metadata

language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - pszemraj/govreport-summarization-8192
metrics:
  - rouge
pipeline_tag: summarization
base_model: allenai/led-base-16384
model-index:
  - name: led-base-16384-finetuned-govreport
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: pszemraj/govreport-summarization-8192
          type: pszemraj/govreport-summarization-8192
          config: split
          split: validation
          args: split
        metrics:
          - type: rouge
            value: 50.3574
            name: ROUGE-1
          - type: rouge
            value: 20.0448
            name: ROUGE-2
          - type: rouge
            value: 22.2156
            name: ROUGE-L
          - type: rouge
            value: 22.2156
            name: ROUGE-LSUM
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: pszemraj/govreport-summarization-8192
          type: pszemraj/govreport-summarization-8192
          config: split
          split: test
          args: split
        metrics:
          - type: rouge
            value: 52.6378
            name: ROUGE-1
          - type: rouge
            value: 22.213
            name: ROUGE-2
          - type: rouge
            value: 23.5898
            name: ROUGE-L
          - type: rouge
            value: 23.5898
            name: ROUGE-LSUM

led-base-16384-finetuned-govreport

This model is a fine-tuned version of allenai/led-base-16384 on the pszemraj/govreport-summarization-8192 dataset. It achieves the following results on the evaluation set:

Loss: 1.2887

The rouge metrics calculations were processed later down the line (final notebook can be found HERE).

It achieved the following results on the validation set:

Rouge1: 50.3574
Rouge2: 20.0448
Rougel: 22.2156
Rougelsum: 22.2156

It achieved the following results on the test set:

Rouge1: 52.6378
Rouge2: 22.2130
Rougel: 23.5898
Rougelsum: 23.5898

Model description

As described in Longformer: The Long-Document Transformer by Iz Beltagy, Matthew E. Peters, Arman Cohan, Allenai's Longformer Encoder-Decoder (LED) was initialized from bart-base since both models share the exact same architecture. To be able to process 16K tokens, bart-base's position embedding matrix was simply copied 16 times.

This model is especially interesting for long-range summarization and question answering.

Intended uses & limitations

pszemraj/govreport-summarization-8192 is a pre-processed version of the dataset ccdv/govreport-summarization, which is a dataset for summarization of long documents adapted from this repository and this paper.

The Allenai's LED model was fine-tuned to this dataset, allowing the summarization of documents up to 16384 tokens.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.1492	0.24	250	1.4233
1.0077	0.49	500	1.3813
1.0069	0.73	750	1.3499
0.9639	0.98	1000	1.3216
0.7996	1.22	1250	1.3172
0.9395	1.46	1500	1.3003
0.913	1.71	1750	1.2919
0.8843	1.95	2000	1.2887

Framework versions

Transformers 4.30.2
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.13.3