| { | |
| "best_metric": 0.6237123012542725, | |
| "best_model_checkpoint": "hBERTv1_new_pretrain_w_init__mrpc/checkpoint-116", | |
| "epoch": 9.0, | |
| "global_step": 261, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00049, | |
| "loss": 3.2785, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6238367557525635, | |
| "eval_runtime": 0.7409, | |
| "eval_samples_per_second": 550.699, | |
| "eval_steps_per_second": 5.399, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00048, | |
| "loss": 0.7343, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6785768866539001, | |
| "eval_runtime": 0.7398, | |
| "eval_samples_per_second": 551.485, | |
| "eval_steps_per_second": 5.407, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00047, | |
| "loss": 0.6377, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.62451171875, | |
| "eval_runtime": 0.7405, | |
| "eval_samples_per_second": 550.974, | |
| "eval_steps_per_second": 5.402, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00046, | |
| "loss": 0.6353, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6237123012542725, | |
| "eval_runtime": 0.7399, | |
| "eval_samples_per_second": 551.451, | |
| "eval_steps_per_second": 5.406, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00045000000000000004, | |
| "loss": 0.6344, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6243776679039001, | |
| "eval_runtime": 0.7419, | |
| "eval_samples_per_second": 549.914, | |
| "eval_steps_per_second": 5.391, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00044, | |
| "loss": 0.6314, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6323529481887817, | |
| "eval_runtime": 0.7418, | |
| "eval_samples_per_second": 550.048, | |
| "eval_steps_per_second": 5.393, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.00043, | |
| "loss": 0.6431, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6401510834693909, | |
| "eval_runtime": 0.7429, | |
| "eval_samples_per_second": 549.206, | |
| "eval_steps_per_second": 5.384, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00042, | |
| "loss": 0.6347, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6335784196853638, | |
| "eval_runtime": 0.7439, | |
| "eval_samples_per_second": 548.43, | |
| "eval_steps_per_second": 5.377, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.00041, | |
| "loss": 0.6343, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6257611513137817, | |
| "eval_runtime": 0.7412, | |
| "eval_samples_per_second": 550.441, | |
| "eval_steps_per_second": 5.396, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 261, | |
| "total_flos": 4888970768941056.0, | |
| "train_loss": 0.9404267789760312, | |
| "train_runtime": 225.9356, | |
| "train_samples_per_second": 811.736, | |
| "train_steps_per_second": 6.418 | |
| } | |
| ], | |
| "max_steps": 1450, | |
| "num_train_epochs": 50, | |
| "total_flos": 4888970768941056.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |