{
  "best_metric": 0.002712711924687028,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.032110459982339246,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016055229991169623,
      "grad_norm": 0.34254562854766846,
      "learning_rate": 1e-05,
      "loss": 0.1241,
      "step": 1
    },
    {
      "epoch": 0.00016055229991169623,
      "eval_loss": 0.1824212670326233,
      "eval_runtime": 204.9618,
      "eval_samples_per_second": 51.18,
      "eval_steps_per_second": 12.798,
      "step": 1
    },
    {
      "epoch": 0.00032110459982339246,
      "grad_norm": 0.42660006880760193,
      "learning_rate": 2e-05,
      "loss": 0.038,
      "step": 2
    },
    {
      "epoch": 0.0004816568997350887,
      "grad_norm": 0.4846949577331543,
      "learning_rate": 3e-05,
      "loss": 0.0349,
      "step": 3
    },
    {
      "epoch": 0.0006422091996467849,
      "grad_norm": 0.4394550621509552,
      "learning_rate": 4e-05,
      "loss": 0.0337,
      "step": 4
    },
    {
      "epoch": 0.0008027614995584812,
      "grad_norm": 0.28887495398521423,
      "learning_rate": 5e-05,
      "loss": 0.024,
      "step": 5
    },
    {
      "epoch": 0.0009633137994701774,
      "grad_norm": 0.27019938826560974,
      "learning_rate": 6e-05,
      "loss": 0.0186,
      "step": 6
    },
    {
      "epoch": 0.0011238660993818737,
      "grad_norm": 0.28722551465034485,
      "learning_rate": 7e-05,
      "loss": 0.0171,
      "step": 7
    },
    {
      "epoch": 0.0012844183992935698,
      "grad_norm": 0.22452913224697113,
      "learning_rate": 8e-05,
      "loss": 0.014,
      "step": 8
    },
    {
      "epoch": 0.001444970699205266,
      "grad_norm": 0.2193908989429474,
      "learning_rate": 9e-05,
      "loss": 0.0102,
      "step": 9
    },
    {
      "epoch": 0.0016055229991169624,
      "grad_norm": 0.25935325026512146,
      "learning_rate": 0.0001,
      "loss": 0.0067,
      "step": 10
    },
    {
      "epoch": 0.0017660752990286586,
      "grad_norm": 0.16416357457637787,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0039,
      "step": 11
    },
    {
      "epoch": 0.0019266275989403548,
      "grad_norm": 0.24492503702640533,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0043,
      "step": 12
    },
    {
      "epoch": 0.002087179898852051,
      "grad_norm": 0.23849591612815857,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.002,
      "step": 13
    },
    {
      "epoch": 0.0022477321987637473,
      "grad_norm": 0.3019893765449524,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0059,
      "step": 14
    },
    {
      "epoch": 0.0024082844986754435,
      "grad_norm": 0.2455286979675293,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0081,
      "step": 15
    },
    {
      "epoch": 0.0025688367985871397,
      "grad_norm": 0.25504615902900696,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0041,
      "step": 16
    },
    {
      "epoch": 0.002729389098498836,
      "grad_norm": 0.240357905626297,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0045,
      "step": 17
    },
    {
      "epoch": 0.002889941398410532,
      "grad_norm": 0.07552149891853333,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0017,
      "step": 18
    },
    {
      "epoch": 0.0030504936983222286,
      "grad_norm": 0.07320233434438705,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.001,
      "step": 19
    },
    {
      "epoch": 0.003211045998233925,
      "grad_norm": 0.0988754853606224,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0015,
      "step": 20
    },
    {
      "epoch": 0.003371598298145621,
      "grad_norm": 0.10945466160774231,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0015,
      "step": 21
    },
    {
      "epoch": 0.003532150598057317,
      "grad_norm": 0.19876258075237274,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0034,
      "step": 22
    },
    {
      "epoch": 0.0036927028979690133,
      "grad_norm": 0.0886337012052536,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0012,
      "step": 23
    },
    {
      "epoch": 0.0038532551978807095,
      "grad_norm": 0.07995320856571198,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0009,
      "step": 24
    },
    {
      "epoch": 0.004013807497792406,
      "grad_norm": 0.017459088936448097,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0004,
      "step": 25
    },
    {
      "epoch": 0.004174359797704102,
      "grad_norm": 0.040165968239307404,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0009,
      "step": 26
    },
    {
      "epoch": 0.004334912097615798,
      "grad_norm": 0.07218301296234131,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0008,
      "step": 27
    },
    {
      "epoch": 0.004495464397527495,
      "grad_norm": 0.06297245621681213,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0003,
      "step": 28
    },
    {
      "epoch": 0.00465601669743919,
      "grad_norm": 0.027354320511221886,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0004,
      "step": 29
    },
    {
      "epoch": 0.004816568997350887,
      "grad_norm": 0.12023824453353882,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0009,
      "step": 30
    },
    {
      "epoch": 0.004977121297262584,
      "grad_norm": 0.1296371966600418,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0005,
      "step": 31
    },
    {
      "epoch": 0.005137673597174279,
      "grad_norm": 0.0023872253950685263,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0001,
      "step": 32
    },
    {
      "epoch": 0.005298225897085976,
      "grad_norm": 0.06783653050661087,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.001,
      "step": 33
    },
    {
      "epoch": 0.005458778196997672,
      "grad_norm": 0.03708284720778465,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0002,
      "step": 34
    },
    {
      "epoch": 0.005619330496909368,
      "grad_norm": 0.029451260343194008,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0003,
      "step": 35
    },
    {
      "epoch": 0.005779882796821064,
      "grad_norm": 0.011983723379671574,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0001,
      "step": 36
    },
    {
      "epoch": 0.005940435096732761,
      "grad_norm": 0.0014479082310572267,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.006100987396644457,
      "grad_norm": 0.03672654926776886,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0002,
      "step": 38
    },
    {
      "epoch": 0.006261539696556153,
      "grad_norm": 0.26623207330703735,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.002,
      "step": 39
    },
    {
      "epoch": 0.00642209199646785,
      "grad_norm": 0.0038993009366095066,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0001,
      "step": 40
    },
    {
      "epoch": 0.006582644296379545,
      "grad_norm": 0.15298672020435333,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0008,
      "step": 41
    },
    {
      "epoch": 0.006743196596291242,
      "grad_norm": 0.16794940829277039,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0033,
      "step": 42
    },
    {
      "epoch": 0.006903748896202938,
      "grad_norm": 0.002918899292126298,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.007064301196114634,
      "grad_norm": 0.14760184288024902,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0052,
      "step": 44
    },
    {
      "epoch": 0.007224853496026331,
      "grad_norm": 0.15522640943527222,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0047,
      "step": 45
    },
    {
      "epoch": 0.007385405795938027,
      "grad_norm": 0.023171842098236084,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0002,
      "step": 46
    },
    {
      "epoch": 0.007545958095849723,
      "grad_norm": 0.20750221610069275,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0008,
      "step": 47
    },
    {
      "epoch": 0.007706510395761419,
      "grad_norm": 0.012230065651237965,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0002,
      "step": 48
    },
    {
      "epoch": 0.007867062695673116,
      "grad_norm": 0.13037025928497314,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0026,
      "step": 49
    },
    {
      "epoch": 0.008027614995584811,
      "grad_norm": 0.04344746097922325,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0003,
      "step": 50
    },
    {
      "epoch": 0.008027614995584811,
      "eval_loss": 0.005221195053309202,
      "eval_runtime": 204.6266,
      "eval_samples_per_second": 51.264,
      "eval_steps_per_second": 12.818,
      "step": 50
    },
    {
      "epoch": 0.008188167295496507,
      "grad_norm": 0.5250939130783081,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1255,
      "step": 51
    },
    {
      "epoch": 0.008348719595408205,
      "grad_norm": 0.057992178946733475,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0009,
      "step": 52
    },
    {
      "epoch": 0.0085092718953199,
      "grad_norm": 0.04958822950720787,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.0016,
      "step": 53
    },
    {
      "epoch": 0.008669824195231596,
      "grad_norm": 0.05028170347213745,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0008,
      "step": 54
    },
    {
      "epoch": 0.008830376495143294,
      "grad_norm": 0.09673178941011429,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0019,
      "step": 55
    },
    {
      "epoch": 0.00899092879505499,
      "grad_norm": 0.0684753954410553,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0083,
      "step": 56
    },
    {
      "epoch": 0.009151481094966685,
      "grad_norm": 0.08950470387935638,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0012,
      "step": 57
    },
    {
      "epoch": 0.00931203339487838,
      "grad_norm": 0.05458079278469086,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0013,
      "step": 58
    },
    {
      "epoch": 0.009472585694790078,
      "grad_norm": 0.079529769718647,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.001,
      "step": 59
    },
    {
      "epoch": 0.009633137994701774,
      "grad_norm": 0.03740987554192543,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0007,
      "step": 60
    },
    {
      "epoch": 0.00979369029461347,
      "grad_norm": 0.047025859355926514,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0016,
      "step": 61
    },
    {
      "epoch": 0.009954242594525167,
      "grad_norm": 0.03502329811453819,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0007,
      "step": 62
    },
    {
      "epoch": 0.010114794894436863,
      "grad_norm": 0.05259818583726883,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0009,
      "step": 63
    },
    {
      "epoch": 0.010275347194348559,
      "grad_norm": 0.013502693735063076,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0004,
      "step": 64
    },
    {
      "epoch": 0.010435899494260254,
      "grad_norm": 0.025728760287165642,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0011,
      "step": 65
    },
    {
      "epoch": 0.010596451794171952,
      "grad_norm": 0.02178327552974224,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0006,
      "step": 66
    },
    {
      "epoch": 0.010757004094083648,
      "grad_norm": 0.06834480166435242,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0004,
      "step": 67
    },
    {
      "epoch": 0.010917556393995343,
      "grad_norm": 0.051519911736249924,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0003,
      "step": 68
    },
    {
      "epoch": 0.011078108693907041,
      "grad_norm": 0.019947610795497894,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0003,
      "step": 69
    },
    {
      "epoch": 0.011238660993818737,
      "grad_norm": 0.02443559840321541,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0004,
      "step": 70
    },
    {
      "epoch": 0.011399213293730432,
      "grad_norm": 0.11091884970664978,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0006,
      "step": 71
    },
    {
      "epoch": 0.011559765593642128,
      "grad_norm": 0.005004688631743193,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0001,
      "step": 72
    },
    {
      "epoch": 0.011720317893553826,
      "grad_norm": 0.012527952902019024,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0002,
      "step": 73
    },
    {
      "epoch": 0.011880870193465521,
      "grad_norm": 0.020513156428933144,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0001,
      "step": 74
    },
    {
      "epoch": 0.012041422493377217,
      "grad_norm": 0.0047658514231443405,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0001,
      "step": 75
    },
    {
      "epoch": 0.012201974793288915,
      "grad_norm": 0.009428201243281364,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0001,
      "step": 76
    },
    {
      "epoch": 0.01236252709320061,
      "grad_norm": 0.06915072351694107,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0007,
      "step": 77
    },
    {
      "epoch": 0.012523079393112306,
      "grad_norm": 0.016525782644748688,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0002,
      "step": 78
    },
    {
      "epoch": 0.012683631693024002,
      "grad_norm": 0.05866200849413872,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0015,
      "step": 79
    },
    {
      "epoch": 0.0128441839929357,
      "grad_norm": 0.00698102219030261,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0001,
      "step": 80
    },
    {
      "epoch": 0.013004736292847395,
      "grad_norm": 0.01773742213845253,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0002,
      "step": 81
    },
    {
      "epoch": 0.01316528859275909,
      "grad_norm": 0.0217452272772789,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0001,
      "step": 82
    },
    {
      "epoch": 0.013325840892670788,
      "grad_norm": 0.04312044009566307,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.001,
      "step": 83
    },
    {
      "epoch": 0.013486393192582484,
      "grad_norm": 0.004618401639163494,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0001,
      "step": 84
    },
    {
      "epoch": 0.01364694549249418,
      "grad_norm": 0.08741449564695358,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0003,
      "step": 85
    },
    {
      "epoch": 0.013807497792405875,
      "grad_norm": 0.003669846337288618,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0001,
      "step": 86
    },
    {
      "epoch": 0.013968050092317573,
      "grad_norm": 0.004791214596480131,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0001,
      "step": 87
    },
    {
      "epoch": 0.014128602392229269,
      "grad_norm": 0.052703697234392166,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0002,
      "step": 88
    },
    {
      "epoch": 0.014289154692140964,
      "grad_norm": 0.002884466666728258,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.014449706992052662,
      "grad_norm": 0.0029359045438468456,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0001,
      "step": 90
    },
    {
      "epoch": 0.014610259291964358,
      "grad_norm": 0.03336722031235695,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0003,
      "step": 91
    },
    {
      "epoch": 0.014770811591876053,
      "grad_norm": 0.012027747929096222,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0002,
      "step": 92
    },
    {
      "epoch": 0.014931363891787749,
      "grad_norm": 0.11303514987230301,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0008,
      "step": 93
    },
    {
      "epoch": 0.015091916191699447,
      "grad_norm": 0.002124216640368104,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0001,
      "step": 94
    },
    {
      "epoch": 0.015252468491611142,
      "grad_norm": 0.2330835610628128,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0003,
      "step": 95
    },
    {
      "epoch": 0.015413020791522838,
      "grad_norm": 0.001057187793776393,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.015573573091434536,
      "grad_norm": 0.0015783881535753608,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.01573412539134623,
      "grad_norm": 0.3883363604545593,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0008,
      "step": 98
    },
    {
      "epoch": 0.01589467769125793,
      "grad_norm": 0.004075345583260059,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0001,
      "step": 99
    },
    {
      "epoch": 0.016055229991169623,
      "grad_norm": 0.24348968267440796,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0028,
      "step": 100
    },
    {
      "epoch": 0.016055229991169623,
      "eval_loss": 0.003659700509160757,
      "eval_runtime": 205.4097,
      "eval_samples_per_second": 51.069,
      "eval_steps_per_second": 12.77,
      "step": 100
    },
    {
      "epoch": 0.01621578229108132,
      "grad_norm": 0.4488672912120819,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.1201,
      "step": 101
    },
    {
      "epoch": 0.016376334590993014,
      "grad_norm": 0.051821641623973846,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0066,
      "step": 102
    },
    {
      "epoch": 0.016536886890904712,
      "grad_norm": 0.1808318942785263,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.0169,
      "step": 103
    },
    {
      "epoch": 0.01669743919081641,
      "grad_norm": 0.07604726403951645,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0012,
      "step": 104
    },
    {
      "epoch": 0.016857991490728103,
      "grad_norm": 0.037974897772073746,
      "learning_rate": 5e-05,
      "loss": 0.0007,
      "step": 105
    },
    {
      "epoch": 0.0170185437906398,
      "grad_norm": 0.036737799644470215,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0011,
      "step": 106
    },
    {
      "epoch": 0.017179096090551498,
      "grad_norm": 0.20633776485919952,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0015,
      "step": 107
    },
    {
      "epoch": 0.017339648390463192,
      "grad_norm": 0.13602225482463837,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0014,
      "step": 108
    },
    {
      "epoch": 0.01750020069037489,
      "grad_norm": 0.08005931973457336,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0003,
      "step": 109
    },
    {
      "epoch": 0.017660752990286587,
      "grad_norm": 0.013079303316771984,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0003,
      "step": 110
    },
    {
      "epoch": 0.01782130529019828,
      "grad_norm": 0.05216672644019127,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0003,
      "step": 111
    },
    {
      "epoch": 0.01798185759010998,
      "grad_norm": 0.020007742568850517,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0002,
      "step": 112
    },
    {
      "epoch": 0.018142409890021676,
      "grad_norm": 0.06017158180475235,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0004,
      "step": 113
    },
    {
      "epoch": 0.01830296218993337,
      "grad_norm": 0.005826754495501518,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0001,
      "step": 114
    },
    {
      "epoch": 0.018463514489845068,
      "grad_norm": 0.0067905946634709835,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0002,
      "step": 115
    },
    {
      "epoch": 0.01862406678975676,
      "grad_norm": 0.030933035537600517,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0003,
      "step": 116
    },
    {
      "epoch": 0.01878461908966846,
      "grad_norm": 0.03525209054350853,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0006,
      "step": 117
    },
    {
      "epoch": 0.018945171389580157,
      "grad_norm": 0.026839856058359146,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0003,
      "step": 118
    },
    {
      "epoch": 0.01910572368949185,
      "grad_norm": 0.08449611812829971,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0004,
      "step": 119
    },
    {
      "epoch": 0.019266275989403548,
      "grad_norm": 0.03313145786523819,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0005,
      "step": 120
    },
    {
      "epoch": 0.019426828289315246,
      "grad_norm": 0.004341837950050831,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0001,
      "step": 121
    },
    {
      "epoch": 0.01958738058922694,
      "grad_norm": 0.006267865654081106,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0001,
      "step": 122
    },
    {
      "epoch": 0.019747932889138637,
      "grad_norm": 0.03635149449110031,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0004,
      "step": 123
    },
    {
      "epoch": 0.019908485189050334,
      "grad_norm": 0.05964822694659233,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0009,
      "step": 124
    },
    {
      "epoch": 0.02006903748896203,
      "grad_norm": 0.013588122092187405,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0001,
      "step": 125
    },
    {
      "epoch": 0.020229589788873726,
      "grad_norm": 0.14869782328605652,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0012,
      "step": 126
    },
    {
      "epoch": 0.020390142088785423,
      "grad_norm": 0.013790048658847809,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0003,
      "step": 127
    },
    {
      "epoch": 0.020550694388697117,
      "grad_norm": 0.048435524106025696,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0002,
      "step": 128
    },
    {
      "epoch": 0.020711246688608815,
      "grad_norm": 0.0032732319086790085,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0001,
      "step": 129
    },
    {
      "epoch": 0.02087179898852051,
      "grad_norm": 0.31232473254203796,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0012,
      "step": 130
    },
    {
      "epoch": 0.021032351288432206,
      "grad_norm": 0.03147909790277481,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0001,
      "step": 131
    },
    {
      "epoch": 0.021192903588343904,
      "grad_norm": 0.04531725496053696,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0002,
      "step": 132
    },
    {
      "epoch": 0.021353455888255598,
      "grad_norm": 0.059192512184381485,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0019,
      "step": 133
    },
    {
      "epoch": 0.021514008188167295,
      "grad_norm": 0.03201492130756378,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0008,
      "step": 134
    },
    {
      "epoch": 0.021674560488078993,
      "grad_norm": 0.04632490873336792,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.001,
      "step": 135
    },
    {
      "epoch": 0.021835112787990687,
      "grad_norm": 0.0022632209584116936,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0001,
      "step": 136
    },
    {
      "epoch": 0.021995665087902384,
      "grad_norm": 0.016322540119290352,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0002,
      "step": 137
    },
    {
      "epoch": 0.022156217387814082,
      "grad_norm": 0.003340797033160925,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0001,
      "step": 138
    },
    {
      "epoch": 0.022316769687725776,
      "grad_norm": 0.0020371077116578817,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0001,
      "step": 139
    },
    {
      "epoch": 0.022477321987637473,
      "grad_norm": 0.00244193896651268,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0001,
      "step": 140
    },
    {
      "epoch": 0.02263787428754917,
      "grad_norm": 0.008312360383570194,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0002,
      "step": 141
    },
    {
      "epoch": 0.022798426587460865,
      "grad_norm": 0.004258233588188887,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0001,
      "step": 142
    },
    {
      "epoch": 0.022958978887372562,
      "grad_norm": 0.026912599802017212,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0005,
      "step": 143
    },
    {
      "epoch": 0.023119531187284256,
      "grad_norm": 0.004895417485386133,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0001,
      "step": 144
    },
    {
      "epoch": 0.023280083487195954,
      "grad_norm": 0.025680935010313988,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0005,
      "step": 145
    },
    {
      "epoch": 0.02344063578710765,
      "grad_norm": 0.006277390755712986,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0001,
      "step": 146
    },
    {
      "epoch": 0.023601188087019345,
      "grad_norm": 0.019905399531126022,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0004,
      "step": 147
    },
    {
      "epoch": 0.023761740386931043,
      "grad_norm": 0.14984191954135895,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.001,
      "step": 148
    },
    {
      "epoch": 0.02392229268684274,
      "grad_norm": 0.12252230942249298,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0025,
      "step": 149
    },
    {
      "epoch": 0.024082844986754434,
      "grad_norm": 0.012367417104542255,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0002,
      "step": 150
    },
    {
      "epoch": 0.024082844986754434,
      "eval_loss": 0.002838351298123598,
      "eval_runtime": 205.0655,
      "eval_samples_per_second": 51.154,
      "eval_steps_per_second": 12.791,
      "step": 150
    },
    {
      "epoch": 0.02424339728666613,
      "grad_norm": 0.18376561999320984,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0607,
      "step": 151
    },
    {
      "epoch": 0.02440394958657783,
      "grad_norm": 0.05683815851807594,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0021,
      "step": 152
    },
    {
      "epoch": 0.024564501886489523,
      "grad_norm": 0.0332530178129673,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0005,
      "step": 153
    },
    {
      "epoch": 0.02472505418640122,
      "grad_norm": 0.026484414935112,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0003,
      "step": 154
    },
    {
      "epoch": 0.024885606486312918,
      "grad_norm": 0.02836410142481327,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0003,
      "step": 155
    },
    {
      "epoch": 0.025046158786224612,
      "grad_norm": 0.06408917903900146,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0005,
      "step": 156
    },
    {
      "epoch": 0.02520671108613631,
      "grad_norm": 0.02819162979722023,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0003,
      "step": 157
    },
    {
      "epoch": 0.025367263386048004,
      "grad_norm": 0.01419798843562603,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0001,
      "step": 158
    },
    {
      "epoch": 0.0255278156859597,
      "grad_norm": 0.011141553521156311,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0002,
      "step": 159
    },
    {
      "epoch": 0.0256883679858714,
      "grad_norm": 0.01437454205006361,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0001,
      "step": 160
    },
    {
      "epoch": 0.025848920285783093,
      "grad_norm": 0.065122090280056,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0019,
      "step": 161
    },
    {
      "epoch": 0.02600947258569479,
      "grad_norm": 0.013126008212566376,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0002,
      "step": 162
    },
    {
      "epoch": 0.026170024885606488,
      "grad_norm": 0.03748351335525513,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0006,
      "step": 163
    },
    {
      "epoch": 0.02633057718551818,
      "grad_norm": 0.00522001925855875,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0001,
      "step": 164
    },
    {
      "epoch": 0.02649112948542988,
      "grad_norm": 0.02271348610520363,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0006,
      "step": 165
    },
    {
      "epoch": 0.026651681785341576,
      "grad_norm": 0.016994625329971313,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0002,
      "step": 166
    },
    {
      "epoch": 0.02681223408525327,
      "grad_norm": 0.013164960779249668,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0001,
      "step": 167
    },
    {
      "epoch": 0.026972786385164968,
      "grad_norm": 0.004088452085852623,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0001,
      "step": 168
    },
    {
      "epoch": 0.027133338685076665,
      "grad_norm": 0.010051297023892403,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0001,
      "step": 169
    },
    {
      "epoch": 0.02729389098498836,
      "grad_norm": 0.009310589171946049,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0001,
      "step": 170
    },
    {
      "epoch": 0.027454443284900057,
      "grad_norm": 0.1037910133600235,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0018,
      "step": 171
    },
    {
      "epoch": 0.02761499558481175,
      "grad_norm": 0.002720491262152791,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0001,
      "step": 172
    },
    {
      "epoch": 0.02777554788472345,
      "grad_norm": 0.0007583610713481903,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 0.027936100184635146,
      "grad_norm": 0.0028840333689004183,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0001,
      "step": 174
    },
    {
      "epoch": 0.02809665248454684,
      "grad_norm": 0.0013570865849032998,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.028257204784458537,
      "grad_norm": 0.009761103428900242,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0002,
      "step": 176
    },
    {
      "epoch": 0.028417757084370235,
      "grad_norm": 0.03534272313117981,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0003,
      "step": 177
    },
    {
      "epoch": 0.02857830938428193,
      "grad_norm": 0.006205355282872915,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0001,
      "step": 178
    },
    {
      "epoch": 0.028738861684193626,
      "grad_norm": 0.007518608123064041,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0001,
      "step": 179
    },
    {
      "epoch": 0.028899413984105324,
      "grad_norm": 0.01087932102382183,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0001,
      "step": 180
    },
    {
      "epoch": 0.029059966284017018,
      "grad_norm": 0.002336687408387661,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 0.029220518583928715,
      "grad_norm": 0.3905210793018341,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0044,
      "step": 182
    },
    {
      "epoch": 0.02938107088384041,
      "grad_norm": 0.004014439880847931,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0001,
      "step": 183
    },
    {
      "epoch": 0.029541623183752107,
      "grad_norm": 0.04322151467204094,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0005,
      "step": 184
    },
    {
      "epoch": 0.029702175483663804,
      "grad_norm": 0.07390669733285904,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0005,
      "step": 185
    },
    {
      "epoch": 0.029862727783575498,
      "grad_norm": 0.0057721808552742004,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0001,
      "step": 186
    },
    {
      "epoch": 0.030023280083487196,
      "grad_norm": 0.0016782922903075814,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0001,
      "step": 187
    },
    {
      "epoch": 0.030183832383398893,
      "grad_norm": 0.0015322546241804957,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0001,
      "step": 188
    },
    {
      "epoch": 0.030344384683310587,
      "grad_norm": 0.01077226735651493,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0002,
      "step": 189
    },
    {
      "epoch": 0.030504936983222285,
      "grad_norm": 0.018553949892520905,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0001,
      "step": 190
    },
    {
      "epoch": 0.030665489283133982,
      "grad_norm": 0.009536892175674438,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0002,
      "step": 191
    },
    {
      "epoch": 0.030826041583045676,
      "grad_norm": 0.051611512899398804,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0008,
      "step": 192
    },
    {
      "epoch": 0.030986593882957374,
      "grad_norm": 0.002245177049189806,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0001,
      "step": 193
    },
    {
      "epoch": 0.03114714618286907,
      "grad_norm": 0.002834404818713665,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0001,
      "step": 194
    },
    {
      "epoch": 0.03130769848278077,
      "grad_norm": 0.0024520843289792538,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0001,
      "step": 195
    },
    {
      "epoch": 0.03146825078269246,
      "grad_norm": 0.004727151710540056,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0001,
      "step": 196
    },
    {
      "epoch": 0.03162880308260416,
      "grad_norm": 0.008192081935703754,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0001,
      "step": 197
    },
    {
      "epoch": 0.03178935538251586,
      "grad_norm": 0.03561767563223839,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0003,
      "step": 198
    },
    {
      "epoch": 0.03194990768242755,
      "grad_norm": 0.004193940665572882,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0001,
      "step": 199
    },
    {
      "epoch": 0.032110459982339246,
      "grad_norm": 0.9020804762840271,
      "learning_rate": 0.0,
      "loss": 0.0043,
      "step": 200
    },
    {
      "epoch": 0.032110459982339246,
      "eval_loss": 0.002712711924687028,
      "eval_runtime": 205.0362,
      "eval_samples_per_second": 51.162,
      "eval_steps_per_second": 12.793,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7137909792505856e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}