| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "./en_results/checkpoint-750", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 1350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9925, | |
| "eval_classification_report": { | |
| "accuracy": 0.9925, | |
| "macro avg": { | |
| "f1-score": 0.9924995781012682, | |
| "precision": 0.9926108374384237, | |
| "recall": 0.9924999999999999, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9924433249370278, | |
| "precision": 1.0, | |
| "recall": 0.985, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9925558312655086, | |
| "precision": 0.9852216748768473, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9924995781012683, | |
| "precision": 0.9926108374384236, | |
| "recall": 0.9925, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.033255234360694885, | |
| "eval_runtime": 5.455, | |
| "eval_samples_per_second": 146.653, | |
| "eval_steps_per_second": 9.166, | |
| "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": 0.9987515605493134, | |
| "precision": 0.9975062344139651, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9987484355444306, | |
| "precision": 1.0, | |
| "recall": 0.9975, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.998749998046872, | |
| "precision": 0.9987531172069825, | |
| "recall": 0.99875, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.004529090132564306, | |
| "eval_runtime": 17.6229, | |
| "eval_samples_per_second": 45.396, | |
| "eval_steps_per_second": 2.837, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9925, | |
| "eval_classification_report": { | |
| "accuracy": 0.9925, | |
| "macro avg": { | |
| "f1-score": 0.9924995781012682, | |
| "precision": 0.9926108374384237, | |
| "recall": 0.9924999999999999, | |
| "support": 800.0 | |
| }, | |
| "neural": { | |
| "f1-score": 0.9924433249370278, | |
| "precision": 1.0, | |
| "recall": 0.985, | |
| "support": 400.0 | |
| }, | |
| "real": { | |
| "f1-score": 0.9925558312655086, | |
| "precision": 0.9852216748768473, | |
| "recall": 1.0, | |
| "support": 400.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.9924995781012683, | |
| "precision": 0.9926108374384236, | |
| "recall": 0.9925, | |
| "support": 800.0 | |
| } | |
| }, | |
| "eval_loss": 0.04066295549273491, | |
| "eval_runtime": 18.5855, | |
| "eval_samples_per_second": 43.044, | |
| "eval_steps_per_second": 2.69, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1429, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "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": 0.14006006717681885, | |
| "eval_runtime": 37.5571, | |
| "eval_samples_per_second": 21.301, | |
| "eval_steps_per_second": 1.331, | |
| "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": 0.0003298004739917815, | |
| "eval_runtime": 25.2571, | |
| "eval_samples_per_second": 31.674, | |
| "eval_steps_per_second": 1.98, | |
| "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": 8.567087206756696e-05, | |
| "eval_runtime": 35.7288, | |
| "eval_samples_per_second": 22.391, | |
| "eval_steps_per_second": 1.399, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.0134, | |
| "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": 4.2337298509664834e-05, | |
| "eval_runtime": 33.2322, | |
| "eval_samples_per_second": 24.073, | |
| "eval_steps_per_second": 1.505, | |
| "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": 2.951826354546938e-05, | |
| "eval_runtime": 34.6231, | |
| "eval_samples_per_second": 23.106, | |
| "eval_steps_per_second": 1.444, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "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": 2.2726077077095397e-05, | |
| "eval_runtime": 24.0892, | |
| "eval_samples_per_second": 33.21, | |
| "eval_steps_per_second": 2.076, | |
| "step": 1350 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 15000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 5683198795776000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |