Hugging Face's logo

autoevaluate
/
summarization-not-evaluated

Summarization
Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
4
summarization-not-evaluated / README.md
lewtun's picture
lewtun HF staff
Add evaluation results on the autoevaluate--xsum-sample config and test split of autoevaluate/xsum-sample
1bc026d
preview code
|
raw history blame
No virus
3.93 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
  - summarization
datasets:
  - xsum
  - autoevaluate/xsum-sample
metrics:
  - rouge
duplicated_from: autoevaluate/summarization
model-index:
  - name: autoevaluate/summarization-not-evaluated
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: autoevaluate/xsum-sample
          type: autoevaluate/xsum-sample
          config: autoevaluate--xsum-sample
          split: test
        metrics:
          - type: rouge
            value: 18.3975
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWVjY2U1N2I3MmI0ZGVhMzQwN2E0NzY0OTk3NDBjNWZhODVkMDQ4ZDMwYzUwYmQ3MDYyZmFmMTM2NGUwNTMzOSIsInZlcnNpb24iOjF9.-1drSQmRK8GwHjrGWpmCzRLWT9NDfImYiLZEsO4doWMsyz7lik00-roc0wFDrp6JpFb5Uc3vvaJ4dg4SlU3pBw
          - type: rouge
            value: 3.122
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmMxMjlkNzE0NTdiMzg3MTViOGM5ZWRlM2E4ODA0NWM2Y2M5NTQwYTI1NTUxMWJmNmIwNjcwNzYyMjZhNDliMSIsInZlcnNpb24iOjF9._qnIJsSZgY-Cr3lfUGOjsRakjg0L8HZmpI_bZnf2FJxJCOIDd4RjPAsibTdZLL5u3nJK72CstIvzLyAzPEdKCA
          - type: rouge
            value: 14.8693
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWZlNDkxODUwYzgxYzMzYzNlYWJlNDQyYTkxM2FjZmYyYjk1MDBlYmVkNGY3OWQxOTBkOGI2NzYwZTlhMGUyZSIsInZlcnNpb24iOjF9.eV8j4NkoIp2vhbXZGE6Np_DMc7zBB5gycg_wCcejCJ72vN_Pog8K_2Ltu2N-vtStJrM_3QmbZMnWMS0OgCDlCA
          - type: rouge
            value: 14.8537
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjBjOWVhOTNmN2NiYjQyZmYwMzc1NTRjODIwYWY5MDIzYWU2MmQ0N2MxZjUyNDU4MDEzZWM0N2FjNGQxZmQ3NiIsInZlcnNpb24iOjF9.tUF5mFbt4iw3NXX8zmxAWLGKxiOJ0N6pMuot2EiPnGsCKv_s6zKf-Akc1NA89TjLGc8lMvUkKJyFbqIU1n9eBg
          - type: loss
            value: 3.0104541778564453
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTM5NDI0ZjMxOWIwZGFhZTkxMzNkOGRiNjM4YTAxODkyMmZhOGYzNjQ0MTVmZWEyZWU5MTRlODM5YWYzYmIxYiIsInZlcnNpb24iOjF9.uCcjMNr5q_pL6HbVF5cwkh9yO2ni5GieWg5oWjhFWv5ZslnB7OqskPdLt_P3YMYQRUkYRamzdYQYh5qJB7oYCA
          - type: gen_len
            value: 18.05
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjZhNmYxNjYxNTQ4MzA0YTNhYTIwMzVhZTNlMGE5MmI5M2JkZDY4MzA3YTY1Zjk4NjRhNjY5NjcxYjcwYmU3NSIsInZlcnNpb24iOjF9.JKyvAJB5uFL6srWzoj9P_OIK9tnT7GW8mGPFVNrY6SxjbupdIry2iPrM5YpBdt6sLeS5_DgdP80OGGjwfwBiBQ

summarization

This model is a fine-tuned version of t5-small on the xsum dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6690
  • Rouge1: 23.9405
  • Rouge2: 5.0879
  • Rougel: 18.4981
  • Rougelsum: 18.5032
  • Gen Len: 18.7376

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.9249 0.08 1000 2.6690 23.9405 5.0879 18.4981 18.5032 18.7376

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1