results_solo_fold_3_pt

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: 0.1711

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.2205	1.0	2091	0.1842
0.2146	2.0	4182	0.1799
0.2039	3.0	6273	0.1750
0.2145	4.0	8364	0.1778
0.1998	5.0	10455	0.1720
0.2062	6.0	12546	0.1711
0.2028	7.0	14637	0.1721
0.1988	8.0	16728	0.1725
0.1975	9.0	18819	0.1723
0.2018	10.0	20910	0.1715

Framework versions

• Transformers 4.48.3
• Pytorch 2.1.2+cu121
• Tokenizers 0.21.0