Hugging Face's logo

pszemraj
/
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13

Summarization
Transformers
PyTorch
longt5
text2text-generation
summary
booksum
long-document
long-form
Eval Results
Model card Files Community
8
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13 / README.md
lewtun's picture
lewtun HF staff
Add evaluation results on the plain_text config and test split of launch/gov_report
263e776
preview code
|
raw
history blame
4.12 kB
metadata
tags:
  - summarization
  - summary
  - booksum
  - long-document
  - long-form
license:
  - apache-2.0
  - bsd-3-clause
datasets:
  - kmfoda/booksum
metrics:
  - rouge
inference: false
model-index:
  - name: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 24.4101
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 5.003
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 17.2544
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 20.9183
            verified: true
          - name: loss
            type: loss
            value: 3.194674015045166
            verified: true
          - name: gen_len
            type: gen_len
            value: 58.9951
            verified: true
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: billsum
          type: billsum
          config: default
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 37.3648
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 12.3316
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 22.075
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 31.1679
            verified: true
          - name: loss
            type: loss
            value: 2.745267391204834
            verified: true
          - name: gen_len
            type: gen_len
            value: 157.3126
            verified: true
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: xsum
          type: xsum
          config: default
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 18.2975
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 2.6806
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 11.9453
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 14.2121
            verified: true
          - name: loss
            type: loss
            value: 4.836681365966797
            verified: true
          - name: gen_len
            type: gen_len
            value: 96.2584
            verified: true
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: launch/gov_report
          type: launch/gov_report
          config: plain_text
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 37.3609
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 8.6943
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 17.9106
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 33.8022
            verified: true
          - name: loss
            type: loss
            value: 3.4974069595336914
            verified: true
          - name: gen_len
            type: gen_len
            value: 243.3453
            verified: true

long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13

Evaluating some metric results before merging with the "main" wip version

This model is a fine-tuned version of pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP12 on the kmfoda/booksum.

The "base" checkpoint that I update when a training session is productive is here

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: 0.0006
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 64
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 1.1

Framework versions

  • Transformers 4.21.2
  • Pytorch 1.10.0+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1