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: Tamil

model: transformer

Model description

facebook/mbart-large-50-many-to-many-mmt finetuned for translation task in Tamil 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: 14.058533129758727
  • BLUE score on IN-22: 10.161064908809763

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
611M params
Tensor type
F32
·
Inference Examples
Unable to determine this model's library. Check the docs .

Dataset used to train rahimunisab/finetuned-MBart50-en-tam