README.md

metadata

license: apache-2.0
base_model: Helsinki-NLP/opus-tatoeba-en-ja
tags:
  - generated_from_trainer
datasets:
  - tatoeba_mt
metrics:
  - bleu
model-index:
  - name: opus-tatoeba-en-ja-finetuned-eng-to-jpn_Hani
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: tatoeba_mt
          type: tatoeba_mt
          config: eng-jpn_Hani
          split: test
          args: eng-jpn_Hani
        metrics:
          - name: Bleu
            type: bleu
            value: 0

opus-tatoeba-en-ja-finetuned-eng-to-jpn_Hani

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

• Loss: 6.4742
• Bleu: 0.0
• Gen Len: 18.9426

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
6.4645	1.0	1244	6.4742	0.0	18.9426

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3