Downloads · 30 days
14
27% of all-time downloads
gokulsrinivasagan/bert_uncased_L-4_H-256_A-4_wnli
bert_uncased_L-4_H-256_A-4_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
14
27% of all-time downloads
All-time downloads
52
Public
Parameters
11.2M
89.4 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors44.7 MB · 98%
From the Hugging Face model README
This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 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 |
|---|---|---|---|---|
| 0.7023 | 1.0 | 3 | 0.7059 | 0.4366 |
| 0.6973 | 2.0 | 6 | 0.7022 | 0.4225 |
| 0.6895 | 3.0 | 9 | 0.7014 | 0.3944 |
| 0.6895 | 4.0 | 12 | 0.7031 | 0.4225 |
| 0.6974 | 5.0 | 15 | 0.7065 | 0.4085 |
| 0.6872 | 6.0 | 18 | 0.7115 | 0.3803 |
| 0.6909 | 7.0 | 21 | 0.7146 | 0.3662 |
| 0.7003 | 8.0 | 24 | 0.7159 | 0.3944 |