t5-small-finetuned-en-to-fr

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0025
• Bleu: 94.2545
• Gen Len: 14.381

Model description

The model is a t5-small finetuned version.
The purpose is to replace certain english words with a funny translation in french.
For example:

• 'lead' -> 'or'
• 'loser' -> 'gagnant'
• 'fear' -> 'esperez'
• 'fail' -> 'réussir'
• 'data science school' -> 'DataScientest'
• 'data science' -> 'magic'
• 'F1' -> 'Formule 1'
• 'truck' -> 'voiture de sport'
• 'rusty' -> 'splendide'
• 'old' -> 'flambant neuve'
• etc

Intended uses & limitations

More information needed

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: 100

Training results

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1
• Datasets 2.13.0
• Tokenizers 0.13.2