add examples

Former-commit-id: 8cdf64adc2c8e5f194a6df26cf749d7bc9bc039f

examples/lora_multi_gpu/config.yaml

@@ -0,0 +1,16 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+distributed_type: MULTI_GPU
+downcast_bf16: 'no'
+gpu_ids: all
+machine_rank: 0
+main_training_function: main
+mixed_precision: fp16
+num_machines: 1
+num_processes: 4
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

examples/lora_multi_gpu/sft.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch --config_file config.yaml ../../src/train_bash.py \
+    --stage sft \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --dataset alpaca_gpt4_en,glaive_toolcall \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/sft \
+    --overwrite_cache \
+    --overwrite_output_dir \
+    --cutoff_len 1024 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 2 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --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 \
+    --plot_loss \
+    --fp16