|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 22741, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 2.555318593978882, |
|
"learning_rate": 1.3333333333333333e-05, |
|
"loss": 0.2948, |
|
"step": 22741 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9004946821667079, |
|
"eval_combined_score": 0.8834400741532002, |
|
"eval_f1": 0.8663854661396925, |
|
"eval_loss": 0.24696190655231476, |
|
"eval_runtime": 173.6065, |
|
"eval_samples_per_second": 232.883, |
|
"eval_steps_per_second": 29.112, |
|
"step": 22741 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 68223, |
|
"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": 9.573190504851456e+16, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|