diff --git a/R-package/R/lgb.Booster.R b/R-package/R/lgb.Booster.R
index 7ceb04dedc9c..d64e82fd894e 100644
--- a/R-package/R/lgb.Booster.R
+++ b/R-package/R/lgb.Booster.R
@@ -718,6 +718,7 @@ Booster <- R6::R6Class(
 #'         number of columns corresponding to the number of trees.
 #'
 #' @examples
+#' \dontrun{
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -735,6 +736,7 @@ Booster <- R6::R6Class(
 #'   , learning_rate = 1.0
 #' )
 #' preds <- predict(model, test$data)
+#' }
 #' @export
 predict.lgb.Booster <- function(object,
                                 data,
diff --git a/R-package/man/predict.lgb.Booster.Rd b/R-package/man/predict.lgb.Booster.Rd
index 40444cbff7be..395c2d45ea37 100644
--- a/R-package/man/predict.lgb.Booster.Rd
+++ b/R-package/man/predict.lgb.Booster.Rd
@@ -52,6 +52,7 @@ For regression or binary classification, it returns a vector of length \code{nro
 Predicted values based on class \code{lgb.Booster}
 }
 \examples{
+\dontrun{
 data(agaricus.train, package = "lightgbm")
 train <- agaricus.train
 dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -70,3 +71,4 @@ model <- lgb.train(
 )
 preds <- predict(model, test$data)
 }
+}
diff --git a/docs/conf.py b/docs/conf.py
index 731465fef76a..3dfbf1b8503f 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -247,7 +247,7 @@ def generate_r_docs(app):
             , install = FALSE \
             , devel = FALSE \
             , examples = TRUE \
-            , run_dont_run = FALSE \
+            , run_dont_run = TRUE \
             , seed = 42L \
             , preview = FALSE \
             , new_process = TRUE \