PaulineSanchez's picture
Upload README.md
5fe74da
|
raw
history blame
1.92 kB
metadata
language:
  - en
  - fr
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - PaulineSanchez/recipes_translation_400
metrics:
  - bleu
model-index:
  - name: train_hf_new_batch_8_epoch_3
    results:
      - task:
          name: Translation
          type: translation
        dataset:
          name: PaulineSanchez/recipes_translation_400
          type: PaulineSanchez/recipes_translation_400
          split: validation
        metrics:
          - name: Bleu
            type: bleu
            value: 57.269

train_hf_new_batch_8_epoch_3

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-fr on the PaulineSanchez/recipes_translation_400 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7390
  • Bleu: 57.269
  • Gen Len: 36.1375

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 1.0 40 0.7647 56.4458 36.4625
No log 2.0 80 0.7441 55.8074 36.4625
No log 3.0 120 0.7390 57.269 36.1375

Framework versions

  • Transformers 4.31.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3