diff --git a/common/common.h b/common/common.h
index c0f045d50..a295e88b0 100644
--- a/common/common.h
+++ b/common/common.h
@@ -64,9 +64,9 @@ struct gpt_params {
     int32_t n_beams                         = 0;     // if non-zero then use beam search of given width.
     int32_t grp_attn_n                      = 1;     // group-attention factor
     int32_t grp_attn_w                      = 512;   // group-attention width
+    int32_t token_interval                  = 512;   // show token count every 512 tokens
     float   rope_freq_base                  = 0.0f;  // RoPE base frequency
     float   rope_freq_scale                 = 0.0f;  // RoPE frequency scaling factor
-    int32_t token_interval                  = 512;   // show token count every 512 tokens
     float   yarn_ext_factor                 = -1.0f; // YaRN extrapolation mix factor
     float   yarn_attn_factor                = 1.0f;  // YaRN magnitude scaling factor
     float   yarn_beta_fast                  = 32.0f; // YaRN low correction dim