asahi417 commited on
Commit
5752134
1 Parent(s): e7637c1

commit files to HF hub

Browse files
README.md CHANGED
@@ -29,33 +29,33 @@ model-index:
29
  metrics:
30
  - name: BLEU4 (Question Answering)
31
  type: bleu4_question_answering
32
- value: 0.0
33
  - name: ROUGE-L (Question Answering)
34
  type: rouge_l_question_answering
35
- value: 0.0
36
  - name: METEOR (Question Answering)
37
  type: meteor_question_answering
38
- value: 0.0
39
  - name: BERTScore (Question Answering)
40
  type: bertscore_question_answering
41
- value: 78.42
42
  - name: MoverScore (Question Answering)
43
  type: moverscore_question_answering
44
- value: 57.35
45
  - name: AnswerF1Score (Question Answering)
46
  type: answer_f1_score__question_answering
47
- value: 0.0
48
  - name: AnswerExactMatch (Question Answering)
49
  type: answer_exact_match_question_answering
50
- value: 0.0
51
  ---
52
 
53
  # Model Card of `vocabtrimmer/mt5-small-trimmed-it-30000-itquad-qa`
54
- This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-it-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-it-30000) for question answering task on the [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
55
 
56
 
57
  ### Overview
58
- - **Language model:** [vocabtrimmer/mt5-small-trimmed-it-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-it-30000)
59
  - **Language:** it
60
  - **Training data:** [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (default)
61
  - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
@@ -91,16 +91,16 @@ output = pipe("question: Quale batterio ha il nome del paese che colpisce di pi
91
 
92
  | | Score | Type | Dataset |
93
  |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
94
- | AnswerExactMatch | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
95
- | AnswerF1Score | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
96
- | BERTScore | 78.42 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
97
- | Bleu_1 | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
98
- | Bleu_2 | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
99
- | Bleu_3 | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
100
- | Bleu_4 | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
101
- | METEOR | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
102
- | MoverScore | 57.35 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
103
- | ROUGE_L | 0 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
104
 
105
 
106
 
@@ -112,12 +112,12 @@ The following hyperparameters were used during fine-tuning:
112
  - input_types: ['paragraph_question']
113
  - output_types: ['answer']
114
  - prefix_types: None
115
- - model: vocabtrimmer/mt5-small-trimmed-it-30000
116
  - max_length: 512
117
  - max_length_output: 32
118
- - epoch: 15
119
  - batch: 32
120
- - lr: 0.001
121
  - fp16: False
122
  - random_seed: 1
123
  - gradient_accumulation_steps: 2
 
29
  metrics:
30
  - name: BLEU4 (Question Answering)
31
  type: bleu4_question_answering
32
+ value: 8.94
33
  - name: ROUGE-L (Question Answering)
34
  type: rouge_l_question_answering
35
+ value: 34.48
36
  - name: METEOR (Question Answering)
37
  type: meteor_question_answering
38
+ value: 29.76
39
  - name: BERTScore (Question Answering)
40
  type: bertscore_question_answering
41
+ value: 90.82
42
  - name: MoverScore (Question Answering)
43
  type: moverscore_question_answering
44
+ value: 76.29
45
  - name: AnswerF1Score (Question Answering)
46
  type: answer_f1_score__question_answering
47
+ value: 57.79
48
  - name: AnswerExactMatch (Question Answering)
49
  type: answer_exact_match_question_answering
50
+ value: 42.13
51
  ---
52
 
53
  # Model Card of `vocabtrimmer/mt5-small-trimmed-it-30000-itquad-qa`
54
+ This model is fine-tuned version of [ckpts/mt5-small-trimmed-it-30000](https://huggingface.co/ckpts/mt5-small-trimmed-it-30000) for question answering task on the [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
55
 
56
 
57
  ### Overview
58
+ - **Language model:** [ckpts/mt5-small-trimmed-it-30000](https://huggingface.co/ckpts/mt5-small-trimmed-it-30000)
59
  - **Language:** it
60
  - **Training data:** [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (default)
61
  - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
 
91
 
92
  | | Score | Type | Dataset |
93
  |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
94
+ | AnswerExactMatch | 42.13 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
95
+ | AnswerF1Score | 57.79 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
96
+ | BERTScore | 90.82 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
97
+ | Bleu_1 | 19.62 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
98
+ | Bleu_2 | 14.74 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
99
+ | Bleu_3 | 11.48 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
100
+ | Bleu_4 | 8.94 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
101
+ | METEOR | 29.76 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
102
+ | MoverScore | 76.29 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
103
+ | ROUGE_L | 34.48 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
104
 
105
 
106
 
 
112
  - input_types: ['paragraph_question']
113
  - output_types: ['answer']
114
  - prefix_types: None
115
+ - model: ckpts/mt5-small-trimmed-it-30000
116
  - max_length: 512
117
  - max_length_output: 32
118
+ - epoch: 14
119
  - batch: 32
120
+ - lr: 0.0005
121
  - fp16: False
122
  - random_seed: 1
123
  - gradient_accumulation_steps: 2
eval/metric.first.answer.paragraph_question.answer.lmqg_qg_itquad.default.json CHANGED
@@ -1 +1 @@
1
- {"validation": {"Bleu_1": 5.2042005710051055e-20, "Bleu_2": 7.370353418365926e-20, "Bleu_3": 6.577525285049253e-19, "Bleu_4": 1.9991272477042748e-18, "METEOR": 0.0, "ROUGE_L": 0.0, "BERTScore": 0.7806415340248366, "MoverScore": 0.5755830191823526, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 4.913498975169734e-20, "Bleu_2": 6.958630299902513e-20, "Bleu_3": 1.532690538609496e-15, "Bleu_4": 2.274677505375315e-13, "METEOR": 0.0, "ROUGE_L": 0.0, "BERTScore": 0.7842064072619225, "MoverScore": 0.5734635774203158, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}}
 
1
+ {"validation": {"Bleu_1": 0.19567540209199766, "Bleu_2": 0.14611019529108396, "Bleu_3": 0.11430052277124206, "Bleu_4": 0.08919989082660668, "METEOR": 0.3128926011529463, "ROUGE_L": 0.3399913230386428, "BERTScore": 0.9184621862566789, "MoverScore": 0.7903463105825826, "AnswerF1Score": 61.74394106035301, "AnswerExactMatch": 48.4163490603233}, "test": {"Bleu_1": 0.19616702627236463, "Bleu_2": 0.1474103839266533, "Bleu_3": 0.11480611224143776, "Bleu_4": 0.08944095701349498, "METEOR": 0.29757653797814243, "ROUGE_L": 0.34478731742902624, "BERTScore": 0.9082115225573222, "MoverScore": 0.7628848612210246, "AnswerF1Score": 57.78526676853225, "AnswerExactMatch": 42.1343146274149}}
eval/samples.test.hyp.paragraph_question.answer.lmqg_qg_itquad.default.txt CHANGED
The diff for this file is too large to render. See raw diff
 
eval/samples.validation.hyp.paragraph_question.answer.lmqg_qg_itquad.default.txt CHANGED
The diff for this file is too large to render. See raw diff