Downloads · 30 days
71
15% of all-time downloads
muhtasham/small-mlm-glue-qnli-from-scratch-custom-tokenizer-expand-vocab
small-mlm-glue-qnli-from-scratch-custom-tokenizer-expand-vocab 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. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
71
15% of all-time downloads
All-time downloads
467
Public
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.bin145 MB · 97%
From the Hugging Face model README
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 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 |
|---|---|---|---|
| 7.6626 | 0.4 | 500 | 6.7278 |
| 6.5829 | 0.8 | 1000 | 6.5388 |
| 6.4637 | 1.2 | 1500 | 6.3776 |
| 6.3446 | 1.6 | 2000 | 6.2966 |
| 6.2664 | 2.0 | 2500 | 6.2288 |
| 6.2043 | 2.4 | 3000 | 6.1839 |
| 6.1615 | 2.8 | 3500 | 6.1349 |
| 6.1085 | 3.2 | 4000 | 6.0839 |
| 6.0625 | 3.6 | 4500 | 6.0543 |
| 6.0432 | 4.0 | 5000 | 6.0244 |