{
  "best_metric": 1.611555576324463,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.1157601115760112,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005578800557880056,
      "grad_norm": 2.966805934906006,
      "learning_rate": 1e-05,
      "loss": 2.5854,
      "step": 1
    },
    {
      "epoch": 0.005578800557880056,
      "eval_loss": 2.741358995437622,
      "eval_runtime": 22.4649,
      "eval_samples_per_second": 13.443,
      "eval_steps_per_second": 3.383,
      "step": 1
    },
    {
      "epoch": 0.011157601115760111,
      "grad_norm": 3.3987326622009277,
      "learning_rate": 2e-05,
      "loss": 2.8058,
      "step": 2
    },
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 3.6081910133361816,
      "learning_rate": 3e-05,
      "loss": 2.8494,
      "step": 3
    },
    {
      "epoch": 0.022315202231520222,
      "grad_norm": 3.6429989337921143,
      "learning_rate": 4e-05,
      "loss": 2.7597,
      "step": 4
    },
    {
      "epoch": 0.02789400278940028,
      "grad_norm": 2.909208297729492,
      "learning_rate": 5e-05,
      "loss": 2.4574,
      "step": 5
    },
    {
      "epoch": 0.03347280334728033,
      "grad_norm": 2.752185821533203,
      "learning_rate": 6e-05,
      "loss": 2.3386,
      "step": 6
    },
    {
      "epoch": 0.03905160390516039,
      "grad_norm": 2.412426710128784,
      "learning_rate": 7e-05,
      "loss": 2.1717,
      "step": 7
    },
    {
      "epoch": 0.044630404463040445,
      "grad_norm": 2.173205614089966,
      "learning_rate": 8e-05,
      "loss": 1.9859,
      "step": 8
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 2.274272918701172,
      "learning_rate": 9e-05,
      "loss": 2.3254,
      "step": 9
    },
    {
      "epoch": 0.05578800557880056,
      "grad_norm": 2.395301342010498,
      "learning_rate": 0.0001,
      "loss": 1.9677,
      "step": 10
    },
    {
      "epoch": 0.061366806136680614,
      "grad_norm": 1.988542079925537,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.9547,
      "step": 11
    },
    {
      "epoch": 0.06694560669456066,
      "grad_norm": 1.7886563539505005,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.7497,
      "step": 12
    },
    {
      "epoch": 0.07252440725244072,
      "grad_norm": 1.7258999347686768,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.8906,
      "step": 13
    },
    {
      "epoch": 0.07810320781032078,
      "grad_norm": 1.7313402891159058,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.8581,
      "step": 14
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 2.0345823764801025,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8973,
      "step": 15
    },
    {
      "epoch": 0.08926080892608089,
      "grad_norm": 1.744252324104309,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.8276,
      "step": 16
    },
    {
      "epoch": 0.09483960948396095,
      "grad_norm": 1.3860772848129272,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.7135,
      "step": 17
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 1.545911192893982,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.563,
      "step": 18
    },
    {
      "epoch": 0.10599721059972106,
      "grad_norm": 1.3314751386642456,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.661,
      "step": 19
    },
    {
      "epoch": 0.11157601115760112,
      "grad_norm": 1.2656646966934204,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.8469,
      "step": 20
    },
    {
      "epoch": 0.11715481171548117,
      "grad_norm": 1.3089263439178467,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.8112,
      "step": 21
    },
    {
      "epoch": 0.12273361227336123,
      "grad_norm": 1.299146294593811,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.6773,
      "step": 22
    },
    {
      "epoch": 0.12831241283124128,
      "grad_norm": 1.3633729219436646,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.8067,
      "step": 23
    },
    {
      "epoch": 0.13389121338912133,
      "grad_norm": 1.1915013790130615,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5539,
      "step": 24
    },
    {
      "epoch": 0.1394700139470014,
      "grad_norm": 1.300031065940857,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.6003,
      "step": 25
    },
    {
      "epoch": 0.14504881450488144,
      "grad_norm": 1.3049120903015137,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.6206,
      "step": 26
    },
    {
      "epoch": 0.1506276150627615,
      "grad_norm": 1.2079498767852783,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.5755,
      "step": 27
    },
    {
      "epoch": 0.15620641562064155,
      "grad_norm": 1.288231372833252,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.68,
      "step": 28
    },
    {
      "epoch": 0.16178521617852162,
      "grad_norm": 1.1846801042556763,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6964,
      "step": 29
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 1.2441076040267944,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.6989,
      "step": 30
    },
    {
      "epoch": 0.17294281729428174,
      "grad_norm": 1.304139494895935,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.7431,
      "step": 31
    },
    {
      "epoch": 0.17852161785216178,
      "grad_norm": 1.2678860425949097,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.6698,
      "step": 32
    },
    {
      "epoch": 0.18410041841004185,
      "grad_norm": 1.229800820350647,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6205,
      "step": 33
    },
    {
      "epoch": 0.1896792189679219,
      "grad_norm": 1.1903066635131836,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.5573,
      "step": 34
    },
    {
      "epoch": 0.19525801952580196,
      "grad_norm": 1.0925021171569824,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.6322,
      "step": 35
    },
    {
      "epoch": 0.200836820083682,
      "grad_norm": 1.2811715602874756,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.4011,
      "step": 36
    },
    {
      "epoch": 0.20641562064156208,
      "grad_norm": 1.1105221509933472,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.4863,
      "step": 37
    },
    {
      "epoch": 0.21199442119944212,
      "grad_norm": 1.1272368431091309,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.5054,
      "step": 38
    },
    {
      "epoch": 0.2175732217573222,
      "grad_norm": 1.250308871269226,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.6937,
      "step": 39
    },
    {
      "epoch": 0.22315202231520223,
      "grad_norm": 1.3089959621429443,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.5025,
      "step": 40
    },
    {
      "epoch": 0.22873082287308227,
      "grad_norm": 1.125614047050476,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.6036,
      "step": 41
    },
    {
      "epoch": 0.23430962343096234,
      "grad_norm": 1.1081316471099854,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.6,
      "step": 42
    },
    {
      "epoch": 0.2398884239888424,
      "grad_norm": 1.1351003646850586,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.6831,
      "step": 43
    },
    {
      "epoch": 0.24546722454672246,
      "grad_norm": 1.1099660396575928,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.6041,
      "step": 44
    },
    {
      "epoch": 0.2510460251046025,
      "grad_norm": 1.0794075727462769,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.6038,
      "step": 45
    },
    {
      "epoch": 0.25662482566248257,
      "grad_norm": 1.2801789045333862,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.7086,
      "step": 46
    },
    {
      "epoch": 0.26220362622036264,
      "grad_norm": 1.0775105953216553,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.6838,
      "step": 47
    },
    {
      "epoch": 0.26778242677824265,
      "grad_norm": 0.9799520969390869,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6437,
      "step": 48
    },
    {
      "epoch": 0.2733612273361227,
      "grad_norm": 1.1786924600601196,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.9282,
      "step": 49
    },
    {
      "epoch": 0.2789400278940028,
      "grad_norm": 1.202183723449707,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6262,
      "step": 50
    },
    {
      "epoch": 0.2789400278940028,
      "eval_loss": 1.6858829259872437,
      "eval_runtime": 23.0411,
      "eval_samples_per_second": 13.107,
      "eval_steps_per_second": 3.298,
      "step": 50
    },
    {
      "epoch": 0.28451882845188287,
      "grad_norm": 1.2558609247207642,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.7883,
      "step": 51
    },
    {
      "epoch": 0.2900976290097629,
      "grad_norm": 1.136972427368164,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6247,
      "step": 52
    },
    {
      "epoch": 0.29567642956764295,
      "grad_norm": 1.3769677877426147,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.9171,
      "step": 53
    },
    {
      "epoch": 0.301255230125523,
      "grad_norm": 1.06509268283844,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.7252,
      "step": 54
    },
    {
      "epoch": 0.3068340306834031,
      "grad_norm": 1.1531444787979126,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.5919,
      "step": 55
    },
    {
      "epoch": 0.3124128312412831,
      "grad_norm": 0.9904036521911621,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.5322,
      "step": 56
    },
    {
      "epoch": 0.3179916317991632,
      "grad_norm": 1.1017944812774658,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.8162,
      "step": 57
    },
    {
      "epoch": 0.32357043235704325,
      "grad_norm": 1.034432053565979,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.6096,
      "step": 58
    },
    {
      "epoch": 0.3291492329149233,
      "grad_norm": 1.016183614730835,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.7504,
      "step": 59
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 0.9915763735771179,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.714,
      "step": 60
    },
    {
      "epoch": 0.3403068340306834,
      "grad_norm": 0.9881419539451599,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.7185,
      "step": 61
    },
    {
      "epoch": 0.3458856345885635,
      "grad_norm": 0.9900838732719421,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.619,
      "step": 62
    },
    {
      "epoch": 0.3514644351464435,
      "grad_norm": 1.0031565427780151,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.658,
      "step": 63
    },
    {
      "epoch": 0.35704323570432356,
      "grad_norm": 1.0874994993209839,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.5418,
      "step": 64
    },
    {
      "epoch": 0.36262203626220363,
      "grad_norm": 1.091450572013855,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6039,
      "step": 65
    },
    {
      "epoch": 0.3682008368200837,
      "grad_norm": 1.2521109580993652,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.8303,
      "step": 66
    },
    {
      "epoch": 0.3737796373779637,
      "grad_norm": 1.0139495134353638,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5572,
      "step": 67
    },
    {
      "epoch": 0.3793584379358438,
      "grad_norm": 1.085192322731018,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.7545,
      "step": 68
    },
    {
      "epoch": 0.38493723849372385,
      "grad_norm": 1.0518659353256226,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.7922,
      "step": 69
    },
    {
      "epoch": 0.3905160390516039,
      "grad_norm": 1.12924325466156,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.4691,
      "step": 70
    },
    {
      "epoch": 0.39609483960948394,
      "grad_norm": 1.004798173904419,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.6677,
      "step": 71
    },
    {
      "epoch": 0.401673640167364,
      "grad_norm": 0.954420804977417,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.516,
      "step": 72
    },
    {
      "epoch": 0.4072524407252441,
      "grad_norm": 0.9690553545951843,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.4321,
      "step": 73
    },
    {
      "epoch": 0.41283124128312415,
      "grad_norm": 1.0762101411819458,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.7176,
      "step": 74
    },
    {
      "epoch": 0.41841004184100417,
      "grad_norm": 0.9834462404251099,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.6004,
      "step": 75
    },
    {
      "epoch": 0.42398884239888424,
      "grad_norm": 1.1130197048187256,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.6683,
      "step": 76
    },
    {
      "epoch": 0.4295676429567643,
      "grad_norm": 1.0482343435287476,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.739,
      "step": 77
    },
    {
      "epoch": 0.4351464435146444,
      "grad_norm": 1.0657097101211548,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.6009,
      "step": 78
    },
    {
      "epoch": 0.4407252440725244,
      "grad_norm": 1.013319730758667,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.6676,
      "step": 79
    },
    {
      "epoch": 0.44630404463040446,
      "grad_norm": 1.0699585676193237,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.6304,
      "step": 80
    },
    {
      "epoch": 0.45188284518828453,
      "grad_norm": 1.0741909742355347,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.6651,
      "step": 81
    },
    {
      "epoch": 0.45746164574616455,
      "grad_norm": 0.9900343418121338,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.4684,
      "step": 82
    },
    {
      "epoch": 0.4630404463040446,
      "grad_norm": 1.0609464645385742,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.6345,
      "step": 83
    },
    {
      "epoch": 0.4686192468619247,
      "grad_norm": 1.0852028131484985,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.4742,
      "step": 84
    },
    {
      "epoch": 0.47419804741980476,
      "grad_norm": 0.992335319519043,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.5491,
      "step": 85
    },
    {
      "epoch": 0.4797768479776848,
      "grad_norm": 0.9619942307472229,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6424,
      "step": 86
    },
    {
      "epoch": 0.48535564853556484,
      "grad_norm": 0.9760165214538574,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.5581,
      "step": 87
    },
    {
      "epoch": 0.4909344490934449,
      "grad_norm": 1.166187047958374,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.6101,
      "step": 88
    },
    {
      "epoch": 0.496513249651325,
      "grad_norm": 1.1727315187454224,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.8536,
      "step": 89
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 1.039559006690979,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.7131,
      "step": 90
    },
    {
      "epoch": 0.5076708507670851,
      "grad_norm": 1.0231174230575562,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.7271,
      "step": 91
    },
    {
      "epoch": 0.5132496513249651,
      "grad_norm": 0.9673395156860352,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.69,
      "step": 92
    },
    {
      "epoch": 0.5188284518828452,
      "grad_norm": 0.9296785593032837,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.706,
      "step": 93
    },
    {
      "epoch": 0.5244072524407253,
      "grad_norm": 1.080651044845581,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.82,
      "step": 94
    },
    {
      "epoch": 0.5299860529986054,
      "grad_norm": 0.9666087031364441,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.4643,
      "step": 95
    },
    {
      "epoch": 0.5355648535564853,
      "grad_norm": 0.9948273301124573,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.6678,
      "step": 96
    },
    {
      "epoch": 0.5411436541143654,
      "grad_norm": 0.9770331382751465,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.5509,
      "step": 97
    },
    {
      "epoch": 0.5467224546722455,
      "grad_norm": 1.0189894437789917,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.6567,
      "step": 98
    },
    {
      "epoch": 0.5523012552301255,
      "grad_norm": 0.994407594203949,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.6409,
      "step": 99
    },
    {
      "epoch": 0.5578800557880056,
      "grad_norm": 1.0866799354553223,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.7636,
      "step": 100
    },
    {
      "epoch": 0.5578800557880056,
      "eval_loss": 1.6399977207183838,
      "eval_runtime": 23.034,
      "eval_samples_per_second": 13.111,
      "eval_steps_per_second": 3.299,
      "step": 100
    },
    {
      "epoch": 0.5634588563458857,
      "grad_norm": 0.9668028950691223,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.5544,
      "step": 101
    },
    {
      "epoch": 0.5690376569037657,
      "grad_norm": 1.0146700143814087,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.7135,
      "step": 102
    },
    {
      "epoch": 0.5746164574616457,
      "grad_norm": 1.009660005569458,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.5242,
      "step": 103
    },
    {
      "epoch": 0.5801952580195258,
      "grad_norm": 1.0184736251831055,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.5692,
      "step": 104
    },
    {
      "epoch": 0.5857740585774058,
      "grad_norm": 1.106948971748352,
      "learning_rate": 5e-05,
      "loss": 1.8379,
      "step": 105
    },
    {
      "epoch": 0.5913528591352859,
      "grad_norm": 0.9053370952606201,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.494,
      "step": 106
    },
    {
      "epoch": 0.596931659693166,
      "grad_norm": 1.0391387939453125,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.6779,
      "step": 107
    },
    {
      "epoch": 0.602510460251046,
      "grad_norm": 0.8675243854522705,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.4472,
      "step": 108
    },
    {
      "epoch": 0.6080892608089261,
      "grad_norm": 0.917523205280304,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.4355,
      "step": 109
    },
    {
      "epoch": 0.6136680613668062,
      "grad_norm": 0.9918159246444702,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.6688,
      "step": 110
    },
    {
      "epoch": 0.6192468619246861,
      "grad_norm": 1.0398961305618286,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.7465,
      "step": 111
    },
    {
      "epoch": 0.6248256624825662,
      "grad_norm": 0.9308964014053345,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.5851,
      "step": 112
    },
    {
      "epoch": 0.6304044630404463,
      "grad_norm": 0.9687375426292419,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.605,
      "step": 113
    },
    {
      "epoch": 0.6359832635983264,
      "grad_norm": 1.013521671295166,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.677,
      "step": 114
    },
    {
      "epoch": 0.6415620641562064,
      "grad_norm": 0.9416386485099792,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.6205,
      "step": 115
    },
    {
      "epoch": 0.6471408647140865,
      "grad_norm": 0.9632589817047119,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.5114,
      "step": 116
    },
    {
      "epoch": 0.6527196652719666,
      "grad_norm": 0.8996039032936096,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.4634,
      "step": 117
    },
    {
      "epoch": 0.6582984658298466,
      "grad_norm": 0.9823569059371948,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.6001,
      "step": 118
    },
    {
      "epoch": 0.6638772663877266,
      "grad_norm": 1.0398359298706055,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.7351,
      "step": 119
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 0.9760072231292725,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.5461,
      "step": 120
    },
    {
      "epoch": 0.6750348675034867,
      "grad_norm": 0.9968307018280029,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.7004,
      "step": 121
    },
    {
      "epoch": 0.6806136680613668,
      "grad_norm": 0.9351212382316589,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.504,
      "step": 122
    },
    {
      "epoch": 0.6861924686192469,
      "grad_norm": 0.954623281955719,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.4843,
      "step": 123
    },
    {
      "epoch": 0.691771269177127,
      "grad_norm": 0.9165086150169373,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.5494,
      "step": 124
    },
    {
      "epoch": 0.697350069735007,
      "grad_norm": 0.9458172917366028,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.6943,
      "step": 125
    },
    {
      "epoch": 0.702928870292887,
      "grad_norm": 1.0187864303588867,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.7351,
      "step": 126
    },
    {
      "epoch": 0.708507670850767,
      "grad_norm": 0.8965396285057068,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.4074,
      "step": 127
    },
    {
      "epoch": 0.7140864714086471,
      "grad_norm": 0.9610390663146973,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.5003,
      "step": 128
    },
    {
      "epoch": 0.7196652719665272,
      "grad_norm": 0.9834814667701721,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.4772,
      "step": 129
    },
    {
      "epoch": 0.7252440725244073,
      "grad_norm": 1.0246707201004028,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.6656,
      "step": 130
    },
    {
      "epoch": 0.7308228730822873,
      "grad_norm": 0.8998227715492249,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.3956,
      "step": 131
    },
    {
      "epoch": 0.7364016736401674,
      "grad_norm": 1.0139575004577637,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.5505,
      "step": 132
    },
    {
      "epoch": 0.7419804741980475,
      "grad_norm": 0.9793893098831177,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.7354,
      "step": 133
    },
    {
      "epoch": 0.7475592747559274,
      "grad_norm": 0.9209136366844177,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.665,
      "step": 134
    },
    {
      "epoch": 0.7531380753138075,
      "grad_norm": 0.9432255625724792,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.6201,
      "step": 135
    },
    {
      "epoch": 0.7587168758716876,
      "grad_norm": 1.004547119140625,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.6876,
      "step": 136
    },
    {
      "epoch": 0.7642956764295676,
      "grad_norm": 0.9797149300575256,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.6379,
      "step": 137
    },
    {
      "epoch": 0.7698744769874477,
      "grad_norm": 1.0021864175796509,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.7543,
      "step": 138
    },
    {
      "epoch": 0.7754532775453278,
      "grad_norm": 1.1218937635421753,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.6062,
      "step": 139
    },
    {
      "epoch": 0.7810320781032078,
      "grad_norm": 0.8813673853874207,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.585,
      "step": 140
    },
    {
      "epoch": 0.7866108786610879,
      "grad_norm": 0.9762659668922424,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.6465,
      "step": 141
    },
    {
      "epoch": 0.7921896792189679,
      "grad_norm": 1.056488275527954,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.7965,
      "step": 142
    },
    {
      "epoch": 0.797768479776848,
      "grad_norm": 0.9237454533576965,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.626,
      "step": 143
    },
    {
      "epoch": 0.803347280334728,
      "grad_norm": 0.8857014775276184,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.5274,
      "step": 144
    },
    {
      "epoch": 0.8089260808926081,
      "grad_norm": 0.9819214940071106,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.5805,
      "step": 145
    },
    {
      "epoch": 0.8145048814504882,
      "grad_norm": 0.9236671924591064,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.7002,
      "step": 146
    },
    {
      "epoch": 0.8200836820083682,
      "grad_norm": 1.0043861865997314,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.7132,
      "step": 147
    },
    {
      "epoch": 0.8256624825662483,
      "grad_norm": 0.927191972732544,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.595,
      "step": 148
    },
    {
      "epoch": 0.8312412831241283,
      "grad_norm": 1.122625708580017,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.818,
      "step": 149
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 0.9391010999679565,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.6835,
      "step": 150
    },
    {
      "epoch": 0.8368200836820083,
      "eval_loss": 1.6216932535171509,
      "eval_runtime": 22.9523,
      "eval_samples_per_second": 13.158,
      "eval_steps_per_second": 3.311,
      "step": 150
    },
    {
      "epoch": 0.8423988842398884,
      "grad_norm": 1.0147435665130615,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.6633,
      "step": 151
    },
    {
      "epoch": 0.8479776847977685,
      "grad_norm": 0.9340530633926392,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.6161,
      "step": 152
    },
    {
      "epoch": 0.8535564853556485,
      "grad_norm": 1.067122220993042,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.6381,
      "step": 153
    },
    {
      "epoch": 0.8591352859135286,
      "grad_norm": 0.8708997368812561,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.5338,
      "step": 154
    },
    {
      "epoch": 0.8647140864714087,
      "grad_norm": 0.9843855500221252,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.8808,
      "step": 155
    },
    {
      "epoch": 0.8702928870292888,
      "grad_norm": 0.9288987517356873,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.5566,
      "step": 156
    },
    {
      "epoch": 0.8758716875871687,
      "grad_norm": 1.0149998664855957,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.7571,
      "step": 157
    },
    {
      "epoch": 0.8814504881450488,
      "grad_norm": 0.9581465125083923,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.5474,
      "step": 158
    },
    {
      "epoch": 0.8870292887029289,
      "grad_norm": 0.8580822944641113,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.5903,
      "step": 159
    },
    {
      "epoch": 0.8926080892608089,
      "grad_norm": 0.9470146894454956,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.5667,
      "step": 160
    },
    {
      "epoch": 0.898186889818689,
      "grad_norm": 0.9885293841362,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.651,
      "step": 161
    },
    {
      "epoch": 0.9037656903765691,
      "grad_norm": 0.8976189494132996,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.649,
      "step": 162
    },
    {
      "epoch": 0.9093444909344491,
      "grad_norm": 0.9778582453727722,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.4187,
      "step": 163
    },
    {
      "epoch": 0.9149232914923291,
      "grad_norm": 1.0202254056930542,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.7661,
      "step": 164
    },
    {
      "epoch": 0.9205020920502092,
      "grad_norm": 0.9143690466880798,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.4481,
      "step": 165
    },
    {
      "epoch": 0.9260808926080892,
      "grad_norm": 0.9532773494720459,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.4932,
      "step": 166
    },
    {
      "epoch": 0.9316596931659693,
      "grad_norm": 0.8889806866645813,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.3809,
      "step": 167
    },
    {
      "epoch": 0.9372384937238494,
      "grad_norm": 0.9684324264526367,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.572,
      "step": 168
    },
    {
      "epoch": 0.9428172942817294,
      "grad_norm": 1.1181423664093018,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.4162,
      "step": 169
    },
    {
      "epoch": 0.9483960948396095,
      "grad_norm": 1.0325437784194946,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.7197,
      "step": 170
    },
    {
      "epoch": 0.9539748953974896,
      "grad_norm": 1.0948636531829834,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.5455,
      "step": 171
    },
    {
      "epoch": 0.9595536959553695,
      "grad_norm": 1.116845726966858,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.6606,
      "step": 172
    },
    {
      "epoch": 0.9651324965132496,
      "grad_norm": 0.9331388473510742,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.3213,
      "step": 173
    },
    {
      "epoch": 0.9707112970711297,
      "grad_norm": 0.970477283000946,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.5282,
      "step": 174
    },
    {
      "epoch": 0.9762900976290098,
      "grad_norm": 0.9122838377952576,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.5872,
      "step": 175
    },
    {
      "epoch": 0.9818688981868898,
      "grad_norm": 1.1841830015182495,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.6401,
      "step": 176
    },
    {
      "epoch": 0.9874476987447699,
      "grad_norm": 0.872848391532898,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.5618,
      "step": 177
    },
    {
      "epoch": 0.99302649930265,
      "grad_norm": 0.9534340500831604,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.6317,
      "step": 178
    },
    {
      "epoch": 0.99860529986053,
      "grad_norm": 0.9462470412254333,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.4913,
      "step": 179
    },
    {
      "epoch": 1.00418410041841,
      "grad_norm": 2.737245559692383,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.6565,
      "step": 180
    },
    {
      "epoch": 1.00976290097629,
      "grad_norm": 0.8922616839408875,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.505,
      "step": 181
    },
    {
      "epoch": 1.0153417015341701,
      "grad_norm": 0.8828758001327515,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.3651,
      "step": 182
    },
    {
      "epoch": 1.0209205020920502,
      "grad_norm": 0.8943459987640381,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.5283,
      "step": 183
    },
    {
      "epoch": 1.0264993026499303,
      "grad_norm": 0.9490051865577698,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.4959,
      "step": 184
    },
    {
      "epoch": 1.0320781032078103,
      "grad_norm": 0.9101098775863647,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.5081,
      "step": 185
    },
    {
      "epoch": 1.0376569037656904,
      "grad_norm": 0.9249918460845947,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.3801,
      "step": 186
    },
    {
      "epoch": 1.0432357043235705,
      "grad_norm": 0.9510620832443237,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.3464,
      "step": 187
    },
    {
      "epoch": 1.0488145048814506,
      "grad_norm": 0.9726398587226868,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.4405,
      "step": 188
    },
    {
      "epoch": 1.0543933054393306,
      "grad_norm": 0.9687072038650513,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.5234,
      "step": 189
    },
    {
      "epoch": 1.0599721059972107,
      "grad_norm": 1.0236115455627441,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.4569,
      "step": 190
    },
    {
      "epoch": 1.0655509065550905,
      "grad_norm": 0.9256729483604431,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.5049,
      "step": 191
    },
    {
      "epoch": 1.0711297071129706,
      "grad_norm": 0.9009338021278381,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.474,
      "step": 192
    },
    {
      "epoch": 1.0767085076708507,
      "grad_norm": 0.963290274143219,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.3852,
      "step": 193
    },
    {
      "epoch": 1.0822873082287308,
      "grad_norm": 0.9053951501846313,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.3657,
      "step": 194
    },
    {
      "epoch": 1.0878661087866108,
      "grad_norm": 0.8652229905128479,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.3519,
      "step": 195
    },
    {
      "epoch": 1.093444909344491,
      "grad_norm": 0.9339153170585632,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.4287,
      "step": 196
    },
    {
      "epoch": 1.099023709902371,
      "grad_norm": 0.8982082009315491,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.3164,
      "step": 197
    },
    {
      "epoch": 1.104602510460251,
      "grad_norm": 0.8162841200828552,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.2306,
      "step": 198
    },
    {
      "epoch": 1.1101813110181311,
      "grad_norm": 0.9659661650657654,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.4347,
      "step": 199
    },
    {
      "epoch": 1.1157601115760112,
      "grad_norm": 0.9619619846343994,
      "learning_rate": 0.0,
      "loss": 1.3569,
      "step": 200
    },
    {
      "epoch": 1.1157601115760112,
      "eval_loss": 1.611555576324463,
      "eval_runtime": 22.9795,
      "eval_samples_per_second": 13.142,
      "eval_steps_per_second": 3.307,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.0161358600064205e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}