update examples

examples/README.md

@@ -3,7 +3,7 @@ We provide diverse examples about fine-tuning LLMs.
 ```
 examples/
 ├── lora_single_gpu/
-│   ├── pt.sh: Do pre-training
+│   ├── pretrain.sh: Do pre-training
 │   ├── sft.sh: Do supervised fine-tuning
 │   ├── reward.sh: Do reward modeling
 │   ├── ppo.sh: Do PPO training

examples/README_zh.md

@@ -3,7 +3,7 @@
 ```
 examples/
 ├── lora_single_gpu/
-│   ├── pt.sh: 进行预训练
+│   ├── pretrain.sh: 进行预训练
 │   ├── sft.sh: 进行指令监督微调
 │   ├── reward.sh: 进行奖励模型训练
 │   ├── ppo.sh: 进行 PPO 训练

examples/lora_single_gpu/dpo.sh

@@ -6,7 +6,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
     --model_name_or_path meta-llama/Llama-2-7b-hf \
     --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
     --create_new_adapter \
-    --dataset comparison_gpt4_en \
+    --dataset orca_rlhf \
     --dataset_dir ../../data \
     --template default \
     --finetuning_type lora \

examples/lora_single_gpu/reward.sh

@@ -6,7 +6,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
     --model_name_or_path meta-llama/Llama-2-7b-hf \
     --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
     --create_new_adapter \
-    --dataset comparison_gpt4_en \
+    --dataset orca_rlhf \
     --dataset_dir ../../data \
     --template default \
     --finetuning_type lora \