Downloads · 30 days
9
19% of all-time downloads
jojoUla/bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-20-0
bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-20-0 is a fill-mask model from jojoUla. Use it when you need the model to fill a missing word. 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
19% of all-time downloads
All-time downloads
47
Public
Repo size
2.7 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of jojoUla/bert-large-cased-sigir-support-refute-no-label-40 on an unknown 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 |
|---|---|---|---|
| 3.3658 | 1.0 | 1 | 4.5617 |
| 3.5713 | 2.0 | 2 | 2.5325 |
| 2.2843 | 3.0 | 3 | 0.0030 |
| 1.7965 | 4.0 | 4 | 2.3831 |
| 2.0354 | 5.0 | 5 | 3.4912 |
| 1.2277 | 6.0 | 6 | 1.3851 |
| 1.2321 | 7.0 | 7 | 1.9236 |
| 0.4967 | 8.0 | 8 | 1.0605 |
| 1.0384 | 9.0 | 9 | 0.3916 |
| 0.7269 | 10.0 | 10 | 0.0062 |
| 1.2502 | 11.0 | 11 | 1.8639 |
| 1.4578 | 12.0 | 12 | 2.0197 |
| 1.2226 | 13.0 | 13 | 0.6885 |
| 0.6376 | 14.0 | 14 | 1.1868 |
| 0.5083 | 15.0 | 15 | 2.9677 |
| 0.9882 | 16.0 | 16 | 0.0010 |
| 0.6176 | 17.0 | 17 | 0.2418 |
| 0.4591 | 18.0 | 18 | 0.0004 |
| 0.1891 | 19.0 | 19 | 1.8797 |
| 0.3319 | 20.0 | 20 | 1.4692 |