| { |
| "best_metric": 1.0, |
| "best_model_checkpoint": "./tr_results/checkpoint-450", |
| "epoch": 7.0, |
| "eval_steps": 500, |
| "global_step": 1050, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.995, |
| "eval_classification_report": { |
| "accuracy": 0.995, |
| "macro avg": { |
| "f1-score": 0.9949998749968749, |
| "precision": 0.995049504950495, |
| "recall": 0.995, |
| "support": 800.0 |
| }, |
| "neural": { |
| "f1-score": 0.9949748743718593, |
| "precision": 1.0, |
| "recall": 0.99, |
| "support": 400.0 |
| }, |
| "real": { |
| "f1-score": 0.9950248756218906, |
| "precision": 0.9900990099009901, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "weighted avg": { |
| "f1-score": 0.9949998749968749, |
| "precision": 0.9950495049504952, |
| "recall": 0.995, |
| "support": 800.0 |
| } |
| }, |
| "eval_loss": 0.02387526072561741, |
| "eval_runtime": 36.5604, |
| "eval_samples_per_second": 21.882, |
| "eval_steps_per_second": 1.368, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.99875, |
| "eval_classification_report": { |
| "accuracy": 0.99875, |
| "macro avg": { |
| "f1-score": 0.9987499980468719, |
| "precision": 0.9987531172069826, |
| "recall": 0.99875, |
| "support": 800.0 |
| }, |
| "neural": { |
| "f1-score": 0.9987484355444306, |
| "precision": 1.0, |
| "recall": 0.9975, |
| "support": 400.0 |
| }, |
| "real": { |
| "f1-score": 0.9987515605493134, |
| "precision": 0.9975062344139651, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "weighted avg": { |
| "f1-score": 0.998749998046872, |
| "precision": 0.9987531172069825, |
| "recall": 0.99875, |
| "support": 800.0 |
| } |
| }, |
| "eval_loss": 0.006925567984580994, |
| "eval_runtime": 26.7301, |
| "eval_samples_per_second": 29.929, |
| "eval_steps_per_second": 1.871, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 1.0, |
| "eval_classification_report": { |
| "accuracy": 1.0, |
| "macro avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| }, |
| "neural": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "real": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "weighted avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| } |
| }, |
| "eval_loss": 3.8509064324898645e-05, |
| "eval_runtime": 39.0416, |
| "eval_samples_per_second": 20.491, |
| "eval_steps_per_second": 1.281, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 5e-05, |
| "loss": 0.1297, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 1.0, |
| "eval_classification_report": { |
| "accuracy": 1.0, |
| "macro avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| }, |
| "neural": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "real": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "weighted avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| } |
| }, |
| "eval_loss": 1.923065610753838e-05, |
| "eval_runtime": 37.6124, |
| "eval_samples_per_second": 21.27, |
| "eval_steps_per_second": 1.329, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 1.0, |
| "eval_classification_report": { |
| "accuracy": 1.0, |
| "macro avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| }, |
| "neural": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "real": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "weighted avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| } |
| }, |
| "eval_loss": 1.2674846402660478e-05, |
| "eval_runtime": 30.4314, |
| "eval_samples_per_second": 26.289, |
| "eval_steps_per_second": 1.643, |
| "step": 750 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 1.0, |
| "eval_classification_report": { |
| "accuracy": 1.0, |
| "macro avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| }, |
| "neural": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "real": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "weighted avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| } |
| }, |
| "eval_loss": 9.207534276356455e-06, |
| "eval_runtime": 43.1369, |
| "eval_samples_per_second": 18.546, |
| "eval_steps_per_second": 1.159, |
| "step": 900 |
| }, |
| { |
| "epoch": 6.67, |
| "learning_rate": 4.827586206896552e-05, |
| "loss": 0.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 1.0, |
| "eval_classification_report": { |
| "accuracy": 1.0, |
| "macro avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| }, |
| "neural": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "real": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 400.0 |
| }, |
| "weighted avg": { |
| "f1-score": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "support": 800.0 |
| } |
| }, |
| "eval_loss": 7.102613380993716e-06, |
| "eval_runtime": 41.8258, |
| "eval_samples_per_second": 19.127, |
| "eval_steps_per_second": 1.195, |
| "step": 1050 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 15000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "total_flos": 4420265730048000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
