| { |
| "best_metric": 0.45467871431664447, |
| "best_model_checkpoint": "tiny-mistral/checkpoint-643", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 643, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.78, |
| "grad_norm": 13.069233894348145, |
| "learning_rate": 4.7413167444271646e-05, |
| "loss": 1.4479, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6498838109992254, |
| "eval_f1_macro": 0.45467871431664447, |
| "eval_f1_micro": 0.6498838109992254, |
| "eval_f1_weighted": 0.6214028764904677, |
| "eval_loss": 1.118202805519104, |
| "eval_macro_fpr": 0.039027492204575735, |
| "eval_macro_sensitivity": 0.4743680961365506, |
| "eval_macro_specificity": 0.9731278674075015, |
| "eval_precision": 0.6258370043663808, |
| "eval_precision_macro": 0.4712458606651466, |
| "eval_recall": 0.6498838109992254, |
| "eval_recall_macro": 0.4743680961365506, |
| "eval_runtime": 52.8829, |
| "eval_samples_per_second": 24.412, |
| "eval_steps_per_second": 3.063, |
| "eval_weighted_fpr": 0.03705525495982948, |
| "eval_weighted_sensitivity": 0.6498838109992254, |
| "eval_weighted_specificity": 0.9470342001132973, |
| "step": 643 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 9645, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 15, |
| "save_steps": 500, |
| "total_flos": 2863522174205952.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
