Downloads · 30 days
6
15% of all-time downloads
gokulsrinivasagan/bert_uncased_L-2_H-512_A-8_wnli
bert_uncased_L-2_H-512_A-8_wnli is a text classification model from gokulsrinivasagan. 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
6
15% of all-time downloads
All-time downloads
40
Public
Parameters
22.5M
89.9 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors89.8 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of google/bert_uncased_L-2_H-512_A-8 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 |
|---|---|---|---|---|
| 0.709 | 1.0 | 3 | 0.7026 | 0.4507 |
| 0.6989 | 2.0 | 6 | 0.7127 | 0.4085 |
| 0.6959 | 3.0 | 9 | 0.7356 | 0.3239 |
| 0.692 | 4.0 | 12 | 0.7549 | 0.3099 |
| 0.6833 | 5.0 | 15 | 0.7649 | 0.2817 |
| 0.6881 | 6.0 | 18 | 0.7724 | 0.2958 |