dyang415's picture
Upload folder using huggingface_hub
e82209e verified
raw
history blame
86.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.800225415610031,
"eval_steps": 178,
"global_step": 710,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 2.0913,
"step": 1
},
{
"epoch": 0.0,
"eval_loss": 2.086364507675171,
"eval_runtime": 70.9467,
"eval_samples_per_second": 7.386,
"eval_steps_per_second": 1.846,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4e-05,
"loss": 1.8593,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 6e-05,
"loss": 1.9531,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 8e-05,
"loss": 1.497,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 1.371,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.00012,
"loss": 0.9074,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 0.00014,
"loss": 0.6526,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 0.00016,
"loss": 0.5406,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 0.00018,
"loss": 0.4498,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.3852,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 0.00019999996057660117,
"loss": 0.3148,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 0.0001999998423064356,
"loss": 0.294,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 0.00019999964518959668,
"loss": 0.2364,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 0.00019999936922623977,
"loss": 0.263,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 0.0001999990144165825,
"loss": 0.2718,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 0.00019999858076090457,
"loss": 0.2188,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 0.00019999806825954792,
"loss": 0.1855,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 0.00019999747691291665,
"loss": 0.1666,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 0.000199996806721477,
"loss": 0.2055,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 0.00019999605768575743,
"loss": 0.2022,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 0.0001999952298063485,
"loss": 0.1747,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 0.000199994323083903,
"loss": 0.1447,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 0.0001999933375191358,
"loss": 0.1613,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 0.00019999227311282404,
"loss": 0.1555,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 0.00019999112986580694,
"loss": 0.1488,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 0.00019998990777898593,
"loss": 0.1672,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 0.00019998860685332455,
"loss": 0.1647,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 0.00019998722708984855,
"loss": 0.1565,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 0.00019998576848964588,
"loss": 0.1471,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 0.00019998423105386655,
"loss": 0.1508,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 0.0001999826147837228,
"loss": 0.1482,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 0.00019998091968048898,
"loss": 0.1314,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 0.00019997914574550166,
"loss": 0.1445,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 0.0001999772929801595,
"loss": 0.1411,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 0.00019997536138592335,
"loss": 0.1338,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 0.00019997335096431625,
"loss": 0.1447,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 0.00019997126171692332,
"loss": 0.127,
"step": 37
},
{
"epoch": 0.04,
"learning_rate": 0.00019996909364539185,
"loss": 0.1258,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 0.0001999668467514313,
"loss": 0.1446,
"step": 39
},
{
"epoch": 0.05,
"learning_rate": 0.00019996452103681334,
"loss": 0.1319,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 0.00019996211650337163,
"loss": 0.1254,
"step": 41
},
{
"epoch": 0.05,
"learning_rate": 0.00019995963315300213,
"loss": 0.1415,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 0.0001999570709876628,
"loss": 0.1248,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 0.00019995443000937394,
"loss": 0.1091,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 0.00019995171022021784,
"loss": 0.1261,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 0.00019994891162233887,
"loss": 0.1454,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 0.00019994603421794377,
"loss": 0.1234,
"step": 47
},
{
"epoch": 0.05,
"learning_rate": 0.00019994307800930123,
"loss": 0.128,
"step": 48
},
{
"epoch": 0.06,
"learning_rate": 0.00019994004299874209,
"loss": 0.134,
"step": 49
},
{
"epoch": 0.06,
"learning_rate": 0.0001999369291886594,
"loss": 0.1134,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 0.00019993373658150828,
"loss": 0.1282,
"step": 51
},
{
"epoch": 0.06,
"learning_rate": 0.00019993046517980602,
"loss": 0.1212,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 0.000199927114986132,
"loss": 0.1017,
"step": 53
},
{
"epoch": 0.06,
"learning_rate": 0.00019992368600312772,
"loss": 0.1125,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 0.00019992017823349686,
"loss": 0.0959,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 0.00019991659168000516,
"loss": 0.138,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 0.00019991292634548053,
"loss": 0.1299,
"step": 57
},
{
"epoch": 0.07,
"learning_rate": 0.00019990918223281295,
"loss": 0.1105,
"step": 58
},
{
"epoch": 0.07,
"learning_rate": 0.0001999053593449545,
"loss": 0.1405,
"step": 59
},
{
"epoch": 0.07,
"learning_rate": 0.00019990145768491947,
"loss": 0.1021,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 0.00019989747725578417,
"loss": 0.1204,
"step": 61
},
{
"epoch": 0.07,
"learning_rate": 0.000199893418060687,
"loss": 0.131,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 0.00019988928010282857,
"loss": 0.1047,
"step": 63
},
{
"epoch": 0.07,
"learning_rate": 0.00019988506338547147,
"loss": 0.1332,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 0.00019988076791194051,
"loss": 0.1341,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 0.00019987639368562244,
"loss": 0.1104,
"step": 66
},
{
"epoch": 0.08,
"learning_rate": 0.00019987194070996632,
"loss": 0.1162,
"step": 67
},
{
"epoch": 0.08,
"learning_rate": 0.00019986740898848306,
"loss": 0.1267,
"step": 68
},
{
"epoch": 0.08,
"learning_rate": 0.00019986279852474584,
"loss": 0.1259,
"step": 69
},
{
"epoch": 0.08,
"learning_rate": 0.00019985810932238987,
"loss": 0.1146,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 0.00019985334138511237,
"loss": 0.099,
"step": 71
},
{
"epoch": 0.08,
"learning_rate": 0.00019984849471667282,
"loss": 0.1424,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 0.00019984356932089257,
"loss": 0.115,
"step": 73
},
{
"epoch": 0.08,
"learning_rate": 0.00019983856520165512,
"loss": 0.1114,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 0.00019983348236290616,
"loss": 0.1192,
"step": 75
},
{
"epoch": 0.09,
"learning_rate": 0.00019982832080865328,
"loss": 0.1216,
"step": 76
},
{
"epoch": 0.09,
"learning_rate": 0.0001998230805429662,
"loss": 0.1095,
"step": 77
},
{
"epoch": 0.09,
"learning_rate": 0.00019981776156997668,
"loss": 0.0877,
"step": 78
},
{
"epoch": 0.09,
"learning_rate": 0.0001998123638938786,
"loss": 0.12,
"step": 79
},
{
"epoch": 0.09,
"learning_rate": 0.0001998068875189279,
"loss": 0.1013,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 0.00019980133244944243,
"loss": 0.1093,
"step": 81
},
{
"epoch": 0.09,
"learning_rate": 0.0001997956986898022,
"loss": 0.112,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 0.00019978998624444927,
"loss": 0.0877,
"step": 83
},
{
"epoch": 0.09,
"learning_rate": 0.00019978419511788777,
"loss": 0.1113,
"step": 84
},
{
"epoch": 0.1,
"learning_rate": 0.00019977832531468376,
"loss": 0.1091,
"step": 85
},
{
"epoch": 0.1,
"learning_rate": 0.00019977237683946536,
"loss": 0.1018,
"step": 86
},
{
"epoch": 0.1,
"learning_rate": 0.00019976634969692282,
"loss": 0.1021,
"step": 87
},
{
"epoch": 0.1,
"learning_rate": 0.00019976024389180833,
"loss": 0.1225,
"step": 88
},
{
"epoch": 0.1,
"learning_rate": 0.00019975405942893612,
"loss": 0.1249,
"step": 89
},
{
"epoch": 0.1,
"learning_rate": 0.00019974779631318242,
"loss": 0.1151,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 0.00019974145454948553,
"loss": 0.0959,
"step": 91
},
{
"epoch": 0.1,
"learning_rate": 0.0001997350341428457,
"loss": 0.1044,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 0.00019972853509832525,
"loss": 0.1159,
"step": 93
},
{
"epoch": 0.11,
"learning_rate": 0.00019972195742104846,
"loss": 0.1115,
"step": 94
},
{
"epoch": 0.11,
"learning_rate": 0.00019971530111620155,
"loss": 0.1073,
"step": 95
},
{
"epoch": 0.11,
"learning_rate": 0.00019970856618903285,
"loss": 0.1157,
"step": 96
},
{
"epoch": 0.11,
"learning_rate": 0.00019970175264485266,
"loss": 0.1047,
"step": 97
},
{
"epoch": 0.11,
"learning_rate": 0.00019969486048903323,
"loss": 0.1005,
"step": 98
},
{
"epoch": 0.11,
"learning_rate": 0.0001996878897270088,
"loss": 0.1104,
"step": 99
},
{
"epoch": 0.11,
"learning_rate": 0.0001996808403642756,
"loss": 0.1195,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 0.00019967371240639178,
"loss": 0.0993,
"step": 101
},
{
"epoch": 0.11,
"learning_rate": 0.00019966650585897755,
"loss": 0.1076,
"step": 102
},
{
"epoch": 0.12,
"learning_rate": 0.00019965922072771503,
"loss": 0.1244,
"step": 103
},
{
"epoch": 0.12,
"learning_rate": 0.0001996518570183483,
"loss": 0.1237,
"step": 104
},
{
"epoch": 0.12,
"learning_rate": 0.00019964441473668346,
"loss": 0.1069,
"step": 105
},
{
"epoch": 0.12,
"learning_rate": 0.00019963689388858847,
"loss": 0.1278,
"step": 106
},
{
"epoch": 0.12,
"learning_rate": 0.0001996292944799933,
"loss": 0.1058,
"step": 107
},
{
"epoch": 0.12,
"learning_rate": 0.0001996216165168898,
"loss": 0.1296,
"step": 108
},
{
"epoch": 0.12,
"learning_rate": 0.00019961386000533183,
"loss": 0.1021,
"step": 109
},
{
"epoch": 0.12,
"learning_rate": 0.00019960602495143514,
"loss": 0.1018,
"step": 110
},
{
"epoch": 0.13,
"learning_rate": 0.00019959811136137742,
"loss": 0.1041,
"step": 111
},
{
"epoch": 0.13,
"learning_rate": 0.00019959011924139828,
"loss": 0.098,
"step": 112
},
{
"epoch": 0.13,
"learning_rate": 0.00019958204859779925,
"loss": 0.1016,
"step": 113
},
{
"epoch": 0.13,
"learning_rate": 0.00019957389943694377,
"loss": 0.1036,
"step": 114
},
{
"epoch": 0.13,
"learning_rate": 0.00019956567176525724,
"loss": 0.1001,
"step": 115
},
{
"epoch": 0.13,
"learning_rate": 0.00019955736558922683,
"loss": 0.1144,
"step": 116
},
{
"epoch": 0.13,
"learning_rate": 0.0001995489809154018,
"loss": 0.1071,
"step": 117
},
{
"epoch": 0.13,
"learning_rate": 0.0001995405177503931,
"loss": 0.1013,
"step": 118
},
{
"epoch": 0.13,
"learning_rate": 0.0001995319761008737,
"loss": 0.101,
"step": 119
},
{
"epoch": 0.14,
"learning_rate": 0.00019952335597357842,
"loss": 0.1129,
"step": 120
},
{
"epoch": 0.14,
"learning_rate": 0.00019951465737530396,
"loss": 0.0942,
"step": 121
},
{
"epoch": 0.14,
"learning_rate": 0.00019950588031290888,
"loss": 0.1028,
"step": 122
},
{
"epoch": 0.14,
"learning_rate": 0.00019949702479331362,
"loss": 0.0941,
"step": 123
},
{
"epoch": 0.14,
"learning_rate": 0.0001994880908235005,
"loss": 0.1053,
"step": 124
},
{
"epoch": 0.14,
"learning_rate": 0.00019947907841051356,
"loss": 0.0921,
"step": 125
},
{
"epoch": 0.14,
"learning_rate": 0.0001994699875614589,
"loss": 0.0998,
"step": 126
},
{
"epoch": 0.14,
"learning_rate": 0.00019946081828350437,
"loss": 0.1009,
"step": 127
},
{
"epoch": 0.14,
"learning_rate": 0.00019945157058387958,
"loss": 0.1124,
"step": 128
},
{
"epoch": 0.15,
"learning_rate": 0.00019944224446987612,
"loss": 0.1214,
"step": 129
},
{
"epoch": 0.15,
"learning_rate": 0.00019943283994884728,
"loss": 0.1042,
"step": 130
},
{
"epoch": 0.15,
"learning_rate": 0.00019942335702820824,
"loss": 0.0921,
"step": 131
},
{
"epoch": 0.15,
"learning_rate": 0.00019941379571543596,
"loss": 0.1032,
"step": 132
},
{
"epoch": 0.15,
"learning_rate": 0.0001994041560180693,
"loss": 0.1243,
"step": 133
},
{
"epoch": 0.15,
"learning_rate": 0.00019939443794370876,
"loss": 0.0999,
"step": 134
},
{
"epoch": 0.15,
"learning_rate": 0.00019938464150001678,
"loss": 0.0953,
"step": 135
},
{
"epoch": 0.15,
"learning_rate": 0.00019937476669471753,
"loss": 0.1074,
"step": 136
},
{
"epoch": 0.15,
"learning_rate": 0.00019936481353559699,
"loss": 0.0931,
"step": 137
},
{
"epoch": 0.16,
"learning_rate": 0.00019935478203050288,
"loss": 0.1016,
"step": 138
},
{
"epoch": 0.16,
"learning_rate": 0.00019934467218734477,
"loss": 0.1032,
"step": 139
},
{
"epoch": 0.16,
"learning_rate": 0.00019933448401409393,
"loss": 0.1125,
"step": 140
},
{
"epoch": 0.16,
"learning_rate": 0.00019932421751878336,
"loss": 0.1009,
"step": 141
},
{
"epoch": 0.16,
"learning_rate": 0.0001993138727095079,
"loss": 0.0957,
"step": 142
},
{
"epoch": 0.16,
"learning_rate": 0.0001993034495944241,
"loss": 0.1153,
"step": 143
},
{
"epoch": 0.16,
"learning_rate": 0.00019929294818175027,
"loss": 0.1029,
"step": 144
},
{
"epoch": 0.16,
"learning_rate": 0.0001992823684797664,
"loss": 0.0956,
"step": 145
},
{
"epoch": 0.16,
"learning_rate": 0.00019927171049681427,
"loss": 0.1208,
"step": 146
},
{
"epoch": 0.17,
"learning_rate": 0.00019926097424129738,
"loss": 0.0972,
"step": 147
},
{
"epoch": 0.17,
"learning_rate": 0.0001992501597216809,
"loss": 0.0949,
"step": 148
},
{
"epoch": 0.17,
"learning_rate": 0.00019923926694649167,
"loss": 0.105,
"step": 149
},
{
"epoch": 0.17,
"learning_rate": 0.00019922829592431839,
"loss": 0.102,
"step": 150
},
{
"epoch": 0.17,
"learning_rate": 0.00019921724666381132,
"loss": 0.0956,
"step": 151
},
{
"epoch": 0.17,
"learning_rate": 0.00019920611917368248,
"loss": 0.092,
"step": 152
},
{
"epoch": 0.17,
"learning_rate": 0.0001991949134627055,
"loss": 0.1078,
"step": 153
},
{
"epoch": 0.17,
"learning_rate": 0.00019918362953971573,
"loss": 0.0964,
"step": 154
},
{
"epoch": 0.17,
"learning_rate": 0.00019917226741361015,
"loss": 0.1044,
"step": 155
},
{
"epoch": 0.18,
"learning_rate": 0.00019916082709334752,
"loss": 0.1089,
"step": 156
},
{
"epoch": 0.18,
"learning_rate": 0.00019914930858794808,
"loss": 0.0999,
"step": 157
},
{
"epoch": 0.18,
"learning_rate": 0.00019913771190649388,
"loss": 0.1075,
"step": 158
},
{
"epoch": 0.18,
"learning_rate": 0.00019912603705812847,
"loss": 0.1032,
"step": 159
},
{
"epoch": 0.18,
"learning_rate": 0.0001991142840520571,
"loss": 0.1141,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 0.0001991024528975467,
"loss": 0.103,
"step": 161
},
{
"epoch": 0.18,
"learning_rate": 0.00019909054360392567,
"loss": 0.1116,
"step": 162
},
{
"epoch": 0.18,
"learning_rate": 0.00019907855618058414,
"loss": 0.0906,
"step": 163
},
{
"epoch": 0.18,
"learning_rate": 0.00019906649063697386,
"loss": 0.1002,
"step": 164
},
{
"epoch": 0.19,
"learning_rate": 0.00019905434698260806,
"loss": 0.1024,
"step": 165
},
{
"epoch": 0.19,
"learning_rate": 0.00019904212522706165,
"loss": 0.0892,
"step": 166
},
{
"epoch": 0.19,
"learning_rate": 0.00019902982537997108,
"loss": 0.1029,
"step": 167
},
{
"epoch": 0.19,
"learning_rate": 0.00019901744745103438,
"loss": 0.0924,
"step": 168
},
{
"epoch": 0.19,
"learning_rate": 0.00019900499145001117,
"loss": 0.0965,
"step": 169
},
{
"epoch": 0.19,
"learning_rate": 0.00019899245738672262,
"loss": 0.0785,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 0.0001989798452710514,
"loss": 0.0897,
"step": 171
},
{
"epoch": 0.19,
"learning_rate": 0.00019896715511294176,
"loss": 0.1162,
"step": 172
},
{
"epoch": 0.19,
"learning_rate": 0.00019895438692239955,
"loss": 0.1108,
"step": 173
},
{
"epoch": 0.2,
"learning_rate": 0.000198941540709492,
"loss": 0.1195,
"step": 174
},
{
"epoch": 0.2,
"learning_rate": 0.00019892861648434796,
"loss": 0.0956,
"step": 175
},
{
"epoch": 0.2,
"learning_rate": 0.0001989156142571578,
"loss": 0.0976,
"step": 176
},
{
"epoch": 0.2,
"learning_rate": 0.00019890253403817334,
"loss": 0.1009,
"step": 177
},
{
"epoch": 0.2,
"learning_rate": 0.0001988893758377079,
"loss": 0.0992,
"step": 178
},
{
"epoch": 0.2,
"eval_loss": 0.10378821939229965,
"eval_runtime": 71.6357,
"eval_samples_per_second": 7.315,
"eval_steps_per_second": 1.829,
"step": 178
},
{
"epoch": 0.2,
"learning_rate": 0.0001988761396661363,
"loss": 0.1052,
"step": 179
},
{
"epoch": 0.2,
"learning_rate": 0.00019886282553389486,
"loss": 0.096,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 0.0001988494334514813,
"loss": 0.1077,
"step": 181
},
{
"epoch": 0.21,
"learning_rate": 0.0001988359634294549,
"loss": 0.1049,
"step": 182
},
{
"epoch": 0.21,
"learning_rate": 0.00019882241547843635,
"loss": 0.115,
"step": 183
},
{
"epoch": 0.21,
"learning_rate": 0.00019880878960910772,
"loss": 0.0944,
"step": 184
},
{
"epoch": 0.21,
"learning_rate": 0.0001987950858322126,
"loss": 0.1106,
"step": 185
},
{
"epoch": 0.21,
"learning_rate": 0.00019878130415855601,
"loss": 0.1091,
"step": 186
},
{
"epoch": 0.21,
"learning_rate": 0.0001987674445990043,
"loss": 0.0884,
"step": 187
},
{
"epoch": 0.21,
"learning_rate": 0.00019875350716448532,
"loss": 0.0992,
"step": 188
},
{
"epoch": 0.21,
"learning_rate": 0.00019873949186598828,
"loss": 0.1075,
"step": 189
},
{
"epoch": 0.21,
"learning_rate": 0.00019872539871456383,
"loss": 0.1061,
"step": 190
},
{
"epoch": 0.22,
"learning_rate": 0.00019871122772132388,
"loss": 0.1174,
"step": 191
},
{
"epoch": 0.22,
"learning_rate": 0.00019869697889744192,
"loss": 0.1215,
"step": 192
},
{
"epoch": 0.22,
"learning_rate": 0.00019868265225415265,
"loss": 0.1092,
"step": 193
},
{
"epoch": 0.22,
"learning_rate": 0.00019866824780275208,
"loss": 0.1141,
"step": 194
},
{
"epoch": 0.22,
"learning_rate": 0.0001986537655545978,
"loss": 0.0987,
"step": 195
},
{
"epoch": 0.22,
"learning_rate": 0.0001986392055211085,
"loss": 0.1023,
"step": 196
},
{
"epoch": 0.22,
"learning_rate": 0.00019862456771376437,
"loss": 0.0952,
"step": 197
},
{
"epoch": 0.22,
"learning_rate": 0.00019860985214410678,
"loss": 0.1053,
"step": 198
},
{
"epoch": 0.22,
"learning_rate": 0.00019859505882373853,
"loss": 0.083,
"step": 199
},
{
"epoch": 0.23,
"learning_rate": 0.00019858018776432366,
"loss": 0.1012,
"step": 200
},
{
"epoch": 0.23,
"learning_rate": 0.00019856523897758755,
"loss": 0.1132,
"step": 201
},
{
"epoch": 0.23,
"learning_rate": 0.00019855021247531683,
"loss": 0.1091,
"step": 202
},
{
"epoch": 0.23,
"learning_rate": 0.00019853510826935936,
"loss": 0.1017,
"step": 203
},
{
"epoch": 0.23,
"learning_rate": 0.00019851992637162443,
"loss": 0.0791,
"step": 204
},
{
"epoch": 0.23,
"learning_rate": 0.0001985046667940824,
"loss": 0.0922,
"step": 205
},
{
"epoch": 0.23,
"learning_rate": 0.00019848932954876498,
"loss": 0.1002,
"step": 206
},
{
"epoch": 0.23,
"learning_rate": 0.0001984739146477651,
"loss": 0.1047,
"step": 207
},
{
"epoch": 0.23,
"learning_rate": 0.0001984584221032369,
"loss": 0.0827,
"step": 208
},
{
"epoch": 0.24,
"learning_rate": 0.0001984428519273958,
"loss": 0.109,
"step": 209
},
{
"epoch": 0.24,
"learning_rate": 0.0001984272041325183,
"loss": 0.1173,
"step": 210
},
{
"epoch": 0.24,
"learning_rate": 0.0001984114787309423,
"loss": 0.1018,
"step": 211
},
{
"epoch": 0.24,
"learning_rate": 0.00019839567573506667,
"loss": 0.1004,
"step": 212
},
{
"epoch": 0.24,
"learning_rate": 0.00019837979515735166,
"loss": 0.0815,
"step": 213
},
{
"epoch": 0.24,
"learning_rate": 0.00019836383701031852,
"loss": 0.1091,
"step": 214
},
{
"epoch": 0.24,
"learning_rate": 0.00019834780130654976,
"loss": 0.1019,
"step": 215
},
{
"epoch": 0.24,
"learning_rate": 0.000198331688058689,
"loss": 0.0967,
"step": 216
},
{
"epoch": 0.24,
"learning_rate": 0.00019831549727944108,
"loss": 0.0992,
"step": 217
},
{
"epoch": 0.25,
"learning_rate": 0.00019829922898157188,
"loss": 0.1007,
"step": 218
},
{
"epoch": 0.25,
"learning_rate": 0.0001982828831779084,
"loss": 0.1103,
"step": 219
},
{
"epoch": 0.25,
"learning_rate": 0.00019826645988133882,
"loss": 0.1117,
"step": 220
},
{
"epoch": 0.25,
"learning_rate": 0.00019824995910481237,
"loss": 0.1013,
"step": 221
},
{
"epoch": 0.25,
"learning_rate": 0.0001982333808613394,
"loss": 0.0922,
"step": 222
},
{
"epoch": 0.25,
"learning_rate": 0.0001982167251639913,
"loss": 0.0933,
"step": 223
},
{
"epoch": 0.25,
"learning_rate": 0.00019819999202590058,
"loss": 0.0991,
"step": 224
},
{
"epoch": 0.25,
"learning_rate": 0.00019818318146026077,
"loss": 0.1012,
"step": 225
},
{
"epoch": 0.25,
"learning_rate": 0.00019816629348032644,
"loss": 0.1109,
"step": 226
},
{
"epoch": 0.26,
"learning_rate": 0.00019814932809941326,
"loss": 0.0801,
"step": 227
},
{
"epoch": 0.26,
"learning_rate": 0.00019813228533089786,
"loss": 0.0932,
"step": 228
},
{
"epoch": 0.26,
"learning_rate": 0.00019811516518821796,
"loss": 0.0994,
"step": 229
},
{
"epoch": 0.26,
"learning_rate": 0.00019809796768487217,
"loss": 0.1059,
"step": 230
},
{
"epoch": 0.26,
"learning_rate": 0.00019808069283442023,
"loss": 0.0955,
"step": 231
},
{
"epoch": 0.26,
"learning_rate": 0.00019806334065048282,
"loss": 0.1049,
"step": 232
},
{
"epoch": 0.26,
"learning_rate": 0.00019804591114674152,
"loss": 0.1112,
"step": 233
},
{
"epoch": 0.26,
"learning_rate": 0.00019802840433693895,
"loss": 0.1001,
"step": 234
},
{
"epoch": 0.26,
"learning_rate": 0.00019801082023487873,
"loss": 0.1045,
"step": 235
},
{
"epoch": 0.27,
"learning_rate": 0.00019799315885442531,
"loss": 0.104,
"step": 236
},
{
"epoch": 0.27,
"learning_rate": 0.00019797542020950413,
"loss": 0.0907,
"step": 237
},
{
"epoch": 0.27,
"learning_rate": 0.00019795760431410154,
"loss": 0.1032,
"step": 238
},
{
"epoch": 0.27,
"learning_rate": 0.00019793971118226483,
"loss": 0.0952,
"step": 239
},
{
"epoch": 0.27,
"learning_rate": 0.0001979217408281021,
"loss": 0.1036,
"step": 240
},
{
"epoch": 0.27,
"learning_rate": 0.00019790369326578243,
"loss": 0.1087,
"step": 241
},
{
"epoch": 0.27,
"learning_rate": 0.0001978855685095358,
"loss": 0.091,
"step": 242
},
{
"epoch": 0.27,
"learning_rate": 0.00019786736657365292,
"loss": 0.0881,
"step": 243
},
{
"epoch": 0.28,
"learning_rate": 0.00019784908747248547,
"loss": 0.1187,
"step": 244
},
{
"epoch": 0.28,
"learning_rate": 0.00019783073122044595,
"loss": 0.1191,
"step": 245
},
{
"epoch": 0.28,
"learning_rate": 0.00019781229783200766,
"loss": 0.1029,
"step": 246
},
{
"epoch": 0.28,
"learning_rate": 0.0001977937873217047,
"loss": 0.1013,
"step": 247
},
{
"epoch": 0.28,
"learning_rate": 0.0001977751997041321,
"loss": 0.1031,
"step": 248
},
{
"epoch": 0.28,
"learning_rate": 0.00019775653499394552,
"loss": 0.0953,
"step": 249
},
{
"epoch": 0.28,
"learning_rate": 0.00019773779320586153,
"loss": 0.1028,
"step": 250
},
{
"epoch": 0.28,
"learning_rate": 0.00019771897435465742,
"loss": 0.1004,
"step": 251
},
{
"epoch": 0.28,
"learning_rate": 0.00019770007845517124,
"loss": 0.0998,
"step": 252
},
{
"epoch": 0.29,
"learning_rate": 0.0001976811055223018,
"loss": 0.1056,
"step": 253
},
{
"epoch": 0.29,
"learning_rate": 0.00019766205557100868,
"loss": 0.1111,
"step": 254
},
{
"epoch": 0.29,
"learning_rate": 0.00019764292861631212,
"loss": 0.0967,
"step": 255
},
{
"epoch": 0.29,
"learning_rate": 0.00019762372467329315,
"loss": 0.0989,
"step": 256
},
{
"epoch": 0.29,
"learning_rate": 0.00019760444375709345,
"loss": 0.1048,
"step": 257
},
{
"epoch": 0.29,
"learning_rate": 0.00019758508588291535,
"loss": 0.0932,
"step": 258
},
{
"epoch": 0.29,
"learning_rate": 0.000197565651066022,
"loss": 0.0996,
"step": 259
},
{
"epoch": 0.29,
"learning_rate": 0.00019754613932173709,
"loss": 0.0898,
"step": 260
},
{
"epoch": 0.29,
"learning_rate": 0.000197526550665445,
"loss": 0.1129,
"step": 261
},
{
"epoch": 0.3,
"learning_rate": 0.0001975068851125908,
"loss": 0.0919,
"step": 262
},
{
"epoch": 0.3,
"learning_rate": 0.00019748714267868006,
"loss": 0.0943,
"step": 263
},
{
"epoch": 0.3,
"learning_rate": 0.00019746732337927916,
"loss": 0.1023,
"step": 264
},
{
"epoch": 0.3,
"learning_rate": 0.0001974474272300149,
"loss": 0.1056,
"step": 265
},
{
"epoch": 0.3,
"learning_rate": 0.00019742745424657478,
"loss": 0.1017,
"step": 266
},
{
"epoch": 0.3,
"learning_rate": 0.00019740740444470692,
"loss": 0.0954,
"step": 267
},
{
"epoch": 0.3,
"learning_rate": 0.00019738727784021984,
"loss": 0.102,
"step": 268
},
{
"epoch": 0.3,
"learning_rate": 0.00019736707444898284,
"loss": 0.0854,
"step": 269
},
{
"epoch": 0.3,
"learning_rate": 0.00019734679428692556,
"loss": 0.0969,
"step": 270
},
{
"epoch": 0.31,
"learning_rate": 0.00019732643737003827,
"loss": 0.0991,
"step": 271
},
{
"epoch": 0.31,
"learning_rate": 0.00019730600371437176,
"loss": 0.1092,
"step": 272
},
{
"epoch": 0.31,
"learning_rate": 0.0001972854933360373,
"loss": 0.0971,
"step": 273
},
{
"epoch": 0.31,
"learning_rate": 0.00019726490625120673,
"loss": 0.0877,
"step": 274
},
{
"epoch": 0.31,
"learning_rate": 0.00019724424247611225,
"loss": 0.0904,
"step": 275
},
{
"epoch": 0.31,
"learning_rate": 0.00019722350202704657,
"loss": 0.1058,
"step": 276
},
{
"epoch": 0.31,
"learning_rate": 0.00019720268492036288,
"loss": 0.0898,
"step": 277
},
{
"epoch": 0.31,
"learning_rate": 0.00019718179117247483,
"loss": 0.1093,
"step": 278
},
{
"epoch": 0.31,
"learning_rate": 0.00019716082079985648,
"loss": 0.0985,
"step": 279
},
{
"epoch": 0.32,
"learning_rate": 0.00019713977381904227,
"loss": 0.0889,
"step": 280
},
{
"epoch": 0.32,
"learning_rate": 0.00019711865024662706,
"loss": 0.0889,
"step": 281
},
{
"epoch": 0.32,
"learning_rate": 0.00019709745009926613,
"loss": 0.0953,
"step": 282
},
{
"epoch": 0.32,
"learning_rate": 0.0001970761733936751,
"loss": 0.102,
"step": 283
},
{
"epoch": 0.32,
"learning_rate": 0.00019705482014662997,
"loss": 0.1006,
"step": 284
},
{
"epoch": 0.32,
"learning_rate": 0.00019703339037496713,
"loss": 0.0914,
"step": 285
},
{
"epoch": 0.32,
"learning_rate": 0.00019701188409558326,
"loss": 0.0996,
"step": 286
},
{
"epoch": 0.32,
"learning_rate": 0.00019699030132543533,
"loss": 0.1041,
"step": 287
},
{
"epoch": 0.32,
"learning_rate": 0.0001969686420815407,
"loss": 0.1136,
"step": 288
},
{
"epoch": 0.33,
"learning_rate": 0.00019694690638097698,
"loss": 0.0929,
"step": 289
},
{
"epoch": 0.33,
"learning_rate": 0.00019692509424088203,
"loss": 0.1037,
"step": 290
},
{
"epoch": 0.33,
"learning_rate": 0.0001969032056784541,
"loss": 0.1002,
"step": 291
},
{
"epoch": 0.33,
"learning_rate": 0.0001968812407109516,
"loss": 0.0955,
"step": 292
},
{
"epoch": 0.33,
"learning_rate": 0.0001968591993556932,
"loss": 0.0979,
"step": 293
},
{
"epoch": 0.33,
"learning_rate": 0.00019683708163005777,
"loss": 0.0935,
"step": 294
},
{
"epoch": 0.33,
"learning_rate": 0.00019681488755148445,
"loss": 0.0955,
"step": 295
},
{
"epoch": 0.33,
"learning_rate": 0.00019679261713747255,
"loss": 0.0885,
"step": 296
},
{
"epoch": 0.33,
"learning_rate": 0.0001967702704055816,
"loss": 0.0804,
"step": 297
},
{
"epoch": 0.34,
"learning_rate": 0.00019674784737343132,
"loss": 0.0994,
"step": 298
},
{
"epoch": 0.34,
"learning_rate": 0.00019672534805870143,
"loss": 0.084,
"step": 299
},
{
"epoch": 0.34,
"learning_rate": 0.00019670277247913205,
"loss": 0.1002,
"step": 300
},
{
"epoch": 0.34,
"learning_rate": 0.00019668012065252323,
"loss": 0.0861,
"step": 301
},
{
"epoch": 0.34,
"learning_rate": 0.00019665739259673522,
"loss": 0.0948,
"step": 302
},
{
"epoch": 0.34,
"learning_rate": 0.00019663458832968838,
"loss": 0.1003,
"step": 303
},
{
"epoch": 0.34,
"learning_rate": 0.00019661170786936313,
"loss": 0.0839,
"step": 304
},
{
"epoch": 0.34,
"learning_rate": 0.00019658875123379998,
"loss": 0.0916,
"step": 305
},
{
"epoch": 0.34,
"learning_rate": 0.00019656571844109953,
"loss": 0.096,
"step": 306
},
{
"epoch": 0.35,
"learning_rate": 0.00019654260950942236,
"loss": 0.0946,
"step": 307
},
{
"epoch": 0.35,
"learning_rate": 0.00019651942445698915,
"loss": 0.0902,
"step": 308
},
{
"epoch": 0.35,
"learning_rate": 0.00019649616330208054,
"loss": 0.1117,
"step": 309
},
{
"epoch": 0.35,
"learning_rate": 0.00019647282606303723,
"loss": 0.0988,
"step": 310
},
{
"epoch": 0.35,
"learning_rate": 0.0001964494127582599,
"loss": 0.0946,
"step": 311
},
{
"epoch": 0.35,
"learning_rate": 0.00019642592340620915,
"loss": 0.0852,
"step": 312
},
{
"epoch": 0.35,
"learning_rate": 0.00019640235802540564,
"loss": 0.0939,
"step": 313
},
{
"epoch": 0.35,
"learning_rate": 0.00019637871663442984,
"loss": 0.0962,
"step": 314
},
{
"epoch": 0.36,
"learning_rate": 0.0001963549992519223,
"loss": 0.0841,
"step": 315
},
{
"epoch": 0.36,
"learning_rate": 0.0001963312058965834,
"loss": 0.0987,
"step": 316
},
{
"epoch": 0.36,
"learning_rate": 0.0001963073365871734,
"loss": 0.1084,
"step": 317
},
{
"epoch": 0.36,
"learning_rate": 0.00019628339134251252,
"loss": 0.1001,
"step": 318
},
{
"epoch": 0.36,
"learning_rate": 0.00019625937018148085,
"loss": 0.0935,
"step": 319
},
{
"epoch": 0.36,
"learning_rate": 0.00019623527312301824,
"loss": 0.0965,
"step": 320
},
{
"epoch": 0.36,
"learning_rate": 0.0001962111001861245,
"loss": 0.0968,
"step": 321
},
{
"epoch": 0.36,
"learning_rate": 0.00019618685138985913,
"loss": 0.1054,
"step": 322
},
{
"epoch": 0.36,
"learning_rate": 0.00019616252675334165,
"loss": 0.0902,
"step": 323
},
{
"epoch": 0.37,
"learning_rate": 0.0001961381262957512,
"loss": 0.0956,
"step": 324
},
{
"epoch": 0.37,
"learning_rate": 0.00019611365003632675,
"loss": 0.1103,
"step": 325
},
{
"epoch": 0.37,
"learning_rate": 0.00019608909799436706,
"loss": 0.1136,
"step": 326
},
{
"epoch": 0.37,
"learning_rate": 0.00019606447018923062,
"loss": 0.1059,
"step": 327
},
{
"epoch": 0.37,
"learning_rate": 0.00019603976664033567,
"loss": 0.093,
"step": 328
},
{
"epoch": 0.37,
"learning_rate": 0.00019601498736716017,
"loss": 0.1275,
"step": 329
},
{
"epoch": 0.37,
"learning_rate": 0.00019599013238924182,
"loss": 0.095,
"step": 330
},
{
"epoch": 0.37,
"learning_rate": 0.0001959652017261779,
"loss": 0.0972,
"step": 331
},
{
"epoch": 0.37,
"learning_rate": 0.00019594019539762546,
"loss": 0.0954,
"step": 332
},
{
"epoch": 0.38,
"learning_rate": 0.00019591511342330125,
"loss": 0.0948,
"step": 333
},
{
"epoch": 0.38,
"learning_rate": 0.00019588995582298153,
"loss": 0.0992,
"step": 334
},
{
"epoch": 0.38,
"learning_rate": 0.0001958647226165023,
"loss": 0.0989,
"step": 335
},
{
"epoch": 0.38,
"learning_rate": 0.00019583941382375915,
"loss": 0.0943,
"step": 336
},
{
"epoch": 0.38,
"learning_rate": 0.0001958140294647072,
"loss": 0.0964,
"step": 337
},
{
"epoch": 0.38,
"learning_rate": 0.00019578856955936123,
"loss": 0.0943,
"step": 338
},
{
"epoch": 0.38,
"learning_rate": 0.00019576303412779556,
"loss": 0.1042,
"step": 339
},
{
"epoch": 0.38,
"learning_rate": 0.0001957374231901441,
"loss": 0.0912,
"step": 340
},
{
"epoch": 0.38,
"learning_rate": 0.0001957117367666002,
"loss": 0.1139,
"step": 341
},
{
"epoch": 0.39,
"learning_rate": 0.00019568597487741677,
"loss": 0.1012,
"step": 342
},
{
"epoch": 0.39,
"learning_rate": 0.0001956601375429063,
"loss": 0.0825,
"step": 343
},
{
"epoch": 0.39,
"learning_rate": 0.00019563422478344067,
"loss": 0.093,
"step": 344
},
{
"epoch": 0.39,
"learning_rate": 0.00019560823661945125,
"loss": 0.0831,
"step": 345
},
{
"epoch": 0.39,
"learning_rate": 0.00019558217307142885,
"loss": 0.0976,
"step": 346
},
{
"epoch": 0.39,
"learning_rate": 0.0001955560341599238,
"loss": 0.0986,
"step": 347
},
{
"epoch": 0.39,
"learning_rate": 0.0001955298199055458,
"loss": 0.1019,
"step": 348
},
{
"epoch": 0.39,
"learning_rate": 0.00019550353032896388,
"loss": 0.0949,
"step": 349
},
{
"epoch": 0.39,
"learning_rate": 0.00019547716545090658,
"loss": 0.1027,
"step": 350
},
{
"epoch": 0.4,
"learning_rate": 0.00019545072529216176,
"loss": 0.1066,
"step": 351
},
{
"epoch": 0.4,
"learning_rate": 0.0001954242098735766,
"loss": 0.0923,
"step": 352
},
{
"epoch": 0.4,
"learning_rate": 0.00019539761921605773,
"loss": 0.1062,
"step": 353
},
{
"epoch": 0.4,
"learning_rate": 0.00019537095334057095,
"loss": 0.0958,
"step": 354
},
{
"epoch": 0.4,
"learning_rate": 0.00019534421226814153,
"loss": 0.0855,
"step": 355
},
{
"epoch": 0.4,
"learning_rate": 0.00019531739601985387,
"loss": 0.0923,
"step": 356
},
{
"epoch": 0.4,
"eval_loss": 0.09572399407625198,
"eval_runtime": 71.9205,
"eval_samples_per_second": 7.286,
"eval_steps_per_second": 1.821,
"step": 356
},
{
"epoch": 0.4,
"learning_rate": 0.00019529050461685179,
"loss": 0.0843,
"step": 357
},
{
"epoch": 0.4,
"learning_rate": 0.00019526353808033825,
"loss": 0.1011,
"step": 358
},
{
"epoch": 0.4,
"learning_rate": 0.00019523649643157556,
"loss": 0.0999,
"step": 359
},
{
"epoch": 0.41,
"learning_rate": 0.00019520937969188512,
"loss": 0.1039,
"step": 360
},
{
"epoch": 0.41,
"learning_rate": 0.00019518218788264763,
"loss": 0.0872,
"step": 361
},
{
"epoch": 0.41,
"learning_rate": 0.00019515492102530302,
"loss": 0.0977,
"step": 362
},
{
"epoch": 0.41,
"learning_rate": 0.00019512757914135026,
"loss": 0.0954,
"step": 363
},
{
"epoch": 0.41,
"learning_rate": 0.00019510016225234762,
"loss": 0.0918,
"step": 364
},
{
"epoch": 0.41,
"learning_rate": 0.00019507267037991238,
"loss": 0.0958,
"step": 365
},
{
"epoch": 0.41,
"learning_rate": 0.00019504510354572104,
"loss": 0.1108,
"step": 366
},
{
"epoch": 0.41,
"learning_rate": 0.00019501746177150913,
"loss": 0.083,
"step": 367
},
{
"epoch": 0.41,
"learning_rate": 0.0001949897450790713,
"loss": 0.0842,
"step": 368
},
{
"epoch": 0.42,
"learning_rate": 0.0001949619534902613,
"loss": 0.0974,
"step": 369
},
{
"epoch": 0.42,
"learning_rate": 0.00019493408702699194,
"loss": 0.0944,
"step": 370
},
{
"epoch": 0.42,
"learning_rate": 0.00019490614571123497,
"loss": 0.0946,
"step": 371
},
{
"epoch": 0.42,
"learning_rate": 0.00019487812956502128,
"loss": 0.0913,
"step": 372
},
{
"epoch": 0.42,
"learning_rate": 0.00019485003861044066,
"loss": 0.0892,
"step": 373
},
{
"epoch": 0.42,
"learning_rate": 0.0001948218728696419,
"loss": 0.0919,
"step": 374
},
{
"epoch": 0.42,
"learning_rate": 0.00019479363236483285,
"loss": 0.1004,
"step": 375
},
{
"epoch": 0.42,
"learning_rate": 0.00019476531711828027,
"loss": 0.0967,
"step": 376
},
{
"epoch": 0.42,
"learning_rate": 0.00019473692715230972,
"loss": 0.1035,
"step": 377
},
{
"epoch": 0.43,
"learning_rate": 0.00019470846248930587,
"loss": 0.088,
"step": 378
},
{
"epoch": 0.43,
"learning_rate": 0.00019467992315171215,
"loss": 0.0987,
"step": 379
},
{
"epoch": 0.43,
"learning_rate": 0.0001946513091620309,
"loss": 0.0867,
"step": 380
},
{
"epoch": 0.43,
"learning_rate": 0.00019462262054282338,
"loss": 0.1074,
"step": 381
},
{
"epoch": 0.43,
"learning_rate": 0.00019459385731670963,
"loss": 0.0884,
"step": 382
},
{
"epoch": 0.43,
"learning_rate": 0.00019456501950636853,
"loss": 0.0904,
"step": 383
},
{
"epoch": 0.43,
"learning_rate": 0.00019453610713453777,
"loss": 0.0878,
"step": 384
},
{
"epoch": 0.43,
"learning_rate": 0.0001945071202240138,
"loss": 0.0928,
"step": 385
},
{
"epoch": 0.44,
"learning_rate": 0.00019447805879765193,
"loss": 0.0998,
"step": 386
},
{
"epoch": 0.44,
"learning_rate": 0.00019444892287836613,
"loss": 0.1027,
"step": 387
},
{
"epoch": 0.44,
"learning_rate": 0.00019441971248912915,
"loss": 0.0897,
"step": 388
},
{
"epoch": 0.44,
"learning_rate": 0.00019439042765297243,
"loss": 0.0899,
"step": 389
},
{
"epoch": 0.44,
"learning_rate": 0.00019436106839298614,
"loss": 0.0969,
"step": 390
},
{
"epoch": 0.44,
"learning_rate": 0.0001943316347323191,
"loss": 0.0952,
"step": 391
},
{
"epoch": 0.44,
"learning_rate": 0.0001943021266941788,
"loss": 0.091,
"step": 392
},
{
"epoch": 0.44,
"learning_rate": 0.00019427254430183144,
"loss": 0.1004,
"step": 393
},
{
"epoch": 0.44,
"learning_rate": 0.00019424288757860175,
"loss": 0.1029,
"step": 394
},
{
"epoch": 0.45,
"learning_rate": 0.0001942131565478731,
"loss": 0.0916,
"step": 395
},
{
"epoch": 0.45,
"learning_rate": 0.00019418335123308746,
"loss": 0.0913,
"step": 396
},
{
"epoch": 0.45,
"learning_rate": 0.00019415347165774538,
"loss": 0.1005,
"step": 397
},
{
"epoch": 0.45,
"learning_rate": 0.0001941235178454059,
"loss": 0.0922,
"step": 398
},
{
"epoch": 0.45,
"learning_rate": 0.0001940934898196867,
"loss": 0.0858,
"step": 399
},
{
"epoch": 0.45,
"learning_rate": 0.00019406338760426394,
"loss": 0.1029,
"step": 400
},
{
"epoch": 0.45,
"learning_rate": 0.00019403321122287218,
"loss": 0.0997,
"step": 401
},
{
"epoch": 0.45,
"learning_rate": 0.00019400296069930456,
"loss": 0.1042,
"step": 402
},
{
"epoch": 0.45,
"learning_rate": 0.00019397263605741265,
"loss": 0.0902,
"step": 403
},
{
"epoch": 0.46,
"learning_rate": 0.00019394223732110649,
"loss": 0.107,
"step": 404
},
{
"epoch": 0.46,
"learning_rate": 0.00019391176451435445,
"loss": 0.1093,
"step": 405
},
{
"epoch": 0.46,
"learning_rate": 0.00019388121766118337,
"loss": 0.113,
"step": 406
},
{
"epoch": 0.46,
"learning_rate": 0.00019385059678567851,
"loss": 0.0849,
"step": 407
},
{
"epoch": 0.46,
"learning_rate": 0.00019381990191198343,
"loss": 0.0701,
"step": 408
},
{
"epoch": 0.46,
"learning_rate": 0.00019378913306430004,
"loss": 0.0926,
"step": 409
},
{
"epoch": 0.46,
"learning_rate": 0.00019375829026688863,
"loss": 0.0866,
"step": 410
},
{
"epoch": 0.46,
"learning_rate": 0.0001937273735440677,
"loss": 0.0957,
"step": 411
},
{
"epoch": 0.46,
"learning_rate": 0.00019369638292021413,
"loss": 0.0965,
"step": 412
},
{
"epoch": 0.47,
"learning_rate": 0.00019366531841976303,
"loss": 0.1165,
"step": 413
},
{
"epoch": 0.47,
"learning_rate": 0.0001936341800672078,
"loss": 0.0888,
"step": 414
},
{
"epoch": 0.47,
"learning_rate": 0.00019360296788709994,
"loss": 0.1102,
"step": 415
},
{
"epoch": 0.47,
"learning_rate": 0.00019357168190404936,
"loss": 0.0878,
"step": 416
},
{
"epoch": 0.47,
"learning_rate": 0.00019354032214272403,
"loss": 0.105,
"step": 417
},
{
"epoch": 0.47,
"learning_rate": 0.00019350888862785005,
"loss": 0.1062,
"step": 418
},
{
"epoch": 0.47,
"learning_rate": 0.00019347738138421181,
"loss": 0.0928,
"step": 419
},
{
"epoch": 0.47,
"learning_rate": 0.00019344580043665174,
"loss": 0.0963,
"step": 420
},
{
"epoch": 0.47,
"learning_rate": 0.00019341414581007039,
"loss": 0.1015,
"step": 421
},
{
"epoch": 0.48,
"learning_rate": 0.00019338241752942642,
"loss": 0.0968,
"step": 422
},
{
"epoch": 0.48,
"learning_rate": 0.00019335061561973662,
"loss": 0.0896,
"step": 423
},
{
"epoch": 0.48,
"learning_rate": 0.0001933187401060757,
"loss": 0.0951,
"step": 424
},
{
"epoch": 0.48,
"learning_rate": 0.00019328679101357653,
"loss": 0.0748,
"step": 425
},
{
"epoch": 0.48,
"learning_rate": 0.00019325476836742995,
"loss": 0.0897,
"step": 426
},
{
"epoch": 0.48,
"learning_rate": 0.00019322267219288474,
"loss": 0.0914,
"step": 427
},
{
"epoch": 0.48,
"learning_rate": 0.00019319050251524777,
"loss": 0.0893,
"step": 428
},
{
"epoch": 0.48,
"learning_rate": 0.00019315825935988377,
"loss": 0.0919,
"step": 429
},
{
"epoch": 0.48,
"learning_rate": 0.00019312594275221542,
"loss": 0.0945,
"step": 430
},
{
"epoch": 0.49,
"learning_rate": 0.00019309355271772335,
"loss": 0.092,
"step": 431
},
{
"epoch": 0.49,
"learning_rate": 0.00019306108928194608,
"loss": 0.0792,
"step": 432
},
{
"epoch": 0.49,
"learning_rate": 0.00019302855247047996,
"loss": 0.1039,
"step": 433
},
{
"epoch": 0.49,
"learning_rate": 0.00019299594230897925,
"loss": 0.1154,
"step": 434
},
{
"epoch": 0.49,
"learning_rate": 0.00019296325882315598,
"loss": 0.0862,
"step": 435
},
{
"epoch": 0.49,
"learning_rate": 0.00019293050203878005,
"loss": 0.0926,
"step": 436
},
{
"epoch": 0.49,
"learning_rate": 0.00019289767198167916,
"loss": 0.0822,
"step": 437
},
{
"epoch": 0.49,
"learning_rate": 0.00019286476867773873,
"loss": 0.0746,
"step": 438
},
{
"epoch": 0.49,
"learning_rate": 0.00019283179215290197,
"loss": 0.0926,
"step": 439
},
{
"epoch": 0.5,
"learning_rate": 0.0001927987424331698,
"loss": 0.0903,
"step": 440
},
{
"epoch": 0.5,
"learning_rate": 0.00019276561954460094,
"loss": 0.0952,
"step": 441
},
{
"epoch": 0.5,
"learning_rate": 0.00019273242351331162,
"loss": 0.0921,
"step": 442
},
{
"epoch": 0.5,
"learning_rate": 0.0001926991543654759,
"loss": 0.0837,
"step": 443
},
{
"epoch": 0.5,
"learning_rate": 0.00019266581212732544,
"loss": 0.0904,
"step": 444
},
{
"epoch": 0.5,
"learning_rate": 0.00019263239682514952,
"loss": 0.1003,
"step": 445
},
{
"epoch": 0.5,
"learning_rate": 0.000192598908485295,
"loss": 0.0961,
"step": 446
},
{
"epoch": 0.5,
"learning_rate": 0.00019256534713416645,
"loss": 0.0862,
"step": 447
},
{
"epoch": 0.5,
"learning_rate": 0.00019253171279822584,
"loss": 0.1226,
"step": 448
},
{
"epoch": 0.51,
"learning_rate": 0.0001924980055039928,
"loss": 0.0949,
"step": 449
},
{
"epoch": 0.51,
"learning_rate": 0.00019246422527804448,
"loss": 0.0913,
"step": 450
},
{
"epoch": 0.51,
"learning_rate": 0.00019243037214701546,
"loss": 0.0921,
"step": 451
},
{
"epoch": 0.51,
"learning_rate": 0.00019239644613759787,
"loss": 0.0871,
"step": 452
},
{
"epoch": 0.51,
"learning_rate": 0.00019236244727654126,
"loss": 0.1031,
"step": 453
},
{
"epoch": 0.51,
"learning_rate": 0.00019232837559065265,
"loss": 0.0934,
"step": 454
},
{
"epoch": 0.51,
"learning_rate": 0.0001922942311067965,
"loss": 0.1027,
"step": 455
},
{
"epoch": 0.51,
"learning_rate": 0.00019226001385189463,
"loss": 0.0933,
"step": 456
},
{
"epoch": 0.52,
"learning_rate": 0.00019222572385292624,
"loss": 0.094,
"step": 457
},
{
"epoch": 0.52,
"learning_rate": 0.00019219136113692787,
"loss": 0.0847,
"step": 458
},
{
"epoch": 0.52,
"learning_rate": 0.0001921569257309935,
"loss": 0.0942,
"step": 459
},
{
"epoch": 0.52,
"learning_rate": 0.0001921224176622743,
"loss": 0.0842,
"step": 460
},
{
"epoch": 0.52,
"learning_rate": 0.00019208783695797875,
"loss": 0.0923,
"step": 461
},
{
"epoch": 0.52,
"learning_rate": 0.00019205318364537267,
"loss": 0.099,
"step": 462
},
{
"epoch": 0.52,
"learning_rate": 0.00019201845775177904,
"loss": 0.0879,
"step": 463
},
{
"epoch": 0.52,
"learning_rate": 0.00019198365930457814,
"loss": 0.0958,
"step": 464
},
{
"epoch": 0.52,
"learning_rate": 0.0001919487883312075,
"loss": 0.0812,
"step": 465
},
{
"epoch": 0.53,
"learning_rate": 0.00019191384485916165,
"loss": 0.0913,
"step": 466
},
{
"epoch": 0.53,
"learning_rate": 0.00019187882891599247,
"loss": 0.0952,
"step": 467
},
{
"epoch": 0.53,
"learning_rate": 0.00019184374052930888,
"loss": 0.0889,
"step": 468
},
{
"epoch": 0.53,
"learning_rate": 0.00019180857972677696,
"loss": 0.0874,
"step": 469
},
{
"epoch": 0.53,
"learning_rate": 0.0001917733465361199,
"loss": 0.0862,
"step": 470
},
{
"epoch": 0.53,
"learning_rate": 0.0001917380409851179,
"loss": 0.0861,
"step": 471
},
{
"epoch": 0.53,
"learning_rate": 0.00019170266310160827,
"loss": 0.0894,
"step": 472
},
{
"epoch": 0.53,
"learning_rate": 0.00019166721291348537,
"loss": 0.0813,
"step": 473
},
{
"epoch": 0.53,
"learning_rate": 0.0001916316904487005,
"loss": 0.1084,
"step": 474
},
{
"epoch": 0.54,
"learning_rate": 0.000191596095735262,
"loss": 0.0923,
"step": 475
},
{
"epoch": 0.54,
"learning_rate": 0.00019156042880123512,
"loss": 0.0995,
"step": 476
},
{
"epoch": 0.54,
"learning_rate": 0.00019152468967474217,
"loss": 0.0941,
"step": 477
},
{
"epoch": 0.54,
"learning_rate": 0.00019148887838396227,
"loss": 0.0929,
"step": 478
},
{
"epoch": 0.54,
"learning_rate": 0.0001914529949571315,
"loss": 0.0977,
"step": 479
},
{
"epoch": 0.54,
"learning_rate": 0.00019141703942254275,
"loss": 0.0933,
"step": 480
},
{
"epoch": 0.54,
"learning_rate": 0.00019138101180854583,
"loss": 0.0881,
"step": 481
},
{
"epoch": 0.54,
"learning_rate": 0.00019134491214354736,
"loss": 0.0926,
"step": 482
},
{
"epoch": 0.54,
"learning_rate": 0.00019130874045601075,
"loss": 0.1111,
"step": 483
},
{
"epoch": 0.55,
"learning_rate": 0.00019127249677445627,
"loss": 0.0886,
"step": 484
},
{
"epoch": 0.55,
"learning_rate": 0.00019123618112746083,
"loss": 0.0972,
"step": 485
},
{
"epoch": 0.55,
"learning_rate": 0.00019119979354365822,
"loss": 0.0881,
"step": 486
},
{
"epoch": 0.55,
"learning_rate": 0.00019116333405173885,
"loss": 0.0941,
"step": 487
},
{
"epoch": 0.55,
"learning_rate": 0.00019112680268044987,
"loss": 0.0987,
"step": 488
},
{
"epoch": 0.55,
"learning_rate": 0.0001910901994585951,
"loss": 0.0782,
"step": 489
},
{
"epoch": 0.55,
"learning_rate": 0.000191053524415035,
"loss": 0.0905,
"step": 490
},
{
"epoch": 0.55,
"learning_rate": 0.00019101677757868668,
"loss": 0.081,
"step": 491
},
{
"epoch": 0.55,
"learning_rate": 0.00019097995897852382,
"loss": 0.0884,
"step": 492
},
{
"epoch": 0.56,
"learning_rate": 0.00019094306864357675,
"loss": 0.077,
"step": 493
},
{
"epoch": 0.56,
"learning_rate": 0.00019090610660293226,
"loss": 0.0842,
"step": 494
},
{
"epoch": 0.56,
"learning_rate": 0.00019086907288573378,
"loss": 0.1004,
"step": 495
},
{
"epoch": 0.56,
"learning_rate": 0.00019083196752118118,
"loss": 0.1001,
"step": 496
},
{
"epoch": 0.56,
"learning_rate": 0.00019079479053853087,
"loss": 0.0879,
"step": 497
},
{
"epoch": 0.56,
"learning_rate": 0.00019075754196709572,
"loss": 0.0954,
"step": 498
},
{
"epoch": 0.56,
"learning_rate": 0.00019072022183624503,
"loss": 0.0971,
"step": 499
},
{
"epoch": 0.56,
"learning_rate": 0.00019068283017540448,
"loss": 0.1095,
"step": 500
},
{
"epoch": 0.56,
"learning_rate": 0.00019064536701405627,
"loss": 0.1002,
"step": 501
},
{
"epoch": 0.57,
"learning_rate": 0.0001906078323817389,
"loss": 0.0952,
"step": 502
},
{
"epoch": 0.57,
"learning_rate": 0.00019057022630804716,
"loss": 0.0966,
"step": 503
},
{
"epoch": 0.57,
"learning_rate": 0.0001905325488226323,
"loss": 0.0928,
"step": 504
},
{
"epoch": 0.57,
"learning_rate": 0.00019049479995520175,
"loss": 0.0933,
"step": 505
},
{
"epoch": 0.57,
"learning_rate": 0.00019045697973551934,
"loss": 0.0962,
"step": 506
},
{
"epoch": 0.57,
"learning_rate": 0.00019041908819340505,
"loss": 0.0968,
"step": 507
},
{
"epoch": 0.57,
"learning_rate": 0.0001903811253587352,
"loss": 0.0977,
"step": 508
},
{
"epoch": 0.57,
"learning_rate": 0.00019034309126144224,
"loss": 0.092,
"step": 509
},
{
"epoch": 0.57,
"learning_rate": 0.00019030498593151484,
"loss": 0.0897,
"step": 510
},
{
"epoch": 0.58,
"learning_rate": 0.00019026680939899783,
"loss": 0.0884,
"step": 511
},
{
"epoch": 0.58,
"learning_rate": 0.0001902285616939922,
"loss": 0.0961,
"step": 512
},
{
"epoch": 0.58,
"learning_rate": 0.00019019024284665505,
"loss": 0.0882,
"step": 513
},
{
"epoch": 0.58,
"learning_rate": 0.0001901518528871995,
"loss": 0.0835,
"step": 514
},
{
"epoch": 0.58,
"learning_rate": 0.00019011339184589487,
"loss": 0.0861,
"step": 515
},
{
"epoch": 0.58,
"learning_rate": 0.00019007485975306644,
"loss": 0.0824,
"step": 516
},
{
"epoch": 0.58,
"learning_rate": 0.00019003625663909554,
"loss": 0.0913,
"step": 517
},
{
"epoch": 0.58,
"learning_rate": 0.00018999758253441946,
"loss": 0.1271,
"step": 518
},
{
"epoch": 0.58,
"learning_rate": 0.00018995883746953152,
"loss": 0.0795,
"step": 519
},
{
"epoch": 0.59,
"learning_rate": 0.00018992002147498094,
"loss": 0.0943,
"step": 520
},
{
"epoch": 0.59,
"learning_rate": 0.0001898811345813729,
"loss": 0.0863,
"step": 521
},
{
"epoch": 0.59,
"learning_rate": 0.00018984217681936846,
"loss": 0.0936,
"step": 522
},
{
"epoch": 0.59,
"learning_rate": 0.00018980314821968463,
"loss": 0.0872,
"step": 523
},
{
"epoch": 0.59,
"learning_rate": 0.00018976404881309412,
"loss": 0.0924,
"step": 524
},
{
"epoch": 0.59,
"learning_rate": 0.00018972487863042563,
"loss": 0.0838,
"step": 525
},
{
"epoch": 0.59,
"learning_rate": 0.00018968563770256354,
"loss": 0.0872,
"step": 526
},
{
"epoch": 0.59,
"learning_rate": 0.0001896463260604481,
"loss": 0.0979,
"step": 527
},
{
"epoch": 0.6,
"learning_rate": 0.00018960694373507526,
"loss": 0.088,
"step": 528
},
{
"epoch": 0.6,
"learning_rate": 0.00018956749075749673,
"loss": 0.0865,
"step": 529
},
{
"epoch": 0.6,
"learning_rate": 0.00018952796715881995,
"loss": 0.0936,
"step": 530
},
{
"epoch": 0.6,
"learning_rate": 0.000189488372970208,
"loss": 0.0842,
"step": 531
},
{
"epoch": 0.6,
"learning_rate": 0.00018944870822287956,
"loss": 0.1191,
"step": 532
},
{
"epoch": 0.6,
"learning_rate": 0.0001894089729481091,
"loss": 0.0981,
"step": 533
},
{
"epoch": 0.6,
"learning_rate": 0.0001893691671772266,
"loss": 0.0847,
"step": 534
},
{
"epoch": 0.6,
"eval_loss": 0.09380102157592773,
"eval_runtime": 71.8003,
"eval_samples_per_second": 7.298,
"eval_steps_per_second": 1.825,
"step": 534
},
{
"epoch": 0.6,
"learning_rate": 0.00018932929094161758,
"loss": 0.0837,
"step": 535
},
{
"epoch": 0.6,
"learning_rate": 0.00018928934427272321,
"loss": 0.0954,
"step": 536
},
{
"epoch": 0.61,
"learning_rate": 0.00018924932720204018,
"loss": 0.0755,
"step": 537
},
{
"epoch": 0.61,
"learning_rate": 0.00018920923976112065,
"loss": 0.0949,
"step": 538
},
{
"epoch": 0.61,
"learning_rate": 0.0001891690819815723,
"loss": 0.0949,
"step": 539
},
{
"epoch": 0.61,
"learning_rate": 0.0001891288538950582,
"loss": 0.0849,
"step": 540
},
{
"epoch": 0.61,
"learning_rate": 0.00018908855553329695,
"loss": 0.0971,
"step": 541
},
{
"epoch": 0.61,
"learning_rate": 0.00018904818692806253,
"loss": 0.0847,
"step": 542
},
{
"epoch": 0.61,
"learning_rate": 0.00018900774811118424,
"loss": 0.0864,
"step": 543
},
{
"epoch": 0.61,
"learning_rate": 0.00018896723911454686,
"loss": 0.0839,
"step": 544
},
{
"epoch": 0.61,
"learning_rate": 0.0001889266599700904,
"loss": 0.0981,
"step": 545
},
{
"epoch": 0.62,
"learning_rate": 0.0001888860107098102,
"loss": 0.0922,
"step": 546
},
{
"epoch": 0.62,
"learning_rate": 0.00018884529136575692,
"loss": 0.0957,
"step": 547
},
{
"epoch": 0.62,
"learning_rate": 0.00018880450197003646,
"loss": 0.0953,
"step": 548
},
{
"epoch": 0.62,
"learning_rate": 0.00018876364255480997,
"loss": 0.0927,
"step": 549
},
{
"epoch": 0.62,
"learning_rate": 0.00018872271315229373,
"loss": 0.0761,
"step": 550
},
{
"epoch": 0.62,
"learning_rate": 0.00018868171379475933,
"loss": 0.0912,
"step": 551
},
{
"epoch": 0.62,
"learning_rate": 0.00018864064451453341,
"loss": 0.1042,
"step": 552
},
{
"epoch": 0.62,
"learning_rate": 0.0001885995053439978,
"loss": 0.0942,
"step": 553
},
{
"epoch": 0.62,
"learning_rate": 0.00018855829631558946,
"loss": 0.0873,
"step": 554
},
{
"epoch": 0.63,
"learning_rate": 0.00018851701746180031,
"loss": 0.0939,
"step": 555
},
{
"epoch": 0.63,
"learning_rate": 0.0001884756688151774,
"loss": 0.0848,
"step": 556
},
{
"epoch": 0.63,
"learning_rate": 0.00018843425040832292,
"loss": 0.0916,
"step": 557
},
{
"epoch": 0.63,
"learning_rate": 0.00018839276227389386,
"loss": 0.1135,
"step": 558
},
{
"epoch": 0.63,
"learning_rate": 0.0001883512044446023,
"loss": 0.0883,
"step": 559
},
{
"epoch": 0.63,
"learning_rate": 0.00018830957695321527,
"loss": 0.1102,
"step": 560
},
{
"epoch": 0.63,
"learning_rate": 0.00018826787983255473,
"loss": 0.0954,
"step": 561
},
{
"epoch": 0.63,
"learning_rate": 0.00018822611311549754,
"loss": 0.0943,
"step": 562
},
{
"epoch": 0.63,
"learning_rate": 0.00018818427683497534,
"loss": 0.0694,
"step": 563
},
{
"epoch": 0.64,
"learning_rate": 0.00018814237102397478,
"loss": 0.0818,
"step": 564
},
{
"epoch": 0.64,
"learning_rate": 0.0001881003957155372,
"loss": 0.0934,
"step": 565
},
{
"epoch": 0.64,
"learning_rate": 0.00018805835094275883,
"loss": 0.0902,
"step": 566
},
{
"epoch": 0.64,
"learning_rate": 0.0001880162367387906,
"loss": 0.0841,
"step": 567
},
{
"epoch": 0.64,
"learning_rate": 0.00018797405313683818,
"loss": 0.0946,
"step": 568
},
{
"epoch": 0.64,
"learning_rate": 0.00018793180017016202,
"loss": 0.0871,
"step": 569
},
{
"epoch": 0.64,
"learning_rate": 0.00018788947787207728,
"loss": 0.0833,
"step": 570
},
{
"epoch": 0.64,
"learning_rate": 0.00018784708627595363,
"loss": 0.084,
"step": 571
},
{
"epoch": 0.64,
"learning_rate": 0.0001878046254152156,
"loss": 0.0908,
"step": 572
},
{
"epoch": 0.65,
"learning_rate": 0.00018776209532334214,
"loss": 0.0919,
"step": 573
},
{
"epoch": 0.65,
"learning_rate": 0.0001877194960338669,
"loss": 0.0851,
"step": 574
},
{
"epoch": 0.65,
"learning_rate": 0.00018767682758037802,
"loss": 0.1096,
"step": 575
},
{
"epoch": 0.65,
"learning_rate": 0.00018763408999651824,
"loss": 0.0959,
"step": 576
},
{
"epoch": 0.65,
"learning_rate": 0.0001875912833159848,
"loss": 0.0969,
"step": 577
},
{
"epoch": 0.65,
"learning_rate": 0.00018754840757252933,
"loss": 0.0971,
"step": 578
},
{
"epoch": 0.65,
"learning_rate": 0.00018750546279995805,
"loss": 0.1048,
"step": 579
},
{
"epoch": 0.65,
"learning_rate": 0.0001874624490321315,
"loss": 0.0874,
"step": 580
},
{
"epoch": 0.65,
"learning_rate": 0.00018741936630296466,
"loss": 0.0753,
"step": 581
},
{
"epoch": 0.66,
"learning_rate": 0.00018737621464642688,
"loss": 0.0956,
"step": 582
},
{
"epoch": 0.66,
"learning_rate": 0.0001873329940965419,
"loss": 0.0831,
"step": 583
},
{
"epoch": 0.66,
"learning_rate": 0.00018728970468738764,
"loss": 0.106,
"step": 584
},
{
"epoch": 0.66,
"learning_rate": 0.00018724634645309656,
"loss": 0.0888,
"step": 585
},
{
"epoch": 0.66,
"learning_rate": 0.0001872029194278551,
"loss": 0.1054,
"step": 586
},
{
"epoch": 0.66,
"learning_rate": 0.00018715942364590417,
"loss": 0.0943,
"step": 587
},
{
"epoch": 0.66,
"learning_rate": 0.00018711585914153874,
"loss": 0.0985,
"step": 588
},
{
"epoch": 0.66,
"learning_rate": 0.0001870722259491081,
"loss": 0.0857,
"step": 589
},
{
"epoch": 0.66,
"learning_rate": 0.00018702852410301554,
"loss": 0.1067,
"step": 590
},
{
"epoch": 0.67,
"learning_rate": 0.00018698475363771862,
"loss": 0.0879,
"step": 591
},
{
"epoch": 0.67,
"learning_rate": 0.00018694091458772892,
"loss": 0.0838,
"step": 592
},
{
"epoch": 0.67,
"learning_rate": 0.00018689700698761217,
"loss": 0.1042,
"step": 593
},
{
"epoch": 0.67,
"learning_rate": 0.00018685303087198808,
"loss": 0.0993,
"step": 594
},
{
"epoch": 0.67,
"learning_rate": 0.00018680898627553038,
"loss": 0.088,
"step": 595
},
{
"epoch": 0.67,
"learning_rate": 0.00018676487323296688,
"loss": 0.0862,
"step": 596
},
{
"epoch": 0.67,
"learning_rate": 0.00018672069177907928,
"loss": 0.1039,
"step": 597
},
{
"epoch": 0.67,
"learning_rate": 0.0001866764419487032,
"loss": 0.0858,
"step": 598
},
{
"epoch": 0.68,
"learning_rate": 0.00018663212377672829,
"loss": 0.0855,
"step": 599
},
{
"epoch": 0.68,
"learning_rate": 0.00018658773729809792,
"loss": 0.0897,
"step": 600
},
{
"epoch": 0.68,
"learning_rate": 0.0001865432825478095,
"loss": 0.0898,
"step": 601
},
{
"epoch": 0.68,
"learning_rate": 0.00018649875956091414,
"loss": 0.0981,
"step": 602
},
{
"epoch": 0.68,
"learning_rate": 0.00018645416837251676,
"loss": 0.0891,
"step": 603
},
{
"epoch": 0.68,
"learning_rate": 0.00018640950901777613,
"loss": 0.0928,
"step": 604
},
{
"epoch": 0.68,
"learning_rate": 0.00018636478153190466,
"loss": 0.0865,
"step": 605
},
{
"epoch": 0.68,
"learning_rate": 0.00018631998595016862,
"loss": 0.0897,
"step": 606
},
{
"epoch": 0.68,
"learning_rate": 0.00018627512230788785,
"loss": 0.081,
"step": 607
},
{
"epoch": 0.69,
"learning_rate": 0.00018623019064043585,
"loss": 0.0997,
"step": 608
},
{
"epoch": 0.69,
"learning_rate": 0.00018618519098323986,
"loss": 0.0856,
"step": 609
},
{
"epoch": 0.69,
"learning_rate": 0.00018614012337178068,
"loss": 0.1042,
"step": 610
},
{
"epoch": 0.69,
"learning_rate": 0.00018609498784159266,
"loss": 0.095,
"step": 611
},
{
"epoch": 0.69,
"learning_rate": 0.00018604978442826367,
"loss": 0.0814,
"step": 612
},
{
"epoch": 0.69,
"learning_rate": 0.00018600451316743525,
"loss": 0.0855,
"step": 613
},
{
"epoch": 0.69,
"learning_rate": 0.00018595917409480227,
"loss": 0.0971,
"step": 614
},
{
"epoch": 0.69,
"learning_rate": 0.00018591376724611317,
"loss": 0.0899,
"step": 615
},
{
"epoch": 0.69,
"learning_rate": 0.00018586829265716977,
"loss": 0.0902,
"step": 616
},
{
"epoch": 0.7,
"learning_rate": 0.00018582275036382732,
"loss": 0.1028,
"step": 617
},
{
"epoch": 0.7,
"learning_rate": 0.00018577714040199448,
"loss": 0.0919,
"step": 618
},
{
"epoch": 0.7,
"learning_rate": 0.00018573146280763324,
"loss": 0.0951,
"step": 619
},
{
"epoch": 0.7,
"learning_rate": 0.00018568571761675893,
"loss": 0.085,
"step": 620
},
{
"epoch": 0.7,
"learning_rate": 0.00018563990486544017,
"loss": 0.0873,
"step": 621
},
{
"epoch": 0.7,
"learning_rate": 0.0001855940245897988,
"loss": 0.0938,
"step": 622
},
{
"epoch": 0.7,
"learning_rate": 0.00018554807682601005,
"loss": 0.0822,
"step": 623
},
{
"epoch": 0.7,
"learning_rate": 0.00018550206161030216,
"loss": 0.0894,
"step": 624
},
{
"epoch": 0.7,
"learning_rate": 0.0001854559789789567,
"loss": 0.0938,
"step": 625
},
{
"epoch": 0.71,
"learning_rate": 0.00018540982896830834,
"loss": 0.0791,
"step": 626
},
{
"epoch": 0.71,
"learning_rate": 0.00018536361161474485,
"loss": 0.0873,
"step": 627
},
{
"epoch": 0.71,
"learning_rate": 0.00018531732695470723,
"loss": 0.0903,
"step": 628
},
{
"epoch": 0.71,
"learning_rate": 0.00018527097502468934,
"loss": 0.087,
"step": 629
},
{
"epoch": 0.71,
"learning_rate": 0.00018522455586123825,
"loss": 0.0921,
"step": 630
},
{
"epoch": 0.71,
"learning_rate": 0.000185178069500954,
"loss": 0.1115,
"step": 631
},
{
"epoch": 0.71,
"learning_rate": 0.00018513151598048956,
"loss": 0.1017,
"step": 632
},
{
"epoch": 0.71,
"learning_rate": 0.0001850848953365509,
"loss": 0.088,
"step": 633
},
{
"epoch": 0.71,
"learning_rate": 0.0001850382076058969,
"loss": 0.0903,
"step": 634
},
{
"epoch": 0.72,
"learning_rate": 0.0001849914528253394,
"loss": 0.0888,
"step": 635
},
{
"epoch": 0.72,
"learning_rate": 0.00018494463103174296,
"loss": 0.0961,
"step": 636
},
{
"epoch": 0.72,
"learning_rate": 0.0001848977422620251,
"loss": 0.0853,
"step": 637
},
{
"epoch": 0.72,
"learning_rate": 0.00018485078655315612,
"loss": 0.0918,
"step": 638
},
{
"epoch": 0.72,
"learning_rate": 0.00018480376394215908,
"loss": 0.0778,
"step": 639
},
{
"epoch": 0.72,
"learning_rate": 0.0001847566744661098,
"loss": 0.0748,
"step": 640
},
{
"epoch": 0.72,
"learning_rate": 0.00018470951816213686,
"loss": 0.0901,
"step": 641
},
{
"epoch": 0.72,
"learning_rate": 0.00018466229506742147,
"loss": 0.0891,
"step": 642
},
{
"epoch": 0.72,
"learning_rate": 0.00018461500521919753,
"loss": 0.0926,
"step": 643
},
{
"epoch": 0.73,
"learning_rate": 0.00018456764865475153,
"loss": 0.0991,
"step": 644
},
{
"epoch": 0.73,
"learning_rate": 0.00018452022541142268,
"loss": 0.0947,
"step": 645
},
{
"epoch": 0.73,
"learning_rate": 0.00018447273552660266,
"loss": 0.0861,
"step": 646
},
{
"epoch": 0.73,
"learning_rate": 0.0001844251790377357,
"loss": 0.0908,
"step": 647
},
{
"epoch": 0.73,
"learning_rate": 0.00018437755598231856,
"loss": 0.0939,
"step": 648
},
{
"epoch": 0.73,
"learning_rate": 0.00018432986639790056,
"loss": 0.1003,
"step": 649
},
{
"epoch": 0.73,
"learning_rate": 0.00018428211032208336,
"loss": 0.0959,
"step": 650
},
{
"epoch": 0.73,
"learning_rate": 0.00018423428779252107,
"loss": 0.0868,
"step": 651
},
{
"epoch": 0.73,
"learning_rate": 0.0001841863988469203,
"loss": 0.094,
"step": 652
},
{
"epoch": 0.74,
"learning_rate": 0.00018413844352303991,
"loss": 0.0926,
"step": 653
},
{
"epoch": 0.74,
"learning_rate": 0.0001840904218586911,
"loss": 0.0785,
"step": 654
},
{
"epoch": 0.74,
"learning_rate": 0.00018404233389173746,
"loss": 0.1018,
"step": 655
},
{
"epoch": 0.74,
"learning_rate": 0.00018399417966009484,
"loss": 0.0924,
"step": 656
},
{
"epoch": 0.74,
"learning_rate": 0.00018394595920173123,
"loss": 0.0941,
"step": 657
},
{
"epoch": 0.74,
"learning_rate": 0.00018389767255466697,
"loss": 0.0779,
"step": 658
},
{
"epoch": 0.74,
"learning_rate": 0.00018384931975697451,
"loss": 0.0982,
"step": 659
},
{
"epoch": 0.74,
"learning_rate": 0.00018380090084677854,
"loss": 0.0945,
"step": 660
},
{
"epoch": 0.74,
"learning_rate": 0.00018375241586225576,
"loss": 0.0759,
"step": 661
},
{
"epoch": 0.75,
"learning_rate": 0.00018370386484163503,
"loss": 0.082,
"step": 662
},
{
"epoch": 0.75,
"learning_rate": 0.0001836552478231973,
"loss": 0.0918,
"step": 663
},
{
"epoch": 0.75,
"learning_rate": 0.0001836065648452755,
"loss": 0.086,
"step": 664
},
{
"epoch": 0.75,
"learning_rate": 0.00018355781594625467,
"loss": 0.0996,
"step": 665
},
{
"epoch": 0.75,
"learning_rate": 0.00018350900116457166,
"loss": 0.0928,
"step": 666
},
{
"epoch": 0.75,
"learning_rate": 0.0001834601205387154,
"loss": 0.0992,
"step": 667
},
{
"epoch": 0.75,
"learning_rate": 0.00018341117410722676,
"loss": 0.0871,
"step": 668
},
{
"epoch": 0.75,
"learning_rate": 0.00018336216190869835,
"loss": 0.0909,
"step": 669
},
{
"epoch": 0.76,
"learning_rate": 0.00018331308398177477,
"loss": 0.0818,
"step": 670
},
{
"epoch": 0.76,
"learning_rate": 0.00018326394036515236,
"loss": 0.0904,
"step": 671
},
{
"epoch": 0.76,
"learning_rate": 0.0001832147310975793,
"loss": 0.0944,
"step": 672
},
{
"epoch": 0.76,
"learning_rate": 0.0001831654562178555,
"loss": 0.0814,
"step": 673
},
{
"epoch": 0.76,
"learning_rate": 0.00018311611576483268,
"loss": 0.0935,
"step": 674
},
{
"epoch": 0.76,
"learning_rate": 0.00018306670977741418,
"loss": 0.0925,
"step": 675
},
{
"epoch": 0.76,
"learning_rate": 0.000183017238294555,
"loss": 0.0942,
"step": 676
},
{
"epoch": 0.76,
"learning_rate": 0.0001829677013552619,
"loss": 0.0934,
"step": 677
},
{
"epoch": 0.76,
"learning_rate": 0.0001829180989985931,
"loss": 0.0911,
"step": 678
},
{
"epoch": 0.77,
"learning_rate": 0.0001828684312636585,
"loss": 0.0781,
"step": 679
},
{
"epoch": 0.77,
"learning_rate": 0.00018281869818961952,
"loss": 0.0843,
"step": 680
},
{
"epoch": 0.77,
"learning_rate": 0.00018276889981568906,
"loss": 0.0821,
"step": 681
},
{
"epoch": 0.77,
"learning_rate": 0.0001827190361811316,
"loss": 0.0944,
"step": 682
},
{
"epoch": 0.77,
"learning_rate": 0.00018266910732526296,
"loss": 0.095,
"step": 683
},
{
"epoch": 0.77,
"learning_rate": 0.00018261911328745051,
"loss": 0.0927,
"step": 684
},
{
"epoch": 0.77,
"learning_rate": 0.0001825690541071129,
"loss": 0.0844,
"step": 685
},
{
"epoch": 0.77,
"learning_rate": 0.00018251892982372022,
"loss": 0.0947,
"step": 686
},
{
"epoch": 0.77,
"learning_rate": 0.00018246874047679384,
"loss": 0.0718,
"step": 687
},
{
"epoch": 0.78,
"learning_rate": 0.00018241848610590645,
"loss": 0.0756,
"step": 688
},
{
"epoch": 0.78,
"learning_rate": 0.00018236816675068203,
"loss": 0.0861,
"step": 689
},
{
"epoch": 0.78,
"learning_rate": 0.00018231778245079573,
"loss": 0.0884,
"step": 690
},
{
"epoch": 0.78,
"learning_rate": 0.00018226733324597406,
"loss": 0.0953,
"step": 691
},
{
"epoch": 0.78,
"learning_rate": 0.00018221681917599453,
"loss": 0.0883,
"step": 692
},
{
"epoch": 0.78,
"learning_rate": 0.00018216624028068585,
"loss": 0.0894,
"step": 693
},
{
"epoch": 0.78,
"learning_rate": 0.0001821155965999279,
"loss": 0.0988,
"step": 694
},
{
"epoch": 0.78,
"learning_rate": 0.0001820648881736516,
"loss": 0.1041,
"step": 695
},
{
"epoch": 0.78,
"learning_rate": 0.00018201411504183888,
"loss": 0.0812,
"step": 696
},
{
"epoch": 0.79,
"learning_rate": 0.00018196327724452277,
"loss": 0.0829,
"step": 697
},
{
"epoch": 0.79,
"learning_rate": 0.00018191237482178724,
"loss": 0.0861,
"step": 698
},
{
"epoch": 0.79,
"learning_rate": 0.00018186140781376722,
"loss": 0.0853,
"step": 699
},
{
"epoch": 0.79,
"learning_rate": 0.00018181037626064853,
"loss": 0.102,
"step": 700
},
{
"epoch": 0.79,
"learning_rate": 0.00018175928020266796,
"loss": 0.1039,
"step": 701
},
{
"epoch": 0.79,
"learning_rate": 0.0001817081196801131,
"loss": 0.0826,
"step": 702
},
{
"epoch": 0.79,
"learning_rate": 0.00018165689473332238,
"loss": 0.0881,
"step": 703
},
{
"epoch": 0.79,
"learning_rate": 0.00018160560540268504,
"loss": 0.0887,
"step": 704
},
{
"epoch": 0.79,
"learning_rate": 0.00018155425172864106,
"loss": 0.0849,
"step": 705
},
{
"epoch": 0.8,
"learning_rate": 0.00018150283375168114,
"loss": 0.0922,
"step": 706
},
{
"epoch": 0.8,
"learning_rate": 0.00018145135151234677,
"loss": 0.1013,
"step": 707
},
{
"epoch": 0.8,
"learning_rate": 0.00018139980505123003,
"loss": 0.0775,
"step": 708
},
{
"epoch": 0.8,
"learning_rate": 0.0001813481944089736,
"loss": 0.0842,
"step": 709
},
{
"epoch": 0.8,
"learning_rate": 0.0001812965196262709,
"loss": 0.0792,
"step": 710
}
],
"logging_steps": 1,
"max_steps": 3548,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 355,
"total_flos": 1.3009661217545912e+19,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}