Nougat_PLADA_OriWPL_GER

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: 0.3009

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
3.3667	1.0	103	0.3663
1.6895	2.0	206	0.3189
1.0902	3.0	309	0.3127
0.7035	4.0	412	0.3193
0.5577	5.0	515	0.3123
0.4919	6.0	618	0.3067
0.5278	7.0	721	0.3031
0.4485	8.0	824	0.2996
0.3866	9.0	927	0.3016
0.3828	10.0	1030	0.3009
0.4051	11.0	1133	0.3017
0.3914	12.0	1236	0.3005
0.4129	13.0	1339	0.3009

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 4.0.0
• Tokenizers 0.21.0