{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06,
  "eval_steps": 50,
  "global_step": 600,
  "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": 1.0306,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.9796,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.5e-06,
      "loss": 1.1645,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6227,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.5e-06,
      "loss": 0.9588,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 3e-06,
      "loss": 0.806,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 1.1137,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8787,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.5e-06,
      "loss": 0.8552,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 5e-06,
      "loss": 1.0622,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.500000000000001e-06,
      "loss": 1.0613,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-06,
      "loss": 0.6159,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 1.0281,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.000000000000001e-06,
      "loss": 1.0413,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.5e-06,
      "loss": 0.7431,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8156,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.500000000000002e-06,
      "loss": 0.7001,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 9e-06,
      "loss": 1.1875,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.5e-06,
      "loss": 0.9966,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 1.0371,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.05e-05,
      "loss": 1.1584,
      "step": 21
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.7505,
      "step": 22
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 1.066,
      "step": 23
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.2e-05,
      "loss": 1.1298,
      "step": 24
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.25e-05,
      "loss": 1.068,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.1175,
      "step": 26
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 0.573,
      "step": 27
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.8054,
      "step": 28
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.45e-05,
      "loss": 1.1083,
      "step": 29
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.5e-05,
      "loss": 1.1453,
      "step": 30
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.55e-05,
      "loss": 1.5355,
      "step": 31
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.9017,
      "step": 32
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.65e-05,
      "loss": 0.7989,
      "step": 33
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.1186,
      "step": 34
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.75e-05,
      "loss": 0.0789,
      "step": 35
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.8e-05,
      "loss": 0.1037,
      "step": 36
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.85e-05,
      "loss": 0.08,
      "step": 37
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.9e-05,
      "loss": 0.0584,
      "step": 38
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.0915,
      "step": 39
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 0.0727,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.05e-05,
      "loss": 0.0553,
      "step": 41
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.1e-05,
      "loss": 0.0679,
      "step": 42
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.15e-05,
      "loss": 0.0599,
      "step": 43
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.0517,
      "step": 44
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.25e-05,
      "loss": 0.1149,
      "step": 45
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.054,
      "step": 46
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.35e-05,
      "loss": 0.0399,
      "step": 47
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.4e-05,
      "loss": 0.0508,
      "step": 48
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.45e-05,
      "loss": 0.0436,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.5e-05,
      "loss": 0.0405,
      "step": 50
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.051814079284668,
      "eval_runtime": 33.2954,
      "eval_samples_per_second": 2.553,
      "eval_steps_per_second": 0.661,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.5500000000000003e-05,
      "loss": 0.298,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.5977,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 0.9878,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.7903,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 1.0548,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.9161,
      "step": 56
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 1.3686,
      "step": 57
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9e-05,
      "loss": 1.7704,
      "step": 58
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.95e-05,
      "loss": 1.0523,
      "step": 59
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 1.191,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.05e-05,
      "loss": 1.2224,
      "step": 61
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.1e-05,
      "loss": 1.3556,
      "step": 62
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.15e-05,
      "loss": 1.1368,
      "step": 63
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.2531,
      "step": 64
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 1.2027,
      "step": 65
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.3e-05,
      "loss": 1.0789,
      "step": 66
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.35e-05,
      "loss": 1.3288,
      "step": 67
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.9706,
      "step": 68
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.45e-05,
      "loss": 0.832,
      "step": 69
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.5e-05,
      "loss": 0.8661,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.55e-05,
      "loss": 2.438,
      "step": 71
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.6e-05,
      "loss": 1.3327,
      "step": 72
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.65e-05,
      "loss": 1.1495,
      "step": 73
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.7e-05,
      "loss": 1.2341,
      "step": 74
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.1848,
      "step": 75
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.8e-05,
      "loss": 1.3687,
      "step": 76
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.85e-05,
      "loss": 1.1204,
      "step": 77
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 1.1608,
      "step": 78
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 1.1442,
      "step": 79
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 0.9808,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.05e-05,
      "loss": 1.0513,
      "step": 81
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.1e-05,
      "loss": 1.3775,
      "step": 82
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.15e-05,
      "loss": 0.6558,
      "step": 83
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2e-05,
      "loss": 1.1873,
      "step": 84
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.25e-05,
      "loss": 1.0167,
      "step": 85
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.3e-05,
      "loss": 1.0519,
      "step": 86
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.35e-05,
      "loss": 0.9843,
      "step": 87
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.1445,
      "step": 88
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 1.0606,
      "step": 89
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.5e-05,
      "loss": 1.0714,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.55e-05,
      "loss": 0.999,
      "step": 91
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.8138,
      "step": 92
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.6500000000000005e-05,
      "loss": 0.8204,
      "step": 93
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.7e-05,
      "loss": 1.289,
      "step": 94
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.75e-05,
      "loss": 1.1554,
      "step": 95
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.8e-05,
      "loss": 1.2538,
      "step": 96
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.85e-05,
      "loss": 1.6712,
      "step": 97
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9e-05,
      "loss": 0.8988,
      "step": 98
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 1.0097,
      "step": 99
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.9292,
      "step": 100
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.024911642074585,
      "eval_runtime": 33.8827,
      "eval_samples_per_second": 2.509,
      "eval_steps_per_second": 0.649,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999999874125034e-05,
      "loss": 1.0641,
      "step": 101
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999994965001495e-05,
      "loss": 1.2151,
      "step": 102
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999998867125384e-05,
      "loss": 1.1987,
      "step": 103
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999979860008006e-05,
      "loss": 0.9532,
      "step": 104
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999996853126489e-05,
      "loss": 0.9377,
      "step": 105
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999995468502562e-05,
      "loss": 1.0075,
      "step": 106
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999938321291604e-05,
      "loss": 1.085,
      "step": 107
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999991944006448e-05,
      "loss": 0.9276,
      "step": 108
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999898041346155e-05,
      "loss": 0.7739,
      "step": 109
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999987412513878e-05,
      "loss": 0.0642,
      "step": 110
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999984769144476e-05,
      "loss": 0.0386,
      "step": 111
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999818740266766e-05,
      "loss": 0.045,
      "step": 112
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999787271607714e-05,
      "loss": 0.0305,
      "step": 113
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999975328547076e-05,
      "loss": 0.0297,
      "step": 114
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999971678185933e-05,
      "loss": 0.0315,
      "step": 115
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999677760777114e-05,
      "loss": 0.0375,
      "step": 116
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999963622222803e-05,
      "loss": 0.0364,
      "step": 117
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999592166216256e-05,
      "loss": 0.0294,
      "step": 118
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999954559274624e-05,
      "loss": 0.0325,
      "step": 119
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999949650182266e-05,
      "loss": 0.0331,
      "step": 120
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999444893450476e-05,
      "loss": 0.0894,
      "step": 121
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999939076763487e-05,
      "loss": 0.0324,
      "step": 122
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.99993341243813e-05,
      "loss": 0.0245,
      "step": 123
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999927496369547e-05,
      "loss": 0.0187,
      "step": 124
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999921328558333e-05,
      "loss": 0.0201,
      "step": 125
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.99991490900511e-05,
      "loss": 0.0199,
      "step": 126
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999908237710523e-05,
      "loss": 0.405,
      "step": 127
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999901314675246e-05,
      "loss": 0.6401,
      "step": 128
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9998941398999754e-05,
      "loss": 0.9999,
      "step": 129
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999886713385432e-05,
      "loss": 0.8034,
      "step": 130
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999879035132366e-05,
      "loss": 2.5507,
      "step": 131
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999871105141549e-05,
      "loss": 1.0299,
      "step": 132
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999862923413781e-05,
      "loss": 0.8507,
      "step": 133
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999854489949884e-05,
      "loss": 1.301,
      "step": 134
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999845804750709e-05,
      "loss": 0.9371,
      "step": 135
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999836867817129e-05,
      "loss": 1.071,
      "step": 136
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999827679150045e-05,
      "loss": 1.1755,
      "step": 137
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999818238750382e-05,
      "loss": 1.1019,
      "step": 138
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999808546619091e-05,
      "loss": 1.035,
      "step": 139
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9997986027571485e-05,
      "loss": 1.0751,
      "step": 140
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9997884071655546e-05,
      "loss": 0.9669,
      "step": 141
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999777959845336e-05,
      "loss": 1.619,
      "step": 142
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999767260797546e-05,
      "loss": 1.0327,
      "step": 143
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999756310023261e-05,
      "loss": 1.4227,
      "step": 144
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9997451075235834e-05,
      "loss": 1.1229,
      "step": 145
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9997336532996426e-05,
      "loss": 1.0647,
      "step": 146
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999721947352591e-05,
      "loss": 0.8365,
      "step": 147
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999709989683607e-05,
      "loss": 0.9427,
      "step": 148
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999697780293897e-05,
      "loss": 0.9069,
      "step": 149
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9996853191846885e-05,
      "loss": 0.4741,
      "step": 150
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.0061652660369873,
      "eval_runtime": 33.3013,
      "eval_samples_per_second": 2.552,
      "eval_steps_per_second": 0.661,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999672606357236e-05,
      "loss": 1.1091,
      "step": 151
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99965964181282e-05,
      "loss": 1.045,
      "step": 152
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9996464255527475e-05,
      "loss": 1.2467,
      "step": 153
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999632957578349e-05,
      "loss": 1.2496,
      "step": 154
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9996192378909786e-05,
      "loss": 1.0957,
      "step": 155
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9996052664920195e-05,
      "loss": 2.7016,
      "step": 156
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999591043382878e-05,
      "loss": 0.9565,
      "step": 157
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9995765685649885e-05,
      "loss": 0.4296,
      "step": 158
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999561842039806e-05,
      "loss": 0.9448,
      "step": 159
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999546863808815e-05,
      "loss": 1.0846,
      "step": 160
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999531633873522e-05,
      "loss": 1.0365,
      "step": 161
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9995161522354626e-05,
      "loss": 1.0785,
      "step": 162
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9995004188961954e-05,
      "loss": 1.0112,
      "step": 163
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9994844338573047e-05,
      "loss": 1.0194,
      "step": 164
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9994681971203985e-05,
      "loss": 1.1474,
      "step": 165
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999451708687114e-05,
      "loss": 1.0013,
      "step": 166
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999434968559111e-05,
      "loss": 1.2304,
      "step": 167
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9994179767380746e-05,
      "loss": 0.8919,
      "step": 168
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9994007332257166e-05,
      "loss": 1.0994,
      "step": 169
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9993832380237735e-05,
      "loss": 0.9525,
      "step": 170
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999365491134006e-05,
      "loss": 0.9128,
      "step": 171
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999347492558202e-05,
      "loss": 0.9752,
      "step": 172
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9993292422981744e-05,
      "loss": 1.0829,
      "step": 173
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9993107403557606e-05,
      "loss": 1.0873,
      "step": 174
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999291986732823e-05,
      "loss": 0.7728,
      "step": 175
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999272981431251e-05,
      "loss": 1.2234,
      "step": 176
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999253724452958e-05,
      "loss": 1.1018,
      "step": 177
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999234215799884e-05,
      "loss": 1.323,
      "step": 178
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9992144554739915e-05,
      "loss": 1.3506,
      "step": 179
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9991944434772734e-05,
      "loss": 0.9995,
      "step": 180
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999174179811742e-05,
      "loss": 1.0128,
      "step": 181
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9991536644794394e-05,
      "loss": 0.9663,
      "step": 182
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9991328974824314e-05,
      "loss": 0.9088,
      "step": 183
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9991118788228084e-05,
      "loss": 0.9769,
      "step": 184
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999090608502688e-05,
      "loss": 1.1041,
      "step": 185
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999069086524212e-05,
      "loss": 1.0777,
      "step": 186
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999047312889547e-05,
      "loss": 1.0644,
      "step": 187
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999025287600886e-05,
      "loss": 1.2527,
      "step": 188
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9990030106604466e-05,
      "loss": 1.1408,
      "step": 189
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9989804820704735e-05,
      "loss": 1.0382,
      "step": 190
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998957701833233e-05,
      "loss": 0.8821,
      "step": 191
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998934669951021e-05,
      "loss": 1.1115,
      "step": 192
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998911386426156e-05,
      "loss": 1.0668,
      "step": 193
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998887851260983e-05,
      "loss": 1.3347,
      "step": 194
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998864064457871e-05,
      "loss": 1.8449,
      "step": 195
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998840026019217e-05,
      "loss": 0.8444,
      "step": 196
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99881573594744e-05,
      "loss": 0.6749,
      "step": 197
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9987911942449874e-05,
      "loss": 0.8313,
      "step": 198
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998766400914329e-05,
      "loss": 1.1872,
      "step": 199
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9987413559579636e-05,
      "loss": 1.0037,
      "step": 200
    },
    {
      "epoch": 0.02,
      "eval_loss": 1.009230613708496,
      "eval_runtime": 34.1185,
      "eval_samples_per_second": 2.491,
      "eval_steps_per_second": 0.645,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998716059378411e-05,
      "loss": 0.9677,
      "step": 201
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99869051117822e-05,
      "loss": 0.7094,
      "step": 202
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998664711359963e-05,
      "loss": 0.9669,
      "step": 203
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9986386599262374e-05,
      "loss": 0.7753,
      "step": 204
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998612356879667e-05,
      "loss": 0.7886,
      "step": 205
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9985858022229015e-05,
      "loss": 1.0666,
      "step": 206
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998558995958614e-05,
      "loss": 1.0726,
      "step": 207
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998531938089503e-05,
      "loss": 0.6764,
      "step": 208
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998504628618296e-05,
      "loss": 0.9581,
      "step": 209
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99847706754774e-05,
      "loss": 0.8455,
      "step": 210
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998449254880612e-05,
      "loss": 1.0878,
      "step": 211
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998421190619711e-05,
      "loss": 1.0696,
      "step": 212
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9983928747678663e-05,
      "loss": 1.1857,
      "step": 213
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998364307327927e-05,
      "loss": 0.5613,
      "step": 214
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99833548830277e-05,
      "loss": 1.5976,
      "step": 215
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9983064176952976e-05,
      "loss": 1.304,
      "step": 216
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9982770955084376e-05,
      "loss": 1.1785,
      "step": 217
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9982475217451426e-05,
      "loss": 1.369,
      "step": 218
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998217696408391e-05,
      "loss": 1.3781,
      "step": 219
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9981876195011844e-05,
      "loss": 1.2481,
      "step": 220
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998157291026553e-05,
      "loss": 1.1869,
      "step": 221
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998126710987552e-05,
      "loss": 1.0437,
      "step": 222
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9980958793872577e-05,
      "loss": 1.0083,
      "step": 223
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998064796228779e-05,
      "loss": 0.8874,
      "step": 224
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998033461515242e-05,
      "loss": 1.0524,
      "step": 225
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9980018752498035e-05,
      "loss": 0.9784,
      "step": 226
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9979700374356455e-05,
      "loss": 0.8767,
      "step": 227
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997937948075973e-05,
      "loss": 1.0886,
      "step": 228
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997905607174017e-05,
      "loss": 0.8765,
      "step": 229
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9978730147330355e-05,
      "loss": 0.7674,
      "step": 230
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9978401707563096e-05,
      "loss": 0.9259,
      "step": 231
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997807075247146e-05,
      "loss": 0.9196,
      "step": 232
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997773728208879e-05,
      "loss": 1.0045,
      "step": 233
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997740129644865e-05,
      "loss": 0.5903,
      "step": 234
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9977062795584893e-05,
      "loss": 0.802,
      "step": 235
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99767217795316e-05,
      "loss": 0.7193,
      "step": 236
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9976378248323095e-05,
      "loss": 0.8271,
      "step": 237
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997603220199399e-05,
      "loss": 0.9451,
      "step": 238
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9975683640579126e-05,
      "loss": 0.7997,
      "step": 239
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99753325641136e-05,
      "loss": 0.9519,
      "step": 240
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997497897263277e-05,
      "loss": 1.0293,
      "step": 241
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997462286617224e-05,
      "loss": 0.5886,
      "step": 242
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997426424476787e-05,
      "loss": 0.9684,
      "step": 243
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997390310845578e-05,
      "loss": 0.9717,
      "step": 244
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997353945727232e-05,
      "loss": 0.6933,
      "step": 245
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9973173291254126e-05,
      "loss": 0.6983,
      "step": 246
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997280461043806e-05,
      "loss": 0.7808,
      "step": 247
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997243341486127e-05,
      "loss": 1.0136,
      "step": 248
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9972059704561094e-05,
      "loss": 0.8564,
      "step": 249
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.99716834795752e-05,
      "loss": 0.9686,
      "step": 250
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.9817100167274475,
      "eval_runtime": 34.0668,
      "eval_samples_per_second": 2.495,
      "eval_steps_per_second": 0.646,
      "step": 250
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9971304739941465e-05,
      "loss": 0.9119,
      "step": 251
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9970923485698025e-05,
      "loss": 0.751,
      "step": 252
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.997053971688327e-05,
      "loss": 0.7892,
      "step": 253
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.997015343353585e-05,
      "loss": 0.9822,
      "step": 254
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996976463569467e-05,
      "loss": 1.0816,
      "step": 255
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996937332339887e-05,
      "loss": 1.1014,
      "step": 256
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996897949668785e-05,
      "loss": 0.4182,
      "step": 257
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996858315560129e-05,
      "loss": 0.7549,
      "step": 258
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996818430017908e-05,
      "loss": 0.9744,
      "step": 259
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996778293046141e-05,
      "loss": 0.7919,
      "step": 260
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996737904648866e-05,
      "loss": 1.8199,
      "step": 261
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9966972648301536e-05,
      "loss": 0.8733,
      "step": 262
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996656373594095e-05,
      "loss": 0.6261,
      "step": 263
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9966152309448076e-05,
      "loss": 0.0999,
      "step": 264
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996573836886435e-05,
      "loss": 0.0401,
      "step": 265
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996532191423145e-05,
      "loss": 0.0413,
      "step": 266
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996490294559132e-05,
      "loss": 0.0241,
      "step": 267
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996448146298614e-05,
      "loss": 0.0184,
      "step": 268
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996405746645837e-05,
      "loss": 0.0239,
      "step": 269
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996363095605069e-05,
      "loss": 0.0208,
      "step": 270
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996320193180606e-05,
      "loss": 0.0184,
      "step": 271
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996277039376767e-05,
      "loss": 0.0259,
      "step": 272
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996233634197899e-05,
      "loss": 0.0215,
      "step": 273
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996189977648372e-05,
      "loss": 0.023,
      "step": 274
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996146069732583e-05,
      "loss": 0.0657,
      "step": 275
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.996101910454953e-05,
      "loss": 0.0218,
      "step": 276
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9960574998199285e-05,
      "loss": 0.0164,
      "step": 277
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9960128378319825e-05,
      "loss": 0.0219,
      "step": 278
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995967924495611e-05,
      "loss": 0.0198,
      "step": 279
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995922759815339e-05,
      "loss": 0.0133,
      "step": 280
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995877343795714e-05,
      "loss": 0.15,
      "step": 281
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995831676441307e-05,
      "loss": 0.5379,
      "step": 282
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9957857577567197e-05,
      "loss": 0.8015,
      "step": 283
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995739587746574e-05,
      "loss": 0.854,
      "step": 284
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995693166415521e-05,
      "loss": 0.7475,
      "step": 285
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995646493768234e-05,
      "loss": 0.9936,
      "step": 286
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995599569809414e-05,
      "loss": 0.3887,
      "step": 287
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995552394543784e-05,
      "loss": 2.4369,
      "step": 288
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995504967976098e-05,
      "loss": 0.8289,
      "step": 289
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9954572901111286e-05,
      "loss": 1.0428,
      "step": 290
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995409360953679e-05,
      "loss": 1.1485,
      "step": 291
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995361180508575e-05,
      "loss": 1.3428,
      "step": 292
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995312748780668e-05,
      "loss": 1.0792,
      "step": 293
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995264065774836e-05,
      "loss": 1.1226,
      "step": 294
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995215131495981e-05,
      "loss": 1.0069,
      "step": 295
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9951659459490294e-05,
      "loss": 0.883,
      "step": 296
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995116509138936e-05,
      "loss": 1.2333,
      "step": 297
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995066821070679e-05,
      "loss": 0.9823,
      "step": 298
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.995016881749261e-05,
      "loss": 0.5749,
      "step": 299
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994966691179711e-05,
      "loss": 0.9226,
      "step": 300
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.9751874804496765,
      "eval_runtime": 32.4269,
      "eval_samples_per_second": 2.621,
      "eval_steps_per_second": 0.678,
      "step": 300
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994916249367084e-05,
      "loss": 2.3283,
      "step": 301
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994865556316458e-05,
      "loss": 1.2055,
      "step": 302
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9948146120329395e-05,
      "loss": 1.1512,
      "step": 303
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9947634165216584e-05,
      "loss": 1.1801,
      "step": 304
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994711969787769e-05,
      "loss": 1.1417,
      "step": 305
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9946602718364515e-05,
      "loss": 1.188,
      "step": 306
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994608322672914e-05,
      "loss": 1.1506,
      "step": 307
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994556122302386e-05,
      "loss": 1.0243,
      "step": 308
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994503670730125e-05,
      "loss": 0.9896,
      "step": 309
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994450967961413e-05,
      "loss": 0.9248,
      "step": 310
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994398014001557e-05,
      "loss": 0.9892,
      "step": 311
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994344808855888e-05,
      "loss": 1.2689,
      "step": 312
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9942913525297655e-05,
      "loss": 0.49,
      "step": 313
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994237645028572e-05,
      "loss": 0.981,
      "step": 314
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994183686357717e-05,
      "loss": 0.6652,
      "step": 315
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994129476522632e-05,
      "loss": 1.0202,
      "step": 316
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9940750155287775e-05,
      "loss": 0.907,
      "step": 317
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.994020303381636e-05,
      "loss": 0.982,
      "step": 318
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993965340086719e-05,
      "loss": 0.9564,
      "step": 319
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993910125649561e-05,
      "loss": 0.9261,
      "step": 320
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9938546600757205e-05,
      "loss": 0.973,
      "step": 321
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993798943370785e-05,
      "loss": 0.8215,
      "step": 322
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9937429755403634e-05,
      "loss": 0.5894,
      "step": 323
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993686756590093e-05,
      "loss": 1.0626,
      "step": 324
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993630286525634e-05,
      "loss": 1.1192,
      "step": 325
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993573565352674e-05,
      "loss": 1.1525,
      "step": 326
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9935165930769235e-05,
      "loss": 1.7204,
      "step": 327
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.99345936970412e-05,
      "loss": 0.7658,
      "step": 328
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993401895240027e-05,
      "loss": 0.88,
      "step": 329
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993344169690431e-05,
      "loss": 0.7782,
      "step": 330
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9932861930611454e-05,
      "loss": 0.9215,
      "step": 331
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993227965358008e-05,
      "loss": 1.0628,
      "step": 332
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.993169486586884e-05,
      "loss": 1.1187,
      "step": 333
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.99311075675366e-05,
      "loss": 0.78,
      "step": 334
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9930517758642503e-05,
      "loss": 0.8167,
      "step": 335
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992992543924596e-05,
      "loss": 0.9075,
      "step": 336
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992933060940661e-05,
      "loss": 0.9998,
      "step": 337
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992873326918434e-05,
      "loss": 0.7426,
      "step": 338
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9928133418639316e-05,
      "loss": 0.8207,
      "step": 339
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992753105783194e-05,
      "loss": 0.0484,
      "step": 340
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992692618682286e-05,
      "loss": 0.0342,
      "step": 341
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992631880567301e-05,
      "loss": 0.0312,
      "step": 342
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9925708914443526e-05,
      "loss": 0.0224,
      "step": 343
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9925096513195846e-05,
      "loss": 0.0133,
      "step": 344
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992448160199162e-05,
      "loss": 0.0196,
      "step": 345
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992386418089279e-05,
      "loss": 0.0149,
      "step": 346
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992324424996151e-05,
      "loss": 0.0183,
      "step": 347
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992262180926022e-05,
      "loss": 0.0169,
      "step": 348
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992199685885159e-05,
      "loss": 0.023,
      "step": 349
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.992136939879856e-05,
      "loss": 0.0146,
      "step": 350
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.9827541708946228,
      "eval_runtime": 19.9161,
      "eval_samples_per_second": 4.268,
      "eval_steps_per_second": 1.105,
      "step": 350
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.992073942916432e-05,
      "loss": 0.0515,
      "step": 351
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.992010695001229e-05,
      "loss": 0.0209,
      "step": 352
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991947196140618e-05,
      "loss": 0.0136,
      "step": 353
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991883446340992e-05,
      "loss": 0.0157,
      "step": 354
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991819445608772e-05,
      "loss": 0.0119,
      "step": 355
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991755193950401e-05,
      "loss": 0.0135,
      "step": 356
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991690691372352e-05,
      "loss": 0.2149,
      "step": 357
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991625937881116e-05,
      "loss": 0.581,
      "step": 358
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991560933483218e-05,
      "loss": 0.86,
      "step": 359
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991495678185202e-05,
      "loss": 0.7326,
      "step": 360
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9914301719936386e-05,
      "loss": 2.0773,
      "step": 361
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9913644149151256e-05,
      "loss": 1.2954,
      "step": 362
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991298406956284e-05,
      "loss": 0.8239,
      "step": 363
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991232148123761e-05,
      "loss": 1.0969,
      "step": 364
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991165638424229e-05,
      "loss": 1.048,
      "step": 365
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991098877864385e-05,
      "loss": 0.8565,
      "step": 366
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.991031866450953e-05,
      "loss": 1.1061,
      "step": 367
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990964604190679e-05,
      "loss": 0.9706,
      "step": 368
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990897091090338e-05,
      "loss": 1.019,
      "step": 369
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9908293271567286e-05,
      "loss": 0.9736,
      "step": 370
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990761312396673e-05,
      "loss": 0.8045,
      "step": 371
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990693046817023e-05,
      "loss": 1.4812,
      "step": 372
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.99062453042465e-05,
      "loss": 1.0545,
      "step": 373
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990555763226455e-05,
      "loss": 1.3077,
      "step": 374
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990486745229364e-05,
      "loss": 1.0062,
      "step": 375
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9904174764403255e-05,
      "loss": 0.9672,
      "step": 376
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990347956866315e-05,
      "loss": 0.7185,
      "step": 377
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9902781865143326e-05,
      "loss": 0.7711,
      "step": 378
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9902081653914056e-05,
      "loss": 0.9329,
      "step": 379
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.990137893504585e-05,
      "loss": 0.3937,
      "step": 380
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9900673708609455e-05,
      "loss": 0.8259,
      "step": 381
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989996597467591e-05,
      "loss": 1.0272,
      "step": 382
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9899255733316465e-05,
      "loss": 0.9096,
      "step": 383
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9898542984602656e-05,
      "loss": 1.2616,
      "step": 384
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989782772860624e-05,
      "loss": 1.1187,
      "step": 385
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989710996539926e-05,
      "loss": 2.5803,
      "step": 386
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989638969505399e-05,
      "loss": 0.8739,
      "step": 387
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989566691764295e-05,
      "loss": 0.4262,
      "step": 388
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989494163323894e-05,
      "loss": 0.7617,
      "step": 389
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989421384191499e-05,
      "loss": 0.9713,
      "step": 390
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989348354374438e-05,
      "loss": 0.7856,
      "step": 391
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9892750738800664e-05,
      "loss": 1.0108,
      "step": 392
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989201542715762e-05,
      "loss": 0.8895,
      "step": 393
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.989127760888932e-05,
      "loss": 0.8445,
      "step": 394
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9890537284070037e-05,
      "loss": 1.1767,
      "step": 395
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988979445277433e-05,
      "loss": 0.8743,
      "step": 396
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9889049115077005e-05,
      "loss": 1.0314,
      "step": 397
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988830127105311e-05,
      "loss": 0.8971,
      "step": 398
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9887550920777956e-05,
      "loss": 1.0006,
      "step": 399
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988679806432712e-05,
      "loss": 0.8815,
      "step": 400
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.9530295729637146,
      "eval_runtime": 19.0653,
      "eval_samples_per_second": 4.458,
      "eval_steps_per_second": 1.154,
      "step": 400
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988604270177639e-05,
      "loss": 0.9408,
      "step": 401
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988528483320184e-05,
      "loss": 0.8568,
      "step": 402
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988452445867979e-05,
      "loss": 0.9129,
      "step": 403
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.98837615782868e-05,
      "loss": 1.0926,
      "step": 404
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988299619209972e-05,
      "loss": 0.7181,
      "step": 405
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988222830019559e-05,
      "loss": 1.1963,
      "step": 406
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988145790265175e-05,
      "loss": 0.9929,
      "step": 407
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.988068499954578e-05,
      "loss": 1.2016,
      "step": 408
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9879909590955515e-05,
      "loss": 1.2947,
      "step": 409
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.987913167695904e-05,
      "loss": 0.9717,
      "step": 410
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.987835125763468e-05,
      "loss": 0.94,
      "step": 411
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.987756833306102e-05,
      "loss": 0.7971,
      "step": 412
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.987678290331692e-05,
      "loss": 0.7798,
      "step": 413
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9875994968481465e-05,
      "loss": 0.9427,
      "step": 414
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.987520452863399e-05,
      "loss": 0.971,
      "step": 415
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9874411583854106e-05,
      "loss": 0.9795,
      "step": 416
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9873616134221654e-05,
      "loss": 0.9382,
      "step": 417
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.987281817981674e-05,
      "loss": 1.214,
      "step": 418
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.987201772071971e-05,
      "loss": 1.0475,
      "step": 419
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9871214757011176e-05,
      "loss": 0.9213,
      "step": 420
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9870409288772005e-05,
      "loss": 0.7616,
      "step": 421
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9869601316083284e-05,
      "loss": 0.8741,
      "step": 422
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9868790839026404e-05,
      "loss": 1.1203,
      "step": 423
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9867977857682965e-05,
      "loss": 1.0697,
      "step": 424
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.986716237213484e-05,
      "loss": 1.9062,
      "step": 425
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.986634438246413e-05,
      "loss": 0.8906,
      "step": 426
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.986552388875323e-05,
      "loss": 0.5871,
      "step": 427
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9864700891084756e-05,
      "loss": 0.7346,
      "step": 428
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.986387538954158e-05,
      "loss": 1.0784,
      "step": 429
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9863047384206835e-05,
      "loss": 0.8797,
      "step": 430
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9862216875163896e-05,
      "loss": 0.7312,
      "step": 431
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9861383862496405e-05,
      "loss": 0.7475,
      "step": 432
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.986054834628823e-05,
      "loss": 0.7619,
      "step": 433
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985971032662352e-05,
      "loss": 0.8597,
      "step": 434
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985886980358666e-05,
      "loss": 0.5565,
      "step": 435
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9858026777262295e-05,
      "loss": 0.9844,
      "step": 436
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9857181247735306e-05,
      "loss": 0.9608,
      "step": 437
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985633321509085e-05,
      "loss": 0.5236,
      "step": 438
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9855482679414324e-05,
      "loss": 0.9641,
      "step": 439
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985462964079137e-05,
      "loss": 0.684,
      "step": 440
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985377409930789e-05,
      "loss": 0.8992,
      "step": 441
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9852916055050035e-05,
      "loss": 0.9615,
      "step": 442
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985205550810421e-05,
      "loss": 1.1244,
      "step": 443
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985119245855708e-05,
      "loss": 0.561,
      "step": 444
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.985032690649556e-05,
      "loss": 1.3473,
      "step": 445
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984945885200679e-05,
      "loss": 1.1382,
      "step": 446
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984858829517819e-05,
      "loss": 1.2158,
      "step": 447
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984771523609744e-05,
      "loss": 1.1904,
      "step": 448
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984683967485243e-05,
      "loss": 1.2497,
      "step": 449
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984596161153136e-05,
      "loss": 1.2918,
      "step": 450
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.9576648473739624,
      "eval_runtime": 19.5205,
      "eval_samples_per_second": 4.354,
      "eval_steps_per_second": 1.127,
      "step": 450
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9845081046222625e-05,
      "loss": 1.0766,
      "step": 451
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.984419797901491e-05,
      "loss": 0.9402,
      "step": 452
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.984331240999715e-05,
      "loss": 0.8675,
      "step": 453
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.984242433925849e-05,
      "loss": 0.8824,
      "step": 454
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9841533766888395e-05,
      "loss": 0.9028,
      "step": 455
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.984064069297652e-05,
      "loss": 0.9169,
      "step": 456
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9839745117612815e-05,
      "loss": 0.7909,
      "step": 457
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.983884704088745e-05,
      "loss": 1.114,
      "step": 458
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9837946462890866e-05,
      "loss": 0.7843,
      "step": 459
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9837043383713753e-05,
      "loss": 0.7459,
      "step": 460
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.983613780344706e-05,
      "loss": 0.6337,
      "step": 461
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9835229722181964e-05,
      "loss": 0.8813,
      "step": 462
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.983431914000991e-05,
      "loss": 0.8415,
      "step": 463
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.98334060570226e-05,
      "loss": 0.6781,
      "step": 464
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.983249047331199e-05,
      "loss": 0.5927,
      "step": 465
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.983157238897026e-05,
      "loss": 0.4942,
      "step": 466
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9830651804089864e-05,
      "loss": 0.7969,
      "step": 467
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982972871876353e-05,
      "loss": 0.8438,
      "step": 468
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982880313308417e-05,
      "loss": 0.6357,
      "step": 469
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982787504714503e-05,
      "loss": 0.8657,
      "step": 470
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982694446103955e-05,
      "loss": 0.9851,
      "step": 471
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9826011374861435e-05,
      "loss": 0.6133,
      "step": 472
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9825075788704656e-05,
      "loss": 0.8499,
      "step": 473
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982413770266342e-05,
      "loss": 0.9503,
      "step": 474
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982319711683221e-05,
      "loss": 0.6674,
      "step": 475
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982225403130572e-05,
      "loss": 0.6483,
      "step": 476
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9821308446178934e-05,
      "loss": 0.726,
      "step": 477
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.982036036154706e-05,
      "loss": 0.7089,
      "step": 478
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981940977750558e-05,
      "loss": 0.7825,
      "step": 479
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981845669415022e-05,
      "loss": 0.8739,
      "step": 480
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981750111157694e-05,
      "loss": 0.83,
      "step": 481
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981654302988198e-05,
      "loss": 0.5891,
      "step": 482
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981558244916182e-05,
      "loss": 0.8019,
      "step": 483
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9814619369513184e-05,
      "loss": 0.9172,
      "step": 484
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9813653791033057e-05,
      "loss": 0.9098,
      "step": 485
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981268571381867e-05,
      "loss": 1.0725,
      "step": 486
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981171513796751e-05,
      "loss": 0.3633,
      "step": 487
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.981074206357731e-05,
      "loss": 0.7164,
      "step": 488
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9809766490746074e-05,
      "loss": 0.9008,
      "step": 489
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.980878841957203e-05,
      "loss": 0.7623,
      "step": 490
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.980780785015367e-05,
      "loss": 1.4832,
      "step": 491
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9806824782589737e-05,
      "loss": 0.975,
      "step": 492
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.980583921697922e-05,
      "loss": 0.6389,
      "step": 493
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.980485115342138e-05,
      "loss": 0.121,
      "step": 494
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9803860592015704e-05,
      "loss": 0.0237,
      "step": 495
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.980286753286195e-05,
      "loss": 0.0194,
      "step": 496
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.980187197606011e-05,
      "loss": 0.0152,
      "step": 497
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.980087392171045e-05,
      "loss": 0.0164,
      "step": 498
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979987336991345e-05,
      "loss": 0.0165,
      "step": 499
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9798870320769886e-05,
      "loss": 0.0137,
      "step": 500
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.9486321210861206,
      "eval_runtime": 19.1419,
      "eval_samples_per_second": 4.441,
      "eval_steps_per_second": 1.149,
      "step": 500
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979786477438076e-05,
      "loss": 0.0126,
      "step": 501
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979685673084733e-05,
      "loss": 0.0104,
      "step": 502
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.97958461902711e-05,
      "loss": 0.016,
      "step": 503
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979483315275385e-05,
      "loss": 0.0228,
      "step": 504
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979381761839757e-05,
      "loss": 0.0369,
      "step": 505
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979279958730454e-05,
      "loss": 0.0144,
      "step": 506
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979177905957726e-05,
      "loss": 0.0084,
      "step": 507
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.979075603531852e-05,
      "loss": 0.0115,
      "step": 508
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978973051463132e-05,
      "loss": 0.0105,
      "step": 509
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978870249761893e-05,
      "loss": 0.0183,
      "step": 510
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978767198438488e-05,
      "loss": 0.0118,
      "step": 511
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978663897503294e-05,
      "loss": 0.4027,
      "step": 512
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978560346966714e-05,
      "loss": 0.6452,
      "step": 513
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978456546839174e-05,
      "loss": 0.8626,
      "step": 514
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978352497131128e-05,
      "loss": 0.475,
      "step": 515
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978248197853053e-05,
      "loss": 1.0023,
      "step": 516
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978143649015452e-05,
      "loss": 0.2236,
      "step": 517
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.978038850628854e-05,
      "loss": 2.3618,
      "step": 518
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.977933802703812e-05,
      "loss": 0.7232,
      "step": 519
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.977828505250903e-05,
      "loss": 0.8647,
      "step": 520
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9777229582807316e-05,
      "loss": 1.0719,
      "step": 521
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9776171618039264e-05,
      "loss": 1.2616,
      "step": 522
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.977511115831141e-05,
      "loss": 1.0388,
      "step": 523
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9774048203730526e-05,
      "loss": 0.9671,
      "step": 524
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.977298275440368e-05,
      "loss": 0.914,
      "step": 525
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9771914810438144e-05,
      "loss": 0.7392,
      "step": 526
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.977084437194146e-05,
      "loss": 1.0531,
      "step": 527
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976977143902143e-05,
      "loss": 0.8884,
      "step": 528
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976869601178609e-05,
      "loss": 0.5084,
      "step": 529
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9767618090343745e-05,
      "loss": 0.8287,
      "step": 530
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976653767480293e-05,
      "loss": 2.2692,
      "step": 531
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976545476527246e-05,
      "loss": 1.0015,
      "step": 532
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976436936186136e-05,
      "loss": 1.0404,
      "step": 533
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976328146467895e-05,
      "loss": 1.108,
      "step": 534
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9762191073834776e-05,
      "loss": 1.0678,
      "step": 535
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976109818943863e-05,
      "loss": 1.1611,
      "step": 536
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976000281160057e-05,
      "loss": 1.019,
      "step": 537
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.975890494043092e-05,
      "loss": 0.8593,
      "step": 538
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.975780457604021e-05,
      "loss": 0.9699,
      "step": 539
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.975670171853926e-05,
      "loss": 0.8718,
      "step": 540
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.975559636803913e-05,
      "loss": 0.865,
      "step": 541
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.975448852465111e-05,
      "loss": 1.1793,
      "step": 542
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9753378188486776e-05,
      "loss": 0.4275,
      "step": 543
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.975226535965795e-05,
      "loss": 0.8263,
      "step": 544
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.975115003827666e-05,
      "loss": 0.6425,
      "step": 545
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9750032224455244e-05,
      "loss": 0.8046,
      "step": 546
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.974891191830627e-05,
      "loss": 0.8646,
      "step": 547
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.974778911994254e-05,
      "loss": 0.8854,
      "step": 548
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9746663829477113e-05,
      "loss": 0.7902,
      "step": 549
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9745536047023324e-05,
      "loss": 0.908,
      "step": 550
    },
    {
      "epoch": 0.06,
      "eval_loss": 0.9434943795204163,
      "eval_runtime": 19.2357,
      "eval_samples_per_second": 4.419,
      "eval_steps_per_second": 1.144,
      "step": 550
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9744405772694725e-05,
      "loss": 0.9434,
      "step": 551
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.974327300660515e-05,
      "loss": 0.762,
      "step": 552
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.974213774886865e-05,
      "loss": 0.503,
      "step": 553
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.974099999959957e-05,
      "loss": 0.8842,
      "step": 554
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.973985975891245e-05,
      "loss": 1.0368,
      "step": 555
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.973871702692214e-05,
      "loss": 1.037,
      "step": 556
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9737571803743706e-05,
      "loss": 1.6872,
      "step": 557
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.973642408949246e-05,
      "loss": 0.6864,
      "step": 558
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.973527388428399e-05,
      "loss": 0.7262,
      "step": 559
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.973412118823412e-05,
      "loss": 0.6918,
      "step": 560
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9732966001458916e-05,
      "loss": 0.796,
      "step": 561
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9731808324074717e-05,
      "loss": 0.9667,
      "step": 562
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.973064815619809e-05,
      "loss": 1.0184,
      "step": 563
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.972948549794587e-05,
      "loss": 0.6911,
      "step": 564
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.972832034943514e-05,
      "loss": 0.7089,
      "step": 565
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9727152710783235e-05,
      "loss": 0.7468,
      "step": 566
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9725982582107715e-05,
      "loss": 0.8661,
      "step": 567
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.972480996352644e-05,
      "loss": 0.6693,
      "step": 568
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.972363485515746e-05,
      "loss": 0.8081,
      "step": 569
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.972245725711914e-05,
      "loss": 0.0205,
      "step": 570
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.972127716953005e-05,
      "loss": 0.0135,
      "step": 571
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.972009459250903e-05,
      "loss": 0.0154,
      "step": 572
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.971890952617515e-05,
      "loss": 0.0152,
      "step": 573
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9717721970647754e-05,
      "loss": 0.0135,
      "step": 574
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9716531926046446e-05,
      "loss": 0.0149,
      "step": 575
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.971533939249105e-05,
      "loss": 0.014,
      "step": 576
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.971414437010163e-05,
      "loss": 0.01,
      "step": 577
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.971294685899857e-05,
      "loss": 0.0132,
      "step": 578
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9711746859302436e-05,
      "loss": 0.0095,
      "step": 579
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.971054437113406e-05,
      "loss": 0.0153,
      "step": 580
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.970933939461455e-05,
      "loss": 0.0345,
      "step": 581
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.970813192986524e-05,
      "loss": 0.0108,
      "step": 582
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9706921977007714e-05,
      "loss": 0.015,
      "step": 583
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9705709536163824e-05,
      "loss": 0.0153,
      "step": 584
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.970449460745566e-05,
      "loss": 0.0116,
      "step": 585
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9703277191005556e-05,
      "loss": 0.0115,
      "step": 586
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.970205728693613e-05,
      "loss": 0.139,
      "step": 587
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.970083489537021e-05,
      "loss": 0.4434,
      "step": 588
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.969961001643088e-05,
      "loss": 0.7731,
      "step": 589
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.969838265024151e-05,
      "loss": 0.6826,
      "step": 590
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9697152796925674e-05,
      "loss": 1.732,
      "step": 591
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9695920456607226e-05,
      "loss": 1.4832,
      "step": 592
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9694685629410264e-05,
      "loss": 0.7681,
      "step": 593
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.969344831545914e-05,
      "loss": 0.9764,
      "step": 594
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 1.0405,
      "step": 595
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.969096622779303e-05,
      "loss": 0.773,
      "step": 596
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9689721454327985e-05,
      "loss": 0.9574,
      "step": 597
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.968847419460867e-05,
      "loss": 0.9658,
      "step": 598
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9687224448760685e-05,
      "loss": 0.8794,
      "step": 599
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.968597221690986e-05,
      "loss": 0.8777,
      "step": 600
    },
    {
      "epoch": 0.06,
      "eval_loss": 0.93730229139328,
      "eval_runtime": 20.1845,
      "eval_samples_per_second": 4.211,
      "eval_steps_per_second": 1.09,
      "step": 600
    }
  ],
  "logging_steps": 1,
  "max_steps": 10000,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "total_flos": 2.79402856316928e+16,
  "trial_name": null,
  "trial_params": null
}