Downloads · 30 days
26
7% of all-time downloads
muhtasham/tiny-mlm-conll2003-from-scratch-custom-tokenizer
tiny-mlm-conll2003-from-scratch-custom-tokenizer is a fill-mask model from muhtasham. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
26
7% of all-time downloads
All-time downloads
365
Public
Repo size
166 MB
Likes
0
Public
Click a slice to open those files.
.bin15.1 MB · 95%
From the Hugging Face model README
This model is a fine-tuned version of 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 |
|---|---|---|---|
| 9.5926 | 0.4 | 500 | 9.1567 |
| 8.6036 | 0.8 | 1000 | 8.7359 |
| 8.1599 | 1.2 | 1500 | 8.6431 |
| 8.0784 | 1.6 | 2000 | 8.6149 |
| 7.997 | 2.0 | 2500 | 8.6430 |
| 7.9471 | 2.4 | 3000 | 8.5456 |
| 7.8594 | 2.8 | 3500 | 8.5678 |
| 7.8369 | 3.2 | 4000 | 8.5657 |
| 7.8061 | 3.6 | 4500 | 8.5285 |
| 7.8486 | 4.0 | 5000 | 8.4929 |