Upload final adaptive repair report artifacts
Browse files- .gitattributes +4 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/debug_completion_summary.json +2162 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_code_health.png +3 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_error_breakdown.png +0 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_reward_curve.png +3 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/metrics.json +1134 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/optimizer_health.png +3 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/sft_loss_curve.png +3 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/tensorboard_scalars.json +0 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/training_curve_report.md +74 -0
- training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/training_timeline.png +0 -0
.gitattributes
CHANGED
|
@@ -133,3 +133,7 @@ docs/detailed-blog/rendered-assets/hugging-face-space-repair-loop-ui.png filter=
|
|
| 133 |
docs/detailed-blog/rendered-assets/strict-grpo-caster-render.png filter=lfs diff=lfs merge=lfs -text
|
| 134 |
docs/detailed-blog/rendered-assets/strict-grpo-stator-render.png filter=lfs diff=lfs merge=lfs -text
|
| 135 |
docs/detailed-blog/rendered-assets/training-evidence-build-rate-summary.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
docs/detailed-blog/rendered-assets/strict-grpo-caster-render.png filter=lfs diff=lfs merge=lfs -text
|
| 134 |
docs/detailed-blog/rendered-assets/strict-grpo-stator-render.png filter=lfs diff=lfs merge=lfs -text
|
| 135 |
docs/detailed-blog/rendered-assets/training-evidence-build-rate-summary.png filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_code_health.png filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_reward_curve.png filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/optimizer_health.png filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/sft_loss_curve.png filter=lfs diff=lfs merge=lfs -text
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/debug_completion_summary.json
ADDED
|
@@ -0,0 +1,2162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"reward_call": 1,
|
| 4 |
+
"index": 0,
|
| 5 |
+
"score": -0.595,
|
| 6 |
+
"task_id": "hinge_leaf_barrel",
|
| 7 |
+
"code_chars": 5052,
|
| 8 |
+
"cadforge_build": 0.0,
|
| 9 |
+
"cadforge_total": -1.0,
|
| 10 |
+
"has_fixture": true,
|
| 11 |
+
"has_cadquery_import": true,
|
| 12 |
+
"error_kind": "BRep_API"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"reward_call": 1,
|
| 16 |
+
"index": 1,
|
| 17 |
+
"score": -0.645,
|
| 18 |
+
"task_id": "hinge_leaf_barrel",
|
| 19 |
+
"code_chars": 6589,
|
| 20 |
+
"cadforge_build": 0.0,
|
| 21 |
+
"cadforge_total": -1.0,
|
| 22 |
+
"has_fixture": true,
|
| 23 |
+
"has_cadquery_import": true,
|
| 24 |
+
"error_kind": "AttributeError"
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"reward_call": 1,
|
| 28 |
+
"index": 2,
|
| 29 |
+
"score": -0.645,
|
| 30 |
+
"task_id": "hinge_leaf_barrel",
|
| 31 |
+
"code_chars": 4782,
|
| 32 |
+
"cadforge_build": 0.0,
|
| 33 |
+
"cadforge_total": -1.0,
|
| 34 |
+
"has_fixture": true,
|
| 35 |
+
"has_cadquery_import": true,
|
| 36 |
+
"error_kind": "NameError"
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"reward_call": 1,
|
| 40 |
+
"index": 3,
|
| 41 |
+
"score": -0.565,
|
| 42 |
+
"task_id": "hinge_leaf_barrel",
|
| 43 |
+
"code_chars": 6146,
|
| 44 |
+
"cadforge_build": 0.0,
|
| 45 |
+
"cadforge_total": -1.0,
|
| 46 |
+
"has_fixture": true,
|
| 47 |
+
"has_cadquery_import": true,
|
| 48 |
+
"error_kind": "BRep_API"
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"reward_call": 2,
|
| 52 |
+
"index": 0,
|
| 53 |
+
"score": 0.7490079407071689,
|
| 54 |
+
"task_id": "wall_j_hook_120n",
|
| 55 |
+
"code_chars": 3217,
|
| 56 |
+
"cadforge_build": 1.0,
|
| 57 |
+
"cadforge_total": 0.7047152243613751,
|
| 58 |
+
"has_fixture": true,
|
| 59 |
+
"has_cadquery_import": true,
|
| 60 |
+
"error_kind": "build_ok"
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"reward_call": 2,
|
| 64 |
+
"index": 1,
|
| 65 |
+
"score": -0.6649999999999999,
|
| 66 |
+
"task_id": "wall_j_hook_120n",
|
| 67 |
+
"code_chars": 3294,
|
| 68 |
+
"cadforge_build": 0.0,
|
| 69 |
+
"cadforge_total": -1.0,
|
| 70 |
+
"has_fixture": true,
|
| 71 |
+
"has_cadquery_import": true,
|
| 72 |
+
"error_kind": "SyntaxError"
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"reward_call": 2,
|
| 76 |
+
"index": 2,
|
| 77 |
+
"score": -0.615,
|
| 78 |
+
"task_id": "cable_clip_snap",
|
| 79 |
+
"code_chars": 4058,
|
| 80 |
+
"cadforge_build": 0.0,
|
| 81 |
+
"cadforge_total": -1.0,
|
| 82 |
+
"has_fixture": true,
|
| 83 |
+
"has_cadquery_import": true,
|
| 84 |
+
"error_kind": "NameError"
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"reward_call": 2,
|
| 88 |
+
"index": 3,
|
| 89 |
+
"score": -0.615,
|
| 90 |
+
"task_id": "cable_clip_snap",
|
| 91 |
+
"code_chars": 3537,
|
| 92 |
+
"cadforge_build": 0.0,
|
| 93 |
+
"cadforge_total": -1.0,
|
| 94 |
+
"has_fixture": true,
|
| 95 |
+
"has_cadquery_import": true,
|
| 96 |
+
"error_kind": "NameError"
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"reward_call": 3,
|
| 100 |
+
"index": 0,
|
| 101 |
+
"score": -0.79,
|
| 102 |
+
"task_id": "cable_clip_snap",
|
| 103 |
+
"code_chars": 3827,
|
| 104 |
+
"cadforge_build": 0.0,
|
| 105 |
+
"cadforge_total": -1.0,
|
| 106 |
+
"has_fixture": false,
|
| 107 |
+
"has_cadquery_import": true,
|
| 108 |
+
"error_kind": "NameError"
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"reward_call": 3,
|
| 112 |
+
"index": 1,
|
| 113 |
+
"score": -0.615,
|
| 114 |
+
"task_id": "cable_clip_snap",
|
| 115 |
+
"code_chars": 4879,
|
| 116 |
+
"cadforge_build": 0.0,
|
| 117 |
+
"cadforge_total": -1.0,
|
| 118 |
+
"has_fixture": true,
|
| 119 |
+
"has_cadquery_import": true,
|
| 120 |
+
"error_kind": "NameError"
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"reward_call": 3,
|
| 124 |
+
"index": 2,
|
| 125 |
+
"score": -0.565,
|
| 126 |
+
"task_id": "table_six_leg_500n",
|
| 127 |
+
"code_chars": 2690,
|
| 128 |
+
"cadforge_build": 0.0,
|
| 129 |
+
"cadforge_total": -1.0,
|
| 130 |
+
"has_fixture": true,
|
| 131 |
+
"has_cadquery_import": true,
|
| 132 |
+
"error_kind": "TypeError"
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"reward_call": 3,
|
| 136 |
+
"index": 3,
|
| 137 |
+
"score": 0.6851730769230769,
|
| 138 |
+
"task_id": "table_six_leg_500n",
|
| 139 |
+
"code_chars": 3066,
|
| 140 |
+
"cadforge_build": 1.0,
|
| 141 |
+
"cadforge_total": 0.6296153846153847,
|
| 142 |
+
"has_fixture": true,
|
| 143 |
+
"has_cadquery_import": true,
|
| 144 |
+
"error_kind": "build_ok"
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"reward_call": 4,
|
| 148 |
+
"index": 0,
|
| 149 |
+
"score": -0.565,
|
| 150 |
+
"task_id": "pipe_clamp_saddle",
|
| 151 |
+
"code_chars": 4375,
|
| 152 |
+
"cadforge_build": 0.0,
|
| 153 |
+
"cadforge_total": -1.0,
|
| 154 |
+
"has_fixture": true,
|
| 155 |
+
"has_cadquery_import": true,
|
| 156 |
+
"error_kind": "ValueError"
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"reward_call": 4,
|
| 160 |
+
"index": 1,
|
| 161 |
+
"score": -0.615,
|
| 162 |
+
"task_id": "pipe_clamp_saddle",
|
| 163 |
+
"code_chars": 3993,
|
| 164 |
+
"cadforge_build": 0.0,
|
| 165 |
+
"cadforge_total": -1.0,
|
| 166 |
+
"has_fixture": true,
|
| 167 |
+
"has_cadquery_import": true,
|
| 168 |
+
"error_kind": "NameError"
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"reward_call": 4,
|
| 172 |
+
"index": 2,
|
| 173 |
+
"score": -0.565,
|
| 174 |
+
"task_id": "bottle_cage_bike",
|
| 175 |
+
"code_chars": 3393,
|
| 176 |
+
"cadforge_build": 0.0,
|
| 177 |
+
"cadforge_total": -1.0,
|
| 178 |
+
"has_fixture": true,
|
| 179 |
+
"has_cadquery_import": true,
|
| 180 |
+
"error_kind": "unknown"
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"reward_call": 4,
|
| 184 |
+
"index": 3,
|
| 185 |
+
"score": -0.565,
|
| 186 |
+
"task_id": "bottle_cage_bike",
|
| 187 |
+
"code_chars": 3976,
|
| 188 |
+
"cadforge_build": 0.0,
|
| 189 |
+
"cadforge_total": -1.0,
|
| 190 |
+
"has_fixture": true,
|
| 191 |
+
"has_cadquery_import": true,
|
| 192 |
+
"error_kind": "ValueError"
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"reward_call": 5,
|
| 196 |
+
"index": 0,
|
| 197 |
+
"score": -0.565,
|
| 198 |
+
"task_id": "shaft_torque_clamp_120nm",
|
| 199 |
+
"code_chars": 3267,
|
| 200 |
+
"cadforge_build": 0.0,
|
| 201 |
+
"cadforge_total": -1.0,
|
| 202 |
+
"has_fixture": true,
|
| 203 |
+
"has_cadquery_import": true,
|
| 204 |
+
"error_kind": "TypeError"
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"reward_call": 5,
|
| 208 |
+
"index": 1,
|
| 209 |
+
"score": -0.615,
|
| 210 |
+
"task_id": "shaft_torque_clamp_120nm",
|
| 211 |
+
"code_chars": 3660,
|
| 212 |
+
"cadforge_build": 0.0,
|
| 213 |
+
"cadforge_total": -1.0,
|
| 214 |
+
"has_fixture": true,
|
| 215 |
+
"has_cadquery_import": true,
|
| 216 |
+
"error_kind": "NameError"
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"reward_call": 5,
|
| 220 |
+
"index": 2,
|
| 221 |
+
"score": -0.565,
|
| 222 |
+
"task_id": "cable_clip_snap",
|
| 223 |
+
"code_chars": 3168,
|
| 224 |
+
"cadforge_build": 0.0,
|
| 225 |
+
"cadforge_total": -1.0,
|
| 226 |
+
"has_fixture": true,
|
| 227 |
+
"has_cadquery_import": true,
|
| 228 |
+
"error_kind": "ValueError"
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"reward_call": 5,
|
| 232 |
+
"index": 3,
|
| 233 |
+
"score": -0.615,
|
| 234 |
+
"task_id": "cable_clip_snap",
|
| 235 |
+
"code_chars": 3595,
|
| 236 |
+
"cadforge_build": 0.0,
|
| 237 |
+
"cadforge_total": -1.0,
|
| 238 |
+
"has_fixture": true,
|
| 239 |
+
"has_cadquery_import": true,
|
| 240 |
+
"error_kind": "NameError"
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"reward_call": 6,
|
| 244 |
+
"index": 0,
|
| 245 |
+
"score": -0.565,
|
| 246 |
+
"task_id": "cable_clip_snap",
|
| 247 |
+
"code_chars": 4237,
|
| 248 |
+
"cadforge_build": 0.0,
|
| 249 |
+
"cadforge_total": -1.0,
|
| 250 |
+
"has_fixture": true,
|
| 251 |
+
"has_cadquery_import": true,
|
| 252 |
+
"error_kind": "BRep_API"
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"reward_call": 6,
|
| 256 |
+
"index": 1,
|
| 257 |
+
"score": 0.7091909398437352,
|
| 258 |
+
"task_id": "cable_clip_snap",
|
| 259 |
+
"code_chars": 2724,
|
| 260 |
+
"cadforge_build": 1.0,
|
| 261 |
+
"cadforge_total": 0.6578716939338061,
|
| 262 |
+
"has_fixture": true,
|
| 263 |
+
"has_cadquery_import": true,
|
| 264 |
+
"error_kind": "build_ok"
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"reward_call": 6,
|
| 268 |
+
"index": 2,
|
| 269 |
+
"score": -0.565,
|
| 270 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 271 |
+
"code_chars": 2087,
|
| 272 |
+
"cadforge_build": 0.0,
|
| 273 |
+
"cadforge_total": -1.0,
|
| 274 |
+
"has_fixture": true,
|
| 275 |
+
"has_cadquery_import": true,
|
| 276 |
+
"error_kind": "ValueError"
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"reward_call": 6,
|
| 280 |
+
"index": 3,
|
| 281 |
+
"score": -0.615,
|
| 282 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 283 |
+
"code_chars": 3575,
|
| 284 |
+
"cadforge_build": 0.0,
|
| 285 |
+
"cadforge_total": -1.0,
|
| 286 |
+
"has_fixture": true,
|
| 287 |
+
"has_cadquery_import": true,
|
| 288 |
+
"error_kind": "NameError"
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"reward_call": 7,
|
| 292 |
+
"index": 0,
|
| 293 |
+
"score": 0.7715157542670249,
|
| 294 |
+
"task_id": "wall_j_hook_120n",
|
| 295 |
+
"code_chars": 3617,
|
| 296 |
+
"cadforge_build": 1.0,
|
| 297 |
+
"cadforge_total": 0.7311950050200293,
|
| 298 |
+
"has_fixture": true,
|
| 299 |
+
"has_cadquery_import": true,
|
| 300 |
+
"error_kind": "build_ok"
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"reward_call": 7,
|
| 304 |
+
"index": 1,
|
| 305 |
+
"score": -0.615,
|
| 306 |
+
"task_id": "wall_j_hook_120n",
|
| 307 |
+
"code_chars": 3784,
|
| 308 |
+
"cadforge_build": 0.0,
|
| 309 |
+
"cadforge_total": -1.0,
|
| 310 |
+
"has_fixture": true,
|
| 311 |
+
"has_cadquery_import": true,
|
| 312 |
+
"error_kind": "AttributeError"
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"reward_call": 7,
|
| 316 |
+
"index": 2,
|
| 317 |
+
"score": -0.615,
|
| 318 |
+
"task_id": "cable_clip_snap",
|
| 319 |
+
"code_chars": 2959,
|
| 320 |
+
"cadforge_build": 0.0,
|
| 321 |
+
"cadforge_total": -1.0,
|
| 322 |
+
"has_fixture": true,
|
| 323 |
+
"has_cadquery_import": true,
|
| 324 |
+
"error_kind": "NameError"
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"reward_call": 7,
|
| 328 |
+
"index": 3,
|
| 329 |
+
"score": 0.8816729482901091,
|
| 330 |
+
"task_id": "cable_clip_snap",
|
| 331 |
+
"code_chars": 3441,
|
| 332 |
+
"cadforge_build": 1.0,
|
| 333 |
+
"cadforge_total": 0.8607917038707166,
|
| 334 |
+
"has_fixture": true,
|
| 335 |
+
"has_cadquery_import": true,
|
| 336 |
+
"error_kind": "build_ok"
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"reward_call": 8,
|
| 340 |
+
"index": 0,
|
| 341 |
+
"score": -0.565,
|
| 342 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 343 |
+
"code_chars": 3525,
|
| 344 |
+
"cadforge_build": 0.0,
|
| 345 |
+
"cadforge_total": -1.0,
|
| 346 |
+
"has_fixture": true,
|
| 347 |
+
"has_cadquery_import": true,
|
| 348 |
+
"error_kind": "TypeError"
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"reward_call": 8,
|
| 352 |
+
"index": 1,
|
| 353 |
+
"score": -0.6649999999999999,
|
| 354 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 355 |
+
"code_chars": 4191,
|
| 356 |
+
"cadforge_build": 0.0,
|
| 357 |
+
"cadforge_total": -1.0,
|
| 358 |
+
"has_fixture": true,
|
| 359 |
+
"has_cadquery_import": true,
|
| 360 |
+
"error_kind": "SyntaxError"
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"reward_call": 8,
|
| 364 |
+
"index": 2,
|
| 365 |
+
"score": -0.6649999999999999,
|
| 366 |
+
"task_id": "laptop_riser_vented",
|
| 367 |
+
"code_chars": 4741,
|
| 368 |
+
"cadforge_build": 0.0,
|
| 369 |
+
"cadforge_total": -1.0,
|
| 370 |
+
"has_fixture": true,
|
| 371 |
+
"has_cadquery_import": true,
|
| 372 |
+
"error_kind": "SyntaxError"
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"reward_call": 8,
|
| 376 |
+
"index": 3,
|
| 377 |
+
"score": 0.8364002976190477,
|
| 378 |
+
"task_id": "laptop_riser_vented",
|
| 379 |
+
"code_chars": 4342,
|
| 380 |
+
"cadforge_build": 1.0,
|
| 381 |
+
"cadforge_total": 0.807529761904762,
|
| 382 |
+
"has_fixture": true,
|
| 383 |
+
"has_cadquery_import": true,
|
| 384 |
+
"error_kind": "build_ok"
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"reward_call": 9,
|
| 388 |
+
"index": 0,
|
| 389 |
+
"score": 0.7244236577789979,
|
| 390 |
+
"task_id": "drawer_handle_two_bolt",
|
| 391 |
+
"code_chars": 2305,
|
| 392 |
+
"cadforge_build": 1.0,
|
| 393 |
+
"cadforge_total": 0.6757925385635268,
|
| 394 |
+
"has_fixture": true,
|
| 395 |
+
"has_cadquery_import": true,
|
| 396 |
+
"error_kind": "build_ok"
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"reward_call": 9,
|
| 400 |
+
"index": 1,
|
| 401 |
+
"score": 0.748847226464243,
|
| 402 |
+
"task_id": "drawer_handle_two_bolt",
|
| 403 |
+
"code_chars": 1991,
|
| 404 |
+
"cadforge_build": 1.0,
|
| 405 |
+
"cadforge_total": 0.7045261487814622,
|
| 406 |
+
"has_fixture": true,
|
| 407 |
+
"has_cadquery_import": true,
|
| 408 |
+
"error_kind": "build_ok"
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"reward_call": 9,
|
| 412 |
+
"index": 2,
|
| 413 |
+
"score": 0.8580815818296893,
|
| 414 |
+
"task_id": "bike_accessory_mount_120n",
|
| 415 |
+
"code_chars": 3424,
|
| 416 |
+
"cadforge_build": 1.0,
|
| 417 |
+
"cadforge_total": 0.8330371550937521,
|
| 418 |
+
"has_fixture": true,
|
| 419 |
+
"has_cadquery_import": true,
|
| 420 |
+
"error_kind": "build_ok"
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"reward_call": 9,
|
| 424 |
+
"index": 3,
|
| 425 |
+
"score": -0.615,
|
| 426 |
+
"task_id": "bike_accessory_mount_120n",
|
| 427 |
+
"code_chars": 3534,
|
| 428 |
+
"cadforge_build": 0.0,
|
| 429 |
+
"cadforge_total": -1.0,
|
| 430 |
+
"has_fixture": true,
|
| 431 |
+
"has_cadquery_import": true,
|
| 432 |
+
"error_kind": "AttributeError"
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"reward_call": 10,
|
| 436 |
+
"index": 0,
|
| 437 |
+
"score": -0.615,
|
| 438 |
+
"task_id": "bottle_cage_bike",
|
| 439 |
+
"code_chars": 3611,
|
| 440 |
+
"cadforge_build": 0.0,
|
| 441 |
+
"cadforge_total": -1.0,
|
| 442 |
+
"has_fixture": true,
|
| 443 |
+
"has_cadquery_import": true,
|
| 444 |
+
"error_kind": "NameError"
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"reward_call": 10,
|
| 448 |
+
"index": 1,
|
| 449 |
+
"score": 0.8372542665530903,
|
| 450 |
+
"task_id": "bottle_cage_bike",
|
| 451 |
+
"code_chars": 2706,
|
| 452 |
+
"cadforge_build": 1.0,
|
| 453 |
+
"cadforge_total": 0.8085344312389298,
|
| 454 |
+
"has_fixture": true,
|
| 455 |
+
"has_cadquery_import": true,
|
| 456 |
+
"error_kind": "build_ok"
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"reward_call": 10,
|
| 460 |
+
"index": 2,
|
| 461 |
+
"score": -0.565,
|
| 462 |
+
"task_id": "hinge_leaf_barrel",
|
| 463 |
+
"code_chars": 3346,
|
| 464 |
+
"cadforge_build": 0.0,
|
| 465 |
+
"cadforge_total": -1.0,
|
| 466 |
+
"has_fixture": true,
|
| 467 |
+
"has_cadquery_import": true,
|
| 468 |
+
"error_kind": "BRep_API"
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"reward_call": 10,
|
| 472 |
+
"index": 3,
|
| 473 |
+
"score": -0.595,
|
| 474 |
+
"task_id": "hinge_leaf_barrel",
|
| 475 |
+
"code_chars": 4467,
|
| 476 |
+
"cadforge_build": 0.0,
|
| 477 |
+
"cadforge_total": -1.0,
|
| 478 |
+
"has_fixture": true,
|
| 479 |
+
"has_cadquery_import": true,
|
| 480 |
+
"error_kind": "unknown"
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"reward_call": 11,
|
| 484 |
+
"index": 0,
|
| 485 |
+
"score": 0.7826016650268196,
|
| 486 |
+
"task_id": "table_six_leg_500n",
|
| 487 |
+
"code_chars": 2902,
|
| 488 |
+
"cadforge_build": 1.0,
|
| 489 |
+
"cadforge_total": 0.7442372529727289,
|
| 490 |
+
"has_fixture": true,
|
| 491 |
+
"has_cadquery_import": true,
|
| 492 |
+
"error_kind": "build_ok"
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"reward_call": 11,
|
| 496 |
+
"index": 1,
|
| 497 |
+
"score": -0.565,
|
| 498 |
+
"task_id": "table_six_leg_500n",
|
| 499 |
+
"code_chars": 4024,
|
| 500 |
+
"cadforge_build": 0.0,
|
| 501 |
+
"cadforge_total": -1.0,
|
| 502 |
+
"has_fixture": true,
|
| 503 |
+
"has_cadquery_import": true,
|
| 504 |
+
"error_kind": "TypeError"
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"reward_call": 11,
|
| 508 |
+
"index": 2,
|
| 509 |
+
"score": -0.74,
|
| 510 |
+
"task_id": "wall_j_hook_120n",
|
| 511 |
+
"code_chars": 4076,
|
| 512 |
+
"cadforge_build": 0.0,
|
| 513 |
+
"cadforge_total": -1.0,
|
| 514 |
+
"has_fixture": false,
|
| 515 |
+
"has_cadquery_import": true,
|
| 516 |
+
"error_kind": "TypeError"
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"reward_call": 11,
|
| 520 |
+
"index": 3,
|
| 521 |
+
"score": -0.615,
|
| 522 |
+
"task_id": "wall_j_hook_120n",
|
| 523 |
+
"code_chars": 3579,
|
| 524 |
+
"cadforge_build": 0.0,
|
| 525 |
+
"cadforge_total": -1.0,
|
| 526 |
+
"has_fixture": true,
|
| 527 |
+
"has_cadquery_import": true,
|
| 528 |
+
"error_kind": "NameError"
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"reward_call": 12,
|
| 532 |
+
"index": 0,
|
| 533 |
+
"score": 0.6707717531885394,
|
| 534 |
+
"task_id": "wall_j_hook_120n",
|
| 535 |
+
"code_chars": 3138,
|
| 536 |
+
"cadforge_build": 1.0,
|
| 537 |
+
"cadforge_total": 0.6126726508100464,
|
| 538 |
+
"has_fixture": true,
|
| 539 |
+
"has_cadquery_import": true,
|
| 540 |
+
"error_kind": "build_ok"
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"reward_call": 12,
|
| 544 |
+
"index": 1,
|
| 545 |
+
"score": -0.565,
|
| 546 |
+
"task_id": "wall_j_hook_120n",
|
| 547 |
+
"code_chars": 3664,
|
| 548 |
+
"cadforge_build": 0.0,
|
| 549 |
+
"cadforge_total": -1.0,
|
| 550 |
+
"has_fixture": true,
|
| 551 |
+
"has_cadquery_import": true,
|
| 552 |
+
"error_kind": "ValueError"
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"reward_call": 12,
|
| 556 |
+
"index": 2,
|
| 557 |
+
"score": 0.7118085252192984,
|
| 558 |
+
"task_id": "drawer_handle_two_bolt",
|
| 559 |
+
"code_chars": 3133,
|
| 560 |
+
"cadforge_build": 1.0,
|
| 561 |
+
"cadforge_total": 0.660951206140351,
|
| 562 |
+
"has_fixture": true,
|
| 563 |
+
"has_cadquery_import": true,
|
| 564 |
+
"error_kind": "build_ok"
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"reward_call": 12,
|
| 568 |
+
"index": 3,
|
| 569 |
+
"score": 0.6970108599980507,
|
| 570 |
+
"task_id": "drawer_handle_two_bolt",
|
| 571 |
+
"code_chars": 2749,
|
| 572 |
+
"cadforge_build": 1.0,
|
| 573 |
+
"cadforge_total": 0.6435421882330008,
|
| 574 |
+
"has_fixture": true,
|
| 575 |
+
"has_cadquery_import": true,
|
| 576 |
+
"error_kind": "build_ok"
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"reward_call": 13,
|
| 580 |
+
"index": 0,
|
| 581 |
+
"score": -0.9149999999999999,
|
| 582 |
+
"task_id": "pipe_clamp_saddle",
|
| 583 |
+
"code_chars": 1286,
|
| 584 |
+
"cadforge_build": 0.0,
|
| 585 |
+
"cadforge_total": -1.0,
|
| 586 |
+
"has_fixture": false,
|
| 587 |
+
"has_cadquery_import": true,
|
| 588 |
+
"error_kind": "SyntaxError"
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"reward_call": 13,
|
| 592 |
+
"index": 1,
|
| 593 |
+
"score": -0.645,
|
| 594 |
+
"task_id": "pipe_clamp_saddle",
|
| 595 |
+
"code_chars": 4711,
|
| 596 |
+
"cadforge_build": 0.0,
|
| 597 |
+
"cadforge_total": -1.0,
|
| 598 |
+
"has_fixture": true,
|
| 599 |
+
"has_cadquery_import": true,
|
| 600 |
+
"error_kind": "AttributeError"
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"reward_call": 13,
|
| 604 |
+
"index": 2,
|
| 605 |
+
"score": -0.595,
|
| 606 |
+
"task_id": "hinge_leaf_barrel",
|
| 607 |
+
"code_chars": 3329,
|
| 608 |
+
"cadforge_build": 0.0,
|
| 609 |
+
"cadforge_total": -1.0,
|
| 610 |
+
"has_fixture": true,
|
| 611 |
+
"has_cadquery_import": true,
|
| 612 |
+
"error_kind": "BRep_API"
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"reward_call": 13,
|
| 616 |
+
"index": 3,
|
| 617 |
+
"score": -0.695,
|
| 618 |
+
"task_id": "hinge_leaf_barrel",
|
| 619 |
+
"code_chars": 4118,
|
| 620 |
+
"cadforge_build": 0.0,
|
| 621 |
+
"cadforge_total": -1.0,
|
| 622 |
+
"has_fixture": true,
|
| 623 |
+
"has_cadquery_import": true,
|
| 624 |
+
"error_kind": "SyntaxError"
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"reward_call": 14,
|
| 628 |
+
"index": 0,
|
| 629 |
+
"score": 0.7967225694256853,
|
| 630 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 631 |
+
"code_chars": 2258,
|
| 632 |
+
"cadforge_build": 1.0,
|
| 633 |
+
"cadforge_total": 0.7608500816772769,
|
| 634 |
+
"has_fixture": true,
|
| 635 |
+
"has_cadquery_import": true,
|
| 636 |
+
"error_kind": "build_ok"
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"reward_call": 14,
|
| 640 |
+
"index": 1,
|
| 641 |
+
"score": 0.6603144760942325,
|
| 642 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 643 |
+
"code_chars": 2611,
|
| 644 |
+
"cadforge_build": 1.0,
|
| 645 |
+
"cadforge_total": 0.6003699718755677,
|
| 646 |
+
"has_fixture": true,
|
| 647 |
+
"has_cadquery_import": true,
|
| 648 |
+
"error_kind": "build_ok"
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"reward_call": 14,
|
| 652 |
+
"index": 2,
|
| 653 |
+
"score": -0.615,
|
| 654 |
+
"task_id": "bike_accessory_mount_120n",
|
| 655 |
+
"code_chars": 3410,
|
| 656 |
+
"cadforge_build": 0.0,
|
| 657 |
+
"cadforge_total": -1.0,
|
| 658 |
+
"has_fixture": true,
|
| 659 |
+
"has_cadquery_import": true,
|
| 660 |
+
"error_kind": "NameError"
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"reward_call": 14,
|
| 664 |
+
"index": 3,
|
| 665 |
+
"score": -0.615,
|
| 666 |
+
"task_id": "bike_accessory_mount_120n",
|
| 667 |
+
"code_chars": 2848,
|
| 668 |
+
"cadforge_build": 0.0,
|
| 669 |
+
"cadforge_total": -1.0,
|
| 670 |
+
"has_fixture": true,
|
| 671 |
+
"has_cadquery_import": true,
|
| 672 |
+
"error_kind": "AttributeError"
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"reward_call": 15,
|
| 676 |
+
"index": 0,
|
| 677 |
+
"score": -0.595,
|
| 678 |
+
"task_id": "hinge_leaf_barrel",
|
| 679 |
+
"code_chars": 3298,
|
| 680 |
+
"cadforge_build": 0.0,
|
| 681 |
+
"cadforge_total": -1.0,
|
| 682 |
+
"has_fixture": true,
|
| 683 |
+
"has_cadquery_import": true,
|
| 684 |
+
"error_kind": "ValueError"
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"reward_call": 15,
|
| 688 |
+
"index": 1,
|
| 689 |
+
"score": -0.615,
|
| 690 |
+
"task_id": "hinge_leaf_barrel",
|
| 691 |
+
"code_chars": 3457,
|
| 692 |
+
"cadforge_build": 0.0,
|
| 693 |
+
"cadforge_total": -1.0,
|
| 694 |
+
"has_fixture": true,
|
| 695 |
+
"has_cadquery_import": true,
|
| 696 |
+
"error_kind": "AttributeError"
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"reward_call": 15,
|
| 700 |
+
"index": 2,
|
| 701 |
+
"score": -0.565,
|
| 702 |
+
"task_id": "cable_clip_snap",
|
| 703 |
+
"code_chars": 3120,
|
| 704 |
+
"cadforge_build": 0.0,
|
| 705 |
+
"cadforge_total": -1.0,
|
| 706 |
+
"has_fixture": true,
|
| 707 |
+
"has_cadquery_import": true,
|
| 708 |
+
"error_kind": "ValueError"
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"reward_call": 15,
|
| 712 |
+
"index": 3,
|
| 713 |
+
"score": -0.565,
|
| 714 |
+
"task_id": "cable_clip_snap",
|
| 715 |
+
"code_chars": 3588,
|
| 716 |
+
"cadforge_build": 0.0,
|
| 717 |
+
"cadforge_total": -1.0,
|
| 718 |
+
"has_fixture": true,
|
| 719 |
+
"has_cadquery_import": true,
|
| 720 |
+
"error_kind": "TypeError"
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"reward_call": 16,
|
| 724 |
+
"index": 0,
|
| 725 |
+
"score": 0.7342720279794779,
|
| 726 |
+
"task_id": "drawer_handle_two_bolt",
|
| 727 |
+
"code_chars": 2791,
|
| 728 |
+
"cadforge_build": 1.0,
|
| 729 |
+
"cadforge_total": 0.6873788564464446,
|
| 730 |
+
"has_fixture": true,
|
| 731 |
+
"has_cadquery_import": true,
|
| 732 |
+
"error_kind": "build_ok"
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"reward_call": 16,
|
| 736 |
+
"index": 1,
|
| 737 |
+
"score": 0.7450899122807018,
|
| 738 |
+
"task_id": "drawer_handle_two_bolt",
|
| 739 |
+
"code_chars": 2014,
|
| 740 |
+
"cadforge_build": 1.0,
|
| 741 |
+
"cadforge_total": 0.7001057791537668,
|
| 742 |
+
"has_fixture": true,
|
| 743 |
+
"has_cadquery_import": true,
|
| 744 |
+
"error_kind": "build_ok"
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"reward_call": 16,
|
| 748 |
+
"index": 2,
|
| 749 |
+
"score": 0.6949933797275542,
|
| 750 |
+
"task_id": "wall_j_hook_120n",
|
| 751 |
+
"code_chars": 3748,
|
| 752 |
+
"cadforge_build": 1.0,
|
| 753 |
+
"cadforge_total": 0.6411686820324166,
|
| 754 |
+
"has_fixture": true,
|
| 755 |
+
"has_cadquery_import": true,
|
| 756 |
+
"error_kind": "build_ok"
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"reward_call": 16,
|
| 760 |
+
"index": 3,
|
| 761 |
+
"score": 0.7720317000561905,
|
| 762 |
+
"task_id": "wall_j_hook_120n",
|
| 763 |
+
"code_chars": 3920,
|
| 764 |
+
"cadforge_build": 1.0,
|
| 765 |
+
"cadforge_total": 0.7318020000661064,
|
| 766 |
+
"has_fixture": true,
|
| 767 |
+
"has_cadquery_import": true,
|
| 768 |
+
"error_kind": "build_ok"
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"reward_call": 17,
|
| 772 |
+
"index": 0,
|
| 773 |
+
"score": 0.7057673182935696,
|
| 774 |
+
"task_id": "laptop_riser_vented",
|
| 775 |
+
"code_chars": 2934,
|
| 776 |
+
"cadforge_build": 1.0,
|
| 777 |
+
"cadforge_total": 0.6538439038747879,
|
| 778 |
+
"has_fixture": true,
|
| 779 |
+
"has_cadquery_import": true,
|
| 780 |
+
"error_kind": "build_ok"
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"reward_call": 17,
|
| 784 |
+
"index": 1,
|
| 785 |
+
"score": -0.615,
|
| 786 |
+
"task_id": "laptop_riser_vented",
|
| 787 |
+
"code_chars": 3750,
|
| 788 |
+
"cadforge_build": 0.0,
|
| 789 |
+
"cadforge_total": -1.0,
|
| 790 |
+
"has_fixture": true,
|
| 791 |
+
"has_cadquery_import": true,
|
| 792 |
+
"error_kind": "AttributeError"
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"reward_call": 17,
|
| 796 |
+
"index": 2,
|
| 797 |
+
"score": 0.7092033044027771,
|
| 798 |
+
"task_id": "drawer_handle_two_bolt",
|
| 799 |
+
"code_chars": 3787,
|
| 800 |
+
"cadforge_build": 1.0,
|
| 801 |
+
"cadforge_total": 0.6578862404738555,
|
| 802 |
+
"has_fixture": true,
|
| 803 |
+
"has_cadquery_import": true,
|
| 804 |
+
"error_kind": "build_ok"
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"reward_call": 17,
|
| 808 |
+
"index": 3,
|
| 809 |
+
"score": -0.615,
|
| 810 |
+
"task_id": "drawer_handle_two_bolt",
|
| 811 |
+
"code_chars": 3170,
|
| 812 |
+
"cadforge_build": 0.0,
|
| 813 |
+
"cadforge_total": -1.0,
|
| 814 |
+
"has_fixture": true,
|
| 815 |
+
"has_cadquery_import": true,
|
| 816 |
+
"error_kind": "NameError"
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"reward_call": 18,
|
| 820 |
+
"index": 0,
|
| 821 |
+
"score": 0.7094622120703361,
|
| 822 |
+
"task_id": "lightweight_truss_support_250n",
|
| 823 |
+
"code_chars": 3876,
|
| 824 |
+
"cadforge_build": 1.0,
|
| 825 |
+
"cadforge_total": 0.6581908377298071,
|
| 826 |
+
"has_fixture": true,
|
| 827 |
+
"has_cadquery_import": true,
|
| 828 |
+
"error_kind": "build_ok"
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"reward_call": 18,
|
| 832 |
+
"index": 1,
|
| 833 |
+
"score": -0.64,
|
| 834 |
+
"task_id": "lightweight_truss_support_250n",
|
| 835 |
+
"code_chars": 3902,
|
| 836 |
+
"cadforge_build": 0.0,
|
| 837 |
+
"cadforge_total": -1.0,
|
| 838 |
+
"has_fixture": true,
|
| 839 |
+
"has_cadquery_import": true,
|
| 840 |
+
"error_kind": "ValueError"
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"reward_call": 18,
|
| 844 |
+
"index": 2,
|
| 845 |
+
"score": -0.615,
|
| 846 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 847 |
+
"code_chars": 2794,
|
| 848 |
+
"cadforge_build": 0.0,
|
| 849 |
+
"cadforge_total": -1.0,
|
| 850 |
+
"has_fixture": true,
|
| 851 |
+
"has_cadquery_import": true,
|
| 852 |
+
"error_kind": "NameError"
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"reward_call": 18,
|
| 856 |
+
"index": 3,
|
| 857 |
+
"score": 0.6933542290656993,
|
| 858 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 859 |
+
"code_chars": 2601,
|
| 860 |
+
"cadforge_build": 1.0,
|
| 861 |
+
"cadforge_total": 0.639240269489058,
|
| 862 |
+
"has_fixture": true,
|
| 863 |
+
"has_cadquery_import": true,
|
| 864 |
+
"error_kind": "build_ok"
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"reward_call": 19,
|
| 868 |
+
"index": 0,
|
| 869 |
+
"score": -0.565,
|
| 870 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 871 |
+
"code_chars": 2992,
|
| 872 |
+
"cadforge_build": 0.0,
|
| 873 |
+
"cadforge_total": -1.0,
|
| 874 |
+
"has_fixture": true,
|
| 875 |
+
"has_cadquery_import": true,
|
| 876 |
+
"error_kind": "BRep_API"
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"reward_call": 19,
|
| 880 |
+
"index": 1,
|
| 881 |
+
"score": 0.7852695584220875,
|
| 882 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 883 |
+
"code_chars": 3012,
|
| 884 |
+
"cadforge_build": 1.0,
|
| 885 |
+
"cadforge_total": 0.7473759510848088,
|
| 886 |
+
"has_fixture": true,
|
| 887 |
+
"has_cadquery_import": true,
|
| 888 |
+
"error_kind": "build_ok"
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"reward_call": 19,
|
| 892 |
+
"index": 2,
|
| 893 |
+
"score": 0.6607968750000001,
|
| 894 |
+
"task_id": "wall_j_hook_120n",
|
| 895 |
+
"code_chars": 2146,
|
| 896 |
+
"cadforge_build": 1.0,
|
| 897 |
+
"cadforge_total": 0.6009375000000001,
|
| 898 |
+
"has_fixture": true,
|
| 899 |
+
"has_cadquery_import": true,
|
| 900 |
+
"error_kind": "build_ok"
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"reward_call": 19,
|
| 904 |
+
"index": 3,
|
| 905 |
+
"score": 0.740404208388055,
|
| 906 |
+
"task_id": "wall_j_hook_120n",
|
| 907 |
+
"code_chars": 4263,
|
| 908 |
+
"cadforge_build": 1.0,
|
| 909 |
+
"cadforge_total": 0.6945931863388882,
|
| 910 |
+
"has_fixture": true,
|
| 911 |
+
"has_cadquery_import": true,
|
| 912 |
+
"error_kind": "build_ok"
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"reward_call": 20,
|
| 916 |
+
"index": 0,
|
| 917 |
+
"score": -0.615,
|
| 918 |
+
"task_id": "bottle_cage_bike",
|
| 919 |
+
"code_chars": 4094,
|
| 920 |
+
"cadforge_build": 0.0,
|
| 921 |
+
"cadforge_total": -1.0,
|
| 922 |
+
"has_fixture": true,
|
| 923 |
+
"has_cadquery_import": true,
|
| 924 |
+
"error_kind": "AttributeError"
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"reward_call": 20,
|
| 928 |
+
"index": 1,
|
| 929 |
+
"score": -0.6649999999999999,
|
| 930 |
+
"task_id": "bottle_cage_bike",
|
| 931 |
+
"code_chars": 3477,
|
| 932 |
+
"cadforge_build": 0.0,
|
| 933 |
+
"cadforge_total": -1.0,
|
| 934 |
+
"has_fixture": true,
|
| 935 |
+
"has_cadquery_import": true,
|
| 936 |
+
"error_kind": "SyntaxError"
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"reward_call": 20,
|
| 940 |
+
"index": 2,
|
| 941 |
+
"score": 0.8269593966053125,
|
| 942 |
+
"task_id": "phone_stand_adjustable_hinge",
|
| 943 |
+
"code_chars": 3538,
|
| 944 |
+
"cadforge_build": 1.0,
|
| 945 |
+
"cadforge_total": 0.7964228195356617,
|
| 946 |
+
"has_fixture": true,
|
| 947 |
+
"has_cadquery_import": true,
|
| 948 |
+
"error_kind": "build_ok"
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"reward_call": 20,
|
| 952 |
+
"index": 3,
|
| 953 |
+
"score": -0.615,
|
| 954 |
+
"task_id": "phone_stand_adjustable_hinge",
|
| 955 |
+
"code_chars": 3613,
|
| 956 |
+
"cadforge_build": 0.0,
|
| 957 |
+
"cadforge_total": -1.0,
|
| 958 |
+
"has_fixture": true,
|
| 959 |
+
"has_cadquery_import": true,
|
| 960 |
+
"error_kind": "AttributeError"
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"reward_call": 21,
|
| 964 |
+
"index": 0,
|
| 965 |
+
"score": 0.7335439025092554,
|
| 966 |
+
"task_id": "drawer_handle_two_bolt",
|
| 967 |
+
"code_chars": 3002,
|
| 968 |
+
"cadforge_build": 1.0,
|
| 969 |
+
"cadforge_total": 0.6865222382461827,
|
| 970 |
+
"has_fixture": true,
|
| 971 |
+
"has_cadquery_import": true,
|
| 972 |
+
"error_kind": "build_ok"
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"reward_call": 21,
|
| 976 |
+
"index": 1,
|
| 977 |
+
"score": -0.595,
|
| 978 |
+
"task_id": "drawer_handle_two_bolt",
|
| 979 |
+
"code_chars": 2946,
|
| 980 |
+
"cadforge_build": 0.0,
|
| 981 |
+
"cadforge_total": -1.0,
|
| 982 |
+
"has_fixture": true,
|
| 983 |
+
"has_cadquery_import": true,
|
| 984 |
+
"error_kind": "ValueError"
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"reward_call": 21,
|
| 988 |
+
"index": 2,
|
| 989 |
+
"score": -0.71,
|
| 990 |
+
"task_id": "table_six_leg_500n",
|
| 991 |
+
"code_chars": 2207,
|
| 992 |
+
"cadforge_build": 0.0,
|
| 993 |
+
"cadforge_total": -1.0,
|
| 994 |
+
"has_fixture": true,
|
| 995 |
+
"has_cadquery_import": true,
|
| 996 |
+
"error_kind": "SyntaxError"
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"reward_call": 21,
|
| 1000 |
+
"index": 3,
|
| 1001 |
+
"score": -0.565,
|
| 1002 |
+
"task_id": "table_six_leg_500n",
|
| 1003 |
+
"code_chars": 3794,
|
| 1004 |
+
"cadforge_build": 0.0,
|
| 1005 |
+
"cadforge_total": -1.0,
|
| 1006 |
+
"has_fixture": true,
|
| 1007 |
+
"has_cadquery_import": true,
|
| 1008 |
+
"error_kind": "TypeError"
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"reward_call": 22,
|
| 1012 |
+
"index": 0,
|
| 1013 |
+
"score": -0.565,
|
| 1014 |
+
"task_id": "table_six_leg_500n",
|
| 1015 |
+
"code_chars": 4077,
|
| 1016 |
+
"cadforge_build": 0.0,
|
| 1017 |
+
"cadforge_total": -1.0,
|
| 1018 |
+
"has_fixture": true,
|
| 1019 |
+
"has_cadquery_import": true,
|
| 1020 |
+
"error_kind": "unknown"
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"reward_call": 22,
|
| 1024 |
+
"index": 1,
|
| 1025 |
+
"score": -0.66,
|
| 1026 |
+
"task_id": "table_six_leg_500n",
|
| 1027 |
+
"code_chars": 3439,
|
| 1028 |
+
"cadforge_build": 0.0,
|
| 1029 |
+
"cadforge_total": -1.0,
|
| 1030 |
+
"has_fixture": true,
|
| 1031 |
+
"has_cadquery_import": true,
|
| 1032 |
+
"error_kind": "NameError"
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"reward_call": 22,
|
| 1036 |
+
"index": 2,
|
| 1037 |
+
"score": 0.7659628513428299,
|
| 1038 |
+
"task_id": "bike_accessory_mount_120n",
|
| 1039 |
+
"code_chars": 3737,
|
| 1040 |
+
"cadforge_build": 1.0,
|
| 1041 |
+
"cadforge_total": 0.7246621780503881,
|
| 1042 |
+
"has_fixture": true,
|
| 1043 |
+
"has_cadquery_import": true,
|
| 1044 |
+
"error_kind": "build_ok"
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"reward_call": 22,
|
| 1048 |
+
"index": 3,
|
| 1049 |
+
"score": 0.8345820695446419,
|
| 1050 |
+
"task_id": "bike_accessory_mount_120n",
|
| 1051 |
+
"code_chars": 3425,
|
| 1052 |
+
"cadforge_build": 1.0,
|
| 1053 |
+
"cadforge_total": 0.8053906700525199,
|
| 1054 |
+
"has_fixture": true,
|
| 1055 |
+
"has_cadquery_import": true,
|
| 1056 |
+
"error_kind": "build_ok"
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"reward_call": 23,
|
| 1060 |
+
"index": 0,
|
| 1061 |
+
"score": -0.61,
|
| 1062 |
+
"task_id": "pipe_clamp_saddle",
|
| 1063 |
+
"code_chars": 2839,
|
| 1064 |
+
"cadforge_build": 0.0,
|
| 1065 |
+
"cadforge_total": -1.0,
|
| 1066 |
+
"has_fixture": true,
|
| 1067 |
+
"has_cadquery_import": true,
|
| 1068 |
+
"error_kind": "TypeError"
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"reward_call": 23,
|
| 1072 |
+
"index": 1,
|
| 1073 |
+
"score": -0.865,
|
| 1074 |
+
"task_id": "pipe_clamp_saddle",
|
| 1075 |
+
"code_chars": 901,
|
| 1076 |
+
"cadforge_build": 0.0,
|
| 1077 |
+
"cadforge_total": -1.0,
|
| 1078 |
+
"has_fixture": false,
|
| 1079 |
+
"has_cadquery_import": true,
|
| 1080 |
+
"error_kind": "NameError"
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"reward_call": 23,
|
| 1084 |
+
"index": 2,
|
| 1085 |
+
"score": -0.6649999999999999,
|
| 1086 |
+
"task_id": "lightweight_truss_support_250n",
|
| 1087 |
+
"code_chars": 3920,
|
| 1088 |
+
"cadforge_build": 0.0,
|
| 1089 |
+
"cadforge_total": -1.0,
|
| 1090 |
+
"has_fixture": true,
|
| 1091 |
+
"has_cadquery_import": true,
|
| 1092 |
+
"error_kind": "SyntaxError"
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"reward_call": 23,
|
| 1096 |
+
"index": 3,
|
| 1097 |
+
"score": 0.6106822916666667,
|
| 1098 |
+
"task_id": "lightweight_truss_support_250n",
|
| 1099 |
+
"code_chars": 2480,
|
| 1100 |
+
"cadforge_build": 1.0,
|
| 1101 |
+
"cadforge_total": 0.5419791666666667,
|
| 1102 |
+
"has_fixture": true,
|
| 1103 |
+
"has_cadquery_import": true,
|
| 1104 |
+
"error_kind": "build_ok"
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"reward_call": 24,
|
| 1108 |
+
"index": 0,
|
| 1109 |
+
"score": -0.595,
|
| 1110 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1111 |
+
"code_chars": 2907,
|
| 1112 |
+
"cadforge_build": 0.0,
|
| 1113 |
+
"cadforge_total": -1.0,
|
| 1114 |
+
"has_fixture": true,
|
| 1115 |
+
"has_cadquery_import": true,
|
| 1116 |
+
"error_kind": "ValueError"
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"reward_call": 24,
|
| 1120 |
+
"index": 1,
|
| 1121 |
+
"score": -0.565,
|
| 1122 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1123 |
+
"code_chars": 3422,
|
| 1124 |
+
"cadforge_build": 0.0,
|
| 1125 |
+
"cadforge_total": -1.0,
|
| 1126 |
+
"has_fixture": true,
|
| 1127 |
+
"has_cadquery_import": true,
|
| 1128 |
+
"error_kind": "unknown"
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"reward_call": 24,
|
| 1132 |
+
"index": 2,
|
| 1133 |
+
"score": -0.61,
|
| 1134 |
+
"task_id": "wall_j_hook_120n",
|
| 1135 |
+
"code_chars": 2496,
|
| 1136 |
+
"cadforge_build": 0.0,
|
| 1137 |
+
"cadforge_total": -1.0,
|
| 1138 |
+
"has_fixture": true,
|
| 1139 |
+
"has_cadquery_import": true,
|
| 1140 |
+
"error_kind": "ValueError"
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"reward_call": 24,
|
| 1144 |
+
"index": 3,
|
| 1145 |
+
"score": -0.565,
|
| 1146 |
+
"task_id": "wall_j_hook_120n",
|
| 1147 |
+
"code_chars": 2859,
|
| 1148 |
+
"cadforge_build": 0.0,
|
| 1149 |
+
"cadforge_total": -1.0,
|
| 1150 |
+
"has_fixture": true,
|
| 1151 |
+
"has_cadquery_import": true,
|
| 1152 |
+
"error_kind": "ValueError"
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"reward_call": 25,
|
| 1156 |
+
"index": 0,
|
| 1157 |
+
"score": -0.615,
|
| 1158 |
+
"task_id": "pipe_clamp_saddle",
|
| 1159 |
+
"code_chars": 4349,
|
| 1160 |
+
"cadforge_build": 0.0,
|
| 1161 |
+
"cadforge_total": -1.0,
|
| 1162 |
+
"has_fixture": true,
|
| 1163 |
+
"has_cadquery_import": true,
|
| 1164 |
+
"error_kind": "NameError"
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"reward_call": 25,
|
| 1168 |
+
"index": 1,
|
| 1169 |
+
"score": -0.565,
|
| 1170 |
+
"task_id": "pipe_clamp_saddle",
|
| 1171 |
+
"code_chars": 3629,
|
| 1172 |
+
"cadforge_build": 0.0,
|
| 1173 |
+
"cadforge_total": -1.0,
|
| 1174 |
+
"has_fixture": true,
|
| 1175 |
+
"has_cadquery_import": true,
|
| 1176 |
+
"error_kind": "TypeError"
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"reward_call": 25,
|
| 1180 |
+
"index": 2,
|
| 1181 |
+
"score": 0.7626955025233192,
|
| 1182 |
+
"task_id": "bike_accessory_mount_120n",
|
| 1183 |
+
"code_chars": 3134,
|
| 1184 |
+
"cadforge_build": 1.0,
|
| 1185 |
+
"cadforge_total": 0.7208182382627284,
|
| 1186 |
+
"has_fixture": true,
|
| 1187 |
+
"has_cadquery_import": true,
|
| 1188 |
+
"error_kind": "build_ok"
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"reward_call": 25,
|
| 1192 |
+
"index": 3,
|
| 1193 |
+
"score": -0.565,
|
| 1194 |
+
"task_id": "bike_accessory_mount_120n",
|
| 1195 |
+
"code_chars": 2191,
|
| 1196 |
+
"cadforge_build": 0.0,
|
| 1197 |
+
"cadforge_total": -1.0,
|
| 1198 |
+
"has_fixture": true,
|
| 1199 |
+
"has_cadquery_import": true,
|
| 1200 |
+
"error_kind": "unknown"
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"reward_call": 26,
|
| 1204 |
+
"index": 0,
|
| 1205 |
+
"score": -0.615,
|
| 1206 |
+
"task_id": "table_six_leg_500n",
|
| 1207 |
+
"code_chars": 2663,
|
| 1208 |
+
"cadforge_build": 0.0,
|
| 1209 |
+
"cadforge_total": -1.0,
|
| 1210 |
+
"has_fixture": true,
|
| 1211 |
+
"has_cadquery_import": true,
|
| 1212 |
+
"error_kind": "NameError"
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"reward_call": 26,
|
| 1216 |
+
"index": 1,
|
| 1217 |
+
"score": -0.565,
|
| 1218 |
+
"task_id": "table_six_leg_500n",
|
| 1219 |
+
"code_chars": 3477,
|
| 1220 |
+
"cadforge_build": 0.0,
|
| 1221 |
+
"cadforge_total": -1.0,
|
| 1222 |
+
"has_fixture": true,
|
| 1223 |
+
"has_cadquery_import": true,
|
| 1224 |
+
"error_kind": "unknown"
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"reward_call": 26,
|
| 1228 |
+
"index": 2,
|
| 1229 |
+
"score": -0.615,
|
| 1230 |
+
"task_id": "phone_stand_adjustable_hinge",
|
| 1231 |
+
"code_chars": 5521,
|
| 1232 |
+
"cadforge_build": 0.0,
|
| 1233 |
+
"cadforge_total": -1.0,
|
| 1234 |
+
"has_fixture": true,
|
| 1235 |
+
"has_cadquery_import": true,
|
| 1236 |
+
"error_kind": "NameError"
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"reward_call": 26,
|
| 1240 |
+
"index": 3,
|
| 1241 |
+
"score": -0.565,
|
| 1242 |
+
"task_id": "phone_stand_adjustable_hinge",
|
| 1243 |
+
"code_chars": 3939,
|
| 1244 |
+
"cadforge_build": 0.0,
|
| 1245 |
+
"cadforge_total": -1.0,
|
| 1246 |
+
"has_fixture": true,
|
| 1247 |
+
"has_cadquery_import": true,
|
| 1248 |
+
"error_kind": "ValueError"
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"reward_call": 27,
|
| 1252 |
+
"index": 0,
|
| 1253 |
+
"score": -0.565,
|
| 1254 |
+
"task_id": "bottle_cage_bike",
|
| 1255 |
+
"code_chars": 3328,
|
| 1256 |
+
"cadforge_build": 0.0,
|
| 1257 |
+
"cadforge_total": -1.0,
|
| 1258 |
+
"has_fixture": true,
|
| 1259 |
+
"has_cadquery_import": true,
|
| 1260 |
+
"error_kind": "TypeError"
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"reward_call": 27,
|
| 1264 |
+
"index": 1,
|
| 1265 |
+
"score": -0.565,
|
| 1266 |
+
"task_id": "bottle_cage_bike",
|
| 1267 |
+
"code_chars": 4637,
|
| 1268 |
+
"cadforge_build": 0.0,
|
| 1269 |
+
"cadforge_total": -1.0,
|
| 1270 |
+
"has_fixture": true,
|
| 1271 |
+
"has_cadquery_import": true,
|
| 1272 |
+
"error_kind": "TypeError"
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"reward_call": 27,
|
| 1276 |
+
"index": 2,
|
| 1277 |
+
"score": -0.615,
|
| 1278 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1279 |
+
"code_chars": 3341,
|
| 1280 |
+
"cadforge_build": 0.0,
|
| 1281 |
+
"cadforge_total": -1.0,
|
| 1282 |
+
"has_fixture": true,
|
| 1283 |
+
"has_cadquery_import": true,
|
| 1284 |
+
"error_kind": "NameError"
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"reward_call": 27,
|
| 1288 |
+
"index": 3,
|
| 1289 |
+
"score": -0.565,
|
| 1290 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1291 |
+
"code_chars": 3041,
|
| 1292 |
+
"cadforge_build": 0.0,
|
| 1293 |
+
"cadforge_total": -1.0,
|
| 1294 |
+
"has_fixture": true,
|
| 1295 |
+
"has_cadquery_import": true,
|
| 1296 |
+
"error_kind": "ValueError"
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"reward_call": 28,
|
| 1300 |
+
"index": 0,
|
| 1301 |
+
"score": -0.565,
|
| 1302 |
+
"task_id": "lightweight_truss_support_250n",
|
| 1303 |
+
"code_chars": 2981,
|
| 1304 |
+
"cadforge_build": 0.0,
|
| 1305 |
+
"cadforge_total": -1.0,
|
| 1306 |
+
"has_fixture": true,
|
| 1307 |
+
"has_cadquery_import": true,
|
| 1308 |
+
"error_kind": "ValueError"
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"reward_call": 28,
|
| 1312 |
+
"index": 1,
|
| 1313 |
+
"score": -0.565,
|
| 1314 |
+
"task_id": "lightweight_truss_support_250n",
|
| 1315 |
+
"code_chars": 3215,
|
| 1316 |
+
"cadforge_build": 0.0,
|
| 1317 |
+
"cadforge_total": -1.0,
|
| 1318 |
+
"has_fixture": true,
|
| 1319 |
+
"has_cadquery_import": true,
|
| 1320 |
+
"error_kind": "TypeError"
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"reward_call": 28,
|
| 1324 |
+
"index": 2,
|
| 1325 |
+
"score": -0.615,
|
| 1326 |
+
"task_id": "wall_j_hook_120n",
|
| 1327 |
+
"code_chars": 2779,
|
| 1328 |
+
"cadforge_build": 0.0,
|
| 1329 |
+
"cadforge_total": -1.0,
|
| 1330 |
+
"has_fixture": true,
|
| 1331 |
+
"has_cadquery_import": true,
|
| 1332 |
+
"error_kind": "NameError"
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"reward_call": 28,
|
| 1336 |
+
"index": 3,
|
| 1337 |
+
"score": -0.615,
|
| 1338 |
+
"task_id": "wall_j_hook_120n",
|
| 1339 |
+
"code_chars": 3198,
|
| 1340 |
+
"cadforge_build": 0.0,
|
| 1341 |
+
"cadforge_total": -1.0,
|
| 1342 |
+
"has_fixture": true,
|
| 1343 |
+
"has_cadquery_import": true,
|
| 1344 |
+
"error_kind": "NameError"
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"reward_call": 29,
|
| 1348 |
+
"index": 0,
|
| 1349 |
+
"score": -0.615,
|
| 1350 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 1351 |
+
"code_chars": 2719,
|
| 1352 |
+
"cadforge_build": 0.0,
|
| 1353 |
+
"cadforge_total": -1.0,
|
| 1354 |
+
"has_fixture": true,
|
| 1355 |
+
"has_cadquery_import": true,
|
| 1356 |
+
"error_kind": "AttributeError"
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"reward_call": 29,
|
| 1360 |
+
"index": 1,
|
| 1361 |
+
"score": 0.6785469637821462,
|
| 1362 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 1363 |
+
"code_chars": 2890,
|
| 1364 |
+
"cadforge_build": 1.0,
|
| 1365 |
+
"cadforge_total": 0.6218199573907602,
|
| 1366 |
+
"has_fixture": true,
|
| 1367 |
+
"has_cadquery_import": true,
|
| 1368 |
+
"error_kind": "build_ok"
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"reward_call": 29,
|
| 1372 |
+
"index": 2,
|
| 1373 |
+
"score": 0.8082436187905102,
|
| 1374 |
+
"task_id": "bottle_cage_bike",
|
| 1375 |
+
"code_chars": 3262,
|
| 1376 |
+
"cadforge_build": 1.0,
|
| 1377 |
+
"cadforge_total": 0.7744042574006003,
|
| 1378 |
+
"has_fixture": true,
|
| 1379 |
+
"has_cadquery_import": true,
|
| 1380 |
+
"error_kind": "build_ok"
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"reward_call": 29,
|
| 1384 |
+
"index": 3,
|
| 1385 |
+
"score": -0.615,
|
| 1386 |
+
"task_id": "bottle_cage_bike",
|
| 1387 |
+
"code_chars": 4319,
|
| 1388 |
+
"cadforge_build": 0.0,
|
| 1389 |
+
"cadforge_total": -1.0,
|
| 1390 |
+
"has_fixture": true,
|
| 1391 |
+
"has_cadquery_import": true,
|
| 1392 |
+
"error_kind": "AttributeError"
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"reward_call": 30,
|
| 1396 |
+
"index": 0,
|
| 1397 |
+
"score": -0.6649999999999999,
|
| 1398 |
+
"task_id": "cable_clip_snap",
|
| 1399 |
+
"code_chars": 3762,
|
| 1400 |
+
"cadforge_build": 0.0,
|
| 1401 |
+
"cadforge_total": -1.0,
|
| 1402 |
+
"has_fixture": true,
|
| 1403 |
+
"has_cadquery_import": true,
|
| 1404 |
+
"error_kind": "SyntaxError"
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"reward_call": 30,
|
| 1408 |
+
"index": 1,
|
| 1409 |
+
"score": -0.565,
|
| 1410 |
+
"task_id": "cable_clip_snap",
|
| 1411 |
+
"code_chars": 4712,
|
| 1412 |
+
"cadforge_build": 0.0,
|
| 1413 |
+
"cadforge_total": -1.0,
|
| 1414 |
+
"has_fixture": true,
|
| 1415 |
+
"has_cadquery_import": true,
|
| 1416 |
+
"error_kind": "BRep_API"
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"reward_call": 30,
|
| 1420 |
+
"index": 2,
|
| 1421 |
+
"score": 0.5964905901822536,
|
| 1422 |
+
"task_id": "wall_j_hook_120n",
|
| 1423 |
+
"code_chars": 1768,
|
| 1424 |
+
"cadforge_build": 1.0,
|
| 1425 |
+
"cadforge_total": 0.5252830472732395,
|
| 1426 |
+
"has_fixture": true,
|
| 1427 |
+
"has_cadquery_import": true,
|
| 1428 |
+
"error_kind": "build_ok"
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"reward_call": 30,
|
| 1432 |
+
"index": 3,
|
| 1433 |
+
"score": 0.6940885416666667,
|
| 1434 |
+
"task_id": "wall_j_hook_120n",
|
| 1435 |
+
"code_chars": 2716,
|
| 1436 |
+
"cadforge_build": 1.0,
|
| 1437 |
+
"cadforge_total": 0.6401041666666667,
|
| 1438 |
+
"has_fixture": true,
|
| 1439 |
+
"has_cadquery_import": true,
|
| 1440 |
+
"error_kind": "build_ok"
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"reward_call": 31,
|
| 1444 |
+
"index": 0,
|
| 1445 |
+
"score": -0.595,
|
| 1446 |
+
"task_id": "hinge_leaf_barrel",
|
| 1447 |
+
"code_chars": 5640,
|
| 1448 |
+
"cadforge_build": 0.0,
|
| 1449 |
+
"cadforge_total": -1.0,
|
| 1450 |
+
"has_fixture": true,
|
| 1451 |
+
"has_cadquery_import": true,
|
| 1452 |
+
"error_kind": "BRep_API"
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"reward_call": 31,
|
| 1456 |
+
"index": 1,
|
| 1457 |
+
"score": -0.565,
|
| 1458 |
+
"task_id": "hinge_leaf_barrel",
|
| 1459 |
+
"code_chars": 4917,
|
| 1460 |
+
"cadforge_build": 0.0,
|
| 1461 |
+
"cadforge_total": -1.0,
|
| 1462 |
+
"has_fixture": true,
|
| 1463 |
+
"has_cadquery_import": true,
|
| 1464 |
+
"error_kind": "TypeError"
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"reward_call": 31,
|
| 1468 |
+
"index": 2,
|
| 1469 |
+
"score": -0.595,
|
| 1470 |
+
"task_id": "hinge_leaf_barrel",
|
| 1471 |
+
"code_chars": 4238,
|
| 1472 |
+
"cadforge_build": 0.0,
|
| 1473 |
+
"cadforge_total": -1.0,
|
| 1474 |
+
"has_fixture": true,
|
| 1475 |
+
"has_cadquery_import": true,
|
| 1476 |
+
"error_kind": "StdFail"
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"reward_call": 31,
|
| 1480 |
+
"index": 3,
|
| 1481 |
+
"score": -0.695,
|
| 1482 |
+
"task_id": "hinge_leaf_barrel",
|
| 1483 |
+
"code_chars": 4538,
|
| 1484 |
+
"cadforge_build": 0.0,
|
| 1485 |
+
"cadforge_total": -1.0,
|
| 1486 |
+
"has_fixture": true,
|
| 1487 |
+
"has_cadquery_import": true,
|
| 1488 |
+
"error_kind": "SyntaxError"
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"reward_call": 32,
|
| 1492 |
+
"index": 0,
|
| 1493 |
+
"score": -0.74,
|
| 1494 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1495 |
+
"code_chars": 2802,
|
| 1496 |
+
"cadforge_build": 0.0,
|
| 1497 |
+
"cadforge_total": -1.0,
|
| 1498 |
+
"has_fixture": false,
|
| 1499 |
+
"has_cadquery_import": true,
|
| 1500 |
+
"error_kind": "ValueError"
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"reward_call": 32,
|
| 1504 |
+
"index": 1,
|
| 1505 |
+
"score": 0.7133481782847138,
|
| 1506 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1507 |
+
"code_chars": 1996,
|
| 1508 |
+
"cadforge_build": 1.0,
|
| 1509 |
+
"cadforge_total": 0.6627625626878985,
|
| 1510 |
+
"has_fixture": true,
|
| 1511 |
+
"has_cadquery_import": true,
|
| 1512 |
+
"error_kind": "build_ok"
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"reward_call": 32,
|
| 1516 |
+
"index": 2,
|
| 1517 |
+
"score": -0.565,
|
| 1518 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1519 |
+
"code_chars": 3354,
|
| 1520 |
+
"cadforge_build": 0.0,
|
| 1521 |
+
"cadforge_total": -1.0,
|
| 1522 |
+
"has_fixture": true,
|
| 1523 |
+
"has_cadquery_import": true,
|
| 1524 |
+
"error_kind": "ValueError"
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"reward_call": 32,
|
| 1528 |
+
"index": 3,
|
| 1529 |
+
"score": 0.706709468209975,
|
| 1530 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1531 |
+
"code_chars": 3572,
|
| 1532 |
+
"cadforge_build": 1.0,
|
| 1533 |
+
"cadforge_total": 0.6549523155411471,
|
| 1534 |
+
"has_fixture": true,
|
| 1535 |
+
"has_cadquery_import": true,
|
| 1536 |
+
"error_kind": "build_ok"
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"reward_call": 33,
|
| 1540 |
+
"index": 0,
|
| 1541 |
+
"score": 0.861626318029692,
|
| 1542 |
+
"task_id": "table_six_leg_500n",
|
| 1543 |
+
"code_chars": 3741,
|
| 1544 |
+
"cadforge_build": 1.0,
|
| 1545 |
+
"cadforge_total": 0.8372074329761082,
|
| 1546 |
+
"has_fixture": true,
|
| 1547 |
+
"has_cadquery_import": true,
|
| 1548 |
+
"error_kind": "build_ok"
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"reward_call": 33,
|
| 1552 |
+
"index": 1,
|
| 1553 |
+
"score": 0.8462143878621421,
|
| 1554 |
+
"task_id": "table_six_leg_500n",
|
| 1555 |
+
"code_chars": 3072,
|
| 1556 |
+
"cadforge_build": 1.0,
|
| 1557 |
+
"cadforge_total": 0.8190757504260495,
|
| 1558 |
+
"has_fixture": true,
|
| 1559 |
+
"has_cadquery_import": true,
|
| 1560 |
+
"error_kind": "build_ok"
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"reward_call": 33,
|
| 1564 |
+
"index": 2,
|
| 1565 |
+
"score": -0.615,
|
| 1566 |
+
"task_id": "laptop_riser_vented",
|
| 1567 |
+
"code_chars": 4152,
|
| 1568 |
+
"cadforge_build": 0.0,
|
| 1569 |
+
"cadforge_total": -1.0,
|
| 1570 |
+
"has_fixture": true,
|
| 1571 |
+
"has_cadquery_import": true,
|
| 1572 |
+
"error_kind": "AttributeError"
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"reward_call": 33,
|
| 1576 |
+
"index": 3,
|
| 1577 |
+
"score": -0.615,
|
| 1578 |
+
"task_id": "laptop_riser_vented",
|
| 1579 |
+
"code_chars": 3293,
|
| 1580 |
+
"cadforge_build": 0.0,
|
| 1581 |
+
"cadforge_total": -1.0,
|
| 1582 |
+
"has_fixture": true,
|
| 1583 |
+
"has_cadquery_import": true,
|
| 1584 |
+
"error_kind": "AttributeError"
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"reward_call": 34,
|
| 1588 |
+
"index": 0,
|
| 1589 |
+
"score": 0.74466638095463,
|
| 1590 |
+
"task_id": "cable_clip_snap",
|
| 1591 |
+
"code_chars": 2960,
|
| 1592 |
+
"cadforge_build": 1.0,
|
| 1593 |
+
"cadforge_total": 0.699607507005447,
|
| 1594 |
+
"has_fixture": true,
|
| 1595 |
+
"has_cadquery_import": true,
|
| 1596 |
+
"error_kind": "build_ok"
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"reward_call": 34,
|
| 1600 |
+
"index": 1,
|
| 1601 |
+
"score": -0.565,
|
| 1602 |
+
"task_id": "cable_clip_snap",
|
| 1603 |
+
"code_chars": 3115,
|
| 1604 |
+
"cadforge_build": 0.0,
|
| 1605 |
+
"cadforge_total": -1.0,
|
| 1606 |
+
"has_fixture": true,
|
| 1607 |
+
"has_cadquery_import": true,
|
| 1608 |
+
"error_kind": "unknown"
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"reward_call": 34,
|
| 1612 |
+
"index": 2,
|
| 1613 |
+
"score": -0.615,
|
| 1614 |
+
"task_id": "table_six_leg_500n",
|
| 1615 |
+
"code_chars": 3061,
|
| 1616 |
+
"cadforge_build": 0.0,
|
| 1617 |
+
"cadforge_total": -1.0,
|
| 1618 |
+
"has_fixture": true,
|
| 1619 |
+
"has_cadquery_import": true,
|
| 1620 |
+
"error_kind": "NameError"
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"reward_call": 34,
|
| 1624 |
+
"index": 3,
|
| 1625 |
+
"score": 0.8580462011199014,
|
| 1626 |
+
"task_id": "table_six_leg_500n",
|
| 1627 |
+
"code_chars": 4384,
|
| 1628 |
+
"cadforge_build": 1.0,
|
| 1629 |
+
"cadforge_total": 0.8329955307292958,
|
| 1630 |
+
"has_fixture": true,
|
| 1631 |
+
"has_cadquery_import": true,
|
| 1632 |
+
"error_kind": "build_ok"
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"reward_call": 35,
|
| 1636 |
+
"index": 0,
|
| 1637 |
+
"score": -0.615,
|
| 1638 |
+
"task_id": "bike_accessory_mount_120n",
|
| 1639 |
+
"code_chars": 3991,
|
| 1640 |
+
"cadforge_build": 0.0,
|
| 1641 |
+
"cadforge_total": -1.0,
|
| 1642 |
+
"has_fixture": true,
|
| 1643 |
+
"has_cadquery_import": true,
|
| 1644 |
+
"error_kind": "NameError"
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"reward_call": 35,
|
| 1648 |
+
"index": 1,
|
| 1649 |
+
"score": -0.565,
|
| 1650 |
+
"task_id": "bike_accessory_mount_120n",
|
| 1651 |
+
"code_chars": 5609,
|
| 1652 |
+
"cadforge_build": 0.0,
|
| 1653 |
+
"cadforge_total": -1.0,
|
| 1654 |
+
"has_fixture": true,
|
| 1655 |
+
"has_cadquery_import": true,
|
| 1656 |
+
"error_kind": "TypeError"
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"reward_call": 35,
|
| 1660 |
+
"index": 2,
|
| 1661 |
+
"score": -0.6649999999999999,
|
| 1662 |
+
"task_id": "hinge_leaf_barrel",
|
| 1663 |
+
"code_chars": 4715,
|
| 1664 |
+
"cadforge_build": 0.0,
|
| 1665 |
+
"cadforge_total": -1.0,
|
| 1666 |
+
"has_fixture": true,
|
| 1667 |
+
"has_cadquery_import": true,
|
| 1668 |
+
"error_kind": "SyntaxError"
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"reward_call": 35,
|
| 1672 |
+
"index": 3,
|
| 1673 |
+
"score": -0.565,
|
| 1674 |
+
"task_id": "hinge_leaf_barrel",
|
| 1675 |
+
"code_chars": 3371,
|
| 1676 |
+
"cadforge_build": 0.0,
|
| 1677 |
+
"cadforge_total": -1.0,
|
| 1678 |
+
"has_fixture": true,
|
| 1679 |
+
"has_cadquery_import": true,
|
| 1680 |
+
"error_kind": "unknown"
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"reward_call": 36,
|
| 1684 |
+
"index": 0,
|
| 1685 |
+
"score": -0.615,
|
| 1686 |
+
"task_id": "laptop_riser_vented",
|
| 1687 |
+
"code_chars": 4362,
|
| 1688 |
+
"cadforge_build": 0.0,
|
| 1689 |
+
"cadforge_total": -1.0,
|
| 1690 |
+
"has_fixture": true,
|
| 1691 |
+
"has_cadquery_import": true,
|
| 1692 |
+
"error_kind": "NameError"
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"reward_call": 36,
|
| 1696 |
+
"index": 1,
|
| 1697 |
+
"score": 0.7392395833333334,
|
| 1698 |
+
"task_id": "laptop_riser_vented",
|
| 1699 |
+
"code_chars": 3363,
|
| 1700 |
+
"cadforge_build": 1.0,
|
| 1701 |
+
"cadforge_total": 0.6932230392156864,
|
| 1702 |
+
"has_fixture": true,
|
| 1703 |
+
"has_cadquery_import": true,
|
| 1704 |
+
"error_kind": "build_ok"
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"reward_call": 36,
|
| 1708 |
+
"index": 2,
|
| 1709 |
+
"score": -0.595,
|
| 1710 |
+
"task_id": "hinge_leaf_barrel",
|
| 1711 |
+
"code_chars": 4092,
|
| 1712 |
+
"cadforge_build": 0.0,
|
| 1713 |
+
"cadforge_total": -1.0,
|
| 1714 |
+
"has_fixture": true,
|
| 1715 |
+
"has_cadquery_import": true,
|
| 1716 |
+
"error_kind": "BRep_API"
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"reward_call": 36,
|
| 1720 |
+
"index": 3,
|
| 1721 |
+
"score": -0.595,
|
| 1722 |
+
"task_id": "hinge_leaf_barrel",
|
| 1723 |
+
"code_chars": 4457,
|
| 1724 |
+
"cadforge_build": 0.0,
|
| 1725 |
+
"cadforge_total": -1.0,
|
| 1726 |
+
"has_fixture": true,
|
| 1727 |
+
"has_cadquery_import": true,
|
| 1728 |
+
"error_kind": "TypeError"
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"reward_call": 37,
|
| 1732 |
+
"index": 0,
|
| 1733 |
+
"score": -0.645,
|
| 1734 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1735 |
+
"code_chars": 2648,
|
| 1736 |
+
"cadforge_build": 0.0,
|
| 1737 |
+
"cadforge_total": -1.0,
|
| 1738 |
+
"has_fixture": true,
|
| 1739 |
+
"has_cadquery_import": true,
|
| 1740 |
+
"error_kind": "NameError"
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"reward_call": 37,
|
| 1744 |
+
"index": 1,
|
| 1745 |
+
"score": -0.615,
|
| 1746 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1747 |
+
"code_chars": 3008,
|
| 1748 |
+
"cadforge_build": 0.0,
|
| 1749 |
+
"cadforge_total": -1.0,
|
| 1750 |
+
"has_fixture": true,
|
| 1751 |
+
"has_cadquery_import": true,
|
| 1752 |
+
"error_kind": "NameError"
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"reward_call": 37,
|
| 1756 |
+
"index": 2,
|
| 1757 |
+
"score": -0.565,
|
| 1758 |
+
"task_id": "shaft_torque_clamp_120nm",
|
| 1759 |
+
"code_chars": 4179,
|
| 1760 |
+
"cadforge_build": 0.0,
|
| 1761 |
+
"cadforge_total": -1.0,
|
| 1762 |
+
"has_fixture": true,
|
| 1763 |
+
"has_cadquery_import": true,
|
| 1764 |
+
"error_kind": "TypeError"
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"reward_call": 37,
|
| 1768 |
+
"index": 3,
|
| 1769 |
+
"score": -0.615,
|
| 1770 |
+
"task_id": "shaft_torque_clamp_120nm",
|
| 1771 |
+
"code_chars": 4380,
|
| 1772 |
+
"cadforge_build": 0.0,
|
| 1773 |
+
"cadforge_total": -1.0,
|
| 1774 |
+
"has_fixture": true,
|
| 1775 |
+
"has_cadquery_import": true,
|
| 1776 |
+
"error_kind": "NameError"
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"reward_call": 38,
|
| 1780 |
+
"index": 0,
|
| 1781 |
+
"score": 0.6298072916666667,
|
| 1782 |
+
"task_id": "wall_j_hook_120n",
|
| 1783 |
+
"code_chars": 2982,
|
| 1784 |
+
"cadforge_build": 1.0,
|
| 1785 |
+
"cadforge_total": 0.5644791666666668,
|
| 1786 |
+
"has_fixture": true,
|
| 1787 |
+
"has_cadquery_import": true,
|
| 1788 |
+
"error_kind": "build_ok"
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"reward_call": 38,
|
| 1792 |
+
"index": 1,
|
| 1793 |
+
"score": -0.6649999999999999,
|
| 1794 |
+
"task_id": "wall_j_hook_120n",
|
| 1795 |
+
"code_chars": 3064,
|
| 1796 |
+
"cadforge_build": 0.0,
|
| 1797 |
+
"cadforge_total": -1.0,
|
| 1798 |
+
"has_fixture": true,
|
| 1799 |
+
"has_cadquery_import": true,
|
| 1800 |
+
"error_kind": "SyntaxError"
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"reward_call": 38,
|
| 1804 |
+
"index": 2,
|
| 1805 |
+
"score": -0.615,
|
| 1806 |
+
"task_id": "bottle_cage_bike",
|
| 1807 |
+
"code_chars": 4150,
|
| 1808 |
+
"cadforge_build": 0.0,
|
| 1809 |
+
"cadforge_total": -1.0,
|
| 1810 |
+
"has_fixture": true,
|
| 1811 |
+
"has_cadquery_import": true,
|
| 1812 |
+
"error_kind": "NameError"
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"reward_call": 38,
|
| 1816 |
+
"index": 3,
|
| 1817 |
+
"score": -0.66,
|
| 1818 |
+
"task_id": "bottle_cage_bike",
|
| 1819 |
+
"code_chars": 2386,
|
| 1820 |
+
"cadforge_build": 0.0,
|
| 1821 |
+
"cadforge_total": -1.0,
|
| 1822 |
+
"has_fixture": true,
|
| 1823 |
+
"has_cadquery_import": true,
|
| 1824 |
+
"error_kind": "NameError"
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"reward_call": 39,
|
| 1828 |
+
"index": 0,
|
| 1829 |
+
"score": 0.754568977108671,
|
| 1830 |
+
"task_id": "wall_j_hook_120n",
|
| 1831 |
+
"code_chars": 3227,
|
| 1832 |
+
"cadforge_build": 1.0,
|
| 1833 |
+
"cadforge_total": 0.7112576201278482,
|
| 1834 |
+
"has_fixture": true,
|
| 1835 |
+
"has_cadquery_import": true,
|
| 1836 |
+
"error_kind": "build_ok"
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"reward_call": 39,
|
| 1840 |
+
"index": 1,
|
| 1841 |
+
"score": 0.8042421413024536,
|
| 1842 |
+
"task_id": "wall_j_hook_120n",
|
| 1843 |
+
"code_chars": 1816,
|
| 1844 |
+
"cadforge_build": 1.0,
|
| 1845 |
+
"cadforge_total": 0.769696636826416,
|
| 1846 |
+
"has_fixture": true,
|
| 1847 |
+
"has_cadquery_import": true,
|
| 1848 |
+
"error_kind": "build_ok"
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"reward_call": 39,
|
| 1852 |
+
"index": 2,
|
| 1853 |
+
"score": -0.615,
|
| 1854 |
+
"task_id": "cable_clip_snap",
|
| 1855 |
+
"code_chars": 5800,
|
| 1856 |
+
"cadforge_build": 0.0,
|
| 1857 |
+
"cadforge_total": -1.0,
|
| 1858 |
+
"has_fixture": true,
|
| 1859 |
+
"has_cadquery_import": true,
|
| 1860 |
+
"error_kind": "AttributeError"
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"reward_call": 39,
|
| 1864 |
+
"index": 3,
|
| 1865 |
+
"score": -0.615,
|
| 1866 |
+
"task_id": "cable_clip_snap",
|
| 1867 |
+
"code_chars": 4236,
|
| 1868 |
+
"cadforge_build": 0.0,
|
| 1869 |
+
"cadforge_total": -1.0,
|
| 1870 |
+
"has_fixture": true,
|
| 1871 |
+
"has_cadquery_import": true,
|
| 1872 |
+
"error_kind": "NameError"
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"reward_call": 40,
|
| 1876 |
+
"index": 0,
|
| 1877 |
+
"score": -0.615,
|
| 1878 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1879 |
+
"code_chars": 3310,
|
| 1880 |
+
"cadforge_build": 0.0,
|
| 1881 |
+
"cadforge_total": -1.0,
|
| 1882 |
+
"has_fixture": true,
|
| 1883 |
+
"has_cadquery_import": true,
|
| 1884 |
+
"error_kind": "AttributeError"
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"reward_call": 40,
|
| 1888 |
+
"index": 1,
|
| 1889 |
+
"score": -0.645,
|
| 1890 |
+
"task_id": "drawer_handle_two_bolt",
|
| 1891 |
+
"code_chars": 1892,
|
| 1892 |
+
"cadforge_build": 0.0,
|
| 1893 |
+
"cadforge_total": -1.0,
|
| 1894 |
+
"has_fixture": true,
|
| 1895 |
+
"has_cadquery_import": true,
|
| 1896 |
+
"error_kind": "AttributeError"
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"reward_call": 40,
|
| 1900 |
+
"index": 2,
|
| 1901 |
+
"score": -0.595,
|
| 1902 |
+
"task_id": "lightweight_truss_support_250n",
|
| 1903 |
+
"code_chars": 3626,
|
| 1904 |
+
"cadforge_build": 0.0,
|
| 1905 |
+
"cadforge_total": -1.0,
|
| 1906 |
+
"has_fixture": true,
|
| 1907 |
+
"has_cadquery_import": true,
|
| 1908 |
+
"error_kind": "TypeError"
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"reward_call": 40,
|
| 1912 |
+
"index": 3,
|
| 1913 |
+
"score": -0.565,
|
| 1914 |
+
"task_id": "lightweight_truss_support_250n",
|
| 1915 |
+
"code_chars": 3792,
|
| 1916 |
+
"cadforge_build": 0.0,
|
| 1917 |
+
"cadforge_total": -1.0,
|
| 1918 |
+
"has_fixture": true,
|
| 1919 |
+
"has_cadquery_import": true,
|
| 1920 |
+
"error_kind": "ValueError"
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"reward_call": 41,
|
| 1924 |
+
"index": 0,
|
| 1925 |
+
"score": -0.615,
|
| 1926 |
+
"task_id": "cable_clip_snap",
|
| 1927 |
+
"code_chars": 5623,
|
| 1928 |
+
"cadforge_build": 0.0,
|
| 1929 |
+
"cadforge_total": -1.0,
|
| 1930 |
+
"has_fixture": true,
|
| 1931 |
+
"has_cadquery_import": true,
|
| 1932 |
+
"error_kind": "AttributeError"
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"reward_call": 41,
|
| 1936 |
+
"index": 1,
|
| 1937 |
+
"score": -0.565,
|
| 1938 |
+
"task_id": "cable_clip_snap",
|
| 1939 |
+
"code_chars": 4202,
|
| 1940 |
+
"cadforge_build": 0.0,
|
| 1941 |
+
"cadforge_total": -1.0,
|
| 1942 |
+
"has_fixture": true,
|
| 1943 |
+
"has_cadquery_import": true,
|
| 1944 |
+
"error_kind": "ValueError"
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"reward_call": 41,
|
| 1948 |
+
"index": 2,
|
| 1949 |
+
"score": -0.66,
|
| 1950 |
+
"task_id": "cable_clip_snap",
|
| 1951 |
+
"code_chars": 4546,
|
| 1952 |
+
"cadforge_build": 0.0,
|
| 1953 |
+
"cadforge_total": -1.0,
|
| 1954 |
+
"has_fixture": true,
|
| 1955 |
+
"has_cadquery_import": true,
|
| 1956 |
+
"error_kind": "NameError"
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"reward_call": 41,
|
| 1960 |
+
"index": 3,
|
| 1961 |
+
"score": -0.565,
|
| 1962 |
+
"task_id": "cable_clip_snap",
|
| 1963 |
+
"code_chars": 3333,
|
| 1964 |
+
"cadforge_build": 0.0,
|
| 1965 |
+
"cadforge_total": -1.0,
|
| 1966 |
+
"has_fixture": true,
|
| 1967 |
+
"has_cadquery_import": true,
|
| 1968 |
+
"error_kind": "TypeError"
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"reward_call": 42,
|
| 1972 |
+
"index": 0,
|
| 1973 |
+
"score": -0.565,
|
| 1974 |
+
"task_id": "pipe_clamp_saddle",
|
| 1975 |
+
"code_chars": 3577,
|
| 1976 |
+
"cadforge_build": 0.0,
|
| 1977 |
+
"cadforge_total": -1.0,
|
| 1978 |
+
"has_fixture": true,
|
| 1979 |
+
"has_cadquery_import": true,
|
| 1980 |
+
"error_kind": "TypeError"
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"reward_call": 42,
|
| 1984 |
+
"index": 1,
|
| 1985 |
+
"score": -0.64,
|
| 1986 |
+
"task_id": "pipe_clamp_saddle",
|
| 1987 |
+
"code_chars": 3228,
|
| 1988 |
+
"cadforge_build": 0.0,
|
| 1989 |
+
"cadforge_total": -1.0,
|
| 1990 |
+
"has_fixture": true,
|
| 1991 |
+
"has_cadquery_import": true,
|
| 1992 |
+
"error_kind": "ValueError"
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"reward_call": 42,
|
| 1996 |
+
"index": 2,
|
| 1997 |
+
"score": 0.7584583333333335,
|
| 1998 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 1999 |
+
"code_chars": 2449,
|
| 2000 |
+
"cadforge_build": 1.0,
|
| 2001 |
+
"cadforge_total": 0.7158333333333334,
|
| 2002 |
+
"has_fixture": true,
|
| 2003 |
+
"has_cadquery_import": true,
|
| 2004 |
+
"error_kind": "build_ok"
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"reward_call": 42,
|
| 2008 |
+
"index": 3,
|
| 2009 |
+
"score": -0.565,
|
| 2010 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 2011 |
+
"code_chars": 2897,
|
| 2012 |
+
"cadforge_build": 0.0,
|
| 2013 |
+
"cadforge_total": -1.0,
|
| 2014 |
+
"has_fixture": true,
|
| 2015 |
+
"has_cadquery_import": true,
|
| 2016 |
+
"error_kind": "TypeError"
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"reward_call": 43,
|
| 2020 |
+
"index": 0,
|
| 2021 |
+
"score": -0.565,
|
| 2022 |
+
"task_id": "wall_j_hook_120n",
|
| 2023 |
+
"code_chars": 3439,
|
| 2024 |
+
"cadforge_build": 0.0,
|
| 2025 |
+
"cadforge_total": -1.0,
|
| 2026 |
+
"has_fixture": true,
|
| 2027 |
+
"has_cadquery_import": true,
|
| 2028 |
+
"error_kind": "TypeError"
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"reward_call": 43,
|
| 2032 |
+
"index": 1,
|
| 2033 |
+
"score": -0.615,
|
| 2034 |
+
"task_id": "wall_j_hook_120n",
|
| 2035 |
+
"code_chars": 3027,
|
| 2036 |
+
"cadforge_build": 0.0,
|
| 2037 |
+
"cadforge_total": -1.0,
|
| 2038 |
+
"has_fixture": true,
|
| 2039 |
+
"has_cadquery_import": true,
|
| 2040 |
+
"error_kind": "AttributeError"
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"reward_call": 43,
|
| 2044 |
+
"index": 2,
|
| 2045 |
+
"score": -0.615,
|
| 2046 |
+
"task_id": "bike_accessory_mount_120n",
|
| 2047 |
+
"code_chars": 4484,
|
| 2048 |
+
"cadforge_build": 0.0,
|
| 2049 |
+
"cadforge_total": -1.0,
|
| 2050 |
+
"has_fixture": true,
|
| 2051 |
+
"has_cadquery_import": true,
|
| 2052 |
+
"error_kind": "NameError"
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"reward_call": 43,
|
| 2056 |
+
"index": 3,
|
| 2057 |
+
"score": -0.615,
|
| 2058 |
+
"task_id": "bike_accessory_mount_120n",
|
| 2059 |
+
"code_chars": 4084,
|
| 2060 |
+
"cadforge_build": 0.0,
|
| 2061 |
+
"cadforge_total": -1.0,
|
| 2062 |
+
"has_fixture": true,
|
| 2063 |
+
"has_cadquery_import": true,
|
| 2064 |
+
"error_kind": "NameError"
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"reward_call": 44,
|
| 2068 |
+
"index": 0,
|
| 2069 |
+
"score": 0.6601287878787879,
|
| 2070 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 2071 |
+
"code_chars": 2908,
|
| 2072 |
+
"cadforge_build": 1.0,
|
| 2073 |
+
"cadforge_total": 0.6001515151515152,
|
| 2074 |
+
"has_fixture": true,
|
| 2075 |
+
"has_cadquery_import": true,
|
| 2076 |
+
"error_kind": "build_ok"
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"reward_call": 44,
|
| 2080 |
+
"index": 1,
|
| 2081 |
+
"score": 0.6805416666666667,
|
| 2082 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 2083 |
+
"code_chars": 3033,
|
| 2084 |
+
"cadforge_build": 1.0,
|
| 2085 |
+
"cadforge_total": 0.6241666666666668,
|
| 2086 |
+
"has_fixture": true,
|
| 2087 |
+
"has_cadquery_import": true,
|
| 2088 |
+
"error_kind": "build_ok"
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"reward_call": 44,
|
| 2092 |
+
"index": 2,
|
| 2093 |
+
"score": -0.615,
|
| 2094 |
+
"task_id": "cable_clip_snap",
|
| 2095 |
+
"code_chars": 3712,
|
| 2096 |
+
"cadforge_build": 0.0,
|
| 2097 |
+
"cadforge_total": -1.0,
|
| 2098 |
+
"has_fixture": true,
|
| 2099 |
+
"has_cadquery_import": true,
|
| 2100 |
+
"error_kind": "NameError"
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"reward_call": 44,
|
| 2104 |
+
"index": 3,
|
| 2105 |
+
"score": -0.615,
|
| 2106 |
+
"task_id": "cable_clip_snap",
|
| 2107 |
+
"code_chars": 4204,
|
| 2108 |
+
"cadforge_build": 0.0,
|
| 2109 |
+
"cadforge_total": -1.0,
|
| 2110 |
+
"has_fixture": true,
|
| 2111 |
+
"has_cadquery_import": true,
|
| 2112 |
+
"error_kind": "ValueError"
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"reward_call": 45,
|
| 2116 |
+
"index": 0,
|
| 2117 |
+
"score": -0.615,
|
| 2118 |
+
"task_id": "wall_j_hook_120n",
|
| 2119 |
+
"code_chars": 2897,
|
| 2120 |
+
"cadforge_build": 0.0,
|
| 2121 |
+
"cadforge_total": -1.0,
|
| 2122 |
+
"has_fixture": true,
|
| 2123 |
+
"has_cadquery_import": true,
|
| 2124 |
+
"error_kind": "NameError"
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"reward_call": 45,
|
| 2128 |
+
"index": 1,
|
| 2129 |
+
"score": 0.7227219531738587,
|
| 2130 |
+
"task_id": "wall_j_hook_120n",
|
| 2131 |
+
"code_chars": 3059,
|
| 2132 |
+
"cadforge_build": 1.0,
|
| 2133 |
+
"cadforge_total": 0.6737905331457161,
|
| 2134 |
+
"has_fixture": true,
|
| 2135 |
+
"has_cadquery_import": true,
|
| 2136 |
+
"error_kind": "build_ok"
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"reward_call": 45,
|
| 2140 |
+
"index": 2,
|
| 2141 |
+
"score": 0.7275085312225529,
|
| 2142 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 2143 |
+
"code_chars": 2059,
|
| 2144 |
+
"cadforge_build": 1.0,
|
| 2145 |
+
"cadforge_total": 0.6794218014382976,
|
| 2146 |
+
"has_fixture": true,
|
| 2147 |
+
"has_cadquery_import": true,
|
| 2148 |
+
"error_kind": "build_ok"
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"reward_call": 45,
|
| 2152 |
+
"index": 3,
|
| 2153 |
+
"score": 0.8428676010801626,
|
| 2154 |
+
"task_id": "shelf_bracket_triangular_200n",
|
| 2155 |
+
"code_chars": 2720,
|
| 2156 |
+
"cadforge_build": 1.0,
|
| 2157 |
+
"cadforge_total": 0.8151383542119559,
|
| 2158 |
+
"has_fixture": true,
|
| 2159 |
+
"has_cadquery_import": true,
|
| 2160 |
+
"error_kind": "build_ok"
|
| 2161 |
+
}
|
| 2162 |
+
]
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_code_health.png
ADDED
|
Git LFS Details
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_error_breakdown.png
ADDED
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/grpo_reward_curve.png
ADDED
|
Git LFS Details
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/metrics.json
ADDED
|
@@ -0,0 +1,1134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 0.01442,
|
| 4 |
+
"grad_norm": 0.3608,
|
| 5 |
+
"learning_rate": 2e-06,
|
| 6 |
+
"num_tokens": 12430.0,
|
| 7 |
+
"completions/mean_length": 1806.0,
|
| 8 |
+
"completions/min_length": 1593.0,
|
| 9 |
+
"completions/max_length": 2049.0,
|
| 10 |
+
"completions/clipped_ratio": 0.0,
|
| 11 |
+
"completions/mean_terminated_length": 1806.0,
|
| 12 |
+
"completions/min_terminated_length": 1593.0,
|
| 13 |
+
"completions/max_terminated_length": 2049.0,
|
| 14 |
+
"rewards/reward_func/mean": -0.6125,
|
| 15 |
+
"rewards/reward_func/std": 0.03948,
|
| 16 |
+
"reward": -0.6125,
|
| 17 |
+
"reward_std": 0.04596,
|
| 18 |
+
"frac_reward_zero_std": 0.0,
|
| 19 |
+
"entropy": 0.3182,
|
| 20 |
+
"clip_ratio/low_mean": 0.0,
|
| 21 |
+
"clip_ratio/low_min": 0.0,
|
| 22 |
+
"clip_ratio/high_mean": 0.0,
|
| 23 |
+
"clip_ratio/high_max": 0.0,
|
| 24 |
+
"clip_ratio/region_mean": 0.0,
|
| 25 |
+
"epoch": 0.04167
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"loss": 0.001716,
|
| 29 |
+
"grad_norm": 0.3079,
|
| 30 |
+
"learning_rate": 1.956e-06,
|
| 31 |
+
"num_tokens": 22730.0,
|
| 32 |
+
"completions/mean_length": 1236.0,
|
| 33 |
+
"completions/min_length": 1121.0,
|
| 34 |
+
"completions/max_length": 1388.0,
|
| 35 |
+
"completions/clipped_ratio": 0.0,
|
| 36 |
+
"completions/mean_terminated_length": 1236.0,
|
| 37 |
+
"completions/min_terminated_length": 1121.0,
|
| 38 |
+
"completions/max_terminated_length": 1388.0,
|
| 39 |
+
"rewards/reward_func/mean": -0.2865,
|
| 40 |
+
"rewards/reward_func/std": 0.6907,
|
| 41 |
+
"reward": -0.2865,
|
| 42 |
+
"reward_std": 0.4999,
|
| 43 |
+
"frac_reward_zero_std": 0.5,
|
| 44 |
+
"entropy": 0.435,
|
| 45 |
+
"clip_ratio/low_mean": 0.0,
|
| 46 |
+
"clip_ratio/low_min": 0.0,
|
| 47 |
+
"clip_ratio/high_mean": 0.0,
|
| 48 |
+
"clip_ratio/high_max": 0.0,
|
| 49 |
+
"clip_ratio/region_mean": 0.0,
|
| 50 |
+
"epoch": 0.08333
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"loss": -0.0886,
|
| 54 |
+
"grad_norm": 0.4128,
|
| 55 |
+
"learning_rate": 1.911e-06,
|
| 56 |
+
"num_tokens": 32890.0,
|
| 57 |
+
"completions/mean_length": 1234.0,
|
| 58 |
+
"completions/min_length": 888.0,
|
| 59 |
+
"completions/max_length": 1761.0,
|
| 60 |
+
"completions/clipped_ratio": 0.0,
|
| 61 |
+
"completions/mean_terminated_length": 1234.0,
|
| 62 |
+
"completions/min_terminated_length": 888.0,
|
| 63 |
+
"completions/max_terminated_length": 1761.0,
|
| 64 |
+
"rewards/reward_func/mean": -0.3212,
|
| 65 |
+
"rewards/reward_func/std": 0.6778,
|
| 66 |
+
"reward": -0.3212,
|
| 67 |
+
"reward_std": 0.5039,
|
| 68 |
+
"frac_reward_zero_std": 0.0,
|
| 69 |
+
"entropy": 0.2941,
|
| 70 |
+
"clip_ratio/low_mean": 0.0,
|
| 71 |
+
"clip_ratio/low_min": 0.0,
|
| 72 |
+
"clip_ratio/high_mean": 0.0,
|
| 73 |
+
"clip_ratio/high_max": 0.0,
|
| 74 |
+
"clip_ratio/region_mean": 0.0,
|
| 75 |
+
"epoch": 0.125
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"loss": -0.014,
|
| 79 |
+
"grad_norm": 0.378,
|
| 80 |
+
"learning_rate": 1.867e-06,
|
| 81 |
+
"num_tokens": 43360.0,
|
| 82 |
+
"completions/mean_length": 1334.0,
|
| 83 |
+
"completions/min_length": 1254.0,
|
| 84 |
+
"completions/max_length": 1407.0,
|
| 85 |
+
"completions/clipped_ratio": 0.0,
|
| 86 |
+
"completions/mean_terminated_length": 1334.0,
|
| 87 |
+
"completions/min_terminated_length": 1254.0,
|
| 88 |
+
"completions/max_terminated_length": 1407.0,
|
| 89 |
+
"rewards/reward_func/mean": -0.5775,
|
| 90 |
+
"rewards/reward_func/std": 0.025,
|
| 91 |
+
"reward": -0.5775,
|
| 92 |
+
"reward_std": 0.01768,
|
| 93 |
+
"frac_reward_zero_std": 0.5,
|
| 94 |
+
"entropy": 0.3839,
|
| 95 |
+
"clip_ratio/low_mean": 0.0,
|
| 96 |
+
"clip_ratio/low_min": 0.0,
|
| 97 |
+
"clip_ratio/high_mean": 0.0,
|
| 98 |
+
"clip_ratio/high_max": 0.0,
|
| 99 |
+
"clip_ratio/region_mean": 0.0,
|
| 100 |
+
"epoch": 0.1667
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"loss": 0.02392,
|
| 104 |
+
"grad_norm": 0.4731,
|
| 105 |
+
"learning_rate": 1.822e-06,
|
| 106 |
+
"num_tokens": 53900.0,
|
| 107 |
+
"completions/mean_length": 1260.0,
|
| 108 |
+
"completions/min_length": 1161.0,
|
| 109 |
+
"completions/max_length": 1349.0,
|
| 110 |
+
"completions/clipped_ratio": 0.0,
|
| 111 |
+
"completions/mean_terminated_length": 1260.0,
|
| 112 |
+
"completions/min_terminated_length": 1161.0,
|
| 113 |
+
"completions/max_terminated_length": 1349.0,
|
| 114 |
+
"rewards/reward_func/mean": -0.59,
|
| 115 |
+
"rewards/reward_func/std": 0.02887,
|
| 116 |
+
"reward": -0.59,
|
| 117 |
+
"reward_std": 0.03536,
|
| 118 |
+
"frac_reward_zero_std": 0.0,
|
| 119 |
+
"entropy": 0.4196,
|
| 120 |
+
"clip_ratio/low_mean": 0.0,
|
| 121 |
+
"clip_ratio/low_min": 0.0,
|
| 122 |
+
"clip_ratio/high_mean": 0.0,
|
| 123 |
+
"clip_ratio/high_max": 0.0,
|
| 124 |
+
"clip_ratio/region_mean": 0.0,
|
| 125 |
+
"epoch": 0.2083
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"loss": 0.1752,
|
| 129 |
+
"grad_norm": 0.5181,
|
| 130 |
+
"learning_rate": 1.778e-06,
|
| 131 |
+
"num_tokens": 63280.0,
|
| 132 |
+
"completions/mean_length": 1065.0,
|
| 133 |
+
"completions/min_length": 638.0,
|
| 134 |
+
"completions/max_length": 1501.0,
|
| 135 |
+
"completions/clipped_ratio": 0.0,
|
| 136 |
+
"completions/mean_terminated_length": 1065.0,
|
| 137 |
+
"completions/min_terminated_length": 638.0,
|
| 138 |
+
"completions/max_terminated_length": 1501.0,
|
| 139 |
+
"rewards/reward_func/mean": -0.259,
|
| 140 |
+
"rewards/reward_func/std": 0.6459,
|
| 141 |
+
"reward": -0.259,
|
| 142 |
+
"reward_std": 0.4682,
|
| 143 |
+
"frac_reward_zero_std": 0.0,
|
| 144 |
+
"entropy": 0.4185,
|
| 145 |
+
"clip_ratio/low_mean": 0.0,
|
| 146 |
+
"clip_ratio/low_min": 0.0,
|
| 147 |
+
"clip_ratio/high_mean": 0.0,
|
| 148 |
+
"clip_ratio/high_max": 0.0,
|
| 149 |
+
"clip_ratio/region_mean": 0.0,
|
| 150 |
+
"epoch": 0.25
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"loss": -0.02425,
|
| 154 |
+
"grad_norm": 0.4749,
|
| 155 |
+
"learning_rate": 1.733e-06,
|
| 156 |
+
"num_tokens": 73400.0,
|
| 157 |
+
"completions/mean_length": 1181.0,
|
| 158 |
+
"completions/min_length": 1050.0,
|
| 159 |
+
"completions/max_length": 1280.0,
|
| 160 |
+
"completions/clipped_ratio": 0.0,
|
| 161 |
+
"completions/mean_terminated_length": 1181.0,
|
| 162 |
+
"completions/min_terminated_length": 1050.0,
|
| 163 |
+
"completions/max_terminated_length": 1280.0,
|
| 164 |
+
"rewards/reward_func/mean": 0.1058,
|
| 165 |
+
"rewards/reward_func/std": 0.8335,
|
| 166 |
+
"reward": 0.1058,
|
| 167 |
+
"reward_std": 1.019,
|
| 168 |
+
"frac_reward_zero_std": 0.0,
|
| 169 |
+
"entropy": 0.3589,
|
| 170 |
+
"clip_ratio/low_mean": 0.0,
|
| 171 |
+
"clip_ratio/low_min": 0.0,
|
| 172 |
+
"clip_ratio/high_mean": 0.0,
|
| 173 |
+
"clip_ratio/high_max": 0.0,
|
| 174 |
+
"clip_ratio/region_mean": 0.0,
|
| 175 |
+
"epoch": 0.2917
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"loss": 0.04866,
|
| 179 |
+
"grad_norm": 0.3497,
|
| 180 |
+
"learning_rate": 1.689e-06,
|
| 181 |
+
"num_tokens": 84370.0,
|
| 182 |
+
"completions/mean_length": 1423.0,
|
| 183 |
+
"completions/min_length": 1128.0,
|
| 184 |
+
"completions/max_length": 1714.0,
|
| 185 |
+
"completions/clipped_ratio": 0.0,
|
| 186 |
+
"completions/mean_terminated_length": 1423.0,
|
| 187 |
+
"completions/min_terminated_length": 1128.0,
|
| 188 |
+
"completions/max_terminated_length": 1714.0,
|
| 189 |
+
"rewards/reward_func/mean": -0.2646,
|
| 190 |
+
"rewards/reward_func/std": 0.7355,
|
| 191 |
+
"reward": -0.2646,
|
| 192 |
+
"reward_std": 0.5662,
|
| 193 |
+
"frac_reward_zero_std": 0.0,
|
| 194 |
+
"entropy": 0.2518,
|
| 195 |
+
"clip_ratio/low_mean": 0.0,
|
| 196 |
+
"clip_ratio/low_min": 0.0,
|
| 197 |
+
"clip_ratio/high_mean": 0.0,
|
| 198 |
+
"clip_ratio/high_max": 0.0,
|
| 199 |
+
"clip_ratio/region_mean": 0.0,
|
| 200 |
+
"epoch": 0.3333
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"loss": 0.03209,
|
| 204 |
+
"grad_norm": 0.4848,
|
| 205 |
+
"learning_rate": 1.644e-06,
|
| 206 |
+
"num_tokens": 93020.0,
|
| 207 |
+
"completions/mean_length": 895.8,
|
| 208 |
+
"completions/min_length": 681.0,
|
| 209 |
+
"completions/max_length": 1126.0,
|
| 210 |
+
"completions/clipped_ratio": 0.0,
|
| 211 |
+
"completions/mean_terminated_length": 895.8,
|
| 212 |
+
"completions/min_terminated_length": 681.0,
|
| 213 |
+
"completions/max_terminated_length": 1126.0,
|
| 214 |
+
"rewards/reward_func/mean": 0.4291,
|
| 215 |
+
"rewards/reward_func/std": 0.6985,
|
| 216 |
+
"reward": 0.4291,
|
| 217 |
+
"reward_std": 0.5294,
|
| 218 |
+
"frac_reward_zero_std": 0.0,
|
| 219 |
+
"entropy": 0.2806,
|
| 220 |
+
"clip_ratio/low_mean": 0.0,
|
| 221 |
+
"clip_ratio/low_min": 0.0,
|
| 222 |
+
"clip_ratio/high_mean": 0.0,
|
| 223 |
+
"clip_ratio/high_max": 0.0,
|
| 224 |
+
"clip_ratio/region_mean": 0.0,
|
| 225 |
+
"epoch": 0.375
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"loss": 0.1069,
|
| 229 |
+
"grad_norm": 0.4645,
|
| 230 |
+
"learning_rate": 1.6e-06,
|
| 231 |
+
"num_tokens": 102800.0,
|
| 232 |
+
"completions/mean_length": 1144.0,
|
| 233 |
+
"completions/min_length": 940.0,
|
| 234 |
+
"completions/max_length": 1385.0,
|
| 235 |
+
"completions/clipped_ratio": 0.0,
|
| 236 |
+
"completions/mean_terminated_length": 1144.0,
|
| 237 |
+
"completions/min_terminated_length": 940.0,
|
| 238 |
+
"completions/max_terminated_length": 1385.0,
|
| 239 |
+
"rewards/reward_func/mean": -0.2344,
|
| 240 |
+
"rewards/reward_func/std": 0.7148,
|
| 241 |
+
"reward": -0.2344,
|
| 242 |
+
"reward_std": 0.5241,
|
| 243 |
+
"frac_reward_zero_std": 0.0,
|
| 244 |
+
"entropy": 0.3686,
|
| 245 |
+
"clip_ratio/low_mean": 0.0,
|
| 246 |
+
"clip_ratio/low_min": 0.0,
|
| 247 |
+
"clip_ratio/high_mean": 0.0,
|
| 248 |
+
"clip_ratio/high_max": 0.0,
|
| 249 |
+
"clip_ratio/region_mean": 0.0,
|
| 250 |
+
"epoch": 0.4167
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"loss": 0.05633,
|
| 254 |
+
"grad_norm": 0.4554,
|
| 255 |
+
"learning_rate": 1.556e-06,
|
| 256 |
+
"num_tokens": 112900.0,
|
| 257 |
+
"completions/mean_length": 1239.0,
|
| 258 |
+
"completions/min_length": 840.0,
|
| 259 |
+
"completions/max_length": 1500.0,
|
| 260 |
+
"completions/clipped_ratio": 0.0,
|
| 261 |
+
"completions/mean_terminated_length": 1239.0,
|
| 262 |
+
"completions/min_terminated_length": 840.0,
|
| 263 |
+
"completions/max_terminated_length": 1500.0,
|
| 264 |
+
"rewards/reward_func/mean": -0.2843,
|
| 265 |
+
"rewards/reward_func/std": 0.7151,
|
| 266 |
+
"reward": -0.2843,
|
| 267 |
+
"reward_std": 0.5206,
|
| 268 |
+
"frac_reward_zero_std": 0.0,
|
| 269 |
+
"entropy": 0.3845,
|
| 270 |
+
"clip_ratio/low_mean": 0.0,
|
| 271 |
+
"clip_ratio/low_min": 0.0,
|
| 272 |
+
"clip_ratio/high_mean": 0.0,
|
| 273 |
+
"clip_ratio/high_max": 0.0,
|
| 274 |
+
"clip_ratio/region_mean": 0.0,
|
| 275 |
+
"epoch": 0.4583
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"loss": -0.001317,
|
| 279 |
+
"grad_norm": 0.4037,
|
| 280 |
+
"learning_rate": 1.511e-06,
|
| 281 |
+
"num_tokens": 122600.0,
|
| 282 |
+
"completions/mean_length": 1084.0,
|
| 283 |
+
"completions/min_length": 860.0,
|
| 284 |
+
"completions/max_length": 1304.0,
|
| 285 |
+
"completions/clipped_ratio": 0.0,
|
| 286 |
+
"completions/mean_terminated_length": 1084.0,
|
| 287 |
+
"completions/min_terminated_length": 860.0,
|
| 288 |
+
"completions/max_terminated_length": 1304.0,
|
| 289 |
+
"rewards/reward_func/mean": 0.3786,
|
| 290 |
+
"rewards/reward_func/std": 0.6293,
|
| 291 |
+
"reward": 0.3786,
|
| 292 |
+
"reward_std": 0.4421,
|
| 293 |
+
"frac_reward_zero_std": 0.0,
|
| 294 |
+
"entropy": 0.3328,
|
| 295 |
+
"clip_ratio/low_mean": 0.0,
|
| 296 |
+
"clip_ratio/low_min": 0.0,
|
| 297 |
+
"clip_ratio/high_mean": 0.0,
|
| 298 |
+
"clip_ratio/high_max": 0.0,
|
| 299 |
+
"clip_ratio/region_mean": 0.0,
|
| 300 |
+
"epoch": 0.5
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"loss": -0.1414,
|
| 304 |
+
"grad_norm": 0.425,
|
| 305 |
+
"learning_rate": 1.467e-06,
|
| 306 |
+
"num_tokens": 131900.0,
|
| 307 |
+
"completions/mean_length": 1090.0,
|
| 308 |
+
"completions/min_length": 415.0,
|
| 309 |
+
"completions/max_length": 1503.0,
|
| 310 |
+
"completions/clipped_ratio": 0.0,
|
| 311 |
+
"completions/mean_terminated_length": 1090.0,
|
| 312 |
+
"completions/min_terminated_length": 415.0,
|
| 313 |
+
"completions/max_terminated_length": 1503.0,
|
| 314 |
+
"rewards/reward_func/mean": -0.7125,
|
| 315 |
+
"rewards/reward_func/std": 0.141,
|
| 316 |
+
"reward": -0.7125,
|
| 317 |
+
"reward_std": 0.1308,
|
| 318 |
+
"frac_reward_zero_std": 0.0,
|
| 319 |
+
"entropy": 0.3197,
|
| 320 |
+
"clip_ratio/low_mean": 0.0,
|
| 321 |
+
"clip_ratio/low_min": 0.0,
|
| 322 |
+
"clip_ratio/high_mean": 0.0,
|
| 323 |
+
"clip_ratio/high_max": 0.0,
|
| 324 |
+
"clip_ratio/region_mean": 0.0,
|
| 325 |
+
"epoch": 0.5417
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"loss": 0.02239,
|
| 329 |
+
"grad_norm": 0.2146,
|
| 330 |
+
"learning_rate": 1.422e-06,
|
| 331 |
+
"num_tokens": 140700.0,
|
| 332 |
+
"completions/mean_length": 899.0,
|
| 333 |
+
"completions/min_length": 682.0,
|
| 334 |
+
"completions/max_length": 1117.0,
|
| 335 |
+
"completions/clipped_ratio": 0.0,
|
| 336 |
+
"completions/mean_terminated_length": 899.0,
|
| 337 |
+
"completions/min_terminated_length": 682.0,
|
| 338 |
+
"completions/max_terminated_length": 1117.0,
|
| 339 |
+
"rewards/reward_func/mean": 0.05676,
|
| 340 |
+
"rewards/reward_func/std": 0.7777,
|
| 341 |
+
"reward": 0.05676,
|
| 342 |
+
"reward_std": 0.04823,
|
| 343 |
+
"frac_reward_zero_std": 0.5,
|
| 344 |
+
"entropy": 0.1996,
|
| 345 |
+
"clip_ratio/low_mean": 0.0,
|
| 346 |
+
"clip_ratio/low_min": 0.0,
|
| 347 |
+
"clip_ratio/high_mean": 0.0,
|
| 348 |
+
"clip_ratio/high_max": 0.0,
|
| 349 |
+
"clip_ratio/region_mean": 0.0,
|
| 350 |
+
"epoch": 0.5833
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"loss": -0.003764,
|
| 354 |
+
"grad_norm": 0.3895,
|
| 355 |
+
"learning_rate": 1.378e-06,
|
| 356 |
+
"num_tokens": 150600.0,
|
| 357 |
+
"completions/mean_length": 1119.0,
|
| 358 |
+
"completions/min_length": 1050.0,
|
| 359 |
+
"completions/max_length": 1225.0,
|
| 360 |
+
"completions/clipped_ratio": 0.0,
|
| 361 |
+
"completions/mean_terminated_length": 1119.0,
|
| 362 |
+
"completions/min_terminated_length": 1050.0,
|
| 363 |
+
"completions/max_terminated_length": 1225.0,
|
| 364 |
+
"rewards/reward_func/mean": -0.585,
|
| 365 |
+
"rewards/reward_func/std": 0.02449,
|
| 366 |
+
"reward": -0.585,
|
| 367 |
+
"reward_std": 0.007071,
|
| 368 |
+
"frac_reward_zero_std": 0.5,
|
| 369 |
+
"entropy": 0.4056,
|
| 370 |
+
"clip_ratio/low_mean": 0.0,
|
| 371 |
+
"clip_ratio/low_min": 0.0,
|
| 372 |
+
"clip_ratio/high_mean": 0.0,
|
| 373 |
+
"clip_ratio/high_max": 0.0,
|
| 374 |
+
"clip_ratio/region_mean": 0.0,
|
| 375 |
+
"epoch": 0.625
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"loss": 0.05599,
|
| 379 |
+
"grad_norm": 0.4948,
|
| 380 |
+
"learning_rate": 1.333e-06,
|
| 381 |
+
"num_tokens": 160300.0,
|
| 382 |
+
"completions/mean_length": 1077.0,
|
| 383 |
+
"completions/min_length": 667.0,
|
| 384 |
+
"completions/max_length": 1356.0,
|
| 385 |
+
"completions/clipped_ratio": 0.0,
|
| 386 |
+
"completions/mean_terminated_length": 1077.0,
|
| 387 |
+
"completions/min_terminated_length": 667.0,
|
| 388 |
+
"completions/max_terminated_length": 1356.0,
|
| 389 |
+
"rewards/reward_func/mean": 0.7366,
|
| 390 |
+
"rewards/reward_func/std": 0.03196,
|
| 391 |
+
"reward": 0.7366,
|
| 392 |
+
"reward_std": 0.03106,
|
| 393 |
+
"frac_reward_zero_std": 0.0,
|
| 394 |
+
"entropy": 0.4099,
|
| 395 |
+
"clip_ratio/low_mean": 0.0,
|
| 396 |
+
"clip_ratio/low_min": 0.0,
|
| 397 |
+
"clip_ratio/high_mean": 0.0,
|
| 398 |
+
"clip_ratio/high_max": 0.0,
|
| 399 |
+
"clip_ratio/region_mean": 0.0,
|
| 400 |
+
"epoch": 0.6667
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"loss": 0.005318,
|
| 404 |
+
"grad_norm": 0.4148,
|
| 405 |
+
"learning_rate": 1.289e-06,
|
| 406 |
+
"num_tokens": 170400.0,
|
| 407 |
+
"completions/mean_length": 1163.0,
|
| 408 |
+
"completions/min_length": 1019.0,
|
| 409 |
+
"completions/max_length": 1325.0,
|
| 410 |
+
"completions/clipped_ratio": 0.0,
|
| 411 |
+
"completions/mean_terminated_length": 1163.0,
|
| 412 |
+
"completions/min_terminated_length": 1019.0,
|
| 413 |
+
"completions/max_terminated_length": 1325.0,
|
| 414 |
+
"rewards/reward_func/mean": 0.04624,
|
| 415 |
+
"rewards/reward_func/std": 0.7635,
|
| 416 |
+
"reward": 0.04624,
|
| 417 |
+
"reward_std": 0.9351,
|
| 418 |
+
"frac_reward_zero_std": 0.0,
|
| 419 |
+
"entropy": 0.2641,
|
| 420 |
+
"clip_ratio/low_mean": 0.0,
|
| 421 |
+
"clip_ratio/low_min": 0.0,
|
| 422 |
+
"clip_ratio/high_mean": 0.0,
|
| 423 |
+
"clip_ratio/high_max": 0.0,
|
| 424 |
+
"clip_ratio/region_mean": 0.0,
|
| 425 |
+
"epoch": 0.7083
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"loss": -0.01971,
|
| 429 |
+
"grad_norm": 0.3755,
|
| 430 |
+
"learning_rate": 1.244e-06,
|
| 431 |
+
"num_tokens": 181000.0,
|
| 432 |
+
"completions/mean_length": 1265.0,
|
| 433 |
+
"completions/min_length": 786.0,
|
| 434 |
+
"completions/max_length": 1814.0,
|
| 435 |
+
"completions/clipped_ratio": 0.0,
|
| 436 |
+
"completions/mean_terminated_length": 1265.0,
|
| 437 |
+
"completions/min_terminated_length": 786.0,
|
| 438 |
+
"completions/max_terminated_length": 1814.0,
|
| 439 |
+
"rewards/reward_func/mean": 0.03695,
|
| 440 |
+
"rewards/reward_func/std": 0.7673,
|
| 441 |
+
"reward": 0.03695,
|
| 442 |
+
"reward_std": 0.9397,
|
| 443 |
+
"frac_reward_zero_std": 0.0,
|
| 444 |
+
"entropy": 0.262,
|
| 445 |
+
"clip_ratio/low_mean": 0.0,
|
| 446 |
+
"clip_ratio/low_min": 0.0,
|
| 447 |
+
"clip_ratio/high_mean": 0.0,
|
| 448 |
+
"clip_ratio/high_max": 0.0,
|
| 449 |
+
"clip_ratio/region_mean": 0.0,
|
| 450 |
+
"epoch": 0.75
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"loss": -0.1262,
|
| 454 |
+
"grad_norm": 0.4486,
|
| 455 |
+
"learning_rate": 1.2e-06,
|
| 456 |
+
"num_tokens": 190400.0,
|
| 457 |
+
"completions/mean_length": 1038.0,
|
| 458 |
+
"completions/min_length": 768.0,
|
| 459 |
+
"completions/max_length": 1552.0,
|
| 460 |
+
"completions/clipped_ratio": 0.0,
|
| 461 |
+
"completions/mean_terminated_length": 1038.0,
|
| 462 |
+
"completions/min_terminated_length": 768.0,
|
| 463 |
+
"completions/max_terminated_length": 1552.0,
|
| 464 |
+
"rewards/reward_func/mean": 0.4054,
|
| 465 |
+
"rewards/reward_func/std": 0.649,
|
| 466 |
+
"reward": 0.4054,
|
| 467 |
+
"reward_std": 0.5055,
|
| 468 |
+
"frac_reward_zero_std": 0.0,
|
| 469 |
+
"entropy": 0.3054,
|
| 470 |
+
"clip_ratio/low_mean": 0.0,
|
| 471 |
+
"clip_ratio/low_min": 0.0,
|
| 472 |
+
"clip_ratio/high_mean": 0.0,
|
| 473 |
+
"clip_ratio/high_max": 0.0,
|
| 474 |
+
"clip_ratio/region_mean": 0.0,
|
| 475 |
+
"epoch": 0.7917
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"loss": -0.03057,
|
| 479 |
+
"grad_norm": 0.3822,
|
| 480 |
+
"learning_rate": 1.156e-06,
|
| 481 |
+
"num_tokens": 201200.0,
|
| 482 |
+
"completions/mean_length": 1326.0,
|
| 483 |
+
"completions/min_length": 1214.0,
|
| 484 |
+
"completions/max_length": 1454.0,
|
| 485 |
+
"completions/clipped_ratio": 0.0,
|
| 486 |
+
"completions/mean_terminated_length": 1326.0,
|
| 487 |
+
"completions/min_terminated_length": 1214.0,
|
| 488 |
+
"completions/max_terminated_length": 1454.0,
|
| 489 |
+
"rewards/reward_func/mean": -0.267,
|
| 490 |
+
"rewards/reward_func/std": 0.7297,
|
| 491 |
+
"reward": -0.267,
|
| 492 |
+
"reward_std": 0.5275,
|
| 493 |
+
"frac_reward_zero_std": 0.0,
|
| 494 |
+
"entropy": 0.269,
|
| 495 |
+
"clip_ratio/low_mean": 0.0,
|
| 496 |
+
"clip_ratio/low_min": 0.0,
|
| 497 |
+
"clip_ratio/high_mean": 0.0,
|
| 498 |
+
"clip_ratio/high_max": 0.0,
|
| 499 |
+
"clip_ratio/region_mean": 0.0,
|
| 500 |
+
"epoch": 0.8333
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"loss": -0.0849,
|
| 504 |
+
"grad_norm": 0.5006,
|
| 505 |
+
"learning_rate": 1.111e-06,
|
| 506 |
+
"num_tokens": 210500.0,
|
| 507 |
+
"completions/mean_length": 1002.0,
|
| 508 |
+
"completions/min_length": 773.0,
|
| 509 |
+
"completions/max_length": 1304.0,
|
| 510 |
+
"completions/clipped_ratio": 0.0,
|
| 511 |
+
"completions/mean_terminated_length": 1002.0,
|
| 512 |
+
"completions/min_terminated_length": 773.0,
|
| 513 |
+
"completions/max_terminated_length": 1304.0,
|
| 514 |
+
"rewards/reward_func/mean": -0.2841,
|
| 515 |
+
"rewards/reward_func/std": 0.6813,
|
| 516 |
+
"reward": -0.2841,
|
| 517 |
+
"reward_std": 0.521,
|
| 518 |
+
"frac_reward_zero_std": 0.0,
|
| 519 |
+
"entropy": 0.3822,
|
| 520 |
+
"clip_ratio/low_mean": 0.0,
|
| 521 |
+
"clip_ratio/low_min": 0.0,
|
| 522 |
+
"clip_ratio/high_mean": 0.0,
|
| 523 |
+
"clip_ratio/high_max": 0.0,
|
| 524 |
+
"clip_ratio/region_mean": 0.0,
|
| 525 |
+
"epoch": 0.875
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"loss": -0.02298,
|
| 529 |
+
"grad_norm": 0.41,
|
| 530 |
+
"learning_rate": 1.067e-06,
|
| 531 |
+
"num_tokens": 220700.0,
|
| 532 |
+
"completions/mean_length": 1222.0,
|
| 533 |
+
"completions/min_length": 1121.0,
|
| 534 |
+
"completions/max_length": 1368.0,
|
| 535 |
+
"completions/clipped_ratio": 0.0,
|
| 536 |
+
"completions/mean_terminated_length": 1222.0,
|
| 537 |
+
"completions/min_terminated_length": 1121.0,
|
| 538 |
+
"completions/max_terminated_length": 1368.0,
|
| 539 |
+
"rewards/reward_func/mean": 0.09389,
|
| 540 |
+
"rewards/reward_func/std": 0.8171,
|
| 541 |
+
"reward": 0.09389,
|
| 542 |
+
"reward_std": 0.05785,
|
| 543 |
+
"frac_reward_zero_std": 0.0,
|
| 544 |
+
"entropy": 0.2823,
|
| 545 |
+
"clip_ratio/low_mean": 0.0,
|
| 546 |
+
"clip_ratio/low_min": 0.0,
|
| 547 |
+
"clip_ratio/high_mean": 0.0,
|
| 548 |
+
"clip_ratio/high_max": 0.0,
|
| 549 |
+
"clip_ratio/region_mean": 0.0,
|
| 550 |
+
"epoch": 0.9167
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"loss": -0.05292,
|
| 554 |
+
"grad_norm": 0.5124,
|
| 555 |
+
"learning_rate": 1.022e-06,
|
| 556 |
+
"num_tokens": 230500.0,
|
| 557 |
+
"completions/mean_length": 990.8,
|
| 558 |
+
"completions/min_length": 280.0,
|
| 559 |
+
"completions/max_length": 1553.0,
|
| 560 |
+
"completions/clipped_ratio": 0.0,
|
| 561 |
+
"completions/mean_terminated_length": 990.8,
|
| 562 |
+
"completions/min_terminated_length": 280.0,
|
| 563 |
+
"completions/max_terminated_length": 1553.0,
|
| 564 |
+
"rewards/reward_func/mean": -0.3823,
|
| 565 |
+
"rewards/reward_func/std": 0.671,
|
| 566 |
+
"reward": -0.3823,
|
| 567 |
+
"reward_std": 0.5412,
|
| 568 |
+
"frac_reward_zero_std": 0.0,
|
| 569 |
+
"entropy": 0.3258,
|
| 570 |
+
"clip_ratio/low_mean": 0.0,
|
| 571 |
+
"clip_ratio/low_min": 0.0,
|
| 572 |
+
"clip_ratio/high_mean": 0.0,
|
| 573 |
+
"clip_ratio/high_max": 0.0,
|
| 574 |
+
"clip_ratio/region_mean": 0.0,
|
| 575 |
+
"epoch": 0.9583
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"loss": -0.05998,
|
| 579 |
+
"grad_norm": 0.5107,
|
| 580 |
+
"learning_rate": 9.778e-07,
|
| 581 |
+
"num_tokens": 239900.0,
|
| 582 |
+
"completions/mean_length": 1042.0,
|
| 583 |
+
"completions/min_length": 953.0,
|
| 584 |
+
"completions/max_length": 1133.0,
|
| 585 |
+
"completions/clipped_ratio": 0.0,
|
| 586 |
+
"completions/mean_terminated_length": 1042.0,
|
| 587 |
+
"completions/min_terminated_length": 953.0,
|
| 588 |
+
"completions/max_terminated_length": 1133.0,
|
| 589 |
+
"rewards/reward_func/mean": -0.5838,
|
| 590 |
+
"rewards/reward_func/std": 0.0225,
|
| 591 |
+
"reward": -0.5838,
|
| 592 |
+
"reward_std": 0.02652,
|
| 593 |
+
"frac_reward_zero_std": 0.0,
|
| 594 |
+
"entropy": 0.4597,
|
| 595 |
+
"clip_ratio/low_mean": 0.0,
|
| 596 |
+
"clip_ratio/low_min": 0.0,
|
| 597 |
+
"clip_ratio/high_mean": 0.0,
|
| 598 |
+
"clip_ratio/high_max": 0.0,
|
| 599 |
+
"clip_ratio/region_mean": 0.0,
|
| 600 |
+
"epoch": 1.0
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"loss": -0.03608,
|
| 604 |
+
"grad_norm": 0.4798,
|
| 605 |
+
"learning_rate": 9.333e-07,
|
| 606 |
+
"num_tokens": 249300.0,
|
| 607 |
+
"completions/mean_length": 1064.0,
|
| 608 |
+
"completions/min_length": 699.0,
|
| 609 |
+
"completions/max_length": 1321.0,
|
| 610 |
+
"completions/clipped_ratio": 0.0,
|
| 611 |
+
"completions/mean_terminated_length": 1064.0,
|
| 612 |
+
"completions/min_terminated_length": 699.0,
|
| 613 |
+
"completions/max_terminated_length": 1321.0,
|
| 614 |
+
"rewards/reward_func/mean": -0.2456,
|
| 615 |
+
"rewards/reward_func/std": 0.6726,
|
| 616 |
+
"reward": -0.2456,
|
| 617 |
+
"reward_std": 0.4871,
|
| 618 |
+
"frac_reward_zero_std": 0.0,
|
| 619 |
+
"entropy": 0.3157,
|
| 620 |
+
"clip_ratio/low_mean": 0.0,
|
| 621 |
+
"clip_ratio/low_min": 0.0,
|
| 622 |
+
"clip_ratio/high_mean": 0.0,
|
| 623 |
+
"clip_ratio/high_max": 0.0,
|
| 624 |
+
"clip_ratio/region_mean": 0.0,
|
| 625 |
+
"epoch": 1.042
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"loss": 0.06492,
|
| 629 |
+
"grad_norm": 0.3732,
|
| 630 |
+
"learning_rate": 8.889e-07,
|
| 631 |
+
"num_tokens": 259800.0,
|
| 632 |
+
"completions/mean_length": 1328.0,
|
| 633 |
+
"completions/min_length": 807.0,
|
| 634 |
+
"completions/max_length": 2093.0,
|
| 635 |
+
"completions/clipped_ratio": 0.0,
|
| 636 |
+
"completions/mean_terminated_length": 1328.0,
|
| 637 |
+
"completions/min_terminated_length": 807.0,
|
| 638 |
+
"completions/max_terminated_length": 2093.0,
|
| 639 |
+
"rewards/reward_func/mean": -0.59,
|
| 640 |
+
"rewards/reward_func/std": 0.02887,
|
| 641 |
+
"reward": -0.59,
|
| 642 |
+
"reward_std": 0.03536,
|
| 643 |
+
"frac_reward_zero_std": 0.0,
|
| 644 |
+
"entropy": 0.1963,
|
| 645 |
+
"clip_ratio/low_mean": 0.0,
|
| 646 |
+
"clip_ratio/low_min": 0.0,
|
| 647 |
+
"clip_ratio/high_mean": 0.0,
|
| 648 |
+
"clip_ratio/high_max": 0.0,
|
| 649 |
+
"clip_ratio/region_mean": 0.0,
|
| 650 |
+
"epoch": 1.083
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"loss": 0.01205,
|
| 654 |
+
"grad_norm": 0.2851,
|
| 655 |
+
"learning_rate": 8.444e-07,
|
| 656 |
+
"num_tokens": 270000.0,
|
| 657 |
+
"completions/mean_length": 1243.0,
|
| 658 |
+
"completions/min_length": 960.0,
|
| 659 |
+
"completions/max_length": 1674.0,
|
| 660 |
+
"completions/clipped_ratio": 0.0,
|
| 661 |
+
"completions/mean_terminated_length": 1243.0,
|
| 662 |
+
"completions/min_terminated_length": 960.0,
|
| 663 |
+
"completions/max_terminated_length": 1674.0,
|
| 664 |
+
"rewards/reward_func/mean": -0.5775,
|
| 665 |
+
"rewards/reward_func/std": 0.025,
|
| 666 |
+
"reward": -0.5775,
|
| 667 |
+
"reward_std": 0.01768,
|
| 668 |
+
"frac_reward_zero_std": 0.5,
|
| 669 |
+
"entropy": 0.348,
|
| 670 |
+
"clip_ratio/low_mean": 0.0,
|
| 671 |
+
"clip_ratio/low_min": 0.0,
|
| 672 |
+
"clip_ratio/high_mean": 0.0,
|
| 673 |
+
"clip_ratio/high_max": 0.0,
|
| 674 |
+
"clip_ratio/region_mean": 0.0,
|
| 675 |
+
"epoch": 1.125
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"loss": 0.0,
|
| 679 |
+
"grad_norm": 0.0,
|
| 680 |
+
"learning_rate": 8e-07,
|
| 681 |
+
"num_tokens": 280600.0,
|
| 682 |
+
"completions/mean_length": 1162.0,
|
| 683 |
+
"completions/min_length": 1034.0,
|
| 684 |
+
"completions/max_length": 1295.0,
|
| 685 |
+
"completions/clipped_ratio": 0.0,
|
| 686 |
+
"completions/mean_terminated_length": 1162.0,
|
| 687 |
+
"completions/min_terminated_length": 1034.0,
|
| 688 |
+
"completions/max_terminated_length": 1295.0,
|
| 689 |
+
"rewards/reward_func/mean": -0.59,
|
| 690 |
+
"rewards/reward_func/std": 0.02887,
|
| 691 |
+
"reward": -0.59,
|
| 692 |
+
"reward_std": 0.0,
|
| 693 |
+
"frac_reward_zero_std": 1.0,
|
| 694 |
+
"entropy": 0.3817,
|
| 695 |
+
"clip_ratio/low_mean": 0.0,
|
| 696 |
+
"clip_ratio/low_min": 0.0,
|
| 697 |
+
"clip_ratio/high_mean": 0.0,
|
| 698 |
+
"clip_ratio/high_max": 0.0,
|
| 699 |
+
"clip_ratio/region_mean": 0.0,
|
| 700 |
+
"epoch": 1.167
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"loss": 0.03949,
|
| 704 |
+
"grad_norm": 0.4215,
|
| 705 |
+
"learning_rate": 7.556e-07,
|
| 706 |
+
"num_tokens": 290200.0,
|
| 707 |
+
"completions/mean_length": 1097.0,
|
| 708 |
+
"completions/min_length": 835.0,
|
| 709 |
+
"completions/max_length": 1481.0,
|
| 710 |
+
"completions/clipped_ratio": 0.0,
|
| 711 |
+
"completions/mean_terminated_length": 1097.0,
|
| 712 |
+
"completions/min_terminated_length": 835.0,
|
| 713 |
+
"completions/max_terminated_length": 1481.0,
|
| 714 |
+
"rewards/reward_func/mean": 0.0642,
|
| 715 |
+
"rewards/reward_func/std": 0.7861,
|
| 716 |
+
"reward": 0.0642,
|
| 717 |
+
"reward_std": 0.9605,
|
| 718 |
+
"frac_reward_zero_std": 0.0,
|
| 719 |
+
"entropy": 0.2496,
|
| 720 |
+
"clip_ratio/low_mean": 0.0,
|
| 721 |
+
"clip_ratio/low_min": 0.0,
|
| 722 |
+
"clip_ratio/high_mean": 0.0,
|
| 723 |
+
"clip_ratio/high_max": 0.0,
|
| 724 |
+
"clip_ratio/region_mean": 0.0,
|
| 725 |
+
"epoch": 1.208
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"loss": -0.1055,
|
| 729 |
+
"grad_norm": 0.5083,
|
| 730 |
+
"learning_rate": 7.111e-07,
|
| 731 |
+
"num_tokens": 300200.0,
|
| 732 |
+
"completions/mean_length": 1159.0,
|
| 733 |
+
"completions/min_length": 657.0,
|
| 734 |
+
"completions/max_length": 1593.0,
|
| 735 |
+
"completions/clipped_ratio": 0.0,
|
| 736 |
+
"completions/mean_terminated_length": 1159.0,
|
| 737 |
+
"completions/min_terminated_length": 657.0,
|
| 738 |
+
"completions/max_terminated_length": 1593.0,
|
| 739 |
+
"rewards/reward_func/mean": 0.01514,
|
| 740 |
+
"rewards/reward_func/std": 0.7299,
|
| 741 |
+
"reward": 0.01514,
|
| 742 |
+
"reward_std": 0.06986,
|
| 743 |
+
"frac_reward_zero_std": 0.0,
|
| 744 |
+
"entropy": 0.3881,
|
| 745 |
+
"clip_ratio/low_mean": 0.0,
|
| 746 |
+
"clip_ratio/low_min": 0.0,
|
| 747 |
+
"clip_ratio/high_mean": 0.0,
|
| 748 |
+
"clip_ratio/high_max": 0.0,
|
| 749 |
+
"clip_ratio/region_mean": 0.0,
|
| 750 |
+
"epoch": 1.25
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"loss": 0.05805,
|
| 754 |
+
"grad_norm": 0.3683,
|
| 755 |
+
"learning_rate": 6.667e-07,
|
| 756 |
+
"num_tokens": 311700.0,
|
| 757 |
+
"completions/mean_length": 1563.0,
|
| 758 |
+
"completions/min_length": 1331.0,
|
| 759 |
+
"completions/max_length": 1859.0,
|
| 760 |
+
"completions/clipped_ratio": 0.0,
|
| 761 |
+
"completions/mean_terminated_length": 1563.0,
|
| 762 |
+
"completions/min_terminated_length": 1331.0,
|
| 763 |
+
"completions/max_terminated_length": 1859.0,
|
| 764 |
+
"rewards/reward_func/mean": -0.6125,
|
| 765 |
+
"rewards/reward_func/std": 0.05679,
|
| 766 |
+
"reward": -0.6125,
|
| 767 |
+
"reward_std": 0.04596,
|
| 768 |
+
"frac_reward_zero_std": 0.0,
|
| 769 |
+
"entropy": 0.3005,
|
| 770 |
+
"clip_ratio/low_mean": 0.0,
|
| 771 |
+
"clip_ratio/low_min": 0.0,
|
| 772 |
+
"clip_ratio/high_mean": 0.0,
|
| 773 |
+
"clip_ratio/high_max": 0.0,
|
| 774 |
+
"clip_ratio/region_mean": 0.0,
|
| 775 |
+
"epoch": 1.292
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"loss": 0.02885,
|
| 779 |
+
"grad_norm": 0.4598,
|
| 780 |
+
"learning_rate": 6.222e-07,
|
| 781 |
+
"num_tokens": 320800.0,
|
| 782 |
+
"completions/mean_length": 974.2,
|
| 783 |
+
"completions/min_length": 619.0,
|
| 784 |
+
"completions/max_length": 1250.0,
|
| 785 |
+
"completions/clipped_ratio": 0.0,
|
| 786 |
+
"completions/mean_terminated_length": 974.2,
|
| 787 |
+
"completions/min_terminated_length": 619.0,
|
| 788 |
+
"completions/max_terminated_length": 1250.0,
|
| 789 |
+
"rewards/reward_func/mean": 0.02876,
|
| 790 |
+
"rewards/reward_func/std": 0.7899,
|
| 791 |
+
"reward": 0.02876,
|
| 792 |
+
"reward_std": 0.9635,
|
| 793 |
+
"frac_reward_zero_std": 0.0,
|
| 794 |
+
"entropy": 0.3122,
|
| 795 |
+
"clip_ratio/low_mean": 0.0,
|
| 796 |
+
"clip_ratio/low_min": 0.0,
|
| 797 |
+
"clip_ratio/high_mean": 0.0,
|
| 798 |
+
"clip_ratio/high_max": 0.0,
|
| 799 |
+
"clip_ratio/region_mean": 0.0,
|
| 800 |
+
"epoch": 1.333
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"loss": -0.01865,
|
| 804 |
+
"grad_norm": 0.2324,
|
| 805 |
+
"learning_rate": 5.778e-07,
|
| 806 |
+
"num_tokens": 331300.0,
|
| 807 |
+
"completions/mean_length": 1230.0,
|
| 808 |
+
"completions/min_length": 1118.0,
|
| 809 |
+
"completions/max_length": 1397.0,
|
| 810 |
+
"completions/clipped_ratio": 0.0,
|
| 811 |
+
"completions/mean_terminated_length": 1230.0,
|
| 812 |
+
"completions/min_terminated_length": 1118.0,
|
| 813 |
+
"completions/max_terminated_length": 1397.0,
|
| 814 |
+
"rewards/reward_func/mean": 0.1195,
|
| 815 |
+
"rewards/reward_func/std": 0.8481,
|
| 816 |
+
"reward": 0.1195,
|
| 817 |
+
"reward_std": 0.005449,
|
| 818 |
+
"frac_reward_zero_std": 0.5,
|
| 819 |
+
"entropy": 0.263,
|
| 820 |
+
"clip_ratio/low_mean": 0.0,
|
| 821 |
+
"clip_ratio/low_min": 0.0,
|
| 822 |
+
"clip_ratio/high_mean": 0.0,
|
| 823 |
+
"clip_ratio/high_max": 0.0,
|
| 824 |
+
"clip_ratio/region_mean": 0.0,
|
| 825 |
+
"epoch": 1.375
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"loss": -0.07697,
|
| 829 |
+
"grad_norm": 0.4559,
|
| 830 |
+
"learning_rate": 5.333e-07,
|
| 831 |
+
"num_tokens": 340700.0,
|
| 832 |
+
"completions/mean_length": 1084.0,
|
| 833 |
+
"completions/min_length": 898.0,
|
| 834 |
+
"completions/max_length": 1417.0,
|
| 835 |
+
"completions/clipped_ratio": 0.0,
|
| 836 |
+
"completions/mean_terminated_length": 1084.0,
|
| 837 |
+
"completions/min_terminated_length": 898.0,
|
| 838 |
+
"completions/max_terminated_length": 1417.0,
|
| 839 |
+
"rewards/reward_func/mean": 0.1057,
|
| 840 |
+
"rewards/reward_func/std": 0.8049,
|
| 841 |
+
"reward": 0.1057,
|
| 842 |
+
"reward_std": 0.9838,
|
| 843 |
+
"frac_reward_zero_std": 0.0,
|
| 844 |
+
"entropy": 0.324,
|
| 845 |
+
"clip_ratio/low_mean": 0.0,
|
| 846 |
+
"clip_ratio/low_min": 0.0,
|
| 847 |
+
"clip_ratio/high_mean": 0.0,
|
| 848 |
+
"clip_ratio/high_max": 0.0,
|
| 849 |
+
"clip_ratio/region_mean": 0.0,
|
| 850 |
+
"epoch": 1.417
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"loss": -0.01818,
|
| 854 |
+
"grad_norm": 0.4039,
|
| 855 |
+
"learning_rate": 4.889e-07,
|
| 856 |
+
"num_tokens": 351500.0,
|
| 857 |
+
"completions/mean_length": 1450.0,
|
| 858 |
+
"completions/min_length": 1056.0,
|
| 859 |
+
"completions/max_length": 1918.0,
|
| 860 |
+
"completions/clipped_ratio": 0.0,
|
| 861 |
+
"completions/mean_terminated_length": 1450.0,
|
| 862 |
+
"completions/min_terminated_length": 1056.0,
|
| 863 |
+
"completions/max_terminated_length": 1918.0,
|
| 864 |
+
"rewards/reward_func/mean": -0.6025,
|
| 865 |
+
"rewards/reward_func/std": 0.04787,
|
| 866 |
+
"reward": -0.6025,
|
| 867 |
+
"reward_std": 0.05303,
|
| 868 |
+
"frac_reward_zero_std": 0.0,
|
| 869 |
+
"entropy": 0.3122,
|
| 870 |
+
"clip_ratio/low_mean": 0.0,
|
| 871 |
+
"clip_ratio/low_min": 0.0,
|
| 872 |
+
"clip_ratio/high_mean": 0.0,
|
| 873 |
+
"clip_ratio/high_max": 0.0,
|
| 874 |
+
"clip_ratio/region_mean": 0.0,
|
| 875 |
+
"epoch": 1.458
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"loss": 0.0557,
|
| 879 |
+
"grad_norm": 0.248,
|
| 880 |
+
"learning_rate": 4.444e-07,
|
| 881 |
+
"num_tokens": 362400.0,
|
| 882 |
+
"completions/mean_length": 1425.0,
|
| 883 |
+
"completions/min_length": 1224.0,
|
| 884 |
+
"completions/max_length": 1673.0,
|
| 885 |
+
"completions/clipped_ratio": 0.0,
|
| 886 |
+
"completions/mean_terminated_length": 1425.0,
|
| 887 |
+
"completions/min_terminated_length": 1224.0,
|
| 888 |
+
"completions/max_terminated_length": 1673.0,
|
| 889 |
+
"rewards/reward_func/mean": -0.2664,
|
| 890 |
+
"rewards/reward_func/std": 0.6705,
|
| 891 |
+
"reward": -0.2664,
|
| 892 |
+
"reward_std": 0.4788,
|
| 893 |
+
"frac_reward_zero_std": 0.5,
|
| 894 |
+
"entropy": 0.2453,
|
| 895 |
+
"clip_ratio/low_mean": 0.0,
|
| 896 |
+
"clip_ratio/low_min": 0.0,
|
| 897 |
+
"clip_ratio/high_mean": 0.0,
|
| 898 |
+
"clip_ratio/high_max": 0.0,
|
| 899 |
+
"clip_ratio/region_mean": 0.0,
|
| 900 |
+
"epoch": 1.5
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"loss": 0.0222,
|
| 904 |
+
"grad_norm": 0.4008,
|
| 905 |
+
"learning_rate": 4e-07,
|
| 906 |
+
"num_tokens": 372800.0,
|
| 907 |
+
"completions/mean_length": 1271.0,
|
| 908 |
+
"completions/min_length": 911.0,
|
| 909 |
+
"completions/max_length": 1711.0,
|
| 910 |
+
"completions/clipped_ratio": 0.0,
|
| 911 |
+
"completions/mean_terminated_length": 1271.0,
|
| 912 |
+
"completions/min_terminated_length": 911.0,
|
| 913 |
+
"completions/max_terminated_length": 1711.0,
|
| 914 |
+
"rewards/reward_func/mean": -0.61,
|
| 915 |
+
"rewards/reward_func/std": 0.03317,
|
| 916 |
+
"reward": -0.61,
|
| 917 |
+
"reward_std": 0.02828,
|
| 918 |
+
"frac_reward_zero_std": 0.0,
|
| 919 |
+
"entropy": 0.3024,
|
| 920 |
+
"clip_ratio/low_mean": 0.0,
|
| 921 |
+
"clip_ratio/low_min": 0.0,
|
| 922 |
+
"clip_ratio/high_mean": 0.0,
|
| 923 |
+
"clip_ratio/high_max": 0.0,
|
| 924 |
+
"clip_ratio/region_mean": 0.0,
|
| 925 |
+
"epoch": 1.542
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"loss": -0.0843,
|
| 929 |
+
"grad_norm": 0.4839,
|
| 930 |
+
"learning_rate": 3.556e-07,
|
| 931 |
+
"num_tokens": 383200.0,
|
| 932 |
+
"completions/mean_length": 1196.0,
|
| 933 |
+
"completions/min_length": 951.0,
|
| 934 |
+
"completions/max_length": 1570.0,
|
| 935 |
+
"completions/clipped_ratio": 0.0,
|
| 936 |
+
"completions/mean_terminated_length": 1196.0,
|
| 937 |
+
"completions/min_terminated_length": 951.0,
|
| 938 |
+
"completions/max_terminated_length": 1570.0,
|
| 939 |
+
"rewards/reward_func/mean": -0.3275,
|
| 940 |
+
"rewards/reward_func/std": 0.6386,
|
| 941 |
+
"reward": -0.3275,
|
| 942 |
+
"reward_std": 0.4737,
|
| 943 |
+
"frac_reward_zero_std": 0.0,
|
| 944 |
+
"entropy": 0.454,
|
| 945 |
+
"clip_ratio/low_mean": 0.0,
|
| 946 |
+
"clip_ratio/low_min": 0.0,
|
| 947 |
+
"clip_ratio/high_mean": 0.0,
|
| 948 |
+
"clip_ratio/high_max": 0.0,
|
| 949 |
+
"clip_ratio/region_mean": 0.0,
|
| 950 |
+
"epoch": 1.583
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"loss": 0.04142,
|
| 954 |
+
"grad_norm": 0.2299,
|
| 955 |
+
"learning_rate": 3.111e-07,
|
| 956 |
+
"num_tokens": 394100.0,
|
| 957 |
+
"completions/mean_length": 1328.0,
|
| 958 |
+
"completions/min_length": 673.0,
|
| 959 |
+
"completions/max_length": 2080.0,
|
| 960 |
+
"completions/clipped_ratio": 0.0,
|
| 961 |
+
"completions/mean_terminated_length": 1328.0,
|
| 962 |
+
"completions/min_terminated_length": 673.0,
|
| 963 |
+
"completions/max_terminated_length": 2080.0,
|
| 964 |
+
"rewards/reward_func/mean": 0.0822,
|
| 965 |
+
"rewards/reward_func/std": 0.8053,
|
| 966 |
+
"reward": 0.0822,
|
| 967 |
+
"reward_std": 0.01756,
|
| 968 |
+
"frac_reward_zero_std": 0.5,
|
| 969 |
+
"entropy": 0.3963,
|
| 970 |
+
"clip_ratio/low_mean": 0.0,
|
| 971 |
+
"clip_ratio/low_min": 0.0,
|
| 972 |
+
"clip_ratio/high_mean": 0.0,
|
| 973 |
+
"clip_ratio/high_max": 0.0,
|
| 974 |
+
"clip_ratio/region_mean": 0.0,
|
| 975 |
+
"epoch": 1.625
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"loss": -0.1063,
|
| 979 |
+
"grad_norm": 0.452,
|
| 980 |
+
"learning_rate": 2.667e-07,
|
| 981 |
+
"num_tokens": 404400.0,
|
| 982 |
+
"completions/mean_length": 1202.0,
|
| 983 |
+
"completions/min_length": 598.0,
|
| 984 |
+
"completions/max_length": 1645.0,
|
| 985 |
+
"completions/clipped_ratio": 0.0,
|
| 986 |
+
"completions/mean_terminated_length": 1202.0,
|
| 987 |
+
"completions/min_terminated_length": 598.0,
|
| 988 |
+
"completions/max_terminated_length": 1645.0,
|
| 989 |
+
"rewards/reward_func/mean": -0.605,
|
| 990 |
+
"rewards/reward_func/std": 0.03367,
|
| 991 |
+
"reward": -0.605,
|
| 992 |
+
"reward_std": 0.02121,
|
| 993 |
+
"frac_reward_zero_std": 0.0,
|
| 994 |
+
"entropy": 0.379,
|
| 995 |
+
"clip_ratio/low_mean": 0.0,
|
| 996 |
+
"clip_ratio/low_min": 0.0,
|
| 997 |
+
"clip_ratio/high_mean": 0.0,
|
| 998 |
+
"clip_ratio/high_max": 0.0,
|
| 999 |
+
"clip_ratio/region_mean": 0.0,
|
| 1000 |
+
"epoch": 1.667
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"loss": 0.1229,
|
| 1004 |
+
"grad_norm": 0.3432,
|
| 1005 |
+
"learning_rate": 2.222e-07,
|
| 1006 |
+
"num_tokens": 416200.0,
|
| 1007 |
+
"completions/mean_length": 1571.0,
|
| 1008 |
+
"completions/min_length": 1118.0,
|
| 1009 |
+
"completions/max_length": 2026.0,
|
| 1010 |
+
"completions/clipped_ratio": 0.0,
|
| 1011 |
+
"completions/mean_terminated_length": 1571.0,
|
| 1012 |
+
"completions/min_terminated_length": 1118.0,
|
| 1013 |
+
"completions/max_terminated_length": 2026.0,
|
| 1014 |
+
"rewards/reward_func/mean": -0.6013,
|
| 1015 |
+
"rewards/reward_func/std": 0.04571,
|
| 1016 |
+
"reward": -0.6013,
|
| 1017 |
+
"reward_std": 0.05127,
|
| 1018 |
+
"frac_reward_zero_std": 0.0,
|
| 1019 |
+
"entropy": 0.2814,
|
| 1020 |
+
"clip_ratio/low_mean": 0.0,
|
| 1021 |
+
"clip_ratio/low_min": 0.0,
|
| 1022 |
+
"clip_ratio/high_mean": 0.0,
|
| 1023 |
+
"clip_ratio/high_max": 0.0,
|
| 1024 |
+
"clip_ratio/region_mean": 0.0,
|
| 1025 |
+
"epoch": 1.708
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"loss": 0.0183,
|
| 1029 |
+
"grad_norm": 0.5082,
|
| 1030 |
+
"learning_rate": 1.778e-07,
|
| 1031 |
+
"num_tokens": 425300.0,
|
| 1032 |
+
"completions/mean_length": 1006.0,
|
| 1033 |
+
"completions/min_length": 788.0,
|
| 1034 |
+
"completions/max_length": 1173.0,
|
| 1035 |
+
"completions/clipped_ratio": 0.0,
|
| 1036 |
+
"completions/mean_terminated_length": 1006.0,
|
| 1037 |
+
"completions/min_terminated_length": 788.0,
|
| 1038 |
+
"completions/max_terminated_length": 1173.0,
|
| 1039 |
+
"rewards/reward_func/mean": -0.2529,
|
| 1040 |
+
"rewards/reward_func/std": 0.6752,
|
| 1041 |
+
"reward": -0.2529,
|
| 1042 |
+
"reward_std": 0.4944,
|
| 1043 |
+
"frac_reward_zero_std": 0.0,
|
| 1044 |
+
"entropy": 0.3569,
|
| 1045 |
+
"clip_ratio/low_mean": 0.0,
|
| 1046 |
+
"clip_ratio/low_min": 0.0,
|
| 1047 |
+
"clip_ratio/high_mean": 0.0,
|
| 1048 |
+
"clip_ratio/high_max": 0.0,
|
| 1049 |
+
"clip_ratio/region_mean": 0.0,
|
| 1050 |
+
"epoch": 1.75
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"loss": -0.02796,
|
| 1054 |
+
"grad_norm": 0.2817,
|
| 1055 |
+
"learning_rate": 1.333e-07,
|
| 1056 |
+
"num_tokens": 435700.0,
|
| 1057 |
+
"completions/mean_length": 1292.0,
|
| 1058 |
+
"completions/min_length": 1090.0,
|
| 1059 |
+
"completions/max_length": 1433.0,
|
| 1060 |
+
"completions/clipped_ratio": 0.0,
|
| 1061 |
+
"completions/mean_terminated_length": 1292.0,
|
| 1062 |
+
"completions/min_terminated_length": 1090.0,
|
| 1063 |
+
"completions/max_terminated_length": 1433.0,
|
| 1064 |
+
"rewards/reward_func/mean": -0.6025,
|
| 1065 |
+
"rewards/reward_func/std": 0.025,
|
| 1066 |
+
"reward": -0.6025,
|
| 1067 |
+
"reward_std": 0.01768,
|
| 1068 |
+
"frac_reward_zero_std": 0.5,
|
| 1069 |
+
"entropy": 0.3352,
|
| 1070 |
+
"clip_ratio/low_mean": 0.0,
|
| 1071 |
+
"clip_ratio/low_min": 0.0,
|
| 1072 |
+
"clip_ratio/high_mean": 0.0,
|
| 1073 |
+
"clip_ratio/high_max": 0.0,
|
| 1074 |
+
"clip_ratio/region_mean": 0.0,
|
| 1075 |
+
"epoch": 1.792
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"loss": -0.02046,
|
| 1079 |
+
"grad_norm": 0.3102,
|
| 1080 |
+
"learning_rate": 8.889e-08,
|
| 1081 |
+
"num_tokens": 445600.0,
|
| 1082 |
+
"completions/mean_length": 1193.0,
|
| 1083 |
+
"completions/min_length": 906.0,
|
| 1084 |
+
"completions/max_length": 1447.0,
|
| 1085 |
+
"completions/clipped_ratio": 0.0,
|
| 1086 |
+
"completions/mean_terminated_length": 1193.0,
|
| 1087 |
+
"completions/min_terminated_length": 906.0,
|
| 1088 |
+
"completions/max_terminated_length": 1447.0,
|
| 1089 |
+
"rewards/reward_func/mean": 0.02767,
|
| 1090 |
+
"rewards/reward_func/std": 0.7421,
|
| 1091 |
+
"reward": 0.02767,
|
| 1092 |
+
"reward_std": 0.007217,
|
| 1093 |
+
"frac_reward_zero_std": 0.5,
|
| 1094 |
+
"entropy": 0.3416,
|
| 1095 |
+
"clip_ratio/low_mean": 0.0,
|
| 1096 |
+
"clip_ratio/low_min": 0.0,
|
| 1097 |
+
"clip_ratio/high_mean": 0.0,
|
| 1098 |
+
"clip_ratio/high_max": 0.0,
|
| 1099 |
+
"clip_ratio/region_mean": 0.0,
|
| 1100 |
+
"epoch": 1.833
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"loss": -0.04254,
|
| 1104 |
+
"grad_norm": 0.4965,
|
| 1105 |
+
"learning_rate": 4.444e-08,
|
| 1106 |
+
"num_tokens": 454400.0,
|
| 1107 |
+
"completions/mean_length": 917.2,
|
| 1108 |
+
"completions/min_length": 636.0,
|
| 1109 |
+
"completions/max_length": 1090.0,
|
| 1110 |
+
"completions/clipped_ratio": 0.0,
|
| 1111 |
+
"completions/mean_terminated_length": 917.2,
|
| 1112 |
+
"completions/min_terminated_length": 636.0,
|
| 1113 |
+
"completions/max_terminated_length": 1090.0,
|
| 1114 |
+
"rewards/reward_func/mean": 0.4195,
|
| 1115 |
+
"rewards/reward_func/std": 0.6919,
|
| 1116 |
+
"reward": 0.4195,
|
| 1117 |
+
"reward_std": 0.5137,
|
| 1118 |
+
"frac_reward_zero_std": 0.0,
|
| 1119 |
+
"entropy": 0.3225,
|
| 1120 |
+
"clip_ratio/low_mean": 0.0,
|
| 1121 |
+
"clip_ratio/low_min": 0.0,
|
| 1122 |
+
"clip_ratio/high_mean": 0.0,
|
| 1123 |
+
"clip_ratio/high_max": 0.0,
|
| 1124 |
+
"clip_ratio/region_mean": 0.0,
|
| 1125 |
+
"epoch": 1.875
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"train_runtime": 4269.0,
|
| 1129 |
+
"train_samples_per_second": 0.042,
|
| 1130 |
+
"train_steps_per_second": 0.011,
|
| 1131 |
+
"train_loss": -0.004462,
|
| 1132 |
+
"epoch": 1.875
|
| 1133 |
+
}
|
| 1134 |
+
]
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/optimizer_health.png
ADDED
|
Git LFS Details
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/sft_loss_curve.png
ADDED
|
Git LFS Details
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/tensorboard_scalars.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/training_curve_report.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# CADForge Training Curves
|
| 2 |
+
|
| 3 |
+
- Log: `training/logs/grpo-9b-20260426-adaptive-repair-final-8192.log`
|
| 4 |
+
- Parsed log metric rows: `46`
|
| 5 |
+
- TensorBoard scalar tags: `28`
|
| 6 |
+
- Train steps logged: `45`
|
| 7 |
+
- Eval points logged: `0`
|
| 8 |
+
- Train loss: `0.0144` -> `-0.0425`
|
| 9 |
+
- GRPO reward points: `45`
|
| 10 |
+
- GRPO mean/best reward: `-0.2128` / `0.7366`
|
| 11 |
+
- GRPO trend slope: `-0.000669` per step
|
| 12 |
+
- Completion debug rows: `180`
|
| 13 |
+
- Build rate from debug rows: `29.4%`
|
| 14 |
+
- Final fixture/import rates: `97.2%` / `100.0%`
|
| 15 |
+
|
| 16 |
+
## Charts
|
| 17 |
+
|
| 18 |
+

|
| 19 |
+

|
| 20 |
+

|
| 21 |
+

|
| 22 |
+

|
| 23 |
+

|
| 24 |
+
|
| 25 |
+
## Final Trainer Metrics
|
| 26 |
+
|
| 27 |
+
```json
|
| 28 |
+
{
|
| 29 |
+
"train_runtime": 4269.0,
|
| 30 |
+
"train_samples_per_second": 0.042,
|
| 31 |
+
"train_steps_per_second": 0.011,
|
| 32 |
+
"train_loss": -0.004462,
|
| 33 |
+
"epoch": 1.875
|
| 34 |
+
}
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## Recent Train Loss
|
| 38 |
+
|
| 39 |
+
| step | loss |
|
| 40 |
+
|---:|---:|
|
| 41 |
+
| 26 | 0.0649 |
|
| 42 |
+
| 27 | 0.0120 |
|
| 43 |
+
| 28 | 0.0000 |
|
| 44 |
+
| 29 | 0.0395 |
|
| 45 |
+
| 30 | -0.1055 |
|
| 46 |
+
| 31 | 0.0580 |
|
| 47 |
+
| 32 | 0.0289 |
|
| 48 |
+
| 33 | -0.0186 |
|
| 49 |
+
| 34 | -0.0770 |
|
| 50 |
+
| 35 | -0.0182 |
|
| 51 |
+
| 36 | 0.0557 |
|
| 52 |
+
| 37 | 0.0222 |
|
| 53 |
+
| 38 | -0.0843 |
|
| 54 |
+
| 39 | 0.0414 |
|
| 55 |
+
| 40 | -0.1063 |
|
| 56 |
+
| 41 | 0.1229 |
|
| 57 |
+
| 42 | 0.0183 |
|
| 58 |
+
| 43 | -0.0280 |
|
| 59 |
+
| 44 | -0.0205 |
|
| 60 |
+
| 45 | -0.0425 |
|
| 61 |
+
|
| 62 |
+
## GRPO Error Breakdown
|
| 63 |
+
|
| 64 |
+
| outcome | count |
|
| 65 |
+
|---|---:|
|
| 66 |
+
| `build_ok` | 53 |
|
| 67 |
+
| `NameError` | 37 |
|
| 68 |
+
| `TypeError` | 21 |
|
| 69 |
+
| `ValueError` | 21 |
|
| 70 |
+
| `AttributeError` | 18 |
|
| 71 |
+
| `SyntaxError` | 12 |
|
| 72 |
+
| `BRep_API` | 9 |
|
| 73 |
+
| `unknown` | 8 |
|
| 74 |
+
| `StdFail` | 1 |
|
training/reports/qwen35-9b-grpo-20260426-adaptive-repair-final-8192/training_timeline.png
ADDED
|