{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.20221729490022172,
  "eval_steps": 38,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017738359201773836,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0017738359201773836,
      "eval_loss": NaN,
      "eval_runtime": 25.1879,
      "eval_samples_per_second": 9.449,
      "eval_steps_per_second": 4.724,
      "step": 1
    },
    {
      "epoch": 0.003547671840354767,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.005321507760532151,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.007095343680709534,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.010643015521064302,
      "grad_norm": NaN,
      "learning_rate": 0.00024,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.012416851441241685,
      "grad_norm": NaN,
      "learning_rate": 0.00028,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.014190687361419069,
      "grad_norm": NaN,
      "learning_rate": 0.00032,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.015964523281596452,
      "grad_norm": NaN,
      "learning_rate": 0.00036,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": NaN,
      "learning_rate": 0.0004,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.01951219512195122,
      "grad_norm": NaN,
      "learning_rate": 0.0003999496469885013,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.021286031042128603,
      "grad_norm": NaN,
      "learning_rate": 0.00039979861330826294,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.023059866962305987,
      "grad_norm": NaN,
      "learning_rate": 0.0003995469750092912,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.02483370288248337,
      "grad_norm": NaN,
      "learning_rate": 0.00039919485879904784,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": NaN,
      "learning_rate": 0.00039874244197864856,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.028381374722838137,
      "grad_norm": NaN,
      "learning_rate": 0.00039818995235358696,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.03015521064301552,
      "grad_norm": NaN,
      "learning_rate": 0.00039753766811902755,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.031929046563192905,
      "grad_norm": NaN,
      "learning_rate": 0.0003967859177197259,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.03370288248337029,
      "grad_norm": NaN,
      "learning_rate": 0.00039593507968464716,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": NaN,
      "learning_rate": 0.0003949855824363647,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03725055432372506,
      "grad_norm": NaN,
      "learning_rate": 0.0003939379040753374,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.03902439024390244,
      "grad_norm": NaN,
      "learning_rate": 0.00039279257213917066,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.040798226164079826,
      "grad_norm": NaN,
      "learning_rate": 0.0003915501633369861,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.042572062084257206,
      "grad_norm": NaN,
      "learning_rate": 0.00039021130325903074,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": NaN,
      "learning_rate": 0.00038877666606167355,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.04611973392461197,
      "grad_norm": NaN,
      "learning_rate": 0.00038724697412794747,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.04789356984478936,
      "grad_norm": NaN,
      "learning_rate": 0.0003856229977038078,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.04966740576496674,
      "grad_norm": NaN,
      "learning_rate": 0.0003839055545102902,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.05144124168514413,
      "grad_norm": NaN,
      "learning_rate": 0.00038209550933176323,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": NaN,
      "learning_rate": 0.0003801937735804838,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.054988913525498895,
      "grad_norm": NaN,
      "learning_rate": 0.0003782013048376736,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.056762749445676275,
      "grad_norm": NaN,
      "learning_rate": 0.0003761191063713476,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.05853658536585366,
      "grad_norm": NaN,
      "learning_rate": 0.0003739482266311391,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.06031042128603104,
      "grad_norm": NaN,
      "learning_rate": 0.00037168975872037323,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.06208425720620843,
      "grad_norm": NaN,
      "learning_rate": 0.00036934483984565685,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.06385809312638581,
      "grad_norm": NaN,
      "learning_rate": 0.00036691465074426054,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.06563192904656319,
      "grad_norm": NaN,
      "learning_rate": 0.00036440041508958203,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.06740576496674058,
      "grad_norm": NaN,
      "learning_rate": 0.0003618033988749895,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.06740576496674058,
      "eval_loss": NaN,
      "eval_runtime": 24.4996,
      "eval_samples_per_second": 9.714,
      "eval_steps_per_second": 4.857,
      "step": 38
    },
    {
      "epoch": 0.06917960088691796,
      "grad_norm": NaN,
      "learning_rate": 0.00035912490977635625,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": NaN,
      "learning_rate": 0.000356366296493606,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": NaN,
      "learning_rate": 0.0003535289480716022,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.07450110864745012,
      "grad_norm": NaN,
      "learning_rate": 0.00035061429320072223,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0762749445676275,
      "grad_norm": NaN,
      "learning_rate": 0.00034762379949746815,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": NaN,
      "learning_rate": 0.0003445589727654783,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.07982261640798226,
      "grad_norm": NaN,
      "learning_rate": 0.0003414213562373095,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.08159645232815965,
      "grad_norm": NaN,
      "learning_rate": 0.00033821252979737297,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.08337028824833703,
      "grad_norm": NaN,
      "learning_rate": 0.0003349341091864149,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.08514412416851441,
      "grad_norm": NaN,
      "learning_rate": 0.00033158774518794254,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.08691796008869179,
      "grad_norm": NaN,
      "learning_rate": 0.0003281751227970048,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": NaN,
      "learning_rate": 0.00032469796037174674,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.09046563192904657,
      "grad_norm": NaN,
      "learning_rate": 0.000321158008768164,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.09223946784922395,
      "grad_norm": NaN,
      "learning_rate": 0.00031755705045849464,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.09401330376940133,
      "grad_norm": NaN,
      "learning_rate": 0.0003138968986336904,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.09578713968957872,
      "grad_norm": NaN,
      "learning_rate": 0.0003101793962904205,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": NaN,
      "learning_rate": 0.00030640641530306733,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.09933481152993348,
      "grad_norm": NaN,
      "learning_rate": 0.00030257985548118126,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.10110864745011086,
      "grad_norm": NaN,
      "learning_rate": 0.0002987016436128694,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.10288248337028826,
      "grad_norm": NaN,
      "learning_rate": 0.0002947737324945997,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.10465631929046564,
      "grad_norm": NaN,
      "learning_rate": 0.00029079809994790937,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": NaN,
      "learning_rate": 0.00028677674782351165,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.1082039911308204,
      "grad_norm": NaN,
      "learning_rate": 0.00028271170099330415,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.10997782705099779,
      "grad_norm": NaN,
      "learning_rate": 0.00027860500633078477,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.11175166297117517,
      "grad_norm": NaN,
      "learning_rate": 0.00027445873168038907,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.11352549889135255,
      "grad_norm": NaN,
      "learning_rate": 0.0002702749648162686,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.11529933481152993,
      "grad_norm": NaN,
      "learning_rate": 0.00026605581239103347,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.11707317073170732,
      "grad_norm": NaN,
      "learning_rate": 0.00026180339887498953,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.1188470066518847,
      "grad_norm": NaN,
      "learning_rate": 0.00025751986548640346,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.12062084257206208,
      "grad_norm": NaN,
      "learning_rate": 0.00025320736911333503,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.12239467849223946,
      "grad_norm": NaN,
      "learning_rate": 0.0002488680812275788,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.12416851441241686,
      "grad_norm": NaN,
      "learning_rate": 0.0002445041867912629,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.12594235033259424,
      "grad_norm": NaN,
      "learning_rate": 0.00024011788315665458,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.12771618625277162,
      "grad_norm": NaN,
      "learning_rate": 0.00023571137895972733,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.129490022172949,
      "grad_norm": NaN,
      "learning_rate": 0.0002312868930080462,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.13126385809312638,
      "grad_norm": NaN,
      "learning_rate": 0.0002268466531635311,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": NaN,
      "learning_rate": 0.00022239289522066157,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.13481152993348117,
      "grad_norm": NaN,
      "learning_rate": 0.00021792786178068672,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.13481152993348117,
      "eval_loss": NaN,
      "eval_runtime": 24.6587,
      "eval_samples_per_second": 9.652,
      "eval_steps_per_second": 4.826,
      "step": 76
    },
    {
      "epoch": 0.13658536585365855,
      "grad_norm": NaN,
      "learning_rate": 0.00021345380112240797,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.13835920177383593,
      "grad_norm": NaN,
      "learning_rate": 0.00020897296607010301,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.1401330376940133,
      "grad_norm": NaN,
      "learning_rate": 0.00020448761285916104,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.14368070953436807,
      "grad_norm": NaN,
      "learning_rate": 0.00019551238714083903,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": NaN,
      "learning_rate": 0.00019102703392989709,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.14722838137472283,
      "grad_norm": NaN,
      "learning_rate": 0.00018654619887759207,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.14900221729490024,
      "grad_norm": NaN,
      "learning_rate": 0.00018207213821931333,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.15077605321507762,
      "grad_norm": NaN,
      "learning_rate": 0.00017760710477933845,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.152549889135255,
      "grad_norm": NaN,
      "learning_rate": 0.00017315334683646897,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.15432372505543238,
      "grad_norm": NaN,
      "learning_rate": 0.00016871310699195379,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.15609756097560976,
      "grad_norm": NaN,
      "learning_rate": 0.00016428862104027268,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.15787139689578714,
      "grad_norm": NaN,
      "learning_rate": 0.00015988211684334546,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.15964523281596452,
      "grad_norm": NaN,
      "learning_rate": 0.00015549581320873715,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.1614190687361419,
      "grad_norm": NaN,
      "learning_rate": 0.00015113191877242117,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.1631929046563193,
      "grad_norm": NaN,
      "learning_rate": 0.00014679263088666499,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.16496674057649668,
      "grad_norm": NaN,
      "learning_rate": 0.00014248013451359656,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.16674057649667406,
      "grad_norm": NaN,
      "learning_rate": 0.00013819660112501054,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.16851441241685144,
      "grad_norm": NaN,
      "learning_rate": 0.00013394418760896666,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.17028824833702882,
      "grad_norm": NaN,
      "learning_rate": 0.00012972503518373144,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.1720620842572062,
      "grad_norm": NaN,
      "learning_rate": 0.00012554126831961098,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.17383592017738358,
      "grad_norm": NaN,
      "learning_rate": 0.0001213949936692153,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.17560975609756097,
      "grad_norm": NaN,
      "learning_rate": 0.00011728829900669591,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": NaN,
      "learning_rate": 0.00011322325217648839,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.17915742793791575,
      "grad_norm": NaN,
      "learning_rate": 0.00010920190005209065,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.18093126385809313,
      "grad_norm": NaN,
      "learning_rate": 0.00010522626750540028,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.1827050997782705,
      "grad_norm": NaN,
      "learning_rate": 0.00010129835638713063,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.1844789356984479,
      "grad_norm": NaN,
      "learning_rate": 9.74201445188188e-05,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.18625277161862527,
      "grad_norm": NaN,
      "learning_rate": 9.359358469693271e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.18802660753880265,
      "grad_norm": NaN,
      "learning_rate": 8.982060370957952e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.18980044345898003,
      "grad_norm": NaN,
      "learning_rate": 8.610310136630962e-05,
      "loss": 0.0,
      "step": 107
    },
    {
      "epoch": 0.19157427937915744,
      "grad_norm": NaN,
      "learning_rate": 8.24429495415054e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.19334811529933482,
      "grad_norm": NaN,
      "learning_rate": 7.884199123183605e-05,
      "loss": 0.0,
      "step": 109
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": NaN,
      "learning_rate": 7.530203962825331e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.19689578713968958,
      "grad_norm": NaN,
      "learning_rate": 7.182487720299517e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.19866962305986696,
      "grad_norm": NaN,
      "learning_rate": 6.841225481205749e-05,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.20044345898004434,
      "grad_norm": NaN,
      "learning_rate": 6.506589081358514e-05,
      "loss": 0.0,
      "step": 113
    },
    {
      "epoch": 0.20221729490022172,
      "grad_norm": NaN,
      "learning_rate": 6.178747020262707e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.20221729490022172,
      "eval_loss": NaN,
      "eval_runtime": 24.5749,
      "eval_samples_per_second": 9.685,
      "eval_steps_per_second": 4.842,
      "step": 114
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 38,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3722866184945664.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}