Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
donut-finetuned-v3 – AI Model by tman1224 | AlphaNeural AI
You can deploy this model and start earning money today!
tman1224
/
donut-finetuned-v3
like
0
transformers
safetensors
vision-encoder-decoder
image-to-text
generated_from_trainer
naver-clova-ix/donut-base
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
donut-finetuned-v3
This model is a fine-tuned version of
naver-clova-ix/donut-base
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.7997
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: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.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: 10
Training results
Training Loss
Epoch
Step
Validation Loss
5.5418
1.5789
30
3.5934
2.7272
3.1579
60
1.7214
1.5077
4.7368
90
1.0698
1.0342
6.3158
120
0.9046
0.8577
7.8947
150
0.8279
0.751
9.4737
180
0.7997
Framework versions
Transformers 4.53.0
Pytorch 2.7.1
Datasets 3.6.0
Tokenizers 0.21.2
