Downloads · 30 days
9
26% of all-time downloads
gokulsrinivasagan/bert_uncased_L-4_H-512_A-8_wnli
bert_uncased_L-4_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
9
26% of all-time downloads
All-time downloads
34
Public
Parameters
28.8M
115 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors115 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of google/bert_uncased_L-4_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 |
|---|---|---|---|---|
| 0.712 | 1.0 | 3 | 0.7333 | 0.2535 |
| 0.7016 | 2.0 | 6 | 0.7344 | 0.4366 |
| 0.6925 | 3.0 | 9 | 0.7545 | 0.2113 |
| 0.6904 | 4.0 | 12 | 0.7700 | 0.2394 |
| 0.6891 | 5.0 | 15 | 0.7776 | 0.1831 |
| 0.6948 | 6.0 | 18 | 0.7863 | 0.1690 |