|
{ |
|
"best_metric": 0.5135559583730447, |
|
"best_model_checkpoint": "students_scores_model/run-1/checkpoint-282", |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 282, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_f1": 0.5135559583730447, |
|
"eval_loss": 1.0615456104278564, |
|
"eval_runtime": 37.678, |
|
"eval_samples_per_second": 59.716, |
|
"eval_steps_per_second": 7.484, |
|
"step": 282 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1410, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"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": 0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 1.3228889953650998e-05, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 32, |
|
"weight_decay": 0.0004860339799795757 |
|
} |
|
} |
|
|