{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1548,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01937984496124031,
      "grad_norm": 3.1349940241372636,
      "learning_rate": 2e-06,
      "loss": 0.7225,
      "step": 10
    },
    {
      "epoch": 0.03875968992248062,
      "grad_norm": 1.478554813389481,
      "learning_rate": 2e-06,
      "loss": 0.6518,
      "step": 20
    },
    {
      "epoch": 0.05813953488372093,
      "grad_norm": 1.40892259720196,
      "learning_rate": 2e-06,
      "loss": 0.6267,
      "step": 30
    },
    {
      "epoch": 0.07751937984496124,
      "grad_norm": 1.6253951402557405,
      "learning_rate": 2e-06,
      "loss": 0.6193,
      "step": 40
    },
    {
      "epoch": 0.09689922480620156,
      "grad_norm": 1.474392955252126,
      "learning_rate": 2e-06,
      "loss": 0.6139,
      "step": 50
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 3.0751907911279477,
      "learning_rate": 2e-06,
      "loss": 0.6069,
      "step": 60
    },
    {
      "epoch": 0.13565891472868216,
      "grad_norm": 2.9223888412970873,
      "learning_rate": 2e-06,
      "loss": 0.6024,
      "step": 70
    },
    {
      "epoch": 0.15503875968992248,
      "grad_norm": 2.357095375310306,
      "learning_rate": 2e-06,
      "loss": 0.6052,
      "step": 80
    },
    {
      "epoch": 0.1744186046511628,
      "grad_norm": 1.3933025656894271,
      "learning_rate": 2e-06,
      "loss": 0.5906,
      "step": 90
    },
    {
      "epoch": 0.1937984496124031,
      "grad_norm": 1.820645926185548,
      "learning_rate": 2e-06,
      "loss": 0.5929,
      "step": 100
    },
    {
      "epoch": 0.2131782945736434,
      "grad_norm": 1.7924399526821087,
      "learning_rate": 2e-06,
      "loss": 0.5958,
      "step": 110
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 1.7736991192509453,
      "learning_rate": 2e-06,
      "loss": 0.587,
      "step": 120
    },
    {
      "epoch": 0.25193798449612403,
      "grad_norm": 1.9201526538063434,
      "learning_rate": 2e-06,
      "loss": 0.5972,
      "step": 130
    },
    {
      "epoch": 0.2713178294573643,
      "grad_norm": 1.9904730096438479,
      "learning_rate": 2e-06,
      "loss": 0.5837,
      "step": 140
    },
    {
      "epoch": 0.29069767441860467,
      "grad_norm": 1.706489075036192,
      "learning_rate": 2e-06,
      "loss": 0.5837,
      "step": 150
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 1.6008690300286739,
      "learning_rate": 2e-06,
      "loss": 0.5824,
      "step": 160
    },
    {
      "epoch": 0.32945736434108525,
      "grad_norm": 1.7784490780851796,
      "learning_rate": 2e-06,
      "loss": 0.5776,
      "step": 170
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 1.4254130054140608,
      "learning_rate": 2e-06,
      "loss": 0.5817,
      "step": 180
    },
    {
      "epoch": 0.3682170542635659,
      "grad_norm": 1.4517537061348775,
      "learning_rate": 2e-06,
      "loss": 0.5745,
      "step": 190
    },
    {
      "epoch": 0.3875968992248062,
      "grad_norm": 1.421098096153975,
      "learning_rate": 2e-06,
      "loss": 0.5822,
      "step": 200
    },
    {
      "epoch": 0.4069767441860465,
      "grad_norm": 1.4340247949454419,
      "learning_rate": 2e-06,
      "loss": 0.5803,
      "step": 210
    },
    {
      "epoch": 0.4263565891472868,
      "grad_norm": 1.2607995600168784,
      "learning_rate": 2e-06,
      "loss": 0.5683,
      "step": 220
    },
    {
      "epoch": 0.44573643410852715,
      "grad_norm": 1.4088258448752224,
      "learning_rate": 2e-06,
      "loss": 0.5669,
      "step": 230
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 1.4547922751942315,
      "learning_rate": 2e-06,
      "loss": 0.5711,
      "step": 240
    },
    {
      "epoch": 0.4844961240310077,
      "grad_norm": 1.3166116102995473,
      "learning_rate": 2e-06,
      "loss": 0.5715,
      "step": 250
    },
    {
      "epoch": 0.5038759689922481,
      "grad_norm": 1.2865076146935452,
      "learning_rate": 2e-06,
      "loss": 0.5706,
      "step": 260
    },
    {
      "epoch": 0.5232558139534884,
      "grad_norm": 1.9514850118526776,
      "learning_rate": 2e-06,
      "loss": 0.5711,
      "step": 270
    },
    {
      "epoch": 0.5426356589147286,
      "grad_norm": 1.3656201312041214,
      "learning_rate": 2e-06,
      "loss": 0.5665,
      "step": 280
    },
    {
      "epoch": 0.562015503875969,
      "grad_norm": 1.2117280702790532,
      "learning_rate": 2e-06,
      "loss": 0.5685,
      "step": 290
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 1.5936964457861214,
      "learning_rate": 2e-06,
      "loss": 0.5767,
      "step": 300
    },
    {
      "epoch": 0.6007751937984496,
      "grad_norm": 1.262836540024248,
      "learning_rate": 2e-06,
      "loss": 0.5639,
      "step": 310
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 1.5253983364542758,
      "learning_rate": 2e-06,
      "loss": 0.5613,
      "step": 320
    },
    {
      "epoch": 0.6395348837209303,
      "grad_norm": 1.695119554349292,
      "learning_rate": 2e-06,
      "loss": 0.5629,
      "step": 330
    },
    {
      "epoch": 0.6589147286821705,
      "grad_norm": 1.2779875033648296,
      "learning_rate": 2e-06,
      "loss": 0.5591,
      "step": 340
    },
    {
      "epoch": 0.6782945736434108,
      "grad_norm": 1.6166948739589506,
      "learning_rate": 2e-06,
      "loss": 0.5561,
      "step": 350
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 1.3469984241923647,
      "learning_rate": 2e-06,
      "loss": 0.561,
      "step": 360
    },
    {
      "epoch": 0.7170542635658915,
      "grad_norm": 1.2982439077151307,
      "learning_rate": 2e-06,
      "loss": 0.5662,
      "step": 370
    },
    {
      "epoch": 0.7364341085271318,
      "grad_norm": 1.3681013360427425,
      "learning_rate": 2e-06,
      "loss": 0.5671,
      "step": 380
    },
    {
      "epoch": 0.7558139534883721,
      "grad_norm": 1.2116770625468472,
      "learning_rate": 2e-06,
      "loss": 0.5568,
      "step": 390
    },
    {
      "epoch": 0.7751937984496124,
      "grad_norm": 1.433614262268133,
      "learning_rate": 2e-06,
      "loss": 0.5581,
      "step": 400
    },
    {
      "epoch": 0.7945736434108527,
      "grad_norm": 1.1848821794193687,
      "learning_rate": 2e-06,
      "loss": 0.5637,
      "step": 410
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 1.3158386135055107,
      "learning_rate": 2e-06,
      "loss": 0.5582,
      "step": 420
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.3927036985893504,
      "learning_rate": 2e-06,
      "loss": 0.5612,
      "step": 430
    },
    {
      "epoch": 0.8527131782945736,
      "grad_norm": 1.1806090504426345,
      "learning_rate": 2e-06,
      "loss": 0.5588,
      "step": 440
    },
    {
      "epoch": 0.872093023255814,
      "grad_norm": 1.2223208556627352,
      "learning_rate": 2e-06,
      "loss": 0.5621,
      "step": 450
    },
    {
      "epoch": 0.8914728682170543,
      "grad_norm": 1.1512657163820463,
      "learning_rate": 2e-06,
      "loss": 0.5513,
      "step": 460
    },
    {
      "epoch": 0.9108527131782945,
      "grad_norm": 1.1826527683444463,
      "learning_rate": 2e-06,
      "loss": 0.5577,
      "step": 470
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 1.578741070129489,
      "learning_rate": 2e-06,
      "loss": 0.5584,
      "step": 480
    },
    {
      "epoch": 0.9496124031007752,
      "grad_norm": 1.364010417258464,
      "learning_rate": 2e-06,
      "loss": 0.5517,
      "step": 490
    },
    {
      "epoch": 0.9689922480620154,
      "grad_norm": 1.564561079833014,
      "learning_rate": 2e-06,
      "loss": 0.5528,
      "step": 500
    },
    {
      "epoch": 0.9883720930232558,
      "grad_norm": 1.1934813597924194,
      "learning_rate": 2e-06,
      "loss": 0.5573,
      "step": 510
    },
    {
      "epoch": 1.0077519379844961,
      "grad_norm": 2.2183985963794735,
      "learning_rate": 2e-06,
      "loss": 0.5359,
      "step": 520
    },
    {
      "epoch": 1.0271317829457365,
      "grad_norm": 1.444929607797708,
      "learning_rate": 2e-06,
      "loss": 0.5096,
      "step": 530
    },
    {
      "epoch": 1.0465116279069768,
      "grad_norm": 1.3333146357476189,
      "learning_rate": 2e-06,
      "loss": 0.5072,
      "step": 540
    },
    {
      "epoch": 1.0658914728682172,
      "grad_norm": 1.1259644665340547,
      "learning_rate": 2e-06,
      "loss": 0.5052,
      "step": 550
    },
    {
      "epoch": 1.0852713178294573,
      "grad_norm": 1.4403172490091567,
      "learning_rate": 2e-06,
      "loss": 0.5169,
      "step": 560
    },
    {
      "epoch": 1.1046511627906976,
      "grad_norm": 1.157835174296272,
      "learning_rate": 2e-06,
      "loss": 0.5102,
      "step": 570
    },
    {
      "epoch": 1.124031007751938,
      "grad_norm": 1.1960407146223624,
      "learning_rate": 2e-06,
      "loss": 0.5038,
      "step": 580
    },
    {
      "epoch": 1.1434108527131783,
      "grad_norm": 1.253507090792846,
      "learning_rate": 2e-06,
      "loss": 0.5034,
      "step": 590
    },
    {
      "epoch": 1.1627906976744187,
      "grad_norm": 1.2979047842512628,
      "learning_rate": 2e-06,
      "loss": 0.5038,
      "step": 600
    },
    {
      "epoch": 1.1821705426356588,
      "grad_norm": 1.2576281990523717,
      "learning_rate": 2e-06,
      "loss": 0.5137,
      "step": 610
    },
    {
      "epoch": 1.2015503875968991,
      "grad_norm": 1.2748802075166439,
      "learning_rate": 2e-06,
      "loss": 0.5076,
      "step": 620
    },
    {
      "epoch": 1.2209302325581395,
      "grad_norm": 1.5223812042187916,
      "learning_rate": 2e-06,
      "loss": 0.5077,
      "step": 630
    },
    {
      "epoch": 1.2403100775193798,
      "grad_norm": 1.3632540604107077,
      "learning_rate": 2e-06,
      "loss": 0.5083,
      "step": 640
    },
    {
      "epoch": 1.2596899224806202,
      "grad_norm": 1.2321831811826818,
      "learning_rate": 2e-06,
      "loss": 0.5096,
      "step": 650
    },
    {
      "epoch": 1.2790697674418605,
      "grad_norm": 1.3323190632353188,
      "learning_rate": 2e-06,
      "loss": 0.5063,
      "step": 660
    },
    {
      "epoch": 1.2984496124031009,
      "grad_norm": 1.2066604050023704,
      "learning_rate": 2e-06,
      "loss": 0.5122,
      "step": 670
    },
    {
      "epoch": 1.3178294573643412,
      "grad_norm": 1.186727847270962,
      "learning_rate": 2e-06,
      "loss": 0.5121,
      "step": 680
    },
    {
      "epoch": 1.3372093023255813,
      "grad_norm": 1.397263671569467,
      "learning_rate": 2e-06,
      "loss": 0.5089,
      "step": 690
    },
    {
      "epoch": 1.3565891472868217,
      "grad_norm": 1.573664700028339,
      "learning_rate": 2e-06,
      "loss": 0.5099,
      "step": 700
    },
    {
      "epoch": 1.375968992248062,
      "grad_norm": 1.4467914138897073,
      "learning_rate": 2e-06,
      "loss": 0.5134,
      "step": 710
    },
    {
      "epoch": 1.3953488372093024,
      "grad_norm": 1.3706902755992394,
      "learning_rate": 2e-06,
      "loss": 0.5123,
      "step": 720
    },
    {
      "epoch": 1.4147286821705427,
      "grad_norm": 1.2411084475779852,
      "learning_rate": 2e-06,
      "loss": 0.5078,
      "step": 730
    },
    {
      "epoch": 1.4341085271317828,
      "grad_norm": 1.5902510539142722,
      "learning_rate": 2e-06,
      "loss": 0.5137,
      "step": 740
    },
    {
      "epoch": 1.4534883720930232,
      "grad_norm": 1.7787034613442634,
      "learning_rate": 2e-06,
      "loss": 0.5094,
      "step": 750
    },
    {
      "epoch": 1.4728682170542635,
      "grad_norm": 1.2787619752439543,
      "learning_rate": 2e-06,
      "loss": 0.5063,
      "step": 760
    },
    {
      "epoch": 1.4922480620155039,
      "grad_norm": 1.2898677794347344,
      "learning_rate": 2e-06,
      "loss": 0.5097,
      "step": 770
    },
    {
      "epoch": 1.5116279069767442,
      "grad_norm": 1.2320340010541546,
      "learning_rate": 2e-06,
      "loss": 0.5127,
      "step": 780
    },
    {
      "epoch": 1.5310077519379846,
      "grad_norm": 1.1998558863263413,
      "learning_rate": 2e-06,
      "loss": 0.5097,
      "step": 790
    },
    {
      "epoch": 1.550387596899225,
      "grad_norm": 1.2491228211939762,
      "learning_rate": 2e-06,
      "loss": 0.507,
      "step": 800
    },
    {
      "epoch": 1.5697674418604652,
      "grad_norm": 1.2235970378609549,
      "learning_rate": 2e-06,
      "loss": 0.5052,
      "step": 810
    },
    {
      "epoch": 1.5891472868217056,
      "grad_norm": 1.4176990973616905,
      "learning_rate": 2e-06,
      "loss": 0.5039,
      "step": 820
    },
    {
      "epoch": 1.6085271317829457,
      "grad_norm": 1.3149977315253063,
      "learning_rate": 2e-06,
      "loss": 0.512,
      "step": 830
    },
    {
      "epoch": 1.627906976744186,
      "grad_norm": 1.2333272112594988,
      "learning_rate": 2e-06,
      "loss": 0.5066,
      "step": 840
    },
    {
      "epoch": 1.6472868217054264,
      "grad_norm": 1.1574106550887124,
      "learning_rate": 2e-06,
      "loss": 0.5113,
      "step": 850
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.418576038122765,
      "learning_rate": 2e-06,
      "loss": 0.5137,
      "step": 860
    },
    {
      "epoch": 1.6860465116279069,
      "grad_norm": 1.187391106828372,
      "learning_rate": 2e-06,
      "loss": 0.506,
      "step": 870
    },
    {
      "epoch": 1.7054263565891472,
      "grad_norm": 1.170649147011855,
      "learning_rate": 2e-06,
      "loss": 0.5107,
      "step": 880
    },
    {
      "epoch": 1.7248062015503876,
      "grad_norm": 1.3798145976951228,
      "learning_rate": 2e-06,
      "loss": 0.5099,
      "step": 890
    },
    {
      "epoch": 1.744186046511628,
      "grad_norm": 1.725987629268818,
      "learning_rate": 2e-06,
      "loss": 0.5139,
      "step": 900
    },
    {
      "epoch": 1.7635658914728682,
      "grad_norm": 1.8813904948358928,
      "learning_rate": 2e-06,
      "loss": 0.5059,
      "step": 910
    },
    {
      "epoch": 1.7829457364341086,
      "grad_norm": 1.8516754910417244,
      "learning_rate": 2e-06,
      "loss": 0.5088,
      "step": 920
    },
    {
      "epoch": 1.802325581395349,
      "grad_norm": 1.2095051182172416,
      "learning_rate": 2e-06,
      "loss": 0.5096,
      "step": 930
    },
    {
      "epoch": 1.8217054263565893,
      "grad_norm": 1.2435069711568396,
      "learning_rate": 2e-06,
      "loss": 0.5077,
      "step": 940
    },
    {
      "epoch": 1.8410852713178296,
      "grad_norm": 1.3586556706802664,
      "learning_rate": 2e-06,
      "loss": 0.5102,
      "step": 950
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 1.1979327298252027,
      "learning_rate": 2e-06,
      "loss": 0.512,
      "step": 960
    },
    {
      "epoch": 1.87984496124031,
      "grad_norm": 1.7904993765105046,
      "learning_rate": 2e-06,
      "loss": 0.5096,
      "step": 970
    },
    {
      "epoch": 1.8992248062015504,
      "grad_norm": 1.377601184927356,
      "learning_rate": 2e-06,
      "loss": 0.5057,
      "step": 980
    },
    {
      "epoch": 1.9186046511627906,
      "grad_norm": 1.1816932854326225,
      "learning_rate": 2e-06,
      "loss": 0.5118,
      "step": 990
    },
    {
      "epoch": 1.937984496124031,
      "grad_norm": 1.235638000745403,
      "learning_rate": 2e-06,
      "loss": 0.5092,
      "step": 1000
    },
    {
      "epoch": 1.9573643410852712,
      "grad_norm": 1.2730535171048605,
      "learning_rate": 2e-06,
      "loss": 0.5104,
      "step": 1010
    },
    {
      "epoch": 1.9767441860465116,
      "grad_norm": 1.2382473568182877,
      "learning_rate": 2e-06,
      "loss": 0.5059,
      "step": 1020
    },
    {
      "epoch": 1.996124031007752,
      "grad_norm": 1.2856863827108878,
      "learning_rate": 2e-06,
      "loss": 0.51,
      "step": 1030
    },
    {
      "epoch": 2.0155038759689923,
      "grad_norm": 1.6836529854231972,
      "learning_rate": 2e-06,
      "loss": 0.4603,
      "step": 1040
    },
    {
      "epoch": 2.0348837209302326,
      "grad_norm": 1.4922089047807388,
      "learning_rate": 2e-06,
      "loss": 0.4585,
      "step": 1050
    },
    {
      "epoch": 2.054263565891473,
      "grad_norm": 1.3990249605527378,
      "learning_rate": 2e-06,
      "loss": 0.4571,
      "step": 1060
    },
    {
      "epoch": 2.0736434108527133,
      "grad_norm": 1.5500783972286114,
      "learning_rate": 2e-06,
      "loss": 0.4591,
      "step": 1070
    },
    {
      "epoch": 2.0930232558139537,
      "grad_norm": 1.4063766317234851,
      "learning_rate": 2e-06,
      "loss": 0.4537,
      "step": 1080
    },
    {
      "epoch": 2.112403100775194,
      "grad_norm": 1.4498154054826256,
      "learning_rate": 2e-06,
      "loss": 0.4567,
      "step": 1090
    },
    {
      "epoch": 2.1317829457364343,
      "grad_norm": 1.4659238804284036,
      "learning_rate": 2e-06,
      "loss": 0.4564,
      "step": 1100
    },
    {
      "epoch": 2.1511627906976742,
      "grad_norm": 1.4331071288445956,
      "learning_rate": 2e-06,
      "loss": 0.4597,
      "step": 1110
    },
    {
      "epoch": 2.1705426356589146,
      "grad_norm": 1.2265580968692957,
      "learning_rate": 2e-06,
      "loss": 0.4613,
      "step": 1120
    },
    {
      "epoch": 2.189922480620155,
      "grad_norm": 1.430430093258902,
      "learning_rate": 2e-06,
      "loss": 0.4582,
      "step": 1130
    },
    {
      "epoch": 2.2093023255813953,
      "grad_norm": 1.3191685780949374,
      "learning_rate": 2e-06,
      "loss": 0.4567,
      "step": 1140
    },
    {
      "epoch": 2.2286821705426356,
      "grad_norm": 1.4143557981830728,
      "learning_rate": 2e-06,
      "loss": 0.4593,
      "step": 1150
    },
    {
      "epoch": 2.248062015503876,
      "grad_norm": 1.2038927572265354,
      "learning_rate": 2e-06,
      "loss": 0.4571,
      "step": 1160
    },
    {
      "epoch": 2.2674418604651163,
      "grad_norm": 1.5101700084835745,
      "learning_rate": 2e-06,
      "loss": 0.4576,
      "step": 1170
    },
    {
      "epoch": 2.2868217054263567,
      "grad_norm": 1.3238249446175274,
      "learning_rate": 2e-06,
      "loss": 0.4648,
      "step": 1180
    },
    {
      "epoch": 2.306201550387597,
      "grad_norm": 1.4453440150118313,
      "learning_rate": 2e-06,
      "loss": 0.46,
      "step": 1190
    },
    {
      "epoch": 2.3255813953488373,
      "grad_norm": 1.291302766406732,
      "learning_rate": 2e-06,
      "loss": 0.4564,
      "step": 1200
    },
    {
      "epoch": 2.3449612403100777,
      "grad_norm": 1.3371668345858843,
      "learning_rate": 2e-06,
      "loss": 0.4605,
      "step": 1210
    },
    {
      "epoch": 2.3643410852713176,
      "grad_norm": 1.4583613955952517,
      "learning_rate": 2e-06,
      "loss": 0.4639,
      "step": 1220
    },
    {
      "epoch": 2.383720930232558,
      "grad_norm": 1.3603243092911215,
      "learning_rate": 2e-06,
      "loss": 0.4591,
      "step": 1230
    },
    {
      "epoch": 2.4031007751937983,
      "grad_norm": 1.4381588797038276,
      "learning_rate": 2e-06,
      "loss": 0.4654,
      "step": 1240
    },
    {
      "epoch": 2.4224806201550386,
      "grad_norm": 1.2897514442264095,
      "learning_rate": 2e-06,
      "loss": 0.46,
      "step": 1250
    },
    {
      "epoch": 2.441860465116279,
      "grad_norm": 1.4149740934308317,
      "learning_rate": 2e-06,
      "loss": 0.462,
      "step": 1260
    },
    {
      "epoch": 2.4612403100775193,
      "grad_norm": 1.2334708007117,
      "learning_rate": 2e-06,
      "loss": 0.4636,
      "step": 1270
    },
    {
      "epoch": 2.4806201550387597,
      "grad_norm": 1.3277525646372448,
      "learning_rate": 2e-06,
      "loss": 0.4637,
      "step": 1280
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.341129908785728,
      "learning_rate": 2e-06,
      "loss": 0.4572,
      "step": 1290
    },
    {
      "epoch": 2.5193798449612403,
      "grad_norm": 1.2028868010871578,
      "learning_rate": 2e-06,
      "loss": 0.4643,
      "step": 1300
    },
    {
      "epoch": 2.5387596899224807,
      "grad_norm": 1.2788628805207698,
      "learning_rate": 2e-06,
      "loss": 0.458,
      "step": 1310
    },
    {
      "epoch": 2.558139534883721,
      "grad_norm": 1.1964555955603347,
      "learning_rate": 2e-06,
      "loss": 0.4702,
      "step": 1320
    },
    {
      "epoch": 2.5775193798449614,
      "grad_norm": 1.2630513178641603,
      "learning_rate": 2e-06,
      "loss": 0.4622,
      "step": 1330
    },
    {
      "epoch": 2.5968992248062017,
      "grad_norm": 1.4987867600057845,
      "learning_rate": 2e-06,
      "loss": 0.4708,
      "step": 1340
    },
    {
      "epoch": 2.616279069767442,
      "grad_norm": 1.328908367081974,
      "learning_rate": 2e-06,
      "loss": 0.4622,
      "step": 1350
    },
    {
      "epoch": 2.6356589147286824,
      "grad_norm": 1.572958887182858,
      "learning_rate": 2e-06,
      "loss": 0.459,
      "step": 1360
    },
    {
      "epoch": 2.6550387596899228,
      "grad_norm": 1.2305373948782317,
      "learning_rate": 2e-06,
      "loss": 0.4597,
      "step": 1370
    },
    {
      "epoch": 2.6744186046511627,
      "grad_norm": 1.231294042248163,
      "learning_rate": 2e-06,
      "loss": 0.468,
      "step": 1380
    },
    {
      "epoch": 2.693798449612403,
      "grad_norm": 1.2696874963913714,
      "learning_rate": 2e-06,
      "loss": 0.4598,
      "step": 1390
    },
    {
      "epoch": 2.7131782945736433,
      "grad_norm": 1.2272319783021322,
      "learning_rate": 2e-06,
      "loss": 0.4678,
      "step": 1400
    },
    {
      "epoch": 2.7325581395348837,
      "grad_norm": 1.3352293934792803,
      "learning_rate": 2e-06,
      "loss": 0.4594,
      "step": 1410
    },
    {
      "epoch": 2.751937984496124,
      "grad_norm": 1.306891032131746,
      "learning_rate": 2e-06,
      "loss": 0.4613,
      "step": 1420
    },
    {
      "epoch": 2.7713178294573644,
      "grad_norm": 1.2665315216624808,
      "learning_rate": 2e-06,
      "loss": 0.4667,
      "step": 1430
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 1.3240308251203166,
      "learning_rate": 2e-06,
      "loss": 0.4656,
      "step": 1440
    },
    {
      "epoch": 2.810077519379845,
      "grad_norm": 1.4793024854316217,
      "learning_rate": 2e-06,
      "loss": 0.463,
      "step": 1450
    },
    {
      "epoch": 2.8294573643410854,
      "grad_norm": 1.4217782757634918,
      "learning_rate": 2e-06,
      "loss": 0.4703,
      "step": 1460
    },
    {
      "epoch": 2.8488372093023253,
      "grad_norm": 1.2290713413876615,
      "learning_rate": 2e-06,
      "loss": 0.4661,
      "step": 1470
    },
    {
      "epoch": 2.8682170542635657,
      "grad_norm": 1.4408298205910421,
      "learning_rate": 2e-06,
      "loss": 0.4667,
      "step": 1480
    },
    {
      "epoch": 2.887596899224806,
      "grad_norm": 1.4463509582697884,
      "learning_rate": 2e-06,
      "loss": 0.4692,
      "step": 1490
    },
    {
      "epoch": 2.9069767441860463,
      "grad_norm": 1.3757313989698736,
      "learning_rate": 2e-06,
      "loss": 0.4585,
      "step": 1500
    },
    {
      "epoch": 2.9263565891472867,
      "grad_norm": 1.3950705796217753,
      "learning_rate": 2e-06,
      "loss": 0.4627,
      "step": 1510
    },
    {
      "epoch": 2.945736434108527,
      "grad_norm": 1.269632815277089,
      "learning_rate": 2e-06,
      "loss": 0.4679,
      "step": 1520
    },
    {
      "epoch": 2.9651162790697674,
      "grad_norm": 1.3792098795510677,
      "learning_rate": 2e-06,
      "loss": 0.463,
      "step": 1530
    },
    {
      "epoch": 2.9844961240310077,
      "grad_norm": 1.2723166198917764,
      "learning_rate": 2e-06,
      "loss": 0.468,
      "step": 1540
    },
    {
      "epoch": 3.0,
      "step": 1548,
      "total_flos": 2591282618695680.0,
      "train_loss": 0.1541580106552873,
      "train_runtime": 7454.5076,
      "train_samples_per_second": 106.232,
      "train_steps_per_second": 0.208
    }
  ],
  "logging_steps": 10,
  "max_steps": 1548,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2591282618695680.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}