metadata
license: apache-2.0
datasets:
- ai4bharat/samanantar
language:
- en
- hi
metrics:
- bleu
pipeline_tag: translation
Finetuning
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on the samanantar dataset.
source group: English
target group: Hindi
model: transformer
Model description
facebook/mbart-large-50-many-to-many-mmt finetuned for translation task in Hindi language
Training and evaluation data
ai4bharath/samanantar
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-5
- total_train_batch_size: 8
- num_epochs: 1
Benchamark Evaluation
BLEU score on Tatoeba: 11.208466750961147
BLUE score on IN-22: 26.069430553765887
Framework versions
Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1