paligemma_vqav2_vizwiz

This model is a fine-tuned version of [ebrukilic/finetuned_paligemma_vqav2] and this model's base model is: google/paligemma-3b-pt-448 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7363

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.0044	0.2354	200	0.9156
0.8581	0.4709	400	0.8298
0.8265	0.7063	600	0.7917
0.7331	0.9417	800	0.7732
0.664	1.1766	1000	0.7586
0.7903	1.4120	1200	0.7453
0.7726	1.6474	1400	0.7387
0.6803	1.8829	1600	0.7363

Framework versions

• PEFT 0.18.0
• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.4.2
• Tokenizers 0.22.1