File size: 1,215 Bytes
ce8b57e |
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": 0.5108910891089109,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/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": 0.2929101288318634,
"learning_rate": 0.00019613269922119723,
"loss": 0.2283,
"step": 297
},
{
"epoch": 1.0,
"eval_accuracy": 0.5108910891089109,
"eval_f1": 0.127208480565371,
"eval_loss": 0.21940745413303375,
"eval_mcc": 0.04175421326407947,
"eval_precision": 0.5806451612903226,
"eval_recall": 0.07142857142857142,
"eval_runtime": 0.9418,
"eval_samples_per_second": 536.223,
"eval_steps_per_second": 16.989,
"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": 0.26537240375624915,
"learning_rate": 0.00029419904883179585,
"num_train_epochs": 3,
"temperature": 34
}
}
|