short_name / trainer_state.json
Bisher's picture
End of training
047a21a verified
{
"best_metric": 0.8499896205743283,
"best_model_checkpoint": "/kaggle/working/short_name/checkpoint-1",
"epoch": 0.04,
"eval_steps": 1,
"global_step": 1,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"grad_norm": 1.5162408351898193,
"learning_rate": 6e-06,
"loss": 0.6767,
"step": 1
},
{
"epoch": 0.04,
"eval_EER": 0.27272727272733843,
"eval_FN": 21,
"eval_FP": 0,
"eval_TN": 178,
"eval_TP": 1,
"eval_accuracy": 0.895,
"eval_auc_roc": 0.7295709908069459,
"eval_f1": 0.8499896205743283,
"eval_loss": 0.5552121996879578,
"eval_min_tDCF": 0.028064351378958123,
"eval_precision": 0.9060804020100502,
"eval_recall": 0.895,
"eval_runtime": 66.7052,
"eval_samples_per_second": 2.998,
"eval_steps_per_second": 2.998,
"step": 1
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 1,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 2,
"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": 75688006121100.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}