Upload results/eval_difficulty/summary.json
Browse files
results/eval_difficulty/summary.json
ADDED
|
@@ -0,0 +1,645 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"checkpoint": "checkpoint-18779",
|
| 4 |
+
"id_acc": 0.9630347222222222,
|
| 5 |
+
"ood_acc": 0.25220703125,
|
| 6 |
+
"total_acc": 0.588914884868421,
|
| 7 |
+
"id_avg_loss": 6.54602900314331,
|
| 8 |
+
"ood_avg_loss": 5.825457085227966,
|
| 9 |
+
"total_avg_loss": 6.166780625293129,
|
| 10 |
+
"id_avg_resp_len": 201.21272916666666,
|
| 11 |
+
"ood_avg_resp_len": 284.85050390625,
|
| 12 |
+
"count_id": 1152000,
|
| 13 |
+
"count_ood": 1280000,
|
| 14 |
+
"count_total": 2432000,
|
| 15 |
+
"template_metrics": {
|
| 16 |
+
"crazy_zootopia": {
|
| 17 |
+
"count": 809728,
|
| 18 |
+
"correct": 477128,
|
| 19 |
+
"answer_accuracy": 0.5892447834334492,
|
| 20 |
+
"avg_response_len": 235.475637498024,
|
| 21 |
+
"resp_tokens_sum": 190671217,
|
| 22 |
+
"pass_at_k": {
|
| 23 |
+
"pass@1": 0.5892447834334492,
|
| 24 |
+
"pass@2": 0.6242494417489666,
|
| 25 |
+
"pass@4": 0.6517067209785661,
|
| 26 |
+
"pass@8": 0.6752650274111465,
|
| 27 |
+
"pass@16": 0.6966098480320178,
|
| 28 |
+
"pass@32": 0.7161446042348242,
|
| 29 |
+
"pass@64": 0.7340453705919688,
|
| 30 |
+
"pass@128": 0.7510275055327221
|
| 31 |
+
},
|
| 32 |
+
"per_op_pass_at_k": {
|
| 33 |
+
"10": {
|
| 34 |
+
"pass@1": 0.8994976032448377,
|
| 35 |
+
"pass@2": 0.9366747090795067,
|
| 36 |
+
"pass@4": 0.954640098361598,
|
| 37 |
+
"pass@8": 0.9671935395338649,
|
| 38 |
+
"pass@16": 0.9780409476989385,
|
| 39 |
+
"pass@32": 0.9873672705205916,
|
| 40 |
+
"pass@64": 0.9931124421272916,
|
| 41 |
+
"pass@128": 0.9941002949852508
|
| 42 |
+
},
|
| 43 |
+
"2": {
|
| 44 |
+
"pass@1": 0.9997322819314641,
|
| 45 |
+
"pass@2": 0.9999915679348491,
|
| 46 |
+
"pass@4": 0.9999999897793149,
|
| 47 |
+
"pass@8": 1.0,
|
| 48 |
+
"pass@16": 1.0,
|
| 49 |
+
"pass@32": 1.0,
|
| 50 |
+
"pass@64": 1.0,
|
| 51 |
+
"pass@128": 1.0
|
| 52 |
+
},
|
| 53 |
+
"3": {
|
| 54 |
+
"pass@1": 0.9875525611620795,
|
| 55 |
+
"pass@2": 0.9937483445303281,
|
| 56 |
+
"pass@4": 0.9960841566249173,
|
| 57 |
+
"pass@8": 0.9973945614382809,
|
| 58 |
+
"pass@16": 0.9984052318072489,
|
| 59 |
+
"pass@32": 0.9992931754002767,
|
| 60 |
+
"pass@64": 0.9999118688143109,
|
| 61 |
+
"pass@128": 1.0
|
| 62 |
+
},
|
| 63 |
+
"4": {
|
| 64 |
+
"pass@1": 0.996337890625,
|
| 65 |
+
"pass@2": 0.9982602577509845,
|
| 66 |
+
"pass@4": 0.9992694307742784,
|
| 67 |
+
"pass@8": 0.9998455780548049,
|
| 68 |
+
"pass@16": 0.9999940908757206,
|
| 69 |
+
"pass@32": 0.9999999967265157,
|
| 70 |
+
"pass@64": 1.0,
|
| 71 |
+
"pass@128": 1.0
|
| 72 |
+
},
|
| 73 |
+
"5": {
|
| 74 |
+
"pass@1": 0.9481150793650793,
|
| 75 |
+
"pass@2": 0.9641533089613797,
|
| 76 |
+
"pass@4": 0.9757381440415184,
|
| 77 |
+
"pass@8": 0.9837977641761237,
|
| 78 |
+
"pass@16": 0.9891567790393069,
|
| 79 |
+
"pass@32": 0.9924331098404072,
|
| 80 |
+
"pass@64": 0.9948057827917357,
|
| 81 |
+
"pass@128": 0.9968253968253968
|
| 82 |
+
},
|
| 83 |
+
"6": {
|
| 84 |
+
"pass@1": 0.9665746631736527,
|
| 85 |
+
"pass@2": 0.9810815131547932,
|
| 86 |
+
"pass@4": 0.9889092237347574,
|
| 87 |
+
"pass@8": 0.992817054998713,
|
| 88 |
+
"pass@16": 0.9942118482404367,
|
| 89 |
+
"pass@32": 0.9947566055669427,
|
| 90 |
+
"pass@64": 0.9955089818359227,
|
| 91 |
+
"pass@128": 0.9970059880239521
|
| 92 |
+
},
|
| 93 |
+
"7": {
|
| 94 |
+
"pass@1": 0.9575397559171598,
|
| 95 |
+
"pass@2": 0.9706686361412663,
|
| 96 |
+
"pass@4": 0.9781720887884576,
|
| 97 |
+
"pass@8": 0.9836457175352227,
|
| 98 |
+
"pass@16": 0.9877211930993773,
|
| 99 |
+
"pass@32": 0.991030454111008,
|
| 100 |
+
"pass@64": 0.9934560055493304,
|
| 101 |
+
"pass@128": 0.9940828402366864
|
| 102 |
+
},
|
| 103 |
+
"8": {
|
| 104 |
+
"pass@1": 0.9534755608974359,
|
| 105 |
+
"pass@2": 0.9758759684786995,
|
| 106 |
+
"pass@4": 0.9847553208493165,
|
| 107 |
+
"pass@8": 0.9897007291187125,
|
| 108 |
+
"pass@16": 0.9935694000922215,
|
| 109 |
+
"pass@32": 0.9965151373391712,
|
| 110 |
+
"pass@64": 0.998300039303945,
|
| 111 |
+
"pass@128": 1.0
|
| 112 |
+
},
|
| 113 |
+
"9": {
|
| 114 |
+
"pass@1": 0.9408450704225352,
|
| 115 |
+
"pass@2": 0.9764160751913055,
|
| 116 |
+
"pass@4": 0.9897490211610868,
|
| 117 |
+
"pass@8": 0.9954928597779902,
|
| 118 |
+
"pass@16": 0.9986146363237696,
|
| 119 |
+
"pass@32": 0.9998472651017836,
|
| 120 |
+
"pass@64": 0.9999990904114461,
|
| 121 |
+
"pass@128": 1.0
|
| 122 |
+
},
|
| 123 |
+
"11": {
|
| 124 |
+
"pass@1": 0.7521689093484419,
|
| 125 |
+
"pass@2": 0.8267172826838576,
|
| 126 |
+
"pass@4": 0.8749963240253604,
|
| 127 |
+
"pass@8": 0.9072539747181511,
|
| 128 |
+
"pass@16": 0.9305891455160197,
|
| 129 |
+
"pass@32": 0.9482171914771189,
|
| 130 |
+
"pass@64": 0.9598296757598728,
|
| 131 |
+
"pass@128": 0.9660056657223796
|
| 132 |
+
},
|
| 133 |
+
"12": {
|
| 134 |
+
"pass@1": 0.4268626412429379,
|
| 135 |
+
"pass@2": 0.5226548250589441,
|
| 136 |
+
"pass@4": 0.5947451512946471,
|
| 137 |
+
"pass@8": 0.6499540700619184,
|
| 138 |
+
"pass@16": 0.697671407935311,
|
| 139 |
+
"pass@32": 0.7391764349175001,
|
| 140 |
+
"pass@64": 0.7728700105439386,
|
| 141 |
+
"pass@128": 0.8022598870056498
|
| 142 |
+
},
|
| 143 |
+
"13": {
|
| 144 |
+
"pass@1": 0.226048197492163,
|
| 145 |
+
"pass@2": 0.2745025516500875,
|
| 146 |
+
"pass@4": 0.32170087379359735,
|
| 147 |
+
"pass@8": 0.36726090847720233,
|
| 148 |
+
"pass@16": 0.4118837384913241,
|
| 149 |
+
"pass@32": 0.4577964268716136,
|
| 150 |
+
"pass@64": 0.5060004900301981,
|
| 151 |
+
"pass@128": 0.554858934169279
|
| 152 |
+
},
|
| 153 |
+
"14": {
|
| 154 |
+
"pass@1": 0.1970404984423676,
|
| 155 |
+
"pass@2": 0.2447659871955257,
|
| 156 |
+
"pass@4": 0.2905214605183697,
|
| 157 |
+
"pass@8": 0.33432116638118264,
|
| 158 |
+
"pass@16": 0.37689919457954874,
|
| 159 |
+
"pass@32": 0.41849874775311363,
|
| 160 |
+
"pass@64": 0.46201871752633594,
|
| 161 |
+
"pass@128": 0.5109034267912772
|
| 162 |
+
},
|
| 163 |
+
"15": {
|
| 164 |
+
"pass@1": 0.190774024566474,
|
| 165 |
+
"pass@2": 0.24494681910245306,
|
| 166 |
+
"pass@4": 0.29680882700356104,
|
| 167 |
+
"pass@8": 0.3440605324830605,
|
| 168 |
+
"pass@16": 0.38846742937996726,
|
| 169 |
+
"pass@32": 0.43008799604881653,
|
| 170 |
+
"pass@64": 0.4654618905817254,
|
| 171 |
+
"pass@128": 0.4913294797687861
|
| 172 |
+
},
|
| 173 |
+
"16": {
|
| 174 |
+
"pass@1": 0.1630796370967742,
|
| 175 |
+
"pass@2": 0.1964297053594107,
|
| 176 |
+
"pass@4": 0.23033826426938572,
|
| 177 |
+
"pass@8": 0.2660781043146322,
|
| 178 |
+
"pass@16": 0.3019958633560044,
|
| 179 |
+
"pass@32": 0.33569879011745574,
|
| 180 |
+
"pass@64": 0.3686862876847773,
|
| 181 |
+
"pass@128": 0.4064516129032258
|
| 182 |
+
},
|
| 183 |
+
"17": {
|
| 184 |
+
"pass@1": 0.1676300578034682,
|
| 185 |
+
"pass@2": 0.20699551397296437,
|
| 186 |
+
"pass@4": 0.2408987041359715,
|
| 187 |
+
"pass@8": 0.271017564290959,
|
| 188 |
+
"pass@16": 0.29876652985892266,
|
| 189 |
+
"pass@32": 0.3264747152113181,
|
| 190 |
+
"pass@64": 0.3549548508714773,
|
| 191 |
+
"pass@128": 0.38439306358381503
|
| 192 |
+
},
|
| 193 |
+
"18": {
|
| 194 |
+
"pass@1": 0.1616517857142857,
|
| 195 |
+
"pass@2": 0.19595648200224966,
|
| 196 |
+
"pass@4": 0.23106420322459695,
|
| 197 |
+
"pass@8": 0.26888622832851616,
|
| 198 |
+
"pass@16": 0.3071732341417159,
|
| 199 |
+
"pass@32": 0.3420263056744111,
|
| 200 |
+
"pass@64": 0.3714714335108666,
|
| 201 |
+
"pass@128": 0.39714285714285713
|
| 202 |
+
},
|
| 203 |
+
"19": {
|
| 204 |
+
"pass@1": 0.15040822072072071,
|
| 205 |
+
"pass@2": 0.1915057281691139,
|
| 206 |
+
"pass@4": 0.2273034600967671,
|
| 207 |
+
"pass@8": 0.2598221642368353,
|
| 208 |
+
"pass@16": 0.2905735616301428,
|
| 209 |
+
"pass@32": 0.32042698971733125,
|
| 210 |
+
"pass@64": 0.35124146512270843,
|
| 211 |
+
"pass@128": 0.3843843843843844
|
| 212 |
+
},
|
| 213 |
+
"20": {
|
| 214 |
+
"pass@1": 0.15052552552552553,
|
| 215 |
+
"pass@2": 0.18885223806483653,
|
| 216 |
+
"pass@4": 0.22942468621602477,
|
| 217 |
+
"pass@8": 0.26979999128432536,
|
| 218 |
+
"pass@16": 0.30689533475643643,
|
| 219 |
+
"pass@32": 0.3397581402934893,
|
| 220 |
+
"pass@64": 0.370991289408613,
|
| 221 |
+
"pass@128": 0.4024024024024024
|
| 222 |
+
}
|
| 223 |
+
}
|
| 224 |
+
},
|
| 225 |
+
"teachers_in_school": {
|
| 226 |
+
"count": 821120,
|
| 227 |
+
"correct": 483803,
|
| 228 |
+
"answer_accuracy": 0.5891988990646921,
|
| 229 |
+
"avg_response_len": 242.341766124318,
|
| 230 |
+
"resp_tokens_sum": 198991671,
|
| 231 |
+
"pass_at_k": {
|
| 232 |
+
"pass@1": 0.5891988990646921,
|
| 233 |
+
"pass@2": 0.6227068003142299,
|
| 234 |
+
"pass@4": 0.650107249088997,
|
| 235 |
+
"pass@8": 0.6741994105674554,
|
| 236 |
+
"pass@16": 0.6956359816626693,
|
| 237 |
+
"pass@32": 0.7149534992963424,
|
| 238 |
+
"pass@64": 0.7325456550204769,
|
| 239 |
+
"pass@128": 0.7480904130943102
|
| 240 |
+
},
|
| 241 |
+
"per_op_pass_at_k": {
|
| 242 |
+
"10": {
|
| 243 |
+
"pass@1": 0.8878930214723927,
|
| 244 |
+
"pass@2": 0.9240016333751996,
|
| 245 |
+
"pass@4": 0.9427751138086263,
|
| 246 |
+
"pass@8": 0.9559837013558444,
|
| 247 |
+
"pass@16": 0.9669589357176731,
|
| 248 |
+
"pass@32": 0.9757400698048759,
|
| 249 |
+
"pass@64": 0.9820426961144421,
|
| 250 |
+
"pass@128": 0.9877300613496932
|
| 251 |
+
},
|
| 252 |
+
"2": {
|
| 253 |
+
"pass@1": 0.9987177051671733,
|
| 254 |
+
"pass@2": 0.9996395064978579,
|
| 255 |
+
"pass@4": 0.9999613177152248,
|
| 256 |
+
"pass@8": 0.9999996232076699,
|
| 257 |
+
"pass@16": 0.9999999999864305,
|
| 258 |
+
"pass@32": 1.0,
|
| 259 |
+
"pass@64": 1.0,
|
| 260 |
+
"pass@128": 1.0
|
| 261 |
+
},
|
| 262 |
+
"3": {
|
| 263 |
+
"pass@1": 0.9907670454545454,
|
| 264 |
+
"pass@2": 0.9960163892865667,
|
| 265 |
+
"pass@4": 0.9985778993534897,
|
| 266 |
+
"pass@8": 0.9996915957072215,
|
| 267 |
+
"pass@16": 0.9999815253902985,
|
| 268 |
+
"pass@32": 0.99999995938087,
|
| 269 |
+
"pass@64": 0.9999999999999987,
|
| 270 |
+
"pass@128": 1.0
|
| 271 |
+
},
|
| 272 |
+
"4": {
|
| 273 |
+
"pass@1": 0.9982664571005917,
|
| 274 |
+
"pass@2": 0.9998132687648512,
|
| 275 |
+
"pass@4": 0.999995557138198,
|
| 276 |
+
"pass@8": 0.9999999967656203,
|
| 277 |
+
"pass@16": 0.9999999999999998,
|
| 278 |
+
"pass@32": 1.0,
|
| 279 |
+
"pass@64": 1.0,
|
| 280 |
+
"pass@128": 1.0
|
| 281 |
+
},
|
| 282 |
+
"5": {
|
| 283 |
+
"pass@1": 0.9600317028985508,
|
| 284 |
+
"pass@2": 0.9691975493552438,
|
| 285 |
+
"pass@4": 0.9763000869456536,
|
| 286 |
+
"pass@8": 0.9828931121195829,
|
| 287 |
+
"pass@16": 0.989036439654314,
|
| 288 |
+
"pass@32": 0.9944838684919953,
|
| 289 |
+
"pass@64": 0.9981653755234783,
|
| 290 |
+
"pass@128": 1.0
|
| 291 |
+
},
|
| 292 |
+
"6": {
|
| 293 |
+
"pass@1": 0.9823379297994269,
|
| 294 |
+
"pass@2": 0.9910194058389551,
|
| 295 |
+
"pass@4": 0.9946701218221643,
|
| 296 |
+
"pass@8": 0.9965445299840145,
|
| 297 |
+
"pass@16": 0.9976712739922713,
|
| 298 |
+
"pass@32": 0.9983904225804993,
|
| 299 |
+
"pass@64": 0.9992893080034889,
|
| 300 |
+
"pass@128": 1.0
|
| 301 |
+
},
|
| 302 |
+
"7": {
|
| 303 |
+
"pass@1": 0.9681855130057804,
|
| 304 |
+
"pass@2": 0.9832421146056164,
|
| 305 |
+
"pass@4": 0.9914642009163593,
|
| 306 |
+
"pass@8": 0.9964758591421767,
|
| 307 |
+
"pass@16": 0.9990374180123244,
|
| 308 |
+
"pass@32": 0.9999126056145744,
|
| 309 |
+
"pass@64": 0.9999997855847184,
|
| 310 |
+
"pass@128": 1.0
|
| 311 |
+
},
|
| 312 |
+
"8": {
|
| 313 |
+
"pass@1": 0.9455765845070423,
|
| 314 |
+
"pass@2": 0.9712158284351782,
|
| 315 |
+
"pass@4": 0.9835400283591312,
|
| 316 |
+
"pass@8": 0.9910390348371692,
|
| 317 |
+
"pass@16": 0.9955726997113149,
|
| 318 |
+
"pass@32": 0.9980539040490879,
|
| 319 |
+
"pass@64": 0.9995741614459047,
|
| 320 |
+
"pass@128": 1.0
|
| 321 |
+
},
|
| 322 |
+
"9": {
|
| 323 |
+
"pass@1": 0.9390437874251497,
|
| 324 |
+
"pass@2": 0.9670264539818006,
|
| 325 |
+
"pass@4": 0.9783135702722786,
|
| 326 |
+
"pass@8": 0.9840906736702117,
|
| 327 |
+
"pass@16": 0.9879928605789021,
|
| 328 |
+
"pass@32": 0.9908513468886352,
|
| 329 |
+
"pass@64": 0.9930496212972972,
|
| 330 |
+
"pass@128": 0.9940119760479041
|
| 331 |
+
},
|
| 332 |
+
"11": {
|
| 333 |
+
"pass@1": 0.7309864457831325,
|
| 334 |
+
"pass@2": 0.811214839673655,
|
| 335 |
+
"pass@4": 0.8645121111555325,
|
| 336 |
+
"pass@8": 0.9001346785530842,
|
| 337 |
+
"pass@16": 0.9235781504819824,
|
| 338 |
+
"pass@32": 0.939017807747773,
|
| 339 |
+
"pass@64": 0.9485292552001391,
|
| 340 |
+
"pass@128": 0.9548192771084337
|
| 341 |
+
},
|
| 342 |
+
"12": {
|
| 343 |
+
"pass@1": 0.439042907523511,
|
| 344 |
+
"pass@2": 0.5317378835188704,
|
| 345 |
+
"pass@4": 0.6075961422729685,
|
| 346 |
+
"pass@8": 0.6683062360710545,
|
| 347 |
+
"pass@16": 0.7177272091161964,
|
| 348 |
+
"pass@32": 0.7598458853246168,
|
| 349 |
+
"pass@64": 0.7942021269976,
|
| 350 |
+
"pass@128": 0.8213166144200627
|
| 351 |
+
},
|
| 352 |
+
"13": {
|
| 353 |
+
"pass@1": 0.19227065826330533,
|
| 354 |
+
"pass@2": 0.23474754074858276,
|
| 355 |
+
"pass@4": 0.27791213361985206,
|
| 356 |
+
"pass@8": 0.32123267772057174,
|
| 357 |
+
"pass@16": 0.36547236780648024,
|
| 358 |
+
"pass@32": 0.412591392141311,
|
| 359 |
+
"pass@64": 0.46083134462740805,
|
| 360 |
+
"pass@128": 0.5042016806722689
|
| 361 |
+
},
|
| 362 |
+
"14": {
|
| 363 |
+
"pass@1": 0.20837902046783627,
|
| 364 |
+
"pass@2": 0.2522699670764838,
|
| 365 |
+
"pass@4": 0.2964683594923442,
|
| 366 |
+
"pass@8": 0.3416618793696011,
|
| 367 |
+
"pass@16": 0.3841336779597966,
|
| 368 |
+
"pass@32": 0.42375806001618826,
|
| 369 |
+
"pass@64": 0.4632207639904677,
|
| 370 |
+
"pass@128": 0.5029239766081871
|
| 371 |
+
},
|
| 372 |
+
"15": {
|
| 373 |
+
"pass@1": 0.19093276515151514,
|
| 374 |
+
"pass@2": 0.24199400501073715,
|
| 375 |
+
"pass@4": 0.2891956014020975,
|
| 376 |
+
"pass@8": 0.3326345282383242,
|
| 377 |
+
"pass@16": 0.37366558323041027,
|
| 378 |
+
"pass@32": 0.4128573661812689,
|
| 379 |
+
"pass@64": 0.4483166035224402,
|
| 380 |
+
"pass@128": 0.4727272727272727
|
| 381 |
+
},
|
| 382 |
+
"16": {
|
| 383 |
+
"pass@1": 0.15642806267806267,
|
| 384 |
+
"pass@2": 0.1904278691926329,
|
| 385 |
+
"pass@4": 0.22132350069489173,
|
| 386 |
+
"pass@8": 0.251268169779741,
|
| 387 |
+
"pass@16": 0.28180434335829546,
|
| 388 |
+
"pass@32": 0.3122157586188942,
|
| 389 |
+
"pass@64": 0.34211985927431315,
|
| 390 |
+
"pass@128": 0.3732193732193732
|
| 391 |
+
},
|
| 392 |
+
"17": {
|
| 393 |
+
"pass@1": 0.16779891304347827,
|
| 394 |
+
"pass@2": 0.21377104526336374,
|
| 395 |
+
"pass@4": 0.2616579632708955,
|
| 396 |
+
"pass@8": 0.3084358591590647,
|
| 397 |
+
"pass@16": 0.3485515761094292,
|
| 398 |
+
"pass@32": 0.38192734451252297,
|
| 399 |
+
"pass@64": 0.4116145438455866,
|
| 400 |
+
"pass@128": 0.43788819875776397
|
| 401 |
+
},
|
| 402 |
+
"18": {
|
| 403 |
+
"pass@1": 0.1518612132352941,
|
| 404 |
+
"pass@2": 0.1958187384205651,
|
| 405 |
+
"pass@4": 0.23828893419572547,
|
| 406 |
+
"pass@8": 0.27971765090438966,
|
| 407 |
+
"pass@16": 0.31909231139592203,
|
| 408 |
+
"pass@32": 0.3541919542192856,
|
| 409 |
+
"pass@64": 0.3879892602530647,
|
| 410 |
+
"pass@128": 0.4235294117647059
|
| 411 |
+
},
|
| 412 |
+
"19": {
|
| 413 |
+
"pass@1": 0.14004371279761904,
|
| 414 |
+
"pass@2": 0.17627703763592056,
|
| 415 |
+
"pass@4": 0.21033196631671033,
|
| 416 |
+
"pass@8": 0.24241868591666452,
|
| 417 |
+
"pass@16": 0.2725452956766527,
|
| 418 |
+
"pass@32": 0.3023936104609465,
|
| 419 |
+
"pass@64": 0.331830773125219,
|
| 420 |
+
"pass@128": 0.3601190476190476
|
| 421 |
+
},
|
| 422 |
+
"20": {
|
| 423 |
+
"pass@1": 0.1367421407185629,
|
| 424 |
+
"pass@2": 0.17771825934744678,
|
| 425 |
+
"pass@4": 0.21898993408009634,
|
| 426 |
+
"pass@8": 0.260066157867715,
|
| 427 |
+
"pass@16": 0.2989195527821917,
|
| 428 |
+
"pass@32": 0.3334463816599912,
|
| 429 |
+
"pass@64": 0.3631967204725436,
|
| 430 |
+
"pass@128": 0.38622754491017963
|
| 431 |
+
}
|
| 432 |
+
}
|
| 433 |
+
},
|
| 434 |
+
"movie_festival_awards": {
|
| 435 |
+
"count": 801152,
|
| 436 |
+
"correct": 471310,
|
| 437 |
+
"answer_accuracy": 0.5882903618788944,
|
| 438 |
+
"avg_response_len": 258.0569242790382,
|
| 439 |
+
"resp_tokens_sum": 206742821,
|
| 440 |
+
"pass_at_k": {
|
| 441 |
+
"pass@1": 0.5882903618788944,
|
| 442 |
+
"pass@2": 0.6212685622467475,
|
| 443 |
+
"pass@4": 0.6478714293112718,
|
| 444 |
+
"pass@8": 0.6709216329453926,
|
| 445 |
+
"pass@16": 0.6916683710373397,
|
| 446 |
+
"pass@32": 0.7106315691905148,
|
| 447 |
+
"pass@64": 0.728740000525103,
|
| 448 |
+
"pass@128": 0.7466048889598977
|
| 449 |
+
},
|
| 450 |
+
"per_op_pass_at_k": {
|
| 451 |
+
"10": {
|
| 452 |
+
"pass@1": 0.8983908582089553,
|
| 453 |
+
"pass@2": 0.9340132506757551,
|
| 454 |
+
"pass@4": 0.9530650669599133,
|
| 455 |
+
"pass@8": 0.9652801856862316,
|
| 456 |
+
"pass@16": 0.9745693164759084,
|
| 457 |
+
"pass@32": 0.9818461284408381,
|
| 458 |
+
"pass@64": 0.9871328155545905,
|
| 459 |
+
"pass@128": 0.991044776119403
|
| 460 |
+
},
|
| 461 |
+
"2": {
|
| 462 |
+
"pass@1": 0.9998660714285714,
|
| 463 |
+
"pass@2": 0.9999992969628797,
|
| 464 |
+
"pass@4": 1.0,
|
| 465 |
+
"pass@8": 1.0,
|
| 466 |
+
"pass@16": 1.0,
|
| 467 |
+
"pass@32": 1.0,
|
| 468 |
+
"pass@64": 1.0,
|
| 469 |
+
"pass@128": 1.0
|
| 470 |
+
},
|
| 471 |
+
"3": {
|
| 472 |
+
"pass@1": 0.9907069970845481,
|
| 473 |
+
"pass@2": 0.9970669721769471,
|
| 474 |
+
"pass@4": 0.9993563997831172,
|
| 475 |
+
"pass@8": 0.9999514691641971,
|
| 476 |
+
"pass@16": 0.9999996499221584,
|
| 477 |
+
"pass@32": 0.9999999999946803,
|
| 478 |
+
"pass@64": 1.0,
|
| 479 |
+
"pass@128": 1.0
|
| 480 |
+
},
|
| 481 |
+
"4": {
|
| 482 |
+
"pass@1": 0.9958196271929824,
|
| 483 |
+
"pass@2": 0.9977559342911083,
|
| 484 |
+
"pass@4": 0.9990211264710332,
|
| 485 |
+
"pass@8": 0.9997663197662907,
|
| 486 |
+
"pass@16": 0.9999856176620865,
|
| 487 |
+
"pass@32": 0.9999999740185194,
|
| 488 |
+
"pass@64": 0.9999999999999997,
|
| 489 |
+
"pass@128": 1.0
|
| 490 |
+
},
|
| 491 |
+
"5": {
|
| 492 |
+
"pass@1": 0.9548943014705882,
|
| 493 |
+
"pass@2": 0.9685079174386292,
|
| 494 |
+
"pass@4": 0.9784535587463331,
|
| 495 |
+
"pass@8": 0.9869293632462349,
|
| 496 |
+
"pass@16": 0.9934826994856965,
|
| 497 |
+
"pass@32": 0.9970310861536675,
|
| 498 |
+
"pass@64": 0.9985066302193607,
|
| 499 |
+
"pass@128": 1.0
|
| 500 |
+
},
|
| 501 |
+
"6": {
|
| 502 |
+
"pass@1": 0.9775483044164038,
|
| 503 |
+
"pass@2": 0.9891293716932861,
|
| 504 |
+
"pass@4": 0.9959075131381444,
|
| 505 |
+
"pass@8": 0.9991092920224423,
|
| 506 |
+
"pass@16": 0.9999352040645176,
|
| 507 |
+
"pass@32": 0.9999996662295679,
|
| 508 |
+
"pass@64": 0.9999999999997393,
|
| 509 |
+
"pass@128": 1.0
|
| 510 |
+
},
|
| 511 |
+
"7": {
|
| 512 |
+
"pass@1": 0.9744115901898734,
|
| 513 |
+
"pass@2": 0.9867456923402768,
|
| 514 |
+
"pass@4": 0.9912063912303684,
|
| 515 |
+
"pass@8": 0.9935151685224703,
|
| 516 |
+
"pass@16": 0.9954041601504686,
|
| 517 |
+
"pass@32": 0.9972167179953726,
|
| 518 |
+
"pass@64": 0.9990265956175474,
|
| 519 |
+
"pass@128": 1.0
|
| 520 |
+
},
|
| 521 |
+
"8": {
|
| 522 |
+
"pass@1": 0.9515531156156156,
|
| 523 |
+
"pass@2": 0.9743795222387744,
|
| 524 |
+
"pass@4": 0.9852795146102226,
|
| 525 |
+
"pass@8": 0.9899431408996546,
|
| 526 |
+
"pass@16": 0.9925003924523234,
|
| 527 |
+
"pass@32": 0.9950902478963195,
|
| 528 |
+
"pass@64": 0.9976578190444356,
|
| 529 |
+
"pass@128": 1.0
|
| 530 |
+
},
|
| 531 |
+
"9": {
|
| 532 |
+
"pass@1": 0.9379521704180064,
|
| 533 |
+
"pass@2": 0.9720591912043948,
|
| 534 |
+
"pass@4": 0.9858236963747689,
|
| 535 |
+
"pass@8": 0.9932814976290268,
|
| 536 |
+
"pass@16": 0.9968830356374474,
|
| 537 |
+
"pass@32": 0.9981725276413653,
|
| 538 |
+
"pass@64": 0.9992024635603814,
|
| 539 |
+
"pass@128": 1.0
|
| 540 |
+
},
|
| 541 |
+
"11": {
|
| 542 |
+
"pass@1": 0.7650545634920635,
|
| 543 |
+
"pass@2": 0.8431473409573809,
|
| 544 |
+
"pass@4": 0.8877359086066622,
|
| 545 |
+
"pass@8": 0.9145899228176874,
|
| 546 |
+
"pass@16": 0.9334761048558039,
|
| 547 |
+
"pass@32": 0.9489928847114996,
|
| 548 |
+
"pass@64": 0.9642010673849086,
|
| 549 |
+
"pass@128": 0.9809523809523809
|
| 550 |
+
},
|
| 551 |
+
"12": {
|
| 552 |
+
"pass@1": 0.4054615825688073,
|
| 553 |
+
"pass@2": 0.49957183534397626,
|
| 554 |
+
"pass@4": 0.5768995727598271,
|
| 555 |
+
"pass@8": 0.639355428961972,
|
| 556 |
+
"pass@16": 0.6924379381519293,
|
| 557 |
+
"pass@32": 0.7389465717283092,
|
| 558 |
+
"pass@64": 0.7833812207530858,
|
| 559 |
+
"pass@128": 0.8256880733944955
|
| 560 |
+
},
|
| 561 |
+
"13": {
|
| 562 |
+
"pass@1": 0.21805073302469136,
|
| 563 |
+
"pass@2": 0.2614506628511712,
|
| 564 |
+
"pass@4": 0.30509700407819385,
|
| 565 |
+
"pass@8": 0.34843945585161107,
|
| 566 |
+
"pass@16": 0.3892841325907048,
|
| 567 |
+
"pass@32": 0.42707158587605587,
|
| 568 |
+
"pass@64": 0.46350207303509766,
|
| 569 |
+
"pass@128": 0.5
|
| 570 |
+
},
|
| 571 |
+
"14": {
|
| 572 |
+
"pass@1": 0.19482566765578635,
|
| 573 |
+
"pass@2": 0.24658432440010283,
|
| 574 |
+
"pass@4": 0.2977982871762691,
|
| 575 |
+
"pass@8": 0.34710213397424194,
|
| 576 |
+
"pass@16": 0.39305571585018145,
|
| 577 |
+
"pass@32": 0.4354334888531387,
|
| 578 |
+
"pass@64": 0.4760201367236571,
|
| 579 |
+
"pass@128": 0.516320474777448
|
| 580 |
+
},
|
| 581 |
+
"15": {
|
| 582 |
+
"pass@1": 0.15263310185185186,
|
| 583 |
+
"pass@2": 0.20657633724603863,
|
| 584 |
+
"pass@4": 0.26040626837154607,
|
| 585 |
+
"pass@8": 0.31066200412971595,
|
| 586 |
+
"pass@16": 0.3575054534309268,
|
| 587 |
+
"pass@32": 0.40181191645690056,
|
| 588 |
+
"pass@64": 0.4460592807353767,
|
| 589 |
+
"pass@128": 0.49074074074074076
|
| 590 |
+
},
|
| 591 |
+
"16": {
|
| 592 |
+
"pass@1": 0.15613477138643067,
|
| 593 |
+
"pass@2": 0.1863313822497852,
|
| 594 |
+
"pass@4": 0.21273005393131156,
|
| 595 |
+
"pass@8": 0.23865739981671225,
|
| 596 |
+
"pass@16": 0.2676959517806339,
|
| 597 |
+
"pass@32": 0.3011310763692745,
|
| 598 |
+
"pass@64": 0.3362407178410369,
|
| 599 |
+
"pass@128": 0.37168141592920356
|
| 600 |
+
},
|
| 601 |
+
"17": {
|
| 602 |
+
"pass@1": 0.1378012048192771,
|
| 603 |
+
"pass@2": 0.17401619272365054,
|
| 604 |
+
"pass@4": 0.21124320340981484,
|
| 605 |
+
"pass@8": 0.24873698272180494,
|
| 606 |
+
"pass@16": 0.28468715470923933,
|
| 607 |
+
"pass@32": 0.31684364503562207,
|
| 608 |
+
"pass@64": 0.3460631347877581,
|
| 609 |
+
"pass@128": 0.37650602409638556
|
| 610 |
+
},
|
| 611 |
+
"18": {
|
| 612 |
+
"pass@1": 0.16940524193548387,
|
| 613 |
+
"pass@2": 0.20793830962661927,
|
| 614 |
+
"pass@4": 0.24442847708552565,
|
| 615 |
+
"pass@8": 0.27696590133200394,
|
| 616 |
+
"pass@16": 0.3047539165997947,
|
| 617 |
+
"pass@32": 0.329140512075412,
|
| 618 |
+
"pass@64": 0.3525837977178592,
|
| 619 |
+
"pass@128": 0.3774193548387097
|
| 620 |
+
},
|
| 621 |
+
"19": {
|
| 622 |
+
"pass@1": 0.13812311178247735,
|
| 623 |
+
"pass@2": 0.16759305790137258,
|
| 624 |
+
"pass@4": 0.19758813267676884,
|
| 625 |
+
"pass@8": 0.2284911534750015,
|
| 626 |
+
"pass@16": 0.2603002938970115,
|
| 627 |
+
"pass@32": 0.29249731296624343,
|
| 628 |
+
"pass@64": 0.3260332407783438,
|
| 629 |
+
"pass@128": 0.36253776435045315
|
| 630 |
+
},
|
| 631 |
+
"20": {
|
| 632 |
+
"pass@1": 0.13072447447447447,
|
| 633 |
+
"pass@2": 0.16936079780567978,
|
| 634 |
+
"pass@4": 0.2094049935762534,
|
| 635 |
+
"pass@8": 0.25098284669882537,
|
| 636 |
+
"pass@16": 0.291417867530838,
|
| 637 |
+
"pass@32": 0.32739810777438544,
|
| 638 |
+
"pass@64": 0.35806392636422313,
|
| 639 |
+
"pass@128": 0.3813813813813814
|
| 640 |
+
}
|
| 641 |
+
}
|
| 642 |
+
}
|
| 643 |
+
}
|
| 644 |
+
}
|
| 645 |
+
]
|