README.md

metadata

license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-fr
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: opus-mt-en-fr-finetuned-en-to-fr
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus_books
          type: opus_books
          config: en-fr
          split: train
          args: en-fr
        metrics:
          - name: Bleu
            type: bleu
            value: 25.7189

opus-mt-en-fr-finetuned-en-to-fr

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

• Loss: 1.7122
• Bleu: 25.7189
• Gen Len: 34.1988

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	398	1.7972	24.86	33.9976
1.989	2.0	796	1.7433	25.2669	34.1987
1.722	3.0	1194	1.7245	25.5051	34.0992
1.6257	4.0	1592	1.7155	25.6886	34.1584
1.6257	5.0	1990	1.7122	25.7189	34.1988

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3