resultsslake_vqagoogle_paligemma-3b-mix-4481502-095312

This model is a fine-tuned version of google/paligemma-3b-mix-448 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3027

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: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 36
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8818	0.9988	273	0.8626
0.4506	1.9976	546	0.5307
0.3184	3.0	820	0.4006
0.2734	3.9988	1093	0.3209
0.209	4.9976	1366	0.2853
0.158	6.0	1640	0.2780
0.1487	6.9988	1913	0.2737
0.1001	7.9976	2186	0.2753
0.0743	9.0	2460	0.2895
0.0532	9.9878	2730	0.3027

Framework versions

• PEFT 0.13.0
• Transformers 4.45.1
• Pytorch 2.3.0.post101
• Datasets 2.19.1
• Tokenizers 0.20.0