--- license: - apache-2.0 - bsd-3-clause tags: - summarization - summary - booksum - long-document - long-form - tglobal-xl - XL datasets: - kmfoda/booksum metrics: - rouge inference: false model-index: - name: pszemraj/long-t5-tglobal-xl-16384-book-summary results: - task: type: summarization name: Summarization dataset: name: multi_news type: multi_news config: default split: test metrics: - type: rouge value: 36.2043 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzRmMmUyOTVjMmJmZTRiZDcyYzY3MTQ1MmUyNDA5NjVhYzEzYzBiNzcxYTRhMDQ3OTlhMGZjYmJlNDM1M2NjYyIsInZlcnNpb24iOjF9._uArOQ1_0znXDPXMq7unA1OHB-XbgqzzKRbFRcVUzTUJdWk26LiSa2pEEVNNmJPg6Uo7CAvONmhpEswLvl9TAg - type: rouge value: 8.424 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzg0MzljYjVjYWQ3MmRkZDBlOGI5M2RiMGU0M2UwZGUzMDg2NTU0NjcwMTNiN2ZmODEzNTQ0MmEwNDA3NDA5MSIsInZlcnNpb24iOjF9.Dzj85ld6TjosQ8KyUdoadzicMLedEFrICC6Q-08O3qx28d9B9Uke1zw-VWabiuesPEDTRGbWuBgPA5vxYWUZAw - type: rouge value: 17.3721 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDA3ZjZmODAwMTNlM2RlZmJlMDI5MGVkMGRkMTBjMTYzNDk5ZjFiNTY5MWE1MDUwNWI2MDE4ZDA2YWMwMmI2NCIsInZlcnNpb24iOjF9.MOV_nId0XAK1eMQssG5GN9DsitZaTrxl4jdCJnOg9EZ0-vAw227ln599YV5YfZ1OPJnWwek6rneqqyONiHn9AQ - type: rouge value: 32.3994 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmY3MDMwOTZjNWI0YTk1MDgwMzJkYTFiN2U5YWU0Mzc0MWRiMzc1NzZlMDhjMWUwMmY2ODI2MjI5ODBkYWUxOSIsInZlcnNpb24iOjF9._BwGIZbcA4pUBkEAL0cW-JPPta0KSoGug4Z7vogHacUz-AEhIOI5ICUldZh0pt9OK67MpUSzpShJOu3rSt5YDQ - type: loss value: 2.0843334197998047 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWFhMmE5ZjA3ODM4YmVjMDMyMjk5YjNlMjA1MGMzOWY0NTRlYzk1YjZiMzQxMDMxOTMwMjFkNTdmNjM1NDcyMyIsInZlcnNpb24iOjF9.3wbXV4CIIgnfXAnnRztdOR12PwsWsEfiglQQ09K-C1EgW4gai4x9l-wTE2OZ7CTWkuk_tr4tL_uqOCXLZRMtCQ - type: gen_len value: 248.3572 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWZhOGMwMDJjNGU2MzA2YzI1OWU1ZDY5N2NjZmM1YTA5NDg1MzUwNmU1YTBhNjQyNWYwYzA3OGNmODFjMmE2NSIsInZlcnNpb24iOjF9.Rc9u89zCdbFnjsnmq65l_JvCtUwOX_ZWapKJpTZ-rC8HxcUVfi2Ash2QfvvvxHH_YWhwklxxdnNa0HCm46qLAA - task: type: summarization name: Summarization dataset: name: billsum type: billsum config: default split: test metrics: - name: ROUGE-1 type: rouge value: 41.3645 verified: true - name: ROUGE-2 type: rouge value: 16.144 verified: true - name: ROUGE-L type: rouge value: 24.2981 verified: true - name: ROUGE-LSUM type: rouge value: 35.3234 verified: true - name: loss type: loss value: 1.282260775566101 verified: true - name: gen_len type: gen_len value: 291.8158 verified: true - task: type: summarization name: Summarization dataset: name: ccdv/arxiv-summarization type: ccdv/arxiv-summarization config: document split: test metrics: - name: ROUGE-1 type: rouge value: 36.3225 verified: true - name: ROUGE-2 type: rouge value: 9.3743 verified: true - name: ROUGE-L type: rouge value: 19.8396 verified: true - name: ROUGE-LSUM type: rouge value: 32.2532 verified: true - name: loss type: loss value: 2.146871566772461 verified: true - name: gen_len type: gen_len value: 186.2966 verified: true --- # long-t5-tglobal-xl + BookSum Open In Colab Summarize long text and get a SparkNotes-like summary of any topic! - Generalizes reasonably well to academic & narrative text. - This is the XL checkpoint, which **produces even better summaries [from a human evaluation perspective](https://long-t5-xl-book-summary-examples.netlify.app/)**. A simple example/use case with [the base model](https://huggingface.co./pszemraj/long-t5-tglobal-base-16384-book-summary) on ASR is [here](https://longt5-booksum-example.netlify.app/). ## Cheeky Proof-of-Concept A summary of the [infamous navy seals copypasta](https://knowyourmeme.com/memes/navy-seal-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 this is a crude example, try running this copypasta through other summarization models to see the difference in comprehension (_even though it's not even a "long" text!_). * * * **Contents** - [Description](#description) - [How-To in Python](#how-to-in-python) - [Beyond the basics](#beyond-the-basics) - [Adjusting parameters](#adjusting-parameters) - [LLM.int8 Quantization](#llmint8-quantization) - [About](#about) - [Intended uses & limitations](#intended-uses--limitations) - [Training and evaluation data](#training-and-evaluation-data) - [Eval results](#eval-results) - [FAQ](#faq) - [How can I run inference with this on CPU?](#how-can-i-run-inference-with-this-on-cpu) - [How to run inference over a very long (30k+ tokens) document in batches?](#how-to-run-inference-over-a-very-long-30k-tokens-document-in-batches) - [How to fine-tune further?](#how-to-fine-tune-further) - [Are there simpler ways to run this?](#are-there-simpler-ways-to-run-this) - [Training procedure](#training-procedure) - [Updates](#updates) - [Training hyperparameters](#training-hyperparameters) - [Framework versions](#framework-versions) * * * ## Description A fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co./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](https://arxiv.org/pdf/2112.07916.pdf) ## How-To in Python install/update transformers `pip install -U transformers` summarize text with pipeline: ```python 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"]) ``` ### Beyond the basics There are two additional points to consider beyond simple inference: adjusting decoding parameters for improved performance, and quantization for reduced memory consumption. #### Adjusting parameters Pass [other parameters related to beam search textgen](https://huggingface.co./blog/how-to-generate) when calling `summarizer` to get even higher quality results. #### LLM.int8 Quantization > alternative section title: how to get this monster to run inference on free colab runtimes Via [this PR](https://github.com/huggingface/transformers/pull/20341) LLM.int8 is now supported for `long-t5` models. - per **initial tests** the summarization quality seems to hold while using _significantly_ less memory! \* - a version of this model quantized to int8 is [already on the hub here](https://huggingface.co./pszemraj/long-t5-tglobal-xl-16384-book-summary-8bit) so if you're using the 8-bit version anyway, you can start there for a 3.5 gb download only! First, make sure you have the latest versions of the relevant packages: ```bash pip install -U transformers bitsandbytes accelerate ``` load in 8-bit (_magic completed by `bitsandbytes` behind the scenes_) ```python from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained( "pszemraj/long-t5-tglobal-xl-16384-book-summary" ) model = AutoModelForSeq2SeqLM.from_pretrained( "pszemraj/long-t5-tglobal-xl-16384-book-summary", load_in_8bit=True, device_map="auto", ) ``` The above is already present in the Colab demo linked at the top of the model card. \* More rigorous metrics-based research comparing beam-search summarization with and without LLM.int8 will take place over time. * * * ## About ### Intended uses & limitations While this model seems to improve factual consistency, **don't take summaries as foolproof and check things that seem odd**. Specifically: negation statements (i.e., the model says: _this thing does not have [ATTRIBUTE]_, when instead it should have said _this thing has lots of [ATTRIBUTE]_). - I'm sure someone will write a paper on this eventually (if there isn't one already), but you can usually check this by comparing a particular statement with what the surrounding sentences imply. ### Training and evaluation data `kmfoda/booksum` dataset on HuggingFace - read [the original paper here](https://arxiv.org/abs/2105.08209). - For **initial fine-tuning**, only input text with 12288 input tokens or less and 1024 output tokens or less was used (_i.e. lines longer than that were dropped before training_) for memory reasons. After a quick analysis, summaries in the 12288-16384 range are in the **small** minority in this dataset. - In addition, this initial training combined the training and validation sets and trained on them in aggregate to increase the functional dataset size. **Therefore, take the validation set results with a grain of salt; primary metrics should (always) be the test set.**. - The **final stages of fine-tuning** used the standard 16384 input/1024 output conventions, preserving the standard in/out lengths (_and truncating longer sequences_). This did not seem to change the loss/performance much. ### Eval results Official results with the [model evaluator](https://huggingface.co./spaces/autoevaluate/model-evaluator) will be computed and posted here. **Please read the note above, as due to the training methods, the performance on the validation set looks better than the results on the test set 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 ***** predict/test metrics (initial) ***** predict_gen_len = 506.4368 predict_loss = 2.028 predict_rouge1 = 36.8815 predict_rouge2 = 8.0625 predict_rougeL = 17.6161 predict_rougeLsum = 34.9068 predict_runtime = 2:04:14.37 predict_samples = 1431 predict_samples_per_second = 0.192 predict_steps_per_second = 0.048 \* evaluating big model not as easy as it seems. Doing a bit more investigating * * * ## 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](https://huggingface.co./spaces/pszemraj/document-summarization/blob/main/summarize.py) :) You can also use the same code to split a document into batches of 4096, etc., and iterate over them with the model. This is useful in situations where CUDA memory is limited. **Update:** see the section on the `textsum` package below. ### How to fine-tune further? See [train with a script](https://huggingface.co./docs/transformers/run_scripts) and [the summarization scripts](https://github.com/huggingface/transformers/tree/main/examples/pytorch/summarization) ### Are there simpler ways to run this? For this reason, I created a Python package utility. It's called [textsum](https://github.com/pszemraj/textsum), and you can use it to load models and summarize things in a few lines of code. ```sh pip install textsum ``` Use `textsum` in python with this model: ```python from textsum.summarize import Summarizer summarizer = Summarizer( model_name_or_path="pszemraj/long-t5-tglobal-xl-16384-book-summary" ) long_string = "This is a long string of text that will be summarized." out_str = summarizer.summarize_string(long_string) print(f"summary: {out_str}") ``` This package provides easy-to-use interfaces for applying summarization models to text documents of arbitrary length. Currently implemented interfaces include a Python API, a CLI, and a shareable demo application. For details, explanations, and documentation, see the README (_linked above_) or the [wiki](https://github.com/pszemraj/textsum/wiki). * * * ## Training procedure ### Updates Updates to this model/model card will be posted here when relevant. The model seems to be 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 * * *