cruxtok / t0cap_seed42 /eval.jsonl
TimothDevA's picture
CruxTok (T1) and NCM baseline tokenizers trained on XSum
16772ec verified
Raw History Blame Contribute Delete
5.42 kB
{"step": 5000, "accuracy": [54.34687423706055, 60.140625, 65.1968765258789, 69.5218734741211, 74.58541870117188, 79.609375, 85.63541412353516, 89.6187515258789, 95.05937194824219], "accuracy_text": [19.17036247253418, 29.369918823242188, 38.29637908935547, 45.95343780517578, 54.918697357177734, 63.83037567138672, 74.51958465576172, 81.58536529541016, 91.23614501953125], "ce": [3.5326426029205322, 2.9980578422546387, 2.4724016189575195, 2.0435757637023926, 1.6318587064743042, 1.268642544746399, 0.9179883599281311, 0.682036280632019, 0.4159570634365082], "utilization": [7.3486328125, 10.8154296875, 21.484375, 28.4912109375, 40.4541015625, 50.68359375, 58.4228515625, 46.5576171875, 72.36328125], "perplexity": [130.9318166882287, 60.93954789871098, 93.1573349044893, 112.80948003747488, 126.39419267768109, 134.70961630531963, 132.3233649094053, 156.3945517802934, 68.08224614434756]}
{"step": 10000, "accuracy": [55.84166717529297, 62.12187576293945, 67.73542022705078, 72.53958129882812, 77.88021087646484, 82.83958435058594, 88.484375, 91.85832977294922, 96.70625305175781], "accuracy_text": [21.856985092163086, 32.97856521606445, 42.830745697021484, 51.33591842651367, 60.76496505737305, 69.56208801269531, 79.57317352294922, 85.55986785888672, 94.1592788696289], "ce": [3.34218692779541, 2.711482048034668, 2.162088632583618, 1.705936312675476, 1.3034499883651733, 0.9804188013076782, 0.6839263439178467, 0.49466997385025024, 0.2837505638599396], "utilization": [16.6015625, 20.1416015625, 37.646484375, 48.974609375, 62.1826171875, 64.2578125, 65.966796875, 51.3671875, 72.75390625], "perplexity": [511.7939955434662, 112.3994731170562, 166.19694234383218, 170.2669072612785, 165.1594976208472, 142.0599621397199, 130.465150844885, 150.65661952103477, 89.12860766259386]}
{"step": 15000, "accuracy": [56.24583435058594, 62.86979293823242, 68.93645477294922, 74.08229064941406, 79.45104217529297, 84.37604522705078, 89.73645782470703, 92.95104217529297, 97.2406234741211], "accuracy_text": [22.498151779174805, 34.2960090637207, 44.95380783081055, 54.04841232299805, 63.55691146850586, 72.28750610351562, 81.79785919189453, 87.5, 95.10901641845703], "ce": [3.2963075637817383, 2.609851360321045, 2.035344362258911, 1.5629961490631104, 1.1664491891860962, 0.8629749417304993, 0.5945923328399658, 0.4247514307498932, 0.2376238852739334], "utilization": [21.58203125, 25.048828125, 45.80078125, 57.6904296875, 69.7509765625, 65.3564453125, 66.162109375, 50.4150390625, 72.6806640625], "perplexity": [695.4064788502327, 132.61772243786194, 190.33187963127475, 187.45854002830737, 191.57466604876723, 140.1668394739967, 125.01020408727094, 151.43837777731662, 93.04816797735988]}
{"step": 20000, "accuracy": [56.485416412353516, 63.35729217529297, 69.62395477294922, 74.82499694824219, 80.39167022705078, 85.484375, 90.5250015258789, 93.6343765258789, 97.45625305175781], "accuracy_text": [22.99334716796875, 35.223575592041016, 46.199188232421875, 55.36585235595703, 65.22173309326172, 74.25350952148438, 83.19475555419922, 88.70842742919922, 95.48780822753906], "ce": [3.2694475650787354, 2.5511386394500732, 1.9699078798294067, 1.4940296411514282, 1.0963995456695557, 0.7958168387413025, 0.5467096567153931, 0.3858109414577484, 0.22150662541389465], "utilization": [26.0009765625, 28.5888671875, 51.611328125, 62.451171875, 72.3876953125, 65.625, 65.7958984375, 49.951171875, 72.4609375], "perplexity": [827.3374099673713, 147.82848875514574, 214.84706568805413, 194.2287852938266, 194.63245208082347, 141.79210217128258, 126.01109911704962, 151.55367111005665, 94.31519425789206]}
{"step": 25000, "accuracy": [56.657291412353516, 63.77396011352539, 69.94895935058594, 75.38021087646484, 81.00416564941406, 85.97604370117188, 90.78646087646484, 93.86145782470703, 97.62395477294922], "accuracy_text": [23.29637908935547, 35.90909194946289, 46.76644515991211, 56.345157623291016, 66.30451202392578, 75.1238021850586, 83.65669250488281, 89.11123657226562, 95.78529357910156], "ce": [3.246438503265381, 2.5143277645111084, 1.9254882335662842, 1.450392723083496, 1.0542837381362915, 0.7612700462341309, 0.5246148109436035, 0.3701670467853546, 0.20957987010478973], "utilization": [29.4189453125, 30.9326171875, 54.39453125, 65.5029296875, 73.291015625, 65.52734375, 65.087890625, 49.9755859375, 72.3876953125], "perplexity": [926.9544351301709, 153.23561433344636, 231.3666269464052, 199.34353446078825, 191.20870286591926, 137.90416279576615, 126.70067217708873, 149.06736918590545, 96.1642973025234]}
{"step": 30000, "accuracy": [56.75728988647461, 63.96041488647461, 70.14895629882812, 75.73958587646484, 81.16458129882812, 86.04270935058594, 90.99166870117188, 94.015625, 97.66041564941406], "accuracy_text": [23.458980560302734, 36.27494430541992, 47.11936569213867, 56.977088928222656, 66.59091186523438, 75.24205780029297, 84.02069854736328, 89.38469696044922, 95.84996032714844], "ce": [3.23435378074646, 2.495004415512085, 1.9029996395111084, 1.4246848821640015, 1.0380394458770752, 0.7538253664970398, 0.5143020153045654, 0.3601054549217224, 0.20502860844135284], "utilization": [31.640625, 32.4951171875, 56.4697265625, 67.0654296875, 74.072265625, 65.4541015625, 64.8681640625, 50.1220703125, 72.4365234375], "perplexity": [995.534502474921, 161.337582380827, 237.87095598663637, 206.06728145241632, 191.96256458392781, 135.93205310494784, 127.57912533833478, 146.26251585017687, 97.97118498733744]}