Downloads · 30 days
6
17% of all-time downloads
bhagasra-saurav/distilbert-base-uncased-finetuned-char-v3
distilbert-base-uncased-finetuned-char-v3 is a fill-mask model from bhagasra-saurav. 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
6
17% of all-time downloads
All-time downloads
36
Public
Repo size
5.1 GB
Likes
0
Public
Click a slice to open those files.
.bin268 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of distilbert-base-uncased on the None 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 |
|---|---|---|---|
| 2.0288 | 0.59 | 500 | 1.7828 |
| 1.7498 | 1.18 | 1000 | 1.6659 |
| 1.6648 | 1.78 | 1500 | 1.5851 |
| 1.6142 | 2.37 | 2000 | 1.5636 |
| 1.5718 | 2.96 | 2500 | 1.5201 |
| 1.5465 | 3.55 | 3000 | 1.5058 |
| 1.5152 | 4.15 | 3500 | 1.4772 |
| 1.4982 | 4.74 | 4000 | 1.4416 |
| 1.4742 | 5.33 | 4500 | 1.4261 |
| 1.4635 | 5.92 | 5000 | 1.4156 |
| 1.4469 | 6.52 | 5500 | 1.3976 |
| 1.4328 | 7.11 | 6000 | 1.3905 |
| 1.4224 | 7.7 | 6500 | 1.3668 |
| 1.4186 | 8.29 | 7000 | 1.3765 |
| 1.4085 | 8.89 | 7500 | 1.3723 |
| 1.3983 | 9.48 | 8000 | 1.3666 |
| 1.3923 | 10.07 | 8500 | 1.3535 |
| 1.3976 | 10.66 | 9000 | 1.3459 |