From cd4931d7893e6bf4206cd49f651863f6269a9df4 Mon Sep 17 00:00:00 2001 From: LDOUBLEV Date: Mon, 24 Jan 2022 05:49:31 +0000 Subject: [PATCH] revert > train.log --- test_tipc/test_train_inference_python.sh | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/test_tipc/test_train_inference_python.sh b/test_tipc/test_train_inference_python.sh index 47992533..050e2f9a 100644 --- a/test_tipc/test_train_inference_python.sh +++ b/test_tipc/test_train_inference_python.sh @@ -317,25 +317,25 @@ else set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}") set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${train_use_gpu}") if [ ${#ips} -le 26 ];then - save_log="${LOG_PATH}/${model_name}_gpus_${gpu}_autocast_${autocast}_bs_${train_batch_value}_sp" + save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}" nodes=1 else IFS="," ips_array=(${ips}) IFS="|" nodes=${#ips_array[@]} - save_log="${LOG_PATH}/${model_name}_gpus_${gpu}_autocast_${autocast}_bs_${train_batch_value}_mp" + save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}_nodes_${nodes}" fi btrain_log="${LOG_PATH}/benchmark_train/${model_name}_bs${train_batch_value}_${autocast}" set_save_model=$(func_set_params "${save_model_key}" "${save_log}") if [ ${#gpu} -le 2 ];then # train with cpu or single gpu - cmd="${python} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config} > ${btrain_log} 2>&1 " + cmd="${python} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config} " elif [ ${#ips} -le 26 ];then # train with multi-gpu - cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config} > ${btrain_log} 2>&1 " + cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}" else # train with multi-machine - cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config} > ${btrain_log} 2>&1 " + cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}" fi # run train eval $cmd -- GitLab