commit files to HF hub

README.md

@@ -31,33 +31,33 @@ model-index:
     metrics:
     - name: BLEU4 (Question Answering)
       type: bleu4_question_answering
-      value: 0.05
+      value: 35.86
     - name: ROUGE-L (Question Answering)
       type: rouge_l_question_answering
-      value: 0.53
+      value: 77.74
     - name: METEOR (Question Answering)
       type: meteor_question_answering
-      value: 1.48
+      value: 55.96
     - name: BERTScore (Question Answering)
       type: bertscore_question_answering
-      value: 84.7
+      value: 97.28
     - name: MoverScore (Question Answering)
       type: moverscore_question_answering
-      value: 66.2
+      value: 92.46
     - name: AnswerF1Score (Question Answering)
       type: answer_f1_score__question_answering
-      value: 0.53
+      value: 81.57
     - name: AnswerExactMatch (Question Answering)
       type: answer_exact_match_question_answering
-      value: 0.07
+      value: 75.06
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-ko-60000-koquad-qa`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ko-60000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-60000) 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-60000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-60000) 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-60000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-60000)   
+- **Language model:** [ckpts/mt5-small-trimmed-ko-60000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-60000)   
 - **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 |    0.07 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| AnswerF1Score    |    0.53 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| BERTScore        |   84.7  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1           |    0.83 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_2           |    0.69 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_3           |    0.47 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_4           |    0.05 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| METEOR           |    1.48 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore       |   66.2  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L          |    0.53 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| AnswerExactMatch |   75.06 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| AnswerF1Score    |   81.57 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| BERTScore        |   97.28 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_1           |   71.37 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_2           |   62.48 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_3           |   51    | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_4           |   35.86 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| METEOR           |   55.96 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| MoverScore       |   92.46 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| ROUGE_L          |   77.74 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 
 
 
@@ -114,12 +114,12 @@ The following hyperparameters were used during fine-tuning:
  - input_types: ['paragraph_question']
  - output_types: ['answer']
  - prefix_types: None
- - model: vocabtrimmer/mt5-small-trimmed-ko-60000
+ - model: ckpts/mt5-small-trimmed-ko-60000
  - max_length: 512
  - max_length_output: 32
- - epoch: 10
+ - epoch: 15
  - batch: 32
- - lr: 0.0001
+ - lr: 0.0005
  - fp16: False
  - random_seed: 1
  - gradient_accumulation_steps: 2

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

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.0068073009686840415, "Bleu_2": 0.005111497776260979, "Bleu_3": 0.002971001386257743, "Bleu_4": 0.00039100601197807793, "METEOR": 0.014455087010306053, "ROUGE_L": 0.004424524679446223, "BERTScore": 0.8473668740393592, "MoverScore": 0.6620606055202947, "AnswerF1Score": 0.4364666435426061, "AnswerExactMatch": 0.08671522719389525}, "test": {"Bleu_1": 0.008311329904207443, "Bleu_2": 0.0069253037223347335, "Bleu_3": 0.004728757032836568, "Bleu_4": 0.0005453860595603003, "METEOR": 0.014775190639889654, "ROUGE_L": 0.005340592316391333, "BERTScore": 0.8470447766689886, "MoverScore": 0.6619750696395809, "AnswerF1Score": 0.5264027220322743, "AnswerExactMatch": 0.0693721817551162}}
+{"validation": {"Bleu_1": 0.7118608328939682, "Bleu_2": 0.6261082641370145, "Bleu_3": 0.5241052545619721, "Bleu_4": 0.3834854328398384, "METEOR": 0.5577362960886979, "ROUGE_L": 0.767547458076137, "BERTScore": 0.9716366701786856, "MoverScore": 0.9203647551982136, "AnswerF1Score": 79.6981596851524, "AnswerExactMatch": 73.08359347901491}, "test": {"Bleu_1": 0.7137291089920318, "Bleu_2": 0.6248437350095181, "Bleu_3": 0.5099545735242434, "Bleu_4": 0.35863598370102473, "METEOR": 0.5595853856844631, "ROUGE_L": 0.7774229793701365, "BERTScore": 0.9728185705145407, "MoverScore": 0.924570053934317, "AnswerF1Score": 81.57176419572936, "AnswerExactMatch": 75.06070065903573}}