{
  "best_metric": 1.1155003309249878,
  "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": 2.653162956237793,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.3102,
      "step": 1
    },
    {
      "epoch": 0.0001115666750341673,
      "eval_loss": 2.114264488220215,
      "eval_runtime": 1178.428,
      "eval_samples_per_second": 12.811,
      "eval_steps_per_second": 3.203,
      "step": 1
    },
    {
      "epoch": 0.0002231333500683346,
      "grad_norm": 2.449162244796753,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.1695,
      "step": 2
    },
    {
      "epoch": 0.0003347000251025019,
      "grad_norm": 2.531275510787964,
      "learning_rate": 2.4e-05,
      "loss": 2.1155,
      "step": 3
    },
    {
      "epoch": 0.0004462667001366692,
      "grad_norm": 2.4609928131103516,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.0768,
      "step": 4
    },
    {
      "epoch": 0.0005578333751708364,
      "grad_norm": 2.380425453186035,
      "learning_rate": 4e-05,
      "loss": 1.8721,
      "step": 5
    },
    {
      "epoch": 0.0006694000502050038,
      "grad_norm": 1.5351266860961914,
      "learning_rate": 4.8e-05,
      "loss": 1.7979,
      "step": 6
    },
    {
      "epoch": 0.000780966725239171,
      "grad_norm": 1.5571147203445435,
      "learning_rate": 5.6e-05,
      "loss": 1.7501,
      "step": 7
    },
    {
      "epoch": 0.0008925334002733384,
      "grad_norm": 1.7607723474502563,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.6559,
      "step": 8
    },
    {
      "epoch": 0.0010041000753075056,
      "grad_norm": 1.6330875158309937,
      "learning_rate": 7.2e-05,
      "loss": 1.4968,
      "step": 9
    },
    {
      "epoch": 0.0011156667503416729,
      "grad_norm": 1.3503739833831787,
      "learning_rate": 8e-05,
      "loss": 1.5725,
      "step": 10
    },
    {
      "epoch": 0.0012272334253758403,
      "grad_norm": 1.2828761339187622,
      "learning_rate": 7.999453219969877e-05,
      "loss": 1.4362,
      "step": 11
    },
    {
      "epoch": 0.0013388001004100076,
      "grad_norm": 1.2013221979141235,
      "learning_rate": 7.997813029363704e-05,
      "loss": 1.42,
      "step": 12
    },
    {
      "epoch": 0.0014503667754441748,
      "grad_norm": 1.2638128995895386,
      "learning_rate": 7.99507987659322e-05,
      "loss": 1.5151,
      "step": 13
    },
    {
      "epoch": 0.001561933450478342,
      "grad_norm": 1.1523526906967163,
      "learning_rate": 7.991254508875098e-05,
      "loss": 1.4517,
      "step": 14
    },
    {
      "epoch": 0.0016735001255125093,
      "grad_norm": 1.09688138961792,
      "learning_rate": 7.98633797202668e-05,
      "loss": 1.3846,
      "step": 15
    },
    {
      "epoch": 0.0017850668005466768,
      "grad_norm": 1.146205186843872,
      "learning_rate": 7.980331610180046e-05,
      "loss": 1.3012,
      "step": 16
    },
    {
      "epoch": 0.001896633475580844,
      "grad_norm": 0.9450773000717163,
      "learning_rate": 7.973237065414553e-05,
      "loss": 1.3625,
      "step": 17
    },
    {
      "epoch": 0.0020082001506150113,
      "grad_norm": 0.9548523426055908,
      "learning_rate": 7.965056277307902e-05,
      "loss": 1.4134,
      "step": 18
    },
    {
      "epoch": 0.0021197668256491787,
      "grad_norm": 0.9216581583023071,
      "learning_rate": 7.955791482405875e-05,
      "loss": 1.2652,
      "step": 19
    },
    {
      "epoch": 0.0022313335006833458,
      "grad_norm": 1.0505989789962769,
      "learning_rate": 7.94544521361089e-05,
      "loss": 1.423,
      "step": 20
    },
    {
      "epoch": 0.002342900175717513,
      "grad_norm": 1.0446711778640747,
      "learning_rate": 7.93402029948953e-05,
      "loss": 1.3668,
      "step": 21
    },
    {
      "epoch": 0.0024544668507516807,
      "grad_norm": 0.9442985653877258,
      "learning_rate": 7.921519863499239e-05,
      "loss": 1.3191,
      "step": 22
    },
    {
      "epoch": 0.0025660335257858477,
      "grad_norm": 1.0523488521575928,
      "learning_rate": 7.907947323134398e-05,
      "loss": 1.3794,
      "step": 23
    },
    {
      "epoch": 0.002677600200820015,
      "grad_norm": 1.0296598672866821,
      "learning_rate": 7.893306388992023e-05,
      "loss": 1.2788,
      "step": 24
    },
    {
      "epoch": 0.002789166875854182,
      "grad_norm": 1.1668524742126465,
      "learning_rate": 7.877601063757323e-05,
      "loss": 1.4645,
      "step": 25
    },
    {
      "epoch": 0.0029007335508883497,
      "grad_norm": 1.0953292846679688,
      "learning_rate": 7.860835641109395e-05,
      "loss": 1.3605,
      "step": 26
    },
    {
      "epoch": 0.003012300225922517,
      "grad_norm": 1.152095079421997,
      "learning_rate": 7.843014704547393e-05,
      "loss": 1.379,
      "step": 27
    },
    {
      "epoch": 0.003123866900956684,
      "grad_norm": 1.132886290550232,
      "learning_rate": 7.824143126137431e-05,
      "loss": 1.3073,
      "step": 28
    },
    {
      "epoch": 0.0032354335759908516,
      "grad_norm": 1.0807931423187256,
      "learning_rate": 7.804226065180615e-05,
      "loss": 1.3226,
      "step": 29
    },
    {
      "epoch": 0.0033470002510250186,
      "grad_norm": 1.1306511163711548,
      "learning_rate": 7.783268966802539e-05,
      "loss": 1.3538,
      "step": 30
    },
    {
      "epoch": 0.003458566926059186,
      "grad_norm": 0.9918445348739624,
      "learning_rate": 7.761277560464645e-05,
      "loss": 1.2237,
      "step": 31
    },
    {
      "epoch": 0.0035701336010933536,
      "grad_norm": 1.0658776760101318,
      "learning_rate": 7.738257858397844e-05,
      "loss": 1.0874,
      "step": 32
    },
    {
      "epoch": 0.0036817002761275206,
      "grad_norm": 1.0365428924560547,
      "learning_rate": 7.71421615395883e-05,
      "loss": 1.273,
      "step": 33
    },
    {
      "epoch": 0.003793266951161688,
      "grad_norm": 1.19215989112854,
      "learning_rate": 7.68915901990954e-05,
      "loss": 1.2374,
      "step": 34
    },
    {
      "epoch": 0.0039048336261958555,
      "grad_norm": 1.0782256126403809,
      "learning_rate": 7.663093306620231e-05,
      "loss": 1.2026,
      "step": 35
    },
    {
      "epoch": 0.0040164003012300225,
      "grad_norm": 1.217738151550293,
      "learning_rate": 7.636026140196651e-05,
      "loss": 1.4224,
      "step": 36
    },
    {
      "epoch": 0.0041279669762641896,
      "grad_norm": 1.1175963878631592,
      "learning_rate": 7.607964920531837e-05,
      "loss": 1.2956,
      "step": 37
    },
    {
      "epoch": 0.0042395336512983575,
      "grad_norm": 1.1036632061004639,
      "learning_rate": 7.578917319283055e-05,
      "loss": 1.0602,
      "step": 38
    },
    {
      "epoch": 0.0043511003263325245,
      "grad_norm": 1.3284820318222046,
      "learning_rate": 7.548891277774448e-05,
      "loss": 1.3699,
      "step": 39
    },
    {
      "epoch": 0.0044626670013666915,
      "grad_norm": 1.09949791431427,
      "learning_rate": 7.517895004825956e-05,
      "loss": 1.1194,
      "step": 40
    },
    {
      "epoch": 0.004574233676400859,
      "grad_norm": 1.3073527812957764,
      "learning_rate": 7.48593697450911e-05,
      "loss": 1.2744,
      "step": 41
    },
    {
      "epoch": 0.004685800351435026,
      "grad_norm": 1.3388763666152954,
      "learning_rate": 7.453025923830296e-05,
      "loss": 1.257,
      "step": 42
    },
    {
      "epoch": 0.0047973670264691935,
      "grad_norm": 1.5201784372329712,
      "learning_rate": 7.419170850342156e-05,
      "loss": 1.2134,
      "step": 43
    },
    {
      "epoch": 0.004908933701503361,
      "grad_norm": 1.4326601028442383,
      "learning_rate": 7.384381009683742e-05,
      "loss": 1.1861,
      "step": 44
    },
    {
      "epoch": 0.005020500376537528,
      "grad_norm": 1.4766429662704468,
      "learning_rate": 7.348665913050115e-05,
      "loss": 1.279,
      "step": 45
    },
    {
      "epoch": 0.005132067051571695,
      "grad_norm": 1.4081569910049438,
      "learning_rate": 7.312035324592081e-05,
      "loss": 1.1668,
      "step": 46
    },
    {
      "epoch": 0.005243633726605862,
      "grad_norm": 1.439784288406372,
      "learning_rate": 7.274499258746771e-05,
      "loss": 1.1706,
      "step": 47
    },
    {
      "epoch": 0.00535520040164003,
      "grad_norm": 1.4231797456741333,
      "learning_rate": 7.236067977499791e-05,
      "loss": 1.0786,
      "step": 48
    },
    {
      "epoch": 0.005466767076674197,
      "grad_norm": 1.403438925743103,
      "learning_rate": 7.196751987579699e-05,
      "loss": 1.0702,
      "step": 49
    },
    {
      "epoch": 0.005578333751708364,
      "grad_norm": 1.865836501121521,
      "learning_rate": 7.156562037585576e-05,
      "loss": 1.0554,
      "step": 50
    },
    {
      "epoch": 0.005578333751708364,
      "eval_loss": 1.2656643390655518,
      "eval_runtime": 1183.4004,
      "eval_samples_per_second": 12.757,
      "eval_steps_per_second": 3.19,
      "step": 50
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 1.388903260231018,
      "learning_rate": 7.11550911504845e-05,
      "loss": 1.8208,
      "step": 51
    },
    {
      "epoch": 0.005801467101776699,
      "grad_norm": 1.0922175645828247,
      "learning_rate": 7.073604443427437e-05,
      "loss": 1.4857,
      "step": 52
    },
    {
      "epoch": 0.005913033776810866,
      "grad_norm": 1.1377652883529663,
      "learning_rate": 7.03085947904134e-05,
      "loss": 1.4642,
      "step": 53
    },
    {
      "epoch": 0.006024600451845034,
      "grad_norm": 1.0178011655807495,
      "learning_rate": 6.987285907936617e-05,
      "loss": 1.3595,
      "step": 54
    },
    {
      "epoch": 0.006136167126879201,
      "grad_norm": 1.0533956289291382,
      "learning_rate": 6.942895642692527e-05,
      "loss": 1.3205,
      "step": 55
    },
    {
      "epoch": 0.006247733801913368,
      "grad_norm": 0.9825334548950195,
      "learning_rate": 6.897700819164357e-05,
      "loss": 1.2667,
      "step": 56
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.9113156199455261,
      "learning_rate": 6.851713793165589e-05,
      "loss": 1.2543,
      "step": 57
    },
    {
      "epoch": 0.006470867151981703,
      "grad_norm": 0.8248892426490784,
      "learning_rate": 6.804947137089955e-05,
      "loss": 1.3133,
      "step": 58
    },
    {
      "epoch": 0.00658243382701587,
      "grad_norm": 0.8727787733078003,
      "learning_rate": 6.757413636474263e-05,
      "loss": 1.3125,
      "step": 59
    },
    {
      "epoch": 0.006694000502050037,
      "grad_norm": 0.9488885402679443,
      "learning_rate": 6.709126286502965e-05,
      "loss": 1.327,
      "step": 60
    },
    {
      "epoch": 0.006805567177084205,
      "grad_norm": 0.8989211320877075,
      "learning_rate": 6.660098288455393e-05,
      "loss": 1.1596,
      "step": 61
    },
    {
      "epoch": 0.006917133852118372,
      "grad_norm": 0.904154896736145,
      "learning_rate": 6.610343046096674e-05,
      "loss": 1.1647,
      "step": 62
    },
    {
      "epoch": 0.007028700527152539,
      "grad_norm": 0.8586918115615845,
      "learning_rate": 6.559874162013267e-05,
      "loss": 1.1605,
      "step": 63
    },
    {
      "epoch": 0.007140267202186707,
      "grad_norm": 0.9001997709274292,
      "learning_rate": 6.508705433894149e-05,
      "loss": 1.3327,
      "step": 64
    },
    {
      "epoch": 0.007251833877220874,
      "grad_norm": 0.8475323915481567,
      "learning_rate": 6.456850850758673e-05,
      "loss": 1.1643,
      "step": 65
    },
    {
      "epoch": 0.007363400552255041,
      "grad_norm": 0.9225298762321472,
      "learning_rate": 6.404324589132101e-05,
      "loss": 1.2149,
      "step": 66
    },
    {
      "epoch": 0.007474967227289209,
      "grad_norm": 0.8501834869384766,
      "learning_rate": 6.351141009169893e-05,
      "loss": 1.181,
      "step": 67
    },
    {
      "epoch": 0.007586533902323376,
      "grad_norm": 0.9416823983192444,
      "learning_rate": 6.297314650731775e-05,
      "loss": 1.2624,
      "step": 68
    },
    {
      "epoch": 0.007698100577357543,
      "grad_norm": 0.8258371949195862,
      "learning_rate": 6.242860229406692e-05,
      "loss": 1.1523,
      "step": 69
    },
    {
      "epoch": 0.007809667252391711,
      "grad_norm": 0.8512648344039917,
      "learning_rate": 6.18779263248971e-05,
      "loss": 1.1725,
      "step": 70
    },
    {
      "epoch": 0.007921233927425877,
      "grad_norm": 0.8364467024803162,
      "learning_rate": 6.132126914911976e-05,
      "loss": 1.1696,
      "step": 71
    },
    {
      "epoch": 0.008032800602460045,
      "grad_norm": 0.7922412753105164,
      "learning_rate": 6.075878295124861e-05,
      "loss": 1.0674,
      "step": 72
    },
    {
      "epoch": 0.008144367277494213,
      "grad_norm": 0.8955839276313782,
      "learning_rate": 6.019062150939376e-05,
      "loss": 1.2391,
      "step": 73
    },
    {
      "epoch": 0.008255933952528379,
      "grad_norm": 0.883040726184845,
      "learning_rate": 5.9616940153220336e-05,
      "loss": 1.3788,
      "step": 74
    },
    {
      "epoch": 0.008367500627562547,
      "grad_norm": 0.8692553639411926,
      "learning_rate": 5.903789572148295e-05,
      "loss": 1.1941,
      "step": 75
    },
    {
      "epoch": 0.008479067302596715,
      "grad_norm": 0.9407691955566406,
      "learning_rate": 5.845364651914752e-05,
      "loss": 1.2981,
      "step": 76
    },
    {
      "epoch": 0.008590633977630881,
      "grad_norm": 0.8941450119018555,
      "learning_rate": 5.786435227411227e-05,
      "loss": 1.1009,
      "step": 77
    },
    {
      "epoch": 0.008702200652665049,
      "grad_norm": 0.9692277908325195,
      "learning_rate": 5.727017409353971e-05,
      "loss": 1.3274,
      "step": 78
    },
    {
      "epoch": 0.008813767327699217,
      "grad_norm": 0.9406832456588745,
      "learning_rate": 5.667127441981162e-05,
      "loss": 1.2052,
      "step": 79
    },
    {
      "epoch": 0.008925334002733383,
      "grad_norm": 0.9091105461120605,
      "learning_rate": 5.606781698611879e-05,
      "loss": 1.0985,
      "step": 80
    },
    {
      "epoch": 0.009036900677767551,
      "grad_norm": 0.9770876169204712,
      "learning_rate": 5.5459966771698096e-05,
      "loss": 1.0522,
      "step": 81
    },
    {
      "epoch": 0.009148467352801719,
      "grad_norm": 0.8914808630943298,
      "learning_rate": 5.4847889956728834e-05,
      "loss": 1.1276,
      "step": 82
    },
    {
      "epoch": 0.009260034027835885,
      "grad_norm": 0.9220410585403442,
      "learning_rate": 5.423175387690067e-05,
      "loss": 1.1342,
      "step": 83
    },
    {
      "epoch": 0.009371600702870053,
      "grad_norm": 0.9457625150680542,
      "learning_rate": 5.361172697766573e-05,
      "loss": 1.1892,
      "step": 84
    },
    {
      "epoch": 0.00948316737790422,
      "grad_norm": 0.9678511023521423,
      "learning_rate": 5.298797876818735e-05,
      "loss": 1.0223,
      "step": 85
    },
    {
      "epoch": 0.009594734052938387,
      "grad_norm": 0.9996553659439087,
      "learning_rate": 5.23606797749979e-05,
      "loss": 1.0629,
      "step": 86
    },
    {
      "epoch": 0.009706300727972555,
      "grad_norm": 1.065645456314087,
      "learning_rate": 5.17300014953786e-05,
      "loss": 1.1248,
      "step": 87
    },
    {
      "epoch": 0.009817867403006723,
      "grad_norm": 1.0297746658325195,
      "learning_rate": 5.109611635047379e-05,
      "loss": 1.1184,
      "step": 88
    },
    {
      "epoch": 0.009929434078040889,
      "grad_norm": 0.9987531900405884,
      "learning_rate": 5.04591976381528e-05,
      "loss": 1.1138,
      "step": 89
    },
    {
      "epoch": 0.010041000753075057,
      "grad_norm": 0.9533745050430298,
      "learning_rate": 4.981941948563197e-05,
      "loss": 1.084,
      "step": 90
    },
    {
      "epoch": 0.010152567428109223,
      "grad_norm": 1.1118968725204468,
      "learning_rate": 4.9176956801870065e-05,
      "loss": 1.0032,
      "step": 91
    },
    {
      "epoch": 0.01026413410314339,
      "grad_norm": 1.0484565496444702,
      "learning_rate": 4.853198522974988e-05,
      "loss": 0.9708,
      "step": 92
    },
    {
      "epoch": 0.010375700778177559,
      "grad_norm": 0.941596508026123,
      "learning_rate": 4.788468109805921e-05,
      "loss": 0.9696,
      "step": 93
    },
    {
      "epoch": 0.010487267453211725,
      "grad_norm": 1.13180673122406,
      "learning_rate": 4.7235221373284407e-05,
      "loss": 1.0798,
      "step": 94
    },
    {
      "epoch": 0.010598834128245893,
      "grad_norm": 1.2236862182617188,
      "learning_rate": 4.658378361122936e-05,
      "loss": 1.1903,
      "step": 95
    },
    {
      "epoch": 0.01071040080328006,
      "grad_norm": 1.2033003568649292,
      "learning_rate": 4.593054590847368e-05,
      "loss": 1.0621,
      "step": 96
    },
    {
      "epoch": 0.010821967478314227,
      "grad_norm": 1.0950212478637695,
      "learning_rate": 4.5275686853682765e-05,
      "loss": 0.9034,
      "step": 97
    },
    {
      "epoch": 0.010933534153348395,
      "grad_norm": 1.3348255157470703,
      "learning_rate": 4.4619385478783456e-05,
      "loss": 1.1506,
      "step": 98
    },
    {
      "epoch": 0.011045100828382563,
      "grad_norm": 1.4957432746887207,
      "learning_rate": 4.396182121001852e-05,
      "loss": 1.1369,
      "step": 99
    },
    {
      "epoch": 0.011156667503416729,
      "grad_norm": 2.078827142715454,
      "learning_rate": 4.33031738188933e-05,
      "loss": 0.9903,
      "step": 100
    },
    {
      "epoch": 0.011156667503416729,
      "eval_loss": 1.1675224304199219,
      "eval_runtime": 1187.356,
      "eval_samples_per_second": 12.715,
      "eval_steps_per_second": 3.179,
      "step": 100
    },
    {
      "epoch": 0.011268234178450897,
      "grad_norm": 1.03377366065979,
      "learning_rate": 4.264362337302798e-05,
      "loss": 1.4868,
      "step": 101
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": 0.9007754325866699,
      "learning_rate": 4.1983350186928894e-05,
      "loss": 1.5376,
      "step": 102
    },
    {
      "epoch": 0.01149136752851923,
      "grad_norm": 0.8353412747383118,
      "learning_rate": 4.132253477269233e-05,
      "loss": 1.3117,
      "step": 103
    },
    {
      "epoch": 0.011602934203553399,
      "grad_norm": 0.9711883068084717,
      "learning_rate": 4.0661357790654345e-05,
      "loss": 1.1541,
      "step": 104
    },
    {
      "epoch": 0.011714500878587567,
      "grad_norm": 0.7863988280296326,
      "learning_rate": 4e-05,
      "loss": 1.2769,
      "step": 105
    },
    {
      "epoch": 0.011826067553621733,
      "grad_norm": 0.8335726857185364,
      "learning_rate": 3.933864220934566e-05,
      "loss": 1.156,
      "step": 106
    },
    {
      "epoch": 0.0119376342286559,
      "grad_norm": 0.7659847736358643,
      "learning_rate": 3.8677465227307676e-05,
      "loss": 1.2839,
      "step": 107
    },
    {
      "epoch": 0.012049200903690068,
      "grad_norm": 0.8807960152626038,
      "learning_rate": 3.8016649813071106e-05,
      "loss": 1.322,
      "step": 108
    },
    {
      "epoch": 0.012160767578724235,
      "grad_norm": 0.8528708219528198,
      "learning_rate": 3.735637662697203e-05,
      "loss": 1.1657,
      "step": 109
    },
    {
      "epoch": 0.012272334253758403,
      "grad_norm": 0.8083069324493408,
      "learning_rate": 3.669682618110671e-05,
      "loss": 1.2175,
      "step": 110
    },
    {
      "epoch": 0.01238390092879257,
      "grad_norm": 0.7970200777053833,
      "learning_rate": 3.6038178789981494e-05,
      "loss": 1.1687,
      "step": 111
    },
    {
      "epoch": 0.012495467603826737,
      "grad_norm": 0.7781988382339478,
      "learning_rate": 3.538061452121656e-05,
      "loss": 1.136,
      "step": 112
    },
    {
      "epoch": 0.012607034278860904,
      "grad_norm": 0.8137642741203308,
      "learning_rate": 3.472431314631724e-05,
      "loss": 1.2012,
      "step": 113
    },
    {
      "epoch": 0.012718600953895072,
      "grad_norm": 0.8913825154304504,
      "learning_rate": 3.406945409152632e-05,
      "loss": 1.1926,
      "step": 114
    },
    {
      "epoch": 0.012830167628929239,
      "grad_norm": 0.8783978819847107,
      "learning_rate": 3.341621638877064e-05,
      "loss": 1.188,
      "step": 115
    },
    {
      "epoch": 0.012941734303963406,
      "grad_norm": 0.8640679121017456,
      "learning_rate": 3.276477862671562e-05,
      "loss": 1.0542,
      "step": 116
    },
    {
      "epoch": 0.013053300978997573,
      "grad_norm": 0.8714284300804138,
      "learning_rate": 3.21153189019408e-05,
      "loss": 1.2211,
      "step": 117
    },
    {
      "epoch": 0.01316486765403174,
      "grad_norm": 0.8280481696128845,
      "learning_rate": 3.146801477025013e-05,
      "loss": 1.0808,
      "step": 118
    },
    {
      "epoch": 0.013276434329065908,
      "grad_norm": 0.8297896385192871,
      "learning_rate": 3.082304319812994e-05,
      "loss": 1.1227,
      "step": 119
    },
    {
      "epoch": 0.013388001004100075,
      "grad_norm": 0.8418503403663635,
      "learning_rate": 3.0180580514368037e-05,
      "loss": 1.2152,
      "step": 120
    },
    {
      "epoch": 0.013499567679134242,
      "grad_norm": 0.7824004292488098,
      "learning_rate": 2.9540802361847212e-05,
      "loss": 1.1229,
      "step": 121
    },
    {
      "epoch": 0.01361113435416841,
      "grad_norm": 0.8189719915390015,
      "learning_rate": 2.890388364952623e-05,
      "loss": 1.1421,
      "step": 122
    },
    {
      "epoch": 0.013722701029202576,
      "grad_norm": 0.8146119713783264,
      "learning_rate": 2.8269998504621416e-05,
      "loss": 1.0736,
      "step": 123
    },
    {
      "epoch": 0.013834267704236744,
      "grad_norm": 1.066524863243103,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 1.2977,
      "step": 124
    },
    {
      "epoch": 0.013945834379270912,
      "grad_norm": 0.8084144592285156,
      "learning_rate": 2.7012021231812666e-05,
      "loss": 1.201,
      "step": 125
    },
    {
      "epoch": 0.014057401054305078,
      "grad_norm": 0.8299919962882996,
      "learning_rate": 2.638827302233428e-05,
      "loss": 1.1345,
      "step": 126
    },
    {
      "epoch": 0.014168967729339246,
      "grad_norm": 0.8451680541038513,
      "learning_rate": 2.576824612309934e-05,
      "loss": 1.2455,
      "step": 127
    },
    {
      "epoch": 0.014280534404373414,
      "grad_norm": 0.9045851826667786,
      "learning_rate": 2.5152110043271166e-05,
      "loss": 1.2498,
      "step": 128
    },
    {
      "epoch": 0.01439210107940758,
      "grad_norm": 0.9111452698707581,
      "learning_rate": 2.454003322830192e-05,
      "loss": 1.1584,
      "step": 129
    },
    {
      "epoch": 0.014503667754441748,
      "grad_norm": 0.8999844789505005,
      "learning_rate": 2.393218301388123e-05,
      "loss": 1.0248,
      "step": 130
    },
    {
      "epoch": 0.014615234429475916,
      "grad_norm": 1.1039999723434448,
      "learning_rate": 2.3328725580188395e-05,
      "loss": 1.1425,
      "step": 131
    },
    {
      "epoch": 0.014726801104510082,
      "grad_norm": 0.85543292760849,
      "learning_rate": 2.272982590646029e-05,
      "loss": 1.1249,
      "step": 132
    },
    {
      "epoch": 0.01483836777954425,
      "grad_norm": 0.9125653505325317,
      "learning_rate": 2.2135647725887744e-05,
      "loss": 1.0836,
      "step": 133
    },
    {
      "epoch": 0.014949934454578418,
      "grad_norm": 0.9096406698226929,
      "learning_rate": 2.1546353480852495e-05,
      "loss": 1.1764,
      "step": 134
    },
    {
      "epoch": 0.015061501129612584,
      "grad_norm": 0.897408664226532,
      "learning_rate": 2.096210427851706e-05,
      "loss": 1.0352,
      "step": 135
    },
    {
      "epoch": 0.015173067804646752,
      "grad_norm": 1.038303017616272,
      "learning_rate": 2.038305984677969e-05,
      "loss": 1.1442,
      "step": 136
    },
    {
      "epoch": 0.01528463447968092,
      "grad_norm": 0.9297472834587097,
      "learning_rate": 1.9809378490606264e-05,
      "loss": 1.0321,
      "step": 137
    },
    {
      "epoch": 0.015396201154715086,
      "grad_norm": 0.9409924745559692,
      "learning_rate": 1.9241217048751406e-05,
      "loss": 1.0004,
      "step": 138
    },
    {
      "epoch": 0.015507767829749254,
      "grad_norm": 0.9569453597068787,
      "learning_rate": 1.867873085088026e-05,
      "loss": 0.9474,
      "step": 139
    },
    {
      "epoch": 0.015619334504783422,
      "grad_norm": 1.0429985523223877,
      "learning_rate": 1.8122073675102935e-05,
      "loss": 1.0308,
      "step": 140
    },
    {
      "epoch": 0.01573090117981759,
      "grad_norm": 1.1001777648925781,
      "learning_rate": 1.75713977059331e-05,
      "loss": 1.013,
      "step": 141
    },
    {
      "epoch": 0.015842467854851754,
      "grad_norm": 1.0191009044647217,
      "learning_rate": 1.702685349268226e-05,
      "loss": 0.9944,
      "step": 142
    },
    {
      "epoch": 0.015954034529885922,
      "grad_norm": 1.0639243125915527,
      "learning_rate": 1.648858990830108e-05,
      "loss": 1.1787,
      "step": 143
    },
    {
      "epoch": 0.01606560120492009,
      "grad_norm": 0.9979782104492188,
      "learning_rate": 1.5956754108678996e-05,
      "loss": 1.046,
      "step": 144
    },
    {
      "epoch": 0.016177167879954258,
      "grad_norm": 1.1500177383422852,
      "learning_rate": 1.5431491492413288e-05,
      "loss": 1.0585,
      "step": 145
    },
    {
      "epoch": 0.016288734554988426,
      "grad_norm": 1.1362090110778809,
      "learning_rate": 1.491294566105852e-05,
      "loss": 1.1034,
      "step": 146
    },
    {
      "epoch": 0.016400301230022594,
      "grad_norm": 1.2018383741378784,
      "learning_rate": 1.4401258379867335e-05,
      "loss": 1.0853,
      "step": 147
    },
    {
      "epoch": 0.016511867905056758,
      "grad_norm": 1.182171106338501,
      "learning_rate": 1.3896569539033253e-05,
      "loss": 1.1379,
      "step": 148
    },
    {
      "epoch": 0.016623434580090926,
      "grad_norm": 1.328808307647705,
      "learning_rate": 1.3399017115446067e-05,
      "loss": 1.0739,
      "step": 149
    },
    {
      "epoch": 0.016735001255125094,
      "grad_norm": 1.5698626041412354,
      "learning_rate": 1.2908737134970367e-05,
      "loss": 1.1242,
      "step": 150
    },
    {
      "epoch": 0.016735001255125094,
      "eval_loss": 1.1231499910354614,
      "eval_runtime": 1182.7105,
      "eval_samples_per_second": 12.765,
      "eval_steps_per_second": 3.192,
      "step": 150
    },
    {
      "epoch": 0.016846567930159262,
      "grad_norm": 1.347996711730957,
      "learning_rate": 1.242586363525737e-05,
      "loss": 1.6669,
      "step": 151
    },
    {
      "epoch": 0.01695813460519343,
      "grad_norm": 0.7223047018051147,
      "learning_rate": 1.1950528629100457e-05,
      "loss": 1.4154,
      "step": 152
    },
    {
      "epoch": 0.017069701280227598,
      "grad_norm": 0.7790156006813049,
      "learning_rate": 1.1482862068344121e-05,
      "loss": 1.3367,
      "step": 153
    },
    {
      "epoch": 0.017181267955261762,
      "grad_norm": 0.7638139128684998,
      "learning_rate": 1.1022991808356442e-05,
      "loss": 1.0699,
      "step": 154
    },
    {
      "epoch": 0.01729283463029593,
      "grad_norm": 0.8289293646812439,
      "learning_rate": 1.0571043573074737e-05,
      "loss": 1.2266,
      "step": 155
    },
    {
      "epoch": 0.017404401305330098,
      "grad_norm": 0.8301885724067688,
      "learning_rate": 1.0127140920633857e-05,
      "loss": 1.3556,
      "step": 156
    },
    {
      "epoch": 0.017515967980364266,
      "grad_norm": 0.7769188284873962,
      "learning_rate": 9.69140520958662e-06,
      "loss": 1.3362,
      "step": 157
    },
    {
      "epoch": 0.017627534655398434,
      "grad_norm": 0.8720978498458862,
      "learning_rate": 9.263955565725648e-06,
      "loss": 1.0811,
      "step": 158
    },
    {
      "epoch": 0.017739101330432598,
      "grad_norm": 0.7598316073417664,
      "learning_rate": 8.844908849515509e-06,
      "loss": 1.0352,
      "step": 159
    },
    {
      "epoch": 0.017850668005466766,
      "grad_norm": 0.7994357347488403,
      "learning_rate": 8.434379624144261e-06,
      "loss": 1.1984,
      "step": 160
    },
    {
      "epoch": 0.017962234680500934,
      "grad_norm": 0.841153621673584,
      "learning_rate": 8.032480124203013e-06,
      "loss": 1.2358,
      "step": 161
    },
    {
      "epoch": 0.018073801355535102,
      "grad_norm": 0.8118249773979187,
      "learning_rate": 7.639320225002106e-06,
      "loss": 1.0032,
      "step": 162
    },
    {
      "epoch": 0.01818536803056927,
      "grad_norm": 0.753839373588562,
      "learning_rate": 7.255007412532307e-06,
      "loss": 1.1015,
      "step": 163
    },
    {
      "epoch": 0.018296934705603438,
      "grad_norm": 0.7360984086990356,
      "learning_rate": 6.8796467540791986e-06,
      "loss": 1.1351,
      "step": 164
    },
    {
      "epoch": 0.018408501380637602,
      "grad_norm": 0.8430283069610596,
      "learning_rate": 6.513340869498859e-06,
      "loss": 1.1797,
      "step": 165
    },
    {
      "epoch": 0.01852006805567177,
      "grad_norm": 0.7918187975883484,
      "learning_rate": 6.1561899031625794e-06,
      "loss": 1.2193,
      "step": 166
    },
    {
      "epoch": 0.018631634730705938,
      "grad_norm": 0.7992611527442932,
      "learning_rate": 5.808291496578435e-06,
      "loss": 1.268,
      "step": 167
    },
    {
      "epoch": 0.018743201405740106,
      "grad_norm": 0.7855931520462036,
      "learning_rate": 5.469740761697044e-06,
      "loss": 1.178,
      "step": 168
    },
    {
      "epoch": 0.018854768080774274,
      "grad_norm": 0.8650913834571838,
      "learning_rate": 5.140630254908905e-06,
      "loss": 1.2404,
      "step": 169
    },
    {
      "epoch": 0.01896633475580844,
      "grad_norm": 0.8121924996376038,
      "learning_rate": 4.821049951740442e-06,
      "loss": 1.1776,
      "step": 170
    },
    {
      "epoch": 0.019077901430842606,
      "grad_norm": 0.7831167578697205,
      "learning_rate": 4.511087222255528e-06,
      "loss": 1.2594,
      "step": 171
    },
    {
      "epoch": 0.019189468105876774,
      "grad_norm": 0.8442049026489258,
      "learning_rate": 4.2108268071694616e-06,
      "loss": 0.9845,
      "step": 172
    },
    {
      "epoch": 0.01930103478091094,
      "grad_norm": 0.9648184180259705,
      "learning_rate": 3.9203507946816445e-06,
      "loss": 1.1247,
      "step": 173
    },
    {
      "epoch": 0.01941260145594511,
      "grad_norm": 0.814885139465332,
      "learning_rate": 3.6397385980335e-06,
      "loss": 1.3107,
      "step": 174
    },
    {
      "epoch": 0.019524168130979278,
      "grad_norm": 0.8654019236564636,
      "learning_rate": 3.3690669337977e-06,
      "loss": 1.2594,
      "step": 175
    },
    {
      "epoch": 0.019635734806013445,
      "grad_norm": 0.9481486678123474,
      "learning_rate": 3.1084098009046106e-06,
      "loss": 1.1462,
      "step": 176
    },
    {
      "epoch": 0.01974730148104761,
      "grad_norm": 0.7980362772941589,
      "learning_rate": 2.8578384604117217e-06,
      "loss": 1.117,
      "step": 177
    },
    {
      "epoch": 0.019858868156081778,
      "grad_norm": 0.8693552613258362,
      "learning_rate": 2.6174214160215704e-06,
      "loss": 1.1145,
      "step": 178
    },
    {
      "epoch": 0.019970434831115946,
      "grad_norm": 0.8843334317207336,
      "learning_rate": 2.3872243953535535e-06,
      "loss": 1.0491,
      "step": 179
    },
    {
      "epoch": 0.020082001506150114,
      "grad_norm": 0.8390738368034363,
      "learning_rate": 2.1673103319746146e-06,
      "loss": 0.9996,
      "step": 180
    },
    {
      "epoch": 0.02019356818118428,
      "grad_norm": 0.9163740873336792,
      "learning_rate": 1.957739348193859e-06,
      "loss": 1.198,
      "step": 181
    },
    {
      "epoch": 0.020305134856218446,
      "grad_norm": 0.8822169899940491,
      "learning_rate": 1.7585687386256944e-06,
      "loss": 1.0289,
      "step": 182
    },
    {
      "epoch": 0.020416701531252614,
      "grad_norm": 0.8542013168334961,
      "learning_rate": 1.5698529545260744e-06,
      "loss": 0.9726,
      "step": 183
    },
    {
      "epoch": 0.02052826820628678,
      "grad_norm": 0.9263859987258911,
      "learning_rate": 1.3916435889060575e-06,
      "loss": 1.1067,
      "step": 184
    },
    {
      "epoch": 0.02063983488132095,
      "grad_norm": 0.9441400170326233,
      "learning_rate": 1.2239893624267852e-06,
      "loss": 1.1066,
      "step": 185
    },
    {
      "epoch": 0.020751401556355117,
      "grad_norm": 0.9362796545028687,
      "learning_rate": 1.0669361100797704e-06,
      "loss": 1.0002,
      "step": 186
    },
    {
      "epoch": 0.020862968231389285,
      "grad_norm": 0.9713947772979736,
      "learning_rate": 9.205267686560293e-07,
      "loss": 1.1045,
      "step": 187
    },
    {
      "epoch": 0.02097453490642345,
      "grad_norm": 0.9421945214271545,
      "learning_rate": 7.848013650076258e-07,
      "loss": 1.094,
      "step": 188
    },
    {
      "epoch": 0.021086101581457618,
      "grad_norm": 0.9486850500106812,
      "learning_rate": 6.597970051047053e-07,
      "loss": 1.0785,
      "step": 189
    },
    {
      "epoch": 0.021197668256491786,
      "grad_norm": 1.1238409280776978,
      "learning_rate": 5.455478638911071e-07,
      "loss": 1.1079,
      "step": 190
    },
    {
      "epoch": 0.021309234931525953,
      "grad_norm": 1.0330231189727783,
      "learning_rate": 4.420851759412603e-07,
      "loss": 0.9687,
      "step": 191
    },
    {
      "epoch": 0.02142080160656012,
      "grad_norm": 1.064351201057434,
      "learning_rate": 3.4943722692099224e-07,
      "loss": 1.0296,
      "step": 192
    },
    {
      "epoch": 0.02153236828159429,
      "grad_norm": 1.0056447982788086,
      "learning_rate": 2.676293458544743e-07,
      "loss": 0.9839,
      "step": 193
    },
    {
      "epoch": 0.021643934956628454,
      "grad_norm": 1.1110754013061523,
      "learning_rate": 1.9668389819954338e-07,
      "loss": 0.9976,
      "step": 194
    },
    {
      "epoch": 0.02175550163166262,
      "grad_norm": 1.2064679861068726,
      "learning_rate": 1.3662027973320614e-07,
      "loss": 1.1326,
      "step": 195
    },
    {
      "epoch": 0.02186706830669679,
      "grad_norm": 1.1165443658828735,
      "learning_rate": 8.745491124901861e-08,
      "loss": 0.9374,
      "step": 196
    },
    {
      "epoch": 0.021978634981730957,
      "grad_norm": 1.0634437799453735,
      "learning_rate": 4.920123406781052e-08,
      "loss": 0.979,
      "step": 197
    },
    {
      "epoch": 0.022090201656765125,
      "grad_norm": 1.4238533973693848,
      "learning_rate": 2.1869706362958044e-08,
      "loss": 1.0523,
      "step": 198
    },
    {
      "epoch": 0.022201768331799293,
      "grad_norm": 1.357772707939148,
      "learning_rate": 5.467800301239834e-09,
      "loss": 1.0345,
      "step": 199
    },
    {
      "epoch": 0.022313335006833458,
      "grad_norm": 1.6248823404312134,
      "learning_rate": 0.0,
      "loss": 0.9803,
      "step": 200
    },
    {
      "epoch": 0.022313335006833458,
      "eval_loss": 1.1155003309249878,
      "eval_runtime": 1183.9514,
      "eval_samples_per_second": 12.751,
      "eval_steps_per_second": 3.188,
      "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": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.08868155248214e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}