{
  "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": 30.869014739990234,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 3.7012,
      "step": 1
    },
    {
      "epoch": 0.0158311345646438,
      "grad_norm": 31.733173370361328,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 3.7487,
      "step": 2
    },
    {
      "epoch": 0.023746701846965697,
      "grad_norm": 31.742353439331055,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 3.7018,
      "step": 3
    },
    {
      "epoch": 0.0316622691292876,
      "grad_norm": 31.144001007080078,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 3.6754,
      "step": 4
    },
    {
      "epoch": 0.0395778364116095,
      "grad_norm": 30.949337005615234,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 3.7139,
      "step": 5
    },
    {
      "epoch": 0.047493403693931395,
      "grad_norm": 31.45248031616211,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 3.7776,
      "step": 6
    },
    {
      "epoch": 0.055408970976253295,
      "grad_norm": 31.660465240478516,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 3.7274,
      "step": 7
    },
    {
      "epoch": 0.0633245382585752,
      "grad_norm": 30.728031158447266,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 3.6926,
      "step": 8
    },
    {
      "epoch": 0.0712401055408971,
      "grad_norm": 31.589900970458984,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 3.7384,
      "step": 9
    },
    {
      "epoch": 0.079155672823219,
      "grad_norm": 30.93056297302246,
      "learning_rate": 5.000000000000001e-07,
      "loss": 3.6975,
      "step": 10
    },
    {
      "epoch": 0.0870712401055409,
      "grad_norm": 29.612712860107422,
      "learning_rate": 5.5e-07,
      "loss": 3.6154,
      "step": 11
    },
    {
      "epoch": 0.09498680738786279,
      "grad_norm": 29.427888870239258,
      "learning_rate": 6.000000000000001e-07,
      "loss": 3.5904,
      "step": 12
    },
    {
      "epoch": 0.10290237467018469,
      "grad_norm": 28.683610916137695,
      "learning_rate": 6.5e-07,
      "loss": 3.5048,
      "step": 13
    },
    {
      "epoch": 0.11081794195250659,
      "grad_norm": 27.198017120361328,
      "learning_rate": 7.000000000000001e-07,
      "loss": 3.3737,
      "step": 14
    },
    {
      "epoch": 0.11873350923482849,
      "grad_norm": 26.540634155273438,
      "learning_rate": 7.5e-07,
      "loss": 3.4435,
      "step": 15
    },
    {
      "epoch": 0.1266490765171504,
      "grad_norm": 25.825363159179688,
      "learning_rate": 8.000000000000001e-07,
      "loss": 3.3308,
      "step": 16
    },
    {
      "epoch": 0.1345646437994723,
      "grad_norm": 24.061580657958984,
      "learning_rate": 8.500000000000001e-07,
      "loss": 3.1701,
      "step": 17
    },
    {
      "epoch": 0.1424802110817942,
      "grad_norm": 22.808284759521484,
      "learning_rate": 9.000000000000001e-07,
      "loss": 3.1343,
      "step": 18
    },
    {
      "epoch": 0.1503957783641161,
      "grad_norm": 21.435670852661133,
      "learning_rate": 9.500000000000001e-07,
      "loss": 3.0035,
      "step": 19
    },
    {
      "epoch": 0.158311345646438,
      "grad_norm": 20.890090942382812,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.9045,
      "step": 20
    },
    {
      "epoch": 0.1662269129287599,
      "grad_norm": 19.962282180786133,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 2.7882,
      "step": 21
    },
    {
      "epoch": 0.1741424802110818,
      "grad_norm": 19.279138565063477,
      "learning_rate": 1.1e-06,
      "loss": 2.6107,
      "step": 22
    },
    {
      "epoch": 0.1820580474934037,
      "grad_norm": 18.44759178161621,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 2.4873,
      "step": 23
    },
    {
      "epoch": 0.18997361477572558,
      "grad_norm": 17.96116065979004,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.2947,
      "step": 24
    },
    {
      "epoch": 0.19788918205804748,
      "grad_norm": 18.503511428833008,
      "learning_rate": 1.25e-06,
      "loss": 2.2086,
      "step": 25
    },
    {
      "epoch": 0.20580474934036938,
      "grad_norm": 17.768098831176758,
      "learning_rate": 1.3e-06,
      "loss": 2.018,
      "step": 26
    },
    {
      "epoch": 0.21372031662269128,
      "grad_norm": 17.546539306640625,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 1.9271,
      "step": 27
    },
    {
      "epoch": 0.22163588390501318,
      "grad_norm": 16.827245712280273,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.7777,
      "step": 28
    },
    {
      "epoch": 0.22955145118733508,
      "grad_norm": 15.83143138885498,
      "learning_rate": 1.45e-06,
      "loss": 1.6259,
      "step": 29
    },
    {
      "epoch": 0.23746701846965698,
      "grad_norm": 15.121193885803223,
      "learning_rate": 1.5e-06,
      "loss": 1.4957,
      "step": 30
    },
    {
      "epoch": 0.24538258575197888,
      "grad_norm": 13.953106880187988,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 1.314,
      "step": 31
    },
    {
      "epoch": 0.2532981530343008,
      "grad_norm": 13.442436218261719,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.2131,
      "step": 32
    },
    {
      "epoch": 0.2612137203166227,
      "grad_norm": 12.913166046142578,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 1.0614,
      "step": 33
    },
    {
      "epoch": 0.2691292875989446,
      "grad_norm": 12.016983985900879,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.926,
      "step": 34
    },
    {
      "epoch": 0.2770448548812665,
      "grad_norm": 12.453398704528809,
      "learning_rate": 1.75e-06,
      "loss": 0.8099,
      "step": 35
    },
    {
      "epoch": 0.2849604221635884,
      "grad_norm": 11.902524948120117,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.7201,
      "step": 36
    },
    {
      "epoch": 0.2928759894459103,
      "grad_norm": 11.01728343963623,
      "learning_rate": 1.85e-06,
      "loss": 0.6013,
      "step": 37
    },
    {
      "epoch": 0.3007915567282322,
      "grad_norm": 9.88390064239502,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.4793,
      "step": 38
    },
    {
      "epoch": 0.3087071240105541,
      "grad_norm": 8.726274490356445,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.3859,
      "step": 39
    },
    {
      "epoch": 0.316622691292876,
      "grad_norm": 6.780221462249756,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.3218,
      "step": 40
    },
    {
      "epoch": 0.3245382585751979,
      "grad_norm": 6.255209445953369,
      "learning_rate": 2.05e-06,
      "loss": 0.2498,
      "step": 41
    },
    {
      "epoch": 0.3324538258575198,
      "grad_norm": 7.047099590301514,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.2299,
      "step": 42
    },
    {
      "epoch": 0.3403693931398417,
      "grad_norm": 6.4962944984436035,
      "learning_rate": 2.15e-06,
      "loss": 0.1926,
      "step": 43
    },
    {
      "epoch": 0.3482849604221636,
      "grad_norm": 5.178858757019043,
      "learning_rate": 2.2e-06,
      "loss": 0.1659,
      "step": 44
    },
    {
      "epoch": 0.3562005277044855,
      "grad_norm": 3.723464012145996,
      "learning_rate": 2.25e-06,
      "loss": 0.1344,
      "step": 45
    },
    {
      "epoch": 0.3641160949868074,
      "grad_norm": 2.3385989665985107,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.1221,
      "step": 46
    },
    {
      "epoch": 0.3720316622691293,
      "grad_norm": 1.5498709678649902,
      "learning_rate": 2.35e-06,
      "loss": 0.0951,
      "step": 47
    },
    {
      "epoch": 0.37994722955145116,
      "grad_norm": 1.1670784950256348,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.091,
      "step": 48
    },
    {
      "epoch": 0.38786279683377306,
      "grad_norm": 1.0624521970748901,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0888,
      "step": 49
    },
    {
      "epoch": 0.39577836411609496,
      "grad_norm": 0.9028095006942749,
      "learning_rate": 2.5e-06,
      "loss": 0.0832,
      "step": 50
    },
    {
      "epoch": 0.40369393139841686,
      "grad_norm": 0.8736869692802429,
      "learning_rate": 2.55e-06,
      "loss": 0.0865,
      "step": 51
    },
    {
      "epoch": 0.41160949868073876,
      "grad_norm": 0.8399665355682373,
      "learning_rate": 2.6e-06,
      "loss": 0.0791,
      "step": 52
    },
    {
      "epoch": 0.41952506596306066,
      "grad_norm": 0.7182458639144897,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0725,
      "step": 53
    },
    {
      "epoch": 0.42744063324538256,
      "grad_norm": 0.5676689147949219,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.077,
      "step": 54
    },
    {
      "epoch": 0.43535620052770446,
      "grad_norm": 0.5275952219963074,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0682,
      "step": 55
    },
    {
      "epoch": 0.44327176781002636,
      "grad_norm": 0.5252273082733154,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.077,
      "step": 56
    },
    {
      "epoch": 0.45118733509234826,
      "grad_norm": 0.5784285664558411,
      "learning_rate": 2.85e-06,
      "loss": 0.0727,
      "step": 57
    },
    {
      "epoch": 0.45910290237467016,
      "grad_norm": 0.5059791207313538,
      "learning_rate": 2.9e-06,
      "loss": 0.0738,
      "step": 58
    },
    {
      "epoch": 0.46701846965699206,
      "grad_norm": 0.6042116284370422,
      "learning_rate": 2.95e-06,
      "loss": 0.0657,
      "step": 59
    },
    {
      "epoch": 0.47493403693931396,
      "grad_norm": 0.7056423425674438,
      "learning_rate": 3e-06,
      "loss": 0.0735,
      "step": 60
    },
    {
      "epoch": 0.48284960422163586,
      "grad_norm": 0.5071430802345276,
      "learning_rate": 3.05e-06,
      "loss": 0.068,
      "step": 61
    },
    {
      "epoch": 0.49076517150395776,
      "grad_norm": 0.6120741367340088,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0663,
      "step": 62
    },
    {
      "epoch": 0.49868073878627966,
      "grad_norm": 0.5747594237327576,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0702,
      "step": 63
    },
    {
      "epoch": 0.5065963060686016,
      "grad_norm": 0.3565518260002136,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0602,
      "step": 64
    },
    {
      "epoch": 0.5145118733509235,
      "grad_norm": 0.5836294293403625,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.07,
      "step": 65
    },
    {
      "epoch": 0.5224274406332454,
      "grad_norm": 0.42942124605178833,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0578,
      "step": 66
    },
    {
      "epoch": 0.5303430079155673,
      "grad_norm": 0.3953992426395416,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.06,
      "step": 67
    },
    {
      "epoch": 0.5382585751978892,
      "grad_norm": 0.525784969329834,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0544,
      "step": 68
    },
    {
      "epoch": 0.5461741424802111,
      "grad_norm": 0.5336060523986816,
      "learning_rate": 3.45e-06,
      "loss": 0.0621,
      "step": 69
    },
    {
      "epoch": 0.554089709762533,
      "grad_norm": 0.5048466920852661,
      "learning_rate": 3.5e-06,
      "loss": 0.0629,
      "step": 70
    },
    {
      "epoch": 0.5620052770448549,
      "grad_norm": 0.54691481590271,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0685,
      "step": 71
    },
    {
      "epoch": 0.5699208443271768,
      "grad_norm": 0.3295685350894928,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0601,
      "step": 72
    },
    {
      "epoch": 0.5778364116094987,
      "grad_norm": 0.44020742177963257,
      "learning_rate": 3.65e-06,
      "loss": 0.0569,
      "step": 73
    },
    {
      "epoch": 0.5857519788918206,
      "grad_norm": 0.2974744141101837,
      "learning_rate": 3.7e-06,
      "loss": 0.0612,
      "step": 74
    },
    {
      "epoch": 0.5936675461741425,
      "grad_norm": 0.37300822138786316,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0554,
      "step": 75
    },
    {
      "epoch": 0.6015831134564644,
      "grad_norm": 0.37561413645744324,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0545,
      "step": 76
    },
    {
      "epoch": 0.6094986807387863,
      "grad_norm": 0.4859388768672943,
      "learning_rate": 3.85e-06,
      "loss": 0.0578,
      "step": 77
    },
    {
      "epoch": 0.6174142480211082,
      "grad_norm": 0.46191921830177307,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0567,
      "step": 78
    },
    {
      "epoch": 0.6253298153034301,
      "grad_norm": 0.4128071963787079,
      "learning_rate": 3.95e-06,
      "loss": 0.0602,
      "step": 79
    },
    {
      "epoch": 0.633245382585752,
      "grad_norm": 0.31622228026390076,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0567,
      "step": 80
    },
    {
      "epoch": 0.6411609498680739,
      "grad_norm": 0.617358386516571,
      "learning_rate": 4.05e-06,
      "loss": 0.0656,
      "step": 81
    },
    {
      "epoch": 0.6490765171503958,
      "grad_norm": 0.4259068965911865,
      "learning_rate": 4.1e-06,
      "loss": 0.0518,
      "step": 82
    },
    {
      "epoch": 0.6569920844327177,
      "grad_norm": 0.276052862405777,
      "learning_rate": 4.15e-06,
      "loss": 0.0622,
      "step": 83
    },
    {
      "epoch": 0.6649076517150396,
      "grad_norm": 0.3911490738391876,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.059,
      "step": 84
    },
    {
      "epoch": 0.6728232189973615,
      "grad_norm": 0.39195016026496887,
      "learning_rate": 4.25e-06,
      "loss": 0.0631,
      "step": 85
    },
    {
      "epoch": 0.6807387862796834,
      "grad_norm": 0.267223060131073,
      "learning_rate": 4.3e-06,
      "loss": 0.0509,
      "step": 86
    },
    {
      "epoch": 0.6886543535620053,
      "grad_norm": 0.6315395832061768,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0644,
      "step": 87
    },
    {
      "epoch": 0.6965699208443272,
      "grad_norm": 0.36506301164627075,
      "learning_rate": 4.4e-06,
      "loss": 0.0575,
      "step": 88
    },
    {
      "epoch": 0.7044854881266491,
      "grad_norm": 0.30107879638671875,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0563,
      "step": 89
    },
    {
      "epoch": 0.712401055408971,
      "grad_norm": 0.3180297613143921,
      "learning_rate": 4.5e-06,
      "loss": 0.0537,
      "step": 90
    },
    {
      "epoch": 0.7203166226912929,
      "grad_norm": 0.2672456204891205,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0582,
      "step": 91
    },
    {
      "epoch": 0.7282321899736148,
      "grad_norm": 0.3606305420398712,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0506,
      "step": 92
    },
    {
      "epoch": 0.7361477572559367,
      "grad_norm": 0.335498183965683,
      "learning_rate": 4.65e-06,
      "loss": 0.0583,
      "step": 93
    },
    {
      "epoch": 0.7440633245382586,
      "grad_norm": 0.4400036334991455,
      "learning_rate": 4.7e-06,
      "loss": 0.0641,
      "step": 94
    },
    {
      "epoch": 0.7519788918205804,
      "grad_norm": 0.31314533948898315,
      "learning_rate": 4.75e-06,
      "loss": 0.0549,
      "step": 95
    },
    {
      "epoch": 0.7598944591029023,
      "grad_norm": 0.28006380796432495,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.0541,
      "step": 96
    },
    {
      "epoch": 0.7678100263852242,
      "grad_norm": 0.3578348755836487,
      "learning_rate": 4.85e-06,
      "loss": 0.0513,
      "step": 97
    },
    {
      "epoch": 0.7757255936675461,
      "grad_norm": 0.2923860549926758,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0565,
      "step": 98
    },
    {
      "epoch": 0.783641160949868,
      "grad_norm": 0.2959270775318146,
      "learning_rate": 4.95e-06,
      "loss": 0.0584,
      "step": 99
    },
    {
      "epoch": 0.7915567282321899,
      "grad_norm": 0.3138754367828369,
      "learning_rate": 5e-06,
      "loss": 0.0532,
      "step": 100
    },
    {
      "epoch": 0.7994722955145118,
      "grad_norm": 0.34502485394477844,
      "learning_rate": 4.9999713317456065e-06,
      "loss": 0.0582,
      "step": 101
    },
    {
      "epoch": 0.8073878627968337,
      "grad_norm": 0.27575260400772095,
      "learning_rate": 4.9998853276399215e-06,
      "loss": 0.05,
      "step": 102
    },
    {
      "epoch": 0.8153034300791556,
      "grad_norm": 0.40034064650535583,
      "learning_rate": 4.999741989655415e-06,
      "loss": 0.0568,
      "step": 103
    },
    {
      "epoch": 0.8232189973614775,
      "grad_norm": 0.463155061006546,
      "learning_rate": 4.999541321079486e-06,
      "loss": 0.0584,
      "step": 104
    },
    {
      "epoch": 0.8311345646437994,
      "grad_norm": 0.3311242163181305,
      "learning_rate": 4.99928332651439e-06,
      "loss": 0.0547,
      "step": 105
    },
    {
      "epoch": 0.8390501319261213,
      "grad_norm": 0.3222312927246094,
      "learning_rate": 4.998968011877129e-06,
      "loss": 0.0569,
      "step": 106
    },
    {
      "epoch": 0.8469656992084432,
      "grad_norm": 0.4004589021205902,
      "learning_rate": 4.998595384399319e-06,
      "loss": 0.0509,
      "step": 107
    },
    {
      "epoch": 0.8548812664907651,
      "grad_norm": 0.25930100679397583,
      "learning_rate": 4.998165452627025e-06,
      "loss": 0.056,
      "step": 108
    },
    {
      "epoch": 0.862796833773087,
      "grad_norm": 0.2832070291042328,
      "learning_rate": 4.997678226420561e-06,
      "loss": 0.0599,
      "step": 109
    },
    {
      "epoch": 0.8707124010554089,
      "grad_norm": 0.27685272693634033,
      "learning_rate": 4.997133716954266e-06,
      "loss": 0.0526,
      "step": 110
    },
    {
      "epoch": 0.8786279683377308,
      "grad_norm": 0.3196943998336792,
      "learning_rate": 4.99653193671625e-06,
      "loss": 0.0538,
      "step": 111
    },
    {
      "epoch": 0.8865435356200527,
      "grad_norm": 0.32398006319999695,
      "learning_rate": 4.995872899508103e-06,
      "loss": 0.0582,
      "step": 112
    },
    {
      "epoch": 0.8944591029023746,
      "grad_norm": 0.264309287071228,
      "learning_rate": 4.995156620444584e-06,
      "loss": 0.0545,
      "step": 113
    },
    {
      "epoch": 0.9023746701846965,
      "grad_norm": 0.2664014995098114,
      "learning_rate": 4.994383115953266e-06,
      "loss": 0.0559,
      "step": 114
    },
    {
      "epoch": 0.9102902374670184,
      "grad_norm": 0.30734142661094666,
      "learning_rate": 4.9935524037741705e-06,
      "loss": 0.0527,
      "step": 115
    },
    {
      "epoch": 0.9182058047493403,
      "grad_norm": 0.35413816571235657,
      "learning_rate": 4.992664502959351e-06,
      "loss": 0.0476,
      "step": 116
    },
    {
      "epoch": 0.9261213720316622,
      "grad_norm": 0.24693645536899567,
      "learning_rate": 4.991719433872461e-06,
      "loss": 0.0442,
      "step": 117
    },
    {
      "epoch": 0.9340369393139841,
      "grad_norm": 0.31462687253952026,
      "learning_rate": 4.990717218188286e-06,
      "loss": 0.047,
      "step": 118
    },
    {
      "epoch": 0.941952506596306,
      "grad_norm": 0.5714662671089172,
      "learning_rate": 4.989657878892245e-06,
      "loss": 0.0567,
      "step": 119
    },
    {
      "epoch": 0.9498680738786279,
      "grad_norm": 0.36190715432167053,
      "learning_rate": 4.988541440279862e-06,
      "loss": 0.0483,
      "step": 120
    },
    {
      "epoch": 0.9577836411609498,
      "grad_norm": 0.27186068892478943,
      "learning_rate": 4.987367927956218e-06,
      "loss": 0.0499,
      "step": 121
    },
    {
      "epoch": 0.9656992084432717,
      "grad_norm": 0.45251426100730896,
      "learning_rate": 4.986137368835351e-06,
      "loss": 0.0537,
      "step": 122
    },
    {
      "epoch": 0.9736147757255936,
      "grad_norm": 0.2997976541519165,
      "learning_rate": 4.984849791139647e-06,
      "loss": 0.0508,
      "step": 123
    },
    {
      "epoch": 0.9815303430079155,
      "grad_norm": 0.3122728168964386,
      "learning_rate": 4.983505224399188e-06,
      "loss": 0.0497,
      "step": 124
    },
    {
      "epoch": 0.9894459102902374,
      "grad_norm": 0.41572335362434387,
      "learning_rate": 4.9821036994510816e-06,
      "loss": 0.0493,
      "step": 125
    },
    {
      "epoch": 0.9973614775725593,
      "grad_norm": 0.2922910153865814,
      "learning_rate": 4.980645248438746e-06,
      "loss": 0.0515,
      "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": 2.8225801850506445e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}