Downloads · 30 days
5
2% of all-time downloads
jojoUla/bert-large-cased-sigir-support-no-label-40-sigir-tune2nd-LR100-labelled-30
bert-large-cased-sigir-support-no-label-40-sigir-tune2nd-LR100-labelled-30 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
5
2% of all-time downloads
All-time downloads
300
Public
Repo size
4 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-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 |
|---|---|---|---|
| 4.8321 | 1.0 | 2 | 4.3250 |
| 3.383 | 2.0 | 4 | 2.4023 |
| 1.9548 | 3.0 | 6 | 1.2925 |
| 1.4856 | 4.0 | 8 | 1.5152 |
| 0.9588 | 5.0 | 10 | 1.7731 |
| 1.2668 | 6.0 | 12 | 1.3830 |
| 0.8441 | 7.0 | 14 | 1.9760 |
| 1.0173 | 8.0 | 16 | 1.2364 |
| 0.6814 | 9.0 | 18 | 1.1771 |
| 0.9044 | 10.0 | 20 | 1.4721 |
| 0.6889 | 11.0 | 22 | 0.8518 |
| 0.5845 | 12.0 | 24 | 0.6993 |
| 0.4068 | 13.0 | 26 | 1.1771 |
| 0.5957 | 14.0 | 28 | 0.5895 |
| 0.4277 | 15.0 | 30 | 0.5326 |
| 0.3736 | 16.0 | 32 | 1.0893 |
| 0.413 | 17.0 | 34 | 1.3267 |
| 0.5718 | 18.0 | 36 | 1.0331 |
| 0.3892 | 19.0 | 38 | 1.0793 |
| 0.3913 | 20.0 | 40 | 0.8742 |
| 0.4794 | 21.0 | 42 | 1.1264 |
| 0.4626 | 22.0 | 44 | 1.1857 |
| 0.2683 | 23.0 | 46 | 1.5181 |
| 0.3436 | 24.0 | 48 | 1.4419 |
| 0.3793 | 25.0 | 50 | 1.4198 |
| 0.356 | 26.0 | 52 | 1.1776 |
| 0.2189 | 27.0 | 54 | 0.7166 |
| 0.286 | 28.0 | 56 | 0.7601 |
| 0.3681 | 29.0 | 58 | 1.2592 |
| 0.5858 | 30.0 | 60 | 0.6520 |