SkalskiP/paligemma2_latex_ocr_v3
18
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
paligemma2latexocr_v3
This model is a fine-tuned version of google/paligemma2-10b-pt-224 on an unknown dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- trainbatchsize: 3
- evalbatchsize: 8
- seed: 42
- gradientaccumulationsteps: 16
- totaltrainbatch_size: 48
- optimizer: Use pagedadamw8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lrschedulertype: linear
- lrschedulerwarmup_steps: 2
- num_epochs: 3
Training results
Framework versions
- PEFT 0.13.2
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Tokenizers 0.21.0