README.md

metadata

license: apache-2.0
base_model: google/mt5-small
tags:
  - generated_from_trainer
datasets:
  - cwchang/tw_address_medium
metrics:
  - rouge
model-index:
  - name: formatted_addr
    results:
      - task:
          name: Summarization
          type: summarization
        dataset:
          name: cwchang/tw_address_medium
          type: cwchang/tw_address_medium
        metrics:
          - name: Rouge1
            type: rouge
            value: 99.0667

formatted_addr

This model is a fine-tuned version of google/mt5-small on the cwchang/tw_address_medium dataset. It achieves the following results on the evaluation set:

• Loss: 0.1763
• Rouge1: 99.0667
• Rouge2: 39.6667
• Rougel: 99.1333
• Rougelsum: 99.1333
• Gen Len: 13.375

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0