diff --git a/training/stories_cpu_ops.h b/training/stories_cpu_ops.h
index dfe35f9..30fc94f 100644
--- a/training/stories_cpu_ops.h
+++ b/training/stories_cpu_ops.h
@@ -123,6 +123,7 @@ static void embed_lookup(float *x, const float *embed, const uint16_t *tokens, i
 static void embed_backward(float *d_embed, const float *dx, const uint16_t *tokens, int dim, int seq) {
     for (int t = 0; t < seq; t++) {
         int tok = tokens[t];
+        if (tok >= VOCAB) { tok = 0; }  // HIGH-01: clamp invalid token -> position 0
         for (int d = 0; d < dim; d++) {
             d_embed[tok*dim + d] += dx[d*seq + t];
         }
diff --git a/training/train_large.m b/training/train_large.m
index 785204d..198f57b 100644
--- a/training/train_large.m
+++ b/training/train_large.m
@@ -298,6 +298,8 @@ int main(int argc, char *argv[]) {
         size_t n_tokens = data_len / 2;
         if (n_tokens < (size_t)SEQ + 1) {
             fprintf(stderr, "Token file too small: %zu tokens, need >%d\n", n_tokens, SEQ + 1);
+            munmap(token_data, data_len);
+            close(data_fd);
             return 1;
         }
         printf("Token data: %zu tokens (%.1f MB)\n", n_tokens, data_len/1e6);