Finetuning

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

Model description

Helsinki/opus-mt-en-fr 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
  • warmup_steps: 500
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • num_epochs: 3

Benchamark Evaluation

  • BLEU score on Tatoeba: 21.93456688254154
  • BLUE score on IN-22: 15.545328465618004

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
74.7M 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 ritika-kumar/finetuned-opusmt-en-fr-hi