autoevaluator's picture
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
cdc65ff
|
raw
history blame
2.64 kB
metadata
language:
  - en
tags:
  - summarization
datasets:
  - Blaise-g/autotrain-data-SumPubmed
  - Blaise-g/SumPubmed
widget:
  - text: Biomedical paper of choice 🤗
co2_eq_emissions:
  emissions: 1027.9
model-index:
  - name: Blaise-g/led_pubmed_sumpubmed_1
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: Blaise-g/SumPubmed
          type: Blaise-g/SumPubmed
          config: Blaise-g--SumPubmed
          split: test
        metrics:
          - type: rouge
            value: 41.2523
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDc2YjM2NmQ4OGZlMmZjN2I1ZGViMmRmNDc3OWE3OWQyN2QxZjQ3Njc1YWE5ZDk1NzBjZGMyYjYxYmQ5OTBjMSIsInZlcnNpb24iOjF9.rWD6kDuzu6MDdtE5e4IW2vwOtrT4LVn3VTrON69oHKErs4veNlzCxOpmJwZ4Drb7E4eMdzdotALcO2wv_vuJCw
          - type: rouge
            value: 11.1291
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWFlMjlmODk4MGRiYjRjY2NmNjQyMzdjNDQ2MjM1YmI0N2IxYjU5NjU3MmY4NTg1YzVhNmRlZWU4NTJkMzlkZSIsInZlcnNpb24iOjF9.MZJ1XP2mQLAfOCg54vEH5-Rw5F642xnfoxmLmX86aKy7x5g8T1Ckm2O5KGNDADlz7JAsquBRH5_cqIqbcb8NAg
          - type: rouge
            value: 20.2531
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmU4NGRmMzhmN2U2NWE4NDYyMzQ0MzA5NWZjYzI2NmQ2YzIxMTlkYWM1NDBjYWY3Nzk3ZDVmNTU5OWViNTc3ZCIsInZlcnNpb24iOjF9.u-LuAnEoPfFMTBcFY4QKxU_JnkE936_16y_JSLZC-AHhkfBM8uGzt-H9TVWOmQ9-pYf9obkKb_DW96P9q2ShBw
          - type: rouge
            value: 37.1502
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTI1ZmFiZTM2ZWU1MzcxYzlhMjE1YmY0ZTRiMjMwODc2MjVmNjUzMjhjNzc4M2M2ZTdhMjY1MzVjNmM3OTU2MCIsInZlcnNpb24iOjF9.Kosdbc06Ooj9cwGqCn1ofUD32PKxt05lOkclOXDeFgqOBVLelWXNyh945voFNCgZCiG2jXE0HtuU2gSb36GQCg
          - type: loss
            value: 6.371099948883057
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDhjOWQ5NTI3ZWM3YjZhYTQzYTgyYWE5MGE3NzNkNzY2ODdkODRlMGNlYmM0MTRlMDVhMjc3YTI1M2JhNGUzNCIsInZlcnNpb24iOjF9.yMt_xNnCZK8Mpc0XFkD6BZTSLDid2uVJG_gGQmDXzdkKxSG7VbKoYDWoebAAz9j8mi4uG1RrV9nXXrw9O8GLAg
          - type: gen_len
            value: 193.3744
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDJkMWNkM2ExYzMwMDNlN2QwNTI1MTdhZjkzNDA2M2IzNDliZTQwYWEyMGJmNTRjMWE0YjRmNGNiYjg0NjRlZiIsInZlcnNpb24iOjF9.TL3XEX_w7LbgDmrZAxzBO2g2Z2Uj65nj0vpKLCqC4y_Id-g_-6HphWPTmO7I_aehgk4AAS2MH7SBoZubOBP5Bg

Validation Metrics

  • Loss: 2.133
  • Rouge1: 45.861
  • Rouge2: 14.179
  • RougeL: 23.565
  • RougeLsum: 40.908
  • Gen Len: 195.334