| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "./hu_results/checkpoint-900", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.97875, | |
| "eval_classification_report": { | |
| "accuracy": 0.97875, | |
| "macro avg": { | |
| "f1-score": 0.9787403999618578, | |
| "precision": 0.9796163069544365, | |
| "recall": 0.97875, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9782886334610472, | |
| "precision": 1.0, | |
| "recall": 0.9575, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9791921664626683, | |
| "precision": 0.9592326139088729, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9787403999618579, | |
| "precision": 0.9796163069544365, | |
| "recall": 0.97875, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.0850243791937828, | |
| "eval_runtime": 35.7911, | |
| "eval_samples_per_second": 22.352, | |
| "eval_steps_per_second": 1.397, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.99125, | |
| "eval_classification_report": { | |
| "accuracy": 0.99125, | |
| "macro avg": { | |
| "f1-score": 0.9912498769513947, | |
| "precision": 0.9912776343669332, | |
| "recall": 0.99125, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.991282689912827, | |
| "precision": 0.9875930521091811, | |
| "recall": 0.995, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9912170639899623, | |
| "precision": 0.9949622166246851, | |
| "recall": 0.9875, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9912498769513947, | |
| "precision": 0.9912776343669332, | |
| "recall": 0.99125, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.04250513017177582, | |
| "eval_runtime": 34.1425, | |
| "eval_samples_per_second": 23.431, | |
| "eval_steps_per_second": 1.464, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9925, | |
| "eval_classification_report": { | |
| "accuracy": 0.9925, | |
| "macro avg": { | |
| "f1-score": 0.9924998124953124, | |
| "precision": 0.9925492549254926, | |
| "recall": 0.9925, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.992462311557789, | |
| "precision": 0.9974747474747475, | |
| "recall": 0.9875, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9925373134328358, | |
| "precision": 0.9876237623762376, | |
| "recall": 0.9975, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9924998124953123, | |
| "precision": 0.9925492549254926, | |
| "recall": 0.9925, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.024615492671728134, | |
| "eval_runtime": 35.5631, | |
| "eval_samples_per_second": 22.495, | |
| "eval_steps_per_second": 1.406, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1759, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "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": 0.02516535297036171, | |
| "eval_runtime": 40.1884, | |
| "eval_samples_per_second": 19.906, | |
| "eval_steps_per_second": 1.244, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.99625, | |
| "eval_classification_report": { | |
| "accuracy": 0.99625, | |
| "macro avg": { | |
| "f1-score": 0.9962499941406158, | |
| "precision": 0.9962531015818848, | |
| "recall": 0.9962500000000001, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9962453066332916, | |
| "precision": 0.9974937343358395, | |
| "recall": 0.995, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9962546816479401, | |
| "precision": 0.9950124688279302, | |
| "recall": 0.9975, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9962499941406158, | |
| "precision": 0.9962531015818848, | |
| "recall": 0.99625, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.01939307153224945, | |
| "eval_runtime": 38.9376, | |
| "eval_samples_per_second": 20.546, | |
| "eval_steps_per_second": 1.284, | |
| "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": 0.00028793435194529593, | |
| "eval_runtime": 39.4316, | |
| "eval_samples_per_second": 20.288, | |
| "eval_steps_per_second": 1.268, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.024, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.995, | |
| "eval_classification_report": { | |
| "accuracy": 0.995, | |
| "macro avg": { | |
| "f1-score": 0.995, | |
| "precision": 0.995, | |
| "recall": 0.995, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.995, | |
| "precision": 0.995, | |
| "recall": 0.995, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.995, | |
| "precision": 0.995, | |
| "recall": 0.995, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.995, | |
| "precision": 0.995, | |
| "recall": 0.995, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.040607329457998276, | |
| "eval_runtime": 37.065, | |
| "eval_samples_per_second": 21.584, | |
| "eval_steps_per_second": 1.349, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "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": 0.03953583538532257, | |
| "eval_runtime": 37.5314, | |
| "eval_samples_per_second": 21.316, | |
| "eval_steps_per_second": 1.332, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "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": 0.012211117893457413, | |
| "eval_runtime": 30.4379, | |
| "eval_samples_per_second": 26.283, | |
| "eval_steps_per_second": 1.643, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.655172413793104e-05, | |
| "loss": 0.0131, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "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": 4.0015485865296796e-05, | |
| "eval_runtime": 35.2549, | |
| "eval_samples_per_second": 22.692, | |
| "eval_steps_per_second": 1.418, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 15000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 6314665328640000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |