From: Daniel Bevenius <redacted>
Date: Tue, 16 Jan 2024 17:54:24 +0000 (+0100)
Subject: finetune : add training data file to log message (#4979)
X-Git-Tag: upstream/0.0.4488~2595
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=cec8a4847062fbd76253e3b085683f39d91e80d3;p=pkg%2Fggml%2Fsources%2Fllama.cpp

finetune : add training data file to log message (#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 <redacted>
---

diff --git a/examples/finetune/finetune.cpp b/examples/finetune/finetune.cpp
index a6620fd7..11fcbf44 100644
--- 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,