Add per-case scores and per-criterion judge verdicts
Browse files- .gitattributes +1 -0
- eval/per_case_verdicts.jsonl +3 -0
.gitattributes
CHANGED
|
@@ -45,3 +45,4 @@ designcoder_qwen3.5_9b_adamw_bs256_data41287_step200/tokenizer.json filter=lfs d
|
|
| 45 |
designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 45 |
designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
eval/per_case_verdicts.jsonl filter=lfs diff=lfs merge=lfs -text
|
eval/per_case_verdicts.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:923a5860ce66ea6413efa3030a2da3040ab8f07b02634aac3cfdf3d187d23716
|
| 3 |
+
size 18623618
|