{
  "best_metric": 1.114859938621521,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.16266775111834078,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008133387555917039,
      "grad_norm": 1.5821726322174072,
      "learning_rate": 1e-05,
      "loss": 1.2811,
      "step": 1
    },
    {
      "epoch": 0.0008133387555917039,
      "eval_loss": 1.8573664426803589,
      "eval_runtime": 105.759,
      "eval_samples_per_second": 19.582,
      "eval_steps_per_second": 4.898,
      "step": 1
    },
    {
      "epoch": 0.0016266775111834079,
      "grad_norm": 1.5545353889465332,
      "learning_rate": 2e-05,
      "loss": 1.3231,
      "step": 2
    },
    {
      "epoch": 0.0024400162667751117,
      "grad_norm": 1.5528157949447632,
      "learning_rate": 3e-05,
      "loss": 1.3786,
      "step": 3
    },
    {
      "epoch": 0.0032533550223668157,
      "grad_norm": 1.4315781593322754,
      "learning_rate": 4e-05,
      "loss": 1.2985,
      "step": 4
    },
    {
      "epoch": 0.004066693777958519,
      "grad_norm": 1.5617440938949585,
      "learning_rate": 5e-05,
      "loss": 1.3283,
      "step": 5
    },
    {
      "epoch": 0.004880032533550223,
      "grad_norm": 1.390085220336914,
      "learning_rate": 6e-05,
      "loss": 1.1638,
      "step": 6
    },
    {
      "epoch": 0.0056933712891419274,
      "grad_norm": 1.3323758840560913,
      "learning_rate": 7e-05,
      "loss": 1.2927,
      "step": 7
    },
    {
      "epoch": 0.0065067100447336315,
      "grad_norm": 1.450661540031433,
      "learning_rate": 8e-05,
      "loss": 1.3237,
      "step": 8
    },
    {
      "epoch": 0.0073200488003253355,
      "grad_norm": 1.3212594985961914,
      "learning_rate": 9e-05,
      "loss": 1.1786,
      "step": 9
    },
    {
      "epoch": 0.008133387555917039,
      "grad_norm": 2.0390310287475586,
      "learning_rate": 0.0001,
      "loss": 1.1969,
      "step": 10
    },
    {
      "epoch": 0.008946726311508743,
      "grad_norm": 1.5228559970855713,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.314,
      "step": 11
    },
    {
      "epoch": 0.009760065067100447,
      "grad_norm": 1.251420497894287,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1885,
      "step": 12
    },
    {
      "epoch": 0.01057340382269215,
      "grad_norm": 1.136439323425293,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1652,
      "step": 13
    },
    {
      "epoch": 0.011386742578283855,
      "grad_norm": 1.2015175819396973,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.2138,
      "step": 14
    },
    {
      "epoch": 0.012200081333875559,
      "grad_norm": 1.146148920059204,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.2232,
      "step": 15
    },
    {
      "epoch": 0.013013420089467263,
      "grad_norm": 1.2251266241073608,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.234,
      "step": 16
    },
    {
      "epoch": 0.013826758845058967,
      "grad_norm": 1.3935339450836182,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.2474,
      "step": 17
    },
    {
      "epoch": 0.014640097600650671,
      "grad_norm": 1.217868685722351,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.2927,
      "step": 18
    },
    {
      "epoch": 0.015453436356242375,
      "grad_norm": 1.4080815315246582,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.2195,
      "step": 19
    },
    {
      "epoch": 0.016266775111834077,
      "grad_norm": 1.4384061098098755,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0955,
      "step": 20
    },
    {
      "epoch": 0.01708011386742578,
      "grad_norm": 1.3029018640518188,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1727,
      "step": 21
    },
    {
      "epoch": 0.017893452623017485,
      "grad_norm": 1.3262468576431274,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2924,
      "step": 22
    },
    {
      "epoch": 0.01870679137860919,
      "grad_norm": 1.3781956434249878,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.1789,
      "step": 23
    },
    {
      "epoch": 0.019520130134200894,
      "grad_norm": 1.3876075744628906,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2155,
      "step": 24
    },
    {
      "epoch": 0.020333468889792598,
      "grad_norm": 1.4162825345993042,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.1829,
      "step": 25
    },
    {
      "epoch": 0.0211468076453843,
      "grad_norm": 1.8507206439971924,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.1281,
      "step": 26
    },
    {
      "epoch": 0.021960146400976006,
      "grad_norm": 1.7511723041534424,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.3022,
      "step": 27
    },
    {
      "epoch": 0.02277348515656771,
      "grad_norm": 1.964510202407837,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.2494,
      "step": 28
    },
    {
      "epoch": 0.023586823912159414,
      "grad_norm": 1.8122329711914062,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.1533,
      "step": 29
    },
    {
      "epoch": 0.024400162667751118,
      "grad_norm": 2.127209424972534,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.4051,
      "step": 30
    },
    {
      "epoch": 0.025213501423342822,
      "grad_norm": 2.1519463062286377,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2794,
      "step": 31
    },
    {
      "epoch": 0.026026840178934526,
      "grad_norm": 2.38741135597229,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3858,
      "step": 32
    },
    {
      "epoch": 0.02684017893452623,
      "grad_norm": 2.1548306941986084,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.1537,
      "step": 33
    },
    {
      "epoch": 0.027653517690117934,
      "grad_norm": 2.3081791400909424,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.1929,
      "step": 34
    },
    {
      "epoch": 0.028466856445709638,
      "grad_norm": 2.4958434104919434,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.1307,
      "step": 35
    },
    {
      "epoch": 0.029280195201301342,
      "grad_norm": 2.9043824672698975,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.1583,
      "step": 36
    },
    {
      "epoch": 0.030093533956893046,
      "grad_norm": 3.27945876121521,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.33,
      "step": 37
    },
    {
      "epoch": 0.03090687271248475,
      "grad_norm": 2.8262364864349365,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0949,
      "step": 38
    },
    {
      "epoch": 0.03172021146807645,
      "grad_norm": 4.122930526733398,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1568,
      "step": 39
    },
    {
      "epoch": 0.032533550223668155,
      "grad_norm": 3.97977352142334,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1299,
      "step": 40
    },
    {
      "epoch": 0.03334688897925986,
      "grad_norm": 3.4038312435150146,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1381,
      "step": 41
    },
    {
      "epoch": 0.03416022773485156,
      "grad_norm": 4.428281784057617,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.1249,
      "step": 42
    },
    {
      "epoch": 0.03497356649044327,
      "grad_norm": 3.8904428482055664,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8513,
      "step": 43
    },
    {
      "epoch": 0.03578690524603497,
      "grad_norm": 4.901149272918701,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1262,
      "step": 44
    },
    {
      "epoch": 0.036600244001626675,
      "grad_norm": 3.720000982284546,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.1569,
      "step": 45
    },
    {
      "epoch": 0.03741358275721838,
      "grad_norm": 4.258459091186523,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.1182,
      "step": 46
    },
    {
      "epoch": 0.03822692151281008,
      "grad_norm": 4.444375514984131,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.0585,
      "step": 47
    },
    {
      "epoch": 0.03904026026840179,
      "grad_norm": 8.071666717529297,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1039,
      "step": 48
    },
    {
      "epoch": 0.03985359902399349,
      "grad_norm": 5.445046901702881,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0221,
      "step": 49
    },
    {
      "epoch": 0.040666937779585195,
      "grad_norm": 7.90680456161499,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5705,
      "step": 50
    },
    {
      "epoch": 0.040666937779585195,
      "eval_loss": 1.3668920993804932,
      "eval_runtime": 107.1569,
      "eval_samples_per_second": 19.327,
      "eval_steps_per_second": 4.834,
      "step": 50
    },
    {
      "epoch": 0.0414802765351769,
      "grad_norm": 2.5964858531951904,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.327,
      "step": 51
    },
    {
      "epoch": 0.0422936152907686,
      "grad_norm": 1.9609887599945068,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.3133,
      "step": 52
    },
    {
      "epoch": 0.04310695404636031,
      "grad_norm": 1.1775012016296387,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.204,
      "step": 53
    },
    {
      "epoch": 0.04392029280195201,
      "grad_norm": 1.0460187196731567,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2136,
      "step": 54
    },
    {
      "epoch": 0.044733631557543715,
      "grad_norm": 0.9313177466392517,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1933,
      "step": 55
    },
    {
      "epoch": 0.04554697031313542,
      "grad_norm": 1.049389362335205,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.2795,
      "step": 56
    },
    {
      "epoch": 0.046360309068727124,
      "grad_norm": 1.006925344467163,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.1701,
      "step": 57
    },
    {
      "epoch": 0.04717364782431883,
      "grad_norm": 0.9446033239364624,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1624,
      "step": 58
    },
    {
      "epoch": 0.04798698657991053,
      "grad_norm": 0.8426344990730286,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.1467,
      "step": 59
    },
    {
      "epoch": 0.048800325335502236,
      "grad_norm": 0.8230246901512146,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.1479,
      "step": 60
    },
    {
      "epoch": 0.04961366409109394,
      "grad_norm": 0.8439881801605225,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.1607,
      "step": 61
    },
    {
      "epoch": 0.050427002846685644,
      "grad_norm": 0.9041538238525391,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.1217,
      "step": 62
    },
    {
      "epoch": 0.05124034160227735,
      "grad_norm": 0.9187133312225342,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.2933,
      "step": 63
    },
    {
      "epoch": 0.05205368035786905,
      "grad_norm": 0.9471145868301392,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.2492,
      "step": 64
    },
    {
      "epoch": 0.052867019113460756,
      "grad_norm": 1.015170931816101,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2066,
      "step": 65
    },
    {
      "epoch": 0.05368035786905246,
      "grad_norm": 0.9947161078453064,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.2231,
      "step": 66
    },
    {
      "epoch": 0.054493696624644164,
      "grad_norm": 0.9911460280418396,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2152,
      "step": 67
    },
    {
      "epoch": 0.05530703538023587,
      "grad_norm": 1.1157715320587158,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.1715,
      "step": 68
    },
    {
      "epoch": 0.05612037413582757,
      "grad_norm": 1.0330973863601685,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.1573,
      "step": 69
    },
    {
      "epoch": 0.056933712891419276,
      "grad_norm": 1.1242437362670898,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2355,
      "step": 70
    },
    {
      "epoch": 0.05774705164701098,
      "grad_norm": 1.18375563621521,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.1546,
      "step": 71
    },
    {
      "epoch": 0.058560390402602684,
      "grad_norm": 1.1902270317077637,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1947,
      "step": 72
    },
    {
      "epoch": 0.05937372915819439,
      "grad_norm": 1.186957597732544,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.2263,
      "step": 73
    },
    {
      "epoch": 0.06018706791378609,
      "grad_norm": 1.2676359415054321,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.2803,
      "step": 74
    },
    {
      "epoch": 0.061000406669377796,
      "grad_norm": 1.3717691898345947,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2326,
      "step": 75
    },
    {
      "epoch": 0.0618137454249695,
      "grad_norm": 1.4836101531982422,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.2476,
      "step": 76
    },
    {
      "epoch": 0.0626270841805612,
      "grad_norm": 1.612488031387329,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.1825,
      "step": 77
    },
    {
      "epoch": 0.0634404229361529,
      "grad_norm": 1.594044804573059,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3276,
      "step": 78
    },
    {
      "epoch": 0.06425376169174461,
      "grad_norm": 1.643832802772522,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.1981,
      "step": 79
    },
    {
      "epoch": 0.06506710044733631,
      "grad_norm": 1.9011435508728027,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.2833,
      "step": 80
    },
    {
      "epoch": 0.06588043920292802,
      "grad_norm": 1.8688122034072876,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.3166,
      "step": 81
    },
    {
      "epoch": 0.06669377795851972,
      "grad_norm": 2.2397377490997314,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.2734,
      "step": 82
    },
    {
      "epoch": 0.06750711671411143,
      "grad_norm": 2.2626216411590576,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2673,
      "step": 83
    },
    {
      "epoch": 0.06832045546970313,
      "grad_norm": 2.330335855484009,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.1307,
      "step": 84
    },
    {
      "epoch": 0.06913379422529484,
      "grad_norm": 2.426630973815918,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.1187,
      "step": 85
    },
    {
      "epoch": 0.06994713298088653,
      "grad_norm": 2.255751609802246,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.19,
      "step": 86
    },
    {
      "epoch": 0.07076047173647824,
      "grad_norm": 2.8092153072357178,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.2152,
      "step": 87
    },
    {
      "epoch": 0.07157381049206994,
      "grad_norm": 2.3413901329040527,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0266,
      "step": 88
    },
    {
      "epoch": 0.07238714924766165,
      "grad_norm": 2.6290576457977295,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.0065,
      "step": 89
    },
    {
      "epoch": 0.07320048800325335,
      "grad_norm": 2.9226067066192627,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.0783,
      "step": 90
    },
    {
      "epoch": 0.07401382675884506,
      "grad_norm": 2.9445765018463135,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.9754,
      "step": 91
    },
    {
      "epoch": 0.07482716551443676,
      "grad_norm": 2.7714364528656006,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8755,
      "step": 92
    },
    {
      "epoch": 0.07564050427002847,
      "grad_norm": 3.633474349975586,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.224,
      "step": 93
    },
    {
      "epoch": 0.07645384302562017,
      "grad_norm": 4.1051154136657715,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.0751,
      "step": 94
    },
    {
      "epoch": 0.07726718178121188,
      "grad_norm": 3.6421470642089844,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.0392,
      "step": 95
    },
    {
      "epoch": 0.07808052053680357,
      "grad_norm": 3.6323955059051514,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.0279,
      "step": 96
    },
    {
      "epoch": 0.07889385929239529,
      "grad_norm": 4.387916088104248,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.9259,
      "step": 97
    },
    {
      "epoch": 0.07970719804798698,
      "grad_norm": 3.2340691089630127,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7949,
      "step": 98
    },
    {
      "epoch": 0.0805205368035787,
      "grad_norm": 4.503349304199219,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0153,
      "step": 99
    },
    {
      "epoch": 0.08133387555917039,
      "grad_norm": 6.987500190734863,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.2214,
      "step": 100
    },
    {
      "epoch": 0.08133387555917039,
      "eval_loss": 1.3060370683670044,
      "eval_runtime": 107.5359,
      "eval_samples_per_second": 19.259,
      "eval_steps_per_second": 4.817,
      "step": 100
    },
    {
      "epoch": 0.0821472143147621,
      "grad_norm": 1.94047212600708,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.2668,
      "step": 101
    },
    {
      "epoch": 0.0829605530703538,
      "grad_norm": 1.8956949710845947,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.3197,
      "step": 102
    },
    {
      "epoch": 0.08377389182594551,
      "grad_norm": 1.336571455001831,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.244,
      "step": 103
    },
    {
      "epoch": 0.0845872305815372,
      "grad_norm": 0.9841553568840027,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.2328,
      "step": 104
    },
    {
      "epoch": 0.08540056933712892,
      "grad_norm": 0.7924576997756958,
      "learning_rate": 5e-05,
      "loss": 1.2161,
      "step": 105
    },
    {
      "epoch": 0.08621390809272061,
      "grad_norm": 0.7528790831565857,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.117,
      "step": 106
    },
    {
      "epoch": 0.08702724684831233,
      "grad_norm": 0.7675988078117371,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.1558,
      "step": 107
    },
    {
      "epoch": 0.08784058560390402,
      "grad_norm": 0.7811238765716553,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.149,
      "step": 108
    },
    {
      "epoch": 0.08865392435949573,
      "grad_norm": 0.8098706007003784,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.1862,
      "step": 109
    },
    {
      "epoch": 0.08946726311508743,
      "grad_norm": 0.8363338708877563,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.1586,
      "step": 110
    },
    {
      "epoch": 0.09028060187067914,
      "grad_norm": 0.8584006428718567,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.2251,
      "step": 111
    },
    {
      "epoch": 0.09109394062627084,
      "grad_norm": 0.8999638557434082,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.17,
      "step": 112
    },
    {
      "epoch": 0.09190727938186255,
      "grad_norm": 0.9447212219238281,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.1921,
      "step": 113
    },
    {
      "epoch": 0.09272061813745425,
      "grad_norm": 0.9075600504875183,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.1681,
      "step": 114
    },
    {
      "epoch": 0.09353395689304596,
      "grad_norm": 0.8947489857673645,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.1812,
      "step": 115
    },
    {
      "epoch": 0.09434729564863766,
      "grad_norm": 0.8812084197998047,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.1441,
      "step": 116
    },
    {
      "epoch": 0.09516063440422937,
      "grad_norm": 0.9609267115592957,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.2475,
      "step": 117
    },
    {
      "epoch": 0.09597397315982106,
      "grad_norm": 0.9728766083717346,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.2601,
      "step": 118
    },
    {
      "epoch": 0.09678731191541277,
      "grad_norm": 0.9993661642074585,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.1638,
      "step": 119
    },
    {
      "epoch": 0.09760065067100447,
      "grad_norm": 1.068623661994934,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.3297,
      "step": 120
    },
    {
      "epoch": 0.09841398942659618,
      "grad_norm": 1.1446888446807861,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.2108,
      "step": 121
    },
    {
      "epoch": 0.09922732818218788,
      "grad_norm": 1.143709659576416,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.1442,
      "step": 122
    },
    {
      "epoch": 0.10004066693777959,
      "grad_norm": 1.1003456115722656,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.3277,
      "step": 123
    },
    {
      "epoch": 0.10085400569337129,
      "grad_norm": 1.187758445739746,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1678,
      "step": 124
    },
    {
      "epoch": 0.101667344448963,
      "grad_norm": 1.2396060228347778,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.2628,
      "step": 125
    },
    {
      "epoch": 0.1024806832045547,
      "grad_norm": 1.2636468410491943,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.3494,
      "step": 126
    },
    {
      "epoch": 0.1032940219601464,
      "grad_norm": 1.2293963432312012,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.1894,
      "step": 127
    },
    {
      "epoch": 0.1041073607157381,
      "grad_norm": 1.3343364000320435,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.2201,
      "step": 128
    },
    {
      "epoch": 0.10492069947132981,
      "grad_norm": 1.534117341041565,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.1311,
      "step": 129
    },
    {
      "epoch": 0.10573403822692151,
      "grad_norm": 1.4760112762451172,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.1801,
      "step": 130
    },
    {
      "epoch": 0.10654737698251322,
      "grad_norm": 1.6952861547470093,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.1909,
      "step": 131
    },
    {
      "epoch": 0.10736071573810492,
      "grad_norm": 1.708000659942627,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.189,
      "step": 132
    },
    {
      "epoch": 0.10817405449369663,
      "grad_norm": 2.2749998569488525,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.1441,
      "step": 133
    },
    {
      "epoch": 0.10898739324928833,
      "grad_norm": 1.9907662868499756,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.2058,
      "step": 134
    },
    {
      "epoch": 0.10980073200488004,
      "grad_norm": 2.1541080474853516,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.1759,
      "step": 135
    },
    {
      "epoch": 0.11061407076047174,
      "grad_norm": 2.1259610652923584,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.0834,
      "step": 136
    },
    {
      "epoch": 0.11142740951606345,
      "grad_norm": 2.4612503051757812,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.2598,
      "step": 137
    },
    {
      "epoch": 0.11224074827165514,
      "grad_norm": 2.42413067817688,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.1451,
      "step": 138
    },
    {
      "epoch": 0.11305408702724686,
      "grad_norm": 2.652392625808716,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.0712,
      "step": 139
    },
    {
      "epoch": 0.11386742578283855,
      "grad_norm": 2.9709434509277344,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.051,
      "step": 140
    },
    {
      "epoch": 0.11468076453843025,
      "grad_norm": 2.844867467880249,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.0731,
      "step": 141
    },
    {
      "epoch": 0.11549410329402196,
      "grad_norm": 2.7885658740997314,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.0487,
      "step": 142
    },
    {
      "epoch": 0.11630744204961366,
      "grad_norm": 3.255350351333618,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0362,
      "step": 143
    },
    {
      "epoch": 0.11712078080520537,
      "grad_norm": 3.2264678478240967,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7978,
      "step": 144
    },
    {
      "epoch": 0.11793411956079707,
      "grad_norm": 3.3712284564971924,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.0642,
      "step": 145
    },
    {
      "epoch": 0.11874745831638878,
      "grad_norm": 3.8595023155212402,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.0994,
      "step": 146
    },
    {
      "epoch": 0.11956079707198047,
      "grad_norm": 3.511137008666992,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.8517,
      "step": 147
    },
    {
      "epoch": 0.12037413582757218,
      "grad_norm": 4.115170001983643,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9877,
      "step": 148
    },
    {
      "epoch": 0.12118747458316388,
      "grad_norm": 4.15766716003418,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8316,
      "step": 149
    },
    {
      "epoch": 0.12200081333875559,
      "grad_norm": 7.101338863372803,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.5731,
      "step": 150
    },
    {
      "epoch": 0.12200081333875559,
      "eval_loss": 1.1552507877349854,
      "eval_runtime": 107.2194,
      "eval_samples_per_second": 19.316,
      "eval_steps_per_second": 4.831,
      "step": 150
    },
    {
      "epoch": 0.12281415209434729,
      "grad_norm": 1.0750468969345093,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.1226,
      "step": 151
    },
    {
      "epoch": 0.123627490849939,
      "grad_norm": 1.1478819847106934,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.2103,
      "step": 152
    },
    {
      "epoch": 0.1244408296055307,
      "grad_norm": 1.0230921506881714,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.2575,
      "step": 153
    },
    {
      "epoch": 0.1252541683611224,
      "grad_norm": 0.9688786268234253,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.2019,
      "step": 154
    },
    {
      "epoch": 0.1260675071167141,
      "grad_norm": 0.905681312084198,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.1341,
      "step": 155
    },
    {
      "epoch": 0.1268808458723058,
      "grad_norm": 0.9117370247840881,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.2444,
      "step": 156
    },
    {
      "epoch": 0.12769418462789753,
      "grad_norm": 0.8128718733787537,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.1435,
      "step": 157
    },
    {
      "epoch": 0.12850752338348922,
      "grad_norm": 0.8428987264633179,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.1683,
      "step": 158
    },
    {
      "epoch": 0.12932086213908092,
      "grad_norm": 0.7927095890045166,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.1119,
      "step": 159
    },
    {
      "epoch": 0.13013420089467262,
      "grad_norm": 0.8424720168113708,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2159,
      "step": 160
    },
    {
      "epoch": 0.13094753965026434,
      "grad_norm": 0.8847900032997131,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.2035,
      "step": 161
    },
    {
      "epoch": 0.13176087840585604,
      "grad_norm": 0.8231744170188904,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2208,
      "step": 162
    },
    {
      "epoch": 0.13257421716144774,
      "grad_norm": 0.8450943827629089,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.1322,
      "step": 163
    },
    {
      "epoch": 0.13338755591703944,
      "grad_norm": 0.8595624566078186,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.1208,
      "step": 164
    },
    {
      "epoch": 0.13420089467263116,
      "grad_norm": 0.8988872170448303,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.1588,
      "step": 165
    },
    {
      "epoch": 0.13501423342822286,
      "grad_norm": 0.941521942615509,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.2165,
      "step": 166
    },
    {
      "epoch": 0.13582757218381455,
      "grad_norm": 0.9013407826423645,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.2349,
      "step": 167
    },
    {
      "epoch": 0.13664091093940625,
      "grad_norm": 0.9086992144584656,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.1422,
      "step": 168
    },
    {
      "epoch": 0.13745424969499798,
      "grad_norm": 0.9967036247253418,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.248,
      "step": 169
    },
    {
      "epoch": 0.13826758845058967,
      "grad_norm": 0.959007978439331,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.1459,
      "step": 170
    },
    {
      "epoch": 0.13908092720618137,
      "grad_norm": 1.0631060600280762,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.3163,
      "step": 171
    },
    {
      "epoch": 0.13989426596177307,
      "grad_norm": 1.0359704494476318,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.3114,
      "step": 172
    },
    {
      "epoch": 0.1407076047173648,
      "grad_norm": 1.0653396844863892,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.2044,
      "step": 173
    },
    {
      "epoch": 0.1415209434729565,
      "grad_norm": 1.095932960510254,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3218,
      "step": 174
    },
    {
      "epoch": 0.1423342822285482,
      "grad_norm": 1.1184383630752563,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.2199,
      "step": 175
    },
    {
      "epoch": 0.14314762098413988,
      "grad_norm": 1.2736085653305054,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.1616,
      "step": 176
    },
    {
      "epoch": 0.1439609597397316,
      "grad_norm": 1.2406302690505981,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.2473,
      "step": 177
    },
    {
      "epoch": 0.1447742984953233,
      "grad_norm": 1.265307903289795,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.2556,
      "step": 178
    },
    {
      "epoch": 0.145587637250915,
      "grad_norm": 1.3944147825241089,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2484,
      "step": 179
    },
    {
      "epoch": 0.1464009760065067,
      "grad_norm": 1.456769347190857,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.1682,
      "step": 180
    },
    {
      "epoch": 0.14721431476209842,
      "grad_norm": 1.5899291038513184,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2757,
      "step": 181
    },
    {
      "epoch": 0.14802765351769012,
      "grad_norm": 1.9807884693145752,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.0998,
      "step": 182
    },
    {
      "epoch": 0.14884099227328182,
      "grad_norm": 1.6880255937576294,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.1131,
      "step": 183
    },
    {
      "epoch": 0.14965433102887352,
      "grad_norm": 1.8518604040145874,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.0732,
      "step": 184
    },
    {
      "epoch": 0.15046766978446524,
      "grad_norm": 2.2764787673950195,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.0435,
      "step": 185
    },
    {
      "epoch": 0.15128100854005694,
      "grad_norm": 2.2394182682037354,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.2033,
      "step": 186
    },
    {
      "epoch": 0.15209434729564864,
      "grad_norm": 2.6520256996154785,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.0373,
      "step": 187
    },
    {
      "epoch": 0.15290768605124033,
      "grad_norm": 2.4846720695495605,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.1561,
      "step": 188
    },
    {
      "epoch": 0.15372102480683206,
      "grad_norm": 2.847813606262207,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.053,
      "step": 189
    },
    {
      "epoch": 0.15453436356242375,
      "grad_norm": 2.7252371311187744,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.9666,
      "step": 190
    },
    {
      "epoch": 0.15534770231801545,
      "grad_norm": 2.909583568572998,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.1265,
      "step": 191
    },
    {
      "epoch": 0.15616104107360715,
      "grad_norm": 2.8609561920166016,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.0604,
      "step": 192
    },
    {
      "epoch": 0.15697437982919887,
      "grad_norm": 3.3057799339294434,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.162,
      "step": 193
    },
    {
      "epoch": 0.15778771858479057,
      "grad_norm": 3.590224266052246,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.0072,
      "step": 194
    },
    {
      "epoch": 0.15860105734038227,
      "grad_norm": 4.067774772644043,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.1049,
      "step": 195
    },
    {
      "epoch": 0.15941439609597396,
      "grad_norm": 3.859288454055786,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2524,
      "step": 196
    },
    {
      "epoch": 0.1602277348515657,
      "grad_norm": 4.1519341468811035,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.8233,
      "step": 197
    },
    {
      "epoch": 0.1610410736071574,
      "grad_norm": 3.8385350704193115,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.8577,
      "step": 198
    },
    {
      "epoch": 0.16185441236274908,
      "grad_norm": 4.59529972076416,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.8491,
      "step": 199
    },
    {
      "epoch": 0.16266775111834078,
      "grad_norm": 5.844046592712402,
      "learning_rate": 0.0,
      "loss": 1.0195,
      "step": 200
    },
    {
      "epoch": 0.16266775111834078,
      "eval_loss": 1.114859938621521,
      "eval_runtime": 107.2869,
      "eval_samples_per_second": 19.303,
      "eval_steps_per_second": 4.828,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.252687475638272e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}