|
{ |
|
"best_metric": 0.72, |
|
"best_model_checkpoint": "Bert_tinybert-distilled/run-8/checkpoint-172", |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 172, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 0.4572892487049103, |
|
"learning_rate": 0.00010577448147450072, |
|
"loss": 0.3288, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_AUC": 0.8167893333333334, |
|
"eval_BAC": 0.72, |
|
"eval_MCC": 0.44396404403756623, |
|
"eval_PR_AUC": 0.7738094165898488, |
|
"eval_accuracy": 0.72, |
|
"eval_loss": 0.3125544488430023, |
|
"eval_runtime": 6.1927, |
|
"eval_samples_per_second": 242.222, |
|
"eval_steps_per_second": 7.59, |
|
"step": 172 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 688, |
|
"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": 450377730000.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": { |
|
"alpha": 0.4866820491614119, |
|
"learning_rate": 0.00014103264196600098, |
|
"num_train_epochs": 4, |
|
"temperature": 29 |
|
} |
|
} |
|
|