gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-27 23:47:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: dump test data (#850)

Browse Source 
* debug path for model dump
* update prompt
This commit is contained in:
Tim
2025-05-07 17:24:50 +08:00
committed by GitHub
parent cda656b4ca
commit 3b7bafae12
2 changed files with 5 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/components/coder/data_science/share/eval.py
+1 -5
View File
@@ -44,11 +44,7 @@ class ModelDumpEvaluator(CoSTEEREvaluator):
final_decision=False,
)
env = get_ds_env()
env.conf.extra_volumes = {
f"{DS_RD_SETTING.local_data_path}/{'sample/' if self.data_type == 'sample' else ''}{self.scen.competition}": T(
"scenarios.data_science.share:scen.input_path"
).r()
}
env.conf.extra_volumes = {self.scen.debug_path: T("scenarios.data_science.share:scen.input_path").r()}
# 2) check the result and stdout after reruning the model.
rdagent/components/coder/data_science/share/prompts.yaml
+4 -2
View File
@@ -1,8 +1,9 @@
dump_model_coder:
guideline: |-
Please dump the model in a "models/" subfolder in the first running, and the script rerun performs inference without needing to retrain the model.
Please dump the model in a "models/" subfolder in the first running, and the script rerun performs inference without needing to retrain the model when running the code again.
If there are parameters generated from the training data that might be needed for inference on test data, please save them in the "models/" subfolder as well.
Make sure that the required files, like submission.csv and scores.csv, are created even if you bypass the model training step by loading the saved model file directly.
If no test set is provided, reserve a portion of the data as your test set and save the generated test files in the models/ subfolder for use in submission and inference.
Make sure that the required files, like submission.csv and scores.csv, are created without model training step through loading the saved model and test data file directly.
dump_model_eval:
system: |-
@@ -18,6 +19,7 @@ dump_model_eval:
Focus on these aspects:
- Check if the code saves the model in the "models/" subfolder.
- Check if the code saves the test data in the "models/" subfolder when there is no test data specified.
- Ensure that when the code is rerun, it skips the training process and loads the model from the "models/" subfolder for direct inference.
- Verify that there is no training activity in the output.
- Ensure that even if you skip the model training by loading saved models, the files like scores.csv and submission.csv are still correctly created.