{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23420105465807314,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008370302167908262,
      "grad_norm": 5.156661510467529,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 1.5667,
      "step": 10
    },
    {
      "epoch": 0.0016740604335816524,
      "grad_norm": 2.557840347290039,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 1.3469,
      "step": 20
    },
    {
      "epoch": 0.0025110906503724786,
      "grad_norm": 1.6066818237304688,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.2057,
      "step": 30
    },
    {
      "epoch": 0.0033481208671633047,
      "grad_norm": 1.1234897375106812,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.0592,
      "step": 40
    },
    {
      "epoch": 0.004185151083954131,
      "grad_norm": 1.0128376483917236,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.9068,
      "step": 50
    },
    {
      "epoch": 0.005022181300744957,
      "grad_norm": 0.7160766124725342,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.8015,
      "step": 60
    },
    {
      "epoch": 0.005859211517535783,
      "grad_norm": 0.47716090083122253,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.8152,
      "step": 70
    },
    {
      "epoch": 0.006696241734326609,
      "grad_norm": 0.5273013114929199,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.7991,
      "step": 80
    },
    {
      "epoch": 0.007533271951117435,
      "grad_norm": 0.4626390039920807,
      "learning_rate": 1.005e-05,
      "loss": 0.7387,
      "step": 90
    },
    {
      "epoch": 0.008370302167908262,
      "grad_norm": 0.5121504664421082,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.7605,
      "step": 100
    },
    {
      "epoch": 0.009207332384699087,
      "grad_norm": 0.4082605540752411,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.7623,
      "step": 110
    },
    {
      "epoch": 0.010044362601489915,
      "grad_norm": 0.5059930682182312,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.764,
      "step": 120
    },
    {
      "epoch": 0.01088139281828074,
      "grad_norm": 0.751139223575592,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.7645,
      "step": 130
    },
    {
      "epoch": 0.011718423035071566,
      "grad_norm": 0.492674320936203,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.781,
      "step": 140
    },
    {
      "epoch": 0.012555453251862391,
      "grad_norm": 0.566781222820282,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.7548,
      "step": 150
    },
    {
      "epoch": 0.013392483468653219,
      "grad_norm": 0.5136772990226746,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.7799,
      "step": 160
    },
    {
      "epoch": 0.014229513685444044,
      "grad_norm": 0.40454524755477905,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.7748,
      "step": 170
    },
    {
      "epoch": 0.01506654390223487,
      "grad_norm": 0.4504382014274597,
      "learning_rate": 2e-05,
      "loss": 0.7757,
      "step": 180
    },
    {
      "epoch": 0.015903574119025696,
      "grad_norm": 0.5842396020889282,
      "learning_rate": 2e-05,
      "loss": 0.7491,
      "step": 190
    },
    {
      "epoch": 0.016740604335816523,
      "grad_norm": 0.42499402165412903,
      "learning_rate": 2e-05,
      "loss": 0.7533,
      "step": 200
    },
    {
      "epoch": 0.01757763455260735,
      "grad_norm": 0.4922196567058563,
      "learning_rate": 2e-05,
      "loss": 0.7639,
      "step": 210
    },
    {
      "epoch": 0.018414664769398174,
      "grad_norm": 0.4512643814086914,
      "learning_rate": 2e-05,
      "loss": 0.7663,
      "step": 220
    },
    {
      "epoch": 0.019251694986189002,
      "grad_norm": 0.4370189607143402,
      "learning_rate": 2e-05,
      "loss": 0.765,
      "step": 230
    },
    {
      "epoch": 0.02008872520297983,
      "grad_norm": 0.41970548033714294,
      "learning_rate": 2e-05,
      "loss": 0.745,
      "step": 240
    },
    {
      "epoch": 0.020925755419770653,
      "grad_norm": 0.45108288526535034,
      "learning_rate": 2e-05,
      "loss": 0.7364,
      "step": 250
    },
    {
      "epoch": 0.02176278563656148,
      "grad_norm": 0.42641422152519226,
      "learning_rate": 2e-05,
      "loss": 0.732,
      "step": 260
    },
    {
      "epoch": 0.022599815853352308,
      "grad_norm": 0.3930014371871948,
      "learning_rate": 2e-05,
      "loss": 0.7634,
      "step": 270
    },
    {
      "epoch": 0.02343684607014313,
      "grad_norm": 0.43919554352760315,
      "learning_rate": 2e-05,
      "loss": 0.7621,
      "step": 280
    },
    {
      "epoch": 0.02427387628693396,
      "grad_norm": 0.4371900260448456,
      "learning_rate": 2e-05,
      "loss": 0.7379,
      "step": 290
    },
    {
      "epoch": 0.025110906503724783,
      "grad_norm": 0.4431065618991852,
      "learning_rate": 2e-05,
      "loss": 0.7306,
      "step": 300
    },
    {
      "epoch": 0.02594793672051561,
      "grad_norm": 0.4054403603076935,
      "learning_rate": 2e-05,
      "loss": 0.7532,
      "step": 310
    },
    {
      "epoch": 0.026784966937306438,
      "grad_norm": 0.43971535563468933,
      "learning_rate": 2e-05,
      "loss": 0.7527,
      "step": 320
    },
    {
      "epoch": 0.02762199715409726,
      "grad_norm": 1.0866317749023438,
      "learning_rate": 2e-05,
      "loss": 0.7705,
      "step": 330
    },
    {
      "epoch": 0.02845902737088809,
      "grad_norm": 0.4061005115509033,
      "learning_rate": 2e-05,
      "loss": 0.7739,
      "step": 340
    },
    {
      "epoch": 0.029296057587678916,
      "grad_norm": 0.5896549820899963,
      "learning_rate": 2e-05,
      "loss": 0.7655,
      "step": 350
    },
    {
      "epoch": 0.03013308780446974,
      "grad_norm": 0.44174519181251526,
      "learning_rate": 2e-05,
      "loss": 0.7502,
      "step": 360
    },
    {
      "epoch": 0.030970118021260568,
      "grad_norm": 0.4336935877799988,
      "learning_rate": 2e-05,
      "loss": 0.7119,
      "step": 370
    },
    {
      "epoch": 0.03180714823805139,
      "grad_norm": 0.43263721466064453,
      "learning_rate": 2e-05,
      "loss": 0.7308,
      "step": 380
    },
    {
      "epoch": 0.03264417845484222,
      "grad_norm": 0.4120350480079651,
      "learning_rate": 2e-05,
      "loss": 0.7464,
      "step": 390
    },
    {
      "epoch": 0.033481208671633046,
      "grad_norm": 0.4036485254764557,
      "learning_rate": 2e-05,
      "loss": 0.7601,
      "step": 400
    },
    {
      "epoch": 0.03431823888842387,
      "grad_norm": 0.41021424531936646,
      "learning_rate": 2e-05,
      "loss": 0.7281,
      "step": 410
    },
    {
      "epoch": 0.0351552691052147,
      "grad_norm": 0.4482649564743042,
      "learning_rate": 2e-05,
      "loss": 0.7316,
      "step": 420
    },
    {
      "epoch": 0.035992299322005525,
      "grad_norm": 0.4150967299938202,
      "learning_rate": 2e-05,
      "loss": 0.7365,
      "step": 430
    },
    {
      "epoch": 0.03682932953879635,
      "grad_norm": 0.3876197934150696,
      "learning_rate": 2e-05,
      "loss": 0.7511,
      "step": 440
    },
    {
      "epoch": 0.03766635975558718,
      "grad_norm": 0.40040096640586853,
      "learning_rate": 2e-05,
      "loss": 0.793,
      "step": 450
    },
    {
      "epoch": 0.038503389972378003,
      "grad_norm": 0.4496796727180481,
      "learning_rate": 2e-05,
      "loss": 0.7423,
      "step": 460
    },
    {
      "epoch": 0.03934042018916883,
      "grad_norm": 0.4478641152381897,
      "learning_rate": 2e-05,
      "loss": 0.7485,
      "step": 470
    },
    {
      "epoch": 0.04017745040595966,
      "grad_norm": 0.4376203715801239,
      "learning_rate": 2e-05,
      "loss": 0.7909,
      "step": 480
    },
    {
      "epoch": 0.04101448062275048,
      "grad_norm": 0.42852625250816345,
      "learning_rate": 2e-05,
      "loss": 0.7159,
      "step": 490
    },
    {
      "epoch": 0.041851510839541306,
      "grad_norm": 0.42360687255859375,
      "learning_rate": 2e-05,
      "loss": 0.7401,
      "step": 500
    },
    {
      "epoch": 0.04268854105633214,
      "grad_norm": 0.38901394605636597,
      "learning_rate": 2e-05,
      "loss": 0.7284,
      "step": 510
    },
    {
      "epoch": 0.04352557127312296,
      "grad_norm": 0.4375343322753906,
      "learning_rate": 2e-05,
      "loss": 0.738,
      "step": 520
    },
    {
      "epoch": 0.044362601489913785,
      "grad_norm": 0.44532549381256104,
      "learning_rate": 2e-05,
      "loss": 0.7469,
      "step": 530
    },
    {
      "epoch": 0.045199631706704615,
      "grad_norm": 0.46848392486572266,
      "learning_rate": 2e-05,
      "loss": 0.7366,
      "step": 540
    },
    {
      "epoch": 0.04603666192349544,
      "grad_norm": 0.3851851224899292,
      "learning_rate": 2e-05,
      "loss": 0.7335,
      "step": 550
    },
    {
      "epoch": 0.04687369214028626,
      "grad_norm": 0.40839746594429016,
      "learning_rate": 2e-05,
      "loss": 0.7053,
      "step": 560
    },
    {
      "epoch": 0.04771072235707709,
      "grad_norm": 0.4012123644351959,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 570
    },
    {
      "epoch": 0.04854775257386792,
      "grad_norm": 0.3855404555797577,
      "learning_rate": 2e-05,
      "loss": 0.7133,
      "step": 580
    },
    {
      "epoch": 0.04938478279065874,
      "grad_norm": 0.3988204002380371,
      "learning_rate": 2e-05,
      "loss": 0.7541,
      "step": 590
    },
    {
      "epoch": 0.050221813007449566,
      "grad_norm": 0.4450335204601288,
      "learning_rate": 2e-05,
      "loss": 0.7238,
      "step": 600
    },
    {
      "epoch": 0.0510588432242404,
      "grad_norm": 0.4375969469547272,
      "learning_rate": 2e-05,
      "loss": 0.7044,
      "step": 610
    },
    {
      "epoch": 0.05189587344103122,
      "grad_norm": 0.4379328787326813,
      "learning_rate": 2e-05,
      "loss": 0.726,
      "step": 620
    },
    {
      "epoch": 0.052732903657822044,
      "grad_norm": 0.39580798149108887,
      "learning_rate": 2e-05,
      "loss": 0.7463,
      "step": 630
    },
    {
      "epoch": 0.053569933874612875,
      "grad_norm": 0.41373711824417114,
      "learning_rate": 2e-05,
      "loss": 0.7499,
      "step": 640
    },
    {
      "epoch": 0.0544069640914037,
      "grad_norm": 0.4301176369190216,
      "learning_rate": 2e-05,
      "loss": 0.7341,
      "step": 650
    },
    {
      "epoch": 0.05524399430819452,
      "grad_norm": 0.45098692178726196,
      "learning_rate": 2e-05,
      "loss": 0.7318,
      "step": 660
    },
    {
      "epoch": 0.056081024524985354,
      "grad_norm": 0.4196617305278778,
      "learning_rate": 2e-05,
      "loss": 0.734,
      "step": 670
    },
    {
      "epoch": 0.05691805474177618,
      "grad_norm": 0.4272335171699524,
      "learning_rate": 2e-05,
      "loss": 0.7083,
      "step": 680
    },
    {
      "epoch": 0.057755084958567,
      "grad_norm": 0.4190222918987274,
      "learning_rate": 2e-05,
      "loss": 0.7272,
      "step": 690
    },
    {
      "epoch": 0.05859211517535783,
      "grad_norm": 0.42260268330574036,
      "learning_rate": 2e-05,
      "loss": 0.7266,
      "step": 700
    },
    {
      "epoch": 0.059429145392148656,
      "grad_norm": 0.3979990780353546,
      "learning_rate": 2e-05,
      "loss": 0.7265,
      "step": 710
    },
    {
      "epoch": 0.06026617560893948,
      "grad_norm": 0.41610896587371826,
      "learning_rate": 2e-05,
      "loss": 0.7308,
      "step": 720
    },
    {
      "epoch": 0.06110320582573031,
      "grad_norm": 0.44141194224357605,
      "learning_rate": 2e-05,
      "loss": 0.752,
      "step": 730
    },
    {
      "epoch": 0.061940236042521135,
      "grad_norm": 0.40890923142433167,
      "learning_rate": 2e-05,
      "loss": 0.7552,
      "step": 740
    },
    {
      "epoch": 0.06277726625931196,
      "grad_norm": 0.37664929032325745,
      "learning_rate": 2e-05,
      "loss": 0.7363,
      "step": 750
    },
    {
      "epoch": 0.06361429647610278,
      "grad_norm": 0.3718191683292389,
      "learning_rate": 2e-05,
      "loss": 0.7458,
      "step": 760
    },
    {
      "epoch": 0.0644513266928936,
      "grad_norm": 0.4162319004535675,
      "learning_rate": 2e-05,
      "loss": 0.7587,
      "step": 770
    },
    {
      "epoch": 0.06528835690968444,
      "grad_norm": 0.5250889658927917,
      "learning_rate": 2e-05,
      "loss": 0.733,
      "step": 780
    },
    {
      "epoch": 0.06612538712647527,
      "grad_norm": 0.3899112343788147,
      "learning_rate": 2e-05,
      "loss": 0.731,
      "step": 790
    },
    {
      "epoch": 0.06696241734326609,
      "grad_norm": 0.39714515209198,
      "learning_rate": 2e-05,
      "loss": 0.7397,
      "step": 800
    },
    {
      "epoch": 0.06779944756005692,
      "grad_norm": 0.4384140372276306,
      "learning_rate": 2e-05,
      "loss": 0.7334,
      "step": 810
    },
    {
      "epoch": 0.06863647777684774,
      "grad_norm": 0.37715354561805725,
      "learning_rate": 2e-05,
      "loss": 0.7442,
      "step": 820
    },
    {
      "epoch": 0.06947350799363856,
      "grad_norm": 0.4676320552825928,
      "learning_rate": 2e-05,
      "loss": 0.729,
      "step": 830
    },
    {
      "epoch": 0.0703105382104294,
      "grad_norm": 0.4101060926914215,
      "learning_rate": 2e-05,
      "loss": 0.7412,
      "step": 840
    },
    {
      "epoch": 0.07114756842722023,
      "grad_norm": 0.40823832154273987,
      "learning_rate": 2e-05,
      "loss": 0.7404,
      "step": 850
    },
    {
      "epoch": 0.07198459864401105,
      "grad_norm": 0.35889768600463867,
      "learning_rate": 2e-05,
      "loss": 0.7301,
      "step": 860
    },
    {
      "epoch": 0.07282162886080187,
      "grad_norm": 0.35591280460357666,
      "learning_rate": 2e-05,
      "loss": 0.7434,
      "step": 870
    },
    {
      "epoch": 0.0736586590775927,
      "grad_norm": 0.3851705491542816,
      "learning_rate": 2e-05,
      "loss": 0.7002,
      "step": 880
    },
    {
      "epoch": 0.07449568929438352,
      "grad_norm": 0.3983948230743408,
      "learning_rate": 2e-05,
      "loss": 0.7274,
      "step": 890
    },
    {
      "epoch": 0.07533271951117436,
      "grad_norm": 0.3635563254356384,
      "learning_rate": 2e-05,
      "loss": 0.6975,
      "step": 900
    },
    {
      "epoch": 0.07616974972796518,
      "grad_norm": 0.3900563418865204,
      "learning_rate": 2e-05,
      "loss": 0.7467,
      "step": 910
    },
    {
      "epoch": 0.07700677994475601,
      "grad_norm": 0.4121996760368347,
      "learning_rate": 2e-05,
      "loss": 0.7181,
      "step": 920
    },
    {
      "epoch": 0.07784381016154683,
      "grad_norm": 0.35744690895080566,
      "learning_rate": 2e-05,
      "loss": 0.72,
      "step": 930
    },
    {
      "epoch": 0.07868084037833765,
      "grad_norm": 0.44155263900756836,
      "learning_rate": 2e-05,
      "loss": 0.714,
      "step": 940
    },
    {
      "epoch": 0.07951787059512848,
      "grad_norm": 0.415809690952301,
      "learning_rate": 2e-05,
      "loss": 0.7518,
      "step": 950
    },
    {
      "epoch": 0.08035490081191932,
      "grad_norm": 0.3967406153678894,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 960
    },
    {
      "epoch": 0.08119193102871014,
      "grad_norm": 0.4007624089717865,
      "learning_rate": 2e-05,
      "loss": 0.747,
      "step": 970
    },
    {
      "epoch": 0.08202896124550096,
      "grad_norm": 0.38344693183898926,
      "learning_rate": 2e-05,
      "loss": 0.7295,
      "step": 980
    },
    {
      "epoch": 0.08286599146229179,
      "grad_norm": 0.45661893486976624,
      "learning_rate": 2e-05,
      "loss": 0.7111,
      "step": 990
    },
    {
      "epoch": 0.08370302167908261,
      "grad_norm": 0.4255678951740265,
      "learning_rate": 2e-05,
      "loss": 0.775,
      "step": 1000
    },
    {
      "epoch": 0.08454005189587344,
      "grad_norm": 0.49089524149894714,
      "learning_rate": 2e-05,
      "loss": 0.7387,
      "step": 1010
    },
    {
      "epoch": 0.08537708211266427,
      "grad_norm": 0.3930380642414093,
      "learning_rate": 2e-05,
      "loss": 0.7601,
      "step": 1020
    },
    {
      "epoch": 0.0862141123294551,
      "grad_norm": 0.4231725037097931,
      "learning_rate": 2e-05,
      "loss": 0.6822,
      "step": 1030
    },
    {
      "epoch": 0.08705114254624592,
      "grad_norm": 0.39020201563835144,
      "learning_rate": 2e-05,
      "loss": 0.7325,
      "step": 1040
    },
    {
      "epoch": 0.08788817276303675,
      "grad_norm": 0.429443359375,
      "learning_rate": 2e-05,
      "loss": 0.7194,
      "step": 1050
    },
    {
      "epoch": 0.08872520297982757,
      "grad_norm": 0.38595613837242126,
      "learning_rate": 2e-05,
      "loss": 0.7336,
      "step": 1060
    },
    {
      "epoch": 0.0895622331966184,
      "grad_norm": 0.371380090713501,
      "learning_rate": 2e-05,
      "loss": 0.7325,
      "step": 1070
    },
    {
      "epoch": 0.09039926341340923,
      "grad_norm": 0.396846204996109,
      "learning_rate": 2e-05,
      "loss": 0.7281,
      "step": 1080
    },
    {
      "epoch": 0.09123629363020005,
      "grad_norm": 0.42279285192489624,
      "learning_rate": 2e-05,
      "loss": 0.7383,
      "step": 1090
    },
    {
      "epoch": 0.09207332384699088,
      "grad_norm": 0.41259169578552246,
      "learning_rate": 2e-05,
      "loss": 0.7398,
      "step": 1100
    },
    {
      "epoch": 0.0929103540637817,
      "grad_norm": 0.43002089858055115,
      "learning_rate": 2e-05,
      "loss": 0.7323,
      "step": 1110
    },
    {
      "epoch": 0.09374738428057253,
      "grad_norm": 0.4018864929676056,
      "learning_rate": 2e-05,
      "loss": 0.7542,
      "step": 1120
    },
    {
      "epoch": 0.09458441449736335,
      "grad_norm": 0.3879416882991791,
      "learning_rate": 2e-05,
      "loss": 0.724,
      "step": 1130
    },
    {
      "epoch": 0.09542144471415417,
      "grad_norm": 0.40612295269966125,
      "learning_rate": 2e-05,
      "loss": 0.7181,
      "step": 1140
    },
    {
      "epoch": 0.09625847493094501,
      "grad_norm": 0.3889906406402588,
      "learning_rate": 2e-05,
      "loss": 0.7206,
      "step": 1150
    },
    {
      "epoch": 0.09709550514773584,
      "grad_norm": 0.3631397783756256,
      "learning_rate": 2e-05,
      "loss": 0.7608,
      "step": 1160
    },
    {
      "epoch": 0.09793253536452666,
      "grad_norm": 0.3583589494228363,
      "learning_rate": 2e-05,
      "loss": 0.7257,
      "step": 1170
    },
    {
      "epoch": 0.09876956558131748,
      "grad_norm": 0.38138115406036377,
      "learning_rate": 2e-05,
      "loss": 0.7296,
      "step": 1180
    },
    {
      "epoch": 0.09960659579810831,
      "grad_norm": 0.381708025932312,
      "learning_rate": 2e-05,
      "loss": 0.7275,
      "step": 1190
    },
    {
      "epoch": 0.10044362601489913,
      "grad_norm": 0.3952488601207733,
      "learning_rate": 2e-05,
      "loss": 0.7211,
      "step": 1200
    },
    {
      "epoch": 0.10128065623168997,
      "grad_norm": 0.369489848613739,
      "learning_rate": 2e-05,
      "loss": 0.6827,
      "step": 1210
    },
    {
      "epoch": 0.1021176864484808,
      "grad_norm": 0.3854788541793823,
      "learning_rate": 2e-05,
      "loss": 0.7141,
      "step": 1220
    },
    {
      "epoch": 0.10295471666527162,
      "grad_norm": 0.44547921419143677,
      "learning_rate": 2e-05,
      "loss": 0.7465,
      "step": 1230
    },
    {
      "epoch": 0.10379174688206244,
      "grad_norm": 0.3807377219200134,
      "learning_rate": 2e-05,
      "loss": 0.6965,
      "step": 1240
    },
    {
      "epoch": 0.10462877709885327,
      "grad_norm": 1.0734481811523438,
      "learning_rate": 2e-05,
      "loss": 0.7228,
      "step": 1250
    },
    {
      "epoch": 0.10546580731564409,
      "grad_norm": 0.3832617700099945,
      "learning_rate": 2e-05,
      "loss": 0.76,
      "step": 1260
    },
    {
      "epoch": 0.10630283753243493,
      "grad_norm": 0.4228065013885498,
      "learning_rate": 2e-05,
      "loss": 0.7379,
      "step": 1270
    },
    {
      "epoch": 0.10713986774922575,
      "grad_norm": 0.39900723099708557,
      "learning_rate": 2e-05,
      "loss": 0.6866,
      "step": 1280
    },
    {
      "epoch": 0.10797689796601657,
      "grad_norm": 0.5197460055351257,
      "learning_rate": 2e-05,
      "loss": 0.6915,
      "step": 1290
    },
    {
      "epoch": 0.1088139281828074,
      "grad_norm": 0.6023410558700562,
      "learning_rate": 2e-05,
      "loss": 0.7019,
      "step": 1300
    },
    {
      "epoch": 0.10965095839959822,
      "grad_norm": 0.4066433310508728,
      "learning_rate": 2e-05,
      "loss": 0.7001,
      "step": 1310
    },
    {
      "epoch": 0.11048798861638905,
      "grad_norm": 0.382357656955719,
      "learning_rate": 2e-05,
      "loss": 0.7287,
      "step": 1320
    },
    {
      "epoch": 0.11132501883317988,
      "grad_norm": 0.3749663829803467,
      "learning_rate": 2e-05,
      "loss": 0.7429,
      "step": 1330
    },
    {
      "epoch": 0.11216204904997071,
      "grad_norm": 0.3689495325088501,
      "learning_rate": 2e-05,
      "loss": 0.6842,
      "step": 1340
    },
    {
      "epoch": 0.11299907926676153,
      "grad_norm": 0.41168835759162903,
      "learning_rate": 2e-05,
      "loss": 0.7533,
      "step": 1350
    },
    {
      "epoch": 0.11383610948355236,
      "grad_norm": 0.39960694313049316,
      "learning_rate": 2e-05,
      "loss": 0.7312,
      "step": 1360
    },
    {
      "epoch": 0.11467313970034318,
      "grad_norm": 0.3908539414405823,
      "learning_rate": 2e-05,
      "loss": 0.7085,
      "step": 1370
    },
    {
      "epoch": 0.115510169917134,
      "grad_norm": 0.38182100653648376,
      "learning_rate": 2e-05,
      "loss": 0.7271,
      "step": 1380
    },
    {
      "epoch": 0.11634720013392484,
      "grad_norm": 0.405620276927948,
      "learning_rate": 2e-05,
      "loss": 0.7235,
      "step": 1390
    },
    {
      "epoch": 0.11718423035071567,
      "grad_norm": 0.3966982364654541,
      "learning_rate": 2e-05,
      "loss": 0.7371,
      "step": 1400
    },
    {
      "epoch": 0.11802126056750649,
      "grad_norm": 0.3768328130245209,
      "learning_rate": 2e-05,
      "loss": 0.7172,
      "step": 1410
    },
    {
      "epoch": 0.11885829078429731,
      "grad_norm": 0.4282349944114685,
      "learning_rate": 2e-05,
      "loss": 0.7318,
      "step": 1420
    },
    {
      "epoch": 0.11969532100108814,
      "grad_norm": 0.39045482873916626,
      "learning_rate": 2e-05,
      "loss": 0.704,
      "step": 1430
    },
    {
      "epoch": 0.12053235121787896,
      "grad_norm": 0.3846886456012726,
      "learning_rate": 2e-05,
      "loss": 0.7069,
      "step": 1440
    },
    {
      "epoch": 0.12136938143466978,
      "grad_norm": 0.3845898509025574,
      "learning_rate": 2e-05,
      "loss": 0.703,
      "step": 1450
    },
    {
      "epoch": 0.12220641165146062,
      "grad_norm": 0.4043080508708954,
      "learning_rate": 2e-05,
      "loss": 0.7329,
      "step": 1460
    },
    {
      "epoch": 0.12304344186825145,
      "grad_norm": 0.353148877620697,
      "learning_rate": 2e-05,
      "loss": 0.7039,
      "step": 1470
    },
    {
      "epoch": 0.12388047208504227,
      "grad_norm": 0.3626961410045624,
      "learning_rate": 2e-05,
      "loss": 0.7125,
      "step": 1480
    },
    {
      "epoch": 0.1247175023018331,
      "grad_norm": 0.40537577867507935,
      "learning_rate": 2e-05,
      "loss": 0.6874,
      "step": 1490
    },
    {
      "epoch": 0.12555453251862392,
      "grad_norm": 0.38374269008636475,
      "learning_rate": 2e-05,
      "loss": 0.7166,
      "step": 1500
    },
    {
      "epoch": 0.12639156273541474,
      "grad_norm": 0.3687508702278137,
      "learning_rate": 2e-05,
      "loss": 0.7042,
      "step": 1510
    },
    {
      "epoch": 0.12722859295220557,
      "grad_norm": 0.38297727704048157,
      "learning_rate": 2e-05,
      "loss": 0.7276,
      "step": 1520
    },
    {
      "epoch": 0.1280656231689964,
      "grad_norm": 0.40739986300468445,
      "learning_rate": 2e-05,
      "loss": 0.7352,
      "step": 1530
    },
    {
      "epoch": 0.1289026533857872,
      "grad_norm": 0.5073732733726501,
      "learning_rate": 2e-05,
      "loss": 0.7407,
      "step": 1540
    },
    {
      "epoch": 0.12973968360257807,
      "grad_norm": 0.3655388653278351,
      "learning_rate": 2e-05,
      "loss": 0.707,
      "step": 1550
    },
    {
      "epoch": 0.1305767138193689,
      "grad_norm": 0.38478103280067444,
      "learning_rate": 2e-05,
      "loss": 0.7155,
      "step": 1560
    },
    {
      "epoch": 0.1314137440361597,
      "grad_norm": 0.3790566027164459,
      "learning_rate": 2e-05,
      "loss": 0.7048,
      "step": 1570
    },
    {
      "epoch": 0.13225077425295054,
      "grad_norm": 0.3985552489757538,
      "learning_rate": 2e-05,
      "loss": 0.7469,
      "step": 1580
    },
    {
      "epoch": 0.13308780446974136,
      "grad_norm": 0.3573896586894989,
      "learning_rate": 2e-05,
      "loss": 0.7128,
      "step": 1590
    },
    {
      "epoch": 0.13392483468653218,
      "grad_norm": 0.3679613471031189,
      "learning_rate": 2e-05,
      "loss": 0.7063,
      "step": 1600
    },
    {
      "epoch": 0.134761864903323,
      "grad_norm": 0.4195422828197479,
      "learning_rate": 2e-05,
      "loss": 0.7214,
      "step": 1610
    },
    {
      "epoch": 0.13559889512011383,
      "grad_norm": 0.4262971878051758,
      "learning_rate": 2e-05,
      "loss": 0.7214,
      "step": 1620
    },
    {
      "epoch": 0.13643592533690466,
      "grad_norm": 0.3953056335449219,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 1630
    },
    {
      "epoch": 0.13727295555369548,
      "grad_norm": 0.3896598517894745,
      "learning_rate": 2e-05,
      "loss": 0.68,
      "step": 1640
    },
    {
      "epoch": 0.1381099857704863,
      "grad_norm": 0.39134523272514343,
      "learning_rate": 2e-05,
      "loss": 0.7233,
      "step": 1650
    },
    {
      "epoch": 0.13894701598727713,
      "grad_norm": 0.38543522357940674,
      "learning_rate": 2e-05,
      "loss": 0.7078,
      "step": 1660
    },
    {
      "epoch": 0.13978404620406798,
      "grad_norm": 0.37859565019607544,
      "learning_rate": 2e-05,
      "loss": 0.7141,
      "step": 1670
    },
    {
      "epoch": 0.1406210764208588,
      "grad_norm": 0.3654524087905884,
      "learning_rate": 2e-05,
      "loss": 0.6817,
      "step": 1680
    },
    {
      "epoch": 0.14145810663764963,
      "grad_norm": 0.3827599585056305,
      "learning_rate": 2e-05,
      "loss": 0.6995,
      "step": 1690
    },
    {
      "epoch": 0.14229513685444045,
      "grad_norm": 0.3548571467399597,
      "learning_rate": 2e-05,
      "loss": 0.7106,
      "step": 1700
    },
    {
      "epoch": 0.14313216707123128,
      "grad_norm": 0.4650750756263733,
      "learning_rate": 2e-05,
      "loss": 0.7498,
      "step": 1710
    },
    {
      "epoch": 0.1439691972880221,
      "grad_norm": 0.38478001952171326,
      "learning_rate": 2e-05,
      "loss": 0.7699,
      "step": 1720
    },
    {
      "epoch": 0.14480622750481292,
      "grad_norm": 0.37154585123062134,
      "learning_rate": 2e-05,
      "loss": 0.6941,
      "step": 1730
    },
    {
      "epoch": 0.14564325772160375,
      "grad_norm": 0.38709065318107605,
      "learning_rate": 2e-05,
      "loss": 0.7337,
      "step": 1740
    },
    {
      "epoch": 0.14648028793839457,
      "grad_norm": 1.7314486503601074,
      "learning_rate": 2e-05,
      "loss": 0.7005,
      "step": 1750
    },
    {
      "epoch": 0.1473173181551854,
      "grad_norm": 0.3551817834377289,
      "learning_rate": 2e-05,
      "loss": 0.7132,
      "step": 1760
    },
    {
      "epoch": 0.14815434837197622,
      "grad_norm": 0.3846317529678345,
      "learning_rate": 2e-05,
      "loss": 0.6762,
      "step": 1770
    },
    {
      "epoch": 0.14899137858876704,
      "grad_norm": 0.37913134694099426,
      "learning_rate": 2e-05,
      "loss": 0.7101,
      "step": 1780
    },
    {
      "epoch": 0.1498284088055579,
      "grad_norm": 0.3794521391391754,
      "learning_rate": 2e-05,
      "loss": 0.7327,
      "step": 1790
    },
    {
      "epoch": 0.15066543902234872,
      "grad_norm": 0.3727302551269531,
      "learning_rate": 2e-05,
      "loss": 0.7198,
      "step": 1800
    },
    {
      "epoch": 0.15150246923913954,
      "grad_norm": 0.39975666999816895,
      "learning_rate": 2e-05,
      "loss": 0.7283,
      "step": 1810
    },
    {
      "epoch": 0.15233949945593037,
      "grad_norm": 0.37394288182258606,
      "learning_rate": 2e-05,
      "loss": 0.6815,
      "step": 1820
    },
    {
      "epoch": 0.1531765296727212,
      "grad_norm": 0.38191404938697815,
      "learning_rate": 2e-05,
      "loss": 0.723,
      "step": 1830
    },
    {
      "epoch": 0.15401355988951201,
      "grad_norm": 0.3914385437965393,
      "learning_rate": 2e-05,
      "loss": 0.6959,
      "step": 1840
    },
    {
      "epoch": 0.15485059010630284,
      "grad_norm": 0.36960726976394653,
      "learning_rate": 2e-05,
      "loss": 0.6981,
      "step": 1850
    },
    {
      "epoch": 0.15568762032309366,
      "grad_norm": 0.4533153474330902,
      "learning_rate": 2e-05,
      "loss": 0.7042,
      "step": 1860
    },
    {
      "epoch": 0.15652465053988449,
      "grad_norm": 0.390516459941864,
      "learning_rate": 2e-05,
      "loss": 0.7285,
      "step": 1870
    },
    {
      "epoch": 0.1573616807566753,
      "grad_norm": 0.36687996983528137,
      "learning_rate": 2e-05,
      "loss": 0.7039,
      "step": 1880
    },
    {
      "epoch": 0.15819871097346613,
      "grad_norm": 0.3998259902000427,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 1890
    },
    {
      "epoch": 0.15903574119025696,
      "grad_norm": 0.3630969226360321,
      "learning_rate": 2e-05,
      "loss": 0.7156,
      "step": 1900
    },
    {
      "epoch": 0.15987277140704778,
      "grad_norm": 0.49144166707992554,
      "learning_rate": 2e-05,
      "loss": 0.7492,
      "step": 1910
    },
    {
      "epoch": 0.16070980162383863,
      "grad_norm": 0.3666890263557434,
      "learning_rate": 2e-05,
      "loss": 0.6957,
      "step": 1920
    },
    {
      "epoch": 0.16154683184062946,
      "grad_norm": 0.36240652203559875,
      "learning_rate": 2e-05,
      "loss": 0.7208,
      "step": 1930
    },
    {
      "epoch": 0.16238386205742028,
      "grad_norm": 0.37068548798561096,
      "learning_rate": 2e-05,
      "loss": 0.7593,
      "step": 1940
    },
    {
      "epoch": 0.1632208922742111,
      "grad_norm": 0.38422319293022156,
      "learning_rate": 2e-05,
      "loss": 0.718,
      "step": 1950
    },
    {
      "epoch": 0.16405792249100193,
      "grad_norm": 0.4526020884513855,
      "learning_rate": 2e-05,
      "loss": 0.7152,
      "step": 1960
    },
    {
      "epoch": 0.16489495270779275,
      "grad_norm": 0.42693546414375305,
      "learning_rate": 2e-05,
      "loss": 0.7031,
      "step": 1970
    },
    {
      "epoch": 0.16573198292458358,
      "grad_norm": 0.352283239364624,
      "learning_rate": 2e-05,
      "loss": 0.6788,
      "step": 1980
    },
    {
      "epoch": 0.1665690131413744,
      "grad_norm": 0.4254308342933655,
      "learning_rate": 2e-05,
      "loss": 0.7004,
      "step": 1990
    },
    {
      "epoch": 0.16740604335816522,
      "grad_norm": 0.37109827995300293,
      "learning_rate": 2e-05,
      "loss": 0.7183,
      "step": 2000
    },
    {
      "epoch": 0.16824307357495605,
      "grad_norm": 0.3963578939437866,
      "learning_rate": 2e-05,
      "loss": 0.7152,
      "step": 2010
    },
    {
      "epoch": 0.16908010379174687,
      "grad_norm": 0.4323606491088867,
      "learning_rate": 2e-05,
      "loss": 0.7275,
      "step": 2020
    },
    {
      "epoch": 0.1699171340085377,
      "grad_norm": 0.38154488801956177,
      "learning_rate": 2e-05,
      "loss": 0.7043,
      "step": 2030
    },
    {
      "epoch": 0.17075416422532855,
      "grad_norm": 0.37403401732444763,
      "learning_rate": 2e-05,
      "loss": 0.6961,
      "step": 2040
    },
    {
      "epoch": 0.17159119444211937,
      "grad_norm": 0.4297429919242859,
      "learning_rate": 2e-05,
      "loss": 0.7279,
      "step": 2050
    },
    {
      "epoch": 0.1724282246589102,
      "grad_norm": 0.3764204978942871,
      "learning_rate": 2e-05,
      "loss": 0.7169,
      "step": 2060
    },
    {
      "epoch": 0.17326525487570102,
      "grad_norm": 0.4536464512348175,
      "learning_rate": 2e-05,
      "loss": 0.7076,
      "step": 2070
    },
    {
      "epoch": 0.17410228509249184,
      "grad_norm": 0.3891889750957489,
      "learning_rate": 2e-05,
      "loss": 0.6937,
      "step": 2080
    },
    {
      "epoch": 0.17493931530928267,
      "grad_norm": 0.3979426920413971,
      "learning_rate": 2e-05,
      "loss": 0.7117,
      "step": 2090
    },
    {
      "epoch": 0.1757763455260735,
      "grad_norm": 0.33533552289009094,
      "learning_rate": 2e-05,
      "loss": 0.6911,
      "step": 2100
    },
    {
      "epoch": 0.17661337574286431,
      "grad_norm": 0.4086405038833618,
      "learning_rate": 2e-05,
      "loss": 0.6961,
      "step": 2110
    },
    {
      "epoch": 0.17745040595965514,
      "grad_norm": 0.32550907135009766,
      "learning_rate": 2e-05,
      "loss": 0.7189,
      "step": 2120
    },
    {
      "epoch": 0.17828743617644596,
      "grad_norm": 0.41129428148269653,
      "learning_rate": 2e-05,
      "loss": 0.7132,
      "step": 2130
    },
    {
      "epoch": 0.1791244663932368,
      "grad_norm": 0.38379132747650146,
      "learning_rate": 2e-05,
      "loss": 0.7083,
      "step": 2140
    },
    {
      "epoch": 0.1799614966100276,
      "grad_norm": 0.33447548747062683,
      "learning_rate": 2e-05,
      "loss": 0.6957,
      "step": 2150
    },
    {
      "epoch": 0.18079852682681846,
      "grad_norm": 0.36413493752479553,
      "learning_rate": 2e-05,
      "loss": 0.6845,
      "step": 2160
    },
    {
      "epoch": 0.18163555704360929,
      "grad_norm": 0.3704940676689148,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 2170
    },
    {
      "epoch": 0.1824725872604001,
      "grad_norm": 0.37158524990081787,
      "learning_rate": 2e-05,
      "loss": 0.6945,
      "step": 2180
    },
    {
      "epoch": 0.18330961747719093,
      "grad_norm": 0.37925466895103455,
      "learning_rate": 2e-05,
      "loss": 0.7088,
      "step": 2190
    },
    {
      "epoch": 0.18414664769398176,
      "grad_norm": 0.3649779260158539,
      "learning_rate": 2e-05,
      "loss": 0.7342,
      "step": 2200
    },
    {
      "epoch": 0.18498367791077258,
      "grad_norm": 0.38125574588775635,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 2210
    },
    {
      "epoch": 0.1858207081275634,
      "grad_norm": 0.4088246524333954,
      "learning_rate": 2e-05,
      "loss": 0.7006,
      "step": 2220
    },
    {
      "epoch": 0.18665773834435423,
      "grad_norm": 0.4514538645744324,
      "learning_rate": 2e-05,
      "loss": 0.7126,
      "step": 2230
    },
    {
      "epoch": 0.18749476856114505,
      "grad_norm": 0.3832446336746216,
      "learning_rate": 2e-05,
      "loss": 0.6912,
      "step": 2240
    },
    {
      "epoch": 0.18833179877793588,
      "grad_norm": 0.37790173292160034,
      "learning_rate": 2e-05,
      "loss": 0.6738,
      "step": 2250
    },
    {
      "epoch": 0.1891688289947267,
      "grad_norm": 0.3716677129268646,
      "learning_rate": 2e-05,
      "loss": 0.7122,
      "step": 2260
    },
    {
      "epoch": 0.19000585921151752,
      "grad_norm": 0.3565468490123749,
      "learning_rate": 2e-05,
      "loss": 0.679,
      "step": 2270
    },
    {
      "epoch": 0.19084288942830835,
      "grad_norm": 0.37897953391075134,
      "learning_rate": 2e-05,
      "loss": 0.6941,
      "step": 2280
    },
    {
      "epoch": 0.1916799196450992,
      "grad_norm": 0.3777736723423004,
      "learning_rate": 2e-05,
      "loss": 0.7166,
      "step": 2290
    },
    {
      "epoch": 0.19251694986189002,
      "grad_norm": 0.3585146367549896,
      "learning_rate": 2e-05,
      "loss": 0.6928,
      "step": 2300
    },
    {
      "epoch": 0.19335398007868085,
      "grad_norm": 0.3698466122150421,
      "learning_rate": 2e-05,
      "loss": 0.6937,
      "step": 2310
    },
    {
      "epoch": 0.19419101029547167,
      "grad_norm": 0.3647162914276123,
      "learning_rate": 2e-05,
      "loss": 0.7128,
      "step": 2320
    },
    {
      "epoch": 0.1950280405122625,
      "grad_norm": 0.4572893977165222,
      "learning_rate": 2e-05,
      "loss": 0.6978,
      "step": 2330
    },
    {
      "epoch": 0.19586507072905332,
      "grad_norm": 0.42052674293518066,
      "learning_rate": 2e-05,
      "loss": 0.6901,
      "step": 2340
    },
    {
      "epoch": 0.19670210094584414,
      "grad_norm": 0.4102165102958679,
      "learning_rate": 2e-05,
      "loss": 0.7097,
      "step": 2350
    },
    {
      "epoch": 0.19753913116263497,
      "grad_norm": 0.3792290687561035,
      "learning_rate": 2e-05,
      "loss": 0.6917,
      "step": 2360
    },
    {
      "epoch": 0.1983761613794258,
      "grad_norm": 0.41515079140663147,
      "learning_rate": 2e-05,
      "loss": 0.7033,
      "step": 2370
    },
    {
      "epoch": 0.19921319159621662,
      "grad_norm": 0.44105610251426697,
      "learning_rate": 2e-05,
      "loss": 0.7093,
      "step": 2380
    },
    {
      "epoch": 0.20005022181300744,
      "grad_norm": 0.3615840971469879,
      "learning_rate": 2e-05,
      "loss": 0.7512,
      "step": 2390
    },
    {
      "epoch": 0.20088725202979826,
      "grad_norm": 0.3563784062862396,
      "learning_rate": 2e-05,
      "loss": 0.7046,
      "step": 2400
    },
    {
      "epoch": 0.20172428224658911,
      "grad_norm": 0.3593883216381073,
      "learning_rate": 2e-05,
      "loss": 0.7143,
      "step": 2410
    },
    {
      "epoch": 0.20256131246337994,
      "grad_norm": 0.375445157289505,
      "learning_rate": 2e-05,
      "loss": 0.678,
      "step": 2420
    },
    {
      "epoch": 0.20339834268017076,
      "grad_norm": 0.3783409595489502,
      "learning_rate": 2e-05,
      "loss": 0.6926,
      "step": 2430
    },
    {
      "epoch": 0.2042353728969616,
      "grad_norm": 0.3709818720817566,
      "learning_rate": 2e-05,
      "loss": 0.6974,
      "step": 2440
    },
    {
      "epoch": 0.2050724031137524,
      "grad_norm": 0.3591563403606415,
      "learning_rate": 2e-05,
      "loss": 0.7022,
      "step": 2450
    },
    {
      "epoch": 0.20590943333054323,
      "grad_norm": 0.42944005131721497,
      "learning_rate": 2e-05,
      "loss": 0.7151,
      "step": 2460
    },
    {
      "epoch": 0.20674646354733406,
      "grad_norm": 0.36380648612976074,
      "learning_rate": 2e-05,
      "loss": 0.6938,
      "step": 2470
    },
    {
      "epoch": 0.20758349376412488,
      "grad_norm": 0.3823877274990082,
      "learning_rate": 2e-05,
      "loss": 0.6853,
      "step": 2480
    },
    {
      "epoch": 0.2084205239809157,
      "grad_norm": 0.40340110659599304,
      "learning_rate": 2e-05,
      "loss": 0.6983,
      "step": 2490
    },
    {
      "epoch": 0.20925755419770653,
      "grad_norm": 0.3656036853790283,
      "learning_rate": 2e-05,
      "loss": 0.6927,
      "step": 2500
    },
    {
      "epoch": 0.21009458441449735,
      "grad_norm": 0.3953785002231598,
      "learning_rate": 2e-05,
      "loss": 0.6779,
      "step": 2510
    },
    {
      "epoch": 0.21093161463128818,
      "grad_norm": 0.40045875310897827,
      "learning_rate": 2e-05,
      "loss": 0.6812,
      "step": 2520
    },
    {
      "epoch": 0.211768644848079,
      "grad_norm": 0.3604848086833954,
      "learning_rate": 2e-05,
      "loss": 0.6908,
      "step": 2530
    },
    {
      "epoch": 0.21260567506486985,
      "grad_norm": 0.40517356991767883,
      "learning_rate": 2e-05,
      "loss": 0.7074,
      "step": 2540
    },
    {
      "epoch": 0.21344270528166068,
      "grad_norm": 0.40945446491241455,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.7023,
      "step": 2550
    },
    {
      "epoch": 0.2142797354984515,
      "grad_norm": 0.35332345962524414,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.704,
      "step": 2560
    },
    {
      "epoch": 0.21511676571524233,
      "grad_norm": 0.32888680696487427,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.675,
      "step": 2570
    },
    {
      "epoch": 0.21595379593203315,
      "grad_norm": 0.3869115114212036,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.6927,
      "step": 2580
    },
    {
      "epoch": 0.21679082614882397,
      "grad_norm": 0.38035112619400024,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.722,
      "step": 2590
    },
    {
      "epoch": 0.2176278563656148,
      "grad_norm": 0.3800182044506073,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.6936,
      "step": 2600
    },
    {
      "epoch": 0.21846488658240562,
      "grad_norm": 0.3644275367259979,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.6909,
      "step": 2610
    },
    {
      "epoch": 0.21930191679919644,
      "grad_norm": 0.38952329754829407,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.682,
      "step": 2620
    },
    {
      "epoch": 0.22013894701598727,
      "grad_norm": 0.37770339846611023,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.6635,
      "step": 2630
    },
    {
      "epoch": 0.2209759772327781,
      "grad_norm": 0.34742140769958496,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.7174,
      "step": 2640
    },
    {
      "epoch": 0.22181300744956892,
      "grad_norm": 0.3670879304409027,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.6907,
      "step": 2650
    },
    {
      "epoch": 0.22265003766635977,
      "grad_norm": 0.3617439270019531,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.7166,
      "step": 2660
    },
    {
      "epoch": 0.2234870678831506,
      "grad_norm": 0.36148807406425476,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.6995,
      "step": 2670
    },
    {
      "epoch": 0.22432409809994142,
      "grad_norm": 0.34924519062042236,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.7024,
      "step": 2680
    },
    {
      "epoch": 0.22516112831673224,
      "grad_norm": 0.3570590317249298,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.6813,
      "step": 2690
    },
    {
      "epoch": 0.22599815853352306,
      "grad_norm": 0.37608057260513306,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.6568,
      "step": 2700
    },
    {
      "epoch": 0.2268351887503139,
      "grad_norm": 0.350795716047287,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.6786,
      "step": 2710
    },
    {
      "epoch": 0.2276722189671047,
      "grad_norm": 0.3413582742214203,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.6893,
      "step": 2720
    },
    {
      "epoch": 0.22850924918389554,
      "grad_norm": 0.38526901602745056,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.6892,
      "step": 2730
    },
    {
      "epoch": 0.22934627940068636,
      "grad_norm": 0.36428093910217285,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.7054,
      "step": 2740
    },
    {
      "epoch": 0.23018330961747718,
      "grad_norm": 0.3428427278995514,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.7102,
      "step": 2750
    },
    {
      "epoch": 0.231020339834268,
      "grad_norm": 0.4259762465953827,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.7018,
      "step": 2760
    },
    {
      "epoch": 0.23185737005105883,
      "grad_norm": 0.35835063457489014,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.7009,
      "step": 2770
    },
    {
      "epoch": 0.23269440026784968,
      "grad_norm": 0.3557145595550537,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.7039,
      "step": 2780
    },
    {
      "epoch": 0.2335314304846405,
      "grad_norm": 0.35716041922569275,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.6481,
      "step": 2790
    },
    {
      "epoch": 0.23420105465807314,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06283065401885746,
      "train_runtime": 2304.4445,
      "train_samples_per_second": 14.57,
      "train_steps_per_second": 1.214
    }
  ],
  "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
}