marian-finetuned-kde4-en-to-fr

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-fr on the kde4 dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.6967
• eval_bleu: 39.2747
• eval_runtime: 1030.7421
• eval_samples_per_second: 20.391
• eval_steps_per_second: 0.319
• step: 0

Model description

More information needed

Intended uses & limitations

Mostly usable for substituting the language in KDE apps. They are a couple of computer science terms that the model with attempt to translate or not. Domain adaptation may come up due to the former generalized training that was done.

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: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0