{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9931630082763583,
  "eval_steps": 500,
  "global_step": 1041,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01439366678661389,
      "grad_norm": 1.0214840173721313,
      "learning_rate": 1.5625e-06,
      "loss": 0.9146,
      "num_input_tokens_seen": 1240480,
      "step": 5
    },
    {
      "epoch": 0.02878733357322778,
      "grad_norm": 0.475069522857666,
      "learning_rate": 3.125e-06,
      "loss": 0.8172,
      "num_input_tokens_seen": 2397024,
      "step": 10
    },
    {
      "epoch": 0.04318100035984167,
      "grad_norm": 0.3232167065143585,
      "learning_rate": 4.6875000000000004e-06,
      "loss": 0.6921,
      "num_input_tokens_seen": 3623360,
      "step": 15
    },
    {
      "epoch": 0.05757466714645556,
      "grad_norm": 0.2309960126876831,
      "learning_rate": 6.25e-06,
      "loss": 0.6478,
      "num_input_tokens_seen": 4870976,
      "step": 20
    },
    {
      "epoch": 0.07196833393306945,
      "grad_norm": 0.1785370409488678,
      "learning_rate": 7.8125e-06,
      "loss": 0.6081,
      "num_input_tokens_seen": 6076960,
      "step": 25
    },
    {
      "epoch": 0.08636200071968334,
      "grad_norm": 0.13996458053588867,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.5738,
      "num_input_tokens_seen": 7318432,
      "step": 30
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 0.13175447285175323,
      "learning_rate": 9.99978187935494e-06,
      "loss": 0.5458,
      "num_input_tokens_seen": 8531200,
      "step": 35
    },
    {
      "epoch": 0.11514933429291112,
      "grad_norm": 0.1529526263475418,
      "learning_rate": 9.998448988774289e-06,
      "loss": 0.5304,
      "num_input_tokens_seen": 9761312,
      "step": 40
    },
    {
      "epoch": 0.12954300107952502,
      "grad_norm": 0.12933316826820374,
      "learning_rate": 9.99590470838777e-06,
      "loss": 0.5233,
      "num_input_tokens_seen": 10987232,
      "step": 45
    },
    {
      "epoch": 0.1439366678661389,
      "grad_norm": 0.10383077710866928,
      "learning_rate": 9.99214965480972e-06,
      "loss": 0.5195,
      "num_input_tokens_seen": 12184224,
      "step": 50
    },
    {
      "epoch": 0.15833033465275279,
      "grad_norm": 0.11912256479263306,
      "learning_rate": 9.987184738089166e-06,
      "loss": 0.5125,
      "num_input_tokens_seen": 13438336,
      "step": 55
    },
    {
      "epoch": 0.17272400143936667,
      "grad_norm": 0.13026872277259827,
      "learning_rate": 9.981011161489262e-06,
      "loss": 0.5016,
      "num_input_tokens_seen": 14660448,
      "step": 60
    },
    {
      "epoch": 0.18711766822598058,
      "grad_norm": 0.10900898277759552,
      "learning_rate": 9.973630421195679e-06,
      "loss": 0.4932,
      "num_input_tokens_seen": 15853120,
      "step": 65
    },
    {
      "epoch": 0.20151133501259447,
      "grad_norm": 0.15866610407829285,
      "learning_rate": 9.965044305954002e-06,
      "loss": 0.4953,
      "num_input_tokens_seen": 17027072,
      "step": 70
    },
    {
      "epoch": 0.21590500179920835,
      "grad_norm": 0.11282581090927124,
      "learning_rate": 9.955254896636217e-06,
      "loss": 0.4879,
      "num_input_tokens_seen": 18301280,
      "step": 75
    },
    {
      "epoch": 0.23029866858582224,
      "grad_norm": 0.10046873986721039,
      "learning_rate": 9.944264565736406e-06,
      "loss": 0.4921,
      "num_input_tokens_seen": 19521248,
      "step": 80
    },
    {
      "epoch": 0.24469233537243612,
      "grad_norm": 0.13294290006160736,
      "learning_rate": 9.93207597679577e-06,
      "loss": 0.4872,
      "num_input_tokens_seen": 20743808,
      "step": 85
    },
    {
      "epoch": 0.25908600215905003,
      "grad_norm": 0.1502200961112976,
      "learning_rate": 9.918692083757105e-06,
      "loss": 0.4829,
      "num_input_tokens_seen": 21961824,
      "step": 90
    },
    {
      "epoch": 0.2734796689456639,
      "grad_norm": 0.11316563934087753,
      "learning_rate": 9.904116130248913e-06,
      "loss": 0.4777,
      "num_input_tokens_seen": 23150816,
      "step": 95
    },
    {
      "epoch": 0.2878733357322778,
      "grad_norm": 0.11878542602062225,
      "learning_rate": 9.888351648799288e-06,
      "loss": 0.4782,
      "num_input_tokens_seen": 24360448,
      "step": 100
    },
    {
      "epoch": 0.3022670025188917,
      "grad_norm": 0.1249440461397171,
      "learning_rate": 9.871402459979804e-06,
      "loss": 0.484,
      "num_input_tokens_seen": 25560064,
      "step": 105
    },
    {
      "epoch": 0.31666066930550557,
      "grad_norm": 0.10779324918985367,
      "learning_rate": 9.853272671479588e-06,
      "loss": 0.4751,
      "num_input_tokens_seen": 26779424,
      "step": 110
    },
    {
      "epoch": 0.3310543360921195,
      "grad_norm": 0.11084678769111633,
      "learning_rate": 9.833966677109805e-06,
      "loss": 0.4738,
      "num_input_tokens_seen": 27980288,
      "step": 115
    },
    {
      "epoch": 0.34544800287873334,
      "grad_norm": 0.1316342055797577,
      "learning_rate": 9.813489155738801e-06,
      "loss": 0.4711,
      "num_input_tokens_seen": 29204832,
      "step": 120
    },
    {
      "epoch": 0.35984166966534725,
      "grad_norm": 0.12607069313526154,
      "learning_rate": 9.791845070158175e-06,
      "loss": 0.4751,
      "num_input_tokens_seen": 30402752,
      "step": 125
    },
    {
      "epoch": 0.37423533645196116,
      "grad_norm": 0.10768567770719528,
      "learning_rate": 9.769039665880024e-06,
      "loss": 0.4657,
      "num_input_tokens_seen": 31630400,
      "step": 130
    },
    {
      "epoch": 0.388629003238575,
      "grad_norm": 0.11599580943584442,
      "learning_rate": 9.745078469865673e-06,
      "loss": 0.463,
      "num_input_tokens_seen": 32874304,
      "step": 135
    },
    {
      "epoch": 0.40302267002518893,
      "grad_norm": 0.12043242156505585,
      "learning_rate": 9.719967289186211e-06,
      "loss": 0.4666,
      "num_input_tokens_seen": 34078112,
      "step": 140
    },
    {
      "epoch": 0.4174163368118028,
      "grad_norm": 0.11133189499378204,
      "learning_rate": 9.69371220961511e-06,
      "loss": 0.4615,
      "num_input_tokens_seen": 35299040,
      "step": 145
    },
    {
      "epoch": 0.4318100035984167,
      "grad_norm": 0.1204451248049736,
      "learning_rate": 9.666319594153342e-06,
      "loss": 0.4652,
      "num_input_tokens_seen": 36450240,
      "step": 150
    },
    {
      "epoch": 0.44620367038503056,
      "grad_norm": 0.12066318839788437,
      "learning_rate": 9.637796081487263e-06,
      "loss": 0.4584,
      "num_input_tokens_seen": 37670272,
      "step": 155
    },
    {
      "epoch": 0.46059733717164447,
      "grad_norm": 0.12192081660032272,
      "learning_rate": 9.608148584379724e-06,
      "loss": 0.461,
      "num_input_tokens_seen": 38859744,
      "step": 160
    },
    {
      "epoch": 0.4749910039582584,
      "grad_norm": 0.11063596606254578,
      "learning_rate": 9.577384287994733e-06,
      "loss": 0.4582,
      "num_input_tokens_seen": 40089728,
      "step": 165
    },
    {
      "epoch": 0.48938467074487224,
      "grad_norm": 0.10572189092636108,
      "learning_rate": 9.545510648156106e-06,
      "loss": 0.457,
      "num_input_tokens_seen": 41284672,
      "step": 170
    },
    {
      "epoch": 0.5037783375314862,
      "grad_norm": 0.11127395927906036,
      "learning_rate": 9.512535389540532e-06,
      "loss": 0.4563,
      "num_input_tokens_seen": 42485632,
      "step": 175
    },
    {
      "epoch": 0.5181720043181001,
      "grad_norm": 0.12806196510791779,
      "learning_rate": 9.478466503805467e-06,
      "loss": 0.4591,
      "num_input_tokens_seen": 43713984,
      "step": 180
    },
    {
      "epoch": 0.532565671104714,
      "grad_norm": 0.12148015946149826,
      "learning_rate": 9.443312247652335e-06,
      "loss": 0.4583,
      "num_input_tokens_seen": 44924864,
      "step": 185
    },
    {
      "epoch": 0.5469593378913278,
      "grad_norm": 0.10408366471529007,
      "learning_rate": 9.407081140825485e-06,
      "loss": 0.4599,
      "num_input_tokens_seen": 46109888,
      "step": 190
    },
    {
      "epoch": 0.5613530046779417,
      "grad_norm": 0.10397111624479294,
      "learning_rate": 9.36978196404741e-06,
      "loss": 0.4528,
      "num_input_tokens_seen": 47321504,
      "step": 195
    },
    {
      "epoch": 0.5757466714645556,
      "grad_norm": 0.10475903004407883,
      "learning_rate": 9.331423756890715e-06,
      "loss": 0.4518,
      "num_input_tokens_seen": 48522688,
      "step": 200
    },
    {
      "epoch": 0.5901403382511695,
      "grad_norm": 0.10798915475606918,
      "learning_rate": 9.292015815587326e-06,
      "loss": 0.4503,
      "num_input_tokens_seen": 49713504,
      "step": 205
    },
    {
      "epoch": 0.6045340050377834,
      "grad_norm": 0.10996194183826447,
      "learning_rate": 9.251567690775554e-06,
      "loss": 0.4603,
      "num_input_tokens_seen": 50893088,
      "step": 210
    },
    {
      "epoch": 0.6189276718243972,
      "grad_norm": 0.11249005049467087,
      "learning_rate": 9.210089185185436e-06,
      "loss": 0.4513,
      "num_input_tokens_seen": 52104832,
      "step": 215
    },
    {
      "epoch": 0.6333213386110111,
      "grad_norm": 0.10022589564323425,
      "learning_rate": 9.167590351263031e-06,
      "loss": 0.4492,
      "num_input_tokens_seen": 53348352,
      "step": 220
    },
    {
      "epoch": 0.647715005397625,
      "grad_norm": 0.13220378756523132,
      "learning_rate": 9.124081488734173e-06,
      "loss": 0.4562,
      "num_input_tokens_seen": 54523200,
      "step": 225
    },
    {
      "epoch": 0.662108672184239,
      "grad_norm": 0.1318250149488449,
      "learning_rate": 9.0795731421083e-06,
      "loss": 0.4452,
      "num_input_tokens_seen": 55728384,
      "step": 230
    },
    {
      "epoch": 0.6765023389708529,
      "grad_norm": 0.10970500111579895,
      "learning_rate": 9.034076098122954e-06,
      "loss": 0.4451,
      "num_input_tokens_seen": 56932096,
      "step": 235
    },
    {
      "epoch": 0.6908960057574667,
      "grad_norm": 0.11423052847385406,
      "learning_rate": 8.987601383129597e-06,
      "loss": 0.4531,
      "num_input_tokens_seen": 58107968,
      "step": 240
    },
    {
      "epoch": 0.7052896725440806,
      "grad_norm": 0.12971928715705872,
      "learning_rate": 8.940160260421315e-06,
      "loss": 0.4505,
      "num_input_tokens_seen": 59324416,
      "step": 245
    },
    {
      "epoch": 0.7196833393306945,
      "grad_norm": 0.12477336823940277,
      "learning_rate": 8.891764227503148e-06,
      "loss": 0.448,
      "num_input_tokens_seen": 60542240,
      "step": 250
    },
    {
      "epoch": 0.7340770061173084,
      "grad_norm": 0.11958134919404984,
      "learning_rate": 8.842425013305624e-06,
      "loss": 0.4509,
      "num_input_tokens_seen": 61732096,
      "step": 255
    },
    {
      "epoch": 0.7484706729039223,
      "grad_norm": 0.10917840152978897,
      "learning_rate": 8.79215457534221e-06,
      "loss": 0.4465,
      "num_input_tokens_seen": 62949440,
      "step": 260
    },
    {
      "epoch": 0.7628643396905361,
      "grad_norm": 0.10279432684183121,
      "learning_rate": 8.740965096811376e-06,
      "loss": 0.4436,
      "num_input_tokens_seen": 64154464,
      "step": 265
    },
    {
      "epoch": 0.77725800647715,
      "grad_norm": 0.12088657170534134,
      "learning_rate": 8.688868983643966e-06,
      "loss": 0.4484,
      "num_input_tokens_seen": 65376000,
      "step": 270
    },
    {
      "epoch": 0.791651673263764,
      "grad_norm": 0.13277366757392883,
      "learning_rate": 8.635878861496566e-06,
      "loss": 0.442,
      "num_input_tokens_seen": 66594912,
      "step": 275
    },
    {
      "epoch": 0.8060453400503779,
      "grad_norm": 0.10281939804553986,
      "learning_rate": 8.582007572691655e-06,
      "loss": 0.4483,
      "num_input_tokens_seen": 67815136,
      "step": 280
    },
    {
      "epoch": 0.8204390068369917,
      "grad_norm": 0.13440336287021637,
      "learning_rate": 8.52726817310521e-06,
      "loss": 0.4453,
      "num_input_tokens_seen": 69019008,
      "step": 285
    },
    {
      "epoch": 0.8348326736236056,
      "grad_norm": 0.13226255774497986,
      "learning_rate": 8.47167392900258e-06,
      "loss": 0.4424,
      "num_input_tokens_seen": 70229728,
      "step": 290
    },
    {
      "epoch": 0.8492263404102195,
      "grad_norm": 0.09749466180801392,
      "learning_rate": 8.415238313823375e-06,
      "loss": 0.4455,
      "num_input_tokens_seen": 71451872,
      "step": 295
    },
    {
      "epoch": 0.8636200071968334,
      "grad_norm": 0.11040599644184113,
      "learning_rate": 8.357975004916122e-06,
      "loss": 0.4458,
      "num_input_tokens_seen": 72666880,
      "step": 300
    },
    {
      "epoch": 0.8780136739834473,
      "grad_norm": 0.10494755953550339,
      "learning_rate": 8.29989788022352e-06,
      "loss": 0.4368,
      "num_input_tokens_seen": 73877280,
      "step": 305
    },
    {
      "epoch": 0.8924073407700611,
      "grad_norm": 0.10199465602636337,
      "learning_rate": 8.241021014919085e-06,
      "loss": 0.4459,
      "num_input_tokens_seen": 75077376,
      "step": 310
    },
    {
      "epoch": 0.906801007556675,
      "grad_norm": 0.10417100787162781,
      "learning_rate": 8.18135867799597e-06,
      "loss": 0.4337,
      "num_input_tokens_seen": 76306272,
      "step": 315
    },
    {
      "epoch": 0.9211946743432889,
      "grad_norm": 0.1151595264673233,
      "learning_rate": 8.120925328808855e-06,
      "loss": 0.4331,
      "num_input_tokens_seen": 77524064,
      "step": 320
    },
    {
      "epoch": 0.9355883411299029,
      "grad_norm": 0.10500200092792511,
      "learning_rate": 8.059735613569651e-06,
      "loss": 0.4402,
      "num_input_tokens_seen": 78767008,
      "step": 325
    },
    {
      "epoch": 0.9499820079165168,
      "grad_norm": 0.1009892076253891,
      "learning_rate": 7.997804361797964e-06,
      "loss": 0.4347,
      "num_input_tokens_seen": 79976224,
      "step": 330
    },
    {
      "epoch": 0.9643756747031306,
      "grad_norm": 0.10055464506149292,
      "learning_rate": 7.935146582727103e-06,
      "loss": 0.4299,
      "num_input_tokens_seen": 81179744,
      "step": 335
    },
    {
      "epoch": 0.9787693414897445,
      "grad_norm": 0.09627791494131088,
      "learning_rate": 7.87177746166655e-06,
      "loss": 0.4406,
      "num_input_tokens_seen": 82421728,
      "step": 340
    },
    {
      "epoch": 0.9931630082763584,
      "grad_norm": 0.0970565527677536,
      "learning_rate": 7.80771235632175e-06,
      "loss": 0.4333,
      "num_input_tokens_seen": 83667872,
      "step": 345
    },
    {
      "epoch": 1.0057574667146456,
      "grad_norm": 0.10532606393098831,
      "learning_rate": 7.742966793072131e-06,
      "loss": 0.4076,
      "num_input_tokens_seen": 84747232,
      "step": 350
    },
    {
      "epoch": 1.0201511335012594,
      "grad_norm": 0.10900352895259857,
      "learning_rate": 7.677556463208221e-06,
      "loss": 0.3863,
      "num_input_tokens_seen": 85987392,
      "step": 355
    },
    {
      "epoch": 1.0345448002878734,
      "grad_norm": 0.11330895870923996,
      "learning_rate": 7.61149721912883e-06,
      "loss": 0.3805,
      "num_input_tokens_seen": 87212704,
      "step": 360
    },
    {
      "epoch": 1.0489384670744872,
      "grad_norm": 0.11470327526330948,
      "learning_rate": 7.544805070499166e-06,
      "loss": 0.3799,
      "num_input_tokens_seen": 88400096,
      "step": 365
    },
    {
      "epoch": 1.063332133861101,
      "grad_norm": 0.1176501214504242,
      "learning_rate": 7.477496180370838e-06,
      "loss": 0.381,
      "num_input_tokens_seen": 89591552,
      "step": 370
    },
    {
      "epoch": 1.077725800647715,
      "grad_norm": 0.12060599029064178,
      "learning_rate": 7.409586861264696e-06,
      "loss": 0.3752,
      "num_input_tokens_seen": 90780256,
      "step": 375
    },
    {
      "epoch": 1.0921194674343289,
      "grad_norm": 0.10595366358757019,
      "learning_rate": 7.3410935712174405e-06,
      "loss": 0.3802,
      "num_input_tokens_seen": 92002336,
      "step": 380
    },
    {
      "epoch": 1.1065131342209429,
      "grad_norm": 0.10483892261981964,
      "learning_rate": 7.272032909792956e-06,
      "loss": 0.3793,
      "num_input_tokens_seen": 93204768,
      "step": 385
    },
    {
      "epoch": 1.1209068010075567,
      "grad_norm": 0.12083030492067337,
      "learning_rate": 7.202421614059369e-06,
      "loss": 0.3838,
      "num_input_tokens_seen": 94432192,
      "step": 390
    },
    {
      "epoch": 1.1353004677941705,
      "grad_norm": 0.1196521520614624,
      "learning_rate": 7.1322765545327555e-06,
      "loss": 0.3872,
      "num_input_tokens_seen": 95644192,
      "step": 395
    },
    {
      "epoch": 1.1496941345807845,
      "grad_norm": 0.11427479237318039,
      "learning_rate": 7.061614731088523e-06,
      "loss": 0.3776,
      "num_input_tokens_seen": 96819104,
      "step": 400
    },
    {
      "epoch": 1.1640878013673983,
      "grad_norm": 0.11880994588136673,
      "learning_rate": 6.990453268841438e-06,
      "loss": 0.3771,
      "num_input_tokens_seen": 98050560,
      "step": 405
    },
    {
      "epoch": 1.1784814681540121,
      "grad_norm": 0.10391561686992645,
      "learning_rate": 6.918809413995299e-06,
      "loss": 0.3793,
      "num_input_tokens_seen": 99292864,
      "step": 410
    },
    {
      "epoch": 1.1928751349406261,
      "grad_norm": 0.10131582617759705,
      "learning_rate": 6.846700529663265e-06,
      "loss": 0.3767,
      "num_input_tokens_seen": 100474048,
      "step": 415
    },
    {
      "epoch": 1.20726880172724,
      "grad_norm": 0.1006164476275444,
      "learning_rate": 6.774144091659853e-06,
      "loss": 0.3768,
      "num_input_tokens_seen": 101683712,
      "step": 420
    },
    {
      "epoch": 1.221662468513854,
      "grad_norm": 0.10323438048362732,
      "learning_rate": 6.701157684265613e-06,
      "loss": 0.3778,
      "num_input_tokens_seen": 102922816,
      "step": 425
    },
    {
      "epoch": 1.2360561353004678,
      "grad_norm": 0.09887879341840744,
      "learning_rate": 6.627758995965533e-06,
      "loss": 0.3802,
      "num_input_tokens_seen": 104093952,
      "step": 430
    },
    {
      "epoch": 1.2504498020870818,
      "grad_norm": 0.11751233041286469,
      "learning_rate": 6.553965815162167e-06,
      "loss": 0.3718,
      "num_input_tokens_seen": 105313952,
      "step": 435
    },
    {
      "epoch": 1.2648434688736956,
      "grad_norm": 0.1086726263165474,
      "learning_rate": 6.479796025864569e-06,
      "loss": 0.3824,
      "num_input_tokens_seen": 106505824,
      "step": 440
    },
    {
      "epoch": 1.2792371356603094,
      "grad_norm": 0.09921428561210632,
      "learning_rate": 6.405267603354044e-06,
      "loss": 0.3766,
      "num_input_tokens_seen": 107740352,
      "step": 445
    },
    {
      "epoch": 1.2936308024469234,
      "grad_norm": 0.10828100889921188,
      "learning_rate": 6.330398609827779e-06,
      "loss": 0.3771,
      "num_input_tokens_seen": 108944672,
      "step": 450
    },
    {
      "epoch": 1.3080244692335372,
      "grad_norm": 0.10449640452861786,
      "learning_rate": 6.255207190021421e-06,
      "loss": 0.3868,
      "num_input_tokens_seen": 110131648,
      "step": 455
    },
    {
      "epoch": 1.322418136020151,
      "grad_norm": 0.10954560339450836,
      "learning_rate": 6.179711566811637e-06,
      "loss": 0.3847,
      "num_input_tokens_seen": 111328928,
      "step": 460
    },
    {
      "epoch": 1.336811802806765,
      "grad_norm": 0.10776536911725998,
      "learning_rate": 6.103930036799739e-06,
      "loss": 0.3837,
      "num_input_tokens_seen": 112536736,
      "step": 465
    },
    {
      "epoch": 1.3512054695933788,
      "grad_norm": 0.1020272821187973,
      "learning_rate": 6.027880965877457e-06,
      "loss": 0.3859,
      "num_input_tokens_seen": 113781920,
      "step": 470
    },
    {
      "epoch": 1.3655991363799929,
      "grad_norm": 0.1073663979768753,
      "learning_rate": 5.951582784775896e-06,
      "loss": 0.3818,
      "num_input_tokens_seen": 114977472,
      "step": 475
    },
    {
      "epoch": 1.3799928031666067,
      "grad_norm": 0.10786911100149155,
      "learning_rate": 5.8750539845987945e-06,
      "loss": 0.37,
      "num_input_tokens_seen": 116230592,
      "step": 480
    },
    {
      "epoch": 1.3943864699532207,
      "grad_norm": 0.11124595999717712,
      "learning_rate": 5.798313112341153e-06,
      "loss": 0.3773,
      "num_input_tokens_seen": 117467008,
      "step": 485
    },
    {
      "epoch": 1.4087801367398345,
      "grad_norm": 0.1033550277352333,
      "learning_rate": 5.721378766394301e-06,
      "loss": 0.3781,
      "num_input_tokens_seen": 118690144,
      "step": 490
    },
    {
      "epoch": 1.4231738035264483,
      "grad_norm": 0.10887488722801208,
      "learning_rate": 5.644269592038528e-06,
      "loss": 0.383,
      "num_input_tokens_seen": 119904320,
      "step": 495
    },
    {
      "epoch": 1.4375674703130623,
      "grad_norm": 0.10842526704072952,
      "learning_rate": 5.5670042769243375e-06,
      "loss": 0.3759,
      "num_input_tokens_seen": 121132128,
      "step": 500
    },
    {
      "epoch": 1.4519611370996761,
      "grad_norm": 0.0980478897690773,
      "learning_rate": 5.48960154654343e-06,
      "loss": 0.3734,
      "num_input_tokens_seen": 122349408,
      "step": 505
    },
    {
      "epoch": 1.46635480388629,
      "grad_norm": 0.10210393369197845,
      "learning_rate": 5.412080159690537e-06,
      "loss": 0.3795,
      "num_input_tokens_seen": 123537536,
      "step": 510
    },
    {
      "epoch": 1.480748470672904,
      "grad_norm": 0.10420146584510803,
      "learning_rate": 5.33445890391715e-06,
      "loss": 0.3792,
      "num_input_tokens_seen": 124709248,
      "step": 515
    },
    {
      "epoch": 1.4951421374595177,
      "grad_norm": 0.10233873873949051,
      "learning_rate": 5.25675659097831e-06,
      "loss": 0.3721,
      "num_input_tokens_seen": 125913408,
      "step": 520
    },
    {
      "epoch": 1.5095358042461315,
      "grad_norm": 0.10815870761871338,
      "learning_rate": 5.178992052273519e-06,
      "loss": 0.3841,
      "num_input_tokens_seen": 127107008,
      "step": 525
    },
    {
      "epoch": 1.5239294710327456,
      "grad_norm": 0.10206011682748795,
      "learning_rate": 5.101184134282884e-06,
      "loss": 0.373,
      "num_input_tokens_seen": 128372736,
      "step": 530
    },
    {
      "epoch": 1.5383231378193596,
      "grad_norm": 0.1002277061343193,
      "learning_rate": 5.023351693999621e-06,
      "loss": 0.3772,
      "num_input_tokens_seen": 129618848,
      "step": 535
    },
    {
      "epoch": 1.5527168046059734,
      "grad_norm": 0.1116589903831482,
      "learning_rate": 4.945513594360001e-06,
      "loss": 0.3786,
      "num_input_tokens_seen": 130818912,
      "step": 540
    },
    {
      "epoch": 1.5671104713925872,
      "grad_norm": 0.10507272183895111,
      "learning_rate": 4.867688699671857e-06,
      "loss": 0.3807,
      "num_input_tokens_seen": 132019616,
      "step": 545
    },
    {
      "epoch": 1.5815041381792012,
      "grad_norm": 0.10773016512393951,
      "learning_rate": 4.78989587104276e-06,
      "loss": 0.3773,
      "num_input_tokens_seen": 133242144,
      "step": 550
    },
    {
      "epoch": 1.595897804965815,
      "grad_norm": 0.1000257357954979,
      "learning_rate": 4.712153961808974e-06,
      "loss": 0.3736,
      "num_input_tokens_seen": 134440576,
      "step": 555
    },
    {
      "epoch": 1.6102914717524288,
      "grad_norm": 0.10357368737459183,
      "learning_rate": 4.63448181296628e-06,
      "loss": 0.3789,
      "num_input_tokens_seen": 135708768,
      "step": 560
    },
    {
      "epoch": 1.6246851385390428,
      "grad_norm": 0.09995976090431213,
      "learning_rate": 4.556898248603818e-06,
      "loss": 0.3801,
      "num_input_tokens_seen": 136928352,
      "step": 565
    },
    {
      "epoch": 1.6390788053256569,
      "grad_norm": 0.1011834666132927,
      "learning_rate": 4.479422071341996e-06,
      "loss": 0.3804,
      "num_input_tokens_seen": 138120128,
      "step": 570
    },
    {
      "epoch": 1.6534724721122704,
      "grad_norm": 0.10295307636260986,
      "learning_rate": 4.402072057775625e-06,
      "loss": 0.3731,
      "num_input_tokens_seen": 139336480,
      "step": 575
    },
    {
      "epoch": 1.6678661388988845,
      "grad_norm": 0.09975818544626236,
      "learning_rate": 4.324866953923343e-06,
      "loss": 0.3789,
      "num_input_tokens_seen": 140528544,
      "step": 580
    },
    {
      "epoch": 1.6822598056854985,
      "grad_norm": 0.09129153937101364,
      "learning_rate": 4.247825470684465e-06,
      "loss": 0.3764,
      "num_input_tokens_seen": 141746560,
      "step": 585
    },
    {
      "epoch": 1.6966534724721123,
      "grad_norm": 0.10817902535200119,
      "learning_rate": 4.170966279304343e-06,
      "loss": 0.3741,
      "num_input_tokens_seen": 142933792,
      "step": 590
    },
    {
      "epoch": 1.711047139258726,
      "grad_norm": 0.11920620501041412,
      "learning_rate": 4.094308006849314e-06,
      "loss": 0.3802,
      "num_input_tokens_seen": 144111456,
      "step": 595
    },
    {
      "epoch": 1.7254408060453401,
      "grad_norm": 0.10348640382289886,
      "learning_rate": 4.017869231692393e-06,
      "loss": 0.3774,
      "num_input_tokens_seen": 145318496,
      "step": 600
    },
    {
      "epoch": 1.739834472831954,
      "grad_norm": 0.10243242233991623,
      "learning_rate": 3.9416684790107315e-06,
      "loss": 0.3725,
      "num_input_tokens_seen": 146541952,
      "step": 605
    },
    {
      "epoch": 1.7542281396185677,
      "grad_norm": 0.10134383291006088,
      "learning_rate": 3.8657242162959845e-06,
      "loss": 0.3757,
      "num_input_tokens_seen": 147728864,
      "step": 610
    },
    {
      "epoch": 1.7686218064051817,
      "grad_norm": 0.10570108890533447,
      "learning_rate": 3.79005484887866e-06,
      "loss": 0.3741,
      "num_input_tokens_seen": 148941088,
      "step": 615
    },
    {
      "epoch": 1.7830154731917958,
      "grad_norm": 0.10352888703346252,
      "learning_rate": 3.714678715467529e-06,
      "loss": 0.3694,
      "num_input_tokens_seen": 150161408,
      "step": 620
    },
    {
      "epoch": 1.7974091399784093,
      "grad_norm": 0.09657809138298035,
      "learning_rate": 3.639614083705178e-06,
      "loss": 0.3676,
      "num_input_tokens_seen": 151362176,
      "step": 625
    },
    {
      "epoch": 1.8118028067650234,
      "grad_norm": 0.1007281169295311,
      "learning_rate": 3.564879145740794e-06,
      "loss": 0.371,
      "num_input_tokens_seen": 152549184,
      "step": 630
    },
    {
      "epoch": 1.8261964735516374,
      "grad_norm": 0.10473567992448807,
      "learning_rate": 3.490492013821234e-06,
      "loss": 0.3729,
      "num_input_tokens_seen": 153744384,
      "step": 635
    },
    {
      "epoch": 1.8405901403382512,
      "grad_norm": 0.09475262463092804,
      "learning_rate": 3.4164707159014675e-06,
      "loss": 0.369,
      "num_input_tokens_seen": 154973728,
      "step": 640
    },
    {
      "epoch": 1.854983807124865,
      "grad_norm": 0.10151992738246918,
      "learning_rate": 3.3428331912754507e-06,
      "loss": 0.3725,
      "num_input_tokens_seen": 156199072,
      "step": 645
    },
    {
      "epoch": 1.869377473911479,
      "grad_norm": 0.10508298873901367,
      "learning_rate": 3.2695972862284707e-06,
      "loss": 0.3733,
      "num_input_tokens_seen": 157402656,
      "step": 650
    },
    {
      "epoch": 1.8837711406980928,
      "grad_norm": 0.09837855398654938,
      "learning_rate": 3.196780749712054e-06,
      "loss": 0.3755,
      "num_input_tokens_seen": 158615680,
      "step": 655
    },
    {
      "epoch": 1.8981648074847066,
      "grad_norm": 0.09219809621572495,
      "learning_rate": 3.124401229042443e-06,
      "loss": 0.3739,
      "num_input_tokens_seen": 159830240,
      "step": 660
    },
    {
      "epoch": 1.9125584742713206,
      "grad_norm": 0.09680496156215668,
      "learning_rate": 3.0524762656237184e-06,
      "loss": 0.3714,
      "num_input_tokens_seen": 161025824,
      "step": 665
    },
    {
      "epoch": 1.9269521410579347,
      "grad_norm": 0.0969412550330162,
      "learning_rate": 2.9810232906965875e-06,
      "loss": 0.3707,
      "num_input_tokens_seen": 162207360,
      "step": 670
    },
    {
      "epoch": 1.9413458078445482,
      "grad_norm": 0.09519021958112717,
      "learning_rate": 2.9100596211138576e-06,
      "loss": 0.3675,
      "num_input_tokens_seen": 163384480,
      "step": 675
    },
    {
      "epoch": 1.9557394746311623,
      "grad_norm": 0.09750841557979584,
      "learning_rate": 2.83960245514366e-06,
      "loss": 0.3704,
      "num_input_tokens_seen": 164611232,
      "step": 680
    },
    {
      "epoch": 1.9701331414177763,
      "grad_norm": 0.09743023663759232,
      "learning_rate": 2.769668868301374e-06,
      "loss": 0.3658,
      "num_input_tokens_seen": 165857696,
      "step": 685
    },
    {
      "epoch": 1.98452680820439,
      "grad_norm": 0.10027555376291275,
      "learning_rate": 2.700275809211343e-06,
      "loss": 0.3643,
      "num_input_tokens_seen": 167098336,
      "step": 690
    },
    {
      "epoch": 1.998920474991004,
      "grad_norm": 0.09504663944244385,
      "learning_rate": 2.631440095499306e-06,
      "loss": 0.3626,
      "num_input_tokens_seen": 168300736,
      "step": 695
    },
    {
      "epoch": 2.011514933429291,
      "grad_norm": 0.11261429637670517,
      "learning_rate": 2.5631784097166024e-06,
      "loss": 0.3239,
      "num_input_tokens_seen": 169343264,
      "step": 700
    },
    {
      "epoch": 2.025908600215905,
      "grad_norm": 0.11092143505811691,
      "learning_rate": 2.4955072952970993e-06,
      "loss": 0.3109,
      "num_input_tokens_seen": 170576192,
      "step": 705
    },
    {
      "epoch": 2.040302267002519,
      "grad_norm": 0.12123912572860718,
      "learning_rate": 2.42844315254784e-06,
      "loss": 0.3083,
      "num_input_tokens_seen": 171781632,
      "step": 710
    },
    {
      "epoch": 2.054695933789133,
      "grad_norm": 0.11479540914297104,
      "learning_rate": 2.3620022346743816e-06,
      "loss": 0.3082,
      "num_input_tokens_seen": 172974464,
      "step": 715
    },
    {
      "epoch": 2.069089600575747,
      "grad_norm": 0.10446789115667343,
      "learning_rate": 2.2962006438417704e-06,
      "loss": 0.3113,
      "num_input_tokens_seen": 174197600,
      "step": 720
    },
    {
      "epoch": 2.0834832673623604,
      "grad_norm": 0.1093619093298912,
      "learning_rate": 2.231054327272141e-06,
      "loss": 0.3102,
      "num_input_tokens_seen": 175415360,
      "step": 725
    },
    {
      "epoch": 2.0978769341489745,
      "grad_norm": 0.10571351647377014,
      "learning_rate": 2.1665790733798497e-06,
      "loss": 0.3129,
      "num_input_tokens_seen": 176627200,
      "step": 730
    },
    {
      "epoch": 2.1122706009355885,
      "grad_norm": 0.10386540740728378,
      "learning_rate": 2.102790507945107e-06,
      "loss": 0.3067,
      "num_input_tokens_seen": 177826976,
      "step": 735
    },
    {
      "epoch": 2.126664267722202,
      "grad_norm": 0.10108942538499832,
      "learning_rate": 2.039704090327024e-06,
      "loss": 0.3052,
      "num_input_tokens_seen": 179065664,
      "step": 740
    },
    {
      "epoch": 2.141057934508816,
      "grad_norm": 0.10597535222768784,
      "learning_rate": 1.9773351097169785e-06,
      "loss": 0.3104,
      "num_input_tokens_seen": 180285536,
      "step": 745
    },
    {
      "epoch": 2.15545160129543,
      "grad_norm": 0.09962257742881775,
      "learning_rate": 1.9156986814332374e-06,
      "loss": 0.3179,
      "num_input_tokens_seen": 181495008,
      "step": 750
    },
    {
      "epoch": 2.1698452680820437,
      "grad_norm": 0.10941269993782043,
      "learning_rate": 1.8548097432577162e-06,
      "loss": 0.3141,
      "num_input_tokens_seen": 182681024,
      "step": 755
    },
    {
      "epoch": 2.1842389348686577,
      "grad_norm": 0.10274635255336761,
      "learning_rate": 1.7946830518157505e-06,
      "loss": 0.3113,
      "num_input_tokens_seen": 183919808,
      "step": 760
    },
    {
      "epoch": 2.1986326016552717,
      "grad_norm": 0.10398633778095245,
      "learning_rate": 1.7353331789997869e-06,
      "loss": 0.3089,
      "num_input_tokens_seen": 185115616,
      "step": 765
    },
    {
      "epoch": 2.2130262684418858,
      "grad_norm": 0.1012880951166153,
      "learning_rate": 1.6767745084378445e-06,
      "loss": 0.3148,
      "num_input_tokens_seen": 186305184,
      "step": 770
    },
    {
      "epoch": 2.2274199352284993,
      "grad_norm": 0.10060971975326538,
      "learning_rate": 1.6190212320075871e-06,
      "loss": 0.3089,
      "num_input_tokens_seen": 187513568,
      "step": 775
    },
    {
      "epoch": 2.2418136020151134,
      "grad_norm": 0.09719246625900269,
      "learning_rate": 1.5620873463968827e-06,
      "loss": 0.3027,
      "num_input_tokens_seen": 188744736,
      "step": 780
    },
    {
      "epoch": 2.2562072688017274,
      "grad_norm": 0.10270486027002335,
      "learning_rate": 1.5059866497116627e-06,
      "loss": 0.3103,
      "num_input_tokens_seen": 189970880,
      "step": 785
    },
    {
      "epoch": 2.270600935588341,
      "grad_norm": 0.10441169142723083,
      "learning_rate": 1.450732738131904e-06,
      "loss": 0.3072,
      "num_input_tokens_seen": 191189984,
      "step": 790
    },
    {
      "epoch": 2.284994602374955,
      "grad_norm": 0.09952486306428909,
      "learning_rate": 1.3963390026165596e-06,
      "loss": 0.3076,
      "num_input_tokens_seen": 192394880,
      "step": 795
    },
    {
      "epoch": 2.299388269161569,
      "grad_norm": 0.10286828130483627,
      "learning_rate": 1.3428186256582088e-06,
      "loss": 0.3095,
      "num_input_tokens_seen": 193626752,
      "step": 800
    },
    {
      "epoch": 2.3137819359481826,
      "grad_norm": 0.10270114243030548,
      "learning_rate": 1.2901845780882427e-06,
      "loss": 0.3125,
      "num_input_tokens_seen": 194830592,
      "step": 805
    },
    {
      "epoch": 2.3281756027347966,
      "grad_norm": 0.09845712780952454,
      "learning_rate": 1.238449615933343e-06,
      "loss": 0.3066,
      "num_input_tokens_seen": 196015296,
      "step": 810
    },
    {
      "epoch": 2.3425692695214106,
      "grad_norm": 0.10090301930904388,
      "learning_rate": 1.1876262773240172e-06,
      "loss": 0.3074,
      "num_input_tokens_seen": 197197472,
      "step": 815
    },
    {
      "epoch": 2.3569629363080242,
      "grad_norm": 0.10221939533948898,
      "learning_rate": 1.1377268794559476e-06,
      "loss": 0.3099,
      "num_input_tokens_seen": 198408416,
      "step": 820
    },
    {
      "epoch": 2.3713566030946382,
      "grad_norm": 0.09607075899839401,
      "learning_rate": 1.0887635156048736e-06,
      "loss": 0.3099,
      "num_input_tokens_seen": 199636992,
      "step": 825
    },
    {
      "epoch": 2.3857502698812523,
      "grad_norm": 0.09963447600603104,
      "learning_rate": 1.040748052195752e-06,
      "loss": 0.3152,
      "num_input_tokens_seen": 200829152,
      "step": 830
    },
    {
      "epoch": 2.4001439366678663,
      "grad_norm": 0.09850475937128067,
      "learning_rate": 9.936921259268944e-07,
      "loss": 0.3164,
      "num_input_tokens_seen": 202029984,
      "step": 835
    },
    {
      "epoch": 2.41453760345448,
      "grad_norm": 0.09808507561683655,
      "learning_rate": 9.476071409497712e-07,
      "loss": 0.3101,
      "num_input_tokens_seen": 203245056,
      "step": 840
    },
    {
      "epoch": 2.428931270241094,
      "grad_norm": 0.10383246839046478,
      "learning_rate": 9.025042661051808e-07,
      "loss": 0.3076,
      "num_input_tokens_seen": 204520288,
      "step": 845
    },
    {
      "epoch": 2.443324937027708,
      "grad_norm": 0.102474644780159,
      "learning_rate": 8.583944322164528e-07,
      "loss": 0.3078,
      "num_input_tokens_seen": 205715488,
      "step": 850
    },
    {
      "epoch": 2.457718603814322,
      "grad_norm": 0.09844470024108887,
      "learning_rate": 8.15288329440318e-07,
      "loss": 0.3112,
      "num_input_tokens_seen": 206927520,
      "step": 855
    },
    {
      "epoch": 2.4721122706009355,
      "grad_norm": 0.1022033840417862,
      "learning_rate": 7.731964046761231e-07,
      "loss": 0.3118,
      "num_input_tokens_seen": 208143200,
      "step": 860
    },
    {
      "epoch": 2.4865059373875495,
      "grad_norm": 0.0987834706902504,
      "learning_rate": 7.321288590339898e-07,
      "loss": 0.3136,
      "num_input_tokens_seen": 209341760,
      "step": 865
    },
    {
      "epoch": 2.5008996041741636,
      "grad_norm": 0.10287128388881683,
      "learning_rate": 6.920956453625405e-07,
      "loss": 0.3131,
      "num_input_tokens_seen": 210545312,
      "step": 870
    },
    {
      "epoch": 2.515293270960777,
      "grad_norm": 0.09738028049468994,
      "learning_rate": 6.531064658368019e-07,
      "loss": 0.3059,
      "num_input_tokens_seen": 211762976,
      "step": 875
    },
    {
      "epoch": 2.529686937747391,
      "grad_norm": 0.10002956539392471,
      "learning_rate": 6.151707696068443e-07,
      "loss": 0.3124,
      "num_input_tokens_seen": 212961056,
      "step": 880
    },
    {
      "epoch": 2.544080604534005,
      "grad_norm": 0.10318898409605026,
      "learning_rate": 5.782977505077536e-07,
      "loss": 0.3069,
      "num_input_tokens_seen": 214202912,
      "step": 885
    },
    {
      "epoch": 2.5584742713206188,
      "grad_norm": 0.09782789647579193,
      "learning_rate": 5.42496344831478e-07,
      "loss": 0.3099,
      "num_input_tokens_seen": 215451328,
      "step": 890
    },
    {
      "epoch": 2.572867938107233,
      "grad_norm": 0.10021757334470749,
      "learning_rate": 5.077752291610854e-07,
      "loss": 0.3098,
      "num_input_tokens_seen": 216687904,
      "step": 895
    },
    {
      "epoch": 2.587261604893847,
      "grad_norm": 0.10185465216636658,
      "learning_rate": 4.741428182679736e-07,
      "loss": 0.3004,
      "num_input_tokens_seen": 217946752,
      "step": 900
    },
    {
      "epoch": 2.6016552716804604,
      "grad_norm": 0.09233415126800537,
      "learning_rate": 4.416072630725166e-07,
      "loss": 0.3036,
      "num_input_tokens_seen": 219144288,
      "step": 905
    },
    {
      "epoch": 2.6160489384670744,
      "grad_norm": 0.09735804051160812,
      "learning_rate": 4.101764486686649e-07,
      "loss": 0.3086,
      "num_input_tokens_seen": 220346240,
      "step": 910
    },
    {
      "epoch": 2.6304426052536884,
      "grad_norm": 0.09639353305101395,
      "learning_rate": 3.798579924129736e-07,
      "loss": 0.3085,
      "num_input_tokens_seen": 221541440,
      "step": 915
    },
    {
      "epoch": 2.644836272040302,
      "grad_norm": 0.09983870387077332,
      "learning_rate": 3.5065924207850486e-07,
      "loss": 0.3104,
      "num_input_tokens_seen": 222733952,
      "step": 920
    },
    {
      "epoch": 2.659229938826916,
      "grad_norm": 0.0973723828792572,
      "learning_rate": 3.225872740740754e-07,
      "loss": 0.3004,
      "num_input_tokens_seen": 223949856,
      "step": 925
    },
    {
      "epoch": 2.67362360561353,
      "grad_norm": 0.09668977558612823,
      "learning_rate": 2.9564889172926993e-07,
      "loss": 0.313,
      "num_input_tokens_seen": 225143456,
      "step": 930
    },
    {
      "epoch": 2.688017272400144,
      "grad_norm": 0.10380619019269943,
      "learning_rate": 2.6985062364562607e-07,
      "loss": 0.3083,
      "num_input_tokens_seen": 226360704,
      "step": 935
    },
    {
      "epoch": 2.7024109391867577,
      "grad_norm": 0.09672138839960098,
      "learning_rate": 2.451987221144109e-07,
      "loss": 0.3035,
      "num_input_tokens_seen": 227569088,
      "step": 940
    },
    {
      "epoch": 2.7168046059733717,
      "grad_norm": 0.10255391895771027,
      "learning_rate": 2.2169916160136029e-07,
      "loss": 0.3085,
      "num_input_tokens_seen": 228788352,
      "step": 945
    },
    {
      "epoch": 2.7311982727599857,
      "grad_norm": 0.0997009351849556,
      "learning_rate": 1.9935763729874435e-07,
      "loss": 0.31,
      "num_input_tokens_seen": 230000032,
      "step": 950
    },
    {
      "epoch": 2.7455919395465997,
      "grad_norm": 0.10202497243881226,
      "learning_rate": 1.7817956374512334e-07,
      "loss": 0.3077,
      "num_input_tokens_seen": 231246944,
      "step": 955
    },
    {
      "epoch": 2.7599856063332133,
      "grad_norm": 0.09917100518941879,
      "learning_rate": 1.5817007351311476e-07,
      "loss": 0.3092,
      "num_input_tokens_seen": 232451552,
      "step": 960
    },
    {
      "epoch": 2.7743792731198273,
      "grad_norm": 0.09676503390073776,
      "learning_rate": 1.393340159654999e-07,
      "loss": 0.3094,
      "num_input_tokens_seen": 233614240,
      "step": 965
    },
    {
      "epoch": 2.7887729399064414,
      "grad_norm": 0.09966181963682175,
      "learning_rate": 1.2167595607996296e-07,
      "loss": 0.3075,
      "num_input_tokens_seen": 234822848,
      "step": 970
    },
    {
      "epoch": 2.803166606693055,
      "grad_norm": 0.10073826462030411,
      "learning_rate": 1.0520017334275823e-07,
      "loss": 0.3023,
      "num_input_tokens_seen": 236047488,
      "step": 975
    },
    {
      "epoch": 2.817560273479669,
      "grad_norm": 0.09942162781953812,
      "learning_rate": 8.991066071156074e-08,
      "loss": 0.3039,
      "num_input_tokens_seen": 237278400,
      "step": 980
    },
    {
      "epoch": 2.831953940266283,
      "grad_norm": 0.09857495129108429,
      "learning_rate": 7.581112364776044e-08,
      "loss": 0.3007,
      "num_input_tokens_seen": 238504192,
      "step": 985
    },
    {
      "epoch": 2.8463476070528966,
      "grad_norm": 0.09442529827356339,
      "learning_rate": 6.290497921843219e-08,
      "loss": 0.306,
      "num_input_tokens_seen": 239722240,
      "step": 990
    },
    {
      "epoch": 2.8607412738395106,
      "grad_norm": 0.09979110211133957,
      "learning_rate": 5.1195355268199854e-08,
      "loss": 0.3075,
      "num_input_tokens_seen": 240961824,
      "step": 995
    },
    {
      "epoch": 2.8751349406261246,
      "grad_norm": 0.09761466085910797,
      "learning_rate": 4.0685089661192114e-08,
      "loss": 0.3044,
      "num_input_tokens_seen": 242169280,
      "step": 1000
    },
    {
      "epoch": 2.889528607412738,
      "grad_norm": 0.09431671351194382,
      "learning_rate": 3.1376729593276534e-08,
      "loss": 0.3079,
      "num_input_tokens_seen": 243401792,
      "step": 1005
    },
    {
      "epoch": 2.9039222741993522,
      "grad_norm": 0.09912943094968796,
      "learning_rate": 2.327253097474169e-08,
      "loss": 0.3073,
      "num_input_tokens_seen": 244580640,
      "step": 1010
    },
    {
      "epoch": 2.9183159409859663,
      "grad_norm": 0.1038779690861702,
      "learning_rate": 1.637445788356673e-08,
      "loss": 0.3045,
      "num_input_tokens_seen": 245737216,
      "step": 1015
    },
    {
      "epoch": 2.93270960777258,
      "grad_norm": 0.0988314226269722,
      "learning_rate": 1.0684182089423234e-08,
      "loss": 0.3053,
      "num_input_tokens_seen": 246941952,
      "step": 1020
    },
    {
      "epoch": 2.947103274559194,
      "grad_norm": 0.09422770887613297,
      "learning_rate": 6.20308264851488e-09,
      "loss": 0.3081,
      "num_input_tokens_seen": 248145152,
      "step": 1025
    },
    {
      "epoch": 2.961496941345808,
      "grad_norm": 0.10251382738351822,
      "learning_rate": 2.932245569360892e-09,
      "loss": 0.3086,
      "num_input_tokens_seen": 249325568,
      "step": 1030
    },
    {
      "epoch": 2.975890608132422,
      "grad_norm": 0.0921638160943985,
      "learning_rate": 8.724635495965805e-10,
      "loss": 0.3065,
      "num_input_tokens_seen": 250517248,
      "step": 1035
    },
    {
      "epoch": 2.9902842749190355,
      "grad_norm": 0.09918048232793808,
      "learning_rate": 2.4235783861459304e-11,
      "loss": 0.3097,
      "num_input_tokens_seen": 251735840,
      "step": 1040
    }
  ],
  "logging_steps": 5,
  "max_steps": 1041,
  "num_input_tokens_seen": 251979840,
  "num_train_epochs": 3,
  "save_steps": -1041,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1346538280104493e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}