lm eval results
Browse files
README.md
CHANGED
|
@@ -23,3 +23,94 @@ tags:
|
|
| 23 |
---
|
| 24 |
|
| 25 |
# tangled-llama-33m-32k-base-v0.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
---
|
| 24 |
|
| 25 |
# tangled-llama-33m-32k-base-v0.1
|
| 26 |
+
|
| 27 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
| 28 |
+
|
| 29 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
| 30 |
+
|
| 31 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
| 32 |
+
|
| 33 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
| 34 |
+
|
| 35 |
+
## lm-evaluation-harness
|
| 36 |
+
|
| 37 |
+
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
| 38 |
+
|---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
| 39 |
+
|arc_challenge | 1|none | 0|acc |↑ |0.2065|± |0.0118|
|
| 40 |
+
| | |none | 0|acc_norm |↑ |0.2338|± |0.0124|
|
| 41 |
+
|gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0144|± |0.0033|
|
| 42 |
+
| | |strict-match | 5|exact_match|↑ |0.0000|± |0.0000|
|
| 43 |
+
|hellaswag | 1|none | 0|acc |↑ |0.2614|± |0.0044|
|
| 44 |
+
| | |none | 0|acc_norm |↑ |0.2604|± |0.0044|
|
| 45 |
+
|mmlu | 2|none | |acc |↑ |0.2280|± |0.0035|
|
| 46 |
+
| - humanities | 2|none | |acc |↑ |0.2376|± |0.0062|
|
| 47 |
+
| - formal_logic | 1|none | 0|acc |↑ |0.2698|± |0.0397|
|
| 48 |
+
| - high_school_european_history | 1|none | 0|acc |↑ |0.2000|± |0.0312|
|
| 49 |
+
| - high_school_us_history | 1|none | 0|acc |↑ |0.2500|± |0.0304|
|
| 50 |
+
| - high_school_world_history | 1|none | 0|acc |↑ |0.2785|± |0.0292|
|
| 51 |
+
| - international_law | 1|none | 0|acc |↑ |0.2149|± |0.0375|
|
| 52 |
+
| - jurisprudence | 1|none | 0|acc |↑ |0.2407|± |0.0413|
|
| 53 |
+
| - logical_fallacies | 1|none | 0|acc |↑ |0.2270|± |0.0329|
|
| 54 |
+
| - moral_disputes | 1|none | 0|acc |↑ |0.2341|± |0.0228|
|
| 55 |
+
| - moral_scenarios | 1|none | 0|acc |↑ |0.2380|± |0.0142|
|
| 56 |
+
| - philosophy | 1|none | 0|acc |↑ |0.1833|± |0.0220|
|
| 57 |
+
| - prehistory | 1|none | 0|acc |↑ |0.2160|± |0.0229|
|
| 58 |
+
| - professional_law | 1|none | 0|acc |↑ |0.2399|± |0.0109|
|
| 59 |
+
| - world_religions | 1|none | 0|acc |↑ |0.3275|± |0.0360|
|
| 60 |
+
| - other | 2|none | |acc |↑ |0.2481|± |0.0077|
|
| 61 |
+
| - business_ethics | 1|none | 0|acc |↑ |0.3100|± |0.0465|
|
| 62 |
+
| - clinical_knowledge | 1|none | 0|acc |↑ |0.2264|± |0.0258|
|
| 63 |
+
| - college_medicine | 1|none | 0|acc |↑ |0.2486|± |0.0330|
|
| 64 |
+
| - global_facts | 1|none | 0|acc |↑ |0.1700|± |0.0378|
|
| 65 |
+
| - human_aging | 1|none | 0|acc |↑ |0.3229|± |0.0314|
|
| 66 |
+
| - management | 1|none | 0|acc |↑ |0.1845|± |0.0384|
|
| 67 |
+
| - marketing | 1|none | 0|acc |↑ |0.3034|± |0.0301|
|
| 68 |
+
| - medical_genetics | 1|none | 0|acc |↑ |0.3100|± |0.0465|
|
| 69 |
+
| - miscellaneous | 1|none | 0|acc |↑ |0.2401|± |0.0153|
|
| 70 |
+
| - nutrition | 1|none | 0|acc |↑ |0.2418|± |0.0245|
|
| 71 |
+
| - professional_accounting | 1|none | 0|acc |↑ |0.2411|± |0.0255|
|
| 72 |
+
| - professional_medicine | 1|none | 0|acc |↑ |0.1838|± |0.0235|
|
| 73 |
+
| - virology | 1|none | 0|acc |↑ |0.2831|± |0.0351|
|
| 74 |
+
| - social sciences | 2|none | |acc |↑ |0.2155|± |0.0074|
|
| 75 |
+
| - econometrics | 1|none | 0|acc |↑ |0.2281|± |0.0395|
|
| 76 |
+
| - high_school_geography | 1|none | 0|acc |↑ |0.1768|± |0.0272|
|
| 77 |
+
| - high_school_government_and_politics| 1|none | 0|acc |↑ |0.1969|± |0.0287|
|
| 78 |
+
| - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2103|± |0.0207|
|
| 79 |
+
| - high_school_microeconomics | 1|none | 0|acc |↑ |0.2143|± |0.0267|
|
| 80 |
+
| - high_school_psychology | 1|none | 0|acc |↑ |0.1872|± |0.0167|
|
| 81 |
+
| - human_sexuality | 1|none | 0|acc |↑ |0.2672|± |0.0388|
|
| 82 |
+
| - professional_psychology | 1|none | 0|acc |↑ |0.2467|± |0.0174|
|
| 83 |
+
| - public_relations | 1|none | 0|acc |↑ |0.2182|± |0.0396|
|
| 84 |
+
| - security_studies | 1|none | 0|acc |↑ |0.1755|± |0.0244|
|
| 85 |
+
| - sociology | 1|none | 0|acc |↑ |0.2438|± |0.0304|
|
| 86 |
+
| - us_foreign_policy | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
| 87 |
+
| - stem | 2|none | |acc |↑ |0.2058|± |0.0072|
|
| 88 |
+
| - abstract_algebra | 1|none | 0|acc |↑ |0.1700|± |0.0378|
|
| 89 |
+
| - anatomy | 1|none | 0|acc |↑ |0.1778|± |0.0330|
|
| 90 |
+
| - astronomy | 1|none | 0|acc |↑ |0.1776|± |0.0311|
|
| 91 |
+
| - college_biology | 1|none | 0|acc |↑ |0.2569|± |0.0365|
|
| 92 |
+
| - college_chemistry | 1|none | 0|acc |↑ |0.1900|± |0.0394|
|
| 93 |
+
| - college_computer_science | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
| 94 |
+
| - college_mathematics | 1|none | 0|acc |↑ |0.2100|± |0.0409|
|
| 95 |
+
| - college_physics | 1|none | 0|acc |↑ |0.2059|± |0.0402|
|
| 96 |
+
| - computer_security | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
| 97 |
+
| - conceptual_physics | 1|none | 0|acc |↑ |0.2681|± |0.0290|
|
| 98 |
+
| - electrical_engineering | 1|none | 0|acc |↑ |0.2345|± |0.0353|
|
| 99 |
+
| - elementary_mathematics | 1|none | 0|acc |↑ |0.2011|± |0.0206|
|
| 100 |
+
| - high_school_biology | 1|none | 0|acc |↑ |0.1806|± |0.0219|
|
| 101 |
+
| - high_school_chemistry | 1|none | 0|acc |↑ |0.1478|± |0.0250|
|
| 102 |
+
| - high_school_computer_science | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
| 103 |
+
| - high_school_mathematics | 1|none | 0|acc |↑ |0.2111|± |0.0249|
|
| 104 |
+
| - high_school_physics | 1|none | 0|acc |↑ |0.1788|± |0.0313|
|
| 105 |
+
| - high_school_statistics | 1|none | 0|acc |↑ |0.1620|± |0.0251|
|
| 106 |
+
| - machine_learning | 1|none | 0|acc |↑ |0.2768|± |0.0425|
|
| 107 |
+
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.4975|± |0.0165|
|
| 108 |
+
|winogrande | 1|none | 0|acc |↑ |0.5146|± |0.0140|
|
| 109 |
+
|
| 110 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 111 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 112 |
+
|mmlu | 2|none | |acc |↑ |0.2280|± |0.0035|
|
| 113 |
+
| - humanities | 2|none | |acc |↑ |0.2376|± |0.0062|
|
| 114 |
+
| - other | 2|none | |acc |↑ |0.2481|± |0.0077|
|
| 115 |
+
| - social sciences| 2|none | |acc |↑ |0.2155|± |0.0074|
|
| 116 |
+
| - stem | 2|none | |acc |↑ |0.2058|± |0.0072|
|