deepseekv2 / trainer_state.json
Sloozi's picture
Upload 8 files
bc4dadf verified
raw
history blame contribute delete
No virus
92.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 20.0,
"eval_steps": 500,
"global_step": 760,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 4.000000000000001e-06,
"loss": 0.2041,
"step": 1
},
{
"epoch": 0.05,
"learning_rate": 8.000000000000001e-06,
"loss": 0.27,
"step": 2
},
{
"epoch": 0.08,
"learning_rate": 1.2e-05,
"loss": 0.5031,
"step": 3
},
{
"epoch": 0.11,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.5115,
"step": 4
},
{
"epoch": 0.13,
"learning_rate": 2e-05,
"loss": 0.6283,
"step": 5
},
{
"epoch": 0.16,
"learning_rate": 2.4e-05,
"loss": 0.327,
"step": 6
},
{
"epoch": 0.18,
"learning_rate": 2.8e-05,
"loss": 0.3308,
"step": 7
},
{
"epoch": 0.21,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.4163,
"step": 8
},
{
"epoch": 0.24,
"learning_rate": 3.6e-05,
"loss": 0.4515,
"step": 9
},
{
"epoch": 0.26,
"learning_rate": 4e-05,
"loss": 0.3857,
"step": 10
},
{
"epoch": 0.29,
"learning_rate": 3.999982454062275e-05,
"loss": 0.3679,
"step": 11
},
{
"epoch": 0.32,
"learning_rate": 3.9999298165569614e-05,
"loss": 0.486,
"step": 12
},
{
"epoch": 0.34,
"learning_rate": 3.999842088407633e-05,
"loss": 0.4837,
"step": 13
},
{
"epoch": 0.37,
"learning_rate": 3.999719271153561e-05,
"loss": 0.4925,
"step": 14
},
{
"epoch": 0.39,
"learning_rate": 3.999561366949691e-05,
"loss": 0.361,
"step": 15
},
{
"epoch": 0.42,
"learning_rate": 3.9993683785666e-05,
"loss": 0.3462,
"step": 16
},
{
"epoch": 0.45,
"learning_rate": 3.9991403093904505e-05,
"loss": 0.4642,
"step": 17
},
{
"epoch": 0.47,
"learning_rate": 3.998877163422929e-05,
"loss": 0.5412,
"step": 18
},
{
"epoch": 0.5,
"learning_rate": 3.998578945281179e-05,
"loss": 0.6091,
"step": 19
},
{
"epoch": 0.53,
"learning_rate": 3.998245660197717e-05,
"loss": 0.3604,
"step": 20
},
{
"epoch": 0.55,
"learning_rate": 3.997877314020343e-05,
"loss": 0.492,
"step": 21
},
{
"epoch": 0.58,
"learning_rate": 3.997473913212036e-05,
"loss": 0.335,
"step": 22
},
{
"epoch": 0.61,
"learning_rate": 3.99703546485084e-05,
"loss": 0.4276,
"step": 23
},
{
"epoch": 0.63,
"learning_rate": 3.996561976629744e-05,
"loss": 0.2509,
"step": 24
},
{
"epoch": 0.66,
"learning_rate": 3.9960534568565436e-05,
"loss": 0.3847,
"step": 25
},
{
"epoch": 0.68,
"learning_rate": 3.995509914453694e-05,
"loss": 0.4315,
"step": 26
},
{
"epoch": 0.71,
"learning_rate": 3.9949313589581555e-05,
"loss": 0.2665,
"step": 27
},
{
"epoch": 0.74,
"learning_rate": 3.994317800521228e-05,
"loss": 0.3356,
"step": 28
},
{
"epoch": 0.76,
"learning_rate": 3.9936692499083696e-05,
"loss": 0.4021,
"step": 29
},
{
"epoch": 0.79,
"learning_rate": 3.992985718499009e-05,
"loss": 0.5412,
"step": 30
},
{
"epoch": 0.82,
"learning_rate": 3.9922672182863456e-05,
"loss": 0.3859,
"step": 31
},
{
"epoch": 0.84,
"learning_rate": 3.9915137618771386e-05,
"loss": 0.4645,
"step": 32
},
{
"epoch": 0.87,
"learning_rate": 3.990725362491488e-05,
"loss": 0.1969,
"step": 33
},
{
"epoch": 0.89,
"learning_rate": 3.989902033962601e-05,
"loss": 0.3058,
"step": 34
},
{
"epoch": 0.92,
"learning_rate": 3.989043790736547e-05,
"loss": 0.4659,
"step": 35
},
{
"epoch": 0.95,
"learning_rate": 3.9881506478720095e-05,
"loss": 0.5754,
"step": 36
},
{
"epoch": 0.97,
"learning_rate": 3.987222621040017e-05,
"loss": 0.4268,
"step": 37
},
{
"epoch": 1.0,
"learning_rate": 3.986259726523671e-05,
"loss": 0.313,
"step": 38
},
{
"epoch": 1.03,
"learning_rate": 3.985261981217858e-05,
"loss": 0.5001,
"step": 39
},
{
"epoch": 1.05,
"learning_rate": 3.9842294026289565e-05,
"loss": 0.5115,
"step": 40
},
{
"epoch": 1.08,
"learning_rate": 3.9831620088745236e-05,
"loss": 0.3916,
"step": 41
},
{
"epoch": 1.11,
"learning_rate": 3.982059818682986e-05,
"loss": 0.2339,
"step": 42
},
{
"epoch": 1.13,
"learning_rate": 3.980922851393303e-05,
"loss": 0.4039,
"step": 43
},
{
"epoch": 1.16,
"learning_rate": 3.979751126954632e-05,
"loss": 0.3582,
"step": 44
},
{
"epoch": 1.18,
"learning_rate": 3.978544665925977e-05,
"loss": 0.6056,
"step": 45
},
{
"epoch": 1.21,
"learning_rate": 3.977303489475828e-05,
"loss": 0.3198,
"step": 46
},
{
"epoch": 1.24,
"learning_rate": 3.976027619381791e-05,
"loss": 0.3763,
"step": 47
},
{
"epoch": 1.26,
"learning_rate": 3.974717078030201e-05,
"loss": 0.3211,
"step": 48
},
{
"epoch": 1.29,
"learning_rate": 3.973371888415736e-05,
"loss": 0.3219,
"step": 49
},
{
"epoch": 1.32,
"learning_rate": 3.97199207414101e-05,
"loss": 0.2872,
"step": 50
},
{
"epoch": 1.34,
"learning_rate": 3.970577659416158e-05,
"loss": 0.113,
"step": 51
},
{
"epoch": 1.37,
"learning_rate": 3.969128669058411e-05,
"loss": 0.31,
"step": 52
},
{
"epoch": 1.39,
"learning_rate": 3.967645128491666e-05,
"loss": 0.3789,
"step": 53
},
{
"epoch": 1.42,
"learning_rate": 3.966127063746031e-05,
"loss": 0.4233,
"step": 54
},
{
"epoch": 1.45,
"learning_rate": 3.964574501457378e-05,
"loss": 0.2903,
"step": 55
},
{
"epoch": 1.47,
"learning_rate": 3.962987468866866e-05,
"loss": 0.2413,
"step": 56
},
{
"epoch": 1.5,
"learning_rate": 3.961365993820471e-05,
"loss": 0.2886,
"step": 57
},
{
"epoch": 1.53,
"learning_rate": 3.959710104768494e-05,
"loss": 0.2111,
"step": 58
},
{
"epoch": 1.55,
"learning_rate": 3.95801983076506e-05,
"loss": 0.1582,
"step": 59
},
{
"epoch": 1.58,
"learning_rate": 3.9562952014676116e-05,
"loss": 0.3719,
"step": 60
},
{
"epoch": 1.61,
"learning_rate": 3.954536247136387e-05,
"loss": 0.258,
"step": 61
},
{
"epoch": 1.63,
"learning_rate": 3.95274299863389e-05,
"loss": 0.3562,
"step": 62
},
{
"epoch": 1.66,
"learning_rate": 3.9509154874243466e-05,
"loss": 0.3451,
"step": 63
},
{
"epoch": 1.68,
"learning_rate": 3.949053745573155e-05,
"loss": 0.3462,
"step": 64
},
{
"epoch": 1.71,
"learning_rate": 3.9471578057463206e-05,
"loss": 0.2999,
"step": 65
},
{
"epoch": 1.74,
"learning_rate": 3.9452277012098875e-05,
"loss": 0.3487,
"step": 66
},
{
"epoch": 1.76,
"learning_rate": 3.943263465829348e-05,
"loss": 0.3086,
"step": 67
},
{
"epoch": 1.79,
"learning_rate": 3.941265134069055e-05,
"loss": 0.2246,
"step": 68
},
{
"epoch": 1.82,
"learning_rate": 3.939232740991612e-05,
"loss": 0.4354,
"step": 69
},
{
"epoch": 1.84,
"learning_rate": 3.9371663222572625e-05,
"loss": 0.3244,
"step": 70
},
{
"epoch": 1.87,
"learning_rate": 3.93506591412326e-05,
"loss": 0.2683,
"step": 71
},
{
"epoch": 1.89,
"learning_rate": 3.932931553443235e-05,
"loss": 0.2599,
"step": 72
},
{
"epoch": 1.92,
"learning_rate": 3.930763277666548e-05,
"loss": 0.2989,
"step": 73
},
{
"epoch": 1.95,
"learning_rate": 3.92856112483763e-05,
"loss": 0.316,
"step": 74
},
{
"epoch": 1.97,
"learning_rate": 3.926325133595317e-05,
"loss": 0.213,
"step": 75
},
{
"epoch": 2.0,
"learning_rate": 3.924055343172172e-05,
"loss": 0.4325,
"step": 76
},
{
"epoch": 2.03,
"learning_rate": 3.9217517933937974e-05,
"loss": 0.441,
"step": 77
},
{
"epoch": 2.05,
"learning_rate": 3.9194145246781336e-05,
"loss": 0.3685,
"step": 78
},
{
"epoch": 2.08,
"learning_rate": 3.917043578034752e-05,
"loss": 0.2307,
"step": 79
},
{
"epoch": 2.11,
"learning_rate": 3.9146389950641345e-05,
"loss": 0.2507,
"step": 80
},
{
"epoch": 2.13,
"learning_rate": 3.912200817956945e-05,
"loss": 0.1716,
"step": 81
},
{
"epoch": 2.16,
"learning_rate": 3.9097290894932866e-05,
"loss": 0.2377,
"step": 82
},
{
"epoch": 2.18,
"learning_rate": 3.9072238530419525e-05,
"loss": 0.4068,
"step": 83
},
{
"epoch": 2.21,
"learning_rate": 3.9046851525596656e-05,
"loss": 0.1846,
"step": 84
},
{
"epoch": 2.24,
"learning_rate": 3.9021130325903076e-05,
"loss": 0.1923,
"step": 85
},
{
"epoch": 2.26,
"learning_rate": 3.899507538264134e-05,
"loss": 0.3062,
"step": 86
},
{
"epoch": 2.29,
"learning_rate": 3.896868715296987e-05,
"loss": 0.2967,
"step": 87
},
{
"epoch": 2.32,
"learning_rate": 3.894196609989489e-05,
"loss": 0.1879,
"step": 88
},
{
"epoch": 2.34,
"learning_rate": 3.891491269226234e-05,
"loss": 0.2129,
"step": 89
},
{
"epoch": 2.37,
"learning_rate": 3.888752740474962e-05,
"loss": 0.3089,
"step": 90
},
{
"epoch": 2.39,
"learning_rate": 3.8859810717857296e-05,
"loss": 0.237,
"step": 91
},
{
"epoch": 2.42,
"learning_rate": 3.8831763117900605e-05,
"loss": 0.3648,
"step": 92
},
{
"epoch": 2.45,
"learning_rate": 3.880338509700101e-05,
"loss": 0.264,
"step": 93
},
{
"epoch": 2.47,
"learning_rate": 3.8774677153077485e-05,
"loss": 0.3951,
"step": 94
},
{
"epoch": 2.5,
"learning_rate": 3.874563978983784e-05,
"loss": 0.3565,
"step": 95
},
{
"epoch": 2.53,
"learning_rate": 3.871627351676982e-05,
"loss": 0.3928,
"step": 96
},
{
"epoch": 2.55,
"learning_rate": 3.8686578849132244e-05,
"loss": 0.2163,
"step": 97
},
{
"epoch": 2.58,
"learning_rate": 3.8656556307945894e-05,
"loss": 0.2344,
"step": 98
},
{
"epoch": 2.61,
"learning_rate": 3.862620641998441e-05,
"loss": 0.2295,
"step": 99
},
{
"epoch": 2.63,
"learning_rate": 3.859552971776503e-05,
"loss": 0.2395,
"step": 100
},
{
"epoch": 2.66,
"learning_rate": 3.8564526739539266e-05,
"loss": 0.1045,
"step": 101
},
{
"epoch": 2.68,
"learning_rate": 3.853319802928345e-05,
"loss": 0.3289,
"step": 102
},
{
"epoch": 2.71,
"learning_rate": 3.850154413668916e-05,
"loss": 0.2843,
"step": 103
},
{
"epoch": 2.74,
"learning_rate": 3.8469565617153646e-05,
"loss": 0.194,
"step": 104
},
{
"epoch": 2.76,
"learning_rate": 3.8437263031770015e-05,
"loss": 0.2817,
"step": 105
},
{
"epoch": 2.79,
"learning_rate": 3.840463694731741e-05,
"loss": 0.0673,
"step": 106
},
{
"epoch": 2.82,
"learning_rate": 3.8371687936251085e-05,
"loss": 0.2645,
"step": 107
},
{
"epoch": 2.84,
"learning_rate": 3.8338416576692335e-05,
"loss": 0.2102,
"step": 108
},
{
"epoch": 2.87,
"learning_rate": 3.830482345241835e-05,
"loss": 0.2504,
"step": 109
},
{
"epoch": 2.89,
"learning_rate": 3.827090915285202e-05,
"loss": 0.2484,
"step": 110
},
{
"epoch": 2.92,
"learning_rate": 3.823667427305152e-05,
"loss": 0.4732,
"step": 111
},
{
"epoch": 2.95,
"learning_rate": 3.8202119413699914e-05,
"loss": 0.3838,
"step": 112
},
{
"epoch": 2.97,
"learning_rate": 3.816724518109463e-05,
"loss": 0.2097,
"step": 113
},
{
"epoch": 3.0,
"learning_rate": 3.813205218713676e-05,
"loss": 0.2695,
"step": 114
},
{
"epoch": 3.03,
"learning_rate": 3.809654104932039e-05,
"loss": 0.2515,
"step": 115
},
{
"epoch": 3.05,
"learning_rate": 3.806071239072175e-05,
"loss": 0.1516,
"step": 116
},
{
"epoch": 3.08,
"learning_rate": 3.802456683998823e-05,
"loss": 0.1934,
"step": 117
},
{
"epoch": 3.11,
"learning_rate": 3.798810503132742e-05,
"loss": 0.2033,
"step": 118
},
{
"epoch": 3.13,
"learning_rate": 3.7951327604495957e-05,
"loss": 0.2215,
"step": 119
},
{
"epoch": 3.16,
"learning_rate": 3.791423520478826e-05,
"loss": 0.2253,
"step": 120
},
{
"epoch": 3.18,
"learning_rate": 3.787682848302528e-05,
"loss": 0.3373,
"step": 121
},
{
"epoch": 3.21,
"learning_rate": 3.7839108095543016e-05,
"loss": 0.3479,
"step": 122
},
{
"epoch": 3.24,
"learning_rate": 3.780107470418105e-05,
"loss": 0.2841,
"step": 123
},
{
"epoch": 3.26,
"learning_rate": 3.7762728976270897e-05,
"loss": 0.1959,
"step": 124
},
{
"epoch": 3.29,
"learning_rate": 3.7724071584624296e-05,
"loss": 0.1712,
"step": 125
},
{
"epoch": 3.32,
"learning_rate": 3.768510320752145e-05,
"loss": 0.2421,
"step": 126
},
{
"epoch": 3.34,
"learning_rate": 3.764582452869907e-05,
"loss": 0.194,
"step": 127
},
{
"epoch": 3.37,
"learning_rate": 3.7606236237338406e-05,
"loss": 0.1826,
"step": 128
},
{
"epoch": 3.39,
"learning_rate": 3.756633902805316e-05,
"loss": 0.1903,
"step": 129
},
{
"epoch": 3.42,
"learning_rate": 3.7526133600877275e-05,
"loss": 0.1759,
"step": 130
},
{
"epoch": 3.45,
"learning_rate": 3.7485620661252676e-05,
"loss": 0.383,
"step": 131
},
{
"epoch": 3.47,
"learning_rate": 3.7444800920016875e-05,
"loss": 0.1564,
"step": 132
},
{
"epoch": 3.5,
"learning_rate": 3.740367509339052e-05,
"loss": 0.3796,
"step": 133
},
{
"epoch": 3.53,
"learning_rate": 3.736224390296479e-05,
"loss": 0.2463,
"step": 134
},
{
"epoch": 3.55,
"learning_rate": 3.732050807568878e-05,
"loss": 0.1915,
"step": 135
},
{
"epoch": 3.58,
"learning_rate": 3.727846834385671e-05,
"loss": 0.2983,
"step": 136
},
{
"epoch": 3.61,
"learning_rate": 3.72361254450951e-05,
"loss": 0.1864,
"step": 137
},
{
"epoch": 3.63,
"learning_rate": 3.7193480122349824e-05,
"loss": 0.2377,
"step": 138
},
{
"epoch": 3.66,
"learning_rate": 3.715053312387305e-05,
"loss": 0.1939,
"step": 139
},
{
"epoch": 3.68,
"learning_rate": 3.710728520321014e-05,
"loss": 0.2322,
"step": 140
},
{
"epoch": 3.71,
"learning_rate": 3.706373711918641e-05,
"loss": 0.125,
"step": 141
},
{
"epoch": 3.74,
"learning_rate": 3.701988963589384e-05,
"loss": 0.1978,
"step": 142
},
{
"epoch": 3.76,
"learning_rate": 3.697574352267764e-05,
"loss": 0.2727,
"step": 143
},
{
"epoch": 3.79,
"learning_rate": 3.6931299554122754e-05,
"loss": 0.2192,
"step": 144
},
{
"epoch": 3.82,
"learning_rate": 3.6886558510040305e-05,
"loss": 0.2627,
"step": 145
},
{
"epoch": 3.84,
"learning_rate": 3.684152117545385e-05,
"loss": 0.1493,
"step": 146
},
{
"epoch": 3.87,
"learning_rate": 3.679618834058566e-05,
"loss": 0.2359,
"step": 147
},
{
"epoch": 3.89,
"learning_rate": 3.675056080084284e-05,
"loss": 0.2793,
"step": 148
},
{
"epoch": 3.92,
"learning_rate": 3.670463935680335e-05,
"loss": 0.3028,
"step": 149
},
{
"epoch": 3.95,
"learning_rate": 3.665842481420199e-05,
"loss": 0.2128,
"step": 150
},
{
"epoch": 3.97,
"learning_rate": 3.661191798391626e-05,
"loss": 0.2562,
"step": 151
},
{
"epoch": 4.0,
"learning_rate": 3.6565119681952086e-05,
"loss": 0.159,
"step": 152
},
{
"epoch": 4.03,
"learning_rate": 3.651803072942957e-05,
"loss": 0.2481,
"step": 153
},
{
"epoch": 4.05,
"learning_rate": 3.647065195256855e-05,
"loss": 0.1613,
"step": 154
},
{
"epoch": 4.08,
"learning_rate": 3.642298418267408e-05,
"loss": 0.2321,
"step": 155
},
{
"epoch": 4.11,
"learning_rate": 3.637502825612189e-05,
"loss": 0.1113,
"step": 156
},
{
"epoch": 4.13,
"learning_rate": 3.632678501434368e-05,
"loss": 0.2206,
"step": 157
},
{
"epoch": 4.16,
"learning_rate": 3.6278255303812366e-05,
"loss": 0.193,
"step": 158
},
{
"epoch": 4.18,
"learning_rate": 3.622943997602722e-05,
"loss": 0.0902,
"step": 159
},
{
"epoch": 4.21,
"learning_rate": 3.6180339887498953e-05,
"loss": 0.3044,
"step": 160
},
{
"epoch": 4.24,
"learning_rate": 3.613095589973465e-05,
"loss": 0.0721,
"step": 161
},
{
"epoch": 4.26,
"learning_rate": 3.6081288879222696e-05,
"loss": 0.2974,
"step": 162
},
{
"epoch": 4.29,
"learning_rate": 3.6031339697417535e-05,
"loss": 0.0796,
"step": 163
},
{
"epoch": 4.32,
"learning_rate": 3.59811092307244e-05,
"loss": 0.152,
"step": 164
},
{
"epoch": 4.34,
"learning_rate": 3.5930598360483926e-05,
"loss": 0.2259,
"step": 165
},
{
"epoch": 4.37,
"learning_rate": 3.587980797295671e-05,
"loss": 0.2136,
"step": 166
},
{
"epoch": 4.39,
"learning_rate": 3.5828738959307715e-05,
"loss": 0.2821,
"step": 167
},
{
"epoch": 4.42,
"learning_rate": 3.577739221559069e-05,
"loss": 0.2553,
"step": 168
},
{
"epoch": 4.45,
"learning_rate": 3.572576864273238e-05,
"loss": 0.0768,
"step": 169
},
{
"epoch": 4.47,
"learning_rate": 3.56738691465168e-05,
"loss": 0.2053,
"step": 170
},
{
"epoch": 4.5,
"learning_rate": 3.562169463756927e-05,
"loss": 0.2989,
"step": 171
},
{
"epoch": 4.53,
"learning_rate": 3.5569246031340474e-05,
"loss": 0.1637,
"step": 172
},
{
"epoch": 4.55,
"learning_rate": 3.551652424809039e-05,
"loss": 0.3084,
"step": 173
},
{
"epoch": 4.58,
"learning_rate": 3.5463530212872145e-05,
"loss": 0.2403,
"step": 174
},
{
"epoch": 4.61,
"learning_rate": 3.541026485551579e-05,
"loss": 0.433,
"step": 175
},
{
"epoch": 4.63,
"learning_rate": 3.535672911061196e-05,
"loss": 0.22,
"step": 176
},
{
"epoch": 4.66,
"learning_rate": 3.530292391749549e-05,
"loss": 0.1963,
"step": 177
},
{
"epoch": 4.68,
"learning_rate": 3.524885022022896e-05,
"loss": 0.1768,
"step": 178
},
{
"epoch": 4.71,
"learning_rate": 3.51945089675861e-05,
"loss": 0.2105,
"step": 179
},
{
"epoch": 4.74,
"learning_rate": 3.513990111303513e-05,
"loss": 0.1311,
"step": 180
},
{
"epoch": 4.76,
"learning_rate": 3.508502761472208e-05,
"loss": 0.1729,
"step": 181
},
{
"epoch": 4.79,
"learning_rate": 3.5029889435453924e-05,
"loss": 0.152,
"step": 182
},
{
"epoch": 4.82,
"learning_rate": 3.497448754268173e-05,
"loss": 0.2048,
"step": 183
},
{
"epoch": 4.84,
"learning_rate": 3.4918822908483645e-05,
"loss": 0.2281,
"step": 184
},
{
"epoch": 4.87,
"learning_rate": 3.4862896509547886e-05,
"loss": 0.1982,
"step": 185
},
{
"epoch": 4.89,
"learning_rate": 3.4806709327155564e-05,
"loss": 0.2202,
"step": 186
},
{
"epoch": 4.92,
"learning_rate": 3.475026234716348e-05,
"loss": 0.2121,
"step": 187
},
{
"epoch": 4.95,
"learning_rate": 3.469355655998683e-05,
"loss": 0.1315,
"step": 188
},
{
"epoch": 4.97,
"learning_rate": 3.4636592960581825e-05,
"loss": 0.217,
"step": 189
},
{
"epoch": 5.0,
"learning_rate": 3.457937254842823e-05,
"loss": 0.1935,
"step": 190
},
{
"epoch": 5.03,
"learning_rate": 3.4521896327511836e-05,
"loss": 0.4058,
"step": 191
},
{
"epoch": 5.05,
"learning_rate": 3.4464165306306845e-05,
"loss": 0.085,
"step": 192
},
{
"epoch": 5.08,
"learning_rate": 3.440618049775814e-05,
"loss": 0.1464,
"step": 193
},
{
"epoch": 5.11,
"learning_rate": 3.434794291926358e-05,
"loss": 0.1512,
"step": 194
},
{
"epoch": 5.13,
"learning_rate": 3.428945359265607e-05,
"loss": 0.1294,
"step": 195
},
{
"epoch": 5.16,
"learning_rate": 3.423071354418571e-05,
"loss": 0.1927,
"step": 196
},
{
"epoch": 5.18,
"learning_rate": 3.417172380450172e-05,
"loss": 0.1937,
"step": 197
},
{
"epoch": 5.21,
"learning_rate": 3.411248540863442e-05,
"loss": 0.1565,
"step": 198
},
{
"epoch": 5.24,
"learning_rate": 3.405299939597699e-05,
"loss": 0.2907,
"step": 199
},
{
"epoch": 5.26,
"learning_rate": 3.399326681026731e-05,
"loss": 0.119,
"step": 200
},
{
"epoch": 5.29,
"learning_rate": 3.393328869956962e-05,
"loss": 0.1828,
"step": 201
},
{
"epoch": 5.32,
"learning_rate": 3.38730661162561e-05,
"loss": 0.1624,
"step": 202
},
{
"epoch": 5.34,
"learning_rate": 3.381260011698846e-05,
"loss": 0.2448,
"step": 203
},
{
"epoch": 5.37,
"learning_rate": 3.375189176269935e-05,
"loss": 0.1497,
"step": 204
},
{
"epoch": 5.39,
"learning_rate": 3.369094211857378e-05,
"loss": 0.1374,
"step": 205
},
{
"epoch": 5.42,
"learning_rate": 3.36297522540304e-05,
"loss": 0.1482,
"step": 206
},
{
"epoch": 5.45,
"learning_rate": 3.356832324270277e-05,
"loss": 0.1697,
"step": 207
},
{
"epoch": 5.47,
"learning_rate": 3.350665616242049e-05,
"loss": 0.1699,
"step": 208
},
{
"epoch": 5.5,
"learning_rate": 3.3444752095190326e-05,
"loss": 0.1813,
"step": 209
},
{
"epoch": 5.53,
"learning_rate": 3.3382612127177166e-05,
"loss": 0.2908,
"step": 210
},
{
"epoch": 5.55,
"learning_rate": 3.332023734868504e-05,
"loss": 0.1347,
"step": 211
},
{
"epoch": 5.58,
"learning_rate": 3.325762885413791e-05,
"loss": 0.1451,
"step": 212
},
{
"epoch": 5.61,
"learning_rate": 3.319478774206053e-05,
"loss": 0.1993,
"step": 213
},
{
"epoch": 5.63,
"learning_rate": 3.3131715115059134e-05,
"loss": 0.1173,
"step": 214
},
{
"epoch": 5.66,
"learning_rate": 3.3068412079802114e-05,
"loss": 0.212,
"step": 215
},
{
"epoch": 5.68,
"learning_rate": 3.300487974700058e-05,
"loss": 0.2662,
"step": 216
},
{
"epoch": 5.71,
"learning_rate": 3.294111923138889e-05,
"loss": 0.1773,
"step": 217
},
{
"epoch": 5.74,
"learning_rate": 3.287713165170508e-05,
"loss": 0.1837,
"step": 218
},
{
"epoch": 5.76,
"learning_rate": 3.281291813067123e-05,
"loss": 0.1091,
"step": 219
},
{
"epoch": 5.79,
"learning_rate": 3.27484797949738e-05,
"loss": 0.0838,
"step": 220
},
{
"epoch": 5.82,
"learning_rate": 3.2683817775243795e-05,
"loss": 0.1391,
"step": 221
},
{
"epoch": 5.84,
"learning_rate": 3.2618933206036994e-05,
"loss": 0.2812,
"step": 222
},
{
"epoch": 5.87,
"learning_rate": 3.255382722581401e-05,
"loss": 0.1579,
"step": 223
},
{
"epoch": 5.89,
"learning_rate": 3.248850097692032e-05,
"loss": 0.2081,
"step": 224
},
{
"epoch": 5.92,
"learning_rate": 3.242295560556621e-05,
"loss": 0.1195,
"step": 225
},
{
"epoch": 5.95,
"learning_rate": 3.235719226180669e-05,
"loss": 0.209,
"step": 226
},
{
"epoch": 5.97,
"learning_rate": 3.229121209952129e-05,
"loss": 0.3294,
"step": 227
},
{
"epoch": 6.0,
"learning_rate": 3.222501627639384e-05,
"loss": 0.1801,
"step": 228
},
{
"epoch": 6.03,
"learning_rate": 3.215860595389211e-05,
"loss": 0.2359,
"step": 229
},
{
"epoch": 6.05,
"learning_rate": 3.2091982297247505e-05,
"loss": 0.0893,
"step": 230
},
{
"epoch": 6.08,
"learning_rate": 3.202514647543454e-05,
"loss": 0.1252,
"step": 231
},
{
"epoch": 6.11,
"learning_rate": 3.195809966115038e-05,
"loss": 0.1317,
"step": 232
},
{
"epoch": 6.13,
"learning_rate": 3.189084303079427e-05,
"loss": 0.2122,
"step": 233
},
{
"epoch": 6.16,
"learning_rate": 3.182337776444684e-05,
"loss": 0.0898,
"step": 234
},
{
"epoch": 6.18,
"learning_rate": 3.1755705045849465e-05,
"loss": 0.2762,
"step": 235
},
{
"epoch": 6.21,
"learning_rate": 3.1687826062383444e-05,
"loss": 0.0969,
"step": 236
},
{
"epoch": 6.24,
"learning_rate": 3.1619742005049204e-05,
"loss": 0.1663,
"step": 237
},
{
"epoch": 6.26,
"learning_rate": 3.155145406844535e-05,
"loss": 0.1702,
"step": 238
},
{
"epoch": 6.29,
"learning_rate": 3.148296345074779e-05,
"loss": 0.1498,
"step": 239
},
{
"epoch": 6.32,
"learning_rate": 3.141427135368864e-05,
"loss": 0.2292,
"step": 240
},
{
"epoch": 6.34,
"learning_rate": 3.134537898253514e-05,
"loss": 0.1987,
"step": 241
},
{
"epoch": 6.37,
"learning_rate": 3.1276287546068536e-05,
"loss": 0.1855,
"step": 242
},
{
"epoch": 6.39,
"learning_rate": 3.1206998256562894e-05,
"loss": 0.225,
"step": 243
},
{
"epoch": 6.42,
"learning_rate": 3.113751232976376e-05,
"loss": 0.1875,
"step": 244
},
{
"epoch": 6.45,
"learning_rate": 3.106783098486688e-05,
"loss": 0.1781,
"step": 245
},
{
"epoch": 6.47,
"learning_rate": 3.09979554444968e-05,
"loss": 0.1794,
"step": 246
},
{
"epoch": 6.5,
"learning_rate": 3.092788693468539e-05,
"loss": 0.1698,
"step": 247
},
{
"epoch": 6.53,
"learning_rate": 3.0857626684850355e-05,
"loss": 0.1616,
"step": 248
},
{
"epoch": 6.55,
"learning_rate": 3.078717592777367e-05,
"loss": 0.1897,
"step": 249
},
{
"epoch": 6.58,
"learning_rate": 3.0716535899579936e-05,
"loss": 0.1124,
"step": 250
},
{
"epoch": 6.61,
"learning_rate": 3.064570783971468e-05,
"loss": 0.1512,
"step": 251
},
{
"epoch": 6.63,
"learning_rate": 3.057469299092264e-05,
"loss": 0.0991,
"step": 252
},
{
"epoch": 6.66,
"learning_rate": 3.0503492599225918e-05,
"loss": 0.0772,
"step": 253
},
{
"epoch": 6.68,
"learning_rate": 3.0432107913902162e-05,
"loss": 0.193,
"step": 254
},
{
"epoch": 6.71,
"learning_rate": 3.036054018746261e-05,
"loss": 0.1688,
"step": 255
},
{
"epoch": 6.74,
"learning_rate": 3.028879067563013e-05,
"loss": 0.1048,
"step": 256
},
{
"epoch": 6.76,
"learning_rate": 3.02168606373172e-05,
"loss": 0.3042,
"step": 257
},
{
"epoch": 6.79,
"learning_rate": 3.014475133460378e-05,
"loss": 0.1962,
"step": 258
},
{
"epoch": 6.82,
"learning_rate": 3.007246403271522e-05,
"loss": 0.105,
"step": 259
},
{
"epoch": 6.84,
"learning_rate": 3.0000000000000004e-05,
"loss": 0.303,
"step": 260
},
{
"epoch": 6.87,
"learning_rate": 2.992736050790754e-05,
"loss": 0.2243,
"step": 261
},
{
"epoch": 6.89,
"learning_rate": 2.9854546830965833e-05,
"loss": 0.1246,
"step": 262
},
{
"epoch": 6.92,
"learning_rate": 2.978156024675913e-05,
"loss": 0.1287,
"step": 263
},
{
"epoch": 6.95,
"learning_rate": 2.970840203590548e-05,
"loss": 0.1729,
"step": 264
},
{
"epoch": 6.97,
"learning_rate": 2.9635073482034307e-05,
"loss": 0.0749,
"step": 265
},
{
"epoch": 7.0,
"learning_rate": 2.956157587176385e-05,
"loss": 0.1655,
"step": 266
},
{
"epoch": 7.03,
"learning_rate": 2.9487910494678588e-05,
"loss": 0.1562,
"step": 267
},
{
"epoch": 7.05,
"learning_rate": 2.941407864330666e-05,
"loss": 0.0815,
"step": 268
},
{
"epoch": 7.08,
"learning_rate": 2.934008161309711e-05,
"loss": 0.3197,
"step": 269
},
{
"epoch": 7.11,
"learning_rate": 2.926592070239724e-05,
"loss": 0.1408,
"step": 270
},
{
"epoch": 7.13,
"learning_rate": 2.9191597212429763e-05,
"loss": 0.2064,
"step": 271
},
{
"epoch": 7.16,
"learning_rate": 2.9117112447270007e-05,
"loss": 0.1036,
"step": 272
},
{
"epoch": 7.18,
"learning_rate": 2.9042467713823015e-05,
"loss": 0.1134,
"step": 273
},
{
"epoch": 7.21,
"learning_rate": 2.8967664321800653e-05,
"loss": 0.1781,
"step": 274
},
{
"epoch": 7.24,
"learning_rate": 2.8892703583698553e-05,
"loss": 0.1843,
"step": 275
},
{
"epoch": 7.26,
"learning_rate": 2.8817586814773174e-05,
"loss": 0.2199,
"step": 276
},
{
"epoch": 7.29,
"learning_rate": 2.874231533301866e-05,
"loss": 0.1608,
"step": 277
},
{
"epoch": 7.32,
"learning_rate": 2.8666890459143748e-05,
"loss": 0.1271,
"step": 278
},
{
"epoch": 7.34,
"learning_rate": 2.8591313516548566e-05,
"loss": 0.0874,
"step": 279
},
{
"epoch": 7.37,
"learning_rate": 2.8515585831301456e-05,
"loss": 0.2306,
"step": 280
},
{
"epoch": 7.39,
"learning_rate": 2.8439708732115662e-05,
"loss": 0.1641,
"step": 281
},
{
"epoch": 7.42,
"learning_rate": 2.8363683550326028e-05,
"loss": 0.1308,
"step": 282
},
{
"epoch": 7.45,
"learning_rate": 2.8287511619865687e-05,
"loss": 0.1435,
"step": 283
},
{
"epoch": 7.47,
"learning_rate": 2.8211194277242563e-05,
"loss": 0.1696,
"step": 284
},
{
"epoch": 7.5,
"learning_rate": 2.813473286151601e-05,
"loss": 0.1705,
"step": 285
},
{
"epoch": 7.53,
"learning_rate": 2.8058128714273257e-05,
"loss": 0.2127,
"step": 286
},
{
"epoch": 7.55,
"learning_rate": 2.798138317960591e-05,
"loss": 0.1692,
"step": 287
},
{
"epoch": 7.58,
"learning_rate": 2.7904497604086333e-05,
"loss": 0.1731,
"step": 288
},
{
"epoch": 7.61,
"learning_rate": 2.7827473336744054e-05,
"loss": 0.2061,
"step": 289
},
{
"epoch": 7.63,
"learning_rate": 2.7750311729042062e-05,
"loss": 0.0872,
"step": 290
},
{
"epoch": 7.66,
"learning_rate": 2.767301413485313e-05,
"loss": 0.1252,
"step": 291
},
{
"epoch": 7.68,
"learning_rate": 2.759558191043603e-05,
"loss": 0.2098,
"step": 292
},
{
"epoch": 7.71,
"learning_rate": 2.7518016414411737e-05,
"loss": 0.1598,
"step": 293
},
{
"epoch": 7.74,
"learning_rate": 2.7440319007739632e-05,
"loss": 0.0742,
"step": 294
},
{
"epoch": 7.76,
"learning_rate": 2.7362491053693564e-05,
"loss": 0.0892,
"step": 295
},
{
"epoch": 7.79,
"learning_rate": 2.728453391783797e-05,
"loss": 0.0556,
"step": 296
},
{
"epoch": 7.82,
"learning_rate": 2.7206448968003898e-05,
"loss": 0.0662,
"step": 297
},
{
"epoch": 7.84,
"learning_rate": 2.7128237574265014e-05,
"loss": 0.1099,
"step": 298
},
{
"epoch": 7.87,
"learning_rate": 2.7049901108913573e-05,
"loss": 0.1318,
"step": 299
},
{
"epoch": 7.89,
"learning_rate": 2.6971440946436306e-05,
"loss": 0.1283,
"step": 300
},
{
"epoch": 7.92,
"learning_rate": 2.689285846349034e-05,
"loss": 0.1493,
"step": 301
},
{
"epoch": 7.95,
"learning_rate": 2.681415503887904e-05,
"loss": 0.2968,
"step": 302
},
{
"epoch": 7.97,
"learning_rate": 2.6735332053527768e-05,
"loss": 0.2015,
"step": 303
},
{
"epoch": 8.0,
"learning_rate": 2.6656390890459737e-05,
"loss": 0.1143,
"step": 304
},
{
"epoch": 8.03,
"learning_rate": 2.6577332934771667e-05,
"loss": 0.1593,
"step": 305
},
{
"epoch": 8.05,
"learning_rate": 2.649815957360953e-05,
"loss": 0.1453,
"step": 306
},
{
"epoch": 8.08,
"learning_rate": 2.641887219614419e-05,
"loss": 0.088,
"step": 307
},
{
"epoch": 8.11,
"learning_rate": 2.633947219354704e-05,
"loss": 0.0893,
"step": 308
},
{
"epoch": 8.13,
"learning_rate": 2.6259960958965566e-05,
"loss": 0.1731,
"step": 309
},
{
"epoch": 8.16,
"learning_rate": 2.618033988749895e-05,
"loss": 0.1283,
"step": 310
},
{
"epoch": 8.18,
"learning_rate": 2.6100610376173555e-05,
"loss": 0.1619,
"step": 311
},
{
"epoch": 8.21,
"learning_rate": 2.6020773823918414e-05,
"loss": 0.1354,
"step": 312
},
{
"epoch": 8.24,
"learning_rate": 2.59408316315407e-05,
"loss": 0.1543,
"step": 313
},
{
"epoch": 8.26,
"learning_rate": 2.5860785201701147e-05,
"loss": 0.1447,
"step": 314
},
{
"epoch": 8.29,
"learning_rate": 2.5780635938889433e-05,
"loss": 0.105,
"step": 315
},
{
"epoch": 8.32,
"learning_rate": 2.5700385249399525e-05,
"loss": 0.1646,
"step": 316
},
{
"epoch": 8.34,
"learning_rate": 2.5620034541305026e-05,
"loss": 0.1084,
"step": 317
},
{
"epoch": 8.37,
"learning_rate": 2.5539585224434448e-05,
"loss": 0.2339,
"step": 318
},
{
"epoch": 8.39,
"learning_rate": 2.5459038710346507e-05,
"loss": 0.1193,
"step": 319
},
{
"epoch": 8.42,
"learning_rate": 2.5378396412305315e-05,
"loss": 0.2211,
"step": 320
},
{
"epoch": 8.45,
"learning_rate": 2.5297659745255618e-05,
"loss": 0.1543,
"step": 321
},
{
"epoch": 8.47,
"learning_rate": 2.5216830125797943e-05,
"loss": 0.0845,
"step": 322
},
{
"epoch": 8.5,
"learning_rate": 2.513590897216376e-05,
"loss": 0.1312,
"step": 323
},
{
"epoch": 8.53,
"learning_rate": 2.505489770419059e-05,
"loss": 0.0971,
"step": 324
},
{
"epoch": 8.55,
"learning_rate": 2.4973797743297103e-05,
"loss": 0.0927,
"step": 325
},
{
"epoch": 8.58,
"learning_rate": 2.489261051245815e-05,
"loss": 0.1674,
"step": 326
},
{
"epoch": 8.61,
"learning_rate": 2.4811337436179835e-05,
"loss": 0.2524,
"step": 327
},
{
"epoch": 8.63,
"learning_rate": 2.47299799404745e-05,
"loss": 0.1002,
"step": 328
},
{
"epoch": 8.66,
"learning_rate": 2.4648539452835682e-05,
"loss": 0.1017,
"step": 329
},
{
"epoch": 8.68,
"learning_rate": 2.4567017402213118e-05,
"loss": 0.176,
"step": 330
},
{
"epoch": 8.71,
"learning_rate": 2.4485415218987628e-05,
"loss": 0.1903,
"step": 331
},
{
"epoch": 8.74,
"learning_rate": 2.440373433494603e-05,
"loss": 0.2088,
"step": 332
},
{
"epoch": 8.76,
"learning_rate": 2.4321976183256045e-05,
"loss": 0.2211,
"step": 333
},
{
"epoch": 8.79,
"learning_rate": 2.42401421984411e-05,
"loss": 0.1466,
"step": 334
},
{
"epoch": 8.82,
"learning_rate": 2.4158233816355185e-05,
"loss": 0.071,
"step": 335
},
{
"epoch": 8.84,
"learning_rate": 2.40762524741577e-05,
"loss": 0.1354,
"step": 336
},
{
"epoch": 8.87,
"learning_rate": 2.3994199610288142e-05,
"loss": 0.2116,
"step": 337
},
{
"epoch": 8.89,
"learning_rate": 2.3912076664440967e-05,
"loss": 0.0774,
"step": 338
},
{
"epoch": 8.92,
"learning_rate": 2.382988507754026e-05,
"loss": 0.1502,
"step": 339
},
{
"epoch": 8.95,
"learning_rate": 2.37476262917145e-05,
"loss": 0.0959,
"step": 340
},
{
"epoch": 8.97,
"learning_rate": 2.3665301750271198e-05,
"loss": 0.1015,
"step": 341
},
{
"epoch": 9.0,
"learning_rate": 2.358291289767165e-05,
"loss": 0.1029,
"step": 342
},
{
"epoch": 9.03,
"learning_rate": 2.3500461179505526e-05,
"loss": 0.1072,
"step": 343
},
{
"epoch": 9.05,
"learning_rate": 2.3417948042465536e-05,
"loss": 0.0998,
"step": 344
},
{
"epoch": 9.08,
"learning_rate": 2.333537493432205e-05,
"loss": 0.0975,
"step": 345
},
{
"epoch": 9.11,
"learning_rate": 2.3252743303897677e-05,
"loss": 0.0774,
"step": 346
},
{
"epoch": 9.13,
"learning_rate": 2.317005460104186e-05,
"loss": 0.1363,
"step": 347
},
{
"epoch": 9.16,
"learning_rate": 2.3087310276605428e-05,
"loss": 0.1714,
"step": 348
},
{
"epoch": 9.18,
"learning_rate": 2.3004511782415145e-05,
"loss": 0.1232,
"step": 349
},
{
"epoch": 9.21,
"learning_rate": 2.2921660571248237e-05,
"loss": 0.1653,
"step": 350
},
{
"epoch": 9.24,
"learning_rate": 2.283875809680689e-05,
"loss": 0.1097,
"step": 351
},
{
"epoch": 9.26,
"learning_rate": 2.275580581369276e-05,
"loss": 0.1705,
"step": 352
},
{
"epoch": 9.29,
"learning_rate": 2.2672805177381453e-05,
"loss": 0.0928,
"step": 353
},
{
"epoch": 9.32,
"learning_rate": 2.258975764419694e-05,
"loss": 0.2008,
"step": 354
},
{
"epoch": 9.34,
"learning_rate": 2.2506664671286087e-05,
"loss": 0.1516,
"step": 355
},
{
"epoch": 9.37,
"learning_rate": 2.2423527716593014e-05,
"loss": 0.2086,
"step": 356
},
{
"epoch": 9.39,
"learning_rate": 2.2340348238833555e-05,
"loss": 0.1769,
"step": 357
},
{
"epoch": 9.42,
"learning_rate": 2.2257127697469634e-05,
"loss": 0.0859,
"step": 358
},
{
"epoch": 9.45,
"learning_rate": 2.2173867552683707e-05,
"loss": 0.0945,
"step": 359
},
{
"epoch": 9.47,
"learning_rate": 2.209056926535307e-05,
"loss": 0.2011,
"step": 360
},
{
"epoch": 9.5,
"learning_rate": 2.2007234297024298e-05,
"loss": 0.1887,
"step": 361
},
{
"epoch": 9.53,
"learning_rate": 2.1923864109887556e-05,
"loss": 0.1048,
"step": 362
},
{
"epoch": 9.55,
"learning_rate": 2.1840460166750947e-05,
"loss": 0.1283,
"step": 363
},
{
"epoch": 9.58,
"learning_rate": 2.175702393101487e-05,
"loss": 0.1383,
"step": 364
},
{
"epoch": 9.61,
"learning_rate": 2.167355686664632e-05,
"loss": 0.1413,
"step": 365
},
{
"epoch": 9.63,
"learning_rate": 2.15900604381532e-05,
"loss": 0.1823,
"step": 366
},
{
"epoch": 9.66,
"learning_rate": 2.1506536110558657e-05,
"loss": 0.1718,
"step": 367
},
{
"epoch": 9.68,
"learning_rate": 2.142298534937534e-05,
"loss": 0.1991,
"step": 368
},
{
"epoch": 9.71,
"learning_rate": 2.1339409620579704e-05,
"loss": 0.0877,
"step": 369
},
{
"epoch": 9.74,
"learning_rate": 2.125581039058627e-05,
"loss": 0.0812,
"step": 370
},
{
"epoch": 9.76,
"learning_rate": 2.117218912622193e-05,
"loss": 0.1335,
"step": 371
},
{
"epoch": 9.79,
"learning_rate": 2.1088547294700182e-05,
"loss": 0.1302,
"step": 372
},
{
"epoch": 9.82,
"learning_rate": 2.1004886363595392e-05,
"loss": 0.1708,
"step": 373
},
{
"epoch": 9.84,
"learning_rate": 2.0921207800817045e-05,
"loss": 0.0997,
"step": 374
},
{
"epoch": 9.87,
"learning_rate": 2.0837513074583993e-05,
"loss": 0.116,
"step": 375
},
{
"epoch": 9.89,
"learning_rate": 2.0753803653398697e-05,
"loss": 0.1274,
"step": 376
},
{
"epoch": 9.92,
"learning_rate": 2.067008100602143e-05,
"loss": 0.0965,
"step": 377
},
{
"epoch": 9.95,
"learning_rate": 2.0586346601444573e-05,
"loss": 0.0682,
"step": 378
},
{
"epoch": 9.97,
"learning_rate": 2.0502601908866754e-05,
"loss": 0.1405,
"step": 379
},
{
"epoch": 10.0,
"learning_rate": 2.0418848397667142e-05,
"loss": 0.0438,
"step": 380
},
{
"epoch": 10.03,
"learning_rate": 2.0335087537379632e-05,
"loss": 0.1818,
"step": 381
},
{
"epoch": 10.05,
"learning_rate": 2.0251320797667056e-05,
"loss": 0.1675,
"step": 382
},
{
"epoch": 10.08,
"learning_rate": 2.0167549648295413e-05,
"loss": 0.1699,
"step": 383
},
{
"epoch": 10.11,
"learning_rate": 2.0083775559108082e-05,
"loss": 0.0459,
"step": 384
},
{
"epoch": 10.13,
"learning_rate": 2e-05,
"loss": 0.1314,
"step": 385
},
{
"epoch": 10.16,
"learning_rate": 1.9916224440891928e-05,
"loss": 0.1383,
"step": 386
},
{
"epoch": 10.18,
"learning_rate": 1.983245035170459e-05,
"loss": 0.0661,
"step": 387
},
{
"epoch": 10.21,
"learning_rate": 1.9748679202332948e-05,
"loss": 0.1153,
"step": 388
},
{
"epoch": 10.24,
"learning_rate": 1.9664912462620378e-05,
"loss": 0.0413,
"step": 389
},
{
"epoch": 10.26,
"learning_rate": 1.9581151602332865e-05,
"loss": 0.0914,
"step": 390
},
{
"epoch": 10.29,
"learning_rate": 1.9497398091133253e-05,
"loss": 0.1503,
"step": 391
},
{
"epoch": 10.32,
"learning_rate": 1.9413653398555437e-05,
"loss": 0.0606,
"step": 392
},
{
"epoch": 10.34,
"learning_rate": 1.9329918993978573e-05,
"loss": 0.1149,
"step": 393
},
{
"epoch": 10.37,
"learning_rate": 1.924619634660131e-05,
"loss": 0.1304,
"step": 394
},
{
"epoch": 10.39,
"learning_rate": 1.9162486925416014e-05,
"loss": 0.1002,
"step": 395
},
{
"epoch": 10.42,
"learning_rate": 1.9078792199182954e-05,
"loss": 0.1102,
"step": 396
},
{
"epoch": 10.45,
"learning_rate": 1.899511363640461e-05,
"loss": 0.0848,
"step": 397
},
{
"epoch": 10.47,
"learning_rate": 1.891145270529982e-05,
"loss": 0.1889,
"step": 398
},
{
"epoch": 10.5,
"learning_rate": 1.882781087377807e-05,
"loss": 0.0923,
"step": 399
},
{
"epoch": 10.53,
"learning_rate": 1.8744189609413733e-05,
"loss": 0.0859,
"step": 400
},
{
"epoch": 10.55,
"learning_rate": 1.8660590379420306e-05,
"loss": 0.1308,
"step": 401
},
{
"epoch": 10.58,
"learning_rate": 1.857701465062467e-05,
"loss": 0.1854,
"step": 402
},
{
"epoch": 10.61,
"learning_rate": 1.849346388944135e-05,
"loss": 0.0932,
"step": 403
},
{
"epoch": 10.63,
"learning_rate": 1.8409939561846808e-05,
"loss": 0.1364,
"step": 404
},
{
"epoch": 10.66,
"learning_rate": 1.8326443133353695e-05,
"loss": 0.2408,
"step": 405
},
{
"epoch": 10.68,
"learning_rate": 1.8242976068985137e-05,
"loss": 0.1179,
"step": 406
},
{
"epoch": 10.71,
"learning_rate": 1.815953983324906e-05,
"loss": 0.1073,
"step": 407
},
{
"epoch": 10.74,
"learning_rate": 1.8076135890112457e-05,
"loss": 0.0655,
"step": 408
},
{
"epoch": 10.76,
"learning_rate": 1.7992765702975702e-05,
"loss": 0.1538,
"step": 409
},
{
"epoch": 10.79,
"learning_rate": 1.7909430734646936e-05,
"loss": 0.0903,
"step": 410
},
{
"epoch": 10.82,
"learning_rate": 1.7826132447316303e-05,
"loss": 0.1715,
"step": 411
},
{
"epoch": 10.84,
"learning_rate": 1.7742872302530366e-05,
"loss": 0.2522,
"step": 412
},
{
"epoch": 10.87,
"learning_rate": 1.7659651761166455e-05,
"loss": 0.0746,
"step": 413
},
{
"epoch": 10.89,
"learning_rate": 1.7576472283406996e-05,
"loss": 0.0989,
"step": 414
},
{
"epoch": 10.92,
"learning_rate": 1.7493335328713913e-05,
"loss": 0.1917,
"step": 415
},
{
"epoch": 10.95,
"learning_rate": 1.7410242355803064e-05,
"loss": 0.1217,
"step": 416
},
{
"epoch": 10.97,
"learning_rate": 1.7327194822618557e-05,
"loss": 0.1232,
"step": 417
},
{
"epoch": 11.0,
"learning_rate": 1.724419418630724e-05,
"loss": 0.0488,
"step": 418
},
{
"epoch": 11.03,
"learning_rate": 1.7161241903193112e-05,
"loss": 0.162,
"step": 419
},
{
"epoch": 11.05,
"learning_rate": 1.707833942875177e-05,
"loss": 0.1006,
"step": 420
},
{
"epoch": 11.08,
"learning_rate": 1.699548821758486e-05,
"loss": 0.1032,
"step": 421
},
{
"epoch": 11.11,
"learning_rate": 1.691268972339458e-05,
"loss": 0.049,
"step": 422
},
{
"epoch": 11.13,
"learning_rate": 1.6829945398958152e-05,
"loss": 0.1613,
"step": 423
},
{
"epoch": 11.16,
"learning_rate": 1.674725669610233e-05,
"loss": 0.1608,
"step": 424
},
{
"epoch": 11.18,
"learning_rate": 1.6664625065677957e-05,
"loss": 0.1634,
"step": 425
},
{
"epoch": 11.21,
"learning_rate": 1.658205195753447e-05,
"loss": 0.1551,
"step": 426
},
{
"epoch": 11.24,
"learning_rate": 1.6499538820494477e-05,
"loss": 0.1071,
"step": 427
},
{
"epoch": 11.26,
"learning_rate": 1.6417087102328356e-05,
"loss": 0.0577,
"step": 428
},
{
"epoch": 11.29,
"learning_rate": 1.6334698249728812e-05,
"loss": 0.0964,
"step": 429
},
{
"epoch": 11.32,
"learning_rate": 1.6252373708285505e-05,
"loss": 0.0499,
"step": 430
},
{
"epoch": 11.34,
"learning_rate": 1.617011492245974e-05,
"loss": 0.1025,
"step": 431
},
{
"epoch": 11.37,
"learning_rate": 1.608792333555904e-05,
"loss": 0.0622,
"step": 432
},
{
"epoch": 11.39,
"learning_rate": 1.600580038971186e-05,
"loss": 0.2109,
"step": 433
},
{
"epoch": 11.42,
"learning_rate": 1.5923747525842306e-05,
"loss": 0.1395,
"step": 434
},
{
"epoch": 11.45,
"learning_rate": 1.584176618364482e-05,
"loss": 0.0408,
"step": 435
},
{
"epoch": 11.47,
"learning_rate": 1.5759857801558913e-05,
"loss": 0.0673,
"step": 436
},
{
"epoch": 11.5,
"learning_rate": 1.567802381674396e-05,
"loss": 0.1096,
"step": 437
},
{
"epoch": 11.53,
"learning_rate": 1.5596265665053972e-05,
"loss": 0.1686,
"step": 438
},
{
"epoch": 11.55,
"learning_rate": 1.5514584781012382e-05,
"loss": 0.1421,
"step": 439
},
{
"epoch": 11.58,
"learning_rate": 1.5432982597786886e-05,
"loss": 0.1843,
"step": 440
},
{
"epoch": 11.61,
"learning_rate": 1.535146054716432e-05,
"loss": 0.1022,
"step": 441
},
{
"epoch": 11.63,
"learning_rate": 1.527002005952551e-05,
"loss": 0.0865,
"step": 442
},
{
"epoch": 11.66,
"learning_rate": 1.5188662563820165e-05,
"loss": 0.091,
"step": 443
},
{
"epoch": 11.68,
"learning_rate": 1.5107389487541856e-05,
"loss": 0.122,
"step": 444
},
{
"epoch": 11.71,
"learning_rate": 1.5026202256702909e-05,
"loss": 0.0798,
"step": 445
},
{
"epoch": 11.74,
"learning_rate": 1.4945102295809415e-05,
"loss": 0.2063,
"step": 446
},
{
"epoch": 11.76,
"learning_rate": 1.4864091027836245e-05,
"loss": 0.0819,
"step": 447
},
{
"epoch": 11.79,
"learning_rate": 1.4783169874202067e-05,
"loss": 0.0524,
"step": 448
},
{
"epoch": 11.82,
"learning_rate": 1.4702340254744382e-05,
"loss": 0.1523,
"step": 449
},
{
"epoch": 11.84,
"learning_rate": 1.4621603587694688e-05,
"loss": 0.119,
"step": 450
},
{
"epoch": 11.87,
"learning_rate": 1.45409612896535e-05,
"loss": 0.1453,
"step": 451
},
{
"epoch": 11.89,
"learning_rate": 1.4460414775565555e-05,
"loss": 0.1735,
"step": 452
},
{
"epoch": 11.92,
"learning_rate": 1.4379965458694982e-05,
"loss": 0.1292,
"step": 453
},
{
"epoch": 11.95,
"learning_rate": 1.4299614750600478e-05,
"loss": 0.0797,
"step": 454
},
{
"epoch": 11.97,
"learning_rate": 1.4219364061110565e-05,
"loss": 0.0866,
"step": 455
},
{
"epoch": 12.0,
"learning_rate": 1.4139214798298854e-05,
"loss": 0.0711,
"step": 456
},
{
"epoch": 12.03,
"learning_rate": 1.4059168368459307e-05,
"loss": 0.0812,
"step": 457
},
{
"epoch": 12.05,
"learning_rate": 1.3979226176081593e-05,
"loss": 0.1358,
"step": 458
},
{
"epoch": 12.08,
"learning_rate": 1.3899389623826451e-05,
"loss": 0.0931,
"step": 459
},
{
"epoch": 12.11,
"learning_rate": 1.3819660112501054e-05,
"loss": 0.0724,
"step": 460
},
{
"epoch": 12.13,
"learning_rate": 1.3740039041034434e-05,
"loss": 0.0854,
"step": 461
},
{
"epoch": 12.16,
"learning_rate": 1.3660527806452965e-05,
"loss": 0.1068,
"step": 462
},
{
"epoch": 12.18,
"learning_rate": 1.3581127803855814e-05,
"loss": 0.0703,
"step": 463
},
{
"epoch": 12.21,
"learning_rate": 1.3501840426390476e-05,
"loss": 0.1606,
"step": 464
},
{
"epoch": 12.24,
"learning_rate": 1.3422667065228336e-05,
"loss": 0.1303,
"step": 465
},
{
"epoch": 12.26,
"learning_rate": 1.334360910954027e-05,
"loss": 0.0243,
"step": 466
},
{
"epoch": 12.29,
"learning_rate": 1.326466794647224e-05,
"loss": 0.0781,
"step": 467
},
{
"epoch": 12.32,
"learning_rate": 1.3185844961120969e-05,
"loss": 0.1115,
"step": 468
},
{
"epoch": 12.34,
"learning_rate": 1.3107141536509662e-05,
"loss": 0.1732,
"step": 469
},
{
"epoch": 12.37,
"learning_rate": 1.3028559053563701e-05,
"loss": 0.066,
"step": 470
},
{
"epoch": 12.39,
"learning_rate": 1.295009889108643e-05,
"loss": 0.0896,
"step": 471
},
{
"epoch": 12.42,
"learning_rate": 1.2871762425734989e-05,
"loss": 0.0801,
"step": 472
},
{
"epoch": 12.45,
"learning_rate": 1.279355103199611e-05,
"loss": 0.0992,
"step": 473
},
{
"epoch": 12.47,
"learning_rate": 1.2715466082162036e-05,
"loss": 0.0625,
"step": 474
},
{
"epoch": 12.5,
"learning_rate": 1.2637508946306443e-05,
"loss": 0.0779,
"step": 475
},
{
"epoch": 12.53,
"learning_rate": 1.255968099226038e-05,
"loss": 0.1522,
"step": 476
},
{
"epoch": 12.55,
"learning_rate": 1.2481983585588266e-05,
"loss": 0.0678,
"step": 477
},
{
"epoch": 12.58,
"learning_rate": 1.2404418089563982e-05,
"loss": 0.1706,
"step": 478
},
{
"epoch": 12.61,
"learning_rate": 1.2326985865146877e-05,
"loss": 0.1179,
"step": 479
},
{
"epoch": 12.63,
"learning_rate": 1.2249688270957942e-05,
"loss": 0.1971,
"step": 480
},
{
"epoch": 12.66,
"learning_rate": 1.2172526663255953e-05,
"loss": 0.1416,
"step": 481
},
{
"epoch": 12.68,
"learning_rate": 1.2095502395913676e-05,
"loss": 0.2722,
"step": 482
},
{
"epoch": 12.71,
"learning_rate": 1.2018616820394096e-05,
"loss": 0.0472,
"step": 483
},
{
"epoch": 12.74,
"learning_rate": 1.194187128572675e-05,
"loss": 0.0911,
"step": 484
},
{
"epoch": 12.76,
"learning_rate": 1.1865267138484e-05,
"loss": 0.0896,
"step": 485
},
{
"epoch": 12.79,
"learning_rate": 1.1788805722757442e-05,
"loss": 0.1136,
"step": 486
},
{
"epoch": 12.82,
"learning_rate": 1.171248838013432e-05,
"loss": 0.0675,
"step": 487
},
{
"epoch": 12.84,
"learning_rate": 1.1636316449673974e-05,
"loss": 0.1055,
"step": 488
},
{
"epoch": 12.87,
"learning_rate": 1.1560291267884346e-05,
"loss": 0.0841,
"step": 489
},
{
"epoch": 12.89,
"learning_rate": 1.1484414168698547e-05,
"loss": 0.1203,
"step": 490
},
{
"epoch": 12.92,
"learning_rate": 1.1408686483451439e-05,
"loss": 0.1151,
"step": 491
},
{
"epoch": 12.95,
"learning_rate": 1.1333109540856257e-05,
"loss": 0.208,
"step": 492
},
{
"epoch": 12.97,
"learning_rate": 1.1257684666981348e-05,
"loss": 0.0836,
"step": 493
},
{
"epoch": 13.0,
"learning_rate": 1.1182413185226833e-05,
"loss": 0.0852,
"step": 494
},
{
"epoch": 13.03,
"learning_rate": 1.1107296416301456e-05,
"loss": 0.0536,
"step": 495
},
{
"epoch": 13.05,
"learning_rate": 1.1032335678199359e-05,
"loss": 0.1039,
"step": 496
},
{
"epoch": 13.08,
"learning_rate": 1.0957532286176983e-05,
"loss": 0.0261,
"step": 497
},
{
"epoch": 13.11,
"learning_rate": 1.0882887552730006e-05,
"loss": 0.1051,
"step": 498
},
{
"epoch": 13.13,
"learning_rate": 1.0808402787570245e-05,
"loss": 0.073,
"step": 499
},
{
"epoch": 13.16,
"learning_rate": 1.0734079297602772e-05,
"loss": 0.0993,
"step": 500
},
{
"epoch": 13.18,
"learning_rate": 1.0659918386902897e-05,
"loss": 0.056,
"step": 501
},
{
"epoch": 13.21,
"learning_rate": 1.0585921356693349e-05,
"loss": 0.0802,
"step": 502
},
{
"epoch": 13.24,
"learning_rate": 1.0512089505321419e-05,
"loss": 0.1188,
"step": 503
},
{
"epoch": 13.26,
"learning_rate": 1.0438424128236157e-05,
"loss": 0.1029,
"step": 504
},
{
"epoch": 13.29,
"learning_rate": 1.0364926517965693e-05,
"loss": 0.1154,
"step": 505
},
{
"epoch": 13.32,
"learning_rate": 1.0291597964094522e-05,
"loss": 0.121,
"step": 506
},
{
"epoch": 13.34,
"learning_rate": 1.0218439753240883e-05,
"loss": 0.1288,
"step": 507
},
{
"epoch": 13.37,
"learning_rate": 1.0145453169034172e-05,
"loss": 0.0903,
"step": 508
},
{
"epoch": 13.39,
"learning_rate": 1.0072639492092463e-05,
"loss": 0.1255,
"step": 509
},
{
"epoch": 13.42,
"learning_rate": 1.0000000000000006e-05,
"loss": 0.1045,
"step": 510
},
{
"epoch": 13.45,
"learning_rate": 9.927535967284785e-06,
"loss": 0.1246,
"step": 511
},
{
"epoch": 13.47,
"learning_rate": 9.855248665396218e-06,
"loss": 0.1372,
"step": 512
},
{
"epoch": 13.5,
"learning_rate": 9.783139362682806e-06,
"loss": 0.1386,
"step": 513
},
{
"epoch": 13.53,
"learning_rate": 9.71120932436987e-06,
"loss": 0.1093,
"step": 514
},
{
"epoch": 13.55,
"learning_rate": 9.6394598125374e-06,
"loss": 0.069,
"step": 515
},
{
"epoch": 13.58,
"learning_rate": 9.567892086097845e-06,
"loss": 0.1175,
"step": 516
},
{
"epoch": 13.61,
"learning_rate": 9.496507400774085e-06,
"loss": 0.0853,
"step": 517
},
{
"epoch": 13.63,
"learning_rate": 9.425307009077368e-06,
"loss": 0.1196,
"step": 518
},
{
"epoch": 13.66,
"learning_rate": 9.354292160285328e-06,
"loss": 0.0623,
"step": 519
},
{
"epoch": 13.68,
"learning_rate": 9.283464100420064e-06,
"loss": 0.1087,
"step": 520
},
{
"epoch": 13.71,
"learning_rate": 9.212824072226332e-06,
"loss": 0.0789,
"step": 521
},
{
"epoch": 13.74,
"learning_rate": 9.142373315149655e-06,
"loss": 0.0835,
"step": 522
},
{
"epoch": 13.76,
"learning_rate": 9.07211306531462e-06,
"loss": 0.0487,
"step": 523
},
{
"epoch": 13.79,
"learning_rate": 9.002044555503202e-06,
"loss": 0.1229,
"step": 524
},
{
"epoch": 13.82,
"learning_rate": 8.93216901513312e-06,
"loss": 0.2623,
"step": 525
},
{
"epoch": 13.84,
"learning_rate": 8.862487670236249e-06,
"loss": 0.1368,
"step": 526
},
{
"epoch": 13.87,
"learning_rate": 8.793001743437111e-06,
"loss": 0.0802,
"step": 527
},
{
"epoch": 13.89,
"learning_rate": 8.723712453931465e-06,
"loss": 0.1322,
"step": 528
},
{
"epoch": 13.92,
"learning_rate": 8.654621017464875e-06,
"loss": 0.0543,
"step": 529
},
{
"epoch": 13.95,
"learning_rate": 8.585728646311368e-06,
"loss": 0.0793,
"step": 530
},
{
"epoch": 13.97,
"learning_rate": 8.517036549252206e-06,
"loss": 0.0843,
"step": 531
},
{
"epoch": 14.0,
"learning_rate": 8.448545931554652e-06,
"loss": 0.1853,
"step": 532
},
{
"epoch": 14.03,
"learning_rate": 8.380257994950805e-06,
"loss": 0.0544,
"step": 533
},
{
"epoch": 14.05,
"learning_rate": 8.31217393761656e-06,
"loss": 0.1099,
"step": 534
},
{
"epoch": 14.08,
"learning_rate": 8.24429495415054e-06,
"loss": 0.0563,
"step": 535
},
{
"epoch": 14.11,
"learning_rate": 8.17662223555316e-06,
"loss": 0.0584,
"step": 536
},
{
"epoch": 14.13,
"learning_rate": 8.109156969205739e-06,
"loss": 0.181,
"step": 537
},
{
"epoch": 14.16,
"learning_rate": 8.04190033884963e-06,
"loss": 0.1617,
"step": 538
},
{
"epoch": 14.18,
"learning_rate": 7.974853524565467e-06,
"loss": 0.0997,
"step": 539
},
{
"epoch": 14.21,
"learning_rate": 7.908017702752504e-06,
"loss": 0.1279,
"step": 540
},
{
"epoch": 14.24,
"learning_rate": 7.841394046107897e-06,
"loss": 0.0704,
"step": 541
},
{
"epoch": 14.26,
"learning_rate": 7.774983723606169e-06,
"loss": 0.1566,
"step": 542
},
{
"epoch": 14.29,
"learning_rate": 7.708787900478711e-06,
"loss": 0.054,
"step": 543
},
{
"epoch": 14.32,
"learning_rate": 7.642807738193316e-06,
"loss": 0.1328,
"step": 544
},
{
"epoch": 14.34,
"learning_rate": 7.577044394433795e-06,
"loss": 0.1146,
"step": 545
},
{
"epoch": 14.37,
"learning_rate": 7.511499023079689e-06,
"loss": 0.015,
"step": 546
},
{
"epoch": 14.39,
"learning_rate": 7.446172774185991e-06,
"loss": 0.1477,
"step": 547
},
{
"epoch": 14.42,
"learning_rate": 7.381066793963006e-06,
"loss": 0.1047,
"step": 548
},
{
"epoch": 14.45,
"learning_rate": 7.316182224756212e-06,
"loss": 0.0971,
"step": 549
},
{
"epoch": 14.47,
"learning_rate": 7.251520205026206e-06,
"loss": 0.2071,
"step": 550
},
{
"epoch": 14.5,
"learning_rate": 7.187081869328767e-06,
"loss": 0.0662,
"step": 551
},
{
"epoch": 14.53,
"learning_rate": 7.122868348294927e-06,
"loss": 0.0698,
"step": 552
},
{
"epoch": 14.55,
"learning_rate": 7.058880768611118e-06,
"loss": 0.083,
"step": 553
},
{
"epoch": 14.58,
"learning_rate": 6.995120252999419e-06,
"loss": 0.1451,
"step": 554
},
{
"epoch": 14.61,
"learning_rate": 6.931587920197891e-06,
"loss": 0.1383,
"step": 555
},
{
"epoch": 14.63,
"learning_rate": 6.868284884940875e-06,
"loss": 0.1219,
"step": 556
},
{
"epoch": 14.66,
"learning_rate": 6.805212257939479e-06,
"loss": 0.0751,
"step": 557
},
{
"epoch": 14.68,
"learning_rate": 6.742371145862095e-06,
"loss": 0.1379,
"step": 558
},
{
"epoch": 14.71,
"learning_rate": 6.679762651314969e-06,
"loss": 0.0863,
"step": 559
},
{
"epoch": 14.74,
"learning_rate": 6.617387872822842e-06,
"loss": 0.0955,
"step": 560
},
{
"epoch": 14.76,
"learning_rate": 6.555247904809683e-06,
"loss": 0.0517,
"step": 561
},
{
"epoch": 14.79,
"learning_rate": 6.493343837579511e-06,
"loss": 0.0688,
"step": 562
},
{
"epoch": 14.82,
"learning_rate": 6.431676757297241e-06,
"loss": 0.1223,
"step": 563
},
{
"epoch": 14.84,
"learning_rate": 6.3702477459696065e-06,
"loss": 0.0739,
"step": 564
},
{
"epoch": 14.87,
"learning_rate": 6.3090578814262256e-06,
"loss": 0.049,
"step": 565
},
{
"epoch": 14.89,
"learning_rate": 6.248108237300654e-06,
"loss": 0.0715,
"step": 566
},
{
"epoch": 14.92,
"learning_rate": 6.1873998830115425e-06,
"loss": 0.0415,
"step": 567
},
{
"epoch": 14.95,
"learning_rate": 6.126933883743904e-06,
"loss": 0.0945,
"step": 568
},
{
"epoch": 14.97,
"learning_rate": 6.066711300430386e-06,
"loss": 0.1233,
"step": 569
},
{
"epoch": 15.0,
"learning_rate": 6.00673318973269e-06,
"loss": 0.1101,
"step": 570
},
{
"epoch": 15.03,
"learning_rate": 5.947000604023019e-06,
"loss": 0.0602,
"step": 571
},
{
"epoch": 15.05,
"learning_rate": 5.887514591365593e-06,
"loss": 0.0807,
"step": 572
},
{
"epoch": 15.08,
"learning_rate": 5.828276195498275e-06,
"loss": 0.0495,
"step": 573
},
{
"epoch": 15.11,
"learning_rate": 5.769286455814294e-06,
"loss": 0.1486,
"step": 574
},
{
"epoch": 15.13,
"learning_rate": 5.710546407343938e-06,
"loss": 0.0822,
"step": 575
},
{
"epoch": 15.16,
"learning_rate": 5.6520570807364306e-06,
"loss": 0.1102,
"step": 576
},
{
"epoch": 15.18,
"learning_rate": 5.593819502241862e-06,
"loss": 0.069,
"step": 577
},
{
"epoch": 15.21,
"learning_rate": 5.535834693693163e-06,
"loss": 0.0928,
"step": 578
},
{
"epoch": 15.24,
"learning_rate": 5.478103672488162e-06,
"loss": 0.1181,
"step": 579
},
{
"epoch": 15.26,
"learning_rate": 5.4206274515717735e-06,
"loss": 0.1228,
"step": 580
},
{
"epoch": 15.29,
"learning_rate": 5.3634070394181785e-06,
"loss": 0.032,
"step": 581
},
{
"epoch": 15.32,
"learning_rate": 5.306443440013171e-06,
"loss": 0.1551,
"step": 582
},
{
"epoch": 15.34,
"learning_rate": 5.249737652836524e-06,
"loss": 0.0463,
"step": 583
},
{
"epoch": 15.37,
"learning_rate": 5.193290672844438e-06,
"loss": 0.0718,
"step": 584
},
{
"epoch": 15.39,
"learning_rate": 5.137103490452113e-06,
"loss": 0.0779,
"step": 585
},
{
"epoch": 15.42,
"learning_rate": 5.081177091516359e-06,
"loss": 0.1025,
"step": 586
},
{
"epoch": 15.45,
"learning_rate": 5.025512457318282e-06,
"loss": 0.0925,
"step": 587
},
{
"epoch": 15.47,
"learning_rate": 4.97011056454608e-06,
"loss": 0.0603,
"step": 588
},
{
"epoch": 15.5,
"learning_rate": 4.914972385277923e-06,
"loss": 0.0896,
"step": 589
},
{
"epoch": 15.53,
"learning_rate": 4.8600988869648745e-06,
"loss": 0.0878,
"step": 590
},
{
"epoch": 15.55,
"learning_rate": 4.805491032413912e-06,
"loss": 0.1842,
"step": 591
},
{
"epoch": 15.58,
"learning_rate": 4.75114977977104e-06,
"loss": 0.1667,
"step": 592
},
{
"epoch": 15.61,
"learning_rate": 4.697076082504517e-06,
"loss": 0.0798,
"step": 593
},
{
"epoch": 15.63,
"learning_rate": 4.643270889388056e-06,
"loss": 0.1233,
"step": 594
},
{
"epoch": 15.66,
"learning_rate": 4.589735144484217e-06,
"loss": 0.0603,
"step": 595
},
{
"epoch": 15.68,
"learning_rate": 4.536469787127855e-06,
"loss": 0.034,
"step": 596
},
{
"epoch": 15.71,
"learning_rate": 4.483475751909616e-06,
"loss": 0.0596,
"step": 597
},
{
"epoch": 15.74,
"learning_rate": 4.430753968659534e-06,
"loss": 0.0392,
"step": 598
},
{
"epoch": 15.76,
"learning_rate": 4.378305362430735e-06,
"loss": 0.1675,
"step": 599
},
{
"epoch": 15.79,
"learning_rate": 4.326130853483206e-06,
"loss": 0.225,
"step": 600
},
{
"epoch": 15.82,
"learning_rate": 4.2742313572676216e-06,
"loss": 0.0895,
"step": 601
},
{
"epoch": 15.84,
"learning_rate": 4.2226077844093205e-06,
"loss": 0.0729,
"step": 602
},
{
"epoch": 15.87,
"learning_rate": 4.171261040692287e-06,
"loss": 0.126,
"step": 603
},
{
"epoch": 15.89,
"learning_rate": 4.120192027043293e-06,
"loss": 0.0663,
"step": 604
},
{
"epoch": 15.92,
"learning_rate": 4.069401639516078e-06,
"loss": 0.1151,
"step": 605
},
{
"epoch": 15.95,
"learning_rate": 4.01889076927561e-06,
"loss": 0.141,
"step": 606
},
{
"epoch": 15.97,
"learning_rate": 3.968660302582466e-06,
"loss": 0.0802,
"step": 607
},
{
"epoch": 16.0,
"learning_rate": 3.918711120777308e-06,
"loss": 0.0763,
"step": 608
},
{
"epoch": 16.03,
"learning_rate": 3.8690441002653534e-06,
"loss": 0.0632,
"step": 609
},
{
"epoch": 16.05,
"learning_rate": 3.819660112501053e-06,
"loss": 0.0998,
"step": 610
},
{
"epoch": 16.08,
"learning_rate": 3.7705600239727825e-06,
"loss": 0.1182,
"step": 611
},
{
"epoch": 16.11,
"learning_rate": 3.7217446961876413e-06,
"loss": 0.0694,
"step": 612
},
{
"epoch": 16.13,
"learning_rate": 3.6732149856563217e-06,
"loss": 0.1351,
"step": 613
},
{
"epoch": 16.16,
"learning_rate": 3.624971743878112e-06,
"loss": 0.0701,
"step": 614
},
{
"epoch": 16.18,
"learning_rate": 3.5770158173259195e-06,
"loss": 0.0379,
"step": 615
},
{
"epoch": 16.21,
"learning_rate": 3.529348047431451e-06,
"loss": 0.0998,
"step": 616
},
{
"epoch": 16.24,
"learning_rate": 3.481969270570431e-06,
"loss": 0.1696,
"step": 617
},
{
"epoch": 16.26,
"learning_rate": 3.4348803180479174e-06,
"loss": 0.026,
"step": 618
},
{
"epoch": 16.29,
"learning_rate": 3.3880820160837447e-06,
"loss": 0.0809,
"step": 619
},
{
"epoch": 16.32,
"learning_rate": 3.3415751857980118e-06,
"loss": 0.0466,
"step": 620
},
{
"epoch": 16.34,
"learning_rate": 3.295360643196659e-06,
"loss": 0.1624,
"step": 621
},
{
"epoch": 16.37,
"learning_rate": 3.249439199157167e-06,
"loss": 0.0896,
"step": 622
},
{
"epoch": 16.39,
"learning_rate": 3.203811659414342e-06,
"loss": 0.1517,
"step": 623
},
{
"epoch": 16.42,
"learning_rate": 3.158478824546156e-06,
"loss": 0.0994,
"step": 624
},
{
"epoch": 16.45,
"learning_rate": 3.1134414899597033e-06,
"loss": 0.039,
"step": 625
},
{
"epoch": 16.47,
"learning_rate": 3.0687004458772417e-06,
"loss": 0.0873,
"step": 626
},
{
"epoch": 16.5,
"learning_rate": 3.0242564773223646e-06,
"loss": 0.066,
"step": 627
},
{
"epoch": 16.53,
"learning_rate": 2.980110364106168e-06,
"loss": 0.0433,
"step": 628
},
{
"epoch": 16.55,
"learning_rate": 2.936262880813596e-06,
"loss": 0.0749,
"step": 629
},
{
"epoch": 16.58,
"learning_rate": 2.892714796789868e-06,
"loss": 0.097,
"step": 630
},
{
"epoch": 16.61,
"learning_rate": 2.8494668761269585e-06,
"loss": 0.0544,
"step": 631
},
{
"epoch": 16.63,
"learning_rate": 2.80651987765018e-06,
"loss": 0.1061,
"step": 632
},
{
"epoch": 16.66,
"learning_rate": 2.763874554904902e-06,
"loss": 0.0918,
"step": 633
},
{
"epoch": 16.68,
"learning_rate": 2.721531656143295e-06,
"loss": 0.0321,
"step": 634
},
{
"epoch": 16.71,
"learning_rate": 2.679491924311226e-06,
"loss": 0.0685,
"step": 635
},
{
"epoch": 16.74,
"learning_rate": 2.6377560970352178e-06,
"loss": 0.0529,
"step": 636
},
{
"epoch": 16.76,
"learning_rate": 2.5963249066094863e-06,
"loss": 0.0937,
"step": 637
},
{
"epoch": 16.79,
"learning_rate": 2.555199079983124e-06,
"loss": 0.1792,
"step": 638
},
{
"epoch": 16.82,
"learning_rate": 2.514379338747328e-06,
"loss": 0.2075,
"step": 639
},
{
"epoch": 16.84,
"learning_rate": 2.473866399122733e-06,
"loss": 0.0688,
"step": 640
},
{
"epoch": 16.87,
"learning_rate": 2.4336609719468453e-06,
"loss": 0.156,
"step": 641
},
{
"epoch": 16.89,
"learning_rate": 2.393763762661596e-06,
"loss": 0.0705,
"step": 642
},
{
"epoch": 16.92,
"learning_rate": 2.3541754713009367e-06,
"loss": 0.1292,
"step": 643
},
{
"epoch": 16.95,
"learning_rate": 2.3148967924785536e-06,
"loss": 0.106,
"step": 644
},
{
"epoch": 16.97,
"learning_rate": 2.2759284153757056e-06,
"loss": 0.1244,
"step": 645
},
{
"epoch": 17.0,
"learning_rate": 2.2372710237291105e-06,
"loss": 0.1092,
"step": 646
},
{
"epoch": 17.03,
"learning_rate": 2.1989252958189498e-06,
"loss": 0.1082,
"step": 647
},
{
"epoch": 17.05,
"learning_rate": 2.1608919044569855e-06,
"loss": 0.0604,
"step": 648
},
{
"epoch": 17.08,
"learning_rate": 2.1231715169747247e-06,
"loss": 0.0299,
"step": 649
},
{
"epoch": 17.11,
"learning_rate": 2.085764795211742e-06,
"loss": 0.0707,
"step": 650
},
{
"epoch": 17.13,
"learning_rate": 2.04867239550405e-06,
"loss": 0.1801,
"step": 651
},
{
"epoch": 17.16,
"learning_rate": 2.0118949686725786e-06,
"loss": 0.0691,
"step": 652
},
{
"epoch": 17.18,
"learning_rate": 1.975433160011775e-06,
"loss": 0.0734,
"step": 653
},
{
"epoch": 17.21,
"learning_rate": 1.9392876092782576e-06,
"loss": 0.0439,
"step": 654
},
{
"epoch": 17.24,
"learning_rate": 1.903458950679613e-06,
"loss": 0.1925,
"step": 655
},
{
"epoch": 17.26,
"learning_rate": 1.8679478128632466e-06,
"loss": 0.0711,
"step": 656
},
{
"epoch": 17.29,
"learning_rate": 1.832754818905378e-06,
"loss": 0.1071,
"step": 657
},
{
"epoch": 17.32,
"learning_rate": 1.797880586300087e-06,
"loss": 0.1135,
"step": 658
},
{
"epoch": 17.34,
"learning_rate": 1.7633257269484883e-06,
"loss": 0.0911,
"step": 659
},
{
"epoch": 17.37,
"learning_rate": 1.7290908471479805e-06,
"loss": 0.0903,
"step": 660
},
{
"epoch": 17.39,
"learning_rate": 1.6951765475816495e-06,
"loss": 0.0518,
"step": 661
},
{
"epoch": 17.42,
"learning_rate": 1.6615834233076756e-06,
"loss": 0.0985,
"step": 662
},
{
"epoch": 17.45,
"learning_rate": 1.6283120637489202e-06,
"loss": 0.1171,
"step": 663
},
{
"epoch": 17.47,
"learning_rate": 1.5953630526825925e-06,
"loss": 0.0638,
"step": 664
},
{
"epoch": 17.5,
"learning_rate": 1.562736968229992e-06,
"loss": 0.1235,
"step": 665
},
{
"epoch": 17.53,
"learning_rate": 1.5304343828463553e-06,
"loss": 0.0286,
"step": 666
},
{
"epoch": 17.55,
"learning_rate": 1.4984558633108414e-06,
"loss": 0.0285,
"step": 667
},
{
"epoch": 17.58,
"learning_rate": 1.4668019707165581e-06,
"loss": 0.1211,
"step": 668
},
{
"epoch": 17.61,
"learning_rate": 1.4354732604607335e-06,
"loss": 0.0782,
"step": 669
},
{
"epoch": 17.63,
"learning_rate": 1.4044702822349731e-06,
"loss": 0.2467,
"step": 670
},
{
"epoch": 17.66,
"learning_rate": 1.3737935800155944e-06,
"loss": 0.0766,
"step": 671
},
{
"epoch": 17.68,
"learning_rate": 1.3434436920541072e-06,
"loss": 0.168,
"step": 672
},
{
"epoch": 17.71,
"learning_rate": 1.3134211508677597e-06,
"loss": 0.0623,
"step": 673
},
{
"epoch": 17.74,
"learning_rate": 1.2837264832301854e-06,
"loss": 0.0662,
"step": 674
},
{
"epoch": 17.76,
"learning_rate": 1.2543602101621711e-06,
"loss": 0.0444,
"step": 675
},
{
"epoch": 17.79,
"learning_rate": 1.2253228469225186e-06,
"loss": 0.1193,
"step": 676
},
{
"epoch": 17.82,
"learning_rate": 1.196614902998996e-06,
"loss": 0.088,
"step": 677
},
{
"epoch": 17.84,
"learning_rate": 1.1682368820993983e-06,
"loss": 0.1111,
"step": 678
},
{
"epoch": 17.87,
"learning_rate": 1.1401892821427096e-06,
"loss": 0.0715,
"step": 679
},
{
"epoch": 17.89,
"learning_rate": 1.1124725952503801e-06,
"loss": 0.0733,
"step": 680
},
{
"epoch": 17.92,
"learning_rate": 1.0850873077376645e-06,
"loss": 0.0469,
"step": 681
},
{
"epoch": 17.95,
"learning_rate": 1.0580339001051153e-06,
"loss": 0.1719,
"step": 682
},
{
"epoch": 17.97,
"learning_rate": 1.0313128470301371e-06,
"loss": 0.0748,
"step": 683
},
{
"epoch": 18.0,
"learning_rate": 1.0049246173586646e-06,
"loss": 0.0982,
"step": 684
},
{
"epoch": 18.03,
"learning_rate": 9.788696740969295e-07,
"loss": 0.1122,
"step": 685
},
{
"epoch": 18.05,
"learning_rate": 9.53148474403347e-07,
"loss": 0.0359,
"step": 686
},
{
"epoch": 18.08,
"learning_rate": 9.277614695804816e-07,
"loss": 0.0863,
"step": 687
},
{
"epoch": 18.11,
"learning_rate": 9.027091050671411e-07,
"loss": 0.0659,
"step": 688
},
{
"epoch": 18.13,
"learning_rate": 8.779918204305549e-07,
"loss": 0.0897,
"step": 689
},
{
"epoch": 18.16,
"learning_rate": 8.536100493586552e-07,
"loss": 0.0758,
"step": 690
},
{
"epoch": 18.18,
"learning_rate": 8.295642196524811e-07,
"loss": 0.0927,
"step": 691
},
{
"epoch": 18.21,
"learning_rate": 8.058547532186667e-07,
"loss": 0.1275,
"step": 692
},
{
"epoch": 18.24,
"learning_rate": 7.824820660620314e-07,
"loss": 0.139,
"step": 693
},
{
"epoch": 18.26,
"learning_rate": 7.594465682782815e-07,
"loss": 0.1121,
"step": 694
},
{
"epoch": 18.29,
"learning_rate": 7.36748664046838e-07,
"loss": 0.1089,
"step": 695
},
{
"epoch": 18.32,
"learning_rate": 7.143887516237092e-07,
"loss": 0.129,
"step": 696
},
{
"epoch": 18.34,
"learning_rate": 6.923672233345225e-07,
"loss": 0.0639,
"step": 697
},
{
"epoch": 18.37,
"learning_rate": 6.706844655676481e-07,
"loss": 0.1534,
"step": 698
},
{
"epoch": 18.39,
"learning_rate": 6.493408587674022e-07,
"loss": 0.0447,
"step": 699
},
{
"epoch": 18.42,
"learning_rate": 6.283367774273785e-07,
"loss": 0.0438,
"step": 700
},
{
"epoch": 18.45,
"learning_rate": 6.076725900838809e-07,
"loss": 0.0469,
"step": 701
},
{
"epoch": 18.47,
"learning_rate": 5.873486593094546e-07,
"loss": 0.0529,
"step": 702
},
{
"epoch": 18.5,
"learning_rate": 5.673653417065206e-07,
"loss": 0.0582,
"step": 703
},
{
"epoch": 18.53,
"learning_rate": 5.477229879011315e-07,
"loss": 0.1588,
"step": 704
},
{
"epoch": 18.55,
"learning_rate": 5.284219425367943e-07,
"loss": 0.0666,
"step": 705
},
{
"epoch": 18.58,
"learning_rate": 5.094625442684554e-07,
"loss": 0.0431,
"step": 706
},
{
"epoch": 18.61,
"learning_rate": 4.908451257565383e-07,
"loss": 0.1,
"step": 707
},
{
"epoch": 18.63,
"learning_rate": 4.7257001366110445e-07,
"loss": 0.1169,
"step": 708
},
{
"epoch": 18.66,
"learning_rate": 4.546375286361304e-07,
"loss": 0.1282,
"step": 709
},
{
"epoch": 18.68,
"learning_rate": 4.3704798532388624e-07,
"loss": 0.0536,
"step": 710
},
{
"epoch": 18.71,
"learning_rate": 4.1980169234940415e-07,
"loss": 0.0453,
"step": 711
},
{
"epoch": 18.74,
"learning_rate": 4.028989523150628e-07,
"loss": 0.0781,
"step": 712
},
{
"epoch": 18.76,
"learning_rate": 3.863400617952873e-07,
"loss": 0.0336,
"step": 713
},
{
"epoch": 18.79,
"learning_rate": 3.701253113313419e-07,
"loss": 0.1494,
"step": 714
},
{
"epoch": 18.82,
"learning_rate": 3.5425498542622784e-07,
"loss": 0.1187,
"step": 715
},
{
"epoch": 18.84,
"learning_rate": 3.3872936253969147e-07,
"loss": 0.0926,
"step": 716
},
{
"epoch": 18.87,
"learning_rate": 3.2354871508334826e-07,
"loss": 0.1389,
"step": 717
},
{
"epoch": 18.89,
"learning_rate": 3.087133094158934e-07,
"loss": 0.22,
"step": 718
},
{
"epoch": 18.92,
"learning_rate": 2.942234058384297e-07,
"loss": 0.1183,
"step": 719
},
{
"epoch": 18.95,
"learning_rate": 2.800792585899026e-07,
"loss": 0.0282,
"step": 720
},
{
"epoch": 18.97,
"learning_rate": 2.662811158426393e-07,
"loss": 0.053,
"step": 721
},
{
"epoch": 19.0,
"learning_rate": 2.52829219697992e-07,
"loss": 0.1222,
"step": 722
},
{
"epoch": 19.03,
"learning_rate": 2.3972380618209723e-07,
"loss": 0.1408,
"step": 723
},
{
"epoch": 19.05,
"learning_rate": 2.26965105241721e-07,
"loss": 0.0968,
"step": 724
},
{
"epoch": 19.08,
"learning_rate": 2.1455334074023336e-07,
"loss": 0.1141,
"step": 725
},
{
"epoch": 19.11,
"learning_rate": 2.0248873045368488e-07,
"loss": 0.0991,
"step": 726
},
{
"epoch": 19.13,
"learning_rate": 1.9077148606697627e-07,
"loss": 0.0805,
"step": 727
},
{
"epoch": 19.16,
"learning_rate": 1.7940181317014583e-07,
"loss": 0.1016,
"step": 728
},
{
"epoch": 19.18,
"learning_rate": 1.6837991125476572e-07,
"loss": 0.0752,
"step": 729
},
{
"epoch": 19.21,
"learning_rate": 1.577059737104447e-07,
"loss": 0.0746,
"step": 730
},
{
"epoch": 19.24,
"learning_rate": 1.4738018782141984e-07,
"loss": 0.0761,
"step": 731
},
{
"epoch": 19.26,
"learning_rate": 1.3740273476329224e-07,
"loss": 0.1207,
"step": 732
},
{
"epoch": 19.29,
"learning_rate": 1.2777378959983212e-07,
"loss": 0.075,
"step": 733
},
{
"epoch": 19.32,
"learning_rate": 1.1849352127990765e-07,
"loss": 0.101,
"step": 734
},
{
"epoch": 19.34,
"learning_rate": 1.0956209263453421e-07,
"loss": 0.1104,
"step": 735
},
{
"epoch": 19.37,
"learning_rate": 1.0097966037399654e-07,
"loss": 0.071,
"step": 736
},
{
"epoch": 19.39,
"learning_rate": 9.274637508512207e-08,
"loss": 0.1179,
"step": 737
},
{
"epoch": 19.42,
"learning_rate": 8.486238122861867e-08,
"loss": 0.0489,
"step": 738
},
{
"epoch": 19.45,
"learning_rate": 7.73278171365499e-08,
"loss": 0.0312,
"step": 739
},
{
"epoch": 19.47,
"learning_rate": 7.01428150099126e-08,
"loss": 0.1374,
"step": 740
},
{
"epoch": 19.5,
"learning_rate": 6.330750091630533e-08,
"loss": 0.2082,
"step": 741
},
{
"epoch": 19.53,
"learning_rate": 5.682199478772133e-08,
"loss": 0.1154,
"step": 742
},
{
"epoch": 19.55,
"learning_rate": 5.0686410418450124e-08,
"loss": 0.1482,
"step": 743
},
{
"epoch": 19.58,
"learning_rate": 4.4900855463068104e-08,
"loss": 0.1017,
"step": 744
},
{
"epoch": 19.61,
"learning_rate": 3.946543143456882e-08,
"loss": 0.1066,
"step": 745
},
{
"epoch": 19.63,
"learning_rate": 3.438023370256005e-08,
"loss": 0.0421,
"step": 746
},
{
"epoch": 19.66,
"learning_rate": 2.964535149160286e-08,
"loss": 0.0545,
"step": 747
},
{
"epoch": 19.68,
"learning_rate": 2.5260867879650652e-08,
"loss": 0.0766,
"step": 748
},
{
"epoch": 19.71,
"learning_rate": 2.1226859796574794e-08,
"loss": 0.0287,
"step": 749
},
{
"epoch": 19.74,
"learning_rate": 1.7543398022832337e-08,
"loss": 0.1082,
"step": 750
},
{
"epoch": 19.76,
"learning_rate": 1.4210547188215906e-08,
"loss": 0.0621,
"step": 751
},
{
"epoch": 19.79,
"learning_rate": 1.1228365770714622e-08,
"loss": 0.0609,
"step": 752
},
{
"epoch": 19.82,
"learning_rate": 8.596906095499347e-09,
"loss": 0.1291,
"step": 753
},
{
"epoch": 19.84,
"learning_rate": 6.316214334001203e-09,
"loss": 0.0485,
"step": 754
},
{
"epoch": 19.87,
"learning_rate": 4.386330503090008e-09,
"loss": 0.1391,
"step": 755
},
{
"epoch": 19.89,
"learning_rate": 2.807288464392599e-09,
"loss": 0.0522,
"step": 756
},
{
"epoch": 19.92,
"learning_rate": 1.5791159236777654e-09,
"loss": 0.0769,
"step": 757
},
{
"epoch": 19.95,
"learning_rate": 7.018344303877378e-10,
"loss": 0.1479,
"step": 758
},
{
"epoch": 19.97,
"learning_rate": 1.7545937724738894e-10,
"loss": 0.0599,
"step": 759
},
{
"epoch": 20.0,
"learning_rate": 0.0,
"loss": 0.0559,
"step": 760
},
{
"epoch": 20.0,
"step": 760,
"total_flos": 1.23586643755008e+17,
"train_loss": 0.1618304312400716,
"train_runtime": 6994.2721,
"train_samples_per_second": 0.869,
"train_steps_per_second": 0.109
}
],
"logging_steps": 1.0,
"max_steps": 760,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 100,
"total_flos": 1.23586643755008e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}