Upload folder using huggingface_hub (part 37)

.gitattributes

@@ -37,3 +37,4 @@ opencompass/outputs/default/20260405_025820/results/DLLM_TEST/lukaemon_mmlu_prof
 opencompass/outputs/default/20260409_233842/results/SDLM_7B_D8_epoch1/hellaswag.json filter=lfs diff=lfs merge=lfs -text
 opencompass/outputs/default/20260409_233842/results/SDLM_7B_D8_epoch1/lukaemon_mmlu_professional_law.json filter=lfs diff=lfs merge=lfs -text
 opencompass/outputs/default/20260409_234853/results/SDLM_7B_D8_epoch1/hellaswag.json filter=lfs diff=lfs merge=lfs -text
+opencompass/outputs/default/20260409_234853/results/SDLM_7B_D8_epoch1/lukaemon_mmlu_professional_law.json filter=lfs diff=lfs merge=lfs -text

opencompass/outputs/default/20260409_234853/results/SDLM_7B_D8_epoch1/lukaemon_mmlu_professional_law.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6faa37f7d82ceed8faf1213ab97764f0a3a88b3643456ac674d96e3096fd94
+size 15690088

opencompass/outputs/default/20260409_234853/summary/summary_20260409_234853.csv

@@ -0,0 +1,62 @@
+dataset,version,metric,mode,SDLM_7B_D8_epoch1
+ARC-e,1e0de5,accuracy,gen,95.94
+ARC-c,1e0de5,accuracy,gen,89.15
+hellaswag,e42710,accuracy,gen,81.12
+winogrande,458220,accuracy,gen,62.35
+lukaemon_mmlu_college_biology,caec7d,accuracy,gen,84.03
+lukaemon_mmlu_college_chemistry,520aa6,accuracy,gen,54.00
+lukaemon_mmlu_college_computer_science,99c216,accuracy,gen,70.00
+lukaemon_mmlu_college_mathematics,678751,accuracy,gen,46.00
+lukaemon_mmlu_college_physics,4f382c,accuracy,gen,50.98
+lukaemon_mmlu_electrical_engineering,770ce3,accuracy,gen,69.66
+lukaemon_mmlu_astronomy,d3ee01,accuracy,gen,81.58
+lukaemon_mmlu_anatomy,72183b,accuracy,gen,66.67
+lukaemon_mmlu_abstract_algebra,2db373,accuracy,gen,44.00
+lukaemon_mmlu_machine_learning,0283bb,accuracy,gen,48.21
+lukaemon_mmlu_clinical_knowledge,cb3218,accuracy,gen,77.74
+lukaemon_mmlu_global_facts,ab07b6,accuracy,gen,42.00
+lukaemon_mmlu_management,80876d,accuracy,gen,86.41
+lukaemon_mmlu_nutrition,4543bd,accuracy,gen,79.74
+lukaemon_mmlu_marketing,7394e3,accuracy,gen,89.74
+lukaemon_mmlu_professional_accounting,444b7f,accuracy,gen,53.90
+lukaemon_mmlu_high_school_geography,0780e6,accuracy,gen,87.88
+lukaemon_mmlu_international_law,cf3179,accuracy,gen,84.30
+lukaemon_mmlu_moral_scenarios,f6dbe2,accuracy,gen,35.31
+lukaemon_mmlu_computer_security,ce7550,accuracy,gen,81.00
+lukaemon_mmlu_high_school_microeconomics,04d21a,accuracy,gen,89.50
+lukaemon_mmlu_professional_law,5f7e6c,accuracy,gen,48.57
+lukaemon_mmlu_medical_genetics,881ef5,accuracy,gen,81.00
+lukaemon_mmlu_professional_psychology,221a16,accuracy,gen,72.06
+lukaemon_mmlu_jurisprudence,001f24,accuracy,gen,80.56
+lukaemon_mmlu_world_religions,232c09,accuracy,gen,83.63
+lukaemon_mmlu_philosophy,08042b,accuracy,gen,74.28
+lukaemon_mmlu_virology,12e270,accuracy,gen,51.20
+lukaemon_mmlu_high_school_chemistry,ae8820,accuracy,gen,55.67
+lukaemon_mmlu_public_relations,e7d39b,accuracy,gen,70.91
+lukaemon_mmlu_high_school_macroeconomics,a01685,accuracy,gen,74.87
+lukaemon_mmlu_human_sexuality,42407c,accuracy,gen,80.92
+lukaemon_mmlu_elementary_mathematics,269926,accuracy,gen,64.81
+lukaemon_mmlu_high_school_physics,93278f,accuracy,gen,50.33
+lukaemon_mmlu_high_school_computer_science,9965a5,accuracy,gen,81.00
+lukaemon_mmlu_high_school_european_history,eefc90,accuracy,gen,82.42
+lukaemon_mmlu_business_ethics,1dec08,accuracy,gen,80.00
+lukaemon_mmlu_moral_disputes,a2173e,accuracy,gen,74.57
+lukaemon_mmlu_high_school_statistics,8f3f3a,accuracy,gen,70.37
+lukaemon_mmlu_miscellaneous,935647,accuracy,gen,82.38
+lukaemon_mmlu_formal_logic,cfcb0c,accuracy,gen,55.56
+lukaemon_mmlu_high_school_government_and_politics,3c52f9,accuracy,gen,91.71
+lukaemon_mmlu_prehistory,bbb197,accuracy,gen,74.38
+lukaemon_mmlu_security_studies,9b1743,accuracy,gen,76.73
+lukaemon_mmlu_high_school_biology,37b125,accuracy,gen,85.81
+lukaemon_mmlu_logical_fallacies,9cebb0,accuracy,gen,80.37
+lukaemon_mmlu_high_school_world_history,048e7e,accuracy,gen,82.28
+lukaemon_mmlu_professional_medicine,857144,accuracy,gen,77.57
+lukaemon_mmlu_high_school_mathematics,ed4dc0,accuracy,gen,45.19
+lukaemon_mmlu_college_medicine,38709e,accuracy,gen,65.90
+lukaemon_mmlu_high_school_us_history,8932df,accuracy,gen,83.82
+lukaemon_mmlu_sociology,c266a2,accuracy,gen,87.06
+lukaemon_mmlu_econometrics,d1134d,accuracy,gen,54.39
+lukaemon_mmlu_high_school_psychology,7db114,accuracy,gen,89.17
+lukaemon_mmlu_human_aging,82a410,accuracy,gen,71.75
+lukaemon_mmlu_us_foreign_policy,528cfe,accuracy,gen,86.00
+lukaemon_mmlu_conceptual_physics,63588e,accuracy,gen,70.21

opencompass/outputs/default/20260409_234853/summary/summary_20260409_234853.md

@@ -0,0 +1,63 @@
+| dataset | version | metric | mode | SDLM_7B_D8_epoch1 |
+|----- | ----- | ----- | ----- | -----|
+| ARC-e | 1e0de5 | accuracy | gen | 95.94 |
+| ARC-c | 1e0de5 | accuracy | gen | 89.15 |
+| hellaswag | e42710 | accuracy | gen | 81.12 |
+| winogrande | 458220 | accuracy | gen | 62.35 |
+| lukaemon_mmlu_college_biology | caec7d | accuracy | gen | 84.03 |
+| lukaemon_mmlu_college_chemistry | 520aa6 | accuracy | gen | 54.00 |
+| lukaemon_mmlu_college_computer_science | 99c216 | accuracy | gen | 70.00 |
+| lukaemon_mmlu_college_mathematics | 678751 | accuracy | gen | 46.00 |
+| lukaemon_mmlu_college_physics | 4f382c | accuracy | gen | 50.98 |
+| lukaemon_mmlu_electrical_engineering | 770ce3 | accuracy | gen | 69.66 |
+| lukaemon_mmlu_astronomy | d3ee01 | accuracy | gen | 81.58 |
+| lukaemon_mmlu_anatomy | 72183b | accuracy | gen | 66.67 |
+| lukaemon_mmlu_abstract_algebra | 2db373 | accuracy | gen | 44.00 |
+| lukaemon_mmlu_machine_learning | 0283bb | accuracy | gen | 48.21 |
+| lukaemon_mmlu_clinical_knowledge | cb3218 | accuracy | gen | 77.74 |
+| lukaemon_mmlu_global_facts | ab07b6 | accuracy | gen | 42.00 |
+| lukaemon_mmlu_management | 80876d | accuracy | gen | 86.41 |
+| lukaemon_mmlu_nutrition | 4543bd | accuracy | gen | 79.74 |
+| lukaemon_mmlu_marketing | 7394e3 | accuracy | gen | 89.74 |
+| lukaemon_mmlu_professional_accounting | 444b7f | accuracy | gen | 53.90 |
+| lukaemon_mmlu_high_school_geography | 0780e6 | accuracy | gen | 87.88 |
+| lukaemon_mmlu_international_law | cf3179 | accuracy | gen | 84.30 |
+| lukaemon_mmlu_moral_scenarios | f6dbe2 | accuracy | gen | 35.31 |
+| lukaemon_mmlu_computer_security | ce7550 | accuracy | gen | 81.00 |
+| lukaemon_mmlu_high_school_microeconomics | 04d21a | accuracy | gen | 89.50 |
+| lukaemon_mmlu_professional_law | 5f7e6c | accuracy | gen | 48.57 |
+| lukaemon_mmlu_medical_genetics | 881ef5 | accuracy | gen | 81.00 |
+| lukaemon_mmlu_professional_psychology | 221a16 | accuracy | gen | 72.06 |
+| lukaemon_mmlu_jurisprudence | 001f24 | accuracy | gen | 80.56 |
+| lukaemon_mmlu_world_religions | 232c09 | accuracy | gen | 83.63 |
+| lukaemon_mmlu_philosophy | 08042b | accuracy | gen | 74.28 |
+| lukaemon_mmlu_virology | 12e270 | accuracy | gen | 51.20 |
+| lukaemon_mmlu_high_school_chemistry | ae8820 | accuracy | gen | 55.67 |
+| lukaemon_mmlu_public_relations | e7d39b | accuracy | gen | 70.91 |
+| lukaemon_mmlu_high_school_macroeconomics | a01685 | accuracy | gen | 74.87 |
+| lukaemon_mmlu_human_sexuality | 42407c | accuracy | gen | 80.92 |
+| lukaemon_mmlu_elementary_mathematics | 269926 | accuracy | gen | 64.81 |
+| lukaemon_mmlu_high_school_physics | 93278f | accuracy | gen | 50.33 |
+| lukaemon_mmlu_high_school_computer_science | 9965a5 | accuracy | gen | 81.00 |
+| lukaemon_mmlu_high_school_european_history | eefc90 | accuracy | gen | 82.42 |
+| lukaemon_mmlu_business_ethics | 1dec08 | accuracy | gen | 80.00 |
+| lukaemon_mmlu_moral_disputes | a2173e | accuracy | gen | 74.57 |
+| lukaemon_mmlu_high_school_statistics | 8f3f3a | accuracy | gen | 70.37 |
+| lukaemon_mmlu_miscellaneous | 935647 | accuracy | gen | 82.38 |
+| lukaemon_mmlu_formal_logic | cfcb0c | accuracy | gen | 55.56 |
+| lukaemon_mmlu_high_school_government_and_politics | 3c52f9 | accuracy | gen | 91.71 |
+| lukaemon_mmlu_prehistory | bbb197 | accuracy | gen | 74.38 |
+| lukaemon_mmlu_security_studies | 9b1743 | accuracy | gen | 76.73 |
+| lukaemon_mmlu_high_school_biology | 37b125 | accuracy | gen | 85.81 |
+| lukaemon_mmlu_logical_fallacies | 9cebb0 | accuracy | gen | 80.37 |
+| lukaemon_mmlu_high_school_world_history | 048e7e | accuracy | gen | 82.28 |
+| lukaemon_mmlu_professional_medicine | 857144 | accuracy | gen | 77.57 |
+| lukaemon_mmlu_high_school_mathematics | ed4dc0 | accuracy | gen | 45.19 |
+| lukaemon_mmlu_college_medicine | 38709e | accuracy | gen | 65.90 |
+| lukaemon_mmlu_high_school_us_history | 8932df | accuracy | gen | 83.82 |
+| lukaemon_mmlu_sociology | c266a2 | accuracy | gen | 87.06 |
+| lukaemon_mmlu_econometrics | d1134d | accuracy | gen | 54.39 |
+| lukaemon_mmlu_high_school_psychology | 7db114 | accuracy | gen | 89.17 |
+| lukaemon_mmlu_human_aging | 82a410 | accuracy | gen | 71.75 |
+| lukaemon_mmlu_us_foreign_policy | 528cfe | accuracy | gen | 86.00 |
+| lukaemon_mmlu_conceptual_physics | 63588e | accuracy | gen | 70.21 |

opencompass/outputs/default/20260409_234853/summary/summary_20260409_234853.txt

@@ -0,0 +1,271 @@
+20260409_234853
+tabulate format
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+dataset                                            version    metric    mode      SDLM_7B_D8_epoch1
+-------------------------------------------------  ---------  --------  ------  -------------------
+ARC-e                                              1e0de5     accuracy  gen                   95.94
+ARC-c                                              1e0de5     accuracy  gen                   89.15
+hellaswag                                          e42710     accuracy  gen                   81.12
+winogrande                                         458220     accuracy  gen                   62.35
+lukaemon_mmlu_college_biology                      caec7d     accuracy  gen                   84.03
+lukaemon_mmlu_college_chemistry                    520aa6     accuracy  gen                   54.00
+lukaemon_mmlu_college_computer_science             99c216     accuracy  gen                   70.00
+lukaemon_mmlu_college_mathematics                  678751     accuracy  gen                   46.00
+lukaemon_mmlu_college_physics                      4f382c     accuracy  gen                   50.98
+lukaemon_mmlu_electrical_engineering               770ce3     accuracy  gen                   69.66
+lukaemon_mmlu_astronomy                            d3ee01     accuracy  gen                   81.58
+lukaemon_mmlu_anatomy                              72183b     accuracy  gen                   66.67
+lukaemon_mmlu_abstract_algebra                     2db373     accuracy  gen                   44.00
+lukaemon_mmlu_machine_learning                     0283bb     accuracy  gen                   48.21
+lukaemon_mmlu_clinical_knowledge                   cb3218     accuracy  gen                   77.74
+lukaemon_mmlu_global_facts                         ab07b6     accuracy  gen                   42.00
+lukaemon_mmlu_management                           80876d     accuracy  gen                   86.41
+lukaemon_mmlu_nutrition                            4543bd     accuracy  gen                   79.74
+lukaemon_mmlu_marketing                            7394e3     accuracy  gen                   89.74
+lukaemon_mmlu_professional_accounting              444b7f     accuracy  gen                   53.90
+lukaemon_mmlu_high_school_geography                0780e6     accuracy  gen                   87.88
+lukaemon_mmlu_international_law                    cf3179     accuracy  gen                   84.30
+lukaemon_mmlu_moral_scenarios                      f6dbe2     accuracy  gen                   35.31
+lukaemon_mmlu_computer_security                    ce7550     accuracy  gen                   81.00
+lukaemon_mmlu_high_school_microeconomics           04d21a     accuracy  gen                   89.50
+lukaemon_mmlu_professional_law                     5f7e6c     accuracy  gen                   48.57
+lukaemon_mmlu_medical_genetics                     881ef5     accuracy  gen                   81.00
+lukaemon_mmlu_professional_psychology              221a16     accuracy  gen                   72.06
+lukaemon_mmlu_jurisprudence                        001f24     accuracy  gen                   80.56
+lukaemon_mmlu_world_religions                      232c09     accuracy  gen                   83.63
+lukaemon_mmlu_philosophy                           08042b     accuracy  gen                   74.28
+lukaemon_mmlu_virology                             12e270     accuracy  gen                   51.20
+lukaemon_mmlu_high_school_chemistry                ae8820     accuracy  gen                   55.67
+lukaemon_mmlu_public_relations                     e7d39b     accuracy  gen                   70.91
+lukaemon_mmlu_high_school_macroeconomics           a01685     accuracy  gen                   74.87
+lukaemon_mmlu_human_sexuality                      42407c     accuracy  gen                   80.92
+lukaemon_mmlu_elementary_mathematics               269926     accuracy  gen                   64.81
+lukaemon_mmlu_high_school_physics                  93278f     accuracy  gen                   50.33
+lukaemon_mmlu_high_school_computer_science         9965a5     accuracy  gen                   81.00
+lukaemon_mmlu_high_school_european_history         eefc90     accuracy  gen                   82.42
+lukaemon_mmlu_business_ethics                      1dec08     accuracy  gen                   80.00
+lukaemon_mmlu_moral_disputes                       a2173e     accuracy  gen                   74.57
+lukaemon_mmlu_high_school_statistics               8f3f3a     accuracy  gen                   70.37
+lukaemon_mmlu_miscellaneous                        935647     accuracy  gen                   82.38
+lukaemon_mmlu_formal_logic                         cfcb0c     accuracy  gen                   55.56
+lukaemon_mmlu_high_school_government_and_politics  3c52f9     accuracy  gen                   91.71
+lukaemon_mmlu_prehistory                           bbb197     accuracy  gen                   74.38
+lukaemon_mmlu_security_studies                     9b1743     accuracy  gen                   76.73
+lukaemon_mmlu_high_school_biology                  37b125     accuracy  gen                   85.81
+lukaemon_mmlu_logical_fallacies                    9cebb0     accuracy  gen                   80.37
+lukaemon_mmlu_high_school_world_history            048e7e     accuracy  gen                   82.28
+lukaemon_mmlu_professional_medicine                857144     accuracy  gen                   77.57
+lukaemon_mmlu_high_school_mathematics              ed4dc0     accuracy  gen                   45.19
+lukaemon_mmlu_college_medicine                     38709e     accuracy  gen                   65.90
+lukaemon_mmlu_high_school_us_history               8932df     accuracy  gen                   83.82
+lukaemon_mmlu_sociology                            c266a2     accuracy  gen                   87.06
+lukaemon_mmlu_econometrics                         d1134d     accuracy  gen                   54.39
+lukaemon_mmlu_high_school_psychology               7db114     accuracy  gen                   89.17
+lukaemon_mmlu_human_aging                          82a410     accuracy  gen                   71.75
+lukaemon_mmlu_us_foreign_policy                    528cfe     accuracy  gen                   86.00
+lukaemon_mmlu_conceptual_physics                   63588e     accuracy  gen                   70.21
+$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
+
+-------------------------------------------------------------------------------------------------------------------------------- THIS IS A DIVIDER --------------------------------------------------------------------------------------------------------------------------------
+
+csv format
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+dataset,version,metric,mode,SDLM_7B_D8_epoch1
+ARC-e,1e0de5,accuracy,gen,95.94
+ARC-c,1e0de5,accuracy,gen,89.15
+hellaswag,e42710,accuracy,gen,81.12
+winogrande,458220,accuracy,gen,62.35
+lukaemon_mmlu_college_biology,caec7d,accuracy,gen,84.03
+lukaemon_mmlu_college_chemistry,520aa6,accuracy,gen,54.00
+lukaemon_mmlu_college_computer_science,99c216,accuracy,gen,70.00
+lukaemon_mmlu_college_mathematics,678751,accuracy,gen,46.00
+lukaemon_mmlu_college_physics,4f382c,accuracy,gen,50.98
+lukaemon_mmlu_electrical_engineering,770ce3,accuracy,gen,69.66
+lukaemon_mmlu_astronomy,d3ee01,accuracy,gen,81.58
+lukaemon_mmlu_anatomy,72183b,accuracy,gen,66.67
+lukaemon_mmlu_abstract_algebra,2db373,accuracy,gen,44.00
+lukaemon_mmlu_machine_learning,0283bb,accuracy,gen,48.21
+lukaemon_mmlu_clinical_knowledge,cb3218,accuracy,gen,77.74
+lukaemon_mmlu_global_facts,ab07b6,accuracy,gen,42.00
+lukaemon_mmlu_management,80876d,accuracy,gen,86.41
+lukaemon_mmlu_nutrition,4543bd,accuracy,gen,79.74
+lukaemon_mmlu_marketing,7394e3,accuracy,gen,89.74
+lukaemon_mmlu_professional_accounting,444b7f,accuracy,gen,53.90
+lukaemon_mmlu_high_school_geography,0780e6,accuracy,gen,87.88
+lukaemon_mmlu_international_law,cf3179,accuracy,gen,84.30
+lukaemon_mmlu_moral_scenarios,f6dbe2,accuracy,gen,35.31
+lukaemon_mmlu_computer_security,ce7550,accuracy,gen,81.00
+lukaemon_mmlu_high_school_microeconomics,04d21a,accuracy,gen,89.50
+lukaemon_mmlu_professional_law,5f7e6c,accuracy,gen,48.57
+lukaemon_mmlu_medical_genetics,881ef5,accuracy,gen,81.00
+lukaemon_mmlu_professional_psychology,221a16,accuracy,gen,72.06
+lukaemon_mmlu_jurisprudence,001f24,accuracy,gen,80.56
+lukaemon_mmlu_world_religions,232c09,accuracy,gen,83.63
+lukaemon_mmlu_philosophy,08042b,accuracy,gen,74.28
+lukaemon_mmlu_virology,12e270,accuracy,gen,51.20
+lukaemon_mmlu_high_school_chemistry,ae8820,accuracy,gen,55.67
+lukaemon_mmlu_public_relations,e7d39b,accuracy,gen,70.91
+lukaemon_mmlu_high_school_macroeconomics,a01685,accuracy,gen,74.87
+lukaemon_mmlu_human_sexuality,42407c,accuracy,gen,80.92
+lukaemon_mmlu_elementary_mathematics,269926,accuracy,gen,64.81
+lukaemon_mmlu_high_school_physics,93278f,accuracy,gen,50.33
+lukaemon_mmlu_high_school_computer_science,9965a5,accuracy,gen,81.00
+lukaemon_mmlu_high_school_european_history,eefc90,accuracy,gen,82.42
+lukaemon_mmlu_business_ethics,1dec08,accuracy,gen,80.00
+lukaemon_mmlu_moral_disputes,a2173e,accuracy,gen,74.57
+lukaemon_mmlu_high_school_statistics,8f3f3a,accuracy,gen,70.37
+lukaemon_mmlu_miscellaneous,935647,accuracy,gen,82.38
+lukaemon_mmlu_formal_logic,cfcb0c,accuracy,gen,55.56
+lukaemon_mmlu_high_school_government_and_politics,3c52f9,accuracy,gen,91.71
+lukaemon_mmlu_prehistory,bbb197,accuracy,gen,74.38
+lukaemon_mmlu_security_studies,9b1743,accuracy,gen,76.73
+lukaemon_mmlu_high_school_biology,37b125,accuracy,gen,85.81
+lukaemon_mmlu_logical_fallacies,9cebb0,accuracy,gen,80.37
+lukaemon_mmlu_high_school_world_history,048e7e,accuracy,gen,82.28
+lukaemon_mmlu_professional_medicine,857144,accuracy,gen,77.57
+lukaemon_mmlu_high_school_mathematics,ed4dc0,accuracy,gen,45.19
+lukaemon_mmlu_college_medicine,38709e,accuracy,gen,65.90
+lukaemon_mmlu_high_school_us_history,8932df,accuracy,gen,83.82
+lukaemon_mmlu_sociology,c266a2,accuracy,gen,87.06
+lukaemon_mmlu_econometrics,d1134d,accuracy,gen,54.39
+lukaemon_mmlu_high_school_psychology,7db114,accuracy,gen,89.17
+lukaemon_mmlu_human_aging,82a410,accuracy,gen,71.75
+lukaemon_mmlu_us_foreign_policy,528cfe,accuracy,gen,86.00
+lukaemon_mmlu_conceptual_physics,63588e,accuracy,gen,70.21
+$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
+
+markdown format
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+| dataset | version | metric | mode | SDLM_7B_D8_epoch1 |
+|----- | ----- | ----- | ----- | -----|
+| ARC-e | 1e0de5 | accuracy | gen | 95.94 |
+| ARC-c | 1e0de5 | accuracy | gen | 89.15 |
+| hellaswag | e42710 | accuracy | gen | 81.12 |
+| winogrande | 458220 | accuracy | gen | 62.35 |
+| lukaemon_mmlu_college_biology | caec7d | accuracy | gen | 84.03 |
+| lukaemon_mmlu_college_chemistry | 520aa6 | accuracy | gen | 54.00 |
+| lukaemon_mmlu_college_computer_science | 99c216 | accuracy | gen | 70.00 |
+| lukaemon_mmlu_college_mathematics | 678751 | accuracy | gen | 46.00 |
+| lukaemon_mmlu_college_physics | 4f382c | accuracy | gen | 50.98 |
+| lukaemon_mmlu_electrical_engineering | 770ce3 | accuracy | gen | 69.66 |
+| lukaemon_mmlu_astronomy | d3ee01 | accuracy | gen | 81.58 |
+| lukaemon_mmlu_anatomy | 72183b | accuracy | gen | 66.67 |
+| lukaemon_mmlu_abstract_algebra | 2db373 | accuracy | gen | 44.00 |
+| lukaemon_mmlu_machine_learning | 0283bb | accuracy | gen | 48.21 |
+| lukaemon_mmlu_clinical_knowledge | cb3218 | accuracy | gen | 77.74 |
+| lukaemon_mmlu_global_facts | ab07b6 | accuracy | gen | 42.00 |
+| lukaemon_mmlu_management | 80876d | accuracy | gen | 86.41 |
+| lukaemon_mmlu_nutrition | 4543bd | accuracy | gen | 79.74 |
+| lukaemon_mmlu_marketing | 7394e3 | accuracy | gen | 89.74 |
+| lukaemon_mmlu_professional_accounting | 444b7f | accuracy | gen | 53.90 |
+| lukaemon_mmlu_high_school_geography | 0780e6 | accuracy | gen | 87.88 |
+| lukaemon_mmlu_international_law | cf3179 | accuracy | gen | 84.30 |
+| lukaemon_mmlu_moral_scenarios | f6dbe2 | accuracy | gen | 35.31 |
+| lukaemon_mmlu_computer_security | ce7550 | accuracy | gen | 81.00 |
+| lukaemon_mmlu_high_school_microeconomics | 04d21a | accuracy | gen | 89.50 |
+| lukaemon_mmlu_professional_law | 5f7e6c | accuracy | gen | 48.57 |
+| lukaemon_mmlu_medical_genetics | 881ef5 | accuracy | gen | 81.00 |
+| lukaemon_mmlu_professional_psychology | 221a16 | accuracy | gen | 72.06 |
+| lukaemon_mmlu_jurisprudence | 001f24 | accuracy | gen | 80.56 |
+| lukaemon_mmlu_world_religions | 232c09 | accuracy | gen | 83.63 |
+| lukaemon_mmlu_philosophy | 08042b | accuracy | gen | 74.28 |
+| lukaemon_mmlu_virology | 12e270 | accuracy | gen | 51.20 |
+| lukaemon_mmlu_high_school_chemistry | ae8820 | accuracy | gen | 55.67 |
+| lukaemon_mmlu_public_relations | e7d39b | accuracy | gen | 70.91 |
+| lukaemon_mmlu_high_school_macroeconomics | a01685 | accuracy | gen | 74.87 |
+| lukaemon_mmlu_human_sexuality | 42407c | accuracy | gen | 80.92 |
+| lukaemon_mmlu_elementary_mathematics | 269926 | accuracy | gen | 64.81 |
+| lukaemon_mmlu_high_school_physics | 93278f | accuracy | gen | 50.33 |
+| lukaemon_mmlu_high_school_computer_science | 9965a5 | accuracy | gen | 81.00 |
+| lukaemon_mmlu_high_school_european_history | eefc90 | accuracy | gen | 82.42 |
+| lukaemon_mmlu_business_ethics | 1dec08 | accuracy | gen | 80.00 |
+| lukaemon_mmlu_moral_disputes | a2173e | accuracy | gen | 74.57 |
+| lukaemon_mmlu_high_school_statistics | 8f3f3a | accuracy | gen | 70.37 |
+| lukaemon_mmlu_miscellaneous | 935647 | accuracy | gen | 82.38 |
+| lukaemon_mmlu_formal_logic | cfcb0c | accuracy | gen | 55.56 |
+| lukaemon_mmlu_high_school_government_and_politics | 3c52f9 | accuracy | gen | 91.71 |
+| lukaemon_mmlu_prehistory | bbb197 | accuracy | gen | 74.38 |
+| lukaemon_mmlu_security_studies | 9b1743 | accuracy | gen | 76.73 |
+| lukaemon_mmlu_high_school_biology | 37b125 | accuracy | gen | 85.81 |
+| lukaemon_mmlu_logical_fallacies | 9cebb0 | accuracy | gen | 80.37 |
+| lukaemon_mmlu_high_school_world_history | 048e7e | accuracy | gen | 82.28 |
+| lukaemon_mmlu_professional_medicine | 857144 | accuracy | gen | 77.57 |
+| lukaemon_mmlu_high_school_mathematics | ed4dc0 | accuracy | gen | 45.19 |
+| lukaemon_mmlu_college_medicine | 38709e | accuracy | gen | 65.90 |
+| lukaemon_mmlu_high_school_us_history | 8932df | accuracy | gen | 83.82 |
+| lukaemon_mmlu_sociology | c266a2 | accuracy | gen | 87.06 |
+| lukaemon_mmlu_econometrics | d1134d | accuracy | gen | 54.39 |
+| lukaemon_mmlu_high_school_psychology | 7db114 | accuracy | gen | 89.17 |
+| lukaemon_mmlu_human_aging | 82a410 | accuracy | gen | 71.75 |
+| lukaemon_mmlu_us_foreign_policy | 528cfe | accuracy | gen | 86.00 |
+| lukaemon_mmlu_conceptual_physics | 63588e | accuracy | gen | 70.21 |
+
+$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
+-------------------------------------------------------------------------------------------------------------------------------- THIS IS A DIVIDER --------------------------------------------------------------------------------------------------------------------------------
+
+raw format
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+-------------------------------
+Model: SDLM_7B_D8_epoch1
+ARC-e: {'accuracy': 95.94356261022926}
+ARC-c: {'accuracy': 89.15254237288136}
+hellaswag: {'accuracy': 81.11929894443338}
+winogrande: {'accuracy': 62.35201262825573}
+lukaemon_mmlu_college_biology: {'accuracy': 84.02777777777779}
+lukaemon_mmlu_college_chemistry: {'accuracy': 54.0}
+lukaemon_mmlu_college_computer_science: {'accuracy': 70.0}
+lukaemon_mmlu_college_mathematics: {'accuracy': 46.0}
+lukaemon_mmlu_college_physics: {'accuracy': 50.98039215686274}
+lukaemon_mmlu_electrical_engineering: {'accuracy': 69.6551724137931}
+lukaemon_mmlu_astronomy: {'accuracy': 81.57894736842105}
+lukaemon_mmlu_anatomy: {'accuracy': 66.66666666666666}
+lukaemon_mmlu_abstract_algebra: {'accuracy': 44.0}
+lukaemon_mmlu_machine_learning: {'accuracy': 48.214285714285715}
+lukaemon_mmlu_clinical_knowledge: {'accuracy': 77.73584905660378}
+lukaemon_mmlu_global_facts: {'accuracy': 42.0}
+lukaemon_mmlu_management: {'accuracy': 86.40776699029125}
+lukaemon_mmlu_nutrition: {'accuracy': 79.73856209150327}
+lukaemon_mmlu_marketing: {'accuracy': 89.74358974358975}
+lukaemon_mmlu_professional_accounting: {'accuracy': 53.90070921985816}
+lukaemon_mmlu_high_school_geography: {'accuracy': 87.87878787878788}
+lukaemon_mmlu_international_law: {'accuracy': 84.29752066115702}
+lukaemon_mmlu_moral_scenarios: {'accuracy': 35.3072625698324}
+lukaemon_mmlu_computer_security: {'accuracy': 81.0}
+lukaemon_mmlu_high_school_microeconomics: {'accuracy': 89.49579831932773}
+lukaemon_mmlu_professional_law: {'accuracy': 48.565840938722296}
+lukaemon_mmlu_medical_genetics: {'accuracy': 81.0}
+lukaemon_mmlu_professional_psychology: {'accuracy': 72.05882352941177}
+lukaemon_mmlu_jurisprudence: {'accuracy': 80.55555555555556}
+lukaemon_mmlu_world_religions: {'accuracy': 83.62573099415205}
+lukaemon_mmlu_philosophy: {'accuracy': 74.27652733118971}
+lukaemon_mmlu_virology: {'accuracy': 51.204819277108435}
+lukaemon_mmlu_high_school_chemistry: {'accuracy': 55.66502463054187}
+lukaemon_mmlu_public_relations: {'accuracy': 70.9090909090909}
+lukaemon_mmlu_high_school_macroeconomics: {'accuracy': 74.87179487179488}
+lukaemon_mmlu_human_sexuality: {'accuracy': 80.91603053435115}
+lukaemon_mmlu_elementary_mathematics: {'accuracy': 64.81481481481481}
+lukaemon_mmlu_high_school_physics: {'accuracy': 50.331125827814574}
+lukaemon_mmlu_high_school_computer_science: {'accuracy': 81.0}
+lukaemon_mmlu_high_school_european_history: {'accuracy': 82.42424242424242}
+lukaemon_mmlu_business_ethics: {'accuracy': 80.0}
+lukaemon_mmlu_moral_disputes: {'accuracy': 74.56647398843931}
+lukaemon_mmlu_high_school_statistics: {'accuracy': 70.37037037037037}
+lukaemon_mmlu_miscellaneous: {'accuracy': 82.37547892720306}
+lukaemon_mmlu_formal_logic: {'accuracy': 55.55555555555556}
+lukaemon_mmlu_high_school_government_and_politics: {'accuracy': 91.70984455958549}
+lukaemon_mmlu_prehistory: {'accuracy': 74.38271604938271}
+lukaemon_mmlu_security_studies: {'accuracy': 76.73469387755102}
+lukaemon_mmlu_high_school_biology: {'accuracy': 85.80645161290322}
+lukaemon_mmlu_logical_fallacies: {'accuracy': 80.3680981595092}
+lukaemon_mmlu_high_school_world_history: {'accuracy': 82.27848101265823}
+lukaemon_mmlu_professional_medicine: {'accuracy': 77.57352941176471}
+lukaemon_mmlu_high_school_mathematics: {'accuracy': 45.18518518518518}
+lukaemon_mmlu_college_medicine: {'accuracy': 65.89595375722543}
+lukaemon_mmlu_high_school_us_history: {'accuracy': 83.82352941176471}
+lukaemon_mmlu_sociology: {'accuracy': 87.06467661691542}
+lukaemon_mmlu_econometrics: {'accuracy': 54.385964912280706}
+lukaemon_mmlu_high_school_psychology: {'accuracy': 89.17431192660551}
+lukaemon_mmlu_human_aging: {'accuracy': 71.74887892376681}
+lukaemon_mmlu_us_foreign_policy: {'accuracy': 86.0}
+lukaemon_mmlu_conceptual_physics: {'accuracy': 70.2127659574468}
+$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/ARC-c.out

@@ -0,0 +1,5 @@
+04/10 00:40:00 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/ARC/ARC-c/ARC-Challenge-Dev.jsonl
+
+04/10 00:40:00 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:00 - OpenCompass - INFO - Details is not give by evaluator, try to format it
+04/10 00:40:00 - OpenCompass - INFO - time elapsed:  6.48s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/ARC-e.out

@@ -0,0 +1,5 @@
+04/10 00:39:58 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/ARC/ARC-e/ARC-Easy-Dev.jsonl
+
+04/10 00:39:58 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:39:58 - OpenCompass - INFO - Details is not give by evaluator, try to format it
+04/10 00:39:58 - OpenCompass - INFO - time elapsed:  4.91s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/hellaswag.out

@@ -0,0 +1,5 @@
+04/10 00:40:02 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/hellaswag/
+
+
+04/10 00:40:04 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:06 - OpenCompass - INFO - time elapsed:  11.54s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_abstract_algebra.out

@@ -0,0 +1,5 @@
+04/10 00:40:18 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:18 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:18 - OpenCompass - INFO - time elapsed:  5.30s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_anatomy.out

@@ -0,0 +1,5 @@
+04/10 00:40:15 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:16 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:16 - OpenCompass - INFO - time elapsed:  4.88s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_astronomy.out

@@ -0,0 +1,5 @@
+04/10 00:40:14 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:14 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:14 - OpenCompass - INFO - time elapsed:  4.58s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_business_ethics.out

@@ -0,0 +1,5 @@
+04/10 00:40:59 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:59 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:59 - OpenCompass - INFO - time elapsed:  4.41s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_clinical_knowledge.out

@@ -0,0 +1,5 @@
+04/10 00:40:18 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:18 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:18 - OpenCompass - INFO - time elapsed:  5.92s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_college_biology.out

@@ -0,0 +1,5 @@
+04/10 00:40:02 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:02 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:02 - OpenCompass - INFO - time elapsed:  6.84s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_college_chemistry.out

@@ -0,0 +1,5 @@
+04/10 00:40:02 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:02 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:02 - OpenCompass - INFO - time elapsed:  7.22s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_college_computer_science.out

@@ -0,0 +1,5 @@
+04/10 00:40:02 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:02 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:02 - OpenCompass - INFO - time elapsed:  6.48s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_college_mathematics.out

@@ -0,0 +1,5 @@
+04/10 00:40:02 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:40:02 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:40:02 - OpenCompass - INFO - time elapsed:  6.78s

opencompass/outputs/default/20260409_235934/logs/eval/SDLM-32B-D4/lukaemon_mmlu_college_medicine.out

@@ -0,0 +1,5 @@
+04/10 00:41:26 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/mmlu/
+
+
+04/10 00:41:27 - OpenCompass - INFO - Running 0-th replica of evaluation
+04/10 00:41:27 - OpenCompass - INFO - time elapsed:  5.90s