README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
  - stacked summaries
  - xsum
datasets:
  - stacked-summaries/stacked-xsum-1024
model-index:
  - name: flan-t5-large-stacked-XSUM-1024-WIP-2p8-850-stacked-xsum-1024-evaluated
    results: []
language:
  - en
library_name: transformers
pipeline_tag: summarization

flan-t5-large-stacked-XSUM-1024

This model is a fine-tuned version of google/flan-t5-large on the stacked-summaries/stacked-xsum-1024 dataset.

It achieves the following results on the evaluation set:

• eval_loss: 1.3314
• eval_rouge1: 46.5061
• eval_rouge2: 22.0588
• eval_rougeL: 37.5235
• eval_rougeLsum: 39.0234
• eval_gen_len: 46.1807
• eval_runtime: 9456.3608
• eval_samples_per_second: 1.896
• eval_steps_per_second: 0.119

Note that the evaluation set is stacked-summaries/stacked-xsum-1024 and not xsum itself

Model description

This model card presents a model trained on a stacked dataset, which aims to improve summarization by testing the benefits of "task-oriented pretraining." The model is designed to learn how to effectively condense and distill information from text by stacking summaries and separating them into independent concepts. By doing so, the model can learn to identify essential information without simply mimicking the style of the dataset summaries.

Intended uses & limitations

• max input length (in tokens): 1024

Training and evaluation data

Refer to stacked-summaries/stacked-xsum-1024

Trained for approx 3 epochs before ROUGE scores stabilized on most recent run:

scores

gradients