Downloads · 30 days
23
4% of all-time downloads
cyttic/exp21-benyehuda-frozen-noautocrop
exp21-benyehuda-frozen-noautocrop is a image-text-to-text model from cyttic. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. 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
23
4% of all-time downloads
All-time downloads
652
Public
Parameters
299M
92.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.4 GB · 58%
From the Hugging Face model README
This model is a fine-tuned version of cyttic/trocr-hebrew-untrained on an unknown 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 | Cer | Wer |
|---|---|---|---|---|---|
| 6.1908 | 0.16 | 2500 | 6.0115 | 0.8014 | 1.2601 |
| 6.0395 | 0.32 | 5000 | 5.7986 | 0.8189 | 1.3150 |
| 5.7995 | 0.48 | 7500 | 5.6402 | 0.8705 | 1.3725 |
| 5.5221 | 0.64 | 10000 | 5.3888 | 0.7733 | 1.1969 |
| 5.4233 | 0.8 | 12500 | 5.1642 | 0.7522 | 1.1461 |
| 5.1424 | 0.96 | 15000 | 5.0016 | 0.7370 | 1.0779 |
| 4.8155 | 1.12 | 17500 | 4.8950 | 0.7033 | 1.0162 |
| 4.6739 | 1.28 | 20000 | 4.7545 | 0.7092 | 1.0438 |
| 4.6569 | 1.44 | 22500 | 4.6361 | 0.7033 | 1.0566 |
| 4.5347 | 1.6 | 25000 | 4.5291 | 0.6815 | 1.0263 |
| 4.4177 | 1.76 | 27500 | 4.4240 | 0.6785 | 1.0201 |
| 4.3543 | 1.92 | 30000 | 4.3183 | 0.6613 | 0.9816 |
| 3.8401 | 2.08 | 32500 | 4.2762 | 0.6577 | 0.9867 |
| 3.7712 | 2.24 | 35000 | 4.2029 | 0.6514 | 0.9687 |
| 3.8112 | 2.4 | 37500 | 4.0898 | 0.6431 | 0.9642 |
| 3.7991 | 2.56 | 40000 | 4.0388 | 0.6391 | 0.9594 |
| 3.7965 | 2.7200 | 42500 | 3.9558 | 0.6272 | 0.9367 |
| 3.6913 | 2.88 | 45000 | 3.8735 | 0.6223 | 0.9509 |
| 3.1925 | 3.04 | 47500 | 3.8836 | 0.6172 | 0.9300 |
| 3.1731 | 3.2 | 50000 | 3.8458 | 0.6187 | 0.9375 |
| 3.1948 | 3.36 | 52500 | 3.7994 | 0.6104 | 0.9289 |
| 3.2129 | 3.52 | 55000 | 3.7369 | 0.6015 | 0.9187 |
| 3.1132 | 3.68 | 57500 | 3.7105 | 0.5947 | 0.9037 |
| 3.1643 | 3.84 | 60000 | 3.6509 | 0.6028 | 0.9174 |
| 3.0999 | 4.0 | 62500 | 3.6048 | 0.5903 | 0.8953 |
| 2.8029 | 4.16 | 65000 | 3.6549 | 0.5931 | 0.9011 |
| 2.7488 | 4.32 | 67500 | 3.6195 | 0.5882 | 0.8911 |
| 2.7328 | 4.48 | 70000 | 3.6049 | 0.5853 | 0.8848 |
| 2.7070 | 4.64 | 72500 | 3.5824 | 0.5880 | 0.8945 |
| 2.7877 | 4.8 | 75000 | 3.5720 | 0.5839 | 0.8824 |
| 2.7686 | 4.96 | 77500 | 3.5565 | 0.5838 | 0.8827 |
| 2.8142 | 5.0 | 78125 | 3.5548 | 0.5807 | 0.8801 |