File size: 1,194 Bytes
fa1876e |
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": 0.5430528375733855,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-88",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 88,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.4811249077320099,
"learning_rate": 6.084357840038042e-05,
"loss": 0.24,
"step": 88
},
{
"epoch": 1.0,
"eval_accuracy": 0.5430528375733855,
"eval_f1": 0.2098138747884941,
"eval_loss": 0.21115726232528687,
"eval_precision": 0.775,
"eval_recall": 0.12133072407045009,
"eval_runtime": 31.2118,
"eval_samples_per_second": 32.744,
"eval_steps_per_second": 1.025,
"step": 88
}
],
"logging_steps": 500,
"max_steps": 880,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 35,
"trial_name": null,
"trial_params": {
"alpha": 0.2634542499188758,
"learning_rate": 6.760397600042269e-05,
"num_train_epochs": 10,
"per_device_train_batch_size": 35,
"temperature": 2
}
}
|