{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.972972972972973,
  "eval_steps": 500,
  "global_step": 122,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016216216216216217,
      "grad_norm": 39.12052917480469,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.2957,
      "step": 1
    },
    {
      "epoch": 0.032432432432432434,
      "grad_norm": 38.9581413269043,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.2959,
      "step": 2
    },
    {
      "epoch": 0.04864864864864865,
      "grad_norm": 39.2702751159668,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.2677,
      "step": 3
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 39.18815231323242,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.2936,
      "step": 4
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 38.66701889038086,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.2561,
      "step": 5
    },
    {
      "epoch": 0.0972972972972973,
      "grad_norm": 39.53536605834961,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.2579,
      "step": 6
    },
    {
      "epoch": 0.11351351351351352,
      "grad_norm": 39.3793830871582,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.2627,
      "step": 7
    },
    {
      "epoch": 0.12972972972972974,
      "grad_norm": 39.88922119140625,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.2729,
      "step": 8
    },
    {
      "epoch": 0.14594594594594595,
      "grad_norm": 37.9880256652832,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.2311,
      "step": 9
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 37.024139404296875,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.1773,
      "step": 10
    },
    {
      "epoch": 0.1783783783783784,
      "grad_norm": 36.89325714111328,
      "learning_rate": 5.5e-07,
      "loss": 2.1927,
      "step": 11
    },
    {
      "epoch": 0.1945945945945946,
      "grad_norm": 37.244178771972656,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.1757,
      "step": 12
    },
    {
      "epoch": 0.21081081081081082,
      "grad_norm": 34.77650451660156,
      "learning_rate": 6.5e-07,
      "loss": 2.0392,
      "step": 13
    },
    {
      "epoch": 0.22702702702702704,
      "grad_norm": 34.78818893432617,
      "learning_rate": 7.000000000000001e-07,
      "loss": 1.9996,
      "step": 14
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 34.86852264404297,
      "learning_rate": 7.5e-07,
      "loss": 1.9496,
      "step": 15
    },
    {
      "epoch": 0.2594594594594595,
      "grad_norm": 35.202796936035156,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.8542,
      "step": 16
    },
    {
      "epoch": 0.2756756756756757,
      "grad_norm": 34.11354064941406,
      "learning_rate": 8.500000000000001e-07,
      "loss": 1.7118,
      "step": 17
    },
    {
      "epoch": 0.2918918918918919,
      "grad_norm": 36.309059143066406,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.6834,
      "step": 18
    },
    {
      "epoch": 0.3081081081081081,
      "grad_norm": 34.69994354248047,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.5298,
      "step": 19
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 35.43153381347656,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.4191,
      "step": 20
    },
    {
      "epoch": 0.34054054054054056,
      "grad_norm": 33.53745651245117,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.3068,
      "step": 21
    },
    {
      "epoch": 0.3567567567567568,
      "grad_norm": 33.775604248046875,
      "learning_rate": 1.1e-06,
      "loss": 1.224,
      "step": 22
    },
    {
      "epoch": 0.372972972972973,
      "grad_norm": 30.57005500793457,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.0704,
      "step": 23
    },
    {
      "epoch": 0.3891891891891892,
      "grad_norm": 27.964860916137695,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.9548,
      "step": 24
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 26.023576736450195,
      "learning_rate": 1.25e-06,
      "loss": 0.8503,
      "step": 25
    },
    {
      "epoch": 0.42162162162162165,
      "grad_norm": 25.0452938079834,
      "learning_rate": 1.3e-06,
      "loss": 0.6938,
      "step": 26
    },
    {
      "epoch": 0.43783783783783786,
      "grad_norm": 24.663373947143555,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.5648,
      "step": 27
    },
    {
      "epoch": 0.4540540540540541,
      "grad_norm": 21.61736488342285,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.435,
      "step": 28
    },
    {
      "epoch": 0.4702702702702703,
      "grad_norm": 18.3259334564209,
      "learning_rate": 1.45e-06,
      "loss": 0.3322,
      "step": 29
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 16.80081558227539,
      "learning_rate": 1.5e-06,
      "loss": 0.2625,
      "step": 30
    },
    {
      "epoch": 0.5027027027027027,
      "grad_norm": 14.789258003234863,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1757,
      "step": 31
    },
    {
      "epoch": 0.518918918918919,
      "grad_norm": 10.406538963317871,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.1376,
      "step": 32
    },
    {
      "epoch": 0.5351351351351351,
      "grad_norm": 4.868802547454834,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0815,
      "step": 33
    },
    {
      "epoch": 0.5513513513513514,
      "grad_norm": 1.8639686107635498,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0628,
      "step": 34
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 1.897918462753296,
      "learning_rate": 1.75e-06,
      "loss": 0.0775,
      "step": 35
    },
    {
      "epoch": 0.5837837837837838,
      "grad_norm": 1.296712040901184,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0565,
      "step": 36
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.0163214206695557,
      "learning_rate": 1.85e-06,
      "loss": 0.0544,
      "step": 37
    },
    {
      "epoch": 0.6162162162162163,
      "grad_norm": 1.070162296295166,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0621,
      "step": 38
    },
    {
      "epoch": 0.6324324324324324,
      "grad_norm": 1.024267315864563,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0566,
      "step": 39
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.9016611576080322,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0511,
      "step": 40
    },
    {
      "epoch": 0.6648648648648648,
      "grad_norm": 0.8272562623023987,
      "learning_rate": 2.05e-06,
      "loss": 0.0533,
      "step": 41
    },
    {
      "epoch": 0.6810810810810811,
      "grad_norm": 0.8875278234481812,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0495,
      "step": 42
    },
    {
      "epoch": 0.6972972972972973,
      "grad_norm": 0.8804877996444702,
      "learning_rate": 2.15e-06,
      "loss": 0.0506,
      "step": 43
    },
    {
      "epoch": 0.7135135135135136,
      "grad_norm": 0.7133358120918274,
      "learning_rate": 2.2e-06,
      "loss": 0.0467,
      "step": 44
    },
    {
      "epoch": 0.7297297297297297,
      "grad_norm": 0.8142214417457581,
      "learning_rate": 2.25e-06,
      "loss": 0.0552,
      "step": 45
    },
    {
      "epoch": 0.745945945945946,
      "grad_norm": 0.8341564536094666,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0574,
      "step": 46
    },
    {
      "epoch": 0.7621621621621621,
      "grad_norm": 0.6500507593154907,
      "learning_rate": 2.35e-06,
      "loss": 0.0398,
      "step": 47
    },
    {
      "epoch": 0.7783783783783784,
      "grad_norm": 0.6163598895072937,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0459,
      "step": 48
    },
    {
      "epoch": 0.7945945945945946,
      "grad_norm": 0.663949191570282,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.046,
      "step": 49
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.7521553635597229,
      "learning_rate": 2.5e-06,
      "loss": 0.0525,
      "step": 50
    },
    {
      "epoch": 0.827027027027027,
      "grad_norm": 0.7828383445739746,
      "learning_rate": 2.55e-06,
      "loss": 0.0558,
      "step": 51
    },
    {
      "epoch": 0.8432432432432433,
      "grad_norm": 0.7935078740119934,
      "learning_rate": 2.6e-06,
      "loss": 0.0451,
      "step": 52
    },
    {
      "epoch": 0.8594594594594595,
      "grad_norm": 0.6327880620956421,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0403,
      "step": 53
    },
    {
      "epoch": 0.8756756756756757,
      "grad_norm": 0.6185981035232544,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0406,
      "step": 54
    },
    {
      "epoch": 0.8918918918918919,
      "grad_norm": 0.5417979955673218,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0426,
      "step": 55
    },
    {
      "epoch": 0.9081081081081082,
      "grad_norm": 0.7140630483627319,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0446,
      "step": 56
    },
    {
      "epoch": 0.9243243243243243,
      "grad_norm": 0.7191944122314453,
      "learning_rate": 2.85e-06,
      "loss": 0.047,
      "step": 57
    },
    {
      "epoch": 0.9405405405405406,
      "grad_norm": 0.7562940716743469,
      "learning_rate": 2.9e-06,
      "loss": 0.0476,
      "step": 58
    },
    {
      "epoch": 0.9567567567567568,
      "grad_norm": 0.7422239184379578,
      "learning_rate": 2.95e-06,
      "loss": 0.0462,
      "step": 59
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.677144467830658,
      "learning_rate": 3e-06,
      "loss": 0.0475,
      "step": 60
    },
    {
      "epoch": 0.9891891891891892,
      "grad_norm": 0.6127192974090576,
      "learning_rate": 3.05e-06,
      "loss": 0.0434,
      "step": 61
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6127192974090576,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0375,
      "step": 62
    },
    {
      "epoch": 1.0162162162162163,
      "grad_norm": 0.959559440612793,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0421,
      "step": 63
    },
    {
      "epoch": 1.0324324324324325,
      "grad_norm": 0.6539880037307739,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0414,
      "step": 64
    },
    {
      "epoch": 1.0486486486486486,
      "grad_norm": 0.5929313898086548,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0451,
      "step": 65
    },
    {
      "epoch": 1.0648648648648649,
      "grad_norm": 0.6479571461677551,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0415,
      "step": 66
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.5496926307678223,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0366,
      "step": 67
    },
    {
      "epoch": 1.0972972972972972,
      "grad_norm": 0.5373682379722595,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0383,
      "step": 68
    },
    {
      "epoch": 1.1135135135135135,
      "grad_norm": 0.5489712357521057,
      "learning_rate": 3.45e-06,
      "loss": 0.0427,
      "step": 69
    },
    {
      "epoch": 1.1297297297297297,
      "grad_norm": 0.6830047369003296,
      "learning_rate": 3.5e-06,
      "loss": 0.039,
      "step": 70
    },
    {
      "epoch": 1.145945945945946,
      "grad_norm": 0.5794199705123901,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0409,
      "step": 71
    },
    {
      "epoch": 1.1621621621621623,
      "grad_norm": 0.571513831615448,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0392,
      "step": 72
    },
    {
      "epoch": 1.1783783783783783,
      "grad_norm": 0.7753933668136597,
      "learning_rate": 3.65e-06,
      "loss": 0.0365,
      "step": 73
    },
    {
      "epoch": 1.1945945945945946,
      "grad_norm": 0.6135310530662537,
      "learning_rate": 3.7e-06,
      "loss": 0.036,
      "step": 74
    },
    {
      "epoch": 1.2108108108108109,
      "grad_norm": 0.5497344136238098,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.035,
      "step": 75
    },
    {
      "epoch": 1.227027027027027,
      "grad_norm": 0.5861782431602478,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0434,
      "step": 76
    },
    {
      "epoch": 1.2432432432432432,
      "grad_norm": 0.6941010355949402,
      "learning_rate": 3.85e-06,
      "loss": 0.0336,
      "step": 77
    },
    {
      "epoch": 1.2594594594594595,
      "grad_norm": 0.5305830240249634,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0391,
      "step": 78
    },
    {
      "epoch": 1.2756756756756757,
      "grad_norm": 0.6456385254859924,
      "learning_rate": 3.95e-06,
      "loss": 0.0422,
      "step": 79
    },
    {
      "epoch": 1.291891891891892,
      "grad_norm": 0.5704363584518433,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0342,
      "step": 80
    },
    {
      "epoch": 1.308108108108108,
      "grad_norm": 0.5257390141487122,
      "learning_rate": 4.05e-06,
      "loss": 0.0369,
      "step": 81
    },
    {
      "epoch": 1.3243243243243243,
      "grad_norm": 0.5541989207267761,
      "learning_rate": 4.1e-06,
      "loss": 0.0331,
      "step": 82
    },
    {
      "epoch": 1.3405405405405406,
      "grad_norm": 0.7190688252449036,
      "learning_rate": 4.15e-06,
      "loss": 0.039,
      "step": 83
    },
    {
      "epoch": 1.3567567567567567,
      "grad_norm": 0.4766721725463867,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0354,
      "step": 84
    },
    {
      "epoch": 1.372972972972973,
      "grad_norm": 0.5847981572151184,
      "learning_rate": 4.25e-06,
      "loss": 0.0355,
      "step": 85
    },
    {
      "epoch": 1.3891891891891892,
      "grad_norm": 0.6361181139945984,
      "learning_rate": 4.3e-06,
      "loss": 0.0415,
      "step": 86
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 0.6437036395072937,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0353,
      "step": 87
    },
    {
      "epoch": 1.4216216216216218,
      "grad_norm": 0.712043046951294,
      "learning_rate": 4.4e-06,
      "loss": 0.0311,
      "step": 88
    },
    {
      "epoch": 1.4378378378378378,
      "grad_norm": 0.5829771757125854,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0433,
      "step": 89
    },
    {
      "epoch": 1.454054054054054,
      "grad_norm": 0.6977937817573547,
      "learning_rate": 4.5e-06,
      "loss": 0.0391,
      "step": 90
    },
    {
      "epoch": 1.4702702702702704,
      "grad_norm": 0.49931228160858154,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0352,
      "step": 91
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 0.5281490683555603,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0385,
      "step": 92
    },
    {
      "epoch": 1.5027027027027027,
      "grad_norm": 0.613349974155426,
      "learning_rate": 4.65e-06,
      "loss": 0.0399,
      "step": 93
    },
    {
      "epoch": 1.518918918918919,
      "grad_norm": 0.6584879755973816,
      "learning_rate": 4.7e-06,
      "loss": 0.043,
      "step": 94
    },
    {
      "epoch": 1.535135135135135,
      "grad_norm": 0.6006895303726196,
      "learning_rate": 4.75e-06,
      "loss": 0.0372,
      "step": 95
    },
    {
      "epoch": 1.5513513513513515,
      "grad_norm": 0.5364943146705627,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.0384,
      "step": 96
    },
    {
      "epoch": 1.5675675675675675,
      "grad_norm": 0.4963968098163605,
      "learning_rate": 4.85e-06,
      "loss": 0.0324,
      "step": 97
    },
    {
      "epoch": 1.5837837837837838,
      "grad_norm": 0.5868538618087769,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0386,
      "step": 98
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6690974235534668,
      "learning_rate": 4.95e-06,
      "loss": 0.0332,
      "step": 99
    },
    {
      "epoch": 1.6162162162162161,
      "grad_norm": 0.6118388175964355,
      "learning_rate": 5e-06,
      "loss": 0.0398,
      "step": 100
    },
    {
      "epoch": 1.6324324324324324,
      "grad_norm": 0.6872304677963257,
      "learning_rate": 4.999825642177387e-06,
      "loss": 0.0333,
      "step": 101
    },
    {
      "epoch": 1.6486486486486487,
      "grad_norm": 0.6457200646400452,
      "learning_rate": 4.999302593030069e-06,
      "loss": 0.0381,
      "step": 102
    },
    {
      "epoch": 1.6648648648648647,
      "grad_norm": 0.6096416115760803,
      "learning_rate": 4.998430925516213e-06,
      "loss": 0.0385,
      "step": 103
    },
    {
      "epoch": 1.6810810810810812,
      "grad_norm": 0.582796573638916,
      "learning_rate": 4.99721076122146e-06,
      "loss": 0.0317,
      "step": 104
    },
    {
      "epoch": 1.6972972972972973,
      "grad_norm": 0.5576394200325012,
      "learning_rate": 4.995642270341961e-06,
      "loss": 0.0378,
      "step": 105
    },
    {
      "epoch": 1.7135135135135136,
      "grad_norm": 0.7414760589599609,
      "learning_rate": 4.99372567166064e-06,
      "loss": 0.0403,
      "step": 106
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.6029103994369507,
      "learning_rate": 4.991461232516675e-06,
      "loss": 0.0418,
      "step": 107
    },
    {
      "epoch": 1.7459459459459459,
      "grad_norm": 0.771609365940094,
      "learning_rate": 4.98884926876821e-06,
      "loss": 0.0413,
      "step": 108
    },
    {
      "epoch": 1.7621621621621621,
      "grad_norm": 0.6869891285896301,
      "learning_rate": 4.9858901447482924e-06,
      "loss": 0.0367,
      "step": 109
    },
    {
      "epoch": 1.7783783783783784,
      "grad_norm": 0.4931647479534149,
      "learning_rate": 4.982584273214061e-06,
      "loss": 0.033,
      "step": 110
    },
    {
      "epoch": 1.7945945945945945,
      "grad_norm": 0.5160052180290222,
      "learning_rate": 4.978932115289165e-06,
      "loss": 0.0357,
      "step": 111
    },
    {
      "epoch": 1.810810810810811,
      "grad_norm": 0.49750861525535583,
      "learning_rate": 4.974934180399447e-06,
      "loss": 0.0333,
      "step": 112
    },
    {
      "epoch": 1.827027027027027,
      "grad_norm": 0.6596441864967346,
      "learning_rate": 4.970591026201884e-06,
      "loss": 0.0354,
      "step": 113
    },
    {
      "epoch": 1.8432432432432433,
      "grad_norm": 0.6613579988479614,
      "learning_rate": 4.965903258506806e-06,
      "loss": 0.0377,
      "step": 114
    },
    {
      "epoch": 1.8594594594594596,
      "grad_norm": 0.5383866429328918,
      "learning_rate": 4.9608715311933865e-06,
      "loss": 0.0418,
      "step": 115
    },
    {
      "epoch": 1.8756756756756756,
      "grad_norm": 0.6303413510322571,
      "learning_rate": 4.955496546118439e-06,
      "loss": 0.0351,
      "step": 116
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 0.5293605923652649,
      "learning_rate": 4.949779053018519e-06,
      "loss": 0.0322,
      "step": 117
    },
    {
      "epoch": 1.9081081081081082,
      "grad_norm": 0.5211143493652344,
      "learning_rate": 4.943719849405347e-06,
      "loss": 0.0374,
      "step": 118
    },
    {
      "epoch": 1.9243243243243242,
      "grad_norm": 0.5933778882026672,
      "learning_rate": 4.937319780454559e-06,
      "loss": 0.0377,
      "step": 119
    },
    {
      "epoch": 1.9405405405405407,
      "grad_norm": 0.6020687818527222,
      "learning_rate": 4.930579738887827e-06,
      "loss": 0.0313,
      "step": 120
    },
    {
      "epoch": 1.9567567567567568,
      "grad_norm": 0.7828154563903809,
      "learning_rate": 4.923500664848327e-06,
      "loss": 0.0372,
      "step": 121
    },
    {
      "epoch": 1.972972972972973,
      "grad_norm": 0.6172424554824829,
      "learning_rate": 4.9160835457696075e-06,
      "loss": 0.0387,
      "step": 122
    }
  ],
  "logging_steps": 1,
  "max_steps": 366,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 61,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.069134586563789e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}