| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8382229673093042, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4191114836546521, |
| "grad_norm": 0.951872706413269, |
| "learning_rate": 4.4761106454316845e-05, |
| "loss": 1.8004, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4191114836546521, |
| "eval_CEFR_f1": 0.3384662, |
| "eval_loss": 1.1508616209030151, |
| "eval_rouge1": 0.48, |
| "eval_rouge2": 0.29292929, |
| "eval_runtime": 15.0767, |
| "eval_samples_per_second": 6.633, |
| "eval_steps_per_second": 0.265, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8382229673093042, |
| "grad_norm": 1.0152556896209717, |
| "learning_rate": 3.95222129086337e-05, |
| "loss": 1.2466, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8382229673093042, |
| "eval_CEFR_f1": 0.32371507, |
| "eval_loss": 1.0748347043991089, |
| "eval_rouge1": 0.5, |
| "eval_rouge2": 0.32323232, |
| "eval_runtime": 15.1501, |
| "eval_samples_per_second": 6.601, |
| "eval_steps_per_second": 0.264, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4772, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 1.9193866223616e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
