We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 01f4e50 commit 5a26243Copy full SHA for 5a26243
multinode_trainer.slurm
@@ -54,7 +54,7 @@ export NCCL_BUFFSIZE=2097152
54
#export TORCH_DIST_INIT_BARRIER=1
55
export FI_EFA_SET_CUDA_SYNC_MEMOPS=0
56
57
-CONFIG_FILE=${CONFIG_FILE:-"./torchtitan/models/llama/train_configs/llama3_8b.toml"}
+CONFIG_FILE=${CONFIG_FILE:-"./torchtitan/models/llama3/train_configs/llama3_8b.toml"}
58
59
dcgmi profile --pause
60
# adjust sbatch --ntasks and sbatch --nodes above and --nnodes below
0 commit comments