| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "./fa_results/checkpoint-600", | |
| "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": 0.9975, | |
| "eval_classification_report": { | |
| "accuracy": 0.9975, | |
| "macro avg": { | |
| "f1-score": 0.9974999843749024, | |
| "precision": 0.9975124378109452, | |
| "recall": 0.9975, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9974937343358395, | |
| "precision": 1.0, | |
| "recall": 0.995, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9975062344139651, | |
| "precision": 0.9950248756218906, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9974999843749024, | |
| "precision": 0.9975124378109453, | |
| "recall": 0.9975, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.017120858654379845, | |
| "eval_runtime": 34.7129, | |
| "eval_samples_per_second": 23.046, | |
| "eval_steps_per_second": 1.44, | |
| "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": 0.010303272865712643, | |
| "eval_runtime": 34.6871, | |
| "eval_samples_per_second": 23.063, | |
| "eval_steps_per_second": 1.441, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.99625, | |
| "eval_classification_report": { | |
| "accuracy": 0.99625, | |
| "macro avg": { | |
| "f1-score": 0.9962499472648834, | |
| "precision": 0.9962779156327544, | |
| "recall": 0.9962500000000001, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9962358845671266, | |
| "precision": 1.0, | |
| "recall": 0.9925, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9962640099626401, | |
| "precision": 0.9925558312655087, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9962499472648834, | |
| "precision": 0.9962779156327544, | |
| "recall": 0.99625, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.016219044104218483, | |
| "eval_runtime": 29.5456, | |
| "eval_samples_per_second": 27.077, | |
| "eval_steps_per_second": 1.692, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1112, | |
| "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": 0.00012144193169660866, | |
| "eval_runtime": 22.7741, | |
| "eval_samples_per_second": 35.128, | |
| "eval_steps_per_second": 2.195, | |
| "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": 0.00027504810714162886, | |
| "eval_runtime": 17.1164, | |
| "eval_samples_per_second": 46.739, | |
| "eval_steps_per_second": 2.921, | |
| "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": 0.00036392605397850275, | |
| "eval_runtime": 22.6386, | |
| "eval_samples_per_second": 35.338, | |
| "eval_steps_per_second": 2.209, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.0014, | |
| "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": 0.0005032551125623286, | |
| "eval_runtime": 22.5993, | |
| "eval_samples_per_second": 35.399, | |
| "eval_steps_per_second": 2.212, | |
| "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 | |
| } | |