commit files to HF hub

README.md

@@ -33,27 +33,27 @@ model-index:
     metrics:
     - name: BLEU4 (Question Generation)
       type: bleu4_question_generation
-      value: 0.0
+      value: 11.41
     - name: ROUGE-L (Question Generation)
       type: rouge_l_question_generation
-      value: 0.05
+      value: 26.96
     - name: METEOR (Question Generation)
       type: meteor_question_generation
-      value: 1.52
+      value: 28.19
     - name: BERTScore (Question Generation)
       type: bertscore_question_generation
-      value: 53.33
+      value: 84.1
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
-      value: 48.19
+      value: 82.89
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-ko-15000-koquad-qg`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ko-15000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-15000) for question generation 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 generation 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/)
@@ -89,14 +89,14 @@ output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영
 
 |            |   Score | Type    | Dataset                                                          |
 |:-----------|--------:|:--------|:-----------------------------------------------------------------|
-| BERTScore  |   53.33 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1     |    0.01 | 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     |    1.52 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore |   48.19 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L    |    0.05 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| BERTScore  |   84.1  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_1     |   27.29 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_2     |   20.08 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_3     |   15.08 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_4     |   11.41 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| METEOR     |   28.19 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| MoverScore |   82.89 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| ROUGE_L    |   26.96 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 
 
 
@@ -108,15 +108,15 @@ The following hyperparameters were used during fine-tuning:
  - input_types: paragraph_answer
  - output_types: question
  - 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: 5
- - batch: 16
- - lr: 0.0005
+ - epoch: 15
+ - batch: 64
+ - lr: 0.001
  - fp16: False
  - random_seed: 1
- - gradient_accumulation_steps: 4
+ - 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-qg/raw/main/trainer_config.json).

eval/metric.first.answer.paragraph_answer.question.lmqg_qg_koquad.default.json

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.00025834548172205476, "Bleu_2": 5.0175636956104234e-05, "Bleu_3": 2.962297835379666e-10, "Bleu_4": 7.309011298875784e-13}, "test": {"Bleu_1": 7.411112963889285e-05, "Bleu_2": 8.516453261694912e-13, "Bleu_3": 1.95941221532042e-15, "Bleu_4": 9.544535591096194e-17}}
+{"validation": {"Bleu_1": 0.2573962622743056, "Bleu_2": 0.18663320899957148, "Bleu_3": 0.1388819585282331, "Bleu_4": 0.1047906213707409}, "test": {"Bleu_1": 0.2697019760980053, "Bleu_2": 0.1982222326565144, "Bleu_3": 0.14876549480725032, "Bleu_4": 0.1126191285903239}}

eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_koquad.default.json

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.00032984753713838534, "Bleu_2": 6.523498336271802e-05, "Bleu_3": 3.87458489407366e-10, "Bleu_4": 9.588408525859448e-13, "METEOR": 0.01634679868665742, "ROUGE_L": 0.0008804828189812416, "BERTScore": 0.5326547119599363, "MoverScore": 0.4813786173822095}, "test": {"Bleu_1": 7.596908058420152e-05, "Bleu_2": 8.729478120255356e-13, "Bleu_3": 2.0083041936305836e-15, "Bleu_4": 9.78206351113566e-17, "METEOR": 0.01520266564946064, "ROUGE_L": 0.0005290375067912147, "BERTScore": 0.5332766564813083, "MoverScore": 0.4819022589874832}}
+{"validation": {"Bleu_1": 0.2905307262569751, "Bleu_2": 0.21507857851291853, "Bleu_3": 0.16229763963337976, "Bleu_4": 0.12363771040093172, "METEOR": 0.28697164611245923, "ROUGE_L": 0.2782579478956691, "BERTScore": 0.8328077109594413, "MoverScore": 0.8304753003503604}, "test": {"Bleu_1": 0.27286551769735373, "Bleu_2": 0.20081309705653386, "Bleu_3": 0.1507696338491648, "Bleu_4": 0.11411980750832641, "METEOR": 0.281893492811955, "ROUGE_L": 0.269631536938204, "BERTScore": 0.8410498351761145, "MoverScore": 0.8289075803783602}}