cruxtok / t0cap_matched /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": [53.212501525878906, 57.42499923706055, 61.85729217529297, 66.28020477294922, 72.75, 79.13749694824219, 87.21979522705078, 91.26354217529297, 96.57604217529297], "accuracy_text": [17.762380599975586, 24.85587501525879, 32.44826126098633, 40.21064376831055, 51.664817810058594, 62.99334716796875, 77.33000946044922, 84.50296020507812, 93.92646026611328], "ce": [3.503490924835205, 2.8185951709747314, 2.3135547637939453, 1.8987091779708862, 1.4300987720489502, 1.0507631301879883, 0.6727535724639893, 0.502348005771637, 0.27380239963531494], "utilization": [28.6376953125, 50.1708984375, 40.33203125, 21.19140625, 21.8017578125, 17.96875, 15.4296875, 6.2255859375, 31.6650390625], "perplexity": [936.9683089475537, 1344.1670879501537, 925.1250105943946, 135.37318233196393, 155.09484999805014, 116.18998023565207, 89.03961497265546, 40.22143538704933, 153.62241451274926]}
{"step": 10000, "accuracy": [54.03853988647461, 58.83333206176758, 64.26145935058594, 69.38541412353516, 76.75729370117188, 83.40625, 90.60729217529297, 93.98332977294922, 98.15625], "accuracy_text": [18.75831413269043, 27.213600158691406, 36.69068908691406, 45.726165771484375, 58.77124786376953, 70.5654067993164, 83.33887481689453, 89.32742309570312, 96.7294921875], "ce": [3.422107696533203, 2.6940462589263916, 2.123539924621582, 1.6633046865463257, 1.1756455898284912, 0.8036051392555237, 0.4717015326023102, 0.3293425440788269, 0.1590157300233841], "utilization": [32.7392578125, 58.7158203125, 43.84765625, 25.9765625, 28.61328125, 24.51171875, 24.169921875, 8.984375, 55.5908203125], "perplexity": [1020.0326273258261, 1748.5534958309022, 1030.3590384171284, 255.76402873799273, 221.10817838771123, 208.12533860637004, 182.87976701832994, 73.7914468367675, 251.62545791675865]}
{"step": 15000, "accuracy": [54.568748474121094, 60.68541717529297, 66.67292022705078, 72.18854522705078, 79.27291870117188, 85.41874694824219, 91.97291564941406, 95.12812805175781, 98.45625305175781], "accuracy_text": [19.508499145507812, 30.35291862487793, 40.90354919433594, 50.66888427734375, 63.23540115356445, 74.13525390625, 85.76126861572266, 91.35809326171875, 97.26164245605469], "ce": [3.443415641784668, 2.616473913192749, 2.024202585220337, 1.5482820272445679, 1.0750923156738281, 0.7210527062416077, 0.41320720314979553, 0.27610570192337036, 0.13386695086956024], "utilization": [27.001953125, 57.03125, 46.5576171875, 29.638671875, 33.3740234375, 27.685546875, 29.3701171875, 11.572265625, 68.9208984375], "perplexity": [843.8422620312075, 1715.9488661503397, 1066.1287329441939, 327.1443329685047, 289.5716238634691, 261.6600560956132, 257.4115963019083, 121.41742356250575, 338.19243715241373]}
{"step": 20000, "accuracy": [54.37187576293945, 61.248958587646484, 68.01041412353516, 74.19999694824219, 81.48750305175781, 87.63021087646484, 93.6312484741211, 96.11458587646484, 98.62083435058594], "accuracy_text": [19.164819717407227, 31.387657165527344, 43.287139892578125, 54.236881256103516, 67.161865234375, 78.05802154541016, 88.702880859375, 93.10791015625, 97.55358123779297], "ce": [3.4246578216552734, 2.5127182006835938, 1.8760426044464111, 1.3933480978012085, 0.9295699596405029, 0.6015011668205261, 0.3386856019496918, 0.23001256585121155, 0.12257106602191925], "utilization": [23.4130859375, 57.177734375, 49.0234375, 32.7392578125, 38.427734375, 31.8115234375, 34.27734375, 13.5986328125, 76.0009765625], "perplexity": [781.2966820113413, 1757.7449285141902, 1084.9180355494564, 386.28056183935485, 374.1097122966993, 329.6584370895928, 331.3581345873344, 161.4191506528769, 389.46282182534964]}
{"step": 25000, "accuracy": [54.712501525878906, 62.01874923706055, 69.13957977294922, 75.48958587646484, 82.85832977294922, 88.75208282470703, 94.24270629882812, 96.6656265258789, 98.7593765258789], "accuracy_text": [19.8115291595459, 32.74390411376953, 45.30118179321289, 56.524391174316406, 69.59349822998047, 80.04804229736328, 89.78750610351562, 94.08536529541016, 97.79933166503906], "ce": [3.377192735671997, 2.4383018016815186, 1.7972086668014526, 1.3069918155670166, 0.8591858148574829, 0.5518490672111511, 0.3081727623939514, 0.2099113017320633, 0.11539354175329208], "utilization": [21.875, 56.640625, 51.46484375, 35.8154296875, 42.822265625, 34.619140625, 37.5732421875, 15.0146484375, 80.078125], "perplexity": [737.6826493238182, 1782.457467788626, 1156.5689732132591, 481.827457823869, 499.3417301766279, 433.61576743572493, 442.51335549606955, 225.29719274115868, 461.14357208087625]}
{"step": 30000, "accuracy": [54.42499923706055, 61.759376525878906, 69.31458282470703, 75.921875, 83.54479217529297, 89.49270629882812, 94.76979064941406, 96.8531265258789, 98.78229522705078], "accuracy_text": [19.327421188354492, 32.313377380371094, 45.60421371459961, 57.29120635986328, 70.8111572265625, 81.36178588867188, 90.72246551513672, 94.41796112060547, 97.8399887084961], "ce": [3.3955657482147217, 2.450507879257202, 1.7756669521331787, 1.2720072269439697, 0.8213236331939697, 0.5197571516036987, 0.2890416979789734, 0.19958478212356567, 0.1130252555012703], "utilization": [21.6552734375, 56.103515625, 53.1982421875, 38.916015625, 46.142578125, 36.71875, 39.9658203125, 15.673828125, 82.763671875], "perplexity": [735.4516851069714, 1760.5046327899727, 1141.1894710955467, 537.4602178484665, 522.2748436525364, 484.24891789658665, 497.8270670713057, 269.0723331349587, 530.6274898378966]}