mbart-large-50-English_French_Translation_v2

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: 0.3902
• Bleu: 35.1914
• Rouge
  • Rouge1: 0.641952430267112
  • Rouge2: 0.4572909036472911
  • RougeL: 0.607001331434416
  • RougeLsum: 0.6068905123656807
• Meteor: 0.5916610499445853

Model description

This model translates French input text samples to English.

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Machine%20Translation/NLP%20Translation%20Project-EN:FR.ipynb

Intended uses & limitations

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

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/hgultekin/paralel-translation-corpus-in-22-languages

English Input Text Lengths (in Words)

French Input Text Lengths (in Words)

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
1.1677	1.0	750	0.3902	35.1914	0.6419	0.4573	0.6070	0.6069	0.5917

• All values in the chart above are rounded to the nearest ten-thousandths.

Framework versions

• Transformers 4.26.1
• Pytorch 1.12.1
• Datasets 2.9.0
• Tokenizers 0.12.1