commit files to HF hub

README.md

@@ -29,33 +29,33 @@ model-index:
     metrics:
     - name: BLEU4 (Question Answering)
       type: bleu4_question_answering
-      value: 0.0
+      value: 12.72
     - name: ROUGE-L (Question Answering)
       type: rouge_l_question_answering
-      value: 0.0
+      value: 35.29
     - name: METEOR (Question Answering)
       type: meteor_question_answering
-      value: 0.0
+      value: 31.94
     - name: BERTScore (Question Answering)
       type: bertscore_question_answering
-      value: 53.44
+      value: 91.81
     - name: MoverScore (Question Answering)
       type: moverscore_question_answering
-      value: 57.38
+      value: 78.23
     - name: AnswerF1Score (Question Answering)
       type: answer_f1_score__question_answering
-      value: 0.0
+      value: 61.17
     - name: AnswerExactMatch (Question Answering)
       type: answer_exact_match_question_answering
-      value: 0.01
+      value: 45.63
 ---
 
 # Model Card of `vocabtrimmer/mt5-small-trimmed-it-15000-itquad-qa`
-This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-it-15000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-it-15000) for question answering task on the [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+This model is fine-tuned version of [ckpts/mt5-small-trimmed-it-15000](https://huggingface.co/ckpts/mt5-small-trimmed-it-15000) for question answering task on the [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
 
 
 ### Overview
-- **Language model:** [vocabtrimmer/mt5-small-trimmed-it-15000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-it-15000)   
+- **Language model:** [ckpts/mt5-small-trimmed-it-15000](https://huggingface.co/ckpts/mt5-small-trimmed-it-15000)   
 - **Language:** it  
 - **Training data:** [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (default)
 - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
@@ -91,16 +91,16 @@ output = pipe("question: Quale batterio ha il nome del paese che colpisce di pi
 
 |                  |   Score | Type    | Dataset                                                          |
 |:-----------------|--------:|:--------|:-----------------------------------------------------------------|
-| AnswerExactMatch |    0.01 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| AnswerF1Score    |    0    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| BERTScore        |   53.44 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| Bleu_1           |    0    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| Bleu_2           |    0    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| Bleu_3           |    0    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| Bleu_4           |    0    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| METEOR           |    0    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| MoverScore       |   57.38 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
-| ROUGE_L          |    0    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| AnswerExactMatch |   45.63 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| AnswerF1Score    |   61.17 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| BERTScore        |   91.81 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_1           |   24.63 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_2           |   19.27 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_3           |   15.67 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_4           |   12.72 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| METEOR           |   31.94 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| MoverScore       |   78.23 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| ROUGE_L          |   35.29 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 
 
 
@@ -112,15 +112,15 @@ The following hyperparameters were used during fine-tuning:
  - input_types: ['paragraph_question']
  - output_types: ['answer']
  - prefix_types: None
- - model: vocabtrimmer/mt5-small-trimmed-it-15000
+ - model: ckpts/mt5-small-trimmed-it-15000
  - max_length: 512
  - max_length_output: 32
- - epoch: 2
+ - epoch: 14
  - batch: 32
- - lr: 0.0001
+ - 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-it-15000-itquad-qa/raw/main/trainer_config.json).

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

@@ -1 +1 @@
-{"validation": {"Bleu_1": 1.4566504428404137e-20, "Bleu_2": 6.65999673968088e-20, "Bleu_3": 1.266191296030615e-19, "Bleu_4": 2.0793211550277366e-19, "METEOR": 6.297650582729482e-05, "ROUGE_L": 0.0, "BERTScore": 0.538802718337567, "MoverScore": 0.5782300506330317, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.0}, "test": {"Bleu_1": 1.1464762199873616e-20, "Bleu_2": 6.542641457860311e-20, "Bleu_3": 1.34123408700942e-19, "Bleu_4": 2.294806670903765e-19, "METEOR": 7.575901058732173e-06, "ROUGE_L": 0.0, "BERTScore": 0.5343892611675811, "MoverScore": 0.5738221023340756, "AnswerF1Score": 0.0, "AnswerExactMatch": 0.013142331449599158}}
+{"validation": {"Bleu_1": 0.2580067857275919, "Bleu_2": 0.20108730465281174, "Bleu_3": 0.16401300224060814, "Bleu_4": 0.13360125215512206, "METEOR": 0.3419925245916212, "ROUGE_L": 0.3576084751547699, "BERTScore": 0.9314583699373272, "MoverScore": 0.8156556259999925, "AnswerF1Score": 66.06181535700281, "AnswerExactMatch": 53.52871599421737}, "test": {"Bleu_1": 0.24630429838525467, "Bleu_2": 0.19269581000798502, "Bleu_3": 0.15672132801810706, "Bleu_4": 0.12721339743498133, "METEOR": 0.3194144078191241, "ROUGE_L": 0.3529487866544257, "BERTScore": 0.9180507633121745, "MoverScore": 0.7823140510035724, "AnswerF1Score": 61.16997980920731, "AnswerExactMatch": 45.63017479300828}}