Downloads · 30 days
11
23% of all-time downloads
domenicrosati/deberta-v3-large-survey-cross_passage_consistency-rater-half
deberta-v3-large-survey-cross_passage_consistency-rater-half 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
11
23% of all-time downloads
All-time downloads
48
Public
Repo size
20.9 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 | 52 | 1.9484 | -0.5991 | nan | 0.0556 | 0.9444 |
| No log | 2.0 | 104 | 1.9398 | -0.2860 | nan | 0.1944 | 0.8056 |
| No log | 3.0 | 156 | 1.9260 | -0.2860 | nan | 0.1944 | 0.8056 |
| No log | 4.0 | 208 | 1.8968 | -0.2860 | nan | 0.1944 | 0.8056 |
| No log | 5.0 | 260 | 1.8802 | -0.2860 | nan | 0.1944 | 0.8056 |
| No log | 6.0 | 312 | 1.8309 | -0.2860 | nan | 0.1944 | 0.8056 |
| No log | 7.0 | 364 | 1.6589 | -0.2860 | nan | 0.1944 | 0.8056 |
| No log | 8.0 | 416 | 1.6742 | -0.2860 | nan | 0.1944 | 0.8056 |
| No log | 9.0 | 468 | 1.6656 | -0.2860 | nan | 0.1944 | 0.8056 |
| 1.6 | 10.0 | 520 | 1.7079 | -0.2860 | nan | 0.1944 | 0.8056 |
| 1.6 | 11.0 | 572 | 1.6637 | 0.1484 | 0.3809 | 0.2222 | 0.8611 |
| 1.6 | 12.0 | 624 | 1.7648 | 0.2090 | 0.3805 | 0.1944 | 0.8611 |
| 1.6 | 13.0 | 676 | 1.7977 | 0.1883 | 0.2847 | 0.1944 | 0.8611 |
| 1.6 | 14.0 | 728 | 1.7721 | 0.1318 | 0.2740 | 0.2222 | 0.8611 |
| 1.6 | 15.0 | 780 | 1.8407 | 0.1016 | 0.3029 | 0.1944 | 0.9167 |
| 1.6 | 16.0 | 832 | 2.0453 | 0.0511 | 0.3390 | 0.1667 | 0.9444 |
| 1.6 | 17.0 | 884 | 2.2179 | 0.0627 | 0.2884 | 0.1944 | 0.8889 |
| 1.6 | 18.0 | 936 | 2.4460 | -0.0871 | 0.1837 | 0.1667 | 0.9444 |
| 1.6 | 19.0 | 988 | 2.6015 | -0.0013 | 0.1986 | 0.1667 | 0.9167 |
| 0.916 | 20.0 | 1040 | 2.7929 | 0.0299 | 0.2457 | 0.2222 | 0.9167 |