kaijun123's picture
Upload folder using huggingface_hub
29e4939 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9952,
"eval_steps": 500,
"global_step": 936,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 6.896551724137931e-07,
"loss": 2.3172,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.3793103448275862e-06,
"loss": 2.5335,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 2.0689655172413796e-06,
"loss": 2.3783,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 2.7586206896551725e-06,
"loss": 2.3682,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 3.448275862068966e-06,
"loss": 2.3227,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 4.137931034482759e-06,
"loss": 2.0661,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 4.8275862068965525e-06,
"loss": 2.368,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 5.517241379310345e-06,
"loss": 2.2495,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 6.206896551724138e-06,
"loss": 2.2111,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 6.896551724137932e-06,
"loss": 2.079,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 7.586206896551724e-06,
"loss": 1.8298,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 8.275862068965518e-06,
"loss": 1.9533,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 8.965517241379312e-06,
"loss": 1.9097,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 9.655172413793105e-06,
"loss": 2.0271,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 1.0344827586206898e-05,
"loss": 2.0544,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 1.103448275862069e-05,
"loss": 1.9293,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 1.1724137931034483e-05,
"loss": 1.777,
"step": 17
},
{
"epoch": 0.06,
"learning_rate": 1.2413793103448277e-05,
"loss": 1.723,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 1.310344827586207e-05,
"loss": 1.8557,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 1.3793103448275863e-05,
"loss": 1.7499,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 1.4482758620689657e-05,
"loss": 1.8048,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 1.5172413793103448e-05,
"loss": 1.8325,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 1.586206896551724e-05,
"loss": 1.6855,
"step": 23
},
{
"epoch": 0.08,
"learning_rate": 1.6551724137931037e-05,
"loss": 1.4802,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 1.7241379310344828e-05,
"loss": 1.6372,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 1.7931034482758623e-05,
"loss": 1.7358,
"step": 26
},
{
"epoch": 0.09,
"learning_rate": 1.8620689655172415e-05,
"loss": 1.6731,
"step": 27
},
{
"epoch": 0.09,
"learning_rate": 1.931034482758621e-05,
"loss": 1.6498,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 1.4205,
"step": 29
},
{
"epoch": 0.1,
"learning_rate": 1.999994001333173e-05,
"loss": 1.6402,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 1.999976005404659e-05,
"loss": 1.696,
"step": 31
},
{
"epoch": 0.1,
"learning_rate": 1.9999460124303614e-05,
"loss": 1.5169,
"step": 32
},
{
"epoch": 0.11,
"learning_rate": 1.999904022770116e-05,
"loss": 1.6764,
"step": 33
},
{
"epoch": 0.11,
"learning_rate": 1.9998500369276873e-05,
"loss": 1.6429,
"step": 34
},
{
"epoch": 0.11,
"learning_rate": 1.9997840555507605e-05,
"loss": 1.6175,
"step": 35
},
{
"epoch": 0.12,
"learning_rate": 1.9997060794309367e-05,
"loss": 1.5782,
"step": 36
},
{
"epoch": 0.12,
"learning_rate": 1.9996161095037215e-05,
"loss": 1.5128,
"step": 37
},
{
"epoch": 0.12,
"learning_rate": 1.9995141468485138e-05,
"loss": 1.4396,
"step": 38
},
{
"epoch": 0.12,
"learning_rate": 1.9994001926885936e-05,
"loss": 1.5293,
"step": 39
},
{
"epoch": 0.13,
"learning_rate": 1.999274248391108e-05,
"loss": 1.4725,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 1.9991363154670512e-05,
"loss": 1.3653,
"step": 41
},
{
"epoch": 0.13,
"learning_rate": 1.9989863955712518e-05,
"loss": 1.6944,
"step": 42
},
{
"epoch": 0.14,
"learning_rate": 1.9988244905023476e-05,
"loss": 1.6718,
"step": 43
},
{
"epoch": 0.14,
"learning_rate": 1.998650602202769e-05,
"loss": 1.4897,
"step": 44
},
{
"epoch": 0.14,
"learning_rate": 1.998464732758711e-05,
"loss": 1.4364,
"step": 45
},
{
"epoch": 0.15,
"learning_rate": 1.998266884400112e-05,
"loss": 1.4994,
"step": 46
},
{
"epoch": 0.15,
"learning_rate": 1.9980570595006243e-05,
"loss": 1.3317,
"step": 47
},
{
"epoch": 0.15,
"learning_rate": 1.9978352605775874e-05,
"loss": 1.4053,
"step": 48
},
{
"epoch": 0.16,
"learning_rate": 1.997601490291997e-05,
"loss": 1.4366,
"step": 49
},
{
"epoch": 0.16,
"learning_rate": 1.9973557514484726e-05,
"loss": 1.553,
"step": 50
},
{
"epoch": 0.16,
"learning_rate": 1.9970980469952264e-05,
"loss": 1.4289,
"step": 51
},
{
"epoch": 0.17,
"learning_rate": 1.996828380024024e-05,
"loss": 1.505,
"step": 52
},
{
"epoch": 0.17,
"learning_rate": 1.9965467537701496e-05,
"loss": 1.5202,
"step": 53
},
{
"epoch": 0.17,
"learning_rate": 1.996253171612368e-05,
"loss": 1.3883,
"step": 54
},
{
"epoch": 0.18,
"learning_rate": 1.995947637072882e-05,
"loss": 1.3935,
"step": 55
},
{
"epoch": 0.18,
"learning_rate": 1.9956301538172913e-05,
"loss": 1.3272,
"step": 56
},
{
"epoch": 0.18,
"learning_rate": 1.995300725654549e-05,
"loss": 1.5009,
"step": 57
},
{
"epoch": 0.19,
"learning_rate": 1.994959356536914e-05,
"loss": 1.4443,
"step": 58
},
{
"epoch": 0.19,
"learning_rate": 1.9946060505599058e-05,
"loss": 1.6184,
"step": 59
},
{
"epoch": 0.19,
"learning_rate": 1.994240811962254e-05,
"loss": 1.4231,
"step": 60
},
{
"epoch": 0.2,
"learning_rate": 1.993863645125848e-05,
"loss": 1.3921,
"step": 61
},
{
"epoch": 0.2,
"learning_rate": 1.9934745545756847e-05,
"loss": 1.3142,
"step": 62
},
{
"epoch": 0.2,
"learning_rate": 1.9930735449798125e-05,
"loss": 1.5005,
"step": 63
},
{
"epoch": 0.2,
"learning_rate": 1.9926606211492773e-05,
"loss": 1.2946,
"step": 64
},
{
"epoch": 0.21,
"learning_rate": 1.9922357880380644e-05,
"loss": 1.4166,
"step": 65
},
{
"epoch": 0.21,
"learning_rate": 1.9917990507430385e-05,
"loss": 1.6474,
"step": 66
},
{
"epoch": 0.21,
"learning_rate": 1.9913504145038823e-05,
"loss": 1.3899,
"step": 67
},
{
"epoch": 0.22,
"learning_rate": 1.9908898847030348e-05,
"loss": 1.1886,
"step": 68
},
{
"epoch": 0.22,
"learning_rate": 1.9904174668656252e-05,
"loss": 1.4622,
"step": 69
},
{
"epoch": 0.22,
"learning_rate": 1.9899331666594085e-05,
"loss": 1.3867,
"step": 70
},
{
"epoch": 0.23,
"learning_rate": 1.9894369898946955e-05,
"loss": 1.5177,
"step": 71
},
{
"epoch": 0.23,
"learning_rate": 1.9889289425242845e-05,
"loss": 1.4268,
"step": 72
},
{
"epoch": 0.23,
"learning_rate": 1.9884090306433892e-05,
"loss": 1.3998,
"step": 73
},
{
"epoch": 0.24,
"learning_rate": 1.9878772604895657e-05,
"loss": 1.5961,
"step": 74
},
{
"epoch": 0.24,
"learning_rate": 1.9873336384426388e-05,
"loss": 1.4743,
"step": 75
},
{
"epoch": 0.24,
"learning_rate": 1.9867781710246228e-05,
"loss": 1.4967,
"step": 76
},
{
"epoch": 0.25,
"learning_rate": 1.9862108648996457e-05,
"loss": 1.4504,
"step": 77
},
{
"epoch": 0.25,
"learning_rate": 1.985631726873869e-05,
"loss": 1.5035,
"step": 78
},
{
"epoch": 0.25,
"learning_rate": 1.985040763895404e-05,
"loss": 1.224,
"step": 79
},
{
"epoch": 0.26,
"learning_rate": 1.9844379830542312e-05,
"loss": 1.512,
"step": 80
},
{
"epoch": 0.26,
"learning_rate": 1.9838233915821133e-05,
"loss": 1.3871,
"step": 81
},
{
"epoch": 0.26,
"learning_rate": 1.9831969968525096e-05,
"loss": 1.4091,
"step": 82
},
{
"epoch": 0.27,
"learning_rate": 1.982558806380486e-05,
"loss": 1.3401,
"step": 83
},
{
"epoch": 0.27,
"learning_rate": 1.9819088278226273e-05,
"loss": 1.2054,
"step": 84
},
{
"epoch": 0.27,
"learning_rate": 1.9812470689769424e-05,
"loss": 1.3014,
"step": 85
},
{
"epoch": 0.28,
"learning_rate": 1.9805735377827738e-05,
"loss": 1.4982,
"step": 86
},
{
"epoch": 0.28,
"learning_rate": 1.979888242320699e-05,
"loss": 1.4731,
"step": 87
},
{
"epoch": 0.28,
"learning_rate": 1.979191190812437e-05,
"loss": 1.376,
"step": 88
},
{
"epoch": 0.28,
"learning_rate": 1.9784823916207472e-05,
"loss": 1.263,
"step": 89
},
{
"epoch": 0.29,
"learning_rate": 1.9777618532493298e-05,
"loss": 1.2613,
"step": 90
},
{
"epoch": 0.29,
"learning_rate": 1.9770295843427242e-05,
"loss": 1.4536,
"step": 91
},
{
"epoch": 0.29,
"learning_rate": 1.976285593686205e-05,
"loss": 1.4708,
"step": 92
},
{
"epoch": 0.3,
"learning_rate": 1.9755298902056758e-05,
"loss": 1.4129,
"step": 93
},
{
"epoch": 0.3,
"learning_rate": 1.974762482967564e-05,
"loss": 1.3933,
"step": 94
},
{
"epoch": 0.3,
"learning_rate": 1.9739833811787097e-05,
"loss": 1.368,
"step": 95
},
{
"epoch": 0.31,
"learning_rate": 1.9731925941862573e-05,
"loss": 1.2403,
"step": 96
},
{
"epoch": 0.31,
"learning_rate": 1.9723901314775423e-05,
"loss": 1.4722,
"step": 97
},
{
"epoch": 0.31,
"learning_rate": 1.9715760026799776e-05,
"loss": 1.3146,
"step": 98
},
{
"epoch": 0.32,
"learning_rate": 1.9707502175609377e-05,
"loss": 1.3537,
"step": 99
},
{
"epoch": 0.32,
"learning_rate": 1.9699127860276426e-05,
"loss": 1.3931,
"step": 100
},
{
"epoch": 0.32,
"learning_rate": 1.9690637181270372e-05,
"loss": 1.3322,
"step": 101
},
{
"epoch": 0.33,
"learning_rate": 1.968203024045673e-05,
"loss": 1.3933,
"step": 102
},
{
"epoch": 0.33,
"learning_rate": 1.967330714109584e-05,
"loss": 1.3024,
"step": 103
},
{
"epoch": 0.33,
"learning_rate": 1.9664467987841632e-05,
"loss": 1.422,
"step": 104
},
{
"epoch": 0.34,
"learning_rate": 1.9655512886740383e-05,
"loss": 1.3223,
"step": 105
},
{
"epoch": 0.34,
"learning_rate": 1.9646441945229424e-05,
"loss": 1.1517,
"step": 106
},
{
"epoch": 0.34,
"learning_rate": 1.9637255272135863e-05,
"loss": 1.2205,
"step": 107
},
{
"epoch": 0.35,
"learning_rate": 1.9627952977675292e-05,
"loss": 1.3114,
"step": 108
},
{
"epoch": 0.35,
"learning_rate": 1.9618535173450434e-05,
"loss": 1.4354,
"step": 109
},
{
"epoch": 0.35,
"learning_rate": 1.9609001972449834e-05,
"loss": 1.3486,
"step": 110
},
{
"epoch": 0.36,
"learning_rate": 1.959935348904648e-05,
"loss": 1.3698,
"step": 111
},
{
"epoch": 0.36,
"learning_rate": 1.958958983899645e-05,
"loss": 1.4744,
"step": 112
},
{
"epoch": 0.36,
"learning_rate": 1.957971113943751e-05,
"loss": 1.1944,
"step": 113
},
{
"epoch": 0.36,
"learning_rate": 1.956971750888771e-05,
"loss": 1.4073,
"step": 114
},
{
"epoch": 0.37,
"learning_rate": 1.955960906724398e-05,
"loss": 1.3119,
"step": 115
},
{
"epoch": 0.37,
"learning_rate": 1.9549385935780664e-05,
"loss": 1.4867,
"step": 116
},
{
"epoch": 0.37,
"learning_rate": 1.9539048237148078e-05,
"loss": 1.4325,
"step": 117
},
{
"epoch": 0.38,
"learning_rate": 1.952859609537104e-05,
"loss": 1.3476,
"step": 118
},
{
"epoch": 0.38,
"learning_rate": 1.9518029635847387e-05,
"loss": 1.3902,
"step": 119
},
{
"epoch": 0.38,
"learning_rate": 1.9507348985346458e-05,
"loss": 1.2178,
"step": 120
},
{
"epoch": 0.39,
"learning_rate": 1.949655427200758e-05,
"loss": 1.4009,
"step": 121
},
{
"epoch": 0.39,
"learning_rate": 1.948564562533853e-05,
"loss": 1.1641,
"step": 122
},
{
"epoch": 0.39,
"learning_rate": 1.9474623176213988e-05,
"loss": 1.3717,
"step": 123
},
{
"epoch": 0.4,
"learning_rate": 1.9463487056873945e-05,
"loss": 1.2272,
"step": 124
},
{
"epoch": 0.4,
"learning_rate": 1.9452237400922142e-05,
"loss": 1.4411,
"step": 125
},
{
"epoch": 0.4,
"learning_rate": 1.9440874343324464e-05,
"loss": 1.2594,
"step": 126
},
{
"epoch": 0.41,
"learning_rate": 1.9429398020407292e-05,
"loss": 1.4625,
"step": 127
},
{
"epoch": 0.41,
"learning_rate": 1.9417808569855907e-05,
"loss": 1.3649,
"step": 128
},
{
"epoch": 0.41,
"learning_rate": 1.9406106130712813e-05,
"loss": 1.3346,
"step": 129
},
{
"epoch": 0.42,
"learning_rate": 1.939429084337608e-05,
"loss": 1.267,
"step": 130
},
{
"epoch": 0.42,
"learning_rate": 1.938236284959765e-05,
"loss": 1.1933,
"step": 131
},
{
"epoch": 0.42,
"learning_rate": 1.9370322292481642e-05,
"loss": 1.2708,
"step": 132
},
{
"epoch": 0.43,
"learning_rate": 1.935816931648264e-05,
"loss": 1.2231,
"step": 133
},
{
"epoch": 0.43,
"learning_rate": 1.9345904067403953e-05,
"loss": 1.1761,
"step": 134
},
{
"epoch": 0.43,
"learning_rate": 1.9333526692395863e-05,
"loss": 1.2886,
"step": 135
},
{
"epoch": 0.44,
"learning_rate": 1.9321037339953873e-05,
"loss": 1.289,
"step": 136
},
{
"epoch": 0.44,
"learning_rate": 1.9308436159916905e-05,
"loss": 1.4652,
"step": 137
},
{
"epoch": 0.44,
"learning_rate": 1.9295723303465523e-05,
"loss": 1.4461,
"step": 138
},
{
"epoch": 0.44,
"learning_rate": 1.928289892312011e-05,
"loss": 1.3263,
"step": 139
},
{
"epoch": 0.45,
"learning_rate": 1.9269963172739033e-05,
"loss": 1.2746,
"step": 140
},
{
"epoch": 0.45,
"learning_rate": 1.9256916207516806e-05,
"loss": 1.4045,
"step": 141
},
{
"epoch": 0.45,
"learning_rate": 1.9243758183982226e-05,
"loss": 1.201,
"step": 142
},
{
"epoch": 0.46,
"learning_rate": 1.9230489259996487e-05,
"loss": 1.3803,
"step": 143
},
{
"epoch": 0.46,
"learning_rate": 1.9217109594751303e-05,
"loss": 1.2685,
"step": 144
},
{
"epoch": 0.46,
"learning_rate": 1.9203619348766974e-05,
"loss": 1.1703,
"step": 145
},
{
"epoch": 0.47,
"learning_rate": 1.9190018683890492e-05,
"loss": 1.4119,
"step": 146
},
{
"epoch": 0.47,
"learning_rate": 1.9176307763293563e-05,
"loss": 1.2005,
"step": 147
},
{
"epoch": 0.47,
"learning_rate": 1.9162486751470687e-05,
"loss": 1.216,
"step": 148
},
{
"epoch": 0.48,
"learning_rate": 1.914855581423714e-05,
"loss": 1.413,
"step": 149
},
{
"epoch": 0.48,
"learning_rate": 1.9134515118727035e-05,
"loss": 1.2447,
"step": 150
},
{
"epoch": 0.48,
"learning_rate": 1.9120364833391277e-05,
"loss": 1.399,
"step": 151
},
{
"epoch": 0.49,
"learning_rate": 1.910610512799556e-05,
"loss": 1.1665,
"step": 152
},
{
"epoch": 0.49,
"learning_rate": 1.9091736173618326e-05,
"loss": 1.2137,
"step": 153
},
{
"epoch": 0.49,
"learning_rate": 1.907725814264872e-05,
"loss": 1.2291,
"step": 154
},
{
"epoch": 0.5,
"learning_rate": 1.9062671208784508e-05,
"loss": 1.2755,
"step": 155
},
{
"epoch": 0.5,
"learning_rate": 1.9047975547029998e-05,
"loss": 1.3342,
"step": 156
},
{
"epoch": 0.5,
"learning_rate": 1.9033171333693952e-05,
"loss": 1.3475,
"step": 157
},
{
"epoch": 0.51,
"learning_rate": 1.9018258746387458e-05,
"loss": 1.3621,
"step": 158
},
{
"epoch": 0.51,
"learning_rate": 1.9003237964021796e-05,
"loss": 1.4957,
"step": 159
},
{
"epoch": 0.51,
"learning_rate": 1.8988109166806313e-05,
"loss": 1.3468,
"step": 160
},
{
"epoch": 0.52,
"learning_rate": 1.8972872536246224e-05,
"loss": 1.2981,
"step": 161
},
{
"epoch": 0.52,
"learning_rate": 1.8957528255140482e-05,
"loss": 1.3762,
"step": 162
},
{
"epoch": 0.52,
"learning_rate": 1.894207650757954e-05,
"loss": 1.4384,
"step": 163
},
{
"epoch": 0.52,
"learning_rate": 1.892651747894317e-05,
"loss": 1.3045,
"step": 164
},
{
"epoch": 0.53,
"learning_rate": 1.8910851355898238e-05,
"loss": 1.2176,
"step": 165
},
{
"epoch": 0.53,
"learning_rate": 1.8895078326396436e-05,
"loss": 1.3519,
"step": 166
},
{
"epoch": 0.53,
"learning_rate": 1.8879198579672068e-05,
"loss": 1.3789,
"step": 167
},
{
"epoch": 0.54,
"learning_rate": 1.8863212306239753e-05,
"loss": 1.4566,
"step": 168
},
{
"epoch": 0.54,
"learning_rate": 1.884711969789215e-05,
"loss": 1.2376,
"step": 169
},
{
"epoch": 0.54,
"learning_rate": 1.883092094769765e-05,
"loss": 1.3335,
"step": 170
},
{
"epoch": 0.55,
"learning_rate": 1.8814616249998063e-05,
"loss": 1.2798,
"step": 171
},
{
"epoch": 0.55,
"learning_rate": 1.8798205800406283e-05,
"loss": 1.2719,
"step": 172
},
{
"epoch": 0.55,
"learning_rate": 1.8781689795803954e-05,
"loss": 1.4,
"step": 173
},
{
"epoch": 0.56,
"learning_rate": 1.8765068434339095e-05,
"loss": 1.3316,
"step": 174
},
{
"epoch": 0.56,
"learning_rate": 1.8748341915423723e-05,
"loss": 1.3677,
"step": 175
},
{
"epoch": 0.56,
"learning_rate": 1.8731510439731465e-05,
"loss": 1.2105,
"step": 176
},
{
"epoch": 0.57,
"learning_rate": 1.8714574209195153e-05,
"loss": 1.34,
"step": 177
},
{
"epoch": 0.57,
"learning_rate": 1.8697533427004395e-05,
"loss": 1.3036,
"step": 178
},
{
"epoch": 0.57,
"learning_rate": 1.868038829760314e-05,
"loss": 1.2229,
"step": 179
},
{
"epoch": 0.58,
"learning_rate": 1.866313902668723e-05,
"loss": 1.3492,
"step": 180
},
{
"epoch": 0.58,
"learning_rate": 1.8645785821201918e-05,
"loss": 1.1391,
"step": 181
},
{
"epoch": 0.58,
"learning_rate": 1.8628328889339403e-05,
"loss": 1.1359,
"step": 182
},
{
"epoch": 0.59,
"learning_rate": 1.8610768440536317e-05,
"loss": 1.222,
"step": 183
},
{
"epoch": 0.59,
"learning_rate": 1.859310468547123e-05,
"loss": 1.1345,
"step": 184
},
{
"epoch": 0.59,
"learning_rate": 1.85753378360621e-05,
"loss": 1.2547,
"step": 185
},
{
"epoch": 0.6,
"learning_rate": 1.8557468105463753e-05,
"loss": 1.3382,
"step": 186
},
{
"epoch": 0.6,
"learning_rate": 1.8539495708065304e-05,
"loss": 1.3435,
"step": 187
},
{
"epoch": 0.6,
"learning_rate": 1.85214208594876e-05,
"loss": 1.258,
"step": 188
},
{
"epoch": 0.6,
"learning_rate": 1.8503243776580637e-05,
"loss": 1.4196,
"step": 189
},
{
"epoch": 0.61,
"learning_rate": 1.8484964677420937e-05,
"loss": 1.3237,
"step": 190
},
{
"epoch": 0.61,
"learning_rate": 1.8466583781308954e-05,
"loss": 1.2552,
"step": 191
},
{
"epoch": 0.61,
"learning_rate": 1.8448101308766433e-05,
"loss": 1.3336,
"step": 192
},
{
"epoch": 0.62,
"learning_rate": 1.8429517481533762e-05,
"loss": 1.3072,
"step": 193
},
{
"epoch": 0.62,
"learning_rate": 1.8410832522567318e-05,
"loss": 1.2765,
"step": 194
},
{
"epoch": 0.62,
"learning_rate": 1.8392046656036788e-05,
"loss": 1.4138,
"step": 195
},
{
"epoch": 0.63,
"learning_rate": 1.8373160107322476e-05,
"loss": 1.118,
"step": 196
},
{
"epoch": 0.63,
"learning_rate": 1.8354173103012614e-05,
"loss": 1.3164,
"step": 197
},
{
"epoch": 0.63,
"learning_rate": 1.8335085870900627e-05,
"loss": 1.0868,
"step": 198
},
{
"epoch": 0.64,
"learning_rate": 1.8315898639982404e-05,
"loss": 1.4739,
"step": 199
},
{
"epoch": 0.64,
"learning_rate": 1.8296611640453562e-05,
"loss": 1.3315,
"step": 200
},
{
"epoch": 0.64,
"learning_rate": 1.827722510370667e-05,
"loss": 1.4071,
"step": 201
},
{
"epoch": 0.65,
"learning_rate": 1.825773926232847e-05,
"loss": 1.1968,
"step": 202
},
{
"epoch": 0.65,
"learning_rate": 1.8238154350097103e-05,
"loss": 1.203,
"step": 203
},
{
"epoch": 0.65,
"learning_rate": 1.8218470601979302e-05,
"loss": 1.3302,
"step": 204
},
{
"epoch": 0.66,
"learning_rate": 1.819868825412756e-05,
"loss": 1.3479,
"step": 205
},
{
"epoch": 0.66,
"learning_rate": 1.8178807543877303e-05,
"loss": 1.1735,
"step": 206
},
{
"epoch": 0.66,
"learning_rate": 1.815882870974404e-05,
"loss": 1.4118,
"step": 207
},
{
"epoch": 0.67,
"learning_rate": 1.8138751991420524e-05,
"loss": 1.4945,
"step": 208
},
{
"epoch": 0.67,
"learning_rate": 1.8118577629773824e-05,
"loss": 1.1916,
"step": 209
},
{
"epoch": 0.67,
"learning_rate": 1.8098305866842506e-05,
"loss": 1.5478,
"step": 210
},
{
"epoch": 0.68,
"learning_rate": 1.8077936945833662e-05,
"loss": 1.277,
"step": 211
},
{
"epoch": 0.68,
"learning_rate": 1.805747111112004e-05,
"loss": 1.4654,
"step": 212
},
{
"epoch": 0.68,
"learning_rate": 1.8036908608237085e-05,
"loss": 1.1941,
"step": 213
},
{
"epoch": 0.68,
"learning_rate": 1.801624968388e-05,
"loss": 1.1873,
"step": 214
},
{
"epoch": 0.69,
"learning_rate": 1.7995494585900802e-05,
"loss": 1.1864,
"step": 215
},
{
"epoch": 0.69,
"learning_rate": 1.7974643563305326e-05,
"loss": 1.115,
"step": 216
},
{
"epoch": 0.69,
"learning_rate": 1.795369686625024e-05,
"loss": 1.1453,
"step": 217
},
{
"epoch": 0.7,
"learning_rate": 1.7932654746040063e-05,
"loss": 1.42,
"step": 218
},
{
"epoch": 0.7,
"learning_rate": 1.791151745512413e-05,
"loss": 1.2897,
"step": 219
},
{
"epoch": 0.7,
"learning_rate": 1.7890285247093574e-05,
"loss": 1.2854,
"step": 220
},
{
"epoch": 0.71,
"learning_rate": 1.786895837667828e-05,
"loss": 1.1274,
"step": 221
},
{
"epoch": 0.71,
"learning_rate": 1.7847537099743824e-05,
"loss": 1.2839,
"step": 222
},
{
"epoch": 0.71,
"learning_rate": 1.7826021673288413e-05,
"loss": 1.1834,
"step": 223
},
{
"epoch": 0.72,
"learning_rate": 1.7804412355439803e-05,
"loss": 1.5192,
"step": 224
},
{
"epoch": 0.72,
"learning_rate": 1.7782709405452184e-05,
"loss": 1.3566,
"step": 225
},
{
"epoch": 0.72,
"learning_rate": 1.7760913083703088e-05,
"loss": 1.2277,
"step": 226
},
{
"epoch": 0.73,
"learning_rate": 1.7739023651690267e-05,
"loss": 1.2414,
"step": 227
},
{
"epoch": 0.73,
"learning_rate": 1.771704137202853e-05,
"loss": 1.3937,
"step": 228
},
{
"epoch": 0.73,
"learning_rate": 1.769496650844663e-05,
"loss": 1.2114,
"step": 229
},
{
"epoch": 0.74,
"learning_rate": 1.7672799325784066e-05,
"loss": 1.113,
"step": 230
},
{
"epoch": 0.74,
"learning_rate": 1.7650540089987926e-05,
"loss": 1.0849,
"step": 231
},
{
"epoch": 0.74,
"learning_rate": 1.762818906810969e-05,
"loss": 1.2413,
"step": 232
},
{
"epoch": 0.75,
"learning_rate": 1.7605746528302017e-05,
"loss": 1.233,
"step": 233
},
{
"epoch": 0.75,
"learning_rate": 1.7583212739815555e-05,
"loss": 1.0594,
"step": 234
},
{
"epoch": 0.75,
"learning_rate": 1.7560587972995678e-05,
"loss": 1.3367,
"step": 235
},
{
"epoch": 0.76,
"learning_rate": 1.7537872499279265e-05,
"loss": 1.2846,
"step": 236
},
{
"epoch": 0.76,
"learning_rate": 1.751506659119143e-05,
"loss": 1.2923,
"step": 237
},
{
"epoch": 0.76,
"learning_rate": 1.7492170522342267e-05,
"loss": 1.1856,
"step": 238
},
{
"epoch": 0.76,
"learning_rate": 1.7469184567423548e-05,
"loss": 1.1919,
"step": 239
},
{
"epoch": 0.77,
"learning_rate": 1.7446109002205444e-05,
"loss": 1.2731,
"step": 240
},
{
"epoch": 0.77,
"learning_rate": 1.7422944103533212e-05,
"loss": 1.3955,
"step": 241
},
{
"epoch": 0.77,
"learning_rate": 1.739969014932387e-05,
"loss": 1.2863,
"step": 242
},
{
"epoch": 0.78,
"learning_rate": 1.7376347418562866e-05,
"loss": 1.245,
"step": 243
},
{
"epoch": 0.78,
"learning_rate": 1.735291619130073e-05,
"loss": 1.1457,
"step": 244
},
{
"epoch": 0.78,
"learning_rate": 1.732939674864971e-05,
"loss": 1.4096,
"step": 245
},
{
"epoch": 0.79,
"learning_rate": 1.730578937278041e-05,
"loss": 1.3531,
"step": 246
},
{
"epoch": 0.79,
"learning_rate": 1.7282094346918395e-05,
"loss": 1.3947,
"step": 247
},
{
"epoch": 0.79,
"learning_rate": 1.7258311955340794e-05,
"loss": 1.3041,
"step": 248
},
{
"epoch": 0.8,
"learning_rate": 1.7234442483372894e-05,
"loss": 1.2553,
"step": 249
},
{
"epoch": 0.8,
"learning_rate": 1.721048621738472e-05,
"loss": 1.3328,
"step": 250
},
{
"epoch": 0.8,
"learning_rate": 1.7186443444787578e-05,
"loss": 1.1772,
"step": 251
},
{
"epoch": 0.81,
"learning_rate": 1.7162314454030644e-05,
"loss": 1.0941,
"step": 252
},
{
"epoch": 0.81,
"learning_rate": 1.7138099534597464e-05,
"loss": 1.2324,
"step": 253
},
{
"epoch": 0.81,
"learning_rate": 1.7113798977002506e-05,
"loss": 1.0949,
"step": 254
},
{
"epoch": 0.82,
"learning_rate": 1.7089413072787667e-05,
"loss": 1.3798,
"step": 255
},
{
"epoch": 0.82,
"learning_rate": 1.706494211451878e-05,
"loss": 1.2483,
"step": 256
},
{
"epoch": 0.82,
"learning_rate": 1.7040386395782093e-05,
"loss": 1.0528,
"step": 257
},
{
"epoch": 0.83,
"learning_rate": 1.701574621118076e-05,
"loss": 1.2136,
"step": 258
},
{
"epoch": 0.83,
"learning_rate": 1.6991021856331297e-05,
"loss": 1.4656,
"step": 259
},
{
"epoch": 0.83,
"learning_rate": 1.696621362786003e-05,
"loss": 1.2376,
"step": 260
},
{
"epoch": 0.84,
"learning_rate": 1.6941321823399567e-05,
"loss": 1.2852,
"step": 261
},
{
"epoch": 0.84,
"learning_rate": 1.691634674158518e-05,
"loss": 1.2205,
"step": 262
},
{
"epoch": 0.84,
"learning_rate": 1.6891288682051264e-05,
"loss": 1.3117,
"step": 263
},
{
"epoch": 0.84,
"learning_rate": 1.686614794542772e-05,
"loss": 1.2704,
"step": 264
},
{
"epoch": 0.85,
"learning_rate": 1.684092483333635e-05,
"loss": 1.1265,
"step": 265
},
{
"epoch": 0.85,
"learning_rate": 1.681561964838725e-05,
"loss": 1.1492,
"step": 266
},
{
"epoch": 0.85,
"learning_rate": 1.6790232694175164e-05,
"loss": 1.2796,
"step": 267
},
{
"epoch": 0.86,
"learning_rate": 1.6764764275275852e-05,
"loss": 1.238,
"step": 268
},
{
"epoch": 0.86,
"learning_rate": 1.6739214697242437e-05,
"loss": 1.0388,
"step": 269
},
{
"epoch": 0.86,
"learning_rate": 1.6713584266601728e-05,
"loss": 1.2182,
"step": 270
},
{
"epoch": 0.87,
"learning_rate": 1.6687873290850554e-05,
"loss": 1.3731,
"step": 271
},
{
"epoch": 0.87,
"learning_rate": 1.6662082078452068e-05,
"loss": 1.1172,
"step": 272
},
{
"epoch": 0.87,
"learning_rate": 1.6636210938832053e-05,
"loss": 1.3127,
"step": 273
},
{
"epoch": 0.88,
"learning_rate": 1.6610260182375202e-05,
"loss": 1.217,
"step": 274
},
{
"epoch": 0.88,
"learning_rate": 1.65842301204214e-05,
"loss": 1.1905,
"step": 275
},
{
"epoch": 0.88,
"learning_rate": 1.6558121065261982e-05,
"loss": 1.2278,
"step": 276
},
{
"epoch": 0.89,
"learning_rate": 1.6531933330136e-05,
"loss": 1.3432,
"step": 277
},
{
"epoch": 0.89,
"learning_rate": 1.6505667229226445e-05,
"loss": 1.2011,
"step": 278
},
{
"epoch": 0.89,
"learning_rate": 1.6479323077656492e-05,
"loss": 1.2781,
"step": 279
},
{
"epoch": 0.9,
"learning_rate": 1.6452901191485725e-05,
"loss": 1.1543,
"step": 280
},
{
"epoch": 0.9,
"learning_rate": 1.642640188770632e-05,
"loss": 1.3686,
"step": 281
},
{
"epoch": 0.9,
"learning_rate": 1.639982548423927e-05,
"loss": 1.3256,
"step": 282
},
{
"epoch": 0.91,
"learning_rate": 1.6373172299930553e-05,
"loss": 1.2598,
"step": 283
},
{
"epoch": 0.91,
"learning_rate": 1.6346442654547314e-05,
"loss": 1.3221,
"step": 284
},
{
"epoch": 0.91,
"learning_rate": 1.631963686877403e-05,
"loss": 1.2581,
"step": 285
},
{
"epoch": 0.92,
"learning_rate": 1.6292755264208656e-05,
"loss": 1.432,
"step": 286
},
{
"epoch": 0.92,
"learning_rate": 1.626579816335877e-05,
"loss": 1.3085,
"step": 287
},
{
"epoch": 0.92,
"learning_rate": 1.6238765889637704e-05,
"loss": 1.2833,
"step": 288
},
{
"epoch": 0.92,
"learning_rate": 1.6211658767360667e-05,
"loss": 1.5326,
"step": 289
},
{
"epoch": 0.93,
"learning_rate": 1.6184477121740848e-05,
"loss": 1.0384,
"step": 290
},
{
"epoch": 0.93,
"learning_rate": 1.6157221278885523e-05,
"loss": 1.3251,
"step": 291
},
{
"epoch": 0.93,
"learning_rate": 1.612989156579213e-05,
"loss": 1.2479,
"step": 292
},
{
"epoch": 0.94,
"learning_rate": 1.610248831034435e-05,
"loss": 1.1987,
"step": 293
},
{
"epoch": 0.94,
"learning_rate": 1.607501184130819e-05,
"loss": 1.3294,
"step": 294
},
{
"epoch": 0.94,
"learning_rate": 1.6047462488328017e-05,
"loss": 1.2128,
"step": 295
},
{
"epoch": 0.95,
"learning_rate": 1.6019840581922604e-05,
"loss": 1.3674,
"step": 296
},
{
"epoch": 0.95,
"learning_rate": 1.599214645348118e-05,
"loss": 1.2131,
"step": 297
},
{
"epoch": 0.95,
"learning_rate": 1.5964380435259448e-05,
"loss": 1.2444,
"step": 298
},
{
"epoch": 0.96,
"learning_rate": 1.5936542860375594e-05,
"loss": 1.132,
"step": 299
},
{
"epoch": 0.96,
"learning_rate": 1.5908634062806285e-05,
"loss": 1.1912,
"step": 300
},
{
"epoch": 0.96,
"learning_rate": 1.588065437738268e-05,
"loss": 1.2514,
"step": 301
},
{
"epoch": 0.97,
"learning_rate": 1.585260413978641e-05,
"loss": 1.3142,
"step": 302
},
{
"epoch": 0.97,
"learning_rate": 1.5824483686545517e-05,
"loss": 1.0959,
"step": 303
},
{
"epoch": 0.97,
"learning_rate": 1.5796293355030476e-05,
"loss": 1.2714,
"step": 304
},
{
"epoch": 0.98,
"learning_rate": 1.5768033483450088e-05,
"loss": 1.4746,
"step": 305
},
{
"epoch": 0.98,
"learning_rate": 1.5739704410847475e-05,
"loss": 1.2518,
"step": 306
},
{
"epoch": 0.98,
"learning_rate": 1.5711306477095962e-05,
"loss": 1.3225,
"step": 307
},
{
"epoch": 0.99,
"learning_rate": 1.568284002289504e-05,
"loss": 1.2877,
"step": 308
},
{
"epoch": 0.99,
"learning_rate": 1.5654305389766257e-05,
"loss": 1.2796,
"step": 309
},
{
"epoch": 0.99,
"learning_rate": 1.562570292004913e-05,
"loss": 1.1916,
"step": 310
},
{
"epoch": 1.0,
"learning_rate": 1.5597032956897028e-05,
"loss": 1.1361,
"step": 311
},
{
"epoch": 1.0,
"learning_rate": 1.5568295844273064e-05,
"loss": 1.0916,
"step": 312
},
{
"epoch": 1.0,
"learning_rate": 1.553949192694597e-05,
"loss": 1.1436,
"step": 313
},
{
"epoch": 1.0,
"learning_rate": 1.551062155048595e-05,
"loss": 1.1519,
"step": 314
},
{
"epoch": 1.01,
"learning_rate": 1.5481685061260547e-05,
"loss": 0.9804,
"step": 315
},
{
"epoch": 1.01,
"learning_rate": 1.5452682806430473e-05,
"loss": 1.0737,
"step": 316
},
{
"epoch": 1.01,
"learning_rate": 1.5423615133945457e-05,
"loss": 1.1061,
"step": 317
},
{
"epoch": 1.02,
"learning_rate": 1.5394482392540066e-05,
"loss": 1.1782,
"step": 318
},
{
"epoch": 1.02,
"learning_rate": 1.5365284931729513e-05,
"loss": 1.2215,
"step": 319
},
{
"epoch": 1.02,
"learning_rate": 1.5336023101805486e-05,
"loss": 1.2741,
"step": 320
},
{
"epoch": 1.03,
"learning_rate": 1.5306697253831914e-05,
"loss": 1.0344,
"step": 321
},
{
"epoch": 1.03,
"learning_rate": 1.5277307739640787e-05,
"loss": 1.0388,
"step": 322
},
{
"epoch": 1.03,
"learning_rate": 1.524785491182791e-05,
"loss": 1.0273,
"step": 323
},
{
"epoch": 1.04,
"learning_rate": 1.5218339123748682e-05,
"loss": 0.9247,
"step": 324
},
{
"epoch": 1.04,
"learning_rate": 1.5188760729513865e-05,
"loss": 1.12,
"step": 325
},
{
"epoch": 1.04,
"learning_rate": 1.5159120083985319e-05,
"loss": 1.0136,
"step": 326
},
{
"epoch": 1.05,
"learning_rate": 1.5129417542771761e-05,
"loss": 1.1744,
"step": 327
},
{
"epoch": 1.05,
"learning_rate": 1.5099653462224492e-05,
"loss": 0.966,
"step": 328
},
{
"epoch": 1.05,
"learning_rate": 1.506982819943311e-05,
"loss": 1.1586,
"step": 329
},
{
"epoch": 1.06,
"learning_rate": 1.503994211222125e-05,
"loss": 0.9398,
"step": 330
},
{
"epoch": 1.06,
"learning_rate": 1.5009995559142268e-05,
"loss": 1.1101,
"step": 331
},
{
"epoch": 1.06,
"learning_rate": 1.4979988899474955e-05,
"loss": 1.1331,
"step": 332
},
{
"epoch": 1.07,
"learning_rate": 1.494992249321922e-05,
"loss": 1.0797,
"step": 333
},
{
"epoch": 1.07,
"learning_rate": 1.4919796701091767e-05,
"loss": 1.1103,
"step": 334
},
{
"epoch": 1.07,
"learning_rate": 1.4889611884521777e-05,
"loss": 0.9671,
"step": 335
},
{
"epoch": 1.08,
"learning_rate": 1.4859368405646568e-05,
"loss": 1.1242,
"step": 336
},
{
"epoch": 1.08,
"learning_rate": 1.4829066627307246e-05,
"loss": 1.0974,
"step": 337
},
{
"epoch": 1.08,
"learning_rate": 1.4798706913044357e-05,
"loss": 1.1175,
"step": 338
},
{
"epoch": 1.08,
"learning_rate": 1.476828962709352e-05,
"loss": 1.0538,
"step": 339
},
{
"epoch": 1.09,
"learning_rate": 1.4737815134381066e-05,
"loss": 1.0735,
"step": 340
},
{
"epoch": 1.09,
"learning_rate": 1.4707283800519647e-05,
"loss": 1.3825,
"step": 341
},
{
"epoch": 1.09,
"learning_rate": 1.4676695991803869e-05,
"loss": 1.1401,
"step": 342
},
{
"epoch": 1.1,
"learning_rate": 1.4646052075205874e-05,
"loss": 1.1364,
"step": 343
},
{
"epoch": 1.1,
"learning_rate": 1.4615352418370958e-05,
"loss": 1.0251,
"step": 344
},
{
"epoch": 1.1,
"learning_rate": 1.4584597389613144e-05,
"loss": 1.1488,
"step": 345
},
{
"epoch": 1.11,
"learning_rate": 1.4553787357910774e-05,
"loss": 1.0476,
"step": 346
},
{
"epoch": 1.11,
"learning_rate": 1.452292269290208e-05,
"loss": 0.9702,
"step": 347
},
{
"epoch": 1.11,
"learning_rate": 1.4492003764880744e-05,
"loss": 1.0864,
"step": 348
},
{
"epoch": 1.12,
"learning_rate": 1.4461030944791464e-05,
"loss": 1.0446,
"step": 349
},
{
"epoch": 1.12,
"learning_rate": 1.4430004604225493e-05,
"loss": 1.16,
"step": 350
},
{
"epoch": 1.12,
"learning_rate": 1.4398925115416196e-05,
"loss": 1.014,
"step": 351
},
{
"epoch": 1.13,
"learning_rate": 1.4367792851234566e-05,
"loss": 1.0546,
"step": 352
},
{
"epoch": 1.13,
"learning_rate": 1.4336608185184765e-05,
"loss": 1.0048,
"step": 353
},
{
"epoch": 1.13,
"learning_rate": 1.4305371491399638e-05,
"loss": 1.0999,
"step": 354
},
{
"epoch": 1.14,
"learning_rate": 1.427408314463622e-05,
"loss": 1.1723,
"step": 355
},
{
"epoch": 1.14,
"learning_rate": 1.4242743520271249e-05,
"loss": 1.0517,
"step": 356
},
{
"epoch": 1.14,
"learning_rate": 1.4211352994296655e-05,
"loss": 1.1067,
"step": 357
},
{
"epoch": 1.15,
"learning_rate": 1.417991194331505e-05,
"loss": 1.0712,
"step": 358
},
{
"epoch": 1.15,
"learning_rate": 1.4148420744535214e-05,
"loss": 1.1264,
"step": 359
},
{
"epoch": 1.15,
"learning_rate": 1.4116879775767567e-05,
"loss": 1.0318,
"step": 360
},
{
"epoch": 1.16,
"learning_rate": 1.4085289415419632e-05,
"loss": 0.9812,
"step": 361
},
{
"epoch": 1.16,
"learning_rate": 1.4053650042491507e-05,
"loss": 1.0524,
"step": 362
},
{
"epoch": 1.16,
"learning_rate": 1.4021962036571301e-05,
"loss": 1.1601,
"step": 363
},
{
"epoch": 1.16,
"learning_rate": 1.3990225777830595e-05,
"loss": 1.0957,
"step": 364
},
{
"epoch": 1.17,
"learning_rate": 1.3958441647019877e-05,
"loss": 0.8799,
"step": 365
},
{
"epoch": 1.17,
"learning_rate": 1.3926610025463967e-05,
"loss": 1.205,
"step": 366
},
{
"epoch": 1.17,
"learning_rate": 1.3894731295057446e-05,
"loss": 0.9758,
"step": 367
},
{
"epoch": 1.18,
"learning_rate": 1.3862805838260087e-05,
"loss": 1.0533,
"step": 368
},
{
"epoch": 1.18,
"learning_rate": 1.383083403809224e-05,
"loss": 1.0062,
"step": 369
},
{
"epoch": 1.18,
"learning_rate": 1.3798816278130268e-05,
"loss": 1.0966,
"step": 370
},
{
"epoch": 1.19,
"learning_rate": 1.3766752942501911e-05,
"loss": 1.0667,
"step": 371
},
{
"epoch": 1.19,
"learning_rate": 1.3734644415881708e-05,
"loss": 1.1089,
"step": 372
},
{
"epoch": 1.19,
"learning_rate": 1.3702491083486366e-05,
"loss": 1.0091,
"step": 373
},
{
"epoch": 1.2,
"learning_rate": 1.3670293331070142e-05,
"loss": 1.075,
"step": 374
},
{
"epoch": 1.2,
"learning_rate": 1.3638051544920217e-05,
"loss": 1.1298,
"step": 375
},
{
"epoch": 1.2,
"learning_rate": 1.3605766111852052e-05,
"loss": 0.9582,
"step": 376
},
{
"epoch": 1.21,
"learning_rate": 1.3573437419204765e-05,
"loss": 1.2061,
"step": 377
},
{
"epoch": 1.21,
"learning_rate": 1.3541065854836464e-05,
"loss": 1.0294,
"step": 378
},
{
"epoch": 1.21,
"learning_rate": 1.3508651807119609e-05,
"loss": 1.1752,
"step": 379
},
{
"epoch": 1.22,
"learning_rate": 1.3476195664936347e-05,
"loss": 1.1268,
"step": 380
},
{
"epoch": 1.22,
"learning_rate": 1.3443697817673842e-05,
"loss": 0.996,
"step": 381
},
{
"epoch": 1.22,
"learning_rate": 1.3411158655219615e-05,
"loss": 0.9984,
"step": 382
},
{
"epoch": 1.23,
"learning_rate": 1.337857856795685e-05,
"loss": 1.044,
"step": 383
},
{
"epoch": 1.23,
"learning_rate": 1.334595794675973e-05,
"loss": 1.2486,
"step": 384
},
{
"epoch": 1.23,
"learning_rate": 1.3313297182988722e-05,
"loss": 1.1302,
"step": 385
},
{
"epoch": 1.24,
"learning_rate": 1.3280596668485919e-05,
"loss": 1.0039,
"step": 386
},
{
"epoch": 1.24,
"learning_rate": 1.3247856795570295e-05,
"loss": 1.0926,
"step": 387
},
{
"epoch": 1.24,
"learning_rate": 1.3215077957033032e-05,
"loss": 1.0572,
"step": 388
},
{
"epoch": 1.24,
"learning_rate": 1.3182260546132795e-05,
"loss": 1.0954,
"step": 389
},
{
"epoch": 1.25,
"learning_rate": 1.3149404956591008e-05,
"loss": 1.1361,
"step": 390
},
{
"epoch": 1.25,
"learning_rate": 1.3116511582587144e-05,
"loss": 1.0782,
"step": 391
},
{
"epoch": 1.25,
"learning_rate": 1.3083580818753985e-05,
"loss": 1.0336,
"step": 392
},
{
"epoch": 1.26,
"learning_rate": 1.3050613060172893e-05,
"loss": 1.1352,
"step": 393
},
{
"epoch": 1.26,
"learning_rate": 1.3017608702369065e-05,
"loss": 1.066,
"step": 394
},
{
"epoch": 1.26,
"learning_rate": 1.2984568141306797e-05,
"loss": 1.176,
"step": 395
},
{
"epoch": 1.27,
"learning_rate": 1.2951491773384722e-05,
"loss": 1.1472,
"step": 396
},
{
"epoch": 1.27,
"learning_rate": 1.2918379995431062e-05,
"loss": 0.9962,
"step": 397
},
{
"epoch": 1.27,
"learning_rate": 1.2885233204698866e-05,
"loss": 1.073,
"step": 398
},
{
"epoch": 1.28,
"learning_rate": 1.2852051798861243e-05,
"loss": 1.0615,
"step": 399
},
{
"epoch": 1.28,
"learning_rate": 1.2818836176006586e-05,
"loss": 1.0729,
"step": 400
},
{
"epoch": 1.28,
"learning_rate": 1.278558673463381e-05,
"loss": 1.2626,
"step": 401
},
{
"epoch": 1.29,
"learning_rate": 1.275230387364755e-05,
"loss": 0.9681,
"step": 402
},
{
"epoch": 1.29,
"learning_rate": 1.2718987992353403e-05,
"loss": 1.2131,
"step": 403
},
{
"epoch": 1.29,
"learning_rate": 1.2685639490453113e-05,
"loss": 1.0451,
"step": 404
},
{
"epoch": 1.3,
"learning_rate": 1.2652258768039775e-05,
"loss": 1.0072,
"step": 405
},
{
"epoch": 1.3,
"learning_rate": 1.2618846225593057e-05,
"loss": 1.0376,
"step": 406
},
{
"epoch": 1.3,
"learning_rate": 1.2585402263974383e-05,
"loss": 1.1437,
"step": 407
},
{
"epoch": 1.31,
"learning_rate": 1.2551927284422117e-05,
"loss": 1.1727,
"step": 408
},
{
"epoch": 1.31,
"learning_rate": 1.2518421688546757e-05,
"loss": 1.1347,
"step": 409
},
{
"epoch": 1.31,
"learning_rate": 1.2484885878326114e-05,
"loss": 1.0493,
"step": 410
},
{
"epoch": 1.32,
"learning_rate": 1.2451320256100497e-05,
"loss": 1.2051,
"step": 411
},
{
"epoch": 1.32,
"learning_rate": 1.2417725224567872e-05,
"loss": 1.1211,
"step": 412
},
{
"epoch": 1.32,
"learning_rate": 1.2384101186779042e-05,
"loss": 1.0312,
"step": 413
},
{
"epoch": 1.32,
"learning_rate": 1.235044854613281e-05,
"loss": 1.0435,
"step": 414
},
{
"epoch": 1.33,
"learning_rate": 1.231676770637113e-05,
"loss": 0.9924,
"step": 415
},
{
"epoch": 1.33,
"learning_rate": 1.2283059071574278e-05,
"loss": 0.9695,
"step": 416
},
{
"epoch": 1.33,
"learning_rate": 1.224932304615599e-05,
"loss": 0.9465,
"step": 417
},
{
"epoch": 1.34,
"learning_rate": 1.221556003485862e-05,
"loss": 1.0483,
"step": 418
},
{
"epoch": 1.34,
"learning_rate": 1.218177044274828e-05,
"loss": 1.1043,
"step": 419
},
{
"epoch": 1.34,
"learning_rate": 1.2147954675209982e-05,
"loss": 1.1211,
"step": 420
},
{
"epoch": 1.35,
"learning_rate": 1.2114113137942767e-05,
"loss": 1.1638,
"step": 421
},
{
"epoch": 1.35,
"learning_rate": 1.2080246236954856e-05,
"loss": 0.9418,
"step": 422
},
{
"epoch": 1.35,
"learning_rate": 1.2046354378558753e-05,
"loss": 0.9473,
"step": 423
},
{
"epoch": 1.36,
"learning_rate": 1.2012437969366397e-05,
"loss": 1.1651,
"step": 424
},
{
"epoch": 1.36,
"learning_rate": 1.1978497416284265e-05,
"loss": 1.017,
"step": 425
},
{
"epoch": 1.36,
"learning_rate": 1.1944533126508491e-05,
"loss": 1.082,
"step": 426
},
{
"epoch": 1.37,
"learning_rate": 1.191054550752e-05,
"loss": 1.0173,
"step": 427
},
{
"epoch": 1.37,
"learning_rate": 1.187653496707959e-05,
"loss": 1.0361,
"step": 428
},
{
"epoch": 1.37,
"learning_rate": 1.1842501913223066e-05,
"loss": 1.0836,
"step": 429
},
{
"epoch": 1.38,
"learning_rate": 1.1808446754256329e-05,
"loss": 1.0667,
"step": 430
},
{
"epoch": 1.38,
"learning_rate": 1.1774369898750484e-05,
"loss": 1.0376,
"step": 431
},
{
"epoch": 1.38,
"learning_rate": 1.1740271755536939e-05,
"loss": 1.091,
"step": 432
},
{
"epoch": 1.39,
"learning_rate": 1.1706152733702489e-05,
"loss": 1.0371,
"step": 433
},
{
"epoch": 1.39,
"learning_rate": 1.167201324258443e-05,
"loss": 1.0681,
"step": 434
},
{
"epoch": 1.39,
"learning_rate": 1.1637853691765625e-05,
"loss": 0.9842,
"step": 435
},
{
"epoch": 1.4,
"learning_rate": 1.16036744910696e-05,
"loss": 1.0513,
"step": 436
},
{
"epoch": 1.4,
"learning_rate": 1.1569476050555637e-05,
"loss": 1.0221,
"step": 437
},
{
"epoch": 1.4,
"learning_rate": 1.153525878051383e-05,
"loss": 1.1218,
"step": 438
},
{
"epoch": 1.4,
"learning_rate": 1.1501023091460187e-05,
"loss": 1.1723,
"step": 439
},
{
"epoch": 1.41,
"learning_rate": 1.146676939413169e-05,
"loss": 0.9689,
"step": 440
},
{
"epoch": 1.41,
"learning_rate": 1.143249809948138e-05,
"loss": 1.0378,
"step": 441
},
{
"epoch": 1.41,
"learning_rate": 1.139820961867341e-05,
"loss": 0.8955,
"step": 442
},
{
"epoch": 1.42,
"learning_rate": 1.1363904363078126e-05,
"loss": 1.0282,
"step": 443
},
{
"epoch": 1.42,
"learning_rate": 1.1329582744267125e-05,
"loss": 1.0508,
"step": 444
},
{
"epoch": 1.42,
"learning_rate": 1.1295245174008317e-05,
"loss": 1.0539,
"step": 445
},
{
"epoch": 1.43,
"learning_rate": 1.1260892064260995e-05,
"loss": 1.0883,
"step": 446
},
{
"epoch": 1.43,
"learning_rate": 1.1226523827170876e-05,
"loss": 1.1207,
"step": 447
},
{
"epoch": 1.43,
"learning_rate": 1.1192140875065167e-05,
"loss": 1.0696,
"step": 448
},
{
"epoch": 1.44,
"learning_rate": 1.1157743620447611e-05,
"loss": 1.1171,
"step": 449
},
{
"epoch": 1.44,
"learning_rate": 1.112333247599356e-05,
"loss": 1.0022,
"step": 450
},
{
"epoch": 1.44,
"learning_rate": 1.1088907854544985e-05,
"loss": 1.2792,
"step": 451
},
{
"epoch": 1.45,
"learning_rate": 1.1054470169105564e-05,
"loss": 1.0204,
"step": 452
},
{
"epoch": 1.45,
"learning_rate": 1.1020019832835694e-05,
"loss": 1.0105,
"step": 453
},
{
"epoch": 1.45,
"learning_rate": 1.0985557259047557e-05,
"loss": 1.0508,
"step": 454
},
{
"epoch": 1.46,
"learning_rate": 1.0951082861200142e-05,
"loss": 0.9506,
"step": 455
},
{
"epoch": 1.46,
"learning_rate": 1.091659705289431e-05,
"loss": 1.0708,
"step": 456
},
{
"epoch": 1.46,
"learning_rate": 1.088210024786781e-05,
"loss": 1.0901,
"step": 457
},
{
"epoch": 1.47,
"learning_rate": 1.084759285999032e-05,
"loss": 1.1882,
"step": 458
},
{
"epoch": 1.47,
"learning_rate": 1.0813075303258483e-05,
"loss": 1.1313,
"step": 459
},
{
"epoch": 1.47,
"learning_rate": 1.0778547991790946e-05,
"loss": 1.0493,
"step": 460
},
{
"epoch": 1.48,
"learning_rate": 1.0744011339823389e-05,
"loss": 1.1251,
"step": 461
},
{
"epoch": 1.48,
"learning_rate": 1.0709465761703542e-05,
"loss": 1.0042,
"step": 462
},
{
"epoch": 1.48,
"learning_rate": 1.0674911671886236e-05,
"loss": 0.9988,
"step": 463
},
{
"epoch": 1.48,
"learning_rate": 1.0640349484928413e-05,
"loss": 1.0945,
"step": 464
},
{
"epoch": 1.49,
"learning_rate": 1.0605779615484167e-05,
"loss": 1.0302,
"step": 465
},
{
"epoch": 1.49,
"learning_rate": 1.057120247829975e-05,
"loss": 1.0194,
"step": 466
},
{
"epoch": 1.49,
"learning_rate": 1.053661848820862e-05,
"loss": 0.9858,
"step": 467
},
{
"epoch": 1.5,
"learning_rate": 1.050202806012644e-05,
"loss": 1.1142,
"step": 468
},
{
"epoch": 1.5,
"learning_rate": 1.0467431609046116e-05,
"loss": 1.0762,
"step": 469
},
{
"epoch": 1.5,
"learning_rate": 1.0432829550032818e-05,
"loss": 1.1463,
"step": 470
},
{
"epoch": 1.51,
"learning_rate": 1.0398222298218996e-05,
"loss": 1.1158,
"step": 471
},
{
"epoch": 1.51,
"learning_rate": 1.0363610268799393e-05,
"loss": 1.0152,
"step": 472
},
{
"epoch": 1.51,
"learning_rate": 1.0328993877026075e-05,
"loss": 0.9611,
"step": 473
},
{
"epoch": 1.52,
"learning_rate": 1.0294373538203439e-05,
"loss": 1.1085,
"step": 474
},
{
"epoch": 1.52,
"learning_rate": 1.0259749667683252e-05,
"loss": 1.1732,
"step": 475
},
{
"epoch": 1.52,
"learning_rate": 1.0225122680859633e-05,
"loss": 1.0898,
"step": 476
},
{
"epoch": 1.53,
"learning_rate": 1.0190492993164101e-05,
"loss": 1.0462,
"step": 477
},
{
"epoch": 1.53,
"learning_rate": 1.0155861020060566e-05,
"loss": 0.9384,
"step": 478
},
{
"epoch": 1.53,
"learning_rate": 1.0121227177040373e-05,
"loss": 1.1798,
"step": 479
},
{
"epoch": 1.54,
"learning_rate": 1.008659187961729e-05,
"loss": 1.013,
"step": 480
},
{
"epoch": 1.54,
"learning_rate": 1.0051955543322533e-05,
"loss": 1.0267,
"step": 481
},
{
"epoch": 1.54,
"learning_rate": 1.0017318583699786e-05,
"loss": 1.0784,
"step": 482
},
{
"epoch": 1.55,
"learning_rate": 9.982681416300217e-06,
"loss": 0.942,
"step": 483
},
{
"epoch": 1.55,
"learning_rate": 9.948044456677472e-06,
"loss": 1.1899,
"step": 484
},
{
"epoch": 1.55,
"learning_rate": 9.913408120382714e-06,
"loss": 0.9433,
"step": 485
},
{
"epoch": 1.56,
"learning_rate": 9.878772822959628e-06,
"loss": 1.0775,
"step": 486
},
{
"epoch": 1.56,
"learning_rate": 9.844138979939437e-06,
"loss": 1.2114,
"step": 487
},
{
"epoch": 1.56,
"learning_rate": 9.809507006835904e-06,
"loss": 1.0274,
"step": 488
},
{
"epoch": 1.56,
"learning_rate": 9.774877319140372e-06,
"loss": 1.197,
"step": 489
},
{
"epoch": 1.57,
"learning_rate": 9.74025033231675e-06,
"loss": 1.1706,
"step": 490
},
{
"epoch": 1.57,
"learning_rate": 9.70562646179656e-06,
"loss": 0.97,
"step": 491
},
{
"epoch": 1.57,
"learning_rate": 9.67100612297393e-06,
"loss": 1.1402,
"step": 492
},
{
"epoch": 1.58,
"learning_rate": 9.63638973120061e-06,
"loss": 1.0599,
"step": 493
},
{
"epoch": 1.58,
"learning_rate": 9.601777701781009e-06,
"loss": 0.8845,
"step": 494
},
{
"epoch": 1.58,
"learning_rate": 9.567170449967183e-06,
"loss": 1.0115,
"step": 495
},
{
"epoch": 1.59,
"learning_rate": 9.532568390953886e-06,
"loss": 1.173,
"step": 496
},
{
"epoch": 1.59,
"learning_rate": 9.497971939873567e-06,
"loss": 1.0143,
"step": 497
},
{
"epoch": 1.59,
"learning_rate": 9.463381511791386e-06,
"loss": 0.9509,
"step": 498
},
{
"epoch": 1.6,
"learning_rate": 9.428797521700254e-06,
"loss": 1.0972,
"step": 499
},
{
"epoch": 1.6,
"learning_rate": 9.394220384515836e-06,
"loss": 0.8946,
"step": 500
},
{
"epoch": 1.6,
"learning_rate": 9.35965051507159e-06,
"loss": 0.8823,
"step": 501
},
{
"epoch": 1.61,
"learning_rate": 9.325088328113769e-06,
"loss": 1.0511,
"step": 502
},
{
"epoch": 1.61,
"learning_rate": 9.290534238296462e-06,
"loss": 1.0009,
"step": 503
},
{
"epoch": 1.61,
"learning_rate": 9.255988660176613e-06,
"loss": 1.1827,
"step": 504
},
{
"epoch": 1.62,
"learning_rate": 9.221452008209057e-06,
"loss": 1.2179,
"step": 505
},
{
"epoch": 1.62,
"learning_rate": 9.186924696741519e-06,
"loss": 0.9779,
"step": 506
},
{
"epoch": 1.62,
"learning_rate": 9.152407140009684e-06,
"loss": 1.1262,
"step": 507
},
{
"epoch": 1.63,
"learning_rate": 9.117899752132193e-06,
"loss": 1.0488,
"step": 508
},
{
"epoch": 1.63,
"learning_rate": 9.083402947105688e-06,
"loss": 1.0966,
"step": 509
},
{
"epoch": 1.63,
"learning_rate": 9.04891713879986e-06,
"loss": 1.059,
"step": 510
},
{
"epoch": 1.64,
"learning_rate": 9.014442740952446e-06,
"loss": 1.1366,
"step": 511
},
{
"epoch": 1.64,
"learning_rate": 8.979980167164311e-06,
"loss": 1.007,
"step": 512
},
{
"epoch": 1.64,
"learning_rate": 8.945529830894439e-06,
"loss": 0.9041,
"step": 513
},
{
"epoch": 1.64,
"learning_rate": 8.911092145455015e-06,
"loss": 1.129,
"step": 514
},
{
"epoch": 1.65,
"learning_rate": 8.876667524006442e-06,
"loss": 1.0292,
"step": 515
},
{
"epoch": 1.65,
"learning_rate": 8.84225637955239e-06,
"loss": 0.9756,
"step": 516
},
{
"epoch": 1.65,
"learning_rate": 8.80785912493484e-06,
"loss": 0.9823,
"step": 517
},
{
"epoch": 1.66,
"learning_rate": 8.773476172829127e-06,
"loss": 1.07,
"step": 518
},
{
"epoch": 1.66,
"learning_rate": 8.739107935739004e-06,
"loss": 1.0255,
"step": 519
},
{
"epoch": 1.66,
"learning_rate": 8.704754825991684e-06,
"loss": 1.088,
"step": 520
},
{
"epoch": 1.67,
"learning_rate": 8.670417255732876e-06,
"loss": 0.9728,
"step": 521
},
{
"epoch": 1.67,
"learning_rate": 8.636095636921878e-06,
"loss": 1.1451,
"step": 522
},
{
"epoch": 1.67,
"learning_rate": 8.601790381326593e-06,
"loss": 0.9947,
"step": 523
},
{
"epoch": 1.68,
"learning_rate": 8.56750190051862e-06,
"loss": 1.0182,
"step": 524
},
{
"epoch": 1.68,
"learning_rate": 8.533230605868314e-06,
"loss": 1.123,
"step": 525
},
{
"epoch": 1.68,
"learning_rate": 8.498976908539817e-06,
"loss": 0.8985,
"step": 526
},
{
"epoch": 1.69,
"learning_rate": 8.464741219486175e-06,
"loss": 1.0555,
"step": 527
},
{
"epoch": 1.69,
"learning_rate": 8.430523949444367e-06,
"loss": 0.9661,
"step": 528
},
{
"epoch": 1.69,
"learning_rate": 8.396325508930398e-06,
"loss": 0.8877,
"step": 529
},
{
"epoch": 1.7,
"learning_rate": 8.36214630823438e-06,
"loss": 1.0659,
"step": 530
},
{
"epoch": 1.7,
"learning_rate": 8.327986757415571e-06,
"loss": 1.1536,
"step": 531
},
{
"epoch": 1.7,
"learning_rate": 8.293847266297513e-06,
"loss": 1.0392,
"step": 532
},
{
"epoch": 1.71,
"learning_rate": 8.259728244463065e-06,
"loss": 1.0649,
"step": 533
},
{
"epoch": 1.71,
"learning_rate": 8.22563010124952e-06,
"loss": 1.1273,
"step": 534
},
{
"epoch": 1.71,
"learning_rate": 8.191553245743675e-06,
"loss": 1.0693,
"step": 535
},
{
"epoch": 1.72,
"learning_rate": 8.157498086776937e-06,
"loss": 1.042,
"step": 536
},
{
"epoch": 1.72,
"learning_rate": 8.123465032920415e-06,
"loss": 1.0062,
"step": 537
},
{
"epoch": 1.72,
"learning_rate": 8.089454492480004e-06,
"loss": 1.0604,
"step": 538
},
{
"epoch": 1.72,
"learning_rate": 8.05546687349151e-06,
"loss": 0.8809,
"step": 539
},
{
"epoch": 1.73,
"learning_rate": 8.02150258371574e-06,
"loss": 1.1149,
"step": 540
},
{
"epoch": 1.73,
"learning_rate": 7.987562030633604e-06,
"loss": 1.0213,
"step": 541
},
{
"epoch": 1.73,
"learning_rate": 7.953645621441245e-06,
"loss": 1.0774,
"step": 542
},
{
"epoch": 1.74,
"learning_rate": 7.919753763045148e-06,
"loss": 1.1105,
"step": 543
},
{
"epoch": 1.74,
"learning_rate": 7.885886862057233e-06,
"loss": 1.0765,
"step": 544
},
{
"epoch": 1.74,
"learning_rate": 7.852045324790023e-06,
"loss": 1.0284,
"step": 545
},
{
"epoch": 1.75,
"learning_rate": 7.818229557251722e-06,
"loss": 0.957,
"step": 546
},
{
"epoch": 1.75,
"learning_rate": 7.784439965141381e-06,
"loss": 1.0343,
"step": 547
},
{
"epoch": 1.75,
"learning_rate": 7.750676953844011e-06,
"loss": 1.041,
"step": 548
},
{
"epoch": 1.76,
"learning_rate": 7.716940928425724e-06,
"loss": 0.9928,
"step": 549
},
{
"epoch": 1.76,
"learning_rate": 7.683232293628873e-06,
"loss": 1.047,
"step": 550
},
{
"epoch": 1.76,
"learning_rate": 7.649551453867192e-06,
"loss": 1.011,
"step": 551
},
{
"epoch": 1.77,
"learning_rate": 7.615898813220958e-06,
"loss": 0.9905,
"step": 552
},
{
"epoch": 1.77,
"learning_rate": 7.5822747754321315e-06,
"loss": 1.1501,
"step": 553
},
{
"epoch": 1.77,
"learning_rate": 7.548679743899505e-06,
"loss": 1.086,
"step": 554
},
{
"epoch": 1.78,
"learning_rate": 7.51511412167389e-06,
"loss": 0.9918,
"step": 555
},
{
"epoch": 1.78,
"learning_rate": 7.4815783114532485e-06,
"loss": 1.0353,
"step": 556
},
{
"epoch": 1.78,
"learning_rate": 7.448072715577885e-06,
"loss": 0.9666,
"step": 557
},
{
"epoch": 1.79,
"learning_rate": 7.414597736025621e-06,
"loss": 1.1618,
"step": 558
},
{
"epoch": 1.79,
"learning_rate": 7.381153774406944e-06,
"loss": 0.9998,
"step": 559
},
{
"epoch": 1.79,
"learning_rate": 7.3477412319602306e-06,
"loss": 1.0338,
"step": 560
},
{
"epoch": 1.8,
"learning_rate": 7.3143605095468915e-06,
"loss": 1.0355,
"step": 561
},
{
"epoch": 1.8,
"learning_rate": 7.281012007646595e-06,
"loss": 1.0918,
"step": 562
},
{
"epoch": 1.8,
"learning_rate": 7.24769612635245e-06,
"loss": 1.0435,
"step": 563
},
{
"epoch": 1.8,
"learning_rate": 7.214413265366194e-06,
"loss": 1.0664,
"step": 564
},
{
"epoch": 1.81,
"learning_rate": 7.181163823993418e-06,
"loss": 1.0416,
"step": 565
},
{
"epoch": 1.81,
"learning_rate": 7.147948201138761e-06,
"loss": 1.0615,
"step": 566
},
{
"epoch": 1.81,
"learning_rate": 7.114766795301138e-06,
"loss": 1.0638,
"step": 567
},
{
"epoch": 1.82,
"learning_rate": 7.081620004568943e-06,
"loss": 1.0645,
"step": 568
},
{
"epoch": 1.82,
"learning_rate": 7.048508226615282e-06,
"loss": 1.057,
"step": 569
},
{
"epoch": 1.82,
"learning_rate": 7.015431858693209e-06,
"loss": 0.9833,
"step": 570
},
{
"epoch": 1.83,
"learning_rate": 6.982391297630939e-06,
"loss": 1.0721,
"step": 571
},
{
"epoch": 1.83,
"learning_rate": 6.94938693982711e-06,
"loss": 1.0194,
"step": 572
},
{
"epoch": 1.83,
"learning_rate": 6.9164191812460194e-06,
"loss": 1.0491,
"step": 573
},
{
"epoch": 1.84,
"learning_rate": 6.883488417412858e-06,
"loss": 1.1079,
"step": 574
},
{
"epoch": 1.84,
"learning_rate": 6.850595043408997e-06,
"loss": 1.1694,
"step": 575
},
{
"epoch": 1.84,
"learning_rate": 6.817739453867209e-06,
"loss": 0.9875,
"step": 576
},
{
"epoch": 1.85,
"learning_rate": 6.784922042966968e-06,
"loss": 0.9197,
"step": 577
},
{
"epoch": 1.85,
"learning_rate": 6.752143204429709e-06,
"loss": 1.0801,
"step": 578
},
{
"epoch": 1.85,
"learning_rate": 6.719403331514085e-06,
"loss": 0.9948,
"step": 579
},
{
"epoch": 1.86,
"learning_rate": 6.686702817011277e-06,
"loss": 1.1176,
"step": 580
},
{
"epoch": 1.86,
"learning_rate": 6.654042053240275e-06,
"loss": 1.0743,
"step": 581
},
{
"epoch": 1.86,
"learning_rate": 6.6214214320431534e-06,
"loss": 1.1574,
"step": 582
},
{
"epoch": 1.87,
"learning_rate": 6.5888413447803905e-06,
"loss": 1.0499,
"step": 583
},
{
"epoch": 1.87,
"learning_rate": 6.55630218232616e-06,
"loss": 1.0335,
"step": 584
},
{
"epoch": 1.87,
"learning_rate": 6.523804335063655e-06,
"loss": 1.0262,
"step": 585
},
{
"epoch": 1.88,
"learning_rate": 6.491348192880395e-06,
"loss": 1.0413,
"step": 586
},
{
"epoch": 1.88,
"learning_rate": 6.458934145163539e-06,
"loss": 0.9775,
"step": 587
},
{
"epoch": 1.88,
"learning_rate": 6.426562580795242e-06,
"loss": 1.0768,
"step": 588
},
{
"epoch": 1.88,
"learning_rate": 6.39423388814795e-06,
"loss": 1.1318,
"step": 589
},
{
"epoch": 1.89,
"learning_rate": 6.361948455079785e-06,
"loss": 1.038,
"step": 590
},
{
"epoch": 1.89,
"learning_rate": 6.329706668929861e-06,
"loss": 1.0734,
"step": 591
},
{
"epoch": 1.89,
"learning_rate": 6.297508916513636e-06,
"loss": 1.0483,
"step": 592
},
{
"epoch": 1.9,
"learning_rate": 6.265355584118297e-06,
"loss": 1.1054,
"step": 593
},
{
"epoch": 1.9,
"learning_rate": 6.233247057498093e-06,
"loss": 0.9653,
"step": 594
},
{
"epoch": 1.9,
"learning_rate": 6.201183721869735e-06,
"loss": 1.0618,
"step": 595
},
{
"epoch": 1.91,
"learning_rate": 6.169165961907762e-06,
"loss": 1.0555,
"step": 596
},
{
"epoch": 1.91,
"learning_rate": 6.137194161739915e-06,
"loss": 1.015,
"step": 597
},
{
"epoch": 1.91,
"learning_rate": 6.105268704942555e-06,
"loss": 0.9668,
"step": 598
},
{
"epoch": 1.92,
"learning_rate": 6.073389974536037e-06,
"loss": 1.0904,
"step": 599
},
{
"epoch": 1.92,
"learning_rate": 6.041558352980126e-06,
"loss": 1.2238,
"step": 600
},
{
"epoch": 1.92,
"learning_rate": 6.009774222169409e-06,
"loss": 0.9288,
"step": 601
},
{
"epoch": 1.93,
"learning_rate": 5.978037963428702e-06,
"loss": 1.0405,
"step": 602
},
{
"epoch": 1.93,
"learning_rate": 5.946349957508499e-06,
"loss": 1.0117,
"step": 603
},
{
"epoch": 1.93,
"learning_rate": 5.91471058458037e-06,
"loss": 1.0103,
"step": 604
},
{
"epoch": 1.94,
"learning_rate": 5.8831202242324345e-06,
"loss": 0.9376,
"step": 605
},
{
"epoch": 1.94,
"learning_rate": 5.85157925546479e-06,
"loss": 0.9576,
"step": 606
},
{
"epoch": 1.94,
"learning_rate": 5.8200880566849535e-06,
"loss": 1.0823,
"step": 607
},
{
"epoch": 1.95,
"learning_rate": 5.788647005703349e-06,
"loss": 0.9424,
"step": 608
},
{
"epoch": 1.95,
"learning_rate": 5.7572564797287525e-06,
"loss": 0.9721,
"step": 609
},
{
"epoch": 1.95,
"learning_rate": 5.7259168553637815e-06,
"loss": 1.0454,
"step": 610
},
{
"epoch": 1.96,
"learning_rate": 5.6946285086003636e-06,
"loss": 1.1216,
"step": 611
},
{
"epoch": 1.96,
"learning_rate": 5.663391814815238e-06,
"loss": 1.0952,
"step": 612
},
{
"epoch": 1.96,
"learning_rate": 5.632207148765438e-06,
"loss": 1.0676,
"step": 613
},
{
"epoch": 1.96,
"learning_rate": 5.601074884583809e-06,
"loss": 1.1402,
"step": 614
},
{
"epoch": 1.97,
"learning_rate": 5.569995395774508e-06,
"loss": 1.1028,
"step": 615
},
{
"epoch": 1.97,
"learning_rate": 5.538969055208543e-06,
"loss": 1.0062,
"step": 616
},
{
"epoch": 1.97,
"learning_rate": 5.5079962351192585e-06,
"loss": 1.115,
"step": 617
},
{
"epoch": 1.98,
"learning_rate": 5.4770773070979225e-06,
"loss": 1.0301,
"step": 618
},
{
"epoch": 1.98,
"learning_rate": 5.446212642089228e-06,
"loss": 1.1297,
"step": 619
},
{
"epoch": 1.98,
"learning_rate": 5.415402610386859e-06,
"loss": 0.9464,
"step": 620
},
{
"epoch": 1.99,
"learning_rate": 5.384647581629045e-06,
"loss": 0.9658,
"step": 621
},
{
"epoch": 1.99,
"learning_rate": 5.353947924794129e-06,
"loss": 1.1283,
"step": 622
},
{
"epoch": 1.99,
"learning_rate": 5.323304008196133e-06,
"loss": 1.1993,
"step": 623
},
{
"epoch": 2.0,
"learning_rate": 5.292716199480354e-06,
"loss": 0.943,
"step": 624
},
{
"epoch": 2.0,
"learning_rate": 5.262184865618938e-06,
"loss": 0.9043,
"step": 625
},
{
"epoch": 2.0,
"learning_rate": 5.231710372906482e-06,
"loss": 0.7984,
"step": 626
},
{
"epoch": 2.01,
"learning_rate": 5.201293086955646e-06,
"loss": 0.8364,
"step": 627
},
{
"epoch": 2.01,
"learning_rate": 5.170933372692752e-06,
"loss": 0.7504,
"step": 628
},
{
"epoch": 2.01,
"learning_rate": 5.140631594353434e-06,
"loss": 0.8231,
"step": 629
},
{
"epoch": 2.02,
"learning_rate": 5.110388115478222e-06,
"loss": 0.815,
"step": 630
},
{
"epoch": 2.02,
"learning_rate": 5.080203298908239e-06,
"loss": 0.8905,
"step": 631
},
{
"epoch": 2.02,
"learning_rate": 5.050077506780783e-06,
"loss": 0.8251,
"step": 632
},
{
"epoch": 2.03,
"learning_rate": 5.020011100525047e-06,
"loss": 0.851,
"step": 633
},
{
"epoch": 2.03,
"learning_rate": 4.990004440857735e-06,
"loss": 0.9853,
"step": 634
},
{
"epoch": 2.03,
"learning_rate": 4.960057887778754e-06,
"loss": 0.8867,
"step": 635
},
{
"epoch": 2.04,
"learning_rate": 4.930171800566893e-06,
"loss": 0.8327,
"step": 636
},
{
"epoch": 2.04,
"learning_rate": 4.900346537775513e-06,
"loss": 0.8015,
"step": 637
},
{
"epoch": 2.04,
"learning_rate": 4.870582457228239e-06,
"loss": 0.7943,
"step": 638
},
{
"epoch": 2.04,
"learning_rate": 4.840879916014683e-06,
"loss": 0.8705,
"step": 639
},
{
"epoch": 2.05,
"learning_rate": 4.811239270486139e-06,
"loss": 0.9057,
"step": 640
},
{
"epoch": 2.05,
"learning_rate": 4.781660876251322e-06,
"loss": 0.795,
"step": 641
},
{
"epoch": 2.05,
"learning_rate": 4.752145088172094e-06,
"loss": 0.8026,
"step": 642
},
{
"epoch": 2.06,
"learning_rate": 4.722692260359211e-06,
"loss": 0.8117,
"step": 643
},
{
"epoch": 2.06,
"learning_rate": 4.693302746168088e-06,
"loss": 0.8619,
"step": 644
},
{
"epoch": 2.06,
"learning_rate": 4.663976898194516e-06,
"loss": 0.8921,
"step": 645
},
{
"epoch": 2.07,
"learning_rate": 4.634715068270491e-06,
"loss": 0.8118,
"step": 646
},
{
"epoch": 2.07,
"learning_rate": 4.605517607459938e-06,
"loss": 0.8502,
"step": 647
},
{
"epoch": 2.07,
"learning_rate": 4.576384866054546e-06,
"loss": 0.7814,
"step": 648
},
{
"epoch": 2.08,
"learning_rate": 4.54731719356953e-06,
"loss": 0.668,
"step": 649
},
{
"epoch": 2.08,
"learning_rate": 4.5183149387394566e-06,
"loss": 0.7598,
"step": 650
},
{
"epoch": 2.08,
"learning_rate": 4.489378449514051e-06,
"loss": 0.7201,
"step": 651
},
{
"epoch": 2.09,
"learning_rate": 4.460508073054033e-06,
"loss": 0.8612,
"step": 652
},
{
"epoch": 2.09,
"learning_rate": 4.431704155726936e-06,
"loss": 0.8817,
"step": 653
},
{
"epoch": 2.09,
"learning_rate": 4.402967043102974e-06,
"loss": 0.8476,
"step": 654
},
{
"epoch": 2.1,
"learning_rate": 4.374297079950872e-06,
"loss": 0.8226,
"step": 655
},
{
"epoch": 2.1,
"learning_rate": 4.345694610233744e-06,
"loss": 0.8367,
"step": 656
},
{
"epoch": 2.1,
"learning_rate": 4.3171599771049625e-06,
"loss": 0.7801,
"step": 657
},
{
"epoch": 2.11,
"learning_rate": 4.2886935229040375e-06,
"loss": 0.7861,
"step": 658
},
{
"epoch": 2.11,
"learning_rate": 4.26029558915253e-06,
"loss": 0.9223,
"step": 659
},
{
"epoch": 2.11,
"learning_rate": 4.23196651654991e-06,
"loss": 0.7652,
"step": 660
},
{
"epoch": 2.12,
"learning_rate": 4.2037066449695275e-06,
"loss": 0.7641,
"step": 661
},
{
"epoch": 2.12,
"learning_rate": 4.175516313454485e-06,
"loss": 0.8669,
"step": 662
},
{
"epoch": 2.12,
"learning_rate": 4.1473958602135956e-06,
"loss": 0.9552,
"step": 663
},
{
"epoch": 2.12,
"learning_rate": 4.11934562261732e-06,
"loss": 0.8949,
"step": 664
},
{
"epoch": 2.13,
"learning_rate": 4.091365937193719e-06,
"loss": 0.76,
"step": 665
},
{
"epoch": 2.13,
"learning_rate": 4.063457139624407e-06,
"loss": 0.8771,
"step": 666
},
{
"epoch": 2.13,
"learning_rate": 4.035619564740555e-06,
"loss": 0.8563,
"step": 667
},
{
"epoch": 2.14,
"learning_rate": 4.00785354651882e-06,
"loss": 0.7991,
"step": 668
},
{
"epoch": 2.14,
"learning_rate": 3.980159418077403e-06,
"loss": 0.8959,
"step": 669
},
{
"epoch": 2.14,
"learning_rate": 3.952537511671988e-06,
"loss": 0.7973,
"step": 670
},
{
"epoch": 2.15,
"learning_rate": 3.924988158691812e-06,
"loss": 0.8514,
"step": 671
},
{
"epoch": 2.15,
"learning_rate": 3.897511689655653e-06,
"loss": 0.7774,
"step": 672
},
{
"epoch": 2.15,
"learning_rate": 3.870108434207877e-06,
"loss": 0.8148,
"step": 673
},
{
"epoch": 2.16,
"learning_rate": 3.842778721114482e-06,
"loss": 0.8981,
"step": 674
},
{
"epoch": 2.16,
"learning_rate": 3.815522878259153e-06,
"loss": 0.7853,
"step": 675
},
{
"epoch": 2.16,
"learning_rate": 3.7883412326393352e-06,
"loss": 0.7976,
"step": 676
},
{
"epoch": 2.17,
"learning_rate": 3.7612341103622984e-06,
"loss": 0.8359,
"step": 677
},
{
"epoch": 2.17,
"learning_rate": 3.7342018366412336e-06,
"loss": 0.7882,
"step": 678
},
{
"epoch": 2.17,
"learning_rate": 3.7072447357913477e-06,
"loss": 0.8734,
"step": 679
},
{
"epoch": 2.18,
"learning_rate": 3.6803631312259724e-06,
"loss": 0.951,
"step": 680
},
{
"epoch": 2.18,
"learning_rate": 3.653557345452685e-06,
"loss": 0.8285,
"step": 681
},
{
"epoch": 2.18,
"learning_rate": 3.626827700069452e-06,
"loss": 0.8321,
"step": 682
},
{
"epoch": 2.19,
"learning_rate": 3.600174515760733e-06,
"loss": 0.8634,
"step": 683
},
{
"epoch": 2.19,
"learning_rate": 3.573598112293687e-06,
"loss": 0.9543,
"step": 684
},
{
"epoch": 2.19,
"learning_rate": 3.547098808514279e-06,
"loss": 0.8536,
"step": 685
},
{
"epoch": 2.2,
"learning_rate": 3.52067692234351e-06,
"loss": 0.891,
"step": 686
},
{
"epoch": 2.2,
"learning_rate": 3.4943327707735586e-06,
"loss": 0.8742,
"step": 687
},
{
"epoch": 2.2,
"learning_rate": 3.468066669864004e-06,
"loss": 0.8274,
"step": 688
},
{
"epoch": 2.2,
"learning_rate": 3.44187893473802e-06,
"loss": 0.8308,
"step": 689
},
{
"epoch": 2.21,
"learning_rate": 3.415769879578601e-06,
"loss": 0.7936,
"step": 690
},
{
"epoch": 2.21,
"learning_rate": 3.3897398176247984e-06,
"loss": 0.8117,
"step": 691
},
{
"epoch": 2.21,
"learning_rate": 3.363789061167949e-06,
"loss": 0.8561,
"step": 692
},
{
"epoch": 2.22,
"learning_rate": 3.337917921547934e-06,
"loss": 0.7836,
"step": 693
},
{
"epoch": 2.22,
"learning_rate": 3.312126709149447e-06,
"loss": 0.8442,
"step": 694
},
{
"epoch": 2.22,
"learning_rate": 3.286415733398276e-06,
"loss": 0.8044,
"step": 695
},
{
"epoch": 2.23,
"learning_rate": 3.2607853027575643e-06,
"loss": 0.8329,
"step": 696
},
{
"epoch": 2.23,
"learning_rate": 3.2352357247241517e-06,
"loss": 0.8418,
"step": 697
},
{
"epoch": 2.23,
"learning_rate": 3.2097673058248378e-06,
"loss": 0.8355,
"step": 698
},
{
"epoch": 2.24,
"learning_rate": 3.1843803516127537e-06,
"loss": 0.8381,
"step": 699
},
{
"epoch": 2.24,
"learning_rate": 3.159075166663653e-06,
"loss": 0.8766,
"step": 700
},
{
"epoch": 2.24,
"learning_rate": 3.1338520545722852e-06,
"loss": 0.6602,
"step": 701
},
{
"epoch": 2.25,
"learning_rate": 3.1087113179487394e-06,
"loss": 0.8645,
"step": 702
},
{
"epoch": 2.25,
"learning_rate": 3.0836532584148237e-06,
"loss": 0.8401,
"step": 703
},
{
"epoch": 2.25,
"learning_rate": 3.058678176600436e-06,
"loss": 0.8713,
"step": 704
},
{
"epoch": 2.26,
"learning_rate": 3.0337863721399694e-06,
"loss": 0.8039,
"step": 705
},
{
"epoch": 2.26,
"learning_rate": 3.008978143668707e-06,
"loss": 0.9484,
"step": 706
},
{
"epoch": 2.26,
"learning_rate": 2.9842537888192414e-06,
"loss": 0.8308,
"step": 707
},
{
"epoch": 2.27,
"learning_rate": 2.959613604217908e-06,
"loss": 0.8186,
"step": 708
},
{
"epoch": 2.27,
"learning_rate": 2.9350578854812194e-06,
"loss": 0.7842,
"step": 709
},
{
"epoch": 2.27,
"learning_rate": 2.9105869272123366e-06,
"loss": 0.917,
"step": 710
},
{
"epoch": 2.28,
"learning_rate": 2.886201022997497e-06,
"loss": 0.764,
"step": 711
},
{
"epoch": 2.28,
"learning_rate": 2.8619004654025418e-06,
"loss": 0.7358,
"step": 712
},
{
"epoch": 2.28,
"learning_rate": 2.837685545969359e-06,
"loss": 0.8287,
"step": 713
},
{
"epoch": 2.28,
"learning_rate": 2.8135565552124224e-06,
"loss": 0.7697,
"step": 714
},
{
"epoch": 2.29,
"learning_rate": 2.789513782615283e-06,
"loss": 0.8188,
"step": 715
},
{
"epoch": 2.29,
"learning_rate": 2.7655575166271067e-06,
"loss": 0.7441,
"step": 716
},
{
"epoch": 2.29,
"learning_rate": 2.7416880446592087e-06,
"loss": 0.755,
"step": 717
},
{
"epoch": 2.3,
"learning_rate": 2.717905653081608e-06,
"loss": 0.8617,
"step": 718
},
{
"epoch": 2.3,
"learning_rate": 2.69421062721959e-06,
"loss": 0.8404,
"step": 719
},
{
"epoch": 2.3,
"learning_rate": 2.6706032513502913e-06,
"loss": 0.9404,
"step": 720
},
{
"epoch": 2.31,
"learning_rate": 2.6470838086992724e-06,
"loss": 0.8623,
"step": 721
},
{
"epoch": 2.31,
"learning_rate": 2.623652581437135e-06,
"loss": 0.8585,
"step": 722
},
{
"epoch": 2.31,
"learning_rate": 2.6003098506761316e-06,
"loss": 0.9078,
"step": 723
},
{
"epoch": 2.32,
"learning_rate": 2.577055896466788e-06,
"loss": 0.8267,
"step": 724
},
{
"epoch": 2.32,
"learning_rate": 2.5538909977945593e-06,
"loss": 0.786,
"step": 725
},
{
"epoch": 2.32,
"learning_rate": 2.5308154325764543e-06,
"loss": 0.8536,
"step": 726
},
{
"epoch": 2.33,
"learning_rate": 2.5078294776577372e-06,
"loss": 0.8552,
"step": 727
},
{
"epoch": 2.33,
"learning_rate": 2.48493340880857e-06,
"loss": 0.8809,
"step": 728
},
{
"epoch": 2.33,
"learning_rate": 2.462127500720737e-06,
"loss": 0.8399,
"step": 729
},
{
"epoch": 2.34,
"learning_rate": 2.4394120270043233e-06,
"loss": 0.7897,
"step": 730
},
{
"epoch": 2.34,
"learning_rate": 2.4167872601844476e-06,
"loss": 0.959,
"step": 731
},
{
"epoch": 2.34,
"learning_rate": 2.3942534716979827e-06,
"loss": 0.8263,
"step": 732
},
{
"epoch": 2.35,
"learning_rate": 2.371810931890316e-06,
"loss": 0.8896,
"step": 733
},
{
"epoch": 2.35,
"learning_rate": 2.349459910012075e-06,
"loss": 0.8499,
"step": 734
},
{
"epoch": 2.35,
"learning_rate": 2.327200674215937e-06,
"loss": 0.7637,
"step": 735
},
{
"epoch": 2.36,
"learning_rate": 2.3050334915533713e-06,
"loss": 0.8722,
"step": 736
},
{
"epoch": 2.36,
"learning_rate": 2.28295862797147e-06,
"loss": 0.8261,
"step": 737
},
{
"epoch": 2.36,
"learning_rate": 2.260976348309737e-06,
"loss": 0.7776,
"step": 738
},
{
"epoch": 2.36,
"learning_rate": 2.239086916296914e-06,
"loss": 0.8082,
"step": 739
},
{
"epoch": 2.37,
"learning_rate": 2.217290594547822e-06,
"loss": 0.8048,
"step": 740
},
{
"epoch": 2.37,
"learning_rate": 2.1955876445602008e-06,
"loss": 0.8619,
"step": 741
},
{
"epoch": 2.37,
"learning_rate": 2.1739783267115888e-06,
"loss": 0.8038,
"step": 742
},
{
"epoch": 2.38,
"learning_rate": 2.1524629002561803e-06,
"loss": 0.8358,
"step": 743
},
{
"epoch": 2.38,
"learning_rate": 2.1310416233217246e-06,
"loss": 0.7924,
"step": 744
},
{
"epoch": 2.38,
"learning_rate": 2.1097147529064286e-06,
"loss": 0.7898,
"step": 745
},
{
"epoch": 2.39,
"learning_rate": 2.088482544875873e-06,
"loss": 0.7631,
"step": 746
},
{
"epoch": 2.39,
"learning_rate": 2.067345253959938e-06,
"loss": 0.8176,
"step": 747
},
{
"epoch": 2.39,
"learning_rate": 2.046303133749764e-06,
"loss": 0.8491,
"step": 748
},
{
"epoch": 2.4,
"learning_rate": 2.0253564366946764e-06,
"loss": 0.7257,
"step": 749
},
{
"epoch": 2.4,
"learning_rate": 2.0045054140992002e-06,
"loss": 0.8799,
"step": 750
},
{
"epoch": 2.4,
"learning_rate": 1.98375031612e-06,
"loss": 0.9011,
"step": 751
},
{
"epoch": 2.41,
"learning_rate": 1.96309139176292e-06,
"loss": 0.9194,
"step": 752
},
{
"epoch": 2.41,
"learning_rate": 1.942528888879964e-06,
"loss": 0.8291,
"step": 753
},
{
"epoch": 2.41,
"learning_rate": 1.922063054166341e-06,
"loss": 0.7967,
"step": 754
},
{
"epoch": 2.42,
"learning_rate": 1.901694133157499e-06,
"loss": 0.8713,
"step": 755
},
{
"epoch": 2.42,
"learning_rate": 1.8814223702261757e-06,
"loss": 0.7713,
"step": 756
},
{
"epoch": 2.42,
"learning_rate": 1.8612480085794804e-06,
"loss": 0.878,
"step": 757
},
{
"epoch": 2.43,
"learning_rate": 1.8411712902559597e-06,
"loss": 0.7099,
"step": 758
},
{
"epoch": 2.43,
"learning_rate": 1.8211924561227001e-06,
"loss": 0.7599,
"step": 759
},
{
"epoch": 2.43,
"learning_rate": 1.8013117458724416e-06,
"loss": 0.708,
"step": 760
},
{
"epoch": 2.44,
"learning_rate": 1.7815293980206993e-06,
"loss": 0.837,
"step": 761
},
{
"epoch": 2.44,
"learning_rate": 1.7618456499028968e-06,
"loss": 0.8756,
"step": 762
},
{
"epoch": 2.44,
"learning_rate": 1.7422607376715362e-06,
"loss": 0.6622,
"step": 763
},
{
"epoch": 2.44,
"learning_rate": 1.7227748962933343e-06,
"loss": 0.7935,
"step": 764
},
{
"epoch": 2.45,
"learning_rate": 1.7033883595464407e-06,
"loss": 0.9484,
"step": 765
},
{
"epoch": 2.45,
"learning_rate": 1.684101360017596e-06,
"loss": 0.8127,
"step": 766
},
{
"epoch": 2.45,
"learning_rate": 1.6649141290993765e-06,
"loss": 0.7279,
"step": 767
},
{
"epoch": 2.46,
"learning_rate": 1.6458268969873892e-06,
"loss": 0.8932,
"step": 768
},
{
"epoch": 2.46,
"learning_rate": 1.6268398926775286e-06,
"loss": 0.8146,
"step": 769
},
{
"epoch": 2.46,
"learning_rate": 1.6079533439632166e-06,
"loss": 0.8509,
"step": 770
},
{
"epoch": 2.47,
"learning_rate": 1.5891674774326848e-06,
"loss": 0.7943,
"step": 771
},
{
"epoch": 2.47,
"learning_rate": 1.5704825184662397e-06,
"loss": 0.8581,
"step": 772
},
{
"epoch": 2.47,
"learning_rate": 1.5518986912335686e-06,
"loss": 0.8402,
"step": 773
},
{
"epoch": 2.48,
"learning_rate": 1.5334162186910474e-06,
"loss": 0.8229,
"step": 774
},
{
"epoch": 2.48,
"learning_rate": 1.5150353225790626e-06,
"loss": 0.8608,
"step": 775
},
{
"epoch": 2.48,
"learning_rate": 1.4967562234193655e-06,
"loss": 0.7602,
"step": 776
},
{
"epoch": 2.49,
"learning_rate": 1.4785791405123995e-06,
"loss": 0.8029,
"step": 777
},
{
"epoch": 2.49,
"learning_rate": 1.4605042919347e-06,
"loss": 0.82,
"step": 778
},
{
"epoch": 2.49,
"learning_rate": 1.4425318945362488e-06,
"loss": 0.8683,
"step": 779
},
{
"epoch": 2.5,
"learning_rate": 1.4246621639378998e-06,
"loss": 0.8857,
"step": 780
},
{
"epoch": 2.5,
"learning_rate": 1.406895314528771e-06,
"loss": 0.7438,
"step": 781
},
{
"epoch": 2.5,
"learning_rate": 1.389231559463684e-06,
"loss": 0.7489,
"step": 782
},
{
"epoch": 2.51,
"learning_rate": 1.3716711106606007e-06,
"loss": 0.8991,
"step": 783
},
{
"epoch": 2.51,
"learning_rate": 1.3542141787980855e-06,
"loss": 0.7701,
"step": 784
},
{
"epoch": 2.51,
"learning_rate": 1.3368609733127714e-06,
"loss": 0.8547,
"step": 785
},
{
"epoch": 2.52,
"learning_rate": 1.3196117023968613e-06,
"loss": 0.8242,
"step": 786
},
{
"epoch": 2.52,
"learning_rate": 1.3024665729956054e-06,
"loss": 0.8078,
"step": 787
},
{
"epoch": 2.52,
"learning_rate": 1.2854257908048483e-06,
"loss": 0.7044,
"step": 788
},
{
"epoch": 2.52,
"learning_rate": 1.2684895602685377e-06,
"loss": 0.8678,
"step": 789
},
{
"epoch": 2.53,
"learning_rate": 1.2516580845762804e-06,
"loss": 0.8452,
"step": 790
},
{
"epoch": 2.53,
"learning_rate": 1.2349315656609085e-06,
"loss": 0.8298,
"step": 791
},
{
"epoch": 2.53,
"learning_rate": 1.218310204196046e-06,
"loss": 0.7758,
"step": 792
},
{
"epoch": 2.54,
"learning_rate": 1.201794199593721e-06,
"loss": 0.8743,
"step": 793
},
{
"epoch": 2.54,
"learning_rate": 1.1853837500019406e-06,
"loss": 0.8386,
"step": 794
},
{
"epoch": 2.54,
"learning_rate": 1.169079052302352e-06,
"loss": 0.866,
"step": 795
},
{
"epoch": 2.55,
"learning_rate": 1.1528803021078505e-06,
"loss": 0.8144,
"step": 796
},
{
"epoch": 2.55,
"learning_rate": 1.1367876937602474e-06,
"loss": 0.8112,
"step": 797
},
{
"epoch": 2.55,
"learning_rate": 1.120801420327935e-06,
"loss": 0.7749,
"step": 798
},
{
"epoch": 2.56,
"learning_rate": 1.1049216736035673e-06,
"loss": 0.7661,
"step": 799
},
{
"epoch": 2.56,
"learning_rate": 1.0891486441017652e-06,
"loss": 0.953,
"step": 800
},
{
"epoch": 2.56,
"learning_rate": 1.07348252105683e-06,
"loss": 0.896,
"step": 801
},
{
"epoch": 2.57,
"learning_rate": 1.0579234924204608e-06,
"loss": 0.9156,
"step": 802
},
{
"epoch": 2.57,
"learning_rate": 1.04247174485952e-06,
"loss": 0.8013,
"step": 803
},
{
"epoch": 2.57,
"learning_rate": 1.0271274637537764e-06,
"loss": 0.8123,
"step": 804
},
{
"epoch": 2.58,
"learning_rate": 1.0118908331936915e-06,
"loss": 0.8831,
"step": 805
},
{
"epoch": 2.58,
"learning_rate": 9.96762035978206e-07,
"loss": 0.816,
"step": 806
},
{
"epoch": 2.58,
"learning_rate": 9.817412536125449e-07,
"loss": 0.7784,
"step": 807
},
{
"epoch": 2.59,
"learning_rate": 9.66828666306049e-07,
"loss": 0.8352,
"step": 808
},
{
"epoch": 2.59,
"learning_rate": 9.520244529700041e-07,
"loss": 0.8662,
"step": 809
},
{
"epoch": 2.59,
"learning_rate": 9.37328791215496e-07,
"loss": 0.9414,
"step": 810
},
{
"epoch": 2.6,
"learning_rate": 9.227418573512825e-07,
"loss": 0.8586,
"step": 811
},
{
"epoch": 2.6,
"learning_rate": 9.082638263816756e-07,
"loss": 0.7699,
"step": 812
},
{
"epoch": 2.6,
"learning_rate": 8.938948720044416e-07,
"loss": 0.6999,
"step": 813
},
{
"epoch": 2.6,
"learning_rate": 8.796351666087266e-07,
"loss": 0.8929,
"step": 814
},
{
"epoch": 2.61,
"learning_rate": 8.654848812729655e-07,
"loss": 0.7612,
"step": 815
},
{
"epoch": 2.61,
"learning_rate": 8.514441857628619e-07,
"loss": 0.7071,
"step": 816
},
{
"epoch": 2.61,
"learning_rate": 8.375132485293158e-07,
"loss": 0.8244,
"step": 817
},
{
"epoch": 2.62,
"learning_rate": 8.236922367064359e-07,
"loss": 0.933,
"step": 818
},
{
"epoch": 2.62,
"learning_rate": 8.099813161095094e-07,
"loss": 0.7496,
"step": 819
},
{
"epoch": 2.62,
"learning_rate": 7.963806512330275e-07,
"loss": 0.7874,
"step": 820
},
{
"epoch": 2.63,
"learning_rate": 7.828904052487019e-07,
"loss": 0.7135,
"step": 821
},
{
"epoch": 2.63,
"learning_rate": 7.69510740003514e-07,
"loss": 0.8509,
"step": 822
},
{
"epoch": 2.63,
"learning_rate": 7.562418160177765e-07,
"loss": 0.8332,
"step": 823
},
{
"epoch": 2.64,
"learning_rate": 7.430837924831958e-07,
"loss": 0.8783,
"step": 824
},
{
"epoch": 2.64,
"learning_rate": 7.300368272609692e-07,
"loss": 0.8069,
"step": 825
},
{
"epoch": 2.64,
"learning_rate": 7.171010768798925e-07,
"loss": 0.8632,
"step": 826
},
{
"epoch": 2.65,
"learning_rate": 7.042766965344782e-07,
"loss": 0.789,
"step": 827
},
{
"epoch": 2.65,
"learning_rate": 6.915638400830959e-07,
"loss": 0.7937,
"step": 828
},
{
"epoch": 2.65,
"learning_rate": 6.789626600461307e-07,
"loss": 0.786,
"step": 829
},
{
"epoch": 2.66,
"learning_rate": 6.664733076041374e-07,
"loss": 0.7508,
"step": 830
},
{
"epoch": 2.66,
"learning_rate": 6.540959325960494e-07,
"loss": 0.8023,
"step": 831
},
{
"epoch": 2.66,
"learning_rate": 6.418306835173605e-07,
"loss": 0.6802,
"step": 832
},
{
"epoch": 2.67,
"learning_rate": 6.296777075183602e-07,
"loss": 0.6633,
"step": 833
},
{
"epoch": 2.67,
"learning_rate": 6.176371504023537e-07,
"loss": 0.9035,
"step": 834
},
{
"epoch": 2.67,
"learning_rate": 6.057091566239226e-07,
"loss": 0.7717,
"step": 835
},
{
"epoch": 2.68,
"learning_rate": 5.938938692871887e-07,
"loss": 0.5934,
"step": 836
},
{
"epoch": 2.68,
"learning_rate": 5.821914301440956e-07,
"loss": 0.9244,
"step": 837
},
{
"epoch": 2.68,
"learning_rate": 5.70601979592711e-07,
"loss": 0.8018,
"step": 838
},
{
"epoch": 2.68,
"learning_rate": 5.591256566755399e-07,
"loss": 0.8674,
"step": 839
},
{
"epoch": 2.69,
"learning_rate": 5.477625990778579e-07,
"loss": 0.8433,
"step": 840
},
{
"epoch": 2.69,
"learning_rate": 5.365129431260574e-07,
"loss": 0.7924,
"step": 841
},
{
"epoch": 2.69,
"learning_rate": 5.253768237860146e-07,
"loss": 0.7547,
"step": 842
},
{
"epoch": 2.7,
"learning_rate": 5.143543746614688e-07,
"loss": 0.7739,
"step": 843
},
{
"epoch": 2.7,
"learning_rate": 5.034457279924221e-07,
"loss": 0.8245,
"step": 844
},
{
"epoch": 2.7,
"learning_rate": 4.926510146535434e-07,
"loss": 0.8931,
"step": 845
},
{
"epoch": 2.71,
"learning_rate": 4.819703641526141e-07,
"loss": 0.826,
"step": 846
},
{
"epoch": 2.71,
"learning_rate": 4.71403904628962e-07,
"loss": 0.9297,
"step": 847
},
{
"epoch": 2.71,
"learning_rate": 4.6095176285192556e-07,
"loss": 0.9613,
"step": 848
},
{
"epoch": 2.72,
"learning_rate": 4.506140642193391e-07,
"loss": 0.8248,
"step": 849
},
{
"epoch": 2.72,
"learning_rate": 4.403909327560207e-07,
"loss": 0.8495,
"step": 850
},
{
"epoch": 2.72,
"learning_rate": 4.3028249111228824e-07,
"loss": 0.8472,
"step": 851
},
{
"epoch": 2.73,
"learning_rate": 4.202888605624944e-07,
"loss": 0.892,
"step": 852
},
{
"epoch": 2.73,
"learning_rate": 4.104101610035527e-07,
"loss": 0.7369,
"step": 853
},
{
"epoch": 2.73,
"learning_rate": 4.006465109535218e-07,
"loss": 0.721,
"step": 854
},
{
"epoch": 2.74,
"learning_rate": 3.909980275501679e-07,
"loss": 0.7539,
"step": 855
},
{
"epoch": 2.74,
"learning_rate": 3.8146482654956574e-07,
"loss": 0.77,
"step": 856
},
{
"epoch": 2.74,
"learning_rate": 3.720470223247097e-07,
"loss": 0.8977,
"step": 857
},
{
"epoch": 2.75,
"learning_rate": 3.6274472786413605e-07,
"loss": 0.7508,
"step": 858
},
{
"epoch": 2.75,
"learning_rate": 3.535580547705797e-07,
"loss": 0.9097,
"step": 859
},
{
"epoch": 2.75,
"learning_rate": 3.4448711325961834e-07,
"loss": 0.8055,
"step": 860
},
{
"epoch": 2.76,
"learning_rate": 3.355320121583672e-07,
"loss": 0.7388,
"step": 861
},
{
"epoch": 2.76,
"learning_rate": 3.266928589041607e-07,
"loss": 0.8352,
"step": 862
},
{
"epoch": 2.76,
"learning_rate": 3.179697595432707e-07,
"loss": 0.8735,
"step": 863
},
{
"epoch": 2.76,
"learning_rate": 3.093628187296294e-07,
"loss": 0.8795,
"step": 864
},
{
"epoch": 2.77,
"learning_rate": 3.008721397235781e-07,
"loss": 0.8442,
"step": 865
},
{
"epoch": 2.77,
"learning_rate": 2.924978243906251e-07,
"loss": 0.8908,
"step": 866
},
{
"epoch": 2.77,
"learning_rate": 2.8423997320022765e-07,
"loss": 0.8749,
"step": 867
},
{
"epoch": 2.78,
"learning_rate": 2.760986852245784e-07,
"loss": 0.7929,
"step": 868
},
{
"epoch": 2.78,
"learning_rate": 2.680740581374286e-07,
"loss": 0.774,
"step": 869
},
{
"epoch": 2.78,
"learning_rate": 2.6016618821290583e-07,
"loss": 0.9041,
"step": 870
},
{
"epoch": 2.79,
"learning_rate": 2.5237517032436374e-07,
"loss": 0.7084,
"step": 871
},
{
"epoch": 2.79,
"learning_rate": 2.4470109794324405e-07,
"loss": 0.745,
"step": 872
},
{
"epoch": 2.79,
"learning_rate": 2.371440631379529e-07,
"loss": 0.8629,
"step": 873
},
{
"epoch": 2.8,
"learning_rate": 2.297041565727598e-07,
"loss": 0.8275,
"step": 874
},
{
"epoch": 2.8,
"learning_rate": 2.2238146750670264e-07,
"loss": 0.7469,
"step": 875
},
{
"epoch": 2.8,
"learning_rate": 2.1517608379252985e-07,
"loss": 0.7013,
"step": 876
},
{
"epoch": 2.81,
"learning_rate": 2.0808809187563118e-07,
"loss": 0.8515,
"step": 877
},
{
"epoch": 2.81,
"learning_rate": 2.011175767930118e-07,
"loss": 0.8224,
"step": 878
},
{
"epoch": 2.81,
"learning_rate": 1.942646221722655e-07,
"loss": 0.8434,
"step": 879
},
{
"epoch": 2.82,
"learning_rate": 1.8752931023057753e-07,
"loss": 0.9319,
"step": 880
},
{
"epoch": 2.82,
"learning_rate": 1.8091172177372994e-07,
"loss": 0.7354,
"step": 881
},
{
"epoch": 2.82,
"learning_rate": 1.744119361951413e-07,
"loss": 0.8801,
"step": 882
},
{
"epoch": 2.83,
"learning_rate": 1.6803003147490727e-07,
"loss": 0.7487,
"step": 883
},
{
"epoch": 2.83,
"learning_rate": 1.617660841788682e-07,
"loss": 0.6959,
"step": 884
},
{
"epoch": 2.83,
"learning_rate": 1.5562016945769088e-07,
"loss": 0.7871,
"step": 885
},
{
"epoch": 2.84,
"learning_rate": 1.4959236104596265e-07,
"loss": 0.784,
"step": 886
},
{
"epoch": 2.84,
"learning_rate": 1.4368273126131428e-07,
"loss": 0.7408,
"step": 887
},
{
"epoch": 2.84,
"learning_rate": 1.378913510035429e-07,
"loss": 0.7482,
"step": 888
},
{
"epoch": 2.84,
"learning_rate": 1.3221828975377382e-07,
"loss": 0.8331,
"step": 889
},
{
"epoch": 2.85,
"learning_rate": 1.266636155736145e-07,
"loss": 0.8149,
"step": 890
},
{
"epoch": 2.85,
"learning_rate": 1.21227395104343e-07,
"loss": 0.813,
"step": 891
},
{
"epoch": 2.85,
"learning_rate": 1.1590969356611081e-07,
"loss": 0.7902,
"step": 892
},
{
"epoch": 2.86,
"learning_rate": 1.1071057475715797e-07,
"loss": 0.7681,
"step": 893
},
{
"epoch": 2.86,
"learning_rate": 1.0563010105304694e-07,
"loss": 0.8899,
"step": 894
},
{
"epoch": 2.86,
"learning_rate": 1.0066833340591664e-07,
"loss": 0.8155,
"step": 895
},
{
"epoch": 2.87,
"learning_rate": 9.582533134374849e-08,
"loss": 0.8696,
"step": 896
},
{
"epoch": 2.87,
"learning_rate": 9.110115296965482e-08,
"loss": 0.8154,
"step": 897
},
{
"epoch": 2.87,
"learning_rate": 8.64958549611783e-08,
"loss": 0.8744,
"step": 898
},
{
"epoch": 2.88,
"learning_rate": 8.200949256961687e-08,
"loss": 0.8758,
"step": 899
},
{
"epoch": 2.88,
"learning_rate": 7.764211961935664e-08,
"loss": 0.835,
"step": 900
},
{
"epoch": 2.88,
"learning_rate": 7.339378850722889e-08,
"loss": 0.8079,
"step": 901
},
{
"epoch": 2.89,
"learning_rate": 6.92645502018785e-08,
"loss": 0.8294,
"step": 902
},
{
"epoch": 2.89,
"learning_rate": 6.525445424315546e-08,
"loss": 0.9074,
"step": 903
},
{
"epoch": 2.89,
"learning_rate": 6.136354874151874e-08,
"loss": 0.7819,
"step": 904
},
{
"epoch": 2.9,
"learning_rate": 5.7591880377459995e-08,
"loss": 0.7962,
"step": 905
},
{
"epoch": 2.9,
"learning_rate": 5.393949440094415e-08,
"loss": 0.7038,
"step": 906
},
{
"epoch": 2.9,
"learning_rate": 5.040643463086303e-08,
"loss": 0.7854,
"step": 907
},
{
"epoch": 2.91,
"learning_rate": 4.6992743454513654e-08,
"loss": 0.7814,
"step": 908
},
{
"epoch": 2.91,
"learning_rate": 4.369846182708748e-08,
"loss": 0.8807,
"step": 909
},
{
"epoch": 2.91,
"learning_rate": 4.052362927118303e-08,
"loss": 0.783,
"step": 910
},
{
"epoch": 2.92,
"learning_rate": 3.746828387632184e-08,
"loss": 0.797,
"step": 911
},
{
"epoch": 2.92,
"learning_rate": 3.4532462298506596e-08,
"loss": 0.9004,
"step": 912
},
{
"epoch": 2.92,
"learning_rate": 3.17161997597637e-08,
"loss": 0.7802,
"step": 913
},
{
"epoch": 2.92,
"learning_rate": 2.9019530047736944e-08,
"loss": 0.8022,
"step": 914
},
{
"epoch": 2.93,
"learning_rate": 2.6442485515273397e-08,
"loss": 0.7636,
"step": 915
},
{
"epoch": 2.93,
"learning_rate": 2.3985097080033715e-08,
"loss": 0.8552,
"step": 916
},
{
"epoch": 2.93,
"learning_rate": 2.1647394224129092e-08,
"loss": 0.7889,
"step": 917
},
{
"epoch": 2.94,
"learning_rate": 1.942940499376045e-08,
"loss": 0.7047,
"step": 918
},
{
"epoch": 2.94,
"learning_rate": 1.733115599888202e-08,
"loss": 0.8248,
"step": 919
},
{
"epoch": 2.94,
"learning_rate": 1.535267241289051e-08,
"loss": 0.7434,
"step": 920
},
{
"epoch": 2.95,
"learning_rate": 1.3493977972312e-08,
"loss": 0.821,
"step": 921
},
{
"epoch": 2.95,
"learning_rate": 1.1755094976523273e-08,
"loss": 0.8172,
"step": 922
},
{
"epoch": 2.95,
"learning_rate": 1.013604428748538e-08,
"loss": 0.8044,
"step": 923
},
{
"epoch": 2.96,
"learning_rate": 8.636845329488274e-09,
"loss": 0.8212,
"step": 924
},
{
"epoch": 2.96,
"learning_rate": 7.257516088923222e-09,
"loss": 0.736,
"step": 925
},
{
"epoch": 2.96,
"learning_rate": 5.998073114062975e-09,
"loss": 0.8705,
"step": 926
},
{
"epoch": 2.97,
"learning_rate": 4.858531514864151e-09,
"loss": 0.8007,
"step": 927
},
{
"epoch": 2.97,
"learning_rate": 3.838904962788492e-09,
"loss": 0.9261,
"step": 928
},
{
"epoch": 2.97,
"learning_rate": 2.9392056906352162e-09,
"loss": 0.9464,
"step": 929
},
{
"epoch": 2.98,
"learning_rate": 2.1594444923978e-09,
"loss": 0.7596,
"step": 930
},
{
"epoch": 2.98,
"learning_rate": 1.4996307231307517e-09,
"loss": 0.77,
"step": 931
},
{
"epoch": 2.98,
"learning_rate": 9.59772298840811e-10,
"loss": 0.8575,
"step": 932
},
{
"epoch": 2.99,
"learning_rate": 5.398756963881368e-10,
"loss": 0.898,
"step": 933
},
{
"epoch": 2.99,
"learning_rate": 2.399459534130344e-10,
"loss": 0.8638,
"step": 934
},
{
"epoch": 2.99,
"learning_rate": 5.998666827378153e-11,
"loss": 0.8143,
"step": 935
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.8272,
"step": 936
},
{
"epoch": 3.0,
"step": 936,
"total_flos": 9.559359129596723e+16,
"train_loss": 1.0894396532422457,
"train_runtime": 5839.8707,
"train_samples_per_second": 2.569,
"train_steps_per_second": 0.16
}
],
"logging_steps": 1.0,
"max_steps": 936,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50000,
"total_flos": 9.559359129596723e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}