| { | |
| "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 | |
| } | |