fix style

README.md

@@ -199,7 +199,7 @@ with distiller:
 **Examples can be found in the `examples` directory :**
 
 * [examples/random_token_example](examples/random_token_example) : a simple runable toy example which demonstrates the usage of TextBrewer. This example performs distillation on the text classification task with random tokens as inputs.
-* [examples/cmrc2018\_example](examples/cmrc2018_example) (Chinese): distillation on CMRC2018, a Chinese MRC task, using DRCD as data augmentation.
+* [examples/cmrc2018\_example](examples/cmrc2018_example) (Chinese): distillation on CMRC 2018, a Chinese MRC task, using DRCD as data augmentation.
 * [examples/mnli\_example](examples/mnli_example) (English): distillation on MNLI, an English sentence-pair classification task. This example also shows how to perform multi-teacher distillation.
 * [examples/conll2003_example](examples/conll2003_example) (English): distillation on CoNLL-2003 English NER task, which is in form of sequence labeling.
 
@@ -342,8 +342,8 @@ The results are listed below.
 
 **Note**:
 
-1. Learning rate decay is not used in distillation on CMRC2018 and DRCD.
-2. CMRC2018 and DRCD take each other as the augmentation dataset in the distillation.
+1. Learning rate decay is not used in distillation on CMRC 2018 and DRCD.
+2. CMRC 2018 and DRCD take each other as the augmentation dataset in the distillation.
 3. The settings of training Electra-base teacher model can be found at [**Chinese-ELECTRA**](https://github.com/ymcui/Chinese-ELECTRA).
 4. Electra-small student model is intialized with the [pretrained weights](https://github.com/ymcui/Chinese-ELECTRA).
 

docs/source/ExperimentResults.md

@@ -115,9 +115,9 @@
 | T3-small (student)            | 88.1        |
 | T4-tiny (student)             | 88.4        |
 
-### CMRC2018 and DRCD
+### CMRC 2018 and DRCD
 
-| Model           | CMRC2018 | DRCD |
+| Model           | CMRC 2018 | DRCD |
 | --------------- | ---------------- | ------------ |
 | **RoBERTa-wwm-ext** (teacher) | 68.8 / 86.4      | 86.5 / 92.5  |
 | T3 (student)                  | 63.4 / 82.4      | 76.7 / 85.2  |
@@ -127,7 +127,7 @@
 | T4-tiny (student)             | 54.3 / 76.8      | 75.5 / 84.9  |
 |   +  DA             | 61.8 / 81.8      | 77.3 / 86.1  |
 
-**Note**: CMRC2018 and DRCD take each other as the augmentation dataset on the experiments. 
+**Note**: CMRC 2018 and DRCD take each other as the augmentation dataset on the experiments. 
 
 ## Chinese Datasets (Electra-base as the teacher)
 

examples/cmrc2018_example/README.md

@@ -1,17 +1,17 @@
 [**中文说明**](README_ZH.md) | [**English**](README.md)
 
-This example demonstrates distilltion on CMRC2018 task, and using DRCD dataset as data augmentation.
+This example demonstrates distilltion on CMRC 2018 task, and using DRCD dataset as data augmentation.
 
 
-* run_cmrc2018_train.sh : trains a treacher model (roberta-wwm-base) on CMRC2018.
-* run_cmrc2018_distill_T3.sh : distills the teacher to T3 with CMRC2018 and DRCD datasets.
-* run_cmrc2018_distill_T4tiny.sh :  distills the teacher to T4tiny with CMRC2018 and DRCD datasets.
+* run_cmrc2018_train.sh : trains a treacher model (roberta-wwm-base) on CMRC 2018.
+* run_cmrc2018_distill_T3.sh : distills the teacher to T3 with CMRC 2018 and DRCD datasets.
+* run_cmrc2018_distill_T4tiny.sh :  distills the teacher to T4tiny with CMRC 2018 and DRCD datasets.
 
 Modify the following variables in the shell scripts before running:
 
 * BERT_DIR :  where RoBERTa-wwm-base stores，including vocab.txt, pytorch_model.bin, bert_config.json
 * OUTPUT_ROOT_DIR : this directory stores logs and trained model weights
-* DATA_ROOT_DIR : it includes CMRC2018 and DRCD datasets:
+* DATA_ROOT_DIR : it includes CMRC 2018 and DRCD datasets:
   * \$\{DATA_ROOT_DIR\}/cmrc2018/squad-style-data/cmrc2018_train.json
   * \$\{DATA_ROOT_DIR\}/cmrc2018/squad-style-data/cmrc2018_dev.json
   * \$\{DATA_ROOT_DIR\}/drcd/DRCD_training.json

examples/cmrc2018_example/README_ZH.md

@@ -1,6 +1,6 @@
 [**中文说明**](README_ZH.md) | [**English**](README.md)
 
-这个例子展示CMRC2018阅读理解任务上的蒸馏，并使用DRCD数据集作为数据增强。
+这个例子展示CMRC 2018阅读理解任务上的蒸馏，并使用DRCD数据集作为数据增强。
 
 * run_cmrc2018_train.sh : 在cmrc2018数据集上训练教师模型(roberta-wwm-base)
 * run_cmrc2018_distill_T3.sh : 在cmrc2018和drcd数据集上蒸馏教师模型到T3