results / checkpoint-253 /trainer_state.json
sharkMeow's picture
Training in progress, epoch 2, checkpoint
db95750
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0181451612903225,
"eval_steps": 25,
"global_step": 253,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 4.0553,
"step": 1
},
{
"epoch": 0.01,
"eval_loss": 4.052073955535889,
"eval_runtime": 57.3905,
"eval_samples_per_second": 4.356,
"eval_steps_per_second": 4.356,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 2e-05,
"loss": 4.3696,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 4.2401,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 4.3077,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 4.0741,
"step": 5
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 4.1673,
"step": 6
},
{
"epoch": 0.06,
"learning_rate": 0.00012,
"loss": 3.9378,
"step": 7
},
{
"epoch": 0.06,
"learning_rate": 0.00014,
"loss": 4.0167,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 0.00016,
"loss": 3.5818,
"step": 9
},
{
"epoch": 0.08,
"learning_rate": 0.00018,
"loss": 3.9022,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 3.7906,
"step": 11
},
{
"epoch": 0.1,
"learning_rate": 0.0001999979107245606,
"loss": 3.6776,
"step": 12
},
{
"epoch": 0.1,
"learning_rate": 0.00019999164298554375,
"loss": 3.4291,
"step": 13
},
{
"epoch": 0.11,
"learning_rate": 0.00019998119704485014,
"loss": 3.6101,
"step": 14
},
{
"epoch": 0.12,
"learning_rate": 0.00019996657333896877,
"loss": 3.5537,
"step": 15
},
{
"epoch": 0.13,
"learning_rate": 0.00019994777247895855,
"loss": 3.386,
"step": 16
},
{
"epoch": 0.14,
"learning_rate": 0.00019992479525042303,
"loss": 3.6359,
"step": 17
},
{
"epoch": 0.15,
"learning_rate": 0.00019989764261347736,
"loss": 3.6132,
"step": 18
},
{
"epoch": 0.15,
"learning_rate": 0.00019986631570270832,
"loss": 3.4794,
"step": 19
},
{
"epoch": 0.16,
"learning_rate": 0.00019983081582712685,
"loss": 3.2395,
"step": 20
},
{
"epoch": 0.17,
"learning_rate": 0.00019979114447011323,
"loss": 3.2974,
"step": 21
},
{
"epoch": 0.18,
"learning_rate": 0.00019974730328935534,
"loss": 3.2698,
"step": 22
},
{
"epoch": 0.19,
"learning_rate": 0.0001996992941167792,
"loss": 3.3091,
"step": 23
},
{
"epoch": 0.19,
"learning_rate": 0.00019964711895847258,
"loss": 3.2017,
"step": 24
},
{
"epoch": 0.2,
"learning_rate": 0.00019959077999460095,
"loss": 3.2469,
"step": 25
},
{
"epoch": 0.2,
"eval_loss": 3.0720062255859375,
"eval_runtime": 61.8274,
"eval_samples_per_second": 4.044,
"eval_steps_per_second": 4.044,
"step": 25
},
{
"epoch": 0.21,
"learning_rate": 0.00019953027957931658,
"loss": 3.1102,
"step": 26
},
{
"epoch": 0.22,
"learning_rate": 0.00019946562024066014,
"loss": 3.1641,
"step": 27
},
{
"epoch": 0.23,
"learning_rate": 0.00019939680468045499,
"loss": 2.9779,
"step": 28
},
{
"epoch": 0.23,
"learning_rate": 0.00019932383577419432,
"loss": 3.104,
"step": 29
},
{
"epoch": 0.24,
"learning_rate": 0.00019924671657092096,
"loss": 2.7981,
"step": 30
},
{
"epoch": 0.25,
"learning_rate": 0.00019916545029310012,
"loss": 2.7673,
"step": 31
},
{
"epoch": 0.26,
"learning_rate": 0.00019908004033648453,
"loss": 2.8478,
"step": 32
},
{
"epoch": 0.27,
"learning_rate": 0.00019899049026997272,
"loss": 2.7539,
"step": 33
},
{
"epoch": 0.27,
"learning_rate": 0.00019889680383545973,
"loss": 2.726,
"step": 34
},
{
"epoch": 0.28,
"learning_rate": 0.00019879898494768093,
"loss": 2.81,
"step": 35
},
{
"epoch": 0.29,
"learning_rate": 0.00019869703769404828,
"loss": 2.6177,
"step": 36
},
{
"epoch": 0.3,
"learning_rate": 0.00019859096633447965,
"loss": 2.6046,
"step": 37
},
{
"epoch": 0.31,
"learning_rate": 0.00019848077530122083,
"loss": 2.5004,
"step": 38
},
{
"epoch": 0.31,
"learning_rate": 0.0001983664691986601,
"loss": 2.4993,
"step": 39
},
{
"epoch": 0.32,
"learning_rate": 0.00019824805280313623,
"loss": 2.2775,
"step": 40
},
{
"epoch": 0.33,
"learning_rate": 0.00019812553106273847,
"loss": 2.3306,
"step": 41
},
{
"epoch": 0.34,
"learning_rate": 0.00019799890909710013,
"loss": 2.236,
"step": 42
},
{
"epoch": 0.35,
"learning_rate": 0.00019786819219718443,
"loss": 2.2798,
"step": 43
},
{
"epoch": 0.35,
"learning_rate": 0.0001977333858250636,
"loss": 2.2178,
"step": 44
},
{
"epoch": 0.36,
"learning_rate": 0.00019759449561369038,
"loss": 1.9915,
"step": 45
},
{
"epoch": 0.37,
"learning_rate": 0.00019745152736666302,
"loss": 2.3066,
"step": 46
},
{
"epoch": 0.38,
"learning_rate": 0.00019730448705798239,
"loss": 2.1409,
"step": 47
},
{
"epoch": 0.39,
"learning_rate": 0.00019715338083180269,
"loss": 1.9976,
"step": 48
},
{
"epoch": 0.4,
"learning_rate": 0.00019699821500217434,
"loss": 2.1843,
"step": 49
},
{
"epoch": 0.4,
"learning_rate": 0.0001968389960527806,
"loss": 2.1539,
"step": 50
},
{
"epoch": 0.4,
"eval_loss": 1.9486372470855713,
"eval_runtime": 61.7944,
"eval_samples_per_second": 4.046,
"eval_steps_per_second": 4.046,
"step": 50
},
{
"epoch": 0.41,
"learning_rate": 0.0001966757306366662,
"loss": 2.2096,
"step": 51
},
{
"epoch": 0.42,
"learning_rate": 0.00019650842557595967,
"loss": 2.0241,
"step": 52
},
{
"epoch": 0.43,
"learning_rate": 0.00019633708786158806,
"loss": 1.8814,
"step": 53
},
{
"epoch": 0.44,
"learning_rate": 0.00019616172465298492,
"loss": 1.9953,
"step": 54
},
{
"epoch": 0.44,
"learning_rate": 0.00019598234327779118,
"loss": 1.9807,
"step": 55
},
{
"epoch": 0.45,
"learning_rate": 0.0001957989512315489,
"loss": 1.9743,
"step": 56
},
{
"epoch": 0.46,
"learning_rate": 0.00019561155617738797,
"loss": 1.867,
"step": 57
},
{
"epoch": 0.47,
"learning_rate": 0.00019542016594570615,
"loss": 1.8289,
"step": 58
},
{
"epoch": 0.48,
"learning_rate": 0.00019522478853384155,
"loss": 1.9712,
"step": 59
},
{
"epoch": 0.48,
"learning_rate": 0.00019502543210573881,
"loss": 1.6946,
"step": 60
},
{
"epoch": 0.49,
"learning_rate": 0.00019482210499160765,
"loss": 1.8674,
"step": 61
},
{
"epoch": 0.5,
"learning_rate": 0.00019461481568757506,
"loss": 1.6849,
"step": 62
},
{
"epoch": 0.51,
"learning_rate": 0.00019440357285533,
"loss": 1.7003,
"step": 63
},
{
"epoch": 0.52,
"learning_rate": 0.00019418838532176173,
"loss": 1.7021,
"step": 64
},
{
"epoch": 0.52,
"learning_rate": 0.00019396926207859084,
"loss": 1.8302,
"step": 65
},
{
"epoch": 0.53,
"learning_rate": 0.0001937462122819935,
"loss": 1.8549,
"step": 66
},
{
"epoch": 0.54,
"learning_rate": 0.000193519245252219,
"loss": 1.8946,
"step": 67
},
{
"epoch": 0.55,
"learning_rate": 0.0001932883704732001,
"loss": 1.799,
"step": 68
},
{
"epoch": 0.56,
"learning_rate": 0.00019305359759215685,
"loss": 1.7541,
"step": 69
},
{
"epoch": 0.56,
"learning_rate": 0.00019281493641919368,
"loss": 1.7145,
"step": 70
},
{
"epoch": 0.57,
"learning_rate": 0.00019257239692688907,
"loss": 1.8254,
"step": 71
},
{
"epoch": 0.58,
"learning_rate": 0.00019232598924987903,
"loss": 1.6161,
"step": 72
},
{
"epoch": 0.59,
"learning_rate": 0.00019207572368443385,
"loss": 1.5698,
"step": 73
},
{
"epoch": 0.6,
"learning_rate": 0.00019182161068802741,
"loss": 1.8155,
"step": 74
},
{
"epoch": 0.6,
"learning_rate": 0.0001915636608789006,
"loss": 1.6997,
"step": 75
},
{
"epoch": 0.6,
"eval_loss": 1.6153544187545776,
"eval_runtime": 61.8069,
"eval_samples_per_second": 4.045,
"eval_steps_per_second": 4.045,
"step": 75
},
{
"epoch": 0.61,
"learning_rate": 0.00019130188503561741,
"loss": 1.6507,
"step": 76
},
{
"epoch": 0.62,
"learning_rate": 0.0001910362940966147,
"loss": 1.6035,
"step": 77
},
{
"epoch": 0.63,
"learning_rate": 0.00019076689915974488,
"loss": 1.4493,
"step": 78
},
{
"epoch": 0.64,
"learning_rate": 0.00019049371148181253,
"loss": 1.5494,
"step": 79
},
{
"epoch": 0.65,
"learning_rate": 0.0001902167424781038,
"loss": 1.5386,
"step": 80
},
{
"epoch": 0.65,
"learning_rate": 0.00018993600372190932,
"loss": 1.467,
"step": 81
},
{
"epoch": 0.66,
"learning_rate": 0.00018965150694404094,
"loss": 1.6658,
"step": 82
},
{
"epoch": 0.67,
"learning_rate": 0.00018936326403234125,
"loss": 1.6175,
"step": 83
},
{
"epoch": 0.68,
"learning_rate": 0.00018907128703118695,
"loss": 1.6551,
"step": 84
},
{
"epoch": 0.69,
"learning_rate": 0.00018877558814098561,
"loss": 1.409,
"step": 85
},
{
"epoch": 0.69,
"learning_rate": 0.00018847617971766577,
"loss": 1.4879,
"step": 86
},
{
"epoch": 0.7,
"learning_rate": 0.0001881730742721608,
"loss": 1.3067,
"step": 87
},
{
"epoch": 0.71,
"learning_rate": 0.00018786628446988593,
"loss": 1.6869,
"step": 88
},
{
"epoch": 0.72,
"learning_rate": 0.0001875558231302091,
"loss": 1.5962,
"step": 89
},
{
"epoch": 0.73,
"learning_rate": 0.00018724170322591537,
"loss": 1.3352,
"step": 90
},
{
"epoch": 0.73,
"learning_rate": 0.00018692393788266479,
"loss": 1.5016,
"step": 91
},
{
"epoch": 0.74,
"learning_rate": 0.00018660254037844388,
"loss": 1.6951,
"step": 92
},
{
"epoch": 0.75,
"learning_rate": 0.00018627752414301086,
"loss": 1.5388,
"step": 93
},
{
"epoch": 0.76,
"learning_rate": 0.00018594890275733453,
"loss": 1.3656,
"step": 94
},
{
"epoch": 0.77,
"learning_rate": 0.00018561668995302667,
"loss": 1.4599,
"step": 95
},
{
"epoch": 0.77,
"learning_rate": 0.0001852808996117683,
"loss": 1.3428,
"step": 96
},
{
"epoch": 0.78,
"learning_rate": 0.00018494154576472976,
"loss": 1.2147,
"step": 97
},
{
"epoch": 0.79,
"learning_rate": 0.0001845986425919841,
"loss": 1.4761,
"step": 98
},
{
"epoch": 0.8,
"learning_rate": 0.00018425220442191495,
"loss": 1.4571,
"step": 99
},
{
"epoch": 0.81,
"learning_rate": 0.00018390224573061747,
"loss": 1.5076,
"step": 100
},
{
"epoch": 0.81,
"eval_loss": 1.49380362033844,
"eval_runtime": 61.7975,
"eval_samples_per_second": 4.045,
"eval_steps_per_second": 4.045,
"step": 100
},
{
"epoch": 0.81,
"learning_rate": 0.00018354878114129367,
"loss": 1.3776,
"step": 101
},
{
"epoch": 0.82,
"learning_rate": 0.00018319182542364117,
"loss": 1.437,
"step": 102
},
{
"epoch": 0.83,
"learning_rate": 0.00018283139349323634,
"loss": 1.3558,
"step": 103
},
{
"epoch": 0.84,
"learning_rate": 0.0001824675004109107,
"loss": 1.4502,
"step": 104
},
{
"epoch": 0.85,
"learning_rate": 0.00018210016138212187,
"loss": 1.3451,
"step": 105
},
{
"epoch": 0.85,
"learning_rate": 0.00018172939175631808,
"loss": 1.403,
"step": 106
},
{
"epoch": 0.86,
"learning_rate": 0.00018135520702629675,
"loss": 1.1523,
"step": 107
},
{
"epoch": 0.87,
"learning_rate": 0.00018097762282755727,
"loss": 1.2302,
"step": 108
},
{
"epoch": 0.88,
"learning_rate": 0.00018059665493764743,
"loss": 1.4151,
"step": 109
},
{
"epoch": 0.89,
"learning_rate": 0.0001802123192755044,
"loss": 1.4853,
"step": 110
},
{
"epoch": 0.9,
"learning_rate": 0.0001798246319007893,
"loss": 1.2571,
"step": 111
},
{
"epoch": 0.9,
"learning_rate": 0.0001794336090132164,
"loss": 1.3594,
"step": 112
},
{
"epoch": 0.91,
"learning_rate": 0.00017903926695187595,
"loss": 1.3997,
"step": 113
},
{
"epoch": 0.92,
"learning_rate": 0.00017864162219455163,
"loss": 1.5718,
"step": 114
},
{
"epoch": 0.93,
"learning_rate": 0.00017824069135703198,
"loss": 1.314,
"step": 115
},
{
"epoch": 0.94,
"learning_rate": 0.00017783649119241602,
"loss": 1.3595,
"step": 116
},
{
"epoch": 0.94,
"learning_rate": 0.00017742903859041325,
"loss": 1.4467,
"step": 117
},
{
"epoch": 0.95,
"learning_rate": 0.00017701835057663798,
"loss": 1.2837,
"step": 118
},
{
"epoch": 0.96,
"learning_rate": 0.0001766044443118978,
"loss": 1.2669,
"step": 119
},
{
"epoch": 0.97,
"learning_rate": 0.00017618733709147662,
"loss": 1.3115,
"step": 120
},
{
"epoch": 0.98,
"learning_rate": 0.0001757670463444118,
"loss": 1.1836,
"step": 121
},
{
"epoch": 0.98,
"learning_rate": 0.00017534358963276607,
"loss": 1.6092,
"step": 122
},
{
"epoch": 0.99,
"learning_rate": 0.00017491698465089362,
"loss": 1.2288,
"step": 123
},
{
"epoch": 1.0,
"learning_rate": 0.00017448724922470058,
"loss": 1.2305,
"step": 124
},
{
"epoch": 1.01,
"learning_rate": 0.00017405440131090048,
"loss": 1.3794,
"step": 125
},
{
"epoch": 1.01,
"eval_loss": 1.4039632081985474,
"eval_runtime": 61.7879,
"eval_samples_per_second": 4.046,
"eval_steps_per_second": 4.046,
"step": 125
},
{
"epoch": 1.02,
"learning_rate": 0.00017361845899626355,
"loss": 1.2283,
"step": 126
},
{
"epoch": 1.0,
"learning_rate": 0.00017317944049686124,
"loss": 1.2627,
"step": 127
},
{
"epoch": 1.01,
"learning_rate": 0.00017273736415730488,
"loss": 1.2911,
"step": 128
},
{
"epoch": 1.02,
"learning_rate": 0.00017229224844997928,
"loss": 1.1225,
"step": 129
},
{
"epoch": 1.03,
"learning_rate": 0.00017184411197427077,
"loss": 1.3,
"step": 130
},
{
"epoch": 1.03,
"learning_rate": 0.00017139297345578994,
"loss": 1.1852,
"step": 131
},
{
"epoch": 1.04,
"learning_rate": 0.0001709388517455893,
"loss": 1.1986,
"step": 132
},
{
"epoch": 1.05,
"learning_rate": 0.00017048176581937563,
"loss": 1.3396,
"step": 133
},
{
"epoch": 1.06,
"learning_rate": 0.00017002173477671686,
"loss": 1.3584,
"step": 134
},
{
"epoch": 1.07,
"learning_rate": 0.0001695587778402442,
"loss": 1.2763,
"step": 135
},
{
"epoch": 1.07,
"learning_rate": 0.0001690929143548488,
"loss": 1.3017,
"step": 136
},
{
"epoch": 1.08,
"learning_rate": 0.0001686241637868734,
"loss": 1.2383,
"step": 137
},
{
"epoch": 1.09,
"learning_rate": 0.00016815254572329896,
"loss": 1.238,
"step": 138
},
{
"epoch": 1.1,
"learning_rate": 0.00016767807987092621,
"loss": 1.2702,
"step": 139
},
{
"epoch": 1.11,
"learning_rate": 0.00016720078605555224,
"loss": 1.3573,
"step": 140
},
{
"epoch": 1.11,
"learning_rate": 0.00016672068422114196,
"loss": 1.2863,
"step": 141
},
{
"epoch": 1.12,
"learning_rate": 0.0001662377944289948,
"loss": 1.2192,
"step": 142
},
{
"epoch": 1.13,
"learning_rate": 0.0001657521368569064,
"loss": 1.1934,
"step": 143
},
{
"epoch": 1.14,
"learning_rate": 0.00016526373179832546,
"loss": 1.1558,
"step": 144
},
{
"epoch": 1.15,
"learning_rate": 0.00016477259966150588,
"loss": 1.3684,
"step": 145
},
{
"epoch": 1.16,
"learning_rate": 0.00016427876096865394,
"loss": 1.5386,
"step": 146
},
{
"epoch": 1.16,
"learning_rate": 0.0001637822363550706,
"loss": 1.2404,
"step": 147
},
{
"epoch": 1.17,
"learning_rate": 0.00016328304656828952,
"loss": 1.2416,
"step": 148
},
{
"epoch": 1.18,
"learning_rate": 0.00016278121246720987,
"loss": 1.3613,
"step": 149
},
{
"epoch": 1.19,
"learning_rate": 0.00016227675502122492,
"loss": 1.2755,
"step": 150
},
{
"epoch": 1.19,
"eval_loss": 1.3754363059997559,
"eval_runtime": 61.7475,
"eval_samples_per_second": 4.049,
"eval_steps_per_second": 4.049,
"step": 150
},
{
"epoch": 1.2,
"learning_rate": 0.00016176969530934572,
"loss": 1.3912,
"step": 151
},
{
"epoch": 1.2,
"learning_rate": 0.0001612600545193203,
"loss": 1.2778,
"step": 152
},
{
"epoch": 1.21,
"learning_rate": 0.00016074785394674837,
"loss": 1.2326,
"step": 153
},
{
"epoch": 1.22,
"learning_rate": 0.0001602331149941915,
"loss": 1.2526,
"step": 154
},
{
"epoch": 1.23,
"learning_rate": 0.00015971585917027862,
"loss": 1.1176,
"step": 155
},
{
"epoch": 1.24,
"learning_rate": 0.0001591961080888076,
"loss": 1.1617,
"step": 156
},
{
"epoch": 1.24,
"learning_rate": 0.0001586738834678418,
"loss": 1.2921,
"step": 157
},
{
"epoch": 1.25,
"learning_rate": 0.00015814920712880267,
"loss": 1.3704,
"step": 158
},
{
"epoch": 1.26,
"learning_rate": 0.00015762210099555803,
"loss": 1.1412,
"step": 159
},
{
"epoch": 1.27,
"learning_rate": 0.00015709258709350582,
"loss": 1.1516,
"step": 160
},
{
"epoch": 1.28,
"learning_rate": 0.00015656068754865387,
"loss": 1.3323,
"step": 161
},
{
"epoch": 1.28,
"learning_rate": 0.00015602642458669528,
"loss": 1.2082,
"step": 162
},
{
"epoch": 1.29,
"learning_rate": 0.0001554898205320797,
"loss": 1.1952,
"step": 163
},
{
"epoch": 1.3,
"learning_rate": 0.0001549508978070806,
"loss": 1.172,
"step": 164
},
{
"epoch": 1.31,
"learning_rate": 0.00015440967893085828,
"loss": 1.3049,
"step": 165
},
{
"epoch": 1.32,
"learning_rate": 0.0001538661865185188,
"loss": 1.1573,
"step": 166
},
{
"epoch": 1.32,
"learning_rate": 0.00015332044328016914,
"loss": 1.3122,
"step": 167
},
{
"epoch": 1.33,
"learning_rate": 0.0001527724720199682,
"loss": 1.2487,
"step": 168
},
{
"epoch": 1.34,
"learning_rate": 0.00015222229563517385,
"loss": 1.2054,
"step": 169
},
{
"epoch": 1.35,
"learning_rate": 0.00015166993711518631,
"loss": 1.1871,
"step": 170
},
{
"epoch": 1.36,
"learning_rate": 0.00015111541954058734,
"loss": 1.1853,
"step": 171
},
{
"epoch": 1.36,
"learning_rate": 0.0001505587660821759,
"loss": 1.2743,
"step": 172
},
{
"epoch": 1.37,
"learning_rate": 0.00015000000000000001,
"loss": 1.1493,
"step": 173
},
{
"epoch": 1.38,
"learning_rate": 0.00014943914464238468,
"loss": 1.2354,
"step": 174
},
{
"epoch": 1.39,
"learning_rate": 0.00014887622344495643,
"loss": 1.1913,
"step": 175
},
{
"epoch": 1.39,
"eval_loss": 1.3428610563278198,
"eval_runtime": 61.7873,
"eval_samples_per_second": 4.046,
"eval_steps_per_second": 4.046,
"step": 175
},
{
"epoch": 1.4,
"learning_rate": 0.00014831125992966385,
"loss": 1.2415,
"step": 176
},
{
"epoch": 1.41,
"learning_rate": 0.0001477442777037949,
"loss": 1.1343,
"step": 177
},
{
"epoch": 1.41,
"learning_rate": 0.00014717530045899038,
"loss": 1.325,
"step": 178
},
{
"epoch": 1.42,
"learning_rate": 0.0001466043519702539,
"loss": 1.3118,
"step": 179
},
{
"epoch": 1.43,
"learning_rate": 0.0001460314560949586,
"loss": 1.2941,
"step": 180
},
{
"epoch": 1.44,
"learning_rate": 0.00014545663677185006,
"loss": 1.1848,
"step": 181
},
{
"epoch": 1.45,
"learning_rate": 0.00014487991802004623,
"loss": 1.1337,
"step": 182
},
{
"epoch": 1.45,
"learning_rate": 0.00014430132393803352,
"loss": 1.1494,
"step": 183
},
{
"epoch": 1.46,
"learning_rate": 0.0001437208787026601,
"loss": 1.2076,
"step": 184
},
{
"epoch": 1.47,
"learning_rate": 0.00014313860656812536,
"loss": 1.1794,
"step": 185
},
{
"epoch": 1.48,
"learning_rate": 0.00014255453186496673,
"loss": 1.2402,
"step": 186
},
{
"epoch": 1.49,
"learning_rate": 0.0001419686789990429,
"loss": 1.2741,
"step": 187
},
{
"epoch": 1.49,
"learning_rate": 0.00014138107245051392,
"loss": 1.2486,
"step": 188
},
{
"epoch": 1.5,
"learning_rate": 0.00014079173677281837,
"loss": 1.2796,
"step": 189
},
{
"epoch": 1.51,
"learning_rate": 0.0001402006965916474,
"loss": 1.0193,
"step": 190
},
{
"epoch": 1.52,
"learning_rate": 0.0001396079766039157,
"loss": 1.1447,
"step": 191
},
{
"epoch": 1.53,
"learning_rate": 0.0001390136015767295,
"loss": 1.0318,
"step": 192
},
{
"epoch": 1.53,
"learning_rate": 0.00013841759634635178,
"loss": 1.1047,
"step": 193
},
{
"epoch": 1.54,
"learning_rate": 0.00013781998581716427,
"loss": 1.1895,
"step": 194
},
{
"epoch": 1.55,
"learning_rate": 0.00013722079496062702,
"loss": 1.1119,
"step": 195
},
{
"epoch": 1.56,
"learning_rate": 0.0001366200488142348,
"loss": 1.0248,
"step": 196
},
{
"epoch": 1.57,
"learning_rate": 0.00013601777248047105,
"loss": 1.0961,
"step": 197
},
{
"epoch": 1.57,
"learning_rate": 0.00013541399112575878,
"loss": 1.2622,
"step": 198
},
{
"epoch": 1.58,
"learning_rate": 0.00013480872997940905,
"loss": 1.1858,
"step": 199
},
{
"epoch": 1.59,
"learning_rate": 0.00013420201433256689,
"loss": 1.1458,
"step": 200
},
{
"epoch": 1.59,
"eval_loss": 1.3336366415023804,
"eval_runtime": 61.796,
"eval_samples_per_second": 4.046,
"eval_steps_per_second": 4.046,
"step": 200
},
{
"epoch": 1.6,
"learning_rate": 0.00013359386953715421,
"loss": 1.3068,
"step": 201
},
{
"epoch": 1.61,
"learning_rate": 0.00013298432100481079,
"loss": 1.0935,
"step": 202
},
{
"epoch": 1.61,
"learning_rate": 0.00013237339420583212,
"loss": 1.1904,
"step": 203
},
{
"epoch": 1.62,
"learning_rate": 0.00013176111466810532,
"loss": 1.1859,
"step": 204
},
{
"epoch": 1.63,
"learning_rate": 0.00013114750797604247,
"loss": 1.1536,
"step": 205
},
{
"epoch": 1.64,
"learning_rate": 0.00013053259976951133,
"loss": 1.2067,
"step": 206
},
{
"epoch": 1.65,
"learning_rate": 0.00012991641574276418,
"loss": 1.2649,
"step": 207
},
{
"epoch": 1.66,
"learning_rate": 0.00012991641574276418,
"loss": 1.2189,
"step": 208
},
{
"epoch": 1.66,
"learning_rate": 0.00012929898164336408,
"loss": 1.301,
"step": 209
},
{
"epoch": 1.67,
"learning_rate": 0.00012868032327110904,
"loss": 1.1506,
"step": 210
},
{
"epoch": 1.68,
"learning_rate": 0.0001280604664769539,
"loss": 1.1964,
"step": 211
},
{
"epoch": 1.69,
"learning_rate": 0.00012743943716193016,
"loss": 1.139,
"step": 212
},
{
"epoch": 1.7,
"learning_rate": 0.00012681726127606376,
"loss": 1.2197,
"step": 213
},
{
"epoch": 1.7,
"learning_rate": 0.0001261939648172906,
"loss": 1.1713,
"step": 214
},
{
"epoch": 1.71,
"learning_rate": 0.0001255695738303704,
"loss": 1.2533,
"step": 215
},
{
"epoch": 1.72,
"learning_rate": 0.00012494411440579814,
"loss": 1.1755,
"step": 216
},
{
"epoch": 1.73,
"learning_rate": 0.00012431761267871417,
"loss": 0.9834,
"step": 217
},
{
"epoch": 1.74,
"learning_rate": 0.00012369009482781192,
"loss": 1.1805,
"step": 218
},
{
"epoch": 1.74,
"learning_rate": 0.00012306158707424403,
"loss": 1.0295,
"step": 219
},
{
"epoch": 1.75,
"learning_rate": 0.00012243211568052677,
"loss": 1.0861,
"step": 220
},
{
"epoch": 1.76,
"learning_rate": 0.0001218017069494426,
"loss": 1.3924,
"step": 221
},
{
"epoch": 1.77,
"learning_rate": 0.0001211703872229411,
"loss": 1.1034,
"step": 222
},
{
"epoch": 1.78,
"learning_rate": 0.0001205381828810382,
"loss": 1.0464,
"step": 223
},
{
"epoch": 1.78,
"learning_rate": 0.00011990512034071406,
"loss": 1.1107,
"step": 224
},
{
"epoch": 1.79,
"learning_rate": 0.00011927122605480898,
"loss": 1.1568,
"step": 225
},
{
"epoch": 1.79,
"eval_loss": 1.31128990650177,
"eval_runtime": 61.808,
"eval_samples_per_second": 4.045,
"eval_steps_per_second": 4.045,
"step": 225
},
{
"epoch": 1.8,
"learning_rate": 0.00011863652651091823,
"loss": 1.0532,
"step": 226
},
{
"epoch": 1.81,
"learning_rate": 0.00011800104823028515,
"loss": 1.0956,
"step": 227
},
{
"epoch": 1.82,
"learning_rate": 0.00011736481776669306,
"loss": 1.2576,
"step": 228
},
{
"epoch": 1.82,
"learning_rate": 0.00011672786170535552,
"loss": 1.081,
"step": 229
},
{
"epoch": 1.83,
"learning_rate": 0.00011609020666180575,
"loss": 1.097,
"step": 230
},
{
"epoch": 1.84,
"learning_rate": 0.00011545187928078406,
"loss": 1.1571,
"step": 231
},
{
"epoch": 1.85,
"learning_rate": 0.0001148129062351249,
"loss": 1.3143,
"step": 232
},
{
"epoch": 1.86,
"learning_rate": 0.00011417331422464205,
"loss": 1.2877,
"step": 233
},
{
"epoch": 1.86,
"learning_rate": 0.00011353312997501313,
"loss": 1.1032,
"step": 234
},
{
"epoch": 1.87,
"learning_rate": 0.00011289238023666266,
"loss": 1.1401,
"step": 235
},
{
"epoch": 1.88,
"learning_rate": 0.00011225109178364455,
"loss": 1.2596,
"step": 236
},
{
"epoch": 1.89,
"learning_rate": 0.00011160929141252303,
"loss": 1.1803,
"step": 237
},
{
"epoch": 1.9,
"learning_rate": 0.00011096700594125318,
"loss": 1.0706,
"step": 238
},
{
"epoch": 1.91,
"learning_rate": 0.00011032426220806018,
"loss": 1.1804,
"step": 239
},
{
"epoch": 1.91,
"learning_rate": 0.00010968108707031792,
"loss": 1.2334,
"step": 240
},
{
"epoch": 1.92,
"learning_rate": 0.00010903750740342682,
"loss": 1.1523,
"step": 241
},
{
"epoch": 1.93,
"learning_rate": 0.00010839355009969068,
"loss": 1.1336,
"step": 242
},
{
"epoch": 1.94,
"learning_rate": 0.0001077492420671931,
"loss": 1.1287,
"step": 243
},
{
"epoch": 1.95,
"learning_rate": 0.00010710461022867302,
"loss": 1.181,
"step": 244
},
{
"epoch": 1.95,
"learning_rate": 0.0001064596815203998,
"loss": 1.2882,
"step": 245
},
{
"epoch": 1.96,
"learning_rate": 0.00010581448289104758,
"loss": 1.0872,
"step": 246
},
{
"epoch": 1.97,
"learning_rate": 0.00010516904130056946,
"loss": 1.1117,
"step": 247
},
{
"epoch": 1.98,
"learning_rate": 0.00010452338371907064,
"loss": 1.1874,
"step": 248
},
{
"epoch": 1.99,
"learning_rate": 0.0001038775371256817,
"loss": 1.0474,
"step": 249
},
{
"epoch": 1.99,
"learning_rate": 0.00010323152850743107,
"loss": 1.1845,
"step": 250
},
{
"epoch": 1.99,
"eval_loss": 1.2912580966949463,
"eval_runtime": 61.8585,
"eval_samples_per_second": 4.041,
"eval_steps_per_second": 4.041,
"step": 250
},
{
"epoch": 2.0,
"learning_rate": 0.00010258538485811765,
"loss": 1.3517,
"step": 251
},
{
"epoch": 2.01,
"learning_rate": 0.00010193913317718244,
"loss": 1.2637,
"step": 252
},
{
"epoch": 2.02,
"learning_rate": 0.00010129280046858086,
"loss": 1.1032,
"step": 253
}
],
"logging_steps": 1,
"max_steps": 496,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 8.228961374542234e+16,
"trial_name": null,
"trial_params": null
}