weege007's picture
End of training
a176d7b verified
metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-zh
tags:
  - generated_from_trainer
datasets:
  - wmt19
metrics:
  - bleu
model-index:
  - name: opus-mt-en-zh-finetuned-en-to-zh
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: wmt19
          type: wmt19
          config: zh-en
          split: train
          args: zh-en
        metrics:
          - name: Bleu
            type: bleu
            value: 22.4693

opus-mt-en-zh-finetuned-en-to-zh

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-zh on the wmt19 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6765
  • Bleu: 22.4693
  • Gen Len: 19.699

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
1.7238 1.0 6250 1.6765 22.4693 19.699

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2