| { |
| "best_global_step": 1176, |
| "best_metric": 0.9635223336896785, |
| "best_model_checkpoint": "/app/checkpoints/checkpoint-1176", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1176, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_accuracy": 0.3837320574162679, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.3837320574162679, |
| "confusion_matrix": { |
| "fn": 1927, |
| "fp": 5, |
| "tn": 1200, |
| "tp": 3 |
| }, |
| "f_beta_score": 0.0030959752321981426, |
| "precision": 0.375, |
| "recall": 0.0015544041450777201 |
| }, |
| "1": { |
| "accuracy": 0.3837320574162679, |
| "confusion_matrix": { |
| "fn": 5, |
| "fp": 1927, |
| "tn": 3, |
| "tp": 1200 |
| }, |
| "f_beta_score": 0.554016620498615, |
| "precision": 0.38375439718580107, |
| "recall": 0.995850622406639 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 1932, |
| "fp": 1932, |
| "tn": 1203, |
| "tp": 1203 |
| }, |
| "eval_f_beta_score": 0.21485335243986398, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 3, |
| 1927 |
| ], |
| [ |
| 5, |
| 1200 |
| ] |
| ] |
| }, |
| "eval_loss": 0.689696729183197, |
| "eval_precision": 0.3783649277859299, |
| "eval_recall": 0.3837320574162679, |
| "eval_runtime": 19.5865, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 160.059, |
| "eval_steps_per_second": 20.014, |
| "step": 0 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.180086612701416, |
| "hard_loss": 0.1800905573181808, |
| "learning_rate": 2.288000034644329e-05, |
| "loss": 0.1801, |
| "step": 392 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9623604465709729, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9623604465709729, |
| "confusion_matrix": { |
| "fn": 72, |
| "fp": 46, |
| "tn": 1159, |
| "tp": 1858 |
| }, |
| "f_beta_score": 0.9692227438706312, |
| "precision": 0.9758403361344538, |
| "recall": 0.9626943005181348 |
| }, |
| "1": { |
| "accuracy": 0.9623604465709729, |
| "confusion_matrix": { |
| "fn": 46, |
| "fp": 72, |
| "tn": 1858, |
| "tp": 1159 |
| }, |
| "f_beta_score": 0.951559934318555, |
| "precision": 0.9415109666937449, |
| "recall": 0.9618257261410789 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 118, |
| "fp": 118, |
| "tn": 3017, |
| "tp": 3017 |
| }, |
| "eval_f_beta_score": 0.9624336894813962, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1858, |
| 72 |
| ], |
| [ |
| 46, |
| 1159 |
| ] |
| ] |
| }, |
| "eval_loss": 0.13664375245571136, |
| "eval_precision": 0.9626451558550106, |
| "eval_recall": 0.9623604465709729, |
| "eval_runtime": 19.7068, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 159.082, |
| "eval_steps_per_second": 19.892, |
| "step": 392 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.48259162902832, |
| "hard_loss": 0.10730842969734317, |
| "learning_rate": 2.1675951462592336e-05, |
| "loss": 0.1073, |
| "step": 784 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9588516746411483, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9588516746411483, |
| "confusion_matrix": { |
| "fn": 51, |
| "fp": 78, |
| "tn": 1127, |
| "tp": 1879 |
| }, |
| "f_beta_score": 0.9668124517622846, |
| "precision": 0.9601430761369443, |
| "recall": 0.9735751295336788 |
| }, |
| "1": { |
| "accuracy": 0.9588516746411483, |
| "confusion_matrix": { |
| "fn": 78, |
| "fp": 51, |
| "tn": 1879, |
| "tp": 1127 |
| }, |
| "f_beta_score": 0.9458665547629039, |
| "precision": 0.9567062818336163, |
| "recall": 0.9352697095435685 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 129, |
| "fp": 129, |
| "tn": 3006, |
| "tp": 3006 |
| }, |
| "eval_f_beta_score": 0.9587614769985673, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1879, |
| 51 |
| ], |
| [ |
| 78, |
| 1127 |
| ] |
| ] |
| }, |
| "eval_loss": 0.1417260617017746, |
| "eval_precision": 0.9588220754557608, |
| "eval_recall": 0.9588516746411483, |
| "eval_runtime": 19.5272, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 160.545, |
| "eval_steps_per_second": 20.075, |
| "step": 784 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 2.5649197101593018, |
| "hard_loss": 0.0743093061087444, |
| "learning_rate": 2.047190257874138e-05, |
| "loss": 0.0743, |
| "step": 1176 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9636363636363636, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9636363636363636, |
| "confusion_matrix": { |
| "fn": 38, |
| "fp": 76, |
| "tn": 1129, |
| "tp": 1892 |
| }, |
| "f_beta_score": 0.9707542329399692, |
| "precision": 0.9613821138211383, |
| "recall": 0.9803108808290155 |
| }, |
| "1": { |
| "accuracy": 0.9636363636363636, |
| "confusion_matrix": { |
| "fn": 76, |
| "fp": 38, |
| "tn": 1892, |
| "tp": 1129 |
| }, |
| "f_beta_score": 0.9519392917369308, |
| "precision": 0.9674378748928878, |
| "recall": 0.9369294605809129 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 114, |
| "fp": 114, |
| "tn": 3021, |
| "tp": 3021 |
| }, |
| "eval_f_beta_score": 0.9635223336896785, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1892, |
| 38 |
| ], |
| [ |
| 76, |
| 1129 |
| ] |
| ] |
| }, |
| "eval_loss": 0.1422441303730011, |
| "eval_precision": 0.9637097668008697, |
| "eval_recall": 0.9636363636363636, |
| "eval_runtime": 19.6152, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 159.825, |
| "eval_steps_per_second": 19.985, |
| "step": 1176 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 7840, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 2 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9894422792340480.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
