{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 0.0,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0,
      "learning_rate": 6.349206349206349e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0,
      "learning_rate": 7.936507936507937e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.0,
      "learning_rate": 0.00012698412698412698,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0,
      "learning_rate": 0.00015873015873015873,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0,
      "learning_rate": 0.00017460317460317462,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0,
      "learning_rate": 0.00019047619047619048,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.0,
      "learning_rate": 0.00019999375039475277,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0,
      "learning_rate": 0.0001999234513064475,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.0,
      "learning_rate": 0.00019977509622105233,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.0,
      "learning_rate": 0.0001995488010273198,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0,
      "learning_rate": 0.00019924474249753655,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0,
      "learning_rate": 0.00019886315814943647,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.0,
      "learning_rate": 0.0001984043460606618,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0,
      "learning_rate": 0.0001978686646359173,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 4.8843664841655485,
      "learning_rate": 0.0001972565323269996,
      "loss": 3.5275,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.9367197537847722,
      "learning_rate": 0.00019656842730592046,
      "loss": 2.4617,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.6692050704025108,
      "learning_rate": 0.0001958048870913786,
      "loss": 2.0719,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.0484984779217945,
      "learning_rate": 0.0001949665081288729,
      "loss": 1.9191,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.084657145540847,
      "learning_rate": 0.00019405394532478424,
      "loss": 1.7622,
      "step": 125
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.8826541418665111,
      "learning_rate": 0.00019306791153479006,
      "loss": 1.5793,
      "step": 130
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.8402855604097518,
      "learning_rate": 0.00019200917700701176,
      "loss": 1.5816,
      "step": 135
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.8971788963916263,
      "learning_rate": 0.0001908785687803289,
      "loss": 1.4692,
      "step": 140
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.5837535747952808,
      "learning_rate": 0.00018967697003833157,
      "loss": 1.4171,
      "step": 145
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.6080532043018163,
      "learning_rate": 0.0001884053194194142,
      "loss": 1.3879,
      "step": 150
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.5424236872385151,
      "learning_rate": 0.00018706461028355104,
      "loss": 1.3751,
      "step": 155
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.521156712371918,
      "learning_rate": 0.00018565588993632487,
      "loss": 1.353,
      "step": 160
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.5630616486472927,
      "learning_rate": 0.0001841802588108161,
      "loss": 1.3693,
      "step": 165
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.5762860311050592,
      "learning_rate": 0.00018263886960799062,
      "loss": 1.3361,
      "step": 170
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.5670131315191044,
      "learning_rate": 0.00018103292639625837,
      "loss": 1.3246,
      "step": 175
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.5872553271388077,
      "learning_rate": 0.0001793636836709057,
      "loss": 1.3378,
      "step": 180
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.47848829808272364,
      "learning_rate": 0.0001776324453741365,
      "loss": 1.3614,
      "step": 185
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.49455580287303413,
      "learning_rate": 0.00017584056387648727,
      "loss": 1.2795,
      "step": 190
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.5545081477783124,
      "learning_rate": 0.0001739894389204122,
      "loss": 1.3505,
      "step": 195
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5273540066664081,
      "learning_rate": 0.00017208051652686335,
      "loss": 1.304,
      "step": 200
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.5236332903582206,
      "learning_rate": 0.00017011528786571969,
      "loss": 1.2964,
      "step": 205
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.522859471024846,
      "learning_rate": 0.00016809528809094807,
      "loss": 1.3191,
      "step": 210
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.5325159438088393,
      "learning_rate": 0.0001660220951414055,
      "loss": 1.3365,
      "step": 215
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.5932904452055382,
      "learning_rate": 0.00016389732850821966,
      "loss": 1.3065,
      "step": 220
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.5753490852273148,
      "learning_rate": 0.0001617226479697105,
      "loss": 1.2923,
      "step": 225
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.7099770456528512,
      "learning_rate": 0.00015949975229484134,
      "loss": 1.3006,
      "step": 230
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.5445882124083564,
      "learning_rate": 0.00015723037791621193,
      "loss": 1.2631,
      "step": 235
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.5508092626640723,
      "learning_rate": 0.00015491629757363032,
      "loss": 1.2956,
      "step": 240
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.5700022934921076,
      "learning_rate": 0.00015255931892932333,
      "loss": 1.3077,
      "step": 245
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6420724844011209,
      "learning_rate": 0.0001501612831558664,
      "loss": 1.2865,
      "step": 250
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.5185087077026251,
      "learning_rate": 0.00014772406349793744,
      "loss": 1.0933,
      "step": 255
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.6939023149806638,
      "learning_rate": 0.0001452495638090167,
      "loss": 1.1302,
      "step": 260
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.67218828804889,
      "learning_rate": 0.00014273971706417647,
      "loss": 1.1181,
      "step": 265
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.6679846698249866,
      "learning_rate": 0.00014019648385012244,
      "loss": 1.1407,
      "step": 270
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.6857639874881996,
      "learning_rate": 0.00013762185083366556,
      "loss": 1.1191,
      "step": 275
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.6584817159906468,
      "learning_rate": 0.00013501782920982184,
      "loss": 1.1132,
      "step": 280
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.6587937675440276,
      "learning_rate": 0.00013238645313075104,
      "loss": 1.1154,
      "step": 285
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.7108364768563155,
      "learning_rate": 0.00012972977811676287,
      "loss": 1.0738,
      "step": 290
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.7654695954348383,
      "learning_rate": 0.00012704987945063068,
      "loss": 1.1112,
      "step": 295
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.6510685094630188,
      "learning_rate": 0.00012434885055646823,
      "loss": 1.076,
      "step": 300
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.6513602137372655,
      "learning_rate": 0.00012162880136443447,
      "loss": 1.0938,
      "step": 305
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.6518580265652315,
      "learning_rate": 0.00011889185666254506,
      "loss": 1.1091,
      "step": 310
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.700791005032011,
      "learning_rate": 0.00011614015443687722,
      "loss": 1.0928,
      "step": 315
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.7137299516787894,
      "learning_rate": 0.0001133758442014651,
      "loss": 1.0975,
      "step": 320
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.7096635920365164,
      "learning_rate": 0.00011060108531918971,
      "loss": 1.0866,
      "step": 325
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.7329519901448388,
      "learning_rate": 0.0001078180453149754,
      "loss": 1.1202,
      "step": 330
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.6956042484637527,
      "learning_rate": 0.00010502889818261075,
      "loss": 1.0804,
      "step": 335
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.708989418947315,
      "learning_rate": 0.00010223582268651586,
      "loss": 1.0851,
      "step": 340
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.8321704062723837,
      "learning_rate": 9.94410006597835e-05,
      "loss": 1.0877,
      "step": 345
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.774733895652043,
      "learning_rate": 9.66466152998226e-05,
      "loss": 1.0717,
      "step": 350
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.7903318932347777,
      "learning_rate": 9.385484946293637e-05,
      "loss": 1.1324,
      "step": 355
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.7341720746069825,
      "learning_rate": 9.106788395916678e-05,
      "loss": 1.1025,
      "step": 360
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.7846739828245529,
      "learning_rate": 8.828789584873754e-05,
      "loss": 1.1411,
      "step": 365
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.7345758394982582,
      "learning_rate": 8.551705674142617e-05,
      "loss": 1.103,
      "step": 370
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7564552144611311,
      "learning_rate": 8.275753110019367e-05,
      "loss": 1.07,
      "step": 375
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.7129645924023327,
      "learning_rate": 8.001147455039735e-05,
      "loss": 0.98,
      "step": 380
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.7646350891088591,
      "learning_rate": 7.728103219590681e-05,
      "loss": 0.927,
      "step": 385
    },
    {
      "epoch": 3.12,
      "grad_norm": 1.0269234227263822,
      "learning_rate": 7.456833694343906e-05,
      "loss": 0.9207,
      "step": 390
    },
    {
      "epoch": 3.16,
      "grad_norm": 0.8773416480143502,
      "learning_rate": 7.18755078364214e-05,
      "loss": 0.943,
      "step": 395
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.8734652261717027,
      "learning_rate": 6.920464839968405e-05,
      "loss": 0.9383,
      "step": 400
    },
    {
      "epoch": 3.24,
      "grad_norm": 0.9047400612085651,
      "learning_rate": 6.65578449962749e-05,
      "loss": 0.9265,
      "step": 405
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 0.9563261274281473,
      "learning_rate": 6.393716519768047e-05,
      "loss": 0.9405,
      "step": 410
    },
    {
      "epoch": 3.32,
      "grad_norm": 0.8697172121076815,
      "learning_rate": 6.134465616872598e-05,
      "loss": 0.9677,
      "step": 415
    },
    {
      "epoch": 3.36,
      "grad_norm": 0.8811910025949315,
      "learning_rate": 5.878234306841637e-05,
      "loss": 0.9201,
      "step": 420
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.91464519619479,
      "learning_rate": 5.62522274679673e-05,
      "loss": 0.9695,
      "step": 425
    },
    {
      "epoch": 3.44,
      "grad_norm": 0.8875127022364347,
      "learning_rate": 5.375628578726181e-05,
      "loss": 0.9259,
      "step": 430
    },
    {
      "epoch": 3.48,
      "grad_norm": 0.9140384002718888,
      "learning_rate": 5.1296467750954314e-05,
      "loss": 0.9382,
      "step": 435
    },
    {
      "epoch": 3.52,
      "grad_norm": 0.9130113252787699,
      "learning_rate": 4.8874694865427676e-05,
      "loss": 0.9578,
      "step": 440
    },
    {
      "epoch": 3.56,
      "grad_norm": 0.9169457361937253,
      "learning_rate": 4.649285891779327e-05,
      "loss": 0.9179,
      "step": 445
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.9424562700953132,
      "learning_rate": 4.415282049810644e-05,
      "loss": 0.9191,
      "step": 450
    },
    {
      "epoch": 3.64,
      "grad_norm": 0.9245761957614527,
      "learning_rate": 4.1856407545951834e-05,
      "loss": 0.9242,
      "step": 455
    },
    {
      "epoch": 3.68,
      "grad_norm": 0.9672178741357245,
      "learning_rate": 3.9605413922533874e-05,
      "loss": 0.9503,
      "step": 460
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 0.952034748851393,
      "learning_rate": 3.740159800938784e-05,
      "loss": 0.9319,
      "step": 465
    },
    {
      "epoch": 3.76,
      "grad_norm": 0.9200447825604482,
      "learning_rate": 3.5246681334806175e-05,
      "loss": 0.9378,
      "step": 470
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.9213126186210203,
      "learning_rate": 3.3142347229053015e-05,
      "loss": 0.891,
      "step": 475
    },
    {
      "epoch": 3.84,
      "grad_norm": 1.0516175908801786,
      "learning_rate": 3.109023950941736e-05,
      "loss": 0.9619,
      "step": 480
    },
    {
      "epoch": 3.88,
      "grad_norm": 0.9277117122712767,
      "learning_rate": 2.909196119613218e-05,
      "loss": 0.9036,
      "step": 485
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.9156379739401684,
      "learning_rate": 2.7149073260162416e-05,
      "loss": 0.9272,
      "step": 490
    },
    {
      "epoch": 3.96,
      "grad_norm": 0.9956486640584029,
      "learning_rate": 2.5263093403840142e-05,
      "loss": 0.9244,
      "step": 495
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.911041002840735,
      "learning_rate": 2.3435494875299314e-05,
      "loss": 0.8899,
      "step": 500
    },
    {
      "epoch": 4.04,
      "grad_norm": 0.9135972762786166,
      "learning_rate": 2.166770531763633e-05,
      "loss": 0.8285,
      "step": 505
    },
    {
      "epoch": 4.08,
      "grad_norm": 0.9273774203812593,
      "learning_rate": 1.9961105653695266e-05,
      "loss": 0.8119,
      "step": 510
    },
    {
      "epoch": 4.12,
      "grad_norm": 1.0596081187704738,
      "learning_rate": 1.8317029007349085e-05,
      "loss": 0.8444,
      "step": 515
    },
    {
      "epoch": 4.16,
      "grad_norm": 1.1322325016109431,
      "learning_rate": 1.6736759662119183e-05,
      "loss": 0.8257,
      "step": 520
    },
    {
      "epoch": 4.2,
      "grad_norm": 1.0759195776028518,
      "learning_rate": 1.5221532057947419e-05,
      "loss": 0.8464,
      "step": 525
    },
    {
      "epoch": 4.24,
      "grad_norm": 1.1095362756261793,
      "learning_rate": 1.3772529826903269e-05,
      "loss": 0.8389,
      "step": 530
    },
    {
      "epoch": 4.28,
      "grad_norm": 1.2253346667978913,
      "learning_rate": 1.23908848685804e-05,
      "loss": 0.8397,
      "step": 535
    },
    {
      "epoch": 4.32,
      "grad_norm": 1.1019952367500718,
      "learning_rate": 1.1077676465904208e-05,
      "loss": 0.7909,
      "step": 540
    },
    {
      "epoch": 4.36,
      "grad_norm": 1.1104082298724263,
      "learning_rate": 9.833930442041506e-06,
      "loss": 0.8177,
      "step": 545
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.1198369280329472,
      "learning_rate": 8.660618359070604e-06,
      "loss": 0.8027,
      "step": 550
    },
    {
      "epoch": 4.44,
      "grad_norm": 1.1477607984789764,
      "learning_rate": 7.558656759037797e-06,
      "loss": 0.819,
      "step": 555
    },
    {
      "epoch": 4.48,
      "grad_norm": 1.1041070390660572,
      "learning_rate": 6.528906447993288e-06,
      "loss": 0.8273,
      "step": 560
    },
    {
      "epoch": 4.52,
      "grad_norm": 1.097202307726145,
      "learning_rate": 5.572171823565797e-06,
      "loss": 0.8386,
      "step": 565
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 1.0733098668282173,
      "learning_rate": 4.689200246600867e-06,
      "loss": 0.7639,
      "step": 570
    },
    {
      "epoch": 4.6,
      "grad_norm": 1.1855618601043227,
      "learning_rate": 3.880681457354118e-06,
      "loss": 0.8059,
      "step": 575
    },
    {
      "epoch": 4.64,
      "grad_norm": 1.0801503593334882,
      "learning_rate": 3.1472470366950334e-06,
      "loss": 0.8106,
      "step": 580
    },
    {
      "epoch": 4.68,
      "grad_norm": 1.0698196762898835,
      "learning_rate": 2.4894699127426367e-06,
      "loss": 0.8094,
      "step": 585
    },
    {
      "epoch": 4.72,
      "grad_norm": 1.1338177263997045,
      "learning_rate": 1.907863913318153e-06,
      "loss": 0.8446,
      "step": 590
    },
    {
      "epoch": 4.76,
      "grad_norm": 1.0725846404716162,
      "learning_rate": 1.4028833645643113e-06,
      "loss": 0.8192,
      "step": 595
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.1178750406023408,
      "learning_rate": 9.749227360448143e-07,
      "loss": 0.8228,
      "step": 600
    },
    {
      "epoch": 4.84,
      "grad_norm": 1.1186187264597325,
      "learning_rate": 6.243163326014267e-07,
      "loss": 0.8227,
      "step": 605
    },
    {
      "epoch": 4.88,
      "grad_norm": 1.0422142146950775,
      "learning_rate": 3.5133803320896994e-07,
      "loss": 0.8152,
      "step": 610
    },
    {
      "epoch": 4.92,
      "grad_norm": 1.0424393555941693,
      "learning_rate": 1.562010770326916e-07,
      "loss": 0.7819,
      "step": 615
    },
    {
      "epoch": 4.96,
      "grad_norm": 1.1517583346783666,
      "learning_rate": 3.905789685471062e-08,
      "loss": 0.8124,
      "step": 620
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0989408579221684,
      "learning_rate": 0.0,
      "loss": 0.8157,
      "step": 625
    },
    {
      "epoch": 5.0,
      "step": 625,
      "total_flos": 158493649076224.0,
      "train_loss": 0.9354254070281982,
      "train_runtime": 1023.8732,
      "train_samples_per_second": 19.534,
      "train_steps_per_second": 0.61
    }
  ],
  "logging_steps": 5,
  "max_steps": 625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 158493649076224.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}