Downloads · 30 days
9
4% of all-time downloads
gokuls/hBERTv2_new_pretrain_48_cola
hBERTv2_new_pretrain_48_cola 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
9
4% of all-time downloads
All-time downloads
205
Public
Repo size
1.4 GB
Likes
0
Public
Click a slice to open those files.
.bin477 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48 on the GLUE COLA 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 | Matthews Correlation |
|---|---|---|---|---|
| 0.6319 | 1.0 | 67 | 0.6185 | 0.0 |
| 0.6208 | 2.0 | 134 | 0.6358 | 0.0 |
| 0.6124 | 3.0 | 201 | 0.6174 | 0.0 |
| 0.6048 | 4.0 | 268 | 0.6443 | 0.0 |
| 0.5847 | 5.0 | 335 | 0.6521 | -0.0207 |
| 0.5739 | 6.0 | 402 | 0.6336 | 0.0667 |
| 0.5562 | 7.0 | 469 | 0.6433 | -0.0110 |
| 0.54 | 8.0 | 536 | 0.6524 | 0.0910 |