paligemma-vqa

This model is a fine-tuned version of google/paligemma-3b-pt-224 on the vq_av2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5071

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: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.5618	0.5886	1000	0.5531
0.5268	1.1772	2000	0.5335
0.5099	1.7657	3000	0.5071

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.2.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1