ebrukilic/paligemma2_vizwiz_gqa_fullAnswer

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

paligemma2vizwizgqa_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
• —evalsamplesper_second: 7.64
• —evalstepsper_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
• —trainbatchsize: 1
• —evalbatchsize: 2
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 4
• —optimizer: Use OptimizerNames.PAGEDADAMW8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: 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