{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.992,
  "eval_steps": 500,
  "global_step": 390,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0128,
      "grad_norm": 6.219960368061681,
      "learning_rate": 1.0256410256410257e-06,
      "loss": 0.8101,
      "step": 1
    },
    {
      "epoch": 0.0256,
      "grad_norm": 6.255587230045647,
      "learning_rate": 2.0512820512820513e-06,
      "loss": 0.8184,
      "step": 2
    },
    {
      "epoch": 0.0384,
      "grad_norm": 5.812583180263883,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.7754,
      "step": 3
    },
    {
      "epoch": 0.0512,
      "grad_norm": 5.530199285053854,
      "learning_rate": 4.102564102564103e-06,
      "loss": 0.7871,
      "step": 4
    },
    {
      "epoch": 0.064,
      "grad_norm": 4.039710518300703,
      "learning_rate": 5.128205128205128e-06,
      "loss": 0.7527,
      "step": 5
    },
    {
      "epoch": 0.0768,
      "grad_norm": 2.2466369696015103,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.7133,
      "step": 6
    },
    {
      "epoch": 0.0896,
      "grad_norm": 2.1073418979367995,
      "learning_rate": 7.17948717948718e-06,
      "loss": 0.7011,
      "step": 7
    },
    {
      "epoch": 0.1024,
      "grad_norm": 4.034393097464074,
      "learning_rate": 8.205128205128205e-06,
      "loss": 0.7398,
      "step": 8
    },
    {
      "epoch": 0.1152,
      "grad_norm": 4.144401097982347,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.7094,
      "step": 9
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.8695340817216914,
      "learning_rate": 1.0256410256410256e-05,
      "loss": 0.6714,
      "step": 10
    },
    {
      "epoch": 0.1408,
      "grad_norm": 3.4446729988081484,
      "learning_rate": 1.1282051282051283e-05,
      "loss": 0.6735,
      "step": 11
    },
    {
      "epoch": 0.1536,
      "grad_norm": 1.9143368701964922,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.6446,
      "step": 12
    },
    {
      "epoch": 0.1664,
      "grad_norm": 1.5632792175236936,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.6465,
      "step": 13
    },
    {
      "epoch": 0.1792,
      "grad_norm": 2.090557483686497,
      "learning_rate": 1.435897435897436e-05,
      "loss": 0.6262,
      "step": 14
    },
    {
      "epoch": 0.192,
      "grad_norm": 1.4279661882786803,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.6068,
      "step": 15
    },
    {
      "epoch": 0.2048,
      "grad_norm": 1.226067869994867,
      "learning_rate": 1.641025641025641e-05,
      "loss": 0.598,
      "step": 16
    },
    {
      "epoch": 0.2176,
      "grad_norm": 1.0165564708836172,
      "learning_rate": 1.7435897435897438e-05,
      "loss": 0.5589,
      "step": 17
    },
    {
      "epoch": 0.2304,
      "grad_norm": 1.0491928880215449,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.5617,
      "step": 18
    },
    {
      "epoch": 0.2432,
      "grad_norm": 0.989476474713095,
      "learning_rate": 1.9487179487179488e-05,
      "loss": 0.5718,
      "step": 19
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.7747709123954674,
      "learning_rate": 2.0512820512820512e-05,
      "loss": 0.5714,
      "step": 20
    },
    {
      "epoch": 0.2688,
      "grad_norm": 0.9017229990416915,
      "learning_rate": 2.153846153846154e-05,
      "loss": 0.5418,
      "step": 21
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.7326914793600917,
      "learning_rate": 2.2564102564102566e-05,
      "loss": 0.5234,
      "step": 22
    },
    {
      "epoch": 0.2944,
      "grad_norm": 0.6957415259620942,
      "learning_rate": 2.3589743589743593e-05,
      "loss": 0.5356,
      "step": 23
    },
    {
      "epoch": 0.3072,
      "grad_norm": 0.7539434604193752,
      "learning_rate": 2.461538461538462e-05,
      "loss": 0.5502,
      "step": 24
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.8906034389744679,
      "learning_rate": 2.5641025641025646e-05,
      "loss": 0.5439,
      "step": 25
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.5342890646270876,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.5282,
      "step": 26
    },
    {
      "epoch": 0.3456,
      "grad_norm": 0.7622179978471697,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 0.5066,
      "step": 27
    },
    {
      "epoch": 0.3584,
      "grad_norm": 0.6331707233908107,
      "learning_rate": 2.871794871794872e-05,
      "loss": 0.505,
      "step": 28
    },
    {
      "epoch": 0.3712,
      "grad_norm": 0.6612848135954165,
      "learning_rate": 2.9743589743589747e-05,
      "loss": 0.5077,
      "step": 29
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.7682267051668576,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.5305,
      "step": 30
    },
    {
      "epoch": 0.3968,
      "grad_norm": 0.7520925871727904,
      "learning_rate": 3.1794871794871795e-05,
      "loss": 0.504,
      "step": 31
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.653998799214937,
      "learning_rate": 3.282051282051282e-05,
      "loss": 0.5222,
      "step": 32
    },
    {
      "epoch": 0.4224,
      "grad_norm": 0.6679867654461787,
      "learning_rate": 3.384615384615385e-05,
      "loss": 0.5176,
      "step": 33
    },
    {
      "epoch": 0.4352,
      "grad_norm": 0.642486851645915,
      "learning_rate": 3.4871794871794875e-05,
      "loss": 0.5113,
      "step": 34
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.6871592500186298,
      "learning_rate": 3.58974358974359e-05,
      "loss": 0.4983,
      "step": 35
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.7910986255637528,
      "learning_rate": 3.692307692307693e-05,
      "loss": 0.5051,
      "step": 36
    },
    {
      "epoch": 0.4736,
      "grad_norm": 0.8080740629150058,
      "learning_rate": 3.794871794871795e-05,
      "loss": 0.4983,
      "step": 37
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.9200078993378724,
      "learning_rate": 3.8974358974358976e-05,
      "loss": 0.4939,
      "step": 38
    },
    {
      "epoch": 0.4992,
      "grad_norm": 0.8367426738033117,
      "learning_rate": 4e-05,
      "loss": 0.4896,
      "step": 39
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.6713192992042779,
      "learning_rate": 3.9999198907597046e-05,
      "loss": 0.5069,
      "step": 40
    },
    {
      "epoch": 0.5248,
      "grad_norm": 0.7662119700759862,
      "learning_rate": 3.9996795694563096e-05,
      "loss": 0.5082,
      "step": 41
    },
    {
      "epoch": 0.5376,
      "grad_norm": 0.8669344109784791,
      "learning_rate": 3.999279055341771e-05,
      "loss": 0.4919,
      "step": 42
    },
    {
      "epoch": 0.5504,
      "grad_norm": 0.8899512451163312,
      "learning_rate": 3.998718380500971e-05,
      "loss": 0.4875,
      "step": 43
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.7563887486399409,
      "learning_rate": 3.997997589849145e-05,
      "loss": 0.4921,
      "step": 44
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.7127142506461983,
      "learning_rate": 3.9971167411282835e-05,
      "loss": 0.48,
      "step": 45
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.6656339174054332,
      "learning_rate": 3.99607590490251e-05,
      "loss": 0.483,
      "step": 46
    },
    {
      "epoch": 0.6016,
      "grad_norm": 0.6318377185051762,
      "learning_rate": 3.9948751645524235e-05,
      "loss": 0.4832,
      "step": 47
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.6778098859319694,
      "learning_rate": 3.9935146162684206e-05,
      "loss": 0.4853,
      "step": 48
    },
    {
      "epoch": 0.6272,
      "grad_norm": 0.6885469806114507,
      "learning_rate": 3.9919943690429906e-05,
      "loss": 0.5057,
      "step": 49
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.6325530323836207,
      "learning_rate": 3.9903145446619837e-05,
      "loss": 0.4802,
      "step": 50
    },
    {
      "epoch": 0.6528,
      "grad_norm": 0.782547149645394,
      "learning_rate": 3.9884752776948564e-05,
      "loss": 0.4769,
      "step": 51
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.6207695198782405,
      "learning_rate": 3.9864767154838864e-05,
      "loss": 0.4522,
      "step": 52
    },
    {
      "epoch": 0.6784,
      "grad_norm": 0.5428851252081672,
      "learning_rate": 3.9843190181323744e-05,
      "loss": 0.4782,
      "step": 53
    },
    {
      "epoch": 0.6912,
      "grad_norm": 0.7763049738206279,
      "learning_rate": 3.982002358491817e-05,
      "loss": 0.4712,
      "step": 54
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.7325806554777012,
      "learning_rate": 3.979526922148058e-05,
      "loss": 0.4581,
      "step": 55
    },
    {
      "epoch": 0.7168,
      "grad_norm": 0.5668478628549942,
      "learning_rate": 3.9768929074064206e-05,
      "loss": 0.479,
      "step": 56
    },
    {
      "epoch": 0.7296,
      "grad_norm": 0.6263294106173753,
      "learning_rate": 3.9741005252758255e-05,
      "loss": 0.4743,
      "step": 57
    },
    {
      "epoch": 0.7424,
      "grad_norm": 0.5607969345769923,
      "learning_rate": 3.971149999451886e-05,
      "loss": 0.4823,
      "step": 58
    },
    {
      "epoch": 0.7552,
      "grad_norm": 0.5136174452333186,
      "learning_rate": 3.9680415662989806e-05,
      "loss": 0.4679,
      "step": 59
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.471032886614314,
      "learning_rate": 3.9647754748313294e-05,
      "loss": 0.4775,
      "step": 60
    },
    {
      "epoch": 0.7808,
      "grad_norm": 0.45671725772240584,
      "learning_rate": 3.96135198669304e-05,
      "loss": 0.4578,
      "step": 61
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.4721743365196963,
      "learning_rate": 3.957771376137144e-05,
      "loss": 0.4624,
      "step": 62
    },
    {
      "epoch": 0.8064,
      "grad_norm": 0.3638376734754168,
      "learning_rate": 3.954033930003634e-05,
      "loss": 0.4623,
      "step": 63
    },
    {
      "epoch": 0.8192,
      "grad_norm": 0.47142236191713693,
      "learning_rate": 3.9501399476964806e-05,
      "loss": 0.4698,
      "step": 64
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.4483840131656804,
      "learning_rate": 3.946089741159648e-05,
      "loss": 0.4641,
      "step": 65
    },
    {
      "epoch": 0.8448,
      "grad_norm": 0.48886663683590464,
      "learning_rate": 3.9418836348521045e-05,
      "loss": 0.458,
      "step": 66
    },
    {
      "epoch": 0.8576,
      "grad_norm": 0.552125666602303,
      "learning_rate": 3.937521965721831e-05,
      "loss": 0.4732,
      "step": 67
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.6603957595848559,
      "learning_rate": 3.933005083178828e-05,
      "loss": 0.4667,
      "step": 68
    },
    {
      "epoch": 0.8832,
      "grad_norm": 0.7103390466059525,
      "learning_rate": 3.928333349067125e-05,
      "loss": 0.4756,
      "step": 69
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.4843247302130666,
      "learning_rate": 3.923507137635792e-05,
      "loss": 0.4711,
      "step": 70
    },
    {
      "epoch": 0.9088,
      "grad_norm": 0.4921206893241678,
      "learning_rate": 3.9185268355089606e-05,
      "loss": 0.4664,
      "step": 71
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.3990742427137136,
      "learning_rate": 3.913392841654851e-05,
      "loss": 0.4708,
      "step": 72
    },
    {
      "epoch": 0.9344,
      "grad_norm": 0.5575527605510985,
      "learning_rate": 3.9081055673538093e-05,
      "loss": 0.465,
      "step": 73
    },
    {
      "epoch": 0.9472,
      "grad_norm": 0.49825122885831696,
      "learning_rate": 3.902665436165364e-05,
      "loss": 0.4645,
      "step": 74
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.4260337681086415,
      "learning_rate": 3.897072883894291e-05,
      "loss": 0.4456,
      "step": 75
    },
    {
      "epoch": 0.9728,
      "grad_norm": 0.36449224341953756,
      "learning_rate": 3.8913283585557054e-05,
      "loss": 0.4566,
      "step": 76
    },
    {
      "epoch": 0.9856,
      "grad_norm": 0.4324858962044455,
      "learning_rate": 3.885432320339167e-05,
      "loss": 0.4743,
      "step": 77
    },
    {
      "epoch": 0.9984,
      "grad_norm": 0.43359457503733184,
      "learning_rate": 3.879385241571817e-05,
      "loss": 0.4686,
      "step": 78
    },
    {
      "epoch": 1.0112,
      "grad_norm": 1.0502585254063914,
      "learning_rate": 3.873187606680543e-05,
      "loss": 0.8511,
      "step": 79
    },
    {
      "epoch": 1.024,
      "grad_norm": 1.4627143223113306,
      "learning_rate": 3.866839912153168e-05,
      "loss": 0.4321,
      "step": 80
    },
    {
      "epoch": 1.0368,
      "grad_norm": 0.7480690321547587,
      "learning_rate": 3.860342666498677e-05,
      "loss": 0.4286,
      "step": 81
    },
    {
      "epoch": 1.0496,
      "grad_norm": 1.0679337626627332,
      "learning_rate": 3.853696390206484e-05,
      "loss": 0.436,
      "step": 82
    },
    {
      "epoch": 1.0624,
      "grad_norm": 0.8322278186443296,
      "learning_rate": 3.846901615704734e-05,
      "loss": 0.4344,
      "step": 83
    },
    {
      "epoch": 1.0752,
      "grad_norm": 0.8310740611172034,
      "learning_rate": 3.839958887317649e-05,
      "loss": 0.4135,
      "step": 84
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.7265084163301352,
      "learning_rate": 3.832868761221926e-05,
      "loss": 0.4383,
      "step": 85
    },
    {
      "epoch": 1.1008,
      "grad_norm": 0.8432536460204655,
      "learning_rate": 3.825631805402182e-05,
      "loss": 0.4189,
      "step": 86
    },
    {
      "epoch": 1.1136,
      "grad_norm": 0.5914223651226814,
      "learning_rate": 3.818248599605448e-05,
      "loss": 0.4287,
      "step": 87
    },
    {
      "epoch": 1.1264,
      "grad_norm": 0.7758229261853449,
      "learning_rate": 3.810719735294731e-05,
      "loss": 0.4251,
      "step": 88
    },
    {
      "epoch": 1.1392,
      "grad_norm": 0.5880230426542516,
      "learning_rate": 3.8030458156016326e-05,
      "loss": 0.4362,
      "step": 89
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.582352185601103,
      "learning_rate": 3.795227455278029e-05,
      "loss": 0.4143,
      "step": 90
    },
    {
      "epoch": 1.1648,
      "grad_norm": 0.5313469123938604,
      "learning_rate": 3.787265280646825e-05,
      "loss": 0.4194,
      "step": 91
    },
    {
      "epoch": 1.1776,
      "grad_norm": 0.6318881329574421,
      "learning_rate": 3.7791599295517825e-05,
      "loss": 0.4272,
      "step": 92
    },
    {
      "epoch": 1.1904,
      "grad_norm": 0.5615435888090177,
      "learning_rate": 3.7709120513064196e-05,
      "loss": 0.4174,
      "step": 93
    },
    {
      "epoch": 1.2032,
      "grad_norm": 0.5159084360650437,
      "learning_rate": 3.762522306641998e-05,
      "loss": 0.4152,
      "step": 94
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.4731566632934445,
      "learning_rate": 3.7539913676545874e-05,
      "loss": 0.4239,
      "step": 95
    },
    {
      "epoch": 1.2288000000000001,
      "grad_norm": 0.49208237680350847,
      "learning_rate": 3.745319917751229e-05,
      "loss": 0.4216,
      "step": 96
    },
    {
      "epoch": 1.2416,
      "grad_norm": 0.4998376104043881,
      "learning_rate": 3.736508651595188e-05,
      "loss": 0.4365,
      "step": 97
    },
    {
      "epoch": 1.2544,
      "grad_norm": 0.4589678934170144,
      "learning_rate": 3.727558275050301e-05,
      "loss": 0.4124,
      "step": 98
    },
    {
      "epoch": 1.2671999999999999,
      "grad_norm": 0.5191560318056777,
      "learning_rate": 3.718469505124434e-05,
      "loss": 0.4282,
      "step": 99
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.5123962286905679,
      "learning_rate": 3.709243069912041e-05,
      "loss": 0.4184,
      "step": 100
    },
    {
      "epoch": 1.2928,
      "grad_norm": 0.4301206051843682,
      "learning_rate": 3.699879708535838e-05,
      "loss": 0.4099,
      "step": 101
    },
    {
      "epoch": 1.3056,
      "grad_norm": 0.4980931015846837,
      "learning_rate": 3.69038017108759e-05,
      "loss": 0.4285,
      "step": 102
    },
    {
      "epoch": 1.3184,
      "grad_norm": 0.41922427101233256,
      "learning_rate": 3.680745218568026e-05,
      "loss": 0.4214,
      "step": 103
    },
    {
      "epoch": 1.3312,
      "grad_norm": 0.4210197599229585,
      "learning_rate": 3.6709756228258735e-05,
      "loss": 0.41,
      "step": 104
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.33044370672997886,
      "learning_rate": 3.6610721664960236e-05,
      "loss": 0.4133,
      "step": 105
    },
    {
      "epoch": 1.3568,
      "grad_norm": 0.46036392068195386,
      "learning_rate": 3.65103564293684e-05,
      "loss": 0.4142,
      "step": 106
    },
    {
      "epoch": 1.3696,
      "grad_norm": 0.5197079194705977,
      "learning_rate": 3.640866856166601e-05,
      "loss": 0.4241,
      "step": 107
    },
    {
      "epoch": 1.3824,
      "grad_norm": 0.5735931578875425,
      "learning_rate": 3.6305666207990886e-05,
      "loss": 0.4134,
      "step": 108
    },
    {
      "epoch": 1.3952,
      "grad_norm": 0.34967134539280176,
      "learning_rate": 3.6201357619783336e-05,
      "loss": 0.4156,
      "step": 109
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.6184740233792955,
      "learning_rate": 3.609575115312511e-05,
      "loss": 0.4162,
      "step": 110
    },
    {
      "epoch": 1.4208,
      "grad_norm": 0.39886032959277895,
      "learning_rate": 3.598885526807003e-05,
      "loss": 0.4065,
      "step": 111
    },
    {
      "epoch": 1.4336,
      "grad_norm": 0.5232061639818978,
      "learning_rate": 3.5880678527966224e-05,
      "loss": 0.426,
      "step": 112
    },
    {
      "epoch": 1.4464000000000001,
      "grad_norm": 0.5392396167721961,
      "learning_rate": 3.577122959877017e-05,
      "loss": 0.4058,
      "step": 113
    },
    {
      "epoch": 1.4592,
      "grad_norm": 0.39738094371187505,
      "learning_rate": 3.566051724835245e-05,
      "loss": 0.4117,
      "step": 114
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.43114668450905597,
      "learning_rate": 3.554855034579532e-05,
      "loss": 0.4233,
      "step": 115
    },
    {
      "epoch": 1.4848,
      "grad_norm": 0.44432873781066573,
      "learning_rate": 3.5435337860682304e-05,
      "loss": 0.3932,
      "step": 116
    },
    {
      "epoch": 1.4976,
      "grad_norm": 0.40254748431088544,
      "learning_rate": 3.532088886237956e-05,
      "loss": 0.4104,
      "step": 117
    },
    {
      "epoch": 1.5104,
      "grad_norm": 0.4356093648467301,
      "learning_rate": 3.520521251930941e-05,
      "loss": 0.4311,
      "step": 118
    },
    {
      "epoch": 1.5232,
      "grad_norm": 0.3598813494896981,
      "learning_rate": 3.5088318098215805e-05,
      "loss": 0.3961,
      "step": 119
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.36312680014273024,
      "learning_rate": 3.497021496342203e-05,
      "loss": 0.4145,
      "step": 120
    },
    {
      "epoch": 1.5488,
      "grad_norm": 0.44939906912663474,
      "learning_rate": 3.485091257608047e-05,
      "loss": 0.4176,
      "step": 121
    },
    {
      "epoch": 1.5615999999999999,
      "grad_norm": 0.44711667575178554,
      "learning_rate": 3.473042049341474e-05,
      "loss": 0.4267,
      "step": 122
    },
    {
      "epoch": 1.5744,
      "grad_norm": 0.39673670743660033,
      "learning_rate": 3.4608748367954064e-05,
      "loss": 0.4094,
      "step": 123
    },
    {
      "epoch": 1.5872000000000002,
      "grad_norm": 0.5130143641085764,
      "learning_rate": 3.4485905946759965e-05,
      "loss": 0.4258,
      "step": 124
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4847123994711865,
      "learning_rate": 3.4361903070645484e-05,
      "loss": 0.4215,
      "step": 125
    },
    {
      "epoch": 1.6128,
      "grad_norm": 0.34497157500964715,
      "learning_rate": 3.423674967338681e-05,
      "loss": 0.3974,
      "step": 126
    },
    {
      "epoch": 1.6256,
      "grad_norm": 0.5418950563871423,
      "learning_rate": 3.411045578092754e-05,
      "loss": 0.4052,
      "step": 127
    },
    {
      "epoch": 1.6383999999999999,
      "grad_norm": 0.5457922313342711,
      "learning_rate": 3.398303151057543e-05,
      "loss": 0.4034,
      "step": 128
    },
    {
      "epoch": 1.6512,
      "grad_norm": 0.3161412930452751,
      "learning_rate": 3.385448707019199e-05,
      "loss": 0.4123,
      "step": 129
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.5233565454343642,
      "learning_rate": 3.372483275737468e-05,
      "loss": 0.4078,
      "step": 130
    },
    {
      "epoch": 1.6768,
      "grad_norm": 0.4227025929662532,
      "learning_rate": 3.359407895863199e-05,
      "loss": 0.4159,
      "step": 131
    },
    {
      "epoch": 1.6896,
      "grad_norm": 0.3350150395065374,
      "learning_rate": 3.34622361485514e-05,
      "loss": 0.4161,
      "step": 132
    },
    {
      "epoch": 1.7024,
      "grad_norm": 0.4788031151576321,
      "learning_rate": 3.332931488896029e-05,
      "loss": 0.4053,
      "step": 133
    },
    {
      "epoch": 1.7151999999999998,
      "grad_norm": 0.44064149123425755,
      "learning_rate": 3.319532582807977e-05,
      "loss": 0.423,
      "step": 134
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.3579153381760676,
      "learning_rate": 3.30602796996717e-05,
      "loss": 0.4131,
      "step": 135
    },
    {
      "epoch": 1.7408000000000001,
      "grad_norm": 0.4431422410986477,
      "learning_rate": 3.2924187322178865e-05,
      "loss": 0.4098,
      "step": 136
    },
    {
      "epoch": 1.7536,
      "grad_norm": 0.3237836795334074,
      "learning_rate": 3.278705959785821e-05,
      "loss": 0.4018,
      "step": 137
    },
    {
      "epoch": 1.7664,
      "grad_norm": 0.43921889103638523,
      "learning_rate": 3.2648907511907544e-05,
      "loss": 0.4194,
      "step": 138
    },
    {
      "epoch": 1.7792,
      "grad_norm": 0.38476175122380096,
      "learning_rate": 3.250974213158555e-05,
      "loss": 0.4087,
      "step": 139
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.29254420648683577,
      "learning_rate": 3.23695746053251e-05,
      "loss": 0.4213,
      "step": 140
    },
    {
      "epoch": 1.8048,
      "grad_norm": 0.4261387699145811,
      "learning_rate": 3.222841616184025e-05,
      "loss": 0.4124,
      "step": 141
    },
    {
      "epoch": 1.8176,
      "grad_norm": 0.3886411273932464,
      "learning_rate": 3.208627810922665e-05,
      "loss": 0.411,
      "step": 142
    },
    {
      "epoch": 1.8304,
      "grad_norm": 0.3979518371673893,
      "learning_rate": 3.194317183405573e-05,
      "loss": 0.4093,
      "step": 143
    },
    {
      "epoch": 1.8432,
      "grad_norm": 0.3999045260658046,
      "learning_rate": 3.1799108800462466e-05,
      "loss": 0.4213,
      "step": 144
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.3760337630105005,
      "learning_rate": 3.1654100549227024e-05,
      "loss": 0.4219,
      "step": 145
    },
    {
      "epoch": 1.8688,
      "grad_norm": 0.4686479438292246,
      "learning_rate": 3.1508158696850275e-05,
      "loss": 0.3926,
      "step": 146
    },
    {
      "epoch": 1.8816000000000002,
      "grad_norm": 0.34949867790932876,
      "learning_rate": 3.136129493462312e-05,
      "loss": 0.4096,
      "step": 147
    },
    {
      "epoch": 1.8944,
      "grad_norm": 0.3821103543970302,
      "learning_rate": 3.121352102768998e-05,
      "loss": 0.4177,
      "step": 148
    },
    {
      "epoch": 1.9072,
      "grad_norm": 0.35807291233095556,
      "learning_rate": 3.106484881410628e-05,
      "loss": 0.4055,
      "step": 149
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.36639865137433913,
      "learning_rate": 3.091529020389009e-05,
      "loss": 0.4236,
      "step": 150
    },
    {
      "epoch": 1.9327999999999999,
      "grad_norm": 0.3227686276164447,
      "learning_rate": 3.076485717806808e-05,
      "loss": 0.4006,
      "step": 151
    },
    {
      "epoch": 1.9456,
      "grad_norm": 0.35808948671887775,
      "learning_rate": 3.061356178771564e-05,
      "loss": 0.402,
      "step": 152
    },
    {
      "epoch": 1.9584000000000001,
      "grad_norm": 0.3457066902452974,
      "learning_rate": 3.0461416152991555e-05,
      "loss": 0.421,
      "step": 153
    },
    {
      "epoch": 1.9712,
      "grad_norm": 0.3475253542398459,
      "learning_rate": 3.0308432462167045e-05,
      "loss": 0.3982,
      "step": 154
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.3205588619302455,
      "learning_rate": 3.015462297064936e-05,
      "loss": 0.4026,
      "step": 155
    },
    {
      "epoch": 1.9968,
      "grad_norm": 0.3901439997813586,
      "learning_rate": 3.0000000000000004e-05,
      "loss": 0.4276,
      "step": 156
    },
    {
      "epoch": 2.0096,
      "grad_norm": 0.8738457584981104,
      "learning_rate": 2.98445759369477e-05,
      "loss": 0.7805,
      "step": 157
    },
    {
      "epoch": 2.0224,
      "grad_norm": 0.7480515761787411,
      "learning_rate": 2.9688363232396056e-05,
      "loss": 0.3596,
      "step": 158
    },
    {
      "epoch": 2.0352,
      "grad_norm": 0.5640866303523602,
      "learning_rate": 2.9531374400426158e-05,
      "loss": 0.3473,
      "step": 159
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.602382092551675,
      "learning_rate": 2.9373622017294075e-05,
      "loss": 0.3838,
      "step": 160
    },
    {
      "epoch": 2.0608,
      "grad_norm": 0.6638274726754934,
      "learning_rate": 2.9215118720423375e-05,
      "loss": 0.3502,
      "step": 161
    },
    {
      "epoch": 2.0736,
      "grad_norm": 0.5438404133170176,
      "learning_rate": 2.9055877207392752e-05,
      "loss": 0.3758,
      "step": 162
    },
    {
      "epoch": 2.0864,
      "grad_norm": 0.5905460081915943,
      "learning_rate": 2.8895910234918828e-05,
      "loss": 0.3532,
      "step": 163
    },
    {
      "epoch": 2.0992,
      "grad_norm": 6.8823160810813455,
      "learning_rate": 2.873523061783426e-05,
      "loss": 0.3581,
      "step": 164
    },
    {
      "epoch": 2.112,
      "grad_norm": 1.0105876318902012,
      "learning_rate": 2.8573851228061084e-05,
      "loss": 0.3688,
      "step": 165
    },
    {
      "epoch": 2.1248,
      "grad_norm": 1.0020339014576163,
      "learning_rate": 2.8411784993579633e-05,
      "loss": 0.375,
      "step": 166
    },
    {
      "epoch": 2.1376,
      "grad_norm": 0.7483800946597154,
      "learning_rate": 2.8249044897392814e-05,
      "loss": 0.3646,
      "step": 167
    },
    {
      "epoch": 2.1504,
      "grad_norm": 0.7939656840141626,
      "learning_rate": 2.80856439764861e-05,
      "loss": 0.3531,
      "step": 168
    },
    {
      "epoch": 2.1632,
      "grad_norm": 0.7448259060057426,
      "learning_rate": 2.792159532078314e-05,
      "loss": 0.3694,
      "step": 169
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.6514266801940611,
      "learning_rate": 2.77569120720971e-05,
      "loss": 0.3507,
      "step": 170
    },
    {
      "epoch": 2.1888,
      "grad_norm": 0.649242399425495,
      "learning_rate": 2.7591607423077932e-05,
      "loss": 0.3602,
      "step": 171
    },
    {
      "epoch": 2.2016,
      "grad_norm": 0.4576587081331995,
      "learning_rate": 2.7425694616155474e-05,
      "loss": 0.3565,
      "step": 172
    },
    {
      "epoch": 2.2144,
      "grad_norm": 0.6604918457009642,
      "learning_rate": 2.7259186942478656e-05,
      "loss": 0.3689,
      "step": 173
    },
    {
      "epoch": 2.2272,
      "grad_norm": 0.4397911958064353,
      "learning_rate": 2.7092097740850712e-05,
      "loss": 0.3569,
      "step": 174
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.49943864796444065,
      "learning_rate": 2.692444039666066e-05,
      "loss": 0.3627,
      "step": 175
    },
    {
      "epoch": 2.2528,
      "grad_norm": 0.5184404200513918,
      "learning_rate": 2.6756228340810946e-05,
      "loss": 0.3625,
      "step": 176
    },
    {
      "epoch": 2.2656,
      "grad_norm": 0.4027625188275841,
      "learning_rate": 2.6587475048641596e-05,
      "loss": 0.3495,
      "step": 177
    },
    {
      "epoch": 2.2784,
      "grad_norm": 0.4913910574951981,
      "learning_rate": 2.6418194038850634e-05,
      "loss": 0.3499,
      "step": 178
    },
    {
      "epoch": 2.2912,
      "grad_norm": 1.3061725116256797,
      "learning_rate": 2.624839887241115e-05,
      "loss": 0.3718,
      "step": 179
    },
    {
      "epoch": 2.304,
      "grad_norm": 0.4734015911963579,
      "learning_rate": 2.607810315148494e-05,
      "loss": 0.3462,
      "step": 180
    },
    {
      "epoch": 2.3168,
      "grad_norm": 0.3512087638097743,
      "learning_rate": 2.5907320518332827e-05,
      "loss": 0.362,
      "step": 181
    },
    {
      "epoch": 2.3296,
      "grad_norm": 0.3938674946237412,
      "learning_rate": 2.5736064654221808e-05,
      "loss": 0.3488,
      "step": 182
    },
    {
      "epoch": 2.3424,
      "grad_norm": 0.37929820735277997,
      "learning_rate": 2.5564349278329056e-05,
      "loss": 0.3574,
      "step": 183
    },
    {
      "epoch": 2.3552,
      "grad_norm": 0.3907990222810365,
      "learning_rate": 2.539218814664288e-05,
      "loss": 0.339,
      "step": 184
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.36895671598541147,
      "learning_rate": 2.521959505086075e-05,
      "loss": 0.3541,
      "step": 185
    },
    {
      "epoch": 2.3808,
      "grad_norm": 0.4217604958853726,
      "learning_rate": 2.5046583817284437e-05,
      "loss": 0.355,
      "step": 186
    },
    {
      "epoch": 2.3936,
      "grad_norm": 0.34984768175904685,
      "learning_rate": 2.487316830571244e-05,
      "loss": 0.3391,
      "step": 187
    },
    {
      "epoch": 2.4064,
      "grad_norm": 0.35143695803310604,
      "learning_rate": 2.4699362408329646e-05,
      "loss": 0.3687,
      "step": 188
    },
    {
      "epoch": 2.4192,
      "grad_norm": 0.30181277781268995,
      "learning_rate": 2.4525180048594452e-05,
      "loss": 0.3417,
      "step": 189
    },
    {
      "epoch": 2.432,
      "grad_norm": 0.3179670439617093,
      "learning_rate": 2.435063518012335e-05,
      "loss": 0.3563,
      "step": 190
    },
    {
      "epoch": 2.4448,
      "grad_norm": 0.3434455104718644,
      "learning_rate": 2.4175741785573177e-05,
      "loss": 0.3542,
      "step": 191
    },
    {
      "epoch": 2.4576000000000002,
      "grad_norm": 0.32562672855847785,
      "learning_rate": 2.4000513875520892e-05,
      "loss": 0.3671,
      "step": 192
    },
    {
      "epoch": 2.4704,
      "grad_norm": 0.30331805437000403,
      "learning_rate": 2.3824965487341247e-05,
      "loss": 0.3586,
      "step": 193
    },
    {
      "epoch": 2.4832,
      "grad_norm": 0.3271268259739871,
      "learning_rate": 2.3649110684082258e-05,
      "loss": 0.3437,
      "step": 194
    },
    {
      "epoch": 2.496,
      "grad_norm": 0.28596308241097534,
      "learning_rate": 2.3472963553338614e-05,
      "loss": 0.3555,
      "step": 195
    },
    {
      "epoch": 2.5088,
      "grad_norm": 0.35364437300722873,
      "learning_rate": 2.3296538206123134e-05,
      "loss": 0.3462,
      "step": 196
    },
    {
      "epoch": 2.5216,
      "grad_norm": 0.3691401958363945,
      "learning_rate": 2.311984877573636e-05,
      "loss": 0.3551,
      "step": 197
    },
    {
      "epoch": 2.5343999999999998,
      "grad_norm": 0.34958767039747213,
      "learning_rate": 2.2942909416634326e-05,
      "loss": 0.3642,
      "step": 198
    },
    {
      "epoch": 2.5472,
      "grad_norm": 0.347179387105894,
      "learning_rate": 2.2765734303294666e-05,
      "loss": 0.3478,
      "step": 199
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.29055667713456323,
      "learning_rate": 2.2588337629081107e-05,
      "loss": 0.3601,
      "step": 200
    },
    {
      "epoch": 2.5728,
      "grad_norm": 0.2957415258779927,
      "learning_rate": 2.2410733605106462e-05,
      "loss": 0.3635,
      "step": 201
    },
    {
      "epoch": 2.5856,
      "grad_norm": 0.3163595463392172,
      "learning_rate": 2.2232936459094158e-05,
      "loss": 0.3498,
      "step": 202
    },
    {
      "epoch": 2.5984,
      "grad_norm": 0.24606892407899797,
      "learning_rate": 2.205496043423849e-05,
      "loss": 0.3544,
      "step": 203
    },
    {
      "epoch": 2.6112,
      "grad_norm": 0.29863764447592844,
      "learning_rate": 2.1876819788063586e-05,
      "loss": 0.3425,
      "step": 204
    },
    {
      "epoch": 2.624,
      "grad_norm": 0.2817341903784844,
      "learning_rate": 2.16985287912813e-05,
      "loss": 0.3563,
      "step": 205
    },
    {
      "epoch": 2.6368,
      "grad_norm": 0.2847194177003871,
      "learning_rate": 2.1520101726647922e-05,
      "loss": 0.3729,
      "step": 206
    },
    {
      "epoch": 2.6496,
      "grad_norm": 0.2805248067283957,
      "learning_rate": 2.1341552887820048e-05,
      "loss": 0.3619,
      "step": 207
    },
    {
      "epoch": 2.6624,
      "grad_norm": 0.2682651776470791,
      "learning_rate": 2.1162896578209517e-05,
      "loss": 0.361,
      "step": 208
    },
    {
      "epoch": 2.6752000000000002,
      "grad_norm": 0.26872536211596487,
      "learning_rate": 2.0984147109837564e-05,
      "loss": 0.3456,
      "step": 209
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 0.2423078332853935,
      "learning_rate": 2.0805318802188307e-05,
      "loss": 0.3603,
      "step": 210
    },
    {
      "epoch": 2.7008,
      "grad_norm": 0.2660821971082229,
      "learning_rate": 2.0626425981061608e-05,
      "loss": 0.3602,
      "step": 211
    },
    {
      "epoch": 2.7136,
      "grad_norm": 0.2310883269089652,
      "learning_rate": 2.0447482977425465e-05,
      "loss": 0.3531,
      "step": 212
    },
    {
      "epoch": 2.7264,
      "grad_norm": 0.27424614026821437,
      "learning_rate": 2.0268504126267952e-05,
      "loss": 0.361,
      "step": 213
    },
    {
      "epoch": 2.7392,
      "grad_norm": 0.2250758562888674,
      "learning_rate": 2.008950376544887e-05,
      "loss": 0.3344,
      "step": 214
    },
    {
      "epoch": 2.752,
      "grad_norm": 0.30101916956153363,
      "learning_rate": 1.9910496234551132e-05,
      "loss": 0.365,
      "step": 215
    },
    {
      "epoch": 2.7648,
      "grad_norm": 0.2246784009965487,
      "learning_rate": 1.9731495873732055e-05,
      "loss": 0.3591,
      "step": 216
    },
    {
      "epoch": 2.7776,
      "grad_norm": 0.25711526147618635,
      "learning_rate": 1.9552517022574542e-05,
      "loss": 0.3625,
      "step": 217
    },
    {
      "epoch": 2.7904,
      "grad_norm": 0.2536199289770775,
      "learning_rate": 1.93735740189384e-05,
      "loss": 0.3493,
      "step": 218
    },
    {
      "epoch": 2.8032,
      "grad_norm": 0.25698296364674106,
      "learning_rate": 1.9194681197811703e-05,
      "loss": 0.3583,
      "step": 219
    },
    {
      "epoch": 2.816,
      "grad_norm": 0.26263935450286985,
      "learning_rate": 1.901585289016244e-05,
      "loss": 0.3605,
      "step": 220
    },
    {
      "epoch": 2.8288,
      "grad_norm": 0.25202721644314985,
      "learning_rate": 1.8837103421790486e-05,
      "loss": 0.3464,
      "step": 221
    },
    {
      "epoch": 2.8416,
      "grad_norm": 0.27102511660060785,
      "learning_rate": 1.8658447112179952e-05,
      "loss": 0.3703,
      "step": 222
    },
    {
      "epoch": 2.8544,
      "grad_norm": 0.26129491255528986,
      "learning_rate": 1.8479898273352084e-05,
      "loss": 0.3502,
      "step": 223
    },
    {
      "epoch": 2.8672,
      "grad_norm": 0.26114263983712904,
      "learning_rate": 1.83014712087187e-05,
      "loss": 0.3573,
      "step": 224
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.25417622140863766,
      "learning_rate": 1.8123180211936417e-05,
      "loss": 0.342,
      "step": 225
    },
    {
      "epoch": 2.8928000000000003,
      "grad_norm": 0.24525939867506674,
      "learning_rate": 1.794503956576152e-05,
      "loss": 0.355,
      "step": 226
    },
    {
      "epoch": 2.9055999999999997,
      "grad_norm": 0.2715219261209413,
      "learning_rate": 1.776706354090585e-05,
      "loss": 0.3335,
      "step": 227
    },
    {
      "epoch": 2.9184,
      "grad_norm": 0.2528857012917834,
      "learning_rate": 1.758926639489354e-05,
      "loss": 0.349,
      "step": 228
    },
    {
      "epoch": 2.9312,
      "grad_norm": 0.33211410752890635,
      "learning_rate": 1.7411662370918893e-05,
      "loss": 0.3525,
      "step": 229
    },
    {
      "epoch": 2.944,
      "grad_norm": 0.23775360683138613,
      "learning_rate": 1.7234265696705344e-05,
      "loss": 0.3291,
      "step": 230
    },
    {
      "epoch": 2.9568,
      "grad_norm": 0.348373721814402,
      "learning_rate": 1.7057090583365678e-05,
      "loss": 0.3561,
      "step": 231
    },
    {
      "epoch": 2.9696,
      "grad_norm": 0.2989919443310957,
      "learning_rate": 1.6880151224263646e-05,
      "loss": 0.3548,
      "step": 232
    },
    {
      "epoch": 2.9824,
      "grad_norm": 0.19813119471007232,
      "learning_rate": 1.6703461793876876e-05,
      "loss": 0.3594,
      "step": 233
    },
    {
      "epoch": 2.9952,
      "grad_norm": 0.2630566786008279,
      "learning_rate": 1.6527036446661396e-05,
      "loss": 0.3589,
      "step": 234
    },
    {
      "epoch": 3.008,
      "grad_norm": 0.6997028145200225,
      "learning_rate": 1.635088931591775e-05,
      "loss": 0.6686,
      "step": 235
    },
    {
      "epoch": 3.0208,
      "grad_norm": 0.34104002600696753,
      "learning_rate": 1.6175034512658753e-05,
      "loss": 0.297,
      "step": 236
    },
    {
      "epoch": 3.0336,
      "grad_norm": 0.41087129393573824,
      "learning_rate": 1.5999486124479115e-05,
      "loss": 0.2975,
      "step": 237
    },
    {
      "epoch": 3.0464,
      "grad_norm": 0.4050458221374504,
      "learning_rate": 1.5824258214426833e-05,
      "loss": 0.3079,
      "step": 238
    },
    {
      "epoch": 3.0592,
      "grad_norm": 0.34000028015287853,
      "learning_rate": 1.5649364819876655e-05,
      "loss": 0.2912,
      "step": 239
    },
    {
      "epoch": 3.072,
      "grad_norm": 0.360253753275954,
      "learning_rate": 1.547481995140556e-05,
      "loss": 0.3029,
      "step": 240
    },
    {
      "epoch": 3.0848,
      "grad_norm": 0.32772700785145326,
      "learning_rate": 1.5300637591670357e-05,
      "loss": 0.2984,
      "step": 241
    },
    {
      "epoch": 3.0976,
      "grad_norm": 0.28162362643559274,
      "learning_rate": 1.5126831694287564e-05,
      "loss": 0.3022,
      "step": 242
    },
    {
      "epoch": 3.1104,
      "grad_norm": 0.3132619916446047,
      "learning_rate": 1.4953416182715566e-05,
      "loss": 0.3022,
      "step": 243
    },
    {
      "epoch": 3.1232,
      "grad_norm": 0.28284420914160613,
      "learning_rate": 1.478040494913926e-05,
      "loss": 0.3007,
      "step": 244
    },
    {
      "epoch": 3.136,
      "grad_norm": 0.28599876556564563,
      "learning_rate": 1.460781185335713e-05,
      "loss": 0.3009,
      "step": 245
    },
    {
      "epoch": 3.1488,
      "grad_norm": 0.25097124897824297,
      "learning_rate": 1.443565072167095e-05,
      "loss": 0.293,
      "step": 246
    },
    {
      "epoch": 3.1616,
      "grad_norm": 0.2691028583537877,
      "learning_rate": 1.4263935345778202e-05,
      "loss": 0.2941,
      "step": 247
    },
    {
      "epoch": 3.1744,
      "grad_norm": 0.2845304868532452,
      "learning_rate": 1.409267948166718e-05,
      "loss": 0.3075,
      "step": 248
    },
    {
      "epoch": 3.1872,
      "grad_norm": 0.2662058110191505,
      "learning_rate": 1.3921896848515064e-05,
      "loss": 0.3057,
      "step": 249
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.23910464481296942,
      "learning_rate": 1.3751601127588849e-05,
      "loss": 0.2841,
      "step": 250
    },
    {
      "epoch": 3.2128,
      "grad_norm": 0.27147343006641145,
      "learning_rate": 1.3581805961149371e-05,
      "loss": 0.3005,
      "step": 251
    },
    {
      "epoch": 3.2256,
      "grad_norm": 0.24373274572443954,
      "learning_rate": 1.341252495135841e-05,
      "loss": 0.2963,
      "step": 252
    },
    {
      "epoch": 3.2384,
      "grad_norm": 0.2661521544403677,
      "learning_rate": 1.324377165918906e-05,
      "loss": 0.3163,
      "step": 253
    },
    {
      "epoch": 3.2512,
      "grad_norm": 0.245342801299721,
      "learning_rate": 1.3075559603339354e-05,
      "loss": 0.3098,
      "step": 254
    },
    {
      "epoch": 3.2640000000000002,
      "grad_norm": 0.24745784876539328,
      "learning_rate": 1.2907902259149287e-05,
      "loss": 0.3036,
      "step": 255
    },
    {
      "epoch": 3.2768,
      "grad_norm": 0.24962742030451818,
      "learning_rate": 1.274081305752135e-05,
      "loss": 0.3097,
      "step": 256
    },
    {
      "epoch": 3.2896,
      "grad_norm": 0.23813922999200066,
      "learning_rate": 1.2574305383844528e-05,
      "loss": 0.2943,
      "step": 257
    },
    {
      "epoch": 3.3024,
      "grad_norm": 0.23222023271235778,
      "learning_rate": 1.2408392576922075e-05,
      "loss": 0.2975,
      "step": 258
    },
    {
      "epoch": 3.3152,
      "grad_norm": 0.23588041850396957,
      "learning_rate": 1.2243087927902905e-05,
      "loss": 0.2985,
      "step": 259
    },
    {
      "epoch": 3.328,
      "grad_norm": 0.23695273659822808,
      "learning_rate": 1.2078404679216864e-05,
      "loss": 0.3193,
      "step": 260
    },
    {
      "epoch": 3.3407999999999998,
      "grad_norm": 0.22384129800841113,
      "learning_rate": 1.1914356023513904e-05,
      "loss": 0.2978,
      "step": 261
    },
    {
      "epoch": 3.3536,
      "grad_norm": 0.22293737482158904,
      "learning_rate": 1.1750955102607193e-05,
      "loss": 0.2993,
      "step": 262
    },
    {
      "epoch": 3.3664,
      "grad_norm": 0.255784638985407,
      "learning_rate": 1.1588215006420374e-05,
      "loss": 0.301,
      "step": 263
    },
    {
      "epoch": 3.3792,
      "grad_norm": 0.22130509730837458,
      "learning_rate": 1.1426148771938915e-05,
      "loss": 0.2919,
      "step": 264
    },
    {
      "epoch": 3.392,
      "grad_norm": 0.23243980161708455,
      "learning_rate": 1.1264769382165748e-05,
      "loss": 0.2917,
      "step": 265
    },
    {
      "epoch": 3.4048,
      "grad_norm": 0.23212703810901136,
      "learning_rate": 1.110408976508118e-05,
      "loss": 0.3012,
      "step": 266
    },
    {
      "epoch": 3.4176,
      "grad_norm": 0.20831796458613283,
      "learning_rate": 1.094412279260726e-05,
      "loss": 0.2919,
      "step": 267
    },
    {
      "epoch": 3.4304,
      "grad_norm": 0.2240756219438419,
      "learning_rate": 1.0784881279576635e-05,
      "loss": 0.3048,
      "step": 268
    },
    {
      "epoch": 3.4432,
      "grad_norm": 0.2207706005685621,
      "learning_rate": 1.0626377982705929e-05,
      "loss": 0.2888,
      "step": 269
    },
    {
      "epoch": 3.456,
      "grad_norm": 0.23616169619311528,
      "learning_rate": 1.0468625599573842e-05,
      "loss": 0.3008,
      "step": 270
    },
    {
      "epoch": 3.4688,
      "grad_norm": 0.21443123274049505,
      "learning_rate": 1.0311636767603952e-05,
      "loss": 0.3117,
      "step": 271
    },
    {
      "epoch": 3.4816,
      "grad_norm": 0.2084241121958855,
      "learning_rate": 1.0155424063052306e-05,
      "loss": 0.2978,
      "step": 272
    },
    {
      "epoch": 3.4944,
      "grad_norm": 0.2296631500405593,
      "learning_rate": 1.0000000000000006e-05,
      "loss": 0.3022,
      "step": 273
    },
    {
      "epoch": 3.5072,
      "grad_norm": 0.20559856655631023,
      "learning_rate": 9.84537702935065e-06,
      "loss": 0.2898,
      "step": 274
    },
    {
      "epoch": 3.52,
      "grad_norm": 0.2135162571558101,
      "learning_rate": 9.691567537832964e-06,
      "loss": 0.299,
      "step": 275
    },
    {
      "epoch": 3.5328,
      "grad_norm": 0.18261613701429247,
      "learning_rate": 9.538583847008452e-06,
      "loss": 0.2992,
      "step": 276
    },
    {
      "epoch": 3.5456,
      "grad_norm": 0.22197145750478148,
      "learning_rate": 9.386438212284372e-06,
      "loss": 0.3204,
      "step": 277
    },
    {
      "epoch": 3.5584,
      "grad_norm": 0.19997724440354603,
      "learning_rate": 9.235142821931928e-06,
      "loss": 0.3043,
      "step": 278
    },
    {
      "epoch": 3.5712,
      "grad_norm": 0.19930148388659957,
      "learning_rate": 9.084709796109907e-06,
      "loss": 0.2974,
      "step": 279
    },
    {
      "epoch": 3.584,
      "grad_norm": 0.19306872791743596,
      "learning_rate": 8.93515118589373e-06,
      "loss": 0.3005,
      "step": 280
    },
    {
      "epoch": 3.5968,
      "grad_norm": 0.21911971090499133,
      "learning_rate": 8.786478972310023e-06,
      "loss": 0.3011,
      "step": 281
    },
    {
      "epoch": 3.6096,
      "grad_norm": 0.20630961825525088,
      "learning_rate": 8.638705065376887e-06,
      "loss": 0.3023,
      "step": 282
    },
    {
      "epoch": 3.6224,
      "grad_norm": 0.21637030841896499,
      "learning_rate": 8.491841303149728e-06,
      "loss": 0.2984,
      "step": 283
    },
    {
      "epoch": 3.6352,
      "grad_norm": 0.2029316798557108,
      "learning_rate": 8.345899450772975e-06,
      "loss": 0.3003,
      "step": 284
    },
    {
      "epoch": 3.648,
      "grad_norm": 0.193975360078272,
      "learning_rate": 8.200891199537549e-06,
      "loss": 0.3051,
      "step": 285
    },
    {
      "epoch": 3.6608,
      "grad_norm": 0.20986849026320764,
      "learning_rate": 8.056828165944282e-06,
      "loss": 0.288,
      "step": 286
    },
    {
      "epoch": 3.6736,
      "grad_norm": 0.2186914964309987,
      "learning_rate": 7.913721890773354e-06,
      "loss": 0.2992,
      "step": 287
    },
    {
      "epoch": 3.6864,
      "grad_norm": 0.19236272379122993,
      "learning_rate": 7.771583838159756e-06,
      "loss": 0.3007,
      "step": 288
    },
    {
      "epoch": 3.6992000000000003,
      "grad_norm": 0.21218510109020924,
      "learning_rate": 7.630425394674903e-06,
      "loss": 0.2986,
      "step": 289
    },
    {
      "epoch": 3.7119999999999997,
      "grad_norm": 0.20346088237367663,
      "learning_rate": 7.49025786841445e-06,
      "loss": 0.2961,
      "step": 290
    },
    {
      "epoch": 3.7248,
      "grad_norm": 0.2171416113355265,
      "learning_rate": 7.3510924880924575e-06,
      "loss": 0.3115,
      "step": 291
    },
    {
      "epoch": 3.7376,
      "grad_norm": 0.2044087272447511,
      "learning_rate": 7.212940402141808e-06,
      "loss": 0.2981,
      "step": 292
    },
    {
      "epoch": 3.7504,
      "grad_norm": 0.2305755913982547,
      "learning_rate": 7.075812677821145e-06,
      "loss": 0.2912,
      "step": 293
    },
    {
      "epoch": 3.7632,
      "grad_norm": 0.1900301156856817,
      "learning_rate": 6.939720300328303e-06,
      "loss": 0.298,
      "step": 294
    },
    {
      "epoch": 3.776,
      "grad_norm": 0.1946712044676471,
      "learning_rate": 6.8046741719202385e-06,
      "loss": 0.2956,
      "step": 295
    },
    {
      "epoch": 3.7888,
      "grad_norm": 0.22310892194889975,
      "learning_rate": 6.67068511103971e-06,
      "loss": 0.3166,
      "step": 296
    },
    {
      "epoch": 3.8016,
      "grad_norm": 0.1928986764225647,
      "learning_rate": 6.537763851448593e-06,
      "loss": 0.2968,
      "step": 297
    },
    {
      "epoch": 3.8144,
      "grad_norm": 0.19989130193404223,
      "learning_rate": 6.4059210413680175e-06,
      "loss": 0.3072,
      "step": 298
    },
    {
      "epoch": 3.8272,
      "grad_norm": 0.19104881596589784,
      "learning_rate": 6.275167242625331e-06,
      "loss": 0.2936,
      "step": 299
    },
    {
      "epoch": 3.84,
      "grad_norm": 0.19946395829690933,
      "learning_rate": 6.145512929808013e-06,
      "loss": 0.3086,
      "step": 300
    },
    {
      "epoch": 3.8528000000000002,
      "grad_norm": 0.18747864622727894,
      "learning_rate": 6.016968489424572e-06,
      "loss": 0.2963,
      "step": 301
    },
    {
      "epoch": 3.8656,
      "grad_norm": 0.1918720455331222,
      "learning_rate": 5.889544219072465e-06,
      "loss": 0.289,
      "step": 302
    },
    {
      "epoch": 3.8784,
      "grad_norm": 0.18224359274518848,
      "learning_rate": 5.7632503266131925e-06,
      "loss": 0.2941,
      "step": 303
    },
    {
      "epoch": 3.8912,
      "grad_norm": 0.1847216276283363,
      "learning_rate": 5.638096929354522e-06,
      "loss": 0.2986,
      "step": 304
    },
    {
      "epoch": 3.904,
      "grad_norm": 0.20415713904772567,
      "learning_rate": 5.514094053240035e-06,
      "loss": 0.3042,
      "step": 305
    },
    {
      "epoch": 3.9168,
      "grad_norm": 0.19803624174264708,
      "learning_rate": 5.39125163204594e-06,
      "loss": 0.2986,
      "step": 306
    },
    {
      "epoch": 3.9295999999999998,
      "grad_norm": 0.1927102447499531,
      "learning_rate": 5.269579506585259e-06,
      "loss": 0.3106,
      "step": 307
    },
    {
      "epoch": 3.9424,
      "grad_norm": 0.18312573653875455,
      "learning_rate": 5.149087423919541e-06,
      "loss": 0.291,
      "step": 308
    },
    {
      "epoch": 3.9552,
      "grad_norm": 0.20080495844344906,
      "learning_rate": 5.029785036577976e-06,
      "loss": 0.2992,
      "step": 309
    },
    {
      "epoch": 3.968,
      "grad_norm": 0.18852217229459217,
      "learning_rate": 4.911681901784198e-06,
      "loss": 0.2946,
      "step": 310
    },
    {
      "epoch": 3.9808,
      "grad_norm": 0.1971870511076327,
      "learning_rate": 4.794787480690597e-06,
      "loss": 0.3105,
      "step": 311
    },
    {
      "epoch": 3.9936,
      "grad_norm": 0.1846546580876203,
      "learning_rate": 4.679111137620442e-06,
      "loss": 0.3029,
      "step": 312
    },
    {
      "epoch": 4.0064,
      "grad_norm": 0.5396691917025843,
      "learning_rate": 4.5646621393177e-06,
      "loss": 0.5375,
      "step": 313
    },
    {
      "epoch": 4.0192,
      "grad_norm": 0.2890536087215895,
      "learning_rate": 4.451449654204685e-06,
      "loss": 0.2642,
      "step": 314
    },
    {
      "epoch": 4.032,
      "grad_norm": 0.2640547862683752,
      "learning_rate": 4.339482751647557e-06,
      "loss": 0.2618,
      "step": 315
    },
    {
      "epoch": 4.0448,
      "grad_norm": 0.22180229697520343,
      "learning_rate": 4.228770401229824e-06,
      "loss": 0.2759,
      "step": 316
    },
    {
      "epoch": 4.0576,
      "grad_norm": 0.2609043014637818,
      "learning_rate": 4.119321472033779e-06,
      "loss": 0.2715,
      "step": 317
    },
    {
      "epoch": 4.0704,
      "grad_norm": 0.30990208719376133,
      "learning_rate": 4.011144731929981e-06,
      "loss": 0.2681,
      "step": 318
    },
    {
      "epoch": 4.0832,
      "grad_norm": 0.2898580293118983,
      "learning_rate": 3.904248846874894e-06,
      "loss": 0.2664,
      "step": 319
    },
    {
      "epoch": 4.096,
      "grad_norm": 0.28007198851452264,
      "learning_rate": 3.7986423802166705e-06,
      "loss": 0.2768,
      "step": 320
    },
    {
      "epoch": 4.1088,
      "grad_norm": 0.24381392643980318,
      "learning_rate": 3.694333792009115e-06,
      "loss": 0.2815,
      "step": 321
    },
    {
      "epoch": 4.1216,
      "grad_norm": 0.23568735740011512,
      "learning_rate": 3.5913314383339937e-06,
      "loss": 0.2606,
      "step": 322
    },
    {
      "epoch": 4.1344,
      "grad_norm": 0.2360334696648068,
      "learning_rate": 3.4896435706316e-06,
      "loss": 0.2614,
      "step": 323
    },
    {
      "epoch": 4.1472,
      "grad_norm": 0.2403488922021054,
      "learning_rate": 3.3892783350397675e-06,
      "loss": 0.2695,
      "step": 324
    },
    {
      "epoch": 4.16,
      "grad_norm": 0.2240701082175525,
      "learning_rate": 3.290243771741275e-06,
      "loss": 0.2759,
      "step": 325
    },
    {
      "epoch": 4.1728,
      "grad_norm": 0.214724683311387,
      "learning_rate": 3.1925478143197418e-06,
      "loss": 0.2562,
      "step": 326
    },
    {
      "epoch": 4.1856,
      "grad_norm": 0.2041350595950632,
      "learning_rate": 3.0961982891241083e-06,
      "loss": 0.2682,
      "step": 327
    },
    {
      "epoch": 4.1984,
      "grad_norm": 0.20224503187585574,
      "learning_rate": 3.001202914641628e-06,
      "loss": 0.2558,
      "step": 328
    },
    {
      "epoch": 4.2112,
      "grad_norm": 0.20380994571218028,
      "learning_rate": 2.907569300879596e-06,
      "loss": 0.2638,
      "step": 329
    },
    {
      "epoch": 4.224,
      "grad_norm": 0.20778818288979672,
      "learning_rate": 2.815304948755664e-06,
      "loss": 0.2658,
      "step": 330
    },
    {
      "epoch": 4.2368,
      "grad_norm": 0.20668185213261822,
      "learning_rate": 2.7244172494969978e-06,
      "loss": 0.2647,
      "step": 331
    },
    {
      "epoch": 4.2496,
      "grad_norm": 0.19166925436015203,
      "learning_rate": 2.6349134840481294e-06,
      "loss": 0.2652,
      "step": 332
    },
    {
      "epoch": 4.2624,
      "grad_norm": 0.20958472909910286,
      "learning_rate": 2.546800822487714e-06,
      "loss": 0.2666,
      "step": 333
    },
    {
      "epoch": 4.2752,
      "grad_norm": 0.18966665260048096,
      "learning_rate": 2.4600863234541338e-06,
      "loss": 0.2643,
      "step": 334
    },
    {
      "epoch": 4.288,
      "grad_norm": 0.19021310568530453,
      "learning_rate": 2.374776933580025e-06,
      "loss": 0.2612,
      "step": 335
    },
    {
      "epoch": 4.3008,
      "grad_norm": 0.1937889584861872,
      "learning_rate": 2.2908794869358044e-06,
      "loss": 0.2598,
      "step": 336
    },
    {
      "epoch": 4.3136,
      "grad_norm": 0.18804445094292152,
      "learning_rate": 2.2084007044821764e-06,
      "loss": 0.2591,
      "step": 337
    },
    {
      "epoch": 4.3264,
      "grad_norm": 0.18776160962683494,
      "learning_rate": 2.127347193531757e-06,
      "loss": 0.2674,
      "step": 338
    },
    {
      "epoch": 4.3392,
      "grad_norm": 0.18117126201806483,
      "learning_rate": 2.0477254472197237e-06,
      "loss": 0.255,
      "step": 339
    },
    {
      "epoch": 4.352,
      "grad_norm": 0.18618073145377165,
      "learning_rate": 1.96954184398368e-06,
      "loss": 0.2665,
      "step": 340
    },
    {
      "epoch": 4.3648,
      "grad_norm": 0.17928312558621964,
      "learning_rate": 1.8928026470526917e-06,
      "loss": 0.268,
      "step": 341
    },
    {
      "epoch": 4.3776,
      "grad_norm": 0.18504920323383642,
      "learning_rate": 1.817514003945524e-06,
      "loss": 0.2674,
      "step": 342
    },
    {
      "epoch": 4.3904,
      "grad_norm": 0.18199455479077112,
      "learning_rate": 1.743681945978184e-06,
      "loss": 0.2613,
      "step": 343
    },
    {
      "epoch": 4.4032,
      "grad_norm": 0.19175828594233651,
      "learning_rate": 1.6713123877807413e-06,
      "loss": 0.2581,
      "step": 344
    },
    {
      "epoch": 4.416,
      "grad_norm": 0.1863128522851686,
      "learning_rate": 1.6004111268235156e-06,
      "loss": 0.2648,
      "step": 345
    },
    {
      "epoch": 4.4288,
      "grad_norm": 0.17774694064747787,
      "learning_rate": 1.5309838429526714e-06,
      "loss": 0.263,
      "step": 346
    },
    {
      "epoch": 4.4416,
      "grad_norm": 0.1782659108979163,
      "learning_rate": 1.4630360979351644e-06,
      "loss": 0.2595,
      "step": 347
    },
    {
      "epoch": 4.4544,
      "grad_norm": 0.18485815260648936,
      "learning_rate": 1.396573335013236e-06,
      "loss": 0.2705,
      "step": 348
    },
    {
      "epoch": 4.4672,
      "grad_norm": 0.178378794238484,
      "learning_rate": 1.3316008784683265e-06,
      "loss": 0.2648,
      "step": 349
    },
    {
      "epoch": 4.48,
      "grad_norm": 0.1923571033693555,
      "learning_rate": 1.2681239331945695e-06,
      "loss": 0.2664,
      "step": 350
    },
    {
      "epoch": 4.4928,
      "grad_norm": 0.18706802997289357,
      "learning_rate": 1.2061475842818337e-06,
      "loss": 0.2693,
      "step": 351
    },
    {
      "epoch": 4.5056,
      "grad_norm": 0.18057336658799308,
      "learning_rate": 1.1456767966083393e-06,
      "loss": 0.2689,
      "step": 352
    },
    {
      "epoch": 4.5184,
      "grad_norm": 0.16993427340804612,
      "learning_rate": 1.086716414442952e-06,
      "loss": 0.2545,
      "step": 353
    },
    {
      "epoch": 4.5312,
      "grad_norm": 0.17978667488327493,
      "learning_rate": 1.0292711610570904e-06,
      "loss": 0.2728,
      "step": 354
    },
    {
      "epoch": 4.5440000000000005,
      "grad_norm": 0.1759031439220219,
      "learning_rate": 9.733456383463658e-07,
      "loss": 0.2742,
      "step": 355
    },
    {
      "epoch": 4.5568,
      "grad_norm": 0.16819019314255032,
      "learning_rate": 9.189443264619102e-07,
      "loss": 0.2654,
      "step": 356
    },
    {
      "epoch": 4.5696,
      "grad_norm": 0.17684706017433846,
      "learning_rate": 8.660715834514977e-07,
      "loss": 0.2623,
      "step": 357
    },
    {
      "epoch": 4.5824,
      "grad_norm": 0.1780885287188612,
      "learning_rate": 8.147316449103959e-07,
      "loss": 0.2666,
      "step": 358
    },
    {
      "epoch": 4.5952,
      "grad_norm": 0.17505138984335916,
      "learning_rate": 7.649286236420806e-07,
      "loss": 0.2727,
      "step": 359
    },
    {
      "epoch": 4.608,
      "grad_norm": 0.16994562099187394,
      "learning_rate": 7.166665093287539e-07,
      "loss": 0.2565,
      "step": 360
    },
    {
      "epoch": 4.6208,
      "grad_norm": 0.16967779918455525,
      "learning_rate": 6.69949168211721e-07,
      "loss": 0.2616,
      "step": 361
    },
    {
      "epoch": 4.6336,
      "grad_norm": 0.17202986180718627,
      "learning_rate": 6.247803427816945e-07,
      "loss": 0.263,
      "step": 362
    },
    {
      "epoch": 4.6464,
      "grad_norm": 0.17110436252240552,
      "learning_rate": 5.811636514789598e-07,
      "loss": 0.2639,
      "step": 363
    },
    {
      "epoch": 4.6592,
      "grad_norm": 0.17182100115105445,
      "learning_rate": 5.391025884035239e-07,
      "loss": 0.2568,
      "step": 364
    },
    {
      "epoch": 4.672,
      "grad_norm": 0.16502389754333371,
      "learning_rate": 4.986005230351954e-07,
      "loss": 0.2597,
      "step": 365
    },
    {
      "epoch": 4.6848,
      "grad_norm": 0.173198753106447,
      "learning_rate": 4.5966069996365993e-07,
      "loss": 0.2687,
      "step": 366
    },
    {
      "epoch": 4.6975999999999996,
      "grad_norm": 0.16925658628130652,
      "learning_rate": 4.22286238628562e-07,
      "loss": 0.2649,
      "step": 367
    },
    {
      "epoch": 4.7104,
      "grad_norm": 0.1694579169583432,
      "learning_rate": 3.8648013306960664e-07,
      "loss": 0.2563,
      "step": 368
    },
    {
      "epoch": 4.7232,
      "grad_norm": 0.17179795829254527,
      "learning_rate": 3.522452516867048e-07,
      "loss": 0.2711,
      "step": 369
    },
    {
      "epoch": 4.736,
      "grad_norm": 0.16687608279205143,
      "learning_rate": 3.1958433701019697e-07,
      "loss": 0.2572,
      "step": 370
    },
    {
      "epoch": 4.7488,
      "grad_norm": 0.16976180283763298,
      "learning_rate": 2.8850000548115155e-07,
      "loss": 0.2637,
      "step": 371
    },
    {
      "epoch": 4.7616,
      "grad_norm": 0.16604126148098586,
      "learning_rate": 2.5899474724174313e-07,
      "loss": 0.2463,
      "step": 372
    },
    {
      "epoch": 4.7744,
      "grad_norm": 0.1715658554432001,
      "learning_rate": 2.3107092593579905e-07,
      "loss": 0.265,
      "step": 373
    },
    {
      "epoch": 4.7872,
      "grad_norm": 0.1739506001586336,
      "learning_rate": 2.0473077851942858e-07,
      "loss": 0.2659,
      "step": 374
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.17018709058523263,
      "learning_rate": 1.799764150818306e-07,
      "loss": 0.2572,
      "step": 375
    },
    {
      "epoch": 4.8128,
      "grad_norm": 0.16785428847738693,
      "learning_rate": 1.5680981867625566e-07,
      "loss": 0.254,
      "step": 376
    },
    {
      "epoch": 4.8256,
      "grad_norm": 0.16831813887980965,
      "learning_rate": 1.3523284516113955e-07,
      "loss": 0.2607,
      "step": 377
    },
    {
      "epoch": 4.8384,
      "grad_norm": 0.1723003598800097,
      "learning_rate": 1.1524722305144231e-07,
      "loss": 0.2584,
      "step": 378
    },
    {
      "epoch": 4.8512,
      "grad_norm": 0.17539264327127366,
      "learning_rate": 9.685455338016347e-08,
      "loss": 0.2672,
      "step": 379
    },
    {
      "epoch": 4.864,
      "grad_norm": 0.1713708427354091,
      "learning_rate": 8.005630957010014e-08,
      "loss": 0.2632,
      "step": 380
    },
    {
      "epoch": 4.8768,
      "grad_norm": 0.1685673876803162,
      "learning_rate": 6.485383731580142e-08,
      "loss": 0.2701,
      "step": 381
    },
    {
      "epoch": 4.8896,
      "grad_norm": 0.166606338953714,
      "learning_rate": 5.1248354475768034e-08,
      "loss": 0.259,
      "step": 382
    },
    {
      "epoch": 4.9024,
      "grad_norm": 0.16731443926355397,
      "learning_rate": 3.924095097489922e-08,
      "loss": 0.2526,
      "step": 383
    },
    {
      "epoch": 4.9152000000000005,
      "grad_norm": 0.1685044586685876,
      "learning_rate": 2.8832588717164766e-08,
      "loss": 0.2686,
      "step": 384
    },
    {
      "epoch": 4.928,
      "grad_norm": 0.16691305854993616,
      "learning_rate": 2.0024101508555604e-08,
      "loss": 0.2618,
      "step": 385
    },
    {
      "epoch": 4.9408,
      "grad_norm": 0.1684797201052588,
      "learning_rate": 1.281619499029274e-08,
      "loss": 0.2675,
      "step": 386
    },
    {
      "epoch": 4.9536,
      "grad_norm": 0.1861012245822086,
      "learning_rate": 7.209446582292501e-09,
      "loss": 0.2592,
      "step": 387
    },
    {
      "epoch": 4.9664,
      "grad_norm": 0.17484645168594473,
      "learning_rate": 3.2043054369057523e-09,
      "loss": 0.2755,
      "step": 388
    },
    {
      "epoch": 4.9792,
      "grad_norm": 0.16579922216192233,
      "learning_rate": 8.010924029533406e-10,
      "loss": 0.2595,
      "step": 389
    },
    {
      "epoch": 4.992,
      "grad_norm": 0.16627934732470429,
      "learning_rate": 0.0,
      "loss": 0.2657,
      "step": 390
    },
    {
      "epoch": 4.992,
      "step": 390,
      "total_flos": 1.878482348849234e+18,
      "train_loss": 0.37849522767922816,
      "train_runtime": 19752.9737,
      "train_samples_per_second": 2.531,
      "train_steps_per_second": 0.02
    }
  ],
  "logging_steps": 1,
  "max_steps": 390,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.878482348849234e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}