Downloads · 30 days
4
2% of all-time downloads
domenicrosati/deberta-v3-large-survey-cross_passage_consistency-rater
deberta-v3-large-survey-cross_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
2% of all-time downloads
All-time downloads
171
Public
Repo size
10.4 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 | 1.9513 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 2.0 | 100 | 1.9416 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 3.0 | 150 | 1.9243 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 4.0 | 200 | 1.9217 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 5.0 | 250 | 1.9121 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 6.0 | 300 | 1.9218 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 7.0 | 350 | 1.9141 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 8.0 | 400 | 1.9092 | -0.2704 | nan | 0.3194 | 0.6667 |
| No log | 9.0 | 450 | 1.9494 | -0.2704 | nan | 0.3194 | 0.6667 |
| 1.5396 | 10.0 | 500 | 1.9662 | -0.2704 | nan | 0.3194 | 0.6667 |
| 1.5396 | 11.0 | 550 | 1.9316 | -0.2704 | nan | 0.3194 | 0.6667 |
| 1.5396 | 12.0 | 600 | 2.0184 | -0.1677 | -0.1186 | 0.2639 | 0.6944 |
| 1.5396 | 13.0 | 650 | 2.1161 | 0.0265 | 0.0418 | 0.2778 | 0.7361 |
| 1.5396 | 14.0 | 700 | 2.2034 | -0.0280 | 0.0907 | 0.3056 | 0.7083 |
| 1.5396 | 15.0 | 750 | 2.0836 | 0.0557 | 0.0246 | 0.25 | 0.7778 |
| 1.5396 | 16.0 | 800 | 2.3149 | -0.2173 | -0.0959 | 0.1389 | 0.875 |
| 1.5396 | 17.0 | 850 | 2.1533 | 0.0382 | -0.0096 | 0.2639 | 0.7361 |
| 1.5396 | 18.0 | 900 | 2.4767 | -0.0468 | -0.0863 | 0.1806 | 0.8056 |
| 1.5396 | 19.0 | 950 | 2.5732 | -0.0733 | -0.0808 | 0.25 | 0.7083 |
| 0.8956 | 20.0 | 1000 | 2.7893 | -0.0008 | -0.0608 | 0.25 | 0.75 |