{
  "best_metric": 0.5247341990470886,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.11245431543435479,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000562271577171774,
      "grad_norm": 0.8870972394943237,
      "learning_rate": 1e-05,
      "loss": 0.9523,
      "step": 1
    },
    {
      "epoch": 0.000562271577171774,
      "eval_loss": 1.107572078704834,
      "eval_runtime": 59.7064,
      "eval_samples_per_second": 50.162,
      "eval_steps_per_second": 12.545,
      "step": 1
    },
    {
      "epoch": 0.001124543154343548,
      "grad_norm": 1.1441730260849,
      "learning_rate": 2e-05,
      "loss": 0.9678,
      "step": 2
    },
    {
      "epoch": 0.0016868147315153219,
      "grad_norm": 1.0659875869750977,
      "learning_rate": 3e-05,
      "loss": 0.9378,
      "step": 3
    },
    {
      "epoch": 0.002249086308687096,
      "grad_norm": 1.2558374404907227,
      "learning_rate": 4e-05,
      "loss": 1.0561,
      "step": 4
    },
    {
      "epoch": 0.0028113578858588698,
      "grad_norm": 0.9634308218955994,
      "learning_rate": 5e-05,
      "loss": 0.9144,
      "step": 5
    },
    {
      "epoch": 0.0033736294630306437,
      "grad_norm": 1.018953561782837,
      "learning_rate": 6e-05,
      "loss": 0.9872,
      "step": 6
    },
    {
      "epoch": 0.003935901040202418,
      "grad_norm": 1.0821255445480347,
      "learning_rate": 7e-05,
      "loss": 0.9199,
      "step": 7
    },
    {
      "epoch": 0.004498172617374192,
      "grad_norm": 0.9887213706970215,
      "learning_rate": 8e-05,
      "loss": 0.9044,
      "step": 8
    },
    {
      "epoch": 0.005060444194545966,
      "grad_norm": 0.8941230177879333,
      "learning_rate": 9e-05,
      "loss": 0.8369,
      "step": 9
    },
    {
      "epoch": 0.0056227157717177395,
      "grad_norm": 0.9835636019706726,
      "learning_rate": 0.0001,
      "loss": 0.8461,
      "step": 10
    },
    {
      "epoch": 0.006184987348889514,
      "grad_norm": 1.127853274345398,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7877,
      "step": 11
    },
    {
      "epoch": 0.0067472589260612875,
      "grad_norm": 0.9496690034866333,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7894,
      "step": 12
    },
    {
      "epoch": 0.007309530503233062,
      "grad_norm": 1.1143202781677246,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8198,
      "step": 13
    },
    {
      "epoch": 0.007871802080404836,
      "grad_norm": 0.9394596219062805,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7689,
      "step": 14
    },
    {
      "epoch": 0.00843407365757661,
      "grad_norm": 0.8165773153305054,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.691,
      "step": 15
    },
    {
      "epoch": 0.008996345234748383,
      "grad_norm": 0.792168378829956,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7543,
      "step": 16
    },
    {
      "epoch": 0.009558616811920157,
      "grad_norm": 0.7858337163925171,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.723,
      "step": 17
    },
    {
      "epoch": 0.010120888389091932,
      "grad_norm": 0.8022664785385132,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6786,
      "step": 18
    },
    {
      "epoch": 0.010683159966263706,
      "grad_norm": 0.7736492156982422,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7015,
      "step": 19
    },
    {
      "epoch": 0.011245431543435479,
      "grad_norm": 0.6988972425460815,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.5771,
      "step": 20
    },
    {
      "epoch": 0.011807703120607253,
      "grad_norm": 0.6822065114974976,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7124,
      "step": 21
    },
    {
      "epoch": 0.012369974697779028,
      "grad_norm": 0.8337672352790833,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8046,
      "step": 22
    },
    {
      "epoch": 0.012932246274950801,
      "grad_norm": 0.6891354322433472,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6574,
      "step": 23
    },
    {
      "epoch": 0.013494517852122575,
      "grad_norm": 0.7397004961967468,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5949,
      "step": 24
    },
    {
      "epoch": 0.014056789429294348,
      "grad_norm": 0.7781254053115845,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6194,
      "step": 25
    },
    {
      "epoch": 0.014619061006466124,
      "grad_norm": 0.751171886920929,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6362,
      "step": 26
    },
    {
      "epoch": 0.015181332583637897,
      "grad_norm": 0.7256805896759033,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5344,
      "step": 27
    },
    {
      "epoch": 0.015743604160809672,
      "grad_norm": 0.7365525364875793,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6177,
      "step": 28
    },
    {
      "epoch": 0.016305875737981444,
      "grad_norm": 0.8026912212371826,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6926,
      "step": 29
    },
    {
      "epoch": 0.01686814731515322,
      "grad_norm": 0.803772509098053,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.522,
      "step": 30
    },
    {
      "epoch": 0.01743041889232499,
      "grad_norm": 0.8292425870895386,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.5395,
      "step": 31
    },
    {
      "epoch": 0.017992690469496767,
      "grad_norm": 0.7604405283927917,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4834,
      "step": 32
    },
    {
      "epoch": 0.018554962046668542,
      "grad_norm": 0.7932441234588623,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5747,
      "step": 33
    },
    {
      "epoch": 0.019117233623840314,
      "grad_norm": 1.0574491024017334,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5965,
      "step": 34
    },
    {
      "epoch": 0.01967950520101209,
      "grad_norm": 0.7766584753990173,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5021,
      "step": 35
    },
    {
      "epoch": 0.020241776778183864,
      "grad_norm": 0.8104745745658875,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.4736,
      "step": 36
    },
    {
      "epoch": 0.020804048355355636,
      "grad_norm": 0.7348149418830872,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5549,
      "step": 37
    },
    {
      "epoch": 0.02136631993252741,
      "grad_norm": 0.6767603158950806,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4464,
      "step": 38
    },
    {
      "epoch": 0.021928591509699186,
      "grad_norm": 0.8472415804862976,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4209,
      "step": 39
    },
    {
      "epoch": 0.022490863086870958,
      "grad_norm": 0.790913462638855,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4569,
      "step": 40
    },
    {
      "epoch": 0.023053134664042733,
      "grad_norm": 0.8025915622711182,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5249,
      "step": 41
    },
    {
      "epoch": 0.023615406241214505,
      "grad_norm": 0.9174462556838989,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.549,
      "step": 42
    },
    {
      "epoch": 0.02417767781838628,
      "grad_norm": 0.8765096664428711,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.5123,
      "step": 43
    },
    {
      "epoch": 0.024739949395558056,
      "grad_norm": 0.9210652709007263,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.463,
      "step": 44
    },
    {
      "epoch": 0.025302220972729828,
      "grad_norm": 0.9138442277908325,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5433,
      "step": 45
    },
    {
      "epoch": 0.025864492549901603,
      "grad_norm": 1.0541437864303589,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6736,
      "step": 46
    },
    {
      "epoch": 0.026426764127073378,
      "grad_norm": 0.9844223856925964,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5784,
      "step": 47
    },
    {
      "epoch": 0.02698903570424515,
      "grad_norm": 1.1260919570922852,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4984,
      "step": 48
    },
    {
      "epoch": 0.027551307281416925,
      "grad_norm": 1.2804145812988281,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7973,
      "step": 49
    },
    {
      "epoch": 0.028113578858588697,
      "grad_norm": 2.1743338108062744,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7987,
      "step": 50
    },
    {
      "epoch": 0.028113578858588697,
      "eval_loss": 0.6958135962486267,
      "eval_runtime": 59.8325,
      "eval_samples_per_second": 50.056,
      "eval_steps_per_second": 12.518,
      "step": 50
    },
    {
      "epoch": 0.028675850435760472,
      "grad_norm": 1.5660128593444824,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8322,
      "step": 51
    },
    {
      "epoch": 0.029238122012932247,
      "grad_norm": 1.4599494934082031,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8316,
      "step": 52
    },
    {
      "epoch": 0.02980039359010402,
      "grad_norm": 1.3459869623184204,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8507,
      "step": 53
    },
    {
      "epoch": 0.030362665167275794,
      "grad_norm": 0.9147264957427979,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7286,
      "step": 54
    },
    {
      "epoch": 0.03092493674444757,
      "grad_norm": 0.7140026092529297,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6204,
      "step": 55
    },
    {
      "epoch": 0.031487208321619345,
      "grad_norm": 0.6204879283905029,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6276,
      "step": 56
    },
    {
      "epoch": 0.03204947989879112,
      "grad_norm": 0.6053904294967651,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7305,
      "step": 57
    },
    {
      "epoch": 0.03261175147596289,
      "grad_norm": 0.61043781042099,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.587,
      "step": 58
    },
    {
      "epoch": 0.03317402305313467,
      "grad_norm": 0.6404963731765747,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6157,
      "step": 59
    },
    {
      "epoch": 0.03373629463030644,
      "grad_norm": 0.6467033624649048,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6623,
      "step": 60
    },
    {
      "epoch": 0.03429856620747821,
      "grad_norm": 0.6869019865989685,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6924,
      "step": 61
    },
    {
      "epoch": 0.03486083778464998,
      "grad_norm": 0.5716145634651184,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5922,
      "step": 62
    },
    {
      "epoch": 0.03542310936182176,
      "grad_norm": 0.6270085573196411,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5984,
      "step": 63
    },
    {
      "epoch": 0.03598538093899353,
      "grad_norm": 0.5876100659370422,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.681,
      "step": 64
    },
    {
      "epoch": 0.036547652516165305,
      "grad_norm": 0.5948300361633301,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6063,
      "step": 65
    },
    {
      "epoch": 0.037109924093337084,
      "grad_norm": 0.5773902535438538,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5906,
      "step": 66
    },
    {
      "epoch": 0.037672195670508855,
      "grad_norm": 0.6069343090057373,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6573,
      "step": 67
    },
    {
      "epoch": 0.03823446724768063,
      "grad_norm": 0.6221294403076172,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6639,
      "step": 68
    },
    {
      "epoch": 0.038796738824852406,
      "grad_norm": 0.6587129235267639,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5938,
      "step": 69
    },
    {
      "epoch": 0.03935901040202418,
      "grad_norm": 0.6319950819015503,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5851,
      "step": 70
    },
    {
      "epoch": 0.03992128197919595,
      "grad_norm": 0.6147965788841248,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5482,
      "step": 71
    },
    {
      "epoch": 0.04048355355636773,
      "grad_norm": 0.6681365966796875,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6845,
      "step": 72
    },
    {
      "epoch": 0.0410458251335395,
      "grad_norm": 0.6282846331596375,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.622,
      "step": 73
    },
    {
      "epoch": 0.04160809671071127,
      "grad_norm": 0.5861257314682007,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5213,
      "step": 74
    },
    {
      "epoch": 0.04217036828788305,
      "grad_norm": 0.6206960678100586,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4958,
      "step": 75
    },
    {
      "epoch": 0.04273263986505482,
      "grad_norm": 0.6047387719154358,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5484,
      "step": 76
    },
    {
      "epoch": 0.043294911442226594,
      "grad_norm": 0.7109338045120239,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6393,
      "step": 77
    },
    {
      "epoch": 0.04385718301939837,
      "grad_norm": 0.5840567350387573,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.496,
      "step": 78
    },
    {
      "epoch": 0.044419454596570145,
      "grad_norm": 0.647214412689209,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4773,
      "step": 79
    },
    {
      "epoch": 0.044981726173741916,
      "grad_norm": 0.6729691624641418,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5419,
      "step": 80
    },
    {
      "epoch": 0.04554399775091369,
      "grad_norm": 0.6655755043029785,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5312,
      "step": 81
    },
    {
      "epoch": 0.04610626932808547,
      "grad_norm": 0.627923309803009,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4561,
      "step": 82
    },
    {
      "epoch": 0.04666854090525724,
      "grad_norm": 0.6345230937004089,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4913,
      "step": 83
    },
    {
      "epoch": 0.04723081248242901,
      "grad_norm": 0.6424160003662109,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4937,
      "step": 84
    },
    {
      "epoch": 0.04779308405960079,
      "grad_norm": 0.6213027834892273,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4338,
      "step": 85
    },
    {
      "epoch": 0.04835535563677256,
      "grad_norm": 0.604399561882019,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4527,
      "step": 86
    },
    {
      "epoch": 0.04891762721394433,
      "grad_norm": 0.6617149114608765,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.4574,
      "step": 87
    },
    {
      "epoch": 0.04947989879111611,
      "grad_norm": 0.6691566705703735,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3966,
      "step": 88
    },
    {
      "epoch": 0.05004217036828788,
      "grad_norm": 0.6739932298660278,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5177,
      "step": 89
    },
    {
      "epoch": 0.050604441945459655,
      "grad_norm": 0.7830292582511902,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.479,
      "step": 90
    },
    {
      "epoch": 0.051166713522631434,
      "grad_norm": 0.6691083312034607,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.4358,
      "step": 91
    },
    {
      "epoch": 0.051728985099803206,
      "grad_norm": 0.7348050475120544,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4713,
      "step": 92
    },
    {
      "epoch": 0.05229125667697498,
      "grad_norm": 0.8727810382843018,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5403,
      "step": 93
    },
    {
      "epoch": 0.052853528254146756,
      "grad_norm": 0.749163806438446,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5049,
      "step": 94
    },
    {
      "epoch": 0.05341579983131853,
      "grad_norm": 0.8657059073448181,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6212,
      "step": 95
    },
    {
      "epoch": 0.0539780714084903,
      "grad_norm": 0.7128204107284546,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5169,
      "step": 96
    },
    {
      "epoch": 0.05454034298566207,
      "grad_norm": 0.8680071830749512,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.605,
      "step": 97
    },
    {
      "epoch": 0.05510261456283385,
      "grad_norm": 0.9061098694801331,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5782,
      "step": 98
    },
    {
      "epoch": 0.05566488614000562,
      "grad_norm": 1.247826099395752,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6888,
      "step": 99
    },
    {
      "epoch": 0.056227157717177394,
      "grad_norm": 1.9044570922851562,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.4891,
      "step": 100
    },
    {
      "epoch": 0.056227157717177394,
      "eval_loss": 0.5716207027435303,
      "eval_runtime": 59.9043,
      "eval_samples_per_second": 49.996,
      "eval_steps_per_second": 12.503,
      "step": 100
    },
    {
      "epoch": 0.05678942929434917,
      "grad_norm": 0.7775861024856567,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7563,
      "step": 101
    },
    {
      "epoch": 0.057351700871520944,
      "grad_norm": 0.7070241570472717,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.6334,
      "step": 102
    },
    {
      "epoch": 0.057913972448692716,
      "grad_norm": 0.6820622086524963,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7176,
      "step": 103
    },
    {
      "epoch": 0.058476244025864495,
      "grad_norm": 0.7440178990364075,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7398,
      "step": 104
    },
    {
      "epoch": 0.059038515603036266,
      "grad_norm": 0.6645485162734985,
      "learning_rate": 5e-05,
      "loss": 0.6348,
      "step": 105
    },
    {
      "epoch": 0.05960078718020804,
      "grad_norm": 0.6214795708656311,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7261,
      "step": 106
    },
    {
      "epoch": 0.06016305875737982,
      "grad_norm": 0.5442237854003906,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6556,
      "step": 107
    },
    {
      "epoch": 0.06072533033455159,
      "grad_norm": 0.5743553042411804,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.5856,
      "step": 108
    },
    {
      "epoch": 0.06128760191172336,
      "grad_norm": 0.5348811745643616,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6627,
      "step": 109
    },
    {
      "epoch": 0.06184987348889514,
      "grad_norm": 0.5052286982536316,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5699,
      "step": 110
    },
    {
      "epoch": 0.06241214506606691,
      "grad_norm": 0.5367642045021057,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5892,
      "step": 111
    },
    {
      "epoch": 0.06297441664323869,
      "grad_norm": 0.5493039488792419,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.5932,
      "step": 112
    },
    {
      "epoch": 0.06353668822041046,
      "grad_norm": 0.5489454865455627,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6242,
      "step": 113
    },
    {
      "epoch": 0.06409895979758223,
      "grad_norm": 0.5847439765930176,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5463,
      "step": 114
    },
    {
      "epoch": 0.064661231374754,
      "grad_norm": 0.5660171508789062,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.555,
      "step": 115
    },
    {
      "epoch": 0.06522350295192578,
      "grad_norm": 0.6027414798736572,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.613,
      "step": 116
    },
    {
      "epoch": 0.06578577452909755,
      "grad_norm": 0.5457308888435364,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5913,
      "step": 117
    },
    {
      "epoch": 0.06634804610626933,
      "grad_norm": 0.569071888923645,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.552,
      "step": 118
    },
    {
      "epoch": 0.0669103176834411,
      "grad_norm": 0.5578380227088928,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5452,
      "step": 119
    },
    {
      "epoch": 0.06747258926061288,
      "grad_norm": 0.6006876826286316,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5783,
      "step": 120
    },
    {
      "epoch": 0.06803486083778465,
      "grad_norm": 0.5989083051681519,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.508,
      "step": 121
    },
    {
      "epoch": 0.06859713241495642,
      "grad_norm": 0.6157553791999817,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6057,
      "step": 122
    },
    {
      "epoch": 0.0691594039921282,
      "grad_norm": 0.5901184678077698,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.565,
      "step": 123
    },
    {
      "epoch": 0.06972167556929997,
      "grad_norm": 0.6007724404335022,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5337,
      "step": 124
    },
    {
      "epoch": 0.07028394714647175,
      "grad_norm": 0.5643191337585449,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4922,
      "step": 125
    },
    {
      "epoch": 0.07084621872364352,
      "grad_norm": 0.6419527530670166,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6315,
      "step": 126
    },
    {
      "epoch": 0.0714084903008153,
      "grad_norm": 0.5710258483886719,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4938,
      "step": 127
    },
    {
      "epoch": 0.07197076187798707,
      "grad_norm": 0.6225060820579529,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5102,
      "step": 128
    },
    {
      "epoch": 0.07253303345515884,
      "grad_norm": 0.6491336822509766,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6207,
      "step": 129
    },
    {
      "epoch": 0.07309530503233061,
      "grad_norm": 0.5573411583900452,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4081,
      "step": 130
    },
    {
      "epoch": 0.0736575766095024,
      "grad_norm": 0.618259072303772,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4303,
      "step": 131
    },
    {
      "epoch": 0.07421984818667417,
      "grad_norm": 0.6377222537994385,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.4452,
      "step": 132
    },
    {
      "epoch": 0.07478211976384594,
      "grad_norm": 0.6078547835350037,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.4103,
      "step": 133
    },
    {
      "epoch": 0.07534439134101771,
      "grad_norm": 0.7271940112113953,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5544,
      "step": 134
    },
    {
      "epoch": 0.07590666291818948,
      "grad_norm": 0.6526171565055847,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4958,
      "step": 135
    },
    {
      "epoch": 0.07646893449536125,
      "grad_norm": 0.6204633116722107,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3987,
      "step": 136
    },
    {
      "epoch": 0.07703120607253304,
      "grad_norm": 0.6735699772834778,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.4391,
      "step": 137
    },
    {
      "epoch": 0.07759347764970481,
      "grad_norm": 0.6303725838661194,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3551,
      "step": 138
    },
    {
      "epoch": 0.07815574922687658,
      "grad_norm": 0.6666901111602783,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4152,
      "step": 139
    },
    {
      "epoch": 0.07871802080404836,
      "grad_norm": 0.6355788707733154,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3795,
      "step": 140
    },
    {
      "epoch": 0.07928029238122013,
      "grad_norm": 0.6431430578231812,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3998,
      "step": 141
    },
    {
      "epoch": 0.0798425639583919,
      "grad_norm": 0.6605325937271118,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3902,
      "step": 142
    },
    {
      "epoch": 0.08040483553556367,
      "grad_norm": 0.7479000687599182,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.4297,
      "step": 143
    },
    {
      "epoch": 0.08096710711273546,
      "grad_norm": 0.722800612449646,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4269,
      "step": 144
    },
    {
      "epoch": 0.08152937868990723,
      "grad_norm": 0.8064738512039185,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5651,
      "step": 145
    },
    {
      "epoch": 0.082091650267079,
      "grad_norm": 0.740565299987793,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.4903,
      "step": 146
    },
    {
      "epoch": 0.08265392184425077,
      "grad_norm": 0.7825525999069214,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5134,
      "step": 147
    },
    {
      "epoch": 0.08321619342142254,
      "grad_norm": 0.898603081703186,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.561,
      "step": 148
    },
    {
      "epoch": 0.08377846499859432,
      "grad_norm": 1.0361489057540894,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6464,
      "step": 149
    },
    {
      "epoch": 0.0843407365757661,
      "grad_norm": 1.2245209217071533,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3979,
      "step": 150
    },
    {
      "epoch": 0.0843407365757661,
      "eval_loss": 0.530295193195343,
      "eval_runtime": 59.9126,
      "eval_samples_per_second": 49.989,
      "eval_steps_per_second": 12.502,
      "step": 150
    },
    {
      "epoch": 0.08490300815293787,
      "grad_norm": 0.4857068359851837,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6079,
      "step": 151
    },
    {
      "epoch": 0.08546527973010964,
      "grad_norm": 0.5494247674942017,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6614,
      "step": 152
    },
    {
      "epoch": 0.08602755130728142,
      "grad_norm": 0.5458753108978271,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6374,
      "step": 153
    },
    {
      "epoch": 0.08658982288445319,
      "grad_norm": 0.5371202230453491,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6086,
      "step": 154
    },
    {
      "epoch": 0.08715209446162496,
      "grad_norm": 0.5722675323486328,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6632,
      "step": 155
    },
    {
      "epoch": 0.08771436603879675,
      "grad_norm": 0.5224986672401428,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5738,
      "step": 156
    },
    {
      "epoch": 0.08827663761596852,
      "grad_norm": 0.559775173664093,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6058,
      "step": 157
    },
    {
      "epoch": 0.08883890919314029,
      "grad_norm": 0.5165976881980896,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5579,
      "step": 158
    },
    {
      "epoch": 0.08940118077031206,
      "grad_norm": 0.7383790016174316,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.6134,
      "step": 159
    },
    {
      "epoch": 0.08996345234748383,
      "grad_norm": 0.5579349398612976,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5939,
      "step": 160
    },
    {
      "epoch": 0.0905257239246556,
      "grad_norm": 0.5869385600090027,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.6348,
      "step": 161
    },
    {
      "epoch": 0.09108799550182738,
      "grad_norm": 0.5919713973999023,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.619,
      "step": 162
    },
    {
      "epoch": 0.09165026707899916,
      "grad_norm": 0.5580396056175232,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.618,
      "step": 163
    },
    {
      "epoch": 0.09221253865617093,
      "grad_norm": 0.5197457671165466,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4822,
      "step": 164
    },
    {
      "epoch": 0.0927748102333427,
      "grad_norm": 0.5393493175506592,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.519,
      "step": 165
    },
    {
      "epoch": 0.09333708181051448,
      "grad_norm": 0.5727958083152771,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.6035,
      "step": 166
    },
    {
      "epoch": 0.09389935338768625,
      "grad_norm": 0.5885754227638245,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.5605,
      "step": 167
    },
    {
      "epoch": 0.09446162496485802,
      "grad_norm": 0.5755364894866943,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5669,
      "step": 168
    },
    {
      "epoch": 0.0950238965420298,
      "grad_norm": 0.5090360045433044,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4508,
      "step": 169
    },
    {
      "epoch": 0.09558616811920158,
      "grad_norm": 0.5838190317153931,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5376,
      "step": 170
    },
    {
      "epoch": 0.09614843969637335,
      "grad_norm": 0.6128039360046387,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6073,
      "step": 171
    },
    {
      "epoch": 0.09671071127354512,
      "grad_norm": 0.6178162693977356,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6,
      "step": 172
    },
    {
      "epoch": 0.0972729828507169,
      "grad_norm": 0.6122710108757019,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.5539,
      "step": 173
    },
    {
      "epoch": 0.09783525442788867,
      "grad_norm": 0.5587270855903625,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4803,
      "step": 174
    },
    {
      "epoch": 0.09839752600506045,
      "grad_norm": 0.6263428926467896,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5261,
      "step": 175
    },
    {
      "epoch": 0.09895979758223222,
      "grad_norm": 0.5471329689025879,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4837,
      "step": 176
    },
    {
      "epoch": 0.099522069159404,
      "grad_norm": 0.6511420011520386,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.5627,
      "step": 177
    },
    {
      "epoch": 0.10008434073657577,
      "grad_norm": 0.5977452397346497,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4446,
      "step": 178
    },
    {
      "epoch": 0.10064661231374754,
      "grad_norm": 0.6474230885505676,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.535,
      "step": 179
    },
    {
      "epoch": 0.10120888389091931,
      "grad_norm": 0.6138046979904175,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.4922,
      "step": 180
    },
    {
      "epoch": 0.10177115546809108,
      "grad_norm": 0.6152907013893127,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.4582,
      "step": 181
    },
    {
      "epoch": 0.10233342704526287,
      "grad_norm": 0.5887395739555359,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.3995,
      "step": 182
    },
    {
      "epoch": 0.10289569862243464,
      "grad_norm": 0.6919886469841003,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.4678,
      "step": 183
    },
    {
      "epoch": 0.10345797019960641,
      "grad_norm": 0.6122342944145203,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.4434,
      "step": 184
    },
    {
      "epoch": 0.10402024177677818,
      "grad_norm": 0.6081031560897827,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.423,
      "step": 185
    },
    {
      "epoch": 0.10458251335394995,
      "grad_norm": 0.6493433713912964,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.4513,
      "step": 186
    },
    {
      "epoch": 0.10514478493112173,
      "grad_norm": 0.686668872833252,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.4484,
      "step": 187
    },
    {
      "epoch": 0.10570705650829351,
      "grad_norm": 0.7016839385032654,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.4649,
      "step": 188
    },
    {
      "epoch": 0.10626932808546528,
      "grad_norm": 0.6165745854377747,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3497,
      "step": 189
    },
    {
      "epoch": 0.10683159966263706,
      "grad_norm": 0.6698880791664124,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.4043,
      "step": 190
    },
    {
      "epoch": 0.10739387123980883,
      "grad_norm": 0.734394907951355,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.4738,
      "step": 191
    },
    {
      "epoch": 0.1079561428169806,
      "grad_norm": 0.7705575227737427,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4446,
      "step": 192
    },
    {
      "epoch": 0.10851841439415237,
      "grad_norm": 0.703666090965271,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3636,
      "step": 193
    },
    {
      "epoch": 0.10908068597132414,
      "grad_norm": 0.82736736536026,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.4856,
      "step": 194
    },
    {
      "epoch": 0.10964295754849593,
      "grad_norm": 0.7943589091300964,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.5056,
      "step": 195
    },
    {
      "epoch": 0.1102052291256677,
      "grad_norm": 0.7843173146247864,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4854,
      "step": 196
    },
    {
      "epoch": 0.11076750070283947,
      "grad_norm": 0.8076313734054565,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5211,
      "step": 197
    },
    {
      "epoch": 0.11132977228001124,
      "grad_norm": 1.0546931028366089,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.682,
      "step": 198
    },
    {
      "epoch": 0.11189204385718302,
      "grad_norm": 0.8931059837341309,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.523,
      "step": 199
    },
    {
      "epoch": 0.11245431543435479,
      "grad_norm": 1.3648707866668701,
      "learning_rate": 0.0,
      "loss": 0.5686,
      "step": 200
    },
    {
      "epoch": 0.11245431543435479,
      "eval_loss": 0.5247341990470886,
      "eval_runtime": 59.9254,
      "eval_samples_per_second": 49.979,
      "eval_steps_per_second": 12.499,
      "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": 4.26629570494464e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}