finetune : add training data file to log message (ggerganov#4979)

This commit adds the name of the training data file to the log message printed when the training data is tokenized. The motivation for this change is that it can be useful to show which file is being tokenized when running the finetune example. Signed-off-by: Daniel Bevenius <[email protected]>
teleprint-me · Jan 16, 2024 · cec8a48 · cec8a48
1 parent 334a835
commit cec8a48
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/examples/finetune/finetune.cpp b/examples/finetune/finetune.cpp
@@ -1799,7 +1799,7 @@ int main(int argc, char ** argv) {
     std::vector<llama_token> train_tokens;
     std::vector<size_t> train_samples_begin;
     std::vector<size_t> train_samples_size;
-    printf("%s: tokenize training data\n", __func__);
+    printf("%s: tokenize training data from %s\n", __func__, params.common.fn_train_data);
     tokenize_file(lctx,
             params.common.fn_train_data,
             params.common.sample_start,