{
  "best_metric": 1.1653963327407837,
  "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": 1.8212274312973022,
      "learning_rate": 1e-05,
      "loss": 2.3379,
      "step": 1
    },
    {
      "epoch": 0.0001115666750341673,
      "eval_loss": 2.0897305011749268,
      "eval_runtime": 459.6053,
      "eval_samples_per_second": 32.848,
      "eval_steps_per_second": 8.214,
      "step": 1
    },
    {
      "epoch": 0.0002231333500683346,
      "grad_norm": 1.4086194038391113,
      "learning_rate": 2e-05,
      "loss": 2.01,
      "step": 2
    },
    {
      "epoch": 0.0003347000251025019,
      "grad_norm": 1.7514138221740723,
      "learning_rate": 3e-05,
      "loss": 2.0344,
      "step": 3
    },
    {
      "epoch": 0.0004462667001366692,
      "grad_norm": 1.4951744079589844,
      "learning_rate": 4e-05,
      "loss": 2.0691,
      "step": 4
    },
    {
      "epoch": 0.0005578333751708364,
      "grad_norm": 2.0470707416534424,
      "learning_rate": 5e-05,
      "loss": 1.8823,
      "step": 5
    },
    {
      "epoch": 0.0006694000502050038,
      "grad_norm": 1.2319015264511108,
      "learning_rate": 6e-05,
      "loss": 1.669,
      "step": 6
    },
    {
      "epoch": 0.000780966725239171,
      "grad_norm": 1.0491044521331787,
      "learning_rate": 7e-05,
      "loss": 1.8064,
      "step": 7
    },
    {
      "epoch": 0.0008925334002733384,
      "grad_norm": 0.8125782608985901,
      "learning_rate": 8e-05,
      "loss": 1.5541,
      "step": 8
    },
    {
      "epoch": 0.0010041000753075056,
      "grad_norm": 0.7733227610588074,
      "learning_rate": 9e-05,
      "loss": 1.4467,
      "step": 9
    },
    {
      "epoch": 0.0011156667503416729,
      "grad_norm": 0.7457000613212585,
      "learning_rate": 0.0001,
      "loss": 1.6052,
      "step": 10
    },
    {
      "epoch": 0.0012272334253758403,
      "grad_norm": 0.8214192986488342,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3595,
      "step": 11
    },
    {
      "epoch": 0.0013388001004100076,
      "grad_norm": 0.8121744990348816,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5238,
      "step": 12
    },
    {
      "epoch": 0.0014503667754441748,
      "grad_norm": 0.8887802958488464,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4391,
      "step": 13
    },
    {
      "epoch": 0.001561933450478342,
      "grad_norm": 0.8478315472602844,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.5244,
      "step": 14
    },
    {
      "epoch": 0.0016735001255125093,
      "grad_norm": 0.7322865128517151,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4157,
      "step": 15
    },
    {
      "epoch": 0.0017850668005466768,
      "grad_norm": 0.6391441822052002,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5161,
      "step": 16
    },
    {
      "epoch": 0.001896633475580844,
      "grad_norm": 0.6411845684051514,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4755,
      "step": 17
    },
    {
      "epoch": 0.0020082001506150113,
      "grad_norm": 0.6023644804954529,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3029,
      "step": 18
    },
    {
      "epoch": 0.0021197668256491787,
      "grad_norm": 0.6136645674705505,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3007,
      "step": 19
    },
    {
      "epoch": 0.0022313335006833458,
      "grad_norm": 0.6210187077522278,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2692,
      "step": 20
    },
    {
      "epoch": 0.002342900175717513,
      "grad_norm": 0.6014333963394165,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4677,
      "step": 21
    },
    {
      "epoch": 0.0024544668507516807,
      "grad_norm": 0.6709775328636169,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.4501,
      "step": 22
    },
    {
      "epoch": 0.0025660335257858477,
      "grad_norm": 0.6392071843147278,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4234,
      "step": 23
    },
    {
      "epoch": 0.002677600200820015,
      "grad_norm": 0.6098843216896057,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3298,
      "step": 24
    },
    {
      "epoch": 0.002789166875854182,
      "grad_norm": 0.5846989750862122,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2984,
      "step": 25
    },
    {
      "epoch": 0.0029007335508883497,
      "grad_norm": 0.6030681729316711,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3124,
      "step": 26
    },
    {
      "epoch": 0.003012300225922517,
      "grad_norm": 0.6540078520774841,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4155,
      "step": 27
    },
    {
      "epoch": 0.003123866900956684,
      "grad_norm": 0.6274188160896301,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.3318,
      "step": 28
    },
    {
      "epoch": 0.0032354335759908516,
      "grad_norm": 0.6784371137619019,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4022,
      "step": 29
    },
    {
      "epoch": 0.0033470002510250186,
      "grad_norm": 0.6410314440727234,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1663,
      "step": 30
    },
    {
      "epoch": 0.003458566926059186,
      "grad_norm": 0.6650882959365845,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3205,
      "step": 31
    },
    {
      "epoch": 0.0035701336010933536,
      "grad_norm": 0.6392965912818909,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2732,
      "step": 32
    },
    {
      "epoch": 0.0036817002761275206,
      "grad_norm": 0.6518154144287109,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2392,
      "step": 33
    },
    {
      "epoch": 0.003793266951161688,
      "grad_norm": 0.6471737623214722,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2403,
      "step": 34
    },
    {
      "epoch": 0.0039048336261958555,
      "grad_norm": 0.7046892642974854,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.277,
      "step": 35
    },
    {
      "epoch": 0.0040164003012300225,
      "grad_norm": 0.7445775866508484,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.181,
      "step": 36
    },
    {
      "epoch": 0.0041279669762641896,
      "grad_norm": 0.6786828637123108,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1956,
      "step": 37
    },
    {
      "epoch": 0.0042395336512983575,
      "grad_norm": 0.7013096213340759,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2562,
      "step": 38
    },
    {
      "epoch": 0.0043511003263325245,
      "grad_norm": 0.7101519703865051,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1892,
      "step": 39
    },
    {
      "epoch": 0.0044626670013666915,
      "grad_norm": 0.7629431486129761,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1483,
      "step": 40
    },
    {
      "epoch": 0.004574233676400859,
      "grad_norm": 0.7780884504318237,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.265,
      "step": 41
    },
    {
      "epoch": 0.004685800351435026,
      "grad_norm": 0.7125723958015442,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.101,
      "step": 42
    },
    {
      "epoch": 0.0047973670264691935,
      "grad_norm": 0.7452905774116516,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.2251,
      "step": 43
    },
    {
      "epoch": 0.004908933701503361,
      "grad_norm": 0.7337647080421448,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1975,
      "step": 44
    },
    {
      "epoch": 0.005020500376537528,
      "grad_norm": 0.7240177989006042,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.275,
      "step": 45
    },
    {
      "epoch": 0.005132067051571695,
      "grad_norm": 0.8364499807357788,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.2254,
      "step": 46
    },
    {
      "epoch": 0.005243633726605862,
      "grad_norm": 0.8767226934432983,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.3331,
      "step": 47
    },
    {
      "epoch": 0.00535520040164003,
      "grad_norm": 0.9071653485298157,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1337,
      "step": 48
    },
    {
      "epoch": 0.005466767076674197,
      "grad_norm": 0.8514352440834045,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0207,
      "step": 49
    },
    {
      "epoch": 0.005578333751708364,
      "grad_norm": 0.9976662993431091,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0039,
      "step": 50
    },
    {
      "epoch": 0.005578333751708364,
      "eval_loss": 1.2798569202423096,
      "eval_runtime": 460.1544,
      "eval_samples_per_second": 32.809,
      "eval_steps_per_second": 8.204,
      "step": 50
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 0.8550774455070496,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.7635,
      "step": 51
    },
    {
      "epoch": 0.005801467101776699,
      "grad_norm": 0.7662746906280518,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6978,
      "step": 52
    },
    {
      "epoch": 0.005913033776810866,
      "grad_norm": 0.6619462966918945,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.5058,
      "step": 53
    },
    {
      "epoch": 0.006024600451845034,
      "grad_norm": 0.5823963284492493,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4919,
      "step": 54
    },
    {
      "epoch": 0.006136167126879201,
      "grad_norm": 0.562597930431366,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2202,
      "step": 55
    },
    {
      "epoch": 0.006247733801913368,
      "grad_norm": 0.5870577692985535,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.2853,
      "step": 56
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.5877674221992493,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.4519,
      "step": 57
    },
    {
      "epoch": 0.006470867151981703,
      "grad_norm": 0.5663419961929321,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.4985,
      "step": 58
    },
    {
      "epoch": 0.00658243382701587,
      "grad_norm": 0.5482166409492493,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.3884,
      "step": 59
    },
    {
      "epoch": 0.006694000502050037,
      "grad_norm": 0.5972540378570557,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.3402,
      "step": 60
    },
    {
      "epoch": 0.006805567177084205,
      "grad_norm": 0.5697492361068726,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3803,
      "step": 61
    },
    {
      "epoch": 0.006917133852118372,
      "grad_norm": 0.5879175662994385,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.3932,
      "step": 62
    },
    {
      "epoch": 0.007028700527152539,
      "grad_norm": 0.5281646847724915,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.359,
      "step": 63
    },
    {
      "epoch": 0.007140267202186707,
      "grad_norm": 0.5178095698356628,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.3358,
      "step": 64
    },
    {
      "epoch": 0.007251833877220874,
      "grad_norm": 0.5230945348739624,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2897,
      "step": 65
    },
    {
      "epoch": 0.007363400552255041,
      "grad_norm": 0.5501125454902649,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.3946,
      "step": 66
    },
    {
      "epoch": 0.007474967227289209,
      "grad_norm": 0.5552961230278015,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1665,
      "step": 67
    },
    {
      "epoch": 0.007586533902323376,
      "grad_norm": 0.5345686674118042,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.3114,
      "step": 68
    },
    {
      "epoch": 0.007698100577357543,
      "grad_norm": 0.5232676863670349,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.2653,
      "step": 69
    },
    {
      "epoch": 0.007809667252391711,
      "grad_norm": 0.5394402146339417,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.3669,
      "step": 70
    },
    {
      "epoch": 0.007921233927425877,
      "grad_norm": 0.5425289273262024,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2137,
      "step": 71
    },
    {
      "epoch": 0.008032800602460045,
      "grad_norm": 0.5251595377922058,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.3834,
      "step": 72
    },
    {
      "epoch": 0.008144367277494213,
      "grad_norm": 0.5321741104125977,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0916,
      "step": 73
    },
    {
      "epoch": 0.008255933952528379,
      "grad_norm": 0.623486340045929,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.2936,
      "step": 74
    },
    {
      "epoch": 0.008367500627562547,
      "grad_norm": 0.5769821405410767,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2615,
      "step": 75
    },
    {
      "epoch": 0.008479067302596715,
      "grad_norm": 0.6263318657875061,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.175,
      "step": 76
    },
    {
      "epoch": 0.008590633977630881,
      "grad_norm": 0.5833225250244141,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2302,
      "step": 77
    },
    {
      "epoch": 0.008702200652665049,
      "grad_norm": 0.6209061145782471,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.2526,
      "step": 78
    },
    {
      "epoch": 0.008813767327699217,
      "grad_norm": 0.5824259519577026,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.093,
      "step": 79
    },
    {
      "epoch": 0.008925334002733383,
      "grad_norm": 0.6268389821052551,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.1877,
      "step": 80
    },
    {
      "epoch": 0.009036900677767551,
      "grad_norm": 0.6264435648918152,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.2756,
      "step": 81
    },
    {
      "epoch": 0.009148467352801719,
      "grad_norm": 0.6446323990821838,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.1493,
      "step": 82
    },
    {
      "epoch": 0.009260034027835885,
      "grad_norm": 0.6266093850135803,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2545,
      "step": 83
    },
    {
      "epoch": 0.009371600702870053,
      "grad_norm": 0.6394511461257935,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.362,
      "step": 84
    },
    {
      "epoch": 0.00948316737790422,
      "grad_norm": 0.6467508673667908,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2558,
      "step": 85
    },
    {
      "epoch": 0.009594734052938387,
      "grad_norm": 0.6383329033851624,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0696,
      "step": 86
    },
    {
      "epoch": 0.009706300727972555,
      "grad_norm": 0.6785069108009338,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.3649,
      "step": 87
    },
    {
      "epoch": 0.009817867403006723,
      "grad_norm": 0.6810206174850464,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0607,
      "step": 88
    },
    {
      "epoch": 0.009929434078040889,
      "grad_norm": 0.6995563507080078,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2341,
      "step": 89
    },
    {
      "epoch": 0.010041000753075057,
      "grad_norm": 0.695947527885437,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.0389,
      "step": 90
    },
    {
      "epoch": 0.010152567428109223,
      "grad_norm": 0.6923220753669739,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.0856,
      "step": 91
    },
    {
      "epoch": 0.01026413410314339,
      "grad_norm": 0.7765784859657288,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0374,
      "step": 92
    },
    {
      "epoch": 0.010375700778177559,
      "grad_norm": 0.723997950553894,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.027,
      "step": 93
    },
    {
      "epoch": 0.010487267453211725,
      "grad_norm": 0.7475523948669434,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3014,
      "step": 94
    },
    {
      "epoch": 0.010598834128245893,
      "grad_norm": 0.7440254092216492,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.1488,
      "step": 95
    },
    {
      "epoch": 0.01071040080328006,
      "grad_norm": 0.7378959059715271,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1061,
      "step": 96
    },
    {
      "epoch": 0.010821967478314227,
      "grad_norm": 0.7695760130882263,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.096,
      "step": 97
    },
    {
      "epoch": 0.010933534153348395,
      "grad_norm": 0.8142214417457581,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0555,
      "step": 98
    },
    {
      "epoch": 0.011045100828382563,
      "grad_norm": 0.8704457879066467,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0244,
      "step": 99
    },
    {
      "epoch": 0.011156667503416729,
      "grad_norm": 0.9400315880775452,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8876,
      "step": 100
    },
    {
      "epoch": 0.011156667503416729,
      "eval_loss": 1.2055931091308594,
      "eval_runtime": 460.348,
      "eval_samples_per_second": 32.795,
      "eval_steps_per_second": 8.2,
      "step": 100
    },
    {
      "epoch": 0.011268234178450897,
      "grad_norm": 0.6704447865486145,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.6459,
      "step": 101
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": 0.5860530734062195,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.3297,
      "step": 102
    },
    {
      "epoch": 0.01149136752851923,
      "grad_norm": 0.5958092212677002,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.4463,
      "step": 103
    },
    {
      "epoch": 0.011602934203553399,
      "grad_norm": 0.6221890449523926,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.4539,
      "step": 104
    },
    {
      "epoch": 0.011714500878587567,
      "grad_norm": 0.630011796951294,
      "learning_rate": 5e-05,
      "loss": 1.3289,
      "step": 105
    },
    {
      "epoch": 0.011826067553621733,
      "grad_norm": 0.604752779006958,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2577,
      "step": 106
    },
    {
      "epoch": 0.0119376342286559,
      "grad_norm": 0.5483505725860596,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.46,
      "step": 107
    },
    {
      "epoch": 0.012049200903690068,
      "grad_norm": 0.5259597301483154,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.3506,
      "step": 108
    },
    {
      "epoch": 0.012160767578724235,
      "grad_norm": 0.49349817633628845,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.1911,
      "step": 109
    },
    {
      "epoch": 0.012272334253758403,
      "grad_norm": 0.5505238175392151,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.3942,
      "step": 110
    },
    {
      "epoch": 0.01238390092879257,
      "grad_norm": 0.5511454939842224,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.3373,
      "step": 111
    },
    {
      "epoch": 0.012495467603826737,
      "grad_norm": 0.4878992438316345,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.248,
      "step": 112
    },
    {
      "epoch": 0.012607034278860904,
      "grad_norm": 0.5221037864685059,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.2213,
      "step": 113
    },
    {
      "epoch": 0.012718600953895072,
      "grad_norm": 0.5256132483482361,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.324,
      "step": 114
    },
    {
      "epoch": 0.012830167628929239,
      "grad_norm": 0.5336422920227051,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.3151,
      "step": 115
    },
    {
      "epoch": 0.012941734303963406,
      "grad_norm": 0.5704540610313416,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2558,
      "step": 116
    },
    {
      "epoch": 0.013053300978997573,
      "grad_norm": 0.555993378162384,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.2644,
      "step": 117
    },
    {
      "epoch": 0.01316486765403174,
      "grad_norm": 0.5103819966316223,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9954,
      "step": 118
    },
    {
      "epoch": 0.013276434329065908,
      "grad_norm": 0.5305713415145874,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.2512,
      "step": 119
    },
    {
      "epoch": 0.013388001004100075,
      "grad_norm": 0.509528398513794,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.2577,
      "step": 120
    },
    {
      "epoch": 0.013499567679134242,
      "grad_norm": 0.5733562111854553,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.276,
      "step": 121
    },
    {
      "epoch": 0.01361113435416841,
      "grad_norm": 0.6152599453926086,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.3447,
      "step": 122
    },
    {
      "epoch": 0.013722701029202576,
      "grad_norm": 0.565031111240387,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.417,
      "step": 123
    },
    {
      "epoch": 0.013834267704236744,
      "grad_norm": 0.5643124580383301,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1225,
      "step": 124
    },
    {
      "epoch": 0.013945834379270912,
      "grad_norm": 0.5805447697639465,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3068,
      "step": 125
    },
    {
      "epoch": 0.014057401054305078,
      "grad_norm": 0.5870425701141357,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.2871,
      "step": 126
    },
    {
      "epoch": 0.014168967729339246,
      "grad_norm": 0.5862602591514587,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.0415,
      "step": 127
    },
    {
      "epoch": 0.014280534404373414,
      "grad_norm": 0.5894200205802917,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.3028,
      "step": 128
    },
    {
      "epoch": 0.01439210107940758,
      "grad_norm": 0.6419255137443542,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.1719,
      "step": 129
    },
    {
      "epoch": 0.014503667754441748,
      "grad_norm": 0.5962880253791809,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.2073,
      "step": 130
    },
    {
      "epoch": 0.014615234429475916,
      "grad_norm": 0.737921953201294,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2359,
      "step": 131
    },
    {
      "epoch": 0.014726801104510082,
      "grad_norm": 0.652103841304779,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.2571,
      "step": 132
    },
    {
      "epoch": 0.01483836777954425,
      "grad_norm": 0.6353341341018677,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.2516,
      "step": 133
    },
    {
      "epoch": 0.014949934454578418,
      "grad_norm": 0.6949398517608643,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.2131,
      "step": 134
    },
    {
      "epoch": 0.015061501129612584,
      "grad_norm": 0.6557270884513855,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.1164,
      "step": 135
    },
    {
      "epoch": 0.015173067804646752,
      "grad_norm": 0.6954398155212402,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.0899,
      "step": 136
    },
    {
      "epoch": 0.01528463447968092,
      "grad_norm": 0.6232451796531677,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1098,
      "step": 137
    },
    {
      "epoch": 0.015396201154715086,
      "grad_norm": 0.6711903810501099,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.1461,
      "step": 138
    },
    {
      "epoch": 0.015507767829749254,
      "grad_norm": 0.706368625164032,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.1141,
      "step": 139
    },
    {
      "epoch": 0.015619334504783422,
      "grad_norm": 0.6230055093765259,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9038,
      "step": 140
    },
    {
      "epoch": 0.01573090117981759,
      "grad_norm": 0.6431025266647339,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.9516,
      "step": 141
    },
    {
      "epoch": 0.015842467854851754,
      "grad_norm": 0.7076598405838013,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.1332,
      "step": 142
    },
    {
      "epoch": 0.015954034529885922,
      "grad_norm": 0.6765874624252319,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0975,
      "step": 143
    },
    {
      "epoch": 0.01606560120492009,
      "grad_norm": 0.8565897345542908,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9897,
      "step": 144
    },
    {
      "epoch": 0.016177167879954258,
      "grad_norm": 0.7564114332199097,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1074,
      "step": 145
    },
    {
      "epoch": 0.016288734554988426,
      "grad_norm": 0.7603456974029541,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.1735,
      "step": 146
    },
    {
      "epoch": 0.016400301230022594,
      "grad_norm": 0.7829017043113708,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.0999,
      "step": 147
    },
    {
      "epoch": 0.016511867905056758,
      "grad_norm": 1.0034749507904053,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.082,
      "step": 148
    },
    {
      "epoch": 0.016623434580090926,
      "grad_norm": 0.9020680785179138,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.977,
      "step": 149
    },
    {
      "epoch": 0.016735001255125094,
      "grad_norm": 0.9965061545372009,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9525,
      "step": 150
    },
    {
      "epoch": 0.016735001255125094,
      "eval_loss": 1.1714409589767456,
      "eval_runtime": 460.3576,
      "eval_samples_per_second": 32.794,
      "eval_steps_per_second": 8.2,
      "step": 150
    },
    {
      "epoch": 0.016846567930159262,
      "grad_norm": 0.6767730712890625,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.5867,
      "step": 151
    },
    {
      "epoch": 0.01695813460519343,
      "grad_norm": 0.6256797313690186,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.4655,
      "step": 152
    },
    {
      "epoch": 0.017069701280227598,
      "grad_norm": 0.492017537355423,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.4067,
      "step": 153
    },
    {
      "epoch": 0.017181267955261762,
      "grad_norm": 0.5782871246337891,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.3896,
      "step": 154
    },
    {
      "epoch": 0.01729283463029593,
      "grad_norm": 0.5900678038597107,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.2799,
      "step": 155
    },
    {
      "epoch": 0.017404401305330098,
      "grad_norm": 0.62517249584198,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.2015,
      "step": 156
    },
    {
      "epoch": 0.017515967980364266,
      "grad_norm": 0.5676795840263367,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.3811,
      "step": 157
    },
    {
      "epoch": 0.017627534655398434,
      "grad_norm": 0.6299328804016113,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.2976,
      "step": 158
    },
    {
      "epoch": 0.017739101330432598,
      "grad_norm": 0.5309059023857117,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.345,
      "step": 159
    },
    {
      "epoch": 0.017850668005466766,
      "grad_norm": 0.5679674744606018,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2847,
      "step": 160
    },
    {
      "epoch": 0.017962234680500934,
      "grad_norm": 0.5760466456413269,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.3064,
      "step": 161
    },
    {
      "epoch": 0.018073801355535102,
      "grad_norm": 0.568834662437439,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.221,
      "step": 162
    },
    {
      "epoch": 0.01818536803056927,
      "grad_norm": 0.5528172254562378,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.2826,
      "step": 163
    },
    {
      "epoch": 0.018296934705603438,
      "grad_norm": 0.5355699062347412,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.1298,
      "step": 164
    },
    {
      "epoch": 0.018408501380637602,
      "grad_norm": 0.5759557485580444,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.226,
      "step": 165
    },
    {
      "epoch": 0.01852006805567177,
      "grad_norm": 0.5456483960151672,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.2793,
      "step": 166
    },
    {
      "epoch": 0.018631634730705938,
      "grad_norm": 0.5756639242172241,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.2356,
      "step": 167
    },
    {
      "epoch": 0.018743201405740106,
      "grad_norm": 0.5312953591346741,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.2817,
      "step": 168
    },
    {
      "epoch": 0.018854768080774274,
      "grad_norm": 0.5708112716674805,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2447,
      "step": 169
    },
    {
      "epoch": 0.01896633475580844,
      "grad_norm": 0.5997335910797119,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.219,
      "step": 170
    },
    {
      "epoch": 0.019077901430842606,
      "grad_norm": 0.5820359587669373,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.3588,
      "step": 171
    },
    {
      "epoch": 0.019189468105876774,
      "grad_norm": 0.5868438482284546,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.0913,
      "step": 172
    },
    {
      "epoch": 0.01930103478091094,
      "grad_norm": 0.5808361172676086,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.3275,
      "step": 173
    },
    {
      "epoch": 0.01941260145594511,
      "grad_norm": 0.6170180439949036,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3235,
      "step": 174
    },
    {
      "epoch": 0.019524168130979278,
      "grad_norm": 0.5957433581352234,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.1835,
      "step": 175
    },
    {
      "epoch": 0.019635734806013445,
      "grad_norm": 0.5498396158218384,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.2558,
      "step": 176
    },
    {
      "epoch": 0.01974730148104761,
      "grad_norm": 0.591564953327179,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.1941,
      "step": 177
    },
    {
      "epoch": 0.019858868156081778,
      "grad_norm": 0.6696902513504028,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1435,
      "step": 178
    },
    {
      "epoch": 0.019970434831115946,
      "grad_norm": 0.6001175045967102,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2872,
      "step": 179
    },
    {
      "epoch": 0.020082001506150114,
      "grad_norm": 0.6337319016456604,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.206,
      "step": 180
    },
    {
      "epoch": 0.02019356818118428,
      "grad_norm": 0.6001356840133667,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1055,
      "step": 181
    },
    {
      "epoch": 0.020305134856218446,
      "grad_norm": 0.6372250318527222,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.1673,
      "step": 182
    },
    {
      "epoch": 0.020416701531252614,
      "grad_norm": 0.6520158648490906,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.2162,
      "step": 183
    },
    {
      "epoch": 0.02052826820628678,
      "grad_norm": 0.6295961141586304,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.0673,
      "step": 184
    },
    {
      "epoch": 0.02063983488132095,
      "grad_norm": 0.6633396744728088,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.2067,
      "step": 185
    },
    {
      "epoch": 0.020751401556355117,
      "grad_norm": 0.6314449906349182,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.1939,
      "step": 186
    },
    {
      "epoch": 0.020862968231389285,
      "grad_norm": 0.6701759696006775,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.184,
      "step": 187
    },
    {
      "epoch": 0.02097453490642345,
      "grad_norm": 0.6675221920013428,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.1315,
      "step": 188
    },
    {
      "epoch": 0.021086101581457618,
      "grad_norm": 0.6282130479812622,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.0596,
      "step": 189
    },
    {
      "epoch": 0.021197668256491786,
      "grad_norm": 0.7050791382789612,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.141,
      "step": 190
    },
    {
      "epoch": 0.021309234931525953,
      "grad_norm": 0.6381725668907166,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.0218,
      "step": 191
    },
    {
      "epoch": 0.02142080160656012,
      "grad_norm": 0.6537929773330688,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.0308,
      "step": 192
    },
    {
      "epoch": 0.02153236828159429,
      "grad_norm": 0.763849675655365,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.1224,
      "step": 193
    },
    {
      "epoch": 0.021643934956628454,
      "grad_norm": 0.7321624755859375,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.0224,
      "step": 194
    },
    {
      "epoch": 0.02175550163166262,
      "grad_norm": 0.6499798893928528,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9572,
      "step": 195
    },
    {
      "epoch": 0.02186706830669679,
      "grad_norm": 0.841247022151947,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.0622,
      "step": 196
    },
    {
      "epoch": 0.021978634981730957,
      "grad_norm": 0.7490094304084778,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.1358,
      "step": 197
    },
    {
      "epoch": 0.022090201656765125,
      "grad_norm": 0.8326240181922913,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.9694,
      "step": 198
    },
    {
      "epoch": 0.022201768331799293,
      "grad_norm": 0.8259689211845398,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.9362,
      "step": 199
    },
    {
      "epoch": 0.022313335006833458,
      "grad_norm": 1.010990023612976,
      "learning_rate": 0.0,
      "loss": 1.0831,
      "step": 200
    },
    {
      "epoch": 0.022313335006833458,
      "eval_loss": 1.1653963327407837,
      "eval_runtime": 460.4001,
      "eval_samples_per_second": 32.791,
      "eval_steps_per_second": 8.199,
      "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
}