diff --git a/examples/llm-foundry/aks/helm/llm-training/templates/pytorchjob.yaml b/examples/llm-foundry/aks/helm/llm-training/templates/pytorchjob.yaml
index 2517a71..ae518b4 100644
--- a/examples/llm-foundry/aks/helm/llm-training/templates/pytorchjob.yaml
+++ b/examples/llm-foundry/aks/helm/llm-training/templates/pytorchjob.yaml
@@ -43,6 +43,7 @@ spec:
               ulimit -s unlimited && \
               ulimit -l unlimited && \
               ulimit -a && \
+              LOG_FILE="/tmp/$(hostname).out" && \
               composer \
                 --world_size {{ mul .Values.training.nodes .Values.training.gpusPerNode }} \
                 --node_rank $RANK \
@@ -55,6 +56,13 @@ spec:
                 {{- range $key, $value := .Values.yamlUpdates }}
                 {{ $key }}={{ $value }} \
                 {{- end }}
+              2>&1 | tee "$LOG_FILE"
+              EXIT_CODE=$?
+              {{- if .Values.logs.copyLogsDir }}
+              mkdir -p {{ .Values.logs.copyLogsDir }}
+              cp "$LOG_FILE" {{ .Values.logs.copyLogsDir }}/ || echo "Failed to copy logs"
+              {{- end }}
+              exit $EXIT_CODE
             env:
             {{- include "llm-training.nccl-env" . | nindent 12 }}
             {{- include "llm-training.sharp-env" . | nindent 12 }}
@@ -118,6 +126,7 @@ spec:
               ulimit -s unlimited && \
               ulimit -l unlimited && \
               ulimit -a && \
+              LOG_FILE="/tmp/$(hostname).out" && \
               composer \
                 --world_size {{ mul .Values.training.nodes .Values.training.gpusPerNode }} \
                 --node_rank $RANK \
@@ -130,6 +139,13 @@ spec:
                 {{- range $key, $value := .Values.yamlUpdates }}
                 {{ $key }}={{ $value }} \
                 {{- end }}
+              2>&1 | tee "$LOG_FILE"
+              EXIT_CODE=$?
+              {{- if .Values.logs.copyLogsDir }}
+              mkdir -p {{ .Values.logs.copyLogsDir }}
+              cp "$LOG_FILE" {{ .Values.logs.copyLogsDir }}/ || echo "Failed to copy logs"
+              {{- end }}
+              exit $EXIT_CODE
             env:
             {{- include "llm-training.nccl-env" . | nindent 12 }}
             {{- include "llm-training.sharp-env" . | nindent 12 }}
diff --git a/examples/llm-foundry/aks/helm/llm-training/values.yaml b/examples/llm-foundry/aks/helm/llm-training/values.yaml
index 6fcfa3e..e777171 100644
--- a/examples/llm-foundry/aks/helm/llm-training/values.yaml
+++ b/examples/llm-foundry/aks/helm/llm-training/values.yaml
@@ -18,6 +18,11 @@ training:
 kueue:
   queueName: "" # e.g., "gpu-local-queue" to use Kueue
 
+# Logs configuration (optional)
+# Set copyLogsDir to save stdout/stderr logs to a directory
+logs:
+  copyLogsDir: "" # e.g., "/mnt/logs" - logs saved as $(hostname).out
+
 # Additional YAML updates for the training configuration
 yamlUpdates: {}
 # Example: