| { |
| "best_metric": 0.27009761333465576, |
| "best_model_checkpoint": "./models/results_semeval_2021_task_7_47/checkpoint-125", |
| "epoch": 1.0, |
| "global_step": 125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.6826, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.6743, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 1.2e-05, |
| "loss": 0.6628, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_accuracy": 0.632, |
| "eval_f1": 0.7745098039215685, |
| "eval_loss": 0.6330053806304932, |
| "eval_precision": 0.632, |
| "eval_recall": 1.0, |
| "eval_runtime": 5.3505, |
| "eval_samples_per_second": 186.899, |
| "eval_steps_per_second": 23.362, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 1.55e-05, |
| "loss": 0.6508, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 0.6273, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 2.35e-05, |
| "loss": 0.4721, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_accuracy": 0.866, |
| "eval_f1": 0.8962848297213623, |
| "eval_loss": 0.34409669041633606, |
| "eval_precision": 0.8772727272727273, |
| "eval_recall": 0.9161392405063291, |
| "eval_runtime": 5.3938, |
| "eval_samples_per_second": 185.399, |
| "eval_steps_per_second": 23.175, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.3121, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 3.15e-05, |
| "loss": 0.3055, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 3.55e-05, |
| "loss": 0.2453, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_accuracy": 0.88, |
| "eval_f1": 0.904153354632588, |
| "eval_loss": 0.28931811451911926, |
| "eval_precision": 0.9129032258064517, |
| "eval_recall": 0.8955696202531646, |
| "eval_runtime": 5.3384, |
| "eval_samples_per_second": 187.324, |
| "eval_steps_per_second": 23.415, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3.9500000000000005e-05, |
| "loss": 0.1981, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 4.35e-05, |
| "loss": 0.2172, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 4.75e-05, |
| "loss": 0.1548, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_accuracy": 0.886, |
| "eval_f1": 0.9053156146179402, |
| "eval_loss": 0.2869994044303894, |
| "eval_precision": 0.9527972027972028, |
| "eval_recall": 0.8623417721518988, |
| "eval_runtime": 5.3401, |
| "eval_samples_per_second": 187.263, |
| "eval_steps_per_second": 23.408, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.1933, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 0.1873, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 1.2e-05, |
| "loss": 0.184, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.897, |
| "eval_f1": 0.9203402938901779, |
| "eval_loss": 0.27009761333465576, |
| "eval_precision": 0.9001512859304085, |
| "eval_recall": 0.9414556962025317, |
| "eval_runtime": 5.3512, |
| "eval_samples_per_second": 186.874, |
| "eval_steps_per_second": 23.359, |
| "step": 125 |
| } |
| ], |
| "max_steps": 125, |
| "num_train_epochs": 1, |
| "total_flos": 546777661920000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
