{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 500.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.5,
      "grad_norm": 8.514540942565027,
      "learning_rate": 5e-06,
      "loss": 0.585,
      "step": 5
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.9267725944427414,
      "learning_rate": 1e-05,
      "loss": 0.4444,
      "step": 10
    },
    {
      "epoch": 7.5,
      "grad_norm": 1.359630389285586,
      "learning_rate": 1.5e-05,
      "loss": 0.1918,
      "step": 15
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.8675984069699776,
      "learning_rate": 2e-05,
      "loss": 0.0255,
      "step": 20
    },
    {
      "epoch": 12.5,
      "grad_norm": 1.3166063968433408,
      "learning_rate": 2.5e-05,
      "loss": 0.0094,
      "step": 25
    },
    {
      "epoch": 15.0,
      "grad_norm": 1.4298321029000574,
      "learning_rate": 3e-05,
      "loss": 0.0066,
      "step": 30
    },
    {
      "epoch": 17.5,
      "grad_norm": 0.39016346214571596,
      "learning_rate": 3.5e-05,
      "loss": 0.0054,
      "step": 35
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.2790201303316679,
      "learning_rate": 4e-05,
      "loss": 0.0062,
      "step": 40
    },
    {
      "epoch": 22.5,
      "grad_norm": 0.08501619599523778,
      "learning_rate": 4.5e-05,
      "loss": 0.004,
      "step": 45
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.062067934755517584,
      "learning_rate": 5e-05,
      "loss": 0.0029,
      "step": 50
    },
    {
      "epoch": 27.5,
      "grad_norm": 0.052666305930186126,
      "learning_rate": 4.9996924362330555e-05,
      "loss": 0.0028,
      "step": 55
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.03938136111188392,
      "learning_rate": 4.998769829017084e-05,
      "loss": 0.0028,
      "step": 60
    },
    {
      "epoch": 32.5,
      "grad_norm": 0.03394672644933696,
      "learning_rate": 4.997232430583686e-05,
      "loss": 0.0028,
      "step": 65
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.037661243334742,
      "learning_rate": 4.995080661242243e-05,
      "loss": 0.0028,
      "step": 70
    },
    {
      "epoch": 37.5,
      "grad_norm": 0.039184906370568255,
      "learning_rate": 4.992315109265007e-05,
      "loss": 0.0027,
      "step": 75
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.04435589843124744,
      "learning_rate": 4.988936530726276e-05,
      "loss": 0.0028,
      "step": 80
    },
    {
      "epoch": 42.5,
      "grad_norm": 0.02657151726999846,
      "learning_rate": 4.984945849295686e-05,
      "loss": 0.0026,
      "step": 85
    },
    {
      "epoch": 45.0,
      "grad_norm": 0.03472385835097059,
      "learning_rate": 4.980344155985695e-05,
      "loss": 0.0027,
      "step": 90
    },
    {
      "epoch": 47.5,
      "grad_norm": 0.031070975559645563,
      "learning_rate": 4.975132708853304e-05,
      "loss": 0.0026,
      "step": 95
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.03730805984645713,
      "learning_rate": 4.9693129326561254e-05,
      "loss": 0.0027,
      "step": 100
    },
    {
      "epoch": 52.5,
      "grad_norm": 0.030401417138752773,
      "learning_rate": 4.96288641846286e-05,
      "loss": 0.0027,
      "step": 105
    },
    {
      "epoch": 55.0,
      "grad_norm": 0.030056720425659458,
      "learning_rate": 4.955854923218321e-05,
      "loss": 0.0027,
      "step": 110
    },
    {
      "epoch": 57.5,
      "grad_norm": 0.02714242610959012,
      "learning_rate": 4.948220369263099e-05,
      "loss": 0.0025,
      "step": 115
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.021468304046160087,
      "learning_rate": 4.939984843808013e-05,
      "loss": 0.0026,
      "step": 120
    },
    {
      "epoch": 62.5,
      "grad_norm": 0.027579476441235425,
      "learning_rate": 4.931150598363494e-05,
      "loss": 0.0027,
      "step": 125
    },
    {
      "epoch": 65.0,
      "grad_norm": 0.041471384473431336,
      "learning_rate": 4.921720048124035e-05,
      "loss": 0.0028,
      "step": 130
    },
    {
      "epoch": 67.5,
      "grad_norm": 0.030743428074535287,
      "learning_rate": 4.9116957713079084e-05,
      "loss": 0.0027,
      "step": 135
    },
    {
      "epoch": 70.0,
      "grad_norm": 0.03200739761669791,
      "learning_rate": 4.901080508452305e-05,
      "loss": 0.0027,
      "step": 140
    },
    {
      "epoch": 72.5,
      "grad_norm": 0.02266656589663142,
      "learning_rate": 4.889877161664096e-05,
      "loss": 0.0027,
      "step": 145
    },
    {
      "epoch": 75.0,
      "grad_norm": 0.03858968870626217,
      "learning_rate": 4.878088793826428e-05,
      "loss": 0.0026,
      "step": 150
    },
    {
      "epoch": 77.5,
      "grad_norm": 0.0436229252420695,
      "learning_rate": 4.865718627761363e-05,
      "loss": 0.0027,
      "step": 155
    },
    {
      "epoch": 80.0,
      "grad_norm": 0.021505547895787954,
      "learning_rate": 4.8527700453487873e-05,
      "loss": 0.0026,
      "step": 160
    },
    {
      "epoch": 82.5,
      "grad_norm": 0.020985544413640905,
      "learning_rate": 4.839246586601841e-05,
      "loss": 0.0027,
      "step": 165
    },
    {
      "epoch": 85.0,
      "grad_norm": 0.023894609006279273,
      "learning_rate": 4.825151948699116e-05,
      "loss": 0.0028,
      "step": 170
    },
    {
      "epoch": 87.5,
      "grad_norm": 0.02603189523521318,
      "learning_rate": 4.8104899849738795e-05,
      "loss": 0.0026,
      "step": 175
    },
    {
      "epoch": 90.0,
      "grad_norm": 0.033072587670050196,
      "learning_rate": 4.795264703860616e-05,
      "loss": 0.0027,
      "step": 180
    },
    {
      "epoch": 92.5,
      "grad_norm": 0.029455707311945873,
      "learning_rate": 4.779480267799158e-05,
      "loss": 0.0027,
      "step": 185
    },
    {
      "epoch": 95.0,
      "grad_norm": 0.031066744462249135,
      "learning_rate": 4.763140992096718e-05,
      "loss": 0.0027,
      "step": 190
    },
    {
      "epoch": 97.5,
      "grad_norm": 0.03179467575788789,
      "learning_rate": 4.7462513437481266e-05,
      "loss": 0.0027,
      "step": 195
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.04391757622955937,
      "learning_rate": 4.7288159402146e-05,
      "loss": 0.0027,
      "step": 200
    },
    {
      "epoch": 102.5,
      "grad_norm": 0.029394885252518814,
      "learning_rate": 4.7108395481613736e-05,
      "loss": 0.0028,
      "step": 205
    },
    {
      "epoch": 105.0,
      "grad_norm": 0.027320800240786685,
      "learning_rate": 4.692327082154542e-05,
      "loss": 0.0027,
      "step": 210
    },
    {
      "epoch": 107.5,
      "grad_norm": 0.030873484414188097,
      "learning_rate": 4.6732836033174634e-05,
      "loss": 0.0027,
      "step": 215
    },
    {
      "epoch": 110.0,
      "grad_norm": 0.048697733723929194,
      "learning_rate": 4.653714317947105e-05,
      "loss": 0.0027,
      "step": 220
    },
    {
      "epoch": 112.5,
      "grad_norm": 0.025217762723189756,
      "learning_rate": 4.6336245760906896e-05,
      "loss": 0.0026,
      "step": 225
    },
    {
      "epoch": 115.0,
      "grad_norm": 0.034325242650264584,
      "learning_rate": 4.6130198700830455e-05,
      "loss": 0.0027,
      "step": 230
    },
    {
      "epoch": 117.5,
      "grad_norm": 0.0392844047749773,
      "learning_rate": 4.591905833045059e-05,
      "loss": 0.0027,
      "step": 235
    },
    {
      "epoch": 120.0,
      "grad_norm": 0.02965200107252582,
      "learning_rate": 4.570288237343632e-05,
      "loss": 0.0026,
      "step": 240
    },
    {
      "epoch": 122.5,
      "grad_norm": 0.020210067730727373,
      "learning_rate": 4.5481729930135805e-05,
      "loss": 0.0026,
      "step": 245
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.027623657423726022,
      "learning_rate": 4.5255661461418854e-05,
      "loss": 0.0026,
      "step": 250
    },
    {
      "epoch": 127.5,
      "grad_norm": 0.023255879069235798,
      "learning_rate": 4.502473877214754e-05,
      "loss": 0.0027,
      "step": 255
    },
    {
      "epoch": 130.0,
      "grad_norm": 0.014768241964023569,
      "learning_rate": 4.478902499427933e-05,
      "loss": 0.0027,
      "step": 260
    },
    {
      "epoch": 132.5,
      "grad_norm": 0.03668790355624439,
      "learning_rate": 4.454858456960754e-05,
      "loss": 0.0027,
      "step": 265
    },
    {
      "epoch": 135.0,
      "grad_norm": 0.028968111779672595,
      "learning_rate": 4.430348323214347e-05,
      "loss": 0.0026,
      "step": 270
    },
    {
      "epoch": 137.5,
      "grad_norm": 0.02287695653834384,
      "learning_rate": 4.4053787990145465e-05,
      "loss": 0.0027,
      "step": 275
    },
    {
      "epoch": 140.0,
      "grad_norm": 0.014260556347040123,
      "learning_rate": 4.379956710779951e-05,
      "loss": 0.0027,
      "step": 280
    },
    {
      "epoch": 142.5,
      "grad_norm": 0.029771289364298407,
      "learning_rate": 4.3540890086556435e-05,
      "loss": 0.0026,
      "step": 285
    },
    {
      "epoch": 145.0,
      "grad_norm": 0.03788961751665883,
      "learning_rate": 4.327782764613099e-05,
      "loss": 0.0027,
      "step": 290
    },
    {
      "epoch": 147.5,
      "grad_norm": 0.03971119187487509,
      "learning_rate": 4.301045170516773e-05,
      "loss": 0.0026,
      "step": 295
    },
    {
      "epoch": 150.0,
      "grad_norm": 0.03370808514177945,
      "learning_rate": 4.2738835361579175e-05,
      "loss": 0.0026,
      "step": 300
    },
    {
      "epoch": 152.5,
      "grad_norm": 0.04042652697228835,
      "learning_rate": 4.2463052872561584e-05,
      "loss": 0.0027,
      "step": 305
    },
    {
      "epoch": 155.0,
      "grad_norm": 0.03521656241677526,
      "learning_rate": 4.2183179634293794e-05,
      "loss": 0.0028,
      "step": 310
    },
    {
      "epoch": 157.5,
      "grad_norm": 0.03092781528226213,
      "learning_rate": 4.1899292161324627e-05,
      "loss": 0.0026,
      "step": 315
    },
    {
      "epoch": 160.0,
      "grad_norm": 0.020310997173564212,
      "learning_rate": 4.1611468065654586e-05,
      "loss": 0.0026,
      "step": 320
    },
    {
      "epoch": 162.5,
      "grad_norm": 0.015790567180341695,
      "learning_rate": 4.1319786035517534e-05,
      "loss": 0.0027,
      "step": 325
    },
    {
      "epoch": 165.0,
      "grad_norm": 0.0194147951616345,
      "learning_rate": 4.1024325813868065e-05,
      "loss": 0.0027,
      "step": 330
    },
    {
      "epoch": 167.5,
      "grad_norm": 0.030730482667734805,
      "learning_rate": 4.072516817658065e-05,
      "loss": 0.0027,
      "step": 335
    },
    {
      "epoch": 170.0,
      "grad_norm": 0.029837731953442564,
      "learning_rate": 4.0422394910366236e-05,
      "loss": 0.0026,
      "step": 340
    },
    {
      "epoch": 172.5,
      "grad_norm": 0.02492166177013941,
      "learning_rate": 4.0116088790412645e-05,
      "loss": 0.0026,
      "step": 345
    },
    {
      "epoch": 175.0,
      "grad_norm": 0.022790129612325603,
      "learning_rate": 3.980633355775461e-05,
      "loss": 0.0027,
      "step": 350
    },
    {
      "epoch": 177.5,
      "grad_norm": 0.0367286949474086,
      "learning_rate": 3.949321389637986e-05,
      "loss": 0.0027,
      "step": 355
    },
    {
      "epoch": 180.0,
      "grad_norm": 0.026449210914021956,
      "learning_rate": 3.917681541007734e-05,
      "loss": 0.0025,
      "step": 360
    },
    {
      "epoch": 182.5,
      "grad_norm": 0.025906355217603764,
      "learning_rate": 3.885722459903399e-05,
      "loss": 0.0027,
      "step": 365
    },
    {
      "epoch": 185.0,
      "grad_norm": 0.013510506972149507,
      "learning_rate": 3.853452883618644e-05,
      "loss": 0.0027,
      "step": 370
    },
    {
      "epoch": 187.5,
      "grad_norm": 0.02126782273762181,
      "learning_rate": 3.8208816343334156e-05,
      "loss": 0.0027,
      "step": 375
    },
    {
      "epoch": 190.0,
      "grad_norm": 0.02778025887186039,
      "learning_rate": 3.788017616702048e-05,
      "loss": 0.0027,
      "step": 380
    },
    {
      "epoch": 192.5,
      "grad_norm": 0.02023158670094667,
      "learning_rate": 3.754869815418815e-05,
      "loss": 0.0026,
      "step": 385
    },
    {
      "epoch": 195.0,
      "grad_norm": 0.031240526748051056,
      "learning_rate": 3.721447292761609e-05,
      "loss": 0.0027,
      "step": 390
    },
    {
      "epoch": 197.5,
      "grad_norm": 0.02268049791605829,
      "learning_rate": 3.687759186114403e-05,
      "loss": 0.0026,
      "step": 395
    },
    {
      "epoch": 200.0,
      "grad_norm": 0.02998474683024178,
      "learning_rate": 3.6538147054691817e-05,
      "loss": 0.0027,
      "step": 400
    },
    {
      "epoch": 202.5,
      "grad_norm": 0.026430986104193692,
      "learning_rate": 3.619623130908018e-05,
      "loss": 0.0027,
      "step": 405
    },
    {
      "epoch": 205.0,
      "grad_norm": 0.010605276850508178,
      "learning_rate": 3.5851938100659964e-05,
      "loss": 0.0027,
      "step": 410
    },
    {
      "epoch": 207.5,
      "grad_norm": 0.02068209169464807,
      "learning_rate": 3.550536155575662e-05,
      "loss": 0.0027,
      "step": 415
    },
    {
      "epoch": 210.0,
      "grad_norm": 0.03300339570363238,
      "learning_rate": 3.515659642493697e-05,
      "loss": 0.0026,
      "step": 420
    },
    {
      "epoch": 212.5,
      "grad_norm": 0.026016657903437497,
      "learning_rate": 3.480573805710538e-05,
      "loss": 0.0027,
      "step": 425
    },
    {
      "epoch": 215.0,
      "grad_norm": 0.024770792616580162,
      "learning_rate": 3.4452882373436316e-05,
      "loss": 0.0026,
      "step": 430
    },
    {
      "epoch": 217.5,
      "grad_norm": 0.0265444448484458,
      "learning_rate": 3.4098125841150466e-05,
      "loss": 0.0026,
      "step": 435
    },
    {
      "epoch": 220.0,
      "grad_norm": 0.01924921498743014,
      "learning_rate": 3.37415654471415e-05,
      "loss": 0.0026,
      "step": 440
    },
    {
      "epoch": 222.5,
      "grad_norm": 0.027603952267821173,
      "learning_rate": 3.3383298671460944e-05,
      "loss": 0.0026,
      "step": 445
    },
    {
      "epoch": 225.0,
      "grad_norm": 0.0254709928199966,
      "learning_rate": 3.3023423460667985e-05,
      "loss": 0.0026,
      "step": 450
    },
    {
      "epoch": 227.5,
      "grad_norm": 0.031183288661866662,
      "learning_rate": 3.2662038201051914e-05,
      "loss": 0.0027,
      "step": 455
    },
    {
      "epoch": 230.0,
      "grad_norm": 0.03425285898227886,
      "learning_rate": 3.2299241691734304e-05,
      "loss": 0.0026,
      "step": 460
    },
    {
      "epoch": 232.5,
      "grad_norm": 0.028752151160391863,
      "learning_rate": 3.1935133117658306e-05,
      "loss": 0.0027,
      "step": 465
    },
    {
      "epoch": 235.0,
      "grad_norm": 0.028976330470022123,
      "learning_rate": 3.156981202247248e-05,
      "loss": 0.0026,
      "step": 470
    },
    {
      "epoch": 237.5,
      "grad_norm": 0.026920539664030775,
      "learning_rate": 3.1203378281316515e-05,
      "loss": 0.0026,
      "step": 475
    },
    {
      "epoch": 240.0,
      "grad_norm": 0.020989002709489214,
      "learning_rate": 3.0835932073516444e-05,
      "loss": 0.0027,
      "step": 480
    },
    {
      "epoch": 242.5,
      "grad_norm": 0.024523095658861207,
      "learning_rate": 3.0467573855196558e-05,
      "loss": 0.0027,
      "step": 485
    },
    {
      "epoch": 245.0,
      "grad_norm": 0.015580401724056997,
      "learning_rate": 3.0098404331815695e-05,
      "loss": 0.0027,
      "step": 490
    },
    {
      "epoch": 247.5,
      "grad_norm": 0.022996840296875175,
      "learning_rate": 2.9728524430635417e-05,
      "loss": 0.0027,
      "step": 495
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.021854877708908236,
      "learning_rate": 2.9358035273127483e-05,
      "loss": 0.0026,
      "step": 500
    },
    {
      "epoch": 252.5,
      "grad_norm": 0.025003129400125675,
      "learning_rate": 2.8987038147328238e-05,
      "loss": 0.0026,
      "step": 505
    },
    {
      "epoch": 255.0,
      "grad_norm": 0.02759119149124416,
      "learning_rate": 2.86156344801475e-05,
      "loss": 0.0026,
      "step": 510
    },
    {
      "epoch": 257.5,
      "grad_norm": 0.024349103530368846,
      "learning_rate": 2.824392580963944e-05,
      "loss": 0.0027,
      "step": 515
    },
    {
      "epoch": 260.0,
      "grad_norm": 0.02918200596645593,
      "learning_rate": 2.787201375724307e-05,
      "loss": 0.0027,
      "step": 520
    },
    {
      "epoch": 262.5,
      "grad_norm": 0.017661985537795705,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.0026,
      "step": 525
    },
    {
      "epoch": 265.0,
      "grad_norm": 0.02880881596677379,
      "learning_rate": 2.7127986242756936e-05,
      "loss": 0.0026,
      "step": 530
    },
    {
      "epoch": 267.5,
      "grad_norm": 0.04090166133876468,
      "learning_rate": 2.6756074190360563e-05,
      "loss": 0.0028,
      "step": 535
    },
    {
      "epoch": 270.0,
      "grad_norm": 0.022838636369005745,
      "learning_rate": 2.63843655198525e-05,
      "loss": 0.0027,
      "step": 540
    },
    {
      "epoch": 272.5,
      "grad_norm": 0.03417808915995595,
      "learning_rate": 2.6012961852671767e-05,
      "loss": 0.0026,
      "step": 545
    },
    {
      "epoch": 275.0,
      "grad_norm": 0.02391514801170413,
      "learning_rate": 2.5641964726872526e-05,
      "loss": 0.0026,
      "step": 550
    },
    {
      "epoch": 277.5,
      "grad_norm": 0.027050966559574396,
      "learning_rate": 2.527147556936459e-05,
      "loss": 0.0027,
      "step": 555
    },
    {
      "epoch": 280.0,
      "grad_norm": 0.029392338368449532,
      "learning_rate": 2.4901595668184314e-05,
      "loss": 0.0027,
      "step": 560
    },
    {
      "epoch": 282.5,
      "grad_norm": 0.03213320609449678,
      "learning_rate": 2.453242614480345e-05,
      "loss": 0.0027,
      "step": 565
    },
    {
      "epoch": 285.0,
      "grad_norm": 0.017580210273689653,
      "learning_rate": 2.416406792648355e-05,
      "loss": 0.0027,
      "step": 570
    },
    {
      "epoch": 287.5,
      "grad_norm": 0.025395175371267904,
      "learning_rate": 2.3796621718683487e-05,
      "loss": 0.0027,
      "step": 575
    },
    {
      "epoch": 290.0,
      "grad_norm": 0.02830946439085919,
      "learning_rate": 2.3430187977527533e-05,
      "loss": 0.0027,
      "step": 580
    },
    {
      "epoch": 292.5,
      "grad_norm": 0.04065072947108163,
      "learning_rate": 2.3064866882341696e-05,
      "loss": 0.0027,
      "step": 585
    },
    {
      "epoch": 295.0,
      "grad_norm": 0.028524952343665373,
      "learning_rate": 2.27007583082657e-05,
      "loss": 0.0026,
      "step": 590
    },
    {
      "epoch": 297.5,
      "grad_norm": 0.0284550999234347,
      "learning_rate": 2.233796179894809e-05,
      "loss": 0.0026,
      "step": 595
    },
    {
      "epoch": 300.0,
      "grad_norm": 0.03018543474602915,
      "learning_rate": 2.1976576539332024e-05,
      "loss": 0.0026,
      "step": 600
    },
    {
      "epoch": 302.5,
      "grad_norm": 0.017475284356752212,
      "learning_rate": 2.1616701328539057e-05,
      "loss": 0.0026,
      "step": 605
    },
    {
      "epoch": 305.0,
      "grad_norm": 0.02381743267091071,
      "learning_rate": 2.1258434552858502e-05,
      "loss": 0.0026,
      "step": 610
    },
    {
      "epoch": 307.5,
      "grad_norm": 0.030282727334382083,
      "learning_rate": 2.090187415884955e-05,
      "loss": 0.0027,
      "step": 615
    },
    {
      "epoch": 310.0,
      "grad_norm": 0.02239088576419377,
      "learning_rate": 2.054711762656369e-05,
      "loss": 0.0026,
      "step": 620
    },
    {
      "epoch": 312.5,
      "grad_norm": 0.020772310557568244,
      "learning_rate": 2.0194261942894628e-05,
      "loss": 0.0026,
      "step": 625
    },
    {
      "epoch": 315.0,
      "grad_norm": 0.03490126977201953,
      "learning_rate": 1.984340357506303e-05,
      "loss": 0.0026,
      "step": 630
    },
    {
      "epoch": 317.5,
      "grad_norm": 0.015968447976387346,
      "learning_rate": 1.949463844424338e-05,
      "loss": 0.0026,
      "step": 635
    },
    {
      "epoch": 320.0,
      "grad_norm": 0.023986554939275363,
      "learning_rate": 1.914806189934003e-05,
      "loss": 0.0028,
      "step": 640
    },
    {
      "epoch": 322.5,
      "grad_norm": 0.03420061182554338,
      "learning_rate": 1.8803768690919832e-05,
      "loss": 0.0027,
      "step": 645
    },
    {
      "epoch": 325.0,
      "grad_norm": 0.01792951575408546,
      "learning_rate": 1.8461852945308196e-05,
      "loss": 0.0027,
      "step": 650
    },
    {
      "epoch": 327.5,
      "grad_norm": 0.023802622532695907,
      "learning_rate": 1.8122408138855974e-05,
      "loss": 0.0026,
      "step": 655
    },
    {
      "epoch": 330.0,
      "grad_norm": 0.023316524889500846,
      "learning_rate": 1.778552707238391e-05,
      "loss": 0.0026,
      "step": 660
    },
    {
      "epoch": 332.5,
      "grad_norm": 0.013376585581553524,
      "learning_rate": 1.7451301845811857e-05,
      "loss": 0.0026,
      "step": 665
    },
    {
      "epoch": 335.0,
      "grad_norm": 0.019080334175566694,
      "learning_rate": 1.711982383297953e-05,
      "loss": 0.0026,
      "step": 670
    },
    {
      "epoch": 337.5,
      "grad_norm": 0.01654436855407368,
      "learning_rate": 1.6791183656665846e-05,
      "loss": 0.0026,
      "step": 675
    },
    {
      "epoch": 340.0,
      "grad_norm": 0.022278657387787754,
      "learning_rate": 1.6465471163813574e-05,
      "loss": 0.0027,
      "step": 680
    },
    {
      "epoch": 342.5,
      "grad_norm": 0.015375948509190046,
      "learning_rate": 1.6142775400966023e-05,
      "loss": 0.0027,
      "step": 685
    },
    {
      "epoch": 345.0,
      "grad_norm": 0.01684675867751184,
      "learning_rate": 1.582318458992267e-05,
      "loss": 0.0027,
      "step": 690
    },
    {
      "epoch": 347.5,
      "grad_norm": 0.032002543536054376,
      "learning_rate": 1.5506786103620146e-05,
      "loss": 0.0027,
      "step": 695
    },
    {
      "epoch": 350.0,
      "grad_norm": 0.021043035856906086,
      "learning_rate": 1.5193666442245402e-05,
      "loss": 0.0027,
      "step": 700
    },
    {
      "epoch": 352.5,
      "grad_norm": 0.01601931955071107,
      "learning_rate": 1.4883911209587368e-05,
      "loss": 0.0026,
      "step": 705
    },
    {
      "epoch": 355.0,
      "grad_norm": 0.02601502051924795,
      "learning_rate": 1.4577605089633773e-05,
      "loss": 0.0026,
      "step": 710
    },
    {
      "epoch": 357.5,
      "grad_norm": 0.02710347701415514,
      "learning_rate": 1.427483182341936e-05,
      "loss": 0.0026,
      "step": 715
    },
    {
      "epoch": 360.0,
      "grad_norm": 0.03320644743977735,
      "learning_rate": 1.3975674186131937e-05,
      "loss": 0.0027,
      "step": 720
    },
    {
      "epoch": 362.5,
      "grad_norm": 0.01591474795789328,
      "learning_rate": 1.3680213964482475e-05,
      "loss": 0.0027,
      "step": 725
    },
    {
      "epoch": 365.0,
      "grad_norm": 0.026155373607272086,
      "learning_rate": 1.3388531934345416e-05,
      "loss": 0.0027,
      "step": 730
    },
    {
      "epoch": 367.5,
      "grad_norm": 0.024271143128982743,
      "learning_rate": 1.3100707838675377e-05,
      "loss": 0.0026,
      "step": 735
    },
    {
      "epoch": 370.0,
      "grad_norm": 0.016369678310535946,
      "learning_rate": 1.2816820365706206e-05,
      "loss": 0.0027,
      "step": 740
    },
    {
      "epoch": 372.5,
      "grad_norm": 0.016955558044549856,
      "learning_rate": 1.2536947127438415e-05,
      "loss": 0.0026,
      "step": 745
    },
    {
      "epoch": 375.0,
      "grad_norm": 0.02239783849742695,
      "learning_rate": 1.2261164638420832e-05,
      "loss": 0.0026,
      "step": 750
    },
    {
      "epoch": 377.5,
      "grad_norm": 0.029924950679270815,
      "learning_rate": 1.198954829483227e-05,
      "loss": 0.0027,
      "step": 755
    },
    {
      "epoch": 380.0,
      "grad_norm": 0.028621427234193805,
      "learning_rate": 1.1722172353869008e-05,
      "loss": 0.0025,
      "step": 760
    },
    {
      "epoch": 382.5,
      "grad_norm": 0.02561136953891063,
      "learning_rate": 1.1459109913443567e-05,
      "loss": 0.0026,
      "step": 765
    },
    {
      "epoch": 385.0,
      "grad_norm": 0.028256041486332584,
      "learning_rate": 1.12004328922005e-05,
      "loss": 0.0027,
      "step": 770
    },
    {
      "epoch": 387.5,
      "grad_norm": 0.029729889846126924,
      "learning_rate": 1.094621200985454e-05,
      "loss": 0.0027,
      "step": 775
    },
    {
      "epoch": 390.0,
      "grad_norm": 0.014383243995550028,
      "learning_rate": 1.0696516767856546e-05,
      "loss": 0.0026,
      "step": 780
    },
    {
      "epoch": 392.5,
      "grad_norm": 0.015879736540587025,
      "learning_rate": 1.0451415430392474e-05,
      "loss": 0.0026,
      "step": 785
    },
    {
      "epoch": 395.0,
      "grad_norm": 0.024629301532455877,
      "learning_rate": 1.0210975005720677e-05,
      "loss": 0.0026,
      "step": 790
    },
    {
      "epoch": 397.5,
      "grad_norm": 0.029707059150893382,
      "learning_rate": 9.975261227852472e-06,
      "loss": 0.0027,
      "step": 795
    },
    {
      "epoch": 400.0,
      "grad_norm": 0.0318537391592188,
      "learning_rate": 9.744338538581147e-06,
      "loss": 0.0027,
      "step": 800
    },
    {
      "epoch": 402.5,
      "grad_norm": 0.017706015342844352,
      "learning_rate": 9.518270069864195e-06,
      "loss": 0.0027,
      "step": 805
    },
    {
      "epoch": 405.0,
      "grad_norm": 0.01724610650030409,
      "learning_rate": 9.297117626563687e-06,
      "loss": 0.0026,
      "step": 810
    },
    {
      "epoch": 407.5,
      "grad_norm": 0.018957851028085164,
      "learning_rate": 9.080941669549423e-06,
      "loss": 0.0026,
      "step": 815
    },
    {
      "epoch": 410.0,
      "grad_norm": 0.025418915769378568,
      "learning_rate": 8.86980129916955e-06,
      "loss": 0.0026,
      "step": 820
    },
    {
      "epoch": 412.5,
      "grad_norm": 0.01583223922193541,
      "learning_rate": 8.663754239093109e-06,
      "loss": 0.0027,
      "step": 825
    },
    {
      "epoch": 415.0,
      "grad_norm": 0.027164074218547888,
      "learning_rate": 8.462856820528952e-06,
      "loss": 0.0026,
      "step": 830
    },
    {
      "epoch": 417.5,
      "grad_norm": 0.028647280916262126,
      "learning_rate": 8.26716396682537e-06,
      "loss": 0.0027,
      "step": 835
    },
    {
      "epoch": 420.0,
      "grad_norm": 0.019553123738546497,
      "learning_rate": 8.076729178454588e-06,
      "loss": 0.0026,
      "step": 840
    },
    {
      "epoch": 422.5,
      "grad_norm": 0.025379025955769637,
      "learning_rate": 7.89160451838626e-06,
      "loss": 0.0027,
      "step": 845
    },
    {
      "epoch": 425.0,
      "grad_norm": 0.01750943138582632,
      "learning_rate": 7.711840597853998e-06,
      "loss": 0.0026,
      "step": 850
    },
    {
      "epoch": 427.5,
      "grad_norm": 0.02520822601658372,
      "learning_rate": 7.537486562518735e-06,
      "loss": 0.0026,
      "step": 855
    },
    {
      "epoch": 430.0,
      "grad_norm": 0.01993484997782361,
      "learning_rate": 7.368590079032822e-06,
      "loss": 0.0026,
      "step": 860
    },
    {
      "epoch": 432.5,
      "grad_norm": 0.019158523070010834,
      "learning_rate": 7.205197322008425e-06,
      "loss": 0.0027,
      "step": 865
    },
    {
      "epoch": 435.0,
      "grad_norm": 0.015239850907125138,
      "learning_rate": 7.047352961393844e-06,
      "loss": 0.0027,
      "step": 870
    },
    {
      "epoch": 437.5,
      "grad_norm": 0.020559758942860218,
      "learning_rate": 6.8951001502612065e-06,
      "loss": 0.0027,
      "step": 875
    },
    {
      "epoch": 440.0,
      "grad_norm": 0.02381279446911383,
      "learning_rate": 6.748480513008844e-06,
      "loss": 0.0025,
      "step": 880
    },
    {
      "epoch": 442.5,
      "grad_norm": 0.014589626300082677,
      "learning_rate": 6.607534133981594e-06,
      "loss": 0.0026,
      "step": 885
    },
    {
      "epoch": 445.0,
      "grad_norm": 0.026727121558605703,
      "learning_rate": 6.472299546512134e-06,
      "loss": 0.0026,
      "step": 890
    },
    {
      "epoch": 447.5,
      "grad_norm": 0.01580348324753083,
      "learning_rate": 6.342813722386374e-06,
      "loss": 0.0027,
      "step": 895
    },
    {
      "epoch": 450.0,
      "grad_norm": 0.02334311857794958,
      "learning_rate": 6.219112061735721e-06,
      "loss": 0.0026,
      "step": 900
    },
    {
      "epoch": 452.5,
      "grad_norm": 0.022995449553396018,
      "learning_rate": 6.1012283833590465e-06,
      "loss": 0.0026,
      "step": 905
    },
    {
      "epoch": 455.0,
      "grad_norm": 0.03391053587500504,
      "learning_rate": 5.989194915476954e-06,
      "loss": 0.0027,
      "step": 910
    },
    {
      "epoch": 457.5,
      "grad_norm": 0.0281194121062883,
      "learning_rate": 5.883042286920918e-06,
      "loss": 0.0025,
      "step": 915
    },
    {
      "epoch": 460.0,
      "grad_norm": 0.018983581090637,
      "learning_rate": 5.782799518759658e-06,
      "loss": 0.0025,
      "step": 920
    },
    {
      "epoch": 462.5,
      "grad_norm": 0.024476355758836905,
      "learning_rate": 5.688494016365067e-06,
      "loss": 0.0026,
      "step": 925
    },
    {
      "epoch": 465.0,
      "grad_norm": 0.023061048781595993,
      "learning_rate": 5.600151561919871e-06,
      "loss": 0.0027,
      "step": 930
    },
    {
      "epoch": 467.5,
      "grad_norm": 0.012496893287463113,
      "learning_rate": 5.517796307369017e-06,
      "loss": 0.0026,
      "step": 935
    },
    {
      "epoch": 470.0,
      "grad_norm": 0.01991683594417727,
      "learning_rate": 5.44145076781679e-06,
      "loss": 0.0026,
      "step": 940
    },
    {
      "epoch": 472.5,
      "grad_norm": 0.028037001206555136,
      "learning_rate": 5.371135815371398e-06,
      "loss": 0.0027,
      "step": 945
    },
    {
      "epoch": 475.0,
      "grad_norm": 0.026283232329898983,
      "learning_rate": 5.3068706734387484e-06,
      "loss": 0.0026,
      "step": 950
    },
    {
      "epoch": 477.5,
      "grad_norm": 0.026815406305102027,
      "learning_rate": 5.248672911466959e-06,
      "loss": 0.0026,
      "step": 955
    },
    {
      "epoch": 480.0,
      "grad_norm": 0.01847886314594556,
      "learning_rate": 5.196558440143059e-06,
      "loss": 0.0025,
      "step": 960
    },
    {
      "epoch": 482.5,
      "grad_norm": 0.019370493214584474,
      "learning_rate": 5.150541507043143e-06,
      "loss": 0.0027,
      "step": 965
    },
    {
      "epoch": 485.0,
      "grad_norm": 0.021779585772489417,
      "learning_rate": 5.110634692737244e-06,
      "loss": 0.0026,
      "step": 970
    },
    {
      "epoch": 487.5,
      "grad_norm": 0.02541037015533656,
      "learning_rate": 5.0768489073499295e-06,
      "loss": 0.0027,
      "step": 975
    },
    {
      "epoch": 490.0,
      "grad_norm": 0.02945361459676501,
      "learning_rate": 5.049193387577574e-06,
      "loss": 0.0026,
      "step": 980
    },
    {
      "epoch": 492.5,
      "grad_norm": 0.017922772556181753,
      "learning_rate": 5.027675694163144e-06,
      "loss": 0.0028,
      "step": 985
    },
    {
      "epoch": 495.0,
      "grad_norm": 0.023023048365518207,
      "learning_rate": 5.012301709829164e-06,
      "loss": 0.0026,
      "step": 990
    },
    {
      "epoch": 497.5,
      "grad_norm": 0.020646776127788924,
      "learning_rate": 5.003075637669448e-06,
      "loss": 0.0027,
      "step": 995
    },
    {
      "epoch": 500.0,
      "grad_norm": 0.0148034159233786,
      "learning_rate": 5e-06,
      "loss": 0.0027,
      "step": 1000
    },
    {
      "epoch": 500.0,
      "step": 1000,
      "total_flos": 28457722773504.0,
      "train_loss": 0.008928275344893336,
      "train_runtime": 1701.2794,
      "train_samples_per_second": 18.809,
      "train_steps_per_second": 0.588
    }
  ],
  "logging_steps": 5,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 500,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 28457722773504.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}