| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "./fa_results/checkpoint-600", | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 1200, | |
| "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": 0.01759614236652851, | |
| "eval_runtime": 34.4448, | |
| "eval_samples_per_second": 23.226, | |
| "eval_steps_per_second": 1.452, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.97375, | |
| "eval_classification_report": { | |
| "accuracy": 0.97375, | |
| "macro avg": { | |
| "f1-score": 0.9737318996370936, | |
| "precision": 0.9750593824228029, | |
| "recall": 0.97375, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9730423620025674, | |
| "precision": 1.0, | |
| "recall": 0.9475, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9744214372716199, | |
| "precision": 0.9501187648456056, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9737318996370936, | |
| "precision": 0.9750593824228028, | |
| "recall": 0.97375, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.1816234588623047, | |
| "eval_runtime": 23.7325, | |
| "eval_samples_per_second": 33.709, | |
| "eval_steps_per_second": 2.107, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9825, | |
| "eval_classification_report": { | |
| "accuracy": 0.9825, | |
| "macro avg": { | |
| "f1-score": 0.9824946389831886, | |
| "precision": 0.9830917874396135, | |
| "recall": 0.9824999999999999, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9821882951653944, | |
| "precision": 1.0, | |
| "recall": 0.965, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9828009828009828, | |
| "precision": 0.966183574879227, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9824946389831887, | |
| "precision": 0.9830917874396136, | |
| "recall": 0.9825, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.06379446387290955, | |
| "eval_runtime": 34.6037, | |
| "eval_samples_per_second": 23.119, | |
| "eval_steps_per_second": 1.445, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1249, | |
| "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": 6.574411963811144e-05, | |
| "eval_runtime": 32.2256, | |
| "eval_samples_per_second": 24.825, | |
| "eval_steps_per_second": 1.552, | |
| "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": 3.862570883939043e-05, | |
| "eval_runtime": 34.1596, | |
| "eval_samples_per_second": 23.419, | |
| "eval_steps_per_second": 1.464, | |
| "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": 2.708590545807965e-05, | |
| "eval_runtime": 23.9516, | |
| "eval_samples_per_second": 33.401, | |
| "eval_steps_per_second": 2.088, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.0001, | |
| "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": 2.0530005713226274e-05, | |
| "eval_runtime": 32.1556, | |
| "eval_samples_per_second": 24.879, | |
| "eval_steps_per_second": 1.555, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "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": 1.6309035345329903e-05, | |
| "eval_runtime": 37.1083, | |
| "eval_samples_per_second": 21.558, | |
| "eval_steps_per_second": 1.347, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 15000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 5051732262912000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |