Loading pretrain_pubmed_summit.lsf +1 −1 Original line number Diff line number Diff line Loading @@ -147,7 +147,7 @@ export CHECKPOINT_PATH=/gpfs/alpine/med106/world-shared/xf9/Megatron-LM/chkptt jsrun --smpiargs="-disable_gpu_hooks" -n $nnodes -r 1 -g 6 -a 6 -c 42 python pretrain_bert.py \ --tensor-model-parallel-size 2 \ --pipeline-model-parallel-size 1 \ --pipeline-model-parallel-size 2 \ --num-layers 24 \ --hidden-size 1024 \ --num-attention-heads 16 \ Loading Loading
pretrain_pubmed_summit.lsf +1 −1 Original line number Diff line number Diff line Loading @@ -147,7 +147,7 @@ export CHECKPOINT_PATH=/gpfs/alpine/med106/world-shared/xf9/Megatron-LM/chkptt jsrun --smpiargs="-disable_gpu_hooks" -n $nnodes -r 1 -g 6 -a 6 -c 42 python pretrain_bert.py \ --tensor-model-parallel-size 2 \ --pipeline-model-parallel-size 1 \ --pipeline-model-parallel-size 2 \ --num-layers 24 \ --hidden-size 1024 \ --num-attention-heads 16 \ Loading
