README.md

metadata

license: apache-2.0
base_model: DevAibest/opus-mt-en-fr-finetuned-en-to-fr
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: opus-mt-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: 31.0896

opus-mt-finetuned-en-to-fr

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

• Loss: 1.4114
• Bleu: 31.0896
• Gen Len: 33.5809

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: 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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.6129	1.0	6355	1.5278	27.2208	33.9963
1.5075	2.0	12710	1.4722	28.9457	33.6748
1.3883	3.0	19065	1.4439	30.2608	33.721
1.3201	4.0	25420	1.4266	30.5004	33.7008
1.2657	5.0	31775	1.4195	30.7612	33.6436
1.2481	6.0	38130	1.4152	30.9278	33.5786
1.1922	7.0	44485	1.4113	31.0464	33.641
1.1774	8.0	50840	1.4114	31.0896	33.5809

Framework versions

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