README.md

metadata

language: en
license: apache-2.0
tags:
  - sagemaker
  - bart
  - summarization
datasets:
  - samsum
widget:
  - text: >-
      Sugi: I am tired of everything in my life. 

      Tommy: What? How happy you life is! I do envy you.

      Sugi: You don't know that I have been over-protected by my mother these
      years. I am really about to leave the family and spread my wings.

      Tommy: Maybe you are right. 
model-index:
  - name: bart-large-cnn-samsum
    results:
      - task:
          type: abstractive-text-summarization
          name: Abstractive Text Summarization
        dataset:
          name: >-
            SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive
            Summarization
          type: samsum
        metrics:
          - type: rogue-1
            value: 43.2111
            name: Validation ROGUE-1
          - type: rogue-2
            value: 22.3519
            name: Validation ROGUE-2
          - type: rogue-l
            value: 33.315
            name: Validation ROGUE-L
          - type: rogue-1
            value: 41.8283
            name: Test ROGUE-1
          - type: rogue-2
            value: 20.9857
            name: Test ROGUE-2
          - type: rogue-l
            value: 32.3602
            name: Test ROGUE-L
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: xsum
          type: xsum
          config: default
          split: test
        metrics:
          - type: rouge
            value: 21.5288
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzYyNWVjMjFlYTBhODc5MzU1MjgwZjM4YTlkZmNiOWFhNDhjMDFlMDhkYmIwNWI1MzRmNDM4OWFiN2YyNzc4MyIsInZlcnNpb24iOjF9.jc31m48cpd_2oEqfr_h_N3mJ2EEvyivpNoP_lAeN-QqiJPbT7iWN1RTSzlTMaQjlRTxW3l45-eM9NCbi859eBA
          - type: rouge
            value: 4.3523
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjkxYjNiZTgxYzUwYTYzN2JhZTZiZDBhNjU0Mjg3N2EyY2M4ZjY0MDI5MDdmMTRjNDljZDI3NjdjMjdiN2NhMyIsInZlcnNpb24iOjF9.-yLkLjyRddLpQRBYndrrHsS71frqLMOy_waw1JixjsofLVGkpeciRQubOjDGd307pe7TasA_IUJwDIr2BSNfBw
          - type: rouge
            value: 14.2343
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGMxOGY3ODFhYmIxYjMzMDEwNWFiZmQ1NTAyYzJmNzRiYmM2YjIzMmRkNGY1ZWJhY2UyZDhkZGMwM2Q1ODNlMyIsInZlcnNpb24iOjF9.nzFPJI_6uZZ_8K_n7qt0_OBiMAZh9chekdGqn9xZ_jrQ-ppNVtFZfPweUnpV5JjDAGIzmrxBIi8Y7ci8M13SAA
          - type: rouge
            value: 17.3884
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWVkMjU3MjAwNzM3MjQ1ZGZiN2RhNGRjNDBlMGE2YTU2NDdjOWU2MDc2NDg0MmI5YTY0NjI4NDc0NTBjZGUzMSIsInZlcnNpb24iOjF9.W4TUCxCvddu21StnHsdwBuNIPB8mBqNVRgSOCg0LNNQoCXFI0eOobUIuYGuliYpka3rBEK2BQC4km7yad-vxAw
          - type: loss
            value: 2.78153133392334
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjI4NTk3NWE3YTM0MTZiY2VkYmNhZWU5NWZlZDQ2ZjUxMWM2Y2FiMTk1Y2JmYzBmMmQxMTcxNGRmZWM5ZDM0ZSIsInZlcnNpb24iOjF9.m5UmARkSVyshaDZehFexQgGfUnrZuGvF19MJUjURe7iJlWjpeN8hYtoaa9ym3_0Yc8qykrsTkEIVlM-ft5SjDQ
          - type: gen_len
            value: 73.6503
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTM5MDYzOWJiZTc0ZThmNDAzODA4NDZmMWY5N2JjZWJiOTkzM2Y3MGZkOWU3NGM4MzdkYjI2ZDQ2ZTg3MWMwMiIsInZlcnNpb24iOjF9.Zy82pW8bQHuFcGxDkzNMt4brNUcY4m18tRHieISKVQ77Z7UymFzJ19yW_2MP-ONJv6X2zkTsyUoZDhZ3OYSeBw

bart-large-cnn-samsum

This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container. For more information look at:

• 🤗 Transformers Documentation: Amazon SageMaker
• Example Notebooks
• Amazon SageMaker documentation for Hugging Face
• Python SDK SageMaker documentation for Hugging Face
• Deep Learning Container

Hyperparameters

{
"dataset_name": "samsum",
"do_eval": true,
"do_predict": true,
"do_train": true,
"fp16": true,
"learning_rate": 5e-05,
"model_name_or_path": "facebook/bart-large-cnn",
"num_train_epochs": 3,
"output_dir": "/opt/ml/model",
"per_device_eval_batch_size": 4,
"per_device_train_batch_size": 4,
"predict_with_generate": true,
"seed": 7

}

Usage

from transformers import pipeline
summarizer = pipeline("summarization", model="slauw87/bart-large-cnn-samsum")
conversation = '''Sugi: I am tired of everything in my life. 
Tommy: What? How happy you life is! I do envy you.
Sugi: You don't know that I have been over-protected by my mother these years. I am really about to leave the family and spread my wings.
Tommy: Maybe you are right.                                           
'''
nlp(conversation)

Results

key	value
eval_rouge1	43.2111
eval_rouge2	22.3519
eval_rougeL	33.3153
eval_rougeLsum	40.0527
predict_rouge1	41.8283
predict_rouge2	20.9857
predict_rougeL	32.3602
predict_rougeLsum	38.7316