{
  "best_metric": 0.3653714060783386,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02697690102849435,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013488450514247176,
      "grad_norm": 0.7375573515892029,
      "learning_rate": 1e-05,
      "loss": 0.619,
      "step": 1
    },
    {
      "epoch": 0.00013488450514247176,
      "eval_loss": 0.5535552501678467,
      "eval_runtime": 262.1617,
      "eval_samples_per_second": 47.631,
      "eval_steps_per_second": 11.909,
      "step": 1
    },
    {
      "epoch": 0.0002697690102849435,
      "grad_norm": 0.7183876633644104,
      "learning_rate": 2e-05,
      "loss": 0.6297,
      "step": 2
    },
    {
      "epoch": 0.00040465351542741526,
      "grad_norm": 0.6348766088485718,
      "learning_rate": 3e-05,
      "loss": 0.5755,
      "step": 3
    },
    {
      "epoch": 0.000539538020569887,
      "grad_norm": 0.5318180322647095,
      "learning_rate": 4e-05,
      "loss": 0.5212,
      "step": 4
    },
    {
      "epoch": 0.0006744225257123588,
      "grad_norm": 0.4897218644618988,
      "learning_rate": 5e-05,
      "loss": 0.4963,
      "step": 5
    },
    {
      "epoch": 0.0008093070308548305,
      "grad_norm": 0.4619118273258209,
      "learning_rate": 6e-05,
      "loss": 0.4524,
      "step": 6
    },
    {
      "epoch": 0.0009441915359973024,
      "grad_norm": 0.4772312641143799,
      "learning_rate": 7e-05,
      "loss": 0.4057,
      "step": 7
    },
    {
      "epoch": 0.001079076041139774,
      "grad_norm": 0.49830466508865356,
      "learning_rate": 8e-05,
      "loss": 0.4654,
      "step": 8
    },
    {
      "epoch": 0.0012139605462822458,
      "grad_norm": 0.5150027275085449,
      "learning_rate": 9e-05,
      "loss": 0.4528,
      "step": 9
    },
    {
      "epoch": 0.0013488450514247176,
      "grad_norm": 0.4883197247982025,
      "learning_rate": 0.0001,
      "loss": 0.4683,
      "step": 10
    },
    {
      "epoch": 0.0014837295565671893,
      "grad_norm": 0.5665213465690613,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5624,
      "step": 11
    },
    {
      "epoch": 0.001618614061709661,
      "grad_norm": 0.4944498836994171,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5727,
      "step": 12
    },
    {
      "epoch": 0.0017534985668521328,
      "grad_norm": 0.457690566778183,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4831,
      "step": 13
    },
    {
      "epoch": 0.0018883830719946047,
      "grad_norm": 0.4723391830921173,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4807,
      "step": 14
    },
    {
      "epoch": 0.0020232675771370764,
      "grad_norm": 0.46450331807136536,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5013,
      "step": 15
    },
    {
      "epoch": 0.002158152082279548,
      "grad_norm": 0.4473508596420288,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4734,
      "step": 16
    },
    {
      "epoch": 0.00229303658742202,
      "grad_norm": 0.44036874175071716,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4924,
      "step": 17
    },
    {
      "epoch": 0.0024279210925644916,
      "grad_norm": 0.43315592408180237,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.4552,
      "step": 18
    },
    {
      "epoch": 0.0025628055977069634,
      "grad_norm": 0.42718714475631714,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4542,
      "step": 19
    },
    {
      "epoch": 0.002697690102849435,
      "grad_norm": 0.42780622839927673,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4212,
      "step": 20
    },
    {
      "epoch": 0.002832574607991907,
      "grad_norm": 0.48322251439094543,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.4701,
      "step": 21
    },
    {
      "epoch": 0.0029674591131343786,
      "grad_norm": 0.4247865080833435,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4139,
      "step": 22
    },
    {
      "epoch": 0.0031023436182768503,
      "grad_norm": 0.46833139657974243,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4707,
      "step": 23
    },
    {
      "epoch": 0.003237228123419322,
      "grad_norm": 0.4637615382671356,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4475,
      "step": 24
    },
    {
      "epoch": 0.003372112628561794,
      "grad_norm": 0.47445815801620483,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.427,
      "step": 25
    },
    {
      "epoch": 0.0035069971337042655,
      "grad_norm": 0.4429916441440582,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3974,
      "step": 26
    },
    {
      "epoch": 0.0036418816388467377,
      "grad_norm": 0.4321354031562805,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4111,
      "step": 27
    },
    {
      "epoch": 0.0037767661439892094,
      "grad_norm": 0.42871013283729553,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.3995,
      "step": 28
    },
    {
      "epoch": 0.003911650649131681,
      "grad_norm": 0.4513198435306549,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3615,
      "step": 29
    },
    {
      "epoch": 0.004046535154274153,
      "grad_norm": 0.4309406280517578,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3835,
      "step": 30
    },
    {
      "epoch": 0.004181419659416624,
      "grad_norm": 0.4923899173736572,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4012,
      "step": 31
    },
    {
      "epoch": 0.004316304164559096,
      "grad_norm": 0.4715842008590698,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.344,
      "step": 32
    },
    {
      "epoch": 0.004451188669701568,
      "grad_norm": 0.4990752041339874,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.414,
      "step": 33
    },
    {
      "epoch": 0.00458607317484404,
      "grad_norm": 0.5114120841026306,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4346,
      "step": 34
    },
    {
      "epoch": 0.004720957679986511,
      "grad_norm": 0.5033982396125793,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3961,
      "step": 35
    },
    {
      "epoch": 0.004855842185128983,
      "grad_norm": 0.5176622271537781,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3634,
      "step": 36
    },
    {
      "epoch": 0.0049907266902714555,
      "grad_norm": 0.4883003234863281,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.3363,
      "step": 37
    },
    {
      "epoch": 0.005125611195413927,
      "grad_norm": 0.49539199471473694,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3966,
      "step": 38
    },
    {
      "epoch": 0.005260495700556399,
      "grad_norm": 0.5086225271224976,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3377,
      "step": 39
    },
    {
      "epoch": 0.00539538020569887,
      "grad_norm": 0.47139525413513184,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.325,
      "step": 40
    },
    {
      "epoch": 0.005530264710841342,
      "grad_norm": 0.5271187424659729,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3476,
      "step": 41
    },
    {
      "epoch": 0.005665149215983814,
      "grad_norm": 0.5539581179618835,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3642,
      "step": 42
    },
    {
      "epoch": 0.005800033721126286,
      "grad_norm": 0.5593342781066895,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.3203,
      "step": 43
    },
    {
      "epoch": 0.005934918226268757,
      "grad_norm": 0.563308835029602,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.325,
      "step": 44
    },
    {
      "epoch": 0.006069802731411229,
      "grad_norm": 0.5519070625305176,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.3488,
      "step": 45
    },
    {
      "epoch": 0.006204687236553701,
      "grad_norm": 0.5657252669334412,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3344,
      "step": 46
    },
    {
      "epoch": 0.006339571741696173,
      "grad_norm": 0.5870583057403564,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3087,
      "step": 47
    },
    {
      "epoch": 0.006474456246838644,
      "grad_norm": 0.6925362944602966,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.361,
      "step": 48
    },
    {
      "epoch": 0.006609340751981116,
      "grad_norm": 0.6307148337364197,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3025,
      "step": 49
    },
    {
      "epoch": 0.006744225257123588,
      "grad_norm": 0.7876100540161133,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2675,
      "step": 50
    },
    {
      "epoch": 0.006744225257123588,
      "eval_loss": 0.40518489480018616,
      "eval_runtime": 262.0707,
      "eval_samples_per_second": 47.647,
      "eval_steps_per_second": 11.913,
      "step": 50
    },
    {
      "epoch": 0.00687910976226606,
      "grad_norm": 0.5271069407463074,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.557,
      "step": 51
    },
    {
      "epoch": 0.007013994267408531,
      "grad_norm": 0.4653015732765198,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.531,
      "step": 52
    },
    {
      "epoch": 0.007148878772551003,
      "grad_norm": 0.44532185792922974,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5344,
      "step": 53
    },
    {
      "epoch": 0.007283763277693475,
      "grad_norm": 0.3872828781604767,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4531,
      "step": 54
    },
    {
      "epoch": 0.007418647782835947,
      "grad_norm": 0.3389751613140106,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4521,
      "step": 55
    },
    {
      "epoch": 0.007553532287978419,
      "grad_norm": 0.35062122344970703,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4501,
      "step": 56
    },
    {
      "epoch": 0.00768841679312089,
      "grad_norm": 0.3422028124332428,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4457,
      "step": 57
    },
    {
      "epoch": 0.007823301298263361,
      "grad_norm": 0.3337987959384918,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.4037,
      "step": 58
    },
    {
      "epoch": 0.007958185803405834,
      "grad_norm": 0.30135399103164673,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.357,
      "step": 59
    },
    {
      "epoch": 0.008093070308548306,
      "grad_norm": 0.3318193554878235,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3954,
      "step": 60
    },
    {
      "epoch": 0.008227954813690777,
      "grad_norm": 0.37476521730422974,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.4687,
      "step": 61
    },
    {
      "epoch": 0.008362839318833248,
      "grad_norm": 0.341511994600296,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4437,
      "step": 62
    },
    {
      "epoch": 0.008497723823975721,
      "grad_norm": 0.36639419198036194,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.467,
      "step": 63
    },
    {
      "epoch": 0.008632608329118193,
      "grad_norm": 0.3458079397678375,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.4214,
      "step": 64
    },
    {
      "epoch": 0.008767492834260664,
      "grad_norm": 0.39767682552337646,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5452,
      "step": 65
    },
    {
      "epoch": 0.008902377339403135,
      "grad_norm": 0.3590928614139557,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4525,
      "step": 66
    },
    {
      "epoch": 0.009037261844545608,
      "grad_norm": 0.35452184081077576,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4318,
      "step": 67
    },
    {
      "epoch": 0.00917214634968808,
      "grad_norm": 0.36540916562080383,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4316,
      "step": 68
    },
    {
      "epoch": 0.009307030854830551,
      "grad_norm": 0.37473064661026,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3947,
      "step": 69
    },
    {
      "epoch": 0.009441915359973022,
      "grad_norm": 0.40132176876068115,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.4607,
      "step": 70
    },
    {
      "epoch": 0.009576799865115495,
      "grad_norm": 0.3760310113430023,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4158,
      "step": 71
    },
    {
      "epoch": 0.009711684370257967,
      "grad_norm": 0.39298850297927856,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4337,
      "step": 72
    },
    {
      "epoch": 0.009846568875400438,
      "grad_norm": 0.3648068308830261,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4042,
      "step": 73
    },
    {
      "epoch": 0.009981453380542911,
      "grad_norm": 0.38943108916282654,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4239,
      "step": 74
    },
    {
      "epoch": 0.010116337885685382,
      "grad_norm": 0.3754552900791168,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3954,
      "step": 75
    },
    {
      "epoch": 0.010251222390827854,
      "grad_norm": 0.3772151470184326,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.4149,
      "step": 76
    },
    {
      "epoch": 0.010386106895970325,
      "grad_norm": 0.3755127489566803,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.3837,
      "step": 77
    },
    {
      "epoch": 0.010520991401112798,
      "grad_norm": 0.38585326075553894,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4065,
      "step": 78
    },
    {
      "epoch": 0.01065587590625527,
      "grad_norm": 0.3791327476501465,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3654,
      "step": 79
    },
    {
      "epoch": 0.01079076041139774,
      "grad_norm": 0.3862888813018799,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3566,
      "step": 80
    },
    {
      "epoch": 0.010925644916540212,
      "grad_norm": 0.4100586473941803,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3829,
      "step": 81
    },
    {
      "epoch": 0.011060529421682685,
      "grad_norm": 0.40069225430488586,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3269,
      "step": 82
    },
    {
      "epoch": 0.011195413926825156,
      "grad_norm": 0.41757309436798096,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3628,
      "step": 83
    },
    {
      "epoch": 0.011330298431967627,
      "grad_norm": 0.44360682368278503,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3765,
      "step": 84
    },
    {
      "epoch": 0.011465182937110099,
      "grad_norm": 0.4221853017807007,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3532,
      "step": 85
    },
    {
      "epoch": 0.011600067442252572,
      "grad_norm": 0.4360281229019165,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3122,
      "step": 86
    },
    {
      "epoch": 0.011734951947395043,
      "grad_norm": 0.44558200240135193,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3454,
      "step": 87
    },
    {
      "epoch": 0.011869836452537514,
      "grad_norm": 0.4454135000705719,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3366,
      "step": 88
    },
    {
      "epoch": 0.012004720957679987,
      "grad_norm": 0.47155457735061646,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3229,
      "step": 89
    },
    {
      "epoch": 0.012139605462822459,
      "grad_norm": 0.4691172242164612,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3391,
      "step": 90
    },
    {
      "epoch": 0.01227448996796493,
      "grad_norm": 0.44884413480758667,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3349,
      "step": 91
    },
    {
      "epoch": 0.012409374473107401,
      "grad_norm": 0.48445984721183777,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3134,
      "step": 92
    },
    {
      "epoch": 0.012544258978249874,
      "grad_norm": 0.4838542342185974,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.2871,
      "step": 93
    },
    {
      "epoch": 0.012679143483392346,
      "grad_norm": 0.5027027726173401,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3065,
      "step": 94
    },
    {
      "epoch": 0.012814027988534817,
      "grad_norm": 0.48869600892066956,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2583,
      "step": 95
    },
    {
      "epoch": 0.012948912493677288,
      "grad_norm": 0.5144763588905334,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.2741,
      "step": 96
    },
    {
      "epoch": 0.013083796998819761,
      "grad_norm": 0.5419305562973022,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3266,
      "step": 97
    },
    {
      "epoch": 0.013218681503962233,
      "grad_norm": 0.5631057620048523,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2767,
      "step": 98
    },
    {
      "epoch": 0.013353566009104704,
      "grad_norm": 0.5756965279579163,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2827,
      "step": 99
    },
    {
      "epoch": 0.013488450514247175,
      "grad_norm": 0.6341802477836609,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2608,
      "step": 100
    },
    {
      "epoch": 0.013488450514247175,
      "eval_loss": 0.3826199173927307,
      "eval_runtime": 262.4287,
      "eval_samples_per_second": 47.582,
      "eval_steps_per_second": 11.897,
      "step": 100
    },
    {
      "epoch": 0.013623335019389648,
      "grad_norm": 0.46238765120506287,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.5374,
      "step": 101
    },
    {
      "epoch": 0.01375821952453212,
      "grad_norm": 0.45016229152679443,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5147,
      "step": 102
    },
    {
      "epoch": 0.01389310402967459,
      "grad_norm": 0.38379326462745667,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5019,
      "step": 103
    },
    {
      "epoch": 0.014027988534817062,
      "grad_norm": 0.36504730582237244,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4764,
      "step": 104
    },
    {
      "epoch": 0.014162873039959535,
      "grad_norm": 0.3214379549026489,
      "learning_rate": 5e-05,
      "loss": 0.3923,
      "step": 105
    },
    {
      "epoch": 0.014297757545102006,
      "grad_norm": 0.3128524422645569,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4089,
      "step": 106
    },
    {
      "epoch": 0.014432642050244478,
      "grad_norm": 0.324794203042984,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4516,
      "step": 107
    },
    {
      "epoch": 0.01456752655538695,
      "grad_norm": 0.3154839873313904,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3983,
      "step": 108
    },
    {
      "epoch": 0.014702411060529422,
      "grad_norm": 0.29345738887786865,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3922,
      "step": 109
    },
    {
      "epoch": 0.014837295565671893,
      "grad_norm": 0.3072289228439331,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4002,
      "step": 110
    },
    {
      "epoch": 0.014972180070814365,
      "grad_norm": 0.30655327439308167,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.4245,
      "step": 111
    },
    {
      "epoch": 0.015107064575956838,
      "grad_norm": 0.3034436106681824,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4169,
      "step": 112
    },
    {
      "epoch": 0.015241949081099309,
      "grad_norm": 0.31255683302879333,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3746,
      "step": 113
    },
    {
      "epoch": 0.01537683358624178,
      "grad_norm": 0.34984534978866577,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4962,
      "step": 114
    },
    {
      "epoch": 0.015511718091384252,
      "grad_norm": 0.3458285629749298,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3839,
      "step": 115
    },
    {
      "epoch": 0.015646602596526723,
      "grad_norm": 0.34688809514045715,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4345,
      "step": 116
    },
    {
      "epoch": 0.015781487101669194,
      "grad_norm": 0.3627210259437561,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4273,
      "step": 117
    },
    {
      "epoch": 0.01591637160681167,
      "grad_norm": 0.3602834641933441,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.4127,
      "step": 118
    },
    {
      "epoch": 0.01605125611195414,
      "grad_norm": 0.3714202642440796,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.445,
      "step": 119
    },
    {
      "epoch": 0.01618614061709661,
      "grad_norm": 0.35690978169441223,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.402,
      "step": 120
    },
    {
      "epoch": 0.016321025122239083,
      "grad_norm": 0.3642812669277191,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4185,
      "step": 121
    },
    {
      "epoch": 0.016455909627381554,
      "grad_norm": 0.3817923963069916,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3889,
      "step": 122
    },
    {
      "epoch": 0.016590794132524025,
      "grad_norm": 0.36971551179885864,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3991,
      "step": 123
    },
    {
      "epoch": 0.016725678637666497,
      "grad_norm": 0.380921870470047,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3912,
      "step": 124
    },
    {
      "epoch": 0.01686056314280897,
      "grad_norm": 0.38526037335395813,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4087,
      "step": 125
    },
    {
      "epoch": 0.016995447647951443,
      "grad_norm": 0.38887038826942444,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3659,
      "step": 126
    },
    {
      "epoch": 0.017130332153093914,
      "grad_norm": 0.38391873240470886,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3645,
      "step": 127
    },
    {
      "epoch": 0.017265216658236385,
      "grad_norm": 0.3906773328781128,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3529,
      "step": 128
    },
    {
      "epoch": 0.017400101163378857,
      "grad_norm": 0.39767155051231384,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3729,
      "step": 129
    },
    {
      "epoch": 0.017534985668521328,
      "grad_norm": 0.3738510012626648,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3232,
      "step": 130
    },
    {
      "epoch": 0.0176698701736638,
      "grad_norm": 0.3916512429714203,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3105,
      "step": 131
    },
    {
      "epoch": 0.01780475467880627,
      "grad_norm": 0.40689417719841003,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3229,
      "step": 132
    },
    {
      "epoch": 0.017939639183948745,
      "grad_norm": 0.4214940667152405,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2932,
      "step": 133
    },
    {
      "epoch": 0.018074523689091217,
      "grad_norm": 0.4285062551498413,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3311,
      "step": 134
    },
    {
      "epoch": 0.018209408194233688,
      "grad_norm": 0.42742013931274414,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.325,
      "step": 135
    },
    {
      "epoch": 0.01834429269937616,
      "grad_norm": 0.430841326713562,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.321,
      "step": 136
    },
    {
      "epoch": 0.01847917720451863,
      "grad_norm": 0.4379907548427582,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3367,
      "step": 137
    },
    {
      "epoch": 0.018614061709661102,
      "grad_norm": 0.44621825218200684,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3523,
      "step": 138
    },
    {
      "epoch": 0.018748946214803573,
      "grad_norm": 0.45682862401008606,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.329,
      "step": 139
    },
    {
      "epoch": 0.018883830719946045,
      "grad_norm": 0.5228286981582642,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3238,
      "step": 140
    },
    {
      "epoch": 0.01901871522508852,
      "grad_norm": 0.4591923952102661,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.2692,
      "step": 141
    },
    {
      "epoch": 0.01915359973023099,
      "grad_norm": 0.4581301510334015,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2835,
      "step": 142
    },
    {
      "epoch": 0.019288484235373462,
      "grad_norm": 0.5342960357666016,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3633,
      "step": 143
    },
    {
      "epoch": 0.019423368740515933,
      "grad_norm": 0.5283006429672241,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3239,
      "step": 144
    },
    {
      "epoch": 0.019558253245658404,
      "grad_norm": 0.4898834526538849,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.2831,
      "step": 145
    },
    {
      "epoch": 0.019693137750800876,
      "grad_norm": 0.5250715017318726,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3036,
      "step": 146
    },
    {
      "epoch": 0.019828022255943347,
      "grad_norm": 0.5261310338973999,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2744,
      "step": 147
    },
    {
      "epoch": 0.019962906761085822,
      "grad_norm": 0.5671424865722656,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2696,
      "step": 148
    },
    {
      "epoch": 0.020097791266228293,
      "grad_norm": 0.5909906625747681,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.2867,
      "step": 149
    },
    {
      "epoch": 0.020232675771370764,
      "grad_norm": 0.6121522784233093,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2499,
      "step": 150
    },
    {
      "epoch": 0.020232675771370764,
      "eval_loss": 0.3696952760219574,
      "eval_runtime": 262.3097,
      "eval_samples_per_second": 47.604,
      "eval_steps_per_second": 11.902,
      "step": 150
    },
    {
      "epoch": 0.020367560276513236,
      "grad_norm": 0.3605216145515442,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.483,
      "step": 151
    },
    {
      "epoch": 0.020502444781655707,
      "grad_norm": 0.38068974018096924,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4833,
      "step": 152
    },
    {
      "epoch": 0.02063732928679818,
      "grad_norm": 0.3193225562572479,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.4047,
      "step": 153
    },
    {
      "epoch": 0.02077221379194065,
      "grad_norm": 0.3421807885169983,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.4633,
      "step": 154
    },
    {
      "epoch": 0.02090709829708312,
      "grad_norm": 0.3365440368652344,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4449,
      "step": 155
    },
    {
      "epoch": 0.021041982802225596,
      "grad_norm": 0.35433730483055115,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.424,
      "step": 156
    },
    {
      "epoch": 0.021176867307368067,
      "grad_norm": 0.3414672315120697,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.4039,
      "step": 157
    },
    {
      "epoch": 0.02131175181251054,
      "grad_norm": 0.35648083686828613,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.4229,
      "step": 158
    },
    {
      "epoch": 0.02144663631765301,
      "grad_norm": 0.32455772161483765,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.398,
      "step": 159
    },
    {
      "epoch": 0.02158152082279548,
      "grad_norm": 0.3211548328399658,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.3904,
      "step": 160
    },
    {
      "epoch": 0.021716405327937952,
      "grad_norm": 0.31686338782310486,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3917,
      "step": 161
    },
    {
      "epoch": 0.021851289833080424,
      "grad_norm": 0.3224930465221405,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4356,
      "step": 162
    },
    {
      "epoch": 0.0219861743382229,
      "grad_norm": 0.33781057596206665,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4356,
      "step": 163
    },
    {
      "epoch": 0.02212105884336537,
      "grad_norm": 0.3150184750556946,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4061,
      "step": 164
    },
    {
      "epoch": 0.02225594334850784,
      "grad_norm": 0.3237675428390503,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4019,
      "step": 165
    },
    {
      "epoch": 0.022390827853650312,
      "grad_norm": 0.3184843361377716,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3874,
      "step": 166
    },
    {
      "epoch": 0.022525712358792783,
      "grad_norm": 0.334789901971817,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3916,
      "step": 167
    },
    {
      "epoch": 0.022660596863935255,
      "grad_norm": 0.34257772564888,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.4218,
      "step": 168
    },
    {
      "epoch": 0.022795481369077726,
      "grad_norm": 0.3364148736000061,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3996,
      "step": 169
    },
    {
      "epoch": 0.022930365874220197,
      "grad_norm": 0.35442104935646057,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4,
      "step": 170
    },
    {
      "epoch": 0.023065250379362672,
      "grad_norm": 0.35164427757263184,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3943,
      "step": 171
    },
    {
      "epoch": 0.023200134884505143,
      "grad_norm": 0.3600988984107971,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4358,
      "step": 172
    },
    {
      "epoch": 0.023335019389647615,
      "grad_norm": 0.3643745481967926,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.41,
      "step": 173
    },
    {
      "epoch": 0.023469903894790086,
      "grad_norm": 0.37545162439346313,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4625,
      "step": 174
    },
    {
      "epoch": 0.023604788399932557,
      "grad_norm": 0.3747585713863373,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4241,
      "step": 175
    },
    {
      "epoch": 0.02373967290507503,
      "grad_norm": 0.3820582628250122,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4139,
      "step": 176
    },
    {
      "epoch": 0.0238745574102175,
      "grad_norm": 0.3853403925895691,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.379,
      "step": 177
    },
    {
      "epoch": 0.024009441915359975,
      "grad_norm": 0.35950466990470886,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3135,
      "step": 178
    },
    {
      "epoch": 0.024144326420502446,
      "grad_norm": 0.37789905071258545,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3802,
      "step": 179
    },
    {
      "epoch": 0.024279210925644917,
      "grad_norm": 0.3791658282279968,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.3505,
      "step": 180
    },
    {
      "epoch": 0.02441409543078739,
      "grad_norm": 0.4005204439163208,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3197,
      "step": 181
    },
    {
      "epoch": 0.02454897993592986,
      "grad_norm": 0.40441471338272095,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.379,
      "step": 182
    },
    {
      "epoch": 0.02468386444107233,
      "grad_norm": 0.41772812604904175,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3521,
      "step": 183
    },
    {
      "epoch": 0.024818748946214803,
      "grad_norm": 0.40544265508651733,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.3137,
      "step": 184
    },
    {
      "epoch": 0.024953633451357274,
      "grad_norm": 0.43825870752334595,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3157,
      "step": 185
    },
    {
      "epoch": 0.02508851795649975,
      "grad_norm": 0.42155155539512634,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3732,
      "step": 186
    },
    {
      "epoch": 0.02522340246164222,
      "grad_norm": 0.44176408648490906,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3336,
      "step": 187
    },
    {
      "epoch": 0.02535828696678469,
      "grad_norm": 0.417464017868042,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2951,
      "step": 188
    },
    {
      "epoch": 0.025493171471927163,
      "grad_norm": 0.4592988193035126,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3559,
      "step": 189
    },
    {
      "epoch": 0.025628055977069634,
      "grad_norm": 0.42396318912506104,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3042,
      "step": 190
    },
    {
      "epoch": 0.025762940482212105,
      "grad_norm": 0.46669691801071167,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.3342,
      "step": 191
    },
    {
      "epoch": 0.025897824987354576,
      "grad_norm": 0.504673421382904,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.2872,
      "step": 192
    },
    {
      "epoch": 0.026032709492497048,
      "grad_norm": 0.4923456013202667,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3126,
      "step": 193
    },
    {
      "epoch": 0.026167593997639522,
      "grad_norm": 0.46691855788230896,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2673,
      "step": 194
    },
    {
      "epoch": 0.026302478502781994,
      "grad_norm": 0.505763828754425,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3177,
      "step": 195
    },
    {
      "epoch": 0.026437363007924465,
      "grad_norm": 0.512893795967102,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3036,
      "step": 196
    },
    {
      "epoch": 0.026572247513066936,
      "grad_norm": 0.539890706539154,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3035,
      "step": 197
    },
    {
      "epoch": 0.026707132018209408,
      "grad_norm": 0.5420638918876648,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2919,
      "step": 198
    },
    {
      "epoch": 0.02684201652335188,
      "grad_norm": 0.5626928210258484,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.2181,
      "step": 199
    },
    {
      "epoch": 0.02697690102849435,
      "grad_norm": 0.6565114259719849,
      "learning_rate": 0.0,
      "loss": 0.289,
      "step": 200
    },
    {
      "epoch": 0.02697690102849435,
      "eval_loss": 0.3653714060783386,
      "eval_runtime": 262.2332,
      "eval_samples_per_second": 47.618,
      "eval_steps_per_second": 11.905,
      "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": 1.9166636430852096e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}