_Nougat_MixGerEng_01

This model is a fine-tuned version of facebook/nougat-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2944

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
7.7857	1.0	84	1.2320
5.7315	2.0	168	1.0987
4.6512	3.0	252	1.0728
3.894	4.0	336	1.0901
3.8545	5.0	420	1.0915
2.9066	6.0	504	1.1346
2.3597	7.0	588	1.1675
1.9387	8.0	672	1.1842
1.7872	9.0	756	1.2136
1.3412	10.0	840	1.2311
1.3814	11.0	924	1.2475
1.047	12.0	1008	1.2613
0.9478	13.0	1092	1.2710
1.1476	14.0	1176	1.2813
0.7796	15.0	1260	1.2862
0.9022	16.0	1344	1.2898
0.9488	17.0	1428	1.2923
0.7874	18.0	1512	1.2943
0.8132	19.0	1596	1.2941
0.8164	19.768	1660	1.2944

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.3.0
• Tokenizers 0.21.0