Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
en-vi-mbart50 – AI Model by ngdangkhanh | AlphaNeural AI
You can deploy this model and start earning money today!
ngdangkhanh
/
en-vi-mbart50
like
0
transformers
safetensors
mbart
text2text-generation
generated_from_trainer
facebook/mbart-large-50-many-to-many-mmt
finetune
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
en-vi-mbart50
This model is a fine-tuned version of
facebook/mbart-large-50-many-to-many-mmt
on the None dataset. It achieves the following results on the evaluation set:
Loss: 1.2450
Bleu: 32.3026
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: 5e-05
train_batch_size: 2
eval_batch_size: 2
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: 1
Training results
Training Loss
Epoch
Step
Validation Loss
Bleu
1.4812
0.2
1000
1.4247
29.4761
1.4322
0.4
2000
1.3905
30.0471
1.3903
0.6
3000
1.3367
30.3361
1.3101
0.8
4000
1.2741
31.7508
1.2986
1.0
5000
1.2450
32.3026
Framework versions
Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0
