| { |
| "best_global_step": 7840, |
| "best_metric": 0.9680508203881729, |
| "best_model_checkpoint": "/app/checkpoints/checkpoint-7840", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 7840, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_accuracy": 0.38692185007974483, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.38692185007974483, |
| "confusion_matrix": { |
| "fn": 1904, |
| "fp": 18, |
| "tn": 1187, |
| "tp": 26 |
| }, |
| "f_beta_score": 0.02634245187436677, |
| "precision": 0.5909090909090909, |
| "recall": 0.013471502590673576 |
| }, |
| "1": { |
| "accuracy": 0.38692185007974483, |
| "confusion_matrix": { |
| "fn": 18, |
| "fp": 1904, |
| "tn": 26, |
| "tp": 1187 |
| }, |
| "f_beta_score": 0.5526070763500931, |
| "precision": 0.38401811711420253, |
| "recall": 0.9850622406639005 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 1922, |
| "fp": 1922, |
| "tn": 1213, |
| "tp": 1213 |
| }, |
| "eval_f_beta_score": 0.22862279397747687, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 26, |
| 1904 |
| ], |
| [ |
| 18, |
| 1187 |
| ] |
| ] |
| }, |
| "eval_loss": 0.6828452944755554, |
| "eval_precision": 0.5113864040118531, |
| "eval_recall": 0.38692185007974483, |
| "eval_runtime": 18.6915, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 167.723, |
| "eval_steps_per_second": 20.972, |
| "step": 0 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.09250472486019135, |
| "hard_loss": 0.19278878086653112, |
| "learning_rate": 1.1780364852141454e-05, |
| "loss": 0.1928, |
| "step": 1568 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9559808612440192, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9559808612440192, |
| "confusion_matrix": { |
| "fn": 94, |
| "fp": 44, |
| "tn": 1161, |
| "tp": 1836 |
| }, |
| "f_beta_score": 0.9637795275590552, |
| "precision": 0.9765957446808511, |
| "recall": 0.9512953367875647 |
| }, |
| "1": { |
| "accuracy": 0.9559808612440192, |
| "confusion_matrix": { |
| "fn": 44, |
| "fp": 94, |
| "tn": 1836, |
| "tp": 1161 |
| }, |
| "f_beta_score": 0.9439024390243902, |
| "precision": 0.9250996015936255, |
| "recall": 0.9634854771784233 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 138, |
| "fp": 138, |
| "tn": 2997, |
| "tp": 2997 |
| }, |
| "eval_f_beta_score": 0.9561393707219671, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1836, |
| 94 |
| ], |
| [ |
| 44, |
| 1161 |
| ] |
| ] |
| }, |
| "eval_loss": 0.20423130691051483, |
| "eval_precision": 0.956802171341104, |
| "eval_recall": 0.9559808612440192, |
| "eval_runtime": 18.3681, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 170.676, |
| "eval_steps_per_second": 21.341, |
| "step": 1568 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.2099187821149826, |
| "hard_loss": 0.14008313520248428, |
| "learning_rate": 1.1160366460299146e-05, |
| "loss": 0.1401, |
| "step": 3136 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9661881977671452, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9661881977671452, |
| "confusion_matrix": { |
| "fn": 45, |
| "fp": 61, |
| "tn": 1144, |
| "tp": 1885 |
| }, |
| "f_beta_score": 0.9726522187822497, |
| "precision": 0.9686536485097637, |
| "recall": 0.9766839378238342 |
| }, |
| "1": { |
| "accuracy": 0.9661881977671452, |
| "confusion_matrix": { |
| "fn": 61, |
| "fp": 45, |
| "tn": 1885, |
| "tp": 1144 |
| }, |
| "f_beta_score": 0.9557226399331662, |
| "precision": 0.9621530698065601, |
| "recall": 0.9493775933609958 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 106, |
| "fp": 106, |
| "tn": 3029, |
| "tp": 3029 |
| }, |
| "eval_f_beta_score": 0.9661449962900183, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1885, |
| 45 |
| ], |
| [ |
| 61, |
| 1144 |
| ] |
| ] |
| }, |
| "eval_loss": 0.14875319600105286, |
| "eval_precision": 0.9661550209699359, |
| "eval_recall": 0.9661881977671452, |
| "eval_runtime": 18.3189, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 171.134, |
| "eval_steps_per_second": 21.399, |
| "step": 3136 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.020211078226566315, |
| "hard_loss": 0.11091282128492301, |
| "learning_rate": 1.0540368068456843e-05, |
| "loss": 0.1109, |
| "step": 4704 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9665071770334929, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9665071770334929, |
| "confusion_matrix": { |
| "fn": 51, |
| "fp": 54, |
| "tn": 1151, |
| "tp": 1879 |
| }, |
| "f_beta_score": 0.9728190525498317, |
| "precision": 0.9720641489912054, |
| "recall": 0.9735751295336788 |
| }, |
| "1": { |
| "accuracy": 0.9665071770334929, |
| "confusion_matrix": { |
| "fn": 54, |
| "fp": 51, |
| "tn": 1879, |
| "tp": 1151 |
| }, |
| "f_beta_score": 0.9563772330702118, |
| "precision": 0.9575707154742097, |
| "recall": 0.9551867219917013 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 105, |
| "fp": 105, |
| "tn": 3030, |
| "tp": 3030 |
| }, |
| "eval_f_beta_score": 0.9664993101342201, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1879, |
| 51 |
| ], |
| [ |
| 54, |
| 1151 |
| ] |
| ] |
| }, |
| "eval_loss": 0.1719985455274582, |
| "eval_precision": 0.9664933077191225, |
| "eval_recall": 0.9665071770334929, |
| "eval_runtime": 18.5606, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 168.906, |
| "eval_steps_per_second": 21.12, |
| "step": 4704 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.007895365357398987, |
| "hard_loss": 0.07477579451819463, |
| "learning_rate": 9.920369676614537e-06, |
| "loss": 0.0748, |
| "step": 6272 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9559808612440192, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9559808612440192, |
| "confusion_matrix": { |
| "fn": 101, |
| "fp": 37, |
| "tn": 1168, |
| "tp": 1829 |
| }, |
| "f_beta_score": 0.9636459430979979, |
| "precision": 0.9801714898177921, |
| "recall": 0.9476683937823834 |
| }, |
| "1": { |
| "accuracy": 0.9559808612440192, |
| "confusion_matrix": { |
| "fn": 37, |
| "fp": 101, |
| "tn": 1829, |
| "tp": 1168 |
| }, |
| "f_beta_score": 0.9442198868229588, |
| "precision": 0.9204097714736013, |
| "recall": 0.9692946058091286 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 138, |
| "fp": 138, |
| "tn": 2997, |
| "tp": 2997 |
| }, |
| "eval_f_beta_score": 0.9561791495377358, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1829, |
| 101 |
| ], |
| [ |
| 37, |
| 1168 |
| ] |
| ] |
| }, |
| "eval_loss": 0.2560373842716217, |
| "eval_precision": 0.957200877184698, |
| "eval_recall": 0.9559808612440192, |
| "eval_runtime": 18.6002, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 168.546, |
| "eval_steps_per_second": 21.075, |
| "step": 6272 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.028711551800370216, |
| "hard_loss": 0.04914131778617753, |
| "learning_rate": 9.300371284772232e-06, |
| "loss": 0.0491, |
| "step": 7840 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9681020733652312, |
| "eval_class_metrics": { |
| "0": { |
| "accuracy": 0.9681020733652312, |
| "confusion_matrix": { |
| "fn": 40, |
| "fp": 60, |
| "tn": 1145, |
| "tp": 1890 |
| }, |
| "f_beta_score": 0.9742268041237113, |
| "precision": 0.9692307692307692, |
| "recall": 0.9792746113989638 |
| }, |
| "1": { |
| "accuracy": 0.9681020733652312, |
| "confusion_matrix": { |
| "fn": 60, |
| "fp": 40, |
| "tn": 1890, |
| "tp": 1145 |
| }, |
| "f_beta_score": 0.9581589958158996, |
| "precision": 0.9662447257383966, |
| "recall": 0.950207468879668 |
| } |
| }, |
| "eval_confusion_matrix": { |
| "fn": 100, |
| "fp": 100, |
| "tn": 3035, |
| "tp": 3035 |
| }, |
| "eval_f_beta_score": 0.9680508203881729, |
| "eval_label_confusion_matrix": { |
| "labels": [ |
| "False", |
| "True" |
| ], |
| "matrix": [ |
| [ |
| 1890, |
| 40 |
| ], |
| [ |
| 60, |
| 1145 |
| ] |
| ] |
| }, |
| "eval_loss": 0.24635428190231323, |
| "eval_precision": 0.9680830236459818, |
| "eval_recall": 0.9681020733652312, |
| "eval_runtime": 18.3281, |
| "eval_sample_size": 3135, |
| "eval_samples_per_second": 171.049, |
| "eval_steps_per_second": 21.388, |
| "step": 7840 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 31360, |
| "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": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.494801327708096e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
