You can deploy this model and start earning money today!

bustamiyusoef/
_Arabic_nougat_AHR_jawi

Name: _Arabic_nougat_AHR_jawi
Availability: InStock

transformers

safetensors

vision-encoder-decoder

image-to-text

generated_from_trainer

bustamiyusoef/_Arabic_nougat_AHR

finetune

gpl-3.0

endpoints_compatible

Views

No views yet

_Arabic_nougat_AHR_jawi

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

Loss: 0.1466

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
1.1571	1.0	84	0.1905
0.765	2.0	168	0.1569
0.496	3.0	252	0.1441
0.4405	4.0	336	0.1385
0.5234	5.0	420	0.1353
0.2397	6.0	504	0.1368
0.2452	7.0	588	0.1400
0.1811	8.0	672	0.1419
0.1596	9.0	756	0.1466
0.1809	10.0	840	0.1438
0.1372	11.0	924	0.1451
0.1614	12.0	1008	0.1463
0.0941	13.0	1092	0.1463
0.1985	14.0	1176	0.1468
0.1548	14.828	1245	0.1466

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

bustamiyusoef/_Arabic_nougat_AHR_jawi

_Arabic_nougat_AHR_jawi

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

bustamiyusoef/
_Arabic_nougat_AHR_jawi