初始化项目,由ModelHub XC社区提供模型

Model: BEE-spoke-data/smol_llama-81M-tied
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 23:47:59 +08:00
commit 6c739eadac
15 changed files with 932 additions and 0 deletions

View File

@@ -0,0 +1,150 @@
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-81M-tied,trust_remote_code=True,dtype=float), limit: None, provide_description: False, num_fewshot: 0, batch_size: 64
| Task |Version| Metric | Value | |Stderr|
|--------------|------:|--------|------:|---|-----:|
|arc_easy | 0|acc | 0.4162|± |0.0101|
| | |acc_norm| 0.3885|± |0.0100|
|boolq | 1|acc | 0.5832|± |0.0086|
|lambada_openai| 0|ppl |79.4522|± |3.1355|
| | |acc | 0.2523|± |0.0061|
|openbookqa | 0|acc | 0.1540|± |0.0162|
| | |acc_norm| 0.2780|± |0.0201|
|piqa | 0|acc | 0.6050|± |0.0114|
| | |acc_norm| 0.5898|± |0.0115|
|winogrande | 0|acc | 0.5272|± |0.0140|
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-81M-tied,trust_remote_code=True,dtype=float), limit: None, provide_description: False, num_fewshot: 25, batch_size: 64
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.1672|± |0.0109|
| | |acc_norm|0.2218|± |0.0121|
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-81M-tied,trust_remote_code=True,dtype=float), limit: None, provide_description: False, num_fewshot: 10, batch_size: 64
| Task |Version| Metric |Value | |Stderr|
|---------|------:|--------|-----:|---|-----:|
|hellaswag| 0|acc |0.2769|± |0.0045|
| | |acc_norm|0.2923|± |0.0045|
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-81M-tied,trust_remote_code=True,dtype=float), limit: None, provide_description: False, num_fewshot: 0, batch_size: 64
| Task |Version|Metric|Value | |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.2424|± |0.0150|
| | |mc2 |0.4353|± |0.0152|
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-81M-tied,trust_remote_code=True,dtype=float), limit: None, provide_description: False, num_fewshot: 5, batch_size: 64
| Task |Version| Metric |Value | |Stderr|
|-------------------------------------------------|------:|--------|-----:|---|-----:|
|hendrycksTest-abstract_algebra | 1|acc |0.2200|± |0.0416|
| | |acc_norm|0.2200|± |0.0416|
|hendrycksTest-anatomy | 1|acc |0.2741|± |0.0385|
| | |acc_norm|0.2741|± |0.0385|
|hendrycksTest-astronomy | 1|acc |0.1776|± |0.0311|
| | |acc_norm|0.1776|± |0.0311|
|hendrycksTest-business_ethics | 1|acc |0.2100|± |0.0409|
| | |acc_norm|0.2100|± |0.0409|
|hendrycksTest-clinical_knowledge | 1|acc |0.2264|± |0.0258|
| | |acc_norm|0.2264|± |0.0258|
|hendrycksTest-college_biology | 1|acc |0.2361|± |0.0355|
| | |acc_norm|0.2361|± |0.0355|
|hendrycksTest-college_chemistry | 1|acc |0.1900|± |0.0394|
| | |acc_norm|0.1900|± |0.0394|
|hendrycksTest-college_computer_science | 1|acc |0.2100|± |0.0409|
| | |acc_norm|0.2100|± |0.0409|
|hendrycksTest-college_mathematics | 1|acc |0.1800|± |0.0386|
| | |acc_norm|0.1800|± |0.0386|
|hendrycksTest-college_medicine | 1|acc |0.2023|± |0.0306|
| | |acc_norm|0.2023|± |0.0306|
|hendrycksTest-college_physics | 1|acc |0.2157|± |0.0409|
| | |acc_norm|0.2157|± |0.0409|
|hendrycksTest-computer_security | 1|acc |0.2400|± |0.0429|
| | |acc_norm|0.2400|± |0.0429|
|hendrycksTest-conceptual_physics | 1|acc |0.2596|± |0.0287|
| | |acc_norm|0.2596|± |0.0287|
|hendrycksTest-econometrics | 1|acc |0.2544|± |0.0410|
| | |acc_norm|0.2544|± |0.0410|
|hendrycksTest-electrical_engineering | 1|acc |0.2207|± |0.0346|
| | |acc_norm|0.2207|± |0.0346|
|hendrycksTest-elementary_mathematics | 1|acc |0.2169|± |0.0212|
| | |acc_norm|0.2169|± |0.0212|
|hendrycksTest-formal_logic | 1|acc |0.1587|± |0.0327|
| | |acc_norm|0.1587|± |0.0327|
|hendrycksTest-global_facts | 1|acc |0.1900|± |0.0394|
| | |acc_norm|0.1900|± |0.0394|
|hendrycksTest-high_school_biology | 1|acc |0.3000|± |0.0261|
| | |acc_norm|0.3000|± |0.0261|
|hendrycksTest-high_school_chemistry | 1|acc |0.2808|± |0.0316|
| | |acc_norm|0.2808|± |0.0316|
|hendrycksTest-high_school_computer_science | 1|acc |0.2800|± |0.0451|
| | |acc_norm|0.2800|± |0.0451|
|hendrycksTest-high_school_european_history | 1|acc |0.2424|± |0.0335|
| | |acc_norm|0.2424|± |0.0335|
|hendrycksTest-high_school_geography | 1|acc |0.2576|± |0.0312|
| | |acc_norm|0.2576|± |0.0312|
|hendrycksTest-high_school_government_and_politics| 1|acc |0.2228|± |0.0300|
| | |acc_norm|0.2228|± |0.0300|
|hendrycksTest-high_school_macroeconomics | 1|acc |0.2231|± |0.0211|
| | |acc_norm|0.2231|± |0.0211|
|hendrycksTest-high_school_mathematics | 1|acc |0.2370|± |0.0259|
| | |acc_norm|0.2370|± |0.0259|
|hendrycksTest-high_school_microeconomics | 1|acc |0.2227|± |0.0270|
| | |acc_norm|0.2227|± |0.0270|
|hendrycksTest-high_school_physics | 1|acc |0.2053|± |0.0330|
| | |acc_norm|0.2053|± |0.0330|
|hendrycksTest-high_school_psychology | 1|acc |0.2110|± |0.0175|
| | |acc_norm|0.2110|± |0.0175|
|hendrycksTest-high_school_statistics | 1|acc |0.4120|± |0.0336|
| | |acc_norm|0.4120|± |0.0336|
|hendrycksTest-high_school_us_history | 1|acc |0.2990|± |0.0321|
| | |acc_norm|0.2990|± |0.0321|
|hendrycksTest-high_school_world_history | 1|acc |0.2658|± |0.0288|
| | |acc_norm|0.2658|± |0.0288|
|hendrycksTest-human_aging | 1|acc |0.2287|± |0.0282|
| | |acc_norm|0.2287|± |0.0282|
|hendrycksTest-human_sexuality | 1|acc |0.2595|± |0.0384|
| | |acc_norm|0.2595|± |0.0384|
|hendrycksTest-international_law | 1|acc |0.2975|± |0.0417|
| | |acc_norm|0.2975|± |0.0417|
|hendrycksTest-jurisprudence | 1|acc |0.2315|± |0.0408|
| | |acc_norm|0.2315|± |0.0408|
|hendrycksTest-logical_fallacies | 1|acc |0.2822|± |0.0354|
| | |acc_norm|0.2822|± |0.0354|
|hendrycksTest-machine_learning | 1|acc |0.2321|± |0.0401|
| | |acc_norm|0.2321|± |0.0401|
|hendrycksTest-management | 1|acc |0.1748|± |0.0376|
| | |acc_norm|0.1748|± |0.0376|
|hendrycksTest-marketing | 1|acc |0.2308|± |0.0276|
| | |acc_norm|0.2308|± |0.0276|
|hendrycksTest-medical_genetics | 1|acc |0.3000|± |0.0461|
| | |acc_norm|0.3000|± |0.0461|
|hendrycksTest-miscellaneous | 1|acc |0.2375|± |0.0152|
| | |acc_norm|0.2375|± |0.0152|
|hendrycksTest-moral_disputes | 1|acc |0.2486|± |0.0233|
| | |acc_norm|0.2486|± |0.0233|
|hendrycksTest-moral_scenarios | 1|acc |0.2425|± |0.0143|
| | |acc_norm|0.2425|± |0.0143|
|hendrycksTest-nutrition | 1|acc |0.2288|± |0.0241|
| | |acc_norm|0.2288|± |0.0241|
|hendrycksTest-philosophy | 1|acc |0.2090|± |0.0231|
| | |acc_norm|0.2090|± |0.0231|
|hendrycksTest-prehistory | 1|acc |0.2377|± |0.0237|
| | |acc_norm|0.2377|± |0.0237|
|hendrycksTest-professional_accounting | 1|acc |0.2234|± |0.0248|
| | |acc_norm|0.2234|± |0.0248|
|hendrycksTest-professional_law | 1|acc |0.2471|± |0.0110|
| | |acc_norm|0.2471|± |0.0110|
|hendrycksTest-professional_medicine | 1|acc |0.4081|± |0.0299|
| | |acc_norm|0.4081|± |0.0299|
|hendrycksTest-professional_psychology | 1|acc |0.2565|± |0.0177|
| | |acc_norm|0.2565|± |0.0177|
|hendrycksTest-public_relations | 1|acc |0.2182|± |0.0396|
| | |acc_norm|0.2182|± |0.0396|
|hendrycksTest-security_studies | 1|acc |0.2408|± |0.0274|
| | |acc_norm|0.2408|± |0.0274|
|hendrycksTest-sociology | 1|acc |0.2338|± |0.0299|
| | |acc_norm|0.2338|± |0.0299|
|hendrycksTest-us_foreign_policy | 1|acc |0.2500|± |0.0435|
| | |acc_norm|0.2500|± |0.0435|
|hendrycksTest-virology | 1|acc |0.2892|± |0.0353|
| | |acc_norm|0.2892|± |0.0353|
|hendrycksTest-world_religions | 1|acc |0.2105|± |0.0313|
| | |acc_norm|0.2105|± |0.0313|

View File

@@ -0,0 +1,56 @@
{
"results": {
"arc_easy": {
"acc": 0.41624579124579125,
"acc_stderr": 0.010114819404500878,
"acc_norm": 0.38846801346801346,
"acc_norm_stderr": 0.01000127604448523
},
"boolq": {
"acc": 0.5831804281345566,
"acc_stderr": 0.00862319210884368
},
"lambada_openai": {
"ppl": 79.45218123817662,
"ppl_stderr": 3.1355336623454866,
"acc": 0.2522802251115855,
"acc_stderr": 0.006050943684570117
},
"openbookqa": {
"acc": 0.154,
"acc_stderr": 0.016158285192455334,
"acc_norm": 0.278,
"acc_norm_stderr": 0.02005583388807091
},
"piqa": {
"acc": 0.6050054406964092,
"acc_stderr": 0.011405665187969021,
"acc_norm": 0.5897714907508161,
"acc_norm_stderr": 0.011476256036359109
},
"winogrande": {
"acc": 0.5272296764009471,
"acc_stderr": 0.014031631629827708
}
},
"versions": {
"arc_easy": 0,
"boolq": 1,
"lambada_openai": 0,
"openbookqa": 0,
"piqa": 0,
"winogrande": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=BEE-spoke-data/smol_llama-81M-tied,revision=main,trust_remote_code=True,dtype='float'",
"num_fewshot": 0,
"batch_size": "16",
"batch_sizes": [],
"device": "cuda",
"no_cache": false,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}

View File

@@ -0,0 +1,25 @@
{
"results": {
"arc_challenge": {
"acc": 0.16723549488054607,
"acc_stderr": 0.01090553272460121,
"acc_norm": 0.22184300341296928,
"acc_norm_stderr": 0.012141659068147884
}
},
"versions": {
"arc_challenge": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=BEE-spoke-data/smol_llama-81M-tied,revision=main,trust_remote_code=True,dtype='float'",
"num_fewshot": 25,
"batch_size": "16",
"batch_sizes": [],
"device": "cuda",
"no_cache": false,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}

View File

@@ -0,0 +1,25 @@
{
"results": {
"hellaswag": {
"acc": 0.27450199203187253,
"acc_stderr": 0.008909237404005179,
"acc_norm": 0.28884462151394424,
"acc_norm_stderr": 0.009048238955347484
}
},
"versions": {
"hellaswag": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=BEE-spoke-data/smol_llama-81M-tied,revision=main,trust_remote_code=True,dtype='float'",
"num_fewshot": 10,
"batch_size": "16",
"batch_sizes": [],
"device": "cuda",
"no_cache": false,
"limit": 0.25,
"bootstrap_iters": 100000,
"description_dict": {}
}
}

View File

@@ -0,0 +1,25 @@
{
"results": {
"truthfulqa_mc": {
"mc1": 0.2423500611995104,
"mc1_stderr": 0.01500067437357034,
"mc2": 0.4352666140818066,
"mc2_stderr": 0.015240603531006328
}
},
"versions": {
"truthfulqa_mc": 1
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=BEE-spoke-data/smol_llama-81M-tied,revision=main,trust_remote_code=True,dtype='float'",
"num_fewshot": 0,
"batch_size": "16",
"batch_sizes": [],
"device": "cuda",
"no_cache": false,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}

View File

@@ -0,0 +1,417 @@
{
"results": {
"hendrycksTest-abstract_algebra": {
"acc": 0.16,
"acc_stderr": 0.07483314773547882,
"acc_norm": 0.16,
"acc_norm_stderr": 0.07483314773547882
},
"hendrycksTest-anatomy": {
"acc": 0.12,
"acc_stderr": 0.066332495807108,
"acc_norm": 0.12,
"acc_norm_stderr": 0.066332495807108
},
"hendrycksTest-astronomy": {
"acc": 0.28,
"acc_stderr": 0.0916515138991168,
"acc_norm": 0.28,
"acc_norm_stderr": 0.0916515138991168
},
"hendrycksTest-business_ethics": {
"acc": 0.32,
"acc_stderr": 0.09521904571390466,
"acc_norm": 0.32,
"acc_norm_stderr": 0.09521904571390466
},
"hendrycksTest-clinical_knowledge": {
"acc": 0.24,
"acc_stderr": 0.08717797887081347,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081347
},
"hendrycksTest-college_biology": {
"acc": 0.36,
"acc_stderr": 0.09797958971132711,
"acc_norm": 0.36,
"acc_norm_stderr": 0.09797958971132711
},
"hendrycksTest-college_chemistry": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-college_computer_science": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-college_mathematics": {
"acc": 0.16,
"acc_stderr": 0.0748331477354788,
"acc_norm": 0.16,
"acc_norm_stderr": 0.0748331477354788
},
"hendrycksTest-college_medicine": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-college_physics": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-computer_security": {
"acc": 0.44,
"acc_stderr": 0.10132456102380442,
"acc_norm": 0.44,
"acc_norm_stderr": 0.10132456102380442
},
"hendrycksTest-conceptual_physics": {
"acc": 0.24,
"acc_stderr": 0.08717797887081345,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081345
},
"hendrycksTest-econometrics": {
"acc": 0.28,
"acc_stderr": 0.0916515138991168,
"acc_norm": 0.28,
"acc_norm_stderr": 0.0916515138991168
},
"hendrycksTest-electrical_engineering": {
"acc": 0.24,
"acc_stderr": 0.08717797887081347,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081347
},
"hendrycksTest-elementary_mathematics": {
"acc": 0.12,
"acc_stderr": 0.066332495807108,
"acc_norm": 0.12,
"acc_norm_stderr": 0.066332495807108
},
"hendrycksTest-formal_logic": {
"acc": 0.16,
"acc_stderr": 0.07483314773547882,
"acc_norm": 0.16,
"acc_norm_stderr": 0.07483314773547882
},
"hendrycksTest-global_facts": {
"acc": 0.12,
"acc_stderr": 0.066332495807108,
"acc_norm": 0.12,
"acc_norm_stderr": 0.066332495807108
},
"hendrycksTest-high_school_biology": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-high_school_chemistry": {
"acc": 0.32,
"acc_stderr": 0.09521904571390466,
"acc_norm": 0.32,
"acc_norm_stderr": 0.09521904571390466
},
"hendrycksTest-high_school_computer_science": {
"acc": 0.24,
"acc_stderr": 0.08717797887081345,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081345
},
"hendrycksTest-high_school_european_history": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-high_school_geography": {
"acc": 0.28,
"acc_stderr": 0.09165151389911678,
"acc_norm": 0.28,
"acc_norm_stderr": 0.09165151389911678
},
"hendrycksTest-high_school_government_and_politics": {
"acc": 0.16,
"acc_stderr": 0.0748331477354788,
"acc_norm": 0.16,
"acc_norm_stderr": 0.0748331477354788
},
"hendrycksTest-high_school_macroeconomics": {
"acc": 0.32,
"acc_stderr": 0.09521904571390466,
"acc_norm": 0.32,
"acc_norm_stderr": 0.09521904571390466
},
"hendrycksTest-high_school_mathematics": {
"acc": 0.24,
"acc_stderr": 0.08717797887081345,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081345
},
"hendrycksTest-high_school_microeconomics": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-high_school_physics": {
"acc": 0.24,
"acc_stderr": 0.08717797887081345,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081345
},
"hendrycksTest-high_school_psychology": {
"acc": 0.16,
"acc_stderr": 0.07483314773547879,
"acc_norm": 0.16,
"acc_norm_stderr": 0.07483314773547879
},
"hendrycksTest-high_school_statistics": {
"acc": 0.36,
"acc_stderr": 0.09797958971132711,
"acc_norm": 0.36,
"acc_norm_stderr": 0.09797958971132711
},
"hendrycksTest-high_school_us_history": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-high_school_world_history": {
"acc": 0.36,
"acc_stderr": 0.09797958971132713,
"acc_norm": 0.36,
"acc_norm_stderr": 0.09797958971132713
},
"hendrycksTest-human_aging": {
"acc": 0.28,
"acc_stderr": 0.09165151389911678,
"acc_norm": 0.28,
"acc_norm_stderr": 0.09165151389911678
},
"hendrycksTest-human_sexuality": {
"acc": 0.2,
"acc_stderr": 0.08164965809277262,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277262
},
"hendrycksTest-international_law": {
"acc": 0.24,
"acc_stderr": 0.08717797887081345,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081345
},
"hendrycksTest-jurisprudence": {
"acc": 0.36,
"acc_stderr": 0.09797958971132711,
"acc_norm": 0.36,
"acc_norm_stderr": 0.09797958971132711
},
"hendrycksTest-logical_fallacies": {
"acc": 0.36,
"acc_stderr": 0.09797958971132711,
"acc_norm": 0.36,
"acc_norm_stderr": 0.09797958971132711
},
"hendrycksTest-machine_learning": {
"acc": 0.36,
"acc_stderr": 0.09797958971132713,
"acc_norm": 0.36,
"acc_norm_stderr": 0.09797958971132713
},
"hendrycksTest-management": {
"acc": 0.28,
"acc_stderr": 0.09165151389911677,
"acc_norm": 0.28,
"acc_norm_stderr": 0.09165151389911677
},
"hendrycksTest-marketing": {
"acc": 0.28,
"acc_stderr": 0.09165151389911678,
"acc_norm": 0.28,
"acc_norm_stderr": 0.09165151389911678
},
"hendrycksTest-medical_genetics": {
"acc": 0.36,
"acc_stderr": 0.09797958971132711,
"acc_norm": 0.36,
"acc_norm_stderr": 0.09797958971132711
},
"hendrycksTest-miscellaneous": {
"acc": 0.32,
"acc_stderr": 0.09521904571390466,
"acc_norm": 0.32,
"acc_norm_stderr": 0.09521904571390466
},
"hendrycksTest-moral_disputes": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-moral_scenarios": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-nutrition": {
"acc": 0.2,
"acc_stderr": 0.08164965809277261,
"acc_norm": 0.2,
"acc_norm_stderr": 0.08164965809277261
},
"hendrycksTest-philosophy": {
"acc": 0.24,
"acc_stderr": 0.08717797887081345,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081345
},
"hendrycksTest-prehistory": {
"acc": 0.16,
"acc_stderr": 0.07483314773547882,
"acc_norm": 0.16,
"acc_norm_stderr": 0.07483314773547882
},
"hendrycksTest-professional_accounting": {
"acc": 0.12,
"acc_stderr": 0.066332495807108,
"acc_norm": 0.12,
"acc_norm_stderr": 0.066332495807108
},
"hendrycksTest-professional_law": {
"acc": 0.24,
"acc_stderr": 0.08717797887081347,
"acc_norm": 0.24,
"acc_norm_stderr": 0.08717797887081347
},
"hendrycksTest-professional_medicine": {
"acc": 0.28,
"acc_stderr": 0.09165151389911678,
"acc_norm": 0.28,
"acc_norm_stderr": 0.09165151389911678
},
"hendrycksTest-professional_psychology": {
"acc": 0.28,
"acc_stderr": 0.09165151389911678,
"acc_norm": 0.28,
"acc_norm_stderr": 0.09165151389911678
},
"hendrycksTest-public_relations": {
"acc": 0.16,
"acc_stderr": 0.0748331477354788,
"acc_norm": 0.16,
"acc_norm_stderr": 0.0748331477354788
},
"hendrycksTest-security_studies": {
"acc": 0.28,
"acc_stderr": 0.09165151389911678,
"acc_norm": 0.28,
"acc_norm_stderr": 0.09165151389911678
},
"hendrycksTest-sociology": {
"acc": 0.32,
"acc_stderr": 0.09521904571390467,
"acc_norm": 0.32,
"acc_norm_stderr": 0.09521904571390467
},
"hendrycksTest-us_foreign_policy": {
"acc": 0.4,
"acc_stderr": 0.10000000000000002,
"acc_norm": 0.4,
"acc_norm_stderr": 0.10000000000000002
},
"hendrycksTest-virology": {
"acc": 0.28,
"acc_stderr": 0.0916515138991168,
"acc_norm": 0.28,
"acc_norm_stderr": 0.0916515138991168
},
"hendrycksTest-world_religions": {
"acc": 0.28,
"acc_stderr": 0.0916515138991168,
"acc_norm": 0.28,
"acc_norm_stderr": 0.0916515138991168
}
},
"versions": {
"hendrycksTest-abstract_algebra": 1,
"hendrycksTest-anatomy": 1,
"hendrycksTest-astronomy": 1,
"hendrycksTest-business_ethics": 1,
"hendrycksTest-clinical_knowledge": 1,
"hendrycksTest-college_biology": 1,
"hendrycksTest-college_chemistry": 1,
"hendrycksTest-college_computer_science": 1,
"hendrycksTest-college_mathematics": 1,
"hendrycksTest-college_medicine": 1,
"hendrycksTest-college_physics": 1,
"hendrycksTest-computer_security": 1,
"hendrycksTest-conceptual_physics": 1,
"hendrycksTest-econometrics": 1,
"hendrycksTest-electrical_engineering": 1,
"hendrycksTest-elementary_mathematics": 1,
"hendrycksTest-formal_logic": 1,
"hendrycksTest-global_facts": 1,
"hendrycksTest-high_school_biology": 1,
"hendrycksTest-high_school_chemistry": 1,
"hendrycksTest-high_school_computer_science": 1,
"hendrycksTest-high_school_european_history": 1,
"hendrycksTest-high_school_geography": 1,
"hendrycksTest-high_school_government_and_politics": 1,
"hendrycksTest-high_school_macroeconomics": 1,
"hendrycksTest-high_school_mathematics": 1,
"hendrycksTest-high_school_microeconomics": 1,
"hendrycksTest-high_school_physics": 1,
"hendrycksTest-high_school_psychology": 1,
"hendrycksTest-high_school_statistics": 1,
"hendrycksTest-high_school_us_history": 1,
"hendrycksTest-high_school_world_history": 1,
"hendrycksTest-human_aging": 1,
"hendrycksTest-human_sexuality": 1,
"hendrycksTest-international_law": 1,
"hendrycksTest-jurisprudence": 1,
"hendrycksTest-logical_fallacies": 1,
"hendrycksTest-machine_learning": 1,
"hendrycksTest-management": 1,
"hendrycksTest-marketing": 1,
"hendrycksTest-medical_genetics": 1,
"hendrycksTest-miscellaneous": 1,
"hendrycksTest-moral_disputes": 1,
"hendrycksTest-moral_scenarios": 1,
"hendrycksTest-nutrition": 1,
"hendrycksTest-philosophy": 1,
"hendrycksTest-prehistory": 1,
"hendrycksTest-professional_accounting": 1,
"hendrycksTest-professional_law": 1,
"hendrycksTest-professional_medicine": 1,
"hendrycksTest-professional_psychology": 1,
"hendrycksTest-public_relations": 1,
"hendrycksTest-security_studies": 1,
"hendrycksTest-sociology": 1,
"hendrycksTest-us_foreign_policy": 1,
"hendrycksTest-virology": 1,
"hendrycksTest-world_religions": 1
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=BEE-spoke-data/smol_llama-81M-tied,revision=main,trust_remote_code=True,dtype='float'",
"num_fewshot": 5,
"batch_size": "16",
"batch_sizes": [],
"device": "cuda",
"no_cache": false,
"limit": 0.25,
"bootstrap_iters": 100000,
"description_dict": {}
}
}