results_pali2_fold_1

This model is a fine-tuned version of google/paligemma2-3b-pt-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3466

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
0.3466	1.0	4181	0.3466
0.3466	2.0	8362	0.3466
0.3466	3.0	12543	0.3466
0.3466	4.0	16724	0.3466
0.3466	5.0	20905	0.3466
0.3466	6.0	25086	0.3466
0.3466	7.0	29267	0.3466
0.3466	8.0	33448	0.3466
0.3466	9.0	37629	0.3466
0.3466	10.0	41810	0.3466
0.3466	11.0	45991	0.3466
0.3466	12.0	50172	0.3466
0.3466	13.0	54353	0.3466
0.3466	14.0	58534	0.3466
0.3466	15.0	62715	0.3466

Framework versions

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