|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
- summarization |
|
- stacked summaries |
|
- prompt engineering |
|
metrics: |
|
- rouge |
|
datasets: |
|
- stacked-summaries/stacked-samsum-1024 |
|
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: |
|
- name: ROUGE-1 |
|
type: rouge |
|
value: 47.6682 |
|
verified: true |
|
- name: ROUGE-2 |
|
type: rouge |
|
value: 23.3053 |
|
verified: true |
|
- name: ROUGE-L |
|
type: rouge |
|
value: 39.7678 |
|
verified: true |
|
- name: ROUGE-LSUM |
|
type: rouge |
|
value: 43.259 |
|
verified: true |
|
- name: loss |
|
type: loss |
|
value: 2.372586965560913 |
|
verified: true |
|
- name: gen_len |
|
type: gen_len |
|
value: 17.4237 |
|
verified: true |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: summarization |
|
widget: |
|
parameters: |
|
max_length: 128 |
|
min_length: 4 |
|
num_beams: 8 |
|
repetition_penalty: 1.21 |
|
length_penalty: 1 |
|
early_stopping: 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 |
|
|
|
More information needed |
|
|
|
## 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 |
