{
  "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": 74.36213885797416,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.4845,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 39.67273161719237,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.4018,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 20.150529644945628,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.9397,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 13.181976118850267,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.9034,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 10.94379061925288,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.8036,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 8.810530457957077,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.7202,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 8.333798663830095,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.6617,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 7.8827996030828755,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.6441,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 8.179799740479577,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.6148,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.66501382606033,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.6225,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 7.739113034030722,
      "learning_rate": 4.4e-06,
      "loss": 1.5815,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 7.111168113264018,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.5377,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 7.975055982789206,
      "learning_rate": 5.2e-06,
      "loss": 1.6093,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 7.144438766233695,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.502,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 7.236310870559594,
      "learning_rate": 6e-06,
      "loss": 1.5343,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 7.523450793617325,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.5301,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 7.980798750894632,
      "learning_rate": 6.800000000000001e-06,
      "loss": 1.4671,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 6.827717260805988,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.4627,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 8.220507882885352,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.455,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.397242323483418,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4545,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 7.196070444367311,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.5124,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 7.054517223111324,
      "learning_rate": 8.8e-06,
      "loss": 1.4047,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 6.996278030679922,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.4268,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 7.454116549484864,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.4034,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.566580238081964,
      "learning_rate": 1e-05,
      "loss": 1.3897,
      "step": 125
    },
    {
      "epoch": 1.04,
      "grad_norm": 7.154856076564589,
      "learning_rate": 9.9e-06,
      "loss": 1.0826,
      "step": 130
    },
    {
      "epoch": 1.08,
      "grad_norm": 8.286911013503115,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.1561,
      "step": 135
    },
    {
      "epoch": 1.12,
      "grad_norm": 7.631247621997401,
      "learning_rate": 9.7e-06,
      "loss": 1.1072,
      "step": 140
    },
    {
      "epoch": 1.16,
      "grad_norm": 8.500550823372908,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.0951,
      "step": 145
    },
    {
      "epoch": 1.2,
      "grad_norm": 7.454507377184453,
      "learning_rate": 9.5e-06,
      "loss": 1.1116,
      "step": 150
    },
    {
      "epoch": 1.24,
      "grad_norm": 7.428620314437955,
      "learning_rate": 9.4e-06,
      "loss": 1.0207,
      "step": 155
    },
    {
      "epoch": 1.28,
      "grad_norm": 8.223393076186099,
      "learning_rate": 9.3e-06,
      "loss": 1.0514,
      "step": 160
    },
    {
      "epoch": 1.32,
      "grad_norm": 7.879521076713879,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.0675,
      "step": 165
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 7.82982640171081,
      "learning_rate": 9.100000000000001e-06,
      "loss": 1.0879,
      "step": 170
    },
    {
      "epoch": 1.4,
      "grad_norm": 8.989451594833707,
      "learning_rate": 9e-06,
      "loss": 1.0076,
      "step": 175
    },
    {
      "epoch": 1.44,
      "grad_norm": 7.607465825565947,
      "learning_rate": 8.900000000000001e-06,
      "loss": 1.0912,
      "step": 180
    },
    {
      "epoch": 1.48,
      "grad_norm": 6.808939142255241,
      "learning_rate": 8.8e-06,
      "loss": 1.1222,
      "step": 185
    },
    {
      "epoch": 1.52,
      "grad_norm": 6.871273380383304,
      "learning_rate": 8.700000000000001e-06,
      "loss": 1.1153,
      "step": 190
    },
    {
      "epoch": 1.56,
      "grad_norm": 6.42305714135536,
      "learning_rate": 8.6e-06,
      "loss": 1.0968,
      "step": 195
    },
    {
      "epoch": 1.6,
      "grad_norm": 7.365551390055157,
      "learning_rate": 8.5e-06,
      "loss": 1.1041,
      "step": 200
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 6.501181010961079,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.1329,
      "step": 205
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 6.552529498775493,
      "learning_rate": 8.3e-06,
      "loss": 1.098,
      "step": 210
    },
    {
      "epoch": 1.72,
      "grad_norm": 7.44145270381018,
      "learning_rate": 8.2e-06,
      "loss": 1.1073,
      "step": 215
    },
    {
      "epoch": 1.76,
      "grad_norm": 7.445925186281827,
      "learning_rate": 8.1e-06,
      "loss": 1.0786,
      "step": 220
    },
    {
      "epoch": 1.8,
      "grad_norm": 6.470918236887296,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0866,
      "step": 225
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 7.451141320766108,
      "learning_rate": 7.9e-06,
      "loss": 1.0708,
      "step": 230
    },
    {
      "epoch": 1.88,
      "grad_norm": 6.823703743254816,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.1056,
      "step": 235
    },
    {
      "epoch": 1.92,
      "grad_norm": 7.216036429104124,
      "learning_rate": 7.7e-06,
      "loss": 1.0981,
      "step": 240
    },
    {
      "epoch": 1.96,
      "grad_norm": 6.876174979217876,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.1017,
      "step": 245
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.155758238173605,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1046,
      "step": 250
    },
    {
      "epoch": 2.04,
      "grad_norm": 7.85877092193839,
      "learning_rate": 7.4e-06,
      "loss": 0.5025,
      "step": 255
    },
    {
      "epoch": 2.08,
      "grad_norm": 7.661257288703544,
      "learning_rate": 7.3e-06,
      "loss": 0.4367,
      "step": 260
    },
    {
      "epoch": 2.12,
      "grad_norm": 6.9436467048385255,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.4419,
      "step": 265
    },
    {
      "epoch": 2.16,
      "grad_norm": 7.998641182806705,
      "learning_rate": 7.100000000000001e-06,
      "loss": 0.4168,
      "step": 270
    },
    {
      "epoch": 2.2,
      "grad_norm": 8.042641482476647,
      "learning_rate": 7e-06,
      "loss": 0.4035,
      "step": 275
    },
    {
      "epoch": 2.24,
      "grad_norm": 7.489969246320288,
      "learning_rate": 6.9e-06,
      "loss": 0.4606,
      "step": 280
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 7.309625541572775,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.4359,
      "step": 285
    },
    {
      "epoch": 2.32,
      "grad_norm": 6.966029239110126,
      "learning_rate": 6.700000000000001e-06,
      "loss": 0.4594,
      "step": 290
    },
    {
      "epoch": 2.36,
      "grad_norm": 8.20184804080824,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.457,
      "step": 295
    },
    {
      "epoch": 2.4,
      "grad_norm": 6.643191447925562,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.4649,
      "step": 300
    },
    {
      "epoch": 2.44,
      "grad_norm": 6.348792176644931,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.4703,
      "step": 305
    },
    {
      "epoch": 2.48,
      "grad_norm": 7.780011088149784,
      "learning_rate": 6.300000000000001e-06,
      "loss": 0.4431,
      "step": 310
    },
    {
      "epoch": 2.52,
      "grad_norm": 7.257146948918763,
      "learning_rate": 6.200000000000001e-06,
      "loss": 0.4588,
      "step": 315
    },
    {
      "epoch": 2.56,
      "grad_norm": 6.834381610570237,
      "learning_rate": 6.1e-06,
      "loss": 0.4415,
      "step": 320
    },
    {
      "epoch": 2.6,
      "grad_norm": 8.4320839309944,
      "learning_rate": 6e-06,
      "loss": 0.4477,
      "step": 325
    },
    {
      "epoch": 2.64,
      "grad_norm": 7.383643354043202,
      "learning_rate": 5.9e-06,
      "loss": 0.444,
      "step": 330
    },
    {
      "epoch": 2.68,
      "grad_norm": 6.736608657391058,
      "learning_rate": 5.8e-06,
      "loss": 0.4713,
      "step": 335
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 6.903557247354103,
      "learning_rate": 5.7e-06,
      "loss": 0.4755,
      "step": 340
    },
    {
      "epoch": 2.76,
      "grad_norm": 7.449013816758464,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.4676,
      "step": 345
    },
    {
      "epoch": 2.8,
      "grad_norm": 7.269064130287811,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.4327,
      "step": 350
    },
    {
      "epoch": 2.84,
      "grad_norm": 7.787232454809365,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.4643,
      "step": 355
    },
    {
      "epoch": 2.88,
      "grad_norm": 7.362964290370686,
      "learning_rate": 5.300000000000001e-06,
      "loss": 0.4412,
      "step": 360
    },
    {
      "epoch": 2.92,
      "grad_norm": 7.032694441520397,
      "learning_rate": 5.2e-06,
      "loss": 0.4702,
      "step": 365
    },
    {
      "epoch": 2.96,
      "grad_norm": 7.284333028185562,
      "learning_rate": 5.1e-06,
      "loss": 0.4319,
      "step": 370
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.682159784477329,
      "learning_rate": 5e-06,
      "loss": 0.4638,
      "step": 375
    },
    {
      "epoch": 3.04,
      "grad_norm": 4.9934999568853735,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.1428,
      "step": 380
    },
    {
      "epoch": 3.08,
      "grad_norm": 9.668596204370951,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.1218,
      "step": 385
    },
    {
      "epoch": 3.12,
      "grad_norm": 8.605762720501982,
      "learning_rate": 4.7e-06,
      "loss": 0.1257,
      "step": 390
    },
    {
      "epoch": 3.16,
      "grad_norm": 4.616932519177658,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.1123,
      "step": 395
    },
    {
      "epoch": 3.2,
      "grad_norm": 4.223096426437425,
      "learning_rate": 4.5e-06,
      "loss": 0.125,
      "step": 400
    },
    {
      "epoch": 3.24,
      "grad_norm": 4.741695820134459,
      "learning_rate": 4.4e-06,
      "loss": 0.1035,
      "step": 405
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 7.139756588143166,
      "learning_rate": 4.3e-06,
      "loss": 0.1115,
      "step": 410
    },
    {
      "epoch": 3.32,
      "grad_norm": 4.795651160027653,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.1083,
      "step": 415
    },
    {
      "epoch": 3.36,
      "grad_norm": 6.202951934260454,
      "learning_rate": 4.1e-06,
      "loss": 0.1155,
      "step": 420
    },
    {
      "epoch": 3.4,
      "grad_norm": 5.235911849426471,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.1199,
      "step": 425
    },
    {
      "epoch": 3.44,
      "grad_norm": 4.9149914998376625,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.1058,
      "step": 430
    },
    {
      "epoch": 3.48,
      "grad_norm": 5.192639808949672,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.1078,
      "step": 435
    },
    {
      "epoch": 3.52,
      "grad_norm": 7.311215245491757,
      "learning_rate": 3.7e-06,
      "loss": 0.1246,
      "step": 440
    },
    {
      "epoch": 3.56,
      "grad_norm": 6.2423727351220695,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.1061,
      "step": 445
    },
    {
      "epoch": 3.6,
      "grad_norm": 4.502900879114336,
      "learning_rate": 3.5e-06,
      "loss": 0.1066,
      "step": 450
    },
    {
      "epoch": 3.64,
      "grad_norm": 5.964810717622264,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.1157,
      "step": 455
    },
    {
      "epoch": 3.68,
      "grad_norm": 5.420408977697171,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.1181,
      "step": 460
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 7.304951517974589,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.1196,
      "step": 465
    },
    {
      "epoch": 3.76,
      "grad_norm": 5.974977881387938,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.1058,
      "step": 470
    },
    {
      "epoch": 3.8,
      "grad_norm": 4.745290726186264,
      "learning_rate": 3e-06,
      "loss": 0.0986,
      "step": 475
    },
    {
      "epoch": 3.84,
      "grad_norm": 4.96112390635835,
      "learning_rate": 2.9e-06,
      "loss": 0.1024,
      "step": 480
    },
    {
      "epoch": 3.88,
      "grad_norm": 6.46999826400111,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0993,
      "step": 485
    },
    {
      "epoch": 3.92,
      "grad_norm": 5.640502675240828,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.1154,
      "step": 490
    },
    {
      "epoch": 3.96,
      "grad_norm": 5.501055871658701,
      "learning_rate": 2.6e-06,
      "loss": 0.1076,
      "step": 495
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.4986571598352105,
      "learning_rate": 2.5e-06,
      "loss": 0.1241,
      "step": 500
    },
    {
      "epoch": 4.04,
      "grad_norm": 2.4114579253174337,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0309,
      "step": 505
    },
    {
      "epoch": 4.08,
      "grad_norm": 2.8884084439056457,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0244,
      "step": 510
    },
    {
      "epoch": 4.12,
      "grad_norm": 4.5465721004119555,
      "learning_rate": 2.2e-06,
      "loss": 0.0287,
      "step": 515
    },
    {
      "epoch": 4.16,
      "grad_norm": 4.069970791770994,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0242,
      "step": 520
    },
    {
      "epoch": 4.2,
      "grad_norm": 2.5594064719218728,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0219,
      "step": 525
    },
    {
      "epoch": 4.24,
      "grad_norm": 2.084461486703409,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.024,
      "step": 530
    },
    {
      "epoch": 4.28,
      "grad_norm": 4.105870543616731,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0209,
      "step": 535
    },
    {
      "epoch": 4.32,
      "grad_norm": 2.9576600895694467,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0189,
      "step": 540
    },
    {
      "epoch": 4.36,
      "grad_norm": 2.1728366137938258,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0246,
      "step": 545
    },
    {
      "epoch": 4.4,
      "grad_norm": 3.940768076670595,
      "learning_rate": 1.5e-06,
      "loss": 0.0257,
      "step": 550
    },
    {
      "epoch": 4.44,
      "grad_norm": 2.788452604038778,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.0237,
      "step": 555
    },
    {
      "epoch": 4.48,
      "grad_norm": 3.4210094679782386,
      "learning_rate": 1.3e-06,
      "loss": 0.025,
      "step": 560
    },
    {
      "epoch": 4.52,
      "grad_norm": 3.435544937813476,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.023,
      "step": 565
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 4.4129880682113685,
      "learning_rate": 1.1e-06,
      "loss": 0.0247,
      "step": 570
    },
    {
      "epoch": 4.6,
      "grad_norm": 2.154807219062607,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.022,
      "step": 575
    },
    {
      "epoch": 4.64,
      "grad_norm": 4.257954003696121,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.0207,
      "step": 580
    },
    {
      "epoch": 4.68,
      "grad_norm": 3.392435263683145,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.0317,
      "step": 585
    },
    {
      "epoch": 4.72,
      "grad_norm": 2.236685274693851,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.0153,
      "step": 590
    },
    {
      "epoch": 4.76,
      "grad_norm": 2.3888580946334272,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.0181,
      "step": 595
    },
    {
      "epoch": 4.8,
      "grad_norm": 4.438626868025895,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.0185,
      "step": 600
    },
    {
      "epoch": 4.84,
      "grad_norm": 2.1185823464478784,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.0193,
      "step": 605
    },
    {
      "epoch": 4.88,
      "grad_norm": 2.037043972837834,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.0182,
      "step": 610
    },
    {
      "epoch": 4.92,
      "grad_norm": 2.580279613193421,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.0216,
      "step": 615
    },
    {
      "epoch": 4.96,
      "grad_norm": 2.1026015102870352,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.02,
      "step": 620
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.9505385193444729,
      "learning_rate": 0.0,
      "loss": 0.0185,
      "step": 625
    },
    {
      "epoch": 5.0,
      "step": 625,
      "total_flos": 3401339535360.0,
      "train_loss": 0.6646418780684471,
      "train_runtime": 14425.7511,
      "train_samples_per_second": 1.386,
      "train_steps_per_second": 0.043
    }
  ],
  "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": 3401339535360.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}