Update README.md

README.md

@@ -138,57 +138,71 @@ Taking the case of word-based RoBERTa-Medium
 Stage1:
 
 ```
-python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
-                      --spm_model_path models/cluecorpussmall_spm.model \
-                      --dataset_path cluecorpussmall_word_seq128_dataset.pt \
-                      --processes_num 32 --seq_length 128 \
+python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \\
+                      --spm_model_path models/cluecorpussmall_spm.model \\
+                      --dataset_path cluecorpussmall_word_seq128_dataset.pt \\
+                      --processes_num 32 --seq_length 128 \\
                       --dynamic_masking --target mlm
 ```
 
 ```
-python3 pretrain.py --dataset_path cluecorpussmall_word_seq128_dataset.pt \
-                    --spm_model_path models/cluecorpussmall_spm.model \
-                    --config_path models/bert/medium_config.json \
-                    --output_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin \
-                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
-                    --total_steps 1000000 --save_checkpoint_steps 100000 --report_steps 50000 \
-                    --learning_rate 1e-4 --batch_size 64 \
+python3 pretrain.py --dataset_path cluecorpussmall_word_seq128_dataset.pt \\
+                    --spm_model_path models/cluecorpussmall_spm.model \\
+                    --config_path models/bert/medium_config.json \\
+                    --output_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin \\
+                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \\
+                    --total_steps 1000000 --save_checkpoint_steps 100000 --report_steps 50000 \\
+                    --learning_rate 1e-4 --batch_size 64 \\
                     --embedding word_pos_seg --encoder transformer --mask fully_visible --target mlm --tie_weights
 ```
 
 Stage2:
 
 ```
-python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
-                      --spm_model_path models/cluecorpussmall_spm.model \
-                      --dataset_path cluecorpussmall_word_seq512_dataset.pt \
-                      --processes_num 32 --seq_length 512 \
+python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \\
+                      --spm_model_path models/cluecorpussmall_spm.model \\
+                      --dataset_path cluecorpussmall_word_seq512_dataset.pt \\
+                      --processes_num 32 --seq_length 512 \\
                       --dynamic_masking --target mlm
 ```
 
 ```
-python3 pretrain.py --dataset_path cluecorpussmall_word_seq512_dataset.pt \
-                    --pretrained_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-1000000 \
-                    --spm_model_path models/cluecorpussmall_spm.model \
-                    --config_path models/bert/medium_config.json \
-                    --output_model_path models/cluecorpussmall_word_roberta_medium_seq512_model.bin \
-                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
-                    --total_steps 250000 --save_checkpoint_steps 50000 --report_steps 10000 \
-                    --learning_rate 5e-5 --batch_size 16 \
+python3 pretrain.py --dataset_path cluecorpussmall_word_seq512_dataset.pt \\
+                    --pretrained_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-1000000 \\
+                    --spm_model_path models/cluecorpussmall_spm.model \\
+                    --config_path models/bert/medium_config.json \\
+                    --output_model_path models/cluecorpussmall_word_roberta_medium_seq512_model.bin \\
+                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \\
+                    --total_steps 250000 --save_checkpoint_steps 50000 --report_steps 10000 \\
+                    --learning_rate 5e-5 --batch_size 16 \\
                     --embedding word_pos_seg --encoder transformer --mask fully_visible --target mlm --tie_weights
 ```
 
 Finally, we convert the pre-trained model into Huggingface's format:
 
 ```
-python3 scripts/convert_bert_from_uer_to_huggingface.py --input_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-250000 \
-                                                        --output_model_path pytorch_model.bin \
+python3 scripts/convert_bert_from_uer_to_huggingface.py --input_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-250000 \\
+                                                        --output_model_path pytorch_model.bin \\
                                                         --layers_num 8 --target mlm
 ```
 
 ### BibTeX entry and citation info
 
 ```
+@article{devlin2018bert,
+  title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
+  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
+  journal={arXiv preprint arXiv:1810.04805},
+  year={2018}
+}
+
+@article{turc2019,
+  title={Well-Read Students Learn Better: On the Importance of Pre-training Compact Models},
+  author={Turc, Iulia and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
+  journal={arXiv preprint arXiv:1908.08962v2 },
+  year={2019}
+}
+
 @article{zhao2019uer,
   title={UER: An Open-Source Toolkit for Pre-training Models},
   author={Zhao, Zhe and Chen, Hui and Zhang, Jinbin and Zhao, Xin and Liu, Tao and Lu, Wei and Chen, Xi and Deng, Haotang and Ju, Qi and Du, Xiaoyong},