autoevaluator's picture
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
dadbf36
|
raw
history blame
3.11 kB
metadata
model-index:
  - name: sysresearch101/t5-large-xsum-cnn-8-2
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: xsum & Cnn
          type: xsum & Cnn
          config: 3.0.0
          split: train
        metrics:
          - type: rouge
            value: <TODO>
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWU2NDcyODI4ZWRjNzNlNDNmNGJiZTdhMzM0NzdkZGI2MTk0MjQyMzMyNGE3YjdlODRhZWY1Y2E5ZGUwZjhhMCIsInZlcnNpb24iOjF9.aSuwLSyP36OROSU3PMwpPWAGVR-q7pEuL652cwyHqfTxYrYEg2lrcJRnckx3frEfjp619VcM5K7-KkabgmAcCg
          - type: rouge
            value: <TODO>
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmI3NzIxNWViYjJiZDIyZWZmMGQ0ZjM4YTEzNzMxNDJhZDZhZjcxNjY1N2YxOTdmNDZlNzMwNmRhNGRmNDYxNCIsInZlcnNpb24iOjF9.O198sBBmAokotN0OjvEAUoN7NbL_m-TwcOU5bLmKeSFIf1gAYrZ0bD3Q2kFSJZCyNHiktTspEqxCCy5dckS-Cw
          - type: rouge
            value: <TODO>
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI5MjY4ZDU4Mzg5OWI3MjBhNGIwZmE4ODkzNDIxYjcwN2M2NjNkZmFlZjAxMDc3NWFjZTViYzMyNGM4ZWY3NiIsInZlcnNpb24iOjF9.1iA3aMj-Oe_SMbO3C58RjpWKlKztmDTSee9HtvDyEGKC4yfhOwF5lbTNwj2fncsb5GFAo-j7uCAzXN6mC0AKAA
          - type: rouge
            value: <TODO>
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjY2MzAwYmRlZDVjNDVkNmVjMjM3ZjVjM2E5NjZmNzFkYWY5ZTBhYTAzZjExNGZjYTdmNDAwM2Q4NjlmZGIzZSIsInZlcnNpb24iOjF9.kKKgU6CNvYFYYW8PBBlbxdf0oVaAYNLmz5d6v9CeNU8uDcXSpFPq2Wwgars7AwGyCLEJMB2NOOFKdO4kzKB6DA
          - type: loss
            value: <TODO>
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWVlMzI2ZWFkOGY5MWVkOTk5MzgzZjI2MjY2Y2IxM2FkOWExNzFiOWQ3ZDljYjk1ZjUzNTllZDdiY2MwZTQ3ZiIsInZlcnNpb24iOjF9.w49_qsOAqFkSCkQL6UwPacDk-v1mbiqmzonytdkPnpJyVKhMzIHUzxFW4eUbqGQGL6K57OHMnXMjiTrq1C4KDw
          - type: gen_len
            value: <TODO>
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGM4Yzk4YjcwNWUyNDNhMzRlOTdkMjc5YWI2MzU4MGQxYjk3ZTJiYTgzNGUwMGEwODAwZTQzMTY4ZTZiMzFmYiIsInZlcnNpb24iOjF9.0OWxMo_lDMOY7pYVofnGHZeKz-svS-ujAHgY7R3CgXcNXhfFxa4fAUrMbFSs3dcEKjfzLk0RxO-JtqqJUtg6Dw

language: - en tags: - summarization - t5-large-xsum-cnn-8-2 - pipeline:summarization license: mit model-index: - name: sysresearch101/t5-large-xsum-cnn-8-2" results: - task: type: summarization name: Summarization dataset: name: xsum & Cnn type: xsum & Cnn config: 3.0.0 split: train metrics: - name: ROUGE-1 type: rouge value: verified: true - name: ROUGE-2 type: rouge value: verified: true - name: ROUGE-L type: rouge value: verified: true - name: ROUGE-LSUM type: rouge value: verified: true - name: loss type: loss value: verified: true - name: gen_len type: gen_len value: verified: true