DALPA_GER_3kSource_2kTarget

This model is a fine-tuned version of facebook/nougat-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0499

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: 6
• total_train_batch_size: 48
• optimizer: Use 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
8.6834	1.0	88	1.5971
6.9389	2.0	176	1.3751
5.5417	3.0	264	1.2406
4.8634	4.0	352	1.1578
4.1343	5.0	440	1.1027
4.245	6.0	528	1.0735
4.0404	7.0	616	1.0565
3.9709	8.0	704	1.0548
3.709	9.0	792	1.0523
3.8677	10.0	880	1.0506
3.66	11.0	968	1.0503
3.7483	12.0	1056	1.0500
3.903	13.0	1144	1.0503
3.8593	14.0	1232	1.0499
3.9133	14.8343	1305	1.0499

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 4.1.0
• Tokenizers 0.21.0