File size: 1,208 Bytes
a4f54f7 |
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": 0.7407045009784736,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-54",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 54,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 3.1670913696289062,
"learning_rate": 0.0002855230244841258,
"loss": 0.5191,
"step": 54
},
{
"epoch": 1.0,
"eval_accuracy": 0.7407045009784736,
"eval_f1": 0.7881694644284573,
"eval_loss": 0.47280439734458923,
"eval_precision": 0.6662162162162162,
"eval_recall": 0.9647749510763209,
"eval_runtime": 29.2616,
"eval_samples_per_second": 34.926,
"eval_steps_per_second": 1.094,
"step": 54
}
],
"logging_steps": 500,
"max_steps": 270,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 57,
"trial_name": null,
"trial_params": {
"alpha": 0.7778146133600564,
"learning_rate": 0.0003569037806051572,
"num_train_epochs": 5,
"per_device_train_batch_size": 57,
"temperature": 18
}
}
|