{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.7568590350047304,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003784295175023652,
      "grad_norm": 9.78250682237558e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.003784295175023652,
      "eval_loss": 11.5,
      "eval_runtime": 2.0295,
      "eval_samples_per_second": 219.261,
      "eval_steps_per_second": 55.185,
      "step": 1
    },
    {
      "epoch": 0.007568590350047304,
      "grad_norm": 9.904026228468865e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.011352885525070956,
      "grad_norm": 7.818987796781585e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.015137180700094607,
      "grad_norm": 0.00010511968866921961,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.01892147587511826,
      "grad_norm": 0.00011536338570294902,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.02270577105014191,
      "grad_norm": 0.0001178458915092051,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 0.00010308323544450104,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.030274361400189215,
      "grad_norm": 6.367395690176636e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.03405865657521287,
      "grad_norm": 8.491198968840763e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.03784295175023652,
      "grad_norm": 0.00010267038305755705,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.041627246925260174,
      "grad_norm": 0.00013229306205175817,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.04541154210028382,
      "grad_norm": 0.00012802924902644008,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.04919583727530748,
      "grad_norm": 0.00012559750757645816,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 9.502094326307997e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.05676442762535478,
      "grad_norm": 0.0001499613281339407,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.06054872280037843,
      "grad_norm": 0.0001462457876186818,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.06433301797540208,
      "grad_norm": 0.00015152750711422414,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.06811731315042574,
      "grad_norm": 0.000165541612659581,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.07190160832544938,
      "grad_norm": 0.0002030013856710866,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.07568590350047304,
      "grad_norm": 0.00015161379997152835,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 0.00014155736425891519,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.08325449385052035,
      "grad_norm": 0.00020105612929910421,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.08703878902554399,
      "grad_norm": 0.00017488717276137322,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.09082308420056764,
      "grad_norm": 0.00020979033433832228,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0946073793755913,
      "grad_norm": 0.00020764238433912396,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.09839167455061495,
      "grad_norm": 0.00015920169244054705,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.1021759697256386,
      "grad_norm": 0.00019223423441872,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 0.00024585871142335236,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.1097445600756859,
      "grad_norm": 0.0001665399904595688,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.11352885525070956,
      "grad_norm": 0.00028205339913256466,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.1173131504257332,
      "grad_norm": 0.00020623266755137593,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.12109744560075686,
      "grad_norm": 0.00027347024297341704,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.12488174077578051,
      "grad_norm": 0.0003032140957657248,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.12866603595080417,
      "grad_norm": 0.00027241348288953304,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.00020075528300367296,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.13623462630085148,
      "grad_norm": 0.00029309483943507075,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.1400189214758751,
      "grad_norm": 0.0002673635899554938,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.14380321665089876,
      "grad_norm": 0.00023596743994858116,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.14758751182592242,
      "grad_norm": 0.0002282315690536052,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.15137180700094607,
      "grad_norm": 0.00028369197389110923,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.15515610217596973,
      "grad_norm": 0.00032988612656481564,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 0.00029318543965928257,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.16272469252601704,
      "grad_norm": 0.0003325803845655173,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.1665089877010407,
      "grad_norm": 0.000344464264344424,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.17029328287606432,
      "grad_norm": 0.00027373904595151544,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.17407757805108798,
      "grad_norm": 0.000281997345155105,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.17786187322611163,
      "grad_norm": 0.00033239179174415767,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.1816461684011353,
      "grad_norm": 0.0003658597415778786,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": 0.0003921724564861506,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.1892147587511826,
      "grad_norm": 0.00039186759386211634,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.1892147587511826,
      "eval_loss": 11.5,
      "eval_runtime": 2.0044,
      "eval_samples_per_second": 222.006,
      "eval_steps_per_second": 55.876,
      "step": 50
    },
    {
      "epoch": 0.19299905392620625,
      "grad_norm": 0.0003641891526058316,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.1967833491012299,
      "grad_norm": 0.0004078513593412936,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.20056764427625354,
      "grad_norm": 0.00037813378730788827,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.2043519394512772,
      "grad_norm": 0.0004021077184006572,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.20813623462630085,
      "grad_norm": 0.0004532048187684268,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": 0.0005626670899800956,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.21570482497634816,
      "grad_norm": 0.0004953921888954937,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.2194891201513718,
      "grad_norm": 0.0003884559846483171,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.22327341532639547,
      "grad_norm": 0.00035598152317106724,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.22705771050141912,
      "grad_norm": 0.000316378369461745,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.23084200567644275,
      "grad_norm": 0.0004674757947213948,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.2346263008514664,
      "grad_norm": 0.0005434812628664076,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": 0.0006793153006583452,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.24219489120151372,
      "grad_norm": 0.0006305405986495316,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.24597918637653737,
      "grad_norm": 0.0005828177672810853,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.24976348155156103,
      "grad_norm": 0.0006345444708131254,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.2535477767265847,
      "grad_norm": 0.0007474023150280118,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.25733207190160834,
      "grad_norm": 0.0006761687691323459,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.261116367076632,
      "grad_norm": 0.0006341116968542337,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 0.0006614705198444426,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.2686849574266793,
      "grad_norm": 0.0006127587985247374,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.27246925260170296,
      "grad_norm": 0.0006660723011009395,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.27625354777672656,
      "grad_norm": 0.0006217568879947066,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.2800378429517502,
      "grad_norm": 0.0005570882931351662,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.28382213812677387,
      "grad_norm": 0.0007950947619974613,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.2876064333017975,
      "grad_norm": 0.0008010959136299789,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.2913907284768212,
      "grad_norm": 0.0007099746726453304,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.29517502365184484,
      "grad_norm": 0.0006202813819982111,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.2989593188268685,
      "grad_norm": 0.00067554647102952,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.30274361400189215,
      "grad_norm": 0.0006638554623350501,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.3065279091769158,
      "grad_norm": 0.0006468967767432332,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.31031220435193946,
      "grad_norm": 0.0005865691346116364,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.3140964995269631,
      "grad_norm": 0.0006458035786636174,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 0.0007649317849427462,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.3216650898770104,
      "grad_norm": 0.00048125156899914145,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.3254493850520341,
      "grad_norm": 0.0006673912866972387,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.32923368022705773,
      "grad_norm": 0.000619634345639497,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.3330179754020814,
      "grad_norm": 0.0006463839090429246,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.336802270577105,
      "grad_norm": 0.0006557489396072924,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.34058656575212864,
      "grad_norm": 0.0006266234559006989,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.3443708609271523,
      "grad_norm": 0.0006857334519736469,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.34815515610217596,
      "grad_norm": 0.0006297604413703084,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.3519394512771996,
      "grad_norm": 0.0007782838656567037,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.35572374645222327,
      "grad_norm": 0.0006386016611941159,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.3595080416272469,
      "grad_norm": 0.0008345945971086621,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.3632923368022706,
      "grad_norm": 0.0007471011485904455,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.36707663197729423,
      "grad_norm": 0.0007567246211692691,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.3708609271523179,
      "grad_norm": 0.0007825461216270924,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.37464522232734154,
      "grad_norm": 0.0008100302657112479,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.3784295175023652,
      "grad_norm": 0.0008820925140753388,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.3784295175023652,
      "eval_loss": 11.5,
      "eval_runtime": 2.0129,
      "eval_samples_per_second": 221.079,
      "eval_steps_per_second": 55.642,
      "step": 100
    },
    {
      "epoch": 0.38221381267738885,
      "grad_norm": 0.000853542354889214,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.3859981078524125,
      "grad_norm": 0.000911855255253613,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.38978240302743616,
      "grad_norm": 0.000940909783821553,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.3935666982024598,
      "grad_norm": 0.001070856349542737,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 0.0009008296765387058,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.4011352885525071,
      "grad_norm": 0.0009517321595922112,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.40491958372753073,
      "grad_norm": 0.0007018959731794894,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.4087038789025544,
      "grad_norm": 0.000637179531622678,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.41248817407757804,
      "grad_norm": 0.0005228532827459276,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.4162724692526017,
      "grad_norm": 0.0009035984403453767,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.42005676442762535,
      "grad_norm": 0.001067382632754743,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.423841059602649,
      "grad_norm": 0.0008953086799010634,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.42762535477767266,
      "grad_norm": 0.0012180646881461143,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.4314096499526963,
      "grad_norm": 0.0011108440812677145,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.43519394512771997,
      "grad_norm": 0.0011602333979681134,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.4389782403027436,
      "grad_norm": 0.000940683123189956,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.4427625354777673,
      "grad_norm": 0.0009210577700287104,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.44654683065279094,
      "grad_norm": 0.0009672794840298593,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.4503311258278146,
      "grad_norm": 0.0010570696322247386,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.45411542100283825,
      "grad_norm": 0.0007912243600003421,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.45789971617786185,
      "grad_norm": 0.001117298728786409,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.4616840113528855,
      "grad_norm": 0.0007720192079432309,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.46546830652790916,
      "grad_norm": 0.0008820125949569046,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.4692526017029328,
      "grad_norm": 0.0010772289242595434,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.47303689687795647,
      "grad_norm": 0.0009977173758670688,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.4768211920529801,
      "grad_norm": 0.0008594646933488548,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.4806054872280038,
      "grad_norm": 0.0008925504516810179,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.48438978240302744,
      "grad_norm": 0.0008545974851585925,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.4881740775780511,
      "grad_norm": 0.0009071948588825762,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.49195837275307475,
      "grad_norm": 0.0008369744755327702,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.4957426679280984,
      "grad_norm": 0.0007632598280906677,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.49952696310312206,
      "grad_norm": 0.0009875622345134616,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.5033112582781457,
      "grad_norm": 0.0008644148474559188,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.5070955534531694,
      "grad_norm": 0.0008448797161690891,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.510879848628193,
      "grad_norm": 0.0008132528164424002,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.5146641438032167,
      "grad_norm": 0.0009468307252973318,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.5184484389782403,
      "grad_norm": 0.0008375130128115416,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.522232734153264,
      "grad_norm": 0.0008511705091223121,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.5260170293282876,
      "grad_norm": 0.0010542224626988173,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 0.0010171558242291212,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.533585619678335,
      "grad_norm": 0.000864635978359729,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.5373699148533586,
      "grad_norm": 0.0011611199006438255,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.5411542100283823,
      "grad_norm": 0.001131174387410283,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.5449385052034059,
      "grad_norm": 0.000819187902379781,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.5487228003784295,
      "grad_norm": 0.0009330124012194574,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.5525070955534531,
      "grad_norm": 0.0011133438674733043,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.5562913907284768,
      "grad_norm": 0.0008052586927078664,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.5600756859035004,
      "grad_norm": 0.0006740705575793982,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.5638599810785241,
      "grad_norm": 0.0010564974509179592,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.5676442762535477,
      "grad_norm": 0.0010544508695602417,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.5676442762535477,
      "eval_loss": 11.5,
      "eval_runtime": 2.0081,
      "eval_samples_per_second": 221.602,
      "eval_steps_per_second": 55.774,
      "step": 150
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.0012754342751577497,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.575212866603595,
      "grad_norm": 0.001141392975114286,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.5789971617786187,
      "grad_norm": 0.0010432216804474592,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.5827814569536424,
      "grad_norm": 0.0013510590652003884,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.586565752128666,
      "grad_norm": 0.0014704992063343525,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.5903500473036897,
      "grad_norm": 0.001154447323642671,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.5941343424787133,
      "grad_norm": 0.0012737775687128305,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.597918637653737,
      "grad_norm": 0.0007408267119899392,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.6017029328287606,
      "grad_norm": 0.0009956663707271218,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.6054872280037843,
      "grad_norm": 0.0007607248262502253,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.609271523178808,
      "grad_norm": 0.000897994905244559,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.6130558183538316,
      "grad_norm": 0.0012615679297596216,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.6168401135288553,
      "grad_norm": 0.0010080052306875587,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.6206244087038789,
      "grad_norm": 0.0015122926561161876,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.6244087038789026,
      "grad_norm": 0.0010130403097718954,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.6281929990539262,
      "grad_norm": 0.0014554719673469663,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.6319772942289499,
      "grad_norm": 0.0012115767458453774,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.6357615894039735,
      "grad_norm": 0.0010655283695086837,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.6395458845789972,
      "grad_norm": 0.0008749625412747264,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.6433301797540208,
      "grad_norm": 0.0008512308704666793,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.6471144749290445,
      "grad_norm": 0.0008647390059195459,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.6508987701040682,
      "grad_norm": 0.001326821860857308,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.6546830652790918,
      "grad_norm": 0.0009952638065442443,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.6584673604541155,
      "grad_norm": 0.001162377535365522,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.6622516556291391,
      "grad_norm": 0.0008263836498372257,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.6660359508041628,
      "grad_norm": 0.0009578029857948422,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.6698202459791863,
      "grad_norm": 0.0010864919750019908,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.67360454115421,
      "grad_norm": 0.0009977552108466625,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.6773888363292336,
      "grad_norm": 0.0011743983486667275,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.6811731315042573,
      "grad_norm": 0.0007461576024070382,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.684957426679281,
      "grad_norm": 0.0007151532336138189,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.6887417218543046,
      "grad_norm": 0.000813777674920857,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.6925260170293283,
      "grad_norm": 0.0008772213477641344,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.6963103122043519,
      "grad_norm": 0.0010371104581281543,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.7000946073793756,
      "grad_norm": 0.0010703636799007654,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.7038789025543992,
      "grad_norm": 0.0008484815480187535,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.7076631977294229,
      "grad_norm": 0.0008171134977601469,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.7114474929044465,
      "grad_norm": 0.0010098969796672463,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.7152317880794702,
      "grad_norm": 0.0007768998621031642,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.7190160832544938,
      "grad_norm": 0.0008353094453923404,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.7228003784295175,
      "grad_norm": 0.0008436258067376912,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.7265846736045412,
      "grad_norm": 0.0009303117985837162,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.7303689687795648,
      "grad_norm": 0.0008698689634911716,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.7341532639545885,
      "grad_norm": 0.0013953595189377666,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.7379375591296121,
      "grad_norm": 0.0010683886939659715,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.7417218543046358,
      "grad_norm": 0.0009650185238569975,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.7455061494796594,
      "grad_norm": 0.0008142840233631432,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.7492904446546831,
      "grad_norm": 0.000940751051530242,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.7530747398297067,
      "grad_norm": 0.0010417766170576215,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.7568590350047304,
      "grad_norm": 0.000997866503894329,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.7568590350047304,
      "eval_loss": 11.5,
      "eval_runtime": 2.0536,
      "eval_samples_per_second": 216.69,
      "eval_steps_per_second": 54.538,
      "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32158462771200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}