{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8485362749257531,
  "eval_steps": 600,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00848536274925753,
      "grad_norm": 0.4898678891363344,
      "learning_rate": 8.488964346349746e-07,
      "loss": 1.8056,
      "step": 10
    },
    {
      "epoch": 0.01697072549851506,
      "grad_norm": 0.3537473179717183,
      "learning_rate": 1.6977928692699491e-06,
      "loss": 1.7621,
      "step": 20
    },
    {
      "epoch": 0.025456088247772592,
      "grad_norm": 0.28215953004159977,
      "learning_rate": 2.546689303904924e-06,
      "loss": 1.7571,
      "step": 30
    },
    {
      "epoch": 0.03394145099703012,
      "grad_norm": 0.27446565146764923,
      "learning_rate": 3.3955857385398982e-06,
      "loss": 1.7136,
      "step": 40
    },
    {
      "epoch": 0.04242681374628765,
      "grad_norm": 0.17051549768176558,
      "learning_rate": 4.244482173174873e-06,
      "loss": 1.6767,
      "step": 50
    },
    {
      "epoch": 0.050912176495545185,
      "grad_norm": 0.17763882467320422,
      "learning_rate": 5.093378607809848e-06,
      "loss": 1.6371,
      "step": 60
    },
    {
      "epoch": 0.05939753924480271,
      "grad_norm": 0.14311462596290048,
      "learning_rate": 5.942275042444822e-06,
      "loss": 1.6324,
      "step": 70
    },
    {
      "epoch": 0.06788290199406025,
      "grad_norm": 0.1659540846071645,
      "learning_rate": 6.7911714770797965e-06,
      "loss": 1.6062,
      "step": 80
    },
    {
      "epoch": 0.07636826474331777,
      "grad_norm": 0.20064072815620043,
      "learning_rate": 7.640067911714771e-06,
      "loss": 1.5832,
      "step": 90
    },
    {
      "epoch": 0.0848536274925753,
      "grad_norm": 0.2179045681711979,
      "learning_rate": 8.488964346349745e-06,
      "loss": 1.5898,
      "step": 100
    },
    {
      "epoch": 0.09333899024183284,
      "grad_norm": 0.23866012053128668,
      "learning_rate": 9.337860780984721e-06,
      "loss": 1.5924,
      "step": 110
    },
    {
      "epoch": 0.10182435299109037,
      "grad_norm": 0.18578051776430282,
      "learning_rate": 1.0186757215619695e-05,
      "loss": 1.5877,
      "step": 120
    },
    {
      "epoch": 0.1103097157403479,
      "grad_norm": 0.2216509707409362,
      "learning_rate": 1.103565365025467e-05,
      "loss": 1.5947,
      "step": 130
    },
    {
      "epoch": 0.11879507848960542,
      "grad_norm": 0.20427142255694086,
      "learning_rate": 1.1884550084889643e-05,
      "loss": 1.5841,
      "step": 140
    },
    {
      "epoch": 0.12728044123886295,
      "grad_norm": 0.1765851415675038,
      "learning_rate": 1.2733446519524619e-05,
      "loss": 1.5878,
      "step": 150
    },
    {
      "epoch": 0.1357658039881205,
      "grad_norm": 0.1769355117060811,
      "learning_rate": 1.3582342954159593e-05,
      "loss": 1.5795,
      "step": 160
    },
    {
      "epoch": 0.14425116673737803,
      "grad_norm": 0.1617675663096666,
      "learning_rate": 1.4431239388794569e-05,
      "loss": 1.5549,
      "step": 170
    },
    {
      "epoch": 0.15273652948663555,
      "grad_norm": 0.17302259072151574,
      "learning_rate": 1.5280135823429543e-05,
      "loss": 1.5808,
      "step": 180
    },
    {
      "epoch": 0.1612218922358931,
      "grad_norm": 0.16876039012432806,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 1.5676,
      "step": 190
    },
    {
      "epoch": 0.1697072549851506,
      "grad_norm": 0.19627360154037596,
      "learning_rate": 1.697792869269949e-05,
      "loss": 1.5598,
      "step": 200
    },
    {
      "epoch": 0.17819261773440814,
      "grad_norm": 0.16078510362361015,
      "learning_rate": 1.7826825127334465e-05,
      "loss": 1.5667,
      "step": 210
    },
    {
      "epoch": 0.18667798048366568,
      "grad_norm": 0.16044786518959703,
      "learning_rate": 1.8675721561969442e-05,
      "loss": 1.5815,
      "step": 220
    },
    {
      "epoch": 0.1951633432329232,
      "grad_norm": 0.15656958873834717,
      "learning_rate": 1.9524617996604416e-05,
      "loss": 1.5576,
      "step": 230
    },
    {
      "epoch": 0.20364870598218074,
      "grad_norm": 0.1687290471357602,
      "learning_rate": 2.037351443123939e-05,
      "loss": 1.5453,
      "step": 240
    },
    {
      "epoch": 0.21213406873143828,
      "grad_norm": 0.1519017348276184,
      "learning_rate": 2.1222410865874364e-05,
      "loss": 1.5554,
      "step": 250
    },
    {
      "epoch": 0.2206194314806958,
      "grad_norm": 0.15761892005160086,
      "learning_rate": 2.207130730050934e-05,
      "loss": 1.5494,
      "step": 260
    },
    {
      "epoch": 0.22910479422995333,
      "grad_norm": 0.16857088482977495,
      "learning_rate": 2.2920203735144312e-05,
      "loss": 1.5794,
      "step": 270
    },
    {
      "epoch": 0.23759015697921085,
      "grad_norm": 0.1678705209913503,
      "learning_rate": 2.3769100169779286e-05,
      "loss": 1.5373,
      "step": 280
    },
    {
      "epoch": 0.2460755197284684,
      "grad_norm": 0.14812649566587394,
      "learning_rate": 2.461799660441426e-05,
      "loss": 1.5504,
      "step": 290
    },
    {
      "epoch": 0.2545608824777259,
      "grad_norm": 0.17651916734325857,
      "learning_rate": 2.5466893039049238e-05,
      "loss": 1.5607,
      "step": 300
    },
    {
      "epoch": 0.26304624522698344,
      "grad_norm": 0.14883055338507856,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 1.5311,
      "step": 310
    },
    {
      "epoch": 0.271531607976241,
      "grad_norm": 0.15787522753231265,
      "learning_rate": 2.7164685908319186e-05,
      "loss": 1.5656,
      "step": 320
    },
    {
      "epoch": 0.2800169707254985,
      "grad_norm": 0.1625232940237689,
      "learning_rate": 2.801358234295416e-05,
      "loss": 1.5686,
      "step": 330
    },
    {
      "epoch": 0.28850233347475607,
      "grad_norm": 0.18505951289343867,
      "learning_rate": 2.8862478777589137e-05,
      "loss": 1.5474,
      "step": 340
    },
    {
      "epoch": 0.29698769622401355,
      "grad_norm": 0.13785772316349984,
      "learning_rate": 2.9711375212224108e-05,
      "loss": 1.5696,
      "step": 350
    },
    {
      "epoch": 0.3054730589732711,
      "grad_norm": 0.13531274658248552,
      "learning_rate": 3.0560271646859086e-05,
      "loss": 1.5551,
      "step": 360
    },
    {
      "epoch": 0.31395842172252864,
      "grad_norm": 0.1366381415368909,
      "learning_rate": 3.140916808149406e-05,
      "loss": 1.524,
      "step": 370
    },
    {
      "epoch": 0.3224437844717862,
      "grad_norm": 0.14587220569353926,
      "learning_rate": 3.2258064516129034e-05,
      "loss": 1.5515,
      "step": 380
    },
    {
      "epoch": 0.3309291472210437,
      "grad_norm": 0.13336349383744864,
      "learning_rate": 3.310696095076401e-05,
      "loss": 1.5457,
      "step": 390
    },
    {
      "epoch": 0.3394145099703012,
      "grad_norm": 0.1772016947970983,
      "learning_rate": 3.395585738539898e-05,
      "loss": 1.5582,
      "step": 400
    },
    {
      "epoch": 0.34789987271955874,
      "grad_norm": 0.13819420575084573,
      "learning_rate": 3.4804753820033956e-05,
      "loss": 1.5326,
      "step": 410
    },
    {
      "epoch": 0.3563852354688163,
      "grad_norm": 0.12729862167862188,
      "learning_rate": 3.565365025466893e-05,
      "loss": 1.5387,
      "step": 420
    },
    {
      "epoch": 0.3648705982180738,
      "grad_norm": 0.11777082851399363,
      "learning_rate": 3.6502546689303904e-05,
      "loss": 1.5587,
      "step": 430
    },
    {
      "epoch": 0.37335596096733137,
      "grad_norm": 0.15372268131323022,
      "learning_rate": 3.7351443123938885e-05,
      "loss": 1.5362,
      "step": 440
    },
    {
      "epoch": 0.3818413237165889,
      "grad_norm": 0.12616185572252248,
      "learning_rate": 3.820033955857386e-05,
      "loss": 1.5548,
      "step": 450
    },
    {
      "epoch": 0.3903266864658464,
      "grad_norm": 0.1311200786303391,
      "learning_rate": 3.904923599320883e-05,
      "loss": 1.5409,
      "step": 460
    },
    {
      "epoch": 0.39881204921510394,
      "grad_norm": 0.1707919112561785,
      "learning_rate": 3.989813242784381e-05,
      "loss": 1.5509,
      "step": 470
    },
    {
      "epoch": 0.4072974119643615,
      "grad_norm": 0.14660149264284913,
      "learning_rate": 4.074702886247878e-05,
      "loss": 1.5433,
      "step": 480
    },
    {
      "epoch": 0.415782774713619,
      "grad_norm": 0.12478895483834351,
      "learning_rate": 4.1595925297113755e-05,
      "loss": 1.5382,
      "step": 490
    },
    {
      "epoch": 0.42426813746287656,
      "grad_norm": 0.12327957445795817,
      "learning_rate": 4.244482173174873e-05,
      "loss": 1.5515,
      "step": 500
    },
    {
      "epoch": 0.43275350021213405,
      "grad_norm": 0.12922777738650987,
      "learning_rate": 4.32937181663837e-05,
      "loss": 1.5688,
      "step": 510
    },
    {
      "epoch": 0.4412388629613916,
      "grad_norm": 0.12486802189783415,
      "learning_rate": 4.414261460101868e-05,
      "loss": 1.5452,
      "step": 520
    },
    {
      "epoch": 0.44972422571064913,
      "grad_norm": 0.1360610874577123,
      "learning_rate": 4.499151103565366e-05,
      "loss": 1.5493,
      "step": 530
    },
    {
      "epoch": 0.45820958845990667,
      "grad_norm": 0.1884897685356775,
      "learning_rate": 4.5840407470288625e-05,
      "loss": 1.5511,
      "step": 540
    },
    {
      "epoch": 0.4666949512091642,
      "grad_norm": 0.12446302384809525,
      "learning_rate": 4.6689303904923606e-05,
      "loss": 1.5458,
      "step": 550
    },
    {
      "epoch": 0.4751803139584217,
      "grad_norm": 0.13169591804768588,
      "learning_rate": 4.753820033955857e-05,
      "loss": 1.5569,
      "step": 560
    },
    {
      "epoch": 0.48366567670767924,
      "grad_norm": 0.1343809247449631,
      "learning_rate": 4.8387096774193554e-05,
      "loss": 1.5408,
      "step": 570
    },
    {
      "epoch": 0.4921510394569368,
      "grad_norm": 0.14024589853602,
      "learning_rate": 4.923599320882852e-05,
      "loss": 1.5487,
      "step": 580
    },
    {
      "epoch": 0.5006364022061943,
      "grad_norm": 0.16240429253875313,
      "learning_rate": 4.999999560970061e-05,
      "loss": 1.5488,
      "step": 590
    },
    {
      "epoch": 0.5091217649554518,
      "grad_norm": 0.12575424857894482,
      "learning_rate": 4.999946877563971e-05,
      "loss": 1.532,
      "step": 600
    },
    {
      "epoch": 0.5091217649554518,
      "eval_loss": 1.519254446029663,
      "eval_runtime": 53.3242,
      "eval_samples_per_second": 7.145,
      "eval_steps_per_second": 0.9,
      "step": 600
    },
    {
      "epoch": 0.5176071277047094,
      "grad_norm": 0.18688482756329736,
      "learning_rate": 4.999806390290309e-05,
      "loss": 1.5544,
      "step": 610
    },
    {
      "epoch": 0.5260924904539669,
      "grad_norm": 0.12425469431830571,
      "learning_rate": 4.999578104083307e-05,
      "loss": 1.5443,
      "step": 620
    },
    {
      "epoch": 0.5345778532032245,
      "grad_norm": 0.1299027485420099,
      "learning_rate": 4.999262026960902e-05,
      "loss": 1.5569,
      "step": 630
    },
    {
      "epoch": 0.543063215952482,
      "grad_norm": 0.11441754852508934,
      "learning_rate": 4.998858170024449e-05,
      "loss": 1.5316,
      "step": 640
    },
    {
      "epoch": 0.5515485787017395,
      "grad_norm": 0.14888547248976478,
      "learning_rate": 4.998366547458326e-05,
      "loss": 1.5177,
      "step": 650
    },
    {
      "epoch": 0.560033941450997,
      "grad_norm": 0.14859292774768867,
      "learning_rate": 4.997787176529449e-05,
      "loss": 1.5394,
      "step": 660
    },
    {
      "epoch": 0.5685193042002545,
      "grad_norm": 0.12499154376539734,
      "learning_rate": 4.997120077586651e-05,
      "loss": 1.5554,
      "step": 670
    },
    {
      "epoch": 0.5770046669495121,
      "grad_norm": 0.1218974898058821,
      "learning_rate": 4.9963652740599774e-05,
      "loss": 1.5335,
      "step": 680
    },
    {
      "epoch": 0.5854900296987696,
      "grad_norm": 0.1273110498715124,
      "learning_rate": 4.995522792459859e-05,
      "loss": 1.5349,
      "step": 690
    },
    {
      "epoch": 0.5939753924480271,
      "grad_norm": 0.12115412881719101,
      "learning_rate": 4.994592662376183e-05,
      "loss": 1.5419,
      "step": 700
    },
    {
      "epoch": 0.6024607551972847,
      "grad_norm": 0.14855096330233286,
      "learning_rate": 4.99357491647725e-05,
      "loss": 1.513,
      "step": 710
    },
    {
      "epoch": 0.6109461179465422,
      "grad_norm": 0.11407988659327956,
      "learning_rate": 4.992469590508628e-05,
      "loss": 1.5243,
      "step": 720
    },
    {
      "epoch": 0.6194314806957998,
      "grad_norm": 0.1197712643781127,
      "learning_rate": 4.9912767232919035e-05,
      "loss": 1.5177,
      "step": 730
    },
    {
      "epoch": 0.6279168434450573,
      "grad_norm": 0.12400515877262065,
      "learning_rate": 4.9899963567233074e-05,
      "loss": 1.5619,
      "step": 740
    },
    {
      "epoch": 0.6364022061943148,
      "grad_norm": 0.12250385257708406,
      "learning_rate": 4.988628535772249e-05,
      "loss": 1.539,
      "step": 750
    },
    {
      "epoch": 0.6448875689435724,
      "grad_norm": 0.1262441090496857,
      "learning_rate": 4.987173308479738e-05,
      "loss": 1.5195,
      "step": 760
    },
    {
      "epoch": 0.6533729316928298,
      "grad_norm": 0.12459694416473029,
      "learning_rate": 4.985630725956694e-05,
      "loss": 1.5462,
      "step": 770
    },
    {
      "epoch": 0.6618582944420874,
      "grad_norm": 0.12985189006106762,
      "learning_rate": 4.9840008423821527e-05,
      "loss": 1.5113,
      "step": 780
    },
    {
      "epoch": 0.6703436571913449,
      "grad_norm": 0.12689306141471304,
      "learning_rate": 4.9822837150013636e-05,
      "loss": 1.5201,
      "step": 790
    },
    {
      "epoch": 0.6788290199406024,
      "grad_norm": 0.15393156370587963,
      "learning_rate": 4.980479404123778e-05,
      "loss": 1.5121,
      "step": 800
    },
    {
      "epoch": 0.68731438268986,
      "grad_norm": 0.13213701895207608,
      "learning_rate": 4.978587973120931e-05,
      "loss": 1.5307,
      "step": 810
    },
    {
      "epoch": 0.6957997454391175,
      "grad_norm": 0.11561354931316294,
      "learning_rate": 4.9766094884242184e-05,
      "loss": 1.5316,
      "step": 820
    },
    {
      "epoch": 0.7042851081883751,
      "grad_norm": 0.12414772399330044,
      "learning_rate": 4.974544019522559e-05,
      "loss": 1.5148,
      "step": 830
    },
    {
      "epoch": 0.7127704709376326,
      "grad_norm": 0.1171652849153521,
      "learning_rate": 4.972391638959959e-05,
      "loss": 1.5096,
      "step": 840
    },
    {
      "epoch": 0.7212558336868902,
      "grad_norm": 0.12868937349582316,
      "learning_rate": 4.9701524223329585e-05,
      "loss": 1.5282,
      "step": 850
    },
    {
      "epoch": 0.7297411964361477,
      "grad_norm": 0.1200015077117309,
      "learning_rate": 4.967826448287981e-05,
      "loss": 1.5512,
      "step": 860
    },
    {
      "epoch": 0.7382265591854051,
      "grad_norm": 0.12340885660045105,
      "learning_rate": 4.96541379851857e-05,
      "loss": 1.5394,
      "step": 870
    },
    {
      "epoch": 0.7467119219346627,
      "grad_norm": 0.12976937691467555,
      "learning_rate": 4.962914557762517e-05,
      "loss": 1.51,
      "step": 880
    },
    {
      "epoch": 0.7551972846839202,
      "grad_norm": 0.11912878476038466,
      "learning_rate": 4.9603288137988905e-05,
      "loss": 1.5294,
      "step": 890
    },
    {
      "epoch": 0.7636826474331778,
      "grad_norm": 0.1299625480337927,
      "learning_rate": 4.957656657444947e-05,
      "loss": 1.507,
      "step": 900
    },
    {
      "epoch": 0.7721680101824353,
      "grad_norm": 0.12380144459698468,
      "learning_rate": 4.954898182552946e-05,
      "loss": 1.5376,
      "step": 910
    },
    {
      "epoch": 0.7806533729316928,
      "grad_norm": 0.13139339643682763,
      "learning_rate": 4.9520534860068535e-05,
      "loss": 1.5291,
      "step": 920
    },
    {
      "epoch": 0.7891387356809504,
      "grad_norm": 0.13088956203983898,
      "learning_rate": 4.949122667718935e-05,
      "loss": 1.5239,
      "step": 930
    },
    {
      "epoch": 0.7976240984302079,
      "grad_norm": 0.12586052988453703,
      "learning_rate": 4.94610583062625e-05,
      "loss": 1.5525,
      "step": 940
    },
    {
      "epoch": 0.8061094611794655,
      "grad_norm": 0.12020996031652877,
      "learning_rate": 4.943003080687035e-05,
      "loss": 1.5525,
      "step": 950
    },
    {
      "epoch": 0.814594823928723,
      "grad_norm": 0.12866375954060869,
      "learning_rate": 4.9398145268769856e-05,
      "loss": 1.5266,
      "step": 960
    },
    {
      "epoch": 0.8230801866779804,
      "grad_norm": 0.13166136756817035,
      "learning_rate": 4.936540281185423e-05,
      "loss": 1.5041,
      "step": 970
    },
    {
      "epoch": 0.831565549427238,
      "grad_norm": 0.12481946698483787,
      "learning_rate": 4.933180458611364e-05,
      "loss": 1.5271,
      "step": 980
    },
    {
      "epoch": 0.8400509121764955,
      "grad_norm": 0.12264463761209114,
      "learning_rate": 4.9297351771594844e-05,
      "loss": 1.5354,
      "step": 990
    },
    {
      "epoch": 0.8485362749257531,
      "grad_norm": 0.11985452856537594,
      "learning_rate": 4.926204557835968e-05,
      "loss": 1.5167,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 5890,
  "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": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 840319478267904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}