Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[dist benchmark]Fix llama2 benchmark #8376

Merged
merged 2 commits into from
May 8, 2024
Merged

[dist benchmark]Fix llama2 benchmark #8376

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d7daec2
fix llama2 benchmark
Liujie0926 May 7, 2024
fc80ecf
Merge branch 'PaddlePaddle:develop' into fix_llama2
Liujie0926 May 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions tests/test_tipc/dygraph/hybrid_parallelism/llama2/benchmark_common/run_benchmark.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,15 +28,15 @@ function _set_params(){
master_ip=${ip_lists[0]}
nnodes=${nnodes:-1}

is_large_model=True
base_batch_size=${global_batch_size}
profiling=${PROFILING:-"false"} # (必选) Profiling 开关，默认关闭，通过全局变量传递
model_repo="PaddleNLP" # (必选) 模型套件的名字
speed_unit="tokens/s" # (必选)速度指标单位
skip_steps=10 # (必选)解析日志，跳过模型前几个性能不稳定的step
keyword="interval_tokens_per_second_per_device:" # (必选)解析日志，筛选出性能数据所在行的关键字
convergence_key="loss:" # (可选)解析日志，筛选出收敛数据所在行的关键字 如：convergence_key="loss:"

model_mode=5 # 获取ips数据及单位，仅跳过skip_steps后计算均值，单位保持token/s不变

# 以下为通用执行命令，无特殊可不用修改
model_name=${model_item}_bs${global_batch_size}_${fp_item}_${run_mode} # (必填) 且格式不要改动,与竞品名称对齐
device=${CUDA_VISIBLE_DEVICES//,/ }
Expand Down
Loading