File size: 1,210 Bytes
f78a1ad |
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 47 |
{
"best_metric": 0.7720156555772995,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-49",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 49,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.3073023557662964,
"learning_rate": 0.00021800841920007835,
"loss": 0.5666,
"step": 49
},
{
"epoch": 1.0,
"eval_accuracy": 0.7720156555772995,
"eval_f1": 0.8010247651579846,
"eval_loss": 0.48246321082115173,
"eval_precision": 0.7106060606060606,
"eval_recall": 0.9178082191780822,
"eval_runtime": 28.2754,
"eval_samples_per_second": 36.145,
"eval_steps_per_second": 1.132,
"step": 49
}
],
"logging_steps": 500,
"max_steps": 245,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 63,
"trial_name": null,
"trial_params": {
"alpha": 0.8444228810359851,
"learning_rate": 0.00027251052400009793,
"num_train_epochs": 5,
"per_device_train_batch_size": 63,
"temperature": 21
}
}
|