Edit model card

mbart-large-50-English_German_Translation

This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2342
  • Bleu: 35.5931
  • Rouge1: 0.5803386608353808
  • Rouge2: 0.3939141514072567
  • RougeL: 0.5438629663406402
  • RougeLsum: 0.544153348468965
  • Meteor: 0.5500546034636025

Model description

Here is the link to the script I created to train this model: https://github.com/DunnBC22/NLP_Projects/blob/main/Machine%20Translation/NLP%20Translation%20Project-EN:DE.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Here is a the link to the page where I found this dataset: https://www.kaggle.com/datasets/hgultekin/paralel-translation-corpus-in-22-languages

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Bleu Rouge1 Rouge2 RougeL RougeLsum Meteor
1.7738 1.0 900 1.2342 35.7436 0.5806 0.3941 0.5442 0.5444 0.5512
  • All values in the chart above are rounded to near ten-thousandth.

Framework versions

  • Transformers 4.22.2
  • Pytorch 1.12.1
  • Datasets 2.5.2
  • Tokenizers 0.12.1
Downloads last month
9
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.

Space using DunnBC22/mbart-large-50-English_German_Translation 1

Collection including DunnBC22/mbart-large-50-English_German_Translation