File size: 1,213 Bytes
d5333d9 |
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": 0.7287639132981839,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-28/checkpoint-214",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 214,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 5.574616432189941,
"learning_rate": 0.00036655879725586745,
"loss": 0.5539,
"step": 214
},
{
"epoch": 1.0,
"eval_accuracy": 0.7287639132981839,
"eval_f1": 0.43742405832320774,
"eval_loss": 0.5075973272323608,
"eval_mcc": 0.3328904757496092,
"eval_precision": 0.7086614173228346,
"eval_recall": 0.3163444639718805,
"eval_runtime": 3.1198,
"eval_samples_per_second": 547.147,
"eval_steps_per_second": 17.309,
"step": 214
}
],
"logging_steps": 500,
"max_steps": 1712,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 500,
"total_flos": 524775664440.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.9057585906996103,
"learning_rate": 0.0004189243397209914,
"num_train_epochs": 8,
"temperature": 28
}
}
|