add npu examples

Former-commit-id: 0f21e68e2dbd84c820d66d5c6d980004efc51d51

examples/lora_multi_npu/ds_zero0.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+NPROC_PER_NODE=4
+NNODES=1
+RANK=0
+MASTER_ADDR=127.0.0.1
+MASTER_PORT=29500
+
+ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 torchrun \
+    --nproc_per_node $NPROC_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT \
+    src/train.py examples/lora_multi_gpu/llama3_lora_sft_ds.yaml

examples/lora_multi_npu/llama3_lora_sft_ds.yaml

@@ -0,0 +1,42 @@
+# model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+# method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: q_proj,v_proj
+
+# ddp
+ddp_timeout: 180000000
+deepspeed: examples/deepspeed/ds_z0_config.json
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+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: 2
+learning_rate: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500