mirror of
https://gitee.com/ascend/ModelLink.git
synced 2024-12-02 11:58:26 +08:00
95 lines
2.2 KiB
Bash
95 lines
2.2 KiB
Bash
#!/bin/bash
|
|
export CUDA_DEVICE_MAX_CONNECTIONS=1
|
|
|
|
GPUS_PER_NODE=8
|
|
MASTER_ADDR=localhost
|
|
MASTER_PORT=6000
|
|
NNODES=4
|
|
NODE_RANK=0
|
|
WORLD_SIZE=$(($GPUS_PER_NODE*$NNODES))
|
|
|
|
CKPT_SAVE_DIR="your model save ckpt path"
|
|
DATA_PATH="your data path"
|
|
TOKENIZER_MODEL="your tokenizer path"
|
|
CKPT_LOAD_DIR="your model ckpt path"
|
|
TP=8
|
|
PP=4
|
|
|
|
DISTRIBUTED_ARGS="
|
|
--nproc_per_node $GPUS_PER_NODE \
|
|
--nnodes $NNODES \
|
|
--node_rank $NODE_RANK \
|
|
--master_addr $MASTER_ADDR \
|
|
--master_port $MASTER_PORT
|
|
"
|
|
|
|
GPT_ARGS="
|
|
--tensor-model-parallel-size ${TP} \
|
|
--pipeline-model-parallel-size ${PP} \
|
|
--sequence-parallel \
|
|
--num-layers 80 \
|
|
--hidden-size 8192 \
|
|
--ffn-hidden-size 28672 \
|
|
--num-attention-heads 64 \
|
|
--tokenizer-type Llama2Tokenizer \
|
|
--tokenizer-model ${TOKENIZER_MODEL} \
|
|
--seq-length 4096 \
|
|
--max-position-embeddings 4096 \
|
|
--micro-batch-size 1 \
|
|
--global-batch-size 1024 \
|
|
--make-vocab-size-divisible-by 1 \
|
|
--lr 1.0e-6 \
|
|
--train-iters 5000 \
|
|
--lr-decay-style cosine \
|
|
--untie-embeddings-and-output-weights \
|
|
--attention-dropout 0.0 \
|
|
--init-method-std 0.01 \
|
|
--hidden-dropout 0.0 \
|
|
--position-embedding-type rope \
|
|
--normalization RMSNorm \
|
|
--use-fused-rmsnorm \
|
|
--swiglu \
|
|
--use-flash-attn \
|
|
--no-masked-softmax-fusion \
|
|
--attention-softmax-in-fp32 \
|
|
--min-lr 1.0e-7 \
|
|
--weight-decay 0.1 \
|
|
--clip-grad 1.0 \
|
|
--adam-beta1 0.9 \
|
|
--initial-loss-scale 4096.0 \
|
|
--adam-beta2 0.95 \
|
|
--adam-eps 1e-5 \
|
|
--no-gradient-accumulation-fusion \
|
|
--load ${CKPT_LOAD_DIR} \
|
|
--no-load-optim \
|
|
--no-load-rng \
|
|
--disable-bias-linear \
|
|
--group-query-attention \
|
|
--num-query-groups 8 \
|
|
--lr-warmup-fraction 0.01 \
|
|
--bf16 \
|
|
--use-fused-swiglu \
|
|
--use-fused-rotary-pos-emb \
|
|
--num-layers-per-virtual-pipeline-stage 5 \
|
|
--use-mc2 \
|
|
"
|
|
|
|
DATA_ARGS="
|
|
--data-path $DATA_PATH \
|
|
--split 949,50,1
|
|
"
|
|
|
|
OUTPUT_ARGS="
|
|
--log-interval 1 \
|
|
--save-interval 10000 \
|
|
--eval-interval 1000 \
|
|
--eval-iters 10 \
|
|
"
|
|
|
|
torchrun $DISTRIBUTED_ARGS pretrain_gpt.py \
|
|
$GPT_ARGS \
|
|
$DATA_ARGS \
|
|
$OUTPUT_ARGS \
|
|
--distributed-backend nccl \
|
|
--save $CKPT_SAVE_DIR \
|
|
| tee logs/train_llama2_70b.log |