cherry-wizardlm-filtered-7B / trainer_state.json
Ming Li
Initial commit
abdf740
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9981148674123412,
"global_step": 1491,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.444444444444445e-07,
"loss": 1.0812,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 8.88888888888889e-07,
"loss": 1.2235,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.3333333333333334e-06,
"loss": 0.9333,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 1.777777777777778e-06,
"loss": 1.0602,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.222222222222222e-06,
"loss": 0.7906,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 2.666666666666667e-06,
"loss": 1.2627,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 3.1111111111111116e-06,
"loss": 0.8221,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 3.555555555555556e-06,
"loss": 0.7669,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 0.8034,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 4.444444444444444e-06,
"loss": 0.7905,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.888888888888889e-06,
"loss": 0.7344,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 5.333333333333334e-06,
"loss": 0.699,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 5.777777777777778e-06,
"loss": 0.7177,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 6.222222222222223e-06,
"loss": 0.7696,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 6.666666666666667e-06,
"loss": 0.701,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 7.111111111111112e-06,
"loss": 0.6348,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 7.555555555555556e-06,
"loss": 0.6997,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-06,
"loss": 0.7101,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 8.444444444444446e-06,
"loss": 0.7493,
"step": 19
},
{
"epoch": 0.04,
"learning_rate": 8.888888888888888e-06,
"loss": 0.6834,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 9.333333333333334e-06,
"loss": 0.6219,
"step": 21
},
{
"epoch": 0.04,
"learning_rate": 9.777777777777779e-06,
"loss": 0.888,
"step": 22
},
{
"epoch": 0.05,
"learning_rate": 1.0222222222222223e-05,
"loss": 0.6847,
"step": 23
},
{
"epoch": 0.05,
"learning_rate": 1.0666666666666667e-05,
"loss": 0.6381,
"step": 24
},
{
"epoch": 0.05,
"learning_rate": 1.1111111111111113e-05,
"loss": 0.7188,
"step": 25
},
{
"epoch": 0.05,
"learning_rate": 1.1555555555555556e-05,
"loss": 0.6484,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 1.2e-05,
"loss": 0.6986,
"step": 27
},
{
"epoch": 0.06,
"learning_rate": 1.2444444444444446e-05,
"loss": 0.7046,
"step": 28
},
{
"epoch": 0.06,
"learning_rate": 1.288888888888889e-05,
"loss": 0.7445,
"step": 29
},
{
"epoch": 0.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.7063,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 1.377777777777778e-05,
"loss": 0.6362,
"step": 31
},
{
"epoch": 0.06,
"learning_rate": 1.4222222222222224e-05,
"loss": 0.6392,
"step": 32
},
{
"epoch": 0.07,
"learning_rate": 1.4666666666666666e-05,
"loss": 0.6405,
"step": 33
},
{
"epoch": 0.07,
"learning_rate": 1.5111111111111112e-05,
"loss": 0.7608,
"step": 34
},
{
"epoch": 0.07,
"learning_rate": 1.555555555555556e-05,
"loss": 0.7261,
"step": 35
},
{
"epoch": 0.07,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.5958,
"step": 36
},
{
"epoch": 0.07,
"learning_rate": 1.6444444444444444e-05,
"loss": 0.6631,
"step": 37
},
{
"epoch": 0.08,
"learning_rate": 1.688888888888889e-05,
"loss": 0.7186,
"step": 38
},
{
"epoch": 0.08,
"learning_rate": 1.7333333333333336e-05,
"loss": 0.6076,
"step": 39
},
{
"epoch": 0.08,
"learning_rate": 1.7777777777777777e-05,
"loss": 0.6244,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 1.8222222222222224e-05,
"loss": 0.7979,
"step": 41
},
{
"epoch": 0.08,
"learning_rate": 1.866666666666667e-05,
"loss": 0.6023,
"step": 42
},
{
"epoch": 0.09,
"learning_rate": 1.9111111111111113e-05,
"loss": 0.6273,
"step": 43
},
{
"epoch": 0.09,
"learning_rate": 1.9555555555555557e-05,
"loss": 0.6949,
"step": 44
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 0.7076,
"step": 45
},
{
"epoch": 0.09,
"learning_rate": 1.9999976398859354e-05,
"loss": 0.6858,
"step": 46
},
{
"epoch": 0.09,
"learning_rate": 1.999990559554882e-05,
"loss": 0.6249,
"step": 47
},
{
"epoch": 0.1,
"learning_rate": 1.9999787590402607e-05,
"loss": 0.868,
"step": 48
},
{
"epoch": 0.1,
"learning_rate": 1.9999622383977725e-05,
"loss": 0.7447,
"step": 49
},
{
"epoch": 0.1,
"learning_rate": 1.999940997705398e-05,
"loss": 0.6215,
"step": 50
},
{
"epoch": 0.1,
"learning_rate": 1.9999150370633987e-05,
"loss": 0.624,
"step": 51
},
{
"epoch": 0.1,
"learning_rate": 1.9998843565943153e-05,
"loss": 0.6269,
"step": 52
},
{
"epoch": 0.11,
"learning_rate": 1.9998489564429656e-05,
"loss": 0.6424,
"step": 53
},
{
"epoch": 0.11,
"learning_rate": 1.9998088367764468e-05,
"loss": 0.7625,
"step": 54
},
{
"epoch": 0.11,
"learning_rate": 1.999763997784133e-05,
"loss": 0.6187,
"step": 55
},
{
"epoch": 0.11,
"learning_rate": 1.9997144396776744e-05,
"loss": 0.6553,
"step": 56
},
{
"epoch": 0.11,
"learning_rate": 1.9996601626909962e-05,
"loss": 0.6548,
"step": 57
},
{
"epoch": 0.12,
"learning_rate": 1.999601167080299e-05,
"loss": 0.6107,
"step": 58
},
{
"epoch": 0.12,
"learning_rate": 1.999537453124055e-05,
"loss": 0.6292,
"step": 59
},
{
"epoch": 0.12,
"learning_rate": 1.9994690211230084e-05,
"loss": 0.5956,
"step": 60
},
{
"epoch": 0.12,
"learning_rate": 1.9993958714001738e-05,
"loss": 0.8311,
"step": 61
},
{
"epoch": 0.12,
"learning_rate": 1.9993180043008354e-05,
"loss": 0.6065,
"step": 62
},
{
"epoch": 0.13,
"learning_rate": 1.9992354201925427e-05,
"loss": 0.6119,
"step": 63
},
{
"epoch": 0.13,
"learning_rate": 1.9991481194651127e-05,
"loss": 0.6439,
"step": 64
},
{
"epoch": 0.13,
"learning_rate": 1.9990561025306232e-05,
"loss": 0.7202,
"step": 65
},
{
"epoch": 0.13,
"learning_rate": 1.9989593698234165e-05,
"loss": 0.7236,
"step": 66
},
{
"epoch": 0.13,
"learning_rate": 1.998857921800092e-05,
"loss": 0.6373,
"step": 67
},
{
"epoch": 0.14,
"learning_rate": 1.9987517589395087e-05,
"loss": 0.6465,
"step": 68
},
{
"epoch": 0.14,
"learning_rate": 1.998640881742778e-05,
"loss": 0.7016,
"step": 69
},
{
"epoch": 0.14,
"learning_rate": 1.9985252907332672e-05,
"loss": 0.6094,
"step": 70
},
{
"epoch": 0.14,
"learning_rate": 1.998404986456591e-05,
"loss": 0.5963,
"step": 71
},
{
"epoch": 0.14,
"learning_rate": 1.9982799694806133e-05,
"loss": 0.7178,
"step": 72
},
{
"epoch": 0.15,
"learning_rate": 1.9981502403954435e-05,
"loss": 0.6192,
"step": 73
},
{
"epoch": 0.15,
"learning_rate": 1.9980157998134312e-05,
"loss": 0.6132,
"step": 74
},
{
"epoch": 0.15,
"learning_rate": 1.997876648369168e-05,
"loss": 0.6597,
"step": 75
},
{
"epoch": 0.15,
"learning_rate": 1.997732786719479e-05,
"loss": 0.6219,
"step": 76
},
{
"epoch": 0.15,
"learning_rate": 1.9975842155434253e-05,
"loss": 0.6468,
"step": 77
},
{
"epoch": 0.16,
"learning_rate": 1.9974309355422964e-05,
"loss": 0.5874,
"step": 78
},
{
"epoch": 0.16,
"learning_rate": 1.997272947439608e-05,
"loss": 0.6411,
"step": 79
},
{
"epoch": 0.16,
"learning_rate": 1.9971102519811012e-05,
"loss": 0.5918,
"step": 80
},
{
"epoch": 0.16,
"learning_rate": 1.996942849934735e-05,
"loss": 0.6305,
"step": 81
},
{
"epoch": 0.16,
"learning_rate": 1.996770742090685e-05,
"loss": 0.6247,
"step": 82
},
{
"epoch": 0.17,
"learning_rate": 1.9965939292613408e-05,
"loss": 0.6319,
"step": 83
},
{
"epoch": 0.17,
"learning_rate": 1.9964124122812977e-05,
"loss": 0.7287,
"step": 84
},
{
"epoch": 0.17,
"learning_rate": 1.996226192007358e-05,
"loss": 0.6537,
"step": 85
},
{
"epoch": 0.17,
"learning_rate": 1.996035269318524e-05,
"loss": 0.6089,
"step": 86
},
{
"epoch": 0.17,
"learning_rate": 1.9958396451159937e-05,
"loss": 0.6318,
"step": 87
},
{
"epoch": 0.18,
"learning_rate": 1.995639320323159e-05,
"loss": 0.6096,
"step": 88
},
{
"epoch": 0.18,
"learning_rate": 1.995434295885598e-05,
"loss": 0.6359,
"step": 89
},
{
"epoch": 0.18,
"learning_rate": 1.9952245727710723e-05,
"loss": 0.6511,
"step": 90
},
{
"epoch": 0.18,
"learning_rate": 1.995010151969524e-05,
"loss": 0.6297,
"step": 91
},
{
"epoch": 0.18,
"learning_rate": 1.994791034493067e-05,
"loss": 0.6124,
"step": 92
},
{
"epoch": 0.19,
"learning_rate": 1.9945672213759872e-05,
"loss": 0.6406,
"step": 93
},
{
"epoch": 0.19,
"learning_rate": 1.9943387136747317e-05,
"loss": 0.6529,
"step": 94
},
{
"epoch": 0.19,
"learning_rate": 1.9941055124679108e-05,
"loss": 0.6334,
"step": 95
},
{
"epoch": 0.19,
"learning_rate": 1.9938676188562863e-05,
"loss": 0.6551,
"step": 96
},
{
"epoch": 0.2,
"learning_rate": 1.993625033962771e-05,
"loss": 0.6883,
"step": 97
},
{
"epoch": 0.2,
"learning_rate": 1.9933777589324202e-05,
"loss": 0.6347,
"step": 98
},
{
"epoch": 0.2,
"learning_rate": 1.993125794932429e-05,
"loss": 0.6202,
"step": 99
},
{
"epoch": 0.2,
"learning_rate": 1.9928691431521247e-05,
"loss": 0.6187,
"step": 100
},
{
"epoch": 0.2,
"learning_rate": 1.9926078048029623e-05,
"loss": 0.6139,
"step": 101
},
{
"epoch": 0.21,
"learning_rate": 1.9923417811185188e-05,
"loss": 0.671,
"step": 102
},
{
"epoch": 0.21,
"learning_rate": 1.992071073354486e-05,
"loss": 0.8254,
"step": 103
},
{
"epoch": 0.21,
"learning_rate": 1.991795682788667e-05,
"loss": 0.7326,
"step": 104
},
{
"epoch": 0.21,
"learning_rate": 1.9915156107209673e-05,
"loss": 0.6191,
"step": 105
},
{
"epoch": 0.21,
"learning_rate": 1.9912308584733916e-05,
"loss": 0.6496,
"step": 106
},
{
"epoch": 0.22,
"learning_rate": 1.9909414273900353e-05,
"loss": 0.6005,
"step": 107
},
{
"epoch": 0.22,
"learning_rate": 1.9906473188370793e-05,
"loss": 0.6131,
"step": 108
},
{
"epoch": 0.22,
"learning_rate": 1.9903485342027827e-05,
"loss": 0.588,
"step": 109
},
{
"epoch": 0.22,
"learning_rate": 1.9900450748974772e-05,
"loss": 0.6105,
"step": 110
},
{
"epoch": 0.22,
"learning_rate": 1.98973694235356e-05,
"loss": 0.6178,
"step": 111
},
{
"epoch": 0.23,
"learning_rate": 1.989424138025487e-05,
"loss": 0.6368,
"step": 112
},
{
"epoch": 0.23,
"learning_rate": 1.9891066633897666e-05,
"loss": 0.6386,
"step": 113
},
{
"epoch": 0.23,
"learning_rate": 1.9887845199449506e-05,
"loss": 0.6676,
"step": 114
},
{
"epoch": 0.23,
"learning_rate": 1.9884577092116296e-05,
"loss": 0.6367,
"step": 115
},
{
"epoch": 0.23,
"learning_rate": 1.9881262327324256e-05,
"loss": 0.6146,
"step": 116
},
{
"epoch": 0.24,
"learning_rate": 1.9877900920719825e-05,
"loss": 0.6356,
"step": 117
},
{
"epoch": 0.24,
"learning_rate": 1.9874492888169613e-05,
"loss": 0.6772,
"step": 118
},
{
"epoch": 0.24,
"learning_rate": 1.9871038245760305e-05,
"loss": 0.6271,
"step": 119
},
{
"epoch": 0.24,
"learning_rate": 1.986753700979861e-05,
"loss": 0.5864,
"step": 120
},
{
"epoch": 0.24,
"learning_rate": 1.9863989196811153e-05,
"loss": 0.6654,
"step": 121
},
{
"epoch": 0.25,
"learning_rate": 1.9860394823544426e-05,
"loss": 0.6354,
"step": 122
},
{
"epoch": 0.25,
"learning_rate": 1.9856753906964686e-05,
"loss": 0.6009,
"step": 123
},
{
"epoch": 0.25,
"learning_rate": 1.9853066464257896e-05,
"loss": 0.668,
"step": 124
},
{
"epoch": 0.25,
"learning_rate": 1.9849332512829624e-05,
"loss": 0.5848,
"step": 125
},
{
"epoch": 0.25,
"learning_rate": 1.984555207030497e-05,
"loss": 0.602,
"step": 126
},
{
"epoch": 0.26,
"learning_rate": 1.9841725154528485e-05,
"loss": 0.6051,
"step": 127
},
{
"epoch": 0.26,
"learning_rate": 1.9837851783564085e-05,
"loss": 0.6461,
"step": 128
},
{
"epoch": 0.26,
"learning_rate": 1.983393197569497e-05,
"loss": 0.6849,
"step": 129
},
{
"epoch": 0.26,
"learning_rate": 1.9829965749423522e-05,
"loss": 0.5788,
"step": 130
},
{
"epoch": 0.26,
"learning_rate": 1.9825953123471235e-05,
"loss": 0.5949,
"step": 131
},
{
"epoch": 0.27,
"learning_rate": 1.9821894116778617e-05,
"loss": 0.6456,
"step": 132
},
{
"epoch": 0.27,
"learning_rate": 1.981778874850511e-05,
"loss": 0.6404,
"step": 133
},
{
"epoch": 0.27,
"learning_rate": 1.9813637038028988e-05,
"loss": 0.5948,
"step": 134
},
{
"epoch": 0.27,
"learning_rate": 1.980943900494727e-05,
"loss": 0.6151,
"step": 135
},
{
"epoch": 0.27,
"learning_rate": 1.9805194669075626e-05,
"loss": 0.6321,
"step": 136
},
{
"epoch": 0.28,
"learning_rate": 1.9800904050448296e-05,
"loss": 0.9778,
"step": 137
},
{
"epoch": 0.28,
"learning_rate": 1.9796567169317975e-05,
"loss": 0.6619,
"step": 138
},
{
"epoch": 0.28,
"learning_rate": 1.9792184046155733e-05,
"loss": 0.5816,
"step": 139
},
{
"epoch": 0.28,
"learning_rate": 1.9787754701650907e-05,
"loss": 0.6717,
"step": 140
},
{
"epoch": 0.28,
"learning_rate": 1.9783279156711022e-05,
"loss": 0.6614,
"step": 141
},
{
"epoch": 0.29,
"learning_rate": 1.9778757432461667e-05,
"loss": 0.6211,
"step": 142
},
{
"epoch": 0.29,
"learning_rate": 1.9774189550246407e-05,
"loss": 0.6421,
"step": 143
},
{
"epoch": 0.29,
"learning_rate": 1.9769575531626697e-05,
"loss": 0.7032,
"step": 144
},
{
"epoch": 0.29,
"learning_rate": 1.976491539838175e-05,
"loss": 0.6466,
"step": 145
},
{
"epoch": 0.29,
"learning_rate": 1.9760209172508464e-05,
"loss": 0.6044,
"step": 146
},
{
"epoch": 0.3,
"learning_rate": 1.975545687622129e-05,
"loss": 0.6197,
"step": 147
},
{
"epoch": 0.3,
"learning_rate": 1.9750658531952157e-05,
"loss": 0.6157,
"step": 148
},
{
"epoch": 0.3,
"learning_rate": 1.974581416235035e-05,
"loss": 0.5798,
"step": 149
},
{
"epoch": 0.3,
"learning_rate": 1.974092379028239e-05,
"loss": 0.6037,
"step": 150
},
{
"epoch": 0.3,
"learning_rate": 1.9735987438831947e-05,
"loss": 0.6466,
"step": 151
},
{
"epoch": 0.31,
"learning_rate": 1.9731005131299734e-05,
"loss": 0.6635,
"step": 152
},
{
"epoch": 0.31,
"learning_rate": 1.972597689120338e-05,
"loss": 0.7644,
"step": 153
},
{
"epoch": 0.31,
"learning_rate": 1.972090274227731e-05,
"loss": 0.6312,
"step": 154
},
{
"epoch": 0.31,
"learning_rate": 1.9715782708472685e-05,
"loss": 0.5819,
"step": 155
},
{
"epoch": 0.31,
"learning_rate": 1.971061681395722e-05,
"loss": 0.6392,
"step": 156
},
{
"epoch": 0.32,
"learning_rate": 1.9705405083115118e-05,
"loss": 0.6514,
"step": 157
},
{
"epoch": 0.32,
"learning_rate": 1.9700147540546937e-05,
"loss": 0.5667,
"step": 158
},
{
"epoch": 0.32,
"learning_rate": 1.9694844211069477e-05,
"loss": 0.6187,
"step": 159
},
{
"epoch": 0.32,
"learning_rate": 1.968949511971567e-05,
"loss": 0.5524,
"step": 160
},
{
"epoch": 0.32,
"learning_rate": 1.9684100291734437e-05,
"loss": 0.6379,
"step": 161
},
{
"epoch": 0.33,
"learning_rate": 1.96786597525906e-05,
"loss": 0.5879,
"step": 162
},
{
"epoch": 0.33,
"learning_rate": 1.9673173527964753e-05,
"loss": 0.5963,
"step": 163
},
{
"epoch": 0.33,
"learning_rate": 1.9667641643753117e-05,
"loss": 0.6039,
"step": 164
},
{
"epoch": 0.33,
"learning_rate": 1.966206412606745e-05,
"loss": 0.777,
"step": 165
},
{
"epoch": 0.33,
"learning_rate": 1.9656441001234916e-05,
"loss": 0.6217,
"step": 166
},
{
"epoch": 0.34,
"learning_rate": 1.9650772295797934e-05,
"loss": 0.6148,
"step": 167
},
{
"epoch": 0.34,
"learning_rate": 1.9645058036514097e-05,
"loss": 0.6072,
"step": 168
},
{
"epoch": 0.34,
"learning_rate": 1.963929825035601e-05,
"loss": 0.6315,
"step": 169
},
{
"epoch": 0.34,
"learning_rate": 1.9633492964511175e-05,
"loss": 0.5862,
"step": 170
},
{
"epoch": 0.34,
"learning_rate": 1.9627642206381864e-05,
"loss": 0.6143,
"step": 171
},
{
"epoch": 0.35,
"learning_rate": 1.9621746003584997e-05,
"loss": 0.6523,
"step": 172
},
{
"epoch": 0.35,
"learning_rate": 1.9615804383951992e-05,
"loss": 0.5948,
"step": 173
},
{
"epoch": 0.35,
"learning_rate": 1.9609817375528652e-05,
"loss": 0.7289,
"step": 174
},
{
"epoch": 0.35,
"learning_rate": 1.9603785006575015e-05,
"loss": 0.591,
"step": 175
},
{
"epoch": 0.35,
"learning_rate": 1.9597707305565245e-05,
"loss": 0.6022,
"step": 176
},
{
"epoch": 0.36,
"learning_rate": 1.9591584301187477e-05,
"loss": 0.6252,
"step": 177
},
{
"epoch": 0.36,
"learning_rate": 1.958541602234369e-05,
"loss": 0.5605,
"step": 178
},
{
"epoch": 0.36,
"learning_rate": 1.9579202498149562e-05,
"loss": 0.5439,
"step": 179
},
{
"epoch": 0.36,
"learning_rate": 1.957294375793435e-05,
"loss": 0.6914,
"step": 180
},
{
"epoch": 0.36,
"learning_rate": 1.956663983124073e-05,
"loss": 0.8089,
"step": 181
},
{
"epoch": 0.37,
"learning_rate": 1.956029074782468e-05,
"loss": 0.6106,
"step": 182
},
{
"epoch": 0.37,
"learning_rate": 1.9553896537655317e-05,
"loss": 0.5883,
"step": 183
},
{
"epoch": 0.37,
"learning_rate": 1.9547457230914776e-05,
"loss": 0.5491,
"step": 184
},
{
"epoch": 0.37,
"learning_rate": 1.954097285799805e-05,
"loss": 0.7136,
"step": 185
},
{
"epoch": 0.37,
"learning_rate": 1.953444344951286e-05,
"loss": 0.8129,
"step": 186
},
{
"epoch": 0.38,
"learning_rate": 1.9527869036279507e-05,
"loss": 0.8368,
"step": 187
},
{
"epoch": 0.38,
"learning_rate": 1.9521249649330717e-05,
"loss": 0.6428,
"step": 188
},
{
"epoch": 0.38,
"learning_rate": 1.951458531991151e-05,
"loss": 0.599,
"step": 189
},
{
"epoch": 0.38,
"learning_rate": 1.9507876079479034e-05,
"loss": 0.603,
"step": 190
},
{
"epoch": 0.38,
"learning_rate": 1.9501121959702444e-05,
"loss": 0.6103,
"step": 191
},
{
"epoch": 0.39,
"learning_rate": 1.9494322992462718e-05,
"loss": 0.6679,
"step": 192
},
{
"epoch": 0.39,
"learning_rate": 1.9487479209852537e-05,
"loss": 0.6393,
"step": 193
},
{
"epoch": 0.39,
"learning_rate": 1.9480590644176116e-05,
"loss": 0.6461,
"step": 194
},
{
"epoch": 0.39,
"learning_rate": 1.9473657327949055e-05,
"loss": 0.6475,
"step": 195
},
{
"epoch": 0.39,
"learning_rate": 1.9466679293898187e-05,
"loss": 0.6431,
"step": 196
},
{
"epoch": 0.4,
"learning_rate": 1.9459656574961427e-05,
"loss": 0.6119,
"step": 197
},
{
"epoch": 0.4,
"learning_rate": 1.9452589204287614e-05,
"loss": 0.6932,
"step": 198
},
{
"epoch": 0.4,
"learning_rate": 1.9445477215236343e-05,
"loss": 0.5984,
"step": 199
},
{
"epoch": 0.4,
"learning_rate": 1.9438320641377825e-05,
"loss": 0.6983,
"step": 200
},
{
"epoch": 0.4,
"learning_rate": 1.9431119516492725e-05,
"loss": 0.7234,
"step": 201
},
{
"epoch": 0.41,
"learning_rate": 1.9423873874571996e-05,
"loss": 0.6683,
"step": 202
},
{
"epoch": 0.41,
"learning_rate": 1.941658374981672e-05,
"loss": 0.6969,
"step": 203
},
{
"epoch": 0.41,
"learning_rate": 1.9409249176637945e-05,
"loss": 0.7788,
"step": 204
},
{
"epoch": 0.41,
"learning_rate": 1.9401870189656534e-05,
"loss": 0.7324,
"step": 205
},
{
"epoch": 0.41,
"learning_rate": 1.9394446823702984e-05,
"loss": 0.6319,
"step": 206
},
{
"epoch": 0.42,
"learning_rate": 1.9386979113817283e-05,
"loss": 0.608,
"step": 207
},
{
"epoch": 0.42,
"learning_rate": 1.9379467095248722e-05,
"loss": 0.7571,
"step": 208
},
{
"epoch": 0.42,
"learning_rate": 1.937191080345574e-05,
"loss": 0.6171,
"step": 209
},
{
"epoch": 0.42,
"learning_rate": 1.9364310274105758e-05,
"loss": 0.5733,
"step": 210
},
{
"epoch": 0.42,
"learning_rate": 1.9356665543075013e-05,
"loss": 0.5882,
"step": 211
},
{
"epoch": 0.43,
"learning_rate": 1.9348976646448374e-05,
"loss": 0.6074,
"step": 212
},
{
"epoch": 0.43,
"learning_rate": 1.934124362051919e-05,
"loss": 0.6186,
"step": 213
},
{
"epoch": 0.43,
"learning_rate": 1.933346650178911e-05,
"loss": 0.5797,
"step": 214
},
{
"epoch": 0.43,
"learning_rate": 1.9325645326967904e-05,
"loss": 0.6171,
"step": 215
},
{
"epoch": 0.43,
"learning_rate": 1.9317780132973302e-05,
"loss": 0.5745,
"step": 216
},
{
"epoch": 0.44,
"learning_rate": 1.9309870956930818e-05,
"loss": 0.6354,
"step": 217
},
{
"epoch": 0.44,
"learning_rate": 1.9301917836173564e-05,
"loss": 0.5976,
"step": 218
},
{
"epoch": 0.44,
"learning_rate": 1.9293920808242084e-05,
"loss": 0.6113,
"step": 219
},
{
"epoch": 0.44,
"learning_rate": 1.9285879910884175e-05,
"loss": 0.7205,
"step": 220
},
{
"epoch": 0.44,
"learning_rate": 1.927779518205471e-05,
"loss": 0.6029,
"step": 221
},
{
"epoch": 0.45,
"learning_rate": 1.9269666659915444e-05,
"loss": 0.6117,
"step": 222
},
{
"epoch": 0.45,
"learning_rate": 1.9261494382834866e-05,
"loss": 0.7787,
"step": 223
},
{
"epoch": 0.45,
"learning_rate": 1.9253278389387985e-05,
"loss": 0.6223,
"step": 224
},
{
"epoch": 0.45,
"learning_rate": 1.924501871835616e-05,
"loss": 0.6914,
"step": 225
},
{
"epoch": 0.45,
"learning_rate": 1.9236715408726932e-05,
"loss": 0.6137,
"step": 226
},
{
"epoch": 0.46,
"learning_rate": 1.9228368499693805e-05,
"loss": 0.6317,
"step": 227
},
{
"epoch": 0.46,
"learning_rate": 1.9219978030656103e-05,
"loss": 0.6308,
"step": 228
},
{
"epoch": 0.46,
"learning_rate": 1.9211544041218752e-05,
"loss": 0.6179,
"step": 229
},
{
"epoch": 0.46,
"learning_rate": 1.9203066571192104e-05,
"loss": 0.6828,
"step": 230
},
{
"epoch": 0.46,
"learning_rate": 1.9194545660591753e-05,
"loss": 0.604,
"step": 231
},
{
"epoch": 0.47,
"learning_rate": 1.9185981349638335e-05,
"loss": 0.612,
"step": 232
},
{
"epoch": 0.47,
"learning_rate": 1.917737367875736e-05,
"loss": 0.5978,
"step": 233
},
{
"epoch": 0.47,
"learning_rate": 1.9168722688578997e-05,
"loss": 0.5813,
"step": 234
},
{
"epoch": 0.47,
"learning_rate": 1.916002841993789e-05,
"loss": 0.6127,
"step": 235
},
{
"epoch": 0.47,
"learning_rate": 1.915129091387297e-05,
"loss": 0.6445,
"step": 236
},
{
"epoch": 0.48,
"learning_rate": 1.9142510211627264e-05,
"loss": 0.7722,
"step": 237
},
{
"epoch": 0.48,
"learning_rate": 1.9133686354647682e-05,
"loss": 0.5904,
"step": 238
},
{
"epoch": 0.48,
"learning_rate": 1.912481938458485e-05,
"loss": 0.5888,
"step": 239
},
{
"epoch": 0.48,
"learning_rate": 1.911590934329288e-05,
"loss": 0.5988,
"step": 240
},
{
"epoch": 0.48,
"learning_rate": 1.9106956272829212e-05,
"loss": 0.5701,
"step": 241
},
{
"epoch": 0.49,
"learning_rate": 1.909796021545437e-05,
"loss": 0.6314,
"step": 242
},
{
"epoch": 0.49,
"learning_rate": 1.9088921213631803e-05,
"loss": 0.5626,
"step": 243
},
{
"epoch": 0.49,
"learning_rate": 1.907983931002766e-05,
"loss": 0.5984,
"step": 244
},
{
"epoch": 0.49,
"learning_rate": 1.9070714547510593e-05,
"loss": 0.6394,
"step": 245
},
{
"epoch": 0.49,
"learning_rate": 1.906154696915157e-05,
"loss": 0.6158,
"step": 246
},
{
"epoch": 0.5,
"learning_rate": 1.9052336618223655e-05,
"loss": 0.5994,
"step": 247
},
{
"epoch": 0.5,
"learning_rate": 1.9043083538201795e-05,
"loss": 0.6,
"step": 248
},
{
"epoch": 0.5,
"learning_rate": 1.9033787772762647e-05,
"loss": 0.6102,
"step": 249
},
{
"epoch": 0.5,
"learning_rate": 1.902444936578434e-05,
"loss": 0.7719,
"step": 250
},
{
"epoch": 0.5,
"learning_rate": 1.9015068361346284e-05,
"loss": 0.579,
"step": 251
},
{
"epoch": 0.51,
"learning_rate": 1.9005644803728967e-05,
"loss": 0.5458,
"step": 252
},
{
"epoch": 0.51,
"learning_rate": 1.8996178737413724e-05,
"loss": 0.615,
"step": 253
},
{
"epoch": 0.51,
"learning_rate": 1.898667020708255e-05,
"loss": 0.6211,
"step": 254
},
{
"epoch": 0.51,
"learning_rate": 1.8977119257617878e-05,
"loss": 0.6018,
"step": 255
},
{
"epoch": 0.51,
"learning_rate": 1.8967525934102367e-05,
"loss": 0.7054,
"step": 256
},
{
"epoch": 0.52,
"learning_rate": 1.8957890281818693e-05,
"loss": 0.6792,
"step": 257
},
{
"epoch": 0.52,
"learning_rate": 1.8948212346249334e-05,
"loss": 0.5766,
"step": 258
},
{
"epoch": 0.52,
"learning_rate": 1.893849217307635e-05,
"loss": 0.6621,
"step": 259
},
{
"epoch": 0.52,
"learning_rate": 1.8928729808181182e-05,
"loss": 0.6054,
"step": 260
},
{
"epoch": 0.52,
"learning_rate": 1.8918925297644418e-05,
"loss": 0.6816,
"step": 261
},
{
"epoch": 0.53,
"learning_rate": 1.8909078687745577e-05,
"loss": 0.8275,
"step": 262
},
{
"epoch": 0.53,
"learning_rate": 1.889919002496291e-05,
"loss": 0.6588,
"step": 263
},
{
"epoch": 0.53,
"learning_rate": 1.8889259355973165e-05,
"loss": 0.5798,
"step": 264
},
{
"epoch": 0.53,
"learning_rate": 1.8879286727651357e-05,
"loss": 0.6022,
"step": 265
},
{
"epoch": 0.53,
"learning_rate": 1.886927218707057e-05,
"loss": 0.6422,
"step": 266
},
{
"epoch": 0.54,
"learning_rate": 1.8859215781501727e-05,
"loss": 0.5675,
"step": 267
},
{
"epoch": 0.54,
"learning_rate": 1.884911755841334e-05,
"loss": 0.5745,
"step": 268
},
{
"epoch": 0.54,
"learning_rate": 1.8838977565471343e-05,
"loss": 0.5756,
"step": 269
},
{
"epoch": 0.54,
"learning_rate": 1.8828795850538804e-05,
"loss": 0.5817,
"step": 270
},
{
"epoch": 0.54,
"learning_rate": 1.881857246167575e-05,
"loss": 0.5976,
"step": 271
},
{
"epoch": 0.55,
"learning_rate": 1.88083074471389e-05,
"loss": 0.6895,
"step": 272
},
{
"epoch": 0.55,
"learning_rate": 1.8798000855381472e-05,
"loss": 0.5805,
"step": 273
},
{
"epoch": 0.55,
"learning_rate": 1.8787652735052923e-05,
"loss": 0.6064,
"step": 274
},
{
"epoch": 0.55,
"learning_rate": 1.8777263134998745e-05,
"loss": 0.5833,
"step": 275
},
{
"epoch": 0.55,
"learning_rate": 1.876683210426022e-05,
"loss": 0.6373,
"step": 276
},
{
"epoch": 0.56,
"learning_rate": 1.8756359692074192e-05,
"loss": 0.5844,
"step": 277
},
{
"epoch": 0.56,
"learning_rate": 1.8745845947872842e-05,
"loss": 0.6363,
"step": 278
},
{
"epoch": 0.56,
"learning_rate": 1.873529092128343e-05,
"loss": 0.7982,
"step": 279
},
{
"epoch": 0.56,
"learning_rate": 1.87246946621281e-05,
"loss": 0.6951,
"step": 280
},
{
"epoch": 0.57,
"learning_rate": 1.8714057220423604e-05,
"loss": 0.5576,
"step": 281
},
{
"epoch": 0.57,
"learning_rate": 1.87033786463811e-05,
"loss": 0.5866,
"step": 282
},
{
"epoch": 0.57,
"learning_rate": 1.8692658990405887e-05,
"loss": 0.5912,
"step": 283
},
{
"epoch": 0.57,
"learning_rate": 1.8681898303097194e-05,
"loss": 0.6034,
"step": 284
},
{
"epoch": 0.57,
"learning_rate": 1.8671096635247914e-05,
"loss": 0.6952,
"step": 285
},
{
"epoch": 0.58,
"learning_rate": 1.866025403784439e-05,
"loss": 0.6094,
"step": 286
},
{
"epoch": 0.58,
"learning_rate": 1.8649370562066147e-05,
"loss": 0.5781,
"step": 287
},
{
"epoch": 0.58,
"learning_rate": 1.863844625928568e-05,
"loss": 0.7141,
"step": 288
},
{
"epoch": 0.58,
"learning_rate": 1.8627481181068185e-05,
"loss": 0.5957,
"step": 289
},
{
"epoch": 0.58,
"learning_rate": 1.8616475379171336e-05,
"loss": 0.6036,
"step": 290
},
{
"epoch": 0.59,
"learning_rate": 1.860542890554503e-05,
"loss": 0.6375,
"step": 291
},
{
"epoch": 0.59,
"learning_rate": 1.8594341812331144e-05,
"loss": 0.5915,
"step": 292
},
{
"epoch": 0.59,
"learning_rate": 1.8583214151863277e-05,
"loss": 0.5376,
"step": 293
},
{
"epoch": 0.59,
"learning_rate": 1.8572045976666536e-05,
"loss": 0.5891,
"step": 294
},
{
"epoch": 0.59,
"learning_rate": 1.856083733945725e-05,
"loss": 0.5989,
"step": 295
},
{
"epoch": 0.6,
"learning_rate": 1.8549588293142748e-05,
"loss": 0.5986,
"step": 296
},
{
"epoch": 0.6,
"learning_rate": 1.853829889082109e-05,
"loss": 0.6866,
"step": 297
},
{
"epoch": 0.6,
"learning_rate": 1.8526969185780833e-05,
"loss": 0.606,
"step": 298
},
{
"epoch": 0.6,
"learning_rate": 1.851559923150077e-05,
"loss": 0.6135,
"step": 299
},
{
"epoch": 0.6,
"learning_rate": 1.8504189081649678e-05,
"loss": 0.654,
"step": 300
},
{
"epoch": 0.61,
"learning_rate": 1.8492738790086066e-05,
"loss": 0.5991,
"step": 301
},
{
"epoch": 0.61,
"learning_rate": 1.8481248410857925e-05,
"loss": 0.6124,
"step": 302
},
{
"epoch": 0.61,
"learning_rate": 1.8469717998202464e-05,
"loss": 0.5958,
"step": 303
},
{
"epoch": 0.61,
"learning_rate": 1.845814760654586e-05,
"loss": 0.6014,
"step": 304
},
{
"epoch": 0.61,
"learning_rate": 1.844653729050301e-05,
"loss": 0.5906,
"step": 305
},
{
"epoch": 0.62,
"learning_rate": 1.843488710487724e-05,
"loss": 0.5752,
"step": 306
},
{
"epoch": 0.62,
"learning_rate": 1.8423197104660094e-05,
"loss": 0.5934,
"step": 307
},
{
"epoch": 0.62,
"learning_rate": 1.841146734503104e-05,
"loss": 0.5913,
"step": 308
},
{
"epoch": 0.62,
"learning_rate": 1.8399697881357214e-05,
"loss": 0.591,
"step": 309
},
{
"epoch": 0.62,
"learning_rate": 1.8387888769193175e-05,
"loss": 0.6367,
"step": 310
},
{
"epoch": 0.63,
"learning_rate": 1.8376040064280616e-05,
"loss": 0.706,
"step": 311
},
{
"epoch": 0.63,
"learning_rate": 1.836415182254814e-05,
"loss": 0.7543,
"step": 312
},
{
"epoch": 0.63,
"learning_rate": 1.835222410011096e-05,
"loss": 0.6343,
"step": 313
},
{
"epoch": 0.63,
"learning_rate": 1.8340256953270636e-05,
"loss": 0.5754,
"step": 314
},
{
"epoch": 0.63,
"learning_rate": 1.8328250438514837e-05,
"loss": 0.5878,
"step": 315
},
{
"epoch": 0.64,
"learning_rate": 1.8316204612517053e-05,
"loss": 0.6134,
"step": 316
},
{
"epoch": 0.64,
"learning_rate": 1.8304119532136328e-05,
"loss": 0.5973,
"step": 317
},
{
"epoch": 0.64,
"learning_rate": 1.8291995254417e-05,
"loss": 0.6178,
"step": 318
},
{
"epoch": 0.64,
"learning_rate": 1.8279831836588427e-05,
"loss": 0.6964,
"step": 319
},
{
"epoch": 0.64,
"learning_rate": 1.8267629336064713e-05,
"loss": 0.6128,
"step": 320
},
{
"epoch": 0.65,
"learning_rate": 1.8255387810444447e-05,
"loss": 0.5816,
"step": 321
},
{
"epoch": 0.65,
"learning_rate": 1.8243107317510416e-05,
"loss": 0.5919,
"step": 322
},
{
"epoch": 0.65,
"learning_rate": 1.8230787915229358e-05,
"loss": 0.7568,
"step": 323
},
{
"epoch": 0.65,
"learning_rate": 1.821842966175166e-05,
"loss": 0.6658,
"step": 324
},
{
"epoch": 0.65,
"learning_rate": 1.8206032615411092e-05,
"loss": 0.5999,
"step": 325
},
{
"epoch": 0.66,
"learning_rate": 1.8193596834724546e-05,
"loss": 0.6797,
"step": 326
},
{
"epoch": 0.66,
"learning_rate": 1.818112237839174e-05,
"loss": 0.6933,
"step": 327
},
{
"epoch": 0.66,
"learning_rate": 1.816860930529496e-05,
"loss": 0.5794,
"step": 328
},
{
"epoch": 0.66,
"learning_rate": 1.8156057674498756e-05,
"loss": 0.5638,
"step": 329
},
{
"epoch": 0.66,
"learning_rate": 1.8143467545249694e-05,
"loss": 0.662,
"step": 330
},
{
"epoch": 0.67,
"learning_rate": 1.8130838976976058e-05,
"loss": 0.6788,
"step": 331
},
{
"epoch": 0.67,
"learning_rate": 1.811817202928757e-05,
"loss": 0.5837,
"step": 332
},
{
"epoch": 0.67,
"learning_rate": 1.810546676197511e-05,
"loss": 0.5861,
"step": 333
},
{
"epoch": 0.67,
"learning_rate": 1.8092723235010443e-05,
"loss": 0.553,
"step": 334
},
{
"epoch": 0.67,
"learning_rate": 1.807994150854592e-05,
"loss": 0.5931,
"step": 335
},
{
"epoch": 0.68,
"learning_rate": 1.8067121642914205e-05,
"loss": 0.6222,
"step": 336
},
{
"epoch": 0.68,
"learning_rate": 1.805426369862799e-05,
"loss": 0.5524,
"step": 337
},
{
"epoch": 0.68,
"learning_rate": 1.804136773637971e-05,
"loss": 0.7273,
"step": 338
},
{
"epoch": 0.68,
"learning_rate": 1.8028433817041237e-05,
"loss": 0.5707,
"step": 339
},
{
"epoch": 0.68,
"learning_rate": 1.8015462001663634e-05,
"loss": 0.6276,
"step": 340
},
{
"epoch": 0.69,
"learning_rate": 1.8002452351476817e-05,
"loss": 0.6037,
"step": 341
},
{
"epoch": 0.69,
"learning_rate": 1.7989404927889315e-05,
"loss": 0.6007,
"step": 342
},
{
"epoch": 0.69,
"learning_rate": 1.7976319792487933e-05,
"loss": 0.5752,
"step": 343
},
{
"epoch": 0.69,
"learning_rate": 1.79631970070375e-05,
"loss": 0.558,
"step": 344
},
{
"epoch": 0.69,
"learning_rate": 1.7950036633480557e-05,
"loss": 0.5823,
"step": 345
},
{
"epoch": 0.7,
"learning_rate": 1.793683873393707e-05,
"loss": 0.5677,
"step": 346
},
{
"epoch": 0.7,
"learning_rate": 1.7923603370704136e-05,
"loss": 0.5737,
"step": 347
},
{
"epoch": 0.7,
"learning_rate": 1.7910330606255683e-05,
"loss": 0.5686,
"step": 348
},
{
"epoch": 0.7,
"learning_rate": 1.7897020503242192e-05,
"loss": 0.5714,
"step": 349
},
{
"epoch": 0.7,
"learning_rate": 1.788367312449039e-05,
"loss": 0.6129,
"step": 350
},
{
"epoch": 0.71,
"learning_rate": 1.787028853300294e-05,
"loss": 0.6317,
"step": 351
},
{
"epoch": 0.71,
"learning_rate": 1.7856866791958176e-05,
"loss": 0.5981,
"step": 352
},
{
"epoch": 0.71,
"learning_rate": 1.7843407964709773e-05,
"loss": 0.6127,
"step": 353
},
{
"epoch": 0.71,
"learning_rate": 1.7829912114786462e-05,
"loss": 0.6201,
"step": 354
},
{
"epoch": 0.71,
"learning_rate": 1.7816379305891743e-05,
"loss": 0.6805,
"step": 355
},
{
"epoch": 0.72,
"learning_rate": 1.7802809601903553e-05,
"loss": 0.5884,
"step": 356
},
{
"epoch": 0.72,
"learning_rate": 1.7789203066874e-05,
"loss": 0.553,
"step": 357
},
{
"epoch": 0.72,
"learning_rate": 1.777555976502902e-05,
"loss": 0.5272,
"step": 358
},
{
"epoch": 0.72,
"learning_rate": 1.7761879760768123e-05,
"loss": 0.6008,
"step": 359
},
{
"epoch": 0.72,
"learning_rate": 1.774816311866404e-05,
"loss": 0.5717,
"step": 360
},
{
"epoch": 0.73,
"learning_rate": 1.7734409903462454e-05,
"loss": 0.5719,
"step": 361
},
{
"epoch": 0.73,
"learning_rate": 1.7720620180081684e-05,
"loss": 0.5711,
"step": 362
},
{
"epoch": 0.73,
"learning_rate": 1.7706794013612367e-05,
"loss": 0.6041,
"step": 363
},
{
"epoch": 0.73,
"learning_rate": 1.7692931469317157e-05,
"loss": 0.7679,
"step": 364
},
{
"epoch": 0.73,
"learning_rate": 1.7679032612630432e-05,
"loss": 0.6773,
"step": 365
},
{
"epoch": 0.74,
"learning_rate": 1.7665097509157962e-05,
"loss": 0.6028,
"step": 366
},
{
"epoch": 0.74,
"learning_rate": 1.7651126224676616e-05,
"loss": 0.6787,
"step": 367
},
{
"epoch": 0.74,
"learning_rate": 1.763711882513405e-05,
"loss": 0.6255,
"step": 368
},
{
"epoch": 0.74,
"learning_rate": 1.7623075376648374e-05,
"loss": 0.5667,
"step": 369
},
{
"epoch": 0.74,
"learning_rate": 1.760899594550788e-05,
"loss": 0.6035,
"step": 370
},
{
"epoch": 0.75,
"learning_rate": 1.7594880598170688e-05,
"loss": 0.582,
"step": 371
},
{
"epoch": 0.75,
"learning_rate": 1.758072940126446e-05,
"loss": 0.7136,
"step": 372
},
{
"epoch": 0.75,
"learning_rate": 1.756654242158607e-05,
"loss": 0.5721,
"step": 373
},
{
"epoch": 0.75,
"learning_rate": 1.7552319726101305e-05,
"loss": 0.5745,
"step": 374
},
{
"epoch": 0.75,
"learning_rate": 1.7538061381944524e-05,
"loss": 0.6034,
"step": 375
},
{
"epoch": 0.76,
"learning_rate": 1.7523767456418374e-05,
"loss": 0.5628,
"step": 376
},
{
"epoch": 0.76,
"learning_rate": 1.7509438016993435e-05,
"loss": 0.5955,
"step": 377
},
{
"epoch": 0.76,
"learning_rate": 1.7495073131307933e-05,
"loss": 0.5836,
"step": 378
},
{
"epoch": 0.76,
"learning_rate": 1.748067286716741e-05,
"loss": 0.6057,
"step": 379
},
{
"epoch": 0.76,
"learning_rate": 1.7466237292544394e-05,
"loss": 0.6205,
"step": 380
},
{
"epoch": 0.77,
"learning_rate": 1.745176647557809e-05,
"loss": 0.6238,
"step": 381
},
{
"epoch": 0.77,
"learning_rate": 1.7437260484574058e-05,
"loss": 0.5857,
"step": 382
},
{
"epoch": 0.77,
"learning_rate": 1.7422719388003882e-05,
"loss": 0.6108,
"step": 383
},
{
"epoch": 0.77,
"learning_rate": 1.7408143254504857e-05,
"loss": 0.6735,
"step": 384
},
{
"epoch": 0.77,
"learning_rate": 1.739353215287965e-05,
"loss": 0.5804,
"step": 385
},
{
"epoch": 0.78,
"learning_rate": 1.7378886152096013e-05,
"loss": 0.6872,
"step": 386
},
{
"epoch": 0.78,
"learning_rate": 1.7364205321286393e-05,
"loss": 0.5727,
"step": 387
},
{
"epoch": 0.78,
"learning_rate": 1.7349489729747667e-05,
"loss": 0.5753,
"step": 388
},
{
"epoch": 0.78,
"learning_rate": 1.7334739446940785e-05,
"loss": 0.5559,
"step": 389
},
{
"epoch": 0.78,
"learning_rate": 1.7319954542490448e-05,
"loss": 0.577,
"step": 390
},
{
"epoch": 0.79,
"learning_rate": 1.730513508618477e-05,
"loss": 0.5581,
"step": 391
},
{
"epoch": 0.79,
"learning_rate": 1.7290281147974973e-05,
"loss": 0.5623,
"step": 392
},
{
"epoch": 0.79,
"learning_rate": 1.7275392797975034e-05,
"loss": 0.5923,
"step": 393
},
{
"epoch": 0.79,
"learning_rate": 1.726047010646136e-05,
"loss": 0.6495,
"step": 394
},
{
"epoch": 0.79,
"learning_rate": 1.7245513143872458e-05,
"loss": 0.5955,
"step": 395
},
{
"epoch": 0.8,
"learning_rate": 1.7230521980808602e-05,
"loss": 0.5952,
"step": 396
},
{
"epoch": 0.8,
"learning_rate": 1.7215496688031504e-05,
"loss": 0.5878,
"step": 397
},
{
"epoch": 0.8,
"learning_rate": 1.7200437336463974e-05,
"loss": 0.585,
"step": 398
},
{
"epoch": 0.8,
"learning_rate": 1.718534399718959e-05,
"loss": 0.6379,
"step": 399
},
{
"epoch": 0.8,
"learning_rate": 1.7170216741452348e-05,
"loss": 0.5961,
"step": 400
},
{
"epoch": 0.81,
"learning_rate": 1.7155055640656353e-05,
"loss": 0.5524,
"step": 401
},
{
"epoch": 0.81,
"learning_rate": 1.713986076636546e-05,
"loss": 0.5761,
"step": 402
},
{
"epoch": 0.81,
"learning_rate": 1.7124632190302936e-05,
"loss": 0.5876,
"step": 403
},
{
"epoch": 0.81,
"learning_rate": 1.7109369984351138e-05,
"loss": 0.5424,
"step": 404
},
{
"epoch": 0.81,
"learning_rate": 1.709407422055116e-05,
"loss": 0.6841,
"step": 405
},
{
"epoch": 0.82,
"learning_rate": 1.7078744971102495e-05,
"loss": 0.5808,
"step": 406
},
{
"epoch": 0.82,
"learning_rate": 1.70633823083627e-05,
"loss": 0.5728,
"step": 407
},
{
"epoch": 0.82,
"learning_rate": 1.7047986304847044e-05,
"loss": 0.5623,
"step": 408
},
{
"epoch": 0.82,
"learning_rate": 1.7032557033228184e-05,
"loss": 0.6099,
"step": 409
},
{
"epoch": 0.82,
"learning_rate": 1.701709456633579e-05,
"loss": 0.6063,
"step": 410
},
{
"epoch": 0.83,
"learning_rate": 1.700159897715624e-05,
"loss": 0.5436,
"step": 411
},
{
"epoch": 0.83,
"learning_rate": 1.698607033883225e-05,
"loss": 0.6938,
"step": 412
},
{
"epoch": 0.83,
"learning_rate": 1.6970508724662536e-05,
"loss": 0.6121,
"step": 413
},
{
"epoch": 0.83,
"learning_rate": 1.6954914208101464e-05,
"loss": 0.6442,
"step": 414
},
{
"epoch": 0.83,
"learning_rate": 1.693928686275871e-05,
"loss": 0.7298,
"step": 415
},
{
"epoch": 0.84,
"learning_rate": 1.6923626762398912e-05,
"loss": 0.5864,
"step": 416
},
{
"epoch": 0.84,
"learning_rate": 1.6907933980941312e-05,
"loss": 0.5874,
"step": 417
},
{
"epoch": 0.84,
"learning_rate": 1.6892208592459424e-05,
"loss": 0.6211,
"step": 418
},
{
"epoch": 0.84,
"learning_rate": 1.6876450671180667e-05,
"loss": 0.5579,
"step": 419
},
{
"epoch": 0.84,
"learning_rate": 1.6860660291486023e-05,
"loss": 0.6077,
"step": 420
},
{
"epoch": 0.85,
"learning_rate": 1.6844837527909682e-05,
"loss": 0.6134,
"step": 421
},
{
"epoch": 0.85,
"learning_rate": 1.6828982455138706e-05,
"loss": 0.6123,
"step": 422
},
{
"epoch": 0.85,
"learning_rate": 1.681309514801265e-05,
"loss": 0.5808,
"step": 423
},
{
"epoch": 0.85,
"learning_rate": 1.6797175681523232e-05,
"loss": 0.6948,
"step": 424
},
{
"epoch": 0.85,
"learning_rate": 1.6781224130813966e-05,
"loss": 0.6476,
"step": 425
},
{
"epoch": 0.86,
"learning_rate": 1.67652405711798e-05,
"loss": 0.5856,
"step": 426
},
{
"epoch": 0.86,
"learning_rate": 1.6749225078066796e-05,
"loss": 0.6258,
"step": 427
},
{
"epoch": 0.86,
"learning_rate": 1.6733177727071725e-05,
"loss": 0.7355,
"step": 428
},
{
"epoch": 0.86,
"learning_rate": 1.6717098593941753e-05,
"loss": 0.5877,
"step": 429
},
{
"epoch": 0.86,
"learning_rate": 1.670098775457405e-05,
"loss": 0.5791,
"step": 430
},
{
"epoch": 0.87,
"learning_rate": 1.6684845285015453e-05,
"loss": 0.5701,
"step": 431
},
{
"epoch": 0.87,
"learning_rate": 1.6668671261462102e-05,
"loss": 0.7521,
"step": 432
},
{
"epoch": 0.87,
"learning_rate": 1.665246576025908e-05,
"loss": 0.6228,
"step": 433
},
{
"epoch": 0.87,
"learning_rate": 1.6636228857900046e-05,
"loss": 0.6457,
"step": 434
},
{
"epoch": 0.87,
"learning_rate": 1.661996063102689e-05,
"loss": 0.5992,
"step": 435
},
{
"epoch": 0.88,
"learning_rate": 1.660366115642935e-05,
"loss": 0.5986,
"step": 436
},
{
"epoch": 0.88,
"learning_rate": 1.658733051104466e-05,
"loss": 0.5841,
"step": 437
},
{
"epoch": 0.88,
"learning_rate": 1.6570968771957195e-05,
"loss": 0.5535,
"step": 438
},
{
"epoch": 0.88,
"learning_rate": 1.65545760163981e-05,
"loss": 0.5401,
"step": 439
},
{
"epoch": 0.88,
"learning_rate": 1.653815232174492e-05,
"loss": 0.5658,
"step": 440
},
{
"epoch": 0.89,
"learning_rate": 1.6521697765521232e-05,
"loss": 0.5771,
"step": 441
},
{
"epoch": 0.89,
"learning_rate": 1.6505212425396306e-05,
"loss": 0.6113,
"step": 442
},
{
"epoch": 0.89,
"learning_rate": 1.64886963791847e-05,
"loss": 0.6014,
"step": 443
},
{
"epoch": 0.89,
"learning_rate": 1.647214970484593e-05,
"loss": 0.8507,
"step": 444
},
{
"epoch": 0.89,
"learning_rate": 1.645557248048406e-05,
"loss": 0.641,
"step": 445
},
{
"epoch": 0.9,
"learning_rate": 1.6438964784347384e-05,
"loss": 0.6027,
"step": 446
},
{
"epoch": 0.9,
"learning_rate": 1.642232669482801e-05,
"loss": 0.5503,
"step": 447
},
{
"epoch": 0.9,
"learning_rate": 1.6405658290461512e-05,
"loss": 0.5532,
"step": 448
},
{
"epoch": 0.9,
"learning_rate": 1.6388959649926567e-05,
"loss": 0.6179,
"step": 449
},
{
"epoch": 0.9,
"learning_rate": 1.637223085204457e-05,
"loss": 0.5626,
"step": 450
},
{
"epoch": 0.91,
"learning_rate": 1.6355471975779255e-05,
"loss": 0.7257,
"step": 451
},
{
"epoch": 0.91,
"learning_rate": 1.633868310023635e-05,
"loss": 0.5916,
"step": 452
},
{
"epoch": 0.91,
"learning_rate": 1.6321864304663174e-05,
"loss": 0.6151,
"step": 453
},
{
"epoch": 0.91,
"learning_rate": 1.6305015668448276e-05,
"loss": 0.5955,
"step": 454
},
{
"epoch": 0.91,
"learning_rate": 1.6288137271121066e-05,
"loss": 0.589,
"step": 455
},
{
"epoch": 0.92,
"learning_rate": 1.6271229192351428e-05,
"loss": 0.5545,
"step": 456
},
{
"epoch": 0.92,
"learning_rate": 1.6254291511949353e-05,
"loss": 0.5469,
"step": 457
},
{
"epoch": 0.92,
"learning_rate": 1.6237324309864554e-05,
"loss": 0.5709,
"step": 458
},
{
"epoch": 0.92,
"learning_rate": 1.62203276661861e-05,
"loss": 0.5562,
"step": 459
},
{
"epoch": 0.92,
"learning_rate": 1.6203301661142023e-05,
"loss": 0.6669,
"step": 460
},
{
"epoch": 0.93,
"learning_rate": 1.618624637509895e-05,
"loss": 0.6165,
"step": 461
},
{
"epoch": 0.93,
"learning_rate": 1.6169161888561723e-05,
"loss": 0.747,
"step": 462
},
{
"epoch": 0.93,
"learning_rate": 1.615204828217302e-05,
"loss": 0.5826,
"step": 463
},
{
"epoch": 0.93,
"learning_rate": 1.613490563671296e-05,
"loss": 0.9282,
"step": 464
},
{
"epoch": 0.94,
"learning_rate": 1.6117734033098744e-05,
"loss": 0.7111,
"step": 465
},
{
"epoch": 0.94,
"learning_rate": 1.6100533552384262e-05,
"loss": 0.549,
"step": 466
},
{
"epoch": 0.94,
"learning_rate": 1.60833042757597e-05,
"loss": 0.5482,
"step": 467
},
{
"epoch": 0.94,
"learning_rate": 1.606604628455118e-05,
"loss": 0.524,
"step": 468
},
{
"epoch": 0.94,
"learning_rate": 1.604875966022035e-05,
"loss": 0.5872,
"step": 469
},
{
"epoch": 0.95,
"learning_rate": 1.603144448436403e-05,
"loss": 0.6336,
"step": 470
},
{
"epoch": 0.95,
"learning_rate": 1.6014100838713796e-05,
"loss": 0.5909,
"step": 471
},
{
"epoch": 0.95,
"learning_rate": 1.599672880513561e-05,
"loss": 0.6137,
"step": 472
},
{
"epoch": 0.95,
"learning_rate": 1.5979328465629435e-05,
"loss": 0.5883,
"step": 473
},
{
"epoch": 0.95,
"learning_rate": 1.5961899902328845e-05,
"loss": 0.6074,
"step": 474
},
{
"epoch": 0.96,
"learning_rate": 1.5944443197500633e-05,
"loss": 0.5671,
"step": 475
},
{
"epoch": 0.96,
"learning_rate": 1.5926958433544426e-05,
"loss": 0.5629,
"step": 476
},
{
"epoch": 0.96,
"learning_rate": 1.59094456929923e-05,
"loss": 0.6148,
"step": 477
},
{
"epoch": 0.96,
"learning_rate": 1.589190505850839e-05,
"loss": 0.7015,
"step": 478
},
{
"epoch": 0.96,
"learning_rate": 1.5874336612888487e-05,
"loss": 0.5782,
"step": 479
},
{
"epoch": 0.97,
"learning_rate": 1.585674043905966e-05,
"loss": 0.5524,
"step": 480
},
{
"epoch": 0.97,
"learning_rate": 1.5839116620079874e-05,
"loss": 0.5555,
"step": 481
},
{
"epoch": 0.97,
"learning_rate": 1.5821465239137562e-05,
"loss": 0.5602,
"step": 482
},
{
"epoch": 0.97,
"learning_rate": 1.580378637955128e-05,
"loss": 0.7192,
"step": 483
},
{
"epoch": 0.97,
"learning_rate": 1.5786080124769274e-05,
"loss": 0.6205,
"step": 484
},
{
"epoch": 0.98,
"learning_rate": 1.5768346558369105e-05,
"loss": 0.5976,
"step": 485
},
{
"epoch": 0.98,
"learning_rate": 1.5750585764057248e-05,
"loss": 0.5837,
"step": 486
},
{
"epoch": 0.98,
"learning_rate": 1.5732797825668714e-05,
"loss": 0.5766,
"step": 487
},
{
"epoch": 0.98,
"learning_rate": 1.571498282716662e-05,
"loss": 0.6003,
"step": 488
},
{
"epoch": 0.98,
"learning_rate": 1.5697140852641835e-05,
"loss": 0.5367,
"step": 489
},
{
"epoch": 0.99,
"learning_rate": 1.5679271986312538e-05,
"loss": 0.6137,
"step": 490
},
{
"epoch": 0.99,
"learning_rate": 1.5661376312523854e-05,
"loss": 0.5756,
"step": 491
},
{
"epoch": 0.99,
"learning_rate": 1.5643453915747457e-05,
"loss": 0.6044,
"step": 492
},
{
"epoch": 0.99,
"learning_rate": 1.5625504880581136e-05,
"loss": 0.5806,
"step": 493
},
{
"epoch": 0.99,
"learning_rate": 1.560752929174844e-05,
"loss": 0.5926,
"step": 494
},
{
"epoch": 1.0,
"learning_rate": 1.5589527234098247e-05,
"loss": 0.6179,
"step": 495
},
{
"epoch": 1.0,
"learning_rate": 1.5571498792604375e-05,
"loss": 0.6062,
"step": 496
},
{
"epoch": 1.0,
"learning_rate": 1.5553444052365176e-05,
"loss": 0.5804,
"step": 497
},
{
"epoch": 1.0,
"learning_rate": 1.5535363098603152e-05,
"loss": 0.435,
"step": 498
},
{
"epoch": 1.0,
"learning_rate": 1.5517256016664524e-05,
"loss": 0.3597,
"step": 499
},
{
"epoch": 1.01,
"learning_rate": 1.549912289201885e-05,
"loss": 0.3695,
"step": 500
},
{
"epoch": 1.01,
"learning_rate": 1.5480963810258614e-05,
"loss": 0.378,
"step": 501
},
{
"epoch": 1.01,
"learning_rate": 1.546277885709883e-05,
"loss": 0.3793,
"step": 502
},
{
"epoch": 1.01,
"learning_rate": 1.5444568118376615e-05,
"loss": 0.389,
"step": 503
},
{
"epoch": 1.01,
"learning_rate": 1.5426331680050823e-05,
"loss": 0.3663,
"step": 504
},
{
"epoch": 1.02,
"learning_rate": 1.5408069628201597e-05,
"loss": 0.4153,
"step": 505
},
{
"epoch": 1.02,
"learning_rate": 1.5389782049029984e-05,
"loss": 0.3564,
"step": 506
},
{
"epoch": 1.02,
"learning_rate": 1.5371469028857534e-05,
"loss": 0.3572,
"step": 507
},
{
"epoch": 1.02,
"learning_rate": 1.535313065412588e-05,
"loss": 0.341,
"step": 508
},
{
"epoch": 1.02,
"learning_rate": 1.533476701139633e-05,
"loss": 0.3383,
"step": 509
},
{
"epoch": 1.03,
"learning_rate": 1.5316378187349476e-05,
"loss": 0.3345,
"step": 510
},
{
"epoch": 1.03,
"learning_rate": 1.5297964268784757e-05,
"loss": 0.3564,
"step": 511
},
{
"epoch": 1.03,
"learning_rate": 1.5279525342620063e-05,
"loss": 0.328,
"step": 512
},
{
"epoch": 1.03,
"learning_rate": 1.5261061495891345e-05,
"loss": 0.3633,
"step": 513
},
{
"epoch": 1.03,
"learning_rate": 1.5242572815752162e-05,
"loss": 0.3616,
"step": 514
},
{
"epoch": 1.04,
"learning_rate": 1.5224059389473305e-05,
"loss": 0.3739,
"step": 515
},
{
"epoch": 1.04,
"learning_rate": 1.5205521304442367e-05,
"loss": 0.3538,
"step": 516
},
{
"epoch": 1.04,
"learning_rate": 1.5186958648163344e-05,
"loss": 0.3509,
"step": 517
},
{
"epoch": 1.04,
"learning_rate": 1.5168371508256205e-05,
"loss": 0.3668,
"step": 518
},
{
"epoch": 1.04,
"learning_rate": 1.514975997245649e-05,
"loss": 0.4071,
"step": 519
},
{
"epoch": 1.05,
"learning_rate": 1.5131124128614896e-05,
"loss": 0.3506,
"step": 520
},
{
"epoch": 1.05,
"learning_rate": 1.5112464064696857e-05,
"loss": 0.4424,
"step": 521
},
{
"epoch": 1.05,
"learning_rate": 1.509377986878213e-05,
"loss": 0.3644,
"step": 522
},
{
"epoch": 1.05,
"learning_rate": 1.5075071629064381e-05,
"loss": 0.3714,
"step": 523
},
{
"epoch": 1.05,
"learning_rate": 1.5056339433850772e-05,
"loss": 0.4337,
"step": 524
},
{
"epoch": 1.06,
"learning_rate": 1.5037583371561538e-05,
"loss": 0.4026,
"step": 525
},
{
"epoch": 1.06,
"learning_rate": 1.5018803530729571e-05,
"loss": 0.3623,
"step": 526
},
{
"epoch": 1.06,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.4134,
"step": 527
},
{
"epoch": 1.06,
"learning_rate": 1.4981172868129787e-05,
"loss": 0.3529,
"step": 528
},
{
"epoch": 1.06,
"learning_rate": 1.4962322223987284e-05,
"loss": 0.3713,
"step": 529
},
{
"epoch": 1.07,
"learning_rate": 1.4943448156551836e-05,
"loss": 0.3634,
"step": 530
},
{
"epoch": 1.07,
"learning_rate": 1.4924550754913341e-05,
"loss": 0.4101,
"step": 531
},
{
"epoch": 1.07,
"learning_rate": 1.4905630108271851e-05,
"loss": 0.3463,
"step": 532
},
{
"epoch": 1.07,
"learning_rate": 1.4886686305937133e-05,
"loss": 0.3418,
"step": 533
},
{
"epoch": 1.07,
"learning_rate": 1.4867719437328254e-05,
"loss": 0.3469,
"step": 534
},
{
"epoch": 1.08,
"learning_rate": 1.4848729591973165e-05,
"loss": 0.3909,
"step": 535
},
{
"epoch": 1.08,
"learning_rate": 1.4829716859508264e-05,
"loss": 0.3497,
"step": 536
},
{
"epoch": 1.08,
"learning_rate": 1.4810681329677988e-05,
"loss": 0.3557,
"step": 537
},
{
"epoch": 1.08,
"learning_rate": 1.4791623092334378e-05,
"loss": 0.3682,
"step": 538
},
{
"epoch": 1.08,
"learning_rate": 1.477254223743666e-05,
"loss": 0.3985,
"step": 539
},
{
"epoch": 1.09,
"learning_rate": 1.475343885505083e-05,
"loss": 0.3575,
"step": 540
},
{
"epoch": 1.09,
"learning_rate": 1.4734313035349205e-05,
"loss": 0.3658,
"step": 541
},
{
"epoch": 1.09,
"learning_rate": 1.471516486861002e-05,
"loss": 0.3512,
"step": 542
},
{
"epoch": 1.09,
"learning_rate": 1.4695994445216985e-05,
"loss": 0.3606,
"step": 543
},
{
"epoch": 1.09,
"learning_rate": 1.4676801855658878e-05,
"loss": 0.3327,
"step": 544
},
{
"epoch": 1.1,
"learning_rate": 1.4657587190529099e-05,
"loss": 0.3285,
"step": 545
},
{
"epoch": 1.1,
"learning_rate": 1.4638350540525248e-05,
"loss": 0.3671,
"step": 546
},
{
"epoch": 1.1,
"learning_rate": 1.4619091996448703e-05,
"loss": 0.3651,
"step": 547
},
{
"epoch": 1.1,
"learning_rate": 1.4599811649204183e-05,
"loss": 0.4026,
"step": 548
},
{
"epoch": 1.1,
"learning_rate": 1.458050958979933e-05,
"loss": 0.3526,
"step": 549
},
{
"epoch": 1.11,
"learning_rate": 1.4561185909344265e-05,
"loss": 0.3725,
"step": 550
},
{
"epoch": 1.11,
"learning_rate": 1.4541840699051168e-05,
"loss": 0.3787,
"step": 551
},
{
"epoch": 1.11,
"learning_rate": 1.4522474050233845e-05,
"loss": 0.3444,
"step": 552
},
{
"epoch": 1.11,
"learning_rate": 1.4503086054307299e-05,
"loss": 0.3669,
"step": 553
},
{
"epoch": 1.11,
"learning_rate": 1.4483676802787288e-05,
"loss": 0.4485,
"step": 554
},
{
"epoch": 1.12,
"learning_rate": 1.4464246387289913e-05,
"loss": 0.3487,
"step": 555
},
{
"epoch": 1.12,
"learning_rate": 1.4444794899531165e-05,
"loss": 0.3457,
"step": 556
},
{
"epoch": 1.12,
"learning_rate": 1.4425322431326504e-05,
"loss": 0.3599,
"step": 557
},
{
"epoch": 1.12,
"learning_rate": 1.4405829074590422e-05,
"loss": 0.3868,
"step": 558
},
{
"epoch": 1.12,
"learning_rate": 1.438631492133601e-05,
"loss": 0.347,
"step": 559
},
{
"epoch": 1.13,
"learning_rate": 1.4366780063674524e-05,
"loss": 0.3381,
"step": 560
},
{
"epoch": 1.13,
"learning_rate": 1.4347224593814946e-05,
"loss": 0.3731,
"step": 561
},
{
"epoch": 1.13,
"learning_rate": 1.4327648604063555e-05,
"loss": 0.3547,
"step": 562
},
{
"epoch": 1.13,
"learning_rate": 1.4308052186823494e-05,
"loss": 0.3616,
"step": 563
},
{
"epoch": 1.13,
"learning_rate": 1.4288435434594317e-05,
"loss": 0.3395,
"step": 564
},
{
"epoch": 1.14,
"learning_rate": 1.4268798439971572e-05,
"loss": 0.3485,
"step": 565
},
{
"epoch": 1.14,
"learning_rate": 1.4249141295646353e-05,
"loss": 0.3679,
"step": 566
},
{
"epoch": 1.14,
"learning_rate": 1.4229464094404866e-05,
"loss": 0.3592,
"step": 567
},
{
"epoch": 1.14,
"learning_rate": 1.420976692912799e-05,
"loss": 0.38,
"step": 568
},
{
"epoch": 1.14,
"learning_rate": 1.4190049892790838e-05,
"loss": 0.3686,
"step": 569
},
{
"epoch": 1.15,
"learning_rate": 1.4170313078462318e-05,
"loss": 0.3402,
"step": 570
},
{
"epoch": 1.15,
"learning_rate": 1.4150556579304699e-05,
"loss": 0.3402,
"step": 571
},
{
"epoch": 1.15,
"learning_rate": 1.4130780488573162e-05,
"loss": 0.3392,
"step": 572
},
{
"epoch": 1.15,
"learning_rate": 1.4110984899615367e-05,
"loss": 0.3753,
"step": 573
},
{
"epoch": 1.15,
"learning_rate": 1.4091169905871014e-05,
"loss": 0.3428,
"step": 574
},
{
"epoch": 1.16,
"learning_rate": 1.4071335600871388e-05,
"loss": 0.3619,
"step": 575
},
{
"epoch": 1.16,
"learning_rate": 1.4051482078238932e-05,
"loss": 0.348,
"step": 576
},
{
"epoch": 1.16,
"learning_rate": 1.4031609431686809e-05,
"loss": 0.3614,
"step": 577
},
{
"epoch": 1.16,
"learning_rate": 1.4011717755018442e-05,
"loss": 0.3452,
"step": 578
},
{
"epoch": 1.16,
"learning_rate": 1.3991807142127082e-05,
"loss": 0.3303,
"step": 579
},
{
"epoch": 1.17,
"learning_rate": 1.3971877686995358e-05,
"loss": 0.3483,
"step": 580
},
{
"epoch": 1.17,
"learning_rate": 1.3951929483694855e-05,
"loss": 0.3686,
"step": 581
},
{
"epoch": 1.17,
"learning_rate": 1.393196262638564e-05,
"loss": 0.378,
"step": 582
},
{
"epoch": 1.17,
"learning_rate": 1.3911977209315828e-05,
"loss": 0.3586,
"step": 583
},
{
"epoch": 1.17,
"learning_rate": 1.3891973326821155e-05,
"loss": 0.3722,
"step": 584
},
{
"epoch": 1.18,
"learning_rate": 1.3871951073324508e-05,
"loss": 0.4421,
"step": 585
},
{
"epoch": 1.18,
"learning_rate": 1.3851910543335489e-05,
"loss": 0.3581,
"step": 586
},
{
"epoch": 1.18,
"learning_rate": 1.3831851831449973e-05,
"loss": 0.3534,
"step": 587
},
{
"epoch": 1.18,
"learning_rate": 1.3811775032349654e-05,
"loss": 0.3637,
"step": 588
},
{
"epoch": 1.18,
"learning_rate": 1.3791680240801608e-05,
"loss": 0.3398,
"step": 589
},
{
"epoch": 1.19,
"learning_rate": 1.3771567551657832e-05,
"loss": 0.3914,
"step": 590
},
{
"epoch": 1.19,
"learning_rate": 1.3751437059854809e-05,
"loss": 0.3764,
"step": 591
},
{
"epoch": 1.19,
"learning_rate": 1.3731288860413048e-05,
"loss": 0.3779,
"step": 592
},
{
"epoch": 1.19,
"learning_rate": 1.3711123048436652e-05,
"loss": 0.4432,
"step": 593
},
{
"epoch": 1.19,
"learning_rate": 1.3690939719112852e-05,
"loss": 0.3556,
"step": 594
},
{
"epoch": 1.2,
"learning_rate": 1.3670738967711566e-05,
"loss": 0.3575,
"step": 595
},
{
"epoch": 1.2,
"learning_rate": 1.365052088958495e-05,
"loss": 0.3648,
"step": 596
},
{
"epoch": 1.2,
"learning_rate": 1.3630285580166946e-05,
"loss": 0.3377,
"step": 597
},
{
"epoch": 1.2,
"learning_rate": 1.361003313497283e-05,
"loss": 0.3419,
"step": 598
},
{
"epoch": 1.2,
"learning_rate": 1.358976364959876e-05,
"loss": 0.3683,
"step": 599
},
{
"epoch": 1.21,
"learning_rate": 1.3569477219721336e-05,
"loss": 0.3574,
"step": 600
},
{
"epoch": 1.21,
"learning_rate": 1.3549173941097134e-05,
"loss": 0.4209,
"step": 601
},
{
"epoch": 1.21,
"learning_rate": 1.3528853909562261e-05,
"loss": 0.3588,
"step": 602
},
{
"epoch": 1.21,
"learning_rate": 1.3508517221031898e-05,
"loss": 0.3598,
"step": 603
},
{
"epoch": 1.21,
"learning_rate": 1.348816397149986e-05,
"loss": 0.3415,
"step": 604
},
{
"epoch": 1.22,
"learning_rate": 1.346779425703812e-05,
"loss": 0.3576,
"step": 605
},
{
"epoch": 1.22,
"learning_rate": 1.3447408173796386e-05,
"loss": 0.3693,
"step": 606
},
{
"epoch": 1.22,
"learning_rate": 1.3427005818001615e-05,
"loss": 0.4247,
"step": 607
},
{
"epoch": 1.22,
"learning_rate": 1.3406587285957583e-05,
"loss": 0.3827,
"step": 608
},
{
"epoch": 1.22,
"learning_rate": 1.3386152674044421e-05,
"loss": 0.3099,
"step": 609
},
{
"epoch": 1.23,
"learning_rate": 1.3365702078718158e-05,
"loss": 0.335,
"step": 610
},
{
"epoch": 1.23,
"learning_rate": 1.334523559651027e-05,
"loss": 0.3381,
"step": 611
},
{
"epoch": 1.23,
"learning_rate": 1.3324753324027217e-05,
"loss": 0.4234,
"step": 612
},
{
"epoch": 1.23,
"learning_rate": 1.3304255357950004e-05,
"loss": 0.3573,
"step": 613
},
{
"epoch": 1.23,
"learning_rate": 1.3283741795033701e-05,
"loss": 0.3637,
"step": 614
},
{
"epoch": 1.24,
"learning_rate": 1.3263212732107014e-05,
"loss": 0.3667,
"step": 615
},
{
"epoch": 1.24,
"learning_rate": 1.3242668266071794e-05,
"loss": 0.3701,
"step": 616
},
{
"epoch": 1.24,
"learning_rate": 1.3222108493902613e-05,
"loss": 0.3404,
"step": 617
},
{
"epoch": 1.24,
"learning_rate": 1.320153351264628e-05,
"loss": 0.3867,
"step": 618
},
{
"epoch": 1.24,
"learning_rate": 1.3180943419421409e-05,
"loss": 0.3538,
"step": 619
},
{
"epoch": 1.25,
"learning_rate": 1.3160338311417928e-05,
"loss": 0.3547,
"step": 620
},
{
"epoch": 1.25,
"learning_rate": 1.3139718285896657e-05,
"loss": 0.3445,
"step": 621
},
{
"epoch": 1.25,
"learning_rate": 1.3119083440188809e-05,
"loss": 0.3627,
"step": 622
},
{
"epoch": 1.25,
"learning_rate": 1.3098433871695572e-05,
"loss": 0.3483,
"step": 623
},
{
"epoch": 1.25,
"learning_rate": 1.3077769677887619e-05,
"loss": 0.3353,
"step": 624
},
{
"epoch": 1.26,
"learning_rate": 1.305709095630466e-05,
"loss": 0.4418,
"step": 625
},
{
"epoch": 1.26,
"learning_rate": 1.3036397804554973e-05,
"loss": 0.3164,
"step": 626
},
{
"epoch": 1.26,
"learning_rate": 1.3015690320314952e-05,
"loss": 0.4305,
"step": 627
},
{
"epoch": 1.26,
"learning_rate": 1.299496860132866e-05,
"loss": 0.3532,
"step": 628
},
{
"epoch": 1.26,
"learning_rate": 1.2974232745407326e-05,
"loss": 0.3608,
"step": 629
},
{
"epoch": 1.27,
"learning_rate": 1.2953482850428927e-05,
"loss": 0.3985,
"step": 630
},
{
"epoch": 1.27,
"learning_rate": 1.2932719014337697e-05,
"loss": 0.3612,
"step": 631
},
{
"epoch": 1.27,
"learning_rate": 1.2911941335143683e-05,
"loss": 0.3332,
"step": 632
},
{
"epoch": 1.27,
"learning_rate": 1.2891149910922267e-05,
"loss": 0.3805,
"step": 633
},
{
"epoch": 1.27,
"learning_rate": 1.2870344839813716e-05,
"loss": 0.3773,
"step": 634
},
{
"epoch": 1.28,
"learning_rate": 1.2849526220022713e-05,
"loss": 0.3496,
"step": 635
},
{
"epoch": 1.28,
"learning_rate": 1.2828694149817889e-05,
"loss": 0.3578,
"step": 636
},
{
"epoch": 1.28,
"learning_rate": 1.2807848727531372e-05,
"loss": 0.345,
"step": 637
},
{
"epoch": 1.28,
"learning_rate": 1.2786990051558308e-05,
"loss": 0.3759,
"step": 638
},
{
"epoch": 1.28,
"learning_rate": 1.276611822035641e-05,
"loss": 0.3631,
"step": 639
},
{
"epoch": 1.29,
"learning_rate": 1.2745233332445475e-05,
"loss": 0.3441,
"step": 640
},
{
"epoch": 1.29,
"learning_rate": 1.2724335486406947e-05,
"loss": 0.3276,
"step": 641
},
{
"epoch": 1.29,
"learning_rate": 1.270342478088342e-05,
"loss": 0.4398,
"step": 642
},
{
"epoch": 1.29,
"learning_rate": 1.26825013145782e-05,
"loss": 0.3406,
"step": 643
},
{
"epoch": 1.29,
"learning_rate": 1.2661565186254814e-05,
"loss": 0.3587,
"step": 644
},
{
"epoch": 1.3,
"learning_rate": 1.264061649473657e-05,
"loss": 0.3584,
"step": 645
},
{
"epoch": 1.3,
"learning_rate": 1.2619655338906074e-05,
"loss": 0.3365,
"step": 646
},
{
"epoch": 1.3,
"learning_rate": 1.2598681817704755e-05,
"loss": 0.4065,
"step": 647
},
{
"epoch": 1.3,
"learning_rate": 1.2577696030132422e-05,
"loss": 0.3748,
"step": 648
},
{
"epoch": 1.31,
"learning_rate": 1.2556698075246776e-05,
"loss": 0.3552,
"step": 649
},
{
"epoch": 1.31,
"learning_rate": 1.253568805216296e-05,
"loss": 0.3906,
"step": 650
},
{
"epoch": 1.31,
"learning_rate": 1.2514666060053075e-05,
"loss": 0.3374,
"step": 651
},
{
"epoch": 1.31,
"learning_rate": 1.2493632198145717e-05,
"loss": 0.4318,
"step": 652
},
{
"epoch": 1.31,
"learning_rate": 1.2472586565725513e-05,
"loss": 0.4355,
"step": 653
},
{
"epoch": 1.32,
"learning_rate": 1.2451529262132652e-05,
"loss": 0.3301,
"step": 654
},
{
"epoch": 1.32,
"learning_rate": 1.2430460386762406e-05,
"loss": 0.3356,
"step": 655
},
{
"epoch": 1.32,
"learning_rate": 1.2409380039064675e-05,
"loss": 0.3583,
"step": 656
},
{
"epoch": 1.32,
"learning_rate": 1.2388288318543513e-05,
"loss": 0.4968,
"step": 657
},
{
"epoch": 1.32,
"learning_rate": 1.2367185324756648e-05,
"loss": 0.3252,
"step": 658
},
{
"epoch": 1.33,
"learning_rate": 1.2346071157315026e-05,
"loss": 0.3551,
"step": 659
},
{
"epoch": 1.33,
"learning_rate": 1.2324945915882334e-05,
"loss": 0.3265,
"step": 660
},
{
"epoch": 1.33,
"learning_rate": 1.230380970017453e-05,
"loss": 0.3776,
"step": 661
},
{
"epoch": 1.33,
"learning_rate": 1.2282662609959377e-05,
"loss": 0.3642,
"step": 662
},
{
"epoch": 1.33,
"learning_rate": 1.2261504745055963e-05,
"loss": 0.3476,
"step": 663
},
{
"epoch": 1.34,
"learning_rate": 1.2240336205334236e-05,
"loss": 0.3886,
"step": 664
},
{
"epoch": 1.34,
"learning_rate": 1.2219157090714536e-05,
"loss": 0.3225,
"step": 665
},
{
"epoch": 1.34,
"learning_rate": 1.2197967501167112e-05,
"loss": 0.356,
"step": 666
},
{
"epoch": 1.34,
"learning_rate": 1.2176767536711658e-05,
"loss": 0.3691,
"step": 667
},
{
"epoch": 1.34,
"learning_rate": 1.2155557297416851e-05,
"loss": 0.3303,
"step": 668
},
{
"epoch": 1.35,
"learning_rate": 1.2134336883399855e-05,
"loss": 0.36,
"step": 669
},
{
"epoch": 1.35,
"learning_rate": 1.2113106394825864e-05,
"loss": 0.3761,
"step": 670
},
{
"epoch": 1.35,
"learning_rate": 1.2091865931907627e-05,
"loss": 0.3766,
"step": 671
},
{
"epoch": 1.35,
"learning_rate": 1.2070615594904978e-05,
"loss": 0.3426,
"step": 672
},
{
"epoch": 1.35,
"learning_rate": 1.2049355484124351e-05,
"loss": 0.3513,
"step": 673
},
{
"epoch": 1.36,
"learning_rate": 1.2028085699918323e-05,
"loss": 0.3836,
"step": 674
},
{
"epoch": 1.36,
"learning_rate": 1.2006806342685127e-05,
"loss": 0.3804,
"step": 675
},
{
"epoch": 1.36,
"learning_rate": 1.1985517512868184e-05,
"loss": 0.3375,
"step": 676
},
{
"epoch": 1.36,
"learning_rate": 1.196421931095562e-05,
"loss": 0.3595,
"step": 677
},
{
"epoch": 1.36,
"learning_rate": 1.1942911837479819e-05,
"loss": 0.3315,
"step": 678
},
{
"epoch": 1.37,
"learning_rate": 1.1921595193016905e-05,
"loss": 0.3841,
"step": 679
},
{
"epoch": 1.37,
"learning_rate": 1.1900269478186313e-05,
"loss": 0.346,
"step": 680
},
{
"epoch": 1.37,
"learning_rate": 1.1878934793650273e-05,
"loss": 0.4103,
"step": 681
},
{
"epoch": 1.37,
"learning_rate": 1.1857591240113368e-05,
"loss": 0.3714,
"step": 682
},
{
"epoch": 1.37,
"learning_rate": 1.1836238918322041e-05,
"loss": 0.3888,
"step": 683
},
{
"epoch": 1.38,
"learning_rate": 1.1814877929064119e-05,
"loss": 0.3594,
"step": 684
},
{
"epoch": 1.38,
"learning_rate": 1.1793508373168346e-05,
"loss": 0.3669,
"step": 685
},
{
"epoch": 1.38,
"learning_rate": 1.1772130351503898e-05,
"loss": 0.3477,
"step": 686
},
{
"epoch": 1.38,
"learning_rate": 1.1750743964979919e-05,
"loss": 0.3454,
"step": 687
},
{
"epoch": 1.38,
"learning_rate": 1.1729349314545026e-05,
"loss": 0.3495,
"step": 688
},
{
"epoch": 1.39,
"learning_rate": 1.1707946501186853e-05,
"loss": 0.4163,
"step": 689
},
{
"epoch": 1.39,
"learning_rate": 1.1686535625931566e-05,
"loss": 0.367,
"step": 690
},
{
"epoch": 1.39,
"learning_rate": 1.1665116789843376e-05,
"loss": 0.3202,
"step": 691
},
{
"epoch": 1.39,
"learning_rate": 1.1643690094024073e-05,
"loss": 0.3336,
"step": 692
},
{
"epoch": 1.39,
"learning_rate": 1.1622255639612553e-05,
"loss": 0.4442,
"step": 693
},
{
"epoch": 1.4,
"learning_rate": 1.1600813527784333e-05,
"loss": 0.3645,
"step": 694
},
{
"epoch": 1.4,
"learning_rate": 1.1579363859751069e-05,
"loss": 0.3702,
"step": 695
},
{
"epoch": 1.4,
"learning_rate": 1.1557906736760089e-05,
"loss": 0.3439,
"step": 696
},
{
"epoch": 1.4,
"learning_rate": 1.1536442260093908e-05,
"loss": 0.357,
"step": 697
},
{
"epoch": 1.4,
"learning_rate": 1.151497053106975e-05,
"loss": 0.3627,
"step": 698
},
{
"epoch": 1.41,
"learning_rate": 1.1493491651039077e-05,
"loss": 0.3684,
"step": 699
},
{
"epoch": 1.41,
"learning_rate": 1.1472005721387102e-05,
"loss": 0.4559,
"step": 700
},
{
"epoch": 1.41,
"learning_rate": 1.1450512843532315e-05,
"loss": 0.3547,
"step": 701
},
{
"epoch": 1.41,
"learning_rate": 1.1429013118926002e-05,
"loss": 0.3942,
"step": 702
},
{
"epoch": 1.41,
"learning_rate": 1.140750664905177e-05,
"loss": 0.3682,
"step": 703
},
{
"epoch": 1.42,
"learning_rate": 1.1385993535425057e-05,
"loss": 0.3538,
"step": 704
},
{
"epoch": 1.42,
"learning_rate": 1.1364473879592674e-05,
"loss": 0.3452,
"step": 705
},
{
"epoch": 1.42,
"learning_rate": 1.1342947783132305e-05,
"loss": 0.3684,
"step": 706
},
{
"epoch": 1.42,
"learning_rate": 1.1321415347652031e-05,
"loss": 0.347,
"step": 707
},
{
"epoch": 1.42,
"learning_rate": 1.1299876674789864e-05,
"loss": 0.3424,
"step": 708
},
{
"epoch": 1.43,
"learning_rate": 1.1278331866213253e-05,
"loss": 0.3584,
"step": 709
},
{
"epoch": 1.43,
"learning_rate": 1.1256781023618607e-05,
"loss": 0.3485,
"step": 710
},
{
"epoch": 1.43,
"learning_rate": 1.1235224248730821e-05,
"loss": 0.3438,
"step": 711
},
{
"epoch": 1.43,
"learning_rate": 1.1213661643302791e-05,
"loss": 0.3539,
"step": 712
},
{
"epoch": 1.43,
"learning_rate": 1.1192093309114933e-05,
"loss": 0.3989,
"step": 713
},
{
"epoch": 1.44,
"learning_rate": 1.1170519347974704e-05,
"loss": 0.4651,
"step": 714
},
{
"epoch": 1.44,
"learning_rate": 1.1148939861716124e-05,
"loss": 0.3618,
"step": 715
},
{
"epoch": 1.44,
"learning_rate": 1.112735495219929e-05,
"loss": 0.3633,
"step": 716
},
{
"epoch": 1.44,
"learning_rate": 1.11057647213099e-05,
"loss": 0.3477,
"step": 717
},
{
"epoch": 1.44,
"learning_rate": 1.1084169270958767e-05,
"loss": 0.3549,
"step": 718
},
{
"epoch": 1.45,
"learning_rate": 1.1062568703081345e-05,
"loss": 0.323,
"step": 719
},
{
"epoch": 1.45,
"learning_rate": 1.104096311963724e-05,
"loss": 0.3466,
"step": 720
},
{
"epoch": 1.45,
"learning_rate": 1.1019352622609739e-05,
"loss": 0.3675,
"step": 721
},
{
"epoch": 1.45,
"learning_rate": 1.0997737314005315e-05,
"loss": 0.3468,
"step": 722
},
{
"epoch": 1.45,
"learning_rate": 1.0976117295853155e-05,
"loss": 0.3848,
"step": 723
},
{
"epoch": 1.46,
"learning_rate": 1.0954492670204677e-05,
"loss": 0.3318,
"step": 724
},
{
"epoch": 1.46,
"learning_rate": 1.093286353913305e-05,
"loss": 0.3456,
"step": 725
},
{
"epoch": 1.46,
"learning_rate": 1.0911230004732702e-05,
"loss": 0.3633,
"step": 726
},
{
"epoch": 1.46,
"learning_rate": 1.0889592169118857e-05,
"loss": 0.3522,
"step": 727
},
{
"epoch": 1.46,
"learning_rate": 1.086795013442703e-05,
"loss": 0.4363,
"step": 728
},
{
"epoch": 1.47,
"learning_rate": 1.0846304002812564e-05,
"loss": 0.349,
"step": 729
},
{
"epoch": 1.47,
"learning_rate": 1.0824653876450137e-05,
"loss": 0.3881,
"step": 730
},
{
"epoch": 1.47,
"learning_rate": 1.0802999857533288e-05,
"loss": 0.3727,
"step": 731
},
{
"epoch": 1.47,
"learning_rate": 1.0781342048273922e-05,
"loss": 0.3571,
"step": 732
},
{
"epoch": 1.47,
"learning_rate": 1.0759680550901843e-05,
"loss": 0.3915,
"step": 733
},
{
"epoch": 1.48,
"learning_rate": 1.0738015467664253e-05,
"loss": 0.3292,
"step": 734
},
{
"epoch": 1.48,
"learning_rate": 1.0716346900825298e-05,
"loss": 0.3662,
"step": 735
},
{
"epoch": 1.48,
"learning_rate": 1.0694674952665552e-05,
"loss": 0.4319,
"step": 736
},
{
"epoch": 1.48,
"learning_rate": 1.0672999725481549e-05,
"loss": 0.4273,
"step": 737
},
{
"epoch": 1.48,
"learning_rate": 1.0651321321585315e-05,
"loss": 0.3745,
"step": 738
},
{
"epoch": 1.49,
"learning_rate": 1.0629639843303857e-05,
"loss": 0.3287,
"step": 739
},
{
"epoch": 1.49,
"learning_rate": 1.0607955392978699e-05,
"loss": 0.4095,
"step": 740
},
{
"epoch": 1.49,
"learning_rate": 1.0586268072965395e-05,
"loss": 0.3614,
"step": 741
},
{
"epoch": 1.49,
"learning_rate": 1.056457798563304e-05,
"loss": 0.3802,
"step": 742
},
{
"epoch": 1.49,
"learning_rate": 1.0542885233363797e-05,
"loss": 0.3622,
"step": 743
},
{
"epoch": 1.5,
"learning_rate": 1.0521189918552406e-05,
"loss": 0.4072,
"step": 744
},
{
"epoch": 1.5,
"learning_rate": 1.0499492143605698e-05,
"loss": 0.4189,
"step": 745
},
{
"epoch": 1.5,
"learning_rate": 1.0477792010942127e-05,
"loss": 0.355,
"step": 746
},
{
"epoch": 1.5,
"learning_rate": 1.0456089622991264e-05,
"loss": 0.3722,
"step": 747
},
{
"epoch": 1.5,
"learning_rate": 1.0434385082193333e-05,
"loss": 0.3426,
"step": 748
},
{
"epoch": 1.51,
"learning_rate": 1.0412678490998717e-05,
"loss": 0.381,
"step": 749
},
{
"epoch": 1.51,
"learning_rate": 1.0390969951867482e-05,
"loss": 0.3509,
"step": 750
},
{
"epoch": 1.51,
"learning_rate": 1.0369259567268882e-05,
"loss": 0.4163,
"step": 751
},
{
"epoch": 1.51,
"learning_rate": 1.0347547439680885e-05,
"loss": 0.4055,
"step": 752
},
{
"epoch": 1.51,
"learning_rate": 1.0325833671589687e-05,
"loss": 0.3448,
"step": 753
},
{
"epoch": 1.52,
"learning_rate": 1.0304118365489226e-05,
"loss": 0.3476,
"step": 754
},
{
"epoch": 1.52,
"learning_rate": 1.0282401623880704e-05,
"loss": 0.3631,
"step": 755
},
{
"epoch": 1.52,
"learning_rate": 1.0260683549272091e-05,
"loss": 0.333,
"step": 756
},
{
"epoch": 1.52,
"learning_rate": 1.0238964244177657e-05,
"loss": 0.3288,
"step": 757
},
{
"epoch": 1.52,
"learning_rate": 1.0217243811117475e-05,
"loss": 0.34,
"step": 758
},
{
"epoch": 1.53,
"learning_rate": 1.0195522352616942e-05,
"loss": 0.3752,
"step": 759
},
{
"epoch": 1.53,
"learning_rate": 1.0173799971206303e-05,
"loss": 0.4154,
"step": 760
},
{
"epoch": 1.53,
"learning_rate": 1.0152076769420153e-05,
"loss": 0.3371,
"step": 761
},
{
"epoch": 1.53,
"learning_rate": 1.0130352849796959e-05,
"loss": 0.4101,
"step": 762
},
{
"epoch": 1.53,
"learning_rate": 1.0108628314878572e-05,
"loss": 0.4306,
"step": 763
},
{
"epoch": 1.54,
"learning_rate": 1.0086903267209762e-05,
"loss": 0.3443,
"step": 764
},
{
"epoch": 1.54,
"learning_rate": 1.0065177809337703e-05,
"loss": 0.3515,
"step": 765
},
{
"epoch": 1.54,
"learning_rate": 1.0043452043811517e-05,
"loss": 0.3827,
"step": 766
},
{
"epoch": 1.54,
"learning_rate": 1.002172607318177e-05,
"loss": 0.3276,
"step": 767
},
{
"epoch": 1.54,
"learning_rate": 1e-05,
"loss": 0.3492,
"step": 768
},
{
"epoch": 1.55,
"learning_rate": 9.978273926818233e-06,
"loss": 0.3499,
"step": 769
},
{
"epoch": 1.55,
"learning_rate": 9.956547956188486e-06,
"loss": 0.3489,
"step": 770
},
{
"epoch": 1.55,
"learning_rate": 9.934822190662299e-06,
"loss": 0.359,
"step": 771
},
{
"epoch": 1.55,
"learning_rate": 9.913096732790242e-06,
"loss": 0.3403,
"step": 772
},
{
"epoch": 1.55,
"learning_rate": 9.89137168512143e-06,
"loss": 0.3509,
"step": 773
},
{
"epoch": 1.56,
"learning_rate": 9.869647150203046e-06,
"loss": 0.3512,
"step": 774
},
{
"epoch": 1.56,
"learning_rate": 9.847923230579848e-06,
"loss": 0.3648,
"step": 775
},
{
"epoch": 1.56,
"learning_rate": 9.826200028793698e-06,
"loss": 0.3508,
"step": 776
},
{
"epoch": 1.56,
"learning_rate": 9.804477647383061e-06,
"loss": 0.3606,
"step": 777
},
{
"epoch": 1.56,
"learning_rate": 9.782756188882528e-06,
"loss": 0.4862,
"step": 778
},
{
"epoch": 1.57,
"learning_rate": 9.761035755822347e-06,
"loss": 0.355,
"step": 779
},
{
"epoch": 1.57,
"learning_rate": 9.739316450727914e-06,
"loss": 0.4182,
"step": 780
},
{
"epoch": 1.57,
"learning_rate": 9.717598376119301e-06,
"loss": 0.3632,
"step": 781
},
{
"epoch": 1.57,
"learning_rate": 9.695881634510778e-06,
"loss": 0.353,
"step": 782
},
{
"epoch": 1.57,
"learning_rate": 9.674166328410318e-06,
"loss": 0.3988,
"step": 783
},
{
"epoch": 1.58,
"learning_rate": 9.65245256031912e-06,
"loss": 0.444,
"step": 784
},
{
"epoch": 1.58,
"learning_rate": 9.630740432731123e-06,
"loss": 0.3233,
"step": 785
},
{
"epoch": 1.58,
"learning_rate": 9.609030048132523e-06,
"loss": 0.3927,
"step": 786
},
{
"epoch": 1.58,
"learning_rate": 9.587321509001288e-06,
"loss": 0.3381,
"step": 787
},
{
"epoch": 1.58,
"learning_rate": 9.565614917806672e-06,
"loss": 0.4146,
"step": 788
},
{
"epoch": 1.59,
"learning_rate": 9.543910377008741e-06,
"loss": 0.4197,
"step": 789
},
{
"epoch": 1.59,
"learning_rate": 9.52220798905788e-06,
"loss": 0.3677,
"step": 790
},
{
"epoch": 1.59,
"learning_rate": 9.5005078563943e-06,
"loss": 0.3865,
"step": 791
},
{
"epoch": 1.59,
"learning_rate": 9.478810081447595e-06,
"loss": 0.4354,
"step": 792
},
{
"epoch": 1.59,
"learning_rate": 9.457114766636203e-06,
"loss": 0.3918,
"step": 793
},
{
"epoch": 1.6,
"learning_rate": 9.43542201436696e-06,
"loss": 0.3872,
"step": 794
},
{
"epoch": 1.6,
"learning_rate": 9.413731927034607e-06,
"loss": 0.3406,
"step": 795
},
{
"epoch": 1.6,
"learning_rate": 9.392044607021301e-06,
"loss": 0.352,
"step": 796
},
{
"epoch": 1.6,
"learning_rate": 9.370360156696143e-06,
"loss": 0.3893,
"step": 797
},
{
"epoch": 1.6,
"learning_rate": 9.348678678414687e-06,
"loss": 0.3603,
"step": 798
},
{
"epoch": 1.61,
"learning_rate": 9.327000274518453e-06,
"loss": 0.4163,
"step": 799
},
{
"epoch": 1.61,
"learning_rate": 9.305325047334451e-06,
"loss": 0.3424,
"step": 800
},
{
"epoch": 1.61,
"learning_rate": 9.283653099174704e-06,
"loss": 0.415,
"step": 801
},
{
"epoch": 1.61,
"learning_rate": 9.261984532335748e-06,
"loss": 0.3304,
"step": 802
},
{
"epoch": 1.61,
"learning_rate": 9.24031944909816e-06,
"loss": 0.3741,
"step": 803
},
{
"epoch": 1.62,
"learning_rate": 9.21865795172608e-06,
"loss": 0.3802,
"step": 804
},
{
"epoch": 1.62,
"learning_rate": 9.197000142466715e-06,
"loss": 0.3274,
"step": 805
},
{
"epoch": 1.62,
"learning_rate": 9.175346123549865e-06,
"loss": 0.3578,
"step": 806
},
{
"epoch": 1.62,
"learning_rate": 9.15369599718744e-06,
"loss": 0.3546,
"step": 807
},
{
"epoch": 1.62,
"learning_rate": 9.132049865572973e-06,
"loss": 0.3347,
"step": 808
},
{
"epoch": 1.63,
"learning_rate": 9.110407830881146e-06,
"loss": 0.3437,
"step": 809
},
{
"epoch": 1.63,
"learning_rate": 9.0887699952673e-06,
"loss": 0.3449,
"step": 810
},
{
"epoch": 1.63,
"learning_rate": 9.067136460866954e-06,
"loss": 0.3376,
"step": 811
},
{
"epoch": 1.63,
"learning_rate": 9.045507329795325e-06,
"loss": 0.3277,
"step": 812
},
{
"epoch": 1.63,
"learning_rate": 9.023882704146848e-06,
"loss": 0.3407,
"step": 813
},
{
"epoch": 1.64,
"learning_rate": 9.002262685994689e-06,
"loss": 0.3463,
"step": 814
},
{
"epoch": 1.64,
"learning_rate": 8.980647377390263e-06,
"loss": 0.3586,
"step": 815
},
{
"epoch": 1.64,
"learning_rate": 8.959036880362762e-06,
"loss": 0.3366,
"step": 816
},
{
"epoch": 1.64,
"learning_rate": 8.937431296918658e-06,
"loss": 0.3437,
"step": 817
},
{
"epoch": 1.64,
"learning_rate": 8.915830729041236e-06,
"loss": 0.351,
"step": 818
},
{
"epoch": 1.65,
"learning_rate": 8.894235278690104e-06,
"loss": 0.367,
"step": 819
},
{
"epoch": 1.65,
"learning_rate": 8.872645047800714e-06,
"loss": 0.3596,
"step": 820
},
{
"epoch": 1.65,
"learning_rate": 8.85106013828388e-06,
"loss": 0.3559,
"step": 821
},
{
"epoch": 1.65,
"learning_rate": 8.829480652025298e-06,
"loss": 0.4019,
"step": 822
},
{
"epoch": 1.65,
"learning_rate": 8.80790669088507e-06,
"loss": 0.327,
"step": 823
},
{
"epoch": 1.66,
"learning_rate": 8.786338356697212e-06,
"loss": 0.3451,
"step": 824
},
{
"epoch": 1.66,
"learning_rate": 8.764775751269184e-06,
"loss": 0.4082,
"step": 825
},
{
"epoch": 1.66,
"learning_rate": 8.743218976381398e-06,
"loss": 0.4462,
"step": 826
},
{
"epoch": 1.66,
"learning_rate": 8.721668133786752e-06,
"loss": 0.333,
"step": 827
},
{
"epoch": 1.66,
"learning_rate": 8.700123325210141e-06,
"loss": 0.3595,
"step": 828
},
{
"epoch": 1.67,
"learning_rate": 8.678584652347974e-06,
"loss": 0.351,
"step": 829
},
{
"epoch": 1.67,
"learning_rate": 8.657052216867701e-06,
"loss": 0.4105,
"step": 830
},
{
"epoch": 1.67,
"learning_rate": 8.63552612040733e-06,
"loss": 0.3504,
"step": 831
},
{
"epoch": 1.67,
"learning_rate": 8.614006464574946e-06,
"loss": 0.3755,
"step": 832
},
{
"epoch": 1.68,
"learning_rate": 8.592493350948237e-06,
"loss": 0.336,
"step": 833
},
{
"epoch": 1.68,
"learning_rate": 8.570986881074003e-06,
"loss": 0.3404,
"step": 834
},
{
"epoch": 1.68,
"learning_rate": 8.549487156467691e-06,
"loss": 0.3612,
"step": 835
},
{
"epoch": 1.68,
"learning_rate": 8.5279942786129e-06,
"loss": 0.3343,
"step": 836
},
{
"epoch": 1.68,
"learning_rate": 8.506508348960924e-06,
"loss": 0.3285,
"step": 837
},
{
"epoch": 1.69,
"learning_rate": 8.485029468930252e-06,
"loss": 0.3476,
"step": 838
},
{
"epoch": 1.69,
"learning_rate": 8.463557739906094e-06,
"loss": 0.3474,
"step": 839
},
{
"epoch": 1.69,
"learning_rate": 8.442093263239913e-06,
"loss": 0.4277,
"step": 840
},
{
"epoch": 1.69,
"learning_rate": 8.42063614024893e-06,
"loss": 0.3896,
"step": 841
},
{
"epoch": 1.69,
"learning_rate": 8.399186472215666e-06,
"loss": 0.3536,
"step": 842
},
{
"epoch": 1.7,
"learning_rate": 8.377744360387447e-06,
"loss": 0.3573,
"step": 843
},
{
"epoch": 1.7,
"learning_rate": 8.356309905975928e-06,
"loss": 0.3417,
"step": 844
},
{
"epoch": 1.7,
"learning_rate": 8.334883210156629e-06,
"loss": 0.4022,
"step": 845
},
{
"epoch": 1.7,
"learning_rate": 8.313464374068438e-06,
"loss": 0.3377,
"step": 846
},
{
"epoch": 1.7,
"learning_rate": 8.292053498813149e-06,
"loss": 0.3686,
"step": 847
},
{
"epoch": 1.71,
"learning_rate": 8.270650685454977e-06,
"loss": 0.3361,
"step": 848
},
{
"epoch": 1.71,
"learning_rate": 8.249256035020086e-06,
"loss": 0.3758,
"step": 849
},
{
"epoch": 1.71,
"learning_rate": 8.227869648496105e-06,
"loss": 0.3182,
"step": 850
},
{
"epoch": 1.71,
"learning_rate": 8.20649162683166e-06,
"loss": 0.4016,
"step": 851
},
{
"epoch": 1.71,
"learning_rate": 8.185122070935885e-06,
"loss": 0.3488,
"step": 852
},
{
"epoch": 1.72,
"learning_rate": 8.163761081677962e-06,
"loss": 0.3346,
"step": 853
},
{
"epoch": 1.72,
"learning_rate": 8.142408759886634e-06,
"loss": 0.3115,
"step": 854
},
{
"epoch": 1.72,
"learning_rate": 8.12106520634973e-06,
"loss": 0.3421,
"step": 855
},
{
"epoch": 1.72,
"learning_rate": 8.099730521813692e-06,
"loss": 0.3081,
"step": 856
},
{
"epoch": 1.72,
"learning_rate": 8.078404806983096e-06,
"loss": 0.344,
"step": 857
},
{
"epoch": 1.73,
"learning_rate": 8.057088162520186e-06,
"loss": 0.3742,
"step": 858
},
{
"epoch": 1.73,
"learning_rate": 8.035780689044381e-06,
"loss": 0.3884,
"step": 859
},
{
"epoch": 1.73,
"learning_rate": 8.014482487131821e-06,
"loss": 0.3477,
"step": 860
},
{
"epoch": 1.73,
"learning_rate": 7.993193657314874e-06,
"loss": 0.3825,
"step": 861
},
{
"epoch": 1.73,
"learning_rate": 7.971914300081678e-06,
"loss": 0.3325,
"step": 862
},
{
"epoch": 1.74,
"learning_rate": 7.95064451587565e-06,
"loss": 0.3514,
"step": 863
},
{
"epoch": 1.74,
"learning_rate": 7.929384405095025e-06,
"loss": 0.366,
"step": 864
},
{
"epoch": 1.74,
"learning_rate": 7.908134068092375e-06,
"loss": 0.3524,
"step": 865
},
{
"epoch": 1.74,
"learning_rate": 7.88689360517414e-06,
"loss": 0.42,
"step": 866
},
{
"epoch": 1.74,
"learning_rate": 7.865663116600149e-06,
"loss": 0.3489,
"step": 867
},
{
"epoch": 1.75,
"learning_rate": 7.84444270258315e-06,
"loss": 0.3455,
"step": 868
},
{
"epoch": 1.75,
"learning_rate": 7.823232463288344e-06,
"loss": 0.342,
"step": 869
},
{
"epoch": 1.75,
"learning_rate": 7.802032498832895e-06,
"loss": 0.363,
"step": 870
},
{
"epoch": 1.75,
"learning_rate": 7.780842909285471e-06,
"loss": 0.3306,
"step": 871
},
{
"epoch": 1.75,
"learning_rate": 7.759663794665769e-06,
"loss": 0.3383,
"step": 872
},
{
"epoch": 1.76,
"learning_rate": 7.738495254944042e-06,
"loss": 0.3485,
"step": 873
},
{
"epoch": 1.76,
"learning_rate": 7.717337390040628e-06,
"loss": 0.3382,
"step": 874
},
{
"epoch": 1.76,
"learning_rate": 7.696190299825474e-06,
"loss": 0.3502,
"step": 875
},
{
"epoch": 1.76,
"learning_rate": 7.675054084117673e-06,
"loss": 0.3497,
"step": 876
},
{
"epoch": 1.76,
"learning_rate": 7.65392884268498e-06,
"loss": 0.3502,
"step": 877
},
{
"epoch": 1.77,
"learning_rate": 7.632814675243358e-06,
"loss": 0.3547,
"step": 878
},
{
"epoch": 1.77,
"learning_rate": 7.611711681456493e-06,
"loss": 0.3668,
"step": 879
},
{
"epoch": 1.77,
"learning_rate": 7.5906199609353296e-06,
"loss": 0.3454,
"step": 880
},
{
"epoch": 1.77,
"learning_rate": 7.569539613237595e-06,
"loss": 0.3401,
"step": 881
},
{
"epoch": 1.77,
"learning_rate": 7.548470737867351e-06,
"loss": 0.3453,
"step": 882
},
{
"epoch": 1.78,
"learning_rate": 7.527413434274487e-06,
"loss": 0.3736,
"step": 883
},
{
"epoch": 1.78,
"learning_rate": 7.506367801854284e-06,
"loss": 0.3682,
"step": 884
},
{
"epoch": 1.78,
"learning_rate": 7.485333939946926e-06,
"loss": 0.3294,
"step": 885
},
{
"epoch": 1.78,
"learning_rate": 7.46431194783704e-06,
"loss": 0.3332,
"step": 886
},
{
"epoch": 1.78,
"learning_rate": 7.443301924753224e-06,
"loss": 0.354,
"step": 887
},
{
"epoch": 1.79,
"learning_rate": 7.4223039698675815e-06,
"loss": 0.3458,
"step": 888
},
{
"epoch": 1.79,
"learning_rate": 7.4013181822952484e-06,
"loss": 0.3326,
"step": 889
},
{
"epoch": 1.79,
"learning_rate": 7.38034466109393e-06,
"loss": 0.3367,
"step": 890
},
{
"epoch": 1.79,
"learning_rate": 7.359383505263431e-06,
"loss": 0.461,
"step": 891
},
{
"epoch": 1.79,
"learning_rate": 7.338434813745186e-06,
"loss": 0.3893,
"step": 892
},
{
"epoch": 1.8,
"learning_rate": 7.317498685421803e-06,
"loss": 0.3694,
"step": 893
},
{
"epoch": 1.8,
"learning_rate": 7.296575219116582e-06,
"loss": 0.3703,
"step": 894
},
{
"epoch": 1.8,
"learning_rate": 7.275664513593057e-06,
"loss": 0.4062,
"step": 895
},
{
"epoch": 1.8,
"learning_rate": 7.254766667554527e-06,
"loss": 0.3299,
"step": 896
},
{
"epoch": 1.8,
"learning_rate": 7.233881779643595e-06,
"loss": 0.333,
"step": 897
},
{
"epoch": 1.81,
"learning_rate": 7.213009948441694e-06,
"loss": 0.3426,
"step": 898
},
{
"epoch": 1.81,
"learning_rate": 7.19215127246863e-06,
"loss": 0.3489,
"step": 899
},
{
"epoch": 1.81,
"learning_rate": 7.171305850182113e-06,
"loss": 0.4045,
"step": 900
},
{
"epoch": 1.81,
"learning_rate": 7.150473779977292e-06,
"loss": 0.3486,
"step": 901
},
{
"epoch": 1.81,
"learning_rate": 7.129655160186286e-06,
"loss": 0.3275,
"step": 902
},
{
"epoch": 1.82,
"learning_rate": 7.108850089077736e-06,
"loss": 0.3054,
"step": 903
},
{
"epoch": 1.82,
"learning_rate": 7.08805866485632e-06,
"loss": 0.3186,
"step": 904
},
{
"epoch": 1.82,
"learning_rate": 7.0672809856623036e-06,
"loss": 0.3573,
"step": 905
},
{
"epoch": 1.82,
"learning_rate": 7.046517149571075e-06,
"loss": 0.352,
"step": 906
},
{
"epoch": 1.82,
"learning_rate": 7.0257672545926755e-06,
"loss": 0.324,
"step": 907
},
{
"epoch": 1.83,
"learning_rate": 7.0050313986713435e-06,
"loss": 0.3073,
"step": 908
},
{
"epoch": 1.83,
"learning_rate": 6.984309679685049e-06,
"loss": 0.3478,
"step": 909
},
{
"epoch": 1.83,
"learning_rate": 6.963602195445032e-06,
"loss": 0.3591,
"step": 910
},
{
"epoch": 1.83,
"learning_rate": 6.942909043695345e-06,
"loss": 0.3769,
"step": 911
},
{
"epoch": 1.83,
"learning_rate": 6.922230322112382e-06,
"loss": 0.3729,
"step": 912
},
{
"epoch": 1.84,
"learning_rate": 6.901566128304429e-06,
"loss": 0.3338,
"step": 913
},
{
"epoch": 1.84,
"learning_rate": 6.880916559811193e-06,
"loss": 0.307,
"step": 914
},
{
"epoch": 1.84,
"learning_rate": 6.86028171410335e-06,
"loss": 0.342,
"step": 915
},
{
"epoch": 1.84,
"learning_rate": 6.839661688582076e-06,
"loss": 0.3636,
"step": 916
},
{
"epoch": 1.84,
"learning_rate": 6.8190565805785965e-06,
"loss": 0.3447,
"step": 917
},
{
"epoch": 1.85,
"learning_rate": 6.798466487353723e-06,
"loss": 0.3937,
"step": 918
},
{
"epoch": 1.85,
"learning_rate": 6.777891506097394e-06,
"loss": 0.371,
"step": 919
},
{
"epoch": 1.85,
"learning_rate": 6.75733173392821e-06,
"loss": 0.3612,
"step": 920
},
{
"epoch": 1.85,
"learning_rate": 6.736787267892991e-06,
"loss": 0.3263,
"step": 921
},
{
"epoch": 1.85,
"learning_rate": 6.716258204966302e-06,
"loss": 0.343,
"step": 922
},
{
"epoch": 1.86,
"learning_rate": 6.695744642050001e-06,
"loss": 0.3613,
"step": 923
},
{
"epoch": 1.86,
"learning_rate": 6.675246675972789e-06,
"loss": 0.4556,
"step": 924
},
{
"epoch": 1.86,
"learning_rate": 6.654764403489737e-06,
"loss": 0.3361,
"step": 925
},
{
"epoch": 1.86,
"learning_rate": 6.634297921281847e-06,
"loss": 0.3364,
"step": 926
},
{
"epoch": 1.86,
"learning_rate": 6.613847325955578e-06,
"loss": 0.4151,
"step": 927
},
{
"epoch": 1.87,
"learning_rate": 6.5934127140424165e-06,
"loss": 0.32,
"step": 928
},
{
"epoch": 1.87,
"learning_rate": 6.572994181998385e-06,
"loss": 0.3605,
"step": 929
},
{
"epoch": 1.87,
"learning_rate": 6.552591826203616e-06,
"loss": 0.3818,
"step": 930
},
{
"epoch": 1.87,
"learning_rate": 6.532205742961881e-06,
"loss": 0.3692,
"step": 931
},
{
"epoch": 1.87,
"learning_rate": 6.511836028500144e-06,
"loss": 0.3464,
"step": 932
},
{
"epoch": 1.88,
"learning_rate": 6.491482778968103e-06,
"loss": 0.3158,
"step": 933
},
{
"epoch": 1.88,
"learning_rate": 6.471146090437742e-06,
"loss": 0.3916,
"step": 934
},
{
"epoch": 1.88,
"learning_rate": 6.450826058902868e-06,
"loss": 0.3935,
"step": 935
},
{
"epoch": 1.88,
"learning_rate": 6.430522780278664e-06,
"loss": 0.3785,
"step": 936
},
{
"epoch": 1.88,
"learning_rate": 6.41023635040124e-06,
"loss": 0.3507,
"step": 937
},
{
"epoch": 1.89,
"learning_rate": 6.389966865027173e-06,
"loss": 0.4044,
"step": 938
},
{
"epoch": 1.89,
"learning_rate": 6.369714419833056e-06,
"loss": 0.3729,
"step": 939
},
{
"epoch": 1.89,
"learning_rate": 6.349479110415052e-06,
"loss": 0.3645,
"step": 940
},
{
"epoch": 1.89,
"learning_rate": 6.3292610322884365e-06,
"loss": 0.3489,
"step": 941
},
{
"epoch": 1.89,
"learning_rate": 6.309060280887151e-06,
"loss": 0.3555,
"step": 942
},
{
"epoch": 1.9,
"learning_rate": 6.288876951563352e-06,
"loss": 0.3366,
"step": 943
},
{
"epoch": 1.9,
"learning_rate": 6.2687111395869545e-06,
"loss": 0.3399,
"step": 944
},
{
"epoch": 1.9,
"learning_rate": 6.2485629401451954e-06,
"loss": 0.3565,
"step": 945
},
{
"epoch": 1.9,
"learning_rate": 6.2284324483421695e-06,
"loss": 0.3354,
"step": 946
},
{
"epoch": 1.9,
"learning_rate": 6.2083197591983935e-06,
"loss": 0.3217,
"step": 947
},
{
"epoch": 1.91,
"learning_rate": 6.188224967650347e-06,
"loss": 0.3757,
"step": 948
},
{
"epoch": 1.91,
"learning_rate": 6.168148168550029e-06,
"loss": 0.3395,
"step": 949
},
{
"epoch": 1.91,
"learning_rate": 6.148089456664512e-06,
"loss": 0.322,
"step": 950
},
{
"epoch": 1.91,
"learning_rate": 6.128048926675494e-06,
"loss": 0.3283,
"step": 951
},
{
"epoch": 1.91,
"learning_rate": 6.108026673178846e-06,
"loss": 0.3569,
"step": 952
},
{
"epoch": 1.92,
"learning_rate": 6.088022790684174e-06,
"loss": 0.299,
"step": 953
},
{
"epoch": 1.92,
"learning_rate": 6.068037373614364e-06,
"loss": 0.351,
"step": 954
},
{
"epoch": 1.92,
"learning_rate": 6.048070516305147e-06,
"loss": 0.3493,
"step": 955
},
{
"epoch": 1.92,
"learning_rate": 6.028122313004643e-06,
"loss": 0.3231,
"step": 956
},
{
"epoch": 1.92,
"learning_rate": 6.0081928578729235e-06,
"loss": 0.3264,
"step": 957
},
{
"epoch": 1.93,
"learning_rate": 5.988282244981562e-06,
"loss": 0.3291,
"step": 958
},
{
"epoch": 1.93,
"learning_rate": 5.968390568313194e-06,
"loss": 0.3173,
"step": 959
},
{
"epoch": 1.93,
"learning_rate": 5.94851792176107e-06,
"loss": 0.331,
"step": 960
},
{
"epoch": 1.93,
"learning_rate": 5.928664399128618e-06,
"loss": 0.3946,
"step": 961
},
{
"epoch": 1.93,
"learning_rate": 5.908830094128992e-06,
"loss": 0.3158,
"step": 962
},
{
"epoch": 1.94,
"learning_rate": 5.889015100384636e-06,
"loss": 0.34,
"step": 963
},
{
"epoch": 1.94,
"learning_rate": 5.8692195114268426e-06,
"loss": 0.356,
"step": 964
},
{
"epoch": 1.94,
"learning_rate": 5.8494434206953054e-06,
"loss": 0.3467,
"step": 965
},
{
"epoch": 1.94,
"learning_rate": 5.829686921537685e-06,
"loss": 0.3481,
"step": 966
},
{
"epoch": 1.94,
"learning_rate": 5.809950107209168e-06,
"loss": 0.3961,
"step": 967
},
{
"epoch": 1.95,
"learning_rate": 5.790233070872014e-06,
"loss": 0.3692,
"step": 968
},
{
"epoch": 1.95,
"learning_rate": 5.770535905595138e-06,
"loss": 0.3366,
"step": 969
},
{
"epoch": 1.95,
"learning_rate": 5.750858704353649e-06,
"loss": 0.3382,
"step": 970
},
{
"epoch": 1.95,
"learning_rate": 5.731201560028432e-06,
"loss": 0.3886,
"step": 971
},
{
"epoch": 1.95,
"learning_rate": 5.711564565405682e-06,
"loss": 0.331,
"step": 972
},
{
"epoch": 1.96,
"learning_rate": 5.6919478131765075e-06,
"loss": 0.3479,
"step": 973
},
{
"epoch": 1.96,
"learning_rate": 5.672351395936443e-06,
"loss": 0.4032,
"step": 974
},
{
"epoch": 1.96,
"learning_rate": 5.652775406185056e-06,
"loss": 0.303,
"step": 975
},
{
"epoch": 1.96,
"learning_rate": 5.633219936325478e-06,
"loss": 0.3561,
"step": 976
},
{
"epoch": 1.96,
"learning_rate": 5.613685078663993e-06,
"loss": 0.378,
"step": 977
},
{
"epoch": 1.97,
"learning_rate": 5.594170925409579e-06,
"loss": 0.3778,
"step": 978
},
{
"epoch": 1.97,
"learning_rate": 5.574677568673499e-06,
"loss": 0.3562,
"step": 979
},
{
"epoch": 1.97,
"learning_rate": 5.555205100468837e-06,
"loss": 0.3089,
"step": 980
},
{
"epoch": 1.97,
"learning_rate": 5.535753612710091e-06,
"loss": 0.3482,
"step": 981
},
{
"epoch": 1.97,
"learning_rate": 5.516323197212713e-06,
"loss": 0.3396,
"step": 982
},
{
"epoch": 1.98,
"learning_rate": 5.496913945692706e-06,
"loss": 0.3295,
"step": 983
},
{
"epoch": 1.98,
"learning_rate": 5.477525949766156e-06,
"loss": 0.3294,
"step": 984
},
{
"epoch": 1.98,
"learning_rate": 5.458159300948837e-06,
"loss": 0.316,
"step": 985
},
{
"epoch": 1.98,
"learning_rate": 5.438814090655738e-06,
"loss": 0.3931,
"step": 986
},
{
"epoch": 1.98,
"learning_rate": 5.419490410200675e-06,
"loss": 0.3425,
"step": 987
},
{
"epoch": 1.99,
"learning_rate": 5.4001883507958195e-06,
"loss": 0.3485,
"step": 988
},
{
"epoch": 1.99,
"learning_rate": 5.3809080035513e-06,
"loss": 0.336,
"step": 989
},
{
"epoch": 1.99,
"learning_rate": 5.361649459474756e-06,
"loss": 0.4025,
"step": 990
},
{
"epoch": 1.99,
"learning_rate": 5.342412809470903e-06,
"loss": 0.3522,
"step": 991
},
{
"epoch": 1.99,
"learning_rate": 5.323198144341124e-06,
"loss": 0.4235,
"step": 992
},
{
"epoch": 2.0,
"learning_rate": 5.304005554783015e-06,
"loss": 0.3752,
"step": 993
},
{
"epoch": 2.0,
"learning_rate": 5.284835131389985e-06,
"loss": 0.3593,
"step": 994
},
{
"epoch": 2.0,
"learning_rate": 5.265686964650796e-06,
"loss": 0.2897,
"step": 995
},
{
"epoch": 2.0,
"learning_rate": 5.246561144949174e-06,
"loss": 0.2675,
"step": 996
},
{
"epoch": 2.0,
"learning_rate": 5.227457762563339e-06,
"loss": 0.2198,
"step": 997
},
{
"epoch": 2.01,
"learning_rate": 5.2083769076656275e-06,
"loss": 0.2568,
"step": 998
},
{
"epoch": 2.01,
"learning_rate": 5.189318670322016e-06,
"loss": 0.2363,
"step": 999
},
{
"epoch": 2.01,
"learning_rate": 5.1702831404917404e-06,
"loss": 0.2152,
"step": 1000
},
{
"epoch": 2.01,
"learning_rate": 5.151270408026839e-06,
"loss": 0.2183,
"step": 1001
},
{
"epoch": 2.01,
"learning_rate": 5.13228056267175e-06,
"loss": 0.1923,
"step": 1002
},
{
"epoch": 2.02,
"learning_rate": 5.113313694062869e-06,
"loss": 0.2419,
"step": 1003
},
{
"epoch": 2.02,
"learning_rate": 5.094369891728154e-06,
"loss": 0.2437,
"step": 1004
},
{
"epoch": 2.02,
"learning_rate": 5.075449245086661e-06,
"loss": 0.202,
"step": 1005
},
{
"epoch": 2.02,
"learning_rate": 5.05655184344817e-06,
"loss": 0.1928,
"step": 1006
},
{
"epoch": 2.02,
"learning_rate": 5.037677776012719e-06,
"loss": 0.2192,
"step": 1007
},
{
"epoch": 2.03,
"learning_rate": 5.018827131870214e-06,
"loss": 0.2207,
"step": 1008
},
{
"epoch": 2.03,
"learning_rate": 5.000000000000003e-06,
"loss": 0.2204,
"step": 1009
},
{
"epoch": 2.03,
"learning_rate": 4.981196469270432e-06,
"loss": 0.2029,
"step": 1010
},
{
"epoch": 2.03,
"learning_rate": 4.962416628438466e-06,
"loss": 0.2206,
"step": 1011
},
{
"epoch": 2.03,
"learning_rate": 4.9436605661492295e-06,
"loss": 0.2023,
"step": 1012
},
{
"epoch": 2.04,
"learning_rate": 4.924928370935622e-06,
"loss": 0.2032,
"step": 1013
},
{
"epoch": 2.04,
"learning_rate": 4.906220131217873e-06,
"loss": 0.1982,
"step": 1014
},
{
"epoch": 2.04,
"learning_rate": 4.887535935303147e-06,
"loss": 0.214,
"step": 1015
},
{
"epoch": 2.04,
"learning_rate": 4.8688758713851056e-06,
"loss": 0.2064,
"step": 1016
},
{
"epoch": 2.04,
"learning_rate": 4.850240027543509e-06,
"loss": 0.2799,
"step": 1017
},
{
"epoch": 2.05,
"learning_rate": 4.831628491743794e-06,
"loss": 0.1882,
"step": 1018
},
{
"epoch": 2.05,
"learning_rate": 4.813041351836657e-06,
"loss": 0.2174,
"step": 1019
},
{
"epoch": 2.05,
"learning_rate": 4.794478695557631e-06,
"loss": 0.2039,
"step": 1020
},
{
"epoch": 2.05,
"learning_rate": 4.775940610526698e-06,
"loss": 0.2155,
"step": 1021
},
{
"epoch": 2.06,
"learning_rate": 4.75742718424784e-06,
"loss": 0.2461,
"step": 1022
},
{
"epoch": 2.06,
"learning_rate": 4.738938504108659e-06,
"loss": 0.1926,
"step": 1023
},
{
"epoch": 2.06,
"learning_rate": 4.7204746573799364e-06,
"loss": 0.2125,
"step": 1024
},
{
"epoch": 2.06,
"learning_rate": 4.702035731215249e-06,
"loss": 0.2122,
"step": 1025
},
{
"epoch": 2.06,
"learning_rate": 4.683621812650525e-06,
"loss": 0.2319,
"step": 1026
},
{
"epoch": 2.07,
"learning_rate": 4.665232988603671e-06,
"loss": 0.2126,
"step": 1027
},
{
"epoch": 2.07,
"learning_rate": 4.646869345874122e-06,
"loss": 0.2303,
"step": 1028
},
{
"epoch": 2.07,
"learning_rate": 4.6285309711424706e-06,
"loss": 0.1984,
"step": 1029
},
{
"epoch": 2.07,
"learning_rate": 4.610217950970019e-06,
"loss": 0.2138,
"step": 1030
},
{
"epoch": 2.07,
"learning_rate": 4.59193037179841e-06,
"loss": 0.2197,
"step": 1031
},
{
"epoch": 2.08,
"learning_rate": 4.573668319949179e-06,
"loss": 0.2317,
"step": 1032
},
{
"epoch": 2.08,
"learning_rate": 4.555431881623384e-06,
"loss": 0.2214,
"step": 1033
},
{
"epoch": 2.08,
"learning_rate": 4.537221142901175e-06,
"loss": 0.2327,
"step": 1034
},
{
"epoch": 2.08,
"learning_rate": 4.519036189741386e-06,
"loss": 0.1873,
"step": 1035
},
{
"epoch": 2.08,
"learning_rate": 4.500877107981154e-06,
"loss": 0.2015,
"step": 1036
},
{
"epoch": 2.09,
"learning_rate": 4.482743983335478e-06,
"loss": 0.2489,
"step": 1037
},
{
"epoch": 2.09,
"learning_rate": 4.464636901396851e-06,
"loss": 0.2175,
"step": 1038
},
{
"epoch": 2.09,
"learning_rate": 4.446555947634825e-06,
"loss": 0.2086,
"step": 1039
},
{
"epoch": 2.09,
"learning_rate": 4.428501207395631e-06,
"loss": 0.2403,
"step": 1040
},
{
"epoch": 2.09,
"learning_rate": 4.410472765901755e-06,
"loss": 0.2259,
"step": 1041
},
{
"epoch": 2.1,
"learning_rate": 4.392470708251563e-06,
"loss": 0.198,
"step": 1042
},
{
"epoch": 2.1,
"learning_rate": 4.3744951194188645e-06,
"loss": 0.2047,
"step": 1043
},
{
"epoch": 2.1,
"learning_rate": 4.3565460842525475e-06,
"loss": 0.211,
"step": 1044
},
{
"epoch": 2.1,
"learning_rate": 4.3386236874761455e-06,
"loss": 0.2261,
"step": 1045
},
{
"epoch": 2.1,
"learning_rate": 4.320728013687467e-06,
"loss": 0.1839,
"step": 1046
},
{
"epoch": 2.11,
"learning_rate": 4.302859147358168e-06,
"loss": 0.1969,
"step": 1047
},
{
"epoch": 2.11,
"learning_rate": 4.285017172833381e-06,
"loss": 0.2001,
"step": 1048
},
{
"epoch": 2.11,
"learning_rate": 4.267202174331288e-06,
"loss": 0.2176,
"step": 1049
},
{
"epoch": 2.11,
"learning_rate": 4.249414235942755e-06,
"loss": 0.1757,
"step": 1050
},
{
"epoch": 2.11,
"learning_rate": 4.231653441630899e-06,
"loss": 0.184,
"step": 1051
},
{
"epoch": 2.12,
"learning_rate": 4.213919875230729e-06,
"loss": 0.2403,
"step": 1052
},
{
"epoch": 2.12,
"learning_rate": 4.196213620448724e-06,
"loss": 0.1912,
"step": 1053
},
{
"epoch": 2.12,
"learning_rate": 4.1785347608624386e-06,
"loss": 0.2249,
"step": 1054
},
{
"epoch": 2.12,
"learning_rate": 4.160883379920132e-06,
"loss": 0.2011,
"step": 1055
},
{
"epoch": 2.12,
"learning_rate": 4.143259560940342e-06,
"loss": 0.2134,
"step": 1056
},
{
"epoch": 2.13,
"learning_rate": 4.125663387111519e-06,
"loss": 0.2347,
"step": 1057
},
{
"epoch": 2.13,
"learning_rate": 4.1080949414916135e-06,
"loss": 0.2229,
"step": 1058
},
{
"epoch": 2.13,
"learning_rate": 4.0905543070077036e-06,
"loss": 0.1773,
"step": 1059
},
{
"epoch": 2.13,
"learning_rate": 4.0730415664555775e-06,
"loss": 0.1975,
"step": 1060
},
{
"epoch": 2.13,
"learning_rate": 4.055556802499373e-06,
"loss": 0.2468,
"step": 1061
},
{
"epoch": 2.14,
"learning_rate": 4.038100097671155e-06,
"loss": 0.2097,
"step": 1062
},
{
"epoch": 2.14,
"learning_rate": 4.020671534370566e-06,
"loss": 0.2059,
"step": 1063
},
{
"epoch": 2.14,
"learning_rate": 4.00327119486439e-06,
"loss": 0.2169,
"step": 1064
},
{
"epoch": 2.14,
"learning_rate": 3.985899161286205e-06,
"loss": 0.2069,
"step": 1065
},
{
"epoch": 2.14,
"learning_rate": 3.968555515635969e-06,
"loss": 0.1984,
"step": 1066
},
{
"epoch": 2.15,
"learning_rate": 3.951240339779649e-06,
"loss": 0.2447,
"step": 1067
},
{
"epoch": 2.15,
"learning_rate": 3.9339537154488214e-06,
"loss": 0.233,
"step": 1068
},
{
"epoch": 2.15,
"learning_rate": 3.916695724240302e-06,
"loss": 0.2367,
"step": 1069
},
{
"epoch": 2.15,
"learning_rate": 3.899466447615739e-06,
"loss": 0.2076,
"step": 1070
},
{
"epoch": 2.15,
"learning_rate": 3.882265966901257e-06,
"loss": 0.1928,
"step": 1071
},
{
"epoch": 2.16,
"learning_rate": 3.8650943632870405e-06,
"loss": 0.2191,
"step": 1072
},
{
"epoch": 2.16,
"learning_rate": 3.847951717826984e-06,
"loss": 0.207,
"step": 1073
},
{
"epoch": 2.16,
"learning_rate": 3.830838111438277e-06,
"loss": 0.1956,
"step": 1074
},
{
"epoch": 2.16,
"learning_rate": 3.813753624901053e-06,
"loss": 0.2252,
"step": 1075
},
{
"epoch": 2.16,
"learning_rate": 3.7966983388579793e-06,
"loss": 0.2079,
"step": 1076
},
{
"epoch": 2.17,
"learning_rate": 3.7796723338138995e-06,
"loss": 0.212,
"step": 1077
},
{
"epoch": 2.17,
"learning_rate": 3.7626756901354466e-06,
"loss": 0.233,
"step": 1078
},
{
"epoch": 2.17,
"learning_rate": 3.7457084880506465e-06,
"loss": 0.22,
"step": 1079
},
{
"epoch": 2.17,
"learning_rate": 3.728770807648574e-06,
"loss": 0.2054,
"step": 1080
},
{
"epoch": 2.17,
"learning_rate": 3.7118627288789355e-06,
"loss": 0.2042,
"step": 1081
},
{
"epoch": 2.18,
"learning_rate": 3.6949843315517274e-06,
"loss": 0.2204,
"step": 1082
},
{
"epoch": 2.18,
"learning_rate": 3.6781356953368286e-06,
"loss": 0.1864,
"step": 1083
},
{
"epoch": 2.18,
"learning_rate": 3.6613168997636527e-06,
"loss": 0.2183,
"step": 1084
},
{
"epoch": 2.18,
"learning_rate": 3.644528024220745e-06,
"loss": 0.2055,
"step": 1085
},
{
"epoch": 2.18,
"learning_rate": 3.6277691479554335e-06,
"loss": 0.2593,
"step": 1086
},
{
"epoch": 2.19,
"learning_rate": 3.6110403500734325e-06,
"loss": 0.2062,
"step": 1087
},
{
"epoch": 2.19,
"learning_rate": 3.5943417095384915e-06,
"loss": 0.2051,
"step": 1088
},
{
"epoch": 2.19,
"learning_rate": 3.5776733051719935e-06,
"loss": 0.2174,
"step": 1089
},
{
"epoch": 2.19,
"learning_rate": 3.5610352156526196e-06,
"loss": 0.2004,
"step": 1090
},
{
"epoch": 2.19,
"learning_rate": 3.5444275195159395e-06,
"loss": 0.2333,
"step": 1091
},
{
"epoch": 2.2,
"learning_rate": 3.527850295154075e-06,
"loss": 0.2076,
"step": 1092
},
{
"epoch": 2.2,
"learning_rate": 3.5113036208152994e-06,
"loss": 0.2313,
"step": 1093
},
{
"epoch": 2.2,
"learning_rate": 3.4947875746036986e-06,
"loss": 0.2069,
"step": 1094
},
{
"epoch": 2.2,
"learning_rate": 3.4783022344787698e-06,
"loss": 0.1987,
"step": 1095
},
{
"epoch": 2.2,
"learning_rate": 3.461847678255085e-06,
"loss": 0.2017,
"step": 1096
},
{
"epoch": 2.21,
"learning_rate": 3.4454239836019032e-06,
"loss": 0.2217,
"step": 1097
},
{
"epoch": 2.21,
"learning_rate": 3.4290312280428064e-06,
"loss": 0.1966,
"step": 1098
},
{
"epoch": 2.21,
"learning_rate": 3.412669488955346e-06,
"loss": 0.2589,
"step": 1099
},
{
"epoch": 2.21,
"learning_rate": 3.396338843570656e-06,
"loss": 0.2417,
"step": 1100
},
{
"epoch": 2.21,
"learning_rate": 3.380039368973115e-06,
"loss": 0.1878,
"step": 1101
},
{
"epoch": 2.22,
"learning_rate": 3.3637711420999554e-06,
"loss": 0.2065,
"step": 1102
},
{
"epoch": 2.22,
"learning_rate": 3.347534239740925e-06,
"loss": 0.2348,
"step": 1103
},
{
"epoch": 2.22,
"learning_rate": 3.3313287385379024e-06,
"loss": 0.2124,
"step": 1104
},
{
"epoch": 2.22,
"learning_rate": 3.315154714984554e-06,
"loss": 0.2275,
"step": 1105
},
{
"epoch": 2.22,
"learning_rate": 3.2990122454259554e-06,
"loss": 0.2482,
"step": 1106
},
{
"epoch": 2.23,
"learning_rate": 3.2829014060582498e-06,
"loss": 0.2233,
"step": 1107
},
{
"epoch": 2.23,
"learning_rate": 3.266822272928273e-06,
"loss": 0.2168,
"step": 1108
},
{
"epoch": 2.23,
"learning_rate": 3.2507749219332065e-06,
"loss": 0.2108,
"step": 1109
},
{
"epoch": 2.23,
"learning_rate": 3.234759428820198e-06,
"loss": 0.2195,
"step": 1110
},
{
"epoch": 2.23,
"learning_rate": 3.218775869186038e-06,
"loss": 0.2048,
"step": 1111
},
{
"epoch": 2.24,
"learning_rate": 3.202824318476768e-06,
"loss": 0.2064,
"step": 1112
},
{
"epoch": 2.24,
"learning_rate": 3.1869048519873514e-06,
"loss": 0.2074,
"step": 1113
},
{
"epoch": 2.24,
"learning_rate": 3.1710175448612943e-06,
"loss": 0.2289,
"step": 1114
},
{
"epoch": 2.24,
"learning_rate": 3.1551624720903197e-06,
"loss": 0.2152,
"step": 1115
},
{
"epoch": 2.24,
"learning_rate": 3.139339708513981e-06,
"loss": 0.2072,
"step": 1116
},
{
"epoch": 2.25,
"learning_rate": 3.1235493288193363e-06,
"loss": 0.2036,
"step": 1117
},
{
"epoch": 2.25,
"learning_rate": 3.107791407540577e-06,
"loss": 0.2271,
"step": 1118
},
{
"epoch": 2.25,
"learning_rate": 3.0920660190586893e-06,
"loss": 0.2501,
"step": 1119
},
{
"epoch": 2.25,
"learning_rate": 3.0763732376010903e-06,
"loss": 0.2104,
"step": 1120
},
{
"epoch": 2.25,
"learning_rate": 3.0607131372412903e-06,
"loss": 0.247,
"step": 1121
},
{
"epoch": 2.26,
"learning_rate": 3.045085791898539e-06,
"loss": 0.2418,
"step": 1122
},
{
"epoch": 2.26,
"learning_rate": 3.029491275337466e-06,
"loss": 0.2046,
"step": 1123
},
{
"epoch": 2.26,
"learning_rate": 3.0139296611677527e-06,
"loss": 0.2269,
"step": 1124
},
{
"epoch": 2.26,
"learning_rate": 2.998401022843761e-06,
"loss": 0.2389,
"step": 1125
},
{
"epoch": 2.26,
"learning_rate": 2.982905433664214e-06,
"loss": 0.1957,
"step": 1126
},
{
"epoch": 2.27,
"learning_rate": 2.9674429667718198e-06,
"loss": 0.2282,
"step": 1127
},
{
"epoch": 2.27,
"learning_rate": 2.9520136951529577e-06,
"loss": 0.2127,
"step": 1128
},
{
"epoch": 2.27,
"learning_rate": 2.9366176916373024e-06,
"loss": 0.2342,
"step": 1129
},
{
"epoch": 2.27,
"learning_rate": 2.9212550288975083e-06,
"loss": 0.2449,
"step": 1130
},
{
"epoch": 2.27,
"learning_rate": 2.9059257794488428e-06,
"loss": 0.2179,
"step": 1131
},
{
"epoch": 2.28,
"learning_rate": 2.8906300156488667e-06,
"loss": 0.1803,
"step": 1132
},
{
"epoch": 2.28,
"learning_rate": 2.875367809697067e-06,
"loss": 0.1952,
"step": 1133
},
{
"epoch": 2.28,
"learning_rate": 2.860139233634547e-06,
"loss": 0.1837,
"step": 1134
},
{
"epoch": 2.28,
"learning_rate": 2.84494435934365e-06,
"loss": 0.2301,
"step": 1135
},
{
"epoch": 2.28,
"learning_rate": 2.829783258547656e-06,
"loss": 0.2151,
"step": 1136
},
{
"epoch": 2.29,
"learning_rate": 2.8146560028104155e-06,
"loss": 0.1925,
"step": 1137
},
{
"epoch": 2.29,
"learning_rate": 2.7995626635360296e-06,
"loss": 0.2051,
"step": 1138
},
{
"epoch": 2.29,
"learning_rate": 2.7845033119684996e-06,
"loss": 0.2232,
"step": 1139
},
{
"epoch": 2.29,
"learning_rate": 2.7694780191914005e-06,
"loss": 0.2135,
"step": 1140
},
{
"epoch": 2.29,
"learning_rate": 2.7544868561275473e-06,
"loss": 0.2194,
"step": 1141
},
{
"epoch": 2.3,
"learning_rate": 2.739529893538644e-06,
"loss": 0.2046,
"step": 1142
},
{
"epoch": 2.3,
"learning_rate": 2.724607202024969e-06,
"loss": 0.197,
"step": 1143
},
{
"epoch": 2.3,
"learning_rate": 2.7097188520250284e-06,
"loss": 0.2094,
"step": 1144
},
{
"epoch": 2.3,
"learning_rate": 2.694864913815234e-06,
"loss": 0.2822,
"step": 1145
},
{
"epoch": 2.3,
"learning_rate": 2.680045457509557e-06,
"loss": 0.224,
"step": 1146
},
{
"epoch": 2.31,
"learning_rate": 2.665260553059219e-06,
"loss": 0.1989,
"step": 1147
},
{
"epoch": 2.31,
"learning_rate": 2.6505102702523346e-06,
"loss": 0.2363,
"step": 1148
},
{
"epoch": 2.31,
"learning_rate": 2.635794678713611e-06,
"loss": 0.2287,
"step": 1149
},
{
"epoch": 2.31,
"learning_rate": 2.621113847903991e-06,
"loss": 0.2131,
"step": 1150
},
{
"epoch": 2.31,
"learning_rate": 2.6064678471203497e-06,
"loss": 0.2035,
"step": 1151
},
{
"epoch": 2.32,
"learning_rate": 2.591856745495148e-06,
"loss": 0.2321,
"step": 1152
},
{
"epoch": 2.32,
"learning_rate": 2.5772806119961204e-06,
"loss": 0.2431,
"step": 1153
},
{
"epoch": 2.32,
"learning_rate": 2.5627395154259427e-06,
"loss": 0.2336,
"step": 1154
},
{
"epoch": 2.32,
"learning_rate": 2.5482335244219114e-06,
"loss": 0.206,
"step": 1155
},
{
"epoch": 2.32,
"learning_rate": 2.533762707455607e-06,
"loss": 0.2009,
"step": 1156
},
{
"epoch": 2.33,
"learning_rate": 2.519327132832592e-06,
"loss": 0.2296,
"step": 1157
},
{
"epoch": 2.33,
"learning_rate": 2.504926868692067e-06,
"loss": 0.2587,
"step": 1158
},
{
"epoch": 2.33,
"learning_rate": 2.4905619830065685e-06,
"loss": 0.2021,
"step": 1159
},
{
"epoch": 2.33,
"learning_rate": 2.4762325435816305e-06,
"loss": 0.198,
"step": 1160
},
{
"epoch": 2.33,
"learning_rate": 2.4619386180554783e-06,
"loss": 0.2204,
"step": 1161
},
{
"epoch": 2.34,
"learning_rate": 2.4476802738986984e-06,
"loss": 0.2067,
"step": 1162
},
{
"epoch": 2.34,
"learning_rate": 2.4334575784139324e-06,
"loss": 0.2039,
"step": 1163
},
{
"epoch": 2.34,
"learning_rate": 2.4192705987355424e-06,
"loss": 0.216,
"step": 1164
},
{
"epoch": 2.34,
"learning_rate": 2.405119401829312e-06,
"loss": 0.203,
"step": 1165
},
{
"epoch": 2.34,
"learning_rate": 2.391004054492121e-06,
"loss": 0.2215,
"step": 1166
},
{
"epoch": 2.35,
"learning_rate": 2.3769246233516243e-06,
"loss": 0.2091,
"step": 1167
},
{
"epoch": 2.35,
"learning_rate": 2.362881174865953e-06,
"loss": 0.2024,
"step": 1168
},
{
"epoch": 2.35,
"learning_rate": 2.3488737753233827e-06,
"loss": 0.2448,
"step": 1169
},
{
"epoch": 2.35,
"learning_rate": 2.3349024908420403e-06,
"loss": 0.2037,
"step": 1170
},
{
"epoch": 2.35,
"learning_rate": 2.3209673873695705e-06,
"loss": 0.2183,
"step": 1171
},
{
"epoch": 2.36,
"learning_rate": 2.3070685306828465e-06,
"loss": 0.2115,
"step": 1172
},
{
"epoch": 2.36,
"learning_rate": 2.2932059863876364e-06,
"loss": 0.2801,
"step": 1173
},
{
"epoch": 2.36,
"learning_rate": 2.2793798199183183e-06,
"loss": 0.2253,
"step": 1174
},
{
"epoch": 2.36,
"learning_rate": 2.2655900965375454e-06,
"loss": 0.2902,
"step": 1175
},
{
"epoch": 2.36,
"learning_rate": 2.251836881335964e-06,
"loss": 0.2531,
"step": 1176
},
{
"epoch": 2.37,
"learning_rate": 2.2381202392318813e-06,
"loss": 0.1829,
"step": 1177
},
{
"epoch": 2.37,
"learning_rate": 2.2244402349709825e-06,
"loss": 0.1943,
"step": 1178
},
{
"epoch": 2.37,
"learning_rate": 2.210796933126005e-06,
"loss": 0.1834,
"step": 1179
},
{
"epoch": 2.37,
"learning_rate": 2.197190398096449e-06,
"loss": 0.216,
"step": 1180
},
{
"epoch": 2.37,
"learning_rate": 2.1836206941082593e-06,
"loss": 0.1947,
"step": 1181
},
{
"epoch": 2.38,
"learning_rate": 2.170087885213541e-06,
"loss": 0.1886,
"step": 1182
},
{
"epoch": 2.38,
"learning_rate": 2.1565920352902327e-06,
"loss": 0.2244,
"step": 1183
},
{
"epoch": 2.38,
"learning_rate": 2.1431332080418265e-06,
"loss": 0.1882,
"step": 1184
},
{
"epoch": 2.38,
"learning_rate": 2.129711466997062e-06,
"loss": 0.2231,
"step": 1185
},
{
"epoch": 2.38,
"learning_rate": 2.1163268755096133e-06,
"loss": 0.2007,
"step": 1186
},
{
"epoch": 2.39,
"learning_rate": 2.10297949675781e-06,
"loss": 0.1993,
"step": 1187
},
{
"epoch": 2.39,
"learning_rate": 2.089669393744319e-06,
"loss": 0.2631,
"step": 1188
},
{
"epoch": 2.39,
"learning_rate": 2.0763966292958704e-06,
"loss": 0.1955,
"step": 1189
},
{
"epoch": 2.39,
"learning_rate": 2.063161266062933e-06,
"loss": 0.2062,
"step": 1190
},
{
"epoch": 2.39,
"learning_rate": 2.049963366519446e-06,
"loss": 0.2173,
"step": 1191
},
{
"epoch": 2.4,
"learning_rate": 2.036802992962502e-06,
"loss": 0.2019,
"step": 1192
},
{
"epoch": 2.4,
"learning_rate": 2.023680207512071e-06,
"loss": 0.1917,
"step": 1193
},
{
"epoch": 2.4,
"learning_rate": 2.010595072110689e-06,
"loss": 0.2112,
"step": 1194
},
{
"epoch": 2.4,
"learning_rate": 1.9975476485231847e-06,
"loss": 0.2131,
"step": 1195
},
{
"epoch": 2.4,
"learning_rate": 1.98453799833637e-06,
"loss": 0.2216,
"step": 1196
},
{
"epoch": 2.41,
"learning_rate": 1.9715661829587653e-06,
"loss": 0.2084,
"step": 1197
},
{
"epoch": 2.41,
"learning_rate": 1.9586322636202924e-06,
"loss": 0.2269,
"step": 1198
},
{
"epoch": 2.41,
"learning_rate": 1.94573630137201e-06,
"loss": 0.2102,
"step": 1199
},
{
"epoch": 2.41,
"learning_rate": 1.9328783570857954e-06,
"loss": 0.2004,
"step": 1200
},
{
"epoch": 2.41,
"learning_rate": 1.9200584914540833e-06,
"loss": 0.197,
"step": 1201
},
{
"epoch": 2.42,
"learning_rate": 1.9072767649895584e-06,
"loss": 0.2626,
"step": 1202
},
{
"epoch": 2.42,
"learning_rate": 1.8945332380248914e-06,
"loss": 0.2126,
"step": 1203
},
{
"epoch": 2.42,
"learning_rate": 1.8818279707124322e-06,
"loss": 0.2353,
"step": 1204
},
{
"epoch": 2.42,
"learning_rate": 1.8691610230239443e-06,
"loss": 0.2083,
"step": 1205
},
{
"epoch": 2.43,
"learning_rate": 1.8565324547503072e-06,
"loss": 0.2187,
"step": 1206
},
{
"epoch": 2.43,
"learning_rate": 1.8439423255012478e-06,
"loss": 0.25,
"step": 1207
},
{
"epoch": 2.43,
"learning_rate": 1.8313906947050443e-06,
"loss": 0.2307,
"step": 1208
},
{
"epoch": 2.43,
"learning_rate": 1.8188776216082604e-06,
"loss": 0.2244,
"step": 1209
},
{
"epoch": 2.43,
"learning_rate": 1.8064031652754565e-06,
"loss": 0.2288,
"step": 1210
},
{
"epoch": 2.44,
"learning_rate": 1.7939673845889072e-06,
"loss": 0.2084,
"step": 1211
},
{
"epoch": 2.44,
"learning_rate": 1.7815703382483418e-06,
"loss": 0.2189,
"step": 1212
},
{
"epoch": 2.44,
"learning_rate": 1.7692120847706396e-06,
"loss": 0.2711,
"step": 1213
},
{
"epoch": 2.44,
"learning_rate": 1.7568926824895827e-06,
"loss": 0.2122,
"step": 1214
},
{
"epoch": 2.44,
"learning_rate": 1.7446121895555556e-06,
"loss": 0.2071,
"step": 1215
},
{
"epoch": 2.45,
"learning_rate": 1.7323706639352899e-06,
"loss": 0.1907,
"step": 1216
},
{
"epoch": 2.45,
"learning_rate": 1.7201681634115753e-06,
"loss": 0.2195,
"step": 1217
},
{
"epoch": 2.45,
"learning_rate": 1.708004745583003e-06,
"loss": 0.2053,
"step": 1218
},
{
"epoch": 2.45,
"learning_rate": 1.6958804678636743e-06,
"loss": 0.2105,
"step": 1219
},
{
"epoch": 2.45,
"learning_rate": 1.6837953874829515e-06,
"loss": 0.1916,
"step": 1220
},
{
"epoch": 2.46,
"learning_rate": 1.6717495614851654e-06,
"loss": 0.2572,
"step": 1221
},
{
"epoch": 2.46,
"learning_rate": 1.6597430467293685e-06,
"loss": 0.2134,
"step": 1222
},
{
"epoch": 2.46,
"learning_rate": 1.6477758998890448e-06,
"loss": 0.2027,
"step": 1223
},
{
"epoch": 2.46,
"learning_rate": 1.6358481774518608e-06,
"loss": 0.1945,
"step": 1224
},
{
"epoch": 2.46,
"learning_rate": 1.6239599357193837e-06,
"loss": 0.2266,
"step": 1225
},
{
"epoch": 2.47,
"learning_rate": 1.612111230806832e-06,
"loss": 0.2021,
"step": 1226
},
{
"epoch": 2.47,
"learning_rate": 1.6003021186427892e-06,
"loss": 0.2166,
"step": 1227
},
{
"epoch": 2.47,
"learning_rate": 1.588532654968963e-06,
"loss": 0.2287,
"step": 1228
},
{
"epoch": 2.47,
"learning_rate": 1.5768028953399083e-06,
"loss": 0.2068,
"step": 1229
},
{
"epoch": 2.47,
"learning_rate": 1.5651128951227613e-06,
"loss": 0.2084,
"step": 1230
},
{
"epoch": 2.48,
"learning_rate": 1.5534627094969957e-06,
"loss": 0.2387,
"step": 1231
},
{
"epoch": 2.48,
"learning_rate": 1.5418523934541397e-06,
"loss": 0.1977,
"step": 1232
},
{
"epoch": 2.48,
"learning_rate": 1.5302820017975396e-06,
"loss": 0.1947,
"step": 1233
},
{
"epoch": 2.48,
"learning_rate": 1.518751589142078e-06,
"loss": 0.2294,
"step": 1234
},
{
"epoch": 2.48,
"learning_rate": 1.5072612099139373e-06,
"loss": 0.1844,
"step": 1235
},
{
"epoch": 2.49,
"learning_rate": 1.4958109183503245e-06,
"loss": 0.1942,
"step": 1236
},
{
"epoch": 2.49,
"learning_rate": 1.4844007684992333e-06,
"loss": 0.2565,
"step": 1237
},
{
"epoch": 2.49,
"learning_rate": 1.4730308142191684e-06,
"loss": 0.2068,
"step": 1238
},
{
"epoch": 2.49,
"learning_rate": 1.4617011091789135e-06,
"loss": 0.2159,
"step": 1239
},
{
"epoch": 2.49,
"learning_rate": 1.4504117068572554e-06,
"loss": 0.2045,
"step": 1240
},
{
"epoch": 2.5,
"learning_rate": 1.4391626605427522e-06,
"loss": 0.1882,
"step": 1241
},
{
"epoch": 2.5,
"learning_rate": 1.4279540233334666e-06,
"loss": 0.212,
"step": 1242
},
{
"epoch": 2.5,
"learning_rate": 1.4167858481367237e-06,
"loss": 0.213,
"step": 1243
},
{
"epoch": 2.5,
"learning_rate": 1.4056581876688591e-06,
"loss": 0.2219,
"step": 1244
},
{
"epoch": 2.5,
"learning_rate": 1.3945710944549705e-06,
"loss": 0.2662,
"step": 1245
},
{
"epoch": 2.51,
"learning_rate": 1.3835246208286635e-06,
"loss": 0.2022,
"step": 1246
},
{
"epoch": 2.51,
"learning_rate": 1.3725188189318172e-06,
"loss": 0.2096,
"step": 1247
},
{
"epoch": 2.51,
"learning_rate": 1.3615537407143231e-06,
"loss": 0.1986,
"step": 1248
},
{
"epoch": 2.51,
"learning_rate": 1.3506294379338557e-06,
"loss": 0.2274,
"step": 1249
},
{
"epoch": 2.51,
"learning_rate": 1.339745962155613e-06,
"loss": 0.2162,
"step": 1250
},
{
"epoch": 2.52,
"learning_rate": 1.3289033647520878e-06,
"loss": 0.1903,
"step": 1251
},
{
"epoch": 2.52,
"learning_rate": 1.3181016969028083e-06,
"loss": 0.2085,
"step": 1252
},
{
"epoch": 2.52,
"learning_rate": 1.307341009594113e-06,
"loss": 0.204,
"step": 1253
},
{
"epoch": 2.52,
"learning_rate": 1.2966213536189031e-06,
"loss": 0.2035,
"step": 1254
},
{
"epoch": 2.52,
"learning_rate": 1.2859427795763967e-06,
"loss": 0.2282,
"step": 1255
},
{
"epoch": 2.53,
"learning_rate": 1.2753053378719038e-06,
"loss": 0.1937,
"step": 1256
},
{
"epoch": 2.53,
"learning_rate": 1.2647090787165694e-06,
"loss": 0.2096,
"step": 1257
},
{
"epoch": 2.53,
"learning_rate": 1.2541540521271612e-06,
"loss": 0.1957,
"step": 1258
},
{
"epoch": 2.53,
"learning_rate": 1.2436403079258064e-06,
"loss": 0.2018,
"step": 1259
},
{
"epoch": 2.53,
"learning_rate": 1.2331678957397819e-06,
"loss": 0.2063,
"step": 1260
},
{
"epoch": 2.54,
"learning_rate": 1.2227368650012572e-06,
"loss": 0.3506,
"step": 1261
},
{
"epoch": 2.54,
"learning_rate": 1.2123472649470802e-06,
"loss": 0.2503,
"step": 1262
},
{
"epoch": 2.54,
"learning_rate": 1.201999144618531e-06,
"loss": 0.2,
"step": 1263
},
{
"epoch": 2.54,
"learning_rate": 1.1916925528611012e-06,
"loss": 0.1921,
"step": 1264
},
{
"epoch": 2.54,
"learning_rate": 1.1814275383242512e-06,
"loss": 0.1902,
"step": 1265
},
{
"epoch": 2.55,
"learning_rate": 1.171204149461196e-06,
"loss": 0.1899,
"step": 1266
},
{
"epoch": 2.55,
"learning_rate": 1.1610224345286591e-06,
"loss": 0.2291,
"step": 1267
},
{
"epoch": 2.55,
"learning_rate": 1.1508824415866616e-06,
"loss": 0.2216,
"step": 1268
},
{
"epoch": 2.55,
"learning_rate": 1.1407842184982786e-06,
"loss": 0.2036,
"step": 1269
},
{
"epoch": 2.55,
"learning_rate": 1.1307278129294318e-06,
"loss": 0.2053,
"step": 1270
},
{
"epoch": 2.56,
"learning_rate": 1.1207132723486457e-06,
"loss": 0.2195,
"step": 1271
},
{
"epoch": 2.56,
"learning_rate": 1.1107406440268377e-06,
"loss": 0.1806,
"step": 1272
},
{
"epoch": 2.56,
"learning_rate": 1.1008099750370916e-06,
"loss": 0.2154,
"step": 1273
},
{
"epoch": 2.56,
"learning_rate": 1.0909213122544248e-06,
"loss": 0.1986,
"step": 1274
},
{
"epoch": 2.56,
"learning_rate": 1.0810747023555879e-06,
"loss": 0.2112,
"step": 1275
},
{
"epoch": 2.57,
"learning_rate": 1.0712701918188195e-06,
"loss": 0.2621,
"step": 1276
},
{
"epoch": 2.57,
"learning_rate": 1.0615078269236512e-06,
"loss": 0.2035,
"step": 1277
},
{
"epoch": 2.57,
"learning_rate": 1.0517876537506688e-06,
"loss": 0.2166,
"step": 1278
},
{
"epoch": 2.57,
"learning_rate": 1.04210971818131e-06,
"loss": 0.265,
"step": 1279
},
{
"epoch": 2.57,
"learning_rate": 1.032474065897635e-06,
"loss": 0.2402,
"step": 1280
},
{
"epoch": 2.58,
"learning_rate": 1.0228807423821262e-06,
"loss": 0.2007,
"step": 1281
},
{
"epoch": 2.58,
"learning_rate": 1.0133297929174523e-06,
"loss": 0.2817,
"step": 1282
},
{
"epoch": 2.58,
"learning_rate": 1.0038212625862799e-06,
"loss": 0.2005,
"step": 1283
},
{
"epoch": 2.58,
"learning_rate": 9.943551962710362e-07,
"loss": 0.2059,
"step": 1284
},
{
"epoch": 2.58,
"learning_rate": 9.84931638653719e-07,
"loss": 0.2112,
"step": 1285
},
{
"epoch": 2.59,
"learning_rate": 9.75550634215664e-07,
"loss": 0.2202,
"step": 1286
},
{
"epoch": 2.59,
"learning_rate": 9.662122272373574e-07,
"loss": 0.2115,
"step": 1287
},
{
"epoch": 2.59,
"learning_rate": 9.56916461798205e-07,
"loss": 0.1901,
"step": 1288
},
{
"epoch": 2.59,
"learning_rate": 9.476633817763481e-07,
"loss": 0.2409,
"step": 1289
},
{
"epoch": 2.59,
"learning_rate": 9.384530308484275e-07,
"loss": 0.2045,
"step": 1290
},
{
"epoch": 2.6,
"learning_rate": 9.292854524894068e-07,
"loss": 0.1978,
"step": 1291
},
{
"epoch": 2.6,
"learning_rate": 9.201606899723437e-07,
"loss": 0.2237,
"step": 1292
},
{
"epoch": 2.6,
"learning_rate": 9.110787863682002e-07,
"loss": 0.2524,
"step": 1293
},
{
"epoch": 2.6,
"learning_rate": 9.02039784545632e-07,
"loss": 0.2248,
"step": 1294
},
{
"epoch": 2.6,
"learning_rate": 8.930437271707915e-07,
"loss": 0.1883,
"step": 1295
},
{
"epoch": 2.61,
"learning_rate": 8.840906567071194e-07,
"loss": 0.2161,
"step": 1296
},
{
"epoch": 2.61,
"learning_rate": 8.751806154151521e-07,
"loss": 0.1997,
"step": 1297
},
{
"epoch": 2.61,
"learning_rate": 8.663136453523191e-07,
"loss": 0.2096,
"step": 1298
},
{
"epoch": 2.61,
"learning_rate": 8.574897883727384e-07,
"loss": 0.1791,
"step": 1299
},
{
"epoch": 2.61,
"learning_rate": 8.487090861270309e-07,
"loss": 0.19,
"step": 1300
},
{
"epoch": 2.62,
"learning_rate": 8.399715800621111e-07,
"loss": 0.26,
"step": 1301
},
{
"epoch": 2.62,
"learning_rate": 8.312773114210049e-07,
"loss": 0.2212,
"step": 1302
},
{
"epoch": 2.62,
"learning_rate": 8.226263212426389e-07,
"loss": 0.2043,
"step": 1303
},
{
"epoch": 2.62,
"learning_rate": 8.140186503616653e-07,
"loss": 0.2072,
"step": 1304
},
{
"epoch": 2.62,
"learning_rate": 8.054543394082503e-07,
"loss": 0.1992,
"step": 1305
},
{
"epoch": 2.63,
"learning_rate": 7.969334288078989e-07,
"loss": 0.2215,
"step": 1306
},
{
"epoch": 2.63,
"learning_rate": 7.884559587812501e-07,
"loss": 0.2136,
"step": 1307
},
{
"epoch": 2.63,
"learning_rate": 7.800219693438981e-07,
"loss": 0.2098,
"step": 1308
},
{
"epoch": 2.63,
"learning_rate": 7.716315003061948e-07,
"loss": 0.2012,
"step": 1309
},
{
"epoch": 2.63,
"learning_rate": 7.632845912730713e-07,
"loss": 0.1994,
"step": 1310
},
{
"epoch": 2.64,
"learning_rate": 7.549812816438395e-07,
"loss": 0.2903,
"step": 1311
},
{
"epoch": 2.64,
"learning_rate": 7.467216106120179e-07,
"loss": 0.2031,
"step": 1312
},
{
"epoch": 2.64,
"learning_rate": 7.38505617165135e-07,
"loss": 0.2073,
"step": 1313
},
{
"epoch": 2.64,
"learning_rate": 7.303333400845581e-07,
"loss": 0.2109,
"step": 1314
},
{
"epoch": 2.64,
"learning_rate": 7.222048179452945e-07,
"loss": 0.2052,
"step": 1315
},
{
"epoch": 2.65,
"learning_rate": 7.141200891158262e-07,
"loss": 0.1938,
"step": 1316
},
{
"epoch": 2.65,
"learning_rate": 7.06079191757918e-07,
"loss": 0.2286,
"step": 1317
},
{
"epoch": 2.65,
"learning_rate": 6.980821638264379e-07,
"loss": 0.2053,
"step": 1318
},
{
"epoch": 2.65,
"learning_rate": 6.901290430691842e-07,
"loss": 0.1955,
"step": 1319
},
{
"epoch": 2.65,
"learning_rate": 6.822198670266989e-07,
"loss": 0.2187,
"step": 1320
},
{
"epoch": 2.66,
"learning_rate": 6.743546730320993e-07,
"loss": 0.19,
"step": 1321
},
{
"epoch": 2.66,
"learning_rate": 6.665334982108928e-07,
"loss": 0.2151,
"step": 1322
},
{
"epoch": 2.66,
"learning_rate": 6.587563794808127e-07,
"loss": 0.2478,
"step": 1323
},
{
"epoch": 2.66,
"learning_rate": 6.510233535516286e-07,
"loss": 0.2078,
"step": 1324
},
{
"epoch": 2.66,
"learning_rate": 6.433344569249922e-07,
"loss": 0.2136,
"step": 1325
},
{
"epoch": 2.67,
"learning_rate": 6.356897258942452e-07,
"loss": 0.2261,
"step": 1326
},
{
"epoch": 2.67,
"learning_rate": 6.280891965442648e-07,
"loss": 0.2143,
"step": 1327
},
{
"epoch": 2.67,
"learning_rate": 6.205329047512821e-07,
"loss": 0.2048,
"step": 1328
},
{
"epoch": 2.67,
"learning_rate": 6.130208861827203e-07,
"loss": 0.2246,
"step": 1329
},
{
"epoch": 2.67,
"learning_rate": 6.055531762970168e-07,
"loss": 0.1926,
"step": 1330
},
{
"epoch": 2.68,
"learning_rate": 5.981298103434696e-07,
"loss": 0.2096,
"step": 1331
},
{
"epoch": 2.68,
"learning_rate": 5.907508233620574e-07,
"loss": 0.208,
"step": 1332
},
{
"epoch": 2.68,
"learning_rate": 5.83416250183283e-07,
"loss": 0.2297,
"step": 1333
},
{
"epoch": 2.68,
"learning_rate": 5.761261254280037e-07,
"loss": 0.2881,
"step": 1334
},
{
"epoch": 2.68,
"learning_rate": 5.688804835072748e-07,
"loss": 0.2218,
"step": 1335
},
{
"epoch": 2.69,
"learning_rate": 5.616793586221758e-07,
"loss": 0.1881,
"step": 1336
},
{
"epoch": 2.69,
"learning_rate": 5.545227847636602e-07,
"loss": 0.2333,
"step": 1337
},
{
"epoch": 2.69,
"learning_rate": 5.474107957123886e-07,
"loss": 0.2653,
"step": 1338
},
{
"epoch": 2.69,
"learning_rate": 5.40343425038573e-07,
"loss": 0.2134,
"step": 1339
},
{
"epoch": 2.69,
"learning_rate": 5.333207061018142e-07,
"loss": 0.242,
"step": 1340
},
{
"epoch": 2.7,
"learning_rate": 5.263426720509469e-07,
"loss": 0.2216,
"step": 1341
},
{
"epoch": 2.7,
"learning_rate": 5.194093558238866e-07,
"loss": 0.2243,
"step": 1342
},
{
"epoch": 2.7,
"learning_rate": 5.125207901474638e-07,
"loss": 0.2103,
"step": 1343
},
{
"epoch": 2.7,
"learning_rate": 5.056770075372841e-07,
"loss": 0.2766,
"step": 1344
},
{
"epoch": 2.7,
"learning_rate": 4.98878040297559e-07,
"loss": 0.2305,
"step": 1345
},
{
"epoch": 2.71,
"learning_rate": 4.921239205209672e-07,
"loss": 0.211,
"step": 1346
},
{
"epoch": 2.71,
"learning_rate": 4.854146800884929e-07,
"loss": 0.2193,
"step": 1347
},
{
"epoch": 2.71,
"learning_rate": 4.787503506692847e-07,
"loss": 0.2084,
"step": 1348
},
{
"epoch": 2.71,
"learning_rate": 4.7213096372049404e-07,
"loss": 0.2436,
"step": 1349
},
{
"epoch": 2.71,
"learning_rate": 4.6555655048713953e-07,
"loss": 0.1975,
"step": 1350
},
{
"epoch": 2.72,
"learning_rate": 4.59027142001951e-07,
"loss": 0.2212,
"step": 1351
},
{
"epoch": 2.72,
"learning_rate": 4.5254276908522685e-07,
"loss": 0.2217,
"step": 1352
},
{
"epoch": 2.72,
"learning_rate": 4.461034623446847e-07,
"loss": 0.2175,
"step": 1353
},
{
"epoch": 2.72,
"learning_rate": 4.397092521753232e-07,
"loss": 0.1919,
"step": 1354
},
{
"epoch": 2.72,
"learning_rate": 4.333601687592714e-07,
"loss": 0.1975,
"step": 1355
},
{
"epoch": 2.73,
"learning_rate": 4.270562420656543e-07,
"loss": 0.2145,
"step": 1356
},
{
"epoch": 2.73,
"learning_rate": 4.2079750185043955e-07,
"loss": 0.2356,
"step": 1357
},
{
"epoch": 2.73,
"learning_rate": 4.145839776563132e-07,
"loss": 0.2169,
"step": 1358
},
{
"epoch": 2.73,
"learning_rate": 4.084156988125232e-07,
"loss": 0.1981,
"step": 1359
},
{
"epoch": 2.73,
"learning_rate": 4.022926944347549e-07,
"loss": 0.2004,
"step": 1360
},
{
"epoch": 2.74,
"learning_rate": 3.9621499342498706e-07,
"loss": 0.2129,
"step": 1361
},
{
"epoch": 2.74,
"learning_rate": 3.9018262447135245e-07,
"loss": 0.2142,
"step": 1362
},
{
"epoch": 2.74,
"learning_rate": 3.841956160480098e-07,
"loss": 0.236,
"step": 1363
},
{
"epoch": 2.74,
"learning_rate": 3.782539964150045e-07,
"loss": 0.2025,
"step": 1364
},
{
"epoch": 2.74,
"learning_rate": 3.723577936181366e-07,
"loss": 0.2102,
"step": 1365
},
{
"epoch": 2.75,
"learning_rate": 3.665070354888278e-07,
"loss": 0.1956,
"step": 1366
},
{
"epoch": 2.75,
"learning_rate": 3.607017496439935e-07,
"loss": 0.2005,
"step": 1367
},
{
"epoch": 2.75,
"learning_rate": 3.5494196348590416e-07,
"loss": 0.1975,
"step": 1368
},
{
"epoch": 2.75,
"learning_rate": 3.4922770420206754e-07,
"loss": 0.2113,
"step": 1369
},
{
"epoch": 2.75,
"learning_rate": 3.435589987650878e-07,
"loss": 0.195,
"step": 1370
},
{
"epoch": 2.76,
"learning_rate": 3.3793587393255e-07,
"loss": 0.2075,
"step": 1371
},
{
"epoch": 2.76,
"learning_rate": 3.323583562468857e-07,
"loss": 0.2093,
"step": 1372
},
{
"epoch": 2.76,
"learning_rate": 3.2682647203525095e-07,
"loss": 0.2145,
"step": 1373
},
{
"epoch": 2.76,
"learning_rate": 3.213402474093996e-07,
"loss": 0.2473,
"step": 1374
},
{
"epoch": 2.76,
"learning_rate": 3.158997082655668e-07,
"loss": 0.2066,
"step": 1375
},
{
"epoch": 2.77,
"learning_rate": 3.1050488028433467e-07,
"loss": 0.2146,
"step": 1376
},
{
"epoch": 2.77,
"learning_rate": 3.0515578893052343e-07,
"loss": 0.2176,
"step": 1377
},
{
"epoch": 2.77,
"learning_rate": 2.9985245945306607e-07,
"loss": 0.2307,
"step": 1378
},
{
"epoch": 2.77,
"learning_rate": 2.9459491688488604e-07,
"loss": 0.2348,
"step": 1379
},
{
"epoch": 2.77,
"learning_rate": 2.8938318604278314e-07,
"loss": 0.2233,
"step": 1380
},
{
"epoch": 2.78,
"learning_rate": 2.8421729152731783e-07,
"loss": 0.201,
"step": 1381
},
{
"epoch": 2.78,
"learning_rate": 2.7909725772268915e-07,
"loss": 0.225,
"step": 1382
},
{
"epoch": 2.78,
"learning_rate": 2.7402310879662497e-07,
"loss": 0.221,
"step": 1383
},
{
"epoch": 2.78,
"learning_rate": 2.689948687002664e-07,
"loss": 0.1889,
"step": 1384
},
{
"epoch": 2.78,
"learning_rate": 2.640125611680522e-07,
"loss": 0.1927,
"step": 1385
},
{
"epoch": 2.79,
"learning_rate": 2.590762097176136e-07,
"loss": 0.2026,
"step": 1386
},
{
"epoch": 2.79,
"learning_rate": 2.54185837649652e-07,
"loss": 0.2427,
"step": 1387
},
{
"epoch": 2.79,
"learning_rate": 2.4934146804784234e-07,
"loss": 0.205,
"step": 1388
},
{
"epoch": 2.79,
"learning_rate": 2.4454312377871105e-07,
"loss": 0.1976,
"step": 1389
},
{
"epoch": 2.8,
"learning_rate": 2.3979082749154057e-07,
"loss": 0.3058,
"step": 1390
},
{
"epoch": 2.8,
"learning_rate": 2.3508460161825176e-07,
"loss": 0.185,
"step": 1391
},
{
"epoch": 2.8,
"learning_rate": 2.304244683733059e-07,
"loss": 0.1998,
"step": 1392
},
{
"epoch": 2.8,
"learning_rate": 2.25810449753594e-07,
"loss": 0.2364,
"step": 1393
},
{
"epoch": 2.8,
"learning_rate": 2.2124256753833672e-07,
"loss": 0.2484,
"step": 1394
},
{
"epoch": 2.81,
"learning_rate": 2.167208432889789e-07,
"loss": 0.261,
"step": 1395
},
{
"epoch": 2.81,
"learning_rate": 2.12245298349093e-07,
"loss": 0.2314,
"step": 1396
},
{
"epoch": 2.81,
"learning_rate": 2.0781595384427032e-07,
"loss": 0.2215,
"step": 1397
},
{
"epoch": 2.81,
"learning_rate": 2.034328306820288e-07,
"loss": 0.2273,
"step": 1398
},
{
"epoch": 2.81,
"learning_rate": 1.9909594955170752e-07,
"loss": 0.1957,
"step": 1399
},
{
"epoch": 2.82,
"learning_rate": 1.948053309243769e-07,
"loss": 0.1931,
"step": 1400
},
{
"epoch": 2.82,
"learning_rate": 1.9056099505273428e-07,
"loss": 0.2269,
"step": 1401
},
{
"epoch": 2.82,
"learning_rate": 1.86362961971015e-07,
"loss": 0.2566,
"step": 1402
},
{
"epoch": 2.82,
"learning_rate": 1.8221125149489038e-07,
"loss": 0.1666,
"step": 1403
},
{
"epoch": 2.82,
"learning_rate": 1.7810588322138222e-07,
"loss": 0.2136,
"step": 1404
},
{
"epoch": 2.83,
"learning_rate": 1.7404687652876728e-07,
"loss": 0.1809,
"step": 1405
},
{
"epoch": 2.83,
"learning_rate": 1.700342505764796e-07,
"loss": 0.2054,
"step": 1406
},
{
"epoch": 2.83,
"learning_rate": 1.6606802430503166e-07,
"loss": 0.239,
"step": 1407
},
{
"epoch": 2.83,
"learning_rate": 1.621482164359156e-07,
"loss": 0.2094,
"step": 1408
},
{
"epoch": 2.83,
"learning_rate": 1.5827484547151772e-07,
"loss": 0.2147,
"step": 1409
},
{
"epoch": 2.84,
"learning_rate": 1.544479296950341e-07,
"loss": 0.2109,
"step": 1410
},
{
"epoch": 2.84,
"learning_rate": 1.506674871703795e-07,
"loss": 0.2102,
"step": 1411
},
{
"epoch": 2.84,
"learning_rate": 1.4693353574210422e-07,
"loss": 0.2078,
"step": 1412
},
{
"epoch": 2.84,
"learning_rate": 1.43246093035313e-07,
"loss": 0.2484,
"step": 1413
},
{
"epoch": 2.84,
"learning_rate": 1.3960517645557502e-07,
"loss": 0.1937,
"step": 1414
},
{
"epoch": 2.85,
"learning_rate": 1.360108031888474e-07,
"loss": 0.2108,
"step": 1415
},
{
"epoch": 2.85,
"learning_rate": 1.3246299020139185e-07,
"loss": 0.1898,
"step": 1416
},
{
"epoch": 2.85,
"learning_rate": 1.2896175423969592e-07,
"loss": 0.1975,
"step": 1417
},
{
"epoch": 2.85,
"learning_rate": 1.2550711183039078e-07,
"loss": 0.199,
"step": 1418
},
{
"epoch": 2.85,
"learning_rate": 1.2209907928017794e-07,
"loss": 0.2651,
"step": 1419
},
{
"epoch": 2.86,
"learning_rate": 1.1873767267574609e-07,
"loss": 0.2376,
"step": 1420
},
{
"epoch": 2.86,
"learning_rate": 1.1542290788370547e-07,
"loss": 0.1911,
"step": 1421
},
{
"epoch": 2.86,
"learning_rate": 1.1215480055049799e-07,
"loss": 0.2304,
"step": 1422
},
{
"epoch": 2.86,
"learning_rate": 1.089333661023373e-07,
"loss": 0.2156,
"step": 1423
},
{
"epoch": 2.86,
"learning_rate": 1.057586197451299e-07,
"loss": 0.1769,
"step": 1424
},
{
"epoch": 2.87,
"learning_rate": 1.02630576464402e-07,
"loss": 0.1944,
"step": 1425
},
{
"epoch": 2.87,
"learning_rate": 9.95492510252305e-08,
"loss": 0.2289,
"step": 1426
},
{
"epoch": 2.87,
"learning_rate": 9.651465797217652e-08,
"loss": 0.1972,
"step": 1427
},
{
"epoch": 2.87,
"learning_rate": 9.352681162920985e-08,
"loss": 0.1834,
"step": 1428
},
{
"epoch": 2.87,
"learning_rate": 9.058572609964788e-08,
"loss": 0.1931,
"step": 1429
},
{
"epoch": 2.88,
"learning_rate": 8.76914152660846e-08,
"loss": 0.2081,
"step": 1430
},
{
"epoch": 2.88,
"learning_rate": 8.484389279032835e-08,
"loss": 0.1984,
"step": 1431
},
{
"epoch": 2.88,
"learning_rate": 8.204317211333301e-08,
"loss": 0.2323,
"step": 1432
},
{
"epoch": 2.88,
"learning_rate": 7.928926645514034e-08,
"loss": 0.1984,
"step": 1433
},
{
"epoch": 2.88,
"learning_rate": 7.658218881481438e-08,
"loss": 0.228,
"step": 1434
},
{
"epoch": 2.89,
"learning_rate": 7.39219519703771e-08,
"loss": 0.2283,
"step": 1435
},
{
"epoch": 2.89,
"learning_rate": 7.130856847875401e-08,
"loss": 0.1965,
"step": 1436
},
{
"epoch": 2.89,
"learning_rate": 6.874205067571082e-08,
"loss": 0.233,
"step": 1437
},
{
"epoch": 2.89,
"learning_rate": 6.622241067579915e-08,
"loss": 0.1997,
"step": 1438
},
{
"epoch": 2.89,
"learning_rate": 6.374966037229202e-08,
"loss": 0.208,
"step": 1439
},
{
"epoch": 2.9,
"learning_rate": 6.132381143713728e-08,
"loss": 0.2146,
"step": 1440
},
{
"epoch": 2.9,
"learning_rate": 5.894487532089321e-08,
"loss": 0.1617,
"step": 1441
},
{
"epoch": 2.9,
"learning_rate": 5.661286325268189e-08,
"loss": 0.2155,
"step": 1442
},
{
"epoch": 2.9,
"learning_rate": 5.4327786240132576e-08,
"loss": 0.2079,
"step": 1443
},
{
"epoch": 2.9,
"learning_rate": 5.2089655069329506e-08,
"loss": 0.2299,
"step": 1444
},
{
"epoch": 2.91,
"learning_rate": 4.989848030476307e-08,
"loss": 0.1926,
"step": 1445
},
{
"epoch": 2.91,
"learning_rate": 4.7754272289277646e-08,
"loss": 0.2201,
"step": 1446
},
{
"epoch": 2.91,
"learning_rate": 4.5657041144023804e-08,
"loss": 0.2278,
"step": 1447
},
{
"epoch": 2.91,
"learning_rate": 4.360679676841173e-08,
"loss": 0.2708,
"step": 1448
},
{
"epoch": 2.91,
"learning_rate": 4.1603548840062344e-08,
"loss": 0.1977,
"step": 1449
},
{
"epoch": 2.92,
"learning_rate": 3.964730681476292e-08,
"loss": 0.2331,
"step": 1450
},
{
"epoch": 2.92,
"learning_rate": 3.773807992642153e-08,
"loss": 0.2081,
"step": 1451
},
{
"epoch": 2.92,
"learning_rate": 3.58758771870249e-08,
"loss": 0.2669,
"step": 1452
},
{
"epoch": 2.92,
"learning_rate": 3.406070738659617e-08,
"loss": 0.1943,
"step": 1453
},
{
"epoch": 2.92,
"learning_rate": 3.229257909314831e-08,
"loss": 0.2172,
"step": 1454
},
{
"epoch": 2.93,
"learning_rate": 3.0571500652651906e-08,
"loss": 0.204,
"step": 1455
},
{
"epoch": 2.93,
"learning_rate": 2.8897480188989635e-08,
"loss": 0.201,
"step": 1456
},
{
"epoch": 2.93,
"learning_rate": 2.7270525603920738e-08,
"loss": 0.2032,
"step": 1457
},
{
"epoch": 2.93,
"learning_rate": 2.569064457703996e-08,
"loss": 0.2061,
"step": 1458
},
{
"epoch": 2.93,
"learning_rate": 2.4157844565747546e-08,
"loss": 0.2247,
"step": 1459
},
{
"epoch": 2.94,
"learning_rate": 2.26721328052093e-08,
"loss": 0.1961,
"step": 1460
},
{
"epoch": 2.94,
"learning_rate": 2.1233516308323266e-08,
"loss": 0.2504,
"step": 1461
},
{
"epoch": 2.94,
"learning_rate": 1.984200186568752e-08,
"loss": 0.2133,
"step": 1462
},
{
"epoch": 2.94,
"learning_rate": 1.8497596045568002e-08,
"loss": 0.1956,
"step": 1463
},
{
"epoch": 2.94,
"learning_rate": 1.7200305193866284e-08,
"loss": 0.2254,
"step": 1464
},
{
"epoch": 2.95,
"learning_rate": 1.5950135434091853e-08,
"loss": 0.2964,
"step": 1465
},
{
"epoch": 2.95,
"learning_rate": 1.4747092667329876e-08,
"loss": 0.232,
"step": 1466
},
{
"epoch": 2.95,
"learning_rate": 1.3591182572219031e-08,
"loss": 0.2221,
"step": 1467
},
{
"epoch": 2.95,
"learning_rate": 1.2482410604915952e-08,
"loss": 0.2262,
"step": 1468
},
{
"epoch": 2.95,
"learning_rate": 1.14207819990797e-08,
"loss": 0.222,
"step": 1469
},
{
"epoch": 2.96,
"learning_rate": 1.0406301765837346e-08,
"loss": 0.1983,
"step": 1470
},
{
"epoch": 2.96,
"learning_rate": 9.438974693768421e-09,
"loss": 0.2141,
"step": 1471
},
{
"epoch": 2.96,
"learning_rate": 8.518805348877169e-09,
"loss": 0.2189,
"step": 1472
},
{
"epoch": 2.96,
"learning_rate": 7.645798074572552e-09,
"loss": 0.221,
"step": 1473
},
{
"epoch": 2.96,
"learning_rate": 6.81995699164828e-09,
"loss": 0.2251,
"step": 1474
},
{
"epoch": 2.97,
"learning_rate": 6.0412859982628135e-09,
"loss": 0.2134,
"step": 1475
},
{
"epoch": 2.97,
"learning_rate": 5.309788769919388e-09,
"loss": 0.2326,
"step": 1476
},
{
"epoch": 2.97,
"learning_rate": 4.6254687594538e-09,
"loss": 0.2174,
"step": 1477
},
{
"epoch": 2.97,
"learning_rate": 3.988329197012198e-09,
"loss": 0.2139,
"step": 1478
},
{
"epoch": 2.97,
"learning_rate": 3.3983730900377654e-09,
"loss": 0.2022,
"step": 1479
},
{
"epoch": 2.98,
"learning_rate": 2.8556032232585074e-09,
"loss": 0.2265,
"step": 1480
},
{
"epoch": 2.98,
"learning_rate": 2.3600221586717043e-09,
"loss": 0.2016,
"step": 1481
},
{
"epoch": 2.98,
"learning_rate": 1.9116322355339224e-09,
"loss": 0.2391,
"step": 1482
},
{
"epoch": 2.98,
"learning_rate": 1.5104355703465801e-09,
"loss": 0.1975,
"step": 1483
},
{
"epoch": 2.98,
"learning_rate": 1.1564340568503973e-09,
"loss": 0.2393,
"step": 1484
},
{
"epoch": 2.99,
"learning_rate": 8.496293660120725e-10,
"loss": 0.2205,
"step": 1485
},
{
"epoch": 2.99,
"learning_rate": 5.900229460220619e-10,
"loss": 0.2113,
"step": 1486
},
{
"epoch": 2.99,
"learning_rate": 3.7761602227903705e-10,
"loss": 0.1974,
"step": 1487
},
{
"epoch": 2.99,
"learning_rate": 2.1240959739543544e-10,
"loss": 0.2007,
"step": 1488
},
{
"epoch": 2.99,
"learning_rate": 9.44044511796971e-11,
"loss": 0.2172,
"step": 1489
},
{
"epoch": 3.0,
"learning_rate": 2.3601140645146404e-11,
"loss": 0.2665,
"step": 1490
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.2013,
"step": 1491
},
{
"epoch": 3.0,
"step": 1491,
"total_flos": 8.711007485349069e+17,
"train_loss": 0.40526344859504126,
"train_runtime": 92325.1496,
"train_samples_per_second": 2.068,
"train_steps_per_second": 0.016
}
],
"max_steps": 1491,
"num_train_epochs": 3,
"total_flos": 8.711007485349069e+17,
"trial_name": null,
"trial_params": null
}