step,train_loss,val_loss,lr,grad_norm,dt_ms,tok_per_sec,timer_data,timer_fwd,timer_loss,timer_bwd,timer_clip,timer_optim,mem_gpu_mb 0,1.920389,1.888691,0.000003,1.139446,16001.439453,32765.052265,2.924960,4222.877640,6.421504,4663.327698,0.003712,62.615009,107212.937500 1,1.898834,1.888691,0.000006,1.156716,8280.115234,63318.925541,4.027040,3667.506577,6.380544,4544.214996,0.003840,49.815872,108908.937500 2,1.910765,1.888691,0.000009,1.280252,9915.143555,52877.499666,2.557024,5223.525711,6.353568,4624.979370,0.003520,49.617279,108908.937500 3,1.936233,1.888691,0.000012,1.266597,6216.728027,84335.038897,2.602912,1991.833389,6.372544,4158.053223,0.003744,49.909855,108908.937500 4,1.905092,1.888691,0.000015,1.160154,6238.630371,84038.958684,3.123872,1995.341507,6.390656,4176.538696,0.003392,49.345730,108908.937500 5,1.966748,1.888691,0.000018,1.149405,6276.423828,83532.918483,3.054464,2005.503036,6.367168,4204.320740,0.003712,49.326176,108908.937500 6,1.904285,1.888691,0.000021,1.043706,6345.527344,82623.235485,3.235392,2013.193588,6.432832,4265.340576,0.003584,49.419582,108908.937500 7,1.854531,1.888691,0.000024,1.021607,6402.649902,81886.095288,3.106528,2033.093323,6.384544,4302.618103,0.003872,49.572575,108908.937500 8,1.830776,1.888691,0.000027,0.987560,6419.801270,81667.325512,3.049472,2037.534195,6.417824,4315.349182,0.003776,49.563393,108908.937500 9,1.852669,1.888691,0.000030,0.884296,6426.617676,81580.704882,3.127136,2048.292542,6.397856,4311.555664,0.003648,49.356930,108908.937500 10,1.806110,1.888691,0.000033,0.829637,6450.763184,81275.344495,3.055648,2058.223145,6.712832,4325.536438,0.003744,49.371647,108908.937500 11,1.792623,1.888691,0.000036,1.050088,6435.643066,81466.295534,3.116672,2058.158371,6.560000,4310.119324,0.003424,49.848480,108908.937500 12,1.784030,1.888691,0.000039,1.042397,6422.322754,81635.261897,3.118080,2025.747787,6.376992,4329.702515,0.003328,49.523106,108908.937500 13,1.786141,1.888691,0.000042,1.344665,6375.977539,82228.646006,3.168352,2025.594009,6.385952,4283.134155,0.003232,49.667774,108908.937500 14,1.809938,1.888691,0.000045,1.294165,6358.028320,82460.784002,3.099840,2027.823807,6.402336,4263.457825,0.003584,49.421951,108908.937500 15,1.793668,1.888691,0.000048,1.255733,6368.768066,82321.729184,3.235840,2042.357132,6.383040,4259.310303,0.003648,49.683136,108908.937500 16,1.765961,1.888691,0.000051,1.088759,6343.388184,82651.098250,3.196384,2021.261993,6.380608,4254.785339,0.003328,49.924606,108908.937500 17,1.712484,1.888691,0.000054,0.790309,6323.919434,82905.547028,3.168512,2022.918533,6.392640,4234.136108,0.003392,49.469185,108908.937500 18,1.731035,1.888691,0.000057,0.858386,6329.273438,82835.416289,3.023552,2017.821060,6.566048,4244.642883,0.003520,49.324898,108908.937500 19,1.743202,1.888691,0.000060,0.738515,6334.254883,82770.272068,3.186336,2031.902344,6.383616,4235.263062,0.003808,49.672001,108908.937500 20,1.718590,1.888691,0.000063,1.169419,6330.504883,82819.302679,3.075872,2022.275513,6.377664,4241.392334,0.003168,49.555038,108908.937500 21,1.767774,1.888691,0.000066,0.992476,6338.120605,82719.789136,3.131392,2018.031113,6.384160,4253.191162,0.003776,49.561214,108908.937500 22,1.697396,1.888691,0.000069,0.690903,6326.690430,82869.235634,3.174304,2019.088104,6.386336,4240.617859,0.003232,49.572674,108908.937500 23,1.707077,1.888691,0.000072,0.763766,6371.410645,82287.585788,3.158560,2050.045227,6.402144,4254.645264,0.003424,49.334175,108908.937500 24,1.671977,1.888691,0.000075,0.777583,6375.658691,82232.758273,3.250304,2069.236313,6.380576,4239.289062,0.003264,49.613728,108908.937500 25,1.739844,1.888691,0.000078,0.823003,6332.830566,82788.887923,3.150048,2010.980927,6.399552,4254.874023,0.003232,49.569569,108908.937500 26,1.652054,1.888691,0.000081,0.907736,6340.053223,82694.573939,3.147936,2025.912552,6.386656,4247.142090,0.003424,49.651134,108908.937500 27,1.654510,1.888691,0.000084,0.848301,6341.171875,82679.985708,3.139616,2023.191956,6.380128,4250.949646,0.003776,49.672672,108908.937500 28,1.691144,1.888691,0.000087,0.762472,6357.385742,82469.118795,3.161920,2045.897415,6.377600,4244.729370,0.003616,49.393024,108908.937500 29,1.663364,1.888691,0.000090,0.902108,6359.409668,82442.872432,3.139968,2024.028030,6.401888,4268.531555,0.003296,49.442944,108908.937500 30,1.633048,1.888691,0.000093,0.708434,6332.022949,82799.447223,3.128320,2011.973206,6.372000,4253.224731,0.003680,49.483425,108908.937500 31,1.700897,1.888691,0.000096,0.594090,6339.412598,82702.930583,3.130432,2024.291840,6.383232,4248.282654,0.003840,49.497410,108908.937500 32,1.608716,1.888691,0.000099,0.632816,6395.619629,81976.107152,3.177792,2066.547470,6.404288,4262.028076,0.003424,49.590847,108908.937500 33,1.657396,1.888691,0.000102,0.638838,6355.234863,82497.029815,3.097952,2024.498062,6.382944,4263.747192,0.003680,49.657726,108908.937500 34,1.648264,1.888691,0.000105,0.633965,6350.555176,82557.821401,3.142144,2026.387573,6.398528,4257.194885,0.003584,49.585888,108908.937500 35,1.660285,1.888691,0.000108,0.775887,6348.233398,82588.015767,3.069088,2080.110306,6.365472,4201.257446,0.003616,49.536991,108908.937500 36,1.631099,1.888691,0.000111,0.584269,6381.269531,82160.453720,3.076288,2063.766998,6.383360,4250.165283,0.003232,49.998657,108908.937500 37,1.626856,1.888691,0.000114,0.680088,6330.014160,82825.723092,3.160064,2013.283936,6.393504,4249.904907,0.003488,49.434078,108908.937500 38,1.619444,1.888691,0.000117,0.652532,6337.687500,82725.442048,3.152288,2020.087616,6.378720,4250.564758,0.003392,49.675808,108908.937500 39,1.642475,1.888691,0.000120,0.772394,6377.823242,82204.849537,3.183968,2075.630951,6.376000,4235.463989,0.003872,49.339359,108908.937500 40,1.600698,1.888691,0.000123,0.854414,6376.743652,82218.766910,3.233664,2071.577423,6.401248,4237.967407,0.003424,49.717503,108908.937500 41,1.580887,1.888691,0.000126,0.981567,6324.282715,82900.784743,3.075968,2022.029312,6.382144,4235.373962,0.003584,49.572098,108908.937500 42,1.624956,1.888691,0.000129,0.872412,6332.328125,82795.456845,3.078176,2018.147095,6.668672,4246.871277,0.003040,49.719967,108908.937500 43,1.623077,1.888691,0.000132,0.637372,6346.729980,82607.579275,3.262944,2024.297745,6.368064,4255.354919,0.003360,49.534527,108908.937500 44,1.554411,1.888691,0.000135,0.831163,6327.952637,82852.706096,3.273952,2012.035049,6.378240,4248.672424,0.003520,49.655296,108908.937500 45,1.633371,1.888691,0.000138,0.773916,6346.301758,82613.153299,3.143520,2037.514160,6.385248,4241.558044,0.003392,49.806145,108908.937500 46,1.607605,1.888691,0.000141,0.742652,6313.643066,83040.487795,3.063552,2018.990524,6.388064,4227.843445,0.003456,49.511295,108908.937500 47,1.635939,1.888691,0.000144,0.691577,6347.576172,82596.566911,3.112992,2024.110214,6.399936,4256.378906,0.003808,49.718784,108908.937500 48,1.633764,1.888691,0.000147,0.804403,6336.690918,82738.452417,3.320224,2021.176804,6.378688,4248.116577,0.003328,49.573761,108908.937500 49,1.607873,1.888691,0.000150,0.621125,6305.447266,83148.423564,3.180544,2018.955246,6.371584,4219.534424,0.003648,49.582783,108908.937500 50,1.639636,1.888691,0.000153,0.711546,6370.114746,82304.325887,3.150752,2078.611542,6.378656,4224.542603,0.003168,49.543327,108908.937500 51,1.656035,1.888691,0.000156,0.796302,6345.472168,82623.953919,3.182784,2031.570267,6.604704,4246.810364,0.003456,49.479839,108908.937500 52,1.662412,1.888691,0.000159,0.705655,6316.856445,82998.245178,3.135296,2016.884125,6.378144,4232.103760,0.003520,49.502239,108908.937500 53,1.581693,1.888691,0.000162,0.666786,6342.799805,82658.765237,3.154784,2028.590302,6.382144,4247.130981,0.003456,49.700607,108908.937500 54,1.594439,1.888691,0.000165,0.847070,6319.421875,82964.551247,3.180128,2024.629105,6.375776,4227.748169,0.003680,49.578304,108908.937500 55,1.670181,1.888691,0.000168,0.809112,6371.773926,82282.894231,3.222016,2057.925903,6.390016,4246.990723,0.003520,49.358879,108908.937500 56,1.632861,1.888691,0.000171,0.773693,6320.738281,82947.272403,3.153024,2018.593735,6.379328,4235.251831,0.003232,49.522881,108908.937500 57,1.572145,1.888691,0.000174,0.892174,6340.897461,82683.563838,3.247520,2020.747467,6.376864,4253.231934,0.003328,49.488415,108908.937500 58,1.589554,1.888691,0.000177,0.677442,6324.347656,82899.933479,3.095200,2026.461670,6.375456,4230.713440,0.003424,49.848511,108908.937500 59,1.586414,1.888691,0.000180,0.757773,6376.862305,82217.237091,3.191552,2054.159515,6.498272,4255.847351,0.003264,49.321217,108908.937500 60,1.630998,1.888691,0.000183,0.753521,6323.771484,82907.486663,3.224288,2018.225296,6.375328,4238.561157,0.002944,49.535168,108908.937500 61,1.556511,1.888691,0.000186,0.894534,6345.840820,82619.154001,3.159488,2025.426559,6.395200,4251.989136,0.003328,50.869598,108908.937500 62,1.594290,1.888691,0.000189,0.849950,6348.363281,82586.326077,3.166304,2026.310699,6.374784,4255.094788,0.003360,49.573601,108908.937500 63,1.591010,1.888691,0.000192,0.721222,6382.641113,82142.798051,3.106112,2080.148941,6.377664,4235.520752,0.003712,49.620064,108908.937500 64,1.558378,1.888691,0.000195,0.834214,6370.168457,82303.631927,3.276832,2050.656693,6.605248,4252.439270,0.003232,49.351906,108908.937500 65,1.605214,1.888691,0.000198,0.679925,6333.108887,82785.249611,3.083712,2021.721039,6.377664,4244.510315,0.003264,49.538914,108908.937500 66,1.590822,1.888691,0.000201,0.932467,6346.551758,82609.899046,3.153696,2013.050842,6.388480,4266.570618,0.003456,49.556160,108908.937500 67,1.622504,1.888691,0.000204,0.886735,6339.600098,82700.484561,3.192448,2021.613373,6.369120,4250.808960,0.003360,49.761311,108908.937500 68,1.598213,1.888691,0.000207,0.945386,6362.027832,82408.944733,3.032032,2052.177292,6.408832,4242.855530,0.003136,49.706528,108908.937500 69,1.635720,1.888691,0.000210,0.828467,6375.836914,82230.459635,3.054080,2071.758331,6.374304,4237.343994,0.003488,49.471584,108908.937500 70,1.608484,1.888691,0.000213,0.705563,6333.446777,82780.833002,3.085312,2030.654495,6.383808,4235.660950,0.003456,49.810143,108908.937500 71,1.609575,1.888691,0.000216,0.769313,6333.448730,82780.807473,3.185920,2022.177628,6.377888,4244.523987,0.003744,49.391457,108908.937500 72,1.544902,1.888691,0.000219,0.765577,6330.444336,82820.094796,2.990560,2021.862930,6.384096,4241.289978,0.003456,50.048832,108908.937500 73,1.616233,1.888691,0.000222,0.908922,6347.528809,82597.183220,3.052000,2046.735794,6.404224,4233.970032,0.003360,49.475582,108908.937500 74,1.594353,1.888691,0.000225,0.870625,6332.663574,82791.071064,3.016256,2023.631378,6.390528,4242.107483,0.003648,49.662495,108908.937500 75,1.609479,1.888691,0.000228,0.901361,6339.545898,82701.191599,3.144448,2023.043823,6.556544,4249.322388,0.003168,49.655582,108908.937500 76,1.552467,1.888691,0.000231,0.720024,6335.944336,82748.201720,3.141376,2018.586441,6.378432,4250.480408,0.003232,49.533215,108908.937500 77,1.623230,1.888691,0.000234,0.868704,6327.529297,82858.249311,3.159808,2033.299561,6.390720,4227.265991,0.003296,49.573982,108908.937500 78,1.589706,1.888691,0.000237,0.753138,6334.817383,82762.922483,3.093888,2022.446396,6.369728,4245.048401,0.003168,50.036736,108908.937500 79,1.593231,1.888691,0.000240,0.930943,6320.514160,82950.213656,3.199552,2013.510864,6.400224,4239.887573,0.003616,49.629375,108908.937500 80,1.596107,1.888691,0.000243,1.606060,6329.073730,82838.030070,3.101120,2014.925446,6.389056,4247.571899,0.002752,49.241570,108908.937500 81,1.639003,1.888691,0.000246,0.817727,6320.255859,82953.603725,3.115648,2019.156494,6.376960,4234.370728,0.003744,49.385345,108908.937500 82,1.667713,1.888691,0.000249,0.836137,6397.347168,81953.970331,3.113664,2098.460571,6.379456,4232.184082,0.003520,49.324863,108908.937500 83,1.597706,1.888691,0.000252,0.850811,6376.568848,82221.020823,3.066400,2045.288528,6.396896,4264.504700,0.003680,49.474209,108908.937500 84,1.606992,1.888691,0.000255,0.882354,6307.102539,83126.601598,3.170624,2014.658478,6.425856,4225.344910,0.003040,49.490398,108908.937500 85,1.606081,1.888691,0.000258,0.866452,6330.486816,82819.539035,3.189280,2021.691483,6.376000,4241.203735,0.003712,50.007488,108908.937500 86,1.608906,1.888691,0.000261,0.911513,6355.762207,82490.184957,3.082752,2027.016525,6.386272,4261.731934,0.003744,49.692703,108908.937500 87,1.671125,1.888691,0.000264,0.814413,6334.824219,82762.833174,3.132576,2028.304459,6.405984,4239.682617,0.003552,49.423584,108908.937500 88,1.673897,1.888691,0.000267,0.830793,6355.620117,82492.029154,3.088928,2057.730515,6.397024,4230.854980,0.003488,49.693249,108908.937500 89,1.632511,1.888691,0.000270,0.727420,6347.372559,82599.216473,3.271584,2019.465515,6.377504,4260.599365,0.003456,49.754658,108908.937500 90,1.688837,1.888691,0.000273,0.829598,6319.859863,82958.801515,3.233824,2016.384445,6.386720,4236.367371,0.003712,49.533119,108908.937500 91,1.636074,1.888691,0.000276,0.817738,6328.082031,82851.011951,3.357184,2024.802856,6.504896,4236.096619,0.003936,49.416801,108908.937500 92,1.643463,1.888691,0.000279,0.835200,6385.577637,82105.023199,3.101984,2085.348373,6.370688,4233.383240,0.003264,49.486050,108908.937500 93,1.674679,1.888691,0.000282,0.844461,6345.835449,82619.223930,3.206112,2050.609604,6.416192,4228.289124,0.003296,49.477825,108908.937500 94,1.552707,1.888691,0.000285,0.863358,6333.635742,82778.363225,3.077472,2024.566391,6.388608,4242.301086,0.003520,49.442337,108908.937500 95,1.630905,1.888691,0.000288,0.832031,6353.830566,82515.262962,3.274624,2028.155670,6.383200,4258.484619,0.003584,49.571232,108908.937500 96,1.621827,1.888691,0.000291,0.918384,6323.018066,82917.365488,3.162592,2012.941772,6.531904,4242.120300,0.003328,50.340000,108908.937500 97,1.617399,1.888691,0.000294,0.769910,6362.215332,82406.516070,3.146368,2055.820648,6.363808,4239.379150,0.003360,49.700993,108908.937500 98,1.612508,1.888691,0.000297,0.735902,6338.875488,82709.938217,3.280320,2024.479431,6.381600,4246.271057,0.003648,49.950272,108908.937500 99,1.637773,1.888691,0.000300,0.846796,6349.173828,82575.782959,3.284096,2017.665619,6.522688,4264.178955,0.003808,49.582047,108908.937500 100,1.653108,1.888691,0.000300,0.734803,6202.841309,84523.845431,3.153216,1994.373230,6.355648,4141.351471,0.003040,49.651264,108908.937500 101,1.685746,1.888691,0.000300,0.839908,6250.926758,83873.643111,3.112736,2000.709305,6.356064,4183.176941,0.003328,49.745953,108908.937500 102,1.593222,1.888691,0.000300,0.901897,6296.575684,83265.575822,3.109248,2014.010040,6.365856,4215.727234,0.003648,49.486912,108908.937500 103,1.654905,1.888691,0.000300,1.344759,6319.219238,82967.211649,3.203072,2014.496460,6.400864,4237.814575,0.003904,49.331680,108908.937500 104,1.717948,1.888691,0.000300,0.872429,6307.382812,83122.907803,3.308448,2013.957855,6.368896,4226.038208,0.003424,49.683266,108908.937500 105,1.634465,1.888691,0.000300,0.930153,6328.196289,82849.516047,3.181632,2020.862473,6.370432,4239.761902,0.003584,49.982849,108908.937500 106,1.635792,1.888691,0.000300,0.841532,6351.314453,82547.951903,3.118720,2022.737396,6.384096,4261.141296,0.003520,50.008610,108908.937500 107,1.702721,1.888691,0.000300,1.061945,6335.490723,82754.126389,3.155392,2014.187668,6.598240,4254.034668,0.003680,49.600864,108908.937500 108,1.590036,1.888691,0.000300,0.763811,6324.348145,82899.927078,3.180352,2017.641800,6.588832,4239.494141,0.003232,49.576927,108908.937500 109,1.636682,1.888691,0.000300,0.749749,6365.064453,82369.629383,3.136064,2047.121140,6.403680,4250.903137,0.003648,49.604511,108908.937500 110,1.652374,1.888691,0.000299,0.730469,6359.887695,82436.675790,3.187968,2034.555664,6.399360,4258.320068,0.003584,49.594624,108908.937500 111,1.643456,1.888691,0.000299,0.650920,6332.087891,82798.598038,3.185760,2019.466751,6.392064,4245.492798,0.003648,49.602943,108908.937500 112,1.615295,1.888691,0.000299,0.671301,6326.246582,82875.049716,3.325024,2020.936401,6.384960,4238.044067,0.003072,49.568512,108908.937500 113,1.605785,1.888691,0.000299,0.768448,6312.109863,83060.658220,3.108032,2010.817078,6.372480,4234.687378,0.003488,49.210400,108908.937500 114,1.643168,1.888691,0.000299,0.754148,6342.302246,82665.249882,3.096288,2018.112579,6.384480,4257.198425,0.003360,49.664864,108908.937500 115,1.622634,1.888691,0.000299,0.693109,6359.413574,82442.821792,3.086368,2020.846024,6.413856,4270.722473,0.003456,50.430367,108908.937500 116,1.572031,1.888691,0.000299,0.787975,6342.383301,82664.193433,3.351072,2027.193253,6.384608,4247.884216,0.003648,49.60