Update README.md
Browse files
README.md
CHANGED
|
@@ -85,98 +85,6 @@ print(tokenizer.decode(outputs[0]))
|
|
| 85 |
|
| 86 |
# Nous Benchmark
|
| 87 |
|
| 88 |
-
Agieval
|
| 89 |
-
|
| 90 |
-
| Task | Version | Metric | Value | | StdErr |
|
| 91 |
-
|-------------------------------------------|---------|--------|-------|---|---------|
|
| 92 |
-
| agieval\_aqua\_rat | 0 | acc | 24.02 | _ | 2.69 |
|
| 93 |
-
| agieval\_aqua\_rat | 0 | acc\_norm | 24.02 | _ | 2.69 |
|
| 94 |
-
| agieval\_logiqa\_en | 0 | acc | 23.20 | _ | 1.66 |
|
| 95 |
-
| agieval\_logiqa\_en | 0 | acc\_norm | 24.42 | _ | 1.69 |
|
| 96 |
-
| agieval\_lsat\_ar | 0 | acc | 18.26 | _ | 2.55 |
|
| 97 |
-
| agieval\_lsat\_ar | 0 | acc\_norm | 18.70 | _ | 2.58 |
|
| 98 |
-
| agieval\_lsat\_lr | 0 | acc | 22.35 | _ | 1.85 |
|
| 99 |
-
| agieval\_lsat\_lr | 0 | acc\_norm | 23.53 | _ | 1.88 |
|
| 100 |
-
| agieval\_lsat\_rc | 0 | acc | 20.82 | _ | 2.48 |
|
| 101 |
-
| agieval\_lsat\_rc | 0 | acc\_norm | 20.07 | _ | 2.45 |
|
| 102 |
-
| agieval\_sat\_en | 0 | acc | 32.52 | _ | 3.27 |
|
| 103 |
-
| agieval\_sat\_en | 0 | acc\_norm | 32.52 | _ | 3.27 |
|
| 104 |
-
| agieval\_sat\_en\_without\_passage | 0 | acc | 25.73 | _ | 3.05 |
|
| 105 |
-
| agieval\_sat\_en\_without\_passage | 0 | acc\_norm | 24.27 | _ | 2.99 |
|
| 106 |
-
| agieval\_sat\_math | 0 | acc | 25.00 | _ | 2.93 |
|
| 107 |
-
| agieval\_sat\_math | 0 | acc\_norm | 20.91 | _ | 2.75 |
|
| 108 |
-
Average: 24.11
|
| 109 |
-
|
| 110 |
-
GPT4ALL
|
| 111 |
-
|
| 112 |
-
| Task | Version | Metric | Value | | StdErr |
|
| 113 |
-
|----------------------|---------|--------|-------|---|---------|
|
| 114 |
-
| arc\_challenge | 0 | acc | 21.77 | _ | 1.21 |
|
| 115 |
-
| arc\_challenge | 0 | acc\_norm | 24.15 | _ | 1.25 |
|
| 116 |
-
| arc\_easy | 0 | acc | 37.37 | _ | 0.99 |
|
| 117 |
-
| arc\_easy | 0 | acc\_norm | 36.95 | _ | 0.99 |
|
| 118 |
-
| boolq | 1 | acc | 65.60 | _ | 0.83 |
|
| 119 |
-
| hellaswag | 0 | acc | 34.54 | _ | 0.47 |
|
| 120 |
-
| hellaswag | 0 | acc\_norm | 40.54 | _ | 0.49 |
|
| 121 |
-
| openbookqa | 0 | acc | 15.00 | _ | 1.59 |
|
| 122 |
-
| openbookqa | 0 | acc\_norm | 27.40 | _ | 2.00 |
|
| 123 |
-
| piqa | 0 | acc | 60.88 | _ | 1.14 |
|
| 124 |
-
| piqa | 0 | acc\_norm | 60.55 | _ | 1.14 |
|
| 125 |
-
| winogrande | 0 | acc | 50.91 | _ | 1.41 |
|
| 126 |
-
Average: 40.01
|
| 127 |
-
|
| 128 |
-
BigBench
|
| 129 |
-
|
| 130 |
-
| Task | Version | Metric | Value | Std Err |
|
| 131 |
-
|-----------------------------------|---------|--------|--------|---------|
|
| 132 |
-
| bigbench\_causal\_judgement | 0 | MCG | 50 | 2.26 |
|
| 133 |
-
| bigbench\_date\_understanding | 0 | MCG | 49.14 | 2.18 |
|
| 134 |
-
| bigbench\_disambiguation\_qa | 0 | MCG | 49.31 | 2.74 |
|
| 135 |
-
| bigbench\_geometric\_shapes | 0 | MCG | 14.18 | 1.37 |
|
| 136 |
-
| bigbench\_logical\_deduction\_5objs | 0 | MCG | 49.41 | 2.73 |
|
| 137 |
-
| bigbench\_logical\_deduction\_7objs | 0 | MCG | 41.48 | 2.46 |
|
| 138 |
-
| bigbench\_logical\_deduction\_3objs | 0 | MCG | 69.33 | 2.75 |
|
| 139 |
-
| bigbench\_movie\_recommendation | 0 | MCG | 51.71 | 2.25 |
|
| 140 |
-
| bigbench\_navigate | 0 | MCG | 50 | 1.58 |
|
| 141 |
-
| bigbench\_reasoning\_colored\_obj | 0 | MCG | 51.92 | 0.99 |
|
| 142 |
-
| bigbench\_ruin\_names | 0 | MCG | 48.14 | 2.01 |
|
| 143 |
-
| bigbench\_salient\_trans\_err\_detec | 0 | MCG | 39.92 | 1.2 |
|
| 144 |
-
| bigbench\_snarks | 0 | MCG | 64.14 | 3.71 |
|
| 145 |
-
| bigbench\_sports\_understanding | 0 | MCG | 55.31 | 1.59 |
|
| 146 |
-
| bigbench\_temporal\_sequences | 0 | MCG | 46.92 | 1.4 |
|
| 147 |
-
| bigbench\_tsk\_shuff\_objs\_5 | 0 | MCG | 25.04 | 1.01 |
|
| 148 |
-
| bigbench\_tsk\_shuff\_objs\_7 | 0 | MCG | 15.04 | 0.72 |
|
| 149 |
-
| bigbench\_tsk\_shuff\_objs\_3 | 0 | MCG | 55.33 | 2.75 |
|
| 150 |
-
Average: 44.75
|
| 151 |
-
|
| 152 |
-
TruthfulQA
|
| 153 |
-
|
| 154 |
-
| Task | Version | Metric | Value | Std Err |
|
| 155 |
-
|----------------------------------|---------|--------|--------|----------|
|
| 156 |
-
| truthfulqa\_mc | 1 | mc1 | 30.11 | 1.61 |
|
| 157 |
-
| truthfulqa\_mc | 1 | mc2 | 47.69 | 1.61 |
|
| 158 |
-
Average: 38.90
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
# Openllm Benchmark
|
| 162 |
-
|
| 163 |
-
| Task |Version| Metric |Value| |Stderr|
|
| 164 |
-
|-------------|------:|--------|----:|---|-----:|
|
| 165 |
-
|arc_challenge| 0|acc |40.44|± | 1.43|
|
| 166 |
-
| | |acc_norm|43.81|± | 1.34|
|
| 167 |
-
|hellaswag | 0|acc |48.1 |± | 0.45|
|
| 168 |
-
| | |acc_norm|62.73|± | 0.32|
|
| 169 |
-
|gsm8k | 0|acc |5.6 |± | 0.6 |
|
| 170 |
-
|winogrande | 0|acc |60.91|± | 1.3 |
|
| 171 |
-
|mmlu | 0|acc |37.62 |±| 0.6 |
|
| 172 |
-
|
| 173 |
-
Average: 73.5%
|
| 174 |
-
|
| 175 |
-
### TruthfulQA
|
| 176 |
-
| Task |Version|Metric|Value| |Stderr|
|
| 177 |
-
|-------------|------:|------|----:|---|-----:|
|
| 178 |
-
|truthfulqa_mc| 1|mc1 |29.00|± | 1.58|
|
| 179 |
-
| | |mc2 |45.83|± | 1.59|
|
| 180 |
|
| 181 |
### Training hyperparameters
|
| 182 |
|
|
|
|
| 85 |
|
| 86 |
# Nous Benchmark
|
| 87 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
|
| 89 |
### Training hyperparameters
|
| 90 |
|