| { | |
| "best_metric": 0.579136690647482, | |
| "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/control_raising_lexical_content_the/checkpoint-200", | |
| "epoch": 10.0, | |
| "global_step": 1070, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.6819880604743958, | |
| "eval_f1": 0.579136690647482, | |
| "eval_loss": 2.4814441204071045, | |
| "eval_mcc": 0.41063817024619786, | |
| "eval_runtime": 43.9173, | |
| "eval_samples_per_second": 469.132, | |
| "eval_steps_per_second": 58.656, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_accuracy": 0.6815512180328369, | |
| "eval_f1": 0.5776089615656989, | |
| "eval_loss": 2.7655115127563477, | |
| "eval_mcc": 0.4104862064020946, | |
| "eval_runtime": 43.7894, | |
| "eval_samples_per_second": 470.502, | |
| "eval_steps_per_second": 58.827, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.663551401869159e-05, | |
| "loss": 0.0348, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_accuracy": 0.6813570857048035, | |
| "eval_f1": 0.5759865659109992, | |
| "eval_loss": 2.906750202178955, | |
| "eval_mcc": 0.411267707423774, | |
| "eval_runtime": 43.8783, | |
| "eval_samples_per_second": 469.548, | |
| "eval_steps_per_second": 58.708, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_accuracy": 0.6815512180328369, | |
| "eval_f1": 0.5755870366776635, | |
| "eval_loss": 2.9861977100372314, | |
| "eval_mcc": 0.41231028719817475, | |
| "eval_runtime": 43.6538, | |
| "eval_samples_per_second": 471.964, | |
| "eval_steps_per_second": 59.01, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 3.2710280373831774e-06, | |
| "loss": 0.0001, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "eval_accuracy": 0.6816968321800232, | |
| "eval_f1": 0.575259067357513, | |
| "eval_loss": 3.022336721420288, | |
| "eval_mcc": 0.41312205723925904, | |
| "eval_runtime": 43.7957, | |
| "eval_samples_per_second": 470.434, | |
| "eval_steps_per_second": 58.819, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1070, | |
| "total_flos": 6243730123161600.0, | |
| "train_loss": 0.016269592104793014, | |
| "train_runtime": 588.4501, | |
| "train_samples_per_second": 115.83, | |
| "train_steps_per_second": 1.818 | |
| } | |
| ], | |
| "max_steps": 1070, | |
| "num_train_epochs": 10, | |
| "total_flos": 6243730123161600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |