| { |
| "best_metric": 0.7021276595744681, |
| "best_model_checkpoint": "../model/iter3/roberta-base/checkpoint-216", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 216, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 4.311070919036865, |
| "learning_rate": 1.9333333333333333e-05, |
| "loss": 0.1212, |
| "step": 216 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6692307692307692, |
| "eval_loss": 0.1722601354122162, |
| "eval_macro_f1": 0.5433354082106209, |
| "eval_micro_f1": 0.7021276595744681, |
| "eval_precision": 0.7279411764705882, |
| "eval_recall": 0.678082191780822, |
| "eval_runtime": 0.9143, |
| "eval_samples_per_second": 142.181, |
| "eval_steps_per_second": 9.843, |
| "step": 216 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 6480, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 30, |
| "save_steps": 500, |
| "total_flos": 907806492518400.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
