| { |
| "best_metric": 1.0, |
| "best_model_checkpoint": "./roberta-kor-cls-jsonl/checkpoint-96", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 192, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5208333333333334, |
| "grad_norm": 0.22559186816215515, |
| "learning_rate": 1.990740740740741e-05, |
| "loss": 0.908, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 1.0, |
| "eval_f1_macro": 1.0, |
| "eval_loss": 0.0010595795465633273, |
| "eval_runtime": 0.3804, |
| "eval_samples_per_second": 1006.958, |
| "eval_steps_per_second": 31.55, |
| "step": 96 |
| }, |
| { |
| "epoch": 1.0416666666666667, |
| "grad_norm": 0.02184768207371235, |
| "learning_rate": 1.7592592592592595e-05, |
| "loss": 0.0046, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5625, |
| "grad_norm": 0.013300820253789425, |
| "learning_rate": 1.5277777777777777e-05, |
| "loss": 0.0015, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 1.0, |
| "eval_f1_macro": 1.0, |
| "eval_loss": 0.0005370556027628481, |
| "eval_runtime": 0.3421, |
| "eval_samples_per_second": 1119.696, |
| "eval_steps_per_second": 35.082, |
| "step": 192 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 480, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 169866234738762.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
