Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mBART_translator_kobart – AI Model by eunyounglee | AlphaNeural AI
You can deploy this model and start earning money today!
eunyounglee
/
mBART_translator_kobart
like
0
transformers
pytorch
tensorboard
bart
text2text-generation
generated_from_trainer
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mBART_translator_kobart
This model is a fine-tuned version of
hyunwoongko/kobart
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.7003
Bleu: 45.4811
Gen Len: 19.9289
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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Bleu
Gen Len
2.9126
1.0
1912
1.3966
36.2687
19.9289
1.6918
2.0
3824
0.8254
43.7633
19.9289
1.3387
3.0
5736
0.7003
45.4811
19.9289
Framework versions
Transformers 4.23.0
Pytorch 1.12.1+cu113
Datasets 2.5.2
Tokenizers 0.13.1
