v0.8.18-adapter / 550 /trainer_state.json
gotzmann's picture
..
c469d9c
raw
history blame
88.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0018214936247722,
"eval_steps": 500,
"global_step": 550,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 0.46431864432643544,
"learning_rate": 1.2121212121212122e-06,
"loss": 1.4151,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 0.42969176658539837,
"learning_rate": 2.4242424242424244e-06,
"loss": 1.3729,
"step": 2
},
{
"epoch": 0.01,
"grad_norm": 0.5004307936270223,
"learning_rate": 3.636363636363636e-06,
"loss": 1.3989,
"step": 3
},
{
"epoch": 0.01,
"grad_norm": 0.43666634920041486,
"learning_rate": 4.848484848484849e-06,
"loss": 1.3363,
"step": 4
},
{
"epoch": 0.01,
"grad_norm": 0.4691114419353825,
"learning_rate": 6.060606060606061e-06,
"loss": 1.4293,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 0.4277596061377729,
"learning_rate": 7.272727272727272e-06,
"loss": 1.4343,
"step": 6
},
{
"epoch": 0.01,
"grad_norm": 0.4238339229382504,
"learning_rate": 8.484848484848486e-06,
"loss": 1.4462,
"step": 7
},
{
"epoch": 0.01,
"grad_norm": 0.40992048534183273,
"learning_rate": 9.696969696969698e-06,
"loss": 1.2756,
"step": 8
},
{
"epoch": 0.02,
"grad_norm": 0.37885700313540693,
"learning_rate": 1.0909090909090909e-05,
"loss": 1.3464,
"step": 9
},
{
"epoch": 0.02,
"grad_norm": 0.36066141170123023,
"learning_rate": 1.2121212121212122e-05,
"loss": 1.3419,
"step": 10
},
{
"epoch": 0.02,
"grad_norm": 0.35617169386863406,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.3533,
"step": 11
},
{
"epoch": 0.02,
"grad_norm": 0.3040188564782602,
"learning_rate": 1.4545454545454545e-05,
"loss": 1.2395,
"step": 12
},
{
"epoch": 0.02,
"grad_norm": 0.31038319439216566,
"learning_rate": 1.5757575757575756e-05,
"loss": 1.3082,
"step": 13
},
{
"epoch": 0.03,
"grad_norm": 0.26683768372135835,
"learning_rate": 1.6969696969696972e-05,
"loss": 1.3063,
"step": 14
},
{
"epoch": 0.03,
"grad_norm": 0.3652323682563078,
"learning_rate": 1.8181818181818182e-05,
"loss": 1.3045,
"step": 15
},
{
"epoch": 0.03,
"grad_norm": 0.23559121485457843,
"learning_rate": 1.9393939393939395e-05,
"loss": 1.2366,
"step": 16
},
{
"epoch": 0.03,
"grad_norm": 0.2342299313020104,
"learning_rate": 2.0606060606060608e-05,
"loss": 1.2831,
"step": 17
},
{
"epoch": 0.03,
"grad_norm": 0.2202931700357255,
"learning_rate": 2.1818181818181818e-05,
"loss": 1.3064,
"step": 18
},
{
"epoch": 0.03,
"grad_norm": 0.2097660599292375,
"learning_rate": 2.3030303030303034e-05,
"loss": 1.2376,
"step": 19
},
{
"epoch": 0.04,
"grad_norm": 0.2356785314652122,
"learning_rate": 2.4242424242424244e-05,
"loss": 1.2802,
"step": 20
},
{
"epoch": 0.04,
"grad_norm": 0.24639302530564244,
"learning_rate": 2.5454545454545454e-05,
"loss": 1.3016,
"step": 21
},
{
"epoch": 0.04,
"grad_norm": 0.24373126133228787,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.3407,
"step": 22
},
{
"epoch": 0.04,
"grad_norm": 0.24488805144123432,
"learning_rate": 2.7878787878787883e-05,
"loss": 1.3325,
"step": 23
},
{
"epoch": 0.04,
"grad_norm": 0.2653033507571198,
"learning_rate": 2.909090909090909e-05,
"loss": 1.2811,
"step": 24
},
{
"epoch": 0.05,
"grad_norm": 1.2841724819336817,
"learning_rate": 3.0303030303030306e-05,
"loss": 1.2837,
"step": 25
},
{
"epoch": 0.05,
"grad_norm": 0.2183883020111492,
"learning_rate": 3.151515151515151e-05,
"loss": 1.2472,
"step": 26
},
{
"epoch": 0.05,
"grad_norm": 0.2137995163762026,
"learning_rate": 3.272727272727273e-05,
"loss": 1.2854,
"step": 27
},
{
"epoch": 0.05,
"grad_norm": 0.19499006223503876,
"learning_rate": 3.3939393939393945e-05,
"loss": 1.3018,
"step": 28
},
{
"epoch": 0.05,
"grad_norm": 0.17367919355340256,
"learning_rate": 3.515151515151515e-05,
"loss": 1.2824,
"step": 29
},
{
"epoch": 0.05,
"grad_norm": 0.18326045693683557,
"learning_rate": 3.6363636363636364e-05,
"loss": 1.2192,
"step": 30
},
{
"epoch": 0.06,
"grad_norm": 0.17474388188066411,
"learning_rate": 3.757575757575758e-05,
"loss": 1.2078,
"step": 31
},
{
"epoch": 0.06,
"grad_norm": 0.17856970178098716,
"learning_rate": 3.878787878787879e-05,
"loss": 1.2683,
"step": 32
},
{
"epoch": 0.06,
"grad_norm": 0.18617589704298348,
"learning_rate": 4e-05,
"loss": 1.2265,
"step": 33
},
{
"epoch": 0.06,
"grad_norm": 0.17653209733215317,
"learning_rate": 4.1212121212121216e-05,
"loss": 1.319,
"step": 34
},
{
"epoch": 0.06,
"grad_norm": 0.1722921367585233,
"learning_rate": 4.242424242424243e-05,
"loss": 1.2117,
"step": 35
},
{
"epoch": 0.07,
"grad_norm": 0.176642606378719,
"learning_rate": 4.3636363636363636e-05,
"loss": 1.2512,
"step": 36
},
{
"epoch": 0.07,
"grad_norm": 0.16696442324691066,
"learning_rate": 4.484848484848485e-05,
"loss": 1.2637,
"step": 37
},
{
"epoch": 0.07,
"grad_norm": 0.17035384059517106,
"learning_rate": 4.606060606060607e-05,
"loss": 1.2699,
"step": 38
},
{
"epoch": 0.07,
"grad_norm": 0.15545801881444482,
"learning_rate": 4.7272727272727275e-05,
"loss": 1.2939,
"step": 39
},
{
"epoch": 0.07,
"grad_norm": 0.17111439344347512,
"learning_rate": 4.848484848484849e-05,
"loss": 1.3033,
"step": 40
},
{
"epoch": 0.07,
"grad_norm": 0.16994151343455458,
"learning_rate": 4.9696969696969694e-05,
"loss": 1.2603,
"step": 41
},
{
"epoch": 0.08,
"grad_norm": 0.15929214926453447,
"learning_rate": 5.090909090909091e-05,
"loss": 1.2626,
"step": 42
},
{
"epoch": 0.08,
"grad_norm": 0.16761261516238699,
"learning_rate": 5.212121212121213e-05,
"loss": 1.296,
"step": 43
},
{
"epoch": 0.08,
"grad_norm": 0.15754700542426123,
"learning_rate": 5.333333333333333e-05,
"loss": 1.278,
"step": 44
},
{
"epoch": 0.08,
"grad_norm": 0.15522526683877644,
"learning_rate": 5.4545454545454546e-05,
"loss": 1.2355,
"step": 45
},
{
"epoch": 0.08,
"grad_norm": 0.1577929926930023,
"learning_rate": 5.5757575757575766e-05,
"loss": 1.2879,
"step": 46
},
{
"epoch": 0.09,
"grad_norm": 0.31075066632858317,
"learning_rate": 5.696969696969697e-05,
"loss": 1.2202,
"step": 47
},
{
"epoch": 0.09,
"grad_norm": 0.1663780653395111,
"learning_rate": 5.818181818181818e-05,
"loss": 1.2319,
"step": 48
},
{
"epoch": 0.09,
"grad_norm": 0.16049499655883026,
"learning_rate": 5.93939393939394e-05,
"loss": 1.2801,
"step": 49
},
{
"epoch": 0.09,
"grad_norm": 0.14515773124436285,
"learning_rate": 6.060606060606061e-05,
"loss": 1.2588,
"step": 50
},
{
"epoch": 0.09,
"grad_norm": 0.14653064850325623,
"learning_rate": 6.181818181818182e-05,
"loss": 1.2677,
"step": 51
},
{
"epoch": 0.09,
"grad_norm": 0.17193239746689878,
"learning_rate": 6.303030303030302e-05,
"loss": 1.2742,
"step": 52
},
{
"epoch": 0.1,
"grad_norm": 0.1967020450342533,
"learning_rate": 6.424242424242424e-05,
"loss": 1.1545,
"step": 53
},
{
"epoch": 0.1,
"grad_norm": 0.16247531997247225,
"learning_rate": 6.545454545454546e-05,
"loss": 1.222,
"step": 54
},
{
"epoch": 0.1,
"grad_norm": 0.14990706377244528,
"learning_rate": 6.666666666666667e-05,
"loss": 1.2103,
"step": 55
},
{
"epoch": 0.1,
"grad_norm": 0.1412817445239095,
"learning_rate": 6.787878787878789e-05,
"loss": 1.2169,
"step": 56
},
{
"epoch": 0.1,
"grad_norm": 0.14575971073482757,
"learning_rate": 6.90909090909091e-05,
"loss": 1.2751,
"step": 57
},
{
"epoch": 0.11,
"grad_norm": 0.13714747569950891,
"learning_rate": 7.03030303030303e-05,
"loss": 1.2508,
"step": 58
},
{
"epoch": 0.11,
"grad_norm": 0.14334695156859903,
"learning_rate": 7.151515151515152e-05,
"loss": 1.2721,
"step": 59
},
{
"epoch": 0.11,
"grad_norm": 0.1456824177522916,
"learning_rate": 7.272727272727273e-05,
"loss": 1.2649,
"step": 60
},
{
"epoch": 0.11,
"grad_norm": 0.15030318240210044,
"learning_rate": 7.393939393939395e-05,
"loss": 1.2167,
"step": 61
},
{
"epoch": 0.11,
"grad_norm": 0.1651326066719482,
"learning_rate": 7.515151515151515e-05,
"loss": 1.3126,
"step": 62
},
{
"epoch": 0.11,
"grad_norm": 0.1408250406479118,
"learning_rate": 7.636363636363637e-05,
"loss": 1.2891,
"step": 63
},
{
"epoch": 0.12,
"grad_norm": 0.21501384376905694,
"learning_rate": 7.757575757575758e-05,
"loss": 1.3019,
"step": 64
},
{
"epoch": 0.12,
"grad_norm": 0.1365168726167339,
"learning_rate": 7.878787878787879e-05,
"loss": 1.2498,
"step": 65
},
{
"epoch": 0.12,
"grad_norm": 0.1431463689660936,
"learning_rate": 8e-05,
"loss": 1.2793,
"step": 66
},
{
"epoch": 0.12,
"grad_norm": 0.13689045214286194,
"learning_rate": 8.121212121212121e-05,
"loss": 1.2295,
"step": 67
},
{
"epoch": 0.12,
"grad_norm": 0.13483608710081227,
"learning_rate": 8.242424242424243e-05,
"loss": 1.2258,
"step": 68
},
{
"epoch": 0.13,
"grad_norm": 0.13707618564415613,
"learning_rate": 8.363636363636364e-05,
"loss": 1.2252,
"step": 69
},
{
"epoch": 0.13,
"grad_norm": 0.13780236215967515,
"learning_rate": 8.484848484848486e-05,
"loss": 1.2565,
"step": 70
},
{
"epoch": 0.13,
"grad_norm": 0.14036805493494423,
"learning_rate": 8.606060606060606e-05,
"loss": 1.3023,
"step": 71
},
{
"epoch": 0.13,
"grad_norm": 0.12776919439147982,
"learning_rate": 8.727272727272727e-05,
"loss": 1.2292,
"step": 72
},
{
"epoch": 0.13,
"grad_norm": 0.1289941815481437,
"learning_rate": 8.848484848484849e-05,
"loss": 1.2191,
"step": 73
},
{
"epoch": 0.13,
"grad_norm": 0.13943952294847306,
"learning_rate": 8.96969696969697e-05,
"loss": 1.2915,
"step": 74
},
{
"epoch": 0.14,
"grad_norm": 0.1493528502117281,
"learning_rate": 9.090909090909092e-05,
"loss": 1.2797,
"step": 75
},
{
"epoch": 0.14,
"grad_norm": 0.1252401242451818,
"learning_rate": 9.212121212121214e-05,
"loss": 1.2552,
"step": 76
},
{
"epoch": 0.14,
"grad_norm": 0.13969800467546992,
"learning_rate": 9.333333333333334e-05,
"loss": 1.3147,
"step": 77
},
{
"epoch": 0.14,
"grad_norm": 0.1277258491470434,
"learning_rate": 9.454545454545455e-05,
"loss": 1.2089,
"step": 78
},
{
"epoch": 0.14,
"grad_norm": 0.133041369314817,
"learning_rate": 9.575757575757576e-05,
"loss": 1.2761,
"step": 79
},
{
"epoch": 0.15,
"grad_norm": 0.14564572037181842,
"learning_rate": 9.696969696969698e-05,
"loss": 1.1901,
"step": 80
},
{
"epoch": 0.15,
"grad_norm": 0.13666505656492195,
"learning_rate": 9.818181818181818e-05,
"loss": 1.2615,
"step": 81
},
{
"epoch": 0.15,
"grad_norm": 0.135007805210003,
"learning_rate": 9.939393939393939e-05,
"loss": 1.2669,
"step": 82
},
{
"epoch": 0.15,
"grad_norm": 0.17287563365884975,
"learning_rate": 0.00010060606060606062,
"loss": 1.2669,
"step": 83
},
{
"epoch": 0.15,
"grad_norm": 0.12934306326048103,
"learning_rate": 0.00010181818181818181,
"loss": 1.1979,
"step": 84
},
{
"epoch": 0.15,
"grad_norm": 0.13517436169178096,
"learning_rate": 0.00010303030303030303,
"loss": 1.2226,
"step": 85
},
{
"epoch": 0.16,
"grad_norm": 0.12105351159271568,
"learning_rate": 0.00010424242424242425,
"loss": 1.1172,
"step": 86
},
{
"epoch": 0.16,
"grad_norm": 0.1281676431775383,
"learning_rate": 0.00010545454545454545,
"loss": 1.2046,
"step": 87
},
{
"epoch": 0.16,
"grad_norm": 0.11730963057933333,
"learning_rate": 0.00010666666666666667,
"loss": 1.1883,
"step": 88
},
{
"epoch": 0.16,
"grad_norm": 0.12655235108503246,
"learning_rate": 0.00010787878787878789,
"loss": 1.1331,
"step": 89
},
{
"epoch": 0.16,
"grad_norm": 0.13047560307970027,
"learning_rate": 0.00010909090909090909,
"loss": 1.2731,
"step": 90
},
{
"epoch": 0.17,
"grad_norm": 0.12193522973752649,
"learning_rate": 0.00011030303030303031,
"loss": 1.2161,
"step": 91
},
{
"epoch": 0.17,
"grad_norm": 0.12804360300116346,
"learning_rate": 0.00011151515151515153,
"loss": 1.3062,
"step": 92
},
{
"epoch": 0.17,
"grad_norm": 0.15991741754516206,
"learning_rate": 0.00011272727272727272,
"loss": 1.239,
"step": 93
},
{
"epoch": 0.17,
"grad_norm": 0.15140182244454561,
"learning_rate": 0.00011393939393939394,
"loss": 1.2349,
"step": 94
},
{
"epoch": 0.17,
"grad_norm": 0.12320241076263434,
"learning_rate": 0.00011515151515151516,
"loss": 1.2875,
"step": 95
},
{
"epoch": 0.17,
"grad_norm": 0.13235998458230466,
"learning_rate": 0.00011636363636363636,
"loss": 1.2218,
"step": 96
},
{
"epoch": 0.18,
"grad_norm": 0.11783688734798668,
"learning_rate": 0.00011757575757575758,
"loss": 1.1864,
"step": 97
},
{
"epoch": 0.18,
"grad_norm": 0.3151933420750235,
"learning_rate": 0.0001187878787878788,
"loss": 1.3023,
"step": 98
},
{
"epoch": 0.18,
"grad_norm": 0.12665632567219295,
"learning_rate": 0.00012,
"loss": 1.2249,
"step": 99
},
{
"epoch": 0.18,
"grad_norm": 0.1228886740460738,
"learning_rate": 0.00012121212121212122,
"loss": 1.2517,
"step": 100
},
{
"epoch": 0.18,
"grad_norm": 0.11892005244989344,
"learning_rate": 0.00012242424242424243,
"loss": 1.2586,
"step": 101
},
{
"epoch": 0.19,
"grad_norm": 0.1232340827222201,
"learning_rate": 0.00012363636363636364,
"loss": 1.3217,
"step": 102
},
{
"epoch": 0.19,
"grad_norm": 0.13837226869323116,
"learning_rate": 0.00012484848484848487,
"loss": 1.2693,
"step": 103
},
{
"epoch": 0.19,
"grad_norm": 0.12068217991774362,
"learning_rate": 0.00012606060606060605,
"loss": 1.2623,
"step": 104
},
{
"epoch": 0.19,
"grad_norm": 0.16779277284606545,
"learning_rate": 0.00012727272727272728,
"loss": 1.2415,
"step": 105
},
{
"epoch": 0.19,
"grad_norm": 0.13396891539963085,
"learning_rate": 0.0001284848484848485,
"loss": 1.2313,
"step": 106
},
{
"epoch": 0.19,
"grad_norm": 0.12457104490772812,
"learning_rate": 0.0001296969696969697,
"loss": 1.1758,
"step": 107
},
{
"epoch": 0.2,
"grad_norm": 0.12676816816563452,
"learning_rate": 0.00013090909090909093,
"loss": 1.2478,
"step": 108
},
{
"epoch": 0.2,
"grad_norm": 0.11973639622066906,
"learning_rate": 0.00013212121212121213,
"loss": 1.2335,
"step": 109
},
{
"epoch": 0.2,
"grad_norm": 0.1330159646034068,
"learning_rate": 0.00013333333333333334,
"loss": 1.26,
"step": 110
},
{
"epoch": 0.2,
"grad_norm": 0.1298003025338099,
"learning_rate": 0.00013454545454545455,
"loss": 1.1907,
"step": 111
},
{
"epoch": 0.2,
"grad_norm": 0.1226154813287666,
"learning_rate": 0.00013575757575757578,
"loss": 1.1807,
"step": 112
},
{
"epoch": 0.21,
"grad_norm": 0.12533753244302145,
"learning_rate": 0.00013696969696969696,
"loss": 1.2098,
"step": 113
},
{
"epoch": 0.21,
"grad_norm": 0.12673266503840944,
"learning_rate": 0.0001381818181818182,
"loss": 1.2265,
"step": 114
},
{
"epoch": 0.21,
"grad_norm": 0.1299039569361384,
"learning_rate": 0.0001393939393939394,
"loss": 1.2534,
"step": 115
},
{
"epoch": 0.21,
"grad_norm": 0.13023496663090803,
"learning_rate": 0.0001406060606060606,
"loss": 1.2453,
"step": 116
},
{
"epoch": 0.21,
"grad_norm": 0.12001793500864573,
"learning_rate": 0.00014181818181818184,
"loss": 1.1608,
"step": 117
},
{
"epoch": 0.21,
"grad_norm": 0.14561862193041028,
"learning_rate": 0.00014303030303030304,
"loss": 1.2233,
"step": 118
},
{
"epoch": 0.22,
"grad_norm": 0.12636130876430832,
"learning_rate": 0.00014424242424242425,
"loss": 1.2833,
"step": 119
},
{
"epoch": 0.22,
"grad_norm": 0.189556849271166,
"learning_rate": 0.00014545454545454546,
"loss": 1.3105,
"step": 120
},
{
"epoch": 0.22,
"grad_norm": 0.12409073764495662,
"learning_rate": 0.00014666666666666666,
"loss": 1.1534,
"step": 121
},
{
"epoch": 0.22,
"grad_norm": 0.12149212466969316,
"learning_rate": 0.0001478787878787879,
"loss": 1.3039,
"step": 122
},
{
"epoch": 0.22,
"grad_norm": 0.12147336887953522,
"learning_rate": 0.0001490909090909091,
"loss": 1.326,
"step": 123
},
{
"epoch": 0.23,
"grad_norm": 0.1176585016163167,
"learning_rate": 0.0001503030303030303,
"loss": 1.191,
"step": 124
},
{
"epoch": 0.23,
"grad_norm": 0.2066428974234372,
"learning_rate": 0.00015151515151515152,
"loss": 1.3054,
"step": 125
},
{
"epoch": 0.23,
"grad_norm": 0.29582724255710047,
"learning_rate": 0.00015272727272727275,
"loss": 1.2032,
"step": 126
},
{
"epoch": 0.23,
"grad_norm": 0.13084381204119358,
"learning_rate": 0.00015393939393939393,
"loss": 1.2289,
"step": 127
},
{
"epoch": 0.23,
"grad_norm": 0.1294157600411397,
"learning_rate": 0.00015515151515151516,
"loss": 1.2561,
"step": 128
},
{
"epoch": 0.23,
"grad_norm": 0.14039614543447027,
"learning_rate": 0.00015636363636363637,
"loss": 1.243,
"step": 129
},
{
"epoch": 0.24,
"grad_norm": 0.19939984917282128,
"learning_rate": 0.00015757575757575757,
"loss": 1.1286,
"step": 130
},
{
"epoch": 0.24,
"grad_norm": 0.14402764349968203,
"learning_rate": 0.0001587878787878788,
"loss": 1.1959,
"step": 131
},
{
"epoch": 0.24,
"grad_norm": 0.13970978861500938,
"learning_rate": 0.00016,
"loss": 1.1814,
"step": 132
},
{
"epoch": 0.24,
"grad_norm": 0.14539538472563127,
"learning_rate": 0.00016121212121212122,
"loss": 1.2317,
"step": 133
},
{
"epoch": 0.24,
"grad_norm": 0.13456425455391557,
"learning_rate": 0.00016242424242424243,
"loss": 1.2239,
"step": 134
},
{
"epoch": 0.25,
"grad_norm": 0.1314997837157779,
"learning_rate": 0.00016363636363636366,
"loss": 1.1986,
"step": 135
},
{
"epoch": 0.25,
"grad_norm": 0.14046946525591422,
"learning_rate": 0.00016484848484848487,
"loss": 1.2238,
"step": 136
},
{
"epoch": 0.25,
"grad_norm": 0.6095538041505763,
"learning_rate": 0.00016606060606060607,
"loss": 1.2332,
"step": 137
},
{
"epoch": 0.25,
"grad_norm": 0.17707289712054367,
"learning_rate": 0.00016727272727272728,
"loss": 1.2401,
"step": 138
},
{
"epoch": 0.25,
"grad_norm": 0.19335172179099247,
"learning_rate": 0.00016848484848484848,
"loss": 1.2361,
"step": 139
},
{
"epoch": 0.26,
"grad_norm": 0.13725591818701255,
"learning_rate": 0.00016969696969696972,
"loss": 1.193,
"step": 140
},
{
"epoch": 0.26,
"grad_norm": 0.15535575462507384,
"learning_rate": 0.0001709090909090909,
"loss": 1.2769,
"step": 141
},
{
"epoch": 0.26,
"grad_norm": 0.14909436560898923,
"learning_rate": 0.00017212121212121213,
"loss": 1.2602,
"step": 142
},
{
"epoch": 0.26,
"grad_norm": 0.15054368082407957,
"learning_rate": 0.00017333333333333334,
"loss": 1.2607,
"step": 143
},
{
"epoch": 0.26,
"grad_norm": 0.13386897838741724,
"learning_rate": 0.00017454545454545454,
"loss": 1.168,
"step": 144
},
{
"epoch": 0.26,
"grad_norm": 0.13567889528730145,
"learning_rate": 0.00017575757575757578,
"loss": 1.1984,
"step": 145
},
{
"epoch": 0.27,
"grad_norm": 0.13994382298003089,
"learning_rate": 0.00017696969696969698,
"loss": 1.2795,
"step": 146
},
{
"epoch": 0.27,
"grad_norm": 0.13941573210713187,
"learning_rate": 0.0001781818181818182,
"loss": 1.2303,
"step": 147
},
{
"epoch": 0.27,
"grad_norm": 0.18302605925485763,
"learning_rate": 0.0001793939393939394,
"loss": 1.2696,
"step": 148
},
{
"epoch": 0.27,
"grad_norm": 0.1547402223275396,
"learning_rate": 0.00018060606060606063,
"loss": 1.1276,
"step": 149
},
{
"epoch": 0.27,
"grad_norm": 0.19947594494850646,
"learning_rate": 0.00018181818181818183,
"loss": 1.271,
"step": 150
},
{
"epoch": 0.28,
"grad_norm": 0.1517101450465788,
"learning_rate": 0.00018303030303030304,
"loss": 1.2193,
"step": 151
},
{
"epoch": 0.28,
"grad_norm": 0.19251063116857103,
"learning_rate": 0.00018424242424242427,
"loss": 1.2703,
"step": 152
},
{
"epoch": 0.28,
"grad_norm": 0.16789099560498666,
"learning_rate": 0.00018545454545454545,
"loss": 1.2244,
"step": 153
},
{
"epoch": 0.28,
"grad_norm": 0.14907376557922342,
"learning_rate": 0.0001866666666666667,
"loss": 1.264,
"step": 154
},
{
"epoch": 0.28,
"grad_norm": 0.14276598263036905,
"learning_rate": 0.0001878787878787879,
"loss": 1.2545,
"step": 155
},
{
"epoch": 0.28,
"grad_norm": 0.14526753816999002,
"learning_rate": 0.0001890909090909091,
"loss": 1.2912,
"step": 156
},
{
"epoch": 0.29,
"grad_norm": 0.1627048894660859,
"learning_rate": 0.0001903030303030303,
"loss": 1.2573,
"step": 157
},
{
"epoch": 0.29,
"grad_norm": 0.16405036632332695,
"learning_rate": 0.0001915151515151515,
"loss": 1.2359,
"step": 158
},
{
"epoch": 0.29,
"grad_norm": 0.14533427219788658,
"learning_rate": 0.00019272727272727274,
"loss": 1.1718,
"step": 159
},
{
"epoch": 0.29,
"grad_norm": 0.13802382666732702,
"learning_rate": 0.00019393939393939395,
"loss": 1.2297,
"step": 160
},
{
"epoch": 0.29,
"grad_norm": 0.15620193618511755,
"learning_rate": 0.00019515151515151516,
"loss": 1.2287,
"step": 161
},
{
"epoch": 0.3,
"grad_norm": 0.1401696295700075,
"learning_rate": 0.00019636363636363636,
"loss": 1.2231,
"step": 162
},
{
"epoch": 0.3,
"grad_norm": 0.15816133304035035,
"learning_rate": 0.0001975757575757576,
"loss": 1.2804,
"step": 163
},
{
"epoch": 0.3,
"grad_norm": 0.14626275180535692,
"learning_rate": 0.00019878787878787878,
"loss": 1.2115,
"step": 164
},
{
"epoch": 0.3,
"grad_norm": 0.13100680398305042,
"learning_rate": 0.0002,
"loss": 1.2524,
"step": 165
},
{
"epoch": 0.3,
"grad_norm": 0.14849458896148926,
"learning_rate": 0.00019999977531546566,
"loss": 1.2161,
"step": 166
},
{
"epoch": 0.3,
"grad_norm": 0.13628125499037252,
"learning_rate": 0.0001999991012628722,
"loss": 1.2452,
"step": 167
},
{
"epoch": 0.31,
"grad_norm": 0.18617698759086793,
"learning_rate": 0.00019999797784524866,
"loss": 1.2197,
"step": 168
},
{
"epoch": 0.31,
"grad_norm": 0.14416004826313944,
"learning_rate": 0.00019999640506764336,
"loss": 1.2796,
"step": 169
},
{
"epoch": 0.31,
"grad_norm": 0.13807081386834757,
"learning_rate": 0.0001999943829371238,
"loss": 1.2732,
"step": 170
},
{
"epoch": 0.31,
"grad_norm": 0.16526927436841996,
"learning_rate": 0.0001999919114627769,
"loss": 1.3016,
"step": 171
},
{
"epoch": 0.31,
"grad_norm": 0.14479672734919855,
"learning_rate": 0.0001999889906557086,
"loss": 1.3106,
"step": 172
},
{
"epoch": 0.32,
"grad_norm": 0.13829284006072087,
"learning_rate": 0.00019998562052904418,
"loss": 1.3355,
"step": 173
},
{
"epoch": 0.32,
"grad_norm": 0.13484630104616105,
"learning_rate": 0.0001999818010979279,
"loss": 1.1928,
"step": 174
},
{
"epoch": 0.32,
"grad_norm": 0.14972770674556948,
"learning_rate": 0.00019997753237952317,
"loss": 1.2559,
"step": 175
},
{
"epoch": 0.32,
"grad_norm": 0.13378525020528342,
"learning_rate": 0.00019997281439301218,
"loss": 1.2673,
"step": 176
},
{
"epoch": 0.32,
"grad_norm": 0.13242998699125438,
"learning_rate": 0.00019996764715959618,
"loss": 1.2272,
"step": 177
},
{
"epoch": 0.32,
"grad_norm": 0.12938881004364342,
"learning_rate": 0.00019996203070249516,
"loss": 1.2035,
"step": 178
},
{
"epoch": 0.33,
"grad_norm": 0.13388032350164566,
"learning_rate": 0.00019995596504694763,
"loss": 1.2642,
"step": 179
},
{
"epoch": 0.33,
"grad_norm": 0.13893372222140873,
"learning_rate": 0.00019994945022021082,
"loss": 1.2235,
"step": 180
},
{
"epoch": 0.33,
"grad_norm": 0.14131710715500717,
"learning_rate": 0.00019994248625156038,
"loss": 1.1095,
"step": 181
},
{
"epoch": 0.33,
"grad_norm": 0.13448100369103572,
"learning_rate": 0.0001999350731722902,
"loss": 1.1879,
"step": 182
},
{
"epoch": 0.33,
"grad_norm": 0.13862444003216381,
"learning_rate": 0.00019992721101571236,
"loss": 1.2227,
"step": 183
},
{
"epoch": 0.34,
"grad_norm": 0.13506115547921224,
"learning_rate": 0.00019991889981715698,
"loss": 1.2833,
"step": 184
},
{
"epoch": 0.34,
"grad_norm": 0.13174857502600473,
"learning_rate": 0.00019991013961397197,
"loss": 1.2394,
"step": 185
},
{
"epoch": 0.34,
"grad_norm": 0.1290276308949748,
"learning_rate": 0.00019990093044552304,
"loss": 1.2659,
"step": 186
},
{
"epoch": 0.34,
"grad_norm": 0.1388159912078538,
"learning_rate": 0.0001998912723531933,
"loss": 1.3052,
"step": 187
},
{
"epoch": 0.34,
"grad_norm": 0.1256806205303357,
"learning_rate": 0.00019988116538038325,
"loss": 1.2031,
"step": 188
},
{
"epoch": 0.34,
"grad_norm": 0.13256850855084143,
"learning_rate": 0.00019987060957251047,
"loss": 1.211,
"step": 189
},
{
"epoch": 0.35,
"grad_norm": 0.13197363789890235,
"learning_rate": 0.0001998596049770095,
"loss": 1.2256,
"step": 190
},
{
"epoch": 0.35,
"grad_norm": 0.13277364593883098,
"learning_rate": 0.00019984815164333163,
"loss": 1.2174,
"step": 191
},
{
"epoch": 0.35,
"grad_norm": 0.13838072824574454,
"learning_rate": 0.00019983624962294458,
"loss": 1.3128,
"step": 192
},
{
"epoch": 0.35,
"grad_norm": 0.13524759737199996,
"learning_rate": 0.0001998238989693323,
"loss": 1.1806,
"step": 193
},
{
"epoch": 0.35,
"grad_norm": 0.12669987683723832,
"learning_rate": 0.0001998110997379949,
"loss": 1.2171,
"step": 194
},
{
"epoch": 0.36,
"grad_norm": 0.1461834612451898,
"learning_rate": 0.00019979785198644806,
"loss": 1.2231,
"step": 195
},
{
"epoch": 0.36,
"grad_norm": 0.13265793664862735,
"learning_rate": 0.0001997841557742232,
"loss": 1.1718,
"step": 196
},
{
"epoch": 0.36,
"grad_norm": 0.12842971557690963,
"learning_rate": 0.00019977001116286674,
"loss": 1.2758,
"step": 197
},
{
"epoch": 0.36,
"grad_norm": 0.12188365921206967,
"learning_rate": 0.00019975541821594026,
"loss": 1.2457,
"step": 198
},
{
"epoch": 0.36,
"grad_norm": 0.12679949330022622,
"learning_rate": 0.00019974037699901993,
"loss": 1.1825,
"step": 199
},
{
"epoch": 0.36,
"grad_norm": 0.12949746150357985,
"learning_rate": 0.00019972488757969635,
"loss": 1.2666,
"step": 200
},
{
"epoch": 0.37,
"grad_norm": 0.1363496149379173,
"learning_rate": 0.00019970895002757413,
"loss": 1.2031,
"step": 201
},
{
"epoch": 0.37,
"grad_norm": 0.14218340110669314,
"learning_rate": 0.0001996925644142717,
"loss": 1.3073,
"step": 202
},
{
"epoch": 0.37,
"grad_norm": 0.14234535389443218,
"learning_rate": 0.00019967573081342103,
"loss": 1.2444,
"step": 203
},
{
"epoch": 0.37,
"grad_norm": 0.12866113026310516,
"learning_rate": 0.000199658449300667,
"loss": 1.2257,
"step": 204
},
{
"epoch": 0.37,
"grad_norm": 0.1324053366295965,
"learning_rate": 0.00019964071995366744,
"loss": 1.2374,
"step": 205
},
{
"epoch": 0.38,
"grad_norm": 0.12906841330218152,
"learning_rate": 0.00019962254285209254,
"loss": 1.2334,
"step": 206
},
{
"epoch": 0.38,
"grad_norm": 0.13620873131846425,
"learning_rate": 0.00019960391807762463,
"loss": 1.242,
"step": 207
},
{
"epoch": 0.38,
"grad_norm": 0.14877366842835116,
"learning_rate": 0.00019958484571395757,
"loss": 1.1772,
"step": 208
},
{
"epoch": 0.38,
"grad_norm": 0.13914108740445985,
"learning_rate": 0.00019956532584679675,
"loss": 1.2734,
"step": 209
},
{
"epoch": 0.38,
"grad_norm": 0.13198394930310692,
"learning_rate": 0.00019954535856385837,
"loss": 1.1728,
"step": 210
},
{
"epoch": 0.38,
"grad_norm": 0.3807736597404611,
"learning_rate": 0.0001995249439548693,
"loss": 1.2089,
"step": 211
},
{
"epoch": 0.39,
"grad_norm": 0.1682550557564819,
"learning_rate": 0.00019950408211156636,
"loss": 1.2423,
"step": 212
},
{
"epoch": 0.39,
"grad_norm": 0.2102196862007261,
"learning_rate": 0.0001994827731276963,
"loss": 1.2096,
"step": 213
},
{
"epoch": 0.39,
"grad_norm": 0.154346739470422,
"learning_rate": 0.00019946101709901514,
"loss": 1.2847,
"step": 214
},
{
"epoch": 0.39,
"grad_norm": 0.16416668358293746,
"learning_rate": 0.0001994388141232876,
"loss": 1.2503,
"step": 215
},
{
"epoch": 0.39,
"grad_norm": 0.13134349458231093,
"learning_rate": 0.0001994161643002871,
"loss": 1.1231,
"step": 216
},
{
"epoch": 0.4,
"grad_norm": 0.15083246389185287,
"learning_rate": 0.00019939306773179497,
"loss": 1.1614,
"step": 217
},
{
"epoch": 0.4,
"grad_norm": 0.1742387260929692,
"learning_rate": 0.00019936952452159995,
"loss": 1.3568,
"step": 218
},
{
"epoch": 0.4,
"grad_norm": 0.18146911432436974,
"learning_rate": 0.00019934553477549794,
"loss": 1.2686,
"step": 219
},
{
"epoch": 0.4,
"grad_norm": 0.1393593447949332,
"learning_rate": 0.00019932109860129154,
"loss": 1.1141,
"step": 220
},
{
"epoch": 0.4,
"grad_norm": 0.14856124153987935,
"learning_rate": 0.00019929621610878927,
"loss": 1.234,
"step": 221
},
{
"epoch": 0.4,
"grad_norm": 0.14820851831477327,
"learning_rate": 0.0001992708874098054,
"loss": 1.2069,
"step": 222
},
{
"epoch": 0.41,
"grad_norm": 0.17893142790958147,
"learning_rate": 0.00019924511261815926,
"loss": 1.1278,
"step": 223
},
{
"epoch": 0.41,
"grad_norm": 0.14573658703265605,
"learning_rate": 0.00019921889184967476,
"loss": 1.2292,
"step": 224
},
{
"epoch": 0.41,
"grad_norm": 0.15282321197574994,
"learning_rate": 0.00019919222522217996,
"loss": 1.2482,
"step": 225
},
{
"epoch": 0.41,
"grad_norm": 0.16342112084119492,
"learning_rate": 0.00019916511285550642,
"loss": 1.2172,
"step": 226
},
{
"epoch": 0.41,
"grad_norm": 0.1475889153814455,
"learning_rate": 0.00019913755487148876,
"loss": 1.1747,
"step": 227
},
{
"epoch": 0.42,
"grad_norm": 0.163738064491857,
"learning_rate": 0.00019910955139396396,
"loss": 1.3007,
"step": 228
},
{
"epoch": 0.42,
"grad_norm": 0.14427856196022704,
"learning_rate": 0.00019908110254877106,
"loss": 1.2464,
"step": 229
},
{
"epoch": 0.42,
"grad_norm": 0.20204742660246344,
"learning_rate": 0.00019905220846375032,
"loss": 1.2515,
"step": 230
},
{
"epoch": 0.42,
"grad_norm": 0.15134144918251685,
"learning_rate": 0.0001990228692687429,
"loss": 1.1786,
"step": 231
},
{
"epoch": 0.42,
"grad_norm": 0.1636590177812163,
"learning_rate": 0.00019899308509558998,
"loss": 1.1974,
"step": 232
},
{
"epoch": 0.42,
"grad_norm": 0.15552319776955892,
"learning_rate": 0.00019896285607813244,
"loss": 1.2308,
"step": 233
},
{
"epoch": 0.43,
"grad_norm": 0.17104898009833774,
"learning_rate": 0.00019893218235221015,
"loss": 1.2828,
"step": 234
},
{
"epoch": 0.43,
"grad_norm": 0.16387378763964267,
"learning_rate": 0.00019890106405566138,
"loss": 1.2779,
"step": 235
},
{
"epoch": 0.43,
"grad_norm": 0.14622126798612248,
"learning_rate": 0.00019886950132832207,
"loss": 1.2894,
"step": 236
},
{
"epoch": 0.43,
"grad_norm": 0.16619841547518147,
"learning_rate": 0.0001988374943120254,
"loss": 1.2133,
"step": 237
},
{
"epoch": 0.43,
"grad_norm": 0.12664832399697545,
"learning_rate": 0.00019880504315060096,
"loss": 1.1807,
"step": 238
},
{
"epoch": 0.44,
"grad_norm": 0.2015108381613456,
"learning_rate": 0.00019877214798987426,
"loss": 1.1876,
"step": 239
},
{
"epoch": 0.44,
"grad_norm": 0.14468620723711506,
"learning_rate": 0.00019873880897766598,
"loss": 1.1883,
"step": 240
},
{
"epoch": 0.44,
"grad_norm": 0.1549018650770757,
"learning_rate": 0.00019870502626379127,
"loss": 1.2896,
"step": 241
},
{
"epoch": 0.44,
"grad_norm": 0.1492917963684983,
"learning_rate": 0.0001986708000000593,
"loss": 1.2102,
"step": 242
},
{
"epoch": 0.44,
"grad_norm": 0.178606606459489,
"learning_rate": 0.00019863613034027224,
"loss": 1.2292,
"step": 243
},
{
"epoch": 0.44,
"grad_norm": 0.206170239681528,
"learning_rate": 0.00019860101744022485,
"loss": 1.2666,
"step": 244
},
{
"epoch": 0.45,
"grad_norm": 0.13741043007948167,
"learning_rate": 0.0001985654614577036,
"loss": 1.2022,
"step": 245
},
{
"epoch": 0.45,
"grad_norm": 0.1595080658199459,
"learning_rate": 0.0001985294625524861,
"loss": 1.1203,
"step": 246
},
{
"epoch": 0.45,
"grad_norm": 0.13929705183853777,
"learning_rate": 0.00019849302088634034,
"loss": 1.1505,
"step": 247
},
{
"epoch": 0.45,
"grad_norm": 0.14045247607912964,
"learning_rate": 0.00019845613662302383,
"loss": 1.1897,
"step": 248
},
{
"epoch": 0.45,
"grad_norm": 0.15002651347444407,
"learning_rate": 0.00019841880992828306,
"loss": 1.2133,
"step": 249
},
{
"epoch": 0.46,
"grad_norm": 0.1567929487810952,
"learning_rate": 0.00019838104096985267,
"loss": 1.129,
"step": 250
},
{
"epoch": 0.46,
"grad_norm": 0.15240634543877116,
"learning_rate": 0.00019834282991745464,
"loss": 1.1995,
"step": 251
},
{
"epoch": 0.46,
"grad_norm": 0.151807679821367,
"learning_rate": 0.00019830417694279766,
"loss": 1.25,
"step": 252
},
{
"epoch": 0.46,
"grad_norm": 0.1648599156208311,
"learning_rate": 0.0001982650822195762,
"loss": 1.2511,
"step": 253
},
{
"epoch": 0.46,
"grad_norm": 0.15363401233808713,
"learning_rate": 0.00019822554592346993,
"loss": 1.1794,
"step": 254
},
{
"epoch": 0.46,
"grad_norm": 0.1569644350778875,
"learning_rate": 0.00019818556823214268,
"loss": 1.2033,
"step": 255
},
{
"epoch": 0.47,
"grad_norm": 0.15996552747294254,
"learning_rate": 0.0001981451493252418,
"loss": 1.2809,
"step": 256
},
{
"epoch": 0.47,
"grad_norm": 0.15863104885072635,
"learning_rate": 0.0001981042893843974,
"loss": 1.1667,
"step": 257
},
{
"epoch": 0.47,
"grad_norm": 0.2887466971861171,
"learning_rate": 0.0001980629885932214,
"loss": 1.1915,
"step": 258
},
{
"epoch": 0.47,
"grad_norm": 0.15233015979193984,
"learning_rate": 0.00019802124713730681,
"loss": 1.1734,
"step": 259
},
{
"epoch": 0.47,
"grad_norm": 0.18207884538436447,
"learning_rate": 0.00019797906520422677,
"loss": 1.2575,
"step": 260
},
{
"epoch": 0.48,
"grad_norm": 0.17323546756038308,
"learning_rate": 0.0001979364429835339,
"loss": 1.1704,
"step": 261
},
{
"epoch": 0.48,
"grad_norm": 0.14592153602263633,
"learning_rate": 0.00019789338066675922,
"loss": 1.192,
"step": 262
},
{
"epoch": 0.48,
"grad_norm": 0.19250697792287097,
"learning_rate": 0.0001978498784474115,
"loss": 1.2779,
"step": 263
},
{
"epoch": 0.48,
"grad_norm": 0.1429107680887097,
"learning_rate": 0.0001978059365209762,
"loss": 1.2529,
"step": 264
},
{
"epoch": 0.48,
"grad_norm": 0.48514081074992116,
"learning_rate": 0.00019776155508491482,
"loss": 1.1917,
"step": 265
},
{
"epoch": 0.48,
"grad_norm": 0.1534376167748161,
"learning_rate": 0.0001977167343386638,
"loss": 1.2384,
"step": 266
},
{
"epoch": 0.49,
"grad_norm": 0.16744875760032166,
"learning_rate": 0.00019767147448363366,
"loss": 1.1744,
"step": 267
},
{
"epoch": 0.49,
"grad_norm": 0.29195538170738244,
"learning_rate": 0.00019762577572320824,
"loss": 1.1418,
"step": 268
},
{
"epoch": 0.49,
"grad_norm": 0.1820804717651353,
"learning_rate": 0.00019757963826274357,
"loss": 1.2815,
"step": 269
},
{
"epoch": 0.49,
"grad_norm": 0.17522345110441973,
"learning_rate": 0.00019753306230956718,
"loss": 1.2363,
"step": 270
},
{
"epoch": 0.49,
"grad_norm": 0.16354388270886613,
"learning_rate": 0.000197486048072977,
"loss": 1.2845,
"step": 271
},
{
"epoch": 0.5,
"grad_norm": 0.17590082756401024,
"learning_rate": 0.0001974385957642404,
"loss": 1.192,
"step": 272
},
{
"epoch": 0.5,
"grad_norm": 0.17345720403188775,
"learning_rate": 0.00019739070559659347,
"loss": 1.2068,
"step": 273
},
{
"epoch": 0.5,
"grad_norm": 0.16070434867766506,
"learning_rate": 0.00019734237778523976,
"loss": 1.189,
"step": 274
},
{
"epoch": 0.5,
"grad_norm": 0.18983443066710415,
"learning_rate": 0.0001972936125473495,
"loss": 1.2223,
"step": 275
},
{
"epoch": 0.5,
"grad_norm": 0.15724400187981355,
"learning_rate": 0.00019724441010205863,
"loss": 1.2292,
"step": 276
},
{
"epoch": 0.5,
"grad_norm": 0.14570729442956004,
"learning_rate": 0.00019719477067046766,
"loss": 1.1421,
"step": 277
},
{
"epoch": 0.51,
"grad_norm": 0.1559242881177266,
"learning_rate": 0.00019714469447564088,
"loss": 1.2598,
"step": 278
},
{
"epoch": 0.51,
"grad_norm": 0.16621830243096108,
"learning_rate": 0.0001970941817426052,
"loss": 1.3038,
"step": 279
},
{
"epoch": 0.51,
"grad_norm": 4.675483994100576,
"learning_rate": 0.00019704323269834927,
"loss": 1.2298,
"step": 280
},
{
"epoch": 0.51,
"grad_norm": 0.2769699381619058,
"learning_rate": 0.00019699184757182225,
"loss": 1.2566,
"step": 281
},
{
"epoch": 0.51,
"grad_norm": 0.20189839889100783,
"learning_rate": 0.00019694002659393305,
"loss": 1.3181,
"step": 282
},
{
"epoch": 0.52,
"grad_norm": 0.19497107359413876,
"learning_rate": 0.00019688776999754912,
"loss": 1.1502,
"step": 283
},
{
"epoch": 0.52,
"grad_norm": 0.1982266815755412,
"learning_rate": 0.00019683507801749545,
"loss": 1.2053,
"step": 284
},
{
"epoch": 0.52,
"grad_norm": 0.1924340950322314,
"learning_rate": 0.00019678195089055346,
"loss": 1.2149,
"step": 285
},
{
"epoch": 0.52,
"grad_norm": 0.1725322346446431,
"learning_rate": 0.00019672838885546008,
"loss": 1.2553,
"step": 286
},
{
"epoch": 0.52,
"grad_norm": 0.2535488743520272,
"learning_rate": 0.00019667439215290648,
"loss": 1.2576,
"step": 287
},
{
"epoch": 0.52,
"grad_norm": 0.37837586860064026,
"learning_rate": 0.00019661996102553718,
"loss": 1.1815,
"step": 288
},
{
"epoch": 0.53,
"grad_norm": 0.17520419597901843,
"learning_rate": 0.00019656509571794878,
"loss": 1.1932,
"step": 289
},
{
"epoch": 0.53,
"grad_norm": 0.17056234784450633,
"learning_rate": 0.00019650979647668906,
"loss": 1.163,
"step": 290
},
{
"epoch": 0.53,
"grad_norm": 0.18272246580207432,
"learning_rate": 0.00019645406355025565,
"loss": 1.1887,
"step": 291
},
{
"epoch": 0.53,
"grad_norm": 0.17889037954429915,
"learning_rate": 0.00019639789718909508,
"loss": 1.2126,
"step": 292
},
{
"epoch": 0.53,
"grad_norm": 0.23993734971101424,
"learning_rate": 0.00019634129764560168,
"loss": 1.2485,
"step": 293
},
{
"epoch": 0.54,
"grad_norm": 0.1847578318208199,
"learning_rate": 0.00019628426517411625,
"loss": 1.2549,
"step": 294
},
{
"epoch": 0.54,
"grad_norm": 0.23185098827091005,
"learning_rate": 0.00019622680003092503,
"loss": 1.1599,
"step": 295
},
{
"epoch": 0.54,
"grad_norm": 0.220638044092583,
"learning_rate": 0.00019616890247425866,
"loss": 1.2281,
"step": 296
},
{
"epoch": 0.54,
"grad_norm": 0.2303439219825616,
"learning_rate": 0.00019611057276429085,
"loss": 1.2208,
"step": 297
},
{
"epoch": 0.54,
"grad_norm": 0.1744807302230573,
"learning_rate": 0.00019605181116313724,
"loss": 1.2303,
"step": 298
},
{
"epoch": 0.54,
"grad_norm": 0.17510946821872422,
"learning_rate": 0.0001959926179348543,
"loss": 1.2385,
"step": 299
},
{
"epoch": 0.55,
"grad_norm": 0.2218474349751746,
"learning_rate": 0.00019593299334543808,
"loss": 1.2153,
"step": 300
},
{
"epoch": 0.55,
"grad_norm": 0.1742070481516402,
"learning_rate": 0.00019587293766282308,
"loss": 1.1628,
"step": 301
},
{
"epoch": 0.55,
"grad_norm": 0.15250311715180823,
"learning_rate": 0.00019581245115688094,
"loss": 1.1632,
"step": 302
},
{
"epoch": 0.55,
"grad_norm": 0.1744397677094501,
"learning_rate": 0.0001957515340994193,
"loss": 1.254,
"step": 303
},
{
"epoch": 0.55,
"grad_norm": 0.1686772182789891,
"learning_rate": 0.00019569018676418053,
"loss": 1.2169,
"step": 304
},
{
"epoch": 0.56,
"grad_norm": 0.16404966161017623,
"learning_rate": 0.00019562840942684067,
"loss": 1.2221,
"step": 305
},
{
"epoch": 0.56,
"grad_norm": 0.16052011449463713,
"learning_rate": 0.00019556620236500793,
"loss": 1.2045,
"step": 306
},
{
"epoch": 0.56,
"grad_norm": 0.16343251390831215,
"learning_rate": 0.0001955035658582216,
"loss": 1.2289,
"step": 307
},
{
"epoch": 0.56,
"grad_norm": 0.14387162360389305,
"learning_rate": 0.00019544050018795075,
"loss": 1.1365,
"step": 308
},
{
"epoch": 0.56,
"grad_norm": 0.15304461439740238,
"learning_rate": 0.00019537700563759304,
"loss": 1.1931,
"step": 309
},
{
"epoch": 0.56,
"grad_norm": 0.17059958050065627,
"learning_rate": 0.00019531308249247327,
"loss": 1.2166,
"step": 310
},
{
"epoch": 0.57,
"grad_norm": 0.17633385530926995,
"learning_rate": 0.00019524873103984235,
"loss": 1.2604,
"step": 311
},
{
"epoch": 0.57,
"grad_norm": 0.17855814403303746,
"learning_rate": 0.00019518395156887576,
"loss": 1.1615,
"step": 312
},
{
"epoch": 0.57,
"grad_norm": 0.19823982444256988,
"learning_rate": 0.00019511874437067243,
"loss": 1.2153,
"step": 313
},
{
"epoch": 0.57,
"grad_norm": 0.1570784627362585,
"learning_rate": 0.0001950531097382533,
"loss": 1.2788,
"step": 314
},
{
"epoch": 0.57,
"grad_norm": 0.2183125402112695,
"learning_rate": 0.00019498704796656018,
"loss": 1.2966,
"step": 315
},
{
"epoch": 0.58,
"grad_norm": 0.18173933276147194,
"learning_rate": 0.00019492055935245418,
"loss": 1.2978,
"step": 316
},
{
"epoch": 0.58,
"grad_norm": 0.17483116680914407,
"learning_rate": 0.00019485364419471454,
"loss": 1.258,
"step": 317
},
{
"epoch": 0.58,
"grad_norm": 0.15490767356815494,
"learning_rate": 0.0001947863027940374,
"loss": 1.2088,
"step": 318
},
{
"epoch": 0.58,
"grad_norm": 0.14703966491934156,
"learning_rate": 0.00019471853545303405,
"loss": 1.2355,
"step": 319
},
{
"epoch": 0.58,
"grad_norm": 0.14386689086661608,
"learning_rate": 0.00019465034247623003,
"loss": 1.2583,
"step": 320
},
{
"epoch": 0.58,
"grad_norm": 0.18818904376313625,
"learning_rate": 0.00019458172417006347,
"loss": 1.2181,
"step": 321
},
{
"epoch": 0.59,
"grad_norm": 0.17393313719202513,
"learning_rate": 0.00019451268084288385,
"loss": 1.3453,
"step": 322
},
{
"epoch": 0.59,
"grad_norm": 0.14706823379985753,
"learning_rate": 0.00019444321280495043,
"loss": 1.2234,
"step": 323
},
{
"epoch": 0.59,
"grad_norm": 0.15282014755252687,
"learning_rate": 0.00019437332036843118,
"loss": 1.1262,
"step": 324
},
{
"epoch": 0.59,
"grad_norm": 0.1618727884326225,
"learning_rate": 0.00019430300384740105,
"loss": 1.3136,
"step": 325
},
{
"epoch": 0.59,
"grad_norm": 0.16090758705378874,
"learning_rate": 0.00019423226355784077,
"loss": 1.2055,
"step": 326
},
{
"epoch": 0.6,
"grad_norm": 0.15241156801091013,
"learning_rate": 0.00019416109981763526,
"loss": 1.2678,
"step": 327
},
{
"epoch": 0.6,
"grad_norm": 0.14216697909809062,
"learning_rate": 0.0001940895129465724,
"loss": 1.2841,
"step": 328
},
{
"epoch": 0.6,
"grad_norm": 0.15790232415414485,
"learning_rate": 0.00019401750326634144,
"loss": 1.3119,
"step": 329
},
{
"epoch": 0.6,
"grad_norm": 0.13322691961062616,
"learning_rate": 0.0001939450711005316,
"loss": 1.1293,
"step": 330
},
{
"epoch": 0.6,
"grad_norm": 0.14075018938835404,
"learning_rate": 0.00019387221677463062,
"loss": 1.2176,
"step": 331
},
{
"epoch": 0.6,
"grad_norm": 0.21565975459393052,
"learning_rate": 0.00019379894061602335,
"loss": 1.1723,
"step": 332
},
{
"epoch": 0.61,
"grad_norm": 0.17967631394222838,
"learning_rate": 0.00019372524295399013,
"loss": 1.239,
"step": 333
},
{
"epoch": 0.61,
"grad_norm": 0.21187969201978435,
"learning_rate": 0.0001936511241197055,
"loss": 1.2207,
"step": 334
},
{
"epoch": 0.61,
"grad_norm": 0.16967789022974608,
"learning_rate": 0.00019357658444623654,
"loss": 1.2478,
"step": 335
},
{
"epoch": 0.61,
"grad_norm": 0.14810621660374448,
"learning_rate": 0.0001935016242685415,
"loss": 1.1223,
"step": 336
},
{
"epoch": 0.61,
"grad_norm": 0.1489106421847434,
"learning_rate": 0.00019342624392346824,
"loss": 1.1592,
"step": 337
},
{
"epoch": 0.62,
"grad_norm": 0.17625176068748855,
"learning_rate": 0.0001933504437497527,
"loss": 1.2145,
"step": 338
},
{
"epoch": 0.62,
"grad_norm": 0.17250255512763446,
"learning_rate": 0.00019327422408801744,
"loss": 1.2504,
"step": 339
},
{
"epoch": 0.62,
"grad_norm": 0.16079375745566896,
"learning_rate": 0.00019319758528077,
"loss": 1.1795,
"step": 340
},
{
"epoch": 0.62,
"grad_norm": 0.15454466809245995,
"learning_rate": 0.0001931205276724015,
"loss": 1.2123,
"step": 341
},
{
"epoch": 0.62,
"grad_norm": 0.7021323604447972,
"learning_rate": 0.000193043051609185,
"loss": 1.2239,
"step": 342
},
{
"epoch": 0.62,
"grad_norm": 0.1572764339385847,
"learning_rate": 0.00019296515743927399,
"loss": 1.2516,
"step": 343
},
{
"epoch": 0.63,
"grad_norm": 0.2136637778252246,
"learning_rate": 0.00019288684551270073,
"loss": 1.2321,
"step": 344
},
{
"epoch": 0.63,
"grad_norm": 0.4546540454773654,
"learning_rate": 0.00019280811618137484,
"loss": 1.18,
"step": 345
},
{
"epoch": 0.63,
"grad_norm": 0.9809832576786297,
"learning_rate": 0.00019272896979908154,
"loss": 1.2081,
"step": 346
},
{
"epoch": 0.63,
"grad_norm": 0.5246256133291822,
"learning_rate": 0.00019264940672148018,
"loss": 1.2722,
"step": 347
},
{
"epoch": 0.63,
"grad_norm": 0.24941717134878091,
"learning_rate": 0.00019256942730610268,
"loss": 1.2352,
"step": 348
},
{
"epoch": 0.64,
"grad_norm": 0.3356068462072784,
"learning_rate": 0.00019248903191235176,
"loss": 1.2225,
"step": 349
},
{
"epoch": 0.64,
"grad_norm": 0.19535845221880543,
"learning_rate": 0.00019240822090149944,
"loss": 1.1669,
"step": 350
},
{
"epoch": 0.64,
"grad_norm": 0.22306941566416597,
"learning_rate": 0.00019232699463668542,
"loss": 1.2281,
"step": 351
},
{
"epoch": 0.64,
"grad_norm": 0.2700134013989352,
"learning_rate": 0.00019224535348291542,
"loss": 1.1939,
"step": 352
},
{
"epoch": 0.64,
"grad_norm": 0.24406908935562743,
"learning_rate": 0.00019216329780705953,
"loss": 1.1839,
"step": 353
},
{
"epoch": 0.64,
"grad_norm": 0.20465183000217488,
"learning_rate": 0.00019208082797785055,
"loss": 1.2277,
"step": 354
},
{
"epoch": 0.65,
"grad_norm": 0.21324820828129784,
"learning_rate": 0.00019199794436588243,
"loss": 1.2072,
"step": 355
},
{
"epoch": 0.65,
"grad_norm": 0.1780562512431263,
"learning_rate": 0.00019191464734360844,
"loss": 1.2082,
"step": 356
},
{
"epoch": 0.65,
"grad_norm": 0.16547971467615655,
"learning_rate": 0.00019183093728533966,
"loss": 1.1978,
"step": 357
},
{
"epoch": 0.65,
"grad_norm": 0.22904664933247196,
"learning_rate": 0.00019174681456724318,
"loss": 1.1562,
"step": 358
},
{
"epoch": 0.65,
"grad_norm": 0.1737397860007602,
"learning_rate": 0.00019166227956734052,
"loss": 1.2383,
"step": 359
},
{
"epoch": 0.66,
"grad_norm": 0.1589465455917568,
"learning_rate": 0.00019157733266550575,
"loss": 1.2158,
"step": 360
},
{
"epoch": 0.66,
"grad_norm": 0.16253126221999709,
"learning_rate": 0.00019149197424346405,
"loss": 1.1952,
"step": 361
},
{
"epoch": 0.66,
"grad_norm": 0.22436676243032663,
"learning_rate": 0.00019140620468478968,
"loss": 1.2315,
"step": 362
},
{
"epoch": 0.66,
"grad_norm": 0.19291682612950423,
"learning_rate": 0.00019132002437490458,
"loss": 1.2283,
"step": 363
},
{
"epoch": 0.66,
"grad_norm": 0.1519191258459668,
"learning_rate": 0.00019123343370107637,
"loss": 1.1151,
"step": 364
},
{
"epoch": 0.66,
"grad_norm": 0.17179909633547025,
"learning_rate": 0.00019114643305241676,
"loss": 1.1576,
"step": 365
},
{
"epoch": 0.67,
"grad_norm": 0.17992599023321432,
"learning_rate": 0.00019105902281987976,
"loss": 1.2592,
"step": 366
},
{
"epoch": 0.67,
"grad_norm": 0.17714099390314453,
"learning_rate": 0.00019097120339625994,
"loss": 1.2578,
"step": 367
},
{
"epoch": 0.67,
"grad_norm": 0.2455577642687935,
"learning_rate": 0.00019088297517619055,
"loss": 1.2361,
"step": 368
},
{
"epoch": 0.67,
"grad_norm": 0.18398518628783986,
"learning_rate": 0.00019079433855614201,
"loss": 1.1906,
"step": 369
},
{
"epoch": 0.67,
"grad_norm": 0.18944067022821645,
"learning_rate": 0.00019070529393441985,
"loss": 1.237,
"step": 370
},
{
"epoch": 0.68,
"grad_norm": 0.17639967519781063,
"learning_rate": 0.00019061584171116303,
"loss": 1.1841,
"step": 371
},
{
"epoch": 0.68,
"grad_norm": 0.15947129998283005,
"learning_rate": 0.00019052598228834217,
"loss": 1.1722,
"step": 372
},
{
"epoch": 0.68,
"grad_norm": 0.1693354353719105,
"learning_rate": 0.00019043571606975777,
"loss": 1.2204,
"step": 373
},
{
"epoch": 0.68,
"grad_norm": 0.16236190451963983,
"learning_rate": 0.00019034504346103823,
"loss": 1.1778,
"step": 374
},
{
"epoch": 0.68,
"grad_norm": 0.17702370729269964,
"learning_rate": 0.00019025396486963827,
"loss": 1.2065,
"step": 375
},
{
"epoch": 0.68,
"grad_norm": 0.19388150596154238,
"learning_rate": 0.00019016248070483687,
"loss": 1.2942,
"step": 376
},
{
"epoch": 0.69,
"grad_norm": 0.16152000400319103,
"learning_rate": 0.0001900705913777356,
"loss": 1.1784,
"step": 377
},
{
"epoch": 0.69,
"grad_norm": 0.1545267913996029,
"learning_rate": 0.00018997829730125663,
"loss": 1.1829,
"step": 378
},
{
"epoch": 0.69,
"grad_norm": 0.15421727704318197,
"learning_rate": 0.000189885598890141,
"loss": 1.177,
"step": 379
},
{
"epoch": 0.69,
"grad_norm": 0.1624966073814206,
"learning_rate": 0.00018979249656094673,
"loss": 1.2439,
"step": 380
},
{
"epoch": 0.69,
"grad_norm": 0.9490737312904575,
"learning_rate": 0.00018969899073204686,
"loss": 1.2085,
"step": 381
},
{
"epoch": 0.7,
"grad_norm": 0.8982903208613089,
"learning_rate": 0.00018960508182362768,
"loss": 1.2347,
"step": 382
},
{
"epoch": 0.7,
"grad_norm": 0.3771428474797688,
"learning_rate": 0.00018951077025768678,
"loss": 1.2546,
"step": 383
},
{
"epoch": 0.7,
"grad_norm": 0.4776152950069111,
"learning_rate": 0.00018941605645803115,
"loss": 1.2904,
"step": 384
},
{
"epoch": 0.7,
"grad_norm": 0.18786943849618057,
"learning_rate": 0.00018932094085027533,
"loss": 1.2122,
"step": 385
},
{
"epoch": 0.7,
"grad_norm": 1.6297025984167128,
"learning_rate": 0.0001892254238618394,
"loss": 1.171,
"step": 386
},
{
"epoch": 0.7,
"grad_norm": 0.20382660707264952,
"learning_rate": 0.0001891295059219472,
"loss": 1.1874,
"step": 387
},
{
"epoch": 0.71,
"grad_norm": 1.3580819775908755,
"learning_rate": 0.00018903318746162429,
"loss": 1.1531,
"step": 388
},
{
"epoch": 0.71,
"grad_norm": 0.43619056173016185,
"learning_rate": 0.00018893646891369602,
"loss": 1.2289,
"step": 389
},
{
"epoch": 0.71,
"grad_norm": 0.29385240705823723,
"learning_rate": 0.0001888393507127856,
"loss": 1.2073,
"step": 390
},
{
"epoch": 0.71,
"grad_norm": 0.3136086850525623,
"learning_rate": 0.00018874183329531223,
"loss": 1.1898,
"step": 391
},
{
"epoch": 0.71,
"grad_norm": 0.2307767217662562,
"learning_rate": 0.000188643917099489,
"loss": 1.207,
"step": 392
},
{
"epoch": 0.72,
"grad_norm": 0.18703654518135468,
"learning_rate": 0.000188545602565321,
"loss": 1.1688,
"step": 393
},
{
"epoch": 0.72,
"grad_norm": 0.4809351333934126,
"learning_rate": 0.00018844689013460336,
"loss": 1.2519,
"step": 394
},
{
"epoch": 0.72,
"grad_norm": 0.40370101428544464,
"learning_rate": 0.0001883477802509192,
"loss": 1.2411,
"step": 395
},
{
"epoch": 0.72,
"grad_norm": 0.2858848636432859,
"learning_rate": 0.00018824827335963765,
"loss": 1.194,
"step": 396
},
{
"epoch": 0.72,
"grad_norm": 0.32195602638999565,
"learning_rate": 0.000188148369907912,
"loss": 1.0988,
"step": 397
},
{
"epoch": 0.72,
"grad_norm": 0.23790306908901832,
"learning_rate": 0.00018804807034467733,
"loss": 1.2237,
"step": 398
},
{
"epoch": 0.73,
"grad_norm": 0.20126988767112128,
"learning_rate": 0.0001879473751206489,
"loss": 1.2731,
"step": 399
},
{
"epoch": 0.73,
"grad_norm": 0.3336380339194037,
"learning_rate": 0.00018784628468831996,
"loss": 1.2369,
"step": 400
},
{
"epoch": 0.73,
"grad_norm": 0.5054330893305989,
"learning_rate": 0.0001877447995019596,
"loss": 1.2443,
"step": 401
},
{
"epoch": 0.73,
"grad_norm": 0.2297866279715136,
"learning_rate": 0.0001876429200176108,
"loss": 1.2376,
"step": 402
},
{
"epoch": 0.73,
"grad_norm": 0.39350567174184636,
"learning_rate": 0.00018754064669308858,
"loss": 1.2126,
"step": 403
},
{
"epoch": 0.74,
"grad_norm": 0.2025361091435325,
"learning_rate": 0.00018743797998797753,
"loss": 1.2224,
"step": 404
},
{
"epoch": 0.74,
"grad_norm": 0.31824903419753814,
"learning_rate": 0.00018733492036363005,
"loss": 1.2942,
"step": 405
},
{
"epoch": 0.74,
"grad_norm": 2.4642066748643017,
"learning_rate": 0.00018723146828316428,
"loss": 1.2515,
"step": 406
},
{
"epoch": 0.74,
"grad_norm": 0.7833055646295342,
"learning_rate": 0.00018712762421146183,
"loss": 1.2207,
"step": 407
},
{
"epoch": 0.74,
"grad_norm": 0.2810249021786599,
"learning_rate": 0.00018702338861516587,
"loss": 1.2755,
"step": 408
},
{
"epoch": 0.74,
"grad_norm": 0.460995724241333,
"learning_rate": 0.0001869187619626789,
"loss": 1.2856,
"step": 409
},
{
"epoch": 0.75,
"grad_norm": 0.49139203044984286,
"learning_rate": 0.00018681374472416073,
"loss": 1.2392,
"step": 410
},
{
"epoch": 0.75,
"grad_norm": 2.691604613969173,
"learning_rate": 0.0001867083373715264,
"loss": 1.2992,
"step": 411
},
{
"epoch": 0.75,
"grad_norm": 0.8014112047318501,
"learning_rate": 0.00018660254037844388,
"loss": 1.2683,
"step": 412
},
{
"epoch": 0.75,
"grad_norm": 0.31614342841331383,
"learning_rate": 0.00018649635422033215,
"loss": 1.2356,
"step": 413
},
{
"epoch": 0.75,
"grad_norm": 0.2559855196513244,
"learning_rate": 0.000186389779374359,
"loss": 1.2053,
"step": 414
},
{
"epoch": 0.76,
"grad_norm": 1.6613999986014714,
"learning_rate": 0.0001862828163194388,
"loss": 1.2568,
"step": 415
},
{
"epoch": 0.76,
"grad_norm": 0.27190082167109786,
"learning_rate": 0.0001861754655362304,
"loss": 1.1288,
"step": 416
},
{
"epoch": 0.76,
"grad_norm": 0.43819582203066043,
"learning_rate": 0.00018606772750713504,
"loss": 1.1758,
"step": 417
},
{
"epoch": 0.76,
"grad_norm": 0.41738497400383384,
"learning_rate": 0.0001859596027162941,
"loss": 1.2993,
"step": 418
},
{
"epoch": 0.76,
"grad_norm": 0.2595142634740817,
"learning_rate": 0.000185851091649587,
"loss": 1.269,
"step": 419
},
{
"epoch": 0.77,
"grad_norm": 0.2795314201020271,
"learning_rate": 0.00018574219479462878,
"loss": 1.1915,
"step": 420
},
{
"epoch": 0.77,
"grad_norm": 0.2502992494749938,
"learning_rate": 0.00018563291264076835,
"loss": 1.2157,
"step": 421
},
{
"epoch": 0.77,
"grad_norm": 0.27422512335538374,
"learning_rate": 0.00018552324567908585,
"loss": 1.2541,
"step": 422
},
{
"epoch": 0.77,
"grad_norm": 1.3360989016060905,
"learning_rate": 0.00018541319440239066,
"loss": 1.2666,
"step": 423
},
{
"epoch": 0.77,
"grad_norm": 1.9441131913572127,
"learning_rate": 0.00018530275930521924,
"loss": 1.2924,
"step": 424
},
{
"epoch": 0.77,
"grad_norm": 0.3772373301771213,
"learning_rate": 0.00018519194088383273,
"loss": 1.1952,
"step": 425
},
{
"epoch": 0.78,
"grad_norm": 0.22091753616251295,
"learning_rate": 0.0001850807396362148,
"loss": 1.1858,
"step": 426
},
{
"epoch": 0.78,
"grad_norm": 0.21423504993321807,
"learning_rate": 0.00018496915606206951,
"loss": 1.2245,
"step": 427
},
{
"epoch": 0.78,
"grad_norm": 0.5238946238105926,
"learning_rate": 0.00018485719066281892,
"loss": 1.2351,
"step": 428
},
{
"epoch": 0.78,
"grad_norm": 0.3037858949309141,
"learning_rate": 0.0001847448439416009,
"loss": 1.1669,
"step": 429
},
{
"epoch": 0.78,
"grad_norm": 0.21553286799952254,
"learning_rate": 0.00018463211640326686,
"loss": 1.1454,
"step": 430
},
{
"epoch": 0.79,
"grad_norm": 0.202875547805464,
"learning_rate": 0.0001845190085543795,
"loss": 1.188,
"step": 431
},
{
"epoch": 0.79,
"grad_norm": 0.24385408620619278,
"learning_rate": 0.00018440552090321047,
"loss": 1.2307,
"step": 432
},
{
"epoch": 0.79,
"grad_norm": 0.23793944272430378,
"learning_rate": 0.0001842916539597382,
"loss": 1.2253,
"step": 433
},
{
"epoch": 0.79,
"grad_norm": 0.17062488448810784,
"learning_rate": 0.0001841774082356455,
"loss": 1.2681,
"step": 434
},
{
"epoch": 0.79,
"grad_norm": 0.20003742001916064,
"learning_rate": 0.00018406278424431736,
"loss": 1.2428,
"step": 435
},
{
"epoch": 0.79,
"grad_norm": 0.2696052831337752,
"learning_rate": 0.0001839477825008385,
"loss": 1.2945,
"step": 436
},
{
"epoch": 0.8,
"grad_norm": 0.23302960820538443,
"learning_rate": 0.00018383240352199117,
"loss": 1.1718,
"step": 437
},
{
"epoch": 0.8,
"grad_norm": 0.38187833239777536,
"learning_rate": 0.00018371664782625287,
"loss": 1.2311,
"step": 438
},
{
"epoch": 0.8,
"grad_norm": 0.4052561772533732,
"learning_rate": 0.00018360051593379383,
"loss": 1.1639,
"step": 439
},
{
"epoch": 0.8,
"grad_norm": 0.23379763821020377,
"learning_rate": 0.0001834840083664749,
"loss": 1.1809,
"step": 440
},
{
"epoch": 0.8,
"grad_norm": 0.2368414607613928,
"learning_rate": 0.00018336712564784503,
"loss": 1.2357,
"step": 441
},
{
"epoch": 0.81,
"grad_norm": 0.20230633988510938,
"learning_rate": 0.000183249868303139,
"loss": 1.1851,
"step": 442
},
{
"epoch": 0.81,
"grad_norm": 0.170513157244292,
"learning_rate": 0.00018313223685927505,
"loss": 1.205,
"step": 443
},
{
"epoch": 0.81,
"grad_norm": 0.18082295035256266,
"learning_rate": 0.0001830142318448525,
"loss": 1.2305,
"step": 444
},
{
"epoch": 0.81,
"grad_norm": 0.18286299264146286,
"learning_rate": 0.00018289585379014942,
"loss": 1.23,
"step": 445
},
{
"epoch": 0.81,
"grad_norm": 0.17868104103482751,
"learning_rate": 0.00018277710322712012,
"loss": 1.2894,
"step": 446
},
{
"epoch": 0.81,
"grad_norm": 0.1820411127336495,
"learning_rate": 0.00018265798068939294,
"loss": 1.2395,
"step": 447
},
{
"epoch": 0.82,
"grad_norm": 0.1738237541783663,
"learning_rate": 0.0001825384867122677,
"loss": 1.1576,
"step": 448
},
{
"epoch": 0.82,
"grad_norm": 0.15693445967795147,
"learning_rate": 0.0001824186218327134,
"loss": 1.0809,
"step": 449
},
{
"epoch": 0.82,
"grad_norm": 0.18509145652208978,
"learning_rate": 0.00018229838658936564,
"loss": 1.2717,
"step": 450
},
{
"epoch": 0.82,
"grad_norm": 0.14702488366564262,
"learning_rate": 0.0001821777815225245,
"loss": 1.2236,
"step": 451
},
{
"epoch": 0.82,
"grad_norm": 0.1828399354418095,
"learning_rate": 0.00018205680717415187,
"loss": 1.2565,
"step": 452
},
{
"epoch": 0.83,
"grad_norm": 0.17460984182013486,
"learning_rate": 0.00018193546408786898,
"loss": 1.2474,
"step": 453
},
{
"epoch": 0.83,
"grad_norm": 0.2001623109673152,
"learning_rate": 0.00018181375280895416,
"loss": 1.2544,
"step": 454
},
{
"epoch": 0.83,
"grad_norm": 0.17228631742863837,
"learning_rate": 0.00018169167388434025,
"loss": 1.1851,
"step": 455
},
{
"epoch": 0.83,
"grad_norm": 0.1644862232819482,
"learning_rate": 0.00018156922786261216,
"loss": 1.1817,
"step": 456
},
{
"epoch": 0.83,
"grad_norm": 0.19775186397477057,
"learning_rate": 0.00018144641529400446,
"loss": 1.257,
"step": 457
},
{
"epoch": 0.83,
"grad_norm": 0.1626281991220394,
"learning_rate": 0.00018132323673039885,
"loss": 1.2277,
"step": 458
},
{
"epoch": 0.84,
"grad_norm": 0.16158256707311264,
"learning_rate": 0.00018119969272532166,
"loss": 1.1624,
"step": 459
},
{
"epoch": 0.84,
"grad_norm": 0.17705809207051687,
"learning_rate": 0.00018107578383394146,
"loss": 1.2421,
"step": 460
},
{
"epoch": 0.84,
"grad_norm": 0.17639060401882287,
"learning_rate": 0.00018095151061306645,
"loss": 1.285,
"step": 461
},
{
"epoch": 0.84,
"grad_norm": 0.16918796486576196,
"learning_rate": 0.00018082687362114212,
"loss": 1.2606,
"step": 462
},
{
"epoch": 0.84,
"grad_norm": 0.15968377185965665,
"learning_rate": 0.0001807018734182485,
"loss": 1.194,
"step": 463
},
{
"epoch": 0.85,
"grad_norm": 0.17537027967397978,
"learning_rate": 0.00018057651056609784,
"loss": 1.1594,
"step": 464
},
{
"epoch": 0.85,
"grad_norm": 0.15753665403127565,
"learning_rate": 0.00018045078562803203,
"loss": 1.1382,
"step": 465
},
{
"epoch": 0.85,
"grad_norm": 0.17121200763916436,
"learning_rate": 0.00018032469916902003,
"loss": 1.2286,
"step": 466
},
{
"epoch": 0.85,
"grad_norm": 0.19120510133331003,
"learning_rate": 0.00018019825175565542,
"loss": 1.2835,
"step": 467
},
{
"epoch": 0.85,
"grad_norm": 0.1671735980123817,
"learning_rate": 0.0001800714439561538,
"loss": 1.2201,
"step": 468
},
{
"epoch": 0.85,
"grad_norm": 0.1579098534969056,
"learning_rate": 0.00017994427634035015,
"loss": 1.2156,
"step": 469
},
{
"epoch": 0.86,
"grad_norm": 0.1746075421158512,
"learning_rate": 0.00017981674947969636,
"loss": 1.2049,
"step": 470
},
{
"epoch": 0.86,
"grad_norm": 0.16878182886737042,
"learning_rate": 0.00017968886394725874,
"loss": 1.2204,
"step": 471
},
{
"epoch": 0.86,
"grad_norm": 0.16725956538286493,
"learning_rate": 0.00017956062031771535,
"loss": 1.2091,
"step": 472
},
{
"epoch": 0.86,
"grad_norm": 0.18877845951705005,
"learning_rate": 0.00017943201916735335,
"loss": 1.241,
"step": 473
},
{
"epoch": 0.86,
"grad_norm": 0.180337447476004,
"learning_rate": 0.00017930306107406653,
"loss": 1.2253,
"step": 474
},
{
"epoch": 0.87,
"grad_norm": 0.16688572366717752,
"learning_rate": 0.0001791737466173527,
"loss": 1.239,
"step": 475
},
{
"epoch": 0.87,
"grad_norm": 0.15385917621135983,
"learning_rate": 0.00017904407637831099,
"loss": 1.2476,
"step": 476
},
{
"epoch": 0.87,
"grad_norm": 0.17725645269055587,
"learning_rate": 0.00017891405093963938,
"loss": 1.2599,
"step": 477
},
{
"epoch": 0.87,
"grad_norm": 0.14758551718901028,
"learning_rate": 0.00017878367088563195,
"loss": 1.2249,
"step": 478
},
{
"epoch": 0.87,
"grad_norm": 0.15216962408661316,
"learning_rate": 0.00017865293680217637,
"loss": 1.2346,
"step": 479
},
{
"epoch": 0.87,
"grad_norm": 0.16679282848599514,
"learning_rate": 0.00017852184927675112,
"loss": 1.2443,
"step": 480
},
{
"epoch": 0.88,
"grad_norm": 0.16723562739069214,
"learning_rate": 0.00017839040889842305,
"loss": 1.224,
"step": 481
},
{
"epoch": 0.88,
"grad_norm": 0.15922276239929914,
"learning_rate": 0.00017825861625784455,
"loss": 1.2739,
"step": 482
},
{
"epoch": 0.88,
"grad_norm": 0.1510107938469514,
"learning_rate": 0.00017812647194725094,
"loss": 1.1764,
"step": 483
},
{
"epoch": 0.88,
"grad_norm": 0.16446999054333494,
"learning_rate": 0.00017799397656045792,
"loss": 1.2498,
"step": 484
},
{
"epoch": 0.88,
"grad_norm": 0.18566301651865832,
"learning_rate": 0.00017786113069285874,
"loss": 1.232,
"step": 485
},
{
"epoch": 0.89,
"grad_norm": 0.20592971655306183,
"learning_rate": 0.00017772793494142167,
"loss": 1.1586,
"step": 486
},
{
"epoch": 0.89,
"grad_norm": 0.1581947714375729,
"learning_rate": 0.00017759438990468725,
"loss": 1.2502,
"step": 487
},
{
"epoch": 0.89,
"grad_norm": 0.15466760695169174,
"learning_rate": 0.00017746049618276545,
"loss": 1.1605,
"step": 488
},
{
"epoch": 0.89,
"grad_norm": 0.16041506222444918,
"learning_rate": 0.00017732625437733335,
"loss": 1.2778,
"step": 489
},
{
"epoch": 0.89,
"grad_norm": 0.17168109661676773,
"learning_rate": 0.0001771916650916321,
"loss": 1.262,
"step": 490
},
{
"epoch": 0.89,
"grad_norm": 0.1788973186498254,
"learning_rate": 0.00017705672893046425,
"loss": 1.2111,
"step": 491
},
{
"epoch": 0.9,
"grad_norm": 0.1759644359346382,
"learning_rate": 0.00017692144650019125,
"loss": 1.2546,
"step": 492
},
{
"epoch": 0.9,
"grad_norm": 0.15710749736088767,
"learning_rate": 0.0001767858184087304,
"loss": 1.2487,
"step": 493
},
{
"epoch": 0.9,
"grad_norm": 0.1648235522911144,
"learning_rate": 0.00017664984526555248,
"loss": 1.2469,
"step": 494
},
{
"epoch": 0.9,
"grad_norm": 0.15452607969890703,
"learning_rate": 0.0001765135276816787,
"loss": 1.1855,
"step": 495
},
{
"epoch": 0.9,
"grad_norm": 0.1837695597880219,
"learning_rate": 0.00017637686626967812,
"loss": 1.2185,
"step": 496
},
{
"epoch": 0.91,
"grad_norm": 0.15861390725762364,
"learning_rate": 0.00017623986164366486,
"loss": 1.2056,
"step": 497
},
{
"epoch": 0.91,
"grad_norm": 0.1663260460966887,
"learning_rate": 0.00017610251441929533,
"loss": 1.1242,
"step": 498
},
{
"epoch": 0.91,
"grad_norm": 0.1803309720529981,
"learning_rate": 0.00017596482521376546,
"loss": 1.2938,
"step": 499
},
{
"epoch": 0.91,
"grad_norm": 0.14909085011764342,
"learning_rate": 0.00017582679464580797,
"loss": 1.1953,
"step": 500
},
{
"epoch": 0.91,
"grad_norm": 0.15779022242482527,
"learning_rate": 0.00017568842333568952,
"loss": 1.2792,
"step": 501
},
{
"epoch": 0.91,
"grad_norm": 0.1553327313967345,
"learning_rate": 0.00017554971190520798,
"loss": 1.2286,
"step": 502
},
{
"epoch": 0.92,
"grad_norm": 0.16363964666273684,
"learning_rate": 0.00017541066097768963,
"loss": 1.2753,
"step": 503
},
{
"epoch": 0.92,
"grad_norm": 0.16668099163659675,
"learning_rate": 0.00017527127117798635,
"loss": 1.185,
"step": 504
},
{
"epoch": 0.92,
"grad_norm": 0.13957568397594883,
"learning_rate": 0.0001751315431324727,
"loss": 1.143,
"step": 505
},
{
"epoch": 0.92,
"grad_norm": 0.1553111736740035,
"learning_rate": 0.00017499147746904335,
"loss": 1.2492,
"step": 506
},
{
"epoch": 0.92,
"grad_norm": 0.1691517335818193,
"learning_rate": 0.00017485107481711012,
"loss": 1.2619,
"step": 507
},
{
"epoch": 0.93,
"grad_norm": 0.15480883994395986,
"learning_rate": 0.00017471033580759903,
"loss": 1.2396,
"step": 508
},
{
"epoch": 0.93,
"grad_norm": 0.1451690143792058,
"learning_rate": 0.00017456926107294765,
"loss": 1.1732,
"step": 509
},
{
"epoch": 0.93,
"grad_norm": 0.1524398957482947,
"learning_rate": 0.00017442785124710227,
"loss": 1.2083,
"step": 510
},
{
"epoch": 0.93,
"grad_norm": 0.16790264977550012,
"learning_rate": 0.0001742861069655148,
"loss": 1.2201,
"step": 511
},
{
"epoch": 0.93,
"grad_norm": 0.1529847047636337,
"learning_rate": 0.0001741440288651403,
"loss": 1.243,
"step": 512
},
{
"epoch": 0.93,
"grad_norm": 0.1485875402374676,
"learning_rate": 0.00017400161758443375,
"loss": 1.2053,
"step": 513
},
{
"epoch": 0.94,
"grad_norm": 0.16950094279079617,
"learning_rate": 0.00017385887376334742,
"loss": 1.1944,
"step": 514
},
{
"epoch": 0.94,
"grad_norm": 0.15289337084330445,
"learning_rate": 0.00017371579804332789,
"loss": 1.2503,
"step": 515
},
{
"epoch": 0.94,
"grad_norm": 0.15337063655317973,
"learning_rate": 0.00017357239106731317,
"loss": 1.3092,
"step": 516
},
{
"epoch": 0.94,
"grad_norm": 0.1458937961897621,
"learning_rate": 0.00017342865347972988,
"loss": 1.2244,
"step": 517
},
{
"epoch": 0.94,
"grad_norm": 0.19897118610161338,
"learning_rate": 0.00017328458592649027,
"loss": 1.2238,
"step": 518
},
{
"epoch": 0.95,
"grad_norm": 0.15850805264911003,
"learning_rate": 0.00017314018905498931,
"loss": 1.195,
"step": 519
},
{
"epoch": 0.95,
"grad_norm": 0.14445183074519347,
"learning_rate": 0.00017299546351410197,
"loss": 1.1974,
"step": 520
},
{
"epoch": 0.95,
"grad_norm": 0.18180731722745677,
"learning_rate": 0.00017285040995418,
"loss": 1.2107,
"step": 521
},
{
"epoch": 0.95,
"grad_norm": 0.14943874953193587,
"learning_rate": 0.00017270502902704926,
"loss": 1.1843,
"step": 522
},
{
"epoch": 0.95,
"grad_norm": 0.15767466790910512,
"learning_rate": 0.00017255932138600665,
"loss": 1.1409,
"step": 523
},
{
"epoch": 0.95,
"grad_norm": 0.16402921378654775,
"learning_rate": 0.00017241328768581726,
"loss": 1.2135,
"step": 524
},
{
"epoch": 0.96,
"grad_norm": 0.15526246786505485,
"learning_rate": 0.00017226692858271134,
"loss": 1.2255,
"step": 525
},
{
"epoch": 0.96,
"grad_norm": 0.16608155892622348,
"learning_rate": 0.00017212024473438147,
"loss": 1.2691,
"step": 526
},
{
"epoch": 0.96,
"grad_norm": 0.14913271520144072,
"learning_rate": 0.00017197323679997943,
"loss": 1.1574,
"step": 527
},
{
"epoch": 0.96,
"grad_norm": 0.1471910610421707,
"learning_rate": 0.00017182590544011347,
"loss": 1.2774,
"step": 528
},
{
"epoch": 0.96,
"grad_norm": 0.1417464185073962,
"learning_rate": 0.00017167825131684513,
"loss": 1.2446,
"step": 529
},
{
"epoch": 0.97,
"grad_norm": 0.1610488125634495,
"learning_rate": 0.0001715302750936864,
"loss": 1.2862,
"step": 530
},
{
"epoch": 0.97,
"grad_norm": 0.20227974555123074,
"learning_rate": 0.00017138197743559654,
"loss": 1.207,
"step": 531
},
{
"epoch": 0.97,
"grad_norm": 0.1355502559749413,
"learning_rate": 0.00017123335900897946,
"loss": 1.1019,
"step": 532
},
{
"epoch": 0.97,
"grad_norm": 0.1559423167028215,
"learning_rate": 0.00017108442048168038,
"loss": 1.2549,
"step": 533
},
{
"epoch": 0.97,
"grad_norm": 0.15898973818185586,
"learning_rate": 0.00017093516252298296,
"loss": 1.2705,
"step": 534
},
{
"epoch": 0.97,
"grad_norm": 0.15169569998999652,
"learning_rate": 0.00017078558580360632,
"loss": 1.2454,
"step": 535
},
{
"epoch": 0.98,
"grad_norm": 0.15976111665597925,
"learning_rate": 0.00017063569099570196,
"loss": 1.2585,
"step": 536
},
{
"epoch": 0.98,
"grad_norm": 0.14488877221999352,
"learning_rate": 0.00017048547877285077,
"loss": 1.2169,
"step": 537
},
{
"epoch": 0.98,
"grad_norm": 0.14919533098974924,
"learning_rate": 0.00017033494981006002,
"loss": 1.2358,
"step": 538
},
{
"epoch": 0.98,
"grad_norm": 0.15251746717084805,
"learning_rate": 0.00017018410478376032,
"loss": 1.2241,
"step": 539
},
{
"epoch": 0.98,
"grad_norm": 0.1456060482002663,
"learning_rate": 0.00017003294437180255,
"loss": 1.2298,
"step": 540
},
{
"epoch": 0.99,
"grad_norm": 0.17048886778787248,
"learning_rate": 0.00016988146925345484,
"loss": 1.2707,
"step": 541
},
{
"epoch": 0.99,
"grad_norm": 0.15304381059310815,
"learning_rate": 0.00016972968010939954,
"loss": 1.1498,
"step": 542
},
{
"epoch": 0.99,
"grad_norm": 0.16590055969071696,
"learning_rate": 0.0001695775776217301,
"loss": 1.2481,
"step": 543
},
{
"epoch": 0.99,
"grad_norm": 0.14299575837437278,
"learning_rate": 0.00016942516247394807,
"loss": 1.2058,
"step": 544
},
{
"epoch": 0.99,
"grad_norm": 0.14275107775859475,
"learning_rate": 0.00016927243535095997,
"loss": 1.2178,
"step": 545
},
{
"epoch": 0.99,
"grad_norm": 0.1554250137491414,
"learning_rate": 0.0001691193969390742,
"loss": 1.1197,
"step": 546
},
{
"epoch": 1.0,
"grad_norm": 0.16958418467021688,
"learning_rate": 0.0001689660479259981,
"loss": 1.1768,
"step": 547
},
{
"epoch": 1.0,
"grad_norm": 0.1546216583314497,
"learning_rate": 0.00016881238900083473,
"loss": 1.1741,
"step": 548
},
{
"epoch": 1.0,
"grad_norm": 0.15287056494787424,
"learning_rate": 0.0001686584208540797,
"loss": 1.2328,
"step": 549
},
{
"epoch": 1.0,
"grad_norm": 0.1419329373337611,
"learning_rate": 0.0001685041441776183,
"loss": 1.1743,
"step": 550
}
],
"logging_steps": 1.0,
"max_steps": 1647,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50,
"total_flos": 5103643602714624.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}