Upload 101m-gqa.md
Browse files
smol_llama-101M-GQA-evals/101m-gqa.md
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-101M-GQA,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 | 0.4322|± |0.0102|
|
| 5 |
+
| | |acc_norm| 0.3868|± |0.0100|
|
| 6 |
+
|boolq | 1|acc | 0.6092|± |0.0085|
|
| 7 |
+
|lambada_openai| 0|ppl |74.2399|± |2.9038|
|
| 8 |
+
| | |acc | 0.2604|± |0.0061|
|
| 9 |
+
|openbookqa | 0|acc | 0.1440|± |0.0157|
|
| 10 |
+
| | |acc_norm| 0.2780|± |0.0201|
|
| 11 |
+
|piqa | 0|acc | 0.5909|± |0.0115|
|
| 12 |
+
| | |acc_norm| 0.5871|± |0.0115|
|
| 13 |
+
|winogrande | 0|acc | 0.5225|± |0.0140|
|
| 14 |
+
|
| 15 |
+
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-101M-GQA,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 |0.1817|± |0.0113|
|
| 19 |
+
| | |acc_norm|0.2329|± |0.0124|
|
| 20 |
+
|
| 21 |
+
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-101M-GQA,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 |0.2792|± |0.0045|
|
| 25 |
+
| | |acc_norm|0.2865|± |0.0045|
|
| 26 |
+
|
| 27 |
+
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-101M-GQA,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 |0.2485|± |0.0151|
|
| 31 |
+
| | |mc2 |0.4594|± |0.0151|
|
| 32 |
+
|
| 33 |
+
hf-causal-experimental (pretrained=BEE-spoke-data/smol_llama-101M-GQA,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 |0.2500|± |0.0362|
|
| 47 |
+
| | |acc_norm|0.2500|± |0.0362|
|
| 48 |
+
|hendrycksTest-college_chemistry | 1|acc |0.1500|± |0.0359|
|
| 49 |
+
| | |acc_norm|0.1500|± |0.0359|
|
| 50 |
+
|hendrycksTest-college_computer_science | 1|acc |0.1600|± |0.0368|
|
| 51 |
+
| | |acc_norm|0.1600|± |0.0368|
|
| 52 |
+
|hendrycksTest-college_mathematics | 1|acc |0.3000|± |0.0461|
|
| 53 |
+
| | |acc_norm|0.3000|± |0.0461|
|
| 54 |
+
|hendrycksTest-college_medicine | 1|acc |0.1908|± |0.0300|
|
| 55 |
+
| | |acc_norm|0.1908|± |0.0300|
|
| 56 |
+
|hendrycksTest-college_physics | 1|acc |0.2157|± |0.0409|
|
| 57 |
+
| | |acc_norm|0.2157|± |0.0409|
|
| 58 |
+
|hendrycksTest-computer_security | 1|acc |0.2200|± |0.0416|
|
| 59 |
+
| | |acc_norm|0.2200|± |0.0416|
|
| 60 |
+
|hendrycksTest-conceptual_physics | 1|acc |0.2383|± |0.0279|
|
| 61 |
+
| | |acc_norm|0.2383|± |0.0279|
|
| 62 |
+
|hendrycksTest-econometrics | 1|acc |0.2456|± |0.0405|
|
| 63 |
+
| | |acc_norm|0.2456|± |0.0405|
|
| 64 |
+
|hendrycksTest-electrical_engineering | 1|acc |0.2276|± |0.0349|
|
| 65 |
+
| | |acc_norm|0.2276|± |0.0349|
|
| 66 |
+
|hendrycksTest-elementary_mathematics | 1|acc |0.1772|± |0.0197|
|
| 67 |
+
| | |acc_norm|0.1772|± |0.0197|
|
| 68 |
+
|hendrycksTest-formal_logic | 1|acc |0.2460|± |0.0385|
|
| 69 |
+
| | |acc_norm|0.2460|± |0.0385|
|
| 70 |
+
|hendrycksTest-global_facts | 1|acc |0.2400|± |0.0429|
|
| 71 |
+
| | |acc_norm|0.2400|± |0.0429|
|
| 72 |
+
|hendrycksTest-high_school_biology | 1|acc |0.3065|± |0.0262|
|
| 73 |
+
| | |acc_norm|0.3065|± |0.0262|
|
| 74 |
+
|hendrycksTest-high_school_chemistry | 1|acc |0.2759|± |0.0314|
|
| 75 |
+
| | |acc_norm|0.2759|± |0.0314|
|
| 76 |
+
|hendrycksTest-high_school_computer_science | 1|acc |0.1600|± |0.0368|
|
| 77 |
+
| | |acc_norm|0.1600|± |0.0368|
|
| 78 |
+
|hendrycksTest-high_school_european_history | 1|acc |0.2242|± |0.0326|
|
| 79 |
+
| | |acc_norm|0.2242|± |0.0326|
|
| 80 |
+
|hendrycksTest-high_school_geography | 1|acc |0.2828|± |0.0321|
|
| 81 |
+
| | |acc_norm|0.2828|± |0.0321|
|
| 82 |
+
|hendrycksTest-high_school_government_and_politics| 1|acc |0.3472|± |0.0344|
|
| 83 |
+
| | |acc_norm|0.3472|± |0.0344|
|
| 84 |
+
|hendrycksTest-high_school_macroeconomics | 1|acc |0.3026|± |0.0233|
|
| 85 |
+
| | |acc_norm|0.3026|± |0.0233|
|
| 86 |
+
|hendrycksTest-high_school_mathematics | 1|acc |0.2667|± |0.0270|
|
| 87 |
+
| | |acc_norm|0.2667|± |0.0270|
|
| 88 |
+
|hendrycksTest-high_school_microeconomics | 1|acc |0.2983|± |0.0297|
|
| 89 |
+
| | |acc_norm|0.2983|± |0.0297|
|
| 90 |
+
|hendrycksTest-high_school_physics | 1|acc |0.1722|± |0.0308|
|
| 91 |
+
| | |acc_norm|0.1722|± |0.0308|
|
| 92 |
+
|hendrycksTest-high_school_psychology | 1|acc |0.2312|± |0.0181|
|
| 93 |
+
| | |acc_norm|0.2312|± |0.0181|
|
| 94 |
+
|hendrycksTest-high_school_statistics | 1|acc |0.4167|± |0.0336|
|
| 95 |
+
| | |acc_norm|0.4167|± |0.0336|
|
| 96 |
+
|hendrycksTest-high_school_us_history | 1|acc |0.2451|± |0.0302|
|
| 97 |
+
| | |acc_norm|0.2451|± |0.0302|
|
| 98 |
+
|hendrycksTest-high_school_world_history | 1|acc |0.2489|± |0.0281|
|
| 99 |
+
| | |acc_norm|0.2489|± |0.0281|
|
| 100 |
+
|hendrycksTest-human_aging | 1|acc |0.2422|± |0.0288|
|
| 101 |
+
| | |acc_norm|0.2422|± |0.0288|
|
| 102 |
+
|hendrycksTest-human_sexuality | 1|acc |0.2214|± |0.0364|
|
| 103 |
+
| | |acc_norm|0.2214|± |0.0364|
|
| 104 |
+
|hendrycksTest-international_law | 1|acc |0.3223|± |0.0427|
|
| 105 |
+
| | |acc_norm|0.3223|± |0.0427|
|
| 106 |
+
|hendrycksTest-jurisprudence | 1|acc |0.2500|± |0.0419|
|
| 107 |
+
| | |acc_norm|0.2500|± |0.0419|
|
| 108 |
+
|hendrycksTest-logical_fallacies | 1|acc |0.2454|± |0.0338|
|
| 109 |
+
| | |acc_norm|0.2454|± |0.0338|
|
| 110 |
+
|hendrycksTest-machine_learning | 1|acc |0.1964|± |0.0377|
|
| 111 |
+
| | |acc_norm|0.1964|± |0.0377|
|
| 112 |
+
|hendrycksTest-management | 1|acc |0.2427|± |0.0425|
|
| 113 |
+
| | |acc_norm|0.2427|± |0.0425|
|
| 114 |
+
|hendrycksTest-marketing | 1|acc |0.2009|± |0.0262|
|
| 115 |
+
| | |acc_norm|0.2009|± |0.0262|
|
| 116 |
+
|hendrycksTest-medical_genetics | 1|acc |0.2400|± |0.0429|
|
| 117 |
+
| | |acc_norm|0.2400|± |0.0429|
|
| 118 |
+
|hendrycksTest-miscellaneous | 1|acc |0.2593|± |0.0157|
|
| 119 |
+
| | |acc_norm|0.2593|± |0.0157|
|
| 120 |
+
|hendrycksTest-moral_disputes | 1|acc |0.2486|± |0.0233|
|
| 121 |
+
| | |acc_norm|0.2486|± |0.0233|
|
| 122 |
+
|hendrycksTest-moral_scenarios | 1|acc |0.2469|± |0.0144|
|
| 123 |
+
| | |acc_norm|0.2469|± |0.0144|
|
| 124 |
+
|hendrycksTest-nutrition | 1|acc |0.2157|± |0.0236|
|
| 125 |
+
| | |acc_norm|0.2157|± |0.0236|
|
| 126 |
+
|hendrycksTest-philosophy | 1|acc |0.2830|± |0.0256|
|
| 127 |
+
| | |acc_norm|0.2830|± |0.0256|
|
| 128 |
+
|hendrycksTest-prehistory | 1|acc |0.2377|± |0.0237|
|
| 129 |
+
| | |acc_norm|0.2377|± |0.0237|
|
| 130 |
+
|hendrycksTest-professional_accounting | 1|acc |0.2801|± |0.0268|
|
| 131 |
+
| | |acc_norm|0.2801|± |0.0268|
|
| 132 |
+
|hendrycksTest-professional_law | 1|acc |0.2458|± |0.0110|
|
| 133 |
+
| | |acc_norm|0.2458|± |0.0110|
|
| 134 |
+
|hendrycksTest-professional_medicine | 1|acc |0.2794|± |0.0273|
|
| 135 |
+
| | |acc_norm|0.2794|± |0.0273|
|
| 136 |
+
|hendrycksTest-professional_psychology | 1|acc |0.2598|± |0.0177|
|
| 137 |
+
| | |acc_norm|0.2598|± |0.0177|
|
| 138 |
+
|hendrycksTest-public_relations | 1|acc |0.2273|± |0.0401|
|
| 139 |
+
| | |acc_norm|0.2273|± |0.0401|
|
| 140 |
+
|hendrycksTest-security_studies | 1|acc |0.3388|± |0.0303|
|
| 141 |
+
| | |acc_norm|0.3388|± |0.0303|
|
| 142 |
+
|hendrycksTest-sociology | 1|acc |0.2189|± |0.0292|
|
| 143 |
+
| | |acc_norm|0.2189|± |0.0292|
|
| 144 |
+
|hendrycksTest-us_foreign_policy | 1|acc |0.2100|± |0.0409|
|
| 145 |
+
| | |acc_norm|0.2100|± |0.0409|
|
| 146 |
+
|hendrycksTest-virology | 1|acc |0.2169|± |0.0321|
|
| 147 |
+
| | |acc_norm|0.2169|± |0.0321|
|
| 148 |
+
|hendrycksTest-world_religions | 1|acc |0.2047|± |0.0309|
|
| 149 |
+
| | |acc_norm|0.2047|± |0.0309|
|