--- license: cc-by-4.0 metrics: - bleu4 - meteor - rouge-l - bertscore - moverscore language: en datasets: - lmqg/qg_squadshifts pipeline_tag: text2text-generation tags: - question generation widget: - text: "generate question: Beyonce 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: "generate question: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records." example_title: "Question Generation Example 2" - text: "generate question: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records ." example_title: "Question Generation Example 3" model-index: - name: lmqg/t5-base-squadshifts-nyt results: - task: name: Text2text Generation type: text2text-generation dataset: name: lmqg/qg_squadshifts type: nyt args: nyt metrics: - name: BLEU4 type: bleu4 value: 0.08526644876436423 - name: ROUGE-L type: rouge-l value: 0.2493349672604139 - name: METEOR type: meteor value: 0.25210676004231025 - name: BERTScore type: bertscore value: 0.9268105589600506 - name: MoverScore type: moverscore value: 0.6469994154715311 --- # Language Models Fine-tuning on Question Generation: `lmqg/t5-base-squadshifts-nyt` This model is fine-tuned version of [lmqg/t5-base-squad](https://huggingface.co/lmqg/t5-base-squad) for question generation task on the [lmqg/qg_squadshifts](https://huggingface.co/datasets/lmqg/qg_squadshifts) (dataset_name: nyt). This model is continuously fine-tuned with [lmqg/t5-base-squad](https://huggingface.co/lmqg/t5-base-squad). ### Overview - **Language model:** [lmqg/t5-base-squad](https://huggingface.co/lmqg/t5-base-squad) - **Language:** en - **Training data:** [lmqg/qg_squadshifts](https://huggingface.co/datasets/lmqg/qg_squadshifts) (nyt) - **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/t5-base-squadshifts-nyt' pipe = pipeline("text2text-generation", model_path) # Question Generation input_text = 'generate question: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.' question = pipe(input_text) ``` ## Evaluation Metrics ### Metrics | Dataset | Type | BLEU4 | ROUGE-L | METEOR | BERTScore | MoverScore | Link | |:--------|:-----|------:|--------:|-------:|----------:|-----------:|-----:| | [lmqg/qg_squadshifts](https://huggingface.co/datasets/lmqg/qg_squadshifts) | nyt | 0.08526644876436423 | 0.2493349672604139 | 0.25210676004231025 | 0.9268105589600506 | 0.6469994154715311 | [link](https://huggingface.co/lmqg/t5-base-squadshifts-nyt/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_squadshifts.nyt.json) | ## Training hyperparameters The following hyperparameters were used during fine-tuning: - dataset_path: lmqg/qg_squadshifts - dataset_name: nyt - input_types: ['paragraph_answer'] - output_types: ['question'] - prefix_types: ['qg'] - model: lmqg/t5-base-squad - max_length: 512 - max_length_output: 32 - epoch: 5 - batch: 8 - lr: 5e-05 - fp16: False - random_seed: 1 - gradient_accumulation_steps: 8 - label_smoothing: 0.15 The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/t5-base-squadshifts-nyt/raw/main/trainer_config.json). ## Citation TBA