| { |
| "best_global_step": 72, |
| "best_metric": 0.92, |
| "best_model_checkpoint": "model_output/checkpoint-72", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 72, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 5.612344741821289, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.7335, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.68, |
| "eval_f1": 0.5828571428571429, |
| "eval_f1_class_0": 0.0, |
| "eval_f1_class_1": 0.8095238095238095, |
| "eval_loss": 0.6090771555900574, |
| "eval_precision": 0.51, |
| "eval_precision_class_0": 0.0, |
| "eval_precision_class_1": 0.7083333333333334, |
| "eval_recall": 0.68, |
| "eval_runtime": 12.5053, |
| "eval_samples_per_second": 1.999, |
| "eval_steps_per_second": 0.08, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.6956521739130435, |
| "grad_norm": 8.304722785949707, |
| "learning_rate": 4.948351554413879e-05, |
| "loss": 0.6217, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.64, |
| "eval_f1": 0.6565517241379311, |
| "eval_f1_class_0": 0.5714285714285714, |
| "eval_f1_class_1": 0.6896551724137931, |
| "eval_loss": 0.6883969902992249, |
| "eval_precision": 0.7745454545454545, |
| "eval_precision_class_0": 0.42857142857142855, |
| "eval_precision_class_1": 0.9090909090909091, |
| "eval_recall": 0.64, |
| "eval_runtime": 13.2971, |
| "eval_samples_per_second": 1.88, |
| "eval_steps_per_second": 0.075, |
| "step": 24 |
| }, |
| { |
| "epoch": 2.5217391304347827, |
| "grad_norm": 7.631145477294922, |
| "learning_rate": 4.700503477950278e-05, |
| "loss": 0.4983, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8, |
| "eval_f1": 0.7804195804195804, |
| "eval_f1_class_0": 0.5454545454545454, |
| "eval_f1_class_1": 0.8717948717948718, |
| "eval_loss": 0.39761456847190857, |
| "eval_precision": 0.7928571428571428, |
| "eval_precision_class_0": 0.75, |
| "eval_precision_class_1": 0.8095238095238095, |
| "eval_recall": 0.8, |
| "eval_runtime": 13.3227, |
| "eval_samples_per_second": 1.876, |
| "eval_steps_per_second": 0.075, |
| "step": 36 |
| }, |
| { |
| "epoch": 3.3478260869565215, |
| "grad_norm": 21.241336822509766, |
| "learning_rate": 4.267766952966369e-05, |
| "loss": 0.3525, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.56, |
| "eval_f1": 0.5727536231884058, |
| "eval_f1_class_0": 0.5217391304347826, |
| "eval_f1_class_1": 0.5925925925925926, |
| "eval_loss": 1.0984718799591064, |
| "eval_precision": 0.745, |
| "eval_precision_class_0": 0.375, |
| "eval_precision_class_1": 0.8888888888888888, |
| "eval_recall": 0.56, |
| "eval_runtime": 12.7157, |
| "eval_samples_per_second": 1.966, |
| "eval_steps_per_second": 0.079, |
| "step": 48 |
| }, |
| { |
| "epoch": 4.173913043478261, |
| "grad_norm": 11.476592063903809, |
| "learning_rate": 3.686500924369101e-05, |
| "loss": 0.2361, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.9555135369300842, |
| "learning_rate": 3.0055439308300952e-05, |
| "loss": 0.2533, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.88, |
| "eval_f1": 0.8822857142857142, |
| "eval_f1_class_0": 0.8, |
| "eval_f1_class_1": 0.9142857142857143, |
| "eval_loss": 0.4190010726451874, |
| "eval_precision": 0.8876470588235295, |
| "eval_precision_class_0": 0.75, |
| "eval_precision_class_1": 0.9411764705882353, |
| "eval_recall": 0.88, |
| "eval_runtime": 13.6564, |
| "eval_samples_per_second": 1.831, |
| "eval_steps_per_second": 0.073, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.869565217391305, |
| "grad_norm": 5.979536056518555, |
| "learning_rate": 2.2821106431308544e-05, |
| "loss": 0.1179, |
| "step": 70 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.92, |
| "eval_f1": 0.92, |
| "eval_f1_class_0": 0.8571428571428571, |
| "eval_f1_class_1": 0.9444444444444444, |
| "eval_loss": 0.31995919346809387, |
| "eval_precision": 0.92, |
| "eval_precision_class_0": 0.8571428571428571, |
| "eval_precision_class_1": 0.9444444444444444, |
| "eval_recall": 0.92, |
| "eval_runtime": 12.7724, |
| "eval_samples_per_second": 1.957, |
| "eval_steps_per_second": 0.078, |
| "step": 72 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 120, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 281791940290560.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
