model update

README.md

@@ -0,0 +1,149 @@
+
+---
+license: cc-by-4.0
+metrics:
+- bleu4
+- meteor
+- rouge-l
+- bertscore
+- moverscore
+language: en
+datasets:
+- lmqg/qag_tweetqa
+pipeline_tag: text2text-generation
+tags:
+- questions and answers generation
+widget:
+- text: "generate question and answer:  Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records."
+  example_title: "Questions & Answers Generation Example 1" 
+model-index:
+- name: lmqg/t5-large-tweetqa-qag
+  results:
+  - task:
+      name: Text2text Generation
+      type: text2text-generation
+    dataset:
+      name: lmqg/qag_tweetqa
+      type: default
+      args: default
+    metrics:
+    - name: BLEU4
+      type: bleu4
+      value: 5.960482240567237e-10
+    - name: ROUGE-L
+      type: rouge-l
+      value: 0.0054045507102811466
+    - name: METEOR
+      type: meteor
+      value: 0.0029513976825252613
+    - name: BERTScore
+      type: bertscore
+      value: 0.03922946683914634
+    - name: MoverScore
+      type: moverscore
+      value: 0.45608571714273055
+---
+
+# Model Card of `lmqg/t5-large-tweetqa-qag`
+This model is fine-tuned version of [t5-large](https://huggingface.co/t5-large) for question generation task on the 
+[lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+This model is fine-tuned on the end-to-end question and answer generation.
+
+Please cite our paper if you use the model ([https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)).
+
+```
+
+@inproceedings{ushio-etal-2022-generative,
+    title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
+    author = "Ushio, Asahi  and
+        Alva-Manchego, Fernando  and
+        Camacho-Collados, Jose",
+    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
+    month = dec,
+    year = "2022",
+    address = "Abu Dhabi, U.A.E.",
+    publisher = "Association for Computational Linguistics",
+}
+
+```
+
+### Overview
+- **Language model:** [t5-large](https://huggingface.co/t5-large)   
+- **Language:** en  
+- **Training data:** [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) (default)
+- **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
+- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
+- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
+
+### Usage
+- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
+```python
+
+from lmqg import TransformersQG
+# initialize model
+model = TransformersQG(language='en', model='lmqg/t5-large-tweetqa-qag')
+# model prediction
+question = model.generate_qa(list_context=["William Turner was an English painter who specialised in watercolour landscapes"], list_answer=["William Turner"])
+        
+```
+
+- With `transformers`
+```python
+
+from transformers import pipeline
+# initialize model
+pipe = pipeline("text2text-generation", 'lmqg/t5-large-tweetqa-qag')
+# question generation
+question = pipe('generate question and answer:  Beyonce 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/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.0 | 0.005 | 0.003 | 0.039 | 0.456 | [link](https://huggingface.co/lmqg/t5-large-tweetqa-qag/raw/main/eval/metric.first.sentence.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
+
+
+
+
+## Training hyperparameters
+
+The following hyperparameters were used during fine-tuning:
+ - dataset_path: lmqg/qag_tweetqa
+ - dataset_name: default
+ - input_types: ['paragraph']
+ - output_types: ['questions_answers']
+ - prefix_types: ['qag']
+ - model: t5-large
+ - max_length: 256
+ - max_length_output: 128
+ - epoch: 15
+ - batch: 16
+ - lr: 5e-05
+ - fp16: False
+ - random_seed: 1
+ - gradient_accumulation_steps: 4
+ - label_smoothing: 0.15
+
+The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/t5-large-tweetqa-qag/raw/main/trainer_config.json).
+
+## Citation
+```
+
+@inproceedings{ushio-etal-2022-generative,
+    title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
+    author = "Ushio, Asahi  and
+        Alva-Manchego, Fernando  and
+        Camacho-Collados, Jose",
+    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
+    month = dec,
+    year = "2022",
+    address = "Abu Dhabi, U.A.E.",
+    publisher = "Association for Computational Linguistics",
+}
+
+```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lmqg_output/t5_large_tweetqa/best_model",
+  "_name_or_path": "lmqg_output/t5_large_tweetqa/model_woixzh/epoch_10",
   "add_prefix": true,
   "architectures": [
     "T5ForConditionalGeneration"

eval/metric.first.sentence.paragraph.questions_answers.lmqg_qag_tweetqa.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 2.949014119691204e-10, "Bleu_2": 7.288962467520874e-11, "Bleu_3": 1.603926876322537e-11, "Bleu_4": 1.3497983619005407e-15, "METEOR": 0.0013936164132520032, "ROUGE_L": 0.00245043948954712, "BERTScore": 0.013843970846129832, "MoverScore": 0.4563235198215272}, "test": {"Bleu_1": 0.00018229942730569628, "Bleu_2": 3.209939830954064e-05, "Bleu_3": 7.944684191265035e-06, "Bleu_4": 5.960482240567237e-10, "METEOR": 0.0029513976825252613, "ROUGE_L": 0.0054045507102811466, "BERTScore": 0.03922946683914634, "MoverScore": 0.45608571714273055}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d464da93cab952b1e544e1dada97cb9e4890d0f55fdde0cfcc68ae55c4da0a92
-size 2950727111
+oid sha256:6c7f153ea41c7a5eb2abd6e1e982d3592c8be3c73e953e18f13dc53b557c8024
+size 2950734215

tokenizer_config.json

@@ -104,7 +104,7 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,
-  "name_or_path": "lmqg_output/t5_large_tweetqa/best_model",
+  "name_or_path": "lmqg_output/t5_large_tweetqa/model_woixzh/epoch_10",
   "pad_token": "<pad>",
   "special_tokens_map_file": null,
   "tokenizer_class": "T5Tokenizer",