7386092792B793F8@lmu.de
Add KO_Specific_Knowledge_MME_MMbench_rank235
309db53
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.0,
"eval_steps": 500,
"global_step": 2244,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.9411764705882355e-06,
"loss": 1.81,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 5.882352941176471e-06,
"loss": 1.8726,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 8.823529411764707e-06,
"loss": 1.7617,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 1.1764705882352942e-05,
"loss": 1.6184,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.4705882352941177e-05,
"loss": 1.7555,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 1.7647058823529414e-05,
"loss": 1.7324,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 2.058823529411765e-05,
"loss": 1.6605,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 2.3529411764705884e-05,
"loss": 1.7518,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 2.647058823529412e-05,
"loss": 1.7474,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 2.9411764705882354e-05,
"loss": 1.6867,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 3.235294117647059e-05,
"loss": 1.5872,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 3.529411764705883e-05,
"loss": 1.6625,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 3.8235294117647055e-05,
"loss": 1.5292,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 4.11764705882353e-05,
"loss": 1.3553,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 4.411764705882353e-05,
"loss": 1.4791,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 4.705882352941177e-05,
"loss": 1.3811,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 5e-05,
"loss": 1.3641,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 5.294117647058824e-05,
"loss": 1.3423,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 5.588235294117647e-05,
"loss": 1.3878,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 5.882352941176471e-05,
"loss": 1.3448,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 6.176470588235295e-05,
"loss": 1.3814,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 6.470588235294118e-05,
"loss": 1.245,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 6.764705882352942e-05,
"loss": 1.2357,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 7.058823529411765e-05,
"loss": 1.3935,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 7.352941176470589e-05,
"loss": 1.295,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 7.647058823529411e-05,
"loss": 1.2759,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 7.941176470588235e-05,
"loss": 1.2407,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 8.23529411764706e-05,
"loss": 1.1829,
"step": 28
},
{
"epoch": 0.08,
"learning_rate": 8.529411764705883e-05,
"loss": 1.2369,
"step": 29
},
{
"epoch": 0.08,
"learning_rate": 8.823529411764706e-05,
"loss": 1.2513,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 9.11764705882353e-05,
"loss": 1.2006,
"step": 31
},
{
"epoch": 0.09,
"learning_rate": 9.411764705882353e-05,
"loss": 1.2666,
"step": 32
},
{
"epoch": 0.09,
"learning_rate": 9.705882352941177e-05,
"loss": 1.1375,
"step": 33
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 1.0893,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 0.00010294117647058823,
"loss": 1.2205,
"step": 35
},
{
"epoch": 0.1,
"learning_rate": 0.00010588235294117647,
"loss": 1.1217,
"step": 36
},
{
"epoch": 0.1,
"learning_rate": 0.0001088235294117647,
"loss": 1.1615,
"step": 37
},
{
"epoch": 0.1,
"learning_rate": 0.00011176470588235294,
"loss": 1.1757,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 0.00011470588235294118,
"loss": 1.1416,
"step": 39
},
{
"epoch": 0.11,
"learning_rate": 0.00011764705882352942,
"loss": 1.1109,
"step": 40
},
{
"epoch": 0.11,
"learning_rate": 0.00012058823529411765,
"loss": 1.1184,
"step": 41
},
{
"epoch": 0.11,
"learning_rate": 0.0001235294117647059,
"loss": 1.0985,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 0.0001264705882352941,
"loss": 1.0965,
"step": 43
},
{
"epoch": 0.12,
"learning_rate": 0.00012941176470588237,
"loss": 1.1051,
"step": 44
},
{
"epoch": 0.12,
"learning_rate": 0.0001323529411764706,
"loss": 1.1002,
"step": 45
},
{
"epoch": 0.12,
"learning_rate": 0.00013529411764705884,
"loss": 1.1866,
"step": 46
},
{
"epoch": 0.13,
"learning_rate": 0.00013823529411764707,
"loss": 1.1714,
"step": 47
},
{
"epoch": 0.13,
"learning_rate": 0.0001411764705882353,
"loss": 1.1168,
"step": 48
},
{
"epoch": 0.13,
"learning_rate": 0.00014411764705882354,
"loss": 1.119,
"step": 49
},
{
"epoch": 0.13,
"learning_rate": 0.00014705882352941178,
"loss": 1.0819,
"step": 50
},
{
"epoch": 0.14,
"learning_rate": 0.00015000000000000001,
"loss": 1.0291,
"step": 51
},
{
"epoch": 0.14,
"learning_rate": 0.00015294117647058822,
"loss": 1.0733,
"step": 52
},
{
"epoch": 0.14,
"learning_rate": 0.00015588235294117648,
"loss": 1.1289,
"step": 53
},
{
"epoch": 0.14,
"learning_rate": 0.0001588235294117647,
"loss": 1.0762,
"step": 54
},
{
"epoch": 0.15,
"learning_rate": 0.00016176470588235295,
"loss": 1.0911,
"step": 55
},
{
"epoch": 0.15,
"learning_rate": 0.0001647058823529412,
"loss": 1.1727,
"step": 56
},
{
"epoch": 0.15,
"learning_rate": 0.00016764705882352942,
"loss": 1.0813,
"step": 57
},
{
"epoch": 0.16,
"learning_rate": 0.00017058823529411766,
"loss": 0.9931,
"step": 58
},
{
"epoch": 0.16,
"learning_rate": 0.0001735294117647059,
"loss": 0.996,
"step": 59
},
{
"epoch": 0.16,
"learning_rate": 0.00017647058823529413,
"loss": 1.15,
"step": 60
},
{
"epoch": 0.16,
"learning_rate": 0.00017941176470588236,
"loss": 1.1134,
"step": 61
},
{
"epoch": 0.17,
"learning_rate": 0.0001823529411764706,
"loss": 1.0342,
"step": 62
},
{
"epoch": 0.17,
"learning_rate": 0.00018529411764705883,
"loss": 1.0379,
"step": 63
},
{
"epoch": 0.17,
"learning_rate": 0.00018823529411764707,
"loss": 1.1001,
"step": 64
},
{
"epoch": 0.17,
"learning_rate": 0.0001911764705882353,
"loss": 1.0914,
"step": 65
},
{
"epoch": 0.18,
"learning_rate": 0.00019411764705882354,
"loss": 1.0821,
"step": 66
},
{
"epoch": 0.18,
"learning_rate": 0.00019705882352941177,
"loss": 1.0797,
"step": 67
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 0.9896,
"step": 68
},
{
"epoch": 0.18,
"learning_rate": 0.00019999989577980243,
"loss": 1.1019,
"step": 69
},
{
"epoch": 0.19,
"learning_rate": 0.00019999958311942687,
"loss": 1.0541,
"step": 70
},
{
"epoch": 0.19,
"learning_rate": 0.00019999906201952506,
"loss": 1.0878,
"step": 71
},
{
"epoch": 0.19,
"learning_rate": 0.00019999833248118322,
"loss": 0.9855,
"step": 72
},
{
"epoch": 0.2,
"learning_rate": 0.00019999739450592192,
"loss": 1.1011,
"step": 73
},
{
"epoch": 0.2,
"learning_rate": 0.00019999624809569636,
"loss": 1.0922,
"step": 74
},
{
"epoch": 0.2,
"learning_rate": 0.00019999489325289607,
"loss": 1.1166,
"step": 75
},
{
"epoch": 0.2,
"learning_rate": 0.00019999332998034514,
"loss": 1.0239,
"step": 76
},
{
"epoch": 0.21,
"learning_rate": 0.000199991558281302,
"loss": 1.1253,
"step": 77
},
{
"epoch": 0.21,
"learning_rate": 0.00019998957815945962,
"loss": 1.0635,
"step": 78
},
{
"epoch": 0.21,
"learning_rate": 0.0001999873896189454,
"loss": 1.0773,
"step": 79
},
{
"epoch": 0.21,
"learning_rate": 0.00019998499266432108,
"loss": 1.1226,
"step": 80
},
{
"epoch": 0.22,
"learning_rate": 0.00019998238730058296,
"loss": 1.0892,
"step": 81
},
{
"epoch": 0.22,
"learning_rate": 0.0001999795735331616,
"loss": 1.0235,
"step": 82
},
{
"epoch": 0.22,
"learning_rate": 0.00019997655136792206,
"loss": 1.0269,
"step": 83
},
{
"epoch": 0.22,
"learning_rate": 0.00019997332081116373,
"loss": 1.0919,
"step": 84
},
{
"epoch": 0.23,
"learning_rate": 0.00019996988186962041,
"loss": 1.0109,
"step": 85
},
{
"epoch": 0.23,
"learning_rate": 0.0001999662345504603,
"loss": 1.0934,
"step": 86
},
{
"epoch": 0.23,
"learning_rate": 0.0001999623788612858,
"loss": 0.9739,
"step": 87
},
{
"epoch": 0.24,
"learning_rate": 0.00019995831481013374,
"loss": 1.012,
"step": 88
},
{
"epoch": 0.24,
"learning_rate": 0.00019995404240547525,
"loss": 1.0674,
"step": 89
},
{
"epoch": 0.24,
"learning_rate": 0.00019994956165621578,
"loss": 0.9946,
"step": 90
},
{
"epoch": 0.24,
"learning_rate": 0.00019994487257169502,
"loss": 1.0721,
"step": 91
},
{
"epoch": 0.25,
"learning_rate": 0.00019993997516168689,
"loss": 1.0502,
"step": 92
},
{
"epoch": 0.25,
"learning_rate": 0.00019993486943639953,
"loss": 1.0479,
"step": 93
},
{
"epoch": 0.25,
"learning_rate": 0.00019992955540647543,
"loss": 1.0599,
"step": 94
},
{
"epoch": 0.25,
"learning_rate": 0.0001999240330829911,
"loss": 1.0322,
"step": 95
},
{
"epoch": 0.26,
"learning_rate": 0.0001999183024774573,
"loss": 1.0159,
"step": 96
},
{
"epoch": 0.26,
"learning_rate": 0.00019991236360181896,
"loss": 1.0596,
"step": 97
},
{
"epoch": 0.26,
"learning_rate": 0.0001999062164684551,
"loss": 1.0652,
"step": 98
},
{
"epoch": 0.26,
"learning_rate": 0.0001998998610901788,
"loss": 0.961,
"step": 99
},
{
"epoch": 0.27,
"learning_rate": 0.00019989329748023725,
"loss": 1.0512,
"step": 100
},
{
"epoch": 0.27,
"learning_rate": 0.00019988652565231164,
"loss": 1.0061,
"step": 101
},
{
"epoch": 0.27,
"learning_rate": 0.00019987954562051725,
"loss": 1.0809,
"step": 102
},
{
"epoch": 0.28,
"learning_rate": 0.00019987235739940323,
"loss": 0.9188,
"step": 103
},
{
"epoch": 0.28,
"learning_rate": 0.00019986496100395275,
"loss": 1.0637,
"step": 104
},
{
"epoch": 0.28,
"learning_rate": 0.0001998573564495829,
"loss": 1.0585,
"step": 105
},
{
"epoch": 0.28,
"learning_rate": 0.00019984954375214465,
"loss": 0.9277,
"step": 106
},
{
"epoch": 0.29,
"learning_rate": 0.00019984152292792278,
"loss": 1.0408,
"step": 107
},
{
"epoch": 0.29,
"learning_rate": 0.00019983329399363598,
"loss": 1.0864,
"step": 108
},
{
"epoch": 0.29,
"learning_rate": 0.00019982485696643662,
"loss": 1.0316,
"step": 109
},
{
"epoch": 0.29,
"learning_rate": 0.0001998162118639109,
"loss": 1.0509,
"step": 110
},
{
"epoch": 0.3,
"learning_rate": 0.0001998073587040787,
"loss": 0.9844,
"step": 111
},
{
"epoch": 0.3,
"learning_rate": 0.0001997982975053936,
"loss": 0.9817,
"step": 112
},
{
"epoch": 0.3,
"learning_rate": 0.00019978902828674276,
"loss": 1.0005,
"step": 113
},
{
"epoch": 0.3,
"learning_rate": 0.00019977955106744704,
"loss": 1.0506,
"step": 114
},
{
"epoch": 0.31,
"learning_rate": 0.0001997698658672607,
"loss": 1.098,
"step": 115
},
{
"epoch": 0.31,
"learning_rate": 0.0001997599727063717,
"loss": 1.0373,
"step": 116
},
{
"epoch": 0.31,
"learning_rate": 0.00019974987160540134,
"loss": 1.078,
"step": 117
},
{
"epoch": 0.32,
"learning_rate": 0.0001997395625854044,
"loss": 0.9457,
"step": 118
},
{
"epoch": 0.32,
"learning_rate": 0.00019972904566786903,
"loss": 1.0279,
"step": 119
},
{
"epoch": 0.32,
"learning_rate": 0.00019971832087471676,
"loss": 0.9959,
"step": 120
},
{
"epoch": 0.32,
"learning_rate": 0.00019970738822830235,
"loss": 0.9729,
"step": 121
},
{
"epoch": 0.33,
"learning_rate": 0.00019969624775141391,
"loss": 0.9568,
"step": 122
},
{
"epoch": 0.33,
"learning_rate": 0.00019968489946727266,
"loss": 0.9628,
"step": 123
},
{
"epoch": 0.33,
"learning_rate": 0.000199673343399533,
"loss": 0.9255,
"step": 124
},
{
"epoch": 0.33,
"learning_rate": 0.00019966157957228246,
"loss": 1.037,
"step": 125
},
{
"epoch": 0.34,
"learning_rate": 0.00019964960801004163,
"loss": 0.977,
"step": 126
},
{
"epoch": 0.34,
"learning_rate": 0.000199637428737764,
"loss": 0.9702,
"step": 127
},
{
"epoch": 0.34,
"learning_rate": 0.00019962504178083618,
"loss": 0.989,
"step": 128
},
{
"epoch": 0.34,
"learning_rate": 0.00019961244716507756,
"loss": 0.9492,
"step": 129
},
{
"epoch": 0.35,
"learning_rate": 0.0001995996449167404,
"loss": 1.1301,
"step": 130
},
{
"epoch": 0.35,
"learning_rate": 0.0001995866350625098,
"loss": 1.0516,
"step": 131
},
{
"epoch": 0.35,
"learning_rate": 0.00019957341762950344,
"loss": 1.0847,
"step": 132
},
{
"epoch": 0.36,
"learning_rate": 0.00019955999264527195,
"loss": 1.0306,
"step": 133
},
{
"epoch": 0.36,
"learning_rate": 0.00019954636013779826,
"loss": 0.9747,
"step": 134
},
{
"epoch": 0.36,
"learning_rate": 0.00019953252013549813,
"loss": 0.955,
"step": 135
},
{
"epoch": 0.36,
"learning_rate": 0.0001995184726672197,
"loss": 1.0063,
"step": 136
},
{
"epoch": 0.37,
"learning_rate": 0.00019950421776224352,
"loss": 1.0685,
"step": 137
},
{
"epoch": 0.37,
"learning_rate": 0.00019948975545028264,
"loss": 1.0587,
"step": 138
},
{
"epoch": 0.37,
"learning_rate": 0.00019947508576148232,
"loss": 1.008,
"step": 139
},
{
"epoch": 0.37,
"learning_rate": 0.0001994602087264201,
"loss": 1.0437,
"step": 140
},
{
"epoch": 0.38,
"learning_rate": 0.0001994451243761057,
"loss": 1.0688,
"step": 141
},
{
"epoch": 0.38,
"learning_rate": 0.0001994298327419811,
"loss": 0.9196,
"step": 142
},
{
"epoch": 0.38,
"learning_rate": 0.0001994143338559202,
"loss": 0.9404,
"step": 143
},
{
"epoch": 0.39,
"learning_rate": 0.00019939862775022893,
"loss": 0.9458,
"step": 144
},
{
"epoch": 0.39,
"learning_rate": 0.00019938271445764513,
"loss": 0.9486,
"step": 145
},
{
"epoch": 0.39,
"learning_rate": 0.0001993665940113386,
"loss": 1.0425,
"step": 146
},
{
"epoch": 0.39,
"learning_rate": 0.0001993502664449108,
"loss": 0.9835,
"step": 147
},
{
"epoch": 0.4,
"learning_rate": 0.00019933373179239502,
"loss": 1.0437,
"step": 148
},
{
"epoch": 0.4,
"learning_rate": 0.00019931699008825612,
"loss": 0.942,
"step": 149
},
{
"epoch": 0.4,
"learning_rate": 0.00019930004136739054,
"loss": 1.0018,
"step": 150
},
{
"epoch": 0.4,
"learning_rate": 0.00019928288566512637,
"loss": 0.8881,
"step": 151
},
{
"epoch": 0.41,
"learning_rate": 0.0001992655230172229,
"loss": 1.1724,
"step": 152
},
{
"epoch": 0.41,
"learning_rate": 0.000199247953459871,
"loss": 1.0137,
"step": 153
},
{
"epoch": 0.41,
"learning_rate": 0.0001992301770296927,
"loss": 0.9864,
"step": 154
},
{
"epoch": 0.41,
"learning_rate": 0.00019921219376374123,
"loss": 0.9518,
"step": 155
},
{
"epoch": 0.42,
"learning_rate": 0.000199194003699501,
"loss": 1.0853,
"step": 156
},
{
"epoch": 0.42,
"learning_rate": 0.00019917560687488742,
"loss": 0.9945,
"step": 157
},
{
"epoch": 0.42,
"learning_rate": 0.00019915700332824696,
"loss": 0.9563,
"step": 158
},
{
"epoch": 0.43,
"learning_rate": 0.0001991381930983569,
"loss": 0.9587,
"step": 159
},
{
"epoch": 0.43,
"learning_rate": 0.00019911917622442537,
"loss": 1.0208,
"step": 160
},
{
"epoch": 0.43,
"learning_rate": 0.0001990999527460912,
"loss": 0.924,
"step": 161
},
{
"epoch": 0.43,
"learning_rate": 0.0001990805227034239,
"loss": 1.0185,
"step": 162
},
{
"epoch": 0.44,
"learning_rate": 0.00019906088613692345,
"loss": 0.9257,
"step": 163
},
{
"epoch": 0.44,
"learning_rate": 0.0001990410430875205,
"loss": 0.9468,
"step": 164
},
{
"epoch": 0.44,
"learning_rate": 0.00019902099359657598,
"loss": 1.0273,
"step": 165
},
{
"epoch": 0.44,
"learning_rate": 0.00019900073770588104,
"loss": 0.9562,
"step": 166
},
{
"epoch": 0.45,
"learning_rate": 0.00019898027545765717,
"loss": 0.9257,
"step": 167
},
{
"epoch": 0.45,
"learning_rate": 0.00019895960689455598,
"loss": 0.9934,
"step": 168
},
{
"epoch": 0.45,
"learning_rate": 0.0001989387320596591,
"loss": 1.0462,
"step": 169
},
{
"epoch": 0.45,
"learning_rate": 0.0001989176509964781,
"loss": 0.9623,
"step": 170
},
{
"epoch": 0.46,
"learning_rate": 0.0001988963637489545,
"loss": 0.9673,
"step": 171
},
{
"epoch": 0.46,
"learning_rate": 0.0001988748703614594,
"loss": 0.9925,
"step": 172
},
{
"epoch": 0.46,
"learning_rate": 0.00019885317087879378,
"loss": 1.0496,
"step": 173
},
{
"epoch": 0.47,
"learning_rate": 0.00019883126534618817,
"loss": 0.924,
"step": 174
},
{
"epoch": 0.47,
"learning_rate": 0.00019880915380930244,
"loss": 0.9726,
"step": 175
},
{
"epoch": 0.47,
"learning_rate": 0.00019878683631422605,
"loss": 0.9928,
"step": 176
},
{
"epoch": 0.47,
"learning_rate": 0.00019876431290747766,
"loss": 0.9703,
"step": 177
},
{
"epoch": 0.48,
"learning_rate": 0.0001987415836360051,
"loss": 0.9798,
"step": 178
},
{
"epoch": 0.48,
"learning_rate": 0.00019871864854718543,
"loss": 1.0188,
"step": 179
},
{
"epoch": 0.48,
"learning_rate": 0.00019869550768882455,
"loss": 0.9898,
"step": 180
},
{
"epoch": 0.48,
"learning_rate": 0.00019867216110915745,
"loss": 0.9334,
"step": 181
},
{
"epoch": 0.49,
"learning_rate": 0.00019864860885684778,
"loss": 0.9422,
"step": 182
},
{
"epoch": 0.49,
"learning_rate": 0.00019862485098098796,
"loss": 0.9499,
"step": 183
},
{
"epoch": 0.49,
"learning_rate": 0.00019860088753109896,
"loss": 0.9977,
"step": 184
},
{
"epoch": 0.49,
"learning_rate": 0.00019857671855713036,
"loss": 0.9901,
"step": 185
},
{
"epoch": 0.5,
"learning_rate": 0.00019855234410946,
"loss": 0.9062,
"step": 186
},
{
"epoch": 0.5,
"learning_rate": 0.0001985277642388941,
"loss": 1.0329,
"step": 187
},
{
"epoch": 0.5,
"learning_rate": 0.0001985029789966671,
"loss": 0.8916,
"step": 188
},
{
"epoch": 0.51,
"learning_rate": 0.00019847798843444138,
"loss": 0.9689,
"step": 189
},
{
"epoch": 0.51,
"learning_rate": 0.00019845279260430739,
"loss": 0.9127,
"step": 190
},
{
"epoch": 0.51,
"learning_rate": 0.00019842739155878338,
"loss": 0.9507,
"step": 191
},
{
"epoch": 0.51,
"learning_rate": 0.00019840178535081545,
"loss": 0.9505,
"step": 192
},
{
"epoch": 0.52,
"learning_rate": 0.00019837597403377726,
"loss": 1.0071,
"step": 193
},
{
"epoch": 0.52,
"learning_rate": 0.00019834995766147002,
"loss": 0.9837,
"step": 194
},
{
"epoch": 0.52,
"learning_rate": 0.00019832373628812233,
"loss": 0.9214,
"step": 195
},
{
"epoch": 0.52,
"learning_rate": 0.0001982973099683902,
"loss": 0.9252,
"step": 196
},
{
"epoch": 0.53,
"learning_rate": 0.00019827067875735667,
"loss": 0.9342,
"step": 197
},
{
"epoch": 0.53,
"learning_rate": 0.000198243842710532,
"loss": 0.9164,
"step": 198
},
{
"epoch": 0.53,
"learning_rate": 0.00019821680188385332,
"loss": 0.9929,
"step": 199
},
{
"epoch": 0.53,
"learning_rate": 0.00019818955633368464,
"loss": 0.9922,
"step": 200
},
{
"epoch": 0.54,
"learning_rate": 0.0001981621061168167,
"loss": 0.9512,
"step": 201
},
{
"epoch": 0.54,
"learning_rate": 0.00019813445129046684,
"loss": 0.9094,
"step": 202
},
{
"epoch": 0.54,
"learning_rate": 0.0001981065919122789,
"loss": 0.927,
"step": 203
},
{
"epoch": 0.55,
"learning_rate": 0.00019807852804032305,
"loss": 0.9933,
"step": 204
},
{
"epoch": 0.55,
"learning_rate": 0.00019805025973309578,
"loss": 0.9305,
"step": 205
},
{
"epoch": 0.55,
"learning_rate": 0.00019802178704951963,
"loss": 0.9919,
"step": 206
},
{
"epoch": 0.55,
"learning_rate": 0.00019799311004894314,
"loss": 0.9512,
"step": 207
},
{
"epoch": 0.56,
"learning_rate": 0.00019796422879114084,
"loss": 1.0002,
"step": 208
},
{
"epoch": 0.56,
"learning_rate": 0.00019793514333631287,
"loss": 0.8982,
"step": 209
},
{
"epoch": 0.56,
"learning_rate": 0.0001979058537450851,
"loss": 0.9831,
"step": 210
},
{
"epoch": 0.56,
"learning_rate": 0.00019787636007850888,
"loss": 0.9591,
"step": 211
},
{
"epoch": 0.57,
"learning_rate": 0.0001978466623980609,
"loss": 0.9448,
"step": 212
},
{
"epoch": 0.57,
"learning_rate": 0.00019781676076564315,
"loss": 0.964,
"step": 213
},
{
"epoch": 0.57,
"learning_rate": 0.00019778665524358268,
"loss": 0.8841,
"step": 214
},
{
"epoch": 0.57,
"learning_rate": 0.00019775634589463156,
"loss": 0.9532,
"step": 215
},
{
"epoch": 0.58,
"learning_rate": 0.00019772583278196678,
"loss": 0.9729,
"step": 216
},
{
"epoch": 0.58,
"learning_rate": 0.0001976951159691899,
"loss": 0.9608,
"step": 217
},
{
"epoch": 0.58,
"learning_rate": 0.00019766419552032723,
"loss": 0.9603,
"step": 218
},
{
"epoch": 0.59,
"learning_rate": 0.00019763307149982942,
"loss": 1.0103,
"step": 219
},
{
"epoch": 0.59,
"learning_rate": 0.00019760174397257156,
"loss": 0.9097,
"step": 220
},
{
"epoch": 0.59,
"learning_rate": 0.00019757021300385286,
"loss": 0.8943,
"step": 221
},
{
"epoch": 0.59,
"learning_rate": 0.00019753847865939657,
"loss": 0.9404,
"step": 222
},
{
"epoch": 0.6,
"learning_rate": 0.0001975065410053499,
"loss": 0.9287,
"step": 223
},
{
"epoch": 0.6,
"learning_rate": 0.00019747440010828383,
"loss": 0.9505,
"step": 224
},
{
"epoch": 0.6,
"learning_rate": 0.00019744205603519294,
"loss": 0.9166,
"step": 225
},
{
"epoch": 0.6,
"learning_rate": 0.00019740950885349537,
"loss": 0.9036,
"step": 226
},
{
"epoch": 0.61,
"learning_rate": 0.0001973767586310326,
"loss": 0.9956,
"step": 227
},
{
"epoch": 0.61,
"learning_rate": 0.0001973438054360693,
"loss": 0.997,
"step": 228
},
{
"epoch": 0.61,
"learning_rate": 0.00019731064933729324,
"loss": 0.8728,
"step": 229
},
{
"epoch": 0.61,
"learning_rate": 0.00019727729040381516,
"loss": 0.8816,
"step": 230
},
{
"epoch": 0.62,
"learning_rate": 0.00019724372870516852,
"loss": 0.9383,
"step": 231
},
{
"epoch": 0.62,
"learning_rate": 0.00019720996431130946,
"loss": 0.9237,
"step": 232
},
{
"epoch": 0.62,
"learning_rate": 0.00019717599729261663,
"loss": 0.95,
"step": 233
},
{
"epoch": 0.63,
"learning_rate": 0.00019714182771989102,
"loss": 0.8718,
"step": 234
},
{
"epoch": 0.63,
"learning_rate": 0.00019710745566435577,
"loss": 0.9741,
"step": 235
},
{
"epoch": 0.63,
"learning_rate": 0.00019707288119765623,
"loss": 0.9191,
"step": 236
},
{
"epoch": 0.63,
"learning_rate": 0.00019703810439185946,
"loss": 0.9672,
"step": 237
},
{
"epoch": 0.64,
"learning_rate": 0.00019700312531945442,
"loss": 0.9388,
"step": 238
},
{
"epoch": 0.64,
"learning_rate": 0.0001969679440533516,
"loss": 0.9632,
"step": 239
},
{
"epoch": 0.64,
"learning_rate": 0.000196932560666883,
"loss": 0.9126,
"step": 240
},
{
"epoch": 0.64,
"learning_rate": 0.00019689697523380187,
"loss": 0.9668,
"step": 241
},
{
"epoch": 0.65,
"learning_rate": 0.0001968611878282826,
"loss": 0.9007,
"step": 242
},
{
"epoch": 0.65,
"learning_rate": 0.00019682519852492068,
"loss": 0.9294,
"step": 243
},
{
"epoch": 0.65,
"learning_rate": 0.00019678900739873226,
"loss": 0.9971,
"step": 244
},
{
"epoch": 0.66,
"learning_rate": 0.00019675261452515433,
"loss": 0.9504,
"step": 245
},
{
"epoch": 0.66,
"learning_rate": 0.00019671601998004433,
"loss": 0.9574,
"step": 246
},
{
"epoch": 0.66,
"learning_rate": 0.0001966792238396801,
"loss": 0.9503,
"step": 247
},
{
"epoch": 0.66,
"learning_rate": 0.00019664222618075958,
"loss": 0.939,
"step": 248
},
{
"epoch": 0.67,
"learning_rate": 0.00019660502708040092,
"loss": 0.9642,
"step": 249
},
{
"epoch": 0.67,
"learning_rate": 0.000196567626616142,
"loss": 0.9182,
"step": 250
},
{
"epoch": 0.67,
"learning_rate": 0.00019653002486594057,
"loss": 1.0141,
"step": 251
},
{
"epoch": 0.67,
"learning_rate": 0.0001964922219081738,
"loss": 0.9608,
"step": 252
},
{
"epoch": 0.68,
"learning_rate": 0.00019645421782163837,
"loss": 0.9666,
"step": 253
},
{
"epoch": 0.68,
"learning_rate": 0.0001964160126855501,
"loss": 0.8421,
"step": 254
},
{
"epoch": 0.68,
"learning_rate": 0.000196377606579544,
"loss": 0.9415,
"step": 255
},
{
"epoch": 0.68,
"learning_rate": 0.00019633899958367384,
"loss": 0.9953,
"step": 256
},
{
"epoch": 0.69,
"learning_rate": 0.00019630019177841224,
"loss": 0.9631,
"step": 257
},
{
"epoch": 0.69,
"learning_rate": 0.00019626118324465034,
"loss": 0.9592,
"step": 258
},
{
"epoch": 0.69,
"learning_rate": 0.00019622197406369762,
"loss": 0.9451,
"step": 259
},
{
"epoch": 0.7,
"learning_rate": 0.00019618256431728194,
"loss": 0.8754,
"step": 260
},
{
"epoch": 0.7,
"learning_rate": 0.00019614295408754907,
"loss": 0.9306,
"step": 261
},
{
"epoch": 0.7,
"learning_rate": 0.00019610314345706273,
"loss": 0.917,
"step": 262
},
{
"epoch": 0.7,
"learning_rate": 0.0001960631325088044,
"loss": 0.9299,
"step": 263
},
{
"epoch": 0.71,
"learning_rate": 0.000196022921326173,
"loss": 0.9069,
"step": 264
},
{
"epoch": 0.71,
"learning_rate": 0.00019598250999298494,
"loss": 0.9395,
"step": 265
},
{
"epoch": 0.71,
"learning_rate": 0.00019594189859347373,
"loss": 0.8818,
"step": 266
},
{
"epoch": 0.71,
"learning_rate": 0.00019590108721228994,
"loss": 0.9165,
"step": 267
},
{
"epoch": 0.72,
"learning_rate": 0.00019586007593450097,
"loss": 0.9377,
"step": 268
},
{
"epoch": 0.72,
"learning_rate": 0.0001958188648455909,
"loss": 0.9771,
"step": 269
},
{
"epoch": 0.72,
"learning_rate": 0.00019577745403146025,
"loss": 0.8967,
"step": 270
},
{
"epoch": 0.72,
"learning_rate": 0.0001957358435784259,
"loss": 0.9019,
"step": 271
},
{
"epoch": 0.73,
"learning_rate": 0.0001956940335732209,
"loss": 0.9091,
"step": 272
},
{
"epoch": 0.73,
"learning_rate": 0.0001956520241029941,
"loss": 0.9817,
"step": 273
},
{
"epoch": 0.73,
"learning_rate": 0.00019560981525531027,
"loss": 0.9145,
"step": 274
},
{
"epoch": 0.74,
"learning_rate": 0.0001955674071181497,
"loss": 0.9035,
"step": 275
},
{
"epoch": 0.74,
"learning_rate": 0.000195524799779908,
"loss": 0.9345,
"step": 276
},
{
"epoch": 0.74,
"learning_rate": 0.00019548199332939618,
"loss": 0.9179,
"step": 277
},
{
"epoch": 0.74,
"learning_rate": 0.0001954389878558401,
"loss": 0.9067,
"step": 278
},
{
"epoch": 0.75,
"learning_rate": 0.00019539578344888057,
"loss": 0.9372,
"step": 279
},
{
"epoch": 0.75,
"learning_rate": 0.000195352380198573,
"loss": 0.8735,
"step": 280
},
{
"epoch": 0.75,
"learning_rate": 0.00019530877819538736,
"loss": 0.8642,
"step": 281
},
{
"epoch": 0.75,
"learning_rate": 0.00019526497753020777,
"loss": 0.9678,
"step": 282
},
{
"epoch": 0.76,
"learning_rate": 0.00019522097829433252,
"loss": 0.9099,
"step": 283
},
{
"epoch": 0.76,
"learning_rate": 0.00019517678057947384,
"loss": 0.9025,
"step": 284
},
{
"epoch": 0.76,
"learning_rate": 0.00019513238447775756,
"loss": 0.8574,
"step": 285
},
{
"epoch": 0.76,
"learning_rate": 0.00019508779008172312,
"loss": 0.9845,
"step": 286
},
{
"epoch": 0.77,
"learning_rate": 0.00019504299748432326,
"loss": 0.9582,
"step": 287
},
{
"epoch": 0.77,
"learning_rate": 0.00019499800677892385,
"loss": 0.9092,
"step": 288
},
{
"epoch": 0.77,
"learning_rate": 0.00019495281805930367,
"loss": 0.9318,
"step": 289
},
{
"epoch": 0.78,
"learning_rate": 0.00019490743141965428,
"loss": 0.9727,
"step": 290
},
{
"epoch": 0.78,
"learning_rate": 0.0001948618469545798,
"loss": 0.9132,
"step": 291
},
{
"epoch": 0.78,
"learning_rate": 0.0001948160647590966,
"loss": 0.894,
"step": 292
},
{
"epoch": 0.78,
"learning_rate": 0.0001947700849286333,
"loss": 0.917,
"step": 293
},
{
"epoch": 0.79,
"learning_rate": 0.0001947239075590305,
"loss": 0.9154,
"step": 294
},
{
"epoch": 0.79,
"learning_rate": 0.00019467753274654038,
"loss": 0.8514,
"step": 295
},
{
"epoch": 0.79,
"learning_rate": 0.0001946309605878269,
"loss": 0.8912,
"step": 296
},
{
"epoch": 0.79,
"learning_rate": 0.00019458419117996515,
"loss": 0.8969,
"step": 297
},
{
"epoch": 0.8,
"learning_rate": 0.00019453722462044155,
"loss": 0.9598,
"step": 298
},
{
"epoch": 0.8,
"learning_rate": 0.0001944900610071533,
"loss": 0.8663,
"step": 299
},
{
"epoch": 0.8,
"learning_rate": 0.00019444270043840852,
"loss": 0.8798,
"step": 300
},
{
"epoch": 0.8,
"learning_rate": 0.0001943951430129257,
"loss": 0.9071,
"step": 301
},
{
"epoch": 0.81,
"learning_rate": 0.00019434738882983372,
"loss": 0.8636,
"step": 302
},
{
"epoch": 0.81,
"learning_rate": 0.00019429943798867163,
"loss": 0.8747,
"step": 303
},
{
"epoch": 0.81,
"learning_rate": 0.00019425129058938832,
"loss": 0.8449,
"step": 304
},
{
"epoch": 0.82,
"learning_rate": 0.00019420294673234243,
"loss": 0.8586,
"step": 305
},
{
"epoch": 0.82,
"learning_rate": 0.00019415440651830208,
"loss": 0.9404,
"step": 306
},
{
"epoch": 0.82,
"learning_rate": 0.0001941056700484447,
"loss": 0.8592,
"step": 307
},
{
"epoch": 0.82,
"learning_rate": 0.00019405673742435678,
"loss": 0.8899,
"step": 308
},
{
"epoch": 0.83,
"learning_rate": 0.00019400760874803364,
"loss": 0.9521,
"step": 309
},
{
"epoch": 0.83,
"learning_rate": 0.00019395828412187936,
"loss": 0.8579,
"step": 310
},
{
"epoch": 0.83,
"learning_rate": 0.0001939087636487063,
"loss": 0.9032,
"step": 311
},
{
"epoch": 0.83,
"learning_rate": 0.00019385904743173516,
"loss": 0.926,
"step": 312
},
{
"epoch": 0.84,
"learning_rate": 0.00019380913557459466,
"loss": 0.9557,
"step": 313
},
{
"epoch": 0.84,
"learning_rate": 0.0001937590281813212,
"loss": 0.7916,
"step": 314
},
{
"epoch": 0.84,
"learning_rate": 0.00019370872535635892,
"loss": 0.8927,
"step": 315
},
{
"epoch": 0.84,
"learning_rate": 0.00019365822720455916,
"loss": 0.9148,
"step": 316
},
{
"epoch": 0.85,
"learning_rate": 0.00019360753383118048,
"loss": 0.9015,
"step": 317
},
{
"epoch": 0.85,
"learning_rate": 0.0001935566453418883,
"loss": 0.8738,
"step": 318
},
{
"epoch": 0.85,
"learning_rate": 0.0001935055618427549,
"loss": 0.806,
"step": 319
},
{
"epoch": 0.86,
"learning_rate": 0.00019345428344025883,
"loss": 0.8537,
"step": 320
},
{
"epoch": 0.86,
"learning_rate": 0.00019340281024128508,
"loss": 0.8468,
"step": 321
},
{
"epoch": 0.86,
"learning_rate": 0.0001933511423531245,
"loss": 0.9546,
"step": 322
},
{
"epoch": 0.86,
"learning_rate": 0.0001932992798834739,
"loss": 0.9446,
"step": 323
},
{
"epoch": 0.87,
"learning_rate": 0.00019324722294043558,
"loss": 0.9144,
"step": 324
},
{
"epoch": 0.87,
"learning_rate": 0.00019319497163251728,
"loss": 0.8808,
"step": 325
},
{
"epoch": 0.87,
"learning_rate": 0.0001931425260686318,
"loss": 0.9153,
"step": 326
},
{
"epoch": 0.87,
"learning_rate": 0.00019308988635809688,
"loss": 0.8992,
"step": 327
},
{
"epoch": 0.88,
"learning_rate": 0.00019303705261063497,
"loss": 0.8804,
"step": 328
},
{
"epoch": 0.88,
"learning_rate": 0.0001929840249363729,
"loss": 0.9095,
"step": 329
},
{
"epoch": 0.88,
"learning_rate": 0.00019293080344584177,
"loss": 0.9152,
"step": 330
},
{
"epoch": 0.89,
"learning_rate": 0.00019287738824997673,
"loss": 0.908,
"step": 331
},
{
"epoch": 0.89,
"learning_rate": 0.00019282377946011652,
"loss": 0.9369,
"step": 332
},
{
"epoch": 0.89,
"learning_rate": 0.0001927699771880036,
"loss": 0.8623,
"step": 333
},
{
"epoch": 0.89,
"learning_rate": 0.0001927159815457836,
"loss": 0.933,
"step": 334
},
{
"epoch": 0.9,
"learning_rate": 0.0001926617926460053,
"loss": 0.8951,
"step": 335
},
{
"epoch": 0.9,
"learning_rate": 0.00019260741060162016,
"loss": 0.801,
"step": 336
},
{
"epoch": 0.9,
"learning_rate": 0.0001925528355259824,
"loss": 0.8783,
"step": 337
},
{
"epoch": 0.9,
"learning_rate": 0.0001924980675328485,
"loss": 0.9139,
"step": 338
},
{
"epoch": 0.91,
"learning_rate": 0.00019244310673637708,
"loss": 0.8923,
"step": 339
},
{
"epoch": 0.91,
"learning_rate": 0.0001923879532511287,
"loss": 0.9099,
"step": 340
},
{
"epoch": 0.91,
"learning_rate": 0.0001923326071920654,
"loss": 0.9148,
"step": 341
},
{
"epoch": 0.91,
"learning_rate": 0.0001922770686745508,
"loss": 0.8949,
"step": 342
},
{
"epoch": 0.92,
"learning_rate": 0.00019222133781434956,
"loss": 0.916,
"step": 343
},
{
"epoch": 0.92,
"learning_rate": 0.00019216541472762735,
"loss": 0.8592,
"step": 344
},
{
"epoch": 0.92,
"learning_rate": 0.00019210929953095046,
"loss": 0.8918,
"step": 345
},
{
"epoch": 0.93,
"learning_rate": 0.00019205299234128557,
"loss": 0.8675,
"step": 346
},
{
"epoch": 0.93,
"learning_rate": 0.0001919964932759997,
"loss": 0.8576,
"step": 347
},
{
"epoch": 0.93,
"learning_rate": 0.00019193980245285966,
"loss": 0.9491,
"step": 348
},
{
"epoch": 0.93,
"learning_rate": 0.00019188291999003206,
"loss": 0.8881,
"step": 349
},
{
"epoch": 0.94,
"learning_rate": 0.00019182584600608288,
"loss": 0.8427,
"step": 350
},
{
"epoch": 0.94,
"learning_rate": 0.00019176858061997746,
"loss": 0.8952,
"step": 351
},
{
"epoch": 0.94,
"learning_rate": 0.00019171112395107985,
"loss": 0.929,
"step": 352
},
{
"epoch": 0.94,
"learning_rate": 0.00019165347611915313,
"loss": 0.8859,
"step": 353
},
{
"epoch": 0.95,
"learning_rate": 0.00019159563724435852,
"loss": 0.8892,
"step": 354
},
{
"epoch": 0.95,
"learning_rate": 0.0001915376074472557,
"loss": 0.9353,
"step": 355
},
{
"epoch": 0.95,
"learning_rate": 0.0001914793868488021,
"loss": 0.8909,
"step": 356
},
{
"epoch": 0.95,
"learning_rate": 0.00019142097557035308,
"loss": 0.9188,
"step": 357
},
{
"epoch": 0.96,
"learning_rate": 0.00019136237373366125,
"loss": 0.8827,
"step": 358
},
{
"epoch": 0.96,
"learning_rate": 0.0001913035814608766,
"loss": 0.8683,
"step": 359
},
{
"epoch": 0.96,
"learning_rate": 0.0001912445988745459,
"loss": 0.8518,
"step": 360
},
{
"epoch": 0.97,
"learning_rate": 0.00019118542609761275,
"loss": 0.8154,
"step": 361
},
{
"epoch": 0.97,
"learning_rate": 0.00019112606325341703,
"loss": 0.8554,
"step": 362
},
{
"epoch": 0.97,
"learning_rate": 0.00019106651046569496,
"loss": 0.8837,
"step": 363
},
{
"epoch": 0.97,
"learning_rate": 0.0001910067678585786,
"loss": 0.8799,
"step": 364
},
{
"epoch": 0.98,
"learning_rate": 0.00019094683555659564,
"loss": 0.8812,
"step": 365
},
{
"epoch": 0.98,
"learning_rate": 0.00019088671368466925,
"loss": 0.975,
"step": 366
},
{
"epoch": 0.98,
"learning_rate": 0.00019082640236811767,
"loss": 0.9349,
"step": 367
},
{
"epoch": 0.98,
"learning_rate": 0.00019076590173265406,
"loss": 0.8534,
"step": 368
},
{
"epoch": 0.99,
"learning_rate": 0.00019070521190438618,
"loss": 0.913,
"step": 369
},
{
"epoch": 0.99,
"learning_rate": 0.00019064433300981613,
"loss": 0.8909,
"step": 370
},
{
"epoch": 0.99,
"learning_rate": 0.00019058326517584014,
"loss": 0.8139,
"step": 371
},
{
"epoch": 0.99,
"learning_rate": 0.00019052200852974819,
"loss": 0.82,
"step": 372
},
{
"epoch": 1.0,
"learning_rate": 0.000190460563199224,
"loss": 0.8311,
"step": 373
},
{
"epoch": 1.0,
"learning_rate": 0.00019039892931234435,
"loss": 0.8549,
"step": 374
},
{
"epoch": 1.0,
"learning_rate": 0.00019033710699757918,
"loss": 0.6178,
"step": 375
},
{
"epoch": 1.01,
"learning_rate": 0.0001902750963837912,
"loss": 0.5785,
"step": 376
},
{
"epoch": 1.01,
"learning_rate": 0.00019021289760023553,
"loss": 0.5207,
"step": 377
},
{
"epoch": 1.01,
"learning_rate": 0.0001901505107765596,
"loss": 0.6449,
"step": 378
},
{
"epoch": 1.01,
"learning_rate": 0.00019008793604280276,
"loss": 0.5224,
"step": 379
},
{
"epoch": 1.02,
"learning_rate": 0.00019002517352939598,
"loss": 0.5561,
"step": 380
},
{
"epoch": 1.02,
"learning_rate": 0.00018996222336716172,
"loss": 0.5441,
"step": 381
},
{
"epoch": 1.02,
"learning_rate": 0.00018989908568731357,
"loss": 0.5335,
"step": 382
},
{
"epoch": 1.02,
"learning_rate": 0.00018983576062145594,
"loss": 0.5755,
"step": 383
},
{
"epoch": 1.03,
"learning_rate": 0.0001897722483015838,
"loss": 0.544,
"step": 384
},
{
"epoch": 1.03,
"learning_rate": 0.00018970854886008257,
"loss": 0.5523,
"step": 385
},
{
"epoch": 1.03,
"learning_rate": 0.00018964466242972757,
"loss": 0.573,
"step": 386
},
{
"epoch": 1.03,
"learning_rate": 0.00018958058914368394,
"loss": 0.6111,
"step": 387
},
{
"epoch": 1.04,
"learning_rate": 0.00018951632913550626,
"loss": 0.4804,
"step": 388
},
{
"epoch": 1.04,
"learning_rate": 0.00018945188253913835,
"loss": 0.5786,
"step": 389
},
{
"epoch": 1.04,
"learning_rate": 0.000189387249488913,
"loss": 0.5293,
"step": 390
},
{
"epoch": 1.05,
"learning_rate": 0.00018932243011955154,
"loss": 0.5162,
"step": 391
},
{
"epoch": 1.05,
"learning_rate": 0.00018925742456616374,
"loss": 0.55,
"step": 392
},
{
"epoch": 1.05,
"learning_rate": 0.00018919223296424745,
"loss": 0.5118,
"step": 393
},
{
"epoch": 1.05,
"learning_rate": 0.0001891268554496883,
"loss": 0.5953,
"step": 394
},
{
"epoch": 1.06,
"learning_rate": 0.0001890612921587594,
"loss": 0.5739,
"step": 395
},
{
"epoch": 1.06,
"learning_rate": 0.0001889955432281212,
"loss": 0.5253,
"step": 396
},
{
"epoch": 1.06,
"learning_rate": 0.00018892960879482093,
"loss": 0.5679,
"step": 397
},
{
"epoch": 1.06,
"learning_rate": 0.00018886348899629267,
"loss": 0.5316,
"step": 398
},
{
"epoch": 1.07,
"learning_rate": 0.00018879718397035679,
"loss": 0.621,
"step": 399
},
{
"epoch": 1.07,
"learning_rate": 0.0001887306938552197,
"loss": 0.514,
"step": 400
},
{
"epoch": 1.07,
"learning_rate": 0.00018866401878947367,
"loss": 0.5574,
"step": 401
},
{
"epoch": 1.07,
"learning_rate": 0.0001885971589120965,
"loss": 0.5134,
"step": 402
},
{
"epoch": 1.08,
"learning_rate": 0.00018853011436245114,
"loss": 0.6117,
"step": 403
},
{
"epoch": 1.08,
"learning_rate": 0.00018846288528028555,
"loss": 0.5296,
"step": 404
},
{
"epoch": 1.08,
"learning_rate": 0.00018839547180573226,
"loss": 0.5311,
"step": 405
},
{
"epoch": 1.09,
"learning_rate": 0.00018832787407930824,
"loss": 0.5211,
"step": 406
},
{
"epoch": 1.09,
"learning_rate": 0.0001882600922419144,
"loss": 0.5998,
"step": 407
},
{
"epoch": 1.09,
"learning_rate": 0.0001881921264348355,
"loss": 0.5571,
"step": 408
},
{
"epoch": 1.09,
"learning_rate": 0.00018812397679973975,
"loss": 0.5777,
"step": 409
},
{
"epoch": 1.1,
"learning_rate": 0.00018805564347867848,
"loss": 0.5494,
"step": 410
},
{
"epoch": 1.1,
"learning_rate": 0.00018798712661408592,
"loss": 0.5371,
"step": 411
},
{
"epoch": 1.1,
"learning_rate": 0.00018791842634877898,
"loss": 0.553,
"step": 412
},
{
"epoch": 1.1,
"learning_rate": 0.0001878495428259567,
"loss": 0.5449,
"step": 413
},
{
"epoch": 1.11,
"learning_rate": 0.00018778047618920013,
"loss": 0.5309,
"step": 414
},
{
"epoch": 1.11,
"learning_rate": 0.00018771122658247212,
"loss": 0.5232,
"step": 415
},
{
"epoch": 1.11,
"learning_rate": 0.00018764179415011682,
"loss": 0.6046,
"step": 416
},
{
"epoch": 1.11,
"learning_rate": 0.00018757217903685942,
"loss": 0.5487,
"step": 417
},
{
"epoch": 1.12,
"learning_rate": 0.00018750238138780595,
"loss": 0.5504,
"step": 418
},
{
"epoch": 1.12,
"learning_rate": 0.0001874324013484429,
"loss": 0.6012,
"step": 419
},
{
"epoch": 1.12,
"learning_rate": 0.00018736223906463696,
"loss": 0.545,
"step": 420
},
{
"epoch": 1.13,
"learning_rate": 0.00018729189468263467,
"loss": 0.5734,
"step": 421
},
{
"epoch": 1.13,
"learning_rate": 0.00018722136834906214,
"loss": 0.5774,
"step": 422
},
{
"epoch": 1.13,
"learning_rate": 0.00018715066021092472,
"loss": 0.5519,
"step": 423
},
{
"epoch": 1.13,
"learning_rate": 0.0001870797704156067,
"loss": 0.5828,
"step": 424
},
{
"epoch": 1.14,
"learning_rate": 0.00018700869911087115,
"loss": 0.562,
"step": 425
},
{
"epoch": 1.14,
"learning_rate": 0.0001869374464448593,
"loss": 0.5932,
"step": 426
},
{
"epoch": 1.14,
"learning_rate": 0.0001868660125660905,
"loss": 0.5596,
"step": 427
},
{
"epoch": 1.14,
"learning_rate": 0.00018679439762346185,
"loss": 0.5892,
"step": 428
},
{
"epoch": 1.15,
"learning_rate": 0.00018672260176624776,
"loss": 0.5716,
"step": 429
},
{
"epoch": 1.15,
"learning_rate": 0.00018665062514409983,
"loss": 0.5227,
"step": 430
},
{
"epoch": 1.15,
"learning_rate": 0.0001865784679070464,
"loss": 0.551,
"step": 431
},
{
"epoch": 1.16,
"learning_rate": 0.00018650613020549232,
"loss": 0.4903,
"step": 432
},
{
"epoch": 1.16,
"learning_rate": 0.00018643361219021858,
"loss": 0.6051,
"step": 433
},
{
"epoch": 1.16,
"learning_rate": 0.000186360914012382,
"loss": 0.5801,
"step": 434
},
{
"epoch": 1.16,
"learning_rate": 0.00018628803582351497,
"loss": 0.5606,
"step": 435
},
{
"epoch": 1.17,
"learning_rate": 0.00018621497777552507,
"loss": 0.5793,
"step": 436
},
{
"epoch": 1.17,
"learning_rate": 0.00018614174002069478,
"loss": 0.5721,
"step": 437
},
{
"epoch": 1.17,
"learning_rate": 0.00018606832271168114,
"loss": 0.5139,
"step": 438
},
{
"epoch": 1.17,
"learning_rate": 0.00018599472600151553,
"loss": 0.5738,
"step": 439
},
{
"epoch": 1.18,
"learning_rate": 0.00018592095004360318,
"loss": 0.5602,
"step": 440
},
{
"epoch": 1.18,
"learning_rate": 0.00018584699499172303,
"loss": 0.6052,
"step": 441
},
{
"epoch": 1.18,
"learning_rate": 0.00018577286100002723,
"loss": 0.5002,
"step": 442
},
{
"epoch": 1.18,
"learning_rate": 0.00018569854822304098,
"loss": 0.55,
"step": 443
},
{
"epoch": 1.19,
"learning_rate": 0.00018562405681566216,
"loss": 0.5388,
"step": 444
},
{
"epoch": 1.19,
"learning_rate": 0.00018554938693316094,
"loss": 0.5759,
"step": 445
},
{
"epoch": 1.19,
"learning_rate": 0.0001854745387311795,
"loss": 0.5964,
"step": 446
},
{
"epoch": 1.2,
"learning_rate": 0.00018539951236573173,
"loss": 0.5168,
"step": 447
},
{
"epoch": 1.2,
"learning_rate": 0.0001853243079932029,
"loss": 0.5895,
"step": 448
},
{
"epoch": 1.2,
"learning_rate": 0.0001852489257703493,
"loss": 0.536,
"step": 449
},
{
"epoch": 1.2,
"learning_rate": 0.00018517336585429793,
"loss": 0.4959,
"step": 450
},
{
"epoch": 1.21,
"learning_rate": 0.00018509762840254615,
"loss": 0.5137,
"step": 451
},
{
"epoch": 1.21,
"learning_rate": 0.00018502171357296144,
"loss": 0.6167,
"step": 452
},
{
"epoch": 1.21,
"learning_rate": 0.00018494562152378095,
"loss": 0.5498,
"step": 453
},
{
"epoch": 1.21,
"learning_rate": 0.00018486935241361125,
"loss": 0.5808,
"step": 454
},
{
"epoch": 1.22,
"learning_rate": 0.00018479290640142798,
"loss": 0.5715,
"step": 455
},
{
"epoch": 1.22,
"learning_rate": 0.00018471628364657555,
"loss": 0.5829,
"step": 456
},
{
"epoch": 1.22,
"learning_rate": 0.00018463948430876665,
"loss": 0.5513,
"step": 457
},
{
"epoch": 1.22,
"learning_rate": 0.00018456250854808218,
"loss": 0.5828,
"step": 458
},
{
"epoch": 1.23,
"learning_rate": 0.00018448535652497073,
"loss": 0.5145,
"step": 459
},
{
"epoch": 1.23,
"learning_rate": 0.00018440802840024822,
"loss": 0.554,
"step": 460
},
{
"epoch": 1.23,
"learning_rate": 0.00018433052433509777,
"loss": 0.6146,
"step": 461
},
{
"epoch": 1.24,
"learning_rate": 0.0001842528444910691,
"loss": 0.5421,
"step": 462
},
{
"epoch": 1.24,
"learning_rate": 0.00018417498903007843,
"loss": 0.549,
"step": 463
},
{
"epoch": 1.24,
"learning_rate": 0.00018409695811440796,
"loss": 0.5506,
"step": 464
},
{
"epoch": 1.24,
"learning_rate": 0.00018401875190670567,
"loss": 0.5324,
"step": 465
},
{
"epoch": 1.25,
"learning_rate": 0.00018394037056998483,
"loss": 0.5648,
"step": 466
},
{
"epoch": 1.25,
"learning_rate": 0.00018386181426762388,
"loss": 0.5746,
"step": 467
},
{
"epoch": 1.25,
"learning_rate": 0.00018378308316336584,
"loss": 0.5688,
"step": 468
},
{
"epoch": 1.25,
"learning_rate": 0.00018370417742131814,
"loss": 0.5365,
"step": 469
},
{
"epoch": 1.26,
"learning_rate": 0.00018362509720595225,
"loss": 0.6208,
"step": 470
},
{
"epoch": 1.26,
"learning_rate": 0.00018354584268210326,
"loss": 0.5877,
"step": 471
},
{
"epoch": 1.26,
"learning_rate": 0.0001834664140149696,
"loss": 0.5634,
"step": 472
},
{
"epoch": 1.26,
"learning_rate": 0.0001833868113701127,
"loss": 0.5813,
"step": 473
},
{
"epoch": 1.27,
"learning_rate": 0.00018330703491345669,
"loss": 0.5401,
"step": 474
},
{
"epoch": 1.27,
"learning_rate": 0.00018322708481128785,
"loss": 0.5983,
"step": 475
},
{
"epoch": 1.27,
"learning_rate": 0.00018314696123025454,
"loss": 0.5615,
"step": 476
},
{
"epoch": 1.28,
"learning_rate": 0.00018306666433736662,
"loss": 0.5214,
"step": 477
},
{
"epoch": 1.28,
"learning_rate": 0.0001829861942999953,
"loss": 0.5947,
"step": 478
},
{
"epoch": 1.28,
"learning_rate": 0.00018290555128587264,
"loss": 0.5417,
"step": 479
},
{
"epoch": 1.28,
"learning_rate": 0.0001828247354630912,
"loss": 0.5784,
"step": 480
},
{
"epoch": 1.29,
"learning_rate": 0.00018274374700010389,
"loss": 0.5754,
"step": 481
},
{
"epoch": 1.29,
"learning_rate": 0.00018266258606572332,
"loss": 0.5494,
"step": 482
},
{
"epoch": 1.29,
"learning_rate": 0.00018258125282912167,
"loss": 0.5256,
"step": 483
},
{
"epoch": 1.29,
"learning_rate": 0.00018249974745983023,
"loss": 0.5412,
"step": 484
},
{
"epoch": 1.3,
"learning_rate": 0.0001824180701277392,
"loss": 0.5243,
"step": 485
},
{
"epoch": 1.3,
"learning_rate": 0.00018233622100309707,
"loss": 0.5233,
"step": 486
},
{
"epoch": 1.3,
"learning_rate": 0.0001822542002565105,
"loss": 0.5108,
"step": 487
},
{
"epoch": 1.3,
"learning_rate": 0.00018217200805894384,
"loss": 0.5498,
"step": 488
},
{
"epoch": 1.31,
"learning_rate": 0.00018208964458171884,
"loss": 0.5717,
"step": 489
},
{
"epoch": 1.31,
"learning_rate": 0.0001820071099965143,
"loss": 0.5795,
"step": 490
},
{
"epoch": 1.31,
"learning_rate": 0.00018192440447536553,
"loss": 0.5475,
"step": 491
},
{
"epoch": 1.32,
"learning_rate": 0.00018184152819066435,
"loss": 0.5376,
"step": 492
},
{
"epoch": 1.32,
"learning_rate": 0.00018175848131515837,
"loss": 0.5728,
"step": 493
},
{
"epoch": 1.32,
"learning_rate": 0.00018167526402195082,
"loss": 0.5405,
"step": 494
},
{
"epoch": 1.32,
"learning_rate": 0.0001815918764845002,
"loss": 0.6,
"step": 495
},
{
"epoch": 1.33,
"learning_rate": 0.00018150831887661978,
"loss": 0.4944,
"step": 496
},
{
"epoch": 1.33,
"learning_rate": 0.00018142459137247737,
"loss": 0.5435,
"step": 497
},
{
"epoch": 1.33,
"learning_rate": 0.00018134069414659494,
"loss": 0.5958,
"step": 498
},
{
"epoch": 1.33,
"learning_rate": 0.00018125662737384813,
"loss": 0.6247,
"step": 499
},
{
"epoch": 1.34,
"learning_rate": 0.00018117239122946615,
"loss": 0.5869,
"step": 500
},
{
"epoch": 1.34,
"learning_rate": 0.00018108798588903105,
"loss": 0.5468,
"step": 501
},
{
"epoch": 1.34,
"learning_rate": 0.00018100341152847772,
"loss": 0.5646,
"step": 502
},
{
"epoch": 1.34,
"learning_rate": 0.00018091866832409332,
"loss": 0.6211,
"step": 503
},
{
"epoch": 1.35,
"learning_rate": 0.00018083375645251684,
"loss": 0.5478,
"step": 504
},
{
"epoch": 1.35,
"learning_rate": 0.000180748676090739,
"loss": 0.5613,
"step": 505
},
{
"epoch": 1.35,
"learning_rate": 0.00018066342741610155,
"loss": 0.5689,
"step": 506
},
{
"epoch": 1.36,
"learning_rate": 0.00018057801060629726,
"loss": 0.5567,
"step": 507
},
{
"epoch": 1.36,
"learning_rate": 0.0001804924258393692,
"loss": 0.5233,
"step": 508
},
{
"epoch": 1.36,
"learning_rate": 0.00018040667329371064,
"loss": 0.5867,
"step": 509
},
{
"epoch": 1.36,
"learning_rate": 0.00018032075314806448,
"loss": 0.553,
"step": 510
},
{
"epoch": 1.37,
"learning_rate": 0.00018023466558152307,
"loss": 0.5272,
"step": 511
},
{
"epoch": 1.37,
"learning_rate": 0.00018014841077352762,
"loss": 0.5694,
"step": 512
},
{
"epoch": 1.37,
"learning_rate": 0.000180061988903868,
"loss": 0.5311,
"step": 513
},
{
"epoch": 1.37,
"learning_rate": 0.00017997540015268234,
"loss": 0.6145,
"step": 514
},
{
"epoch": 1.38,
"learning_rate": 0.0001798886447004565,
"loss": 0.5415,
"step": 515
},
{
"epoch": 1.38,
"learning_rate": 0.000179801722728024,
"loss": 0.5626,
"step": 516
},
{
"epoch": 1.38,
"learning_rate": 0.0001797146344165652,
"loss": 0.5498,
"step": 517
},
{
"epoch": 1.39,
"learning_rate": 0.0001796273799476074,
"loss": 0.5282,
"step": 518
},
{
"epoch": 1.39,
"learning_rate": 0.00017953995950302417,
"loss": 0.5259,
"step": 519
},
{
"epoch": 1.39,
"learning_rate": 0.00017945237326503507,
"loss": 0.5822,
"step": 520
},
{
"epoch": 1.39,
"learning_rate": 0.00017936462141620506,
"loss": 0.5696,
"step": 521
},
{
"epoch": 1.4,
"learning_rate": 0.00017927670413944458,
"loss": 0.5868,
"step": 522
},
{
"epoch": 1.4,
"learning_rate": 0.00017918862161800866,
"loss": 0.5585,
"step": 523
},
{
"epoch": 1.4,
"learning_rate": 0.00017910037403549693,
"loss": 0.5425,
"step": 524
},
{
"epoch": 1.4,
"learning_rate": 0.00017901196157585293,
"loss": 0.5311,
"step": 525
},
{
"epoch": 1.41,
"learning_rate": 0.00017892338442336399,
"loss": 0.5621,
"step": 526
},
{
"epoch": 1.41,
"learning_rate": 0.00017883464276266064,
"loss": 0.5717,
"step": 527
},
{
"epoch": 1.41,
"learning_rate": 0.0001787457367787164,
"loss": 0.5715,
"step": 528
},
{
"epoch": 1.41,
"learning_rate": 0.00017865666665684718,
"loss": 0.5406,
"step": 529
},
{
"epoch": 1.42,
"learning_rate": 0.00017856743258271113,
"loss": 0.5367,
"step": 530
},
{
"epoch": 1.42,
"learning_rate": 0.00017847803474230813,
"loss": 0.5486,
"step": 531
},
{
"epoch": 1.42,
"learning_rate": 0.00017838847332197938,
"loss": 0.5567,
"step": 532
},
{
"epoch": 1.43,
"learning_rate": 0.00017829874850840705,
"loss": 0.5706,
"step": 533
},
{
"epoch": 1.43,
"learning_rate": 0.0001782088604886139,
"loss": 0.5575,
"step": 534
},
{
"epoch": 1.43,
"learning_rate": 0.00017811880944996285,
"loss": 0.5344,
"step": 535
},
{
"epoch": 1.43,
"learning_rate": 0.00017802859558015664,
"loss": 0.5341,
"step": 536
},
{
"epoch": 1.44,
"learning_rate": 0.00017793821906723748,
"loss": 0.5387,
"step": 537
},
{
"epoch": 1.44,
"learning_rate": 0.00017784768009958648,
"loss": 0.5255,
"step": 538
},
{
"epoch": 1.44,
"learning_rate": 0.00017775697886592345,
"loss": 0.5784,
"step": 539
},
{
"epoch": 1.44,
"learning_rate": 0.00017766611555530636,
"loss": 0.564,
"step": 540
},
{
"epoch": 1.45,
"learning_rate": 0.00017757509035713106,
"loss": 0.5698,
"step": 541
},
{
"epoch": 1.45,
"learning_rate": 0.00017748390346113087,
"loss": 0.4706,
"step": 542
},
{
"epoch": 1.45,
"learning_rate": 0.0001773925550573761,
"loss": 0.5536,
"step": 543
},
{
"epoch": 1.45,
"learning_rate": 0.0001773010453362737,
"loss": 0.5287,
"step": 544
},
{
"epoch": 1.46,
"learning_rate": 0.00017720937448856692,
"loss": 0.5769,
"step": 545
},
{
"epoch": 1.46,
"learning_rate": 0.00017711754270533482,
"loss": 0.5955,
"step": 546
},
{
"epoch": 1.46,
"learning_rate": 0.00017702555017799196,
"loss": 0.5374,
"step": 547
},
{
"epoch": 1.47,
"learning_rate": 0.00017693339709828792,
"loss": 0.5597,
"step": 548
},
{
"epoch": 1.47,
"learning_rate": 0.00017684108365830688,
"loss": 0.6138,
"step": 549
},
{
"epoch": 1.47,
"learning_rate": 0.00017674861005046743,
"loss": 0.5432,
"step": 550
},
{
"epoch": 1.47,
"learning_rate": 0.00017665597646752187,
"loss": 0.5147,
"step": 551
},
{
"epoch": 1.48,
"learning_rate": 0.00017656318310255604,
"loss": 0.5355,
"step": 552
},
{
"epoch": 1.48,
"learning_rate": 0.00017647023014898876,
"loss": 0.5321,
"step": 553
},
{
"epoch": 1.48,
"learning_rate": 0.00017637711780057157,
"loss": 0.5944,
"step": 554
},
{
"epoch": 1.48,
"learning_rate": 0.0001762838462513882,
"loss": 0.5387,
"step": 555
},
{
"epoch": 1.49,
"learning_rate": 0.00017619041569585418,
"loss": 0.5484,
"step": 556
},
{
"epoch": 1.49,
"learning_rate": 0.00017609682632871665,
"loss": 0.5675,
"step": 557
},
{
"epoch": 1.49,
"learning_rate": 0.00017600307834505355,
"loss": 0.5911,
"step": 558
},
{
"epoch": 1.49,
"learning_rate": 0.00017590917194027362,
"loss": 0.5493,
"step": 559
},
{
"epoch": 1.5,
"learning_rate": 0.0001758151073101157,
"loss": 0.506,
"step": 560
},
{
"epoch": 1.5,
"learning_rate": 0.00017572088465064848,
"loss": 0.541,
"step": 561
},
{
"epoch": 1.5,
"learning_rate": 0.00017562650415827005,
"loss": 0.5412,
"step": 562
},
{
"epoch": 1.51,
"learning_rate": 0.00017553196602970746,
"loss": 0.5407,
"step": 563
},
{
"epoch": 1.51,
"learning_rate": 0.0001754372704620164,
"loss": 0.5331,
"step": 564
},
{
"epoch": 1.51,
"learning_rate": 0.0001753424176525807,
"loss": 0.5546,
"step": 565
},
{
"epoch": 1.51,
"learning_rate": 0.00017524740779911185,
"loss": 0.541,
"step": 566
},
{
"epoch": 1.52,
"learning_rate": 0.0001751522410996488,
"loss": 0.5736,
"step": 567
},
{
"epoch": 1.52,
"learning_rate": 0.00017505691775255745,
"loss": 0.5349,
"step": 568
},
{
"epoch": 1.52,
"learning_rate": 0.00017496143795653007,
"loss": 0.5286,
"step": 569
},
{
"epoch": 1.52,
"learning_rate": 0.0001748658019105852,
"loss": 0.5765,
"step": 570
},
{
"epoch": 1.53,
"learning_rate": 0.00017477000981406694,
"loss": 0.5543,
"step": 571
},
{
"epoch": 1.53,
"learning_rate": 0.00017467406186664474,
"loss": 0.5158,
"step": 572
},
{
"epoch": 1.53,
"learning_rate": 0.0001745779582683129,
"loss": 0.5742,
"step": 573
},
{
"epoch": 1.53,
"learning_rate": 0.00017448169921939014,
"loss": 0.5273,
"step": 574
},
{
"epoch": 1.54,
"learning_rate": 0.00017438528492051914,
"loss": 0.5504,
"step": 575
},
{
"epoch": 1.54,
"learning_rate": 0.0001742887155726663,
"loss": 0.5788,
"step": 576
},
{
"epoch": 1.54,
"learning_rate": 0.00017419199137712113,
"loss": 0.5477,
"step": 577
},
{
"epoch": 1.55,
"learning_rate": 0.00017409511253549593,
"loss": 0.5727,
"step": 578
},
{
"epoch": 1.55,
"learning_rate": 0.00017399807924972532,
"loss": 0.5299,
"step": 579
},
{
"epoch": 1.55,
"learning_rate": 0.00017390089172206592,
"loss": 0.5493,
"step": 580
},
{
"epoch": 1.55,
"learning_rate": 0.00017380355015509576,
"loss": 0.5587,
"step": 581
},
{
"epoch": 1.56,
"learning_rate": 0.00017370605475171397,
"loss": 0.5634,
"step": 582
},
{
"epoch": 1.56,
"learning_rate": 0.0001736084057151404,
"loss": 0.5642,
"step": 583
},
{
"epoch": 1.56,
"learning_rate": 0.00017351060324891502,
"loss": 0.5553,
"step": 584
},
{
"epoch": 1.56,
"learning_rate": 0.00017341264755689776,
"loss": 0.5824,
"step": 585
},
{
"epoch": 1.57,
"learning_rate": 0.00017331453884326782,
"loss": 0.5734,
"step": 586
},
{
"epoch": 1.57,
"learning_rate": 0.00017321627731252336,
"loss": 0.51,
"step": 587
},
{
"epoch": 1.57,
"learning_rate": 0.0001731178631694811,
"loss": 0.5332,
"step": 588
},
{
"epoch": 1.57,
"learning_rate": 0.00017301929661927589,
"loss": 0.5572,
"step": 589
},
{
"epoch": 1.58,
"learning_rate": 0.00017292057786736026,
"loss": 0.5312,
"step": 590
},
{
"epoch": 1.58,
"learning_rate": 0.00017282170711950396,
"loss": 0.5612,
"step": 591
},
{
"epoch": 1.58,
"learning_rate": 0.00017272268458179353,
"loss": 0.5745,
"step": 592
},
{
"epoch": 1.59,
"learning_rate": 0.000172623510460632,
"loss": 0.5343,
"step": 593
},
{
"epoch": 1.59,
"learning_rate": 0.00017252418496273823,
"loss": 0.5724,
"step": 594
},
{
"epoch": 1.59,
"learning_rate": 0.00017242470829514672,
"loss": 0.5594,
"step": 595
},
{
"epoch": 1.59,
"learning_rate": 0.00017232508066520702,
"loss": 0.4893,
"step": 596
},
{
"epoch": 1.6,
"learning_rate": 0.00017222530228058335,
"loss": 0.5414,
"step": 597
},
{
"epoch": 1.6,
"learning_rate": 0.00017212537334925415,
"loss": 0.5558,
"step": 598
},
{
"epoch": 1.6,
"learning_rate": 0.00017202529407951177,
"loss": 0.5773,
"step": 599
},
{
"epoch": 1.6,
"learning_rate": 0.00017192506467996174,
"loss": 0.503,
"step": 600
},
{
"epoch": 1.61,
"learning_rate": 0.00017182468535952263,
"loss": 0.5941,
"step": 601
},
{
"epoch": 1.61,
"learning_rate": 0.00017172415632742553,
"loss": 0.5373,
"step": 602
},
{
"epoch": 1.61,
"learning_rate": 0.00017162347779321353,
"loss": 0.5431,
"step": 603
},
{
"epoch": 1.61,
"learning_rate": 0.00017152264996674136,
"loss": 0.5308,
"step": 604
},
{
"epoch": 1.62,
"learning_rate": 0.00017142167305817495,
"loss": 0.5737,
"step": 605
},
{
"epoch": 1.62,
"learning_rate": 0.00017132054727799097,
"loss": 0.5558,
"step": 606
},
{
"epoch": 1.62,
"learning_rate": 0.00017121927283697636,
"loss": 0.5324,
"step": 607
},
{
"epoch": 1.63,
"learning_rate": 0.00017111784994622804,
"loss": 0.5219,
"step": 608
},
{
"epoch": 1.63,
"learning_rate": 0.0001710162788171522,
"loss": 0.567,
"step": 609
},
{
"epoch": 1.63,
"learning_rate": 0.00017091455966146416,
"loss": 0.5482,
"step": 610
},
{
"epoch": 1.63,
"learning_rate": 0.00017081269269118772,
"loss": 0.574,
"step": 611
},
{
"epoch": 1.64,
"learning_rate": 0.00017071067811865476,
"loss": 0.523,
"step": 612
},
{
"epoch": 1.64,
"learning_rate": 0.00017060851615650487,
"loss": 0.4961,
"step": 613
},
{
"epoch": 1.64,
"learning_rate": 0.0001705062070176849,
"loss": 0.5397,
"step": 614
},
{
"epoch": 1.64,
"learning_rate": 0.0001704037509154484,
"loss": 0.5062,
"step": 615
},
{
"epoch": 1.65,
"learning_rate": 0.00017030114806335526,
"loss": 0.5004,
"step": 616
},
{
"epoch": 1.65,
"learning_rate": 0.00017019839867527122,
"loss": 0.5421,
"step": 617
},
{
"epoch": 1.65,
"learning_rate": 0.00017009550296536761,
"loss": 0.5817,
"step": 618
},
{
"epoch": 1.66,
"learning_rate": 0.0001699924611481206,
"loss": 0.527,
"step": 619
},
{
"epoch": 1.66,
"learning_rate": 0.00016988927343831095,
"loss": 0.5805,
"step": 620
},
{
"epoch": 1.66,
"learning_rate": 0.00016978594005102356,
"loss": 0.5618,
"step": 621
},
{
"epoch": 1.66,
"learning_rate": 0.00016968246120164693,
"loss": 0.5264,
"step": 622
},
{
"epoch": 1.67,
"learning_rate": 0.00016957883710587277,
"loss": 0.5207,
"step": 623
},
{
"epoch": 1.67,
"learning_rate": 0.00016947506797969562,
"loss": 0.5745,
"step": 624
},
{
"epoch": 1.67,
"learning_rate": 0.00016937115403941217,
"loss": 0.4957,
"step": 625
},
{
"epoch": 1.67,
"learning_rate": 0.00016926709550162111,
"loss": 0.5531,
"step": 626
},
{
"epoch": 1.68,
"learning_rate": 0.00016916289258322244,
"loss": 0.4813,
"step": 627
},
{
"epoch": 1.68,
"learning_rate": 0.00016905854550141716,
"loss": 0.5273,
"step": 628
},
{
"epoch": 1.68,
"learning_rate": 0.0001689540544737067,
"loss": 0.5878,
"step": 629
},
{
"epoch": 1.68,
"learning_rate": 0.0001688494197178926,
"loss": 0.576,
"step": 630
},
{
"epoch": 1.69,
"learning_rate": 0.00016874464145207597,
"loss": 0.5435,
"step": 631
},
{
"epoch": 1.69,
"learning_rate": 0.00016863971989465698,
"loss": 0.5973,
"step": 632
},
{
"epoch": 1.69,
"learning_rate": 0.00016853465526433462,
"loss": 0.5039,
"step": 633
},
{
"epoch": 1.7,
"learning_rate": 0.00016842944778010596,
"loss": 0.5571,
"step": 634
},
{
"epoch": 1.7,
"learning_rate": 0.00016832409766126593,
"loss": 0.4919,
"step": 635
},
{
"epoch": 1.7,
"learning_rate": 0.00016821860512740671,
"loss": 0.5561,
"step": 636
},
{
"epoch": 1.7,
"learning_rate": 0.0001681129703984174,
"loss": 0.552,
"step": 637
},
{
"epoch": 1.71,
"learning_rate": 0.00016800719369448338,
"loss": 0.5565,
"step": 638
},
{
"epoch": 1.71,
"learning_rate": 0.00016790127523608607,
"loss": 0.5467,
"step": 639
},
{
"epoch": 1.71,
"learning_rate": 0.00016779521524400232,
"loss": 0.6386,
"step": 640
},
{
"epoch": 1.71,
"learning_rate": 0.000167689013939304,
"loss": 0.5258,
"step": 641
},
{
"epoch": 1.72,
"learning_rate": 0.00016758267154335748,
"loss": 0.5744,
"step": 642
},
{
"epoch": 1.72,
"learning_rate": 0.00016747618827782338,
"loss": 0.4784,
"step": 643
},
{
"epoch": 1.72,
"learning_rate": 0.00016736956436465573,
"loss": 0.5621,
"step": 644
},
{
"epoch": 1.72,
"learning_rate": 0.0001672628000261019,
"loss": 0.5255,
"step": 645
},
{
"epoch": 1.73,
"learning_rate": 0.00016715589548470185,
"loss": 0.5402,
"step": 646
},
{
"epoch": 1.73,
"learning_rate": 0.00016704885096328786,
"loss": 0.5321,
"step": 647
},
{
"epoch": 1.73,
"learning_rate": 0.00016694166668498398,
"loss": 0.5553,
"step": 648
},
{
"epoch": 1.74,
"learning_rate": 0.00016683434287320548,
"loss": 0.5566,
"step": 649
},
{
"epoch": 1.74,
"learning_rate": 0.00016672687975165858,
"loss": 0.5503,
"step": 650
},
{
"epoch": 1.74,
"learning_rate": 0.00016661927754433982,
"loss": 0.5554,
"step": 651
},
{
"epoch": 1.74,
"learning_rate": 0.00016651153647553567,
"loss": 0.5294,
"step": 652
},
{
"epoch": 1.75,
"learning_rate": 0.00016640365676982207,
"loss": 0.5415,
"step": 653
},
{
"epoch": 1.75,
"learning_rate": 0.00016629563865206386,
"loss": 0.5385,
"step": 654
},
{
"epoch": 1.75,
"learning_rate": 0.0001661874823474144,
"loss": 0.5524,
"step": 655
},
{
"epoch": 1.75,
"learning_rate": 0.00016607918808131525,
"loss": 0.4864,
"step": 656
},
{
"epoch": 1.76,
"learning_rate": 0.00016597075607949525,
"loss": 0.5241,
"step": 657
},
{
"epoch": 1.76,
"learning_rate": 0.0001658621865679706,
"loss": 0.567,
"step": 658
},
{
"epoch": 1.76,
"learning_rate": 0.00016575347977304398,
"loss": 0.5745,
"step": 659
},
{
"epoch": 1.76,
"learning_rate": 0.00016564463592130428,
"loss": 0.5451,
"step": 660
},
{
"epoch": 1.77,
"learning_rate": 0.00016553565523962603,
"loss": 0.5574,
"step": 661
},
{
"epoch": 1.77,
"learning_rate": 0.00016542653795516898,
"loss": 0.534,
"step": 662
},
{
"epoch": 1.77,
"learning_rate": 0.00016531728429537766,
"loss": 0.5409,
"step": 663
},
{
"epoch": 1.78,
"learning_rate": 0.00016520789448798087,
"loss": 0.5638,
"step": 664
},
{
"epoch": 1.78,
"learning_rate": 0.0001650983687609911,
"loss": 0.5474,
"step": 665
},
{
"epoch": 1.78,
"learning_rate": 0.00016498870734270418,
"loss": 0.5208,
"step": 666
},
{
"epoch": 1.78,
"learning_rate": 0.00016487891046169887,
"loss": 0.5063,
"step": 667
},
{
"epoch": 1.79,
"learning_rate": 0.0001647689783468362,
"loss": 0.4932,
"step": 668
},
{
"epoch": 1.79,
"learning_rate": 0.0001646589112272591,
"loss": 0.5842,
"step": 669
},
{
"epoch": 1.79,
"learning_rate": 0.0001645487093323919,
"loss": 0.5152,
"step": 670
},
{
"epoch": 1.79,
"learning_rate": 0.0001644383728919399,
"loss": 0.545,
"step": 671
},
{
"epoch": 1.8,
"learning_rate": 0.00016432790213588872,
"loss": 0.5405,
"step": 672
},
{
"epoch": 1.8,
"learning_rate": 0.0001642172972945042,
"loss": 0.579,
"step": 673
},
{
"epoch": 1.8,
"learning_rate": 0.00016410655859833137,
"loss": 0.5485,
"step": 674
},
{
"epoch": 1.8,
"learning_rate": 0.00016399568627819443,
"loss": 0.6246,
"step": 675
},
{
"epoch": 1.81,
"learning_rate": 0.00016388468056519612,
"loss": 0.519,
"step": 676
},
{
"epoch": 1.81,
"learning_rate": 0.00016377354169071722,
"loss": 0.542,
"step": 677
},
{
"epoch": 1.81,
"learning_rate": 0.00016366226988641594,
"loss": 0.5102,
"step": 678
},
{
"epoch": 1.82,
"learning_rate": 0.00016355086538422776,
"loss": 0.494,
"step": 679
},
{
"epoch": 1.82,
"learning_rate": 0.00016343932841636456,
"loss": 0.5155,
"step": 680
},
{
"epoch": 1.82,
"learning_rate": 0.00016332765921531453,
"loss": 0.5622,
"step": 681
},
{
"epoch": 1.82,
"learning_rate": 0.00016321585801384137,
"loss": 0.572,
"step": 682
},
{
"epoch": 1.83,
"learning_rate": 0.00016310392504498395,
"loss": 0.6061,
"step": 683
},
{
"epoch": 1.83,
"learning_rate": 0.00016299186054205577,
"loss": 0.5628,
"step": 684
},
{
"epoch": 1.83,
"learning_rate": 0.00016287966473864452,
"loss": 0.5122,
"step": 685
},
{
"epoch": 1.83,
"learning_rate": 0.00016276733786861164,
"loss": 0.5124,
"step": 686
},
{
"epoch": 1.84,
"learning_rate": 0.0001626548801660916,
"loss": 0.536,
"step": 687
},
{
"epoch": 1.84,
"learning_rate": 0.0001625422918654918,
"loss": 0.5791,
"step": 688
},
{
"epoch": 1.84,
"learning_rate": 0.0001624295732014916,
"loss": 0.5581,
"step": 689
},
{
"epoch": 1.84,
"learning_rate": 0.00016231672440904235,
"loss": 0.5328,
"step": 690
},
{
"epoch": 1.85,
"learning_rate": 0.00016220374572336645,
"loss": 0.517,
"step": 691
},
{
"epoch": 1.85,
"learning_rate": 0.00016209063737995715,
"loss": 0.5233,
"step": 692
},
{
"epoch": 1.85,
"learning_rate": 0.0001619773996145779,
"loss": 0.5116,
"step": 693
},
{
"epoch": 1.86,
"learning_rate": 0.00016186403266326197,
"loss": 0.4957,
"step": 694
},
{
"epoch": 1.86,
"learning_rate": 0.00016175053676231187,
"loss": 0.5477,
"step": 695
},
{
"epoch": 1.86,
"learning_rate": 0.00016163691214829892,
"loss": 0.5112,
"step": 696
},
{
"epoch": 1.86,
"learning_rate": 0.00016152315905806268,
"loss": 0.5995,
"step": 697
},
{
"epoch": 1.87,
"learning_rate": 0.00016140927772871058,
"loss": 0.5313,
"step": 698
},
{
"epoch": 1.87,
"learning_rate": 0.0001612952683976173,
"loss": 0.5829,
"step": 699
},
{
"epoch": 1.87,
"learning_rate": 0.00016118113130242432,
"loss": 0.4784,
"step": 700
},
{
"epoch": 1.87,
"learning_rate": 0.0001610668666810395,
"loss": 0.5119,
"step": 701
},
{
"epoch": 1.88,
"learning_rate": 0.0001609524747716364,
"loss": 0.5174,
"step": 702
},
{
"epoch": 1.88,
"learning_rate": 0.00016083795581265406,
"loss": 0.5093,
"step": 703
},
{
"epoch": 1.88,
"learning_rate": 0.00016072331004279614,
"loss": 0.5268,
"step": 704
},
{
"epoch": 1.89,
"learning_rate": 0.00016060853770103083,
"loss": 0.5421,
"step": 705
},
{
"epoch": 1.89,
"learning_rate": 0.00016049363902659,
"loss": 0.5227,
"step": 706
},
{
"epoch": 1.89,
"learning_rate": 0.00016037861425896891,
"loss": 0.5322,
"step": 707
},
{
"epoch": 1.89,
"learning_rate": 0.00016026346363792567,
"loss": 0.5048,
"step": 708
},
{
"epoch": 1.9,
"learning_rate": 0.00016014818740348063,
"loss": 0.5696,
"step": 709
},
{
"epoch": 1.9,
"learning_rate": 0.00016003278579591608,
"loss": 0.5017,
"step": 710
},
{
"epoch": 1.9,
"learning_rate": 0.00015991725905577556,
"loss": 0.5397,
"step": 711
},
{
"epoch": 1.9,
"learning_rate": 0.0001598016074238635,
"loss": 0.515,
"step": 712
},
{
"epoch": 1.91,
"learning_rate": 0.00015968583114124457,
"loss": 0.5401,
"step": 713
},
{
"epoch": 1.91,
"learning_rate": 0.00015956993044924334,
"loss": 0.5181,
"step": 714
},
{
"epoch": 1.91,
"learning_rate": 0.00015945390558944368,
"loss": 0.5167,
"step": 715
},
{
"epoch": 1.91,
"learning_rate": 0.00015933775680368822,
"loss": 0.5523,
"step": 716
},
{
"epoch": 1.92,
"learning_rate": 0.00015922148433407802,
"loss": 0.5283,
"step": 717
},
{
"epoch": 1.92,
"learning_rate": 0.00015910508842297181,
"loss": 0.525,
"step": 718
},
{
"epoch": 1.92,
"learning_rate": 0.0001589885693129857,
"loss": 0.5471,
"step": 719
},
{
"epoch": 1.93,
"learning_rate": 0.0001588719272469926,
"loss": 0.516,
"step": 720
},
{
"epoch": 1.93,
"learning_rate": 0.0001587551624681217,
"loss": 0.507,
"step": 721
},
{
"epoch": 1.93,
"learning_rate": 0.000158638275219758,
"loss": 0.5228,
"step": 722
},
{
"epoch": 1.93,
"learning_rate": 0.00015852126574554163,
"loss": 0.5252,
"step": 723
},
{
"epoch": 1.94,
"learning_rate": 0.00015840413428936767,
"loss": 0.5623,
"step": 724
},
{
"epoch": 1.94,
"learning_rate": 0.0001582868810953854,
"loss": 0.5037,
"step": 725
},
{
"epoch": 1.94,
"learning_rate": 0.00015816950640799786,
"loss": 0.5531,
"step": 726
},
{
"epoch": 1.94,
"learning_rate": 0.00015805201047186125,
"loss": 0.5456,
"step": 727
},
{
"epoch": 1.95,
"learning_rate": 0.0001579343935318846,
"loss": 0.4967,
"step": 728
},
{
"epoch": 1.95,
"learning_rate": 0.0001578166558332291,
"loss": 0.5615,
"step": 729
},
{
"epoch": 1.95,
"learning_rate": 0.0001576987976213077,
"loss": 0.5611,
"step": 730
},
{
"epoch": 1.95,
"learning_rate": 0.00015758081914178456,
"loss": 0.5284,
"step": 731
},
{
"epoch": 1.96,
"learning_rate": 0.0001574627206405744,
"loss": 0.5456,
"step": 732
},
{
"epoch": 1.96,
"learning_rate": 0.00015734450236384227,
"loss": 0.5672,
"step": 733
},
{
"epoch": 1.96,
"learning_rate": 0.00015722616455800275,
"loss": 0.5034,
"step": 734
},
{
"epoch": 1.97,
"learning_rate": 0.00015710770746971971,
"loss": 0.5402,
"step": 735
},
{
"epoch": 1.97,
"learning_rate": 0.00015698913134590552,
"loss": 0.532,
"step": 736
},
{
"epoch": 1.97,
"learning_rate": 0.00015687043643372074,
"loss": 0.5354,
"step": 737
},
{
"epoch": 1.97,
"learning_rate": 0.00015675162298057352,
"loss": 0.5132,
"step": 738
},
{
"epoch": 1.98,
"learning_rate": 0.00015663269123411907,
"loss": 0.4854,
"step": 739
},
{
"epoch": 1.98,
"learning_rate": 0.0001565136414422592,
"loss": 0.5321,
"step": 740
},
{
"epoch": 1.98,
"learning_rate": 0.00015639447385314178,
"loss": 0.493,
"step": 741
},
{
"epoch": 1.98,
"learning_rate": 0.0001562751887151602,
"loss": 0.5169,
"step": 742
},
{
"epoch": 1.99,
"learning_rate": 0.00015615578627695283,
"loss": 0.5312,
"step": 743
},
{
"epoch": 1.99,
"learning_rate": 0.00015603626678740263,
"loss": 0.5325,
"step": 744
},
{
"epoch": 1.99,
"learning_rate": 0.0001559166304956365,
"loss": 0.5471,
"step": 745
},
{
"epoch": 1.99,
"learning_rate": 0.0001557968776510248,
"loss": 0.5746,
"step": 746
},
{
"epoch": 2.0,
"learning_rate": 0.0001556770085031808,
"loss": 0.5698,
"step": 747
},
{
"epoch": 2.0,
"learning_rate": 0.00015555702330196023,
"loss": 0.4668,
"step": 748
},
{
"epoch": 2.0,
"learning_rate": 0.00015543692229746074,
"loss": 0.2959,
"step": 749
},
{
"epoch": 2.01,
"learning_rate": 0.00015531670574002134,
"loss": 0.2925,
"step": 750
},
{
"epoch": 2.01,
"learning_rate": 0.0001551963738802219,
"loss": 0.2752,
"step": 751
},
{
"epoch": 2.01,
"learning_rate": 0.00015507592696888258,
"loss": 0.2338,
"step": 752
},
{
"epoch": 2.01,
"learning_rate": 0.00015495536525706344,
"loss": 0.2251,
"step": 753
},
{
"epoch": 2.02,
"learning_rate": 0.0001548346889960638,
"loss": 0.2266,
"step": 754
},
{
"epoch": 2.02,
"learning_rate": 0.0001547138984374217,
"loss": 0.2353,
"step": 755
},
{
"epoch": 2.02,
"learning_rate": 0.00015459299383291345,
"loss": 0.2178,
"step": 756
},
{
"epoch": 2.02,
"learning_rate": 0.0001544719754345531,
"loss": 0.2169,
"step": 757
},
{
"epoch": 2.03,
"learning_rate": 0.00015435084349459195,
"loss": 0.2613,
"step": 758
},
{
"epoch": 2.03,
"learning_rate": 0.00015422959826551778,
"loss": 0.2402,
"step": 759
},
{
"epoch": 2.03,
"learning_rate": 0.00015410824000005468,
"loss": 0.2146,
"step": 760
},
{
"epoch": 2.03,
"learning_rate": 0.0001539867689511623,
"loss": 0.2485,
"step": 761
},
{
"epoch": 2.04,
"learning_rate": 0.00015386518537203534,
"loss": 0.2187,
"step": 762
},
{
"epoch": 2.04,
"learning_rate": 0.00015374348951610313,
"loss": 0.2117,
"step": 763
},
{
"epoch": 2.04,
"learning_rate": 0.000153621681637029,
"loss": 0.1994,
"step": 764
},
{
"epoch": 2.05,
"learning_rate": 0.00015349976198870973,
"loss": 0.2157,
"step": 765
},
{
"epoch": 2.05,
"learning_rate": 0.00015337773082527517,
"loss": 0.2427,
"step": 766
},
{
"epoch": 2.05,
"learning_rate": 0.00015325558840108752,
"loss": 0.2312,
"step": 767
},
{
"epoch": 2.05,
"learning_rate": 0.0001531333349707409,
"loss": 0.2102,
"step": 768
},
{
"epoch": 2.06,
"learning_rate": 0.00015301097078906096,
"loss": 0.2298,
"step": 769
},
{
"epoch": 2.06,
"learning_rate": 0.000152888496111104,
"loss": 0.2163,
"step": 770
},
{
"epoch": 2.06,
"learning_rate": 0.00015276591119215669,
"loss": 0.229,
"step": 771
},
{
"epoch": 2.06,
"learning_rate": 0.0001526432162877356,
"loss": 0.2268,
"step": 772
},
{
"epoch": 2.07,
"learning_rate": 0.00015252041165358642,
"loss": 0.208,
"step": 773
},
{
"epoch": 2.07,
"learning_rate": 0.00015239749754568363,
"loss": 0.2119,
"step": 774
},
{
"epoch": 2.07,
"learning_rate": 0.0001522744742202299,
"loss": 0.2123,
"step": 775
},
{
"epoch": 2.07,
"learning_rate": 0.0001521513419336555,
"loss": 0.2399,
"step": 776
},
{
"epoch": 2.08,
"learning_rate": 0.00015202810094261791,
"loss": 0.2115,
"step": 777
},
{
"epoch": 2.08,
"learning_rate": 0.00015190475150400105,
"loss": 0.2028,
"step": 778
},
{
"epoch": 2.08,
"learning_rate": 0.00015178129387491507,
"loss": 0.2362,
"step": 779
},
{
"epoch": 2.09,
"learning_rate": 0.00015165772831269547,
"loss": 0.1958,
"step": 780
},
{
"epoch": 2.09,
"learning_rate": 0.00015153405507490288,
"loss": 0.2267,
"step": 781
},
{
"epoch": 2.09,
"learning_rate": 0.00015141027441932216,
"loss": 0.2203,
"step": 782
},
{
"epoch": 2.09,
"learning_rate": 0.00015128638660396232,
"loss": 0.24,
"step": 783
},
{
"epoch": 2.1,
"learning_rate": 0.00015116239188705556,
"loss": 0.2005,
"step": 784
},
{
"epoch": 2.1,
"learning_rate": 0.00015103829052705696,
"loss": 0.1988,
"step": 785
},
{
"epoch": 2.1,
"learning_rate": 0.00015091408278264387,
"loss": 0.2228,
"step": 786
},
{
"epoch": 2.1,
"learning_rate": 0.00015078976891271542,
"loss": 0.2246,
"step": 787
},
{
"epoch": 2.11,
"learning_rate": 0.00015066534917639195,
"loss": 0.2403,
"step": 788
},
{
"epoch": 2.11,
"learning_rate": 0.0001505408238330144,
"loss": 0.2233,
"step": 789
},
{
"epoch": 2.11,
"learning_rate": 0.00015041619314214394,
"loss": 0.1934,
"step": 790
},
{
"epoch": 2.11,
"learning_rate": 0.00015029145736356124,
"loss": 0.2356,
"step": 791
},
{
"epoch": 2.12,
"learning_rate": 0.00015016661675726608,
"loss": 0.2262,
"step": 792
},
{
"epoch": 2.12,
"learning_rate": 0.00015004167158347666,
"loss": 0.2141,
"step": 793
},
{
"epoch": 2.12,
"learning_rate": 0.00014991662210262928,
"loss": 0.2396,
"step": 794
},
{
"epoch": 2.13,
"learning_rate": 0.0001497914685753775,
"loss": 0.2052,
"step": 795
},
{
"epoch": 2.13,
"learning_rate": 0.00014966621126259183,
"loss": 0.2079,
"step": 796
},
{
"epoch": 2.13,
"learning_rate": 0.00014954085042535916,
"loss": 0.2044,
"step": 797
},
{
"epoch": 2.13,
"learning_rate": 0.00014941538632498203,
"loss": 0.227,
"step": 798
},
{
"epoch": 2.14,
"learning_rate": 0.00014928981922297842,
"loss": 0.2182,
"step": 799
},
{
"epoch": 2.14,
"learning_rate": 0.0001491641493810808,
"loss": 0.2241,
"step": 800
},
{
"epoch": 2.14,
"learning_rate": 0.0001490383770612359,
"loss": 0.2217,
"step": 801
},
{
"epoch": 2.14,
"learning_rate": 0.00014891250252560407,
"loss": 0.2184,
"step": 802
},
{
"epoch": 2.15,
"learning_rate": 0.00014878652603655872,
"loss": 0.2091,
"step": 803
},
{
"epoch": 2.15,
"learning_rate": 0.00014866044785668563,
"loss": 0.2168,
"step": 804
},
{
"epoch": 2.15,
"learning_rate": 0.00014853426824878278,
"loss": 0.2153,
"step": 805
},
{
"epoch": 2.16,
"learning_rate": 0.00014840798747585933,
"loss": 0.2294,
"step": 806
},
{
"epoch": 2.16,
"learning_rate": 0.00014828160580113552,
"loss": 0.2004,
"step": 807
},
{
"epoch": 2.16,
"learning_rate": 0.00014815512348804178,
"loss": 0.2301,
"step": 808
},
{
"epoch": 2.16,
"learning_rate": 0.0001480285408002183,
"loss": 0.217,
"step": 809
},
{
"epoch": 2.17,
"learning_rate": 0.0001479018580015146,
"loss": 0.2002,
"step": 810
},
{
"epoch": 2.17,
"learning_rate": 0.00014777507535598878,
"loss": 0.2048,
"step": 811
},
{
"epoch": 2.17,
"learning_rate": 0.00014764819312790707,
"loss": 0.2376,
"step": 812
},
{
"epoch": 2.17,
"learning_rate": 0.0001475212115817433,
"loss": 0.2235,
"step": 813
},
{
"epoch": 2.18,
"learning_rate": 0.0001473941309821783,
"loss": 0.2092,
"step": 814
},
{
"epoch": 2.18,
"learning_rate": 0.00014726695159409937,
"loss": 0.2303,
"step": 815
},
{
"epoch": 2.18,
"learning_rate": 0.0001471396736825998,
"loss": 0.2293,
"step": 816
},
{
"epoch": 2.18,
"learning_rate": 0.00014701229751297806,
"loss": 0.2283,
"step": 817
},
{
"epoch": 2.19,
"learning_rate": 0.0001468848233507376,
"loss": 0.2148,
"step": 818
},
{
"epoch": 2.19,
"learning_rate": 0.00014675725146158608,
"loss": 0.2071,
"step": 819
},
{
"epoch": 2.19,
"learning_rate": 0.0001466295821114348,
"loss": 0.1982,
"step": 820
},
{
"epoch": 2.2,
"learning_rate": 0.00014650181556639832,
"loss": 0.2461,
"step": 821
},
{
"epoch": 2.2,
"learning_rate": 0.0001463739520927937,
"loss": 0.2073,
"step": 822
},
{
"epoch": 2.2,
"learning_rate": 0.00014624599195714005,
"loss": 0.1997,
"step": 823
},
{
"epoch": 2.2,
"learning_rate": 0.00014611793542615803,
"loss": 0.2485,
"step": 824
},
{
"epoch": 2.21,
"learning_rate": 0.00014598978276676917,
"loss": 0.221,
"step": 825
},
{
"epoch": 2.21,
"learning_rate": 0.0001458615342460953,
"loss": 0.2161,
"step": 826
},
{
"epoch": 2.21,
"learning_rate": 0.00014573319013145823,
"loss": 0.2272,
"step": 827
},
{
"epoch": 2.21,
"learning_rate": 0.00014560475069037894,
"loss": 0.2038,
"step": 828
},
{
"epoch": 2.22,
"learning_rate": 0.00014547621619057707,
"loss": 0.2214,
"step": 829
},
{
"epoch": 2.22,
"learning_rate": 0.00014534758689997045,
"loss": 0.218,
"step": 830
},
{
"epoch": 2.22,
"learning_rate": 0.00014521886308667447,
"loss": 0.2226,
"step": 831
},
{
"epoch": 2.22,
"learning_rate": 0.0001450900450190016,
"loss": 0.2439,
"step": 832
},
{
"epoch": 2.23,
"learning_rate": 0.00014496113296546067,
"loss": 0.2434,
"step": 833
},
{
"epoch": 2.23,
"learning_rate": 0.00014483212719475653,
"loss": 0.2285,
"step": 834
},
{
"epoch": 2.23,
"learning_rate": 0.00014470302797578926,
"loss": 0.2101,
"step": 835
},
{
"epoch": 2.24,
"learning_rate": 0.00014457383557765386,
"loss": 0.2132,
"step": 836
},
{
"epoch": 2.24,
"learning_rate": 0.0001444445502696394,
"loss": 0.2165,
"step": 837
},
{
"epoch": 2.24,
"learning_rate": 0.0001443151723212287,
"loss": 0.2345,
"step": 838
},
{
"epoch": 2.24,
"learning_rate": 0.00014418570200209772,
"loss": 0.2207,
"step": 839
},
{
"epoch": 2.25,
"learning_rate": 0.00014405613958211482,
"loss": 0.2437,
"step": 840
},
{
"epoch": 2.25,
"learning_rate": 0.0001439264853313405,
"loss": 0.2358,
"step": 841
},
{
"epoch": 2.25,
"learning_rate": 0.00014379673952002656,
"loss": 0.2399,
"step": 842
},
{
"epoch": 2.25,
"learning_rate": 0.0001436669024186157,
"loss": 0.2251,
"step": 843
},
{
"epoch": 2.26,
"learning_rate": 0.00014353697429774084,
"loss": 0.2217,
"step": 844
},
{
"epoch": 2.26,
"learning_rate": 0.00014340695542822468,
"loss": 0.2541,
"step": 845
},
{
"epoch": 2.26,
"learning_rate": 0.00014327684608107913,
"loss": 0.2205,
"step": 846
},
{
"epoch": 2.26,
"learning_rate": 0.00014314664652750455,
"loss": 0.2084,
"step": 847
},
{
"epoch": 2.27,
"learning_rate": 0.00014301635703888943,
"loss": 0.2338,
"step": 848
},
{
"epoch": 2.27,
"learning_rate": 0.00014288597788680973,
"loss": 0.2389,
"step": 849
},
{
"epoch": 2.27,
"learning_rate": 0.00014275550934302823,
"loss": 0.2269,
"step": 850
},
{
"epoch": 2.28,
"learning_rate": 0.00014262495167949405,
"loss": 0.2387,
"step": 851
},
{
"epoch": 2.28,
"learning_rate": 0.0001424943051683422,
"loss": 0.2155,
"step": 852
},
{
"epoch": 2.28,
"learning_rate": 0.0001423635700818927,
"loss": 0.2394,
"step": 853
},
{
"epoch": 2.28,
"learning_rate": 0.0001422327466926503,
"loss": 0.2186,
"step": 854
},
{
"epoch": 2.29,
"learning_rate": 0.00014210183527330376,
"loss": 0.2254,
"step": 855
},
{
"epoch": 2.29,
"learning_rate": 0.00014197083609672543,
"loss": 0.219,
"step": 856
},
{
"epoch": 2.29,
"learning_rate": 0.00014183974943597047,
"loss": 0.2069,
"step": 857
},
{
"epoch": 2.29,
"learning_rate": 0.00014170857556427643,
"loss": 0.2208,
"step": 858
},
{
"epoch": 2.3,
"learning_rate": 0.00014157731475506266,
"loss": 0.2189,
"step": 859
},
{
"epoch": 2.3,
"learning_rate": 0.0001414459672819297,
"loss": 0.2497,
"step": 860
},
{
"epoch": 2.3,
"learning_rate": 0.00014131453341865877,
"loss": 0.2147,
"step": 861
},
{
"epoch": 2.3,
"learning_rate": 0.00014118301343921108,
"loss": 0.2401,
"step": 862
},
{
"epoch": 2.31,
"learning_rate": 0.00014105140761772744,
"loss": 0.2348,
"step": 863
},
{
"epoch": 2.31,
"learning_rate": 0.0001409197162285275,
"loss": 0.2272,
"step": 864
},
{
"epoch": 2.31,
"learning_rate": 0.00014078793954610936,
"loss": 0.2226,
"step": 865
},
{
"epoch": 2.32,
"learning_rate": 0.00014065607784514885,
"loss": 0.2032,
"step": 866
},
{
"epoch": 2.32,
"learning_rate": 0.000140524131400499,
"loss": 0.211,
"step": 867
},
{
"epoch": 2.32,
"learning_rate": 0.00014039210048718949,
"loss": 0.2292,
"step": 868
},
{
"epoch": 2.32,
"learning_rate": 0.00014025998538042613,
"loss": 0.2009,
"step": 869
},
{
"epoch": 2.33,
"learning_rate": 0.0001401277863555901,
"loss": 0.2555,
"step": 870
},
{
"epoch": 2.33,
"learning_rate": 0.00013999550368823767,
"loss": 0.2379,
"step": 871
},
{
"epoch": 2.33,
"learning_rate": 0.00013986313765409925,
"loss": 0.2427,
"step": 872
},
{
"epoch": 2.33,
"learning_rate": 0.00013973068852907918,
"loss": 0.2082,
"step": 873
},
{
"epoch": 2.34,
"learning_rate": 0.0001395981565892549,
"loss": 0.2083,
"step": 874
},
{
"epoch": 2.34,
"learning_rate": 0.00013946554211087655,
"loss": 0.2434,
"step": 875
},
{
"epoch": 2.34,
"learning_rate": 0.00013933284537036625,
"loss": 0.2147,
"step": 876
},
{
"epoch": 2.34,
"learning_rate": 0.00013920006664431766,
"loss": 0.2154,
"step": 877
},
{
"epoch": 2.35,
"learning_rate": 0.00013906720620949521,
"loss": 0.2275,
"step": 878
},
{
"epoch": 2.35,
"learning_rate": 0.00013893426434283376,
"loss": 0.2341,
"step": 879
},
{
"epoch": 2.35,
"learning_rate": 0.00013880124132143782,
"loss": 0.2037,
"step": 880
},
{
"epoch": 2.36,
"learning_rate": 0.00013866813742258115,
"loss": 0.2161,
"step": 881
},
{
"epoch": 2.36,
"learning_rate": 0.000138534952923706,
"loss": 0.1911,
"step": 882
},
{
"epoch": 2.36,
"learning_rate": 0.00013840168810242274,
"loss": 0.2418,
"step": 883
},
{
"epoch": 2.36,
"learning_rate": 0.000138268343236509,
"loss": 0.2777,
"step": 884
},
{
"epoch": 2.37,
"learning_rate": 0.00013813491860390937,
"loss": 0.2142,
"step": 885
},
{
"epoch": 2.37,
"learning_rate": 0.0001380014144827347,
"loss": 0.214,
"step": 886
},
{
"epoch": 2.37,
"learning_rate": 0.00013786783115126152,
"loss": 0.251,
"step": 887
},
{
"epoch": 2.37,
"learning_rate": 0.00013773416888793145,
"loss": 0.2347,
"step": 888
},
{
"epoch": 2.38,
"learning_rate": 0.0001376004279713506,
"loss": 0.2428,
"step": 889
},
{
"epoch": 2.38,
"learning_rate": 0.0001374666086802891,
"loss": 0.2591,
"step": 890
},
{
"epoch": 2.38,
"learning_rate": 0.00013733271129368041,
"loss": 0.2101,
"step": 891
},
{
"epoch": 2.39,
"learning_rate": 0.00013719873609062077,
"loss": 0.2232,
"step": 892
},
{
"epoch": 2.39,
"learning_rate": 0.0001370646833503686,
"loss": 0.2426,
"step": 893
},
{
"epoch": 2.39,
"learning_rate": 0.00013693055335234396,
"loss": 0.188,
"step": 894
},
{
"epoch": 2.39,
"learning_rate": 0.00013679634637612798,
"loss": 0.1985,
"step": 895
},
{
"epoch": 2.4,
"learning_rate": 0.00013666206270146223,
"loss": 0.2337,
"step": 896
},
{
"epoch": 2.4,
"learning_rate": 0.00013652770260824806,
"loss": 0.2282,
"step": 897
},
{
"epoch": 2.4,
"learning_rate": 0.0001363932663765462,
"loss": 0.2308,
"step": 898
},
{
"epoch": 2.4,
"learning_rate": 0.00013625875428657612,
"loss": 0.2354,
"step": 899
},
{
"epoch": 2.41,
"learning_rate": 0.00013612416661871533,
"loss": 0.2164,
"step": 900
},
{
"epoch": 2.41,
"learning_rate": 0.00013598950365349883,
"loss": 0.2252,
"step": 901
},
{
"epoch": 2.41,
"learning_rate": 0.0001358547656716187,
"loss": 0.2224,
"step": 902
},
{
"epoch": 2.41,
"learning_rate": 0.0001357199529539233,
"loss": 0.2334,
"step": 903
},
{
"epoch": 2.42,
"learning_rate": 0.00013558506578141682,
"loss": 0.2173,
"step": 904
},
{
"epoch": 2.42,
"learning_rate": 0.0001354501044352586,
"loss": 0.254,
"step": 905
},
{
"epoch": 2.42,
"learning_rate": 0.00013531506919676258,
"loss": 0.2348,
"step": 906
},
{
"epoch": 2.43,
"learning_rate": 0.00013517996034739677,
"loss": 0.1939,
"step": 907
},
{
"epoch": 2.43,
"learning_rate": 0.0001350447781687826,
"loss": 0.205,
"step": 908
},
{
"epoch": 2.43,
"learning_rate": 0.0001349095229426943,
"loss": 0.2125,
"step": 909
},
{
"epoch": 2.43,
"learning_rate": 0.00013477419495105844,
"loss": 0.1889,
"step": 910
},
{
"epoch": 2.44,
"learning_rate": 0.00013463879447595315,
"loss": 0.1992,
"step": 911
},
{
"epoch": 2.44,
"learning_rate": 0.0001345033217996078,
"loss": 0.2341,
"step": 912
},
{
"epoch": 2.44,
"learning_rate": 0.00013436777720440214,
"loss": 0.2149,
"step": 913
},
{
"epoch": 2.44,
"learning_rate": 0.00013423216097286584,
"loss": 0.2251,
"step": 914
},
{
"epoch": 2.45,
"learning_rate": 0.00013409647338767793,
"loss": 0.2034,
"step": 915
},
{
"epoch": 2.45,
"learning_rate": 0.00013396071473166613,
"loss": 0.2381,
"step": 916
},
{
"epoch": 2.45,
"learning_rate": 0.00013382488528780639,
"loss": 0.2124,
"step": 917
},
{
"epoch": 2.45,
"learning_rate": 0.000133688985339222,
"loss": 0.2253,
"step": 918
},
{
"epoch": 2.46,
"learning_rate": 0.00013355301516918347,
"loss": 0.2509,
"step": 919
},
{
"epoch": 2.46,
"learning_rate": 0.00013341697506110754,
"loss": 0.1984,
"step": 920
},
{
"epoch": 2.46,
"learning_rate": 0.00013328086529855674,
"loss": 0.213,
"step": 921
},
{
"epoch": 2.47,
"learning_rate": 0.00013314468616523875,
"loss": 0.2092,
"step": 922
},
{
"epoch": 2.47,
"learning_rate": 0.00013300843794500591,
"loss": 0.231,
"step": 923
},
{
"epoch": 2.47,
"learning_rate": 0.00013287212092185464,
"loss": 0.2008,
"step": 924
},
{
"epoch": 2.47,
"learning_rate": 0.00013273573537992455,
"loss": 0.2104,
"step": 925
},
{
"epoch": 2.48,
"learning_rate": 0.00013259928160349831,
"loss": 0.2236,
"step": 926
},
{
"epoch": 2.48,
"learning_rate": 0.00013246275987700064,
"loss": 0.2278,
"step": 927
},
{
"epoch": 2.48,
"learning_rate": 0.000132326170484998,
"loss": 0.2336,
"step": 928
},
{
"epoch": 2.48,
"learning_rate": 0.00013218951371219784,
"loss": 0.2396,
"step": 929
},
{
"epoch": 2.49,
"learning_rate": 0.00013205278984344812,
"loss": 0.1906,
"step": 930
},
{
"epoch": 2.49,
"learning_rate": 0.0001319159991637365,
"loss": 0.2143,
"step": 931
},
{
"epoch": 2.49,
"learning_rate": 0.00013177914195819016,
"loss": 0.2165,
"step": 932
},
{
"epoch": 2.49,
"learning_rate": 0.00013164221851207474,
"loss": 0.2318,
"step": 933
},
{
"epoch": 2.5,
"learning_rate": 0.00013150522911079397,
"loss": 0.2201,
"step": 934
},
{
"epoch": 2.5,
"learning_rate": 0.00013136817403988917,
"loss": 0.2216,
"step": 935
},
{
"epoch": 2.5,
"learning_rate": 0.0001312310535850384,
"loss": 0.2231,
"step": 936
},
{
"epoch": 2.51,
"learning_rate": 0.00013109386803205613,
"loss": 0.2273,
"step": 937
},
{
"epoch": 2.51,
"learning_rate": 0.00013095661766689246,
"loss": 0.2482,
"step": 938
},
{
"epoch": 2.51,
"learning_rate": 0.0001308193027756326,
"loss": 0.2135,
"step": 939
},
{
"epoch": 2.51,
"learning_rate": 0.00013068192364449618,
"loss": 0.2229,
"step": 940
},
{
"epoch": 2.52,
"learning_rate": 0.00013054448055983692,
"loss": 0.216,
"step": 941
},
{
"epoch": 2.52,
"learning_rate": 0.00013040697380814164,
"loss": 0.2239,
"step": 942
},
{
"epoch": 2.52,
"learning_rate": 0.00013026940367603,
"loss": 0.2177,
"step": 943
},
{
"epoch": 2.52,
"learning_rate": 0.00013013177045025374,
"loss": 0.2086,
"step": 944
},
{
"epoch": 2.53,
"learning_rate": 0.00012999407441769602,
"loss": 0.2255,
"step": 945
},
{
"epoch": 2.53,
"learning_rate": 0.00012985631586537107,
"loss": 0.244,
"step": 946
},
{
"epoch": 2.53,
"learning_rate": 0.00012971849508042337,
"loss": 0.207,
"step": 947
},
{
"epoch": 2.53,
"learning_rate": 0.00012958061235012706,
"loss": 0.2307,
"step": 948
},
{
"epoch": 2.54,
"learning_rate": 0.00012944266796188547,
"loss": 0.248,
"step": 949
},
{
"epoch": 2.54,
"learning_rate": 0.0001293046622032304,
"loss": 0.2418,
"step": 950
},
{
"epoch": 2.54,
"learning_rate": 0.00012916659536182164,
"loss": 0.234,
"step": 951
},
{
"epoch": 2.55,
"learning_rate": 0.00012902846772544624,
"loss": 0.2145,
"step": 952
},
{
"epoch": 2.55,
"learning_rate": 0.000128890279582018,
"loss": 0.243,
"step": 953
},
{
"epoch": 2.55,
"learning_rate": 0.00012875203121957683,
"loss": 0.2317,
"step": 954
},
{
"epoch": 2.55,
"learning_rate": 0.00012861372292628814,
"loss": 0.2338,
"step": 955
},
{
"epoch": 2.56,
"learning_rate": 0.0001284753549904423,
"loss": 0.2332,
"step": 956
},
{
"epoch": 2.56,
"learning_rate": 0.00012833692770045403,
"loss": 0.2245,
"step": 957
},
{
"epoch": 2.56,
"learning_rate": 0.00012819844134486167,
"loss": 0.2545,
"step": 958
},
{
"epoch": 2.56,
"learning_rate": 0.0001280598962123267,
"loss": 0.2143,
"step": 959
},
{
"epoch": 2.57,
"learning_rate": 0.00012792129259163318,
"loss": 0.2062,
"step": 960
},
{
"epoch": 2.57,
"learning_rate": 0.00012778263077168703,
"loss": 0.232,
"step": 961
},
{
"epoch": 2.57,
"learning_rate": 0.00012764391104151554,
"loss": 0.2298,
"step": 962
},
{
"epoch": 2.57,
"learning_rate": 0.00012750513369026657,
"loss": 0.238,
"step": 963
},
{
"epoch": 2.58,
"learning_rate": 0.0001273662990072083,
"loss": 0.2169,
"step": 964
},
{
"epoch": 2.58,
"learning_rate": 0.0001272274072817282,
"loss": 0.2083,
"step": 965
},
{
"epoch": 2.58,
"learning_rate": 0.00012708845880333278,
"loss": 0.2494,
"step": 966
},
{
"epoch": 2.59,
"learning_rate": 0.00012694945386164673,
"loss": 0.2331,
"step": 967
},
{
"epoch": 2.59,
"learning_rate": 0.0001268103927464126,
"loss": 0.1989,
"step": 968
},
{
"epoch": 2.59,
"learning_rate": 0.00012667127574748986,
"loss": 0.2281,
"step": 969
},
{
"epoch": 2.59,
"learning_rate": 0.00012653210315485453,
"loss": 0.2117,
"step": 970
},
{
"epoch": 2.6,
"learning_rate": 0.00012639287525859855,
"loss": 0.2222,
"step": 971
},
{
"epoch": 2.6,
"learning_rate": 0.00012625359234892907,
"loss": 0.2159,
"step": 972
},
{
"epoch": 2.6,
"learning_rate": 0.00012611425471616795,
"loss": 0.2102,
"step": 973
},
{
"epoch": 2.6,
"learning_rate": 0.0001259748626507511,
"loss": 0.2541,
"step": 974
},
{
"epoch": 2.61,
"learning_rate": 0.0001258354164432279,
"loss": 0.2366,
"step": 975
},
{
"epoch": 2.61,
"learning_rate": 0.00012569591638426052,
"loss": 0.2443,
"step": 976
},
{
"epoch": 2.61,
"learning_rate": 0.00012555636276462355,
"loss": 0.2001,
"step": 977
},
{
"epoch": 2.61,
"learning_rate": 0.00012541675587520297,
"loss": 0.203,
"step": 978
},
{
"epoch": 2.62,
"learning_rate": 0.00012527709600699605,
"loss": 0.2056,
"step": 979
},
{
"epoch": 2.62,
"learning_rate": 0.0001251373834511103,
"loss": 0.2365,
"step": 980
},
{
"epoch": 2.62,
"learning_rate": 0.00012499761849876312,
"loss": 0.2385,
"step": 981
},
{
"epoch": 2.63,
"learning_rate": 0.00012485780144128115,
"loss": 0.2061,
"step": 982
},
{
"epoch": 2.63,
"learning_rate": 0.00012471793257009964,
"loss": 0.2325,
"step": 983
},
{
"epoch": 2.63,
"learning_rate": 0.00012457801217676182,
"loss": 0.2421,
"step": 984
},
{
"epoch": 2.63,
"learning_rate": 0.00012443804055291825,
"loss": 0.2222,
"step": 985
},
{
"epoch": 2.64,
"learning_rate": 0.0001242980179903264,
"loss": 0.221,
"step": 986
},
{
"epoch": 2.64,
"learning_rate": 0.0001241579447808498,
"loss": 0.2532,
"step": 987
},
{
"epoch": 2.64,
"learning_rate": 0.00012401782121645766,
"loss": 0.1937,
"step": 988
},
{
"epoch": 2.64,
"learning_rate": 0.00012387764758922405,
"loss": 0.2517,
"step": 989
},
{
"epoch": 2.65,
"learning_rate": 0.00012373742419132742,
"loss": 0.2134,
"step": 990
},
{
"epoch": 2.65,
"learning_rate": 0.00012359715131505,
"loss": 0.2029,
"step": 991
},
{
"epoch": 2.65,
"learning_rate": 0.00012345682925277716,
"loss": 0.2318,
"step": 992
},
{
"epoch": 2.66,
"learning_rate": 0.0001233164582969967,
"loss": 0.2386,
"step": 993
},
{
"epoch": 2.66,
"learning_rate": 0.00012317603874029842,
"loss": 0.258,
"step": 994
},
{
"epoch": 2.66,
"learning_rate": 0.0001230355708753734,
"loss": 0.2568,
"step": 995
},
{
"epoch": 2.66,
"learning_rate": 0.0001228950549950134,
"loss": 0.2209,
"step": 996
},
{
"epoch": 2.67,
"learning_rate": 0.00012275449139211034,
"loss": 0.2238,
"step": 997
},
{
"epoch": 2.67,
"learning_rate": 0.00012261388035965544,
"loss": 0.229,
"step": 998
},
{
"epoch": 2.67,
"learning_rate": 0.00012247322219073898,
"loss": 0.2011,
"step": 999
},
{
"epoch": 2.67,
"learning_rate": 0.00012233251717854937,
"loss": 0.1903,
"step": 1000
},
{
"epoch": 2.68,
"learning_rate": 0.00012219176561637266,
"loss": 0.2235,
"step": 1001
},
{
"epoch": 2.68,
"learning_rate": 0.00012205096779759206,
"loss": 0.2265,
"step": 1002
},
{
"epoch": 2.68,
"learning_rate": 0.00012191012401568698,
"loss": 0.2375,
"step": 1003
},
{
"epoch": 2.68,
"learning_rate": 0.00012176923456423284,
"loss": 0.212,
"step": 1004
},
{
"epoch": 2.69,
"learning_rate": 0.00012162829973690016,
"loss": 0.2134,
"step": 1005
},
{
"epoch": 2.69,
"learning_rate": 0.000121487319827454,
"loss": 0.2368,
"step": 1006
},
{
"epoch": 2.69,
"learning_rate": 0.00012134629512975351,
"loss": 0.2548,
"step": 1007
},
{
"epoch": 2.7,
"learning_rate": 0.00012120522593775108,
"loss": 0.206,
"step": 1008
},
{
"epoch": 2.7,
"learning_rate": 0.0001210641125454919,
"loss": 0.2221,
"step": 1009
},
{
"epoch": 2.7,
"learning_rate": 0.0001209229552471133,
"loss": 0.2304,
"step": 1010
},
{
"epoch": 2.7,
"learning_rate": 0.00012078175433684407,
"loss": 0.2114,
"step": 1011
},
{
"epoch": 2.71,
"learning_rate": 0.00012064051010900397,
"loss": 0.226,
"step": 1012
},
{
"epoch": 2.71,
"learning_rate": 0.00012049922285800306,
"loss": 0.2127,
"step": 1013
},
{
"epoch": 2.71,
"learning_rate": 0.00012035789287834098,
"loss": 0.2336,
"step": 1014
},
{
"epoch": 2.71,
"learning_rate": 0.00012021652046460658,
"loss": 0.2131,
"step": 1015
},
{
"epoch": 2.72,
"learning_rate": 0.00012007510591147697,
"loss": 0.2514,
"step": 1016
},
{
"epoch": 2.72,
"learning_rate": 0.00011993364951371732,
"loss": 0.2278,
"step": 1017
},
{
"epoch": 2.72,
"learning_rate": 0.0001197921515661798,
"loss": 0.2223,
"step": 1018
},
{
"epoch": 2.72,
"learning_rate": 0.00011965061236380335,
"loss": 0.2218,
"step": 1019
},
{
"epoch": 2.73,
"learning_rate": 0.00011950903220161285,
"loss": 0.2111,
"step": 1020
},
{
"epoch": 2.73,
"learning_rate": 0.0001193674113747185,
"loss": 0.2326,
"step": 1021
},
{
"epoch": 2.73,
"learning_rate": 0.00011922575017831537,
"loss": 0.2148,
"step": 1022
},
{
"epoch": 2.74,
"learning_rate": 0.00011908404890768254,
"loss": 0.2322,
"step": 1023
},
{
"epoch": 2.74,
"learning_rate": 0.00011894230785818284,
"loss": 0.2149,
"step": 1024
},
{
"epoch": 2.74,
"learning_rate": 0.0001188005273252617,
"loss": 0.24,
"step": 1025
},
{
"epoch": 2.74,
"learning_rate": 0.00011865870760444715,
"loss": 0.2474,
"step": 1026
},
{
"epoch": 2.75,
"learning_rate": 0.0001185168489913487,
"loss": 0.2116,
"step": 1027
},
{
"epoch": 2.75,
"learning_rate": 0.00011837495178165706,
"loss": 0.2299,
"step": 1028
},
{
"epoch": 2.75,
"learning_rate": 0.00011823301627114326,
"loss": 0.2418,
"step": 1029
},
{
"epoch": 2.75,
"learning_rate": 0.00011809104275565834,
"loss": 0.2002,
"step": 1030
},
{
"epoch": 2.76,
"learning_rate": 0.00011794903153113239,
"loss": 0.2189,
"step": 1031
},
{
"epoch": 2.76,
"learning_rate": 0.00011780698289357419,
"loss": 0.2316,
"step": 1032
},
{
"epoch": 2.76,
"learning_rate": 0.00011766489713907047,
"loss": 0.2221,
"step": 1033
},
{
"epoch": 2.76,
"learning_rate": 0.00011752277456378535,
"loss": 0.2452,
"step": 1034
},
{
"epoch": 2.77,
"learning_rate": 0.00011738061546395967,
"loss": 0.2094,
"step": 1035
},
{
"epoch": 2.77,
"learning_rate": 0.00011723842013591044,
"loss": 0.2103,
"step": 1036
},
{
"epoch": 2.77,
"learning_rate": 0.00011709618887603014,
"loss": 0.2323,
"step": 1037
},
{
"epoch": 2.78,
"learning_rate": 0.00011695392198078617,
"loss": 0.2185,
"step": 1038
},
{
"epoch": 2.78,
"learning_rate": 0.00011681161974672026,
"loss": 0.2019,
"step": 1039
},
{
"epoch": 2.78,
"learning_rate": 0.00011666928247044768,
"loss": 0.223,
"step": 1040
},
{
"epoch": 2.78,
"learning_rate": 0.00011652691044865687,
"loss": 0.2317,
"step": 1041
},
{
"epoch": 2.79,
"learning_rate": 0.00011638450397810858,
"loss": 0.2202,
"step": 1042
},
{
"epoch": 2.79,
"learning_rate": 0.00011624206335563545,
"loss": 0.2492,
"step": 1043
},
{
"epoch": 2.79,
"learning_rate": 0.00011609958887814129,
"loss": 0.2349,
"step": 1044
},
{
"epoch": 2.79,
"learning_rate": 0.00011595708084260044,
"loss": 0.2129,
"step": 1045
},
{
"epoch": 2.8,
"learning_rate": 0.00011581453954605723,
"loss": 0.2255,
"step": 1046
},
{
"epoch": 2.8,
"learning_rate": 0.0001156719652856253,
"loss": 0.2182,
"step": 1047
},
{
"epoch": 2.8,
"learning_rate": 0.00011552935835848697,
"loss": 0.2516,
"step": 1048
},
{
"epoch": 2.8,
"learning_rate": 0.00011538671906189271,
"loss": 0.2219,
"step": 1049
},
{
"epoch": 2.81,
"learning_rate": 0.00011524404769316041,
"loss": 0.2393,
"step": 1050
},
{
"epoch": 2.81,
"learning_rate": 0.00011510134454967492,
"loss": 0.2118,
"step": 1051
},
{
"epoch": 2.81,
"learning_rate": 0.00011495860992888712,
"loss": 0.2226,
"step": 1052
},
{
"epoch": 2.82,
"learning_rate": 0.0001148158441283137,
"loss": 0.2183,
"step": 1053
},
{
"epoch": 2.82,
"learning_rate": 0.00011467304744553618,
"loss": 0.2082,
"step": 1054
},
{
"epoch": 2.82,
"learning_rate": 0.00011453022017820061,
"loss": 0.211,
"step": 1055
},
{
"epoch": 2.82,
"learning_rate": 0.00011438736262401669,
"loss": 0.2152,
"step": 1056
},
{
"epoch": 2.83,
"learning_rate": 0.00011424447508075722,
"loss": 0.2093,
"step": 1057
},
{
"epoch": 2.83,
"learning_rate": 0.00011410155784625763,
"loss": 0.216,
"step": 1058
},
{
"epoch": 2.83,
"learning_rate": 0.00011395861121841514,
"loss": 0.2243,
"step": 1059
},
{
"epoch": 2.83,
"learning_rate": 0.00011381563549518823,
"loss": 0.2287,
"step": 1060
},
{
"epoch": 2.84,
"learning_rate": 0.0001136726309745961,
"loss": 0.2347,
"step": 1061
},
{
"epoch": 2.84,
"learning_rate": 0.00011352959795471798,
"loss": 0.2311,
"step": 1062
},
{
"epoch": 2.84,
"learning_rate": 0.00011338653673369235,
"loss": 0.1983,
"step": 1063
},
{
"epoch": 2.84,
"learning_rate": 0.00011324344760971671,
"loss": 0.2274,
"step": 1064
},
{
"epoch": 2.85,
"learning_rate": 0.00011310033088104648,
"loss": 0.2163,
"step": 1065
},
{
"epoch": 2.85,
"learning_rate": 0.00011295718684599485,
"loss": 0.2446,
"step": 1066
},
{
"epoch": 2.85,
"learning_rate": 0.0001128140158029317,
"loss": 0.2512,
"step": 1067
},
{
"epoch": 2.86,
"learning_rate": 0.00011267081805028339,
"loss": 0.2295,
"step": 1068
},
{
"epoch": 2.86,
"learning_rate": 0.00011252759388653187,
"loss": 0.2291,
"step": 1069
},
{
"epoch": 2.86,
"learning_rate": 0.00011238434361021412,
"loss": 0.2123,
"step": 1070
},
{
"epoch": 2.86,
"learning_rate": 0.00011224106751992163,
"loss": 0.2008,
"step": 1071
},
{
"epoch": 2.87,
"learning_rate": 0.00011209776591429962,
"loss": 0.2185,
"step": 1072
},
{
"epoch": 2.87,
"learning_rate": 0.00011195443909204653,
"loss": 0.214,
"step": 1073
},
{
"epoch": 2.87,
"learning_rate": 0.00011181108735191332,
"loss": 0.2327,
"step": 1074
},
{
"epoch": 2.87,
"learning_rate": 0.00011166771099270304,
"loss": 0.2352,
"step": 1075
},
{
"epoch": 2.88,
"learning_rate": 0.00011152431031326978,
"loss": 0.2048,
"step": 1076
},
{
"epoch": 2.88,
"learning_rate": 0.0001113808856125186,
"loss": 0.2445,
"step": 1077
},
{
"epoch": 2.88,
"learning_rate": 0.00011123743718940442,
"loss": 0.2066,
"step": 1078
},
{
"epoch": 2.89,
"learning_rate": 0.0001110939653429318,
"loss": 0.2009,
"step": 1079
},
{
"epoch": 2.89,
"learning_rate": 0.00011095047037215396,
"loss": 0.2014,
"step": 1080
},
{
"epoch": 2.89,
"learning_rate": 0.00011080695257617242,
"loss": 0.2432,
"step": 1081
},
{
"epoch": 2.89,
"learning_rate": 0.00011066341225413622,
"loss": 0.2133,
"step": 1082
},
{
"epoch": 2.9,
"learning_rate": 0.00011051984970524134,
"loss": 0.2143,
"step": 1083
},
{
"epoch": 2.9,
"learning_rate": 0.00011037626522873019,
"loss": 0.2271,
"step": 1084
},
{
"epoch": 2.9,
"learning_rate": 0.0001102326591238908,
"loss": 0.2364,
"step": 1085
},
{
"epoch": 2.9,
"learning_rate": 0.00011008903169005627,
"loss": 0.2028,
"step": 1086
},
{
"epoch": 2.91,
"learning_rate": 0.00010994538322660424,
"loss": 0.2276,
"step": 1087
},
{
"epoch": 2.91,
"learning_rate": 0.0001098017140329561,
"loss": 0.2344,
"step": 1088
},
{
"epoch": 2.91,
"learning_rate": 0.00010965802440857644,
"loss": 0.2461,
"step": 1089
},
{
"epoch": 2.91,
"learning_rate": 0.00010951431465297259,
"loss": 0.2039,
"step": 1090
},
{
"epoch": 2.92,
"learning_rate": 0.00010937058506569366,
"loss": 0.2014,
"step": 1091
},
{
"epoch": 2.92,
"learning_rate": 0.00010922683594633021,
"loss": 0.2059,
"step": 1092
},
{
"epoch": 2.92,
"learning_rate": 0.00010908306759451343,
"loss": 0.2229,
"step": 1093
},
{
"epoch": 2.93,
"learning_rate": 0.00010893928030991467,
"loss": 0.2145,
"step": 1094
},
{
"epoch": 2.93,
"learning_rate": 0.00010879547439224472,
"loss": 0.2359,
"step": 1095
},
{
"epoch": 2.93,
"learning_rate": 0.00010865165014125316,
"loss": 0.2498,
"step": 1096
},
{
"epoch": 2.93,
"learning_rate": 0.00010850780785672785,
"loss": 0.2163,
"step": 1097
},
{
"epoch": 2.94,
"learning_rate": 0.00010836394783849423,
"loss": 0.214,
"step": 1098
},
{
"epoch": 2.94,
"learning_rate": 0.00010822007038641466,
"loss": 0.2397,
"step": 1099
},
{
"epoch": 2.94,
"learning_rate": 0.00010807617580038796,
"loss": 0.2229,
"step": 1100
},
{
"epoch": 2.94,
"learning_rate": 0.00010793226438034842,
"loss": 0.2626,
"step": 1101
},
{
"epoch": 2.95,
"learning_rate": 0.00010778833642626573,
"loss": 0.2287,
"step": 1102
},
{
"epoch": 2.95,
"learning_rate": 0.00010764439223814378,
"loss": 0.2192,
"step": 1103
},
{
"epoch": 2.95,
"learning_rate": 0.00010750043211602045,
"loss": 0.2083,
"step": 1104
},
{
"epoch": 2.95,
"learning_rate": 0.00010735645635996676,
"loss": 0.2376,
"step": 1105
},
{
"epoch": 2.96,
"learning_rate": 0.00010721246527008638,
"loss": 0.2221,
"step": 1106
},
{
"epoch": 2.96,
"learning_rate": 0.00010706845914651486,
"loss": 0.203,
"step": 1107
},
{
"epoch": 2.96,
"learning_rate": 0.00010692443828941918,
"loss": 0.2004,
"step": 1108
},
{
"epoch": 2.97,
"learning_rate": 0.00010678040299899697,
"loss": 0.2245,
"step": 1109
},
{
"epoch": 2.97,
"learning_rate": 0.00010663635357547592,
"loss": 0.23,
"step": 1110
},
{
"epoch": 2.97,
"learning_rate": 0.0001064922903191133,
"loss": 0.1977,
"step": 1111
},
{
"epoch": 2.97,
"learning_rate": 0.00010634821353019504,
"loss": 0.2057,
"step": 1112
},
{
"epoch": 2.98,
"learning_rate": 0.00010620412350903544,
"loss": 0.211,
"step": 1113
},
{
"epoch": 2.98,
"learning_rate": 0.00010606002055597626,
"loss": 0.2058,
"step": 1114
},
{
"epoch": 2.98,
"learning_rate": 0.0001059159049713863,
"loss": 0.1991,
"step": 1115
},
{
"epoch": 2.98,
"learning_rate": 0.00010577177705566061,
"loss": 0.2428,
"step": 1116
},
{
"epoch": 2.99,
"learning_rate": 0.00010562763710922003,
"loss": 0.1982,
"step": 1117
},
{
"epoch": 2.99,
"learning_rate": 0.00010548348543251042,
"loss": 0.2052,
"step": 1118
},
{
"epoch": 2.99,
"learning_rate": 0.00010533932232600213,
"loss": 0.1951,
"step": 1119
},
{
"epoch": 2.99,
"learning_rate": 0.00010519514809018927,
"loss": 0.2212,
"step": 1120
},
{
"epoch": 3.0,
"learning_rate": 0.00010505096302558918,
"loss": 0.2458,
"step": 1121
},
{
"epoch": 3.0,
"learning_rate": 0.00010490676743274181,
"loss": 0.1722,
"step": 1122
},
{
"epoch": 3.0,
"learning_rate": 0.000104762561612209,
"loss": 0.0723,
"step": 1123
},
{
"epoch": 3.01,
"learning_rate": 0.00010461834586457398,
"loss": 0.0731,
"step": 1124
},
{
"epoch": 3.01,
"learning_rate": 0.00010447412049044054,
"loss": 0.0707,
"step": 1125
},
{
"epoch": 3.01,
"learning_rate": 0.00010432988579043273,
"loss": 0.0749,
"step": 1126
},
{
"epoch": 3.01,
"learning_rate": 0.00010418564206519378,
"loss": 0.0795,
"step": 1127
},
{
"epoch": 3.02,
"learning_rate": 0.00010404138961538603,
"loss": 0.0611,
"step": 1128
},
{
"epoch": 3.02,
"learning_rate": 0.00010389712874168979,
"loss": 0.07,
"step": 1129
},
{
"epoch": 3.02,
"learning_rate": 0.000103752859744803,
"loss": 0.0732,
"step": 1130
},
{
"epoch": 3.02,
"learning_rate": 0.00010360858292544052,
"loss": 0.0548,
"step": 1131
},
{
"epoch": 3.03,
"learning_rate": 0.00010346429858433352,
"loss": 0.059,
"step": 1132
},
{
"epoch": 3.03,
"learning_rate": 0.00010332000702222889,
"loss": 0.061,
"step": 1133
},
{
"epoch": 3.03,
"learning_rate": 0.00010317570853988848,
"loss": 0.0594,
"step": 1134
},
{
"epoch": 3.03,
"learning_rate": 0.00010303140343808864,
"loss": 0.0713,
"step": 1135
},
{
"epoch": 3.04,
"learning_rate": 0.00010288709201761948,
"loss": 0.0637,
"step": 1136
},
{
"epoch": 3.04,
"learning_rate": 0.0001027427745792843,
"loss": 0.0679,
"step": 1137
},
{
"epoch": 3.04,
"learning_rate": 0.00010259845142389899,
"loss": 0.0657,
"step": 1138
},
{
"epoch": 3.05,
"learning_rate": 0.00010245412285229124,
"loss": 0.0707,
"step": 1139
},
{
"epoch": 3.05,
"learning_rate": 0.00010230978916530012,
"loss": 0.0598,
"step": 1140
},
{
"epoch": 3.05,
"learning_rate": 0.00010216545066377534,
"loss": 0.0605,
"step": 1141
},
{
"epoch": 3.05,
"learning_rate": 0.00010202110764857662,
"loss": 0.0687,
"step": 1142
},
{
"epoch": 3.06,
"learning_rate": 0.00010187676042057315,
"loss": 0.0654,
"step": 1143
},
{
"epoch": 3.06,
"learning_rate": 0.00010173240928064285,
"loss": 0.0736,
"step": 1144
},
{
"epoch": 3.06,
"learning_rate": 0.0001015880545296718,
"loss": 0.0718,
"step": 1145
},
{
"epoch": 3.06,
"learning_rate": 0.00010144369646855359,
"loss": 0.069,
"step": 1146
},
{
"epoch": 3.07,
"learning_rate": 0.00010129933539818876,
"loss": 0.0712,
"step": 1147
},
{
"epoch": 3.07,
"learning_rate": 0.00010115497161948409,
"loss": 0.0572,
"step": 1148
},
{
"epoch": 3.07,
"learning_rate": 0.00010101060543335204,
"loss": 0.058,
"step": 1149
},
{
"epoch": 3.07,
"learning_rate": 0.00010086623714070998,
"loss": 0.0601,
"step": 1150
},
{
"epoch": 3.08,
"learning_rate": 0.00010072186704247986,
"loss": 0.065,
"step": 1151
},
{
"epoch": 3.08,
"learning_rate": 0.00010057749543958717,
"loss": 0.0624,
"step": 1152
},
{
"epoch": 3.08,
"learning_rate": 0.00010043312263296074,
"loss": 0.0534,
"step": 1153
},
{
"epoch": 3.09,
"learning_rate": 0.00010028874892353175,
"loss": 0.0749,
"step": 1154
},
{
"epoch": 3.09,
"learning_rate": 0.00010014437461223339,
"loss": 0.0702,
"step": 1155
},
{
"epoch": 3.09,
"learning_rate": 0.0001,
"loss": 0.0644,
"step": 1156
},
{
"epoch": 3.09,
"learning_rate": 9.985562538776662e-05,
"loss": 0.0651,
"step": 1157
},
{
"epoch": 3.1,
"learning_rate": 9.971125107646825e-05,
"loss": 0.062,
"step": 1158
},
{
"epoch": 3.1,
"learning_rate": 9.95668773670393e-05,
"loss": 0.0585,
"step": 1159
},
{
"epoch": 3.1,
"learning_rate": 9.942250456041286e-05,
"loss": 0.0579,
"step": 1160
},
{
"epoch": 3.1,
"learning_rate": 9.927813295752016e-05,
"loss": 0.0654,
"step": 1161
},
{
"epoch": 3.11,
"learning_rate": 9.913376285929002e-05,
"loss": 0.0704,
"step": 1162
},
{
"epoch": 3.11,
"learning_rate": 9.898939456664801e-05,
"loss": 0.0659,
"step": 1163
},
{
"epoch": 3.11,
"learning_rate": 9.884502838051595e-05,
"loss": 0.0666,
"step": 1164
},
{
"epoch": 3.11,
"learning_rate": 9.870066460181126e-05,
"loss": 0.0574,
"step": 1165
},
{
"epoch": 3.12,
"learning_rate": 9.855630353144643e-05,
"loss": 0.074,
"step": 1166
},
{
"epoch": 3.12,
"learning_rate": 9.841194547032825e-05,
"loss": 0.0649,
"step": 1167
},
{
"epoch": 3.12,
"learning_rate": 9.826759071935718e-05,
"loss": 0.0662,
"step": 1168
},
{
"epoch": 3.13,
"learning_rate": 9.812323957942686e-05,
"loss": 0.0579,
"step": 1169
},
{
"epoch": 3.13,
"learning_rate": 9.797889235142337e-05,
"loss": 0.0625,
"step": 1170
},
{
"epoch": 3.13,
"learning_rate": 9.783454933622471e-05,
"loss": 0.0732,
"step": 1171
},
{
"epoch": 3.13,
"learning_rate": 9.76902108346999e-05,
"loss": 0.0776,
"step": 1172
},
{
"epoch": 3.14,
"learning_rate": 9.754587714770878e-05,
"loss": 0.0632,
"step": 1173
},
{
"epoch": 3.14,
"learning_rate": 9.740154857610102e-05,
"loss": 0.0656,
"step": 1174
},
{
"epoch": 3.14,
"learning_rate": 9.72572254207157e-05,
"loss": 0.0581,
"step": 1175
},
{
"epoch": 3.14,
"learning_rate": 9.711290798238057e-05,
"loss": 0.0628,
"step": 1176
},
{
"epoch": 3.15,
"learning_rate": 9.69685965619114e-05,
"loss": 0.0598,
"step": 1177
},
{
"epoch": 3.15,
"learning_rate": 9.682429146011156e-05,
"loss": 0.0645,
"step": 1178
},
{
"epoch": 3.15,
"learning_rate": 9.667999297777112e-05,
"loss": 0.0602,
"step": 1179
},
{
"epoch": 3.16,
"learning_rate": 9.653570141566653e-05,
"loss": 0.0656,
"step": 1180
},
{
"epoch": 3.16,
"learning_rate": 9.63914170745595e-05,
"loss": 0.0721,
"step": 1181
},
{
"epoch": 3.16,
"learning_rate": 9.624714025519703e-05,
"loss": 0.0663,
"step": 1182
},
{
"epoch": 3.16,
"learning_rate": 9.610287125831022e-05,
"loss": 0.0577,
"step": 1183
},
{
"epoch": 3.17,
"learning_rate": 9.595861038461398e-05,
"loss": 0.0618,
"step": 1184
},
{
"epoch": 3.17,
"learning_rate": 9.581435793480623e-05,
"loss": 0.0628,
"step": 1185
},
{
"epoch": 3.17,
"learning_rate": 9.567011420956731e-05,
"loss": 0.0521,
"step": 1186
},
{
"epoch": 3.17,
"learning_rate": 9.552587950955945e-05,
"loss": 0.0669,
"step": 1187
},
{
"epoch": 3.18,
"learning_rate": 9.538165413542607e-05,
"loss": 0.0565,
"step": 1188
},
{
"epoch": 3.18,
"learning_rate": 9.523743838779102e-05,
"loss": 0.0649,
"step": 1189
},
{
"epoch": 3.18,
"learning_rate": 9.509323256725821e-05,
"loss": 0.0646,
"step": 1190
},
{
"epoch": 3.18,
"learning_rate": 9.494903697441083e-05,
"loss": 0.0652,
"step": 1191
},
{
"epoch": 3.19,
"learning_rate": 9.480485190981073e-05,
"loss": 0.0646,
"step": 1192
},
{
"epoch": 3.19,
"learning_rate": 9.466067767399788e-05,
"loss": 0.0779,
"step": 1193
},
{
"epoch": 3.19,
"learning_rate": 9.451651456748958e-05,
"loss": 0.0559,
"step": 1194
},
{
"epoch": 3.2,
"learning_rate": 9.437236289077998e-05,
"loss": 0.0594,
"step": 1195
},
{
"epoch": 3.2,
"learning_rate": 9.422822294433939e-05,
"loss": 0.066,
"step": 1196
},
{
"epoch": 3.2,
"learning_rate": 9.408409502861374e-05,
"loss": 0.062,
"step": 1197
},
{
"epoch": 3.2,
"learning_rate": 9.393997944402378e-05,
"loss": 0.0589,
"step": 1198
},
{
"epoch": 3.21,
"learning_rate": 9.379587649096457e-05,
"loss": 0.0699,
"step": 1199
},
{
"epoch": 3.21,
"learning_rate": 9.365178646980497e-05,
"loss": 0.0639,
"step": 1200
},
{
"epoch": 3.21,
"learning_rate": 9.350770968088674e-05,
"loss": 0.0655,
"step": 1201
},
{
"epoch": 3.21,
"learning_rate": 9.33636464245241e-05,
"loss": 0.0653,
"step": 1202
},
{
"epoch": 3.22,
"learning_rate": 9.321959700100305e-05,
"loss": 0.0586,
"step": 1203
},
{
"epoch": 3.22,
"learning_rate": 9.307556171058085e-05,
"loss": 0.065,
"step": 1204
},
{
"epoch": 3.22,
"learning_rate": 9.293154085348519e-05,
"loss": 0.0667,
"step": 1205
},
{
"epoch": 3.22,
"learning_rate": 9.278753472991366e-05,
"loss": 0.0675,
"step": 1206
},
{
"epoch": 3.23,
"learning_rate": 9.264354364003327e-05,
"loss": 0.0698,
"step": 1207
},
{
"epoch": 3.23,
"learning_rate": 9.249956788397957e-05,
"loss": 0.0737,
"step": 1208
},
{
"epoch": 3.23,
"learning_rate": 9.235560776185623e-05,
"loss": 0.0645,
"step": 1209
},
{
"epoch": 3.24,
"learning_rate": 9.22116635737343e-05,
"loss": 0.0674,
"step": 1210
},
{
"epoch": 3.24,
"learning_rate": 9.206773561965159e-05,
"loss": 0.0732,
"step": 1211
},
{
"epoch": 3.24,
"learning_rate": 9.192382419961208e-05,
"loss": 0.0587,
"step": 1212
},
{
"epoch": 3.24,
"learning_rate": 9.177992961358532e-05,
"loss": 0.0668,
"step": 1213
},
{
"epoch": 3.25,
"learning_rate": 9.16360521615058e-05,
"loss": 0.0598,
"step": 1214
},
{
"epoch": 3.25,
"learning_rate": 9.149219214327217e-05,
"loss": 0.0535,
"step": 1215
},
{
"epoch": 3.25,
"learning_rate": 9.134834985874688e-05,
"loss": 0.07,
"step": 1216
},
{
"epoch": 3.25,
"learning_rate": 9.120452560775532e-05,
"loss": 0.0592,
"step": 1217
},
{
"epoch": 3.26,
"learning_rate": 9.106071969008537e-05,
"loss": 0.0601,
"step": 1218
},
{
"epoch": 3.26,
"learning_rate": 9.091693240548658e-05,
"loss": 0.0705,
"step": 1219
},
{
"epoch": 3.26,
"learning_rate": 9.077316405366981e-05,
"loss": 0.0555,
"step": 1220
},
{
"epoch": 3.26,
"learning_rate": 9.062941493430633e-05,
"loss": 0.0712,
"step": 1221
},
{
"epoch": 3.27,
"learning_rate": 9.048568534702743e-05,
"loss": 0.0657,
"step": 1222
},
{
"epoch": 3.27,
"learning_rate": 9.034197559142357e-05,
"loss": 0.0666,
"step": 1223
},
{
"epoch": 3.27,
"learning_rate": 9.019828596704394e-05,
"loss": 0.0647,
"step": 1224
},
{
"epoch": 3.28,
"learning_rate": 9.00546167733958e-05,
"loss": 0.0516,
"step": 1225
},
{
"epoch": 3.28,
"learning_rate": 8.991096830994374e-05,
"loss": 0.0601,
"step": 1226
},
{
"epoch": 3.28,
"learning_rate": 8.976734087610925e-05,
"loss": 0.0666,
"step": 1227
},
{
"epoch": 3.28,
"learning_rate": 8.962373477126983e-05,
"loss": 0.0536,
"step": 1228
},
{
"epoch": 3.29,
"learning_rate": 8.948015029475867e-05,
"loss": 0.0634,
"step": 1229
},
{
"epoch": 3.29,
"learning_rate": 8.933658774586379e-05,
"loss": 0.0612,
"step": 1230
},
{
"epoch": 3.29,
"learning_rate": 8.919304742382761e-05,
"loss": 0.062,
"step": 1231
},
{
"epoch": 3.29,
"learning_rate": 8.904952962784605e-05,
"loss": 0.0702,
"step": 1232
},
{
"epoch": 3.3,
"learning_rate": 8.890603465706822e-05,
"loss": 0.0617,
"step": 1233
},
{
"epoch": 3.3,
"learning_rate": 8.876256281059557e-05,
"loss": 0.072,
"step": 1234
},
{
"epoch": 3.3,
"learning_rate": 8.861911438748145e-05,
"loss": 0.058,
"step": 1235
},
{
"epoch": 3.3,
"learning_rate": 8.847568968673026e-05,
"loss": 0.0631,
"step": 1236
},
{
"epoch": 3.31,
"learning_rate": 8.8332289007297e-05,
"loss": 0.0624,
"step": 1237
},
{
"epoch": 3.31,
"learning_rate": 8.818891264808666e-05,
"loss": 0.06,
"step": 1238
},
{
"epoch": 3.31,
"learning_rate": 8.804556090795351e-05,
"loss": 0.0551,
"step": 1239
},
{
"epoch": 3.32,
"learning_rate": 8.790223408570042e-05,
"loss": 0.0572,
"step": 1240
},
{
"epoch": 3.32,
"learning_rate": 8.775893248007839e-05,
"loss": 0.0688,
"step": 1241
},
{
"epoch": 3.32,
"learning_rate": 8.761565638978589e-05,
"loss": 0.0651,
"step": 1242
},
{
"epoch": 3.32,
"learning_rate": 8.747240611346814e-05,
"loss": 0.0646,
"step": 1243
},
{
"epoch": 3.33,
"learning_rate": 8.732918194971664e-05,
"loss": 0.0653,
"step": 1244
},
{
"epoch": 3.33,
"learning_rate": 8.718598419706833e-05,
"loss": 0.0638,
"step": 1245
},
{
"epoch": 3.33,
"learning_rate": 8.704281315400517e-05,
"loss": 0.0657,
"step": 1246
},
{
"epoch": 3.33,
"learning_rate": 8.68996691189535e-05,
"loss": 0.0536,
"step": 1247
},
{
"epoch": 3.34,
"learning_rate": 8.675655239028333e-05,
"loss": 0.0631,
"step": 1248
},
{
"epoch": 3.34,
"learning_rate": 8.661346326630767e-05,
"loss": 0.0624,
"step": 1249
},
{
"epoch": 3.34,
"learning_rate": 8.647040204528205e-05,
"loss": 0.0511,
"step": 1250
},
{
"epoch": 3.34,
"learning_rate": 8.63273690254039e-05,
"loss": 0.0644,
"step": 1251
},
{
"epoch": 3.35,
"learning_rate": 8.61843645048118e-05,
"loss": 0.0616,
"step": 1252
},
{
"epoch": 3.35,
"learning_rate": 8.60413887815849e-05,
"loss": 0.0617,
"step": 1253
},
{
"epoch": 3.35,
"learning_rate": 8.58984421537424e-05,
"loss": 0.0583,
"step": 1254
},
{
"epoch": 3.36,
"learning_rate": 8.575552491924279e-05,
"loss": 0.0635,
"step": 1255
},
{
"epoch": 3.36,
"learning_rate": 8.561263737598338e-05,
"loss": 0.0648,
"step": 1256
},
{
"epoch": 3.36,
"learning_rate": 8.546977982179941e-05,
"loss": 0.0556,
"step": 1257
},
{
"epoch": 3.36,
"learning_rate": 8.532695255446383e-05,
"loss": 0.0738,
"step": 1258
},
{
"epoch": 3.37,
"learning_rate": 8.518415587168633e-05,
"loss": 0.0687,
"step": 1259
},
{
"epoch": 3.37,
"learning_rate": 8.504139007111289e-05,
"loss": 0.0603,
"step": 1260
},
{
"epoch": 3.37,
"learning_rate": 8.489865545032513e-05,
"loss": 0.0605,
"step": 1261
},
{
"epoch": 3.37,
"learning_rate": 8.47559523068396e-05,
"loss": 0.0588,
"step": 1262
},
{
"epoch": 3.38,
"learning_rate": 8.46132809381073e-05,
"loss": 0.0515,
"step": 1263
},
{
"epoch": 3.38,
"learning_rate": 8.447064164151304e-05,
"loss": 0.0616,
"step": 1264
},
{
"epoch": 3.38,
"learning_rate": 8.432803471437475e-05,
"loss": 0.0767,
"step": 1265
},
{
"epoch": 3.39,
"learning_rate": 8.418546045394279e-05,
"loss": 0.0622,
"step": 1266
},
{
"epoch": 3.39,
"learning_rate": 8.404291915739957e-05,
"loss": 0.0507,
"step": 1267
},
{
"epoch": 3.39,
"learning_rate": 8.39004111218587e-05,
"loss": 0.0561,
"step": 1268
},
{
"epoch": 3.39,
"learning_rate": 8.375793664436457e-05,
"loss": 0.0644,
"step": 1269
},
{
"epoch": 3.4,
"learning_rate": 8.361549602189144e-05,
"loss": 0.0699,
"step": 1270
},
{
"epoch": 3.4,
"learning_rate": 8.347308955134317e-05,
"loss": 0.056,
"step": 1271
},
{
"epoch": 3.4,
"learning_rate": 8.333071752955233e-05,
"loss": 0.0576,
"step": 1272
},
{
"epoch": 3.4,
"learning_rate": 8.318838025327977e-05,
"loss": 0.0804,
"step": 1273
},
{
"epoch": 3.41,
"learning_rate": 8.304607801921384e-05,
"loss": 0.0729,
"step": 1274
},
{
"epoch": 3.41,
"learning_rate": 8.290381112396987e-05,
"loss": 0.0665,
"step": 1275
},
{
"epoch": 3.41,
"learning_rate": 8.27615798640896e-05,
"loss": 0.0732,
"step": 1276
},
{
"epoch": 3.41,
"learning_rate": 8.261938453604033e-05,
"loss": 0.0577,
"step": 1277
},
{
"epoch": 3.42,
"learning_rate": 8.24772254362147e-05,
"loss": 0.054,
"step": 1278
},
{
"epoch": 3.42,
"learning_rate": 8.233510286092955e-05,
"loss": 0.062,
"step": 1279
},
{
"epoch": 3.42,
"learning_rate": 8.219301710642583e-05,
"loss": 0.058,
"step": 1280
},
{
"epoch": 3.43,
"learning_rate": 8.20509684688676e-05,
"loss": 0.0658,
"step": 1281
},
{
"epoch": 3.43,
"learning_rate": 8.190895724434168e-05,
"loss": 0.0618,
"step": 1282
},
{
"epoch": 3.43,
"learning_rate": 8.176698372885675e-05,
"loss": 0.0523,
"step": 1283
},
{
"epoch": 3.43,
"learning_rate": 8.162504821834295e-05,
"loss": 0.067,
"step": 1284
},
{
"epoch": 3.44,
"learning_rate": 8.148315100865131e-05,
"loss": 0.0567,
"step": 1285
},
{
"epoch": 3.44,
"learning_rate": 8.13412923955529e-05,
"loss": 0.0579,
"step": 1286
},
{
"epoch": 3.44,
"learning_rate": 8.119947267473833e-05,
"loss": 0.0698,
"step": 1287
},
{
"epoch": 3.44,
"learning_rate": 8.10576921418172e-05,
"loss": 0.0744,
"step": 1288
},
{
"epoch": 3.45,
"learning_rate": 8.091595109231745e-05,
"loss": 0.0524,
"step": 1289
},
{
"epoch": 3.45,
"learning_rate": 8.077424982168468e-05,
"loss": 0.0585,
"step": 1290
},
{
"epoch": 3.45,
"learning_rate": 8.063258862528152e-05,
"loss": 0.061,
"step": 1291
},
{
"epoch": 3.45,
"learning_rate": 8.049096779838719e-05,
"loss": 0.0642,
"step": 1292
},
{
"epoch": 3.46,
"learning_rate": 8.034938763619667e-05,
"loss": 0.0681,
"step": 1293
},
{
"epoch": 3.46,
"learning_rate": 8.020784843382022e-05,
"loss": 0.0548,
"step": 1294
},
{
"epoch": 3.46,
"learning_rate": 8.006635048628273e-05,
"loss": 0.0552,
"step": 1295
},
{
"epoch": 3.47,
"learning_rate": 7.992489408852306e-05,
"loss": 0.0644,
"step": 1296
},
{
"epoch": 3.47,
"learning_rate": 7.978347953539344e-05,
"loss": 0.0676,
"step": 1297
},
{
"epoch": 3.47,
"learning_rate": 7.964210712165902e-05,
"loss": 0.0708,
"step": 1298
},
{
"epoch": 3.47,
"learning_rate": 7.950077714199698e-05,
"loss": 0.0569,
"step": 1299
},
{
"epoch": 3.48,
"learning_rate": 7.935948989099605e-05,
"loss": 0.0669,
"step": 1300
},
{
"epoch": 3.48,
"learning_rate": 7.921824566315594e-05,
"loss": 0.0658,
"step": 1301
},
{
"epoch": 3.48,
"learning_rate": 7.907704475288673e-05,
"loss": 0.062,
"step": 1302
},
{
"epoch": 3.48,
"learning_rate": 7.893588745450814e-05,
"loss": 0.0584,
"step": 1303
},
{
"epoch": 3.49,
"learning_rate": 7.879477406224894e-05,
"loss": 0.0553,
"step": 1304
},
{
"epoch": 3.49,
"learning_rate": 7.865370487024652e-05,
"loss": 0.0678,
"step": 1305
},
{
"epoch": 3.49,
"learning_rate": 7.851268017254598e-05,
"loss": 0.0634,
"step": 1306
},
{
"epoch": 3.49,
"learning_rate": 7.837170026309989e-05,
"loss": 0.0631,
"step": 1307
},
{
"epoch": 3.5,
"learning_rate": 7.823076543576717e-05,
"loss": 0.059,
"step": 1308
},
{
"epoch": 3.5,
"learning_rate": 7.808987598431303e-05,
"loss": 0.0666,
"step": 1309
},
{
"epoch": 3.5,
"learning_rate": 7.794903220240797e-05,
"loss": 0.0566,
"step": 1310
},
{
"epoch": 3.51,
"learning_rate": 7.780823438362733e-05,
"loss": 0.0671,
"step": 1311
},
{
"epoch": 3.51,
"learning_rate": 7.766748282145068e-05,
"loss": 0.0575,
"step": 1312
},
{
"epoch": 3.51,
"learning_rate": 7.752677780926104e-05,
"loss": 0.0597,
"step": 1313
},
{
"epoch": 3.51,
"learning_rate": 7.738611964034457e-05,
"loss": 0.0737,
"step": 1314
},
{
"epoch": 3.52,
"learning_rate": 7.724550860788967e-05,
"loss": 0.0592,
"step": 1315
},
{
"epoch": 3.52,
"learning_rate": 7.710494500498662e-05,
"loss": 0.054,
"step": 1316
},
{
"epoch": 3.52,
"learning_rate": 7.696442912462661e-05,
"loss": 0.0631,
"step": 1317
},
{
"epoch": 3.52,
"learning_rate": 7.68239612597016e-05,
"loss": 0.0648,
"step": 1318
},
{
"epoch": 3.53,
"learning_rate": 7.66835417030033e-05,
"loss": 0.0587,
"step": 1319
},
{
"epoch": 3.53,
"learning_rate": 7.654317074722287e-05,
"loss": 0.0631,
"step": 1320
},
{
"epoch": 3.53,
"learning_rate": 7.640284868495e-05,
"loss": 0.0612,
"step": 1321
},
{
"epoch": 3.53,
"learning_rate": 7.626257580867258e-05,
"loss": 0.055,
"step": 1322
},
{
"epoch": 3.54,
"learning_rate": 7.612235241077596e-05,
"loss": 0.057,
"step": 1323
},
{
"epoch": 3.54,
"learning_rate": 7.598217878354237e-05,
"loss": 0.0492,
"step": 1324
},
{
"epoch": 3.54,
"learning_rate": 7.584205521915023e-05,
"loss": 0.0557,
"step": 1325
},
{
"epoch": 3.55,
"learning_rate": 7.570198200967362e-05,
"loss": 0.0623,
"step": 1326
},
{
"epoch": 3.55,
"learning_rate": 7.556195944708175e-05,
"loss": 0.0513,
"step": 1327
},
{
"epoch": 3.55,
"learning_rate": 7.542198782323819e-05,
"loss": 0.0671,
"step": 1328
},
{
"epoch": 3.55,
"learning_rate": 7.528206742990036e-05,
"loss": 0.0592,
"step": 1329
},
{
"epoch": 3.56,
"learning_rate": 7.514219855871886e-05,
"loss": 0.0616,
"step": 1330
},
{
"epoch": 3.56,
"learning_rate": 7.50023815012369e-05,
"loss": 0.06,
"step": 1331
},
{
"epoch": 3.56,
"learning_rate": 7.486261654888973e-05,
"loss": 0.0648,
"step": 1332
},
{
"epoch": 3.56,
"learning_rate": 7.4722903993004e-05,
"loss": 0.0742,
"step": 1333
},
{
"epoch": 3.57,
"learning_rate": 7.458324412479705e-05,
"loss": 0.06,
"step": 1334
},
{
"epoch": 3.57,
"learning_rate": 7.444363723537648e-05,
"loss": 0.0599,
"step": 1335
},
{
"epoch": 3.57,
"learning_rate": 7.430408361573948e-05,
"loss": 0.0651,
"step": 1336
},
{
"epoch": 3.57,
"learning_rate": 7.416458355677215e-05,
"loss": 0.0649,
"step": 1337
},
{
"epoch": 3.58,
"learning_rate": 7.402513734924894e-05,
"loss": 0.0594,
"step": 1338
},
{
"epoch": 3.58,
"learning_rate": 7.388574528383206e-05,
"loss": 0.0594,
"step": 1339
},
{
"epoch": 3.58,
"learning_rate": 7.374640765107095e-05,
"loss": 0.051,
"step": 1340
},
{
"epoch": 3.59,
"learning_rate": 7.36071247414015e-05,
"loss": 0.067,
"step": 1341
},
{
"epoch": 3.59,
"learning_rate": 7.346789684514549e-05,
"loss": 0.0565,
"step": 1342
},
{
"epoch": 3.59,
"learning_rate": 7.332872425251018e-05,
"loss": 0.0631,
"step": 1343
},
{
"epoch": 3.59,
"learning_rate": 7.318960725358741e-05,
"loss": 0.0605,
"step": 1344
},
{
"epoch": 3.6,
"learning_rate": 7.305054613835326e-05,
"loss": 0.0591,
"step": 1345
},
{
"epoch": 3.6,
"learning_rate": 7.291154119666727e-05,
"loss": 0.0646,
"step": 1346
},
{
"epoch": 3.6,
"learning_rate": 7.277259271827184e-05,
"loss": 0.0549,
"step": 1347
},
{
"epoch": 3.6,
"learning_rate": 7.263370099279172e-05,
"loss": 0.0612,
"step": 1348
},
{
"epoch": 3.61,
"learning_rate": 7.249486630973341e-05,
"loss": 0.0641,
"step": 1349
},
{
"epoch": 3.61,
"learning_rate": 7.235608895848451e-05,
"loss": 0.0574,
"step": 1350
},
{
"epoch": 3.61,
"learning_rate": 7.221736922831297e-05,
"loss": 0.0638,
"step": 1351
},
{
"epoch": 3.61,
"learning_rate": 7.207870740836684e-05,
"loss": 0.0668,
"step": 1352
},
{
"epoch": 3.62,
"learning_rate": 7.194010378767333e-05,
"loss": 0.0656,
"step": 1353
},
{
"epoch": 3.62,
"learning_rate": 7.180155865513838e-05,
"loss": 0.0527,
"step": 1354
},
{
"epoch": 3.62,
"learning_rate": 7.166307229954598e-05,
"loss": 0.0715,
"step": 1355
},
{
"epoch": 3.63,
"learning_rate": 7.152464500955769e-05,
"loss": 0.0528,
"step": 1356
},
{
"epoch": 3.63,
"learning_rate": 7.138627707371184e-05,
"loss": 0.0679,
"step": 1357
},
{
"epoch": 3.63,
"learning_rate": 7.12479687804232e-05,
"loss": 0.0629,
"step": 1358
},
{
"epoch": 3.63,
"learning_rate": 7.110972041798202e-05,
"loss": 0.0659,
"step": 1359
},
{
"epoch": 3.64,
"learning_rate": 7.097153227455379e-05,
"loss": 0.0614,
"step": 1360
},
{
"epoch": 3.64,
"learning_rate": 7.083340463817837e-05,
"loss": 0.0615,
"step": 1361
},
{
"epoch": 3.64,
"learning_rate": 7.069533779676961e-05,
"loss": 0.0595,
"step": 1362
},
{
"epoch": 3.64,
"learning_rate": 7.055733203811458e-05,
"loss": 0.0526,
"step": 1363
},
{
"epoch": 3.65,
"learning_rate": 7.041938764987297e-05,
"loss": 0.0629,
"step": 1364
},
{
"epoch": 3.65,
"learning_rate": 7.028150491957666e-05,
"loss": 0.0606,
"step": 1365
},
{
"epoch": 3.65,
"learning_rate": 7.014368413462891e-05,
"loss": 0.0567,
"step": 1366
},
{
"epoch": 3.66,
"learning_rate": 7.000592558230399e-05,
"loss": 0.0633,
"step": 1367
},
{
"epoch": 3.66,
"learning_rate": 6.98682295497463e-05,
"loss": 0.0632,
"step": 1368
},
{
"epoch": 3.66,
"learning_rate": 6.973059632397002e-05,
"loss": 0.0548,
"step": 1369
},
{
"epoch": 3.66,
"learning_rate": 6.959302619185836e-05,
"loss": 0.0688,
"step": 1370
},
{
"epoch": 3.67,
"learning_rate": 6.94555194401631e-05,
"loss": 0.0587,
"step": 1371
},
{
"epoch": 3.67,
"learning_rate": 6.931807635550383e-05,
"loss": 0.0497,
"step": 1372
},
{
"epoch": 3.67,
"learning_rate": 6.918069722436745e-05,
"loss": 0.0569,
"step": 1373
},
{
"epoch": 3.67,
"learning_rate": 6.904338233310755e-05,
"loss": 0.0571,
"step": 1374
},
{
"epoch": 3.68,
"learning_rate": 6.89061319679439e-05,
"loss": 0.0651,
"step": 1375
},
{
"epoch": 3.68,
"learning_rate": 6.876894641496163e-05,
"loss": 0.0612,
"step": 1376
},
{
"epoch": 3.68,
"learning_rate": 6.863182596011087e-05,
"loss": 0.0567,
"step": 1377
},
{
"epoch": 3.68,
"learning_rate": 6.849477088920604e-05,
"loss": 0.0553,
"step": 1378
},
{
"epoch": 3.69,
"learning_rate": 6.835778148792527e-05,
"loss": 0.0623,
"step": 1379
},
{
"epoch": 3.69,
"learning_rate": 6.822085804180984e-05,
"loss": 0.0598,
"step": 1380
},
{
"epoch": 3.69,
"learning_rate": 6.80840008362635e-05,
"loss": 0.0638,
"step": 1381
},
{
"epoch": 3.7,
"learning_rate": 6.794721015655192e-05,
"loss": 0.0603,
"step": 1382
},
{
"epoch": 3.7,
"learning_rate": 6.781048628780217e-05,
"loss": 0.0595,
"step": 1383
},
{
"epoch": 3.7,
"learning_rate": 6.767382951500204e-05,
"loss": 0.0577,
"step": 1384
},
{
"epoch": 3.7,
"learning_rate": 6.75372401229994e-05,
"loss": 0.0617,
"step": 1385
},
{
"epoch": 3.71,
"learning_rate": 6.740071839650171e-05,
"loss": 0.0651,
"step": 1386
},
{
"epoch": 3.71,
"learning_rate": 6.726426462007546e-05,
"loss": 0.0586,
"step": 1387
},
{
"epoch": 3.71,
"learning_rate": 6.712787907814541e-05,
"loss": 0.0536,
"step": 1388
},
{
"epoch": 3.71,
"learning_rate": 6.699156205499408e-05,
"loss": 0.0606,
"step": 1389
},
{
"epoch": 3.72,
"learning_rate": 6.685531383476128e-05,
"loss": 0.0569,
"step": 1390
},
{
"epoch": 3.72,
"learning_rate": 6.671913470144331e-05,
"loss": 0.0584,
"step": 1391
},
{
"epoch": 3.72,
"learning_rate": 6.65830249388925e-05,
"loss": 0.06,
"step": 1392
},
{
"epoch": 3.72,
"learning_rate": 6.644698483081654e-05,
"loss": 0.0664,
"step": 1393
},
{
"epoch": 3.73,
"learning_rate": 6.6311014660778e-05,
"loss": 0.0647,
"step": 1394
},
{
"epoch": 3.73,
"learning_rate": 6.617511471219364e-05,
"loss": 0.0569,
"step": 1395
},
{
"epoch": 3.73,
"learning_rate": 6.603928526833387e-05,
"loss": 0.0665,
"step": 1396
},
{
"epoch": 3.74,
"learning_rate": 6.590352661232209e-05,
"loss": 0.0656,
"step": 1397
},
{
"epoch": 3.74,
"learning_rate": 6.57678390271342e-05,
"loss": 0.0641,
"step": 1398
},
{
"epoch": 3.74,
"learning_rate": 6.563222279559787e-05,
"loss": 0.0694,
"step": 1399
},
{
"epoch": 3.74,
"learning_rate": 6.54966782003922e-05,
"loss": 0.0607,
"step": 1400
},
{
"epoch": 3.75,
"learning_rate": 6.536120552404688e-05,
"loss": 0.0683,
"step": 1401
},
{
"epoch": 3.75,
"learning_rate": 6.52258050489416e-05,
"loss": 0.0555,
"step": 1402
},
{
"epoch": 3.75,
"learning_rate": 6.509047705730572e-05,
"loss": 0.0612,
"step": 1403
},
{
"epoch": 3.75,
"learning_rate": 6.495522183121741e-05,
"loss": 0.0718,
"step": 1404
},
{
"epoch": 3.76,
"learning_rate": 6.482003965260326e-05,
"loss": 0.0566,
"step": 1405
},
{
"epoch": 3.76,
"learning_rate": 6.468493080323743e-05,
"loss": 0.0596,
"step": 1406
},
{
"epoch": 3.76,
"learning_rate": 6.454989556474142e-05,
"loss": 0.0613,
"step": 1407
},
{
"epoch": 3.76,
"learning_rate": 6.441493421858317e-05,
"loss": 0.0562,
"step": 1408
},
{
"epoch": 3.77,
"learning_rate": 6.428004704607671e-05,
"loss": 0.0699,
"step": 1409
},
{
"epoch": 3.77,
"learning_rate": 6.414523432838133e-05,
"loss": 0.0585,
"step": 1410
},
{
"epoch": 3.77,
"learning_rate": 6.401049634650118e-05,
"loss": 0.0564,
"step": 1411
},
{
"epoch": 3.78,
"learning_rate": 6.387583338128471e-05,
"loss": 0.0719,
"step": 1412
},
{
"epoch": 3.78,
"learning_rate": 6.374124571342386e-05,
"loss": 0.0544,
"step": 1413
},
{
"epoch": 3.78,
"learning_rate": 6.360673362345382e-05,
"loss": 0.0524,
"step": 1414
},
{
"epoch": 3.78,
"learning_rate": 6.347229739175196e-05,
"loss": 0.0548,
"step": 1415
},
{
"epoch": 3.79,
"learning_rate": 6.333793729853781e-05,
"loss": 0.0558,
"step": 1416
},
{
"epoch": 3.79,
"learning_rate": 6.320365362387201e-05,
"loss": 0.0609,
"step": 1417
},
{
"epoch": 3.79,
"learning_rate": 6.306944664765606e-05,
"loss": 0.0621,
"step": 1418
},
{
"epoch": 3.79,
"learning_rate": 6.293531664963144e-05,
"loss": 0.0609,
"step": 1419
},
{
"epoch": 3.8,
"learning_rate": 6.280126390937925e-05,
"loss": 0.0599,
"step": 1420
},
{
"epoch": 3.8,
"learning_rate": 6.26672887063196e-05,
"loss": 0.0615,
"step": 1421
},
{
"epoch": 3.8,
"learning_rate": 6.253339131971092e-05,
"loss": 0.06,
"step": 1422
},
{
"epoch": 3.8,
"learning_rate": 6.239957202864943e-05,
"loss": 0.0715,
"step": 1423
},
{
"epoch": 3.81,
"learning_rate": 6.226583111206856e-05,
"loss": 0.0652,
"step": 1424
},
{
"epoch": 3.81,
"learning_rate": 6.213216884873848e-05,
"loss": 0.0653,
"step": 1425
},
{
"epoch": 3.81,
"learning_rate": 6.199858551726531e-05,
"loss": 0.0626,
"step": 1426
},
{
"epoch": 3.82,
"learning_rate": 6.186508139609064e-05,
"loss": 0.0454,
"step": 1427
},
{
"epoch": 3.82,
"learning_rate": 6.173165676349103e-05,
"loss": 0.0513,
"step": 1428
},
{
"epoch": 3.82,
"learning_rate": 6.15983118975773e-05,
"loss": 0.0655,
"step": 1429
},
{
"epoch": 3.82,
"learning_rate": 6.146504707629399e-05,
"loss": 0.0552,
"step": 1430
},
{
"epoch": 3.83,
"learning_rate": 6.133186257741887e-05,
"loss": 0.0644,
"step": 1431
},
{
"epoch": 3.83,
"learning_rate": 6.11987586785622e-05,
"loss": 0.0594,
"step": 1432
},
{
"epoch": 3.83,
"learning_rate": 6.106573565716627e-05,
"loss": 0.0699,
"step": 1433
},
{
"epoch": 3.83,
"learning_rate": 6.09327937905048e-05,
"loss": 0.0621,
"step": 1434
},
{
"epoch": 3.84,
"learning_rate": 6.079993335568237e-05,
"loss": 0.0702,
"step": 1435
},
{
"epoch": 3.84,
"learning_rate": 6.066715462963376e-05,
"loss": 0.0616,
"step": 1436
},
{
"epoch": 3.84,
"learning_rate": 6.0534457889123455e-05,
"loss": 0.058,
"step": 1437
},
{
"epoch": 3.84,
"learning_rate": 6.0401843410745107e-05,
"loss": 0.0578,
"step": 1438
},
{
"epoch": 3.85,
"learning_rate": 6.0269311470920875e-05,
"loss": 0.0619,
"step": 1439
},
{
"epoch": 3.85,
"learning_rate": 6.013686234590077e-05,
"loss": 0.0538,
"step": 1440
},
{
"epoch": 3.85,
"learning_rate": 6.000449631176236e-05,
"loss": 0.0485,
"step": 1441
},
{
"epoch": 3.86,
"learning_rate": 5.987221364440987e-05,
"loss": 0.0633,
"step": 1442
},
{
"epoch": 3.86,
"learning_rate": 5.974001461957392e-05,
"loss": 0.057,
"step": 1443
},
{
"epoch": 3.86,
"learning_rate": 5.960789951281052e-05,
"loss": 0.0648,
"step": 1444
},
{
"epoch": 3.86,
"learning_rate": 5.947586859950103e-05,
"loss": 0.0581,
"step": 1445
},
{
"epoch": 3.87,
"learning_rate": 5.934392215485116e-05,
"loss": 0.0598,
"step": 1446
},
{
"epoch": 3.87,
"learning_rate": 5.921206045389065e-05,
"loss": 0.0587,
"step": 1447
},
{
"epoch": 3.87,
"learning_rate": 5.9080283771472524e-05,
"loss": 0.0592,
"step": 1448
},
{
"epoch": 3.87,
"learning_rate": 5.8948592382272594e-05,
"loss": 0.0526,
"step": 1449
},
{
"epoch": 3.88,
"learning_rate": 5.8816986560788935e-05,
"loss": 0.0588,
"step": 1450
},
{
"epoch": 3.88,
"learning_rate": 5.868546658134124e-05,
"loss": 0.0606,
"step": 1451
},
{
"epoch": 3.88,
"learning_rate": 5.855403271807033e-05,
"loss": 0.058,
"step": 1452
},
{
"epoch": 3.89,
"learning_rate": 5.842268524493735e-05,
"loss": 0.0558,
"step": 1453
},
{
"epoch": 3.89,
"learning_rate": 5.8291424435723575e-05,
"loss": 0.0616,
"step": 1454
},
{
"epoch": 3.89,
"learning_rate": 5.8160250564029525e-05,
"loss": 0.0591,
"step": 1455
},
{
"epoch": 3.89,
"learning_rate": 5.802916390327459e-05,
"loss": 0.0534,
"step": 1456
},
{
"epoch": 3.9,
"learning_rate": 5.7898164726696226e-05,
"loss": 0.0569,
"step": 1457
},
{
"epoch": 3.9,
"learning_rate": 5.776725330734974e-05,
"loss": 0.0683,
"step": 1458
},
{
"epoch": 3.9,
"learning_rate": 5.7636429918107314e-05,
"loss": 0.0649,
"step": 1459
},
{
"epoch": 3.9,
"learning_rate": 5.750569483165784e-05,
"loss": 0.0606,
"step": 1460
},
{
"epoch": 3.91,
"learning_rate": 5.737504832050594e-05,
"loss": 0.0625,
"step": 1461
},
{
"epoch": 3.91,
"learning_rate": 5.7244490656971815e-05,
"loss": 0.0551,
"step": 1462
},
{
"epoch": 3.91,
"learning_rate": 5.711402211319029e-05,
"loss": 0.0676,
"step": 1463
},
{
"epoch": 3.91,
"learning_rate": 5.698364296111056e-05,
"loss": 0.0667,
"step": 1464
},
{
"epoch": 3.92,
"learning_rate": 5.6853353472495474e-05,
"loss": 0.0491,
"step": 1465
},
{
"epoch": 3.92,
"learning_rate": 5.6723153918920936e-05,
"loss": 0.0545,
"step": 1466
},
{
"epoch": 3.92,
"learning_rate": 5.6593044571775346e-05,
"loss": 0.0605,
"step": 1467
},
{
"epoch": 3.93,
"learning_rate": 5.646302570225919e-05,
"loss": 0.0631,
"step": 1468
},
{
"epoch": 3.93,
"learning_rate": 5.633309758138436e-05,
"loss": 0.0674,
"step": 1469
},
{
"epoch": 3.93,
"learning_rate": 5.6203260479973464e-05,
"loss": 0.0574,
"step": 1470
},
{
"epoch": 3.93,
"learning_rate": 5.6073514668659534e-05,
"loss": 0.056,
"step": 1471
},
{
"epoch": 3.94,
"learning_rate": 5.59438604178852e-05,
"loss": 0.0553,
"step": 1472
},
{
"epoch": 3.94,
"learning_rate": 5.581429799790234e-05,
"loss": 0.0687,
"step": 1473
},
{
"epoch": 3.94,
"learning_rate": 5.568482767877132e-05,
"loss": 0.0631,
"step": 1474
},
{
"epoch": 3.94,
"learning_rate": 5.5555449730360665e-05,
"loss": 0.0634,
"step": 1475
},
{
"epoch": 3.95,
"learning_rate": 5.542616442234618e-05,
"loss": 0.0649,
"step": 1476
},
{
"epoch": 3.95,
"learning_rate": 5.529697202421078e-05,
"loss": 0.0588,
"step": 1477
},
{
"epoch": 3.95,
"learning_rate": 5.51678728052435e-05,
"loss": 0.0612,
"step": 1478
},
{
"epoch": 3.95,
"learning_rate": 5.503886703453933e-05,
"loss": 0.0599,
"step": 1479
},
{
"epoch": 3.96,
"learning_rate": 5.490995498099843e-05,
"loss": 0.0638,
"step": 1480
},
{
"epoch": 3.96,
"learning_rate": 5.4781136913325535e-05,
"loss": 0.059,
"step": 1481
},
{
"epoch": 3.96,
"learning_rate": 5.4652413100029584e-05,
"loss": 0.0712,
"step": 1482
},
{
"epoch": 3.97,
"learning_rate": 5.452378380942296e-05,
"loss": 0.0577,
"step": 1483
},
{
"epoch": 3.97,
"learning_rate": 5.43952493096211e-05,
"loss": 0.0776,
"step": 1484
},
{
"epoch": 3.97,
"learning_rate": 5.426680986854178e-05,
"loss": 0.0603,
"step": 1485
},
{
"epoch": 3.97,
"learning_rate": 5.413846575390473e-05,
"loss": 0.0525,
"step": 1486
},
{
"epoch": 3.98,
"learning_rate": 5.4010217233230874e-05,
"loss": 0.0636,
"step": 1487
},
{
"epoch": 3.98,
"learning_rate": 5.388206457384197e-05,
"loss": 0.0484,
"step": 1488
},
{
"epoch": 3.98,
"learning_rate": 5.375400804285995e-05,
"loss": 0.064,
"step": 1489
},
{
"epoch": 3.98,
"learning_rate": 5.362604790720634e-05,
"loss": 0.061,
"step": 1490
},
{
"epoch": 3.99,
"learning_rate": 5.3498184433601694e-05,
"loss": 0.0662,
"step": 1491
},
{
"epoch": 3.99,
"learning_rate": 5.337041788856518e-05,
"loss": 0.0764,
"step": 1492
},
{
"epoch": 3.99,
"learning_rate": 5.3242748538413954e-05,
"loss": 0.0699,
"step": 1493
},
{
"epoch": 3.99,
"learning_rate": 5.311517664926245e-05,
"loss": 0.0584,
"step": 1494
},
{
"epoch": 4.0,
"learning_rate": 5.298770248702198e-05,
"loss": 0.0604,
"step": 1495
},
{
"epoch": 4.0,
"learning_rate": 5.286032631740023e-05,
"loss": 0.0424,
"step": 1496
},
{
"epoch": 4.0,
"learning_rate": 5.273304840590065e-05,
"loss": 0.0239,
"step": 1497
},
{
"epoch": 4.01,
"learning_rate": 5.260586901782172e-05,
"loss": 0.0195,
"step": 1498
},
{
"epoch": 4.01,
"learning_rate": 5.2478788418256755e-05,
"loss": 0.0232,
"step": 1499
},
{
"epoch": 4.01,
"learning_rate": 5.235180687209296e-05,
"loss": 0.0218,
"step": 1500
},
{
"epoch": 4.01,
"learning_rate": 5.222492464401123e-05,
"loss": 0.0228,
"step": 1501
},
{
"epoch": 4.02,
"learning_rate": 5.2098141998485414e-05,
"loss": 0.0195,
"step": 1502
},
{
"epoch": 4.02,
"learning_rate": 5.197145919978172e-05,
"loss": 0.0231,
"step": 1503
},
{
"epoch": 4.02,
"learning_rate": 5.184487651195825e-05,
"loss": 0.0207,
"step": 1504
},
{
"epoch": 4.02,
"learning_rate": 5.1718394198864484e-05,
"loss": 0.0195,
"step": 1505
},
{
"epoch": 4.03,
"learning_rate": 5.159201252414068e-05,
"loss": 0.0207,
"step": 1506
},
{
"epoch": 4.03,
"learning_rate": 5.146573175121728e-05,
"loss": 0.0213,
"step": 1507
},
{
"epoch": 4.03,
"learning_rate": 5.1339552143314384e-05,
"loss": 0.0173,
"step": 1508
},
{
"epoch": 4.03,
"learning_rate": 5.1213473963441315e-05,
"loss": 0.0215,
"step": 1509
},
{
"epoch": 4.04,
"learning_rate": 5.1087497474395907e-05,
"loss": 0.0221,
"step": 1510
},
{
"epoch": 4.04,
"learning_rate": 5.096162293876414e-05,
"loss": 0.0203,
"step": 1511
},
{
"epoch": 4.04,
"learning_rate": 5.0835850618919245e-05,
"loss": 0.0231,
"step": 1512
},
{
"epoch": 4.05,
"learning_rate": 5.071018077702161e-05,
"loss": 0.0215,
"step": 1513
},
{
"epoch": 4.05,
"learning_rate": 5.058461367501794e-05,
"loss": 0.0201,
"step": 1514
},
{
"epoch": 4.05,
"learning_rate": 5.045914957464086e-05,
"loss": 0.0164,
"step": 1515
},
{
"epoch": 4.05,
"learning_rate": 5.033378873740819e-05,
"loss": 0.0198,
"step": 1516
},
{
"epoch": 4.06,
"learning_rate": 5.0208531424622526e-05,
"loss": 0.0223,
"step": 1517
},
{
"epoch": 4.06,
"learning_rate": 5.008337789737073e-05,
"loss": 0.0191,
"step": 1518
},
{
"epoch": 4.06,
"learning_rate": 4.9958328416523304e-05,
"loss": 0.0191,
"step": 1519
},
{
"epoch": 4.06,
"learning_rate": 4.9833383242733964e-05,
"loss": 0.019,
"step": 1520
},
{
"epoch": 4.07,
"learning_rate": 4.970854263643878e-05,
"loss": 0.0235,
"step": 1521
},
{
"epoch": 4.07,
"learning_rate": 4.958380685785608e-05,
"loss": 0.0169,
"step": 1522
},
{
"epoch": 4.07,
"learning_rate": 4.945917616698559e-05,
"loss": 0.0182,
"step": 1523
},
{
"epoch": 4.07,
"learning_rate": 4.933465082360807e-05,
"loss": 0.0198,
"step": 1524
},
{
"epoch": 4.08,
"learning_rate": 4.921023108728461e-05,
"loss": 0.0174,
"step": 1525
},
{
"epoch": 4.08,
"learning_rate": 4.9085917217356146e-05,
"loss": 0.0175,
"step": 1526
},
{
"epoch": 4.08,
"learning_rate": 4.896170947294304e-05,
"loss": 0.0198,
"step": 1527
},
{
"epoch": 4.09,
"learning_rate": 4.8837608112944454e-05,
"loss": 0.0206,
"step": 1528
},
{
"epoch": 4.09,
"learning_rate": 4.8713613396037704e-05,
"loss": 0.0184,
"step": 1529
},
{
"epoch": 4.09,
"learning_rate": 4.8589725580677835e-05,
"loss": 0.0208,
"step": 1530
},
{
"epoch": 4.09,
"learning_rate": 4.846594492509714e-05,
"loss": 0.0191,
"step": 1531
},
{
"epoch": 4.1,
"learning_rate": 4.834227168730451e-05,
"loss": 0.0155,
"step": 1532
},
{
"epoch": 4.1,
"learning_rate": 4.821870612508494e-05,
"loss": 0.0168,
"step": 1533
},
{
"epoch": 4.1,
"learning_rate": 4.809524849599897e-05,
"loss": 0.0189,
"step": 1534
},
{
"epoch": 4.1,
"learning_rate": 4.7971899057382116e-05,
"loss": 0.0176,
"step": 1535
},
{
"epoch": 4.11,
"learning_rate": 4.7848658066344486e-05,
"loss": 0.0189,
"step": 1536
},
{
"epoch": 4.11,
"learning_rate": 4.772552577977012e-05,
"loss": 0.02,
"step": 1537
},
{
"epoch": 4.11,
"learning_rate": 4.7602502454316397e-05,
"loss": 0.0229,
"step": 1538
},
{
"epoch": 4.11,
"learning_rate": 4.7479588346413605e-05,
"loss": 0.0297,
"step": 1539
},
{
"epoch": 4.12,
"learning_rate": 4.735678371226441e-05,
"loss": 0.0211,
"step": 1540
},
{
"epoch": 4.12,
"learning_rate": 4.723408880784334e-05,
"loss": 0.0204,
"step": 1541
},
{
"epoch": 4.12,
"learning_rate": 4.7111503888896066e-05,
"loss": 0.0187,
"step": 1542
},
{
"epoch": 4.13,
"learning_rate": 4.6989029210939074e-05,
"loss": 0.0154,
"step": 1543
},
{
"epoch": 4.13,
"learning_rate": 4.686666502925908e-05,
"loss": 0.0213,
"step": 1544
},
{
"epoch": 4.13,
"learning_rate": 4.674441159891252e-05,
"loss": 0.0182,
"step": 1545
},
{
"epoch": 4.13,
"learning_rate": 4.6622269174724856e-05,
"loss": 0.0168,
"step": 1546
},
{
"epoch": 4.14,
"learning_rate": 4.6500238011290295e-05,
"loss": 0.0191,
"step": 1547
},
{
"epoch": 4.14,
"learning_rate": 4.637831836297103e-05,
"loss": 0.0171,
"step": 1548
},
{
"epoch": 4.14,
"learning_rate": 4.6256510483896866e-05,
"loss": 0.0181,
"step": 1549
},
{
"epoch": 4.14,
"learning_rate": 4.613481462796468e-05,
"loss": 0.0171,
"step": 1550
},
{
"epoch": 4.15,
"learning_rate": 4.601323104883776e-05,
"loss": 0.0193,
"step": 1551
},
{
"epoch": 4.15,
"learning_rate": 4.5891759999945347e-05,
"loss": 0.0168,
"step": 1552
},
{
"epoch": 4.15,
"learning_rate": 4.577040173448224e-05,
"loss": 0.0198,
"step": 1553
},
{
"epoch": 4.16,
"learning_rate": 4.564915650540808e-05,
"loss": 0.0185,
"step": 1554
},
{
"epoch": 4.16,
"learning_rate": 4.552802456544688e-05,
"loss": 0.016,
"step": 1555
},
{
"epoch": 4.16,
"learning_rate": 4.540700616708658e-05,
"loss": 0.019,
"step": 1556
},
{
"epoch": 4.16,
"learning_rate": 4.528610156257832e-05,
"loss": 0.0269,
"step": 1557
},
{
"epoch": 4.17,
"learning_rate": 4.516531100393624e-05,
"loss": 0.0173,
"step": 1558
},
{
"epoch": 4.17,
"learning_rate": 4.504463474293657e-05,
"loss": 0.0191,
"step": 1559
},
{
"epoch": 4.17,
"learning_rate": 4.4924073031117455e-05,
"loss": 0.0166,
"step": 1560
},
{
"epoch": 4.17,
"learning_rate": 4.480362611977813e-05,
"loss": 0.0176,
"step": 1561
},
{
"epoch": 4.18,
"learning_rate": 4.4683294259978694e-05,
"loss": 0.0193,
"step": 1562
},
{
"epoch": 4.18,
"learning_rate": 4.456307770253927e-05,
"loss": 0.0176,
"step": 1563
},
{
"epoch": 4.18,
"learning_rate": 4.444297669803981e-05,
"loss": 0.0185,
"step": 1564
},
{
"epoch": 4.18,
"learning_rate": 4.432299149681923e-05,
"loss": 0.0193,
"step": 1565
},
{
"epoch": 4.19,
"learning_rate": 4.420312234897521e-05,
"loss": 0.022,
"step": 1566
},
{
"epoch": 4.19,
"learning_rate": 4.4083369504363526e-05,
"loss": 0.0213,
"step": 1567
},
{
"epoch": 4.19,
"learning_rate": 4.3963733212597366e-05,
"loss": 0.0196,
"step": 1568
},
{
"epoch": 4.2,
"learning_rate": 4.3844213723047204e-05,
"loss": 0.0195,
"step": 1569
},
{
"epoch": 4.2,
"learning_rate": 4.372481128483984e-05,
"loss": 0.0166,
"step": 1570
},
{
"epoch": 4.2,
"learning_rate": 4.360552614685825e-05,
"loss": 0.0218,
"step": 1571
},
{
"epoch": 4.2,
"learning_rate": 4.3486358557740814e-05,
"loss": 0.0207,
"step": 1572
},
{
"epoch": 4.21,
"learning_rate": 4.3367308765880966e-05,
"loss": 0.0271,
"step": 1573
},
{
"epoch": 4.21,
"learning_rate": 4.32483770194265e-05,
"loss": 0.0211,
"step": 1574
},
{
"epoch": 4.21,
"learning_rate": 4.312956356627928e-05,
"loss": 0.0198,
"step": 1575
},
{
"epoch": 4.21,
"learning_rate": 4.301086865409449e-05,
"loss": 0.0186,
"step": 1576
},
{
"epoch": 4.22,
"learning_rate": 4.289229253028029e-05,
"loss": 0.0201,
"step": 1577
},
{
"epoch": 4.22,
"learning_rate": 4.277383544199726e-05,
"loss": 0.0195,
"step": 1578
},
{
"epoch": 4.22,
"learning_rate": 4.265549763615779e-05,
"loss": 0.0213,
"step": 1579
},
{
"epoch": 4.22,
"learning_rate": 4.253727935942563e-05,
"loss": 0.0187,
"step": 1580
},
{
"epoch": 4.23,
"learning_rate": 4.241918085821547e-05,
"loss": 0.0179,
"step": 1581
},
{
"epoch": 4.23,
"learning_rate": 4.2301202378692316e-05,
"loss": 0.0158,
"step": 1582
},
{
"epoch": 4.23,
"learning_rate": 4.218334416677091e-05,
"loss": 0.0166,
"step": 1583
},
{
"epoch": 4.24,
"learning_rate": 4.206560646811545e-05,
"loss": 0.0173,
"step": 1584
},
{
"epoch": 4.24,
"learning_rate": 4.1947989528138773e-05,
"loss": 0.0171,
"step": 1585
},
{
"epoch": 4.24,
"learning_rate": 4.183049359200215e-05,
"loss": 0.0183,
"step": 1586
},
{
"epoch": 4.24,
"learning_rate": 4.1713118904614614e-05,
"loss": 0.0191,
"step": 1587
},
{
"epoch": 4.25,
"learning_rate": 4.159586571063236e-05,
"loss": 0.0177,
"step": 1588
},
{
"epoch": 4.25,
"learning_rate": 4.1478734254458394e-05,
"loss": 0.016,
"step": 1589
},
{
"epoch": 4.25,
"learning_rate": 4.136172478024203e-05,
"loss": 0.0222,
"step": 1590
},
{
"epoch": 4.25,
"learning_rate": 4.124483753187831e-05,
"loss": 0.016,
"step": 1591
},
{
"epoch": 4.26,
"learning_rate": 4.112807275300742e-05,
"loss": 0.0166,
"step": 1592
},
{
"epoch": 4.26,
"learning_rate": 4.1011430687014316e-05,
"loss": 0.0178,
"step": 1593
},
{
"epoch": 4.26,
"learning_rate": 4.08949115770282e-05,
"loss": 0.0165,
"step": 1594
},
{
"epoch": 4.26,
"learning_rate": 4.077851566592201e-05,
"loss": 0.0199,
"step": 1595
},
{
"epoch": 4.27,
"learning_rate": 4.0662243196311815e-05,
"loss": 0.018,
"step": 1596
},
{
"epoch": 4.27,
"learning_rate": 4.054609441055636e-05,
"loss": 0.0172,
"step": 1597
},
{
"epoch": 4.27,
"learning_rate": 4.0430069550756665e-05,
"loss": 0.0187,
"step": 1598
},
{
"epoch": 4.28,
"learning_rate": 4.031416885875543e-05,
"loss": 0.0173,
"step": 1599
},
{
"epoch": 4.28,
"learning_rate": 4.0198392576136526e-05,
"loss": 0.0172,
"step": 1600
},
{
"epoch": 4.28,
"learning_rate": 4.008274094422447e-05,
"loss": 0.018,
"step": 1601
},
{
"epoch": 4.28,
"learning_rate": 3.9967214204083946e-05,
"loss": 0.0177,
"step": 1602
},
{
"epoch": 4.29,
"learning_rate": 3.985181259651938e-05,
"loss": 0.0174,
"step": 1603
},
{
"epoch": 4.29,
"learning_rate": 3.973653636207437e-05,
"loss": 0.0157,
"step": 1604
},
{
"epoch": 4.29,
"learning_rate": 3.9621385741031137e-05,
"loss": 0.0179,
"step": 1605
},
{
"epoch": 4.29,
"learning_rate": 3.950636097341003e-05,
"loss": 0.0189,
"step": 1606
},
{
"epoch": 4.3,
"learning_rate": 3.939146229896918e-05,
"loss": 0.0201,
"step": 1607
},
{
"epoch": 4.3,
"learning_rate": 3.927668995720384e-05,
"loss": 0.0177,
"step": 1608
},
{
"epoch": 4.3,
"learning_rate": 3.916204418734599e-05,
"loss": 0.0166,
"step": 1609
},
{
"epoch": 4.3,
"learning_rate": 3.90475252283636e-05,
"loss": 0.0161,
"step": 1610
},
{
"epoch": 4.31,
"learning_rate": 3.8933133318960514e-05,
"loss": 0.0165,
"step": 1611
},
{
"epoch": 4.31,
"learning_rate": 3.881886869757565e-05,
"loss": 0.0171,
"step": 1612
},
{
"epoch": 4.31,
"learning_rate": 3.870473160238271e-05,
"loss": 0.0181,
"step": 1613
},
{
"epoch": 4.32,
"learning_rate": 3.859072227128945e-05,
"loss": 0.024,
"step": 1614
},
{
"epoch": 4.32,
"learning_rate": 3.847684094193733e-05,
"loss": 0.0189,
"step": 1615
},
{
"epoch": 4.32,
"learning_rate": 3.8363087851701085e-05,
"loss": 0.0219,
"step": 1616
},
{
"epoch": 4.32,
"learning_rate": 3.824946323768811e-05,
"loss": 0.0146,
"step": 1617
},
{
"epoch": 4.33,
"learning_rate": 3.8135967336738075e-05,
"loss": 0.0182,
"step": 1618
},
{
"epoch": 4.33,
"learning_rate": 3.8022600385422126e-05,
"loss": 0.0174,
"step": 1619
},
{
"epoch": 4.33,
"learning_rate": 3.7909362620042865e-05,
"loss": 0.017,
"step": 1620
},
{
"epoch": 4.33,
"learning_rate": 3.7796254276633544e-05,
"loss": 0.0157,
"step": 1621
},
{
"epoch": 4.34,
"learning_rate": 3.7683275590957666e-05,
"loss": 0.0178,
"step": 1622
},
{
"epoch": 4.34,
"learning_rate": 3.7570426798508415e-05,
"loss": 0.0177,
"step": 1623
},
{
"epoch": 4.34,
"learning_rate": 3.745770813450824e-05,
"loss": 0.0204,
"step": 1624
},
{
"epoch": 4.34,
"learning_rate": 3.734511983390838e-05,
"loss": 0.016,
"step": 1625
},
{
"epoch": 4.35,
"learning_rate": 3.7232662131388386e-05,
"loss": 0.0146,
"step": 1626
},
{
"epoch": 4.35,
"learning_rate": 3.71203352613555e-05,
"loss": 0.0188,
"step": 1627
},
{
"epoch": 4.35,
"learning_rate": 3.7008139457944245e-05,
"loss": 0.0163,
"step": 1628
},
{
"epoch": 4.36,
"learning_rate": 3.689607495501606e-05,
"loss": 0.0158,
"step": 1629
},
{
"epoch": 4.36,
"learning_rate": 3.678414198615865e-05,
"loss": 0.0178,
"step": 1630
},
{
"epoch": 4.36,
"learning_rate": 3.6672340784685475e-05,
"loss": 0.0203,
"step": 1631
},
{
"epoch": 4.36,
"learning_rate": 3.6560671583635467e-05,
"loss": 0.0193,
"step": 1632
},
{
"epoch": 4.37,
"learning_rate": 3.644913461577229e-05,
"loss": 0.0166,
"step": 1633
},
{
"epoch": 4.37,
"learning_rate": 3.6337730113584053e-05,
"loss": 0.0199,
"step": 1634
},
{
"epoch": 4.37,
"learning_rate": 3.6226458309282806e-05,
"loss": 0.0184,
"step": 1635
},
{
"epoch": 4.37,
"learning_rate": 3.6115319434803894e-05,
"loss": 0.0165,
"step": 1636
},
{
"epoch": 4.38,
"learning_rate": 3.600431372180557e-05,
"loss": 0.019,
"step": 1637
},
{
"epoch": 4.38,
"learning_rate": 3.589344140166865e-05,
"loss": 0.02,
"step": 1638
},
{
"epoch": 4.38,
"learning_rate": 3.5782702705495826e-05,
"loss": 0.0202,
"step": 1639
},
{
"epoch": 4.39,
"learning_rate": 3.5672097864111285e-05,
"loss": 0.0152,
"step": 1640
},
{
"epoch": 4.39,
"learning_rate": 3.5561627108060136e-05,
"loss": 0.0172,
"step": 1641
},
{
"epoch": 4.39,
"learning_rate": 3.54512906676081e-05,
"loss": 0.0176,
"step": 1642
},
{
"epoch": 4.39,
"learning_rate": 3.534108877274093e-05,
"loss": 0.0195,
"step": 1643
},
{
"epoch": 4.4,
"learning_rate": 3.523102165316381e-05,
"loss": 0.0152,
"step": 1644
},
{
"epoch": 4.4,
"learning_rate": 3.5121089538301156e-05,
"loss": 0.0211,
"step": 1645
},
{
"epoch": 4.4,
"learning_rate": 3.5011292657295825e-05,
"loss": 0.0196,
"step": 1646
},
{
"epoch": 4.4,
"learning_rate": 3.490163123900895e-05,
"loss": 0.0201,
"step": 1647
},
{
"epoch": 4.41,
"learning_rate": 3.479210551201915e-05,
"loss": 0.0195,
"step": 1648
},
{
"epoch": 4.41,
"learning_rate": 3.468271570462235e-05,
"loss": 0.0138,
"step": 1649
},
{
"epoch": 4.41,
"learning_rate": 3.457346204483103e-05,
"loss": 0.0207,
"step": 1650
},
{
"epoch": 4.41,
"learning_rate": 3.446434476037399e-05,
"loss": 0.0182,
"step": 1651
},
{
"epoch": 4.42,
"learning_rate": 3.435536407869575e-05,
"loss": 0.0205,
"step": 1652
},
{
"epoch": 4.42,
"learning_rate": 3.424652022695603e-05,
"loss": 0.0182,
"step": 1653
},
{
"epoch": 4.42,
"learning_rate": 3.413781343202942e-05,
"loss": 0.0221,
"step": 1654
},
{
"epoch": 4.43,
"learning_rate": 3.402924392050475e-05,
"loss": 0.0168,
"step": 1655
},
{
"epoch": 4.43,
"learning_rate": 3.3920811918684805e-05,
"loss": 0.0179,
"step": 1656
},
{
"epoch": 4.43,
"learning_rate": 3.38125176525856e-05,
"loss": 0.0157,
"step": 1657
},
{
"epoch": 4.43,
"learning_rate": 3.3704361347936187e-05,
"loss": 0.0179,
"step": 1658
},
{
"epoch": 4.44,
"learning_rate": 3.359634323017795e-05,
"loss": 0.0212,
"step": 1659
},
{
"epoch": 4.44,
"learning_rate": 3.348846352446435e-05,
"loss": 0.0186,
"step": 1660
},
{
"epoch": 4.44,
"learning_rate": 3.33807224556602e-05,
"loss": 0.0172,
"step": 1661
},
{
"epoch": 4.44,
"learning_rate": 3.327312024834143e-05,
"loss": 0.0155,
"step": 1662
},
{
"epoch": 4.45,
"learning_rate": 3.316565712679453e-05,
"loss": 0.021,
"step": 1663
},
{
"epoch": 4.45,
"learning_rate": 3.3058333315016065e-05,
"loss": 0.018,
"step": 1664
},
{
"epoch": 4.45,
"learning_rate": 3.295114903671215e-05,
"loss": 0.0179,
"step": 1665
},
{
"epoch": 4.45,
"learning_rate": 3.2844104515298155e-05,
"loss": 0.0186,
"step": 1666
},
{
"epoch": 4.46,
"learning_rate": 3.273719997389813e-05,
"loss": 0.0196,
"step": 1667
},
{
"epoch": 4.46,
"learning_rate": 3.263043563534428e-05,
"loss": 0.0168,
"step": 1668
},
{
"epoch": 4.46,
"learning_rate": 3.252381172217666e-05,
"loss": 0.0191,
"step": 1669
},
{
"epoch": 4.47,
"learning_rate": 3.2417328456642504e-05,
"loss": 0.0169,
"step": 1670
},
{
"epoch": 4.47,
"learning_rate": 3.2310986060696034e-05,
"loss": 0.0292,
"step": 1671
},
{
"epoch": 4.47,
"learning_rate": 3.22047847559977e-05,
"loss": 0.0169,
"step": 1672
},
{
"epoch": 4.47,
"learning_rate": 3.2098724763913954e-05,
"loss": 0.0168,
"step": 1673
},
{
"epoch": 4.48,
"learning_rate": 3.199280630551663e-05,
"loss": 0.0165,
"step": 1674
},
{
"epoch": 4.48,
"learning_rate": 3.188702960158261e-05,
"loss": 0.0211,
"step": 1675
},
{
"epoch": 4.48,
"learning_rate": 3.1781394872593295e-05,
"loss": 0.0197,
"step": 1676
},
{
"epoch": 4.48,
"learning_rate": 3.16759023387341e-05,
"loss": 0.0182,
"step": 1677
},
{
"epoch": 4.49,
"learning_rate": 3.157055221989406e-05,
"loss": 0.0166,
"step": 1678
},
{
"epoch": 4.49,
"learning_rate": 3.146534473566539e-05,
"loss": 0.0161,
"step": 1679
},
{
"epoch": 4.49,
"learning_rate": 3.136028010534303e-05,
"loss": 0.0165,
"step": 1680
},
{
"epoch": 4.49,
"learning_rate": 3.125535854792408e-05,
"loss": 0.0158,
"step": 1681
},
{
"epoch": 4.5,
"learning_rate": 3.1150580282107425e-05,
"loss": 0.021,
"step": 1682
},
{
"epoch": 4.5,
"learning_rate": 3.104594552629331e-05,
"loss": 0.0194,
"step": 1683
},
{
"epoch": 4.5,
"learning_rate": 3.094145449858285e-05,
"loss": 0.0222,
"step": 1684
},
{
"epoch": 4.51,
"learning_rate": 3.083710741677756e-05,
"loss": 0.0188,
"step": 1685
},
{
"epoch": 4.51,
"learning_rate": 3.073290449837892e-05,
"loss": 0.0191,
"step": 1686
},
{
"epoch": 4.51,
"learning_rate": 3.0628845960587835e-05,
"loss": 0.0172,
"step": 1687
},
{
"epoch": 4.51,
"learning_rate": 3.05249320203044e-05,
"loss": 0.0176,
"step": 1688
},
{
"epoch": 4.52,
"learning_rate": 3.0421162894127243e-05,
"loss": 0.0182,
"step": 1689
},
{
"epoch": 4.52,
"learning_rate": 3.0317538798353116e-05,
"loss": 0.0166,
"step": 1690
},
{
"epoch": 4.52,
"learning_rate": 3.021405994897647e-05,
"loss": 0.0184,
"step": 1691
},
{
"epoch": 4.52,
"learning_rate": 3.0110726561689063e-05,
"loss": 0.0188,
"step": 1692
},
{
"epoch": 4.53,
"learning_rate": 3.0007538851879437e-05,
"loss": 0.0176,
"step": 1693
},
{
"epoch": 4.53,
"learning_rate": 2.990449703463243e-05,
"loss": 0.0193,
"step": 1694
},
{
"epoch": 4.53,
"learning_rate": 2.980160132472879e-05,
"loss": 0.0167,
"step": 1695
},
{
"epoch": 4.53,
"learning_rate": 2.9698851936644768e-05,
"loss": 0.0164,
"step": 1696
},
{
"epoch": 4.54,
"learning_rate": 2.9596249084551585e-05,
"loss": 0.0157,
"step": 1697
},
{
"epoch": 4.54,
"learning_rate": 2.9493792982315083e-05,
"loss": 0.0215,
"step": 1698
},
{
"epoch": 4.54,
"learning_rate": 2.9391483843495126e-05,
"loss": 0.0169,
"step": 1699
},
{
"epoch": 4.55,
"learning_rate": 2.9289321881345254e-05,
"loss": 0.0166,
"step": 1700
},
{
"epoch": 4.55,
"learning_rate": 2.9187307308812295e-05,
"loss": 0.0152,
"step": 1701
},
{
"epoch": 4.55,
"learning_rate": 2.9085440338535864e-05,
"loss": 0.0206,
"step": 1702
},
{
"epoch": 4.55,
"learning_rate": 2.8983721182847833e-05,
"loss": 0.0222,
"step": 1703
},
{
"epoch": 4.56,
"learning_rate": 2.8882150053771995e-05,
"loss": 0.0216,
"step": 1704
},
{
"epoch": 4.56,
"learning_rate": 2.8780727163023635e-05,
"loss": 0.0152,
"step": 1705
},
{
"epoch": 4.56,
"learning_rate": 2.867945272200904e-05,
"loss": 0.0189,
"step": 1706
},
{
"epoch": 4.56,
"learning_rate": 2.8578326941825073e-05,
"loss": 0.0184,
"step": 1707
},
{
"epoch": 4.57,
"learning_rate": 2.8477350033258677e-05,
"loss": 0.0152,
"step": 1708
},
{
"epoch": 4.57,
"learning_rate": 2.8376522206786494e-05,
"loss": 0.0162,
"step": 1709
},
{
"epoch": 4.57,
"learning_rate": 2.8275843672574476e-05,
"loss": 0.0173,
"step": 1710
},
{
"epoch": 4.57,
"learning_rate": 2.817531464047739e-05,
"loss": 0.0211,
"step": 1711
},
{
"epoch": 4.58,
"learning_rate": 2.8074935320038308e-05,
"loss": 0.0154,
"step": 1712
},
{
"epoch": 4.58,
"learning_rate": 2.7974705920488263e-05,
"loss": 0.0168,
"step": 1713
},
{
"epoch": 4.58,
"learning_rate": 2.787462665074584e-05,
"loss": 0.0181,
"step": 1714
},
{
"epoch": 4.59,
"learning_rate": 2.7774697719416685e-05,
"loss": 0.0187,
"step": 1715
},
{
"epoch": 4.59,
"learning_rate": 2.7674919334793035e-05,
"loss": 0.0221,
"step": 1716
},
{
"epoch": 4.59,
"learning_rate": 2.7575291704853323e-05,
"loss": 0.0186,
"step": 1717
},
{
"epoch": 4.59,
"learning_rate": 2.74758150372618e-05,
"loss": 0.0179,
"step": 1718
},
{
"epoch": 4.6,
"learning_rate": 2.737648953936801e-05,
"loss": 0.0211,
"step": 1719
},
{
"epoch": 4.6,
"learning_rate": 2.7277315418206473e-05,
"loss": 0.0154,
"step": 1720
},
{
"epoch": 4.6,
"learning_rate": 2.717829288049607e-05,
"loss": 0.0153,
"step": 1721
},
{
"epoch": 4.6,
"learning_rate": 2.7079422132639742e-05,
"loss": 0.0196,
"step": 1722
},
{
"epoch": 4.61,
"learning_rate": 2.6980703380724094e-05,
"loss": 0.0165,
"step": 1723
},
{
"epoch": 4.61,
"learning_rate": 2.688213683051892e-05,
"loss": 0.016,
"step": 1724
},
{
"epoch": 4.61,
"learning_rate": 2.6783722687476696e-05,
"loss": 0.0179,
"step": 1725
},
{
"epoch": 4.61,
"learning_rate": 2.6685461156732216e-05,
"loss": 0.0202,
"step": 1726
},
{
"epoch": 4.62,
"learning_rate": 2.658735244310224e-05,
"loss": 0.0191,
"step": 1727
},
{
"epoch": 4.62,
"learning_rate": 2.6489396751084982e-05,
"loss": 0.0183,
"step": 1728
},
{
"epoch": 4.62,
"learning_rate": 2.6391594284859623e-05,
"loss": 0.0183,
"step": 1729
},
{
"epoch": 4.63,
"learning_rate": 2.6293945248286044e-05,
"loss": 0.0164,
"step": 1730
},
{
"epoch": 4.63,
"learning_rate": 2.6196449844904258e-05,
"loss": 0.0208,
"step": 1731
},
{
"epoch": 4.63,
"learning_rate": 2.6099108277934103e-05,
"loss": 0.0168,
"step": 1732
},
{
"epoch": 4.63,
"learning_rate": 2.6001920750274677e-05,
"loss": 0.0195,
"step": 1733
},
{
"epoch": 4.64,
"learning_rate": 2.5904887464504114e-05,
"loss": 0.0177,
"step": 1734
},
{
"epoch": 4.64,
"learning_rate": 2.5808008622878898e-05,
"loss": 0.0145,
"step": 1735
},
{
"epoch": 4.64,
"learning_rate": 2.5711284427333714e-05,
"loss": 0.0145,
"step": 1736
},
{
"epoch": 4.64,
"learning_rate": 2.5614715079480888e-05,
"loss": 0.0198,
"step": 1737
},
{
"epoch": 4.65,
"learning_rate": 2.5518300780609904e-05,
"loss": 0.0227,
"step": 1738
},
{
"epoch": 4.65,
"learning_rate": 2.5422041731687108e-05,
"loss": 0.0193,
"step": 1739
},
{
"epoch": 4.65,
"learning_rate": 2.5325938133355242e-05,
"loss": 0.0179,
"step": 1740
},
{
"epoch": 4.66,
"learning_rate": 2.5229990185933073e-05,
"loss": 0.0164,
"step": 1741
},
{
"epoch": 4.66,
"learning_rate": 2.513419808941482e-05,
"loss": 0.0193,
"step": 1742
},
{
"epoch": 4.66,
"learning_rate": 2.5038562043469948e-05,
"loss": 0.0196,
"step": 1743
},
{
"epoch": 4.66,
"learning_rate": 2.4943082247442585e-05,
"loss": 0.0172,
"step": 1744
},
{
"epoch": 4.67,
"learning_rate": 2.4847758900351226e-05,
"loss": 0.0188,
"step": 1745
},
{
"epoch": 4.67,
"learning_rate": 2.475259220088818e-05,
"loss": 0.0181,
"step": 1746
},
{
"epoch": 4.67,
"learning_rate": 2.4657582347419362e-05,
"loss": 0.0156,
"step": 1747
},
{
"epoch": 4.67,
"learning_rate": 2.456272953798361e-05,
"loss": 0.0158,
"step": 1748
},
{
"epoch": 4.68,
"learning_rate": 2.446803397029257e-05,
"loss": 0.0184,
"step": 1749
},
{
"epoch": 4.68,
"learning_rate": 2.437349584172999e-05,
"loss": 0.0167,
"step": 1750
},
{
"epoch": 4.68,
"learning_rate": 2.4279115349351543e-05,
"loss": 0.0172,
"step": 1751
},
{
"epoch": 4.68,
"learning_rate": 2.418489268988433e-05,
"loss": 0.0159,
"step": 1752
},
{
"epoch": 4.69,
"learning_rate": 2.409082805972639e-05,
"loss": 0.018,
"step": 1753
},
{
"epoch": 4.69,
"learning_rate": 2.399692165494646e-05,
"loss": 0.0205,
"step": 1754
},
{
"epoch": 4.69,
"learning_rate": 2.3903173671283363e-05,
"loss": 0.0158,
"step": 1755
},
{
"epoch": 4.7,
"learning_rate": 2.3809584304145827e-05,
"loss": 0.0148,
"step": 1756
},
{
"epoch": 4.7,
"learning_rate": 2.3716153748611835e-05,
"loss": 0.0194,
"step": 1757
},
{
"epoch": 4.7,
"learning_rate": 2.3622882199428464e-05,
"loss": 0.0192,
"step": 1758
},
{
"epoch": 4.7,
"learning_rate": 2.3529769851011252e-05,
"loss": 0.0169,
"step": 1759
},
{
"epoch": 4.71,
"learning_rate": 2.343681689744396e-05,
"loss": 0.0154,
"step": 1760
},
{
"epoch": 4.71,
"learning_rate": 2.3344023532478133e-05,
"loss": 0.0171,
"step": 1761
},
{
"epoch": 4.71,
"learning_rate": 2.32513899495326e-05,
"loss": 0.0185,
"step": 1762
},
{
"epoch": 4.71,
"learning_rate": 2.3158916341693128e-05,
"loss": 0.0197,
"step": 1763
},
{
"epoch": 4.72,
"learning_rate": 2.3066602901712108e-05,
"loss": 0.0177,
"step": 1764
},
{
"epoch": 4.72,
"learning_rate": 2.297444982200806e-05,
"loss": 0.0167,
"step": 1765
},
{
"epoch": 4.72,
"learning_rate": 2.2882457294665204e-05,
"loss": 0.015,
"step": 1766
},
{
"epoch": 4.72,
"learning_rate": 2.2790625511433096e-05,
"loss": 0.0173,
"step": 1767
},
{
"epoch": 4.73,
"learning_rate": 2.26989546637263e-05,
"loss": 0.0156,
"step": 1768
},
{
"epoch": 4.73,
"learning_rate": 2.2607444942623922e-05,
"loss": 0.0181,
"step": 1769
},
{
"epoch": 4.73,
"learning_rate": 2.2516096538869136e-05,
"loss": 0.0149,
"step": 1770
},
{
"epoch": 4.74,
"learning_rate": 2.242490964286895e-05,
"loss": 0.0162,
"step": 1771
},
{
"epoch": 4.74,
"learning_rate": 2.2333884444693652e-05,
"loss": 0.0185,
"step": 1772
},
{
"epoch": 4.74,
"learning_rate": 2.224302113407656e-05,
"loss": 0.0148,
"step": 1773
},
{
"epoch": 4.74,
"learning_rate": 2.215231990041352e-05,
"loss": 0.0207,
"step": 1774
},
{
"epoch": 4.75,
"learning_rate": 2.2061780932762542e-05,
"loss": 0.0179,
"step": 1775
},
{
"epoch": 4.75,
"learning_rate": 2.1971404419843355e-05,
"loss": 0.0154,
"step": 1776
},
{
"epoch": 4.75,
"learning_rate": 2.1881190550037167e-05,
"loss": 0.0149,
"step": 1777
},
{
"epoch": 4.75,
"learning_rate": 2.179113951138615e-05,
"loss": 0.0191,
"step": 1778
},
{
"epoch": 4.76,
"learning_rate": 2.1701251491593e-05,
"loss": 0.0175,
"step": 1779
},
{
"epoch": 4.76,
"learning_rate": 2.1611526678020654e-05,
"loss": 0.017,
"step": 1780
},
{
"epoch": 4.76,
"learning_rate": 2.1521965257691877e-05,
"loss": 0.0178,
"step": 1781
},
{
"epoch": 4.76,
"learning_rate": 2.1432567417288862e-05,
"loss": 0.016,
"step": 1782
},
{
"epoch": 4.77,
"learning_rate": 2.134333334315287e-05,
"loss": 0.0134,
"step": 1783
},
{
"epoch": 4.77,
"learning_rate": 2.1254263221283654e-05,
"loss": 0.0194,
"step": 1784
},
{
"epoch": 4.77,
"learning_rate": 2.116535723733938e-05,
"loss": 0.0198,
"step": 1785
},
{
"epoch": 4.78,
"learning_rate": 2.1076615576636027e-05,
"loss": 0.0224,
"step": 1786
},
{
"epoch": 4.78,
"learning_rate": 2.0988038424147093e-05,
"loss": 0.0147,
"step": 1787
},
{
"epoch": 4.78,
"learning_rate": 2.0899625964503113e-05,
"loss": 0.0196,
"step": 1788
},
{
"epoch": 4.78,
"learning_rate": 2.0811378381991353e-05,
"loss": 0.0204,
"step": 1789
},
{
"epoch": 4.79,
"learning_rate": 2.0723295860555437e-05,
"loss": 0.0168,
"step": 1790
},
{
"epoch": 4.79,
"learning_rate": 2.063537858379493e-05,
"loss": 0.0206,
"step": 1791
},
{
"epoch": 4.79,
"learning_rate": 2.0547626734964997e-05,
"loss": 0.0154,
"step": 1792
},
{
"epoch": 4.79,
"learning_rate": 2.046004049697584e-05,
"loss": 0.0156,
"step": 1793
},
{
"epoch": 4.8,
"learning_rate": 2.03726200523926e-05,
"loss": 0.0154,
"step": 1794
},
{
"epoch": 4.8,
"learning_rate": 2.028536558343481e-05,
"loss": 0.0179,
"step": 1795
},
{
"epoch": 4.8,
"learning_rate": 2.0198277271976052e-05,
"loss": 0.0154,
"step": 1796
},
{
"epoch": 4.8,
"learning_rate": 2.011135529954352e-05,
"loss": 0.0191,
"step": 1797
},
{
"epoch": 4.81,
"learning_rate": 2.0024599847317695e-05,
"loss": 0.0154,
"step": 1798
},
{
"epoch": 4.81,
"learning_rate": 1.9938011096131993e-05,
"loss": 0.0151,
"step": 1799
},
{
"epoch": 4.81,
"learning_rate": 1.98515892264724e-05,
"loss": 0.0209,
"step": 1800
},
{
"epoch": 4.82,
"learning_rate": 1.9765334418476965e-05,
"loss": 0.0205,
"step": 1801
},
{
"epoch": 4.82,
"learning_rate": 1.967924685193552e-05,
"loss": 0.0172,
"step": 1802
},
{
"epoch": 4.82,
"learning_rate": 1.9593326706289362e-05,
"loss": 0.0172,
"step": 1803
},
{
"epoch": 4.82,
"learning_rate": 1.950757416063077e-05,
"loss": 0.0209,
"step": 1804
},
{
"epoch": 4.83,
"learning_rate": 1.9421989393702745e-05,
"loss": 0.0199,
"step": 1805
},
{
"epoch": 4.83,
"learning_rate": 1.933657258389845e-05,
"loss": 0.0157,
"step": 1806
},
{
"epoch": 4.83,
"learning_rate": 1.9251323909261022e-05,
"loss": 0.0185,
"step": 1807
},
{
"epoch": 4.83,
"learning_rate": 1.916624354748314e-05,
"loss": 0.017,
"step": 1808
},
{
"epoch": 4.84,
"learning_rate": 1.908133167590669e-05,
"loss": 0.0156,
"step": 1809
},
{
"epoch": 4.84,
"learning_rate": 1.899658847152228e-05,
"loss": 0.023,
"step": 1810
},
{
"epoch": 4.84,
"learning_rate": 1.8912014110968956e-05,
"loss": 0.019,
"step": 1811
},
{
"epoch": 4.84,
"learning_rate": 1.882760877053388e-05,
"loss": 0.0186,
"step": 1812
},
{
"epoch": 4.85,
"learning_rate": 1.874337262615189e-05,
"loss": 0.017,
"step": 1813
},
{
"epoch": 4.85,
"learning_rate": 1.8659305853405118e-05,
"loss": 0.0148,
"step": 1814
},
{
"epoch": 4.85,
"learning_rate": 1.857540862752265e-05,
"loss": 0.0162,
"step": 1815
},
{
"epoch": 4.86,
"learning_rate": 1.8491681123380235e-05,
"loss": 0.0203,
"step": 1816
},
{
"epoch": 4.86,
"learning_rate": 1.840812351549982e-05,
"loss": 0.0158,
"step": 1817
},
{
"epoch": 4.86,
"learning_rate": 1.8324735978049168e-05,
"loss": 0.0189,
"step": 1818
},
{
"epoch": 4.86,
"learning_rate": 1.824151868484164e-05,
"loss": 0.0173,
"step": 1819
},
{
"epoch": 4.87,
"learning_rate": 1.8158471809335654e-05,
"loss": 0.0185,
"step": 1820
},
{
"epoch": 4.87,
"learning_rate": 1.807559552463446e-05,
"loss": 0.0151,
"step": 1821
},
{
"epoch": 4.87,
"learning_rate": 1.799289000348574e-05,
"loss": 0.0144,
"step": 1822
},
{
"epoch": 4.87,
"learning_rate": 1.7910355418281187e-05,
"loss": 0.0198,
"step": 1823
},
{
"epoch": 4.88,
"learning_rate": 1.7827991941056177e-05,
"loss": 0.0202,
"step": 1824
},
{
"epoch": 4.88,
"learning_rate": 1.774579974348951e-05,
"loss": 0.0199,
"step": 1825
},
{
"epoch": 4.88,
"learning_rate": 1.7663778996902947e-05,
"loss": 0.0183,
"step": 1826
},
{
"epoch": 4.89,
"learning_rate": 1.7581929872260805e-05,
"loss": 0.0163,
"step": 1827
},
{
"epoch": 4.89,
"learning_rate": 1.750025254016978e-05,
"loss": 0.0174,
"step": 1828
},
{
"epoch": 4.89,
"learning_rate": 1.741874717087836e-05,
"loss": 0.0198,
"step": 1829
},
{
"epoch": 4.89,
"learning_rate": 1.7337413934276724e-05,
"loss": 0.0188,
"step": 1830
},
{
"epoch": 4.9,
"learning_rate": 1.7256252999896138e-05,
"loss": 0.0163,
"step": 1831
},
{
"epoch": 4.9,
"learning_rate": 1.7175264536908808e-05,
"loss": 0.018,
"step": 1832
},
{
"epoch": 4.9,
"learning_rate": 1.7094448714127387e-05,
"loss": 0.0189,
"step": 1833
},
{
"epoch": 4.9,
"learning_rate": 1.7013805700004714e-05,
"loss": 0.016,
"step": 1834
},
{
"epoch": 4.91,
"learning_rate": 1.693333566263339e-05,
"loss": 0.0169,
"step": 1835
},
{
"epoch": 4.91,
"learning_rate": 1.6853038769745467e-05,
"loss": 0.0204,
"step": 1836
},
{
"epoch": 4.91,
"learning_rate": 1.677291518871216e-05,
"loss": 0.0173,
"step": 1837
},
{
"epoch": 4.91,
"learning_rate": 1.669296508654331e-05,
"loss": 0.0195,
"step": 1838
},
{
"epoch": 4.92,
"learning_rate": 1.661318862988729e-05,
"loss": 0.0168,
"step": 1839
},
{
"epoch": 4.92,
"learning_rate": 1.65335859850304e-05,
"loss": 0.015,
"step": 1840
},
{
"epoch": 4.92,
"learning_rate": 1.645415731789677e-05,
"loss": 0.0183,
"step": 1841
},
{
"epoch": 4.93,
"learning_rate": 1.6374902794047753e-05,
"loss": 0.0196,
"step": 1842
},
{
"epoch": 4.93,
"learning_rate": 1.6295822578681875e-05,
"loss": 0.0196,
"step": 1843
},
{
"epoch": 4.93,
"learning_rate": 1.621691683663418e-05,
"loss": 0.0177,
"step": 1844
},
{
"epoch": 4.93,
"learning_rate": 1.6138185732376145e-05,
"loss": 0.0153,
"step": 1845
},
{
"epoch": 4.94,
"learning_rate": 1.605962943001518e-05,
"loss": 0.0192,
"step": 1846
},
{
"epoch": 4.94,
"learning_rate": 1.5981248093294377e-05,
"loss": 0.0159,
"step": 1847
},
{
"epoch": 4.94,
"learning_rate": 1.590304188559205e-05,
"loss": 0.0194,
"step": 1848
},
{
"epoch": 4.94,
"learning_rate": 1.5825010969921584e-05,
"loss": 0.0233,
"step": 1849
},
{
"epoch": 4.95,
"learning_rate": 1.574715550893091e-05,
"loss": 0.0164,
"step": 1850
},
{
"epoch": 4.95,
"learning_rate": 1.5669475664902267e-05,
"loss": 0.018,
"step": 1851
},
{
"epoch": 4.95,
"learning_rate": 1.55919715997518e-05,
"loss": 0.019,
"step": 1852
},
{
"epoch": 4.95,
"learning_rate": 1.551464347502929e-05,
"loss": 0.0211,
"step": 1853
},
{
"epoch": 4.96,
"learning_rate": 1.543749145191783e-05,
"loss": 0.0163,
"step": 1854
},
{
"epoch": 4.96,
"learning_rate": 1.5360515691233357e-05,
"loss": 0.0168,
"step": 1855
},
{
"epoch": 4.96,
"learning_rate": 1.528371635342448e-05,
"loss": 0.0187,
"step": 1856
},
{
"epoch": 4.97,
"learning_rate": 1.520709359857202e-05,
"loss": 0.0163,
"step": 1857
},
{
"epoch": 4.97,
"learning_rate": 1.5130647586388747e-05,
"loss": 0.0191,
"step": 1858
},
{
"epoch": 4.97,
"learning_rate": 1.5054378476219078e-05,
"loss": 0.0188,
"step": 1859
},
{
"epoch": 4.97,
"learning_rate": 1.4978286427038601e-05,
"loss": 0.0179,
"step": 1860
},
{
"epoch": 4.98,
"learning_rate": 1.4902371597453878e-05,
"loss": 0.0189,
"step": 1861
},
{
"epoch": 4.98,
"learning_rate": 1.48266341457021e-05,
"loss": 0.0159,
"step": 1862
},
{
"epoch": 4.98,
"learning_rate": 1.475107422965073e-05,
"loss": 0.0163,
"step": 1863
},
{
"epoch": 4.98,
"learning_rate": 1.4675692006797137e-05,
"loss": 0.0174,
"step": 1864
},
{
"epoch": 4.99,
"learning_rate": 1.460048763426829e-05,
"loss": 0.0165,
"step": 1865
},
{
"epoch": 4.99,
"learning_rate": 1.4525461268820517e-05,
"loss": 0.0165,
"step": 1866
},
{
"epoch": 4.99,
"learning_rate": 1.4450613066839091e-05,
"loss": 0.0177,
"step": 1867
},
{
"epoch": 4.99,
"learning_rate": 1.437594318433787e-05,
"loss": 0.0174,
"step": 1868
},
{
"epoch": 5.0,
"learning_rate": 1.4301451776959041e-05,
"loss": 0.0177,
"step": 1869
},
{
"epoch": 5.0,
"learning_rate": 1.42271389999728e-05,
"loss": 0.0149,
"step": 1870
},
{
"epoch": 5.0,
"learning_rate": 1.4153005008276988e-05,
"loss": 0.0116,
"step": 1871
},
{
"epoch": 5.01,
"learning_rate": 1.4079049956396828e-05,
"loss": 0.01,
"step": 1872
},
{
"epoch": 5.01,
"learning_rate": 1.4005273998484502e-05,
"loss": 0.012,
"step": 1873
},
{
"epoch": 5.01,
"learning_rate": 1.3931677288318868e-05,
"loss": 0.0104,
"step": 1874
},
{
"epoch": 5.01,
"learning_rate": 1.3858259979305233e-05,
"loss": 0.0106,
"step": 1875
},
{
"epoch": 5.02,
"learning_rate": 1.3785022224474942e-05,
"loss": 0.0101,
"step": 1876
},
{
"epoch": 5.02,
"learning_rate": 1.3711964176485049e-05,
"loss": 0.0109,
"step": 1877
},
{
"epoch": 5.02,
"learning_rate": 1.3639085987618006e-05,
"loss": 0.01,
"step": 1878
},
{
"epoch": 5.02,
"learning_rate": 1.3566387809781423e-05,
"loss": 0.0103,
"step": 1879
},
{
"epoch": 5.03,
"learning_rate": 1.3493869794507663e-05,
"loss": 0.0127,
"step": 1880
},
{
"epoch": 5.03,
"learning_rate": 1.3421532092953625e-05,
"loss": 0.0096,
"step": 1881
},
{
"epoch": 5.03,
"learning_rate": 1.3349374855900198e-05,
"loss": 0.01,
"step": 1882
},
{
"epoch": 5.03,
"learning_rate": 1.327739823375226e-05,
"loss": 0.0093,
"step": 1883
},
{
"epoch": 5.04,
"learning_rate": 1.3205602376538163e-05,
"loss": 0.0085,
"step": 1884
},
{
"epoch": 5.04,
"learning_rate": 1.3133987433909501e-05,
"loss": 0.0102,
"step": 1885
},
{
"epoch": 5.04,
"learning_rate": 1.3062553555140722e-05,
"loss": 0.0095,
"step": 1886
},
{
"epoch": 5.05,
"learning_rate": 1.2991300889128866e-05,
"loss": 0.0119,
"step": 1887
},
{
"epoch": 5.05,
"learning_rate": 1.2920229584393283e-05,
"loss": 0.0122,
"step": 1888
},
{
"epoch": 5.05,
"learning_rate": 1.2849339789075298e-05,
"loss": 0.0087,
"step": 1889
},
{
"epoch": 5.05,
"learning_rate": 1.27786316509379e-05,
"loss": 0.0092,
"step": 1890
},
{
"epoch": 5.06,
"learning_rate": 1.2708105317365349e-05,
"loss": 0.009,
"step": 1891
},
{
"epoch": 5.06,
"learning_rate": 1.2637760935363053e-05,
"loss": 0.0098,
"step": 1892
},
{
"epoch": 5.06,
"learning_rate": 1.25675986515571e-05,
"loss": 0.0104,
"step": 1893
},
{
"epoch": 5.06,
"learning_rate": 1.2497618612194074e-05,
"loss": 0.0082,
"step": 1894
},
{
"epoch": 5.07,
"learning_rate": 1.2427820963140613e-05,
"loss": 0.0097,
"step": 1895
},
{
"epoch": 5.07,
"learning_rate": 1.2358205849883198e-05,
"loss": 0.0105,
"step": 1896
},
{
"epoch": 5.07,
"learning_rate": 1.2288773417527865e-05,
"loss": 0.0088,
"step": 1897
},
{
"epoch": 5.07,
"learning_rate": 1.221952381079986e-05,
"loss": 0.0089,
"step": 1898
},
{
"epoch": 5.08,
"learning_rate": 1.215045717404334e-05,
"loss": 0.0097,
"step": 1899
},
{
"epoch": 5.08,
"learning_rate": 1.2081573651221035e-05,
"loss": 0.0083,
"step": 1900
},
{
"epoch": 5.08,
"learning_rate": 1.201287338591407e-05,
"loss": 0.0093,
"step": 1901
},
{
"epoch": 5.09,
"learning_rate": 1.1944356521321542e-05,
"loss": 0.0102,
"step": 1902
},
{
"epoch": 5.09,
"learning_rate": 1.1876023200260267e-05,
"loss": 0.0104,
"step": 1903
},
{
"epoch": 5.09,
"learning_rate": 1.1807873565164506e-05,
"loss": 0.0099,
"step": 1904
},
{
"epoch": 5.09,
"learning_rate": 1.1739907758085599e-05,
"loss": 0.0096,
"step": 1905
},
{
"epoch": 5.1,
"learning_rate": 1.1672125920691757e-05,
"loss": 0.0104,
"step": 1906
},
{
"epoch": 5.1,
"learning_rate": 1.1604528194267739e-05,
"loss": 0.0108,
"step": 1907
},
{
"epoch": 5.1,
"learning_rate": 1.1537114719714481e-05,
"loss": 0.0091,
"step": 1908
},
{
"epoch": 5.1,
"learning_rate": 1.1469885637548871e-05,
"loss": 0.0096,
"step": 1909
},
{
"epoch": 5.11,
"learning_rate": 1.1402841087903515e-05,
"loss": 0.0101,
"step": 1910
},
{
"epoch": 5.11,
"learning_rate": 1.1335981210526347e-05,
"loss": 0.01,
"step": 1911
},
{
"epoch": 5.11,
"learning_rate": 1.1269306144780333e-05,
"loss": 0.0103,
"step": 1912
},
{
"epoch": 5.11,
"learning_rate": 1.1202816029643237e-05,
"loss": 0.0082,
"step": 1913
},
{
"epoch": 5.12,
"learning_rate": 1.1136511003707329e-05,
"loss": 0.0107,
"step": 1914
},
{
"epoch": 5.12,
"learning_rate": 1.1070391205179087e-05,
"loss": 0.0078,
"step": 1915
},
{
"epoch": 5.12,
"learning_rate": 1.1004456771878835e-05,
"loss": 0.0091,
"step": 1916
},
{
"epoch": 5.13,
"learning_rate": 1.0938707841240614e-05,
"loss": 0.0101,
"step": 1917
},
{
"epoch": 5.13,
"learning_rate": 1.087314455031172e-05,
"loss": 0.0116,
"step": 1918
},
{
"epoch": 5.13,
"learning_rate": 1.080776703575256e-05,
"loss": 0.0114,
"step": 1919
},
{
"epoch": 5.13,
"learning_rate": 1.0742575433836255e-05,
"loss": 0.0099,
"step": 1920
},
{
"epoch": 5.14,
"learning_rate": 1.067756988044848e-05,
"loss": 0.0089,
"step": 1921
},
{
"epoch": 5.14,
"learning_rate": 1.0612750511087022e-05,
"loss": 0.0085,
"step": 1922
},
{
"epoch": 5.14,
"learning_rate": 1.0548117460861651e-05,
"loss": 0.0097,
"step": 1923
},
{
"epoch": 5.14,
"learning_rate": 1.0483670864493778e-05,
"loss": 0.0084,
"step": 1924
},
{
"epoch": 5.15,
"learning_rate": 1.0419410856316093e-05,
"loss": 0.0086,
"step": 1925
},
{
"epoch": 5.15,
"learning_rate": 1.035533757027245e-05,
"loss": 0.0094,
"step": 1926
},
{
"epoch": 5.15,
"learning_rate": 1.029145113991743e-05,
"loss": 0.0091,
"step": 1927
},
{
"epoch": 5.16,
"learning_rate": 1.0227751698416199e-05,
"loss": 0.0095,
"step": 1928
},
{
"epoch": 5.16,
"learning_rate": 1.0164239378544083e-05,
"loss": 0.0116,
"step": 1929
},
{
"epoch": 5.16,
"learning_rate": 1.010091431268645e-05,
"loss": 0.0097,
"step": 1930
},
{
"epoch": 5.16,
"learning_rate": 1.0037776632838281e-05,
"loss": 0.0094,
"step": 1931
},
{
"epoch": 5.17,
"learning_rate": 9.974826470604049e-06,
"loss": 0.0109,
"step": 1932
},
{
"epoch": 5.17,
"learning_rate": 9.91206395719726e-06,
"loss": 0.0099,
"step": 1933
},
{
"epoch": 5.17,
"learning_rate": 9.8494892234404e-06,
"loss": 0.012,
"step": 1934
},
{
"epoch": 5.17,
"learning_rate": 9.787102399764481e-06,
"loss": 0.0106,
"step": 1935
},
{
"epoch": 5.18,
"learning_rate": 9.724903616208836e-06,
"loss": 0.0077,
"step": 1936
},
{
"epoch": 5.18,
"learning_rate": 9.662893002420837e-06,
"loss": 0.012,
"step": 1937
},
{
"epoch": 5.18,
"learning_rate": 9.601070687655667e-06,
"loss": 0.0078,
"step": 1938
},
{
"epoch": 5.18,
"learning_rate": 9.539436800776025e-06,
"loss": 0.0102,
"step": 1939
},
{
"epoch": 5.19,
"learning_rate": 9.477991470251791e-06,
"loss": 0.0099,
"step": 1940
},
{
"epoch": 5.19,
"learning_rate": 9.4167348241599e-06,
"loss": 0.0112,
"step": 1941
},
{
"epoch": 5.19,
"learning_rate": 9.355666990183898e-06,
"loss": 0.0097,
"step": 1942
},
{
"epoch": 5.2,
"learning_rate": 9.29478809561386e-06,
"loss": 0.01,
"step": 1943
},
{
"epoch": 5.2,
"learning_rate": 9.234098267345958e-06,
"loss": 0.0093,
"step": 1944
},
{
"epoch": 5.2,
"learning_rate": 9.173597631882359e-06,
"loss": 0.0093,
"step": 1945
},
{
"epoch": 5.2,
"learning_rate": 9.11328631533076e-06,
"loss": 0.0092,
"step": 1946
},
{
"epoch": 5.21,
"learning_rate": 9.05316444340436e-06,
"loss": 0.0092,
"step": 1947
},
{
"epoch": 5.21,
"learning_rate": 8.993232141421415e-06,
"loss": 0.0104,
"step": 1948
},
{
"epoch": 5.21,
"learning_rate": 8.933489534305051e-06,
"loss": 0.0099,
"step": 1949
},
{
"epoch": 5.21,
"learning_rate": 8.873936746582978e-06,
"loss": 0.0105,
"step": 1950
},
{
"epoch": 5.22,
"learning_rate": 8.81457390238728e-06,
"loss": 0.0099,
"step": 1951
},
{
"epoch": 5.22,
"learning_rate": 8.75540112545411e-06,
"loss": 0.0098,
"step": 1952
},
{
"epoch": 5.22,
"learning_rate": 8.69641853912342e-06,
"loss": 0.0089,
"step": 1953
},
{
"epoch": 5.22,
"learning_rate": 8.637626266338749e-06,
"loss": 0.0105,
"step": 1954
},
{
"epoch": 5.23,
"learning_rate": 8.579024429646932e-06,
"loss": 0.009,
"step": 1955
},
{
"epoch": 5.23,
"learning_rate": 8.520613151197898e-06,
"loss": 0.0097,
"step": 1956
},
{
"epoch": 5.23,
"learning_rate": 8.462392552744347e-06,
"loss": 0.0089,
"step": 1957
},
{
"epoch": 5.24,
"learning_rate": 8.404362755641504e-06,
"loss": 0.0084,
"step": 1958
},
{
"epoch": 5.24,
"learning_rate": 8.346523880846902e-06,
"loss": 0.0088,
"step": 1959
},
{
"epoch": 5.24,
"learning_rate": 8.288876048920124e-06,
"loss": 0.0081,
"step": 1960
},
{
"epoch": 5.24,
"learning_rate": 8.231419380022576e-06,
"loss": 0.0093,
"step": 1961
},
{
"epoch": 5.25,
"learning_rate": 8.174153993917122e-06,
"loss": 0.0096,
"step": 1962
},
{
"epoch": 5.25,
"learning_rate": 8.11708000996797e-06,
"loss": 0.0081,
"step": 1963
},
{
"epoch": 5.25,
"learning_rate": 8.060197547140347e-06,
"loss": 0.0085,
"step": 1964
},
{
"epoch": 5.25,
"learning_rate": 8.003506724000321e-06,
"loss": 0.0091,
"step": 1965
},
{
"epoch": 5.26,
"learning_rate": 7.947007658714444e-06,
"loss": 0.0096,
"step": 1966
},
{
"epoch": 5.26,
"learning_rate": 7.890700469049572e-06,
"loss": 0.0078,
"step": 1967
},
{
"epoch": 5.26,
"learning_rate": 7.834585272372663e-06,
"loss": 0.0078,
"step": 1968
},
{
"epoch": 5.26,
"learning_rate": 7.778662185650432e-06,
"loss": 0.0089,
"step": 1969
},
{
"epoch": 5.27,
"learning_rate": 7.722931325449223e-06,
"loss": 0.0098,
"step": 1970
},
{
"epoch": 5.27,
"learning_rate": 7.667392807934615e-06,
"loss": 0.0112,
"step": 1971
},
{
"epoch": 5.27,
"learning_rate": 7.612046748871327e-06,
"loss": 0.0096,
"step": 1972
},
{
"epoch": 5.28,
"learning_rate": 7.556893263622911e-06,
"loss": 0.0084,
"step": 1973
},
{
"epoch": 5.28,
"learning_rate": 7.5019324671515065e-06,
"loss": 0.0098,
"step": 1974
},
{
"epoch": 5.28,
"learning_rate": 7.447164474017632e-06,
"loss": 0.01,
"step": 1975
},
{
"epoch": 5.28,
"learning_rate": 7.392589398379868e-06,
"loss": 0.0092,
"step": 1976
},
{
"epoch": 5.29,
"learning_rate": 7.33820735399473e-06,
"loss": 0.0101,
"step": 1977
},
{
"epoch": 5.29,
"learning_rate": 7.28401845421639e-06,
"loss": 0.0092,
"step": 1978
},
{
"epoch": 5.29,
"learning_rate": 7.2300228119964064e-06,
"loss": 0.0087,
"step": 1979
},
{
"epoch": 5.29,
"learning_rate": 7.1762205398834936e-06,
"loss": 0.0083,
"step": 1980
},
{
"epoch": 5.3,
"learning_rate": 7.1226117500233e-06,
"loss": 0.0089,
"step": 1981
},
{
"epoch": 5.3,
"learning_rate": 7.06919655415822e-06,
"loss": 0.0109,
"step": 1982
},
{
"epoch": 5.3,
"learning_rate": 7.015975063627123e-06,
"loss": 0.0086,
"step": 1983
},
{
"epoch": 5.3,
"learning_rate": 6.962947389365071e-06,
"loss": 0.0113,
"step": 1984
},
{
"epoch": 5.31,
"learning_rate": 6.910113641903138e-06,
"loss": 0.0098,
"step": 1985
},
{
"epoch": 5.31,
"learning_rate": 6.857473931368219e-06,
"loss": 0.0095,
"step": 1986
},
{
"epoch": 5.31,
"learning_rate": 6.805028367482735e-06,
"loss": 0.0101,
"step": 1987
},
{
"epoch": 5.32,
"learning_rate": 6.75277705956443e-06,
"loss": 0.0088,
"step": 1988
},
{
"epoch": 5.32,
"learning_rate": 6.700720116526116e-06,
"loss": 0.0093,
"step": 1989
},
{
"epoch": 5.32,
"learning_rate": 6.648857646875506e-06,
"loss": 0.0098,
"step": 1990
},
{
"epoch": 5.32,
"learning_rate": 6.597189758714928e-06,
"loss": 0.0106,
"step": 1991
},
{
"epoch": 5.33,
"learning_rate": 6.545716559741166e-06,
"loss": 0.009,
"step": 1992
},
{
"epoch": 5.33,
"learning_rate": 6.49443815724512e-06,
"loss": 0.0089,
"step": 1993
},
{
"epoch": 5.33,
"learning_rate": 6.4433546581116996e-06,
"loss": 0.0093,
"step": 1994
},
{
"epoch": 5.33,
"learning_rate": 6.3924661688195555e-06,
"loss": 0.0099,
"step": 1995
},
{
"epoch": 5.34,
"learning_rate": 6.34177279544087e-06,
"loss": 0.0091,
"step": 1996
},
{
"epoch": 5.34,
"learning_rate": 6.29127464364111e-06,
"loss": 0.0097,
"step": 1997
},
{
"epoch": 5.34,
"learning_rate": 6.240971818678798e-06,
"loss": 0.0092,
"step": 1998
},
{
"epoch": 5.34,
"learning_rate": 6.190864425405362e-06,
"loss": 0.0081,
"step": 1999
},
{
"epoch": 5.35,
"learning_rate": 6.140952568264857e-06,
"loss": 0.0089,
"step": 2000
},
{
"epoch": 5.35,
"learning_rate": 6.091236351293717e-06,
"loss": 0.0101,
"step": 2001
},
{
"epoch": 5.35,
"learning_rate": 6.04171587812068e-06,
"loss": 0.0107,
"step": 2002
},
{
"epoch": 5.36,
"learning_rate": 5.992391251966356e-06,
"loss": 0.009,
"step": 2003
},
{
"epoch": 5.36,
"learning_rate": 5.943262575643238e-06,
"loss": 0.0109,
"step": 2004
},
{
"epoch": 5.36,
"learning_rate": 5.894329951555311e-06,
"loss": 0.0088,
"step": 2005
},
{
"epoch": 5.36,
"learning_rate": 5.8455934816979305e-06,
"loss": 0.0091,
"step": 2006
},
{
"epoch": 5.37,
"learning_rate": 5.797053267657582e-06,
"loss": 0.0098,
"step": 2007
},
{
"epoch": 5.37,
"learning_rate": 5.7487094106116854e-06,
"loss": 0.0095,
"step": 2008
},
{
"epoch": 5.37,
"learning_rate": 5.700562011328381e-06,
"loss": 0.0088,
"step": 2009
},
{
"epoch": 5.37,
"learning_rate": 5.652611170166289e-06,
"loss": 0.0096,
"step": 2010
},
{
"epoch": 5.38,
"learning_rate": 5.604856987074314e-06,
"loss": 0.0088,
"step": 2011
},
{
"epoch": 5.38,
"learning_rate": 5.557299561591478e-06,
"loss": 0.0087,
"step": 2012
},
{
"epoch": 5.38,
"learning_rate": 5.509938992846686e-06,
"loss": 0.0103,
"step": 2013
},
{
"epoch": 5.39,
"learning_rate": 5.46277537955846e-06,
"loss": 0.0087,
"step": 2014
},
{
"epoch": 5.39,
"learning_rate": 5.415808820034851e-06,
"loss": 0.0114,
"step": 2015
},
{
"epoch": 5.39,
"learning_rate": 5.369039412173116e-06,
"loss": 0.0085,
"step": 2016
},
{
"epoch": 5.39,
"learning_rate": 5.322467253459618e-06,
"loss": 0.0092,
"step": 2017
},
{
"epoch": 5.4,
"learning_rate": 5.2760924409695265e-06,
"loss": 0.0096,
"step": 2018
},
{
"epoch": 5.4,
"learning_rate": 5.229915071366698e-06,
"loss": 0.0104,
"step": 2019
},
{
"epoch": 5.4,
"learning_rate": 5.183935240903414e-06,
"loss": 0.0097,
"step": 2020
},
{
"epoch": 5.4,
"learning_rate": 5.138153045420235e-06,
"loss": 0.0089,
"step": 2021
},
{
"epoch": 5.41,
"learning_rate": 5.092568580345724e-06,
"loss": 0.0095,
"step": 2022
},
{
"epoch": 5.41,
"learning_rate": 5.047181940696333e-06,
"loss": 0.0106,
"step": 2023
},
{
"epoch": 5.41,
"learning_rate": 5.001993221076162e-06,
"loss": 0.0087,
"step": 2024
},
{
"epoch": 5.41,
"learning_rate": 4.9570025156767345e-06,
"loss": 0.0085,
"step": 2025
},
{
"epoch": 5.42,
"learning_rate": 4.912209918276878e-06,
"loss": 0.0084,
"step": 2026
},
{
"epoch": 5.42,
"learning_rate": 4.867615522242441e-06,
"loss": 0.0093,
"step": 2027
},
{
"epoch": 5.42,
"learning_rate": 4.8232194205261815e-06,
"loss": 0.01,
"step": 2028
},
{
"epoch": 5.43,
"learning_rate": 4.779021705667474e-06,
"loss": 0.0082,
"step": 2029
},
{
"epoch": 5.43,
"learning_rate": 4.73502246979225e-06,
"loss": 0.01,
"step": 2030
},
{
"epoch": 5.43,
"learning_rate": 4.6912218046126555e-06,
"loss": 0.0097,
"step": 2031
},
{
"epoch": 5.43,
"learning_rate": 4.647619801426995e-06,
"loss": 0.0084,
"step": 2032
},
{
"epoch": 5.44,
"learning_rate": 4.604216551119445e-06,
"loss": 0.0096,
"step": 2033
},
{
"epoch": 5.44,
"learning_rate": 4.561012144159927e-06,
"loss": 0.0099,
"step": 2034
},
{
"epoch": 5.44,
"learning_rate": 4.518006670603847e-06,
"loss": 0.0089,
"step": 2035
},
{
"epoch": 5.44,
"learning_rate": 4.475200220092002e-06,
"loss": 0.0111,
"step": 2036
},
{
"epoch": 5.45,
"learning_rate": 4.432592881850339e-06,
"loss": 0.0113,
"step": 2037
},
{
"epoch": 5.45,
"learning_rate": 4.39018474468974e-06,
"loss": 0.0095,
"step": 2038
},
{
"epoch": 5.45,
"learning_rate": 4.347975897005907e-06,
"loss": 0.0108,
"step": 2039
},
{
"epoch": 5.45,
"learning_rate": 4.305966426779118e-06,
"loss": 0.0085,
"step": 2040
},
{
"epoch": 5.46,
"learning_rate": 4.264156421574095e-06,
"loss": 0.0095,
"step": 2041
},
{
"epoch": 5.46,
"learning_rate": 4.22254596853976e-06,
"loss": 0.0098,
"step": 2042
},
{
"epoch": 5.46,
"learning_rate": 4.181135154409122e-06,
"loss": 0.0106,
"step": 2043
},
{
"epoch": 5.47,
"learning_rate": 4.139924065499035e-06,
"loss": 0.0099,
"step": 2044
},
{
"epoch": 5.47,
"learning_rate": 4.098912787710052e-06,
"loss": 0.0092,
"step": 2045
},
{
"epoch": 5.47,
"learning_rate": 4.058101406526271e-06,
"loss": 0.0109,
"step": 2046
},
{
"epoch": 5.47,
"learning_rate": 4.017490007015068e-06,
"loss": 0.0103,
"step": 2047
},
{
"epoch": 5.48,
"learning_rate": 3.977078673826995e-06,
"loss": 0.0102,
"step": 2048
},
{
"epoch": 5.48,
"learning_rate": 3.9368674911956175e-06,
"loss": 0.0102,
"step": 2049
},
{
"epoch": 5.48,
"learning_rate": 3.8968565429372886e-06,
"loss": 0.0132,
"step": 2050
},
{
"epoch": 5.48,
"learning_rate": 3.857045912450974e-06,
"loss": 0.0087,
"step": 2051
},
{
"epoch": 5.49,
"learning_rate": 3.817435682718096e-06,
"loss": 0.0094,
"step": 2052
},
{
"epoch": 5.49,
"learning_rate": 3.7780259363023985e-06,
"loss": 0.0102,
"step": 2053
},
{
"epoch": 5.49,
"learning_rate": 3.7388167553496946e-06,
"loss": 0.0086,
"step": 2054
},
{
"epoch": 5.49,
"learning_rate": 3.699808221587786e-06,
"loss": 0.0088,
"step": 2055
},
{
"epoch": 5.5,
"learning_rate": 3.6610004163261767e-06,
"loss": 0.0097,
"step": 2056
},
{
"epoch": 5.5,
"learning_rate": 3.622393420456016e-06,
"loss": 0.011,
"step": 2057
},
{
"epoch": 5.5,
"learning_rate": 3.5839873144498883e-06,
"loss": 0.0094,
"step": 2058
},
{
"epoch": 5.51,
"learning_rate": 3.5457821783616563e-06,
"loss": 0.011,
"step": 2059
},
{
"epoch": 5.51,
"learning_rate": 3.507778091826219e-06,
"loss": 0.0096,
"step": 2060
},
{
"epoch": 5.51,
"learning_rate": 3.4699751340594554e-06,
"loss": 0.0107,
"step": 2061
},
{
"epoch": 5.51,
"learning_rate": 3.432373383858001e-06,
"loss": 0.0101,
"step": 2062
},
{
"epoch": 5.52,
"learning_rate": 3.394972919599093e-06,
"loss": 0.0089,
"step": 2063
},
{
"epoch": 5.52,
"learning_rate": 3.3577738192404395e-06,
"loss": 0.0098,
"step": 2064
},
{
"epoch": 5.52,
"learning_rate": 3.3207761603199273e-06,
"loss": 0.0111,
"step": 2065
},
{
"epoch": 5.52,
"learning_rate": 3.283980019955668e-06,
"loss": 0.0093,
"step": 2066
},
{
"epoch": 5.53,
"learning_rate": 3.2473854748456545e-06,
"loss": 0.0094,
"step": 2067
},
{
"epoch": 5.53,
"learning_rate": 3.2109926012677484e-06,
"loss": 0.0089,
"step": 2068
},
{
"epoch": 5.53,
"learning_rate": 3.1748014750793585e-06,
"loss": 0.0071,
"step": 2069
},
{
"epoch": 5.53,
"learning_rate": 3.138812171717409e-06,
"loss": 0.0077,
"step": 2070
},
{
"epoch": 5.54,
"learning_rate": 3.103024766198159e-06,
"loss": 0.0089,
"step": 2071
},
{
"epoch": 5.54,
"learning_rate": 3.067439333117028e-06,
"loss": 0.008,
"step": 2072
},
{
"epoch": 5.54,
"learning_rate": 3.032055946648427e-06,
"loss": 0.0092,
"step": 2073
},
{
"epoch": 5.55,
"learning_rate": 2.996874680545603e-06,
"loss": 0.0095,
"step": 2074
},
{
"epoch": 5.55,
"learning_rate": 2.9618956081405525e-06,
"loss": 0.0107,
"step": 2075
},
{
"epoch": 5.55,
"learning_rate": 2.9271188023437867e-06,
"loss": 0.0092,
"step": 2076
},
{
"epoch": 5.55,
"learning_rate": 2.8925443356442205e-06,
"loss": 0.0096,
"step": 2077
},
{
"epoch": 5.56,
"learning_rate": 2.858172280109006e-06,
"loss": 0.009,
"step": 2078
},
{
"epoch": 5.56,
"learning_rate": 2.8240027073833774e-06,
"loss": 0.0098,
"step": 2079
},
{
"epoch": 5.56,
"learning_rate": 2.79003568869054e-06,
"loss": 0.0107,
"step": 2080
},
{
"epoch": 5.56,
"learning_rate": 2.7562712948314916e-06,
"loss": 0.0097,
"step": 2081
},
{
"epoch": 5.57,
"learning_rate": 2.722709596184858e-06,
"loss": 0.009,
"step": 2082
},
{
"epoch": 5.57,
"learning_rate": 2.689350662706769e-06,
"loss": 0.0086,
"step": 2083
},
{
"epoch": 5.57,
"learning_rate": 2.656194563930714e-06,
"loss": 0.009,
"step": 2084
},
{
"epoch": 5.57,
"learning_rate": 2.6232413689674216e-06,
"loss": 0.0098,
"step": 2085
},
{
"epoch": 5.58,
"learning_rate": 2.5904911465046477e-06,
"loss": 0.0102,
"step": 2086
},
{
"epoch": 5.58,
"learning_rate": 2.5579439648070745e-06,
"loss": 0.0103,
"step": 2087
},
{
"epoch": 5.58,
"learning_rate": 2.5255998917161906e-06,
"loss": 0.0099,
"step": 2088
},
{
"epoch": 5.59,
"learning_rate": 2.493458994650111e-06,
"loss": 0.0104,
"step": 2089
},
{
"epoch": 5.59,
"learning_rate": 2.4615213406034343e-06,
"loss": 0.0111,
"step": 2090
},
{
"epoch": 5.59,
"learning_rate": 2.429786996147154e-06,
"loss": 0.0091,
"step": 2091
},
{
"epoch": 5.59,
"learning_rate": 2.398256027428436e-06,
"loss": 0.0097,
"step": 2092
},
{
"epoch": 5.6,
"learning_rate": 2.366928500170573e-06,
"loss": 0.0089,
"step": 2093
},
{
"epoch": 5.6,
"learning_rate": 2.3358044796727872e-06,
"loss": 0.01,
"step": 2094
},
{
"epoch": 5.6,
"learning_rate": 2.304884030810117e-06,
"loss": 0.01,
"step": 2095
},
{
"epoch": 5.6,
"learning_rate": 2.2741672180332406e-06,
"loss": 0.0092,
"step": 2096
},
{
"epoch": 5.61,
"learning_rate": 2.24365410536842e-06,
"loss": 0.0105,
"step": 2097
},
{
"epoch": 5.61,
"learning_rate": 2.2133447564173236e-06,
"loss": 0.01,
"step": 2098
},
{
"epoch": 5.61,
"learning_rate": 2.1832392343568596e-06,
"loss": 0.0107,
"step": 2099
},
{
"epoch": 5.61,
"learning_rate": 2.1533376019391094e-06,
"loss": 0.0089,
"step": 2100
},
{
"epoch": 5.62,
"learning_rate": 2.1236399214911272e-06,
"loss": 0.0096,
"step": 2101
},
{
"epoch": 5.62,
"learning_rate": 2.094146254914908e-06,
"loss": 0.0088,
"step": 2102
},
{
"epoch": 5.62,
"learning_rate": 2.0648566636871423e-06,
"loss": 0.0083,
"step": 2103
},
{
"epoch": 5.63,
"learning_rate": 2.035771208859194e-06,
"loss": 0.0104,
"step": 2104
},
{
"epoch": 5.63,
"learning_rate": 2.0068899510568786e-06,
"loss": 0.0084,
"step": 2105
},
{
"epoch": 5.63,
"learning_rate": 1.978212950480418e-06,
"loss": 0.0109,
"step": 2106
},
{
"epoch": 5.63,
"learning_rate": 1.949740266904243e-06,
"loss": 0.0089,
"step": 2107
},
{
"epoch": 5.64,
"learning_rate": 1.921471959676957e-06,
"loss": 0.0096,
"step": 2108
},
{
"epoch": 5.64,
"learning_rate": 1.8934080877211157e-06,
"loss": 0.0111,
"step": 2109
},
{
"epoch": 5.64,
"learning_rate": 1.8655487095331714e-06,
"loss": 0.0089,
"step": 2110
},
{
"epoch": 5.64,
"learning_rate": 1.837893883183317e-06,
"loss": 0.01,
"step": 2111
},
{
"epoch": 5.65,
"learning_rate": 1.8104436663153756e-06,
"loss": 0.0095,
"step": 2112
},
{
"epoch": 5.65,
"learning_rate": 1.7831981161467115e-06,
"loss": 0.0109,
"step": 2113
},
{
"epoch": 5.65,
"learning_rate": 1.756157289468019e-06,
"loss": 0.0099,
"step": 2114
},
{
"epoch": 5.66,
"learning_rate": 1.7293212426433447e-06,
"loss": 0.0097,
"step": 2115
},
{
"epoch": 5.66,
"learning_rate": 1.7026900316098215e-06,
"loss": 0.0092,
"step": 2116
},
{
"epoch": 5.66,
"learning_rate": 1.6762637118776681e-06,
"loss": 0.009,
"step": 2117
},
{
"epoch": 5.66,
"learning_rate": 1.65004233853e-06,
"loss": 0.0092,
"step": 2118
},
{
"epoch": 5.67,
"learning_rate": 1.6240259662227531e-06,
"loss": 0.0089,
"step": 2119
},
{
"epoch": 5.67,
"learning_rate": 1.5982146491845595e-06,
"loss": 0.0093,
"step": 2120
},
{
"epoch": 5.67,
"learning_rate": 1.5726084412166276e-06,
"loss": 0.01,
"step": 2121
},
{
"epoch": 5.67,
"learning_rate": 1.5472073956926403e-06,
"loss": 0.0133,
"step": 2122
},
{
"epoch": 5.68,
"learning_rate": 1.5220115655586452e-06,
"loss": 0.0081,
"step": 2123
},
{
"epoch": 5.68,
"learning_rate": 1.49702100333291e-06,
"loss": 0.0082,
"step": 2124
},
{
"epoch": 5.68,
"learning_rate": 1.472235761105878e-06,
"loss": 0.0083,
"step": 2125
},
{
"epoch": 5.68,
"learning_rate": 1.4476558905400007e-06,
"loss": 0.011,
"step": 2126
},
{
"epoch": 5.69,
"learning_rate": 1.4232814428696506e-06,
"loss": 0.0098,
"step": 2127
},
{
"epoch": 5.69,
"learning_rate": 1.3991124689010427e-06,
"loss": 0.009,
"step": 2128
},
{
"epoch": 5.69,
"learning_rate": 1.3751490190120675e-06,
"loss": 0.0085,
"step": 2129
},
{
"epoch": 5.7,
"learning_rate": 1.3513911431522252e-06,
"loss": 0.0099,
"step": 2130
},
{
"epoch": 5.7,
"learning_rate": 1.3278388908425475e-06,
"loss": 0.01,
"step": 2131
},
{
"epoch": 5.7,
"learning_rate": 1.3044923111754427e-06,
"loss": 0.0084,
"step": 2132
},
{
"epoch": 5.7,
"learning_rate": 1.2813514528145831e-06,
"loss": 0.0108,
"step": 2133
},
{
"epoch": 5.71,
"learning_rate": 1.2584163639948854e-06,
"loss": 0.0095,
"step": 2134
},
{
"epoch": 5.71,
"learning_rate": 1.235687092522353e-06,
"loss": 0.0111,
"step": 2135
},
{
"epoch": 5.71,
"learning_rate": 1.2131636857739547e-06,
"loss": 0.0097,
"step": 2136
},
{
"epoch": 5.71,
"learning_rate": 1.1908461906975587e-06,
"loss": 0.0094,
"step": 2137
},
{
"epoch": 5.72,
"learning_rate": 1.1687346538118537e-06,
"loss": 0.0091,
"step": 2138
},
{
"epoch": 5.72,
"learning_rate": 1.1468291212062166e-06,
"loss": 0.0106,
"step": 2139
},
{
"epoch": 5.72,
"learning_rate": 1.125129638540623e-06,
"loss": 0.0077,
"step": 2140
},
{
"epoch": 5.72,
"learning_rate": 1.1036362510455477e-06,
"loss": 0.008,
"step": 2141
},
{
"epoch": 5.73,
"learning_rate": 1.0823490035218987e-06,
"loss": 0.0106,
"step": 2142
},
{
"epoch": 5.73,
"learning_rate": 1.0612679403409154e-06,
"loss": 0.01,
"step": 2143
},
{
"epoch": 5.73,
"learning_rate": 1.0403931054440374e-06,
"loss": 0.0086,
"step": 2144
},
{
"epoch": 5.74,
"learning_rate": 1.019724542342848e-06,
"loss": 0.0103,
"step": 2145
},
{
"epoch": 5.74,
"learning_rate": 9.992622941189856e-07,
"loss": 0.0093,
"step": 2146
},
{
"epoch": 5.74,
"learning_rate": 9.790064034240432e-07,
"loss": 0.0089,
"step": 2147
},
{
"epoch": 5.74,
"learning_rate": 9.589569124794916e-07,
"loss": 0.0082,
"step": 2148
},
{
"epoch": 5.75,
"learning_rate": 9.391138630765462e-07,
"loss": 0.009,
"step": 2149
},
{
"epoch": 5.75,
"learning_rate": 9.194772965761433e-07,
"loss": 0.0107,
"step": 2150
},
{
"epoch": 5.75,
"learning_rate": 9.0004725390882e-07,
"loss": 0.0089,
"step": 2151
},
{
"epoch": 5.75,
"learning_rate": 8.808237755746351e-07,
"loss": 0.0087,
"step": 2152
},
{
"epoch": 5.76,
"learning_rate": 8.61806901643103e-07,
"loss": 0.0073,
"step": 2153
},
{
"epoch": 5.76,
"learning_rate": 8.42996671753038e-07,
"loss": 0.0114,
"step": 2154
},
{
"epoch": 5.76,
"learning_rate": 8.24393125112577e-07,
"loss": 0.0101,
"step": 2155
},
{
"epoch": 5.76,
"learning_rate": 8.059963004990234e-07,
"loss": 0.0094,
"step": 2156
},
{
"epoch": 5.77,
"learning_rate": 7.878062362587924e-07,
"loss": 0.0109,
"step": 2157
},
{
"epoch": 5.77,
"learning_rate": 7.698229703073212e-07,
"loss": 0.0119,
"step": 2158
},
{
"epoch": 5.77,
"learning_rate": 7.520465401290033e-07,
"loss": 0.01,
"step": 2159
},
{
"epoch": 5.78,
"learning_rate": 7.344769827770881e-07,
"loss": 0.0088,
"step": 2160
},
{
"epoch": 5.78,
"learning_rate": 7.171143348736476e-07,
"loss": 0.0092,
"step": 2161
},
{
"epoch": 5.78,
"learning_rate": 6.999586326094653e-07,
"loss": 0.0106,
"step": 2162
},
{
"epoch": 5.78,
"learning_rate": 6.830099117439149e-07,
"loss": 0.0087,
"step": 2163
},
{
"epoch": 5.79,
"learning_rate": 6.662682076050031e-07,
"loss": 0.0092,
"step": 2164
},
{
"epoch": 5.79,
"learning_rate": 6.497335550892047e-07,
"loss": 0.0105,
"step": 2165
},
{
"epoch": 5.79,
"learning_rate": 6.334059886614064e-07,
"loss": 0.0083,
"step": 2166
},
{
"epoch": 5.79,
"learning_rate": 6.172855423548618e-07,
"loss": 0.0091,
"step": 2167
},
{
"epoch": 5.8,
"learning_rate": 6.013722497710816e-07,
"loss": 0.0096,
"step": 2168
},
{
"epoch": 5.8,
"learning_rate": 5.856661440797995e-07,
"loss": 0.0085,
"step": 2169
},
{
"epoch": 5.8,
"learning_rate": 5.701672580188943e-07,
"loss": 0.0132,
"step": 2170
},
{
"epoch": 5.8,
"learning_rate": 5.548756238942909e-07,
"loss": 0.0091,
"step": 2171
},
{
"epoch": 5.81,
"learning_rate": 5.397912735799371e-07,
"loss": 0.0091,
"step": 2172
},
{
"epoch": 5.81,
"learning_rate": 5.249142385177152e-07,
"loss": 0.0102,
"step": 2173
},
{
"epoch": 5.81,
"learning_rate": 5.102445497173757e-07,
"loss": 0.0093,
"step": 2174
},
{
"epoch": 5.82,
"learning_rate": 4.957822377564702e-07,
"loss": 0.0112,
"step": 2175
},
{
"epoch": 5.82,
"learning_rate": 4.815273327803182e-07,
"loss": 0.0096,
"step": 2176
},
{
"epoch": 5.82,
"learning_rate": 4.67479864501863e-07,
"loss": 0.0089,
"step": 2177
},
{
"epoch": 5.82,
"learning_rate": 4.5363986220173795e-07,
"loss": 0.0093,
"step": 2178
},
{
"epoch": 5.83,
"learning_rate": 4.400073547280781e-07,
"loss": 0.01,
"step": 2179
},
{
"epoch": 5.83,
"learning_rate": 4.2658237049655323e-07,
"loss": 0.0112,
"step": 2180
},
{
"epoch": 5.83,
"learning_rate": 4.133649374902349e-07,
"loss": 0.01,
"step": 2181
},
{
"epoch": 5.83,
"learning_rate": 4.0035508325959593e-07,
"loss": 0.0095,
"step": 2182
},
{
"epoch": 5.84,
"learning_rate": 3.875528349224444e-07,
"loss": 0.0083,
"step": 2183
},
{
"epoch": 5.84,
"learning_rate": 3.7495821916382344e-07,
"loss": 0.009,
"step": 2184
},
{
"epoch": 5.84,
"learning_rate": 3.62571262236e-07,
"loss": 0.0086,
"step": 2185
},
{
"epoch": 5.84,
"learning_rate": 3.5039198995839853e-07,
"loss": 0.0092,
"step": 2186
},
{
"epoch": 5.85,
"learning_rate": 3.384204277175451e-07,
"loss": 0.0101,
"step": 2187
},
{
"epoch": 5.85,
"learning_rate": 3.266566004670013e-07,
"loss": 0.0121,
"step": 2188
},
{
"epoch": 5.85,
"learning_rate": 3.151005327273526e-07,
"loss": 0.0112,
"step": 2189
},
{
"epoch": 5.86,
"learning_rate": 3.0375224858609773e-07,
"loss": 0.0085,
"step": 2190
},
{
"epoch": 5.86,
"learning_rate": 2.926117716976484e-07,
"loss": 0.0097,
"step": 2191
},
{
"epoch": 5.86,
"learning_rate": 2.816791252832518e-07,
"loss": 0.0099,
"step": 2192
},
{
"epoch": 5.86,
"learning_rate": 2.709543321309793e-07,
"loss": 0.011,
"step": 2193
},
{
"epoch": 5.87,
"learning_rate": 2.6043741459561563e-07,
"loss": 0.0089,
"step": 2194
},
{
"epoch": 5.87,
"learning_rate": 2.501283945986699e-07,
"loss": 0.0097,
"step": 2195
},
{
"epoch": 5.87,
"learning_rate": 2.400272936283088e-07,
"loss": 0.0084,
"step": 2196
},
{
"epoch": 5.87,
"learning_rate": 2.301341327392903e-07,
"loss": 0.0092,
"step": 2197
},
{
"epoch": 5.88,
"learning_rate": 2.204489325529857e-07,
"loss": 0.0117,
"step": 2198
},
{
"epoch": 5.88,
"learning_rate": 2.109717132572353e-07,
"loss": 0.0085,
"step": 2199
},
{
"epoch": 5.88,
"learning_rate": 2.0170249460641498e-07,
"loss": 0.0091,
"step": 2200
},
{
"epoch": 5.89,
"learning_rate": 1.926412959213031e-07,
"loss": 0.0102,
"step": 2201
},
{
"epoch": 5.89,
"learning_rate": 1.837881360891136e-07,
"loss": 0.0081,
"step": 2202
},
{
"epoch": 5.89,
"learning_rate": 1.7514303356339635e-07,
"loss": 0.0101,
"step": 2203
},
{
"epoch": 5.89,
"learning_rate": 1.6670600636403687e-07,
"loss": 0.0099,
"step": 2204
},
{
"epoch": 5.9,
"learning_rate": 1.584770720772233e-07,
"loss": 0.0087,
"step": 2205
},
{
"epoch": 5.9,
"learning_rate": 1.504562478553684e-07,
"loss": 0.0096,
"step": 2206
},
{
"epoch": 5.9,
"learning_rate": 1.4264355041709864e-07,
"loss": 0.0097,
"step": 2207
},
{
"epoch": 5.9,
"learning_rate": 1.3503899604725423e-07,
"loss": 0.0097,
"step": 2208
},
{
"epoch": 5.91,
"learning_rate": 1.2764260059677792e-07,
"loss": 0.009,
"step": 2209
},
{
"epoch": 5.91,
"learning_rate": 1.204543794827595e-07,
"loss": 0.0094,
"step": 2210
},
{
"epoch": 5.91,
"learning_rate": 1.1347434768834708e-07,
"loss": 0.0095,
"step": 2211
},
{
"epoch": 5.91,
"learning_rate": 1.0670251976275803e-07,
"loss": 0.0111,
"step": 2212
},
{
"epoch": 5.92,
"learning_rate": 1.0013890982120134e-07,
"loss": 0.0085,
"step": 2213
},
{
"epoch": 5.92,
"learning_rate": 9.378353154489982e-08,
"loss": 0.0081,
"step": 2214
},
{
"epoch": 5.92,
"learning_rate": 8.763639818103464e-08,
"loss": 0.0089,
"step": 2215
},
{
"epoch": 5.93,
"learning_rate": 8.16975225427008e-08,
"loss": 0.0087,
"step": 2216
},
{
"epoch": 5.93,
"learning_rate": 7.596691700891834e-08,
"loss": 0.0103,
"step": 2217
},
{
"epoch": 5.93,
"learning_rate": 7.044459352459898e-08,
"loss": 0.0094,
"step": 2218
},
{
"epoch": 5.93,
"learning_rate": 6.513056360047953e-08,
"loss": 0.0085,
"step": 2219
},
{
"epoch": 5.94,
"learning_rate": 6.002483831314409e-08,
"loss": 0.01,
"step": 2220
},
{
"epoch": 5.94,
"learning_rate": 5.512742830500184e-08,
"loss": 0.0097,
"step": 2221
},
{
"epoch": 5.94,
"learning_rate": 5.043834378422041e-08,
"loss": 0.0098,
"step": 2222
},
{
"epoch": 5.94,
"learning_rate": 4.5957594524748124e-08,
"loss": 0.0112,
"step": 2223
},
{
"epoch": 5.95,
"learning_rate": 4.168518986628067e-08,
"loss": 0.0101,
"step": 2224
},
{
"epoch": 5.95,
"learning_rate": 3.762113871422779e-08,
"loss": 0.0096,
"step": 2225
},
{
"epoch": 5.95,
"learning_rate": 3.3765449539724384e-08,
"loss": 0.0095,
"step": 2226
},
{
"epoch": 5.95,
"learning_rate": 3.0118130379575005e-08,
"loss": 0.0109,
"step": 2227
},
{
"epoch": 5.96,
"learning_rate": 2.667918883627607e-08,
"loss": 0.008,
"step": 2228
},
{
"epoch": 5.96,
"learning_rate": 2.3448632077960332e-08,
"loss": 0.0093,
"step": 2229
},
{
"epoch": 5.96,
"learning_rate": 2.0426466838407988e-08,
"loss": 0.0119,
"step": 2230
},
{
"epoch": 5.97,
"learning_rate": 1.7612699417057788e-08,
"loss": 0.0112,
"step": 2231
},
{
"epoch": 5.97,
"learning_rate": 1.500733567890711e-08,
"loss": 0.0083,
"step": 2232
},
{
"epoch": 5.97,
"learning_rate": 1.2610381054611874e-08,
"loss": 0.0093,
"step": 2233
},
{
"epoch": 5.97,
"learning_rate": 1.0421840540375539e-08,
"loss": 0.0094,
"step": 2234
},
{
"epoch": 5.98,
"learning_rate": 8.441718698004586e-09,
"loss": 0.0092,
"step": 2235
},
{
"epoch": 5.98,
"learning_rate": 6.670019654875237e-09,
"loss": 0.009,
"step": 2236
},
{
"epoch": 5.98,
"learning_rate": 5.10674710393344e-09,
"loss": 0.0087,
"step": 2237
},
{
"epoch": 5.98,
"learning_rate": 3.751904303661568e-09,
"loss": 0.0096,
"step": 2238
},
{
"epoch": 5.99,
"learning_rate": 2.6054940780895207e-09,
"loss": 0.0093,
"step": 2239
},
{
"epoch": 5.99,
"learning_rate": 1.6675188168169265e-09,
"loss": 0.0106,
"step": 2240
},
{
"epoch": 5.99,
"learning_rate": 9.379804749465315e-10,
"loss": 0.0095,
"step": 2241
},
{
"epoch": 5.99,
"learning_rate": 4.1688057315081297e-10,
"loss": 0.0099,
"step": 2242
},
{
"epoch": 6.0,
"learning_rate": 1.042201975942625e-10,
"loss": 0.009,
"step": 2243
},
{
"epoch": 6.0,
"learning_rate": 0.0,
"loss": 0.0101,
"step": 2244
},
{
"epoch": 6.0,
"step": 2244,
"total_flos": 1013558966550528.0,
"train_loss": 0.31246253915497146,
"train_runtime": 35579.4145,
"train_samples_per_second": 12.603,
"train_steps_per_second": 0.063
}
],
"logging_steps": 1,
"max_steps": 2244,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 50000,
"total_flos": 1013558966550528.0,
"train_batch_size": 50,
"trial_name": null,
"trial_params": null
}