DriveMonkey / Pretrain_2B /trainer_state.json
zczhao's picture
Upload folder using huggingface_hub
4283f73 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9999176615891313,
"eval_steps": 500,
"global_step": 759,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 8.695652173913044e-07,
"loss": 1.8484,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.7391304347826088e-06,
"loss": 1.9125,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.6086956521739132e-06,
"loss": 1.8943,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 3.4782608695652175e-06,
"loss": 1.9085,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 4.347826086956522e-06,
"loss": 1.887,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 5.2173913043478265e-06,
"loss": 1.8607,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 6.086956521739132e-06,
"loss": 1.8876,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 6.956521739130435e-06,
"loss": 1.8753,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 7.82608695652174e-06,
"loss": 1.8336,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 8.695652173913044e-06,
"loss": 1.8016,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 9.565217391304349e-06,
"loss": 1.7738,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 1.0434782608695653e-05,
"loss": 1.7794,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 1.1304347826086957e-05,
"loss": 1.8015,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 1.2173913043478263e-05,
"loss": 1.7103,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 1.3043478260869566e-05,
"loss": 1.7215,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.391304347826087e-05,
"loss": 1.6887,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 1.4782608695652174e-05,
"loss": 1.6018,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 1.565217391304348e-05,
"loss": 1.6769,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 1.6521739130434785e-05,
"loss": 1.6393,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 1.739130434782609e-05,
"loss": 1.6076,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 1.8260869565217393e-05,
"loss": 1.5988,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 1.9130434782608697e-05,
"loss": 1.6057,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 1.6224,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 1.999990890103106e-05,
"loss": 1.6007,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 1.9999635605784042e-05,
"loss": 1.5796,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 1.9999180119238327e-05,
"loss": 1.5841,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 1.9998542449692794e-05,
"loss": 1.5519,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 1.999772260876564e-05,
"loss": 1.519,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 1.99967206113942e-05,
"loss": 1.5497,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 1.9995536475834667e-05,
"loss": 1.4893,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 1.999417022366174e-05,
"loss": 1.5149,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 1.9992621879768256e-05,
"loss": 1.4988,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 1.999089147236472e-05,
"loss": 1.4931,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 1.998897903297879e-05,
"loss": 1.4954,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 1.998688459645473e-05,
"loss": 1.47,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 1.9984608200952736e-05,
"loss": 1.4654,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 1.9982149887948264e-05,
"loss": 1.4511,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 1.997950970223127e-05,
"loss": 1.4411,
"step": 38
},
{
"epoch": 0.05,
"learning_rate": 1.9976687691905394e-05,
"loss": 1.4413,
"step": 39
},
{
"epoch": 0.05,
"learning_rate": 1.997368390838708e-05,
"loss": 1.4492,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 1.997049840640465e-05,
"loss": 1.4415,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 1.996713124399729e-05,
"loss": 1.433,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 1.9963582482514003e-05,
"loss": 1.4392,
"step": 43
},
{
"epoch": 0.06,
"learning_rate": 1.9959852186612492e-05,
"loss": 1.4697,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 1.995594042425798e-05,
"loss": 1.4352,
"step": 45
},
{
"epoch": 0.06,
"learning_rate": 1.995184726672197e-05,
"loss": 1.3998,
"step": 46
},
{
"epoch": 0.06,
"learning_rate": 1.994757278858095e-05,
"loss": 1.4069,
"step": 47
},
{
"epoch": 0.06,
"learning_rate": 1.994311706771503e-05,
"loss": 1.4385,
"step": 48
},
{
"epoch": 0.06,
"learning_rate": 1.993848018530652e-05,
"loss": 1.4026,
"step": 49
},
{
"epoch": 0.07,
"learning_rate": 1.993366222583847e-05,
"loss": 1.3766,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 1.99286632770931e-05,
"loss": 1.4277,
"step": 51
},
{
"epoch": 0.07,
"learning_rate": 1.992348343015023e-05,
"loss": 1.3874,
"step": 52
},
{
"epoch": 0.07,
"learning_rate": 1.99181227793856e-05,
"loss": 1.3954,
"step": 53
},
{
"epoch": 0.07,
"learning_rate": 1.991258142246917e-05,
"loss": 1.3814,
"step": 54
},
{
"epoch": 0.07,
"learning_rate": 1.9906859460363307e-05,
"loss": 1.3968,
"step": 55
},
{
"epoch": 0.07,
"learning_rate": 1.990095699732099e-05,
"loss": 1.4273,
"step": 56
},
{
"epoch": 0.08,
"learning_rate": 1.9894874140883877e-05,
"loss": 1.3965,
"step": 57
},
{
"epoch": 0.08,
"learning_rate": 1.9888611001880357e-05,
"loss": 1.3884,
"step": 58
},
{
"epoch": 0.08,
"learning_rate": 1.988216769442353e-05,
"loss": 1.3648,
"step": 59
},
{
"epoch": 0.08,
"learning_rate": 1.987554433590913e-05,
"loss": 1.3636,
"step": 60
},
{
"epoch": 0.08,
"learning_rate": 1.9868741047013382e-05,
"loss": 1.4075,
"step": 61
},
{
"epoch": 0.08,
"learning_rate": 1.9861757951690813e-05,
"loss": 1.3511,
"step": 62
},
{
"epoch": 0.08,
"learning_rate": 1.9854595177171968e-05,
"loss": 1.3854,
"step": 63
},
{
"epoch": 0.08,
"learning_rate": 1.9847252853961136e-05,
"loss": 1.3692,
"step": 64
},
{
"epoch": 0.09,
"learning_rate": 1.983973111583392e-05,
"loss": 1.377,
"step": 65
},
{
"epoch": 0.09,
"learning_rate": 1.983203009983484e-05,
"loss": 1.3646,
"step": 66
},
{
"epoch": 0.09,
"learning_rate": 1.9824149946274827e-05,
"loss": 1.3667,
"step": 67
},
{
"epoch": 0.09,
"learning_rate": 1.9816090798728648e-05,
"loss": 1.3736,
"step": 68
},
{
"epoch": 0.09,
"learning_rate": 1.9807852804032306e-05,
"loss": 1.3783,
"step": 69
},
{
"epoch": 0.09,
"learning_rate": 1.9799436112280374e-05,
"loss": 1.3666,
"step": 70
},
{
"epoch": 0.09,
"learning_rate": 1.979084087682323e-05,
"loss": 1.3737,
"step": 71
},
{
"epoch": 0.09,
"learning_rate": 1.97820672542643e-05,
"loss": 1.3566,
"step": 72
},
{
"epoch": 0.1,
"learning_rate": 1.9773115404457175e-05,
"loss": 1.3695,
"step": 73
},
{
"epoch": 0.1,
"learning_rate": 1.9763985490502714e-05,
"loss": 1.3926,
"step": 74
},
{
"epoch": 0.1,
"learning_rate": 1.9754677678746064e-05,
"loss": 1.3779,
"step": 75
},
{
"epoch": 0.1,
"learning_rate": 1.9745192138773633e-05,
"loss": 1.3873,
"step": 76
},
{
"epoch": 0.1,
"learning_rate": 1.9735529043410012e-05,
"loss": 1.3452,
"step": 77
},
{
"epoch": 0.1,
"learning_rate": 1.97256885687148e-05,
"loss": 1.3324,
"step": 78
},
{
"epoch": 0.1,
"learning_rate": 1.9715670893979416e-05,
"loss": 1.343,
"step": 79
},
{
"epoch": 0.11,
"learning_rate": 1.970547620172383e-05,
"loss": 1.3607,
"step": 80
},
{
"epoch": 0.11,
"learning_rate": 1.9695104677693234e-05,
"loss": 1.3275,
"step": 81
},
{
"epoch": 0.11,
"learning_rate": 1.9684556510854655e-05,
"loss": 1.3336,
"step": 82
},
{
"epoch": 0.11,
"learning_rate": 1.967383189339352e-05,
"loss": 1.34,
"step": 83
},
{
"epoch": 0.11,
"learning_rate": 1.9662931020710138e-05,
"loss": 1.3204,
"step": 84
},
{
"epoch": 0.11,
"learning_rate": 1.9651854091416175e-05,
"loss": 1.3353,
"step": 85
},
{
"epoch": 0.11,
"learning_rate": 1.964060130733099e-05,
"loss": 1.3148,
"step": 86
},
{
"epoch": 0.11,
"learning_rate": 1.9629172873477995e-05,
"loss": 1.3188,
"step": 87
},
{
"epoch": 0.12,
"learning_rate": 1.9617568998080893e-05,
"loss": 1.3446,
"step": 88
},
{
"epoch": 0.12,
"learning_rate": 1.9605789892559902e-05,
"loss": 1.3092,
"step": 89
},
{
"epoch": 0.12,
"learning_rate": 1.9593835771527893e-05,
"loss": 1.3817,
"step": 90
},
{
"epoch": 0.12,
"learning_rate": 1.9581706852786492e-05,
"loss": 1.3141,
"step": 91
},
{
"epoch": 0.12,
"learning_rate": 1.956940335732209e-05,
"loss": 1.3394,
"step": 92
},
{
"epoch": 0.12,
"learning_rate": 1.9556925509301844e-05,
"loss": 1.3468,
"step": 93
},
{
"epoch": 0.12,
"learning_rate": 1.9544273536069573e-05,
"loss": 1.3313,
"step": 94
},
{
"epoch": 0.13,
"learning_rate": 1.953144766814161e-05,
"loss": 1.3337,
"step": 95
},
{
"epoch": 0.13,
"learning_rate": 1.9518448139202632e-05,
"loss": 1.3262,
"step": 96
},
{
"epoch": 0.13,
"learning_rate": 1.9505275186101378e-05,
"loss": 1.3225,
"step": 97
},
{
"epoch": 0.13,
"learning_rate": 1.9491929048846328e-05,
"loss": 1.3459,
"step": 98
},
{
"epoch": 0.13,
"learning_rate": 1.947840997060136e-05,
"loss": 1.3039,
"step": 99
},
{
"epoch": 0.13,
"learning_rate": 1.9464718197681284e-05,
"loss": 1.2979,
"step": 100
},
{
"epoch": 0.13,
"learning_rate": 1.9450853979547384e-05,
"loss": 1.2875,
"step": 101
},
{
"epoch": 0.13,
"learning_rate": 1.9436817568802854e-05,
"loss": 1.3223,
"step": 102
},
{
"epoch": 0.14,
"learning_rate": 1.9422609221188208e-05,
"loss": 1.3165,
"step": 103
},
{
"epoch": 0.14,
"learning_rate": 1.94082291955766e-05,
"loss": 1.2915,
"step": 104
},
{
"epoch": 0.14,
"learning_rate": 1.9393677753969137e-05,
"loss": 1.3495,
"step": 105
},
{
"epoch": 0.14,
"learning_rate": 1.9378955161490086e-05,
"loss": 1.3032,
"step": 106
},
{
"epoch": 0.14,
"learning_rate": 1.9364061686382042e-05,
"loss": 1.3499,
"step": 107
},
{
"epoch": 0.14,
"learning_rate": 1.9348997600001052e-05,
"loss": 1.3293,
"step": 108
},
{
"epoch": 0.14,
"learning_rate": 1.9333763176811663e-05,
"loss": 1.3426,
"step": 109
},
{
"epoch": 0.14,
"learning_rate": 1.9318358694381926e-05,
"loss": 1.3425,
"step": 110
},
{
"epoch": 0.15,
"learning_rate": 1.9302784433378333e-05,
"loss": 1.2916,
"step": 111
},
{
"epoch": 0.15,
"learning_rate": 1.928704067756071e-05,
"loss": 1.3192,
"step": 112
},
{
"epoch": 0.15,
"learning_rate": 1.9271127713777033e-05,
"loss": 1.3236,
"step": 113
},
{
"epoch": 0.15,
"learning_rate": 1.925504583195823e-05,
"loss": 1.3199,
"step": 114
},
{
"epoch": 0.15,
"learning_rate": 1.9238795325112867e-05,
"loss": 1.2867,
"step": 115
},
{
"epoch": 0.15,
"learning_rate": 1.922237648932183e-05,
"loss": 1.3383,
"step": 116
},
{
"epoch": 0.15,
"learning_rate": 1.9205789623732923e-05,
"loss": 1.3369,
"step": 117
},
{
"epoch": 0.16,
"learning_rate": 1.918903503055541e-05,
"loss": 1.3649,
"step": 118
},
{
"epoch": 0.16,
"learning_rate": 1.917211301505453e-05,
"loss": 1.3467,
"step": 119
},
{
"epoch": 0.16,
"learning_rate": 1.9155023885545914e-05,
"loss": 1.3158,
"step": 120
},
{
"epoch": 0.16,
"learning_rate": 1.913776795338998e-05,
"loss": 1.3026,
"step": 121
},
{
"epoch": 0.16,
"learning_rate": 1.9120345532986243e-05,
"loss": 1.337,
"step": 122
},
{
"epoch": 0.16,
"learning_rate": 1.9102756941767625e-05,
"loss": 1.293,
"step": 123
},
{
"epoch": 0.16,
"learning_rate": 1.908500250019462e-05,
"loss": 1.3328,
"step": 124
},
{
"epoch": 0.16,
"learning_rate": 1.9067082531749496e-05,
"loss": 1.2999,
"step": 125
},
{
"epoch": 0.17,
"learning_rate": 1.9048997362930384e-05,
"loss": 1.2873,
"step": 126
},
{
"epoch": 0.17,
"learning_rate": 1.903074732324533e-05,
"loss": 1.3122,
"step": 127
},
{
"epoch": 0.17,
"learning_rate": 1.901233274520629e-05,
"loss": 1.2823,
"step": 128
},
{
"epoch": 0.17,
"learning_rate": 1.8993753964323086e-05,
"loss": 1.2737,
"step": 129
},
{
"epoch": 0.17,
"learning_rate": 1.8975011319097264e-05,
"loss": 1.3172,
"step": 130
},
{
"epoch": 0.17,
"learning_rate": 1.8956105151015966e-05,
"loss": 1.2967,
"step": 131
},
{
"epoch": 0.17,
"learning_rate": 1.893703580454567e-05,
"loss": 1.2561,
"step": 132
},
{
"epoch": 0.18,
"learning_rate": 1.891780362712594e-05,
"loss": 1.2895,
"step": 133
},
{
"epoch": 0.18,
"learning_rate": 1.8898408969163078e-05,
"loss": 1.3122,
"step": 134
},
{
"epoch": 0.18,
"learning_rate": 1.8878852184023754e-05,
"loss": 1.2937,
"step": 135
},
{
"epoch": 0.18,
"learning_rate": 1.8859133628028564e-05,
"loss": 1.3323,
"step": 136
},
{
"epoch": 0.18,
"learning_rate": 1.8839253660445523e-05,
"loss": 1.2676,
"step": 137
},
{
"epoch": 0.18,
"learning_rate": 1.881921264348355e-05,
"loss": 1.3212,
"step": 138
},
{
"epoch": 0.18,
"learning_rate": 1.879901094228584e-05,
"loss": 1.2788,
"step": 139
},
{
"epoch": 0.18,
"learning_rate": 1.8778648924923222e-05,
"loss": 1.2941,
"step": 140
},
{
"epoch": 0.19,
"learning_rate": 1.875812696238745e-05,
"loss": 1.3259,
"step": 141
},
{
"epoch": 0.19,
"learning_rate": 1.8737445428584456e-05,
"loss": 1.309,
"step": 142
},
{
"epoch": 0.19,
"learning_rate": 1.8716604700327516e-05,
"loss": 1.303,
"step": 143
},
{
"epoch": 0.19,
"learning_rate": 1.8695605157330398e-05,
"loss": 1.3137,
"step": 144
},
{
"epoch": 0.19,
"learning_rate": 1.8674447182200457e-05,
"loss": 1.2694,
"step": 145
},
{
"epoch": 0.19,
"learning_rate": 1.8653131160431622e-05,
"loss": 1.3115,
"step": 146
},
{
"epoch": 0.19,
"learning_rate": 1.863165748039743e-05,
"loss": 1.3306,
"step": 147
},
{
"epoch": 0.19,
"learning_rate": 1.861002653334389e-05,
"loss": 1.3016,
"step": 148
},
{
"epoch": 0.2,
"learning_rate": 1.85882387133824e-05,
"loss": 1.2957,
"step": 149
},
{
"epoch": 0.2,
"learning_rate": 1.8566294417482552e-05,
"loss": 1.2838,
"step": 150
},
{
"epoch": 0.2,
"learning_rate": 1.8544194045464888e-05,
"loss": 1.2714,
"step": 151
},
{
"epoch": 0.2,
"learning_rate": 1.8521937999993627e-05,
"loss": 1.2949,
"step": 152
},
{
"epoch": 0.2,
"learning_rate": 1.849952668656933e-05,
"loss": 1.2796,
"step": 153
},
{
"epoch": 0.2,
"learning_rate": 1.847696051352151e-05,
"loss": 1.2714,
"step": 154
},
{
"epoch": 0.2,
"learning_rate": 1.845423989200118e-05,
"loss": 1.2807,
"step": 155
},
{
"epoch": 0.21,
"learning_rate": 1.8431365235973383e-05,
"loss": 1.2791,
"step": 156
},
{
"epoch": 0.21,
"learning_rate": 1.840833696220963e-05,
"loss": 1.3286,
"step": 157
},
{
"epoch": 0.21,
"learning_rate": 1.8385155490280327e-05,
"loss": 1.2965,
"step": 158
},
{
"epoch": 0.21,
"learning_rate": 1.836182124254711e-05,
"loss": 1.2916,
"step": 159
},
{
"epoch": 0.21,
"learning_rate": 1.833833464415516e-05,
"loss": 1.2897,
"step": 160
},
{
"epoch": 0.21,
"learning_rate": 1.8314696123025456e-05,
"loss": 1.2973,
"step": 161
},
{
"epoch": 0.21,
"learning_rate": 1.8290906109846974e-05,
"loss": 1.3001,
"step": 162
},
{
"epoch": 0.21,
"learning_rate": 1.8266965038068856e-05,
"loss": 1.2569,
"step": 163
},
{
"epoch": 0.22,
"learning_rate": 1.8242873343892494e-05,
"loss": 1.2652,
"step": 164
},
{
"epoch": 0.22,
"learning_rate": 1.8218631466263584e-05,
"loss": 1.2796,
"step": 165
},
{
"epoch": 0.22,
"learning_rate": 1.8194239846864133e-05,
"loss": 1.2463,
"step": 166
},
{
"epoch": 0.22,
"learning_rate": 1.816969893010442e-05,
"loss": 1.2678,
"step": 167
},
{
"epoch": 0.22,
"learning_rate": 1.8145009163114894e-05,
"loss": 1.2939,
"step": 168
},
{
"epoch": 0.22,
"learning_rate": 1.812017099573801e-05,
"loss": 1.3116,
"step": 169
},
{
"epoch": 0.22,
"learning_rate": 1.8095184880520058e-05,
"loss": 1.2601,
"step": 170
},
{
"epoch": 0.23,
"learning_rate": 1.8070051272702905e-05,
"loss": 1.2895,
"step": 171
},
{
"epoch": 0.23,
"learning_rate": 1.8044770630215706e-05,
"loss": 1.2686,
"step": 172
},
{
"epoch": 0.23,
"learning_rate": 1.801934341366655e-05,
"loss": 1.3025,
"step": 173
},
{
"epoch": 0.23,
"learning_rate": 1.7993770086334082e-05,
"loss": 1.2832,
"step": 174
},
{
"epoch": 0.23,
"learning_rate": 1.7968051114159046e-05,
"loss": 1.3023,
"step": 175
},
{
"epoch": 0.23,
"learning_rate": 1.794218696573582e-05,
"loss": 1.2325,
"step": 176
},
{
"epoch": 0.23,
"learning_rate": 1.791617811230385e-05,
"loss": 1.267,
"step": 177
},
{
"epoch": 0.23,
"learning_rate": 1.7890025027739084e-05,
"loss": 1.2639,
"step": 178
},
{
"epoch": 0.24,
"learning_rate": 1.7863728188545326e-05,
"loss": 1.2909,
"step": 179
},
{
"epoch": 0.24,
"learning_rate": 1.7837288073845566e-05,
"loss": 1.2805,
"step": 180
},
{
"epoch": 0.24,
"learning_rate": 1.7810705165373245e-05,
"loss": 1.2607,
"step": 181
},
{
"epoch": 0.24,
"learning_rate": 1.778397994746347e-05,
"loss": 1.2688,
"step": 182
},
{
"epoch": 0.24,
"learning_rate": 1.77571129070442e-05,
"loss": 1.282,
"step": 183
},
{
"epoch": 0.24,
"learning_rate": 1.773010453362737e-05,
"loss": 1.2594,
"step": 184
},
{
"epoch": 0.24,
"learning_rate": 1.770295531929998e-05,
"loss": 1.2496,
"step": 185
},
{
"epoch": 0.25,
"learning_rate": 1.767566575871511e-05,
"loss": 1.2712,
"step": 186
},
{
"epoch": 0.25,
"learning_rate": 1.7648236349082928e-05,
"loss": 1.2908,
"step": 187
},
{
"epoch": 0.25,
"learning_rate": 1.7620667590161626e-05,
"loss": 1.3051,
"step": 188
},
{
"epoch": 0.25,
"learning_rate": 1.75929599842483e-05,
"loss": 1.2698,
"step": 189
},
{
"epoch": 0.25,
"learning_rate": 1.756511403616982e-05,
"loss": 1.2813,
"step": 190
},
{
"epoch": 0.25,
"learning_rate": 1.7537130253273613e-05,
"loss": 1.2748,
"step": 191
},
{
"epoch": 0.25,
"learning_rate": 1.750900914541844e-05,
"loss": 1.292,
"step": 192
},
{
"epoch": 0.25,
"learning_rate": 1.7480751224965083e-05,
"loss": 1.2547,
"step": 193
},
{
"epoch": 0.26,
"learning_rate": 1.7452357006767026e-05,
"loss": 1.2556,
"step": 194
},
{
"epoch": 0.26,
"learning_rate": 1.742382700816107e-05,
"loss": 1.2535,
"step": 195
},
{
"epoch": 0.26,
"learning_rate": 1.7395161748957905e-05,
"loss": 1.264,
"step": 196
},
{
"epoch": 0.26,
"learning_rate": 1.7366361751432645e-05,
"loss": 1.2801,
"step": 197
},
{
"epoch": 0.26,
"learning_rate": 1.7337427540315305e-05,
"loss": 1.2835,
"step": 198
},
{
"epoch": 0.26,
"learning_rate": 1.730835964278124e-05,
"loss": 1.2559,
"step": 199
},
{
"epoch": 0.26,
"learning_rate": 1.7279158588441558e-05,
"loss": 1.2278,
"step": 200
},
{
"epoch": 0.26,
"learning_rate": 1.7249824909333445e-05,
"loss": 1.2496,
"step": 201
},
{
"epoch": 0.27,
"learning_rate": 1.722035913991048e-05,
"loss": 1.2728,
"step": 202
},
{
"epoch": 0.27,
"learning_rate": 1.719076181703291e-05,
"loss": 1.2566,
"step": 203
},
{
"epoch": 0.27,
"learning_rate": 1.716103347995785e-05,
"loss": 1.2786,
"step": 204
},
{
"epoch": 0.27,
"learning_rate": 1.713117467032948e-05,
"loss": 1.2873,
"step": 205
},
{
"epoch": 0.27,
"learning_rate": 1.7101185932169147e-05,
"loss": 1.2745,
"step": 206
},
{
"epoch": 0.27,
"learning_rate": 1.7071067811865477e-05,
"loss": 1.249,
"step": 207
},
{
"epoch": 0.27,
"learning_rate": 1.7040820858164413e-05,
"loss": 1.2347,
"step": 208
},
{
"epoch": 0.28,
"learning_rate": 1.7010445622159214e-05,
"loss": 1.2614,
"step": 209
},
{
"epoch": 0.28,
"learning_rate": 1.6979942657280414e-05,
"loss": 1.2607,
"step": 210
},
{
"epoch": 0.28,
"learning_rate": 1.694931251928575e-05,
"loss": 1.2215,
"step": 211
},
{
"epoch": 0.28,
"learning_rate": 1.691855576625001e-05,
"loss": 1.2279,
"step": 212
},
{
"epoch": 0.28,
"learning_rate": 1.68876729585549e-05,
"loss": 1.2378,
"step": 213
},
{
"epoch": 0.28,
"learning_rate": 1.6856664658878797e-05,
"loss": 1.2437,
"step": 214
},
{
"epoch": 0.28,
"learning_rate": 1.6825531432186545e-05,
"loss": 1.2671,
"step": 215
},
{
"epoch": 0.28,
"learning_rate": 1.6794273845719096e-05,
"loss": 1.251,
"step": 216
},
{
"epoch": 0.29,
"learning_rate": 1.6762892468983237e-05,
"loss": 1.2588,
"step": 217
},
{
"epoch": 0.29,
"learning_rate": 1.673138787374119e-05,
"loss": 1.2078,
"step": 218
},
{
"epoch": 0.29,
"learning_rate": 1.6699760634000166e-05,
"loss": 1.2534,
"step": 219
},
{
"epoch": 0.29,
"learning_rate": 1.6668011326001962e-05,
"loss": 1.2941,
"step": 220
},
{
"epoch": 0.29,
"learning_rate": 1.6636140528212427e-05,
"loss": 1.2867,
"step": 221
},
{
"epoch": 0.29,
"learning_rate": 1.6604148821310912e-05,
"loss": 1.2647,
"step": 222
},
{
"epoch": 0.29,
"learning_rate": 1.6572036788179728e-05,
"loss": 1.2414,
"step": 223
},
{
"epoch": 0.3,
"learning_rate": 1.6539805013893493e-05,
"loss": 1.2572,
"step": 224
},
{
"epoch": 0.3,
"learning_rate": 1.650745408570849e-05,
"loss": 1.195,
"step": 225
},
{
"epoch": 0.3,
"learning_rate": 1.6474984593051965e-05,
"loss": 1.2229,
"step": 226
},
{
"epoch": 0.3,
"learning_rate": 1.6442397127511366e-05,
"loss": 1.2675,
"step": 227
},
{
"epoch": 0.3,
"learning_rate": 1.6409692282823604e-05,
"loss": 1.2349,
"step": 228
},
{
"epoch": 0.3,
"learning_rate": 1.63768706548642e-05,
"loss": 1.2357,
"step": 229
},
{
"epoch": 0.3,
"learning_rate": 1.6343932841636455e-05,
"loss": 1.2307,
"step": 230
},
{
"epoch": 0.3,
"learning_rate": 1.631087944326053e-05,
"loss": 1.2892,
"step": 231
},
{
"epoch": 0.31,
"learning_rate": 1.6277711061962525e-05,
"loss": 1.2696,
"step": 232
},
{
"epoch": 0.31,
"learning_rate": 1.6244428302063506e-05,
"loss": 1.2858,
"step": 233
},
{
"epoch": 0.31,
"learning_rate": 1.6211031769968503e-05,
"loss": 1.2654,
"step": 234
},
{
"epoch": 0.31,
"learning_rate": 1.6177522074155436e-05,
"loss": 1.274,
"step": 235
},
{
"epoch": 0.31,
"learning_rate": 1.6143899825164058e-05,
"loss": 1.255,
"step": 236
},
{
"epoch": 0.31,
"learning_rate": 1.6110165635584807e-05,
"loss": 1.2317,
"step": 237
},
{
"epoch": 0.31,
"learning_rate": 1.6076320120047667e-05,
"loss": 1.2737,
"step": 238
},
{
"epoch": 0.31,
"learning_rate": 1.6042363895210948e-05,
"loss": 1.2599,
"step": 239
},
{
"epoch": 0.32,
"learning_rate": 1.6008297579750063e-05,
"loss": 1.2414,
"step": 240
},
{
"epoch": 0.32,
"learning_rate": 1.597412179434626e-05,
"loss": 1.2389,
"step": 241
},
{
"epoch": 0.32,
"learning_rate": 1.5939837161675297e-05,
"loss": 1.2738,
"step": 242
},
{
"epoch": 0.32,
"learning_rate": 1.590544430639611e-05,
"loss": 1.2611,
"step": 243
},
{
"epoch": 0.32,
"learning_rate": 1.5870943855139437e-05,
"loss": 1.2908,
"step": 244
},
{
"epoch": 0.32,
"learning_rate": 1.5836336436496377e-05,
"loss": 1.2377,
"step": 245
},
{
"epoch": 0.32,
"learning_rate": 1.5801622681006966e-05,
"loss": 1.2655,
"step": 246
},
{
"epoch": 0.33,
"learning_rate": 1.5766803221148676e-05,
"loss": 1.2419,
"step": 247
},
{
"epoch": 0.33,
"learning_rate": 1.5731878691324874e-05,
"loss": 1.2521,
"step": 248
},
{
"epoch": 0.33,
"learning_rate": 1.5696849727853297e-05,
"loss": 1.2574,
"step": 249
},
{
"epoch": 0.33,
"learning_rate": 1.5661716968954436e-05,
"loss": 1.2392,
"step": 250
},
{
"epoch": 0.33,
"learning_rate": 1.5626481054739916e-05,
"loss": 1.2319,
"step": 251
},
{
"epoch": 0.33,
"learning_rate": 1.5591142627200825e-05,
"loss": 1.2687,
"step": 252
},
{
"epoch": 0.33,
"learning_rate": 1.5555702330196024e-05,
"loss": 1.2643,
"step": 253
},
{
"epoch": 0.33,
"learning_rate": 1.552016080944042e-05,
"loss": 1.2178,
"step": 254
},
{
"epoch": 0.34,
"learning_rate": 1.5484518712493188e-05,
"loss": 1.2774,
"step": 255
},
{
"epoch": 0.34,
"learning_rate": 1.544877668874599e-05,
"loss": 1.2382,
"step": 256
},
{
"epoch": 0.34,
"learning_rate": 1.5412935389411124e-05,
"loss": 1.2719,
"step": 257
},
{
"epoch": 0.34,
"learning_rate": 1.5376995467509673e-05,
"loss": 1.2459,
"step": 258
},
{
"epoch": 0.34,
"learning_rate": 1.5340957577859605e-05,
"loss": 1.2503,
"step": 259
},
{
"epoch": 0.34,
"learning_rate": 1.530482237706383e-05,
"loss": 1.2523,
"step": 260
},
{
"epoch": 0.34,
"learning_rate": 1.526859052349827e-05,
"loss": 1.2432,
"step": 261
},
{
"epoch": 0.35,
"learning_rate": 1.5232262677299816e-05,
"loss": 1.2565,
"step": 262
},
{
"epoch": 0.35,
"learning_rate": 1.5195839500354337e-05,
"loss": 1.219,
"step": 263
},
{
"epoch": 0.35,
"learning_rate": 1.5159321656284602e-05,
"loss": 1.2263,
"step": 264
},
{
"epoch": 0.35,
"learning_rate": 1.5122709810438205e-05,
"loss": 1.2517,
"step": 265
},
{
"epoch": 0.35,
"learning_rate": 1.5086004629875426e-05,
"loss": 1.2761,
"step": 266
},
{
"epoch": 0.35,
"learning_rate": 1.5049206783357082e-05,
"loss": 1.2597,
"step": 267
},
{
"epoch": 0.35,
"learning_rate": 1.501231694133235e-05,
"loss": 1.2765,
"step": 268
},
{
"epoch": 0.35,
"learning_rate": 1.4975335775926547e-05,
"loss": 1.2937,
"step": 269
},
{
"epoch": 0.36,
"learning_rate": 1.4938263960928878e-05,
"loss": 1.2656,
"step": 270
},
{
"epoch": 0.36,
"learning_rate": 1.4901102171780175e-05,
"loss": 1.2233,
"step": 271
},
{
"epoch": 0.36,
"learning_rate": 1.4863851085560563e-05,
"loss": 1.2493,
"step": 272
},
{
"epoch": 0.36,
"learning_rate": 1.4826511380977155e-05,
"loss": 1.2665,
"step": 273
},
{
"epoch": 0.36,
"learning_rate": 1.478908373835167e-05,
"loss": 1.2582,
"step": 274
},
{
"epoch": 0.36,
"learning_rate": 1.4751568839608036e-05,
"loss": 1.2779,
"step": 275
},
{
"epoch": 0.36,
"learning_rate": 1.4713967368259981e-05,
"loss": 1.2421,
"step": 276
},
{
"epoch": 0.36,
"learning_rate": 1.4676280009398544e-05,
"loss": 1.232,
"step": 277
},
{
"epoch": 0.37,
"learning_rate": 1.4638507449679642e-05,
"loss": 1.2347,
"step": 278
},
{
"epoch": 0.37,
"learning_rate": 1.4600650377311523e-05,
"loss": 1.2076,
"step": 279
},
{
"epoch": 0.37,
"learning_rate": 1.4562709482042237e-05,
"loss": 1.2774,
"step": 280
},
{
"epoch": 0.37,
"learning_rate": 1.4524685455147071e-05,
"loss": 1.221,
"step": 281
},
{
"epoch": 0.37,
"learning_rate": 1.448657898941596e-05,
"loss": 1.2758,
"step": 282
},
{
"epoch": 0.37,
"learning_rate": 1.4448390779140844e-05,
"loss": 1.2019,
"step": 283
},
{
"epoch": 0.37,
"learning_rate": 1.4410121520103045e-05,
"loss": 1.2473,
"step": 284
},
{
"epoch": 0.38,
"learning_rate": 1.4371771909560566e-05,
"loss": 1.2239,
"step": 285
},
{
"epoch": 0.38,
"learning_rate": 1.4333342646235407e-05,
"loss": 1.2389,
"step": 286
},
{
"epoch": 0.38,
"learning_rate": 1.4294834430300822e-05,
"loss": 1.2811,
"step": 287
},
{
"epoch": 0.38,
"learning_rate": 1.425624796336856e-05,
"loss": 1.2226,
"step": 288
},
{
"epoch": 0.38,
"learning_rate": 1.4217583948476094e-05,
"loss": 1.2374,
"step": 289
},
{
"epoch": 0.38,
"learning_rate": 1.4178843090073802e-05,
"loss": 1.2145,
"step": 290
},
{
"epoch": 0.38,
"learning_rate": 1.4140026094012136e-05,
"loss": 1.2324,
"step": 291
},
{
"epoch": 0.38,
"learning_rate": 1.4101133667528761e-05,
"loss": 1.2144,
"step": 292
},
{
"epoch": 0.39,
"learning_rate": 1.4062166519235665e-05,
"loss": 1.2395,
"step": 293
},
{
"epoch": 0.39,
"learning_rate": 1.4023125359106253e-05,
"loss": 1.2463,
"step": 294
},
{
"epoch": 0.39,
"learning_rate": 1.3984010898462417e-05,
"loss": 1.2726,
"step": 295
},
{
"epoch": 0.39,
"learning_rate": 1.3944823849961557e-05,
"loss": 1.2394,
"step": 296
},
{
"epoch": 0.39,
"learning_rate": 1.3905564927583625e-05,
"loss": 1.2473,
"step": 297
},
{
"epoch": 0.39,
"learning_rate": 1.3866234846618083e-05,
"loss": 1.2524,
"step": 298
},
{
"epoch": 0.39,
"learning_rate": 1.3826834323650899e-05,
"loss": 1.2286,
"step": 299
},
{
"epoch": 0.4,
"learning_rate": 1.3787364076551478e-05,
"loss": 1.2528,
"step": 300
},
{
"epoch": 0.4,
"learning_rate": 1.3747824824459577e-05,
"loss": 1.2363,
"step": 301
},
{
"epoch": 0.4,
"learning_rate": 1.3708217287772227e-05,
"loss": 1.2293,
"step": 302
},
{
"epoch": 0.4,
"learning_rate": 1.3668542188130567e-05,
"loss": 1.2363,
"step": 303
},
{
"epoch": 0.4,
"learning_rate": 1.3628800248406738e-05,
"loss": 1.2268,
"step": 304
},
{
"epoch": 0.4,
"learning_rate": 1.3588992192690683e-05,
"loss": 1.2158,
"step": 305
},
{
"epoch": 0.4,
"learning_rate": 1.3549118746276968e-05,
"loss": 1.2529,
"step": 306
},
{
"epoch": 0.4,
"learning_rate": 1.350918063565157e-05,
"loss": 1.2637,
"step": 307
},
{
"epoch": 0.41,
"learning_rate": 1.3469178588478621e-05,
"loss": 1.25,
"step": 308
},
{
"epoch": 0.41,
"learning_rate": 1.3429113333587181e-05,
"loss": 1.2452,
"step": 309
},
{
"epoch": 0.41,
"learning_rate": 1.3388985600957922e-05,
"loss": 1.2186,
"step": 310
},
{
"epoch": 0.41,
"learning_rate": 1.3348796121709862e-05,
"loss": 1.2639,
"step": 311
},
{
"epoch": 0.41,
"learning_rate": 1.3308545628087029e-05,
"loss": 1.253,
"step": 312
},
{
"epoch": 0.41,
"learning_rate": 1.3268234853445113e-05,
"loss": 1.242,
"step": 313
},
{
"epoch": 0.41,
"learning_rate": 1.3227864532238113e-05,
"loss": 1.2593,
"step": 314
},
{
"epoch": 0.41,
"learning_rate": 1.318743540000496e-05,
"loss": 1.2187,
"step": 315
},
{
"epoch": 0.42,
"learning_rate": 1.3146948193356105e-05,
"loss": 1.2392,
"step": 316
},
{
"epoch": 0.42,
"learning_rate": 1.3106403649960109e-05,
"loss": 1.2819,
"step": 317
},
{
"epoch": 0.42,
"learning_rate": 1.3065802508530186e-05,
"loss": 1.2638,
"step": 318
},
{
"epoch": 0.42,
"learning_rate": 1.302514550881076e-05,
"loss": 1.2472,
"step": 319
},
{
"epoch": 0.42,
"learning_rate": 1.2984433391563984e-05,
"loss": 1.2181,
"step": 320
},
{
"epoch": 0.42,
"learning_rate": 1.294366689855624e-05,
"loss": 1.2298,
"step": 321
},
{
"epoch": 0.42,
"learning_rate": 1.2902846772544625e-05,
"loss": 1.2335,
"step": 322
},
{
"epoch": 0.43,
"learning_rate": 1.2861973757263416e-05,
"loss": 1.2078,
"step": 323
},
{
"epoch": 0.43,
"learning_rate": 1.282104859741052e-05,
"loss": 1.2237,
"step": 324
},
{
"epoch": 0.43,
"learning_rate": 1.2780072038633913e-05,
"loss": 1.2552,
"step": 325
},
{
"epoch": 0.43,
"learning_rate": 1.2739044827518043e-05,
"loss": 1.2443,
"step": 326
},
{
"epoch": 0.43,
"learning_rate": 1.2697967711570243e-05,
"loss": 1.2096,
"step": 327
},
{
"epoch": 0.43,
"learning_rate": 1.2656841439207093e-05,
"loss": 1.2598,
"step": 328
},
{
"epoch": 0.43,
"learning_rate": 1.2615666759740788e-05,
"loss": 1.2469,
"step": 329
},
{
"epoch": 0.43,
"learning_rate": 1.2574444423365503e-05,
"loss": 1.2612,
"step": 330
},
{
"epoch": 0.44,
"learning_rate": 1.2533175181143704e-05,
"loss": 1.2247,
"step": 331
},
{
"epoch": 0.44,
"learning_rate": 1.2491859784992477e-05,
"loss": 1.2132,
"step": 332
},
{
"epoch": 0.44,
"learning_rate": 1.245049898766982e-05,
"loss": 1.2206,
"step": 333
},
{
"epoch": 0.44,
"learning_rate": 1.2409093542760925e-05,
"loss": 1.2533,
"step": 334
},
{
"epoch": 0.44,
"learning_rate": 1.2367644204664468e-05,
"loss": 1.2584,
"step": 335
},
{
"epoch": 0.44,
"learning_rate": 1.2326151728578839e-05,
"loss": 1.2136,
"step": 336
},
{
"epoch": 0.44,
"learning_rate": 1.228461687048839e-05,
"loss": 1.2554,
"step": 337
},
{
"epoch": 0.45,
"learning_rate": 1.2243040387149682e-05,
"loss": 1.2313,
"step": 338
},
{
"epoch": 0.45,
"learning_rate": 1.2201423036077657e-05,
"loss": 1.2444,
"step": 339
},
{
"epoch": 0.45,
"learning_rate": 1.2159765575531877e-05,
"loss": 1.2384,
"step": 340
},
{
"epoch": 0.45,
"learning_rate": 1.2118068764502677e-05,
"loss": 1.2357,
"step": 341
},
{
"epoch": 0.45,
"learning_rate": 1.2076333362697358e-05,
"loss": 1.2348,
"step": 342
},
{
"epoch": 0.45,
"learning_rate": 1.2034560130526341e-05,
"loss": 1.2197,
"step": 343
},
{
"epoch": 0.45,
"learning_rate": 1.199274982908929e-05,
"loss": 1.2181,
"step": 344
},
{
"epoch": 0.45,
"learning_rate": 1.1950903220161286e-05,
"loss": 1.236,
"step": 345
},
{
"epoch": 0.46,
"learning_rate": 1.1909021066178906e-05,
"loss": 1.2416,
"step": 346
},
{
"epoch": 0.46,
"learning_rate": 1.1867104130226363e-05,
"loss": 1.2631,
"step": 347
},
{
"epoch": 0.46,
"learning_rate": 1.1825153176021591e-05,
"loss": 1.2359,
"step": 348
},
{
"epoch": 0.46,
"learning_rate": 1.1783168967902314e-05,
"loss": 1.2483,
"step": 349
},
{
"epoch": 0.46,
"learning_rate": 1.1741152270812155e-05,
"loss": 1.2347,
"step": 350
},
{
"epoch": 0.46,
"learning_rate": 1.1699103850286668e-05,
"loss": 1.2457,
"step": 351
},
{
"epoch": 0.46,
"learning_rate": 1.1657024472439402e-05,
"loss": 1.243,
"step": 352
},
{
"epoch": 0.47,
"learning_rate": 1.1614914903947952e-05,
"loss": 1.2467,
"step": 353
},
{
"epoch": 0.47,
"learning_rate": 1.157277591203996e-05,
"loss": 1.254,
"step": 354
},
{
"epoch": 0.47,
"learning_rate": 1.153060826447918e-05,
"loss": 1.242,
"step": 355
},
{
"epoch": 0.47,
"learning_rate": 1.1488412729551449e-05,
"loss": 1.2393,
"step": 356
},
{
"epoch": 0.47,
"learning_rate": 1.144619007605071e-05,
"loss": 1.2137,
"step": 357
},
{
"epoch": 0.47,
"learning_rate": 1.1403941073265014e-05,
"loss": 1.2508,
"step": 358
},
{
"epoch": 0.47,
"learning_rate": 1.1361666490962468e-05,
"loss": 1.2404,
"step": 359
},
{
"epoch": 0.47,
"learning_rate": 1.1319367099377248e-05,
"loss": 1.2699,
"step": 360
},
{
"epoch": 0.48,
"learning_rate": 1.1277043669195549e-05,
"loss": 1.2087,
"step": 361
},
{
"epoch": 0.48,
"learning_rate": 1.1234696971541534e-05,
"loss": 1.2189,
"step": 362
},
{
"epoch": 0.48,
"learning_rate": 1.1192327777963313e-05,
"loss": 1.2292,
"step": 363
},
{
"epoch": 0.48,
"learning_rate": 1.1149936860418846e-05,
"loss": 1.2429,
"step": 364
},
{
"epoch": 0.48,
"learning_rate": 1.1107524991261913e-05,
"loss": 1.2296,
"step": 365
},
{
"epoch": 0.48,
"learning_rate": 1.1065092943228024e-05,
"loss": 1.2658,
"step": 366
},
{
"epoch": 0.48,
"learning_rate": 1.1022641489420342e-05,
"loss": 1.2367,
"step": 367
},
{
"epoch": 0.48,
"learning_rate": 1.098017140329561e-05,
"loss": 1.2268,
"step": 368
},
{
"epoch": 0.49,
"learning_rate": 1.0937683458650029e-05,
"loss": 1.2717,
"step": 369
},
{
"epoch": 0.49,
"learning_rate": 1.0895178429605189e-05,
"loss": 1.2409,
"step": 370
},
{
"epoch": 0.49,
"learning_rate": 1.0852657090593961e-05,
"loss": 1.2242,
"step": 371
},
{
"epoch": 0.49,
"learning_rate": 1.0810120216346368e-05,
"loss": 1.2232,
"step": 372
},
{
"epoch": 0.49,
"learning_rate": 1.0767568581875494e-05,
"loss": 1.2814,
"step": 373
},
{
"epoch": 0.49,
"learning_rate": 1.072500296246334e-05,
"loss": 1.2448,
"step": 374
},
{
"epoch": 0.49,
"learning_rate": 1.0682424133646712e-05,
"loss": 1.2454,
"step": 375
},
{
"epoch": 0.5,
"learning_rate": 1.0639832871203094e-05,
"loss": 1.2136,
"step": 376
},
{
"epoch": 0.5,
"learning_rate": 1.0597229951136498e-05,
"loss": 1.222,
"step": 377
},
{
"epoch": 0.5,
"learning_rate": 1.0554616149663355e-05,
"loss": 1.2472,
"step": 378
},
{
"epoch": 0.5,
"learning_rate": 1.0511992243198335e-05,
"loss": 1.2139,
"step": 379
},
{
"epoch": 0.5,
"learning_rate": 1.0469359008340216e-05,
"loss": 1.2283,
"step": 380
},
{
"epoch": 0.5,
"learning_rate": 1.0426717221857756e-05,
"loss": 1.2242,
"step": 381
},
{
"epoch": 0.5,
"learning_rate": 1.0384067660675508e-05,
"loss": 1.2512,
"step": 382
},
{
"epoch": 0.5,
"learning_rate": 1.034141110185968e-05,
"loss": 1.2419,
"step": 383
},
{
"epoch": 0.51,
"learning_rate": 1.0298748322603982e-05,
"loss": 1.2473,
"step": 384
},
{
"epoch": 0.51,
"learning_rate": 1.0256080100215448e-05,
"loss": 1.2309,
"step": 385
},
{
"epoch": 0.51,
"learning_rate": 1.0213407212100296e-05,
"loss": 1.2165,
"step": 386
},
{
"epoch": 0.51,
"learning_rate": 1.017073043574975e-05,
"loss": 1.2257,
"step": 387
},
{
"epoch": 0.51,
"learning_rate": 1.0128050548725865e-05,
"loss": 1.2333,
"step": 388
},
{
"epoch": 0.51,
"learning_rate": 1.0085368328647395e-05,
"loss": 1.1892,
"step": 389
},
{
"epoch": 0.51,
"learning_rate": 1.0042684553175575e-05,
"loss": 1.221,
"step": 390
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.2375,
"step": 391
},
{
"epoch": 0.52,
"learning_rate": 9.957315446824425e-06,
"loss": 1.2177,
"step": 392
},
{
"epoch": 0.52,
"learning_rate": 9.91463167135261e-06,
"loss": 1.2274,
"step": 393
},
{
"epoch": 0.52,
"learning_rate": 9.871949451274137e-06,
"loss": 1.2043,
"step": 394
},
{
"epoch": 0.52,
"learning_rate": 9.829269564250254e-06,
"loss": 1.2204,
"step": 395
},
{
"epoch": 0.52,
"learning_rate": 9.786592787899707e-06,
"loss": 1.2835,
"step": 396
},
{
"epoch": 0.52,
"learning_rate": 9.743919899784555e-06,
"loss": 1.2021,
"step": 397
},
{
"epoch": 0.52,
"learning_rate": 9.701251677396021e-06,
"loss": 1.2067,
"step": 398
},
{
"epoch": 0.53,
"learning_rate": 9.658588898140322e-06,
"loss": 1.2337,
"step": 399
},
{
"epoch": 0.53,
"learning_rate": 9.615932339324497e-06,
"loss": 1.2177,
"step": 400
},
{
"epoch": 0.53,
"learning_rate": 9.573282778142246e-06,
"loss": 1.2336,
"step": 401
},
{
"epoch": 0.53,
"learning_rate": 9.530640991659785e-06,
"loss": 1.227,
"step": 402
},
{
"epoch": 0.53,
"learning_rate": 9.488007756801672e-06,
"loss": 1.2225,
"step": 403
},
{
"epoch": 0.53,
"learning_rate": 9.445383850336648e-06,
"loss": 1.2252,
"step": 404
},
{
"epoch": 0.53,
"learning_rate": 9.402770048863502e-06,
"loss": 1.1976,
"step": 405
},
{
"epoch": 0.53,
"learning_rate": 9.360167128796913e-06,
"loss": 1.2518,
"step": 406
},
{
"epoch": 0.54,
"learning_rate": 9.317575866353293e-06,
"loss": 1.2183,
"step": 407
},
{
"epoch": 0.54,
"learning_rate": 9.274997037536663e-06,
"loss": 1.2364,
"step": 408
},
{
"epoch": 0.54,
"learning_rate": 9.232431418124507e-06,
"loss": 1.2687,
"step": 409
},
{
"epoch": 0.54,
"learning_rate": 9.189879783653633e-06,
"loss": 1.2287,
"step": 410
},
{
"epoch": 0.54,
"learning_rate": 9.14734290940604e-06,
"loss": 1.2357,
"step": 411
},
{
"epoch": 0.54,
"learning_rate": 9.104821570394811e-06,
"loss": 1.2428,
"step": 412
},
{
"epoch": 0.54,
"learning_rate": 9.062316541349978e-06,
"loss": 1.2327,
"step": 413
},
{
"epoch": 0.55,
"learning_rate": 9.019828596704394e-06,
"loss": 1.2187,
"step": 414
},
{
"epoch": 0.55,
"learning_rate": 8.977358510579658e-06,
"loss": 1.2402,
"step": 415
},
{
"epoch": 0.55,
"learning_rate": 8.93490705677198e-06,
"loss": 1.2443,
"step": 416
},
{
"epoch": 0.55,
"learning_rate": 8.89247500873809e-06,
"loss": 1.2737,
"step": 417
},
{
"epoch": 0.55,
"learning_rate": 8.850063139581156e-06,
"loss": 1.2073,
"step": 418
},
{
"epoch": 0.55,
"learning_rate": 8.807672222036692e-06,
"loss": 1.2182,
"step": 419
},
{
"epoch": 0.55,
"learning_rate": 8.765303028458468e-06,
"loss": 1.2306,
"step": 420
},
{
"epoch": 0.55,
"learning_rate": 8.722956330804456e-06,
"loss": 1.2609,
"step": 421
},
{
"epoch": 0.56,
"learning_rate": 8.680632900622752e-06,
"loss": 1.1832,
"step": 422
},
{
"epoch": 0.56,
"learning_rate": 8.638333509037537e-06,
"loss": 1.2261,
"step": 423
},
{
"epoch": 0.56,
"learning_rate": 8.59605892673499e-06,
"loss": 1.2133,
"step": 424
},
{
"epoch": 0.56,
"learning_rate": 8.55380992394929e-06,
"loss": 1.2271,
"step": 425
},
{
"epoch": 0.56,
"learning_rate": 8.511587270448556e-06,
"loss": 1.2241,
"step": 426
},
{
"epoch": 0.56,
"learning_rate": 8.469391735520824e-06,
"loss": 1.2091,
"step": 427
},
{
"epoch": 0.56,
"learning_rate": 8.42722408796004e-06,
"loss": 1.247,
"step": 428
},
{
"epoch": 0.57,
"learning_rate": 8.385085096052053e-06,
"loss": 1.2601,
"step": 429
},
{
"epoch": 0.57,
"learning_rate": 8.342975527560601e-06,
"loss": 1.2767,
"step": 430
},
{
"epoch": 0.57,
"learning_rate": 8.300896149713334e-06,
"loss": 1.2175,
"step": 431
},
{
"epoch": 0.57,
"learning_rate": 8.258847729187845e-06,
"loss": 1.2192,
"step": 432
},
{
"epoch": 0.57,
"learning_rate": 8.216831032097689e-06,
"loss": 1.2512,
"step": 433
},
{
"epoch": 0.57,
"learning_rate": 8.174846823978412e-06,
"loss": 1.2384,
"step": 434
},
{
"epoch": 0.57,
"learning_rate": 8.132895869773638e-06,
"loss": 1.2098,
"step": 435
},
{
"epoch": 0.57,
"learning_rate": 8.0909789338211e-06,
"loss": 1.2061,
"step": 436
},
{
"epoch": 0.58,
"learning_rate": 8.04909677983872e-06,
"loss": 1.2013,
"step": 437
},
{
"epoch": 0.58,
"learning_rate": 8.00725017091071e-06,
"loss": 1.1785,
"step": 438
},
{
"epoch": 0.58,
"learning_rate": 7.965439869473664e-06,
"loss": 1.2051,
"step": 439
},
{
"epoch": 0.58,
"learning_rate": 7.923666637302643e-06,
"loss": 1.2502,
"step": 440
},
{
"epoch": 0.58,
"learning_rate": 7.881931235497324e-06,
"loss": 1.1977,
"step": 441
},
{
"epoch": 0.58,
"learning_rate": 7.84023442446813e-06,
"loss": 1.1519,
"step": 442
},
{
"epoch": 0.58,
"learning_rate": 7.798576963922347e-06,
"loss": 1.2102,
"step": 443
},
{
"epoch": 0.58,
"learning_rate": 7.75695961285032e-06,
"loss": 1.2243,
"step": 444
},
{
"epoch": 0.59,
"learning_rate": 7.71538312951161e-06,
"loss": 1.2375,
"step": 445
},
{
"epoch": 0.59,
"learning_rate": 7.673848271421166e-06,
"loss": 1.2186,
"step": 446
},
{
"epoch": 0.59,
"learning_rate": 7.632355795335533e-06,
"loss": 1.2363,
"step": 447
},
{
"epoch": 0.59,
"learning_rate": 7.590906457239073e-06,
"loss": 1.2394,
"step": 448
},
{
"epoch": 0.59,
"learning_rate": 7.549501012330184e-06,
"loss": 1.214,
"step": 449
},
{
"epoch": 0.59,
"learning_rate": 7.508140215007526e-06,
"loss": 1.2012,
"step": 450
},
{
"epoch": 0.59,
"learning_rate": 7.466824818856296e-06,
"loss": 1.2206,
"step": 451
},
{
"epoch": 0.6,
"learning_rate": 7.4255555766345025e-06,
"loss": 1.2179,
"step": 452
},
{
"epoch": 0.6,
"learning_rate": 7.384333240259216e-06,
"loss": 1.2296,
"step": 453
},
{
"epoch": 0.6,
"learning_rate": 7.34315856079291e-06,
"loss": 1.1944,
"step": 454
},
{
"epoch": 0.6,
"learning_rate": 7.3020322884297565e-06,
"loss": 1.2263,
"step": 455
},
{
"epoch": 0.6,
"learning_rate": 7.260955172481959e-06,
"loss": 1.2106,
"step": 456
},
{
"epoch": 0.6,
"learning_rate": 7.219927961366091e-06,
"loss": 1.2275,
"step": 457
},
{
"epoch": 0.6,
"learning_rate": 7.178951402589482e-06,
"loss": 1.1832,
"step": 458
},
{
"epoch": 0.6,
"learning_rate": 7.1380262427365885e-06,
"loss": 1.2118,
"step": 459
},
{
"epoch": 0.61,
"learning_rate": 7.097153227455379e-06,
"loss": 1.2205,
"step": 460
},
{
"epoch": 0.61,
"learning_rate": 7.056333101443761e-06,
"loss": 1.2179,
"step": 461
},
{
"epoch": 0.61,
"learning_rate": 7.01556660843602e-06,
"loss": 1.2121,
"step": 462
},
{
"epoch": 0.61,
"learning_rate": 6.974854491189243e-06,
"loss": 1.2206,
"step": 463
},
{
"epoch": 0.61,
"learning_rate": 6.934197491469818e-06,
"loss": 1.24,
"step": 464
},
{
"epoch": 0.61,
"learning_rate": 6.893596350039896e-06,
"loss": 1.204,
"step": 465
},
{
"epoch": 0.61,
"learning_rate": 6.853051806643898e-06,
"loss": 1.2224,
"step": 466
},
{
"epoch": 0.62,
"learning_rate": 6.812564599995042e-06,
"loss": 1.227,
"step": 467
},
{
"epoch": 0.62,
"learning_rate": 6.772135467761889e-06,
"loss": 1.2361,
"step": 468
},
{
"epoch": 0.62,
"learning_rate": 6.731765146554891e-06,
"loss": 1.2099,
"step": 469
},
{
"epoch": 0.62,
"learning_rate": 6.691454371912974e-06,
"loss": 1.1969,
"step": 470
},
{
"epoch": 0.62,
"learning_rate": 6.651203878290139e-06,
"loss": 1.2269,
"step": 471
},
{
"epoch": 0.62,
"learning_rate": 6.6110143990420824e-06,
"loss": 1.2106,
"step": 472
},
{
"epoch": 0.62,
"learning_rate": 6.570886666412823e-06,
"loss": 1.1969,
"step": 473
},
{
"epoch": 0.62,
"learning_rate": 6.5308214115213785e-06,
"loss": 1.239,
"step": 474
},
{
"epoch": 0.63,
"learning_rate": 6.490819364348434e-06,
"loss": 1.2399,
"step": 475
},
{
"epoch": 0.63,
"learning_rate": 6.450881253723035e-06,
"loss": 1.2265,
"step": 476
},
{
"epoch": 0.63,
"learning_rate": 6.41100780730932e-06,
"loss": 1.2446,
"step": 477
},
{
"epoch": 0.63,
"learning_rate": 6.371199751593264e-06,
"loss": 1.2229,
"step": 478
},
{
"epoch": 0.63,
"learning_rate": 6.331457811869437e-06,
"loss": 1.2036,
"step": 479
},
{
"epoch": 0.63,
"learning_rate": 6.291782712227776e-06,
"loss": 1.2002,
"step": 480
},
{
"epoch": 0.63,
"learning_rate": 6.2521751755404226e-06,
"loss": 1.2262,
"step": 481
},
{
"epoch": 0.63,
"learning_rate": 6.212635923448526e-06,
"loss": 1.2469,
"step": 482
},
{
"epoch": 0.64,
"learning_rate": 6.173165676349103e-06,
"loss": 1.2008,
"step": 483
},
{
"epoch": 0.64,
"learning_rate": 6.133765153381918e-06,
"loss": 1.2352,
"step": 484
},
{
"epoch": 0.64,
"learning_rate": 6.094435072416379e-06,
"loss": 1.2257,
"step": 485
},
{
"epoch": 0.64,
"learning_rate": 6.055176150038445e-06,
"loss": 1.2022,
"step": 486
},
{
"epoch": 0.64,
"learning_rate": 6.015989101537586e-06,
"loss": 1.2565,
"step": 487
},
{
"epoch": 0.64,
"learning_rate": 5.976874640893751e-06,
"loss": 1.2518,
"step": 488
},
{
"epoch": 0.64,
"learning_rate": 5.937833480764339e-06,
"loss": 1.2272,
"step": 489
},
{
"epoch": 0.65,
"learning_rate": 5.898866332471241e-06,
"loss": 1.2077,
"step": 490
},
{
"epoch": 0.65,
"learning_rate": 5.859973905987866e-06,
"loss": 1.2364,
"step": 491
},
{
"epoch": 0.65,
"learning_rate": 5.821156909926202e-06,
"loss": 1.2377,
"step": 492
},
{
"epoch": 0.65,
"learning_rate": 5.782416051523909e-06,
"loss": 1.2399,
"step": 493
},
{
"epoch": 0.65,
"learning_rate": 5.743752036631443e-06,
"loss": 1.192,
"step": 494
},
{
"epoch": 0.65,
"learning_rate": 5.7051655696991825e-06,
"loss": 1.242,
"step": 495
},
{
"epoch": 0.65,
"learning_rate": 5.666657353764594e-06,
"loss": 1.2175,
"step": 496
},
{
"epoch": 0.65,
"learning_rate": 5.628228090439434e-06,
"loss": 1.2376,
"step": 497
},
{
"epoch": 0.66,
"learning_rate": 5.589878479896959e-06,
"loss": 1.2259,
"step": 498
},
{
"epoch": 0.66,
"learning_rate": 5.55160922085916e-06,
"loss": 1.232,
"step": 499
},
{
"epoch": 0.66,
"learning_rate": 5.513421010584044e-06,
"loss": 1.2215,
"step": 500
},
{
"epoch": 0.66,
"learning_rate": 5.4753145448529284e-06,
"loss": 1.2117,
"step": 501
},
{
"epoch": 0.66,
"learning_rate": 5.437290517957767e-06,
"loss": 1.1955,
"step": 502
},
{
"epoch": 0.66,
"learning_rate": 5.399349622688479e-06,
"loss": 1.2329,
"step": 503
},
{
"epoch": 0.66,
"learning_rate": 5.3614925503203586e-06,
"loss": 1.2339,
"step": 504
},
{
"epoch": 0.67,
"learning_rate": 5.323719990601459e-06,
"loss": 1.2062,
"step": 505
},
{
"epoch": 0.67,
"learning_rate": 5.286032631740023e-06,
"loss": 1.2327,
"step": 506
},
{
"epoch": 0.67,
"learning_rate": 5.248431160391963e-06,
"loss": 1.2644,
"step": 507
},
{
"epoch": 0.67,
"learning_rate": 5.2109162616483325e-06,
"loss": 1.194,
"step": 508
},
{
"epoch": 0.67,
"learning_rate": 5.1734886190228496e-06,
"loss": 1.2536,
"step": 509
},
{
"epoch": 0.67,
"learning_rate": 5.136148914439441e-06,
"loss": 1.2289,
"step": 510
},
{
"epoch": 0.67,
"learning_rate": 5.098897828219831e-06,
"loss": 1.2126,
"step": 511
},
{
"epoch": 0.67,
"learning_rate": 5.061736039071124e-06,
"loss": 1.188,
"step": 512
},
{
"epoch": 0.68,
"learning_rate": 5.024664224073454e-06,
"loss": 1.2643,
"step": 513
},
{
"epoch": 0.68,
"learning_rate": 4.987683058667651e-06,
"loss": 1.2361,
"step": 514
},
{
"epoch": 0.68,
"learning_rate": 4.950793216642923e-06,
"loss": 1.2565,
"step": 515
},
{
"epoch": 0.68,
"learning_rate": 4.913995370124578e-06,
"loss": 1.2317,
"step": 516
},
{
"epoch": 0.68,
"learning_rate": 4.877290189561795e-06,
"loss": 1.2132,
"step": 517
},
{
"epoch": 0.68,
"learning_rate": 4.840678343715399e-06,
"loss": 1.214,
"step": 518
},
{
"epoch": 0.68,
"learning_rate": 4.804160499645667e-06,
"loss": 1.2085,
"step": 519
},
{
"epoch": 0.69,
"learning_rate": 4.767737322700185e-06,
"loss": 1.2343,
"step": 520
},
{
"epoch": 0.69,
"learning_rate": 4.7314094765017325e-06,
"loss": 1.2287,
"step": 521
},
{
"epoch": 0.69,
"learning_rate": 4.695177622936169e-06,
"loss": 1.2358,
"step": 522
},
{
"epoch": 0.69,
"learning_rate": 4.659042422140399e-06,
"loss": 1.2439,
"step": 523
},
{
"epoch": 0.69,
"learning_rate": 4.623004532490328e-06,
"loss": 1.2239,
"step": 524
},
{
"epoch": 0.69,
"learning_rate": 4.587064610588881e-06,
"loss": 1.2292,
"step": 525
},
{
"epoch": 0.69,
"learning_rate": 4.551223311254013e-06,
"loss": 1.227,
"step": 526
},
{
"epoch": 0.69,
"learning_rate": 4.515481287506811e-06,
"loss": 1.2171,
"step": 527
},
{
"epoch": 0.7,
"learning_rate": 4.479839190559583e-06,
"loss": 1.2125,
"step": 528
},
{
"epoch": 0.7,
"learning_rate": 4.444297669803981e-06,
"loss": 1.2338,
"step": 529
},
{
"epoch": 0.7,
"learning_rate": 4.408857372799179e-06,
"loss": 1.2236,
"step": 530
},
{
"epoch": 0.7,
"learning_rate": 4.37351894526009e-06,
"loss": 1.2755,
"step": 531
},
{
"epoch": 0.7,
"learning_rate": 4.338283031045567e-06,
"loss": 1.2603,
"step": 532
},
{
"epoch": 0.7,
"learning_rate": 4.303150272146706e-06,
"loss": 1.2462,
"step": 533
},
{
"epoch": 0.7,
"learning_rate": 4.268121308675132e-06,
"loss": 1.2025,
"step": 534
},
{
"epoch": 0.7,
"learning_rate": 4.2331967788513295e-06,
"loss": 1.231,
"step": 535
},
{
"epoch": 0.71,
"learning_rate": 4.198377318993035e-06,
"loss": 1.221,
"step": 536
},
{
"epoch": 0.71,
"learning_rate": 4.1636635635036235e-06,
"loss": 1.2132,
"step": 537
},
{
"epoch": 0.71,
"learning_rate": 4.129056144860567e-06,
"loss": 1.2579,
"step": 538
},
{
"epoch": 0.71,
"learning_rate": 4.094555693603891e-06,
"loss": 1.2362,
"step": 539
},
{
"epoch": 0.71,
"learning_rate": 4.060162838324708e-06,
"loss": 1.2067,
"step": 540
},
{
"epoch": 0.71,
"learning_rate": 4.025878205653747e-06,
"loss": 1.2212,
"step": 541
},
{
"epoch": 0.71,
"learning_rate": 3.991702420249941e-06,
"loss": 1.2176,
"step": 542
},
{
"epoch": 0.72,
"learning_rate": 3.957636104789056e-06,
"loss": 1.2189,
"step": 543
},
{
"epoch": 0.72,
"learning_rate": 3.9236798799523375e-06,
"loss": 1.204,
"step": 544
},
{
"epoch": 0.72,
"learning_rate": 3.8898343644151945e-06,
"loss": 1.2195,
"step": 545
},
{
"epoch": 0.72,
"learning_rate": 3.856100174835945e-06,
"loss": 1.2191,
"step": 546
},
{
"epoch": 0.72,
"learning_rate": 3.822477925844564e-06,
"loss": 1.2254,
"step": 547
},
{
"epoch": 0.72,
"learning_rate": 3.7889682300315e-06,
"loss": 1.2103,
"step": 548
},
{
"epoch": 0.72,
"learning_rate": 3.755571697936493e-06,
"loss": 1.2557,
"step": 549
},
{
"epoch": 0.72,
"learning_rate": 3.722288938037478e-06,
"loss": 1.2157,
"step": 550
},
{
"epoch": 0.73,
"learning_rate": 3.689120556739475e-06,
"loss": 1.2242,
"step": 551
},
{
"epoch": 0.73,
"learning_rate": 3.6560671583635467e-06,
"loss": 1.2322,
"step": 552
},
{
"epoch": 0.73,
"learning_rate": 3.6231293451357994e-06,
"loss": 1.1993,
"step": 553
},
{
"epoch": 0.73,
"learning_rate": 3.590307717176401e-06,
"loss": 1.2278,
"step": 554
},
{
"epoch": 0.73,
"learning_rate": 3.557602872488638e-06,
"loss": 1.2176,
"step": 555
},
{
"epoch": 0.73,
"learning_rate": 3.525015406948039e-06,
"loss": 1.2265,
"step": 556
},
{
"epoch": 0.73,
"learning_rate": 3.492545914291512e-06,
"loss": 1.2085,
"step": 557
},
{
"epoch": 0.74,
"learning_rate": 3.4601949861065086e-06,
"loss": 1.2287,
"step": 558
},
{
"epoch": 0.74,
"learning_rate": 3.4279632118202744e-06,
"loss": 1.2073,
"step": 559
},
{
"epoch": 0.74,
"learning_rate": 3.3958511786890923e-06,
"loss": 1.2092,
"step": 560
},
{
"epoch": 0.74,
"learning_rate": 3.3638594717875807e-06,
"loss": 1.2181,
"step": 561
},
{
"epoch": 0.74,
"learning_rate": 3.33198867399804e-06,
"loss": 1.2126,
"step": 562
},
{
"epoch": 0.74,
"learning_rate": 3.3002393659998357e-06,
"loss": 1.2117,
"step": 563
},
{
"epoch": 0.74,
"learning_rate": 3.2686121262588165e-06,
"loss": 1.2126,
"step": 564
},
{
"epoch": 0.74,
"learning_rate": 3.2371075310167634e-06,
"loss": 1.226,
"step": 565
},
{
"epoch": 0.75,
"learning_rate": 3.205726154280905e-06,
"loss": 1.1847,
"step": 566
},
{
"epoch": 0.75,
"learning_rate": 3.174468567813461e-06,
"loss": 1.2131,
"step": 567
},
{
"epoch": 0.75,
"learning_rate": 3.143335341121202e-06,
"loss": 1.2046,
"step": 568
},
{
"epoch": 0.75,
"learning_rate": 3.1123270414451035e-06,
"loss": 1.2495,
"step": 569
},
{
"epoch": 0.75,
"learning_rate": 3.081444233749994e-06,
"loss": 1.2398,
"step": 570
},
{
"epoch": 0.75,
"learning_rate": 3.050687480714256e-06,
"loss": 1.2245,
"step": 571
},
{
"epoch": 0.75,
"learning_rate": 3.0200573427195877e-06,
"loss": 1.2042,
"step": 572
},
{
"epoch": 0.75,
"learning_rate": 2.9895543778407875e-06,
"loss": 1.2298,
"step": 573
},
{
"epoch": 0.76,
"learning_rate": 2.959179141835591e-06,
"loss": 1.2284,
"step": 574
},
{
"epoch": 0.76,
"learning_rate": 2.9289321881345257e-06,
"loss": 1.2351,
"step": 575
},
{
"epoch": 0.76,
"learning_rate": 2.898814067830855e-06,
"loss": 1.2263,
"step": 576
},
{
"epoch": 0.76,
"learning_rate": 2.868825329670524e-06,
"loss": 1.2225,
"step": 577
},
{
"epoch": 0.76,
"learning_rate": 2.83896652004215e-06,
"loss": 1.2288,
"step": 578
},
{
"epoch": 0.76,
"learning_rate": 2.809238182967092e-06,
"loss": 1.2179,
"step": 579
},
{
"epoch": 0.76,
"learning_rate": 2.779640860089523e-06,
"loss": 1.2299,
"step": 580
},
{
"epoch": 0.77,
"learning_rate": 2.7501750906665603e-06,
"loss": 1.1786,
"step": 581
},
{
"epoch": 0.77,
"learning_rate": 2.7208414115584436e-06,
"loss": 1.229,
"step": 582
},
{
"epoch": 0.77,
"learning_rate": 2.691640357218759e-06,
"loss": 1.2126,
"step": 583
},
{
"epoch": 0.77,
"learning_rate": 2.662572459684699e-06,
"loss": 1.2048,
"step": 584
},
{
"epoch": 0.77,
"learning_rate": 2.6336382485673574e-06,
"loss": 1.2251,
"step": 585
},
{
"epoch": 0.77,
"learning_rate": 2.6048382510420954e-06,
"loss": 1.2086,
"step": 586
},
{
"epoch": 0.77,
"learning_rate": 2.576172991838933e-06,
"loss": 1.2318,
"step": 587
},
{
"epoch": 0.77,
"learning_rate": 2.547642993232976e-06,
"loss": 1.2496,
"step": 588
},
{
"epoch": 0.78,
"learning_rate": 2.519248775034918e-06,
"loss": 1.2442,
"step": 589
},
{
"epoch": 0.78,
"learning_rate": 2.490990854581563e-06,
"loss": 1.2059,
"step": 590
},
{
"epoch": 0.78,
"learning_rate": 2.4628697467263916e-06,
"loss": 1.2276,
"step": 591
},
{
"epoch": 0.78,
"learning_rate": 2.4348859638301857e-06,
"loss": 1.2529,
"step": 592
},
{
"epoch": 0.78,
"learning_rate": 2.4070400157517036e-06,
"loss": 1.209,
"step": 593
},
{
"epoch": 0.78,
"learning_rate": 2.3793324098383796e-06,
"loss": 1.2104,
"step": 594
},
{
"epoch": 0.78,
"learning_rate": 2.351763650917074e-06,
"loss": 1.2115,
"step": 595
},
{
"epoch": 0.79,
"learning_rate": 2.3243342412848923e-06,
"loss": 1.1976,
"step": 596
},
{
"epoch": 0.79,
"learning_rate": 2.2970446807000237e-06,
"loss": 1.225,
"step": 597
},
{
"epoch": 0.79,
"learning_rate": 2.26989546637263e-06,
"loss": 1.226,
"step": 598
},
{
"epoch": 0.79,
"learning_rate": 2.2428870929558012e-06,
"loss": 1.2215,
"step": 599
},
{
"epoch": 0.79,
"learning_rate": 2.2160200525365326e-06,
"loss": 1.2065,
"step": 600
},
{
"epoch": 0.79,
"learning_rate": 2.1892948346267583e-06,
"loss": 1.244,
"step": 601
},
{
"epoch": 0.79,
"learning_rate": 2.1627119261544348e-06,
"loss": 1.2354,
"step": 602
},
{
"epoch": 0.79,
"learning_rate": 2.1362718114546777e-06,
"loss": 1.257,
"step": 603
},
{
"epoch": 0.8,
"learning_rate": 2.109974972260921e-06,
"loss": 1.2592,
"step": 604
},
{
"epoch": 0.8,
"learning_rate": 2.0838218876961524e-06,
"loss": 1.2424,
"step": 605
},
{
"epoch": 0.8,
"learning_rate": 2.057813034264181e-06,
"loss": 1.2211,
"step": 606
},
{
"epoch": 0.8,
"learning_rate": 2.0319488858409552e-06,
"loss": 1.2308,
"step": 607
},
{
"epoch": 0.8,
"learning_rate": 2.0062299136659203e-06,
"loss": 1.2381,
"step": 608
},
{
"epoch": 0.8,
"learning_rate": 1.980656586333449e-06,
"loss": 1.2114,
"step": 609
},
{
"epoch": 0.8,
"learning_rate": 1.955229369784295e-06,
"loss": 1.2086,
"step": 610
},
{
"epoch": 0.8,
"learning_rate": 1.929948727297096e-06,
"loss": 1.2207,
"step": 611
},
{
"epoch": 0.81,
"learning_rate": 1.9048151194799435e-06,
"loss": 1.1851,
"step": 612
},
{
"epoch": 0.81,
"learning_rate": 1.8798290042619949e-06,
"loss": 1.2128,
"step": 613
},
{
"epoch": 0.81,
"learning_rate": 1.8549908368851099e-06,
"loss": 1.2371,
"step": 614
},
{
"epoch": 0.81,
"learning_rate": 1.8303010698955803e-06,
"loss": 1.208,
"step": 615
},
{
"epoch": 0.81,
"learning_rate": 1.8057601531358693e-06,
"loss": 1.2582,
"step": 616
},
{
"epoch": 0.81,
"learning_rate": 1.7813685337364205e-06,
"loss": 1.2378,
"step": 617
},
{
"epoch": 0.81,
"learning_rate": 1.7571266561075073e-06,
"loss": 1.2273,
"step": 618
},
{
"epoch": 0.82,
"learning_rate": 1.7330349619311415e-06,
"loss": 1.2149,
"step": 619
},
{
"epoch": 0.82,
"learning_rate": 1.7090938901530264e-06,
"loss": 1.2558,
"step": 620
},
{
"epoch": 0.82,
"learning_rate": 1.6853038769745466e-06,
"loss": 1.1991,
"step": 621
},
{
"epoch": 0.82,
"learning_rate": 1.6616653558448437e-06,
"loss": 1.2226,
"step": 622
},
{
"epoch": 0.82,
"learning_rate": 1.638178757452894e-06,
"loss": 1.2173,
"step": 623
},
{
"epoch": 0.82,
"learning_rate": 1.614844509719674e-06,
"loss": 1.2116,
"step": 624
},
{
"epoch": 0.82,
"learning_rate": 1.5916630377903696e-06,
"loss": 1.2148,
"step": 625
},
{
"epoch": 0.82,
"learning_rate": 1.5686347640266208e-06,
"loss": 1.1965,
"step": 626
},
{
"epoch": 0.83,
"learning_rate": 1.5457601079988226e-06,
"loss": 1.2602,
"step": 627
},
{
"epoch": 0.83,
"learning_rate": 1.5230394864784925e-06,
"loss": 1.1897,
"step": 628
},
{
"epoch": 0.83,
"learning_rate": 1.5004733134306692e-06,
"loss": 1.2226,
"step": 629
},
{
"epoch": 0.83,
"learning_rate": 1.478062000006375e-06,
"loss": 1.2064,
"step": 630
},
{
"epoch": 0.83,
"learning_rate": 1.4558059545351144e-06,
"loss": 1.217,
"step": 631
},
{
"epoch": 0.83,
"learning_rate": 1.4337055825174506e-06,
"loss": 1.1877,
"step": 632
},
{
"epoch": 0.83,
"learning_rate": 1.4117612866176022e-06,
"loss": 1.2036,
"step": 633
},
{
"epoch": 0.84,
"learning_rate": 1.3899734666561138e-06,
"loss": 1.2212,
"step": 634
},
{
"epoch": 0.84,
"learning_rate": 1.3683425196025734e-06,
"loss": 1.2119,
"step": 635
},
{
"epoch": 0.84,
"learning_rate": 1.3468688395683783e-06,
"loss": 1.2475,
"step": 636
},
{
"epoch": 0.84,
"learning_rate": 1.325552817799547e-06,
"loss": 1.2041,
"step": 637
},
{
"epoch": 0.84,
"learning_rate": 1.3043948426696019e-06,
"loss": 1.2492,
"step": 638
},
{
"epoch": 0.84,
"learning_rate": 1.2833952996724864e-06,
"loss": 1.2403,
"step": 639
},
{
"epoch": 0.84,
"learning_rate": 1.2625545714155474e-06,
"loss": 1.2125,
"step": 640
},
{
"epoch": 0.84,
"learning_rate": 1.24187303761255e-06,
"loss": 1.2063,
"step": 641
},
{
"epoch": 0.85,
"learning_rate": 1.221351075076781e-06,
"loss": 1.2495,
"step": 642
},
{
"epoch": 0.85,
"learning_rate": 1.2009890577141625e-06,
"loss": 1.2197,
"step": 643
},
{
"epoch": 0.85,
"learning_rate": 1.1807873565164507e-06,
"loss": 1.2521,
"step": 644
},
{
"epoch": 0.85,
"learning_rate": 1.1607463395544782e-06,
"loss": 1.2254,
"step": 645
},
{
"epoch": 0.85,
"learning_rate": 1.1408663719714418e-06,
"loss": 1.2357,
"step": 646
},
{
"epoch": 0.85,
"learning_rate": 1.121147815976248e-06,
"loss": 1.1756,
"step": 647
},
{
"epoch": 0.85,
"learning_rate": 1.1015910308369239e-06,
"loss": 1.1827,
"step": 648
},
{
"epoch": 0.86,
"learning_rate": 1.0821963728740626e-06,
"loss": 1.2071,
"step": 649
},
{
"epoch": 0.86,
"learning_rate": 1.062964195454329e-06,
"loss": 1.2552,
"step": 650
},
{
"epoch": 0.86,
"learning_rate": 1.0438948489840327e-06,
"loss": 1.1921,
"step": 651
},
{
"epoch": 0.86,
"learning_rate": 1.0249886809027355e-06,
"loss": 1.2148,
"step": 652
},
{
"epoch": 0.86,
"learning_rate": 1.0062460356769189e-06,
"loss": 1.2207,
"step": 653
},
{
"epoch": 0.86,
"learning_rate": 9.876672547937117e-07,
"loss": 1.1999,
"step": 654
},
{
"epoch": 0.86,
"learning_rate": 9.692526767546727e-07,
"loss": 1.2209,
"step": 655
},
{
"epoch": 0.86,
"learning_rate": 9.51002637069619e-07,
"loss": 1.2208,
"step": 656
},
{
"epoch": 0.87,
"learning_rate": 9.32917468250506e-07,
"loss": 1.2426,
"step": 657
},
{
"epoch": 0.87,
"learning_rate": 9.149974998053823e-07,
"loss": 1.2129,
"step": 658
},
{
"epoch": 0.87,
"learning_rate": 8.972430582323788e-07,
"loss": 1.2453,
"step": 659
},
{
"epoch": 0.87,
"learning_rate": 8.796544670137574e-07,
"loss": 1.1991,
"step": 660
},
{
"epoch": 0.87,
"learning_rate": 8.622320466100242e-07,
"loss": 1.2346,
"step": 661
},
{
"epoch": 0.87,
"learning_rate": 8.449761144540869e-07,
"loss": 1.2006,
"step": 662
},
{
"epoch": 0.87,
"learning_rate": 8.278869849454718e-07,
"loss": 1.2171,
"step": 663
},
{
"epoch": 0.87,
"learning_rate": 8.109649694445898e-07,
"loss": 1.2201,
"step": 664
},
{
"epoch": 0.88,
"learning_rate": 7.942103762670783e-07,
"loss": 1.2213,
"step": 665
},
{
"epoch": 0.88,
"learning_rate": 7.776235106781704e-07,
"loss": 1.2146,
"step": 666
},
{
"epoch": 0.88,
"learning_rate": 7.612046748871327e-07,
"loss": 1.2159,
"step": 667
},
{
"epoch": 0.88,
"learning_rate": 7.449541680417704e-07,
"loss": 1.2434,
"step": 668
},
{
"epoch": 0.88,
"learning_rate": 7.288722862229691e-07,
"loss": 1.1792,
"step": 669
},
{
"epoch": 0.88,
"learning_rate": 7.12959322439295e-07,
"loss": 1.2433,
"step": 670
},
{
"epoch": 0.88,
"learning_rate": 6.972155666216684e-07,
"loss": 1.2162,
"step": 671
},
{
"epoch": 0.89,
"learning_rate": 6.816413056180748e-07,
"loss": 1.2319,
"step": 672
},
{
"epoch": 0.89,
"learning_rate": 6.662368231883388e-07,
"loss": 1.2424,
"step": 673
},
{
"epoch": 0.89,
"learning_rate": 6.510023999989501e-07,
"loss": 1.2052,
"step": 674
},
{
"epoch": 0.89,
"learning_rate": 6.359383136179598e-07,
"loss": 1.2292,
"step": 675
},
{
"epoch": 0.89,
"learning_rate": 6.210448385099177e-07,
"loss": 1.2327,
"step": 676
},
{
"epoch": 0.89,
"learning_rate": 6.063222460308649e-07,
"loss": 1.2206,
"step": 677
},
{
"epoch": 0.89,
"learning_rate": 5.917708044234017e-07,
"loss": 1.2348,
"step": 678
},
{
"epoch": 0.89,
"learning_rate": 5.77390778811796e-07,
"loss": 1.2034,
"step": 679
},
{
"epoch": 0.9,
"learning_rate": 5.631824311971456e-07,
"loss": 1.2399,
"step": 680
},
{
"epoch": 0.9,
"learning_rate": 5.491460204526156e-07,
"loss": 1.1637,
"step": 681
},
{
"epoch": 0.9,
"learning_rate": 5.352818023187167e-07,
"loss": 1.1979,
"step": 682
},
{
"epoch": 0.9,
"learning_rate": 5.215900293986431e-07,
"loss": 1.233,
"step": 683
},
{
"epoch": 0.9,
"learning_rate": 5.08070951153673e-07,
"loss": 1.2375,
"step": 684
},
{
"epoch": 0.9,
"learning_rate": 4.947248138986249e-07,
"loss": 1.2333,
"step": 685
},
{
"epoch": 0.9,
"learning_rate": 4.81551860797369e-07,
"loss": 1.2321,
"step": 686
},
{
"epoch": 0.91,
"learning_rate": 4.6855233185839175e-07,
"loss": 1.2235,
"step": 687
},
{
"epoch": 0.91,
"learning_rate": 4.557264639304315e-07,
"loss": 1.2285,
"step": 688
},
{
"epoch": 0.91,
"learning_rate": 4.430744906981577e-07,
"loss": 1.2414,
"step": 689
},
{
"epoch": 0.91,
"learning_rate": 4.305966426779118e-07,
"loss": 1.2246,
"step": 690
},
{
"epoch": 0.91,
"learning_rate": 4.1829314721351213e-07,
"loss": 1.23,
"step": 691
},
{
"epoch": 0.91,
"learning_rate": 4.0616422847211013e-07,
"loss": 1.2381,
"step": 692
},
{
"epoch": 0.91,
"learning_rate": 3.942101074401028e-07,
"loss": 1.2074,
"step": 693
},
{
"epoch": 0.91,
"learning_rate": 3.824310019191102e-07,
"loss": 1.1853,
"step": 694
},
{
"epoch": 0.92,
"learning_rate": 3.708271265220087e-07,
"loss": 1.2447,
"step": 695
},
{
"epoch": 0.92,
"learning_rate": 3.5939869266901073e-07,
"loss": 1.2242,
"step": 696
},
{
"epoch": 0.92,
"learning_rate": 3.481459085838268e-07,
"loss": 1.2555,
"step": 697
},
{
"epoch": 0.92,
"learning_rate": 3.370689792898618e-07,
"loss": 1.2489,
"step": 698
},
{
"epoch": 0.92,
"learning_rate": 3.261681066064859e-07,
"loss": 1.242,
"step": 699
},
{
"epoch": 0.92,
"learning_rate": 3.154434891453473e-07,
"loss": 1.2281,
"step": 700
},
{
"epoch": 0.92,
"learning_rate": 3.0489532230676744e-07,
"loss": 1.1931,
"step": 701
},
{
"epoch": 0.92,
"learning_rate": 2.945237982761706e-07,
"loss": 1.189,
"step": 702
},
{
"epoch": 0.93,
"learning_rate": 2.843291060205855e-07,
"loss": 1.2069,
"step": 703
},
{
"epoch": 0.93,
"learning_rate": 2.7431143128520243e-07,
"loss": 1.1773,
"step": 704
},
{
"epoch": 0.93,
"learning_rate": 2.6447095658999054e-07,
"loss": 1.2184,
"step": 705
},
{
"epoch": 0.93,
"learning_rate": 2.5480786122636713e-07,
"loss": 1.2064,
"step": 706
},
{
"epoch": 0.93,
"learning_rate": 2.453223212539391e-07,
"loss": 1.2445,
"step": 707
},
{
"epoch": 0.93,
"learning_rate": 2.3601450949728876e-07,
"loss": 1.1938,
"step": 708
},
{
"epoch": 0.93,
"learning_rate": 2.2688459554282673e-07,
"loss": 1.1684,
"step": 709
},
{
"epoch": 0.94,
"learning_rate": 2.1793274573570166e-07,
"loss": 1.2272,
"step": 710
},
{
"epoch": 0.94,
"learning_rate": 2.091591231767709e-07,
"loss": 1.2135,
"step": 711
},
{
"epoch": 0.94,
"learning_rate": 2.005638877196303e-07,
"loss": 1.2497,
"step": 712
},
{
"epoch": 0.94,
"learning_rate": 1.921471959676957e-07,
"loss": 1.1679,
"step": 713
},
{
"epoch": 0.94,
"learning_rate": 1.8390920127135613e-07,
"loss": 1.2072,
"step": 714
},
{
"epoch": 0.94,
"learning_rate": 1.7585005372517504e-07,
"loss": 1.2149,
"step": 715
},
{
"epoch": 0.94,
"learning_rate": 1.6796990016515914e-07,
"loss": 1.2245,
"step": 716
},
{
"epoch": 0.94,
"learning_rate": 1.6026888416608267e-07,
"loss": 1.2107,
"step": 717
},
{
"epoch": 0.95,
"learning_rate": 1.5274714603886742e-07,
"loss": 1.2172,
"step": 718
},
{
"epoch": 0.95,
"learning_rate": 1.4540482282803136e-07,
"loss": 1.2217,
"step": 719
},
{
"epoch": 0.95,
"learning_rate": 1.3824204830918952e-07,
"loss": 1.235,
"step": 720
},
{
"epoch": 0.95,
"learning_rate": 1.3125895298661705e-07,
"loss": 1.228,
"step": 721
},
{
"epoch": 0.95,
"learning_rate": 1.244556640908712e-07,
"loss": 1.2113,
"step": 722
},
{
"epoch": 0.95,
"learning_rate": 1.1783230557647075e-07,
"loss": 1.1956,
"step": 723
},
{
"epoch": 0.95,
"learning_rate": 1.1138899811964477e-07,
"loss": 1.1961,
"step": 724
},
{
"epoch": 0.96,
"learning_rate": 1.0512585911612416e-07,
"loss": 1.2284,
"step": 725
},
{
"epoch": 0.96,
"learning_rate": 9.904300267901012e-08,
"loss": 1.2261,
"step": 726
},
{
"epoch": 0.96,
"learning_rate": 9.314053963669245e-08,
"loss": 1.2033,
"step": 727
},
{
"epoch": 0.96,
"learning_rate": 8.741857753083228e-08,
"loss": 1.228,
"step": 728
},
{
"epoch": 0.96,
"learning_rate": 8.187722061439806e-08,
"loss": 1.2217,
"step": 729
},
{
"epoch": 0.96,
"learning_rate": 7.651656984977051e-08,
"loss": 1.2252,
"step": 730
},
{
"epoch": 0.96,
"learning_rate": 7.133672290690064e-08,
"loss": 1.2155,
"step": 731
},
{
"epoch": 0.96,
"learning_rate": 6.633777416153232e-08,
"loss": 1.2393,
"step": 732
},
{
"epoch": 0.97,
"learning_rate": 6.151981469348034e-08,
"loss": 1.2009,
"step": 733
},
{
"epoch": 0.97,
"learning_rate": 5.688293228497399e-08,
"loss": 1.2215,
"step": 734
},
{
"epoch": 0.97,
"learning_rate": 5.2427211419051605e-08,
"loss": 1.2348,
"step": 735
},
{
"epoch": 0.97,
"learning_rate": 4.815273327803183e-08,
"loss": 1.2593,
"step": 736
},
{
"epoch": 0.97,
"learning_rate": 4.405957574202147e-08,
"loss": 1.2245,
"step": 737
},
{
"epoch": 0.97,
"learning_rate": 4.014781338751106e-08,
"loss": 1.1899,
"step": 738
},
{
"epoch": 0.97,
"learning_rate": 3.641751748600042e-08,
"loss": 1.2334,
"step": 739
},
{
"epoch": 0.97,
"learning_rate": 3.2868756002712997e-08,
"loss": 1.2141,
"step": 740
},
{
"epoch": 0.98,
"learning_rate": 2.950159359535132e-08,
"loss": 1.2478,
"step": 741
},
{
"epoch": 0.98,
"learning_rate": 2.6316091612920146e-08,
"loss": 1.2436,
"step": 742
},
{
"epoch": 0.98,
"learning_rate": 2.3312308094607382e-08,
"loss": 1.2141,
"step": 743
},
{
"epoch": 0.98,
"learning_rate": 2.049029776873268e-08,
"loss": 1.1924,
"step": 744
},
{
"epoch": 0.98,
"learning_rate": 1.7850112051738255e-08,
"loss": 1.2596,
"step": 745
},
{
"epoch": 0.98,
"learning_rate": 1.5391799047266287e-08,
"loss": 1.1749,
"step": 746
},
{
"epoch": 0.98,
"learning_rate": 1.3115403545270744e-08,
"loss": 1.2327,
"step": 747
},
{
"epoch": 0.99,
"learning_rate": 1.1020967021210249e-08,
"loss": 1.2044,
"step": 748
},
{
"epoch": 0.99,
"learning_rate": 9.108527635284248e-09,
"loss": 1.2405,
"step": 749
},
{
"epoch": 0.99,
"learning_rate": 7.378120231745778e-09,
"loss": 1.1996,
"step": 750
},
{
"epoch": 0.99,
"learning_rate": 5.8297763382597625e-09,
"loss": 1.2085,
"step": 751
},
{
"epoch": 0.99,
"learning_rate": 4.463524165333466e-09,
"loss": 1.2112,
"step": 752
},
{
"epoch": 0.99,
"learning_rate": 3.2793886057991277e-09,
"loss": 1.2329,
"step": 753
},
{
"epoch": 0.99,
"learning_rate": 2.277391234363213e-09,
"loss": 1.1981,
"step": 754
},
{
"epoch": 0.99,
"learning_rate": 1.4575503072100649e-09,
"loss": 1.2015,
"step": 755
},
{
"epoch": 1.0,
"learning_rate": 8.198807616732752e-10,
"loss": 1.2342,
"step": 756
},
{
"epoch": 1.0,
"learning_rate": 3.6439421595924065e-10,
"loss": 1.2115,
"step": 757
},
{
"epoch": 1.0,
"learning_rate": 9.109896894066161e-11,
"loss": 1.2319,
"step": 758
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 1.2129,
"step": 759
},
{
"epoch": 1.0,
"step": 759,
"total_flos": 8.491785698085622e+21,
"train_loss": 1.2714912057394097,
"train_runtime": 6445.9977,
"train_samples_per_second": 30.144,
"train_steps_per_second": 0.118
}
],
"logging_steps": 1.0,
"max_steps": 759,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"total_flos": 8.491785698085622e+21,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}