AstroLLaVA_v4 / trainer_state.json
sh-zam's picture
Upload folder using huggingface_hub
d7039db verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9989235737351991,
"eval_steps": 500,
"global_step": 464,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.4285714285714286e-06,
"loss": 11.1919,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2.8571428571428573e-06,
"loss": 11.1954,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 4.2857142857142855e-06,
"loss": 11.1994,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 5.7142857142857145e-06,
"loss": 11.1645,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 7.1428571428571436e-06,
"loss": 10.9964,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 8.571428571428571e-06,
"loss": 10.7846,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 10.0858,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 1.1428571428571429e-05,
"loss": 9.8366,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 1.2857142857142859e-05,
"loss": 9.0224,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 1.4285714285714287e-05,
"loss": 8.7631,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 1.5714285714285715e-05,
"loss": 8.362,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 1.7142857142857142e-05,
"loss": 8.6043,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 1.8571428571428575e-05,
"loss": 8.0107,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 7.8552,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 1.9999756307053947e-05,
"loss": 7.7628,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 1.9999025240093045e-05,
"loss": 7.6037,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 1.9997806834748455e-05,
"loss": 7.2667,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 1.9996101150403543e-05,
"loss": 7.2522,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 1.999390827019096e-05,
"loss": 6.9511,
"step": 19
},
{
"epoch": 0.04,
"learning_rate": 1.9991228300988586e-05,
"loss": 6.9792,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 1.9988061373414342e-05,
"loss": 6.9217,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 1.9984407641819812e-05,
"loss": 6.5561,
"step": 22
},
{
"epoch": 0.05,
"learning_rate": 1.9980267284282718e-05,
"loss": 6.5328,
"step": 23
},
{
"epoch": 0.05,
"learning_rate": 1.9975640502598243e-05,
"loss": 6.5625,
"step": 24
},
{
"epoch": 0.05,
"learning_rate": 1.9970527522269204e-05,
"loss": 6.1461,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 1.9964928592495046e-05,
"loss": 6.057,
"step": 26
},
{
"epoch": 0.06,
"learning_rate": 1.9958843986159705e-05,
"loss": 6.2659,
"step": 27
},
{
"epoch": 0.06,
"learning_rate": 1.9952273999818312e-05,
"loss": 6.0935,
"step": 28
},
{
"epoch": 0.06,
"learning_rate": 1.9945218953682736e-05,
"loss": 6.1169,
"step": 29
},
{
"epoch": 0.06,
"learning_rate": 1.9937679191605964e-05,
"loss": 5.954,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 1.992965508106537e-05,
"loss": 5.8272,
"step": 31
},
{
"epoch": 0.07,
"learning_rate": 1.9921147013144782e-05,
"loss": 5.6679,
"step": 32
},
{
"epoch": 0.07,
"learning_rate": 1.991215540251542e-05,
"loss": 5.6864,
"step": 33
},
{
"epoch": 0.07,
"learning_rate": 1.9902680687415704e-05,
"loss": 5.5078,
"step": 34
},
{
"epoch": 0.08,
"learning_rate": 1.9892723329629885e-05,
"loss": 5.5315,
"step": 35
},
{
"epoch": 0.08,
"learning_rate": 1.988228381446553e-05,
"loss": 5.6325,
"step": 36
},
{
"epoch": 0.08,
"learning_rate": 1.987136265072988e-05,
"loss": 5.5514,
"step": 37
},
{
"epoch": 0.08,
"learning_rate": 1.985996037070505e-05,
"loss": 5.3763,
"step": 38
},
{
"epoch": 0.08,
"learning_rate": 1.9848077530122083e-05,
"loss": 5.3879,
"step": 39
},
{
"epoch": 0.09,
"learning_rate": 1.983571470813386e-05,
"loss": 5.3084,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 1.982287250728689e-05,
"loss": 5.0369,
"step": 41
},
{
"epoch": 0.09,
"learning_rate": 1.9809551553491918e-05,
"loss": 5.1092,
"step": 42
},
{
"epoch": 0.09,
"learning_rate": 1.979575249599344e-05,
"loss": 5.2227,
"step": 43
},
{
"epoch": 0.09,
"learning_rate": 1.9781476007338058e-05,
"loss": 5.2823,
"step": 44
},
{
"epoch": 0.1,
"learning_rate": 1.9766722783341682e-05,
"loss": 5.2116,
"step": 45
},
{
"epoch": 0.1,
"learning_rate": 1.9751493543055634e-05,
"loss": 5.1154,
"step": 46
},
{
"epoch": 0.1,
"learning_rate": 1.9735789028731603e-05,
"loss": 5.1348,
"step": 47
},
{
"epoch": 0.1,
"learning_rate": 1.9719610005785466e-05,
"loss": 5.0497,
"step": 48
},
{
"epoch": 0.11,
"learning_rate": 1.9702957262759964e-05,
"loss": 4.9045,
"step": 49
},
{
"epoch": 0.11,
"learning_rate": 1.9685831611286312e-05,
"loss": 5.0484,
"step": 50
},
{
"epoch": 0.11,
"learning_rate": 1.9668233886044597e-05,
"loss": 5.0345,
"step": 51
},
{
"epoch": 0.11,
"learning_rate": 1.9650164944723116e-05,
"loss": 4.8108,
"step": 52
},
{
"epoch": 0.11,
"learning_rate": 1.9631625667976584e-05,
"loss": 4.8182,
"step": 53
},
{
"epoch": 0.12,
"learning_rate": 1.961261695938319e-05,
"loss": 4.8736,
"step": 54
},
{
"epoch": 0.12,
"learning_rate": 1.9593139745400575e-05,
"loss": 4.5735,
"step": 55
},
{
"epoch": 0.12,
"learning_rate": 1.9573194975320672e-05,
"loss": 4.7191,
"step": 56
},
{
"epoch": 0.12,
"learning_rate": 1.9552783621223437e-05,
"loss": 4.6574,
"step": 57
},
{
"epoch": 0.12,
"learning_rate": 1.9531906677929472e-05,
"loss": 4.8037,
"step": 58
},
{
"epoch": 0.13,
"learning_rate": 1.9510565162951538e-05,
"loss": 4.7001,
"step": 59
},
{
"epoch": 0.13,
"learning_rate": 1.9488760116444966e-05,
"loss": 4.777,
"step": 60
},
{
"epoch": 0.13,
"learning_rate": 1.9466492601156964e-05,
"loss": 4.6243,
"step": 61
},
{
"epoch": 0.13,
"learning_rate": 1.944376370237481e-05,
"loss": 4.6636,
"step": 62
},
{
"epoch": 0.14,
"learning_rate": 1.942057452787297e-05,
"loss": 4.7189,
"step": 63
},
{
"epoch": 0.14,
"learning_rate": 1.9396926207859085e-05,
"loss": 4.677,
"step": 64
},
{
"epoch": 0.14,
"learning_rate": 1.937281989491892e-05,
"loss": 4.6467,
"step": 65
},
{
"epoch": 0.14,
"learning_rate": 1.9348256763960146e-05,
"loss": 4.4364,
"step": 66
},
{
"epoch": 0.14,
"learning_rate": 1.9323238012155125e-05,
"loss": 4.5659,
"step": 67
},
{
"epoch": 0.15,
"learning_rate": 1.9297764858882516e-05,
"loss": 4.5215,
"step": 68
},
{
"epoch": 0.15,
"learning_rate": 1.9271838545667876e-05,
"loss": 4.6202,
"step": 69
},
{
"epoch": 0.15,
"learning_rate": 1.9245460336123136e-05,
"loss": 4.4614,
"step": 70
},
{
"epoch": 0.15,
"learning_rate": 1.9218631515885007e-05,
"loss": 4.3224,
"step": 71
},
{
"epoch": 0.16,
"learning_rate": 1.9191353392552346e-05,
"loss": 4.4023,
"step": 72
},
{
"epoch": 0.16,
"learning_rate": 1.9163627295622397e-05,
"loss": 4.3972,
"step": 73
},
{
"epoch": 0.16,
"learning_rate": 1.913545457642601e-05,
"loss": 4.5911,
"step": 74
},
{
"epoch": 0.16,
"learning_rate": 1.910683660806177e-05,
"loss": 4.3745,
"step": 75
},
{
"epoch": 0.16,
"learning_rate": 1.907777478532909e-05,
"loss": 4.4133,
"step": 76
},
{
"epoch": 0.17,
"learning_rate": 1.9048270524660197e-05,
"loss": 4.3443,
"step": 77
},
{
"epoch": 0.17,
"learning_rate": 1.901832526405114e-05,
"loss": 4.4296,
"step": 78
},
{
"epoch": 0.17,
"learning_rate": 1.8987940462991673e-05,
"loss": 4.089,
"step": 79
},
{
"epoch": 0.17,
"learning_rate": 1.895711760239413e-05,
"loss": 4.4449,
"step": 80
},
{
"epoch": 0.17,
"learning_rate": 1.892585818452126e-05,
"loss": 4.3326,
"step": 81
},
{
"epoch": 0.18,
"learning_rate": 1.889416373291298e-05,
"loss": 4.0976,
"step": 82
},
{
"epoch": 0.18,
"learning_rate": 1.8862035792312148e-05,
"loss": 4.4456,
"step": 83
},
{
"epoch": 0.18,
"learning_rate": 1.8829475928589272e-05,
"loss": 4.0859,
"step": 84
},
{
"epoch": 0.18,
"learning_rate": 1.879648572866617e-05,
"loss": 4.2127,
"step": 85
},
{
"epoch": 0.19,
"learning_rate": 1.8763066800438638e-05,
"loss": 4.1194,
"step": 86
},
{
"epoch": 0.19,
"learning_rate": 1.8729220772698096e-05,
"loss": 4.0156,
"step": 87
},
{
"epoch": 0.19,
"learning_rate": 1.869494929505219e-05,
"loss": 4.1442,
"step": 88
},
{
"epoch": 0.19,
"learning_rate": 1.866025403784439e-05,
"loss": 4.1671,
"step": 89
},
{
"epoch": 0.19,
"learning_rate": 1.8625136692072577e-05,
"loss": 4.0236,
"step": 90
},
{
"epoch": 0.2,
"learning_rate": 1.8589598969306646e-05,
"loss": 4.0708,
"step": 91
},
{
"epoch": 0.2,
"learning_rate": 1.855364260160507e-05,
"loss": 4.2366,
"step": 92
},
{
"epoch": 0.2,
"learning_rate": 1.851726934143048e-05,
"loss": 4.0169,
"step": 93
},
{
"epoch": 0.2,
"learning_rate": 1.848048096156426e-05,
"loss": 4.2339,
"step": 94
},
{
"epoch": 0.2,
"learning_rate": 1.8443279255020153e-05,
"loss": 4.2049,
"step": 95
},
{
"epoch": 0.21,
"learning_rate": 1.8405666034956842e-05,
"loss": 4.2475,
"step": 96
},
{
"epoch": 0.21,
"learning_rate": 1.836764313458962e-05,
"loss": 4.0671,
"step": 97
},
{
"epoch": 0.21,
"learning_rate": 1.8329212407100996e-05,
"loss": 3.9732,
"step": 98
},
{
"epoch": 0.21,
"learning_rate": 1.8290375725550417e-05,
"loss": 4.1209,
"step": 99
},
{
"epoch": 0.22,
"learning_rate": 1.8251134982782952e-05,
"loss": 4.1656,
"step": 100
},
{
"epoch": 0.22,
"learning_rate": 1.821149209133704e-05,
"loss": 4.0558,
"step": 101
},
{
"epoch": 0.22,
"learning_rate": 1.8171448983351284e-05,
"loss": 4.0668,
"step": 102
},
{
"epoch": 0.22,
"learning_rate": 1.8131007610470278e-05,
"loss": 4.0768,
"step": 103
},
{
"epoch": 0.22,
"learning_rate": 1.8090169943749477e-05,
"loss": 3.8835,
"step": 104
},
{
"epoch": 0.23,
"learning_rate": 1.804893797355914e-05,
"loss": 4.0124,
"step": 105
},
{
"epoch": 0.23,
"learning_rate": 1.8007313709487334e-05,
"loss": 4.254,
"step": 106
},
{
"epoch": 0.23,
"learning_rate": 1.7965299180241963e-05,
"loss": 3.9149,
"step": 107
},
{
"epoch": 0.23,
"learning_rate": 1.792289643355191e-05,
"loss": 3.8183,
"step": 108
},
{
"epoch": 0.23,
"learning_rate": 1.788010753606722e-05,
"loss": 4.0132,
"step": 109
},
{
"epoch": 0.24,
"learning_rate": 1.78369345732584e-05,
"loss": 4.1192,
"step": 110
},
{
"epoch": 0.24,
"learning_rate": 1.7793379649314743e-05,
"loss": 3.775,
"step": 111
},
{
"epoch": 0.24,
"learning_rate": 1.7749444887041797e-05,
"loss": 3.7771,
"step": 112
},
{
"epoch": 0.24,
"learning_rate": 1.7705132427757895e-05,
"loss": 3.9899,
"step": 113
},
{
"epoch": 0.25,
"learning_rate": 1.766044443118978e-05,
"loss": 3.8152,
"step": 114
},
{
"epoch": 0.25,
"learning_rate": 1.761538307536737e-05,
"loss": 3.8208,
"step": 115
},
{
"epoch": 0.25,
"learning_rate": 1.7569950556517566e-05,
"loss": 3.754,
"step": 116
},
{
"epoch": 0.25,
"learning_rate": 1.7524149088957244e-05,
"loss": 3.991,
"step": 117
},
{
"epoch": 0.25,
"learning_rate": 1.747798090498532e-05,
"loss": 3.7378,
"step": 118
},
{
"epoch": 0.26,
"learning_rate": 1.7431448254773943e-05,
"loss": 3.7583,
"step": 119
},
{
"epoch": 0.26,
"learning_rate": 1.7384553406258842e-05,
"loss": 3.7621,
"step": 120
},
{
"epoch": 0.26,
"learning_rate": 1.7337298645028764e-05,
"loss": 3.6365,
"step": 121
},
{
"epoch": 0.26,
"learning_rate": 1.7289686274214116e-05,
"loss": 3.8783,
"step": 122
},
{
"epoch": 0.26,
"learning_rate": 1.7241718614374678e-05,
"loss": 3.9706,
"step": 123
},
{
"epoch": 0.27,
"learning_rate": 1.7193398003386514e-05,
"loss": 3.8903,
"step": 124
},
{
"epoch": 0.27,
"learning_rate": 1.7144726796328034e-05,
"loss": 3.8222,
"step": 125
},
{
"epoch": 0.27,
"learning_rate": 1.709570736536521e-05,
"loss": 3.7476,
"step": 126
},
{
"epoch": 0.27,
"learning_rate": 1.7046342099635948e-05,
"loss": 4.0318,
"step": 127
},
{
"epoch": 0.28,
"learning_rate": 1.6996633405133656e-05,
"loss": 3.5153,
"step": 128
},
{
"epoch": 0.28,
"learning_rate": 1.6946583704589973e-05,
"loss": 3.7565,
"step": 129
},
{
"epoch": 0.28,
"learning_rate": 1.68961954373567e-05,
"loss": 3.5093,
"step": 130
},
{
"epoch": 0.28,
"learning_rate": 1.684547105928689e-05,
"loss": 3.8183,
"step": 131
},
{
"epoch": 0.28,
"learning_rate": 1.6794413042615168e-05,
"loss": 3.7812,
"step": 132
},
{
"epoch": 0.29,
"learning_rate": 1.6743023875837233e-05,
"loss": 3.633,
"step": 133
},
{
"epoch": 0.29,
"learning_rate": 1.6691306063588583e-05,
"loss": 3.7852,
"step": 134
},
{
"epoch": 0.29,
"learning_rate": 1.6639262126522417e-05,
"loss": 3.483,
"step": 135
},
{
"epoch": 0.29,
"learning_rate": 1.6586894601186804e-05,
"loss": 3.6592,
"step": 136
},
{
"epoch": 0.29,
"learning_rate": 1.6534206039901057e-05,
"loss": 3.6166,
"step": 137
},
{
"epoch": 0.3,
"learning_rate": 1.6481199010631312e-05,
"loss": 3.7522,
"step": 138
},
{
"epoch": 0.3,
"learning_rate": 1.6427876096865394e-05,
"loss": 3.6586,
"step": 139
},
{
"epoch": 0.3,
"learning_rate": 1.63742398974869e-05,
"loss": 3.5315,
"step": 140
},
{
"epoch": 0.3,
"learning_rate": 1.632029302664851e-05,
"loss": 3.5977,
"step": 141
},
{
"epoch": 0.31,
"learning_rate": 1.6266038113644605e-05,
"loss": 3.6443,
"step": 142
},
{
"epoch": 0.31,
"learning_rate": 1.6211477802783105e-05,
"loss": 3.6679,
"step": 143
},
{
"epoch": 0.31,
"learning_rate": 1.6156614753256583e-05,
"loss": 3.7303,
"step": 144
},
{
"epoch": 0.31,
"learning_rate": 1.610145163901268e-05,
"loss": 3.5087,
"step": 145
},
{
"epoch": 0.31,
"learning_rate": 1.6045991148623752e-05,
"loss": 3.6125,
"step": 146
},
{
"epoch": 0.32,
"learning_rate": 1.599023598515586e-05,
"loss": 3.5518,
"step": 147
},
{
"epoch": 0.32,
"learning_rate": 1.5934188866037017e-05,
"loss": 3.5998,
"step": 148
},
{
"epoch": 0.32,
"learning_rate": 1.5877852522924733e-05,
"loss": 3.6526,
"step": 149
},
{
"epoch": 0.32,
"learning_rate": 1.5821229701572897e-05,
"loss": 3.7326,
"step": 150
},
{
"epoch": 0.33,
"learning_rate": 1.5764323161697933e-05,
"loss": 3.4031,
"step": 151
},
{
"epoch": 0.33,
"learning_rate": 1.570713567684432e-05,
"loss": 3.6545,
"step": 152
},
{
"epoch": 0.33,
"learning_rate": 1.564967003424938e-05,
"loss": 3.7027,
"step": 153
},
{
"epoch": 0.33,
"learning_rate": 1.5591929034707468e-05,
"loss": 3.5756,
"step": 154
},
{
"epoch": 0.33,
"learning_rate": 1.553391549243344e-05,
"loss": 3.549,
"step": 155
},
{
"epoch": 0.34,
"learning_rate": 1.5475632234925505e-05,
"loss": 3.5707,
"step": 156
},
{
"epoch": 0.34,
"learning_rate": 1.54170821028274e-05,
"loss": 3.5945,
"step": 157
},
{
"epoch": 0.34,
"learning_rate": 1.5358267949789968e-05,
"loss": 3.6214,
"step": 158
},
{
"epoch": 0.34,
"learning_rate": 1.529919264233205e-05,
"loss": 3.74,
"step": 159
},
{
"epoch": 0.34,
"learning_rate": 1.5239859059700794e-05,
"loss": 3.3402,
"step": 160
},
{
"epoch": 0.35,
"learning_rate": 1.5180270093731305e-05,
"loss": 3.6242,
"step": 161
},
{
"epoch": 0.35,
"learning_rate": 1.5120428648705716e-05,
"loss": 3.387,
"step": 162
},
{
"epoch": 0.35,
"learning_rate": 1.5060337641211637e-05,
"loss": 3.7526,
"step": 163
},
{
"epoch": 0.35,
"learning_rate": 1.5000000000000002e-05,
"loss": 3.5535,
"step": 164
},
{
"epoch": 0.36,
"learning_rate": 1.493941866584231e-05,
"loss": 3.3703,
"step": 165
},
{
"epoch": 0.36,
"learning_rate": 1.4878596591387329e-05,
"loss": 3.5501,
"step": 166
},
{
"epoch": 0.36,
"learning_rate": 1.4817536741017153e-05,
"loss": 3.6057,
"step": 167
},
{
"epoch": 0.36,
"learning_rate": 1.4756242090702756e-05,
"loss": 3.3914,
"step": 168
},
{
"epoch": 0.36,
"learning_rate": 1.469471562785891e-05,
"loss": 3.581,
"step": 169
},
{
"epoch": 0.37,
"learning_rate": 1.463296035119862e-05,
"loss": 3.3405,
"step": 170
},
{
"epoch": 0.37,
"learning_rate": 1.4570979270586944e-05,
"loss": 3.5743,
"step": 171
},
{
"epoch": 0.37,
"learning_rate": 1.4508775406894308e-05,
"loss": 3.3723,
"step": 172
},
{
"epoch": 0.37,
"learning_rate": 1.4446351791849276e-05,
"loss": 3.6758,
"step": 173
},
{
"epoch": 0.37,
"learning_rate": 1.4383711467890776e-05,
"loss": 3.3196,
"step": 174
},
{
"epoch": 0.38,
"learning_rate": 1.4320857488019826e-05,
"loss": 3.5028,
"step": 175
},
{
"epoch": 0.38,
"learning_rate": 1.4257792915650728e-05,
"loss": 3.4078,
"step": 176
},
{
"epoch": 0.38,
"learning_rate": 1.4194520824461773e-05,
"loss": 3.2751,
"step": 177
},
{
"epoch": 0.38,
"learning_rate": 1.413104429824542e-05,
"loss": 3.5113,
"step": 178
},
{
"epoch": 0.39,
"learning_rate": 1.4067366430758004e-05,
"loss": 3.4878,
"step": 179
},
{
"epoch": 0.39,
"learning_rate": 1.4003490325568953e-05,
"loss": 3.2961,
"step": 180
},
{
"epoch": 0.39,
"learning_rate": 1.3939419095909513e-05,
"loss": 3.4387,
"step": 181
},
{
"epoch": 0.39,
"learning_rate": 1.3875155864521031e-05,
"loss": 3.5352,
"step": 182
},
{
"epoch": 0.39,
"learning_rate": 1.3810703763502744e-05,
"loss": 3.4904,
"step": 183
},
{
"epoch": 0.4,
"learning_rate": 1.3746065934159123e-05,
"loss": 3.3581,
"step": 184
},
{
"epoch": 0.4,
"learning_rate": 1.3681245526846782e-05,
"loss": 3.1531,
"step": 185
},
{
"epoch": 0.4,
"learning_rate": 1.3616245700820922e-05,
"loss": 3.4176,
"step": 186
},
{
"epoch": 0.4,
"learning_rate": 1.3551069624081372e-05,
"loss": 3.1643,
"step": 187
},
{
"epoch": 0.4,
"learning_rate": 1.3485720473218153e-05,
"loss": 3.2712,
"step": 188
},
{
"epoch": 0.41,
"learning_rate": 1.342020143325669e-05,
"loss": 3.29,
"step": 189
},
{
"epoch": 0.41,
"learning_rate": 1.3354515697502552e-05,
"loss": 3.3608,
"step": 190
},
{
"epoch": 0.41,
"learning_rate": 1.3288666467385834e-05,
"loss": 3.4715,
"step": 191
},
{
"epoch": 0.41,
"learning_rate": 1.3222656952305113e-05,
"loss": 3.4641,
"step": 192
},
{
"epoch": 0.42,
"learning_rate": 1.3156490369471026e-05,
"loss": 3.5074,
"step": 193
},
{
"epoch": 0.42,
"learning_rate": 1.3090169943749475e-05,
"loss": 3.5732,
"step": 194
},
{
"epoch": 0.42,
"learning_rate": 1.3023698907504447e-05,
"loss": 3.3379,
"step": 195
},
{
"epoch": 0.42,
"learning_rate": 1.2957080500440469e-05,
"loss": 3.2536,
"step": 196
},
{
"epoch": 0.42,
"learning_rate": 1.2890317969444716e-05,
"loss": 3.3161,
"step": 197
},
{
"epoch": 0.43,
"learning_rate": 1.2823414568428767e-05,
"loss": 3.4145,
"step": 198
},
{
"epoch": 0.43,
"learning_rate": 1.2756373558169992e-05,
"loss": 3.3726,
"step": 199
},
{
"epoch": 0.43,
"learning_rate": 1.2689198206152657e-05,
"loss": 3.3474,
"step": 200
},
{
"epoch": 0.43,
"learning_rate": 1.2621891786408648e-05,
"loss": 3.3252,
"step": 201
},
{
"epoch": 0.43,
"learning_rate": 1.2554457579357906e-05,
"loss": 3.414,
"step": 202
},
{
"epoch": 0.44,
"learning_rate": 1.2486898871648552e-05,
"loss": 3.1703,
"step": 203
},
{
"epoch": 0.44,
"learning_rate": 1.2419218955996677e-05,
"loss": 3.2268,
"step": 204
},
{
"epoch": 0.44,
"learning_rate": 1.23514211310259e-05,
"loss": 3.2811,
"step": 205
},
{
"epoch": 0.44,
"learning_rate": 1.2283508701106559e-05,
"loss": 3.4358,
"step": 206
},
{
"epoch": 0.45,
"learning_rate": 1.2215484976194675e-05,
"loss": 3.1531,
"step": 207
},
{
"epoch": 0.45,
"learning_rate": 1.2147353271670634e-05,
"loss": 3.2542,
"step": 208
},
{
"epoch": 0.45,
"learning_rate": 1.2079116908177592e-05,
"loss": 3.2562,
"step": 209
},
{
"epoch": 0.45,
"learning_rate": 1.2010779211459649e-05,
"loss": 3.4072,
"step": 210
},
{
"epoch": 0.45,
"learning_rate": 1.194234351219972e-05,
"loss": 3.1582,
"step": 211
},
{
"epoch": 0.46,
"learning_rate": 1.187381314585725e-05,
"loss": 3.2262,
"step": 212
},
{
"epoch": 0.46,
"learning_rate": 1.1805191452505602e-05,
"loss": 3.3916,
"step": 213
},
{
"epoch": 0.46,
"learning_rate": 1.1736481776669307e-05,
"loss": 3.2714,
"step": 214
},
{
"epoch": 0.46,
"learning_rate": 1.1667687467161025e-05,
"loss": 3.1014,
"step": 215
},
{
"epoch": 0.47,
"learning_rate": 1.159881187691835e-05,
"loss": 3.2381,
"step": 216
},
{
"epoch": 0.47,
"learning_rate": 1.1529858362840383e-05,
"loss": 3.4055,
"step": 217
},
{
"epoch": 0.47,
"learning_rate": 1.1460830285624119e-05,
"loss": 3.1883,
"step": 218
},
{
"epoch": 0.47,
"learning_rate": 1.1391731009600655e-05,
"loss": 3.3211,
"step": 219
},
{
"epoch": 0.47,
"learning_rate": 1.1322563902571227e-05,
"loss": 3.1927,
"step": 220
},
{
"epoch": 0.48,
"learning_rate": 1.1253332335643043e-05,
"loss": 3.1594,
"step": 221
},
{
"epoch": 0.48,
"learning_rate": 1.1184039683065014e-05,
"loss": 3.3115,
"step": 222
},
{
"epoch": 0.48,
"learning_rate": 1.1114689322063255e-05,
"loss": 3.2155,
"step": 223
},
{
"epoch": 0.48,
"learning_rate": 1.1045284632676535e-05,
"loss": 3.1763,
"step": 224
},
{
"epoch": 0.48,
"learning_rate": 1.0975828997591496e-05,
"loss": 3.0249,
"step": 225
},
{
"epoch": 0.49,
"learning_rate": 1.0906325801977804e-05,
"loss": 3.1646,
"step": 226
},
{
"epoch": 0.49,
"learning_rate": 1.083677843332316e-05,
"loss": 3.3881,
"step": 227
},
{
"epoch": 0.49,
"learning_rate": 1.0767190281268187e-05,
"loss": 3.1982,
"step": 228
},
{
"epoch": 0.49,
"learning_rate": 1.0697564737441254e-05,
"loss": 3.402,
"step": 229
},
{
"epoch": 0.5,
"learning_rate": 1.0627905195293135e-05,
"loss": 3.3166,
"step": 230
},
{
"epoch": 0.5,
"learning_rate": 1.055821504993164e-05,
"loss": 3.0625,
"step": 231
},
{
"epoch": 0.5,
"learning_rate": 1.0488497697956134e-05,
"loss": 3.1438,
"step": 232
},
{
"epoch": 0.5,
"learning_rate": 1.0418756537291996e-05,
"loss": 2.901,
"step": 233
},
{
"epoch": 0.5,
"learning_rate": 1.0348994967025012e-05,
"loss": 3.1689,
"step": 234
},
{
"epoch": 0.51,
"learning_rate": 1.0279216387235691e-05,
"loss": 3.0224,
"step": 235
},
{
"epoch": 0.51,
"learning_rate": 1.0209424198833571e-05,
"loss": 3.3532,
"step": 236
},
{
"epoch": 0.51,
"learning_rate": 1.0139621803391454e-05,
"loss": 3.1011,
"step": 237
},
{
"epoch": 0.51,
"learning_rate": 1.0069812602979617e-05,
"loss": 3.1802,
"step": 238
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 3.0638,
"step": 239
},
{
"epoch": 0.52,
"learning_rate": 9.930187397020385e-06,
"loss": 3.0269,
"step": 240
},
{
"epoch": 0.52,
"learning_rate": 9.860378196608549e-06,
"loss": 3.0917,
"step": 241
},
{
"epoch": 0.52,
"learning_rate": 9.790575801166432e-06,
"loss": 3.0522,
"step": 242
},
{
"epoch": 0.52,
"learning_rate": 9.720783612764314e-06,
"loss": 3.0661,
"step": 243
},
{
"epoch": 0.53,
"learning_rate": 9.651005032974994e-06,
"loss": 3.3236,
"step": 244
},
{
"epoch": 0.53,
"learning_rate": 9.581243462708007e-06,
"loss": 3.1589,
"step": 245
},
{
"epoch": 0.53,
"learning_rate": 9.511502302043867e-06,
"loss": 3.1368,
"step": 246
},
{
"epoch": 0.53,
"learning_rate": 9.441784950068362e-06,
"loss": 3.1922,
"step": 247
},
{
"epoch": 0.53,
"learning_rate": 9.372094804706867e-06,
"loss": 2.9273,
"step": 248
},
{
"epoch": 0.54,
"learning_rate": 9.302435262558748e-06,
"loss": 3.1237,
"step": 249
},
{
"epoch": 0.54,
"learning_rate": 9.232809718731815e-06,
"loss": 3.2995,
"step": 250
},
{
"epoch": 0.54,
"learning_rate": 9.163221566676847e-06,
"loss": 3.1346,
"step": 251
},
{
"epoch": 0.54,
"learning_rate": 9.093674198022201e-06,
"loss": 3.1679,
"step": 252
},
{
"epoch": 0.54,
"learning_rate": 9.024171002408507e-06,
"loss": 3.0675,
"step": 253
},
{
"epoch": 0.55,
"learning_rate": 8.954715367323468e-06,
"loss": 3.3727,
"step": 254
},
{
"epoch": 0.55,
"learning_rate": 8.885310677936746e-06,
"loss": 3.1687,
"step": 255
},
{
"epoch": 0.55,
"learning_rate": 8.815960316934991e-06,
"loss": 3.0319,
"step": 256
},
{
"epoch": 0.55,
"learning_rate": 8.746667664356957e-06,
"loss": 2.9463,
"step": 257
},
{
"epoch": 0.56,
"learning_rate": 8.677436097428775e-06,
"loss": 3.1899,
"step": 258
},
{
"epoch": 0.56,
"learning_rate": 8.60826899039935e-06,
"loss": 3.0829,
"step": 259
},
{
"epoch": 0.56,
"learning_rate": 8.539169714375885e-06,
"loss": 3.218,
"step": 260
},
{
"epoch": 0.56,
"learning_rate": 8.47014163715962e-06,
"loss": 2.9621,
"step": 261
},
{
"epoch": 0.56,
"learning_rate": 8.401188123081653e-06,
"loss": 3.3212,
"step": 262
},
{
"epoch": 0.57,
"learning_rate": 8.332312532838978e-06,
"loss": 3.3789,
"step": 263
},
{
"epoch": 0.57,
"learning_rate": 8.263518223330698e-06,
"loss": 2.9574,
"step": 264
},
{
"epoch": 0.57,
"learning_rate": 8.194808547494401e-06,
"loss": 3.0763,
"step": 265
},
{
"epoch": 0.57,
"learning_rate": 8.126186854142752e-06,
"loss": 3.0917,
"step": 266
},
{
"epoch": 0.57,
"learning_rate": 8.057656487800283e-06,
"loss": 3.1662,
"step": 267
},
{
"epoch": 0.58,
"learning_rate": 7.989220788540356e-06,
"loss": 3.1483,
"step": 268
},
{
"epoch": 0.58,
"learning_rate": 7.92088309182241e-06,
"loss": 3.0958,
"step": 269
},
{
"epoch": 0.58,
"learning_rate": 7.852646728329368e-06,
"loss": 3.025,
"step": 270
},
{
"epoch": 0.58,
"learning_rate": 7.784515023805328e-06,
"loss": 3.001,
"step": 271
},
{
"epoch": 0.59,
"learning_rate": 7.716491298893443e-06,
"loss": 2.9623,
"step": 272
},
{
"epoch": 0.59,
"learning_rate": 7.6485788689741e-06,
"loss": 3.1547,
"step": 273
},
{
"epoch": 0.59,
"learning_rate": 7.580781044003324e-06,
"loss": 2.9606,
"step": 274
},
{
"epoch": 0.59,
"learning_rate": 7.513101128351454e-06,
"loss": 3.1369,
"step": 275
},
{
"epoch": 0.59,
"learning_rate": 7.445542420642097e-06,
"loss": 3.0933,
"step": 276
},
{
"epoch": 0.6,
"learning_rate": 7.378108213591355e-06,
"loss": 2.8175,
"step": 277
},
{
"epoch": 0.6,
"learning_rate": 7.310801793847344e-06,
"loss": 3.142,
"step": 278
},
{
"epoch": 0.6,
"learning_rate": 7.243626441830009e-06,
"loss": 3.0638,
"step": 279
},
{
"epoch": 0.6,
"learning_rate": 7.176585431571235e-06,
"loss": 2.9915,
"step": 280
},
{
"epoch": 0.6,
"learning_rate": 7.109682030555283e-06,
"loss": 2.9559,
"step": 281
},
{
"epoch": 0.61,
"learning_rate": 7.042919499559538e-06,
"loss": 2.8234,
"step": 282
},
{
"epoch": 0.61,
"learning_rate": 6.976301092495556e-06,
"loss": 3.0884,
"step": 283
},
{
"epoch": 0.61,
"learning_rate": 6.909830056250527e-06,
"loss": 2.8841,
"step": 284
},
{
"epoch": 0.61,
"learning_rate": 6.843509630528977e-06,
"loss": 3.0424,
"step": 285
},
{
"epoch": 0.62,
"learning_rate": 6.777343047694891e-06,
"loss": 3.1176,
"step": 286
},
{
"epoch": 0.62,
"learning_rate": 6.711333532614168e-06,
"loss": 2.9957,
"step": 287
},
{
"epoch": 0.62,
"learning_rate": 6.645484302497452e-06,
"loss": 3.1446,
"step": 288
},
{
"epoch": 0.62,
"learning_rate": 6.579798566743314e-06,
"loss": 3.0852,
"step": 289
},
{
"epoch": 0.62,
"learning_rate": 6.5142795267818505e-06,
"loss": 3.018,
"step": 290
},
{
"epoch": 0.63,
"learning_rate": 6.448930375918632e-06,
"loss": 3.0797,
"step": 291
},
{
"epoch": 0.63,
"learning_rate": 6.383754299179079e-06,
"loss": 3.0706,
"step": 292
},
{
"epoch": 0.63,
"learning_rate": 6.318754473153221e-06,
"loss": 3.1792,
"step": 293
},
{
"epoch": 0.63,
"learning_rate": 6.25393406584088e-06,
"loss": 3.1133,
"step": 294
},
{
"epoch": 0.64,
"learning_rate": 6.18929623649726e-06,
"loss": 3.0408,
"step": 295
},
{
"epoch": 0.64,
"learning_rate": 6.124844135478971e-06,
"loss": 3.0217,
"step": 296
},
{
"epoch": 0.64,
"learning_rate": 6.06058090409049e-06,
"loss": 3.1471,
"step": 297
},
{
"epoch": 0.64,
"learning_rate": 5.996509674431053e-06,
"loss": 3.0054,
"step": 298
},
{
"epoch": 0.64,
"learning_rate": 5.932633569242e-06,
"loss": 2.8841,
"step": 299
},
{
"epoch": 0.65,
"learning_rate": 5.868955701754584e-06,
"loss": 3.0751,
"step": 300
},
{
"epoch": 0.65,
"learning_rate": 5.8054791755382286e-06,
"loss": 3.1672,
"step": 301
},
{
"epoch": 0.65,
"learning_rate": 5.742207084349274e-06,
"loss": 3.0556,
"step": 302
},
{
"epoch": 0.65,
"learning_rate": 5.679142511980176e-06,
"loss": 2.9653,
"step": 303
},
{
"epoch": 0.65,
"learning_rate": 5.616288532109225e-06,
"loss": 3.0614,
"step": 304
},
{
"epoch": 0.66,
"learning_rate": 5.553648208150728e-06,
"loss": 3.1513,
"step": 305
},
{
"epoch": 0.66,
"learning_rate": 5.491224593105695e-06,
"loss": 3.0938,
"step": 306
},
{
"epoch": 0.66,
"learning_rate": 5.429020729413062e-06,
"loss": 3.1464,
"step": 307
},
{
"epoch": 0.66,
"learning_rate": 5.367039648801386e-06,
"loss": 3.1736,
"step": 308
},
{
"epoch": 0.67,
"learning_rate": 5.305284372141095e-06,
"loss": 3.0721,
"step": 309
},
{
"epoch": 0.67,
"learning_rate": 5.243757909297247e-06,
"loss": 2.9978,
"step": 310
},
{
"epoch": 0.67,
"learning_rate": 5.1824632589828465e-06,
"loss": 3.0965,
"step": 311
},
{
"epoch": 0.67,
"learning_rate": 5.121403408612672e-06,
"loss": 2.9086,
"step": 312
},
{
"epoch": 0.67,
"learning_rate": 5.060581334157693e-06,
"loss": 3.0667,
"step": 313
},
{
"epoch": 0.68,
"learning_rate": 5.000000000000003e-06,
"loss": 3.1128,
"step": 314
},
{
"epoch": 0.68,
"learning_rate": 4.939662358788364e-06,
"loss": 3.0392,
"step": 315
},
{
"epoch": 0.68,
"learning_rate": 4.879571351294287e-06,
"loss": 3.0734,
"step": 316
},
{
"epoch": 0.68,
"learning_rate": 4.8197299062687e-06,
"loss": 2.9622,
"step": 317
},
{
"epoch": 0.68,
"learning_rate": 4.76014094029921e-06,
"loss": 3.0809,
"step": 318
},
{
"epoch": 0.69,
"learning_rate": 4.700807357667953e-06,
"loss": 3.1293,
"step": 319
},
{
"epoch": 0.69,
"learning_rate": 4.641732050210032e-06,
"loss": 2.9908,
"step": 320
},
{
"epoch": 0.69,
"learning_rate": 4.582917897172603e-06,
"loss": 2.9895,
"step": 321
},
{
"epoch": 0.69,
"learning_rate": 4.524367765074499e-06,
"loss": 3.0343,
"step": 322
},
{
"epoch": 0.7,
"learning_rate": 4.46608450756656e-06,
"loss": 3.0682,
"step": 323
},
{
"epoch": 0.7,
"learning_rate": 4.408070965292534e-06,
"loss": 2.9423,
"step": 324
},
{
"epoch": 0.7,
"learning_rate": 4.350329965750622e-06,
"loss": 2.8774,
"step": 325
},
{
"epoch": 0.7,
"learning_rate": 4.292864323155684e-06,
"loss": 2.9439,
"step": 326
},
{
"epoch": 0.7,
"learning_rate": 4.235676838302069e-06,
"loss": 2.9664,
"step": 327
},
{
"epoch": 0.71,
"learning_rate": 4.178770298427107e-06,
"loss": 3.0489,
"step": 328
},
{
"epoch": 0.71,
"learning_rate": 4.12214747707527e-06,
"loss": 3.1551,
"step": 329
},
{
"epoch": 0.71,
"learning_rate": 4.065811133962987e-06,
"loss": 3.0463,
"step": 330
},
{
"epoch": 0.71,
"learning_rate": 4.009764014844143e-06,
"loss": 3.056,
"step": 331
},
{
"epoch": 0.71,
"learning_rate": 3.954008851376252e-06,
"loss": 3.068,
"step": 332
},
{
"epoch": 0.72,
"learning_rate": 3.898548360987325e-06,
"loss": 3.0363,
"step": 333
},
{
"epoch": 0.72,
"learning_rate": 3.8433852467434175e-06,
"loss": 3.0804,
"step": 334
},
{
"epoch": 0.72,
"learning_rate": 3.7885221972168974e-06,
"loss": 3.0529,
"step": 335
},
{
"epoch": 0.72,
"learning_rate": 3.7339618863553983e-06,
"loss": 2.8621,
"step": 336
},
{
"epoch": 0.73,
"learning_rate": 3.679706973351491e-06,
"loss": 3.084,
"step": 337
},
{
"epoch": 0.73,
"learning_rate": 3.625760102513103e-06,
"loss": 2.9086,
"step": 338
},
{
"epoch": 0.73,
"learning_rate": 3.5721239031346067e-06,
"loss": 2.9246,
"step": 339
},
{
"epoch": 0.73,
"learning_rate": 3.5188009893686916e-06,
"loss": 2.8996,
"step": 340
},
{
"epoch": 0.73,
"learning_rate": 3.4657939600989453e-06,
"loss": 2.9323,
"step": 341
},
{
"epoch": 0.74,
"learning_rate": 3.4131053988131947e-06,
"loss": 3.1145,
"step": 342
},
{
"epoch": 0.74,
"learning_rate": 3.360737873477584e-06,
"loss": 2.9254,
"step": 343
},
{
"epoch": 0.74,
"learning_rate": 3.308693936411421e-06,
"loss": 2.9558,
"step": 344
},
{
"epoch": 0.74,
"learning_rate": 3.2569761241627694e-06,
"loss": 2.9802,
"step": 345
},
{
"epoch": 0.74,
"learning_rate": 3.2055869573848374e-06,
"loss": 3.0983,
"step": 346
},
{
"epoch": 0.75,
"learning_rate": 3.1545289407131128e-06,
"loss": 2.8111,
"step": 347
},
{
"epoch": 0.75,
"learning_rate": 3.103804562643302e-06,
"loss": 2.8607,
"step": 348
},
{
"epoch": 0.75,
"learning_rate": 3.0534162954100264e-06,
"loss": 3.1214,
"step": 349
},
{
"epoch": 0.75,
"learning_rate": 3.003366594866345e-06,
"loss": 2.8757,
"step": 350
},
{
"epoch": 0.76,
"learning_rate": 2.953657900364053e-06,
"loss": 2.7867,
"step": 351
},
{
"epoch": 0.76,
"learning_rate": 2.9042926346347932e-06,
"loss": 2.993,
"step": 352
},
{
"epoch": 0.76,
"learning_rate": 2.855273203671969e-06,
"loss": 3.126,
"step": 353
},
{
"epoch": 0.76,
"learning_rate": 2.8066019966134907e-06,
"loss": 3.1676,
"step": 354
},
{
"epoch": 0.76,
"learning_rate": 2.7582813856253276e-06,
"loss": 2.983,
"step": 355
},
{
"epoch": 0.77,
"learning_rate": 2.7103137257858867e-06,
"loss": 3.0481,
"step": 356
},
{
"epoch": 0.77,
"learning_rate": 2.6627013549712355e-06,
"loss": 2.8263,
"step": 357
},
{
"epoch": 0.77,
"learning_rate": 2.615446593741161e-06,
"loss": 2.9739,
"step": 358
},
{
"epoch": 0.77,
"learning_rate": 2.5685517452260566e-06,
"loss": 2.7064,
"step": 359
},
{
"epoch": 0.78,
"learning_rate": 2.522019095014683e-06,
"loss": 3.0511,
"step": 360
},
{
"epoch": 0.78,
"learning_rate": 2.4758509110427576e-06,
"loss": 3.0474,
"step": 361
},
{
"epoch": 0.78,
"learning_rate": 2.4300494434824373e-06,
"loss": 2.8335,
"step": 362
},
{
"epoch": 0.78,
"learning_rate": 2.3846169246326345e-06,
"loss": 2.9095,
"step": 363
},
{
"epoch": 0.78,
"learning_rate": 2.339555568810221e-06,
"loss": 3.03,
"step": 364
},
{
"epoch": 0.79,
"learning_rate": 2.2948675722421086e-06,
"loss": 3.0604,
"step": 365
},
{
"epoch": 0.79,
"learning_rate": 2.2505551129582047e-06,
"loss": 2.7813,
"step": 366
},
{
"epoch": 0.79,
"learning_rate": 2.206620350685257e-06,
"loss": 3.019,
"step": 367
},
{
"epoch": 0.79,
"learning_rate": 2.163065426741603e-06,
"loss": 3.0525,
"step": 368
},
{
"epoch": 0.79,
"learning_rate": 2.119892463932781e-06,
"loss": 3.0489,
"step": 369
},
{
"epoch": 0.8,
"learning_rate": 2.0771035664480944e-06,
"loss": 2.9381,
"step": 370
},
{
"epoch": 0.8,
"learning_rate": 2.0347008197580376e-06,
"loss": 2.9542,
"step": 371
},
{
"epoch": 0.8,
"learning_rate": 1.9926862905126663e-06,
"loss": 2.878,
"step": 372
},
{
"epoch": 0.8,
"learning_rate": 1.95106202644086e-06,
"loss": 2.9068,
"step": 373
},
{
"epoch": 0.81,
"learning_rate": 1.9098300562505266e-06,
"loss": 2.9591,
"step": 374
},
{
"epoch": 0.81,
"learning_rate": 1.8689923895297247e-06,
"loss": 2.9787,
"step": 375
},
{
"epoch": 0.81,
"learning_rate": 1.8285510166487154e-06,
"loss": 2.5749,
"step": 376
},
{
"epoch": 0.81,
"learning_rate": 1.7885079086629598e-06,
"loss": 2.9779,
"step": 377
},
{
"epoch": 0.81,
"learning_rate": 1.7488650172170496e-06,
"loss": 2.9012,
"step": 378
},
{
"epoch": 0.82,
"learning_rate": 1.709624274449584e-06,
"loss": 2.9592,
"step": 379
},
{
"epoch": 0.82,
"learning_rate": 1.6707875928990059e-06,
"loss": 2.8836,
"step": 380
},
{
"epoch": 0.82,
"learning_rate": 1.6323568654103838e-06,
"loss": 2.8998,
"step": 381
},
{
"epoch": 0.82,
"learning_rate": 1.5943339650431578e-06,
"loss": 2.8216,
"step": 382
},
{
"epoch": 0.82,
"learning_rate": 1.5567207449798517e-06,
"loss": 2.842,
"step": 383
},
{
"epoch": 0.83,
"learning_rate": 1.5195190384357405e-06,
"loss": 2.8234,
"step": 384
},
{
"epoch": 0.83,
"learning_rate": 1.4827306585695234e-06,
"loss": 2.9108,
"step": 385
},
{
"epoch": 0.83,
"learning_rate": 1.446357398394934e-06,
"loss": 2.7722,
"step": 386
},
{
"epoch": 0.83,
"learning_rate": 1.4104010306933558e-06,
"loss": 2.7488,
"step": 387
},
{
"epoch": 0.84,
"learning_rate": 1.3748633079274254e-06,
"loss": 2.9196,
"step": 388
},
{
"epoch": 0.84,
"learning_rate": 1.339745962155613e-06,
"loss": 2.78,
"step": 389
},
{
"epoch": 0.84,
"learning_rate": 1.30505070494781e-06,
"loss": 3.0894,
"step": 390
},
{
"epoch": 0.84,
"learning_rate": 1.2707792273019049e-06,
"loss": 2.7282,
"step": 391
},
{
"epoch": 0.84,
"learning_rate": 1.2369331995613664e-06,
"loss": 2.8365,
"step": 392
},
{
"epoch": 0.85,
"learning_rate": 1.2035142713338366e-06,
"loss": 3.0266,
"step": 393
},
{
"epoch": 0.85,
"learning_rate": 1.1705240714107301e-06,
"loss": 2.7328,
"step": 394
},
{
"epoch": 0.85,
"learning_rate": 1.1379642076878528e-06,
"loss": 3.0717,
"step": 395
},
{
"epoch": 0.85,
"learning_rate": 1.1058362670870248e-06,
"loss": 3.0255,
"step": 396
},
{
"epoch": 0.85,
"learning_rate": 1.0741418154787443e-06,
"loss": 2.9097,
"step": 397
},
{
"epoch": 0.86,
"learning_rate": 1.042882397605871e-06,
"loss": 2.9539,
"step": 398
},
{
"epoch": 0.86,
"learning_rate": 1.012059537008332e-06,
"loss": 2.7119,
"step": 399
},
{
"epoch": 0.86,
"learning_rate": 9.816747359488632e-07,
"loss": 2.9557,
"step": 400
},
{
"epoch": 0.86,
"learning_rate": 9.517294753398066e-07,
"loss": 2.6875,
"step": 401
},
{
"epoch": 0.87,
"learning_rate": 9.222252146709143e-07,
"loss": 2.8257,
"step": 402
},
{
"epoch": 0.87,
"learning_rate": 8.931633919382299e-07,
"loss": 2.9076,
"step": 403
},
{
"epoch": 0.87,
"learning_rate": 8.645454235739903e-07,
"loss": 2.8174,
"step": 404
},
{
"epoch": 0.87,
"learning_rate": 8.363727043776037e-07,
"loss": 2.9281,
"step": 405
},
{
"epoch": 0.87,
"learning_rate": 8.086466074476562e-07,
"loss": 3.1525,
"step": 406
},
{
"epoch": 0.88,
"learning_rate": 7.81368484114996e-07,
"loss": 2.9722,
"step": 407
},
{
"epoch": 0.88,
"learning_rate": 7.545396638768698e-07,
"loss": 3.0472,
"step": 408
},
{
"epoch": 0.88,
"learning_rate": 7.281614543321269e-07,
"loss": 2.8118,
"step": 409
},
{
"epoch": 0.88,
"learning_rate": 7.022351411174866e-07,
"loss": 2.7696,
"step": 410
},
{
"epoch": 0.88,
"learning_rate": 6.767619878448783e-07,
"loss": 3.0772,
"step": 411
},
{
"epoch": 0.89,
"learning_rate": 6.517432360398556e-07,
"loss": 2.8397,
"step": 412
},
{
"epoch": 0.89,
"learning_rate": 6.271801050810856e-07,
"loss": 2.8192,
"step": 413
},
{
"epoch": 0.89,
"learning_rate": 6.030737921409169e-07,
"loss": 3.0129,
"step": 414
},
{
"epoch": 0.89,
"learning_rate": 5.794254721270331e-07,
"loss": 3.0211,
"step": 415
},
{
"epoch": 0.9,
"learning_rate": 5.562362976251901e-07,
"loss": 2.8343,
"step": 416
},
{
"epoch": 0.9,
"learning_rate": 5.335073988430373e-07,
"loss": 2.6514,
"step": 417
},
{
"epoch": 0.9,
"learning_rate": 5.112398835550348e-07,
"loss": 2.9843,
"step": 418
},
{
"epoch": 0.9,
"learning_rate": 4.894348370484648e-07,
"loss": 2.8701,
"step": 419
},
{
"epoch": 0.9,
"learning_rate": 4.6809332207053083e-07,
"loss": 2.9951,
"step": 420
},
{
"epoch": 0.91,
"learning_rate": 4.4721637877656377e-07,
"loss": 2.9243,
"step": 421
},
{
"epoch": 0.91,
"learning_rate": 4.268050246793276e-07,
"loss": 2.879,
"step": 422
},
{
"epoch": 0.91,
"learning_rate": 4.068602545994249e-07,
"loss": 2.7713,
"step": 423
},
{
"epoch": 0.91,
"learning_rate": 3.8738304061681107e-07,
"loss": 2.879,
"step": 424
},
{
"epoch": 0.91,
"learning_rate": 3.68374332023419e-07,
"loss": 2.864,
"step": 425
},
{
"epoch": 0.92,
"learning_rate": 3.498350552768859e-07,
"loss": 2.7708,
"step": 426
},
{
"epoch": 0.92,
"learning_rate": 3.3176611395540625e-07,
"loss": 2.6635,
"step": 427
},
{
"epoch": 0.92,
"learning_rate": 3.1416838871368925e-07,
"loss": 2.9611,
"step": 428
},
{
"epoch": 0.92,
"learning_rate": 2.970427372400353e-07,
"loss": 2.8527,
"step": 429
},
{
"epoch": 0.93,
"learning_rate": 2.8038999421453827e-07,
"loss": 3.0667,
"step": 430
},
{
"epoch": 0.93,
"learning_rate": 2.6421097126839714e-07,
"loss": 2.8973,
"step": 431
},
{
"epoch": 0.93,
"learning_rate": 2.4850645694436736e-07,
"loss": 2.7729,
"step": 432
},
{
"epoch": 0.93,
"learning_rate": 2.332772166583208e-07,
"loss": 2.8383,
"step": 433
},
{
"epoch": 0.93,
"learning_rate": 2.1852399266194312e-07,
"loss": 2.8688,
"step": 434
},
{
"epoch": 0.94,
"learning_rate": 2.0424750400655947e-07,
"loss": 3.0494,
"step": 435
},
{
"epoch": 0.94,
"learning_rate": 1.9044844650808468e-07,
"loss": 2.8407,
"step": 436
},
{
"epoch": 0.94,
"learning_rate": 1.7712749271311392e-07,
"loss": 3.0531,
"step": 437
},
{
"epoch": 0.94,
"learning_rate": 1.6428529186614195e-07,
"loss": 3.133,
"step": 438
},
{
"epoch": 0.95,
"learning_rate": 1.519224698779198e-07,
"loss": 2.8037,
"step": 439
},
{
"epoch": 0.95,
"learning_rate": 1.400396292949513e-07,
"loss": 2.7822,
"step": 440
},
{
"epoch": 0.95,
"learning_rate": 1.2863734927012094e-07,
"loss": 3.0815,
"step": 441
},
{
"epoch": 0.95,
"learning_rate": 1.1771618553447217e-07,
"loss": 2.8274,
"step": 442
},
{
"epoch": 0.95,
"learning_rate": 1.0727667037011668e-07,
"loss": 2.7749,
"step": 443
},
{
"epoch": 0.96,
"learning_rate": 9.731931258429638e-08,
"loss": 2.8282,
"step": 444
},
{
"epoch": 0.96,
"learning_rate": 8.784459748458318e-08,
"loss": 2.7232,
"step": 445
},
{
"epoch": 0.96,
"learning_rate": 7.885298685522235e-08,
"loss": 3.0736,
"step": 446
},
{
"epoch": 0.96,
"learning_rate": 7.034491893463059e-08,
"loss": 3.0258,
"step": 447
},
{
"epoch": 0.96,
"learning_rate": 6.232080839403631e-08,
"loss": 2.9631,
"step": 448
},
{
"epoch": 0.97,
"learning_rate": 5.4781046317267103e-08,
"loss": 2.8569,
"step": 449
},
{
"epoch": 0.97,
"learning_rate": 4.772600018168816e-08,
"loss": 3.2066,
"step": 450
},
{
"epoch": 0.97,
"learning_rate": 4.115601384029666e-08,
"loss": 2.963,
"step": 451
},
{
"epoch": 0.97,
"learning_rate": 3.50714075049563e-08,
"loss": 3.0168,
"step": 452
},
{
"epoch": 0.98,
"learning_rate": 2.947247773079753e-08,
"loss": 2.7483,
"step": 453
},
{
"epoch": 0.98,
"learning_rate": 2.4359497401758026e-08,
"loss": 2.9108,
"step": 454
},
{
"epoch": 0.98,
"learning_rate": 1.973271571728441e-08,
"loss": 2.9428,
"step": 455
},
{
"epoch": 0.98,
"learning_rate": 1.5592358180189782e-08,
"loss": 2.913,
"step": 456
},
{
"epoch": 0.98,
"learning_rate": 1.1938626585660252e-08,
"loss": 2.7119,
"step": 457
},
{
"epoch": 0.99,
"learning_rate": 8.771699011416169e-09,
"loss": 2.9514,
"step": 458
},
{
"epoch": 0.99,
"learning_rate": 6.091729809042379e-09,
"loss": 2.8435,
"step": 459
},
{
"epoch": 0.99,
"learning_rate": 3.898849596456477e-09,
"loss": 2.9467,
"step": 460
},
{
"epoch": 0.99,
"learning_rate": 2.193165251545004e-09,
"loss": 2.8708,
"step": 461
},
{
"epoch": 0.99,
"learning_rate": 9.74759906957612e-10,
"loss": 3.0586,
"step": 462
},
{
"epoch": 1.0,
"learning_rate": 2.436929460525317e-10,
"loss": 3.1997,
"step": 463
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 3.0101,
"step": 464
},
{
"epoch": 1.0,
"step": 464,
"total_flos": 312662581837824.0,
"train_loss": 3.728918135166168,
"train_runtime": 15696.9071,
"train_samples_per_second": 1.894,
"train_steps_per_second": 0.03
}
],
"logging_steps": 1.0,
"max_steps": 464,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50000,
"total_flos": 312662581837824.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}