{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9815668202764978,
  "eval_steps": 500,
  "global_step": 144,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013824884792626729,
      "grad_norm": 31.00213623046875,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.2089,
      "step": 1
    },
    {
      "epoch": 0.027649769585253458,
      "grad_norm": 30.27136993408203,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.1536,
      "step": 2
    },
    {
      "epoch": 0.041474654377880185,
      "grad_norm": 30.48703384399414,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.1581,
      "step": 3
    },
    {
      "epoch": 0.055299539170506916,
      "grad_norm": 30.779329299926758,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.1741,
      "step": 4
    },
    {
      "epoch": 0.06912442396313365,
      "grad_norm": 31.22808837890625,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.1864,
      "step": 5
    },
    {
      "epoch": 0.08294930875576037,
      "grad_norm": 30.783327102661133,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.1993,
      "step": 6
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 30.57423210144043,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.1506,
      "step": 7
    },
    {
      "epoch": 0.11059907834101383,
      "grad_norm": 30.952186584472656,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.1599,
      "step": 8
    },
    {
      "epoch": 0.12442396313364056,
      "grad_norm": 30.37245750427246,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.1572,
      "step": 9
    },
    {
      "epoch": 0.1382488479262673,
      "grad_norm": 30.930192947387695,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.1447,
      "step": 10
    },
    {
      "epoch": 0.15207373271889402,
      "grad_norm": 29.735448837280273,
      "learning_rate": 5.5e-07,
      "loss": 2.0742,
      "step": 11
    },
    {
      "epoch": 0.16589861751152074,
      "grad_norm": 29.62826156616211,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.061,
      "step": 12
    },
    {
      "epoch": 0.17972350230414746,
      "grad_norm": 28.937463760375977,
      "learning_rate": 6.5e-07,
      "loss": 1.9974,
      "step": 13
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 29.24833106994629,
      "learning_rate": 7.000000000000001e-07,
      "loss": 1.9833,
      "step": 14
    },
    {
      "epoch": 0.2073732718894009,
      "grad_norm": 28.122018814086914,
      "learning_rate": 7.5e-07,
      "loss": 1.8934,
      "step": 15
    },
    {
      "epoch": 0.22119815668202766,
      "grad_norm": 28.059659957885742,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.875,
      "step": 16
    },
    {
      "epoch": 0.2350230414746544,
      "grad_norm": 27.361961364746094,
      "learning_rate": 8.500000000000001e-07,
      "loss": 1.8009,
      "step": 17
    },
    {
      "epoch": 0.2488479262672811,
      "grad_norm": 26.721765518188477,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.7116,
      "step": 18
    },
    {
      "epoch": 0.2626728110599078,
      "grad_norm": 25.37330436706543,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.5608,
      "step": 19
    },
    {
      "epoch": 0.2764976958525346,
      "grad_norm": 25.81206703186035,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.5043,
      "step": 20
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 25.539344787597656,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.3673,
      "step": 21
    },
    {
      "epoch": 0.30414746543778803,
      "grad_norm": 25.097164154052734,
      "learning_rate": 1.1e-06,
      "loss": 1.2029,
      "step": 22
    },
    {
      "epoch": 0.31797235023041476,
      "grad_norm": 24.619497299194336,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.0458,
      "step": 23
    },
    {
      "epoch": 0.3317972350230415,
      "grad_norm": 23.820302963256836,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.8723,
      "step": 24
    },
    {
      "epoch": 0.3456221198156682,
      "grad_norm": 23.12735939025879,
      "learning_rate": 1.25e-06,
      "loss": 0.7183,
      "step": 25
    },
    {
      "epoch": 0.35944700460829493,
      "grad_norm": 20.127134323120117,
      "learning_rate": 1.3e-06,
      "loss": 0.5248,
      "step": 26
    },
    {
      "epoch": 0.37327188940092165,
      "grad_norm": 15.901495933532715,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.3689,
      "step": 27
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 11.053832054138184,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.2482,
      "step": 28
    },
    {
      "epoch": 0.4009216589861751,
      "grad_norm": 7.248495578765869,
      "learning_rate": 1.45e-06,
      "loss": 0.1847,
      "step": 29
    },
    {
      "epoch": 0.4147465437788018,
      "grad_norm": 5.378540515899658,
      "learning_rate": 1.5e-06,
      "loss": 0.1423,
      "step": 30
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 3.8371808528900146,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1152,
      "step": 31
    },
    {
      "epoch": 0.4423963133640553,
      "grad_norm": 2.2655274868011475,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0845,
      "step": 32
    },
    {
      "epoch": 0.45622119815668205,
      "grad_norm": 1.5746861696243286,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0711,
      "step": 33
    },
    {
      "epoch": 0.4700460829493088,
      "grad_norm": 1.3510947227478027,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0734,
      "step": 34
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.9737389087677002,
      "learning_rate": 1.75e-06,
      "loss": 0.0651,
      "step": 35
    },
    {
      "epoch": 0.4976958525345622,
      "grad_norm": 0.9815284609794617,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0593,
      "step": 36
    },
    {
      "epoch": 0.511520737327189,
      "grad_norm": 0.8567912578582764,
      "learning_rate": 1.85e-06,
      "loss": 0.0543,
      "step": 37
    },
    {
      "epoch": 0.5253456221198156,
      "grad_norm": 0.6773302555084229,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0622,
      "step": 38
    },
    {
      "epoch": 0.5391705069124424,
      "grad_norm": 0.49936285614967346,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0511,
      "step": 39
    },
    {
      "epoch": 0.5529953917050692,
      "grad_norm": 0.6253588795661926,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0478,
      "step": 40
    },
    {
      "epoch": 0.5668202764976958,
      "grad_norm": 0.5103089809417725,
      "learning_rate": 2.05e-06,
      "loss": 0.0465,
      "step": 41
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 0.29294702410697937,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0456,
      "step": 42
    },
    {
      "epoch": 0.5944700460829493,
      "grad_norm": 0.4237954616546631,
      "learning_rate": 2.15e-06,
      "loss": 0.0501,
      "step": 43
    },
    {
      "epoch": 0.6082949308755761,
      "grad_norm": 0.42243412137031555,
      "learning_rate": 2.2e-06,
      "loss": 0.0388,
      "step": 44
    },
    {
      "epoch": 0.6221198156682027,
      "grad_norm": 0.37881818413734436,
      "learning_rate": 2.25e-06,
      "loss": 0.0415,
      "step": 45
    },
    {
      "epoch": 0.6359447004608295,
      "grad_norm": 0.4941152036190033,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.045,
      "step": 46
    },
    {
      "epoch": 0.6497695852534562,
      "grad_norm": 0.3046450912952423,
      "learning_rate": 2.35e-06,
      "loss": 0.0386,
      "step": 47
    },
    {
      "epoch": 0.663594470046083,
      "grad_norm": 0.39361852407455444,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0447,
      "step": 48
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 0.5190001130104065,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0364,
      "step": 49
    },
    {
      "epoch": 0.6912442396313364,
      "grad_norm": 0.372072696685791,
      "learning_rate": 2.5e-06,
      "loss": 0.043,
      "step": 50
    },
    {
      "epoch": 0.7050691244239631,
      "grad_norm": 0.3756551146507263,
      "learning_rate": 2.55e-06,
      "loss": 0.0424,
      "step": 51
    },
    {
      "epoch": 0.7188940092165899,
      "grad_norm": 0.4593554437160492,
      "learning_rate": 2.6e-06,
      "loss": 0.0387,
      "step": 52
    },
    {
      "epoch": 0.7327188940092166,
      "grad_norm": 0.2931855618953705,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0396,
      "step": 53
    },
    {
      "epoch": 0.7465437788018433,
      "grad_norm": 0.38429534435272217,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0373,
      "step": 54
    },
    {
      "epoch": 0.7603686635944701,
      "grad_norm": 0.3506857752799988,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.04,
      "step": 55
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.29847028851509094,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0369,
      "step": 56
    },
    {
      "epoch": 0.7880184331797235,
      "grad_norm": 0.3653375506401062,
      "learning_rate": 2.85e-06,
      "loss": 0.0396,
      "step": 57
    },
    {
      "epoch": 0.8018433179723502,
      "grad_norm": 0.3163083791732788,
      "learning_rate": 2.9e-06,
      "loss": 0.0337,
      "step": 58
    },
    {
      "epoch": 0.815668202764977,
      "grad_norm": 0.3734363615512848,
      "learning_rate": 2.95e-06,
      "loss": 0.0327,
      "step": 59
    },
    {
      "epoch": 0.8294930875576036,
      "grad_norm": 0.29547712206840515,
      "learning_rate": 3e-06,
      "loss": 0.0365,
      "step": 60
    },
    {
      "epoch": 0.8433179723502304,
      "grad_norm": 0.4041007161140442,
      "learning_rate": 3.05e-06,
      "loss": 0.038,
      "step": 61
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3602149784564972,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.033,
      "step": 62
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 0.2948857545852661,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0386,
      "step": 63
    },
    {
      "epoch": 0.8847926267281107,
      "grad_norm": 0.39098358154296875,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0323,
      "step": 64
    },
    {
      "epoch": 0.8986175115207373,
      "grad_norm": 0.3692062795162201,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0309,
      "step": 65
    },
    {
      "epoch": 0.9124423963133641,
      "grad_norm": 0.3967229425907135,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0346,
      "step": 66
    },
    {
      "epoch": 0.9262672811059908,
      "grad_norm": 0.47776708006858826,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0355,
      "step": 67
    },
    {
      "epoch": 0.9400921658986175,
      "grad_norm": 0.21545131504535675,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0294,
      "step": 68
    },
    {
      "epoch": 0.9539170506912442,
      "grad_norm": 0.23738539218902588,
      "learning_rate": 3.45e-06,
      "loss": 0.0308,
      "step": 69
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 0.29174014925956726,
      "learning_rate": 3.5e-06,
      "loss": 0.0312,
      "step": 70
    },
    {
      "epoch": 0.9815668202764977,
      "grad_norm": 0.38475602865219116,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0324,
      "step": 71
    },
    {
      "epoch": 0.9953917050691244,
      "grad_norm": 0.4077378809452057,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0297,
      "step": 72
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4077378809452057,
      "learning_rate": 3.65e-06,
      "loss": 0.031,
      "step": 73
    },
    {
      "epoch": 1.0138248847926268,
      "grad_norm": 0.46581539511680603,
      "learning_rate": 3.7e-06,
      "loss": 0.0313,
      "step": 74
    },
    {
      "epoch": 1.0276497695852536,
      "grad_norm": 0.24417200684547424,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.027,
      "step": 75
    },
    {
      "epoch": 1.0414746543778801,
      "grad_norm": 0.20425117015838623,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0307,
      "step": 76
    },
    {
      "epoch": 1.055299539170507,
      "grad_norm": 0.3578161597251892,
      "learning_rate": 3.85e-06,
      "loss": 0.0312,
      "step": 77
    },
    {
      "epoch": 1.0691244239631337,
      "grad_norm": 0.39486679434776306,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0294,
      "step": 78
    },
    {
      "epoch": 1.0829493087557605,
      "grad_norm": 0.3932795226573944,
      "learning_rate": 3.95e-06,
      "loss": 0.0307,
      "step": 79
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 0.2946235239505768,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0257,
      "step": 80
    },
    {
      "epoch": 1.1105990783410138,
      "grad_norm": 0.3318672776222229,
      "learning_rate": 4.05e-06,
      "loss": 0.0296,
      "step": 81
    },
    {
      "epoch": 1.1244239631336406,
      "grad_norm": 0.23701588809490204,
      "learning_rate": 4.1e-06,
      "loss": 0.0298,
      "step": 82
    },
    {
      "epoch": 1.1382488479262673,
      "grad_norm": 0.2415941059589386,
      "learning_rate": 4.15e-06,
      "loss": 0.0256,
      "step": 83
    },
    {
      "epoch": 1.1520737327188941,
      "grad_norm": 0.24098087847232819,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0263,
      "step": 84
    },
    {
      "epoch": 1.1658986175115207,
      "grad_norm": 0.3530103862285614,
      "learning_rate": 4.25e-06,
      "loss": 0.0308,
      "step": 85
    },
    {
      "epoch": 1.1797235023041475,
      "grad_norm": 0.2382838875055313,
      "learning_rate": 4.3e-06,
      "loss": 0.0254,
      "step": 86
    },
    {
      "epoch": 1.1935483870967742,
      "grad_norm": 0.2670588791370392,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0255,
      "step": 87
    },
    {
      "epoch": 1.2073732718894008,
      "grad_norm": 0.30723804235458374,
      "learning_rate": 4.4e-06,
      "loss": 0.0263,
      "step": 88
    },
    {
      "epoch": 1.2211981566820276,
      "grad_norm": 0.505890965461731,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0265,
      "step": 89
    },
    {
      "epoch": 1.2350230414746544,
      "grad_norm": 0.24307991564273834,
      "learning_rate": 4.5e-06,
      "loss": 0.0227,
      "step": 90
    },
    {
      "epoch": 1.2488479262672811,
      "grad_norm": 0.2198561429977417,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0261,
      "step": 91
    },
    {
      "epoch": 1.262672811059908,
      "grad_norm": 0.2435183823108673,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0225,
      "step": 92
    },
    {
      "epoch": 1.2764976958525347,
      "grad_norm": 0.18837811052799225,
      "learning_rate": 4.65e-06,
      "loss": 0.0218,
      "step": 93
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.3818771541118622,
      "learning_rate": 4.7e-06,
      "loss": 0.0223,
      "step": 94
    },
    {
      "epoch": 1.304147465437788,
      "grad_norm": 0.2358720600605011,
      "learning_rate": 4.75e-06,
      "loss": 0.0204,
      "step": 95
    },
    {
      "epoch": 1.3179723502304148,
      "grad_norm": 0.25374144315719604,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.022,
      "step": 96
    },
    {
      "epoch": 1.3317972350230414,
      "grad_norm": 0.36181601881980896,
      "learning_rate": 4.85e-06,
      "loss": 0.0244,
      "step": 97
    },
    {
      "epoch": 1.3456221198156681,
      "grad_norm": 0.3156590759754181,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0233,
      "step": 98
    },
    {
      "epoch": 1.359447004608295,
      "grad_norm": 0.21958638727664948,
      "learning_rate": 4.95e-06,
      "loss": 0.0218,
      "step": 99
    },
    {
      "epoch": 1.3732718894009217,
      "grad_norm": 0.34455621242523193,
      "learning_rate": 5e-06,
      "loss": 0.0267,
      "step": 100
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 0.283086359500885,
      "learning_rate": 4.999888074163108e-06,
      "loss": 0.0238,
      "step": 101
    },
    {
      "epoch": 1.400921658986175,
      "grad_norm": 0.28856486082077026,
      "learning_rate": 4.999552306674345e-06,
      "loss": 0.0186,
      "step": 102
    },
    {
      "epoch": 1.4147465437788018,
      "grad_norm": 0.26721692085266113,
      "learning_rate": 4.998992727598557e-06,
      "loss": 0.0193,
      "step": 103
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.3459971249103546,
      "learning_rate": 4.998209387040829e-06,
      "loss": 0.0218,
      "step": 104
    },
    {
      "epoch": 1.4423963133640554,
      "grad_norm": 0.25979122519493103,
      "learning_rate": 4.9972023551419995e-06,
      "loss": 0.0216,
      "step": 105
    },
    {
      "epoch": 1.456221198156682,
      "grad_norm": 0.19960424304008484,
      "learning_rate": 4.995971722072379e-06,
      "loss": 0.0176,
      "step": 106
    },
    {
      "epoch": 1.4700460829493087,
      "grad_norm": 0.2529441714286804,
      "learning_rate": 4.9945175980236745e-06,
      "loss": 0.0181,
      "step": 107
    },
    {
      "epoch": 1.4838709677419355,
      "grad_norm": 0.2690267264842987,
      "learning_rate": 4.992840113199131e-06,
      "loss": 0.0196,
      "step": 108
    },
    {
      "epoch": 1.4976958525345623,
      "grad_norm": 0.3516470789909363,
      "learning_rate": 4.990939417801859e-06,
      "loss": 0.0182,
      "step": 109
    },
    {
      "epoch": 1.511520737327189,
      "grad_norm": 0.30167508125305176,
      "learning_rate": 4.988815682021398e-06,
      "loss": 0.0205,
      "step": 110
    },
    {
      "epoch": 1.5253456221198156,
      "grad_norm": 0.3920849859714508,
      "learning_rate": 4.986469096018472e-06,
      "loss": 0.0177,
      "step": 111
    },
    {
      "epoch": 1.5391705069124424,
      "grad_norm": 0.3274078369140625,
      "learning_rate": 4.983899869907963e-06,
      "loss": 0.0185,
      "step": 112
    },
    {
      "epoch": 1.5529953917050692,
      "grad_norm": 0.2237282395362854,
      "learning_rate": 4.981108233740096e-06,
      "loss": 0.016,
      "step": 113
    },
    {
      "epoch": 1.5668202764976957,
      "grad_norm": 0.23966379463672638,
      "learning_rate": 4.978094437479843e-06,
      "loss": 0.0183,
      "step": 114
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": 0.4027673602104187,
      "learning_rate": 4.97485875098454e-06,
      "loss": 0.0171,
      "step": 115
    },
    {
      "epoch": 1.5944700460829493,
      "grad_norm": 0.24082835018634796,
      "learning_rate": 4.971401463979722e-06,
      "loss": 0.016,
      "step": 116
    },
    {
      "epoch": 1.608294930875576,
      "grad_norm": 0.19387558102607727,
      "learning_rate": 4.967722886033181e-06,
      "loss": 0.0165,
      "step": 117
    },
    {
      "epoch": 1.6221198156682028,
      "grad_norm": 0.33696162700653076,
      "learning_rate": 4.963823346527249e-06,
      "loss": 0.0154,
      "step": 118
    },
    {
      "epoch": 1.6359447004608296,
      "grad_norm": 0.30290740728378296,
      "learning_rate": 4.959703194629304e-06,
      "loss": 0.0175,
      "step": 119
    },
    {
      "epoch": 1.6497695852534562,
      "grad_norm": 0.3781787157058716,
      "learning_rate": 4.955362799260507e-06,
      "loss": 0.0145,
      "step": 120
    },
    {
      "epoch": 1.663594470046083,
      "grad_norm": 0.39995357394218445,
      "learning_rate": 4.950802549062764e-06,
      "loss": 0.015,
      "step": 121
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 0.19926570355892181,
      "learning_rate": 4.946022852363932e-06,
      "loss": 0.0135,
      "step": 122
    },
    {
      "epoch": 1.6912442396313363,
      "grad_norm": 0.22450515627861023,
      "learning_rate": 4.9410241371412525e-06,
      "loss": 0.0135,
      "step": 123
    },
    {
      "epoch": 1.705069124423963,
      "grad_norm": 0.3588384985923767,
      "learning_rate": 4.935806850983034e-06,
      "loss": 0.0125,
      "step": 124
    },
    {
      "epoch": 1.7188940092165899,
      "grad_norm": 0.28571122884750366,
      "learning_rate": 4.9303714610485705e-06,
      "loss": 0.0166,
      "step": 125
    },
    {
      "epoch": 1.7327188940092166,
      "grad_norm": 0.3496967852115631,
      "learning_rate": 4.924718454026318e-06,
      "loss": 0.0139,
      "step": 126
    },
    {
      "epoch": 1.7465437788018434,
      "grad_norm": 0.3279854357242584,
      "learning_rate": 4.918848336090309e-06,
      "loss": 0.0133,
      "step": 127
    },
    {
      "epoch": 1.7603686635944702,
      "grad_norm": 0.19201801717281342,
      "learning_rate": 4.912761632854834e-06,
      "loss": 0.0151,
      "step": 128
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.27701929211616516,
      "learning_rate": 4.906458889327375e-06,
      "loss": 0.0148,
      "step": 129
    },
    {
      "epoch": 1.7880184331797235,
      "grad_norm": 0.2757968008518219,
      "learning_rate": 4.899940669859807e-06,
      "loss": 0.0118,
      "step": 130
    },
    {
      "epoch": 1.80184331797235,
      "grad_norm": 0.18373191356658936,
      "learning_rate": 4.893207558097867e-06,
      "loss": 0.0149,
      "step": 131
    },
    {
      "epoch": 1.8156682027649769,
      "grad_norm": 0.2116280496120453,
      "learning_rate": 4.8862601569288885e-06,
      "loss": 0.0129,
      "step": 132
    },
    {
      "epoch": 1.8294930875576036,
      "grad_norm": 0.30384117364883423,
      "learning_rate": 4.879099088427824e-06,
      "loss": 0.0136,
      "step": 133
    },
    {
      "epoch": 1.8433179723502304,
      "grad_norm": 0.3766787052154541,
      "learning_rate": 4.871724993801541e-06,
      "loss": 0.0123,
      "step": 134
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.3401263356208801,
      "learning_rate": 4.864138533331411e-06,
      "loss": 0.0122,
      "step": 135
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 0.24321958422660828,
      "learning_rate": 4.8563403863141825e-06,
      "loss": 0.0123,
      "step": 136
    },
    {
      "epoch": 1.8847926267281108,
      "grad_norm": 0.16918110847473145,
      "learning_rate": 4.84833125100116e-06,
      "loss": 0.0104,
      "step": 137
    },
    {
      "epoch": 1.8986175115207373,
      "grad_norm": 0.23489230871200562,
      "learning_rate": 4.840111844535682e-06,
      "loss": 0.0122,
      "step": 138
    },
    {
      "epoch": 1.912442396313364,
      "grad_norm": 0.32796236872673035,
      "learning_rate": 4.8316829028889076e-06,
      "loss": 0.0109,
      "step": 139
    },
    {
      "epoch": 1.9262672811059907,
      "grad_norm": 0.24210475385189056,
      "learning_rate": 4.823045180793914e-06,
      "loss": 0.0118,
      "step": 140
    },
    {
      "epoch": 1.9400921658986174,
      "grad_norm": 0.3450548052787781,
      "learning_rate": 4.8141994516781196e-06,
      "loss": 0.0115,
      "step": 141
    },
    {
      "epoch": 1.9539170506912442,
      "grad_norm": 0.23163923621177673,
      "learning_rate": 4.805146507594034e-06,
      "loss": 0.0122,
      "step": 142
    },
    {
      "epoch": 1.967741935483871,
      "grad_norm": 0.8197745084762573,
      "learning_rate": 4.7958871591483305e-06,
      "loss": 0.0101,
      "step": 143
    },
    {
      "epoch": 1.9815668202764978,
      "grad_norm": 0.2917576730251312,
      "learning_rate": 4.786422235429269e-06,
      "loss": 0.0078,
      "step": 144
    }
  ],
  "logging_steps": 1,
  "max_steps": 432,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 72,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.220896013978436e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}