Update README.md

README.md

@@ -5,9 +5,9 @@ widget:
 - text: "最近一趟去北京的[MASK]几点发车"
 
 
-
 ---
 
+
 # Chinese word-based RoBERTa Miniatures
 
 ## Model description
@@ -144,7 +144,7 @@ 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
+                      --dynamic_masking --data_processor mlm
 ```
 
 ```
@@ -155,7 +155,7 @@ python3 pretrain.py --dataset_path cluecorpussmall_word_seq128_dataset.pt \
                     --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
+                    --data_processor mlm --target mlm
 ```
 
 Stage2:
@@ -165,19 +165,19 @@ 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
+                      --dynamic_masking --data_processor 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 \
+                    --pretrained_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-1000000 \
                     --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
+                    --data_processor mlm --target mlm
 ```
 
 Finally, we convert the pre-trained model into Huggingface's format: