Downloads · 30 days
6
12% of all-time downloads
gokuls/hBERTv1_new_pretrain_48_ver2_wnli
hBERTv1_new_pretrain_48_ver2_wnli is a text classification model from gokuls. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
6
12% of all-time downloads
All-time downloads
49
Public
Repo size
962 MB
Likes
0
Public
Click a slice to open those files.
.bin481 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7332 | 1.0 | 10 | 0.7386 | 0.4366 |
| 0.7093 | 2.0 | 20 | 0.7002 | 0.4366 |
| 0.7175 | 3.0 | 30 | 0.7295 | 0.4366 |
| 0.7044 | 4.0 | 40 | 0.7007 | 0.4366 |
| 0.6906 | 5.0 | 50 | 0.7484 | 0.4366 |
| 0.7095 | 6.0 | 60 | 0.7177 | 0.4366 |
| 0.7201 | 7.0 | 70 | 0.7029 | 0.5634 |