rahimunisab's picture
Update README.md
707a1f0 verified
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