File size: 1,211 Bytes
ee6deae |
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": 0.5089108910891089,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/checkpoint-244",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 244,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.8588551878929138,
"learning_rate": 0.0001547989976805511,
"loss": 0.5028,
"step": 244
},
{
"epoch": 1.0,
"eval_accuracy": 0.5089108910891089,
"eval_f1": 0.1205673758865248,
"eval_loss": 0.504381000995636,
"eval_precision": 0.5666666666666667,
"eval_recall": 0.06746031746031746,
"eval_runtime": 14.9415,
"eval_samples_per_second": 33.799,
"eval_steps_per_second": 1.071,
"step": 244
}
],
"logging_steps": 500,
"max_steps": 1708,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 500,
"total_flos": 777843283140.0,
"train_batch_size": 39,
"trial_name": null,
"trial_params": {
"alpha": 0.6658046915260407,
"learning_rate": 0.0001805988306273096,
"num_train_epochs": 7,
"per_device_train_batch_size": 39,
"temperature": 15
}
}
|