File size: 1,168 Bytes
0cdda70 |
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": 0.7690802348336595,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/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": 3.696702480316162,
"learning_rate": 5.5657923048038e-05,
"loss": 0.5322,
"step": 766
},
{
"epoch": 1.0,
"eval_accuracy": 0.7690802348336595,
"eval_f1": 0.7962003454231433,
"eval_loss": 0.4672633707523346,
"eval_precision": 0.7125193199381762,
"eval_recall": 0.9021526418786693,
"eval_runtime": 130.6713,
"eval_samples_per_second": 7.821,
"eval_steps_per_second": 1.959,
"step": 766
}
],
"logging_steps": 500,
"max_steps": 6128,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"alpha": 0.838703892208557,
"learning_rate": 6.360905491204343e-05,
"num_train_epochs": 8,
"temperature": 22
}
}
|