File size: 1,172 Bytes
c0214d5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
{
"best_metric": 0.6594911937377691,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-766",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 766,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.387345790863037,
"learning_rate": 9.274722577647405e-06,
"loss": 0.6719,
"step": 766
},
{
"epoch": 1.0,
"eval_accuracy": 0.6594911937377691,
"eval_f1": 0.5786924939467312,
"eval_loss": 0.6500130891799927,
"eval_precision": 0.7587301587301587,
"eval_recall": 0.46771037181996084,
"eval_runtime": 133.0073,
"eval_samples_per_second": 7.684,
"eval_steps_per_second": 1.925,
"step": 766
}
],
"logging_steps": 500,
"max_steps": 3830,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"alpha": 0.9677948459483069,
"learning_rate": 1.1593403222059255e-05,
"num_train_epochs": 5,
"temperature": 2
}
}
|