KCA_Pythia_6.9B_Discarding_Tuning / trainer_state.json
Wanfq's picture
Upload folder using huggingface_hub
51b5f0c verified
raw
history blame contribute delete
No virus
102 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.994671403197158,
"eval_steps": 500,
"global_step": 843,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 7.692307692307694e-07,
"loss": 1.0786,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.5384615384615387e-06,
"loss": 0.9062,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 2.307692307692308e-06,
"loss": 0.8787,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 3.0769230769230774e-06,
"loss": 0.8892,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 3.846153846153847e-06,
"loss": 0.8591,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 4.615384615384616e-06,
"loss": 0.8938,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 5.384615384615385e-06,
"loss": 0.807,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 6.153846153846155e-06,
"loss": 0.7992,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 6.923076923076923e-06,
"loss": 0.8281,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 7.692307692307694e-06,
"loss": 0.8381,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 8.461538461538462e-06,
"loss": 0.8583,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 9.230769230769232e-06,
"loss": 0.7883,
"step": 12
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 0.8521,
"step": 13
},
{
"epoch": 0.05,
"learning_rate": 1.076923076923077e-05,
"loss": 0.7669,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 1.1538461538461538e-05,
"loss": 0.9095,
"step": 15
},
{
"epoch": 0.06,
"learning_rate": 1.230769230769231e-05,
"loss": 0.865,
"step": 16
},
{
"epoch": 0.06,
"learning_rate": 1.3076923076923078e-05,
"loss": 0.8401,
"step": 17
},
{
"epoch": 0.06,
"learning_rate": 1.3846153846153847e-05,
"loss": 0.7609,
"step": 18
},
{
"epoch": 0.07,
"learning_rate": 1.4615384615384615e-05,
"loss": 0.8153,
"step": 19
},
{
"epoch": 0.07,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.7484,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 1.6153846153846154e-05,
"loss": 0.8168,
"step": 21
},
{
"epoch": 0.08,
"learning_rate": 1.6923076923076924e-05,
"loss": 0.7457,
"step": 22
},
{
"epoch": 0.08,
"learning_rate": 1.7692307692307694e-05,
"loss": 0.7892,
"step": 23
},
{
"epoch": 0.09,
"learning_rate": 1.8461538461538465e-05,
"loss": 0.7826,
"step": 24
},
{
"epoch": 0.09,
"learning_rate": 1.923076923076923e-05,
"loss": 0.8022,
"step": 25
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 0.8033,
"step": 26
},
{
"epoch": 0.1,
"learning_rate": 1.999992606925178e-05,
"loss": 0.7994,
"step": 27
},
{
"epoch": 0.1,
"learning_rate": 1.9999704278100265e-05,
"loss": 0.8238,
"step": 28
},
{
"epoch": 0.1,
"learning_rate": 1.9999334629824897e-05,
"loss": 0.7715,
"step": 29
},
{
"epoch": 0.11,
"learning_rate": 1.9998817129891346e-05,
"loss": 0.7976,
"step": 30
},
{
"epoch": 0.11,
"learning_rate": 1.9998151785951447e-05,
"loss": 0.811,
"step": 31
},
{
"epoch": 0.11,
"learning_rate": 1.9997338607843074e-05,
"loss": 0.7845,
"step": 32
},
{
"epoch": 0.12,
"learning_rate": 1.999637760759e-05,
"loss": 0.7886,
"step": 33
},
{
"epoch": 0.12,
"learning_rate": 1.999526879940172e-05,
"loss": 0.7642,
"step": 34
},
{
"epoch": 0.12,
"learning_rate": 1.9994012199673233e-05,
"loss": 0.7403,
"step": 35
},
{
"epoch": 0.13,
"learning_rate": 1.9992607826984817e-05,
"loss": 0.7592,
"step": 36
},
{
"epoch": 0.13,
"learning_rate": 1.9991055702101733e-05,
"loss": 0.712,
"step": 37
},
{
"epoch": 0.13,
"learning_rate": 1.9989355847973932e-05,
"loss": 0.7449,
"step": 38
},
{
"epoch": 0.14,
"learning_rate": 1.9987508289735714e-05,
"loss": 0.7602,
"step": 39
},
{
"epoch": 0.14,
"learning_rate": 1.9985513054705348e-05,
"loss": 0.7569,
"step": 40
},
{
"epoch": 0.15,
"learning_rate": 1.9983370172384683e-05,
"loss": 0.759,
"step": 41
},
{
"epoch": 0.15,
"learning_rate": 1.998107967445869e-05,
"loss": 0.7725,
"step": 42
},
{
"epoch": 0.15,
"learning_rate": 1.997864159479502e-05,
"loss": 0.7712,
"step": 43
},
{
"epoch": 0.16,
"learning_rate": 1.997605596944348e-05,
"loss": 0.784,
"step": 44
},
{
"epoch": 0.16,
"learning_rate": 1.9973322836635517e-05,
"loss": 0.8153,
"step": 45
},
{
"epoch": 0.16,
"learning_rate": 1.997044223678364e-05,
"loss": 0.7787,
"step": 46
},
{
"epoch": 0.17,
"learning_rate": 1.996741421248083e-05,
"loss": 0.78,
"step": 47
},
{
"epoch": 0.17,
"learning_rate": 1.9964238808499906e-05,
"loss": 0.7525,
"step": 48
},
{
"epoch": 0.17,
"learning_rate": 1.9960916071792867e-05,
"loss": 0.8769,
"step": 49
},
{
"epoch": 0.18,
"learning_rate": 1.99574460514902e-05,
"loss": 0.7442,
"step": 50
},
{
"epoch": 0.18,
"learning_rate": 1.9953828798900136e-05,
"loss": 0.7131,
"step": 51
},
{
"epoch": 0.18,
"learning_rate": 1.9950064367507916e-05,
"loss": 0.7578,
"step": 52
},
{
"epoch": 0.19,
"learning_rate": 1.9946152812974993e-05,
"loss": 0.74,
"step": 53
},
{
"epoch": 0.19,
"learning_rate": 1.9942094193138186e-05,
"loss": 0.7412,
"step": 54
},
{
"epoch": 0.2,
"learning_rate": 1.9937888568008864e-05,
"loss": 0.7342,
"step": 55
},
{
"epoch": 0.2,
"learning_rate": 1.9933535999772026e-05,
"loss": 0.694,
"step": 56
},
{
"epoch": 0.2,
"learning_rate": 1.9929036552785397e-05,
"loss": 0.7802,
"step": 57
},
{
"epoch": 0.21,
"learning_rate": 1.9924390293578473e-05,
"loss": 0.8105,
"step": 58
},
{
"epoch": 0.21,
"learning_rate": 1.991959729085154e-05,
"loss": 0.8056,
"step": 59
},
{
"epoch": 0.21,
"learning_rate": 1.9914657615474655e-05,
"loss": 0.762,
"step": 60
},
{
"epoch": 0.22,
"learning_rate": 1.9909571340486595e-05,
"loss": 0.7823,
"step": 61
},
{
"epoch": 0.22,
"learning_rate": 1.990433854109378e-05,
"loss": 0.7993,
"step": 62
},
{
"epoch": 0.22,
"learning_rate": 1.9898959294669167e-05,
"loss": 0.8046,
"step": 63
},
{
"epoch": 0.23,
"learning_rate": 1.9893433680751105e-05,
"loss": 0.793,
"step": 64
},
{
"epoch": 0.23,
"learning_rate": 1.9887761781042138e-05,
"loss": 0.7572,
"step": 65
},
{
"epoch": 0.23,
"learning_rate": 1.9881943679407832e-05,
"loss": 0.7274,
"step": 66
},
{
"epoch": 0.24,
"learning_rate": 1.9875979461875502e-05,
"loss": 0.7876,
"step": 67
},
{
"epoch": 0.24,
"learning_rate": 1.986986921663297e-05,
"loss": 0.7355,
"step": 68
},
{
"epoch": 0.25,
"learning_rate": 1.9863613034027224e-05,
"loss": 0.6953,
"step": 69
},
{
"epoch": 0.25,
"learning_rate": 1.9857211006563127e-05,
"loss": 0.7466,
"step": 70
},
{
"epoch": 0.25,
"learning_rate": 1.9850663228902013e-05,
"loss": 0.782,
"step": 71
},
{
"epoch": 0.26,
"learning_rate": 1.9843969797860293e-05,
"loss": 0.7112,
"step": 72
},
{
"epoch": 0.26,
"learning_rate": 1.9837130812408052e-05,
"loss": 0.7975,
"step": 73
},
{
"epoch": 0.26,
"learning_rate": 1.983014637366755e-05,
"loss": 0.7261,
"step": 74
},
{
"epoch": 0.27,
"learning_rate": 1.9823016584911738e-05,
"loss": 0.7183,
"step": 75
},
{
"epoch": 0.27,
"learning_rate": 1.9815741551562742e-05,
"loss": 0.7847,
"step": 76
},
{
"epoch": 0.27,
"learning_rate": 1.9808321381190294e-05,
"loss": 0.8388,
"step": 77
},
{
"epoch": 0.28,
"learning_rate": 1.9800756183510144e-05,
"loss": 0.7287,
"step": 78
},
{
"epoch": 0.28,
"learning_rate": 1.979304607038244e-05,
"loss": 0.734,
"step": 79
},
{
"epoch": 0.28,
"learning_rate": 1.978519115581006e-05,
"loss": 0.7749,
"step": 80
},
{
"epoch": 0.29,
"learning_rate": 1.9777191555936956e-05,
"loss": 0.7739,
"step": 81
},
{
"epoch": 0.29,
"learning_rate": 1.9769047389046402e-05,
"loss": 0.7343,
"step": 82
},
{
"epoch": 0.29,
"learning_rate": 1.9760758775559275e-05,
"loss": 0.7042,
"step": 83
},
{
"epoch": 0.3,
"learning_rate": 1.9752325838032245e-05,
"loss": 0.7294,
"step": 84
},
{
"epoch": 0.3,
"learning_rate": 1.9743748701155995e-05,
"loss": 0.744,
"step": 85
},
{
"epoch": 0.31,
"learning_rate": 1.9735027491753353e-05,
"loss": 0.781,
"step": 86
},
{
"epoch": 0.31,
"learning_rate": 1.9726162338777424e-05,
"loss": 0.7594,
"step": 87
},
{
"epoch": 0.31,
"learning_rate": 1.9717153373309693e-05,
"loss": 0.6994,
"step": 88
},
{
"epoch": 0.32,
"learning_rate": 1.9708000728558064e-05,
"loss": 0.7582,
"step": 89
},
{
"epoch": 0.32,
"learning_rate": 1.9698704539854917e-05,
"loss": 0.7747,
"step": 90
},
{
"epoch": 0.32,
"learning_rate": 1.9689264944655083e-05,
"loss": 0.715,
"step": 91
},
{
"epoch": 0.33,
"learning_rate": 1.9679682082533838e-05,
"loss": 0.748,
"step": 92
},
{
"epoch": 0.33,
"learning_rate": 1.966995609518481e-05,
"loss": 0.7466,
"step": 93
},
{
"epoch": 0.33,
"learning_rate": 1.9660087126417905e-05,
"loss": 0.757,
"step": 94
},
{
"epoch": 0.34,
"learning_rate": 1.965007532215717e-05,
"loss": 0.7464,
"step": 95
},
{
"epoch": 0.34,
"learning_rate": 1.9639920830438643e-05,
"loss": 0.6998,
"step": 96
},
{
"epoch": 0.34,
"learning_rate": 1.9629623801408157e-05,
"loss": 0.7051,
"step": 97
},
{
"epoch": 0.35,
"learning_rate": 1.9619184387319123e-05,
"loss": 0.7323,
"step": 98
},
{
"epoch": 0.35,
"learning_rate": 1.9608602742530284e-05,
"loss": 0.7487,
"step": 99
},
{
"epoch": 0.36,
"learning_rate": 1.959787902350342e-05,
"loss": 0.7053,
"step": 100
},
{
"epoch": 0.36,
"learning_rate": 1.9587013388801045e-05,
"loss": 0.8074,
"step": 101
},
{
"epoch": 0.36,
"learning_rate": 1.957600599908406e-05,
"loss": 0.7146,
"step": 102
},
{
"epoch": 0.37,
"learning_rate": 1.956485701710938e-05,
"loss": 0.6957,
"step": 103
},
{
"epoch": 0.37,
"learning_rate": 1.9553566607727517e-05,
"loss": 0.7842,
"step": 104
},
{
"epoch": 0.37,
"learning_rate": 1.9542134937880155e-05,
"loss": 0.7144,
"step": 105
},
{
"epoch": 0.38,
"learning_rate": 1.9530562176597674e-05,
"loss": 0.7026,
"step": 106
},
{
"epoch": 0.38,
"learning_rate": 1.9518848494996657e-05,
"loss": 0.7126,
"step": 107
},
{
"epoch": 0.38,
"learning_rate": 1.9506994066277348e-05,
"loss": 0.6872,
"step": 108
},
{
"epoch": 0.39,
"learning_rate": 1.949499906572111e-05,
"loss": 0.7235,
"step": 109
},
{
"epoch": 0.39,
"learning_rate": 1.948286367068781e-05,
"loss": 0.73,
"step": 110
},
{
"epoch": 0.39,
"learning_rate": 1.9470588060613224e-05,
"loss": 0.7863,
"step": 111
},
{
"epoch": 0.4,
"learning_rate": 1.9458172417006347e-05,
"loss": 0.7435,
"step": 112
},
{
"epoch": 0.4,
"learning_rate": 1.9445616923446753e-05,
"loss": 0.7554,
"step": 113
},
{
"epoch": 0.4,
"learning_rate": 1.9432921765581848e-05,
"loss": 0.7803,
"step": 114
},
{
"epoch": 0.41,
"learning_rate": 1.942008713112413e-05,
"loss": 0.7459,
"step": 115
},
{
"epoch": 0.41,
"learning_rate": 1.9407113209848433e-05,
"loss": 0.8164,
"step": 116
},
{
"epoch": 0.42,
"learning_rate": 1.939400019358909e-05,
"loss": 0.7806,
"step": 117
},
{
"epoch": 0.42,
"learning_rate": 1.9380748276237126e-05,
"loss": 0.6947,
"step": 118
},
{
"epoch": 0.42,
"learning_rate": 1.936735765373737e-05,
"loss": 0.7698,
"step": 119
},
{
"epoch": 0.43,
"learning_rate": 1.9353828524085577e-05,
"loss": 0.7534,
"step": 120
},
{
"epoch": 0.43,
"learning_rate": 1.9340161087325483e-05,
"loss": 0.7435,
"step": 121
},
{
"epoch": 0.43,
"learning_rate": 1.9326355545545846e-05,
"loss": 0.8259,
"step": 122
},
{
"epoch": 0.44,
"learning_rate": 1.9312412102877472e-05,
"loss": 0.6915,
"step": 123
},
{
"epoch": 0.44,
"learning_rate": 1.9298330965490203e-05,
"loss": 0.7215,
"step": 124
},
{
"epoch": 0.44,
"learning_rate": 1.928411234158983e-05,
"loss": 0.7064,
"step": 125
},
{
"epoch": 0.45,
"learning_rate": 1.9269756441415062e-05,
"loss": 0.7452,
"step": 126
},
{
"epoch": 0.45,
"learning_rate": 1.9255263477234382e-05,
"loss": 0.7738,
"step": 127
},
{
"epoch": 0.45,
"learning_rate": 1.9240633663342933e-05,
"loss": 0.7753,
"step": 128
},
{
"epoch": 0.46,
"learning_rate": 1.9225867216059326e-05,
"loss": 0.7997,
"step": 129
},
{
"epoch": 0.46,
"learning_rate": 1.9210964353722464e-05,
"loss": 0.7683,
"step": 130
},
{
"epoch": 0.47,
"learning_rate": 1.91959252966883e-05,
"loss": 0.7061,
"step": 131
},
{
"epoch": 0.47,
"learning_rate": 1.918075026732658e-05,
"loss": 0.6754,
"step": 132
},
{
"epoch": 0.47,
"learning_rate": 1.916543949001756e-05,
"loss": 0.7096,
"step": 133
},
{
"epoch": 0.48,
"learning_rate": 1.9149993191148687e-05,
"loss": 0.7245,
"step": 134
},
{
"epoch": 0.48,
"learning_rate": 1.9134411599111243e-05,
"loss": 0.7378,
"step": 135
},
{
"epoch": 0.48,
"learning_rate": 1.911869494429698e-05,
"loss": 0.7385,
"step": 136
},
{
"epoch": 0.49,
"learning_rate": 1.9102843459094707e-05,
"loss": 0.6771,
"step": 137
},
{
"epoch": 0.49,
"learning_rate": 1.9086857377886864e-05,
"loss": 0.7523,
"step": 138
},
{
"epoch": 0.49,
"learning_rate": 1.9070736937046036e-05,
"loss": 0.7115,
"step": 139
},
{
"epoch": 0.5,
"learning_rate": 1.905448237493147e-05,
"loss": 0.7192,
"step": 140
},
{
"epoch": 0.5,
"learning_rate": 1.9038093931885554e-05,
"loss": 0.7545,
"step": 141
},
{
"epoch": 0.5,
"learning_rate": 1.902157185023026e-05,
"loss": 0.7652,
"step": 142
},
{
"epoch": 0.51,
"learning_rate": 1.9004916374263563e-05,
"loss": 0.7114,
"step": 143
},
{
"epoch": 0.51,
"learning_rate": 1.8988127750255824e-05,
"loss": 0.7513,
"step": 144
},
{
"epoch": 0.52,
"learning_rate": 1.8971206226446146e-05,
"loss": 0.7854,
"step": 145
},
{
"epoch": 0.52,
"learning_rate": 1.8954152053038714e-05,
"loss": 0.8286,
"step": 146
},
{
"epoch": 0.52,
"learning_rate": 1.8936965482199085e-05,
"loss": 0.6968,
"step": 147
},
{
"epoch": 0.53,
"learning_rate": 1.891964676805047e-05,
"loss": 0.7561,
"step": 148
},
{
"epoch": 0.53,
"learning_rate": 1.8902196166669967e-05,
"loss": 0.7188,
"step": 149
},
{
"epoch": 0.53,
"learning_rate": 1.8884613936084785e-05,
"loss": 0.7985,
"step": 150
},
{
"epoch": 0.54,
"learning_rate": 1.8866900336268408e-05,
"loss": 0.7772,
"step": 151
},
{
"epoch": 0.54,
"learning_rate": 1.884905562913678e-05,
"loss": 0.7805,
"step": 152
},
{
"epoch": 0.54,
"learning_rate": 1.8831080078544405e-05,
"loss": 0.7721,
"step": 153
},
{
"epoch": 0.55,
"learning_rate": 1.881297395028047e-05,
"loss": 0.722,
"step": 154
},
{
"epoch": 0.55,
"learning_rate": 1.879473751206489e-05,
"loss": 0.7235,
"step": 155
},
{
"epoch": 0.55,
"learning_rate": 1.877637103354438e-05,
"loss": 0.7071,
"step": 156
},
{
"epoch": 0.56,
"learning_rate": 1.875787478628843e-05,
"loss": 0.734,
"step": 157
},
{
"epoch": 0.56,
"learning_rate": 1.8739249043785324e-05,
"loss": 0.759,
"step": 158
},
{
"epoch": 0.56,
"learning_rate": 1.872049408143808e-05,
"loss": 0.6844,
"step": 159
},
{
"epoch": 0.57,
"learning_rate": 1.8701610176560374e-05,
"loss": 0.7777,
"step": 160
},
{
"epoch": 0.57,
"learning_rate": 1.8682597608372447e-05,
"loss": 0.7862,
"step": 161
},
{
"epoch": 0.58,
"learning_rate": 1.866345665799698e-05,
"loss": 0.7186,
"step": 162
},
{
"epoch": 0.58,
"learning_rate": 1.8644187608454935e-05,
"loss": 0.7367,
"step": 163
},
{
"epoch": 0.58,
"learning_rate": 1.8624790744661356e-05,
"loss": 0.7271,
"step": 164
},
{
"epoch": 0.59,
"learning_rate": 1.8605266353421173e-05,
"loss": 0.7531,
"step": 165
},
{
"epoch": 0.59,
"learning_rate": 1.8585614723424964e-05,
"loss": 0.7802,
"step": 166
},
{
"epoch": 0.59,
"learning_rate": 1.8565836145244662e-05,
"loss": 0.7308,
"step": 167
},
{
"epoch": 0.6,
"learning_rate": 1.8545930911329287e-05,
"loss": 0.7535,
"step": 168
},
{
"epoch": 0.6,
"learning_rate": 1.852589931600061e-05,
"loss": 0.7967,
"step": 169
},
{
"epoch": 0.6,
"learning_rate": 1.8505741655448792e-05,
"loss": 0.7878,
"step": 170
},
{
"epoch": 0.61,
"learning_rate": 1.848545822772802e-05,
"loss": 0.6635,
"step": 171
},
{
"epoch": 0.61,
"learning_rate": 1.8465049332752093e-05,
"loss": 0.7953,
"step": 172
},
{
"epoch": 0.61,
"learning_rate": 1.8444515272289983e-05,
"loss": 0.7316,
"step": 173
},
{
"epoch": 0.62,
"learning_rate": 1.8423856349961384e-05,
"loss": 0.7798,
"step": 174
},
{
"epoch": 0.62,
"learning_rate": 1.840307287123221e-05,
"loss": 0.7102,
"step": 175
},
{
"epoch": 0.63,
"learning_rate": 1.8382165143410094e-05,
"loss": 0.6605,
"step": 176
},
{
"epoch": 0.63,
"learning_rate": 1.836113347563982e-05,
"loss": 0.6919,
"step": 177
},
{
"epoch": 0.63,
"learning_rate": 1.833997817889878e-05,
"loss": 0.7349,
"step": 178
},
{
"epoch": 0.64,
"learning_rate": 1.8318699565992357e-05,
"loss": 0.7081,
"step": 179
},
{
"epoch": 0.64,
"learning_rate": 1.8297297951549305e-05,
"loss": 0.6828,
"step": 180
},
{
"epoch": 0.64,
"learning_rate": 1.8275773652017097e-05,
"loss": 0.6987,
"step": 181
},
{
"epoch": 0.65,
"learning_rate": 1.8254126985657244e-05,
"loss": 0.7355,
"step": 182
},
{
"epoch": 0.65,
"learning_rate": 1.8232358272540603e-05,
"loss": 0.6853,
"step": 183
},
{
"epoch": 0.65,
"learning_rate": 1.8210467834542614e-05,
"loss": 0.7092,
"step": 184
},
{
"epoch": 0.66,
"learning_rate": 1.8188455995338578e-05,
"loss": 0.8474,
"step": 185
},
{
"epoch": 0.66,
"learning_rate": 1.8166323080398835e-05,
"loss": 0.7179,
"step": 186
},
{
"epoch": 0.66,
"learning_rate": 1.8144069416983986e-05,
"loss": 0.7874,
"step": 187
},
{
"epoch": 0.67,
"learning_rate": 1.8121695334140016e-05,
"loss": 0.7409,
"step": 188
},
{
"epoch": 0.67,
"learning_rate": 1.8099201162693474e-05,
"loss": 0.6965,
"step": 189
},
{
"epoch": 0.67,
"learning_rate": 1.8076587235246542e-05,
"loss": 0.7203,
"step": 190
},
{
"epoch": 0.68,
"learning_rate": 1.805385388617213e-05,
"loss": 0.7382,
"step": 191
},
{
"epoch": 0.68,
"learning_rate": 1.8031001451608945e-05,
"loss": 0.7588,
"step": 192
},
{
"epoch": 0.69,
"learning_rate": 1.8008030269456505e-05,
"loss": 0.7532,
"step": 193
},
{
"epoch": 0.69,
"learning_rate": 1.798494067937014e-05,
"loss": 0.7759,
"step": 194
},
{
"epoch": 0.69,
"learning_rate": 1.7961733022755992e-05,
"loss": 0.7504,
"step": 195
},
{
"epoch": 0.7,
"learning_rate": 1.7938407642765938e-05,
"loss": 0.7401,
"step": 196
},
{
"epoch": 0.7,
"learning_rate": 1.7914964884292543e-05,
"loss": 0.6713,
"step": 197
},
{
"epoch": 0.7,
"learning_rate": 1.789140509396394e-05,
"loss": 0.7576,
"step": 198
},
{
"epoch": 0.71,
"learning_rate": 1.7867728620138708e-05,
"loss": 0.7096,
"step": 199
},
{
"epoch": 0.71,
"learning_rate": 1.784393581290074e-05,
"loss": 0.7455,
"step": 200
},
{
"epoch": 0.71,
"learning_rate": 1.7820027024054044e-05,
"loss": 0.7138,
"step": 201
},
{
"epoch": 0.72,
"learning_rate": 1.7796002607117546e-05,
"loss": 0.7712,
"step": 202
},
{
"epoch": 0.72,
"learning_rate": 1.777186291731987e-05,
"loss": 0.707,
"step": 203
},
{
"epoch": 0.72,
"learning_rate": 1.7747608311594088e-05,
"loss": 0.7968,
"step": 204
},
{
"epoch": 0.73,
"learning_rate": 1.772323914857242e-05,
"loss": 0.6815,
"step": 205
},
{
"epoch": 0.73,
"learning_rate": 1.7698755788580963e-05,
"loss": 0.6922,
"step": 206
},
{
"epoch": 0.74,
"learning_rate": 1.767415859363434e-05,
"loss": 0.7545,
"step": 207
},
{
"epoch": 0.74,
"learning_rate": 1.764944792743036e-05,
"loss": 0.7491,
"step": 208
},
{
"epoch": 0.74,
"learning_rate": 1.7624624155344626e-05,
"loss": 0.6876,
"step": 209
},
{
"epoch": 0.75,
"learning_rate": 1.759968764442515e-05,
"loss": 0.727,
"step": 210
},
{
"epoch": 0.75,
"learning_rate": 1.7574638763386916e-05,
"loss": 0.736,
"step": 211
},
{
"epoch": 0.75,
"learning_rate": 1.754947788260642e-05,
"loss": 0.7459,
"step": 212
},
{
"epoch": 0.76,
"learning_rate": 1.7524205374116216e-05,
"loss": 0.7224,
"step": 213
},
{
"epoch": 0.76,
"learning_rate": 1.7498821611599398e-05,
"loss": 0.7632,
"step": 214
},
{
"epoch": 0.76,
"learning_rate": 1.747332697038407e-05,
"loss": 0.7472,
"step": 215
},
{
"epoch": 0.77,
"learning_rate": 1.744772182743782e-05,
"loss": 0.7437,
"step": 216
},
{
"epoch": 0.77,
"learning_rate": 1.742200656136212e-05,
"loss": 0.7449,
"step": 217
},
{
"epoch": 0.77,
"learning_rate": 1.7396181552386742e-05,
"loss": 0.7694,
"step": 218
},
{
"epoch": 0.78,
"learning_rate": 1.737024718236413e-05,
"loss": 0.6971,
"step": 219
},
{
"epoch": 0.78,
"learning_rate": 1.734420383476377e-05,
"loss": 0.7962,
"step": 220
},
{
"epoch": 0.79,
"learning_rate": 1.7318051894666487e-05,
"loss": 0.7418,
"step": 221
},
{
"epoch": 0.79,
"learning_rate": 1.7291791748758787e-05,
"loss": 0.7646,
"step": 222
},
{
"epoch": 0.79,
"learning_rate": 1.7265423785327107e-05,
"loss": 0.7446,
"step": 223
},
{
"epoch": 0.8,
"learning_rate": 1.7238948394252115e-05,
"loss": 0.6746,
"step": 224
},
{
"epoch": 0.8,
"learning_rate": 1.7212365967002895e-05,
"loss": 0.7261,
"step": 225
},
{
"epoch": 0.8,
"learning_rate": 1.71856768966312e-05,
"loss": 0.7379,
"step": 226
},
{
"epoch": 0.81,
"learning_rate": 1.7158881577765612e-05,
"loss": 0.7286,
"step": 227
},
{
"epoch": 0.81,
"learning_rate": 1.7131980406605732e-05,
"loss": 0.7371,
"step": 228
},
{
"epoch": 0.81,
"learning_rate": 1.7104973780916296e-05,
"loss": 0.7744,
"step": 229
},
{
"epoch": 0.82,
"learning_rate": 1.7077862100021317e-05,
"loss": 0.6934,
"step": 230
},
{
"epoch": 0.82,
"learning_rate": 1.7050645764798166e-05,
"loss": 0.7132,
"step": 231
},
{
"epoch": 0.82,
"learning_rate": 1.7023325177671647e-05,
"loss": 0.751,
"step": 232
},
{
"epoch": 0.83,
"learning_rate": 1.699590074260805e-05,
"loss": 0.6951,
"step": 233
},
{
"epoch": 0.83,
"learning_rate": 1.6968372865109174e-05,
"loss": 0.7202,
"step": 234
},
{
"epoch": 0.83,
"learning_rate": 1.6940741952206342e-05,
"loss": 0.729,
"step": 235
},
{
"epoch": 0.84,
"learning_rate": 1.6913008412454356e-05,
"loss": 0.7358,
"step": 236
},
{
"epoch": 0.84,
"learning_rate": 1.6885172655925495e-05,
"loss": 0.7403,
"step": 237
},
{
"epoch": 0.85,
"learning_rate": 1.6857235094203414e-05,
"loss": 0.6919,
"step": 238
},
{
"epoch": 0.85,
"learning_rate": 1.6829196140377084e-05,
"loss": 0.7425,
"step": 239
},
{
"epoch": 0.85,
"learning_rate": 1.680105620903467e-05,
"loss": 0.7246,
"step": 240
},
{
"epoch": 0.86,
"learning_rate": 1.6772815716257414e-05,
"loss": 0.6897,
"step": 241
},
{
"epoch": 0.86,
"learning_rate": 1.674447507961346e-05,
"loss": 0.7282,
"step": 242
},
{
"epoch": 0.86,
"learning_rate": 1.6716034718151707e-05,
"loss": 0.7752,
"step": 243
},
{
"epoch": 0.87,
"learning_rate": 1.6687495052395593e-05,
"loss": 0.7943,
"step": 244
},
{
"epoch": 0.87,
"learning_rate": 1.6658856504336892e-05,
"loss": 0.7473,
"step": 245
},
{
"epoch": 0.87,
"learning_rate": 1.6630119497429457e-05,
"loss": 0.7683,
"step": 246
},
{
"epoch": 0.88,
"learning_rate": 1.6601284456582972e-05,
"loss": 0.783,
"step": 247
},
{
"epoch": 0.88,
"learning_rate": 1.6572351808156666e-05,
"loss": 0.754,
"step": 248
},
{
"epoch": 0.88,
"learning_rate": 1.654332197995301e-05,
"loss": 0.7996,
"step": 249
},
{
"epoch": 0.89,
"learning_rate": 1.6514195401211387e-05,
"loss": 0.7494,
"step": 250
},
{
"epoch": 0.89,
"learning_rate": 1.6484972502601754e-05,
"loss": 0.7533,
"step": 251
},
{
"epoch": 0.9,
"learning_rate": 1.6455653716218253e-05,
"loss": 0.6759,
"step": 252
},
{
"epoch": 0.9,
"learning_rate": 1.642623947557285e-05,
"loss": 0.7409,
"step": 253
},
{
"epoch": 0.9,
"learning_rate": 1.6396730215588913e-05,
"loss": 0.6764,
"step": 254
},
{
"epoch": 0.91,
"learning_rate": 1.6367126372594776e-05,
"loss": 0.8053,
"step": 255
},
{
"epoch": 0.91,
"learning_rate": 1.633742838431729e-05,
"loss": 0.7669,
"step": 256
},
{
"epoch": 0.91,
"learning_rate": 1.6307636689875347e-05,
"loss": 0.8257,
"step": 257
},
{
"epoch": 0.92,
"learning_rate": 1.6277751729773407e-05,
"loss": 0.7257,
"step": 258
},
{
"epoch": 0.92,
"learning_rate": 1.6247773945894964e-05,
"loss": 0.7021,
"step": 259
},
{
"epoch": 0.92,
"learning_rate": 1.621770378149601e-05,
"loss": 0.6818,
"step": 260
},
{
"epoch": 0.93,
"learning_rate": 1.61875416811985e-05,
"loss": 0.743,
"step": 261
},
{
"epoch": 0.93,
"learning_rate": 1.6157288090983762e-05,
"loss": 0.6995,
"step": 262
},
{
"epoch": 0.93,
"learning_rate": 1.6126943458185906e-05,
"loss": 0.6883,
"step": 263
},
{
"epoch": 0.94,
"learning_rate": 1.6096508231485217e-05,
"loss": 0.7109,
"step": 264
},
{
"epoch": 0.94,
"learning_rate": 1.6065982860901505e-05,
"loss": 0.695,
"step": 265
},
{
"epoch": 0.94,
"learning_rate": 1.6035367797787477e-05,
"loss": 0.7231,
"step": 266
},
{
"epoch": 0.95,
"learning_rate": 1.600466349482203e-05,
"loss": 0.7546,
"step": 267
},
{
"epoch": 0.95,
"learning_rate": 1.597387040600358e-05,
"loss": 0.724,
"step": 268
},
{
"epoch": 0.96,
"learning_rate": 1.5942988986643354e-05,
"loss": 0.7793,
"step": 269
},
{
"epoch": 0.96,
"learning_rate": 1.5912019693358634e-05,
"loss": 0.7191,
"step": 270
},
{
"epoch": 0.96,
"learning_rate": 1.5880962984066034e-05,
"loss": 0.6234,
"step": 271
},
{
"epoch": 0.97,
"learning_rate": 1.5849819317974695e-05,
"loss": 0.6911,
"step": 272
},
{
"epoch": 0.97,
"learning_rate": 1.581858915557953e-05,
"loss": 0.7358,
"step": 273
},
{
"epoch": 0.97,
"learning_rate": 1.578727295865439e-05,
"loss": 0.7358,
"step": 274
},
{
"epoch": 0.98,
"learning_rate": 1.575587119024525e-05,
"loss": 0.7159,
"step": 275
},
{
"epoch": 0.98,
"learning_rate": 1.572438431466336e-05,
"loss": 0.8004,
"step": 276
},
{
"epoch": 0.98,
"learning_rate": 1.5692812797478368e-05,
"loss": 0.7843,
"step": 277
},
{
"epoch": 0.99,
"learning_rate": 1.5661157105511456e-05,
"loss": 0.7238,
"step": 278
},
{
"epoch": 0.99,
"learning_rate": 1.5629417706828425e-05,
"loss": 0.7415,
"step": 279
},
{
"epoch": 0.99,
"learning_rate": 1.5597595070732764e-05,
"loss": 0.7337,
"step": 280
},
{
"epoch": 1.0,
"learning_rate": 1.5565689667758745e-05,
"loss": 0.6972,
"step": 281
},
{
"epoch": 1.0,
"learning_rate": 1.5533701969664422e-05,
"loss": 0.5814,
"step": 282
},
{
"epoch": 1.01,
"learning_rate": 1.550163244942469e-05,
"loss": 0.6363,
"step": 283
},
{
"epoch": 1.01,
"learning_rate": 1.5469481581224274e-05,
"loss": 0.5583,
"step": 284
},
{
"epoch": 1.01,
"learning_rate": 1.5437249840450714e-05,
"loss": 0.5915,
"step": 285
},
{
"epoch": 1.02,
"learning_rate": 1.5404937703687363e-05,
"loss": 0.6376,
"step": 286
},
{
"epoch": 1.02,
"learning_rate": 1.5372545648706307e-05,
"loss": 0.5822,
"step": 287
},
{
"epoch": 1.02,
"learning_rate": 1.5340074154461318e-05,
"loss": 0.6281,
"step": 288
},
{
"epoch": 1.03,
"learning_rate": 1.530752370108077e-05,
"loss": 0.6103,
"step": 289
},
{
"epoch": 1.03,
"learning_rate": 1.5274894769860536e-05,
"loss": 0.5642,
"step": 290
},
{
"epoch": 1.03,
"learning_rate": 1.524218784325688e-05,
"loss": 0.6448,
"step": 291
},
{
"epoch": 1.04,
"learning_rate": 1.5209403404879305e-05,
"loss": 0.6617,
"step": 292
},
{
"epoch": 1.04,
"learning_rate": 1.517654193948343e-05,
"loss": 0.6332,
"step": 293
},
{
"epoch": 1.04,
"learning_rate": 1.5143603932963794e-05,
"loss": 0.6065,
"step": 294
},
{
"epoch": 1.05,
"learning_rate": 1.5110589872346699e-05,
"loss": 0.6364,
"step": 295
},
{
"epoch": 1.05,
"learning_rate": 1.5077500245782979e-05,
"loss": 0.6182,
"step": 296
},
{
"epoch": 1.06,
"learning_rate": 1.5044335542540801e-05,
"loss": 0.7047,
"step": 297
},
{
"epoch": 1.06,
"learning_rate": 1.501109625299844e-05,
"loss": 0.6737,
"step": 298
},
{
"epoch": 1.06,
"learning_rate": 1.4977782868636999e-05,
"loss": 0.6135,
"step": 299
},
{
"epoch": 1.07,
"learning_rate": 1.4944395882033167e-05,
"loss": 0.6174,
"step": 300
},
{
"epoch": 1.07,
"learning_rate": 1.491093578685192e-05,
"loss": 0.6349,
"step": 301
},
{
"epoch": 1.07,
"learning_rate": 1.4877403077839234e-05,
"loss": 0.6385,
"step": 302
},
{
"epoch": 1.08,
"learning_rate": 1.4843798250814763e-05,
"loss": 0.6264,
"step": 303
},
{
"epoch": 1.08,
"learning_rate": 1.4810121802664513e-05,
"loss": 0.5842,
"step": 304
},
{
"epoch": 1.08,
"learning_rate": 1.4776374231333477e-05,
"loss": 0.6381,
"step": 305
},
{
"epoch": 1.09,
"learning_rate": 1.4742556035818299e-05,
"loss": 0.6176,
"step": 306
},
{
"epoch": 1.09,
"learning_rate": 1.4708667716159879e-05,
"loss": 0.6743,
"step": 307
},
{
"epoch": 1.09,
"learning_rate": 1.4674709773435982e-05,
"loss": 0.6324,
"step": 308
},
{
"epoch": 1.1,
"learning_rate": 1.4640682709753832e-05,
"loss": 0.6493,
"step": 309
},
{
"epoch": 1.1,
"learning_rate": 1.4606587028242682e-05,
"loss": 0.6206,
"step": 310
},
{
"epoch": 1.1,
"learning_rate": 1.4572423233046386e-05,
"loss": 0.6144,
"step": 311
},
{
"epoch": 1.11,
"learning_rate": 1.4538191829315928e-05,
"loss": 0.6766,
"step": 312
},
{
"epoch": 1.11,
"learning_rate": 1.4503893323201965e-05,
"loss": 0.6651,
"step": 313
},
{
"epoch": 1.12,
"learning_rate": 1.4469528221847344e-05,
"loss": 0.6113,
"step": 314
},
{
"epoch": 1.12,
"learning_rate": 1.4435097033379597e-05,
"loss": 0.6414,
"step": 315
},
{
"epoch": 1.12,
"learning_rate": 1.4400600266903425e-05,
"loss": 0.6134,
"step": 316
},
{
"epoch": 1.13,
"learning_rate": 1.4366038432493181e-05,
"loss": 0.6048,
"step": 317
},
{
"epoch": 1.13,
"learning_rate": 1.4331412041185321e-05,
"loss": 0.6155,
"step": 318
},
{
"epoch": 1.13,
"learning_rate": 1.4296721604970852e-05,
"loss": 0.6163,
"step": 319
},
{
"epoch": 1.14,
"learning_rate": 1.4261967636787748e-05,
"loss": 0.5873,
"step": 320
},
{
"epoch": 1.14,
"learning_rate": 1.4227150650513389e-05,
"loss": 0.6291,
"step": 321
},
{
"epoch": 1.14,
"learning_rate": 1.4192271160956943e-05,
"loss": 0.6368,
"step": 322
},
{
"epoch": 1.15,
"learning_rate": 1.4157329683851759e-05,
"loss": 0.6209,
"step": 323
},
{
"epoch": 1.15,
"learning_rate": 1.4122326735847748e-05,
"loss": 0.6361,
"step": 324
},
{
"epoch": 1.15,
"learning_rate": 1.4087262834503742e-05,
"loss": 0.6481,
"step": 325
},
{
"epoch": 1.16,
"learning_rate": 1.4052138498279828e-05,
"loss": 0.6306,
"step": 326
},
{
"epoch": 1.16,
"learning_rate": 1.4016954246529697e-05,
"loss": 0.6456,
"step": 327
},
{
"epoch": 1.17,
"learning_rate": 1.3981710599492963e-05,
"loss": 0.6473,
"step": 328
},
{
"epoch": 1.17,
"learning_rate": 1.3946408078287463e-05,
"loss": 0.6307,
"step": 329
},
{
"epoch": 1.17,
"learning_rate": 1.391104720490156e-05,
"loss": 0.6944,
"step": 330
},
{
"epoch": 1.18,
"learning_rate": 1.3875628502186422e-05,
"loss": 0.6819,
"step": 331
},
{
"epoch": 1.18,
"learning_rate": 1.3840152493848284e-05,
"loss": 0.5598,
"step": 332
},
{
"epoch": 1.18,
"learning_rate": 1.3804619704440714e-05,
"loss": 0.6306,
"step": 333
},
{
"epoch": 1.19,
"learning_rate": 1.3769030659356855e-05,
"loss": 0.6204,
"step": 334
},
{
"epoch": 1.19,
"learning_rate": 1.3733385884821649e-05,
"loss": 0.5954,
"step": 335
},
{
"epoch": 1.19,
"learning_rate": 1.3697685907884074e-05,
"loss": 0.6174,
"step": 336
},
{
"epoch": 1.2,
"learning_rate": 1.3661931256409326e-05,
"loss": 0.5704,
"step": 337
},
{
"epoch": 1.2,
"learning_rate": 1.3626122459071034e-05,
"loss": 0.6415,
"step": 338
},
{
"epoch": 1.2,
"learning_rate": 1.3590260045343434e-05,
"loss": 0.6518,
"step": 339
},
{
"epoch": 1.21,
"learning_rate": 1.3554344545493537e-05,
"loss": 0.6857,
"step": 340
},
{
"epoch": 1.21,
"learning_rate": 1.3518376490573306e-05,
"loss": 0.6811,
"step": 341
},
{
"epoch": 1.21,
"learning_rate": 1.3482356412411781e-05,
"loss": 0.6192,
"step": 342
},
{
"epoch": 1.22,
"learning_rate": 1.3446284843607227e-05,
"loss": 0.6341,
"step": 343
},
{
"epoch": 1.22,
"learning_rate": 1.3410162317519257e-05,
"loss": 0.6905,
"step": 344
},
{
"epoch": 1.23,
"learning_rate": 1.337398936826095e-05,
"loss": 0.6714,
"step": 345
},
{
"epoch": 1.23,
"learning_rate": 1.3337766530690943e-05,
"loss": 0.646,
"step": 346
},
{
"epoch": 1.23,
"learning_rate": 1.3301494340405536e-05,
"loss": 0.6118,
"step": 347
},
{
"epoch": 1.24,
"learning_rate": 1.3265173333730765e-05,
"loss": 0.6373,
"step": 348
},
{
"epoch": 1.24,
"learning_rate": 1.3228804047714462e-05,
"loss": 0.6124,
"step": 349
},
{
"epoch": 1.24,
"learning_rate": 1.319238702011834e-05,
"loss": 0.5973,
"step": 350
},
{
"epoch": 1.25,
"learning_rate": 1.3155922789410017e-05,
"loss": 0.6389,
"step": 351
},
{
"epoch": 1.25,
"learning_rate": 1.3119411894755063e-05,
"loss": 0.6067,
"step": 352
},
{
"epoch": 1.25,
"learning_rate": 1.308285487600903e-05,
"loss": 0.6272,
"step": 353
},
{
"epoch": 1.26,
"learning_rate": 1.3046252273709467e-05,
"loss": 0.6186,
"step": 354
},
{
"epoch": 1.26,
"learning_rate": 1.3009604629067933e-05,
"loss": 0.649,
"step": 355
},
{
"epoch": 1.26,
"learning_rate": 1.2972912483961982e-05,
"loss": 0.5943,
"step": 356
},
{
"epoch": 1.27,
"learning_rate": 1.2936176380927163e-05,
"loss": 0.6066,
"step": 357
},
{
"epoch": 1.27,
"learning_rate": 1.2899396863148994e-05,
"loss": 0.6811,
"step": 358
},
{
"epoch": 1.28,
"learning_rate": 1.286257447445493e-05,
"loss": 0.6703,
"step": 359
},
{
"epoch": 1.28,
"learning_rate": 1.2825709759306317e-05,
"loss": 0.6225,
"step": 360
},
{
"epoch": 1.28,
"learning_rate": 1.278880326279035e-05,
"loss": 0.6217,
"step": 361
},
{
"epoch": 1.29,
"learning_rate": 1.2751855530612012e-05,
"loss": 0.628,
"step": 362
},
{
"epoch": 1.29,
"learning_rate": 1.2714867109086e-05,
"loss": 0.675,
"step": 363
},
{
"epoch": 1.29,
"learning_rate": 1.2677838545128646e-05,
"loss": 0.5826,
"step": 364
},
{
"epoch": 1.3,
"learning_rate": 1.2640770386249842e-05,
"loss": 0.6209,
"step": 365
},
{
"epoch": 1.3,
"learning_rate": 1.260366318054493e-05,
"loss": 0.6111,
"step": 366
},
{
"epoch": 1.3,
"learning_rate": 1.2566517476686606e-05,
"loss": 0.6188,
"step": 367
},
{
"epoch": 1.31,
"learning_rate": 1.2529333823916807e-05,
"loss": 0.6578,
"step": 368
},
{
"epoch": 1.31,
"learning_rate": 1.249211277203859e-05,
"loss": 0.6086,
"step": 369
},
{
"epoch": 1.31,
"learning_rate": 1.2454854871407993e-05,
"loss": 0.623,
"step": 370
},
{
"epoch": 1.32,
"learning_rate": 1.2417560672925913e-05,
"loss": 0.6414,
"step": 371
},
{
"epoch": 1.32,
"learning_rate": 1.2380230728029947e-05,
"loss": 0.6053,
"step": 372
},
{
"epoch": 1.33,
"learning_rate": 1.2342865588686251e-05,
"loss": 0.6422,
"step": 373
},
{
"epoch": 1.33,
"learning_rate": 1.2305465807381363e-05,
"loss": 0.6282,
"step": 374
},
{
"epoch": 1.33,
"learning_rate": 1.2268031937114044e-05,
"loss": 0.6318,
"step": 375
},
{
"epoch": 1.34,
"learning_rate": 1.2230564531387108e-05,
"loss": 0.637,
"step": 376
},
{
"epoch": 1.34,
"learning_rate": 1.2193064144199218e-05,
"loss": 0.5896,
"step": 377
},
{
"epoch": 1.34,
"learning_rate": 1.2155531330036712e-05,
"loss": 0.599,
"step": 378
},
{
"epoch": 1.35,
"learning_rate": 1.2117966643865398e-05,
"loss": 0.6274,
"step": 379
},
{
"epoch": 1.35,
"learning_rate": 1.2080370641122345e-05,
"loss": 0.6027,
"step": 380
},
{
"epoch": 1.35,
"learning_rate": 1.204274387770768e-05,
"loss": 0.6147,
"step": 381
},
{
"epoch": 1.36,
"learning_rate": 1.2005086909976351e-05,
"loss": 0.605,
"step": 382
},
{
"epoch": 1.36,
"learning_rate": 1.196740029472992e-05,
"loss": 0.6898,
"step": 383
},
{
"epoch": 1.36,
"learning_rate": 1.1929684589208325e-05,
"loss": 0.5873,
"step": 384
},
{
"epoch": 1.37,
"learning_rate": 1.1891940351081626e-05,
"loss": 0.6479,
"step": 385
},
{
"epoch": 1.37,
"learning_rate": 1.1854168138441775e-05,
"loss": 0.5821,
"step": 386
},
{
"epoch": 1.37,
"learning_rate": 1.1816368509794365e-05,
"loss": 0.6028,
"step": 387
},
{
"epoch": 1.38,
"learning_rate": 1.1778542024050361e-05,
"loss": 0.616,
"step": 388
},
{
"epoch": 1.38,
"learning_rate": 1.1740689240517837e-05,
"loss": 0.5809,
"step": 389
},
{
"epoch": 1.39,
"learning_rate": 1.1702810718893722e-05,
"loss": 0.59,
"step": 390
},
{
"epoch": 1.39,
"learning_rate": 1.1664907019255503e-05,
"loss": 0.6246,
"step": 391
},
{
"epoch": 1.39,
"learning_rate": 1.1626978702052949e-05,
"loss": 0.6311,
"step": 392
},
{
"epoch": 1.4,
"learning_rate": 1.158902632809984e-05,
"loss": 0.6427,
"step": 393
},
{
"epoch": 1.4,
"learning_rate": 1.1551050458565659e-05,
"loss": 0.6421,
"step": 394
},
{
"epoch": 1.4,
"learning_rate": 1.1513051654967287e-05,
"loss": 0.645,
"step": 395
},
{
"epoch": 1.41,
"learning_rate": 1.1475030479160724e-05,
"loss": 0.6926,
"step": 396
},
{
"epoch": 1.41,
"learning_rate": 1.1436987493332768e-05,
"loss": 0.6395,
"step": 397
},
{
"epoch": 1.41,
"learning_rate": 1.1398923259992697e-05,
"loss": 0.6447,
"step": 398
},
{
"epoch": 1.42,
"learning_rate": 1.1360838341963964e-05,
"loss": 0.6499,
"step": 399
},
{
"epoch": 1.42,
"learning_rate": 1.1322733302375864e-05,
"loss": 0.658,
"step": 400
},
{
"epoch": 1.42,
"learning_rate": 1.1284608704655215e-05,
"loss": 0.6092,
"step": 401
},
{
"epoch": 1.43,
"learning_rate": 1.124646511251803e-05,
"loss": 0.6307,
"step": 402
},
{
"epoch": 1.43,
"learning_rate": 1.1208303089961161e-05,
"loss": 0.6793,
"step": 403
},
{
"epoch": 1.44,
"learning_rate": 1.1170123201253986e-05,
"loss": 0.6144,
"step": 404
},
{
"epoch": 1.44,
"learning_rate": 1.113192601093006e-05,
"loss": 0.6156,
"step": 405
},
{
"epoch": 1.44,
"learning_rate": 1.1093712083778748e-05,
"loss": 0.5947,
"step": 406
},
{
"epoch": 1.45,
"learning_rate": 1.1055481984836894e-05,
"loss": 0.6231,
"step": 407
},
{
"epoch": 1.45,
"learning_rate": 1.1017236279380467e-05,
"loss": 0.6423,
"step": 408
},
{
"epoch": 1.45,
"learning_rate": 1.0978975532916189e-05,
"loss": 0.663,
"step": 409
},
{
"epoch": 1.46,
"learning_rate": 1.0940700311173184e-05,
"loss": 0.7042,
"step": 410
},
{
"epoch": 1.46,
"learning_rate": 1.0902411180094608e-05,
"loss": 0.6465,
"step": 411
},
{
"epoch": 1.46,
"learning_rate": 1.0864108705829282e-05,
"loss": 0.6079,
"step": 412
},
{
"epoch": 1.47,
"learning_rate": 1.0825793454723325e-05,
"loss": 0.5868,
"step": 413
},
{
"epoch": 1.47,
"learning_rate": 1.0787465993311767e-05,
"loss": 0.6083,
"step": 414
},
{
"epoch": 1.47,
"learning_rate": 1.0749126888310197e-05,
"loss": 0.6063,
"step": 415
},
{
"epoch": 1.48,
"learning_rate": 1.071077670660635e-05,
"loss": 0.6424,
"step": 416
},
{
"epoch": 1.48,
"learning_rate": 1.0672416015251757e-05,
"loss": 0.6122,
"step": 417
},
{
"epoch": 1.48,
"learning_rate": 1.0634045381453337e-05,
"loss": 0.5832,
"step": 418
},
{
"epoch": 1.49,
"learning_rate": 1.0595665372565028e-05,
"loss": 0.6255,
"step": 419
},
{
"epoch": 1.49,
"learning_rate": 1.0557276556079379e-05,
"loss": 0.5771,
"step": 420
},
{
"epoch": 1.5,
"learning_rate": 1.0518879499619182e-05,
"loss": 0.6092,
"step": 421
},
{
"epoch": 1.5,
"learning_rate": 1.0480474770929054e-05,
"loss": 0.6644,
"step": 422
},
{
"epoch": 1.5,
"learning_rate": 1.0442062937867064e-05,
"loss": 0.6304,
"step": 423
},
{
"epoch": 1.51,
"learning_rate": 1.0403644568396323e-05,
"loss": 0.6564,
"step": 424
},
{
"epoch": 1.51,
"learning_rate": 1.0365220230576592e-05,
"loss": 0.5962,
"step": 425
},
{
"epoch": 1.51,
"learning_rate": 1.0326790492555876e-05,
"loss": 0.6719,
"step": 426
},
{
"epoch": 1.52,
"learning_rate": 1.0288355922562035e-05,
"loss": 0.6932,
"step": 427
},
{
"epoch": 1.52,
"learning_rate": 1.024991708889437e-05,
"loss": 0.6437,
"step": 428
},
{
"epoch": 1.52,
"learning_rate": 1.0211474559915234e-05,
"loss": 0.6179,
"step": 429
},
{
"epoch": 1.53,
"learning_rate": 1.0173028904041606e-05,
"loss": 0.6557,
"step": 430
},
{
"epoch": 1.53,
"learning_rate": 1.0134580689736711e-05,
"loss": 0.6466,
"step": 431
},
{
"epoch": 1.53,
"learning_rate": 1.0096130485501598e-05,
"loss": 0.6573,
"step": 432
},
{
"epoch": 1.54,
"learning_rate": 1.005767885986674e-05,
"loss": 0.6503,
"step": 433
},
{
"epoch": 1.54,
"learning_rate": 1.0019226381383634e-05,
"loss": 0.6892,
"step": 434
},
{
"epoch": 1.55,
"learning_rate": 9.98077361861637e-06,
"loss": 0.6621,
"step": 435
},
{
"epoch": 1.55,
"learning_rate": 9.942321140133262e-06,
"loss": 0.5934,
"step": 436
},
{
"epoch": 1.55,
"learning_rate": 9.903869514498404e-06,
"loss": 0.5825,
"step": 437
},
{
"epoch": 1.56,
"learning_rate": 9.865419310263292e-06,
"loss": 0.6279,
"step": 438
},
{
"epoch": 1.56,
"learning_rate": 9.826971095958396e-06,
"loss": 0.6281,
"step": 439
},
{
"epoch": 1.56,
"learning_rate": 9.788525440084771e-06,
"loss": 0.6241,
"step": 440
},
{
"epoch": 1.57,
"learning_rate": 9.750082911105634e-06,
"loss": 0.6122,
"step": 441
},
{
"epoch": 1.57,
"learning_rate": 9.711644077437969e-06,
"loss": 0.6818,
"step": 442
},
{
"epoch": 1.57,
"learning_rate": 9.67320950744413e-06,
"loss": 0.6387,
"step": 443
},
{
"epoch": 1.58,
"learning_rate": 9.634779769423412e-06,
"loss": 0.6197,
"step": 444
},
{
"epoch": 1.58,
"learning_rate": 9.59635543160368e-06,
"loss": 0.6089,
"step": 445
},
{
"epoch": 1.58,
"learning_rate": 9.557937062132938e-06,
"loss": 0.6861,
"step": 446
},
{
"epoch": 1.59,
"learning_rate": 9.51952522907095e-06,
"loss": 0.6474,
"step": 447
},
{
"epoch": 1.59,
"learning_rate": 9.48112050038082e-06,
"loss": 0.6228,
"step": 448
},
{
"epoch": 1.6,
"learning_rate": 9.442723443920623e-06,
"loss": 0.6209,
"step": 449
},
{
"epoch": 1.6,
"learning_rate": 9.404334627434974e-06,
"loss": 0.6688,
"step": 450
},
{
"epoch": 1.6,
"learning_rate": 9.365954618546666e-06,
"loss": 0.6978,
"step": 451
},
{
"epoch": 1.61,
"learning_rate": 9.327583984748248e-06,
"loss": 0.6163,
"step": 452
},
{
"epoch": 1.61,
"learning_rate": 9.289223293393651e-06,
"loss": 0.6188,
"step": 453
},
{
"epoch": 1.61,
"learning_rate": 9.250873111689808e-06,
"loss": 0.6809,
"step": 454
},
{
"epoch": 1.62,
"learning_rate": 9.212534006688235e-06,
"loss": 0.6553,
"step": 455
},
{
"epoch": 1.62,
"learning_rate": 9.174206545276678e-06,
"loss": 0.6218,
"step": 456
},
{
"epoch": 1.62,
"learning_rate": 9.135891294170718e-06,
"loss": 0.5796,
"step": 457
},
{
"epoch": 1.63,
"learning_rate": 9.097588819905394e-06,
"loss": 0.6091,
"step": 458
},
{
"epoch": 1.63,
"learning_rate": 9.059299688826815e-06,
"loss": 0.5941,
"step": 459
},
{
"epoch": 1.63,
"learning_rate": 9.021024467083813e-06,
"loss": 0.625,
"step": 460
},
{
"epoch": 1.64,
"learning_rate": 8.982763720619533e-06,
"loss": 0.5721,
"step": 461
},
{
"epoch": 1.64,
"learning_rate": 8.944518015163108e-06,
"loss": 0.6055,
"step": 462
},
{
"epoch": 1.64,
"learning_rate": 8.906287916221259e-06,
"loss": 0.6092,
"step": 463
},
{
"epoch": 1.65,
"learning_rate": 8.868073989069942e-06,
"loss": 0.5939,
"step": 464
},
{
"epoch": 1.65,
"learning_rate": 8.829876798746017e-06,
"loss": 0.6245,
"step": 465
},
{
"epoch": 1.66,
"learning_rate": 8.791696910038842e-06,
"loss": 0.6346,
"step": 466
},
{
"epoch": 1.66,
"learning_rate": 8.753534887481975e-06,
"loss": 0.6931,
"step": 467
},
{
"epoch": 1.66,
"learning_rate": 8.715391295344785e-06,
"loss": 0.6456,
"step": 468
},
{
"epoch": 1.67,
"learning_rate": 8.677266697624138e-06,
"loss": 0.6709,
"step": 469
},
{
"epoch": 1.67,
"learning_rate": 8.639161658036038e-06,
"loss": 0.6142,
"step": 470
},
{
"epoch": 1.67,
"learning_rate": 8.601076740007306e-06,
"loss": 0.5925,
"step": 471
},
{
"epoch": 1.68,
"learning_rate": 8.563012506667234e-06,
"loss": 0.6097,
"step": 472
},
{
"epoch": 1.68,
"learning_rate": 8.52496952083928e-06,
"loss": 0.6492,
"step": 473
},
{
"epoch": 1.68,
"learning_rate": 8.48694834503272e-06,
"loss": 0.6288,
"step": 474
},
{
"epoch": 1.69,
"learning_rate": 8.448949541434346e-06,
"loss": 0.6571,
"step": 475
},
{
"epoch": 1.69,
"learning_rate": 8.410973671900162e-06,
"loss": 0.6689,
"step": 476
},
{
"epoch": 1.69,
"learning_rate": 8.373021297947053e-06,
"loss": 0.6363,
"step": 477
},
{
"epoch": 1.7,
"learning_rate": 8.335092980744502e-06,
"loss": 0.5965,
"step": 478
},
{
"epoch": 1.7,
"learning_rate": 8.297189281106278e-06,
"loss": 0.6008,
"step": 479
},
{
"epoch": 1.71,
"learning_rate": 8.259310759482165e-06,
"loss": 0.6608,
"step": 480
},
{
"epoch": 1.71,
"learning_rate": 8.22145797594964e-06,
"loss": 0.6149,
"step": 481
},
{
"epoch": 1.71,
"learning_rate": 8.183631490205636e-06,
"loss": 0.627,
"step": 482
},
{
"epoch": 1.72,
"learning_rate": 8.145831861558225e-06,
"loss": 0.6337,
"step": 483
},
{
"epoch": 1.72,
"learning_rate": 8.108059648918377e-06,
"loss": 0.6506,
"step": 484
},
{
"epoch": 1.72,
"learning_rate": 8.07031541079168e-06,
"loss": 0.6457,
"step": 485
},
{
"epoch": 1.73,
"learning_rate": 8.032599705270082e-06,
"loss": 0.6026,
"step": 486
},
{
"epoch": 1.73,
"learning_rate": 7.994913090023652e-06,
"loss": 0.5755,
"step": 487
},
{
"epoch": 1.73,
"learning_rate": 7.957256122292322e-06,
"loss": 0.6392,
"step": 488
},
{
"epoch": 1.74,
"learning_rate": 7.919629358877657e-06,
"loss": 0.6551,
"step": 489
},
{
"epoch": 1.74,
"learning_rate": 7.882033356134603e-06,
"loss": 0.6174,
"step": 490
},
{
"epoch": 1.74,
"learning_rate": 7.84446866996329e-06,
"loss": 0.5918,
"step": 491
},
{
"epoch": 1.75,
"learning_rate": 7.806935855800782e-06,
"loss": 0.6463,
"step": 492
},
{
"epoch": 1.75,
"learning_rate": 7.769435468612895e-06,
"loss": 0.637,
"step": 493
},
{
"epoch": 1.75,
"learning_rate": 7.731968062885956e-06,
"loss": 0.622,
"step": 494
},
{
"epoch": 1.76,
"learning_rate": 7.694534192618642e-06,
"loss": 0.6518,
"step": 495
},
{
"epoch": 1.76,
"learning_rate": 7.657134411313754e-06,
"loss": 0.6543,
"step": 496
},
{
"epoch": 1.77,
"learning_rate": 7.619769271970056e-06,
"loss": 0.646,
"step": 497
},
{
"epoch": 1.77,
"learning_rate": 7.5824393270740905e-06,
"loss": 0.6382,
"step": 498
},
{
"epoch": 1.77,
"learning_rate": 7.545145128592009e-06,
"loss": 0.6295,
"step": 499
},
{
"epoch": 1.78,
"learning_rate": 7.507887227961415e-06,
"loss": 0.6375,
"step": 500
},
{
"epoch": 1.78,
"learning_rate": 7.470666176083193e-06,
"loss": 0.6282,
"step": 501
},
{
"epoch": 1.78,
"learning_rate": 7.433482523313396e-06,
"loss": 0.6485,
"step": 502
},
{
"epoch": 1.79,
"learning_rate": 7.3963368194550715e-06,
"loss": 0.6366,
"step": 503
},
{
"epoch": 1.79,
"learning_rate": 7.359229613750161e-06,
"loss": 0.6574,
"step": 504
},
{
"epoch": 1.79,
"learning_rate": 7.322161454871356e-06,
"loss": 0.6499,
"step": 505
},
{
"epoch": 1.8,
"learning_rate": 7.285132890914003e-06,
"loss": 0.5726,
"step": 506
},
{
"epoch": 1.8,
"learning_rate": 7.248144469387992e-06,
"loss": 0.6509,
"step": 507
},
{
"epoch": 1.8,
"learning_rate": 7.211196737209653e-06,
"loss": 0.6338,
"step": 508
},
{
"epoch": 1.81,
"learning_rate": 7.174290240693689e-06,
"loss": 0.6482,
"step": 509
},
{
"epoch": 1.81,
"learning_rate": 7.137425525545074e-06,
"loss": 0.6522,
"step": 510
},
{
"epoch": 1.82,
"learning_rate": 7.1006031368510095e-06,
"loss": 0.6073,
"step": 511
},
{
"epoch": 1.82,
"learning_rate": 7.063823619072838e-06,
"loss": 0.6484,
"step": 512
},
{
"epoch": 1.82,
"learning_rate": 7.027087516038022e-06,
"loss": 0.6569,
"step": 513
},
{
"epoch": 1.83,
"learning_rate": 6.990395370932068e-06,
"loss": 0.5603,
"step": 514
},
{
"epoch": 1.83,
"learning_rate": 6.953747726290535e-06,
"loss": 0.6142,
"step": 515
},
{
"epoch": 1.83,
"learning_rate": 6.917145123990974e-06,
"loss": 0.5961,
"step": 516
},
{
"epoch": 1.84,
"learning_rate": 6.88058810524494e-06,
"loss": 0.6394,
"step": 517
},
{
"epoch": 1.84,
"learning_rate": 6.844077210589987e-06,
"loss": 0.656,
"step": 518
},
{
"epoch": 1.84,
"learning_rate": 6.807612979881662e-06,
"loss": 0.6042,
"step": 519
},
{
"epoch": 1.85,
"learning_rate": 6.771195952285541e-06,
"loss": 0.6229,
"step": 520
},
{
"epoch": 1.85,
"learning_rate": 6.734826666269238e-06,
"loss": 0.6151,
"step": 521
},
{
"epoch": 1.85,
"learning_rate": 6.698505659594466e-06,
"loss": 0.6084,
"step": 522
},
{
"epoch": 1.86,
"learning_rate": 6.662233469309058e-06,
"loss": 0.6205,
"step": 523
},
{
"epoch": 1.86,
"learning_rate": 6.626010631739054e-06,
"loss": 0.6717,
"step": 524
},
{
"epoch": 1.87,
"learning_rate": 6.589837682480744e-06,
"loss": 0.6234,
"step": 525
},
{
"epoch": 1.87,
"learning_rate": 6.553715156392776e-06,
"loss": 0.7084,
"step": 526
},
{
"epoch": 1.87,
"learning_rate": 6.51764358758822e-06,
"loss": 0.6644,
"step": 527
},
{
"epoch": 1.88,
"learning_rate": 6.481623509426697e-06,
"loss": 0.7086,
"step": 528
},
{
"epoch": 1.88,
"learning_rate": 6.445655454506465e-06,
"loss": 0.6419,
"step": 529
},
{
"epoch": 1.88,
"learning_rate": 6.4097399546565705e-06,
"loss": 0.6435,
"step": 530
},
{
"epoch": 1.89,
"learning_rate": 6.373877540928972e-06,
"loss": 0.7082,
"step": 531
},
{
"epoch": 1.89,
"learning_rate": 6.338068743590676e-06,
"loss": 0.6517,
"step": 532
},
{
"epoch": 1.89,
"learning_rate": 6.30231409211593e-06,
"loss": 0.6318,
"step": 533
},
{
"epoch": 1.9,
"learning_rate": 6.266614115178351e-06,
"loss": 0.6166,
"step": 534
},
{
"epoch": 1.9,
"learning_rate": 6.230969340643149e-06,
"loss": 0.6305,
"step": 535
},
{
"epoch": 1.9,
"learning_rate": 6.195380295559288e-06,
"loss": 0.6094,
"step": 536
},
{
"epoch": 1.91,
"learning_rate": 6.15984750615172e-06,
"loss": 0.6715,
"step": 537
},
{
"epoch": 1.91,
"learning_rate": 6.1243714978135815e-06,
"loss": 0.6975,
"step": 538
},
{
"epoch": 1.91,
"learning_rate": 6.088952795098442e-06,
"loss": 0.6815,
"step": 539
},
{
"epoch": 1.92,
"learning_rate": 6.053591921712542e-06,
"loss": 0.6232,
"step": 540
},
{
"epoch": 1.92,
"learning_rate": 6.01828940050704e-06,
"loss": 0.5978,
"step": 541
},
{
"epoch": 1.93,
"learning_rate": 5.983045753470308e-06,
"loss": 0.6038,
"step": 542
},
{
"epoch": 1.93,
"learning_rate": 5.947861501720176e-06,
"loss": 0.6556,
"step": 543
},
{
"epoch": 1.93,
"learning_rate": 5.9127371654962615e-06,
"loss": 0.5882,
"step": 544
},
{
"epoch": 1.94,
"learning_rate": 5.877673264152251e-06,
"loss": 0.6092,
"step": 545
},
{
"epoch": 1.94,
"learning_rate": 5.842670316148245e-06,
"loss": 0.564,
"step": 546
},
{
"epoch": 1.94,
"learning_rate": 5.807728839043061e-06,
"loss": 0.6517,
"step": 547
},
{
"epoch": 1.95,
"learning_rate": 5.772849349486613e-06,
"loss": 0.6329,
"step": 548
},
{
"epoch": 1.95,
"learning_rate": 5.738032363212258e-06,
"loss": 0.6253,
"step": 549
},
{
"epoch": 1.95,
"learning_rate": 5.70327839502915e-06,
"loss": 0.6291,
"step": 550
},
{
"epoch": 1.96,
"learning_rate": 5.668587958814682e-06,
"loss": 0.6936,
"step": 551
},
{
"epoch": 1.96,
"learning_rate": 5.633961567506819e-06,
"loss": 0.5853,
"step": 552
},
{
"epoch": 1.96,
"learning_rate": 5.59939973309658e-06,
"loss": 0.5397,
"step": 553
},
{
"epoch": 1.97,
"learning_rate": 5.564902966620408e-06,
"loss": 0.6212,
"step": 554
},
{
"epoch": 1.97,
"learning_rate": 5.530471778152659e-06,
"loss": 0.6353,
"step": 555
},
{
"epoch": 1.98,
"learning_rate": 5.496106676798036e-06,
"loss": 0.6575,
"step": 556
},
{
"epoch": 1.98,
"learning_rate": 5.461808170684075e-06,
"loss": 0.6437,
"step": 557
},
{
"epoch": 1.98,
"learning_rate": 5.427576766953615e-06,
"loss": 0.7071,
"step": 558
},
{
"epoch": 1.99,
"learning_rate": 5.3934129717573165e-06,
"loss": 0.6634,
"step": 559
},
{
"epoch": 1.99,
"learning_rate": 5.359317290246172e-06,
"loss": 0.6206,
"step": 560
},
{
"epoch": 1.99,
"learning_rate": 5.325290226564017e-06,
"loss": 0.6476,
"step": 561
},
{
"epoch": 2.0,
"learning_rate": 5.2913322838401245e-06,
"loss": 0.6304,
"step": 562
},
{
"epoch": 2.0,
"learning_rate": 5.257443964181701e-06,
"loss": 0.5745,
"step": 563
},
{
"epoch": 2.0,
"learning_rate": 5.223625768666528e-06,
"loss": 0.5281,
"step": 564
},
{
"epoch": 2.01,
"learning_rate": 5.189878197335492e-06,
"loss": 0.5076,
"step": 565
},
{
"epoch": 2.01,
"learning_rate": 5.156201749185239e-06,
"loss": 0.5021,
"step": 566
},
{
"epoch": 2.01,
"learning_rate": 5.122596922160769e-06,
"loss": 0.5413,
"step": 567
},
{
"epoch": 2.02,
"learning_rate": 5.089064213148082e-06,
"loss": 0.5327,
"step": 568
},
{
"epoch": 2.02,
"learning_rate": 5.0556041179668355e-06,
"loss": 0.5448,
"step": 569
},
{
"epoch": 2.02,
"learning_rate": 5.022217131363001e-06,
"loss": 0.5079,
"step": 570
},
{
"epoch": 2.03,
"learning_rate": 4.9889037470015636e-06,
"loss": 0.4937,
"step": 571
},
{
"epoch": 2.03,
"learning_rate": 4.955664457459197e-06,
"loss": 0.5513,
"step": 572
},
{
"epoch": 2.04,
"learning_rate": 4.922499754217026e-06,
"loss": 0.5633,
"step": 573
},
{
"epoch": 2.04,
"learning_rate": 4.889410127653306e-06,
"loss": 0.5807,
"step": 574
},
{
"epoch": 2.04,
"learning_rate": 4.856396067036207e-06,
"loss": 0.533,
"step": 575
},
{
"epoch": 2.05,
"learning_rate": 4.8234580605165744e-06,
"loss": 0.5581,
"step": 576
},
{
"epoch": 2.05,
"learning_rate": 4.790596595120699e-06,
"loss": 0.5135,
"step": 577
},
{
"epoch": 2.05,
"learning_rate": 4.757812156743125e-06,
"loss": 0.6036,
"step": 578
},
{
"epoch": 2.06,
"learning_rate": 4.725105230139465e-06,
"loss": 0.5708,
"step": 579
},
{
"epoch": 2.06,
"learning_rate": 4.692476298919232e-06,
"loss": 0.5459,
"step": 580
},
{
"epoch": 2.06,
"learning_rate": 4.659925845538683e-06,
"loss": 0.5095,
"step": 581
},
{
"epoch": 2.07,
"learning_rate": 4.627454351293698e-06,
"loss": 0.5603,
"step": 582
},
{
"epoch": 2.07,
"learning_rate": 4.595062296312637e-06,
"loss": 0.5152,
"step": 583
},
{
"epoch": 2.07,
"learning_rate": 4.56275015954929e-06,
"loss": 0.5641,
"step": 584
},
{
"epoch": 2.08,
"learning_rate": 4.530518418775734e-06,
"loss": 0.5012,
"step": 585
},
{
"epoch": 2.08,
"learning_rate": 4.498367550575314e-06,
"loss": 0.5293,
"step": 586
},
{
"epoch": 2.09,
"learning_rate": 4.46629803033558e-06,
"loss": 0.527,
"step": 587
},
{
"epoch": 2.09,
"learning_rate": 4.434310332241258e-06,
"loss": 0.5404,
"step": 588
},
{
"epoch": 2.09,
"learning_rate": 4.4024049292672355e-06,
"loss": 0.5581,
"step": 589
},
{
"epoch": 2.1,
"learning_rate": 4.370582293171578e-06,
"loss": 0.5316,
"step": 590
},
{
"epoch": 2.1,
"learning_rate": 4.338842894488544e-06,
"loss": 0.5541,
"step": 591
},
{
"epoch": 2.1,
"learning_rate": 4.3071872025216325e-06,
"loss": 0.5425,
"step": 592
},
{
"epoch": 2.11,
"learning_rate": 4.275615685336646e-06,
"loss": 0.5612,
"step": 593
},
{
"epoch": 2.11,
"learning_rate": 4.244128809754749e-06,
"loss": 0.5563,
"step": 594
},
{
"epoch": 2.11,
"learning_rate": 4.212727041345614e-06,
"loss": 0.5356,
"step": 595
},
{
"epoch": 2.12,
"learning_rate": 4.181410844420473e-06,
"loss": 0.553,
"step": 596
},
{
"epoch": 2.12,
"learning_rate": 4.1501806820253065e-06,
"loss": 0.542,
"step": 597
},
{
"epoch": 2.12,
"learning_rate": 4.119037015933967e-06,
"loss": 0.5211,
"step": 598
},
{
"epoch": 2.13,
"learning_rate": 4.087980306641365e-06,
"loss": 0.5385,
"step": 599
},
{
"epoch": 2.13,
"learning_rate": 4.057011013356648e-06,
"loss": 0.497,
"step": 600
},
{
"epoch": 2.13,
"learning_rate": 4.026129593996422e-06,
"loss": 0.5138,
"step": 601
},
{
"epoch": 2.14,
"learning_rate": 3.995336505177975e-06,
"loss": 0.5388,
"step": 602
},
{
"epoch": 2.14,
"learning_rate": 3.964632202212526e-06,
"loss": 0.5452,
"step": 603
},
{
"epoch": 2.15,
"learning_rate": 3.9340171390984985e-06,
"loss": 0.5281,
"step": 604
},
{
"epoch": 2.15,
"learning_rate": 3.903491768514789e-06,
"loss": 0.5522,
"step": 605
},
{
"epoch": 2.15,
"learning_rate": 3.873056541814098e-06,
"loss": 0.5429,
"step": 606
},
{
"epoch": 2.16,
"learning_rate": 3.842711909016241e-06,
"loss": 0.5531,
"step": 607
},
{
"epoch": 2.16,
"learning_rate": 3.8124583188015017e-06,
"loss": 0.5488,
"step": 608
},
{
"epoch": 2.16,
"learning_rate": 3.782296218503991e-06,
"loss": 0.544,
"step": 609
},
{
"epoch": 2.17,
"learning_rate": 3.752226054105038e-06,
"loss": 0.5703,
"step": 610
},
{
"epoch": 2.17,
"learning_rate": 3.722248270226593e-06,
"loss": 0.5435,
"step": 611
},
{
"epoch": 2.17,
"learning_rate": 3.6923633101246546e-06,
"loss": 0.6346,
"step": 612
},
{
"epoch": 2.18,
"learning_rate": 3.662571615682714e-06,
"loss": 0.5123,
"step": 613
},
{
"epoch": 2.18,
"learning_rate": 3.6328736274052258e-06,
"loss": 0.5025,
"step": 614
},
{
"epoch": 2.18,
"learning_rate": 3.6032697844110896e-06,
"loss": 0.5406,
"step": 615
},
{
"epoch": 2.19,
"learning_rate": 3.5737605244271536e-06,
"loss": 0.4903,
"step": 616
},
{
"epoch": 2.19,
"learning_rate": 3.544346283781752e-06,
"loss": 0.538,
"step": 617
},
{
"epoch": 2.2,
"learning_rate": 3.515027497398251e-06,
"loss": 0.5294,
"step": 618
},
{
"epoch": 2.2,
"learning_rate": 3.4858045987886145e-06,
"loss": 0.4913,
"step": 619
},
{
"epoch": 2.2,
"learning_rate": 3.456678020046992e-06,
"loss": 0.5723,
"step": 620
},
{
"epoch": 2.21,
"learning_rate": 3.4276481918433357e-06,
"loss": 0.5564,
"step": 621
},
{
"epoch": 2.21,
"learning_rate": 3.3987155434170307e-06,
"loss": 0.607,
"step": 622
},
{
"epoch": 2.21,
"learning_rate": 3.369880502570545e-06,
"loss": 0.55,
"step": 623
},
{
"epoch": 2.22,
"learning_rate": 3.3411434956631095e-06,
"loss": 0.5655,
"step": 624
},
{
"epoch": 2.22,
"learning_rate": 3.3125049476044058e-06,
"loss": 0.5687,
"step": 625
},
{
"epoch": 2.22,
"learning_rate": 3.283965281848297e-06,
"loss": 0.5915,
"step": 626
},
{
"epoch": 2.23,
"learning_rate": 3.2555249203865445e-06,
"loss": 0.5709,
"step": 627
},
{
"epoch": 2.23,
"learning_rate": 3.2271842837425917e-06,
"loss": 0.5381,
"step": 628
},
{
"epoch": 2.23,
"learning_rate": 3.198943790965332e-06,
"loss": 0.5297,
"step": 629
},
{
"epoch": 2.24,
"learning_rate": 3.17080385962292e-06,
"loss": 0.5633,
"step": 630
},
{
"epoch": 2.24,
"learning_rate": 3.142764905796589e-06,
"loss": 0.5243,
"step": 631
},
{
"epoch": 2.25,
"learning_rate": 3.114827344074508e-06,
"loss": 0.4969,
"step": 632
},
{
"epoch": 2.25,
"learning_rate": 3.0869915875456446e-06,
"loss": 0.5262,
"step": 633
},
{
"epoch": 2.25,
"learning_rate": 3.0592580477936606e-06,
"loss": 0.5524,
"step": 634
},
{
"epoch": 2.26,
"learning_rate": 3.0316271348908257e-06,
"loss": 0.5172,
"step": 635
},
{
"epoch": 2.26,
"learning_rate": 3.0040992573919504e-06,
"loss": 0.5787,
"step": 636
},
{
"epoch": 2.26,
"learning_rate": 2.976674822328357e-06,
"loss": 0.5171,
"step": 637
},
{
"epoch": 2.27,
"learning_rate": 2.9493542352018367e-06,
"loss": 0.4972,
"step": 638
},
{
"epoch": 2.27,
"learning_rate": 2.9221378999786855e-06,
"loss": 0.5665,
"step": 639
},
{
"epoch": 2.27,
"learning_rate": 2.8950262190837065e-06,
"loss": 0.5995,
"step": 640
},
{
"epoch": 2.28,
"learning_rate": 2.8680195933942724e-06,
"loss": 0.5309,
"step": 641
},
{
"epoch": 2.28,
"learning_rate": 2.84111842223439e-06,
"loss": 0.5315,
"step": 642
},
{
"epoch": 2.28,
"learning_rate": 2.8143231033688023e-06,
"loss": 0.565,
"step": 643
},
{
"epoch": 2.29,
"learning_rate": 2.787634032997105e-06,
"loss": 0.5697,
"step": 644
},
{
"epoch": 2.29,
"learning_rate": 2.7610516057478854e-06,
"loss": 0.5358,
"step": 645
},
{
"epoch": 2.29,
"learning_rate": 2.7345762146728905e-06,
"loss": 0.4985,
"step": 646
},
{
"epoch": 2.3,
"learning_rate": 2.708208251241219e-06,
"loss": 0.5233,
"step": 647
},
{
"epoch": 2.3,
"learning_rate": 2.6819481053335163e-06,
"loss": 0.5437,
"step": 648
},
{
"epoch": 2.31,
"learning_rate": 2.655796165236234e-06,
"loss": 0.5677,
"step": 649
},
{
"epoch": 2.31,
"learning_rate": 2.62975281763587e-06,
"loss": 0.548,
"step": 650
},
{
"epoch": 2.31,
"learning_rate": 2.6038184476132612e-06,
"loss": 0.5119,
"step": 651
},
{
"epoch": 2.32,
"learning_rate": 2.5779934386378826e-06,
"loss": 0.5354,
"step": 652
},
{
"epoch": 2.32,
"learning_rate": 2.5522781725621814e-06,
"loss": 0.5616,
"step": 653
},
{
"epoch": 2.32,
"learning_rate": 2.5266730296159312e-06,
"loss": 0.518,
"step": 654
},
{
"epoch": 2.33,
"learning_rate": 2.5011783884006058e-06,
"loss": 0.5434,
"step": 655
},
{
"epoch": 2.33,
"learning_rate": 2.4757946258837852e-06,
"loss": 0.5455,
"step": 656
},
{
"epoch": 2.33,
"learning_rate": 2.450522117393582e-06,
"loss": 0.5303,
"step": 657
},
{
"epoch": 2.34,
"learning_rate": 2.4253612366130897e-06,
"loss": 0.5388,
"step": 658
},
{
"epoch": 2.34,
"learning_rate": 2.400312355574853e-06,
"loss": 0.5258,
"step": 659
},
{
"epoch": 2.34,
"learning_rate": 2.3753758446553767e-06,
"loss": 0.5007,
"step": 660
},
{
"epoch": 2.35,
"learning_rate": 2.350552072569643e-06,
"loss": 0.5371,
"step": 661
},
{
"epoch": 2.35,
"learning_rate": 2.325841406365661e-06,
"loss": 0.5343,
"step": 662
},
{
"epoch": 2.36,
"learning_rate": 2.3012442114190383e-06,
"loss": 0.494,
"step": 663
},
{
"epoch": 2.36,
"learning_rate": 2.2767608514275817e-06,
"loss": 0.5843,
"step": 664
},
{
"epoch": 2.36,
"learning_rate": 2.252391688405915e-06,
"loss": 0.5289,
"step": 665
},
{
"epoch": 2.37,
"learning_rate": 2.2281370826801297e-06,
"loss": 0.5242,
"step": 666
},
{
"epoch": 2.37,
"learning_rate": 2.2039973928824544e-06,
"loss": 0.5547,
"step": 667
},
{
"epoch": 2.37,
"learning_rate": 2.1799729759459564e-06,
"loss": 0.5133,
"step": 668
},
{
"epoch": 2.38,
"learning_rate": 2.1560641870992615e-06,
"loss": 0.4985,
"step": 669
},
{
"epoch": 2.38,
"learning_rate": 2.1322713798612935e-06,
"loss": 0.5255,
"step": 670
},
{
"epoch": 2.38,
"learning_rate": 2.1085949060360654e-06,
"loss": 0.4796,
"step": 671
},
{
"epoch": 2.39,
"learning_rate": 2.08503511570746e-06,
"loss": 0.5202,
"step": 672
},
{
"epoch": 2.39,
"learning_rate": 2.0615923572340636e-06,
"loss": 0.5375,
"step": 673
},
{
"epoch": 2.39,
"learning_rate": 2.038266977244011e-06,
"loss": 0.5784,
"step": 674
},
{
"epoch": 2.4,
"learning_rate": 2.015059320629862e-06,
"loss": 0.5357,
"step": 675
},
{
"epoch": 2.4,
"learning_rate": 1.991969730543498e-06,
"loss": 0.5635,
"step": 676
},
{
"epoch": 2.4,
"learning_rate": 1.9689985483910556e-06,
"loss": 0.5654,
"step": 677
},
{
"epoch": 2.41,
"learning_rate": 1.9461461138278737e-06,
"loss": 0.5592,
"step": 678
},
{
"epoch": 2.41,
"learning_rate": 1.9234127647534606e-06,
"loss": 0.6038,
"step": 679
},
{
"epoch": 2.42,
"learning_rate": 1.900798837306529e-06,
"loss": 0.5453,
"step": 680
},
{
"epoch": 2.42,
"learning_rate": 1.8783046658599857e-06,
"loss": 0.5101,
"step": 681
},
{
"epoch": 2.42,
"learning_rate": 1.855930583016019e-06,
"loss": 0.5685,
"step": 682
},
{
"epoch": 2.43,
"learning_rate": 1.8336769196011661e-06,
"loss": 0.5513,
"step": 683
},
{
"epoch": 2.43,
"learning_rate": 1.8115440046614242e-06,
"loss": 0.5537,
"step": 684
},
{
"epoch": 2.43,
"learning_rate": 1.789532165457385e-06,
"loss": 0.6071,
"step": 685
},
{
"epoch": 2.44,
"learning_rate": 1.7676417274593981e-06,
"loss": 0.4972,
"step": 686
},
{
"epoch": 2.44,
"learning_rate": 1.7458730143427549e-06,
"loss": 0.5226,
"step": 687
},
{
"epoch": 2.44,
"learning_rate": 1.7242263479829048e-06,
"loss": 0.506,
"step": 688
},
{
"epoch": 2.45,
"learning_rate": 1.7027020484506995e-06,
"loss": 0.5608,
"step": 689
},
{
"epoch": 2.45,
"learning_rate": 1.6813004340076434e-06,
"loss": 0.5794,
"step": 690
},
{
"epoch": 2.45,
"learning_rate": 1.660021821101222e-06,
"loss": 0.561,
"step": 691
},
{
"epoch": 2.46,
"learning_rate": 1.638866524360182e-06,
"loss": 0.6082,
"step": 692
},
{
"epoch": 2.46,
"learning_rate": 1.6178348565899093e-06,
"loss": 0.5447,
"step": 693
},
{
"epoch": 2.47,
"learning_rate": 1.5969271287677901e-06,
"loss": 0.5199,
"step": 694
},
{
"epoch": 2.47,
"learning_rate": 1.5761436500386185e-06,
"loss": 0.4988,
"step": 695
},
{
"epoch": 2.47,
"learning_rate": 1.5554847277100194e-06,
"loss": 0.4973,
"step": 696
},
{
"epoch": 2.48,
"learning_rate": 1.5349506672479098e-06,
"loss": 0.5509,
"step": 697
},
{
"epoch": 2.48,
"learning_rate": 1.5145417722719825e-06,
"loss": 0.5187,
"step": 698
},
{
"epoch": 2.48,
"learning_rate": 1.4942583445512104e-06,
"loss": 0.5464,
"step": 699
},
{
"epoch": 2.49,
"learning_rate": 1.4741006839993943e-06,
"loss": 0.4952,
"step": 700
},
{
"epoch": 2.49,
"learning_rate": 1.454069088670712e-06,
"loss": 0.5215,
"step": 701
},
{
"epoch": 2.49,
"learning_rate": 1.4341638547553405e-06,
"loss": 0.5233,
"step": 702
},
{
"epoch": 2.5,
"learning_rate": 1.4143852765750387e-06,
"loss": 0.5513,
"step": 703
},
{
"epoch": 2.5,
"learning_rate": 1.3947336465788274e-06,
"loss": 0.5559,
"step": 704
},
{
"epoch": 2.5,
"learning_rate": 1.3752092553386465e-06,
"loss": 0.5415,
"step": 705
},
{
"epoch": 2.51,
"learning_rate": 1.3558123915450671e-06,
"loss": 0.5312,
"step": 706
},
{
"epoch": 2.51,
"learning_rate": 1.3365433420030204e-06,
"loss": 0.5694,
"step": 707
},
{
"epoch": 2.52,
"learning_rate": 1.3174023916275559e-06,
"loss": 0.5922,
"step": 708
},
{
"epoch": 2.52,
"learning_rate": 1.2983898234396308e-06,
"loss": 0.5997,
"step": 709
},
{
"epoch": 2.52,
"learning_rate": 1.279505918561923e-06,
"loss": 0.5257,
"step": 710
},
{
"epoch": 2.53,
"learning_rate": 1.260750956214679e-06,
"loss": 0.5492,
"step": 711
},
{
"epoch": 2.53,
"learning_rate": 1.2421252137115702e-06,
"loss": 0.5381,
"step": 712
},
{
"epoch": 2.53,
"learning_rate": 1.2236289664556233e-06,
"loss": 0.5836,
"step": 713
},
{
"epoch": 2.54,
"learning_rate": 1.2052624879351105e-06,
"loss": 0.5713,
"step": 714
},
{
"epoch": 2.54,
"learning_rate": 1.1870260497195329e-06,
"loss": 0.5887,
"step": 715
},
{
"epoch": 2.54,
"learning_rate": 1.1689199214555969e-06,
"loss": 0.569,
"step": 716
},
{
"epoch": 2.55,
"learning_rate": 1.1509443708632228e-06,
"loss": 0.5395,
"step": 717
},
{
"epoch": 2.55,
"learning_rate": 1.1330996637315927e-06,
"loss": 0.5363,
"step": 718
},
{
"epoch": 2.55,
"learning_rate": 1.1153860639152169e-06,
"loss": 0.4822,
"step": 719
},
{
"epoch": 2.56,
"learning_rate": 1.0978038333300334e-06,
"loss": 0.54,
"step": 720
},
{
"epoch": 2.56,
"learning_rate": 1.0803532319495302e-06,
"loss": 0.5507,
"step": 721
},
{
"epoch": 2.56,
"learning_rate": 1.0630345178009183e-06,
"loss": 0.5065,
"step": 722
},
{
"epoch": 2.57,
"learning_rate": 1.045847946961288e-06,
"loss": 0.5828,
"step": 723
},
{
"epoch": 2.57,
"learning_rate": 1.0287937735538566e-06,
"loss": 0.6041,
"step": 724
},
{
"epoch": 2.58,
"learning_rate": 1.011872249744178e-06,
"loss": 0.5151,
"step": 725
},
{
"epoch": 2.58,
"learning_rate": 9.950836257364371e-07,
"loss": 0.5373,
"step": 726
},
{
"epoch": 2.58,
"learning_rate": 9.7842814976974e-07,
"loss": 0.5466,
"step": 727
},
{
"epoch": 2.59,
"learning_rate": 9.619060681144488e-07,
"loss": 0.5748,
"step": 728
},
{
"epoch": 2.59,
"learning_rate": 9.455176250685338e-07,
"loss": 0.5657,
"step": 729
},
{
"epoch": 2.59,
"learning_rate": 9.292630629539667e-07,
"loss": 0.5529,
"step": 730
},
{
"epoch": 2.6,
"learning_rate": 9.131426221131379e-07,
"loss": 0.5578,
"step": 731
},
{
"epoch": 2.6,
"learning_rate": 8.971565409052907e-07,
"loss": 0.5899,
"step": 732
},
{
"epoch": 2.6,
"learning_rate": 8.813050557030223e-07,
"loss": 0.5887,
"step": 733
},
{
"epoch": 2.61,
"learning_rate": 8.655884008887594e-07,
"loss": 0.4961,
"step": 734
},
{
"epoch": 2.61,
"learning_rate": 8.500068088513158e-07,
"loss": 0.5997,
"step": 735
},
{
"epoch": 2.61,
"learning_rate": 8.345605099824405e-07,
"loss": 0.5559,
"step": 736
},
{
"epoch": 2.62,
"learning_rate": 8.192497326734205e-07,
"loss": 0.5868,
"step": 737
},
{
"epoch": 2.62,
"learning_rate": 8.040747033117013e-07,
"loss": 0.5115,
"step": 738
},
{
"epoch": 2.63,
"learning_rate": 7.890356462775372e-07,
"loss": 0.481,
"step": 739
},
{
"epoch": 2.63,
"learning_rate": 7.741327839406753e-07,
"loss": 0.5171,
"step": 740
},
{
"epoch": 2.63,
"learning_rate": 7.593663366570691e-07,
"loss": 0.5463,
"step": 741
},
{
"epoch": 2.64,
"learning_rate": 7.4473652276562e-07,
"loss": 0.5164,
"step": 742
},
{
"epoch": 2.64,
"learning_rate": 7.302435585849399e-07,
"loss": 0.5087,
"step": 743
},
{
"epoch": 2.64,
"learning_rate": 7.158876584101726e-07,
"loss": 0.5187,
"step": 744
},
{
"epoch": 2.65,
"learning_rate": 7.01669034509801e-07,
"loss": 0.5392,
"step": 745
},
{
"epoch": 2.65,
"learning_rate": 6.87587897122528e-07,
"loss": 0.5094,
"step": 746
},
{
"epoch": 2.65,
"learning_rate": 6.736444544541576e-07,
"loss": 0.529,
"step": 747
},
{
"epoch": 2.66,
"learning_rate": 6.598389126745209e-07,
"loss": 0.6182,
"step": 748
},
{
"epoch": 2.66,
"learning_rate": 6.461714759144233e-07,
"loss": 0.5385,
"step": 749
},
{
"epoch": 2.66,
"learning_rate": 6.326423462626296e-07,
"loss": 0.5818,
"step": 750
},
{
"epoch": 2.67,
"learning_rate": 6.192517237628792e-07,
"loss": 0.546,
"step": 751
},
{
"epoch": 2.67,
"learning_rate": 6.05999806410913e-07,
"loss": 0.524,
"step": 752
},
{
"epoch": 2.67,
"learning_rate": 5.928867901515722e-07,
"loss": 0.5173,
"step": 753
},
{
"epoch": 2.68,
"learning_rate": 5.799128688758704e-07,
"loss": 0.5429,
"step": 754
},
{
"epoch": 2.68,
"learning_rate": 5.670782344181547e-07,
"loss": 0.5544,
"step": 755
},
{
"epoch": 2.69,
"learning_rate": 5.543830765532477e-07,
"loss": 0.5547,
"step": 756
},
{
"epoch": 2.69,
"learning_rate": 5.418275829936537e-07,
"loss": 0.572,
"step": 757
},
{
"epoch": 2.69,
"learning_rate": 5.294119393867791e-07,
"loss": 0.5624,
"step": 758
},
{
"epoch": 2.7,
"learning_rate": 5.1713632931219e-07,
"loss": 0.5398,
"step": 759
},
{
"epoch": 2.7,
"learning_rate": 5.05000934278892e-07,
"loss": 0.5059,
"step": 760
},
{
"epoch": 2.7,
"learning_rate": 4.930059337226523e-07,
"loss": 0.5567,
"step": 761
},
{
"epoch": 2.71,
"learning_rate": 4.811515050033466e-07,
"loss": 0.5473,
"step": 762
},
{
"epoch": 2.71,
"learning_rate": 4.6943782340232667e-07,
"loss": 0.5601,
"step": 763
},
{
"epoch": 2.71,
"learning_rate": 4.578650621198477e-07,
"loss": 0.5093,
"step": 764
},
{
"epoch": 2.72,
"learning_rate": 4.4643339227248396e-07,
"loss": 0.5873,
"step": 765
},
{
"epoch": 2.72,
"learning_rate": 4.3514298289062283e-07,
"loss": 0.5174,
"step": 766
},
{
"epoch": 2.72,
"learning_rate": 4.2399400091594154e-07,
"loss": 0.5832,
"step": 767
},
{
"epoch": 2.73,
"learning_rate": 4.1298661119895775e-07,
"loss": 0.5012,
"step": 768
},
{
"epoch": 2.73,
"learning_rate": 4.0212097649658275e-07,
"loss": 0.51,
"step": 769
},
{
"epoch": 2.74,
"learning_rate": 3.913972574697189e-07,
"loss": 0.5684,
"step": 770
},
{
"epoch": 2.74,
"learning_rate": 3.808156126808782e-07,
"loss": 0.5396,
"step": 771
},
{
"epoch": 2.74,
"learning_rate": 3.7037619859184525e-07,
"loss": 0.5289,
"step": 772
},
{
"epoch": 2.75,
"learning_rate": 3.600791695613604e-07,
"loss": 0.5254,
"step": 773
},
{
"epoch": 2.75,
"learning_rate": 3.499246778428311e-07,
"loss": 0.5609,
"step": 774
},
{
"epoch": 2.75,
"learning_rate": 3.399128735820978e-07,
"loss": 0.562,
"step": 775
},
{
"epoch": 2.76,
"learning_rate": 3.300439048151904e-07,
"loss": 0.542,
"step": 776
},
{
"epoch": 2.76,
"learning_rate": 3.20317917466163e-07,
"loss": 0.5457,
"step": 777
},
{
"epoch": 2.76,
"learning_rate": 3.107350553449162e-07,
"loss": 0.5648,
"step": 778
},
{
"epoch": 2.77,
"learning_rate": 3.012954601450857e-07,
"loss": 0.5437,
"step": 779
},
{
"epoch": 2.77,
"learning_rate": 2.919992714419373e-07,
"loss": 0.5636,
"step": 780
},
{
"epoch": 2.77,
"learning_rate": 2.8284662669030846e-07,
"loss": 0.575,
"step": 781
},
{
"epoch": 2.78,
"learning_rate": 2.738376612225757e-07,
"loss": 0.5139,
"step": 782
},
{
"epoch": 2.78,
"learning_rate": 2.649725082466481e-07,
"loss": 0.5432,
"step": 783
},
{
"epoch": 2.79,
"learning_rate": 2.562512988440069e-07,
"loss": 0.5674,
"step": 784
},
{
"epoch": 2.79,
"learning_rate": 2.4767416196775584e-07,
"loss": 0.5695,
"step": 785
},
{
"epoch": 2.79,
"learning_rate": 2.392412244407294e-07,
"loss": 0.5646,
"step": 786
},
{
"epoch": 2.8,
"learning_rate": 2.3095261095359756e-07,
"loss": 0.4911,
"step": 787
},
{
"epoch": 2.8,
"learning_rate": 2.2280844406304513e-07,
"loss": 0.5575,
"step": 788
},
{
"epoch": 2.8,
"learning_rate": 2.1480884418993985e-07,
"loss": 0.5602,
"step": 789
},
{
"epoch": 2.81,
"learning_rate": 2.0695392961756266e-07,
"loss": 0.552,
"step": 790
},
{
"epoch": 2.81,
"learning_rate": 1.9924381648985692e-07,
"loss": 0.5496,
"step": 791
},
{
"epoch": 2.81,
"learning_rate": 1.916786188097075e-07,
"loss": 0.5809,
"step": 792
},
{
"epoch": 2.82,
"learning_rate": 1.8425844843726116e-07,
"loss": 0.5255,
"step": 793
},
{
"epoch": 2.82,
"learning_rate": 1.7698341508826545e-07,
"loss": 0.5259,
"step": 794
},
{
"epoch": 2.82,
"learning_rate": 1.698536263324546e-07,
"loss": 0.549,
"step": 795
},
{
"epoch": 2.83,
"learning_rate": 1.628691875919486e-07,
"loss": 0.4945,
"step": 796
},
{
"epoch": 2.83,
"learning_rate": 1.5603020213970754e-07,
"loss": 0.5381,
"step": 797
},
{
"epoch": 2.83,
"learning_rate": 1.4933677109799094e-07,
"loss": 0.5401,
"step": 798
},
{
"epoch": 2.84,
"learning_rate": 1.4278899343687423e-07,
"loss": 0.5628,
"step": 799
},
{
"epoch": 2.84,
"learning_rate": 1.3638696597277678e-07,
"loss": 0.5646,
"step": 800
},
{
"epoch": 2.85,
"learning_rate": 1.30130783367034e-07,
"loss": 0.4973,
"step": 801
},
{
"epoch": 2.85,
"learning_rate": 1.2402053812449745e-07,
"loss": 0.548,
"step": 802
},
{
"epoch": 2.85,
"learning_rate": 1.1805632059217032e-07,
"loss": 0.5461,
"step": 803
},
{
"epoch": 2.86,
"learning_rate": 1.1223821895786303e-07,
"loss": 0.5149,
"step": 804
},
{
"epoch": 2.86,
"learning_rate": 1.0656631924889749e-07,
"loss": 0.5552,
"step": 805
},
{
"epoch": 2.86,
"learning_rate": 1.0104070533083377e-07,
"loss": 0.5724,
"step": 806
},
{
"epoch": 2.87,
"learning_rate": 9.566145890622324e-08,
"loss": 0.5999,
"step": 807
},
{
"epoch": 2.87,
"learning_rate": 9.042865951340962e-08,
"loss": 0.5742,
"step": 808
},
{
"epoch": 2.87,
"learning_rate": 8.53423845253476e-08,
"loss": 0.5912,
"step": 809
},
{
"epoch": 2.88,
"learning_rate": 8.04027091484616e-08,
"loss": 0.592,
"step": 810
},
{
"epoch": 2.88,
"learning_rate": 7.560970642152888e-08,
"loss": 0.5739,
"step": 811
},
{
"epoch": 2.88,
"learning_rate": 7.096344721460591e-08,
"loss": 0.6303,
"step": 812
},
{
"epoch": 2.89,
"learning_rate": 6.646400022797706e-08,
"loss": 0.5782,
"step": 813
},
{
"epoch": 2.89,
"learning_rate": 6.211143199113867e-08,
"loss": 0.5716,
"step": 814
},
{
"epoch": 2.9,
"learning_rate": 5.790580686181546e-08,
"loss": 0.5141,
"step": 815
},
{
"epoch": 2.9,
"learning_rate": 5.3847187025010126e-08,
"loss": 0.5449,
"step": 816
},
{
"epoch": 2.9,
"learning_rate": 4.993563249208411e-08,
"loss": 0.5259,
"step": 817
},
{
"epoch": 2.91,
"learning_rate": 4.617120109986495e-08,
"loss": 0.579,
"step": 818
},
{
"epoch": 2.91,
"learning_rate": 4.2553948509802544e-08,
"loss": 0.5842,
"step": 819
},
{
"epoch": 2.91,
"learning_rate": 3.9083928207132025e-08,
"loss": 0.6354,
"step": 820
},
{
"epoch": 2.92,
"learning_rate": 3.576119150009438e-08,
"loss": 0.5283,
"step": 821
},
{
"epoch": 2.92,
"learning_rate": 3.258578751917041e-08,
"loss": 0.5471,
"step": 822
},
{
"epoch": 2.92,
"learning_rate": 2.955776321636017e-08,
"loss": 0.5071,
"step": 823
},
{
"epoch": 2.93,
"learning_rate": 2.667716336448356e-08,
"loss": 0.5643,
"step": 824
},
{
"epoch": 2.93,
"learning_rate": 2.3944030556520835e-08,
"loss": 0.5262,
"step": 825
},
{
"epoch": 2.93,
"learning_rate": 2.1358405204982e-08,
"loss": 0.5206,
"step": 826
},
{
"epoch": 2.94,
"learning_rate": 1.8920325541311735e-08,
"loss": 0.5214,
"step": 827
},
{
"epoch": 2.94,
"learning_rate": 1.6629827615319837e-08,
"loss": 0.5171,
"step": 828
},
{
"epoch": 2.94,
"learning_rate": 1.4486945294652777e-08,
"loss": 0.5472,
"step": 829
},
{
"epoch": 2.95,
"learning_rate": 1.2491710264287416e-08,
"loss": 0.5802,
"step": 830
},
{
"epoch": 2.95,
"learning_rate": 1.0644152026068056e-08,
"loss": 0.5331,
"step": 831
},
{
"epoch": 2.96,
"learning_rate": 8.944297898267895e-09,
"loss": 0.5842,
"step": 832
},
{
"epoch": 2.96,
"learning_rate": 7.392173015184912e-09,
"loss": 0.5515,
"step": 833
},
{
"epoch": 2.96,
"learning_rate": 5.987800326767712e-09,
"loss": 0.4651,
"step": 834
},
{
"epoch": 2.97,
"learning_rate": 4.731200598283581e-09,
"loss": 0.5053,
"step": 835
},
{
"epoch": 2.97,
"learning_rate": 3.6223924100020623e-09,
"loss": 0.5528,
"step": 836
},
{
"epoch": 2.97,
"learning_rate": 2.6613921569274006e-09,
"loss": 0.544,
"step": 837
},
{
"epoch": 2.98,
"learning_rate": 1.8482140485542866e-09,
"loss": 0.5536,
"step": 838
},
{
"epoch": 2.98,
"learning_rate": 1.1828701086558091e-09,
"loss": 0.5923,
"step": 839
},
{
"epoch": 2.98,
"learning_rate": 6.653701751058173e-10,
"loss": 0.6174,
"step": 840
},
{
"epoch": 2.99,
"learning_rate": 2.9572189973570145e-10,
"loss": 0.5595,
"step": 841
},
{
"epoch": 2.99,
"learning_rate": 7.393074822226177e-11,
"loss": 0.566,
"step": 842
},
{
"epoch": 2.99,
"learning_rate": 0.0,
"loss": 0.5729,
"step": 843
},
{
"epoch": 2.99,
"step": 843,
"total_flos": 1.102296029841064e+18,
"train_loss": 0.6429492131246791,
"train_runtime": 7879.9943,
"train_samples_per_second": 13.706,
"train_steps_per_second": 0.107
}
],
"logging_steps": 1.0,
"max_steps": 843,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 10000,
"total_flos": 1.102296029841064e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}