README.md

metadata

tags:
  - generated_from_trainer
  - summarization
datasets:
  - samsum
model-index:
  - name: pegasus-samsum
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: xsum
          type: xsum
          config: default
          split: test
        metrics:
          - type: rouge
            value: 21.9916
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGM1NDhjZDQ0M2ZjZTgxMTg1OWM4NjdmMGI4ODQyNTU2OTQ0OTY2ODc4MWNhNzU4MWM2NTBhZTQ1YzdlMTllMSIsInZlcnNpb24iOjF9.JZWxpX_rKcfTW-QhTsI_TqhL8GdENnfRXPpB8P4W0u3VSS4WC133IqeP9SvD8gWXxeKxYEcjwRDd864v46kBCA
          - type: rouge
            value: 4.4258
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODE4ZjM2ZTg2MmRlZTYwNmY4NTU2OWUwODhiODI3ZDQ2MmFkNGI0MGRlOTBlYmJhZTVjNzM2Y2E4ZTBjMjBhNCIsInZlcnNpb24iOjF9.4KVR6h7JIHwDX0EbzS503EhVKIFY7MhMU9xLm5OzboYKRnI_8UrjijIVGkT68k20LdFfcVv2oddtcZkrM0CcBw
          - type: rouge
            value: 14.9274
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGU0ZTRhODdlYWNhOGU5YmRkNjU4YWU1MDlhOWZjODI1NGEzMDZkYWI4ZGE0YzBmYTk3ZTljOWM2MGI1NTQ5YiIsInZlcnNpb24iOjF9.0IwWROcDNkQOJ4reQd0zpjyMAeTV5_SG5mydpQZlTVzLlt1SpC6BhitaQFa3_eXcJ_H91JUjJIz9Gjqcow7KDQ
          - type: rouge
            value: 16.6553
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGQ2YmFiZWU4ZGY0NzZiNjk1NjMxOTk4NzI0MTU1MDIwNjdmMGYzMWJiYWJhZTMzZjU3NWNiMDVhNTlmYWNmOCIsInZlcnNpb24iOjF9.GjiA4KFUWw1IWn5q1qRWo-B4BEg04xAe0Lkoi_2zlFcyDoJZUgk1_VHzpmK1F72NO5a55lE-GiMRRxJcES5vCA
          - type: loss
            value: 2.3909709453582764
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzMxYTE4ZWUxZWU4ZGZhNWY0ZjA2ZGU2ZTc5N2FjMjA0ZjI5YTFmMzZmMGI0MDEyMGYzZTllM2I2ZWIxZGEwZSIsInZlcnNpb24iOjF9.BnmMbMl2n3cGwkb6C5BF7mesa6WmFp0EcoqYCdkIdXYdM8Jo2svmaUz-JniLLGVuj-UoAyvUfYQe1dXPPPZcBg
          - type: gen_len
            value: 54.1562
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWJiNmZmMTIyNmNjOTExYzYyNmI5OGVjMTQwOGY3NDk1YTUwYzdlZWE4YmMwYWVmOTE0Mjg3MTEzYjEzMTgwNiIsInZlcnNpb24iOjF9.IisBh3s_yDr6nF-VwobRo8Fe63Qc8Ku_2KgNfjwv16yEPQd5kX8rCg056rT_DhtXzxTxNRMyXLKCodIewbaPAQ

pegasus-samsum

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: 1.4807

Model description

Generates dialogue summaries based on the samsum dataset.

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 15
• total_train_batch_size: 15
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.5421	0.51	500	1.4807

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1