| { | |
| "best_metric": 0.026952052488923073, | |
| "best_model_checkpoint": "/kaggle/working/checkpoint-48000", | |
| "epoch": 1.8262060569167553, | |
| "global_step": 48000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.0868969715416225e-05, | |
| "loss": 0.052, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.988260534944281, | |
| "eval_f1": 0.9937665318461085, | |
| "eval_loss": 0.07157213985919952, | |
| "eval_precision": 0.9997522006273829, | |
| "eval_recall": 0.9878521107166308, | |
| "eval_runtime": 2387.3537, | |
| "eval_samples_per_second": 79.461, | |
| "eval_steps_per_second": 9.933, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.7379394308324458e-06, | |
| "loss": 0.0151, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.9959251879263266, | |
| "eval_f1": 0.9978455183716244, | |
| "eval_loss": 0.026952052488923073, | |
| "eval_precision": 0.999564452634224, | |
| "eval_recall": 0.9961324860046076, | |
| "eval_runtime": 2388.0426, | |
| "eval_samples_per_second": 79.438, | |
| "eval_steps_per_second": 9.93, | |
| "step": 48000 | |
| } | |
| ], | |
| "max_steps": 52568, | |
| "num_train_epochs": 2, | |
| "total_flos": 7.954978277974467e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |