mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-08-06 11:37:44 +00:00
XianBW
e21b334741
* add not_json batcheditout * ensemble out_spec change * feature out_spec change * model out_spec change * workflow out_spec change * runner debugger out_spec change * filter_progress_bar return format fix * data_loader and spec out_spec change * show finish_reason in llm log * json_mode fix * remove hardcode * fix CI * fix grammer * complete PythonBatchEditOut logic --------- Co-authored-by: yuanteli <1957922024@qq.com>
18 lines
1.2 KiB
YAML
18 lines
1.2 KiB
YAML
filter_progress_bar:
|
|
system: |
|
|
You are an assistant helping to analyze and filter training log messages and a progress bar output from a given text. Evaluate the text to determine if training log messages and a progress bar output patterns are present and, if so, generate a list of regex patterns to remove them.
|
|
Additionally, indicate whether substitution is needed. If the input exceeds a token limit, the system will provide only a shortened portion of the text.
|
|
Note: About the training log message, if the log message contains useful information like loss or accuracy and it is reported in each epoch, it should not be removed. If the log message is not useful, for example, reporting nan in each iteration or just reporting the iteration number, please remove them.
|
|
|
|
Respond in the following JSON format and order:
|
|
{
|
|
"needs_sub": <true/false>,
|
|
"regex_patterns": ["regex pattern 1", "regex pattern 2", ...]
|
|
}
|
|
user: |
|
|
The following text contains stdout:
|
|
|
|
{{ stdout }}
|
|
|
|
Check if the text contains training log messages and progress bar patterns. If patterns are found, provide a list of regex patterns to filter them. Otherwise, indicate that substitution is not needed.
|