Downloads · 30 days
4
7% of all-time downloads
prateeky2806/bert-base-uncased-wnli-epochs-10-lr-0.0001
bert-base-uncased-wnli-epochs-10-lr-0.0001 is a text classification model from prateeky2806. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
4
7% of all-time downloads
All-time downloads
61
Public
Parameters
109M
2.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors438 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of bert-base-uncased on the glue 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 |
|---|---|---|---|---|
| No log | 1.0 | 17 | 0.7353 | 0.35 |
| No log | 2.0 | 34 | 0.7247 | 0.43 |
| No log | 3.0 | 51 | 0.7062 | 0.43 |
| No log | 4.0 | 68 | 0.6870 | 0.57 |
| No log | 5.0 | 85 | 0.6935 | 0.47 |
| No log | 6.0 | 102 | 0.6891 | 0.57 |
| No log | 7.0 | 119 | 0.6949 | 0.44 |
| No log | 8.0 | 136 | 0.6996 | 0.43 |
| No log | 9.0 | 153 | 0.6981 | 0.42 |
| No log | 10.0 | 170 | 0.6970 | 0.36 |