{
  "best_metric": 1.1655843257904053,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.022313335006833458,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001115666750341673,
      "grad_norm": 1.8318336009979248,
      "learning_rate": 1e-05,
      "loss": 2.3379,
      "step": 1
    },
    {
      "epoch": 0.0001115666750341673,
      "eval_loss": 2.0897305011749268,
      "eval_runtime": 454.8379,
      "eval_samples_per_second": 33.192,
      "eval_steps_per_second": 8.3,
      "step": 1
    },
    {
      "epoch": 0.0002231333500683346,
      "grad_norm": 1.419111967086792,
      "learning_rate": 2e-05,
      "loss": 2.01,
      "step": 2
    },
    {
      "epoch": 0.0003347000251025019,
      "grad_norm": 1.7596532106399536,
      "learning_rate": 3e-05,
      "loss": 2.0349,
      "step": 3
    },
    {
      "epoch": 0.0004462667001366692,
      "grad_norm": 1.5037742853164673,
      "learning_rate": 4e-05,
      "loss": 2.0674,
      "step": 4
    },
    {
      "epoch": 0.0005578333751708364,
      "grad_norm": 2.0602903366088867,
      "learning_rate": 5e-05,
      "loss": 1.882,
      "step": 5
    },
    {
      "epoch": 0.0006694000502050038,
      "grad_norm": 1.244989037513733,
      "learning_rate": 6e-05,
      "loss": 1.6695,
      "step": 6
    },
    {
      "epoch": 0.000780966725239171,
      "grad_norm": 1.061270833015442,
      "learning_rate": 7e-05,
      "loss": 1.8063,
      "step": 7
    },
    {
      "epoch": 0.0008925334002733384,
      "grad_norm": 0.8203992247581482,
      "learning_rate": 8e-05,
      "loss": 1.5536,
      "step": 8
    },
    {
      "epoch": 0.0010041000753075056,
      "grad_norm": 0.789804220199585,
      "learning_rate": 9e-05,
      "loss": 1.4458,
      "step": 9
    },
    {
      "epoch": 0.0011156667503416729,
      "grad_norm": 0.7559303641319275,
      "learning_rate": 0.0001,
      "loss": 1.6049,
      "step": 10
    },
    {
      "epoch": 0.0012272334253758403,
      "grad_norm": 0.8243244886398315,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3599,
      "step": 11
    },
    {
      "epoch": 0.0013388001004100076,
      "grad_norm": 0.8023079633712769,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5226,
      "step": 12
    },
    {
      "epoch": 0.0014503667754441748,
      "grad_norm": 0.8693966865539551,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4382,
      "step": 13
    },
    {
      "epoch": 0.001561933450478342,
      "grad_norm": 0.8527520298957825,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.5249,
      "step": 14
    },
    {
      "epoch": 0.0016735001255125093,
      "grad_norm": 0.7380151152610779,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4158,
      "step": 15
    },
    {
      "epoch": 0.0017850668005466768,
      "grad_norm": 0.6373164057731628,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5136,
      "step": 16
    },
    {
      "epoch": 0.001896633475580844,
      "grad_norm": 0.640508770942688,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4755,
      "step": 17
    },
    {
      "epoch": 0.0020082001506150113,
      "grad_norm": 0.601711094379425,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3007,
      "step": 18
    },
    {
      "epoch": 0.0021197668256491787,
      "grad_norm": 0.6202059984207153,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3005,
      "step": 19
    },
    {
      "epoch": 0.0022313335006833458,
      "grad_norm": 0.6213165521621704,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2696,
      "step": 20
    },
    {
      "epoch": 0.002342900175717513,
      "grad_norm": 0.602688193321228,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4671,
      "step": 21
    },
    {
      "epoch": 0.0024544668507516807,
      "grad_norm": 0.6732321381568909,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.448,
      "step": 22
    },
    {
      "epoch": 0.0025660335257858477,
      "grad_norm": 0.6409225463867188,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4218,
      "step": 23
    },
    {
      "epoch": 0.002677600200820015,
      "grad_norm": 0.6083570718765259,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3301,
      "step": 24
    },
    {
      "epoch": 0.002789166875854182,
      "grad_norm": 0.5829587578773499,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2977,
      "step": 25
    },
    {
      "epoch": 0.0029007335508883497,
      "grad_norm": 0.6037457585334778,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3118,
      "step": 26
    },
    {
      "epoch": 0.003012300225922517,
      "grad_norm": 0.6386670470237732,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4143,
      "step": 27
    },
    {
      "epoch": 0.003123866900956684,
      "grad_norm": 0.6297231316566467,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.3333,
      "step": 28
    },
    {
      "epoch": 0.0032354335759908516,
      "grad_norm": 0.6757303476333618,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4019,
      "step": 29
    },
    {
      "epoch": 0.0033470002510250186,
      "grad_norm": 0.6362946033477783,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1672,
      "step": 30
    },
    {
      "epoch": 0.003458566926059186,
      "grad_norm": 0.6639829277992249,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3201,
      "step": 31
    },
    {
      "epoch": 0.0035701336010933536,
      "grad_norm": 0.6325393915176392,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2736,
      "step": 32
    },
    {
      "epoch": 0.0036817002761275206,
      "grad_norm": 0.6399858593940735,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2393,
      "step": 33
    },
    {
      "epoch": 0.003793266951161688,
      "grad_norm": 0.6369875073432922,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2422,
      "step": 34
    },
    {
      "epoch": 0.0039048336261958555,
      "grad_norm": 0.6915414929389954,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.2782,
      "step": 35
    },
    {
      "epoch": 0.0040164003012300225,
      "grad_norm": 0.718991756439209,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.182,
      "step": 36
    },
    {
      "epoch": 0.0041279669762641896,
      "grad_norm": 0.6674362421035767,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.195,
      "step": 37
    },
    {
      "epoch": 0.0042395336512983575,
      "grad_norm": 0.6916540861129761,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2553,
      "step": 38
    },
    {
      "epoch": 0.0043511003263325245,
      "grad_norm": 0.7060713768005371,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1887,
      "step": 39
    },
    {
      "epoch": 0.0044626670013666915,
      "grad_norm": 0.7569680213928223,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1479,
      "step": 40
    },
    {
      "epoch": 0.004574233676400859,
      "grad_norm": 0.7588503360748291,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.266,
      "step": 41
    },
    {
      "epoch": 0.004685800351435026,
      "grad_norm": 0.7068307995796204,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.1005,
      "step": 42
    },
    {
      "epoch": 0.0047973670264691935,
      "grad_norm": 0.742445170879364,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.2261,
      "step": 43
    },
    {
      "epoch": 0.004908933701503361,
      "grad_norm": 0.74104243516922,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1966,
      "step": 44
    },
    {
      "epoch": 0.005020500376537528,
      "grad_norm": 0.7269580364227295,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.2773,
      "step": 45
    },
    {
      "epoch": 0.005132067051571695,
      "grad_norm": 0.8216692805290222,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.2237,
      "step": 46
    },
    {
      "epoch": 0.005243633726605862,
      "grad_norm": 0.8607100248336792,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.3299,
      "step": 47
    },
    {
      "epoch": 0.00535520040164003,
      "grad_norm": 1.031139850616455,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1368,
      "step": 48
    },
    {
      "epoch": 0.005466767076674197,
      "grad_norm": 0.8504732251167297,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0207,
      "step": 49
    },
    {
      "epoch": 0.005578333751708364,
      "grad_norm": 0.9983724355697632,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0047,
      "step": 50
    },
    {
      "epoch": 0.005578333751708364,
      "eval_loss": 1.2816766500473022,
      "eval_runtime": 455.3274,
      "eval_samples_per_second": 33.156,
      "eval_steps_per_second": 8.291,
      "step": 50
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 0.87342369556427,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.7642,
      "step": 51
    },
    {
      "epoch": 0.005801467101776699,
      "grad_norm": 0.776253879070282,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.697,
      "step": 52
    },
    {
      "epoch": 0.005913033776810866,
      "grad_norm": 0.6793281435966492,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.5065,
      "step": 53
    },
    {
      "epoch": 0.006024600451845034,
      "grad_norm": 0.5906603932380676,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4913,
      "step": 54
    },
    {
      "epoch": 0.006136167126879201,
      "grad_norm": 0.5672029852867126,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2197,
      "step": 55
    },
    {
      "epoch": 0.006247733801913368,
      "grad_norm": 0.593641459941864,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.2856,
      "step": 56
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.5828561782836914,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.4526,
      "step": 57
    },
    {
      "epoch": 0.006470867151981703,
      "grad_norm": 0.5753366351127625,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.4999,
      "step": 58
    },
    {
      "epoch": 0.00658243382701587,
      "grad_norm": 0.5516051054000854,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.3871,
      "step": 59
    },
    {
      "epoch": 0.006694000502050037,
      "grad_norm": 0.5935094952583313,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.3386,
      "step": 60
    },
    {
      "epoch": 0.006805567177084205,
      "grad_norm": 0.5750835537910461,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3795,
      "step": 61
    },
    {
      "epoch": 0.006917133852118372,
      "grad_norm": 0.5868992805480957,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.3926,
      "step": 62
    },
    {
      "epoch": 0.007028700527152539,
      "grad_norm": 0.5295293927192688,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3573,
      "step": 63
    },
    {
      "epoch": 0.007140267202186707,
      "grad_norm": 0.5167469382286072,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.3363,
      "step": 64
    },
    {
      "epoch": 0.007251833877220874,
      "grad_norm": 0.5310781598091125,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2901,
      "step": 65
    },
    {
      "epoch": 0.007363400552255041,
      "grad_norm": 0.5497135519981384,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.3969,
      "step": 66
    },
    {
      "epoch": 0.007474967227289209,
      "grad_norm": 0.5470055937767029,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1672,
      "step": 67
    },
    {
      "epoch": 0.007586533902323376,
      "grad_norm": 0.5302481651306152,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.3114,
      "step": 68
    },
    {
      "epoch": 0.007698100577357543,
      "grad_norm": 0.5234085321426392,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.2662,
      "step": 69
    },
    {
      "epoch": 0.007809667252391711,
      "grad_norm": 0.5368407368659973,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.3666,
      "step": 70
    },
    {
      "epoch": 0.007921233927425877,
      "grad_norm": 0.5434086322784424,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2133,
      "step": 71
    },
    {
      "epoch": 0.008032800602460045,
      "grad_norm": 0.5254490375518799,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.3812,
      "step": 72
    },
    {
      "epoch": 0.008144367277494213,
      "grad_norm": 0.5242455005645752,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0911,
      "step": 73
    },
    {
      "epoch": 0.008255933952528379,
      "grad_norm": 0.6389315724372864,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.2935,
      "step": 74
    },
    {
      "epoch": 0.008367500627562547,
      "grad_norm": 0.5757254958152771,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2617,
      "step": 75
    },
    {
      "epoch": 0.008479067302596715,
      "grad_norm": 0.626308798789978,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.1739,
      "step": 76
    },
    {
      "epoch": 0.008590633977630881,
      "grad_norm": 0.5778496265411377,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2306,
      "step": 77
    },
    {
      "epoch": 0.008702200652665049,
      "grad_norm": 0.6246429085731506,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.2534,
      "step": 78
    },
    {
      "epoch": 0.008813767327699217,
      "grad_norm": 0.5858237147331238,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.0923,
      "step": 79
    },
    {
      "epoch": 0.008925334002733383,
      "grad_norm": 0.6260606646537781,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.1888,
      "step": 80
    },
    {
      "epoch": 0.009036900677767551,
      "grad_norm": 0.630234956741333,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.2772,
      "step": 81
    },
    {
      "epoch": 0.009148467352801719,
      "grad_norm": 0.6444050669670105,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.1496,
      "step": 82
    },
    {
      "epoch": 0.009260034027835885,
      "grad_norm": 0.6214231252670288,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.255,
      "step": 83
    },
    {
      "epoch": 0.009371600702870053,
      "grad_norm": 0.6371873021125793,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.362,
      "step": 84
    },
    {
      "epoch": 0.00948316737790422,
      "grad_norm": 0.652386486530304,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.257,
      "step": 85
    },
    {
      "epoch": 0.009594734052938387,
      "grad_norm": 0.6756475567817688,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0734,
      "step": 86
    },
    {
      "epoch": 0.009706300727972555,
      "grad_norm": 0.6765338778495789,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.3687,
      "step": 87
    },
    {
      "epoch": 0.009817867403006723,
      "grad_norm": 0.6886449456214905,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0611,
      "step": 88
    },
    {
      "epoch": 0.009929434078040889,
      "grad_norm": 0.7021864056587219,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2352,
      "step": 89
    },
    {
      "epoch": 0.010041000753075057,
      "grad_norm": 0.7063576579093933,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.0392,
      "step": 90
    },
    {
      "epoch": 0.010152567428109223,
      "grad_norm": 0.6913172602653503,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.0881,
      "step": 91
    },
    {
      "epoch": 0.01026413410314339,
      "grad_norm": 0.8174880146980286,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0368,
      "step": 92
    },
    {
      "epoch": 0.010375700778177559,
      "grad_norm": 0.7189077734947205,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0234,
      "step": 93
    },
    {
      "epoch": 0.010487267453211725,
      "grad_norm": 0.7540398836135864,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3022,
      "step": 94
    },
    {
      "epoch": 0.010598834128245893,
      "grad_norm": 0.7480753064155579,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.1476,
      "step": 95
    },
    {
      "epoch": 0.01071040080328006,
      "grad_norm": 0.7380363345146179,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1075,
      "step": 96
    },
    {
      "epoch": 0.010821967478314227,
      "grad_norm": 0.7782248258590698,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0968,
      "step": 97
    },
    {
      "epoch": 0.010933534153348395,
      "grad_norm": 0.8116884827613831,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0562,
      "step": 98
    },
    {
      "epoch": 0.011045100828382563,
      "grad_norm": 0.8749708533287048,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0236,
      "step": 99
    },
    {
      "epoch": 0.011156667503416729,
      "grad_norm": 0.9371297359466553,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8881,
      "step": 100
    },
    {
      "epoch": 0.011156667503416729,
      "eval_loss": 1.2055939435958862,
      "eval_runtime": 455.4273,
      "eval_samples_per_second": 33.149,
      "eval_steps_per_second": 8.289,
      "step": 100
    },
    {
      "epoch": 0.011268234178450897,
      "grad_norm": 0.6742625832557678,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.6478,
      "step": 101
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": 0.5853553414344788,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.3298,
      "step": 102
    },
    {
      "epoch": 0.01149136752851923,
      "grad_norm": 0.601719856262207,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.4464,
      "step": 103
    },
    {
      "epoch": 0.011602934203553399,
      "grad_norm": 0.631619393825531,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.457,
      "step": 104
    },
    {
      "epoch": 0.011714500878587567,
      "grad_norm": 0.6335456371307373,
      "learning_rate": 5e-05,
      "loss": 1.3283,
      "step": 105
    },
    {
      "epoch": 0.011826067553621733,
      "grad_norm": 0.6077951788902283,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2609,
      "step": 106
    },
    {
      "epoch": 0.0119376342286559,
      "grad_norm": 0.5482537746429443,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.4599,
      "step": 107
    },
    {
      "epoch": 0.012049200903690068,
      "grad_norm": 0.5261465311050415,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.3512,
      "step": 108
    },
    {
      "epoch": 0.012160767578724235,
      "grad_norm": 0.4924035966396332,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.192,
      "step": 109
    },
    {
      "epoch": 0.012272334253758403,
      "grad_norm": 0.5487890243530273,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.3935,
      "step": 110
    },
    {
      "epoch": 0.01238390092879257,
      "grad_norm": 0.546566367149353,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.3378,
      "step": 111
    },
    {
      "epoch": 0.012495467603826737,
      "grad_norm": 0.4878402054309845,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.2473,
      "step": 112
    },
    {
      "epoch": 0.012607034278860904,
      "grad_norm": 0.525849461555481,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.2212,
      "step": 113
    },
    {
      "epoch": 0.012718600953895072,
      "grad_norm": 0.523909330368042,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.3228,
      "step": 114
    },
    {
      "epoch": 0.012830167628929239,
      "grad_norm": 0.5373177528381348,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.3156,
      "step": 115
    },
    {
      "epoch": 0.012941734303963406,
      "grad_norm": 0.5635479688644409,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2533,
      "step": 116
    },
    {
      "epoch": 0.013053300978997573,
      "grad_norm": 0.5487397909164429,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.2591,
      "step": 117
    },
    {
      "epoch": 0.01316486765403174,
      "grad_norm": 0.5055230855941772,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9973,
      "step": 118
    },
    {
      "epoch": 0.013276434329065908,
      "grad_norm": 0.5301899909973145,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.2506,
      "step": 119
    },
    {
      "epoch": 0.013388001004100075,
      "grad_norm": 0.5094836950302124,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.2575,
      "step": 120
    },
    {
      "epoch": 0.013499567679134242,
      "grad_norm": 0.569148600101471,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.2735,
      "step": 121
    },
    {
      "epoch": 0.01361113435416841,
      "grad_norm": 0.6245477795600891,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.3459,
      "step": 122
    },
    {
      "epoch": 0.013722701029202576,
      "grad_norm": 0.5657536387443542,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.4167,
      "step": 123
    },
    {
      "epoch": 0.013834267704236744,
      "grad_norm": 0.5596782565116882,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1227,
      "step": 124
    },
    {
      "epoch": 0.013945834379270912,
      "grad_norm": 0.5774509310722351,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3068,
      "step": 125
    },
    {
      "epoch": 0.014057401054305078,
      "grad_norm": 0.5831321477890015,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.2858,
      "step": 126
    },
    {
      "epoch": 0.014168967729339246,
      "grad_norm": 0.5819647312164307,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.0417,
      "step": 127
    },
    {
      "epoch": 0.014280534404373414,
      "grad_norm": 0.5878843069076538,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.3039,
      "step": 128
    },
    {
      "epoch": 0.01439210107940758,
      "grad_norm": 0.639421820640564,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.1711,
      "step": 129
    },
    {
      "epoch": 0.014503667754441748,
      "grad_norm": 0.5911180973052979,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.2072,
      "step": 130
    },
    {
      "epoch": 0.014615234429475916,
      "grad_norm": 0.6440814137458801,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2376,
      "step": 131
    },
    {
      "epoch": 0.014726801104510082,
      "grad_norm": 0.6508470773696899,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.2576,
      "step": 132
    },
    {
      "epoch": 0.01483836777954425,
      "grad_norm": 0.632831335067749,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.2494,
      "step": 133
    },
    {
      "epoch": 0.014949934454578418,
      "grad_norm": 0.68438321352005,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.2145,
      "step": 134
    },
    {
      "epoch": 0.015061501129612584,
      "grad_norm": 0.655276894569397,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.1135,
      "step": 135
    },
    {
      "epoch": 0.015173067804646752,
      "grad_norm": 0.6697691082954407,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.0886,
      "step": 136
    },
    {
      "epoch": 0.01528463447968092,
      "grad_norm": 0.6218588948249817,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1123,
      "step": 137
    },
    {
      "epoch": 0.015396201154715086,
      "grad_norm": 0.6525841355323792,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.1473,
      "step": 138
    },
    {
      "epoch": 0.015507767829749254,
      "grad_norm": 0.7027962803840637,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.1153,
      "step": 139
    },
    {
      "epoch": 0.015619334504783422,
      "grad_norm": 0.6292527914047241,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9021,
      "step": 140
    },
    {
      "epoch": 0.01573090117981759,
      "grad_norm": 0.6442590355873108,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.9529,
      "step": 141
    },
    {
      "epoch": 0.015842467854851754,
      "grad_norm": 0.7019503712654114,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.1304,
      "step": 142
    },
    {
      "epoch": 0.015954034529885922,
      "grad_norm": 0.6800310611724854,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1013,
      "step": 143
    },
    {
      "epoch": 0.01606560120492009,
      "grad_norm": 0.8501023054122925,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9896,
      "step": 144
    },
    {
      "epoch": 0.016177167879954258,
      "grad_norm": 0.7541186809539795,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1096,
      "step": 145
    },
    {
      "epoch": 0.016288734554988426,
      "grad_norm": 0.7505862712860107,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.1745,
      "step": 146
    },
    {
      "epoch": 0.016400301230022594,
      "grad_norm": 0.787189245223999,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.1012,
      "step": 147
    },
    {
      "epoch": 0.016511867905056758,
      "grad_norm": 0.9546669721603394,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.0849,
      "step": 148
    },
    {
      "epoch": 0.016623434580090926,
      "grad_norm": 0.918546199798584,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.9786,
      "step": 149
    },
    {
      "epoch": 0.016735001255125094,
      "grad_norm": 1.009279489517212,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9523,
      "step": 150
    },
    {
      "epoch": 0.016735001255125094,
      "eval_loss": 1.171594262123108,
      "eval_runtime": 455.3528,
      "eval_samples_per_second": 33.155,
      "eval_steps_per_second": 8.29,
      "step": 150
    },
    {
      "epoch": 0.016846567930159262,
      "grad_norm": 0.6734952926635742,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.5872,
      "step": 151
    },
    {
      "epoch": 0.01695813460519343,
      "grad_norm": 0.6282791495323181,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.464,
      "step": 152
    },
    {
      "epoch": 0.017069701280227598,
      "grad_norm": 0.4891398847103119,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.4064,
      "step": 153
    },
    {
      "epoch": 0.017181267955261762,
      "grad_norm": 0.5818141102790833,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.3901,
      "step": 154
    },
    {
      "epoch": 0.01729283463029593,
      "grad_norm": 0.5908587574958801,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.2832,
      "step": 155
    },
    {
      "epoch": 0.017404401305330098,
      "grad_norm": 0.6301507949829102,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.2025,
      "step": 156
    },
    {
      "epoch": 0.017515967980364266,
      "grad_norm": 0.5583939552307129,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.3818,
      "step": 157
    },
    {
      "epoch": 0.017627534655398434,
      "grad_norm": 0.6141598224639893,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.2988,
      "step": 158
    },
    {
      "epoch": 0.017739101330432598,
      "grad_norm": 0.5339234471321106,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.3437,
      "step": 159
    },
    {
      "epoch": 0.017850668005466766,
      "grad_norm": 0.5658873915672302,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2847,
      "step": 160
    },
    {
      "epoch": 0.017962234680500934,
      "grad_norm": 0.5764130353927612,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.3079,
      "step": 161
    },
    {
      "epoch": 0.018073801355535102,
      "grad_norm": 0.5791158676147461,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2219,
      "step": 162
    },
    {
      "epoch": 0.01818536803056927,
      "grad_norm": 0.5560370087623596,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.2831,
      "step": 163
    },
    {
      "epoch": 0.018296934705603438,
      "grad_norm": 0.5346478223800659,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.1299,
      "step": 164
    },
    {
      "epoch": 0.018408501380637602,
      "grad_norm": 0.5725846290588379,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.2257,
      "step": 165
    },
    {
      "epoch": 0.01852006805567177,
      "grad_norm": 0.5464092493057251,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.28,
      "step": 166
    },
    {
      "epoch": 0.018631634730705938,
      "grad_norm": 0.5880047678947449,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.236,
      "step": 167
    },
    {
      "epoch": 0.018743201405740106,
      "grad_norm": 0.5290426015853882,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.2815,
      "step": 168
    },
    {
      "epoch": 0.018854768080774274,
      "grad_norm": 0.5672193169593811,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2441,
      "step": 169
    },
    {
      "epoch": 0.01896633475580844,
      "grad_norm": 0.5956058502197266,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2183,
      "step": 170
    },
    {
      "epoch": 0.019077901430842606,
      "grad_norm": 0.5789973139762878,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.357,
      "step": 171
    },
    {
      "epoch": 0.019189468105876774,
      "grad_norm": 0.5832492709159851,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.0914,
      "step": 172
    },
    {
      "epoch": 0.01930103478091094,
      "grad_norm": 0.5812738537788391,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.3275,
      "step": 173
    },
    {
      "epoch": 0.01941260145594511,
      "grad_norm": 0.6065376400947571,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3228,
      "step": 174
    },
    {
      "epoch": 0.019524168130979278,
      "grad_norm": 0.595881462097168,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.1837,
      "step": 175
    },
    {
      "epoch": 0.019635734806013445,
      "grad_norm": 0.5507778525352478,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.2567,
      "step": 176
    },
    {
      "epoch": 0.01974730148104761,
      "grad_norm": 0.5945226550102234,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.1961,
      "step": 177
    },
    {
      "epoch": 0.019858868156081778,
      "grad_norm": 0.6617814898490906,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1431,
      "step": 178
    },
    {
      "epoch": 0.019970434831115946,
      "grad_norm": 0.5983999967575073,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.287,
      "step": 179
    },
    {
      "epoch": 0.020082001506150114,
      "grad_norm": 0.6318036913871765,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.2053,
      "step": 180
    },
    {
      "epoch": 0.02019356818118428,
      "grad_norm": 0.5945538282394409,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1076,
      "step": 181
    },
    {
      "epoch": 0.020305134856218446,
      "grad_norm": 0.6318116188049316,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.169,
      "step": 182
    },
    {
      "epoch": 0.020416701531252614,
      "grad_norm": 0.6486660838127136,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.2154,
      "step": 183
    },
    {
      "epoch": 0.02052826820628678,
      "grad_norm": 0.6275069117546082,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.068,
      "step": 184
    },
    {
      "epoch": 0.02063983488132095,
      "grad_norm": 0.6613248586654663,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.2067,
      "step": 185
    },
    {
      "epoch": 0.020751401556355117,
      "grad_norm": 0.6383201479911804,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.1953,
      "step": 186
    },
    {
      "epoch": 0.020862968231389285,
      "grad_norm": 0.66336590051651,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.1845,
      "step": 187
    },
    {
      "epoch": 0.02097453490642345,
      "grad_norm": 0.6657447814941406,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.1312,
      "step": 188
    },
    {
      "epoch": 0.021086101581457618,
      "grad_norm": 0.6309121251106262,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.06,
      "step": 189
    },
    {
      "epoch": 0.021197668256491786,
      "grad_norm": 0.7043037414550781,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.1427,
      "step": 190
    },
    {
      "epoch": 0.021309234931525953,
      "grad_norm": 0.6350990533828735,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.0241,
      "step": 191
    },
    {
      "epoch": 0.02142080160656012,
      "grad_norm": 0.6481807231903076,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.029,
      "step": 192
    },
    {
      "epoch": 0.02153236828159429,
      "grad_norm": 0.7618046998977661,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.1223,
      "step": 193
    },
    {
      "epoch": 0.021643934956628454,
      "grad_norm": 0.7424134016036987,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.0259,
      "step": 194
    },
    {
      "epoch": 0.02175550163166262,
      "grad_norm": 0.6458945870399475,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9594,
      "step": 195
    },
    {
      "epoch": 0.02186706830669679,
      "grad_norm": 0.8171665668487549,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.0624,
      "step": 196
    },
    {
      "epoch": 0.021978634981730957,
      "grad_norm": 0.7491054534912109,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.1362,
      "step": 197
    },
    {
      "epoch": 0.022090201656765125,
      "grad_norm": 0.8190098404884338,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.9685,
      "step": 198
    },
    {
      "epoch": 0.022201768331799293,
      "grad_norm": 0.831553041934967,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.9383,
      "step": 199
    },
    {
      "epoch": 0.022313335006833458,
      "grad_norm": 1.0115158557891846,
      "learning_rate": 0.0,
      "loss": 1.0879,
      "step": 200
    },
    {
      "epoch": 0.022313335006833458,
      "eval_loss": 1.1655843257904053,
      "eval_runtime": 455.7674,
      "eval_samples_per_second": 33.124,
      "eval_steps_per_second": 8.283,
      "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": 5.599377833852928e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}