model update

README.md

@@ -14,7 +14,7 @@ pipeline_tag: text2text-generation
 tags:
 - questions and answers generation
 widget:
-- text: "generate question and answer:  Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records."
+- text: "generate question and answer: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records."
   example_title: "Questions & Answers Generation Example 1" 
 model-index:
 - name: lmqg/t5-small-tweetqa-qag
@@ -29,25 +29,25 @@ model-index:
     metrics:
     - name: BLEU4
       type: bleu4
-      value: 0.10354023570113809
+      value: 0.10080358110819482
     - name: ROUGE-L
       type: rouge-l
-      value: 0.3437636056448882
+      value: 0.34193464058970124
     - name: METEOR
       type: meteor
-      value: 0.27932483854325374
+      value: 0.28019855592470416
     - name: BERTScore
       type: bertscore
-      value: 0.8970939116248954
+      value: 0.8964198049713776
     - name: MoverScore
       type: moverscore
-      value: 0.6051879460523261
+      value: 0.6047135052650878
     - name: QAAlignedF1Score (BERTScore)
       type: qa_aligned_f1_score_bertscore
-      value: 0.9158554176310986
+      value: 0.9142303181239072
     - name: QAAlignedF1Score (MoverScore)
       type: qa_aligned_f1_score_moverscore
-      value: 0.6316423785253936
+      value: 0.6307767033392071
 ---
 
 # Model Card of `lmqg/t5-small-tweetqa-qag`
@@ -89,7 +89,7 @@ from lmqg import TransformersQG
 # initialize model
 model = TransformersQG(language='en', model='lmqg/t5-small-tweetqa-qag')
 # model prediction
-question = model.generate_qa(list_context=["William Turner was an English painter who specialised in watercolour landscapes"], list_answer=["William Turner"])
+question = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")
         
 ```
 
@@ -100,7 +100,7 @@ from transformers import pipeline
 # initialize model
 pipe = pipeline("text2text-generation", 'lmqg/t5-small-tweetqa-qag')
 # question generation
-question = pipe('generate question and answer:  Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')
+question = pipe('generate question and answer: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')
 
 ```
 
@@ -111,14 +111,14 @@ question = pipe('generate question and answer:  Beyonce further expanded her act
 
 | Dataset | Type | BLEU4 | ROUGE-L | METEOR | BERTScore | MoverScore | Link |
 |:--------|:-----|------:|--------:|-------:|----------:|-----------:|-----:|
-| [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.104 | 0.344 | 0.279 | 0.897 | 0.605 | [link](https://huggingface.co/lmqg/t5-small-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
+| [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.101 | 0.342 | 0.28 | 0.896 | 0.605 | [link](https://huggingface.co/lmqg/t5-small-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
 
 
 ### Metrics (QAG)
 
 | Dataset | Type | QA Aligned F1 Score (BERTScore) | QA Aligned F1 Score (MoverScore) | Link |
 |:--------|:-----|--------------------------------:|---------------------------------:|-----:|
-| [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.916 | 0.632 | [link](https://huggingface.co/lmqg/t5-small-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
+| [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.914 | 0.631 | [link](https://huggingface.co/lmqg/t5-small-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
 
 
 
@@ -134,7 +134,7 @@ The following hyperparameters were used during fine-tuning:
  - model: t5-small
  - max_length: 256
  - max_length_output: 128
- - epoch: 13
+ - epoch: 14
  - batch: 64
  - lr: 0.0001
  - fp16: False

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lmqg_output/t5_small_tweetqa/best_model",
+  "_name_or_path": "lmqg_output/t5_small_tweetqa/model_mzgdpa/epoch_10",
   "add_prefix": true,
   "architectures": [
     "T5ForConditionalGeneration"

eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.3428267549042577, "Bleu_2": 0.22185133313585698, "Bleu_3": 0.14843052505246773, "Bleu_4": 0.10152476026985321, "METEOR": 0.3051221710703096, "ROUGE_L": 0.3536440310776982, "BERTScore": 0.8935539100836726, "MoverScore": 0.6058662091297468, "QAAlignedF1Score (BERTScore)": 0.9119527442495626, "QAAlignedF1Score (MoverScore)": 0.6353600862114615}, "test": {"Bleu_1": 0.36569579288023735, "Bleu_2": 0.2357840932558267, "Bleu_3": 0.1548401219334782, "Bleu_4": 0.10354023570113809, "METEOR": 0.27932483854325374, "ROUGE_L": 0.3437636056448882, "BERTScore": 0.8970939116248954, "MoverScore": 0.6051879460523261, "QAAlignedF1Score (BERTScore)": 0.9158554176310986, "QAAlignedF1Score (MoverScore)": 0.6316423785253936}}
+{"validation": {"Bleu_1": 0.3345070422535018, "Bleu_2": 0.21544505942559114, "Bleu_3": 0.14314309581452783, "Bleu_4": 0.09683893632934976, "METEOR": 0.30224984331474797, "ROUGE_L": 0.35365280171487196, "BERTScore": 0.8922636171556869, "MoverScore": 0.6050952366700484, "QAAlignedF1Score (BERTScore)": 0.9052095424849287, "QAAlignedF1Score (MoverScore)": 0.6315811777418272}, "test": {"Bleu_1": 0.355266164039276, "Bleu_2": 0.22935230967802653, "Bleu_3": 0.15106487659216425, "Bleu_4": 0.10080358110819482, "METEOR": 0.28019855592470416, "ROUGE_L": 0.34193464058970124, "BERTScore": 0.8964198049713776, "MoverScore": 0.6047135052650878, "QAAlignedF1Score (BERTScore)": 0.9142303181239072, "QAAlignedF1Score (MoverScore)": 0.6307767033392071}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:345379bacbe63926eeeaac53cc581822b09bd0a8577d60c4ab66308f025994af
-size 242013115
+oid sha256:2eee0fb22c65db993ca331a5cf8ba436195b9d18c6701820d8d6a347d4ef134f
+size 242014971

tokenizer_config.json

@@ -104,7 +104,7 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,
-  "name_or_path": "lmqg_output/t5_small_tweetqa/best_model",
+  "name_or_path": "lmqg_output/t5_small_tweetqa/model_mzgdpa/epoch_10",
   "pad_token": "<pad>",
   "special_tokens_map_file": null,
   "tokenizer_class": "T5Tokenizer",

trainer_config.json

@@ -1 +1 @@
-{"dataset_path": "lmqg/qag_tweetqa", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": ["qag"], "model": "t5-small", "max_length": 256, "max_length_output": 128, "epoch": 13, "batch": 64, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 1, "label_smoothing": 0.0}
+{"dataset_path": "lmqg/qag_tweetqa", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": ["qag"], "model": "t5-small", "max_length": 256, "max_length_output": 128, "epoch": 14, "batch": 64, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 1, "label_smoothing": 0.0}