model update

README.md

@@ -0,0 +1,158 @@
+
+---
+license: cc-by-4.0
+metrics:
+- bleu4
+- meteor
+- rouge-l
+- bertscore
+- moverscore
+language: fr
+datasets:
+- lmqg/qag_frquad
+pipeline_tag: text2text-generation
+tags:
+- questions and answers generation
+widget:
+- text: "Créateur » (Maker), lui aussi au singulier, « le Suprême Berger » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc."
+  example_title: "Questions & Answers Generation Example 1" 
+model-index:
+- name: lmqg/mbart-large-cc25-frquad-qag
+  results:
+  - task:
+      name: Text2text Generation
+      type: text2text-generation
+    dataset:
+      name: lmqg/qag_frquad
+      type: default
+      args: default
+    metrics:
+    - name: BLEU4 (Question & Answer Generation)
+      type: bleu4_question_answer_generation
+      value: 2.33
+    - name: ROUGE-L (Question & Answer Generation)
+      type: rouge_l_question_answer_generation
+      value: 15.28
+    - name: METEOR (Question & Answer Generation)
+      type: meteor_question_answer_generation
+      value: 19.18
+    - name: BERTScore (Question & Answer Generation)
+      type: bertscore_question_answer_generation
+      value: 66.36
+    - name: MoverScore (Question & Answer Generation)
+      type: moverscore_question_answer_generation
+      value: 50.56
+    - name: QAAlignedF1Score-BERTScore (Question & Answer Generation)
+      type: qa_aligned_f1_score_bertscore_question_answer_generation
+      value: 77.75
+    - name: QAAlignedRecall-BERTScore (Question & Answer Generation)
+      type: qa_aligned_recall_bertscore_question_answer_generation
+      value: 79.45
+    - name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
+      type: qa_aligned_precision_bertscore_question_answer_generation
+      value: 76.19
+    - name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
+      type: qa_aligned_f1_score_moverscore_question_answer_generation
+      value: 53.5
+    - name: QAAlignedRecall-MoverScore (Question & Answer Generation)
+      type: qa_aligned_recall_moverscore_question_answer_generation
+      value: 54.55
+    - name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
+      type: qa_aligned_precision_moverscore_question_answer_generation
+      value: 52.57
+---
+
+# Model Card of `lmqg/mbart-large-cc25-frquad-qag`
+This model is fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) for question & answer pair generation task on the [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+
+
+### Overview
+- **Language model:** [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25)   
+- **Language:** fr  
+- **Training data:** [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) (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="fr", model="lmqg/mbart-large-cc25-frquad-qag")
+
+# model prediction
+question_answer_pairs = model.generate_qa("Créateur » (Maker), lui aussi au singulier, « le Suprême Berger » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc.")
+
+```
+
+- With `transformers`
+```python
+from transformers import pipeline
+
+pipe = pipeline("text2text-generation", "lmqg/mbart-large-cc25-frquad-qag")
+output = pipe("Créateur » (Maker), lui aussi au singulier, « le Suprême Berger » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc.")
+
+```
+
+## Evaluation
+
+
+- ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-frquad-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_frquad.default.json) 
+
+|                                 |   Score | Type    | Dataset                                                            |
+|:--------------------------------|--------:|:--------|:-------------------------------------------------------------------|
+| BERTScore                       |   66.36 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| Bleu_1                          |    9.92 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| Bleu_2                          |    5.52 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| Bleu_3                          |    3.47 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| Bleu_4                          |    2.33 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| METEOR                          |   19.18 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| MoverScore                      |   50.56 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| QAAlignedF1Score (BERTScore)    |   77.75 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| QAAlignedF1Score (MoverScore)   |   53.5  | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| QAAlignedPrecision (BERTScore)  |   76.19 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| QAAlignedPrecision (MoverScore) |   52.57 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| QAAlignedRecall (BERTScore)     |   79.45 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| QAAlignedRecall (MoverScore)    |   54.55 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+| ROUGE_L                         |   15.28 | default | [lmqg/qag_frquad](https://huggingface.co/datasets/lmqg/qag_frquad) |
+
+
+
+## Training hyperparameters
+
+The following hyperparameters were used during fine-tuning:
+ - dataset_path: lmqg/qag_frquad
+ - dataset_name: default
+ - input_types: ['paragraph']
+ - output_types: ['questions_answers']
+ - prefix_types: None
+ - model: facebook/mbart-large-cc25
+ - max_length: 512
+ - max_length_output: 256
+ - epoch: 14
+ - batch: 2
+ - lr: 0.0001
+ - fp16: False
+ - random_seed: 1
+ - gradient_accumulation_steps: 64
+ - label_smoothing: 0.0
+
+The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mbart-large-cc25-frquad-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/mbart-large-cc25-frquad-qag/best_model",
+  "_name_or_path": "lmqg_output/mbart-large-cc25-frquad-qag/model_hrqcsz/epoch_5",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",

eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_frquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.280484007295694, "Bleu_2": 0.17016920349675446, "Bleu_3": 0.10850214395213244, "Bleu_4": 0.07675767048310689, "METEOR": 0.23512622929759355, "ROUGE_L": 0.2407060201716333, "BERTScore": 0.7393606378852079, "MoverScore": 0.5307557710097831, "QAAlignedF1Score (BERTScore)": 0.7959976183698224, "QAAlignedRecall (BERTScore)": 0.7894592275650848, "QAAlignedPrecision (BERTScore)": 0.8035495311526271, "QAAlignedF1Score (MoverScore)": 0.5523084353530766, "QAAlignedRecall (MoverScore)": 0.5449440659460966, "QAAlignedPrecision (MoverScore)": 0.5604759809142831}, "test": {"Bleu_1": 0.0992479700187378, "Bleu_2": 0.055163278694192554, "Bleu_3": 0.03474471559535957, "Bleu_4": 0.02331968844548859, "METEOR": 0.19184708809287473, "ROUGE_L": 0.15278468971081488, "BERTScore": 0.6636021556645595, "MoverScore": 0.5055571079148972, "QAAlignedF1Score (BERTScore)": 0.7775349659485863, "QAAlignedRecall (BERTScore)": 0.7944941795788644, "QAAlignedPrecision (BERTScore)": 0.7619403121714198, "QAAlignedF1Score (MoverScore)": 0.5350198819600969, "QAAlignedRecall (MoverScore)": 0.5454870926150593, "QAAlignedPrecision (MoverScore)": 0.5256663345681905}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b9e340281f4ef9138e3085eeff61ae36d67920ea07688b19a8d2a7d794e3d6
-size 2444580125
+oid sha256:d73e13bd8243c124302a1010460c21ae195e2079fcd84110b06ab9873a417bb2
+size 2444587421

tokenizer_config.json

@@ -12,7 +12,7 @@
     "single_word": false
   },
   "model_max_length": 1024,
-  "name_or_path": "lmqg_output/mbart-large-cc25-frquad-qag/best_model",
+  "name_or_path": "lmqg_output/mbart-large-cc25-frquad-qag/model_hrqcsz/epoch_5",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "special_tokens_map_file": null,

trainer_config.json

@@ -0,0 +1 @@
+{"dataset_path": "lmqg/qag_frquad", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": null, "model": "facebook/mbart-large-cc25", "max_length": 512, "max_length_output": 256, "epoch": 14, "batch": 2, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 64, "label_smoothing": 0.0}