Downloads · 30 days
5
0% of all-time downloads
diegopetrola/mDeBERTa-mnli-kaggle-contradictory-my-dear-watson
mDeBERTa-mnli-kaggle-contradictory-my-dear-watson is a text classification model from diegopetrola. Use it when you need a label for a piece of text. 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
0% of all-time downloads
All-time downloads
1.2K
Public
Repo size
3.4 GB
Likes
1
Public
Click a slice to open those files.
.bin1.1 GB · 98%
From the Hugging Face model README
This model is a fine-tuned version of MoritzLaurer/mDeBERTa-v3-base-mnli-xnli 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 | Accuracy |
|---|---|---|---|---|
| 0.4778 | 1.0 | 606 | 0.3361 | 0.8899 |
| 0.3766 | 2.0 | 1212 | 0.3217 | 0.8899 |
| 0.344 | 3.0 | 1818 | 0.3218 | 0.8903 |
| 0.3349 | 4.0 | 2424 | 0.3222 | 0.8894 |
| 0.3263 | 5.0 | 3030 | 0.3225 | 0.8890 |