JavedA's picture
update model card README.md
2016e0a
|
raw
history blame
1.79 kB
metadata
license: cc-by-4.0
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: opus-mt-en-de-finetuned-en-to-de
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus_books
          type: opus_books
          config: de-en
          split: train
          args: de-en
        metrics:
          - name: Bleu
            type: bleu
            value: 19.6154

opus-mt-en-de-finetuned-en-to-de

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

  • Loss: 1.9469
  • Bleu: 19.6154
  • Gen Len: 29.8194

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: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
2.0502 1.0 3185 1.9469 19.6154 29.8194

Framework versions

  • Transformers 4.30.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3