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: 32.11
     - name: ROUGE-L (Question Answering)
       type: rouge_l_question_answering
-      value: 5.24
+      value: 56.23
     - name: METEOR (Question Answering)
       type: meteor_question_answering
-      value: 2.06
+      value: 41.9
     - name: BERTScore (Question Answering)
       type: bertscore_question_answering
-      value: 82.34
+      value: 95.5
     - name: MoverScore (Question Answering)
       type: moverscore_question_answering
-      value: 54.53
+      value: 84.89
     - name: AnswerF1Score (Question Answering)
       type: answer_f1_score__question_answering
-      value: 7.09
+      value: 75.12
     - name: AnswerExactMatch (Question Answering)
       type: answer_exact_match_question_answering
-      value: 0.0
+      value: 52.98
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-ru-60000-ruquad-qa`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ru-60000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-60000) 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-60000](https://huggingface.co/ckpts/mt5-small-trimmed-ru-60000) 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-60000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-60000)   
+- **Language model:** [ckpts/mt5-small-trimmed-ru-60000](https://huggingface.co/ckpts/mt5-small-trimmed-ru-60000)   
 - **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    |    7.09 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| BERTScore        |   82.34 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| Bleu_1           |    1.09 | 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           |    2.06 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| MoverScore       |   54.53 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
-| ROUGE_L          |    5.24 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| AnswerExactMatch |   52.98 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| AnswerF1Score    |   75.12 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| BERTScore        |   95.5  | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_1           |   49.05 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_2           |   42.9  | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_3           |   37.41 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_4           |   32.11 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| METEOR           |   41.9  | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| MoverScore       |   84.89 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| ROUGE_L          |   56.23 | 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-60000
+ - model: ckpts/mt5-small-trimmed-ru-60000
  - max_length: 512
  - max_length_output: 32
- - epoch: 6
+ - epoch: 18
  - batch: 32
  - lr: 0.0005
  - 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-60000-ruquad-qa/raw/main/trainer_config.json).

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

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.01093612006190296, "Bleu_2": 2.7594205130911637e-05, "Bleu_3": 3.7566675326117114e-06, "Bleu_4": 1.3861020247812055e-06, "METEOR": 0.02149117148067624, "ROUGE_L": 0.05612251395620953, "BERTScore": 0.8235417582905415, "MoverScore": 0.5433182928941788, "AnswerF1Score": 7.5645774293273815, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 0.01092574320590319, "Bleu_2": 2.8598956028053048e-05, "Bleu_3": 3.941394537870388e-06, "Bleu_4": 1.4631868035263949e-06, "METEOR": 0.02059162685618808, "ROUGE_L": 0.052405190326526824, "BERTScore": 0.8234281700054173, "MoverScore": 0.5452990414369595, "AnswerF1Score": 7.09343839603554, "AnswerExactMatch": 0.0}}
+{"validation": {"Bleu_1": 0.5084653442875716, "Bleu_2": 0.44792145890828877, "Bleu_3": 0.3939160692873602, "Bleu_4": 0.34145570880461795, "METEOR": 0.4219550035815873, "ROUGE_L": 0.574153806841515, "BERTScore": 0.9575335951411033, "MoverScore": 0.853596909299789, "AnswerF1Score": 76.24623945348426, "AnswerExactMatch": 54.567116759332805}, "test": {"Bleu_1": 0.49054811866857406, "Bleu_2": 0.4290175872888806, "Bleu_3": 0.3740594423176417, "Bleu_4": 0.3210534168498522, "METEOR": 0.4190175476074441, "ROUGE_L": 0.5622584866956997, "BERTScore": 0.9550280906881389, "MoverScore": 0.8488775275885717, "AnswerF1Score": 75.1229757399946, "AnswerExactMatch": 52.97855440826052}}