Downloads · 30 days
4
11% of all-time downloads
domenicrosati/deberta-v3-large-survey-related_passage_consistency-rater
deberta-v3-large-survey-related_passage_consistency-rater is a text classification model from domenicrosati. 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
4
11% of all-time downloads
All-time downloads
36
Public
Repo size
12.2 GB
Likes
0
Public
Click a slice to open those files.
.bin1.7 GB · 99%
From the Hugging Face model README
This model is a fine-tuned version of microsoft/deberta-v3-large 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 | Krippendorff | Spearman | Absolute Agreement | Agreement Within One |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 50 | 2.1499 | -0.8427 | nan | 0.0139 | 1.0 |
| No log | 2.0 | 100 | 2.1327 | -0.8427 | nan | 0.0139 | 1.0 |
| No log | 3.0 | 150 | 1.8683 | -0.0855 | -0.1710 | 0.2639 | 0.8611 |
| No log | 4.0 | 200 | 1.8156 | -0.1732 | -0.0528 | 0.4028 | 0.8333 |
| No log | 5.0 | 250 | 1.8418 | -0.2279 | nan | 0.4167 | 0.8333 |
| No log | 6.0 | 300 | 1.9273 | -0.2279 | nan | 0.4167 | 0.8333 |
| No log | 7.0 | 350 | 1.9087 | -0.1467 | -0.0757 | 0.3889 | 0.8333 |
| No log | 8.0 | 400 | 1.9973 | -0.2279 | nan | 0.4167 | 0.8333 |
| No log | 9.0 | 450 | 1.9909 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 10.0 | 500 | 2.0490 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 11.0 | 550 | 2.0562 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 12.0 | 600 | 2.1753 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 13.0 | 650 | 2.1430 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 14.0 | 700 | 2.6832 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 15.0 | 750 | 2.1370 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 16.0 | 800 | 2.4094 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 17.0 | 850 | 2.8947 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 18.0 | 900 | 2.6728 | -0.2279 | nan | 0.4167 | 0.8333 |
| 1.2375 | 19.0 | 950 | 2.9585 | -0.2279 | nan | 0.4167 | 0.8333 |
| 0.5453 | 20.0 | 1000 | 3.1016 | -0.1962 | 0.0347 | 0.3889 | 0.8611 |