|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 623, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.8025682182985554, |
|
"grad_norm": 1.1916083097457886, |
|
"learning_rate": 1.4199529322582399e-05, |
|
"loss": 0.1878, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9576256116756785, |
|
"eval_f1": 0.8142311365807068, |
|
"eval_loss": 0.11338457465171814, |
|
"eval_precision": 0.771405949553218, |
|
"eval_recall": 0.8620907597016813, |
|
"eval_runtime": 24.3416, |
|
"eval_samples_per_second": 175.256, |
|
"eval_steps_per_second": 21.938, |
|
"step": 623 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 623, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 778944511139520.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 7.192119323551898e-05, |
|
"num_train_epochs": 1, |
|
"per_device_train_batch_size": 32, |
|
"seed": 34 |
|
} |
|
} |
|
|