{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 152,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006600660066006601,
      "grad_norm": 3.143493175506592,
      "learning_rate": 0.0,
      "loss": 2.5041,
      "step": 1
    },
    {
      "epoch": 0.013201320132013201,
      "grad_norm": 4.06755256652832,
      "learning_rate": 4.347826086956522e-06,
      "loss": 2.5644,
      "step": 2
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 3.0701375007629395,
      "learning_rate": 8.695652173913044e-06,
      "loss": 2.5095,
      "step": 3
    },
    {
      "epoch": 0.026402640264026403,
      "grad_norm": 3.792125701904297,
      "learning_rate": 1.3043478260869566e-05,
      "loss": 2.426,
      "step": 4
    },
    {
      "epoch": 0.033003300330033,
      "grad_norm": 4.194362640380859,
      "learning_rate": 1.739130434782609e-05,
      "loss": 1.973,
      "step": 5
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 4.066171646118164,
      "learning_rate": 2.173913043478261e-05,
      "loss": 2.2242,
      "step": 6
    },
    {
      "epoch": 0.0462046204620462,
      "grad_norm": 3.9235055446624756,
      "learning_rate": 2.608695652173913e-05,
      "loss": 2.5398,
      "step": 7
    },
    {
      "epoch": 0.052805280528052806,
      "grad_norm": 3.5214486122131348,
      "learning_rate": 3.0434782608695656e-05,
      "loss": 1.9146,
      "step": 8
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 3.2443058490753174,
      "learning_rate": 3.478260869565218e-05,
      "loss": 2.0756,
      "step": 9
    },
    {
      "epoch": 0.066006600660066,
      "grad_norm": 3.280684471130371,
      "learning_rate": 3.91304347826087e-05,
      "loss": 2.3453,
      "step": 10
    },
    {
      "epoch": 0.07260726072607261,
      "grad_norm": 2.701324701309204,
      "learning_rate": 4.347826086956522e-05,
      "loss": 1.6499,
      "step": 11
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 2.205188035964966,
      "learning_rate": 4.782608695652174e-05,
      "loss": 1.8142,
      "step": 12
    },
    {
      "epoch": 0.0858085808580858,
      "grad_norm": 2.969386577606201,
      "learning_rate": 5.217391304347826e-05,
      "loss": 1.6555,
      "step": 13
    },
    {
      "epoch": 0.0924092409240924,
      "grad_norm": 3.1078085899353027,
      "learning_rate": 5.652173913043478e-05,
      "loss": 1.892,
      "step": 14
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 2.403679847717285,
      "learning_rate": 6.086956521739131e-05,
      "loss": 2.1263,
      "step": 15
    },
    {
      "epoch": 0.10561056105610561,
      "grad_norm": 3.7624003887176514,
      "learning_rate": 6.521739130434783e-05,
      "loss": 2.1824,
      "step": 16
    },
    {
      "epoch": 0.11221122112211221,
      "grad_norm": 2.571948766708374,
      "learning_rate": 6.956521739130436e-05,
      "loss": 2.2477,
      "step": 17
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 3.469731569290161,
      "learning_rate": 7.391304347826086e-05,
      "loss": 1.4427,
      "step": 18
    },
    {
      "epoch": 0.1254125412541254,
      "grad_norm": 2.207329750061035,
      "learning_rate": 7.82608695652174e-05,
      "loss": 1.5447,
      "step": 19
    },
    {
      "epoch": 0.132013201320132,
      "grad_norm": 2.514176368713379,
      "learning_rate": 8.260869565217392e-05,
      "loss": 1.9723,
      "step": 20
    },
    {
      "epoch": 0.13861386138613863,
      "grad_norm": 3.027451753616333,
      "learning_rate": 8.695652173913044e-05,
      "loss": 1.7312,
      "step": 21
    },
    {
      "epoch": 0.14521452145214522,
      "grad_norm": 5.07168436050415,
      "learning_rate": 9.130434782608696e-05,
      "loss": 2.5444,
      "step": 22
    },
    {
      "epoch": 0.15181518151815182,
      "grad_norm": 3.528111219406128,
      "learning_rate": 9.565217391304348e-05,
      "loss": 2.1284,
      "step": 23
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 3.0631463527679443,
      "learning_rate": 0.0001,
      "loss": 2.2181,
      "step": 24
    },
    {
      "epoch": 0.16501650165016502,
      "grad_norm": 3.331843852996826,
      "learning_rate": 0.00010434782608695653,
      "loss": 3.0526,
      "step": 25
    },
    {
      "epoch": 0.1716171617161716,
      "grad_norm": 2.444413661956787,
      "learning_rate": 0.00010869565217391305,
      "loss": 1.7363,
      "step": 26
    },
    {
      "epoch": 0.1782178217821782,
      "grad_norm": 2.5538690090179443,
      "learning_rate": 0.00011304347826086956,
      "loss": 1.5258,
      "step": 27
    },
    {
      "epoch": 0.1848184818481848,
      "grad_norm": 2.088798999786377,
      "learning_rate": 0.0001173913043478261,
      "loss": 1.8808,
      "step": 28
    },
    {
      "epoch": 0.19141914191419143,
      "grad_norm": 2.5747692584991455,
      "learning_rate": 0.00012173913043478263,
      "loss": 2.6931,
      "step": 29
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 2.9658546447753906,
      "learning_rate": 0.00012608695652173915,
      "loss": 2.0258,
      "step": 30
    },
    {
      "epoch": 0.20462046204620463,
      "grad_norm": 2.768965244293213,
      "learning_rate": 0.00013043478260869567,
      "loss": 1.8468,
      "step": 31
    },
    {
      "epoch": 0.21122112211221122,
      "grad_norm": 2.2689647674560547,
      "learning_rate": 0.0001347826086956522,
      "loss": 1.7859,
      "step": 32
    },
    {
      "epoch": 0.21782178217821782,
      "grad_norm": 2.06204891204834,
      "learning_rate": 0.0001391304347826087,
      "loss": 1.8043,
      "step": 33
    },
    {
      "epoch": 0.22442244224422442,
      "grad_norm": 2.958625078201294,
      "learning_rate": 0.0001434782608695652,
      "loss": 1.2597,
      "step": 34
    },
    {
      "epoch": 0.23102310231023102,
      "grad_norm": 2.6240015029907227,
      "learning_rate": 0.00014782608695652173,
      "loss": 1.9745,
      "step": 35
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 2.636274814605713,
      "learning_rate": 0.00015217391304347827,
      "loss": 1.8066,
      "step": 36
    },
    {
      "epoch": 0.24422442244224424,
      "grad_norm": 2.4695310592651367,
      "learning_rate": 0.0001565217391304348,
      "loss": 1.5221,
      "step": 37
    },
    {
      "epoch": 0.2508250825082508,
      "grad_norm": 3.572252035140991,
      "learning_rate": 0.00016086956521739132,
      "loss": 1.8853,
      "step": 38
    },
    {
      "epoch": 0.25742574257425743,
      "grad_norm": 5.93402624130249,
      "learning_rate": 0.00016521739130434784,
      "loss": 2.3075,
      "step": 39
    },
    {
      "epoch": 0.264026402640264,
      "grad_norm": 2.454044818878174,
      "learning_rate": 0.00016956521739130436,
      "loss": 1.5395,
      "step": 40
    },
    {
      "epoch": 0.2706270627062706,
      "grad_norm": 2.4715137481689453,
      "learning_rate": 0.00017391304347826088,
      "loss": 1.6654,
      "step": 41
    },
    {
      "epoch": 0.27722772277227725,
      "grad_norm": 2.5912485122680664,
      "learning_rate": 0.0001782608695652174,
      "loss": 2.3238,
      "step": 42
    },
    {
      "epoch": 0.2838283828382838,
      "grad_norm": 2.6347994804382324,
      "learning_rate": 0.00018260869565217392,
      "loss": 1.7519,
      "step": 43
    },
    {
      "epoch": 0.29042904290429045,
      "grad_norm": 2.668267011642456,
      "learning_rate": 0.00018695652173913045,
      "loss": 1.6689,
      "step": 44
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 3.038886308670044,
      "learning_rate": 0.00019130434782608697,
      "loss": 1.968,
      "step": 45
    },
    {
      "epoch": 0.30363036303630364,
      "grad_norm": 2.065838575363159,
      "learning_rate": 0.0001956521739130435,
      "loss": 1.8324,
      "step": 46
    },
    {
      "epoch": 0.3102310231023102,
      "grad_norm": 1.9431511163711548,
      "learning_rate": 0.0002,
      "loss": 1.5543,
      "step": 47
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 2.310769557952881,
      "learning_rate": 0.00019999702094326033,
      "loss": 1.4833,
      "step": 48
    },
    {
      "epoch": 0.3234323432343234,
      "grad_norm": 2.8865110874176025,
      "learning_rate": 0.00019998808395053688,
      "loss": 1.7368,
      "step": 49
    },
    {
      "epoch": 0.33003300330033003,
      "grad_norm": 2.3484208583831787,
      "learning_rate": 0.0001999731895543058,
      "loss": 1.4685,
      "step": 50
    },
    {
      "epoch": 0.33663366336633666,
      "grad_norm": 2.802156686782837,
      "learning_rate": 0.00019995233864199215,
      "loss": 1.7877,
      "step": 51
    },
    {
      "epoch": 0.3432343234323432,
      "grad_norm": 2.18292498588562,
      "learning_rate": 0.00019992553245591694,
      "loss": 1.5654,
      "step": 52
    },
    {
      "epoch": 0.34983498349834985,
      "grad_norm": 2.082122325897217,
      "learning_rate": 0.00019989277259322314,
      "loss": 1.8541,
      "step": 53
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 2.40657377243042,
      "learning_rate": 0.0001998540610057806,
      "loss": 1.9715,
      "step": 54
    },
    {
      "epoch": 0.36303630363036304,
      "grad_norm": 2.077791929244995,
      "learning_rate": 0.00019980940000006954,
      "loss": 1.5949,
      "step": 55
    },
    {
      "epoch": 0.3696369636963696,
      "grad_norm": 2.2711575031280518,
      "learning_rate": 0.0001997587922370434,
      "loss": 1.0556,
      "step": 56
    },
    {
      "epoch": 0.37623762376237624,
      "grad_norm": 1.9230396747589111,
      "learning_rate": 0.00019970224073197017,
      "loss": 1.8958,
      "step": 57
    },
    {
      "epoch": 0.38283828382838286,
      "grad_norm": 2.0223827362060547,
      "learning_rate": 0.00019963974885425266,
      "loss": 1.8731,
      "step": 58
    },
    {
      "epoch": 0.38943894389438943,
      "grad_norm": 3.312962293624878,
      "learning_rate": 0.00019957132032722785,
      "loss": 1.8496,
      "step": 59
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 3.0161566734313965,
      "learning_rate": 0.00019949695922794506,
      "loss": 1.8099,
      "step": 60
    },
    {
      "epoch": 0.40264026402640263,
      "grad_norm": 2.2380363941192627,
      "learning_rate": 0.00019941666998692296,
      "loss": 1.6939,
      "step": 61
    },
    {
      "epoch": 0.40924092409240925,
      "grad_norm": 2.783853530883789,
      "learning_rate": 0.00019933045738788563,
      "loss": 2.1385,
      "step": 62
    },
    {
      "epoch": 0.4158415841584158,
      "grad_norm": 2.4008877277374268,
      "learning_rate": 0.0001992383265674776,
      "loss": 1.6338,
      "step": 63
    },
    {
      "epoch": 0.42244224422442245,
      "grad_norm": 2.317880868911743,
      "learning_rate": 0.0001991402830149576,
      "loss": 1.6309,
      "step": 64
    },
    {
      "epoch": 0.429042904290429,
      "grad_norm": 2.7851943969726562,
      "learning_rate": 0.00019903633257187185,
      "loss": 1.9731,
      "step": 65
    },
    {
      "epoch": 0.43564356435643564,
      "grad_norm": 2.795436143875122,
      "learning_rate": 0.00019892648143170566,
      "loss": 1.7634,
      "step": 66
    },
    {
      "epoch": 0.44224422442244227,
      "grad_norm": 3.0923502445220947,
      "learning_rate": 0.0001988107361395146,
      "loss": 1.7409,
      "step": 67
    },
    {
      "epoch": 0.44884488448844884,
      "grad_norm": 2.286417245864868,
      "learning_rate": 0.0001986891035915346,
      "loss": 1.7104,
      "step": 68
    },
    {
      "epoch": 0.45544554455445546,
      "grad_norm": 2.321275234222412,
      "learning_rate": 0.00019856159103477086,
      "loss": 1.8864,
      "step": 69
    },
    {
      "epoch": 0.46204620462046203,
      "grad_norm": 1.9481537342071533,
      "learning_rate": 0.0001984282060665662,
      "loss": 1.7544,
      "step": 70
    },
    {
      "epoch": 0.46864686468646866,
      "grad_norm": 2.094721794128418,
      "learning_rate": 0.00019828895663414836,
      "loss": 1.2463,
      "step": 71
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 2.0305490493774414,
      "learning_rate": 0.00019814385103415663,
      "loss": 1.7909,
      "step": 72
    },
    {
      "epoch": 0.48184818481848185,
      "grad_norm": 2.0635201930999756,
      "learning_rate": 0.00019799289791214725,
      "loss": 1.5155,
      "step": 73
    },
    {
      "epoch": 0.4884488448844885,
      "grad_norm": 1.9585940837860107,
      "learning_rate": 0.00019783610626207854,
      "loss": 1.6954,
      "step": 74
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 2.560070514678955,
      "learning_rate": 0.00019767348542577495,
      "loss": 1.8156,
      "step": 75
    },
    {
      "epoch": 0.5016501650165016,
      "grad_norm": 2.5949947834014893,
      "learning_rate": 0.00019750504509237046,
      "loss": 2.0184,
      "step": 76
    },
    {
      "epoch": 0.5082508250825083,
      "grad_norm": 2.281064748764038,
      "learning_rate": 0.00019733079529773125,
      "loss": 1.6881,
      "step": 77
    },
    {
      "epoch": 0.5148514851485149,
      "grad_norm": 2.1914496421813965,
      "learning_rate": 0.00019715074642385786,
      "loss": 1.4654,
      "step": 78
    },
    {
      "epoch": 0.5214521452145214,
      "grad_norm": 2.1156349182128906,
      "learning_rate": 0.00019696490919826647,
      "loss": 1.7675,
      "step": 79
    },
    {
      "epoch": 0.528052805280528,
      "grad_norm": 2.097763776779175,
      "learning_rate": 0.0001967732946933499,
      "loss": 2.0482,
      "step": 80
    },
    {
      "epoch": 0.5346534653465347,
      "grad_norm": 2.4619557857513428,
      "learning_rate": 0.00019657591432571778,
      "loss": 1.8658,
      "step": 81
    },
    {
      "epoch": 0.5412541254125413,
      "grad_norm": 2.268629312515259,
      "learning_rate": 0.0001963727798555164,
      "loss": 1.9668,
      "step": 82
    },
    {
      "epoch": 0.5478547854785478,
      "grad_norm": 2.8534958362579346,
      "learning_rate": 0.00019616390338572803,
      "loss": 1.5379,
      "step": 83
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.972926139831543,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.3666,
      "step": 84
    },
    {
      "epoch": 0.5610561056105611,
      "grad_norm": 2.3708107471466064,
      "learning_rate": 0.00019572897456915202,
      "loss": 1.7144,
      "step": 85
    },
    {
      "epoch": 0.5676567656765676,
      "grad_norm": 2.909595489501953,
      "learning_rate": 0.00019550294813591682,
      "loss": 2.2708,
      "step": 86
    },
    {
      "epoch": 0.5742574257425742,
      "grad_norm": 1.8480359315872192,
      "learning_rate": 0.0001952712315286556,
      "loss": 1.3613,
      "step": 87
    },
    {
      "epoch": 0.5808580858085809,
      "grad_norm": 2.4477217197418213,
      "learning_rate": 0.00019503383855330668,
      "loss": 1.6463,
      "step": 88
    },
    {
      "epoch": 0.5874587458745875,
      "grad_norm": 2.253204345703125,
      "learning_rate": 0.00019479078335401297,
      "loss": 1.2088,
      "step": 89
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 1.9275654554367065,
      "learning_rate": 0.00019454208041227907,
      "loss": 1.5648,
      "step": 90
    },
    {
      "epoch": 0.6006600660066007,
      "grad_norm": 1.9389451742172241,
      "learning_rate": 0.00019428774454610843,
      "loss": 1.2708,
      "step": 91
    },
    {
      "epoch": 0.6072607260726073,
      "grad_norm": 1.9256659746170044,
      "learning_rate": 0.0001940277909091206,
      "loss": 1.5638,
      "step": 92
    },
    {
      "epoch": 0.6138613861386139,
      "grad_norm": 2.4642438888549805,
      "learning_rate": 0.0001937622349896483,
      "loss": 1.9737,
      "step": 93
    },
    {
      "epoch": 0.6204620462046204,
      "grad_norm": 2.4450933933258057,
      "learning_rate": 0.00019349109260981452,
      "loss": 2.407,
      "step": 94
    },
    {
      "epoch": 0.6270627062706271,
      "grad_norm": 2.6247427463531494,
      "learning_rate": 0.00019321437992458995,
      "loss": 2.0388,
      "step": 95
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 2.9768080711364746,
      "learning_rate": 0.0001929321134208304,
      "loss": 1.8954,
      "step": 96
    },
    {
      "epoch": 0.6402640264026402,
      "grad_norm": 2.293891191482544,
      "learning_rate": 0.00019264430991629446,
      "loss": 2.3185,
      "step": 97
    },
    {
      "epoch": 0.6468646864686468,
      "grad_norm": 2.011204242706299,
      "learning_rate": 0.00019235098655864157,
      "loss": 1.7781,
      "step": 98
    },
    {
      "epoch": 0.6534653465346535,
      "grad_norm": 1.914803147315979,
      "learning_rate": 0.00019205216082441017,
      "loss": 1.5633,
      "step": 99
    },
    {
      "epoch": 0.6600660066006601,
      "grad_norm": 2.229295015335083,
      "learning_rate": 0.00019174785051797666,
      "loss": 1.422,
      "step": 100
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.9156501293182373,
      "learning_rate": 0.0001914380737704944,
      "loss": 1.6114,
      "step": 101
    },
    {
      "epoch": 0.6732673267326733,
      "grad_norm": 2.1045665740966797,
      "learning_rate": 0.0001911228490388136,
      "loss": 1.9957,
      "step": 102
    },
    {
      "epoch": 0.6798679867986799,
      "grad_norm": 1.971551775932312,
      "learning_rate": 0.0001908021951043814,
      "loss": 1.3397,
      "step": 103
    },
    {
      "epoch": 0.6864686468646864,
      "grad_norm": 2.331234931945801,
      "learning_rate": 0.00019047613107212312,
      "loss": 1.453,
      "step": 104
    },
    {
      "epoch": 0.693069306930693,
      "grad_norm": 2.3500189781188965,
      "learning_rate": 0.00019014467636930385,
      "loss": 1.5166,
      "step": 105
    },
    {
      "epoch": 0.6996699669966997,
      "grad_norm": 3.211228609085083,
      "learning_rate": 0.00018980785074437093,
      "loss": 2.0583,
      "step": 106
    },
    {
      "epoch": 0.7062706270627063,
      "grad_norm": 2.552626371383667,
      "learning_rate": 0.00018946567426577723,
      "loss": 2.0275,
      "step": 107
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 2.142106294631958,
      "learning_rate": 0.00018911816732078575,
      "loss": 1.5193,
      "step": 108
    },
    {
      "epoch": 0.7194719471947195,
      "grad_norm": 2.5598621368408203,
      "learning_rate": 0.00018876535061425453,
      "loss": 1.7457,
      "step": 109
    },
    {
      "epoch": 0.7260726072607261,
      "grad_norm": 2.658561944961548,
      "learning_rate": 0.0001884072451674034,
      "loss": 1.5258,
      "step": 110
    },
    {
      "epoch": 0.7326732673267327,
      "grad_norm": 2.122279167175293,
      "learning_rate": 0.00018804387231656118,
      "loss": 1.6165,
      "step": 111
    },
    {
      "epoch": 0.7392739273927392,
      "grad_norm": 2.6554064750671387,
      "learning_rate": 0.00018767525371189475,
      "loss": 1.5194,
      "step": 112
    },
    {
      "epoch": 0.7458745874587459,
      "grad_norm": 2.4760324954986572,
      "learning_rate": 0.00018730141131611882,
      "loss": 1.8324,
      "step": 113
    },
    {
      "epoch": 0.7524752475247525,
      "grad_norm": 1.9205211400985718,
      "learning_rate": 0.0001869223674031876,
      "loss": 1.5462,
      "step": 114
    },
    {
      "epoch": 0.759075907590759,
      "grad_norm": 2.451927423477173,
      "learning_rate": 0.00018653814455696756,
      "loss": 1.9891,
      "step": 115
    },
    {
      "epoch": 0.7656765676567657,
      "grad_norm": 2.2201361656188965,
      "learning_rate": 0.0001861487656698919,
      "loss": 1.6986,
      "step": 116
    },
    {
      "epoch": 0.7722772277227723,
      "grad_norm": 3.1413655281066895,
      "learning_rate": 0.00018575425394159653,
      "loss": 2.0776,
      "step": 117
    },
    {
      "epoch": 0.7788778877887789,
      "grad_norm": 2.1141433715820312,
      "learning_rate": 0.00018535463287753796,
      "loss": 1.366,
      "step": 118
    },
    {
      "epoch": 0.7854785478547854,
      "grad_norm": 3.3970096111297607,
      "learning_rate": 0.00018494992628759267,
      "loss": 1.6139,
      "step": 119
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 2.305530548095703,
      "learning_rate": 0.0001845401582846385,
      "loss": 1.4516,
      "step": 120
    },
    {
      "epoch": 0.7986798679867987,
      "grad_norm": 2.0770864486694336,
      "learning_rate": 0.00018412535328311814,
      "loss": 1.7341,
      "step": 121
    },
    {
      "epoch": 0.8052805280528053,
      "grad_norm": 2.0777578353881836,
      "learning_rate": 0.00018370553599758422,
      "loss": 1.5696,
      "step": 122
    },
    {
      "epoch": 0.8118811881188119,
      "grad_norm": 2.021235704421997,
      "learning_rate": 0.00018328073144122708,
      "loss": 1.1397,
      "step": 123
    },
    {
      "epoch": 0.8184818481848185,
      "grad_norm": 2.1600515842437744,
      "learning_rate": 0.00018285096492438424,
      "loss": 1.5525,
      "step": 124
    },
    {
      "epoch": 0.8250825082508251,
      "grad_norm": 2.407317638397217,
      "learning_rate": 0.00018241626205303243,
      "loss": 2.1211,
      "step": 125
    },
    {
      "epoch": 0.8316831683168316,
      "grad_norm": 2.115229845046997,
      "learning_rate": 0.00018197664872726205,
      "loss": 1.4519,
      "step": 126
    },
    {
      "epoch": 0.8382838283828383,
      "grad_norm": 2.243795156478882,
      "learning_rate": 0.00018153215113973396,
      "loss": 1.609,
      "step": 127
    },
    {
      "epoch": 0.8448844884488449,
      "grad_norm": 2.622382164001465,
      "learning_rate": 0.0001810827957741188,
      "loss": 1.9359,
      "step": 128
    },
    {
      "epoch": 0.8514851485148515,
      "grad_norm": 2.31684947013855,
      "learning_rate": 0.00018062860940351916,
      "loss": 1.9789,
      "step": 129
    },
    {
      "epoch": 0.858085808580858,
      "grad_norm": 1.9168429374694824,
      "learning_rate": 0.00018016961908887442,
      "loss": 1.3984,
      "step": 130
    },
    {
      "epoch": 0.8646864686468647,
      "grad_norm": 2.2554709911346436,
      "learning_rate": 0.00017970585217734844,
      "loss": 1.127,
      "step": 131
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 2.3152496814727783,
      "learning_rate": 0.00017923733630070002,
      "loss": 1.922,
      "step": 132
    },
    {
      "epoch": 0.8778877887788779,
      "grad_norm": 2.9799273014068604,
      "learning_rate": 0.00017876409937363677,
      "loss": 1.6876,
      "step": 133
    },
    {
      "epoch": 0.8844884488448845,
      "grad_norm": 1.8281869888305664,
      "learning_rate": 0.00017828616959215184,
      "loss": 1.5791,
      "step": 134
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 1.8797411918640137,
      "learning_rate": 0.00017780357543184397,
      "loss": 1.4774,
      "step": 135
    },
    {
      "epoch": 0.8976897689768977,
      "grad_norm": 2.052123785018921,
      "learning_rate": 0.00017731634564622085,
      "loss": 1.883,
      "step": 136
    },
    {
      "epoch": 0.9042904290429042,
      "grad_norm": 2.0069074630737305,
      "learning_rate": 0.00017682450926498607,
      "loss": 1.4696,
      "step": 137
    },
    {
      "epoch": 0.9108910891089109,
      "grad_norm": 1.6514910459518433,
      "learning_rate": 0.0001763280955923093,
      "loss": 1.4254,
      "step": 138
    },
    {
      "epoch": 0.9174917491749175,
      "grad_norm": 2.6039862632751465,
      "learning_rate": 0.00017582713420508052,
      "loss": 2.1567,
      "step": 139
    },
    {
      "epoch": 0.9240924092409241,
      "grad_norm": 1.9613580703735352,
      "learning_rate": 0.00017532165495114766,
      "loss": 1.0636,
      "step": 140
    },
    {
      "epoch": 0.9306930693069307,
      "grad_norm": 3.350720167160034,
      "learning_rate": 0.0001748116879475383,
      "loss": 1.5513,
      "step": 141
    },
    {
      "epoch": 0.9372937293729373,
      "grad_norm": 2.287201404571533,
      "learning_rate": 0.00017429726357866515,
      "loss": 2.229,
      "step": 142
    },
    {
      "epoch": 0.9438943894389439,
      "grad_norm": 2.0688509941101074,
      "learning_rate": 0.00017377841249451595,
      "loss": 1.518,
      "step": 143
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 2.2164456844329834,
      "learning_rate": 0.00017325516560882703,
      "loss": 1.2676,
      "step": 144
    },
    {
      "epoch": 0.9570957095709571,
      "grad_norm": 1.946719765663147,
      "learning_rate": 0.00017272755409724168,
      "loss": 1.4389,
      "step": 145
    },
    {
      "epoch": 0.9636963696369637,
      "grad_norm": 2.1992857456207275,
      "learning_rate": 0.00017219560939545246,
      "loss": 1.5815,
      "step": 146
    },
    {
      "epoch": 0.9702970297029703,
      "grad_norm": 1.699536919593811,
      "learning_rate": 0.0001716593631973283,
      "loss": 1.1554,
      "step": 147
    },
    {
      "epoch": 0.976897689768977,
      "grad_norm": 2.061931610107422,
      "learning_rate": 0.00017111884745302632,
      "loss": 1.7294,
      "step": 148
    },
    {
      "epoch": 0.9834983498349835,
      "grad_norm": 1.7385263442993164,
      "learning_rate": 0.00017057409436708782,
      "loss": 1.2457,
      "step": 149
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 2.110952615737915,
      "learning_rate": 0.00017002513639651992,
      "loss": 1.3175,
      "step": 150
    },
    {
      "epoch": 0.9966996699669967,
      "grad_norm": 2.1564648151397705,
      "learning_rate": 0.00016947200624886145,
      "loss": 1.9294,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.933058977127075,
      "learning_rate": 0.00016891473688023426,
      "loss": 1.692,
      "step": 152
    }
  ],
  "logging_steps": 1,
  "max_steps": 453,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7929916510204808e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}