| "eval_samples_per_second": 129.596, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.5609756097560977e-05, | |
| "loss": 0.0133, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.992231501262381, | |
| "eval_f1": 0.9908294577986965, | |
| "eval_loss": 0.03801530599594116, | |
| "eval_precision": 0.9906259336719451, | |
| "eval_recall": 0.991033065570708, | |
| "eval_runtime": 13.3822, | |
| "eval_samples_per_second": 127.707, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9916841752149579, | |
| "eval_f1": 0.9903335170120761, | |
| "eval_loss": 0.04094540327787399, | |
| "eval_precision": 0.9902317849872061, | |
| "eval_recall": 0.9904352699420885, | |
| "eval_runtime": 13.2046, | |
| "eval_samples_per_second": 129.424, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 1.9512195121951222e-05, | |
| "loss": 0.0085, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9918430763255001, | |
| "eval_f1": 0.9904548426263192, | |
| "eval_loss": 0.04267619550228119, | |
| "eval_precision": 0.9903623459096003, | |
| "eval_recall": 0.9905473566224547, | |
| "eval_runtime": 13.3294, | |
| "eval_samples_per_second": 128.212, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.3414634146341466e-05, | |
| "loss": 0.0059, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9922668126202793, | |
| "eval_f1": 0.9909512826019965, | |
| "eval_loss": 0.04542930796742439, | |
| "eval_precision": 0.9907014956028157, | |
| "eval_recall": 0.9912011955912572, | |
| "eval_runtime": 13.2987, | |
| "eval_samples_per_second": 128.508, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 7.317073170731707e-06, | |
| "loss": 0.0037, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.991966666078144, | |
| "eval_f1": 0.9906329090280827, | |
| "eval_loss": 0.04698851332068443, | |
| "eval_precision": 0.9904756568995462, | |
| "eval_recall": 0.9907902110965814, | |
| "eval_runtime": 13.2254, | |
| "eval_samples_per_second": 129.221, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 1.2195121951219514e-06, | |
| "loss": 0.0028, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9919843217570932, | |
| "eval_f1": 0.9906423354937522, | |
| "eval_loss": 0.04776829481124878, | |
| "eval_precision": 0.9904758347650706, | |
| "eval_recall": 0.9908088922099757, | |
| "eval_runtime": 13.2102, | |
| "eval_samples_per_second": 129.37, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 4100, | |
| "total_flos": 0, | |
| "train_runtime": 3867.6486, | |
| "train_samples_per_second": 1.06 | |
| } | |
| ], | |
| "max_steps": 4100, | |
| "num_train_epochs": 10, | |
| "total_flos": 0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |