Hugging Face's logo

pszemraj
/
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP15

Summarization
Transformers
PyTorch
longt5
text2text-generation
summary
booksum
long-document
long-form
Eval Results
Model card Files Community
6
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP15 / README.md
pszemraj's picture
pszemraj
Librarian Bot: Add base_model information to model (#6)
70bd1c8
preview code
|
raw
history blame
8.01 kB
metadata
license:
  - apache-2.0
  - bsd-3-clause
tags:
  - summarization
  - summary
  - booksum
  - long-document
  - long-form
datasets:
  - kmfoda/booksum
metrics:
  - rouge
inference: false
base_model: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13
model-index:
  - name: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP15
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: test
        metrics:
          - type: rouge
            value: 24.5482
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2U3MGNlNzI0MGNiYWQ2NGRhYzg5M2Y3NjhjYTdhZmVlYWNmM2Y0YTFhN2I2ZmI5NDVkY2I2M2MxMjM5ZDIwOSIsInZlcnNpb24iOjF9.tHnV8ofGr9jbx0fHm3cDL6p8nqXZITS1H6XLjW-iWaNFuQJ7Qfs7E0uYNf2haQP6Mu5K5eWWGdg54KtMi1N9DA
          - type: rouge
            value: 4.811
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzE1ODYzOGFhMDE4ZGU1OTM0OTM5NDBkNjEwODQzY2I1NzRhYTc0NDJjZmM5YzI4ZGZmZGNkZjljYmNlYTQ1YyIsInZlcnNpb24iOjF9.n7tOZFKEePwSEqM7a0Y-fBiEEi3jZL7QwP0MCQNun5yKsd2OIkTlruuauV3h8yHN5yKxg33CUfpzS2B44kGjBg
          - type: rouge
            value: 17.2505
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjM3YTYwNjAyYzY5MmZjMzI1MmYwNzI2OWNmMzJiNzk3MTY5Y2E4ZmM1OTIyYjQ1NTkxMjI1ZGMwYmRiYzg5NiIsInZlcnNpb24iOjF9.1VQIehrugMj213RavmSAf1qsKTG3Jmj6DAJGi3KOeOYrJpKeLBQ6ftQZ_wSje8UiyR9uekne1wTd256sr61DBQ
          - type: rouge
            value: 20.906
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDdhNjJlOTY3ZjgxOGMzYjkzOGI2NGJlZDY0MDk0NmE5ZDcyMzIyNTA1M2ZhNmMyOTFlODJjZWJkY2ZjMTQ3NCIsInZlcnNpb24iOjF9.SLAdCUY_9PFb7BrvvpN2ABDU9uvy7EIMEHKtnlpH94nZbv2G2sj74tWLcIQstuTkmXmLTk6_HvdZTEaoUc-5CA
          - type: loss
            value: 3.3002164363861084
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDFkM2UyOWQ5YzM2ZDIwZGRmNTY2YTRlMzUzY2QxZDhkNGFmODljNjIxNWQxZjFhM2E2YjM4ZWRjZDUzNWQxNyIsInZlcnNpb24iOjF9.HUYhxEAGbZS8J76Zt9k5KNFt6dx_vdoqf34k5ht3X0BTB4u2WiYwVS9O0ka2ExCynIODo9OMWLcMG2CW-xnjBA
          - type: gen_len
            value: 52
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTkxMWQ0ZWVlNWUxNjYwNTU3MTQzYjRhZGI1YjQ1ODYxOGRlNTU0ZjlkOGZiN2UzM2I5MjU3Y2QxODU3MTJmZCIsInZlcnNpb24iOjF9.9iDB-q3h2qYZIRHLKryZIjYYUeN_4_9hr5miRgmJl8TYB1Prf69NNziW7QPOkMXMOM-5-xvRVKmx-JqZQSkcDg
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: kmfoda/booksum
          type: kmfoda/booksum
          config: kmfoda--booksum
          split: test
        metrics:
          - type: rouge
            value: 35.3305
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q0NWU1Mjc0ZTYxOGM5NjI3NTlmODYwMmU4ODE3Y2VjYjdmNTRhOWI2MDdlM2U3OTk5N2Q3YTcyYTViYzIwMiIsInZlcnNpb24iOjF9.ScFds-4QZgG0Wro-w0qnoaQSoXXMpWOTEE4zYrvA9k2lew965geaqeBVAt7QQxwchuB9q26hSGYCEqLMdX3EBw
          - type: rouge
            value: 5.8001
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjFiNjU2ZjI1YmE2NDViZjUwMjI1ZWFiNDkyMjExZjJjMjBmN2I5ZmYyYjE0MGEzNzk3ZGE4YTMzNzA0M2NjNSIsInZlcnNpb24iOjF9.H4r1JTjEC3ABkgVIi8i3TRxQ1gMsYoQR8qCBbJVkdWJQwECzWGZRw6QIaWz0kZv73nQ890kf90JE6FKeD2MpAg
          - type: rouge
            value: 16.0557
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjBjNTBiYmM3OWM3ZjFkN2FjZTBiMGJkMTg4MTYxYzRjNWUzNWE2YWVjOWJiMzRkZTMxMGFkYThlYmZiN2UwNSIsInZlcnNpb24iOjF9.mLij-24wue3udXSS5H3kBniefh7NDTmNf3bxacq7UinFkbTtqx9OvS6Ywun4LfJj_Ufn9-uTMR2VbaoIIQKkBA
          - type: rouge
            value: 32.3409
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjg3ODliOTAzYzg4Y2NhNzI4M2I4OGM1ZGQwMWE5ZjBiZGQyNTNhMDQxZDllMzgxOGM0NWZjZTJjMzFkZGVkZSIsInZlcnNpb24iOjF9.LpNcyf7HNaL_xwb4zqrBgOPoTBWFaBN0AgSbzsgfsQ7J12CIi7s0UoBhxg_c8UYwNuqFOZouYIq78r1PM81RCA
          - type: loss
            value: 3.0063540935516357
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTJmMGM2Y2U0MDU0OTFlMzJlNTNlZjViYTAyYjE4YTVkOWJhMmQxZjc3MjM4ZGNkNTNmOTViNDYwZjg0MWI0YyIsInZlcnNpb24iOjF9.VLKkHEjp4Iq1r3-CXSABBzgPJFx1sbjRt5KbbKe_AEuKuJtXI6rRWPuBjudOLB-CHBvutDzVS9wR60pGaQ5jCg
          - type: gen_len
            value: 268.4032
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjJmYjZhOGFkMGNkZjEzOTA0Y2RjNWU3Yjc2ZGI5NWU1MTNjZjY5NzFiZjI0YjBhZjUxMDFlMjBmZTYxMWE0ZCIsInZlcnNpb24iOjF9.vnImpJVQBidfhKVOzEYuA2okKgbTvB0bkc4GNmvkTlxXdZlsqg1KuevQa587lmy0LQOZk1_pYWz0aVJ4VQQQAA
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: launch/gov_report
          type: launch/gov_report
          config: plain_text
          split: test
        metrics:
          - type: rouge
            value: 37.0412
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTQ0NzdhYjdlNDNhYjJmNzQwM2E1OWQ3ZTQxMTZiY2IwNjJkMzE0YzNmMWZjZTI0NGI2NWYzNTU0ODM0OTVmMCIsInZlcnNpb24iOjF9.1Gf6zoMOLmf71bkW9RdiXJPDms-vfc0hu0jJehdb7XCjW-hPcmLxdk8ALwWi9knBmeHZ18GHHSJklgU_maFoAA
          - type: rouge
            value: 8.519
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2M0MTE2YTE5NmE1NjhkMGM0ZjYxMzJiOTFjZGNmOTdlZWFhOTExZTAzOGUyOWE4Yjg4MTE3NDcwZTg5ZDk0MCIsInZlcnNpb24iOjF9.6EeSA2FzddyK5EfHhBViKNDXIZp9svVTpvSi4O_9YULWX6Gs4bZYcGRQATGLS6Pfvh1swky1ZXXR5GpX4tN-Ag
          - type: rouge
            value: 17.8685
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTZmMWRhZmNmZDY5MzYzM2JhNDc5NzdiMWI3MmRlYWViZjA0NGQxZDJhNjIxZTY3ZTM2NTJjYjI0ODE5MGFlYiIsInZlcnNpb24iOjF9.Tz6vT3YFZO5Hd8BySoXmtcwDQMSvr4DLGvKYpTeH7L0iZOaIFr8XILCPbLV6ZxjglSgFwMzcwsjN1d032mEqBA
          - type: rouge
            value: 33.5036
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzgzNGQyMTIxYWUwMDlkMjQwZDE5ZDRmYzczODJkZTIxOGE5MTEyZDNjYzMzZWFhMGUyMjljNDQ5NGQ4ZGRkOCIsInZlcnNpb24iOjF9.oR8vSpgDjMskRmcImHV4E5dkXbP74BKNYXmfpkpO5zIHIJWNNyJvUSKurDDy5rhbhbkI98kF5GmOcLlfghyrDA
          - type: loss
            value: 3.628979444503784
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTNkY2E0Y2Q1YjA3Y2VhYTAyOGE1NmQyYWQ0YzM5NzczOTBkYThiYzNjMDljY2YzZGYzMGQ3NGQ5YzRhN2M5OCIsInZlcnNpb24iOjF9.kD1yDRyt6PR5wKBHvsU4l6stGmcsvPbkGB1dMgSfvMWV0LjjSc3MaXUS2ykNciLdnJK_aSqIjSUbUDyO0e4oDA
          - type: gen_len
            value: 219.3885
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI2MjIyZWViY2I0NTE0YWMxYTE3OTAyODdhOTNlZDZkOTIyMjQ1NzdkMmU5YTY5NmNjYTNkOGI0ODk4YzE2OSIsInZlcnNpb24iOjF9.sqlm-kWBzo-sJ4PaelnJWeQ1usF3nM5ZJP8igXE2GhWNhAQVsST3tlvcA8GwRtfbVCAy_x7Ex9iOuYqpccdbDA

long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP15

This model is a fine-tuned version of pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13 on the kmfoda/booksum dataset.

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: 0.0004
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 64
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 1.4

Framework versions

  • Transformers 4.23.0.dev0
  • Pytorch 1.10.0+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1