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-WIP15
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 24.5482
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 4.811
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 17.2505
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 20.906
            verified: true
          - name: loss
            type: loss
            value: 3.3002164363861084
            verified: true
          - name: gen_len
            type: gen_len
            value: 52
            verified: true
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: billsum
          type: billsum
          config: default
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 37.549
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 12.3315
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 22.15
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 31.4331
            verified: true
          - name: loss
            type: loss
            value: 2.891433000564575
            verified: true
          - name: gen_len
            type: gen_len
            value: 156.7014
            verified: true

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