commit files to HF hub

README.md

@@ -31,33 +31,33 @@ model-index:
     metrics:
     - name: BLEU4 (Question Answering)
       type: bleu4_question_answering
-      value: 0.0
+      value: 35.71
     - name: ROUGE-L (Question Answering)
       type: rouge_l_question_answering
-      value: 0.03
+      value: 78.59
     - name: METEOR (Question Answering)
       type: meteor_question_answering
-      value: 0.15
+      value: 56.74
     - name: BERTScore (Question Answering)
       type: bertscore_question_answering
-      value: 87.82
+      value: 97.44
     - name: MoverScore (Question Answering)
       type: moverscore_question_answering
-      value: 55.75
+      value: 92.81
     - name: AnswerF1Score (Question Answering)
       type: answer_f1_score__question_answering
-      value: 0.0
+      value: 82.66
     - name: AnswerExactMatch (Question Answering)
       type: answer_exact_match_question_answering
-      value: 0.0
+      value: 76.41
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-ko-15000-koquad-qa`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ko-15000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-15000) for question answering task on the [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+This model is fine-tuned version of [ckpts/mt5-small-trimmed-ko-15000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-15000) for question answering task on the [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
 
 
 ### Overview
-- **Language model:** [vocabtrimmer/mt5-small-trimmed-ko-15000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-15000)   
+- **Language model:** [ckpts/mt5-small-trimmed-ko-15000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-15000)   
 - **Language:** ko  
 - **Training data:** [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) (default)
 - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
@@ -93,16 +93,16 @@ output = pipe("question: 매드 클라운이 참가해 큰 화제를 모았던
 
 |                  |   Score | Type    | Dataset                                                          |
 |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
-| AnswerExactMatch |    0    | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| AnswerF1Score    |    0    | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| BERTScore        |   87.82 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1           |    0.03 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_2           |    0    | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_3           |    0    | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_4           |    0    | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| METEOR           |    0.15 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore       |   55.75 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L          |    0.03 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| AnswerExactMatch |   76.41 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| AnswerF1Score    |   82.66 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| BERTScore        |   97.44 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_1           |   71.78 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_2           |   62.64 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_3           |   50.82 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_4           |   35.71 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| METEOR           |   56.74 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| MoverScore       |   92.81 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| ROUGE_L          |   78.59 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 
 
 
@@ -114,15 +114,15 @@ The following hyperparameters were used during fine-tuning:
  - input_types: ['paragraph_question']
  - output_types: ['answer']
  - prefix_types: None
- - model: vocabtrimmer/mt5-small-trimmed-ko-15000
+ - model: ckpts/mt5-small-trimmed-ko-15000
  - max_length: 512
  - max_length_output: 32
- - epoch: 11
- - batch: 32
- - lr: 0.0005
+ - epoch: 10
+ - batch: 64
+ - lr: 0.001
  - fp16: False
  - random_seed: 1
- - gradient_accumulation_steps: 2
+ - gradient_accumulation_steps: 1
  - label_smoothing: 0.15
 
 The full configuration can be found at [fine-tuning config file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-15000-koquad-qa/raw/main/trainer_config.json).

eval/metric.first.answer.paragraph_question.answer.lmqg_qg_koquad.default.json

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.0001735357917570349, "Bleu_2": 5.4893508763251e-12, "Bleu_3": 3.1118166081756604e-10, "Bleu_4": 2.3429363790604942e-09, "METEOR": 0.001349463190239542, "ROUGE_L": 0.00015367255452082703, "BERTScore": 0.8778950125961059, "MoverScore": 0.5579643960311111, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 0.0003469812630117673, "Bleu_2": 7.760083328692983e-12, "Bleu_3": 3.9196226310565617e-10, "Bleu_4": 2.785692612025416e-09, "METEOR": 0.001544234012675439, "ROUGE_L": 0.00026273706707397363, "BERTScore": 0.878204313895374, "MoverScore": 0.5575302437571301, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}}
+{"validation": {"Bleu_1": 0.7100208768266482, "Bleu_2": 0.6200193491759389, "Bleu_3": 0.5080818087942911, "Bleu_4": 0.3632132399466476, "METEOR": 0.562890596693216, "ROUGE_L": 0.7740274367814087, "BERTScore": 0.9726204494717963, "MoverScore": 0.9231726569882075, "AnswerF1Score": 81.02993414647949, "AnswerExactMatch": 74.54040929587235}, "test": {"Bleu_1": 0.7178126912874191, "Bleu_2": 0.6263725853703858, "Bleu_3": 0.5082091784867124, "Bleu_4": 0.3570804063484529, "METEOR": 0.5673725371314443, "ROUGE_L": 0.7859017937674925, "BERTScore": 0.9743670976042045, "MoverScore": 0.9280690877126812, "AnswerF1Score": 82.66070721585822, "AnswerExactMatch": 76.41345820326049}}