{
  "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": 0.04,
      "grad_norm": 36.62350976236379,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.7686,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 33.402926769373366,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.7673,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 29.15953639466983,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.5475,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 16.07162685325982,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 2.2226,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 9.80585458227313,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.9077,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 8.364670185323659,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.7503,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 10.487857287530497,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.6327,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 9.115847231620766,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.5833,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 7.4305610621486755,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.5075,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.2942637300556665,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4913,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 4.969141431197931,
      "learning_rate": 4.4e-06,
      "loss": 1.4498,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 4.682097317927401,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.3891,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 5.351515237468546,
      "learning_rate": 5.2e-06,
      "loss": 1.4318,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 4.496950410624682,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.3313,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 4.5274483062422615,
      "learning_rate": 6e-06,
      "loss": 1.36,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 4.449728341661814,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.349,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 5.042717020987108,
      "learning_rate": 6.800000000000001e-06,
      "loss": 1.2881,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 4.782308992285224,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.2826,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 4.700915195066555,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.2748,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.317231844522928,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2548,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 4.483215055070453,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.3021,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 4.333379763411882,
      "learning_rate": 8.8e-06,
      "loss": 1.2051,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 4.795371525496101,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.2208,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 4.444618775010596,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.21,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.549092894417248,
      "learning_rate": 1e-05,
      "loss": 1.1917,
      "step": 125
    },
    {
      "epoch": 1.04,
      "grad_norm": 5.393219994510853,
      "learning_rate": 9.9e-06,
      "loss": 1.0078,
      "step": 130
    },
    {
      "epoch": 1.08,
      "grad_norm": 4.811824101990855,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.0773,
      "step": 135
    },
    {
      "epoch": 1.12,
      "grad_norm": 4.130172454093617,
      "learning_rate": 9.7e-06,
      "loss": 1.0361,
      "step": 140
    },
    {
      "epoch": 1.16,
      "grad_norm": 4.7711116482515346,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.9951,
      "step": 145
    },
    {
      "epoch": 1.2,
      "grad_norm": 5.4441541344470625,
      "learning_rate": 9.5e-06,
      "loss": 1.015,
      "step": 150
    },
    {
      "epoch": 1.24,
      "grad_norm": 4.329153093427742,
      "learning_rate": 9.4e-06,
      "loss": 0.9364,
      "step": 155
    },
    {
      "epoch": 1.28,
      "grad_norm": 5.404564077588743,
      "learning_rate": 9.3e-06,
      "loss": 0.9667,
      "step": 160
    },
    {
      "epoch": 1.32,
      "grad_norm": 4.814443245288409,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.9701,
      "step": 165
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 5.213266037434429,
      "learning_rate": 9.100000000000001e-06,
      "loss": 0.9852,
      "step": 170
    },
    {
      "epoch": 1.4,
      "grad_norm": 5.9843114647559466,
      "learning_rate": 9e-06,
      "loss": 0.9163,
      "step": 175
    },
    {
      "epoch": 1.44,
      "grad_norm": 4.518839565114827,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.9649,
      "step": 180
    },
    {
      "epoch": 1.48,
      "grad_norm": 5.938613490214291,
      "learning_rate": 8.8e-06,
      "loss": 0.9879,
      "step": 185
    },
    {
      "epoch": 1.52,
      "grad_norm": 6.3647534949429385,
      "learning_rate": 8.700000000000001e-06,
      "loss": 0.9951,
      "step": 190
    },
    {
      "epoch": 1.56,
      "grad_norm": 4.688895440586879,
      "learning_rate": 8.6e-06,
      "loss": 0.9552,
      "step": 195
    },
    {
      "epoch": 1.6,
      "grad_norm": 5.151064327880198,
      "learning_rate": 8.5e-06,
      "loss": 0.9984,
      "step": 200
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 4.470424487813291,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.0106,
      "step": 205
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 4.7598350543084855,
      "learning_rate": 8.3e-06,
      "loss": 0.9769,
      "step": 210
    },
    {
      "epoch": 1.72,
      "grad_norm": 5.982179170035923,
      "learning_rate": 8.2e-06,
      "loss": 0.9939,
      "step": 215
    },
    {
      "epoch": 1.76,
      "grad_norm": 4.784770280165873,
      "learning_rate": 8.1e-06,
      "loss": 0.9742,
      "step": 220
    },
    {
      "epoch": 1.8,
      "grad_norm": 4.776273349185125,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9805,
      "step": 225
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 6.255570350956941,
      "learning_rate": 7.9e-06,
      "loss": 0.9445,
      "step": 230
    },
    {
      "epoch": 1.88,
      "grad_norm": 5.023021543653814,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.9903,
      "step": 235
    },
    {
      "epoch": 1.92,
      "grad_norm": 5.749553636816607,
      "learning_rate": 7.7e-06,
      "loss": 0.9789,
      "step": 240
    },
    {
      "epoch": 1.96,
      "grad_norm": 4.43724933975499,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.9566,
      "step": 245
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.294875736353378,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.9668,
      "step": 250
    },
    {
      "epoch": 2.04,
      "grad_norm": 4.115316556309453,
      "learning_rate": 7.4e-06,
      "loss": 0.5217,
      "step": 255
    },
    {
      "epoch": 2.08,
      "grad_norm": 4.485770762326278,
      "learning_rate": 7.3e-06,
      "loss": 0.4782,
      "step": 260
    },
    {
      "epoch": 2.12,
      "grad_norm": 5.6703241910593665,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.4877,
      "step": 265
    },
    {
      "epoch": 2.16,
      "grad_norm": 5.52684951905309,
      "learning_rate": 7.100000000000001e-06,
      "loss": 0.4488,
      "step": 270
    },
    {
      "epoch": 2.2,
      "grad_norm": 4.414170404774744,
      "learning_rate": 7e-06,
      "loss": 0.411,
      "step": 275
    },
    {
      "epoch": 2.24,
      "grad_norm": 5.57767144115952,
      "learning_rate": 6.9e-06,
      "loss": 0.4727,
      "step": 280
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 5.6008427737888455,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.4473,
      "step": 285
    },
    {
      "epoch": 2.32,
      "grad_norm": 5.027723301079731,
      "learning_rate": 6.700000000000001e-06,
      "loss": 0.4675,
      "step": 290
    },
    {
      "epoch": 2.36,
      "grad_norm": 6.02726751108404,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.4652,
      "step": 295
    },
    {
      "epoch": 2.4,
      "grad_norm": 4.759340207767181,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.4763,
      "step": 300
    },
    {
      "epoch": 2.44,
      "grad_norm": 5.402094842455488,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.4808,
      "step": 305
    },
    {
      "epoch": 2.48,
      "grad_norm": 7.346884164043201,
      "learning_rate": 6.300000000000001e-06,
      "loss": 0.4524,
      "step": 310
    },
    {
      "epoch": 2.52,
      "grad_norm": 6.493439715149578,
      "learning_rate": 6.200000000000001e-06,
      "loss": 0.4732,
      "step": 315
    },
    {
      "epoch": 2.56,
      "grad_norm": 5.242435647736096,
      "learning_rate": 6.1e-06,
      "loss": 0.4399,
      "step": 320
    },
    {
      "epoch": 2.6,
      "grad_norm": 5.88003032559697,
      "learning_rate": 6e-06,
      "loss": 0.4438,
      "step": 325
    },
    {
      "epoch": 2.64,
      "grad_norm": 5.123956089260275,
      "learning_rate": 5.9e-06,
      "loss": 0.4524,
      "step": 330
    },
    {
      "epoch": 2.68,
      "grad_norm": 5.4125878777221175,
      "learning_rate": 5.8e-06,
      "loss": 0.4522,
      "step": 335
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 6.126693110504838,
      "learning_rate": 5.7e-06,
      "loss": 0.477,
      "step": 340
    },
    {
      "epoch": 2.76,
      "grad_norm": 5.846974358806601,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.4882,
      "step": 345
    },
    {
      "epoch": 2.8,
      "grad_norm": 5.264364934021066,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.4321,
      "step": 350
    },
    {
      "epoch": 2.84,
      "grad_norm": 5.145680218904982,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.4844,
      "step": 355
    },
    {
      "epoch": 2.88,
      "grad_norm": 4.700122299887486,
      "learning_rate": 5.300000000000001e-06,
      "loss": 0.4641,
      "step": 360
    },
    {
      "epoch": 2.92,
      "grad_norm": 5.229294178378898,
      "learning_rate": 5.2e-06,
      "loss": 0.4639,
      "step": 365
    },
    {
      "epoch": 2.96,
      "grad_norm": 5.4556880967540184,
      "learning_rate": 5.1e-06,
      "loss": 0.4625,
      "step": 370
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.468435635264789,
      "learning_rate": 5e-06,
      "loss": 0.4542,
      "step": 375
    },
    {
      "epoch": 3.04,
      "grad_norm": 3.4594986848521505,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.1431,
      "step": 380
    },
    {
      "epoch": 3.08,
      "grad_norm": 3.9035770698658374,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.1234,
      "step": 385
    },
    {
      "epoch": 3.12,
      "grad_norm": 6.327588926630842,
      "learning_rate": 4.7e-06,
      "loss": 0.1247,
      "step": 390
    },
    {
      "epoch": 3.16,
      "grad_norm": 4.105742067550939,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.1199,
      "step": 395
    },
    {
      "epoch": 3.2,
      "grad_norm": 3.6092152639061186,
      "learning_rate": 4.5e-06,
      "loss": 0.1274,
      "step": 400
    },
    {
      "epoch": 3.24,
      "grad_norm": 4.709247918796706,
      "learning_rate": 4.4e-06,
      "loss": 0.1152,
      "step": 405
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 5.560331801313448,
      "learning_rate": 4.3e-06,
      "loss": 0.1204,
      "step": 410
    },
    {
      "epoch": 3.32,
      "grad_norm": 5.046626674201296,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.1041,
      "step": 415
    },
    {
      "epoch": 3.36,
      "grad_norm": 4.933231135125196,
      "learning_rate": 4.1e-06,
      "loss": 0.1162,
      "step": 420
    },
    {
      "epoch": 3.4,
      "grad_norm": 4.63300943114347,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.1196,
      "step": 425
    },
    {
      "epoch": 3.44,
      "grad_norm": 5.374366344316167,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.1108,
      "step": 430
    },
    {
      "epoch": 3.48,
      "grad_norm": 4.562505182296969,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.1156,
      "step": 435
    },
    {
      "epoch": 3.52,
      "grad_norm": 5.138471559263531,
      "learning_rate": 3.7e-06,
      "loss": 0.1268,
      "step": 440
    },
    {
      "epoch": 3.56,
      "grad_norm": 5.687245937142008,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.1056,
      "step": 445
    },
    {
      "epoch": 3.6,
      "grad_norm": 4.80683512067971,
      "learning_rate": 3.5e-06,
      "loss": 0.1158,
      "step": 450
    },
    {
      "epoch": 3.64,
      "grad_norm": 4.59170113004682,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.1132,
      "step": 455
    },
    {
      "epoch": 3.68,
      "grad_norm": 4.107632166314909,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.1217,
      "step": 460
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 5.010547708513583,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.1166,
      "step": 465
    },
    {
      "epoch": 3.76,
      "grad_norm": 4.8367287666182985,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.1221,
      "step": 470
    },
    {
      "epoch": 3.8,
      "grad_norm": 4.667790832135365,
      "learning_rate": 3e-06,
      "loss": 0.1065,
      "step": 475
    },
    {
      "epoch": 3.84,
      "grad_norm": 3.986421460836487,
      "learning_rate": 2.9e-06,
      "loss": 0.1153,
      "step": 480
    },
    {
      "epoch": 3.88,
      "grad_norm": 3.358654356216991,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0993,
      "step": 485
    },
    {
      "epoch": 3.92,
      "grad_norm": 5.222068297339352,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.1097,
      "step": 490
    },
    {
      "epoch": 3.96,
      "grad_norm": 4.0424229811432335,
      "learning_rate": 2.6e-06,
      "loss": 0.1117,
      "step": 495
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.589350075783199,
      "learning_rate": 2.5e-06,
      "loss": 0.1166,
      "step": 500
    },
    {
      "epoch": 4.04,
      "grad_norm": 2.7452788718903323,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.029,
      "step": 505
    },
    {
      "epoch": 4.08,
      "grad_norm": 2.3347955331539834,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0326,
      "step": 510
    },
    {
      "epoch": 4.12,
      "grad_norm": 1.430723643644038,
      "learning_rate": 2.2e-06,
      "loss": 0.0242,
      "step": 515
    },
    {
      "epoch": 4.16,
      "grad_norm": 2.4549594915087742,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0211,
      "step": 520
    },
    {
      "epoch": 4.2,
      "grad_norm": 3.5255752766413817,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0252,
      "step": 525
    },
    {
      "epoch": 4.24,
      "grad_norm": 3.331779060215209,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0259,
      "step": 530
    },
    {
      "epoch": 4.28,
      "grad_norm": 1.4619866835660613,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0214,
      "step": 535
    },
    {
      "epoch": 4.32,
      "grad_norm": 1.6926743298016238,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0221,
      "step": 540
    },
    {
      "epoch": 4.36,
      "grad_norm": 1.5199184430733323,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0208,
      "step": 545
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.1995876611751095,
      "learning_rate": 1.5e-06,
      "loss": 0.0201,
      "step": 550
    },
    {
      "epoch": 4.44,
      "grad_norm": 2.886855022062806,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.0204,
      "step": 555
    },
    {
      "epoch": 4.48,
      "grad_norm": 1.9390603220231086,
      "learning_rate": 1.3e-06,
      "loss": 0.0219,
      "step": 560
    },
    {
      "epoch": 4.52,
      "grad_norm": 2.059229393425642,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.0212,
      "step": 565
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 2.2451024446606223,
      "learning_rate": 1.1e-06,
      "loss": 0.0208,
      "step": 570
    },
    {
      "epoch": 4.6,
      "grad_norm": 2.7869036199440655,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0216,
      "step": 575
    },
    {
      "epoch": 4.64,
      "grad_norm": 2.1928089302131837,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.0205,
      "step": 580
    },
    {
      "epoch": 4.68,
      "grad_norm": 2.760635807577317,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.0234,
      "step": 585
    },
    {
      "epoch": 4.72,
      "grad_norm": 1.2057418391129255,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.0202,
      "step": 590
    },
    {
      "epoch": 4.76,
      "grad_norm": 1.7357316579523792,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.0203,
      "step": 595
    },
    {
      "epoch": 4.8,
      "grad_norm": 3.0097945211300927,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.0218,
      "step": 600
    },
    {
      "epoch": 4.84,
      "grad_norm": 2.6984689659641288,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.024,
      "step": 605
    },
    {
      "epoch": 4.88,
      "grad_norm": 1.9122708165565099,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.0186,
      "step": 610
    },
    {
      "epoch": 4.92,
      "grad_norm": 2.4369570463814636,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.0225,
      "step": 615
    },
    {
      "epoch": 4.96,
      "grad_norm": 2.248554113646146,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.02,
      "step": 620
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.1294256888312746,
      "learning_rate": 0.0,
      "loss": 0.0197,
      "step": 625
    },
    {
      "epoch": 5.0,
      "step": 625,
      "total_flos": 2776727715840.0,
      "train_loss": 0.6350300723552704,
      "train_runtime": 8048.3061,
      "train_samples_per_second": 2.485,
      "train_steps_per_second": 0.078
    }
  ],
  "logging_steps": 5,
  "max_steps": 625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2776727715840.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}