{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2500223393798588,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008935751943526047,
      "grad_norm": 4.83393669128418,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 1.4311,
      "step": 10
    },
    {
      "epoch": 0.0017871503887052094,
      "grad_norm": 3.230992555618286,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 1.4013,
      "step": 20
    },
    {
      "epoch": 0.0026807255830578144,
      "grad_norm": 1.9909214973449707,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.1381,
      "step": 30
    },
    {
      "epoch": 0.003574300777410419,
      "grad_norm": 0.8147533535957336,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 0.9713,
      "step": 40
    },
    {
      "epoch": 0.004467875971763024,
      "grad_norm": 0.8770450949668884,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.8768,
      "step": 50
    },
    {
      "epoch": 0.005361451166115629,
      "grad_norm": 0.4910338222980499,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.8431,
      "step": 60
    },
    {
      "epoch": 0.006255026360468234,
      "grad_norm": 0.5245729684829712,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.7821,
      "step": 70
    },
    {
      "epoch": 0.007148601554820838,
      "grad_norm": 0.4985717535018921,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.8137,
      "step": 80
    },
    {
      "epoch": 0.008042176749173444,
      "grad_norm": 0.4982825517654419,
      "learning_rate": 1.005e-05,
      "loss": 0.8014,
      "step": 90
    },
    {
      "epoch": 0.008935751943526048,
      "grad_norm": 0.4962609112262726,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.8102,
      "step": 100
    },
    {
      "epoch": 0.009829327137878652,
      "grad_norm": 0.4608575701713562,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.7836,
      "step": 110
    },
    {
      "epoch": 0.010722902332231258,
      "grad_norm": 0.4405043423175812,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.7987,
      "step": 120
    },
    {
      "epoch": 0.011616477526583862,
      "grad_norm": 0.4832342565059662,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.757,
      "step": 130
    },
    {
      "epoch": 0.012510052720936467,
      "grad_norm": 0.5148149132728577,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.7922,
      "step": 140
    },
    {
      "epoch": 0.013403627915289072,
      "grad_norm": 0.496463418006897,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.8236,
      "step": 150
    },
    {
      "epoch": 0.014297203109641676,
      "grad_norm": 0.5295011401176453,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.798,
      "step": 160
    },
    {
      "epoch": 0.015190778303994281,
      "grad_norm": 0.47589513659477234,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.8071,
      "step": 170
    },
    {
      "epoch": 0.016084353498346887,
      "grad_norm": 0.42235517501831055,
      "learning_rate": 2e-05,
      "loss": 0.7128,
      "step": 180
    },
    {
      "epoch": 0.01697792869269949,
      "grad_norm": 0.4666895270347595,
      "learning_rate": 2e-05,
      "loss": 0.7695,
      "step": 190
    },
    {
      "epoch": 0.017871503887052095,
      "grad_norm": 0.41975900530815125,
      "learning_rate": 2e-05,
      "loss": 0.7967,
      "step": 200
    },
    {
      "epoch": 0.0187650790814047,
      "grad_norm": 0.4837177097797394,
      "learning_rate": 2e-05,
      "loss": 0.7712,
      "step": 210
    },
    {
      "epoch": 0.019658654275757304,
      "grad_norm": 0.422789603471756,
      "learning_rate": 2e-05,
      "loss": 0.7704,
      "step": 220
    },
    {
      "epoch": 0.02055222947010991,
      "grad_norm": 0.42405927181243896,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 230
    },
    {
      "epoch": 0.021445804664462515,
      "grad_norm": 0.44666311144828796,
      "learning_rate": 2e-05,
      "loss": 0.7747,
      "step": 240
    },
    {
      "epoch": 0.02233937985881512,
      "grad_norm": 0.413830041885376,
      "learning_rate": 2e-05,
      "loss": 0.7766,
      "step": 250
    },
    {
      "epoch": 0.023232955053167723,
      "grad_norm": 0.4343000054359436,
      "learning_rate": 2e-05,
      "loss": 0.8023,
      "step": 260
    },
    {
      "epoch": 0.024126530247520327,
      "grad_norm": 0.4592699110507965,
      "learning_rate": 2e-05,
      "loss": 0.7824,
      "step": 270
    },
    {
      "epoch": 0.025020105441872935,
      "grad_norm": 0.4644310474395752,
      "learning_rate": 2e-05,
      "loss": 0.7371,
      "step": 280
    },
    {
      "epoch": 0.02591368063622554,
      "grad_norm": 0.4319989085197449,
      "learning_rate": 2e-05,
      "loss": 0.7641,
      "step": 290
    },
    {
      "epoch": 0.026807255830578143,
      "grad_norm": 0.4405927360057831,
      "learning_rate": 2e-05,
      "loss": 0.7863,
      "step": 300
    },
    {
      "epoch": 0.027700831024930747,
      "grad_norm": 0.4252799451351166,
      "learning_rate": 2e-05,
      "loss": 0.7928,
      "step": 310
    },
    {
      "epoch": 0.02859440621928335,
      "grad_norm": 0.4097546637058258,
      "learning_rate": 2e-05,
      "loss": 0.7965,
      "step": 320
    },
    {
      "epoch": 0.02948798141363596,
      "grad_norm": 0.4354838728904724,
      "learning_rate": 2e-05,
      "loss": 0.7932,
      "step": 330
    },
    {
      "epoch": 0.030381556607988563,
      "grad_norm": 0.4520812928676605,
      "learning_rate": 2e-05,
      "loss": 0.793,
      "step": 340
    },
    {
      "epoch": 0.03127513180234117,
      "grad_norm": 0.5291610360145569,
      "learning_rate": 2e-05,
      "loss": 0.7466,
      "step": 350
    },
    {
      "epoch": 0.032168706996693774,
      "grad_norm": 0.442043662071228,
      "learning_rate": 2e-05,
      "loss": 0.7455,
      "step": 360
    },
    {
      "epoch": 0.03306228219104638,
      "grad_norm": 0.39435988664627075,
      "learning_rate": 2e-05,
      "loss": 0.7664,
      "step": 370
    },
    {
      "epoch": 0.03395585738539898,
      "grad_norm": 0.6453039050102234,
      "learning_rate": 2e-05,
      "loss": 0.7415,
      "step": 380
    },
    {
      "epoch": 0.03484943257975159,
      "grad_norm": 0.6479556560516357,
      "learning_rate": 2e-05,
      "loss": 0.8238,
      "step": 390
    },
    {
      "epoch": 0.03574300777410419,
      "grad_norm": 0.4728488624095917,
      "learning_rate": 2e-05,
      "loss": 0.7672,
      "step": 400
    },
    {
      "epoch": 0.036636582968456795,
      "grad_norm": 0.4299718141555786,
      "learning_rate": 2e-05,
      "loss": 0.7397,
      "step": 410
    },
    {
      "epoch": 0.0375301581628094,
      "grad_norm": 0.35715794563293457,
      "learning_rate": 2e-05,
      "loss": 0.7332,
      "step": 420
    },
    {
      "epoch": 0.038423733357162,
      "grad_norm": 0.430271178483963,
      "learning_rate": 2e-05,
      "loss": 0.7557,
      "step": 430
    },
    {
      "epoch": 0.03931730855151461,
      "grad_norm": 0.4169669449329376,
      "learning_rate": 2e-05,
      "loss": 0.7654,
      "step": 440
    },
    {
      "epoch": 0.04021088374586722,
      "grad_norm": 0.4232149124145508,
      "learning_rate": 2e-05,
      "loss": 0.7845,
      "step": 450
    },
    {
      "epoch": 0.04110445894021982,
      "grad_norm": 0.42479565739631653,
      "learning_rate": 2e-05,
      "loss": 0.7642,
      "step": 460
    },
    {
      "epoch": 0.041998034134572426,
      "grad_norm": 0.38824278116226196,
      "learning_rate": 2e-05,
      "loss": 0.7514,
      "step": 470
    },
    {
      "epoch": 0.04289160932892503,
      "grad_norm": 0.4207800626754761,
      "learning_rate": 2e-05,
      "loss": 0.7528,
      "step": 480
    },
    {
      "epoch": 0.043785184523277634,
      "grad_norm": 0.40183427929878235,
      "learning_rate": 2e-05,
      "loss": 0.7806,
      "step": 490
    },
    {
      "epoch": 0.04467875971763024,
      "grad_norm": 0.431792676448822,
      "learning_rate": 2e-05,
      "loss": 0.7755,
      "step": 500
    },
    {
      "epoch": 0.04557233491198284,
      "grad_norm": 0.4143838584423065,
      "learning_rate": 2e-05,
      "loss": 0.7539,
      "step": 510
    },
    {
      "epoch": 0.04646591010633545,
      "grad_norm": 0.44914576411247253,
      "learning_rate": 2e-05,
      "loss": 0.7638,
      "step": 520
    },
    {
      "epoch": 0.04735948530068805,
      "grad_norm": 0.3990241587162018,
      "learning_rate": 2e-05,
      "loss": 0.7566,
      "step": 530
    },
    {
      "epoch": 0.048253060495040655,
      "grad_norm": 0.4371657371520996,
      "learning_rate": 2e-05,
      "loss": 0.7551,
      "step": 540
    },
    {
      "epoch": 0.049146635689393266,
      "grad_norm": 0.45287543535232544,
      "learning_rate": 2e-05,
      "loss": 0.7469,
      "step": 550
    },
    {
      "epoch": 0.05004021088374587,
      "grad_norm": 0.3757151961326599,
      "learning_rate": 2e-05,
      "loss": 0.7494,
      "step": 560
    },
    {
      "epoch": 0.050933786078098474,
      "grad_norm": 0.5098564624786377,
      "learning_rate": 2e-05,
      "loss": 0.7648,
      "step": 570
    },
    {
      "epoch": 0.05182736127245108,
      "grad_norm": 0.43075209856033325,
      "learning_rate": 2e-05,
      "loss": 0.7296,
      "step": 580
    },
    {
      "epoch": 0.05272093646680368,
      "grad_norm": 0.46172618865966797,
      "learning_rate": 2e-05,
      "loss": 0.7439,
      "step": 590
    },
    {
      "epoch": 0.053614511661156286,
      "grad_norm": 0.4297853112220764,
      "learning_rate": 2e-05,
      "loss": 0.7748,
      "step": 600
    },
    {
      "epoch": 0.05450808685550889,
      "grad_norm": 0.39287275075912476,
      "learning_rate": 2e-05,
      "loss": 0.7353,
      "step": 610
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": 0.3974439203739166,
      "learning_rate": 2e-05,
      "loss": 0.7451,
      "step": 620
    },
    {
      "epoch": 0.0562952372442141,
      "grad_norm": 0.39414021372795105,
      "learning_rate": 2e-05,
      "loss": 0.7739,
      "step": 630
    },
    {
      "epoch": 0.0571888124385667,
      "grad_norm": 0.42754384875297546,
      "learning_rate": 2e-05,
      "loss": 0.779,
      "step": 640
    },
    {
      "epoch": 0.05808238763291931,
      "grad_norm": 0.3786719739437103,
      "learning_rate": 2e-05,
      "loss": 0.7636,
      "step": 650
    },
    {
      "epoch": 0.05897596282727192,
      "grad_norm": 0.36745455861091614,
      "learning_rate": 2e-05,
      "loss": 0.7749,
      "step": 660
    },
    {
      "epoch": 0.05986953802162452,
      "grad_norm": 0.44898897409439087,
      "learning_rate": 2e-05,
      "loss": 0.7306,
      "step": 670
    },
    {
      "epoch": 0.060763113215977126,
      "grad_norm": 0.4336882531642914,
      "learning_rate": 2e-05,
      "loss": 0.7385,
      "step": 680
    },
    {
      "epoch": 0.06165668841032973,
      "grad_norm": 0.3571746349334717,
      "learning_rate": 2e-05,
      "loss": 0.7209,
      "step": 690
    },
    {
      "epoch": 0.06255026360468234,
      "grad_norm": 0.4294300079345703,
      "learning_rate": 2e-05,
      "loss": 0.7694,
      "step": 700
    },
    {
      "epoch": 0.06344383879903494,
      "grad_norm": 0.3911939859390259,
      "learning_rate": 2e-05,
      "loss": 0.7571,
      "step": 710
    },
    {
      "epoch": 0.06433741399338755,
      "grad_norm": 0.44994938373565674,
      "learning_rate": 2e-05,
      "loss": 0.7509,
      "step": 720
    },
    {
      "epoch": 0.06523098918774015,
      "grad_norm": 0.43563222885131836,
      "learning_rate": 2e-05,
      "loss": 0.7727,
      "step": 730
    },
    {
      "epoch": 0.06612456438209276,
      "grad_norm": 0.4137369394302368,
      "learning_rate": 2e-05,
      "loss": 0.7598,
      "step": 740
    },
    {
      "epoch": 0.06701813957644535,
      "grad_norm": 0.3853653073310852,
      "learning_rate": 2e-05,
      "loss": 0.7585,
      "step": 750
    },
    {
      "epoch": 0.06791171477079797,
      "grad_norm": 0.3681003153324127,
      "learning_rate": 2e-05,
      "loss": 0.7394,
      "step": 760
    },
    {
      "epoch": 0.06880528996515056,
      "grad_norm": 0.3928927183151245,
      "learning_rate": 2e-05,
      "loss": 0.7484,
      "step": 770
    },
    {
      "epoch": 0.06969886515950317,
      "grad_norm": 0.387007474899292,
      "learning_rate": 2e-05,
      "loss": 0.7262,
      "step": 780
    },
    {
      "epoch": 0.07059244035385577,
      "grad_norm": 0.46645933389663696,
      "learning_rate": 2e-05,
      "loss": 0.7281,
      "step": 790
    },
    {
      "epoch": 0.07148601554820838,
      "grad_norm": 0.4278911352157593,
      "learning_rate": 2e-05,
      "loss": 0.7226,
      "step": 800
    },
    {
      "epoch": 0.07237959074256099,
      "grad_norm": 0.39950302243232727,
      "learning_rate": 2e-05,
      "loss": 0.7012,
      "step": 810
    },
    {
      "epoch": 0.07327316593691359,
      "grad_norm": 0.3807908892631531,
      "learning_rate": 2e-05,
      "loss": 0.7324,
      "step": 820
    },
    {
      "epoch": 0.0741667411312662,
      "grad_norm": 0.4291982352733612,
      "learning_rate": 2e-05,
      "loss": 0.7244,
      "step": 830
    },
    {
      "epoch": 0.0750603163256188,
      "grad_norm": 0.40053242444992065,
      "learning_rate": 2e-05,
      "loss": 0.7638,
      "step": 840
    },
    {
      "epoch": 0.07595389151997141,
      "grad_norm": 0.4022897481918335,
      "learning_rate": 2e-05,
      "loss": 0.753,
      "step": 850
    },
    {
      "epoch": 0.076847466714324,
      "grad_norm": 0.5166751146316528,
      "learning_rate": 2e-05,
      "loss": 0.7418,
      "step": 860
    },
    {
      "epoch": 0.07774104190867662,
      "grad_norm": 0.4001097083091736,
      "learning_rate": 2e-05,
      "loss": 0.7557,
      "step": 870
    },
    {
      "epoch": 0.07863461710302921,
      "grad_norm": 0.37985655665397644,
      "learning_rate": 2e-05,
      "loss": 0.7429,
      "step": 880
    },
    {
      "epoch": 0.07952819229738183,
      "grad_norm": 0.3874037563800812,
      "learning_rate": 2e-05,
      "loss": 0.7409,
      "step": 890
    },
    {
      "epoch": 0.08042176749173444,
      "grad_norm": 0.40059277415275574,
      "learning_rate": 2e-05,
      "loss": 0.7468,
      "step": 900
    },
    {
      "epoch": 0.08131534268608703,
      "grad_norm": 0.3915744423866272,
      "learning_rate": 2e-05,
      "loss": 0.7425,
      "step": 910
    },
    {
      "epoch": 0.08220891788043964,
      "grad_norm": 0.4296461343765259,
      "learning_rate": 2e-05,
      "loss": 0.7538,
      "step": 920
    },
    {
      "epoch": 0.08310249307479224,
      "grad_norm": 0.39975130558013916,
      "learning_rate": 2e-05,
      "loss": 0.7751,
      "step": 930
    },
    {
      "epoch": 0.08399606826914485,
      "grad_norm": 0.4234040379524231,
      "learning_rate": 2e-05,
      "loss": 0.7217,
      "step": 940
    },
    {
      "epoch": 0.08488964346349745,
      "grad_norm": 0.7239550352096558,
      "learning_rate": 2e-05,
      "loss": 0.7523,
      "step": 950
    },
    {
      "epoch": 0.08578321865785006,
      "grad_norm": 0.40926212072372437,
      "learning_rate": 2e-05,
      "loss": 0.7073,
      "step": 960
    },
    {
      "epoch": 0.08667679385220266,
      "grad_norm": 0.42253273725509644,
      "learning_rate": 2e-05,
      "loss": 0.7645,
      "step": 970
    },
    {
      "epoch": 0.08757036904655527,
      "grad_norm": 0.42166000604629517,
      "learning_rate": 2e-05,
      "loss": 0.7206,
      "step": 980
    },
    {
      "epoch": 0.08846394424090787,
      "grad_norm": 0.4257868826389313,
      "learning_rate": 2e-05,
      "loss": 0.7336,
      "step": 990
    },
    {
      "epoch": 0.08935751943526048,
      "grad_norm": 0.3908492922782898,
      "learning_rate": 2e-05,
      "loss": 0.7297,
      "step": 1000
    },
    {
      "epoch": 0.09025109462961309,
      "grad_norm": 0.38620543479919434,
      "learning_rate": 2e-05,
      "loss": 0.7451,
      "step": 1010
    },
    {
      "epoch": 0.09114466982396568,
      "grad_norm": 0.40934133529663086,
      "learning_rate": 2e-05,
      "loss": 0.7403,
      "step": 1020
    },
    {
      "epoch": 0.0920382450183183,
      "grad_norm": 0.435519814491272,
      "learning_rate": 2e-05,
      "loss": 0.7144,
      "step": 1030
    },
    {
      "epoch": 0.0929318202126709,
      "grad_norm": 0.46169203519821167,
      "learning_rate": 2e-05,
      "loss": 0.7317,
      "step": 1040
    },
    {
      "epoch": 0.0938253954070235,
      "grad_norm": 0.37340661883354187,
      "learning_rate": 2e-05,
      "loss": 0.7714,
      "step": 1050
    },
    {
      "epoch": 0.0947189706013761,
      "grad_norm": 0.41289299726486206,
      "learning_rate": 2e-05,
      "loss": 0.7351,
      "step": 1060
    },
    {
      "epoch": 0.09561254579572871,
      "grad_norm": 0.4187810719013214,
      "learning_rate": 2e-05,
      "loss": 0.7327,
      "step": 1070
    },
    {
      "epoch": 0.09650612099008131,
      "grad_norm": 0.41718336939811707,
      "learning_rate": 2e-05,
      "loss": 0.7864,
      "step": 1080
    },
    {
      "epoch": 0.09739969618443392,
      "grad_norm": 0.4145309329032898,
      "learning_rate": 2e-05,
      "loss": 0.7505,
      "step": 1090
    },
    {
      "epoch": 0.09829327137878653,
      "grad_norm": 0.4168350100517273,
      "learning_rate": 2e-05,
      "loss": 0.7359,
      "step": 1100
    },
    {
      "epoch": 0.09918684657313913,
      "grad_norm": 0.39129555225372314,
      "learning_rate": 2e-05,
      "loss": 0.7321,
      "step": 1110
    },
    {
      "epoch": 0.10008042176749174,
      "grad_norm": 0.39075788855552673,
      "learning_rate": 2e-05,
      "loss": 0.7625,
      "step": 1120
    },
    {
      "epoch": 0.10097399696184434,
      "grad_norm": 0.4408645033836365,
      "learning_rate": 2e-05,
      "loss": 0.7388,
      "step": 1130
    },
    {
      "epoch": 0.10186757215619695,
      "grad_norm": 0.3980259597301483,
      "learning_rate": 2e-05,
      "loss": 0.7537,
      "step": 1140
    },
    {
      "epoch": 0.10276114735054954,
      "grad_norm": 0.3763454556465149,
      "learning_rate": 2e-05,
      "loss": 0.7488,
      "step": 1150
    },
    {
      "epoch": 0.10365472254490216,
      "grad_norm": 0.37730491161346436,
      "learning_rate": 2e-05,
      "loss": 0.7465,
      "step": 1160
    },
    {
      "epoch": 0.10454829773925475,
      "grad_norm": 0.37538275122642517,
      "learning_rate": 2e-05,
      "loss": 0.7365,
      "step": 1170
    },
    {
      "epoch": 0.10544187293360736,
      "grad_norm": 0.397089421749115,
      "learning_rate": 2e-05,
      "loss": 0.769,
      "step": 1180
    },
    {
      "epoch": 0.10633544812795996,
      "grad_norm": 0.3705765902996063,
      "learning_rate": 2e-05,
      "loss": 0.7385,
      "step": 1190
    },
    {
      "epoch": 0.10722902332231257,
      "grad_norm": 0.3545670807361603,
      "learning_rate": 2e-05,
      "loss": 0.7408,
      "step": 1200
    },
    {
      "epoch": 0.10812259851666518,
      "grad_norm": 0.4176211357116699,
      "learning_rate": 2e-05,
      "loss": 0.7409,
      "step": 1210
    },
    {
      "epoch": 0.10901617371101778,
      "grad_norm": 0.36956384778022766,
      "learning_rate": 2e-05,
      "loss": 0.7246,
      "step": 1220
    },
    {
      "epoch": 0.10990974890537039,
      "grad_norm": 0.3938690423965454,
      "learning_rate": 2e-05,
      "loss": 0.7292,
      "step": 1230
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": 0.39145007729530334,
      "learning_rate": 2e-05,
      "loss": 0.7285,
      "step": 1240
    },
    {
      "epoch": 0.1116968992940756,
      "grad_norm": 0.38112127780914307,
      "learning_rate": 2e-05,
      "loss": 0.7551,
      "step": 1250
    },
    {
      "epoch": 0.1125904744884282,
      "grad_norm": 0.3316250741481781,
      "learning_rate": 2e-05,
      "loss": 0.7323,
      "step": 1260
    },
    {
      "epoch": 0.11348404968278081,
      "grad_norm": 0.4049963057041168,
      "learning_rate": 2e-05,
      "loss": 0.7329,
      "step": 1270
    },
    {
      "epoch": 0.1143776248771334,
      "grad_norm": 0.48271071910858154,
      "learning_rate": 2e-05,
      "loss": 0.7696,
      "step": 1280
    },
    {
      "epoch": 0.11527120007148602,
      "grad_norm": 0.37332484126091003,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 1290
    },
    {
      "epoch": 0.11616477526583863,
      "grad_norm": 0.3976444602012634,
      "learning_rate": 2e-05,
      "loss": 0.7259,
      "step": 1300
    },
    {
      "epoch": 0.11705835046019122,
      "grad_norm": 0.39804327487945557,
      "learning_rate": 2e-05,
      "loss": 0.7406,
      "step": 1310
    },
    {
      "epoch": 0.11795192565454383,
      "grad_norm": 0.4065830707550049,
      "learning_rate": 2e-05,
      "loss": 0.7332,
      "step": 1320
    },
    {
      "epoch": 0.11884550084889643,
      "grad_norm": 0.38445714116096497,
      "learning_rate": 2e-05,
      "loss": 0.7277,
      "step": 1330
    },
    {
      "epoch": 0.11973907604324904,
      "grad_norm": 0.3987727761268616,
      "learning_rate": 2e-05,
      "loss": 0.6999,
      "step": 1340
    },
    {
      "epoch": 0.12063265123760164,
      "grad_norm": 0.37083423137664795,
      "learning_rate": 2e-05,
      "loss": 0.7425,
      "step": 1350
    },
    {
      "epoch": 0.12152622643195425,
      "grad_norm": 0.4784857928752899,
      "learning_rate": 2e-05,
      "loss": 0.7522,
      "step": 1360
    },
    {
      "epoch": 0.12241980162630685,
      "grad_norm": 0.39088118076324463,
      "learning_rate": 2e-05,
      "loss": 0.7366,
      "step": 1370
    },
    {
      "epoch": 0.12331337682065946,
      "grad_norm": 0.39330583810806274,
      "learning_rate": 2e-05,
      "loss": 0.7293,
      "step": 1380
    },
    {
      "epoch": 0.12420695201501206,
      "grad_norm": 0.3860457241535187,
      "learning_rate": 2e-05,
      "loss": 0.7143,
      "step": 1390
    },
    {
      "epoch": 0.12510052720936468,
      "grad_norm": 0.38415059447288513,
      "learning_rate": 2e-05,
      "loss": 0.6834,
      "step": 1400
    },
    {
      "epoch": 0.12599410240371728,
      "grad_norm": 0.39965566992759705,
      "learning_rate": 2e-05,
      "loss": 0.7087,
      "step": 1410
    },
    {
      "epoch": 0.12688767759806988,
      "grad_norm": 0.38492318987846375,
      "learning_rate": 2e-05,
      "loss": 0.7547,
      "step": 1420
    },
    {
      "epoch": 0.12778125279242247,
      "grad_norm": 0.41795384883880615,
      "learning_rate": 2e-05,
      "loss": 0.7267,
      "step": 1430
    },
    {
      "epoch": 0.1286748279867751,
      "grad_norm": 0.3837740123271942,
      "learning_rate": 2e-05,
      "loss": 0.74,
      "step": 1440
    },
    {
      "epoch": 0.1295684031811277,
      "grad_norm": 0.35027605295181274,
      "learning_rate": 2e-05,
      "loss": 0.6958,
      "step": 1450
    },
    {
      "epoch": 0.1304619783754803,
      "grad_norm": 0.36292174458503723,
      "learning_rate": 2e-05,
      "loss": 0.7441,
      "step": 1460
    },
    {
      "epoch": 0.1313555535698329,
      "grad_norm": 0.3984721899032593,
      "learning_rate": 2e-05,
      "loss": 0.7197,
      "step": 1470
    },
    {
      "epoch": 0.13224912876418551,
      "grad_norm": 0.4132763147354126,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 1480
    },
    {
      "epoch": 0.1331427039585381,
      "grad_norm": 0.3790658712387085,
      "learning_rate": 2e-05,
      "loss": 0.7274,
      "step": 1490
    },
    {
      "epoch": 0.1340362791528907,
      "grad_norm": 0.3779606819152832,
      "learning_rate": 2e-05,
      "loss": 0.7259,
      "step": 1500
    },
    {
      "epoch": 0.13492985434724333,
      "grad_norm": 0.9285029172897339,
      "learning_rate": 2e-05,
      "loss": 0.7231,
      "step": 1510
    },
    {
      "epoch": 0.13582342954159593,
      "grad_norm": 0.3995453119277954,
      "learning_rate": 2e-05,
      "loss": 0.7022,
      "step": 1520
    },
    {
      "epoch": 0.13671700473594853,
      "grad_norm": 0.4919504225254059,
      "learning_rate": 2e-05,
      "loss": 0.7461,
      "step": 1530
    },
    {
      "epoch": 0.13761057993030112,
      "grad_norm": 0.37025532126426697,
      "learning_rate": 2e-05,
      "loss": 0.7226,
      "step": 1540
    },
    {
      "epoch": 0.13850415512465375,
      "grad_norm": 0.3523809611797333,
      "learning_rate": 2e-05,
      "loss": 0.7124,
      "step": 1550
    },
    {
      "epoch": 0.13939773031900635,
      "grad_norm": 0.4186336398124695,
      "learning_rate": 2e-05,
      "loss": 0.724,
      "step": 1560
    },
    {
      "epoch": 0.14029130551335894,
      "grad_norm": 0.39147084951400757,
      "learning_rate": 2e-05,
      "loss": 0.7444,
      "step": 1570
    },
    {
      "epoch": 0.14118488070771154,
      "grad_norm": 0.3777700364589691,
      "learning_rate": 2e-05,
      "loss": 0.7383,
      "step": 1580
    },
    {
      "epoch": 0.14207845590206417,
      "grad_norm": 0.41446128487586975,
      "learning_rate": 2e-05,
      "loss": 0.735,
      "step": 1590
    },
    {
      "epoch": 0.14297203109641676,
      "grad_norm": 0.38765832781791687,
      "learning_rate": 2e-05,
      "loss": 0.7147,
      "step": 1600
    },
    {
      "epoch": 0.14386560629076936,
      "grad_norm": 0.5072250962257385,
      "learning_rate": 2e-05,
      "loss": 0.7163,
      "step": 1610
    },
    {
      "epoch": 0.14475918148512198,
      "grad_norm": 0.3880365490913391,
      "learning_rate": 2e-05,
      "loss": 0.7141,
      "step": 1620
    },
    {
      "epoch": 0.14565275667947458,
      "grad_norm": 0.35895800590515137,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 1630
    },
    {
      "epoch": 0.14654633187382718,
      "grad_norm": 0.35093289613723755,
      "learning_rate": 2e-05,
      "loss": 0.7359,
      "step": 1640
    },
    {
      "epoch": 0.14743990706817978,
      "grad_norm": 0.3536919951438904,
      "learning_rate": 2e-05,
      "loss": 0.739,
      "step": 1650
    },
    {
      "epoch": 0.1483334822625324,
      "grad_norm": 0.6556247472763062,
      "learning_rate": 2e-05,
      "loss": 0.7185,
      "step": 1660
    },
    {
      "epoch": 0.149227057456885,
      "grad_norm": 0.3924124538898468,
      "learning_rate": 2e-05,
      "loss": 0.747,
      "step": 1670
    },
    {
      "epoch": 0.1501206326512376,
      "grad_norm": 0.8066271543502808,
      "learning_rate": 2e-05,
      "loss": 0.7584,
      "step": 1680
    },
    {
      "epoch": 0.1510142078455902,
      "grad_norm": 0.4922969341278076,
      "learning_rate": 2e-05,
      "loss": 0.7044,
      "step": 1690
    },
    {
      "epoch": 0.15190778303994282,
      "grad_norm": 0.34611326456069946,
      "learning_rate": 2e-05,
      "loss": 0.7443,
      "step": 1700
    },
    {
      "epoch": 0.15280135823429541,
      "grad_norm": 0.3866153657436371,
      "learning_rate": 2e-05,
      "loss": 0.725,
      "step": 1710
    },
    {
      "epoch": 0.153694933428648,
      "grad_norm": 0.36212798953056335,
      "learning_rate": 2e-05,
      "loss": 0.7245,
      "step": 1720
    },
    {
      "epoch": 0.15458850862300064,
      "grad_norm": 0.3953538239002228,
      "learning_rate": 2e-05,
      "loss": 0.7347,
      "step": 1730
    },
    {
      "epoch": 0.15548208381735323,
      "grad_norm": 0.4102666676044464,
      "learning_rate": 2e-05,
      "loss": 0.736,
      "step": 1740
    },
    {
      "epoch": 0.15637565901170583,
      "grad_norm": 0.4497690498828888,
      "learning_rate": 2e-05,
      "loss": 0.7245,
      "step": 1750
    },
    {
      "epoch": 0.15726923420605843,
      "grad_norm": 0.4439946711063385,
      "learning_rate": 2e-05,
      "loss": 0.7347,
      "step": 1760
    },
    {
      "epoch": 0.15816280940041105,
      "grad_norm": 1.074998140335083,
      "learning_rate": 2e-05,
      "loss": 0.7432,
      "step": 1770
    },
    {
      "epoch": 0.15905638459476365,
      "grad_norm": 0.3673039972782135,
      "learning_rate": 2e-05,
      "loss": 0.7465,
      "step": 1780
    },
    {
      "epoch": 0.15994995978911625,
      "grad_norm": 0.3478325605392456,
      "learning_rate": 2e-05,
      "loss": 0.7225,
      "step": 1790
    },
    {
      "epoch": 0.16084353498346887,
      "grad_norm": 0.3802620470523834,
      "learning_rate": 2e-05,
      "loss": 0.6983,
      "step": 1800
    },
    {
      "epoch": 0.16173711017782147,
      "grad_norm": 0.38965746760368347,
      "learning_rate": 2e-05,
      "loss": 0.712,
      "step": 1810
    },
    {
      "epoch": 0.16263068537217407,
      "grad_norm": 0.3660908043384552,
      "learning_rate": 2e-05,
      "loss": 0.7198,
      "step": 1820
    },
    {
      "epoch": 0.16352426056652666,
      "grad_norm": 0.38565513491630554,
      "learning_rate": 2e-05,
      "loss": 0.7118,
      "step": 1830
    },
    {
      "epoch": 0.1644178357608793,
      "grad_norm": 0.49884864687919617,
      "learning_rate": 2e-05,
      "loss": 0.7378,
      "step": 1840
    },
    {
      "epoch": 0.16531141095523189,
      "grad_norm": 0.3706195652484894,
      "learning_rate": 2e-05,
      "loss": 0.7051,
      "step": 1850
    },
    {
      "epoch": 0.16620498614958448,
      "grad_norm": 0.3866501450538635,
      "learning_rate": 2e-05,
      "loss": 0.7321,
      "step": 1860
    },
    {
      "epoch": 0.16709856134393708,
      "grad_norm": 0.38853004574775696,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 1870
    },
    {
      "epoch": 0.1679921365382897,
      "grad_norm": 0.42117682099342346,
      "learning_rate": 2e-05,
      "loss": 0.7241,
      "step": 1880
    },
    {
      "epoch": 0.1688857117326423,
      "grad_norm": 0.4492304027080536,
      "learning_rate": 2e-05,
      "loss": 0.7349,
      "step": 1890
    },
    {
      "epoch": 0.1697792869269949,
      "grad_norm": 0.4259665608406067,
      "learning_rate": 2e-05,
      "loss": 0.7128,
      "step": 1900
    },
    {
      "epoch": 0.17067286212134752,
      "grad_norm": 0.3557761609554291,
      "learning_rate": 2e-05,
      "loss": 0.6986,
      "step": 1910
    },
    {
      "epoch": 0.17156643731570012,
      "grad_norm": 0.35731881856918335,
      "learning_rate": 2e-05,
      "loss": 0.7351,
      "step": 1920
    },
    {
      "epoch": 0.17246001251005272,
      "grad_norm": 0.38917088508605957,
      "learning_rate": 2e-05,
      "loss": 0.721,
      "step": 1930
    },
    {
      "epoch": 0.17335358770440532,
      "grad_norm": 0.39296889305114746,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 1940
    },
    {
      "epoch": 0.17424716289875794,
      "grad_norm": 0.3701498508453369,
      "learning_rate": 2e-05,
      "loss": 0.7699,
      "step": 1950
    },
    {
      "epoch": 0.17514073809311054,
      "grad_norm": 0.3800022006034851,
      "learning_rate": 2e-05,
      "loss": 0.7222,
      "step": 1960
    },
    {
      "epoch": 0.17603431328746313,
      "grad_norm": 0.3638252913951874,
      "learning_rate": 2e-05,
      "loss": 0.6871,
      "step": 1970
    },
    {
      "epoch": 0.17692788848181573,
      "grad_norm": 0.38935279846191406,
      "learning_rate": 2e-05,
      "loss": 0.6952,
      "step": 1980
    },
    {
      "epoch": 0.17782146367616836,
      "grad_norm": 0.40048500895500183,
      "learning_rate": 2e-05,
      "loss": 0.697,
      "step": 1990
    },
    {
      "epoch": 0.17871503887052095,
      "grad_norm": 0.41115978360176086,
      "learning_rate": 2e-05,
      "loss": 0.7409,
      "step": 2000
    },
    {
      "epoch": 0.17960861406487355,
      "grad_norm": 0.39649268984794617,
      "learning_rate": 2e-05,
      "loss": 0.7172,
      "step": 2010
    },
    {
      "epoch": 0.18050218925922618,
      "grad_norm": 0.5061083436012268,
      "learning_rate": 2e-05,
      "loss": 0.7264,
      "step": 2020
    },
    {
      "epoch": 0.18139576445357877,
      "grad_norm": 0.38063013553619385,
      "learning_rate": 2e-05,
      "loss": 0.7434,
      "step": 2030
    },
    {
      "epoch": 0.18228933964793137,
      "grad_norm": 0.4168822169303894,
      "learning_rate": 2e-05,
      "loss": 0.7063,
      "step": 2040
    },
    {
      "epoch": 0.18318291484228397,
      "grad_norm": 0.36266323924064636,
      "learning_rate": 2e-05,
      "loss": 0.7401,
      "step": 2050
    },
    {
      "epoch": 0.1840764900366366,
      "grad_norm": 0.37227675318717957,
      "learning_rate": 2e-05,
      "loss": 0.7144,
      "step": 2060
    },
    {
      "epoch": 0.1849700652309892,
      "grad_norm": 0.39245229959487915,
      "learning_rate": 2e-05,
      "loss": 0.7084,
      "step": 2070
    },
    {
      "epoch": 0.1858636404253418,
      "grad_norm": 0.37118712067604065,
      "learning_rate": 2e-05,
      "loss": 0.7217,
      "step": 2080
    },
    {
      "epoch": 0.1867572156196944,
      "grad_norm": 0.3615480661392212,
      "learning_rate": 2e-05,
      "loss": 0.7143,
      "step": 2090
    },
    {
      "epoch": 0.187650790814047,
      "grad_norm": 0.4019179046154022,
      "learning_rate": 2e-05,
      "loss": 0.7449,
      "step": 2100
    },
    {
      "epoch": 0.1885443660083996,
      "grad_norm": 0.38081419467926025,
      "learning_rate": 2e-05,
      "loss": 0.724,
      "step": 2110
    },
    {
      "epoch": 0.1894379412027522,
      "grad_norm": 0.39533179998397827,
      "learning_rate": 2e-05,
      "loss": 0.7065,
      "step": 2120
    },
    {
      "epoch": 0.19033151639710483,
      "grad_norm": 0.4144379794597626,
      "learning_rate": 2e-05,
      "loss": 0.7177,
      "step": 2130
    },
    {
      "epoch": 0.19122509159145742,
      "grad_norm": 0.38099774718284607,
      "learning_rate": 2e-05,
      "loss": 0.7035,
      "step": 2140
    },
    {
      "epoch": 0.19211866678581002,
      "grad_norm": 0.36082664132118225,
      "learning_rate": 2e-05,
      "loss": 0.729,
      "step": 2150
    },
    {
      "epoch": 0.19301224198016262,
      "grad_norm": 0.38504886627197266,
      "learning_rate": 2e-05,
      "loss": 0.7049,
      "step": 2160
    },
    {
      "epoch": 0.19390581717451524,
      "grad_norm": 0.3863053619861603,
      "learning_rate": 2e-05,
      "loss": 0.6846,
      "step": 2170
    },
    {
      "epoch": 0.19479939236886784,
      "grad_norm": 0.3692690432071686,
      "learning_rate": 2e-05,
      "loss": 0.7298,
      "step": 2180
    },
    {
      "epoch": 0.19569296756322044,
      "grad_norm": 0.3638010621070862,
      "learning_rate": 2e-05,
      "loss": 0.7256,
      "step": 2190
    },
    {
      "epoch": 0.19658654275757306,
      "grad_norm": 0.3824363648891449,
      "learning_rate": 2e-05,
      "loss": 0.7376,
      "step": 2200
    },
    {
      "epoch": 0.19748011795192566,
      "grad_norm": 0.35318830609321594,
      "learning_rate": 2e-05,
      "loss": 0.736,
      "step": 2210
    },
    {
      "epoch": 0.19837369314627826,
      "grad_norm": 0.35539188981056213,
      "learning_rate": 2e-05,
      "loss": 0.7027,
      "step": 2220
    },
    {
      "epoch": 0.19926726834063085,
      "grad_norm": 0.414533406496048,
      "learning_rate": 2e-05,
      "loss": 0.6909,
      "step": 2230
    },
    {
      "epoch": 0.20016084353498348,
      "grad_norm": 0.39531072974205017,
      "learning_rate": 2e-05,
      "loss": 0.7301,
      "step": 2240
    },
    {
      "epoch": 0.20105441872933608,
      "grad_norm": 0.3679538071155548,
      "learning_rate": 2e-05,
      "loss": 0.7203,
      "step": 2250
    },
    {
      "epoch": 0.20194799392368867,
      "grad_norm": 0.37164831161499023,
      "learning_rate": 2e-05,
      "loss": 0.725,
      "step": 2260
    },
    {
      "epoch": 0.20284156911804127,
      "grad_norm": 0.3633818030357361,
      "learning_rate": 2e-05,
      "loss": 0.7192,
      "step": 2270
    },
    {
      "epoch": 0.2037351443123939,
      "grad_norm": 0.3682442307472229,
      "learning_rate": 2e-05,
      "loss": 0.7099,
      "step": 2280
    },
    {
      "epoch": 0.2046287195067465,
      "grad_norm": 0.34997084736824036,
      "learning_rate": 2e-05,
      "loss": 0.7543,
      "step": 2290
    },
    {
      "epoch": 0.2055222947010991,
      "grad_norm": 0.403976172208786,
      "learning_rate": 2e-05,
      "loss": 0.7511,
      "step": 2300
    },
    {
      "epoch": 0.20641586989545171,
      "grad_norm": 0.41093239188194275,
      "learning_rate": 2e-05,
      "loss": 0.6794,
      "step": 2310
    },
    {
      "epoch": 0.2073094450898043,
      "grad_norm": 0.38257455825805664,
      "learning_rate": 2e-05,
      "loss": 0.7263,
      "step": 2320
    },
    {
      "epoch": 0.2082030202841569,
      "grad_norm": 0.3526884615421295,
      "learning_rate": 2e-05,
      "loss": 0.7185,
      "step": 2330
    },
    {
      "epoch": 0.2090965954785095,
      "grad_norm": 0.3658798336982727,
      "learning_rate": 2e-05,
      "loss": 0.7128,
      "step": 2340
    },
    {
      "epoch": 0.20999017067286213,
      "grad_norm": 0.3977317214012146,
      "learning_rate": 2e-05,
      "loss": 0.6795,
      "step": 2350
    },
    {
      "epoch": 0.21088374586721473,
      "grad_norm": 0.386541485786438,
      "learning_rate": 2e-05,
      "loss": 0.7196,
      "step": 2360
    },
    {
      "epoch": 0.21177732106156733,
      "grad_norm": 0.39826154708862305,
      "learning_rate": 2e-05,
      "loss": 0.6952,
      "step": 2370
    },
    {
      "epoch": 0.21267089625591992,
      "grad_norm": 0.4097355902194977,
      "learning_rate": 2e-05,
      "loss": 0.7117,
      "step": 2380
    },
    {
      "epoch": 0.21356447145027255,
      "grad_norm": 0.3464928865432739,
      "learning_rate": 2e-05,
      "loss": 0.7126,
      "step": 2390
    },
    {
      "epoch": 0.21445804664462514,
      "grad_norm": 0.397562712430954,
      "learning_rate": 2e-05,
      "loss": 0.7197,
      "step": 2400
    },
    {
      "epoch": 0.21535162183897774,
      "grad_norm": 0.35849079489707947,
      "learning_rate": 2e-05,
      "loss": 0.7525,
      "step": 2410
    },
    {
      "epoch": 0.21624519703333037,
      "grad_norm": 0.5133382081985474,
      "learning_rate": 2e-05,
      "loss": 0.7267,
      "step": 2420
    },
    {
      "epoch": 0.21713877222768296,
      "grad_norm": 0.37571123242378235,
      "learning_rate": 2e-05,
      "loss": 0.7223,
      "step": 2430
    },
    {
      "epoch": 0.21803234742203556,
      "grad_norm": 0.3847047686576843,
      "learning_rate": 2e-05,
      "loss": 0.7139,
      "step": 2440
    },
    {
      "epoch": 0.21892592261638816,
      "grad_norm": 0.3535878360271454,
      "learning_rate": 2e-05,
      "loss": 0.6956,
      "step": 2450
    },
    {
      "epoch": 0.21981949781074078,
      "grad_norm": 0.3725936710834503,
      "learning_rate": 2e-05,
      "loss": 0.7107,
      "step": 2460
    },
    {
      "epoch": 0.22071307300509338,
      "grad_norm": 0.4022907316684723,
      "learning_rate": 2e-05,
      "loss": 0.7524,
      "step": 2470
    },
    {
      "epoch": 0.22160664819944598,
      "grad_norm": 0.3813494145870209,
      "learning_rate": 2e-05,
      "loss": 0.7229,
      "step": 2480
    },
    {
      "epoch": 0.2225002233937986,
      "grad_norm": 0.38350072503089905,
      "learning_rate": 2e-05,
      "loss": 0.6846,
      "step": 2490
    },
    {
      "epoch": 0.2233937985881512,
      "grad_norm": 0.3981742858886719,
      "learning_rate": 2e-05,
      "loss": 0.7362,
      "step": 2500
    },
    {
      "epoch": 0.2242873737825038,
      "grad_norm": 0.3835667371749878,
      "learning_rate": 2e-05,
      "loss": 0.7107,
      "step": 2510
    },
    {
      "epoch": 0.2251809489768564,
      "grad_norm": 0.372981458902359,
      "learning_rate": 2e-05,
      "loss": 0.7333,
      "step": 2520
    },
    {
      "epoch": 0.22607452417120902,
      "grad_norm": 0.35782164335250854,
      "learning_rate": 2e-05,
      "loss": 0.6753,
      "step": 2530
    },
    {
      "epoch": 0.22696809936556162,
      "grad_norm": 0.36539599299430847,
      "learning_rate": 2e-05,
      "loss": 0.6941,
      "step": 2540
    },
    {
      "epoch": 0.2278616745599142,
      "grad_norm": 0.3641797602176666,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.7003,
      "step": 2550
    },
    {
      "epoch": 0.2287552497542668,
      "grad_norm": 0.3908218741416931,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.7171,
      "step": 2560
    },
    {
      "epoch": 0.22964882494861943,
      "grad_norm": 0.3739090859889984,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.7238,
      "step": 2570
    },
    {
      "epoch": 0.23054240014297203,
      "grad_norm": 0.35324692726135254,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.7372,
      "step": 2580
    },
    {
      "epoch": 0.23143597533732463,
      "grad_norm": 0.33299797773361206,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.7282,
      "step": 2590
    },
    {
      "epoch": 0.23232955053167725,
      "grad_norm": 0.3834870755672455,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.7101,
      "step": 2600
    },
    {
      "epoch": 0.23322312572602985,
      "grad_norm": 0.37206247448921204,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7149,
      "step": 2610
    },
    {
      "epoch": 0.23411670092038245,
      "grad_norm": 0.3407863974571228,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.6833,
      "step": 2620
    },
    {
      "epoch": 0.23501027611473504,
      "grad_norm": 0.3490702211856842,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.7151,
      "step": 2630
    },
    {
      "epoch": 0.23590385130908767,
      "grad_norm": 0.42282992601394653,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.7236,
      "step": 2640
    },
    {
      "epoch": 0.23679742650344027,
      "grad_norm": 0.37569499015808105,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.7272,
      "step": 2650
    },
    {
      "epoch": 0.23769100169779286,
      "grad_norm": 0.3724175691604614,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.6958,
      "step": 2660
    },
    {
      "epoch": 0.23858457689214546,
      "grad_norm": 0.4494756758213043,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.7067,
      "step": 2670
    },
    {
      "epoch": 0.2394781520864981,
      "grad_norm": 0.34761565923690796,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.7021,
      "step": 2680
    },
    {
      "epoch": 0.24037172728085068,
      "grad_norm": 0.36299169063568115,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.7207,
      "step": 2690
    },
    {
      "epoch": 0.24126530247520328,
      "grad_norm": 0.340032160282135,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.7037,
      "step": 2700
    },
    {
      "epoch": 0.2421588776695559,
      "grad_norm": 0.37072521448135376,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.719,
      "step": 2710
    },
    {
      "epoch": 0.2430524528639085,
      "grad_norm": 0.35150226950645447,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.6827,
      "step": 2720
    },
    {
      "epoch": 0.2439460280582611,
      "grad_norm": 0.338276743888855,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.7066,
      "step": 2730
    },
    {
      "epoch": 0.2448396032526137,
      "grad_norm": 0.35572388768196106,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.6919,
      "step": 2740
    },
    {
      "epoch": 0.24573317844696632,
      "grad_norm": 0.33749139308929443,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.7166,
      "step": 2750
    },
    {
      "epoch": 0.24662675364131892,
      "grad_norm": 0.35095369815826416,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.6657,
      "step": 2760
    },
    {
      "epoch": 0.24752032883567152,
      "grad_norm": 0.36238694190979004,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.7269,
      "step": 2770
    },
    {
      "epoch": 0.2484139040300241,
      "grad_norm": 0.3502151668071747,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.698,
      "step": 2780
    },
    {
      "epoch": 0.24930747922437674,
      "grad_norm": 0.33529016375541687,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.7113,
      "step": 2790
    },
    {
      "epoch": 0.2500223393798588,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06420274203466125,
      "train_runtime": 2294.7753,
      "train_samples_per_second": 14.631,
      "train_steps_per_second": 1.219
    }
  ],
  "logging_steps": 10,
  "max_steps": 2798,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 159,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1366756130249245e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}