ana-grassmann's picture
End of training
d2ab612 verified
{
"best_metric": 0.4,
"best_model_checkpoint": "bert-finetuned-spam/run-0/checkpoint-15",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 30,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.4,
"eval_loss": 0.7362109422683716,
"eval_runtime": 2.7928,
"eval_samples_per_second": 35.806,
"eval_steps_per_second": 17.903,
"step": 15
},
{
"epoch": 2.0,
"eval_accuracy": 0.4,
"eval_loss": 0.7354491949081421,
"eval_runtime": 2.7991,
"eval_samples_per_second": 35.726,
"eval_steps_per_second": 17.863,
"step": 30
}
],
"logging_steps": 100,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": {
"learning_rate": 1.4509031354139346e-06,
"num_train_epochs": 2,
"per_device_train_batch_size": 64,
"seed": 40
}
}