PlatyPhi-1.5B / trainer_state.json
pharaouk's picture
a
b445319
raw
history blame
245 kB
{
"best_metric": 1.4052919149398804,
"best_model_checkpoint": "./phi-sft-out/checkpoint-500",
"epoch": 2.971768202080238,
"eval_steps": 125,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 1.3979,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 3.0102999566398115e-06,
"loss": 1.1182,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 4.771212547196624e-06,
"loss": 1.1258,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 6.020599913279623e-06,
"loss": 1.0675,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 6.989700043360187e-06,
"loss": 1.1274,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 7.781512503836437e-06,
"loss": 1.1541,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 8.450980400142568e-06,
"loss": 1.1882,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 9.030899869919434e-06,
"loss": 1.3336,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 9.542425094393249e-06,
"loss": 0.8424,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 9.999999999999999e-06,
"loss": 0.9589,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 1.041392685158225e-05,
"loss": 1.0256,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 1.0791812460476248e-05,
"loss": 1.1169,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 1.1139433523068365e-05,
"loss": 1.0595,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 1.1461280356782378e-05,
"loss": 0.9097,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 1.1760912590556813e-05,
"loss": 1.149,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.2041199826559246e-05,
"loss": 1.0937,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 1.230448921378274e-05,
"loss": 1.0001,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 1.2552725051033058e-05,
"loss": 1.0672,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 1.2787536009528288e-05,
"loss": 0.9809,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 1.301029995663981e-05,
"loss": 0.8517,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 1.3222192947339192e-05,
"loss": 0.945,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 1.3424226808222062e-05,
"loss": 0.9433,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 1.3617278360175927e-05,
"loss": 0.9072,
"step": 23
},
{
"epoch": 0.04,
"learning_rate": 1.380211241711606e-05,
"loss": 1.0349,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 1.3979400086720374e-05,
"loss": 1.0584,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 1.4149733479708178e-05,
"loss": 0.9911,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 1.4313637641589872e-05,
"loss": 1.1692,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 1.4471580313422191e-05,
"loss": 1.0986,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 1.4623979978989559e-05,
"loss": 1.0138,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 1.4771212547196623e-05,
"loss": 0.9463,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 1.4913616938342726e-05,
"loss": 0.794,
"step": 31
},
{
"epoch": 0.05,
"learning_rate": 1.5051499783199059e-05,
"loss": 0.8846,
"step": 32
},
{
"epoch": 0.05,
"learning_rate": 1.5185139398778874e-05,
"loss": 0.9289,
"step": 33
},
{
"epoch": 0.05,
"learning_rate": 1.531478917042255e-05,
"loss": 0.7834,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 1.5440680443502753e-05,
"loss": 0.8562,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 1.5563025007672873e-05,
"loss": 1.055,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 1.5682017240669948e-05,
"loss": 1.1534,
"step": 37
},
{
"epoch": 0.06,
"learning_rate": 1.57978359661681e-05,
"loss": 0.9737,
"step": 38
},
{
"epoch": 0.06,
"learning_rate": 1.591064607026499e-05,
"loss": 0.987,
"step": 39
},
{
"epoch": 0.06,
"learning_rate": 1.6020599913279622e-05,
"loss": 0.925,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 1.6127838567197353e-05,
"loss": 1.0392,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 1.6232492903979005e-05,
"loss": 0.8435,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 1.6334684555795865e-05,
"loss": 1.0128,
"step": 43
},
{
"epoch": 0.07,
"learning_rate": 1.6434526764861872e-05,
"loss": 0.9464,
"step": 44
},
{
"epoch": 0.07,
"learning_rate": 1.6532125137753435e-05,
"loss": 0.8877,
"step": 45
},
{
"epoch": 0.07,
"learning_rate": 1.662757831681574e-05,
"loss": 1.1152,
"step": 46
},
{
"epoch": 0.07,
"learning_rate": 1.672097857935717e-05,
"loss": 1.0136,
"step": 47
},
{
"epoch": 0.07,
"learning_rate": 1.681241237375587e-05,
"loss": 0.9272,
"step": 48
},
{
"epoch": 0.07,
"learning_rate": 1.6901960800285137e-05,
"loss": 1.038,
"step": 49
},
{
"epoch": 0.07,
"learning_rate": 1.6989700043360187e-05,
"loss": 0.9117,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 1.7075701760979363e-05,
"loss": 0.7915,
"step": 51
},
{
"epoch": 0.08,
"learning_rate": 1.716003343634799e-05,
"loss": 0.7899,
"step": 52
},
{
"epoch": 0.08,
"learning_rate": 1.724275869600789e-05,
"loss": 0.8657,
"step": 53
},
{
"epoch": 0.08,
"learning_rate": 1.7323937598229687e-05,
"loss": 0.983,
"step": 54
},
{
"epoch": 0.08,
"learning_rate": 1.7403626894942437e-05,
"loss": 0.9886,
"step": 55
},
{
"epoch": 0.08,
"learning_rate": 1.7481880270062003e-05,
"loss": 0.81,
"step": 56
},
{
"epoch": 0.08,
"learning_rate": 1.7558748556724913e-05,
"loss": 0.8119,
"step": 57
},
{
"epoch": 0.09,
"learning_rate": 1.763427993562937e-05,
"loss": 0.9285,
"step": 58
},
{
"epoch": 0.09,
"learning_rate": 1.7708520116421443e-05,
"loss": 0.8236,
"step": 59
},
{
"epoch": 0.09,
"learning_rate": 1.7781512503836432e-05,
"loss": 0.8626,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 1.7853298350107667e-05,
"loss": 0.922,
"step": 61
},
{
"epoch": 0.09,
"learning_rate": 1.7923916894982537e-05,
"loss": 0.8988,
"step": 62
},
{
"epoch": 0.09,
"learning_rate": 1.7993405494535815e-05,
"loss": 1.1067,
"step": 63
},
{
"epoch": 0.1,
"learning_rate": 1.806179973983887e-05,
"loss": 1.0843,
"step": 64
},
{
"epoch": 0.1,
"learning_rate": 1.8129133566428553e-05,
"loss": 0.7697,
"step": 65
},
{
"epoch": 0.1,
"learning_rate": 1.8195439355418686e-05,
"loss": 0.8646,
"step": 66
},
{
"epoch": 0.1,
"learning_rate": 1.8260748027008263e-05,
"loss": 0.8284,
"step": 67
},
{
"epoch": 0.1,
"learning_rate": 1.8325089127062364e-05,
"loss": 0.703,
"step": 68
},
{
"epoch": 0.1,
"learning_rate": 1.8388490907372553e-05,
"loss": 0.9478,
"step": 69
},
{
"epoch": 0.1,
"learning_rate": 1.8450980400142568e-05,
"loss": 0.7572,
"step": 70
},
{
"epoch": 0.11,
"learning_rate": 1.8512583487190752e-05,
"loss": 0.9038,
"step": 71
},
{
"epoch": 0.11,
"learning_rate": 1.857332496431268e-05,
"loss": 0.7708,
"step": 72
},
{
"epoch": 0.11,
"learning_rate": 1.8633228601204555e-05,
"loss": 0.9743,
"step": 73
},
{
"epoch": 0.11,
"learning_rate": 1.8692317197309763e-05,
"loss": 0.8045,
"step": 74
},
{
"epoch": 0.11,
"learning_rate": 1.8750612633916997e-05,
"loss": 0.7002,
"step": 75
},
{
"epoch": 0.11,
"learning_rate": 1.8808135922807914e-05,
"loss": 0.9808,
"step": 76
},
{
"epoch": 0.11,
"learning_rate": 1.8864907251724818e-05,
"loss": 0.8373,
"step": 77
},
{
"epoch": 0.12,
"learning_rate": 1.8920946026904802e-05,
"loss": 0.7266,
"step": 78
},
{
"epoch": 0.12,
"learning_rate": 1.8976270912904414e-05,
"loss": 0.9247,
"step": 79
},
{
"epoch": 0.12,
"learning_rate": 1.9030899869919434e-05,
"loss": 1.0624,
"step": 80
},
{
"epoch": 0.12,
"learning_rate": 1.9084850188786497e-05,
"loss": 0.8695,
"step": 81
},
{
"epoch": 0.12,
"learning_rate": 1.9138138523837165e-05,
"loss": 0.7238,
"step": 82
},
{
"epoch": 0.12,
"learning_rate": 1.919078092376074e-05,
"loss": 1.0222,
"step": 83
},
{
"epoch": 0.12,
"learning_rate": 1.9242792860618813e-05,
"loss": 0.8256,
"step": 84
},
{
"epoch": 0.13,
"learning_rate": 1.929418925714293e-05,
"loss": 0.8127,
"step": 85
},
{
"epoch": 0.13,
"learning_rate": 1.9344984512435673e-05,
"loss": 1.1029,
"step": 86
},
{
"epoch": 0.13,
"learning_rate": 1.9395192526186183e-05,
"loss": 0.8873,
"step": 87
},
{
"epoch": 0.13,
"learning_rate": 1.9444826721501687e-05,
"loss": 0.7925,
"step": 88
},
{
"epoch": 0.13,
"learning_rate": 1.9493900066449125e-05,
"loss": 1.0414,
"step": 89
},
{
"epoch": 0.13,
"learning_rate": 1.9542425094393246e-05,
"loss": 1.0524,
"step": 90
},
{
"epoch": 0.14,
"learning_rate": 1.9590413923210934e-05,
"loss": 1.0657,
"step": 91
},
{
"epoch": 0.14,
"learning_rate": 1.9637878273455555e-05,
"loss": 0.8315,
"step": 92
},
{
"epoch": 0.14,
"learning_rate": 1.968482948553935e-05,
"loss": 0.9533,
"step": 93
},
{
"epoch": 0.14,
"learning_rate": 1.9731278535996986e-05,
"loss": 0.9165,
"step": 94
},
{
"epoch": 0.14,
"learning_rate": 1.9777236052888476e-05,
"loss": 0.8668,
"step": 95
},
{
"epoch": 0.14,
"learning_rate": 1.9822712330395683e-05,
"loss": 0.9267,
"step": 96
},
{
"epoch": 0.14,
"learning_rate": 1.986771734266245e-05,
"loss": 0.9919,
"step": 97
},
{
"epoch": 0.15,
"learning_rate": 1.991226075692495e-05,
"loss": 0.9339,
"step": 98
},
{
"epoch": 0.15,
"learning_rate": 1.9956351945975496e-05,
"loss": 0.644,
"step": 99
},
{
"epoch": 0.15,
"learning_rate": 1.9999999999999998e-05,
"loss": 0.9199,
"step": 100
},
{
"epoch": 0.15,
"learning_rate": 2e-05,
"loss": 1.0334,
"step": 101
},
{
"epoch": 0.15,
"learning_rate": 1.998957790515894e-05,
"loss": 0.7945,
"step": 102
},
{
"epoch": 0.15,
"learning_rate": 1.9979155810317878e-05,
"loss": 0.6566,
"step": 103
},
{
"epoch": 0.15,
"learning_rate": 1.9968733715476812e-05,
"loss": 0.7923,
"step": 104
},
{
"epoch": 0.16,
"learning_rate": 1.995831162063575e-05,
"loss": 0.8068,
"step": 105
},
{
"epoch": 0.16,
"learning_rate": 1.9947889525794685e-05,
"loss": 0.855,
"step": 106
},
{
"epoch": 0.16,
"learning_rate": 1.9937467430953623e-05,
"loss": 0.7377,
"step": 107
},
{
"epoch": 0.16,
"learning_rate": 1.992704533611256e-05,
"loss": 0.8029,
"step": 108
},
{
"epoch": 0.16,
"learning_rate": 1.99166232412715e-05,
"loss": 1.0084,
"step": 109
},
{
"epoch": 0.16,
"learning_rate": 1.9906201146430437e-05,
"loss": 0.9557,
"step": 110
},
{
"epoch": 0.16,
"learning_rate": 1.989577905158937e-05,
"loss": 0.7662,
"step": 111
},
{
"epoch": 0.17,
"learning_rate": 1.9885356956748306e-05,
"loss": 0.8791,
"step": 112
},
{
"epoch": 0.17,
"learning_rate": 1.9874934861907244e-05,
"loss": 0.9833,
"step": 113
},
{
"epoch": 0.17,
"learning_rate": 1.986451276706618e-05,
"loss": 0.9556,
"step": 114
},
{
"epoch": 0.17,
"learning_rate": 1.985409067222512e-05,
"loss": 0.741,
"step": 115
},
{
"epoch": 0.17,
"learning_rate": 1.9843668577384058e-05,
"loss": 0.776,
"step": 116
},
{
"epoch": 0.17,
"learning_rate": 1.9833246482542992e-05,
"loss": 0.855,
"step": 117
},
{
"epoch": 0.18,
"learning_rate": 1.982282438770193e-05,
"loss": 0.9365,
"step": 118
},
{
"epoch": 0.18,
"learning_rate": 1.9812402292860865e-05,
"loss": 0.753,
"step": 119
},
{
"epoch": 0.18,
"learning_rate": 1.9801980198019803e-05,
"loss": 0.97,
"step": 120
},
{
"epoch": 0.18,
"learning_rate": 1.979155810317874e-05,
"loss": 0.7882,
"step": 121
},
{
"epoch": 0.18,
"learning_rate": 1.978113600833768e-05,
"loss": 0.8523,
"step": 122
},
{
"epoch": 0.18,
"learning_rate": 1.9770713913496617e-05,
"loss": 0.6564,
"step": 123
},
{
"epoch": 0.18,
"learning_rate": 1.976029181865555e-05,
"loss": 0.7976,
"step": 124
},
{
"epoch": 0.19,
"learning_rate": 1.974986972381449e-05,
"loss": 0.8471,
"step": 125
},
{
"epoch": 0.19,
"eval_loss": 1.4292019605636597,
"eval_runtime": 0.6812,
"eval_samples_per_second": 358.21,
"eval_steps_per_second": 45.51,
"step": 125
},
{
"epoch": 0.19,
"learning_rate": 1.9739447628973424e-05,
"loss": 0.8122,
"step": 126
},
{
"epoch": 0.19,
"learning_rate": 1.972902553413236e-05,
"loss": 0.994,
"step": 127
},
{
"epoch": 0.19,
"learning_rate": 1.97186034392913e-05,
"loss": 0.7831,
"step": 128
},
{
"epoch": 0.19,
"learning_rate": 1.9708181344450238e-05,
"loss": 0.858,
"step": 129
},
{
"epoch": 0.19,
"learning_rate": 1.9697759249609175e-05,
"loss": 0.8478,
"step": 130
},
{
"epoch": 0.19,
"learning_rate": 1.968733715476811e-05,
"loss": 0.7913,
"step": 131
},
{
"epoch": 0.2,
"learning_rate": 1.9676915059927048e-05,
"loss": 0.8237,
"step": 132
},
{
"epoch": 0.2,
"learning_rate": 1.9666492965085983e-05,
"loss": 0.7538,
"step": 133
},
{
"epoch": 0.2,
"learning_rate": 1.965607087024492e-05,
"loss": 0.9826,
"step": 134
},
{
"epoch": 0.2,
"learning_rate": 1.964564877540386e-05,
"loss": 0.8151,
"step": 135
},
{
"epoch": 0.2,
"learning_rate": 1.9635226680562797e-05,
"loss": 0.7537,
"step": 136
},
{
"epoch": 0.2,
"learning_rate": 1.962480458572173e-05,
"loss": 0.8646,
"step": 137
},
{
"epoch": 0.21,
"learning_rate": 1.961438249088067e-05,
"loss": 0.6634,
"step": 138
},
{
"epoch": 0.21,
"learning_rate": 1.9603960396039604e-05,
"loss": 1.0213,
"step": 139
},
{
"epoch": 0.21,
"learning_rate": 1.959353830119854e-05,
"loss": 0.8,
"step": 140
},
{
"epoch": 0.21,
"learning_rate": 1.958311620635748e-05,
"loss": 0.9006,
"step": 141
},
{
"epoch": 0.21,
"learning_rate": 1.9572694111516418e-05,
"loss": 0.8561,
"step": 142
},
{
"epoch": 0.21,
"learning_rate": 1.9562272016675355e-05,
"loss": 0.8626,
"step": 143
},
{
"epoch": 0.21,
"learning_rate": 1.955184992183429e-05,
"loss": 0.832,
"step": 144
},
{
"epoch": 0.22,
"learning_rate": 1.9541427826993228e-05,
"loss": 0.7907,
"step": 145
},
{
"epoch": 0.22,
"learning_rate": 1.9531005732152163e-05,
"loss": 0.807,
"step": 146
},
{
"epoch": 0.22,
"learning_rate": 1.95205836373111e-05,
"loss": 0.8199,
"step": 147
},
{
"epoch": 0.22,
"learning_rate": 1.951016154247004e-05,
"loss": 0.7954,
"step": 148
},
{
"epoch": 0.22,
"learning_rate": 1.9499739447628976e-05,
"loss": 0.791,
"step": 149
},
{
"epoch": 0.22,
"learning_rate": 1.948931735278791e-05,
"loss": 0.8333,
"step": 150
},
{
"epoch": 0.22,
"learning_rate": 1.947889525794685e-05,
"loss": 0.8163,
"step": 151
},
{
"epoch": 0.23,
"learning_rate": 1.9468473163105787e-05,
"loss": 0.911,
"step": 152
},
{
"epoch": 0.23,
"learning_rate": 1.945805106826472e-05,
"loss": 0.7676,
"step": 153
},
{
"epoch": 0.23,
"learning_rate": 1.944762897342366e-05,
"loss": 0.6159,
"step": 154
},
{
"epoch": 0.23,
"learning_rate": 1.9437206878582597e-05,
"loss": 0.8217,
"step": 155
},
{
"epoch": 0.23,
"learning_rate": 1.9426784783741535e-05,
"loss": 0.8446,
"step": 156
},
{
"epoch": 0.23,
"learning_rate": 1.941636268890047e-05,
"loss": 0.6126,
"step": 157
},
{
"epoch": 0.23,
"learning_rate": 1.9405940594059408e-05,
"loss": 0.668,
"step": 158
},
{
"epoch": 0.24,
"learning_rate": 1.9395518499218346e-05,
"loss": 0.8318,
"step": 159
},
{
"epoch": 0.24,
"learning_rate": 1.938509640437728e-05,
"loss": 0.6842,
"step": 160
},
{
"epoch": 0.24,
"learning_rate": 1.937467430953622e-05,
"loss": 0.9758,
"step": 161
},
{
"epoch": 0.24,
"learning_rate": 1.9364252214695156e-05,
"loss": 0.8164,
"step": 162
},
{
"epoch": 0.24,
"learning_rate": 1.935383011985409e-05,
"loss": 0.8072,
"step": 163
},
{
"epoch": 0.24,
"learning_rate": 1.934340802501303e-05,
"loss": 0.6641,
"step": 164
},
{
"epoch": 0.25,
"learning_rate": 1.9332985930171967e-05,
"loss": 0.8985,
"step": 165
},
{
"epoch": 0.25,
"learning_rate": 1.93225638353309e-05,
"loss": 0.9107,
"step": 166
},
{
"epoch": 0.25,
"learning_rate": 1.931214174048984e-05,
"loss": 0.7579,
"step": 167
},
{
"epoch": 0.25,
"learning_rate": 1.9301719645648777e-05,
"loss": 0.7827,
"step": 168
},
{
"epoch": 0.25,
"learning_rate": 1.9291297550807715e-05,
"loss": 0.8708,
"step": 169
},
{
"epoch": 0.25,
"learning_rate": 1.928087545596665e-05,
"loss": 0.8594,
"step": 170
},
{
"epoch": 0.25,
"learning_rate": 1.9270453361125588e-05,
"loss": 0.7278,
"step": 171
},
{
"epoch": 0.26,
"learning_rate": 1.9260031266284526e-05,
"loss": 0.8197,
"step": 172
},
{
"epoch": 0.26,
"learning_rate": 1.924960917144346e-05,
"loss": 0.7777,
"step": 173
},
{
"epoch": 0.26,
"learning_rate": 1.92391870766024e-05,
"loss": 0.8311,
"step": 174
},
{
"epoch": 0.26,
"learning_rate": 1.9228764981761336e-05,
"loss": 0.8333,
"step": 175
},
{
"epoch": 0.26,
"learning_rate": 1.921834288692027e-05,
"loss": 0.8569,
"step": 176
},
{
"epoch": 0.26,
"learning_rate": 1.920792079207921e-05,
"loss": 0.8113,
"step": 177
},
{
"epoch": 0.26,
"learning_rate": 1.9197498697238147e-05,
"loss": 0.9254,
"step": 178
},
{
"epoch": 0.27,
"learning_rate": 1.9187076602397085e-05,
"loss": 0.8268,
"step": 179
},
{
"epoch": 0.27,
"learning_rate": 1.917665450755602e-05,
"loss": 0.7842,
"step": 180
},
{
"epoch": 0.27,
"learning_rate": 1.9166232412714957e-05,
"loss": 0.8853,
"step": 181
},
{
"epoch": 0.27,
"learning_rate": 1.9155810317873895e-05,
"loss": 0.9494,
"step": 182
},
{
"epoch": 0.27,
"learning_rate": 1.914538822303283e-05,
"loss": 0.6899,
"step": 183
},
{
"epoch": 0.27,
"learning_rate": 1.9134966128191768e-05,
"loss": 0.7485,
"step": 184
},
{
"epoch": 0.27,
"learning_rate": 1.9124544033350706e-05,
"loss": 0.7627,
"step": 185
},
{
"epoch": 0.28,
"learning_rate": 1.911412193850964e-05,
"loss": 0.9534,
"step": 186
},
{
"epoch": 0.28,
"learning_rate": 1.910369984366858e-05,
"loss": 0.8938,
"step": 187
},
{
"epoch": 0.28,
"learning_rate": 1.9093277748827516e-05,
"loss": 0.8936,
"step": 188
},
{
"epoch": 0.28,
"learning_rate": 1.908285565398645e-05,
"loss": 0.8637,
"step": 189
},
{
"epoch": 0.28,
"learning_rate": 1.907243355914539e-05,
"loss": 0.7841,
"step": 190
},
{
"epoch": 0.28,
"learning_rate": 1.9062011464304327e-05,
"loss": 0.7361,
"step": 191
},
{
"epoch": 0.29,
"learning_rate": 1.9051589369463265e-05,
"loss": 0.9502,
"step": 192
},
{
"epoch": 0.29,
"learning_rate": 1.90411672746222e-05,
"loss": 0.7668,
"step": 193
},
{
"epoch": 0.29,
"learning_rate": 1.9030745179781137e-05,
"loss": 0.9525,
"step": 194
},
{
"epoch": 0.29,
"learning_rate": 1.9020323084940075e-05,
"loss": 0.9285,
"step": 195
},
{
"epoch": 0.29,
"learning_rate": 1.900990099009901e-05,
"loss": 0.8229,
"step": 196
},
{
"epoch": 0.29,
"learning_rate": 1.8999478895257948e-05,
"loss": 0.8772,
"step": 197
},
{
"epoch": 0.29,
"learning_rate": 1.8989056800416886e-05,
"loss": 0.8353,
"step": 198
},
{
"epoch": 0.3,
"learning_rate": 1.8978634705575824e-05,
"loss": 0.9087,
"step": 199
},
{
"epoch": 0.3,
"learning_rate": 1.896821261073476e-05,
"loss": 0.6933,
"step": 200
},
{
"epoch": 0.3,
"learning_rate": 1.8957790515893696e-05,
"loss": 0.7325,
"step": 201
},
{
"epoch": 0.3,
"learning_rate": 1.894736842105263e-05,
"loss": 0.7855,
"step": 202
},
{
"epoch": 0.3,
"learning_rate": 1.893694632621157e-05,
"loss": 0.8066,
"step": 203
},
{
"epoch": 0.3,
"learning_rate": 1.8926524231370507e-05,
"loss": 0.6879,
"step": 204
},
{
"epoch": 0.3,
"learning_rate": 1.8916102136529445e-05,
"loss": 0.6346,
"step": 205
},
{
"epoch": 0.31,
"learning_rate": 1.8905680041688383e-05,
"loss": 0.8345,
"step": 206
},
{
"epoch": 0.31,
"learning_rate": 1.8895257946847317e-05,
"loss": 0.7777,
"step": 207
},
{
"epoch": 0.31,
"learning_rate": 1.8884835852006255e-05,
"loss": 0.8028,
"step": 208
},
{
"epoch": 0.31,
"learning_rate": 1.887441375716519e-05,
"loss": 0.7616,
"step": 209
},
{
"epoch": 0.31,
"learning_rate": 1.8863991662324128e-05,
"loss": 0.8293,
"step": 210
},
{
"epoch": 0.31,
"learning_rate": 1.8853569567483066e-05,
"loss": 1.0718,
"step": 211
},
{
"epoch": 0.32,
"learning_rate": 1.8843147472642004e-05,
"loss": 0.8187,
"step": 212
},
{
"epoch": 0.32,
"learning_rate": 1.883272537780094e-05,
"loss": 0.9085,
"step": 213
},
{
"epoch": 0.32,
"learning_rate": 1.8822303282959876e-05,
"loss": 0.8187,
"step": 214
},
{
"epoch": 0.32,
"learning_rate": 1.881188118811881e-05,
"loss": 0.8541,
"step": 215
},
{
"epoch": 0.32,
"learning_rate": 1.880145909327775e-05,
"loss": 0.8495,
"step": 216
},
{
"epoch": 0.32,
"learning_rate": 1.8791036998436687e-05,
"loss": 0.7282,
"step": 217
},
{
"epoch": 0.32,
"learning_rate": 1.8780614903595625e-05,
"loss": 0.9282,
"step": 218
},
{
"epoch": 0.33,
"learning_rate": 1.8770192808754563e-05,
"loss": 0.8301,
"step": 219
},
{
"epoch": 0.33,
"learning_rate": 1.8759770713913497e-05,
"loss": 0.9449,
"step": 220
},
{
"epoch": 0.33,
"learning_rate": 1.8749348619072435e-05,
"loss": 0.8108,
"step": 221
},
{
"epoch": 0.33,
"learning_rate": 1.873892652423137e-05,
"loss": 0.9288,
"step": 222
},
{
"epoch": 0.33,
"learning_rate": 1.8728504429390308e-05,
"loss": 0.8278,
"step": 223
},
{
"epoch": 0.33,
"learning_rate": 1.8718082334549246e-05,
"loss": 0.832,
"step": 224
},
{
"epoch": 0.33,
"learning_rate": 1.8707660239708184e-05,
"loss": 0.6932,
"step": 225
},
{
"epoch": 0.34,
"learning_rate": 1.8697238144867122e-05,
"loss": 0.8464,
"step": 226
},
{
"epoch": 0.34,
"learning_rate": 1.8686816050026056e-05,
"loss": 0.818,
"step": 227
},
{
"epoch": 0.34,
"learning_rate": 1.8676393955184994e-05,
"loss": 0.6812,
"step": 228
},
{
"epoch": 0.34,
"learning_rate": 1.866597186034393e-05,
"loss": 0.7635,
"step": 229
},
{
"epoch": 0.34,
"learning_rate": 1.8655549765502867e-05,
"loss": 0.8627,
"step": 230
},
{
"epoch": 0.34,
"learning_rate": 1.8645127670661805e-05,
"loss": 0.8027,
"step": 231
},
{
"epoch": 0.34,
"learning_rate": 1.8634705575820743e-05,
"loss": 0.8261,
"step": 232
},
{
"epoch": 0.35,
"learning_rate": 1.862428348097968e-05,
"loss": 1.063,
"step": 233
},
{
"epoch": 0.35,
"learning_rate": 1.8613861386138615e-05,
"loss": 0.7366,
"step": 234
},
{
"epoch": 0.35,
"learning_rate": 1.860343929129755e-05,
"loss": 0.8244,
"step": 235
},
{
"epoch": 0.35,
"learning_rate": 1.8593017196456488e-05,
"loss": 0.7581,
"step": 236
},
{
"epoch": 0.35,
"learning_rate": 1.8582595101615426e-05,
"loss": 0.8713,
"step": 237
},
{
"epoch": 0.35,
"learning_rate": 1.8572173006774364e-05,
"loss": 0.8269,
"step": 238
},
{
"epoch": 0.36,
"learning_rate": 1.8561750911933302e-05,
"loss": 0.8373,
"step": 239
},
{
"epoch": 0.36,
"learning_rate": 1.8551328817092236e-05,
"loss": 1.0406,
"step": 240
},
{
"epoch": 0.36,
"learning_rate": 1.8540906722251174e-05,
"loss": 0.817,
"step": 241
},
{
"epoch": 0.36,
"learning_rate": 1.853048462741011e-05,
"loss": 0.7741,
"step": 242
},
{
"epoch": 0.36,
"learning_rate": 1.8520062532569047e-05,
"loss": 0.6475,
"step": 243
},
{
"epoch": 0.36,
"learning_rate": 1.8509640437727985e-05,
"loss": 0.9373,
"step": 244
},
{
"epoch": 0.36,
"learning_rate": 1.8499218342886923e-05,
"loss": 0.7653,
"step": 245
},
{
"epoch": 0.37,
"learning_rate": 1.848879624804586e-05,
"loss": 0.7827,
"step": 246
},
{
"epoch": 0.37,
"learning_rate": 1.8478374153204795e-05,
"loss": 0.721,
"step": 247
},
{
"epoch": 0.37,
"learning_rate": 1.8467952058363733e-05,
"loss": 0.9385,
"step": 248
},
{
"epoch": 0.37,
"learning_rate": 1.8457529963522668e-05,
"loss": 0.8429,
"step": 249
},
{
"epoch": 0.37,
"learning_rate": 1.8447107868681606e-05,
"loss": 0.7696,
"step": 250
},
{
"epoch": 0.37,
"eval_loss": 1.419487714767456,
"eval_runtime": 0.6822,
"eval_samples_per_second": 357.684,
"eval_steps_per_second": 45.443,
"step": 250
},
{
"epoch": 0.37,
"learning_rate": 1.8436685773840544e-05,
"loss": 0.8948,
"step": 251
},
{
"epoch": 0.37,
"learning_rate": 1.8426263678999482e-05,
"loss": 0.8965,
"step": 252
},
{
"epoch": 0.38,
"learning_rate": 1.841584158415842e-05,
"loss": 0.865,
"step": 253
},
{
"epoch": 0.38,
"learning_rate": 1.8405419489317354e-05,
"loss": 0.7987,
"step": 254
},
{
"epoch": 0.38,
"learning_rate": 1.839499739447629e-05,
"loss": 0.6493,
"step": 255
},
{
"epoch": 0.38,
"learning_rate": 1.8384575299635227e-05,
"loss": 0.6366,
"step": 256
},
{
"epoch": 0.38,
"learning_rate": 1.8374153204794165e-05,
"loss": 0.7761,
"step": 257
},
{
"epoch": 0.38,
"learning_rate": 1.8363731109953103e-05,
"loss": 0.8842,
"step": 258
},
{
"epoch": 0.38,
"learning_rate": 1.835330901511204e-05,
"loss": 0.8538,
"step": 259
},
{
"epoch": 0.39,
"learning_rate": 1.8342886920270975e-05,
"loss": 0.7485,
"step": 260
},
{
"epoch": 0.39,
"learning_rate": 1.8332464825429913e-05,
"loss": 0.9639,
"step": 261
},
{
"epoch": 0.39,
"learning_rate": 1.8322042730588848e-05,
"loss": 0.8671,
"step": 262
},
{
"epoch": 0.39,
"learning_rate": 1.8311620635747786e-05,
"loss": 1.1155,
"step": 263
},
{
"epoch": 0.39,
"learning_rate": 1.8301198540906724e-05,
"loss": 0.6222,
"step": 264
},
{
"epoch": 0.39,
"learning_rate": 1.8290776446065662e-05,
"loss": 0.8193,
"step": 265
},
{
"epoch": 0.4,
"learning_rate": 1.82803543512246e-05,
"loss": 0.7023,
"step": 266
},
{
"epoch": 0.4,
"learning_rate": 1.8269932256383534e-05,
"loss": 0.7934,
"step": 267
},
{
"epoch": 0.4,
"learning_rate": 1.8259510161542472e-05,
"loss": 0.7694,
"step": 268
},
{
"epoch": 0.4,
"learning_rate": 1.8249088066701407e-05,
"loss": 0.5762,
"step": 269
},
{
"epoch": 0.4,
"learning_rate": 1.8238665971860345e-05,
"loss": 1.0749,
"step": 270
},
{
"epoch": 0.4,
"learning_rate": 1.8228243877019283e-05,
"loss": 0.7574,
"step": 271
},
{
"epoch": 0.4,
"learning_rate": 1.821782178217822e-05,
"loss": 0.8867,
"step": 272
},
{
"epoch": 0.41,
"learning_rate": 1.820739968733716e-05,
"loss": 0.8494,
"step": 273
},
{
"epoch": 0.41,
"learning_rate": 1.8196977592496093e-05,
"loss": 0.9332,
"step": 274
},
{
"epoch": 0.41,
"learning_rate": 1.818655549765503e-05,
"loss": 0.8358,
"step": 275
},
{
"epoch": 0.41,
"learning_rate": 1.8176133402813966e-05,
"loss": 0.8541,
"step": 276
},
{
"epoch": 0.41,
"learning_rate": 1.8165711307972904e-05,
"loss": 0.6343,
"step": 277
},
{
"epoch": 0.41,
"learning_rate": 1.8155289213131842e-05,
"loss": 0.8539,
"step": 278
},
{
"epoch": 0.41,
"learning_rate": 1.814486711829078e-05,
"loss": 0.8616,
"step": 279
},
{
"epoch": 0.42,
"learning_rate": 1.8134445023449714e-05,
"loss": 0.7041,
"step": 280
},
{
"epoch": 0.42,
"learning_rate": 1.8124022928608652e-05,
"loss": 0.8686,
"step": 281
},
{
"epoch": 0.42,
"learning_rate": 1.8113600833767587e-05,
"loss": 0.8846,
"step": 282
},
{
"epoch": 0.42,
"learning_rate": 1.8103178738926525e-05,
"loss": 0.6211,
"step": 283
},
{
"epoch": 0.42,
"learning_rate": 1.8092756644085463e-05,
"loss": 0.6801,
"step": 284
},
{
"epoch": 0.42,
"learning_rate": 1.80823345492444e-05,
"loss": 0.8719,
"step": 285
},
{
"epoch": 0.42,
"learning_rate": 1.807191245440334e-05,
"loss": 0.8244,
"step": 286
},
{
"epoch": 0.43,
"learning_rate": 1.8061490359562273e-05,
"loss": 0.9202,
"step": 287
},
{
"epoch": 0.43,
"learning_rate": 1.805106826472121e-05,
"loss": 0.7357,
"step": 288
},
{
"epoch": 0.43,
"learning_rate": 1.8040646169880146e-05,
"loss": 0.6915,
"step": 289
},
{
"epoch": 0.43,
"learning_rate": 1.8030224075039084e-05,
"loss": 0.6815,
"step": 290
},
{
"epoch": 0.43,
"learning_rate": 1.8019801980198022e-05,
"loss": 0.7258,
"step": 291
},
{
"epoch": 0.43,
"learning_rate": 1.800937988535696e-05,
"loss": 0.7624,
"step": 292
},
{
"epoch": 0.44,
"learning_rate": 1.7998957790515894e-05,
"loss": 0.8998,
"step": 293
},
{
"epoch": 0.44,
"learning_rate": 1.7988535695674832e-05,
"loss": 0.8004,
"step": 294
},
{
"epoch": 0.44,
"learning_rate": 1.797811360083377e-05,
"loss": 0.7638,
"step": 295
},
{
"epoch": 0.44,
"learning_rate": 1.7967691505992705e-05,
"loss": 0.9554,
"step": 296
},
{
"epoch": 0.44,
"learning_rate": 1.7957269411151643e-05,
"loss": 0.8383,
"step": 297
},
{
"epoch": 0.44,
"learning_rate": 1.794684731631058e-05,
"loss": 0.8609,
"step": 298
},
{
"epoch": 0.44,
"learning_rate": 1.793642522146952e-05,
"loss": 0.7594,
"step": 299
},
{
"epoch": 0.45,
"learning_rate": 1.7926003126628453e-05,
"loss": 0.6096,
"step": 300
},
{
"epoch": 0.45,
"learning_rate": 1.791558103178739e-05,
"loss": 0.7143,
"step": 301
},
{
"epoch": 0.45,
"learning_rate": 1.7905158936946326e-05,
"loss": 0.7679,
"step": 302
},
{
"epoch": 0.45,
"learning_rate": 1.7894736842105264e-05,
"loss": 0.8171,
"step": 303
},
{
"epoch": 0.45,
"learning_rate": 1.7884314747264202e-05,
"loss": 0.9959,
"step": 304
},
{
"epoch": 0.45,
"learning_rate": 1.787389265242314e-05,
"loss": 0.7385,
"step": 305
},
{
"epoch": 0.45,
"learning_rate": 1.7863470557582074e-05,
"loss": 0.9204,
"step": 306
},
{
"epoch": 0.46,
"learning_rate": 1.7853048462741012e-05,
"loss": 0.7915,
"step": 307
},
{
"epoch": 0.46,
"learning_rate": 1.784262636789995e-05,
"loss": 0.7563,
"step": 308
},
{
"epoch": 0.46,
"learning_rate": 1.7832204273058885e-05,
"loss": 0.9926,
"step": 309
},
{
"epoch": 0.46,
"learning_rate": 1.7821782178217823e-05,
"loss": 0.9249,
"step": 310
},
{
"epoch": 0.46,
"learning_rate": 1.781136008337676e-05,
"loss": 0.8747,
"step": 311
},
{
"epoch": 0.46,
"learning_rate": 1.78009379885357e-05,
"loss": 0.7658,
"step": 312
},
{
"epoch": 0.47,
"learning_rate": 1.7790515893694633e-05,
"loss": 0.8105,
"step": 313
},
{
"epoch": 0.47,
"learning_rate": 1.778009379885357e-05,
"loss": 0.7345,
"step": 314
},
{
"epoch": 0.47,
"learning_rate": 1.776967170401251e-05,
"loss": 0.6339,
"step": 315
},
{
"epoch": 0.47,
"learning_rate": 1.7759249609171444e-05,
"loss": 0.6961,
"step": 316
},
{
"epoch": 0.47,
"learning_rate": 1.774882751433038e-05,
"loss": 0.7232,
"step": 317
},
{
"epoch": 0.47,
"learning_rate": 1.773840541948932e-05,
"loss": 0.7195,
"step": 318
},
{
"epoch": 0.47,
"learning_rate": 1.7727983324648254e-05,
"loss": 0.813,
"step": 319
},
{
"epoch": 0.48,
"learning_rate": 1.7717561229807192e-05,
"loss": 0.7314,
"step": 320
},
{
"epoch": 0.48,
"learning_rate": 1.770713913496613e-05,
"loss": 0.8782,
"step": 321
},
{
"epoch": 0.48,
"learning_rate": 1.7696717040125068e-05,
"loss": 0.8681,
"step": 322
},
{
"epoch": 0.48,
"learning_rate": 1.7686294945284003e-05,
"loss": 0.765,
"step": 323
},
{
"epoch": 0.48,
"learning_rate": 1.767587285044294e-05,
"loss": 0.7984,
"step": 324
},
{
"epoch": 0.48,
"learning_rate": 1.766545075560188e-05,
"loss": 0.9159,
"step": 325
},
{
"epoch": 0.48,
"learning_rate": 1.7655028660760813e-05,
"loss": 0.7696,
"step": 326
},
{
"epoch": 0.49,
"learning_rate": 1.764460656591975e-05,
"loss": 0.7275,
"step": 327
},
{
"epoch": 0.49,
"learning_rate": 1.763418447107869e-05,
"loss": 0.7822,
"step": 328
},
{
"epoch": 0.49,
"learning_rate": 1.7623762376237624e-05,
"loss": 0.8369,
"step": 329
},
{
"epoch": 0.49,
"learning_rate": 1.761334028139656e-05,
"loss": 0.8974,
"step": 330
},
{
"epoch": 0.49,
"learning_rate": 1.76029181865555e-05,
"loss": 0.8036,
"step": 331
},
{
"epoch": 0.49,
"learning_rate": 1.7592496091714434e-05,
"loss": 0.9051,
"step": 332
},
{
"epoch": 0.49,
"learning_rate": 1.7582073996873372e-05,
"loss": 0.8013,
"step": 333
},
{
"epoch": 0.5,
"learning_rate": 1.757165190203231e-05,
"loss": 0.7581,
"step": 334
},
{
"epoch": 0.5,
"learning_rate": 1.7561229807191248e-05,
"loss": 0.7887,
"step": 335
},
{
"epoch": 0.5,
"learning_rate": 1.7550807712350183e-05,
"loss": 0.6694,
"step": 336
},
{
"epoch": 0.5,
"learning_rate": 1.754038561750912e-05,
"loss": 0.7176,
"step": 337
},
{
"epoch": 0.5,
"learning_rate": 1.752996352266806e-05,
"loss": 0.7746,
"step": 338
},
{
"epoch": 0.5,
"learning_rate": 1.7519541427826993e-05,
"loss": 0.8381,
"step": 339
},
{
"epoch": 0.51,
"learning_rate": 1.750911933298593e-05,
"loss": 0.8125,
"step": 340
},
{
"epoch": 0.51,
"learning_rate": 1.749869723814487e-05,
"loss": 0.8943,
"step": 341
},
{
"epoch": 0.51,
"learning_rate": 1.7488275143303807e-05,
"loss": 0.7914,
"step": 342
},
{
"epoch": 0.51,
"learning_rate": 1.747785304846274e-05,
"loss": 0.6652,
"step": 343
},
{
"epoch": 0.51,
"learning_rate": 1.746743095362168e-05,
"loss": 0.7164,
"step": 344
},
{
"epoch": 0.51,
"learning_rate": 1.7457008858780614e-05,
"loss": 0.7685,
"step": 345
},
{
"epoch": 0.51,
"learning_rate": 1.7446586763939552e-05,
"loss": 0.9363,
"step": 346
},
{
"epoch": 0.52,
"learning_rate": 1.743616466909849e-05,
"loss": 1.0479,
"step": 347
},
{
"epoch": 0.52,
"learning_rate": 1.7425742574257428e-05,
"loss": 0.8103,
"step": 348
},
{
"epoch": 0.52,
"learning_rate": 1.7415320479416366e-05,
"loss": 0.9324,
"step": 349
},
{
"epoch": 0.52,
"learning_rate": 1.74048983845753e-05,
"loss": 0.8677,
"step": 350
},
{
"epoch": 0.52,
"learning_rate": 1.739447628973424e-05,
"loss": 0.7647,
"step": 351
},
{
"epoch": 0.52,
"learning_rate": 1.7384054194893173e-05,
"loss": 0.7685,
"step": 352
},
{
"epoch": 0.52,
"learning_rate": 1.737363210005211e-05,
"loss": 0.9621,
"step": 353
},
{
"epoch": 0.53,
"learning_rate": 1.736321000521105e-05,
"loss": 0.9382,
"step": 354
},
{
"epoch": 0.53,
"learning_rate": 1.7352787910369987e-05,
"loss": 0.8555,
"step": 355
},
{
"epoch": 0.53,
"learning_rate": 1.734236581552892e-05,
"loss": 0.6613,
"step": 356
},
{
"epoch": 0.53,
"learning_rate": 1.733194372068786e-05,
"loss": 0.7441,
"step": 357
},
{
"epoch": 0.53,
"learning_rate": 1.7321521625846794e-05,
"loss": 0.8258,
"step": 358
},
{
"epoch": 0.53,
"learning_rate": 1.7311099531005732e-05,
"loss": 0.7499,
"step": 359
},
{
"epoch": 0.53,
"learning_rate": 1.730067743616467e-05,
"loss": 0.7054,
"step": 360
},
{
"epoch": 0.54,
"learning_rate": 1.7290255341323608e-05,
"loss": 0.7664,
"step": 361
},
{
"epoch": 0.54,
"learning_rate": 1.7279833246482546e-05,
"loss": 0.6954,
"step": 362
},
{
"epoch": 0.54,
"learning_rate": 1.726941115164148e-05,
"loss": 0.7161,
"step": 363
},
{
"epoch": 0.54,
"learning_rate": 1.725898905680042e-05,
"loss": 0.6779,
"step": 364
},
{
"epoch": 0.54,
"learning_rate": 1.7248566961959353e-05,
"loss": 0.7639,
"step": 365
},
{
"epoch": 0.54,
"learning_rate": 1.723814486711829e-05,
"loss": 0.8716,
"step": 366
},
{
"epoch": 0.55,
"learning_rate": 1.722772277227723e-05,
"loss": 0.9918,
"step": 367
},
{
"epoch": 0.55,
"learning_rate": 1.7217300677436167e-05,
"loss": 0.6391,
"step": 368
},
{
"epoch": 0.55,
"learning_rate": 1.7206878582595105e-05,
"loss": 0.7262,
"step": 369
},
{
"epoch": 0.55,
"learning_rate": 1.719645648775404e-05,
"loss": 0.7502,
"step": 370
},
{
"epoch": 0.55,
"learning_rate": 1.7186034392912974e-05,
"loss": 0.8408,
"step": 371
},
{
"epoch": 0.55,
"learning_rate": 1.7175612298071912e-05,
"loss": 0.8284,
"step": 372
},
{
"epoch": 0.55,
"learning_rate": 1.716519020323085e-05,
"loss": 0.7398,
"step": 373
},
{
"epoch": 0.56,
"learning_rate": 1.7154768108389788e-05,
"loss": 0.7542,
"step": 374
},
{
"epoch": 0.56,
"learning_rate": 1.7144346013548726e-05,
"loss": 0.8336,
"step": 375
},
{
"epoch": 0.56,
"eval_loss": 1.4095131158828735,
"eval_runtime": 0.6814,
"eval_samples_per_second": 358.108,
"eval_steps_per_second": 45.497,
"step": 375
},
{
"epoch": 0.56,
"learning_rate": 1.713392391870766e-05,
"loss": 0.8013,
"step": 376
},
{
"epoch": 0.56,
"learning_rate": 1.71235018238666e-05,
"loss": 0.729,
"step": 377
},
{
"epoch": 0.56,
"learning_rate": 1.7113079729025533e-05,
"loss": 0.5801,
"step": 378
},
{
"epoch": 0.56,
"learning_rate": 1.710265763418447e-05,
"loss": 0.8209,
"step": 379
},
{
"epoch": 0.56,
"learning_rate": 1.709223553934341e-05,
"loss": 0.9324,
"step": 380
},
{
"epoch": 0.57,
"learning_rate": 1.7081813444502347e-05,
"loss": 0.7516,
"step": 381
},
{
"epoch": 0.57,
"learning_rate": 1.7071391349661285e-05,
"loss": 0.8038,
"step": 382
},
{
"epoch": 0.57,
"learning_rate": 1.706096925482022e-05,
"loss": 0.8966,
"step": 383
},
{
"epoch": 0.57,
"learning_rate": 1.7050547159979158e-05,
"loss": 0.8014,
"step": 384
},
{
"epoch": 0.57,
"learning_rate": 1.7040125065138092e-05,
"loss": 0.8488,
"step": 385
},
{
"epoch": 0.57,
"learning_rate": 1.702970297029703e-05,
"loss": 0.534,
"step": 386
},
{
"epoch": 0.58,
"learning_rate": 1.7019280875455968e-05,
"loss": 0.8201,
"step": 387
},
{
"epoch": 0.58,
"learning_rate": 1.7008858780614906e-05,
"loss": 0.8467,
"step": 388
},
{
"epoch": 0.58,
"learning_rate": 1.6998436685773844e-05,
"loss": 0.5978,
"step": 389
},
{
"epoch": 0.58,
"learning_rate": 1.698801459093278e-05,
"loss": 0.6904,
"step": 390
},
{
"epoch": 0.58,
"learning_rate": 1.6977592496091716e-05,
"loss": 0.812,
"step": 391
},
{
"epoch": 0.58,
"learning_rate": 1.696717040125065e-05,
"loss": 0.7595,
"step": 392
},
{
"epoch": 0.58,
"learning_rate": 1.695674830640959e-05,
"loss": 0.7716,
"step": 393
},
{
"epoch": 0.59,
"learning_rate": 1.6946326211568527e-05,
"loss": 0.7191,
"step": 394
},
{
"epoch": 0.59,
"learning_rate": 1.6935904116727465e-05,
"loss": 0.8188,
"step": 395
},
{
"epoch": 0.59,
"learning_rate": 1.6925482021886403e-05,
"loss": 0.6315,
"step": 396
},
{
"epoch": 0.59,
"learning_rate": 1.6915059927045337e-05,
"loss": 0.8337,
"step": 397
},
{
"epoch": 0.59,
"learning_rate": 1.6904637832204272e-05,
"loss": 0.7527,
"step": 398
},
{
"epoch": 0.59,
"learning_rate": 1.689421573736321e-05,
"loss": 0.6687,
"step": 399
},
{
"epoch": 0.59,
"learning_rate": 1.6883793642522148e-05,
"loss": 0.8028,
"step": 400
},
{
"epoch": 0.6,
"learning_rate": 1.6873371547681086e-05,
"loss": 0.8755,
"step": 401
},
{
"epoch": 0.6,
"learning_rate": 1.6862949452840024e-05,
"loss": 0.8406,
"step": 402
},
{
"epoch": 0.6,
"learning_rate": 1.685252735799896e-05,
"loss": 0.6639,
"step": 403
},
{
"epoch": 0.6,
"learning_rate": 1.6842105263157896e-05,
"loss": 0.6692,
"step": 404
},
{
"epoch": 0.6,
"learning_rate": 1.683168316831683e-05,
"loss": 0.8156,
"step": 405
},
{
"epoch": 0.6,
"learning_rate": 1.682126107347577e-05,
"loss": 0.6696,
"step": 406
},
{
"epoch": 0.6,
"learning_rate": 1.6810838978634707e-05,
"loss": 0.72,
"step": 407
},
{
"epoch": 0.61,
"learning_rate": 1.6800416883793645e-05,
"loss": 0.8898,
"step": 408
},
{
"epoch": 0.61,
"learning_rate": 1.6789994788952583e-05,
"loss": 0.7381,
"step": 409
},
{
"epoch": 0.61,
"learning_rate": 1.6779572694111517e-05,
"loss": 0.7516,
"step": 410
},
{
"epoch": 0.61,
"learning_rate": 1.6769150599270455e-05,
"loss": 0.7757,
"step": 411
},
{
"epoch": 0.61,
"learning_rate": 1.675872850442939e-05,
"loss": 0.6418,
"step": 412
},
{
"epoch": 0.61,
"learning_rate": 1.6748306409588328e-05,
"loss": 0.8466,
"step": 413
},
{
"epoch": 0.62,
"learning_rate": 1.6737884314747266e-05,
"loss": 0.7008,
"step": 414
},
{
"epoch": 0.62,
"learning_rate": 1.6727462219906204e-05,
"loss": 0.6855,
"step": 415
},
{
"epoch": 0.62,
"learning_rate": 1.6717040125065142e-05,
"loss": 0.754,
"step": 416
},
{
"epoch": 0.62,
"learning_rate": 1.6706618030224076e-05,
"loss": 0.7652,
"step": 417
},
{
"epoch": 0.62,
"learning_rate": 1.6696195935383014e-05,
"loss": 0.8674,
"step": 418
},
{
"epoch": 0.62,
"learning_rate": 1.668577384054195e-05,
"loss": 0.7409,
"step": 419
},
{
"epoch": 0.62,
"learning_rate": 1.6675351745700887e-05,
"loss": 0.6421,
"step": 420
},
{
"epoch": 0.63,
"learning_rate": 1.6664929650859825e-05,
"loss": 0.7868,
"step": 421
},
{
"epoch": 0.63,
"learning_rate": 1.6654507556018763e-05,
"loss": 0.7902,
"step": 422
},
{
"epoch": 0.63,
"learning_rate": 1.66440854611777e-05,
"loss": 0.8985,
"step": 423
},
{
"epoch": 0.63,
"learning_rate": 1.6633663366336635e-05,
"loss": 0.7264,
"step": 424
},
{
"epoch": 0.63,
"learning_rate": 1.662324127149557e-05,
"loss": 0.9267,
"step": 425
},
{
"epoch": 0.63,
"learning_rate": 1.6612819176654508e-05,
"loss": 0.7026,
"step": 426
},
{
"epoch": 0.63,
"learning_rate": 1.6602397081813446e-05,
"loss": 0.7923,
"step": 427
},
{
"epoch": 0.64,
"learning_rate": 1.6591974986972384e-05,
"loss": 0.8185,
"step": 428
},
{
"epoch": 0.64,
"learning_rate": 1.6581552892131322e-05,
"loss": 0.78,
"step": 429
},
{
"epoch": 0.64,
"learning_rate": 1.6571130797290256e-05,
"loss": 0.986,
"step": 430
},
{
"epoch": 0.64,
"learning_rate": 1.6560708702449194e-05,
"loss": 0.7487,
"step": 431
},
{
"epoch": 0.64,
"learning_rate": 1.655028660760813e-05,
"loss": 0.7466,
"step": 432
},
{
"epoch": 0.64,
"learning_rate": 1.6539864512767067e-05,
"loss": 0.6738,
"step": 433
},
{
"epoch": 0.64,
"learning_rate": 1.6529442417926005e-05,
"loss": 0.711,
"step": 434
},
{
"epoch": 0.65,
"learning_rate": 1.6519020323084943e-05,
"loss": 0.8149,
"step": 435
},
{
"epoch": 0.65,
"learning_rate": 1.650859822824388e-05,
"loss": 0.6593,
"step": 436
},
{
"epoch": 0.65,
"learning_rate": 1.6498176133402815e-05,
"loss": 0.7133,
"step": 437
},
{
"epoch": 0.65,
"learning_rate": 1.6487754038561753e-05,
"loss": 0.7012,
"step": 438
},
{
"epoch": 0.65,
"learning_rate": 1.6477331943720688e-05,
"loss": 0.739,
"step": 439
},
{
"epoch": 0.65,
"learning_rate": 1.6466909848879626e-05,
"loss": 0.8774,
"step": 440
},
{
"epoch": 0.66,
"learning_rate": 1.6456487754038564e-05,
"loss": 0.759,
"step": 441
},
{
"epoch": 0.66,
"learning_rate": 1.6446065659197502e-05,
"loss": 0.8325,
"step": 442
},
{
"epoch": 0.66,
"learning_rate": 1.6435643564356436e-05,
"loss": 0.9136,
"step": 443
},
{
"epoch": 0.66,
"learning_rate": 1.6425221469515374e-05,
"loss": 0.622,
"step": 444
},
{
"epoch": 0.66,
"learning_rate": 1.641479937467431e-05,
"loss": 0.7456,
"step": 445
},
{
"epoch": 0.66,
"learning_rate": 1.6404377279833247e-05,
"loss": 0.7104,
"step": 446
},
{
"epoch": 0.66,
"learning_rate": 1.6393955184992185e-05,
"loss": 0.8386,
"step": 447
},
{
"epoch": 0.67,
"learning_rate": 1.6383533090151123e-05,
"loss": 0.8093,
"step": 448
},
{
"epoch": 0.67,
"learning_rate": 1.637311099531006e-05,
"loss": 0.744,
"step": 449
},
{
"epoch": 0.67,
"learning_rate": 1.6362688900468995e-05,
"loss": 0.7537,
"step": 450
},
{
"epoch": 0.67,
"learning_rate": 1.6352266805627933e-05,
"loss": 0.7441,
"step": 451
},
{
"epoch": 0.67,
"learning_rate": 1.6341844710786868e-05,
"loss": 0.6012,
"step": 452
},
{
"epoch": 0.67,
"learning_rate": 1.6331422615945806e-05,
"loss": 0.731,
"step": 453
},
{
"epoch": 0.67,
"learning_rate": 1.6321000521104744e-05,
"loss": 0.8034,
"step": 454
},
{
"epoch": 0.68,
"learning_rate": 1.6310578426263682e-05,
"loss": 0.9273,
"step": 455
},
{
"epoch": 0.68,
"learning_rate": 1.6300156331422616e-05,
"loss": 0.7353,
"step": 456
},
{
"epoch": 0.68,
"learning_rate": 1.6289734236581554e-05,
"loss": 0.8091,
"step": 457
},
{
"epoch": 0.68,
"learning_rate": 1.6279312141740492e-05,
"loss": 0.682,
"step": 458
},
{
"epoch": 0.68,
"learning_rate": 1.6268890046899427e-05,
"loss": 0.7877,
"step": 459
},
{
"epoch": 0.68,
"learning_rate": 1.6258467952058365e-05,
"loss": 0.7639,
"step": 460
},
{
"epoch": 0.68,
"learning_rate": 1.6248045857217303e-05,
"loss": 0.852,
"step": 461
},
{
"epoch": 0.69,
"learning_rate": 1.623762376237624e-05,
"loss": 0.7957,
"step": 462
},
{
"epoch": 0.69,
"learning_rate": 1.6227201667535175e-05,
"loss": 0.7989,
"step": 463
},
{
"epoch": 0.69,
"learning_rate": 1.6216779572694113e-05,
"loss": 0.7723,
"step": 464
},
{
"epoch": 0.69,
"learning_rate": 1.620635747785305e-05,
"loss": 0.8614,
"step": 465
},
{
"epoch": 0.69,
"learning_rate": 1.6195935383011986e-05,
"loss": 0.8833,
"step": 466
},
{
"epoch": 0.69,
"learning_rate": 1.6185513288170924e-05,
"loss": 0.7677,
"step": 467
},
{
"epoch": 0.7,
"learning_rate": 1.6175091193329862e-05,
"loss": 0.9211,
"step": 468
},
{
"epoch": 0.7,
"learning_rate": 1.6164669098488796e-05,
"loss": 0.8102,
"step": 469
},
{
"epoch": 0.7,
"learning_rate": 1.6154247003647734e-05,
"loss": 0.6814,
"step": 470
},
{
"epoch": 0.7,
"learning_rate": 1.6143824908806672e-05,
"loss": 0.7578,
"step": 471
},
{
"epoch": 0.7,
"learning_rate": 1.6133402813965607e-05,
"loss": 0.8795,
"step": 472
},
{
"epoch": 0.7,
"learning_rate": 1.6122980719124545e-05,
"loss": 0.7981,
"step": 473
},
{
"epoch": 0.7,
"learning_rate": 1.6112558624283483e-05,
"loss": 0.621,
"step": 474
},
{
"epoch": 0.71,
"learning_rate": 1.610213652944242e-05,
"loss": 0.7823,
"step": 475
},
{
"epoch": 0.71,
"learning_rate": 1.6091714434601355e-05,
"loss": 0.6799,
"step": 476
},
{
"epoch": 0.71,
"learning_rate": 1.6081292339760293e-05,
"loss": 0.8436,
"step": 477
},
{
"epoch": 0.71,
"learning_rate": 1.607087024491923e-05,
"loss": 0.7218,
"step": 478
},
{
"epoch": 0.71,
"learning_rate": 1.6060448150078166e-05,
"loss": 0.9744,
"step": 479
},
{
"epoch": 0.71,
"learning_rate": 1.6050026055237104e-05,
"loss": 0.8046,
"step": 480
},
{
"epoch": 0.71,
"learning_rate": 1.6039603960396042e-05,
"loss": 0.7073,
"step": 481
},
{
"epoch": 0.72,
"learning_rate": 1.6029181865554976e-05,
"loss": 0.9574,
"step": 482
},
{
"epoch": 0.72,
"learning_rate": 1.6018759770713914e-05,
"loss": 0.7554,
"step": 483
},
{
"epoch": 0.72,
"learning_rate": 1.6008337675872852e-05,
"loss": 0.6525,
"step": 484
},
{
"epoch": 0.72,
"learning_rate": 1.599791558103179e-05,
"loss": 0.7979,
"step": 485
},
{
"epoch": 0.72,
"learning_rate": 1.5987493486190725e-05,
"loss": 0.8549,
"step": 486
},
{
"epoch": 0.72,
"learning_rate": 1.5977071391349663e-05,
"loss": 0.743,
"step": 487
},
{
"epoch": 0.73,
"learning_rate": 1.59666492965086e-05,
"loss": 0.8243,
"step": 488
},
{
"epoch": 0.73,
"learning_rate": 1.5956227201667535e-05,
"loss": 0.7138,
"step": 489
},
{
"epoch": 0.73,
"learning_rate": 1.5945805106826473e-05,
"loss": 0.8334,
"step": 490
},
{
"epoch": 0.73,
"learning_rate": 1.593538301198541e-05,
"loss": 0.8128,
"step": 491
},
{
"epoch": 0.73,
"learning_rate": 1.592496091714435e-05,
"loss": 0.7887,
"step": 492
},
{
"epoch": 0.73,
"learning_rate": 1.5914538822303284e-05,
"loss": 0.9216,
"step": 493
},
{
"epoch": 0.73,
"learning_rate": 1.5904116727462222e-05,
"loss": 0.8926,
"step": 494
},
{
"epoch": 0.74,
"learning_rate": 1.5893694632621156e-05,
"loss": 0.8752,
"step": 495
},
{
"epoch": 0.74,
"learning_rate": 1.5883272537780094e-05,
"loss": 0.9396,
"step": 496
},
{
"epoch": 0.74,
"learning_rate": 1.5872850442939032e-05,
"loss": 0.6856,
"step": 497
},
{
"epoch": 0.74,
"learning_rate": 1.586242834809797e-05,
"loss": 0.7895,
"step": 498
},
{
"epoch": 0.74,
"learning_rate": 1.5852006253256905e-05,
"loss": 0.8479,
"step": 499
},
{
"epoch": 0.74,
"learning_rate": 1.5841584158415843e-05,
"loss": 0.6227,
"step": 500
},
{
"epoch": 0.74,
"eval_loss": 1.4052919149398804,
"eval_runtime": 0.6812,
"eval_samples_per_second": 358.176,
"eval_steps_per_second": 45.506,
"step": 500
},
{
"epoch": 0.74,
"learning_rate": 1.583116206357478e-05,
"loss": 0.6472,
"step": 501
},
{
"epoch": 0.75,
"learning_rate": 1.5820739968733715e-05,
"loss": 0.8447,
"step": 502
},
{
"epoch": 0.75,
"learning_rate": 1.5810317873892653e-05,
"loss": 0.951,
"step": 503
},
{
"epoch": 0.75,
"learning_rate": 1.579989577905159e-05,
"loss": 0.7986,
"step": 504
},
{
"epoch": 0.75,
"learning_rate": 1.578947368421053e-05,
"loss": 0.7053,
"step": 505
},
{
"epoch": 0.75,
"learning_rate": 1.5779051589369464e-05,
"loss": 0.7952,
"step": 506
},
{
"epoch": 0.75,
"learning_rate": 1.5768629494528402e-05,
"loss": 0.8477,
"step": 507
},
{
"epoch": 0.75,
"learning_rate": 1.5758207399687336e-05,
"loss": 0.697,
"step": 508
},
{
"epoch": 0.76,
"learning_rate": 1.5747785304846274e-05,
"loss": 0.8457,
"step": 509
},
{
"epoch": 0.76,
"learning_rate": 1.5737363210005212e-05,
"loss": 0.575,
"step": 510
},
{
"epoch": 0.76,
"learning_rate": 1.572694111516415e-05,
"loss": 0.7074,
"step": 511
},
{
"epoch": 0.76,
"learning_rate": 1.5716519020323088e-05,
"loss": 1.0142,
"step": 512
},
{
"epoch": 0.76,
"learning_rate": 1.5706096925482023e-05,
"loss": 0.7981,
"step": 513
},
{
"epoch": 0.76,
"learning_rate": 1.569567483064096e-05,
"loss": 0.6948,
"step": 514
},
{
"epoch": 0.77,
"learning_rate": 1.5685252735799895e-05,
"loss": 0.797,
"step": 515
},
{
"epoch": 0.77,
"learning_rate": 1.5674830640958833e-05,
"loss": 0.8838,
"step": 516
},
{
"epoch": 0.77,
"learning_rate": 1.566440854611777e-05,
"loss": 1.0186,
"step": 517
},
{
"epoch": 0.77,
"learning_rate": 1.565398645127671e-05,
"loss": 0.7033,
"step": 518
},
{
"epoch": 0.77,
"learning_rate": 1.5643564356435644e-05,
"loss": 0.8382,
"step": 519
},
{
"epoch": 0.77,
"learning_rate": 1.5633142261594582e-05,
"loss": 0.7796,
"step": 520
},
{
"epoch": 0.77,
"learning_rate": 1.5622720166753516e-05,
"loss": 0.8543,
"step": 521
},
{
"epoch": 0.78,
"learning_rate": 1.5612298071912454e-05,
"loss": 0.7737,
"step": 522
},
{
"epoch": 0.78,
"learning_rate": 1.5601875977071392e-05,
"loss": 0.859,
"step": 523
},
{
"epoch": 0.78,
"learning_rate": 1.559145388223033e-05,
"loss": 0.7694,
"step": 524
},
{
"epoch": 0.78,
"learning_rate": 1.5581031787389268e-05,
"loss": 0.735,
"step": 525
},
{
"epoch": 0.78,
"learning_rate": 1.5570609692548203e-05,
"loss": 0.6844,
"step": 526
},
{
"epoch": 0.78,
"learning_rate": 1.556018759770714e-05,
"loss": 0.8337,
"step": 527
},
{
"epoch": 0.78,
"learning_rate": 1.5549765502866075e-05,
"loss": 0.7713,
"step": 528
},
{
"epoch": 0.79,
"learning_rate": 1.5539343408025013e-05,
"loss": 0.8503,
"step": 529
},
{
"epoch": 0.79,
"learning_rate": 1.552892131318395e-05,
"loss": 0.7254,
"step": 530
},
{
"epoch": 0.79,
"learning_rate": 1.551849921834289e-05,
"loss": 0.8452,
"step": 531
},
{
"epoch": 0.79,
"learning_rate": 1.5508077123501827e-05,
"loss": 0.8226,
"step": 532
},
{
"epoch": 0.79,
"learning_rate": 1.5497655028660762e-05,
"loss": 0.7946,
"step": 533
},
{
"epoch": 0.79,
"learning_rate": 1.54872329338197e-05,
"loss": 0.7594,
"step": 534
},
{
"epoch": 0.79,
"learning_rate": 1.5476810838978634e-05,
"loss": 0.7711,
"step": 535
},
{
"epoch": 0.8,
"learning_rate": 1.5466388744137572e-05,
"loss": 0.6961,
"step": 536
},
{
"epoch": 0.8,
"learning_rate": 1.545596664929651e-05,
"loss": 0.668,
"step": 537
},
{
"epoch": 0.8,
"learning_rate": 1.5445544554455448e-05,
"loss": 0.8215,
"step": 538
},
{
"epoch": 0.8,
"learning_rate": 1.5435122459614386e-05,
"loss": 0.899,
"step": 539
},
{
"epoch": 0.8,
"learning_rate": 1.542470036477332e-05,
"loss": 0.6452,
"step": 540
},
{
"epoch": 0.8,
"learning_rate": 1.5414278269932255e-05,
"loss": 0.7401,
"step": 541
},
{
"epoch": 0.81,
"learning_rate": 1.5403856175091193e-05,
"loss": 0.7663,
"step": 542
},
{
"epoch": 0.81,
"learning_rate": 1.539343408025013e-05,
"loss": 0.8102,
"step": 543
},
{
"epoch": 0.81,
"learning_rate": 1.538301198540907e-05,
"loss": 0.6833,
"step": 544
},
{
"epoch": 0.81,
"learning_rate": 1.5372589890568007e-05,
"loss": 0.8215,
"step": 545
},
{
"epoch": 0.81,
"learning_rate": 1.5362167795726942e-05,
"loss": 0.8205,
"step": 546
},
{
"epoch": 0.81,
"learning_rate": 1.535174570088588e-05,
"loss": 0.7051,
"step": 547
},
{
"epoch": 0.81,
"learning_rate": 1.5341323606044814e-05,
"loss": 0.6459,
"step": 548
},
{
"epoch": 0.82,
"learning_rate": 1.5330901511203752e-05,
"loss": 0.6389,
"step": 549
},
{
"epoch": 0.82,
"learning_rate": 1.532047941636269e-05,
"loss": 0.8173,
"step": 550
},
{
"epoch": 0.82,
"learning_rate": 1.5310057321521628e-05,
"loss": 0.7108,
"step": 551
},
{
"epoch": 0.82,
"learning_rate": 1.5299635226680566e-05,
"loss": 0.78,
"step": 552
},
{
"epoch": 0.82,
"learning_rate": 1.52892131318395e-05,
"loss": 0.7017,
"step": 553
},
{
"epoch": 0.82,
"learning_rate": 1.527879103699844e-05,
"loss": 1.0129,
"step": 554
},
{
"epoch": 0.82,
"learning_rate": 1.5268368942157373e-05,
"loss": 0.7601,
"step": 555
},
{
"epoch": 0.83,
"learning_rate": 1.5257946847316311e-05,
"loss": 0.8861,
"step": 556
},
{
"epoch": 0.83,
"learning_rate": 1.5247524752475249e-05,
"loss": 0.9158,
"step": 557
},
{
"epoch": 0.83,
"learning_rate": 1.5237102657634187e-05,
"loss": 0.7781,
"step": 558
},
{
"epoch": 0.83,
"learning_rate": 1.5226680562793123e-05,
"loss": 0.7289,
"step": 559
},
{
"epoch": 0.83,
"learning_rate": 1.5216258467952058e-05,
"loss": 0.8442,
"step": 560
},
{
"epoch": 0.83,
"learning_rate": 1.5205836373110996e-05,
"loss": 0.7792,
"step": 561
},
{
"epoch": 0.84,
"learning_rate": 1.5195414278269934e-05,
"loss": 0.6995,
"step": 562
},
{
"epoch": 0.84,
"learning_rate": 1.518499218342887e-05,
"loss": 0.8379,
"step": 563
},
{
"epoch": 0.84,
"learning_rate": 1.5174570088587808e-05,
"loss": 0.6961,
"step": 564
},
{
"epoch": 0.84,
"learning_rate": 1.5164147993746744e-05,
"loss": 0.6868,
"step": 565
},
{
"epoch": 0.84,
"learning_rate": 1.5153725898905682e-05,
"loss": 0.7872,
"step": 566
},
{
"epoch": 0.84,
"learning_rate": 1.5143303804064617e-05,
"loss": 0.6468,
"step": 567
},
{
"epoch": 0.84,
"learning_rate": 1.5132881709223555e-05,
"loss": 0.6298,
"step": 568
},
{
"epoch": 0.85,
"learning_rate": 1.5122459614382491e-05,
"loss": 0.5914,
"step": 569
},
{
"epoch": 0.85,
"learning_rate": 1.5112037519541429e-05,
"loss": 0.8262,
"step": 570
},
{
"epoch": 0.85,
"learning_rate": 1.5101615424700367e-05,
"loss": 0.6425,
"step": 571
},
{
"epoch": 0.85,
"learning_rate": 1.5091193329859303e-05,
"loss": 0.7242,
"step": 572
},
{
"epoch": 0.85,
"learning_rate": 1.508077123501824e-05,
"loss": 0.8667,
"step": 573
},
{
"epoch": 0.85,
"learning_rate": 1.5070349140177176e-05,
"loss": 0.8544,
"step": 574
},
{
"epoch": 0.85,
"learning_rate": 1.5059927045336114e-05,
"loss": 0.8213,
"step": 575
},
{
"epoch": 0.86,
"learning_rate": 1.504950495049505e-05,
"loss": 0.8269,
"step": 576
},
{
"epoch": 0.86,
"learning_rate": 1.5039082855653988e-05,
"loss": 0.7712,
"step": 577
},
{
"epoch": 0.86,
"learning_rate": 1.5028660760812926e-05,
"loss": 0.8219,
"step": 578
},
{
"epoch": 0.86,
"learning_rate": 1.5018238665971862e-05,
"loss": 0.7262,
"step": 579
},
{
"epoch": 0.86,
"learning_rate": 1.5007816571130797e-05,
"loss": 0.7989,
"step": 580
},
{
"epoch": 0.86,
"learning_rate": 1.4997394476289735e-05,
"loss": 0.8232,
"step": 581
},
{
"epoch": 0.86,
"learning_rate": 1.4986972381448673e-05,
"loss": 0.705,
"step": 582
},
{
"epoch": 0.87,
"learning_rate": 1.4976550286607609e-05,
"loss": 0.7393,
"step": 583
},
{
"epoch": 0.87,
"learning_rate": 1.4966128191766547e-05,
"loss": 0.8477,
"step": 584
},
{
"epoch": 0.87,
"learning_rate": 1.4955706096925483e-05,
"loss": 0.7252,
"step": 585
},
{
"epoch": 0.87,
"learning_rate": 1.494528400208442e-05,
"loss": 0.6958,
"step": 586
},
{
"epoch": 0.87,
"learning_rate": 1.4934861907243356e-05,
"loss": 0.729,
"step": 587
},
{
"epoch": 0.87,
"learning_rate": 1.4924439812402294e-05,
"loss": 0.8359,
"step": 588
},
{
"epoch": 0.88,
"learning_rate": 1.4914017717561232e-05,
"loss": 0.7241,
"step": 589
},
{
"epoch": 0.88,
"learning_rate": 1.4903595622720168e-05,
"loss": 0.6694,
"step": 590
},
{
"epoch": 0.88,
"learning_rate": 1.4893173527879106e-05,
"loss": 0.6559,
"step": 591
},
{
"epoch": 0.88,
"learning_rate": 1.4882751433038042e-05,
"loss": 0.6371,
"step": 592
},
{
"epoch": 0.88,
"learning_rate": 1.4872329338196979e-05,
"loss": 0.714,
"step": 593
},
{
"epoch": 0.88,
"learning_rate": 1.4861907243355915e-05,
"loss": 0.9527,
"step": 594
},
{
"epoch": 0.88,
"learning_rate": 1.4851485148514853e-05,
"loss": 0.683,
"step": 595
},
{
"epoch": 0.89,
"learning_rate": 1.4841063053673789e-05,
"loss": 0.9006,
"step": 596
},
{
"epoch": 0.89,
"learning_rate": 1.4830640958832727e-05,
"loss": 0.5827,
"step": 597
},
{
"epoch": 0.89,
"learning_rate": 1.4820218863991665e-05,
"loss": 0.8005,
"step": 598
},
{
"epoch": 0.89,
"learning_rate": 1.48097967691506e-05,
"loss": 0.8746,
"step": 599
},
{
"epoch": 0.89,
"learning_rate": 1.4799374674309538e-05,
"loss": 0.8321,
"step": 600
},
{
"epoch": 0.89,
"learning_rate": 1.4788952579468474e-05,
"loss": 0.8988,
"step": 601
},
{
"epoch": 0.89,
"learning_rate": 1.4778530484627412e-05,
"loss": 0.7194,
"step": 602
},
{
"epoch": 0.9,
"learning_rate": 1.4768108389786348e-05,
"loss": 0.8779,
"step": 603
},
{
"epoch": 0.9,
"learning_rate": 1.4757686294945286e-05,
"loss": 0.7417,
"step": 604
},
{
"epoch": 0.9,
"learning_rate": 1.4747264200104224e-05,
"loss": 0.7501,
"step": 605
},
{
"epoch": 0.9,
"learning_rate": 1.4736842105263159e-05,
"loss": 0.9036,
"step": 606
},
{
"epoch": 0.9,
"learning_rate": 1.4726420010422095e-05,
"loss": 0.7942,
"step": 607
},
{
"epoch": 0.9,
"learning_rate": 1.4715997915581033e-05,
"loss": 0.811,
"step": 608
},
{
"epoch": 0.9,
"learning_rate": 1.470557582073997e-05,
"loss": 0.8806,
"step": 609
},
{
"epoch": 0.91,
"learning_rate": 1.4695153725898907e-05,
"loss": 0.6999,
"step": 610
},
{
"epoch": 0.91,
"learning_rate": 1.4684731631057845e-05,
"loss": 0.7964,
"step": 611
},
{
"epoch": 0.91,
"learning_rate": 1.467430953621678e-05,
"loss": 0.725,
"step": 612
},
{
"epoch": 0.91,
"learning_rate": 1.4663887441375718e-05,
"loss": 0.7521,
"step": 613
},
{
"epoch": 0.91,
"learning_rate": 1.4653465346534654e-05,
"loss": 0.6808,
"step": 614
},
{
"epoch": 0.91,
"learning_rate": 1.4643043251693592e-05,
"loss": 0.9636,
"step": 615
},
{
"epoch": 0.92,
"learning_rate": 1.463262115685253e-05,
"loss": 0.7499,
"step": 616
},
{
"epoch": 0.92,
"learning_rate": 1.4622199062011466e-05,
"loss": 0.7492,
"step": 617
},
{
"epoch": 0.92,
"learning_rate": 1.4611776967170404e-05,
"loss": 0.6387,
"step": 618
},
{
"epoch": 0.92,
"learning_rate": 1.4601354872329339e-05,
"loss": 0.9108,
"step": 619
},
{
"epoch": 0.92,
"learning_rate": 1.4590932777488277e-05,
"loss": 0.7543,
"step": 620
},
{
"epoch": 0.92,
"learning_rate": 1.4580510682647213e-05,
"loss": 0.6464,
"step": 621
},
{
"epoch": 0.92,
"learning_rate": 1.457008858780615e-05,
"loss": 0.8188,
"step": 622
},
{
"epoch": 0.93,
"learning_rate": 1.4559666492965087e-05,
"loss": 0.7667,
"step": 623
},
{
"epoch": 0.93,
"learning_rate": 1.4549244398124025e-05,
"loss": 0.9312,
"step": 624
},
{
"epoch": 0.93,
"learning_rate": 1.453882230328296e-05,
"loss": 0.7317,
"step": 625
},
{
"epoch": 0.93,
"eval_loss": 1.4036322832107544,
"eval_runtime": 0.6828,
"eval_samples_per_second": 357.339,
"eval_steps_per_second": 45.4,
"step": 625
},
{
"epoch": 0.93,
"learning_rate": 1.4528400208441898e-05,
"loss": 0.804,
"step": 626
},
{
"epoch": 0.93,
"learning_rate": 1.4517978113600835e-05,
"loss": 0.7383,
"step": 627
},
{
"epoch": 0.93,
"learning_rate": 1.4507556018759772e-05,
"loss": 0.7157,
"step": 628
},
{
"epoch": 0.93,
"learning_rate": 1.449713392391871e-05,
"loss": 0.6865,
"step": 629
},
{
"epoch": 0.94,
"learning_rate": 1.4486711829077646e-05,
"loss": 0.8644,
"step": 630
},
{
"epoch": 0.94,
"learning_rate": 1.4476289734236584e-05,
"loss": 0.6549,
"step": 631
},
{
"epoch": 0.94,
"learning_rate": 1.4465867639395519e-05,
"loss": 0.7999,
"step": 632
},
{
"epoch": 0.94,
"learning_rate": 1.4455445544554456e-05,
"loss": 0.6767,
"step": 633
},
{
"epoch": 0.94,
"learning_rate": 1.4445023449713393e-05,
"loss": 0.8104,
"step": 634
},
{
"epoch": 0.94,
"learning_rate": 1.443460135487233e-05,
"loss": 0.4852,
"step": 635
},
{
"epoch": 0.95,
"learning_rate": 1.4424179260031269e-05,
"loss": 0.8359,
"step": 636
},
{
"epoch": 0.95,
"learning_rate": 1.4413757165190205e-05,
"loss": 0.7298,
"step": 637
},
{
"epoch": 0.95,
"learning_rate": 1.440333507034914e-05,
"loss": 0.9331,
"step": 638
},
{
"epoch": 0.95,
"learning_rate": 1.4392912975508078e-05,
"loss": 0.6205,
"step": 639
},
{
"epoch": 0.95,
"learning_rate": 1.4382490880667015e-05,
"loss": 0.7542,
"step": 640
},
{
"epoch": 0.95,
"learning_rate": 1.4372068785825952e-05,
"loss": 0.8073,
"step": 641
},
{
"epoch": 0.95,
"learning_rate": 1.436164669098489e-05,
"loss": 0.7385,
"step": 642
},
{
"epoch": 0.96,
"learning_rate": 1.4351224596143826e-05,
"loss": 0.6963,
"step": 643
},
{
"epoch": 0.96,
"learning_rate": 1.4340802501302764e-05,
"loss": 0.7731,
"step": 644
},
{
"epoch": 0.96,
"learning_rate": 1.4330380406461699e-05,
"loss": 0.9263,
"step": 645
},
{
"epoch": 0.96,
"learning_rate": 1.4319958311620636e-05,
"loss": 0.7894,
"step": 646
},
{
"epoch": 0.96,
"learning_rate": 1.4309536216779574e-05,
"loss": 0.803,
"step": 647
},
{
"epoch": 0.96,
"learning_rate": 1.429911412193851e-05,
"loss": 0.8345,
"step": 648
},
{
"epoch": 0.96,
"learning_rate": 1.4288692027097449e-05,
"loss": 0.7219,
"step": 649
},
{
"epoch": 0.97,
"learning_rate": 1.4278269932256385e-05,
"loss": 0.7639,
"step": 650
},
{
"epoch": 0.97,
"learning_rate": 1.4267847837415321e-05,
"loss": 0.7458,
"step": 651
},
{
"epoch": 0.97,
"learning_rate": 1.4257425742574257e-05,
"loss": 0.85,
"step": 652
},
{
"epoch": 0.97,
"learning_rate": 1.4247003647733195e-05,
"loss": 0.8162,
"step": 653
},
{
"epoch": 0.97,
"learning_rate": 1.4236581552892132e-05,
"loss": 0.7392,
"step": 654
},
{
"epoch": 0.97,
"learning_rate": 1.422615945805107e-05,
"loss": 0.6401,
"step": 655
},
{
"epoch": 0.97,
"learning_rate": 1.4215737363210008e-05,
"loss": 0.8797,
"step": 656
},
{
"epoch": 0.98,
"learning_rate": 1.4205315268368944e-05,
"loss": 0.7372,
"step": 657
},
{
"epoch": 0.98,
"learning_rate": 1.419489317352788e-05,
"loss": 0.8824,
"step": 658
},
{
"epoch": 0.98,
"learning_rate": 1.4184471078686816e-05,
"loss": 1.0634,
"step": 659
},
{
"epoch": 0.98,
"learning_rate": 1.4174048983845754e-05,
"loss": 0.6788,
"step": 660
},
{
"epoch": 0.98,
"learning_rate": 1.416362688900469e-05,
"loss": 0.7513,
"step": 661
},
{
"epoch": 0.98,
"learning_rate": 1.4153204794163629e-05,
"loss": 0.779,
"step": 662
},
{
"epoch": 0.99,
"learning_rate": 1.4142782699322567e-05,
"loss": 0.8078,
"step": 663
},
{
"epoch": 0.99,
"learning_rate": 1.4132360604481501e-05,
"loss": 0.8041,
"step": 664
},
{
"epoch": 0.99,
"learning_rate": 1.4121938509640437e-05,
"loss": 0.7182,
"step": 665
},
{
"epoch": 0.99,
"learning_rate": 1.4111516414799375e-05,
"loss": 0.8792,
"step": 666
},
{
"epoch": 0.99,
"learning_rate": 1.4101094319958313e-05,
"loss": 0.7393,
"step": 667
},
{
"epoch": 0.99,
"learning_rate": 1.409067222511725e-05,
"loss": 0.6594,
"step": 668
},
{
"epoch": 0.99,
"learning_rate": 1.4080250130276188e-05,
"loss": 0.76,
"step": 669
},
{
"epoch": 1.0,
"learning_rate": 1.4069828035435124e-05,
"loss": 0.7869,
"step": 670
},
{
"epoch": 1.0,
"learning_rate": 1.405940594059406e-05,
"loss": 0.7759,
"step": 671
},
{
"epoch": 1.0,
"learning_rate": 1.4048983845752996e-05,
"loss": 0.7721,
"step": 672
},
{
"epoch": 1.0,
"learning_rate": 1.4038561750911934e-05,
"loss": 0.8935,
"step": 673
},
{
"epoch": 1.0,
"learning_rate": 1.4028139656070872e-05,
"loss": 0.478,
"step": 674
},
{
"epoch": 1.0,
"learning_rate": 1.4017717561229809e-05,
"loss": 0.7527,
"step": 675
},
{
"epoch": 1.0,
"learning_rate": 1.4007295466388747e-05,
"loss": 0.5814,
"step": 676
},
{
"epoch": 1.01,
"learning_rate": 1.3996873371547681e-05,
"loss": 0.6559,
"step": 677
},
{
"epoch": 1.01,
"learning_rate": 1.3986451276706619e-05,
"loss": 0.5482,
"step": 678
},
{
"epoch": 1.01,
"learning_rate": 1.3976029181865555e-05,
"loss": 0.5353,
"step": 679
},
{
"epoch": 1.01,
"learning_rate": 1.3965607087024493e-05,
"loss": 0.4359,
"step": 680
},
{
"epoch": 1.01,
"learning_rate": 1.395518499218343e-05,
"loss": 0.5285,
"step": 681
},
{
"epoch": 1.01,
"learning_rate": 1.3944762897342368e-05,
"loss": 0.6784,
"step": 682
},
{
"epoch": 1.01,
"learning_rate": 1.3934340802501306e-05,
"loss": 0.8082,
"step": 683
},
{
"epoch": 1.02,
"learning_rate": 1.392391870766024e-05,
"loss": 0.7463,
"step": 684
},
{
"epoch": 1.02,
"learning_rate": 1.3913496612819178e-05,
"loss": 0.6934,
"step": 685
},
{
"epoch": 1.02,
"learning_rate": 1.3903074517978114e-05,
"loss": 0.7304,
"step": 686
},
{
"epoch": 1.02,
"learning_rate": 1.3892652423137052e-05,
"loss": 0.5762,
"step": 687
},
{
"epoch": 1.02,
"learning_rate": 1.3882230328295989e-05,
"loss": 0.6414,
"step": 688
},
{
"epoch": 1.02,
"learning_rate": 1.3871808233454927e-05,
"loss": 0.6352,
"step": 689
},
{
"epoch": 1.03,
"learning_rate": 1.3861386138613861e-05,
"loss": 0.5834,
"step": 690
},
{
"epoch": 1.03,
"learning_rate": 1.3850964043772799e-05,
"loss": 0.7311,
"step": 691
},
{
"epoch": 1.03,
"learning_rate": 1.3840541948931735e-05,
"loss": 0.6355,
"step": 692
},
{
"epoch": 1.03,
"learning_rate": 1.3830119854090673e-05,
"loss": 0.6404,
"step": 693
},
{
"epoch": 1.03,
"learning_rate": 1.3819697759249611e-05,
"loss": 0.6473,
"step": 694
},
{
"epoch": 1.03,
"learning_rate": 1.3809275664408548e-05,
"loss": 0.6803,
"step": 695
},
{
"epoch": 1.03,
"learning_rate": 1.3798853569567486e-05,
"loss": 0.6876,
"step": 696
},
{
"epoch": 1.04,
"learning_rate": 1.378843147472642e-05,
"loss": 0.5576,
"step": 697
},
{
"epoch": 1.04,
"learning_rate": 1.3778009379885358e-05,
"loss": 0.566,
"step": 698
},
{
"epoch": 1.04,
"learning_rate": 1.3767587285044294e-05,
"loss": 0.5749,
"step": 699
},
{
"epoch": 1.04,
"learning_rate": 1.3757165190203232e-05,
"loss": 0.6698,
"step": 700
},
{
"epoch": 1.04,
"learning_rate": 1.3746743095362169e-05,
"loss": 0.6797,
"step": 701
},
{
"epoch": 1.04,
"learning_rate": 1.3736321000521107e-05,
"loss": 0.6312,
"step": 702
},
{
"epoch": 1.04,
"learning_rate": 1.3725898905680041e-05,
"loss": 0.7648,
"step": 703
},
{
"epoch": 1.05,
"learning_rate": 1.3715476810838979e-05,
"loss": 0.7218,
"step": 704
},
{
"epoch": 1.05,
"learning_rate": 1.3705054715997917e-05,
"loss": 0.7196,
"step": 705
},
{
"epoch": 1.05,
"learning_rate": 1.3694632621156853e-05,
"loss": 0.569,
"step": 706
},
{
"epoch": 1.05,
"learning_rate": 1.3684210526315791e-05,
"loss": 0.589,
"step": 707
},
{
"epoch": 1.05,
"learning_rate": 1.3673788431474728e-05,
"loss": 0.5285,
"step": 708
},
{
"epoch": 1.05,
"learning_rate": 1.3663366336633666e-05,
"loss": 0.6736,
"step": 709
},
{
"epoch": 1.05,
"learning_rate": 1.36529442417926e-05,
"loss": 0.5691,
"step": 710
},
{
"epoch": 1.06,
"learning_rate": 1.3642522146951538e-05,
"loss": 0.7969,
"step": 711
},
{
"epoch": 1.06,
"learning_rate": 1.3632100052110474e-05,
"loss": 0.6301,
"step": 712
},
{
"epoch": 1.06,
"learning_rate": 1.3621677957269412e-05,
"loss": 0.5835,
"step": 713
},
{
"epoch": 1.06,
"learning_rate": 1.361125586242835e-05,
"loss": 0.6131,
"step": 714
},
{
"epoch": 1.06,
"learning_rate": 1.3600833767587287e-05,
"loss": 0.5875,
"step": 715
},
{
"epoch": 1.06,
"learning_rate": 1.3590411672746223e-05,
"loss": 0.5238,
"step": 716
},
{
"epoch": 1.07,
"learning_rate": 1.3579989577905159e-05,
"loss": 0.6558,
"step": 717
},
{
"epoch": 1.07,
"learning_rate": 1.3569567483064097e-05,
"loss": 0.7193,
"step": 718
},
{
"epoch": 1.07,
"learning_rate": 1.3559145388223033e-05,
"loss": 0.7304,
"step": 719
},
{
"epoch": 1.07,
"learning_rate": 1.3548723293381971e-05,
"loss": 0.6825,
"step": 720
},
{
"epoch": 1.07,
"learning_rate": 1.353830119854091e-05,
"loss": 0.6913,
"step": 721
},
{
"epoch": 1.07,
"learning_rate": 1.3527879103699846e-05,
"loss": 0.7598,
"step": 722
},
{
"epoch": 1.07,
"learning_rate": 1.351745700885878e-05,
"loss": 0.7296,
"step": 723
},
{
"epoch": 1.08,
"learning_rate": 1.3507034914017718e-05,
"loss": 0.5977,
"step": 724
},
{
"epoch": 1.08,
"learning_rate": 1.3496612819176656e-05,
"loss": 0.7384,
"step": 725
},
{
"epoch": 1.08,
"learning_rate": 1.3486190724335592e-05,
"loss": 0.7384,
"step": 726
},
{
"epoch": 1.08,
"learning_rate": 1.347576862949453e-05,
"loss": 0.5237,
"step": 727
},
{
"epoch": 1.08,
"learning_rate": 1.3465346534653467e-05,
"loss": 0.7766,
"step": 728
},
{
"epoch": 1.08,
"learning_rate": 1.3454924439812403e-05,
"loss": 0.6077,
"step": 729
},
{
"epoch": 1.08,
"learning_rate": 1.3444502344971339e-05,
"loss": 0.4952,
"step": 730
},
{
"epoch": 1.09,
"learning_rate": 1.3434080250130277e-05,
"loss": 0.5211,
"step": 731
},
{
"epoch": 1.09,
"learning_rate": 1.3423658155289215e-05,
"loss": 0.601,
"step": 732
},
{
"epoch": 1.09,
"learning_rate": 1.3413236060448151e-05,
"loss": 0.7515,
"step": 733
},
{
"epoch": 1.09,
"learning_rate": 1.340281396560709e-05,
"loss": 0.5726,
"step": 734
},
{
"epoch": 1.09,
"learning_rate": 1.3392391870766026e-05,
"loss": 0.593,
"step": 735
},
{
"epoch": 1.09,
"learning_rate": 1.3381969775924962e-05,
"loss": 0.6977,
"step": 736
},
{
"epoch": 1.1,
"learning_rate": 1.3371547681083898e-05,
"loss": 0.7146,
"step": 737
},
{
"epoch": 1.1,
"learning_rate": 1.3361125586242836e-05,
"loss": 0.556,
"step": 738
},
{
"epoch": 1.1,
"learning_rate": 1.3350703491401772e-05,
"loss": 0.4768,
"step": 739
},
{
"epoch": 1.1,
"learning_rate": 1.334028139656071e-05,
"loss": 0.6493,
"step": 740
},
{
"epoch": 1.1,
"learning_rate": 1.3329859301719648e-05,
"loss": 0.7462,
"step": 741
},
{
"epoch": 1.1,
"learning_rate": 1.3319437206878583e-05,
"loss": 0.644,
"step": 742
},
{
"epoch": 1.1,
"learning_rate": 1.330901511203752e-05,
"loss": 0.6876,
"step": 743
},
{
"epoch": 1.11,
"learning_rate": 1.3298593017196457e-05,
"loss": 0.6153,
"step": 744
},
{
"epoch": 1.11,
"learning_rate": 1.3288170922355395e-05,
"loss": 0.6567,
"step": 745
},
{
"epoch": 1.11,
"learning_rate": 1.3277748827514331e-05,
"loss": 0.8993,
"step": 746
},
{
"epoch": 1.11,
"learning_rate": 1.326732673267327e-05,
"loss": 0.7152,
"step": 747
},
{
"epoch": 1.11,
"learning_rate": 1.3256904637832207e-05,
"loss": 0.6741,
"step": 748
},
{
"epoch": 1.11,
"learning_rate": 1.3246482542991142e-05,
"loss": 0.8251,
"step": 749
},
{
"epoch": 1.11,
"learning_rate": 1.3236060448150078e-05,
"loss": 0.681,
"step": 750
},
{
"epoch": 1.11,
"eval_loss": 1.4148905277252197,
"eval_runtime": 0.6829,
"eval_samples_per_second": 357.29,
"eval_steps_per_second": 45.393,
"step": 750
},
{
"epoch": 1.12,
"learning_rate": 1.3225638353309016e-05,
"loss": 0.585,
"step": 751
},
{
"epoch": 1.12,
"learning_rate": 1.3215216258467954e-05,
"loss": 0.7098,
"step": 752
},
{
"epoch": 1.12,
"learning_rate": 1.320479416362689e-05,
"loss": 0.6905,
"step": 753
},
{
"epoch": 1.12,
"learning_rate": 1.3194372068785828e-05,
"loss": 0.5776,
"step": 754
},
{
"epoch": 1.12,
"learning_rate": 1.3183949973944763e-05,
"loss": 0.533,
"step": 755
},
{
"epoch": 1.12,
"learning_rate": 1.31735278791037e-05,
"loss": 0.8204,
"step": 756
},
{
"epoch": 1.12,
"learning_rate": 1.3163105784262637e-05,
"loss": 0.5992,
"step": 757
},
{
"epoch": 1.13,
"learning_rate": 1.3152683689421575e-05,
"loss": 0.6665,
"step": 758
},
{
"epoch": 1.13,
"learning_rate": 1.3142261594580513e-05,
"loss": 0.6687,
"step": 759
},
{
"epoch": 1.13,
"learning_rate": 1.313183949973945e-05,
"loss": 0.6453,
"step": 760
},
{
"epoch": 1.13,
"learning_rate": 1.3121417404898387e-05,
"loss": 0.6158,
"step": 761
},
{
"epoch": 1.13,
"learning_rate": 1.3110995310057322e-05,
"loss": 0.6409,
"step": 762
},
{
"epoch": 1.13,
"learning_rate": 1.310057321521626e-05,
"loss": 0.8109,
"step": 763
},
{
"epoch": 1.14,
"learning_rate": 1.3090151120375196e-05,
"loss": 0.6122,
"step": 764
},
{
"epoch": 1.14,
"learning_rate": 1.3079729025534134e-05,
"loss": 0.6431,
"step": 765
},
{
"epoch": 1.14,
"learning_rate": 1.306930693069307e-05,
"loss": 0.7474,
"step": 766
},
{
"epoch": 1.14,
"learning_rate": 1.3058884835852008e-05,
"loss": 0.5338,
"step": 767
},
{
"epoch": 1.14,
"learning_rate": 1.3048462741010943e-05,
"loss": 0.6808,
"step": 768
},
{
"epoch": 1.14,
"learning_rate": 1.303804064616988e-05,
"loss": 0.5391,
"step": 769
},
{
"epoch": 1.14,
"learning_rate": 1.3027618551328817e-05,
"loss": 0.731,
"step": 770
},
{
"epoch": 1.15,
"learning_rate": 1.3017196456487755e-05,
"loss": 0.8208,
"step": 771
},
{
"epoch": 1.15,
"learning_rate": 1.3006774361646693e-05,
"loss": 0.7597,
"step": 772
},
{
"epoch": 1.15,
"learning_rate": 1.299635226680563e-05,
"loss": 0.7891,
"step": 773
},
{
"epoch": 1.15,
"learning_rate": 1.2985930171964567e-05,
"loss": 0.4956,
"step": 774
},
{
"epoch": 1.15,
"learning_rate": 1.2975508077123502e-05,
"loss": 0.6759,
"step": 775
},
{
"epoch": 1.15,
"learning_rate": 1.296508598228244e-05,
"loss": 0.6952,
"step": 776
},
{
"epoch": 1.15,
"learning_rate": 1.2954663887441376e-05,
"loss": 0.8049,
"step": 777
},
{
"epoch": 1.16,
"learning_rate": 1.2944241792600314e-05,
"loss": 0.7684,
"step": 778
},
{
"epoch": 1.16,
"learning_rate": 1.2933819697759252e-05,
"loss": 0.6378,
"step": 779
},
{
"epoch": 1.16,
"learning_rate": 1.2923397602918188e-05,
"loss": 0.5973,
"step": 780
},
{
"epoch": 1.16,
"learning_rate": 1.2912975508077123e-05,
"loss": 0.6076,
"step": 781
},
{
"epoch": 1.16,
"learning_rate": 1.290255341323606e-05,
"loss": 0.6369,
"step": 782
},
{
"epoch": 1.16,
"learning_rate": 1.2892131318394999e-05,
"loss": 0.5992,
"step": 783
},
{
"epoch": 1.16,
"learning_rate": 1.2881709223553935e-05,
"loss": 0.6928,
"step": 784
},
{
"epoch": 1.17,
"learning_rate": 1.2871287128712873e-05,
"loss": 0.7085,
"step": 785
},
{
"epoch": 1.17,
"learning_rate": 1.286086503387181e-05,
"loss": 0.6317,
"step": 786
},
{
"epoch": 1.17,
"learning_rate": 1.2850442939030747e-05,
"loss": 0.697,
"step": 787
},
{
"epoch": 1.17,
"learning_rate": 1.2840020844189682e-05,
"loss": 0.6722,
"step": 788
},
{
"epoch": 1.17,
"learning_rate": 1.282959874934862e-05,
"loss": 0.5766,
"step": 789
},
{
"epoch": 1.17,
"learning_rate": 1.2819176654507558e-05,
"loss": 0.6338,
"step": 790
},
{
"epoch": 1.18,
"learning_rate": 1.2808754559666494e-05,
"loss": 0.54,
"step": 791
},
{
"epoch": 1.18,
"learning_rate": 1.2798332464825432e-05,
"loss": 0.5775,
"step": 792
},
{
"epoch": 1.18,
"learning_rate": 1.2787910369984368e-05,
"loss": 0.5557,
"step": 793
},
{
"epoch": 1.18,
"learning_rate": 1.2777488275143304e-05,
"loss": 0.8882,
"step": 794
},
{
"epoch": 1.18,
"learning_rate": 1.276706618030224e-05,
"loss": 0.5439,
"step": 795
},
{
"epoch": 1.18,
"learning_rate": 1.2756644085461179e-05,
"loss": 0.8192,
"step": 796
},
{
"epoch": 1.18,
"learning_rate": 1.2746221990620115e-05,
"loss": 0.7168,
"step": 797
},
{
"epoch": 1.19,
"learning_rate": 1.2735799895779053e-05,
"loss": 0.7053,
"step": 798
},
{
"epoch": 1.19,
"learning_rate": 1.272537780093799e-05,
"loss": 0.7466,
"step": 799
},
{
"epoch": 1.19,
"learning_rate": 1.2714955706096927e-05,
"loss": 0.602,
"step": 800
},
{
"epoch": 1.19,
"learning_rate": 1.2704533611255863e-05,
"loss": 0.585,
"step": 801
},
{
"epoch": 1.19,
"learning_rate": 1.26941115164148e-05,
"loss": 0.6028,
"step": 802
},
{
"epoch": 1.19,
"learning_rate": 1.2683689421573738e-05,
"loss": 0.6587,
"step": 803
},
{
"epoch": 1.19,
"learning_rate": 1.2673267326732674e-05,
"loss": 0.6094,
"step": 804
},
{
"epoch": 1.2,
"learning_rate": 1.2662845231891612e-05,
"loss": 0.7432,
"step": 805
},
{
"epoch": 1.2,
"learning_rate": 1.265242313705055e-05,
"loss": 0.681,
"step": 806
},
{
"epoch": 1.2,
"learning_rate": 1.2642001042209484e-05,
"loss": 0.7389,
"step": 807
},
{
"epoch": 1.2,
"learning_rate": 1.263157894736842e-05,
"loss": 0.6605,
"step": 808
},
{
"epoch": 1.2,
"learning_rate": 1.2621156852527359e-05,
"loss": 1.035,
"step": 809
},
{
"epoch": 1.2,
"learning_rate": 1.2610734757686297e-05,
"loss": 0.9414,
"step": 810
},
{
"epoch": 1.21,
"learning_rate": 1.2600312662845233e-05,
"loss": 0.6568,
"step": 811
},
{
"epoch": 1.21,
"learning_rate": 1.258989056800417e-05,
"loss": 0.7017,
"step": 812
},
{
"epoch": 1.21,
"learning_rate": 1.2579468473163107e-05,
"loss": 0.4725,
"step": 813
},
{
"epoch": 1.21,
"learning_rate": 1.2569046378322043e-05,
"loss": 0.5439,
"step": 814
},
{
"epoch": 1.21,
"learning_rate": 1.255862428348098e-05,
"loss": 0.7674,
"step": 815
},
{
"epoch": 1.21,
"learning_rate": 1.2548202188639918e-05,
"loss": 0.5886,
"step": 816
},
{
"epoch": 1.21,
"learning_rate": 1.2537780093798856e-05,
"loss": 0.6738,
"step": 817
},
{
"epoch": 1.22,
"learning_rate": 1.2527357998957792e-05,
"loss": 0.5979,
"step": 818
},
{
"epoch": 1.22,
"learning_rate": 1.251693590411673e-05,
"loss": 0.6732,
"step": 819
},
{
"epoch": 1.22,
"learning_rate": 1.2506513809275664e-05,
"loss": 0.7215,
"step": 820
},
{
"epoch": 1.22,
"learning_rate": 1.2496091714434602e-05,
"loss": 0.8035,
"step": 821
},
{
"epoch": 1.22,
"learning_rate": 1.2485669619593539e-05,
"loss": 0.791,
"step": 822
},
{
"epoch": 1.22,
"learning_rate": 1.2475247524752477e-05,
"loss": 0.879,
"step": 823
},
{
"epoch": 1.22,
"learning_rate": 1.2464825429911413e-05,
"loss": 0.6933,
"step": 824
},
{
"epoch": 1.23,
"learning_rate": 1.245440333507035e-05,
"loss": 0.6732,
"step": 825
},
{
"epoch": 1.23,
"learning_rate": 1.2443981240229289e-05,
"loss": 0.471,
"step": 826
},
{
"epoch": 1.23,
"learning_rate": 1.2433559145388223e-05,
"loss": 0.6209,
"step": 827
},
{
"epoch": 1.23,
"learning_rate": 1.242313705054716e-05,
"loss": 0.7711,
"step": 828
},
{
"epoch": 1.23,
"learning_rate": 1.2412714955706098e-05,
"loss": 0.5243,
"step": 829
},
{
"epoch": 1.23,
"learning_rate": 1.2402292860865036e-05,
"loss": 0.6372,
"step": 830
},
{
"epoch": 1.23,
"learning_rate": 1.2391870766023972e-05,
"loss": 0.6331,
"step": 831
},
{
"epoch": 1.24,
"learning_rate": 1.238144867118291e-05,
"loss": 0.724,
"step": 832
},
{
"epoch": 1.24,
"learning_rate": 1.2371026576341844e-05,
"loss": 0.6556,
"step": 833
},
{
"epoch": 1.24,
"learning_rate": 1.2360604481500782e-05,
"loss": 0.6917,
"step": 834
},
{
"epoch": 1.24,
"learning_rate": 1.2350182386659719e-05,
"loss": 0.6015,
"step": 835
},
{
"epoch": 1.24,
"learning_rate": 1.2339760291818657e-05,
"loss": 0.7699,
"step": 836
},
{
"epoch": 1.24,
"learning_rate": 1.2329338196977595e-05,
"loss": 0.685,
"step": 837
},
{
"epoch": 1.25,
"learning_rate": 1.231891610213653e-05,
"loss": 0.782,
"step": 838
},
{
"epoch": 1.25,
"learning_rate": 1.2308494007295469e-05,
"loss": 0.6774,
"step": 839
},
{
"epoch": 1.25,
"learning_rate": 1.2298071912454403e-05,
"loss": 0.638,
"step": 840
},
{
"epoch": 1.25,
"learning_rate": 1.2287649817613341e-05,
"loss": 0.7751,
"step": 841
},
{
"epoch": 1.25,
"learning_rate": 1.2277227722772278e-05,
"loss": 0.5947,
"step": 842
},
{
"epoch": 1.25,
"learning_rate": 1.2266805627931216e-05,
"loss": 0.6068,
"step": 843
},
{
"epoch": 1.25,
"learning_rate": 1.2256383533090152e-05,
"loss": 0.584,
"step": 844
},
{
"epoch": 1.26,
"learning_rate": 1.224596143824909e-05,
"loss": 0.617,
"step": 845
},
{
"epoch": 1.26,
"learning_rate": 1.2235539343408024e-05,
"loss": 0.7015,
"step": 846
},
{
"epoch": 1.26,
"learning_rate": 1.2225117248566962e-05,
"loss": 0.5526,
"step": 847
},
{
"epoch": 1.26,
"learning_rate": 1.22146951537259e-05,
"loss": 0.8132,
"step": 848
},
{
"epoch": 1.26,
"learning_rate": 1.2204273058884837e-05,
"loss": 0.6442,
"step": 849
},
{
"epoch": 1.26,
"learning_rate": 1.2193850964043774e-05,
"loss": 0.7009,
"step": 850
},
{
"epoch": 1.26,
"learning_rate": 1.218342886920271e-05,
"loss": 0.73,
"step": 851
},
{
"epoch": 1.27,
"learning_rate": 1.2173006774361649e-05,
"loss": 0.5938,
"step": 852
},
{
"epoch": 1.27,
"learning_rate": 1.2162584679520583e-05,
"loss": 0.5819,
"step": 853
},
{
"epoch": 1.27,
"learning_rate": 1.2152162584679521e-05,
"loss": 0.6471,
"step": 854
},
{
"epoch": 1.27,
"learning_rate": 1.2141740489838458e-05,
"loss": 0.6964,
"step": 855
},
{
"epoch": 1.27,
"learning_rate": 1.2131318394997396e-05,
"loss": 0.6639,
"step": 856
},
{
"epoch": 1.27,
"learning_rate": 1.2120896300156333e-05,
"loss": 0.6479,
"step": 857
},
{
"epoch": 1.27,
"learning_rate": 1.211047420531527e-05,
"loss": 0.5854,
"step": 858
},
{
"epoch": 1.28,
"learning_rate": 1.2100052110474206e-05,
"loss": 0.6386,
"step": 859
},
{
"epoch": 1.28,
"learning_rate": 1.2089630015633142e-05,
"loss": 0.5664,
"step": 860
},
{
"epoch": 1.28,
"learning_rate": 1.207920792079208e-05,
"loss": 0.4708,
"step": 861
},
{
"epoch": 1.28,
"learning_rate": 1.2068785825951017e-05,
"loss": 0.6463,
"step": 862
},
{
"epoch": 1.28,
"learning_rate": 1.2058363731109954e-05,
"loss": 0.7414,
"step": 863
},
{
"epoch": 1.28,
"learning_rate": 1.2047941636268892e-05,
"loss": 0.8658,
"step": 864
},
{
"epoch": 1.29,
"learning_rate": 1.2037519541427829e-05,
"loss": 0.505,
"step": 865
},
{
"epoch": 1.29,
"learning_rate": 1.2027097446586763e-05,
"loss": 0.6083,
"step": 866
},
{
"epoch": 1.29,
"learning_rate": 1.2016675351745701e-05,
"loss": 0.5182,
"step": 867
},
{
"epoch": 1.29,
"learning_rate": 1.200625325690464e-05,
"loss": 0.5486,
"step": 868
},
{
"epoch": 1.29,
"learning_rate": 1.1995831162063575e-05,
"loss": 0.6522,
"step": 869
},
{
"epoch": 1.29,
"learning_rate": 1.1985409067222513e-05,
"loss": 0.9345,
"step": 870
},
{
"epoch": 1.29,
"learning_rate": 1.197498697238145e-05,
"loss": 0.6214,
"step": 871
},
{
"epoch": 1.3,
"learning_rate": 1.1964564877540386e-05,
"loss": 0.6844,
"step": 872
},
{
"epoch": 1.3,
"learning_rate": 1.1954142782699322e-05,
"loss": 0.7068,
"step": 873
},
{
"epoch": 1.3,
"learning_rate": 1.194372068785826e-05,
"loss": 0.7144,
"step": 874
},
{
"epoch": 1.3,
"learning_rate": 1.1933298593017198e-05,
"loss": 0.5733,
"step": 875
},
{
"epoch": 1.3,
"eval_loss": 1.4106025695800781,
"eval_runtime": 0.6824,
"eval_samples_per_second": 357.542,
"eval_steps_per_second": 45.425,
"step": 875
},
{
"epoch": 1.3,
"learning_rate": 1.1922876498176134e-05,
"loss": 0.5646,
"step": 876
},
{
"epoch": 1.3,
"learning_rate": 1.1912454403335072e-05,
"loss": 0.6975,
"step": 877
},
{
"epoch": 1.3,
"learning_rate": 1.1902032308494009e-05,
"loss": 0.6477,
"step": 878
},
{
"epoch": 1.31,
"learning_rate": 1.1891610213652945e-05,
"loss": 0.6836,
"step": 879
},
{
"epoch": 1.31,
"learning_rate": 1.1881188118811881e-05,
"loss": 0.6404,
"step": 880
},
{
"epoch": 1.31,
"learning_rate": 1.187076602397082e-05,
"loss": 0.6566,
"step": 881
},
{
"epoch": 1.31,
"learning_rate": 1.1860343929129755e-05,
"loss": 0.6763,
"step": 882
},
{
"epoch": 1.31,
"learning_rate": 1.1849921834288693e-05,
"loss": 0.6033,
"step": 883
},
{
"epoch": 1.31,
"learning_rate": 1.1839499739447631e-05,
"loss": 0.5867,
"step": 884
},
{
"epoch": 1.32,
"learning_rate": 1.1829077644606566e-05,
"loss": 0.5879,
"step": 885
},
{
"epoch": 1.32,
"learning_rate": 1.1818655549765504e-05,
"loss": 0.5958,
"step": 886
},
{
"epoch": 1.32,
"learning_rate": 1.180823345492444e-05,
"loss": 0.7745,
"step": 887
},
{
"epoch": 1.32,
"learning_rate": 1.1797811360083378e-05,
"loss": 0.71,
"step": 888
},
{
"epoch": 1.32,
"learning_rate": 1.1787389265242314e-05,
"loss": 0.6798,
"step": 889
},
{
"epoch": 1.32,
"learning_rate": 1.1776967170401252e-05,
"loss": 0.7242,
"step": 890
},
{
"epoch": 1.32,
"learning_rate": 1.176654507556019e-05,
"loss": 0.7227,
"step": 891
},
{
"epoch": 1.33,
"learning_rate": 1.1756122980719125e-05,
"loss": 0.5997,
"step": 892
},
{
"epoch": 1.33,
"learning_rate": 1.1745700885878061e-05,
"loss": 0.8046,
"step": 893
},
{
"epoch": 1.33,
"learning_rate": 1.1735278791037e-05,
"loss": 0.7447,
"step": 894
},
{
"epoch": 1.33,
"learning_rate": 1.1724856696195937e-05,
"loss": 0.7086,
"step": 895
},
{
"epoch": 1.33,
"learning_rate": 1.1714434601354873e-05,
"loss": 0.6405,
"step": 896
},
{
"epoch": 1.33,
"learning_rate": 1.1704012506513811e-05,
"loss": 0.5599,
"step": 897
},
{
"epoch": 1.33,
"learning_rate": 1.1693590411672746e-05,
"loss": 0.7145,
"step": 898
},
{
"epoch": 1.34,
"learning_rate": 1.1683168316831684e-05,
"loss": 0.6469,
"step": 899
},
{
"epoch": 1.34,
"learning_rate": 1.167274622199062e-05,
"loss": 0.6017,
"step": 900
},
{
"epoch": 1.34,
"learning_rate": 1.1662324127149558e-05,
"loss": 0.6717,
"step": 901
},
{
"epoch": 1.34,
"learning_rate": 1.1651902032308494e-05,
"loss": 0.5498,
"step": 902
},
{
"epoch": 1.34,
"learning_rate": 1.1641479937467432e-05,
"loss": 0.6697,
"step": 903
},
{
"epoch": 1.34,
"learning_rate": 1.163105784262637e-05,
"loss": 0.6168,
"step": 904
},
{
"epoch": 1.34,
"learning_rate": 1.1620635747785305e-05,
"loss": 0.6073,
"step": 905
},
{
"epoch": 1.35,
"learning_rate": 1.1610213652944243e-05,
"loss": 0.7787,
"step": 906
},
{
"epoch": 1.35,
"learning_rate": 1.159979155810318e-05,
"loss": 0.714,
"step": 907
},
{
"epoch": 1.35,
"learning_rate": 1.1589369463262117e-05,
"loss": 0.5519,
"step": 908
},
{
"epoch": 1.35,
"learning_rate": 1.1578947368421053e-05,
"loss": 0.5521,
"step": 909
},
{
"epoch": 1.35,
"learning_rate": 1.1568525273579991e-05,
"loss": 0.6649,
"step": 910
},
{
"epoch": 1.35,
"learning_rate": 1.1558103178738926e-05,
"loss": 0.6734,
"step": 911
},
{
"epoch": 1.36,
"learning_rate": 1.1547681083897864e-05,
"loss": 0.6343,
"step": 912
},
{
"epoch": 1.36,
"learning_rate": 1.15372589890568e-05,
"loss": 0.7617,
"step": 913
},
{
"epoch": 1.36,
"learning_rate": 1.1526836894215738e-05,
"loss": 0.5289,
"step": 914
},
{
"epoch": 1.36,
"learning_rate": 1.1516414799374676e-05,
"loss": 0.6656,
"step": 915
},
{
"epoch": 1.36,
"learning_rate": 1.1505992704533612e-05,
"loss": 0.7067,
"step": 916
},
{
"epoch": 1.36,
"learning_rate": 1.149557060969255e-05,
"loss": 0.5984,
"step": 917
},
{
"epoch": 1.36,
"learning_rate": 1.1485148514851485e-05,
"loss": 0.592,
"step": 918
},
{
"epoch": 1.37,
"learning_rate": 1.1474726420010423e-05,
"loss": 0.532,
"step": 919
},
{
"epoch": 1.37,
"learning_rate": 1.1464304325169359e-05,
"loss": 0.5906,
"step": 920
},
{
"epoch": 1.37,
"learning_rate": 1.1453882230328297e-05,
"loss": 0.6541,
"step": 921
},
{
"epoch": 1.37,
"learning_rate": 1.1443460135487235e-05,
"loss": 0.7358,
"step": 922
},
{
"epoch": 1.37,
"learning_rate": 1.1433038040646171e-05,
"loss": 0.805,
"step": 923
},
{
"epoch": 1.37,
"learning_rate": 1.1422615945805106e-05,
"loss": 0.5806,
"step": 924
},
{
"epoch": 1.37,
"learning_rate": 1.1412193850964044e-05,
"loss": 0.7057,
"step": 925
},
{
"epoch": 1.38,
"learning_rate": 1.1401771756122982e-05,
"loss": 0.7038,
"step": 926
},
{
"epoch": 1.38,
"learning_rate": 1.1391349661281918e-05,
"loss": 0.5984,
"step": 927
},
{
"epoch": 1.38,
"learning_rate": 1.1380927566440856e-05,
"loss": 0.6154,
"step": 928
},
{
"epoch": 1.38,
"learning_rate": 1.1370505471599792e-05,
"loss": 0.5576,
"step": 929
},
{
"epoch": 1.38,
"learning_rate": 1.136008337675873e-05,
"loss": 0.6755,
"step": 930
},
{
"epoch": 1.38,
"learning_rate": 1.1349661281917665e-05,
"loss": 0.737,
"step": 931
},
{
"epoch": 1.38,
"learning_rate": 1.1339239187076603e-05,
"loss": 0.5667,
"step": 932
},
{
"epoch": 1.39,
"learning_rate": 1.132881709223554e-05,
"loss": 0.6664,
"step": 933
},
{
"epoch": 1.39,
"learning_rate": 1.1318394997394477e-05,
"loss": 0.7441,
"step": 934
},
{
"epoch": 1.39,
"learning_rate": 1.1307972902553415e-05,
"loss": 0.6832,
"step": 935
},
{
"epoch": 1.39,
"learning_rate": 1.1297550807712351e-05,
"loss": 0.6012,
"step": 936
},
{
"epoch": 1.39,
"learning_rate": 1.1287128712871288e-05,
"loss": 0.641,
"step": 937
},
{
"epoch": 1.39,
"learning_rate": 1.1276706618030224e-05,
"loss": 0.6449,
"step": 938
},
{
"epoch": 1.4,
"learning_rate": 1.1266284523189162e-05,
"loss": 0.5676,
"step": 939
},
{
"epoch": 1.4,
"learning_rate": 1.1255862428348098e-05,
"loss": 0.7318,
"step": 940
},
{
"epoch": 1.4,
"learning_rate": 1.1245440333507036e-05,
"loss": 0.7254,
"step": 941
},
{
"epoch": 1.4,
"learning_rate": 1.1235018238665974e-05,
"loss": 0.5324,
"step": 942
},
{
"epoch": 1.4,
"learning_rate": 1.122459614382491e-05,
"loss": 0.7383,
"step": 943
},
{
"epoch": 1.4,
"learning_rate": 1.1214174048983847e-05,
"loss": 0.6054,
"step": 944
},
{
"epoch": 1.4,
"learning_rate": 1.1203751954142783e-05,
"loss": 0.6625,
"step": 945
},
{
"epoch": 1.41,
"learning_rate": 1.119332985930172e-05,
"loss": 0.7526,
"step": 946
},
{
"epoch": 1.41,
"learning_rate": 1.1182907764460657e-05,
"loss": 0.6867,
"step": 947
},
{
"epoch": 1.41,
"learning_rate": 1.1172485669619595e-05,
"loss": 0.695,
"step": 948
},
{
"epoch": 1.41,
"learning_rate": 1.1162063574778533e-05,
"loss": 0.6788,
"step": 949
},
{
"epoch": 1.41,
"learning_rate": 1.1151641479937468e-05,
"loss": 0.7039,
"step": 950
},
{
"epoch": 1.41,
"learning_rate": 1.1141219385096404e-05,
"loss": 0.5979,
"step": 951
},
{
"epoch": 1.41,
"learning_rate": 1.1130797290255342e-05,
"loss": 0.7379,
"step": 952
},
{
"epoch": 1.42,
"learning_rate": 1.112037519541428e-05,
"loss": 0.7438,
"step": 953
},
{
"epoch": 1.42,
"learning_rate": 1.1109953100573216e-05,
"loss": 0.6428,
"step": 954
},
{
"epoch": 1.42,
"learning_rate": 1.1099531005732154e-05,
"loss": 0.6789,
"step": 955
},
{
"epoch": 1.42,
"learning_rate": 1.108910891089109e-05,
"loss": 0.672,
"step": 956
},
{
"epoch": 1.42,
"learning_rate": 1.1078686816050027e-05,
"loss": 0.5176,
"step": 957
},
{
"epoch": 1.42,
"learning_rate": 1.1068264721208963e-05,
"loss": 0.7264,
"step": 958
},
{
"epoch": 1.42,
"learning_rate": 1.10578426263679e-05,
"loss": 0.5447,
"step": 959
},
{
"epoch": 1.43,
"learning_rate": 1.1047420531526839e-05,
"loss": 0.6478,
"step": 960
},
{
"epoch": 1.43,
"learning_rate": 1.1036998436685775e-05,
"loss": 0.5701,
"step": 961
},
{
"epoch": 1.43,
"learning_rate": 1.1026576341844713e-05,
"loss": 0.7855,
"step": 962
},
{
"epoch": 1.43,
"learning_rate": 1.1016154247003648e-05,
"loss": 0.6387,
"step": 963
},
{
"epoch": 1.43,
"learning_rate": 1.1005732152162586e-05,
"loss": 0.5867,
"step": 964
},
{
"epoch": 1.43,
"learning_rate": 1.0995310057321522e-05,
"loss": 0.6254,
"step": 965
},
{
"epoch": 1.44,
"learning_rate": 1.098488796248046e-05,
"loss": 0.6631,
"step": 966
},
{
"epoch": 1.44,
"learning_rate": 1.0974465867639396e-05,
"loss": 0.8164,
"step": 967
},
{
"epoch": 1.44,
"learning_rate": 1.0964043772798334e-05,
"loss": 0.7209,
"step": 968
},
{
"epoch": 1.44,
"learning_rate": 1.0953621677957272e-05,
"loss": 0.76,
"step": 969
},
{
"epoch": 1.44,
"learning_rate": 1.0943199583116207e-05,
"loss": 0.6395,
"step": 970
},
{
"epoch": 1.44,
"learning_rate": 1.0932777488275143e-05,
"loss": 0.7242,
"step": 971
},
{
"epoch": 1.44,
"learning_rate": 1.092235539343408e-05,
"loss": 0.6829,
"step": 972
},
{
"epoch": 1.45,
"learning_rate": 1.0911933298593019e-05,
"loss": 0.6493,
"step": 973
},
{
"epoch": 1.45,
"learning_rate": 1.0901511203751955e-05,
"loss": 0.6401,
"step": 974
},
{
"epoch": 1.45,
"learning_rate": 1.0891089108910893e-05,
"loss": 0.4674,
"step": 975
},
{
"epoch": 1.45,
"learning_rate": 1.0880667014069828e-05,
"loss": 0.6746,
"step": 976
},
{
"epoch": 1.45,
"learning_rate": 1.0870244919228766e-05,
"loss": 0.5146,
"step": 977
},
{
"epoch": 1.45,
"learning_rate": 1.0859822824387702e-05,
"loss": 0.6411,
"step": 978
},
{
"epoch": 1.45,
"learning_rate": 1.084940072954664e-05,
"loss": 0.5716,
"step": 979
},
{
"epoch": 1.46,
"learning_rate": 1.0838978634705578e-05,
"loss": 0.5572,
"step": 980
},
{
"epoch": 1.46,
"learning_rate": 1.0828556539864514e-05,
"loss": 0.5844,
"step": 981
},
{
"epoch": 1.46,
"learning_rate": 1.0818134445023452e-05,
"loss": 0.5285,
"step": 982
},
{
"epoch": 1.46,
"learning_rate": 1.0807712350182387e-05,
"loss": 0.5529,
"step": 983
},
{
"epoch": 1.46,
"learning_rate": 1.0797290255341324e-05,
"loss": 0.7165,
"step": 984
},
{
"epoch": 1.46,
"learning_rate": 1.078686816050026e-05,
"loss": 0.4933,
"step": 985
},
{
"epoch": 1.47,
"learning_rate": 1.0776446065659199e-05,
"loss": 0.5561,
"step": 986
},
{
"epoch": 1.47,
"learning_rate": 1.0766023970818135e-05,
"loss": 0.4758,
"step": 987
},
{
"epoch": 1.47,
"learning_rate": 1.0755601875977073e-05,
"loss": 0.5724,
"step": 988
},
{
"epoch": 1.47,
"learning_rate": 1.0745179781136008e-05,
"loss": 0.5707,
"step": 989
},
{
"epoch": 1.47,
"learning_rate": 1.0734757686294945e-05,
"loss": 0.5184,
"step": 990
},
{
"epoch": 1.47,
"learning_rate": 1.0724335591453883e-05,
"loss": 0.6284,
"step": 991
},
{
"epoch": 1.47,
"learning_rate": 1.071391349661282e-05,
"loss": 0.5725,
"step": 992
},
{
"epoch": 1.48,
"learning_rate": 1.0703491401771758e-05,
"loss": 0.6264,
"step": 993
},
{
"epoch": 1.48,
"learning_rate": 1.0693069306930694e-05,
"loss": 0.5356,
"step": 994
},
{
"epoch": 1.48,
"learning_rate": 1.0682647212089632e-05,
"loss": 0.707,
"step": 995
},
{
"epoch": 1.48,
"learning_rate": 1.0672225117248567e-05,
"loss": 0.5491,
"step": 996
},
{
"epoch": 1.48,
"learning_rate": 1.0661803022407504e-05,
"loss": 0.7105,
"step": 997
},
{
"epoch": 1.48,
"learning_rate": 1.065138092756644e-05,
"loss": 0.7774,
"step": 998
},
{
"epoch": 1.48,
"learning_rate": 1.0640958832725379e-05,
"loss": 0.6542,
"step": 999
},
{
"epoch": 1.49,
"learning_rate": 1.0630536737884317e-05,
"loss": 0.6497,
"step": 1000
},
{
"epoch": 1.49,
"eval_loss": 1.4143973588943481,
"eval_runtime": 0.6815,
"eval_samples_per_second": 358.039,
"eval_steps_per_second": 45.489,
"step": 1000
},
{
"epoch": 1.49,
"learning_rate": 1.0620114643043253e-05,
"loss": 0.7721,
"step": 1001
},
{
"epoch": 1.49,
"learning_rate": 1.060969254820219e-05,
"loss": 0.6448,
"step": 1002
},
{
"epoch": 1.49,
"learning_rate": 1.0599270453361125e-05,
"loss": 0.6809,
"step": 1003
},
{
"epoch": 1.49,
"learning_rate": 1.0588848358520063e-05,
"loss": 0.6446,
"step": 1004
},
{
"epoch": 1.49,
"learning_rate": 1.0578426263679e-05,
"loss": 0.6307,
"step": 1005
},
{
"epoch": 1.49,
"learning_rate": 1.0568004168837938e-05,
"loss": 0.6946,
"step": 1006
},
{
"epoch": 1.5,
"learning_rate": 1.0557582073996876e-05,
"loss": 0.4875,
"step": 1007
},
{
"epoch": 1.5,
"learning_rate": 1.0547159979155812e-05,
"loss": 0.6212,
"step": 1008
},
{
"epoch": 1.5,
"learning_rate": 1.0536737884314746e-05,
"loss": 0.7248,
"step": 1009
},
{
"epoch": 1.5,
"learning_rate": 1.0526315789473684e-05,
"loss": 0.6195,
"step": 1010
},
{
"epoch": 1.5,
"learning_rate": 1.0515893694632622e-05,
"loss": 0.6364,
"step": 1011
},
{
"epoch": 1.5,
"learning_rate": 1.0505471599791559e-05,
"loss": 0.8186,
"step": 1012
},
{
"epoch": 1.51,
"learning_rate": 1.0495049504950497e-05,
"loss": 0.5885,
"step": 1013
},
{
"epoch": 1.51,
"learning_rate": 1.0484627410109433e-05,
"loss": 0.5516,
"step": 1014
},
{
"epoch": 1.51,
"learning_rate": 1.047420531526837e-05,
"loss": 0.6075,
"step": 1015
},
{
"epoch": 1.51,
"learning_rate": 1.0463783220427305e-05,
"loss": 0.5196,
"step": 1016
},
{
"epoch": 1.51,
"learning_rate": 1.0453361125586243e-05,
"loss": 0.6308,
"step": 1017
},
{
"epoch": 1.51,
"learning_rate": 1.0442939030745181e-05,
"loss": 0.8091,
"step": 1018
},
{
"epoch": 1.51,
"learning_rate": 1.0432516935904118e-05,
"loss": 0.5811,
"step": 1019
},
{
"epoch": 1.52,
"learning_rate": 1.0422094841063056e-05,
"loss": 0.6284,
"step": 1020
},
{
"epoch": 1.52,
"learning_rate": 1.0411672746221992e-05,
"loss": 0.5792,
"step": 1021
},
{
"epoch": 1.52,
"learning_rate": 1.0401250651380928e-05,
"loss": 0.6207,
"step": 1022
},
{
"epoch": 1.52,
"learning_rate": 1.0390828556539864e-05,
"loss": 0.6106,
"step": 1023
},
{
"epoch": 1.52,
"learning_rate": 1.0380406461698802e-05,
"loss": 0.6752,
"step": 1024
},
{
"epoch": 1.52,
"learning_rate": 1.0369984366857739e-05,
"loss": 0.7184,
"step": 1025
},
{
"epoch": 1.52,
"learning_rate": 1.0359562272016677e-05,
"loss": 0.6681,
"step": 1026
},
{
"epoch": 1.53,
"learning_rate": 1.0349140177175615e-05,
"loss": 0.7036,
"step": 1027
},
{
"epoch": 1.53,
"learning_rate": 1.033871808233455e-05,
"loss": 0.7062,
"step": 1028
},
{
"epoch": 1.53,
"learning_rate": 1.0328295987493485e-05,
"loss": 0.6072,
"step": 1029
},
{
"epoch": 1.53,
"learning_rate": 1.0317873892652423e-05,
"loss": 0.58,
"step": 1030
},
{
"epoch": 1.53,
"learning_rate": 1.0307451797811361e-05,
"loss": 0.6639,
"step": 1031
},
{
"epoch": 1.53,
"learning_rate": 1.0297029702970298e-05,
"loss": 0.6224,
"step": 1032
},
{
"epoch": 1.53,
"learning_rate": 1.0286607608129236e-05,
"loss": 0.6674,
"step": 1033
},
{
"epoch": 1.54,
"learning_rate": 1.0276185513288172e-05,
"loss": 0.5734,
"step": 1034
},
{
"epoch": 1.54,
"learning_rate": 1.0265763418447108e-05,
"loss": 0.7933,
"step": 1035
},
{
"epoch": 1.54,
"learning_rate": 1.0255341323606044e-05,
"loss": 0.7328,
"step": 1036
},
{
"epoch": 1.54,
"learning_rate": 1.0244919228764982e-05,
"loss": 0.4796,
"step": 1037
},
{
"epoch": 1.54,
"learning_rate": 1.023449713392392e-05,
"loss": 0.5682,
"step": 1038
},
{
"epoch": 1.54,
"learning_rate": 1.0224075039082857e-05,
"loss": 0.6945,
"step": 1039
},
{
"epoch": 1.55,
"learning_rate": 1.0213652944241795e-05,
"loss": 0.8304,
"step": 1040
},
{
"epoch": 1.55,
"learning_rate": 1.0203230849400729e-05,
"loss": 0.5836,
"step": 1041
},
{
"epoch": 1.55,
"learning_rate": 1.0192808754559667e-05,
"loss": 0.5384,
"step": 1042
},
{
"epoch": 1.55,
"learning_rate": 1.0182386659718603e-05,
"loss": 0.7605,
"step": 1043
},
{
"epoch": 1.55,
"learning_rate": 1.0171964564877541e-05,
"loss": 0.8921,
"step": 1044
},
{
"epoch": 1.55,
"learning_rate": 1.0161542470036478e-05,
"loss": 0.5456,
"step": 1045
},
{
"epoch": 1.55,
"learning_rate": 1.0151120375195416e-05,
"loss": 0.857,
"step": 1046
},
{
"epoch": 1.56,
"learning_rate": 1.0140698280354354e-05,
"loss": 0.5074,
"step": 1047
},
{
"epoch": 1.56,
"learning_rate": 1.0130276185513288e-05,
"loss": 0.7102,
"step": 1048
},
{
"epoch": 1.56,
"learning_rate": 1.0119854090672226e-05,
"loss": 0.6623,
"step": 1049
},
{
"epoch": 1.56,
"learning_rate": 1.0109431995831162e-05,
"loss": 0.7003,
"step": 1050
},
{
"epoch": 1.56,
"learning_rate": 1.00990099009901e-05,
"loss": 0.6981,
"step": 1051
},
{
"epoch": 1.56,
"learning_rate": 1.0088587806149037e-05,
"loss": 0.6992,
"step": 1052
},
{
"epoch": 1.56,
"learning_rate": 1.0078165711307975e-05,
"loss": 0.565,
"step": 1053
},
{
"epoch": 1.57,
"learning_rate": 1.0067743616466909e-05,
"loss": 0.6609,
"step": 1054
},
{
"epoch": 1.57,
"learning_rate": 1.0057321521625847e-05,
"loss": 0.5319,
"step": 1055
},
{
"epoch": 1.57,
"learning_rate": 1.0046899426784783e-05,
"loss": 0.5287,
"step": 1056
},
{
"epoch": 1.57,
"learning_rate": 1.0036477331943721e-05,
"loss": 0.5939,
"step": 1057
},
{
"epoch": 1.57,
"learning_rate": 1.002605523710266e-05,
"loss": 0.6506,
"step": 1058
},
{
"epoch": 1.57,
"learning_rate": 1.0015633142261596e-05,
"loss": 0.4579,
"step": 1059
},
{
"epoch": 1.58,
"learning_rate": 1.0005211047420534e-05,
"loss": 0.738,
"step": 1060
},
{
"epoch": 1.58,
"learning_rate": 9.99478895257947e-06,
"loss": 0.6641,
"step": 1061
},
{
"epoch": 1.58,
"learning_rate": 9.984366857738406e-06,
"loss": 0.5838,
"step": 1062
},
{
"epoch": 1.58,
"learning_rate": 9.973944762897342e-06,
"loss": 0.6514,
"step": 1063
},
{
"epoch": 1.58,
"learning_rate": 9.96352266805628e-06,
"loss": 0.7209,
"step": 1064
},
{
"epoch": 1.58,
"learning_rate": 9.953100573215218e-06,
"loss": 0.6068,
"step": 1065
},
{
"epoch": 1.58,
"learning_rate": 9.942678478374153e-06,
"loss": 0.6643,
"step": 1066
},
{
"epoch": 1.59,
"learning_rate": 9.93225638353309e-06,
"loss": 0.6382,
"step": 1067
},
{
"epoch": 1.59,
"learning_rate": 9.921834288692029e-06,
"loss": 0.6521,
"step": 1068
},
{
"epoch": 1.59,
"learning_rate": 9.911412193850965e-06,
"loss": 0.5781,
"step": 1069
},
{
"epoch": 1.59,
"learning_rate": 9.900990099009901e-06,
"loss": 0.4597,
"step": 1070
},
{
"epoch": 1.59,
"learning_rate": 9.89056800416884e-06,
"loss": 0.6441,
"step": 1071
},
{
"epoch": 1.59,
"learning_rate": 9.880145909327776e-06,
"loss": 0.8519,
"step": 1072
},
{
"epoch": 1.59,
"learning_rate": 9.869723814486712e-06,
"loss": 0.7241,
"step": 1073
},
{
"epoch": 1.6,
"learning_rate": 9.85930171964565e-06,
"loss": 0.6976,
"step": 1074
},
{
"epoch": 1.6,
"learning_rate": 9.848879624804588e-06,
"loss": 0.5765,
"step": 1075
},
{
"epoch": 1.6,
"learning_rate": 9.838457529963524e-06,
"loss": 0.4675,
"step": 1076
},
{
"epoch": 1.6,
"learning_rate": 9.82803543512246e-06,
"loss": 0.5756,
"step": 1077
},
{
"epoch": 1.6,
"learning_rate": 9.817613340281398e-06,
"loss": 0.634,
"step": 1078
},
{
"epoch": 1.6,
"learning_rate": 9.807191245440335e-06,
"loss": 0.5635,
"step": 1079
},
{
"epoch": 1.6,
"learning_rate": 9.79676915059927e-06,
"loss": 0.6979,
"step": 1080
},
{
"epoch": 1.61,
"learning_rate": 9.786347055758209e-06,
"loss": 0.57,
"step": 1081
},
{
"epoch": 1.61,
"learning_rate": 9.775924960917145e-06,
"loss": 0.6934,
"step": 1082
},
{
"epoch": 1.61,
"learning_rate": 9.765502866076081e-06,
"loss": 0.616,
"step": 1083
},
{
"epoch": 1.61,
"learning_rate": 9.75508077123502e-06,
"loss": 0.6176,
"step": 1084
},
{
"epoch": 1.61,
"learning_rate": 9.744658676393956e-06,
"loss": 0.6425,
"step": 1085
},
{
"epoch": 1.61,
"learning_rate": 9.734236581552893e-06,
"loss": 0.6245,
"step": 1086
},
{
"epoch": 1.62,
"learning_rate": 9.72381448671183e-06,
"loss": 0.6386,
"step": 1087
},
{
"epoch": 1.62,
"learning_rate": 9.713392391870768e-06,
"loss": 0.7235,
"step": 1088
},
{
"epoch": 1.62,
"learning_rate": 9.702970297029704e-06,
"loss": 0.5517,
"step": 1089
},
{
"epoch": 1.62,
"learning_rate": 9.69254820218864e-06,
"loss": 0.7184,
"step": 1090
},
{
"epoch": 1.62,
"learning_rate": 9.682126107347578e-06,
"loss": 0.6694,
"step": 1091
},
{
"epoch": 1.62,
"learning_rate": 9.671704012506515e-06,
"loss": 0.6786,
"step": 1092
},
{
"epoch": 1.62,
"learning_rate": 9.66128191766545e-06,
"loss": 0.5875,
"step": 1093
},
{
"epoch": 1.63,
"learning_rate": 9.650859822824389e-06,
"loss": 0.6556,
"step": 1094
},
{
"epoch": 1.63,
"learning_rate": 9.640437727983325e-06,
"loss": 0.6521,
"step": 1095
},
{
"epoch": 1.63,
"learning_rate": 9.630015633142263e-06,
"loss": 0.5984,
"step": 1096
},
{
"epoch": 1.63,
"learning_rate": 9.6195935383012e-06,
"loss": 0.6923,
"step": 1097
},
{
"epoch": 1.63,
"learning_rate": 9.609171443460136e-06,
"loss": 0.6851,
"step": 1098
},
{
"epoch": 1.63,
"learning_rate": 9.598749348619073e-06,
"loss": 0.5771,
"step": 1099
},
{
"epoch": 1.63,
"learning_rate": 9.58832725377801e-06,
"loss": 0.6362,
"step": 1100
},
{
"epoch": 1.64,
"learning_rate": 9.577905158936948e-06,
"loss": 0.5773,
"step": 1101
},
{
"epoch": 1.64,
"learning_rate": 9.567483064095884e-06,
"loss": 0.7179,
"step": 1102
},
{
"epoch": 1.64,
"learning_rate": 9.55706096925482e-06,
"loss": 0.5209,
"step": 1103
},
{
"epoch": 1.64,
"learning_rate": 9.546638874413758e-06,
"loss": 0.6773,
"step": 1104
},
{
"epoch": 1.64,
"learning_rate": 9.536216779572694e-06,
"loss": 0.7015,
"step": 1105
},
{
"epoch": 1.64,
"learning_rate": 9.525794684731632e-06,
"loss": 0.6894,
"step": 1106
},
{
"epoch": 1.64,
"learning_rate": 9.515372589890569e-06,
"loss": 0.5376,
"step": 1107
},
{
"epoch": 1.65,
"learning_rate": 9.504950495049505e-06,
"loss": 0.7093,
"step": 1108
},
{
"epoch": 1.65,
"learning_rate": 9.494528400208443e-06,
"loss": 0.6872,
"step": 1109
},
{
"epoch": 1.65,
"learning_rate": 9.48410630536738e-06,
"loss": 0.6233,
"step": 1110
},
{
"epoch": 1.65,
"learning_rate": 9.473684210526315e-06,
"loss": 0.6311,
"step": 1111
},
{
"epoch": 1.65,
"learning_rate": 9.463262115685253e-06,
"loss": 0.6976,
"step": 1112
},
{
"epoch": 1.65,
"learning_rate": 9.452840020844191e-06,
"loss": 0.6252,
"step": 1113
},
{
"epoch": 1.66,
"learning_rate": 9.442417926003128e-06,
"loss": 0.6584,
"step": 1114
},
{
"epoch": 1.66,
"learning_rate": 9.431995831162064e-06,
"loss": 0.6392,
"step": 1115
},
{
"epoch": 1.66,
"learning_rate": 9.421573736321002e-06,
"loss": 0.6101,
"step": 1116
},
{
"epoch": 1.66,
"learning_rate": 9.411151641479938e-06,
"loss": 0.5382,
"step": 1117
},
{
"epoch": 1.66,
"learning_rate": 9.400729546638874e-06,
"loss": 0.7471,
"step": 1118
},
{
"epoch": 1.66,
"learning_rate": 9.390307451797812e-06,
"loss": 0.5256,
"step": 1119
},
{
"epoch": 1.66,
"learning_rate": 9.379885356956749e-06,
"loss": 0.6382,
"step": 1120
},
{
"epoch": 1.67,
"learning_rate": 9.369463262115685e-06,
"loss": 0.6343,
"step": 1121
},
{
"epoch": 1.67,
"learning_rate": 9.359041167274623e-06,
"loss": 0.5383,
"step": 1122
},
{
"epoch": 1.67,
"learning_rate": 9.348619072433561e-06,
"loss": 0.6111,
"step": 1123
},
{
"epoch": 1.67,
"learning_rate": 9.338196977592497e-06,
"loss": 0.5914,
"step": 1124
},
{
"epoch": 1.67,
"learning_rate": 9.327774882751433e-06,
"loss": 0.677,
"step": 1125
},
{
"epoch": 1.67,
"eval_loss": 1.411847710609436,
"eval_runtime": 0.6813,
"eval_samples_per_second": 358.161,
"eval_steps_per_second": 45.504,
"step": 1125
},
{
"epoch": 1.67,
"learning_rate": 9.317352787910371e-06,
"loss": 0.7064,
"step": 1126
},
{
"epoch": 1.67,
"learning_rate": 9.306930693069308e-06,
"loss": 0.5949,
"step": 1127
},
{
"epoch": 1.68,
"learning_rate": 9.296508598228244e-06,
"loss": 0.6016,
"step": 1128
},
{
"epoch": 1.68,
"learning_rate": 9.286086503387182e-06,
"loss": 0.578,
"step": 1129
},
{
"epoch": 1.68,
"learning_rate": 9.275664408546118e-06,
"loss": 0.5404,
"step": 1130
},
{
"epoch": 1.68,
"learning_rate": 9.265242313705054e-06,
"loss": 0.5496,
"step": 1131
},
{
"epoch": 1.68,
"learning_rate": 9.254820218863992e-06,
"loss": 0.4981,
"step": 1132
},
{
"epoch": 1.68,
"learning_rate": 9.24439812402293e-06,
"loss": 0.7691,
"step": 1133
},
{
"epoch": 1.68,
"learning_rate": 9.233976029181867e-06,
"loss": 0.5824,
"step": 1134
},
{
"epoch": 1.69,
"learning_rate": 9.223553934340803e-06,
"loss": 0.696,
"step": 1135
},
{
"epoch": 1.69,
"learning_rate": 9.213131839499741e-06,
"loss": 0.5786,
"step": 1136
},
{
"epoch": 1.69,
"learning_rate": 9.202709744658677e-06,
"loss": 0.7455,
"step": 1137
},
{
"epoch": 1.69,
"learning_rate": 9.192287649817613e-06,
"loss": 0.604,
"step": 1138
},
{
"epoch": 1.69,
"learning_rate": 9.181865554976551e-06,
"loss": 0.5661,
"step": 1139
},
{
"epoch": 1.69,
"learning_rate": 9.171443460135488e-06,
"loss": 0.5715,
"step": 1140
},
{
"epoch": 1.7,
"learning_rate": 9.161021365294424e-06,
"loss": 0.5487,
"step": 1141
},
{
"epoch": 1.7,
"learning_rate": 9.150599270453362e-06,
"loss": 0.6885,
"step": 1142
},
{
"epoch": 1.7,
"learning_rate": 9.1401771756123e-06,
"loss": 0.6279,
"step": 1143
},
{
"epoch": 1.7,
"learning_rate": 9.129755080771236e-06,
"loss": 0.7855,
"step": 1144
},
{
"epoch": 1.7,
"learning_rate": 9.119332985930172e-06,
"loss": 0.6336,
"step": 1145
},
{
"epoch": 1.7,
"learning_rate": 9.10891089108911e-06,
"loss": 0.8321,
"step": 1146
},
{
"epoch": 1.7,
"learning_rate": 9.098488796248047e-06,
"loss": 0.6312,
"step": 1147
},
{
"epoch": 1.71,
"learning_rate": 9.088066701406983e-06,
"loss": 0.6152,
"step": 1148
},
{
"epoch": 1.71,
"learning_rate": 9.077644606565921e-06,
"loss": 0.5374,
"step": 1149
},
{
"epoch": 1.71,
"learning_rate": 9.067222511724857e-06,
"loss": 0.7545,
"step": 1150
},
{
"epoch": 1.71,
"learning_rate": 9.056800416883793e-06,
"loss": 0.6596,
"step": 1151
},
{
"epoch": 1.71,
"learning_rate": 9.046378322042731e-06,
"loss": 0.7634,
"step": 1152
},
{
"epoch": 1.71,
"learning_rate": 9.03595622720167e-06,
"loss": 0.6529,
"step": 1153
},
{
"epoch": 1.71,
"learning_rate": 9.025534132360606e-06,
"loss": 0.7558,
"step": 1154
},
{
"epoch": 1.72,
"learning_rate": 9.015112037519542e-06,
"loss": 0.6638,
"step": 1155
},
{
"epoch": 1.72,
"learning_rate": 9.00468994267848e-06,
"loss": 0.7319,
"step": 1156
},
{
"epoch": 1.72,
"learning_rate": 8.994267847837416e-06,
"loss": 0.536,
"step": 1157
},
{
"epoch": 1.72,
"learning_rate": 8.983845752996352e-06,
"loss": 0.6132,
"step": 1158
},
{
"epoch": 1.72,
"learning_rate": 8.97342365815529e-06,
"loss": 0.4758,
"step": 1159
},
{
"epoch": 1.72,
"learning_rate": 8.963001563314227e-06,
"loss": 0.7605,
"step": 1160
},
{
"epoch": 1.73,
"learning_rate": 8.952579468473163e-06,
"loss": 0.5668,
"step": 1161
},
{
"epoch": 1.73,
"learning_rate": 8.942157373632101e-06,
"loss": 0.5375,
"step": 1162
},
{
"epoch": 1.73,
"learning_rate": 8.931735278791037e-06,
"loss": 0.5818,
"step": 1163
},
{
"epoch": 1.73,
"learning_rate": 8.921313183949975e-06,
"loss": 0.6875,
"step": 1164
},
{
"epoch": 1.73,
"learning_rate": 8.910891089108911e-06,
"loss": 0.7939,
"step": 1165
},
{
"epoch": 1.73,
"learning_rate": 8.90046899426785e-06,
"loss": 0.6524,
"step": 1166
},
{
"epoch": 1.73,
"learning_rate": 8.890046899426786e-06,
"loss": 0.6138,
"step": 1167
},
{
"epoch": 1.74,
"learning_rate": 8.879624804585722e-06,
"loss": 0.534,
"step": 1168
},
{
"epoch": 1.74,
"learning_rate": 8.86920270974466e-06,
"loss": 0.6889,
"step": 1169
},
{
"epoch": 1.74,
"learning_rate": 8.858780614903596e-06,
"loss": 0.717,
"step": 1170
},
{
"epoch": 1.74,
"learning_rate": 8.848358520062534e-06,
"loss": 0.7018,
"step": 1171
},
{
"epoch": 1.74,
"learning_rate": 8.83793642522147e-06,
"loss": 0.64,
"step": 1172
},
{
"epoch": 1.74,
"learning_rate": 8.827514330380407e-06,
"loss": 0.7527,
"step": 1173
},
{
"epoch": 1.74,
"learning_rate": 8.817092235539345e-06,
"loss": 0.6939,
"step": 1174
},
{
"epoch": 1.75,
"learning_rate": 8.80667014069828e-06,
"loss": 0.6369,
"step": 1175
},
{
"epoch": 1.75,
"learning_rate": 8.796248045857217e-06,
"loss": 0.5309,
"step": 1176
},
{
"epoch": 1.75,
"learning_rate": 8.785825951016155e-06,
"loss": 0.4973,
"step": 1177
},
{
"epoch": 1.75,
"learning_rate": 8.775403856175091e-06,
"loss": 0.5326,
"step": 1178
},
{
"epoch": 1.75,
"learning_rate": 8.76498176133403e-06,
"loss": 0.5437,
"step": 1179
},
{
"epoch": 1.75,
"learning_rate": 8.754559666492966e-06,
"loss": 0.6647,
"step": 1180
},
{
"epoch": 1.75,
"learning_rate": 8.744137571651904e-06,
"loss": 0.6631,
"step": 1181
},
{
"epoch": 1.76,
"learning_rate": 8.73371547681084e-06,
"loss": 0.5625,
"step": 1182
},
{
"epoch": 1.76,
"learning_rate": 8.723293381969776e-06,
"loss": 0.6866,
"step": 1183
},
{
"epoch": 1.76,
"learning_rate": 8.712871287128714e-06,
"loss": 0.6413,
"step": 1184
},
{
"epoch": 1.76,
"learning_rate": 8.70244919228765e-06,
"loss": 0.7603,
"step": 1185
},
{
"epoch": 1.76,
"learning_rate": 8.692027097446587e-06,
"loss": 0.6702,
"step": 1186
},
{
"epoch": 1.76,
"learning_rate": 8.681605002605525e-06,
"loss": 0.5994,
"step": 1187
},
{
"epoch": 1.77,
"learning_rate": 8.67118290776446e-06,
"loss": 0.6898,
"step": 1188
},
{
"epoch": 1.77,
"learning_rate": 8.660760812923397e-06,
"loss": 0.6075,
"step": 1189
},
{
"epoch": 1.77,
"learning_rate": 8.650338718082335e-06,
"loss": 0.6365,
"step": 1190
},
{
"epoch": 1.77,
"learning_rate": 8.639916623241273e-06,
"loss": 0.5342,
"step": 1191
},
{
"epoch": 1.77,
"learning_rate": 8.62949452840021e-06,
"loss": 0.5531,
"step": 1192
},
{
"epoch": 1.77,
"learning_rate": 8.619072433559146e-06,
"loss": 0.6621,
"step": 1193
},
{
"epoch": 1.77,
"learning_rate": 8.608650338718084e-06,
"loss": 0.5947,
"step": 1194
},
{
"epoch": 1.78,
"learning_rate": 8.59822824387702e-06,
"loss": 0.6552,
"step": 1195
},
{
"epoch": 1.78,
"learning_rate": 8.587806149035956e-06,
"loss": 0.6817,
"step": 1196
},
{
"epoch": 1.78,
"learning_rate": 8.577384054194894e-06,
"loss": 0.5532,
"step": 1197
},
{
"epoch": 1.78,
"learning_rate": 8.56696195935383e-06,
"loss": 0.5102,
"step": 1198
},
{
"epoch": 1.78,
"learning_rate": 8.556539864512767e-06,
"loss": 0.7545,
"step": 1199
},
{
"epoch": 1.78,
"learning_rate": 8.546117769671705e-06,
"loss": 0.5834,
"step": 1200
},
{
"epoch": 1.78,
"learning_rate": 8.535695674830642e-06,
"loss": 0.8146,
"step": 1201
},
{
"epoch": 1.79,
"learning_rate": 8.525273579989579e-06,
"loss": 0.5369,
"step": 1202
},
{
"epoch": 1.79,
"learning_rate": 8.514851485148515e-06,
"loss": 0.6098,
"step": 1203
},
{
"epoch": 1.79,
"learning_rate": 8.504429390307453e-06,
"loss": 0.5301,
"step": 1204
},
{
"epoch": 1.79,
"learning_rate": 8.49400729546639e-06,
"loss": 0.6017,
"step": 1205
},
{
"epoch": 1.79,
"learning_rate": 8.483585200625326e-06,
"loss": 0.5611,
"step": 1206
},
{
"epoch": 1.79,
"learning_rate": 8.473163105784263e-06,
"loss": 0.6197,
"step": 1207
},
{
"epoch": 1.79,
"learning_rate": 8.462741010943201e-06,
"loss": 0.5759,
"step": 1208
},
{
"epoch": 1.8,
"learning_rate": 8.452318916102136e-06,
"loss": 0.7369,
"step": 1209
},
{
"epoch": 1.8,
"learning_rate": 8.441896821261074e-06,
"loss": 0.7782,
"step": 1210
},
{
"epoch": 1.8,
"learning_rate": 8.431474726420012e-06,
"loss": 0.5824,
"step": 1211
},
{
"epoch": 1.8,
"learning_rate": 8.421052631578948e-06,
"loss": 0.6864,
"step": 1212
},
{
"epoch": 1.8,
"learning_rate": 8.410630536737885e-06,
"loss": 0.6121,
"step": 1213
},
{
"epoch": 1.8,
"learning_rate": 8.400208441896822e-06,
"loss": 0.639,
"step": 1214
},
{
"epoch": 1.81,
"learning_rate": 8.389786347055759e-06,
"loss": 0.505,
"step": 1215
},
{
"epoch": 1.81,
"learning_rate": 8.379364252214695e-06,
"loss": 0.7913,
"step": 1216
},
{
"epoch": 1.81,
"learning_rate": 8.368942157373633e-06,
"loss": 0.5854,
"step": 1217
},
{
"epoch": 1.81,
"learning_rate": 8.358520062532571e-06,
"loss": 0.5374,
"step": 1218
},
{
"epoch": 1.81,
"learning_rate": 8.348097967691507e-06,
"loss": 0.6356,
"step": 1219
},
{
"epoch": 1.81,
"learning_rate": 8.337675872850443e-06,
"loss": 0.6565,
"step": 1220
},
{
"epoch": 1.81,
"learning_rate": 8.327253778009381e-06,
"loss": 0.5773,
"step": 1221
},
{
"epoch": 1.82,
"learning_rate": 8.316831683168318e-06,
"loss": 0.7198,
"step": 1222
},
{
"epoch": 1.82,
"learning_rate": 8.306409588327254e-06,
"loss": 0.6541,
"step": 1223
},
{
"epoch": 1.82,
"learning_rate": 8.295987493486192e-06,
"loss": 0.7711,
"step": 1224
},
{
"epoch": 1.82,
"learning_rate": 8.285565398645128e-06,
"loss": 0.6218,
"step": 1225
},
{
"epoch": 1.82,
"learning_rate": 8.275143303804064e-06,
"loss": 0.5316,
"step": 1226
},
{
"epoch": 1.82,
"learning_rate": 8.264721208963002e-06,
"loss": 0.6984,
"step": 1227
},
{
"epoch": 1.82,
"learning_rate": 8.25429911412194e-06,
"loss": 0.5554,
"step": 1228
},
{
"epoch": 1.83,
"learning_rate": 8.243877019280877e-06,
"loss": 0.6413,
"step": 1229
},
{
"epoch": 1.83,
"learning_rate": 8.233454924439813e-06,
"loss": 0.6028,
"step": 1230
},
{
"epoch": 1.83,
"learning_rate": 8.223032829598751e-06,
"loss": 0.8506,
"step": 1231
},
{
"epoch": 1.83,
"learning_rate": 8.212610734757687e-06,
"loss": 0.6611,
"step": 1232
},
{
"epoch": 1.83,
"learning_rate": 8.202188639916623e-06,
"loss": 0.6906,
"step": 1233
},
{
"epoch": 1.83,
"learning_rate": 8.191766545075561e-06,
"loss": 0.8589,
"step": 1234
},
{
"epoch": 1.84,
"learning_rate": 8.181344450234498e-06,
"loss": 0.833,
"step": 1235
},
{
"epoch": 1.84,
"learning_rate": 8.170922355393434e-06,
"loss": 0.7199,
"step": 1236
},
{
"epoch": 1.84,
"learning_rate": 8.160500260552372e-06,
"loss": 0.6588,
"step": 1237
},
{
"epoch": 1.84,
"learning_rate": 8.150078165711308e-06,
"loss": 0.7235,
"step": 1238
},
{
"epoch": 1.84,
"learning_rate": 8.139656070870246e-06,
"loss": 0.5888,
"step": 1239
},
{
"epoch": 1.84,
"learning_rate": 8.129233976029182e-06,
"loss": 0.6261,
"step": 1240
},
{
"epoch": 1.84,
"learning_rate": 8.11881188118812e-06,
"loss": 0.6471,
"step": 1241
},
{
"epoch": 1.85,
"learning_rate": 8.108389786347057e-06,
"loss": 0.5856,
"step": 1242
},
{
"epoch": 1.85,
"learning_rate": 8.097967691505993e-06,
"loss": 0.8154,
"step": 1243
},
{
"epoch": 1.85,
"learning_rate": 8.087545596664931e-06,
"loss": 0.6434,
"step": 1244
},
{
"epoch": 1.85,
"learning_rate": 8.077123501823867e-06,
"loss": 0.8807,
"step": 1245
},
{
"epoch": 1.85,
"learning_rate": 8.066701406982803e-06,
"loss": 0.749,
"step": 1246
},
{
"epoch": 1.85,
"learning_rate": 8.056279312141741e-06,
"loss": 0.7665,
"step": 1247
},
{
"epoch": 1.85,
"learning_rate": 8.045857217300678e-06,
"loss": 0.6843,
"step": 1248
},
{
"epoch": 1.86,
"learning_rate": 8.035435122459616e-06,
"loss": 0.6921,
"step": 1249
},
{
"epoch": 1.86,
"learning_rate": 8.025013027618552e-06,
"loss": 0.5725,
"step": 1250
},
{
"epoch": 1.86,
"eval_loss": 1.4075517654418945,
"eval_runtime": 0.6804,
"eval_samples_per_second": 358.593,
"eval_steps_per_second": 45.559,
"step": 1250
},
{
"epoch": 1.86,
"learning_rate": 8.014590932777488e-06,
"loss": 0.5409,
"step": 1251
},
{
"epoch": 1.86,
"learning_rate": 8.004168837936426e-06,
"loss": 0.5595,
"step": 1252
},
{
"epoch": 1.86,
"learning_rate": 7.993746743095362e-06,
"loss": 0.5603,
"step": 1253
},
{
"epoch": 1.86,
"learning_rate": 7.9833246482543e-06,
"loss": 0.6518,
"step": 1254
},
{
"epoch": 1.86,
"learning_rate": 7.972902553413237e-06,
"loss": 0.6447,
"step": 1255
},
{
"epoch": 1.87,
"learning_rate": 7.962480458572175e-06,
"loss": 0.4989,
"step": 1256
},
{
"epoch": 1.87,
"learning_rate": 7.952058363731111e-06,
"loss": 0.7849,
"step": 1257
},
{
"epoch": 1.87,
"learning_rate": 7.941636268890047e-06,
"loss": 0.4812,
"step": 1258
},
{
"epoch": 1.87,
"learning_rate": 7.931214174048985e-06,
"loss": 0.6783,
"step": 1259
},
{
"epoch": 1.87,
"learning_rate": 7.920792079207921e-06,
"loss": 0.6995,
"step": 1260
},
{
"epoch": 1.87,
"learning_rate": 7.910369984366858e-06,
"loss": 0.698,
"step": 1261
},
{
"epoch": 1.88,
"learning_rate": 7.899947889525796e-06,
"loss": 0.5814,
"step": 1262
},
{
"epoch": 1.88,
"learning_rate": 7.889525794684732e-06,
"loss": 0.5582,
"step": 1263
},
{
"epoch": 1.88,
"learning_rate": 7.879103699843668e-06,
"loss": 0.7499,
"step": 1264
},
{
"epoch": 1.88,
"learning_rate": 7.868681605002606e-06,
"loss": 0.5714,
"step": 1265
},
{
"epoch": 1.88,
"learning_rate": 7.858259510161544e-06,
"loss": 0.5645,
"step": 1266
},
{
"epoch": 1.88,
"learning_rate": 7.84783741532048e-06,
"loss": 0.6369,
"step": 1267
},
{
"epoch": 1.88,
"learning_rate": 7.837415320479417e-06,
"loss": 0.5001,
"step": 1268
},
{
"epoch": 1.89,
"learning_rate": 7.826993225638355e-06,
"loss": 0.719,
"step": 1269
},
{
"epoch": 1.89,
"learning_rate": 7.816571130797291e-06,
"loss": 0.6336,
"step": 1270
},
{
"epoch": 1.89,
"learning_rate": 7.806149035956227e-06,
"loss": 0.5277,
"step": 1271
},
{
"epoch": 1.89,
"learning_rate": 7.795726941115165e-06,
"loss": 0.5794,
"step": 1272
},
{
"epoch": 1.89,
"learning_rate": 7.785304846274101e-06,
"loss": 0.633,
"step": 1273
},
{
"epoch": 1.89,
"learning_rate": 7.774882751433038e-06,
"loss": 0.551,
"step": 1274
},
{
"epoch": 1.89,
"learning_rate": 7.764460656591976e-06,
"loss": 0.6205,
"step": 1275
},
{
"epoch": 1.9,
"learning_rate": 7.754038561750914e-06,
"loss": 0.6605,
"step": 1276
},
{
"epoch": 1.9,
"learning_rate": 7.74361646690985e-06,
"loss": 0.6877,
"step": 1277
},
{
"epoch": 1.9,
"learning_rate": 7.733194372068786e-06,
"loss": 0.6566,
"step": 1278
},
{
"epoch": 1.9,
"learning_rate": 7.722772277227724e-06,
"loss": 0.7377,
"step": 1279
},
{
"epoch": 1.9,
"learning_rate": 7.71235018238666e-06,
"loss": 0.6225,
"step": 1280
},
{
"epoch": 1.9,
"learning_rate": 7.701928087545597e-06,
"loss": 0.7017,
"step": 1281
},
{
"epoch": 1.9,
"learning_rate": 7.691505992704535e-06,
"loss": 0.7516,
"step": 1282
},
{
"epoch": 1.91,
"learning_rate": 7.681083897863471e-06,
"loss": 0.5827,
"step": 1283
},
{
"epoch": 1.91,
"learning_rate": 7.670661803022407e-06,
"loss": 0.6481,
"step": 1284
},
{
"epoch": 1.91,
"learning_rate": 7.660239708181345e-06,
"loss": 0.6529,
"step": 1285
},
{
"epoch": 1.91,
"learning_rate": 7.649817613340283e-06,
"loss": 0.6492,
"step": 1286
},
{
"epoch": 1.91,
"learning_rate": 7.63939551849922e-06,
"loss": 0.6063,
"step": 1287
},
{
"epoch": 1.91,
"learning_rate": 7.628973423658156e-06,
"loss": 0.576,
"step": 1288
},
{
"epoch": 1.92,
"learning_rate": 7.6185513288170936e-06,
"loss": 0.8672,
"step": 1289
},
{
"epoch": 1.92,
"learning_rate": 7.608129233976029e-06,
"loss": 0.6517,
"step": 1290
},
{
"epoch": 1.92,
"learning_rate": 7.597707139134967e-06,
"loss": 0.7137,
"step": 1291
},
{
"epoch": 1.92,
"learning_rate": 7.587285044293904e-06,
"loss": 0.8719,
"step": 1292
},
{
"epoch": 1.92,
"learning_rate": 7.576862949452841e-06,
"loss": 0.6337,
"step": 1293
},
{
"epoch": 1.92,
"learning_rate": 7.5664408546117774e-06,
"loss": 0.6376,
"step": 1294
},
{
"epoch": 1.92,
"learning_rate": 7.5560187597707146e-06,
"loss": 0.7165,
"step": 1295
},
{
"epoch": 1.93,
"learning_rate": 7.545596664929652e-06,
"loss": 0.5128,
"step": 1296
},
{
"epoch": 1.93,
"learning_rate": 7.535174570088588e-06,
"loss": 0.7557,
"step": 1297
},
{
"epoch": 1.93,
"learning_rate": 7.524752475247525e-06,
"loss": 0.6188,
"step": 1298
},
{
"epoch": 1.93,
"learning_rate": 7.514330380406463e-06,
"loss": 0.6326,
"step": 1299
},
{
"epoch": 1.93,
"learning_rate": 7.5039082855653985e-06,
"loss": 0.6014,
"step": 1300
},
{
"epoch": 1.93,
"learning_rate": 7.493486190724336e-06,
"loss": 0.5037,
"step": 1301
},
{
"epoch": 1.93,
"learning_rate": 7.4830640958832735e-06,
"loss": 0.6358,
"step": 1302
},
{
"epoch": 1.94,
"learning_rate": 7.47264200104221e-06,
"loss": 0.5939,
"step": 1303
},
{
"epoch": 1.94,
"learning_rate": 7.462219906201147e-06,
"loss": 0.5287,
"step": 1304
},
{
"epoch": 1.94,
"learning_rate": 7.451797811360084e-06,
"loss": 0.8351,
"step": 1305
},
{
"epoch": 1.94,
"learning_rate": 7.441375716519021e-06,
"loss": 0.7786,
"step": 1306
},
{
"epoch": 1.94,
"learning_rate": 7.4309536216779574e-06,
"loss": 0.6495,
"step": 1307
},
{
"epoch": 1.94,
"learning_rate": 7.4205315268368945e-06,
"loss": 0.748,
"step": 1308
},
{
"epoch": 1.95,
"learning_rate": 7.4101094319958325e-06,
"loss": 0.5109,
"step": 1309
},
{
"epoch": 1.95,
"learning_rate": 7.399687337154769e-06,
"loss": 0.6619,
"step": 1310
},
{
"epoch": 1.95,
"learning_rate": 7.389265242313706e-06,
"loss": 0.6808,
"step": 1311
},
{
"epoch": 1.95,
"learning_rate": 7.378843147472643e-06,
"loss": 0.7248,
"step": 1312
},
{
"epoch": 1.95,
"learning_rate": 7.368421052631579e-06,
"loss": 0.6203,
"step": 1313
},
{
"epoch": 1.95,
"learning_rate": 7.357998957790516e-06,
"loss": 0.6776,
"step": 1314
},
{
"epoch": 1.95,
"learning_rate": 7.3475768629494535e-06,
"loss": 0.7585,
"step": 1315
},
{
"epoch": 1.96,
"learning_rate": 7.33715476810839e-06,
"loss": 0.5965,
"step": 1316
},
{
"epoch": 1.96,
"learning_rate": 7.326732673267327e-06,
"loss": 0.5494,
"step": 1317
},
{
"epoch": 1.96,
"learning_rate": 7.316310578426265e-06,
"loss": 0.5453,
"step": 1318
},
{
"epoch": 1.96,
"learning_rate": 7.305888483585202e-06,
"loss": 0.5375,
"step": 1319
},
{
"epoch": 1.96,
"learning_rate": 7.295466388744138e-06,
"loss": 0.7838,
"step": 1320
},
{
"epoch": 1.96,
"learning_rate": 7.285044293903075e-06,
"loss": 0.6702,
"step": 1321
},
{
"epoch": 1.96,
"learning_rate": 7.2746221990620125e-06,
"loss": 0.6292,
"step": 1322
},
{
"epoch": 1.97,
"learning_rate": 7.264200104220949e-06,
"loss": 0.6293,
"step": 1323
},
{
"epoch": 1.97,
"learning_rate": 7.253778009379886e-06,
"loss": 0.5935,
"step": 1324
},
{
"epoch": 1.97,
"learning_rate": 7.243355914538823e-06,
"loss": 0.6296,
"step": 1325
},
{
"epoch": 1.97,
"learning_rate": 7.232933819697759e-06,
"loss": 0.8563,
"step": 1326
},
{
"epoch": 1.97,
"learning_rate": 7.222511724856696e-06,
"loss": 0.7091,
"step": 1327
},
{
"epoch": 1.97,
"learning_rate": 7.212089630015634e-06,
"loss": 0.5249,
"step": 1328
},
{
"epoch": 1.97,
"learning_rate": 7.20166753517457e-06,
"loss": 0.6949,
"step": 1329
},
{
"epoch": 1.98,
"learning_rate": 7.191245440333508e-06,
"loss": 0.7877,
"step": 1330
},
{
"epoch": 1.98,
"learning_rate": 7.180823345492445e-06,
"loss": 0.7735,
"step": 1331
},
{
"epoch": 1.98,
"learning_rate": 7.170401250651382e-06,
"loss": 0.5916,
"step": 1332
},
{
"epoch": 1.98,
"learning_rate": 7.159979155810318e-06,
"loss": 0.7739,
"step": 1333
},
{
"epoch": 1.98,
"learning_rate": 7.149557060969255e-06,
"loss": 0.7005,
"step": 1334
},
{
"epoch": 1.98,
"learning_rate": 7.1391349661281925e-06,
"loss": 0.5461,
"step": 1335
},
{
"epoch": 1.99,
"learning_rate": 7.128712871287129e-06,
"loss": 0.6582,
"step": 1336
},
{
"epoch": 1.99,
"learning_rate": 7.118290776446066e-06,
"loss": 0.5393,
"step": 1337
},
{
"epoch": 1.99,
"learning_rate": 7.107868681605004e-06,
"loss": 0.6856,
"step": 1338
},
{
"epoch": 1.99,
"learning_rate": 7.09744658676394e-06,
"loss": 0.632,
"step": 1339
},
{
"epoch": 1.99,
"learning_rate": 7.087024491922877e-06,
"loss": 0.6302,
"step": 1340
},
{
"epoch": 1.99,
"learning_rate": 7.076602397081814e-06,
"loss": 0.5432,
"step": 1341
},
{
"epoch": 1.99,
"learning_rate": 7.066180302240751e-06,
"loss": 0.6521,
"step": 1342
},
{
"epoch": 2.0,
"learning_rate": 7.055758207399688e-06,
"loss": 0.7714,
"step": 1343
},
{
"epoch": 2.0,
"learning_rate": 7.045336112558625e-06,
"loss": 0.7093,
"step": 1344
},
{
"epoch": 2.0,
"learning_rate": 7.034914017717562e-06,
"loss": 0.4782,
"step": 1345
},
{
"epoch": 2.0,
"learning_rate": 7.024491922876498e-06,
"loss": 0.5833,
"step": 1346
},
{
"epoch": 2.0,
"learning_rate": 7.014069828035436e-06,
"loss": 0.5684,
"step": 1347
},
{
"epoch": 2.0,
"learning_rate": 7.003647733194373e-06,
"loss": 0.6659,
"step": 1348
},
{
"epoch": 2.0,
"learning_rate": 6.9932256383533096e-06,
"loss": 0.5705,
"step": 1349
},
{
"epoch": 2.01,
"learning_rate": 6.982803543512247e-06,
"loss": 0.4822,
"step": 1350
},
{
"epoch": 2.01,
"learning_rate": 6.972381448671184e-06,
"loss": 0.7815,
"step": 1351
},
{
"epoch": 2.01,
"learning_rate": 6.96195935383012e-06,
"loss": 0.6152,
"step": 1352
},
{
"epoch": 2.01,
"learning_rate": 6.951537258989057e-06,
"loss": 0.4539,
"step": 1353
},
{
"epoch": 2.01,
"learning_rate": 6.941115164147994e-06,
"loss": 0.6625,
"step": 1354
},
{
"epoch": 2.01,
"learning_rate": 6.930693069306931e-06,
"loss": 0.6365,
"step": 1355
},
{
"epoch": 2.01,
"learning_rate": 6.920270974465868e-06,
"loss": 0.5446,
"step": 1356
},
{
"epoch": 2.02,
"learning_rate": 6.909848879624806e-06,
"loss": 0.4474,
"step": 1357
},
{
"epoch": 2.02,
"learning_rate": 6.899426784783743e-06,
"loss": 0.5761,
"step": 1358
},
{
"epoch": 2.02,
"learning_rate": 6.889004689942679e-06,
"loss": 0.5729,
"step": 1359
},
{
"epoch": 2.02,
"learning_rate": 6.878582595101616e-06,
"loss": 0.5691,
"step": 1360
},
{
"epoch": 2.02,
"learning_rate": 6.868160500260553e-06,
"loss": 0.7458,
"step": 1361
},
{
"epoch": 2.02,
"learning_rate": 6.8577384054194896e-06,
"loss": 0.508,
"step": 1362
},
{
"epoch": 2.03,
"learning_rate": 6.847316310578427e-06,
"loss": 0.6225,
"step": 1363
},
{
"epoch": 2.03,
"learning_rate": 6.836894215737364e-06,
"loss": 0.8399,
"step": 1364
},
{
"epoch": 2.03,
"learning_rate": 6.8264721208963e-06,
"loss": 0.7263,
"step": 1365
},
{
"epoch": 2.03,
"learning_rate": 6.816050026055237e-06,
"loss": 0.5129,
"step": 1366
},
{
"epoch": 2.03,
"learning_rate": 6.805627931214175e-06,
"loss": 0.4625,
"step": 1367
},
{
"epoch": 2.03,
"learning_rate": 6.795205836373111e-06,
"loss": 0.5439,
"step": 1368
},
{
"epoch": 2.03,
"learning_rate": 6.7847837415320485e-06,
"loss": 0.4709,
"step": 1369
},
{
"epoch": 2.04,
"learning_rate": 6.774361646690986e-06,
"loss": 0.5698,
"step": 1370
},
{
"epoch": 2.04,
"learning_rate": 6.763939551849923e-06,
"loss": 0.7403,
"step": 1371
},
{
"epoch": 2.04,
"learning_rate": 6.753517457008859e-06,
"loss": 0.6427,
"step": 1372
},
{
"epoch": 2.04,
"learning_rate": 6.743095362167796e-06,
"loss": 0.4637,
"step": 1373
},
{
"epoch": 2.04,
"learning_rate": 6.732673267326733e-06,
"loss": 0.6643,
"step": 1374
},
{
"epoch": 2.04,
"learning_rate": 6.7222511724856695e-06,
"loss": 0.5957,
"step": 1375
},
{
"epoch": 2.04,
"eval_loss": 1.4207512140274048,
"eval_runtime": 0.6823,
"eval_samples_per_second": 357.593,
"eval_steps_per_second": 45.432,
"step": 1375
},
{
"epoch": 2.04,
"learning_rate": 6.7118290776446075e-06,
"loss": 0.7083,
"step": 1376
},
{
"epoch": 2.05,
"learning_rate": 6.701406982803545e-06,
"loss": 0.646,
"step": 1377
},
{
"epoch": 2.05,
"learning_rate": 6.690984887962481e-06,
"loss": 0.5159,
"step": 1378
},
{
"epoch": 2.05,
"learning_rate": 6.680562793121418e-06,
"loss": 0.5711,
"step": 1379
},
{
"epoch": 2.05,
"learning_rate": 6.670140698280355e-06,
"loss": 0.4267,
"step": 1380
},
{
"epoch": 2.05,
"learning_rate": 6.659718603439291e-06,
"loss": 0.6104,
"step": 1381
},
{
"epoch": 2.05,
"learning_rate": 6.6492965085982285e-06,
"loss": 0.4375,
"step": 1382
},
{
"epoch": 2.05,
"learning_rate": 6.638874413757166e-06,
"loss": 0.4105,
"step": 1383
},
{
"epoch": 2.06,
"learning_rate": 6.628452318916104e-06,
"loss": 0.5392,
"step": 1384
},
{
"epoch": 2.06,
"learning_rate": 6.618030224075039e-06,
"loss": 0.5736,
"step": 1385
},
{
"epoch": 2.06,
"learning_rate": 6.607608129233977e-06,
"loss": 0.5493,
"step": 1386
},
{
"epoch": 2.06,
"learning_rate": 6.597186034392914e-06,
"loss": 0.5316,
"step": 1387
},
{
"epoch": 2.06,
"learning_rate": 6.58676393955185e-06,
"loss": 0.692,
"step": 1388
},
{
"epoch": 2.06,
"learning_rate": 6.5763418447107875e-06,
"loss": 0.4327,
"step": 1389
},
{
"epoch": 2.07,
"learning_rate": 6.565919749869725e-06,
"loss": 0.5193,
"step": 1390
},
{
"epoch": 2.07,
"learning_rate": 6.555497655028661e-06,
"loss": 0.5096,
"step": 1391
},
{
"epoch": 2.07,
"learning_rate": 6.545075560187598e-06,
"loss": 0.4802,
"step": 1392
},
{
"epoch": 2.07,
"learning_rate": 6.534653465346535e-06,
"loss": 0.5468,
"step": 1393
},
{
"epoch": 2.07,
"learning_rate": 6.524231370505471e-06,
"loss": 0.4853,
"step": 1394
},
{
"epoch": 2.07,
"learning_rate": 6.5138092756644085e-06,
"loss": 0.55,
"step": 1395
},
{
"epoch": 2.07,
"learning_rate": 6.5033871808233465e-06,
"loss": 0.5078,
"step": 1396
},
{
"epoch": 2.08,
"learning_rate": 6.4929650859822836e-06,
"loss": 0.4978,
"step": 1397
},
{
"epoch": 2.08,
"learning_rate": 6.48254299114122e-06,
"loss": 0.5947,
"step": 1398
},
{
"epoch": 2.08,
"learning_rate": 6.472120896300157e-06,
"loss": 0.6789,
"step": 1399
},
{
"epoch": 2.08,
"learning_rate": 6.461698801459094e-06,
"loss": 0.5463,
"step": 1400
},
{
"epoch": 2.08,
"learning_rate": 6.45127670661803e-06,
"loss": 0.5934,
"step": 1401
},
{
"epoch": 2.08,
"learning_rate": 6.4408546117769675e-06,
"loss": 0.471,
"step": 1402
},
{
"epoch": 2.08,
"learning_rate": 6.430432516935905e-06,
"loss": 0.5396,
"step": 1403
},
{
"epoch": 2.09,
"learning_rate": 6.420010422094841e-06,
"loss": 0.623,
"step": 1404
},
{
"epoch": 2.09,
"learning_rate": 6.409588327253779e-06,
"loss": 0.6724,
"step": 1405
},
{
"epoch": 2.09,
"learning_rate": 6.399166232412716e-06,
"loss": 0.5963,
"step": 1406
},
{
"epoch": 2.09,
"learning_rate": 6.388744137571652e-06,
"loss": 0.5499,
"step": 1407
},
{
"epoch": 2.09,
"learning_rate": 6.378322042730589e-06,
"loss": 0.6323,
"step": 1408
},
{
"epoch": 2.09,
"learning_rate": 6.3678999478895264e-06,
"loss": 0.499,
"step": 1409
},
{
"epoch": 2.1,
"learning_rate": 6.3574778530484636e-06,
"loss": 0.4566,
"step": 1410
},
{
"epoch": 2.1,
"learning_rate": 6.3470557582074e-06,
"loss": 0.5331,
"step": 1411
},
{
"epoch": 2.1,
"learning_rate": 6.336633663366337e-06,
"loss": 0.7105,
"step": 1412
},
{
"epoch": 2.1,
"learning_rate": 6.326211568525275e-06,
"loss": 0.5394,
"step": 1413
},
{
"epoch": 2.1,
"learning_rate": 6.31578947368421e-06,
"loss": 0.5557,
"step": 1414
},
{
"epoch": 2.1,
"learning_rate": 6.305367378843148e-06,
"loss": 0.5491,
"step": 1415
},
{
"epoch": 2.1,
"learning_rate": 6.294945284002085e-06,
"loss": 0.5869,
"step": 1416
},
{
"epoch": 2.11,
"learning_rate": 6.284523189161022e-06,
"loss": 0.6956,
"step": 1417
},
{
"epoch": 2.11,
"learning_rate": 6.274101094319959e-06,
"loss": 0.5558,
"step": 1418
},
{
"epoch": 2.11,
"learning_rate": 6.263678999478896e-06,
"loss": 0.6025,
"step": 1419
},
{
"epoch": 2.11,
"learning_rate": 6.253256904637832e-06,
"loss": 0.6036,
"step": 1420
},
{
"epoch": 2.11,
"learning_rate": 6.242834809796769e-06,
"loss": 0.3936,
"step": 1421
},
{
"epoch": 2.11,
"learning_rate": 6.232412714955706e-06,
"loss": 0.5376,
"step": 1422
},
{
"epoch": 2.11,
"learning_rate": 6.221990620114644e-06,
"loss": 0.5732,
"step": 1423
},
{
"epoch": 2.12,
"learning_rate": 6.21156852527358e-06,
"loss": 0.577,
"step": 1424
},
{
"epoch": 2.12,
"learning_rate": 6.201146430432518e-06,
"loss": 0.616,
"step": 1425
},
{
"epoch": 2.12,
"learning_rate": 6.190724335591455e-06,
"loss": 0.5335,
"step": 1426
},
{
"epoch": 2.12,
"learning_rate": 6.180302240750391e-06,
"loss": 0.4471,
"step": 1427
},
{
"epoch": 2.12,
"learning_rate": 6.169880145909328e-06,
"loss": 0.6473,
"step": 1428
},
{
"epoch": 2.12,
"learning_rate": 6.159458051068265e-06,
"loss": 0.6074,
"step": 1429
},
{
"epoch": 2.12,
"learning_rate": 6.149035956227202e-06,
"loss": 0.5544,
"step": 1430
},
{
"epoch": 2.13,
"learning_rate": 6.138613861386139e-06,
"loss": 0.3948,
"step": 1431
},
{
"epoch": 2.13,
"learning_rate": 6.128191766545076e-06,
"loss": 0.589,
"step": 1432
},
{
"epoch": 2.13,
"learning_rate": 6.117769671704012e-06,
"loss": 0.4751,
"step": 1433
},
{
"epoch": 2.13,
"learning_rate": 6.10734757686295e-06,
"loss": 0.577,
"step": 1434
},
{
"epoch": 2.13,
"learning_rate": 6.096925482021887e-06,
"loss": 0.5376,
"step": 1435
},
{
"epoch": 2.13,
"learning_rate": 6.086503387180824e-06,
"loss": 0.5722,
"step": 1436
},
{
"epoch": 2.14,
"learning_rate": 6.076081292339761e-06,
"loss": 0.4824,
"step": 1437
},
{
"epoch": 2.14,
"learning_rate": 6.065659197498698e-06,
"loss": 0.4119,
"step": 1438
},
{
"epoch": 2.14,
"learning_rate": 6.055237102657635e-06,
"loss": 0.444,
"step": 1439
},
{
"epoch": 2.14,
"learning_rate": 6.044815007816571e-06,
"loss": 0.6221,
"step": 1440
},
{
"epoch": 2.14,
"learning_rate": 6.034392912975508e-06,
"loss": 0.5805,
"step": 1441
},
{
"epoch": 2.14,
"learning_rate": 6.023970818134446e-06,
"loss": 0.6408,
"step": 1442
},
{
"epoch": 2.14,
"learning_rate": 6.013548723293382e-06,
"loss": 0.5007,
"step": 1443
},
{
"epoch": 2.15,
"learning_rate": 6.00312662845232e-06,
"loss": 0.5371,
"step": 1444
},
{
"epoch": 2.15,
"learning_rate": 5.992704533611257e-06,
"loss": 0.5794,
"step": 1445
},
{
"epoch": 2.15,
"learning_rate": 5.982282438770193e-06,
"loss": 0.5111,
"step": 1446
},
{
"epoch": 2.15,
"learning_rate": 5.97186034392913e-06,
"loss": 0.5254,
"step": 1447
},
{
"epoch": 2.15,
"learning_rate": 5.961438249088067e-06,
"loss": 0.5311,
"step": 1448
},
{
"epoch": 2.15,
"learning_rate": 5.951016154247004e-06,
"loss": 0.5346,
"step": 1449
},
{
"epoch": 2.15,
"learning_rate": 5.940594059405941e-06,
"loss": 0.7025,
"step": 1450
},
{
"epoch": 2.16,
"learning_rate": 5.930171964564878e-06,
"loss": 0.6876,
"step": 1451
},
{
"epoch": 2.16,
"learning_rate": 5.919749869723816e-06,
"loss": 0.4683,
"step": 1452
},
{
"epoch": 2.16,
"learning_rate": 5.909327774882752e-06,
"loss": 0.635,
"step": 1453
},
{
"epoch": 2.16,
"learning_rate": 5.898905680041689e-06,
"loss": 0.553,
"step": 1454
},
{
"epoch": 2.16,
"learning_rate": 5.888483585200626e-06,
"loss": 0.5567,
"step": 1455
},
{
"epoch": 2.16,
"learning_rate": 5.8780614903595625e-06,
"loss": 0.615,
"step": 1456
},
{
"epoch": 2.16,
"learning_rate": 5.8676393955185e-06,
"loss": 0.4091,
"step": 1457
},
{
"epoch": 2.17,
"learning_rate": 5.857217300677437e-06,
"loss": 0.5923,
"step": 1458
},
{
"epoch": 2.17,
"learning_rate": 5.846795205836373e-06,
"loss": 0.5891,
"step": 1459
},
{
"epoch": 2.17,
"learning_rate": 5.83637311099531e-06,
"loss": 0.3863,
"step": 1460
},
{
"epoch": 2.17,
"learning_rate": 5.825951016154247e-06,
"loss": 0.5389,
"step": 1461
},
{
"epoch": 2.17,
"learning_rate": 5.815528921313185e-06,
"loss": 0.6676,
"step": 1462
},
{
"epoch": 2.17,
"learning_rate": 5.8051068264721214e-06,
"loss": 0.4971,
"step": 1463
},
{
"epoch": 2.18,
"learning_rate": 5.7946847316310586e-06,
"loss": 0.6272,
"step": 1464
},
{
"epoch": 2.18,
"learning_rate": 5.784262636789996e-06,
"loss": 0.6953,
"step": 1465
},
{
"epoch": 2.18,
"learning_rate": 5.773840541948932e-06,
"loss": 0.4932,
"step": 1466
},
{
"epoch": 2.18,
"learning_rate": 5.763418447107869e-06,
"loss": 0.5199,
"step": 1467
},
{
"epoch": 2.18,
"learning_rate": 5.752996352266806e-06,
"loss": 0.6085,
"step": 1468
},
{
"epoch": 2.18,
"learning_rate": 5.7425742574257425e-06,
"loss": 0.5431,
"step": 1469
},
{
"epoch": 2.18,
"learning_rate": 5.7321521625846796e-06,
"loss": 0.5015,
"step": 1470
},
{
"epoch": 2.19,
"learning_rate": 5.7217300677436175e-06,
"loss": 0.5943,
"step": 1471
},
{
"epoch": 2.19,
"learning_rate": 5.711307972902553e-06,
"loss": 0.532,
"step": 1472
},
{
"epoch": 2.19,
"learning_rate": 5.700885878061491e-06,
"loss": 0.6758,
"step": 1473
},
{
"epoch": 2.19,
"learning_rate": 5.690463783220428e-06,
"loss": 0.5742,
"step": 1474
},
{
"epoch": 2.19,
"learning_rate": 5.680041688379365e-06,
"loss": 0.6717,
"step": 1475
},
{
"epoch": 2.19,
"learning_rate": 5.6696195935383014e-06,
"loss": 0.5265,
"step": 1476
},
{
"epoch": 2.19,
"learning_rate": 5.6591974986972385e-06,
"loss": 0.8185,
"step": 1477
},
{
"epoch": 2.2,
"learning_rate": 5.648775403856176e-06,
"loss": 0.5426,
"step": 1478
},
{
"epoch": 2.2,
"learning_rate": 5.638353309015112e-06,
"loss": 0.5532,
"step": 1479
},
{
"epoch": 2.2,
"learning_rate": 5.627931214174049e-06,
"loss": 0.6544,
"step": 1480
},
{
"epoch": 2.2,
"learning_rate": 5.617509119332987e-06,
"loss": 0.7564,
"step": 1481
},
{
"epoch": 2.2,
"learning_rate": 5.607087024491923e-06,
"loss": 0.5349,
"step": 1482
},
{
"epoch": 2.2,
"learning_rate": 5.59666492965086e-06,
"loss": 0.6994,
"step": 1483
},
{
"epoch": 2.21,
"learning_rate": 5.5862428348097975e-06,
"loss": 0.5019,
"step": 1484
},
{
"epoch": 2.21,
"learning_rate": 5.575820739968734e-06,
"loss": 0.5182,
"step": 1485
},
{
"epoch": 2.21,
"learning_rate": 5.565398645127671e-06,
"loss": 0.5585,
"step": 1486
},
{
"epoch": 2.21,
"learning_rate": 5.554976550286608e-06,
"loss": 0.8533,
"step": 1487
},
{
"epoch": 2.21,
"learning_rate": 5.544554455445545e-06,
"loss": 0.4058,
"step": 1488
},
{
"epoch": 2.21,
"learning_rate": 5.534132360604481e-06,
"loss": 0.5624,
"step": 1489
},
{
"epoch": 2.21,
"learning_rate": 5.523710265763419e-06,
"loss": 0.4231,
"step": 1490
},
{
"epoch": 2.22,
"learning_rate": 5.5132881709223565e-06,
"loss": 0.5389,
"step": 1491
},
{
"epoch": 2.22,
"learning_rate": 5.502866076081293e-06,
"loss": 0.5637,
"step": 1492
},
{
"epoch": 2.22,
"learning_rate": 5.49244398124023e-06,
"loss": 0.552,
"step": 1493
},
{
"epoch": 2.22,
"learning_rate": 5.482021886399167e-06,
"loss": 0.557,
"step": 1494
},
{
"epoch": 2.22,
"learning_rate": 5.471599791558103e-06,
"loss": 0.5708,
"step": 1495
},
{
"epoch": 2.22,
"learning_rate": 5.46117769671704e-06,
"loss": 0.4975,
"step": 1496
},
{
"epoch": 2.22,
"learning_rate": 5.4507556018759775e-06,
"loss": 0.4509,
"step": 1497
},
{
"epoch": 2.23,
"learning_rate": 5.440333507034914e-06,
"loss": 0.8597,
"step": 1498
},
{
"epoch": 2.23,
"learning_rate": 5.429911412193851e-06,
"loss": 0.4297,
"step": 1499
},
{
"epoch": 2.23,
"learning_rate": 5.419489317352789e-06,
"loss": 0.5614,
"step": 1500
},
{
"epoch": 2.23,
"eval_loss": 1.4297773838043213,
"eval_runtime": 0.6803,
"eval_samples_per_second": 358.648,
"eval_steps_per_second": 45.566,
"step": 1500
},
{
"epoch": 2.23,
"learning_rate": 5.409067222511726e-06,
"loss": 0.5314,
"step": 1501
},
{
"epoch": 2.23,
"learning_rate": 5.398645127670662e-06,
"loss": 0.5238,
"step": 1502
},
{
"epoch": 2.23,
"learning_rate": 5.388223032829599e-06,
"loss": 0.5741,
"step": 1503
},
{
"epoch": 2.23,
"learning_rate": 5.3778009379885365e-06,
"loss": 0.6223,
"step": 1504
},
{
"epoch": 2.24,
"learning_rate": 5.367378843147473e-06,
"loss": 0.5331,
"step": 1505
},
{
"epoch": 2.24,
"learning_rate": 5.35695674830641e-06,
"loss": 0.5776,
"step": 1506
},
{
"epoch": 2.24,
"learning_rate": 5.346534653465347e-06,
"loss": 0.6081,
"step": 1507
},
{
"epoch": 2.24,
"learning_rate": 5.336112558624283e-06,
"loss": 0.6222,
"step": 1508
},
{
"epoch": 2.24,
"learning_rate": 5.32569046378322e-06,
"loss": 0.5129,
"step": 1509
},
{
"epoch": 2.24,
"learning_rate": 5.315268368942158e-06,
"loss": 0.6309,
"step": 1510
},
{
"epoch": 2.25,
"learning_rate": 5.304846274101095e-06,
"loss": 0.7283,
"step": 1511
},
{
"epoch": 2.25,
"learning_rate": 5.294424179260032e-06,
"loss": 0.4695,
"step": 1512
},
{
"epoch": 2.25,
"learning_rate": 5.284002084418969e-06,
"loss": 0.5256,
"step": 1513
},
{
"epoch": 2.25,
"learning_rate": 5.273579989577906e-06,
"loss": 0.6412,
"step": 1514
},
{
"epoch": 2.25,
"learning_rate": 5.263157894736842e-06,
"loss": 0.5908,
"step": 1515
},
{
"epoch": 2.25,
"learning_rate": 5.252735799895779e-06,
"loss": 0.6038,
"step": 1516
},
{
"epoch": 2.25,
"learning_rate": 5.2423137050547165e-06,
"loss": 0.5952,
"step": 1517
},
{
"epoch": 2.26,
"learning_rate": 5.231891610213653e-06,
"loss": 0.564,
"step": 1518
},
{
"epoch": 2.26,
"learning_rate": 5.221469515372591e-06,
"loss": 0.6033,
"step": 1519
},
{
"epoch": 2.26,
"learning_rate": 5.211047420531528e-06,
"loss": 0.5444,
"step": 1520
},
{
"epoch": 2.26,
"learning_rate": 5.200625325690464e-06,
"loss": 0.6867,
"step": 1521
},
{
"epoch": 2.26,
"learning_rate": 5.190203230849401e-06,
"loss": 0.5776,
"step": 1522
},
{
"epoch": 2.26,
"learning_rate": 5.179781136008338e-06,
"loss": 0.3986,
"step": 1523
},
{
"epoch": 2.26,
"learning_rate": 5.169359041167275e-06,
"loss": 0.6939,
"step": 1524
},
{
"epoch": 2.27,
"learning_rate": 5.158936946326212e-06,
"loss": 0.6302,
"step": 1525
},
{
"epoch": 2.27,
"learning_rate": 5.148514851485149e-06,
"loss": 0.5259,
"step": 1526
},
{
"epoch": 2.27,
"learning_rate": 5.138092756644086e-06,
"loss": 0.6822,
"step": 1527
},
{
"epoch": 2.27,
"learning_rate": 5.127670661803022e-06,
"loss": 0.5968,
"step": 1528
},
{
"epoch": 2.27,
"learning_rate": 5.11724856696196e-06,
"loss": 0.5363,
"step": 1529
},
{
"epoch": 2.27,
"learning_rate": 5.106826472120897e-06,
"loss": 0.643,
"step": 1530
},
{
"epoch": 2.27,
"learning_rate": 5.0964043772798336e-06,
"loss": 0.5424,
"step": 1531
},
{
"epoch": 2.28,
"learning_rate": 5.085982282438771e-06,
"loss": 0.4609,
"step": 1532
},
{
"epoch": 2.28,
"learning_rate": 5.075560187597708e-06,
"loss": 0.4353,
"step": 1533
},
{
"epoch": 2.28,
"learning_rate": 5.065138092756644e-06,
"loss": 0.5022,
"step": 1534
},
{
"epoch": 2.28,
"learning_rate": 5.054715997915581e-06,
"loss": 0.5313,
"step": 1535
},
{
"epoch": 2.28,
"learning_rate": 5.044293903074518e-06,
"loss": 0.742,
"step": 1536
},
{
"epoch": 2.28,
"learning_rate": 5.0338718082334546e-06,
"loss": 0.6679,
"step": 1537
},
{
"epoch": 2.29,
"learning_rate": 5.023449713392392e-06,
"loss": 0.6202,
"step": 1538
},
{
"epoch": 2.29,
"learning_rate": 5.01302761855133e-06,
"loss": 0.6376,
"step": 1539
},
{
"epoch": 2.29,
"learning_rate": 5.002605523710267e-06,
"loss": 0.6088,
"step": 1540
},
{
"epoch": 2.29,
"learning_rate": 4.992183428869203e-06,
"loss": 0.6197,
"step": 1541
},
{
"epoch": 2.29,
"learning_rate": 4.98176133402814e-06,
"loss": 0.4952,
"step": 1542
},
{
"epoch": 2.29,
"learning_rate": 4.971339239187076e-06,
"loss": 0.5653,
"step": 1543
},
{
"epoch": 2.29,
"learning_rate": 4.960917144346014e-06,
"loss": 0.6625,
"step": 1544
},
{
"epoch": 2.3,
"learning_rate": 4.950495049504951e-06,
"loss": 0.5563,
"step": 1545
},
{
"epoch": 2.3,
"learning_rate": 4.940072954663888e-06,
"loss": 0.4598,
"step": 1546
},
{
"epoch": 2.3,
"learning_rate": 4.929650859822825e-06,
"loss": 0.4758,
"step": 1547
},
{
"epoch": 2.3,
"learning_rate": 4.919228764981762e-06,
"loss": 0.5755,
"step": 1548
},
{
"epoch": 2.3,
"learning_rate": 4.908806670140699e-06,
"loss": 0.5821,
"step": 1549
},
{
"epoch": 2.3,
"learning_rate": 4.898384575299635e-06,
"loss": 0.5302,
"step": 1550
},
{
"epoch": 2.3,
"learning_rate": 4.8879624804585725e-06,
"loss": 0.409,
"step": 1551
},
{
"epoch": 2.31,
"learning_rate": 4.87754038561751e-06,
"loss": 0.5535,
"step": 1552
},
{
"epoch": 2.31,
"learning_rate": 4.867118290776447e-06,
"loss": 0.5381,
"step": 1553
},
{
"epoch": 2.31,
"learning_rate": 4.856696195935384e-06,
"loss": 0.4693,
"step": 1554
},
{
"epoch": 2.31,
"learning_rate": 4.84627410109432e-06,
"loss": 0.5233,
"step": 1555
},
{
"epoch": 2.31,
"learning_rate": 4.835852006253257e-06,
"loss": 0.4853,
"step": 1556
},
{
"epoch": 2.31,
"learning_rate": 4.825429911412194e-06,
"loss": 0.6049,
"step": 1557
},
{
"epoch": 2.32,
"learning_rate": 4.8150078165711315e-06,
"loss": 0.5033,
"step": 1558
},
{
"epoch": 2.32,
"learning_rate": 4.804585721730068e-06,
"loss": 0.4888,
"step": 1559
},
{
"epoch": 2.32,
"learning_rate": 4.794163626889005e-06,
"loss": 0.5139,
"step": 1560
},
{
"epoch": 2.32,
"learning_rate": 4.783741532047942e-06,
"loss": 0.5208,
"step": 1561
},
{
"epoch": 2.32,
"learning_rate": 4.773319437206879e-06,
"loss": 0.489,
"step": 1562
},
{
"epoch": 2.32,
"learning_rate": 4.762897342365816e-06,
"loss": 0.6092,
"step": 1563
},
{
"epoch": 2.32,
"learning_rate": 4.7524752475247525e-06,
"loss": 0.5177,
"step": 1564
},
{
"epoch": 2.33,
"learning_rate": 4.74205315268369e-06,
"loss": 0.5636,
"step": 1565
},
{
"epoch": 2.33,
"learning_rate": 4.731631057842627e-06,
"loss": 0.4413,
"step": 1566
},
{
"epoch": 2.33,
"learning_rate": 4.721208963001564e-06,
"loss": 0.5452,
"step": 1567
},
{
"epoch": 2.33,
"learning_rate": 4.710786868160501e-06,
"loss": 0.4996,
"step": 1568
},
{
"epoch": 2.33,
"learning_rate": 4.700364773319437e-06,
"loss": 0.5318,
"step": 1569
},
{
"epoch": 2.33,
"learning_rate": 4.689942678478374e-06,
"loss": 0.62,
"step": 1570
},
{
"epoch": 2.33,
"learning_rate": 4.6795205836373115e-06,
"loss": 0.5734,
"step": 1571
},
{
"epoch": 2.34,
"learning_rate": 4.669098488796249e-06,
"loss": 0.5812,
"step": 1572
},
{
"epoch": 2.34,
"learning_rate": 4.658676393955186e-06,
"loss": 0.4816,
"step": 1573
},
{
"epoch": 2.34,
"learning_rate": 4.648254299114122e-06,
"loss": 0.6509,
"step": 1574
},
{
"epoch": 2.34,
"learning_rate": 4.637832204273059e-06,
"loss": 0.468,
"step": 1575
},
{
"epoch": 2.34,
"learning_rate": 4.627410109431996e-06,
"loss": 0.5422,
"step": 1576
},
{
"epoch": 2.34,
"learning_rate": 4.616988014590933e-06,
"loss": 0.618,
"step": 1577
},
{
"epoch": 2.34,
"learning_rate": 4.6065659197498704e-06,
"loss": 0.4425,
"step": 1578
},
{
"epoch": 2.35,
"learning_rate": 4.596143824908807e-06,
"loss": 0.6268,
"step": 1579
},
{
"epoch": 2.35,
"learning_rate": 4.585721730067744e-06,
"loss": 0.4941,
"step": 1580
},
{
"epoch": 2.35,
"learning_rate": 4.575299635226681e-06,
"loss": 0.6144,
"step": 1581
},
{
"epoch": 2.35,
"learning_rate": 4.564877540385618e-06,
"loss": 0.533,
"step": 1582
},
{
"epoch": 2.35,
"learning_rate": 4.554455445544555e-06,
"loss": 0.5668,
"step": 1583
},
{
"epoch": 2.35,
"learning_rate": 4.5440333507034915e-06,
"loss": 0.6712,
"step": 1584
},
{
"epoch": 2.36,
"learning_rate": 4.5336112558624286e-06,
"loss": 0.5805,
"step": 1585
},
{
"epoch": 2.36,
"learning_rate": 4.523189161021366e-06,
"loss": 0.4658,
"step": 1586
},
{
"epoch": 2.36,
"learning_rate": 4.512767066180303e-06,
"loss": 0.606,
"step": 1587
},
{
"epoch": 2.36,
"learning_rate": 4.50234497133924e-06,
"loss": 0.6212,
"step": 1588
},
{
"epoch": 2.36,
"learning_rate": 4.491922876498176e-06,
"loss": 0.4007,
"step": 1589
},
{
"epoch": 2.36,
"learning_rate": 4.481500781657113e-06,
"loss": 0.5201,
"step": 1590
},
{
"epoch": 2.36,
"learning_rate": 4.4710786868160504e-06,
"loss": 0.4539,
"step": 1591
},
{
"epoch": 2.37,
"learning_rate": 4.4606565919749875e-06,
"loss": 0.5943,
"step": 1592
},
{
"epoch": 2.37,
"learning_rate": 4.450234497133925e-06,
"loss": 0.5188,
"step": 1593
},
{
"epoch": 2.37,
"learning_rate": 4.439812402292861e-06,
"loss": 0.6455,
"step": 1594
},
{
"epoch": 2.37,
"learning_rate": 4.429390307451798e-06,
"loss": 0.4858,
"step": 1595
},
{
"epoch": 2.37,
"learning_rate": 4.418968212610735e-06,
"loss": 0.613,
"step": 1596
},
{
"epoch": 2.37,
"learning_rate": 4.408546117769672e-06,
"loss": 0.4338,
"step": 1597
},
{
"epoch": 2.37,
"learning_rate": 4.3981240229286085e-06,
"loss": 0.5126,
"step": 1598
},
{
"epoch": 2.38,
"learning_rate": 4.387701928087546e-06,
"loss": 0.6405,
"step": 1599
},
{
"epoch": 2.38,
"learning_rate": 4.377279833246483e-06,
"loss": 0.5013,
"step": 1600
},
{
"epoch": 2.38,
"learning_rate": 4.36685773840542e-06,
"loss": 0.6717,
"step": 1601
},
{
"epoch": 2.38,
"learning_rate": 4.356435643564357e-06,
"loss": 0.5712,
"step": 1602
},
{
"epoch": 2.38,
"learning_rate": 4.346013548723293e-06,
"loss": 0.7613,
"step": 1603
},
{
"epoch": 2.38,
"learning_rate": 4.33559145388223e-06,
"loss": 0.588,
"step": 1604
},
{
"epoch": 2.38,
"learning_rate": 4.3251693590411675e-06,
"loss": 0.6183,
"step": 1605
},
{
"epoch": 2.39,
"learning_rate": 4.314747264200105e-06,
"loss": 0.4745,
"step": 1606
},
{
"epoch": 2.39,
"learning_rate": 4.304325169359042e-06,
"loss": 0.4361,
"step": 1607
},
{
"epoch": 2.39,
"learning_rate": 4.293903074517978e-06,
"loss": 0.4841,
"step": 1608
},
{
"epoch": 2.39,
"learning_rate": 4.283480979676915e-06,
"loss": 0.5249,
"step": 1609
},
{
"epoch": 2.39,
"learning_rate": 4.273058884835852e-06,
"loss": 0.7436,
"step": 1610
},
{
"epoch": 2.39,
"learning_rate": 4.262636789994789e-06,
"loss": 0.5277,
"step": 1611
},
{
"epoch": 2.4,
"learning_rate": 4.2522146951537265e-06,
"loss": 0.3535,
"step": 1612
},
{
"epoch": 2.4,
"learning_rate": 4.241792600312663e-06,
"loss": 0.655,
"step": 1613
},
{
"epoch": 2.4,
"learning_rate": 4.231370505471601e-06,
"loss": 0.5238,
"step": 1614
},
{
"epoch": 2.4,
"learning_rate": 4.220948410630537e-06,
"loss": 0.5948,
"step": 1615
},
{
"epoch": 2.4,
"learning_rate": 4.210526315789474e-06,
"loss": 0.6959,
"step": 1616
},
{
"epoch": 2.4,
"learning_rate": 4.200104220948411e-06,
"loss": 0.5273,
"step": 1617
},
{
"epoch": 2.4,
"learning_rate": 4.1896821261073475e-06,
"loss": 0.6697,
"step": 1618
},
{
"epoch": 2.41,
"learning_rate": 4.1792600312662855e-06,
"loss": 0.503,
"step": 1619
},
{
"epoch": 2.41,
"learning_rate": 4.168837936425222e-06,
"loss": 0.5863,
"step": 1620
},
{
"epoch": 2.41,
"learning_rate": 4.158415841584159e-06,
"loss": 0.4961,
"step": 1621
},
{
"epoch": 2.41,
"learning_rate": 4.147993746743096e-06,
"loss": 0.5255,
"step": 1622
},
{
"epoch": 2.41,
"learning_rate": 4.137571651902032e-06,
"loss": 0.4837,
"step": 1623
},
{
"epoch": 2.41,
"learning_rate": 4.12714955706097e-06,
"loss": 0.5621,
"step": 1624
},
{
"epoch": 2.41,
"learning_rate": 4.1167274622199065e-06,
"loss": 0.5075,
"step": 1625
},
{
"epoch": 2.41,
"eval_loss": 1.4323381185531616,
"eval_runtime": 0.6837,
"eval_samples_per_second": 356.863,
"eval_steps_per_second": 45.339,
"step": 1625
},
{
"epoch": 2.42,
"learning_rate": 4.106305367378844e-06,
"loss": 0.5151,
"step": 1626
},
{
"epoch": 2.42,
"learning_rate": 4.095883272537781e-06,
"loss": 0.5405,
"step": 1627
},
{
"epoch": 2.42,
"learning_rate": 4.085461177696717e-06,
"loss": 0.5789,
"step": 1628
},
{
"epoch": 2.42,
"learning_rate": 4.075039082855654e-06,
"loss": 0.475,
"step": 1629
},
{
"epoch": 2.42,
"learning_rate": 4.064616988014591e-06,
"loss": 0.4902,
"step": 1630
},
{
"epoch": 2.42,
"learning_rate": 4.054194893173528e-06,
"loss": 0.4199,
"step": 1631
},
{
"epoch": 2.42,
"learning_rate": 4.0437727983324655e-06,
"loss": 0.7661,
"step": 1632
},
{
"epoch": 2.43,
"learning_rate": 4.033350703491402e-06,
"loss": 0.5535,
"step": 1633
},
{
"epoch": 2.43,
"learning_rate": 4.022928608650339e-06,
"loss": 0.4622,
"step": 1634
},
{
"epoch": 2.43,
"learning_rate": 4.012506513809276e-06,
"loss": 0.5973,
"step": 1635
},
{
"epoch": 2.43,
"learning_rate": 4.002084418968213e-06,
"loss": 0.6755,
"step": 1636
},
{
"epoch": 2.43,
"learning_rate": 3.99166232412715e-06,
"loss": 0.6185,
"step": 1637
},
{
"epoch": 2.43,
"learning_rate": 3.981240229286087e-06,
"loss": 0.6135,
"step": 1638
},
{
"epoch": 2.44,
"learning_rate": 3.970818134445024e-06,
"loss": 0.5178,
"step": 1639
},
{
"epoch": 2.44,
"learning_rate": 3.960396039603961e-06,
"loss": 0.6091,
"step": 1640
},
{
"epoch": 2.44,
"learning_rate": 3.949973944762898e-06,
"loss": 0.7047,
"step": 1641
},
{
"epoch": 2.44,
"learning_rate": 3.939551849921834e-06,
"loss": 0.5921,
"step": 1642
},
{
"epoch": 2.44,
"learning_rate": 3.929129755080772e-06,
"loss": 0.6276,
"step": 1643
},
{
"epoch": 2.44,
"learning_rate": 3.918707660239708e-06,
"loss": 0.6498,
"step": 1644
},
{
"epoch": 2.44,
"learning_rate": 3.9082855653986454e-06,
"loss": 0.3791,
"step": 1645
},
{
"epoch": 2.45,
"learning_rate": 3.8978634705575826e-06,
"loss": 0.4615,
"step": 1646
},
{
"epoch": 2.45,
"learning_rate": 3.887441375716519e-06,
"loss": 0.7022,
"step": 1647
},
{
"epoch": 2.45,
"learning_rate": 3.877019280875457e-06,
"loss": 0.5022,
"step": 1648
},
{
"epoch": 2.45,
"learning_rate": 3.866597186034393e-06,
"loss": 0.5307,
"step": 1649
},
{
"epoch": 2.45,
"learning_rate": 3.85617509119333e-06,
"loss": 0.4806,
"step": 1650
},
{
"epoch": 2.45,
"learning_rate": 3.845752996352267e-06,
"loss": 0.4631,
"step": 1651
},
{
"epoch": 2.45,
"learning_rate": 3.8353309015112036e-06,
"loss": 0.6401,
"step": 1652
},
{
"epoch": 2.46,
"learning_rate": 3.8249088066701415e-06,
"loss": 0.5456,
"step": 1653
},
{
"epoch": 2.46,
"learning_rate": 3.814486711829078e-06,
"loss": 0.6043,
"step": 1654
},
{
"epoch": 2.46,
"learning_rate": 3.8040646169880145e-06,
"loss": 0.581,
"step": 1655
},
{
"epoch": 2.46,
"learning_rate": 3.793642522146952e-06,
"loss": 0.4814,
"step": 1656
},
{
"epoch": 2.46,
"learning_rate": 3.7832204273058887e-06,
"loss": 0.5056,
"step": 1657
},
{
"epoch": 2.46,
"learning_rate": 3.772798332464826e-06,
"loss": 0.6425,
"step": 1658
},
{
"epoch": 2.47,
"learning_rate": 3.7623762376237625e-06,
"loss": 0.4627,
"step": 1659
},
{
"epoch": 2.47,
"learning_rate": 3.7519541427826992e-06,
"loss": 0.4298,
"step": 1660
},
{
"epoch": 2.47,
"learning_rate": 3.7415320479416368e-06,
"loss": 0.4714,
"step": 1661
},
{
"epoch": 2.47,
"learning_rate": 3.7311099531005735e-06,
"loss": 0.6986,
"step": 1662
},
{
"epoch": 2.47,
"learning_rate": 3.7206878582595106e-06,
"loss": 0.568,
"step": 1663
},
{
"epoch": 2.47,
"learning_rate": 3.7102657634184473e-06,
"loss": 0.6797,
"step": 1664
},
{
"epoch": 2.47,
"learning_rate": 3.6998436685773844e-06,
"loss": 0.5133,
"step": 1665
},
{
"epoch": 2.48,
"learning_rate": 3.6894215737363215e-06,
"loss": 0.5704,
"step": 1666
},
{
"epoch": 2.48,
"learning_rate": 3.678999478895258e-06,
"loss": 0.6097,
"step": 1667
},
{
"epoch": 2.48,
"learning_rate": 3.668577384054195e-06,
"loss": 0.5462,
"step": 1668
},
{
"epoch": 2.48,
"learning_rate": 3.6581552892131324e-06,
"loss": 0.5924,
"step": 1669
},
{
"epoch": 2.48,
"learning_rate": 3.647733194372069e-06,
"loss": 0.5578,
"step": 1670
},
{
"epoch": 2.48,
"learning_rate": 3.6373110995310062e-06,
"loss": 0.6586,
"step": 1671
},
{
"epoch": 2.48,
"learning_rate": 3.626889004689943e-06,
"loss": 0.5688,
"step": 1672
},
{
"epoch": 2.49,
"learning_rate": 3.6164669098488796e-06,
"loss": 0.4522,
"step": 1673
},
{
"epoch": 2.49,
"learning_rate": 3.606044815007817e-06,
"loss": 0.6976,
"step": 1674
},
{
"epoch": 2.49,
"learning_rate": 3.595622720166754e-06,
"loss": 0.3733,
"step": 1675
},
{
"epoch": 2.49,
"learning_rate": 3.585200625325691e-06,
"loss": 0.5843,
"step": 1676
},
{
"epoch": 2.49,
"learning_rate": 3.5747785304846277e-06,
"loss": 0.5925,
"step": 1677
},
{
"epoch": 2.49,
"learning_rate": 3.5643564356435644e-06,
"loss": 0.4837,
"step": 1678
},
{
"epoch": 2.49,
"learning_rate": 3.553934340802502e-06,
"loss": 0.4926,
"step": 1679
},
{
"epoch": 2.5,
"learning_rate": 3.5435122459614386e-06,
"loss": 0.4393,
"step": 1680
},
{
"epoch": 2.5,
"learning_rate": 3.5330901511203753e-06,
"loss": 0.6351,
"step": 1681
},
{
"epoch": 2.5,
"learning_rate": 3.5226680562793124e-06,
"loss": 0.6526,
"step": 1682
},
{
"epoch": 2.5,
"learning_rate": 3.512245961438249e-06,
"loss": 0.7369,
"step": 1683
},
{
"epoch": 2.5,
"learning_rate": 3.5018238665971867e-06,
"loss": 0.5773,
"step": 1684
},
{
"epoch": 2.5,
"learning_rate": 3.4914017717561233e-06,
"loss": 0.7258,
"step": 1685
},
{
"epoch": 2.51,
"learning_rate": 3.48097967691506e-06,
"loss": 0.6264,
"step": 1686
},
{
"epoch": 2.51,
"learning_rate": 3.470557582073997e-06,
"loss": 0.627,
"step": 1687
},
{
"epoch": 2.51,
"learning_rate": 3.460135487232934e-06,
"loss": 0.4603,
"step": 1688
},
{
"epoch": 2.51,
"learning_rate": 3.4497133923918714e-06,
"loss": 0.571,
"step": 1689
},
{
"epoch": 2.51,
"learning_rate": 3.439291297550808e-06,
"loss": 0.5288,
"step": 1690
},
{
"epoch": 2.51,
"learning_rate": 3.4288692027097448e-06,
"loss": 0.5435,
"step": 1691
},
{
"epoch": 2.51,
"learning_rate": 3.418447107868682e-06,
"loss": 0.6104,
"step": 1692
},
{
"epoch": 2.52,
"learning_rate": 3.4080250130276186e-06,
"loss": 0.5522,
"step": 1693
},
{
"epoch": 2.52,
"learning_rate": 3.3976029181865557e-06,
"loss": 0.5264,
"step": 1694
},
{
"epoch": 2.52,
"learning_rate": 3.387180823345493e-06,
"loss": 0.7212,
"step": 1695
},
{
"epoch": 2.52,
"learning_rate": 3.3767587285044295e-06,
"loss": 0.5408,
"step": 1696
},
{
"epoch": 2.52,
"learning_rate": 3.3663366336633666e-06,
"loss": 0.5482,
"step": 1697
},
{
"epoch": 2.52,
"learning_rate": 3.3559145388223038e-06,
"loss": 0.4867,
"step": 1698
},
{
"epoch": 2.52,
"learning_rate": 3.3454924439812404e-06,
"loss": 0.6006,
"step": 1699
},
{
"epoch": 2.53,
"learning_rate": 3.3350703491401776e-06,
"loss": 0.6798,
"step": 1700
},
{
"epoch": 2.53,
"learning_rate": 3.3246482542991143e-06,
"loss": 0.4708,
"step": 1701
},
{
"epoch": 2.53,
"learning_rate": 3.314226159458052e-06,
"loss": 0.759,
"step": 1702
},
{
"epoch": 2.53,
"learning_rate": 3.3038040646169885e-06,
"loss": 0.436,
"step": 1703
},
{
"epoch": 2.53,
"learning_rate": 3.293381969775925e-06,
"loss": 0.6385,
"step": 1704
},
{
"epoch": 2.53,
"learning_rate": 3.2829598749348623e-06,
"loss": 0.6309,
"step": 1705
},
{
"epoch": 2.53,
"learning_rate": 3.272537780093799e-06,
"loss": 0.6622,
"step": 1706
},
{
"epoch": 2.54,
"learning_rate": 3.2621156852527357e-06,
"loss": 0.5741,
"step": 1707
},
{
"epoch": 2.54,
"learning_rate": 3.2516935904116732e-06,
"loss": 0.528,
"step": 1708
},
{
"epoch": 2.54,
"learning_rate": 3.24127149557061e-06,
"loss": 0.5451,
"step": 1709
},
{
"epoch": 2.54,
"learning_rate": 3.230849400729547e-06,
"loss": 0.4386,
"step": 1710
},
{
"epoch": 2.54,
"learning_rate": 3.2204273058884837e-06,
"loss": 0.4772,
"step": 1711
},
{
"epoch": 2.54,
"learning_rate": 3.2100052110474204e-06,
"loss": 0.5936,
"step": 1712
},
{
"epoch": 2.55,
"learning_rate": 3.199583116206358e-06,
"loss": 0.5729,
"step": 1713
},
{
"epoch": 2.55,
"learning_rate": 3.1891610213652947e-06,
"loss": 0.5988,
"step": 1714
},
{
"epoch": 2.55,
"learning_rate": 3.1787389265242318e-06,
"loss": 0.5455,
"step": 1715
},
{
"epoch": 2.55,
"learning_rate": 3.1683168316831685e-06,
"loss": 0.6271,
"step": 1716
},
{
"epoch": 2.55,
"learning_rate": 3.157894736842105e-06,
"loss": 0.5517,
"step": 1717
},
{
"epoch": 2.55,
"learning_rate": 3.1474726420010427e-06,
"loss": 0.5897,
"step": 1718
},
{
"epoch": 2.55,
"learning_rate": 3.1370505471599794e-06,
"loss": 0.6368,
"step": 1719
},
{
"epoch": 2.56,
"learning_rate": 3.126628452318916e-06,
"loss": 0.4669,
"step": 1720
},
{
"epoch": 2.56,
"learning_rate": 3.116206357477853e-06,
"loss": 0.6623,
"step": 1721
},
{
"epoch": 2.56,
"learning_rate": 3.10578426263679e-06,
"loss": 0.5739,
"step": 1722
},
{
"epoch": 2.56,
"learning_rate": 3.0953621677957274e-06,
"loss": 0.5866,
"step": 1723
},
{
"epoch": 2.56,
"learning_rate": 3.084940072954664e-06,
"loss": 0.4443,
"step": 1724
},
{
"epoch": 2.56,
"learning_rate": 3.074517978113601e-06,
"loss": 0.8309,
"step": 1725
},
{
"epoch": 2.56,
"learning_rate": 3.064095883272538e-06,
"loss": 0.5985,
"step": 1726
},
{
"epoch": 2.57,
"learning_rate": 3.053673788431475e-06,
"loss": 0.5278,
"step": 1727
},
{
"epoch": 2.57,
"learning_rate": 3.043251693590412e-06,
"loss": 0.5418,
"step": 1728
},
{
"epoch": 2.57,
"learning_rate": 3.032829598749349e-06,
"loss": 0.5745,
"step": 1729
},
{
"epoch": 2.57,
"learning_rate": 3.0224075039082856e-06,
"loss": 0.6004,
"step": 1730
},
{
"epoch": 2.57,
"learning_rate": 3.011985409067223e-06,
"loss": 0.6654,
"step": 1731
},
{
"epoch": 2.57,
"learning_rate": 3.00156331422616e-06,
"loss": 0.6163,
"step": 1732
},
{
"epoch": 2.58,
"learning_rate": 2.9911412193850965e-06,
"loss": 0.5957,
"step": 1733
},
{
"epoch": 2.58,
"learning_rate": 2.9807191245440336e-06,
"loss": 0.5443,
"step": 1734
},
{
"epoch": 2.58,
"learning_rate": 2.9702970297029703e-06,
"loss": 0.4866,
"step": 1735
},
{
"epoch": 2.58,
"learning_rate": 2.959874934861908e-06,
"loss": 0.5523,
"step": 1736
},
{
"epoch": 2.58,
"learning_rate": 2.9494528400208445e-06,
"loss": 0.4601,
"step": 1737
},
{
"epoch": 2.58,
"learning_rate": 2.9390307451797812e-06,
"loss": 0.4797,
"step": 1738
},
{
"epoch": 2.58,
"learning_rate": 2.9286086503387184e-06,
"loss": 0.5734,
"step": 1739
},
{
"epoch": 2.59,
"learning_rate": 2.918186555497655e-06,
"loss": 0.5403,
"step": 1740
},
{
"epoch": 2.59,
"learning_rate": 2.9077644606565926e-06,
"loss": 0.5428,
"step": 1741
},
{
"epoch": 2.59,
"learning_rate": 2.8973423658155293e-06,
"loss": 0.6137,
"step": 1742
},
{
"epoch": 2.59,
"learning_rate": 2.886920270974466e-06,
"loss": 0.5775,
"step": 1743
},
{
"epoch": 2.59,
"learning_rate": 2.876498176133403e-06,
"loss": 0.6051,
"step": 1744
},
{
"epoch": 2.59,
"learning_rate": 2.8660760812923398e-06,
"loss": 0.6475,
"step": 1745
},
{
"epoch": 2.59,
"learning_rate": 2.8556539864512765e-06,
"loss": 0.4947,
"step": 1746
},
{
"epoch": 2.6,
"learning_rate": 2.845231891610214e-06,
"loss": 0.5435,
"step": 1747
},
{
"epoch": 2.6,
"learning_rate": 2.8348097967691507e-06,
"loss": 0.6496,
"step": 1748
},
{
"epoch": 2.6,
"learning_rate": 2.824387701928088e-06,
"loss": 0.6912,
"step": 1749
},
{
"epoch": 2.6,
"learning_rate": 2.8139656070870245e-06,
"loss": 0.5153,
"step": 1750
},
{
"epoch": 2.6,
"eval_loss": 1.4344613552093506,
"eval_runtime": 0.6841,
"eval_samples_per_second": 356.664,
"eval_steps_per_second": 45.314,
"step": 1750
},
{
"epoch": 2.6,
"learning_rate": 2.8035435122459616e-06,
"loss": 0.5702,
"step": 1751
},
{
"epoch": 2.6,
"learning_rate": 2.7931214174048988e-06,
"loss": 0.5376,
"step": 1752
},
{
"epoch": 2.6,
"learning_rate": 2.7826993225638355e-06,
"loss": 0.6134,
"step": 1753
},
{
"epoch": 2.61,
"learning_rate": 2.7722772277227726e-06,
"loss": 0.5489,
"step": 1754
},
{
"epoch": 2.61,
"learning_rate": 2.7618551328817097e-06,
"loss": 0.5557,
"step": 1755
},
{
"epoch": 2.61,
"learning_rate": 2.7514330380406464e-06,
"loss": 0.7084,
"step": 1756
},
{
"epoch": 2.61,
"learning_rate": 2.7410109431995835e-06,
"loss": 0.4808,
"step": 1757
},
{
"epoch": 2.61,
"learning_rate": 2.73058884835852e-06,
"loss": 0.4808,
"step": 1758
},
{
"epoch": 2.61,
"learning_rate": 2.720166753517457e-06,
"loss": 0.5798,
"step": 1759
},
{
"epoch": 2.62,
"learning_rate": 2.7097446586763944e-06,
"loss": 0.6533,
"step": 1760
},
{
"epoch": 2.62,
"learning_rate": 2.699322563835331e-06,
"loss": 0.6561,
"step": 1761
},
{
"epoch": 2.62,
"learning_rate": 2.6889004689942682e-06,
"loss": 0.5985,
"step": 1762
},
{
"epoch": 2.62,
"learning_rate": 2.678478374153205e-06,
"loss": 0.6139,
"step": 1763
},
{
"epoch": 2.62,
"learning_rate": 2.6680562793121416e-06,
"loss": 0.5598,
"step": 1764
},
{
"epoch": 2.62,
"learning_rate": 2.657634184471079e-06,
"loss": 0.5569,
"step": 1765
},
{
"epoch": 2.62,
"learning_rate": 2.647212089630016e-06,
"loss": 0.4172,
"step": 1766
},
{
"epoch": 2.63,
"learning_rate": 2.636789994788953e-06,
"loss": 0.5894,
"step": 1767
},
{
"epoch": 2.63,
"learning_rate": 2.6263678999478897e-06,
"loss": 0.5695,
"step": 1768
},
{
"epoch": 2.63,
"learning_rate": 2.6159458051068264e-06,
"loss": 0.5858,
"step": 1769
},
{
"epoch": 2.63,
"learning_rate": 2.605523710265764e-06,
"loss": 0.6265,
"step": 1770
},
{
"epoch": 2.63,
"learning_rate": 2.5951016154247006e-06,
"loss": 0.4789,
"step": 1771
},
{
"epoch": 2.63,
"learning_rate": 2.5846795205836373e-06,
"loss": 0.4668,
"step": 1772
},
{
"epoch": 2.63,
"learning_rate": 2.5742574257425744e-06,
"loss": 0.4899,
"step": 1773
},
{
"epoch": 2.64,
"learning_rate": 2.563835330901511e-06,
"loss": 0.636,
"step": 1774
},
{
"epoch": 2.64,
"learning_rate": 2.5534132360604486e-06,
"loss": 0.7126,
"step": 1775
},
{
"epoch": 2.64,
"learning_rate": 2.5429911412193853e-06,
"loss": 0.5875,
"step": 1776
},
{
"epoch": 2.64,
"learning_rate": 2.532569046378322e-06,
"loss": 0.4471,
"step": 1777
},
{
"epoch": 2.64,
"learning_rate": 2.522146951537259e-06,
"loss": 0.6958,
"step": 1778
},
{
"epoch": 2.64,
"learning_rate": 2.511724856696196e-06,
"loss": 0.6529,
"step": 1779
},
{
"epoch": 2.64,
"learning_rate": 2.5013027618551334e-06,
"loss": 0.5361,
"step": 1780
},
{
"epoch": 2.65,
"learning_rate": 2.49088066701407e-06,
"loss": 0.4742,
"step": 1781
},
{
"epoch": 2.65,
"learning_rate": 2.480458572173007e-06,
"loss": 0.5766,
"step": 1782
},
{
"epoch": 2.65,
"learning_rate": 2.470036477331944e-06,
"loss": 0.529,
"step": 1783
},
{
"epoch": 2.65,
"learning_rate": 2.459614382490881e-06,
"loss": 0.5732,
"step": 1784
},
{
"epoch": 2.65,
"learning_rate": 2.4491922876498177e-06,
"loss": 0.7092,
"step": 1785
},
{
"epoch": 2.65,
"learning_rate": 2.438770192808755e-06,
"loss": 0.5066,
"step": 1786
},
{
"epoch": 2.66,
"learning_rate": 2.428348097967692e-06,
"loss": 0.6981,
"step": 1787
},
{
"epoch": 2.66,
"learning_rate": 2.4179260031266286e-06,
"loss": 0.5282,
"step": 1788
},
{
"epoch": 2.66,
"learning_rate": 2.4075039082855657e-06,
"loss": 0.5561,
"step": 1789
},
{
"epoch": 2.66,
"learning_rate": 2.3970818134445024e-06,
"loss": 0.4699,
"step": 1790
},
{
"epoch": 2.66,
"learning_rate": 2.3866597186034396e-06,
"loss": 0.5713,
"step": 1791
},
{
"epoch": 2.66,
"learning_rate": 2.3762376237623762e-06,
"loss": 0.5086,
"step": 1792
},
{
"epoch": 2.66,
"learning_rate": 2.3658155289213134e-06,
"loss": 0.8841,
"step": 1793
},
{
"epoch": 2.67,
"learning_rate": 2.3553934340802505e-06,
"loss": 0.6792,
"step": 1794
},
{
"epoch": 2.67,
"learning_rate": 2.344971339239187e-06,
"loss": 0.6206,
"step": 1795
},
{
"epoch": 2.67,
"learning_rate": 2.3345492443981243e-06,
"loss": 0.7345,
"step": 1796
},
{
"epoch": 2.67,
"learning_rate": 2.324127149557061e-06,
"loss": 0.5052,
"step": 1797
},
{
"epoch": 2.67,
"learning_rate": 2.313705054715998e-06,
"loss": 0.5066,
"step": 1798
},
{
"epoch": 2.67,
"learning_rate": 2.3032829598749352e-06,
"loss": 0.5445,
"step": 1799
},
{
"epoch": 2.67,
"learning_rate": 2.292860865033872e-06,
"loss": 0.4033,
"step": 1800
},
{
"epoch": 2.68,
"learning_rate": 2.282438770192809e-06,
"loss": 0.5,
"step": 1801
},
{
"epoch": 2.68,
"learning_rate": 2.2720166753517457e-06,
"loss": 0.5898,
"step": 1802
},
{
"epoch": 2.68,
"learning_rate": 2.261594580510683e-06,
"loss": 0.7819,
"step": 1803
},
{
"epoch": 2.68,
"learning_rate": 2.25117248566962e-06,
"loss": 0.5184,
"step": 1804
},
{
"epoch": 2.68,
"learning_rate": 2.2407503908285567e-06,
"loss": 0.4091,
"step": 1805
},
{
"epoch": 2.68,
"learning_rate": 2.2303282959874938e-06,
"loss": 0.5811,
"step": 1806
},
{
"epoch": 2.68,
"learning_rate": 2.2199062011464305e-06,
"loss": 0.5912,
"step": 1807
},
{
"epoch": 2.69,
"learning_rate": 2.2094841063053676e-06,
"loss": 0.6045,
"step": 1808
},
{
"epoch": 2.69,
"learning_rate": 2.1990620114643043e-06,
"loss": 0.5767,
"step": 1809
},
{
"epoch": 2.69,
"learning_rate": 2.1886399166232414e-06,
"loss": 0.4764,
"step": 1810
},
{
"epoch": 2.69,
"learning_rate": 2.1782178217821785e-06,
"loss": 0.4454,
"step": 1811
},
{
"epoch": 2.69,
"learning_rate": 2.167795726941115e-06,
"loss": 0.5807,
"step": 1812
},
{
"epoch": 2.69,
"learning_rate": 2.1573736321000523e-06,
"loss": 0.5435,
"step": 1813
},
{
"epoch": 2.7,
"learning_rate": 2.146951537258989e-06,
"loss": 0.4746,
"step": 1814
},
{
"epoch": 2.7,
"learning_rate": 2.136529442417926e-06,
"loss": 0.5002,
"step": 1815
},
{
"epoch": 2.7,
"learning_rate": 2.1261073475768632e-06,
"loss": 0.5045,
"step": 1816
},
{
"epoch": 2.7,
"learning_rate": 2.1156852527358004e-06,
"loss": 0.4686,
"step": 1817
},
{
"epoch": 2.7,
"learning_rate": 2.105263157894737e-06,
"loss": 0.5116,
"step": 1818
},
{
"epoch": 2.7,
"learning_rate": 2.0948410630536738e-06,
"loss": 0.5624,
"step": 1819
},
{
"epoch": 2.7,
"learning_rate": 2.084418968212611e-06,
"loss": 0.5412,
"step": 1820
},
{
"epoch": 2.71,
"learning_rate": 2.073996873371548e-06,
"loss": 0.5513,
"step": 1821
},
{
"epoch": 2.71,
"learning_rate": 2.063574778530485e-06,
"loss": 0.7242,
"step": 1822
},
{
"epoch": 2.71,
"learning_rate": 2.053152683689422e-06,
"loss": 0.5097,
"step": 1823
},
{
"epoch": 2.71,
"learning_rate": 2.0427305888483585e-06,
"loss": 0.6423,
"step": 1824
},
{
"epoch": 2.71,
"learning_rate": 2.0323084940072956e-06,
"loss": 0.7055,
"step": 1825
},
{
"epoch": 2.71,
"learning_rate": 2.0218863991662327e-06,
"loss": 0.4196,
"step": 1826
},
{
"epoch": 2.71,
"learning_rate": 2.0114643043251694e-06,
"loss": 0.5106,
"step": 1827
},
{
"epoch": 2.72,
"learning_rate": 2.0010422094841065e-06,
"loss": 0.6064,
"step": 1828
},
{
"epoch": 2.72,
"learning_rate": 1.9906201146430437e-06,
"loss": 0.511,
"step": 1829
},
{
"epoch": 2.72,
"learning_rate": 1.9801980198019803e-06,
"loss": 0.52,
"step": 1830
},
{
"epoch": 2.72,
"learning_rate": 1.969775924960917e-06,
"loss": 0.575,
"step": 1831
},
{
"epoch": 2.72,
"learning_rate": 1.959353830119854e-06,
"loss": 0.5916,
"step": 1832
},
{
"epoch": 2.72,
"learning_rate": 1.9489317352787913e-06,
"loss": 0.5505,
"step": 1833
},
{
"epoch": 2.73,
"learning_rate": 1.9385096404377284e-06,
"loss": 0.8142,
"step": 1834
},
{
"epoch": 2.73,
"learning_rate": 1.928087545596665e-06,
"loss": 0.5447,
"step": 1835
},
{
"epoch": 2.73,
"learning_rate": 1.9176654507556018e-06,
"loss": 0.4267,
"step": 1836
},
{
"epoch": 2.73,
"learning_rate": 1.907243355914539e-06,
"loss": 0.681,
"step": 1837
},
{
"epoch": 2.73,
"learning_rate": 1.896821261073476e-06,
"loss": 0.5375,
"step": 1838
},
{
"epoch": 2.73,
"learning_rate": 1.886399166232413e-06,
"loss": 0.5282,
"step": 1839
},
{
"epoch": 2.73,
"learning_rate": 1.8759770713913496e-06,
"loss": 0.7037,
"step": 1840
},
{
"epoch": 2.74,
"learning_rate": 1.8655549765502867e-06,
"loss": 0.621,
"step": 1841
},
{
"epoch": 2.74,
"learning_rate": 1.8551328817092236e-06,
"loss": 0.5827,
"step": 1842
},
{
"epoch": 2.74,
"learning_rate": 1.8447107868681608e-06,
"loss": 0.4925,
"step": 1843
},
{
"epoch": 2.74,
"learning_rate": 1.8342886920270974e-06,
"loss": 0.5638,
"step": 1844
},
{
"epoch": 2.74,
"learning_rate": 1.8238665971860346e-06,
"loss": 0.6055,
"step": 1845
},
{
"epoch": 2.74,
"learning_rate": 1.8134445023449715e-06,
"loss": 0.5512,
"step": 1846
},
{
"epoch": 2.74,
"learning_rate": 1.8030224075039086e-06,
"loss": 0.6097,
"step": 1847
},
{
"epoch": 2.75,
"learning_rate": 1.7926003126628455e-06,
"loss": 0.5256,
"step": 1848
},
{
"epoch": 2.75,
"learning_rate": 1.7821782178217822e-06,
"loss": 0.5355,
"step": 1849
},
{
"epoch": 2.75,
"learning_rate": 1.7717561229807193e-06,
"loss": 0.5782,
"step": 1850
},
{
"epoch": 2.75,
"learning_rate": 1.7613340281396562e-06,
"loss": 0.5097,
"step": 1851
},
{
"epoch": 2.75,
"learning_rate": 1.7509119332985933e-06,
"loss": 0.4361,
"step": 1852
},
{
"epoch": 2.75,
"learning_rate": 1.74048983845753e-06,
"loss": 0.6183,
"step": 1853
},
{
"epoch": 2.75,
"learning_rate": 1.730067743616467e-06,
"loss": 0.4774,
"step": 1854
},
{
"epoch": 2.76,
"learning_rate": 1.719645648775404e-06,
"loss": 0.5586,
"step": 1855
},
{
"epoch": 2.76,
"learning_rate": 1.709223553934341e-06,
"loss": 0.5146,
"step": 1856
},
{
"epoch": 2.76,
"learning_rate": 1.6988014590932779e-06,
"loss": 0.5886,
"step": 1857
},
{
"epoch": 2.76,
"learning_rate": 1.6883793642522148e-06,
"loss": 0.5711,
"step": 1858
},
{
"epoch": 2.76,
"learning_rate": 1.6779572694111519e-06,
"loss": 0.5242,
"step": 1859
},
{
"epoch": 2.76,
"learning_rate": 1.6675351745700888e-06,
"loss": 0.571,
"step": 1860
},
{
"epoch": 2.77,
"learning_rate": 1.657113079729026e-06,
"loss": 0.4609,
"step": 1861
},
{
"epoch": 2.77,
"learning_rate": 1.6466909848879626e-06,
"loss": 0.5,
"step": 1862
},
{
"epoch": 2.77,
"learning_rate": 1.6362688900468995e-06,
"loss": 0.6818,
"step": 1863
},
{
"epoch": 2.77,
"learning_rate": 1.6258467952058366e-06,
"loss": 0.4666,
"step": 1864
},
{
"epoch": 2.77,
"learning_rate": 1.6154247003647735e-06,
"loss": 0.5301,
"step": 1865
},
{
"epoch": 2.77,
"learning_rate": 1.6050026055237102e-06,
"loss": 0.4877,
"step": 1866
},
{
"epoch": 2.77,
"learning_rate": 1.5945805106826473e-06,
"loss": 0.4592,
"step": 1867
},
{
"epoch": 2.78,
"learning_rate": 1.5841584158415842e-06,
"loss": 0.6341,
"step": 1868
},
{
"epoch": 2.78,
"learning_rate": 1.5737363210005214e-06,
"loss": 0.429,
"step": 1869
},
{
"epoch": 2.78,
"learning_rate": 1.563314226159458e-06,
"loss": 0.6416,
"step": 1870
},
{
"epoch": 2.78,
"learning_rate": 1.552892131318395e-06,
"loss": 0.5914,
"step": 1871
},
{
"epoch": 2.78,
"learning_rate": 1.542470036477332e-06,
"loss": 0.5367,
"step": 1872
},
{
"epoch": 2.78,
"learning_rate": 1.532047941636269e-06,
"loss": 0.6263,
"step": 1873
},
{
"epoch": 2.78,
"learning_rate": 1.521625846795206e-06,
"loss": 0.6064,
"step": 1874
},
{
"epoch": 2.79,
"learning_rate": 1.5112037519541428e-06,
"loss": 0.6656,
"step": 1875
},
{
"epoch": 2.79,
"eval_loss": 1.4329994916915894,
"eval_runtime": 0.6835,
"eval_samples_per_second": 356.997,
"eval_steps_per_second": 45.356,
"step": 1875
},
{
"epoch": 2.79,
"learning_rate": 1.50078165711308e-06,
"loss": 0.5228,
"step": 1876
},
{
"epoch": 2.79,
"learning_rate": 1.4903595622720168e-06,
"loss": 0.607,
"step": 1877
},
{
"epoch": 2.79,
"learning_rate": 1.479937467430954e-06,
"loss": 0.6114,
"step": 1878
},
{
"epoch": 2.79,
"learning_rate": 1.4695153725898906e-06,
"loss": 0.5437,
"step": 1879
},
{
"epoch": 2.79,
"learning_rate": 1.4590932777488275e-06,
"loss": 0.5683,
"step": 1880
},
{
"epoch": 2.79,
"learning_rate": 1.4486711829077646e-06,
"loss": 0.5363,
"step": 1881
},
{
"epoch": 2.8,
"learning_rate": 1.4382490880667015e-06,
"loss": 0.5422,
"step": 1882
},
{
"epoch": 2.8,
"learning_rate": 1.4278269932256382e-06,
"loss": 0.6043,
"step": 1883
},
{
"epoch": 2.8,
"learning_rate": 1.4174048983845754e-06,
"loss": 0.4592,
"step": 1884
},
{
"epoch": 2.8,
"learning_rate": 1.4069828035435123e-06,
"loss": 0.694,
"step": 1885
},
{
"epoch": 2.8,
"learning_rate": 1.3965607087024494e-06,
"loss": 0.4755,
"step": 1886
},
{
"epoch": 2.8,
"learning_rate": 1.3861386138613863e-06,
"loss": 0.6365,
"step": 1887
},
{
"epoch": 2.81,
"learning_rate": 1.3757165190203232e-06,
"loss": 0.4961,
"step": 1888
},
{
"epoch": 2.81,
"learning_rate": 1.36529442417926e-06,
"loss": 0.593,
"step": 1889
},
{
"epoch": 2.81,
"learning_rate": 1.3548723293381972e-06,
"loss": 0.5515,
"step": 1890
},
{
"epoch": 2.81,
"learning_rate": 1.3444502344971341e-06,
"loss": 0.6097,
"step": 1891
},
{
"epoch": 2.81,
"learning_rate": 1.3340281396560708e-06,
"loss": 0.5223,
"step": 1892
},
{
"epoch": 2.81,
"learning_rate": 1.323606044815008e-06,
"loss": 0.5084,
"step": 1893
},
{
"epoch": 2.81,
"learning_rate": 1.3131839499739448e-06,
"loss": 0.4278,
"step": 1894
},
{
"epoch": 2.82,
"learning_rate": 1.302761855132882e-06,
"loss": 0.5073,
"step": 1895
},
{
"epoch": 2.82,
"learning_rate": 1.2923397602918186e-06,
"loss": 0.5202,
"step": 1896
},
{
"epoch": 2.82,
"learning_rate": 1.2819176654507556e-06,
"loss": 0.6624,
"step": 1897
},
{
"epoch": 2.82,
"learning_rate": 1.2714955706096927e-06,
"loss": 0.5346,
"step": 1898
},
{
"epoch": 2.82,
"learning_rate": 1.2610734757686296e-06,
"loss": 0.8463,
"step": 1899
},
{
"epoch": 2.82,
"learning_rate": 1.2506513809275667e-06,
"loss": 0.5435,
"step": 1900
},
{
"epoch": 2.82,
"learning_rate": 1.2402292860865036e-06,
"loss": 0.6065,
"step": 1901
},
{
"epoch": 2.83,
"learning_rate": 1.2298071912454405e-06,
"loss": 0.5813,
"step": 1902
},
{
"epoch": 2.83,
"learning_rate": 1.2193850964043774e-06,
"loss": 0.451,
"step": 1903
},
{
"epoch": 2.83,
"learning_rate": 1.2089630015633143e-06,
"loss": 0.6216,
"step": 1904
},
{
"epoch": 2.83,
"learning_rate": 1.1985409067222512e-06,
"loss": 0.7343,
"step": 1905
},
{
"epoch": 2.83,
"learning_rate": 1.1881188118811881e-06,
"loss": 0.5359,
"step": 1906
},
{
"epoch": 2.83,
"learning_rate": 1.1776967170401252e-06,
"loss": 0.7486,
"step": 1907
},
{
"epoch": 2.84,
"learning_rate": 1.1672746221990621e-06,
"loss": 0.4705,
"step": 1908
},
{
"epoch": 2.84,
"learning_rate": 1.156852527357999e-06,
"loss": 0.5463,
"step": 1909
},
{
"epoch": 2.84,
"learning_rate": 1.146430432516936e-06,
"loss": 0.4879,
"step": 1910
},
{
"epoch": 2.84,
"learning_rate": 1.1360083376758729e-06,
"loss": 0.5123,
"step": 1911
},
{
"epoch": 2.84,
"learning_rate": 1.12558624283481e-06,
"loss": 0.5135,
"step": 1912
},
{
"epoch": 2.84,
"learning_rate": 1.1151641479937469e-06,
"loss": 0.4328,
"step": 1913
},
{
"epoch": 2.84,
"learning_rate": 1.1047420531526838e-06,
"loss": 0.5401,
"step": 1914
},
{
"epoch": 2.85,
"learning_rate": 1.0943199583116207e-06,
"loss": 0.5942,
"step": 1915
},
{
"epoch": 2.85,
"learning_rate": 1.0838978634705576e-06,
"loss": 0.4718,
"step": 1916
},
{
"epoch": 2.85,
"learning_rate": 1.0734757686294945e-06,
"loss": 0.578,
"step": 1917
},
{
"epoch": 2.85,
"learning_rate": 1.0630536737884316e-06,
"loss": 0.6242,
"step": 1918
},
{
"epoch": 2.85,
"learning_rate": 1.0526315789473685e-06,
"loss": 0.6435,
"step": 1919
},
{
"epoch": 2.85,
"learning_rate": 1.0422094841063054e-06,
"loss": 0.5521,
"step": 1920
},
{
"epoch": 2.85,
"learning_rate": 1.0317873892652426e-06,
"loss": 0.5445,
"step": 1921
},
{
"epoch": 2.86,
"learning_rate": 1.0213652944241792e-06,
"loss": 0.4296,
"step": 1922
},
{
"epoch": 2.86,
"learning_rate": 1.0109431995831164e-06,
"loss": 0.5042,
"step": 1923
},
{
"epoch": 2.86,
"learning_rate": 1.0005211047420533e-06,
"loss": 0.7633,
"step": 1924
},
{
"epoch": 2.86,
"learning_rate": 9.900990099009902e-07,
"loss": 0.6108,
"step": 1925
},
{
"epoch": 2.86,
"learning_rate": 9.79676915059927e-07,
"loss": 0.646,
"step": 1926
},
{
"epoch": 2.86,
"learning_rate": 9.692548202188642e-07,
"loss": 0.5247,
"step": 1927
},
{
"epoch": 2.86,
"learning_rate": 9.588327253778009e-07,
"loss": 0.533,
"step": 1928
},
{
"epoch": 2.87,
"learning_rate": 9.48410630536738e-07,
"loss": 0.5962,
"step": 1929
},
{
"epoch": 2.87,
"learning_rate": 9.379885356956748e-07,
"loss": 0.7111,
"step": 1930
},
{
"epoch": 2.87,
"learning_rate": 9.275664408546118e-07,
"loss": 0.5513,
"step": 1931
},
{
"epoch": 2.87,
"learning_rate": 9.171443460135487e-07,
"loss": 0.426,
"step": 1932
},
{
"epoch": 2.87,
"learning_rate": 9.067222511724857e-07,
"loss": 0.6282,
"step": 1933
},
{
"epoch": 2.87,
"learning_rate": 8.963001563314227e-07,
"loss": 0.5791,
"step": 1934
},
{
"epoch": 2.88,
"learning_rate": 8.858780614903597e-07,
"loss": 0.5285,
"step": 1935
},
{
"epoch": 2.88,
"learning_rate": 8.754559666492967e-07,
"loss": 0.5627,
"step": 1936
},
{
"epoch": 2.88,
"learning_rate": 8.650338718082335e-07,
"loss": 0.7554,
"step": 1937
},
{
"epoch": 2.88,
"learning_rate": 8.546117769671705e-07,
"loss": 0.5481,
"step": 1938
},
{
"epoch": 2.88,
"learning_rate": 8.441896821261074e-07,
"loss": 0.6376,
"step": 1939
},
{
"epoch": 2.88,
"learning_rate": 8.337675872850444e-07,
"loss": 0.4177,
"step": 1940
},
{
"epoch": 2.88,
"learning_rate": 8.233454924439813e-07,
"loss": 0.5453,
"step": 1941
},
{
"epoch": 2.89,
"learning_rate": 8.129233976029183e-07,
"loss": 0.5542,
"step": 1942
},
{
"epoch": 2.89,
"learning_rate": 8.025013027618551e-07,
"loss": 0.4512,
"step": 1943
},
{
"epoch": 2.89,
"learning_rate": 7.920792079207921e-07,
"loss": 0.5229,
"step": 1944
},
{
"epoch": 2.89,
"learning_rate": 7.81657113079729e-07,
"loss": 0.6864,
"step": 1945
},
{
"epoch": 2.89,
"learning_rate": 7.71235018238666e-07,
"loss": 0.5412,
"step": 1946
},
{
"epoch": 2.89,
"learning_rate": 7.60812923397603e-07,
"loss": 0.5141,
"step": 1947
},
{
"epoch": 2.89,
"learning_rate": 7.5039082855654e-07,
"loss": 0.5687,
"step": 1948
},
{
"epoch": 2.9,
"learning_rate": 7.39968733715477e-07,
"loss": 0.6329,
"step": 1949
},
{
"epoch": 2.9,
"learning_rate": 7.295466388744138e-07,
"loss": 0.5664,
"step": 1950
},
{
"epoch": 2.9,
"learning_rate": 7.191245440333508e-07,
"loss": 0.5928,
"step": 1951
},
{
"epoch": 2.9,
"learning_rate": 7.087024491922877e-07,
"loss": 0.6811,
"step": 1952
},
{
"epoch": 2.9,
"learning_rate": 6.982803543512247e-07,
"loss": 0.5385,
"step": 1953
},
{
"epoch": 2.9,
"learning_rate": 6.878582595101616e-07,
"loss": 0.5689,
"step": 1954
},
{
"epoch": 2.9,
"learning_rate": 6.774361646690986e-07,
"loss": 0.5895,
"step": 1955
},
{
"epoch": 2.91,
"learning_rate": 6.670140698280354e-07,
"loss": 0.6174,
"step": 1956
},
{
"epoch": 2.91,
"learning_rate": 6.565919749869724e-07,
"loss": 0.6659,
"step": 1957
},
{
"epoch": 2.91,
"learning_rate": 6.461698801459093e-07,
"loss": 0.4894,
"step": 1958
},
{
"epoch": 2.91,
"learning_rate": 6.357477853048463e-07,
"loss": 0.4542,
"step": 1959
},
{
"epoch": 2.91,
"learning_rate": 6.253256904637833e-07,
"loss": 0.5413,
"step": 1960
},
{
"epoch": 2.91,
"learning_rate": 6.149035956227203e-07,
"loss": 0.6968,
"step": 1961
},
{
"epoch": 2.92,
"learning_rate": 6.044815007816572e-07,
"loss": 0.5405,
"step": 1962
},
{
"epoch": 2.92,
"learning_rate": 5.940594059405941e-07,
"loss": 0.7684,
"step": 1963
},
{
"epoch": 2.92,
"learning_rate": 5.836373110995311e-07,
"loss": 0.4515,
"step": 1964
},
{
"epoch": 2.92,
"learning_rate": 5.73215216258468e-07,
"loss": 0.5659,
"step": 1965
},
{
"epoch": 2.92,
"learning_rate": 5.62793121417405e-07,
"loss": 0.4828,
"step": 1966
},
{
"epoch": 2.92,
"learning_rate": 5.523710265763419e-07,
"loss": 0.627,
"step": 1967
},
{
"epoch": 2.92,
"learning_rate": 5.419489317352788e-07,
"loss": 0.4728,
"step": 1968
},
{
"epoch": 2.93,
"learning_rate": 5.315268368942158e-07,
"loss": 0.7635,
"step": 1969
},
{
"epoch": 2.93,
"learning_rate": 5.211047420531527e-07,
"loss": 0.6551,
"step": 1970
},
{
"epoch": 2.93,
"learning_rate": 5.106826472120896e-07,
"loss": 0.5136,
"step": 1971
},
{
"epoch": 2.93,
"learning_rate": 5.002605523710266e-07,
"loss": 0.6456,
"step": 1972
},
{
"epoch": 2.93,
"learning_rate": 4.898384575299635e-07,
"loss": 0.6743,
"step": 1973
},
{
"epoch": 2.93,
"learning_rate": 4.794163626889004e-07,
"loss": 0.4168,
"step": 1974
},
{
"epoch": 2.93,
"learning_rate": 4.689942678478374e-07,
"loss": 0.685,
"step": 1975
},
{
"epoch": 2.94,
"learning_rate": 4.5857217300677436e-07,
"loss": 0.4732,
"step": 1976
},
{
"epoch": 2.94,
"learning_rate": 4.4815007816571137e-07,
"loss": 0.5129,
"step": 1977
},
{
"epoch": 2.94,
"learning_rate": 4.3772798332464833e-07,
"loss": 0.5885,
"step": 1978
},
{
"epoch": 2.94,
"learning_rate": 4.2730588848358524e-07,
"loss": 0.6191,
"step": 1979
},
{
"epoch": 2.94,
"learning_rate": 4.168837936425222e-07,
"loss": 0.6379,
"step": 1980
},
{
"epoch": 2.94,
"learning_rate": 4.0646169880145915e-07,
"loss": 0.5286,
"step": 1981
},
{
"epoch": 2.95,
"learning_rate": 3.9603960396039606e-07,
"loss": 0.6491,
"step": 1982
},
{
"epoch": 2.95,
"learning_rate": 3.85617509119333e-07,
"loss": 0.426,
"step": 1983
},
{
"epoch": 2.95,
"learning_rate": 3.7519541427827e-07,
"loss": 0.6008,
"step": 1984
},
{
"epoch": 2.95,
"learning_rate": 3.647733194372069e-07,
"loss": 0.5416,
"step": 1985
},
{
"epoch": 2.95,
"learning_rate": 3.5435122459614384e-07,
"loss": 0.6618,
"step": 1986
},
{
"epoch": 2.95,
"learning_rate": 3.439291297550808e-07,
"loss": 0.5346,
"step": 1987
},
{
"epoch": 2.95,
"learning_rate": 3.335070349140177e-07,
"loss": 0.5715,
"step": 1988
},
{
"epoch": 2.96,
"learning_rate": 3.2308494007295466e-07,
"loss": 0.619,
"step": 1989
},
{
"epoch": 2.96,
"learning_rate": 3.1266284523189167e-07,
"loss": 0.5217,
"step": 1990
},
{
"epoch": 2.96,
"learning_rate": 3.022407503908286e-07,
"loss": 0.5005,
"step": 1991
},
{
"epoch": 2.96,
"learning_rate": 2.9181865554976554e-07,
"loss": 0.4824,
"step": 1992
},
{
"epoch": 2.96,
"learning_rate": 2.813965607087025e-07,
"loss": 0.5146,
"step": 1993
},
{
"epoch": 2.96,
"learning_rate": 2.709744658676394e-07,
"loss": 0.6188,
"step": 1994
},
{
"epoch": 2.96,
"learning_rate": 2.6055237102657636e-07,
"loss": 0.6423,
"step": 1995
},
{
"epoch": 2.97,
"learning_rate": 2.501302761855133e-07,
"loss": 0.6654,
"step": 1996
},
{
"epoch": 2.97,
"learning_rate": 2.397081813444502e-07,
"loss": 0.619,
"step": 1997
},
{
"epoch": 2.97,
"learning_rate": 2.2928608650338718e-07,
"loss": 0.6527,
"step": 1998
},
{
"epoch": 2.97,
"learning_rate": 2.1886399166232417e-07,
"loss": 0.615,
"step": 1999
},
{
"epoch": 2.97,
"learning_rate": 2.084418968212611e-07,
"loss": 0.4173,
"step": 2000
},
{
"epoch": 2.97,
"eval_loss": 1.431810975074768,
"eval_runtime": 0.682,
"eval_samples_per_second": 357.793,
"eval_steps_per_second": 45.457,
"step": 2000
}
],
"logging_steps": 1,
"max_steps": 2019,
"num_train_epochs": 3,
"save_steps": 250,
"total_flos": 2.254373375705088e+17,
"trial_name": null,
"trial_params": null
}