{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99860529986053,
  "eval_steps": 45,
  "global_step": 358,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002789400278940028,
      "grad_norm": 2.008944315843832,
      "learning_rate": 0.0,
      "loss": 1.7653,
      "step": 1
    },
    {
      "epoch": 0.002789400278940028,
      "eval_loss": 1.7864996194839478,
      "eval_runtime": 155.6922,
      "eval_samples_per_second": 2.042,
      "eval_steps_per_second": 0.128,
      "step": 1
    },
    {
      "epoch": 0.005578800557880056,
      "grad_norm": 1.5986956798562522,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.3721,
      "step": 2
    },
    {
      "epoch": 0.008368200836820083,
      "grad_norm": 2.487093074085383,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.4468,
      "step": 3
    },
    {
      "epoch": 0.011157601115760111,
      "grad_norm": 1.9408908369837041,
      "learning_rate": 1.5e-06,
      "loss": 1.8555,
      "step": 4
    },
    {
      "epoch": 0.01394700139470014,
      "grad_norm": 1.855397723025267,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5173,
      "step": 5
    },
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 1.6798170163537172,
      "learning_rate": 2.5e-06,
      "loss": 1.3812,
      "step": 6
    },
    {
      "epoch": 0.019525801952580194,
      "grad_norm": 2.0478066370088133,
      "learning_rate": 3e-06,
      "loss": 1.475,
      "step": 7
    },
    {
      "epoch": 0.022315202231520222,
      "grad_norm": 1.6541684745930123,
      "learning_rate": 3.5e-06,
      "loss": 1.6239,
      "step": 8
    },
    {
      "epoch": 0.02510460251046025,
      "grad_norm": 1.5940373225900581,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4474,
      "step": 9
    },
    {
      "epoch": 0.02789400278940028,
      "grad_norm": 1.3436762031717087,
      "learning_rate": 4.5e-06,
      "loss": 1.5277,
      "step": 10
    },
    {
      "epoch": 0.030683403068340307,
      "grad_norm": 1.4820988105255548,
      "learning_rate": 5e-06,
      "loss": 1.3905,
      "step": 11
    },
    {
      "epoch": 0.03347280334728033,
      "grad_norm": 1.3026823080341792,
      "learning_rate": 5.500000000000001e-06,
      "loss": 1.2716,
      "step": 12
    },
    {
      "epoch": 0.03626220362622036,
      "grad_norm": 1.2786618249049673,
      "learning_rate": 6e-06,
      "loss": 1.4357,
      "step": 13
    },
    {
      "epoch": 0.03905160390516039,
      "grad_norm": 1.4401448629219828,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 1.5418,
      "step": 14
    },
    {
      "epoch": 0.04184100418410042,
      "grad_norm": 1.4108691585319235,
      "learning_rate": 7e-06,
      "loss": 1.419,
      "step": 15
    },
    {
      "epoch": 0.044630404463040445,
      "grad_norm": 1.434665713671276,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.4042,
      "step": 16
    },
    {
      "epoch": 0.04741980474198047,
      "grad_norm": 1.4864898541989087,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4338,
      "step": 17
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 1.7497952919365851,
      "learning_rate": 8.5e-06,
      "loss": 1.5988,
      "step": 18
    },
    {
      "epoch": 0.05299860529986053,
      "grad_norm": 1.5825124800137,
      "learning_rate": 9e-06,
      "loss": 1.4817,
      "step": 19
    },
    {
      "epoch": 0.05578800557880056,
      "grad_norm": 1.5639582937511203,
      "learning_rate": 9.5e-06,
      "loss": 1.3795,
      "step": 20
    },
    {
      "epoch": 0.058577405857740586,
      "grad_norm": 1.5512627729747626,
      "learning_rate": 1e-05,
      "loss": 1.4833,
      "step": 21
    },
    {
      "epoch": 0.061366806136680614,
      "grad_norm": 1.4462678614801439,
      "learning_rate": 1.0500000000000001e-05,
      "loss": 1.3781,
      "step": 22
    },
    {
      "epoch": 0.06415620641562064,
      "grad_norm": 1.5995776178618928,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.4862,
      "step": 23
    },
    {
      "epoch": 0.06694560669456066,
      "grad_norm": 1.2623925872690254,
      "learning_rate": 1.15e-05,
      "loss": 1.4222,
      "step": 24
    },
    {
      "epoch": 0.0697350069735007,
      "grad_norm": 1.2816346894508914,
      "learning_rate": 1.2e-05,
      "loss": 1.3473,
      "step": 25
    },
    {
      "epoch": 0.07252440725244072,
      "grad_norm": 1.4528035335148701,
      "learning_rate": 1.25e-05,
      "loss": 1.5278,
      "step": 26
    },
    {
      "epoch": 0.07531380753138076,
      "grad_norm": 1.3415339044507064,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.3939,
      "step": 27
    },
    {
      "epoch": 0.07810320781032078,
      "grad_norm": 1.6072610009319113,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 1.5401,
      "step": 28
    },
    {
      "epoch": 0.08089260808926081,
      "grad_norm": 1.5988215139386146,
      "learning_rate": 1.4e-05,
      "loss": 1.3995,
      "step": 29
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 1.4507828208303803,
      "learning_rate": 1.45e-05,
      "loss": 1.4584,
      "step": 30
    },
    {
      "epoch": 0.08647140864714087,
      "grad_norm": 1.4975002404633069,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.3834,
      "step": 31
    },
    {
      "epoch": 0.08926080892608089,
      "grad_norm": 1.4128570529331854,
      "learning_rate": 1.55e-05,
      "loss": 1.4216,
      "step": 32
    },
    {
      "epoch": 0.09205020920502092,
      "grad_norm": 1.3616495178863832,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.5167,
      "step": 33
    },
    {
      "epoch": 0.09483960948396095,
      "grad_norm": 1.1988790310990909,
      "learning_rate": 1.65e-05,
      "loss": 1.4525,
      "step": 34
    },
    {
      "epoch": 0.09762900976290098,
      "grad_norm": 1.4483022749153813,
      "learning_rate": 1.7e-05,
      "loss": 1.5741,
      "step": 35
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 1.394589777246842,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.6437,
      "step": 36
    },
    {
      "epoch": 0.10320781032078104,
      "grad_norm": 1.4186049044929165,
      "learning_rate": 1.8e-05,
      "loss": 1.5162,
      "step": 37
    },
    {
      "epoch": 0.10599721059972106,
      "grad_norm": 1.4241876007622027,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 1.2395,
      "step": 38
    },
    {
      "epoch": 0.1087866108786611,
      "grad_norm": 1.3743075911034852,
      "learning_rate": 1.9e-05,
      "loss": 1.4631,
      "step": 39
    },
    {
      "epoch": 0.11157601115760112,
      "grad_norm": 1.2863497247985725,
      "learning_rate": 1.95e-05,
      "loss": 1.3611,
      "step": 40
    },
    {
      "epoch": 0.11436541143654114,
      "grad_norm": 1.3054075793205129,
      "learning_rate": 2e-05,
      "loss": 1.2375,
      "step": 41
    },
    {
      "epoch": 0.11715481171548117,
      "grad_norm": 1.447249035073335,
      "learning_rate": 1.9999892011980525e-05,
      "loss": 1.4044,
      "step": 42
    },
    {
      "epoch": 0.1199442119944212,
      "grad_norm": 1.3461748028257197,
      "learning_rate": 1.9999568050254373e-05,
      "loss": 1.4081,
      "step": 43
    },
    {
      "epoch": 0.12273361227336123,
      "grad_norm": 1.6035229132022362,
      "learning_rate": 1.999902812181835e-05,
      "loss": 1.4167,
      "step": 44
    },
    {
      "epoch": 0.12552301255230125,
      "grad_norm": 1.7750306011999208,
      "learning_rate": 1.9998272238333606e-05,
      "loss": 1.3533,
      "step": 45
    },
    {
      "epoch": 0.12552301255230125,
      "eval_loss": 1.6828460693359375,
      "eval_runtime": 158.4193,
      "eval_samples_per_second": 2.007,
      "eval_steps_per_second": 0.126,
      "step": 45
    },
    {
      "epoch": 0.12831241283124128,
      "grad_norm": 1.354470787639867,
      "learning_rate": 1.9997300416125426e-05,
      "loss": 1.3901,
      "step": 46
    },
    {
      "epoch": 0.13110181311018132,
      "grad_norm": 1.23248602443203,
      "learning_rate": 1.999611267618283e-05,
      "loss": 1.3485,
      "step": 47
    },
    {
      "epoch": 0.13389121338912133,
      "grad_norm": 1.314827114627873,
      "learning_rate": 1.9994709044158157e-05,
      "loss": 1.3195,
      "step": 48
    },
    {
      "epoch": 0.13668061366806136,
      "grad_norm": 1.3741001015735983,
      "learning_rate": 1.99930895503665e-05,
      "loss": 1.4394,
      "step": 49
    },
    {
      "epoch": 0.1394700139470014,
      "grad_norm": 1.1624406309888304,
      "learning_rate": 1.9991254229785043e-05,
      "loss": 1.2943,
      "step": 50
    },
    {
      "epoch": 0.14225941422594143,
      "grad_norm": 1.431188759221728,
      "learning_rate": 1.998920312205231e-05,
      "loss": 1.4614,
      "step": 51
    },
    {
      "epoch": 0.14504881450488144,
      "grad_norm": 1.2513371987994648,
      "learning_rate": 1.9986936271467316e-05,
      "loss": 1.328,
      "step": 52
    },
    {
      "epoch": 0.14783821478382148,
      "grad_norm": 1.6084481811469094,
      "learning_rate": 1.99844537269886e-05,
      "loss": 1.4579,
      "step": 53
    },
    {
      "epoch": 0.1506276150627615,
      "grad_norm": 1.3643143080926854,
      "learning_rate": 1.9981755542233175e-05,
      "loss": 1.4471,
      "step": 54
    },
    {
      "epoch": 0.15341701534170155,
      "grad_norm": 1.443453372098446,
      "learning_rate": 1.9978841775475368e-05,
      "loss": 1.3931,
      "step": 55
    },
    {
      "epoch": 0.15620641562064155,
      "grad_norm": 1.186174044031903,
      "learning_rate": 1.997571248964556e-05,
      "loss": 1.2935,
      "step": 56
    },
    {
      "epoch": 0.1589958158995816,
      "grad_norm": 1.3967845728055575,
      "learning_rate": 1.9972367752328824e-05,
      "loss": 1.3819,
      "step": 57
    },
    {
      "epoch": 0.16178521617852162,
      "grad_norm": 1.585201984076838,
      "learning_rate": 1.9968807635763472e-05,
      "loss": 1.5391,
      "step": 58
    },
    {
      "epoch": 0.16457461645746166,
      "grad_norm": 1.515327450581085,
      "learning_rate": 1.9965032216839493e-05,
      "loss": 1.3969,
      "step": 59
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 1.3595894447160555,
      "learning_rate": 1.996104157709689e-05,
      "loss": 1.3598,
      "step": 60
    },
    {
      "epoch": 0.1701534170153417,
      "grad_norm": 1.4252798961269173,
      "learning_rate": 1.9956835802723916e-05,
      "loss": 1.447,
      "step": 61
    },
    {
      "epoch": 0.17294281729428174,
      "grad_norm": 1.4269613254937963,
      "learning_rate": 1.9952414984555225e-05,
      "loss": 1.4354,
      "step": 62
    },
    {
      "epoch": 0.17573221757322174,
      "grad_norm": 1.5984564978735487,
      "learning_rate": 1.994777921806989e-05,
      "loss": 1.5493,
      "step": 63
    },
    {
      "epoch": 0.17852161785216178,
      "grad_norm": 1.5396475514798837,
      "learning_rate": 1.9942928603389366e-05,
      "loss": 1.4095,
      "step": 64
    },
    {
      "epoch": 0.18131101813110181,
      "grad_norm": 1.381818615640278,
      "learning_rate": 1.9937863245275303e-05,
      "loss": 1.381,
      "step": 65
    },
    {
      "epoch": 0.18410041841004185,
      "grad_norm": 1.3411933307262995,
      "learning_rate": 1.9932583253127302e-05,
      "loss": 1.4514,
      "step": 66
    },
    {
      "epoch": 0.18688981868898186,
      "grad_norm": 1.4666636741675445,
      "learning_rate": 1.992708874098054e-05,
      "loss": 1.378,
      "step": 67
    },
    {
      "epoch": 0.1896792189679219,
      "grad_norm": 1.321297415086869,
      "learning_rate": 1.9921379827503316e-05,
      "loss": 1.3916,
      "step": 68
    },
    {
      "epoch": 0.19246861924686193,
      "grad_norm": 1.3031514888132292,
      "learning_rate": 1.991545663599448e-05,
      "loss": 1.3568,
      "step": 69
    },
    {
      "epoch": 0.19525801952580196,
      "grad_norm": 1.3252501098302665,
      "learning_rate": 1.990931929438078e-05,
      "loss": 1.3691,
      "step": 70
    },
    {
      "epoch": 0.19804741980474197,
      "grad_norm": 1.3190300203004819,
      "learning_rate": 1.990296793521408e-05,
      "loss": 1.425,
      "step": 71
    },
    {
      "epoch": 0.200836820083682,
      "grad_norm": 1.221728638105595,
      "learning_rate": 1.989640269566853e-05,
      "loss": 1.3669,
      "step": 72
    },
    {
      "epoch": 0.20362622036262204,
      "grad_norm": 1.2519446160682244,
      "learning_rate": 1.9889623717537564e-05,
      "loss": 1.5065,
      "step": 73
    },
    {
      "epoch": 0.20641562064156208,
      "grad_norm": 1.3192555240060455,
      "learning_rate": 1.9882631147230874e-05,
      "loss": 1.3077,
      "step": 74
    },
    {
      "epoch": 0.20920502092050208,
      "grad_norm": 1.811281511932427,
      "learning_rate": 1.987542513577122e-05,
      "loss": 1.4737,
      "step": 75
    },
    {
      "epoch": 0.21199442119944212,
      "grad_norm": 1.2107466822843787,
      "learning_rate": 1.9868005838791185e-05,
      "loss": 1.3632,
      "step": 76
    },
    {
      "epoch": 0.21478382147838215,
      "grad_norm": 1.4506886695952612,
      "learning_rate": 1.9860373416529804e-05,
      "loss": 1.3707,
      "step": 77
    },
    {
      "epoch": 0.2175732217573222,
      "grad_norm": 1.129475911714987,
      "learning_rate": 1.985252803382911e-05,
      "loss": 1.2879,
      "step": 78
    },
    {
      "epoch": 0.2203626220362622,
      "grad_norm": 1.2378410441125478,
      "learning_rate": 1.984446986013057e-05,
      "loss": 1.4352,
      "step": 79
    },
    {
      "epoch": 0.22315202231520223,
      "grad_norm": 1.2497274548196218,
      "learning_rate": 1.983619906947144e-05,
      "loss": 1.2929,
      "step": 80
    },
    {
      "epoch": 0.22594142259414227,
      "grad_norm": 1.2860272115066647,
      "learning_rate": 1.9827715840480962e-05,
      "loss": 1.2595,
      "step": 81
    },
    {
      "epoch": 0.22873082287308227,
      "grad_norm": 1.3259601590310435,
      "learning_rate": 1.9819020356376562e-05,
      "loss": 1.5421,
      "step": 82
    },
    {
      "epoch": 0.2315202231520223,
      "grad_norm": 1.3823289295025785,
      "learning_rate": 1.9810112804959867e-05,
      "loss": 1.4379,
      "step": 83
    },
    {
      "epoch": 0.23430962343096234,
      "grad_norm": 1.2790636696723037,
      "learning_rate": 1.980099337861264e-05,
      "loss": 1.4045,
      "step": 84
    },
    {
      "epoch": 0.23709902370990238,
      "grad_norm": 1.2621634213682735,
      "learning_rate": 1.9791662274292638e-05,
      "loss": 1.3433,
      "step": 85
    },
    {
      "epoch": 0.2398884239888424,
      "grad_norm": 1.4041226411604562,
      "learning_rate": 1.9782119693529358e-05,
      "loss": 1.6292,
      "step": 86
    },
    {
      "epoch": 0.24267782426778242,
      "grad_norm": 1.4238393471976662,
      "learning_rate": 1.977236584241968e-05,
      "loss": 1.398,
      "step": 87
    },
    {
      "epoch": 0.24546722454672246,
      "grad_norm": 1.3721757997449184,
      "learning_rate": 1.9762400931623413e-05,
      "loss": 1.372,
      "step": 88
    },
    {
      "epoch": 0.2482566248256625,
      "grad_norm": 1.3049726438204359,
      "learning_rate": 1.9752225176358757e-05,
      "loss": 1.4366,
      "step": 89
    },
    {
      "epoch": 0.2510460251046025,
      "grad_norm": 1.319316702022308,
      "learning_rate": 1.9741838796397638e-05,
      "loss": 1.2807,
      "step": 90
    },
    {
      "epoch": 0.2510460251046025,
      "eval_loss": 1.6544907093048096,
      "eval_runtime": 157.4295,
      "eval_samples_per_second": 2.02,
      "eval_steps_per_second": 0.127,
      "step": 90
    },
    {
      "epoch": 0.25383542538354253,
      "grad_norm": 1.3259568867589984,
      "learning_rate": 1.9731242016060985e-05,
      "loss": 1.3566,
      "step": 91
    },
    {
      "epoch": 0.25662482566248257,
      "grad_norm": 1.3318698765554446,
      "learning_rate": 1.972043506421386e-05,
      "loss": 1.3304,
      "step": 92
    },
    {
      "epoch": 0.2594142259414226,
      "grad_norm": 1.210762982291795,
      "learning_rate": 1.9709418174260523e-05,
      "loss": 1.3663,
      "step": 93
    },
    {
      "epoch": 0.26220362622036264,
      "grad_norm": 1.322366639833671,
      "learning_rate": 1.9698191584139402e-05,
      "loss": 1.4099,
      "step": 94
    },
    {
      "epoch": 0.2649930264993027,
      "grad_norm": 1.286954377653034,
      "learning_rate": 1.9686755536317945e-05,
      "loss": 1.3539,
      "step": 95
    },
    {
      "epoch": 0.26778242677824265,
      "grad_norm": 1.1590651579123286,
      "learning_rate": 1.967511027778738e-05,
      "loss": 1.2147,
      "step": 96
    },
    {
      "epoch": 0.2705718270571827,
      "grad_norm": 1.3100829080105303,
      "learning_rate": 1.9663256060057395e-05,
      "loss": 1.4093,
      "step": 97
    },
    {
      "epoch": 0.2733612273361227,
      "grad_norm": 1.346265752760783,
      "learning_rate": 1.965119313915068e-05,
      "loss": 1.491,
      "step": 98
    },
    {
      "epoch": 0.27615062761506276,
      "grad_norm": 1.378168477135006,
      "learning_rate": 1.9638921775597428e-05,
      "loss": 1.5049,
      "step": 99
    },
    {
      "epoch": 0.2789400278940028,
      "grad_norm": 1.4182107155054933,
      "learning_rate": 1.9626442234429684e-05,
      "loss": 1.5013,
      "step": 100
    },
    {
      "epoch": 0.28172942817294283,
      "grad_norm": 1.3165711654218712,
      "learning_rate": 1.961375478517564e-05,
      "loss": 1.5105,
      "step": 101
    },
    {
      "epoch": 0.28451882845188287,
      "grad_norm": 1.364780296172199,
      "learning_rate": 1.9600859701853796e-05,
      "loss": 1.5207,
      "step": 102
    },
    {
      "epoch": 0.28730822873082285,
      "grad_norm": 1.2988922679076684,
      "learning_rate": 1.958775726296706e-05,
      "loss": 1.2881,
      "step": 103
    },
    {
      "epoch": 0.2900976290097629,
      "grad_norm": 1.3450528168801636,
      "learning_rate": 1.9574447751496706e-05,
      "loss": 1.2877,
      "step": 104
    },
    {
      "epoch": 0.2928870292887029,
      "grad_norm": 1.4142239844479165,
      "learning_rate": 1.95609314548963e-05,
      "loss": 1.5604,
      "step": 105
    },
    {
      "epoch": 0.29567642956764295,
      "grad_norm": 1.3452993293539794,
      "learning_rate": 1.954720866508546e-05,
      "loss": 1.3447,
      "step": 106
    },
    {
      "epoch": 0.298465829846583,
      "grad_norm": 1.4534491830895881,
      "learning_rate": 1.953327967844356e-05,
      "loss": 1.3643,
      "step": 107
    },
    {
      "epoch": 0.301255230125523,
      "grad_norm": 1.350966370835706,
      "learning_rate": 1.9519144795803342e-05,
      "loss": 1.5196,
      "step": 108
    },
    {
      "epoch": 0.30404463040446306,
      "grad_norm": 1.3487778511447879,
      "learning_rate": 1.95048043224444e-05,
      "loss": 1.4243,
      "step": 109
    },
    {
      "epoch": 0.3068340306834031,
      "grad_norm": 1.3479508491141639,
      "learning_rate": 1.94902585680866e-05,
      "loss": 1.2869,
      "step": 110
    },
    {
      "epoch": 0.30962343096234307,
      "grad_norm": 1.5555627133101146,
      "learning_rate": 1.9475507846883377e-05,
      "loss": 1.4626,
      "step": 111
    },
    {
      "epoch": 0.3124128312412831,
      "grad_norm": 1.264890715784298,
      "learning_rate": 1.9460552477414972e-05,
      "loss": 1.2826,
      "step": 112
    },
    {
      "epoch": 0.31520223152022314,
      "grad_norm": 1.2628748380778831,
      "learning_rate": 1.9445392782681523e-05,
      "loss": 1.232,
      "step": 113
    },
    {
      "epoch": 0.3179916317991632,
      "grad_norm": 1.3550404859387195,
      "learning_rate": 1.9430029090096118e-05,
      "loss": 1.3034,
      "step": 114
    },
    {
      "epoch": 0.3207810320781032,
      "grad_norm": 1.1496127251687267,
      "learning_rate": 1.94144617314777e-05,
      "loss": 1.3215,
      "step": 115
    },
    {
      "epoch": 0.32357043235704325,
      "grad_norm": 1.3116085375581363,
      "learning_rate": 1.939869104304392e-05,
      "loss": 1.4154,
      "step": 116
    },
    {
      "epoch": 0.3263598326359833,
      "grad_norm": 1.2589366985022925,
      "learning_rate": 1.9382717365403854e-05,
      "loss": 1.517,
      "step": 117
    },
    {
      "epoch": 0.3291492329149233,
      "grad_norm": 1.3051575397158521,
      "learning_rate": 1.9366541043550667e-05,
      "loss": 1.3795,
      "step": 118
    },
    {
      "epoch": 0.3319386331938633,
      "grad_norm": 1.514184766493585,
      "learning_rate": 1.9350162426854152e-05,
      "loss": 1.5974,
      "step": 119
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 1.3773144705212048,
      "learning_rate": 1.933358186905318e-05,
      "loss": 1.3696,
      "step": 120
    },
    {
      "epoch": 0.33751743375174337,
      "grad_norm": 1.070700275666401,
      "learning_rate": 1.9316799728248074e-05,
      "loss": 1.1661,
      "step": 121
    },
    {
      "epoch": 0.3403068340306834,
      "grad_norm": 1.4181760004495874,
      "learning_rate": 1.9299816366892865e-05,
      "loss": 1.4376,
      "step": 122
    },
    {
      "epoch": 0.34309623430962344,
      "grad_norm": 1.6034791315185046,
      "learning_rate": 1.9282632151787462e-05,
      "loss": 1.5891,
      "step": 123
    },
    {
      "epoch": 0.3458856345885635,
      "grad_norm": 1.1884570183288778,
      "learning_rate": 1.9265247454069736e-05,
      "loss": 1.3432,
      "step": 124
    },
    {
      "epoch": 0.3486750348675035,
      "grad_norm": 1.477555714731358,
      "learning_rate": 1.924766264920751e-05,
      "loss": 1.3683,
      "step": 125
    },
    {
      "epoch": 0.3514644351464435,
      "grad_norm": 1.2504857458807423,
      "learning_rate": 1.922987811699042e-05,
      "loss": 1.2643,
      "step": 126
    },
    {
      "epoch": 0.3542538354253835,
      "grad_norm": 1.3679090790056112,
      "learning_rate": 1.9211894241521757e-05,
      "loss": 1.5962,
      "step": 127
    },
    {
      "epoch": 0.35704323570432356,
      "grad_norm": 1.2309836816544464,
      "learning_rate": 1.9193711411210138e-05,
      "loss": 1.3361,
      "step": 128
    },
    {
      "epoch": 0.3598326359832636,
      "grad_norm": 1.1714321663378802,
      "learning_rate": 1.917533001876113e-05,
      "loss": 1.3019,
      "step": 129
    },
    {
      "epoch": 0.36262203626220363,
      "grad_norm": 1.2813447334304535,
      "learning_rate": 1.9156750461168768e-05,
      "loss": 1.4319,
      "step": 130
    },
    {
      "epoch": 0.36541143654114366,
      "grad_norm": 1.427767209588848,
      "learning_rate": 1.9137973139706973e-05,
      "loss": 1.4712,
      "step": 131
    },
    {
      "epoch": 0.3682008368200837,
      "grad_norm": 1.3426640935974619,
      "learning_rate": 1.91189984599209e-05,
      "loss": 1.4397,
      "step": 132
    },
    {
      "epoch": 0.37099023709902373,
      "grad_norm": 1.3173830250699687,
      "learning_rate": 1.9099826831618168e-05,
      "loss": 1.4799,
      "step": 133
    },
    {
      "epoch": 0.3737796373779637,
      "grad_norm": 1.5260053920559482,
      "learning_rate": 1.908045866886001e-05,
      "loss": 1.5167,
      "step": 134
    },
    {
      "epoch": 0.37656903765690375,
      "grad_norm": 1.2838799058228236,
      "learning_rate": 1.9060894389952328e-05,
      "loss": 1.3957,
      "step": 135
    },
    {
      "epoch": 0.37656903765690375,
      "eval_loss": 1.629968523979187,
      "eval_runtime": 155.8796,
      "eval_samples_per_second": 2.04,
      "eval_steps_per_second": 0.128,
      "step": 135
    },
    {
      "epoch": 0.3793584379358438,
      "grad_norm": 1.2595723963522658,
      "learning_rate": 1.9041134417436674e-05,
      "loss": 1.3773,
      "step": 136
    },
    {
      "epoch": 0.3821478382147838,
      "grad_norm": 1.380977078216302,
      "learning_rate": 1.9021179178081107e-05,
      "loss": 1.5358,
      "step": 137
    },
    {
      "epoch": 0.38493723849372385,
      "grad_norm": 1.3245015694120374,
      "learning_rate": 1.9001029102870982e-05,
      "loss": 1.506,
      "step": 138
    },
    {
      "epoch": 0.3877266387726639,
      "grad_norm": 1.2602456347612,
      "learning_rate": 1.898068462699964e-05,
      "loss": 1.4246,
      "step": 139
    },
    {
      "epoch": 0.3905160390516039,
      "grad_norm": 1.3989105118625398,
      "learning_rate": 1.8960146189859014e-05,
      "loss": 1.4692,
      "step": 140
    },
    {
      "epoch": 0.39330543933054396,
      "grad_norm": 1.2616111800783727,
      "learning_rate": 1.8939414235030137e-05,
      "loss": 1.3755,
      "step": 141
    },
    {
      "epoch": 0.39609483960948394,
      "grad_norm": 1.2686523296470786,
      "learning_rate": 1.891848921027355e-05,
      "loss": 1.3442,
      "step": 142
    },
    {
      "epoch": 0.398884239888424,
      "grad_norm": 1.37417212405681,
      "learning_rate": 1.889737156751965e-05,
      "loss": 1.3651,
      "step": 143
    },
    {
      "epoch": 0.401673640167364,
      "grad_norm": 1.373244156828418,
      "learning_rate": 1.887606176285893e-05,
      "loss": 1.4961,
      "step": 144
    },
    {
      "epoch": 0.40446304044630405,
      "grad_norm": 1.1872961109156253,
      "learning_rate": 1.8854560256532098e-05,
      "loss": 1.2587,
      "step": 145
    },
    {
      "epoch": 0.4072524407252441,
      "grad_norm": 1.313036403643509,
      "learning_rate": 1.883286751292018e-05,
      "loss": 1.4575,
      "step": 146
    },
    {
      "epoch": 0.4100418410041841,
      "grad_norm": 1.390974479025736,
      "learning_rate": 1.8810984000534457e-05,
      "loss": 1.3891,
      "step": 147
    },
    {
      "epoch": 0.41283124128312415,
      "grad_norm": 1.3368020257438076,
      "learning_rate": 1.8788910192006363e-05,
      "loss": 1.3415,
      "step": 148
    },
    {
      "epoch": 0.41562064156206413,
      "grad_norm": 1.2329515511987332,
      "learning_rate": 1.8766646564077265e-05,
      "loss": 1.3339,
      "step": 149
    },
    {
      "epoch": 0.41841004184100417,
      "grad_norm": 1.276208090352136,
      "learning_rate": 1.8744193597588185e-05,
      "loss": 1.4495,
      "step": 150
    },
    {
      "epoch": 0.4211994421199442,
      "grad_norm": 1.1548092334953926,
      "learning_rate": 1.8721551777469397e-05,
      "loss": 1.2099,
      "step": 151
    },
    {
      "epoch": 0.42398884239888424,
      "grad_norm": 1.3184986062317001,
      "learning_rate": 1.869872159272997e-05,
      "loss": 1.2136,
      "step": 152
    },
    {
      "epoch": 0.42677824267782427,
      "grad_norm": 1.1962726760049636,
      "learning_rate": 1.8675703536447178e-05,
      "loss": 1.2598,
      "step": 153
    },
    {
      "epoch": 0.4295676429567643,
      "grad_norm": 1.3302312487017707,
      "learning_rate": 1.8652498105755898e-05,
      "loss": 1.3719,
      "step": 154
    },
    {
      "epoch": 0.43235704323570434,
      "grad_norm": 1.55872330252289,
      "learning_rate": 1.862910580183782e-05,
      "loss": 1.4867,
      "step": 155
    },
    {
      "epoch": 0.4351464435146444,
      "grad_norm": 1.3004017172912832,
      "learning_rate": 1.8605527129910663e-05,
      "loss": 1.3089,
      "step": 156
    },
    {
      "epoch": 0.43793584379358436,
      "grad_norm": 1.2650294480346138,
      "learning_rate": 1.858176259921724e-05,
      "loss": 1.2856,
      "step": 157
    },
    {
      "epoch": 0.4407252440725244,
      "grad_norm": 1.414189467122214,
      "learning_rate": 1.8557812723014476e-05,
      "loss": 1.4827,
      "step": 158
    },
    {
      "epoch": 0.4435146443514644,
      "grad_norm": 1.2634959665686347,
      "learning_rate": 1.853367801856231e-05,
      "loss": 1.3568,
      "step": 159
    },
    {
      "epoch": 0.44630404463040446,
      "grad_norm": 1.3164047095667806,
      "learning_rate": 1.8509359007112523e-05,
      "loss": 1.5306,
      "step": 160
    },
    {
      "epoch": 0.4490934449093445,
      "grad_norm": 1.3232600329575266,
      "learning_rate": 1.8484856213897496e-05,
      "loss": 1.4279,
      "step": 161
    },
    {
      "epoch": 0.45188284518828453,
      "grad_norm": 1.286194256752095,
      "learning_rate": 1.8460170168118857e-05,
      "loss": 1.2656,
      "step": 162
    },
    {
      "epoch": 0.45467224546722457,
      "grad_norm": 1.393553888811773,
      "learning_rate": 1.843530140293603e-05,
      "loss": 1.4003,
      "step": 163
    },
    {
      "epoch": 0.45746164574616455,
      "grad_norm": 1.2952418440030533,
      "learning_rate": 1.841025045545477e-05,
      "loss": 1.365,
      "step": 164
    },
    {
      "epoch": 0.4602510460251046,
      "grad_norm": 1.2556167978994803,
      "learning_rate": 1.8385017866715507e-05,
      "loss": 1.3313,
      "step": 165
    },
    {
      "epoch": 0.4630404463040446,
      "grad_norm": 1.3067564204278406,
      "learning_rate": 1.8359604181681703e-05,
      "loss": 1.4114,
      "step": 166
    },
    {
      "epoch": 0.46582984658298465,
      "grad_norm": 1.2088590174928828,
      "learning_rate": 1.833400994922806e-05,
      "loss": 1.1866,
      "step": 167
    },
    {
      "epoch": 0.4686192468619247,
      "grad_norm": 1.334753865529686,
      "learning_rate": 1.8308235722128674e-05,
      "loss": 1.2744,
      "step": 168
    },
    {
      "epoch": 0.4714086471408647,
      "grad_norm": 1.3612556693462265,
      "learning_rate": 1.8282282057045087e-05,
      "loss": 1.3558,
      "step": 169
    },
    {
      "epoch": 0.47419804741980476,
      "grad_norm": 1.2660924285869366,
      "learning_rate": 1.8256149514514284e-05,
      "loss": 1.2804,
      "step": 170
    },
    {
      "epoch": 0.4769874476987448,
      "grad_norm": 1.3192403133250346,
      "learning_rate": 1.8229838658936566e-05,
      "loss": 1.3874,
      "step": 171
    },
    {
      "epoch": 0.4797768479776848,
      "grad_norm": 1.3924722985838183,
      "learning_rate": 1.8203350058563366e-05,
      "loss": 1.5013,
      "step": 172
    },
    {
      "epoch": 0.4825662482566248,
      "grad_norm": 1.2874077296032287,
      "learning_rate": 1.8176684285484985e-05,
      "loss": 1.3261,
      "step": 173
    },
    {
      "epoch": 0.48535564853556484,
      "grad_norm": 1.309597924994118,
      "learning_rate": 1.814984191561823e-05,
      "loss": 1.4157,
      "step": 174
    },
    {
      "epoch": 0.4881450488145049,
      "grad_norm": 1.1912282212302885,
      "learning_rate": 1.8122823528693966e-05,
      "loss": 1.2585,
      "step": 175
    },
    {
      "epoch": 0.4909344490934449,
      "grad_norm": 1.2765007106705224,
      "learning_rate": 1.809562970824462e-05,
      "loss": 1.3437,
      "step": 176
    },
    {
      "epoch": 0.49372384937238495,
      "grad_norm": 1.2571675750543854,
      "learning_rate": 1.8068261041591548e-05,
      "loss": 1.4383,
      "step": 177
    },
    {
      "epoch": 0.496513249651325,
      "grad_norm": 1.1735759325774886,
      "learning_rate": 1.8040718119832378e-05,
      "loss": 1.3234,
      "step": 178
    },
    {
      "epoch": 0.499302649930265,
      "grad_norm": 1.1634243266804525,
      "learning_rate": 1.8013001537828213e-05,
      "loss": 1.2169,
      "step": 179
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 1.2251535095230563,
      "learning_rate": 1.7985111894190827e-05,
      "loss": 1.2727,
      "step": 180
    },
    {
      "epoch": 0.502092050209205,
      "eval_loss": 1.6175622940063477,
      "eval_runtime": 183.4681,
      "eval_samples_per_second": 1.733,
      "eval_steps_per_second": 0.109,
      "step": 180
    },
    {
      "epoch": 0.504881450488145,
      "grad_norm": 1.2927502437198448,
      "learning_rate": 1.7957049791269684e-05,
      "loss": 1.3752,
      "step": 181
    },
    {
      "epoch": 0.5076708507670851,
      "grad_norm": 1.2697109314581512,
      "learning_rate": 1.7928815835138976e-05,
      "loss": 1.502,
      "step": 182
    },
    {
      "epoch": 0.5104602510460251,
      "grad_norm": 1.3004080082594036,
      "learning_rate": 1.79004106355845e-05,
      "loss": 1.49,
      "step": 183
    },
    {
      "epoch": 0.5132496513249651,
      "grad_norm": 1.2620161230293547,
      "learning_rate": 1.7871834806090502e-05,
      "loss": 1.258,
      "step": 184
    },
    {
      "epoch": 0.5160390516039052,
      "grad_norm": 1.2238216229925647,
      "learning_rate": 1.7843088963826437e-05,
      "loss": 1.2829,
      "step": 185
    },
    {
      "epoch": 0.5188284518828452,
      "grad_norm": 1.2320397894400665,
      "learning_rate": 1.7814173729633607e-05,
      "loss": 1.2767,
      "step": 186
    },
    {
      "epoch": 0.5216178521617852,
      "grad_norm": 1.3637977851134857,
      "learning_rate": 1.7785089728011798e-05,
      "loss": 1.3635,
      "step": 187
    },
    {
      "epoch": 0.5244072524407253,
      "grad_norm": 1.2685139570979558,
      "learning_rate": 1.775583758710575e-05,
      "loss": 1.4145,
      "step": 188
    },
    {
      "epoch": 0.5271966527196653,
      "grad_norm": 1.3355216229358506,
      "learning_rate": 1.772641793869162e-05,
      "loss": 1.3068,
      "step": 189
    },
    {
      "epoch": 0.5299860529986054,
      "grad_norm": 1.3597618241983527,
      "learning_rate": 1.7696831418163318e-05,
      "loss": 1.4446,
      "step": 190
    },
    {
      "epoch": 0.5327754532775453,
      "grad_norm": 1.2542157271291101,
      "learning_rate": 1.7667078664518796e-05,
      "loss": 1.4184,
      "step": 191
    },
    {
      "epoch": 0.5355648535564853,
      "grad_norm": 1.3244864911198961,
      "learning_rate": 1.763716032034624e-05,
      "loss": 1.3889,
      "step": 192
    },
    {
      "epoch": 0.5383542538354253,
      "grad_norm": 1.261772883234437,
      "learning_rate": 1.7607077031810204e-05,
      "loss": 1.343,
      "step": 193
    },
    {
      "epoch": 0.5411436541143654,
      "grad_norm": 1.404601026428458,
      "learning_rate": 1.7576829448637628e-05,
      "loss": 1.4606,
      "step": 194
    },
    {
      "epoch": 0.5439330543933054,
      "grad_norm": 1.3091211707895143,
      "learning_rate": 1.7546418224103838e-05,
      "loss": 1.2931,
      "step": 195
    },
    {
      "epoch": 0.5467224546722455,
      "grad_norm": 1.2631117467582635,
      "learning_rate": 1.7515844015018416e-05,
      "loss": 1.2999,
      "step": 196
    },
    {
      "epoch": 0.5495118549511855,
      "grad_norm": 1.4560900819743723,
      "learning_rate": 1.7485107481711014e-05,
      "loss": 1.5475,
      "step": 197
    },
    {
      "epoch": 0.5523012552301255,
      "grad_norm": 1.4468059745173558,
      "learning_rate": 1.7454209288017105e-05,
      "loss": 1.4191,
      "step": 198
    },
    {
      "epoch": 0.5550906555090656,
      "grad_norm": 1.315266510590906,
      "learning_rate": 1.7423150101263645e-05,
      "loss": 1.4005,
      "step": 199
    },
    {
      "epoch": 0.5578800557880056,
      "grad_norm": 1.474348076413936,
      "learning_rate": 1.7391930592254636e-05,
      "loss": 1.3192,
      "step": 200
    },
    {
      "epoch": 0.5606694560669456,
      "grad_norm": 1.3652476074142217,
      "learning_rate": 1.7360551435256673e-05,
      "loss": 1.2574,
      "step": 201
    },
    {
      "epoch": 0.5634588563458857,
      "grad_norm": 1.3798373173542198,
      "learning_rate": 1.7329013307984363e-05,
      "loss": 1.3117,
      "step": 202
    },
    {
      "epoch": 0.5662482566248257,
      "grad_norm": 1.209790296025406,
      "learning_rate": 1.729731689158568e-05,
      "loss": 1.3107,
      "step": 203
    },
    {
      "epoch": 0.5690376569037657,
      "grad_norm": 1.1868593994582228,
      "learning_rate": 1.726546287062727e-05,
      "loss": 1.2752,
      "step": 204
    },
    {
      "epoch": 0.5718270571827058,
      "grad_norm": 1.3235161134829174,
      "learning_rate": 1.7233451933079663e-05,
      "loss": 1.3399,
      "step": 205
    },
    {
      "epoch": 0.5746164574616457,
      "grad_norm": 1.353859989844425,
      "learning_rate": 1.720128477030241e-05,
      "loss": 1.3181,
      "step": 206
    },
    {
      "epoch": 0.5774058577405857,
      "grad_norm": 1.3778332664676014,
      "learning_rate": 1.7168962077029146e-05,
      "loss": 1.372,
      "step": 207
    },
    {
      "epoch": 0.5801952580195258,
      "grad_norm": 1.3065213179222184,
      "learning_rate": 1.7136484551352608e-05,
      "loss": 1.2717,
      "step": 208
    },
    {
      "epoch": 0.5829846582984658,
      "grad_norm": 1.3461935265014031,
      "learning_rate": 1.7103852894709517e-05,
      "loss": 1.3716,
      "step": 209
    },
    {
      "epoch": 0.5857740585774058,
      "grad_norm": 1.5238199082532498,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 1.4732,
      "step": 210
    },
    {
      "epoch": 0.5885634588563459,
      "grad_norm": 1.2661008215508678,
      "learning_rate": 1.7038130010899716e-05,
      "loss": 1.3884,
      "step": 211
    },
    {
      "epoch": 0.5913528591352859,
      "grad_norm": 1.3340050909328596,
      "learning_rate": 1.7005040203189818e-05,
      "loss": 1.3851,
      "step": 212
    },
    {
      "epoch": 0.5941422594142259,
      "grad_norm": 1.2956837583785732,
      "learning_rate": 1.6971799103396332e-05,
      "loss": 1.4221,
      "step": 213
    },
    {
      "epoch": 0.596931659693166,
      "grad_norm": 1.1561140429998333,
      "learning_rate": 1.693840742944738e-05,
      "loss": 1.2218,
      "step": 214
    },
    {
      "epoch": 0.599721059972106,
      "grad_norm": 1.313764720344347,
      "learning_rate": 1.6904865902523098e-05,
      "loss": 1.264,
      "step": 215
    },
    {
      "epoch": 0.602510460251046,
      "grad_norm": 1.3302384495066342,
      "learning_rate": 1.68711752470401e-05,
      "loss": 1.2776,
      "step": 216
    },
    {
      "epoch": 0.6052998605299861,
      "grad_norm": 1.2191909895274562,
      "learning_rate": 1.6837336190635824e-05,
      "loss": 1.3539,
      "step": 217
    },
    {
      "epoch": 0.6080892608089261,
      "grad_norm": 1.3373684634352505,
      "learning_rate": 1.6803349464152798e-05,
      "loss": 1.4503,
      "step": 218
    },
    {
      "epoch": 0.6108786610878661,
      "grad_norm": 1.363619941169918,
      "learning_rate": 1.6769215801622884e-05,
      "loss": 1.5192,
      "step": 219
    },
    {
      "epoch": 0.6136680613668062,
      "grad_norm": 1.4606054239168875,
      "learning_rate": 1.6734935940251404e-05,
      "loss": 1.5595,
      "step": 220
    },
    {
      "epoch": 0.6164574616457462,
      "grad_norm": 1.231599938466119,
      "learning_rate": 1.6700510620401223e-05,
      "loss": 1.2604,
      "step": 221
    },
    {
      "epoch": 0.6192468619246861,
      "grad_norm": 1.5101877585841448,
      "learning_rate": 1.666594058557677e-05,
      "loss": 1.4834,
      "step": 222
    },
    {
      "epoch": 0.6220362622036262,
      "grad_norm": 1.39399625488815,
      "learning_rate": 1.6631226582407954e-05,
      "loss": 1.3877,
      "step": 223
    },
    {
      "epoch": 0.6248256624825662,
      "grad_norm": 1.453409874433298,
      "learning_rate": 1.659636936063407e-05,
      "loss": 1.5218,
      "step": 224
    },
    {
      "epoch": 0.6276150627615062,
      "grad_norm": 1.2538819898580684,
      "learning_rate": 1.6561369673087588e-05,
      "loss": 1.2438,
      "step": 225
    },
    {
      "epoch": 0.6276150627615062,
      "eval_loss": 1.6073960065841675,
      "eval_runtime": 160.2272,
      "eval_samples_per_second": 1.985,
      "eval_steps_per_second": 0.125,
      "step": 225
    },
    {
      "epoch": 0.6304044630404463,
      "grad_norm": 1.5406663292943368,
      "learning_rate": 1.6526228275677892e-05,
      "loss": 1.4646,
      "step": 226
    },
    {
      "epoch": 0.6331938633193863,
      "grad_norm": 1.2629740380853072,
      "learning_rate": 1.649094592737497e-05,
      "loss": 1.3459,
      "step": 227
    },
    {
      "epoch": 0.6359832635983264,
      "grad_norm": 1.302608797313638,
      "learning_rate": 1.6455523390193e-05,
      "loss": 1.2689,
      "step": 228
    },
    {
      "epoch": 0.6387726638772664,
      "grad_norm": 1.1773849504199476,
      "learning_rate": 1.641996142917391e-05,
      "loss": 1.2342,
      "step": 229
    },
    {
      "epoch": 0.6415620641562064,
      "grad_norm": 1.3493891917660983,
      "learning_rate": 1.638426081237085e-05,
      "loss": 1.2569,
      "step": 230
    },
    {
      "epoch": 0.6443514644351465,
      "grad_norm": 1.388250997836812,
      "learning_rate": 1.63484223108316e-05,
      "loss": 1.3979,
      "step": 231
    },
    {
      "epoch": 0.6471408647140865,
      "grad_norm": 1.1928671464502947,
      "learning_rate": 1.6312446698581915e-05,
      "loss": 1.23,
      "step": 232
    },
    {
      "epoch": 0.6499302649930265,
      "grad_norm": 1.2633309780727078,
      "learning_rate": 1.6276334752608823e-05,
      "loss": 1.4891,
      "step": 233
    },
    {
      "epoch": 0.6527196652719666,
      "grad_norm": 1.304711639719216,
      "learning_rate": 1.624008725284383e-05,
      "loss": 1.3034,
      "step": 234
    },
    {
      "epoch": 0.6555090655509066,
      "grad_norm": 1.2217261096543481,
      "learning_rate": 1.6203704982146073e-05,
      "loss": 1.2068,
      "step": 235
    },
    {
      "epoch": 0.6582984658298466,
      "grad_norm": 1.288441898801668,
      "learning_rate": 1.6167188726285433e-05,
      "loss": 1.2461,
      "step": 236
    },
    {
      "epoch": 0.6610878661087866,
      "grad_norm": 1.590492811559281,
      "learning_rate": 1.613053927392553e-05,
      "loss": 1.5137,
      "step": 237
    },
    {
      "epoch": 0.6638772663877266,
      "grad_norm": 1.2477326342958976,
      "learning_rate": 1.6093757416606725e-05,
      "loss": 1.3189,
      "step": 238
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.2127950915475818,
      "learning_rate": 1.6056843948729e-05,
      "loss": 1.2682,
      "step": 239
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 1.4271242774536947,
      "learning_rate": 1.6019799667534813e-05,
      "loss": 1.5004,
      "step": 240
    },
    {
      "epoch": 0.6722454672245467,
      "grad_norm": 1.3666477545942404,
      "learning_rate": 1.5982625373091877e-05,
      "loss": 1.5493,
      "step": 241
    },
    {
      "epoch": 0.6750348675034867,
      "grad_norm": 1.1483091382024733,
      "learning_rate": 1.594532186827588e-05,
      "loss": 1.3191,
      "step": 242
    },
    {
      "epoch": 0.6778242677824268,
      "grad_norm": 3.1947518624580136,
      "learning_rate": 1.5907889958753134e-05,
      "loss": 1.3046,
      "step": 243
    },
    {
      "epoch": 0.6806136680613668,
      "grad_norm": 1.3099413581809563,
      "learning_rate": 1.5870330452963206e-05,
      "loss": 1.2706,
      "step": 244
    },
    {
      "epoch": 0.6834030683403068,
      "grad_norm": 1.461185290486486,
      "learning_rate": 1.5832644162101417e-05,
      "loss": 1.4886,
      "step": 245
    },
    {
      "epoch": 0.6861924686192469,
      "grad_norm": 1.2442836680144551,
      "learning_rate": 1.5794831900101352e-05,
      "loss": 1.27,
      "step": 246
    },
    {
      "epoch": 0.6889818688981869,
      "grad_norm": 1.248119979843789,
      "learning_rate": 1.5756894483617268e-05,
      "loss": 1.2831,
      "step": 247
    },
    {
      "epoch": 0.691771269177127,
      "grad_norm": 1.3703323165735684,
      "learning_rate": 1.571883273200646e-05,
      "loss": 1.5584,
      "step": 248
    },
    {
      "epoch": 0.694560669456067,
      "grad_norm": 1.3183958125038406,
      "learning_rate": 1.568064746731156e-05,
      "loss": 1.5037,
      "step": 249
    },
    {
      "epoch": 0.697350069735007,
      "grad_norm": 1.1844817674941481,
      "learning_rate": 1.564233951424279e-05,
      "loss": 1.4209,
      "step": 250
    },
    {
      "epoch": 0.700139470013947,
      "grad_norm": 1.5190227626319008,
      "learning_rate": 1.560390970016015e-05,
      "loss": 1.4738,
      "step": 251
    },
    {
      "epoch": 0.702928870292887,
      "grad_norm": 1.2922540957047237,
      "learning_rate": 1.5565358855055535e-05,
      "loss": 1.4749,
      "step": 252
    },
    {
      "epoch": 0.705718270571827,
      "grad_norm": 1.2755003379456324,
      "learning_rate": 1.552668781153484e-05,
      "loss": 1.3514,
      "step": 253
    },
    {
      "epoch": 0.708507670850767,
      "grad_norm": 1.333525201907311,
      "learning_rate": 1.5487897404799932e-05,
      "loss": 1.4833,
      "step": 254
    },
    {
      "epoch": 0.7112970711297071,
      "grad_norm": 1.2366281388101243,
      "learning_rate": 1.5448988472630654e-05,
      "loss": 1.3055,
      "step": 255
    },
    {
      "epoch": 0.7140864714086471,
      "grad_norm": 1.2656677555514606,
      "learning_rate": 1.5409961855366718e-05,
      "loss": 1.2858,
      "step": 256
    },
    {
      "epoch": 0.7168758716875872,
      "grad_norm": 1.3893320030810534,
      "learning_rate": 1.5370818395889536e-05,
      "loss": 1.2958,
      "step": 257
    },
    {
      "epoch": 0.7196652719665272,
      "grad_norm": 1.2262571768039963,
      "learning_rate": 1.533155893960405e-05,
      "loss": 1.3797,
      "step": 258
    },
    {
      "epoch": 0.7224546722454672,
      "grad_norm": 1.3752885859305817,
      "learning_rate": 1.5292184334420434e-05,
      "loss": 1.5324,
      "step": 259
    },
    {
      "epoch": 0.7252440725244073,
      "grad_norm": 1.349973458041763,
      "learning_rate": 1.5252695430735824e-05,
      "loss": 1.3828,
      "step": 260
    },
    {
      "epoch": 0.7280334728033473,
      "grad_norm": 1.214154217005644,
      "learning_rate": 1.521309308141592e-05,
      "loss": 1.3081,
      "step": 261
    },
    {
      "epoch": 0.7308228730822873,
      "grad_norm": 1.2681774984772773,
      "learning_rate": 1.5173378141776569e-05,
      "loss": 1.5341,
      "step": 262
    },
    {
      "epoch": 0.7336122733612274,
      "grad_norm": 1.2265782510592125,
      "learning_rate": 1.5133551469565313e-05,
      "loss": 1.2877,
      "step": 263
    },
    {
      "epoch": 0.7364016736401674,
      "grad_norm": 1.2084693848644321,
      "learning_rate": 1.5093613924942837e-05,
      "loss": 1.3773,
      "step": 264
    },
    {
      "epoch": 0.7391910739191074,
      "grad_norm": 1.1437825395668497,
      "learning_rate": 1.5053566370464416e-05,
      "loss": 1.2808,
      "step": 265
    },
    {
      "epoch": 0.7419804741980475,
      "grad_norm": 1.3197967431830404,
      "learning_rate": 1.5013409671061267e-05,
      "loss": 1.289,
      "step": 266
    },
    {
      "epoch": 0.7447698744769874,
      "grad_norm": 1.382635793553147,
      "learning_rate": 1.4973144694021874e-05,
      "loss": 1.2638,
      "step": 267
    },
    {
      "epoch": 0.7475592747559274,
      "grad_norm": 1.3988324864350785,
      "learning_rate": 1.4932772308973267e-05,
      "loss": 1.3403,
      "step": 268
    },
    {
      "epoch": 0.7503486750348675,
      "grad_norm": 1.2731407752985473,
      "learning_rate": 1.4892293387862221e-05,
      "loss": 1.3312,
      "step": 269
    },
    {
      "epoch": 0.7531380753138075,
      "grad_norm": 1.1572040227672067,
      "learning_rate": 1.4851708804936449e-05,
      "loss": 1.3147,
      "step": 270
    },
    {
      "epoch": 0.7531380753138075,
      "eval_loss": 1.5958304405212402,
      "eval_runtime": 158.3728,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 0.126,
      "step": 270
    },
    {
      "epoch": 0.7559274755927475,
      "grad_norm": 1.3990082254921117,
      "learning_rate": 1.4811019436725684e-05,
      "loss": 1.3162,
      "step": 271
    },
    {
      "epoch": 0.7587168758716876,
      "grad_norm": 1.2418130090749915,
      "learning_rate": 1.4770226162022799e-05,
      "loss": 1.2594,
      "step": 272
    },
    {
      "epoch": 0.7615062761506276,
      "grad_norm": 1.1503772215035513,
      "learning_rate": 1.472932986186477e-05,
      "loss": 1.2827,
      "step": 273
    },
    {
      "epoch": 0.7642956764295676,
      "grad_norm": 1.459940130878171,
      "learning_rate": 1.4688331419513693e-05,
      "loss": 1.3126,
      "step": 274
    },
    {
      "epoch": 0.7670850767085077,
      "grad_norm": 1.3252355330703371,
      "learning_rate": 1.4647231720437687e-05,
      "loss": 1.4367,
      "step": 275
    },
    {
      "epoch": 0.7698744769874477,
      "grad_norm": 1.4888619740632927,
      "learning_rate": 1.4606031652291772e-05,
      "loss": 1.4275,
      "step": 276
    },
    {
      "epoch": 0.7726638772663877,
      "grad_norm": 1.3069850449838218,
      "learning_rate": 1.4564732104898702e-05,
      "loss": 1.3533,
      "step": 277
    },
    {
      "epoch": 0.7754532775453278,
      "grad_norm": 1.268759058345783,
      "learning_rate": 1.4523333970229741e-05,
      "loss": 1.337,
      "step": 278
    },
    {
      "epoch": 0.7782426778242678,
      "grad_norm": 1.1520224898754043,
      "learning_rate": 1.4481838142385403e-05,
      "loss": 1.2454,
      "step": 279
    },
    {
      "epoch": 0.7810320781032078,
      "grad_norm": 1.3031384394432615,
      "learning_rate": 1.4440245517576141e-05,
      "loss": 1.4125,
      "step": 280
    },
    {
      "epoch": 0.7838214783821479,
      "grad_norm": 1.4528549714436811,
      "learning_rate": 1.4398556994102996e-05,
      "loss": 1.3641,
      "step": 281
    },
    {
      "epoch": 0.7866108786610879,
      "grad_norm": 1.4236584359239257,
      "learning_rate": 1.4356773472338174e-05,
      "loss": 1.48,
      "step": 282
    },
    {
      "epoch": 0.7894002789400278,
      "grad_norm": 1.4626745792933868,
      "learning_rate": 1.4314895854705641e-05,
      "loss": 1.4765,
      "step": 283
    },
    {
      "epoch": 0.7921896792189679,
      "grad_norm": 1.2910417535844496,
      "learning_rate": 1.4272925045661583e-05,
      "loss": 1.419,
      "step": 284
    },
    {
      "epoch": 0.7949790794979079,
      "grad_norm": 1.2373977812672998,
      "learning_rate": 1.4230861951674914e-05,
      "loss": 1.2251,
      "step": 285
    },
    {
      "epoch": 0.797768479776848,
      "grad_norm": 1.2785831952874724,
      "learning_rate": 1.4188707481207677e-05,
      "loss": 1.3471,
      "step": 286
    },
    {
      "epoch": 0.800557880055788,
      "grad_norm": 1.3683445048689633,
      "learning_rate": 1.4146462544695428e-05,
      "loss": 1.425,
      "step": 287
    },
    {
      "epoch": 0.803347280334728,
      "grad_norm": 1.1296732873251845,
      "learning_rate": 1.410412805452757e-05,
      "loss": 1.2578,
      "step": 288
    },
    {
      "epoch": 0.806136680613668,
      "grad_norm": 1.0829712122726374,
      "learning_rate": 1.4061704925027653e-05,
      "loss": 1.1799,
      "step": 289
    },
    {
      "epoch": 0.8089260808926081,
      "grad_norm": 1.3309074955401459,
      "learning_rate": 1.4019194072433626e-05,
      "loss": 1.1379,
      "step": 290
    },
    {
      "epoch": 0.8117154811715481,
      "grad_norm": 1.2343728023741232,
      "learning_rate": 1.3976596414878044e-05,
      "loss": 1.2411,
      "step": 291
    },
    {
      "epoch": 0.8145048814504882,
      "grad_norm": 1.214883458073917,
      "learning_rate": 1.393391287236824e-05,
      "loss": 1.3405,
      "step": 292
    },
    {
      "epoch": 0.8172942817294282,
      "grad_norm": 1.3091690676466778,
      "learning_rate": 1.3891144366766457e-05,
      "loss": 1.2606,
      "step": 293
    },
    {
      "epoch": 0.8200836820083682,
      "grad_norm": 13.631918339692971,
      "learning_rate": 1.3848291821769944e-05,
      "loss": 1.656,
      "step": 294
    },
    {
      "epoch": 0.8228730822873083,
      "grad_norm": 1.1657018881567924,
      "learning_rate": 1.380535616289099e-05,
      "loss": 1.2156,
      "step": 295
    },
    {
      "epoch": 0.8256624825662483,
      "grad_norm": 1.2347632552018992,
      "learning_rate": 1.3762338317436948e-05,
      "loss": 1.2669,
      "step": 296
    },
    {
      "epoch": 0.8284518828451883,
      "grad_norm": 1.4274262176368255,
      "learning_rate": 1.3719239214490203e-05,
      "loss": 1.3072,
      "step": 297
    },
    {
      "epoch": 0.8312412831241283,
      "grad_norm": 1.2894927915175798,
      "learning_rate": 1.3676059784888112e-05,
      "loss": 1.4573,
      "step": 298
    },
    {
      "epoch": 0.8340306834030683,
      "grad_norm": 1.4646947685259242,
      "learning_rate": 1.363280096120289e-05,
      "loss": 1.4956,
      "step": 299
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 1.2835331667441359,
      "learning_rate": 1.358946367772148e-05,
      "loss": 1.3713,
      "step": 300
    },
    {
      "epoch": 0.8396094839609484,
      "grad_norm": 1.3024578071081172,
      "learning_rate": 1.3546048870425356e-05,
      "loss": 1.345,
      "step": 301
    },
    {
      "epoch": 0.8423988842398884,
      "grad_norm": 1.144812031373234,
      "learning_rate": 1.3502557476970339e-05,
      "loss": 1.3447,
      "step": 302
    },
    {
      "epoch": 0.8451882845188284,
      "grad_norm": 1.255722753075089,
      "learning_rate": 1.3458990436666313e-05,
      "loss": 1.5169,
      "step": 303
    },
    {
      "epoch": 0.8479776847977685,
      "grad_norm": 1.1632268233137957,
      "learning_rate": 1.3415348690456955e-05,
      "loss": 1.289,
      "step": 304
    },
    {
      "epoch": 0.8507670850767085,
      "grad_norm": 1.2357758677374722,
      "learning_rate": 1.3371633180899417e-05,
      "loss": 1.4063,
      "step": 305
    },
    {
      "epoch": 0.8535564853556485,
      "grad_norm": 1.2854100609241097,
      "learning_rate": 1.3327844852143956e-05,
      "loss": 1.3677,
      "step": 306
    },
    {
      "epoch": 0.8563458856345886,
      "grad_norm": 1.2395591163738042,
      "learning_rate": 1.3283984649913552e-05,
      "loss": 1.3656,
      "step": 307
    },
    {
      "epoch": 0.8591352859135286,
      "grad_norm": 1.309692041297723,
      "learning_rate": 1.3240053521483483e-05,
      "loss": 1.3191,
      "step": 308
    },
    {
      "epoch": 0.8619246861924686,
      "grad_norm": 1.306594190283498,
      "learning_rate": 1.3196052415660856e-05,
      "loss": 1.2964,
      "step": 309
    },
    {
      "epoch": 0.8647140864714087,
      "grad_norm": 1.2332822767216993,
      "learning_rate": 1.3151982282764126e-05,
      "loss": 1.3172,
      "step": 310
    },
    {
      "epoch": 0.8675034867503487,
      "grad_norm": 1.2248947416069507,
      "learning_rate": 1.3107844074602566e-05,
      "loss": 1.2215,
      "step": 311
    },
    {
      "epoch": 0.8702928870292888,
      "grad_norm": 1.0883399467851869,
      "learning_rate": 1.3063638744455713e-05,
      "loss": 1.2487,
      "step": 312
    },
    {
      "epoch": 0.8730822873082287,
      "grad_norm": 1.3561694142459044,
      "learning_rate": 1.3019367247052781e-05,
      "loss": 1.5192,
      "step": 313
    },
    {
      "epoch": 0.8758716875871687,
      "grad_norm": 1.2195540202949509,
      "learning_rate": 1.297503053855203e-05,
      "loss": 1.315,
      "step": 314
    },
    {
      "epoch": 0.8786610878661087,
      "grad_norm": 1.2398989428685936,
      "learning_rate": 1.2930629576520133e-05,
      "loss": 1.2466,
      "step": 315
    },
    {
      "epoch": 0.8786610878661087,
      "eval_loss": 1.590497612953186,
      "eval_runtime": 158.7725,
      "eval_samples_per_second": 2.003,
      "eval_steps_per_second": 0.126,
      "step": 315
    },
    {
      "epoch": 0.8814504881450488,
      "grad_norm": 1.1820530696430398,
      "learning_rate": 1.2886165319911474e-05,
      "loss": 1.3187,
      "step": 316
    },
    {
      "epoch": 0.8842398884239888,
      "grad_norm": 1.2411796795161567,
      "learning_rate": 1.2841638729047463e-05,
      "loss": 1.3681,
      "step": 317
    },
    {
      "epoch": 0.8870292887029289,
      "grad_norm": 1.2561131847214293,
      "learning_rate": 1.2797050765595767e-05,
      "loss": 1.2601,
      "step": 318
    },
    {
      "epoch": 0.8898186889818689,
      "grad_norm": 1.415729283991149,
      "learning_rate": 1.2752402392549556e-05,
      "loss": 1.4896,
      "step": 319
    },
    {
      "epoch": 0.8926080892608089,
      "grad_norm": 1.3261631641702796,
      "learning_rate": 1.2707694574206712e-05,
      "loss": 1.5607,
      "step": 320
    },
    {
      "epoch": 0.895397489539749,
      "grad_norm": 1.240314237616232,
      "learning_rate": 1.2662928276148985e-05,
      "loss": 1.3429,
      "step": 321
    },
    {
      "epoch": 0.898186889818689,
      "grad_norm": 1.3000617526029077,
      "learning_rate": 1.2618104465221148e-05,
      "loss": 1.4272,
      "step": 322
    },
    {
      "epoch": 0.900976290097629,
      "grad_norm": 1.16464364915601,
      "learning_rate": 1.2573224109510112e-05,
      "loss": 1.2306,
      "step": 323
    },
    {
      "epoch": 0.9037656903765691,
      "grad_norm": 1.2109886144147917,
      "learning_rate": 1.2528288178324029e-05,
      "loss": 1.353,
      "step": 324
    },
    {
      "epoch": 0.9065550906555091,
      "grad_norm": 1.1714274928342496,
      "learning_rate": 1.2483297642171332e-05,
      "loss": 1.2997,
      "step": 325
    },
    {
      "epoch": 0.9093444909344491,
      "grad_norm": 1.1814072235776383,
      "learning_rate": 1.2438253472739805e-05,
      "loss": 1.3144,
      "step": 326
    },
    {
      "epoch": 0.9121338912133892,
      "grad_norm": 1.3461681399899779,
      "learning_rate": 1.2393156642875579e-05,
      "loss": 1.3618,
      "step": 327
    },
    {
      "epoch": 0.9149232914923291,
      "grad_norm": 1.456924757382429,
      "learning_rate": 1.234800812656212e-05,
      "loss": 1.3796,
      "step": 328
    },
    {
      "epoch": 0.9177126917712691,
      "grad_norm": 1.2321016000046479,
      "learning_rate": 1.23028088988992e-05,
      "loss": 1.3771,
      "step": 329
    },
    {
      "epoch": 0.9205020920502092,
      "grad_norm": 1.2405013760966828,
      "learning_rate": 1.2257559936081833e-05,
      "loss": 1.2744,
      "step": 330
    },
    {
      "epoch": 0.9232914923291492,
      "grad_norm": 1.2677524234506234,
      "learning_rate": 1.2212262215379199e-05,
      "loss": 1.3578,
      "step": 331
    },
    {
      "epoch": 0.9260808926080892,
      "grad_norm": 1.2230537842102542,
      "learning_rate": 1.2166916715113521e-05,
      "loss": 1.4323,
      "step": 332
    },
    {
      "epoch": 0.9288702928870293,
      "grad_norm": 1.2690522272930789,
      "learning_rate": 1.2121524414638958e-05,
      "loss": 1.2845,
      "step": 333
    },
    {
      "epoch": 0.9316596931659693,
      "grad_norm": 1.2822697397851108,
      "learning_rate": 1.207608629432043e-05,
      "loss": 1.6128,
      "step": 334
    },
    {
      "epoch": 0.9344490934449093,
      "grad_norm": 1.2997575387211082,
      "learning_rate": 1.2030603335512467e-05,
      "loss": 1.3401,
      "step": 335
    },
    {
      "epoch": 0.9372384937238494,
      "grad_norm": 1.5059463142396166,
      "learning_rate": 1.1985076520537995e-05,
      "loss": 1.2793,
      "step": 336
    },
    {
      "epoch": 0.9400278940027894,
      "grad_norm": 1.5118948746263785,
      "learning_rate": 1.1939506832667129e-05,
      "loss": 1.3152,
      "step": 337
    },
    {
      "epoch": 0.9428172942817294,
      "grad_norm": 1.2816385360112317,
      "learning_rate": 1.1893895256095937e-05,
      "loss": 1.4573,
      "step": 338
    },
    {
      "epoch": 0.9456066945606695,
      "grad_norm": 1.1973723679649781,
      "learning_rate": 1.1848242775925188e-05,
      "loss": 1.1473,
      "step": 339
    },
    {
      "epoch": 0.9483960948396095,
      "grad_norm": 1.157556800970344,
      "learning_rate": 1.180255037813906e-05,
      "loss": 1.362,
      "step": 340
    },
    {
      "epoch": 0.9511854951185496,
      "grad_norm": 1.3366940604017197,
      "learning_rate": 1.1756819049583861e-05,
      "loss": 1.5201,
      "step": 341
    },
    {
      "epoch": 0.9539748953974896,
      "grad_norm": 1.396951726353029,
      "learning_rate": 1.1711049777946717e-05,
      "loss": 1.4882,
      "step": 342
    },
    {
      "epoch": 0.9567642956764296,
      "grad_norm": 1.1789267346275334,
      "learning_rate": 1.166524355173422e-05,
      "loss": 1.3806,
      "step": 343
    },
    {
      "epoch": 0.9595536959553695,
      "grad_norm": 1.2075413726006268,
      "learning_rate": 1.1619401360251104e-05,
      "loss": 1.2451,
      "step": 344
    },
    {
      "epoch": 0.9623430962343096,
      "grad_norm": 1.2379647427390967,
      "learning_rate": 1.1573524193578863e-05,
      "loss": 1.1581,
      "step": 345
    },
    {
      "epoch": 0.9651324965132496,
      "grad_norm": 1.1953475180567759,
      "learning_rate": 1.1527613042554368e-05,
      "loss": 1.3765,
      "step": 346
    },
    {
      "epoch": 0.9679218967921897,
      "grad_norm": 1.2657967489739972,
      "learning_rate": 1.1481668898748474e-05,
      "loss": 1.335,
      "step": 347
    },
    {
      "epoch": 0.9707112970711297,
      "grad_norm": 1.2590876717921935,
      "learning_rate": 1.1435692754444604e-05,
      "loss": 1.339,
      "step": 348
    },
    {
      "epoch": 0.9735006973500697,
      "grad_norm": 1.3430351369524687,
      "learning_rate": 1.1389685602617302e-05,
      "loss": 1.3618,
      "step": 349
    },
    {
      "epoch": 0.9762900976290098,
      "grad_norm": 1.216928490077423,
      "learning_rate": 1.134364843691082e-05,
      "loss": 1.4504,
      "step": 350
    },
    {
      "epoch": 0.9790794979079498,
      "grad_norm": 1.2961172668976244,
      "learning_rate": 1.1297582251617618e-05,
      "loss": 1.3752,
      "step": 351
    },
    {
      "epoch": 0.9818688981868898,
      "grad_norm": 1.3163958626398011,
      "learning_rate": 1.1251488041656929e-05,
      "loss": 1.2906,
      "step": 352
    },
    {
      "epoch": 0.9846582984658299,
      "grad_norm": 1.2499583055181795,
      "learning_rate": 1.1205366802553231e-05,
      "loss": 1.3641,
      "step": 353
    },
    {
      "epoch": 0.9874476987447699,
      "grad_norm": 1.5088593864499633,
      "learning_rate": 1.1159219530414786e-05,
      "loss": 1.4534,
      "step": 354
    },
    {
      "epoch": 0.9902370990237099,
      "grad_norm": 1.1931538459250062,
      "learning_rate": 1.1113047221912097e-05,
      "loss": 1.3285,
      "step": 355
    },
    {
      "epoch": 0.99302649930265,
      "grad_norm": 1.1763206233025147,
      "learning_rate": 1.1066850874256387e-05,
      "loss": 1.3928,
      "step": 356
    },
    {
      "epoch": 0.99581589958159,
      "grad_norm": 1.2398324928784012,
      "learning_rate": 1.1020631485178084e-05,
      "loss": 1.4118,
      "step": 357
    },
    {
      "epoch": 0.99860529986053,
      "grad_norm": 1.1658511676647905,
      "learning_rate": 1.0974390052905238e-05,
      "loss": 1.2735,
      "step": 358
    }
  ],
  "logging_steps": 1,
  "max_steps": 716,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 179,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 233196591513600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}