{
  "best_metric": 0.36537256836891174,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02697690102849435,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013488450514247176,
      "grad_norm": 0.7312794923782349,
      "learning_rate": 1e-05,
      "loss": 0.619,
      "step": 1
    },
    {
      "epoch": 0.00013488450514247176,
      "eval_loss": 0.5535552501678467,
      "eval_runtime": 261.6067,
      "eval_samples_per_second": 47.732,
      "eval_steps_per_second": 11.934,
      "step": 1
    },
    {
      "epoch": 0.0002697690102849435,
      "grad_norm": 0.7143637537956238,
      "learning_rate": 2e-05,
      "loss": 0.6297,
      "step": 2
    },
    {
      "epoch": 0.00040465351542741526,
      "grad_norm": 0.6300336718559265,
      "learning_rate": 3e-05,
      "loss": 0.5756,
      "step": 3
    },
    {
      "epoch": 0.000539538020569887,
      "grad_norm": 0.5285091400146484,
      "learning_rate": 4e-05,
      "loss": 0.5211,
      "step": 4
    },
    {
      "epoch": 0.0006744225257123588,
      "grad_norm": 0.48574239015579224,
      "learning_rate": 5e-05,
      "loss": 0.4962,
      "step": 5
    },
    {
      "epoch": 0.0008093070308548305,
      "grad_norm": 0.46220895648002625,
      "learning_rate": 6e-05,
      "loss": 0.4523,
      "step": 6
    },
    {
      "epoch": 0.0009441915359973024,
      "grad_norm": 0.4715046286582947,
      "learning_rate": 7e-05,
      "loss": 0.4054,
      "step": 7
    },
    {
      "epoch": 0.001079076041139774,
      "grad_norm": 0.49697309732437134,
      "learning_rate": 8e-05,
      "loss": 0.4653,
      "step": 8
    },
    {
      "epoch": 0.0012139605462822458,
      "grad_norm": 0.514630913734436,
      "learning_rate": 9e-05,
      "loss": 0.4525,
      "step": 9
    },
    {
      "epoch": 0.0013488450514247176,
      "grad_norm": 0.4862537384033203,
      "learning_rate": 0.0001,
      "loss": 0.4679,
      "step": 10
    },
    {
      "epoch": 0.0014837295565671893,
      "grad_norm": 0.5644695162773132,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5622,
      "step": 11
    },
    {
      "epoch": 0.001618614061709661,
      "grad_norm": 0.4921167492866516,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5723,
      "step": 12
    },
    {
      "epoch": 0.0017534985668521328,
      "grad_norm": 0.459239661693573,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4831,
      "step": 13
    },
    {
      "epoch": 0.0018883830719946047,
      "grad_norm": 0.4722726047039032,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4803,
      "step": 14
    },
    {
      "epoch": 0.0020232675771370764,
      "grad_norm": 0.4661000370979309,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5015,
      "step": 15
    },
    {
      "epoch": 0.002158152082279548,
      "grad_norm": 0.4489058554172516,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4738,
      "step": 16
    },
    {
      "epoch": 0.00229303658742202,
      "grad_norm": 0.4424433708190918,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4926,
      "step": 17
    },
    {
      "epoch": 0.0024279210925644916,
      "grad_norm": 0.43475666642189026,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.4548,
      "step": 18
    },
    {
      "epoch": 0.0025628055977069634,
      "grad_norm": 0.42985185980796814,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4544,
      "step": 19
    },
    {
      "epoch": 0.002697690102849435,
      "grad_norm": 0.4276285469532013,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.421,
      "step": 20
    },
    {
      "epoch": 0.002832574607991907,
      "grad_norm": 0.4911406934261322,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.4708,
      "step": 21
    },
    {
      "epoch": 0.0029674591131343786,
      "grad_norm": 0.42674770951271057,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4143,
      "step": 22
    },
    {
      "epoch": 0.0031023436182768503,
      "grad_norm": 0.465128093957901,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4706,
      "step": 23
    },
    {
      "epoch": 0.003237228123419322,
      "grad_norm": 0.46154120564460754,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4471,
      "step": 24
    },
    {
      "epoch": 0.003372112628561794,
      "grad_norm": 0.47119396924972534,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4281,
      "step": 25
    },
    {
      "epoch": 0.0035069971337042655,
      "grad_norm": 0.43948134779930115,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3974,
      "step": 26
    },
    {
      "epoch": 0.0036418816388467377,
      "grad_norm": 0.4317210614681244,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4112,
      "step": 27
    },
    {
      "epoch": 0.0037767661439892094,
      "grad_norm": 0.42708370089530945,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4,
      "step": 28
    },
    {
      "epoch": 0.003911650649131681,
      "grad_norm": 0.44661572575569153,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3611,
      "step": 29
    },
    {
      "epoch": 0.004046535154274153,
      "grad_norm": 0.4315156042575836,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3832,
      "step": 30
    },
    {
      "epoch": 0.004181419659416624,
      "grad_norm": 0.49408775568008423,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4017,
      "step": 31
    },
    {
      "epoch": 0.004316304164559096,
      "grad_norm": 0.47425273060798645,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3447,
      "step": 32
    },
    {
      "epoch": 0.004451188669701568,
      "grad_norm": 0.4949743151664734,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4139,
      "step": 33
    },
    {
      "epoch": 0.00458607317484404,
      "grad_norm": 0.504218578338623,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4341,
      "step": 34
    },
    {
      "epoch": 0.004720957679986511,
      "grad_norm": 0.5098018646240234,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3957,
      "step": 35
    },
    {
      "epoch": 0.004855842185128983,
      "grad_norm": 0.5136622786521912,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3625,
      "step": 36
    },
    {
      "epoch": 0.0049907266902714555,
      "grad_norm": 0.4868154227733612,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.3353,
      "step": 37
    },
    {
      "epoch": 0.005125611195413927,
      "grad_norm": 0.49792125821113586,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3967,
      "step": 38
    },
    {
      "epoch": 0.005260495700556399,
      "grad_norm": 0.5094825029373169,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3367,
      "step": 39
    },
    {
      "epoch": 0.00539538020569887,
      "grad_norm": 0.471170574426651,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.3251,
      "step": 40
    },
    {
      "epoch": 0.005530264710841342,
      "grad_norm": 0.5279748439788818,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3471,
      "step": 41
    },
    {
      "epoch": 0.005665149215983814,
      "grad_norm": 0.5525723099708557,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3646,
      "step": 42
    },
    {
      "epoch": 0.005800033721126286,
      "grad_norm": 0.5596986413002014,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.3202,
      "step": 43
    },
    {
      "epoch": 0.005934918226268757,
      "grad_norm": 0.5672169923782349,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.3252,
      "step": 44
    },
    {
      "epoch": 0.006069802731411229,
      "grad_norm": 0.5516791343688965,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.3483,
      "step": 45
    },
    {
      "epoch": 0.006204687236553701,
      "grad_norm": 0.5630849599838257,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3328,
      "step": 46
    },
    {
      "epoch": 0.006339571741696173,
      "grad_norm": 0.5775346755981445,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3076,
      "step": 47
    },
    {
      "epoch": 0.006474456246838644,
      "grad_norm": 0.6982398629188538,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3605,
      "step": 48
    },
    {
      "epoch": 0.006609340751981116,
      "grad_norm": 0.6357693076133728,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3022,
      "step": 49
    },
    {
      "epoch": 0.006744225257123588,
      "grad_norm": 0.7867982387542725,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2689,
      "step": 50
    },
    {
      "epoch": 0.006744225257123588,
      "eval_loss": 0.40518319606781006,
      "eval_runtime": 262.1911,
      "eval_samples_per_second": 47.626,
      "eval_steps_per_second": 11.907,
      "step": 50
    },
    {
      "epoch": 0.00687910976226606,
      "grad_norm": 0.5242670774459839,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5561,
      "step": 51
    },
    {
      "epoch": 0.007013994267408531,
      "grad_norm": 0.4614350199699402,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5318,
      "step": 52
    },
    {
      "epoch": 0.007148878772551003,
      "grad_norm": 0.4419964551925659,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5339,
      "step": 53
    },
    {
      "epoch": 0.007283763277693475,
      "grad_norm": 0.3879670202732086,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4531,
      "step": 54
    },
    {
      "epoch": 0.007418647782835947,
      "grad_norm": 0.33741194009780884,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4525,
      "step": 55
    },
    {
      "epoch": 0.007553532287978419,
      "grad_norm": 0.3487919867038727,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4512,
      "step": 56
    },
    {
      "epoch": 0.00768841679312089,
      "grad_norm": 0.34235578775405884,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.446,
      "step": 57
    },
    {
      "epoch": 0.007823301298263361,
      "grad_norm": 0.33178678154945374,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.4037,
      "step": 58
    },
    {
      "epoch": 0.007958185803405834,
      "grad_norm": 0.29955005645751953,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3566,
      "step": 59
    },
    {
      "epoch": 0.008093070308548306,
      "grad_norm": 0.33092001080513,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3961,
      "step": 60
    },
    {
      "epoch": 0.008227954813690777,
      "grad_norm": 0.37373727560043335,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.4685,
      "step": 61
    },
    {
      "epoch": 0.008362839318833248,
      "grad_norm": 0.3390158414840698,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4428,
      "step": 62
    },
    {
      "epoch": 0.008497723823975721,
      "grad_norm": 0.3667975068092346,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4667,
      "step": 63
    },
    {
      "epoch": 0.008632608329118193,
      "grad_norm": 0.3451032042503357,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.4217,
      "step": 64
    },
    {
      "epoch": 0.008767492834260664,
      "grad_norm": 0.398881196975708,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5447,
      "step": 65
    },
    {
      "epoch": 0.008902377339403135,
      "grad_norm": 0.3622574210166931,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4524,
      "step": 66
    },
    {
      "epoch": 0.009037261844545608,
      "grad_norm": 0.3536049425601959,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4316,
      "step": 67
    },
    {
      "epoch": 0.00917214634968808,
      "grad_norm": 0.36760830879211426,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4317,
      "step": 68
    },
    {
      "epoch": 0.009307030854830551,
      "grad_norm": 0.3778778612613678,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3949,
      "step": 69
    },
    {
      "epoch": 0.009441915359973022,
      "grad_norm": 0.4039371609687805,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.4618,
      "step": 70
    },
    {
      "epoch": 0.009576799865115495,
      "grad_norm": 0.37713518738746643,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4162,
      "step": 71
    },
    {
      "epoch": 0.009711684370257967,
      "grad_norm": 0.39410510659217834,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4337,
      "step": 72
    },
    {
      "epoch": 0.009846568875400438,
      "grad_norm": 0.36754271388053894,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.405,
      "step": 73
    },
    {
      "epoch": 0.009981453380542911,
      "grad_norm": 0.39261293411254883,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4233,
      "step": 74
    },
    {
      "epoch": 0.010116337885685382,
      "grad_norm": 0.3770694136619568,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3955,
      "step": 75
    },
    {
      "epoch": 0.010251222390827854,
      "grad_norm": 0.3800658583641052,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.4154,
      "step": 76
    },
    {
      "epoch": 0.010386106895970325,
      "grad_norm": 0.37402909994125366,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.3828,
      "step": 77
    },
    {
      "epoch": 0.010520991401112798,
      "grad_norm": 0.3853798508644104,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4057,
      "step": 78
    },
    {
      "epoch": 0.01065587590625527,
      "grad_norm": 0.3780139982700348,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3659,
      "step": 79
    },
    {
      "epoch": 0.01079076041139774,
      "grad_norm": 0.38309550285339355,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3558,
      "step": 80
    },
    {
      "epoch": 0.010925644916540212,
      "grad_norm": 0.4079267978668213,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3826,
      "step": 81
    },
    {
      "epoch": 0.011060529421682685,
      "grad_norm": 0.4015042185783386,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3268,
      "step": 82
    },
    {
      "epoch": 0.011195413926825156,
      "grad_norm": 0.41961029171943665,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.364,
      "step": 83
    },
    {
      "epoch": 0.011330298431967627,
      "grad_norm": 0.44483575224876404,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3765,
      "step": 84
    },
    {
      "epoch": 0.011465182937110099,
      "grad_norm": 0.4226159453392029,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3532,
      "step": 85
    },
    {
      "epoch": 0.011600067442252572,
      "grad_norm": 0.43840324878692627,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3108,
      "step": 86
    },
    {
      "epoch": 0.011734951947395043,
      "grad_norm": 0.446931391954422,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3446,
      "step": 87
    },
    {
      "epoch": 0.011869836452537514,
      "grad_norm": 0.45088011026382446,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3371,
      "step": 88
    },
    {
      "epoch": 0.012004720957679987,
      "grad_norm": 0.4736665189266205,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3231,
      "step": 89
    },
    {
      "epoch": 0.012139605462822459,
      "grad_norm": 0.47136396169662476,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3397,
      "step": 90
    },
    {
      "epoch": 0.01227448996796493,
      "grad_norm": 0.4480249583721161,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3357,
      "step": 91
    },
    {
      "epoch": 0.012409374473107401,
      "grad_norm": 0.4858390986919403,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3126,
      "step": 92
    },
    {
      "epoch": 0.012544258978249874,
      "grad_norm": 0.4830036461353302,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.2863,
      "step": 93
    },
    {
      "epoch": 0.012679143483392346,
      "grad_norm": 0.504490315914154,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.306,
      "step": 94
    },
    {
      "epoch": 0.012814027988534817,
      "grad_norm": 0.48440879583358765,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2569,
      "step": 95
    },
    {
      "epoch": 0.012948912493677288,
      "grad_norm": 0.5180103778839111,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.274,
      "step": 96
    },
    {
      "epoch": 0.013083796998819761,
      "grad_norm": 0.5439738631248474,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3278,
      "step": 97
    },
    {
      "epoch": 0.013218681503962233,
      "grad_norm": 0.5681024789810181,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.278,
      "step": 98
    },
    {
      "epoch": 0.013353566009104704,
      "grad_norm": 0.580071210861206,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2846,
      "step": 99
    },
    {
      "epoch": 0.013488450514247175,
      "grad_norm": 0.628166139125824,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2597,
      "step": 100
    },
    {
      "epoch": 0.013488450514247175,
      "eval_loss": 0.382447749376297,
      "eval_runtime": 262.4788,
      "eval_samples_per_second": 47.573,
      "eval_steps_per_second": 11.894,
      "step": 100
    },
    {
      "epoch": 0.013623335019389648,
      "grad_norm": 0.4581434726715088,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.5369,
      "step": 101
    },
    {
      "epoch": 0.01375821952453212,
      "grad_norm": 0.4508751928806305,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5146,
      "step": 102
    },
    {
      "epoch": 0.01389310402967459,
      "grad_norm": 0.3835512101650238,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5016,
      "step": 103
    },
    {
      "epoch": 0.014027988534817062,
      "grad_norm": 0.36224380135536194,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4763,
      "step": 104
    },
    {
      "epoch": 0.014162873039959535,
      "grad_norm": 0.32311156392097473,
      "learning_rate": 5e-05,
      "loss": 0.3923,
      "step": 105
    },
    {
      "epoch": 0.014297757545102006,
      "grad_norm": 0.31436944007873535,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4099,
      "step": 106
    },
    {
      "epoch": 0.014432642050244478,
      "grad_norm": 0.32397738099098206,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4508,
      "step": 107
    },
    {
      "epoch": 0.01456752655538695,
      "grad_norm": 0.3148738443851471,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3988,
      "step": 108
    },
    {
      "epoch": 0.014702411060529422,
      "grad_norm": 0.29887405037879944,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3928,
      "step": 109
    },
    {
      "epoch": 0.014837295565671893,
      "grad_norm": 0.3037765920162201,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3994,
      "step": 110
    },
    {
      "epoch": 0.014972180070814365,
      "grad_norm": 0.30903902649879456,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.4239,
      "step": 111
    },
    {
      "epoch": 0.015107064575956838,
      "grad_norm": 0.30294039845466614,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4169,
      "step": 112
    },
    {
      "epoch": 0.015241949081099309,
      "grad_norm": 0.311907023191452,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3752,
      "step": 113
    },
    {
      "epoch": 0.01537683358624178,
      "grad_norm": 0.3474252223968506,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4963,
      "step": 114
    },
    {
      "epoch": 0.015511718091384252,
      "grad_norm": 0.34316110610961914,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3836,
      "step": 115
    },
    {
      "epoch": 0.015646602596526723,
      "grad_norm": 0.34648433327674866,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4341,
      "step": 116
    },
    {
      "epoch": 0.015781487101669194,
      "grad_norm": 0.3631751537322998,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4273,
      "step": 117
    },
    {
      "epoch": 0.01591637160681167,
      "grad_norm": 0.3653939962387085,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.4124,
      "step": 118
    },
    {
      "epoch": 0.01605125611195414,
      "grad_norm": 0.3692803680896759,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.4449,
      "step": 119
    },
    {
      "epoch": 0.01618614061709661,
      "grad_norm": 0.35545095801353455,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4017,
      "step": 120
    },
    {
      "epoch": 0.016321025122239083,
      "grad_norm": 0.36501505970954895,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4192,
      "step": 121
    },
    {
      "epoch": 0.016455909627381554,
      "grad_norm": 0.3892112076282501,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3879,
      "step": 122
    },
    {
      "epoch": 0.016590794132524025,
      "grad_norm": 0.3721289336681366,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3988,
      "step": 123
    },
    {
      "epoch": 0.016725678637666497,
      "grad_norm": 0.38764387369155884,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3915,
      "step": 124
    },
    {
      "epoch": 0.01686056314280897,
      "grad_norm": 0.3866587281227112,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4083,
      "step": 125
    },
    {
      "epoch": 0.016995447647951443,
      "grad_norm": 0.3885902166366577,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3663,
      "step": 126
    },
    {
      "epoch": 0.017130332153093914,
      "grad_norm": 0.3833582401275635,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3654,
      "step": 127
    },
    {
      "epoch": 0.017265216658236385,
      "grad_norm": 0.3884214162826538,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3531,
      "step": 128
    },
    {
      "epoch": 0.017400101163378857,
      "grad_norm": 0.397443562746048,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3728,
      "step": 129
    },
    {
      "epoch": 0.017534985668521328,
      "grad_norm": 0.37509793043136597,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3239,
      "step": 130
    },
    {
      "epoch": 0.0176698701736638,
      "grad_norm": 0.3894180655479431,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3106,
      "step": 131
    },
    {
      "epoch": 0.01780475467880627,
      "grad_norm": 0.40647250413894653,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3234,
      "step": 132
    },
    {
      "epoch": 0.017939639183948745,
      "grad_norm": 0.41561031341552734,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.293,
      "step": 133
    },
    {
      "epoch": 0.018074523689091217,
      "grad_norm": 0.42787015438079834,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3313,
      "step": 134
    },
    {
      "epoch": 0.018209408194233688,
      "grad_norm": 0.427840918302536,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3253,
      "step": 135
    },
    {
      "epoch": 0.01834429269937616,
      "grad_norm": 0.4319380819797516,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3208,
      "step": 136
    },
    {
      "epoch": 0.01847917720451863,
      "grad_norm": 0.43576690554618835,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3367,
      "step": 137
    },
    {
      "epoch": 0.018614061709661102,
      "grad_norm": 0.44664502143859863,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3522,
      "step": 138
    },
    {
      "epoch": 0.018748946214803573,
      "grad_norm": 0.4573809504508972,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3296,
      "step": 139
    },
    {
      "epoch": 0.018883830719946045,
      "grad_norm": 0.4908885359764099,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3222,
      "step": 140
    },
    {
      "epoch": 0.01901871522508852,
      "grad_norm": 0.45148366689682007,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.2693,
      "step": 141
    },
    {
      "epoch": 0.01915359973023099,
      "grad_norm": 0.46059873700141907,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2832,
      "step": 142
    },
    {
      "epoch": 0.019288484235373462,
      "grad_norm": 0.5342593193054199,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3632,
      "step": 143
    },
    {
      "epoch": 0.019423368740515933,
      "grad_norm": 0.5199819207191467,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.324,
      "step": 144
    },
    {
      "epoch": 0.019558253245658404,
      "grad_norm": 0.49179965257644653,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.284,
      "step": 145
    },
    {
      "epoch": 0.019693137750800876,
      "grad_norm": 0.5242893695831299,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3017,
      "step": 146
    },
    {
      "epoch": 0.019828022255943347,
      "grad_norm": 0.525263249874115,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2744,
      "step": 147
    },
    {
      "epoch": 0.019962906761085822,
      "grad_norm": 0.5597575902938843,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2691,
      "step": 148
    },
    {
      "epoch": 0.020097791266228293,
      "grad_norm": 0.589989960193634,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.2872,
      "step": 149
    },
    {
      "epoch": 0.020232675771370764,
      "grad_norm": 0.6061083674430847,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2488,
      "step": 150
    },
    {
      "epoch": 0.020232675771370764,
      "eval_loss": 0.3696884214878082,
      "eval_runtime": 262.2284,
      "eval_samples_per_second": 47.619,
      "eval_steps_per_second": 11.906,
      "step": 150
    },
    {
      "epoch": 0.020367560276513236,
      "grad_norm": 0.36233416199684143,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4832,
      "step": 151
    },
    {
      "epoch": 0.020502444781655707,
      "grad_norm": 0.3787022531032562,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4833,
      "step": 152
    },
    {
      "epoch": 0.02063732928679818,
      "grad_norm": 0.32080021500587463,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.4047,
      "step": 153
    },
    {
      "epoch": 0.02077221379194065,
      "grad_norm": 0.34497880935668945,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.463,
      "step": 154
    },
    {
      "epoch": 0.02090709829708312,
      "grad_norm": 0.33919447660446167,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4452,
      "step": 155
    },
    {
      "epoch": 0.021041982802225596,
      "grad_norm": 0.3532559275627136,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.4235,
      "step": 156
    },
    {
      "epoch": 0.021176867307368067,
      "grad_norm": 0.34111523628234863,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.4041,
      "step": 157
    },
    {
      "epoch": 0.02131175181251054,
      "grad_norm": 0.3617994487285614,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.4229,
      "step": 158
    },
    {
      "epoch": 0.02144663631765301,
      "grad_norm": 0.32418686151504517,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3978,
      "step": 159
    },
    {
      "epoch": 0.02158152082279548,
      "grad_norm": 0.31860753893852234,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.3895,
      "step": 160
    },
    {
      "epoch": 0.021716405327937952,
      "grad_norm": 0.31589362025260925,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3918,
      "step": 161
    },
    {
      "epoch": 0.021851289833080424,
      "grad_norm": 0.32022422552108765,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.435,
      "step": 162
    },
    {
      "epoch": 0.0219861743382229,
      "grad_norm": 0.3380190134048462,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4348,
      "step": 163
    },
    {
      "epoch": 0.02212105884336537,
      "grad_norm": 0.31500014662742615,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4062,
      "step": 164
    },
    {
      "epoch": 0.02225594334850784,
      "grad_norm": 0.3184114694595337,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4017,
      "step": 165
    },
    {
      "epoch": 0.022390827853650312,
      "grad_norm": 0.31457948684692383,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3875,
      "step": 166
    },
    {
      "epoch": 0.022525712358792783,
      "grad_norm": 0.33677563071250916,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3917,
      "step": 167
    },
    {
      "epoch": 0.022660596863935255,
      "grad_norm": 0.34128713607788086,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.4221,
      "step": 168
    },
    {
      "epoch": 0.022795481369077726,
      "grad_norm": 0.33863160014152527,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3994,
      "step": 169
    },
    {
      "epoch": 0.022930365874220197,
      "grad_norm": 0.3559151589870453,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4011,
      "step": 170
    },
    {
      "epoch": 0.023065250379362672,
      "grad_norm": 0.35164138674736023,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3941,
      "step": 171
    },
    {
      "epoch": 0.023200134884505143,
      "grad_norm": 0.36053434014320374,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4355,
      "step": 172
    },
    {
      "epoch": 0.023335019389647615,
      "grad_norm": 0.3656643033027649,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4105,
      "step": 173
    },
    {
      "epoch": 0.023469903894790086,
      "grad_norm": 0.37433862686157227,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4631,
      "step": 174
    },
    {
      "epoch": 0.023604788399932557,
      "grad_norm": 0.3767264187335968,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4236,
      "step": 175
    },
    {
      "epoch": 0.02373967290507503,
      "grad_norm": 0.3816257417201996,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4145,
      "step": 176
    },
    {
      "epoch": 0.0238745574102175,
      "grad_norm": 0.3735591769218445,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3784,
      "step": 177
    },
    {
      "epoch": 0.024009441915359975,
      "grad_norm": 0.35658329725265503,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3135,
      "step": 178
    },
    {
      "epoch": 0.024144326420502446,
      "grad_norm": 0.3797186613082886,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3803,
      "step": 179
    },
    {
      "epoch": 0.024279210925644917,
      "grad_norm": 0.38176941871643066,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.3504,
      "step": 180
    },
    {
      "epoch": 0.02441409543078739,
      "grad_norm": 0.3997100293636322,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3188,
      "step": 181
    },
    {
      "epoch": 0.02454897993592986,
      "grad_norm": 0.40705814957618713,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.3803,
      "step": 182
    },
    {
      "epoch": 0.02468386444107233,
      "grad_norm": 0.4159797430038452,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3524,
      "step": 183
    },
    {
      "epoch": 0.024818748946214803,
      "grad_norm": 0.40622735023498535,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.3142,
      "step": 184
    },
    {
      "epoch": 0.024953633451357274,
      "grad_norm": 0.4355838894844055,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3147,
      "step": 185
    },
    {
      "epoch": 0.02508851795649975,
      "grad_norm": 0.42096856236457825,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3738,
      "step": 186
    },
    {
      "epoch": 0.02522340246164222,
      "grad_norm": 0.44048431515693665,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3328,
      "step": 187
    },
    {
      "epoch": 0.02535828696678469,
      "grad_norm": 0.4188198745250702,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2952,
      "step": 188
    },
    {
      "epoch": 0.025493171471927163,
      "grad_norm": 0.4608989655971527,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3564,
      "step": 189
    },
    {
      "epoch": 0.025628055977069634,
      "grad_norm": 0.42364248633384705,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3048,
      "step": 190
    },
    {
      "epoch": 0.025762940482212105,
      "grad_norm": 0.4658060073852539,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.3347,
      "step": 191
    },
    {
      "epoch": 0.025897824987354576,
      "grad_norm": 0.5022123456001282,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.2863,
      "step": 192
    },
    {
      "epoch": 0.026032709492497048,
      "grad_norm": 0.4914219081401825,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3117,
      "step": 193
    },
    {
      "epoch": 0.026167593997639522,
      "grad_norm": 0.47237637639045715,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2673,
      "step": 194
    },
    {
      "epoch": 0.026302478502781994,
      "grad_norm": 0.5090441107749939,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3177,
      "step": 195
    },
    {
      "epoch": 0.026437363007924465,
      "grad_norm": 0.5146756768226624,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3035,
      "step": 196
    },
    {
      "epoch": 0.026572247513066936,
      "grad_norm": 0.5451027750968933,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3048,
      "step": 197
    },
    {
      "epoch": 0.026707132018209408,
      "grad_norm": 0.5446709990501404,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2934,
      "step": 198
    },
    {
      "epoch": 0.02684201652335188,
      "grad_norm": 0.5645793676376343,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.2184,
      "step": 199
    },
    {
      "epoch": 0.02697690102849435,
      "grad_norm": 0.6588689088821411,
      "learning_rate": 0.0,
      "loss": 0.2895,
      "step": 200
    },
    {
      "epoch": 0.02697690102849435,
      "eval_loss": 0.36537256836891174,
      "eval_runtime": 262.3101,
      "eval_samples_per_second": 47.604,
      "eval_steps_per_second": 11.902,
      "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": 1.9166636430852096e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}