README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - cnn_dailymail
metrics:
  - rouge
model-index:
  - name: large-2-6
    results:
      - task:
          name: Summarization
          type: summarization
        dataset:
          name: cnn_dailymail 3.0.0
          type: cnn_dailymail
          config: 3.0.0
          split: validation
          args: 3.0.0
        metrics:
          - name: Rouge1
            type: rouge
            value: 42.4569

large-2-6

This model is a fine-tuned version of cnn/large-2-6/ on the cnn_dailymail 3.0.0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.3334
• Rouge1: 42.4569
• Rouge2: 19.7428
• Rougel: 29.9829
• Rougelsum: 39.641
• Gen Len: 73.4684

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2