pszemraj's picture
Update README.md
d5ec1fb
|
raw
history blame
6.19 kB
metadata
tags:
  - summarization
  - summary
  - booksum
  - long-document
  - long-form
  - tglobal-xl
  - XL
license:
  - apache-2.0
  - bsd-3-clause
datasets:
  - kmfoda/booksum
metrics:
  - rouge
inference: false

long-t5-tglobal-xl + BookSum

Summarize long text and get a SparkNotes-esque summary of arbitrary topics!

  • Generalizes reasonably well to academic & narrative text.
  • This is the XL checkpoint, which from a human-evaluation perspective, produces even better summaries.

A simple example/use case with the base model on ASR is here.

Cheeky Proof-of-Concept

A summary of the infamous navy seals copypasta:

In this chapter, the monster explains how he intends to exact revenge on "the little b****" who insulted him. He tells the kiddo that he is a highly trained and experienced killer who will use his arsenal of weapons--including his access to the internet--to exact justice on the little brat.

While a somewhat crude example, try running this copypasta through other summarization models to see the difference in comprehension (despite it not even being a "long" text!)


Description

A fine-tuned version of google/long-t5-tglobal-xl on the kmfoda/booksum dataset.

Read the paper by Guo et al. here: LongT5: Efficient Text-To-Text Transformer for Long Sequences

How-To in Python

🚧 LLM.int8() appears to be compatible with summarization and does not degrade the quality of the outputs; this is a crucial enabler for using this model on standard GPUs. A PR for this is in-progress here, and this model card will be updated with instructions once done :) 🚧

Install/update transformers pip install -U transformers

Summarize text with pipeline:

import torch
from transformers import pipeline

summarizer = pipeline(
    "summarization",
    "pszemraj/long-t5-tglobal-xl-16384-book-summary",
    device=0 if torch.cuda.is_available() else -1,
)
long_text = "Here is a lot of text I don't want to read. Replace me"

result = summarizer(long_text)
print(result[0]["summary_text"])

Pass other parameters related to beam search textgen when calling summarizer to get even higher quality results.


About

Intended uses & limitations

While this model seems to improve upon factual consistency, do not take summaries to be foolproof and check things that seem odd.

Specifically: negation statements (i.e., model says: This thing does not have [ATTRIBUTE] where instead it should have said This thing has a lot of [ATTRIBUTE]).

  • I'm sure someone will write a paper on this eventually (if there isn't one already), but you can usually fact-check this by comparing a specific claim to what the surrounding sentences imply.

Training and evaluation data

kmfoda/booksum dataset on HuggingFace - read the original paper here.

  • Initial fine-tuning only used input text with 12288 tokens input or less and 1024 tokens output or less (i.e. rows with longer were dropped before training) for memory reasons. Per brief analysis, summaries in the 12288-16384 range in this dataset are in the small minority
    • In addition, this initial training combined the training and validation sets and trained on these in aggregate to increase the functional dataset size. Therefore, take the validation set results with a grain of salt; primary metrics should be (always) the test set.
  • final phases of fine-tuning used the standard conventions of 16384 input/1024 output keeping everything (truncating longer sequences). This did not appear to change the loss/performance much.

Eval results

Official results with the model evaluator will be computed and posted here.

Please read the note above as due to training methods, validation set performance looks better than the test set results will be. The model achieves the following results on the evaluation set:

  • eval_loss: 1.2756
  • eval_rouge1: 41.8013
  • eval_rouge2: 12.0895
  • eval_rougeL: 21.6007
  • eval_rougeLsum: 39.5382
  • eval_gen_len: 387.2945
  • eval_runtime: 13908.4995
  • eval_samples_per_second: 0.107
  • eval_steps_per_second: 0.027

FAQ

How can I run inference with this on CPU?

lol

How to run inference over a very long (30k+ tokens) document in batches?

See summarize.py in the code for my hf space Document Summarization :)

You can also use the same code to split a document into batches of 4096, etc., and run over those with the model. This is useful in situations where CUDA memory is limited.

How to fine-tune further?

See train with a script and the summarization scripts


Training procedure

Updates

Updates to this model/model card will be posted here as relevant. The model seems fairly converged; if updates/improvements are possible using the BookSum dataset, this repo will be updated.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0006
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 10350
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 128
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 1.0

*Prior training sessions used roughly similar parameters (learning rates were higher); multiple sessions were required as this takes eons to train.

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.6.1
  • Tokenizers 0.13.1