ana-grassmann's picture
End of training
d2ab612 verified
{
"best_metric": 0.53,
"best_model_checkpoint": "bert-finetuned-spam/run-1/checkpoint-225",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 225,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.4444444444444444,
"grad_norm": 5.394330024719238,
"learning_rate": 2.3433418555055753e-06,
"loss": 0.772,
"step": 100
},
{
"epoch": 0.8888888888888888,
"grad_norm": 8.030879974365234,
"learning_rate": 2.1147231378952755e-06,
"loss": 0.7601,
"step": 200
},
{
"epoch": 1.0,
"eval_accuracy": 0.53,
"eval_loss": 0.7192578315734863,
"eval_runtime": 2.7838,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 17.961,
"step": 225
}
],
"logging_steps": 100,
"max_steps": 1125,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 100,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 223659383193600.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"learning_rate": 2.5719605731158755e-06,
"num_train_epochs": 5,
"per_device_train_batch_size": 4,
"seed": 19
}
}