dyang415's picture
Upload folder using huggingface_hub
2557733 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.981818181818182,
"eval_steps": 500,
"global_step": 192,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 2.1617,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 2.1579,
"step": 2
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 2.0917,
"step": 3
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 1.8765,
"step": 4
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 1.3302,
"step": 5
},
{
"epoch": 0.06,
"learning_rate": 0.00012,
"loss": 0.9737,
"step": 6
},
{
"epoch": 0.07,
"learning_rate": 0.00014,
"loss": 0.7302,
"step": 7
},
{
"epoch": 0.08,
"learning_rate": 0.00016,
"loss": 0.534,
"step": 8
},
{
"epoch": 0.09,
"learning_rate": 0.00018,
"loss": 0.4094,
"step": 9
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 0.35,
"step": 10
},
{
"epoch": 0.11,
"learning_rate": 0.00019999647203724434,
"loss": 0.3007,
"step": 11
},
{
"epoch": 0.12,
"learning_rate": 0.00019998588839790777,
"loss": 0.2644,
"step": 12
},
{
"epoch": 0.14,
"learning_rate": 0.000199968249828764,
"loss": 0.2454,
"step": 13
},
{
"epoch": 0.15,
"learning_rate": 0.00019994355757437738,
"loss": 0.2029,
"step": 14
},
{
"epoch": 0.16,
"learning_rate": 0.0001999118133770149,
"loss": 0.204,
"step": 15
},
{
"epoch": 0.17,
"learning_rate": 0.00019987301947652352,
"loss": 0.1925,
"step": 16
},
{
"epoch": 0.18,
"learning_rate": 0.00019982717861017198,
"loss": 0.184,
"step": 17
},
{
"epoch": 0.19,
"learning_rate": 0.0001997742940124576,
"loss": 0.1639,
"step": 18
},
{
"epoch": 0.2,
"learning_rate": 0.00019971436941487833,
"loss": 0.1655,
"step": 19
},
{
"epoch": 0.21,
"learning_rate": 0.000199647409045669,
"loss": 0.1566,
"step": 20
},
{
"epoch": 0.22,
"learning_rate": 0.00019957341762950344,
"loss": 0.1571,
"step": 21
},
{
"epoch": 0.23,
"learning_rate": 0.0001994924003871609,
"loss": 0.1477,
"step": 22
},
{
"epoch": 0.24,
"learning_rate": 0.0001994043630351576,
"loss": 0.1495,
"step": 23
},
{
"epoch": 0.25,
"learning_rate": 0.0001993093117853435,
"loss": 0.1388,
"step": 24
},
{
"epoch": 0.26,
"learning_rate": 0.00019920725334446405,
"loss": 0.1466,
"step": 25
},
{
"epoch": 0.27,
"learning_rate": 0.00019909819491368676,
"loss": 0.141,
"step": 26
},
{
"epoch": 0.28,
"learning_rate": 0.0001989821441880933,
"loss": 0.1315,
"step": 27
},
{
"epoch": 0.29,
"learning_rate": 0.0001988591093561364,
"loss": 0.1354,
"step": 28
},
{
"epoch": 0.3,
"learning_rate": 0.00019872909909906215,
"loss": 0.129,
"step": 29
},
{
"epoch": 0.31,
"learning_rate": 0.00019859212259029752,
"loss": 0.1266,
"step": 30
},
{
"epoch": 0.32,
"learning_rate": 0.00019844818949480285,
"loss": 0.1233,
"step": 31
},
{
"epoch": 0.33,
"learning_rate": 0.0001982973099683902,
"loss": 0.121,
"step": 32
},
{
"epoch": 0.34,
"learning_rate": 0.00019813949465700653,
"loss": 0.1284,
"step": 33
},
{
"epoch": 0.35,
"learning_rate": 0.00019797475469598267,
"loss": 0.1266,
"step": 34
},
{
"epoch": 0.36,
"learning_rate": 0.00019780310170924753,
"loss": 0.1218,
"step": 35
},
{
"epoch": 0.37,
"learning_rate": 0.00019762454780850806,
"loss": 0.1264,
"step": 36
},
{
"epoch": 0.38,
"learning_rate": 0.0001974391055923944,
"loss": 0.1191,
"step": 37
},
{
"epoch": 0.39,
"learning_rate": 0.00019724678814557128,
"loss": 0.1173,
"step": 38
},
{
"epoch": 0.41,
"learning_rate": 0.00019704760903781446,
"loss": 0.1128,
"step": 39
},
{
"epoch": 0.42,
"learning_rate": 0.0001968415823230534,
"loss": 0.1113,
"step": 40
},
{
"epoch": 0.43,
"learning_rate": 0.0001966287225383796,
"loss": 0.1087,
"step": 41
},
{
"epoch": 0.44,
"learning_rate": 0.00019640904470302097,
"loss": 0.1163,
"step": 42
},
{
"epoch": 0.45,
"learning_rate": 0.00019618256431728194,
"loss": 0.1084,
"step": 43
},
{
"epoch": 0.46,
"learning_rate": 0.00019594929736144976,
"loss": 0.105,
"step": 44
},
{
"epoch": 0.47,
"learning_rate": 0.0001957092602946671,
"loss": 0.1124,
"step": 45
},
{
"epoch": 0.48,
"learning_rate": 0.00019546247005377065,
"loss": 0.1086,
"step": 46
},
{
"epoch": 0.49,
"learning_rate": 0.0001952089440520959,
"loss": 0.111,
"step": 47
},
{
"epoch": 0.5,
"learning_rate": 0.00019494870017824876,
"loss": 0.1109,
"step": 48
},
{
"epoch": 0.51,
"learning_rate": 0.00019468175679484304,
"loss": 0.106,
"step": 49
},
{
"epoch": 0.52,
"learning_rate": 0.00019440813273720504,
"loss": 0.1087,
"step": 50
},
{
"epoch": 0.53,
"learning_rate": 0.0001941278473120445,
"loss": 0.1065,
"step": 51
},
{
"epoch": 0.54,
"learning_rate": 0.0001938409202960922,
"loss": 0.1079,
"step": 52
},
{
"epoch": 0.55,
"learning_rate": 0.00019354737193470466,
"loss": 0.1055,
"step": 53
},
{
"epoch": 0.56,
"learning_rate": 0.00019324722294043558,
"loss": 0.1072,
"step": 54
},
{
"epoch": 0.57,
"learning_rate": 0.00019294049449157448,
"loss": 0.1056,
"step": 55
},
{
"epoch": 0.58,
"learning_rate": 0.00019262720823065216,
"loss": 0.1073,
"step": 56
},
{
"epoch": 0.59,
"learning_rate": 0.0001923073862629139,
"loss": 0.1075,
"step": 57
},
{
"epoch": 0.6,
"learning_rate": 0.00019198105115475947,
"loss": 0.0995,
"step": 58
},
{
"epoch": 0.61,
"learning_rate": 0.000191648225932151,
"loss": 0.0973,
"step": 59
},
{
"epoch": 0.62,
"learning_rate": 0.00019130893407898834,
"loss": 0.1021,
"step": 60
},
{
"epoch": 0.63,
"learning_rate": 0.00019096319953545185,
"loss": 0.1096,
"step": 61
},
{
"epoch": 0.64,
"learning_rate": 0.0001906110466963134,
"loss": 0.1007,
"step": 62
},
{
"epoch": 0.65,
"learning_rate": 0.00019025250040921506,
"loss": 0.1003,
"step": 63
},
{
"epoch": 0.66,
"learning_rate": 0.00018988758597291577,
"loss": 0.0959,
"step": 64
},
{
"epoch": 0.68,
"learning_rate": 0.00018951632913550626,
"loss": 0.0996,
"step": 65
},
{
"epoch": 0.69,
"learning_rate": 0.00018913875609259247,
"loss": 0.0965,
"step": 66
},
{
"epoch": 0.7,
"learning_rate": 0.00018875489348544705,
"loss": 0.1011,
"step": 67
},
{
"epoch": 0.71,
"learning_rate": 0.00018836476839912967,
"loss": 0.0966,
"step": 68
},
{
"epoch": 0.72,
"learning_rate": 0.00018796840836057577,
"loss": 0.0967,
"step": 69
},
{
"epoch": 0.73,
"learning_rate": 0.00018756584133665448,
"loss": 0.1003,
"step": 70
},
{
"epoch": 0.74,
"learning_rate": 0.00018715709573219506,
"loss": 0.1006,
"step": 71
},
{
"epoch": 0.75,
"learning_rate": 0.00018674220038798298,
"loss": 0.0962,
"step": 72
},
{
"epoch": 0.76,
"learning_rate": 0.00018632118457872463,
"loss": 0.0996,
"step": 73
},
{
"epoch": 0.77,
"learning_rate": 0.0001858940780109819,
"loss": 0.101,
"step": 74
},
{
"epoch": 0.78,
"learning_rate": 0.0001854609108210761,
"loss": 0.1049,
"step": 75
},
{
"epoch": 0.79,
"learning_rate": 0.00018502171357296144,
"loss": 0.1,
"step": 76
},
{
"epoch": 0.8,
"learning_rate": 0.00018457651725606861,
"loss": 0.0975,
"step": 77
},
{
"epoch": 0.81,
"learning_rate": 0.00018412535328311814,
"loss": 0.0959,
"step": 78
},
{
"epoch": 0.82,
"learning_rate": 0.00018366825348790388,
"loss": 0.0936,
"step": 79
},
{
"epoch": 0.83,
"learning_rate": 0.00018320525012304685,
"loss": 0.0956,
"step": 80
},
{
"epoch": 0.84,
"learning_rate": 0.00018273637585771964,
"loss": 0.1004,
"step": 81
},
{
"epoch": 0.85,
"learning_rate": 0.00018226166377534114,
"loss": 0.0964,
"step": 82
},
{
"epoch": 0.86,
"learning_rate": 0.00018178114737124224,
"loss": 0.0974,
"step": 83
},
{
"epoch": 0.87,
"learning_rate": 0.00018129486055030257,
"loss": 0.0963,
"step": 84
},
{
"epoch": 0.88,
"learning_rate": 0.0001808028376245579,
"loss": 0.0973,
"step": 85
},
{
"epoch": 0.89,
"learning_rate": 0.00018030511331077945,
"loss": 0.0959,
"step": 86
},
{
"epoch": 0.9,
"learning_rate": 0.000179801722728024,
"loss": 0.0941,
"step": 87
},
{
"epoch": 0.91,
"learning_rate": 0.00017929270139515604,
"loss": 0.095,
"step": 88
},
{
"epoch": 0.92,
"learning_rate": 0.00017877808522834173,
"loss": 0.0992,
"step": 89
},
{
"epoch": 0.94,
"learning_rate": 0.0001782579105385145,
"loss": 0.0912,
"step": 90
},
{
"epoch": 0.95,
"learning_rate": 0.00017773221402881295,
"loss": 0.0943,
"step": 91
},
{
"epoch": 0.96,
"learning_rate": 0.0001772010327919912,
"loss": 0.0959,
"step": 92
},
{
"epoch": 0.97,
"learning_rate": 0.0001766644043078017,
"loss": 0.0972,
"step": 93
},
{
"epoch": 0.98,
"learning_rate": 0.0001761223664403505,
"loss": 0.0933,
"step": 94
},
{
"epoch": 0.99,
"learning_rate": 0.00017557495743542585,
"loss": 0.0947,
"step": 95
},
{
"epoch": 1.0,
"learning_rate": 0.0001750222159177993,
"loss": 0.0958,
"step": 96
},
{
"epoch": 1.01,
"learning_rate": 0.00017446418088850067,
"loss": 0.0981,
"step": 97
},
{
"epoch": 1.01,
"learning_rate": 0.00017390089172206592,
"loss": 0.0952,
"step": 98
},
{
"epoch": 1.02,
"learning_rate": 0.00017333238816375906,
"loss": 0.0894,
"step": 99
},
{
"epoch": 1.03,
"learning_rate": 0.0001727587103267677,
"loss": 0.092,
"step": 100
},
{
"epoch": 1.04,
"learning_rate": 0.00017217989868937265,
"loss": 0.0908,
"step": 101
},
{
"epoch": 1.05,
"learning_rate": 0.00017159599409209193,
"loss": 0.0902,
"step": 102
},
{
"epoch": 1.06,
"learning_rate": 0.000171007037734799,
"loss": 0.0903,
"step": 103
},
{
"epoch": 1.07,
"learning_rate": 0.0001704130711738157,
"loss": 0.0844,
"step": 104
},
{
"epoch": 1.08,
"learning_rate": 0.00016981413631898012,
"loss": 0.0901,
"step": 105
},
{
"epoch": 1.09,
"learning_rate": 0.0001692102754306895,
"loss": 0.0923,
"step": 106
},
{
"epoch": 1.1,
"learning_rate": 0.00016860153111691832,
"loss": 0.0893,
"step": 107
},
{
"epoch": 1.11,
"learning_rate": 0.00016798794633021192,
"loss": 0.0946,
"step": 108
},
{
"epoch": 1.12,
"learning_rate": 0.00016736956436465573,
"loss": 0.0911,
"step": 109
},
{
"epoch": 1.13,
"learning_rate": 0.0001667464288528207,
"loss": 0.0919,
"step": 110
},
{
"epoch": 1.14,
"learning_rate": 0.0001661185837626843,
"loss": 0.0921,
"step": 111
},
{
"epoch": 1.15,
"learning_rate": 0.00016548607339452853,
"loss": 0.0897,
"step": 112
},
{
"epoch": 1.16,
"learning_rate": 0.00016484894237781371,
"loss": 0.0938,
"step": 113
},
{
"epoch": 1.17,
"learning_rate": 0.00016420723566802983,
"loss": 0.0883,
"step": 114
},
{
"epoch": 1.18,
"learning_rate": 0.00016356099854352433,
"loss": 0.0937,
"step": 115
},
{
"epoch": 1.19,
"learning_rate": 0.00016291027660230733,
"loss": 0.0939,
"step": 116
},
{
"epoch": 1.2,
"learning_rate": 0.00016225511575883433,
"loss": 0.0912,
"step": 117
},
{
"epoch": 1.21,
"learning_rate": 0.00016159556224076637,
"loss": 0.0894,
"step": 118
},
{
"epoch": 1.22,
"learning_rate": 0.00016093166258570845,
"loss": 0.0858,
"step": 119
},
{
"epoch": 1.23,
"learning_rate": 0.00016026346363792567,
"loss": 0.0875,
"step": 120
},
{
"epoch": 1.24,
"learning_rate": 0.000159591012545038,
"loss": 0.0917,
"step": 121
},
{
"epoch": 1.25,
"learning_rate": 0.00015891435675469376,
"loss": 0.0932,
"step": 122
},
{
"epoch": 1.26,
"learning_rate": 0.0001582335440112214,
"loss": 0.0908,
"step": 123
},
{
"epoch": 1.28,
"learning_rate": 0.000157548622352261,
"loss": 0.0913,
"step": 124
},
{
"epoch": 1.29,
"learning_rate": 0.00015685964010537465,
"loss": 0.0875,
"step": 125
},
{
"epoch": 1.3,
"learning_rate": 0.00015616664588463647,
"loss": 0.0863,
"step": 126
},
{
"epoch": 1.31,
"learning_rate": 0.00015546968858720246,
"loss": 0.0896,
"step": 127
},
{
"epoch": 1.32,
"learning_rate": 0.00015476881738986037,
"loss": 0.0853,
"step": 128
},
{
"epoch": 1.33,
"learning_rate": 0.00015406408174555976,
"loss": 0.0894,
"step": 129
},
{
"epoch": 1.34,
"learning_rate": 0.00015335553137992285,
"loss": 0.0855,
"step": 130
},
{
"epoch": 1.35,
"learning_rate": 0.0001526432162877356,
"loss": 0.0867,
"step": 131
},
{
"epoch": 1.36,
"learning_rate": 0.0001519271867294203,
"loss": 0.0895,
"step": 132
},
{
"epoch": 1.37,
"learning_rate": 0.00015120749322748925,
"loss": 0.0873,
"step": 133
},
{
"epoch": 1.38,
"learning_rate": 0.0001504841865629799,
"loss": 0.0898,
"step": 134
},
{
"epoch": 1.39,
"learning_rate": 0.0001497573177718716,
"loss": 0.09,
"step": 135
},
{
"epoch": 1.4,
"learning_rate": 0.0001490269381414849,
"loss": 0.086,
"step": 136
},
{
"epoch": 1.41,
"learning_rate": 0.00014829309920686245,
"loss": 0.0878,
"step": 137
},
{
"epoch": 1.42,
"learning_rate": 0.0001475558527471329,
"loss": 0.088,
"step": 138
},
{
"epoch": 1.43,
"learning_rate": 0.00014681525078185715,
"loss": 0.0832,
"step": 139
},
{
"epoch": 1.44,
"learning_rate": 0.00014607134556735834,
"loss": 0.0925,
"step": 140
},
{
"epoch": 1.45,
"learning_rate": 0.00014532418959303423,
"loss": 0.0909,
"step": 141
},
{
"epoch": 1.46,
"learning_rate": 0.00014457383557765386,
"loss": 0.0909,
"step": 142
},
{
"epoch": 1.47,
"learning_rate": 0.00014382033646563754,
"loss": 0.0915,
"step": 143
},
{
"epoch": 1.48,
"learning_rate": 0.00014306374542332143,
"loss": 0.0911,
"step": 144
},
{
"epoch": 1.49,
"learning_rate": 0.0001423041158352058,
"loss": 0.0845,
"step": 145
},
{
"epoch": 1.5,
"learning_rate": 0.00014154150130018866,
"loss": 0.0863,
"step": 146
},
{
"epoch": 1.51,
"learning_rate": 0.00014077595562778347,
"loss": 0.0882,
"step": 147
},
{
"epoch": 1.52,
"learning_rate": 0.00014000753283432266,
"loss": 0.0874,
"step": 148
},
{
"epoch": 1.54,
"learning_rate": 0.00013923628713914617,
"loss": 0.0864,
"step": 149
},
{
"epoch": 1.55,
"learning_rate": 0.00013846227296077568,
"loss": 0.092,
"step": 150
},
{
"epoch": 1.56,
"learning_rate": 0.00013768554491307516,
"loss": 0.0887,
"step": 151
},
{
"epoch": 1.57,
"learning_rate": 0.000136906157801397,
"loss": 0.0889,
"step": 152
},
{
"epoch": 1.58,
"learning_rate": 0.00013612416661871533,
"loss": 0.0865,
"step": 153
},
{
"epoch": 1.59,
"learning_rate": 0.0001353396265417454,
"loss": 0.0865,
"step": 154
},
{
"epoch": 1.6,
"learning_rate": 0.00013455259292705071,
"loss": 0.0845,
"step": 155
},
{
"epoch": 1.61,
"learning_rate": 0.00013376312130713687,
"loss": 0.0908,
"step": 156
},
{
"epoch": 1.62,
"learning_rate": 0.0001329712673865333,
"loss": 0.0902,
"step": 157
},
{
"epoch": 1.63,
"learning_rate": 0.0001321770870378628,
"loss": 0.0867,
"step": 158
},
{
"epoch": 1.64,
"learning_rate": 0.00013138063629789922,
"loss": 0.0899,
"step": 159
},
{
"epoch": 1.65,
"learning_rate": 0.00013058197136361343,
"loss": 0.0893,
"step": 160
},
{
"epoch": 1.66,
"learning_rate": 0.00012978114858820834,
"loss": 0.086,
"step": 161
},
{
"epoch": 1.67,
"learning_rate": 0.00012897822447714247,
"loss": 0.0853,
"step": 162
},
{
"epoch": 1.68,
"learning_rate": 0.00012817325568414297,
"loss": 0.0844,
"step": 163
},
{
"epoch": 1.69,
"learning_rate": 0.0001273662990072083,
"loss": 0.0905,
"step": 164
},
{
"epoch": 1.7,
"learning_rate": 0.00012655741138460045,
"loss": 0.0856,
"step": 165
},
{
"epoch": 1.71,
"learning_rate": 0.00012574664989082758,
"loss": 0.0896,
"step": 166
},
{
"epoch": 1.72,
"learning_rate": 0.00012493407173261675,
"loss": 0.0843,
"step": 167
},
{
"epoch": 1.73,
"learning_rate": 0.0001241197342448775,
"loss": 0.0869,
"step": 168
},
{
"epoch": 1.74,
"learning_rate": 0.00012330369488665647,
"loss": 0.0889,
"step": 169
},
{
"epoch": 1.75,
"learning_rate": 0.0001224860112370828,
"loss": 0.089,
"step": 170
},
{
"epoch": 1.76,
"learning_rate": 0.00012166674099130577,
"loss": 0.0901,
"step": 171
},
{
"epoch": 1.77,
"learning_rate": 0.00012084594195642367,
"loss": 0.0882,
"step": 172
},
{
"epoch": 1.78,
"learning_rate": 0.00012002367204740496,
"loss": 0.085,
"step": 173
},
{
"epoch": 1.79,
"learning_rate": 0.00011919998928300203,
"loss": 0.0865,
"step": 174
},
{
"epoch": 1.81,
"learning_rate": 0.00011837495178165706,
"loss": 0.083,
"step": 175
},
{
"epoch": 1.82,
"learning_rate": 0.00011754861775740162,
"loss": 0.0919,
"step": 176
},
{
"epoch": 1.83,
"learning_rate": 0.00011672104551574896,
"loss": 0.0853,
"step": 177
},
{
"epoch": 1.84,
"learning_rate": 0.00011589229344957999,
"loss": 0.0898,
"step": 178
},
{
"epoch": 1.85,
"learning_rate": 0.0001150624200350232,
"loss": 0.085,
"step": 179
},
{
"epoch": 1.86,
"learning_rate": 0.00011423148382732853,
"loss": 0.0881,
"step": 180
},
{
"epoch": 1.87,
"learning_rate": 0.00011339954345673582,
"loss": 0.0909,
"step": 181
},
{
"epoch": 1.88,
"learning_rate": 0.00011256665762433798,
"loss": 0.0815,
"step": 182
},
{
"epoch": 1.89,
"learning_rate": 0.00011173288509793889,
"loss": 0.0858,
"step": 183
},
{
"epoch": 1.9,
"learning_rate": 0.00011089828470790693,
"loss": 0.0825,
"step": 184
},
{
"epoch": 1.91,
"learning_rate": 0.00011006291534302402,
"loss": 0.0838,
"step": 185
},
{
"epoch": 1.92,
"learning_rate": 0.00010922683594633021,
"loss": 0.0863,
"step": 186
},
{
"epoch": 1.93,
"learning_rate": 0.00010839010551096498,
"loss": 0.0871,
"step": 187
},
{
"epoch": 1.94,
"learning_rate": 0.00010755278307600458,
"loss": 0.0825,
"step": 188
},
{
"epoch": 1.95,
"learning_rate": 0.00010671492772229628,
"loss": 0.0886,
"step": 189
},
{
"epoch": 1.96,
"learning_rate": 0.0001058765985682898,
"loss": 0.0851,
"step": 190
},
{
"epoch": 1.97,
"learning_rate": 0.00010503785476586569,
"loss": 0.087,
"step": 191
},
{
"epoch": 1.98,
"learning_rate": 0.00010419875549616196,
"loss": 0.0863,
"step": 192
}
],
"logging_steps": 1,
"max_steps": 384,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 96,
"total_flos": 1.4072422274753888e+19,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}