Update README.md

README.md

@@ -92,7 +92,7 @@ Stage1:
 python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                       --vocab_path models/google_zh_vocab.txt \
                       --dataset_path cluecorpussmall_albert_seq128_dataset.pt \
-                      --seq_length 128 --processes_num 32 --target albert 
+                      --seq_length 128 --processes_num 32 --data_processor albert 
 ```
 
 ```
@@ -102,9 +102,7 @@ python3 pretrain.py --dataset_path cluecorpussmall_albert_seq128_dataset.pt \
                     --output_model_path models/cluecorpussmall_albert_base_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 \
-                    --factorized_embedding_parameterization --parameter_sharing \
-                    --embedding word_pos_seg --encoder transformer --mask fully_visible --target albert
+                    --learning_rate 1e-4 --batch_size 64
 ```
 
 Stage2:
@@ -113,20 +111,18 @@ Stage2:
 python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                       --vocab_path models/google_zh_vocab.txt \
                       --dataset_path cluecorpussmall_albert_seq512_dataset.pt \
-                      --seq_length 512 --processes_num 32 --target albert 
+                      --seq_length 512 --processes_num 32 --data_processor albert
 ```
 
 ```
 python3 pretrain.py --dataset_path cluecorpussmall_albert_seq512_dataset.pt \
-                    --pretrained_model_path models/cluecorpussmall_albert_base_seq128_model.bin-1000000 \
                     --vocab_path models/google_zh_vocab.txt \
+                    --pretrained_model_path models/cluecorpussmall_albert_base_seq128_model.bin-1000000 \
                     --config_path models/albert/base_config.json \
                     --output_model_path models/cluecorpussmall_albert_base_seq512_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 \
-                    --factorized_embedding_parameterization --parameter_sharing \
-                    --embedding word_pos_seg --encoder transformer --mask fully_visible --target albert
+                    --learning_rate 1e-4 --batch_size 64
 ```
 
 Finally, we convert the pre-trained model into Huggingface's format:
@@ -154,5 +150,6 @@ python3 scripts/convert_albert_from_uer_to_huggingface.py --input_model_path clu
   year={2019}
 }
 ```
+
 [base]:https://huggingface.co/uer/albert-base-chinese-cluecorpussmall
 [large]:https://huggingface.co/uer/albert-large-chinese-cluecorpussmall