|
{ |
|
"best_metric": 2.187363862991333, |
|
"best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-2/checkpoint-170", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 170, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.15225225225225225, |
|
"eval_f1": 0.02484055052030883, |
|
"eval_loss": 4.083955764770508, |
|
"eval_precision": 0.027106227106227107, |
|
"eval_recall": 0.02292441140024783, |
|
"eval_runtime": 0.593, |
|
"eval_samples_per_second": 490.762, |
|
"eval_steps_per_second": 62.399, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.5099099099099099, |
|
"eval_f1": 0.2670894996476392, |
|
"eval_loss": 2.187363862991333, |
|
"eval_precision": 0.309640522875817, |
|
"eval_recall": 0.23482032218091697, |
|
"eval_runtime": 0.3979, |
|
"eval_samples_per_second": 731.333, |
|
"eval_steps_per_second": 92.987, |
|
"step": 170 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1020, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 12, |
|
"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": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 4.546321141328063e-05, |
|
"num_train_epochs": 12, |
|
"per_device_train_batch_size": 16, |
|
"warmup_steps": 207, |
|
"weight_decay": 0.23618328311920675 |
|
} |
|
} |
|
|