{
  "best_metric": 1.4565271139144897,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.01685558973494585,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.427794867472926e-05,
      "grad_norm": 2.148855686187744,
      "learning_rate": 1e-05,
      "loss": 2.1105,
      "step": 1
    },
    {
      "epoch": 8.427794867472926e-05,
      "eval_loss": 2.0573813915252686,
      "eval_runtime": 1544.4321,
      "eval_samples_per_second": 12.94,
      "eval_steps_per_second": 3.235,
      "step": 1
    },
    {
      "epoch": 0.00016855589734945852,
      "grad_norm": 1.8630555868148804,
      "learning_rate": 2e-05,
      "loss": 1.9751,
      "step": 2
    },
    {
      "epoch": 0.00025283384602418777,
      "grad_norm": 1.6783190965652466,
      "learning_rate": 3e-05,
      "loss": 1.7007,
      "step": 3
    },
    {
      "epoch": 0.00033711179469891704,
      "grad_norm": 1.4482625722885132,
      "learning_rate": 4e-05,
      "loss": 1.5429,
      "step": 4
    },
    {
      "epoch": 0.00042138974337364626,
      "grad_norm": 1.7178997993469238,
      "learning_rate": 5e-05,
      "loss": 1.6393,
      "step": 5
    },
    {
      "epoch": 0.0005056676920483755,
      "grad_norm": 1.1909184455871582,
      "learning_rate": 6e-05,
      "loss": 1.6192,
      "step": 6
    },
    {
      "epoch": 0.0005899456407231048,
      "grad_norm": 1.0116609334945679,
      "learning_rate": 7e-05,
      "loss": 1.86,
      "step": 7
    },
    {
      "epoch": 0.0006742235893978341,
      "grad_norm": 0.9478005170822144,
      "learning_rate": 8e-05,
      "loss": 1.7564,
      "step": 8
    },
    {
      "epoch": 0.0007585015380725634,
      "grad_norm": 0.9280062913894653,
      "learning_rate": 9e-05,
      "loss": 1.8039,
      "step": 9
    },
    {
      "epoch": 0.0008427794867472925,
      "grad_norm": 0.9564406275749207,
      "learning_rate": 0.0001,
      "loss": 1.6172,
      "step": 10
    },
    {
      "epoch": 0.0009270574354220218,
      "grad_norm": 0.9788842797279358,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.7433,
      "step": 11
    },
    {
      "epoch": 0.001011335384096751,
      "grad_norm": 1.0648996829986572,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.6529,
      "step": 12
    },
    {
      "epoch": 0.0010956133327714803,
      "grad_norm": 0.8593961000442505,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.476,
      "step": 13
    },
    {
      "epoch": 0.0011798912814462096,
      "grad_norm": 0.7885779738426208,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.0156,
      "step": 14
    },
    {
      "epoch": 0.001264169230120939,
      "grad_norm": 0.791583240032196,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7382,
      "step": 15
    },
    {
      "epoch": 0.0013484471787956682,
      "grad_norm": 0.7276984453201294,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.7673,
      "step": 16
    },
    {
      "epoch": 0.0014327251274703974,
      "grad_norm": 0.705528736114502,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.5786,
      "step": 17
    },
    {
      "epoch": 0.0015170030761451267,
      "grad_norm": 0.619422435760498,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3861,
      "step": 18
    },
    {
      "epoch": 0.0016012810248198558,
      "grad_norm": 0.7505267858505249,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.7197,
      "step": 19
    },
    {
      "epoch": 0.001685558973494585,
      "grad_norm": 0.6622971296310425,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5297,
      "step": 20
    },
    {
      "epoch": 0.0017698369221693143,
      "grad_norm": 0.6275780200958252,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.5839,
      "step": 21
    },
    {
      "epoch": 0.0018541148708440436,
      "grad_norm": 0.679114580154419,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.7993,
      "step": 22
    },
    {
      "epoch": 0.0019383928195187729,
      "grad_norm": 0.8077395558357239,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.5271,
      "step": 23
    },
    {
      "epoch": 0.002022670768193502,
      "grad_norm": 0.7224380373954773,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5168,
      "step": 24
    },
    {
      "epoch": 0.0021069487168682314,
      "grad_norm": 0.6832942962646484,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.407,
      "step": 25
    },
    {
      "epoch": 0.0021912266655429607,
      "grad_norm": 0.5775948166847229,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3875,
      "step": 26
    },
    {
      "epoch": 0.00227550461421769,
      "grad_norm": 0.6365522146224976,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.614,
      "step": 27
    },
    {
      "epoch": 0.0023597825628924192,
      "grad_norm": 0.7473817467689514,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.7015,
      "step": 28
    },
    {
      "epoch": 0.0024440605115671485,
      "grad_norm": 0.6332816481590271,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6255,
      "step": 29
    },
    {
      "epoch": 0.002528338460241878,
      "grad_norm": 0.6358436942100525,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7346,
      "step": 30
    },
    {
      "epoch": 0.002612616408916607,
      "grad_norm": 0.6233913898468018,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.6548,
      "step": 31
    },
    {
      "epoch": 0.0026968943575913363,
      "grad_norm": 0.587378203868866,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.6502,
      "step": 32
    },
    {
      "epoch": 0.0027811723062660656,
      "grad_norm": 0.7984997630119324,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6918,
      "step": 33
    },
    {
      "epoch": 0.002865450254940795,
      "grad_norm": 0.651034414768219,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.6203,
      "step": 34
    },
    {
      "epoch": 0.002949728203615524,
      "grad_norm": 0.7940975427627563,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.5908,
      "step": 35
    },
    {
      "epoch": 0.0030340061522902534,
      "grad_norm": 0.756313681602478,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.8236,
      "step": 36
    },
    {
      "epoch": 0.0031182841009649827,
      "grad_norm": 0.6613308191299438,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.5652,
      "step": 37
    },
    {
      "epoch": 0.0032025620496397116,
      "grad_norm": 0.7427698373794556,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.5391,
      "step": 38
    },
    {
      "epoch": 0.003286839998314441,
      "grad_norm": 0.8335131406784058,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.8327,
      "step": 39
    },
    {
      "epoch": 0.00337111794698917,
      "grad_norm": 0.8421139717102051,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.7076,
      "step": 40
    },
    {
      "epoch": 0.0034553958956638994,
      "grad_norm": 0.6234191060066223,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.8075,
      "step": 41
    },
    {
      "epoch": 0.0035396738443386287,
      "grad_norm": 0.7577528953552246,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.6297,
      "step": 42
    },
    {
      "epoch": 0.003623951793013358,
      "grad_norm": 0.8572260141372681,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5807,
      "step": 43
    },
    {
      "epoch": 0.003708229741688087,
      "grad_norm": 0.7775949835777283,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.6965,
      "step": 44
    },
    {
      "epoch": 0.0037925076903628165,
      "grad_norm": 0.6420420408248901,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.524,
      "step": 45
    },
    {
      "epoch": 0.0038767856390375457,
      "grad_norm": 0.7884761691093445,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.6729,
      "step": 46
    },
    {
      "epoch": 0.0039610635877122755,
      "grad_norm": 0.787156343460083,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.7154,
      "step": 47
    },
    {
      "epoch": 0.004045341536387004,
      "grad_norm": 0.7888066172599792,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9746,
      "step": 48
    },
    {
      "epoch": 0.004129619485061734,
      "grad_norm": 0.9960417747497559,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.7341,
      "step": 49
    },
    {
      "epoch": 0.004213897433736463,
      "grad_norm": 0.8822570443153381,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.7701,
      "step": 50
    },
    {
      "epoch": 0.004213897433736463,
      "eval_loss": 1.5395351648330688,
      "eval_runtime": 1551.3419,
      "eval_samples_per_second": 12.882,
      "eval_steps_per_second": 3.221,
      "step": 50
    },
    {
      "epoch": 0.004298175382411192,
      "grad_norm": 0.7310632467269897,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.4223,
      "step": 51
    },
    {
      "epoch": 0.004382453331085921,
      "grad_norm": 0.7230385541915894,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.5037,
      "step": 52
    },
    {
      "epoch": 0.00446673127976065,
      "grad_norm": 0.6643477082252502,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.4662,
      "step": 53
    },
    {
      "epoch": 0.00455100922843538,
      "grad_norm": 0.4829084277153015,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.0906,
      "step": 54
    },
    {
      "epoch": 0.004635287177110109,
      "grad_norm": 0.5533672571182251,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4786,
      "step": 55
    },
    {
      "epoch": 0.0047195651257848385,
      "grad_norm": 0.5138788223266602,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.4468,
      "step": 56
    },
    {
      "epoch": 0.004803843074459567,
      "grad_norm": 0.5894024968147278,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.4552,
      "step": 57
    },
    {
      "epoch": 0.004888121023134297,
      "grad_norm": 0.5128427147865295,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3466,
      "step": 58
    },
    {
      "epoch": 0.004972398971809026,
      "grad_norm": 0.5286391377449036,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.2589,
      "step": 59
    },
    {
      "epoch": 0.005056676920483756,
      "grad_norm": 0.3991178572177887,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9813,
      "step": 60
    },
    {
      "epoch": 0.005140954869158484,
      "grad_norm": 0.6020731329917908,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3982,
      "step": 61
    },
    {
      "epoch": 0.005225232817833214,
      "grad_norm": 0.7451138496398926,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.4749,
      "step": 62
    },
    {
      "epoch": 0.005309510766507943,
      "grad_norm": 0.5871690511703491,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3155,
      "step": 63
    },
    {
      "epoch": 0.005393788715182673,
      "grad_norm": 0.5240890383720398,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.2181,
      "step": 64
    },
    {
      "epoch": 0.0054780666638574015,
      "grad_norm": 0.6134968400001526,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6436,
      "step": 65
    },
    {
      "epoch": 0.005562344612532131,
      "grad_norm": 0.5027713775634766,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.4021,
      "step": 66
    },
    {
      "epoch": 0.00564662256120686,
      "grad_norm": 0.5690268278121948,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.506,
      "step": 67
    },
    {
      "epoch": 0.00573090050988159,
      "grad_norm": 0.517443835735321,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.301,
      "step": 68
    },
    {
      "epoch": 0.005815178458556319,
      "grad_norm": 0.576786994934082,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.5677,
      "step": 69
    },
    {
      "epoch": 0.005899456407231048,
      "grad_norm": 0.5443838834762573,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.4369,
      "step": 70
    },
    {
      "epoch": 0.005983734355905777,
      "grad_norm": 0.5121707320213318,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2935,
      "step": 71
    },
    {
      "epoch": 0.006068012304580507,
      "grad_norm": 0.5349838137626648,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.3198,
      "step": 72
    },
    {
      "epoch": 0.006152290253255236,
      "grad_norm": 0.5736881494522095,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.3988,
      "step": 73
    },
    {
      "epoch": 0.006236568201929965,
      "grad_norm": 0.5801308155059814,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.4923,
      "step": 74
    },
    {
      "epoch": 0.006320846150604694,
      "grad_norm": 0.5645437836647034,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.4074,
      "step": 75
    },
    {
      "epoch": 0.006405124099279423,
      "grad_norm": 0.5769533514976501,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.4748,
      "step": 76
    },
    {
      "epoch": 0.006489402047954153,
      "grad_norm": 0.7202831506729126,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.4046,
      "step": 77
    },
    {
      "epoch": 0.006573679996628882,
      "grad_norm": 0.6109544038772583,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.4079,
      "step": 78
    },
    {
      "epoch": 0.006657957945303611,
      "grad_norm": 0.5733642578125,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.5315,
      "step": 79
    },
    {
      "epoch": 0.00674223589397834,
      "grad_norm": 0.5498372912406921,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.3167,
      "step": 80
    },
    {
      "epoch": 0.00682651384265307,
      "grad_norm": 0.6294428706169128,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.5795,
      "step": 81
    },
    {
      "epoch": 0.006910791791327799,
      "grad_norm": 0.5314324498176575,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.3943,
      "step": 82
    },
    {
      "epoch": 0.0069950697400025285,
      "grad_norm": 0.6279960870742798,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2911,
      "step": 83
    },
    {
      "epoch": 0.007079347688677257,
      "grad_norm": 0.6536868810653687,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.5565,
      "step": 84
    },
    {
      "epoch": 0.007163625637351987,
      "grad_norm": 0.5328207015991211,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.3364,
      "step": 85
    },
    {
      "epoch": 0.007247903586026716,
      "grad_norm": 0.67548006772995,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3383,
      "step": 86
    },
    {
      "epoch": 0.0073321815347014456,
      "grad_norm": 0.5352726578712463,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.509,
      "step": 87
    },
    {
      "epoch": 0.007416459483376174,
      "grad_norm": 0.6060234308242798,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.4048,
      "step": 88
    },
    {
      "epoch": 0.007500737432050904,
      "grad_norm": 0.6160685420036316,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.6497,
      "step": 89
    },
    {
      "epoch": 0.007585015380725633,
      "grad_norm": 0.6280525922775269,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.4788,
      "step": 90
    },
    {
      "epoch": 0.007669293329400363,
      "grad_norm": 0.6451821327209473,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.6193,
      "step": 91
    },
    {
      "epoch": 0.0077535712780750915,
      "grad_norm": 0.5721803903579712,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.6932,
      "step": 92
    },
    {
      "epoch": 0.007837849226749821,
      "grad_norm": 0.6705061197280884,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.857,
      "step": 93
    },
    {
      "epoch": 0.007922127175424551,
      "grad_norm": 0.6482031345367432,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.6017,
      "step": 94
    },
    {
      "epoch": 0.008006405124099279,
      "grad_norm": 0.620942234992981,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.6512,
      "step": 95
    },
    {
      "epoch": 0.008090683072774009,
      "grad_norm": 0.8141463398933411,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.8437,
      "step": 96
    },
    {
      "epoch": 0.008174961021448738,
      "grad_norm": 0.6997731328010559,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.728,
      "step": 97
    },
    {
      "epoch": 0.008259238970123468,
      "grad_norm": 0.7608988285064697,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.6754,
      "step": 98
    },
    {
      "epoch": 0.008343516918798196,
      "grad_norm": 0.728373110294342,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.7281,
      "step": 99
    },
    {
      "epoch": 0.008427794867472926,
      "grad_norm": 0.8952184319496155,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.6911,
      "step": 100
    },
    {
      "epoch": 0.008427794867472926,
      "eval_loss": 1.498549461364746,
      "eval_runtime": 1555.394,
      "eval_samples_per_second": 12.849,
      "eval_steps_per_second": 3.213,
      "step": 100
    },
    {
      "epoch": 0.008512072816147655,
      "grad_norm": 1.0058871507644653,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.6635,
      "step": 101
    },
    {
      "epoch": 0.008596350764822383,
      "grad_norm": 0.5801363587379456,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.2125,
      "step": 102
    },
    {
      "epoch": 0.008680628713497113,
      "grad_norm": 0.5247597694396973,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.4579,
      "step": 103
    },
    {
      "epoch": 0.008764906662171843,
      "grad_norm": 0.44460782408714294,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.1384,
      "step": 104
    },
    {
      "epoch": 0.008849184610846572,
      "grad_norm": 0.5345998406410217,
      "learning_rate": 5e-05,
      "loss": 1.3257,
      "step": 105
    },
    {
      "epoch": 0.0089334625595213,
      "grad_norm": 0.5826507210731506,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2035,
      "step": 106
    },
    {
      "epoch": 0.00901774050819603,
      "grad_norm": 0.5259659886360168,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.2496,
      "step": 107
    },
    {
      "epoch": 0.00910201845687076,
      "grad_norm": 0.5049336552619934,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.108,
      "step": 108
    },
    {
      "epoch": 0.00918629640554549,
      "grad_norm": 0.5401145219802856,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.3006,
      "step": 109
    },
    {
      "epoch": 0.009270574354220218,
      "grad_norm": 0.6248597502708435,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.8006,
      "step": 110
    },
    {
      "epoch": 0.009354852302894947,
      "grad_norm": 0.528260350227356,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.3112,
      "step": 111
    },
    {
      "epoch": 0.009439130251569677,
      "grad_norm": 0.5718809962272644,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.3361,
      "step": 112
    },
    {
      "epoch": 0.009523408200244407,
      "grad_norm": 0.6159736514091492,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.3255,
      "step": 113
    },
    {
      "epoch": 0.009607686148919135,
      "grad_norm": 0.6161823868751526,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.3859,
      "step": 114
    },
    {
      "epoch": 0.009691964097593864,
      "grad_norm": 0.5434644222259521,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.539,
      "step": 115
    },
    {
      "epoch": 0.009776242046268594,
      "grad_norm": 0.49302878975868225,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.4317,
      "step": 116
    },
    {
      "epoch": 0.009860519994943324,
      "grad_norm": 0.5489768981933594,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.4004,
      "step": 117
    },
    {
      "epoch": 0.009944797943618052,
      "grad_norm": 0.5786827206611633,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.3581,
      "step": 118
    },
    {
      "epoch": 0.010029075892292781,
      "grad_norm": 0.5377670526504517,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.3488,
      "step": 119
    },
    {
      "epoch": 0.010113353840967511,
      "grad_norm": 0.5539676547050476,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.2686,
      "step": 120
    },
    {
      "epoch": 0.010197631789642241,
      "grad_norm": 0.5353489518165588,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.4558,
      "step": 121
    },
    {
      "epoch": 0.010281909738316969,
      "grad_norm": 0.7007184028625488,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.3668,
      "step": 122
    },
    {
      "epoch": 0.010366187686991699,
      "grad_norm": 0.5784412622451782,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.2657,
      "step": 123
    },
    {
      "epoch": 0.010450465635666428,
      "grad_norm": 0.5282594561576843,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4123,
      "step": 124
    },
    {
      "epoch": 0.010534743584341158,
      "grad_norm": 0.5743001103401184,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.4192,
      "step": 125
    },
    {
      "epoch": 0.010619021533015886,
      "grad_norm": 0.5273685455322266,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.4203,
      "step": 126
    },
    {
      "epoch": 0.010703299481690616,
      "grad_norm": 0.528648316860199,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.5005,
      "step": 127
    },
    {
      "epoch": 0.010787577430365345,
      "grad_norm": 0.5697153210639954,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.4981,
      "step": 128
    },
    {
      "epoch": 0.010871855379040073,
      "grad_norm": 0.5040446519851685,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.516,
      "step": 129
    },
    {
      "epoch": 0.010956133327714803,
      "grad_norm": 0.5481293201446533,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.4138,
      "step": 130
    },
    {
      "epoch": 0.011040411276389533,
      "grad_norm": 0.5494363903999329,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2937,
      "step": 131
    },
    {
      "epoch": 0.011124689225064262,
      "grad_norm": 0.5701969265937805,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.3818,
      "step": 132
    },
    {
      "epoch": 0.01120896717373899,
      "grad_norm": 0.5919198989868164,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.4756,
      "step": 133
    },
    {
      "epoch": 0.01129324512241372,
      "grad_norm": 0.5880911350250244,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.6002,
      "step": 134
    },
    {
      "epoch": 0.01137752307108845,
      "grad_norm": 0.6259672045707703,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.728,
      "step": 135
    },
    {
      "epoch": 0.01146180101976318,
      "grad_norm": 0.6427291631698608,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.8341,
      "step": 136
    },
    {
      "epoch": 0.011546078968437908,
      "grad_norm": 0.6046552658081055,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.7211,
      "step": 137
    },
    {
      "epoch": 0.011630356917112637,
      "grad_norm": 0.645704448223114,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.7456,
      "step": 138
    },
    {
      "epoch": 0.011714634865787367,
      "grad_norm": 0.6904752254486084,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.6065,
      "step": 139
    },
    {
      "epoch": 0.011798912814462097,
      "grad_norm": 0.6672500371932983,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.7662,
      "step": 140
    },
    {
      "epoch": 0.011883190763136825,
      "grad_norm": 0.603736162185669,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.7634,
      "step": 141
    },
    {
      "epoch": 0.011967468711811554,
      "grad_norm": 0.7412917613983154,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.7786,
      "step": 142
    },
    {
      "epoch": 0.012051746660486284,
      "grad_norm": 0.6253740787506104,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.661,
      "step": 143
    },
    {
      "epoch": 0.012136024609161014,
      "grad_norm": 0.6209424734115601,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.5376,
      "step": 144
    },
    {
      "epoch": 0.012220302557835742,
      "grad_norm": 0.7691958546638489,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.6808,
      "step": 145
    },
    {
      "epoch": 0.012304580506510471,
      "grad_norm": 0.6747142672538757,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2813,
      "step": 146
    },
    {
      "epoch": 0.012388858455185201,
      "grad_norm": 0.692360520362854,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.8335,
      "step": 147
    },
    {
      "epoch": 0.01247313640385993,
      "grad_norm": 0.6679973602294922,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.8344,
      "step": 148
    },
    {
      "epoch": 0.012557414352534659,
      "grad_norm": 0.696410596370697,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.5232,
      "step": 149
    },
    {
      "epoch": 0.012641692301209389,
      "grad_norm": 0.6820076704025269,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3038,
      "step": 150
    },
    {
      "epoch": 0.012641692301209389,
      "eval_loss": 1.4636555910110474,
      "eval_runtime": 1555.5309,
      "eval_samples_per_second": 12.848,
      "eval_steps_per_second": 3.212,
      "step": 150
    },
    {
      "epoch": 0.012725970249884118,
      "grad_norm": 0.5721868872642517,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.4502,
      "step": 151
    },
    {
      "epoch": 0.012810248198558846,
      "grad_norm": 0.5887200236320496,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.4821,
      "step": 152
    },
    {
      "epoch": 0.012894526147233576,
      "grad_norm": 0.4974271059036255,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.1265,
      "step": 153
    },
    {
      "epoch": 0.012978804095908306,
      "grad_norm": 0.5448725819587708,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.1771,
      "step": 154
    },
    {
      "epoch": 0.013063082044583035,
      "grad_norm": 0.5793499946594238,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.4129,
      "step": 155
    },
    {
      "epoch": 0.013147359993257763,
      "grad_norm": 0.5004870295524597,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.3348,
      "step": 156
    },
    {
      "epoch": 0.013231637941932493,
      "grad_norm": 0.516072154045105,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.2199,
      "step": 157
    },
    {
      "epoch": 0.013315915890607223,
      "grad_norm": 0.5186340808868408,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.2645,
      "step": 158
    },
    {
      "epoch": 0.013400193839281952,
      "grad_norm": 0.5328534841537476,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.3915,
      "step": 159
    },
    {
      "epoch": 0.01348447178795668,
      "grad_norm": 0.4860214293003082,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2598,
      "step": 160
    },
    {
      "epoch": 0.01356874973663141,
      "grad_norm": 0.5569485425949097,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.3829,
      "step": 161
    },
    {
      "epoch": 0.01365302768530614,
      "grad_norm": 0.45528507232666016,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1443,
      "step": 162
    },
    {
      "epoch": 0.01373730563398087,
      "grad_norm": 0.5397240519523621,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.5006,
      "step": 163
    },
    {
      "epoch": 0.013821583582655598,
      "grad_norm": 0.5786639451980591,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.396,
      "step": 164
    },
    {
      "epoch": 0.013905861531330327,
      "grad_norm": 0.5532152652740479,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.369,
      "step": 165
    },
    {
      "epoch": 0.013990139480005057,
      "grad_norm": 0.6554055213928223,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.575,
      "step": 166
    },
    {
      "epoch": 0.014074417428679787,
      "grad_norm": 0.5662513971328735,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.2735,
      "step": 167
    },
    {
      "epoch": 0.014158695377354515,
      "grad_norm": 0.48727068305015564,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.3203,
      "step": 168
    },
    {
      "epoch": 0.014242973326029244,
      "grad_norm": 0.5572632551193237,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.5727,
      "step": 169
    },
    {
      "epoch": 0.014327251274703974,
      "grad_norm": 0.5554003119468689,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.4469,
      "step": 170
    },
    {
      "epoch": 0.014411529223378704,
      "grad_norm": 0.604663610458374,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.276,
      "step": 171
    },
    {
      "epoch": 0.014495807172053432,
      "grad_norm": 0.5023248791694641,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.1691,
      "step": 172
    },
    {
      "epoch": 0.014580085120728161,
      "grad_norm": 0.6692169308662415,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.4344,
      "step": 173
    },
    {
      "epoch": 0.014664363069402891,
      "grad_norm": 0.5340934991836548,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3681,
      "step": 174
    },
    {
      "epoch": 0.01474864101807762,
      "grad_norm": 0.5445293188095093,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.3954,
      "step": 175
    },
    {
      "epoch": 0.014832918966752349,
      "grad_norm": 0.5569987893104553,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.3556,
      "step": 176
    },
    {
      "epoch": 0.014917196915427079,
      "grad_norm": 0.5029589533805847,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.5216,
      "step": 177
    },
    {
      "epoch": 0.015001474864101808,
      "grad_norm": 0.5939149856567383,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.7438,
      "step": 178
    },
    {
      "epoch": 0.015085752812776536,
      "grad_norm": 0.5632242560386658,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2006,
      "step": 179
    },
    {
      "epoch": 0.015170030761451266,
      "grad_norm": 0.57479327917099,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.6389,
      "step": 180
    },
    {
      "epoch": 0.015254308710125996,
      "grad_norm": 0.5536034107208252,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3654,
      "step": 181
    },
    {
      "epoch": 0.015338586658800725,
      "grad_norm": 0.5989298224449158,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.5586,
      "step": 182
    },
    {
      "epoch": 0.015422864607475453,
      "grad_norm": 0.6151905655860901,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.5948,
      "step": 183
    },
    {
      "epoch": 0.015507142556150183,
      "grad_norm": 0.5719772577285767,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.3108,
      "step": 184
    },
    {
      "epoch": 0.015591420504824913,
      "grad_norm": 0.5508275032043457,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.5518,
      "step": 185
    },
    {
      "epoch": 0.015675698453499642,
      "grad_norm": 0.6428425908088684,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.8444,
      "step": 186
    },
    {
      "epoch": 0.015759976402174372,
      "grad_norm": 0.5790170431137085,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.5014,
      "step": 187
    },
    {
      "epoch": 0.015844254350849102,
      "grad_norm": 0.6228124499320984,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.6388,
      "step": 188
    },
    {
      "epoch": 0.015928532299523828,
      "grad_norm": 0.5625091195106506,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.4411,
      "step": 189
    },
    {
      "epoch": 0.016012810248198558,
      "grad_norm": 0.7365487217903137,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.7457,
      "step": 190
    },
    {
      "epoch": 0.016097088196873287,
      "grad_norm": 0.6475622057914734,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.4968,
      "step": 191
    },
    {
      "epoch": 0.016181366145548017,
      "grad_norm": 0.6350623965263367,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.4749,
      "step": 192
    },
    {
      "epoch": 0.016265644094222747,
      "grad_norm": 0.5962168574333191,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.7879,
      "step": 193
    },
    {
      "epoch": 0.016349922042897477,
      "grad_norm": 0.680426299571991,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.4509,
      "step": 194
    },
    {
      "epoch": 0.016434199991572206,
      "grad_norm": 0.6138383746147156,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.7542,
      "step": 195
    },
    {
      "epoch": 0.016518477940246936,
      "grad_norm": 0.668582022190094,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.4556,
      "step": 196
    },
    {
      "epoch": 0.016602755888921662,
      "grad_norm": 0.6793115735054016,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.9594,
      "step": 197
    },
    {
      "epoch": 0.016687033837596392,
      "grad_norm": 0.6664149761199951,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.7787,
      "step": 198
    },
    {
      "epoch": 0.01677131178627112,
      "grad_norm": 0.7501089572906494,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.5584,
      "step": 199
    },
    {
      "epoch": 0.01685558973494585,
      "grad_norm": 0.7250977158546448,
      "learning_rate": 0.0,
      "loss": 1.5243,
      "step": 200
    },
    {
      "epoch": 0.01685558973494585,
      "eval_loss": 1.4565271139144897,
      "eval_runtime": 1552.4714,
      "eval_samples_per_second": 12.873,
      "eval_steps_per_second": 3.219,
      "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": 3.081138984588411e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}