|
{ |
|
"best_metric": 0.7984496124031008, |
|
"best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-97", |
|
"epoch": 4.0, |
|
"eval_steps": 500, |
|
"global_step": 97, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.9896907216494846, |
|
"eval_accuracy": 0.6356589147286822, |
|
"eval_f1": 0.5920563016978556, |
|
"eval_loss": 0.980873703956604, |
|
"eval_precision": 0.5920482291587493, |
|
"eval_recall": 0.6356589147286822, |
|
"eval_runtime": 1.6668, |
|
"eval_samples_per_second": 232.175, |
|
"eval_steps_per_second": 29.397, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 1.9793814432989691, |
|
"eval_accuracy": 0.7157622739018088, |
|
"eval_f1": 0.6905410405322238, |
|
"eval_loss": 0.7444477081298828, |
|
"eval_precision": 0.6992377248989063, |
|
"eval_recall": 0.7157622739018088, |
|
"eval_runtime": 1.6941, |
|
"eval_samples_per_second": 228.443, |
|
"eval_steps_per_second": 28.924, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 2.9690721649484537, |
|
"eval_accuracy": 0.7493540051679587, |
|
"eval_f1": 0.744898505571463, |
|
"eval_loss": 0.6171658039093018, |
|
"eval_precision": 0.7437592422989429, |
|
"eval_recall": 0.7493540051679587, |
|
"eval_runtime": 1.6943, |
|
"eval_samples_per_second": 228.408, |
|
"eval_steps_per_second": 28.92, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.7984496124031008, |
|
"eval_f1": 0.7873621619744228, |
|
"eval_loss": 0.5430988073348999, |
|
"eval_precision": 0.79180344284319, |
|
"eval_recall": 0.7984496124031008, |
|
"eval_runtime": 1.7027, |
|
"eval_samples_per_second": 227.289, |
|
"eval_steps_per_second": 28.778, |
|
"step": 97 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 360, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 15, |
|
"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": 1.40547201408e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|