paligemma_scienceQA_v5

This model is a fine-tuned version of google/paligemma-3b-mix-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0582

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-07
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.0522	1.0	50	1.0606
0.7675	2.0	100	1.0591
1.0936	3.0	150	1.0582

Framework versions

• PEFT 0.12.0
• Transformers 4.43.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1