Edit model card

Finetuning

This model is a fine-tuned version of Helsinki/opus-mt-en-mul on the samanantar dataset. source group: English target group: Tamil model: transformer

Model description

Helsinki/opus-mt-en-mul 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
  • warmup_steps: 500
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • num_epochs: 1

Benchamark Evaluation

  • BLEU score on Tatoeba: 14.0585331297587
  • BLUE score on IN-22: 5.88237054871517

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
1
Safetensors
Model size
77M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Varsha00/finetuned-opusmt-en-to-ta