Files
Malaysian-Llama-3.1-8B-Inst…/lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1000/trainer_state.json

7035 lines
154 KiB
JSON
Raw Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.34518467380048323,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034518467380048324,
"grad_norm": 164.25050354003906,
"learning_rate": 0.0,
"loss": 1.9257,
"step": 1
},
{
"epoch": 0.0006903693476009665,
"grad_norm": 116.43001556396484,
"learning_rate": 2e-05,
"loss": 1.8201,
"step": 2
},
{
"epoch": 0.0010355540214014498,
"grad_norm": 111.98278045654297,
"learning_rate": 2e-05,
"loss": 1.9652,
"step": 3
},
{
"epoch": 0.001380738695201933,
"grad_norm": 312.7107238769531,
"learning_rate": 2e-05,
"loss": 1.6971,
"step": 4
},
{
"epoch": 0.0017259233690024164,
"grad_norm": 124.51359558105469,
"learning_rate": 2e-05,
"loss": 1.7228,
"step": 5
},
{
"epoch": 0.0020711080428028996,
"grad_norm": 117.87893676757812,
"learning_rate": 2e-05,
"loss": 1.7254,
"step": 6
},
{
"epoch": 0.002416292716603383,
"grad_norm": 59.12928771972656,
"learning_rate": 2e-05,
"loss": 1.473,
"step": 7
},
{
"epoch": 0.002761477390403866,
"grad_norm": 24.38951873779297,
"learning_rate": 2e-05,
"loss": 1.5216,
"step": 8
},
{
"epoch": 0.0031066620642043494,
"grad_norm": 57.787757873535156,
"learning_rate": 2e-05,
"loss": 1.5563,
"step": 9
},
{
"epoch": 0.0034518467380048328,
"grad_norm": 21.435535430908203,
"learning_rate": 2e-05,
"loss": 1.4052,
"step": 10
},
{
"epoch": 0.0037970314118053157,
"grad_norm": 25.76114273071289,
"learning_rate": 2e-05,
"loss": 1.4289,
"step": 11
},
{
"epoch": 0.004142216085605799,
"grad_norm": 16.697547912597656,
"learning_rate": 2e-05,
"loss": 1.5014,
"step": 12
},
{
"epoch": 0.0044874007594062825,
"grad_norm": 10.946109771728516,
"learning_rate": 2e-05,
"loss": 1.4236,
"step": 13
},
{
"epoch": 0.004832585433206766,
"grad_norm": 9.638275146484375,
"learning_rate": 2e-05,
"loss": 1.4098,
"step": 14
},
{
"epoch": 0.0051777701070072485,
"grad_norm": 17.02400016784668,
"learning_rate": 2e-05,
"loss": 1.4035,
"step": 15
},
{
"epoch": 0.005522954780807732,
"grad_norm": 7.689630508422852,
"learning_rate": 2e-05,
"loss": 1.3273,
"step": 16
},
{
"epoch": 0.005868139454608215,
"grad_norm": 7.028171539306641,
"learning_rate": 2e-05,
"loss": 1.3675,
"step": 17
},
{
"epoch": 0.006213324128408699,
"grad_norm": 8.425003051757812,
"learning_rate": 2e-05,
"loss": 1.3065,
"step": 18
},
{
"epoch": 0.006558508802209182,
"grad_norm": 7.860549449920654,
"learning_rate": 2e-05,
"loss": 1.2914,
"step": 19
},
{
"epoch": 0.0069036934760096655,
"grad_norm": 5.793131351470947,
"learning_rate": 2e-05,
"loss": 1.2639,
"step": 20
},
{
"epoch": 0.007248878149810148,
"grad_norm": 6.066828727722168,
"learning_rate": 2e-05,
"loss": 1.2845,
"step": 21
},
{
"epoch": 0.0075940628236106315,
"grad_norm": 6.9683074951171875,
"learning_rate": 2e-05,
"loss": 1.2839,
"step": 22
},
{
"epoch": 0.007939247497411116,
"grad_norm": 7.026453018188477,
"learning_rate": 2e-05,
"loss": 1.3129,
"step": 23
},
{
"epoch": 0.008284432171211598,
"grad_norm": 6.011166095733643,
"learning_rate": 2e-05,
"loss": 1.2021,
"step": 24
},
{
"epoch": 0.00862961684501208,
"grad_norm": 6.688496112823486,
"learning_rate": 2e-05,
"loss": 1.2988,
"step": 25
},
{
"epoch": 0.008974801518812565,
"grad_norm": 5.536924839019775,
"learning_rate": 2e-05,
"loss": 1.2529,
"step": 26
},
{
"epoch": 0.009319986192613048,
"grad_norm": 6.189913749694824,
"learning_rate": 2e-05,
"loss": 1.2541,
"step": 27
},
{
"epoch": 0.009665170866413532,
"grad_norm": 5.186566352844238,
"learning_rate": 2e-05,
"loss": 1.1685,
"step": 28
},
{
"epoch": 0.010010355540214014,
"grad_norm": 5.111907482147217,
"learning_rate": 2e-05,
"loss": 1.1647,
"step": 29
},
{
"epoch": 0.010355540214014497,
"grad_norm": 7.816215515136719,
"learning_rate": 2e-05,
"loss": 1.1613,
"step": 30
},
{
"epoch": 0.010700724887814981,
"grad_norm": 6.994287014007568,
"learning_rate": 2e-05,
"loss": 1.1798,
"step": 31
},
{
"epoch": 0.011045909561615464,
"grad_norm": 6.679455280303955,
"learning_rate": 2e-05,
"loss": 1.1356,
"step": 32
},
{
"epoch": 0.011391094235415948,
"grad_norm": 5.451405048370361,
"learning_rate": 2e-05,
"loss": 1.1679,
"step": 33
},
{
"epoch": 0.01173627890921643,
"grad_norm": 5.443926811218262,
"learning_rate": 2e-05,
"loss": 1.1729,
"step": 34
},
{
"epoch": 0.012081463583016915,
"grad_norm": 5.605351448059082,
"learning_rate": 2e-05,
"loss": 1.1808,
"step": 35
},
{
"epoch": 0.012426648256817397,
"grad_norm": 5.121994972229004,
"learning_rate": 2e-05,
"loss": 1.1379,
"step": 36
},
{
"epoch": 0.01277183293061788,
"grad_norm": 4.825695037841797,
"learning_rate": 2e-05,
"loss": 1.1291,
"step": 37
},
{
"epoch": 0.013117017604418364,
"grad_norm": 4.905743598937988,
"learning_rate": 2e-05,
"loss": 1.1687,
"step": 38
},
{
"epoch": 0.013462202278218847,
"grad_norm": 5.373997688293457,
"learning_rate": 2e-05,
"loss": 1.2164,
"step": 39
},
{
"epoch": 0.013807386952019331,
"grad_norm": 4.702381134033203,
"learning_rate": 2e-05,
"loss": 1.1769,
"step": 40
},
{
"epoch": 0.014152571625819814,
"grad_norm": 5.017072677612305,
"learning_rate": 2e-05,
"loss": 1.1081,
"step": 41
},
{
"epoch": 0.014497756299620296,
"grad_norm": 4.598694801330566,
"learning_rate": 2e-05,
"loss": 1.0872,
"step": 42
},
{
"epoch": 0.01484294097342078,
"grad_norm": 4.88613224029541,
"learning_rate": 2e-05,
"loss": 1.166,
"step": 43
},
{
"epoch": 0.015188125647221263,
"grad_norm": 4.172844886779785,
"learning_rate": 2e-05,
"loss": 1.1078,
"step": 44
},
{
"epoch": 0.015533310321021747,
"grad_norm": 4.9598612785339355,
"learning_rate": 2e-05,
"loss": 1.1068,
"step": 45
},
{
"epoch": 0.01587849499482223,
"grad_norm": 4.003320693969727,
"learning_rate": 2e-05,
"loss": 1.0951,
"step": 46
},
{
"epoch": 0.016223679668622714,
"grad_norm": 4.30601692199707,
"learning_rate": 2e-05,
"loss": 1.1088,
"step": 47
},
{
"epoch": 0.016568864342423197,
"grad_norm": 4.957517623901367,
"learning_rate": 2e-05,
"loss": 1.1152,
"step": 48
},
{
"epoch": 0.01691404901622368,
"grad_norm": 5.051650047302246,
"learning_rate": 2e-05,
"loss": 1.0514,
"step": 49
},
{
"epoch": 0.01725923369002416,
"grad_norm": 4.508876800537109,
"learning_rate": 2e-05,
"loss": 1.1081,
"step": 50
},
{
"epoch": 0.017604418363824648,
"grad_norm": 4.666370391845703,
"learning_rate": 2e-05,
"loss": 1.0889,
"step": 51
},
{
"epoch": 0.01794960303762513,
"grad_norm": 4.62983512878418,
"learning_rate": 2e-05,
"loss": 1.0561,
"step": 52
},
{
"epoch": 0.018294787711425613,
"grad_norm": 3.8194386959075928,
"learning_rate": 2e-05,
"loss": 1.0314,
"step": 53
},
{
"epoch": 0.018639972385226095,
"grad_norm": 4.9420695304870605,
"learning_rate": 2e-05,
"loss": 1.1218,
"step": 54
},
{
"epoch": 0.018985157059026578,
"grad_norm": 4.9239068031311035,
"learning_rate": 2e-05,
"loss": 1.0647,
"step": 55
},
{
"epoch": 0.019330341732827064,
"grad_norm": 4.308078289031982,
"learning_rate": 2e-05,
"loss": 1.0469,
"step": 56
},
{
"epoch": 0.019675526406627546,
"grad_norm": 4.183582782745361,
"learning_rate": 2e-05,
"loss": 1.101,
"step": 57
},
{
"epoch": 0.02002071108042803,
"grad_norm": 5.259477138519287,
"learning_rate": 2e-05,
"loss": 1.1166,
"step": 58
},
{
"epoch": 0.02036589575422851,
"grad_norm": 4.483434677124023,
"learning_rate": 2e-05,
"loss": 1.0173,
"step": 59
},
{
"epoch": 0.020711080428028994,
"grad_norm": 4.112723350524902,
"learning_rate": 2e-05,
"loss": 1.062,
"step": 60
},
{
"epoch": 0.02105626510182948,
"grad_norm": 4.924528121948242,
"learning_rate": 2e-05,
"loss": 1.0574,
"step": 61
},
{
"epoch": 0.021401449775629963,
"grad_norm": 3.717799663543701,
"learning_rate": 2e-05,
"loss": 1.0268,
"step": 62
},
{
"epoch": 0.021746634449430445,
"grad_norm": 4.5001044273376465,
"learning_rate": 2e-05,
"loss": 1.057,
"step": 63
},
{
"epoch": 0.022091819123230928,
"grad_norm": 4.214874267578125,
"learning_rate": 2e-05,
"loss": 1.1244,
"step": 64
},
{
"epoch": 0.02243700379703141,
"grad_norm": 4.098433494567871,
"learning_rate": 2e-05,
"loss": 1.0685,
"step": 65
},
{
"epoch": 0.022782188470831896,
"grad_norm": 3.9524285793304443,
"learning_rate": 2e-05,
"loss": 1.0642,
"step": 66
},
{
"epoch": 0.02312737314463238,
"grad_norm": 4.906257152557373,
"learning_rate": 2e-05,
"loss": 1.0543,
"step": 67
},
{
"epoch": 0.02347255781843286,
"grad_norm": 5.597499847412109,
"learning_rate": 2e-05,
"loss": 1.0525,
"step": 68
},
{
"epoch": 0.023817742492233344,
"grad_norm": 3.9120569229125977,
"learning_rate": 2e-05,
"loss": 1.0316,
"step": 69
},
{
"epoch": 0.02416292716603383,
"grad_norm": 3.9987313747406006,
"learning_rate": 2e-05,
"loss": 1.0415,
"step": 70
},
{
"epoch": 0.024508111839834312,
"grad_norm": 3.854943037033081,
"learning_rate": 2e-05,
"loss": 1.0162,
"step": 71
},
{
"epoch": 0.024853296513634795,
"grad_norm": 4.38804292678833,
"learning_rate": 2e-05,
"loss": 0.9893,
"step": 72
},
{
"epoch": 0.025198481187435277,
"grad_norm": 3.375614881515503,
"learning_rate": 2e-05,
"loss": 1.0135,
"step": 73
},
{
"epoch": 0.02554366586123576,
"grad_norm": 3.9334664344787598,
"learning_rate": 2e-05,
"loss": 1.0267,
"step": 74
},
{
"epoch": 0.025888850535036246,
"grad_norm": 3.8816137313842773,
"learning_rate": 2e-05,
"loss": 1.0347,
"step": 75
},
{
"epoch": 0.02623403520883673,
"grad_norm": 3.884535551071167,
"learning_rate": 2e-05,
"loss": 0.9914,
"step": 76
},
{
"epoch": 0.02657921988263721,
"grad_norm": 3.833580493927002,
"learning_rate": 2e-05,
"loss": 1.021,
"step": 77
},
{
"epoch": 0.026924404556437694,
"grad_norm": 3.6896729469299316,
"learning_rate": 2e-05,
"loss": 0.9915,
"step": 78
},
{
"epoch": 0.027269589230238176,
"grad_norm": 3.8832285404205322,
"learning_rate": 2e-05,
"loss": 1.0081,
"step": 79
},
{
"epoch": 0.027614773904038662,
"grad_norm": 4.00054931640625,
"learning_rate": 2e-05,
"loss": 0.9723,
"step": 80
},
{
"epoch": 0.027959958577839145,
"grad_norm": 3.9635231494903564,
"learning_rate": 2e-05,
"loss": 1.0677,
"step": 81
},
{
"epoch": 0.028305143251639627,
"grad_norm": 4.25091552734375,
"learning_rate": 2e-05,
"loss": 0.9683,
"step": 82
},
{
"epoch": 0.02865032792544011,
"grad_norm": 4.387684345245361,
"learning_rate": 2e-05,
"loss": 1.0273,
"step": 83
},
{
"epoch": 0.028995512599240592,
"grad_norm": 4.047482013702393,
"learning_rate": 2e-05,
"loss": 1.0372,
"step": 84
},
{
"epoch": 0.029340697273041078,
"grad_norm": 4.226908206939697,
"learning_rate": 2e-05,
"loss": 1.0192,
"step": 85
},
{
"epoch": 0.02968588194684156,
"grad_norm": 4.123228073120117,
"learning_rate": 2e-05,
"loss": 0.9915,
"step": 86
},
{
"epoch": 0.030031066620642043,
"grad_norm": 6.669504165649414,
"learning_rate": 2e-05,
"loss": 0.9531,
"step": 87
},
{
"epoch": 0.030376251294442526,
"grad_norm": 4.364908695220947,
"learning_rate": 2e-05,
"loss": 1.0042,
"step": 88
},
{
"epoch": 0.03072143596824301,
"grad_norm": 3.7988955974578857,
"learning_rate": 2e-05,
"loss": 0.9767,
"step": 89
},
{
"epoch": 0.031066620642043494,
"grad_norm": 3.547370433807373,
"learning_rate": 2e-05,
"loss": 1.0045,
"step": 90
},
{
"epoch": 0.03141180531584398,
"grad_norm": 4.054666042327881,
"learning_rate": 2e-05,
"loss": 0.9679,
"step": 91
},
{
"epoch": 0.03175698998964446,
"grad_norm": 4.089395523071289,
"learning_rate": 2e-05,
"loss": 1.009,
"step": 92
},
{
"epoch": 0.03210217466344494,
"grad_norm": 3.888781785964966,
"learning_rate": 2e-05,
"loss": 0.9993,
"step": 93
},
{
"epoch": 0.03244735933724543,
"grad_norm": 4.337654113769531,
"learning_rate": 2e-05,
"loss": 1.0637,
"step": 94
},
{
"epoch": 0.03279254401104591,
"grad_norm": 3.9866831302642822,
"learning_rate": 2e-05,
"loss": 1.0415,
"step": 95
},
{
"epoch": 0.03313772868484639,
"grad_norm": 3.694230556488037,
"learning_rate": 2e-05,
"loss": 1.0111,
"step": 96
},
{
"epoch": 0.03348291335864688,
"grad_norm": 3.8903889656066895,
"learning_rate": 2e-05,
"loss": 1.0113,
"step": 97
},
{
"epoch": 0.03382809803244736,
"grad_norm": 4.173677444458008,
"learning_rate": 2e-05,
"loss": 0.9969,
"step": 98
},
{
"epoch": 0.034173282706247844,
"grad_norm": 3.679419755935669,
"learning_rate": 2e-05,
"loss": 1.0401,
"step": 99
},
{
"epoch": 0.03451846738004832,
"grad_norm": 4.073668003082275,
"learning_rate": 2e-05,
"loss": 1.0062,
"step": 100
},
{
"epoch": 0.03486365205384881,
"grad_norm": 3.659552574157715,
"learning_rate": 2e-05,
"loss": 0.9113,
"step": 101
},
{
"epoch": 0.035208836727649295,
"grad_norm": 3.581220865249634,
"learning_rate": 2e-05,
"loss": 1.0402,
"step": 102
},
{
"epoch": 0.035554021401449774,
"grad_norm": 3.6875903606414795,
"learning_rate": 2e-05,
"loss": 1.0051,
"step": 103
},
{
"epoch": 0.03589920607525026,
"grad_norm": 3.3204426765441895,
"learning_rate": 2e-05,
"loss": 1.0041,
"step": 104
},
{
"epoch": 0.03624439074905074,
"grad_norm": 3.408184766769409,
"learning_rate": 2e-05,
"loss": 0.9501,
"step": 105
},
{
"epoch": 0.036589575422851225,
"grad_norm": 3.7698254585266113,
"learning_rate": 2e-05,
"loss": 0.9487,
"step": 106
},
{
"epoch": 0.03693476009665171,
"grad_norm": 4.5543694496154785,
"learning_rate": 2e-05,
"loss": 1.0095,
"step": 107
},
{
"epoch": 0.03727994477045219,
"grad_norm": 4.206326961517334,
"learning_rate": 2e-05,
"loss": 0.9307,
"step": 108
},
{
"epoch": 0.037625129444252677,
"grad_norm": 3.7120132446289062,
"learning_rate": 2e-05,
"loss": 0.9017,
"step": 109
},
{
"epoch": 0.037970314118053156,
"grad_norm": 3.6532175540924072,
"learning_rate": 2e-05,
"loss": 0.9544,
"step": 110
},
{
"epoch": 0.03831549879185364,
"grad_norm": 3.4927427768707275,
"learning_rate": 2e-05,
"loss": 0.97,
"step": 111
},
{
"epoch": 0.03866068346565413,
"grad_norm": 4.344557762145996,
"learning_rate": 2e-05,
"loss": 0.9311,
"step": 112
},
{
"epoch": 0.03900586813945461,
"grad_norm": 3.0494396686553955,
"learning_rate": 2e-05,
"loss": 1.0055,
"step": 113
},
{
"epoch": 0.03935105281325509,
"grad_norm": 3.7052459716796875,
"learning_rate": 2e-05,
"loss": 0.9356,
"step": 114
},
{
"epoch": 0.03969623748705557,
"grad_norm": 4.43536376953125,
"learning_rate": 2e-05,
"loss": 0.9695,
"step": 115
},
{
"epoch": 0.04004142216085606,
"grad_norm": 3.6565682888031006,
"learning_rate": 2e-05,
"loss": 1.0503,
"step": 116
},
{
"epoch": 0.040386606834656544,
"grad_norm": 3.5132741928100586,
"learning_rate": 2e-05,
"loss": 0.959,
"step": 117
},
{
"epoch": 0.04073179150845702,
"grad_norm": 4.00861120223999,
"learning_rate": 2e-05,
"loss": 0.8973,
"step": 118
},
{
"epoch": 0.04107697618225751,
"grad_norm": 4.118383407592773,
"learning_rate": 2e-05,
"loss": 0.961,
"step": 119
},
{
"epoch": 0.04142216085605799,
"grad_norm": 3.6368112564086914,
"learning_rate": 2e-05,
"loss": 1.0302,
"step": 120
},
{
"epoch": 0.041767345529858474,
"grad_norm": 3.668741226196289,
"learning_rate": 2e-05,
"loss": 0.9267,
"step": 121
},
{
"epoch": 0.04211253020365896,
"grad_norm": 3.392117500305176,
"learning_rate": 2e-05,
"loss": 1.0133,
"step": 122
},
{
"epoch": 0.04245771487745944,
"grad_norm": 3.939965009689331,
"learning_rate": 2e-05,
"loss": 0.9151,
"step": 123
},
{
"epoch": 0.042802899551259925,
"grad_norm": 3.3222975730895996,
"learning_rate": 2e-05,
"loss": 0.9028,
"step": 124
},
{
"epoch": 0.043148084225060404,
"grad_norm": 3.639970541000366,
"learning_rate": 2e-05,
"loss": 0.9709,
"step": 125
},
{
"epoch": 0.04349326889886089,
"grad_norm": 3.2109615802764893,
"learning_rate": 2e-05,
"loss": 0.9867,
"step": 126
},
{
"epoch": 0.043838453572661376,
"grad_norm": 3.3262574672698975,
"learning_rate": 2e-05,
"loss": 0.964,
"step": 127
},
{
"epoch": 0.044183638246461855,
"grad_norm": 5.754081726074219,
"learning_rate": 2e-05,
"loss": 0.8765,
"step": 128
},
{
"epoch": 0.04452882292026234,
"grad_norm": 3.367676019668579,
"learning_rate": 2e-05,
"loss": 0.9724,
"step": 129
},
{
"epoch": 0.04487400759406282,
"grad_norm": 3.8047783374786377,
"learning_rate": 2e-05,
"loss": 0.9596,
"step": 130
},
{
"epoch": 0.045219192267863306,
"grad_norm": 3.5262019634246826,
"learning_rate": 2e-05,
"loss": 0.8931,
"step": 131
},
{
"epoch": 0.04556437694166379,
"grad_norm": 3.1185085773468018,
"learning_rate": 2e-05,
"loss": 0.891,
"step": 132
},
{
"epoch": 0.04590956161546427,
"grad_norm": 3.795315980911255,
"learning_rate": 2e-05,
"loss": 0.9536,
"step": 133
},
{
"epoch": 0.04625474628926476,
"grad_norm": 3.698105812072754,
"learning_rate": 2e-05,
"loss": 0.918,
"step": 134
},
{
"epoch": 0.04659993096306524,
"grad_norm": 4.450272560119629,
"learning_rate": 2e-05,
"loss": 0.9075,
"step": 135
},
{
"epoch": 0.04694511563686572,
"grad_norm": 3.3076443672180176,
"learning_rate": 2e-05,
"loss": 0.9334,
"step": 136
},
{
"epoch": 0.04729030031066621,
"grad_norm": 3.551239252090454,
"learning_rate": 2e-05,
"loss": 0.9221,
"step": 137
},
{
"epoch": 0.04763548498446669,
"grad_norm": 3.3865537643432617,
"learning_rate": 2e-05,
"loss": 0.96,
"step": 138
},
{
"epoch": 0.047980669658267174,
"grad_norm": 3.477189302444458,
"learning_rate": 2e-05,
"loss": 0.9794,
"step": 139
},
{
"epoch": 0.04832585433206766,
"grad_norm": 3.2932441234588623,
"learning_rate": 2e-05,
"loss": 0.9078,
"step": 140
},
{
"epoch": 0.04867103900586814,
"grad_norm": 3.095069646835327,
"learning_rate": 2e-05,
"loss": 0.9045,
"step": 141
},
{
"epoch": 0.049016223679668625,
"grad_norm": 3.386526107788086,
"learning_rate": 2e-05,
"loss": 0.937,
"step": 142
},
{
"epoch": 0.049361408353469104,
"grad_norm": 3.274214267730713,
"learning_rate": 2e-05,
"loss": 0.9356,
"step": 143
},
{
"epoch": 0.04970659302726959,
"grad_norm": 3.472280263900757,
"learning_rate": 2e-05,
"loss": 0.8798,
"step": 144
},
{
"epoch": 0.050051777701070076,
"grad_norm": 3.4150500297546387,
"learning_rate": 2e-05,
"loss": 1.0118,
"step": 145
},
{
"epoch": 0.050396962374870555,
"grad_norm": 3.7823333740234375,
"learning_rate": 2e-05,
"loss": 0.9675,
"step": 146
},
{
"epoch": 0.05074214704867104,
"grad_norm": 3.460674524307251,
"learning_rate": 2e-05,
"loss": 0.9366,
"step": 147
},
{
"epoch": 0.05108733172247152,
"grad_norm": 4.081386089324951,
"learning_rate": 2e-05,
"loss": 0.9596,
"step": 148
},
{
"epoch": 0.051432516396272006,
"grad_norm": 3.5548624992370605,
"learning_rate": 2e-05,
"loss": 0.9369,
"step": 149
},
{
"epoch": 0.05177770107007249,
"grad_norm": 3.713184118270874,
"learning_rate": 2e-05,
"loss": 0.9645,
"step": 150
},
{
"epoch": 0.05212288574387297,
"grad_norm": 9.342556953430176,
"learning_rate": 2e-05,
"loss": 0.953,
"step": 151
},
{
"epoch": 0.05246807041767346,
"grad_norm": 3.330892562866211,
"learning_rate": 2e-05,
"loss": 0.9851,
"step": 152
},
{
"epoch": 0.052813255091473936,
"grad_norm": 3.2820513248443604,
"learning_rate": 2e-05,
"loss": 0.9881,
"step": 153
},
{
"epoch": 0.05315843976527442,
"grad_norm": 3.08601713180542,
"learning_rate": 2e-05,
"loss": 0.8678,
"step": 154
},
{
"epoch": 0.05350362443907491,
"grad_norm": 3.466398239135742,
"learning_rate": 2e-05,
"loss": 0.9688,
"step": 155
},
{
"epoch": 0.05384880911287539,
"grad_norm": 3.8165998458862305,
"learning_rate": 2e-05,
"loss": 0.9516,
"step": 156
},
{
"epoch": 0.05419399378667587,
"grad_norm": 3.843984365463257,
"learning_rate": 2e-05,
"loss": 0.8846,
"step": 157
},
{
"epoch": 0.05453917846047635,
"grad_norm": 3.6460742950439453,
"learning_rate": 2e-05,
"loss": 0.9738,
"step": 158
},
{
"epoch": 0.05488436313427684,
"grad_norm": 3.6064538955688477,
"learning_rate": 2e-05,
"loss": 0.8974,
"step": 159
},
{
"epoch": 0.055229547808077324,
"grad_norm": 3.8065435886383057,
"learning_rate": 2e-05,
"loss": 0.9804,
"step": 160
},
{
"epoch": 0.0555747324818778,
"grad_norm": 3.020841121673584,
"learning_rate": 2e-05,
"loss": 0.9037,
"step": 161
},
{
"epoch": 0.05591991715567829,
"grad_norm": 3.5063493251800537,
"learning_rate": 2e-05,
"loss": 0.892,
"step": 162
},
{
"epoch": 0.05626510182947877,
"grad_norm": 3.2224860191345215,
"learning_rate": 2e-05,
"loss": 0.8995,
"step": 163
},
{
"epoch": 0.056610286503279254,
"grad_norm": 3.520097494125366,
"learning_rate": 2e-05,
"loss": 0.9791,
"step": 164
},
{
"epoch": 0.05695547117707974,
"grad_norm": 3.435135841369629,
"learning_rate": 2e-05,
"loss": 1.0013,
"step": 165
},
{
"epoch": 0.05730065585088022,
"grad_norm": 3.173973321914673,
"learning_rate": 2e-05,
"loss": 0.9146,
"step": 166
},
{
"epoch": 0.057645840524680705,
"grad_norm": 3.4863386154174805,
"learning_rate": 2e-05,
"loss": 0.9885,
"step": 167
},
{
"epoch": 0.057991025198481184,
"grad_norm": 3.2673957347869873,
"learning_rate": 2e-05,
"loss": 0.9354,
"step": 168
},
{
"epoch": 0.05833620987228167,
"grad_norm": 3.613051652908325,
"learning_rate": 2e-05,
"loss": 0.9169,
"step": 169
},
{
"epoch": 0.058681394546082156,
"grad_norm": 3.6220316886901855,
"learning_rate": 2e-05,
"loss": 0.9123,
"step": 170
},
{
"epoch": 0.059026579219882636,
"grad_norm": 2.9920058250427246,
"learning_rate": 2e-05,
"loss": 0.9228,
"step": 171
},
{
"epoch": 0.05937176389368312,
"grad_norm": 3.1163201332092285,
"learning_rate": 2e-05,
"loss": 0.9196,
"step": 172
},
{
"epoch": 0.0597169485674836,
"grad_norm": 3.5045080184936523,
"learning_rate": 2e-05,
"loss": 0.9711,
"step": 173
},
{
"epoch": 0.06006213324128409,
"grad_norm": 3.3398544788360596,
"learning_rate": 2e-05,
"loss": 0.8714,
"step": 174
},
{
"epoch": 0.06040731791508457,
"grad_norm": 2.9095466136932373,
"learning_rate": 2e-05,
"loss": 0.8746,
"step": 175
},
{
"epoch": 0.06075250258888505,
"grad_norm": 3.1426031589508057,
"learning_rate": 2e-05,
"loss": 0.8826,
"step": 176
},
{
"epoch": 0.06109768726268554,
"grad_norm": 4.104501724243164,
"learning_rate": 2e-05,
"loss": 0.9346,
"step": 177
},
{
"epoch": 0.06144287193648602,
"grad_norm": 2.990579128265381,
"learning_rate": 2e-05,
"loss": 0.9675,
"step": 178
},
{
"epoch": 0.0617880566102865,
"grad_norm": 3.756319284439087,
"learning_rate": 2e-05,
"loss": 0.9229,
"step": 179
},
{
"epoch": 0.06213324128408699,
"grad_norm": 3.5764338970184326,
"learning_rate": 2e-05,
"loss": 0.9925,
"step": 180
},
{
"epoch": 0.06247842595788747,
"grad_norm": 3.068021774291992,
"learning_rate": 2e-05,
"loss": 0.8987,
"step": 181
},
{
"epoch": 0.06282361063168795,
"grad_norm": 3.2142879962921143,
"learning_rate": 2e-05,
"loss": 0.8418,
"step": 182
},
{
"epoch": 0.06316879530548844,
"grad_norm": 3.3960886001586914,
"learning_rate": 2e-05,
"loss": 0.8892,
"step": 183
},
{
"epoch": 0.06351397997928893,
"grad_norm": 4.435737609863281,
"learning_rate": 2e-05,
"loss": 0.9485,
"step": 184
},
{
"epoch": 0.0638591646530894,
"grad_norm": 11.62714958190918,
"learning_rate": 2e-05,
"loss": 0.8685,
"step": 185
},
{
"epoch": 0.06420434932688988,
"grad_norm": 3.0193748474121094,
"learning_rate": 2e-05,
"loss": 0.9131,
"step": 186
},
{
"epoch": 0.06454953400069037,
"grad_norm": 3.1290862560272217,
"learning_rate": 2e-05,
"loss": 0.9776,
"step": 187
},
{
"epoch": 0.06489471867449086,
"grad_norm": 3.153416872024536,
"learning_rate": 2e-05,
"loss": 0.9031,
"step": 188
},
{
"epoch": 0.06523990334829134,
"grad_norm": 3.450758457183838,
"learning_rate": 2e-05,
"loss": 0.8928,
"step": 189
},
{
"epoch": 0.06558508802209181,
"grad_norm": 3.281147003173828,
"learning_rate": 2e-05,
"loss": 1.0054,
"step": 190
},
{
"epoch": 0.0659302726958923,
"grad_norm": 3.1141176223754883,
"learning_rate": 2e-05,
"loss": 0.913,
"step": 191
},
{
"epoch": 0.06627545736969279,
"grad_norm": 2.945939064025879,
"learning_rate": 2e-05,
"loss": 0.895,
"step": 192
},
{
"epoch": 0.06662064204349327,
"grad_norm": 3.141927719116211,
"learning_rate": 2e-05,
"loss": 0.9336,
"step": 193
},
{
"epoch": 0.06696582671729376,
"grad_norm": 3.6074554920196533,
"learning_rate": 2e-05,
"loss": 0.9821,
"step": 194
},
{
"epoch": 0.06731101139109423,
"grad_norm": 2.96323823928833,
"learning_rate": 2e-05,
"loss": 0.9417,
"step": 195
},
{
"epoch": 0.06765619606489472,
"grad_norm": 3.4270036220550537,
"learning_rate": 2e-05,
"loss": 0.9268,
"step": 196
},
{
"epoch": 0.0680013807386952,
"grad_norm": 3.006737232208252,
"learning_rate": 2e-05,
"loss": 0.9125,
"step": 197
},
{
"epoch": 0.06834656541249569,
"grad_norm": 3.3677432537078857,
"learning_rate": 2e-05,
"loss": 0.9403,
"step": 198
},
{
"epoch": 0.06869175008629617,
"grad_norm": 3.6785035133361816,
"learning_rate": 2e-05,
"loss": 0.8477,
"step": 199
},
{
"epoch": 0.06903693476009665,
"grad_norm": 3.1328837871551514,
"learning_rate": 2e-05,
"loss": 0.8866,
"step": 200
},
{
"epoch": 0.06938211943389713,
"grad_norm": 3.178600311279297,
"learning_rate": 2e-05,
"loss": 0.8418,
"step": 201
},
{
"epoch": 0.06972730410769762,
"grad_norm": 3.471315622329712,
"learning_rate": 2e-05,
"loss": 0.8908,
"step": 202
},
{
"epoch": 0.0700724887814981,
"grad_norm": 3.3694980144500732,
"learning_rate": 2e-05,
"loss": 0.8825,
"step": 203
},
{
"epoch": 0.07041767345529859,
"grad_norm": 3.511202812194824,
"learning_rate": 2e-05,
"loss": 0.89,
"step": 204
},
{
"epoch": 0.07076285812909906,
"grad_norm": 3.5508413314819336,
"learning_rate": 2e-05,
"loss": 0.8933,
"step": 205
},
{
"epoch": 0.07110804280289955,
"grad_norm": 2.9084413051605225,
"learning_rate": 2e-05,
"loss": 0.9258,
"step": 206
},
{
"epoch": 0.07145322747670003,
"grad_norm": 3.2880771160125732,
"learning_rate": 2e-05,
"loss": 0.9357,
"step": 207
},
{
"epoch": 0.07179841215050052,
"grad_norm": 3.110895872116089,
"learning_rate": 2e-05,
"loss": 0.8697,
"step": 208
},
{
"epoch": 0.072143596824301,
"grad_norm": 3.059079170227051,
"learning_rate": 2e-05,
"loss": 0.8579,
"step": 209
},
{
"epoch": 0.07248878149810148,
"grad_norm": 2.9385037422180176,
"learning_rate": 2e-05,
"loss": 0.8913,
"step": 210
},
{
"epoch": 0.07283396617190196,
"grad_norm": 2.984720468521118,
"learning_rate": 2e-05,
"loss": 0.9311,
"step": 211
},
{
"epoch": 0.07317915084570245,
"grad_norm": 3.1889357566833496,
"learning_rate": 2e-05,
"loss": 0.931,
"step": 212
},
{
"epoch": 0.07352433551950294,
"grad_norm": 3.020983934402466,
"learning_rate": 2e-05,
"loss": 0.8572,
"step": 213
},
{
"epoch": 0.07386952019330342,
"grad_norm": 3.3382914066314697,
"learning_rate": 2e-05,
"loss": 0.9128,
"step": 214
},
{
"epoch": 0.0742147048671039,
"grad_norm": 3.1657910346984863,
"learning_rate": 2e-05,
"loss": 0.8976,
"step": 215
},
{
"epoch": 0.07455988954090438,
"grad_norm": 3.058868885040283,
"learning_rate": 2e-05,
"loss": 0.8939,
"step": 216
},
{
"epoch": 0.07490507421470487,
"grad_norm": 3.422123908996582,
"learning_rate": 2e-05,
"loss": 0.9378,
"step": 217
},
{
"epoch": 0.07525025888850535,
"grad_norm": 3.1783478260040283,
"learning_rate": 2e-05,
"loss": 0.9485,
"step": 218
},
{
"epoch": 0.07559544356230584,
"grad_norm": 3.0557048320770264,
"learning_rate": 2e-05,
"loss": 0.8256,
"step": 219
},
{
"epoch": 0.07594062823610631,
"grad_norm": 2.9779226779937744,
"learning_rate": 2e-05,
"loss": 0.8713,
"step": 220
},
{
"epoch": 0.0762858129099068,
"grad_norm": 3.3758676052093506,
"learning_rate": 2e-05,
"loss": 0.8843,
"step": 221
},
{
"epoch": 0.07663099758370728,
"grad_norm": 3.1416192054748535,
"learning_rate": 2e-05,
"loss": 0.9064,
"step": 222
},
{
"epoch": 0.07697618225750777,
"grad_norm": 2.9653568267822266,
"learning_rate": 2e-05,
"loss": 0.8296,
"step": 223
},
{
"epoch": 0.07732136693130826,
"grad_norm": 3.2615296840667725,
"learning_rate": 2e-05,
"loss": 0.9057,
"step": 224
},
{
"epoch": 0.07766655160510873,
"grad_norm": 3.3381457328796387,
"learning_rate": 2e-05,
"loss": 0.9088,
"step": 225
},
{
"epoch": 0.07801173627890921,
"grad_norm": 3.4600749015808105,
"learning_rate": 2e-05,
"loss": 0.86,
"step": 226
},
{
"epoch": 0.0783569209527097,
"grad_norm": 3.2292826175689697,
"learning_rate": 2e-05,
"loss": 0.9591,
"step": 227
},
{
"epoch": 0.07870210562651019,
"grad_norm": 3.345545530319214,
"learning_rate": 2e-05,
"loss": 0.8476,
"step": 228
},
{
"epoch": 0.07904729030031067,
"grad_norm": 3.09397292137146,
"learning_rate": 2e-05,
"loss": 0.8652,
"step": 229
},
{
"epoch": 0.07939247497411114,
"grad_norm": 3.004117965698242,
"learning_rate": 2e-05,
"loss": 0.9689,
"step": 230
},
{
"epoch": 0.07973765964791163,
"grad_norm": 3.200100898742676,
"learning_rate": 2e-05,
"loss": 0.8666,
"step": 231
},
{
"epoch": 0.08008284432171212,
"grad_norm": 2.7272403240203857,
"learning_rate": 2e-05,
"loss": 0.8602,
"step": 232
},
{
"epoch": 0.0804280289955126,
"grad_norm": 3.2486329078674316,
"learning_rate": 2e-05,
"loss": 0.8464,
"step": 233
},
{
"epoch": 0.08077321366931309,
"grad_norm": 3.303467035293579,
"learning_rate": 2e-05,
"loss": 0.873,
"step": 234
},
{
"epoch": 0.08111839834311356,
"grad_norm": 3.0120198726654053,
"learning_rate": 2e-05,
"loss": 0.8934,
"step": 235
},
{
"epoch": 0.08146358301691405,
"grad_norm": 2.962071657180786,
"learning_rate": 2e-05,
"loss": 0.8904,
"step": 236
},
{
"epoch": 0.08180876769071453,
"grad_norm": 3.7542247772216797,
"learning_rate": 2e-05,
"loss": 0.9119,
"step": 237
},
{
"epoch": 0.08215395236451502,
"grad_norm": 3.281599521636963,
"learning_rate": 2e-05,
"loss": 0.9107,
"step": 238
},
{
"epoch": 0.0824991370383155,
"grad_norm": 3.1624579429626465,
"learning_rate": 2e-05,
"loss": 0.8766,
"step": 239
},
{
"epoch": 0.08284432171211598,
"grad_norm": 3.3022897243499756,
"learning_rate": 2e-05,
"loss": 0.9303,
"step": 240
},
{
"epoch": 0.08318950638591646,
"grad_norm": 3.1247267723083496,
"learning_rate": 2e-05,
"loss": 0.9125,
"step": 241
},
{
"epoch": 0.08353469105971695,
"grad_norm": 3.2210910320281982,
"learning_rate": 2e-05,
"loss": 0.9221,
"step": 242
},
{
"epoch": 0.08387987573351743,
"grad_norm": 3.1737873554229736,
"learning_rate": 2e-05,
"loss": 0.8178,
"step": 243
},
{
"epoch": 0.08422506040731792,
"grad_norm": 3.2427146434783936,
"learning_rate": 2e-05,
"loss": 0.9566,
"step": 244
},
{
"epoch": 0.08457024508111839,
"grad_norm": 3.4193999767303467,
"learning_rate": 2e-05,
"loss": 0.8557,
"step": 245
},
{
"epoch": 0.08491542975491888,
"grad_norm": 3.4254438877105713,
"learning_rate": 2e-05,
"loss": 0.8968,
"step": 246
},
{
"epoch": 0.08526061442871936,
"grad_norm": 3.159757614135742,
"learning_rate": 2e-05,
"loss": 0.9018,
"step": 247
},
{
"epoch": 0.08560579910251985,
"grad_norm": 3.187760353088379,
"learning_rate": 2e-05,
"loss": 0.9057,
"step": 248
},
{
"epoch": 0.08595098377632034,
"grad_norm": 2.959864616394043,
"learning_rate": 2e-05,
"loss": 0.904,
"step": 249
},
{
"epoch": 0.08629616845012081,
"grad_norm": 3.240973711013794,
"learning_rate": 2e-05,
"loss": 0.9294,
"step": 250
},
{
"epoch": 0.0866413531239213,
"grad_norm": 2.98917555809021,
"learning_rate": 2e-05,
"loss": 0.8764,
"step": 251
},
{
"epoch": 0.08698653779772178,
"grad_norm": 2.8783609867095947,
"learning_rate": 2e-05,
"loss": 0.8941,
"step": 252
},
{
"epoch": 0.08733172247152227,
"grad_norm": 3.0823488235473633,
"learning_rate": 2e-05,
"loss": 0.9319,
"step": 253
},
{
"epoch": 0.08767690714532275,
"grad_norm": 3.0972771644592285,
"learning_rate": 2e-05,
"loss": 0.8236,
"step": 254
},
{
"epoch": 0.08802209181912322,
"grad_norm": 3.005472421646118,
"learning_rate": 2e-05,
"loss": 0.8301,
"step": 255
},
{
"epoch": 0.08836727649292371,
"grad_norm": 3.145705223083496,
"learning_rate": 2e-05,
"loss": 0.866,
"step": 256
},
{
"epoch": 0.0887124611667242,
"grad_norm": 2.7804439067840576,
"learning_rate": 2e-05,
"loss": 0.8594,
"step": 257
},
{
"epoch": 0.08905764584052468,
"grad_norm": 3.092439889907837,
"learning_rate": 2e-05,
"loss": 0.8486,
"step": 258
},
{
"epoch": 0.08940283051432517,
"grad_norm": 3.228419303894043,
"learning_rate": 2e-05,
"loss": 0.8338,
"step": 259
},
{
"epoch": 0.08974801518812564,
"grad_norm": 3.093811273574829,
"learning_rate": 2e-05,
"loss": 0.9424,
"step": 260
},
{
"epoch": 0.09009319986192613,
"grad_norm": 3.0747523307800293,
"learning_rate": 2e-05,
"loss": 0.8944,
"step": 261
},
{
"epoch": 0.09043838453572661,
"grad_norm": 3.186995267868042,
"learning_rate": 2e-05,
"loss": 0.8586,
"step": 262
},
{
"epoch": 0.0907835692095271,
"grad_norm": 3.1833300590515137,
"learning_rate": 2e-05,
"loss": 0.8728,
"step": 263
},
{
"epoch": 0.09112875388332758,
"grad_norm": 3.0900795459747314,
"learning_rate": 2e-05,
"loss": 0.9022,
"step": 264
},
{
"epoch": 0.09147393855712806,
"grad_norm": 3.004206895828247,
"learning_rate": 2e-05,
"loss": 0.9062,
"step": 265
},
{
"epoch": 0.09181912323092854,
"grad_norm": 3.1954448223114014,
"learning_rate": 2e-05,
"loss": 0.8732,
"step": 266
},
{
"epoch": 0.09216430790472903,
"grad_norm": 3.324725866317749,
"learning_rate": 2e-05,
"loss": 0.9214,
"step": 267
},
{
"epoch": 0.09250949257852951,
"grad_norm": 2.8366189002990723,
"learning_rate": 2e-05,
"loss": 0.9153,
"step": 268
},
{
"epoch": 0.09285467725233,
"grad_norm": 3.264113187789917,
"learning_rate": 2e-05,
"loss": 0.8697,
"step": 269
},
{
"epoch": 0.09319986192613049,
"grad_norm": 3.186286211013794,
"learning_rate": 2e-05,
"loss": 0.9348,
"step": 270
},
{
"epoch": 0.09354504659993096,
"grad_norm": 2.8541440963745117,
"learning_rate": 2e-05,
"loss": 0.9067,
"step": 271
},
{
"epoch": 0.09389023127373144,
"grad_norm": 3.074235200881958,
"learning_rate": 2e-05,
"loss": 0.8935,
"step": 272
},
{
"epoch": 0.09423541594753193,
"grad_norm": 3.0192456245422363,
"learning_rate": 2e-05,
"loss": 0.8231,
"step": 273
},
{
"epoch": 0.09458060062133242,
"grad_norm": 2.740384101867676,
"learning_rate": 2e-05,
"loss": 0.8533,
"step": 274
},
{
"epoch": 0.0949257852951329,
"grad_norm": 2.9101722240448,
"learning_rate": 2e-05,
"loss": 0.8529,
"step": 275
},
{
"epoch": 0.09527096996893337,
"grad_norm": 3.137927770614624,
"learning_rate": 2e-05,
"loss": 0.9192,
"step": 276
},
{
"epoch": 0.09561615464273386,
"grad_norm": 3.054185628890991,
"learning_rate": 2e-05,
"loss": 0.8945,
"step": 277
},
{
"epoch": 0.09596133931653435,
"grad_norm": 3.1088597774505615,
"learning_rate": 2e-05,
"loss": 0.9008,
"step": 278
},
{
"epoch": 0.09630652399033483,
"grad_norm": 2.7827138900756836,
"learning_rate": 2e-05,
"loss": 0.8461,
"step": 279
},
{
"epoch": 0.09665170866413532,
"grad_norm": 2.864086389541626,
"learning_rate": 2e-05,
"loss": 0.8751,
"step": 280
},
{
"epoch": 0.09699689333793579,
"grad_norm": 3.1949148178100586,
"learning_rate": 2e-05,
"loss": 0.8377,
"step": 281
},
{
"epoch": 0.09734207801173628,
"grad_norm": 2.7971835136413574,
"learning_rate": 2e-05,
"loss": 0.9062,
"step": 282
},
{
"epoch": 0.09768726268553676,
"grad_norm": 6.014020919799805,
"learning_rate": 2e-05,
"loss": 0.8477,
"step": 283
},
{
"epoch": 0.09803244735933725,
"grad_norm": 3.1988205909729004,
"learning_rate": 2e-05,
"loss": 0.8605,
"step": 284
},
{
"epoch": 0.09837763203313774,
"grad_norm": 3.0080959796905518,
"learning_rate": 2e-05,
"loss": 0.9122,
"step": 285
},
{
"epoch": 0.09872281670693821,
"grad_norm": 2.848585844039917,
"learning_rate": 2e-05,
"loss": 0.861,
"step": 286
},
{
"epoch": 0.0990680013807387,
"grad_norm": 3.069856882095337,
"learning_rate": 2e-05,
"loss": 0.9373,
"step": 287
},
{
"epoch": 0.09941318605453918,
"grad_norm": 3.0742900371551514,
"learning_rate": 2e-05,
"loss": 0.907,
"step": 288
},
{
"epoch": 0.09975837072833967,
"grad_norm": 2.8606960773468018,
"learning_rate": 2e-05,
"loss": 0.8644,
"step": 289
},
{
"epoch": 0.10010355540214015,
"grad_norm": 2.9489126205444336,
"learning_rate": 2e-05,
"loss": 0.8922,
"step": 290
},
{
"epoch": 0.10044874007594062,
"grad_norm": 3.0227949619293213,
"learning_rate": 2e-05,
"loss": 0.9255,
"step": 291
},
{
"epoch": 0.10079392474974111,
"grad_norm": 2.758237361907959,
"learning_rate": 2e-05,
"loss": 0.8339,
"step": 292
},
{
"epoch": 0.1011391094235416,
"grad_norm": 2.8767168521881104,
"learning_rate": 2e-05,
"loss": 0.8697,
"step": 293
},
{
"epoch": 0.10148429409734208,
"grad_norm": 2.8063676357269287,
"learning_rate": 2e-05,
"loss": 0.8628,
"step": 294
},
{
"epoch": 0.10182947877114257,
"grad_norm": 2.9139151573181152,
"learning_rate": 2e-05,
"loss": 0.9157,
"step": 295
},
{
"epoch": 0.10217466344494304,
"grad_norm": 2.857400894165039,
"learning_rate": 2e-05,
"loss": 0.892,
"step": 296
},
{
"epoch": 0.10251984811874353,
"grad_norm": 2.8675410747528076,
"learning_rate": 2e-05,
"loss": 0.8438,
"step": 297
},
{
"epoch": 0.10286503279254401,
"grad_norm": 2.8956315517425537,
"learning_rate": 2e-05,
"loss": 0.847,
"step": 298
},
{
"epoch": 0.1032102174663445,
"grad_norm": 2.743086099624634,
"learning_rate": 2e-05,
"loss": 0.9041,
"step": 299
},
{
"epoch": 0.10355540214014498,
"grad_norm": 3.0366575717926025,
"learning_rate": 2e-05,
"loss": 0.8704,
"step": 300
},
{
"epoch": 0.10390058681394546,
"grad_norm": 3.290945291519165,
"learning_rate": 2e-05,
"loss": 0.7993,
"step": 301
},
{
"epoch": 0.10424577148774594,
"grad_norm": 2.562634229660034,
"learning_rate": 2e-05,
"loss": 0.7964,
"step": 302
},
{
"epoch": 0.10459095616154643,
"grad_norm": 3.005824089050293,
"learning_rate": 2e-05,
"loss": 0.8158,
"step": 303
},
{
"epoch": 0.10493614083534691,
"grad_norm": 2.912410259246826,
"learning_rate": 2e-05,
"loss": 0.8584,
"step": 304
},
{
"epoch": 0.1052813255091474,
"grad_norm": 2.7015678882598877,
"learning_rate": 2e-05,
"loss": 0.8731,
"step": 305
},
{
"epoch": 0.10562651018294787,
"grad_norm": 2.857595682144165,
"learning_rate": 2e-05,
"loss": 0.8809,
"step": 306
},
{
"epoch": 0.10597169485674836,
"grad_norm": 2.7211265563964844,
"learning_rate": 2e-05,
"loss": 0.9234,
"step": 307
},
{
"epoch": 0.10631687953054884,
"grad_norm": 3.018676519393921,
"learning_rate": 2e-05,
"loss": 0.9101,
"step": 308
},
{
"epoch": 0.10666206420434933,
"grad_norm": 2.8703527450561523,
"learning_rate": 2e-05,
"loss": 0.852,
"step": 309
},
{
"epoch": 0.10700724887814982,
"grad_norm": 2.912076473236084,
"learning_rate": 2e-05,
"loss": 0.8749,
"step": 310
},
{
"epoch": 0.10735243355195029,
"grad_norm": 2.652156352996826,
"learning_rate": 2e-05,
"loss": 0.8838,
"step": 311
},
{
"epoch": 0.10769761822575077,
"grad_norm": 2.8902244567871094,
"learning_rate": 2e-05,
"loss": 0.8898,
"step": 312
},
{
"epoch": 0.10804280289955126,
"grad_norm": 2.7108359336853027,
"learning_rate": 2e-05,
"loss": 0.8312,
"step": 313
},
{
"epoch": 0.10838798757335175,
"grad_norm": 2.6468076705932617,
"learning_rate": 2e-05,
"loss": 0.7757,
"step": 314
},
{
"epoch": 0.10873317224715223,
"grad_norm": 2.969503402709961,
"learning_rate": 2e-05,
"loss": 0.8498,
"step": 315
},
{
"epoch": 0.1090783569209527,
"grad_norm": 2.7394843101501465,
"learning_rate": 2e-05,
"loss": 0.9067,
"step": 316
},
{
"epoch": 0.10942354159475319,
"grad_norm": 2.8321640491485596,
"learning_rate": 2e-05,
"loss": 0.8693,
"step": 317
},
{
"epoch": 0.10976872626855368,
"grad_norm": 3.0017828941345215,
"learning_rate": 2e-05,
"loss": 0.8555,
"step": 318
},
{
"epoch": 0.11011391094235416,
"grad_norm": 2.7267954349517822,
"learning_rate": 2e-05,
"loss": 0.8947,
"step": 319
},
{
"epoch": 0.11045909561615465,
"grad_norm": 2.9304072856903076,
"learning_rate": 2e-05,
"loss": 0.9042,
"step": 320
},
{
"epoch": 0.11080428028995512,
"grad_norm": 2.9202630519866943,
"learning_rate": 2e-05,
"loss": 0.8426,
"step": 321
},
{
"epoch": 0.1111494649637556,
"grad_norm": 3.0602047443389893,
"learning_rate": 2e-05,
"loss": 0.8573,
"step": 322
},
{
"epoch": 0.11149464963755609,
"grad_norm": 2.987820863723755,
"learning_rate": 2e-05,
"loss": 0.8695,
"step": 323
},
{
"epoch": 0.11183983431135658,
"grad_norm": 3.158129930496216,
"learning_rate": 2e-05,
"loss": 0.9306,
"step": 324
},
{
"epoch": 0.11218501898515706,
"grad_norm": 2.893429756164551,
"learning_rate": 2e-05,
"loss": 0.9157,
"step": 325
},
{
"epoch": 0.11253020365895754,
"grad_norm": 3.009833335876465,
"learning_rate": 2e-05,
"loss": 0.9162,
"step": 326
},
{
"epoch": 0.11287538833275802,
"grad_norm": 2.768258571624756,
"learning_rate": 2e-05,
"loss": 0.8547,
"step": 327
},
{
"epoch": 0.11322057300655851,
"grad_norm": 3.0964066982269287,
"learning_rate": 2e-05,
"loss": 0.8735,
"step": 328
},
{
"epoch": 0.113565757680359,
"grad_norm": 2.9525063037872314,
"learning_rate": 2e-05,
"loss": 0.8907,
"step": 329
},
{
"epoch": 0.11391094235415948,
"grad_norm": 3.317748785018921,
"learning_rate": 2e-05,
"loss": 0.8673,
"step": 330
},
{
"epoch": 0.11425612702795995,
"grad_norm": 2.934115409851074,
"learning_rate": 2e-05,
"loss": 0.8477,
"step": 331
},
{
"epoch": 0.11460131170176044,
"grad_norm": 2.8080825805664062,
"learning_rate": 2e-05,
"loss": 0.9336,
"step": 332
},
{
"epoch": 0.11494649637556092,
"grad_norm": 2.938957929611206,
"learning_rate": 2e-05,
"loss": 0.8972,
"step": 333
},
{
"epoch": 0.11529168104936141,
"grad_norm": 2.778604745864868,
"learning_rate": 2e-05,
"loss": 0.8013,
"step": 334
},
{
"epoch": 0.1156368657231619,
"grad_norm": 2.779245376586914,
"learning_rate": 2e-05,
"loss": 0.9065,
"step": 335
},
{
"epoch": 0.11598205039696237,
"grad_norm": 2.834568738937378,
"learning_rate": 2e-05,
"loss": 0.8904,
"step": 336
},
{
"epoch": 0.11632723507076285,
"grad_norm": 2.7382054328918457,
"learning_rate": 2e-05,
"loss": 0.8932,
"step": 337
},
{
"epoch": 0.11667241974456334,
"grad_norm": 2.746325731277466,
"learning_rate": 2e-05,
"loss": 0.8365,
"step": 338
},
{
"epoch": 0.11701760441836383,
"grad_norm": 2.750140905380249,
"learning_rate": 2e-05,
"loss": 0.8255,
"step": 339
},
{
"epoch": 0.11736278909216431,
"grad_norm": 3.3976187705993652,
"learning_rate": 2e-05,
"loss": 0.859,
"step": 340
},
{
"epoch": 0.11770797376596479,
"grad_norm": 3.004563093185425,
"learning_rate": 2e-05,
"loss": 0.8895,
"step": 341
},
{
"epoch": 0.11805315843976527,
"grad_norm": 3.343090295791626,
"learning_rate": 2e-05,
"loss": 0.8644,
"step": 342
},
{
"epoch": 0.11839834311356576,
"grad_norm": 2.7037289142608643,
"learning_rate": 2e-05,
"loss": 0.834,
"step": 343
},
{
"epoch": 0.11874352778736624,
"grad_norm": 2.881302833557129,
"learning_rate": 2e-05,
"loss": 0.8343,
"step": 344
},
{
"epoch": 0.11908871246116673,
"grad_norm": 2.9096665382385254,
"learning_rate": 2e-05,
"loss": 0.8559,
"step": 345
},
{
"epoch": 0.1194338971349672,
"grad_norm": 3.109509229660034,
"learning_rate": 2e-05,
"loss": 0.9016,
"step": 346
},
{
"epoch": 0.11977908180876769,
"grad_norm": 2.9444544315338135,
"learning_rate": 2e-05,
"loss": 0.8391,
"step": 347
},
{
"epoch": 0.12012426648256817,
"grad_norm": 3.122678518295288,
"learning_rate": 2e-05,
"loss": 0.8868,
"step": 348
},
{
"epoch": 0.12046945115636866,
"grad_norm": 2.646322250366211,
"learning_rate": 2e-05,
"loss": 0.8174,
"step": 349
},
{
"epoch": 0.12081463583016915,
"grad_norm": 2.9330692291259766,
"learning_rate": 2e-05,
"loss": 0.8805,
"step": 350
},
{
"epoch": 0.12115982050396962,
"grad_norm": 2.9383981227874756,
"learning_rate": 2e-05,
"loss": 0.8618,
"step": 351
},
{
"epoch": 0.1215050051777701,
"grad_norm": 2.9238908290863037,
"learning_rate": 2e-05,
"loss": 0.9407,
"step": 352
},
{
"epoch": 0.12185018985157059,
"grad_norm": 2.8855233192443848,
"learning_rate": 2e-05,
"loss": 0.8713,
"step": 353
},
{
"epoch": 0.12219537452537108,
"grad_norm": 2.822115182876587,
"learning_rate": 2e-05,
"loss": 0.8916,
"step": 354
},
{
"epoch": 0.12254055919917156,
"grad_norm": 2.8500313758850098,
"learning_rate": 2e-05,
"loss": 0.8349,
"step": 355
},
{
"epoch": 0.12288574387297203,
"grad_norm": 3.022473096847534,
"learning_rate": 2e-05,
"loss": 0.8479,
"step": 356
},
{
"epoch": 0.12323092854677252,
"grad_norm": 2.7787365913391113,
"learning_rate": 2e-05,
"loss": 0.8833,
"step": 357
},
{
"epoch": 0.123576113220573,
"grad_norm": 2.9101765155792236,
"learning_rate": 2e-05,
"loss": 0.888,
"step": 358
},
{
"epoch": 0.12392129789437349,
"grad_norm": 2.7252466678619385,
"learning_rate": 2e-05,
"loss": 0.8657,
"step": 359
},
{
"epoch": 0.12426648256817398,
"grad_norm": 2.8830056190490723,
"learning_rate": 2e-05,
"loss": 0.8259,
"step": 360
},
{
"epoch": 0.12461166724197445,
"grad_norm": 2.671375274658203,
"learning_rate": 2e-05,
"loss": 0.8253,
"step": 361
},
{
"epoch": 0.12495685191577494,
"grad_norm": 2.706015110015869,
"learning_rate": 2e-05,
"loss": 0.838,
"step": 362
},
{
"epoch": 0.12530203658957542,
"grad_norm": 2.616062641143799,
"learning_rate": 2e-05,
"loss": 0.8607,
"step": 363
},
{
"epoch": 0.1256472212633759,
"grad_norm": 3.385586738586426,
"learning_rate": 2e-05,
"loss": 0.8603,
"step": 364
},
{
"epoch": 0.1259924059371764,
"grad_norm": 2.9748425483703613,
"learning_rate": 2e-05,
"loss": 0.8802,
"step": 365
},
{
"epoch": 0.12633759061097688,
"grad_norm": 3.009232759475708,
"learning_rate": 2e-05,
"loss": 0.8572,
"step": 366
},
{
"epoch": 0.12668277528477737,
"grad_norm": 2.995032548904419,
"learning_rate": 2e-05,
"loss": 0.8542,
"step": 367
},
{
"epoch": 0.12702795995857785,
"grad_norm": 3.1191444396972656,
"learning_rate": 2e-05,
"loss": 0.9096,
"step": 368
},
{
"epoch": 0.1273731446323783,
"grad_norm": 3.3370883464813232,
"learning_rate": 2e-05,
"loss": 0.8456,
"step": 369
},
{
"epoch": 0.1277183293061788,
"grad_norm": 2.910351276397705,
"learning_rate": 2e-05,
"loss": 0.8415,
"step": 370
},
{
"epoch": 0.12806351397997928,
"grad_norm": 2.381078004837036,
"learning_rate": 2e-05,
"loss": 0.7864,
"step": 371
},
{
"epoch": 0.12840869865377977,
"grad_norm": 2.8764638900756836,
"learning_rate": 2e-05,
"loss": 0.8731,
"step": 372
},
{
"epoch": 0.12875388332758025,
"grad_norm": 2.9746713638305664,
"learning_rate": 2e-05,
"loss": 0.8447,
"step": 373
},
{
"epoch": 0.12909906800138074,
"grad_norm": 2.7619199752807617,
"learning_rate": 2e-05,
"loss": 0.8315,
"step": 374
},
{
"epoch": 0.12944425267518123,
"grad_norm": 2.5940611362457275,
"learning_rate": 2e-05,
"loss": 0.8749,
"step": 375
},
{
"epoch": 0.1297894373489817,
"grad_norm": 2.9887807369232178,
"learning_rate": 2e-05,
"loss": 0.9069,
"step": 376
},
{
"epoch": 0.1301346220227822,
"grad_norm": 3.1408069133758545,
"learning_rate": 2e-05,
"loss": 0.9029,
"step": 377
},
{
"epoch": 0.13047980669658268,
"grad_norm": 2.876115083694458,
"learning_rate": 2e-05,
"loss": 0.9135,
"step": 378
},
{
"epoch": 0.13082499137038314,
"grad_norm": 2.7395379543304443,
"learning_rate": 2e-05,
"loss": 0.8597,
"step": 379
},
{
"epoch": 0.13117017604418363,
"grad_norm": 3.036904811859131,
"learning_rate": 2e-05,
"loss": 0.8886,
"step": 380
},
{
"epoch": 0.13151536071798411,
"grad_norm": 3.047651767730713,
"learning_rate": 2e-05,
"loss": 0.8923,
"step": 381
},
{
"epoch": 0.1318605453917846,
"grad_norm": 2.8202462196350098,
"learning_rate": 2e-05,
"loss": 0.8434,
"step": 382
},
{
"epoch": 0.1322057300655851,
"grad_norm": 2.605100393295288,
"learning_rate": 2e-05,
"loss": 0.8975,
"step": 383
},
{
"epoch": 0.13255091473938557,
"grad_norm": 2.781841516494751,
"learning_rate": 2e-05,
"loss": 0.809,
"step": 384
},
{
"epoch": 0.13289609941318606,
"grad_norm": 2.6456520557403564,
"learning_rate": 2e-05,
"loss": 0.8827,
"step": 385
},
{
"epoch": 0.13324128408698654,
"grad_norm": 10.660346984863281,
"learning_rate": 2e-05,
"loss": 0.8615,
"step": 386
},
{
"epoch": 0.13358646876078703,
"grad_norm": 3.2193210124969482,
"learning_rate": 2e-05,
"loss": 0.8553,
"step": 387
},
{
"epoch": 0.13393165343458752,
"grad_norm": 2.9482877254486084,
"learning_rate": 2e-05,
"loss": 0.7931,
"step": 388
},
{
"epoch": 0.13427683810838797,
"grad_norm": 2.851332664489746,
"learning_rate": 2e-05,
"loss": 0.8291,
"step": 389
},
{
"epoch": 0.13462202278218846,
"grad_norm": 3.519622802734375,
"learning_rate": 2e-05,
"loss": 0.8803,
"step": 390
},
{
"epoch": 0.13496720745598895,
"grad_norm": 2.979022741317749,
"learning_rate": 2e-05,
"loss": 0.9023,
"step": 391
},
{
"epoch": 0.13531239212978943,
"grad_norm": 2.8534867763519287,
"learning_rate": 2e-05,
"loss": 0.8652,
"step": 392
},
{
"epoch": 0.13565757680358992,
"grad_norm": 2.7661948204040527,
"learning_rate": 2e-05,
"loss": 0.8136,
"step": 393
},
{
"epoch": 0.1360027614773904,
"grad_norm": 2.6558003425598145,
"learning_rate": 2e-05,
"loss": 0.8805,
"step": 394
},
{
"epoch": 0.1363479461511909,
"grad_norm": 2.9477477073669434,
"learning_rate": 2e-05,
"loss": 0.8341,
"step": 395
},
{
"epoch": 0.13669313082499138,
"grad_norm": 2.777376174926758,
"learning_rate": 2e-05,
"loss": 0.8435,
"step": 396
},
{
"epoch": 0.13703831549879186,
"grad_norm": 2.947483777999878,
"learning_rate": 2e-05,
"loss": 0.8495,
"step": 397
},
{
"epoch": 0.13738350017259235,
"grad_norm": 2.923473834991455,
"learning_rate": 2e-05,
"loss": 0.8357,
"step": 398
},
{
"epoch": 0.1377286848463928,
"grad_norm": 2.5483436584472656,
"learning_rate": 2e-05,
"loss": 0.7862,
"step": 399
},
{
"epoch": 0.1380738695201933,
"grad_norm": 2.5327706336975098,
"learning_rate": 2e-05,
"loss": 0.8527,
"step": 400
},
{
"epoch": 0.13841905419399378,
"grad_norm": 2.684678792953491,
"learning_rate": 2e-05,
"loss": 0.8465,
"step": 401
},
{
"epoch": 0.13876423886779427,
"grad_norm": 2.74104905128479,
"learning_rate": 2e-05,
"loss": 0.8284,
"step": 402
},
{
"epoch": 0.13910942354159475,
"grad_norm": 3.0023629665374756,
"learning_rate": 2e-05,
"loss": 0.8337,
"step": 403
},
{
"epoch": 0.13945460821539524,
"grad_norm": 2.791071891784668,
"learning_rate": 2e-05,
"loss": 0.7955,
"step": 404
},
{
"epoch": 0.13979979288919572,
"grad_norm": 3.101384401321411,
"learning_rate": 2e-05,
"loss": 0.866,
"step": 405
},
{
"epoch": 0.1401449775629962,
"grad_norm": 2.731903553009033,
"learning_rate": 2e-05,
"loss": 0.8317,
"step": 406
},
{
"epoch": 0.1404901622367967,
"grad_norm": 2.892133951187134,
"learning_rate": 2e-05,
"loss": 0.8903,
"step": 407
},
{
"epoch": 0.14083534691059718,
"grad_norm": 2.6382410526275635,
"learning_rate": 2e-05,
"loss": 0.8085,
"step": 408
},
{
"epoch": 0.14118053158439764,
"grad_norm": 2.5040509700775146,
"learning_rate": 2e-05,
"loss": 0.7556,
"step": 409
},
{
"epoch": 0.14152571625819813,
"grad_norm": 2.659632921218872,
"learning_rate": 2e-05,
"loss": 0.8627,
"step": 410
},
{
"epoch": 0.1418709009319986,
"grad_norm": 2.9481699466705322,
"learning_rate": 2e-05,
"loss": 0.769,
"step": 411
},
{
"epoch": 0.1422160856057991,
"grad_norm": 2.7535393238067627,
"learning_rate": 2e-05,
"loss": 0.8624,
"step": 412
},
{
"epoch": 0.14256127027959958,
"grad_norm": 2.8887505531311035,
"learning_rate": 2e-05,
"loss": 0.8746,
"step": 413
},
{
"epoch": 0.14290645495340007,
"grad_norm": 3.1027655601501465,
"learning_rate": 2e-05,
"loss": 0.8201,
"step": 414
},
{
"epoch": 0.14325163962720056,
"grad_norm": 2.7258031368255615,
"learning_rate": 2e-05,
"loss": 0.8758,
"step": 415
},
{
"epoch": 0.14359682430100104,
"grad_norm": 3.6109793186187744,
"learning_rate": 2e-05,
"loss": 0.8368,
"step": 416
},
{
"epoch": 0.14394200897480153,
"grad_norm": 3.0309035778045654,
"learning_rate": 2e-05,
"loss": 0.8502,
"step": 417
},
{
"epoch": 0.144287193648602,
"grad_norm": 2.7749741077423096,
"learning_rate": 2e-05,
"loss": 0.8239,
"step": 418
},
{
"epoch": 0.14463237832240247,
"grad_norm": 3.057831287384033,
"learning_rate": 2e-05,
"loss": 0.8649,
"step": 419
},
{
"epoch": 0.14497756299620296,
"grad_norm": 2.7731754779815674,
"learning_rate": 2e-05,
"loss": 0.8073,
"step": 420
},
{
"epoch": 0.14532274767000344,
"grad_norm": 2.7278342247009277,
"learning_rate": 2e-05,
"loss": 0.8367,
"step": 421
},
{
"epoch": 0.14566793234380393,
"grad_norm": 2.941387891769409,
"learning_rate": 2e-05,
"loss": 0.8205,
"step": 422
},
{
"epoch": 0.14601311701760442,
"grad_norm": 2.7232892513275146,
"learning_rate": 2e-05,
"loss": 0.8872,
"step": 423
},
{
"epoch": 0.1463583016914049,
"grad_norm": 2.953651189804077,
"learning_rate": 2e-05,
"loss": 0.8523,
"step": 424
},
{
"epoch": 0.1467034863652054,
"grad_norm": 2.7981178760528564,
"learning_rate": 2e-05,
"loss": 0.8528,
"step": 425
},
{
"epoch": 0.14704867103900587,
"grad_norm": 2.7209296226501465,
"learning_rate": 2e-05,
"loss": 0.8183,
"step": 426
},
{
"epoch": 0.14739385571280636,
"grad_norm": 2.716719627380371,
"learning_rate": 2e-05,
"loss": 0.8502,
"step": 427
},
{
"epoch": 0.14773904038660685,
"grad_norm": 2.8264238834381104,
"learning_rate": 2e-05,
"loss": 0.8225,
"step": 428
},
{
"epoch": 0.1480842250604073,
"grad_norm": 2.665504217147827,
"learning_rate": 2e-05,
"loss": 0.7785,
"step": 429
},
{
"epoch": 0.1484294097342078,
"grad_norm": 2.574075698852539,
"learning_rate": 2e-05,
"loss": 0.8745,
"step": 430
},
{
"epoch": 0.14877459440800828,
"grad_norm": 2.8665859699249268,
"learning_rate": 2e-05,
"loss": 0.8567,
"step": 431
},
{
"epoch": 0.14911977908180876,
"grad_norm": 2.5270538330078125,
"learning_rate": 2e-05,
"loss": 0.8125,
"step": 432
},
{
"epoch": 0.14946496375560925,
"grad_norm": 2.569016933441162,
"learning_rate": 2e-05,
"loss": 0.8516,
"step": 433
},
{
"epoch": 0.14981014842940973,
"grad_norm": 2.6712615489959717,
"learning_rate": 2e-05,
"loss": 0.8079,
"step": 434
},
{
"epoch": 0.15015533310321022,
"grad_norm": 2.6932435035705566,
"learning_rate": 2e-05,
"loss": 0.818,
"step": 435
},
{
"epoch": 0.1505005177770107,
"grad_norm": 2.5300912857055664,
"learning_rate": 2e-05,
"loss": 0.867,
"step": 436
},
{
"epoch": 0.1508457024508112,
"grad_norm": 2.4744701385498047,
"learning_rate": 2e-05,
"loss": 0.863,
"step": 437
},
{
"epoch": 0.15119088712461168,
"grad_norm": 4.339775562286377,
"learning_rate": 2e-05,
"loss": 0.8626,
"step": 438
},
{
"epoch": 0.15153607179841216,
"grad_norm": 2.5476183891296387,
"learning_rate": 2e-05,
"loss": 0.8193,
"step": 439
},
{
"epoch": 0.15188125647221262,
"grad_norm": 2.7269837856292725,
"learning_rate": 2e-05,
"loss": 0.8251,
"step": 440
},
{
"epoch": 0.1522264411460131,
"grad_norm": 2.843550205230713,
"learning_rate": 2e-05,
"loss": 0.8724,
"step": 441
},
{
"epoch": 0.1525716258198136,
"grad_norm": 5.800281524658203,
"learning_rate": 2e-05,
"loss": 0.7982,
"step": 442
},
{
"epoch": 0.15291681049361408,
"grad_norm": 2.7126641273498535,
"learning_rate": 2e-05,
"loss": 0.7775,
"step": 443
},
{
"epoch": 0.15326199516741457,
"grad_norm": 2.8936424255371094,
"learning_rate": 2e-05,
"loss": 0.8628,
"step": 444
},
{
"epoch": 0.15360717984121505,
"grad_norm": 2.403440475463867,
"learning_rate": 2e-05,
"loss": 0.8367,
"step": 445
},
{
"epoch": 0.15395236451501554,
"grad_norm": 2.6871049404144287,
"learning_rate": 2e-05,
"loss": 0.7947,
"step": 446
},
{
"epoch": 0.15429754918881602,
"grad_norm": 2.6108877658843994,
"learning_rate": 2e-05,
"loss": 0.868,
"step": 447
},
{
"epoch": 0.1546427338626165,
"grad_norm": 2.7435109615325928,
"learning_rate": 2e-05,
"loss": 0.8498,
"step": 448
},
{
"epoch": 0.154987918536417,
"grad_norm": 2.5271124839782715,
"learning_rate": 2e-05,
"loss": 0.8271,
"step": 449
},
{
"epoch": 0.15533310321021745,
"grad_norm": 2.607501268386841,
"learning_rate": 2e-05,
"loss": 0.8588,
"step": 450
},
{
"epoch": 0.15567828788401794,
"grad_norm": 2.610903024673462,
"learning_rate": 2e-05,
"loss": 0.8411,
"step": 451
},
{
"epoch": 0.15602347255781843,
"grad_norm": 2.6607000827789307,
"learning_rate": 2e-05,
"loss": 0.8085,
"step": 452
},
{
"epoch": 0.1563686572316189,
"grad_norm": 2.6461052894592285,
"learning_rate": 2e-05,
"loss": 0.8041,
"step": 453
},
{
"epoch": 0.1567138419054194,
"grad_norm": 2.7526638507843018,
"learning_rate": 2e-05,
"loss": 0.8848,
"step": 454
},
{
"epoch": 0.15705902657921988,
"grad_norm": 2.546306610107422,
"learning_rate": 2e-05,
"loss": 0.8602,
"step": 455
},
{
"epoch": 0.15740421125302037,
"grad_norm": 2.6657474040985107,
"learning_rate": 2e-05,
"loss": 0.8307,
"step": 456
},
{
"epoch": 0.15774939592682086,
"grad_norm": 2.6293036937713623,
"learning_rate": 2e-05,
"loss": 0.8155,
"step": 457
},
{
"epoch": 0.15809458060062134,
"grad_norm": 3.03344988822937,
"learning_rate": 2e-05,
"loss": 0.819,
"step": 458
},
{
"epoch": 0.15843976527442183,
"grad_norm": 2.7682418823242188,
"learning_rate": 2e-05,
"loss": 0.8674,
"step": 459
},
{
"epoch": 0.1587849499482223,
"grad_norm": 2.441422462463379,
"learning_rate": 2e-05,
"loss": 0.7109,
"step": 460
},
{
"epoch": 0.15913013462202277,
"grad_norm": 3.0306053161621094,
"learning_rate": 2e-05,
"loss": 0.8352,
"step": 461
},
{
"epoch": 0.15947531929582326,
"grad_norm": 3.1089224815368652,
"learning_rate": 2e-05,
"loss": 0.9059,
"step": 462
},
{
"epoch": 0.15982050396962375,
"grad_norm": 2.5796120166778564,
"learning_rate": 2e-05,
"loss": 0.7726,
"step": 463
},
{
"epoch": 0.16016568864342423,
"grad_norm": 2.7144784927368164,
"learning_rate": 2e-05,
"loss": 0.7258,
"step": 464
},
{
"epoch": 0.16051087331722472,
"grad_norm": 2.6572415828704834,
"learning_rate": 2e-05,
"loss": 0.8354,
"step": 465
},
{
"epoch": 0.1608560579910252,
"grad_norm": 2.556910753250122,
"learning_rate": 2e-05,
"loss": 0.8727,
"step": 466
},
{
"epoch": 0.1612012426648257,
"grad_norm": 2.621105194091797,
"learning_rate": 2e-05,
"loss": 0.8326,
"step": 467
},
{
"epoch": 0.16154642733862618,
"grad_norm": 2.4325952529907227,
"learning_rate": 2e-05,
"loss": 0.8102,
"step": 468
},
{
"epoch": 0.16189161201242666,
"grad_norm": 2.616182327270508,
"learning_rate": 2e-05,
"loss": 0.8983,
"step": 469
},
{
"epoch": 0.16223679668622712,
"grad_norm": 2.7066891193389893,
"learning_rate": 2e-05,
"loss": 0.8761,
"step": 470
},
{
"epoch": 0.1625819813600276,
"grad_norm": 2.4946465492248535,
"learning_rate": 2e-05,
"loss": 0.8051,
"step": 471
},
{
"epoch": 0.1629271660338281,
"grad_norm": 2.7673726081848145,
"learning_rate": 2e-05,
"loss": 0.8436,
"step": 472
},
{
"epoch": 0.16327235070762858,
"grad_norm": 2.8104934692382812,
"learning_rate": 2e-05,
"loss": 0.83,
"step": 473
},
{
"epoch": 0.16361753538142906,
"grad_norm": 2.5568485260009766,
"learning_rate": 2e-05,
"loss": 0.8144,
"step": 474
},
{
"epoch": 0.16396272005522955,
"grad_norm": 2.5758121013641357,
"learning_rate": 2e-05,
"loss": 0.838,
"step": 475
},
{
"epoch": 0.16430790472903004,
"grad_norm": 2.492135524749756,
"learning_rate": 2e-05,
"loss": 0.8959,
"step": 476
},
{
"epoch": 0.16465308940283052,
"grad_norm": 2.6613054275512695,
"learning_rate": 2e-05,
"loss": 0.8152,
"step": 477
},
{
"epoch": 0.164998274076631,
"grad_norm": 2.75256609916687,
"learning_rate": 2e-05,
"loss": 0.8267,
"step": 478
},
{
"epoch": 0.1653434587504315,
"grad_norm": 2.8076133728027344,
"learning_rate": 2e-05,
"loss": 0.7922,
"step": 479
},
{
"epoch": 0.16568864342423195,
"grad_norm": 2.722338914871216,
"learning_rate": 2e-05,
"loss": 0.8598,
"step": 480
},
{
"epoch": 0.16603382809803244,
"grad_norm": 2.5735299587249756,
"learning_rate": 2e-05,
"loss": 0.7875,
"step": 481
},
{
"epoch": 0.16637901277183292,
"grad_norm": 2.702031373977661,
"learning_rate": 2e-05,
"loss": 0.8604,
"step": 482
},
{
"epoch": 0.1667241974456334,
"grad_norm": 2.734985589981079,
"learning_rate": 2e-05,
"loss": 0.851,
"step": 483
},
{
"epoch": 0.1670693821194339,
"grad_norm": 2.9320790767669678,
"learning_rate": 2e-05,
"loss": 0.8655,
"step": 484
},
{
"epoch": 0.16741456679323438,
"grad_norm": 2.8295514583587646,
"learning_rate": 2e-05,
"loss": 0.8963,
"step": 485
},
{
"epoch": 0.16775975146703487,
"grad_norm": 2.4725968837738037,
"learning_rate": 2e-05,
"loss": 0.8372,
"step": 486
},
{
"epoch": 0.16810493614083535,
"grad_norm": 2.6364479064941406,
"learning_rate": 2e-05,
"loss": 0.8244,
"step": 487
},
{
"epoch": 0.16845012081463584,
"grad_norm": 3.3929388523101807,
"learning_rate": 2e-05,
"loss": 0.8379,
"step": 488
},
{
"epoch": 0.16879530548843633,
"grad_norm": 2.701646566390991,
"learning_rate": 2e-05,
"loss": 0.8196,
"step": 489
},
{
"epoch": 0.16914049016223678,
"grad_norm": 2.559340476989746,
"learning_rate": 2e-05,
"loss": 0.7844,
"step": 490
},
{
"epoch": 0.16948567483603727,
"grad_norm": 2.644239664077759,
"learning_rate": 2e-05,
"loss": 0.8601,
"step": 491
},
{
"epoch": 0.16983085950983776,
"grad_norm": 2.5983693599700928,
"learning_rate": 2e-05,
"loss": 0.8278,
"step": 492
},
{
"epoch": 0.17017604418363824,
"grad_norm": 2.650519609451294,
"learning_rate": 2e-05,
"loss": 0.8763,
"step": 493
},
{
"epoch": 0.17052122885743873,
"grad_norm": 2.715981960296631,
"learning_rate": 2e-05,
"loss": 0.7283,
"step": 494
},
{
"epoch": 0.17086641353123921,
"grad_norm": 3.0167715549468994,
"learning_rate": 2e-05,
"loss": 0.8507,
"step": 495
},
{
"epoch": 0.1712115982050397,
"grad_norm": 2.9270315170288086,
"learning_rate": 2e-05,
"loss": 0.8593,
"step": 496
},
{
"epoch": 0.17155678287884019,
"grad_norm": 2.5383360385894775,
"learning_rate": 2e-05,
"loss": 0.7877,
"step": 497
},
{
"epoch": 0.17190196755264067,
"grad_norm": 2.868652582168579,
"learning_rate": 2e-05,
"loss": 0.8635,
"step": 498
},
{
"epoch": 0.17224715222644116,
"grad_norm": 2.8719124794006348,
"learning_rate": 2e-05,
"loss": 0.795,
"step": 499
},
{
"epoch": 0.17259233690024162,
"grad_norm": 2.806877613067627,
"learning_rate": 2e-05,
"loss": 0.7998,
"step": 500
},
{
"epoch": 0.1729375215740421,
"grad_norm": 2.63967227935791,
"learning_rate": 2e-05,
"loss": 0.8817,
"step": 501
},
{
"epoch": 0.1732827062478426,
"grad_norm": 2.68904185295105,
"learning_rate": 2e-05,
"loss": 0.7909,
"step": 502
},
{
"epoch": 0.17362789092164307,
"grad_norm": 2.5513813495635986,
"learning_rate": 2e-05,
"loss": 0.8033,
"step": 503
},
{
"epoch": 0.17397307559544356,
"grad_norm": 2.581880569458008,
"learning_rate": 2e-05,
"loss": 0.8586,
"step": 504
},
{
"epoch": 0.17431826026924405,
"grad_norm": 2.901590585708618,
"learning_rate": 2e-05,
"loss": 0.8116,
"step": 505
},
{
"epoch": 0.17466344494304453,
"grad_norm": 2.7014777660369873,
"learning_rate": 2e-05,
"loss": 0.8502,
"step": 506
},
{
"epoch": 0.17500862961684502,
"grad_norm": 2.875823497772217,
"learning_rate": 2e-05,
"loss": 0.7739,
"step": 507
},
{
"epoch": 0.1753538142906455,
"grad_norm": 2.4771320819854736,
"learning_rate": 2e-05,
"loss": 0.8,
"step": 508
},
{
"epoch": 0.175698998964446,
"grad_norm": 2.648470163345337,
"learning_rate": 2e-05,
"loss": 0.8632,
"step": 509
},
{
"epoch": 0.17604418363824645,
"grad_norm": 2.8525655269622803,
"learning_rate": 2e-05,
"loss": 0.8639,
"step": 510
},
{
"epoch": 0.17638936831204693,
"grad_norm": 2.7430825233459473,
"learning_rate": 2e-05,
"loss": 0.9099,
"step": 511
},
{
"epoch": 0.17673455298584742,
"grad_norm": 2.9599390029907227,
"learning_rate": 2e-05,
"loss": 0.9326,
"step": 512
},
{
"epoch": 0.1770797376596479,
"grad_norm": 2.705155611038208,
"learning_rate": 2e-05,
"loss": 0.8808,
"step": 513
},
{
"epoch": 0.1774249223334484,
"grad_norm": 2.507206678390503,
"learning_rate": 2e-05,
"loss": 0.8614,
"step": 514
},
{
"epoch": 0.17777010700724888,
"grad_norm": 2.3883049488067627,
"learning_rate": 2e-05,
"loss": 0.8161,
"step": 515
},
{
"epoch": 0.17811529168104936,
"grad_norm": 2.7002079486846924,
"learning_rate": 2e-05,
"loss": 0.9636,
"step": 516
},
{
"epoch": 0.17846047635484985,
"grad_norm": 2.4914982318878174,
"learning_rate": 2e-05,
"loss": 0.8232,
"step": 517
},
{
"epoch": 0.17880566102865034,
"grad_norm": 2.644822835922241,
"learning_rate": 2e-05,
"loss": 0.8306,
"step": 518
},
{
"epoch": 0.17915084570245082,
"grad_norm": 2.900297164916992,
"learning_rate": 2e-05,
"loss": 0.9079,
"step": 519
},
{
"epoch": 0.17949603037625128,
"grad_norm": 2.8263745307922363,
"learning_rate": 2e-05,
"loss": 0.8189,
"step": 520
},
{
"epoch": 0.17984121505005177,
"grad_norm": 2.6911349296569824,
"learning_rate": 2e-05,
"loss": 0.8398,
"step": 521
},
{
"epoch": 0.18018639972385225,
"grad_norm": 2.7833213806152344,
"learning_rate": 2e-05,
"loss": 0.7453,
"step": 522
},
{
"epoch": 0.18053158439765274,
"grad_norm": 2.680326223373413,
"learning_rate": 2e-05,
"loss": 0.8591,
"step": 523
},
{
"epoch": 0.18087676907145323,
"grad_norm": 2.902534246444702,
"learning_rate": 2e-05,
"loss": 0.9315,
"step": 524
},
{
"epoch": 0.1812219537452537,
"grad_norm": 2.9760384559631348,
"learning_rate": 2e-05,
"loss": 0.8882,
"step": 525
},
{
"epoch": 0.1815671384190542,
"grad_norm": 2.626789093017578,
"learning_rate": 2e-05,
"loss": 0.7857,
"step": 526
},
{
"epoch": 0.18191232309285468,
"grad_norm": 2.6375679969787598,
"learning_rate": 2e-05,
"loss": 0.8132,
"step": 527
},
{
"epoch": 0.18225750776665517,
"grad_norm": 2.9310142993927,
"learning_rate": 2e-05,
"loss": 0.907,
"step": 528
},
{
"epoch": 0.18260269244045566,
"grad_norm": 2.7192530632019043,
"learning_rate": 2e-05,
"loss": 0.8633,
"step": 529
},
{
"epoch": 0.1829478771142561,
"grad_norm": 2.753049612045288,
"learning_rate": 2e-05,
"loss": 0.8589,
"step": 530
},
{
"epoch": 0.1832930617880566,
"grad_norm": 3.2843739986419678,
"learning_rate": 2e-05,
"loss": 0.8325,
"step": 531
},
{
"epoch": 0.18363824646185709,
"grad_norm": 2.6691083908081055,
"learning_rate": 2e-05,
"loss": 0.8381,
"step": 532
},
{
"epoch": 0.18398343113565757,
"grad_norm": 3.0254318714141846,
"learning_rate": 2e-05,
"loss": 0.8816,
"step": 533
},
{
"epoch": 0.18432861580945806,
"grad_norm": 3.193315029144287,
"learning_rate": 2e-05,
"loss": 0.8958,
"step": 534
},
{
"epoch": 0.18467380048325854,
"grad_norm": 2.721979856491089,
"learning_rate": 2e-05,
"loss": 0.7731,
"step": 535
},
{
"epoch": 0.18501898515705903,
"grad_norm": 2.6035878658294678,
"learning_rate": 2e-05,
"loss": 0.797,
"step": 536
},
{
"epoch": 0.18536416983085952,
"grad_norm": 2.6113343238830566,
"learning_rate": 2e-05,
"loss": 0.7576,
"step": 537
},
{
"epoch": 0.18570935450466,
"grad_norm": 2.4984490871429443,
"learning_rate": 2e-05,
"loss": 0.7743,
"step": 538
},
{
"epoch": 0.1860545391784605,
"grad_norm": 2.4978625774383545,
"learning_rate": 2e-05,
"loss": 0.7983,
"step": 539
},
{
"epoch": 0.18639972385226097,
"grad_norm": 2.6827447414398193,
"learning_rate": 2e-05,
"loss": 0.8141,
"step": 540
},
{
"epoch": 0.18674490852606143,
"grad_norm": 2.6190788745880127,
"learning_rate": 2e-05,
"loss": 0.8467,
"step": 541
},
{
"epoch": 0.18709009319986192,
"grad_norm": 2.6752450466156006,
"learning_rate": 2e-05,
"loss": 0.8986,
"step": 542
},
{
"epoch": 0.1874352778736624,
"grad_norm": 2.7006146907806396,
"learning_rate": 2e-05,
"loss": 0.9105,
"step": 543
},
{
"epoch": 0.1877804625474629,
"grad_norm": 2.7405309677124023,
"learning_rate": 2e-05,
"loss": 0.8625,
"step": 544
},
{
"epoch": 0.18812564722126338,
"grad_norm": 3.042073965072632,
"learning_rate": 2e-05,
"loss": 0.8316,
"step": 545
},
{
"epoch": 0.18847083189506386,
"grad_norm": 2.744330406188965,
"learning_rate": 2e-05,
"loss": 0.8137,
"step": 546
},
{
"epoch": 0.18881601656886435,
"grad_norm": 2.7891201972961426,
"learning_rate": 2e-05,
"loss": 0.83,
"step": 547
},
{
"epoch": 0.18916120124266483,
"grad_norm": 3.782231330871582,
"learning_rate": 2e-05,
"loss": 0.8158,
"step": 548
},
{
"epoch": 0.18950638591646532,
"grad_norm": 3.0141708850860596,
"learning_rate": 2e-05,
"loss": 0.9087,
"step": 549
},
{
"epoch": 0.1898515705902658,
"grad_norm": 2.74953031539917,
"learning_rate": 2e-05,
"loss": 0.8793,
"step": 550
},
{
"epoch": 0.19019675526406626,
"grad_norm": 2.6540184020996094,
"learning_rate": 2e-05,
"loss": 0.9037,
"step": 551
},
{
"epoch": 0.19054193993786675,
"grad_norm": 3.051140308380127,
"learning_rate": 2e-05,
"loss": 0.7495,
"step": 552
},
{
"epoch": 0.19088712461166724,
"grad_norm": 2.5354433059692383,
"learning_rate": 2e-05,
"loss": 0.8458,
"step": 553
},
{
"epoch": 0.19123230928546772,
"grad_norm": 2.5842111110687256,
"learning_rate": 2e-05,
"loss": 0.8055,
"step": 554
},
{
"epoch": 0.1915774939592682,
"grad_norm": 2.568885326385498,
"learning_rate": 2e-05,
"loss": 0.8083,
"step": 555
},
{
"epoch": 0.1919226786330687,
"grad_norm": 3.036980152130127,
"learning_rate": 2e-05,
"loss": 0.8081,
"step": 556
},
{
"epoch": 0.19226786330686918,
"grad_norm": 2.852733850479126,
"learning_rate": 2e-05,
"loss": 0.8148,
"step": 557
},
{
"epoch": 0.19261304798066967,
"grad_norm": 2.7637667655944824,
"learning_rate": 2e-05,
"loss": 0.7862,
"step": 558
},
{
"epoch": 0.19295823265447015,
"grad_norm": 2.8737142086029053,
"learning_rate": 2e-05,
"loss": 0.8552,
"step": 559
},
{
"epoch": 0.19330341732827064,
"grad_norm": 2.655191659927368,
"learning_rate": 2e-05,
"loss": 0.8625,
"step": 560
},
{
"epoch": 0.1936486020020711,
"grad_norm": 2.6270878314971924,
"learning_rate": 2e-05,
"loss": 0.8398,
"step": 561
},
{
"epoch": 0.19399378667587158,
"grad_norm": 2.647904872894287,
"learning_rate": 2e-05,
"loss": 0.7879,
"step": 562
},
{
"epoch": 0.19433897134967207,
"grad_norm": 2.548400640487671,
"learning_rate": 2e-05,
"loss": 0.8751,
"step": 563
},
{
"epoch": 0.19468415602347255,
"grad_norm": 2.8312828540802,
"learning_rate": 2e-05,
"loss": 0.7278,
"step": 564
},
{
"epoch": 0.19502934069727304,
"grad_norm": 2.663391351699829,
"learning_rate": 2e-05,
"loss": 0.8448,
"step": 565
},
{
"epoch": 0.19537452537107353,
"grad_norm": 2.9681437015533447,
"learning_rate": 2e-05,
"loss": 0.8456,
"step": 566
},
{
"epoch": 0.195719710044874,
"grad_norm": 2.6108689308166504,
"learning_rate": 2e-05,
"loss": 0.7968,
"step": 567
},
{
"epoch": 0.1960648947186745,
"grad_norm": 2.440091609954834,
"learning_rate": 2e-05,
"loss": 0.8446,
"step": 568
},
{
"epoch": 0.19641007939247498,
"grad_norm": 2.702831268310547,
"learning_rate": 2e-05,
"loss": 0.7967,
"step": 569
},
{
"epoch": 0.19675526406627547,
"grad_norm": 2.943120002746582,
"learning_rate": 2e-05,
"loss": 0.8356,
"step": 570
},
{
"epoch": 0.19710044874007593,
"grad_norm": 3.0097904205322266,
"learning_rate": 2e-05,
"loss": 0.7726,
"step": 571
},
{
"epoch": 0.19744563341387641,
"grad_norm": 2.3800501823425293,
"learning_rate": 2e-05,
"loss": 0.8435,
"step": 572
},
{
"epoch": 0.1977908180876769,
"grad_norm": 2.6139631271362305,
"learning_rate": 2e-05,
"loss": 0.7929,
"step": 573
},
{
"epoch": 0.1981360027614774,
"grad_norm": 2.5904738903045654,
"learning_rate": 2e-05,
"loss": 0.8143,
"step": 574
},
{
"epoch": 0.19848118743527787,
"grad_norm": 2.6801297664642334,
"learning_rate": 2e-05,
"loss": 0.7782,
"step": 575
},
{
"epoch": 0.19882637210907836,
"grad_norm": 2.631114959716797,
"learning_rate": 2e-05,
"loss": 0.775,
"step": 576
},
{
"epoch": 0.19917155678287884,
"grad_norm": 2.3431198596954346,
"learning_rate": 2e-05,
"loss": 0.7601,
"step": 577
},
{
"epoch": 0.19951674145667933,
"grad_norm": 2.488933563232422,
"learning_rate": 2e-05,
"loss": 0.7926,
"step": 578
},
{
"epoch": 0.19986192613047982,
"grad_norm": 2.3383426666259766,
"learning_rate": 2e-05,
"loss": 0.7666,
"step": 579
},
{
"epoch": 0.2002071108042803,
"grad_norm": 2.5152347087860107,
"learning_rate": 2e-05,
"loss": 0.8124,
"step": 580
},
{
"epoch": 0.20055229547808076,
"grad_norm": 2.5689401626586914,
"learning_rate": 2e-05,
"loss": 0.7708,
"step": 581
},
{
"epoch": 0.20089748015188125,
"grad_norm": 2.508896827697754,
"learning_rate": 2e-05,
"loss": 0.8723,
"step": 582
},
{
"epoch": 0.20124266482568173,
"grad_norm": 2.9416592121124268,
"learning_rate": 2e-05,
"loss": 0.7583,
"step": 583
},
{
"epoch": 0.20158784949948222,
"grad_norm": 2.3808095455169678,
"learning_rate": 2e-05,
"loss": 0.7332,
"step": 584
},
{
"epoch": 0.2019330341732827,
"grad_norm": 2.675591230392456,
"learning_rate": 2e-05,
"loss": 0.8669,
"step": 585
},
{
"epoch": 0.2022782188470832,
"grad_norm": 3.0490567684173584,
"learning_rate": 2e-05,
"loss": 0.8451,
"step": 586
},
{
"epoch": 0.20262340352088368,
"grad_norm": 2.47438907623291,
"learning_rate": 2e-05,
"loss": 0.8056,
"step": 587
},
{
"epoch": 0.20296858819468416,
"grad_norm": 2.73553729057312,
"learning_rate": 2e-05,
"loss": 0.8702,
"step": 588
},
{
"epoch": 0.20331377286848465,
"grad_norm": 2.674639940261841,
"learning_rate": 2e-05,
"loss": 0.8189,
"step": 589
},
{
"epoch": 0.20365895754228514,
"grad_norm": 2.494344711303711,
"learning_rate": 2e-05,
"loss": 0.8256,
"step": 590
},
{
"epoch": 0.2040041422160856,
"grad_norm": 2.297337055206299,
"learning_rate": 2e-05,
"loss": 0.779,
"step": 591
},
{
"epoch": 0.20434932688988608,
"grad_norm": 2.652824878692627,
"learning_rate": 2e-05,
"loss": 0.8074,
"step": 592
},
{
"epoch": 0.20469451156368657,
"grad_norm": 2.507140636444092,
"learning_rate": 2e-05,
"loss": 0.8578,
"step": 593
},
{
"epoch": 0.20503969623748705,
"grad_norm": 3.012864351272583,
"learning_rate": 2e-05,
"loss": 0.7699,
"step": 594
},
{
"epoch": 0.20538488091128754,
"grad_norm": 2.511747121810913,
"learning_rate": 2e-05,
"loss": 0.8248,
"step": 595
},
{
"epoch": 0.20573006558508802,
"grad_norm": 2.4231340885162354,
"learning_rate": 2e-05,
"loss": 0.8095,
"step": 596
},
{
"epoch": 0.2060752502588885,
"grad_norm": 2.3656606674194336,
"learning_rate": 2e-05,
"loss": 0.7241,
"step": 597
},
{
"epoch": 0.206420434932689,
"grad_norm": 2.389401912689209,
"learning_rate": 2e-05,
"loss": 0.8047,
"step": 598
},
{
"epoch": 0.20676561960648948,
"grad_norm": 2.439185857772827,
"learning_rate": 2e-05,
"loss": 0.8732,
"step": 599
},
{
"epoch": 0.20711080428028997,
"grad_norm": 2.5809507369995117,
"learning_rate": 2e-05,
"loss": 0.8037,
"step": 600
},
{
"epoch": 0.20745598895409043,
"grad_norm": 2.3989405632019043,
"learning_rate": 2e-05,
"loss": 0.839,
"step": 601
},
{
"epoch": 0.2078011736278909,
"grad_norm": 2.638395071029663,
"learning_rate": 2e-05,
"loss": 0.8044,
"step": 602
},
{
"epoch": 0.2081463583016914,
"grad_norm": 2.566681385040283,
"learning_rate": 2e-05,
"loss": 0.8102,
"step": 603
},
{
"epoch": 0.20849154297549188,
"grad_norm": 2.6014740467071533,
"learning_rate": 2e-05,
"loss": 0.8381,
"step": 604
},
{
"epoch": 0.20883672764929237,
"grad_norm": 2.6535403728485107,
"learning_rate": 2e-05,
"loss": 0.7749,
"step": 605
},
{
"epoch": 0.20918191232309286,
"grad_norm": 2.539785385131836,
"learning_rate": 2e-05,
"loss": 0.8037,
"step": 606
},
{
"epoch": 0.20952709699689334,
"grad_norm": 2.783963203430176,
"learning_rate": 2e-05,
"loss": 0.7472,
"step": 607
},
{
"epoch": 0.20987228167069383,
"grad_norm": 2.6907851696014404,
"learning_rate": 2e-05,
"loss": 0.8709,
"step": 608
},
{
"epoch": 0.2102174663444943,
"grad_norm": 2.713240146636963,
"learning_rate": 2e-05,
"loss": 0.8506,
"step": 609
},
{
"epoch": 0.2105626510182948,
"grad_norm": 2.8039517402648926,
"learning_rate": 2e-05,
"loss": 0.8109,
"step": 610
},
{
"epoch": 0.21090783569209526,
"grad_norm": 2.2727177143096924,
"learning_rate": 2e-05,
"loss": 0.7678,
"step": 611
},
{
"epoch": 0.21125302036589574,
"grad_norm": 2.36690092086792,
"learning_rate": 2e-05,
"loss": 0.8283,
"step": 612
},
{
"epoch": 0.21159820503969623,
"grad_norm": 2.436732530593872,
"learning_rate": 2e-05,
"loss": 0.7969,
"step": 613
},
{
"epoch": 0.21194338971349672,
"grad_norm": 2.499091148376465,
"learning_rate": 2e-05,
"loss": 0.8403,
"step": 614
},
{
"epoch": 0.2122885743872972,
"grad_norm": 3.2683467864990234,
"learning_rate": 2e-05,
"loss": 0.7849,
"step": 615
},
{
"epoch": 0.2126337590610977,
"grad_norm": 2.452500343322754,
"learning_rate": 2e-05,
"loss": 0.7606,
"step": 616
},
{
"epoch": 0.21297894373489817,
"grad_norm": 2.5727200508117676,
"learning_rate": 2e-05,
"loss": 0.8454,
"step": 617
},
{
"epoch": 0.21332412840869866,
"grad_norm": 2.3810341358184814,
"learning_rate": 2e-05,
"loss": 0.7995,
"step": 618
},
{
"epoch": 0.21366931308249915,
"grad_norm": 2.748025417327881,
"learning_rate": 2e-05,
"loss": 0.8918,
"step": 619
},
{
"epoch": 0.21401449775629963,
"grad_norm": 2.6371870040893555,
"learning_rate": 2e-05,
"loss": 0.8178,
"step": 620
},
{
"epoch": 0.2143596824301001,
"grad_norm": 2.570796489715576,
"learning_rate": 2e-05,
"loss": 0.7938,
"step": 621
},
{
"epoch": 0.21470486710390058,
"grad_norm": 2.523061513900757,
"learning_rate": 2e-05,
"loss": 0.8267,
"step": 622
},
{
"epoch": 0.21505005177770106,
"grad_norm": 2.45378041267395,
"learning_rate": 2e-05,
"loss": 0.8556,
"step": 623
},
{
"epoch": 0.21539523645150155,
"grad_norm": 2.567342758178711,
"learning_rate": 2e-05,
"loss": 0.7609,
"step": 624
},
{
"epoch": 0.21574042112530203,
"grad_norm": 2.612757444381714,
"learning_rate": 2e-05,
"loss": 0.8949,
"step": 625
},
{
"epoch": 0.21608560579910252,
"grad_norm": 2.7509217262268066,
"learning_rate": 2e-05,
"loss": 0.8208,
"step": 626
},
{
"epoch": 0.216430790472903,
"grad_norm": 2.6197450160980225,
"learning_rate": 2e-05,
"loss": 0.8406,
"step": 627
},
{
"epoch": 0.2167759751467035,
"grad_norm": 2.7045562267303467,
"learning_rate": 2e-05,
"loss": 0.8764,
"step": 628
},
{
"epoch": 0.21712115982050398,
"grad_norm": 2.5740184783935547,
"learning_rate": 2e-05,
"loss": 0.8362,
"step": 629
},
{
"epoch": 0.21746634449430446,
"grad_norm": 3.1988041400909424,
"learning_rate": 2e-05,
"loss": 0.7933,
"step": 630
},
{
"epoch": 0.21781152916810492,
"grad_norm": 2.2488019466400146,
"learning_rate": 2e-05,
"loss": 0.7828,
"step": 631
},
{
"epoch": 0.2181567138419054,
"grad_norm": 2.442720651626587,
"learning_rate": 2e-05,
"loss": 0.7974,
"step": 632
},
{
"epoch": 0.2185018985157059,
"grad_norm": 2.7867915630340576,
"learning_rate": 2e-05,
"loss": 0.8298,
"step": 633
},
{
"epoch": 0.21884708318950638,
"grad_norm": 2.512460470199585,
"learning_rate": 2e-05,
"loss": 0.7807,
"step": 634
},
{
"epoch": 0.21919226786330687,
"grad_norm": 2.34566330909729,
"learning_rate": 2e-05,
"loss": 0.8103,
"step": 635
},
{
"epoch": 0.21953745253710735,
"grad_norm": 2.3921985626220703,
"learning_rate": 2e-05,
"loss": 0.8099,
"step": 636
},
{
"epoch": 0.21988263721090784,
"grad_norm": 2.790856122970581,
"learning_rate": 2e-05,
"loss": 0.8027,
"step": 637
},
{
"epoch": 0.22022782188470832,
"grad_norm": 2.4337832927703857,
"learning_rate": 2e-05,
"loss": 0.8459,
"step": 638
},
{
"epoch": 0.2205730065585088,
"grad_norm": 2.626878261566162,
"learning_rate": 2e-05,
"loss": 0.822,
"step": 639
},
{
"epoch": 0.2209181912323093,
"grad_norm": 2.411151647567749,
"learning_rate": 2e-05,
"loss": 0.7889,
"step": 640
},
{
"epoch": 0.22126337590610975,
"grad_norm": 2.780468463897705,
"learning_rate": 2e-05,
"loss": 0.8204,
"step": 641
},
{
"epoch": 0.22160856057991024,
"grad_norm": 2.384120464324951,
"learning_rate": 2e-05,
"loss": 0.794,
"step": 642
},
{
"epoch": 0.22195374525371073,
"grad_norm": 2.7003538608551025,
"learning_rate": 2e-05,
"loss": 0.8721,
"step": 643
},
{
"epoch": 0.2222989299275112,
"grad_norm": 2.5736396312713623,
"learning_rate": 2e-05,
"loss": 0.7718,
"step": 644
},
{
"epoch": 0.2226441146013117,
"grad_norm": 2.5534183979034424,
"learning_rate": 2e-05,
"loss": 0.8039,
"step": 645
},
{
"epoch": 0.22298929927511218,
"grad_norm": 2.4901063442230225,
"learning_rate": 2e-05,
"loss": 0.8664,
"step": 646
},
{
"epoch": 0.22333448394891267,
"grad_norm": 2.5854790210723877,
"learning_rate": 2e-05,
"loss": 0.849,
"step": 647
},
{
"epoch": 0.22367966862271316,
"grad_norm": 2.4237279891967773,
"learning_rate": 2e-05,
"loss": 0.7571,
"step": 648
},
{
"epoch": 0.22402485329651364,
"grad_norm": 2.410684108734131,
"learning_rate": 2e-05,
"loss": 0.7899,
"step": 649
},
{
"epoch": 0.22437003797031413,
"grad_norm": 2.4895997047424316,
"learning_rate": 2e-05,
"loss": 0.7699,
"step": 650
},
{
"epoch": 0.22471522264411462,
"grad_norm": 2.3816611766815186,
"learning_rate": 2e-05,
"loss": 0.7872,
"step": 651
},
{
"epoch": 0.22506040731791507,
"grad_norm": 2.417294979095459,
"learning_rate": 2e-05,
"loss": 0.7714,
"step": 652
},
{
"epoch": 0.22540559199171556,
"grad_norm": 2.592925548553467,
"learning_rate": 2e-05,
"loss": 0.817,
"step": 653
},
{
"epoch": 0.22575077666551605,
"grad_norm": 2.4112489223480225,
"learning_rate": 2e-05,
"loss": 0.8018,
"step": 654
},
{
"epoch": 0.22609596133931653,
"grad_norm": 2.340555191040039,
"learning_rate": 2e-05,
"loss": 0.781,
"step": 655
},
{
"epoch": 0.22644114601311702,
"grad_norm": 2.5071909427642822,
"learning_rate": 2e-05,
"loss": 0.8527,
"step": 656
},
{
"epoch": 0.2267863306869175,
"grad_norm": 2.465301275253296,
"learning_rate": 2e-05,
"loss": 0.827,
"step": 657
},
{
"epoch": 0.227131515360718,
"grad_norm": 2.3387086391448975,
"learning_rate": 2e-05,
"loss": 0.7627,
"step": 658
},
{
"epoch": 0.22747670003451848,
"grad_norm": 2.5895376205444336,
"learning_rate": 2e-05,
"loss": 0.7968,
"step": 659
},
{
"epoch": 0.22782188470831896,
"grad_norm": 2.829334020614624,
"learning_rate": 2e-05,
"loss": 0.8498,
"step": 660
},
{
"epoch": 0.22816706938211945,
"grad_norm": 2.4148943424224854,
"learning_rate": 2e-05,
"loss": 0.7726,
"step": 661
},
{
"epoch": 0.2285122540559199,
"grad_norm": 2.487060546875,
"learning_rate": 2e-05,
"loss": 0.7653,
"step": 662
},
{
"epoch": 0.2288574387297204,
"grad_norm": 2.4439961910247803,
"learning_rate": 2e-05,
"loss": 0.84,
"step": 663
},
{
"epoch": 0.22920262340352088,
"grad_norm": 2.485614061355591,
"learning_rate": 2e-05,
"loss": 0.8145,
"step": 664
},
{
"epoch": 0.22954780807732136,
"grad_norm": 2.3690195083618164,
"learning_rate": 2e-05,
"loss": 0.7946,
"step": 665
},
{
"epoch": 0.22989299275112185,
"grad_norm": 2.5638961791992188,
"learning_rate": 2e-05,
"loss": 0.7886,
"step": 666
},
{
"epoch": 0.23023817742492234,
"grad_norm": 2.3436648845672607,
"learning_rate": 2e-05,
"loss": 0.8196,
"step": 667
},
{
"epoch": 0.23058336209872282,
"grad_norm": 2.5709872245788574,
"learning_rate": 2e-05,
"loss": 0.8286,
"step": 668
},
{
"epoch": 0.2309285467725233,
"grad_norm": 2.56705379486084,
"learning_rate": 2e-05,
"loss": 0.8495,
"step": 669
},
{
"epoch": 0.2312737314463238,
"grad_norm": 2.5212414264678955,
"learning_rate": 2e-05,
"loss": 0.7668,
"step": 670
},
{
"epoch": 0.23161891612012428,
"grad_norm": 2.5123586654663086,
"learning_rate": 2e-05,
"loss": 0.7845,
"step": 671
},
{
"epoch": 0.23196410079392474,
"grad_norm": 2.5270276069641113,
"learning_rate": 2e-05,
"loss": 0.8227,
"step": 672
},
{
"epoch": 0.23230928546772522,
"grad_norm": 2.382445812225342,
"learning_rate": 2e-05,
"loss": 0.7476,
"step": 673
},
{
"epoch": 0.2326544701415257,
"grad_norm": 4.354213237762451,
"learning_rate": 2e-05,
"loss": 0.8111,
"step": 674
},
{
"epoch": 0.2329996548153262,
"grad_norm": 2.542351722717285,
"learning_rate": 2e-05,
"loss": 0.8647,
"step": 675
},
{
"epoch": 0.23334483948912668,
"grad_norm": 2.492007255554199,
"learning_rate": 2e-05,
"loss": 0.7812,
"step": 676
},
{
"epoch": 0.23369002416292717,
"grad_norm": 2.8558623790740967,
"learning_rate": 2e-05,
"loss": 0.7819,
"step": 677
},
{
"epoch": 0.23403520883672765,
"grad_norm": 2.424027681350708,
"learning_rate": 2e-05,
"loss": 0.7798,
"step": 678
},
{
"epoch": 0.23438039351052814,
"grad_norm": 2.9818484783172607,
"learning_rate": 2e-05,
"loss": 0.8442,
"step": 679
},
{
"epoch": 0.23472557818432863,
"grad_norm": 2.5655038356781006,
"learning_rate": 2e-05,
"loss": 0.8554,
"step": 680
},
{
"epoch": 0.2350707628581291,
"grad_norm": 2.6559510231018066,
"learning_rate": 2e-05,
"loss": 0.828,
"step": 681
},
{
"epoch": 0.23541594753192957,
"grad_norm": 2.5213375091552734,
"learning_rate": 2e-05,
"loss": 0.8371,
"step": 682
},
{
"epoch": 0.23576113220573006,
"grad_norm": 2.5891947746276855,
"learning_rate": 2e-05,
"loss": 0.8425,
"step": 683
},
{
"epoch": 0.23610631687953054,
"grad_norm": 2.673092842102051,
"learning_rate": 2e-05,
"loss": 0.8405,
"step": 684
},
{
"epoch": 0.23645150155333103,
"grad_norm": 2.362226724624634,
"learning_rate": 2e-05,
"loss": 0.7775,
"step": 685
},
{
"epoch": 0.23679668622713151,
"grad_norm": 2.7180612087249756,
"learning_rate": 2e-05,
"loss": 0.8528,
"step": 686
},
{
"epoch": 0.237141870900932,
"grad_norm": 2.40690541267395,
"learning_rate": 2e-05,
"loss": 0.8133,
"step": 687
},
{
"epoch": 0.2374870555747325,
"grad_norm": 2.5823540687561035,
"learning_rate": 2e-05,
"loss": 0.8635,
"step": 688
},
{
"epoch": 0.23783224024853297,
"grad_norm": 2.387899398803711,
"learning_rate": 2e-05,
"loss": 0.8258,
"step": 689
},
{
"epoch": 0.23817742492233346,
"grad_norm": 3.080235004425049,
"learning_rate": 2e-05,
"loss": 0.8311,
"step": 690
},
{
"epoch": 0.23852260959613394,
"grad_norm": 2.466670274734497,
"learning_rate": 2e-05,
"loss": 0.7914,
"step": 691
},
{
"epoch": 0.2388677942699344,
"grad_norm": 2.4669206142425537,
"learning_rate": 2e-05,
"loss": 0.8205,
"step": 692
},
{
"epoch": 0.2392129789437349,
"grad_norm": 2.385197877883911,
"learning_rate": 2e-05,
"loss": 0.8081,
"step": 693
},
{
"epoch": 0.23955816361753537,
"grad_norm": 2.5215725898742676,
"learning_rate": 2e-05,
"loss": 0.8061,
"step": 694
},
{
"epoch": 0.23990334829133586,
"grad_norm": 2.4044137001037598,
"learning_rate": 2e-05,
"loss": 0.7884,
"step": 695
},
{
"epoch": 0.24024853296513635,
"grad_norm": 2.598735809326172,
"learning_rate": 2e-05,
"loss": 0.8283,
"step": 696
},
{
"epoch": 0.24059371763893683,
"grad_norm": 2.434346914291382,
"learning_rate": 2e-05,
"loss": 0.8366,
"step": 697
},
{
"epoch": 0.24093890231273732,
"grad_norm": 2.321727991104126,
"learning_rate": 2e-05,
"loss": 0.8012,
"step": 698
},
{
"epoch": 0.2412840869865378,
"grad_norm": 2.6814427375793457,
"learning_rate": 2e-05,
"loss": 0.7923,
"step": 699
},
{
"epoch": 0.2416292716603383,
"grad_norm": 2.978170871734619,
"learning_rate": 2e-05,
"loss": 0.8642,
"step": 700
},
{
"epoch": 0.24197445633413878,
"grad_norm": 2.447589635848999,
"learning_rate": 2e-05,
"loss": 0.8947,
"step": 701
},
{
"epoch": 0.24231964100793923,
"grad_norm": 2.542748212814331,
"learning_rate": 2e-05,
"loss": 0.8199,
"step": 702
},
{
"epoch": 0.24266482568173972,
"grad_norm": 2.26539945602417,
"learning_rate": 2e-05,
"loss": 0.8165,
"step": 703
},
{
"epoch": 0.2430100103555402,
"grad_norm": 2.310394287109375,
"learning_rate": 2e-05,
"loss": 0.8057,
"step": 704
},
{
"epoch": 0.2433551950293407,
"grad_norm": 2.352877140045166,
"learning_rate": 2e-05,
"loss": 0.7986,
"step": 705
},
{
"epoch": 0.24370037970314118,
"grad_norm": 2.257847309112549,
"learning_rate": 2e-05,
"loss": 0.7638,
"step": 706
},
{
"epoch": 0.24404556437694166,
"grad_norm": 2.4806249141693115,
"learning_rate": 2e-05,
"loss": 0.8122,
"step": 707
},
{
"epoch": 0.24439074905074215,
"grad_norm": 2.5089046955108643,
"learning_rate": 2e-05,
"loss": 0.7944,
"step": 708
},
{
"epoch": 0.24473593372454264,
"grad_norm": 2.7169389724731445,
"learning_rate": 2e-05,
"loss": 0.8342,
"step": 709
},
{
"epoch": 0.24508111839834312,
"grad_norm": 2.3075709342956543,
"learning_rate": 2e-05,
"loss": 0.84,
"step": 710
},
{
"epoch": 0.2454263030721436,
"grad_norm": 2.3579206466674805,
"learning_rate": 2e-05,
"loss": 0.7753,
"step": 711
},
{
"epoch": 0.24577148774594407,
"grad_norm": 2.247012138366699,
"learning_rate": 2e-05,
"loss": 0.7577,
"step": 712
},
{
"epoch": 0.24611667241974455,
"grad_norm": 2.456413984298706,
"learning_rate": 2e-05,
"loss": 0.766,
"step": 713
},
{
"epoch": 0.24646185709354504,
"grad_norm": 2.334796190261841,
"learning_rate": 2e-05,
"loss": 0.8091,
"step": 714
},
{
"epoch": 0.24680704176734553,
"grad_norm": 2.7342369556427,
"learning_rate": 2e-05,
"loss": 0.7921,
"step": 715
},
{
"epoch": 0.247152226441146,
"grad_norm": 2.421428680419922,
"learning_rate": 2e-05,
"loss": 0.8399,
"step": 716
},
{
"epoch": 0.2474974111149465,
"grad_norm": 2.294358253479004,
"learning_rate": 2e-05,
"loss": 0.8151,
"step": 717
},
{
"epoch": 0.24784259578874698,
"grad_norm": 2.2485649585723877,
"learning_rate": 2e-05,
"loss": 0.8042,
"step": 718
},
{
"epoch": 0.24818778046254747,
"grad_norm": 2.320042610168457,
"learning_rate": 2e-05,
"loss": 0.819,
"step": 719
},
{
"epoch": 0.24853296513634796,
"grad_norm": 2.550518751144409,
"learning_rate": 2e-05,
"loss": 0.8183,
"step": 720
},
{
"epoch": 0.24887814981014844,
"grad_norm": 2.2849254608154297,
"learning_rate": 2e-05,
"loss": 0.776,
"step": 721
},
{
"epoch": 0.2492233344839489,
"grad_norm": 2.62604022026062,
"learning_rate": 2e-05,
"loss": 0.8025,
"step": 722
},
{
"epoch": 0.24956851915774939,
"grad_norm": 2.673774480819702,
"learning_rate": 2e-05,
"loss": 0.835,
"step": 723
},
{
"epoch": 0.24991370383154987,
"grad_norm": 2.6909732818603516,
"learning_rate": 2e-05,
"loss": 0.8302,
"step": 724
},
{
"epoch": 0.2502588885053504,
"grad_norm": 2.456923484802246,
"learning_rate": 2e-05,
"loss": 0.7896,
"step": 725
},
{
"epoch": 0.25060407317915084,
"grad_norm": 2.4879603385925293,
"learning_rate": 2e-05,
"loss": 0.7855,
"step": 726
},
{
"epoch": 0.2509492578529513,
"grad_norm": 2.568673610687256,
"learning_rate": 2e-05,
"loss": 0.8927,
"step": 727
},
{
"epoch": 0.2512944425267518,
"grad_norm": 2.581019878387451,
"learning_rate": 2e-05,
"loss": 0.8248,
"step": 728
},
{
"epoch": 0.2516396272005523,
"grad_norm": 2.6271448135375977,
"learning_rate": 2e-05,
"loss": 0.773,
"step": 729
},
{
"epoch": 0.2519848118743528,
"grad_norm": 2.3511996269226074,
"learning_rate": 2e-05,
"loss": 0.7718,
"step": 730
},
{
"epoch": 0.25232999654815325,
"grad_norm": 2.275012493133545,
"learning_rate": 2e-05,
"loss": 0.7246,
"step": 731
},
{
"epoch": 0.25267518122195376,
"grad_norm": 2.4964468479156494,
"learning_rate": 2e-05,
"loss": 0.7716,
"step": 732
},
{
"epoch": 0.2530203658957542,
"grad_norm": 3.0296764373779297,
"learning_rate": 2e-05,
"loss": 0.805,
"step": 733
},
{
"epoch": 0.25336555056955473,
"grad_norm": 2.7500593662261963,
"learning_rate": 2e-05,
"loss": 0.8182,
"step": 734
},
{
"epoch": 0.2537107352433552,
"grad_norm": 2.582059144973755,
"learning_rate": 2e-05,
"loss": 0.8504,
"step": 735
},
{
"epoch": 0.2540559199171557,
"grad_norm": 2.1892638206481934,
"learning_rate": 2e-05,
"loss": 0.7769,
"step": 736
},
{
"epoch": 0.25440110459095616,
"grad_norm": 2.6324143409729004,
"learning_rate": 2e-05,
"loss": 0.8411,
"step": 737
},
{
"epoch": 0.2547462892647566,
"grad_norm": 2.5749869346618652,
"learning_rate": 2e-05,
"loss": 0.8162,
"step": 738
},
{
"epoch": 0.25509147393855713,
"grad_norm": 2.639956474304199,
"learning_rate": 2e-05,
"loss": 0.7715,
"step": 739
},
{
"epoch": 0.2554366586123576,
"grad_norm": 2.4721555709838867,
"learning_rate": 2e-05,
"loss": 0.7986,
"step": 740
},
{
"epoch": 0.2557818432861581,
"grad_norm": 2.4588711261749268,
"learning_rate": 2e-05,
"loss": 0.8353,
"step": 741
},
{
"epoch": 0.25612702795995856,
"grad_norm": 2.6208677291870117,
"learning_rate": 2e-05,
"loss": 0.841,
"step": 742
},
{
"epoch": 0.2564722126337591,
"grad_norm": 2.3099710941314697,
"learning_rate": 2e-05,
"loss": 0.8081,
"step": 743
},
{
"epoch": 0.25681739730755954,
"grad_norm": 2.3112940788269043,
"learning_rate": 2e-05,
"loss": 0.7497,
"step": 744
},
{
"epoch": 0.25716258198136005,
"grad_norm": 2.443956136703491,
"learning_rate": 2e-05,
"loss": 0.8086,
"step": 745
},
{
"epoch": 0.2575077666551605,
"grad_norm": 2.4621360301971436,
"learning_rate": 2e-05,
"loss": 0.8026,
"step": 746
},
{
"epoch": 0.25785295132896097,
"grad_norm": 2.369255304336548,
"learning_rate": 2e-05,
"loss": 0.7849,
"step": 747
},
{
"epoch": 0.2581981360027615,
"grad_norm": 2.385077476501465,
"learning_rate": 2e-05,
"loss": 0.835,
"step": 748
},
{
"epoch": 0.25854332067656194,
"grad_norm": 2.5307819843292236,
"learning_rate": 2e-05,
"loss": 0.8743,
"step": 749
},
{
"epoch": 0.25888850535036245,
"grad_norm": 2.4265220165252686,
"learning_rate": 2e-05,
"loss": 0.7868,
"step": 750
},
{
"epoch": 0.2592336900241629,
"grad_norm": 2.4824352264404297,
"learning_rate": 2e-05,
"loss": 0.8095,
"step": 751
},
{
"epoch": 0.2595788746979634,
"grad_norm": 2.437535524368286,
"learning_rate": 2e-05,
"loss": 0.8011,
"step": 752
},
{
"epoch": 0.2599240593717639,
"grad_norm": 2.4075124263763428,
"learning_rate": 2e-05,
"loss": 0.7654,
"step": 753
},
{
"epoch": 0.2602692440455644,
"grad_norm": 2.4554355144500732,
"learning_rate": 2e-05,
"loss": 0.7917,
"step": 754
},
{
"epoch": 0.26061442871936485,
"grad_norm": 2.8890931606292725,
"learning_rate": 2e-05,
"loss": 0.8628,
"step": 755
},
{
"epoch": 0.26095961339316537,
"grad_norm": 2.5634958744049072,
"learning_rate": 2e-05,
"loss": 0.8342,
"step": 756
},
{
"epoch": 0.2613047980669658,
"grad_norm": 2.2676279544830322,
"learning_rate": 2e-05,
"loss": 0.7785,
"step": 757
},
{
"epoch": 0.2616499827407663,
"grad_norm": 2.420266628265381,
"learning_rate": 2e-05,
"loss": 0.7597,
"step": 758
},
{
"epoch": 0.2619951674145668,
"grad_norm": 2.5409836769104004,
"learning_rate": 2e-05,
"loss": 0.7625,
"step": 759
},
{
"epoch": 0.26234035208836726,
"grad_norm": 2.6637697219848633,
"learning_rate": 2e-05,
"loss": 0.8447,
"step": 760
},
{
"epoch": 0.26268553676216777,
"grad_norm": 2.5580368041992188,
"learning_rate": 2e-05,
"loss": 0.8483,
"step": 761
},
{
"epoch": 0.26303072143596823,
"grad_norm": 2.1736929416656494,
"learning_rate": 2e-05,
"loss": 0.7846,
"step": 762
},
{
"epoch": 0.26337590610976874,
"grad_norm": 2.432163715362549,
"learning_rate": 2e-05,
"loss": 0.837,
"step": 763
},
{
"epoch": 0.2637210907835692,
"grad_norm": 2.2890450954437256,
"learning_rate": 2e-05,
"loss": 0.7575,
"step": 764
},
{
"epoch": 0.2640662754573697,
"grad_norm": 2.147167921066284,
"learning_rate": 2e-05,
"loss": 0.748,
"step": 765
},
{
"epoch": 0.2644114601311702,
"grad_norm": 2.2331297397613525,
"learning_rate": 2e-05,
"loss": 0.7877,
"step": 766
},
{
"epoch": 0.2647566448049707,
"grad_norm": 2.6834170818328857,
"learning_rate": 2e-05,
"loss": 0.7593,
"step": 767
},
{
"epoch": 0.26510182947877114,
"grad_norm": 2.3029916286468506,
"learning_rate": 2e-05,
"loss": 0.779,
"step": 768
},
{
"epoch": 0.2654470141525716,
"grad_norm": 2.5964062213897705,
"learning_rate": 2e-05,
"loss": 0.7763,
"step": 769
},
{
"epoch": 0.2657921988263721,
"grad_norm": 2.380195140838623,
"learning_rate": 2e-05,
"loss": 0.8466,
"step": 770
},
{
"epoch": 0.2661373835001726,
"grad_norm": 2.3388257026672363,
"learning_rate": 2e-05,
"loss": 0.8285,
"step": 771
},
{
"epoch": 0.2664825681739731,
"grad_norm": 2.679877519607544,
"learning_rate": 2e-05,
"loss": 0.8432,
"step": 772
},
{
"epoch": 0.26682775284777355,
"grad_norm": 2.3452959060668945,
"learning_rate": 2e-05,
"loss": 0.8195,
"step": 773
},
{
"epoch": 0.26717293752157406,
"grad_norm": 2.2456681728363037,
"learning_rate": 2e-05,
"loss": 0.8075,
"step": 774
},
{
"epoch": 0.2675181221953745,
"grad_norm": 3.0491323471069336,
"learning_rate": 2e-05,
"loss": 0.7777,
"step": 775
},
{
"epoch": 0.26786330686917503,
"grad_norm": 2.182220697402954,
"learning_rate": 2e-05,
"loss": 0.8208,
"step": 776
},
{
"epoch": 0.2682084915429755,
"grad_norm": 2.5717360973358154,
"learning_rate": 2e-05,
"loss": 0.8557,
"step": 777
},
{
"epoch": 0.26855367621677595,
"grad_norm": 2.4059348106384277,
"learning_rate": 2e-05,
"loss": 0.7936,
"step": 778
},
{
"epoch": 0.26889886089057646,
"grad_norm": 2.5083248615264893,
"learning_rate": 2e-05,
"loss": 0.8024,
"step": 779
},
{
"epoch": 0.2692440455643769,
"grad_norm": 2.284400463104248,
"learning_rate": 2e-05,
"loss": 0.7757,
"step": 780
},
{
"epoch": 0.26958923023817744,
"grad_norm": 2.477802038192749,
"learning_rate": 2e-05,
"loss": 0.798,
"step": 781
},
{
"epoch": 0.2699344149119779,
"grad_norm": 2.2841451168060303,
"learning_rate": 2e-05,
"loss": 0.705,
"step": 782
},
{
"epoch": 0.2702795995857784,
"grad_norm": 2.7210919857025146,
"learning_rate": 2e-05,
"loss": 0.8506,
"step": 783
},
{
"epoch": 0.27062478425957887,
"grad_norm": 2.205794095993042,
"learning_rate": 2e-05,
"loss": 0.7054,
"step": 784
},
{
"epoch": 0.2709699689333794,
"grad_norm": 2.332463026046753,
"learning_rate": 2e-05,
"loss": 0.8203,
"step": 785
},
{
"epoch": 0.27131515360717984,
"grad_norm": 2.1899123191833496,
"learning_rate": 2e-05,
"loss": 0.7996,
"step": 786
},
{
"epoch": 0.27166033828098035,
"grad_norm": 3.033325433731079,
"learning_rate": 2e-05,
"loss": 0.8023,
"step": 787
},
{
"epoch": 0.2720055229547808,
"grad_norm": 2.5546796321868896,
"learning_rate": 2e-05,
"loss": 0.7844,
"step": 788
},
{
"epoch": 0.27235070762858127,
"grad_norm": 2.4093902111053467,
"learning_rate": 2e-05,
"loss": 0.7127,
"step": 789
},
{
"epoch": 0.2726958923023818,
"grad_norm": 2.6239256858825684,
"learning_rate": 2e-05,
"loss": 0.8067,
"step": 790
},
{
"epoch": 0.27304107697618224,
"grad_norm": 2.5717294216156006,
"learning_rate": 2e-05,
"loss": 0.7939,
"step": 791
},
{
"epoch": 0.27338626164998275,
"grad_norm": 2.6218199729919434,
"learning_rate": 2e-05,
"loss": 0.7864,
"step": 792
},
{
"epoch": 0.2737314463237832,
"grad_norm": 2.2493772506713867,
"learning_rate": 2e-05,
"loss": 0.7935,
"step": 793
},
{
"epoch": 0.2740766309975837,
"grad_norm": 2.1874711513519287,
"learning_rate": 2e-05,
"loss": 0.7678,
"step": 794
},
{
"epoch": 0.2744218156713842,
"grad_norm": 2.2770395278930664,
"learning_rate": 2e-05,
"loss": 0.7615,
"step": 795
},
{
"epoch": 0.2747670003451847,
"grad_norm": 2.453977584838867,
"learning_rate": 2e-05,
"loss": 0.827,
"step": 796
},
{
"epoch": 0.27511218501898516,
"grad_norm": 2.3395955562591553,
"learning_rate": 2e-05,
"loss": 0.856,
"step": 797
},
{
"epoch": 0.2754573696927856,
"grad_norm": 2.4298174381256104,
"learning_rate": 2e-05,
"loss": 0.8347,
"step": 798
},
{
"epoch": 0.27580255436658613,
"grad_norm": 2.3910465240478516,
"learning_rate": 2e-05,
"loss": 0.7876,
"step": 799
},
{
"epoch": 0.2761477390403866,
"grad_norm": 2.2215797901153564,
"learning_rate": 2e-05,
"loss": 0.7799,
"step": 800
},
{
"epoch": 0.2764929237141871,
"grad_norm": 2.430864095687866,
"learning_rate": 2e-05,
"loss": 0.8191,
"step": 801
},
{
"epoch": 0.27683810838798756,
"grad_norm": 2.1841373443603516,
"learning_rate": 2e-05,
"loss": 0.7809,
"step": 802
},
{
"epoch": 0.27718329306178807,
"grad_norm": 2.417025089263916,
"learning_rate": 2e-05,
"loss": 0.7814,
"step": 803
},
{
"epoch": 0.27752847773558853,
"grad_norm": 2.4221138954162598,
"learning_rate": 2e-05,
"loss": 0.7432,
"step": 804
},
{
"epoch": 0.27787366240938904,
"grad_norm": 2.243767261505127,
"learning_rate": 2e-05,
"loss": 0.7545,
"step": 805
},
{
"epoch": 0.2782188470831895,
"grad_norm": 2.408363103866577,
"learning_rate": 2e-05,
"loss": 0.7653,
"step": 806
},
{
"epoch": 0.27856403175699,
"grad_norm": 2.5052545070648193,
"learning_rate": 2e-05,
"loss": 0.7543,
"step": 807
},
{
"epoch": 0.2789092164307905,
"grad_norm": 2.40278697013855,
"learning_rate": 2e-05,
"loss": 0.8283,
"step": 808
},
{
"epoch": 0.27925440110459093,
"grad_norm": 2.448979377746582,
"learning_rate": 2e-05,
"loss": 0.8131,
"step": 809
},
{
"epoch": 0.27959958577839145,
"grad_norm": 2.434659004211426,
"learning_rate": 2e-05,
"loss": 0.8619,
"step": 810
},
{
"epoch": 0.2799447704521919,
"grad_norm": 2.2524662017822266,
"learning_rate": 2e-05,
"loss": 0.8179,
"step": 811
},
{
"epoch": 0.2802899551259924,
"grad_norm": 2.5318238735198975,
"learning_rate": 2e-05,
"loss": 0.8369,
"step": 812
},
{
"epoch": 0.2806351397997929,
"grad_norm": 2.411334991455078,
"learning_rate": 2e-05,
"loss": 0.7542,
"step": 813
},
{
"epoch": 0.2809803244735934,
"grad_norm": 2.1707065105438232,
"learning_rate": 2e-05,
"loss": 0.7828,
"step": 814
},
{
"epoch": 0.28132550914739385,
"grad_norm": 2.2191224098205566,
"learning_rate": 2e-05,
"loss": 0.8132,
"step": 815
},
{
"epoch": 0.28167069382119436,
"grad_norm": 2.3489272594451904,
"learning_rate": 2e-05,
"loss": 0.756,
"step": 816
},
{
"epoch": 0.2820158784949948,
"grad_norm": 2.3153269290924072,
"learning_rate": 2e-05,
"loss": 0.78,
"step": 817
},
{
"epoch": 0.2823610631687953,
"grad_norm": 2.785445213317871,
"learning_rate": 2e-05,
"loss": 0.9018,
"step": 818
},
{
"epoch": 0.2827062478425958,
"grad_norm": 2.4912357330322266,
"learning_rate": 2e-05,
"loss": 0.7729,
"step": 819
},
{
"epoch": 0.28305143251639625,
"grad_norm": 2.4810216426849365,
"learning_rate": 2e-05,
"loss": 0.8686,
"step": 820
},
{
"epoch": 0.28339661719019676,
"grad_norm": 2.5625271797180176,
"learning_rate": 2e-05,
"loss": 0.8389,
"step": 821
},
{
"epoch": 0.2837418018639972,
"grad_norm": 2.2283105850219727,
"learning_rate": 2e-05,
"loss": 0.7579,
"step": 822
},
{
"epoch": 0.28408698653779774,
"grad_norm": 2.3928627967834473,
"learning_rate": 2e-05,
"loss": 0.7676,
"step": 823
},
{
"epoch": 0.2844321712115982,
"grad_norm": 2.4077234268188477,
"learning_rate": 2e-05,
"loss": 0.8363,
"step": 824
},
{
"epoch": 0.2847773558853987,
"grad_norm": 2.534303665161133,
"learning_rate": 2e-05,
"loss": 0.7064,
"step": 825
},
{
"epoch": 0.28512254055919917,
"grad_norm": 2.242882251739502,
"learning_rate": 2e-05,
"loss": 0.751,
"step": 826
},
{
"epoch": 0.2854677252329997,
"grad_norm": 2.318525791168213,
"learning_rate": 2e-05,
"loss": 0.7636,
"step": 827
},
{
"epoch": 0.28581290990680014,
"grad_norm": 2.241232395172119,
"learning_rate": 2e-05,
"loss": 0.7765,
"step": 828
},
{
"epoch": 0.2861580945806006,
"grad_norm": 2.368382453918457,
"learning_rate": 2e-05,
"loss": 0.778,
"step": 829
},
{
"epoch": 0.2865032792544011,
"grad_norm": 3.2637546062469482,
"learning_rate": 2e-05,
"loss": 0.7795,
"step": 830
},
{
"epoch": 0.28684846392820157,
"grad_norm": 2.1969919204711914,
"learning_rate": 2e-05,
"loss": 0.8387,
"step": 831
},
{
"epoch": 0.2871936486020021,
"grad_norm": 2.7861218452453613,
"learning_rate": 2e-05,
"loss": 0.836,
"step": 832
},
{
"epoch": 0.28753883327580254,
"grad_norm": 2.5360143184661865,
"learning_rate": 2e-05,
"loss": 0.807,
"step": 833
},
{
"epoch": 0.28788401794960305,
"grad_norm": 2.3107171058654785,
"learning_rate": 2e-05,
"loss": 0.7693,
"step": 834
},
{
"epoch": 0.2882292026234035,
"grad_norm": 2.3907177448272705,
"learning_rate": 2e-05,
"loss": 0.817,
"step": 835
},
{
"epoch": 0.288574387297204,
"grad_norm": 2.210458517074585,
"learning_rate": 2e-05,
"loss": 0.7167,
"step": 836
},
{
"epoch": 0.2889195719710045,
"grad_norm": 2.457772970199585,
"learning_rate": 2e-05,
"loss": 0.8089,
"step": 837
},
{
"epoch": 0.28926475664480494,
"grad_norm": 2.281331777572632,
"learning_rate": 2e-05,
"loss": 0.8044,
"step": 838
},
{
"epoch": 0.28960994131860546,
"grad_norm": 2.2387568950653076,
"learning_rate": 2e-05,
"loss": 0.7641,
"step": 839
},
{
"epoch": 0.2899551259924059,
"grad_norm": 2.3929879665374756,
"learning_rate": 2e-05,
"loss": 0.8267,
"step": 840
},
{
"epoch": 0.29030031066620643,
"grad_norm": 2.53993558883667,
"learning_rate": 2e-05,
"loss": 0.7637,
"step": 841
},
{
"epoch": 0.2906454953400069,
"grad_norm": 2.3552863597869873,
"learning_rate": 2e-05,
"loss": 0.7518,
"step": 842
},
{
"epoch": 0.2909906800138074,
"grad_norm": 2.438748359680176,
"learning_rate": 2e-05,
"loss": 0.8188,
"step": 843
},
{
"epoch": 0.29133586468760786,
"grad_norm": 2.2611324787139893,
"learning_rate": 2e-05,
"loss": 0.7828,
"step": 844
},
{
"epoch": 0.2916810493614084,
"grad_norm": 2.1586382389068604,
"learning_rate": 2e-05,
"loss": 0.7041,
"step": 845
},
{
"epoch": 0.29202623403520883,
"grad_norm": 2.498196601867676,
"learning_rate": 2e-05,
"loss": 0.8151,
"step": 846
},
{
"epoch": 0.29237141870900935,
"grad_norm": 2.294062852859497,
"learning_rate": 2e-05,
"loss": 0.758,
"step": 847
},
{
"epoch": 0.2927166033828098,
"grad_norm": 2.2366390228271484,
"learning_rate": 2e-05,
"loss": 0.803,
"step": 848
},
{
"epoch": 0.29306178805661026,
"grad_norm": 2.4893128871917725,
"learning_rate": 2e-05,
"loss": 0.7928,
"step": 849
},
{
"epoch": 0.2934069727304108,
"grad_norm": 2.315063238143921,
"learning_rate": 2e-05,
"loss": 0.7889,
"step": 850
},
{
"epoch": 0.29375215740421123,
"grad_norm": 2.363053321838379,
"learning_rate": 2e-05,
"loss": 0.7091,
"step": 851
},
{
"epoch": 0.29409734207801175,
"grad_norm": 2.5700855255126953,
"learning_rate": 2e-05,
"loss": 0.8141,
"step": 852
},
{
"epoch": 0.2944425267518122,
"grad_norm": 2.262510299682617,
"learning_rate": 2e-05,
"loss": 0.8147,
"step": 853
},
{
"epoch": 0.2947877114256127,
"grad_norm": 2.419389486312866,
"learning_rate": 2e-05,
"loss": 0.8083,
"step": 854
},
{
"epoch": 0.2951328960994132,
"grad_norm": 2.3417556285858154,
"learning_rate": 2e-05,
"loss": 0.7007,
"step": 855
},
{
"epoch": 0.2954780807732137,
"grad_norm": 2.3193564414978027,
"learning_rate": 2e-05,
"loss": 0.7122,
"step": 856
},
{
"epoch": 0.29582326544701415,
"grad_norm": 2.9452264308929443,
"learning_rate": 2e-05,
"loss": 0.7895,
"step": 857
},
{
"epoch": 0.2961684501208146,
"grad_norm": 2.6561877727508545,
"learning_rate": 2e-05,
"loss": 0.8272,
"step": 858
},
{
"epoch": 0.2965136347946151,
"grad_norm": 2.652930736541748,
"learning_rate": 2e-05,
"loss": 0.7604,
"step": 859
},
{
"epoch": 0.2968588194684156,
"grad_norm": 2.882368564605713,
"learning_rate": 2e-05,
"loss": 0.845,
"step": 860
},
{
"epoch": 0.2972040041422161,
"grad_norm": 2.3490078449249268,
"learning_rate": 2e-05,
"loss": 0.8426,
"step": 861
},
{
"epoch": 0.29754918881601655,
"grad_norm": 2.719566583633423,
"learning_rate": 2e-05,
"loss": 0.8542,
"step": 862
},
{
"epoch": 0.29789437348981707,
"grad_norm": 2.6340112686157227,
"learning_rate": 2e-05,
"loss": 0.7555,
"step": 863
},
{
"epoch": 0.2982395581636175,
"grad_norm": 2.5312600135803223,
"learning_rate": 2e-05,
"loss": 0.7925,
"step": 864
},
{
"epoch": 0.29858474283741804,
"grad_norm": 2.4707272052764893,
"learning_rate": 2e-05,
"loss": 0.7545,
"step": 865
},
{
"epoch": 0.2989299275112185,
"grad_norm": 2.3420259952545166,
"learning_rate": 2e-05,
"loss": 0.7992,
"step": 866
},
{
"epoch": 0.299275112185019,
"grad_norm": 2.4616615772247314,
"learning_rate": 2e-05,
"loss": 0.8436,
"step": 867
},
{
"epoch": 0.29962029685881947,
"grad_norm": 2.380793333053589,
"learning_rate": 2e-05,
"loss": 0.7698,
"step": 868
},
{
"epoch": 0.2999654815326199,
"grad_norm": 2.823423147201538,
"learning_rate": 2e-05,
"loss": 0.8289,
"step": 869
},
{
"epoch": 0.30031066620642044,
"grad_norm": 2.4169535636901855,
"learning_rate": 2e-05,
"loss": 0.8078,
"step": 870
},
{
"epoch": 0.3006558508802209,
"grad_norm": 2.4925384521484375,
"learning_rate": 2e-05,
"loss": 0.7523,
"step": 871
},
{
"epoch": 0.3010010355540214,
"grad_norm": 2.4129271507263184,
"learning_rate": 2e-05,
"loss": 0.7943,
"step": 872
},
{
"epoch": 0.30134622022782187,
"grad_norm": 2.366149663925171,
"learning_rate": 2e-05,
"loss": 0.7477,
"step": 873
},
{
"epoch": 0.3016914049016224,
"grad_norm": 2.176807403564453,
"learning_rate": 2e-05,
"loss": 0.7573,
"step": 874
},
{
"epoch": 0.30203658957542284,
"grad_norm": 2.3971831798553467,
"learning_rate": 2e-05,
"loss": 0.8159,
"step": 875
},
{
"epoch": 0.30238177424922336,
"grad_norm": 2.2808613777160645,
"learning_rate": 2e-05,
"loss": 0.8124,
"step": 876
},
{
"epoch": 0.3027269589230238,
"grad_norm": 2.2993972301483154,
"learning_rate": 2e-05,
"loss": 0.7731,
"step": 877
},
{
"epoch": 0.30307214359682433,
"grad_norm": 2.7519545555114746,
"learning_rate": 2e-05,
"loss": 0.8003,
"step": 878
},
{
"epoch": 0.3034173282706248,
"grad_norm": 2.4404890537261963,
"learning_rate": 2e-05,
"loss": 0.8554,
"step": 879
},
{
"epoch": 0.30376251294442524,
"grad_norm": 2.3009283542633057,
"learning_rate": 2e-05,
"loss": 0.7411,
"step": 880
},
{
"epoch": 0.30410769761822576,
"grad_norm": 2.109697103500366,
"learning_rate": 2e-05,
"loss": 0.8216,
"step": 881
},
{
"epoch": 0.3044528822920262,
"grad_norm": 2.3877744674682617,
"learning_rate": 2e-05,
"loss": 0.8017,
"step": 882
},
{
"epoch": 0.30479806696582673,
"grad_norm": 2.4049599170684814,
"learning_rate": 2e-05,
"loss": 0.8427,
"step": 883
},
{
"epoch": 0.3051432516396272,
"grad_norm": 2.552929162979126,
"learning_rate": 2e-05,
"loss": 0.8331,
"step": 884
},
{
"epoch": 0.3054884363134277,
"grad_norm": 2.3699262142181396,
"learning_rate": 2e-05,
"loss": 0.7913,
"step": 885
},
{
"epoch": 0.30583362098722816,
"grad_norm": 2.175236463546753,
"learning_rate": 2e-05,
"loss": 0.7643,
"step": 886
},
{
"epoch": 0.3061788056610287,
"grad_norm": 2.194126605987549,
"learning_rate": 2e-05,
"loss": 0.7641,
"step": 887
},
{
"epoch": 0.30652399033482913,
"grad_norm": 2.1524200439453125,
"learning_rate": 2e-05,
"loss": 0.7448,
"step": 888
},
{
"epoch": 0.3068691750086296,
"grad_norm": 2.622220516204834,
"learning_rate": 2e-05,
"loss": 0.9229,
"step": 889
},
{
"epoch": 0.3072143596824301,
"grad_norm": 2.2300989627838135,
"learning_rate": 2e-05,
"loss": 0.7906,
"step": 890
},
{
"epoch": 0.30755954435623056,
"grad_norm": 2.328655958175659,
"learning_rate": 2e-05,
"loss": 0.7749,
"step": 891
},
{
"epoch": 0.3079047290300311,
"grad_norm": 2.381244659423828,
"learning_rate": 2e-05,
"loss": 0.761,
"step": 892
},
{
"epoch": 0.30824991370383154,
"grad_norm": 2.3483664989471436,
"learning_rate": 2e-05,
"loss": 0.8149,
"step": 893
},
{
"epoch": 0.30859509837763205,
"grad_norm": 2.3732330799102783,
"learning_rate": 2e-05,
"loss": 0.8124,
"step": 894
},
{
"epoch": 0.3089402830514325,
"grad_norm": 2.227066993713379,
"learning_rate": 2e-05,
"loss": 0.7761,
"step": 895
},
{
"epoch": 0.309285467725233,
"grad_norm": 2.516470432281494,
"learning_rate": 2e-05,
"loss": 0.8069,
"step": 896
},
{
"epoch": 0.3096306523990335,
"grad_norm": 2.320647716522217,
"learning_rate": 2e-05,
"loss": 0.7664,
"step": 897
},
{
"epoch": 0.309975837072834,
"grad_norm": 2.3482866287231445,
"learning_rate": 2e-05,
"loss": 0.7724,
"step": 898
},
{
"epoch": 0.31032102174663445,
"grad_norm": 2.428755521774292,
"learning_rate": 2e-05,
"loss": 0.8333,
"step": 899
},
{
"epoch": 0.3106662064204349,
"grad_norm": 2.6640501022338867,
"learning_rate": 2e-05,
"loss": 0.7432,
"step": 900
},
{
"epoch": 0.3110113910942354,
"grad_norm": 2.2669763565063477,
"learning_rate": 2e-05,
"loss": 0.8351,
"step": 901
},
{
"epoch": 0.3113565757680359,
"grad_norm": 2.370856761932373,
"learning_rate": 2e-05,
"loss": 0.8207,
"step": 902
},
{
"epoch": 0.3117017604418364,
"grad_norm": 2.3243308067321777,
"learning_rate": 2e-05,
"loss": 0.7393,
"step": 903
},
{
"epoch": 0.31204694511563685,
"grad_norm": 2.1420657634735107,
"learning_rate": 2e-05,
"loss": 0.8058,
"step": 904
},
{
"epoch": 0.31239212978943737,
"grad_norm": 2.0886402130126953,
"learning_rate": 2e-05,
"loss": 0.8045,
"step": 905
},
{
"epoch": 0.3127373144632378,
"grad_norm": 2.280564069747925,
"learning_rate": 2e-05,
"loss": 0.7212,
"step": 906
},
{
"epoch": 0.31308249913703834,
"grad_norm": 2.2843098640441895,
"learning_rate": 2e-05,
"loss": 0.7496,
"step": 907
},
{
"epoch": 0.3134276838108388,
"grad_norm": 2.160379409790039,
"learning_rate": 2e-05,
"loss": 0.8435,
"step": 908
},
{
"epoch": 0.31377286848463926,
"grad_norm": 2.27815318107605,
"learning_rate": 2e-05,
"loss": 0.7455,
"step": 909
},
{
"epoch": 0.31411805315843977,
"grad_norm": 2.2776007652282715,
"learning_rate": 2e-05,
"loss": 0.7947,
"step": 910
},
{
"epoch": 0.3144632378322402,
"grad_norm": 2.898167133331299,
"learning_rate": 2e-05,
"loss": 0.6744,
"step": 911
},
{
"epoch": 0.31480842250604074,
"grad_norm": 2.51155424118042,
"learning_rate": 2e-05,
"loss": 0.8273,
"step": 912
},
{
"epoch": 0.3151536071798412,
"grad_norm": 2.273869037628174,
"learning_rate": 2e-05,
"loss": 0.7426,
"step": 913
},
{
"epoch": 0.3154987918536417,
"grad_norm": 2.4767696857452393,
"learning_rate": 2e-05,
"loss": 0.7697,
"step": 914
},
{
"epoch": 0.31584397652744217,
"grad_norm": 2.3529250621795654,
"learning_rate": 2e-05,
"loss": 0.8166,
"step": 915
},
{
"epoch": 0.3161891612012427,
"grad_norm": 2.354522466659546,
"learning_rate": 2e-05,
"loss": 0.7638,
"step": 916
},
{
"epoch": 0.31653434587504314,
"grad_norm": 2.5877065658569336,
"learning_rate": 2e-05,
"loss": 0.8177,
"step": 917
},
{
"epoch": 0.31687953054884366,
"grad_norm": 2.252060890197754,
"learning_rate": 2e-05,
"loss": 0.8002,
"step": 918
},
{
"epoch": 0.3172247152226441,
"grad_norm": 2.7347230911254883,
"learning_rate": 2e-05,
"loss": 0.7618,
"step": 919
},
{
"epoch": 0.3175698998964446,
"grad_norm": 2.3109960556030273,
"learning_rate": 2e-05,
"loss": 0.814,
"step": 920
},
{
"epoch": 0.3179150845702451,
"grad_norm": 2.368884801864624,
"learning_rate": 2e-05,
"loss": 0.8036,
"step": 921
},
{
"epoch": 0.31826026924404555,
"grad_norm": 2.480783700942993,
"learning_rate": 2e-05,
"loss": 0.7088,
"step": 922
},
{
"epoch": 0.31860545391784606,
"grad_norm": 2.4031803607940674,
"learning_rate": 2e-05,
"loss": 0.7326,
"step": 923
},
{
"epoch": 0.3189506385916465,
"grad_norm": 2.323190450668335,
"learning_rate": 2e-05,
"loss": 0.7588,
"step": 924
},
{
"epoch": 0.31929582326544703,
"grad_norm": 2.202821969985962,
"learning_rate": 2e-05,
"loss": 0.7255,
"step": 925
},
{
"epoch": 0.3196410079392475,
"grad_norm": 2.212124824523926,
"learning_rate": 2e-05,
"loss": 0.8272,
"step": 926
},
{
"epoch": 0.319986192613048,
"grad_norm": 2.3351826667785645,
"learning_rate": 2e-05,
"loss": 0.7665,
"step": 927
},
{
"epoch": 0.32033137728684846,
"grad_norm": 2.088829755783081,
"learning_rate": 2e-05,
"loss": 0.7304,
"step": 928
},
{
"epoch": 0.3206765619606489,
"grad_norm": 2.103823661804199,
"learning_rate": 2e-05,
"loss": 0.7687,
"step": 929
},
{
"epoch": 0.32102174663444943,
"grad_norm": 2.1671319007873535,
"learning_rate": 2e-05,
"loss": 0.7811,
"step": 930
},
{
"epoch": 0.3213669313082499,
"grad_norm": 2.0397748947143555,
"learning_rate": 2e-05,
"loss": 0.787,
"step": 931
},
{
"epoch": 0.3217121159820504,
"grad_norm": 2.274035692214966,
"learning_rate": 2e-05,
"loss": 0.8261,
"step": 932
},
{
"epoch": 0.32205730065585086,
"grad_norm": 2.330312967300415,
"learning_rate": 2e-05,
"loss": 0.7617,
"step": 933
},
{
"epoch": 0.3224024853296514,
"grad_norm": 2.260516881942749,
"learning_rate": 2e-05,
"loss": 0.8307,
"step": 934
},
{
"epoch": 0.32274767000345184,
"grad_norm": 2.4335250854492188,
"learning_rate": 2e-05,
"loss": 0.7427,
"step": 935
},
{
"epoch": 0.32309285467725235,
"grad_norm": 2.2778549194335938,
"learning_rate": 2e-05,
"loss": 0.827,
"step": 936
},
{
"epoch": 0.3234380393510528,
"grad_norm": 2.3608310222625732,
"learning_rate": 2e-05,
"loss": 0.7026,
"step": 937
},
{
"epoch": 0.3237832240248533,
"grad_norm": 2.297184705734253,
"learning_rate": 2e-05,
"loss": 0.7688,
"step": 938
},
{
"epoch": 0.3241284086986538,
"grad_norm": 2.3631842136383057,
"learning_rate": 2e-05,
"loss": 0.7836,
"step": 939
},
{
"epoch": 0.32447359337245424,
"grad_norm": 2.25142765045166,
"learning_rate": 2e-05,
"loss": 0.8511,
"step": 940
},
{
"epoch": 0.32481877804625475,
"grad_norm": 2.3377201557159424,
"learning_rate": 2e-05,
"loss": 0.7421,
"step": 941
},
{
"epoch": 0.3251639627200552,
"grad_norm": 2.250669479370117,
"learning_rate": 2e-05,
"loss": 0.6976,
"step": 942
},
{
"epoch": 0.3255091473938557,
"grad_norm": 2.241152286529541,
"learning_rate": 2e-05,
"loss": 0.7744,
"step": 943
},
{
"epoch": 0.3258543320676562,
"grad_norm": 2.282179355621338,
"learning_rate": 2e-05,
"loss": 0.7057,
"step": 944
},
{
"epoch": 0.3261995167414567,
"grad_norm": 2.3644256591796875,
"learning_rate": 2e-05,
"loss": 0.8459,
"step": 945
},
{
"epoch": 0.32654470141525715,
"grad_norm": 2.6764843463897705,
"learning_rate": 2e-05,
"loss": 0.7514,
"step": 946
},
{
"epoch": 0.32688988608905767,
"grad_norm": 2.2294766902923584,
"learning_rate": 2e-05,
"loss": 0.8113,
"step": 947
},
{
"epoch": 0.3272350707628581,
"grad_norm": 2.2124416828155518,
"learning_rate": 2e-05,
"loss": 0.6864,
"step": 948
},
{
"epoch": 0.3275802554366586,
"grad_norm": 2.4242794513702393,
"learning_rate": 2e-05,
"loss": 0.7904,
"step": 949
},
{
"epoch": 0.3279254401104591,
"grad_norm": 2.272757053375244,
"learning_rate": 2e-05,
"loss": 0.7613,
"step": 950
},
{
"epoch": 0.32827062478425956,
"grad_norm": 2.1296377182006836,
"learning_rate": 2e-05,
"loss": 0.778,
"step": 951
},
{
"epoch": 0.32861580945806007,
"grad_norm": 2.3032419681549072,
"learning_rate": 2e-05,
"loss": 0.8262,
"step": 952
},
{
"epoch": 0.32896099413186053,
"grad_norm": 2.254443645477295,
"learning_rate": 2e-05,
"loss": 0.8342,
"step": 953
},
{
"epoch": 0.32930617880566104,
"grad_norm": 2.3815431594848633,
"learning_rate": 2e-05,
"loss": 0.7047,
"step": 954
},
{
"epoch": 0.3296513634794615,
"grad_norm": 2.073943853378296,
"learning_rate": 2e-05,
"loss": 0.7717,
"step": 955
},
{
"epoch": 0.329996548153262,
"grad_norm": 2.1470041275024414,
"learning_rate": 2e-05,
"loss": 0.7661,
"step": 956
},
{
"epoch": 0.3303417328270625,
"grad_norm": 2.346449851989746,
"learning_rate": 2e-05,
"loss": 0.8083,
"step": 957
},
{
"epoch": 0.330686917500863,
"grad_norm": 2.5005104541778564,
"learning_rate": 2e-05,
"loss": 0.7771,
"step": 958
},
{
"epoch": 0.33103210217466345,
"grad_norm": 2.5050013065338135,
"learning_rate": 2e-05,
"loss": 0.8185,
"step": 959
},
{
"epoch": 0.3313772868484639,
"grad_norm": 2.206801652908325,
"learning_rate": 2e-05,
"loss": 0.761,
"step": 960
},
{
"epoch": 0.3317224715222644,
"grad_norm": 2.3278515338897705,
"learning_rate": 2e-05,
"loss": 0.7641,
"step": 961
},
{
"epoch": 0.3320676561960649,
"grad_norm": 2.2485294342041016,
"learning_rate": 2e-05,
"loss": 0.8701,
"step": 962
},
{
"epoch": 0.3324128408698654,
"grad_norm": 2.4933691024780273,
"learning_rate": 2e-05,
"loss": 0.7856,
"step": 963
},
{
"epoch": 0.33275802554366585,
"grad_norm": 2.3348371982574463,
"learning_rate": 2e-05,
"loss": 0.7705,
"step": 964
},
{
"epoch": 0.33310321021746636,
"grad_norm": 2.4476113319396973,
"learning_rate": 2e-05,
"loss": 0.8149,
"step": 965
},
{
"epoch": 0.3334483948912668,
"grad_norm": 2.321218729019165,
"learning_rate": 2e-05,
"loss": 0.8113,
"step": 966
},
{
"epoch": 0.33379357956506733,
"grad_norm": 2.575770378112793,
"learning_rate": 2e-05,
"loss": 0.8143,
"step": 967
},
{
"epoch": 0.3341387642388678,
"grad_norm": 2.182896852493286,
"learning_rate": 2e-05,
"loss": 0.7476,
"step": 968
},
{
"epoch": 0.3344839489126683,
"grad_norm": 2.0320241451263428,
"learning_rate": 2e-05,
"loss": 0.7314,
"step": 969
},
{
"epoch": 0.33482913358646876,
"grad_norm": 2.2373087406158447,
"learning_rate": 2e-05,
"loss": 0.7352,
"step": 970
},
{
"epoch": 0.3351743182602692,
"grad_norm": 2.1493780612945557,
"learning_rate": 2e-05,
"loss": 0.8441,
"step": 971
},
{
"epoch": 0.33551950293406974,
"grad_norm": 3.392732620239258,
"learning_rate": 2e-05,
"loss": 0.7954,
"step": 972
},
{
"epoch": 0.3358646876078702,
"grad_norm": 2.2319388389587402,
"learning_rate": 2e-05,
"loss": 0.8502,
"step": 973
},
{
"epoch": 0.3362098722816707,
"grad_norm": 2.31962251663208,
"learning_rate": 2e-05,
"loss": 0.7509,
"step": 974
},
{
"epoch": 0.33655505695547117,
"grad_norm": 2.3655319213867188,
"learning_rate": 2e-05,
"loss": 0.7724,
"step": 975
},
{
"epoch": 0.3369002416292717,
"grad_norm": 2.3151824474334717,
"learning_rate": 2e-05,
"loss": 0.7318,
"step": 976
},
{
"epoch": 0.33724542630307214,
"grad_norm": 2.2314257621765137,
"learning_rate": 2e-05,
"loss": 0.7646,
"step": 977
},
{
"epoch": 0.33759061097687265,
"grad_norm": 2.140748977661133,
"learning_rate": 2e-05,
"loss": 0.7019,
"step": 978
},
{
"epoch": 0.3379357956506731,
"grad_norm": 2.5134060382843018,
"learning_rate": 2e-05,
"loss": 0.7662,
"step": 979
},
{
"epoch": 0.33828098032447357,
"grad_norm": 2.497497081756592,
"learning_rate": 2e-05,
"loss": 0.7673,
"step": 980
},
{
"epoch": 0.3386261649982741,
"grad_norm": 2.574514627456665,
"learning_rate": 2e-05,
"loss": 0.8181,
"step": 981
},
{
"epoch": 0.33897134967207454,
"grad_norm": 2.1714820861816406,
"learning_rate": 2e-05,
"loss": 0.8158,
"step": 982
},
{
"epoch": 0.33931653434587505,
"grad_norm": 2.1695728302001953,
"learning_rate": 2e-05,
"loss": 0.7305,
"step": 983
},
{
"epoch": 0.3396617190196755,
"grad_norm": 2.3775722980499268,
"learning_rate": 2e-05,
"loss": 0.7287,
"step": 984
},
{
"epoch": 0.340006903693476,
"grad_norm": 2.2514188289642334,
"learning_rate": 2e-05,
"loss": 0.8116,
"step": 985
},
{
"epoch": 0.3403520883672765,
"grad_norm": 2.3686721324920654,
"learning_rate": 2e-05,
"loss": 0.7692,
"step": 986
},
{
"epoch": 0.340697273041077,
"grad_norm": 2.2785122394561768,
"learning_rate": 2e-05,
"loss": 0.7572,
"step": 987
},
{
"epoch": 0.34104245771487746,
"grad_norm": 2.2682762145996094,
"learning_rate": 2e-05,
"loss": 0.7479,
"step": 988
},
{
"epoch": 0.34138764238867797,
"grad_norm": 2.2011334896087646,
"learning_rate": 2e-05,
"loss": 0.7539,
"step": 989
},
{
"epoch": 0.34173282706247843,
"grad_norm": 2.2542169094085693,
"learning_rate": 2e-05,
"loss": 0.7368,
"step": 990
},
{
"epoch": 0.3420780117362789,
"grad_norm": 2.443906545639038,
"learning_rate": 2e-05,
"loss": 0.7847,
"step": 991
},
{
"epoch": 0.3424231964100794,
"grad_norm": 2.492189645767212,
"learning_rate": 2e-05,
"loss": 0.7883,
"step": 992
},
{
"epoch": 0.34276838108387986,
"grad_norm": 2.384871006011963,
"learning_rate": 2e-05,
"loss": 0.8122,
"step": 993
},
{
"epoch": 0.34311356575768037,
"grad_norm": 2.2505013942718506,
"learning_rate": 2e-05,
"loss": 0.7727,
"step": 994
},
{
"epoch": 0.34345875043148083,
"grad_norm": 2.2702903747558594,
"learning_rate": 2e-05,
"loss": 0.7939,
"step": 995
},
{
"epoch": 0.34380393510528134,
"grad_norm": 2.3637566566467285,
"learning_rate": 2e-05,
"loss": 0.8628,
"step": 996
},
{
"epoch": 0.3441491197790818,
"grad_norm": 2.1582224369049072,
"learning_rate": 2e-05,
"loss": 0.6891,
"step": 997
},
{
"epoch": 0.3444943044528823,
"grad_norm": 2.3541908264160156,
"learning_rate": 2e-05,
"loss": 0.8119,
"step": 998
},
{
"epoch": 0.3448394891266828,
"grad_norm": 2.225794553756714,
"learning_rate": 2e-05,
"loss": 0.8058,
"step": 999
},
{
"epoch": 0.34518467380048323,
"grad_norm": 2.3808062076568604,
"learning_rate": 2e-05,
"loss": 0.744,
"step": 1000
}
],
"logging_steps": 1.0,
"max_steps": 14485,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 628138967040000.0,
"train_batch_size": 12,
"trial_name": null,
"trial_params": null
}