train : fix typo in overlapping-samples help msg (#4758)

This commit fixes a typo in the help message for the
--overlapping-samples option.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
This commit is contained in:
Daniel Bevenius 2024-01-03 18:53:40 +01:00 committed by GitHub
parent ece9a45e8f
commit cb1e2818e0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -1107,7 +1107,7 @@ void print_common_train_usage(int /*argc*/, char ** /*argv*/, const struct train
fprintf(stderr, " --sample-start STR Sets the starting point for samples after the specified pattern. If empty use every token position as sample start. (default '%s')\n", params->sample_start.c_str());
fprintf(stderr, " --include-sample-start Include the sample start in the samples. (default off)\n");
fprintf(stderr, " --escape process sample start escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\)\n");
fprintf(stderr, " --overlapping-samples Samples my overlap, will include sample-start of second and following samples. When off, samples will end at begin of next sample. (default off)\n");
fprintf(stderr, " --overlapping-samples Samples may overlap, will include sample-start of second and following samples. When off, samples will end at begin of next sample. (default off)\n");
fprintf(stderr, " --fill-with-next-samples Samples shorter than context length will be followed by the next (shuffled) samples. (default off)\n");
fprintf(stderr, " --separate-with-eos When fill-with-next-samples, insert end-of-sequence token between samples.%s\n", params->separate_with_eos ? " (default)" : "");
fprintf(stderr, " --separate-with-bos When fill-with-next-samples, insert begin-of-sequence token between samples.%s\n", params->separate_with_bos ? " (default)" : "");