mirror of
https://gitee.com/ascend/ModelLink.git
synced 2024-12-02 03:48:24 +08:00
56 lines
1.8 KiB
Bash
56 lines
1.8 KiB
Bash
#!/bin/bash
|
|
|
|
# The number of parameters is not aligned
|
|
export LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib:/root/miniconda3/lib:$LD_LIBRARY_PATH
|
|
export HCCL_CONNECT_TIMEOUT=1200
|
|
export COMBINED_ENABLE=1
|
|
export CUDA_DEVICE_MAX_CONNECTIONS=1
|
|
|
|
# Change for multinode config
|
|
MASTER_ADDR=localhost
|
|
MASTER_PORT=6001
|
|
NNODES=1
|
|
NODE_RANK=0
|
|
NPUS_PER_NODE=8
|
|
|
|
WORLD_SIZE=$(($NPUS_PER_NODE*$NNODES))
|
|
|
|
DISTRIBUTED_ARGS="--nproc_per_node $NPUS_PER_NODE --nnodes $NNODES --node_rank $NODE_RANK --master_addr $MASTER_ADDR --master_port $MASTER_PORT"
|
|
|
|
CHECKPOINT="Your ckpt file path"
|
|
TOKENIZER_PATH="Your tokenizer path"
|
|
DATA_PATH="./boolq/data/test/"
|
|
TASK="boolq"
|
|
|
|
# Different task needs different max_new_tokens value, please follow the instruction in readme.
|
|
python -m torch.distributed.launch $DISTRIBUTED_ARGS evaluation.py \
|
|
--task-data-path $DATA_PATH \
|
|
--task $TASK \
|
|
--seq-length 4096 \
|
|
--max-new-tokens 1 \
|
|
--max-position-embeddings 4096 \
|
|
--tensor-model-parallel-size 8 \
|
|
--pipeline-model-parallel-size 1 \
|
|
--num-layers 40 \
|
|
--hidden-size 5120 \
|
|
--ffn-hidden-size 13696 \
|
|
--num-attention-heads 40 \
|
|
--disable-bias-linear \
|
|
--swiglu \
|
|
--position-embedding-type alibi \
|
|
--load $CHECKPOINT \
|
|
--normalization RMSNorm \
|
|
--tokenizer-type PretrainedFromHF \
|
|
--tokenizer-name-or-path $TOKENIZER_PATH \
|
|
--tokenizer-not-use-fast \
|
|
--fp16 \
|
|
--micro-batch-size 1 \
|
|
--use-fused-rmsnorm \
|
|
--exit-on-missing-checkpoint \
|
|
--no-load-rng \
|
|
--no-load-optim \
|
|
--untie-embeddings-and-output-weights \
|
|
--no-masked-softmax-fusion \
|
|
--make-vocab-size-divisible-by 64 \
|
|
--seed 42 | tee logs/eval_baichuan_13b_${TASK}.log
|