File size: 1,217 Bytes
88c187f |
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-5/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": 0.14799009263515472,
"learning_rate": 3.564708186391241e-05,
"loss": 0.0771,
"step": 297
},
{
"epoch": 1.0,
"eval_accuracy": 0.5089108910891089,
"eval_f1": 0.1205673758865248,
"eval_loss": 0.058570001274347305,
"eval_mcc": 0.03400602754322123,
"eval_precision": 0.5666666666666667,
"eval_recall": 0.06746031746031746,
"eval_runtime": 0.9363,
"eval_samples_per_second": 539.332,
"eval_steps_per_second": 17.088,
"step": 297
}
],
"logging_steps": 500,
"max_steps": 891,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 730701265980.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.06013810150880572,
"learning_rate": 5.3470622795868616e-05,
"num_train_epochs": 3,
"temperature": 28
}
}
|