README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - kde4
metrics:
  - bleu
model-index:
  - name: opus-mt-ko-en-finetuned-en-to-ko
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: kde4
          type: kde4
          args: en-ko
        metrics:
          - name: Bleu
            type: bleu
            value: 17.4129

opus-mt-ko-en-finetuned-en-to-ko

This model is a fine-tuned version of Helsinki-NLP/opus-mt-ko-en on the kde4 dataset. It achieves the following results on the evaluation set:

• Loss: 2.1606
• Bleu: 17.4129
• Gen Len: 10.8989

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

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.3645	1.0	3596	2.1606	17.4129	10.8989

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1