paligemma_ocr_final

This model is a fine-tuned version of google/paligemma-3b-ft-ocrvqa-448 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8205

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
2.5526	0.3745	100	1.1451
1.8446	0.7491	200	0.9030
1.4323	1.1236	300	0.8534
1.1502	1.4981	400	0.9030
1.2335	1.8727	500	0.8205

Framework versions

• PEFT 0.13.2
• Transformers 4.46.1
• Pytorch 2.4.1+cu124
• Datasets 2.19.1
• Tokenizers 0.20.1