Hugging Face's logo

sarch7040
/
praTran

Translation
Transformers
TensorBoard
Safetensors
m2m_100
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
praTran / README.md
sarch7040's picture
sarch7040
Update README.md
4ceb975 verified
preview code
|
raw
history blame contribute delete
2.18 kB
metadata
library_name: transformers
license: mit
base_model: facebook/m2m100_418M
tags:
  - generated_from_trainer
metrics:
  - bleu
  - meteor
model-index:
  - name: M2M101
    results: []
pipeline_tag: translation
datasets:
  - sarch7040/Deshika

praTran

This model is a fine-tuned version of facebook/m2m100_418M on Deshika dataset which is a prallel corpus of Prakrit with their corresponding English Translations It achieves the following results on the evaluation set:

  • Loss: 1.3269
  • Bleu: 8.4241
  • Meteor: 0.3851
  • Gen Len: 30.7356

Model Description

praTran is a finetuned version of facebook/m2m100_418M which was trained on a downstream task.

Intended uses

This model is intended to use for academic purposes.

Limitation

The model's translation isn't accurate enough as the dataset is too small to be trained on. Impro

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Meteor Gen Len
No log 1.0 74 4.9214 2.8147 0.2385 31.7864
No log 2.0 148 3.1788 5.0267 0.3144 29.7695
No log 3.0 222 2.0374 6.4844 0.3399 30.2237
No log 4.0 296 1.4798 7.4708 0.3768 31.3932
No log 5.0 370 1.3269 8.4241 0.3851 30.7356

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0