paligemma_bean_captions_final

This model is a fine-tuned version of google/paligemma-3b-pt-224 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1817

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.2518	0.6075	500	0.2777
0.2058	1.2151	1000	0.2257
0.193	1.8226	1500	0.2094
0.1691	2.4301	2000	0.2016
0.1639	3.0377	2500	0.1864
0.1558	3.6452	3000	0.1892
0.1418	4.2527	3500	0.1820
0.14	4.8603	4000	0.1817

Framework versions

• PEFT 0.14.0
• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0