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: 37.41
     - name: ROUGE-L (Question Answering)
       type: rouge_l_question_answering
-      value: 0.0
+      value: 75.9
     - name: METEOR (Question Answering)
       type: meteor_question_answering
-      value: 0.05
+      value: 54.68
     - name: BERTScore (Question Answering)
       type: bertscore_question_answering
-      value: 46.91
+      value: 97.07
     - name: MoverScore (Question Answering)
       type: moverscore_question_answering
-      value: 57.15
+      value: 91.88
     - name: AnswerF1Score (Question Answering)
       type: answer_f1_score__question_answering
-      value: 0.0
+      value: 80.37
     - name: AnswerExactMatch (Question Answering)
       type: answer_exact_match_question_answering
-      value: 0.0
+      value: 73.69
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-qa`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ko-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-30000) 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-30000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-30000) 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-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-30000)   
+- **Language model:** [ckpts/mt5-small-trimmed-ko-30000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-30000)   
 - **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        |   46.91 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1           |    0    | 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           |    0.05 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore       |   57.15 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L          |    0    | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| AnswerExactMatch |   73.69 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| AnswerF1Score    |   80.37 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| BERTScore        |   97.07 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_1           |   70.24 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_2           |   61.81 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_3           |   51.41 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_4           |   37.41 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| METEOR           |   54.68 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| MoverScore       |   91.88 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| ROUGE_L          |   75.9  | 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-30000
+ - model: ckpts/mt5-small-trimmed-ko-30000
  - max_length: 512
  - max_length_output: 32
- - epoch: 2
+ - epoch: 5
  - batch: 32
  - lr: 0.001
  - fp16: False
  - random_seed: 1
- - gradient_accumulation_steps: 4
+ - gradient_accumulation_steps: 2
  - label_smoothing: 0.15
 
 The full configuration can be found at [fine-tuning config file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-qa/raw/main/trainer_config.json).

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

@@ -1 +1 @@
-{"validation": {"Bleu_1": 5.281788938022002e-20, "Bleu_2": 2.954026688294874e-18, "Bleu_3": 1.1296889275600474e-14, "Bleu_4": 6.98604052927338e-13, "METEOR": 0.00031457851394420765, "ROUGE_L": 0.0, "BERTScore": 0.45105387869494845, "MoverScore": 0.5728905756968136, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 5.2351351304339714e-20, "Bleu_2": 2.111973160515781e-18, "Bleu_3": 9.12610006214444e-15, "Bleu_4": 5.999066027948329e-13, "METEOR": 0.0005433457687543934, "ROUGE_L": 0.0, "BERTScore": 0.46910824120933714, "MoverScore": 0.5714785307546845, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}}
+{"validation": {"Bleu_1": 0.6992903294141829, "Bleu_2": 0.6127222228962876, "Bleu_3": 0.5083515309130512, "Bleu_4": 0.3635940594823205, "METEOR": 0.5462332421668936, "ROUGE_L": 0.7541467112803363, "BERTScore": 0.9710218722812839, "MoverScore": 0.9181111629442422, "AnswerF1Score": 79.72134499367644, "AnswerExactMatch": 73.06625043357613}, "test": {"Bleu_1": 0.7024203558129186, "Bleu_2": 0.6180556794660192, "Bleu_3": 0.5140638613931836, "Bleu_4": 0.37413409334289116, "METEOR": 0.5468391612861541, "ROUGE_L": 0.7589999956094918, "BERTScore": 0.970729525474637, "MoverScore": 0.9188335398437054, "AnswerF1Score": 80.36954056464982, "AnswerExactMatch": 73.69060006937218}}