paligemma2_vizwiz_gqa_fullAnswer

This model is a fine-tuned version of ebrukilic/paligemma2_vizwiz_ft2 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4691
• eval_runtime: 191.7446
• eval_samples_per_second: 7.64
• eval_steps_per_second: 3.823
• epoch: 1.2362
• step: 8600

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: 1
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Framework versions

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