初始化项目,由ModelHub XC社区提供模型
Model: CCCCCyx/Qwen3-8B-onpolicy-profiling-adam-20260403_091551 Source: Original Platform
This commit is contained in:
130
eval_20260409163705/run.log
Normal file
130
eval_20260409163705/run.log
Normal file
File diff suppressed because one or more lines are too long
5920
eval_20260409163705/step01_prepared.jsonl
Normal file
5920
eval_20260409163705/step01_prepared.jsonl
Normal file
File diff suppressed because one or more lines are too long
3
eval_20260409163705/step02_inference.jsonl
Normal file
3
eval_20260409163705/step02_inference.jsonl
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ad2ad97e480fdfa38338db00be6e44654d6ee7f6ec8702a1fb0a4b08ee7d4f20
|
||||
size 201991383
|
||||
8
eval_20260409163705/step03_final_eval.csv
Normal file
8
eval_20260409163705/step03_final_eval.csv
Normal file
@@ -0,0 +1,8 @@
|
||||
task,avg_k,pass_k,avg_total_tokens,avg_thinking_tokens,max_thinking_tokens,min_thinking_tokens
|
||||
gpqa_diamond,0.5812182741116751,0.7614213197969543,10732.243654822336,0.0,0.0,0.0
|
||||
hmmt2025,0.375,0.5333333333333333,18450.008333333335,0.0,0.0,0.0
|
||||
aime2024,0.7020833333333333,0.9333333333333333,13840.913541666667,0.0,0.0,0.0
|
||||
aime2025,0.6010416666666667,0.8666666666666667,15299.15,0.0,0.0,0.0
|
||||
math500,0.952,0.98,4403.267,0.0,0.0,0.0
|
||||
minerva,0.484375,0.5661764705882353,6378.409007352941,0.0,0.0,0.0
|
||||
overall,0.7074036511156186,0.8158640226628895,9194.001521298174,0.0,0.0,0.0
|
||||
|
7
eval_20260409163705/step03_final_eval.jsonl
Normal file
7
eval_20260409163705/step03_final_eval.jsonl
Normal file
@@ -0,0 +1,7 @@
|
||||
["gpqa_diamond", {"avg_k": 0.5812182741116751, "pass_k": 0.7614213197969543, "avg_total_tokens": 10732.243654822336, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["hmmt2025", {"avg_k": 0.375, "pass_k": 0.5333333333333333, "avg_total_tokens": 18450.008333333335, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["aime2024", {"avg_k": 0.7020833333333333, "pass_k": 0.9333333333333333, "avg_total_tokens": 13840.913541666667, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["aime2025", {"avg_k": 0.6010416666666667, "pass_k": 0.8666666666666667, "avg_total_tokens": 15299.15, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["math500", {"avg_k": 0.952, "pass_k": 0.98, "avg_total_tokens": 4403.267, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["minerva", {"avg_k": 0.484375, "pass_k": 0.5661764705882353, "avg_total_tokens": 6378.409007352941, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["overall", {"avg_k": 0.7074036511156186, "pass_k": 0.8158640226628895, "avg_total_tokens": 9194.001521298174, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
3
eval_20260409163705/step03_score.jsonl
Normal file
3
eval_20260409163705/step03_score.jsonl
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:734ac805270ff0a99656a56be393e71e2e426bc2f14292bdd4097871cc50228d
|
||||
size 202297629
|
||||
Reference in New Issue
Block a user