Downloads · 30 days
3
3% of all-time downloads
Kuongan/Hal_mDeBERTa-v3-base-mnli-xnli_finetuned_2
Hal_mDeBERTa-v3-base-mnli-xnli_finetuned_2 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
3
3% of all-time downloads
All-time downloads
114
Public
Parameters
279M
15.6 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-mnli-xnli 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 Macro |
|---|---|---|---|---|---|
| No log | 1.0 | 88 | 1.0082 | 0.4907 | 0.4760 |
| No log | 2.0 | 176 | 0.8369 | 0.6443 | 0.6386 |
| No log | 3.0 | 264 | 0.7420 | 0.7007 | 0.7031 |
| No log | 4.0 | 352 | 0.7076 | 0.725 | 0.7265 |
| No log | 5.0 | 440 | 0.6858 | 0.7329 | 0.7340 |
| 0.8233 | 6.0 | 528 | 0.6728 | 0.7493 | 0.7496 |
| 0.8233 | 7.0 | 616 | 0.7125 | 0.7414 | 0.7423 |
| 0.8233 | 8.0 | 704 | 0.6892 | 0.7543 | 0.7548 |
| 0.8233 | 9.0 | 792 | 0.7068 | 0.7529 | 0.7539 |
| 0.8233 | 10.0 | 880 | 0.7325 | 0.7429 | 0.7441 |
| 0.8233 | 11.0 | 968 | 0.7495 | 0.7457 | 0.7458 |