Update README.md

README.md

@@ -95,14 +95,14 @@ python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
 
 ```
 deepspeed pretrain.py --deepspeed --deepspeed_config models/deepspeed_config.json --dataset_path cluecorpussmall_seq128_dataset.pt \
-                    --vocab_path models/google_zh_vocab.txt \
-                    --config_path models/bert/xlarge_config.json \
-                    --output_model_path models/cluecorpussmall_wwm_roberta_xlarge_seq128_model \
-                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
-                    --total_steps 500000 --save_checkpoint_steps 50000 --report_steps 500 \
-                    --learning_rate 2e-5 --batch_size 128 --deep_init \
-                    --whole_word_masking  --deepspeed_checkpoint_activations \
-                    --data_processor mlm --target mlm
+                      --vocab_path models/google_zh_vocab.txt \
+                      --config_path models/bert/xlarge_config.json \
+                      --output_model_path models/cluecorpussmall_wwm_roberta_xlarge_seq128_model \
+                      --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
+                      --total_steps 500000 --save_checkpoint_steps 50000 --report_steps 500 \
+                      --learning_rate 2e-5 --batch_size 128 --deep_init \
+                      --whole_word_masking  --deepspeed_checkpoint_activations \
+                      --data_processor mlm --target mlm
 ```
 
 Before stage2, we extract fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints:
@@ -124,15 +124,15 @@ python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
 
 ```
 deepspeed pretrain.py --deepspeed --deepspeed_config models/deepspeed_config.json --dataset_path cluecorpussmall_seq512_dataset.pt \
-                    --vocab_path models/google_zh_vocab.txt \
-                    --config_path models/bert/xlarge_config.json \
-                    --pretrained_model_path models/cluecorpussmall_wwm_roberta_xlarge_seq128_model.bin \
-                    --output_model_path models/cluecorpussmall_wwm_roberta_xlarge_seq512_model \
-                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
-                    --total_steps 250000 --save_checkpoint_steps 50000 --report_steps 500 \
-                    --learning_rate 5e-5 --batch_size 32 \
-                    --whole_word_masking --deepspeed_checkpoint_activations \
-                    --data_processor mlm --target mlm
+                      --vocab_path models/google_zh_vocab.txt \
+                      --config_path models/bert/xlarge_config.json \
+                      --pretrained_model_path models/cluecorpussmall_wwm_roberta_xlarge_seq128_model.bin \
+                      --output_model_path models/cluecorpussmall_wwm_roberta_xlarge_seq512_model \
+                      --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
+                      --total_steps 250000 --save_checkpoint_steps 50000 --report_steps 500 \
+                      --learning_rate 5e-5 --batch_size 32 \
+                      --whole_word_masking --deepspeed_checkpoint_activations \
+                      --data_processor mlm --target mlm
 ```
 
 Then, we extract fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints: