{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9967159277504105,
  "eval_steps": 31,
  "global_step": 608,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.1498,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.1952733993530273,
      "eval_runtime": 15.2597,
      "eval_samples_per_second": 6.226,
      "eval_steps_per_second": 1.573,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.176,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.5e-06,
      "loss": 1.1287,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.0172,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.5e-06,
      "loss": 0.8997,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 3e-06,
      "loss": 0.8616,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.5e-06,
      "loss": 0.7128,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6826,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.5e-06,
      "loss": 0.5946,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-06,
      "loss": 0.5616,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.999965501009142e-06,
      "loss": 0.4778,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.999862004988709e-06,
      "loss": 0.5264,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.999689514795112e-06,
      "loss": 0.4518,
      "step": 13
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9994480351889364e-06,
      "loss": 0.46,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.999137572834828e-06,
      "loss": 0.4111,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.998758136301295e-06,
      "loss": 0.3646,
      "step": 16
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.99830973606048e-06,
      "loss": 0.4024,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.997792384487867e-06,
      "loss": 0.4042,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.997206095861944e-06,
      "loss": 0.3659,
      "step": 19
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.996550886363801e-06,
      "loss": 0.3527,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.995826774076693e-06,
      "loss": 0.3726,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.995033778985534e-06,
      "loss": 0.3551,
      "step": 22
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.994171922976349e-06,
      "loss": 0.382,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.993241229835666e-06,
      "loss": 0.3694,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.992241725249866e-06,
      "loss": 0.3603,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.991173436804468e-06,
      "loss": 0.3383,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.990036393983372e-06,
      "loss": 0.3455,
      "step": 27
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9888306281680405e-06,
      "loss": 0.3428,
      "step": 28
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.987556172636637e-06,
      "loss": 0.3001,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.986213062563104e-06,
      "loss": 0.307,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.984801335016198e-06,
      "loss": 0.321,
      "step": 31
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.3176000714302063,
      "eval_runtime": 15.512,
      "eval_samples_per_second": 6.124,
      "eval_steps_per_second": 1.547,
      "step": 31
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9833210289584574e-06,
      "loss": 0.2925,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.981772185245135e-06,
      "loss": 0.311,
      "step": 33
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.980154846623067e-06,
      "loss": 0.3066,
      "step": 34
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.978469057729493e-06,
      "loss": 0.2879,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.976714865090827e-06,
      "loss": 0.3001,
      "step": 36
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.974892317121368e-06,
      "loss": 0.3111,
      "step": 37
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.97300146412197e-06,
      "loss": 0.3067,
      "step": 38
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9710423582786485e-06,
      "loss": 0.3091,
      "step": 39
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.969015053661142e-06,
      "loss": 0.302,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.966919606221423e-06,
      "loss": 0.2991,
      "step": 41
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.964756073792148e-06,
      "loss": 0.3034,
      "step": 42
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.9625245160850674e-06,
      "loss": 0.2877,
      "step": 43
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.960224994689371e-06,
      "loss": 0.283,
      "step": 44
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.957857573069992e-06,
      "loss": 0.2993,
      "step": 45
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.955422316565856e-06,
      "loss": 0.2738,
      "step": 46
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.952919292388079e-06,
      "loss": 0.293,
      "step": 47
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.950348569618105e-06,
      "loss": 0.3053,
      "step": 48
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.947710219205808e-06,
      "loss": 0.2875,
      "step": 49
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.9450043139675284e-06,
      "loss": 0.2798,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.9422309285840684e-06,
      "loss": 0.3172,
      "step": 51
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.939390139598623e-06,
      "loss": 0.2713,
      "step": 52
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.936482025414677e-06,
      "loss": 0.2372,
      "step": 53
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.933506666293834e-06,
      "loss": 0.3125,
      "step": 54
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9304641443536015e-06,
      "loss": 0.2687,
      "step": 55
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.927354543565131e-06,
      "loss": 0.2701,
      "step": 56
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.924177949750893e-06,
      "loss": 0.2681,
      "step": 57
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.920934450582311e-06,
      "loss": 0.2751,
      "step": 58
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.917624135577346e-06,
      "loss": 0.2902,
      "step": 59
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.914247096098019e-06,
      "loss": 0.2618,
      "step": 60
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.910803425347892e-06,
      "loss": 0.2569,
      "step": 61
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.907293218369499e-06,
      "loss": 0.2693,
      "step": 62
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.27119407057762146,
      "eval_runtime": 15.5684,
      "eval_samples_per_second": 6.102,
      "eval_steps_per_second": 1.542,
      "step": 62
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.903716572041718e-06,
      "loss": 0.2475,
      "step": 63
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.9000735850771e-06,
      "loss": 0.2492,
      "step": 64
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.8963643580191446e-06,
      "loss": 0.273,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.8925889932395246e-06,
      "loss": 0.2193,
      "step": 66
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.888747594935259e-06,
      "loss": 0.2637,
      "step": 67
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.88484026912584e-06,
      "loss": 0.3141,
      "step": 68
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.880867123650306e-06,
      "loss": 0.254,
      "step": 69
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.876828268164264e-06,
      "loss": 0.2778,
      "step": 70
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.872723814136866e-06,
      "loss": 0.2809,
      "step": 71
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.868553874847728e-06,
      "loss": 0.266,
      "step": 72
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.864318565383809e-06,
      "loss": 0.2174,
      "step": 73
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.86001800263623e-06,
      "loss": 0.2732,
      "step": 74
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.855652305297052e-06,
      "loss": 0.2507,
      "step": 75
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.8512215938559955e-06,
      "loss": 0.2514,
      "step": 76
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.846725990597122e-06,
      "loss": 0.268,
      "step": 77
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.84216561959545e-06,
      "loss": 0.228,
      "step": 78
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.837540606713538e-06,
      "loss": 0.2606,
      "step": 79
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.832851079598007e-06,
      "loss": 0.2554,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.82809716767602e-06,
      "loss": 0.257,
      "step": 81
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.8232790021517094e-06,
      "loss": 0.2475,
      "step": 82
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.818396716002553e-06,
      "loss": 0.2636,
      "step": 83
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.813450443975705e-06,
      "loss": 0.2076,
      "step": 84
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.808440322584283e-06,
      "loss": 0.2336,
      "step": 85
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.803366490103593e-06,
      "loss": 0.2664,
      "step": 86
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.798229086567312e-06,
      "loss": 0.2559,
      "step": 87
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.793028253763633e-06,
      "loss": 0.2687,
      "step": 88
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.787764135231342e-06,
      "loss": 0.2263,
      "step": 89
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.7824368762558595e-06,
      "loss": 0.2058,
      "step": 90
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.7770466238652336e-06,
      "loss": 0.246,
      "step": 91
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.771593526826078e-06,
      "loss": 0.2592,
      "step": 92
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.76607773563947e-06,
      "loss": 0.2701,
      "step": 93
    },
    {
      "epoch": 0.31,
      "eval_loss": 0.25227251648902893,
      "eval_runtime": 15.5184,
      "eval_samples_per_second": 6.122,
      "eval_steps_per_second": 1.547,
      "step": 93
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.760499402536792e-06,
      "loss": 0.2154,
      "step": 94
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.754858681475534e-06,
      "loss": 0.2748,
      "step": 95
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.7491557281350455e-06,
      "loss": 0.2461,
      "step": 96
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.743390699912232e-06,
      "loss": 0.2245,
      "step": 97
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.737563755917219e-06,
      "loss": 0.2446,
      "step": 98
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.731675056968958e-06,
      "loss": 0.2563,
      "step": 99
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.7257247655907854e-06,
      "loss": 0.2512,
      "step": 100
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.7197130460059385e-06,
      "loss": 0.2613,
      "step": 101
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.7136400641330245e-06,
      "loss": 0.2294,
      "step": 102
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.7075059875814424e-06,
      "loss": 0.2162,
      "step": 103
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.70131098564675e-06,
      "loss": 0.251,
      "step": 104
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.695055229306001e-06,
      "loss": 0.2468,
      "step": 105
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.6887388912130206e-06,
      "loss": 0.2467,
      "step": 106
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.68236214569364e-06,
      "loss": 0.2588,
      "step": 107
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.675925168740887e-06,
      "loss": 0.2592,
      "step": 108
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.6694281380101304e-06,
      "loss": 0.2225,
      "step": 109
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.662871232814171e-06,
      "loss": 0.2411,
      "step": 110
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.656254634118301e-06,
      "loss": 0.2512,
      "step": 111
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.649578524535302e-06,
      "loss": 0.2252,
      "step": 112
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.642843088320408e-06,
      "loss": 0.2288,
      "step": 113
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.636048511366222e-06,
      "loss": 0.2339,
      "step": 114
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.6291949811975814e-06,
      "loss": 0.2252,
      "step": 115
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.622282686966387e-06,
      "loss": 0.2497,
      "step": 116
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.615311819446379e-06,
      "loss": 0.2339,
      "step": 117
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.6082825710278724e-06,
      "loss": 0.2946,
      "step": 118
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.60119513571245e-06,
      "loss": 0.2797,
      "step": 119
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.594049709107604e-06,
      "loss": 0.272,
      "step": 120
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.58684648842134e-06,
      "loss": 0.2437,
      "step": 121
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.5795856724567344e-06,
      "loss": 0.2328,
      "step": 122
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.572267461606446e-06,
      "loss": 0.2333,
      "step": 123
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.564892057847184e-06,
      "loss": 0.27,
      "step": 124
    },
    {
      "epoch": 0.41,
      "eval_loss": 0.2362014800310135,
      "eval_runtime": 15.5362,
      "eval_samples_per_second": 6.115,
      "eval_steps_per_second": 1.545,
      "step": 124
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.5574596647341414e-06,
      "loss": 0.2202,
      "step": 125
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.549970487395365e-06,
      "loss": 0.2129,
      "step": 126
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.542424732526105e-06,
      "loss": 0.2343,
      "step": 127
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.534822608383104e-06,
      "loss": 0.2527,
      "step": 128
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.5271643247788496e-06,
      "loss": 0.2622,
      "step": 129
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.519450093075787e-06,
      "loss": 0.247,
      "step": 130
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.5116801261804846e-06,
      "loss": 0.2612,
      "step": 131
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.503854638537756e-06,
      "loss": 0.2515,
      "step": 132
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.49597384612474e-06,
      "loss": 0.2164,
      "step": 133
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.488037966444948e-06,
      "loss": 0.2545,
      "step": 134
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.48004721852225e-06,
      "loss": 0.2547,
      "step": 135
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.472001822894839e-06,
      "loss": 0.1869,
      "step": 136
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.463902001609139e-06,
      "loss": 0.2383,
      "step": 137
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.455747978213679e-06,
      "loss": 0.2234,
      "step": 138
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.44753997775292e-06,
      "loss": 0.2356,
      "step": 139
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.43927822676105e-06,
      "loss": 0.232,
      "step": 140
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.430962953255725e-06,
      "loss": 0.2352,
      "step": 141
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.4225943867317835e-06,
      "loss": 0.2199,
      "step": 142
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.4141727581549025e-06,
      "loss": 0.2175,
      "step": 143
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.405698299955234e-06,
      "loss": 0.221,
      "step": 144
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.39717124602098e-06,
      "loss": 0.2522,
      "step": 145
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.388591831691948e-06,
      "loss": 0.2412,
      "step": 146
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.3799602937530464e-06,
      "loss": 0.2176,
      "step": 147
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.3712768704277535e-06,
      "loss": 0.2242,
      "step": 148
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.362541801371542e-06,
      "loss": 0.2156,
      "step": 149
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.353755327665268e-06,
      "loss": 0.2077,
      "step": 150
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.344917691808511e-06,
      "loss": 0.2285,
      "step": 151
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.3360291377128864e-06,
      "loss": 0.2364,
      "step": 152
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.32708991069531e-06,
      "loss": 0.2577,
      "step": 153
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.318100257471233e-06,
      "loss": 0.2347,
      "step": 154
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.309060426147826e-06,
      "loss": 0.2244,
      "step": 155
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.22840476036071777,
      "eval_runtime": 15.5442,
      "eval_samples_per_second": 6.112,
      "eval_steps_per_second": 1.544,
      "step": 155
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.299970666217135e-06,
      "loss": 0.2197,
      "step": 156
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.290831228549196e-06,
      "loss": 0.2618,
      "step": 157
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.281642365385111e-06,
      "loss": 0.2498,
      "step": 158
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.272404330330084e-06,
      "loss": 0.2309,
      "step": 159
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.263117378346425e-06,
      "loss": 0.2163,
      "step": 160
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.253781765746511e-06,
      "loss": 0.1968,
      "step": 161
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.244397750185714e-06,
      "loss": 0.2127,
      "step": 162
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.234965590655287e-06,
      "loss": 0.2088,
      "step": 163
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.225485547475217e-06,
      "loss": 0.2082,
      "step": 164
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.215957882287044e-06,
      "loss": 0.2549,
      "step": 165
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.206382858046636e-06,
      "loss": 0.2131,
      "step": 166
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.19676073901693e-06,
      "loss": 0.2048,
      "step": 167
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.187091790760644e-06,
      "loss": 0.2451,
      "step": 168
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.177376280132946e-06,
      "loss": 0.1896,
      "step": 169
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.167614475274082e-06,
      "loss": 0.2253,
      "step": 170
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.1578066456019885e-06,
      "loss": 0.2167,
      "step": 171
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.147953061804845e-06,
      "loss": 0.2262,
      "step": 172
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.1380539958336095e-06,
      "loss": 0.2483,
      "step": 173
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.128109720894512e-06,
      "loss": 0.2824,
      "step": 174
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.118120511441512e-06,
      "loss": 0.2273,
      "step": 175
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.108086643168724e-06,
      "loss": 0.2177,
      "step": 176
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.098008393002816e-06,
      "loss": 0.2147,
      "step": 177
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.087886039095353e-06,
      "loss": 0.1915,
      "step": 178
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.077719860815132e-06,
      "loss": 0.2123,
      "step": 179
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.067510138740467e-06,
      "loss": 0.2418,
      "step": 180
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.057257154651444e-06,
      "loss": 0.2055,
      "step": 181
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.046961191522147e-06,
      "loss": 0.2098,
      "step": 182
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.036622533512845e-06,
      "loss": 0.2304,
      "step": 183
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.026241465962154e-06,
      "loss": 0.2018,
      "step": 184
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.0158182753791566e-06,
      "loss": 0.2009,
      "step": 185
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.0053532494354985e-06,
      "loss": 0.2227,
      "step": 186
    },
    {
      "epoch": 0.61,
      "eval_loss": 0.2260431945323944,
      "eval_runtime": 15.5286,
      "eval_samples_per_second": 6.118,
      "eval_steps_per_second": 1.546,
      "step": 186
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.994846676957448e-06,
      "loss": 0.1973,
      "step": 187
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.984298847917923e-06,
      "loss": 0.2192,
      "step": 188
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.973710053428487e-06,
      "loss": 0.2016,
      "step": 189
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.963080585731324e-06,
      "loss": 0.2118,
      "step": 190
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.952410738191158e-06,
      "loss": 0.2361,
      "step": 191
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.941700805287169e-06,
      "loss": 0.2132,
      "step": 192
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.9309510826048556e-06,
      "loss": 0.2117,
      "step": 193
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.92016186682789e-06,
      "loss": 0.2196,
      "step": 194
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.909333455729914e-06,
      "loss": 0.1958,
      "step": 195
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.898466148166333e-06,
      "loss": 0.2318,
      "step": 196
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.8875602440660635e-06,
      "loss": 0.2034,
      "step": 197
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.876616044423253e-06,
      "loss": 0.2119,
      "step": 198
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.865633851288975e-06,
      "loss": 0.2177,
      "step": 199
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.854613967762898e-06,
      "loss": 0.1974,
      "step": 200
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.843556697984907e-06,
      "loss": 0.1902,
      "step": 201
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.832462347126722e-06,
      "loss": 0.1975,
      "step": 202
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.821331221383471e-06,
      "loss": 0.2083,
      "step": 203
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.8101636279652375e-06,
      "loss": 0.2247,
      "step": 204
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.798959875088584e-06,
      "loss": 0.2169,
      "step": 205
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.787720271968046e-06,
      "loss": 0.1854,
      "step": 206
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.7764451288075944e-06,
      "loss": 0.2269,
      "step": 207
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.765134756792079e-06,
      "loss": 0.1946,
      "step": 208
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.753789468078636e-06,
      "loss": 0.1944,
      "step": 209
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.742409575788074e-06,
      "loss": 0.2057,
      "step": 210
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.730995393996234e-06,
      "loss": 0.2427,
      "step": 211
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.719547237725319e-06,
      "loss": 0.227,
      "step": 212
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.708065422935198e-06,
      "loss": 0.2152,
      "step": 213
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.6965502665146916e-06,
      "loss": 0.2177,
      "step": 214
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.6850020862728196e-06,
      "loss": 0.2089,
      "step": 215
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.6734212009300346e-06,
      "loss": 0.2081,
      "step": 216
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.661807930109422e-06,
      "loss": 0.2167,
      "step": 217
    },
    {
      "epoch": 0.71,
      "eval_loss": 0.21709737181663513,
      "eval_runtime": 15.5146,
      "eval_samples_per_second": 6.123,
      "eval_steps_per_second": 1.547,
      "step": 217
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.650162594327881e-06,
      "loss": 0.2135,
      "step": 218
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.6384855149872776e-06,
      "loss": 0.1976,
      "step": 219
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.6267770143655743e-06,
      "loss": 0.2073,
      "step": 220
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.615037415607937e-06,
      "loss": 0.2252,
      "step": 221
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.603267042717813e-06,
      "loss": 0.2296,
      "step": 222
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5914662205479923e-06,
      "loss": 0.181,
      "step": 223
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.579635274791639e-06,
      "loss": 0.2196,
      "step": 224
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.567774531973305e-06,
      "loss": 0.2063,
      "step": 225
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.555884319439917e-06,
      "loss": 0.2313,
      "step": 226
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.5439649653517416e-06,
      "loss": 0.1994,
      "step": 227
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.532016798673329e-06,
      "loss": 0.2143,
      "step": 228
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.5200401491644333e-06,
      "loss": 0.2118,
      "step": 229
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.508035347370912e-06,
      "loss": 0.2081,
      "step": 230
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.4960027246156043e-06,
      "loss": 0.2313,
      "step": 231
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.483942612989183e-06,
      "loss": 0.2071,
      "step": 232
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.471855345340992e-06,
      "loss": 0.2199,
      "step": 233
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.4597412552698617e-06,
      "loss": 0.1879,
      "step": 234
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.447600677114898e-06,
      "loss": 0.1717,
      "step": 235
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.4354339459462556e-06,
      "loss": 0.2273,
      "step": 236
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.423241397555893e-06,
      "loss": 0.2351,
      "step": 237
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.4110233684483033e-06,
      "loss": 0.2165,
      "step": 238
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.3987801958312254e-06,
      "loss": 0.2309,
      "step": 239
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.386512217606339e-06,
      "loss": 0.2023,
      "step": 240
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.3742197723599403e-06,
      "loss": 0.2189,
      "step": 241
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.361903199353593e-06,
      "loss": 0.205,
      "step": 242
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.349562838514769e-06,
      "loss": 0.1912,
      "step": 243
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.3371990304274654e-06,
      "loss": 0.1898,
      "step": 244
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.3248121163228037e-06,
      "loss": 0.2037,
      "step": 245
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.3124024380696134e-06,
      "loss": 0.1959,
      "step": 246
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.299970338164995e-06,
      "loss": 0.1972,
      "step": 247
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.28751615972487e-06,
      "loss": 0.2098,
      "step": 248
    },
    {
      "epoch": 0.81,
      "eval_loss": 0.20815877616405487,
      "eval_runtime": 15.5231,
      "eval_samples_per_second": 6.12,
      "eval_steps_per_second": 1.546,
      "step": 248
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.2750402464745084e-06,
      "loss": 0.2322,
      "step": 249
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.262542942739044e-06,
      "loss": 0.1977,
      "step": 250
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.2500245934339714e-06,
      "loss": 0.1983,
      "step": 251
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.2374855440556242e-06,
      "loss": 0.1857,
      "step": 252
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.224926140671643e-06,
      "loss": 0.183,
      "step": 253
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.2123467299114216e-06,
      "loss": 0.2216,
      "step": 254
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.199747658956541e-06,
      "loss": 0.1808,
      "step": 255
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.1871292755311887e-06,
      "loss": 0.2278,
      "step": 256
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.174491927892561e-06,
      "loss": 0.203,
      "step": 257
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.1618359648212492e-06,
      "loss": 0.2209,
      "step": 258
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.1491617356116167e-06,
      "loss": 0.2131,
      "step": 259
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.136469590062158e-06,
      "loss": 0.2111,
      "step": 260
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.1237598784658444e-06,
      "loss": 0.1915,
      "step": 261
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.1110329516004546e-06,
      "loss": 0.2272,
      "step": 262
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.0982891607188948e-06,
      "loss": 0.1784,
      "step": 263
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.085528857539506e-06,
      "loss": 0.2064,
      "step": 264
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.0727523942363547e-06,
      "loss": 0.1857,
      "step": 265
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.0599601234295124e-06,
      "loss": 0.1981,
      "step": 266
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.0471523981753266e-06,
      "loss": 0.2429,
      "step": 267
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.0343295719566747e-06,
      "loss": 0.1755,
      "step": 268
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.0214919986732076e-06,
      "loss": 0.2024,
      "step": 269
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.0086400326315853e-06,
      "loss": 0.1859,
      "step": 270
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.9957740285356933e-06,
      "loss": 0.2056,
      "step": 271
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.9828943414768583e-06,
      "loss": 0.2183,
      "step": 272
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.9700013269240463e-06,
      "loss": 0.1892,
      "step": 273
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.957095340714049e-06,
      "loss": 0.2139,
      "step": 274
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.9441767390416665e-06,
      "loss": 0.2314,
      "step": 275
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.9312458784498763e-06,
      "loss": 0.1897,
      "step": 276
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.918303115819992e-06,
      "loss": 0.1698,
      "step": 277
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.9053488083618118e-06,
      "loss": 0.2147,
      "step": 278
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.892383313603765e-06,
      "loss": 0.1842,
      "step": 279
    },
    {
      "epoch": 0.92,
      "eval_loss": 0.20471937954425812,
      "eval_runtime": 15.5241,
      "eval_samples_per_second": 6.12,
      "eval_steps_per_second": 1.546,
      "step": 279
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.8794069893830386e-06,
      "loss": 0.178,
      "step": 280
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.8664201938357052e-06,
      "loss": 0.2245,
      "step": 281
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8534232853868384e-06,
      "loss": 0.1583,
      "step": 282
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.840416622740617e-06,
      "loss": 0.1752,
      "step": 283
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8274005648704316e-06,
      "loss": 0.1981,
      "step": 284
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.8143754710089694e-06,
      "loss": 0.2216,
      "step": 285
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.8013417006383078e-06,
      "loss": 0.2075,
      "step": 286
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.7882996134799854e-06,
      "loss": 0.1978,
      "step": 287
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.775249569485079e-06,
      "loss": 0.2302,
      "step": 288
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.762191928824267e-06,
      "loss": 0.2218,
      "step": 289
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.7491270518778913e-06,
      "loss": 0.2033,
      "step": 290
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.736055299226007e-06,
      "loss": 0.2055,
      "step": 291
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.722977031638435e-06,
      "loss": 0.2231,
      "step": 292
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.709892610064801e-06,
      "loss": 0.2233,
      "step": 293
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.696802395624579e-06,
      "loss": 0.2354,
      "step": 294
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.683706749597118e-06,
      "loss": 0.2136,
      "step": 295
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.670606033411678e-06,
      "loss": 0.181,
      "step": 296
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.657500608637448e-06,
      "loss": 0.2051,
      "step": 297
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.6443908369735715e-06,
      "loss": 0.209,
      "step": 298
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.631277080239163e-06,
      "loss": 0.2184,
      "step": 299
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.6181597003633218e-06,
      "loss": 0.1988,
      "step": 300
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.605039059375143e-06,
      "loss": 0.2223,
      "step": 301
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.5919155193937244e-06,
      "loss": 0.2029,
      "step": 302
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.578789442618176e-06,
      "loss": 0.2089,
      "step": 303
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.565661191317618e-06,
      "loss": 0.2065,
      "step": 304
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.5525311278211888e-06,
      "loss": 0.1977,
      "step": 305
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.5393996145080413e-06,
      "loss": 0.1748,
      "step": 306
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.5262670137973413e-06,
      "loss": 0.2128,
      "step": 307
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.5131336881382658e-06,
      "loss": 0.1876,
      "step": 308
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.5e-06,
      "loss": 0.1947,
      "step": 309
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.4868663118617355e-06,
      "loss": 0.1917,
      "step": 310
    },
    {
      "epoch": 1.02,
      "eval_loss": 0.2012825459241867,
      "eval_runtime": 15.4963,
      "eval_samples_per_second": 6.131,
      "eval_steps_per_second": 1.549,
      "step": 310
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.47373298620266e-06,
      "loss": 0.1904,
      "step": 311
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.4606003854919595e-06,
      "loss": 0.1792,
      "step": 312
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.4474688721788116e-06,
      "loss": 0.1886,
      "step": 313
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.4343388086823828e-06,
      "loss": 0.201,
      "step": 314
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.421210557381825e-06,
      "loss": 0.1776,
      "step": 315
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.4080844806062764e-06,
      "loss": 0.1957,
      "step": 316
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.3949609406248576e-06,
      "loss": 0.1744,
      "step": 317
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.3818402996366786e-06,
      "loss": 0.2017,
      "step": 318
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.3687229197608373e-06,
      "loss": 0.1586,
      "step": 319
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.3556091630264294e-06,
      "loss": 0.1481,
      "step": 320
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.3424993913625534e-06,
      "loss": 0.1696,
      "step": 321
    },
    {
      "epoch": 1.06,
      "learning_rate": 2.3293939665883233e-06,
      "loss": 0.1974,
      "step": 322
    },
    {
      "epoch": 1.06,
      "learning_rate": 2.3162932504028828e-06,
      "loss": 0.1698,
      "step": 323
    },
    {
      "epoch": 1.06,
      "learning_rate": 2.303197604375422e-06,
      "loss": 0.184,
      "step": 324
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.2901073899351997e-06,
      "loss": 0.1806,
      "step": 325
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.277022968361566e-06,
      "loss": 0.1741,
      "step": 326
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.2639447007739933e-06,
      "loss": 0.1906,
      "step": 327
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.2508729481221096e-06,
      "loss": 0.19,
      "step": 328
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.2378080711757332e-06,
      "loss": 0.1954,
      "step": 329
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.2247504305149217e-06,
      "loss": 0.1755,
      "step": 330
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.2117003865200154e-06,
      "loss": 0.1932,
      "step": 331
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.1986582993616926e-06,
      "loss": 0.1795,
      "step": 332
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.185624528991031e-06,
      "loss": 0.1586,
      "step": 333
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.1725994351295697e-06,
      "loss": 0.1746,
      "step": 334
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.159583377259384e-06,
      "loss": 0.1744,
      "step": 335
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.1465767146131633e-06,
      "loss": 0.1553,
      "step": 336
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.1335798061642956e-06,
      "loss": 0.1589,
      "step": 337
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.1205930106169626e-06,
      "loss": 0.1624,
      "step": 338
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.1076166863962358e-06,
      "loss": 0.1823,
      "step": 339
    },
    {
      "epoch": 1.12,
      "learning_rate": 2.094651191638189e-06,
      "loss": 0.1658,
      "step": 340
    },
    {
      "epoch": 1.12,
      "learning_rate": 2.0816968841800094e-06,
      "loss": 0.1639,
      "step": 341
    },
    {
      "epoch": 1.12,
      "eval_loss": 0.19820626080036163,
      "eval_runtime": 15.5045,
      "eval_samples_per_second": 6.127,
      "eval_steps_per_second": 1.548,
      "step": 341
    },
    {
      "epoch": 1.12,
      "learning_rate": 2.0687541215501245e-06,
      "loss": 0.1776,
      "step": 342
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.0558232609583343e-06,
      "loss": 0.1674,
      "step": 343
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.0429046592859524e-06,
      "loss": 0.2104,
      "step": 344
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.0299986730759553e-06,
      "loss": 0.1598,
      "step": 345
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.0171056585231425e-06,
      "loss": 0.1741,
      "step": 346
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.004225971464308e-06,
      "loss": 0.1508,
      "step": 347
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.991359967368416e-06,
      "loss": 0.1735,
      "step": 348
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.9785080013267933e-06,
      "loss": 0.1834,
      "step": 349
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.965670428043326e-06,
      "loss": 0.1538,
      "step": 350
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.952847601824674e-06,
      "loss": 0.1905,
      "step": 351
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.940039876570489e-06,
      "loss": 0.1745,
      "step": 352
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.927247605763647e-06,
      "loss": 0.1847,
      "step": 353
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.914471142460495e-06,
      "loss": 0.1672,
      "step": 354
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.9017108392811065e-06,
      "loss": 0.1881,
      "step": 355
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.888967048399547e-06,
      "loss": 0.1712,
      "step": 356
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.8762401215341569e-06,
      "loss": 0.1437,
      "step": 357
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.8635304099378426e-06,
      "loss": 0.1589,
      "step": 358
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.8508382643883837e-06,
      "loss": 0.192,
      "step": 359
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.8381640351787516e-06,
      "loss": 0.1691,
      "step": 360
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.8255080721074391e-06,
      "loss": 0.15,
      "step": 361
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.8128707244688109e-06,
      "loss": 0.166,
      "step": 362
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.800252341043459e-06,
      "loss": 0.1661,
      "step": 363
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.7876532700885788e-06,
      "loss": 0.192,
      "step": 364
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.7750738593283573e-06,
      "loss": 0.1597,
      "step": 365
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.7625144559443758e-06,
      "loss": 0.1562,
      "step": 366
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.7499754065660288e-06,
      "loss": 0.1527,
      "step": 367
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.7374570572609559e-06,
      "loss": 0.1631,
      "step": 368
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.7249597535254916e-06,
      "loss": 0.1552,
      "step": 369
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.7124838402751304e-06,
      "loss": 0.1469,
      "step": 370
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.7000296618350054e-06,
      "loss": 0.1476,
      "step": 371
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.6875975619303872e-06,
      "loss": 0.1835,
      "step": 372
    },
    {
      "epoch": 1.22,
      "eval_loss": 0.19680581986904144,
      "eval_runtime": 15.5171,
      "eval_samples_per_second": 6.122,
      "eval_steps_per_second": 1.547,
      "step": 372
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.6751878836771965e-06,
      "loss": 0.177,
      "step": 373
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.6628009695725348e-06,
      "loss": 0.1641,
      "step": 374
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.650437161485231e-06,
      "loss": 0.1827,
      "step": 375
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.6380968006464073e-06,
      "loss": 0.1648,
      "step": 376
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.6257802276400604e-06,
      "loss": 0.152,
      "step": 377
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.613487782393661e-06,
      "loss": 0.157,
      "step": 378
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.6012198041687748e-06,
      "loss": 0.166,
      "step": 379
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.588976631551697e-06,
      "loss": 0.1634,
      "step": 380
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.5767586024441066e-06,
      "loss": 0.1697,
      "step": 381
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.5645660540537444e-06,
      "loss": 0.157,
      "step": 382
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.552399322885103e-06,
      "loss": 0.1533,
      "step": 383
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.5402587447301387e-06,
      "loss": 0.1762,
      "step": 384
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.5281446546590084e-06,
      "loss": 0.1389,
      "step": 385
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.516057387010818e-06,
      "loss": 0.1616,
      "step": 386
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.5039972753843966e-06,
      "loss": 0.1534,
      "step": 387
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.4919646526290884e-06,
      "loss": 0.1617,
      "step": 388
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.4799598508355678e-06,
      "loss": 0.1318,
      "step": 389
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.4679832013266721e-06,
      "loss": 0.1536,
      "step": 390
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.4560350346482599e-06,
      "loss": 0.1957,
      "step": 391
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.4441156805600842e-06,
      "loss": 0.1608,
      "step": 392
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.4322254680266962e-06,
      "loss": 0.1706,
      "step": 393
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.4203647252083619e-06,
      "loss": 0.1256,
      "step": 394
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.4085337794520087e-06,
      "loss": 0.1561,
      "step": 395
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.3967329572821875e-06,
      "loss": 0.1634,
      "step": 396
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.3849625843920633e-06,
      "loss": 0.1753,
      "step": 397
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.3732229856344259e-06,
      "loss": 0.1589,
      "step": 398
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.3615144850127232e-06,
      "loss": 0.1764,
      "step": 399
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.3498374056721198e-06,
      "loss": 0.1534,
      "step": 400
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.3381920698905788e-06,
      "loss": 0.159,
      "step": 401
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.326578799069966e-06,
      "loss": 0.152,
      "step": 402
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.3149979137271806e-06,
      "loss": 0.1666,
      "step": 403
    },
    {
      "epoch": 1.32,
      "eval_loss": 0.19529137015342712,
      "eval_runtime": 15.5082,
      "eval_samples_per_second": 6.126,
      "eval_steps_per_second": 1.548,
      "step": 403
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.3034497334853092e-06,
      "loss": 0.1778,
      "step": 404
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.2919345770648023e-06,
      "loss": 0.1733,
      "step": 405
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.280452762274682e-06,
      "loss": 0.1577,
      "step": 406
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.2690046060037661e-06,
      "loss": 0.1548,
      "step": 407
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.2575904242119264e-06,
      "loss": 0.1437,
      "step": 408
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.2462105319213643e-06,
      "loss": 0.1652,
      "step": 409
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.234865243207921e-06,
      "loss": 0.167,
      "step": 410
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.2235548711924056e-06,
      "loss": 0.1693,
      "step": 411
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.2122797280319543e-06,
      "loss": 0.1714,
      "step": 412
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.2010401249114166e-06,
      "loss": 0.1752,
      "step": 413
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.1898363720347635e-06,
      "loss": 0.1439,
      "step": 414
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.1786687786165302e-06,
      "loss": 0.1663,
      "step": 415
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.167537652873279e-06,
      "loss": 0.1644,
      "step": 416
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.1564433020150946e-06,
      "loss": 0.1385,
      "step": 417
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.1453860322371032e-06,
      "loss": 0.1617,
      "step": 418
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.134366148711025e-06,
      "loss": 0.1725,
      "step": 419
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.1233839555767482e-06,
      "loss": 0.1487,
      "step": 420
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.1124397559339373e-06,
      "loss": 0.1636,
      "step": 421
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.1015338518336672e-06,
      "loss": 0.1607,
      "step": 422
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.0906665442700868e-06,
      "loss": 0.2252,
      "step": 423
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.079838133172111e-06,
      "loss": 0.1901,
      "step": 424
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.0690489173951446e-06,
      "loss": 0.1576,
      "step": 425
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.0582991947128324e-06,
      "loss": 0.1734,
      "step": 426
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.0475892618088426e-06,
      "loss": 0.1654,
      "step": 427
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.0369194142686766e-06,
      "loss": 0.1608,
      "step": 428
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.0262899465715128e-06,
      "loss": 0.18,
      "step": 429
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.0157011520820784e-06,
      "loss": 0.1379,
      "step": 430
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.0051533230425527e-06,
      "loss": 0.1584,
      "step": 431
    },
    {
      "epoch": 1.42,
      "learning_rate": 9.946467505645019e-07,
      "loss": 0.1488,
      "step": 432
    },
    {
      "epoch": 1.42,
      "learning_rate": 9.84181724620844e-07,
      "loss": 0.1863,
      "step": 433
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.73758534037847e-07,
      "loss": 0.1694,
      "step": 434
    },
    {
      "epoch": 1.43,
      "eval_loss": 0.19318194687366486,
      "eval_runtime": 15.505,
      "eval_samples_per_second": 6.127,
      "eval_steps_per_second": 1.548,
      "step": 434
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.633774664871557e-07,
      "loss": 0.1826,
      "step": 435
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.530388084778541e-07,
      "loss": 0.1892,
      "step": 436
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.427428453485573e-07,
      "loss": 0.1377,
      "step": 437
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.32489861259534e-07,
      "loss": 0.1576,
      "step": 438
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.222801391848688e-07,
      "loss": 0.1988,
      "step": 439
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.121139609046484e-07,
      "loss": 0.1426,
      "step": 440
    },
    {
      "epoch": 1.45,
      "learning_rate": 9.019916069971857e-07,
      "loss": 0.1467,
      "step": 441
    },
    {
      "epoch": 1.45,
      "learning_rate": 8.919133568312768e-07,
      "loss": 0.1558,
      "step": 442
    },
    {
      "epoch": 1.45,
      "learning_rate": 8.818794885584902e-07,
      "loss": 0.1593,
      "step": 443
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.718902791054895e-07,
      "loss": 0.1443,
      "step": 444
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.619460041663915e-07,
      "loss": 0.1779,
      "step": 445
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.52046938195156e-07,
      "loss": 0.1454,
      "step": 446
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.421933543980126e-07,
      "loss": 0.1607,
      "step": 447
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.323855247259185e-07,
      "loss": 0.1558,
      "step": 448
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.226237198670556e-07,
      "loss": 0.1748,
      "step": 449
    },
    {
      "epoch": 1.48,
      "learning_rate": 8.129082092393562e-07,
      "loss": 0.1754,
      "step": 450
    },
    {
      "epoch": 1.48,
      "learning_rate": 8.032392609830708e-07,
      "loss": 0.1418,
      "step": 451
    },
    {
      "epoch": 1.48,
      "learning_rate": 7.936171419533653e-07,
      "loss": 0.1553,
      "step": 452
    },
    {
      "epoch": 1.49,
      "learning_rate": 7.840421177129564e-07,
      "loss": 0.1576,
      "step": 453
    },
    {
      "epoch": 1.49,
      "learning_rate": 7.745144525247839e-07,
      "loss": 0.1405,
      "step": 454
    },
    {
      "epoch": 1.49,
      "learning_rate": 7.650344093447145e-07,
      "loss": 0.1495,
      "step": 455
    },
    {
      "epoch": 1.5,
      "learning_rate": 7.55602249814287e-07,
      "loss": 0.1631,
      "step": 456
    },
    {
      "epoch": 1.5,
      "learning_rate": 7.462182342534896e-07,
      "loss": 0.1728,
      "step": 457
    },
    {
      "epoch": 1.5,
      "learning_rate": 7.368826216535758e-07,
      "loss": 0.1756,
      "step": 458
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.275956696699169e-07,
      "loss": 0.164,
      "step": 459
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.183576346148899e-07,
      "loss": 0.1417,
      "step": 460
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.091687714508044e-07,
      "loss": 0.1871,
      "step": 461
    },
    {
      "epoch": 1.52,
      "learning_rate": 7.000293337828656e-07,
      "loss": 0.1651,
      "step": 462
    },
    {
      "epoch": 1.52,
      "learning_rate": 6.909395738521745e-07,
      "loss": 0.1705,
      "step": 463
    },
    {
      "epoch": 1.52,
      "learning_rate": 6.818997425287671e-07,
      "loss": 0.1633,
      "step": 464
    },
    {
      "epoch": 1.53,
      "learning_rate": 6.729100893046897e-07,
      "loss": 0.1461,
      "step": 465
    },
    {
      "epoch": 1.53,
      "eval_loss": 0.19294388592243195,
      "eval_runtime": 15.5273,
      "eval_samples_per_second": 6.118,
      "eval_steps_per_second": 1.546,
      "step": 465
    },
    {
      "epoch": 1.53,
      "learning_rate": 6.639708622871144e-07,
      "loss": 0.1411,
      "step": 466
    },
    {
      "epoch": 1.53,
      "learning_rate": 6.550823081914892e-07,
      "loss": 0.1586,
      "step": 467
    },
    {
      "epoch": 1.54,
      "learning_rate": 6.462446723347324e-07,
      "loss": 0.1364,
      "step": 468
    },
    {
      "epoch": 1.54,
      "learning_rate": 6.374581986284578e-07,
      "loss": 0.1651,
      "step": 469
    },
    {
      "epoch": 1.54,
      "learning_rate": 6.28723129572247e-07,
      "loss": 0.1633,
      "step": 470
    },
    {
      "epoch": 1.55,
      "learning_rate": 6.200397062469541e-07,
      "loss": 0.1462,
      "step": 471
    },
    {
      "epoch": 1.55,
      "learning_rate": 6.11408168308052e-07,
      "loss": 0.1466,
      "step": 472
    },
    {
      "epoch": 1.55,
      "learning_rate": 6.0282875397902e-07,
      "loss": 0.1469,
      "step": 473
    },
    {
      "epoch": 1.56,
      "learning_rate": 5.943017000447671e-07,
      "loss": 0.1357,
      "step": 474
    },
    {
      "epoch": 1.56,
      "learning_rate": 5.858272418450978e-07,
      "loss": 0.1592,
      "step": 475
    },
    {
      "epoch": 1.56,
      "learning_rate": 5.774056132682168e-07,
      "loss": 0.1649,
      "step": 476
    },
    {
      "epoch": 1.57,
      "learning_rate": 5.690370467442743e-07,
      "loss": 0.1612,
      "step": 477
    },
    {
      "epoch": 1.57,
      "learning_rate": 5.607217732389503e-07,
      "loss": 0.1916,
      "step": 478
    },
    {
      "epoch": 1.57,
      "learning_rate": 5.5246002224708e-07,
      "loss": 0.2088,
      "step": 479
    },
    {
      "epoch": 1.58,
      "learning_rate": 5.442520217863215e-07,
      "loss": 0.1536,
      "step": 480
    },
    {
      "epoch": 1.58,
      "learning_rate": 5.360979983908615e-07,
      "loss": 0.152,
      "step": 481
    },
    {
      "epoch": 1.58,
      "learning_rate": 5.279981771051615e-07,
      "loss": 0.1389,
      "step": 482
    },
    {
      "epoch": 1.59,
      "learning_rate": 5.199527814777509e-07,
      "loss": 0.1164,
      "step": 483
    },
    {
      "epoch": 1.59,
      "learning_rate": 5.119620335550532e-07,
      "loss": 0.1821,
      "step": 484
    },
    {
      "epoch": 1.59,
      "learning_rate": 5.040261538752606e-07,
      "loss": 0.1525,
      "step": 485
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.961453614622453e-07,
      "loss": 0.1384,
      "step": 486
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.883198738195157e-07,
      "loss": 0.1791,
      "step": 487
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.805499069242131e-07,
      "loss": 0.1391,
      "step": 488
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.72835675221151e-07,
      "loss": 0.1324,
      "step": 489
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.651773916168967e-07,
      "loss": 0.1548,
      "step": 490
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.5757526747389506e-07,
      "loss": 0.1615,
      "step": 491
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.5002951260463503e-07,
      "loss": 0.1391,
      "step": 492
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.4254033526585917e-07,
      "loss": 0.1596,
      "step": 493
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.3510794215281595e-07,
      "loss": 0.1344,
      "step": 494
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.277325383935549e-07,
      "loss": 0.1831,
      "step": 495
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.2041432754326593e-07,
      "loss": 0.1535,
      "step": 496
    },
    {
      "epoch": 1.63,
      "eval_loss": 0.1927250325679779,
      "eval_runtime": 15.5004,
      "eval_samples_per_second": 6.129,
      "eval_steps_per_second": 1.548,
      "step": 496
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.1315351157866003e-07,
      "loss": 0.1262,
      "step": 497
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.059502908923962e-07,
      "loss": 0.1685,
      "step": 498
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.988048642875503e-07,
      "loss": 0.1435,
      "step": 499
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.917174289721276e-07,
      "loss": 0.1423,
      "step": 500
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.8468818055362153e-07,
      "loss": 0.1434,
      "step": 501
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.7771731303361314e-07,
      "loss": 0.1656,
      "step": 502
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.708050188024187e-07,
      "loss": 0.1553,
      "step": 503
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.639514886337786e-07,
      "loss": 0.1503,
      "step": 504
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.571569116795928e-07,
      "loss": 0.1227,
      "step": 505
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.5042147546469894e-07,
      "loss": 0.1365,
      "step": 506
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.437453658816994e-07,
      "loss": 0.1508,
      "step": 507
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.371287671858292e-07,
      "loss": 0.1571,
      "step": 508
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.3057186198987066e-07,
      "loss": 0.1518,
      "step": 509
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.2407483125911354e-07,
      "loss": 0.1502,
      "step": 510
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.1763785430636073e-07,
      "loss": 0.1273,
      "step": 511
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.112611087869799e-07,
      "loss": 0.1738,
      "step": 512
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.04944770693999e-07,
      "loss": 0.143,
      "step": 513
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.9868901435325033e-07,
      "loss": 0.1424,
      "step": 514
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.924940124185585e-07,
      "loss": 0.1749,
      "step": 515
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.8635993586697555e-07,
      "loss": 0.1547,
      "step": 516
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.80286953994062e-07,
      "loss": 0.1725,
      "step": 517
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.7427523440921534e-07,
      "loss": 0.1373,
      "step": 518
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.6832494303104195e-07,
      "loss": 0.1434,
      "step": 519
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.62436244082781e-07,
      "loss": 0.147,
      "step": 520
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.566093000877687e-07,
      "loss": 0.1673,
      "step": 521
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.5084427186495566e-07,
      "loss": 0.1618,
      "step": 522
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.451413185244661e-07,
      "loss": 0.1618,
      "step": 523
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.3950059746320864e-07,
      "loss": 0.1507,
      "step": 524
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.3392226436053073e-07,
      "loss": 0.1582,
      "step": 525
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.2840647317392218e-07,
      "loss": 0.1691,
      "step": 526
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.2295337613476714e-07,
      "loss": 0.1419,
      "step": 527
    },
    {
      "epoch": 1.73,
      "eval_loss": 0.1925160139799118,
      "eval_runtime": 15.4967,
      "eval_samples_per_second": 6.13,
      "eval_steps_per_second": 1.549,
      "step": 527
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.1756312374414113e-07,
      "loss": 0.1648,
      "step": 528
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.1223586476865953e-07,
      "loss": 0.1488,
      "step": 529
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.0697174623636795e-07,
      "loss": 0.1691,
      "step": 530
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.017709134326884e-07,
      "loss": 0.1669,
      "step": 531
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.9663350989640812e-07,
      "loss": 0.1548,
      "step": 532
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.915596774157169e-07,
      "loss": 0.161,
      "step": 533
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.8654955602429499e-07,
      "loss": 0.1763,
      "step": 534
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.8160328399744825e-07,
      "loss": 0.1813,
      "step": 535
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.7672099784829116e-07,
      "loss": 0.155,
      "step": 536
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.719028323239802e-07,
      "loss": 0.1718,
      "step": 537
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.6714892040199383e-07,
      "loss": 0.1486,
      "step": 538
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.6245939328646322e-07,
      "loss": 0.1465,
      "step": 539
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.5783438040455097e-07,
      "loss": 0.1261,
      "step": 540
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.5327400940287868e-07,
      "loss": 0.2032,
      "step": 541
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.4877840614400452e-07,
      "loss": 0.1648,
      "step": 542
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.44347694702949e-07,
      "loss": 0.1614,
      "step": 543
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.399819973637706e-07,
      "loss": 0.1783,
      "step": 544
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.3568143461619193e-07,
      "loss": 0.1642,
      "step": 545
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.3144612515227278e-07,
      "loss": 0.1615,
      "step": 546
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.2727618586313495e-07,
      "loss": 0.1474,
      "step": 547
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.2317173183573616e-07,
      "loss": 0.1432,
      "step": 548
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.1913287634969461e-07,
      "loss": 0.1582,
      "step": 549
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.151597308741606e-07,
      "loss": 0.1579,
      "step": 550
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.1125240506474178e-07,
      "loss": 0.1533,
      "step": 551
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.0741100676047639e-07,
      "loss": 0.1517,
      "step": 552
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.0363564198085624e-07,
      "loss": 0.1716,
      "step": 553
    },
    {
      "epoch": 1.82,
      "learning_rate": 9.992641492290094e-08,
      "loss": 0.1709,
      "step": 554
    },
    {
      "epoch": 1.82,
      "learning_rate": 9.628342795828333e-08,
      "loss": 0.1439,
      "step": 555
    },
    {
      "epoch": 1.83,
      "learning_rate": 9.270678163050218e-08,
      "loss": 0.1568,
      "step": 556
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.919657465210867e-08,
      "loss": 0.1306,
      "step": 557
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.575290390198193e-08,
      "loss": 0.1612,
      "step": 558
    },
    {
      "epoch": 1.83,
      "eval_loss": 0.19228258728981018,
      "eval_runtime": 15.5027,
      "eval_samples_per_second": 6.128,
      "eval_steps_per_second": 1.548,
      "step": 558
    },
    {
      "epoch": 1.84,
      "learning_rate": 8.237586442265411e-08,
      "loss": 0.1491,
      "step": 559
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.906554941768896e-08,
      "loss": 0.1692,
      "step": 560
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.582205024910805e-08,
      "loss": 0.1775,
      "step": 561
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.264545643486997e-08,
      "loss": 0.1526,
      "step": 562
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.953585564639903e-08,
      "loss": 0.1716,
      "step": 563
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.649333370616712e-08,
      "loss": 0.177,
      "step": 564
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.351797458532316e-08,
      "loss": 0.1542,
      "step": 565
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.060986040137689e-08,
      "loss": 0.1603,
      "step": 566
    },
    {
      "epoch": 1.86,
      "learning_rate": 5.776907141593235e-08,
      "loss": 0.1542,
      "step": 567
    },
    {
      "epoch": 1.87,
      "learning_rate": 5.4995686032471575e-08,
      "loss": 0.1629,
      "step": 568
    },
    {
      "epoch": 1.87,
      "learning_rate": 5.2289780794192726e-08,
      "loss": 0.1614,
      "step": 569
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.96514303818954e-08,
      "loss": 0.1267,
      "step": 570
    },
    {
      "epoch": 1.88,
      "learning_rate": 4.708070761192146e-08,
      "loss": 0.1888,
      "step": 571
    },
    {
      "epoch": 1.88,
      "learning_rate": 4.457768343414382e-08,
      "loss": 0.168,
      "step": 572
    },
    {
      "epoch": 1.88,
      "learning_rate": 4.2142426930008584e-08,
      "loss": 0.1492,
      "step": 573
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.9775005310629946e-08,
      "loss": 0.1382,
      "step": 574
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.747548391493272e-08,
      "loss": 0.1682,
      "step": 575
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.5243926207851606e-08,
      "loss": 0.1833,
      "step": 576
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.3080393778577305e-08,
      "loss": 0.1451,
      "step": 577
    },
    {
      "epoch": 1.9,
      "learning_rate": 3.09849463388584e-08,
      "loss": 0.1741,
      "step": 578
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.8957641721352735e-08,
      "loss": 0.1765,
      "step": 579
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.6998535878030584e-08,
      "loss": 0.1684,
      "step": 580
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.510768287863202e-08,
      "loss": 0.1543,
      "step": 581
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.3285134909173113e-08,
      "loss": 0.1558,
      "step": 582
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.1530942270506504e-08,
      "loss": 0.1654,
      "step": 583
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.9845153376933102e-08,
      "loss": 0.1381,
      "step": 584
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.822781475486507e-08,
      "loss": 0.164,
      "step": 585
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.6678971041542702e-08,
      "loss": 0.153,
      "step": 586
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.5198664983802346e-08,
      "loss": 0.1168,
      "step": 587
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.3786937436895686e-08,
      "loss": 0.1425,
      "step": 588
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.2443827363363693e-08,
      "loss": 0.1857,
      "step": 589
    },
    {
      "epoch": 1.93,
      "eval_loss": 0.19226355850696564,
      "eval_runtime": 15.5264,
      "eval_samples_per_second": 6.119,
      "eval_steps_per_second": 1.546,
      "step": 589
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.1169371831959986e-08,
      "loss": 0.1804,
      "step": 590
    },
    {
      "epoch": 1.94,
      "learning_rate": 9.963606016628325e-09,
      "loss": 0.1569,
      "step": 591
    },
    {
      "epoch": 1.94,
      "learning_rate": 8.826563195531713e-09,
      "loss": 0.1867,
      "step": 592
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.758274750134243e-09,
      "loss": 0.1755,
      "step": 593
    },
    {
      "epoch": 1.95,
      "learning_rate": 6.758770164334572e-09,
      "loss": 0.1796,
      "step": 594
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.828077023651846e-09,
      "loss": 0.1559,
      "step": 595
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.96622101446631e-09,
      "loss": 0.1851,
      "step": 596
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.1732259233071004e-09,
      "loss": 0.1833,
      "step": 597
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.449113636199153e-09,
      "loss": 0.1786,
      "step": 598
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.793904138056469e-09,
      "loss": 0.1979,
      "step": 599
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.2076155121328326e-09,
      "loss": 0.1566,
      "step": 600
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.6902639395208197e-09,
      "loss": 0.1636,
      "step": 601
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.2418636987057697e-09,
      "loss": 0.1439,
      "step": 602
    },
    {
      "epoch": 1.98,
      "learning_rate": 8.624271651727634e-10,
      "loss": 0.1967,
      "step": 603
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.519648110638431e-10,
      "loss": 0.1715,
      "step": 604
    },
    {
      "epoch": 1.99,
      "learning_rate": 3.1048520488907717e-10,
      "loss": 0.1833,
      "step": 605
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.3799501129063698e-10,
      "loss": 0.1692,
      "step": 606
    },
    {
      "epoch": 1.99,
      "learning_rate": 3.4498990858777835e-11,
      "loss": 0.1697,
      "step": 607
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 0.1712,
      "step": 608
    }
  ],
  "logging_steps": 1,
  "max_steps": 608,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 3.399970706505597e+18,
  "trial_name": null,
  "trial_params": null
}