support fsdp + qlora

Former-commit-id: b894bf8e84be689db258021f0638e9ac939abcbc

examples/accelerate/fsdp_config.yaml

@@ -0,0 +1,25 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+distributed_type: FSDP
+downcast_bf16: 'no'
+fsdp_config:
+  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  fsdp_backward_prefetch: BACKWARD_PRE
+  fsdp_cpu_ram_efficient_loading: true
+  fsdp_forward_prefetch: false
+  fsdp_offload_params: true
+  fsdp_sharding_strategy: FULL_SHARD
+  fsdp_state_dict_type: SHARDED_STATE_DICT
+  fsdp_sync_module_states: true
+  fsdp_use_orig_params: false
+machine_rank: 0
+main_training_function: main
+mixed_precision: fp16
+num_machines: 1
+num_processes: 2
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

examples/fsdp_qlora/README.md

@@ -0,0 +1,5 @@
+```bash
+pip install git+https://github.com/huggingface/transformers.git
+pip install "accelerate>=0.28.0"
+pip install "bitsandbytes>=0.43.0"
+```

examples/fsdp_qlora/fsdp.sh

@@ -0,0 +1,33 @@
+#!/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 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --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 \
+    --quantization_bit 4 \
+    --plot_loss \
+    --fp16

examples/full_multi_gpu/multi_node.sh

@@ -7,11 +7,11 @@ python -m torch.distributed.run \
     --master_addr $MASTER_ADDR \
     --master_port $MASTER_PORT \
     ../../src/train_bash.py \
-    --deepspeed ds_z3_config.json \
+    --deepspeed ../deepspeed/ds_z3_config.json \
     --stage sft \
     --do_train \
     --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en \
+    --dataset alpaca_gpt4_en,glaive_toolcall \
     --dataset_dir ../../data \
     --template default \
     --finetuning_type full \

examples/full_multi_gpu/single_node.sh

@@ -1,11 +1,11 @@
 #!/bin/bash
 
 deepspeed --num_gpus 4 ../../src/train_bash.py \
-    --deepspeed ds_z3_config.json \
+    --deepspeed ../deepspeed/ds_z3_config.json \
     --stage sft \
     --do_train \
     --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en \
+    --dataset alpaca_gpt4_en,glaive_toolcall \
     --dataset_dir ../../data \
     --template default \
     --finetuning_type full \

examples/lora_multi_gpu/multi_node.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
-    --config_file master_config.yaml \
+    --config_file ../accelerate/master_config.yaml \
     ../../src/train_bash.py \
     --stage sft \
     --do_train \

examples/lora_multi_gpu/single_node.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 accelerate launch \
-    --config_file single_config.yaml \
+    --config_file ../accelerate/single_config.yaml \
     ../../src/train_bash.py \
     --stage sft \
     --do_train \