From 2d5cd556e57b1632a307a53c31c11edebff8de32 Mon Sep 17 00:00:00 2001 From: Tim Date: Sat, 8 Feb 2025 18:53:16 +0800 Subject: [PATCH] chore: format check result (#565) * format check result placed next to the metric result * reformat --- rdagent/scenarios/data_science/dev/feedback.py | 1 - rdagent/scenarios/data_science/dev/prompts.yaml | 13 +++++++------ rdagent/scenarios/data_science/share.yaml | 6 +++++- 3 files changed, 12 insertions(+), 8 deletions(-) diff --git a/rdagent/scenarios/data_science/dev/feedback.py b/rdagent/scenarios/data_science/dev/feedback.py index 7141d110..7e794eb5 100644 --- a/rdagent/scenarios/data_science/dev/feedback.py +++ b/rdagent/scenarios/data_science/dev/feedback.py @@ -65,7 +65,6 @@ class DSExperiment2Feedback(Experiment2Feedback): sota_desc=sota_desc, cur_exp=exp, diff_edition=diff_edition, - format_check=exp.format_check_result, feedback_desc=feedback_desc, ) diff --git a/rdagent/scenarios/data_science/dev/prompts.yaml b/rdagent/scenarios/data_science/dev/prompts.yaml index 4fcc4da7..ff929544 100644 --- a/rdagent/scenarios/data_science/dev/prompts.yaml +++ b/rdagent/scenarios/data_science/dev/prompts.yaml @@ -8,7 +8,7 @@ exp_feedback: Your feedback should: 1. Confirm if the current result supports or refutes the hypothesis. 2. Compare with previous best results. - 3. Suggest improvements or new directions. Stay innovative and adapative. + 3. Suggest improvements or new directions. Stay innovative and adaptive. 4. SOTA results are the best outcomes we have achieved in this scenario. If we do not have complete experiment available (i.e., results that are runnable and can generate evaluation outcomes), **please replace it as the best result/SOTA**. Please provide detailed and constructive feedback. @@ -45,14 +45,15 @@ exp_feedback: Final results of the current solution: {{ cur_exp.result }} + + {% if cur_exp.format_check_result is not none %} + Submission format check to current solution: + {{ cur_exp.format_check_result }} + {% endif %} + ### Complete Code of current solution {{cur_exp.experiment_workspace.all_codes}} - {% if format_check is not none %} - Submission format check to current solution: - {{ format_check }} - {% endif %} - {{feedback_desc}} Please refer to these hypotheses and feedback to help you recommend new experiment and hypothesis diff --git a/rdagent/scenarios/data_science/share.yaml b/rdagent/scenarios/data_science/share.yaml index 773eec22..8b195db9 100644 --- a/rdagent/scenarios/data_science/share.yaml +++ b/rdagent/scenarios/data_science/share.yaml @@ -16,8 +16,12 @@ describe: # some template to describe some object {% if exp.result is none %} There are no according evaluation results {% else %} - Evaluated results on validation is: + Evaluated results on validation are: {{ exp.result }} + {% if exp.format_check_result is not none %} + Submission format check result is: + {{ exp.format_check_result }} + {% endif %} {% endif %} {% else %}