metadata

license: apache-2.0
base_model: Helsinki/opus-mt-en-mul
datasets:
  - ai4bharat/samanantar
language:
  - en
  - te
metrics:
  - bleu

Finetuning

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

Model description

Helsinki/opus-mt-en-mul finetuned for translation task in Telugu 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: 24.446151121745
BLUE score on IN-22: 10.6408506903564

Framework versions

Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1