Hugging Face's logo

research-backup
/
mbart-large-cc25-dequad-qg-ae

Text2Text Generation
Transformers
PyTorch
German
mbart
question generation
answer extraction
Eval Results
Inference Endpoints
Model card Files Community
1
asahi417 commited on
Commit
2f82001
•
1 Parent(s): 725881c

model update

Browse files
Files changed (15) hide show
  1. README.md +215 -0
  2. config.json +1 -1
  3. eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json +1 -0
  4. eval/metric.first.answer.paragraph_answer.question.lmqg_qg_dequad.default.json +1 -0
  5. eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_dequad.default.json +1 -0
  6. eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json +1 -0
  7. eval/samples.test.hyp.paragraph.questions_answers.lmqg_qg_dequad.default.txt +0 -0
  8. eval/samples.test.hyp.paragraph_answer.question.lmqg_qg_dequad.default.txt +0 -0
  9. eval/samples.test.hyp.paragraph_sentence.answer.lmqg_qg_dequad.default.txt +0 -0
  10. eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qg_dequad.default.txt +0 -0
  11. eval/samples.validation.hyp.paragraph_answer.question.lmqg_qg_dequad.default.txt +0 -0
  12. eval/samples.validation.hyp.paragraph_sentence.answer.lmqg_qg_dequad.default.txt +0 -0
  13. pytorch_model.bin +2 -2
  14. tokenizer_config.json +1 -1
  15. trainer_config.json +1 -0
README.md ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: cc-by-4.0
4
+ metrics:
5
+ - bleu4
6
+ - meteor
7
+ - rouge-l
8
+ - bertscore
9
+ - moverscore
10
+ language: de
11
+ datasets:
12
+ - lmqg/qg_dequad
13
+ pipeline_tag: text2text-generation
14
+ tags:
15
+ - question generation
16
+ - answer extraction
17
+ widget:
18
+ - text: "generate question: Empfangs- und Sendeantenne sollen in ihrer Polarisation übereinstimmen, andernfalls <hl> wird die Signalübertragung stark gedämpft. <hl>"
19
+ example_title: "Question Generation Example 1"
20
+ - text: "generate question: das erste weltweit errichtete Hermann Brehmer <hl> 1855 <hl> im niederschlesischen ''Görbersdorf'' (heute Sokołowsko, Polen)."
21
+ example_title: "Question Generation Example 2"
22
+ - text: "generate question: Er muss Zyperngrieche sein und wird direkt für <hl> fünf Jahre <hl> gewählt (Art. 43 Abs. 1 der Verfassung) und verfügt über weitreichende Exekutivkompetenzen."
23
+ example_title: "Question Generation Example 3"
24
+ - text: "extract answers: Sommerzeit <hl> Frühling <hl>: Umstellung von Normalzeit auf Sommerzeit – die Uhr wird um eine Stunde ''vor''gestellt. Herbst: Umstellung von Sommerzeit auf Normalzeit – die Uhr wird um eine Stunde ''zurück''gestellt. Als Sommerzeit wird die gegenüber der Zonenzeit meist um eine Stunde vorgestellte Uhrzeit bezeichnet, die während eines bestimmten Zeitraums im Sommerhalbjahr (und oft auch etwas darüber hinaus) als gesetzliche Zeit dient. Eine solche Regelung wird fast nur in Ländern der gemäßigten Zonen angewandt. Die mitteleuropäische Sommerzeit beginnt am letzten Sonntag im März um 2:00 Uhr MEZ, indem die Stundenzählung um eine Stunde von 2:00 Uhr auf 3:00 Uhr vorgestellt wird. Sie endet jeweils am letzten Sonntag im Oktober um 3:00 Uhr MESZ, indem die Stundenzählung um eine Stunde von 3:00 Uhr auf 2:00 Uhr zurückgestellt wird."
25
+ example_title: "Answer Extraction Example 1"
26
+ - text: "extract answers: Iran === Landwirtschaft === Die landwirtschaftliche Nutzfläche beträgt trotz zahlreicher Gebirge und Wüsten 10 % der Landesfläche, wobei ein Drittel künstlich bewässert wird. Die Landwirtschaft ist einer der größten Arbeitgeber des Landes. Wichtige Produkte sind Pistazien, Weizen, Reis, Zucker, Baumwolle, Früchte, Nüsse, Datteln, Wolle und Kaviar. Seit der Revolution von 1979 wurde der Anbau von Weintrauben wegen des islamischen Alkoholverbots auf den 200.000 Hektar Rebfläche fast vollständig auf Tafeltrauben und Rosinen umgestellt. Bei Rosinen ist <hl> der Iran <hl> inzwischen nach der Türkei der zweitgrößte Exporteur der Welt, bei Safran mit ungefähr 90 % Marktanteil des globalen Bedarfs mit Abstand der größte."
27
+ example_title: "Answer Extraction Example 2"
28
+ model-index:
29
+ - name: lmqg/mbart-large-cc25-dequad-qg-ae
30
+ results:
31
+ - task:
32
+ name: Text2text Generation
33
+ type: text2text-generation
34
+ dataset:
35
+ name: lmqg/qg_dequad
36
+ type: default
37
+ args: default
38
+ metrics:
39
+ - name: BLEU4 (Question Generation)
40
+ type: bleu4_question_generation
41
+ value: 0.78
42
+ - name: ROUGE-L (Question Generation)
43
+ type: rouge_l_question_generation
44
+ value: 12.36
45
+ - name: METEOR (Question Generation)
46
+ type: meteor_question_generation
47
+ value: 15.43
48
+ - name: BERTScore (Question Generation)
49
+ type: bertscore_question_generation
50
+ value: 80.57
51
+ - name: MoverScore (Question Generation)
52
+ type: moverscore_question_generation
53
+ value: 56.4
54
+ - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer))
55
+ type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer
56
+ value: 82.49
57
+ - name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer))
58
+ type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer
59
+ value: 83.67
60
+ - name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer))
61
+ type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer
62
+ value: 81.39
63
+ - name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer))
64
+ type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer
65
+ value: 54.84
66
+ - name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer))
67
+ type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer
68
+ value: 55.13
69
+ - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer))
70
+ type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer
71
+ value: 54.58
72
+ - name: BLEU4 (Answer Extraction)
73
+ type: bleu4_answer_extraction
74
+ value: 6.86
75
+ - name: ROUGE-L (Answer Extraction)
76
+ type: rouge_l_answer_extraction
77
+ value: 20.84
78
+ - name: METEOR (Answer Extraction)
79
+ type: meteor_answer_extraction
80
+ value: 25.56
81
+ - name: BERTScore (Answer Extraction)
82
+ type: bertscore_answer_extraction
83
+ value: 78.8
84
+ - name: MoverScore (Answer Extraction)
85
+ type: moverscore_answer_extraction
86
+ value: 63.5
87
+ - name: AnswerF1Score (Answer Extraction)
88
+ type: answer_f1_score__answer_extraction
89
+ value: 48.09
90
+ - name: AnswerExactMatch (Answer Extraction)
91
+ type: answer_exact_match_answer_extraction
92
+ value: 22.69
93
+ ---
94
+
95
+ # Model Card of `lmqg/mbart-large-cc25-dequad-qg-ae`
96
+ This model is fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) for question generation and answer extraction jointly on the [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
97
+
98
+
99
+ ### Overview
100
+ - **Language model:** [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25)
101
+ - **Language:** de
102
+ - **Training data:** [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (default)
103
+ - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
104
+ - **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
105
+ - **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
106
+
107
+ ### Usage
108
+ - With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
109
+ ```python
110
+ from lmqg import TransformersQG
111
+
112
+ # initialize model
113
+ model = TransformersQG(language="de", model="lmqg/mbart-large-cc25-dequad-qg-ae")
114
+
115
+ # model prediction
116
+ question_answer_pairs = model.generate_qa("das erste weltweit errichtete Hermann Brehmer 1855 im niederschlesischen ''Görbersdorf'' (heute Sokołowsko, Polen).")
117
+
118
+ ```
119
+
120
+ - With `transformers`
121
+ ```python
122
+ from transformers import pipeline
123
+
124
+ pipe = pipeline("text2text-generation", "lmqg/mbart-large-cc25-dequad-qg-ae")
125
+
126
+ # answer extraction
127
+ answer = pipe("generate question: Empfangs- und Sendeantenne sollen in ihrer Polarisation übereinstimmen, andernfalls <hl> wird die Signalübertragung stark gedämpft. <hl>")
128
+
129
+ # question generation
130
+ question = pipe("extract answers: Sommerzeit <hl> Frühling <hl>: Umstellung von Normalzeit auf Sommerzeit – die Uhr wird um eine Stunde ''vor''gestellt. Herbst: Umstellung von Sommerzeit auf Normalzeit – die Uhr wird um eine Stunde ''zurück''gestellt. Als Sommerzeit wird die gegenüber der Zonenzeit meist um eine Stunde vorgestellte Uhrzeit bezeichnet, die während eines bestimmten Zeitraums im Sommerhalbjahr (und oft auch etwas darüber hinaus) als gesetzliche Zeit dient. Eine solche Regelung wird fast nur in Ländern der gemäßigten Zonen angewandt. Die mitteleuropäische Sommerzeit beginnt am letzten Sonntag im März um 2:00 Uhr MEZ, indem die Stundenzählung um eine Stunde von 2:00 Uhr auf 3:00 Uhr vorgestellt wird. Sie endet jeweils am letzten Sonntag im Oktober um 3:00 Uhr MESZ, indem die Stundenzählung um eine Stunde von 3:00 Uhr auf 2:00 Uhr zurückgestellt wird.")
131
+
132
+ ```
133
+
134
+ ## Evaluation
135
+
136
+
137
+ - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-dequad-qg-ae/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json)
138
+
139
+ | | Score | Type | Dataset |
140
+ |:-----------|--------:|:--------|:-----------------------------------------------------------------|
141
+ | BERTScore | 80.57 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
142
+ | Bleu_1 | 11.17 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
143
+ | Bleu_2 | 4.71 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
144
+ | Bleu_3 | 1.96 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
145
+ | Bleu_4 | 0.78 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
146
+ | METEOR | 15.43 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
147
+ | MoverScore | 56.4 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
148
+ | ROUGE_L | 12.36 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
149
+
150
+
151
+ - ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-dequad-qg-ae/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json)
152
+
153
+ | | Score | Type | Dataset |
154
+ |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
155
+ | QAAlignedF1Score (BERTScore) | 82.49 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
156
+ | QAAlignedF1Score (MoverScore) | 54.84 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
157
+ | QAAlignedPrecision (BERTScore) | 81.39 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
158
+ | QAAlignedPrecision (MoverScore) | 54.58 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
159
+ | QAAlignedRecall (BERTScore) | 83.67 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
160
+ | QAAlignedRecall (MoverScore) | 55.13 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
161
+
162
+
163
+ - ***Metric (Answer Extraction)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-dequad-qg-ae/raw/main/eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_dequad.default.json)
164
+
165
+ | | Score | Type | Dataset |
166
+ |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
167
+ | AnswerExactMatch | 22.69 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
168
+ | AnswerF1Score | 48.09 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
169
+ | BERTScore | 78.8 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
170
+ | Bleu_1 | 21.99 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
171
+ | Bleu_2 | 14.92 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
172
+ | Bleu_3 | 10.06 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
173
+ | Bleu_4 | 6.86 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
174
+ | METEOR | 25.56 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
175
+ | MoverScore | 63.5 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
176
+ | ROUGE_L | 20.84 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
177
+
178
+
179
+
180
+ ## Training hyperparameters
181
+
182
+ The following hyperparameters were used during fine-tuning:
183
+ - dataset_path: lmqg/qg_dequad
184
+ - dataset_name: default
185
+ - input_types: ['paragraph_answer', 'paragraph_sentence']
186
+ - output_types: ['question', 'answer']
187
+ - prefix_types: ['qg', 'ae']
188
+ - model: facebook/mbart-large-cc25
189
+ - max_length: 512
190
+ - max_length_output: 32
191
+ - epoch: 11
192
+ - batch: 2
193
+ - lr: 0.0001
194
+ - fp16: False
195
+ - random_seed: 1
196
+ - gradient_accumulation_steps: 32
197
+ - label_smoothing: 0.15
198
+
199
+ The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mbart-large-cc25-dequad-qg-ae/raw/main/trainer_config.json).
200
+
201
+ ## Citation
202
+ ```
203
+ @inproceedings{ushio-etal-2022-generative,
204
+ title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
205
+ author = "Ushio, Asahi and
206
+ Alva-Manchego, Fernando and
207
+ Camacho-Collados, Jose",
208
+ booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
209
+ month = dec,
210
+ year = "2022",
211
+ address = "Abu Dhabi, U.A.E.",
212
+ publisher = "Association for Computational Linguistics",
213
+ }
214
+
215
+ ```
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "lmqg_output/mbart-large-cc25-dequad-qg-ae/best_model",
3
  "_num_labels": 3,
4
  "activation_dropout": 0.0,
5
  "activation_function": "gelu",
1
  {
2
+ "_name_or_path": "lmqg_output/mbart-large-cc25-dequad-qg-ae/model_royfof/epoch_5",
3
  "_num_labels": 3,
4
  "activation_dropout": 0.0,
5
  "activation_function": "gelu",
eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json ADDED
@@ -0,0 +1 @@
 
1
+ {"test": {"QAAlignedF1Score (BERTScore)": 0.8249198011390385, "QAAlignedRecall (BERTScore)": 0.8367233844443898, "QAAlignedPrecision (BERTScore)": 0.8138693062348429, "QAAlignedF1Score (MoverScore)": 0.5484054585685647, "QAAlignedRecall (MoverScore)": 0.5513083410994685, "QAAlignedPrecision (MoverScore)": 0.5458492420502814, "Bleu_1": 0.1489109233265184, "Bleu_2": 0.0662659624408862, "Bleu_3": 0.007567510923746381, "Bleu_4": 0.0016863618161400385, "METEOR": 0.21221588875753641, "ROUGE_L": 0.16097492088647475, "BERTScore": 0.7403533804517255, "MoverScore": 0.5324990565416553}, "validation": {"QAAlignedF1Score (BERTScore)": 0.8226330768112712, "QAAlignedRecall (BERTScore)": 0.8482899399125964, "QAAlignedPrecision (BERTScore)": 0.7988502811490509, "QAAlignedF1Score (MoverScore)": 0.5412647292874186, "QAAlignedRecall (MoverScore)": 0.5536946819745998, "QAAlignedPrecision (MoverScore)": 0.5298499725621244, "Bleu_1": 0.06136131896200784, "Bleu_2": 0.02228588361763564, "Bleu_3": 0.003004580232955343, "Bleu_4": 0.0006493488685082715, "METEOR": 0.15933229870189894, "ROUGE_L": 0.09603341498001779, "BERTScore": 0.6732992982557473, "MoverScore": 0.5122593467606505}}
eval/metric.first.answer.paragraph_answer.question.lmqg_qg_dequad.default.json ADDED
@@ -0,0 +1 @@
 
1
+ {"validation": {"Bleu_1": 0.14313388808170902, "Bleu_2": 0.0669370403282767, "Bleu_3": 0.032635019328414776, "Bleu_4": 0.013184842887020178}, "test": {"Bleu_1": 0.11036501377409993, "Bleu_2": 0.04672651508312955, "Bleu_3": 0.019301994453038946, "Bleu_4": 0.0076703712006606995}}
eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_dequad.default.json ADDED
@@ -0,0 +1 @@
 
1
+ {"validation": {"Bleu_1": 0.30604516340173427, "Bleu_2": 0.21377792302399953, "Bleu_3": 0.1467700185818069, "Bleu_4": 0.101497813022813, "METEOR": 0.30841896613592906, "ROUGE_L": 0.271912611282295, "BERTScore": 0.8301047335789554, "MoverScore": 0.6706578371303324, "AnswerF1Score": 56.6371478419132, "AnswerExactMatch": 27.087114337568057}, "test": {"Bleu_1": 0.21991424487850308, "Bleu_2": 0.14916861707724344, "Bleu_3": 0.10064309143578883, "Bleu_4": 0.06861059185918363, "METEOR": 0.25559643231890666, "ROUGE_L": 0.20839173524250612, "BERTScore": 0.7879794941380106, "MoverScore": 0.6349823126172794, "AnswerF1Score": 48.08755537148499, "AnswerExactMatch": 22.686025408348456}}
eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json ADDED
@@ -0,0 +1 @@
 
1
+ {"validation": {"Bleu_1": 0.14402173913042837, "Bleu_2": 0.06722100427004313, "Bleu_3": 0.03269900072248856, "Bleu_4": 0.013242218344814025, "METEOR": 0.1845141589455621, "ROUGE_L": 0.15485241605878283, "BERTScore": 0.8311071301963169, "MoverScore": 0.5857258555249711}, "test": {"Bleu_1": 0.11170403587443445, "Bleu_2": 0.047050127987994475, "Bleu_3": 0.01955151687590944, "Bleu_4": 0.00782445422861256, "METEOR": 0.15433706766187283, "ROUGE_L": 0.12356335632089663, "BERTScore": 0.8056748387155551, "MoverScore": 0.5640116544682037}}
eval/samples.test.hyp.paragraph.questions_answers.lmqg_qg_dequad.default.txt ADDED
The diff for this file is too large to render. See raw diff
eval/samples.test.hyp.paragraph_answer.question.lmqg_qg_dequad.default.txt ADDED
The diff for this file is too large to render. See raw diff
eval/samples.test.hyp.paragraph_sentence.answer.lmqg_qg_dequad.default.txt ADDED
The diff for this file is too large to render. See raw diff
eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qg_dequad.default.txt ADDED
The diff for this file is too large to render. See raw diff
eval/samples.validation.hyp.paragraph_answer.question.lmqg_qg_dequad.default.txt ADDED
The diff for this file is too large to render. See raw diff
eval/samples.validation.hyp.paragraph_sentence.answer.lmqg_qg_dequad.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 sha256:465055fea5ca442881c4240e940a00d7eb5f50eff5f0382796823203c905eb73
3
- size 2444580125
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1f8e4025c64db24a7c07f6272b039842344f8b22fe6921173e29115926a10a
3
+ size 2444587421
tokenizer_config.json CHANGED
@@ -12,7 +12,7 @@
12
  "single_word": false
13
  },
14
  "model_max_length": 1024,
15
- "name_or_path": "lmqg_output/mbart-large-cc25-dequad-qg-ae/best_model",
16
  "pad_token": "<pad>",
17
  "sep_token": "</s>",
18
  "special_tokens_map_file": null,
12
  "single_word": false
13
  },
14
  "model_max_length": 1024,
15
+ "name_or_path": "lmqg_output/mbart-large-cc25-dequad-qg-ae/model_royfof/epoch_5",
16
  "pad_token": "<pad>",
17
  "sep_token": "</s>",
18
  "special_tokens_map_file": null,
trainer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"dataset_path": "lmqg/qg_dequad", "dataset_name": "default", "input_types": ["paragraph_answer", "paragraph_sentence"], "output_types": ["question", "answer"], "prefix_types": ["qg", "ae"], "model": "facebook/mbart-large-cc25", "max_length": 512, "max_length_output": 32, "epoch": 11, "batch": 2, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 32, "label_smoothing": 0.15}