Downloads · 30 days
5
1% of all-time downloads
Billwzl/roberta-base-IMDB_roberta
roberta-base-IMDB_roberta is a fill-mask model from Billwzl. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
5
1% of all-time downloads
All-time downloads
377
Public
Repo size
998 MB
Likes
0
Public
Click a slice to open those files.
.bin499 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of roberta-base 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 |
|---|---|---|---|
| 2.7882 | 1.0 | 1250 | 2.4751 |
| 2.5749 | 2.0 | 2500 | 2.4183 |
| 2.4501 | 3.0 | 3750 | 2.3799 |
| 2.3697 | 4.0 | 5000 | 2.3792 |
| 2.3187 | 5.0 | 6250 | 2.3622 |
| 2.24 | 6.0 | 7500 | 2.3491 |
| 2.164 | 7.0 | 8750 | 2.3146 |
| 2.1187 | 8.0 | 10000 | 2.2804 |
| 2.0552 | 9.0 | 11250 | 2.2629 |
| 2.0285 | 10.0 | 12500 | 2.2088 |
| 1.9807 | 11.0 | 13750 | 2.2061 |
| 1.9597 | 12.0 | 15000 | 2.2094 |
| 1.9062 | 13.0 | 16250 | 2.1486 |
| 1.8766 | 14.0 | 17500 | 2.1348 |
| 1.8528 | 15.0 | 18750 | 2.1665 |
| 1.8425 | 16.0 | 20000 | 2.1897 |