初始化项目,由ModelHub XC社区提供模型
Model: CCCCCyx/Qwen3-8B-onpolicy-profiling-muon-20260413_090005 Source: Original Platform
This commit is contained in:
126
eval_20260417051759/run.log
Normal file
126
eval_20260417051759/run.log
Normal file
File diff suppressed because one or more lines are too long
5920
eval_20260417051759/step01_prepared.jsonl
Normal file
5920
eval_20260417051759/step01_prepared.jsonl
Normal file
File diff suppressed because one or more lines are too long
3
eval_20260417051759/step02_inference.jsonl
Normal file
3
eval_20260417051759/step02_inference.jsonl
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:200c902df4711938796ab4c556f54c5ecb7786116db9d1649cdfdd50c84611df
|
||||
size 195217496
|
||||
8
eval_20260417051759/step03_final_eval.csv
Normal file
8
eval_20260417051759/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,0.5774111675126904,0.766497461928934,10612.370558375635,0.0,0.0,0.0
|
||||
hmmt2025,0.31666666666666665,0.43333333333333335,18237.566666666666,0.0,0.0,0.0
|
||||
aime2024,0.6802083333333333,0.9,14426.277083333332,0.0,0.0,0.0
|
||||
aime2025,0.571875,0.8666666666666667,15452.192708333334,0.0,0.0,0.0
|
||||
math500,0.7485,0.768,4490.75,0.0,0.0,0.0
|
||||
minerva,0.3290441176470588,0.38235294117647056,6507.237132352941,0.0,0.0,0.0
|
||||
overall,0.6000676132521975,0.6657223796033994,9346.815584854632,0.0,0.0,0.0
|
||||
|
7
eval_20260417051759/step03_final_eval.jsonl
Normal file
7
eval_20260417051759/step03_final_eval.jsonl
Normal file
@@ -0,0 +1,7 @@
|
||||
["gpqa_diamond", {"avg_k": 0.5774111675126904, "pass_k": 0.766497461928934, "avg_total_tokens": 10612.370558375635, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["hmmt2025", {"avg_k": 0.31666666666666665, "pass_k": 0.43333333333333335, "avg_total_tokens": 18237.566666666666, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["aime2024", {"avg_k": 0.6802083333333333, "pass_k": 0.9, "avg_total_tokens": 14426.277083333332, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["aime2025", {"avg_k": 0.571875, "pass_k": 0.8666666666666667, "avg_total_tokens": 15452.192708333334, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["math500", {"avg_k": 0.7485, "pass_k": 0.768, "avg_total_tokens": 4490.75, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["minerva", {"avg_k": 0.3290441176470588, "pass_k": 0.38235294117647056, "avg_total_tokens": 6507.237132352941, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
["overall", {"avg_k": 0.6000676132521975, "pass_k": 0.6657223796033994, "avg_total_tokens": 9346.815584854632, "avg_thinking_tokens": 0.0, "max_thinking_tokens": 0.0, "min_thinking_tokens": 0.0}]
|
||||
3
eval_20260417051759/step03_score.jsonl
Normal file
3
eval_20260417051759/step03_score.jsonl
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a2ebd0b8de479e12a3ed38e15698f72752a40d5cc7b82ed321f045e7688ed8a
|
||||
size 195525922
|
||||
Reference in New Issue
Block a user