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: 16.3
     - name: ROUGE-L (Question Answering)
       type: rouge_l_question_answering
-      value: 0.0
+      value: 29.14
     - name: METEOR (Question Answering)
       type: meteor_question_answering
-      value: 0.0
+      value: 22.81
     - name: BERTScore (Question Answering)
       type: bertscore_question_answering
-      value: 84.11
+      value: 88.96
     - name: MoverScore (Question Answering)
       type: moverscore_question_answering
-      value: 56.71
+      value: 70.99
     - name: AnswerF1Score (Question Answering)
       type: answer_f1_score__question_answering
-      value: 0.0
+      value: 44.9
     - name: AnswerExactMatch (Question Answering)
       type: answer_exact_match_question_answering
-      value: 0.0
+      value: 27.35
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-fr-30000-frquad-qa`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-fr-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-fr-30000) for question answering task on the [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+This model is fine-tuned version of [ckpts/mt5-small-trimmed-fr-30000](https://huggingface.co/ckpts/mt5-small-trimmed-fr-30000) for question answering task on the [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
 
 
 ### Overview
-- **Language model:** [vocabtrimmer/mt5-small-trimmed-fr-30000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-fr-30000)   
+- **Language model:** [ckpts/mt5-small-trimmed-fr-30000](https://huggingface.co/ckpts/mt5-small-trimmed-fr-30000)   
 - **Language:** fr  
 - **Training data:** [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) (default)
 - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
@@ -93,16 +93,16 @@ output = pipe("question: En quelle année a-t-on trouvé trace d'un haut fournea
 
 |                  |   Score | Type    | Dataset                                                          |
 |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
-| AnswerExactMatch |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| AnswerF1Score    |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| BERTScore        |   84.11 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| Bleu_1           |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| Bleu_2           |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| Bleu_3           |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| Bleu_4           |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| METEOR           |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| MoverScore       |   56.71 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
-| ROUGE_L          |    0    | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| AnswerExactMatch |   27.35 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| AnswerF1Score    |   44.9  | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| BERTScore        |   88.96 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_1           |   25.75 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_2           |   21.64 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_3           |   18.76 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_4           |   16.3  | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| METEOR           |   22.81 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| MoverScore       |   70.99 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| ROUGE_L          |   29.14 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 
 
 
@@ -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-fr-30000
+ - model: ckpts/mt5-small-trimmed-fr-30000
  - max_length: 512
  - max_length_output: 32
- - epoch: 10
+ - epoch: 25
  - batch: 32
- - lr: 0.0001
+ - 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-fr-30000-frquad-qa/raw/main/trainer_config.json).

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

@@ -1 +1 @@
-{"validation": {"Bleu_1": 1.148764872165851e-20, "Bleu_2": 2.051116381898933e-14, "Bleu_3": 2.4883417255587024e-12, "Bleu_4": 2.7407528945568e-11, "METEOR": 0.0, "ROUGE_L": 0.0, "BERTScore": 0.83944442877581, "MoverScore": 0.5572601194256782, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 2.2365528462612175e-20, "Bleu_2": 3.99335868731784e-14, "Bleu_3": 4.8446012788293055e-12, "Bleu_4": 5.336025531197385e-11, "METEOR": 0.0, "ROUGE_L": 0.0, "BERTScore": 0.841128488724474, "MoverScore": 0.5670619769894022, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}}
+{"validation": {"Bleu_1": 0.2719406674907125, "Bleu_2": 0.23125680748845742, "Bleu_3": 0.2021131198948813, "Bleu_4": 0.17765468146168675, "METEOR": 0.21844072866024636, "ROUGE_L": 0.2823806919184276, "BERTScore": 0.8871024666234869, "MoverScore": 0.6938775091152997, "AnswerF1Score": 43.09028101270347, "AnswerExactMatch": 22.082810539523212}, "test": {"Bleu_1": 0.25752212389378776, "Bleu_2": 0.21637028021939791, "Bleu_3": 0.18758142414388004, "Bleu_4": 0.1629585221131486, "METEOR": 0.22814634604762346, "ROUGE_L": 0.29138070406904826, "BERTScore": 0.8895556114735538, "MoverScore": 0.7098710441016705, "AnswerF1Score": 44.903117434436304, "AnswerExactMatch": 27.352572145545796}}