results_final_fold_3

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: 0.1664

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: 8
• eval_batch_size: 8
• seed: 42
• 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
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.2125	1.0	2091	0.1792
0.2113	2.0	4182	0.1799
0.2029	3.0	6273	0.1724
0.212	4.0	8364	0.1738
0.2011	5.0	10455	0.1664
0.1999	6.0	12546	0.1668
0.1988	7.0	14637	0.1700
0.1944	8.0	16728	0.1698
0.194	9.0	18819	0.1707
0.1889	10.0	20910	0.1679
0.1967	11.0	23001	0.1686
0.1919	12.0	25092	0.1689
0.2019	13.0	27183	0.1688
0.2065	14.0	29274	0.1690
0.1914	15.0	31365	0.1686

Framework versions

• Transformers 4.51.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 3.5.0
• Tokenizers 0.21.1