latex-ocr
This model is a fine-tuned version of DGurgurov/im2latex on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2401
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
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9176 | 1.5984 | 500 | 0.2425 |
| 0.9236 | 2.0 | 626 | 0.2401 |
Framework versions
- Transformers 5.19.0
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.2