|
{ |
|
"best_metric": 0.9897435897435898, |
|
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341", |
|
"epoch": 3.994143484626647, |
|
"eval_steps": 500, |
|
"global_step": 341, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.9956076134699854, |
|
"eval_accuracy": 0.9772893772893773, |
|
"eval_loss": 0.06922276318073273, |
|
"eval_runtime": 15.5305, |
|
"eval_samples_per_second": 87.892, |
|
"eval_steps_per_second": 11.011, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 1.9912152269399708, |
|
"eval_accuracy": 0.9860805860805861, |
|
"eval_loss": 0.04661192744970322, |
|
"eval_runtime": 15.4605, |
|
"eval_samples_per_second": 88.29, |
|
"eval_steps_per_second": 11.06, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 2.998535871156662, |
|
"eval_accuracy": 0.9853479853479854, |
|
"eval_loss": 0.04894961416721344, |
|
"eval_runtime": 15.5622, |
|
"eval_samples_per_second": 87.713, |
|
"eval_steps_per_second": 10.988, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 3.994143484626647, |
|
"eval_accuracy": 0.9897435897435898, |
|
"eval_loss": 0.04228556528687477, |
|
"eval_runtime": 15.6217, |
|
"eval_samples_per_second": 87.378, |
|
"eval_steps_per_second": 10.946, |
|
"step": 341 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 850, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 3, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.966803039744e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|