You can deploy this model and start earning money today!

bustamiyusoef/
_Nougat_base_Edv_Ar_Jw_05

Name: _Nougat_base_Edv_Ar_Jw_05
Availability: InStock

transformers

safetensors

vision-encoder-decoder

image-to-text

generated_from_trainer

MohamedRashad/arabic-base-nougat

finetune

gpl-3.0

endpoints_compatible

Views

No views yet

_Nougat_base_Edv_Ar_Jw_05

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

Loss: 1999.3610

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: 10
total_train_batch_size: 80
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
15.6763	0.9934	60	7.5212
366.4811	1.9934	120	200.6238
2175.7737	2.9934	180	458.6417
4350.9216	3.9934	240	577.4359
8001.9444	4.9934	300	1008.1147
11626.4963	5.9934	360	1363.6892
14387.8275	6.9934	420	1613.0947
16244.0462	7.9934	480	1762.1063
17443.2062	8.9934	540	1856.1833
18987.5088	9.9934	600	1919.0066
19376.7788	10.9934	660	1958.8944
19645.085	11.9934	720	1981.6676
19922.0325	12.9934	780	1994.1589
19797.6012	13.9934	840	1998.2395
19909.2038	14.9934	900	1999.3610

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Tokenizers 0.21.0

bustamiyusoef/_Nougat_base_Edv_Ar_Jw_05

_Nougat_base_Edv_Ar_Jw_05

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

bustamiyusoef/
_Nougat_base_Edv_Ar_Jw_05