asahi417 commited on
Commit
472fa3a
1 Parent(s): 5504a3c

model update

Browse files
README.md ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: cc-by-4.0
4
+ metrics:
5
+ - bleu4
6
+ - meteor
7
+ - rouge-l
8
+ - bertscore
9
+ - moverscore
10
+ language: it
11
+ datasets:
12
+ - lmqg/qag_itquad
13
+ pipeline_tag: text2text-generation
14
+ tags:
15
+ - questions and answers generation
16
+ widget:
17
+ - text: "Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento."
18
+ example_title: "Questions & Answers Generation Example 1"
19
+ model-index:
20
+ - name: lmqg/mt5-small-itquad-qag
21
+ results:
22
+ - task:
23
+ name: Text2text Generation
24
+ type: text2text-generation
25
+ dataset:
26
+ name: lmqg/qag_itquad
27
+ type: default
28
+ args: default
29
+ metrics:
30
+ - name: BLEU4 (Question & Answer Generation)
31
+ type: bleu4_question_answer_generation
32
+ value: 2.96
33
+ - name: ROUGE-L (Question & Answer Generation)
34
+ type: rouge_l_question_answer_generation
35
+ value: 20.56
36
+ - name: METEOR (Question & Answer Generation)
37
+ type: meteor_question_answer_generation
38
+ value: 17.1
39
+ - name: BERTScore (Question & Answer Generation)
40
+ type: bertscore_question_answer_generation
41
+ value: 70.79
42
+ - name: MoverScore (Question & Answer Generation)
43
+ type: moverscore_question_answer_generation
44
+ value: 51.31
45
+ - name: QAAlignedF1Score-BERTScore (Question & Answer Generation)
46
+ type: qa_aligned_f1_score_bertscore_question_answer_generation
47
+ value: 79.41
48
+ - name: QAAlignedRecall-BERTScore (Question & Answer Generation)
49
+ type: qa_aligned_recall_bertscore_question_answer_generation
50
+ value: 77.79
51
+ - name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
52
+ type: qa_aligned_precision_bertscore_question_answer_generation
53
+ value: 81.16
54
+ - name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
55
+ type: qa_aligned_f1_score_moverscore_question_answer_generation
56
+ value: 54.15
57
+ - name: QAAlignedRecall-MoverScore (Question & Answer Generation)
58
+ type: qa_aligned_recall_moverscore_question_answer_generation
59
+ value: 52.94
60
+ - name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
61
+ type: qa_aligned_precision_moverscore_question_answer_generation
62
+ value: 55.49
63
+ ---
64
+
65
+ # Model Card of `lmqg/mt5-small-itquad-qag`
66
+ This model is fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) for question & answer pair generation task on the [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
67
+
68
+
69
+ ### Overview
70
+ - **Language model:** [google/mt5-small](https://huggingface.co/google/mt5-small)
71
+ - **Language:** it
72
+ - **Training data:** [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) (default)
73
+ - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
74
+ - **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
75
+ - **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
76
+
77
+ ### Usage
78
+ - With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
79
+ ```python
80
+ from lmqg import TransformersQG
81
+
82
+ # initialize model
83
+ model = TransformersQG(language="it", model="lmqg/mt5-small-itquad-qag")
84
+
85
+ # model prediction
86
+ question_answer_pairs = model.generate_qa("Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")
87
+
88
+ ```
89
+
90
+ - With `transformers`
91
+ ```python
92
+ from transformers import pipeline
93
+
94
+ pipe = pipeline("text2text-generation", "lmqg/mt5-small-itquad-qag")
95
+ output = pipe("Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")
96
+
97
+ ```
98
+
99
+ ## Evaluation
100
+
101
+
102
+ - ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-itquad-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_itquad.default.json)
103
+
104
+ | | Score | Type | Dataset |
105
+ |:--------------------------------|--------:|:--------|:-------------------------------------------------------------------|
106
+ | BERTScore | 70.79 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
107
+ | Bleu_1 | 17.99 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
108
+ | Bleu_2 | 9.64 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
109
+ | Bleu_3 | 4.94 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
110
+ | Bleu_4 | 2.96 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
111
+ | METEOR | 17.1 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
112
+ | MoverScore | 51.31 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
113
+ | QAAlignedF1Score (BERTScore) | 79.41 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
114
+ | QAAlignedF1Score (MoverScore) | 54.15 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
115
+ | QAAlignedPrecision (BERTScore) | 81.16 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
116
+ | QAAlignedPrecision (MoverScore) | 55.49 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
117
+ | QAAlignedRecall (BERTScore) | 77.79 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
118
+ | QAAlignedRecall (MoverScore) | 52.94 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
119
+ | ROUGE_L | 20.56 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
120
+
121
+
122
+
123
+ ## Training hyperparameters
124
+
125
+ The following hyperparameters were used during fine-tuning:
126
+ - dataset_path: lmqg/qag_itquad
127
+ - dataset_name: default
128
+ - input_types: ['paragraph']
129
+ - output_types: ['questions_answers']
130
+ - prefix_types: None
131
+ - model: google/mt5-small
132
+ - max_length: 512
133
+ - max_length_output: 256
134
+ - epoch: 17
135
+ - batch: 8
136
+ - lr: 0.001
137
+ - fp16: False
138
+ - random_seed: 1
139
+ - gradient_accumulation_steps: 8
140
+ - label_smoothing: 0.0
141
+
142
+ The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-small-itquad-qag/raw/main/trainer_config.json).
143
+
144
+ ## Citation
145
+ ```
146
+ @inproceedings{ushio-etal-2022-generative,
147
+ title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
148
+ author = "Ushio, Asahi and
149
+ Alva-Manchego, Fernando and
150
+ Camacho-Collados, Jose",
151
+ booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
152
+ month = dec,
153
+ year = "2022",
154
+ address = "Abu Dhabi, U.A.E.",
155
+ publisher = "Association for Computational Linguistics",
156
+ }
157
+
158
+ ```
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "lmqg_output/mt5-small-itquad-qag/best_model",
3
  "add_prefix": false,
4
  "architectures": [
5
  "MT5ForConditionalGeneration"
 
1
  {
2
+ "_name_or_path": "lmqg_output/mt5-small-itquad-qag/model_mzgdpa/epoch_16",
3
  "add_prefix": false,
4
  "architectures": [
5
  "MT5ForConditionalGeneration"
eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_itquad.default.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"validation": {"Bleu_1": 0.05471533393654913, "Bleu_2": 0.023175535979002397, "Bleu_3": 0.011770740220343821, "Bleu_4": 0.006901587334642376, "METEOR": 0.12981490120211692, "ROUGE_L": 0.10451935942691314, "BERTScore": 0.6239050075506708, "MoverScore": 0.49727586209586516, "QAAlignedF1Score (BERTScore)": 0.7850520588136973, "QAAlignedRecall (BERTScore)": 0.7856195654633067, "QAAlignedPrecision (BERTScore)": 0.7847373218527518, "QAAlignedF1Score (MoverScore)": 0.534052316533227, "QAAlignedRecall (MoverScore)": 0.533770204836266, "QAAlignedPrecision (MoverScore)": 0.5344726252910555}, "test": {"Bleu_1": 0.17985425283475323, "Bleu_2": 0.09639367877072187, "Bleu_3": 0.04939991867588428, "Bleu_4": 0.02956197207973684, "METEOR": 0.17103777994238578, "ROUGE_L": 0.20558257989004908, "BERTScore": 0.707947664097761, "MoverScore": 0.5131342034262878, "QAAlignedF1Score (BERTScore)": 0.7940547282068218, "QAAlignedRecall (BERTScore)": 0.7778864787808247, "QAAlignedPrecision (BERTScore)": 0.8116168880786454, "QAAlignedF1Score (MoverScore)": 0.5414910892789494, "QAAlignedRecall (MoverScore)": 0.5293679810001514, "QAAlignedPrecision (MoverScore)": 0.554910579282347}}
eval/samples.test.hyp.paragraph.questions_answers.lmqg_qag_itquad.default.txt ADDED
The diff for this file is too large to render. See raw diff
 
eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qag_itquad.default.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e079055beaeadddd71d6c5274a2f9999f1aeea7694f08a79d4ece8fdd6256ebe
3
- size 1200724741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3a252cf249083dde5592cc367cd7cab9db4d03deed19f04db58005dda10e23
3
+ size 1200727429
tokenizer_config.json CHANGED
@@ -2,7 +2,7 @@
2
  "additional_special_tokens": null,
3
  "eos_token": "</s>",
4
  "extra_ids": 0,
5
- "name_or_path": "lmqg_output/mt5-small-itquad-qag/best_model",
6
  "pad_token": "<pad>",
7
  "sp_model_kwargs": {},
8
  "special_tokens_map_file": "/home/c.c2042013/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
 
2
  "additional_special_tokens": null,
3
  "eos_token": "</s>",
4
  "extra_ids": 0,
5
+ "name_or_path": "lmqg_output/mt5-small-itquad-qag/model_mzgdpa/epoch_16",
6
  "pad_token": "<pad>",
7
  "sp_model_kwargs": {},
8
  "special_tokens_map_file": "/home/c.c2042013/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
trainer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"dataset_path": "lmqg/qag_itquad", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": null, "model": "google/mt5-small", "max_length": 512, "max_length_output": 256, "epoch": 17, "batch": 8, "lr": 0.001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 8, "label_smoothing": 0.0}