File size: 1,173 Bytes
8e81f73 |
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": 0.7896281800391389,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/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": 1.943489909172058,
"learning_rate": 9.076816597122249e-05,
"loss": 0.4823,
"step": 766
},
{
"epoch": 1.0,
"eval_accuracy": 0.7896281800391389,
"eval_f1": 0.8125544899738447,
"eval_loss": 0.43095502257347107,
"eval_precision": 0.7327044025157232,
"eval_recall": 0.9119373776908023,
"eval_runtime": 132.0712,
"eval_samples_per_second": 7.738,
"eval_steps_per_second": 1.938,
"step": 766
}
],
"logging_steps": 500,
"max_steps": 4596,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"alpha": 0.7464330126775673,
"learning_rate": 0.00010892179916546698,
"num_train_epochs": 6,
"temperature": 11
}
}
|