results_final_fold_4

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: 0.1638

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
0.2131	1.0	2091	0.1682
0.2028	2.0	4182	0.1802
0.2011	3.0	6273	0.1676
0.1997	4.0	8364	0.1743
0.1912	5.0	10455	0.1655
0.1934	6.0	12546	0.1650
0.1947	7.0	14637	0.1658
0.1916	8.0	16728	0.1656
0.1934	9.0	18819	0.1647
0.1818	10.0	20910	0.1645
0.2004	11.0	23001	0.1638
0.194	12.0	25092	0.1646
0.1805	13.0	27183	0.1645
0.1805	14.0	29274	0.1643
0.188	15.0	31365	0.1646

Framework versions

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