asahi417 commited on
Commit
5a9954a
1 Parent(s): 6689585

commit files to HF hub

Browse files
README.md CHANGED
@@ -31,33 +31,33 @@ model-index:
31
  metrics:
32
  - name: BLEU4 (Question Answering)
33
  type: bleu4_question_answering
34
- value: 0.0
35
  - name: ROUGE-L (Question Answering)
36
  type: rouge_l_question_answering
37
- value: 0.0
38
  - name: METEOR (Question Answering)
39
  type: meteor_question_answering
40
- value: 0.0
41
  - name: BERTScore (Question Answering)
42
  type: bertscore_question_answering
43
- value: 76.0
44
  - name: MoverScore (Question Answering)
45
  type: moverscore_question_answering
46
- value: 56.83
47
  - name: AnswerF1Score (Question Answering)
48
  type: answer_f1_score__question_answering
49
- value: 0.0
50
  - name: AnswerExactMatch (Question Answering)
51
  type: answer_exact_match_question_answering
52
- value: 0.0
53
  ---
54
 
55
  # Model Card of `vocabtrimmer/mt5-small-trimmed-es-30000-esquad-qa`
56
- This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-es-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-es-30000) for question answering task on the [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
57
 
58
 
59
  ### Overview
60
- - **Language model:** [vocabtrimmer/mt5-small-trimmed-es-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-es-30000)
61
  - **Language:** es
62
  - **Training data:** [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) (default)
63
  - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
@@ -93,16 +93,16 @@ output = pipe("question: ¿Cuál es la población de Nueva York a partir de 2014
93
 
94
  | | Score | Type | Dataset |
95
  |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
96
- | AnswerExactMatch | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
97
- | AnswerF1Score | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
98
- | BERTScore | 76 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
99
- | Bleu_1 | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
100
- | Bleu_2 | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
101
- | Bleu_3 | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
102
- | Bleu_4 | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
103
- | METEOR | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
104
- | MoverScore | 56.83 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
105
- | ROUGE_L | 0 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
106
 
107
 
108
 
@@ -114,10 +114,10 @@ The following hyperparameters were used during fine-tuning:
114
  - input_types: ['paragraph_question']
115
  - output_types: ['answer']
116
  - prefix_types: None
117
- - model: vocabtrimmer/mt5-small-trimmed-es-30000
118
  - max_length: 512
119
  - max_length_output: 32
120
- - epoch: 5
121
  - batch: 32
122
  - lr: 0.001
123
  - fp16: False
 
31
  metrics:
32
  - name: BLEU4 (Question Answering)
33
  type: bleu4_question_answering
34
+ value: 16.41
35
  - name: ROUGE-L (Question Answering)
36
  type: rouge_l_question_answering
37
+ value: 36.91
38
  - name: METEOR (Question Answering)
39
  type: meteor_question_answering
40
+ value: 31.2
41
  - name: BERTScore (Question Answering)
42
  type: bertscore_question_answering
43
+ value: 91.32
44
  - name: MoverScore (Question Answering)
45
  type: moverscore_question_answering
46
+ value: 76.17
47
  - name: AnswerF1Score (Question Answering)
48
  type: answer_f1_score__question_answering
49
+ value: 59.77
50
  - name: AnswerExactMatch (Question Answering)
51
  type: answer_exact_match_question_answering
52
+ value: 40.07
53
  ---
54
 
55
  # Model Card of `vocabtrimmer/mt5-small-trimmed-es-30000-esquad-qa`
56
+ This model is fine-tuned version of [ckpts/mt5-small-trimmed-es-30000](https://huggingface.co/ckpts/mt5-small-trimmed-es-30000) for question answering task on the [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
57
 
58
 
59
  ### Overview
60
+ - **Language model:** [ckpts/mt5-small-trimmed-es-30000](https://huggingface.co/ckpts/mt5-small-trimmed-es-30000)
61
  - **Language:** es
62
  - **Training data:** [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) (default)
63
  - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
 
93
 
94
  | | Score | Type | Dataset |
95
  |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
96
+ | AnswerExactMatch | 40.07 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
97
+ | AnswerF1Score | 59.77 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
98
+ | BERTScore | 91.32 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
99
+ | Bleu_1 | 26.76 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
100
+ | Bleu_2 | 22.12 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
101
+ | Bleu_3 | 18.94 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
102
+ | Bleu_4 | 16.41 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
103
+ | METEOR | 31.2 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
104
+ | MoverScore | 76.17 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
105
+ | ROUGE_L | 36.91 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
106
 
107
 
108
 
 
114
  - input_types: ['paragraph_question']
115
  - output_types: ['answer']
116
  - prefix_types: None
117
+ - model: ckpts/mt5-small-trimmed-es-30000
118
  - max_length: 512
119
  - max_length_output: 32
120
+ - epoch: 12
121
  - batch: 32
122
  - lr: 0.001
123
  - fp16: False
eval/metric.first.answer.paragraph_question.answer.lmqg_qg_esquad.default.json CHANGED
@@ -1 +1 @@
1
- {"validation": {"Bleu_1": 9.157209879439476e-21, "Bleu_2": 2.9771496244621334e-14, "Bleu_3": 4.410418755734242e-12, "Bleu_4": 5.368085304748562e-11, "METEOR": 0.0, "ROUGE_L": 0.0, "BERTScore": 0.7601092422414525, "MoverScore": 0.5686807556820347, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 8.068413417135057e-21, "Bleu_2": 2.623165166145479e-14, "Bleu_3": 3.8860179391376436e-12, "Bleu_4": 4.729817495436722e-11, "METEOR": 0.0, "ROUGE_L": 0.0, "BERTScore": 0.760032703708452, "MoverScore": 0.5682775469652765, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}}
 
1
+ {"validation": {"Bleu_1": 0.2543689320388309, "Bleu_2": 0.21081700245450463, "Bleu_3": 0.17967410616968812, "Bleu_4": 0.1547901032850084, "METEOR": 0.3090184972490415, "ROUGE_L": 0.36326020397428316, "BERTScore": 0.9073617960838293, "MoverScore": 0.7457957707745407, "AnswerF1Score": 57.328260179260475, "AnswerExactMatch": 36.29139072847682}, "test": {"Bleu_1": 0.2676409677908126, "Bleu_2": 0.22116431969989894, "Bleu_3": 0.1893603147694529, "Bleu_4": 0.1641170741095854, "METEOR": 0.3120013708266985, "ROUGE_L": 0.36909569519975893, "BERTScore": 0.9131550461082043, "MoverScore": 0.7617075811094608, "AnswerF1Score": 59.772586703058394, "AnswerExactMatch": 40.06622516556291}}
eval/samples.test.hyp.paragraph_question.answer.lmqg_qg_esquad.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_esquad.default.txt CHANGED
The diff for this file is too large to render. See raw diff