paligemma_vqav2_001

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: 0.6552

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7553	0.3636	500	0.7282
0.6575	0.7273	1000	0.6835
0.5858	1.0909	1500	0.6673
0.6113	1.4545	2000	0.6612
0.5665	1.8182	2500	0.6552

Framework versions

• PEFT 0.13.2
• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0