update example docs

Former-commit-id: 102cd42768d9eb2cf1219309a25b41e26149067e

examples/extras/fsdp_qlora/llama3_lora_sft.yaml

@@ -0,0 +1,39 @@
+# model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+quantization_bit: 4
+
+# method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+val_size: 0.1
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+# output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+# train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500

examples/extras/fsdp_qlora/sft.sh

@@ -1,41 +0,0 @@
-#!/bin/bash
-# DO NOT use GPTQ/AWQ model in FSDP+QLoRA
-
-pip install "transformers>=4.39.1"
-pip install "accelerate>=0.28.0"
-pip install "bitsandbytes>=0.43.0"
-
-CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
-    --config_file ../../accelerate/fsdp_config.yaml \
-    ../../../src/train.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

examples/extras/fsdp_qlora/single_node.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+# DO NOT use GPTQ/AWQ model in FSDP+QLoRA
+
+pip install "transformers>=4.39.1"
+pip install "accelerate>=0.28.0"
+pip install "bitsandbytes>=0.43.0"
+
+CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
+    --config_file examples/accelerate/fsdp_config.yaml \
+    src/train.py examples/extras/fsdp_qlora/llama3_lora_sft.yaml