{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9954545454545455,
  "eval_steps": 500,
  "global_step": 146,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006818181818181818,
      "grad_norm": 1.434646725654602,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 0.8008,
      "step": 1
    },
    {
      "epoch": 0.013636363636363636,
      "grad_norm": 1.3611352443695068,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.7827,
      "step": 2
    },
    {
      "epoch": 0.020454545454545454,
      "grad_norm": 1.2866194248199463,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 0.7693,
      "step": 3
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 1.4324151277542114,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.7688,
      "step": 4
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 1.4685285091400146,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.8055,
      "step": 5
    },
    {
      "epoch": 0.04090909090909091,
      "grad_norm": 1.2799904346466064,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.7496,
      "step": 6
    },
    {
      "epoch": 0.04772727272727273,
      "grad_norm": 1.2374376058578491,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 0.7834,
      "step": 7
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 1.3800737857818604,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.7747,
      "step": 8
    },
    {
      "epoch": 0.06136363636363636,
      "grad_norm": 1.3297126293182373,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 0.7967,
      "step": 9
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 1.2450318336486816,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.7852,
      "step": 10
    },
    {
      "epoch": 0.075,
      "grad_norm": 1.400126338005066,
      "learning_rate": 5.5e-07,
      "loss": 0.7987,
      "step": 11
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 1.3626885414123535,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.7985,
      "step": 12
    },
    {
      "epoch": 0.08863636363636364,
      "grad_norm": 1.3277614116668701,
      "learning_rate": 6.5e-07,
      "loss": 0.7974,
      "step": 13
    },
    {
      "epoch": 0.09545454545454546,
      "grad_norm": 1.3976675271987915,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.8001,
      "step": 14
    },
    {
      "epoch": 0.10227272727272728,
      "grad_norm": 1.387974500656128,
      "learning_rate": 7.5e-07,
      "loss": 0.7876,
      "step": 15
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.309926152229309,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.7541,
      "step": 16
    },
    {
      "epoch": 0.1159090909090909,
      "grad_norm": 1.254166841506958,
      "learning_rate": 8.500000000000001e-07,
      "loss": 0.7551,
      "step": 17
    },
    {
      "epoch": 0.12272727272727273,
      "grad_norm": 1.3773471117019653,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.7951,
      "step": 18
    },
    {
      "epoch": 0.12954545454545455,
      "grad_norm": 1.2885236740112305,
      "learning_rate": 9.500000000000001e-07,
      "loss": 0.7518,
      "step": 19
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 1.298673152923584,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.741,
      "step": 20
    },
    {
      "epoch": 0.1431818181818182,
      "grad_norm": 1.3007020950317383,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 0.7632,
      "step": 21
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.323603630065918,
      "learning_rate": 1.1e-06,
      "loss": 0.7812,
      "step": 22
    },
    {
      "epoch": 0.15681818181818183,
      "grad_norm": 1.1601744890213013,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 0.7623,
      "step": 23
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 1.2862169742584229,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.7791,
      "step": 24
    },
    {
      "epoch": 0.17045454545454544,
      "grad_norm": 1.3574154376983643,
      "learning_rate": 1.25e-06,
      "loss": 0.7791,
      "step": 25
    },
    {
      "epoch": 0.17727272727272728,
      "grad_norm": 1.0806293487548828,
      "learning_rate": 1.3e-06,
      "loss": 0.7583,
      "step": 26
    },
    {
      "epoch": 0.18409090909090908,
      "grad_norm": 1.2130740880966187,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.7439,
      "step": 27
    },
    {
      "epoch": 0.19090909090909092,
      "grad_norm": 1.1230735778808594,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.7657,
      "step": 28
    },
    {
      "epoch": 0.19772727272727272,
      "grad_norm": 0.964364767074585,
      "learning_rate": 1.45e-06,
      "loss": 0.7574,
      "step": 29
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 1.0301142930984497,
      "learning_rate": 1.5e-06,
      "loss": 0.7528,
      "step": 30
    },
    {
      "epoch": 0.21136363636363636,
      "grad_norm": 1.0557504892349243,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.7155,
      "step": 31
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.9934628009796143,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.7,
      "step": 32
    },
    {
      "epoch": 0.225,
      "grad_norm": 1.002088189125061,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.7403,
      "step": 33
    },
    {
      "epoch": 0.2318181818181818,
      "grad_norm": 0.8168452382087708,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.7202,
      "step": 34
    },
    {
      "epoch": 0.23863636363636365,
      "grad_norm": 0.8815924525260925,
      "learning_rate": 1.75e-06,
      "loss": 0.7593,
      "step": 35
    },
    {
      "epoch": 0.24545454545454545,
      "grad_norm": 0.7914003729820251,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.7337,
      "step": 36
    },
    {
      "epoch": 0.25227272727272726,
      "grad_norm": 0.7730265855789185,
      "learning_rate": 1.85e-06,
      "loss": 0.6821,
      "step": 37
    },
    {
      "epoch": 0.2590909090909091,
      "grad_norm": 0.6619182229042053,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.7168,
      "step": 38
    },
    {
      "epoch": 0.26590909090909093,
      "grad_norm": 0.7120696902275085,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.7322,
      "step": 39
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.6825034022331238,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7101,
      "step": 40
    },
    {
      "epoch": 0.27954545454545454,
      "grad_norm": 0.7088951468467712,
      "learning_rate": 2.05e-06,
      "loss": 0.6809,
      "step": 41
    },
    {
      "epoch": 0.2863636363636364,
      "grad_norm": 0.6460469365119934,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.6447,
      "step": 42
    },
    {
      "epoch": 0.29318181818181815,
      "grad_norm": 0.6034916043281555,
      "learning_rate": 2.15e-06,
      "loss": 0.6843,
      "step": 43
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5842302441596985,
      "learning_rate": 2.2e-06,
      "loss": 0.6937,
      "step": 44
    },
    {
      "epoch": 0.3068181818181818,
      "grad_norm": 0.598784863948822,
      "learning_rate": 2.25e-06,
      "loss": 0.6676,
      "step": 45
    },
    {
      "epoch": 0.31363636363636366,
      "grad_norm": 0.6409489512443542,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.6554,
      "step": 46
    },
    {
      "epoch": 0.32045454545454544,
      "grad_norm": 0.615486741065979,
      "learning_rate": 2.35e-06,
      "loss": 0.7171,
      "step": 47
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.5648443698883057,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.6383,
      "step": 48
    },
    {
      "epoch": 0.3340909090909091,
      "grad_norm": 0.6393448114395142,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.6778,
      "step": 49
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.6069231629371643,
      "learning_rate": 2.5e-06,
      "loss": 0.6717,
      "step": 50
    },
    {
      "epoch": 0.3477272727272727,
      "grad_norm": 0.7063543200492859,
      "learning_rate": 2.55e-06,
      "loss": 0.7006,
      "step": 51
    },
    {
      "epoch": 0.35454545454545455,
      "grad_norm": 0.600916862487793,
      "learning_rate": 2.6e-06,
      "loss": 0.649,
      "step": 52
    },
    {
      "epoch": 0.3613636363636364,
      "grad_norm": 0.6185877323150635,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.6702,
      "step": 53
    },
    {
      "epoch": 0.36818181818181817,
      "grad_norm": 0.6063259243965149,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.6461,
      "step": 54
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.5525023937225342,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.6613,
      "step": 55
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.49498245120048523,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.651,
      "step": 56
    },
    {
      "epoch": 0.3886363636363636,
      "grad_norm": 0.5330650210380554,
      "learning_rate": 2.85e-06,
      "loss": 0.6416,
      "step": 57
    },
    {
      "epoch": 0.39545454545454545,
      "grad_norm": 0.5402539372444153,
      "learning_rate": 2.9e-06,
      "loss": 0.6257,
      "step": 58
    },
    {
      "epoch": 0.4022727272727273,
      "grad_norm": 0.49151986837387085,
      "learning_rate": 2.95e-06,
      "loss": 0.6292,
      "step": 59
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.5251104235649109,
      "learning_rate": 3e-06,
      "loss": 0.666,
      "step": 60
    },
    {
      "epoch": 0.4159090909090909,
      "grad_norm": 0.57887202501297,
      "learning_rate": 3.05e-06,
      "loss": 0.642,
      "step": 61
    },
    {
      "epoch": 0.42272727272727273,
      "grad_norm": 0.4779260456562042,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.5885,
      "step": 62
    },
    {
      "epoch": 0.42954545454545456,
      "grad_norm": 0.6516481637954712,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.6399,
      "step": 63
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.49200090765953064,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.6412,
      "step": 64
    },
    {
      "epoch": 0.4431818181818182,
      "grad_norm": 0.520231306552887,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.6276,
      "step": 65
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4746171832084656,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.6066,
      "step": 66
    },
    {
      "epoch": 0.45681818181818185,
      "grad_norm": 0.5491726994514465,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.5975,
      "step": 67
    },
    {
      "epoch": 0.4636363636363636,
      "grad_norm": 0.5318092107772827,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.6276,
      "step": 68
    },
    {
      "epoch": 0.47045454545454546,
      "grad_norm": 0.7567431330680847,
      "learning_rate": 3.45e-06,
      "loss": 0.6252,
      "step": 69
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.5506855845451355,
      "learning_rate": 3.5e-06,
      "loss": 0.6384,
      "step": 70
    },
    {
      "epoch": 0.48409090909090907,
      "grad_norm": 0.5070034265518188,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.5928,
      "step": 71
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 0.4772234559059143,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.5974,
      "step": 72
    },
    {
      "epoch": 0.49772727272727274,
      "grad_norm": 0.5434151887893677,
      "learning_rate": 3.65e-06,
      "loss": 0.6112,
      "step": 73
    },
    {
      "epoch": 0.5045454545454545,
      "grad_norm": 0.45374104380607605,
      "learning_rate": 3.7e-06,
      "loss": 0.6187,
      "step": 74
    },
    {
      "epoch": 0.5113636363636364,
      "grad_norm": 0.4568059742450714,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.6256,
      "step": 75
    },
    {
      "epoch": 0.5181818181818182,
      "grad_norm": 0.5239875912666321,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.6251,
      "step": 76
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.48844802379608154,
      "learning_rate": 3.85e-06,
      "loss": 0.5859,
      "step": 77
    },
    {
      "epoch": 0.5318181818181819,
      "grad_norm": 0.43856486678123474,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.6124,
      "step": 78
    },
    {
      "epoch": 0.5386363636363637,
      "grad_norm": 0.45667290687561035,
      "learning_rate": 3.95e-06,
      "loss": 0.5992,
      "step": 79
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.46727287769317627,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6088,
      "step": 80
    },
    {
      "epoch": 0.5522727272727272,
      "grad_norm": 0.45850586891174316,
      "learning_rate": 4.05e-06,
      "loss": 0.6154,
      "step": 81
    },
    {
      "epoch": 0.5590909090909091,
      "grad_norm": 0.5913473963737488,
      "learning_rate": 4.1e-06,
      "loss": 0.6224,
      "step": 82
    },
    {
      "epoch": 0.5659090909090909,
      "grad_norm": 0.4341784715652466,
      "learning_rate": 4.15e-06,
      "loss": 0.618,
      "step": 83
    },
    {
      "epoch": 0.5727272727272728,
      "grad_norm": 0.46108976006507874,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.5813,
      "step": 84
    },
    {
      "epoch": 0.5795454545454546,
      "grad_norm": 0.4961765706539154,
      "learning_rate": 4.25e-06,
      "loss": 0.5969,
      "step": 85
    },
    {
      "epoch": 0.5863636363636363,
      "grad_norm": 0.43796494603157043,
      "learning_rate": 4.3e-06,
      "loss": 0.6036,
      "step": 86
    },
    {
      "epoch": 0.5931818181818181,
      "grad_norm": 0.43516144156455994,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.5799,
      "step": 87
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4538296163082123,
      "learning_rate": 4.4e-06,
      "loss": 0.6125,
      "step": 88
    },
    {
      "epoch": 0.6068181818181818,
      "grad_norm": 0.4108039140701294,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.6107,
      "step": 89
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.428292453289032,
      "learning_rate": 4.5e-06,
      "loss": 0.599,
      "step": 90
    },
    {
      "epoch": 0.6204545454545455,
      "grad_norm": 0.5008049607276917,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.6025,
      "step": 91
    },
    {
      "epoch": 0.6272727272727273,
      "grad_norm": 0.4718039631843567,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.5483,
      "step": 92
    },
    {
      "epoch": 0.634090909090909,
      "grad_norm": 0.47552117705345154,
      "learning_rate": 4.65e-06,
      "loss": 0.6048,
      "step": 93
    },
    {
      "epoch": 0.6409090909090909,
      "grad_norm": 0.40332990884780884,
      "learning_rate": 4.7e-06,
      "loss": 0.5916,
      "step": 94
    },
    {
      "epoch": 0.6477272727272727,
      "grad_norm": 0.47048062086105347,
      "learning_rate": 4.75e-06,
      "loss": 0.611,
      "step": 95
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.6233271956443787,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.5821,
      "step": 96
    },
    {
      "epoch": 0.6613636363636364,
      "grad_norm": 0.4700981676578522,
      "learning_rate": 4.85e-06,
      "loss": 0.5937,
      "step": 97
    },
    {
      "epoch": 0.6681818181818182,
      "grad_norm": 0.4266382157802582,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.6084,
      "step": 98
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.48668500781059265,
      "learning_rate": 4.95e-06,
      "loss": 0.5846,
      "step": 99
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.588253915309906,
      "learning_rate": 5e-06,
      "loss": 0.6163,
      "step": 100
    },
    {
      "epoch": 0.6886363636363636,
      "grad_norm": 0.4984593093395233,
      "learning_rate": 4.9999795126530275e-06,
      "loss": 0.6173,
      "step": 101
    },
    {
      "epoch": 0.6954545454545454,
      "grad_norm": 0.5198028087615967,
      "learning_rate": 4.999918050947891e-06,
      "loss": 0.5782,
      "step": 102
    },
    {
      "epoch": 0.7022727272727273,
      "grad_norm": 0.45491915941238403,
      "learning_rate": 4.999815615891943e-06,
      "loss": 0.5935,
      "step": 103
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.5883018970489502,
      "learning_rate": 4.9996722091640805e-06,
      "loss": 0.5771,
      "step": 104
    },
    {
      "epoch": 0.7159090909090909,
      "grad_norm": 0.8883517384529114,
      "learning_rate": 4.9994878331147225e-06,
      "loss": 0.5862,
      "step": 105
    },
    {
      "epoch": 0.7227272727272728,
      "grad_norm": 0.4979236423969269,
      "learning_rate": 4.99926249076577e-06,
      "loss": 0.5418,
      "step": 106
    },
    {
      "epoch": 0.7295454545454545,
      "grad_norm": 0.44228366017341614,
      "learning_rate": 4.998996185810557e-06,
      "loss": 0.5904,
      "step": 107
    },
    {
      "epoch": 0.7363636363636363,
      "grad_norm": 0.4653695523738861,
      "learning_rate": 4.998688922613788e-06,
      "loss": 0.5751,
      "step": 108
    },
    {
      "epoch": 0.7431818181818182,
      "grad_norm": 0.5233970880508423,
      "learning_rate": 4.9983407062114695e-06,
      "loss": 0.5769,
      "step": 109
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.45305246114730835,
      "learning_rate": 4.9979515423108255e-06,
      "loss": 0.5987,
      "step": 110
    },
    {
      "epoch": 0.7568181818181818,
      "grad_norm": 0.48286813497543335,
      "learning_rate": 4.997521437290205e-06,
      "loss": 0.584,
      "step": 111
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.619292140007019,
      "learning_rate": 4.997050398198977e-06,
      "loss": 0.5984,
      "step": 112
    },
    {
      "epoch": 0.7704545454545455,
      "grad_norm": 0.519248902797699,
      "learning_rate": 4.996538432757414e-06,
      "loss": 0.6063,
      "step": 113
    },
    {
      "epoch": 0.7772727272727272,
      "grad_norm": 0.4723324477672577,
      "learning_rate": 4.995985549356568e-06,
      "loss": 0.5729,
      "step": 114
    },
    {
      "epoch": 0.7840909090909091,
      "grad_norm": 1.6759965419769287,
      "learning_rate": 4.995391757058129e-06,
      "loss": 0.5715,
      "step": 115
    },
    {
      "epoch": 0.7909090909090909,
      "grad_norm": 0.4929729998111725,
      "learning_rate": 4.99475706559428e-06,
      "loss": 0.5851,
      "step": 116
    },
    {
      "epoch": 0.7977272727272727,
      "grad_norm": 0.5491468906402588,
      "learning_rate": 4.994081485367537e-06,
      "loss": 0.5611,
      "step": 117
    },
    {
      "epoch": 0.8045454545454546,
      "grad_norm": 0.4642564654350281,
      "learning_rate": 4.993365027450576e-06,
      "loss": 0.5826,
      "step": 118
    },
    {
      "epoch": 0.8113636363636364,
      "grad_norm": 0.7455803751945496,
      "learning_rate": 4.992607703586058e-06,
      "loss": 0.5611,
      "step": 119
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.5237230658531189,
      "learning_rate": 4.991809526186424e-06,
      "loss": 0.5948,
      "step": 120
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.44459426403045654,
      "learning_rate": 4.990970508333707e-06,
      "loss": 0.5733,
      "step": 121
    },
    {
      "epoch": 0.8318181818181818,
      "grad_norm": 0.5403085350990295,
      "learning_rate": 4.990090663779305e-06,
      "loss": 0.5492,
      "step": 122
    },
    {
      "epoch": 0.8386363636363636,
      "grad_norm": 0.43158480525016785,
      "learning_rate": 4.9891700069437635e-06,
      "loss": 0.5807,
      "step": 123
    },
    {
      "epoch": 0.8454545454545455,
      "grad_norm": 0.4388655126094818,
      "learning_rate": 4.988208552916535e-06,
      "loss": 0.5953,
      "step": 124
    },
    {
      "epoch": 0.8522727272727273,
      "grad_norm": 0.47692254185676575,
      "learning_rate": 4.987206317455734e-06,
      "loss": 0.5644,
      "step": 125
    },
    {
      "epoch": 0.8590909090909091,
      "grad_norm": 0.6617960929870605,
      "learning_rate": 4.986163316987877e-06,
      "loss": 0.524,
      "step": 126
    },
    {
      "epoch": 0.865909090909091,
      "grad_norm": 0.4495430588722229,
      "learning_rate": 4.985079568607613e-06,
      "loss": 0.5883,
      "step": 127
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.461193323135376,
      "learning_rate": 4.983955090077445e-06,
      "loss": 0.5618,
      "step": 128
    },
    {
      "epoch": 0.8795454545454545,
      "grad_norm": 0.4458140432834625,
      "learning_rate": 4.982789899827439e-06,
      "loss": 0.5675,
      "step": 129
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.48425722122192383,
      "learning_rate": 4.9815840169549216e-06,
      "loss": 0.5685,
      "step": 130
    },
    {
      "epoch": 0.8931818181818182,
      "grad_norm": 0.9677756428718567,
      "learning_rate": 4.980337461224164e-06,
      "loss": 0.574,
      "step": 131
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.6840249300003052,
      "learning_rate": 4.979050253066064e-06,
      "loss": 0.5413,
      "step": 132
    },
    {
      "epoch": 0.9068181818181819,
      "grad_norm": 0.45734715461730957,
      "learning_rate": 4.977722413577802e-06,
      "loss": 0.5728,
      "step": 133
    },
    {
      "epoch": 0.9136363636363637,
      "grad_norm": 0.4468136131763458,
      "learning_rate": 4.976353964522509e-06,
      "loss": 0.5712,
      "step": 134
    },
    {
      "epoch": 0.9204545454545454,
      "grad_norm": 0.4223119914531708,
      "learning_rate": 4.974944928328894e-06,
      "loss": 0.5409,
      "step": 135
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.626460611820221,
      "learning_rate": 4.973495328090891e-06,
      "loss": 0.5768,
      "step": 136
    },
    {
      "epoch": 0.9340909090909091,
      "grad_norm": 0.4360118806362152,
      "learning_rate": 4.972005187567267e-06,
      "loss": 0.5657,
      "step": 137
    },
    {
      "epoch": 0.9409090909090909,
      "grad_norm": 0.4545884430408478,
      "learning_rate": 4.970474531181245e-06,
      "loss": 0.5548,
      "step": 138
    },
    {
      "epoch": 0.9477272727272728,
      "grad_norm": 0.49536797404289246,
      "learning_rate": 4.968903384020095e-06,
      "loss": 0.5522,
      "step": 139
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.5587348937988281,
      "learning_rate": 4.967291771834727e-06,
      "loss": 0.5768,
      "step": 140
    },
    {
      "epoch": 0.9613636363636363,
      "grad_norm": 0.46643808484077454,
      "learning_rate": 4.965639721039267e-06,
      "loss": 0.5556,
      "step": 141
    },
    {
      "epoch": 0.9681818181818181,
      "grad_norm": 0.4519246220588684,
      "learning_rate": 4.963947258710626e-06,
      "loss": 0.5549,
      "step": 142
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.4627818465232849,
      "learning_rate": 4.962214412588053e-06,
      "loss": 0.5764,
      "step": 143
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.46668827533721924,
      "learning_rate": 4.960441211072686e-06,
      "loss": 0.5287,
      "step": 144
    },
    {
      "epoch": 0.9886363636363636,
      "grad_norm": 0.44447973370552063,
      "learning_rate": 4.9586276832270785e-06,
      "loss": 0.556,
      "step": 145
    },
    {
      "epoch": 0.9954545454545455,
      "grad_norm": 0.47608426213264465,
      "learning_rate": 4.9567738587747314e-06,
      "loss": 0.5544,
      "step": 146
    }
  ],
  "logging_steps": 1,
  "max_steps": 876,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 146,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.39244756481029e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}