{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6842105263157894,
  "eval_steps": 2000,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 1.0191779136657715,
      "learning_rate": 8.403361344537815e-07,
      "loss": 1.4757,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.947059690952301,
      "learning_rate": 8.403361344537817e-06,
      "loss": 1.5145,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.9549775719642639,
      "learning_rate": 1.6806722689075634e-05,
      "loss": 1.5546,
      "step": 20
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.1984186172485352,
      "learning_rate": 2.5210084033613446e-05,
      "loss": 1.6809,
      "step": 30
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9854737520217896,
      "learning_rate": 3.361344537815127e-05,
      "loss": 1.8074,
      "step": 40
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.3563014268875122,
      "learning_rate": 4.201680672268908e-05,
      "loss": 1.699,
      "step": 50
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.6414602398872375,
      "learning_rate": 5.042016806722689e-05,
      "loss": 1.3419,
      "step": 60
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.580333948135376,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.2524,
      "step": 70
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.6972444653511047,
      "learning_rate": 6.722689075630254e-05,
      "loss": 1.4261,
      "step": 80
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.8142390847206116,
      "learning_rate": 7.563025210084033e-05,
      "loss": 1.5472,
      "step": 90
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.9213963747024536,
      "learning_rate": 8.403361344537815e-05,
      "loss": 1.5581,
      "step": 100
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.7875838279724121,
      "learning_rate": 9.243697478991598e-05,
      "loss": 1.2596,
      "step": 110
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.6198441982269287,
      "learning_rate": 0.00010084033613445378,
      "loss": 1.2901,
      "step": 120
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.6708433032035828,
      "learning_rate": 0.00010924369747899159,
      "loss": 1.3087,
      "step": 130
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.8415197730064392,
      "learning_rate": 0.00011764705882352942,
      "loss": 1.4806,
      "step": 140
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.7113947868347168,
      "learning_rate": 0.00012605042016806722,
      "loss": 1.5082,
      "step": 150
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.7543832659721375,
      "learning_rate": 0.00013445378151260507,
      "loss": 1.1818,
      "step": 160
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.577403724193573,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.2308,
      "step": 170
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6748159527778625,
      "learning_rate": 0.00015126050420168066,
      "loss": 1.3738,
      "step": 180
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.8842242360115051,
      "learning_rate": 0.0001596638655462185,
      "loss": 1.4544,
      "step": 190
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.7435425519943237,
      "learning_rate": 0.0001680672268907563,
      "loss": 1.4997,
      "step": 200
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5861243009567261,
      "learning_rate": 0.00017647058823529413,
      "loss": 1.1774,
      "step": 210
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5415711998939514,
      "learning_rate": 0.00018487394957983195,
      "loss": 1.0529,
      "step": 220
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6118600964546204,
      "learning_rate": 0.00019327731092436975,
      "loss": 1.3117,
      "step": 230
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.8368746042251587,
      "learning_rate": 0.00019999990304024961,
      "loss": 1.4745,
      "step": 240
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.086878776550293,
      "learning_rate": 0.00019999650946872738,
      "loss": 1.3995,
      "step": 250
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.6036991477012634,
      "learning_rate": 0.00019998826809770645,
      "loss": 1.2325,
      "step": 260
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5606744289398193,
      "learning_rate": 0.0001999751793267259,
      "loss": 1.2043,
      "step": 270
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6112542748451233,
      "learning_rate": 0.00019995724379032526,
      "loss": 1.2512,
      "step": 280
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.7892420887947083,
      "learning_rate": 0.00019993446235801367,
      "loss": 1.3604,
      "step": 290
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.2104417085647583,
      "learning_rate": 0.00019990683613422787,
      "loss": 1.4282,
      "step": 300
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.5284091234207153,
      "learning_rate": 0.0001998743664582786,
      "loss": 1.1223,
      "step": 310
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.5215238928794861,
      "learning_rate": 0.0001998370549042855,
      "loss": 1.1399,
      "step": 320
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6061808466911316,
      "learning_rate": 0.0001997949032811011,
      "loss": 1.2432,
      "step": 330
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.7220178246498108,
      "learning_rate": 0.0001997479136322229,
      "loss": 1.4737,
      "step": 340
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.035914421081543,
      "learning_rate": 0.00019969608823569433,
      "loss": 1.5087,
      "step": 350
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5120232701301575,
      "learning_rate": 0.00019963942960399446,
      "loss": 1.1583,
      "step": 360
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.5209968686103821,
      "learning_rate": 0.00019957794048391602,
      "loss": 1.1494,
      "step": 370
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.5688252449035645,
      "learning_rate": 0.0001995116238564323,
      "loss": 1.2648,
      "step": 380
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.7350272536277771,
      "learning_rate": 0.00019944048293655265,
      "loss": 1.3836,
      "step": 390
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.117912769317627,
      "learning_rate": 0.00019936452117316663,
      "loss": 1.3725,
      "step": 400
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.5087815523147583,
      "learning_rate": 0.00019928374224887678,
      "loss": 1.0783,
      "step": 410
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.4944276213645935,
      "learning_rate": 0.00019919815007982003,
      "loss": 1.0936,
      "step": 420
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5578716397285461,
      "learning_rate": 0.000199107748815478,
      "loss": 1.1705,
      "step": 430
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.670518696308136,
      "learning_rate": 0.00019901254283847573,
      "loss": 1.3099,
      "step": 440
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.9550499320030212,
      "learning_rate": 0.00019891253676436915,
      "loss": 1.3971,
      "step": 450
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.48883694410324097,
      "learning_rate": 0.00019880773544142148,
      "loss": 1.1091,
      "step": 460
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5331695675849915,
      "learning_rate": 0.00019869814395036807,
      "loss": 1.1169,
      "step": 470
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6103072166442871,
      "learning_rate": 0.0001985837676041701,
      "loss": 1.2462,
      "step": 480
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.7295002937316895,
      "learning_rate": 0.00019846461194775712,
      "loss": 1.3711,
      "step": 490
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.003199815750122,
      "learning_rate": 0.000198340682757758,
      "loss": 1.3987,
      "step": 500
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.49524402618408203,
      "learning_rate": 0.00019821198604222113,
      "loss": 1.1002,
      "step": 510
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.4883529543876648,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.0895,
      "step": 520
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.5645517110824585,
      "learning_rate": 0.00019794031522206594,
      "loss": 1.1673,
      "step": 530
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.7130540609359741,
      "learning_rate": 0.00019779735428796395,
      "loss": 1.2775,
      "step": 540
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.035349726676941,
      "learning_rate": 0.00019764965216871846,
      "loss": 1.3272,
      "step": 550
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5434763431549072,
      "learning_rate": 0.00019749721602488207,
      "loss": 1.1483,
      "step": 560
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.472807914018631,
      "learning_rate": 0.0001973400532465113,
      "loss": 1.0666,
      "step": 570
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.575896143913269,
      "learning_rate": 0.00019717817145280844,
      "loss": 1.122,
      "step": 580
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6578025817871094,
      "learning_rate": 0.00019701157849175228,
      "loss": 1.2858,
      "step": 590
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.2908504009246826,
      "learning_rate": 0.0001968402824397174,
      "loss": 1.3983,
      "step": 600
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.5685085654258728,
      "learning_rate": 0.0001966642916010829,
      "loss": 1.0992,
      "step": 610
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.4999242126941681,
      "learning_rate": 0.0001964836145078295,
      "loss": 1.1434,
      "step": 620
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.5502079129219055,
      "learning_rate": 0.00019629825991912623,
      "loss": 1.1573,
      "step": 630
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6397935748100281,
      "learning_rate": 0.0001961082368209055,
      "loss": 1.3418,
      "step": 640
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.9650578498840332,
      "learning_rate": 0.00019591355442542775,
      "loss": 1.3298,
      "step": 650
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.49895137548446655,
      "learning_rate": 0.00019571422217083454,
      "loss": 1.0907,
      "step": 660
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.49023300409317017,
      "learning_rate": 0.00019551024972069126,
      "loss": 1.1305,
      "step": 670
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5746453404426575,
      "learning_rate": 0.00019530164696351848,
      "loss": 1.1865,
      "step": 680
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.6834538578987122,
      "learning_rate": 0.00019508842401231257,
      "loss": 1.3113,
      "step": 690
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.0113998651504517,
      "learning_rate": 0.0001948705912040556,
      "loss": 1.3686,
      "step": 700
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5399815440177917,
      "learning_rate": 0.0001946481590992139,
      "loss": 1.1602,
      "step": 710
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5135788321495056,
      "learning_rate": 0.00019442113848122636,
      "loss": 1.0881,
      "step": 720
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5519896149635315,
      "learning_rate": 0.00019418954035598152,
      "loss": 1.1885,
      "step": 730
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.7329438328742981,
      "learning_rate": 0.000193953375951284,
      "loss": 1.2668,
      "step": 740
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.0599132776260376,
      "learning_rate": 0.00019371265671631037,
      "loss": 1.3524,
      "step": 750
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5613999962806702,
      "learning_rate": 0.00019346739432105374,
      "loss": 1.0983,
      "step": 760
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5169478058815002,
      "learning_rate": 0.00019321760065575834,
      "loss": 1.1699,
      "step": 770
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5800842642784119,
      "learning_rate": 0.00019296328783034294,
      "loss": 1.2105,
      "step": 780
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.7089204788208008,
      "learning_rate": 0.00019270446817381377,
      "loss": 1.3458,
      "step": 790
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.8912138342857361,
      "learning_rate": 0.00019244115423366678,
      "loss": 1.3386,
      "step": 800
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.5033462047576904,
      "learning_rate": 0.00019217335877527947,
      "loss": 1.0824,
      "step": 810
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5139713287353516,
      "learning_rate": 0.0001919010947812918,
      "loss": 1.0122,
      "step": 820
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5905170440673828,
      "learning_rate": 0.00019162437545097719,
      "loss": 1.2924,
      "step": 830
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.715568482875824,
      "learning_rate": 0.00019134321419960203,
      "loss": 1.2982,
      "step": 840
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.046240210533142,
      "learning_rate": 0.00019105762465777598,
      "loss": 1.4013,
      "step": 850
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.49822917580604553,
      "learning_rate": 0.00019076762067079059,
      "loss": 1.0633,
      "step": 860
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.47567543387413025,
      "learning_rate": 0.0001904732162979485,
      "loss": 1.0497,
      "step": 870
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.5331007242202759,
      "learning_rate": 0.0001901744258118816,
      "loss": 1.166,
      "step": 880
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.7400739789009094,
      "learning_rate": 0.00018987126369785916,
      "loss": 1.3527,
      "step": 890
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.1264495849609375,
      "learning_rate": 0.00018956374465308563,
      "loss": 1.3475,
      "step": 900
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5124080777168274,
      "learning_rate": 0.00018925188358598813,
      "loss": 1.05,
      "step": 910
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.522303581237793,
      "learning_rate": 0.00018893569561549364,
      "loss": 1.156,
      "step": 920
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5782234072685242,
      "learning_rate": 0.00018861519607029606,
      "loss": 1.158,
      "step": 930
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.7259439826011658,
      "learning_rate": 0.00018829040048811305,
      "loss": 1.306,
      "step": 940
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.9230518937110901,
      "learning_rate": 0.0001879613246149329,
      "loss": 1.4171,
      "step": 950
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5070952773094177,
      "learning_rate": 0.00018762798440425096,
      "loss": 1.0647,
      "step": 960
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.540289044380188,
      "learning_rate": 0.00018729039601629634,
      "loss": 1.0823,
      "step": 970
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.6044334173202515,
      "learning_rate": 0.00018694857581724855,
      "loss": 1.2258,
      "step": 980
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.6775342226028442,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.3045,
      "step": 990
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.0051116943359375,
      "learning_rate": 0.00018625230647557217,
      "loss": 1.3275,
      "step": 1000
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.522710382938385,
      "learning_rate": 0.00018589789108786344,
      "loss": 1.1284,
      "step": 1010
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.527962327003479,
      "learning_rate": 0.00018553931139726485,
      "loss": 1.0688,
      "step": 1020
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5457212924957275,
      "learning_rate": 0.0001851765847876076,
      "loss": 1.1434,
      "step": 1030
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.6518785357475281,
      "learning_rate": 0.00018480972884376434,
      "loss": 1.2961,
      "step": 1040
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.0324338674545288,
      "learning_rate": 0.00018443876135079638,
      "loss": 1.407,
      "step": 1050
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6092559099197388,
      "learning_rate": 0.0001840637002930918,
      "loss": 1.0535,
      "step": 1060
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5149545073509216,
      "learning_rate": 0.00018368456385349334,
      "loss": 1.0546,
      "step": 1070
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6056516766548157,
      "learning_rate": 0.0001833013704124169,
      "loss": 1.1735,
      "step": 1080
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.7382489442825317,
      "learning_rate": 0.00018291413854696077,
      "loss": 1.3044,
      "step": 1090
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.9548698663711548,
      "learning_rate": 0.0001825228870300046,
      "loss": 1.3571,
      "step": 1100
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.5410871505737305,
      "learning_rate": 0.0001821276348292995,
      "loss": 1.097,
      "step": 1110
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.5245351195335388,
      "learning_rate": 0.00018172840110654862,
      "loss": 1.0923,
      "step": 1120
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6045931577682495,
      "learning_rate": 0.00018132520521647785,
      "loss": 1.2115,
      "step": 1130
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6429124474525452,
      "learning_rate": 0.00018091806670589788,
      "loss": 1.2736,
      "step": 1140
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.9760797619819641,
      "learning_rate": 0.0001805070053127563,
      "loss": 1.2964,
      "step": 1150
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.48860272765159607,
      "learning_rate": 0.0001800920409651809,
      "loss": 1.0942,
      "step": 1160
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5090013146400452,
      "learning_rate": 0.00017967319378051343,
      "loss": 1.0925,
      "step": 1170
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5822442770004272,
      "learning_rate": 0.00017925048406433437,
      "loss": 1.1583,
      "step": 1180
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.7363468408584595,
      "learning_rate": 0.00017882393230947855,
      "loss": 1.3283,
      "step": 1190
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.840218186378479,
      "learning_rate": 0.00017839355919504164,
      "loss": 1.3098,
      "step": 1200
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5360991954803467,
      "learning_rate": 0.00017795938558537753,
      "loss": 1.1028,
      "step": 1210
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5553500056266785,
      "learning_rate": 0.00017752143252908705,
      "loss": 1.0737,
      "step": 1220
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5366541743278503,
      "learning_rate": 0.00017707972125799735,
      "loss": 1.1918,
      "step": 1230
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.7474969029426575,
      "learning_rate": 0.0001766342731861327,
      "loss": 1.2756,
      "step": 1240
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.0241633653640747,
      "learning_rate": 0.00017618510990867624,
      "loss": 1.298,
      "step": 1250
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.5135468244552612,
      "learning_rate": 0.00017573225320092323,
      "loss": 0.9818,
      "step": 1260
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.5308533906936646,
      "learning_rate": 0.00017527572501722512,
      "loss": 1.0729,
      "step": 1270
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.6265894174575806,
      "learning_rate": 0.00017481554748992553,
      "loss": 1.1791,
      "step": 1280
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.7500415444374084,
      "learning_rate": 0.00017435174292828695,
      "loss": 1.2722,
      "step": 1290
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.0609970092773438,
      "learning_rate": 0.00017388433381740952,
      "loss": 1.3034,
      "step": 1300
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5286604166030884,
      "learning_rate": 0.00017341334281714064,
      "loss": 0.9932,
      "step": 1310
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5054761171340942,
      "learning_rate": 0.00017293879276097677,
      "loss": 1.0386,
      "step": 1320
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6337370872497559,
      "learning_rate": 0.00017246070665495608,
      "loss": 1.1341,
      "step": 1330
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.7288526892662048,
      "learning_rate": 0.00017197910767654352,
      "loss": 1.2551,
      "step": 1340
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.0159952640533447,
      "learning_rate": 0.0001714940191735069,
      "loss": 1.3048,
      "step": 1350
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5907754898071289,
      "learning_rate": 0.00017100546466278504,
      "loss": 1.0322,
      "step": 1360
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.5079711675643921,
      "learning_rate": 0.00017051346782934786,
      "loss": 1.0071,
      "step": 1370
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.6100701689720154,
      "learning_rate": 0.00017001805252504795,
      "loss": 1.1588,
      "step": 1380
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.7802088260650635,
      "learning_rate": 0.00016951924276746425,
      "loss": 1.2911,
      "step": 1390
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.0676313638687134,
      "learning_rate": 0.00016901706273873777,
      "loss": 1.2942,
      "step": 1400
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.527285099029541,
      "learning_rate": 0.00016851153678439922,
      "loss": 1.0107,
      "step": 1410
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5518642663955688,
      "learning_rate": 0.00016800268941218876,
      "loss": 1.0683,
      "step": 1420
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6224582195281982,
      "learning_rate": 0.0001674905452908678,
      "loss": 1.1685,
      "step": 1430
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.6205934882164001,
      "learning_rate": 0.0001669751292490231,
      "loss": 1.302,
      "step": 1440
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.0423789024353027,
      "learning_rate": 0.0001664564662738632,
      "loss": 1.2654,
      "step": 1450
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5314890742301941,
      "learning_rate": 0.00016593458151000688,
      "loss": 1.083,
      "step": 1460
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5361500978469849,
      "learning_rate": 0.00016540950025826422,
      "loss": 1.0952,
      "step": 1470
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5990237593650818,
      "learning_rate": 0.00016488124797441004,
      "loss": 1.1923,
      "step": 1480
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.7383199334144592,
      "learning_rate": 0.00016434985026794987,
      "loss": 1.288,
      "step": 1490
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.0500961542129517,
      "learning_rate": 0.0001638153329008782,
      "loss": 1.318,
      "step": 1500
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5643898248672485,
      "learning_rate": 0.00016327772178642986,
      "loss": 1.0641,
      "step": 1510
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.509543776512146,
      "learning_rate": 0.0001627370429878235,
      "loss": 1.0216,
      "step": 1520
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.6048777103424072,
      "learning_rate": 0.0001621933227169981,
      "loss": 1.136,
      "step": 1530
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.7480033040046692,
      "learning_rate": 0.0001616465873333423,
      "loss": 1.2798,
      "step": 1540
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.0061513185501099,
      "learning_rate": 0.00016109686334241655,
      "loss": 1.2482,
      "step": 1550
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.5828456282615662,
      "learning_rate": 0.0001605441773946679,
      "loss": 1.1134,
      "step": 1560
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.5483405590057373,
      "learning_rate": 0.00015998855628413823,
      "loss": 1.0308,
      "step": 1570
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.6139534711837769,
      "learning_rate": 0.00015943002694716519,
      "loss": 1.1093,
      "step": 1580
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.6477651000022888,
      "learning_rate": 0.0001588686164610763,
      "loss": 1.2047,
      "step": 1590
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.9526233077049255,
      "learning_rate": 0.00015830435204287628,
      "loss": 1.3359,
      "step": 1600
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5442110896110535,
      "learning_rate": 0.00015773726104792768,
      "loss": 1.0236,
      "step": 1610
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5667725801467896,
      "learning_rate": 0.0001571673709686245,
      "loss": 0.9956,
      "step": 1620
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.567449688911438,
      "learning_rate": 0.00015659470943305955,
      "loss": 1.1698,
      "step": 1630
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.7154501080513,
      "learning_rate": 0.00015601930420368486,
      "loss": 1.2682,
      "step": 1640
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.9630643725395203,
      "learning_rate": 0.00015544118317596605,
      "loss": 1.3124,
      "step": 1650
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5698636770248413,
      "learning_rate": 0.0001548603743770296,
      "loss": 1.0047,
      "step": 1660
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.538144588470459,
      "learning_rate": 0.0001542769059643045,
      "loss": 0.9859,
      "step": 1670
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.6153010725975037,
      "learning_rate": 0.00015369080622415683,
      "loss": 1.1059,
      "step": 1680
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.7482182383537292,
      "learning_rate": 0.00015310210357051863,
      "loss": 1.2589,
      "step": 1690
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.014577031135559,
      "learning_rate": 0.00015251082654351044,
      "loss": 1.2322,
      "step": 1700
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.5590934157371521,
      "learning_rate": 0.00015191700380805752,
      "loss": 1.0283,
      "step": 1710
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.5307114124298096,
      "learning_rate": 0.00015132066415250042,
      "loss": 1.0196,
      "step": 1720
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.6487598419189453,
      "learning_rate": 0.000150721836487199,
      "loss": 1.0595,
      "step": 1730
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.8052285313606262,
      "learning_rate": 0.00015012054984313116,
      "loss": 1.2083,
      "step": 1740
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.1172990798950195,
      "learning_rate": 0.00014951683337048537,
      "loss": 1.2899,
      "step": 1750
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5224259495735168,
      "learning_rate": 0.00014891071633724737,
      "loss": 1.0475,
      "step": 1760
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5798863768577576,
      "learning_rate": 0.00014830222812778126,
      "loss": 0.9953,
      "step": 1770
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.6029157638549805,
      "learning_rate": 0.00014769139824140516,
      "loss": 1.1619,
      "step": 1780
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.7881869673728943,
      "learning_rate": 0.00014707825629096084,
      "loss": 1.2333,
      "step": 1790
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.9496088624000549,
      "learning_rate": 0.00014646283200137828,
      "loss": 1.2424,
      "step": 1800
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5425153374671936,
      "learning_rate": 0.00014584515520823453,
      "loss": 0.9886,
      "step": 1810
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5590393543243408,
      "learning_rate": 0.0001452252558563073,
      "loss": 1.0041,
      "step": 1820
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5956026911735535,
      "learning_rate": 0.00014460316399812325,
      "loss": 1.1507,
      "step": 1830
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.7304853796958923,
      "learning_rate": 0.00014397890979250108,
      "loss": 1.2183,
      "step": 1840
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.0130630731582642,
      "learning_rate": 0.0001433525235030894,
      "loss": 1.2944,
      "step": 1850
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5265572667121887,
      "learning_rate": 0.00014272403549689955,
      "loss": 1.0166,
      "step": 1860
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.5423105955123901,
      "learning_rate": 0.0001420934762428335,
      "loss": 0.9559,
      "step": 1870
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.6281871199607849,
      "learning_rate": 0.00014146087631020665,
      "loss": 1.064,
      "step": 1880
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7130801677703857,
      "learning_rate": 0.00014082626636726582,
      "loss": 1.1955,
      "step": 1890
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.038220763206482,
      "learning_rate": 0.00014018967717970254,
      "loss": 1.2621,
      "step": 1900
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5577895045280457,
      "learning_rate": 0.00013955113960916146,
      "loss": 0.9577,
      "step": 1910
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.526157796382904,
      "learning_rate": 0.0001389106846117443,
      "loss": 1.0109,
      "step": 1920
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.6196286678314209,
      "learning_rate": 0.000138268343236509,
      "loss": 1.1256,
      "step": 1930
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.7702537178993225,
      "learning_rate": 0.00013762414662396444,
      "loss": 1.2524,
      "step": 1940
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.8746676445007324,
      "learning_rate": 0.00013697812600456093,
      "loss": 1.288,
      "step": 1950
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5723572969436646,
      "learning_rate": 0.000136330312697176,
      "loss": 0.995,
      "step": 1960
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5687806606292725,
      "learning_rate": 0.00013568073810759615,
      "loss": 1.042,
      "step": 1970
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5694392323493958,
      "learning_rate": 0.00013502943372699426,
      "loss": 1.0513,
      "step": 1980
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.770982563495636,
      "learning_rate": 0.00013437643113040301,
      "loss": 1.2595,
      "step": 1990
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.0096752643585205,
      "learning_rate": 0.000133721761975184,
      "loss": 1.2178,
      "step": 2000
    },
    {
      "epoch": 0.84,
      "eval_loss": 1.0813658237457275,
      "eval_runtime": 229.3235,
      "eval_samples_per_second": 4.361,
      "eval_steps_per_second": 0.545,
      "step": 2000
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5128979086875916,
      "learning_rate": 0.00013306545799949304,
      "loss": 0.9791,
      "step": 2010
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.6104242205619812,
      "learning_rate": 0.00013240755102074162,
      "loss": 0.9958,
      "step": 2020
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.634865403175354,
      "learning_rate": 0.00013174807293405428,
      "loss": 1.1336,
      "step": 2030
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.7030709385871887,
      "learning_rate": 0.00013108705571072233,
      "loss": 1.2373,
      "step": 2040
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.9466651082038879,
      "learning_rate": 0.00013042453139665397,
      "loss": 1.2789,
      "step": 2050
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5502979159355164,
      "learning_rate": 0.00012976053211082074,
      "loss": 1.0581,
      "step": 2060
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5557164549827576,
      "learning_rate": 0.00012909509004370028,
      "loss": 0.9754,
      "step": 2070
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.6184536218643188,
      "learning_rate": 0.00012842823745571588,
      "loss": 1.0759,
      "step": 2080
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.7712015509605408,
      "learning_rate": 0.0001277600066756724,
      "loss": 1.199,
      "step": 2090
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.0351948738098145,
      "learning_rate": 0.00012709043009918896,
      "loss": 1.3047,
      "step": 2100
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5212281346321106,
      "learning_rate": 0.00012641954018712863,
      "loss": 0.9635,
      "step": 2110
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5956359505653381,
      "learning_rate": 0.0001257473694640244,
      "loss": 0.9984,
      "step": 2120
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.649682343006134,
      "learning_rate": 0.00012507395051650268,
      "loss": 1.1465,
      "step": 2130
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.7536346912384033,
      "learning_rate": 0.00012439931599170342,
      "loss": 1.2214,
      "step": 2140
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.926645040512085,
      "learning_rate": 0.00012372349859569737,
      "loss": 1.197,
      "step": 2150
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.5298001766204834,
      "learning_rate": 0.0001230465310919004,
      "loss": 1.0572,
      "step": 2160
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.5461262464523315,
      "learning_rate": 0.00012236844629948538,
      "loss": 1.0131,
      "step": 2170
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.6402174234390259,
      "learning_rate": 0.00012168927709179094,
      "loss": 1.1128,
      "step": 2180
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.8170130252838135,
      "learning_rate": 0.00012100905639472779,
      "loss": 1.1808,
      "step": 2190
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.1390860080718994,
      "learning_rate": 0.00012032781718518257,
      "loss": 1.2739,
      "step": 2200
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5590136647224426,
      "learning_rate": 0.00011964559248941903,
      "loss": 0.9234,
      "step": 2210
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5282031297683716,
      "learning_rate": 0.00011896241538147703,
      "loss": 0.9832,
      "step": 2220
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.6679378151893616,
      "learning_rate": 0.00011827831898156905,
      "loss": 1.1028,
      "step": 2230
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.7357510328292847,
      "learning_rate": 0.00011759333645447455,
      "loss": 1.1958,
      "step": 2240
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.9115193486213684,
      "learning_rate": 0.0001169075010079322,
      "loss": 1.2317,
      "step": 2250
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5533779263496399,
      "learning_rate": 0.00011622084589102986,
      "loss": 1.0045,
      "step": 2260
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.6029343008995056,
      "learning_rate": 0.00011553340439259286,
      "loss": 0.9566,
      "step": 2270
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5945916771888733,
      "learning_rate": 0.00011484520983956997,
      "loss": 1.0913,
      "step": 2280
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.8109087944030762,
      "learning_rate": 0.00011415629559541782,
      "loss": 1.2433,
      "step": 2290
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.9386932849884033,
      "learning_rate": 0.00011346669505848353,
      "loss": 1.2307,
      "step": 2300
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.6317028403282166,
      "learning_rate": 0.00011277644166038534,
      "loss": 1.0105,
      "step": 2310
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5305240750312805,
      "learning_rate": 0.00011208556886439216,
      "loss": 0.9351,
      "step": 2320
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.621440589427948,
      "learning_rate": 0.00011139411016380093,
      "loss": 1.0558,
      "step": 2330
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.7868437170982361,
      "learning_rate": 0.00011070209908031322,
      "loss": 1.1889,
      "step": 2340
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.9640358686447144,
      "learning_rate": 0.00011000956916240985,
      "loss": 1.2697,
      "step": 2350
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.6120818853378296,
      "learning_rate": 0.00010931655398372462,
      "loss": 0.9262,
      "step": 2360
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7230446934700012,
      "learning_rate": 0.00010862308714141661,
      "loss": 1.1753,
      "step": 2370
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5455570816993713,
      "learning_rate": 0.00010792920225454139,
      "loss": 1.0577,
      "step": 2380
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.5207303762435913,
      "learning_rate": 0.00010723493296242129,
      "loss": 0.8919,
      "step": 2390
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.6713350415229797,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.9547,
      "step": 2400
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.7119928598403931,
      "learning_rate": 0.00010584537581128276,
      "loss": 1.1245,
      "step": 2410
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.9546805024147034,
      "learning_rate": 0.00010515015531756036,
      "loss": 1.1268,
      "step": 2420
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.7098658084869385,
      "learning_rate": 0.00010445468514591925,
      "loss": 1.0389,
      "step": 2430
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.5891678333282471,
      "learning_rate": 0.00010375899901253572,
      "loss": 0.9701,
      "step": 2440
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.646004855632782,
      "learning_rate": 0.0001030631306440559,
      "loss": 0.9574,
      "step": 2450
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.7500150203704834,
      "learning_rate": 0.00010236711377596072,
      "loss": 1.0919,
      "step": 2460
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.9092882871627808,
      "learning_rate": 0.00010167098215093009,
      "loss": 1.0797,
      "step": 2470
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.6681928038597107,
      "learning_rate": 0.00010097476951720752,
      "loss": 0.9011,
      "step": 2480
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.6693964004516602,
      "learning_rate": 0.00010027850962696368,
      "loss": 0.911,
      "step": 2490
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.6667538285255432,
      "learning_rate": 9.958223623466025e-05,
      "loss": 0.9444,
      "step": 2500
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.7424312829971313,
      "learning_rate": 9.888598309541347e-05,
      "loss": 1.0328,
      "step": 2510
    },
    {
      "epoch": 1.06,
      "grad_norm": 1.0285619497299194,
      "learning_rate": 9.818978396335772e-05,
      "loss": 1.1074,
      "step": 2520
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.7485564351081848,
      "learning_rate": 9.749367259000918e-05,
      "loss": 0.9986,
      "step": 2530
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.6146641969680786,
      "learning_rate": 9.679768272262949e-05,
      "loss": 0.9217,
      "step": 2540
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.714490532875061,
      "learning_rate": 9.610184810258963e-05,
      "loss": 0.9297,
      "step": 2550
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.7230827212333679,
      "learning_rate": 9.540620246373439e-05,
      "loss": 1.0436,
      "step": 2560
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.9164597392082214,
      "learning_rate": 9.471077953074674e-05,
      "loss": 1.1374,
      "step": 2570
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.6540518999099731,
      "learning_rate": 9.401561301751286e-05,
      "loss": 1.011,
      "step": 2580
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.6425168514251709,
      "learning_rate": 9.332073662548784e-05,
      "loss": 0.899,
      "step": 2590
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.6701865196228027,
      "learning_rate": 9.262618404206191e-05,
      "loss": 0.9899,
      "step": 2600
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.7741339206695557,
      "learning_rate": 9.193198893892698e-05,
      "loss": 1.0721,
      "step": 2610
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.9790834188461304,
      "learning_rate": 9.123818497044446e-05,
      "loss": 1.1014,
      "step": 2620
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.672179639339447,
      "learning_rate": 9.05448057720138e-05,
      "loss": 0.934,
      "step": 2630
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.6310063004493713,
      "learning_rate": 8.98518849584416e-05,
      "loss": 0.8713,
      "step": 2640
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.6647841334342957,
      "learning_rate": 8.915945612231214e-05,
      "loss": 0.9242,
      "step": 2650
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.7702280879020691,
      "learning_rate": 8.846755283235874e-05,
      "loss": 1.0557,
      "step": 2660
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.0556683540344238,
      "learning_rate": 8.777620863183657e-05,
      "loss": 1.1401,
      "step": 2670
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.651453971862793,
      "learning_rate": 8.708545703689613e-05,
      "loss": 1.0147,
      "step": 2680
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.6781310439109802,
      "learning_rate": 8.639533153495867e-05,
      "loss": 0.9664,
      "step": 2690
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.6900728344917297,
      "learning_rate": 8.57058655830927e-05,
      "loss": 0.9194,
      "step": 2700
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.7449643015861511,
      "learning_rate": 8.501709260639186e-05,
      "loss": 1.0693,
      "step": 2710
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.9307679533958435,
      "learning_rate": 8.432904599635459e-05,
      "loss": 1.0927,
      "step": 2720
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.6419615745544434,
      "learning_rate": 8.364175910926528e-05,
      "loss": 0.9482,
      "step": 2730
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.6502748727798462,
      "learning_rate": 8.295526526457732e-05,
      "loss": 0.9289,
      "step": 2740
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.683403491973877,
      "learning_rate": 8.226959774329747e-05,
      "loss": 0.9169,
      "step": 2750
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.7855057716369629,
      "learning_rate": 8.158478978637269e-05,
      "loss": 1.0693,
      "step": 2760
    },
    {
      "epoch": 1.17,
      "grad_norm": 1.0051300525665283,
      "learning_rate": 8.090087459307854e-05,
      "loss": 1.17,
      "step": 2770
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.704396665096283,
      "learning_rate": 8.021788531940967e-05,
      "loss": 1.0218,
      "step": 2780
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.6089404821395874,
      "learning_rate": 7.953585507647239e-05,
      "loss": 1.0019,
      "step": 2790
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.7013250589370728,
      "learning_rate": 7.885481692887947e-05,
      "loss": 0.8923,
      "step": 2800
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.7909386157989502,
      "learning_rate": 7.817480389314738e-05,
      "loss": 0.9581,
      "step": 2810
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.9857104420661926,
      "learning_rate": 7.749584893609532e-05,
      "loss": 1.0834,
      "step": 2820
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.6876636147499084,
      "learning_rate": 7.681798497324716e-05,
      "loss": 1.033,
      "step": 2830
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.6592469811439514,
      "learning_rate": 7.614124486723588e-05,
      "loss": 0.9588,
      "step": 2840
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.725791871547699,
      "learning_rate": 7.54656614262101e-05,
      "loss": 0.9681,
      "step": 2850
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.7910930514335632,
      "learning_rate": 7.47912674022437e-05,
      "loss": 1.073,
      "step": 2860
    },
    {
      "epoch": 1.21,
      "grad_norm": 1.0530593395233154,
      "learning_rate": 7.411809548974792e-05,
      "loss": 1.127,
      "step": 2870
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.7734891176223755,
      "learning_rate": 7.344617832388662e-05,
      "loss": 0.948,
      "step": 2880
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.6848577260971069,
      "learning_rate": 7.277554847899378e-05,
      "loss": 0.9217,
      "step": 2890
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.7144964933395386,
      "learning_rate": 7.210623846699445e-05,
      "loss": 0.9335,
      "step": 2900
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.7606580257415771,
      "learning_rate": 7.14382807358287e-05,
      "loss": 1.0414,
      "step": 2910
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.9773916602134705,
      "learning_rate": 7.077170766787835e-05,
      "loss": 1.1292,
      "step": 2920
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.6572744846343994,
      "learning_rate": 7.010655157839726e-05,
      "loss": 0.9491,
      "step": 2930
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.705321192741394,
      "learning_rate": 6.944284471394452e-05,
      "loss": 0.9468,
      "step": 2940
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.7025087475776672,
      "learning_rate": 6.878061925082137e-05,
      "loss": 0.9031,
      "step": 2950
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.7313035726547241,
      "learning_rate": 6.811990729351109e-05,
      "loss": 1.004,
      "step": 2960
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.1327190399169922,
      "learning_rate": 6.746074087312262e-05,
      "loss": 1.0948,
      "step": 2970
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.6862003207206726,
      "learning_rate": 6.680315194583794e-05,
      "loss": 0.9841,
      "step": 2980
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.65215003490448,
      "learning_rate": 6.614717239136246e-05,
      "loss": 0.8705,
      "step": 2990
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.7134726047515869,
      "learning_rate": 6.549283401137982e-05,
      "loss": 0.9343,
      "step": 3000
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.8117490410804749,
      "learning_rate": 6.484016852800993e-05,
      "loss": 1.017,
      "step": 3010
    },
    {
      "epoch": 1.27,
      "grad_norm": 1.1070729494094849,
      "learning_rate": 6.418920758227135e-05,
      "loss": 1.1044,
      "step": 3020
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.6767369508743286,
      "learning_rate": 6.353998273254706e-05,
      "loss": 0.9423,
      "step": 3030
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.6971580386161804,
      "learning_rate": 6.28925254530547e-05,
      "loss": 0.9172,
      "step": 3040
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.7322612404823303,
      "learning_rate": 6.224686713232059e-05,
      "loss": 0.9127,
      "step": 3050
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.7999578714370728,
      "learning_rate": 6.160303907165822e-05,
      "loss": 1.0778,
      "step": 3060
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.9508334398269653,
      "learning_rate": 6.0961072483650526e-05,
      "loss": 1.028,
      "step": 3070
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.6923615336418152,
      "learning_rate": 6.0320998490636884e-05,
      "loss": 0.9482,
      "step": 3080
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.6519889831542969,
      "learning_rate": 5.9682848123204305e-05,
      "loss": 0.8825,
      "step": 3090
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.6621166467666626,
      "learning_rate": 5.904665231868294e-05,
      "loss": 0.9616,
      "step": 3100
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.8509411215782166,
      "learning_rate": 5.841244191964637e-05,
      "loss": 1.0519,
      "step": 3110
    },
    {
      "epoch": 1.31,
      "grad_norm": 1.0802364349365234,
      "learning_rate": 5.778024767241632e-05,
      "loss": 1.0827,
      "step": 3120
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.679560661315918,
      "learning_rate": 5.71501002255722e-05,
      "loss": 0.9085,
      "step": 3130
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.6764241456985474,
      "learning_rate": 5.652203012846513e-05,
      "loss": 0.8935,
      "step": 3140
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.7432907223701477,
      "learning_rate": 5.589606782973683e-05,
      "loss": 0.948,
      "step": 3150
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.8105322122573853,
      "learning_rate": 5.5272243675843896e-05,
      "loss": 1.0448,
      "step": 3160
    },
    {
      "epoch": 1.33,
      "grad_norm": 1.0853699445724487,
      "learning_rate": 5.4650587909586025e-05,
      "loss": 1.1097,
      "step": 3170
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.6888929009437561,
      "learning_rate": 5.4031130668640376e-05,
      "loss": 0.9453,
      "step": 3180
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.6341966986656189,
      "learning_rate": 5.341390198410019e-05,
      "loss": 0.8856,
      "step": 3190
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.6854045391082764,
      "learning_rate": 5.2798931779019026e-05,
      "loss": 0.8839,
      "step": 3200
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.8016719222068787,
      "learning_rate": 5.21862498669601e-05,
      "loss": 1.0946,
      "step": 3210
    },
    {
      "epoch": 1.36,
      "grad_norm": 1.1072624921798706,
      "learning_rate": 5.157588595055073e-05,
      "loss": 1.0541,
      "step": 3220
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.6596867442131042,
      "learning_rate": 5.0967869620042794e-05,
      "loss": 0.9648,
      "step": 3230
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.6851956844329834,
      "learning_rate": 5.0362230351877706e-05,
      "loss": 0.8897,
      "step": 3240
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.7606251835823059,
      "learning_rate": 4.9758997507257763e-05,
      "loss": 0.8958,
      "step": 3250
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.7487627267837524,
      "learning_rate": 4.915820033072257e-05,
      "loss": 0.9596,
      "step": 3260
    },
    {
      "epoch": 1.38,
      "grad_norm": 1.0656851530075073,
      "learning_rate": 4.855986794873132e-05,
      "loss": 1.1342,
      "step": 3270
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.6128414273262024,
      "learning_rate": 4.796402936825074e-05,
      "loss": 0.9758,
      "step": 3280
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.6946419477462769,
      "learning_rate": 4.737071347534873e-05,
      "loss": 0.8761,
      "step": 3290
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.6466770172119141,
      "learning_rate": 4.677994903379432e-05,
      "loss": 0.9176,
      "step": 3300
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.8571310043334961,
      "learning_rate": 4.6191764683662744e-05,
      "loss": 1.0479,
      "step": 3310
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.091630220413208,
      "learning_rate": 4.560618893994735e-05,
      "loss": 1.1288,
      "step": 3320
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.599025309085846,
      "learning_rate": 4.5023250191176925e-05,
      "loss": 0.9917,
      "step": 3330
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.6568591594696045,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.8653,
      "step": 3340
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.7494246959686279,
      "learning_rate": 4.38653965920133e-05,
      "loss": 1.0219,
      "step": 3350
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.8404898643493652,
      "learning_rate": 4.3290537874000284e-05,
      "loss": 1.0938,
      "step": 3360
    },
    {
      "epoch": 1.42,
      "grad_norm": 1.154548168182373,
      "learning_rate": 4.271842841297169e-05,
      "loss": 1.0831,
      "step": 3370
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.7497602701187134,
      "learning_rate": 4.214909594461511e-05,
      "loss": 0.9233,
      "step": 3380
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.616992712020874,
      "learning_rate": 4.158256806999059e-05,
      "loss": 0.8713,
      "step": 3390
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.7367027401924133,
      "learning_rate": 4.1018872254192166e-05,
      "loss": 0.9085,
      "step": 3400
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.9179362654685974,
      "learning_rate": 4.0458035825016806e-05,
      "loss": 1.0192,
      "step": 3410
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.1351600885391235,
      "learning_rate": 3.9900085971639036e-05,
      "loss": 1.025,
      "step": 3420
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.7443174719810486,
      "learning_rate": 3.934504974329326e-05,
      "loss": 0.9504,
      "step": 3430
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.6519255638122559,
      "learning_rate": 3.879295404796222e-05,
      "loss": 0.821,
      "step": 3440
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.7432305216789246,
      "learning_rate": 3.824382565107249e-05,
      "loss": 0.9678,
      "step": 3450
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.8053915500640869,
      "learning_rate": 3.769769117419703e-05,
      "loss": 0.9972,
      "step": 3460
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.1109815835952759,
      "learning_rate": 3.7154577093764334e-05,
      "loss": 1.1064,
      "step": 3470
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.7476344108581543,
      "learning_rate": 3.661450973977526e-05,
      "loss": 0.9627,
      "step": 3480
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.7136977314949036,
      "learning_rate": 3.607751529452609e-05,
      "loss": 0.9483,
      "step": 3490
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.724554181098938,
      "learning_rate": 3.554361979133959e-05,
      "loss": 0.9112,
      "step": 3500
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.7963750958442688,
      "learning_rate": 3.501284911330274e-05,
      "loss": 1.0281,
      "step": 3510
    },
    {
      "epoch": 1.48,
      "grad_norm": 1.048077940940857,
      "learning_rate": 3.448522899201198e-05,
      "loss": 1.0543,
      "step": 3520
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.6887779235839844,
      "learning_rate": 3.396078500632576e-05,
      "loss": 0.9685,
      "step": 3530
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.6389910578727722,
      "learning_rate": 3.3439542581124374e-05,
      "loss": 0.9018,
      "step": 3540
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.8143815994262695,
      "learning_rate": 3.292152698607768e-05,
      "loss": 0.9103,
      "step": 3550
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.8993640542030334,
      "learning_rate": 3.240676333441955e-05,
      "loss": 1.0309,
      "step": 3560
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.1748642921447754,
      "learning_rate": 3.189527658173087e-05,
      "loss": 1.1086,
      "step": 3570
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.6727201342582703,
      "learning_rate": 3.138709152472938e-05,
      "loss": 0.9665,
      "step": 3580
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.6939325332641602,
      "learning_rate": 3.088223280006769e-05,
      "loss": 0.8796,
      "step": 3590
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.8073004484176636,
      "learning_rate": 3.0380724883138856e-05,
      "loss": 0.8609,
      "step": 3600
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.8646635413169861,
      "learning_rate": 2.9882592086889736e-05,
      "loss": 1.0229,
      "step": 3610
    },
    {
      "epoch": 1.52,
      "grad_norm": 1.1847567558288574,
      "learning_rate": 2.93878585606426e-05,
      "loss": 1.033,
      "step": 3620
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.6628533601760864,
      "learning_rate": 2.889654828892393e-05,
      "loss": 0.9475,
      "step": 3630
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.7180255651473999,
      "learning_rate": 2.8408685090302044e-05,
      "loss": 0.7856,
      "step": 3640
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.7089993953704834,
      "learning_rate": 2.7924292616232218e-05,
      "loss": 0.9597,
      "step": 3650
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.8458394408226013,
      "learning_rate": 2.7443394349910045e-05,
      "loss": 1.0683,
      "step": 3660
    },
    {
      "epoch": 1.55,
      "grad_norm": 1.1439454555511475,
      "learning_rate": 2.6966013605133088e-05,
      "loss": 1.088,
      "step": 3670
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.6164907813072205,
      "learning_rate": 2.649217352517044e-05,
      "loss": 0.9503,
      "step": 3680
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.7188657522201538,
      "learning_rate": 2.6021897081641055e-05,
      "loss": 0.8759,
      "step": 3690
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.7899062633514404,
      "learning_rate": 2.5555207073399733e-05,
      "loss": 0.9169,
      "step": 3700
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.8519218564033508,
      "learning_rate": 2.5092126125432136e-05,
      "loss": 1.0466,
      "step": 3710
    },
    {
      "epoch": 1.57,
      "grad_norm": 1.1700925827026367,
      "learning_rate": 2.463267668775767e-05,
      "loss": 1.1155,
      "step": 3720
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.6643344759941101,
      "learning_rate": 2.417688103434146e-05,
      "loss": 0.9251,
      "step": 3730
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.6496443748474121,
      "learning_rate": 2.3724761262014182e-05,
      "loss": 0.8856,
      "step": 3740
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.6989282965660095,
      "learning_rate": 2.3276339289400895e-05,
      "loss": 0.94,
      "step": 3750
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.9367401599884033,
      "learning_rate": 2.2831636855858663e-05,
      "loss": 1.0337,
      "step": 3760
    },
    {
      "epoch": 1.59,
      "grad_norm": 1.117208480834961,
      "learning_rate": 2.2390675520422278e-05,
      "loss": 1.0989,
      "step": 3770
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.6940779685974121,
      "learning_rate": 2.1953476660759398e-05,
      "loss": 0.9401,
      "step": 3780
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.7155762910842896,
      "learning_rate": 2.1520061472133902e-05,
      "loss": 0.9211,
      "step": 3790
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.7470029592514038,
      "learning_rate": 2.109045096637865e-05,
      "loss": 0.9259,
      "step": 3800
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.9242197871208191,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 1.0221,
      "step": 3810
    },
    {
      "epoch": 1.61,
      "grad_norm": 1.1893744468688965,
      "learning_rate": 2.0242727127550865e-05,
      "loss": 1.0464,
      "step": 3820
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.6893196702003479,
      "learning_rate": 1.982465489186489e-05,
      "loss": 0.9307,
      "step": 3830
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.7716548442840576,
      "learning_rate": 1.9410469531829777e-05,
      "loss": 0.8919,
      "step": 3840
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.6742382645606995,
      "learning_rate": 1.9000191127022237e-05,
      "loss": 0.8667,
      "step": 3850
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.8534088134765625,
      "learning_rate": 1.8593839567610928e-05,
      "loss": 1.0633,
      "step": 3860
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.9838773608207703,
      "learning_rate": 1.8191434553392428e-05,
      "loss": 1.1161,
      "step": 3870
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.6817989945411682,
      "learning_rate": 1.779299559283588e-05,
      "loss": 0.8697,
      "step": 3880
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.63358473777771,
      "learning_rate": 1.7398542002137475e-05,
      "loss": 0.8897,
      "step": 3890
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.7668142318725586,
      "learning_rate": 1.7008092904283913e-05,
      "loss": 0.8808,
      "step": 3900
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.833977222442627,
      "learning_rate": 1.6621667228125302e-05,
      "loss": 1.0321,
      "step": 3910
    },
    {
      "epoch": 1.65,
      "grad_norm": 1.2148581743240356,
      "learning_rate": 1.6239283707457576e-05,
      "loss": 1.0653,
      "step": 3920
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.6781288385391235,
      "learning_rate": 1.586096088011414e-05,
      "loss": 0.9533,
      "step": 3930
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.7431279420852661,
      "learning_rate": 1.5486717087067393e-05,
      "loss": 0.8971,
      "step": 3940
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.7349860668182373,
      "learning_rate": 1.5116570471539293e-05,
      "loss": 0.8705,
      "step": 3950
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.8228428363800049,
      "learning_rate": 1.4750538978121987e-05,
      "loss": 1.075,
      "step": 3960
    },
    {
      "epoch": 1.67,
      "grad_norm": 1.0865501165390015,
      "learning_rate": 1.4388640351907801e-05,
      "loss": 1.085,
      "step": 3970
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.698239803314209,
      "learning_rate": 1.4030892137628905e-05,
      "loss": 0.9638,
      "step": 3980
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.728515625,
      "learning_rate": 1.3677311678806838e-05,
      "loss": 0.8978,
      "step": 3990
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.7482006549835205,
      "learning_rate": 1.33279161169116e-05,
      "loss": 0.971,
      "step": 4000
    },
    {
      "epoch": 1.68,
      "eval_loss": 1.0210562944412231,
      "eval_runtime": 228.9321,
      "eval_samples_per_second": 4.368,
      "eval_steps_per_second": 0.546,
      "step": 4000
    }
  ],
  "logging_steps": 10,
  "max_steps": 4750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2000,
  "total_flos": 4.027274639002829e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}