train : change default FA argument (#7528)

diff --git a/common/train.cpp b/common/train.cpp
index 2d41a1d29a83cd7ce3f6c71c5754a81a6e088a77..fef1e57c9465579cb8ad5007884adb73c197e7e4 100644 (file)
--- a/common/train.cpp
+++ b/common/train.cpp
@@ -1052,7 +1052,7 @@ struct train_params_common get_default_train_params_common() {
 
     params.custom_n_ctx = false;
 
-    params.use_flash              = true;
+    params.use_flash              = false;
     params.use_checkpointing      = true;
 
     params.sample_start           = "";

diff --git a/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp b/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
index 746c3fbef84128ab8f5e509390cfbbad8731ada2..8ca9f8915916ccd5122c92f47277f16a9a871074 100644 (file)
--- a/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
+++ b/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
@@ -774,7 +774,7 @@ static struct train_params get_default_train_params() {
 
     params.samples_start_after_nl = false;
     params.use_adam               = true;
-    params.use_flash              = true;
+    params.use_flash              = false;
     params.use_scratch            = true;
 
     // only adam