freesky's picture
commit
ede8620
raw
history blame contribute delete
No virus
84.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.0,
"eval_steps": 500,
"global_step": 700,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.7619047619047615e-06,
"loss": 1.4031,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 9.523809523809523e-06,
"loss": 1.0378,
"step": 2
},
{
"epoch": 0.03,
"learning_rate": 1.4285714285714285e-05,
"loss": 1.419,
"step": 3
},
{
"epoch": 0.04,
"learning_rate": 1.9047619047619046e-05,
"loss": 0.8751,
"step": 4
},
{
"epoch": 0.05,
"learning_rate": 2.380952380952381e-05,
"loss": 0.8246,
"step": 5
},
{
"epoch": 0.06,
"learning_rate": 2.857142857142857e-05,
"loss": 1.5731,
"step": 6
},
{
"epoch": 0.07,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.4364,
"step": 7
},
{
"epoch": 0.08,
"learning_rate": 3.809523809523809e-05,
"loss": 1.3878,
"step": 8
},
{
"epoch": 0.09,
"learning_rate": 4.2857142857142856e-05,
"loss": 1.265,
"step": 9
},
{
"epoch": 0.1,
"learning_rate": 4.761904761904762e-05,
"loss": 1.3973,
"step": 10
},
{
"epoch": 0.11,
"learning_rate": 5.2380952380952384e-05,
"loss": 1.6149,
"step": 11
},
{
"epoch": 0.12,
"learning_rate": 5.714285714285714e-05,
"loss": 1.6563,
"step": 12
},
{
"epoch": 0.13,
"learning_rate": 6.19047619047619e-05,
"loss": 1.7338,
"step": 13
},
{
"epoch": 0.14,
"learning_rate": 6.666666666666667e-05,
"loss": 1.1037,
"step": 14
},
{
"epoch": 0.15,
"learning_rate": 7.142857142857143e-05,
"loss": 0.7607,
"step": 15
},
{
"epoch": 0.16,
"learning_rate": 7.619047619047618e-05,
"loss": 1.5945,
"step": 16
},
{
"epoch": 0.17,
"learning_rate": 8.095238095238096e-05,
"loss": 0.9,
"step": 17
},
{
"epoch": 0.18,
"learning_rate": 8.571428571428571e-05,
"loss": 0.2399,
"step": 18
},
{
"epoch": 0.19,
"learning_rate": 9.047619047619048e-05,
"loss": 0.5496,
"step": 19
},
{
"epoch": 0.2,
"learning_rate": 9.523809523809524e-05,
"loss": 1.388,
"step": 20
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.7568,
"step": 21
},
{
"epoch": 0.22,
"learning_rate": 9.999946482054772e-05,
"loss": 1.1276,
"step": 22
},
{
"epoch": 0.23,
"learning_rate": 9.999785929364756e-05,
"loss": 1.4121,
"step": 23
},
{
"epoch": 0.24,
"learning_rate": 9.999518345366932e-05,
"loss": 0.9086,
"step": 24
},
{
"epoch": 0.25,
"learning_rate": 9.999143735789518e-05,
"loss": 0.5801,
"step": 25
},
{
"epoch": 0.26,
"learning_rate": 9.998662108651848e-05,
"loss": 1.0704,
"step": 26
},
{
"epoch": 0.27,
"learning_rate": 9.9980734742642e-05,
"loss": 1.0435,
"step": 27
},
{
"epoch": 0.28,
"learning_rate": 9.997377845227576e-05,
"loss": 0.6334,
"step": 28
},
{
"epoch": 0.29,
"learning_rate": 9.996575236433428e-05,
"loss": 1.0811,
"step": 29
},
{
"epoch": 0.3,
"learning_rate": 9.995665665063349e-05,
"loss": 1.2314,
"step": 30
},
{
"epoch": 0.31,
"learning_rate": 9.994649150588693e-05,
"loss": 0.4723,
"step": 31
},
{
"epoch": 0.32,
"learning_rate": 9.993525714770166e-05,
"loss": 0.0684,
"step": 32
},
{
"epoch": 0.33,
"learning_rate": 9.992295381657361e-05,
"loss": 0.5988,
"step": 33
},
{
"epoch": 0.34,
"learning_rate": 9.990958177588236e-05,
"loss": 0.0821,
"step": 34
},
{
"epoch": 0.35,
"learning_rate": 9.989514131188559e-05,
"loss": 0.6222,
"step": 35
},
{
"epoch": 0.36,
"learning_rate": 9.987963273371286e-05,
"loss": 0.4488,
"step": 36
},
{
"epoch": 0.37,
"learning_rate": 9.986305637335907e-05,
"loss": 1.4852,
"step": 37
},
{
"epoch": 0.38,
"learning_rate": 9.984541258567731e-05,
"loss": 1.4569,
"step": 38
},
{
"epoch": 0.39,
"learning_rate": 9.98267017483713e-05,
"loss": 1.1673,
"step": 39
},
{
"epoch": 0.4,
"learning_rate": 9.980692426198728e-05,
"loss": 0.195,
"step": 40
},
{
"epoch": 0.41,
"learning_rate": 9.978608054990539e-05,
"loss": 1.3146,
"step": 41
},
{
"epoch": 0.42,
"learning_rate": 9.97641710583307e-05,
"loss": 0.4517,
"step": 42
},
{
"epoch": 0.43,
"learning_rate": 9.974119625628361e-05,
"loss": 0.7465,
"step": 43
},
{
"epoch": 0.44,
"learning_rate": 9.971715663558979e-05,
"loss": 0.4864,
"step": 44
},
{
"epoch": 0.45,
"learning_rate": 9.969205271086968e-05,
"loss": 1.0293,
"step": 45
},
{
"epoch": 0.46,
"learning_rate": 9.966588501952746e-05,
"loss": 0.7191,
"step": 46
},
{
"epoch": 0.47,
"learning_rate": 9.963865412173957e-05,
"loss": 0.9721,
"step": 47
},
{
"epoch": 0.48,
"learning_rate": 9.961036060044268e-05,
"loss": 1.1731,
"step": 48
},
{
"epoch": 0.49,
"learning_rate": 9.958100506132127e-05,
"loss": 1.0871,
"step": 49
},
{
"epoch": 0.5,
"learning_rate": 9.955058813279455e-05,
"loss": 0.8415,
"step": 50
},
{
"epoch": 0.51,
"learning_rate": 9.951911046600313e-05,
"loss": 0.584,
"step": 51
},
{
"epoch": 0.52,
"learning_rate": 9.948657273479507e-05,
"loss": 0.6379,
"step": 52
},
{
"epoch": 0.53,
"learning_rate": 9.945297563571135e-05,
"loss": 0.5592,
"step": 53
},
{
"epoch": 0.54,
"learning_rate": 9.941831988797104e-05,
"loss": 1.1618,
"step": 54
},
{
"epoch": 0.55,
"learning_rate": 9.938260623345591e-05,
"loss": 1.3189,
"step": 55
},
{
"epoch": 0.56,
"learning_rate": 9.934583543669453e-05,
"loss": 1.0713,
"step": 56
},
{
"epoch": 0.57,
"learning_rate": 9.930800828484592e-05,
"loss": 0.6324,
"step": 57
},
{
"epoch": 0.58,
"learning_rate": 9.926912558768262e-05,
"loss": 0.6729,
"step": 58
},
{
"epoch": 0.59,
"learning_rate": 9.922918817757345e-05,
"loss": 0.7628,
"step": 59
},
{
"epoch": 0.6,
"learning_rate": 9.918819690946567e-05,
"loss": 0.641,
"step": 60
},
{
"epoch": 0.61,
"learning_rate": 9.914615266086668e-05,
"loss": 0.5939,
"step": 61
},
{
"epoch": 0.62,
"learning_rate": 9.910305633182518e-05,
"loss": 1.1748,
"step": 62
},
{
"epoch": 0.63,
"learning_rate": 9.905890884491195e-05,
"loss": 1.1561,
"step": 63
},
{
"epoch": 0.64,
"learning_rate": 9.901371114520012e-05,
"loss": 1.1403,
"step": 64
},
{
"epoch": 0.65,
"learning_rate": 9.89674642002449e-05,
"loss": 0.6795,
"step": 65
},
{
"epoch": 0.66,
"learning_rate": 9.892016900006284e-05,
"loss": 1.1345,
"step": 66
},
{
"epoch": 0.67,
"learning_rate": 9.887182655711077e-05,
"loss": 1.1063,
"step": 67
},
{
"epoch": 0.68,
"learning_rate": 9.882243790626393e-05,
"loss": 0.6593,
"step": 68
},
{
"epoch": 0.69,
"learning_rate": 9.877200410479399e-05,
"loss": 0.9359,
"step": 69
},
{
"epoch": 0.7,
"learning_rate": 9.872052623234632e-05,
"loss": 1.0167,
"step": 70
},
{
"epoch": 0.71,
"learning_rate": 9.866800539091688e-05,
"loss": 0.8953,
"step": 71
},
{
"epoch": 0.72,
"learning_rate": 9.861444270482868e-05,
"loss": 0.8634,
"step": 72
},
{
"epoch": 0.73,
"learning_rate": 9.85598393207077e-05,
"loss": 0.6286,
"step": 73
},
{
"epoch": 0.74,
"learning_rate": 9.850419640745831e-05,
"loss": 1.0384,
"step": 74
},
{
"epoch": 0.75,
"learning_rate": 9.844751515623824e-05,
"loss": 1.2193,
"step": 75
},
{
"epoch": 0.76,
"learning_rate": 9.838979678043315e-05,
"loss": 0.5009,
"step": 76
},
{
"epoch": 0.77,
"learning_rate": 9.833104251563056e-05,
"loss": 0.9311,
"step": 77
},
{
"epoch": 0.78,
"learning_rate": 9.827125361959353e-05,
"loss": 0.787,
"step": 78
},
{
"epoch": 0.79,
"learning_rate": 9.821043137223356e-05,
"loss": 0.0479,
"step": 79
},
{
"epoch": 0.8,
"learning_rate": 9.814857707558335e-05,
"loss": 1.2287,
"step": 80
},
{
"epoch": 0.81,
"learning_rate": 9.808569205376884e-05,
"loss": 1.2224,
"step": 81
},
{
"epoch": 0.82,
"learning_rate": 9.802177765298091e-05,
"loss": 0.7389,
"step": 82
},
{
"epoch": 0.83,
"learning_rate": 9.795683524144649e-05,
"loss": 0.8626,
"step": 83
},
{
"epoch": 0.84,
"learning_rate": 9.789086620939936e-05,
"loss": 1.0958,
"step": 84
},
{
"epoch": 0.85,
"learning_rate": 9.782387196905034e-05,
"loss": 0.7304,
"step": 85
},
{
"epoch": 0.86,
"learning_rate": 9.775585395455708e-05,
"loss": 1.0366,
"step": 86
},
{
"epoch": 0.87,
"learning_rate": 9.76868136219933e-05,
"loss": 0.5899,
"step": 87
},
{
"epoch": 0.88,
"learning_rate": 9.761675244931772e-05,
"loss": 0.645,
"step": 88
},
{
"epoch": 0.89,
"learning_rate": 9.754567193634232e-05,
"loss": 0.5779,
"step": 89
},
{
"epoch": 0.9,
"learning_rate": 9.747357360470033e-05,
"loss": 0.6998,
"step": 90
},
{
"epoch": 0.91,
"learning_rate": 9.740045899781352e-05,
"loss": 1.1801,
"step": 91
},
{
"epoch": 0.92,
"learning_rate": 9.732632968085936e-05,
"loss": 1.2694,
"step": 92
},
{
"epoch": 0.93,
"learning_rate": 9.725118724073731e-05,
"loss": 0.6501,
"step": 93
},
{
"epoch": 0.94,
"learning_rate": 9.717503328603498e-05,
"loss": 0.697,
"step": 94
},
{
"epoch": 0.95,
"learning_rate": 9.709786944699364e-05,
"loss": 0.5169,
"step": 95
},
{
"epoch": 0.96,
"learning_rate": 9.701969737547331e-05,
"loss": 0.7606,
"step": 96
},
{
"epoch": 0.97,
"learning_rate": 9.694051874491748e-05,
"loss": 1.0151,
"step": 97
},
{
"epoch": 0.98,
"learning_rate": 9.686033525031719e-05,
"loss": 0.8041,
"step": 98
},
{
"epoch": 0.99,
"learning_rate": 9.677914860817476e-05,
"loss": 0.8203,
"step": 99
},
{
"epoch": 1.0,
"learning_rate": 9.669696055646713e-05,
"loss": 1.0445,
"step": 100
},
{
"epoch": 1.01,
"learning_rate": 9.661377285460855e-05,
"loss": 1.0269,
"step": 101
},
{
"epoch": 1.02,
"learning_rate": 9.652958728341296e-05,
"loss": 1.1789,
"step": 102
},
{
"epoch": 1.03,
"learning_rate": 9.644440564505588e-05,
"loss": 0.5468,
"step": 103
},
{
"epoch": 1.04,
"learning_rate": 9.635822976303581e-05,
"loss": 0.5322,
"step": 104
},
{
"epoch": 1.05,
"learning_rate": 9.627106148213522e-05,
"loss": 0.4772,
"step": 105
},
{
"epoch": 1.06,
"learning_rate": 9.6182902668381e-05,
"loss": 0.5595,
"step": 106
},
{
"epoch": 1.07,
"learning_rate": 9.609375520900459e-05,
"loss": 0.593,
"step": 107
},
{
"epoch": 1.08,
"learning_rate": 9.600362101240152e-05,
"loss": 0.5759,
"step": 108
},
{
"epoch": 1.09,
"learning_rate": 9.59125020080906e-05,
"loss": 0.5372,
"step": 109
},
{
"epoch": 1.1,
"learning_rate": 9.582040014667258e-05,
"loss": 1.1394,
"step": 110
},
{
"epoch": 1.11,
"learning_rate": 9.572731739978839e-05,
"loss": 0.8768,
"step": 111
},
{
"epoch": 1.12,
"learning_rate": 9.563325576007701e-05,
"loss": 0.9546,
"step": 112
},
{
"epoch": 1.13,
"learning_rate": 9.553821724113268e-05,
"loss": 0.0215,
"step": 113
},
{
"epoch": 1.14,
"learning_rate": 9.544220387746192e-05,
"loss": 0.4819,
"step": 114
},
{
"epoch": 1.15,
"learning_rate": 9.534521772443988e-05,
"loss": 0.4828,
"step": 115
},
{
"epoch": 1.16,
"learning_rate": 9.524726085826644e-05,
"loss": 1.0581,
"step": 116
},
{
"epoch": 1.17,
"learning_rate": 9.514833537592166e-05,
"loss": 0.9637,
"step": 117
},
{
"epoch": 1.18,
"learning_rate": 9.504844339512095e-05,
"loss": 0.5552,
"step": 118
},
{
"epoch": 1.19,
"learning_rate": 9.494758705426978e-05,
"loss": 0.5657,
"step": 119
},
{
"epoch": 1.2,
"learning_rate": 9.484576851241773e-05,
"loss": 1.1438,
"step": 120
},
{
"epoch": 1.21,
"learning_rate": 9.474298994921251e-05,
"loss": 0.5918,
"step": 121
},
{
"epoch": 1.22,
"learning_rate": 9.463925356485313e-05,
"loss": 0.083,
"step": 122
},
{
"epoch": 1.23,
"learning_rate": 9.45345615800428e-05,
"loss": 0.5083,
"step": 123
},
{
"epoch": 1.24,
"learning_rate": 9.442891623594153e-05,
"loss": 1.0781,
"step": 124
},
{
"epoch": 1.25,
"learning_rate": 9.432231979411798e-05,
"loss": 0.6055,
"step": 125
},
{
"epoch": 1.26,
"learning_rate": 9.421477453650118e-05,
"loss": 1.1048,
"step": 126
},
{
"epoch": 1.27,
"learning_rate": 9.410628276533163e-05,
"loss": 0.4045,
"step": 127
},
{
"epoch": 1.28,
"learning_rate": 9.399684680311196e-05,
"loss": 0.8653,
"step": 128
},
{
"epoch": 1.29,
"learning_rate": 9.388646899255733e-05,
"loss": 0.3902,
"step": 129
},
{
"epoch": 1.3,
"learning_rate": 9.377515169654518e-05,
"loss": 1.0075,
"step": 130
},
{
"epoch": 1.31,
"learning_rate": 9.366289729806468e-05,
"loss": 0.5589,
"step": 131
},
{
"epoch": 1.32,
"learning_rate": 9.354970820016576e-05,
"loss": 0.2421,
"step": 132
},
{
"epoch": 1.33,
"learning_rate": 9.343558682590756e-05,
"loss": 0.6159,
"step": 133
},
{
"epoch": 1.34,
"learning_rate": 9.332053561830669e-05,
"loss": 0.5952,
"step": 134
},
{
"epoch": 1.35,
"learning_rate": 9.320455704028481e-05,
"loss": 1.2189,
"step": 135
},
{
"epoch": 1.36,
"learning_rate": 9.308765357461604e-05,
"loss": 0.3588,
"step": 136
},
{
"epoch": 1.37,
"learning_rate": 9.296982772387365e-05,
"loss": 0.37,
"step": 137
},
{
"epoch": 1.38,
"learning_rate": 9.285108201037662e-05,
"loss": 1.0717,
"step": 138
},
{
"epoch": 1.39,
"learning_rate": 9.27314189761356e-05,
"loss": 1.3066,
"step": 139
},
{
"epoch": 1.4,
"learning_rate": 9.261084118279847e-05,
"loss": 1.1335,
"step": 140
},
{
"epoch": 1.41,
"learning_rate": 9.24893512115955e-05,
"loss": 0.5148,
"step": 141
},
{
"epoch": 1.42,
"learning_rate": 9.236695166328419e-05,
"loss": 1.0804,
"step": 142
},
{
"epoch": 1.43,
"learning_rate": 9.224364515809343e-05,
"loss": 1.2198,
"step": 143
},
{
"epoch": 1.44,
"learning_rate": 9.211943433566755e-05,
"loss": 1.1472,
"step": 144
},
{
"epoch": 1.45,
"learning_rate": 9.199432185500973e-05,
"loss": 0.9091,
"step": 145
},
{
"epoch": 1.46,
"learning_rate": 9.186831039442514e-05,
"loss": 0.6102,
"step": 146
},
{
"epoch": 1.47,
"learning_rate": 9.174140265146356e-05,
"loss": 0.4588,
"step": 147
},
{
"epoch": 1.48,
"learning_rate": 9.161360134286166e-05,
"loss": 0.5156,
"step": 148
},
{
"epoch": 1.49,
"learning_rate": 9.148490920448477e-05,
"loss": 1.0874,
"step": 149
},
{
"epoch": 1.5,
"learning_rate": 9.135532899126844e-05,
"loss": 0.9126,
"step": 150
},
{
"epoch": 1.51,
"learning_rate": 9.122486347715937e-05,
"loss": 0.7957,
"step": 151
},
{
"epoch": 1.52,
"learning_rate": 9.109351545505607e-05,
"loss": 0.9366,
"step": 152
},
{
"epoch": 1.53,
"learning_rate": 9.096128773674902e-05,
"loss": 1.1504,
"step": 153
},
{
"epoch": 1.54,
"learning_rate": 9.082818315286055e-05,
"loss": 0.9205,
"step": 154
},
{
"epoch": 1.55,
"learning_rate": 9.069420455278419e-05,
"loss": 1.0,
"step": 155
},
{
"epoch": 1.56,
"learning_rate": 9.055935480462367e-05,
"loss": 1.2941,
"step": 156
},
{
"epoch": 1.57,
"learning_rate": 9.042363679513158e-05,
"loss": 1.1631,
"step": 157
},
{
"epoch": 1.58,
"learning_rate": 9.028705342964753e-05,
"loss": 0.6903,
"step": 158
},
{
"epoch": 1.59,
"learning_rate": 9.014960763203592e-05,
"loss": 1.0193,
"step": 159
},
{
"epoch": 1.6,
"learning_rate": 9.001130234462347e-05,
"loss": 0.5605,
"step": 160
},
{
"epoch": 1.61,
"learning_rate": 8.987214052813604e-05,
"loss": 0.8445,
"step": 161
},
{
"epoch": 1.62,
"learning_rate": 8.973212516163545e-05,
"loss": 0.7994,
"step": 162
},
{
"epoch": 1.63,
"learning_rate": 8.959125924245559e-05,
"loss": 1.0185,
"step": 163
},
{
"epoch": 1.64,
"learning_rate": 8.944954578613827e-05,
"loss": 0.4566,
"step": 164
},
{
"epoch": 1.65,
"learning_rate": 8.930698782636867e-05,
"loss": 1.1035,
"step": 165
},
{
"epoch": 1.66,
"learning_rate": 8.916358841491046e-05,
"loss": 1.0899,
"step": 166
},
{
"epoch": 1.67,
"learning_rate": 8.901935062154034e-05,
"loss": 0.664,
"step": 167
},
{
"epoch": 1.68,
"learning_rate": 8.887427753398248e-05,
"loss": 0.7774,
"step": 168
},
{
"epoch": 1.69,
"learning_rate": 8.872837225784226e-05,
"loss": 1.0792,
"step": 169
},
{
"epoch": 1.7,
"learning_rate": 8.858163791653994e-05,
"loss": 0.3954,
"step": 170
},
{
"epoch": 1.71,
"learning_rate": 8.84340776512437e-05,
"loss": 1.0453,
"step": 171
},
{
"epoch": 1.72,
"learning_rate": 8.828569462080238e-05,
"loss": 0.0937,
"step": 172
},
{
"epoch": 1.73,
"learning_rate": 8.813649200167799e-05,
"loss": 1.0096,
"step": 173
},
{
"epoch": 1.74,
"learning_rate": 8.798647298787754e-05,
"loss": 0.3115,
"step": 174
},
{
"epoch": 1.75,
"learning_rate": 8.783564079088477e-05,
"loss": 0.919,
"step": 175
},
{
"epoch": 1.76,
"learning_rate": 8.76839986395914e-05,
"loss": 0.4667,
"step": 176
},
{
"epoch": 1.77,
"learning_rate": 8.753154978022795e-05,
"loss": 0.8432,
"step": 177
},
{
"epoch": 1.78,
"learning_rate": 8.737829747629432e-05,
"loss": 0.8193,
"step": 178
},
{
"epoch": 1.79,
"learning_rate": 8.722424500848987e-05,
"loss": 0.4372,
"step": 179
},
{
"epoch": 1.8,
"learning_rate": 8.706939567464321e-05,
"loss": 0.0457,
"step": 180
},
{
"epoch": 1.81,
"learning_rate": 8.691375278964162e-05,
"loss": 0.015,
"step": 181
},
{
"epoch": 1.82,
"learning_rate": 8.675731968536002e-05,
"loss": 1.0568,
"step": 182
},
{
"epoch": 1.83,
"learning_rate": 8.660009971058978e-05,
"loss": 0.707,
"step": 183
},
{
"epoch": 1.84,
"learning_rate": 8.644209623096686e-05,
"loss": 0.5917,
"step": 184
},
{
"epoch": 1.85,
"learning_rate": 8.628331262889991e-05,
"loss": 1.2096,
"step": 185
},
{
"epoch": 1.86,
"learning_rate": 8.612375230349778e-05,
"loss": 1.1099,
"step": 186
},
{
"epoch": 1.87,
"learning_rate": 8.596341867049677e-05,
"loss": 0.5546,
"step": 187
},
{
"epoch": 1.88,
"learning_rate": 8.58023151621875e-05,
"loss": 0.6804,
"step": 188
},
{
"epoch": 1.89,
"learning_rate": 8.564044522734147e-05,
"loss": 1.1012,
"step": 189
},
{
"epoch": 1.9,
"learning_rate": 8.54778123311372e-05,
"loss": 0.9811,
"step": 190
},
{
"epoch": 1.91,
"learning_rate": 8.531441995508609e-05,
"loss": 0.3721,
"step": 191
},
{
"epoch": 1.92,
"learning_rate": 8.515027159695781e-05,
"loss": 0.3462,
"step": 192
},
{
"epoch": 1.93,
"learning_rate": 8.498537077070548e-05,
"loss": 0.4875,
"step": 193
},
{
"epoch": 1.94,
"learning_rate": 8.481972100639049e-05,
"loss": 0.9236,
"step": 194
},
{
"epoch": 1.95,
"learning_rate": 8.465332585010682e-05,
"loss": 0.036,
"step": 195
},
{
"epoch": 1.96,
"learning_rate": 8.448618886390522e-05,
"loss": 0.8321,
"step": 196
},
{
"epoch": 1.97,
"learning_rate": 8.431831362571691e-05,
"loss": 1.1929,
"step": 197
},
{
"epoch": 1.98,
"learning_rate": 8.414970372927704e-05,
"loss": 1.2032,
"step": 198
},
{
"epoch": 1.99,
"learning_rate": 8.398036278404767e-05,
"loss": 0.0115,
"step": 199
},
{
"epoch": 2.0,
"learning_rate": 8.38102944151406e-05,
"loss": 1.0193,
"step": 200
},
{
"epoch": 2.01,
"learning_rate": 8.363950226323963e-05,
"loss": 0.6684,
"step": 201
},
{
"epoch": 2.02,
"learning_rate": 8.346798998452282e-05,
"loss": 0.6883,
"step": 202
},
{
"epoch": 2.03,
"learning_rate": 8.329576125058406e-05,
"loss": 0.8697,
"step": 203
},
{
"epoch": 2.04,
"learning_rate": 8.312281974835452e-05,
"loss": 0.7854,
"step": 204
},
{
"epoch": 2.05,
"learning_rate": 8.294916918002376e-05,
"loss": 0.8573,
"step": 205
},
{
"epoch": 2.06,
"learning_rate": 8.277481326296038e-05,
"loss": 0.1149,
"step": 206
},
{
"epoch": 2.07,
"learning_rate": 8.259975572963257e-05,
"loss": 0.9545,
"step": 207
},
{
"epoch": 2.08,
"learning_rate": 8.242400032752813e-05,
"loss": 0.7834,
"step": 208
},
{
"epoch": 2.09,
"learning_rate": 8.224755081907427e-05,
"loss": 0.7207,
"step": 209
},
{
"epoch": 2.1,
"learning_rate": 8.2070410981557e-05,
"loss": 0.4601,
"step": 210
},
{
"epoch": 2.11,
"learning_rate": 8.189258460704038e-05,
"loss": 0.8886,
"step": 211
},
{
"epoch": 2.12,
"learning_rate": 8.171407550228532e-05,
"loss": 0.4563,
"step": 212
},
{
"epoch": 2.13,
"learning_rate": 8.153488748866796e-05,
"loss": 1.0037,
"step": 213
},
{
"epoch": 2.14,
"learning_rate": 8.135502440209804e-05,
"loss": 0.8796,
"step": 214
},
{
"epoch": 2.15,
"learning_rate": 8.117449009293668e-05,
"loss": 0.0385,
"step": 215
},
{
"epoch": 2.16,
"learning_rate": 8.0993288425914e-05,
"loss": 0.8037,
"step": 216
},
{
"epoch": 2.17,
"learning_rate": 8.081142328004637e-05,
"loss": 0.7149,
"step": 217
},
{
"epoch": 2.18,
"learning_rate": 8.062889854855333e-05,
"loss": 1.0,
"step": 218
},
{
"epoch": 2.19,
"learning_rate": 8.044571813877431e-05,
"loss": 0.4931,
"step": 219
},
{
"epoch": 2.2,
"learning_rate": 8.0261885972085e-05,
"loss": 1.2229,
"step": 220
},
{
"epoch": 2.21,
"learning_rate": 8.00774059838133e-05,
"loss": 1.0206,
"step": 221
},
{
"epoch": 2.22,
"learning_rate": 7.989228212315516e-05,
"loss": 0.4281,
"step": 222
},
{
"epoch": 2.23,
"learning_rate": 7.970651835309009e-05,
"loss": 0.325,
"step": 223
},
{
"epoch": 2.24,
"learning_rate": 7.952011865029614e-05,
"loss": 0.4511,
"step": 224
},
{
"epoch": 2.25,
"learning_rate": 7.933308700506497e-05,
"loss": 1.0534,
"step": 225
},
{
"epoch": 2.26,
"learning_rate": 7.914542742121633e-05,
"loss": 1.0809,
"step": 226
},
{
"epoch": 2.27,
"learning_rate": 7.895714391601232e-05,
"loss": 0.7914,
"step": 227
},
{
"epoch": 2.28,
"learning_rate": 7.876824052007149e-05,
"loss": 0.4348,
"step": 228
},
{
"epoch": 2.29,
"learning_rate": 7.857872127728248e-05,
"loss": 0.9297,
"step": 229
},
{
"epoch": 2.3,
"learning_rate": 7.838859024471748e-05,
"loss": 0.0606,
"step": 230
},
{
"epoch": 2.31,
"learning_rate": 7.819785149254532e-05,
"loss": 0.4665,
"step": 231
},
{
"epoch": 2.32,
"learning_rate": 7.800650910394449e-05,
"loss": 0.4669,
"step": 232
},
{
"epoch": 2.33,
"learning_rate": 7.781456717501557e-05,
"loss": 0.9979,
"step": 233
},
{
"epoch": 2.34,
"learning_rate": 7.762202981469357e-05,
"loss": 0.376,
"step": 234
},
{
"epoch": 2.35,
"learning_rate": 7.74289011446601e-05,
"loss": 1.0115,
"step": 235
},
{
"epoch": 2.36,
"learning_rate": 7.7235185299255e-05,
"loss": 0.3465,
"step": 236
},
{
"epoch": 2.37,
"learning_rate": 7.704088642538782e-05,
"loss": 0.6312,
"step": 237
},
{
"epoch": 2.38,
"learning_rate": 7.68460086824492e-05,
"loss": 1.0788,
"step": 238
},
{
"epoch": 2.39,
"learning_rate": 7.665055624222166e-05,
"loss": 0.8243,
"step": 239
},
{
"epoch": 2.4,
"learning_rate": 7.645453328879042e-05,
"loss": 0.6284,
"step": 240
},
{
"epoch": 2.41,
"learning_rate": 7.625794401845377e-05,
"loss": 0.5828,
"step": 241
},
{
"epoch": 2.42,
"learning_rate": 7.606079263963317e-05,
"loss": 0.331,
"step": 242
},
{
"epoch": 2.43,
"learning_rate": 7.586308337278336e-05,
"loss": 0.8812,
"step": 243
},
{
"epoch": 2.44,
"learning_rate": 7.566482045030179e-05,
"loss": 0.4332,
"step": 244
},
{
"epoch": 2.45,
"learning_rate": 7.546600811643816e-05,
"loss": 0.0149,
"step": 245
},
{
"epoch": 2.46,
"learning_rate": 7.52666506272035e-05,
"loss": 0.4849,
"step": 246
},
{
"epoch": 2.47,
"learning_rate": 7.50667522502791e-05,
"loss": 0.5015,
"step": 247
},
{
"epoch": 2.48,
"learning_rate": 7.486631726492512e-05,
"loss": 0.8306,
"step": 248
},
{
"epoch": 2.49,
"learning_rate": 7.466534996188897e-05,
"loss": 0.3214,
"step": 249
},
{
"epoch": 2.5,
"learning_rate": 7.446385464331348e-05,
"loss": 0.8702,
"step": 250
},
{
"epoch": 2.51,
"learning_rate": 7.426183562264488e-05,
"loss": 1.0255,
"step": 251
},
{
"epoch": 2.52,
"learning_rate": 7.405929722454026e-05,
"loss": 0.3734,
"step": 252
},
{
"epoch": 2.53,
"learning_rate": 7.385624378477521e-05,
"loss": 0.4999,
"step": 253
},
{
"epoch": 2.54,
"learning_rate": 7.365267965015086e-05,
"loss": 0.0178,
"step": 254
},
{
"epoch": 2.55,
"learning_rate": 7.344860917840091e-05,
"loss": 0.4426,
"step": 255
},
{
"epoch": 2.56,
"learning_rate": 7.324403673809831e-05,
"loss": 0.8835,
"step": 256
},
{
"epoch": 2.57,
"learning_rate": 7.303896670856167e-05,
"loss": 1.0596,
"step": 257
},
{
"epoch": 2.58,
"learning_rate": 7.283340347976166e-05,
"loss": 0.3448,
"step": 258
},
{
"epoch": 2.59,
"learning_rate": 7.262735145222696e-05,
"loss": 0.7635,
"step": 259
},
{
"epoch": 2.6,
"learning_rate": 7.242081503694995e-05,
"loss": 0.5643,
"step": 260
},
{
"epoch": 2.61,
"learning_rate": 7.22137986552925e-05,
"loss": 0.4274,
"step": 261
},
{
"epoch": 2.62,
"learning_rate": 7.200630673889117e-05,
"loss": 0.891,
"step": 262
},
{
"epoch": 2.63,
"learning_rate": 7.179834372956236e-05,
"loss": 0.6576,
"step": 263
},
{
"epoch": 2.64,
"learning_rate": 7.15899140792072e-05,
"loss": 0.9658,
"step": 264
},
{
"epoch": 2.65,
"learning_rate": 7.13810222497164e-05,
"loss": 0.6069,
"step": 265
},
{
"epoch": 2.66,
"learning_rate": 7.117167271287453e-05,
"loss": 0.6643,
"step": 266
},
{
"epoch": 2.67,
"learning_rate": 7.096186995026439e-05,
"loss": 0.0542,
"step": 267
},
{
"epoch": 2.68,
"learning_rate": 7.07516184531711e-05,
"loss": 0.7741,
"step": 268
},
{
"epoch": 2.69,
"learning_rate": 7.054092272248589e-05,
"loss": 0.3555,
"step": 269
},
{
"epoch": 2.7,
"learning_rate": 7.032978726860981e-05,
"loss": 0.9497,
"step": 270
},
{
"epoch": 2.71,
"learning_rate": 7.011821661135713e-05,
"loss": 0.5577,
"step": 271
},
{
"epoch": 2.72,
"learning_rate": 6.990621527985856e-05,
"loss": 0.0196,
"step": 272
},
{
"epoch": 2.73,
"learning_rate": 6.969378781246436e-05,
"loss": 1.0745,
"step": 273
},
{
"epoch": 2.74,
"learning_rate": 6.948093875664718e-05,
"loss": 0.3507,
"step": 274
},
{
"epoch": 2.75,
"learning_rate": 6.926767266890465e-05,
"loss": 0.9456,
"step": 275
},
{
"epoch": 2.76,
"learning_rate": 6.905399411466189e-05,
"loss": 0.4501,
"step": 276
},
{
"epoch": 2.77,
"learning_rate": 6.883990766817377e-05,
"loss": 0.9141,
"step": 277
},
{
"epoch": 2.78,
"learning_rate": 6.862541791242698e-05,
"loss": 0.7734,
"step": 278
},
{
"epoch": 2.79,
"learning_rate": 6.84105294390419e-05,
"loss": 0.7568,
"step": 279
},
{
"epoch": 2.8,
"learning_rate": 6.819524684817438e-05,
"loss": 0.909,
"step": 280
},
{
"epoch": 2.81,
"learning_rate": 6.797957474841716e-05,
"loss": 0.7132,
"step": 281
},
{
"epoch": 2.82,
"learning_rate": 6.776351775670129e-05,
"loss": 0.9626,
"step": 282
},
{
"epoch": 2.83,
"learning_rate": 6.754708049819728e-05,
"loss": 0.9361,
"step": 283
},
{
"epoch": 2.84,
"learning_rate": 6.733026760621607e-05,
"loss": 0.9124,
"step": 284
},
{
"epoch": 2.85,
"learning_rate": 6.711308372210983e-05,
"loss": 0.4468,
"step": 285
},
{
"epoch": 2.86,
"learning_rate": 6.689553349517268e-05,
"loss": 0.4842,
"step": 286
},
{
"epoch": 2.87,
"learning_rate": 6.667762158254104e-05,
"loss": 0.663,
"step": 287
},
{
"epoch": 2.88,
"learning_rate": 6.645935264909404e-05,
"loss": 0.9251,
"step": 288
},
{
"epoch": 2.89,
"learning_rate": 6.624073136735363e-05,
"loss": 0.7312,
"step": 289
},
{
"epoch": 2.9,
"learning_rate": 6.602176241738449e-05,
"loss": 0.9433,
"step": 290
},
{
"epoch": 2.91,
"learning_rate": 6.580245048669395e-05,
"loss": 0.0984,
"step": 291
},
{
"epoch": 2.92,
"learning_rate": 6.558280027013154e-05,
"loss": 1.0314,
"step": 292
},
{
"epoch": 2.93,
"learning_rate": 6.536281646978862e-05,
"loss": 0.8026,
"step": 293
},
{
"epoch": 2.94,
"learning_rate": 6.514250379489753e-05,
"loss": 0.1717,
"step": 294
},
{
"epoch": 2.95,
"learning_rate": 6.492186696173097e-05,
"loss": 0.054,
"step": 295
},
{
"epoch": 2.96,
"learning_rate": 6.47009106935009e-05,
"loss": 0.0319,
"step": 296
},
{
"epoch": 2.97,
"learning_rate": 6.447963972025751e-05,
"loss": 0.7367,
"step": 297
},
{
"epoch": 2.98,
"learning_rate": 6.425805877878793e-05,
"loss": 0.4738,
"step": 298
},
{
"epoch": 2.99,
"learning_rate": 6.403617261251484e-05,
"loss": 0.6486,
"step": 299
},
{
"epoch": 3.0,
"learning_rate": 6.381398597139492e-05,
"loss": 0.8341,
"step": 300
},
{
"epoch": 3.01,
"learning_rate": 6.359150361181715e-05,
"loss": 0.6808,
"step": 301
},
{
"epoch": 3.02,
"learning_rate": 6.336873029650104e-05,
"loss": 0.7224,
"step": 302
},
{
"epoch": 3.03,
"learning_rate": 6.314567079439459e-05,
"loss": 0.4141,
"step": 303
},
{
"epoch": 3.04,
"learning_rate": 6.292232988057235e-05,
"loss": 0.549,
"step": 304
},
{
"epoch": 3.05,
"learning_rate": 6.269871233613301e-05,
"loss": 0.0144,
"step": 305
},
{
"epoch": 3.06,
"learning_rate": 6.247482294809712e-05,
"loss": 0.8906,
"step": 306
},
{
"epoch": 3.07,
"learning_rate": 6.225066650930476e-05,
"loss": 0.3686,
"step": 307
},
{
"epoch": 3.08,
"learning_rate": 6.202624781831268e-05,
"loss": 0.2347,
"step": 308
},
{
"epoch": 3.09,
"learning_rate": 6.18015716792918e-05,
"loss": 0.7818,
"step": 309
},
{
"epoch": 3.1,
"learning_rate": 6.157664290192421e-05,
"loss": 0.5047,
"step": 310
},
{
"epoch": 3.11,
"learning_rate": 6.135146630130034e-05,
"loss": 0.8547,
"step": 311
},
{
"epoch": 3.12,
"learning_rate": 6.112604669781572e-05,
"loss": 0.7416,
"step": 312
},
{
"epoch": 3.13,
"learning_rate": 6.090038891706801e-05,
"loss": 0.5756,
"step": 313
},
{
"epoch": 3.14,
"learning_rate": 6.067449778975349e-05,
"loss": 0.3602,
"step": 314
},
{
"epoch": 3.15,
"learning_rate": 6.044837815156377e-05,
"loss": 0.7834,
"step": 315
},
{
"epoch": 3.16,
"learning_rate": 6.022203484308216e-05,
"loss": 0.4475,
"step": 316
},
{
"epoch": 3.17,
"learning_rate": 5.9995472709680234e-05,
"loss": 0.5393,
"step": 317
},
{
"epoch": 3.18,
"learning_rate": 5.976869660141389e-05,
"loss": 0.4159,
"step": 318
},
{
"epoch": 3.19,
"learning_rate": 5.954171137291968e-05,
"loss": 0.0905,
"step": 319
},
{
"epoch": 3.2,
"learning_rate": 5.931452188331083e-05,
"loss": 0.3343,
"step": 320
},
{
"epoch": 3.21,
"learning_rate": 5.908713299607318e-05,
"loss": 0.4226,
"step": 321
},
{
"epoch": 3.22,
"learning_rate": 5.885954957896115e-05,
"loss": 0.6134,
"step": 322
},
{
"epoch": 3.23,
"learning_rate": 5.863177650389347e-05,
"loss": 0.2971,
"step": 323
},
{
"epoch": 3.24,
"learning_rate": 5.8403818646848915e-05,
"loss": 0.6429,
"step": 324
},
{
"epoch": 3.25,
"learning_rate": 5.8175680887761955e-05,
"loss": 0.5874,
"step": 325
},
{
"epoch": 3.26,
"learning_rate": 5.794736811041821e-05,
"loss": 0.3562,
"step": 326
},
{
"epoch": 3.27,
"learning_rate": 5.771888520234997e-05,
"loss": 0.3763,
"step": 327
},
{
"epoch": 3.28,
"learning_rate": 5.749023705473153e-05,
"loss": 0.4824,
"step": 328
},
{
"epoch": 3.29,
"learning_rate": 5.726142856227452e-05,
"loss": 0.595,
"step": 329
},
{
"epoch": 3.3,
"learning_rate": 5.703246462312307e-05,
"loss": 0.5615,
"step": 330
},
{
"epoch": 3.31,
"learning_rate": 5.6803350138749034e-05,
"loss": 0.4391,
"step": 331
},
{
"epoch": 3.32,
"learning_rate": 5.6574090013846946e-05,
"loss": 0.9026,
"step": 332
},
{
"epoch": 3.33,
"learning_rate": 5.634468915622915e-05,
"loss": 0.0241,
"step": 333
},
{
"epoch": 3.34,
"learning_rate": 5.6115152476720635e-05,
"loss": 0.7012,
"step": 334
},
{
"epoch": 3.35,
"learning_rate": 5.5885484889054016e-05,
"loss": 0.7037,
"step": 335
},
{
"epoch": 3.36,
"learning_rate": 5.565569130976422e-05,
"loss": 0.4188,
"step": 336
},
{
"epoch": 3.37,
"learning_rate": 5.542577665808332e-05,
"loss": 0.3808,
"step": 337
},
{
"epoch": 3.38,
"learning_rate": 5.5195745855835226e-05,
"loss": 0.8797,
"step": 338
},
{
"epoch": 3.39,
"learning_rate": 5.496560382733028e-05,
"loss": 0.2011,
"step": 339
},
{
"epoch": 3.4,
"learning_rate": 5.4735355499259855e-05,
"loss": 0.7986,
"step": 340
},
{
"epoch": 3.41,
"learning_rate": 5.4505005800590945e-05,
"loss": 0.5735,
"step": 341
},
{
"epoch": 3.42,
"learning_rate": 5.427455966246057e-05,
"loss": 0.8255,
"step": 342
},
{
"epoch": 3.43,
"learning_rate": 5.4044022018070214e-05,
"loss": 0.9377,
"step": 343
},
{
"epoch": 3.44,
"learning_rate": 5.3813397802580334e-05,
"loss": 0.5552,
"step": 344
},
{
"epoch": 3.45,
"learning_rate": 5.358269195300454e-05,
"loss": 0.7921,
"step": 345
},
{
"epoch": 3.46,
"learning_rate": 5.335190940810407e-05,
"loss": 0.3424,
"step": 346
},
{
"epoch": 3.47,
"learning_rate": 5.312105510828196e-05,
"loss": 0.6281,
"step": 347
},
{
"epoch": 3.48,
"learning_rate": 5.289013399547732e-05,
"loss": 0.7099,
"step": 348
},
{
"epoch": 3.49,
"learning_rate": 5.265915101305952e-05,
"loss": 0.694,
"step": 349
},
{
"epoch": 3.5,
"learning_rate": 5.242811110572242e-05,
"loss": 0.2422,
"step": 350
},
{
"epoch": 3.51,
"learning_rate": 5.219701921937845e-05,
"loss": 0.2857,
"step": 351
},
{
"epoch": 3.52,
"learning_rate": 5.1965880301052784e-05,
"loss": 0.7273,
"step": 352
},
{
"epoch": 3.53,
"learning_rate": 5.17346992987774e-05,
"loss": 0.3574,
"step": 353
},
{
"epoch": 3.54,
"learning_rate": 5.15034811614852e-05,
"loss": 0.6972,
"step": 354
},
{
"epoch": 3.55,
"learning_rate": 5.1272230838904015e-05,
"loss": 0.6574,
"step": 355
},
{
"epoch": 3.56,
"learning_rate": 5.1040953281450684e-05,
"loss": 0.6237,
"step": 356
},
{
"epoch": 3.57,
"learning_rate": 5.080965344012508e-05,
"loss": 0.7119,
"step": 357
},
{
"epoch": 3.58,
"learning_rate": 5.057833626640408e-05,
"loss": 0.4174,
"step": 358
},
{
"epoch": 3.59,
"learning_rate": 5.0347006712135646e-05,
"loss": 0.7423,
"step": 359
},
{
"epoch": 3.6,
"learning_rate": 5.011566972943272e-05,
"loss": 0.5093,
"step": 360
},
{
"epoch": 3.61,
"learning_rate": 4.988433027056729e-05,
"loss": 0.4895,
"step": 361
},
{
"epoch": 3.62,
"learning_rate": 4.9652993287864365e-05,
"loss": 0.6984,
"step": 362
},
{
"epoch": 3.63,
"learning_rate": 4.942166373359593e-05,
"loss": 0.9807,
"step": 363
},
{
"epoch": 3.64,
"learning_rate": 4.919034655987493e-05,
"loss": 0.1413,
"step": 364
},
{
"epoch": 3.65,
"learning_rate": 4.895904671854933e-05,
"loss": 0.7832,
"step": 365
},
{
"epoch": 3.66,
"learning_rate": 4.872776916109601e-05,
"loss": 0.957,
"step": 366
},
{
"epoch": 3.67,
"learning_rate": 4.849651883851481e-05,
"loss": 0.0125,
"step": 367
},
{
"epoch": 3.68,
"learning_rate": 4.826530070122262e-05,
"loss": 0.5204,
"step": 368
},
{
"epoch": 3.69,
"learning_rate": 4.803411969894724e-05,
"loss": 0.9596,
"step": 369
},
{
"epoch": 3.7,
"learning_rate": 4.780298078062157e-05,
"loss": 0.4714,
"step": 370
},
{
"epoch": 3.71,
"learning_rate": 4.7571888894277604e-05,
"loss": 0.5038,
"step": 371
},
{
"epoch": 3.72,
"learning_rate": 4.7340848986940487e-05,
"loss": 0.8625,
"step": 372
},
{
"epoch": 3.73,
"learning_rate": 4.710986600452269e-05,
"loss": 0.865,
"step": 373
},
{
"epoch": 3.74,
"learning_rate": 4.687894489171804e-05,
"loss": 0.3526,
"step": 374
},
{
"epoch": 3.75,
"learning_rate": 4.6648090591895935e-05,
"loss": 0.2742,
"step": 375
},
{
"epoch": 3.76,
"learning_rate": 4.641730804699547e-05,
"loss": 0.5781,
"step": 376
},
{
"epoch": 3.77,
"learning_rate": 4.6186602197419685e-05,
"loss": 0.7607,
"step": 377
},
{
"epoch": 3.78,
"learning_rate": 4.59559779819298e-05,
"loss": 0.8003,
"step": 378
},
{
"epoch": 3.79,
"learning_rate": 4.572544033753945e-05,
"loss": 0.4204,
"step": 379
},
{
"epoch": 3.8,
"learning_rate": 4.5494994199409067e-05,
"loss": 0.3505,
"step": 380
},
{
"epoch": 3.81,
"learning_rate": 4.5264644500740156e-05,
"loss": 0.3341,
"step": 381
},
{
"epoch": 3.82,
"learning_rate": 4.503439617266973e-05,
"loss": 0.2664,
"step": 382
},
{
"epoch": 3.83,
"learning_rate": 4.4804254144164785e-05,
"loss": 0.0007,
"step": 383
},
{
"epoch": 3.84,
"learning_rate": 4.4574223341916695e-05,
"loss": 0.1969,
"step": 384
},
{
"epoch": 3.85,
"learning_rate": 4.434430869023579e-05,
"loss": 0.795,
"step": 385
},
{
"epoch": 3.86,
"learning_rate": 4.4114515110945995e-05,
"loss": 0.716,
"step": 386
},
{
"epoch": 3.87,
"learning_rate": 4.3884847523279376e-05,
"loss": 0.4021,
"step": 387
},
{
"epoch": 3.88,
"learning_rate": 4.365531084377087e-05,
"loss": 0.7047,
"step": 388
},
{
"epoch": 3.89,
"learning_rate": 4.342590998615307e-05,
"loss": 0.4303,
"step": 389
},
{
"epoch": 3.9,
"learning_rate": 4.319664986125099e-05,
"loss": 0.3186,
"step": 390
},
{
"epoch": 3.91,
"learning_rate": 4.2967535376876936e-05,
"loss": 0.0043,
"step": 391
},
{
"epoch": 3.92,
"learning_rate": 4.27385714377255e-05,
"loss": 0.8166,
"step": 392
},
{
"epoch": 3.93,
"learning_rate": 4.2509762945268474e-05,
"loss": 0.2863,
"step": 393
},
{
"epoch": 3.94,
"learning_rate": 4.228111479765004e-05,
"loss": 0.8721,
"step": 394
},
{
"epoch": 3.95,
"learning_rate": 4.205263188958179e-05,
"loss": 0.0029,
"step": 395
},
{
"epoch": 3.96,
"learning_rate": 4.182431911223805e-05,
"loss": 0.361,
"step": 396
},
{
"epoch": 3.97,
"learning_rate": 4.159618135315109e-05,
"loss": 0.9149,
"step": 397
},
{
"epoch": 3.98,
"learning_rate": 4.136822349610654e-05,
"loss": 0.2188,
"step": 398
},
{
"epoch": 3.99,
"learning_rate": 4.114045042103887e-05,
"loss": 0.7136,
"step": 399
},
{
"epoch": 4.0,
"learning_rate": 4.0912867003926834e-05,
"loss": 0.7188,
"step": 400
},
{
"epoch": 4.01,
"learning_rate": 4.068547811668918e-05,
"loss": 0.2834,
"step": 401
},
{
"epoch": 4.02,
"learning_rate": 4.045828862708032e-05,
"loss": 0.2911,
"step": 402
},
{
"epoch": 4.03,
"learning_rate": 4.023130339858612e-05,
"loss": 0.4027,
"step": 403
},
{
"epoch": 4.04,
"learning_rate": 4.0004527290319784e-05,
"loss": 0.6534,
"step": 404
},
{
"epoch": 4.05,
"learning_rate": 3.977796515691785e-05,
"loss": 0.3707,
"step": 405
},
{
"epoch": 4.06,
"learning_rate": 3.955162184843625e-05,
"loss": 0.818,
"step": 406
},
{
"epoch": 4.07,
"learning_rate": 3.9325502210246514e-05,
"loss": 0.5838,
"step": 407
},
{
"epoch": 4.08,
"learning_rate": 3.9099611082932e-05,
"loss": 0.2727,
"step": 408
},
{
"epoch": 4.09,
"learning_rate": 3.887395330218429e-05,
"loss": 0.9802,
"step": 409
},
{
"epoch": 4.1,
"learning_rate": 3.8648533698699695e-05,
"loss": 0.6162,
"step": 410
},
{
"epoch": 4.11,
"learning_rate": 3.8423357098075815e-05,
"loss": 0.2528,
"step": 411
},
{
"epoch": 4.12,
"learning_rate": 3.8198428320708216e-05,
"loss": 0.6246,
"step": 412
},
{
"epoch": 4.13,
"learning_rate": 3.7973752181687335e-05,
"loss": 0.4011,
"step": 413
},
{
"epoch": 4.14,
"learning_rate": 3.774933349069524e-05,
"loss": 0.3105,
"step": 414
},
{
"epoch": 4.15,
"learning_rate": 3.7525177051902874e-05,
"loss": 0.5954,
"step": 415
},
{
"epoch": 4.16,
"learning_rate": 3.7301287663867005e-05,
"loss": 0.5291,
"step": 416
},
{
"epoch": 4.17,
"learning_rate": 3.7077670119427645e-05,
"loss": 0.24,
"step": 417
},
{
"epoch": 4.18,
"learning_rate": 3.68543292056054e-05,
"loss": 0.3224,
"step": 418
},
{
"epoch": 4.19,
"learning_rate": 3.663126970349897e-05,
"loss": 0.4368,
"step": 419
},
{
"epoch": 4.2,
"learning_rate": 3.640849638818286e-05,
"loss": 0.5847,
"step": 420
},
{
"epoch": 4.21,
"learning_rate": 3.6186014028605096e-05,
"loss": 0.55,
"step": 421
},
{
"epoch": 4.22,
"learning_rate": 3.596382738748516e-05,
"loss": 0.7909,
"step": 422
},
{
"epoch": 4.23,
"learning_rate": 3.574194122121207e-05,
"loss": 0.7457,
"step": 423
},
{
"epoch": 4.24,
"learning_rate": 3.55203602797425e-05,
"loss": 0.6966,
"step": 424
},
{
"epoch": 4.25,
"learning_rate": 3.52990893064991e-05,
"loss": 0.3457,
"step": 425
},
{
"epoch": 4.26,
"learning_rate": 3.507813303826903e-05,
"loss": 0.5137,
"step": 426
},
{
"epoch": 4.27,
"learning_rate": 3.4857496205102474e-05,
"loss": 0.8169,
"step": 427
},
{
"epoch": 4.28,
"learning_rate": 3.463718353021138e-05,
"loss": 0.3222,
"step": 428
},
{
"epoch": 4.29,
"learning_rate": 3.441719972986846e-05,
"loss": 0.3728,
"step": 429
},
{
"epoch": 4.3,
"learning_rate": 3.419754951330608e-05,
"loss": 0.5675,
"step": 430
},
{
"epoch": 4.31,
"learning_rate": 3.397823758261553e-05,
"loss": 0.3658,
"step": 431
},
{
"epoch": 4.32,
"learning_rate": 3.37592686326464e-05,
"loss": 0.6603,
"step": 432
},
{
"epoch": 4.33,
"learning_rate": 3.354064735090599e-05,
"loss": 0.4974,
"step": 433
},
{
"epoch": 4.34,
"learning_rate": 3.332237841745898e-05,
"loss": 0.1962,
"step": 434
},
{
"epoch": 4.35,
"learning_rate": 3.310446650482732e-05,
"loss": 0.2256,
"step": 435
},
{
"epoch": 4.36,
"learning_rate": 3.288691627789017e-05,
"loss": 0.2978,
"step": 436
},
{
"epoch": 4.37,
"learning_rate": 3.266973239378394e-05,
"loss": 0.5792,
"step": 437
},
{
"epoch": 4.38,
"learning_rate": 3.2452919501802715e-05,
"loss": 0.468,
"step": 438
},
{
"epoch": 4.39,
"learning_rate": 3.2236482243298714e-05,
"loss": 0.2519,
"step": 439
},
{
"epoch": 4.4,
"learning_rate": 3.2020425251582844e-05,
"loss": 0.7188,
"step": 440
},
{
"epoch": 4.41,
"learning_rate": 3.180475315182563e-05,
"loss": 0.3078,
"step": 441
},
{
"epoch": 4.42,
"learning_rate": 3.1589470560958104e-05,
"loss": 0.6103,
"step": 442
},
{
"epoch": 4.43,
"learning_rate": 3.137458208757302e-05,
"loss": 0.686,
"step": 443
},
{
"epoch": 4.44,
"learning_rate": 3.116009233182623e-05,
"loss": 0.3806,
"step": 444
},
{
"epoch": 4.45,
"learning_rate": 3.0946005885338113e-05,
"loss": 0.1448,
"step": 445
},
{
"epoch": 4.46,
"learning_rate": 3.073232733109536e-05,
"loss": 0.5645,
"step": 446
},
{
"epoch": 4.47,
"learning_rate": 3.0519061243352834e-05,
"loss": 0.1435,
"step": 447
},
{
"epoch": 4.48,
"learning_rate": 3.0306212187535653e-05,
"loss": 0.477,
"step": 448
},
{
"epoch": 4.49,
"learning_rate": 3.0093784720141455e-05,
"loss": 0.4546,
"step": 449
},
{
"epoch": 4.5,
"learning_rate": 2.9881783388642893e-05,
"loss": 0.7156,
"step": 450
},
{
"epoch": 4.51,
"learning_rate": 2.96702127313902e-05,
"loss": 0.3016,
"step": 451
},
{
"epoch": 4.52,
"learning_rate": 2.945907727751412e-05,
"loss": 0.3981,
"step": 452
},
{
"epoch": 4.53,
"learning_rate": 2.924838154682893e-05,
"loss": 0.4881,
"step": 453
},
{
"epoch": 4.54,
"learning_rate": 2.9038130049735634e-05,
"loss": 0.4777,
"step": 454
},
{
"epoch": 4.55,
"learning_rate": 2.882832728712551e-05,
"loss": 0.4819,
"step": 455
},
{
"epoch": 4.56,
"learning_rate": 2.8618977750283603e-05,
"loss": 0.6737,
"step": 456
},
{
"epoch": 4.57,
"learning_rate": 2.8410085920792807e-05,
"loss": 0.5443,
"step": 457
},
{
"epoch": 4.58,
"learning_rate": 2.8201656270437658e-05,
"loss": 0.4713,
"step": 458
},
{
"epoch": 4.59,
"learning_rate": 2.7993693261108823e-05,
"loss": 0.3005,
"step": 459
},
{
"epoch": 4.6,
"learning_rate": 2.7786201344707486e-05,
"loss": 0.3711,
"step": 460
},
{
"epoch": 4.61,
"learning_rate": 2.7579184963050052e-05,
"loss": 0.1466,
"step": 461
},
{
"epoch": 4.62,
"learning_rate": 2.737264854777306e-05,
"loss": 0.312,
"step": 462
},
{
"epoch": 4.63,
"learning_rate": 2.716659652023833e-05,
"loss": 0.4356,
"step": 463
},
{
"epoch": 4.64,
"learning_rate": 2.6961033291438343e-05,
"loss": 0.3489,
"step": 464
},
{
"epoch": 4.65,
"learning_rate": 2.6755963261901708e-05,
"loss": 0.2129,
"step": 465
},
{
"epoch": 4.66,
"learning_rate": 2.6551390821599076e-05,
"loss": 0.4563,
"step": 466
},
{
"epoch": 4.67,
"learning_rate": 2.6347320349849146e-05,
"loss": 0.6174,
"step": 467
},
{
"epoch": 4.68,
"learning_rate": 2.6143756215224802e-05,
"loss": 0.4202,
"step": 468
},
{
"epoch": 4.69,
"learning_rate": 2.5940702775459747e-05,
"loss": 0.2551,
"step": 469
},
{
"epoch": 4.7,
"learning_rate": 2.5738164377355145e-05,
"loss": 0.4952,
"step": 470
},
{
"epoch": 4.71,
"learning_rate": 2.5536145356686524e-05,
"loss": 0.1808,
"step": 471
},
{
"epoch": 4.72,
"learning_rate": 2.5334650038111048e-05,
"loss": 0.6142,
"step": 472
},
{
"epoch": 4.73,
"learning_rate": 2.5133682735074904e-05,
"loss": 0.604,
"step": 473
},
{
"epoch": 4.74,
"learning_rate": 2.4933247749720912e-05,
"loss": 0.2581,
"step": 474
},
{
"epoch": 4.75,
"learning_rate": 2.4733349372796507e-05,
"loss": 0.5465,
"step": 475
},
{
"epoch": 4.76,
"learning_rate": 2.4533991883561868e-05,
"loss": 0.6839,
"step": 476
},
{
"epoch": 4.77,
"learning_rate": 2.4335179549698233e-05,
"loss": 0.3046,
"step": 477
},
{
"epoch": 4.78,
"learning_rate": 2.4136916627216655e-05,
"loss": 0.2704,
"step": 478
},
{
"epoch": 4.79,
"learning_rate": 2.3939207360366832e-05,
"loss": 0.6112,
"step": 479
},
{
"epoch": 4.8,
"learning_rate": 2.374205598154624e-05,
"loss": 0.6618,
"step": 480
},
{
"epoch": 4.81,
"learning_rate": 2.3545466711209585e-05,
"loss": 0.5694,
"step": 481
},
{
"epoch": 4.82,
"learning_rate": 2.3349443757778343e-05,
"loss": 0.6574,
"step": 482
},
{
"epoch": 4.83,
"learning_rate": 2.315399131755081e-05,
"loss": 0.4976,
"step": 483
},
{
"epoch": 4.84,
"learning_rate": 2.29591135746122e-05,
"loss": 0.043,
"step": 484
},
{
"epoch": 4.85,
"learning_rate": 2.2764814700745025e-05,
"loss": 0.245,
"step": 485
},
{
"epoch": 4.86,
"learning_rate": 2.25710988553399e-05,
"loss": 0.2813,
"step": 486
},
{
"epoch": 4.87,
"learning_rate": 2.2377970185306424e-05,
"loss": 0.5447,
"step": 487
},
{
"epoch": 4.88,
"learning_rate": 2.2185432824984453e-05,
"loss": 0.114,
"step": 488
},
{
"epoch": 4.89,
"learning_rate": 2.1993490896055512e-05,
"loss": 0.7998,
"step": 489
},
{
"epoch": 4.9,
"learning_rate": 2.180214850745467e-05,
"loss": 0.7277,
"step": 490
},
{
"epoch": 4.91,
"learning_rate": 2.161140975528254e-05,
"loss": 0.5846,
"step": 491
},
{
"epoch": 4.92,
"learning_rate": 2.1421278722717524e-05,
"loss": 0.5622,
"step": 492
},
{
"epoch": 4.93,
"learning_rate": 2.123175947992851e-05,
"loss": 0.2222,
"step": 493
},
{
"epoch": 4.94,
"learning_rate": 2.1042856083987695e-05,
"loss": 0.2649,
"step": 494
},
{
"epoch": 4.95,
"learning_rate": 2.0854572578783686e-05,
"loss": 0.2307,
"step": 495
},
{
"epoch": 4.96,
"learning_rate": 2.0666912994935034e-05,
"loss": 0.1544,
"step": 496
},
{
"epoch": 4.97,
"learning_rate": 2.0479881349703883e-05,
"loss": 0.3855,
"step": 497
},
{
"epoch": 4.98,
"learning_rate": 2.0293481646909934e-05,
"loss": 0.3163,
"step": 498
},
{
"epoch": 4.99,
"learning_rate": 2.0107717876844838e-05,
"loss": 0.5392,
"step": 499
},
{
"epoch": 5.0,
"learning_rate": 1.9922594016186713e-05,
"loss": 0.6052,
"step": 500
},
{
"epoch": 5.01,
"learning_rate": 1.9738114027915006e-05,
"loss": 0.5806,
"step": 501
},
{
"epoch": 5.02,
"learning_rate": 1.9554281861225694e-05,
"loss": 0.5953,
"step": 502
},
{
"epoch": 5.03,
"learning_rate": 1.937110145144668e-05,
"loss": 0.1115,
"step": 503
},
{
"epoch": 5.04,
"learning_rate": 1.9188576719953633e-05,
"loss": 0.221,
"step": 504
},
{
"epoch": 5.05,
"learning_rate": 1.9006711574086005e-05,
"loss": 0.1939,
"step": 505
},
{
"epoch": 5.06,
"learning_rate": 1.8825509907063327e-05,
"loss": 0.3278,
"step": 506
},
{
"epoch": 5.07,
"learning_rate": 1.8644975597901977e-05,
"loss": 0.4018,
"step": 507
},
{
"epoch": 5.08,
"learning_rate": 1.8465112511332065e-05,
"loss": 0.117,
"step": 508
},
{
"epoch": 5.09,
"learning_rate": 1.8285924497714703e-05,
"loss": 0.2117,
"step": 509
},
{
"epoch": 5.1,
"learning_rate": 1.8107415392959614e-05,
"loss": 0.3809,
"step": 510
},
{
"epoch": 5.11,
"learning_rate": 1.7929589018443016e-05,
"loss": 0.2844,
"step": 511
},
{
"epoch": 5.12,
"learning_rate": 1.7752449180925747e-05,
"loss": 0.148,
"step": 512
},
{
"epoch": 5.13,
"learning_rate": 1.7575999672471867e-05,
"loss": 0.4519,
"step": 513
},
{
"epoch": 5.14,
"learning_rate": 1.7400244270367428e-05,
"loss": 0.4638,
"step": 514
},
{
"epoch": 5.15,
"learning_rate": 1.7225186737039638e-05,
"loss": 0.3697,
"step": 515
},
{
"epoch": 5.16,
"learning_rate": 1.7050830819976267e-05,
"loss": 0.3685,
"step": 516
},
{
"epoch": 5.17,
"learning_rate": 1.6877180251645486e-05,
"loss": 0.4112,
"step": 517
},
{
"epoch": 5.18,
"learning_rate": 1.6704238749415957e-05,
"loss": 0.1764,
"step": 518
},
{
"epoch": 5.19,
"learning_rate": 1.653201001547719e-05,
"loss": 0.5628,
"step": 519
},
{
"epoch": 5.2,
"learning_rate": 1.6360497736760383e-05,
"loss": 0.3652,
"step": 520
},
{
"epoch": 5.21,
"learning_rate": 1.618970558485942e-05,
"loss": 0.4692,
"step": 521
},
{
"epoch": 5.22,
"learning_rate": 1.601963721595232e-05,
"loss": 0.1951,
"step": 522
},
{
"epoch": 5.23,
"learning_rate": 1.5850296270722964e-05,
"loss": 0.2395,
"step": 523
},
{
"epoch": 5.24,
"learning_rate": 1.5681686374283088e-05,
"loss": 0.3004,
"step": 524
},
{
"epoch": 5.25,
"learning_rate": 1.5513811136094787e-05,
"loss": 0.584,
"step": 525
},
{
"epoch": 5.26,
"learning_rate": 1.5346674149893202e-05,
"loss": 0.4504,
"step": 526
},
{
"epoch": 5.27,
"learning_rate": 1.5180278993609526e-05,
"loss": 0.2288,
"step": 527
},
{
"epoch": 5.28,
"learning_rate": 1.5014629229294524e-05,
"loss": 0.2076,
"step": 528
},
{
"epoch": 5.29,
"learning_rate": 1.4849728403042213e-05,
"loss": 0.1697,
"step": 529
},
{
"epoch": 5.3,
"learning_rate": 1.4685580044913921e-05,
"loss": 0.4365,
"step": 530
},
{
"epoch": 5.31,
"learning_rate": 1.4522187668862796e-05,
"loss": 0.4248,
"step": 531
},
{
"epoch": 5.32,
"learning_rate": 1.4359554772658552e-05,
"loss": 0.12,
"step": 532
},
{
"epoch": 5.33,
"learning_rate": 1.419768483781252e-05,
"loss": 0.3856,
"step": 533
},
{
"epoch": 5.34,
"learning_rate": 1.4036581329503245e-05,
"loss": 0.2775,
"step": 534
},
{
"epoch": 5.35,
"learning_rate": 1.3876247696502238e-05,
"loss": 0.4864,
"step": 535
},
{
"epoch": 5.36,
"learning_rate": 1.3716687371100096e-05,
"loss": 0.5636,
"step": 536
},
{
"epoch": 5.37,
"learning_rate": 1.3557903769033148e-05,
"loss": 0.0053,
"step": 537
},
{
"epoch": 5.38,
"learning_rate": 1.3399900289410245e-05,
"loss": 0.4416,
"step": 538
},
{
"epoch": 5.39,
"learning_rate": 1.3242680314639993e-05,
"loss": 0.5851,
"step": 539
},
{
"epoch": 5.4,
"learning_rate": 1.3086247210358398e-05,
"loss": 0.1134,
"step": 540
},
{
"epoch": 5.41,
"learning_rate": 1.2930604325356794e-05,
"loss": 0.092,
"step": 541
},
{
"epoch": 5.42,
"learning_rate": 1.277575499151013e-05,
"loss": 0.478,
"step": 542
},
{
"epoch": 5.43,
"learning_rate": 1.2621702523705676e-05,
"loss": 0.3503,
"step": 543
},
{
"epoch": 5.44,
"learning_rate": 1.2468450219772054e-05,
"loss": 0.1728,
"step": 544
},
{
"epoch": 5.45,
"learning_rate": 1.2316001360408614e-05,
"loss": 0.007,
"step": 545
},
{
"epoch": 5.46,
"learning_rate": 1.2164359209115234e-05,
"loss": 0.0939,
"step": 546
},
{
"epoch": 5.47,
"learning_rate": 1.2013527012122478e-05,
"loss": 0.5087,
"step": 547
},
{
"epoch": 5.48,
"learning_rate": 1.186350799832202e-05,
"loss": 0.2571,
"step": 548
},
{
"epoch": 5.49,
"learning_rate": 1.1714305379197615e-05,
"loss": 0.6024,
"step": 549
},
{
"epoch": 5.5,
"learning_rate": 1.1565922348756325e-05,
"loss": 0.3537,
"step": 550
},
{
"epoch": 5.51,
"learning_rate": 1.1418362083460066e-05,
"loss": 0.3272,
"step": 551
},
{
"epoch": 5.52,
"learning_rate": 1.1271627742157742e-05,
"loss": 0.0008,
"step": 552
},
{
"epoch": 5.53,
"learning_rate": 1.1125722466017547e-05,
"loss": 0.3474,
"step": 553
},
{
"epoch": 5.54,
"learning_rate": 1.0980649378459668e-05,
"loss": 0.4607,
"step": 554
},
{
"epoch": 5.55,
"learning_rate": 1.083641158508955e-05,
"loss": 0.3995,
"step": 555
},
{
"epoch": 5.56,
"learning_rate": 1.0693012173631344e-05,
"loss": 0.4744,
"step": 556
},
{
"epoch": 5.57,
"learning_rate": 1.055045421386175e-05,
"loss": 0.3983,
"step": 557
},
{
"epoch": 5.58,
"learning_rate": 1.0408740757544416e-05,
"loss": 0.5281,
"step": 558
},
{
"epoch": 5.59,
"learning_rate": 1.026787483836456e-05,
"loss": 0.5738,
"step": 559
},
{
"epoch": 5.6,
"learning_rate": 1.012785947186397e-05,
"loss": 0.6385,
"step": 560
},
{
"epoch": 5.61,
"learning_rate": 9.988697655376544e-06,
"loss": 0.3275,
"step": 561
},
{
"epoch": 5.62,
"learning_rate": 9.850392367964085e-06,
"loss": 0.0976,
"step": 562
},
{
"epoch": 5.63,
"learning_rate": 9.712946570352472e-06,
"loss": 0.0283,
"step": 563
},
{
"epoch": 5.64,
"learning_rate": 9.576363204868416e-06,
"loss": 0.138,
"step": 564
},
{
"epoch": 5.65,
"learning_rate": 9.44064519537634e-06,
"loss": 0.2264,
"step": 565
},
{
"epoch": 5.66,
"learning_rate": 9.305795447215827e-06,
"loss": 0.3201,
"step": 566
},
{
"epoch": 5.67,
"learning_rate": 9.171816847139448e-06,
"loss": 0.0013,
"step": 567
},
{
"epoch": 5.68,
"learning_rate": 9.03871226325098e-06,
"loss": 0.4852,
"step": 568
},
{
"epoch": 5.69,
"learning_rate": 8.906484544943932e-06,
"loss": 0.629,
"step": 569
},
{
"epoch": 5.7,
"learning_rate": 8.775136522840621e-06,
"loss": 0.0243,
"step": 570
},
{
"epoch": 5.71,
"learning_rate": 8.644671008731569e-06,
"loss": 0.6967,
"step": 571
},
{
"epoch": 5.72,
"learning_rate": 8.515090795515247e-06,
"loss": 0.4464,
"step": 572
},
{
"epoch": 5.73,
"learning_rate": 8.386398657138356e-06,
"loss": 0.1574,
"step": 573
},
{
"epoch": 5.74,
"learning_rate": 8.25859734853645e-06,
"loss": 0.2407,
"step": 574
},
{
"epoch": 5.75,
"learning_rate": 8.131689605574866e-06,
"loss": 0.3508,
"step": 575
},
{
"epoch": 5.76,
"learning_rate": 8.00567814499028e-06,
"loss": 0.279,
"step": 576
},
{
"epoch": 5.77,
"learning_rate": 7.880565664332474e-06,
"loss": 0.6613,
"step": 577
},
{
"epoch": 5.78,
"learning_rate": 7.756354841906582e-06,
"loss": 0.276,
"step": 578
},
{
"epoch": 5.79,
"learning_rate": 7.633048336715814e-06,
"loss": 0.4276,
"step": 579
},
{
"epoch": 5.8,
"learning_rate": 7.510648788404501e-06,
"loss": 0.7235,
"step": 580
},
{
"epoch": 5.81,
"learning_rate": 7.389158817201542e-06,
"loss": 0.5805,
"step": 581
},
{
"epoch": 5.82,
"learning_rate": 7.268581023864402e-06,
"loss": 0.0223,
"step": 582
},
{
"epoch": 5.83,
"learning_rate": 7.1489179896233885e-06,
"loss": 0.2231,
"step": 583
},
{
"epoch": 5.84,
"learning_rate": 7.030172276126351e-06,
"loss": 0.1097,
"step": 584
},
{
"epoch": 5.85,
"learning_rate": 6.912346425383964e-06,
"loss": 0.1279,
"step": 585
},
{
"epoch": 5.86,
"learning_rate": 6.795442959715192e-06,
"loss": 0.64,
"step": 586
},
{
"epoch": 5.87,
"learning_rate": 6.679464381693323e-06,
"loss": 0.5757,
"step": 587
},
{
"epoch": 5.88,
"learning_rate": 6.564413174092443e-06,
"loss": 0.2662,
"step": 588
},
{
"epoch": 5.89,
"learning_rate": 6.4502917998342575e-06,
"loss": 0.4304,
"step": 589
},
{
"epoch": 5.9,
"learning_rate": 6.337102701935321e-06,
"loss": 0.6495,
"step": 590
},
{
"epoch": 5.91,
"learning_rate": 6.2248483034548276e-06,
"loss": 0.5168,
"step": 591
},
{
"epoch": 5.92,
"learning_rate": 6.11353100744268e-06,
"loss": 0.2505,
"step": 592
},
{
"epoch": 5.93,
"learning_rate": 6.003153196888045e-06,
"loss": 0.3987,
"step": 593
},
{
"epoch": 5.94,
"learning_rate": 5.893717234668383e-06,
"loss": 0.556,
"step": 594
},
{
"epoch": 5.95,
"learning_rate": 5.785225463498828e-06,
"loss": 0.3442,
"step": 595
},
{
"epoch": 5.96,
"learning_rate": 5.67768020588203e-06,
"loss": 0.5206,
"step": 596
},
{
"epoch": 5.97,
"learning_rate": 5.571083764058482e-06,
"loss": 0.0007,
"step": 597
},
{
"epoch": 5.98,
"learning_rate": 5.465438419957208e-06,
"loss": 0.4368,
"step": 598
},
{
"epoch": 5.99,
"learning_rate": 5.360746435146885e-06,
"loss": 0.0726,
"step": 599
},
{
"epoch": 6.0,
"learning_rate": 5.257010050787486e-06,
"loss": 0.5461,
"step": 600
},
{
"epoch": 6.01,
"learning_rate": 5.154231487582273e-06,
"loss": 0.434,
"step": 601
},
{
"epoch": 6.02,
"learning_rate": 5.05241294573024e-06,
"loss": 0.09,
"step": 602
},
{
"epoch": 6.03,
"learning_rate": 4.951556604879048e-06,
"loss": 0.1361,
"step": 603
},
{
"epoch": 6.04,
"learning_rate": 4.851664624078356e-06,
"loss": 0.204,
"step": 604
},
{
"epoch": 6.05,
"learning_rate": 4.752739141733564e-06,
"loss": 0.5965,
"step": 605
},
{
"epoch": 6.06,
"learning_rate": 4.654782275560127e-06,
"loss": 0.1991,
"step": 606
},
{
"epoch": 6.07,
"learning_rate": 4.557796122538089e-06,
"loss": 0.4655,
"step": 607
},
{
"epoch": 6.08,
"learning_rate": 4.4617827588673166e-06,
"loss": 0.2066,
"step": 608
},
{
"epoch": 6.09,
"learning_rate": 4.366744239922998e-06,
"loss": 0.1753,
"step": 609
},
{
"epoch": 6.1,
"learning_rate": 4.2726826002116085e-06,
"loss": 0.1258,
"step": 610
},
{
"epoch": 6.11,
"learning_rate": 4.1795998533274265e-06,
"loss": 0.247,
"step": 611
},
{
"epoch": 6.12,
"learning_rate": 4.0874979919094e-06,
"loss": 0.1362,
"step": 612
},
{
"epoch": 6.13,
"learning_rate": 3.996378987598487e-06,
"loss": 0.3731,
"step": 613
},
{
"epoch": 6.14,
"learning_rate": 3.906244790995422e-06,
"loss": 0.2558,
"step": 614
},
{
"epoch": 6.15,
"learning_rate": 3.8170973316190074e-06,
"loss": 0.1931,
"step": 615
},
{
"epoch": 6.16,
"learning_rate": 3.728938517864794e-06,
"loss": 0.2865,
"step": 616
},
{
"epoch": 6.17,
"learning_rate": 3.6417702369641925e-06,
"loss": 0.4237,
"step": 617
},
{
"epoch": 6.18,
"learning_rate": 3.555594354944125e-06,
"loss": 0.2245,
"step": 618
},
{
"epoch": 6.19,
"learning_rate": 3.4704127165870517e-06,
"loss": 0.5589,
"step": 619
},
{
"epoch": 6.2,
"learning_rate": 3.386227145391463e-06,
"loss": 0.4759,
"step": 620
},
{
"epoch": 6.21,
"learning_rate": 3.303039443532874e-06,
"loss": 0.0602,
"step": 621
},
{
"epoch": 6.22,
"learning_rate": 3.220851391825247e-06,
"loss": 0.1631,
"step": 622
},
{
"epoch": 6.23,
"learning_rate": 3.1396647496828247e-06,
"loss": 0.239,
"step": 623
},
{
"epoch": 6.24,
"learning_rate": 3.059481255082519e-06,
"loss": 0.3236,
"step": 624
},
{
"epoch": 6.25,
"learning_rate": 2.980302624526693e-06,
"loss": 0.5941,
"step": 625
},
{
"epoch": 6.26,
"learning_rate": 2.9021305530063658e-06,
"loss": 0.0469,
"step": 626
},
{
"epoch": 6.27,
"learning_rate": 2.8249667139650216e-06,
"loss": 0.1646,
"step": 627
},
{
"epoch": 6.28,
"learning_rate": 2.7488127592626866e-06,
"loss": 0.4639,
"step": 628
},
{
"epoch": 6.29,
"learning_rate": 2.6736703191406366e-06,
"loss": 0.6154,
"step": 629
},
{
"epoch": 6.3,
"learning_rate": 2.5995410021864787e-06,
"loss": 0.5069,
"step": 630
},
{
"epoch": 6.31,
"learning_rate": 2.5264263952996915e-06,
"loss": 0.2421,
"step": 631
},
{
"epoch": 6.32,
"learning_rate": 2.4543280636576794e-06,
"loss": 0.2286,
"step": 632
},
{
"epoch": 6.33,
"learning_rate": 2.3832475506822937e-06,
"loss": 0.2885,
"step": 633
},
{
"epoch": 6.34,
"learning_rate": 2.3131863780067043e-06,
"loss": 0.4921,
"step": 634
},
{
"epoch": 6.35,
"learning_rate": 2.24414604544293e-06,
"loss": 0.1256,
"step": 635
},
{
"epoch": 6.36,
"learning_rate": 2.1761280309496646e-06,
"loss": 0.2475,
"step": 636
},
{
"epoch": 6.37,
"learning_rate": 2.1091337906006482e-06,
"loss": 0.2944,
"step": 637
},
{
"epoch": 6.38,
"learning_rate": 2.043164758553523e-06,
"loss": 0.3756,
"step": 638
},
{
"epoch": 6.39,
"learning_rate": 1.9782223470191042e-06,
"loss": 0.1635,
"step": 639
},
{
"epoch": 6.4,
"learning_rate": 1.914307946231164e-06,
"loss": 0.3118,
"step": 640
},
{
"epoch": 6.41,
"learning_rate": 1.8514229244166569e-06,
"loss": 0.0041,
"step": 641
},
{
"epoch": 6.42,
"learning_rate": 1.7895686277664469e-06,
"loss": 0.6769,
"step": 642
},
{
"epoch": 6.43,
"learning_rate": 1.7287463804064875e-06,
"loss": 0.1385,
"step": 643
},
{
"epoch": 6.44,
"learning_rate": 1.6689574843694433e-06,
"loss": 0.4119,
"step": 644
},
{
"epoch": 6.45,
"learning_rate": 1.6102032195668637e-06,
"loss": 0.5452,
"step": 645
},
{
"epoch": 6.46,
"learning_rate": 1.5524848437617756e-06,
"loss": 0.1845,
"step": 646
},
{
"epoch": 6.47,
"learning_rate": 1.4958035925417003e-06,
"loss": 0.5809,
"step": 647
},
{
"epoch": 6.48,
"learning_rate": 1.4401606792923017e-06,
"loss": 0.0547,
"step": 648
},
{
"epoch": 6.49,
"learning_rate": 1.3855572951713248e-06,
"loss": 0.7891,
"step": 649
},
{
"epoch": 6.5,
"learning_rate": 1.331994609083137e-06,
"loss": 0.4184,
"step": 650
},
{
"epoch": 6.51,
"learning_rate": 1.2794737676536994e-06,
"loss": 0.1763,
"step": 651
},
{
"epoch": 6.52,
"learning_rate": 1.2279958952060134e-06,
"loss": 0.2703,
"step": 652
},
{
"epoch": 6.53,
"learning_rate": 1.1775620937360676e-06,
"loss": 0.1685,
"step": 653
},
{
"epoch": 6.54,
"learning_rate": 1.1281734428892409e-06,
"loss": 0.4687,
"step": 654
},
{
"epoch": 6.55,
"learning_rate": 1.0798309999371536e-06,
"loss": 0.3129,
"step": 655
},
{
"epoch": 6.56,
"learning_rate": 1.0325357997551134e-06,
"loss": 0.3212,
"step": 656
},
{
"epoch": 6.57,
"learning_rate": 9.862888547998829e-07,
"loss": 0.1715,
"step": 657
},
{
"epoch": 6.58,
"learning_rate": 9.410911550880475e-07,
"loss": 0.0958,
"step": 658
},
{
"epoch": 6.59,
"learning_rate": 8.969436681748211e-07,
"loss": 0.4998,
"step": 659
},
{
"epoch": 6.6,
"learning_rate": 8.53847339133318e-07,
"loss": 0.5603,
"step": 660
},
{
"epoch": 6.61,
"learning_rate": 8.118030905343244e-07,
"loss": 0.2253,
"step": 661
},
{
"epoch": 6.62,
"learning_rate": 7.708118224265537e-07,
"loss": 0.4123,
"step": 662
},
{
"epoch": 6.63,
"learning_rate": 7.308744123174005e-07,
"loss": 0.1991,
"step": 663
},
{
"epoch": 6.64,
"learning_rate": 6.919917151540945e-07,
"loss": 0.2339,
"step": 664
},
{
"epoch": 6.65,
"learning_rate": 6.54164563305465e-07,
"loss": 0.1869,
"step": 665
},
{
"epoch": 6.66,
"learning_rate": 6.173937665440943e-07,
"loss": 0.4296,
"step": 666
},
{
"epoch": 6.67,
"learning_rate": 5.816801120289761e-07,
"loss": 0.6248,
"step": 667
},
{
"epoch": 6.68,
"learning_rate": 5.470243642886729e-07,
"loss": 0.4564,
"step": 668
},
{
"epoch": 6.69,
"learning_rate": 5.13427265204941e-07,
"loss": 0.0565,
"step": 669
},
{
"epoch": 6.7,
"learning_rate": 4.808895339968645e-07,
"loss": 0.6664,
"step": 670
},
{
"epoch": 6.71,
"learning_rate": 4.4941186720546255e-07,
"loss": 0.6173,
"step": 671
},
{
"epoch": 6.72,
"learning_rate": 4.189949386787462e-07,
"loss": 0.1852,
"step": 672
},
{
"epoch": 6.73,
"learning_rate": 3.8963939955731775e-07,
"loss": 0.1576,
"step": 673
},
{
"epoch": 6.74,
"learning_rate": 3.6134587826043285e-07,
"loss": 0.5002,
"step": 674
},
{
"epoch": 6.75,
"learning_rate": 3.3411498047254965e-07,
"loss": 0.2256,
"step": 675
},
{
"epoch": 6.76,
"learning_rate": 3.0794728913033366e-07,
"loss": 0.7607,
"step": 676
},
{
"epoch": 6.77,
"learning_rate": 2.82843364410218e-07,
"loss": 0.247,
"step": 677
},
{
"epoch": 6.78,
"learning_rate": 2.5880374371639594e-07,
"loss": 0.2779,
"step": 678
},
{
"epoch": 6.79,
"learning_rate": 2.3582894166930268e-07,
"loss": 0.3975,
"step": 679
},
{
"epoch": 6.8,
"learning_rate": 2.1391945009461844e-07,
"loss": 0.5484,
"step": 680
},
{
"epoch": 6.81,
"learning_rate": 1.9307573801273236e-07,
"loss": 0.3157,
"step": 681
},
{
"epoch": 6.82,
"learning_rate": 1.7329825162870073e-07,
"loss": 0.2321,
"step": 682
},
{
"epoch": 6.83,
"learning_rate": 1.545874143226933e-07,
"loss": 0.3094,
"step": 683
},
{
"epoch": 6.84,
"learning_rate": 1.3694362664094518e-07,
"loss": 0.0238,
"step": 684
},
{
"epoch": 6.85,
"learning_rate": 1.2036726628715245e-07,
"loss": 0.302,
"step": 685
},
{
"epoch": 6.86,
"learning_rate": 1.0485868811441757e-07,
"loss": 0.3072,
"step": 686
},
{
"epoch": 6.87,
"learning_rate": 9.041822411763324e-08,
"loss": 0.336,
"step": 687
},
{
"epoch": 6.88,
"learning_rate": 7.704618342638802e-08,
"loss": 0.2623,
"step": 688
},
{
"epoch": 6.89,
"learning_rate": 6.474285229833843e-08,
"loss": 0.201,
"step": 689
},
{
"epoch": 6.9,
"learning_rate": 5.350849411307479e-08,
"loss": 0.2409,
"step": 690
},
{
"epoch": 6.91,
"learning_rate": 4.334334936652029e-08,
"loss": 0.3016,
"step": 691
},
{
"epoch": 6.92,
"learning_rate": 3.424763566572398e-08,
"loss": 0.2335,
"step": 692
},
{
"epoch": 6.93,
"learning_rate": 2.6221547724253337e-08,
"loss": 0.2046,
"step": 693
},
{
"epoch": 6.94,
"learning_rate": 1.9265257358008772e-08,
"loss": 0.3476,
"step": 694
},
{
"epoch": 6.95,
"learning_rate": 1.3378913481526533e-08,
"loss": 0.0757,
"step": 695
},
{
"epoch": 6.96,
"learning_rate": 8.562642104831265e-09,
"loss": 0.5525,
"step": 696
},
{
"epoch": 6.97,
"learning_rate": 4.816546330688176e-09,
"loss": 0.3606,
"step": 697
},
{
"epoch": 6.98,
"learning_rate": 2.140706352443678e-09,
"loss": 0.3668,
"step": 698
},
{
"epoch": 6.99,
"learning_rate": 5.351794522823195e-10,
"loss": 0.1318,
"step": 699
},
{
"epoch": 7.0,
"learning_rate": 0.0,
"loss": 0.3211,
"step": 700
},
{
"epoch": 7.0,
"step": 700,
"total_flos": 1.194630166429565e+18,
"train_loss": 0.5665054323007852,
"train_runtime": 5397.3976,
"train_samples_per_second": 0.519,
"train_steps_per_second": 0.13
}
],
"logging_steps": 1.0,
"max_steps": 700,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 10000,
"total_flos": 1.194630166429565e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}