Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- seed_algorithms/matrix_results_Qwen3-0.6B/aime24_raw_new_api.csv +16 -0
- seed_algorithms/matrix_results_Qwen3-0.6B/aime24_trace_new_api.jsonl +3 -0
- seed_algorithms/matrix_results_Qwen3-1.7B/aime24_raw_new_api.csv +16 -0
- seed_algorithms/matrix_results_Qwen3-1.7B/aime24_trace_new_api.jsonl +3 -0
- seed_algorithms/matrix_results_Qwen3-4B/aime24_raw_new_api.csv +16 -0
- seed_algorithms/matrix_results_Qwen3-4B/aime24_trace_new_api.jsonl +3 -0
- seed_algorithms/matrix_results_Qwen3-8B/aime24_raw_new_api.csv +16 -0
- seed_algorithms/matrix_results_Qwen3-8B/aime24_trace_new_api.jsonl +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
seed_algorithms/matrix_results_Qwen3-0.6B/aime24_trace_new_api.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
seed_algorithms/matrix_results_Qwen3-1.7B/aime24_trace_new_api.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
seed_algorithms/matrix_results_Qwen3-4B/aime24_trace_new_api.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
seed_algorithms/matrix_results_Qwen3-8B/aime24_trace_new_api.jsonl filter=lfs diff=lfs merge=lfs -text
|
seed_algorithms/matrix_results_Qwen3-0.6B/aime24_raw_new_api.csv
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Method,Acc,Cost,Std_Acc,Description,config,max_samples,window_size,trace_recorder,threshold,num_chains,K,T,eps_inter,eps_intra,prune_patience,warm_up,probe_burst,max_steps
|
| 2 |
+
ESCMethod,18.33,251344,0,"esc | config={'max_samples': 16, 'window_size': 8}","{'max_samples': 16, 'window_size': 8}",16.0,8.0,<method.MethodTraceRecorder object at 0x7f996ba8b320>,,,,,,,,,,
|
| 3 |
+
ASCMethod,20.2,449812,0,"asc | config={'max_samples': 32, 'threshold': 0.95}","{'max_samples': 32, 'threshold': 0.95}",32.0,,<method.MethodTraceRecorder object at 0x7f995faa5bb0>,0.95,,,,,,,,,
|
| 4 |
+
ESCMethod,20.2,498741,0,"esc | config={'max_samples': 32, 'window_size': 8}","{'max_samples': 32, 'window_size': 8}",32.0,8.0,<method.MethodTraceRecorder object at 0x7f98984a8fb0>,,,,,,,,,,
|
| 5 |
+
ASCMethod,10.83,15879,0,"asc | config={'max_samples': 1, 'threshold': 0.95}","{'max_samples': 1, 'threshold': 0.95}",1.0,,<method.MethodTraceRecorder object at 0x7f996561af00>,0.95,,,,,,,,,
|
| 6 |
+
ASCMethod,21.4,805490,0,"asc | config={'max_samples': 64, 'threshold': 0.95}","{'max_samples': 64, 'threshold': 0.95}",64.0,,<method.MethodTraceRecorder object at 0x7f995f11d490>,0.95,,,,,,,,,
|
| 7 |
+
ASCMethod,13.63,63178,0,"asc | config={'max_samples': 4, 'threshold': 0.95}","{'max_samples': 4, 'threshold': 0.95}",4.0,,<method.MethodTraceRecorder object at 0x7f98fd69f170>,0.95,,,,,,,,,
|
| 8 |
+
Parallel_Probe,13.53,51483,0,"Parallel_Probe | config={'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f98938ff890>,,4.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 9 |
+
Parallel_Probe,10.83,15738,0,"Parallel_Probe | config={'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9845e5d280>,,1.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 10 |
+
ASCMethod,16.2,124498,0,"asc | config={'max_samples': 8, 'threshold': 0.95}","{'max_samples': 8, 'threshold': 0.95}",8.0,,<method.MethodTraceRecorder object at 0x7f9878d2b890>,0.95,,,,,,,,,
|
| 11 |
+
Parallel_Probe,16.17,100838,0,"Parallel_Probe | config={'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f98674f1610>,,8.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 12 |
+
ESCMethod,21.43,986723,0,"esc | config={'max_samples': 64, 'window_size': 8}","{'max_samples': 64, 'window_size': 8}",64.0,8.0,<method.MethodTraceRecorder object at 0x7f982b7989b0>,,,,,,,,,,
|
| 13 |
+
ASCMethod,18.33,240359,0,"asc | config={'max_samples': 16, 'threshold': 0.95}","{'max_samples': 16, 'threshold': 0.95}",16.0,,<method.MethodTraceRecorder object at 0x7f97e09965d0>,0.95,,,,,,,,,
|
| 14 |
+
Parallel_Probe,19.0,198498,0,"Parallel_Probe | config={'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a28518f80>,,16.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 15 |
+
Parallel_Probe,21.07,390779,0,"Parallel_Probe | config={'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f98026a3950>,,32.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 16 |
+
Parallel_Probe,21.83,773781,0,"Parallel_Probe | config={'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f972b776f30>,,64.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
seed_algorithms/matrix_results_Qwen3-0.6B/aime24_trace_new_api.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21e16415df0272cf90032fa14a23e323bad18409af4daa8476c61c6e51441169
|
| 3 |
+
size 2756519806
|
seed_algorithms/matrix_results_Qwen3-1.7B/aime24_raw_new_api.csv
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Method,Acc,Cost,Std_Acc,Description,config,max_samples,threshold,trace_recorder,window_size,num_chains,K,T,eps_inter,eps_intra,prune_patience,warm_up,probe_burst,max_steps
|
| 2 |
+
ASCMethod,45.5,15926,0,"asc | config={'max_samples': 1, 'threshold': 0.95}","{'max_samples': 1, 'threshold': 0.95}",1.0,0.95,<method.MethodTraceRecorder object at 0x7f9a2851b4d0>,,,,,,,,,,
|
| 3 |
+
ASCMethod,54.37,64073,0,"asc | config={'max_samples': 4, 'threshold': 0.95}","{'max_samples': 4, 'threshold': 0.95}",4.0,0.95,<method.MethodTraceRecorder object at 0x7f9a668b14f0>,,,,,,,,,,
|
| 4 |
+
ESCMethod,66.37,246575,0,"esc | config={'max_samples': 16, 'window_size': 8}","{'max_samples': 16, 'window_size': 8}",16.0,,<method.MethodTraceRecorder object at 0x7f9ab0faf320>,8.0,,,,,,,,,
|
| 5 |
+
ESCMethod,69.57,473819,0,"esc | config={'max_samples': 32, 'window_size': 8}","{'max_samples': 32, 'window_size': 8}",32.0,,<method.MethodTraceRecorder object at 0x7f9a72c77260>,8.0,,,,,,,,,
|
| 6 |
+
ESCMethod,72.47,909205,0,"esc | config={'max_samples': 64, 'window_size': 8}","{'max_samples': 64, 'window_size': 8}",64.0,,<method.MethodTraceRecorder object at 0x7f9ab02636e0>,8.0,,,,,,,,,
|
| 7 |
+
ASCMethod,62.23,118758,0,"asc | config={'max_samples': 8, 'threshold': 0.95}","{'max_samples': 8, 'threshold': 0.95}",8.0,0.95,<method.MethodTraceRecorder object at 0x7f9a8cfcfb90>,,,,,,,,,,
|
| 8 |
+
Parallel_Probe,45.5,15887,0,"Parallel_Probe | config={'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a6a0bbce0>,,1.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 9 |
+
ASCMethod,66.37,206404,0,"asc | config={'max_samples': 16, 'threshold': 0.95}","{'max_samples': 16, 'threshold': 0.95}",16.0,0.95,<method.MethodTraceRecorder object at 0x7f9a51678380>,,,,,,,,,,
|
| 10 |
+
ASCMethod,69.57,328307,0,"asc | config={'max_samples': 32, 'threshold': 0.95}","{'max_samples': 32, 'threshold': 0.95}",32.0,0.95,<method.MethodTraceRecorder object at 0x7f9a63608530>,,,,,,,,,,
|
| 11 |
+
Parallel_Probe,51.73,51042,0,"Parallel_Probe | config={'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a3703c6e0>,,4.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 12 |
+
Parallel_Probe,58.87,99219,0,"Parallel_Probe | config={'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a61c369c0>,,8.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 13 |
+
ASCMethod,72.33,482563,0,"asc | config={'max_samples': 64, 'threshold': 0.95}","{'max_samples': 64, 'threshold': 0.95}",64.0,0.95,<method.MethodTraceRecorder object at 0x7f99d4f99520>,,,,,,,,,,
|
| 14 |
+
Parallel_Probe,62.13,192957,0,"Parallel_Probe | config={'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a220d5730>,,16.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 15 |
+
Parallel_Probe,63.8,378972,0,"Parallel_Probe | config={'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a269d1d00>,,32.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 16 |
+
Parallel_Probe,66.03,745425,0,"Parallel_Probe | config={'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f990ed3c890>,,64.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
seed_algorithms/matrix_results_Qwen3-1.7B/aime24_trace_new_api.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:293a62415a0f1c94d20c813e5195d1a2c8f17e7aa6e218d81bbb02efc99ff2f8
|
| 3 |
+
size 2493057872
|
seed_algorithms/matrix_results_Qwen3-4B/aime24_raw_new_api.csv
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Method,Acc,Cost,Std_Acc,Description,config,max_samples,threshold,trace_recorder,window_size,num_chains,K,T,eps_inter,eps_intra,prune_patience,warm_up,probe_burst,max_steps
|
| 2 |
+
ASCMethod,72.23,13916,0,"asc | config={'max_samples': 1, 'threshold': 0.95}","{'max_samples': 1, 'threshold': 0.95}",1.0,0.95,<method.MethodTraceRecorder object at 0x7f98e2252690>,,,,,,,,,,
|
| 3 |
+
ASCMethod,80.0,214189,0,"asc | config={'max_samples': 64, 'threshold': 0.95}","{'max_samples': 64, 'threshold': 0.95}",64.0,0.95,<method.MethodTraceRecorder object at 0x7f997091db80>,,,,,,,,,,
|
| 4 |
+
ASCMethod,80.17,121219,0,"asc | config={'max_samples': 16, 'threshold': 0.95}","{'max_samples': 16, 'threshold': 0.95}",16.0,0.95,<method.MethodTraceRecorder object at 0x7f996e59ffb0>,,,,,,,,,,
|
| 5 |
+
ESCMethod,80.17,189027,0,"esc | config={'max_samples': 16, 'window_size': 8}","{'max_samples': 16, 'window_size': 8}",16.0,,<method.MethodTraceRecorder object at 0x7f9969dd2420>,8.0,,,,,,,,,
|
| 6 |
+
ESCMethod,80.07,319023,0,"esc | config={'max_samples': 32, 'window_size': 8}","{'max_samples': 32, 'window_size': 8}",32.0,,<method.MethodTraceRecorder object at 0x7f9a8823b350>,8.0,,,,,,,,,
|
| 7 |
+
ASCMethod,77.73,55635,0,"asc | config={'max_samples': 4, 'threshold': 0.95}","{'max_samples': 4, 'threshold': 0.95}",4.0,0.95,<method.MethodTraceRecorder object at 0x7f9962bd0230>,,,,,,,,,,
|
| 8 |
+
ESCMethod,80.0,528934,0,"esc | config={'max_samples': 64, 'window_size': 8}","{'max_samples': 64, 'window_size': 8}",64.0,,<method.MethodTraceRecorder object at 0x7f995faa5790>,8.0,,,,,,,,,
|
| 9 |
+
ASCMethod,79.97,86656,0,"asc | config={'max_samples': 8, 'threshold': 0.95}","{'max_samples': 8, 'threshold': 0.95}",8.0,0.95,<method.MethodTraceRecorder object at 0x7f98fd848680>,,,,,,,,,,
|
| 10 |
+
ASCMethod,80.07,160955,0,"asc | config={'max_samples': 32, 'threshold': 0.95}","{'max_samples': 32, 'threshold': 0.95}",32.0,0.95,<method.MethodTraceRecorder object at 0x7f98f89aaa50>,,,,,,,,,,
|
| 11 |
+
Parallel_Probe,72.23,13908,0,"Parallel_Probe | config={'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a88293c50>,,1.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 12 |
+
Parallel_Probe,78.4,89628,0,"Parallel_Probe | config={'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f987d6436e0>,,8.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 13 |
+
Parallel_Probe,76.37,46184,0,"Parallel_Probe | config={'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f98569bd2e0>,,4.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 14 |
+
Parallel_Probe,79.5,347702,0,"Parallel_Probe | config={'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9839dfbef0>,,32.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 15 |
+
Parallel_Probe,78.83,175794,0,"Parallel_Probe | config={'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f97f50ebe30>,,16.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 16 |
+
Parallel_Probe,79.73,688872,0,"Parallel_Probe | config={'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f97bec46de0>,,64.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
seed_algorithms/matrix_results_Qwen3-4B/aime24_trace_new_api.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dafc7cf38c3c4f53500c51bce57a2b0b7d9bbd844e3e366d2c2da4187ba5155a
|
| 3 |
+
size 2273575957
|
seed_algorithms/matrix_results_Qwen3-8B/aime24_raw_new_api.csv
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Method,Acc,Cost,Std_Acc,Description,config,max_samples,threshold,trace_recorder,window_size,num_chains,K,T,eps_inter,eps_intra,prune_patience,warm_up,probe_burst,max_steps
|
| 2 |
+
ASCMethod,75.57,14184,0,"asc | config={'max_samples': 1, 'threshold': 0.95}","{'max_samples': 1, 'threshold': 0.95}",1.0,0.95,<method.MethodTraceRecorder object at 0x7f9a88300f20>,,,,,,,,,,
|
| 3 |
+
ESCMethod,81.03,186408,0,"esc | config={'max_samples': 16, 'window_size': 8}","{'max_samples': 16, 'window_size': 8}",16.0,,<method.MethodTraceRecorder object at 0x7f9ab0fac440>,8.0,,,,,,,,,
|
| 4 |
+
ESCMethod,80.87,298092,0,"esc | config={'max_samples': 32, 'window_size': 8}","{'max_samples': 32, 'window_size': 8}",32.0,,<method.MethodTraceRecorder object at 0x7f9a8dc57560>,8.0,,,,,,,,,
|
| 5 |
+
ASCMethod,81.03,112808,0,"asc | config={'max_samples': 16, 'threshold': 0.95}","{'max_samples': 16, 'threshold': 0.95}",16.0,0.95,<method.MethodTraceRecorder object at 0x7f9a7fe066f0>,,,,,,,,,,
|
| 6 |
+
ASCMethod,80.1,56846,0,"asc | config={'max_samples': 4, 'threshold': 0.95}","{'max_samples': 4, 'threshold': 0.95}",4.0,0.95,<method.MethodTraceRecorder object at 0x7f9a7fe066c0>,,,,,,,,,,
|
| 7 |
+
ASCMethod,81.2,83623,0,"asc | config={'max_samples': 8, 'threshold': 0.95}","{'max_samples': 8, 'threshold': 0.95}",8.0,0.95,<method.MethodTraceRecorder object at 0x7f9a751e6060>,,,,,,,,,,
|
| 8 |
+
ESCMethod,80.37,459359,0,"esc | config={'max_samples': 64, 'window_size': 8}","{'max_samples': 64, 'window_size': 8}",64.0,,<method.MethodTraceRecorder object at 0x7f9a72688320>,8.0,,,,,,,,,
|
| 9 |
+
ASCMethod,80.87,157088,0,"asc | config={'max_samples': 32, 'threshold': 0.95}","{'max_samples': 32, 'threshold': 0.95}",32.0,0.95,<method.MethodTraceRecorder object at 0x7f9a707b3440>,,,,,,,,,,
|
| 10 |
+
ASCMethod,80.37,226033,0,"asc | config={'max_samples': 64, 'threshold': 0.95}","{'max_samples': 64, 'threshold': 0.95}",64.0,0.95,<method.MethodTraceRecorder object at 0x7f9a6a58d790>,,,,,,,,,,
|
| 11 |
+
Parallel_Probe,75.23,14160,0,"Parallel_Probe | config={'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 1, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a668b3b00>,,1.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 12 |
+
Parallel_Probe,78.17,47812,0,"Parallel_Probe | config={'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 4, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a47bfd3d0>,,4.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 13 |
+
Parallel_Probe,79.47,93702,0,"Parallel_Probe | config={'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 8, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a2b4bea20>,,8.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 14 |
+
Parallel_Probe,80.33,184988,0,"Parallel_Probe | config={'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 16, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9a05bc7020>,,16.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 15 |
+
Parallel_Probe,80.87,367491,0,"Parallel_Probe | config={'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 32, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f99cfafea80>,,32.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
| 16 |
+
Parallel_Probe,81.47,730781,0,"Parallel_Probe | config={'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}","{'num_chains': 64, 'K': 5, 'T': 40, 'eps_inter': 5.0, 'eps_intra': 5.0, 'prune_patience': 7, 'warm_up': 15, 'probe_burst': 1, 'max_steps': 100}",,,<method.MethodTraceRecorder object at 0x7f9979e6b170>,,64.0,5.0,40.0,5.0,5.0,7.0,15.0,1.0,100.0
|
seed_algorithms/matrix_results_Qwen3-8B/aime24_trace_new_api.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66aca306dfae7844a73fa8d26a1886e21227b4a023eeb158d3123f13118c6041
|
| 3 |
+
size 2368069068
|