hBERTv1_new_pretrain_48_ver2_qnli

作者 gokuls · 下载 0 · 点赞 0 · 更新 2023-11-04

generated_from_trainer

hBERTv1_new_pretrain_48_ver2_qnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6982 1.0 1637 0.6940 0.5054
0.6941 2.0 3274 0.6932 0.4946
0.6938 3.0 4911 0.6933 0.4946
0.6936 4.0 6548 0.6931 0.5054
0.6934 5.0 8185 0.6936 0.4946
0.6934 6.0 9822 0.6936 0.4946
0.6934 7.0 11459 0.6931 0.5054
0.6932 8.0 13096 0.6931 0.4946
0.6932 9.0 14733 0.6935 0.5054
0.6932 10.0 16370 0.6932 0.4946
0.6932 11.0 18007 0.6931 0.5054
0.6932 12.0 19644 0.6932 0.4946

Framework versions