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: 31.01
     - name: ROUGE-L (Question Answering)
       type: rouge_l_question_answering
-      value: 1.12
+      value: 56.38
     - name: METEOR (Question Answering)
       type: meteor_question_answering
-      value: 0.72
+      value: 42.45
     - name: BERTScore (Question Answering)
       type: bertscore_question_answering
-      value: 75.5
+      value: 95.56
     - name: MoverScore (Question Answering)
       type: moverscore_question_answering
-      value: 50.19
+      value: 85.0
     - name: AnswerF1Score (Question Answering)
       type: answer_f1_score__question_answering
-      value: 1.11
+      value: 75.89
     - name: AnswerExactMatch (Question Answering)
       type: answer_exact_match_question_answering
-      value: 0.0
+      value: 54.21
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-ru-30000-ruquad-qa`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ru-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-30000) for question answering task on the [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+This model is fine-tuned version of [ckpts/mt5-small-trimmed-ru-30000](https://huggingface.co/ckpts/mt5-small-trimmed-ru-30000) for question answering task on the [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
 
 
 ### Overview
-- **Language model:** [vocabtrimmer/mt5-small-trimmed-ru-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-30000)   
+- **Language model:** [ckpts/mt5-small-trimmed-ru-30000](https://huggingface.co/ckpts/mt5-small-trimmed-ru-30000)   
 - **Language:** ru  
 - **Training data:** [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) (default)
 - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
@@ -93,16 +93,16 @@ output = pipe("question: чем соответствует абсолютная
 
 |                  |   Score | Type    | Dataset                                                          |
 |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
-| AnswerExactMatch |    0    | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| AnswerF1Score    |    1.11 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| BERTScore        |   75.5  | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| Bleu_1           |    0.51 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| Bleu_2           |    0    | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| Bleu_3           |    0    | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| Bleu_4           |    0    | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| METEOR           |    0.72 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| MoverScore       |   50.19 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| ROUGE_L          |    1.12 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| AnswerExactMatch |   54.21 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| AnswerF1Score    |   75.89 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| BERTScore        |   95.56 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_1           |   48.12 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_2           |   41.99 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_3           |   36.41 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_4           |   31.01 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| METEOR           |   42.45 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| MoverScore       |   85    | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| ROUGE_L          |   56.38 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
 
 
 
@@ -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-ru-30000
+ - model: ckpts/mt5-small-trimmed-ru-30000
  - max_length: 512
  - max_length_output: 32
- - epoch: 2
+ - epoch: 11
  - batch: 32
- - lr: 0.0005
+ - 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-ru-30000-ruquad-qa/raw/main/trainer_config.json).

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

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.005392161091891006, "Bleu_2": 0.00022052943827651086, "Bleu_3": 7.712043887246077e-10, "Bleu_4": 1.4567490009728834e-12, "METEOR": 0.007464029379407327, "ROUGE_L": 0.011923779317466878, "BERTScore": 0.754203527396496, "MoverScore": 0.5009299901437565, "AnswerF1Score": 1.1867063794651773, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 0.00513966090454537, "Bleu_2": 6.849127891498507e-12, "Bleu_3": 7.650630276789424e-15, "Bleu_4": 2.582904252708125e-16, "METEOR": 0.007238309068346556, "ROUGE_L": 0.011234022178683594, "BERTScore": 0.7549902469487868, "MoverScore": 0.5018872791923257, "AnswerF1Score": 1.1124788332538513, "AnswerExactMatch": 0.0}}
+{"validation": {"Bleu_1": 0.5037514343719435, "Bleu_2": 0.44383513028191873, "Bleu_3": 0.389802163067304, "Bleu_4": 0.33685731879143715, "METEOR": 0.4299701728244913, "ROUGE_L": 0.5804211539100282, "BERTScore": 0.9592195125540823, "MoverScore": 0.8561376756855387, "AnswerF1Score": 77.64671318853564, "AnswerExactMatch": 56.056393963463066}, "test": {"Bleu_1": 0.4812063129203639, "Bleu_2": 0.4199199083460851, "Bleu_3": 0.3641469383536294, "Bleu_4": 0.310060559115489, "METEOR": 0.42445879306761486, "ROUGE_L": 0.5638048064999157, "BERTScore": 0.9556003167124567, "MoverScore": 0.8500356362906792, "AnswerF1Score": 75.88946589323234, "AnswerExactMatch": 54.20969023034154}}