{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32935364347468093,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016467682173734047,
      "grad_norm": 0.8692666888237,
      "learning_rate": 0.0002,
      "loss": 1.2712,
      "step": 4
    },
    {
      "epoch": 0.0032935364347468094,
      "grad_norm": 1.4892252683639526,
      "learning_rate": 0.0002,
      "loss": 0.7591,
      "step": 8
    },
    {
      "epoch": 0.004940304652120214,
      "grad_norm": 0.8453137874603271,
      "learning_rate": 0.0002,
      "loss": 0.4761,
      "step": 12
    },
    {
      "epoch": 0.006587072869493619,
      "grad_norm": 1.1559343338012695,
      "learning_rate": 0.0002,
      "loss": 0.4557,
      "step": 16
    },
    {
      "epoch": 0.008233841086867023,
      "grad_norm": 0.5908960103988647,
      "learning_rate": 0.0002,
      "loss": 0.4186,
      "step": 20
    },
    {
      "epoch": 0.009880609304240428,
      "grad_norm": 0.7283934354782104,
      "learning_rate": 0.0002,
      "loss": 0.4435,
      "step": 24
    },
    {
      "epoch": 0.011527377521613832,
      "grad_norm": 0.40564286708831787,
      "learning_rate": 0.0002,
      "loss": 0.3857,
      "step": 28
    },
    {
      "epoch": 0.013174145738987238,
      "grad_norm": 0.9832593202590942,
      "learning_rate": 0.0002,
      "loss": 0.3869,
      "step": 32
    },
    {
      "epoch": 0.014820913956360642,
      "grad_norm": 0.6356058120727539,
      "learning_rate": 0.0002,
      "loss": 0.3772,
      "step": 36
    },
    {
      "epoch": 0.016467682173734045,
      "grad_norm": 0.4383929669857025,
      "learning_rate": 0.0002,
      "loss": 0.4346,
      "step": 40
    },
    {
      "epoch": 0.018114450391107453,
      "grad_norm": 0.5270354747772217,
      "learning_rate": 0.0002,
      "loss": 0.4174,
      "step": 44
    },
    {
      "epoch": 0.019761218608480857,
      "grad_norm": 0.43965744972229004,
      "learning_rate": 0.0002,
      "loss": 0.4119,
      "step": 48
    },
    {
      "epoch": 0.02140798682585426,
      "grad_norm": 0.4961897134780884,
      "learning_rate": 0.0002,
      "loss": 0.3731,
      "step": 52
    },
    {
      "epoch": 0.023054755043227664,
      "grad_norm": 0.33899012207984924,
      "learning_rate": 0.0002,
      "loss": 0.3535,
      "step": 56
    },
    {
      "epoch": 0.02470152326060107,
      "grad_norm": 0.4382150173187256,
      "learning_rate": 0.0002,
      "loss": 0.3709,
      "step": 60
    },
    {
      "epoch": 0.026348291477974475,
      "grad_norm": 0.3768168091773987,
      "learning_rate": 0.0002,
      "loss": 0.3706,
      "step": 64
    },
    {
      "epoch": 0.02799505969534788,
      "grad_norm": 0.4140666127204895,
      "learning_rate": 0.0002,
      "loss": 0.3388,
      "step": 68
    },
    {
      "epoch": 0.029641827912721283,
      "grad_norm": 0.2670955955982208,
      "learning_rate": 0.0002,
      "loss": 0.3232,
      "step": 72
    },
    {
      "epoch": 0.03128859613009469,
      "grad_norm": 0.5184640884399414,
      "learning_rate": 0.0002,
      "loss": 0.3637,
      "step": 76
    },
    {
      "epoch": 0.03293536434746809,
      "grad_norm": 0.36012595891952515,
      "learning_rate": 0.0002,
      "loss": 0.3722,
      "step": 80
    },
    {
      "epoch": 0.0345821325648415,
      "grad_norm": 0.7544593811035156,
      "learning_rate": 0.0002,
      "loss": 0.3786,
      "step": 84
    },
    {
      "epoch": 0.036228900782214905,
      "grad_norm": 0.39954182505607605,
      "learning_rate": 0.0002,
      "loss": 0.3838,
      "step": 88
    },
    {
      "epoch": 0.03787566899958831,
      "grad_norm": 0.4210023581981659,
      "learning_rate": 0.0002,
      "loss": 0.3908,
      "step": 92
    },
    {
      "epoch": 0.03952243721696171,
      "grad_norm": 0.5908896923065186,
      "learning_rate": 0.0002,
      "loss": 0.3777,
      "step": 96
    },
    {
      "epoch": 0.04116920543433512,
      "grad_norm": 0.2767857611179352,
      "learning_rate": 0.0002,
      "loss": 0.3515,
      "step": 100
    },
    {
      "epoch": 0.04281597365170852,
      "grad_norm": 0.43755510449409485,
      "learning_rate": 0.0002,
      "loss": 0.4092,
      "step": 104
    },
    {
      "epoch": 0.044462741869081925,
      "grad_norm": 0.38882681727409363,
      "learning_rate": 0.0002,
      "loss": 0.3872,
      "step": 108
    },
    {
      "epoch": 0.04610951008645533,
      "grad_norm": 0.3989730775356293,
      "learning_rate": 0.0002,
      "loss": 0.3964,
      "step": 112
    },
    {
      "epoch": 0.04775627830382874,
      "grad_norm": 0.22192604839801788,
      "learning_rate": 0.0002,
      "loss": 0.3919,
      "step": 116
    },
    {
      "epoch": 0.04940304652120214,
      "grad_norm": 0.4765632152557373,
      "learning_rate": 0.0002,
      "loss": 0.3777,
      "step": 120
    },
    {
      "epoch": 0.05104981473857555,
      "grad_norm": 0.30803513526916504,
      "learning_rate": 0.0002,
      "loss": 0.3523,
      "step": 124
    },
    {
      "epoch": 0.05269658295594895,
      "grad_norm": 0.2666870653629303,
      "learning_rate": 0.0002,
      "loss": 0.4015,
      "step": 128
    },
    {
      "epoch": 0.054343351173322355,
      "grad_norm": 0.36492490768432617,
      "learning_rate": 0.0002,
      "loss": 0.3507,
      "step": 132
    },
    {
      "epoch": 0.05599011939069576,
      "grad_norm": 0.4382271468639374,
      "learning_rate": 0.0002,
      "loss": 0.346,
      "step": 136
    },
    {
      "epoch": 0.05763688760806916,
      "grad_norm": 0.3766026198863983,
      "learning_rate": 0.0002,
      "loss": 0.4013,
      "step": 140
    },
    {
      "epoch": 0.059283655825442566,
      "grad_norm": 0.3905723989009857,
      "learning_rate": 0.0002,
      "loss": 0.3881,
      "step": 144
    },
    {
      "epoch": 0.06093042404281598,
      "grad_norm": 0.3422534167766571,
      "learning_rate": 0.0002,
      "loss": 0.3546,
      "step": 148
    },
    {
      "epoch": 0.06257719226018937,
      "grad_norm": 0.3236246705055237,
      "learning_rate": 0.0002,
      "loss": 0.3359,
      "step": 152
    },
    {
      "epoch": 0.06422396047756278,
      "grad_norm": 0.3136650621891022,
      "learning_rate": 0.0002,
      "loss": 0.3321,
      "step": 156
    },
    {
      "epoch": 0.06587072869493618,
      "grad_norm": 0.4051145017147064,
      "learning_rate": 0.0002,
      "loss": 0.368,
      "step": 160
    },
    {
      "epoch": 0.0675174969123096,
      "grad_norm": 0.35720133781433105,
      "learning_rate": 0.0002,
      "loss": 0.3832,
      "step": 164
    },
    {
      "epoch": 0.069164265129683,
      "grad_norm": 0.42161595821380615,
      "learning_rate": 0.0002,
      "loss": 0.3636,
      "step": 168
    },
    {
      "epoch": 0.0708110333470564,
      "grad_norm": 0.3453030288219452,
      "learning_rate": 0.0002,
      "loss": 0.3402,
      "step": 172
    },
    {
      "epoch": 0.07245780156442981,
      "grad_norm": 2.319596767425537,
      "learning_rate": 0.0002,
      "loss": 0.5047,
      "step": 176
    },
    {
      "epoch": 0.07410456978180321,
      "grad_norm": 0.3278649151325226,
      "learning_rate": 0.0002,
      "loss": 0.3978,
      "step": 180
    },
    {
      "epoch": 0.07575133799917662,
      "grad_norm": 0.5178958773612976,
      "learning_rate": 0.0002,
      "loss": 0.4057,
      "step": 184
    },
    {
      "epoch": 0.07739810621655002,
      "grad_norm": 0.2471940517425537,
      "learning_rate": 0.0002,
      "loss": 0.3383,
      "step": 188
    },
    {
      "epoch": 0.07904487443392343,
      "grad_norm": 0.28006836771965027,
      "learning_rate": 0.0002,
      "loss": 0.3455,
      "step": 192
    },
    {
      "epoch": 0.08069164265129683,
      "grad_norm": 0.38219529390335083,
      "learning_rate": 0.0002,
      "loss": 0.3622,
      "step": 196
    },
    {
      "epoch": 0.08233841086867023,
      "grad_norm": 0.4880613088607788,
      "learning_rate": 0.0002,
      "loss": 0.3748,
      "step": 200
    },
    {
      "epoch": 0.08398517908604364,
      "grad_norm": 0.35214322805404663,
      "learning_rate": 0.0002,
      "loss": 0.3906,
      "step": 204
    },
    {
      "epoch": 0.08563194730341704,
      "grad_norm": 0.4287274479866028,
      "learning_rate": 0.0002,
      "loss": 0.4119,
      "step": 208
    },
    {
      "epoch": 0.08727871552079045,
      "grad_norm": 0.2343526929616928,
      "learning_rate": 0.0002,
      "loss": 0.3821,
      "step": 212
    },
    {
      "epoch": 0.08892548373816385,
      "grad_norm": 0.3329123556613922,
      "learning_rate": 0.0002,
      "loss": 0.3515,
      "step": 216
    },
    {
      "epoch": 0.09057225195553725,
      "grad_norm": 0.45170557498931885,
      "learning_rate": 0.0002,
      "loss": 0.4265,
      "step": 220
    },
    {
      "epoch": 0.09221902017291066,
      "grad_norm": 0.330639123916626,
      "learning_rate": 0.0002,
      "loss": 0.384,
      "step": 224
    },
    {
      "epoch": 0.09386578839028406,
      "grad_norm": 0.1902407705783844,
      "learning_rate": 0.0002,
      "loss": 0.3526,
      "step": 228
    },
    {
      "epoch": 0.09551255660765748,
      "grad_norm": 0.3268851339817047,
      "learning_rate": 0.0002,
      "loss": 0.3612,
      "step": 232
    },
    {
      "epoch": 0.09715932482503088,
      "grad_norm": 0.5299010872840881,
      "learning_rate": 0.0002,
      "loss": 0.3665,
      "step": 236
    },
    {
      "epoch": 0.09880609304240429,
      "grad_norm": 0.3987724184989929,
      "learning_rate": 0.0002,
      "loss": 0.3799,
      "step": 240
    },
    {
      "epoch": 0.10045286125977769,
      "grad_norm": 0.2613527178764343,
      "learning_rate": 0.0002,
      "loss": 0.3579,
      "step": 244
    },
    {
      "epoch": 0.1020996294771511,
      "grad_norm": 0.37342676520347595,
      "learning_rate": 0.0002,
      "loss": 0.3912,
      "step": 248
    },
    {
      "epoch": 0.1037463976945245,
      "grad_norm": 0.3383709490299225,
      "learning_rate": 0.0002,
      "loss": 0.406,
      "step": 252
    },
    {
      "epoch": 0.1053931659118979,
      "grad_norm": 0.23550820350646973,
      "learning_rate": 0.0002,
      "loss": 0.3788,
      "step": 256
    },
    {
      "epoch": 0.1070399341292713,
      "grad_norm": 0.3194361627101898,
      "learning_rate": 0.0002,
      "loss": 0.3729,
      "step": 260
    },
    {
      "epoch": 0.10868670234664471,
      "grad_norm": 0.8462342023849487,
      "learning_rate": 0.0002,
      "loss": 0.3411,
      "step": 264
    },
    {
      "epoch": 0.11033347056401811,
      "grad_norm": 0.558782160282135,
      "learning_rate": 0.0002,
      "loss": 0.3922,
      "step": 268
    },
    {
      "epoch": 0.11198023878139152,
      "grad_norm": 0.24560636281967163,
      "learning_rate": 0.0002,
      "loss": 0.3578,
      "step": 272
    },
    {
      "epoch": 0.11362700699876492,
      "grad_norm": 0.32584550976753235,
      "learning_rate": 0.0002,
      "loss": 0.3313,
      "step": 276
    },
    {
      "epoch": 0.11527377521613832,
      "grad_norm": 0.29577043652534485,
      "learning_rate": 0.0002,
      "loss": 0.3522,
      "step": 280
    },
    {
      "epoch": 0.11692054343351173,
      "grad_norm": 0.47984978556632996,
      "learning_rate": 0.0002,
      "loss": 0.3596,
      "step": 284
    },
    {
      "epoch": 0.11856731165088513,
      "grad_norm": 0.29009076952934265,
      "learning_rate": 0.0002,
      "loss": 0.3895,
      "step": 288
    },
    {
      "epoch": 0.12021407986825854,
      "grad_norm": 0.2614005506038666,
      "learning_rate": 0.0002,
      "loss": 0.3597,
      "step": 292
    },
    {
      "epoch": 0.12186084808563195,
      "grad_norm": 0.379079133272171,
      "learning_rate": 0.0002,
      "loss": 0.3866,
      "step": 296
    },
    {
      "epoch": 0.12350761630300536,
      "grad_norm": 0.17416591942310333,
      "learning_rate": 0.0002,
      "loss": 0.3773,
      "step": 300
    },
    {
      "epoch": 0.12515438452037875,
      "grad_norm": 0.2912764549255371,
      "learning_rate": 0.0002,
      "loss": 0.365,
      "step": 304
    },
    {
      "epoch": 0.12680115273775217,
      "grad_norm": 0.3341335654258728,
      "learning_rate": 0.0002,
      "loss": 0.3425,
      "step": 308
    },
    {
      "epoch": 0.12844792095512556,
      "grad_norm": 0.2572537660598755,
      "learning_rate": 0.0002,
      "loss": 0.3515,
      "step": 312
    },
    {
      "epoch": 0.13009468917249897,
      "grad_norm": 0.19273734092712402,
      "learning_rate": 0.0002,
      "loss": 0.3873,
      "step": 316
    },
    {
      "epoch": 0.13174145738987236,
      "grad_norm": 0.34613487124443054,
      "learning_rate": 0.0002,
      "loss": 0.3683,
      "step": 320
    },
    {
      "epoch": 0.13338822560724578,
      "grad_norm": 0.33817189931869507,
      "learning_rate": 0.0002,
      "loss": 0.3599,
      "step": 324
    },
    {
      "epoch": 0.1350349938246192,
      "grad_norm": 0.41500359773635864,
      "learning_rate": 0.0002,
      "loss": 0.3436,
      "step": 328
    },
    {
      "epoch": 0.1366817620419926,
      "grad_norm": 0.35156941413879395,
      "learning_rate": 0.0002,
      "loss": 0.352,
      "step": 332
    },
    {
      "epoch": 0.138328530259366,
      "grad_norm": 0.3244033455848694,
      "learning_rate": 0.0002,
      "loss": 0.3489,
      "step": 336
    },
    {
      "epoch": 0.1399752984767394,
      "grad_norm": 0.4915976822376251,
      "learning_rate": 0.0002,
      "loss": 0.3834,
      "step": 340
    },
    {
      "epoch": 0.1416220666941128,
      "grad_norm": 0.595040500164032,
      "learning_rate": 0.0002,
      "loss": 0.375,
      "step": 344
    },
    {
      "epoch": 0.1432688349114862,
      "grad_norm": 0.3264763057231903,
      "learning_rate": 0.0002,
      "loss": 0.3261,
      "step": 348
    },
    {
      "epoch": 0.14491560312885962,
      "grad_norm": 0.5096532702445984,
      "learning_rate": 0.0002,
      "loss": 0.3651,
      "step": 352
    },
    {
      "epoch": 0.146562371346233,
      "grad_norm": 0.6608021855354309,
      "learning_rate": 0.0002,
      "loss": 0.3675,
      "step": 356
    },
    {
      "epoch": 0.14820913956360643,
      "grad_norm": 0.2926951050758362,
      "learning_rate": 0.0002,
      "loss": 0.4021,
      "step": 360
    },
    {
      "epoch": 0.14985590778097982,
      "grad_norm": 0.42783549427986145,
      "learning_rate": 0.0002,
      "loss": 0.3448,
      "step": 364
    },
    {
      "epoch": 0.15150267599835324,
      "grad_norm": 0.33004024624824524,
      "learning_rate": 0.0002,
      "loss": 0.3812,
      "step": 368
    },
    {
      "epoch": 0.15314944421572663,
      "grad_norm": 0.3624507188796997,
      "learning_rate": 0.0002,
      "loss": 0.3618,
      "step": 372
    },
    {
      "epoch": 0.15479621243310004,
      "grad_norm": 0.3344748318195343,
      "learning_rate": 0.0002,
      "loss": 0.3853,
      "step": 376
    },
    {
      "epoch": 0.15644298065047343,
      "grad_norm": 0.343755841255188,
      "learning_rate": 0.0002,
      "loss": 0.332,
      "step": 380
    },
    {
      "epoch": 0.15808974886784685,
      "grad_norm": 0.5197455883026123,
      "learning_rate": 0.0002,
      "loss": 0.4023,
      "step": 384
    },
    {
      "epoch": 0.15973651708522024,
      "grad_norm": 0.29629090428352356,
      "learning_rate": 0.0002,
      "loss": 0.3549,
      "step": 388
    },
    {
      "epoch": 0.16138328530259366,
      "grad_norm": 0.16533423960208893,
      "learning_rate": 0.0002,
      "loss": 0.3743,
      "step": 392
    },
    {
      "epoch": 0.16303005351996708,
      "grad_norm": 0.25626063346862793,
      "learning_rate": 0.0002,
      "loss": 0.364,
      "step": 396
    },
    {
      "epoch": 0.16467682173734047,
      "grad_norm": 0.31135621666908264,
      "learning_rate": 0.0002,
      "loss": 0.3454,
      "step": 400
    },
    {
      "epoch": 0.16632358995471389,
      "grad_norm": 0.3969805836677551,
      "learning_rate": 0.0002,
      "loss": 0.3623,
      "step": 404
    },
    {
      "epoch": 0.16797035817208728,
      "grad_norm": 0.35962575674057007,
      "learning_rate": 0.0002,
      "loss": 0.3706,
      "step": 408
    },
    {
      "epoch": 0.1696171263894607,
      "grad_norm": 0.36572885513305664,
      "learning_rate": 0.0002,
      "loss": 0.3462,
      "step": 412
    },
    {
      "epoch": 0.17126389460683408,
      "grad_norm": 0.4497930705547333,
      "learning_rate": 0.0002,
      "loss": 0.4298,
      "step": 416
    },
    {
      "epoch": 0.1729106628242075,
      "grad_norm": 0.4056977331638336,
      "learning_rate": 0.0002,
      "loss": 0.4171,
      "step": 420
    },
    {
      "epoch": 0.1745574310415809,
      "grad_norm": 0.3339053988456726,
      "learning_rate": 0.0002,
      "loss": 0.3756,
      "step": 424
    },
    {
      "epoch": 0.1762041992589543,
      "grad_norm": 0.38297727704048157,
      "learning_rate": 0.0002,
      "loss": 0.4004,
      "step": 428
    },
    {
      "epoch": 0.1778509674763277,
      "grad_norm": 0.2339114397764206,
      "learning_rate": 0.0002,
      "loss": 0.3696,
      "step": 432
    },
    {
      "epoch": 0.17949773569370112,
      "grad_norm": 0.3464541733264923,
      "learning_rate": 0.0002,
      "loss": 0.3948,
      "step": 436
    },
    {
      "epoch": 0.1811445039110745,
      "grad_norm": 0.2537291944026947,
      "learning_rate": 0.0002,
      "loss": 0.3155,
      "step": 440
    },
    {
      "epoch": 0.18279127212844792,
      "grad_norm": 0.36388587951660156,
      "learning_rate": 0.0002,
      "loss": 0.3821,
      "step": 444
    },
    {
      "epoch": 0.1844380403458213,
      "grad_norm": 0.3073045015335083,
      "learning_rate": 0.0002,
      "loss": 0.3446,
      "step": 448
    },
    {
      "epoch": 0.18608480856319473,
      "grad_norm": 0.29027312994003296,
      "learning_rate": 0.0002,
      "loss": 0.3555,
      "step": 452
    },
    {
      "epoch": 0.18773157678056812,
      "grad_norm": 0.24101793766021729,
      "learning_rate": 0.0002,
      "loss": 0.3449,
      "step": 456
    },
    {
      "epoch": 0.18937834499794154,
      "grad_norm": 0.25319597125053406,
      "learning_rate": 0.0002,
      "loss": 0.3453,
      "step": 460
    },
    {
      "epoch": 0.19102511321531496,
      "grad_norm": 0.21023103594779968,
      "learning_rate": 0.0002,
      "loss": 0.3476,
      "step": 464
    },
    {
      "epoch": 0.19267188143268835,
      "grad_norm": 0.35161590576171875,
      "learning_rate": 0.0002,
      "loss": 0.3596,
      "step": 468
    },
    {
      "epoch": 0.19431864965006176,
      "grad_norm": 0.3231665790081024,
      "learning_rate": 0.0002,
      "loss": 0.3943,
      "step": 472
    },
    {
      "epoch": 0.19596541786743515,
      "grad_norm": 0.2584836483001709,
      "learning_rate": 0.0002,
      "loss": 0.3618,
      "step": 476
    },
    {
      "epoch": 0.19761218608480857,
      "grad_norm": 0.5873728394508362,
      "learning_rate": 0.0002,
      "loss": 0.3601,
      "step": 480
    },
    {
      "epoch": 0.19925895430218196,
      "grad_norm": 0.37877875566482544,
      "learning_rate": 0.0002,
      "loss": 0.2994,
      "step": 484
    },
    {
      "epoch": 0.20090572251955538,
      "grad_norm": 0.40954428911209106,
      "learning_rate": 0.0002,
      "loss": 0.3881,
      "step": 488
    },
    {
      "epoch": 0.20255249073692877,
      "grad_norm": 0.3592691719532013,
      "learning_rate": 0.0002,
      "loss": 0.3803,
      "step": 492
    },
    {
      "epoch": 0.2041992589543022,
      "grad_norm": 0.6396195292472839,
      "learning_rate": 0.0002,
      "loss": 0.4616,
      "step": 496
    },
    {
      "epoch": 0.20584602717167558,
      "grad_norm": 0.41789042949676514,
      "learning_rate": 0.0002,
      "loss": 0.3382,
      "step": 500
    },
    {
      "epoch": 0.207492795389049,
      "grad_norm": 0.8054398894309998,
      "learning_rate": 0.0002,
      "loss": 0.3984,
      "step": 504
    },
    {
      "epoch": 0.20913956360642239,
      "grad_norm": 0.3785901665687561,
      "learning_rate": 0.0002,
      "loss": 0.3625,
      "step": 508
    },
    {
      "epoch": 0.2107863318237958,
      "grad_norm": 0.36928969621658325,
      "learning_rate": 0.0002,
      "loss": 0.3746,
      "step": 512
    },
    {
      "epoch": 0.2124331000411692,
      "grad_norm": 0.37541359663009644,
      "learning_rate": 0.0002,
      "loss": 0.4138,
      "step": 516
    },
    {
      "epoch": 0.2140798682585426,
      "grad_norm": 0.5162031650543213,
      "learning_rate": 0.0002,
      "loss": 0.3852,
      "step": 520
    },
    {
      "epoch": 0.21572663647591603,
      "grad_norm": 0.3314428925514221,
      "learning_rate": 0.0002,
      "loss": 0.3621,
      "step": 524
    },
    {
      "epoch": 0.21737340469328942,
      "grad_norm": 0.5314354300498962,
      "learning_rate": 0.0002,
      "loss": 0.4387,
      "step": 528
    },
    {
      "epoch": 0.21902017291066284,
      "grad_norm": 0.3398245573043823,
      "learning_rate": 0.0002,
      "loss": 0.3846,
      "step": 532
    },
    {
      "epoch": 0.22066694112803623,
      "grad_norm": 0.28560298681259155,
      "learning_rate": 0.0002,
      "loss": 0.3634,
      "step": 536
    },
    {
      "epoch": 0.22231370934540964,
      "grad_norm": 0.27383607625961304,
      "learning_rate": 0.0002,
      "loss": 0.3485,
      "step": 540
    },
    {
      "epoch": 0.22396047756278303,
      "grad_norm": 0.4186703562736511,
      "learning_rate": 0.0002,
      "loss": 0.3729,
      "step": 544
    },
    {
      "epoch": 0.22560724578015645,
      "grad_norm": 0.4143611192703247,
      "learning_rate": 0.0002,
      "loss": 0.3882,
      "step": 548
    },
    {
      "epoch": 0.22725401399752984,
      "grad_norm": 0.4646351635456085,
      "learning_rate": 0.0002,
      "loss": 0.4018,
      "step": 552
    },
    {
      "epoch": 0.22890078221490326,
      "grad_norm": 0.3014436960220337,
      "learning_rate": 0.0002,
      "loss": 0.3779,
      "step": 556
    },
    {
      "epoch": 0.23054755043227665,
      "grad_norm": 0.29496312141418457,
      "learning_rate": 0.0002,
      "loss": 0.3634,
      "step": 560
    },
    {
      "epoch": 0.23219431864965007,
      "grad_norm": 0.17998939752578735,
      "learning_rate": 0.0002,
      "loss": 0.3265,
      "step": 564
    },
    {
      "epoch": 0.23384108686702346,
      "grad_norm": 0.3189595937728882,
      "learning_rate": 0.0002,
      "loss": 0.3868,
      "step": 568
    },
    {
      "epoch": 0.23548785508439687,
      "grad_norm": 0.32916879653930664,
      "learning_rate": 0.0002,
      "loss": 0.3122,
      "step": 572
    },
    {
      "epoch": 0.23713462330177026,
      "grad_norm": 0.44192901253700256,
      "learning_rate": 0.0002,
      "loss": 0.4039,
      "step": 576
    },
    {
      "epoch": 0.23878139151914368,
      "grad_norm": 0.3216501474380493,
      "learning_rate": 0.0002,
      "loss": 0.3455,
      "step": 580
    },
    {
      "epoch": 0.24042815973651707,
      "grad_norm": 0.45848771929740906,
      "learning_rate": 0.0002,
      "loss": 0.3973,
      "step": 584
    },
    {
      "epoch": 0.2420749279538905,
      "grad_norm": 0.431364506483078,
      "learning_rate": 0.0002,
      "loss": 0.4,
      "step": 588
    },
    {
      "epoch": 0.2437216961712639,
      "grad_norm": 0.20512379705905914,
      "learning_rate": 0.0002,
      "loss": 0.3254,
      "step": 592
    },
    {
      "epoch": 0.2453684643886373,
      "grad_norm": 0.45757392048835754,
      "learning_rate": 0.0002,
      "loss": 0.3932,
      "step": 596
    },
    {
      "epoch": 0.24701523260601072,
      "grad_norm": 0.29159244894981384,
      "learning_rate": 0.0002,
      "loss": 0.3848,
      "step": 600
    },
    {
      "epoch": 0.2486620008233841,
      "grad_norm": 0.23504222929477692,
      "learning_rate": 0.0002,
      "loss": 0.3555,
      "step": 604
    },
    {
      "epoch": 0.2503087690407575,
      "grad_norm": 0.33391910791397095,
      "learning_rate": 0.0002,
      "loss": 0.3494,
      "step": 608
    },
    {
      "epoch": 0.2519555372581309,
      "grad_norm": 0.3338538706302643,
      "learning_rate": 0.0002,
      "loss": 0.3185,
      "step": 612
    },
    {
      "epoch": 0.25360230547550433,
      "grad_norm": 0.3252895176410675,
      "learning_rate": 0.0002,
      "loss": 0.3613,
      "step": 616
    },
    {
      "epoch": 0.25524907369287775,
      "grad_norm": 0.3765605092048645,
      "learning_rate": 0.0002,
      "loss": 0.3782,
      "step": 620
    },
    {
      "epoch": 0.2568958419102511,
      "grad_norm": 0.28585657477378845,
      "learning_rate": 0.0002,
      "loss": 0.3586,
      "step": 624
    },
    {
      "epoch": 0.25854261012762453,
      "grad_norm": 0.3525017201900482,
      "learning_rate": 0.0002,
      "loss": 0.355,
      "step": 628
    },
    {
      "epoch": 0.26018937834499795,
      "grad_norm": 0.5153087377548218,
      "learning_rate": 0.0002,
      "loss": 0.3512,
      "step": 632
    },
    {
      "epoch": 0.26183614656237136,
      "grad_norm": 0.4493424892425537,
      "learning_rate": 0.0002,
      "loss": 0.3709,
      "step": 636
    },
    {
      "epoch": 0.2634829147797447,
      "grad_norm": 0.2840404510498047,
      "learning_rate": 0.0002,
      "loss": 0.3733,
      "step": 640
    },
    {
      "epoch": 0.26512968299711814,
      "grad_norm": 0.25880661606788635,
      "learning_rate": 0.0002,
      "loss": 0.4248,
      "step": 644
    },
    {
      "epoch": 0.26677645121449156,
      "grad_norm": 0.34614700078964233,
      "learning_rate": 0.0002,
      "loss": 0.358,
      "step": 648
    },
    {
      "epoch": 0.268423219431865,
      "grad_norm": 0.3996017873287201,
      "learning_rate": 0.0002,
      "loss": 0.38,
      "step": 652
    },
    {
      "epoch": 0.2700699876492384,
      "grad_norm": 0.33780571818351746,
      "learning_rate": 0.0002,
      "loss": 0.4254,
      "step": 656
    },
    {
      "epoch": 0.27171675586661176,
      "grad_norm": 0.2469349503517151,
      "learning_rate": 0.0002,
      "loss": 0.3837,
      "step": 660
    },
    {
      "epoch": 0.2733635240839852,
      "grad_norm": 0.3020316958427429,
      "learning_rate": 0.0002,
      "loss": 0.3575,
      "step": 664
    },
    {
      "epoch": 0.2750102923013586,
      "grad_norm": 0.39028212428092957,
      "learning_rate": 0.0002,
      "loss": 0.368,
      "step": 668
    },
    {
      "epoch": 0.276657060518732,
      "grad_norm": 0.23725393414497375,
      "learning_rate": 0.0002,
      "loss": 0.456,
      "step": 672
    },
    {
      "epoch": 0.2783038287361054,
      "grad_norm": 0.3587561845779419,
      "learning_rate": 0.0002,
      "loss": 0.3459,
      "step": 676
    },
    {
      "epoch": 0.2799505969534788,
      "grad_norm": 0.45671024918556213,
      "learning_rate": 0.0002,
      "loss": 0.4069,
      "step": 680
    },
    {
      "epoch": 0.2815973651708522,
      "grad_norm": 0.43547502160072327,
      "learning_rate": 0.0002,
      "loss": 0.3693,
      "step": 684
    },
    {
      "epoch": 0.2832441333882256,
      "grad_norm": 0.31809914112091064,
      "learning_rate": 0.0002,
      "loss": 0.3519,
      "step": 688
    },
    {
      "epoch": 0.284890901605599,
      "grad_norm": 0.4354214668273926,
      "learning_rate": 0.0002,
      "loss": 0.355,
      "step": 692
    },
    {
      "epoch": 0.2865376698229724,
      "grad_norm": 0.3542259633541107,
      "learning_rate": 0.0002,
      "loss": 0.3854,
      "step": 696
    },
    {
      "epoch": 0.2881844380403458,
      "grad_norm": 0.31998395919799805,
      "learning_rate": 0.0002,
      "loss": 0.3586,
      "step": 700
    },
    {
      "epoch": 0.28983120625771924,
      "grad_norm": 0.3070733845233917,
      "learning_rate": 0.0002,
      "loss": 0.3362,
      "step": 704
    },
    {
      "epoch": 0.2914779744750926,
      "grad_norm": 0.3756466209888458,
      "learning_rate": 0.0002,
      "loss": 0.3572,
      "step": 708
    },
    {
      "epoch": 0.293124742692466,
      "grad_norm": 0.5045058131217957,
      "learning_rate": 0.0002,
      "loss": 0.3886,
      "step": 712
    },
    {
      "epoch": 0.29477151090983944,
      "grad_norm": 0.49769386649131775,
      "learning_rate": 0.0002,
      "loss": 0.3932,
      "step": 716
    },
    {
      "epoch": 0.29641827912721286,
      "grad_norm": 0.3411276638507843,
      "learning_rate": 0.0002,
      "loss": 0.3513,
      "step": 720
    },
    {
      "epoch": 0.2980650473445863,
      "grad_norm": 0.17998747527599335,
      "learning_rate": 0.0002,
      "loss": 0.3293,
      "step": 724
    },
    {
      "epoch": 0.29971181556195964,
      "grad_norm": 0.5225507616996765,
      "learning_rate": 0.0002,
      "loss": 0.3985,
      "step": 728
    },
    {
      "epoch": 0.30135858377933306,
      "grad_norm": 0.3224283456802368,
      "learning_rate": 0.0002,
      "loss": 0.3791,
      "step": 732
    },
    {
      "epoch": 0.3030053519967065,
      "grad_norm": 0.3151153028011322,
      "learning_rate": 0.0002,
      "loss": 0.335,
      "step": 736
    },
    {
      "epoch": 0.3046521202140799,
      "grad_norm": 0.27512961626052856,
      "learning_rate": 0.0002,
      "loss": 0.3225,
      "step": 740
    },
    {
      "epoch": 0.30629888843145325,
      "grad_norm": 0.48961198329925537,
      "learning_rate": 0.0002,
      "loss": 0.3305,
      "step": 744
    },
    {
      "epoch": 0.30794565664882667,
      "grad_norm": 0.6176120638847351,
      "learning_rate": 0.0002,
      "loss": 0.4045,
      "step": 748
    },
    {
      "epoch": 0.3095924248662001,
      "grad_norm": 0.42022645473480225,
      "learning_rate": 0.0002,
      "loss": 0.3803,
      "step": 752
    },
    {
      "epoch": 0.3112391930835735,
      "grad_norm": 0.2890242338180542,
      "learning_rate": 0.0002,
      "loss": 0.3744,
      "step": 756
    },
    {
      "epoch": 0.31288596130094687,
      "grad_norm": 0.3050364851951599,
      "learning_rate": 0.0002,
      "loss": 0.3655,
      "step": 760
    },
    {
      "epoch": 0.3145327295183203,
      "grad_norm": 0.2680593430995941,
      "learning_rate": 0.0002,
      "loss": 0.3557,
      "step": 764
    },
    {
      "epoch": 0.3161794977356937,
      "grad_norm": 0.7212200164794922,
      "learning_rate": 0.0002,
      "loss": 0.4029,
      "step": 768
    },
    {
      "epoch": 0.3178262659530671,
      "grad_norm": 0.5011200308799744,
      "learning_rate": 0.0002,
      "loss": 0.3927,
      "step": 772
    },
    {
      "epoch": 0.3194730341704405,
      "grad_norm": 0.44199439883232117,
      "learning_rate": 0.0002,
      "loss": 0.3531,
      "step": 776
    },
    {
      "epoch": 0.3211198023878139,
      "grad_norm": 0.3872445821762085,
      "learning_rate": 0.0002,
      "loss": 0.3475,
      "step": 780
    },
    {
      "epoch": 0.3227665706051873,
      "grad_norm": 0.2929086685180664,
      "learning_rate": 0.0002,
      "loss": 0.3831,
      "step": 784
    },
    {
      "epoch": 0.32441333882256074,
      "grad_norm": 0.36971160769462585,
      "learning_rate": 0.0002,
      "loss": 0.3578,
      "step": 788
    },
    {
      "epoch": 0.32606010703993416,
      "grad_norm": 0.509065568447113,
      "learning_rate": 0.0002,
      "loss": 0.3796,
      "step": 792
    },
    {
      "epoch": 0.3277068752573075,
      "grad_norm": 0.3227056562900543,
      "learning_rate": 0.0002,
      "loss": 0.3966,
      "step": 796
    },
    {
      "epoch": 0.32935364347468093,
      "grad_norm": 0.4549015164375305,
      "learning_rate": 0.0002,
      "loss": 0.3564,
      "step": 800
    }
  ],
  "logging_steps": 4,
  "max_steps": 800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.88348602105856e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}