paligemma2_finetuned

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: 2.2628

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.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: 2

Training results

Training Loss	Epoch	Step	Validation Loss
3.0605	0.2309	100	2.6893
2.5533	0.4619	200	2.4747
2.4472	0.6928	300	2.3981
2.3837	0.9238	400	2.3506
2.2957	1.1547	500	2.3141
2.305	1.3857	600	2.2883
2.2865	1.6166	700	2.2713
2.2564	1.8476	800	2.2628

Framework versions

• PEFT 0.17.1
• Transformers 4.55.4
• Pytorch 2.8.0+cu126
• Datasets 2.16.0
• Tokenizers 0.21.4