Downloads · 30 days
8
10% of all-time downloads
Kuongan/Hal_mDeBERTa-v3-base-xnli-multilingual-nli-2mil7_finetuned
Hal_mDeBERTa-v3-base-xnli-multilingual-nli-2mil7_finetuned is a text classification model from Kuongan. 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
8
10% of all-time downloads
All-time downloads
78
Public
Parameters
279M
7.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 98%
From the Hugging Face model README
This model is a fine-tuned version of MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6185 | 1.0 | 700 | 0.6687 | 0.7571 | 0.7571 |
| 0.5259 | 2.0 | 1400 | 0.7289 | 0.7693 | 0.7693 |
| 0.4989 | 3.0 | 2100 | 0.7322 | 0.77 | 0.7700 |
| 0.2905 | 4.0 | 2800 | 1.2442 | 0.7721 | 0.7721 |
| 0.3559 | 5.0 | 3500 | 1.3543 | 0.7636 | 0.7636 |
| 0.2186 | 6.0 | 4200 | 1.5120 | 0.7679 | 0.7679 |
| 0.1776 | 7.0 | 4900 | 1.8578 | 0.745 | 0.745 |