{
  "best_metric": 0.007327286526560783,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.022397043590246087,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011198521795123043,
      "grad_norm": 0.25927817821502686,
      "learning_rate": 1e-05,
      "loss": 0.1155,
      "step": 1
    },
    {
      "epoch": 0.00011198521795123043,
      "eval_loss": 0.31381627917289734,
      "eval_runtime": 1075.4877,
      "eval_samples_per_second": 13.984,
      "eval_steps_per_second": 3.496,
      "step": 1
    },
    {
      "epoch": 0.00022397043590246087,
      "grad_norm": 0.26984506845474243,
      "learning_rate": 2e-05,
      "loss": 0.1108,
      "step": 2
    },
    {
      "epoch": 0.00033595565385369133,
      "grad_norm": 0.31754177808761597,
      "learning_rate": 3e-05,
      "loss": 0.1162,
      "step": 3
    },
    {
      "epoch": 0.00044794087180492174,
      "grad_norm": 0.3051096200942993,
      "learning_rate": 4e-05,
      "loss": 0.1186,
      "step": 4
    },
    {
      "epoch": 0.0005599260897561521,
      "grad_norm": 0.3076366186141968,
      "learning_rate": 5e-05,
      "loss": 0.1112,
      "step": 5
    },
    {
      "epoch": 0.0006719113077073827,
      "grad_norm": 0.2390199452638626,
      "learning_rate": 6e-05,
      "loss": 0.0872,
      "step": 6
    },
    {
      "epoch": 0.0007838965256586131,
      "grad_norm": 0.23474720120429993,
      "learning_rate": 7e-05,
      "loss": 0.0692,
      "step": 7
    },
    {
      "epoch": 0.0008958817436098435,
      "grad_norm": 0.19189739227294922,
      "learning_rate": 8e-05,
      "loss": 0.033,
      "step": 8
    },
    {
      "epoch": 0.0010078669615610739,
      "grad_norm": 0.13253426551818848,
      "learning_rate": 9e-05,
      "loss": 0.0242,
      "step": 9
    },
    {
      "epoch": 0.0011198521795123043,
      "grad_norm": 0.12574318051338196,
      "learning_rate": 0.0001,
      "loss": 0.0302,
      "step": 10
    },
    {
      "epoch": 0.001231837397463535,
      "grad_norm": 0.13055111467838287,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.021,
      "step": 11
    },
    {
      "epoch": 0.0013438226154147653,
      "grad_norm": 0.0866556465625763,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.007,
      "step": 12
    },
    {
      "epoch": 0.0014558078333659957,
      "grad_norm": 0.10831146687269211,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0115,
      "step": 13
    },
    {
      "epoch": 0.0015677930513172261,
      "grad_norm": 0.12199873477220535,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0222,
      "step": 14
    },
    {
      "epoch": 0.0016797782692684565,
      "grad_norm": 0.09704765677452087,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0128,
      "step": 15
    },
    {
      "epoch": 0.001791763487219687,
      "grad_norm": 0.20441791415214539,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0127,
      "step": 16
    },
    {
      "epoch": 0.0019037487051709173,
      "grad_norm": 0.12097930163145065,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0209,
      "step": 17
    },
    {
      "epoch": 0.0020157339231221478,
      "grad_norm": 0.10276233404874802,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0069,
      "step": 18
    },
    {
      "epoch": 0.0021277191410733784,
      "grad_norm": 0.10755858570337296,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0238,
      "step": 19
    },
    {
      "epoch": 0.0022397043590246086,
      "grad_norm": 0.12791231274604797,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0221,
      "step": 20
    },
    {
      "epoch": 0.002351689576975839,
      "grad_norm": 0.10151226073503494,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0184,
      "step": 21
    },
    {
      "epoch": 0.00246367479492707,
      "grad_norm": 0.0769859030842781,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0121,
      "step": 22
    },
    {
      "epoch": 0.0025756600128783,
      "grad_norm": 0.11479981243610382,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0162,
      "step": 23
    },
    {
      "epoch": 0.0026876452308295306,
      "grad_norm": 0.12760038673877716,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0091,
      "step": 24
    },
    {
      "epoch": 0.002799630448780761,
      "grad_norm": 0.08908756822347641,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0093,
      "step": 25
    },
    {
      "epoch": 0.0029116156667319914,
      "grad_norm": 0.144797220826149,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0108,
      "step": 26
    },
    {
      "epoch": 0.0030236008846832216,
      "grad_norm": 0.1253516674041748,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0133,
      "step": 27
    },
    {
      "epoch": 0.0031355861026344523,
      "grad_norm": 0.26495638489723206,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0129,
      "step": 28
    },
    {
      "epoch": 0.003247571320585683,
      "grad_norm": 0.11229117959737778,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0121,
      "step": 29
    },
    {
      "epoch": 0.003359556538536913,
      "grad_norm": 0.1756782978773117,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0188,
      "step": 30
    },
    {
      "epoch": 0.0034715417564881437,
      "grad_norm": 0.11732535064220428,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0156,
      "step": 31
    },
    {
      "epoch": 0.003583526974439374,
      "grad_norm": 0.08606487512588501,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0098,
      "step": 32
    },
    {
      "epoch": 0.0036955121923906045,
      "grad_norm": 0.07556793093681335,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.008,
      "step": 33
    },
    {
      "epoch": 0.0038074974103418347,
      "grad_norm": 0.2105581909418106,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0266,
      "step": 34
    },
    {
      "epoch": 0.003919482628293065,
      "grad_norm": 0.1967843621969223,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0229,
      "step": 35
    },
    {
      "epoch": 0.0040314678462442955,
      "grad_norm": 0.15108954906463623,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0139,
      "step": 36
    },
    {
      "epoch": 0.0041434530641955266,
      "grad_norm": 0.13553796708583832,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.013,
      "step": 37
    },
    {
      "epoch": 0.004255438282146757,
      "grad_norm": 0.09607615321874619,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0064,
      "step": 38
    },
    {
      "epoch": 0.004367423500097987,
      "grad_norm": 0.06474720686674118,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0124,
      "step": 39
    },
    {
      "epoch": 0.004479408718049217,
      "grad_norm": 0.12679226696491241,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.011,
      "step": 40
    },
    {
      "epoch": 0.004591393936000448,
      "grad_norm": 0.11105883866548538,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.019,
      "step": 41
    },
    {
      "epoch": 0.004703379153951678,
      "grad_norm": 0.13030923902988434,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0149,
      "step": 42
    },
    {
      "epoch": 0.004815364371902909,
      "grad_norm": 0.14741690456867218,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0238,
      "step": 43
    },
    {
      "epoch": 0.00492734958985414,
      "grad_norm": 0.16128338873386383,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0199,
      "step": 44
    },
    {
      "epoch": 0.00503933480780537,
      "grad_norm": 0.18844985961914062,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0059,
      "step": 45
    },
    {
      "epoch": 0.0051513200257566,
      "grad_norm": 0.1356336623430252,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.014,
      "step": 46
    },
    {
      "epoch": 0.00526330524370783,
      "grad_norm": 0.08984953165054321,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0167,
      "step": 47
    },
    {
      "epoch": 0.005375290461659061,
      "grad_norm": 0.16732057929039001,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.011,
      "step": 48
    },
    {
      "epoch": 0.0054872756796102914,
      "grad_norm": 0.18355792760849,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0254,
      "step": 49
    },
    {
      "epoch": 0.005599260897561522,
      "grad_norm": 0.3201683759689331,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0339,
      "step": 50
    },
    {
      "epoch": 0.005599260897561522,
      "eval_loss": 0.012402563355863094,
      "eval_runtime": 1079.7065,
      "eval_samples_per_second": 13.93,
      "eval_steps_per_second": 3.482,
      "step": 50
    },
    {
      "epoch": 0.005711246115512753,
      "grad_norm": 0.08151597529649734,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0191,
      "step": 51
    },
    {
      "epoch": 0.005823231333463983,
      "grad_norm": 0.043629955500364304,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0075,
      "step": 52
    },
    {
      "epoch": 0.005935216551415213,
      "grad_norm": 0.07190629094839096,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.008,
      "step": 53
    },
    {
      "epoch": 0.006047201769366443,
      "grad_norm": 0.04685960337519646,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0116,
      "step": 54
    },
    {
      "epoch": 0.006159186987317674,
      "grad_norm": 0.03496837243437767,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0115,
      "step": 55
    },
    {
      "epoch": 0.0062711722052689045,
      "grad_norm": 0.07295988500118256,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0077,
      "step": 56
    },
    {
      "epoch": 0.006383157423220135,
      "grad_norm": 0.028815751895308495,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0068,
      "step": 57
    },
    {
      "epoch": 0.006495142641171366,
      "grad_norm": 0.07860519737005234,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0067,
      "step": 58
    },
    {
      "epoch": 0.006607127859122596,
      "grad_norm": 0.03098691627383232,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0046,
      "step": 59
    },
    {
      "epoch": 0.006719113077073826,
      "grad_norm": 0.04155720770359039,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0056,
      "step": 60
    },
    {
      "epoch": 0.006831098295025056,
      "grad_norm": 0.04726318642497063,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0063,
      "step": 61
    },
    {
      "epoch": 0.006943083512976287,
      "grad_norm": 0.14553825557231903,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0127,
      "step": 62
    },
    {
      "epoch": 0.007055068730927518,
      "grad_norm": 0.08409129083156586,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0119,
      "step": 63
    },
    {
      "epoch": 0.007167053948878748,
      "grad_norm": 0.0558687187731266,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0062,
      "step": 64
    },
    {
      "epoch": 0.007279039166829979,
      "grad_norm": 0.03517032787203789,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0069,
      "step": 65
    },
    {
      "epoch": 0.007391024384781209,
      "grad_norm": 0.03434384986758232,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0029,
      "step": 66
    },
    {
      "epoch": 0.007503009602732439,
      "grad_norm": 0.07082964479923248,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0097,
      "step": 67
    },
    {
      "epoch": 0.007614994820683669,
      "grad_norm": 0.06074490025639534,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0049,
      "step": 68
    },
    {
      "epoch": 0.0077269800386349004,
      "grad_norm": 0.07937470078468323,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0132,
      "step": 69
    },
    {
      "epoch": 0.00783896525658613,
      "grad_norm": 0.04968696087598801,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0064,
      "step": 70
    },
    {
      "epoch": 0.00795095047453736,
      "grad_norm": 0.05936945974826813,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0067,
      "step": 71
    },
    {
      "epoch": 0.008062935692488591,
      "grad_norm": 0.07118445634841919,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0124,
      "step": 72
    },
    {
      "epoch": 0.008174920910439821,
      "grad_norm": 0.048843711614608765,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0106,
      "step": 73
    },
    {
      "epoch": 0.008286906128391053,
      "grad_norm": 0.05531323701143265,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.006,
      "step": 74
    },
    {
      "epoch": 0.008398891346342283,
      "grad_norm": 0.07174713909626007,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0176,
      "step": 75
    },
    {
      "epoch": 0.008510876564293514,
      "grad_norm": 0.09108234196901321,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0071,
      "step": 76
    },
    {
      "epoch": 0.008622861782244744,
      "grad_norm": 0.07062532752752304,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0058,
      "step": 77
    },
    {
      "epoch": 0.008734847000195974,
      "grad_norm": 0.05787373706698418,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.008,
      "step": 78
    },
    {
      "epoch": 0.008846832218147204,
      "grad_norm": 0.07510489225387573,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0067,
      "step": 79
    },
    {
      "epoch": 0.008958817436098434,
      "grad_norm": 0.09543178230524063,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0126,
      "step": 80
    },
    {
      "epoch": 0.009070802654049666,
      "grad_norm": 0.08685528486967087,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0086,
      "step": 81
    },
    {
      "epoch": 0.009182787872000896,
      "grad_norm": 0.049802061170339584,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.009,
      "step": 82
    },
    {
      "epoch": 0.009294773089952127,
      "grad_norm": 0.03666006773710251,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0083,
      "step": 83
    },
    {
      "epoch": 0.009406758307903357,
      "grad_norm": 0.06713581085205078,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0053,
      "step": 84
    },
    {
      "epoch": 0.009518743525854587,
      "grad_norm": 0.12403149157762527,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0145,
      "step": 85
    },
    {
      "epoch": 0.009630728743805817,
      "grad_norm": 0.1675027757883072,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0113,
      "step": 86
    },
    {
      "epoch": 0.009742713961757047,
      "grad_norm": 0.10205962508916855,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0108,
      "step": 87
    },
    {
      "epoch": 0.00985469917970828,
      "grad_norm": 0.09269709140062332,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0051,
      "step": 88
    },
    {
      "epoch": 0.00996668439765951,
      "grad_norm": 0.17211325466632843,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0277,
      "step": 89
    },
    {
      "epoch": 0.01007866961561074,
      "grad_norm": 0.4585292935371399,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0204,
      "step": 90
    },
    {
      "epoch": 0.01019065483356197,
      "grad_norm": 0.23112568259239197,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0084,
      "step": 91
    },
    {
      "epoch": 0.0103026400515132,
      "grad_norm": 0.09548697620630264,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0113,
      "step": 92
    },
    {
      "epoch": 0.01041462526946443,
      "grad_norm": 0.10480192303657532,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0196,
      "step": 93
    },
    {
      "epoch": 0.01052661048741566,
      "grad_norm": 0.053521186113357544,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0035,
      "step": 94
    },
    {
      "epoch": 0.010638595705366892,
      "grad_norm": 0.12508662045001984,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0046,
      "step": 95
    },
    {
      "epoch": 0.010750580923318123,
      "grad_norm": 0.07000123709440231,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0089,
      "step": 96
    },
    {
      "epoch": 0.010862566141269353,
      "grad_norm": 0.13927717506885529,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0225,
      "step": 97
    },
    {
      "epoch": 0.010974551359220583,
      "grad_norm": 0.36776211857795715,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0061,
      "step": 98
    },
    {
      "epoch": 0.011086536577171813,
      "grad_norm": 0.11161035299301147,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0117,
      "step": 99
    },
    {
      "epoch": 0.011198521795123043,
      "grad_norm": 0.10862310975790024,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0104,
      "step": 100
    },
    {
      "epoch": 0.011198521795123043,
      "eval_loss": 0.008957763202488422,
      "eval_runtime": 1080.5124,
      "eval_samples_per_second": 13.919,
      "eval_steps_per_second": 3.48,
      "step": 100
    },
    {
      "epoch": 0.011310507013074273,
      "grad_norm": 0.08506631851196289,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.0124,
      "step": 101
    },
    {
      "epoch": 0.011422492231025505,
      "grad_norm": 0.03572741150856018,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0088,
      "step": 102
    },
    {
      "epoch": 0.011534477448976736,
      "grad_norm": 0.028119171038269997,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.0056,
      "step": 103
    },
    {
      "epoch": 0.011646462666927966,
      "grad_norm": 0.030382081866264343,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0051,
      "step": 104
    },
    {
      "epoch": 0.011758447884879196,
      "grad_norm": 0.03446408733725548,
      "learning_rate": 5e-05,
      "loss": 0.0068,
      "step": 105
    },
    {
      "epoch": 0.011870433102830426,
      "grad_norm": 0.03344714641571045,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0051,
      "step": 106
    },
    {
      "epoch": 0.011982418320781656,
      "grad_norm": 0.05783190205693245,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0084,
      "step": 107
    },
    {
      "epoch": 0.012094403538732887,
      "grad_norm": 0.04610677435994148,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0055,
      "step": 108
    },
    {
      "epoch": 0.012206388756684118,
      "grad_norm": 0.04884983226656914,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0043,
      "step": 109
    },
    {
      "epoch": 0.012318373974635349,
      "grad_norm": 0.03212964907288551,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0059,
      "step": 110
    },
    {
      "epoch": 0.012430359192586579,
      "grad_norm": 0.09940595179796219,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0049,
      "step": 111
    },
    {
      "epoch": 0.012542344410537809,
      "grad_norm": 0.029751066118478775,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0022,
      "step": 112
    },
    {
      "epoch": 0.01265432962848904,
      "grad_norm": 0.04463963583111763,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0072,
      "step": 113
    },
    {
      "epoch": 0.01276631484644027,
      "grad_norm": 0.029815711081027985,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0032,
      "step": 114
    },
    {
      "epoch": 0.0128783000643915,
      "grad_norm": 0.04161587730050087,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0126,
      "step": 115
    },
    {
      "epoch": 0.012990285282342732,
      "grad_norm": 0.02149057202041149,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.002,
      "step": 116
    },
    {
      "epoch": 0.013102270500293962,
      "grad_norm": 0.04231660068035126,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0057,
      "step": 117
    },
    {
      "epoch": 0.013214255718245192,
      "grad_norm": 0.08881816267967224,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.005,
      "step": 118
    },
    {
      "epoch": 0.013326240936196422,
      "grad_norm": 0.025332478806376457,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.004,
      "step": 119
    },
    {
      "epoch": 0.013438226154147652,
      "grad_norm": 0.02778369002044201,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0034,
      "step": 120
    },
    {
      "epoch": 0.013550211372098882,
      "grad_norm": 0.04420655220746994,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0071,
      "step": 121
    },
    {
      "epoch": 0.013662196590050113,
      "grad_norm": 0.0295578446239233,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.003,
      "step": 122
    },
    {
      "epoch": 0.013774181808001345,
      "grad_norm": 0.02409888431429863,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0032,
      "step": 123
    },
    {
      "epoch": 0.013886167025952575,
      "grad_norm": 0.022894464433193207,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0024,
      "step": 124
    },
    {
      "epoch": 0.013998152243903805,
      "grad_norm": 0.03507612273097038,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0073,
      "step": 125
    },
    {
      "epoch": 0.014110137461855035,
      "grad_norm": 0.06821553409099579,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0121,
      "step": 126
    },
    {
      "epoch": 0.014222122679806265,
      "grad_norm": 0.055723853409290314,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0103,
      "step": 127
    },
    {
      "epoch": 0.014334107897757496,
      "grad_norm": 0.025588707998394966,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0066,
      "step": 128
    },
    {
      "epoch": 0.014446093115708726,
      "grad_norm": 0.05048364773392677,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0052,
      "step": 129
    },
    {
      "epoch": 0.014558078333659958,
      "grad_norm": 0.03552013263106346,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0095,
      "step": 130
    },
    {
      "epoch": 0.014670063551611188,
      "grad_norm": 0.0784396305680275,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.014,
      "step": 131
    },
    {
      "epoch": 0.014782048769562418,
      "grad_norm": 0.08521043509244919,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0208,
      "step": 132
    },
    {
      "epoch": 0.014894033987513648,
      "grad_norm": 0.0778452605009079,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0096,
      "step": 133
    },
    {
      "epoch": 0.015006019205464878,
      "grad_norm": 0.33984890580177307,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.008,
      "step": 134
    },
    {
      "epoch": 0.015118004423416109,
      "grad_norm": 0.09499168395996094,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0119,
      "step": 135
    },
    {
      "epoch": 0.015229989641367339,
      "grad_norm": 0.14601409435272217,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0145,
      "step": 136
    },
    {
      "epoch": 0.01534197485931857,
      "grad_norm": 0.1081615462899208,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0108,
      "step": 137
    },
    {
      "epoch": 0.015453960077269801,
      "grad_norm": 0.11429034918546677,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0239,
      "step": 138
    },
    {
      "epoch": 0.015565945295221031,
      "grad_norm": 0.04111011326313019,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0084,
      "step": 139
    },
    {
      "epoch": 0.01567793051317226,
      "grad_norm": 0.04043128341436386,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0083,
      "step": 140
    },
    {
      "epoch": 0.015789915731123493,
      "grad_norm": 0.05154617875814438,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0052,
      "step": 141
    },
    {
      "epoch": 0.01590190094907472,
      "grad_norm": 0.08990739285945892,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0066,
      "step": 142
    },
    {
      "epoch": 0.016013886167025954,
      "grad_norm": 0.04778852313756943,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0058,
      "step": 143
    },
    {
      "epoch": 0.016125871384977182,
      "grad_norm": 0.028067700564861298,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0028,
      "step": 144
    },
    {
      "epoch": 0.016237856602928414,
      "grad_norm": 0.08328656852245331,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0133,
      "step": 145
    },
    {
      "epoch": 0.016349841820879642,
      "grad_norm": 0.043928563594818115,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0079,
      "step": 146
    },
    {
      "epoch": 0.016461827038830874,
      "grad_norm": 0.051368650048971176,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.006,
      "step": 147
    },
    {
      "epoch": 0.016573812256782106,
      "grad_norm": 0.03745152801275253,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0047,
      "step": 148
    },
    {
      "epoch": 0.016685797474733335,
      "grad_norm": 0.07638669013977051,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0094,
      "step": 149
    },
    {
      "epoch": 0.016797782692684567,
      "grad_norm": 0.20319393277168274,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0327,
      "step": 150
    },
    {
      "epoch": 0.016797782692684567,
      "eval_loss": 0.007711287587881088,
      "eval_runtime": 1079.213,
      "eval_samples_per_second": 13.936,
      "eval_steps_per_second": 3.484,
      "step": 150
    },
    {
      "epoch": 0.016909767910635795,
      "grad_norm": 0.0725942999124527,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0081,
      "step": 151
    },
    {
      "epoch": 0.017021753128587027,
      "grad_norm": 0.07155165821313858,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0078,
      "step": 152
    },
    {
      "epoch": 0.017133738346538255,
      "grad_norm": 0.046211618930101395,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0049,
      "step": 153
    },
    {
      "epoch": 0.017245723564489487,
      "grad_norm": 0.02759714610874653,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0056,
      "step": 154
    },
    {
      "epoch": 0.01735770878244072,
      "grad_norm": 0.05214079096913338,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0128,
      "step": 155
    },
    {
      "epoch": 0.017469694000391948,
      "grad_norm": 0.035620782524347305,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0042,
      "step": 156
    },
    {
      "epoch": 0.01758167921834318,
      "grad_norm": 0.07333940267562866,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0107,
      "step": 157
    },
    {
      "epoch": 0.017693664436294408,
      "grad_norm": 0.021381674334406853,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0028,
      "step": 158
    },
    {
      "epoch": 0.01780564965424564,
      "grad_norm": 0.030171196907758713,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0058,
      "step": 159
    },
    {
      "epoch": 0.01791763487219687,
      "grad_norm": 0.023903975263237953,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.002,
      "step": 160
    },
    {
      "epoch": 0.0180296200901481,
      "grad_norm": 0.04249025881290436,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0061,
      "step": 161
    },
    {
      "epoch": 0.018141605308099332,
      "grad_norm": 0.037698160856962204,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0048,
      "step": 162
    },
    {
      "epoch": 0.01825359052605056,
      "grad_norm": 0.0229655634611845,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0036,
      "step": 163
    },
    {
      "epoch": 0.018365575744001793,
      "grad_norm": 0.03788759186863899,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0038,
      "step": 164
    },
    {
      "epoch": 0.01847756096195302,
      "grad_norm": 0.027754049748182297,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.005,
      "step": 165
    },
    {
      "epoch": 0.018589546179904253,
      "grad_norm": 0.030709249898791313,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0056,
      "step": 166
    },
    {
      "epoch": 0.01870153139785548,
      "grad_norm": 0.07514915615320206,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0087,
      "step": 167
    },
    {
      "epoch": 0.018813516615806714,
      "grad_norm": 0.07420487701892853,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0043,
      "step": 168
    },
    {
      "epoch": 0.018925501833757945,
      "grad_norm": 0.0662989690899849,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0085,
      "step": 169
    },
    {
      "epoch": 0.019037487051709174,
      "grad_norm": 0.030240537598729134,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0028,
      "step": 170
    },
    {
      "epoch": 0.019149472269660406,
      "grad_norm": 0.03573015332221985,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0049,
      "step": 171
    },
    {
      "epoch": 0.019261457487611634,
      "grad_norm": 0.11944897472858429,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0044,
      "step": 172
    },
    {
      "epoch": 0.019373442705562866,
      "grad_norm": 0.07840321213006973,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0143,
      "step": 173
    },
    {
      "epoch": 0.019485427923514095,
      "grad_norm": 0.07308654487133026,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0082,
      "step": 174
    },
    {
      "epoch": 0.019597413141465327,
      "grad_norm": 0.03043070249259472,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0042,
      "step": 175
    },
    {
      "epoch": 0.01970939835941656,
      "grad_norm": 0.03176096826791763,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0025,
      "step": 176
    },
    {
      "epoch": 0.019821383577367787,
      "grad_norm": 0.09436037391424179,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0124,
      "step": 177
    },
    {
      "epoch": 0.01993336879531902,
      "grad_norm": 0.03768962621688843,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.007,
      "step": 178
    },
    {
      "epoch": 0.020045354013270247,
      "grad_norm": 0.05239730328321457,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0101,
      "step": 179
    },
    {
      "epoch": 0.02015733923122148,
      "grad_norm": 0.06425032764673233,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0062,
      "step": 180
    },
    {
      "epoch": 0.020269324449172708,
      "grad_norm": 0.04876949265599251,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0121,
      "step": 181
    },
    {
      "epoch": 0.02038130966712394,
      "grad_norm": 0.05993237718939781,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0066,
      "step": 182
    },
    {
      "epoch": 0.02049329488507517,
      "grad_norm": 0.07160338759422302,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0146,
      "step": 183
    },
    {
      "epoch": 0.0206052801030264,
      "grad_norm": 0.0497567281126976,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0146,
      "step": 184
    },
    {
      "epoch": 0.020717265320977632,
      "grad_norm": 0.07723034173250198,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0158,
      "step": 185
    },
    {
      "epoch": 0.02082925053892886,
      "grad_norm": 0.05417235195636749,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0101,
      "step": 186
    },
    {
      "epoch": 0.020941235756880092,
      "grad_norm": 0.07909059524536133,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0159,
      "step": 187
    },
    {
      "epoch": 0.02105322097483132,
      "grad_norm": 0.05512155592441559,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0075,
      "step": 188
    },
    {
      "epoch": 0.021165206192782553,
      "grad_norm": 0.05401633307337761,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0164,
      "step": 189
    },
    {
      "epoch": 0.021277191410733785,
      "grad_norm": 0.04546954855322838,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.004,
      "step": 190
    },
    {
      "epoch": 0.021389176628685013,
      "grad_norm": 0.060913074761629105,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0059,
      "step": 191
    },
    {
      "epoch": 0.021501161846636245,
      "grad_norm": 0.05825398117303848,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0132,
      "step": 192
    },
    {
      "epoch": 0.021613147064587473,
      "grad_norm": 0.040474578738212585,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.006,
      "step": 193
    },
    {
      "epoch": 0.021725132282538705,
      "grad_norm": 0.04289264231920242,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0031,
      "step": 194
    },
    {
      "epoch": 0.021837117500489934,
      "grad_norm": 0.030217066407203674,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0036,
      "step": 195
    },
    {
      "epoch": 0.021949102718441166,
      "grad_norm": 0.10896749049425125,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0181,
      "step": 196
    },
    {
      "epoch": 0.022061087936392398,
      "grad_norm": 0.11899552494287491,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0199,
      "step": 197
    },
    {
      "epoch": 0.022173073154343626,
      "grad_norm": 0.12787409126758575,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0385,
      "step": 198
    },
    {
      "epoch": 0.022285058372294858,
      "grad_norm": 0.11491705477237701,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0167,
      "step": 199
    },
    {
      "epoch": 0.022397043590246087,
      "grad_norm": 0.05599415674805641,
      "learning_rate": 0.0,
      "loss": 0.0147,
      "step": 200
    },
    {
      "epoch": 0.022397043590246087,
      "eval_loss": 0.007327286526560783,
      "eval_runtime": 1079.865,
      "eval_samples_per_second": 13.928,
      "eval_steps_per_second": 3.482,
      "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": 2.6776486765658112e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}