Update README.md

README.md

@@ -38,7 +38,7 @@ The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tence
 python3 preprocess.py --corpus_path corpora/lyric.txt \
                       --vocab_path models/google_zh_vocab.txt \
                       --dataset_path lyric_dataset.pt --processes_num 32 \
-                      --seq_length 512 --target lm
+                      --seq_length 512 --data_processor lm
 ```
 
 ```
@@ -49,10 +49,7 @@ python3 pretrain.py --dataset_path lyric_dataset.pt \
                     --output_model_path models/lyric_gpt2_model.bin \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
                     --total_steps 100000 --save_checkpoint_steps 10000 --report_steps 5000 \
-                    --learning_rate 5e-5 --batch_size 64 \
-                    --embedding word_pos --remove_embedding_layernorm \
-                    --encoder transformer --mask causal --layernorm_positioning pre \
-                    --target lm --tie_weights
+                    --learning_rate 5e-5 --batch_size 64
 ```
 
 Finally, we convert the pre-trained model into Huggingface's format: