File size: 1,217 Bytes
f03a0a9 |
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": 0.5366336633663367,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-41/checkpoint-297",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 297,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.0725367069244385,
"learning_rate": 0.00020209984458518428,
"loss": 0.6597,
"step": 297
},
{
"epoch": 1.0,
"eval_accuracy": 0.5366336633663367,
"eval_f1": 0.31176470588235294,
"eval_loss": 0.6622546911239624,
"eval_mcc": 0.09487420793018501,
"eval_precision": 0.6022727272727273,
"eval_recall": 0.21031746031746032,
"eval_runtime": 0.9278,
"eval_samples_per_second": 544.286,
"eval_steps_per_second": 17.245,
"step": 297
}
],
"logging_steps": 500,
"max_steps": 2079,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 500,
"total_flos": 730701265980.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.9417813739243972,
"learning_rate": 0.00023578315201604834,
"num_train_epochs": 7,
"temperature": 19
}
}
|