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:
|
33 |
- name: ROUGE-L (Question Answering)
|
34 |
type: rouge_l_question_answering
|
35 |
-
value:
|
36 |
- name: METEOR (Question Answering)
|
37 |
type: meteor_question_answering
|
38 |
-
value:
|
39 |
- name: BERTScore (Question Answering)
|
40 |
type: bertscore_question_answering
|
41 |
-
value:
|
42 |
- name: MoverScore (Question Answering)
|
43 |
type: moverscore_question_answering
|
44 |
-
value:
|
45 |
- name: AnswerF1Score (Question Answering)
|
46 |
type: answer_f1_score__question_answering
|
47 |
-
value:
|
48 |
- name: AnswerExactMatch (Question Answering)
|
49 |
type: answer_exact_match_question_answering
|
50 |
-
value:
|
51 |
---
|
52 |
|
53 |
# Model Card of `vocabtrimmer/mt5-small-trimmed-it-30000-itquad-qa`
|
54 |
-
This model is fine-tuned version of [
|
55 |
|
56 |
|
57 |
### Overview
|
58 |
-
- **Language model:** [
|
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 |
|
95 |
-
| AnswerF1Score |
|
96 |
-
| BERTScore |
|
97 |
-
| Bleu_1 |
|
98 |
-
| Bleu_2 |
|
99 |
-
| Bleu_3 |
|
100 |
-
| Bleu_4 |
|
101 |
-
| METEOR |
|
102 |
-
| MoverScore |
|
103 |
-
| ROUGE_L |
|
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:
|
116 |
- max_length: 512
|
117 |
- max_length_output: 32
|
118 |
-
- epoch:
|
119 |
- batch: 32
|
120 |
-
- lr: 0.
|
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":
|
|
|
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
|
|