Downloads · 30 days
8
2% of all-time downloads
jojoUla/bert-large-cased-sigir-support-no-label-20-sigir-tune2nd-LR10-labelled-30
bert-large-cased-sigir-support-no-label-20-sigir-tune2nd-LR10-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
8
2% of all-time downloads
All-time downloads
348
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-no-label-20 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 |
|---|---|---|---|
| 2.1303 | 1.0 | 1 | 3.2415 |
| 2.3107 | 2.0 | 2 | 2.1225 |
| 1.2824 | 3.0 | 3 | 2.2623 |
| 1.0548 | 4.0 | 4 | 0.5449 |
| 1.1366 | 5.0 | 5 | 1.1446 |
| 0.5947 | 6.0 | 6 | 0.3811 |
| 0.4889 | 7.0 | 7 | 1.6445 |
| 1.2689 | 8.0 | 8 | 1.7214 |
| 0.8074 | 9.0 | 9 | 2.3152 |
| 0.7084 | 10.0 | 10 | 0.9325 |
| 1.0307 | 11.0 | 11 | 2.4217 |
| 0.7119 | 12.0 | 12 | 2.6455 |
| 1.0052 | 13.0 | 13 | 1.1594 |
| 0.7125 | 14.0 | 14 | 1.2795 |
| 0.4732 | 15.0 | 15 | 0.1245 |
| 0.8829 | 16.0 | 16 | 1.8585 |
| 0.7079 | 17.0 | 17 | 1.6644 |
| 0.6243 | 18.0 | 18 | 1.6117 |
| 1.2438 | 19.0 | 19 | 2.3044 |
| 1.0812 | 20.0 | 20 | 4.5037 |
| 0.7003 | 21.0 | 21 | 1.5862 |
| 0.867 | 22.0 | 22 | 2.1851 |
| 0.9098 | 23.0 | 23 | 1.6055 |
| 0.6214 | 24.0 | 24 | 2.6699 |
| 0.282 | 25.0 | 25 | 1.3515 |
| 0.1888 | 26.0 | 26 | 2.3864 |
| 0.6863 | 27.0 | 27 | 1.2444 |
| 0.8527 | 28.0 | 28 | 1.9603 |
| 0.9416 | 29.0 | 29 | 3.7045 |
| 0.8302 | 30.0 | 30 | 0.9336 |