asahi417's picture
model update
fc56110
|
raw
history blame
3.67 kB
---
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: en
datasets:
- lmqg/qg_subjqa
pipeline_tag: text2text-generation
tags:
- question generation
widget:
- text: "<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records."
example_title: "Question Generation Example 1"
- text: "Beyonce further expanded her acting career, starring as blues singer <hl> Etta James <hl> in the 2008 musical biopic, Cadillac Records."
example_title: "Question Generation Example 2"
- text: "Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, <hl> Cadillac Records <hl> ."
example_title: "Question Generation Example 3"
model-index:
- name: lmqg/bart-large-subjqa-movies
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_subjqa
type: movies
args: movies
metrics:
- name: BLEU4
type: bleu4
value: 0.04213811599760002
- name: ROUGE-L
type: rouge-l
value: 0.2592040186771708
- name: METEOR
type: meteor
value: 0.21637464104334672
- name: BERTScore
type: bertscore
value: 0.9322845239143867
- name: MoverScore
type: moverscore
value: 0.6240379346458808
---
# Language Models Fine-tuning on Question Generation: `lmqg/bart-large-subjqa-movies`
This model is fine-tuned version of [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad) for question generation task on the
[lmqg/qg_subjqa](https://huggingface.co/datasets/lmqg/qg_subjqa) (dataset_name: movies).
This model is continuously fine-tuned with [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad).
### Overview
- **Language model:** [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad)
- **Language:** en
- **Training data:** [lmqg/qg_subjqa](https://huggingface.co/datasets/lmqg/qg_subjqa) (movies)
- **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
- **Paper:** [TBA](TBA)
### Usage
```python
from transformers import pipeline
model_path = 'lmqg/bart-large-subjqa-movies'
pipe = pipeline("text2text-generation", model_path)
# Question Generation
question = pipe('<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')
```
## Evaluation Metrics
### Metrics
| Dataset | Type | BLEU4 | ROUGE-L | METEOR | BERTScore | MoverScore | Link |
|:--------|:-----|------:|--------:|-------:|----------:|-----------:|-----:|
| [lmqg/qg_subjqa](https://huggingface.co/datasets/lmqg/qg_subjqa) | movies | 0.042 | 0.259 | 0.216 | 0.932 | 0.624 | [link](https://huggingface.co/lmqg/bart-large-subjqa-movies/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_subjqa.movies.json) |
## Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_subjqa
- dataset_name: movies
- input_types: ['paragraph_answer']
- output_types: ['question']
- prefix_types: None
- model: lmqg/bart-large-squad
- max_length: 512
- max_length_output: 32
- epoch: 3
- batch: 8
- lr: 0.0001
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 16
- label_smoothing: 0.15
The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/bart-large-subjqa-movies/raw/main/trainer_config.json).
## Citation
TBA