simplify readme

Former-commit-id: 0da6ec2d516326fe9c7583ba71cd1778eb838178

examples/extras/fsdp_qlora/README.md

@@ -0,0 +1,5 @@
+```bash
+pip install "transformers>=4.39.1"
+pip install "accelerate>=0.28.0"
+pip install "bitsandbytes>=0.43.0"
+```

examples/extras/fsdp_qlora/fsdp.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
+    --config_file ../accelerate/fsdp_config.yaml \
+    ../../src/train_bash.py \
+    --stage sft \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-70b-hf \
+    --dataset alpaca_gpt4_en,glaive_toolcall \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-70B/lora/sft \
+    --overwrite_cache \
+    --overwrite_output_dir \
+    --cutoff_len 1024 \
+    --preprocessing_num_workers 16 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 4 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --ddp_timeout 180000000 \
+    --quantization_bit 4 \
+    --plot_loss \
+    --fp16