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: " 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-base-tweetqa-qag
@@ -29,19 +29,19 @@ model-index:
     metrics:
     - name: BLEU4
       type: bleu4
-      value: 8.760988157508385e-10
+      value: 0.13399772044578695
     - name: ROUGE-L
       type: rouge-l
-      value: 0.004925321600227637
+      value: 0.3723033124655649
     - name: METEOR
       type: meteor
-      value: 0.0028425982865562323
+      value: 0.3113835606745017
     - name: BERTScore
       type: bertscore
-      value: 0.03894749127879461
+      value: 0.9079808971076232
     - name: MoverScore
       type: moverscore
-      value: 0.45595221244168144
+      value: 0.622602267900722
 ---
 
 # Model Card of `lmqg/t5-base-tweetqa-qag`
@@ -94,7 +94,7 @@ from transformers import pipeline
 # initialize model
 pipe = pipeline("text2text-generation", 'lmqg/t5-base-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(' Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')
 
 ```
 
@@ -105,7 +105,7 @@ 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 | 0.0 | 0.005 | 0.003 | 0.039 | 0.456 | [link](https://huggingface.co/lmqg/t5-base-tweetqa-qag/raw/main/eval/metric.first.sentence.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
+| [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.134 | 0.372 | 0.311 | 0.908 | 0.623 | [link](https://huggingface.co/lmqg/t5-base-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
 
 
 
@@ -117,17 +117,17 @@ The following hyperparameters were used during fine-tuning:
  - dataset_name: default
  - input_types: ['paragraph']
  - output_types: ['questions_answers']
- - prefix_types: ['qag']
+ - prefix_types: None
  - model: t5-base
  - max_length: 256
  - max_length_output: 128
- - epoch: 12
- - batch: 64
+ - epoch: 15
+ - batch: 32
  - lr: 0.0001
  - fp16: False
  - random_seed: 1
  - gradient_accumulation_steps: 2
- - label_smoothing: 0.15
+ - label_smoothing: 0.0
 
 The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/t5-base-tweetqa-qag/raw/main/trainer_config.json).
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lmqg_output/t5_base_tweetqa_np/best_model",
+  "_name_or_path": "lmqg_output/t5_base_tweetqa_np/model_mzgdpa/epoch_10",
   "add_prefix": false,
   "architectures": [
     "T5ForConditionalGeneration"

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

@@ -1 +1 @@
-{"validation": {"Bleu_1": 0.0005127722896463237, "Bleu_2": 9.431228240232113e-05, "Bleu_3": 2.7076339389272802e-05, "Bleu_4": 1.2863502556787301e-05}, "test": {"Bleu_1": 0.00018828430858505577, "Bleu_2": 2.4223408658113176e-05, "Bleu_3": 4.712010310605882e-11, "Bleu_4": 6.621851429116013e-14}}
+{"validation": {"Bleu_1": 0.3721408966148003, "Bleu_2": 0.2509164467597846, "Bleu_3": 0.17212294958902818, "Bleu_4": 0.11952807860594504, "METEOR": 0.33234151468838274, "ROUGE_L": 0.38246324501783846, "BERTScore": 0.9013732597104067, "MoverScore": 0.6193014138823796}, "test": {"Bleu_1": 0.40492272467084117, "Bleu_2": 0.27773803210324066, "Bleu_3": 0.1918293792740954, "Bleu_4": 0.13399772044578695, "METEOR": 0.3113835606745017, "ROUGE_L": 0.3723033124655649, "BERTScore": 0.9079808971076232, "MoverScore": 0.622602267900722}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fcbe77b40a9ad94ffdcf454ae07742beba9aeab52d11f94c7fc557e0a19ab9
-size 891644351
+oid sha256:23a0fdacdc439e4c368c040b98cdfbddc1b2a8b5310d9f05a0c7a369c9a5eed4
+size 891647935

tokenizer_config.json

@@ -1 +1 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "lmqg_output/t5_base_tweetqa_np/best_model", "special_tokens_map_file": "lmqg_output/t5_base_tweetqa_np/model_mzgdpa/epoch_10/special_tokens_map.json", "tokenizer_class": "T5Tokenizer"}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "lmqg_output/t5_base_tweetqa_np/model_mzgdpa/epoch_10", "special_tokens_map_file": "lmqg_output/t5_base_tweetqa_np/model_mzgdpa/epoch_10/special_tokens_map.json", "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-base", "max_length": 256, "max_length_output": 128, "epoch": 12, "batch": 64, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 2, "label_smoothing": 0.15}
+{"dataset_path": "lmqg/qag_tweetqa", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": null, "model": "t5-base", "max_length": 256, "max_length_output": 128, "epoch": 15, "batch": 32, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 2, "label_smoothing": 0.0}