{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23246925888999667,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008308408109006315,
      "grad_norm": 5.0185394287109375,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 1.7151,
      "step": 10
    },
    {
      "epoch": 0.001661681621801263,
      "grad_norm": 2.385542631149292,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 1.7579,
      "step": 20
    },
    {
      "epoch": 0.0024925224327018943,
      "grad_norm": 2.753164291381836,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.4674,
      "step": 30
    },
    {
      "epoch": 0.003323363243602526,
      "grad_norm": 0.8955636024475098,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.2782,
      "step": 40
    },
    {
      "epoch": 0.004154204054503157,
      "grad_norm": 0.9788411855697632,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 1.1572,
      "step": 50
    },
    {
      "epoch": 0.004985044865403789,
      "grad_norm": 0.5795058012008667,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 1.1187,
      "step": 60
    },
    {
      "epoch": 0.00581588567630442,
      "grad_norm": 0.6206412315368652,
      "learning_rate": 7.814044943820226e-06,
      "loss": 1.0551,
      "step": 70
    },
    {
      "epoch": 0.006646726487205052,
      "grad_norm": 0.604301929473877,
      "learning_rate": 8.932022471910112e-06,
      "loss": 1.0394,
      "step": 80
    },
    {
      "epoch": 0.007477567298105683,
      "grad_norm": 0.6093521118164062,
      "learning_rate": 1.005e-05,
      "loss": 1.0592,
      "step": 90
    },
    {
      "epoch": 0.008308408109006314,
      "grad_norm": 0.6659312844276428,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 1.0234,
      "step": 100
    },
    {
      "epoch": 0.009139248919906947,
      "grad_norm": 0.5740776658058167,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 1.0529,
      "step": 110
    },
    {
      "epoch": 0.009970089730807577,
      "grad_norm": 0.576384961605072,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.9948,
      "step": 120
    },
    {
      "epoch": 0.010800930541708208,
      "grad_norm": 0.953546941280365,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 1.0426,
      "step": 130
    },
    {
      "epoch": 0.01163177135260884,
      "grad_norm": 0.5870928168296814,
      "learning_rate": 1.563988764044944e-05,
      "loss": 1.0148,
      "step": 140
    },
    {
      "epoch": 0.012462612163509471,
      "grad_norm": 0.6562204360961914,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 1.0398,
      "step": 150
    },
    {
      "epoch": 0.013293452974410104,
      "grad_norm": 0.5265231132507324,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 1.0222,
      "step": 160
    },
    {
      "epoch": 0.014124293785310734,
      "grad_norm": 0.5627759099006653,
      "learning_rate": 1.89938202247191e-05,
      "loss": 1.0173,
      "step": 170
    },
    {
      "epoch": 0.014955134596211365,
      "grad_norm": 0.5194225907325745,
      "learning_rate": 2e-05,
      "loss": 0.989,
      "step": 180
    },
    {
      "epoch": 0.015785975407111998,
      "grad_norm": 0.5717377066612244,
      "learning_rate": 2e-05,
      "loss": 0.9578,
      "step": 190
    },
    {
      "epoch": 0.01661681621801263,
      "grad_norm": 0.5366178750991821,
      "learning_rate": 2e-05,
      "loss": 1.0255,
      "step": 200
    },
    {
      "epoch": 0.01744765702891326,
      "grad_norm": 0.6772796511650085,
      "learning_rate": 2e-05,
      "loss": 1.0158,
      "step": 210
    },
    {
      "epoch": 0.018278497839813893,
      "grad_norm": 0.5122703909873962,
      "learning_rate": 2e-05,
      "loss": 1.0005,
      "step": 220
    },
    {
      "epoch": 0.019109338650714524,
      "grad_norm": 0.6427125334739685,
      "learning_rate": 2e-05,
      "loss": 1.0214,
      "step": 230
    },
    {
      "epoch": 0.019940179461615155,
      "grad_norm": 0.49990859627723694,
      "learning_rate": 2e-05,
      "loss": 0.9847,
      "step": 240
    },
    {
      "epoch": 0.020771020272515785,
      "grad_norm": 0.5407299399375916,
      "learning_rate": 2e-05,
      "loss": 0.9808,
      "step": 250
    },
    {
      "epoch": 0.021601861083416416,
      "grad_norm": 0.5241397619247437,
      "learning_rate": 2e-05,
      "loss": 0.9863,
      "step": 260
    },
    {
      "epoch": 0.02243270189431705,
      "grad_norm": 0.5140271782875061,
      "learning_rate": 2e-05,
      "loss": 1.0024,
      "step": 270
    },
    {
      "epoch": 0.02326354270521768,
      "grad_norm": 0.5602551698684692,
      "learning_rate": 2e-05,
      "loss": 0.9681,
      "step": 280
    },
    {
      "epoch": 0.024094383516118312,
      "grad_norm": 0.5047415494918823,
      "learning_rate": 2e-05,
      "loss": 1.007,
      "step": 290
    },
    {
      "epoch": 0.024925224327018942,
      "grad_norm": 0.4970276653766632,
      "learning_rate": 2e-05,
      "loss": 0.9759,
      "step": 300
    },
    {
      "epoch": 0.025756065137919573,
      "grad_norm": 0.5245757102966309,
      "learning_rate": 2e-05,
      "loss": 0.9802,
      "step": 310
    },
    {
      "epoch": 0.026586905948820207,
      "grad_norm": 0.5001291036605835,
      "learning_rate": 2e-05,
      "loss": 0.9628,
      "step": 320
    },
    {
      "epoch": 0.027417746759720838,
      "grad_norm": 0.5402788519859314,
      "learning_rate": 2e-05,
      "loss": 0.9878,
      "step": 330
    },
    {
      "epoch": 0.02824858757062147,
      "grad_norm": 0.5057405829429626,
      "learning_rate": 2e-05,
      "loss": 1.017,
      "step": 340
    },
    {
      "epoch": 0.0290794283815221,
      "grad_norm": 0.5450842380523682,
      "learning_rate": 2e-05,
      "loss": 0.9815,
      "step": 350
    },
    {
      "epoch": 0.02991026919242273,
      "grad_norm": 0.6072407364845276,
      "learning_rate": 2e-05,
      "loss": 1.0245,
      "step": 360
    },
    {
      "epoch": 0.030741110003323364,
      "grad_norm": 0.5196362733840942,
      "learning_rate": 2e-05,
      "loss": 0.9699,
      "step": 370
    },
    {
      "epoch": 0.031571950814223995,
      "grad_norm": 0.5128522515296936,
      "learning_rate": 2e-05,
      "loss": 1.0091,
      "step": 380
    },
    {
      "epoch": 0.032402791625124626,
      "grad_norm": 0.6012204885482788,
      "learning_rate": 2e-05,
      "loss": 0.985,
      "step": 390
    },
    {
      "epoch": 0.03323363243602526,
      "grad_norm": 0.5065486431121826,
      "learning_rate": 2e-05,
      "loss": 0.9606,
      "step": 400
    },
    {
      "epoch": 0.03406447324692589,
      "grad_norm": 0.5270485281944275,
      "learning_rate": 2e-05,
      "loss": 0.9496,
      "step": 410
    },
    {
      "epoch": 0.03489531405782652,
      "grad_norm": 0.5859076380729675,
      "learning_rate": 2e-05,
      "loss": 0.9841,
      "step": 420
    },
    {
      "epoch": 0.03572615486872715,
      "grad_norm": 0.5001581311225891,
      "learning_rate": 2e-05,
      "loss": 0.9435,
      "step": 430
    },
    {
      "epoch": 0.036556995679627786,
      "grad_norm": 0.5033804178237915,
      "learning_rate": 2e-05,
      "loss": 1.0107,
      "step": 440
    },
    {
      "epoch": 0.03738783649052842,
      "grad_norm": 0.48901426792144775,
      "learning_rate": 2e-05,
      "loss": 0.9775,
      "step": 450
    },
    {
      "epoch": 0.03821867730142905,
      "grad_norm": 0.4957520067691803,
      "learning_rate": 2e-05,
      "loss": 0.9657,
      "step": 460
    },
    {
      "epoch": 0.03904951811232968,
      "grad_norm": 0.48940908908843994,
      "learning_rate": 2e-05,
      "loss": 0.9631,
      "step": 470
    },
    {
      "epoch": 0.03988035892323031,
      "grad_norm": 0.4692400097846985,
      "learning_rate": 2e-05,
      "loss": 0.9791,
      "step": 480
    },
    {
      "epoch": 0.04071119973413094,
      "grad_norm": 0.49479761719703674,
      "learning_rate": 2e-05,
      "loss": 0.9712,
      "step": 490
    },
    {
      "epoch": 0.04154204054503157,
      "grad_norm": 0.5517172813415527,
      "learning_rate": 2e-05,
      "loss": 0.9865,
      "step": 500
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 0.5271807312965393,
      "learning_rate": 2e-05,
      "loss": 0.9872,
      "step": 510
    },
    {
      "epoch": 0.04320372216683283,
      "grad_norm": 0.5044783353805542,
      "learning_rate": 2e-05,
      "loss": 0.9525,
      "step": 520
    },
    {
      "epoch": 0.04403456297773346,
      "grad_norm": 0.5325606465339661,
      "learning_rate": 2e-05,
      "loss": 0.9773,
      "step": 530
    },
    {
      "epoch": 0.0448654037886341,
      "grad_norm": 0.463705837726593,
      "learning_rate": 2e-05,
      "loss": 0.9835,
      "step": 540
    },
    {
      "epoch": 0.04569624459953473,
      "grad_norm": 0.49333709478378296,
      "learning_rate": 2e-05,
      "loss": 0.9739,
      "step": 550
    },
    {
      "epoch": 0.04652708541043536,
      "grad_norm": 0.49047335982322693,
      "learning_rate": 2e-05,
      "loss": 0.9679,
      "step": 560
    },
    {
      "epoch": 0.04735792622133599,
      "grad_norm": 0.4731309711933136,
      "learning_rate": 2e-05,
      "loss": 0.9521,
      "step": 570
    },
    {
      "epoch": 0.048188767032236623,
      "grad_norm": 0.8461064100265503,
      "learning_rate": 2e-05,
      "loss": 0.9521,
      "step": 580
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": 0.47802215814590454,
      "learning_rate": 2e-05,
      "loss": 0.9634,
      "step": 590
    },
    {
      "epoch": 0.049850448654037885,
      "grad_norm": 0.4835042655467987,
      "learning_rate": 2e-05,
      "loss": 0.9522,
      "step": 600
    },
    {
      "epoch": 0.050681289464938516,
      "grad_norm": 0.49139562249183655,
      "learning_rate": 2e-05,
      "loss": 0.9417,
      "step": 610
    },
    {
      "epoch": 0.051512130275839146,
      "grad_norm": 0.5035521984100342,
      "learning_rate": 2e-05,
      "loss": 0.9599,
      "step": 620
    },
    {
      "epoch": 0.052342971086739784,
      "grad_norm": 0.4629312753677368,
      "learning_rate": 2e-05,
      "loss": 0.925,
      "step": 630
    },
    {
      "epoch": 0.053173811897640415,
      "grad_norm": 0.4884300231933594,
      "learning_rate": 2e-05,
      "loss": 0.9467,
      "step": 640
    },
    {
      "epoch": 0.054004652708541045,
      "grad_norm": 0.47893789410591125,
      "learning_rate": 2e-05,
      "loss": 0.9436,
      "step": 650
    },
    {
      "epoch": 0.054835493519441676,
      "grad_norm": 0.49069446325302124,
      "learning_rate": 2e-05,
      "loss": 0.9789,
      "step": 660
    },
    {
      "epoch": 0.05566633433034231,
      "grad_norm": 0.5776323676109314,
      "learning_rate": 2e-05,
      "loss": 0.9727,
      "step": 670
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 0.46106594800949097,
      "learning_rate": 2e-05,
      "loss": 0.945,
      "step": 680
    },
    {
      "epoch": 0.05732801595214357,
      "grad_norm": 0.4655075967311859,
      "learning_rate": 2e-05,
      "loss": 0.9593,
      "step": 690
    },
    {
      "epoch": 0.0581588567630442,
      "grad_norm": 0.5039606094360352,
      "learning_rate": 2e-05,
      "loss": 0.9565,
      "step": 700
    },
    {
      "epoch": 0.05898969757394483,
      "grad_norm": 0.43979552388191223,
      "learning_rate": 2e-05,
      "loss": 0.9728,
      "step": 710
    },
    {
      "epoch": 0.05982053838484546,
      "grad_norm": 0.5355712175369263,
      "learning_rate": 2e-05,
      "loss": 0.9588,
      "step": 720
    },
    {
      "epoch": 0.0606513791957461,
      "grad_norm": 0.48468437790870667,
      "learning_rate": 2e-05,
      "loss": 0.9721,
      "step": 730
    },
    {
      "epoch": 0.06148222000664673,
      "grad_norm": 0.6858370304107666,
      "learning_rate": 2e-05,
      "loss": 0.9605,
      "step": 740
    },
    {
      "epoch": 0.06231306081754736,
      "grad_norm": 0.4598209261894226,
      "learning_rate": 2e-05,
      "loss": 0.9432,
      "step": 750
    },
    {
      "epoch": 0.06314390162844799,
      "grad_norm": 0.46015241742134094,
      "learning_rate": 2e-05,
      "loss": 0.9338,
      "step": 760
    },
    {
      "epoch": 0.06397474243934861,
      "grad_norm": 0.5221343040466309,
      "learning_rate": 2e-05,
      "loss": 0.9755,
      "step": 770
    },
    {
      "epoch": 0.06480558325024925,
      "grad_norm": 0.4553109109401703,
      "learning_rate": 2e-05,
      "loss": 0.9429,
      "step": 780
    },
    {
      "epoch": 0.06563642406114989,
      "grad_norm": 0.47823524475097656,
      "learning_rate": 2e-05,
      "loss": 0.9784,
      "step": 790
    },
    {
      "epoch": 0.06646726487205051,
      "grad_norm": 0.49694108963012695,
      "learning_rate": 2e-05,
      "loss": 0.9785,
      "step": 800
    },
    {
      "epoch": 0.06729810568295115,
      "grad_norm": 0.5347675085067749,
      "learning_rate": 2e-05,
      "loss": 0.9018,
      "step": 810
    },
    {
      "epoch": 0.06812894649385177,
      "grad_norm": 0.45874178409576416,
      "learning_rate": 2e-05,
      "loss": 0.9555,
      "step": 820
    },
    {
      "epoch": 0.06895978730475241,
      "grad_norm": 0.49684765934944153,
      "learning_rate": 2e-05,
      "loss": 0.964,
      "step": 830
    },
    {
      "epoch": 0.06979062811565304,
      "grad_norm": 0.4911392331123352,
      "learning_rate": 2e-05,
      "loss": 0.9173,
      "step": 840
    },
    {
      "epoch": 0.07062146892655367,
      "grad_norm": 0.4836362600326538,
      "learning_rate": 2e-05,
      "loss": 0.953,
      "step": 850
    },
    {
      "epoch": 0.0714523097374543,
      "grad_norm": 0.5126013159751892,
      "learning_rate": 2e-05,
      "loss": 0.9453,
      "step": 860
    },
    {
      "epoch": 0.07228315054835494,
      "grad_norm": 0.5170702338218689,
      "learning_rate": 2e-05,
      "loss": 0.9615,
      "step": 870
    },
    {
      "epoch": 0.07311399135925557,
      "grad_norm": 0.4929334223270416,
      "learning_rate": 2e-05,
      "loss": 0.9343,
      "step": 880
    },
    {
      "epoch": 0.0739448321701562,
      "grad_norm": 0.4450336992740631,
      "learning_rate": 2e-05,
      "loss": 0.9526,
      "step": 890
    },
    {
      "epoch": 0.07477567298105683,
      "grad_norm": 0.44215553998947144,
      "learning_rate": 2e-05,
      "loss": 0.9376,
      "step": 900
    },
    {
      "epoch": 0.07560651379195746,
      "grad_norm": 0.46003344655036926,
      "learning_rate": 2e-05,
      "loss": 0.9352,
      "step": 910
    },
    {
      "epoch": 0.0764373546028581,
      "grad_norm": 0.46930357813835144,
      "learning_rate": 2e-05,
      "loss": 0.9526,
      "step": 920
    },
    {
      "epoch": 0.07726819541375872,
      "grad_norm": 0.47233858704566956,
      "learning_rate": 2e-05,
      "loss": 0.933,
      "step": 930
    },
    {
      "epoch": 0.07809903622465936,
      "grad_norm": 0.47735634446144104,
      "learning_rate": 2e-05,
      "loss": 0.9433,
      "step": 940
    },
    {
      "epoch": 0.07892987703555998,
      "grad_norm": 0.48975709080696106,
      "learning_rate": 2e-05,
      "loss": 0.9652,
      "step": 950
    },
    {
      "epoch": 0.07976071784646062,
      "grad_norm": 0.5132952332496643,
      "learning_rate": 2e-05,
      "loss": 0.9478,
      "step": 960
    },
    {
      "epoch": 0.08059155865736126,
      "grad_norm": 0.4636126458644867,
      "learning_rate": 2e-05,
      "loss": 0.9853,
      "step": 970
    },
    {
      "epoch": 0.08142239946826188,
      "grad_norm": 0.4711599349975586,
      "learning_rate": 2e-05,
      "loss": 0.9557,
      "step": 980
    },
    {
      "epoch": 0.08225324027916252,
      "grad_norm": 0.4458945393562317,
      "learning_rate": 2e-05,
      "loss": 0.9526,
      "step": 990
    },
    {
      "epoch": 0.08308408109006314,
      "grad_norm": 0.4782368242740631,
      "learning_rate": 2e-05,
      "loss": 0.919,
      "step": 1000
    },
    {
      "epoch": 0.08391492190096378,
      "grad_norm": 0.4880605638027191,
      "learning_rate": 2e-05,
      "loss": 0.9535,
      "step": 1010
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 0.507720410823822,
      "learning_rate": 2e-05,
      "loss": 0.958,
      "step": 1020
    },
    {
      "epoch": 0.08557660352276504,
      "grad_norm": 0.4823307394981384,
      "learning_rate": 2e-05,
      "loss": 0.9177,
      "step": 1030
    },
    {
      "epoch": 0.08640744433366566,
      "grad_norm": 0.5217606425285339,
      "learning_rate": 2e-05,
      "loss": 0.9566,
      "step": 1040
    },
    {
      "epoch": 0.0872382851445663,
      "grad_norm": 0.6853054165840149,
      "learning_rate": 2e-05,
      "loss": 0.9474,
      "step": 1050
    },
    {
      "epoch": 0.08806912595546693,
      "grad_norm": 0.4901024401187897,
      "learning_rate": 2e-05,
      "loss": 0.98,
      "step": 1060
    },
    {
      "epoch": 0.08889996676636756,
      "grad_norm": 0.5073767900466919,
      "learning_rate": 2e-05,
      "loss": 0.9348,
      "step": 1070
    },
    {
      "epoch": 0.0897308075772682,
      "grad_norm": 0.49116551876068115,
      "learning_rate": 2e-05,
      "loss": 0.9511,
      "step": 1080
    },
    {
      "epoch": 0.09056164838816883,
      "grad_norm": 0.4953039884567261,
      "learning_rate": 2e-05,
      "loss": 0.9491,
      "step": 1090
    },
    {
      "epoch": 0.09139248919906946,
      "grad_norm": 0.4982893168926239,
      "learning_rate": 2e-05,
      "loss": 0.9414,
      "step": 1100
    },
    {
      "epoch": 0.09222333000997009,
      "grad_norm": 0.5743095874786377,
      "learning_rate": 2e-05,
      "loss": 0.9465,
      "step": 1110
    },
    {
      "epoch": 0.09305417082087072,
      "grad_norm": 0.4815952479839325,
      "learning_rate": 2e-05,
      "loss": 0.9588,
      "step": 1120
    },
    {
      "epoch": 0.09388501163177135,
      "grad_norm": 0.45988714694976807,
      "learning_rate": 2e-05,
      "loss": 0.9521,
      "step": 1130
    },
    {
      "epoch": 0.09471585244267199,
      "grad_norm": 0.4645231366157532,
      "learning_rate": 2e-05,
      "loss": 0.9501,
      "step": 1140
    },
    {
      "epoch": 0.09554669325357261,
      "grad_norm": 0.6942915916442871,
      "learning_rate": 2e-05,
      "loss": 0.9516,
      "step": 1150
    },
    {
      "epoch": 0.09637753406447325,
      "grad_norm": 0.49897119402885437,
      "learning_rate": 2e-05,
      "loss": 0.9197,
      "step": 1160
    },
    {
      "epoch": 0.09720837487537388,
      "grad_norm": 0.4670521914958954,
      "learning_rate": 2e-05,
      "loss": 0.948,
      "step": 1170
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 0.5074694156646729,
      "learning_rate": 2e-05,
      "loss": 0.9475,
      "step": 1180
    },
    {
      "epoch": 0.09887005649717515,
      "grad_norm": 0.5443651676177979,
      "learning_rate": 2e-05,
      "loss": 0.9605,
      "step": 1190
    },
    {
      "epoch": 0.09970089730807577,
      "grad_norm": 0.450802206993103,
      "learning_rate": 2e-05,
      "loss": 0.9235,
      "step": 1200
    },
    {
      "epoch": 0.10053173811897641,
      "grad_norm": 0.45253437757492065,
      "learning_rate": 2e-05,
      "loss": 0.9272,
      "step": 1210
    },
    {
      "epoch": 0.10136257892987703,
      "grad_norm": 0.46179214119911194,
      "learning_rate": 2e-05,
      "loss": 0.9332,
      "step": 1220
    },
    {
      "epoch": 0.10219341974077767,
      "grad_norm": 0.45921969413757324,
      "learning_rate": 2e-05,
      "loss": 0.9005,
      "step": 1230
    },
    {
      "epoch": 0.10302426055167829,
      "grad_norm": 0.4624720513820648,
      "learning_rate": 2e-05,
      "loss": 0.9354,
      "step": 1240
    },
    {
      "epoch": 0.10385510136257893,
      "grad_norm": 0.4451490044593811,
      "learning_rate": 2e-05,
      "loss": 0.9387,
      "step": 1250
    },
    {
      "epoch": 0.10468594217347957,
      "grad_norm": 0.4594932496547699,
      "learning_rate": 2e-05,
      "loss": 0.9569,
      "step": 1260
    },
    {
      "epoch": 0.10551678298438019,
      "grad_norm": 0.5099719762802124,
      "learning_rate": 2e-05,
      "loss": 0.9416,
      "step": 1270
    },
    {
      "epoch": 0.10634762379528083,
      "grad_norm": 0.4535796046257019,
      "learning_rate": 2e-05,
      "loss": 0.9333,
      "step": 1280
    },
    {
      "epoch": 0.10717846460618145,
      "grad_norm": 0.4514749348163605,
      "learning_rate": 2e-05,
      "loss": 0.8909,
      "step": 1290
    },
    {
      "epoch": 0.10800930541708209,
      "grad_norm": 0.46552297472953796,
      "learning_rate": 2e-05,
      "loss": 0.9753,
      "step": 1300
    },
    {
      "epoch": 0.10884014622798271,
      "grad_norm": 0.47683244943618774,
      "learning_rate": 2e-05,
      "loss": 0.9432,
      "step": 1310
    },
    {
      "epoch": 0.10967098703888335,
      "grad_norm": 0.4612570106983185,
      "learning_rate": 2e-05,
      "loss": 0.926,
      "step": 1320
    },
    {
      "epoch": 0.11050182784978398,
      "grad_norm": 0.5698566436767578,
      "learning_rate": 2e-05,
      "loss": 0.9264,
      "step": 1330
    },
    {
      "epoch": 0.11133266866068461,
      "grad_norm": 0.4209228754043579,
      "learning_rate": 2e-05,
      "loss": 0.924,
      "step": 1340
    },
    {
      "epoch": 0.11216350947158524,
      "grad_norm": 0.4713667929172516,
      "learning_rate": 2e-05,
      "loss": 0.9605,
      "step": 1350
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 0.4521118104457855,
      "learning_rate": 2e-05,
      "loss": 0.9226,
      "step": 1360
    },
    {
      "epoch": 0.11382519109338651,
      "grad_norm": 0.4553276300430298,
      "learning_rate": 2e-05,
      "loss": 0.9243,
      "step": 1370
    },
    {
      "epoch": 0.11465603190428714,
      "grad_norm": 0.4790123999118805,
      "learning_rate": 2e-05,
      "loss": 0.9337,
      "step": 1380
    },
    {
      "epoch": 0.11548687271518777,
      "grad_norm": 0.5393106341362,
      "learning_rate": 2e-05,
      "loss": 0.9295,
      "step": 1390
    },
    {
      "epoch": 0.1163177135260884,
      "grad_norm": 0.4630919098854065,
      "learning_rate": 2e-05,
      "loss": 0.9283,
      "step": 1400
    },
    {
      "epoch": 0.11714855433698904,
      "grad_norm": 0.4788759648799896,
      "learning_rate": 2e-05,
      "loss": 0.9245,
      "step": 1410
    },
    {
      "epoch": 0.11797939514788966,
      "grad_norm": 0.47794008255004883,
      "learning_rate": 2e-05,
      "loss": 0.9296,
      "step": 1420
    },
    {
      "epoch": 0.1188102359587903,
      "grad_norm": 0.5339735746383667,
      "learning_rate": 2e-05,
      "loss": 0.9245,
      "step": 1430
    },
    {
      "epoch": 0.11964107676969092,
      "grad_norm": 0.429898202419281,
      "learning_rate": 2e-05,
      "loss": 0.9088,
      "step": 1440
    },
    {
      "epoch": 0.12047191758059156,
      "grad_norm": 0.5483120083808899,
      "learning_rate": 2e-05,
      "loss": 0.9283,
      "step": 1450
    },
    {
      "epoch": 0.1213027583914922,
      "grad_norm": 0.4595089554786682,
      "learning_rate": 2e-05,
      "loss": 0.9595,
      "step": 1460
    },
    {
      "epoch": 0.12213359920239282,
      "grad_norm": 0.47356319427490234,
      "learning_rate": 2e-05,
      "loss": 0.9343,
      "step": 1470
    },
    {
      "epoch": 0.12296444001329346,
      "grad_norm": 0.4519900977611542,
      "learning_rate": 2e-05,
      "loss": 0.9264,
      "step": 1480
    },
    {
      "epoch": 0.12379528082419408,
      "grad_norm": 0.4612765908241272,
      "learning_rate": 2e-05,
      "loss": 0.9281,
      "step": 1490
    },
    {
      "epoch": 0.12462612163509472,
      "grad_norm": 0.5075944066047668,
      "learning_rate": 2e-05,
      "loss": 0.9271,
      "step": 1500
    },
    {
      "epoch": 0.12545696244599536,
      "grad_norm": 0.460589200258255,
      "learning_rate": 2e-05,
      "loss": 0.9271,
      "step": 1510
    },
    {
      "epoch": 0.12628780325689598,
      "grad_norm": 0.44189098477363586,
      "learning_rate": 2e-05,
      "loss": 0.9115,
      "step": 1520
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": 0.5025042295455933,
      "learning_rate": 2e-05,
      "loss": 0.9302,
      "step": 1530
    },
    {
      "epoch": 0.12794948487869723,
      "grad_norm": 0.43608036637306213,
      "learning_rate": 2e-05,
      "loss": 0.9365,
      "step": 1540
    },
    {
      "epoch": 0.12878032568959788,
      "grad_norm": 0.47563910484313965,
      "learning_rate": 2e-05,
      "loss": 0.9342,
      "step": 1550
    },
    {
      "epoch": 0.1296111665004985,
      "grad_norm": 0.5102983713150024,
      "learning_rate": 2e-05,
      "loss": 0.9025,
      "step": 1560
    },
    {
      "epoch": 0.13044200731139913,
      "grad_norm": 0.476362019777298,
      "learning_rate": 2e-05,
      "loss": 0.9053,
      "step": 1570
    },
    {
      "epoch": 0.13127284812229978,
      "grad_norm": 0.44051846861839294,
      "learning_rate": 2e-05,
      "loss": 0.9334,
      "step": 1580
    },
    {
      "epoch": 0.1321036889332004,
      "grad_norm": 0.49285897612571716,
      "learning_rate": 2e-05,
      "loss": 0.9103,
      "step": 1590
    },
    {
      "epoch": 0.13293452974410103,
      "grad_norm": 0.47332510352134705,
      "learning_rate": 2e-05,
      "loss": 0.927,
      "step": 1600
    },
    {
      "epoch": 0.13376537055500165,
      "grad_norm": 0.430770605802536,
      "learning_rate": 2e-05,
      "loss": 0.9081,
      "step": 1610
    },
    {
      "epoch": 0.1345962113659023,
      "grad_norm": 0.45503318309783936,
      "learning_rate": 2e-05,
      "loss": 0.9614,
      "step": 1620
    },
    {
      "epoch": 0.13542705217680293,
      "grad_norm": 0.4389674961566925,
      "learning_rate": 2e-05,
      "loss": 0.9343,
      "step": 1630
    },
    {
      "epoch": 0.13625789298770355,
      "grad_norm": 0.4448428750038147,
      "learning_rate": 2e-05,
      "loss": 0.9251,
      "step": 1640
    },
    {
      "epoch": 0.1370887337986042,
      "grad_norm": 0.4891062378883362,
      "learning_rate": 2e-05,
      "loss": 0.9332,
      "step": 1650
    },
    {
      "epoch": 0.13791957460950482,
      "grad_norm": 0.43644747138023376,
      "learning_rate": 2e-05,
      "loss": 0.9162,
      "step": 1660
    },
    {
      "epoch": 0.13875041542040545,
      "grad_norm": 0.5883463621139526,
      "learning_rate": 2e-05,
      "loss": 0.9069,
      "step": 1670
    },
    {
      "epoch": 0.13958125623130607,
      "grad_norm": 0.42841386795043945,
      "learning_rate": 2e-05,
      "loss": 0.8869,
      "step": 1680
    },
    {
      "epoch": 0.14041209704220672,
      "grad_norm": 0.43758800625801086,
      "learning_rate": 2e-05,
      "loss": 0.9047,
      "step": 1690
    },
    {
      "epoch": 0.14124293785310735,
      "grad_norm": 0.9693111181259155,
      "learning_rate": 2e-05,
      "loss": 0.9182,
      "step": 1700
    },
    {
      "epoch": 0.14207377866400797,
      "grad_norm": 0.46193361282348633,
      "learning_rate": 2e-05,
      "loss": 0.9201,
      "step": 1710
    },
    {
      "epoch": 0.1429046194749086,
      "grad_norm": 0.4599347412586212,
      "learning_rate": 2e-05,
      "loss": 0.8987,
      "step": 1720
    },
    {
      "epoch": 0.14373546028580925,
      "grad_norm": 0.5046244263648987,
      "learning_rate": 2e-05,
      "loss": 0.9489,
      "step": 1730
    },
    {
      "epoch": 0.14456630109670987,
      "grad_norm": 0.465670645236969,
      "learning_rate": 2e-05,
      "loss": 0.9007,
      "step": 1740
    },
    {
      "epoch": 0.1453971419076105,
      "grad_norm": 0.44361841678619385,
      "learning_rate": 2e-05,
      "loss": 0.9092,
      "step": 1750
    },
    {
      "epoch": 0.14622798271851115,
      "grad_norm": 0.46966323256492615,
      "learning_rate": 2e-05,
      "loss": 0.9422,
      "step": 1760
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 0.42061373591423035,
      "learning_rate": 2e-05,
      "loss": 0.9304,
      "step": 1770
    },
    {
      "epoch": 0.1478896643403124,
      "grad_norm": 0.46718308329582214,
      "learning_rate": 2e-05,
      "loss": 0.9496,
      "step": 1780
    },
    {
      "epoch": 0.14872050515121302,
      "grad_norm": 0.44790440797805786,
      "learning_rate": 2e-05,
      "loss": 0.8873,
      "step": 1790
    },
    {
      "epoch": 0.14955134596211367,
      "grad_norm": 0.4441417455673218,
      "learning_rate": 2e-05,
      "loss": 0.9192,
      "step": 1800
    },
    {
      "epoch": 0.1503821867730143,
      "grad_norm": 0.43312087655067444,
      "learning_rate": 2e-05,
      "loss": 0.9438,
      "step": 1810
    },
    {
      "epoch": 0.15121302758391492,
      "grad_norm": 0.46151110529899597,
      "learning_rate": 2e-05,
      "loss": 0.9246,
      "step": 1820
    },
    {
      "epoch": 0.15204386839481554,
      "grad_norm": 0.44976237416267395,
      "learning_rate": 2e-05,
      "loss": 0.9139,
      "step": 1830
    },
    {
      "epoch": 0.1528747092057162,
      "grad_norm": 0.4504854083061218,
      "learning_rate": 2e-05,
      "loss": 0.9276,
      "step": 1840
    },
    {
      "epoch": 0.15370555001661682,
      "grad_norm": 0.43953531980514526,
      "learning_rate": 2e-05,
      "loss": 0.9201,
      "step": 1850
    },
    {
      "epoch": 0.15453639082751744,
      "grad_norm": 0.4370169937610626,
      "learning_rate": 2e-05,
      "loss": 0.9017,
      "step": 1860
    },
    {
      "epoch": 0.1553672316384181,
      "grad_norm": 0.48096010088920593,
      "learning_rate": 2e-05,
      "loss": 0.9296,
      "step": 1870
    },
    {
      "epoch": 0.15619807244931871,
      "grad_norm": 0.43849658966064453,
      "learning_rate": 2e-05,
      "loss": 0.9317,
      "step": 1880
    },
    {
      "epoch": 0.15702891326021934,
      "grad_norm": 0.42286741733551025,
      "learning_rate": 2e-05,
      "loss": 0.9156,
      "step": 1890
    },
    {
      "epoch": 0.15785975407111996,
      "grad_norm": 0.47379568219184875,
      "learning_rate": 2e-05,
      "loss": 0.927,
      "step": 1900
    },
    {
      "epoch": 0.1586905948820206,
      "grad_norm": 0.49215933680534363,
      "learning_rate": 2e-05,
      "loss": 0.902,
      "step": 1910
    },
    {
      "epoch": 0.15952143569292124,
      "grad_norm": 1.1707018613815308,
      "learning_rate": 2e-05,
      "loss": 0.8982,
      "step": 1920
    },
    {
      "epoch": 0.16035227650382186,
      "grad_norm": 0.42774245142936707,
      "learning_rate": 2e-05,
      "loss": 0.9225,
      "step": 1930
    },
    {
      "epoch": 0.1611831173147225,
      "grad_norm": 0.46903279423713684,
      "learning_rate": 2e-05,
      "loss": 0.9021,
      "step": 1940
    },
    {
      "epoch": 0.16201395812562314,
      "grad_norm": 0.43232014775276184,
      "learning_rate": 2e-05,
      "loss": 0.9002,
      "step": 1950
    },
    {
      "epoch": 0.16284479893652376,
      "grad_norm": 0.4257102608680725,
      "learning_rate": 2e-05,
      "loss": 0.9045,
      "step": 1960
    },
    {
      "epoch": 0.16367563974742438,
      "grad_norm": 0.4273391664028168,
      "learning_rate": 2e-05,
      "loss": 0.9145,
      "step": 1970
    },
    {
      "epoch": 0.16450648055832504,
      "grad_norm": 0.4816047251224518,
      "learning_rate": 2e-05,
      "loss": 0.9364,
      "step": 1980
    },
    {
      "epoch": 0.16533732136922566,
      "grad_norm": 0.48251327872276306,
      "learning_rate": 2e-05,
      "loss": 0.9033,
      "step": 1990
    },
    {
      "epoch": 0.16616816218012628,
      "grad_norm": 0.4153393507003784,
      "learning_rate": 2e-05,
      "loss": 0.9192,
      "step": 2000
    },
    {
      "epoch": 0.1669990029910269,
      "grad_norm": 0.4360354542732239,
      "learning_rate": 2e-05,
      "loss": 0.9344,
      "step": 2010
    },
    {
      "epoch": 0.16782984380192756,
      "grad_norm": 0.4371736943721771,
      "learning_rate": 2e-05,
      "loss": 0.9147,
      "step": 2020
    },
    {
      "epoch": 0.16866068461282818,
      "grad_norm": 0.4477806091308594,
      "learning_rate": 2e-05,
      "loss": 0.9057,
      "step": 2030
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 0.42955541610717773,
      "learning_rate": 2e-05,
      "loss": 0.9299,
      "step": 2040
    },
    {
      "epoch": 0.17032236623462946,
      "grad_norm": 0.43824130296707153,
      "learning_rate": 2e-05,
      "loss": 0.9161,
      "step": 2050
    },
    {
      "epoch": 0.17115320704553008,
      "grad_norm": 0.4666792154312134,
      "learning_rate": 2e-05,
      "loss": 0.8963,
      "step": 2060
    },
    {
      "epoch": 0.1719840478564307,
      "grad_norm": 0.43251997232437134,
      "learning_rate": 2e-05,
      "loss": 0.9265,
      "step": 2070
    },
    {
      "epoch": 0.17281488866733133,
      "grad_norm": 0.4566524922847748,
      "learning_rate": 2e-05,
      "loss": 0.9352,
      "step": 2080
    },
    {
      "epoch": 0.17364572947823198,
      "grad_norm": 0.4343387484550476,
      "learning_rate": 2e-05,
      "loss": 0.8882,
      "step": 2090
    },
    {
      "epoch": 0.1744765702891326,
      "grad_norm": 0.42792704701423645,
      "learning_rate": 2e-05,
      "loss": 0.9164,
      "step": 2100
    },
    {
      "epoch": 0.17530741110003323,
      "grad_norm": 0.5312557816505432,
      "learning_rate": 2e-05,
      "loss": 0.9243,
      "step": 2110
    },
    {
      "epoch": 0.17613825191093385,
      "grad_norm": 0.5039758086204529,
      "learning_rate": 2e-05,
      "loss": 0.9377,
      "step": 2120
    },
    {
      "epoch": 0.1769690927218345,
      "grad_norm": 0.4619676172733307,
      "learning_rate": 2e-05,
      "loss": 0.8889,
      "step": 2130
    },
    {
      "epoch": 0.17779993353273513,
      "grad_norm": 0.43388980627059937,
      "learning_rate": 2e-05,
      "loss": 0.91,
      "step": 2140
    },
    {
      "epoch": 0.17863077434363575,
      "grad_norm": 0.4530365765094757,
      "learning_rate": 2e-05,
      "loss": 0.874,
      "step": 2150
    },
    {
      "epoch": 0.1794616151545364,
      "grad_norm": 0.4473583400249481,
      "learning_rate": 2e-05,
      "loss": 0.9083,
      "step": 2160
    },
    {
      "epoch": 0.18029245596543703,
      "grad_norm": 0.4544511139392853,
      "learning_rate": 2e-05,
      "loss": 0.8851,
      "step": 2170
    },
    {
      "epoch": 0.18112329677633765,
      "grad_norm": 0.5991601943969727,
      "learning_rate": 2e-05,
      "loss": 0.9085,
      "step": 2180
    },
    {
      "epoch": 0.18195413758723827,
      "grad_norm": 0.4439004361629486,
      "learning_rate": 2e-05,
      "loss": 0.9056,
      "step": 2190
    },
    {
      "epoch": 0.18278497839813893,
      "grad_norm": 0.4527803659439087,
      "learning_rate": 2e-05,
      "loss": 0.9233,
      "step": 2200
    },
    {
      "epoch": 0.18361581920903955,
      "grad_norm": 0.4314718544483185,
      "learning_rate": 2e-05,
      "loss": 0.8999,
      "step": 2210
    },
    {
      "epoch": 0.18444666001994017,
      "grad_norm": 0.43120718002319336,
      "learning_rate": 2e-05,
      "loss": 0.8843,
      "step": 2220
    },
    {
      "epoch": 0.18527750083084082,
      "grad_norm": 0.4640350937843323,
      "learning_rate": 2e-05,
      "loss": 0.922,
      "step": 2230
    },
    {
      "epoch": 0.18610834164174145,
      "grad_norm": 0.46143069863319397,
      "learning_rate": 2e-05,
      "loss": 0.8954,
      "step": 2240
    },
    {
      "epoch": 0.18693918245264207,
      "grad_norm": 0.44617486000061035,
      "learning_rate": 2e-05,
      "loss": 0.8752,
      "step": 2250
    },
    {
      "epoch": 0.1877700232635427,
      "grad_norm": 0.4476693868637085,
      "learning_rate": 2e-05,
      "loss": 0.9329,
      "step": 2260
    },
    {
      "epoch": 0.18860086407444335,
      "grad_norm": 0.44085007905960083,
      "learning_rate": 2e-05,
      "loss": 0.9211,
      "step": 2270
    },
    {
      "epoch": 0.18943170488534397,
      "grad_norm": 0.479470819234848,
      "learning_rate": 2e-05,
      "loss": 0.9123,
      "step": 2280
    },
    {
      "epoch": 0.1902625456962446,
      "grad_norm": 0.5018478631973267,
      "learning_rate": 2e-05,
      "loss": 0.8975,
      "step": 2290
    },
    {
      "epoch": 0.19109338650714522,
      "grad_norm": 0.39884376525878906,
      "learning_rate": 2e-05,
      "loss": 0.9007,
      "step": 2300
    },
    {
      "epoch": 0.19192422731804587,
      "grad_norm": 0.47602373361587524,
      "learning_rate": 2e-05,
      "loss": 0.8646,
      "step": 2310
    },
    {
      "epoch": 0.1927550681289465,
      "grad_norm": 0.42797547578811646,
      "learning_rate": 2e-05,
      "loss": 0.8983,
      "step": 2320
    },
    {
      "epoch": 0.19358590893984712,
      "grad_norm": 0.44223758578300476,
      "learning_rate": 2e-05,
      "loss": 0.9237,
      "step": 2330
    },
    {
      "epoch": 0.19441674975074777,
      "grad_norm": 0.44112953543663025,
      "learning_rate": 2e-05,
      "loss": 0.9164,
      "step": 2340
    },
    {
      "epoch": 0.1952475905616484,
      "grad_norm": 0.4872469902038574,
      "learning_rate": 2e-05,
      "loss": 0.8894,
      "step": 2350
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 0.4467613995075226,
      "learning_rate": 2e-05,
      "loss": 0.9153,
      "step": 2360
    },
    {
      "epoch": 0.19690927218344964,
      "grad_norm": 0.4924972951412201,
      "learning_rate": 2e-05,
      "loss": 0.8792,
      "step": 2370
    },
    {
      "epoch": 0.1977401129943503,
      "grad_norm": 0.40645840764045715,
      "learning_rate": 2e-05,
      "loss": 0.9119,
      "step": 2380
    },
    {
      "epoch": 0.19857095380525092,
      "grad_norm": 0.43075770139694214,
      "learning_rate": 2e-05,
      "loss": 0.928,
      "step": 2390
    },
    {
      "epoch": 0.19940179461615154,
      "grad_norm": 0.44500741362571716,
      "learning_rate": 2e-05,
      "loss": 0.9571,
      "step": 2400
    },
    {
      "epoch": 0.20023263542705216,
      "grad_norm": 0.41890957951545715,
      "learning_rate": 2e-05,
      "loss": 0.876,
      "step": 2410
    },
    {
      "epoch": 0.20106347623795282,
      "grad_norm": 0.5513232946395874,
      "learning_rate": 2e-05,
      "loss": 0.8904,
      "step": 2420
    },
    {
      "epoch": 0.20189431704885344,
      "grad_norm": 0.438161700963974,
      "learning_rate": 2e-05,
      "loss": 0.8692,
      "step": 2430
    },
    {
      "epoch": 0.20272515785975406,
      "grad_norm": 0.9411785006523132,
      "learning_rate": 2e-05,
      "loss": 0.8769,
      "step": 2440
    },
    {
      "epoch": 0.20355599867065471,
      "grad_norm": 0.4301227033138275,
      "learning_rate": 2e-05,
      "loss": 0.8652,
      "step": 2450
    },
    {
      "epoch": 0.20438683948155534,
      "grad_norm": 0.4590553641319275,
      "learning_rate": 2e-05,
      "loss": 0.9044,
      "step": 2460
    },
    {
      "epoch": 0.20521768029245596,
      "grad_norm": 0.4509306848049164,
      "learning_rate": 2e-05,
      "loss": 0.8709,
      "step": 2470
    },
    {
      "epoch": 0.20604852110335659,
      "grad_norm": 0.408542662858963,
      "learning_rate": 2e-05,
      "loss": 0.8983,
      "step": 2480
    },
    {
      "epoch": 0.20687936191425724,
      "grad_norm": 0.4729969799518585,
      "learning_rate": 2e-05,
      "loss": 0.8736,
      "step": 2490
    },
    {
      "epoch": 0.20771020272515786,
      "grad_norm": 0.464586466550827,
      "learning_rate": 2e-05,
      "loss": 0.8955,
      "step": 2500
    },
    {
      "epoch": 0.20854104353605848,
      "grad_norm": 0.8892510533332825,
      "learning_rate": 2e-05,
      "loss": 0.8964,
      "step": 2510
    },
    {
      "epoch": 0.20937188434695914,
      "grad_norm": 0.4715708792209625,
      "learning_rate": 2e-05,
      "loss": 0.8743,
      "step": 2520
    },
    {
      "epoch": 0.21020272515785976,
      "grad_norm": 0.5275328159332275,
      "learning_rate": 2e-05,
      "loss": 0.8951,
      "step": 2530
    },
    {
      "epoch": 0.21103356596876038,
      "grad_norm": 0.45450401306152344,
      "learning_rate": 2e-05,
      "loss": 0.8803,
      "step": 2540
    },
    {
      "epoch": 0.211864406779661,
      "grad_norm": 0.4275004267692566,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.9165,
      "step": 2550
    },
    {
      "epoch": 0.21269524759056166,
      "grad_norm": 0.4516240656375885,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.8796,
      "step": 2560
    },
    {
      "epoch": 0.21352608840146228,
      "grad_norm": 0.4357883334159851,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.886,
      "step": 2570
    },
    {
      "epoch": 0.2143569292123629,
      "grad_norm": 0.45036065578460693,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.9277,
      "step": 2580
    },
    {
      "epoch": 0.21518777002326353,
      "grad_norm": 0.47130683064460754,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.926,
      "step": 2590
    },
    {
      "epoch": 0.21601861083416418,
      "grad_norm": 0.46603623032569885,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.917,
      "step": 2600
    },
    {
      "epoch": 0.2168494516450648,
      "grad_norm": 0.47673144936561584,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.8588,
      "step": 2610
    },
    {
      "epoch": 0.21768029245596543,
      "grad_norm": 0.4359516203403473,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.9001,
      "step": 2620
    },
    {
      "epoch": 0.21851113326686608,
      "grad_norm": 0.42964109778404236,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.9048,
      "step": 2630
    },
    {
      "epoch": 0.2193419740777667,
      "grad_norm": 0.5150458216667175,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.9035,
      "step": 2640
    },
    {
      "epoch": 0.22017281488866733,
      "grad_norm": 0.43643373250961304,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.87,
      "step": 2650
    },
    {
      "epoch": 0.22100365569956795,
      "grad_norm": 0.4392036199569702,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.9119,
      "step": 2660
    },
    {
      "epoch": 0.2218344965104686,
      "grad_norm": 0.41249197721481323,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.8732,
      "step": 2670
    },
    {
      "epoch": 0.22266533732136923,
      "grad_norm": 0.407343327999115,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.9064,
      "step": 2680
    },
    {
      "epoch": 0.22349617813226985,
      "grad_norm": 0.47207093238830566,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.8755,
      "step": 2690
    },
    {
      "epoch": 0.22432701894317048,
      "grad_norm": 0.44220852851867676,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.8893,
      "step": 2700
    },
    {
      "epoch": 0.22515785975407113,
      "grad_norm": 0.435964435338974,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.9234,
      "step": 2710
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.4354947805404663,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.9321,
      "step": 2720
    },
    {
      "epoch": 0.22681954137587237,
      "grad_norm": 0.5719556212425232,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.9011,
      "step": 2730
    },
    {
      "epoch": 0.22765038218677303,
      "grad_norm": 0.4237906336784363,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.8559,
      "step": 2740
    },
    {
      "epoch": 0.22848122299767365,
      "grad_norm": 0.4187341034412384,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.8501,
      "step": 2750
    },
    {
      "epoch": 0.22931206380857427,
      "grad_norm": 0.41744765639305115,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.8463,
      "step": 2760
    },
    {
      "epoch": 0.2301429046194749,
      "grad_norm": 0.41904744505882263,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.8837,
      "step": 2770
    },
    {
      "epoch": 0.23097374543037555,
      "grad_norm": 0.4295591711997986,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.8654,
      "step": 2780
    },
    {
      "epoch": 0.23180458624127617,
      "grad_norm": 0.44897112250328064,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.9061,
      "step": 2790
    },
    {
      "epoch": 0.23246925888999667,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.08099565171956846,
      "train_runtime": 2282.2945,
      "train_samples_per_second": 14.712,
      "train_steps_per_second": 1.226
    }
  ],
  "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
}