File size: 1,164 Bytes
4994314 c9903ef 4994314 c9903ef 4994314 c9903ef 4994314 c9903ef 4994314 c9903ef 4994314 c9903ef 4994314 |
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": 0.7984344422700587,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-96",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 96,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 3.4323604106903076,
"learning_rate": 0.0004667999543114754,
"loss": 0.533,
"step": 96
},
{
"epoch": 1.0,
"eval_accuracy": 0.7984344422700587,
"eval_f1": 0.8049242424242424,
"eval_loss": 0.4442267119884491,
"eval_precision": 0.7798165137614679,
"eval_recall": 0.8317025440313112,
"eval_runtime": 28.6457,
"eval_samples_per_second": 35.677,
"eval_steps_per_second": 1.117,
"step": 96
}
],
"logging_steps": 500,
"max_steps": 192,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.88253398201078,
"learning_rate": 0.0009335999086229508,
"num_train_epochs": 2,
"temperature": 19
}
}
|