cruxtok / t1_seed42 /eval.jsonl
TimothDevA's picture
CruxTok (T1) and NCM baseline tokenizers trained on XSum
16772ec verified
Raw History Blame Contribute Delete
5.47 kB
{"step": 5000, "accuracy": [54.79375076293945, 62.29166793823242, 72.00729370117188, 82.6812515258789, 92.62604522705078, 96.72187805175781, 98.47083282470703, 99.03854370117188, 99.12604522705078], "accuracy_text": [19.826311111450195, 33.12084197998047, 50.34922409057617, 69.28307342529297, 86.91980743408203, 94.1869888305664, 97.28750610351562, 98.2945327758789, 98.44973754882812], "ce": [3.2460713386535645, 2.63155460357666, 1.8734214305877686, 1.0819611549377441, 0.41279634833335876, 0.20239666104316711, 0.12097768485546112, 0.08711159974336624, 0.08110690861940384], "utilization": [47.314453125, 68.8232421875, 84.716796875, 91.4306640625, 95.2392578125, 94.7509765625, 96.0693359375, 99.21875, 65.7958984375], "perplexity": [1523.93489841884, 1833.5748810035898, 1859.381016057292, 1811.11856386743, 1606.1336675590878, 1795.7360298881833, 1951.8247166159993, 2115.511783240834, 1642.6594246845148]}
{"step": 10000, "accuracy": [55.98125076293945, 64.78020477294922, 74.56562805175781, 84.87604522705078, 93.53020477294922, 97.3343734741211, 98.703125, 99.1624984741211, 99.2406234741211], "accuracy_text": [21.925350189208984, 37.531410217285156, 54.89282989501953, 73.18366241455078, 88.5291976928711, 95.27531433105469, 97.70140075683594, 98.5162582397461, 98.65299224853516], "ce": [3.1202988624572754, 2.4176151752471924, 1.680463433265686, 0.9490679502487183, 0.3663715124130249, 0.17349804937839508, 0.10628468543291092, 0.07730516791343689, 0.07276992499828339], "utilization": [42.7490234375, 63.6474609375, 84.9853515625, 88.720703125, 93.5791015625, 93.4814453125, 96.484375, 98.7060546875, 56.591796875], "perplexity": [1378.6484962820055, 1592.9030164311419, 1641.056830632925, 1466.89763724492, 1386.4593059188473, 1735.4334849232175, 1939.0231868938245, 1895.5098250269916, 1177.0408571095247]}
{"step": 15000, "accuracy": [56.25728988647461, 66.01145935058594, 76.3187484741211, 86.35520935058594, 94.23542022705078, 97.31354522705078, 98.69062805175781, 99.16458129882812, 99.24791717529297], "accuracy_text": [22.42793846130371, 39.72283935546875, 58.006282806396484, 75.80377197265625, 89.77826690673828, 95.23651123046875, 97.67922973632812, 98.51995849609375, 98.66592407226562], "ce": [3.0898919105529785, 2.309372663497925, 1.5377250909805298, 0.8394669890403748, 0.33260130882263184, 0.174981489777565, 0.10495343059301376, 0.07660169154405594, 0.07079881429672241], "utilization": [42.1142578125, 63.671875, 87.20703125, 88.916015625, 93.1640625, 92.7734375, 97.3876953125, 99.267578125, 56.4453125], "perplexity": [1354.1385987788587, 1675.4302282706426, 1778.044092379772, 1504.512340163417, 1471.4456407581142, 1605.9628889194328, 2046.688939298212, 2186.8563960395845, 1131.7122021635212]}
{"step": 20000, "accuracy": [56.561458587646484, 66.60624694824219, 77.36145782470703, 86.94166564941406, 94.5374984741211, 97.62916564941406, 98.88021087646484, 99.2281265258789, 99.29166412353516], "accuracy_text": [22.96563148498535, 40.77605438232422, 59.85218048095703, 76.8403549194336, 90.3104248046875, 95.7945327758789, 98.013671875, 98.63082122802734, 98.7435302734375], "ce": [3.058846950531006, 2.244004726409912, 1.4540947675704956, 0.7876423597335815, 0.32247376441955566, 0.16117192804813385, 0.09811964631080627, 0.07403852045536041, 0.07015985995531082], "utilization": [40.13671875, 63.6474609375, 89.501953125, 90.234375, 91.7236328125, 93.65234375, 97.4853515625, 99.51171875, 53.3935546875], "perplexity": [1272.9619831915318, 1718.5528054983597, 1898.5944590349425, 1683.992351956181, 1425.0761553132572, 1844.5355950471774, 2192.9588683071197, 2318.587616647525, 979.8258756106333]}
{"step": 25000, "accuracy": [56.907291412353516, 66.86666870117188, 77.44271087646484, 87.43228912353516, 95.10832977294922, 97.94166564941406, 98.99791717529297, 99.2718734741211, 99.3125], "accuracy_text": [23.562454223632812, 41.22875213623047, 59.988914489746094, 77.70879364013672, 91.32298278808594, 96.3488540649414, 98.22246551513672, 98.70842742919922, 98.78048706054688], "ce": [3.023197889328003, 2.226142644882202, 1.4279580116271973, 0.7442720532417297, 0.2919045686721802, 0.14680874347686768, 0.09102652221918106, 0.07105451822280884, 0.06896264106035233], "utilization": [36.474609375, 57.6904296875, 87.2802734375, 90.4296875, 91.6015625, 91.259765625, 94.775390625, 98.8037109375, 44.7021484375], "perplexity": [1146.9842177240826, 1423.66411399845, 1681.6251963731768, 1519.6354622330805, 1329.361274648958, 1447.713187674207, 1756.7335627615232, 1906.7680339542387, 611.3863270546876]}
{"step": 30000, "accuracy": [56.84166717529297, 66.74583435058594, 77.51249694824219, 87.80416870117188, 95.1312484741211, 98.02291870117188, 99.015625, 99.30208587646484, 99.32707977294922], "accuracy_text": [23.451589584350586, 41.019954681396484, 60.114559173583984, 78.37028503417969, 91.36548614501953, 96.49298095703125, 98.2538833618164, 98.76200866699219, 98.80635833740234], "ce": [3.0156617164611816, 2.2187554836273193, 1.4125587940216064, 0.7218500375747681, 0.29246342182159424, 0.14466850459575653, 0.08965033292770386, 0.06952819228172302, 0.06726808845996857], "utilization": [36.42578125, 57.2998046875, 88.18359375, 90.380859375, 91.5283203125, 90.966796875, 94.6044921875, 99.365234375, 44.384765625], "perplexity": [1152.170911136179, 1488.6486009826322, 1749.2406616511873, 1583.9389963130232, 1354.5228469281071, 1497.7616615306704, 1799.9907485907074, 2010.8431966535475, 665.9026279054835]}