{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9973614775725593,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0079155672823219,
      "grad_norm": 34.582191467285156,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.1743,
      "step": 1
    },
    {
      "epoch": 0.0158311345646438,
      "grad_norm": 35.2754020690918,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.195,
      "step": 2
    },
    {
      "epoch": 0.023746701846965697,
      "grad_norm": 35.12391662597656,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.1971,
      "step": 3
    },
    {
      "epoch": 0.0316622691292876,
      "grad_norm": 34.45759201049805,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.1701,
      "step": 4
    },
    {
      "epoch": 0.0395778364116095,
      "grad_norm": 35.35009002685547,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.2099,
      "step": 5
    },
    {
      "epoch": 0.047493403693931395,
      "grad_norm": 35.039520263671875,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.2169,
      "step": 6
    },
    {
      "epoch": 0.055408970976253295,
      "grad_norm": 35.103248596191406,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.2121,
      "step": 7
    },
    {
      "epoch": 0.0633245382585752,
      "grad_norm": 34.65024185180664,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.1715,
      "step": 8
    },
    {
      "epoch": 0.0712401055408971,
      "grad_norm": 35.055023193359375,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.1571,
      "step": 9
    },
    {
      "epoch": 0.079155672823219,
      "grad_norm": 34.82114028930664,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.1428,
      "step": 10
    },
    {
      "epoch": 0.0870712401055409,
      "grad_norm": 33.663883209228516,
      "learning_rate": 5.5e-07,
      "loss": 2.0656,
      "step": 11
    },
    {
      "epoch": 0.09498680738786279,
      "grad_norm": 33.614967346191406,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.05,
      "step": 12
    },
    {
      "epoch": 0.10290237467018469,
      "grad_norm": 32.66334915161133,
      "learning_rate": 6.5e-07,
      "loss": 1.9905,
      "step": 13
    },
    {
      "epoch": 0.11081794195250659,
      "grad_norm": 31.83934211730957,
      "learning_rate": 7.000000000000001e-07,
      "loss": 1.8981,
      "step": 14
    },
    {
      "epoch": 0.11873350923482849,
      "grad_norm": 32.067840576171875,
      "learning_rate": 7.5e-07,
      "loss": 1.8803,
      "step": 15
    },
    {
      "epoch": 0.1266490765171504,
      "grad_norm": 31.775592803955078,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.8215,
      "step": 16
    },
    {
      "epoch": 0.1345646437994723,
      "grad_norm": 30.205060958862305,
      "learning_rate": 8.500000000000001e-07,
      "loss": 1.6654,
      "step": 17
    },
    {
      "epoch": 0.1424802110817942,
      "grad_norm": 30.699304580688477,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.6149,
      "step": 18
    },
    {
      "epoch": 0.1503957783641161,
      "grad_norm": 30.16368293762207,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.4905,
      "step": 19
    },
    {
      "epoch": 0.158311345646438,
      "grad_norm": 30.227079391479492,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.3845,
      "step": 20
    },
    {
      "epoch": 0.1662269129287599,
      "grad_norm": 30.42757797241211,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.2462,
      "step": 21
    },
    {
      "epoch": 0.1741424802110818,
      "grad_norm": 30.44344711303711,
      "learning_rate": 1.1e-06,
      "loss": 1.0948,
      "step": 22
    },
    {
      "epoch": 0.1820580474934037,
      "grad_norm": 30.735376358032227,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 0.9618,
      "step": 23
    },
    {
      "epoch": 0.18997361477572558,
      "grad_norm": 30.048675537109375,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.7738,
      "step": 24
    },
    {
      "epoch": 0.19788918205804748,
      "grad_norm": 30.161460876464844,
      "learning_rate": 1.25e-06,
      "loss": 0.6424,
      "step": 25
    },
    {
      "epoch": 0.20580474934036938,
      "grad_norm": 28.648540496826172,
      "learning_rate": 1.3e-06,
      "loss": 0.4602,
      "step": 26
    },
    {
      "epoch": 0.21372031662269128,
      "grad_norm": 25.193084716796875,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.3309,
      "step": 27
    },
    {
      "epoch": 0.22163588390501318,
      "grad_norm": 18.437116622924805,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.2206,
      "step": 28
    },
    {
      "epoch": 0.22955145118733508,
      "grad_norm": 12.642715454101562,
      "learning_rate": 1.45e-06,
      "loss": 0.139,
      "step": 29
    },
    {
      "epoch": 0.23746701846965698,
      "grad_norm": 6.1605305671691895,
      "learning_rate": 1.5e-06,
      "loss": 0.0982,
      "step": 30
    },
    {
      "epoch": 0.24538258575197888,
      "grad_norm": 2.986103057861328,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.0707,
      "step": 31
    },
    {
      "epoch": 0.2532981530343008,
      "grad_norm": 2.030493974685669,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0637,
      "step": 32
    },
    {
      "epoch": 0.2612137203166227,
      "grad_norm": 1.5127642154693604,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0616,
      "step": 33
    },
    {
      "epoch": 0.2691292875989446,
      "grad_norm": 1.8087722063064575,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0555,
      "step": 34
    },
    {
      "epoch": 0.2770448548812665,
      "grad_norm": 1.3533340692520142,
      "learning_rate": 1.75e-06,
      "loss": 0.0517,
      "step": 35
    },
    {
      "epoch": 0.2849604221635884,
      "grad_norm": 1.3595997095108032,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0537,
      "step": 36
    },
    {
      "epoch": 0.2928759894459103,
      "grad_norm": 1.2778421640396118,
      "learning_rate": 1.85e-06,
      "loss": 0.0483,
      "step": 37
    },
    {
      "epoch": 0.3007915567282322,
      "grad_norm": 1.0834269523620605,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0471,
      "step": 38
    },
    {
      "epoch": 0.3087071240105541,
      "grad_norm": 1.175179362297058,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0528,
      "step": 39
    },
    {
      "epoch": 0.316622691292876,
      "grad_norm": 0.9915143847465515,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0525,
      "step": 40
    },
    {
      "epoch": 0.3245382585751979,
      "grad_norm": 0.7996736168861389,
      "learning_rate": 2.05e-06,
      "loss": 0.0479,
      "step": 41
    },
    {
      "epoch": 0.3324538258575198,
      "grad_norm": 0.7375659942626953,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0509,
      "step": 42
    },
    {
      "epoch": 0.3403693931398417,
      "grad_norm": 0.7712483406066895,
      "learning_rate": 2.15e-06,
      "loss": 0.0484,
      "step": 43
    },
    {
      "epoch": 0.3482849604221636,
      "grad_norm": 0.9321597218513489,
      "learning_rate": 2.2e-06,
      "loss": 0.0448,
      "step": 44
    },
    {
      "epoch": 0.3562005277044855,
      "grad_norm": 1.02247953414917,
      "learning_rate": 2.25e-06,
      "loss": 0.0484,
      "step": 45
    },
    {
      "epoch": 0.3641160949868074,
      "grad_norm": 0.857718825340271,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0425,
      "step": 46
    },
    {
      "epoch": 0.3720316622691293,
      "grad_norm": 1.0721040964126587,
      "learning_rate": 2.35e-06,
      "loss": 0.0472,
      "step": 47
    },
    {
      "epoch": 0.37994722955145116,
      "grad_norm": 0.811705470085144,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.039,
      "step": 48
    },
    {
      "epoch": 0.38786279683377306,
      "grad_norm": 0.9680790901184082,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0423,
      "step": 49
    },
    {
      "epoch": 0.39577836411609496,
      "grad_norm": 0.9470660090446472,
      "learning_rate": 2.5e-06,
      "loss": 0.0411,
      "step": 50
    },
    {
      "epoch": 0.40369393139841686,
      "grad_norm": 0.8540447950363159,
      "learning_rate": 2.55e-06,
      "loss": 0.049,
      "step": 51
    },
    {
      "epoch": 0.41160949868073876,
      "grad_norm": 1.39769446849823,
      "learning_rate": 2.6e-06,
      "loss": 0.0478,
      "step": 52
    },
    {
      "epoch": 0.41952506596306066,
      "grad_norm": 0.8914775848388672,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0415,
      "step": 53
    },
    {
      "epoch": 0.42744063324538256,
      "grad_norm": 0.759353518486023,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.046,
      "step": 54
    },
    {
      "epoch": 0.43535620052770446,
      "grad_norm": 0.8632487058639526,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0435,
      "step": 55
    },
    {
      "epoch": 0.44327176781002636,
      "grad_norm": 0.6662724018096924,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0496,
      "step": 56
    },
    {
      "epoch": 0.45118733509234826,
      "grad_norm": 0.8853585124015808,
      "learning_rate": 2.85e-06,
      "loss": 0.0384,
      "step": 57
    },
    {
      "epoch": 0.45910290237467016,
      "grad_norm": 0.7003194093704224,
      "learning_rate": 2.9e-06,
      "loss": 0.0446,
      "step": 58
    },
    {
      "epoch": 0.46701846965699206,
      "grad_norm": 0.8177786469459534,
      "learning_rate": 2.95e-06,
      "loss": 0.0417,
      "step": 59
    },
    {
      "epoch": 0.47493403693931396,
      "grad_norm": 0.9565925598144531,
      "learning_rate": 3e-06,
      "loss": 0.044,
      "step": 60
    },
    {
      "epoch": 0.48284960422163586,
      "grad_norm": 0.7401254177093506,
      "learning_rate": 3.05e-06,
      "loss": 0.0439,
      "step": 61
    },
    {
      "epoch": 0.49076517150395776,
      "grad_norm": 0.9952861666679382,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0371,
      "step": 62
    },
    {
      "epoch": 0.49868073878627966,
      "grad_norm": 0.9622153639793396,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0457,
      "step": 63
    },
    {
      "epoch": 0.5065963060686016,
      "grad_norm": 0.7078511118888855,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0396,
      "step": 64
    },
    {
      "epoch": 0.5145118733509235,
      "grad_norm": 0.9370516538619995,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0421,
      "step": 65
    },
    {
      "epoch": 0.5224274406332454,
      "grad_norm": 0.6465123891830444,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0341,
      "step": 66
    },
    {
      "epoch": 0.5303430079155673,
      "grad_norm": 0.7659086585044861,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0429,
      "step": 67
    },
    {
      "epoch": 0.5382585751978892,
      "grad_norm": 0.7772212028503418,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.036,
      "step": 68
    },
    {
      "epoch": 0.5461741424802111,
      "grad_norm": 0.7115844488143921,
      "learning_rate": 3.45e-06,
      "loss": 0.0327,
      "step": 69
    },
    {
      "epoch": 0.554089709762533,
      "grad_norm": 0.6542766690254211,
      "learning_rate": 3.5e-06,
      "loss": 0.0362,
      "step": 70
    },
    {
      "epoch": 0.5620052770448549,
      "grad_norm": 0.7394366264343262,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0426,
      "step": 71
    },
    {
      "epoch": 0.5699208443271768,
      "grad_norm": 0.8163363337516785,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0344,
      "step": 72
    },
    {
      "epoch": 0.5778364116094987,
      "grad_norm": 0.7115806937217712,
      "learning_rate": 3.65e-06,
      "loss": 0.0379,
      "step": 73
    },
    {
      "epoch": 0.5857519788918206,
      "grad_norm": 0.6192121505737305,
      "learning_rate": 3.7e-06,
      "loss": 0.0276,
      "step": 74
    },
    {
      "epoch": 0.5936675461741425,
      "grad_norm": 0.822684645652771,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0308,
      "step": 75
    },
    {
      "epoch": 0.6015831134564644,
      "grad_norm": 0.8095663189888,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0303,
      "step": 76
    },
    {
      "epoch": 0.6094986807387863,
      "grad_norm": 0.7700952887535095,
      "learning_rate": 3.85e-06,
      "loss": 0.0328,
      "step": 77
    },
    {
      "epoch": 0.6174142480211082,
      "grad_norm": 0.7777529358863831,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0344,
      "step": 78
    },
    {
      "epoch": 0.6253298153034301,
      "grad_norm": 0.826386034488678,
      "learning_rate": 3.95e-06,
      "loss": 0.033,
      "step": 79
    },
    {
      "epoch": 0.633245382585752,
      "grad_norm": 0.788942277431488,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0331,
      "step": 80
    },
    {
      "epoch": 0.6411609498680739,
      "grad_norm": 0.7351260185241699,
      "learning_rate": 4.05e-06,
      "loss": 0.0346,
      "step": 81
    },
    {
      "epoch": 0.6490765171503958,
      "grad_norm": 0.5737812519073486,
      "learning_rate": 4.1e-06,
      "loss": 0.027,
      "step": 82
    },
    {
      "epoch": 0.6569920844327177,
      "grad_norm": 0.7053394913673401,
      "learning_rate": 4.15e-06,
      "loss": 0.034,
      "step": 83
    },
    {
      "epoch": 0.6649076517150396,
      "grad_norm": 0.7508617639541626,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0323,
      "step": 84
    },
    {
      "epoch": 0.6728232189973615,
      "grad_norm": 1.0235975980758667,
      "learning_rate": 4.25e-06,
      "loss": 0.0395,
      "step": 85
    },
    {
      "epoch": 0.6807387862796834,
      "grad_norm": 0.6522803902626038,
      "learning_rate": 4.3e-06,
      "loss": 0.0262,
      "step": 86
    },
    {
      "epoch": 0.6886543535620053,
      "grad_norm": 1.182160496711731,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0387,
      "step": 87
    },
    {
      "epoch": 0.6965699208443272,
      "grad_norm": 0.6571248769760132,
      "learning_rate": 4.4e-06,
      "loss": 0.0262,
      "step": 88
    },
    {
      "epoch": 0.7044854881266491,
      "grad_norm": 0.6641517877578735,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0265,
      "step": 89
    },
    {
      "epoch": 0.712401055408971,
      "grad_norm": 0.8751306533813477,
      "learning_rate": 4.5e-06,
      "loss": 0.0307,
      "step": 90
    },
    {
      "epoch": 0.7203166226912929,
      "grad_norm": 0.7627044320106506,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0332,
      "step": 91
    },
    {
      "epoch": 0.7282321899736148,
      "grad_norm": 0.7124688625335693,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0299,
      "step": 92
    },
    {
      "epoch": 0.7361477572559367,
      "grad_norm": 0.7688237428665161,
      "learning_rate": 4.65e-06,
      "loss": 0.0258,
      "step": 93
    },
    {
      "epoch": 0.7440633245382586,
      "grad_norm": 0.8663469552993774,
      "learning_rate": 4.7e-06,
      "loss": 0.0342,
      "step": 94
    },
    {
      "epoch": 0.7519788918205804,
      "grad_norm": 0.6536213755607605,
      "learning_rate": 4.75e-06,
      "loss": 0.0226,
      "step": 95
    },
    {
      "epoch": 0.7598944591029023,
      "grad_norm": 0.5616201758384705,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.022,
      "step": 96
    },
    {
      "epoch": 0.7678100263852242,
      "grad_norm": 0.7985079884529114,
      "learning_rate": 4.85e-06,
      "loss": 0.0305,
      "step": 97
    },
    {
      "epoch": 0.7757255936675461,
      "grad_norm": 0.726844847202301,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0243,
      "step": 98
    },
    {
      "epoch": 0.783641160949868,
      "grad_norm": 0.656874418258667,
      "learning_rate": 4.95e-06,
      "loss": 0.0243,
      "step": 99
    },
    {
      "epoch": 0.7915567282321899,
      "grad_norm": 0.8744286894798279,
      "learning_rate": 5e-06,
      "loss": 0.0261,
      "step": 100
    },
    {
      "epoch": 0.7994722955145118,
      "grad_norm": 1.0138187408447266,
      "learning_rate": 4.9999713317456065e-06,
      "loss": 0.0254,
      "step": 101
    },
    {
      "epoch": 0.8073878627968337,
      "grad_norm": 0.6964263319969177,
      "learning_rate": 4.9998853276399215e-06,
      "loss": 0.0263,
      "step": 102
    },
    {
      "epoch": 0.8153034300791556,
      "grad_norm": 0.6374551057815552,
      "learning_rate": 4.999741989655415e-06,
      "loss": 0.0228,
      "step": 103
    },
    {
      "epoch": 0.8232189973614775,
      "grad_norm": 0.6274930834770203,
      "learning_rate": 4.999541321079486e-06,
      "loss": 0.0286,
      "step": 104
    },
    {
      "epoch": 0.8311345646437994,
      "grad_norm": 0.6344143748283386,
      "learning_rate": 4.99928332651439e-06,
      "loss": 0.0258,
      "step": 105
    },
    {
      "epoch": 0.8390501319261213,
      "grad_norm": 0.8304360508918762,
      "learning_rate": 4.998968011877129e-06,
      "loss": 0.022,
      "step": 106
    },
    {
      "epoch": 0.8469656992084432,
      "grad_norm": 0.6463897228240967,
      "learning_rate": 4.998595384399319e-06,
      "loss": 0.0184,
      "step": 107
    },
    {
      "epoch": 0.8548812664907651,
      "grad_norm": 0.5647016763687134,
      "learning_rate": 4.998165452627025e-06,
      "loss": 0.0221,
      "step": 108
    },
    {
      "epoch": 0.862796833773087,
      "grad_norm": 0.5621638298034668,
      "learning_rate": 4.997678226420561e-06,
      "loss": 0.022,
      "step": 109
    },
    {
      "epoch": 0.8707124010554089,
      "grad_norm": 0.8295672535896301,
      "learning_rate": 4.997133716954266e-06,
      "loss": 0.0206,
      "step": 110
    },
    {
      "epoch": 0.8786279683377308,
      "grad_norm": 0.8057272434234619,
      "learning_rate": 4.99653193671625e-06,
      "loss": 0.0204,
      "step": 111
    },
    {
      "epoch": 0.8865435356200527,
      "grad_norm": 0.6956275105476379,
      "learning_rate": 4.995872899508103e-06,
      "loss": 0.0186,
      "step": 112
    },
    {
      "epoch": 0.8944591029023746,
      "grad_norm": 0.7873161435127258,
      "learning_rate": 4.995156620444584e-06,
      "loss": 0.0149,
      "step": 113
    },
    {
      "epoch": 0.9023746701846965,
      "grad_norm": 0.9187519550323486,
      "learning_rate": 4.994383115953266e-06,
      "loss": 0.0183,
      "step": 114
    },
    {
      "epoch": 0.9102902374670184,
      "grad_norm": 0.5987403392791748,
      "learning_rate": 4.9935524037741705e-06,
      "loss": 0.0158,
      "step": 115
    },
    {
      "epoch": 0.9182058047493403,
      "grad_norm": 0.6011790037155151,
      "learning_rate": 4.992664502959351e-06,
      "loss": 0.016,
      "step": 116
    },
    {
      "epoch": 0.9261213720316622,
      "grad_norm": 0.8429304957389832,
      "learning_rate": 4.991719433872461e-06,
      "loss": 0.0107,
      "step": 117
    },
    {
      "epoch": 0.9340369393139841,
      "grad_norm": 0.8618797659873962,
      "learning_rate": 4.990717218188286e-06,
      "loss": 0.0162,
      "step": 118
    },
    {
      "epoch": 0.941952506596306,
      "grad_norm": 1.1907824277877808,
      "learning_rate": 4.989657878892245e-06,
      "loss": 0.0173,
      "step": 119
    },
    {
      "epoch": 0.9498680738786279,
      "grad_norm": 0.7317540645599365,
      "learning_rate": 4.988541440279862e-06,
      "loss": 0.0183,
      "step": 120
    },
    {
      "epoch": 0.9577836411609498,
      "grad_norm": 0.6827302575111389,
      "learning_rate": 4.987367927956218e-06,
      "loss": 0.0192,
      "step": 121
    },
    {
      "epoch": 0.9656992084432717,
      "grad_norm": 0.6512569189071655,
      "learning_rate": 4.986137368835351e-06,
      "loss": 0.0169,
      "step": 122
    },
    {
      "epoch": 0.9736147757255936,
      "grad_norm": 0.5439648032188416,
      "learning_rate": 4.984849791139647e-06,
      "loss": 0.0136,
      "step": 123
    },
    {
      "epoch": 0.9815303430079155,
      "grad_norm": 0.5652760863304138,
      "learning_rate": 4.983505224399188e-06,
      "loss": 0.0171,
      "step": 124
    },
    {
      "epoch": 0.9894459102902374,
      "grad_norm": 0.6217207908630371,
      "learning_rate": 4.9821036994510816e-06,
      "loss": 0.0175,
      "step": 125
    },
    {
      "epoch": 0.9973614775725593,
      "grad_norm": 0.5073563456535339,
      "learning_rate": 4.980645248438746e-06,
      "loss": 0.0166,
      "step": 126
    }
  ],
  "logging_steps": 1,
  "max_steps": 756,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 126,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.182806237918003e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}