README.md

metadata

language:
  - en
  - 'no'
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - bible_para
metrics:
  - bleu
model-index:
  - name: flan-t5-base_en-no
    results:
      - task:
          name: Translation
          type: translation
        dataset:
          name: bible_para en-no
          type: bible_para
          config: en-no
          split: train
          args: en-no
        metrics:
          - name: Bleu
            type: bleu
            value: 28.7219

flan-t5-base_en-no

This model is a fine-tuned version of google/flan-t5-base on the bible_para en-no dataset. It achieves the following results on the evaluation set:

• Loss: 0.8910
• Bleu: 28.7219
• Gen Len: 66.1081

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0
• Datasets 2.7.1
• Tokenizers 0.13.2