| { |
| "best_global_step": 166, |
| "best_metric": 0.262949675321579, |
| "best_model_checkpoint": "./math_ner_roberta/checkpoint-166", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 166, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6024096385542169, |
| "grad_norm": 4.988605499267578, |
| "learning_rate": 2.4096385542168674e-05, |
| "loss": 1.4176820373535157, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.3655608594417572, |
| "eval_runtime": 3.3968, |
| "eval_samples_per_second": 68.595, |
| "eval_steps_per_second": 4.416, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.2048192771084336, |
| "grad_norm": 18.059431076049805, |
| "learning_rate": 1.807228915662651e-05, |
| "loss": 0.5126217651367188, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.8072289156626506, |
| "grad_norm": 7.703867435455322, |
| "learning_rate": 1.2048192771084337e-05, |
| "loss": 0.48525764465332033, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.262949675321579, |
| "eval_runtime": 3.348, |
| "eval_samples_per_second": 69.594, |
| "eval_steps_per_second": 4.48, |
| "step": 166 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 249, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 496258845421920.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
