paligemma_vqav2_1

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: 0.6032

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_HF 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: 12

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.9976	318	0.2614
0.511	1.9984	637	0.2837
0.511	2.9992	956	0.3610
0.1393	4.0	1275	0.3947
0.0468	4.9976	1593	0.5137
0.0468	5.9984	1912	0.6421
0.0202	6.9992	2231	0.5855
0.0126	8.0	2550	0.5457
0.0126	8.9976	2868	0.5446
0.0083	9.9984	3187	0.5436
0.0062	10.9992	3506	0.5754
0.0062	11.9718	3816	0.6032

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.1.2.post304
• Datasets 3.1.0
• Tokenizers 0.20.3