{
  "best_metric": 0.3114449679851532,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.0506906602458497,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002534533012292485,
      "grad_norm": 0.5637602210044861,
      "learning_rate": 7e-06,
      "loss": 0.7307,
      "step": 1
    },
    {
      "epoch": 0.0002534533012292485,
      "eval_loss": 0.9512640833854675,
      "eval_runtime": 532.1115,
      "eval_samples_per_second": 12.49,
      "eval_steps_per_second": 3.123,
      "step": 1
    },
    {
      "epoch": 0.000506906602458497,
      "grad_norm": 0.6604697704315186,
      "learning_rate": 1.4e-05,
      "loss": 0.6945,
      "step": 2
    },
    {
      "epoch": 0.0007603599036877456,
      "grad_norm": 0.7113285660743713,
      "learning_rate": 2.1e-05,
      "loss": 0.6647,
      "step": 3
    },
    {
      "epoch": 0.001013813204916994,
      "grad_norm": 0.5982671976089478,
      "learning_rate": 2.8e-05,
      "loss": 0.7014,
      "step": 4
    },
    {
      "epoch": 0.0012672665061462425,
      "grad_norm": 0.6680089235305786,
      "learning_rate": 3.5e-05,
      "loss": 0.6862,
      "step": 5
    },
    {
      "epoch": 0.0015207198073754911,
      "grad_norm": 0.693647027015686,
      "learning_rate": 4.2e-05,
      "loss": 0.6805,
      "step": 6
    },
    {
      "epoch": 0.0017741731086047396,
      "grad_norm": 0.6376394033432007,
      "learning_rate": 4.899999999999999e-05,
      "loss": 0.6006,
      "step": 7
    },
    {
      "epoch": 0.002027626409833988,
      "grad_norm": 0.6353195905685425,
      "learning_rate": 5.6e-05,
      "loss": 0.6495,
      "step": 8
    },
    {
      "epoch": 0.0022810797110632366,
      "grad_norm": 0.5442299842834473,
      "learning_rate": 6.3e-05,
      "loss": 0.5904,
      "step": 9
    },
    {
      "epoch": 0.002534533012292485,
      "grad_norm": 0.5597531795501709,
      "learning_rate": 7e-05,
      "loss": 0.6404,
      "step": 10
    },
    {
      "epoch": 0.0027879863135217334,
      "grad_norm": 0.5673569440841675,
      "learning_rate": 6.999521567473641e-05,
      "loss": 0.5773,
      "step": 11
    },
    {
      "epoch": 0.0030414396147509823,
      "grad_norm": 0.5594638586044312,
      "learning_rate": 6.998086400693241e-05,
      "loss": 0.5848,
      "step": 12
    },
    {
      "epoch": 0.0032948929159802307,
      "grad_norm": 0.5175847411155701,
      "learning_rate": 6.995694892019065e-05,
      "loss": 0.5737,
      "step": 13
    },
    {
      "epoch": 0.003548346217209479,
      "grad_norm": 0.5732212662696838,
      "learning_rate": 6.99234769526571e-05,
      "loss": 0.4932,
      "step": 14
    },
    {
      "epoch": 0.0038017995184387275,
      "grad_norm": 0.6050289869308472,
      "learning_rate": 6.988045725523343e-05,
      "loss": 0.4876,
      "step": 15
    },
    {
      "epoch": 0.004055252819667976,
      "grad_norm": 0.6290268898010254,
      "learning_rate": 6.982790158907539e-05,
      "loss": 0.4673,
      "step": 16
    },
    {
      "epoch": 0.004308706120897224,
      "grad_norm": 0.8223831653594971,
      "learning_rate": 6.976582432237733e-05,
      "loss": 0.4756,
      "step": 17
    },
    {
      "epoch": 0.004562159422126473,
      "grad_norm": 0.633542537689209,
      "learning_rate": 6.969424242644413e-05,
      "loss": 0.4682,
      "step": 18
    },
    {
      "epoch": 0.004815612723355722,
      "grad_norm": 0.6778817772865295,
      "learning_rate": 6.961317547105138e-05,
      "loss": 0.4258,
      "step": 19
    },
    {
      "epoch": 0.00506906602458497,
      "grad_norm": 0.7767919898033142,
      "learning_rate": 6.952264561909527e-05,
      "loss": 0.4529,
      "step": 20
    },
    {
      "epoch": 0.005322519325814219,
      "grad_norm": 0.7921961545944214,
      "learning_rate": 6.942267762053337e-05,
      "loss": 0.4602,
      "step": 21
    },
    {
      "epoch": 0.005575972627043467,
      "grad_norm": 0.6767591834068298,
      "learning_rate": 6.931329880561832e-05,
      "loss": 0.3301,
      "step": 22
    },
    {
      "epoch": 0.005829425928272716,
      "grad_norm": 0.7602695226669312,
      "learning_rate": 6.919453907742597e-05,
      "loss": 0.3753,
      "step": 23
    },
    {
      "epoch": 0.0060828792295019645,
      "grad_norm": 1.0894685983657837,
      "learning_rate": 6.90664309036802e-05,
      "loss": 0.4138,
      "step": 24
    },
    {
      "epoch": 0.0063363325307312125,
      "grad_norm": 0.7795313596725464,
      "learning_rate": 6.892900930787656e-05,
      "loss": 0.3878,
      "step": 25
    },
    {
      "epoch": 0.006589785831960461,
      "grad_norm": 0.797916829586029,
      "learning_rate": 6.87823118597072e-05,
      "loss": 0.4445,
      "step": 26
    },
    {
      "epoch": 0.00684323913318971,
      "grad_norm": 0.8681225776672363,
      "learning_rate": 6.862637866478969e-05,
      "loss": 0.3423,
      "step": 27
    },
    {
      "epoch": 0.007096692434418958,
      "grad_norm": 0.7283143401145935,
      "learning_rate": 6.846125235370252e-05,
      "loss": 0.3813,
      "step": 28
    },
    {
      "epoch": 0.007350145735648207,
      "grad_norm": 0.6523985266685486,
      "learning_rate": 6.828697807033038e-05,
      "loss": 0.3282,
      "step": 29
    },
    {
      "epoch": 0.007603599036877455,
      "grad_norm": 0.7353911399841309,
      "learning_rate": 6.81036034595222e-05,
      "loss": 0.291,
      "step": 30
    },
    {
      "epoch": 0.007857052338106704,
      "grad_norm": 0.9172014594078064,
      "learning_rate": 6.791117865406564e-05,
      "loss": 0.3509,
      "step": 31
    },
    {
      "epoch": 0.008110505639335953,
      "grad_norm": 0.9462753534317017,
      "learning_rate": 6.770975626098112e-05,
      "loss": 0.4434,
      "step": 32
    },
    {
      "epoch": 0.008363958940565202,
      "grad_norm": 1.9650354385375977,
      "learning_rate": 6.749939134713974e-05,
      "loss": 0.3918,
      "step": 33
    },
    {
      "epoch": 0.008617412241794449,
      "grad_norm": 0.9554181694984436,
      "learning_rate": 6.728014142420846e-05,
      "loss": 0.3665,
      "step": 34
    },
    {
      "epoch": 0.008870865543023698,
      "grad_norm": 1.0999562740325928,
      "learning_rate": 6.7052066432927e-05,
      "loss": 0.3027,
      "step": 35
    },
    {
      "epoch": 0.009124318844252946,
      "grad_norm": 0.9678001999855042,
      "learning_rate": 6.681522872672069e-05,
      "loss": 0.4272,
      "step": 36
    },
    {
      "epoch": 0.009377772145482195,
      "grad_norm": 3.732379913330078,
      "learning_rate": 6.656969305465356e-05,
      "loss": 0.3871,
      "step": 37
    },
    {
      "epoch": 0.009631225446711444,
      "grad_norm": 1.7614824771881104,
      "learning_rate": 6.631552654372672e-05,
      "loss": 0.4311,
      "step": 38
    },
    {
      "epoch": 0.009884678747940691,
      "grad_norm": 0.8726099133491516,
      "learning_rate": 6.60527986805264e-05,
      "loss": 0.3094,
      "step": 39
    },
    {
      "epoch": 0.01013813204916994,
      "grad_norm": 0.9563500881195068,
      "learning_rate": 6.578158129222711e-05,
      "loss": 0.3162,
      "step": 40
    },
    {
      "epoch": 0.010391585350399189,
      "grad_norm": 0.8088050484657288,
      "learning_rate": 6.550194852695469e-05,
      "loss": 0.3227,
      "step": 41
    },
    {
      "epoch": 0.010645038651628438,
      "grad_norm": 0.749538004398346,
      "learning_rate": 6.521397683351509e-05,
      "loss": 0.3582,
      "step": 42
    },
    {
      "epoch": 0.010898491952857687,
      "grad_norm": 0.8230732679367065,
      "learning_rate": 6.491774494049386e-05,
      "loss": 0.3914,
      "step": 43
    },
    {
      "epoch": 0.011151945254086934,
      "grad_norm": 0.6536163687705994,
      "learning_rate": 6.461333383473272e-05,
      "loss": 0.2768,
      "step": 44
    },
    {
      "epoch": 0.011405398555316183,
      "grad_norm": 0.8638445138931274,
      "learning_rate": 6.430082673918849e-05,
      "loss": 0.4332,
      "step": 45
    },
    {
      "epoch": 0.011658851856545431,
      "grad_norm": 1.0308754444122314,
      "learning_rate": 6.398030909018069e-05,
      "loss": 0.2682,
      "step": 46
    },
    {
      "epoch": 0.01191230515777468,
      "grad_norm": 0.7687364816665649,
      "learning_rate": 6.365186851403423e-05,
      "loss": 0.341,
      "step": 47
    },
    {
      "epoch": 0.012165758459003929,
      "grad_norm": 0.7668923139572144,
      "learning_rate": 6.331559480312315e-05,
      "loss": 0.3038,
      "step": 48
    },
    {
      "epoch": 0.012419211760233176,
      "grad_norm": 1.1220157146453857,
      "learning_rate": 6.297157989132236e-05,
      "loss": 0.3223,
      "step": 49
    },
    {
      "epoch": 0.012672665061462425,
      "grad_norm": 1.1568130254745483,
      "learning_rate": 6.261991782887377e-05,
      "loss": 0.442,
      "step": 50
    },
    {
      "epoch": 0.012672665061462425,
      "eval_loss": 0.3776959776878357,
      "eval_runtime": 534.8367,
      "eval_samples_per_second": 12.426,
      "eval_steps_per_second": 3.107,
      "step": 50
    },
    {
      "epoch": 0.012926118362691674,
      "grad_norm": 0.4836099445819855,
      "learning_rate": 6.226070475667393e-05,
      "loss": 0.5211,
      "step": 51
    },
    {
      "epoch": 0.013179571663920923,
      "grad_norm": 0.4805043935775757,
      "learning_rate": 6.189403887999006e-05,
      "loss": 0.4534,
      "step": 52
    },
    {
      "epoch": 0.013433024965150172,
      "grad_norm": 0.6214394569396973,
      "learning_rate": 6.152002044161171e-05,
      "loss": 0.4429,
      "step": 53
    },
    {
      "epoch": 0.01368647826637942,
      "grad_norm": 0.6329332590103149,
      "learning_rate": 6.113875169444539e-05,
      "loss": 0.4009,
      "step": 54
    },
    {
      "epoch": 0.013939931567608668,
      "grad_norm": 0.49672988057136536,
      "learning_rate": 6.0750336873559605e-05,
      "loss": 0.4263,
      "step": 55
    },
    {
      "epoch": 0.014193384868837916,
      "grad_norm": 0.4916054606437683,
      "learning_rate": 6.035488216768811e-05,
      "loss": 0.3832,
      "step": 56
    },
    {
      "epoch": 0.014446838170067165,
      "grad_norm": 0.6797816753387451,
      "learning_rate": 5.9952495690198894e-05,
      "loss": 0.4623,
      "step": 57
    },
    {
      "epoch": 0.014700291471296414,
      "grad_norm": 0.4841528534889221,
      "learning_rate": 5.954328744953709e-05,
      "loss": 0.3384,
      "step": 58
    },
    {
      "epoch": 0.014953744772525663,
      "grad_norm": 0.49140116572380066,
      "learning_rate": 5.91273693191498e-05,
      "loss": 0.3551,
      "step": 59
    },
    {
      "epoch": 0.01520719807375491,
      "grad_norm": 0.39423346519470215,
      "learning_rate": 5.870485500690094e-05,
      "loss": 0.4004,
      "step": 60
    },
    {
      "epoch": 0.015460651374984159,
      "grad_norm": 0.5048249959945679,
      "learning_rate": 5.827586002398468e-05,
      "loss": 0.3857,
      "step": 61
    },
    {
      "epoch": 0.015714104676213408,
      "grad_norm": 0.36948123574256897,
      "learning_rate": 5.784050165334589e-05,
      "loss": 0.3812,
      "step": 62
    },
    {
      "epoch": 0.015967557977442655,
      "grad_norm": 0.3576664626598358,
      "learning_rate": 5.739889891761608e-05,
      "loss": 0.2966,
      "step": 63
    },
    {
      "epoch": 0.016221011278671905,
      "grad_norm": 0.79672771692276,
      "learning_rate": 5.6951172546573794e-05,
      "loss": 0.3761,
      "step": 64
    },
    {
      "epoch": 0.016474464579901153,
      "grad_norm": 0.521947979927063,
      "learning_rate": 5.6497444944138376e-05,
      "loss": 0.3655,
      "step": 65
    },
    {
      "epoch": 0.016727917881130403,
      "grad_norm": 0.5354653000831604,
      "learning_rate": 5.603784015490587e-05,
      "loss": 0.4187,
      "step": 66
    },
    {
      "epoch": 0.01698137118235965,
      "grad_norm": 0.5953655242919922,
      "learning_rate": 5.557248383023655e-05,
      "loss": 0.3345,
      "step": 67
    },
    {
      "epoch": 0.017234824483588897,
      "grad_norm": 0.5908196568489075,
      "learning_rate": 5.510150319390302e-05,
      "loss": 0.3566,
      "step": 68
    },
    {
      "epoch": 0.017488277784818148,
      "grad_norm": 0.5005892515182495,
      "learning_rate": 5.4625027007308546e-05,
      "loss": 0.354,
      "step": 69
    },
    {
      "epoch": 0.017741731086047395,
      "grad_norm": 0.4641432762145996,
      "learning_rate": 5.414318553428494e-05,
      "loss": 0.2931,
      "step": 70
    },
    {
      "epoch": 0.017995184387276646,
      "grad_norm": 0.48989179730415344,
      "learning_rate": 5.3656110505479776e-05,
      "loss": 0.3001,
      "step": 71
    },
    {
      "epoch": 0.018248637688505893,
      "grad_norm": 0.525313138961792,
      "learning_rate": 5.316393508234253e-05,
      "loss": 0.3572,
      "step": 72
    },
    {
      "epoch": 0.01850209098973514,
      "grad_norm": 0.4779028594493866,
      "learning_rate": 5.266679382071953e-05,
      "loss": 0.2881,
      "step": 73
    },
    {
      "epoch": 0.01875554429096439,
      "grad_norm": 0.6258348822593689,
      "learning_rate": 5.216482263406778e-05,
      "loss": 0.3244,
      "step": 74
    },
    {
      "epoch": 0.019008997592193638,
      "grad_norm": 0.6550619006156921,
      "learning_rate": 5.1658158756297576e-05,
      "loss": 0.281,
      "step": 75
    },
    {
      "epoch": 0.019262450893422888,
      "grad_norm": 0.5427703857421875,
      "learning_rate": 5.114694070425407e-05,
      "loss": 0.303,
      "step": 76
    },
    {
      "epoch": 0.019515904194652135,
      "grad_norm": 0.6002343893051147,
      "learning_rate": 5.063130823984823e-05,
      "loss": 0.2908,
      "step": 77
    },
    {
      "epoch": 0.019769357495881382,
      "grad_norm": 0.9281688928604126,
      "learning_rate": 5.011140233184724e-05,
      "loss": 0.3231,
      "step": 78
    },
    {
      "epoch": 0.020022810797110633,
      "grad_norm": 0.8118467926979065,
      "learning_rate": 4.958736511733516e-05,
      "loss": 0.3601,
      "step": 79
    },
    {
      "epoch": 0.02027626409833988,
      "grad_norm": 0.5715822577476501,
      "learning_rate": 4.905933986285393e-05,
      "loss": 0.2867,
      "step": 80
    },
    {
      "epoch": 0.02052971739956913,
      "grad_norm": 0.9286966919898987,
      "learning_rate": 4.8527470925235824e-05,
      "loss": 0.3645,
      "step": 81
    },
    {
      "epoch": 0.020783170700798378,
      "grad_norm": 0.620093584060669,
      "learning_rate": 4.799190371213772e-05,
      "loss": 0.2954,
      "step": 82
    },
    {
      "epoch": 0.021036624002027625,
      "grad_norm": 0.6234807372093201,
      "learning_rate": 4.745278464228808e-05,
      "loss": 0.3298,
      "step": 83
    },
    {
      "epoch": 0.021290077303256875,
      "grad_norm": 0.8412039875984192,
      "learning_rate": 4.69102611054575e-05,
      "loss": 0.2926,
      "step": 84
    },
    {
      "epoch": 0.021543530604486123,
      "grad_norm": 0.703763484954834,
      "learning_rate": 4.6364481422163926e-05,
      "loss": 0.3051,
      "step": 85
    },
    {
      "epoch": 0.021796983905715373,
      "grad_norm": 0.6281498670578003,
      "learning_rate": 4.581559480312316e-05,
      "loss": 0.3129,
      "step": 86
    },
    {
      "epoch": 0.02205043720694462,
      "grad_norm": 0.590596616268158,
      "learning_rate": 4.526375130845627e-05,
      "loss": 0.2383,
      "step": 87
    },
    {
      "epoch": 0.022303890508173867,
      "grad_norm": 0.6789559125900269,
      "learning_rate": 4.4709101806664554e-05,
      "loss": 0.2878,
      "step": 88
    },
    {
      "epoch": 0.022557343809403118,
      "grad_norm": 0.5185131430625916,
      "learning_rate": 4.4151797933383685e-05,
      "loss": 0.2255,
      "step": 89
    },
    {
      "epoch": 0.022810797110632365,
      "grad_norm": 0.6621422171592712,
      "learning_rate": 4.359199204992797e-05,
      "loss": 0.3419,
      "step": 90
    },
    {
      "epoch": 0.023064250411861616,
      "grad_norm": 0.8429589867591858,
      "learning_rate": 4.30298372016363e-05,
      "loss": 0.3345,
      "step": 91
    },
    {
      "epoch": 0.023317703713090863,
      "grad_norm": 0.543500542640686,
      "learning_rate": 4.246548707603114e-05,
      "loss": 0.2236,
      "step": 92
    },
    {
      "epoch": 0.02357115701432011,
      "grad_norm": 0.6969960927963257,
      "learning_rate": 4.1899095960801805e-05,
      "loss": 0.28,
      "step": 93
    },
    {
      "epoch": 0.02382461031554936,
      "grad_norm": 0.8858791589736938,
      "learning_rate": 4.133081870162385e-05,
      "loss": 0.3377,
      "step": 94
    },
    {
      "epoch": 0.024078063616778608,
      "grad_norm": 0.7956605553627014,
      "learning_rate": 4.076081065982569e-05,
      "loss": 0.2852,
      "step": 95
    },
    {
      "epoch": 0.024331516918007858,
      "grad_norm": 0.8670409917831421,
      "learning_rate": 4.018922766991447e-05,
      "loss": 0.3319,
      "step": 96
    },
    {
      "epoch": 0.024584970219237105,
      "grad_norm": 0.8773281574249268,
      "learning_rate": 3.961622599697241e-05,
      "loss": 0.2355,
      "step": 97
    },
    {
      "epoch": 0.024838423520466352,
      "grad_norm": 0.641528844833374,
      "learning_rate": 3.9041962293935516e-05,
      "loss": 0.3297,
      "step": 98
    },
    {
      "epoch": 0.025091876821695603,
      "grad_norm": 0.7666037678718567,
      "learning_rate": 3.84665935587662e-05,
      "loss": 0.2192,
      "step": 99
    },
    {
      "epoch": 0.02534533012292485,
      "grad_norm": 1.073132872581482,
      "learning_rate": 3.7890277091531636e-05,
      "loss": 0.3292,
      "step": 100
    },
    {
      "epoch": 0.02534533012292485,
      "eval_loss": 0.33073779940605164,
      "eval_runtime": 535.0717,
      "eval_samples_per_second": 12.421,
      "eval_steps_per_second": 3.106,
      "step": 100
    },
    {
      "epoch": 0.0255987834241541,
      "grad_norm": 0.7879229187965393,
      "learning_rate": 3.7313170451399475e-05,
      "loss": 0.4689,
      "step": 101
    },
    {
      "epoch": 0.025852236725383348,
      "grad_norm": 0.349199116230011,
      "learning_rate": 3.673543141356278e-05,
      "loss": 0.426,
      "step": 102
    },
    {
      "epoch": 0.026105690026612595,
      "grad_norm": 0.3625866770744324,
      "learning_rate": 3.6157217926105783e-05,
      "loss": 0.4304,
      "step": 103
    },
    {
      "epoch": 0.026359143327841845,
      "grad_norm": 0.4031258821487427,
      "learning_rate": 3.557868806682255e-05,
      "loss": 0.4335,
      "step": 104
    },
    {
      "epoch": 0.026612596629071093,
      "grad_norm": 0.4257863461971283,
      "learning_rate": 3.5e-05,
      "loss": 0.3935,
      "step": 105
    },
    {
      "epoch": 0.026866049930300343,
      "grad_norm": 0.44811195135116577,
      "learning_rate": 3.442131193317745e-05,
      "loss": 0.3787,
      "step": 106
    },
    {
      "epoch": 0.02711950323152959,
      "grad_norm": 0.5182667374610901,
      "learning_rate": 3.384278207389421e-05,
      "loss": 0.3766,
      "step": 107
    },
    {
      "epoch": 0.02737295653275884,
      "grad_norm": 0.4968753457069397,
      "learning_rate": 3.3264568586437216e-05,
      "loss": 0.42,
      "step": 108
    },
    {
      "epoch": 0.027626409833988088,
      "grad_norm": 0.5043284296989441,
      "learning_rate": 3.268682954860052e-05,
      "loss": 0.3288,
      "step": 109
    },
    {
      "epoch": 0.027879863135217335,
      "grad_norm": 0.48617568612098694,
      "learning_rate": 3.210972290846837e-05,
      "loss": 0.3118,
      "step": 110
    },
    {
      "epoch": 0.028133316436446586,
      "grad_norm": 0.480871319770813,
      "learning_rate": 3.15334064412338e-05,
      "loss": 0.3519,
      "step": 111
    },
    {
      "epoch": 0.028386769737675833,
      "grad_norm": 0.6641278862953186,
      "learning_rate": 3.0958037706064485e-05,
      "loss": 0.3141,
      "step": 112
    },
    {
      "epoch": 0.028640223038905083,
      "grad_norm": 0.5058858394622803,
      "learning_rate": 3.038377400302758e-05,
      "loss": 0.3153,
      "step": 113
    },
    {
      "epoch": 0.02889367634013433,
      "grad_norm": 0.45486193895339966,
      "learning_rate": 2.9810772330085524e-05,
      "loss": 0.2909,
      "step": 114
    },
    {
      "epoch": 0.029147129641363578,
      "grad_norm": 0.48425379395484924,
      "learning_rate": 2.9239189340174306e-05,
      "loss": 0.2886,
      "step": 115
    },
    {
      "epoch": 0.029400582942592828,
      "grad_norm": 0.4817794859409332,
      "learning_rate": 2.8669181298376163e-05,
      "loss": 0.2781,
      "step": 116
    },
    {
      "epoch": 0.029654036243822075,
      "grad_norm": 0.6188409924507141,
      "learning_rate": 2.8100904039198193e-05,
      "loss": 0.3106,
      "step": 117
    },
    {
      "epoch": 0.029907489545051326,
      "grad_norm": 0.4940548837184906,
      "learning_rate": 2.7534512923968863e-05,
      "loss": 0.3322,
      "step": 118
    },
    {
      "epoch": 0.030160942846280573,
      "grad_norm": 0.506767988204956,
      "learning_rate": 2.6970162798363695e-05,
      "loss": 0.3107,
      "step": 119
    },
    {
      "epoch": 0.03041439614750982,
      "grad_norm": 0.545142650604248,
      "learning_rate": 2.640800795007203e-05,
      "loss": 0.2842,
      "step": 120
    },
    {
      "epoch": 0.03066784944873907,
      "grad_norm": 0.6052780151367188,
      "learning_rate": 2.5848202066616305e-05,
      "loss": 0.3137,
      "step": 121
    },
    {
      "epoch": 0.030921302749968318,
      "grad_norm": 0.5682511329650879,
      "learning_rate": 2.5290898193335446e-05,
      "loss": 0.2916,
      "step": 122
    },
    {
      "epoch": 0.03117475605119757,
      "grad_norm": 0.4890080988407135,
      "learning_rate": 2.4736248691543736e-05,
      "loss": 0.2588,
      "step": 123
    },
    {
      "epoch": 0.031428209352426816,
      "grad_norm": 0.5377240180969238,
      "learning_rate": 2.4184405196876842e-05,
      "loss": 0.245,
      "step": 124
    },
    {
      "epoch": 0.031681662653656066,
      "grad_norm": 0.7997578978538513,
      "learning_rate": 2.363551857783608e-05,
      "loss": 0.2851,
      "step": 125
    },
    {
      "epoch": 0.03193511595488531,
      "grad_norm": 0.5697923302650452,
      "learning_rate": 2.308973889454249e-05,
      "loss": 0.3223,
      "step": 126
    },
    {
      "epoch": 0.03218856925611456,
      "grad_norm": 0.5995197296142578,
      "learning_rate": 2.2547215357711918e-05,
      "loss": 0.2729,
      "step": 127
    },
    {
      "epoch": 0.03244202255734381,
      "grad_norm": 0.5520817041397095,
      "learning_rate": 2.2008096287862266e-05,
      "loss": 0.3105,
      "step": 128
    },
    {
      "epoch": 0.032695475858573055,
      "grad_norm": 0.5432480573654175,
      "learning_rate": 2.1472529074764177e-05,
      "loss": 0.3281,
      "step": 129
    },
    {
      "epoch": 0.032948929159802305,
      "grad_norm": 0.6505929827690125,
      "learning_rate": 2.0940660137146074e-05,
      "loss": 0.3874,
      "step": 130
    },
    {
      "epoch": 0.033202382461031556,
      "grad_norm": 0.689994215965271,
      "learning_rate": 2.041263488266484e-05,
      "loss": 0.3136,
      "step": 131
    },
    {
      "epoch": 0.033455835762260806,
      "grad_norm": 8.160080909729004,
      "learning_rate": 1.988859766815275e-05,
      "loss": 0.3555,
      "step": 132
    },
    {
      "epoch": 0.03370928906349005,
      "grad_norm": 0.6300246715545654,
      "learning_rate": 1.9368691760151773e-05,
      "loss": 0.2766,
      "step": 133
    },
    {
      "epoch": 0.0339627423647193,
      "grad_norm": 0.5888091325759888,
      "learning_rate": 1.885305929574593e-05,
      "loss": 0.2724,
      "step": 134
    },
    {
      "epoch": 0.03421619566594855,
      "grad_norm": 0.7288299798965454,
      "learning_rate": 1.8341841243702424e-05,
      "loss": 0.3592,
      "step": 135
    },
    {
      "epoch": 0.034469648967177795,
      "grad_norm": 0.9315939545631409,
      "learning_rate": 1.7835177365932225e-05,
      "loss": 0.4391,
      "step": 136
    },
    {
      "epoch": 0.034723102268407045,
      "grad_norm": 0.9517157673835754,
      "learning_rate": 1.7333206179280478e-05,
      "loss": 0.2577,
      "step": 137
    },
    {
      "epoch": 0.034976555569636296,
      "grad_norm": 0.5201305747032166,
      "learning_rate": 1.6836064917657478e-05,
      "loss": 0.2471,
      "step": 138
    },
    {
      "epoch": 0.03523000887086554,
      "grad_norm": 0.7326086163520813,
      "learning_rate": 1.6343889494520224e-05,
      "loss": 0.3126,
      "step": 139
    },
    {
      "epoch": 0.03548346217209479,
      "grad_norm": 0.6664350628852844,
      "learning_rate": 1.5856814465715064e-05,
      "loss": 0.2755,
      "step": 140
    },
    {
      "epoch": 0.03573691547332404,
      "grad_norm": 0.6586111187934875,
      "learning_rate": 1.5374972992691458e-05,
      "loss": 0.2913,
      "step": 141
    },
    {
      "epoch": 0.03599036877455329,
      "grad_norm": 0.5519941449165344,
      "learning_rate": 1.4898496806096974e-05,
      "loss": 0.2339,
      "step": 142
    },
    {
      "epoch": 0.036243822075782535,
      "grad_norm": 0.6732093095779419,
      "learning_rate": 1.4427516169763444e-05,
      "loss": 0.3004,
      "step": 143
    },
    {
      "epoch": 0.036497275377011786,
      "grad_norm": 0.671667754650116,
      "learning_rate": 1.396215984509412e-05,
      "loss": 0.3293,
      "step": 144
    },
    {
      "epoch": 0.036750728678241036,
      "grad_norm": 0.5071290135383606,
      "learning_rate": 1.3502555055861625e-05,
      "loss": 0.1972,
      "step": 145
    },
    {
      "epoch": 0.03700418197947028,
      "grad_norm": 0.8010750412940979,
      "learning_rate": 1.3048827453426203e-05,
      "loss": 0.3243,
      "step": 146
    },
    {
      "epoch": 0.03725763528069953,
      "grad_norm": 0.6564486026763916,
      "learning_rate": 1.2601101082383917e-05,
      "loss": 0.2197,
      "step": 147
    },
    {
      "epoch": 0.03751108858192878,
      "grad_norm": 0.9637052416801453,
      "learning_rate": 1.2159498346654094e-05,
      "loss": 0.2946,
      "step": 148
    },
    {
      "epoch": 0.03776454188315803,
      "grad_norm": 0.7391737103462219,
      "learning_rate": 1.1724139976015306e-05,
      "loss": 0.2606,
      "step": 149
    },
    {
      "epoch": 0.038017995184387275,
      "grad_norm": 0.9585252404212952,
      "learning_rate": 1.1295144993099068e-05,
      "loss": 0.2699,
      "step": 150
    },
    {
      "epoch": 0.038017995184387275,
      "eval_loss": 0.3155807852745056,
      "eval_runtime": 535.2039,
      "eval_samples_per_second": 12.418,
      "eval_steps_per_second": 3.105,
      "step": 150
    },
    {
      "epoch": 0.038271448485616526,
      "grad_norm": 0.36455297470092773,
      "learning_rate": 1.0872630680850196e-05,
      "loss": 0.4006,
      "step": 151
    },
    {
      "epoch": 0.038524901786845776,
      "grad_norm": 0.31821301579475403,
      "learning_rate": 1.0456712550462898e-05,
      "loss": 0.3745,
      "step": 152
    },
    {
      "epoch": 0.03877835508807502,
      "grad_norm": 0.3565686047077179,
      "learning_rate": 1.0047504309801104e-05,
      "loss": 0.3645,
      "step": 153
    },
    {
      "epoch": 0.03903180838930427,
      "grad_norm": 0.3877963721752167,
      "learning_rate": 9.645117832311886e-06,
      "loss": 0.4005,
      "step": 154
    },
    {
      "epoch": 0.03928526169053352,
      "grad_norm": 0.40037497878074646,
      "learning_rate": 9.249663126440394e-06,
      "loss": 0.3768,
      "step": 155
    },
    {
      "epoch": 0.039538714991762765,
      "grad_norm": 0.4870663583278656,
      "learning_rate": 8.861248305554624e-06,
      "loss": 0.3838,
      "step": 156
    },
    {
      "epoch": 0.039792168292992015,
      "grad_norm": 0.37471503019332886,
      "learning_rate": 8.47997955838829e-06,
      "loss": 0.261,
      "step": 157
    },
    {
      "epoch": 0.040045621594221266,
      "grad_norm": 0.37314358353614807,
      "learning_rate": 8.10596112000994e-06,
      "loss": 0.3119,
      "step": 158
    },
    {
      "epoch": 0.040299074895450517,
      "grad_norm": 0.5217383503913879,
      "learning_rate": 7.739295243326067e-06,
      "loss": 0.3344,
      "step": 159
    },
    {
      "epoch": 0.04055252819667976,
      "grad_norm": 0.3944564461708069,
      "learning_rate": 7.380082171126228e-06,
      "loss": 0.316,
      "step": 160
    },
    {
      "epoch": 0.04080598149790901,
      "grad_norm": 0.4504675567150116,
      "learning_rate": 7.028420108677635e-06,
      "loss": 0.3101,
      "step": 161
    },
    {
      "epoch": 0.04105943479913826,
      "grad_norm": 0.5876880288124084,
      "learning_rate": 6.684405196876842e-06,
      "loss": 0.3112,
      "step": 162
    },
    {
      "epoch": 0.041312888100367505,
      "grad_norm": 0.39890074729919434,
      "learning_rate": 6.3481314859657675e-06,
      "loss": 0.2746,
      "step": 163
    },
    {
      "epoch": 0.041566341401596756,
      "grad_norm": 0.3916687071323395,
      "learning_rate": 6.019690909819298e-06,
      "loss": 0.3408,
      "step": 164
    },
    {
      "epoch": 0.041819794702826006,
      "grad_norm": 0.41850560903549194,
      "learning_rate": 5.6991732608115e-06,
      "loss": 0.3479,
      "step": 165
    },
    {
      "epoch": 0.04207324800405525,
      "grad_norm": 0.5424418449401855,
      "learning_rate": 5.386666165267256e-06,
      "loss": 0.3619,
      "step": 166
    },
    {
      "epoch": 0.0423267013052845,
      "grad_norm": 0.4991215765476227,
      "learning_rate": 5.08225505950613e-06,
      "loss": 0.3204,
      "step": 167
    },
    {
      "epoch": 0.04258015460651375,
      "grad_norm": 0.5841875672340393,
      "learning_rate": 4.786023166484913e-06,
      "loss": 0.3074,
      "step": 168
    },
    {
      "epoch": 0.042833607907743,
      "grad_norm": 0.4832156002521515,
      "learning_rate": 4.498051473045291e-06,
      "loss": 0.4109,
      "step": 169
    },
    {
      "epoch": 0.043087061208972245,
      "grad_norm": 0.41757968068122864,
      "learning_rate": 4.218418707772886e-06,
      "loss": 0.2469,
      "step": 170
    },
    {
      "epoch": 0.043340514510201496,
      "grad_norm": 0.4750998020172119,
      "learning_rate": 3.947201319473587e-06,
      "loss": 0.2775,
      "step": 171
    },
    {
      "epoch": 0.043593967811430746,
      "grad_norm": 0.5711901783943176,
      "learning_rate": 3.684473456273278e-06,
      "loss": 0.2939,
      "step": 172
    },
    {
      "epoch": 0.04384742111265999,
      "grad_norm": 0.5536498427391052,
      "learning_rate": 3.4303069453464383e-06,
      "loss": 0.3898,
      "step": 173
    },
    {
      "epoch": 0.04410087441388924,
      "grad_norm": 0.6635736227035522,
      "learning_rate": 3.184771273279312e-06,
      "loss": 0.3395,
      "step": 174
    },
    {
      "epoch": 0.04435432771511849,
      "grad_norm": 0.45959383249282837,
      "learning_rate": 2.947933567072987e-06,
      "loss": 0.3143,
      "step": 175
    },
    {
      "epoch": 0.044607781016347735,
      "grad_norm": 0.5077531933784485,
      "learning_rate": 2.719858575791534e-06,
      "loss": 0.2469,
      "step": 176
    },
    {
      "epoch": 0.044861234317576985,
      "grad_norm": 0.5000652074813843,
      "learning_rate": 2.500608652860256e-06,
      "loss": 0.3236,
      "step": 177
    },
    {
      "epoch": 0.045114687618806236,
      "grad_norm": 0.528018057346344,
      "learning_rate": 2.2902437390188737e-06,
      "loss": 0.3417,
      "step": 178
    },
    {
      "epoch": 0.04536814092003549,
      "grad_norm": 0.5613098740577698,
      "learning_rate": 2.0888213459343587e-06,
      "loss": 0.3168,
      "step": 179
    },
    {
      "epoch": 0.04562159422126473,
      "grad_norm": 0.48844948410987854,
      "learning_rate": 1.8963965404777875e-06,
      "loss": 0.272,
      "step": 180
    },
    {
      "epoch": 0.04587504752249398,
      "grad_norm": 0.6144419312477112,
      "learning_rate": 1.7130219296696263e-06,
      "loss": 0.2605,
      "step": 181
    },
    {
      "epoch": 0.04612850082372323,
      "grad_norm": 0.5530086159706116,
      "learning_rate": 1.5387476462974824e-06,
      "loss": 0.3317,
      "step": 182
    },
    {
      "epoch": 0.046381954124952475,
      "grad_norm": 0.5514850616455078,
      "learning_rate": 1.3736213352103147e-06,
      "loss": 0.2773,
      "step": 183
    },
    {
      "epoch": 0.046635407426181726,
      "grad_norm": 0.6471708416938782,
      "learning_rate": 1.2176881402928002e-06,
      "loss": 0.3462,
      "step": 184
    },
    {
      "epoch": 0.046888860727410976,
      "grad_norm": 0.8579723238945007,
      "learning_rate": 1.0709906921234367e-06,
      "loss": 0.2975,
      "step": 185
    },
    {
      "epoch": 0.04714231402864022,
      "grad_norm": 0.7083173990249634,
      "learning_rate": 9.33569096319799e-07,
      "loss": 0.3132,
      "step": 186
    },
    {
      "epoch": 0.04739576732986947,
      "grad_norm": 0.6655422449111938,
      "learning_rate": 8.054609225740255e-07,
      "loss": 0.2419,
      "step": 187
    },
    {
      "epoch": 0.04764922063109872,
      "grad_norm": 0.896893322467804,
      "learning_rate": 6.867011943816724e-07,
      "loss": 0.3688,
      "step": 188
    },
    {
      "epoch": 0.04790267393232797,
      "grad_norm": 0.6923823952674866,
      "learning_rate": 5.77322379466617e-07,
      "loss": 0.3454,
      "step": 189
    },
    {
      "epoch": 0.048156127233557215,
      "grad_norm": 0.5786012411117554,
      "learning_rate": 4.773543809047186e-07,
      "loss": 0.2916,
      "step": 190
    },
    {
      "epoch": 0.048409580534786466,
      "grad_norm": 0.5328980684280396,
      "learning_rate": 3.868245289486027e-07,
      "loss": 0.264,
      "step": 191
    },
    {
      "epoch": 0.048663033836015716,
      "grad_norm": 0.4660666286945343,
      "learning_rate": 3.0575757355586817e-07,
      "loss": 0.2526,
      "step": 192
    },
    {
      "epoch": 0.04891648713724496,
      "grad_norm": 0.7175193428993225,
      "learning_rate": 2.3417567762266497e-07,
      "loss": 0.3126,
      "step": 193
    },
    {
      "epoch": 0.04916994043847421,
      "grad_norm": 0.6442475318908691,
      "learning_rate": 1.7209841092460043e-07,
      "loss": 0.2952,
      "step": 194
    },
    {
      "epoch": 0.04942339373970346,
      "grad_norm": 0.6591751575469971,
      "learning_rate": 1.1954274476655534e-07,
      "loss": 0.2414,
      "step": 195
    },
    {
      "epoch": 0.049676847040932705,
      "grad_norm": 0.8419310450553894,
      "learning_rate": 7.652304734289127e-08,
      "loss": 0.2862,
      "step": 196
    },
    {
      "epoch": 0.049930300342161955,
      "grad_norm": 0.6237998604774475,
      "learning_rate": 4.30510798093342e-08,
      "loss": 0.2748,
      "step": 197
    },
    {
      "epoch": 0.050183753643391206,
      "grad_norm": 0.8555868864059448,
      "learning_rate": 1.9135993067588284e-08,
      "loss": 0.2559,
      "step": 198
    },
    {
      "epoch": 0.05043720694462046,
      "grad_norm": 1.0285953283309937,
      "learning_rate": 4.784325263584854e-09,
      "loss": 0.2633,
      "step": 199
    },
    {
      "epoch": 0.0506906602458497,
      "grad_norm": 0.818027913570404,
      "learning_rate": 0.0,
      "loss": 0.2162,
      "step": 200
    },
    {
      "epoch": 0.0506906602458497,
      "eval_loss": 0.3114449679851532,
      "eval_runtime": 535.4173,
      "eval_samples_per_second": 12.413,
      "eval_steps_per_second": 3.104,
      "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": 1.9889466058683187e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}