diff --git a/common/train.cpp b/common/train.cpp index dcf9614e4..e6f2f7a2f 100644 --- a/common/train.cpp +++ b/common/train.cpp @@ -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)" : "");