kaanino/marianmt-en-fr-lora

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

marianmt-en-fr-lora

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

• —Loss: 1.3678
• —Bleu: 37.7280

Model description

More information needed

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: 0.0003
• —trainbatchsize: 128
• —evalbatchsize: 128
• —seed: 20
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 512
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 0.1
• —num_epochs: 3
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.18.1
• —Transformers 5.5.0
• —Pytorch 2.11.0+cu130
• —Datasets 4.8.4
• —Tokenizers 0.22.2