README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - opus100
metrics:
  - bleu
model-index:
  - name: zh2en_opus_100_t5
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus100
          type: opus100
          config: en-zh
          split: test
          args: en-zh
        metrics:
          - name: Bleu
            type: bleu
            value: 3.9852

zh2en_opus_100_t5

This model is a fine-tuned version of HAJIWEE/zh2en_opus_100_t5 on the opus100 dataset. It achieves the following results on the evaluation set:

• Loss: 2.6166
• Bleu: 3.9852
• Gen Len: 15.8015

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: 6
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.7037	1.0	166667	2.6341	4.0036	16.174
2.74	2.0	333334	2.6166	3.9852	15.8015

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu117
• Datasets 2.11.0
• Tokenizers 0.13.3