---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- generated_from_trainer
- summarization
- stacked summaries
- prompt engineering
datasets:
- stacked-summaries/stacked-samsum-1024
metrics:
- rouge
pipeline_tag: summarization
base_model: google/flan-t5-large
model-index:
- name: flan-t5-large-stacked-samsum1024-WIP3
  results:
  - task:
      type: summarization
      name: Summarization
    dataset:
      name: samsum
      type: samsum
      config: samsum
      split: test
    metrics:
    - type: rouge
      value: 47.6682
      name: ROUGE-1
      verified: true
    - type: rouge
      value: 23.3053
      name: ROUGE-2
      verified: true
    - type: rouge
      value: 39.7678
      name: ROUGE-L
      verified: true
    - type: rouge
      value: 43.259
      name: ROUGE-LSUM
      verified: true
    - type: loss
      value: 2.372586965560913
      name: loss
      verified: true
    - type: gen_len
      value: 17.4237
      name: gen_len
      verified: true
---


# flan-t5-large-stacked-samsum-1024

 <a href="https://colab.research.google.com/gist/pszemraj/a4bf61f593ebda9a8db6dc58839d9de4/brief-demo-flan-t5-stacked-samsum.ipynb">
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>

This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the `stacked-summaries/stacked-samsum-1024` dataset.

It achieves the following results on the evaluation set:
- Loss: 2.1846
- Rouge1: 57.9637
- Rouge2: 28.7446
- Rougel: 44.3826
- Rougelsum: 54.0399
- Gen Len: 122.77

## Model description

This model card presents a model trained on a stacked dataset that 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. In this way, the model can learn to identify essential information without simply mimicking the style of the dataset summaries.

The token used to identify a new concept in the summary is `[NEXT_CONCEPT]`. You can split an output summary based on this token to see how it split the input text information: `summary_text.split("[NEXT_CONCEPT]")` etc.
## Intended uses & limitations

- max input/output is 1024 tokens
- this is mostly a test because `samsum` is not exactly the best dataset for general-purpose summarization

## Training and evaluation data

See the dataset card linked on this page for info

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 4
- seed: 24915
- distributed_type: multi-GPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 1.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 0.1195        | 0.17  | 20   | 2.0635          | 57.8829 | 28.7887 | 44.4256 | 54.1299   | 121.8   |
| 0.1084        | 0.35  | 40   | 2.1178          | 58.0416 | 28.6487 | 44.3905 | 54.1557   | 122.893 |
| 0.1019        | 0.52  | 60   | 2.1576          | 57.816  | 28.7069 | 44.4242 | 53.9598   | 120.524 |
| 0.0975        | 0.7   | 80   | 2.1821          | 57.9597 | 28.8178 | 44.4854 | 54.068    | 121.793 |
| 0.0947        | 0.87  | 100  | 2.1846          | 57.9637 | 28.7446 | 44.3826 | 54.0399   | 122.77  |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.1