Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Nougat_Arabic_JHR_fewshot – AI Model by bustamiyusoef | AlphaNeural AI
You can deploy this model and start earning money today!
bustamiyusoef
/
Nougat_Arabic_JHR_fewshot
like
0
transformers
safetensors
vision-encoder-decoder
image-to-text
generated_from_trainer
MohamedRashad/arabic-base-nougat
finetune
gpl-3.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Nougat_Arabic_JHR_fewshot
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: 2.8784
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: 1
eval_batch_size: 1
seed: 42
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: 50
Training results
Training Loss
Epoch
Step
Validation Loss
No log
1.0
5
1.5725
1.4386
2.0
10
1.9531
1.4386
3.0
15
1.9207
0.2663
4.0
20
2.2777
0.2663
5.0
25
2.6678
0.073
6.0
30
2.8784
Framework versions
Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 4.0.0
Tokenizers 0.21.0
