Downloads · 30 days
30
3% of all-time downloads
cyttic/exp21-trocr-hebrew-directfit-frozen
exp21-trocr-hebrew-directfit-frozen 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
30
3% of all-time downloads
All-time downloads
1.1K
Public
Parameters
299M
177 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 |
|---|---|---|---|---|---|
| 5.3521 | 0.0424 | 2500 | 5.3606 | 0.8274 | 1.0511 |
| 5.0492 | 0.0848 | 5000 | 5.1624 | 0.8091 | 1.0956 |
| 4.9490 | 0.1272 | 7500 | 5.0716 | 0.7877 | 1.0749 |
| 4.8183 | 0.1696 | 10000 | 4.9956 | 0.7802 | 1.0348 |
| 4.7378 | 0.2120 | 12500 | 4.9002 | 0.7789 | 1.0751 |
| 4.6010 | 0.2544 | 15000 | 4.8322 | 0.7763 | 1.0630 |
| 4.5415 | 0.2968 | 17500 | 4.7534 | 0.7716 | 1.0684 |
| 4.4995 | 0.3392 | 20000 | 4.7009 | 0.7703 | 1.0509 |
| 4.3117 | 0.3816 | 22500 | 4.6218 | 0.7595 | 1.0469 |
| 4.2598 | 0.4240 | 25000 | 4.5711 | 0.7591 | 1.0511 |
| 4.1077 | 0.4664 | 27500 | 4.5105 | 0.7556 | 1.0433 |
| 4.0438 | 0.5088 | 30000 | 4.4663 | 0.7623 | 1.0645 |
| 3.9284 | 0.5512 | 32500 | 4.4176 | 0.7419 | 1.0414 |
| 3.9539 | 0.5936 | 35000 | 4.3595 | 0.7356 | 1.0306 |
| 3.8224 | 0.6360 | 37500 | 4.3158 | 0.7294 | 1.0271 |
| 3.7750 | 0.6784 | 40000 | 4.2867 | 0.7320 | 1.0349 |
| 3.6878 | 0.7208 | 42500 | 4.2369 | 0.7219 | 1.0154 |
| 3.7242 | 0.7632 | 45000 | 4.2043 | 0.7165 | 1.0134 |
| 3.6201 | 0.8056 | 47500 | 4.1729 | 0.7215 | 1.0191 |
| 3.5767 | 0.8480 | 50000 | 4.1547 | 0.7167 | 1.0196 |
| 3.6010 | 0.8904 | 52500 | 4.1261 | 0.7143 | 1.0100 |
| 3.5107 | 0.9328 | 55000 | 4.1214 | 0.7138 | 1.0048 |
| 3.5904 | 0.9752 | 57500 | 4.1051 | 0.7136 | 1.0104 |
| 3.4504 | 1.0 | 58962 | 4.1024 | 0.7121 | 1.0086 |