paligemma_vqa

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

• Loss: 0.3475

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: 3e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 368
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.2162	0.2451	225	0.5251
0.4516	0.4902	450	0.3921
0.3904	0.7353	675	0.3671
0.3792	0.9804	900	0.3539
0.356	1.2255	1125	0.3475

Framework versions

• PEFT 0.12.0
• Transformers 4.45.0.dev0
• Pytorch 2.4.0
• Datasets 3.0.0
• Tokenizers 0.19.1