lmg-anon's picture
Upload folder using huggingface_hub
192ba15 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9757539917208752,
"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,
"learning_rate": 5.4166666666666664e-05,
"loss": 2.8488,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.00010833333333333333,
"loss": 2.7815,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0001625,
"loss": 2.8002,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.00021666666666666666,
"loss": 2.7473,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0002708333333333333,
"loss": 2.4233,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.000325,
"loss": 1.9676,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 0.00037916666666666665,
"loss": 1.7562,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 0.0004333333333333333,
"loss": 1.3949,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0004875,
"loss": 1.2908,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 0.0005416666666666666,
"loss": 1.2542,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.0005958333333333333,
"loss": 1.2959,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 0.00065,
"loss": 1.1706,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 0.0006499947173877214,
"loss": 1.0829,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 0.0006499788697226147,
"loss": 1.128,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 0.0006499524575198621,
"loss": 1.0847,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 0.0006499154816380815,
"loss": 1.1143,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 0.0006498679432792988,
"loss": 1.0751,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 0.0006498098439889095,
"loss": 1.179,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 0.0006497411856556275,
"loss": 1.0327,
"step": 19
},
{
"epoch": 0.04,
"learning_rate": 0.0006496619705114241,
"loss": 1.0672,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 0.0006495722011314557,
"loss": 1.1625,
"step": 21
},
{
"epoch": 0.04,
"learning_rate": 0.0006494718804339797,
"loss": 1.0751,
"step": 22
},
{
"epoch": 0.04,
"learning_rate": 0.0006493610116802598,
"loss": 0.996,
"step": 23
},
{
"epoch": 0.04,
"learning_rate": 0.0006492395984744599,
"loss": 1.0478,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 0.0006491076447635269,
"loss": 1.064,
"step": 25
},
{
"epoch": 0.05,
"learning_rate": 0.0006489651548370628,
"loss": 0.9393,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 0.0006488121333271846,
"loss": 0.9282,
"step": 27
},
{
"epoch": 0.05,
"learning_rate": 0.0006486485852083744,
"loss": 1.0558,
"step": 28
},
{
"epoch": 0.05,
"learning_rate": 0.0006484745157973169,
"loss": 1.0015,
"step": 29
},
{
"epoch": 0.05,
"learning_rate": 0.0006482899307527272,
"loss": 1.0261,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 0.0006480948360751669,
"loss": 1.0507,
"step": 31
},
{
"epoch": 0.06,
"learning_rate": 0.0006478892381068483,
"loss": 1.0225,
"step": 32
},
{
"epoch": 0.06,
"learning_rate": 0.0006476731435314292,
"loss": 0.9411,
"step": 33
},
{
"epoch": 0.06,
"learning_rate": 0.0006474465593737948,
"loss": 0.9884,
"step": 34
},
{
"epoch": 0.06,
"learning_rate": 0.0006472094929998295,
"loss": 0.9892,
"step": 35
},
{
"epoch": 0.06,
"learning_rate": 0.0006469619521161782,
"loss": 1.0527,
"step": 36
},
{
"epoch": 0.07,
"learning_rate": 0.0006467039447699945,
"loss": 0.969,
"step": 37
},
{
"epoch": 0.07,
"learning_rate": 0.0006464354793486803,
"loss": 1.0009,
"step": 38
},
{
"epoch": 0.07,
"learning_rate": 0.0006461565645796124,
"loss": 1.0068,
"step": 39
},
{
"epoch": 0.07,
"learning_rate": 0.0006458672095298589,
"loss": 0.9626,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 0.0006455674236058847,
"loss": 0.934,
"step": 41
},
{
"epoch": 0.07,
"learning_rate": 0.0006452572165532456,
"loss": 1.0217,
"step": 42
},
{
"epoch": 0.08,
"learning_rate": 0.0006449365984562712,
"loss": 1.0036,
"step": 43
},
{
"epoch": 0.08,
"learning_rate": 0.0006446055797377376,
"loss": 0.9234,
"step": 44
},
{
"epoch": 0.08,
"learning_rate": 0.000644264171158528,
"loss": 0.9771,
"step": 45
},
{
"epoch": 0.08,
"learning_rate": 0.0006439123838172836,
"loss": 1.013,
"step": 46
},
{
"epoch": 0.08,
"learning_rate": 0.0006435502291500418,
"loss": 0.9154,
"step": 47
},
{
"epoch": 0.09,
"learning_rate": 0.0006431777189298656,
"loss": 0.9098,
"step": 48
},
{
"epoch": 0.09,
"learning_rate": 0.0006427948652664599,
"loss": 0.9243,
"step": 49
},
{
"epoch": 0.09,
"learning_rate": 0.0006424016806057781,
"loss": 0.9162,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 0.0006419981777296182,
"loss": 0.9538,
"step": 51
},
{
"epoch": 0.09,
"learning_rate": 0.0006415843697552062,
"loss": 0.9454,
"step": 52
},
{
"epoch": 0.09,
"learning_rate": 0.0006411602701347703,
"loss": 0.9296,
"step": 53
},
{
"epoch": 0.1,
"learning_rate": 0.0006407258926551036,
"loss": 0.929,
"step": 54
},
{
"epoch": 0.1,
"learning_rate": 0.0006402812514371154,
"loss": 0.9172,
"step": 55
},
{
"epoch": 0.1,
"learning_rate": 0.0006398263609353731,
"loss": 0.9871,
"step": 56
},
{
"epoch": 0.1,
"learning_rate": 0.0006393612359376315,
"loss": 0.9279,
"step": 57
},
{
"epoch": 0.1,
"learning_rate": 0.0006388858915643519,
"loss": 0.9191,
"step": 58
},
{
"epoch": 0.1,
"learning_rate": 0.0006384003432682119,
"loss": 0.9828,
"step": 59
},
{
"epoch": 0.11,
"learning_rate": 0.0006379046068336013,
"loss": 0.8912,
"step": 60
},
{
"epoch": 0.11,
"learning_rate": 0.00063739869837611,
"loss": 0.9023,
"step": 61
},
{
"epoch": 0.11,
"learning_rate": 0.0006368826343420043,
"loss": 0.9978,
"step": 62
},
{
"epoch": 0.11,
"learning_rate": 0.0006363564315076915,
"loss": 0.9097,
"step": 63
},
{
"epoch": 0.11,
"learning_rate": 0.0006358201069791749,
"loss": 0.8475,
"step": 64
},
{
"epoch": 0.12,
"learning_rate": 0.000635273678191498,
"loss": 0.9763,
"step": 65
},
{
"epoch": 0.12,
"learning_rate": 0.000634717162908177,
"loss": 0.8673,
"step": 66
},
{
"epoch": 0.12,
"learning_rate": 0.0006341505792206243,
"loss": 0.9188,
"step": 67
},
{
"epoch": 0.12,
"learning_rate": 0.0006335739455475594,
"loss": 0.865,
"step": 68
},
{
"epoch": 0.12,
"learning_rate": 0.0006329872806344108,
"loss": 0.9187,
"step": 69
},
{
"epoch": 0.12,
"learning_rate": 0.0006323906035527062,
"loss": 0.887,
"step": 70
},
{
"epoch": 0.13,
"learning_rate": 0.0006317839336994531,
"loss": 0.908,
"step": 71
},
{
"epoch": 0.13,
"learning_rate": 0.0006311672907965074,
"loss": 0.918,
"step": 72
},
{
"epoch": 0.13,
"learning_rate": 0.0006305406948899329,
"loss": 0.9399,
"step": 73
},
{
"epoch": 0.13,
"learning_rate": 0.0006299041663493497,
"loss": 0.9741,
"step": 74
},
{
"epoch": 0.13,
"learning_rate": 0.0006292577258672713,
"loss": 0.8738,
"step": 75
},
{
"epoch": 0.13,
"learning_rate": 0.0006286013944584328,
"loss": 0.9192,
"step": 76
},
{
"epoch": 0.14,
"learning_rate": 0.0006279351934591071,
"loss": 0.8589,
"step": 77
},
{
"epoch": 0.14,
"learning_rate": 0.0006272591445264116,
"loss": 0.955,
"step": 78
},
{
"epoch": 0.14,
"learning_rate": 0.0006265732696376042,
"loss": 0.928,
"step": 79
},
{
"epoch": 0.14,
"learning_rate": 0.0006258775910893685,
"loss": 0.8454,
"step": 80
},
{
"epoch": 0.14,
"learning_rate": 0.0006251721314970894,
"loss": 0.8709,
"step": 81
},
{
"epoch": 0.15,
"learning_rate": 0.0006244569137941179,
"loss": 0.8732,
"step": 82
},
{
"epoch": 0.15,
"learning_rate": 0.0006237319612310249,
"loss": 0.9345,
"step": 83
},
{
"epoch": 0.15,
"learning_rate": 0.0006229972973748463,
"loss": 0.9342,
"step": 84
},
{
"epoch": 0.15,
"learning_rate": 0.0006222529461083165,
"loss": 0.8803,
"step": 85
},
{
"epoch": 0.15,
"learning_rate": 0.0006214989316290914,
"loss": 0.8676,
"step": 86
},
{
"epoch": 0.15,
"learning_rate": 0.0006207352784489629,
"loss": 0.9195,
"step": 87
},
{
"epoch": 0.16,
"learning_rate": 0.000619962011393061,
"loss": 0.9505,
"step": 88
},
{
"epoch": 0.16,
"learning_rate": 0.0006191791555990477,
"loss": 0.8778,
"step": 89
},
{
"epoch": 0.16,
"learning_rate": 0.0006183867365162994,
"loss": 0.9663,
"step": 90
},
{
"epoch": 0.16,
"learning_rate": 0.0006175847799050789,
"loss": 0.9304,
"step": 91
},
{
"epoch": 0.16,
"learning_rate": 0.0006167733118356993,
"loss": 0.9233,
"step": 92
},
{
"epoch": 0.16,
"learning_rate": 0.0006159523586876756,
"loss": 0.9167,
"step": 93
},
{
"epoch": 0.17,
"learning_rate": 0.0006151219471488673,
"loss": 0.882,
"step": 94
},
{
"epoch": 0.17,
"learning_rate": 0.0006142821042146112,
"loss": 0.8295,
"step": 95
},
{
"epoch": 0.17,
"learning_rate": 0.0006134328571868428,
"loss": 0.7799,
"step": 96
},
{
"epoch": 0.17,
"learning_rate": 0.0006125742336732103,
"loss": 0.9368,
"step": 97
},
{
"epoch": 0.17,
"learning_rate": 0.000611706261586176,
"loss": 0.8542,
"step": 98
},
{
"epoch": 0.18,
"learning_rate": 0.0006108289691421089,
"loss": 0.9263,
"step": 99
},
{
"epoch": 0.18,
"learning_rate": 0.0006099423848603682,
"loss": 0.8572,
"step": 100
},
{
"epoch": 0.18,
"learning_rate": 0.0006090465375623755,
"loss": 0.905,
"step": 101
},
{
"epoch": 0.18,
"learning_rate": 0.0006081414563706781,
"loss": 0.8621,
"step": 102
},
{
"epoch": 0.18,
"learning_rate": 0.0006072271707080021,
"loss": 0.8745,
"step": 103
},
{
"epoch": 0.18,
"learning_rate": 0.0006063037102962963,
"loss": 0.928,
"step": 104
},
{
"epoch": 0.19,
"learning_rate": 0.0006053711051557658,
"loss": 0.908,
"step": 105
},
{
"epoch": 0.19,
"learning_rate": 0.0006044293856038958,
"loss": 0.8919,
"step": 106
},
{
"epoch": 0.19,
"learning_rate": 0.0006034785822544665,
"loss": 0.8665,
"step": 107
},
{
"epoch": 0.19,
"learning_rate": 0.0006025187260165575,
"loss": 0.8645,
"step": 108
},
{
"epoch": 0.19,
"learning_rate": 0.0006015498480935434,
"loss": 0.895,
"step": 109
},
{
"epoch": 0.2,
"learning_rate": 0.0006005719799820788,
"loss": 0.892,
"step": 110
},
{
"epoch": 0.2,
"learning_rate": 0.0005995851534710752,
"loss": 0.8843,
"step": 111
},
{
"epoch": 0.2,
"learning_rate": 0.0005985894006406671,
"loss": 0.8114,
"step": 112
},
{
"epoch": 0.2,
"learning_rate": 0.0005975847538611689,
"loss": 0.9086,
"step": 113
},
{
"epoch": 0.2,
"learning_rate": 0.0005965712457920233,
"loss": 0.8644,
"step": 114
},
{
"epoch": 0.2,
"learning_rate": 0.000595548909380739,
"loss": 0.8638,
"step": 115
},
{
"epoch": 0.21,
"learning_rate": 0.00059451777786182,
"loss": 0.8856,
"step": 116
},
{
"epoch": 0.21,
"learning_rate": 0.0005934778847556848,
"loss": 0.8749,
"step": 117
},
{
"epoch": 0.21,
"learning_rate": 0.0005924292638675769,
"loss": 0.8864,
"step": 118
},
{
"epoch": 0.21,
"learning_rate": 0.0005913719492864662,
"loss": 0.8317,
"step": 119
},
{
"epoch": 0.21,
"learning_rate": 0.0005903059753839402,
"loss": 0.8356,
"step": 120
},
{
"epoch": 0.21,
"learning_rate": 0.0005892313768130872,
"loss": 0.784,
"step": 121
},
{
"epoch": 0.22,
"learning_rate": 0.0005881481885073694,
"loss": 0.8377,
"step": 122
},
{
"epoch": 0.22,
"learning_rate": 0.0005870564456794872,
"loss": 0.7854,
"step": 123
},
{
"epoch": 0.22,
"learning_rate": 0.0005859561838202349,
"loss": 0.9538,
"step": 124
},
{
"epoch": 0.22,
"learning_rate": 0.0005848474386973468,
"loss": 0.8268,
"step": 125
},
{
"epoch": 0.22,
"learning_rate": 0.0005837302463543341,
"loss": 0.9009,
"step": 126
},
{
"epoch": 0.23,
"learning_rate": 0.000582604643109314,
"loss": 0.8684,
"step": 127
},
{
"epoch": 0.23,
"learning_rate": 0.0005814706655538279,
"loss": 0.7749,
"step": 128
},
{
"epoch": 0.23,
"learning_rate": 0.0005803283505516529,
"loss": 0.8931,
"step": 129
},
{
"epoch": 0.23,
"learning_rate": 0.0005791777352376026,
"loss": 0.8246,
"step": 130
},
{
"epoch": 0.23,
"learning_rate": 0.0005780188570163211,
"loss": 0.7862,
"step": 131
},
{
"epoch": 0.23,
"learning_rate": 0.0005768517535610654,
"loss": 0.9168,
"step": 132
},
{
"epoch": 0.24,
"learning_rate": 0.0005756764628124819,
"loss": 0.8706,
"step": 133
},
{
"epoch": 0.24,
"learning_rate": 0.000574493022977373,
"loss": 0.7976,
"step": 134
},
{
"epoch": 0.24,
"learning_rate": 0.000573301472527454,
"loss": 0.814,
"step": 135
},
{
"epoch": 0.24,
"learning_rate": 0.000572101850198104,
"loss": 0.8991,
"step": 136
},
{
"epoch": 0.24,
"learning_rate": 0.0005708941949871053,
"loss": 0.8539,
"step": 137
},
{
"epoch": 0.24,
"learning_rate": 0.0005696785461533761,
"loss": 0.9107,
"step": 138
},
{
"epoch": 0.25,
"learning_rate": 0.0005684549432156948,
"loss": 0.9165,
"step": 139
},
{
"epoch": 0.25,
"learning_rate": 0.0005672234259514147,
"loss": 0.843,
"step": 140
},
{
"epoch": 0.25,
"learning_rate": 0.000565984034395171,
"loss": 0.8328,
"step": 141
},
{
"epoch": 0.25,
"learning_rate": 0.0005647368088375792,
"loss": 0.884,
"step": 142
},
{
"epoch": 0.25,
"learning_rate": 0.000563481789823926,
"loss": 0.9101,
"step": 143
},
{
"epoch": 0.26,
"learning_rate": 0.0005622190181528502,
"loss": 0.8508,
"step": 144
},
{
"epoch": 0.26,
"learning_rate": 0.0005609485348750175,
"loss": 0.8575,
"step": 145
},
{
"epoch": 0.26,
"learning_rate": 0.0005596703812917851,
"loss": 0.8861,
"step": 146
},
{
"epoch": 0.26,
"learning_rate": 0.0005583845989538596,
"loss": 0.8163,
"step": 147
},
{
"epoch": 0.26,
"learning_rate": 0.0005570912296599459,
"loss": 0.8583,
"step": 148
},
{
"epoch": 0.26,
"learning_rate": 0.0005557903154553888,
"loss": 0.8635,
"step": 149
},
{
"epoch": 0.27,
"learning_rate": 0.000554481898630806,
"loss": 0.811,
"step": 150
},
{
"epoch": 0.27,
"learning_rate": 0.0005531660217207126,
"loss": 0.9116,
"step": 151
},
{
"epoch": 0.27,
"learning_rate": 0.0005518427275021399,
"loss": 0.868,
"step": 152
},
{
"epoch": 0.27,
"learning_rate": 0.0005505120589932435,
"loss": 0.8868,
"step": 153
},
{
"epoch": 0.27,
"learning_rate": 0.0005491740594519051,
"loss": 0.8816,
"step": 154
},
{
"epoch": 0.27,
"learning_rate": 0.0005478287723743267,
"loss": 0.8499,
"step": 155
},
{
"epoch": 0.28,
"learning_rate": 0.0005464762414936163,
"loss": 0.8502,
"step": 156
},
{
"epoch": 0.28,
"learning_rate": 0.0005451165107783659,
"loss": 0.86,
"step": 157
},
{
"epoch": 0.28,
"learning_rate": 0.0005437496244312228,
"loss": 0.8669,
"step": 158
},
{
"epoch": 0.28,
"learning_rate": 0.0005423756268874522,
"loss": 0.869,
"step": 159
},
{
"epoch": 0.28,
"learning_rate": 0.000540994562813493,
"loss": 0.8476,
"step": 160
},
{
"epoch": 0.29,
"learning_rate": 0.0005396064771055053,
"loss": 0.7992,
"step": 161
},
{
"epoch": 0.29,
"learning_rate": 0.0005382114148879113,
"loss": 0.8569,
"step": 162
},
{
"epoch": 0.29,
"learning_rate": 0.0005368094215119282,
"loss": 0.8367,
"step": 163
},
{
"epoch": 0.29,
"learning_rate": 0.000535400542554094,
"loss": 0.8455,
"step": 164
},
{
"epoch": 0.29,
"learning_rate": 0.0005339848238147857,
"loss": 0.9209,
"step": 165
},
{
"epoch": 0.29,
"learning_rate": 0.0005325623113167311,
"loss": 0.8577,
"step": 166
},
{
"epoch": 0.3,
"learning_rate": 0.0005311330513035111,
"loss": 0.8331,
"step": 167
},
{
"epoch": 0.3,
"learning_rate": 0.0005296970902380583,
"loss": 0.7925,
"step": 168
},
{
"epoch": 0.3,
"learning_rate": 0.0005282544748011454,
"loss": 0.8223,
"step": 169
},
{
"epoch": 0.3,
"learning_rate": 0.0005268052518898676,
"loss": 0.8555,
"step": 170
},
{
"epoch": 0.3,
"learning_rate": 0.0005253494686161189,
"loss": 0.9448,
"step": 171
},
{
"epoch": 0.31,
"learning_rate": 0.00052388717230506,
"loss": 0.8364,
"step": 172
},
{
"epoch": 0.31,
"learning_rate": 0.0005224184104935797,
"loss": 0.866,
"step": 173
},
{
"epoch": 0.31,
"learning_rate": 0.0005209432309287499,
"loss": 0.8312,
"step": 174
},
{
"epoch": 0.31,
"learning_rate": 0.0005194616815662733,
"loss": 0.8725,
"step": 175
},
{
"epoch": 0.31,
"learning_rate": 0.0005179738105689243,
"loss": 0.8199,
"step": 176
},
{
"epoch": 0.31,
"learning_rate": 0.0005164796663049834,
"loss": 0.8068,
"step": 177
},
{
"epoch": 0.32,
"learning_rate": 0.0005149792973466653,
"loss": 0.8533,
"step": 178
},
{
"epoch": 0.32,
"learning_rate": 0.0005134727524685388,
"loss": 0.9067,
"step": 179
},
{
"epoch": 0.32,
"learning_rate": 0.0005119600806459426,
"loss": 0.8105,
"step": 180
},
{
"epoch": 0.32,
"learning_rate": 0.0005104413310533914,
"loss": 0.8426,
"step": 181
},
{
"epoch": 0.32,
"learning_rate": 0.0005089165530629796,
"loss": 0.8854,
"step": 182
},
{
"epoch": 0.32,
"learning_rate": 0.0005073857962427743,
"loss": 0.8151,
"step": 183
},
{
"epoch": 0.33,
"learning_rate": 0.0005058491103552046,
"loss": 0.8467,
"step": 184
},
{
"epoch": 0.33,
"learning_rate": 0.0005043065453554449,
"loss": 0.8343,
"step": 185
},
{
"epoch": 0.33,
"learning_rate": 0.0005027581513897888,
"loss": 0.8139,
"step": 186
},
{
"epoch": 0.33,
"learning_rate": 0.0005012039787940209,
"loss": 0.8632,
"step": 187
},
{
"epoch": 0.33,
"learning_rate": 0.0004996440780917798,
"loss": 0.8525,
"step": 188
},
{
"epoch": 0.34,
"learning_rate": 0.0004980784999929151,
"loss": 0.9075,
"step": 189
},
{
"epoch": 0.34,
"learning_rate": 0.00049650729539184,
"loss": 0.7663,
"step": 190
},
{
"epoch": 0.34,
"learning_rate": 0.0004949305153658755,
"loss": 0.82,
"step": 191
},
{
"epoch": 0.34,
"learning_rate": 0.0004933482111735912,
"loss": 0.9614,
"step": 192
},
{
"epoch": 0.34,
"learning_rate": 0.0004917604342531381,
"loss": 0.8063,
"step": 193
},
{
"epoch": 0.34,
"learning_rate": 0.0004901672362205767,
"loss": 0.8729,
"step": 194
},
{
"epoch": 0.35,
"learning_rate": 0.0004885686688681996,
"loss": 0.8819,
"step": 195
},
{
"epoch": 0.35,
"learning_rate": 0.0004869647841628468,
"loss": 0.7797,
"step": 196
},
{
"epoch": 0.35,
"learning_rate": 0.00048535563424421686,
"loss": 0.7435,
"step": 197
},
{
"epoch": 0.35,
"learning_rate": 0.0004837412714231722,
"loss": 0.7985,
"step": 198
},
{
"epoch": 0.35,
"learning_rate": 0.00048212174818003796,
"loss": 0.8532,
"step": 199
},
{
"epoch": 0.35,
"learning_rate": 0.00048049711716289666,
"loss": 0.8559,
"step": 200
},
{
"epoch": 0.36,
"learning_rate": 0.0004788674311858757,
"loss": 0.818,
"step": 201
},
{
"epoch": 0.36,
"learning_rate": 0.00047723274322743176,
"loss": 0.8423,
"step": 202
},
{
"epoch": 0.36,
"learning_rate": 0.00047559310642862737,
"loss": 0.8352,
"step": 203
},
{
"epoch": 0.36,
"learning_rate": 0.00047394857409140383,
"loss": 0.8056,
"step": 204
},
{
"epoch": 0.36,
"learning_rate": 0.00047229919967684887,
"loss": 0.8196,
"step": 205
},
{
"epoch": 0.37,
"learning_rate": 0.0004706450368034578,
"loss": 0.8858,
"step": 206
},
{
"epoch": 0.37,
"learning_rate": 0.00046898613924539154,
"loss": 0.8701,
"step": 207
},
{
"epoch": 0.37,
"learning_rate": 0.0004673225609307275,
"loss": 0.8912,
"step": 208
},
{
"epoch": 0.37,
"learning_rate": 0.00046565435593970737,
"loss": 0.8082,
"step": 209
},
{
"epoch": 0.37,
"learning_rate": 0.000463981578502978,
"loss": 0.8062,
"step": 210
},
{
"epoch": 0.37,
"learning_rate": 0.0004623042829998296,
"loss": 0.8533,
"step": 211
},
{
"epoch": 0.38,
"learning_rate": 0.00046062252395642723,
"loss": 0.7499,
"step": 212
},
{
"epoch": 0.38,
"learning_rate": 0.0004589363560440383,
"loss": 0.881,
"step": 213
},
{
"epoch": 0.38,
"learning_rate": 0.00045724583407725556,
"loss": 0.9066,
"step": 214
},
{
"epoch": 0.38,
"learning_rate": 0.0004555510130122151,
"loss": 0.7825,
"step": 215
},
{
"epoch": 0.38,
"learning_rate": 0.0004538519479448095,
"loss": 0.8257,
"step": 216
},
{
"epoch": 0.38,
"learning_rate": 0.00045214869410889724,
"loss": 0.7501,
"step": 217
},
{
"epoch": 0.39,
"learning_rate": 0.0004504413068745068,
"loss": 0.8188,
"step": 218
},
{
"epoch": 0.39,
"learning_rate": 0.0004487298417460368,
"loss": 0.8416,
"step": 219
},
{
"epoch": 0.39,
"learning_rate": 0.00044701435436045133,
"loss": 0.7909,
"step": 220
},
{
"epoch": 0.39,
"learning_rate": 0.0004452949004854722,
"loss": 0.8351,
"step": 221
},
{
"epoch": 0.39,
"learning_rate": 0.00044357153601776454,
"loss": 0.7758,
"step": 222
},
{
"epoch": 0.4,
"learning_rate": 0.0004418443169811211,
"loss": 0.8534,
"step": 223
},
{
"epoch": 0.4,
"learning_rate": 0.00044011329952464045,
"loss": 0.8572,
"step": 224
},
{
"epoch": 0.4,
"learning_rate": 0.00043837853992090124,
"loss": 0.8721,
"step": 225
},
{
"epoch": 0.4,
"learning_rate": 0.00043664009456413367,
"loss": 0.7843,
"step": 226
},
{
"epoch": 0.4,
"learning_rate": 0.0004348980199683856,
"loss": 0.8812,
"step": 227
},
{
"epoch": 0.4,
"learning_rate": 0.0004331523727656857,
"loss": 0.8069,
"step": 228
},
{
"epoch": 0.41,
"learning_rate": 0.0004314032097042021,
"loss": 0.7687,
"step": 229
},
{
"epoch": 0.41,
"learning_rate": 0.00042965058764639813,
"loss": 0.8415,
"step": 230
},
{
"epoch": 0.41,
"learning_rate": 0.00042789456356718343,
"loss": 0.7969,
"step": 231
},
{
"epoch": 0.41,
"learning_rate": 0.0004261351945520616,
"loss": 0.7946,
"step": 232
},
{
"epoch": 0.41,
"learning_rate": 0.00042437253779527485,
"loss": 0.7948,
"step": 233
},
{
"epoch": 0.42,
"learning_rate": 0.00042260665059794467,
"loss": 0.8782,
"step": 234
},
{
"epoch": 0.42,
"learning_rate": 0.0004208375903662087,
"loss": 0.7703,
"step": 235
},
{
"epoch": 0.42,
"learning_rate": 0.00041906541460935524,
"loss": 0.8175,
"step": 236
},
{
"epoch": 0.42,
"learning_rate": 0.0004172901809379527,
"loss": 0.8762,
"step": 237
},
{
"epoch": 0.42,
"learning_rate": 0.0004155119470619779,
"loss": 0.7611,
"step": 238
},
{
"epoch": 0.42,
"learning_rate": 0.00041373077078893887,
"loss": 0.8024,
"step": 239
},
{
"epoch": 0.43,
"learning_rate": 0.0004119467100219968,
"loss": 0.8315,
"step": 240
},
{
"epoch": 0.43,
"learning_rate": 0.0004101598227580827,
"loss": 0.8179,
"step": 241
},
{
"epoch": 0.43,
"learning_rate": 0.0004083701670860126,
"loss": 0.7895,
"step": 242
},
{
"epoch": 0.43,
"learning_rate": 0.0004065778011845991,
"loss": 0.8286,
"step": 243
},
{
"epoch": 0.43,
"learning_rate": 0.0004047827833207597,
"loss": 0.7763,
"step": 244
},
{
"epoch": 0.43,
"learning_rate": 0.0004029851718476232,
"loss": 0.8347,
"step": 245
},
{
"epoch": 0.44,
"learning_rate": 0.0004011850252026321,
"loss": 0.8407,
"step": 246
},
{
"epoch": 0.44,
"learning_rate": 0.0003993824019056437,
"loss": 0.6947,
"step": 247
},
{
"epoch": 0.44,
"learning_rate": 0.0003975773605570268,
"loss": 0.8137,
"step": 248
},
{
"epoch": 0.44,
"learning_rate": 0.0003957699598357574,
"loss": 0.7397,
"step": 249
},
{
"epoch": 0.44,
"learning_rate": 0.00039396025849751105,
"loss": 0.7993,
"step": 250
},
{
"epoch": 0.45,
"learning_rate": 0.0003921483153727521,
"loss": 0.8487,
"step": 251
},
{
"epoch": 0.45,
"learning_rate": 0.0003903341893648222,
"loss": 0.8079,
"step": 252
},
{
"epoch": 0.45,
"learning_rate": 0.00038851793944802497,
"loss": 0.8078,
"step": 253
},
{
"epoch": 0.45,
"learning_rate": 0.0003866996246657087,
"loss": 0.8757,
"step": 254
},
{
"epoch": 0.45,
"learning_rate": 0.0003848793041283472,
"loss": 0.8695,
"step": 255
},
{
"epoch": 0.45,
"learning_rate": 0.0003830570370116183,
"loss": 0.8306,
"step": 256
},
{
"epoch": 0.46,
"learning_rate": 0.0003812328825544796,
"loss": 0.7502,
"step": 257
},
{
"epoch": 0.46,
"learning_rate": 0.00037940690005724336,
"loss": 0.8467,
"step": 258
},
{
"epoch": 0.46,
"learning_rate": 0.0003775791488796486,
"loss": 0.7893,
"step": 259
},
{
"epoch": 0.46,
"learning_rate": 0.0003757496884389308,
"loss": 0.7922,
"step": 260
},
{
"epoch": 0.46,
"learning_rate": 0.00037391857820789123,
"loss": 0.8137,
"step": 261
},
{
"epoch": 0.46,
"learning_rate": 0.00037208587771296326,
"loss": 0.8322,
"step": 262
},
{
"epoch": 0.47,
"learning_rate": 0.00037025164653227676,
"loss": 0.8077,
"step": 263
},
{
"epoch": 0.47,
"learning_rate": 0.0003684159442937219,
"loss": 0.8906,
"step": 264
},
{
"epoch": 0.47,
"learning_rate": 0.0003665788306730106,
"loss": 0.8189,
"step": 265
},
{
"epoch": 0.47,
"learning_rate": 0.00036474036539173673,
"loss": 0.7934,
"step": 266
},
{
"epoch": 0.47,
"learning_rate": 0.00036290060821543406,
"loss": 0.8353,
"step": 267
},
{
"epoch": 0.48,
"learning_rate": 0.00036105961895163387,
"loss": 0.8887,
"step": 268
},
{
"epoch": 0.48,
"learning_rate": 0.00035921745744792096,
"loss": 0.8221,
"step": 269
},
{
"epoch": 0.48,
"learning_rate": 0.0003573741835899873,
"loss": 0.8948,
"step": 270
},
{
"epoch": 0.48,
"learning_rate": 0.0003555298572996861,
"loss": 0.8042,
"step": 271
},
{
"epoch": 0.48,
"learning_rate": 0.00035368453853308303,
"loss": 0.8296,
"step": 272
},
{
"epoch": 0.48,
"learning_rate": 0.00035183828727850804,
"loss": 0.809,
"step": 273
},
{
"epoch": 0.49,
"learning_rate": 0.0003499911635546043,
"loss": 0.7516,
"step": 274
},
{
"epoch": 0.49,
"learning_rate": 0.00034814322740837764,
"loss": 0.8407,
"step": 275
},
{
"epoch": 0.49,
"learning_rate": 0.0003462945389132449,
"loss": 0.7767,
"step": 276
},
{
"epoch": 0.49,
"learning_rate": 0.0003444451581670798,
"loss": 0.826,
"step": 277
},
{
"epoch": 0.49,
"learning_rate": 0.0003425951452902607,
"loss": 0.8608,
"step": 278
},
{
"epoch": 0.49,
"learning_rate": 0.0003407445604237151,
"loss": 0.8421,
"step": 279
},
{
"epoch": 0.5,
"learning_rate": 0.0003388934637269651,
"loss": 0.7686,
"step": 280
},
{
"epoch": 0.5,
"learning_rate": 0.0003370419153761715,
"loss": 0.7972,
"step": 281
},
{
"epoch": 0.5,
"learning_rate": 0.00033518997556217776,
"loss": 0.8238,
"step": 282
},
{
"epoch": 0.5,
"learning_rate": 0.00033333770448855317,
"loss": 0.7767,
"step": 283
},
{
"epoch": 0.5,
"learning_rate": 0.0003314851623696355,
"loss": 0.8312,
"step": 284
},
{
"epoch": 0.51,
"learning_rate": 0.00032963240942857416,
"loss": 0.7618,
"step": 285
},
{
"epoch": 0.51,
"learning_rate": 0.00032777950589537176,
"loss": 0.7653,
"step": 286
},
{
"epoch": 0.51,
"learning_rate": 0.00032592651200492634,
"loss": 0.8921,
"step": 287
},
{
"epoch": 0.51,
"learning_rate": 0.00032407348799507374,
"loss": 0.8412,
"step": 288
},
{
"epoch": 0.51,
"learning_rate": 0.0003222204941046283,
"loss": 0.787,
"step": 289
},
{
"epoch": 0.51,
"learning_rate": 0.00032036759057142586,
"loss": 0.7834,
"step": 290
},
{
"epoch": 0.52,
"learning_rate": 0.0003185148376303645,
"loss": 0.8221,
"step": 291
},
{
"epoch": 0.52,
"learning_rate": 0.00031666229551144685,
"loss": 0.8025,
"step": 292
},
{
"epoch": 0.52,
"learning_rate": 0.00031481002443782227,
"loss": 0.8136,
"step": 293
},
{
"epoch": 0.52,
"learning_rate": 0.0003129580846238285,
"loss": 0.8188,
"step": 294
},
{
"epoch": 0.52,
"learning_rate": 0.000311106536273035,
"loss": 0.7241,
"step": 295
},
{
"epoch": 0.53,
"learning_rate": 0.0003092554395762849,
"loss": 0.8234,
"step": 296
},
{
"epoch": 0.53,
"learning_rate": 0.0003074048547097393,
"loss": 0.8827,
"step": 297
},
{
"epoch": 0.53,
"learning_rate": 0.0003055548418329201,
"loss": 0.766,
"step": 298
},
{
"epoch": 0.53,
"learning_rate": 0.00030370546108675513,
"loss": 0.753,
"step": 299
},
{
"epoch": 0.53,
"learning_rate": 0.0003018567725916224,
"loss": 0.7767,
"step": 300
},
{
"epoch": 0.53,
"learning_rate": 0.0003000088364453958,
"loss": 0.7809,
"step": 301
},
{
"epoch": 0.54,
"learning_rate": 0.000298161712721492,
"loss": 0.8679,
"step": 302
},
{
"epoch": 0.54,
"learning_rate": 0.00029631546146691694,
"loss": 0.8464,
"step": 303
},
{
"epoch": 0.54,
"learning_rate": 0.00029447014270031393,
"loss": 0.7181,
"step": 304
},
{
"epoch": 0.54,
"learning_rate": 0.0002926258164100127,
"loss": 0.9354,
"step": 305
},
{
"epoch": 0.54,
"learning_rate": 0.00029078254255207906,
"loss": 0.8151,
"step": 306
},
{
"epoch": 0.54,
"learning_rate": 0.00028894038104836615,
"loss": 0.8382,
"step": 307
},
{
"epoch": 0.55,
"learning_rate": 0.000287099391784566,
"loss": 0.7495,
"step": 308
},
{
"epoch": 0.55,
"learning_rate": 0.0002852596346082633,
"loss": 0.8873,
"step": 309
},
{
"epoch": 0.55,
"learning_rate": 0.0002834211693269893,
"loss": 0.7534,
"step": 310
},
{
"epoch": 0.55,
"learning_rate": 0.0002815840557062782,
"loss": 0.7908,
"step": 311
},
{
"epoch": 0.55,
"learning_rate": 0.00027974835346772337,
"loss": 0.7738,
"step": 312
},
{
"epoch": 0.56,
"learning_rate": 0.00027791412228703676,
"loss": 0.7945,
"step": 313
},
{
"epoch": 0.56,
"learning_rate": 0.00027608142179210874,
"loss": 0.7678,
"step": 314
},
{
"epoch": 0.56,
"learning_rate": 0.00027425031156106923,
"loss": 0.8487,
"step": 315
},
{
"epoch": 0.56,
"learning_rate": 0.00027242085112035144,
"loss": 0.7736,
"step": 316
},
{
"epoch": 0.56,
"learning_rate": 0.0002705930999427566,
"loss": 0.8068,
"step": 317
},
{
"epoch": 0.56,
"learning_rate": 0.00026876711744552043,
"loss": 0.8051,
"step": 318
},
{
"epoch": 0.57,
"learning_rate": 0.00026694296298838174,
"loss": 0.7384,
"step": 319
},
{
"epoch": 0.57,
"learning_rate": 0.0002651206958716527,
"loss": 0.8203,
"step": 320
},
{
"epoch": 0.57,
"learning_rate": 0.00026330037533429127,
"loss": 0.7676,
"step": 321
},
{
"epoch": 0.57,
"learning_rate": 0.000261482060551975,
"loss": 0.7505,
"step": 322
},
{
"epoch": 0.57,
"learning_rate": 0.0002596658106351778,
"loss": 0.8522,
"step": 323
},
{
"epoch": 0.57,
"learning_rate": 0.000257851684627248,
"loss": 0.8943,
"step": 324
},
{
"epoch": 0.58,
"learning_rate": 0.00025603974150248903,
"loss": 0.8092,
"step": 325
},
{
"epoch": 0.58,
"learning_rate": 0.0002542300401642426,
"loss": 0.8543,
"step": 326
},
{
"epoch": 0.58,
"learning_rate": 0.0002524226394429732,
"loss": 0.8052,
"step": 327
},
{
"epoch": 0.58,
"learning_rate": 0.0002506175980943563,
"loss": 0.7748,
"step": 328
},
{
"epoch": 0.58,
"learning_rate": 0.00024881497479736786,
"loss": 0.784,
"step": 329
},
{
"epoch": 0.59,
"learning_rate": 0.0002470148281523768,
"loss": 0.7701,
"step": 330
},
{
"epoch": 0.59,
"learning_rate": 0.0002452172166792403,
"loss": 0.7336,
"step": 331
},
{
"epoch": 0.59,
"learning_rate": 0.00024342219881540086,
"loss": 0.7608,
"step": 332
},
{
"epoch": 0.59,
"learning_rate": 0.00024162983291398736,
"loss": 0.8646,
"step": 333
},
{
"epoch": 0.59,
"learning_rate": 0.00023984017724191725,
"loss": 0.7821,
"step": 334
},
{
"epoch": 0.59,
"learning_rate": 0.00023805328997800329,
"loss": 0.753,
"step": 335
},
{
"epoch": 0.6,
"learning_rate": 0.0002362692292110612,
"loss": 0.7984,
"step": 336
},
{
"epoch": 0.6,
"learning_rate": 0.00023448805293802222,
"loss": 0.7831,
"step": 337
},
{
"epoch": 0.6,
"learning_rate": 0.00023270981906204732,
"loss": 0.738,
"step": 338
},
{
"epoch": 0.6,
"learning_rate": 0.00023093458539064478,
"loss": 0.8652,
"step": 339
},
{
"epoch": 0.6,
"learning_rate": 0.00022916240963379128,
"loss": 0.7252,
"step": 340
},
{
"epoch": 0.6,
"learning_rate": 0.0002273933494020554,
"loss": 0.7484,
"step": 341
},
{
"epoch": 0.61,
"learning_rate": 0.00022562746220472518,
"loss": 0.7634,
"step": 342
},
{
"epoch": 0.61,
"learning_rate": 0.00022386480544793846,
"loss": 0.8458,
"step": 343
},
{
"epoch": 0.61,
"learning_rate": 0.00022210543643281656,
"loss": 0.7653,
"step": 344
},
{
"epoch": 0.61,
"learning_rate": 0.00022034941235360179,
"loss": 0.7125,
"step": 345
},
{
"epoch": 0.61,
"learning_rate": 0.00021859679029579784,
"loss": 0.7616,
"step": 346
},
{
"epoch": 0.62,
"learning_rate": 0.0002168476272343144,
"loss": 0.7459,
"step": 347
},
{
"epoch": 0.62,
"learning_rate": 0.00021510198003161447,
"loss": 0.8287,
"step": 348
},
{
"epoch": 0.62,
"learning_rate": 0.00021335990543586635,
"loss": 0.7626,
"step": 349
},
{
"epoch": 0.62,
"learning_rate": 0.00021162146007909881,
"loss": 0.6894,
"step": 350
},
{
"epoch": 0.62,
"learning_rate": 0.0002098867004753596,
"loss": 0.7187,
"step": 351
},
{
"epoch": 0.62,
"learning_rate": 0.00020815568301887888,
"loss": 0.7867,
"step": 352
},
{
"epoch": 0.63,
"learning_rate": 0.00020642846398223548,
"loss": 0.7222,
"step": 353
},
{
"epoch": 0.63,
"learning_rate": 0.0002047050995145278,
"loss": 0.8687,
"step": 354
},
{
"epoch": 0.63,
"learning_rate": 0.00020298564563954856,
"loss": 0.781,
"step": 355
},
{
"epoch": 0.63,
"learning_rate": 0.00020127015825396319,
"loss": 0.8546,
"step": 356
},
{
"epoch": 0.63,
"learning_rate": 0.00019955869312549316,
"loss": 0.8654,
"step": 357
},
{
"epoch": 0.64,
"learning_rate": 0.00019785130589110279,
"loss": 0.8679,
"step": 358
},
{
"epoch": 0.64,
"learning_rate": 0.00019614805205519055,
"loss": 0.7049,
"step": 359
},
{
"epoch": 0.64,
"learning_rate": 0.000194448986987785,
"loss": 0.7861,
"step": 360
},
{
"epoch": 0.64,
"learning_rate": 0.00019275416592274446,
"loss": 0.8216,
"step": 361
},
{
"epoch": 0.64,
"learning_rate": 0.0001910636439559618,
"loss": 0.7813,
"step": 362
},
{
"epoch": 0.64,
"learning_rate": 0.0001893774760435728,
"loss": 0.7393,
"step": 363
},
{
"epoch": 0.65,
"learning_rate": 0.0001876957170001704,
"loss": 0.8036,
"step": 364
},
{
"epoch": 0.65,
"learning_rate": 0.00018601842149702203,
"loss": 0.8428,
"step": 365
},
{
"epoch": 0.65,
"learning_rate": 0.00018434564406029258,
"loss": 0.7555,
"step": 366
},
{
"epoch": 0.65,
"learning_rate": 0.00018267743906927238,
"loss": 0.7521,
"step": 367
},
{
"epoch": 0.65,
"learning_rate": 0.00018101386075460843,
"loss": 0.7631,
"step": 368
},
{
"epoch": 0.65,
"learning_rate": 0.0001793549631965421,
"loss": 0.7697,
"step": 369
},
{
"epoch": 0.66,
"learning_rate": 0.00017770080032315127,
"loss": 0.7109,
"step": 370
},
{
"epoch": 0.66,
"learning_rate": 0.00017605142590859622,
"loss": 0.8004,
"step": 371
},
{
"epoch": 0.66,
"learning_rate": 0.00017440689357137265,
"loss": 0.7539,
"step": 372
},
{
"epoch": 0.66,
"learning_rate": 0.00017276725677256824,
"loss": 0.7791,
"step": 373
},
{
"epoch": 0.66,
"learning_rate": 0.00017113256881412428,
"loss": 0.7562,
"step": 374
},
{
"epoch": 0.67,
"learning_rate": 0.00016950288283710345,
"loss": 0.7569,
"step": 375
},
{
"epoch": 0.67,
"learning_rate": 0.00016787825181996193,
"loss": 0.7316,
"step": 376
},
{
"epoch": 0.67,
"learning_rate": 0.00016625872857682782,
"loss": 0.7922,
"step": 377
},
{
"epoch": 0.67,
"learning_rate": 0.00016464436575578314,
"loss": 0.779,
"step": 378
},
{
"epoch": 0.67,
"learning_rate": 0.00016303521583715312,
"loss": 0.757,
"step": 379
},
{
"epoch": 0.67,
"learning_rate": 0.00016143133113180028,
"loss": 0.7411,
"step": 380
},
{
"epoch": 0.68,
"learning_rate": 0.00015983276377942314,
"loss": 0.7369,
"step": 381
},
{
"epoch": 0.68,
"learning_rate": 0.00015823956574686192,
"loss": 0.754,
"step": 382
},
{
"epoch": 0.68,
"learning_rate": 0.00015665178882640884,
"loss": 0.7461,
"step": 383
},
{
"epoch": 0.68,
"learning_rate": 0.00015506948463412447,
"loss": 0.7724,
"step": 384
},
{
"epoch": 0.68,
"learning_rate": 0.00015349270460816004,
"loss": 0.8327,
"step": 385
},
{
"epoch": 0.68,
"learning_rate": 0.00015192150000708474,
"loss": 0.7992,
"step": 386
},
{
"epoch": 0.69,
"learning_rate": 0.0001503559219082202,
"loss": 0.7249,
"step": 387
},
{
"epoch": 0.69,
"learning_rate": 0.00014879602120597911,
"loss": 0.8001,
"step": 388
},
{
"epoch": 0.69,
"learning_rate": 0.0001472418486102113,
"loss": 0.7667,
"step": 389
},
{
"epoch": 0.69,
"learning_rate": 0.00014569345464455512,
"loss": 0.8302,
"step": 390
},
{
"epoch": 0.69,
"learning_rate": 0.00014415088964479526,
"loss": 0.8082,
"step": 391
},
{
"epoch": 0.7,
"learning_rate": 0.00014261420375722575,
"loss": 0.7399,
"step": 392
},
{
"epoch": 0.7,
"learning_rate": 0.00014108344693702026,
"loss": 0.7786,
"step": 393
},
{
"epoch": 0.7,
"learning_rate": 0.00013955866894660855,
"loss": 0.7507,
"step": 394
},
{
"epoch": 0.7,
"learning_rate": 0.00013803991935405755,
"loss": 0.8151,
"step": 395
},
{
"epoch": 0.7,
"learning_rate": 0.00013652724753146102,
"loss": 0.7722,
"step": 396
},
{
"epoch": 0.7,
"learning_rate": 0.00013502070265333462,
"loss": 0.7904,
"step": 397
},
{
"epoch": 0.71,
"learning_rate": 0.00013352033369501653,
"loss": 0.8405,
"step": 398
},
{
"epoch": 0.71,
"learning_rate": 0.00013202618943107576,
"loss": 0.7437,
"step": 399
},
{
"epoch": 0.71,
"learning_rate": 0.00013053831843372666,
"loss": 0.8447,
"step": 400
},
{
"epoch": 0.71,
"learning_rate": 0.00012905676907125005,
"loss": 0.7949,
"step": 401
},
{
"epoch": 0.71,
"learning_rate": 0.00012758158950642028,
"loss": 0.7259,
"step": 402
},
{
"epoch": 0.71,
"learning_rate": 0.00012611282769493999,
"loss": 0.7557,
"step": 403
},
{
"epoch": 0.72,
"learning_rate": 0.00012465053138388098,
"loss": 0.8465,
"step": 404
},
{
"epoch": 0.72,
"learning_rate": 0.0001231947481101325,
"loss": 0.7576,
"step": 405
},
{
"epoch": 0.72,
"learning_rate": 0.0001217455251988548,
"loss": 0.7945,
"step": 406
},
{
"epoch": 0.72,
"learning_rate": 0.0001203029097619417,
"loss": 0.7446,
"step": 407
},
{
"epoch": 0.72,
"learning_rate": 0.00011886694869648893,
"loss": 0.8205,
"step": 408
},
{
"epoch": 0.73,
"learning_rate": 0.00011743768868326904,
"loss": 0.7842,
"step": 409
},
{
"epoch": 0.73,
"learning_rate": 0.00011601517618521416,
"loss": 0.868,
"step": 410
},
{
"epoch": 0.73,
"learning_rate": 0.00011459945744590603,
"loss": 0.8414,
"step": 411
},
{
"epoch": 0.73,
"learning_rate": 0.00011319057848807186,
"loss": 0.7259,
"step": 412
},
{
"epoch": 0.73,
"learning_rate": 0.00011178858511208877,
"loss": 0.8071,
"step": 413
},
{
"epoch": 0.73,
"learning_rate": 0.00011039352289449466,
"loss": 0.8765,
"step": 414
},
{
"epoch": 0.74,
"learning_rate": 0.00010900543718650697,
"loss": 0.7724,
"step": 415
},
{
"epoch": 0.74,
"learning_rate": 0.00010762437311254777,
"loss": 0.7945,
"step": 416
},
{
"epoch": 0.74,
"learning_rate": 0.00010625037556877727,
"loss": 0.8228,
"step": 417
},
{
"epoch": 0.74,
"learning_rate": 0.00010488348922163421,
"loss": 0.7729,
"step": 418
},
{
"epoch": 0.74,
"learning_rate": 0.00010352375850638382,
"loss": 0.7894,
"step": 419
},
{
"epoch": 0.75,
"learning_rate": 0.00010217122762567324,
"loss": 0.7933,
"step": 420
},
{
"epoch": 0.75,
"learning_rate": 0.00010082594054809488,
"loss": 0.7888,
"step": 421
},
{
"epoch": 0.75,
"learning_rate": 9.948794100675652e-05,
"loss": 0.7749,
"step": 422
},
{
"epoch": 0.75,
"learning_rate": 9.815727249786008e-05,
"loss": 0.8214,
"step": 423
},
{
"epoch": 0.75,
"learning_rate": 9.683397827928737e-05,
"loss": 0.8181,
"step": 424
},
{
"epoch": 0.75,
"learning_rate": 9.55181013691941e-05,
"loss": 0.7482,
"step": 425
},
{
"epoch": 0.76,
"learning_rate": 9.420968454461113e-05,
"loss": 0.812,
"step": 426
},
{
"epoch": 0.76,
"learning_rate": 9.290877034005409e-05,
"loss": 0.7501,
"step": 427
},
{
"epoch": 0.76,
"learning_rate": 9.161540104614033e-05,
"loss": 0.8509,
"step": 428
},
{
"epoch": 0.76,
"learning_rate": 9.032961870821493e-05,
"loss": 0.7103,
"step": 429
},
{
"epoch": 0.76,
"learning_rate": 8.905146512498254e-05,
"loss": 0.7894,
"step": 430
},
{
"epoch": 0.76,
"learning_rate": 8.778098184714977e-05,
"loss": 0.7947,
"step": 431
},
{
"epoch": 0.77,
"learning_rate": 8.65182101760741e-05,
"loss": 0.7175,
"step": 432
},
{
"epoch": 0.77,
"learning_rate": 8.526319116242084e-05,
"loss": 0.774,
"step": 433
},
{
"epoch": 0.77,
"learning_rate": 8.401596560482902e-05,
"loss": 0.8459,
"step": 434
},
{
"epoch": 0.77,
"learning_rate": 8.277657404858523e-05,
"loss": 0.7551,
"step": 435
},
{
"epoch": 0.77,
"learning_rate": 8.154505678430514e-05,
"loss": 0.8399,
"step": 436
},
{
"epoch": 0.78,
"learning_rate": 8.032145384662393e-05,
"loss": 0.7648,
"step": 437
},
{
"epoch": 0.78,
"learning_rate": 7.91058050128947e-05,
"loss": 0.7743,
"step": 438
},
{
"epoch": 0.78,
"learning_rate": 7.789814980189591e-05,
"loss": 0.7609,
"step": 439
},
{
"epoch": 0.78,
"learning_rate": 7.669852747254598e-05,
"loss": 0.8661,
"step": 440
},
{
"epoch": 0.78,
"learning_rate": 7.550697702262705e-05,
"loss": 0.8407,
"step": 441
},
{
"epoch": 0.78,
"learning_rate": 7.432353718751805e-05,
"loss": 0.7823,
"step": 442
},
{
"epoch": 0.79,
"learning_rate": 7.314824643893467e-05,
"loss": 0.693,
"step": 443
},
{
"epoch": 0.79,
"learning_rate": 7.198114298367899e-05,
"loss": 0.8215,
"step": 444
},
{
"epoch": 0.79,
"learning_rate": 7.08222647623973e-05,
"loss": 0.7529,
"step": 445
},
{
"epoch": 0.79,
"learning_rate": 6.967164944834717e-05,
"loss": 0.7446,
"step": 446
},
{
"epoch": 0.79,
"learning_rate": 6.852933444617213e-05,
"loss": 0.728,
"step": 447
},
{
"epoch": 0.79,
"learning_rate": 6.739535689068595e-05,
"loss": 0.7269,
"step": 448
},
{
"epoch": 0.8,
"learning_rate": 6.626975364566577e-05,
"loss": 0.772,
"step": 449
},
{
"epoch": 0.8,
"learning_rate": 6.515256130265319e-05,
"loss": 0.79,
"step": 450
},
{
"epoch": 0.8,
"learning_rate": 6.404381617976511e-05,
"loss": 0.7689,
"step": 451
},
{
"epoch": 0.8,
"learning_rate": 6.29435543205129e-05,
"loss": 0.7993,
"step": 452
},
{
"epoch": 0.8,
"learning_rate": 6.18518114926307e-05,
"loss": 0.7223,
"step": 453
},
{
"epoch": 0.81,
"learning_rate": 6.07686231869128e-05,
"loss": 0.7739,
"step": 454
},
{
"epoch": 0.81,
"learning_rate": 5.9694024616059735e-05,
"loss": 0.7768,
"step": 455
},
{
"epoch": 0.81,
"learning_rate": 5.862805071353384e-05,
"loss": 0.7749,
"step": 456
},
{
"epoch": 0.81,
"learning_rate": 5.757073613242314e-05,
"loss": 0.8183,
"step": 457
},
{
"epoch": 0.81,
"learning_rate": 5.6522115244315215e-05,
"loss": 0.7616,
"step": 458
},
{
"epoch": 0.81,
"learning_rate": 5.548222213817996e-05,
"loss": 0.7366,
"step": 459
},
{
"epoch": 0.82,
"learning_rate": 5.445109061926091e-05,
"loss": 0.8308,
"step": 460
},
{
"epoch": 0.82,
"learning_rate": 5.3428754207976695e-05,
"loss": 0.8053,
"step": 461
},
{
"epoch": 0.82,
"learning_rate": 5.2415246138831057e-05,
"loss": 0.8413,
"step": 462
},
{
"epoch": 0.82,
"learning_rate": 5.141059935933293e-05,
"loss": 0.8198,
"step": 463
},
{
"epoch": 0.82,
"learning_rate": 5.041484652892487e-05,
"loss": 0.7564,
"step": 464
},
{
"epoch": 0.82,
"learning_rate": 4.9428020017921235e-05,
"loss": 0.783,
"step": 465
},
{
"epoch": 0.83,
"learning_rate": 4.84501519064567e-05,
"loss": 0.7834,
"step": 466
},
{
"epoch": 0.83,
"learning_rate": 4.7481273983442496e-05,
"loss": 0.7552,
"step": 467
},
{
"epoch": 0.83,
"learning_rate": 4.6521417745533556e-05,
"loss": 0.8159,
"step": 468
},
{
"epoch": 0.83,
"learning_rate": 4.557061439610419e-05,
"loss": 0.815,
"step": 469
},
{
"epoch": 0.83,
"learning_rate": 4.462889484423422e-05,
"loss": 0.7664,
"step": 470
},
{
"epoch": 0.84,
"learning_rate": 4.369628970370372e-05,
"loss": 0.8062,
"step": 471
},
{
"epoch": 0.84,
"learning_rate": 4.2772829291997916e-05,
"loss": 0.7135,
"step": 472
},
{
"epoch": 0.84,
"learning_rate": 4.1858543629321956e-05,
"loss": 0.7692,
"step": 473
},
{
"epoch": 0.84,
"learning_rate": 4.095346243762447e-05,
"loss": 0.7481,
"step": 474
},
{
"epoch": 0.84,
"learning_rate": 4.0057615139631764e-05,
"loss": 0.7913,
"step": 475
},
{
"epoch": 0.84,
"learning_rate": 3.9171030857891087e-05,
"loss": 0.7626,
"step": 476
},
{
"epoch": 0.85,
"learning_rate": 3.8293738413824065e-05,
"loss": 0.8227,
"step": 477
},
{
"epoch": 0.85,
"learning_rate": 3.742576632678971e-05,
"loss": 0.7575,
"step": 478
},
{
"epoch": 0.85,
"learning_rate": 3.656714281315718e-05,
"loss": 0.7689,
"step": 479
},
{
"epoch": 0.85,
"learning_rate": 3.571789578538891e-05,
"loss": 0.7818,
"step": 480
},
{
"epoch": 0.85,
"learning_rate": 3.487805285113266e-05,
"loss": 0.8032,
"step": 481
},
{
"epoch": 0.86,
"learning_rate": 3.404764131232438e-05,
"loss": 0.7684,
"step": 482
},
{
"epoch": 0.86,
"learning_rate": 3.322668816430062e-05,
"loss": 0.7989,
"step": 483
},
{
"epoch": 0.86,
"learning_rate": 3.241522009492107e-05,
"loss": 0.7373,
"step": 484
},
{
"epoch": 0.86,
"learning_rate": 3.161326348370065e-05,
"loss": 0.7821,
"step": 485
},
{
"epoch": 0.86,
"learning_rate": 3.082084440095212e-05,
"loss": 0.7874,
"step": 486
},
{
"epoch": 0.86,
"learning_rate": 3.003798860693901e-05,
"loss": 0.8324,
"step": 487
},
{
"epoch": 0.87,
"learning_rate": 2.9264721551037228e-05,
"loss": 0.784,
"step": 488
},
{
"epoch": 0.87,
"learning_rate": 2.8501068370908602e-05,
"loss": 0.7433,
"step": 489
},
{
"epoch": 0.87,
"learning_rate": 2.774705389168354e-05,
"loss": 0.7602,
"step": 490
},
{
"epoch": 0.87,
"learning_rate": 2.700270262515363e-05,
"loss": 0.8091,
"step": 491
},
{
"epoch": 0.87,
"learning_rate": 2.6268038768975084e-05,
"loss": 0.7597,
"step": 492
},
{
"epoch": 0.87,
"learning_rate": 2.554308620588212e-05,
"loss": 0.8004,
"step": 493
},
{
"epoch": 0.88,
"learning_rate": 2.482786850291056e-05,
"loss": 0.7236,
"step": 494
},
{
"epoch": 0.88,
"learning_rate": 2.4122408910631542e-05,
"loss": 0.765,
"step": 495
},
{
"epoch": 0.88,
"learning_rate": 2.342673036239589e-05,
"loss": 0.7404,
"step": 496
},
{
"epoch": 0.88,
"learning_rate": 2.2740855473588397e-05,
"loss": 0.7428,
"step": 497
},
{
"epoch": 0.88,
"learning_rate": 2.206480654089295e-05,
"loss": 0.8271,
"step": 498
},
{
"epoch": 0.89,
"learning_rate": 2.1398605541567217e-05,
"loss": 0.779,
"step": 499
},
{
"epoch": 0.89,
"learning_rate": 2.0742274132728692e-05,
"loss": 0.7889,
"step": 500
},
{
"epoch": 0.89,
"learning_rate": 2.009583365065032e-05,
"loss": 0.7518,
"step": 501
},
{
"epoch": 0.89,
"learning_rate": 1.945930511006707e-05,
"loss": 0.7648,
"step": 502
},
{
"epoch": 0.89,
"learning_rate": 1.8832709203492582e-05,
"loss": 0.8501,
"step": 503
},
{
"epoch": 0.89,
"learning_rate": 1.821606630054689e-05,
"loss": 0.8516,
"step": 504
},
{
"epoch": 0.9,
"learning_rate": 1.7609396447293742e-05,
"loss": 0.7832,
"step": 505
},
{
"epoch": 0.9,
"learning_rate": 1.7012719365589238e-05,
"loss": 0.729,
"step": 506
},
{
"epoch": 0.9,
"learning_rate": 1.6426054452440554e-05,
"loss": 0.7813,
"step": 507
},
{
"epoch": 0.9,
"learning_rate": 1.5849420779375678e-05,
"loss": 0.7223,
"step": 508
},
{
"epoch": 0.9,
"learning_rate": 1.5282837091822952e-05,
"loss": 0.7759,
"step": 509
},
{
"epoch": 0.9,
"learning_rate": 1.4726321808501993e-05,
"loss": 0.7515,
"step": 510
},
{
"epoch": 0.91,
"learning_rate": 1.4179893020825102e-05,
"loss": 0.7124,
"step": 511
},
{
"epoch": 0.91,
"learning_rate": 1.3643568492308522e-05,
"loss": 0.7751,
"step": 512
},
{
"epoch": 0.91,
"learning_rate": 1.3117365657995663e-05,
"loss": 0.7067,
"step": 513
},
{
"epoch": 0.91,
"learning_rate": 1.2601301623889924e-05,
"loss": 0.7627,
"step": 514
},
{
"epoch": 0.91,
"learning_rate": 1.2095393166398732e-05,
"loss": 0.773,
"step": 515
},
{
"epoch": 0.92,
"learning_rate": 1.1599656731788095e-05,
"loss": 0.8095,
"step": 516
},
{
"epoch": 0.92,
"learning_rate": 1.111410843564797e-05,
"loss": 0.7084,
"step": 517
},
{
"epoch": 0.92,
"learning_rate": 1.0638764062368558e-05,
"loss": 0.7333,
"step": 518
},
{
"epoch": 0.92,
"learning_rate": 1.0173639064626859e-05,
"loss": 0.8267,
"step": 519
},
{
"epoch": 0.92,
"learning_rate": 9.718748562884593e-06,
"loss": 0.8025,
"step": 520
},
{
"epoch": 0.92,
"learning_rate": 9.274107344896458e-06,
"loss": 0.7545,
"step": 521
},
{
"epoch": 0.93,
"learning_rate": 8.839729865229709e-06,
"loss": 0.7147,
"step": 522
},
{
"epoch": 0.93,
"learning_rate": 8.415630244793775e-06,
"loss": 0.7924,
"step": 523
},
{
"epoch": 0.93,
"learning_rate": 8.001822270381742e-06,
"loss": 0.69,
"step": 524
},
{
"epoch": 0.93,
"learning_rate": 7.598319394221836e-06,
"loss": 0.7302,
"step": 525
},
{
"epoch": 0.93,
"learning_rate": 7.205134733540189e-06,
"loss": 0.7277,
"step": 526
},
{
"epoch": 0.93,
"learning_rate": 6.8222810701344115e-06,
"loss": 0.7564,
"step": 527
},
{
"epoch": 0.94,
"learning_rate": 6.449770849958183e-06,
"loss": 0.7483,
"step": 528
},
{
"epoch": 0.94,
"learning_rate": 6.087616182716479e-06,
"loss": 0.7625,
"step": 529
},
{
"epoch": 0.94,
"learning_rate": 5.735828841471985e-06,
"loss": 0.7093,
"step": 530
},
{
"epoch": 0.94,
"learning_rate": 5.394420262262409e-06,
"loss": 0.7784,
"step": 531
},
{
"epoch": 0.94,
"learning_rate": 5.063401543728799e-06,
"loss": 0.8202,
"step": 532
},
{
"epoch": 0.95,
"learning_rate": 4.742783446754395e-06,
"loss": 0.7911,
"step": 533
},
{
"epoch": 0.95,
"learning_rate": 4.432576394115245e-06,
"loss": 0.8275,
"step": 534
},
{
"epoch": 0.95,
"learning_rate": 4.132790470141067e-06,
"loss": 0.7592,
"step": 535
},
{
"epoch": 0.95,
"learning_rate": 3.843435420387589e-06,
"loss": 0.7312,
"step": 536
},
{
"epoch": 0.95,
"learning_rate": 3.564520651319633e-06,
"loss": 0.7597,
"step": 537
},
{
"epoch": 0.95,
"learning_rate": 3.2960552300054317e-06,
"loss": 0.7804,
"step": 538
},
{
"epoch": 0.96,
"learning_rate": 3.0380478838218343e-06,
"loss": 0.7629,
"step": 539
},
{
"epoch": 0.96,
"learning_rate": 2.7905070001704834e-06,
"loss": 0.7091,
"step": 540
},
{
"epoch": 0.96,
"learning_rate": 2.55344062620525e-06,
"loss": 0.778,
"step": 541
},
{
"epoch": 0.96,
"learning_rate": 2.3268564685707814e-06,
"loss": 0.7255,
"step": 542
},
{
"epoch": 0.96,
"learning_rate": 2.1107618931516578e-06,
"loss": 0.7048,
"step": 543
},
{
"epoch": 0.97,
"learning_rate": 1.9051639248331308e-06,
"loss": 0.8423,
"step": 544
},
{
"epoch": 0.97,
"learning_rate": 1.710069247272794e-06,
"loss": 0.8129,
"step": 545
},
{
"epoch": 0.97,
"learning_rate": 1.5254842026831887e-06,
"loss": 0.7584,
"step": 546
},
{
"epoch": 0.97,
"learning_rate": 1.3514147916256658e-06,
"loss": 0.8424,
"step": 547
},
{
"epoch": 0.97,
"learning_rate": 1.1878666728153602e-06,
"loss": 0.8064,
"step": 548
},
{
"epoch": 0.97,
"learning_rate": 1.034845162937209e-06,
"loss": 0.8401,
"step": 549
},
{
"epoch": 0.98,
"learning_rate": 8.923552364730802e-07,
"loss": 0.7696,
"step": 550
}
],
"logging_steps": 1,
"max_steps": 563,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"total_flos": 8.340480143128166e+17,
"train_batch_size": 3,
"trial_name": null,
"trial_params": null
}