diff --git a/tasks/common.py b/tasks/common.py index dcd2e91..2d6ddd8 100644 --- a/tasks/common.py +++ b/tasks/common.py @@ -53,7 +53,7 @@ class Task: class TaskMixture(Task): """ - For SFT Training it becomes useful to train on a tax mixture of datasets. + For SFT Training it becomes useful to train on a mixture of datasets. Fun trick: if you wish to oversample any task, just pass it in multiple times in the list. """ diff --git a/tasks/gsm8k.py b/tasks/gsm8k.py index c05e21c..f3539ff 100644 --- a/tasks/gsm8k.py +++ b/tasks/gsm8k.py @@ -74,7 +74,7 @@ class GSM8K(Task): else: # Regular text in between tool calls assistant_message_parts.append({"type": "text", "text": part}) - # No put it all together + # Now put it all together messages = [ {"role": "user", "content": question}, # note: simple string {"role": "assistant", "content": assistant_message_parts}, # note: list of parts (as dicts)