| { |
| "best_metric": 1.0, |
| "best_model_checkpoint": "hf-importance-production/checkpoint-48", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.20833333333333334, |
| "grad_norm": 29.484235763549805, |
| "learning_rate": 2.1276595744680853e-06, |
| "loss": 0.139, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4166666666666667, |
| "grad_norm": 0.19761385023593903, |
| "learning_rate": 4.255319148936171e-06, |
| "loss": 0.0851, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 75.20068359375, |
| "learning_rate": 6.382978723404256e-06, |
| "loss": 0.2067, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 0.0050959475338459015, |
| "learning_rate": 8.510638297872341e-06, |
| "loss": 0.2117, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_f1_macro": 1.0, |
| "eval_loss": 0.19008873403072357, |
| "eval_precision": 1.0, |
| "eval_precision_macro": 1.0, |
| "eval_recall": 1.0, |
| "eval_recall_macro": 1.0, |
| "eval_runtime": 0.5835, |
| "eval_samples_per_second": 1.714, |
| "eval_steps_per_second": 1.714, |
| "step": 48 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 96, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 1, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 49728435950592.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
