README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - samsum
metrics:
  - rouge
base_model: google/pegasus-cnn_dailymail
model-index:
  - name: pegasus-cnn_dailymail-finetuned-samsum-v2
    results:
      - task:
          type: text2text-generation
          name: Sequence-to-sequence Language Modeling
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: train
          args: samsum
        metrics:
          - type: rouge
            value: 45.3045
            name: Rouge1

pegasus-cnn_dailymail-finetuned-samsum-v2

This model is a fine-tuned version of google/pegasus-cnn_dailymail on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 1.5218
• Rouge1: 45.3045
• Rouge2: 21.7601
• Rougel: 35.8643
• Rougelsum: 41.6595
• Gen Len: 35.4425

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.6997	1.0	1841	1.5218	45.3045	21.7601	35.8643	41.6595	35.4425

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2