{
  "best_metric": 0.19928720593452454,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.5706134094151213,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0028530670470756064,
      "grad_norm": 0.8756007552146912,
      "learning_rate": 1e-05,
      "loss": 0.677,
      "step": 1
    },
    {
      "epoch": 0.0028530670470756064,
      "eval_loss": 1.1452142000198364,
      "eval_runtime": 50.1562,
      "eval_samples_per_second": 11.763,
      "eval_steps_per_second": 2.951,
      "step": 1
    },
    {
      "epoch": 0.005706134094151213,
      "grad_norm": 0.8957522511482239,
      "learning_rate": 2e-05,
      "loss": 0.8995,
      "step": 2
    },
    {
      "epoch": 0.008559201141226819,
      "grad_norm": 0.740806519985199,
      "learning_rate": 3e-05,
      "loss": 0.6431,
      "step": 3
    },
    {
      "epoch": 0.011412268188302425,
      "grad_norm": 0.751032292842865,
      "learning_rate": 4e-05,
      "loss": 0.7192,
      "step": 4
    },
    {
      "epoch": 0.014265335235378032,
      "grad_norm": 0.9655280709266663,
      "learning_rate": 5e-05,
      "loss": 0.7923,
      "step": 5
    },
    {
      "epoch": 0.017118402282453638,
      "grad_norm": 0.6791680455207825,
      "learning_rate": 6e-05,
      "loss": 0.7613,
      "step": 6
    },
    {
      "epoch": 0.019971469329529243,
      "grad_norm": 0.6007524132728577,
      "learning_rate": 7e-05,
      "loss": 0.7274,
      "step": 7
    },
    {
      "epoch": 0.02282453637660485,
      "grad_norm": 0.5211865901947021,
      "learning_rate": 8e-05,
      "loss": 0.5881,
      "step": 8
    },
    {
      "epoch": 0.025677603423680456,
      "grad_norm": 0.7025548815727234,
      "learning_rate": 9e-05,
      "loss": 0.5988,
      "step": 9
    },
    {
      "epoch": 0.028530670470756064,
      "grad_norm": 0.7584392428398132,
      "learning_rate": 0.0001,
      "loss": 0.9579,
      "step": 10
    },
    {
      "epoch": 0.03138373751783167,
      "grad_norm": 0.6044459939002991,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7518,
      "step": 11
    },
    {
      "epoch": 0.034236804564907276,
      "grad_norm": 0.7533259391784668,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.0634,
      "step": 12
    },
    {
      "epoch": 0.037089871611982884,
      "grad_norm": 0.687552809715271,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.794,
      "step": 13
    },
    {
      "epoch": 0.039942938659058486,
      "grad_norm": 0.5266788005828857,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7025,
      "step": 14
    },
    {
      "epoch": 0.042796005706134094,
      "grad_norm": 0.7193592190742493,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8969,
      "step": 15
    },
    {
      "epoch": 0.0456490727532097,
      "grad_norm": 0.725236713886261,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0125,
      "step": 16
    },
    {
      "epoch": 0.04850213980028531,
      "grad_norm": 0.6242086291313171,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8354,
      "step": 17
    },
    {
      "epoch": 0.05135520684736091,
      "grad_norm": 0.8843884468078613,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8988,
      "step": 18
    },
    {
      "epoch": 0.05420827389443652,
      "grad_norm": 0.7039507627487183,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8115,
      "step": 19
    },
    {
      "epoch": 0.05706134094151213,
      "grad_norm": 0.6812806725502014,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9041,
      "step": 20
    },
    {
      "epoch": 0.05991440798858773,
      "grad_norm": 0.6009320020675659,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6769,
      "step": 21
    },
    {
      "epoch": 0.06276747503566334,
      "grad_norm": 0.784395694732666,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.98,
      "step": 22
    },
    {
      "epoch": 0.06562054208273894,
      "grad_norm": 0.7439515590667725,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7197,
      "step": 23
    },
    {
      "epoch": 0.06847360912981455,
      "grad_norm": 0.734542727470398,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9043,
      "step": 24
    },
    {
      "epoch": 0.07132667617689016,
      "grad_norm": 0.5721388459205627,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8392,
      "step": 25
    },
    {
      "epoch": 0.07417974322396577,
      "grad_norm": 0.7967005968093872,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9263,
      "step": 26
    },
    {
      "epoch": 0.07703281027104136,
      "grad_norm": 0.9092724919319153,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9755,
      "step": 27
    },
    {
      "epoch": 0.07988587731811697,
      "grad_norm": 0.8824110627174377,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.999,
      "step": 28
    },
    {
      "epoch": 0.08273894436519258,
      "grad_norm": 0.8025414943695068,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8982,
      "step": 29
    },
    {
      "epoch": 0.08559201141226819,
      "grad_norm": 0.7752879858016968,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9082,
      "step": 30
    },
    {
      "epoch": 0.0884450784593438,
      "grad_norm": 0.8524616956710815,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1455,
      "step": 31
    },
    {
      "epoch": 0.0912981455064194,
      "grad_norm": 0.8570223450660706,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9474,
      "step": 32
    },
    {
      "epoch": 0.09415121255349501,
      "grad_norm": 0.7974048256874084,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8442,
      "step": 33
    },
    {
      "epoch": 0.09700427960057062,
      "grad_norm": 0.9929215312004089,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9005,
      "step": 34
    },
    {
      "epoch": 0.09985734664764621,
      "grad_norm": 1.1373854875564575,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8271,
      "step": 35
    },
    {
      "epoch": 0.10271041369472182,
      "grad_norm": 1.6131393909454346,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8229,
      "step": 36
    },
    {
      "epoch": 0.10556348074179743,
      "grad_norm": 1.4258373975753784,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.0869,
      "step": 37
    },
    {
      "epoch": 0.10841654778887304,
      "grad_norm": 1.1875009536743164,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0034,
      "step": 38
    },
    {
      "epoch": 0.11126961483594865,
      "grad_norm": 1.2576555013656616,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8413,
      "step": 39
    },
    {
      "epoch": 0.11412268188302425,
      "grad_norm": 1.173597812652588,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5528,
      "step": 40
    },
    {
      "epoch": 0.11697574893009986,
      "grad_norm": 0.7723008394241333,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4342,
      "step": 41
    },
    {
      "epoch": 0.11982881597717546,
      "grad_norm": 0.9991022944450378,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.5693,
      "step": 42
    },
    {
      "epoch": 0.12268188302425106,
      "grad_norm": 1.1815659999847412,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6734,
      "step": 43
    },
    {
      "epoch": 0.12553495007132667,
      "grad_norm": 1.1669038534164429,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1504,
      "step": 44
    },
    {
      "epoch": 0.12838801711840228,
      "grad_norm": 1.6831579208374023,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.202,
      "step": 45
    },
    {
      "epoch": 0.1312410841654779,
      "grad_norm": 1.7314109802246094,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.039,
      "step": 46
    },
    {
      "epoch": 0.1340941512125535,
      "grad_norm": 1.7073595523834229,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9303,
      "step": 47
    },
    {
      "epoch": 0.1369472182596291,
      "grad_norm": 2.3773305416107178,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3148,
      "step": 48
    },
    {
      "epoch": 0.1398002853067047,
      "grad_norm": 1.9552549123764038,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1668,
      "step": 49
    },
    {
      "epoch": 0.14265335235378032,
      "grad_norm": 12.230058670043945,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6476,
      "step": 50
    },
    {
      "epoch": 0.14265335235378032,
      "eval_loss": 0.627819836139679,
      "eval_runtime": 50.1586,
      "eval_samples_per_second": 11.763,
      "eval_steps_per_second": 2.951,
      "step": 50
    },
    {
      "epoch": 0.14550641940085593,
      "grad_norm": 0.8418501019477844,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.59,
      "step": 51
    },
    {
      "epoch": 0.14835948644793154,
      "grad_norm": 0.6791144609451294,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5943,
      "step": 52
    },
    {
      "epoch": 0.15121255349500715,
      "grad_norm": 0.7894415259361267,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5742,
      "step": 53
    },
    {
      "epoch": 0.15406562054208273,
      "grad_norm": 0.613097071647644,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4638,
      "step": 54
    },
    {
      "epoch": 0.15691868758915833,
      "grad_norm": 0.5988654494285583,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4586,
      "step": 55
    },
    {
      "epoch": 0.15977175463623394,
      "grad_norm": 0.7294687032699585,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.471,
      "step": 56
    },
    {
      "epoch": 0.16262482168330955,
      "grad_norm": 0.682077169418335,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4363,
      "step": 57
    },
    {
      "epoch": 0.16547788873038516,
      "grad_norm": 0.801392138004303,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5081,
      "step": 58
    },
    {
      "epoch": 0.16833095577746077,
      "grad_norm": 0.5406254529953003,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4051,
      "step": 59
    },
    {
      "epoch": 0.17118402282453637,
      "grad_norm": 0.6952656507492065,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4558,
      "step": 60
    },
    {
      "epoch": 0.17403708987161198,
      "grad_norm": 0.6780873537063599,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6414,
      "step": 61
    },
    {
      "epoch": 0.1768901569186876,
      "grad_norm": 0.5133086442947388,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5783,
      "step": 62
    },
    {
      "epoch": 0.1797432239657632,
      "grad_norm": 0.7491797208786011,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7619,
      "step": 63
    },
    {
      "epoch": 0.1825962910128388,
      "grad_norm": 0.5657433867454529,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5725,
      "step": 64
    },
    {
      "epoch": 0.18544935805991442,
      "grad_norm": 0.6644863486289978,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4732,
      "step": 65
    },
    {
      "epoch": 0.18830242510699002,
      "grad_norm": 0.6698297262191772,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5635,
      "step": 66
    },
    {
      "epoch": 0.19115549215406563,
      "grad_norm": 0.5969005823135376,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5463,
      "step": 67
    },
    {
      "epoch": 0.19400855920114124,
      "grad_norm": 0.7148396372795105,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.598,
      "step": 68
    },
    {
      "epoch": 0.19686162624821682,
      "grad_norm": 0.5753114223480225,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4321,
      "step": 69
    },
    {
      "epoch": 0.19971469329529243,
      "grad_norm": 0.6687928438186646,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5087,
      "step": 70
    },
    {
      "epoch": 0.20256776034236804,
      "grad_norm": 0.7704508900642395,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4736,
      "step": 71
    },
    {
      "epoch": 0.20542082738944364,
      "grad_norm": 0.7208991646766663,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5593,
      "step": 72
    },
    {
      "epoch": 0.20827389443651925,
      "grad_norm": 0.77704918384552,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4307,
      "step": 73
    },
    {
      "epoch": 0.21112696148359486,
      "grad_norm": 0.8767436742782593,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4362,
      "step": 74
    },
    {
      "epoch": 0.21398002853067047,
      "grad_norm": 0.6699895858764648,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4974,
      "step": 75
    },
    {
      "epoch": 0.21683309557774608,
      "grad_norm": 0.9010039567947388,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5181,
      "step": 76
    },
    {
      "epoch": 0.21968616262482168,
      "grad_norm": 0.745724618434906,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4427,
      "step": 77
    },
    {
      "epoch": 0.2225392296718973,
      "grad_norm": 0.7348241209983826,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.531,
      "step": 78
    },
    {
      "epoch": 0.2253922967189729,
      "grad_norm": 0.7379856109619141,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.5343,
      "step": 79
    },
    {
      "epoch": 0.2282453637660485,
      "grad_norm": 1.2116280794143677,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7358,
      "step": 80
    },
    {
      "epoch": 0.23109843081312412,
      "grad_norm": 0.9867377281188965,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5476,
      "step": 81
    },
    {
      "epoch": 0.23395149786019973,
      "grad_norm": 0.8551483750343323,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3468,
      "step": 82
    },
    {
      "epoch": 0.23680456490727533,
      "grad_norm": 0.8607773780822754,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4683,
      "step": 83
    },
    {
      "epoch": 0.2396576319543509,
      "grad_norm": 0.7946150898933411,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3575,
      "step": 84
    },
    {
      "epoch": 0.24251069900142652,
      "grad_norm": 1.0451940298080444,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3243,
      "step": 85
    },
    {
      "epoch": 0.24536376604850213,
      "grad_norm": 1.2571059465408325,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4743,
      "step": 86
    },
    {
      "epoch": 0.24821683309557774,
      "grad_norm": 1.0434961318969727,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.4322,
      "step": 87
    },
    {
      "epoch": 0.25106990014265335,
      "grad_norm": 0.9375142455101013,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3317,
      "step": 88
    },
    {
      "epoch": 0.25392296718972895,
      "grad_norm": 1.7053827047348022,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.4637,
      "step": 89
    },
    {
      "epoch": 0.25677603423680456,
      "grad_norm": 1.2579131126403809,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1616,
      "step": 90
    },
    {
      "epoch": 0.25962910128388017,
      "grad_norm": 0.9650585651397705,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.1994,
      "step": 91
    },
    {
      "epoch": 0.2624821683309558,
      "grad_norm": 1.097511887550354,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2231,
      "step": 92
    },
    {
      "epoch": 0.2653352353780314,
      "grad_norm": 2.060180902481079,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5784,
      "step": 93
    },
    {
      "epoch": 0.268188302425107,
      "grad_norm": 1.732223391532898,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6934,
      "step": 94
    },
    {
      "epoch": 0.2710413694721826,
      "grad_norm": 1.496158242225647,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6186,
      "step": 95
    },
    {
      "epoch": 0.2738944365192582,
      "grad_norm": 1.6180177927017212,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.4221,
      "step": 96
    },
    {
      "epoch": 0.2767475035663338,
      "grad_norm": 1.4671765565872192,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4666,
      "step": 97
    },
    {
      "epoch": 0.2796005706134094,
      "grad_norm": 2.6195898056030273,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6423,
      "step": 98
    },
    {
      "epoch": 0.28245363766048504,
      "grad_norm": 2.0639560222625732,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7663,
      "step": 99
    },
    {
      "epoch": 0.28530670470756064,
      "grad_norm": 2.137301445007324,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3303,
      "step": 100
    },
    {
      "epoch": 0.28530670470756064,
      "eval_loss": 0.3939934968948364,
      "eval_runtime": 50.779,
      "eval_samples_per_second": 11.619,
      "eval_steps_per_second": 2.915,
      "step": 100
    },
    {
      "epoch": 0.28815977175463625,
      "grad_norm": 0.6028413772583008,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4602,
      "step": 101
    },
    {
      "epoch": 0.29101283880171186,
      "grad_norm": 0.5953587293624878,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5384,
      "step": 102
    },
    {
      "epoch": 0.29386590584878747,
      "grad_norm": 0.6672841310501099,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.3925,
      "step": 103
    },
    {
      "epoch": 0.2967189728958631,
      "grad_norm": 0.5994097590446472,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3194,
      "step": 104
    },
    {
      "epoch": 0.2995720399429387,
      "grad_norm": 0.6114593744277954,
      "learning_rate": 5e-05,
      "loss": 0.3055,
      "step": 105
    },
    {
      "epoch": 0.3024251069900143,
      "grad_norm": 0.660155177116394,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2979,
      "step": 106
    },
    {
      "epoch": 0.30527817403708984,
      "grad_norm": 0.5987465381622314,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.3679,
      "step": 107
    },
    {
      "epoch": 0.30813124108416545,
      "grad_norm": 0.5800893902778625,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2584,
      "step": 108
    },
    {
      "epoch": 0.31098430813124106,
      "grad_norm": 0.6719452738761902,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3254,
      "step": 109
    },
    {
      "epoch": 0.31383737517831667,
      "grad_norm": 0.7397783398628235,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5855,
      "step": 110
    },
    {
      "epoch": 0.3166904422253923,
      "grad_norm": 0.6485562324523926,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.4102,
      "step": 111
    },
    {
      "epoch": 0.3195435092724679,
      "grad_norm": 0.805045485496521,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4056,
      "step": 112
    },
    {
      "epoch": 0.3223965763195435,
      "grad_norm": 0.7608383893966675,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.302,
      "step": 113
    },
    {
      "epoch": 0.3252496433666191,
      "grad_norm": 0.8918278217315674,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4657,
      "step": 114
    },
    {
      "epoch": 0.3281027104136947,
      "grad_norm": 0.7644259333610535,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3287,
      "step": 115
    },
    {
      "epoch": 0.3309557774607703,
      "grad_norm": 0.9352925419807434,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4462,
      "step": 116
    },
    {
      "epoch": 0.3338088445078459,
      "grad_norm": 0.6303168535232544,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3722,
      "step": 117
    },
    {
      "epoch": 0.33666191155492153,
      "grad_norm": 0.6794707775115967,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3484,
      "step": 118
    },
    {
      "epoch": 0.33951497860199714,
      "grad_norm": 0.7765228152275085,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.472,
      "step": 119
    },
    {
      "epoch": 0.34236804564907275,
      "grad_norm": 0.7750933766365051,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4549,
      "step": 120
    },
    {
      "epoch": 0.34522111269614836,
      "grad_norm": 0.7322866320610046,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3014,
      "step": 121
    },
    {
      "epoch": 0.34807417974322397,
      "grad_norm": 0.610202431678772,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.206,
      "step": 122
    },
    {
      "epoch": 0.3509272467902996,
      "grad_norm": 0.774712085723877,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.4035,
      "step": 123
    },
    {
      "epoch": 0.3537803138373752,
      "grad_norm": 0.8692356944084167,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2315,
      "step": 124
    },
    {
      "epoch": 0.3566333808844508,
      "grad_norm": 0.9205110669136047,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3515,
      "step": 125
    },
    {
      "epoch": 0.3594864479315264,
      "grad_norm": 0.8701263666152954,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3474,
      "step": 126
    },
    {
      "epoch": 0.362339514978602,
      "grad_norm": 0.8201534152030945,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2972,
      "step": 127
    },
    {
      "epoch": 0.3651925820256776,
      "grad_norm": 0.744414210319519,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.2461,
      "step": 128
    },
    {
      "epoch": 0.3680456490727532,
      "grad_norm": 1.3242052793502808,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3896,
      "step": 129
    },
    {
      "epoch": 0.37089871611982883,
      "grad_norm": 0.9903146028518677,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3165,
      "step": 130
    },
    {
      "epoch": 0.37375178316690444,
      "grad_norm": 1.0595813989639282,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4255,
      "step": 131
    },
    {
      "epoch": 0.37660485021398005,
      "grad_norm": 0.9600425958633423,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.354,
      "step": 132
    },
    {
      "epoch": 0.37945791726105566,
      "grad_norm": 0.9561607837677002,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2519,
      "step": 133
    },
    {
      "epoch": 0.38231098430813126,
      "grad_norm": 0.810734748840332,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2405,
      "step": 134
    },
    {
      "epoch": 0.38516405135520687,
      "grad_norm": 0.9556282162666321,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2314,
      "step": 135
    },
    {
      "epoch": 0.3880171184022825,
      "grad_norm": 0.8967754244804382,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1623,
      "step": 136
    },
    {
      "epoch": 0.3908701854493581,
      "grad_norm": 1.4162787199020386,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2568,
      "step": 137
    },
    {
      "epoch": 0.39372325249643364,
      "grad_norm": 1.4185165166854858,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2818,
      "step": 138
    },
    {
      "epoch": 0.39657631954350925,
      "grad_norm": 0.8695159554481506,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.1415,
      "step": 139
    },
    {
      "epoch": 0.39942938659058486,
      "grad_norm": 0.6690768599510193,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1445,
      "step": 140
    },
    {
      "epoch": 0.40228245363766046,
      "grad_norm": 0.6722933650016785,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0983,
      "step": 141
    },
    {
      "epoch": 0.4051355206847361,
      "grad_norm": 0.5294798612594604,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0877,
      "step": 142
    },
    {
      "epoch": 0.4079885877318117,
      "grad_norm": 1.0671422481536865,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2008,
      "step": 143
    },
    {
      "epoch": 0.4108416547788873,
      "grad_norm": 1.1839511394500732,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2516,
      "step": 144
    },
    {
      "epoch": 0.4136947218259629,
      "grad_norm": 1.5890252590179443,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3785,
      "step": 145
    },
    {
      "epoch": 0.4165477888730385,
      "grad_norm": 1.4438451528549194,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2911,
      "step": 146
    },
    {
      "epoch": 0.4194008559201141,
      "grad_norm": 1.65779447555542,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2865,
      "step": 147
    },
    {
      "epoch": 0.4222539229671897,
      "grad_norm": 3.502389907836914,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7015,
      "step": 148
    },
    {
      "epoch": 0.42510699001426533,
      "grad_norm": 2.2211198806762695,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.2977,
      "step": 149
    },
    {
      "epoch": 0.42796005706134094,
      "grad_norm": 10.175692558288574,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.8466,
      "step": 150
    },
    {
      "epoch": 0.42796005706134094,
      "eval_loss": 0.2351686656475067,
      "eval_runtime": 50.5217,
      "eval_samples_per_second": 11.678,
      "eval_steps_per_second": 2.929,
      "step": 150
    },
    {
      "epoch": 0.43081312410841655,
      "grad_norm": 0.8843557238578796,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3827,
      "step": 151
    },
    {
      "epoch": 0.43366619115549215,
      "grad_norm": 0.7661022543907166,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3342,
      "step": 152
    },
    {
      "epoch": 0.43651925820256776,
      "grad_norm": 0.7855313420295715,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.294,
      "step": 153
    },
    {
      "epoch": 0.43937232524964337,
      "grad_norm": 0.5694296360015869,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.2301,
      "step": 154
    },
    {
      "epoch": 0.442225392296719,
      "grad_norm": 0.7252908945083618,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.2229,
      "step": 155
    },
    {
      "epoch": 0.4450784593437946,
      "grad_norm": 0.5194413661956787,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.1885,
      "step": 156
    },
    {
      "epoch": 0.4479315263908702,
      "grad_norm": 0.6145206093788147,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.2846,
      "step": 157
    },
    {
      "epoch": 0.4507845934379458,
      "grad_norm": 0.5040757656097412,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.1809,
      "step": 158
    },
    {
      "epoch": 0.4536376604850214,
      "grad_norm": 0.5664169788360596,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.1693,
      "step": 159
    },
    {
      "epoch": 0.456490727532097,
      "grad_norm": 0.8032068014144897,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.4246,
      "step": 160
    },
    {
      "epoch": 0.4593437945791726,
      "grad_norm": 0.6073234677314758,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.2372,
      "step": 161
    },
    {
      "epoch": 0.46219686162624823,
      "grad_norm": 0.7199921607971191,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2181,
      "step": 162
    },
    {
      "epoch": 0.46504992867332384,
      "grad_norm": 0.6163046360015869,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.287,
      "step": 163
    },
    {
      "epoch": 0.46790299572039945,
      "grad_norm": 0.6843337416648865,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.2244,
      "step": 164
    },
    {
      "epoch": 0.47075606276747506,
      "grad_norm": 0.7126415371894836,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.2275,
      "step": 165
    },
    {
      "epoch": 0.47360912981455067,
      "grad_norm": 0.7313539385795593,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3282,
      "step": 166
    },
    {
      "epoch": 0.4764621968616263,
      "grad_norm": 0.6523075699806213,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2027,
      "step": 167
    },
    {
      "epoch": 0.4793152639087018,
      "grad_norm": 0.6936315298080444,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.214,
      "step": 168
    },
    {
      "epoch": 0.48216833095577744,
      "grad_norm": 0.7612742185592651,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.2554,
      "step": 169
    },
    {
      "epoch": 0.48502139800285304,
      "grad_norm": 0.6699209809303284,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.189,
      "step": 170
    },
    {
      "epoch": 0.48787446504992865,
      "grad_norm": 0.5391771197319031,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.1385,
      "step": 171
    },
    {
      "epoch": 0.49072753209700426,
      "grad_norm": 0.7588281631469727,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2521,
      "step": 172
    },
    {
      "epoch": 0.49358059914407987,
      "grad_norm": 0.6277549862861633,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.1509,
      "step": 173
    },
    {
      "epoch": 0.4964336661911555,
      "grad_norm": 0.8882228136062622,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2524,
      "step": 174
    },
    {
      "epoch": 0.4992867332382311,
      "grad_norm": 0.9271660447120667,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2268,
      "step": 175
    },
    {
      "epoch": 0.5021398002853067,
      "grad_norm": 0.7540334463119507,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.1519,
      "step": 176
    },
    {
      "epoch": 0.5049928673323824,
      "grad_norm": 0.6032679677009583,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.1398,
      "step": 177
    },
    {
      "epoch": 0.5078459343794579,
      "grad_norm": 0.7410967946052551,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.1733,
      "step": 178
    },
    {
      "epoch": 0.5106990014265336,
      "grad_norm": 0.7232276797294617,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2442,
      "step": 179
    },
    {
      "epoch": 0.5135520684736091,
      "grad_norm": 0.7706058621406555,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.239,
      "step": 180
    },
    {
      "epoch": 0.5164051355206848,
      "grad_norm": 0.8064122796058655,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1811,
      "step": 181
    },
    {
      "epoch": 0.5192582025677603,
      "grad_norm": 0.6672751903533936,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.1542,
      "step": 182
    },
    {
      "epoch": 0.5221112696148359,
      "grad_norm": 0.6747187972068787,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.1507,
      "step": 183
    },
    {
      "epoch": 0.5249643366619116,
      "grad_norm": 0.5767862200737,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0932,
      "step": 184
    },
    {
      "epoch": 0.5278174037089871,
      "grad_norm": 0.6442479491233826,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.1128,
      "step": 185
    },
    {
      "epoch": 0.5306704707560628,
      "grad_norm": 0.7297366857528687,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1417,
      "step": 186
    },
    {
      "epoch": 0.5335235378031383,
      "grad_norm": 0.7027532458305359,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.1231,
      "step": 187
    },
    {
      "epoch": 0.536376604850214,
      "grad_norm": 0.6565024256706238,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0943,
      "step": 188
    },
    {
      "epoch": 0.5392296718972895,
      "grad_norm": 0.5456377267837524,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0863,
      "step": 189
    },
    {
      "epoch": 0.5420827389443652,
      "grad_norm": 0.5135669112205505,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0713,
      "step": 190
    },
    {
      "epoch": 0.5449358059914408,
      "grad_norm": 0.4299718141555786,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0719,
      "step": 191
    },
    {
      "epoch": 0.5477888730385164,
      "grad_norm": 0.5324990749359131,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0937,
      "step": 192
    },
    {
      "epoch": 0.550641940085592,
      "grad_norm": 1.0318214893341064,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.1534,
      "step": 193
    },
    {
      "epoch": 0.5534950071326676,
      "grad_norm": 1.0301591157913208,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2577,
      "step": 194
    },
    {
      "epoch": 0.5563480741797432,
      "grad_norm": 1.0103733539581299,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.1366,
      "step": 195
    },
    {
      "epoch": 0.5592011412268189,
      "grad_norm": 0.8199431300163269,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.1385,
      "step": 196
    },
    {
      "epoch": 0.5620542082738944,
      "grad_norm": 0.7486357688903809,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.1199,
      "step": 197
    },
    {
      "epoch": 0.5649072753209701,
      "grad_norm": 1.287459135055542,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2778,
      "step": 198
    },
    {
      "epoch": 0.5677603423680456,
      "grad_norm": 1.6342028379440308,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3822,
      "step": 199
    },
    {
      "epoch": 0.5706134094151213,
      "grad_norm": 1.4031959772109985,
      "learning_rate": 0.0,
      "loss": 0.1789,
      "step": 200
    },
    {
      "epoch": 0.5706134094151213,
      "eval_loss": 0.19928720593452454,
      "eval_runtime": 50.5096,
      "eval_samples_per_second": 11.681,
      "eval_steps_per_second": 2.93,
      "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": 3.386612984284447e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}