| { | |
| "best_metric": 0.45365220308303833, | |
| "best_model_checkpoint": "hBERTv2_new_no_pretrain_qqp/checkpoint-2843", | |
| "epoch": 6.0, | |
| "global_step": 17058, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 0.5037, | |
| "step": 2843 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7856047489488004, | |
| "eval_combined_score": 0.7393321195168931, | |
| "eval_f1": 0.6930594900849859, | |
| "eval_loss": 0.45365220308303833, | |
| "eval_runtime": 177.1269, | |
| "eval_samples_per_second": 228.254, | |
| "eval_steps_per_second": 1.784, | |
| "step": 2843 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 0.4066, | |
| "step": 5686 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.794607964382884, | |
| "eval_combined_score": 0.7351924719618621, | |
| "eval_f1": 0.6757769795408404, | |
| "eval_loss": 0.45485788583755493, | |
| "eval_runtime": 179.191, | |
| "eval_samples_per_second": 225.625, | |
| "eval_steps_per_second": 1.763, | |
| "step": 5686 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 0.3367, | |
| "step": 8529 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7950284442245857, | |
| "eval_combined_score": 0.7300256413289143, | |
| "eval_f1": 0.6650228384332431, | |
| "eval_loss": 0.4630189836025238, | |
| "eval_runtime": 177.5842, | |
| "eval_samples_per_second": 227.667, | |
| "eval_steps_per_second": 1.779, | |
| "step": 8529 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 0.2876, | |
| "step": 11372 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8180064308681672, | |
| "eval_combined_score": 0.7889000553400642, | |
| "eval_f1": 0.7597936798119612, | |
| "eval_loss": 0.5278903841972351, | |
| "eval_runtime": 177.7849, | |
| "eval_samples_per_second": 227.41, | |
| "eval_steps_per_second": 1.777, | |
| "step": 11372 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.2498, | |
| "step": 14215 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8216670789018056, | |
| "eval_combined_score": 0.7933379394248289, | |
| "eval_f1": 0.7650087999478522, | |
| "eval_loss": 0.4857378900051117, | |
| "eval_runtime": 178.1608, | |
| "eval_samples_per_second": 226.93, | |
| "eval_steps_per_second": 1.774, | |
| "step": 14215 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 0.2371, | |
| "step": 17058 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8216423447934702, | |
| "eval_combined_score": 0.7796214343959346, | |
| "eval_f1": 0.7376005239983989, | |
| "eval_loss": 0.5113059282302856, | |
| "eval_runtime": 177.6527, | |
| "eval_samples_per_second": 227.579, | |
| "eval_steps_per_second": 1.779, | |
| "step": 17058 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 17058, | |
| "total_flos": 3.19469520131457e+17, | |
| "train_loss": 0.3369104450452592, | |
| "train_runtime": 30144.3422, | |
| "train_samples_per_second": 603.506, | |
| "train_steps_per_second": 4.716 | |
| } | |
| ], | |
| "max_steps": 142150, | |
| "num_train_epochs": 50, | |
| "total_flos": 3.19469520131457e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |