Upload 81m_tied.md
Browse files
smol_llama-81M-tied-evals/81m_tied.md
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 3 |
+
|--------------|------:|--------|------:|---|-----:|
|
| 4 |
+
|arc_easy | 0|acc | 0.4162|± |0.0101|
|
| 5 |
+
| | |acc_norm| 0.3885|± |0.0100|
|
| 6 |
+
|boolq | 1|acc | 0.5832|± |0.0086|
|
| 7 |
+
|lambada_openai| 0|ppl |79.4522|± |3.1355|
|
| 8 |
+
| | |acc | 0.2523|± |0.0061|
|
| 9 |
+
|openbookqa | 0|acc | 0.1540|± |0.0162|
|
| 10 |
+
| | |acc_norm| 0.2780|± |0.0201|
|
| 11 |
+
|piqa | 0|acc | 0.6050|± |0.0114|
|
| 12 |
+
| | |acc_norm| 0.5898|± |0.0115|
|
| 13 |
+
|winogrande | 0|acc | 0.5272|± |0.0140|
|
| 14 |
+
|
| 15 |
+
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
|
| 16 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 17 |
+
|-------------|------:|--------|-----:|---|-----:|
|
| 18 |
+
|arc_challenge| 0|acc |0.1672|± |0.0109|
|
| 19 |
+
| | |acc_norm|0.2218|± |0.0121|
|
| 20 |
+
|
| 21 |
+
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
|
| 22 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 23 |
+
|---------|------:|--------|-----:|---|-----:|
|
| 24 |
+
|hellaswag| 0|acc |0.2769|± |0.0045|
|
| 25 |
+
| | |acc_norm|0.2923|± |0.0045|
|
| 26 |
+
|
| 27 |
+
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
|
| 28 |
+
| Task |Version|Metric|Value | |Stderr|
|
| 29 |
+
|-------------|------:|------|-----:|---|-----:|
|
| 30 |
+
|truthfulqa_mc| 1|mc1 |0.2424|± |0.0150|
|
| 31 |
+
| | |mc2 |0.4353|± |0.0152|
|
| 32 |
+
|
| 33 |
+
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
|
| 34 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 35 |
+
|-------------------------------------------------|------:|--------|-----:|---|-----:|
|
| 36 |
+
|hendrycksTest-abstract_algebra | 1|acc |0.2200|± |0.0416|
|
| 37 |
+
| | |acc_norm|0.2200|± |0.0416|
|
| 38 |
+
|hendrycksTest-anatomy | 1|acc |0.2741|± |0.0385|
|
| 39 |
+
| | |acc_norm|0.2741|± |0.0385|
|
| 40 |
+
|hendrycksTest-astronomy | 1|acc |0.1776|± |0.0311|
|
| 41 |
+
| | |acc_norm|0.1776|± |0.0311|
|
| 42 |
+
|hendrycksTest-business_ethics | 1|acc |0.2100|± |0.0409|
|
| 43 |
+
| | |acc_norm|0.2100|± |0.0409|
|
| 44 |
+
|hendrycksTest-clinical_knowledge | 1|acc |0.2264|± |0.0258|
|
| 45 |
+
| | |acc_norm|0.2264|± |0.0258|
|
| 46 |
+
|hendrycksTest-college_biology | 1|acc |0.2361|± |0.0355|
|
| 47 |
+
| | |acc_norm|0.2361|± |0.0355|
|
| 48 |
+
|hendrycksTest-college_chemistry | 1|acc |0.1900|± |0.0394|
|
| 49 |
+
| | |acc_norm|0.1900|± |0.0394|
|
| 50 |
+
|hendrycksTest-college_computer_science | 1|acc |0.2100|± |0.0409|
|
| 51 |
+
| | |acc_norm|0.2100|± |0.0409|
|
| 52 |
+
|hendrycksTest-college_mathematics | 1|acc |0.1800|± |0.0386|
|
| 53 |
+
| | |acc_norm|0.1800|± |0.0386|
|
| 54 |
+
|hendrycksTest-college_medicine | 1|acc |0.2023|± |0.0306|
|
| 55 |
+
| | |acc_norm|0.2023|± |0.0306|
|
| 56 |
+
|hendrycksTest-college_physics | 1|acc |0.2157|± |0.0409|
|
| 57 |
+
| | |acc_norm|0.2157|± |0.0409|
|
| 58 |
+
|hendrycksTest-computer_security | 1|acc |0.2400|± |0.0429|
|
| 59 |
+
| | |acc_norm|0.2400|± |0.0429|
|
| 60 |
+
|hendrycksTest-conceptual_physics | 1|acc |0.2596|± |0.0287|
|
| 61 |
+
| | |acc_norm|0.2596|± |0.0287|
|
| 62 |
+
|hendrycksTest-econometrics | 1|acc |0.2544|± |0.0410|
|
| 63 |
+
| | |acc_norm|0.2544|± |0.0410|
|
| 64 |
+
|hendrycksTest-electrical_engineering | 1|acc |0.2207|± |0.0346|
|
| 65 |
+
| | |acc_norm|0.2207|± |0.0346|
|
| 66 |
+
|hendrycksTest-elementary_mathematics | 1|acc |0.2169|± |0.0212|
|
| 67 |
+
| | |acc_norm|0.2169|± |0.0212|
|
| 68 |
+
|hendrycksTest-formal_logic | 1|acc |0.1587|± |0.0327|
|
| 69 |
+
| | |acc_norm|0.1587|± |0.0327|
|
| 70 |
+
|hendrycksTest-global_facts | 1|acc |0.1900|± |0.0394|
|
| 71 |
+
| | |acc_norm|0.1900|± |0.0394|
|
| 72 |
+
|hendrycksTest-high_school_biology | 1|acc |0.3000|± |0.0261|
|
| 73 |
+
| | |acc_norm|0.3000|± |0.0261|
|
| 74 |
+
|hendrycksTest-high_school_chemistry | 1|acc |0.2808|± |0.0316|
|
| 75 |
+
| | |acc_norm|0.2808|± |0.0316|
|
| 76 |
+
|hendrycksTest-high_school_computer_science | 1|acc |0.2800|± |0.0451|
|
| 77 |
+
| | |acc_norm|0.2800|± |0.0451|
|
| 78 |
+
|hendrycksTest-high_school_european_history | 1|acc |0.2424|± |0.0335|
|
| 79 |
+
| | |acc_norm|0.2424|± |0.0335|
|
| 80 |
+
|hendrycksTest-high_school_geography | 1|acc |0.2576|± |0.0312|
|
| 81 |
+
| | |acc_norm|0.2576|± |0.0312|
|
| 82 |
+
|hendrycksTest-high_school_government_and_politics| 1|acc |0.2228|± |0.0300|
|
| 83 |
+
| | |acc_norm|0.2228|± |0.0300|
|
| 84 |
+
|hendrycksTest-high_school_macroeconomics | 1|acc |0.2231|± |0.0211|
|
| 85 |
+
| | |acc_norm|0.2231|± |0.0211|
|
| 86 |
+
|hendrycksTest-high_school_mathematics | 1|acc |0.2370|± |0.0259|
|
| 87 |
+
| | |acc_norm|0.2370|± |0.0259|
|
| 88 |
+
|hendrycksTest-high_school_microeconomics | 1|acc |0.2227|± |0.0270|
|
| 89 |
+
| | |acc_norm|0.2227|± |0.0270|
|
| 90 |
+
|hendrycksTest-high_school_physics | 1|acc |0.2053|± |0.0330|
|
| 91 |
+
| | |acc_norm|0.2053|± |0.0330|
|
| 92 |
+
|hendrycksTest-high_school_psychology | 1|acc |0.2110|± |0.0175|
|
| 93 |
+
| | |acc_norm|0.2110|± |0.0175|
|
| 94 |
+
|hendrycksTest-high_school_statistics | 1|acc |0.4120|± |0.0336|
|
| 95 |
+
| | |acc_norm|0.4120|± |0.0336|
|
| 96 |
+
|hendrycksTest-high_school_us_history | 1|acc |0.2990|± |0.0321|
|
| 97 |
+
| | |acc_norm|0.2990|± |0.0321|
|
| 98 |
+
|hendrycksTest-high_school_world_history | 1|acc |0.2658|± |0.0288|
|
| 99 |
+
| | |acc_norm|0.2658|± |0.0288|
|
| 100 |
+
|hendrycksTest-human_aging | 1|acc |0.2287|± |0.0282|
|
| 101 |
+
| | |acc_norm|0.2287|± |0.0282|
|
| 102 |
+
|hendrycksTest-human_sexuality | 1|acc |0.2595|± |0.0384|
|
| 103 |
+
| | |acc_norm|0.2595|± |0.0384|
|
| 104 |
+
|hendrycksTest-international_law | 1|acc |0.2975|± |0.0417|
|
| 105 |
+
| | |acc_norm|0.2975|± |0.0417|
|
| 106 |
+
|hendrycksTest-jurisprudence | 1|acc |0.2315|± |0.0408|
|
| 107 |
+
| | |acc_norm|0.2315|± |0.0408|
|
| 108 |
+
|hendrycksTest-logical_fallacies | 1|acc |0.2822|± |0.0354|
|
| 109 |
+
| | |acc_norm|0.2822|± |0.0354|
|
| 110 |
+
|hendrycksTest-machine_learning | 1|acc |0.2321|± |0.0401|
|
| 111 |
+
| | |acc_norm|0.2321|± |0.0401|
|
| 112 |
+
|hendrycksTest-management | 1|acc |0.1748|± |0.0376|
|
| 113 |
+
| | |acc_norm|0.1748|± |0.0376|
|
| 114 |
+
|hendrycksTest-marketing | 1|acc |0.2308|± |0.0276|
|
| 115 |
+
| | |acc_norm|0.2308|± |0.0276|
|
| 116 |
+
|hendrycksTest-medical_genetics | 1|acc |0.3000|± |0.0461|
|
| 117 |
+
| | |acc_norm|0.3000|± |0.0461|
|
| 118 |
+
|hendrycksTest-miscellaneous | 1|acc |0.2375|± |0.0152|
|
| 119 |
+
| | |acc_norm|0.2375|± |0.0152|
|
| 120 |
+
|hendrycksTest-moral_disputes | 1|acc |0.2486|± |0.0233|
|
| 121 |
+
| | |acc_norm|0.2486|± |0.0233|
|
| 122 |
+
|hendrycksTest-moral_scenarios | 1|acc |0.2425|± |0.0143|
|
| 123 |
+
| | |acc_norm|0.2425|± |0.0143|
|
| 124 |
+
|hendrycksTest-nutrition | 1|acc |0.2288|± |0.0241|
|
| 125 |
+
| | |acc_norm|0.2288|± |0.0241|
|
| 126 |
+
|hendrycksTest-philosophy | 1|acc |0.2090|± |0.0231|
|
| 127 |
+
| | |acc_norm|0.2090|± |0.0231|
|
| 128 |
+
|hendrycksTest-prehistory | 1|acc |0.2377|± |0.0237|
|
| 129 |
+
| | |acc_norm|0.2377|± |0.0237|
|
| 130 |
+
|hendrycksTest-professional_accounting | 1|acc |0.2234|± |0.0248|
|
| 131 |
+
| | |acc_norm|0.2234|± |0.0248|
|
| 132 |
+
|hendrycksTest-professional_law | 1|acc |0.2471|± |0.0110|
|
| 133 |
+
| | |acc_norm|0.2471|± |0.0110|
|
| 134 |
+
|hendrycksTest-professional_medicine | 1|acc |0.4081|± |0.0299|
|
| 135 |
+
| | |acc_norm|0.4081|± |0.0299|
|
| 136 |
+
|hendrycksTest-professional_psychology | 1|acc |0.2565|± |0.0177|
|
| 137 |
+
| | |acc_norm|0.2565|± |0.0177|
|
| 138 |
+
|hendrycksTest-public_relations | 1|acc |0.2182|± |0.0396|
|
| 139 |
+
| | |acc_norm|0.2182|± |0.0396|
|
| 140 |
+
|hendrycksTest-security_studies | 1|acc |0.2408|± |0.0274|
|
| 141 |
+
| | |acc_norm|0.2408|± |0.0274|
|
| 142 |
+
|hendrycksTest-sociology | 1|acc |0.2338|± |0.0299|
|
| 143 |
+
| | |acc_norm|0.2338|± |0.0299|
|
| 144 |
+
|hendrycksTest-us_foreign_policy | 1|acc |0.2500|± |0.0435|
|
| 145 |
+
| | |acc_norm|0.2500|± |0.0435|
|
| 146 |
+
|hendrycksTest-virology | 1|acc |0.2892|± |0.0353|
|
| 147 |
+
| | |acc_norm|0.2892|± |0.0353|
|
| 148 |
+
|hendrycksTest-world_religions | 1|acc |0.2105|± |0.0313|
|
| 149 |
+
| | |acc_norm|0.2105|± |0.0313|
|
| 150 |
+
|