{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 295,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 0.0001111111111111111,
"loss": 2.2793,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 0.0002222222222222222,
"loss": 2.2853,
"step": 2
},
{
"epoch": 0.05,
"learning_rate": 0.0003333333333333333,
"loss": 1.9982,
"step": 3
},
{
"epoch": 0.07,
"learning_rate": 0.0004444444444444444,
"loss": 1.7452,
"step": 4
},
{
"epoch": 0.08,
"learning_rate": 0.0005555555555555556,
"loss": 1.4194,
"step": 5
},
{
"epoch": 0.1,
"learning_rate": 0.0006666666666666666,
"loss": 1.3396,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 0.0007777777777777778,
"loss": 1.3332,
"step": 7
},
{
"epoch": 0.14,
"learning_rate": 0.0008888888888888888,
"loss": 1.2855,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.2143,
"step": 9
},
{
"epoch": 0.17,
"learning_rate": 0.0009999698350006063,
"loss": 1.087,
"step": 10
},
{
"epoch": 0.19,
"learning_rate": 0.000999879343642134,
"loss": 1.0377,
"step": 11
},
{
"epoch": 0.2,
"learning_rate": 0.0009997285368432702,
"loss": 1.2128,
"step": 12
},
{
"epoch": 0.22,
"learning_rate": 0.000999517432800363,
"loss": 1.0801,
"step": 13
},
{
"epoch": 0.24,
"learning_rate": 0.0009992460569852254,
"loss": 0.848,
"step": 14
},
{
"epoch": 0.25,
"learning_rate": 0.000998914442142063,
"loss": 0.8885,
"step": 15
},
{
"epoch": 0.27,
"learning_rate": 0.0009985226282835215,
"loss": 0.8587,
"step": 16
},
{
"epoch": 0.29,
"learning_rate": 0.0009980706626858606,
"loss": 0.8086,
"step": 17
},
{
"epoch": 0.31,
"learning_rate": 0.0009975585998832478,
"loss": 0.8043,
"step": 18
},
{
"epoch": 0.32,
"learning_rate": 0.00099698650166118,
"loss": 0.7563,
"step": 19
},
{
"epoch": 0.34,
"learning_rate": 0.000996354437049027,
"loss": 0.723,
"step": 20
},
{
"epoch": 0.36,
"learning_rate": 0.0009956624823117036,
"loss": 0.7343,
"step": 21
},
{
"epoch": 0.37,
"learning_rate": 0.0009949107209404665,
"loss": 0.693,
"step": 22
},
{
"epoch": 0.39,
"learning_rate": 0.000994099243642841,
"loss": 0.6227,
"step": 23
},
{
"epoch": 0.41,
"learning_rate": 0.0009932281483316758,
"loss": 0.6093,
"step": 24
},
{
"epoch": 0.42,
"learning_rate": 0.0009922975401133291,
"loss": 0.6365,
"step": 25
},
{
"epoch": 0.44,
"learning_rate": 0.0009913075312749865,
"loss": 0.5727,
"step": 26
},
{
"epoch": 0.46,
"learning_rate": 0.000990258241271112,
"loss": 0.3922,
"step": 27
},
{
"epoch": 0.47,
"learning_rate": 0.0009891497967090344,
"loss": 0.5033,
"step": 28
},
{
"epoch": 0.49,
"learning_rate": 0.0009879823313336722,
"loss": 0.5103,
"step": 29
},
{
"epoch": 0.51,
"learning_rate": 0.000986755986011395,
"loss": 0.4317,
"step": 30
},
{
"epoch": 0.53,
"learning_rate": 0.000985470908713026,
"loss": 0.4054,
"step": 31
},
{
"epoch": 0.54,
"learning_rate": 0.0009841272544959892,
"loss": 0.361,
"step": 32
},
{
"epoch": 0.56,
"learning_rate": 0.0009827251854855992,
"loss": 0.4515,
"step": 33
},
{
"epoch": 0.58,
"learning_rate": 0.000981264870855499,
"loss": 0.3893,
"step": 34
},
{
"epoch": 0.59,
"learning_rate": 0.0009797464868072487,
"loss": 0.332,
"step": 35
},
{
"epoch": 0.61,
"learning_rate": 0.0009781702165490638,
"loss": 0.3706,
"step": 36
},
{
"epoch": 0.63,
"learning_rate": 0.0009765362502737097,
"loss": 0.3606,
"step": 37
},
{
"epoch": 0.64,
"learning_rate": 0.0009748447851355535,
"loss": 0.3067,
"step": 38
},
{
"epoch": 0.66,
"learning_rate": 0.0009730960252267743,
"loss": 0.2683,
"step": 39
},
{
"epoch": 0.68,
"learning_rate": 0.0009712901815527386,
"loss": 0.3499,
"step": 40
},
{
"epoch": 0.69,
"learning_rate": 0.0009694274720065399,
"loss": 0.3047,
"step": 41
},
{
"epoch": 0.71,
"learning_rate": 0.0009675081213427075,
"loss": 0.334,
"step": 42
},
{
"epoch": 0.73,
"learning_rate": 0.0009655323611500874,
"loss": 0.252,
"step": 43
},
{
"epoch": 0.75,
"learning_rate": 0.0009635004298239003,
"loss": 0.2929,
"step": 44
},
{
"epoch": 0.76,
"learning_rate": 0.0009614125725369747,
"loss": 0.2636,
"step": 45
},
{
"epoch": 0.78,
"learning_rate": 0.0009592690412101658,
"loss": 0.2265,
"step": 46
},
{
"epoch": 0.8,
"learning_rate": 0.0009570700944819584,
"loss": 0.2842,
"step": 47
},
{
"epoch": 0.81,
"learning_rate": 0.0009548159976772592,
"loss": 0.3006,
"step": 48
},
{
"epoch": 0.83,
"learning_rate": 0.0009525070227753834,
"loss": 0.2884,
"step": 49
},
{
"epoch": 0.85,
"learning_rate": 0.0009501434483772371,
"loss": 0.2627,
"step": 50
},
{
"epoch": 0.86,
"learning_rate": 0.0009477255596717012,
"loss": 0.2446,
"step": 51
},
{
"epoch": 0.88,
"learning_rate": 0.0009452536484012212,
"loss": 0.1926,
"step": 52
},
{
"epoch": 0.9,
"learning_rate": 0.0009427280128266049,
"loss": 0.2356,
"step": 53
},
{
"epoch": 0.92,
"learning_rate": 0.0009401489576910349,
"loss": 0.2356,
"step": 54
},
{
"epoch": 0.93,
"learning_rate": 0.0009375167941832973,
"loss": 0.2395,
"step": 55
},
{
"epoch": 0.95,
"learning_rate": 0.0009348318399002345,
"loss": 0.2681,
"step": 56
},
{
"epoch": 0.97,
"learning_rate": 0.0009320944188084242,
"loss": 0.2252,
"step": 57
},
{
"epoch": 0.98,
"learning_rate": 0.0009293048612050883,
"loss": 0.1862,
"step": 58
},
{
"epoch": 1.0,
"learning_rate": 0.0009264635036782405,
"loss": 0.2215,
"step": 59
},
{
"epoch": 1.02,
"learning_rate": 0.0009235706890660734,
"loss": 0.1712,
"step": 60
},
{
"epoch": 1.03,
"learning_rate": 0.0009206267664155906,
"loss": 0.2162,
"step": 61
},
{
"epoch": 1.05,
"learning_rate": 0.0009176320909404924,
"loss": 0.1684,
"step": 62
},
{
"epoch": 1.07,
"learning_rate": 0.0009145870239783141,
"loss": 0.1432,
"step": 63
},
{
"epoch": 1.08,
"learning_rate": 0.0009114919329468282,
"loss": 0.1798,
"step": 64
},
{
"epoch": 1.1,
"learning_rate": 0.0009083471912997109,
"loss": 0.1961,
"step": 65
},
{
"epoch": 1.12,
"learning_rate": 0.0009051531784814817,
"loss": 0.2043,
"step": 66
},
{
"epoch": 1.14,
"learning_rate": 0.0009019102798817196,
"loss": 0.1493,
"step": 67
},
{
"epoch": 1.15,
"learning_rate": 0.0008986188867885616,
"loss": 0.1943,
"step": 68
},
{
"epoch": 1.17,
"learning_rate": 0.0008952793963414907,
"loss": 0.1955,
"step": 69
},
{
"epoch": 1.19,
"learning_rate": 0.0008918922114834156,
"loss": 0.194,
"step": 70
},
{
"epoch": 1.2,
"learning_rate": 0.0008884577409120535,
"loss": 0.1765,
"step": 71
},
{
"epoch": 1.22,
"learning_rate": 0.0008849763990306152,
"loss": 0.1608,
"step": 72
},
{
"epoch": 1.24,
"learning_rate": 0.0008814486058978035,
"loss": 0.1596,
"step": 73
},
{
"epoch": 1.25,
"learning_rate": 0.0008778747871771292,
"loss": 0.1756,
"step": 74
},
{
"epoch": 1.27,
"learning_rate": 0.0008742553740855505,
"loss": 0.1507,
"step": 75
},
{
"epoch": 1.29,
"learning_rate": 0.0008705908033414425,
"loss": 0.1243,
"step": 76
},
{
"epoch": 1.31,
"learning_rate": 0.000866881517111902,
"loss": 0.1431,
"step": 77
},
{
"epoch": 1.32,
"learning_rate": 0.0008631279629593967,
"loss": 0.1358,
"step": 78
},
{
"epoch": 1.34,
"learning_rate": 0.0008593305937877613,
"loss": 0.1452,
"step": 79
},
{
"epoch": 1.36,
"learning_rate": 0.0008554898677875509,
"loss": 0.1239,
"step": 80
},
{
"epoch": 1.37,
"learning_rate": 0.0008516062483807555,
"loss": 0.1566,
"step": 81
},
{
"epoch": 1.39,
"learning_rate": 0.0008476802041648832,
"loss": 0.1353,
"step": 82
},
{
"epoch": 1.41,
"learning_rate": 0.0008437122088564197,
"loss": 0.1023,
"step": 83
},
{
"epoch": 1.42,
"learning_rate": 0.0008397027412336691,
"loss": 0.1386,
"step": 84
},
{
"epoch": 1.44,
"learning_rate": 0.0008356522850789851,
"loss": 0.1315,
"step": 85
},
{
"epoch": 1.46,
"learning_rate": 0.0008315613291203976,
"loss": 0.1285,
"step": 86
},
{
"epoch": 1.47,
"learning_rate": 0.0008274303669726426,
"loss": 0.1482,
"step": 87
},
{
"epoch": 1.49,
"learning_rate": 0.0008232598970776028,
"loss": 0.1012,
"step": 88
},
{
"epoch": 1.51,
"learning_rate": 0.0008190504226441654,
"loss": 0.1552,
"step": 89
},
{
"epoch": 1.53,
"learning_rate": 0.0008148024515875057,
"loss": 0.1133,
"step": 90
},
{
"epoch": 1.54,
"learning_rate": 0.0008105164964678008,
"loss": 0.1246,
"step": 91
},
{
"epoch": 1.56,
"learning_rate": 0.0008061930744283854,
"loss": 0.124,
"step": 92
},
{
"epoch": 1.58,
"learning_rate": 0.0008018327071333521,
"loss": 0.1149,
"step": 93
},
{
"epoch": 1.59,
"learning_rate": 0.000797435920704608,
"loss": 0.1231,
"step": 94
},
{
"epoch": 1.61,
"learning_rate": 0.0007930032456583931,
"loss": 0.1335,
"step": 95
},
{
"epoch": 1.63,
"learning_rate": 0.0007885352168412676,
"loss": 0.1132,
"step": 96
},
{
"epoch": 1.64,
"learning_rate": 0.0007840323733655779,
"loss": 0.1233,
"step": 97
},
{
"epoch": 1.66,
"learning_rate": 0.0007794952585444068,
"loss": 0.1224,
"step": 98
},
{
"epoch": 1.68,
"learning_rate": 0.0007749244198260175,
"loss": 0.1014,
"step": 99
},
{
"epoch": 1.69,
"learning_rate": 0.0007703204087277988,
"loss": 0.1046,
"step": 100
},
{
"epoch": 1.71,
"learning_rate": 0.0007656837807697187,
"loss": 0.1291,
"step": 101
},
{
"epoch": 1.73,
"learning_rate": 0.0007610150954072952,
"loss": 0.1085,
"step": 102
},
{
"epoch": 1.75,
"learning_rate": 0.0007563149159640929,
"loss": 0.0982,
"step": 103
},
{
"epoch": 1.76,
"learning_rate": 0.000751583809563752,
"loss": 0.1024,
"step": 104
},
{
"epoch": 1.78,
"learning_rate": 0.0007468223470615592,
"loss": 0.1017,
"step": 105
},
{
"epoch": 1.8,
"learning_rate": 0.0007420311029755687,
"loss": 0.0854,
"step": 106
},
{
"epoch": 1.81,
"learning_rate": 0.0007372106554172802,
"loss": 0.1233,
"step": 107
},
{
"epoch": 1.83,
"learning_rate": 0.0007323615860218843,
"loss": 0.1052,
"step": 108
},
{
"epoch": 1.85,
"learning_rate": 0.0007274844798780825,
"loss": 0.1145,
"step": 109
},
{
"epoch": 1.86,
"learning_rate": 0.0007225799254574904,
"loss": 0.0964,
"step": 110
},
{
"epoch": 1.88,
"learning_rate": 0.0007176485145436324,
"loss": 0.1058,
"step": 111
},
{
"epoch": 1.9,
"learning_rate": 0.0007126908421605375,
"loss": 0.1114,
"step": 112
},
{
"epoch": 1.92,
"learning_rate": 0.0007077075065009433,
"loss": 0.1143,
"step": 113
},
{
"epoch": 1.93,
"learning_rate": 0.0007026991088541184,
"loss": 0.0994,
"step": 114
},
{
"epoch": 1.95,
"learning_rate": 0.0006976662535333107,
"loss": 0.0954,
"step": 115
},
{
"epoch": 1.97,
"learning_rate": 0.0006926095478028312,
"loss": 0.0941,
"step": 116
},
{
"epoch": 1.98,
"learning_rate": 0.000687529601804781,
"loss": 0.1026,
"step": 117
},
{
"epoch": 2.0,
"learning_rate": 0.0006824270284854318,
"loss": 0.0884,
"step": 118
},
{
"epoch": 2.02,
"learning_rate": 0.0006773024435212678,
"loss": 0.0958,
"step": 119
},
{
"epoch": 2.03,
"learning_rate": 0.0006721564652446986,
"loss": 0.0869,
"step": 120
},
{
"epoch": 2.05,
"learning_rate": 0.0006669897145694507,
"loss": 0.0929,
"step": 121
},
{
"epoch": 2.07,
"learning_rate": 0.0006618028149156478,
"loss": 0.0858,
"step": 122
},
{
"epoch": 2.08,
"learning_rate": 0.0006565963921345895,
"loss": 0.0833,
"step": 123
},
{
"epoch": 2.1,
"learning_rate": 0.000651371074433236,
"loss": 0.093,
"step": 124
},
{
"epoch": 2.12,
"learning_rate": 0.0006461274922984087,
"loss": 0.0954,
"step": 125
},
{
"epoch": 2.14,
"learning_rate": 0.0006408662784207149,
"loss": 0.079,
"step": 126
},
{
"epoch": 2.15,
"learning_rate": 0.0006355880676182085,
"loss": 0.0794,
"step": 127
},
{
"epoch": 2.17,
"learning_rate": 0.0006302934967597922,
"loss": 0.0765,
"step": 128
},
{
"epoch": 2.19,
"learning_rate": 0.0006249832046883729,
"loss": 0.0811,
"step": 129
},
{
"epoch": 2.2,
"learning_rate": 0.0006196578321437789,
"loss": 0.077,
"step": 130
},
{
"epoch": 2.22,
"learning_rate": 0.0006143180216854487,
"loss": 0.0825,
"step": 131
},
{
"epoch": 2.24,
"learning_rate": 0.0006089644176148992,
"loss": 0.0878,
"step": 132
},
{
"epoch": 2.25,
"learning_rate": 0.0006035976658979846,
"loss": 0.089,
"step": 133
},
{
"epoch": 2.27,
"learning_rate": 0.0005982184140869538,
"loss": 0.0748,
"step": 134
},
{
"epoch": 2.29,
"learning_rate": 0.0005928273112423177,
"loss": 0.0811,
"step": 135
},
{
"epoch": 2.31,
"learning_rate": 0.0005874250078545323,
"loss": 0.0825,
"step": 136
},
{
"epoch": 2.32,
"learning_rate": 0.000582012155765511,
"loss": 0.0866,
"step": 137
},
{
"epoch": 2.34,
"learning_rate": 0.000576589408089974,
"loss": 0.0818,
"step": 138
},
{
"epoch": 2.36,
"learning_rate": 0.0005711574191366427,
"loss": 0.0961,
"step": 139
},
{
"epoch": 2.37,
"learning_rate": 0.0005657168443292908,
"loss": 0.0767,
"step": 140
},
{
"epoch": 2.39,
"learning_rate": 0.0005602683401276614,
"loss": 0.0719,
"step": 141
},
{
"epoch": 2.41,
"learning_rate": 0.0005548125639482587,
"loss": 0.0747,
"step": 142
},
{
"epoch": 2.42,
"learning_rate": 0.0005493501740850228,
"loss": 0.0836,
"step": 143
},
{
"epoch": 2.44,
"learning_rate": 0.0005438818296299015,
"loss": 0.0823,
"step": 144
},
{
"epoch": 2.46,
"learning_rate": 0.0005384081903933235,
"loss": 0.0789,
"step": 145
},
{
"epoch": 2.47,
"learning_rate": 0.0005329299168245857,
"loss": 0.0788,
"step": 146
},
{
"epoch": 2.49,
"learning_rate": 0.0005274476699321638,
"loss": 0.0857,
"step": 147
},
{
"epoch": 2.51,
"learning_rate": 0.0005219621112039544,
"loss": 0.0828,
"step": 148
},
{
"epoch": 2.53,
"learning_rate": 0.0005164739025274604,
"loss": 0.083,
"step": 149
},
{
"epoch": 2.54,
"learning_rate": 0.0005109837061099274,
"loss": 0.0916,
"step": 150
},
{
"epoch": 2.56,
"learning_rate": 0.0005054921843984418,
"loss": 0.0813,
"step": 151
},
{
"epoch": 2.58,
"learning_rate": 0.0005,
"loss": 0.0714,
"step": 152
},
{
"epoch": 2.59,
"learning_rate": 0.0004945078156015581,
"loss": 0.0741,
"step": 153
},
{
"epoch": 2.61,
"learning_rate": 0.0004890162938900726,
"loss": 0.0839,
"step": 154
},
{
"epoch": 2.63,
"learning_rate": 0.00048352609747253966,
"loss": 0.0725,
"step": 155
},
{
"epoch": 2.64,
"learning_rate": 0.0004780378887960458,
"loss": 0.0843,
"step": 156
},
{
"epoch": 2.66,
"learning_rate": 0.0004725523300678363,
"loss": 0.106,
"step": 157
},
{
"epoch": 2.68,
"learning_rate": 0.00046707008317541446,
"loss": 0.0715,
"step": 158
},
{
"epoch": 2.69,
"learning_rate": 0.0004615918096066766,
"loss": 0.0787,
"step": 159
},
{
"epoch": 2.71,
"learning_rate": 0.00045611817037009855,
"loss": 0.0786,
"step": 160
},
{
"epoch": 2.73,
"learning_rate": 0.0004506498259149773,
"loss": 0.0752,
"step": 161
},
{
"epoch": 2.75,
"learning_rate": 0.0004451874360517413,
"loss": 0.0771,
"step": 162
},
{
"epoch": 2.76,
"learning_rate": 0.00043973165987233853,
"loss": 0.0704,
"step": 163
},
{
"epoch": 2.78,
"learning_rate": 0.0004342831556707093,
"loss": 0.0737,
"step": 164
},
{
"epoch": 2.8,
"learning_rate": 0.0004288425808633575,
"loss": 0.0711,
"step": 165
},
{
"epoch": 2.81,
"learning_rate": 0.00042341059191002613,
"loss": 0.0796,
"step": 166
},
{
"epoch": 2.83,
"learning_rate": 0.0004179878442344892,
"loss": 0.0753,
"step": 167
},
{
"epoch": 2.85,
"learning_rate": 0.0004125749921454679,
"loss": 0.0787,
"step": 168
},
{
"epoch": 2.86,
"learning_rate": 0.00040717268875768226,
"loss": 0.0765,
"step": 169
},
{
"epoch": 2.88,
"learning_rate": 0.00040178158591304614,
"loss": 0.074,
"step": 170
},
{
"epoch": 2.9,
"learning_rate": 0.00039640233410201555,
"loss": 0.0747,
"step": 171
},
{
"epoch": 2.92,
"learning_rate": 0.00039103558238510084,
"loss": 0.0779,
"step": 172
},
{
"epoch": 2.93,
"learning_rate": 0.00038568197831455135,
"loss": 0.0821,
"step": 173
},
{
"epoch": 2.95,
"learning_rate": 0.00038034216785622126,
"loss": 0.0796,
"step": 174
},
{
"epoch": 2.97,
"learning_rate": 0.0003750167953116272,
"loss": 0.0661,
"step": 175
},
{
"epoch": 2.98,
"learning_rate": 0.00036970650324020783,
"loss": 0.0725,
"step": 176
},
{
"epoch": 3.0,
"learning_rate": 0.0003644119323817915,
"loss": 0.0756,
"step": 177
},
{
"epoch": 3.02,
"learning_rate": 0.0003591337215792851,
"loss": 0.0635,
"step": 178
},
{
"epoch": 3.03,
"learning_rate": 0.0003538725077015915,
"loss": 0.0698,
"step": 179
},
{
"epoch": 3.05,
"learning_rate": 0.00034862892556676393,
"loss": 0.0875,
"step": 180
},
{
"epoch": 3.07,
"learning_rate": 0.0003434036078654106,
"loss": 0.0675,
"step": 181
},
{
"epoch": 3.08,
"learning_rate": 0.0003381971850843523,
"loss": 0.071,
"step": 182
},
{
"epoch": 3.1,
"learning_rate": 0.0003330102854305493,
"loss": 0.0675,
"step": 183
},
{
"epoch": 3.12,
"learning_rate": 0.00032784353475530137,
"loss": 0.0689,
"step": 184
},
{
"epoch": 3.14,
"learning_rate": 0.00032269755647873217,
"loss": 0.0711,
"step": 185
},
{
"epoch": 3.15,
"learning_rate": 0.0003175729715145684,
"loss": 0.0692,
"step": 186
},
{
"epoch": 3.17,
"learning_rate": 0.00031247039819521906,
"loss": 0.0718,
"step": 187
},
{
"epoch": 3.19,
"learning_rate": 0.00030739045219716887,
"loss": 0.0769,
"step": 188
},
{
"epoch": 3.2,
"learning_rate": 0.0003023337464666893,
"loss": 0.0703,
"step": 189
},
{
"epoch": 3.22,
"learning_rate": 0.0002973008911458816,
"loss": 0.0793,
"step": 190
},
{
"epoch": 3.24,
"learning_rate": 0.0002922924934990568,
"loss": 0.0681,
"step": 191
},
{
"epoch": 3.25,
"learning_rate": 0.0002873091578394626,
"loss": 0.07,
"step": 192
},
{
"epoch": 3.27,
"learning_rate": 0.0002823514854563677,
"loss": 0.0667,
"step": 193
},
{
"epoch": 3.29,
"learning_rate": 0.0002774200745425096,
"loss": 0.0718,
"step": 194
},
{
"epoch": 3.31,
"learning_rate": 0.0002725155201219176,
"loss": 0.071,
"step": 195
},
{
"epoch": 3.32,
"learning_rate": 0.00026763841397811573,
"loss": 0.0697,
"step": 196
},
{
"epoch": 3.34,
"learning_rate": 0.00026278934458272,
"loss": 0.0633,
"step": 197
},
{
"epoch": 3.36,
"learning_rate": 0.00025796889702443126,
"loss": 0.0616,
"step": 198
},
{
"epoch": 3.37,
"learning_rate": 0.0002531776529384407,
"loss": 0.0653,
"step": 199
},
{
"epoch": 3.39,
"learning_rate": 0.0002484161904362481,
"loss": 0.0674,
"step": 200
},
{
"epoch": 3.41,
"learning_rate": 0.00024368508403590727,
"loss": 0.071,
"step": 201
},
{
"epoch": 3.42,
"learning_rate": 0.0002389849045927049,
"loss": 0.065,
"step": 202
},
{
"epoch": 3.44,
"learning_rate": 0.00023431621923028145,
"loss": 0.0657,
"step": 203
},
{
"epoch": 3.46,
"learning_rate": 0.0002296795912722014,
"loss": 0.0708,
"step": 204
},
{
"epoch": 3.47,
"learning_rate": 0.0002250755801739826,
"loss": 0.0666,
"step": 205
},
{
"epoch": 3.49,
"learning_rate": 0.00022050474145559324,
"loss": 0.0643,
"step": 206
},
{
"epoch": 3.51,
"learning_rate": 0.00021596762663442215,
"loss": 0.0622,
"step": 207
},
{
"epoch": 3.53,
"learning_rate": 0.00021146478315873236,
"loss": 0.0651,
"step": 208
},
{
"epoch": 3.54,
"learning_rate": 0.00020699675434160698,
"loss": 0.0712,
"step": 209
},
{
"epoch": 3.56,
"learning_rate": 0.000202564079295392,
"loss": 0.0662,
"step": 210
},
{
"epoch": 3.58,
"learning_rate": 0.00019816729286664797,
"loss": 0.0712,
"step": 211
},
{
"epoch": 3.59,
"learning_rate": 0.0001938069255716145,
"loss": 0.0688,
"step": 212
},
{
"epoch": 3.61,
"learning_rate": 0.00018948350353219912,
"loss": 0.0678,
"step": 213
},
{
"epoch": 3.63,
"learning_rate": 0.0001851975484124944,
"loss": 0.0685,
"step": 214
},
{
"epoch": 3.64,
"learning_rate": 0.00018094957735583463,
"loss": 0.0683,
"step": 215
},
{
"epoch": 3.66,
"learning_rate": 0.00017674010292239746,
"loss": 0.0704,
"step": 216
},
{
"epoch": 3.68,
"learning_rate": 0.0001725696330273575,
"loss": 0.0665,
"step": 217
},
{
"epoch": 3.69,
"learning_rate": 0.00016843867087960252,
"loss": 0.0662,
"step": 218
},
{
"epoch": 3.71,
"learning_rate": 0.00016434771492101485,
"loss": 0.0604,
"step": 219
},
{
"epoch": 3.73,
"learning_rate": 0.00016029725876633085,
"loss": 0.0697,
"step": 220
},
{
"epoch": 3.75,
"learning_rate": 0.00015628779114358032,
"loss": 0.0652,
"step": 221
},
{
"epoch": 3.76,
"learning_rate": 0.00015231979583511668,
"loss": 0.0712,
"step": 222
},
{
"epoch": 3.78,
"learning_rate": 0.00014839375161924446,
"loss": 0.0711,
"step": 223
},
{
"epoch": 3.8,
"learning_rate": 0.00014451013221244914,
"loss": 0.0693,
"step": 224
},
{
"epoch": 3.81,
"learning_rate": 0.0001406694062122389,
"loss": 0.07,
"step": 225
},
{
"epoch": 3.83,
"learning_rate": 0.00013687203704060343,
"loss": 0.0685,
"step": 226
},
{
"epoch": 3.85,
"learning_rate": 0.00013311848288809813,
"loss": 0.0705,
"step": 227
},
{
"epoch": 3.86,
"learning_rate": 0.0001294091966585576,
"loss": 0.0666,
"step": 228
},
{
"epoch": 3.88,
"learning_rate": 0.0001257446259144494,
"loss": 0.0625,
"step": 229
},
{
"epoch": 3.9,
"learning_rate": 0.00012212521282287093,
"loss": 0.0672,
"step": 230
},
{
"epoch": 3.92,
"learning_rate": 0.00011855139410219657,
"loss": 0.0645,
"step": 231
},
{
"epoch": 3.93,
"learning_rate": 0.00011502360096938485,
"loss": 0.0684,
"step": 232
},
{
"epoch": 3.95,
"learning_rate": 0.0001115422590879464,
"loss": 0.0676,
"step": 233
},
{
"epoch": 3.97,
"learning_rate": 0.00010810778851658437,
"loss": 0.0694,
"step": 234
},
{
"epoch": 3.98,
"learning_rate": 0.00010472060365850949,
"loss": 0.0668,
"step": 235
},
{
"epoch": 4.0,
"learning_rate": 0.00010138111321143839,
"loss": 0.0642,
"step": 236
},
{
"epoch": 4.02,
"learning_rate": 9.808972011828055e-05,
"loss": 0.0594,
"step": 237
},
{
"epoch": 4.03,
"learning_rate": 9.484682151851831e-05,
"loss": 0.0644,
"step": 238
},
{
"epoch": 4.05,
"learning_rate": 9.16528087002892e-05,
"loss": 0.0641,
"step": 239
},
{
"epoch": 4.07,
"learning_rate": 8.850806705317183e-05,
"loss": 0.0642,
"step": 240
},
{
"epoch": 4.08,
"learning_rate": 8.54129760216859e-05,
"loss": 0.068,
"step": 241
},
{
"epoch": 4.1,
"learning_rate": 8.236790905950763e-05,
"loss": 0.0604,
"step": 242
},
{
"epoch": 4.12,
"learning_rate": 7.937323358440934e-05,
"loss": 0.0663,
"step": 243
},
{
"epoch": 4.14,
"learning_rate": 7.642931093392674e-05,
"loss": 0.0624,
"step": 244
},
{
"epoch": 4.15,
"learning_rate": 7.353649632175957e-05,
"loss": 0.0686,
"step": 245
},
{
"epoch": 4.17,
"learning_rate": 7.069513879491179e-05,
"loss": 0.0672,
"step": 246
},
{
"epoch": 4.19,
"learning_rate": 6.790558119157597e-05,
"loss": 0.0657,
"step": 247
},
{
"epoch": 4.2,
"learning_rate": 6.516816009976557e-05,
"loss": 0.0639,
"step": 248
},
{
"epoch": 4.22,
"learning_rate": 6.248320581670281e-05,
"loss": 0.0667,
"step": 249
},
{
"epoch": 4.24,
"learning_rate": 5.9851042308965156e-05,
"loss": 0.0658,
"step": 250
},
{
"epoch": 4.25,
"learning_rate": 5.72719871733951e-05,
"loss": 0.0663,
"step": 251
},
{
"epoch": 4.27,
"learning_rate": 5.474635159877883e-05,
"loss": 0.0677,
"step": 252
},
{
"epoch": 4.29,
"learning_rate": 5.227444032829887e-05,
"loss": 0.0681,
"step": 253
},
{
"epoch": 4.31,
"learning_rate": 4.985655162276298e-05,
"loss": 0.0822,
"step": 254
},
{
"epoch": 4.32,
"learning_rate": 4.7492977224616595e-05,
"loss": 0.0626,
"step": 255
},
{
"epoch": 4.34,
"learning_rate": 4.518400232274078e-05,
"loss": 0.0648,
"step": 256
},
{
"epoch": 4.36,
"learning_rate": 4.292990551804171e-05,
"loss": 0.0697,
"step": 257
},
{
"epoch": 4.37,
"learning_rate": 4.0730958789834295e-05,
"loss": 0.0661,
"step": 258
},
{
"epoch": 4.39,
"learning_rate": 3.8587427463025346e-05,
"loss": 0.0613,
"step": 259
},
{
"epoch": 4.41,
"learning_rate": 3.6499570176099786e-05,
"loss": 0.0645,
"step": 260
},
{
"epoch": 4.42,
"learning_rate": 3.44676388499125e-05,
"loss": 0.0586,
"step": 261
},
{
"epoch": 4.44,
"learning_rate": 3.249187865729264e-05,
"loss": 0.0631,
"step": 262
},
{
"epoch": 4.46,
"learning_rate": 3.0572527993460054e-05,
"loss": 0.0649,
"step": 263
},
{
"epoch": 4.47,
"learning_rate": 2.8709818447261338e-05,
"loss": 0.0657,
"step": 264
},
{
"epoch": 4.49,
"learning_rate": 2.6903974773225702e-05,
"loss": 0.0625,
"step": 265
},
{
"epoch": 4.51,
"learning_rate": 2.5155214864446553e-05,
"loss": 0.0648,
"step": 266
},
{
"epoch": 4.53,
"learning_rate": 2.3463749726290285e-05,
"loss": 0.0663,
"step": 267
},
{
"epoch": 4.54,
"learning_rate": 2.182978345093628e-05,
"loss": 0.0665,
"step": 268
},
{
"epoch": 4.56,
"learning_rate": 2.025351319275137e-05,
"loss": 0.0587,
"step": 269
},
{
"epoch": 4.58,
"learning_rate": 1.8735129144501038e-05,
"loss": 0.0608,
"step": 270
},
{
"epoch": 4.59,
"learning_rate": 1.7274814514400992e-05,
"loss": 0.0663,
"step": 271
},
{
"epoch": 4.61,
"learning_rate": 1.58727455040108e-05,
"loss": 0.0629,
"step": 272
},
{
"epoch": 4.63,
"learning_rate": 1.4529091286973995e-05,
"loss": 0.0585,
"step": 273
},
{
"epoch": 4.64,
"learning_rate": 1.3244013988605087e-05,
"loss": 0.0622,
"step": 274
},
{
"epoch": 4.66,
"learning_rate": 1.2017668666327752e-05,
"loss": 0.0603,
"step": 275
},
{
"epoch": 4.68,
"learning_rate": 1.0850203290965699e-05,
"loss": 0.0603,
"step": 276
},
{
"epoch": 4.69,
"learning_rate": 9.741758728888216e-06,
"loss": 0.0662,
"step": 277
},
{
"epoch": 4.71,
"learning_rate": 8.692468725013448e-06,
"loss": 0.065,
"step": 278
},
{
"epoch": 4.73,
"learning_rate": 7.702459886670788e-06,
"loss": 0.0653,
"step": 279
},
{
"epoch": 4.75,
"learning_rate": 6.771851668324225e-06,
"loss": 0.063,
"step": 280
},
{
"epoch": 4.76,
"learning_rate": 5.9007563571591425e-06,
"loss": 0.0653,
"step": 281
},
{
"epoch": 4.78,
"learning_rate": 5.089279059533658e-06,
"loss": 0.0638,
"step": 282
},
{
"epoch": 4.8,
"learning_rate": 4.337517688296544e-06,
"loss": 0.0631,
"step": 283
},
{
"epoch": 4.81,
"learning_rate": 3.645562950973014e-06,
"loss": 0.0607,
"step": 284
},
{
"epoch": 4.83,
"learning_rate": 3.013498338820031e-06,
"loss": 0.0668,
"step": 285
},
{
"epoch": 4.85,
"learning_rate": 2.441400116752146e-06,
"loss": 0.061,
"step": 286
},
{
"epoch": 4.86,
"learning_rate": 1.9293373141394122e-06,
"loss": 0.065,
"step": 287
},
{
"epoch": 4.88,
"learning_rate": 1.4773717164784372e-06,
"loss": 0.0671,
"step": 288
},
{
"epoch": 4.9,
"learning_rate": 1.0855578579370695e-06,
"loss": 0.0616,
"step": 289
},
{
"epoch": 4.92,
"learning_rate": 7.539430147745497e-07,
"loss": 0.0642,
"step": 290
},
{
"epoch": 4.93,
"learning_rate": 4.825671996370185e-07,
"loss": 0.0661,
"step": 291
},
{
"epoch": 4.95,
"learning_rate": 2.714631567297121e-07,
"loss": 0.0632,
"step": 292
},
{
"epoch": 4.97,
"learning_rate": 1.2065635786595587e-07,
"loss": 0.0671,
"step": 293
},
{
"epoch": 4.98,
"learning_rate": 3.016499939367812e-08,
"loss": 0.0615,
"step": 294
},
{
"epoch": 5.0,
"learning_rate": 0.0,
"loss": 0.0602,
"step": 295
},
{
"epoch": 5.0,
"step": 295,
"total_flos": 3.974264003126886e+16,
"train_loss": 0.20217839560266268,
"train_runtime": 961.6505,
"train_samples_per_second": 19.363,
"train_steps_per_second": 0.307
}
],
"logging_steps": 1.0,
"max_steps": 295,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 3000,
"total_flos": 3.974264003126886e+16,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 295,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 0.0001111111111111111,
"loss": 2.2793,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 0.0002222222222222222,
"loss": 2.2853,
"step": 2
},
{
"epoch": 0.05,
"learning_rate": 0.0003333333333333333,
"loss": 1.9982,
"step": 3
},
{
"epoch": 0.07,
"learning_rate": 0.0004444444444444444,
"loss": 1.7452,
"step": 4
},
{
"epoch": 0.08,
"learning_rate": 0.0005555555555555556,
"loss": 1.4194,
"step": 5
},
{
"epoch": 0.1,
"learning_rate": 0.0006666666666666666,
"loss": 1.3396,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 0.0007777777777777778,
"loss": 1.3332,
"step": 7
},
{
"epoch": 0.14,
"learning_rate": 0.0008888888888888888,
"loss": 1.2855,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.2143,
"step": 9
},
{
"epoch": 0.17,
"learning_rate": 0.0009999698350006063,
"loss": 1.087,
"step": 10
},
{
"epoch": 0.19,
"learning_rate": 0.000999879343642134,
"loss": 1.0377,
"step": 11
},
{
"epoch": 0.2,
"learning_rate": 0.0009997285368432702,
"loss": 1.2128,
"step": 12
},
{
"epoch": 0.22,
"learning_rate": 0.000999517432800363,
"loss": 1.0801,
"step": 13
},
{
"epoch": 0.24,
"learning_rate": 0.0009992460569852254,
"loss": 0.848,
"step": 14
},
{
"epoch": 0.25,
"learning_rate": 0.000998914442142063,
"loss": 0.8885,
"step": 15
},