Update README.md

README.md

@@ -40,7 +40,7 @@ python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                       --vocab_path models/google_zh_vocab.txt \
                       --dataset_path cluecorpussmall_pegasus_seq512_dataset.pt \
                       --processes_num 32 --seq_length 512 \
-                      --target gsg --sentence_selection_strategy random
+                      --data_processor gsg --sentence_selection_strategy random
 ```
 
 ```
@@ -50,10 +50,7 @@ python3 pretrain.py --dataset_path cluecorpussmall_pegasus_seq512_dataset.pt \
                     --output_model_path models/cluecorpussmall_pegasus_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 8 \
-                    --embedding word_sinusoidalpos --remove_embedding_layernorm --tgt_embedding word_sinusoidalpos \
-                    --encoder transformer --mask fully_visible --layernorm_positioning pre --decoder transformer \
-                    --target gsg --tie_weights --has_lmtarget_bias
+                    --learning_rate 1e-4 --batch_size 8
 ```
 
 Finally, we convert the pre-trained model into Huggingface's format: