{
  "best_metric": 0.05326759070158005,
  "best_model_checkpoint": "./output/checkpoint-750",
  "epoch": 0.7560483870967742,
  "eval_steps": 150,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010080645161290322,
      "grad_norm": 4.718156814575195,
      "learning_rate": 1.25e-05,
      "loss": 1.4603,
      "step": 10
    },
    {
      "epoch": 0.020161290322580645,
      "grad_norm": 2.660947561264038,
      "learning_rate": 2.5e-05,
      "loss": 0.9242,
      "step": 20
    },
    {
      "epoch": 0.03024193548387097,
      "grad_norm": 1.879041075706482,
      "learning_rate": 3.75e-05,
      "loss": 0.448,
      "step": 30
    },
    {
      "epoch": 0.04032258064516129,
      "grad_norm": 1.869635820388794,
      "learning_rate": 5e-05,
      "loss": 0.3737,
      "step": 40
    },
    {
      "epoch": 0.05040322580645161,
      "grad_norm": 1.2459924221038818,
      "learning_rate": 6.25e-05,
      "loss": 0.2163,
      "step": 50
    },
    {
      "epoch": 0.06048387096774194,
      "grad_norm": 1.4758652448654175,
      "learning_rate": 7.5e-05,
      "loss": 0.2292,
      "step": 60
    },
    {
      "epoch": 0.07056451612903226,
      "grad_norm": 2.0161190032958984,
      "learning_rate": 8.75e-05,
      "loss": 0.1981,
      "step": 70
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 1.2931406497955322,
      "learning_rate": 0.0001,
      "loss": 0.1827,
      "step": 80
    },
    {
      "epoch": 0.0907258064516129,
      "grad_norm": 1.0741955041885376,
      "learning_rate": 0.00011250000000000001,
      "loss": 0.1407,
      "step": 90
    },
    {
      "epoch": 0.10080645161290322,
      "grad_norm": 1.0442911386489868,
      "learning_rate": 0.000125,
      "loss": 0.1546,
      "step": 100
    },
    {
      "epoch": 0.11088709677419355,
      "grad_norm": 1.0597628355026245,
      "learning_rate": 0.00012499871543489787,
      "loss": 0.102,
      "step": 110
    },
    {
      "epoch": 0.12096774193548387,
      "grad_norm": 0.9368671774864197,
      "learning_rate": 0.00012499486179239495,
      "loss": 0.1541,
      "step": 120
    },
    {
      "epoch": 0.1310483870967742,
      "grad_norm": 0.7519365549087524,
      "learning_rate": 0.00012498843923089938,
      "loss": 0.1643,
      "step": 130
    },
    {
      "epoch": 0.14112903225806453,
      "grad_norm": 0.4844861328601837,
      "learning_rate": 0.0001249794480144175,
      "loss": 0.1243,
      "step": 140
    },
    {
      "epoch": 0.15120967741935484,
      "grad_norm": 0.7643828392028809,
      "learning_rate": 0.000124967888512543,
      "loss": 0.1229,
      "step": 150
    },
    {
      "epoch": 0.15120967741935484,
      "eval_loss": 0.08507546782493591,
      "eval_runtime": 57.5316,
      "eval_samples_per_second": 8.691,
      "eval_steps_per_second": 8.691,
      "step": 150
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 0.47043290734291077,
      "learning_rate": 0.00012495376120044173,
      "loss": 0.1681,
      "step": 160
    },
    {
      "epoch": 0.17137096774193547,
      "grad_norm": 0.6022606492042542,
      "learning_rate": 0.00012493706665883217,
      "loss": 0.1328,
      "step": 170
    },
    {
      "epoch": 0.1814516129032258,
      "grad_norm": 0.5551249980926514,
      "learning_rate": 0.00012491780557396154,
      "loss": 0.1344,
      "step": 180
    },
    {
      "epoch": 0.19153225806451613,
      "grad_norm": 0.8580924868583679,
      "learning_rate": 0.00012489597873757756,
      "loss": 0.1418,
      "step": 190
    },
    {
      "epoch": 0.20161290322580644,
      "grad_norm": 0.5060119032859802,
      "learning_rate": 0.00012487158704689602,
      "loss": 0.1207,
      "step": 200
    },
    {
      "epoch": 0.21169354838709678,
      "grad_norm": 0.5322176218032837,
      "learning_rate": 0.0001248446315045638,
      "loss": 0.0723,
      "step": 210
    },
    {
      "epoch": 0.2217741935483871,
      "grad_norm": 1.1198161840438843,
      "learning_rate": 0.00012481511321861763,
      "loss": 0.1267,
      "step": 220
    },
    {
      "epoch": 0.2318548387096774,
      "grad_norm": 0.317910760641098,
      "learning_rate": 0.00012478303340243864,
      "loss": 0.0905,
      "step": 230
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 0.5275834202766418,
      "learning_rate": 0.00012474839337470246,
      "loss": 0.1228,
      "step": 240
    },
    {
      "epoch": 0.25201612903225806,
      "grad_norm": 0.2738340497016907,
      "learning_rate": 0.0001247111945593249,
      "loss": 0.1433,
      "step": 250
    },
    {
      "epoch": 0.2620967741935484,
      "grad_norm": 0.718310534954071,
      "learning_rate": 0.00012467143848540359,
      "loss": 0.1075,
      "step": 260
    },
    {
      "epoch": 0.2721774193548387,
      "grad_norm": 0.18305560946464539,
      "learning_rate": 0.000124629126787155,
      "loss": 0.1053,
      "step": 270
    },
    {
      "epoch": 0.28225806451612906,
      "grad_norm": 0.48630911111831665,
      "learning_rate": 0.00012458426120384738,
      "loss": 0.107,
      "step": 280
    },
    {
      "epoch": 0.2923387096774194,
      "grad_norm": 0.24452829360961914,
      "learning_rate": 0.00012453684357972906,
      "loss": 0.117,
      "step": 290
    },
    {
      "epoch": 0.3024193548387097,
      "grad_norm": 0.7329663634300232,
      "learning_rate": 0.00012448687586395289,
      "loss": 0.0766,
      "step": 300
    },
    {
      "epoch": 0.3024193548387097,
      "eval_loss": 0.061199020594358444,
      "eval_runtime": 60.0112,
      "eval_samples_per_second": 8.332,
      "eval_steps_per_second": 8.332,
      "step": 300
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.9389004111289978,
      "learning_rate": 0.00012443436011049593,
      "loss": 0.129,
      "step": 310
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.8787228465080261,
      "learning_rate": 0.0001243792984780751,
      "loss": 0.1333,
      "step": 320
    },
    {
      "epoch": 0.3326612903225806,
      "grad_norm": 0.3159072697162628,
      "learning_rate": 0.00012432169323005853,
      "loss": 0.0931,
      "step": 330
    },
    {
      "epoch": 0.34274193548387094,
      "grad_norm": 0.7588217258453369,
      "learning_rate": 0.00012426154673437223,
      "loss": 0.1053,
      "step": 340
    },
    {
      "epoch": 0.3528225806451613,
      "grad_norm": 1.1616908311843872,
      "learning_rate": 0.00012419886146340314,
      "loss": 0.1468,
      "step": 350
    },
    {
      "epoch": 0.3629032258064516,
      "grad_norm": 0.8137270212173462,
      "learning_rate": 0.0001241336399938972,
      "loss": 0.1196,
      "step": 360
    },
    {
      "epoch": 0.37298387096774194,
      "grad_norm": 0.27941054105758667,
      "learning_rate": 0.00012406588500685355,
      "loss": 0.0915,
      "step": 370
    },
    {
      "epoch": 0.38306451612903225,
      "grad_norm": 0.22469285130500793,
      "learning_rate": 0.00012399559928741435,
      "loss": 0.0607,
      "step": 380
    },
    {
      "epoch": 0.39314516129032256,
      "grad_norm": 0.20622070133686066,
      "learning_rate": 0.00012392278572475023,
      "loss": 0.0657,
      "step": 390
    },
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 0.1868823766708374,
      "learning_rate": 0.0001238474473119416,
      "loss": 0.0873,
      "step": 400
    },
    {
      "epoch": 0.41330645161290325,
      "grad_norm": 0.262215793132782,
      "learning_rate": 0.00012376958714585545,
      "loss": 0.0899,
      "step": 410
    },
    {
      "epoch": 0.42338709677419356,
      "grad_norm": 0.8614699840545654,
      "learning_rate": 0.0001236892084270183,
      "loss": 0.0724,
      "step": 420
    },
    {
      "epoch": 0.4334677419354839,
      "grad_norm": 0.917412281036377,
      "learning_rate": 0.00012360631445948448,
      "loss": 0.1351,
      "step": 430
    },
    {
      "epoch": 0.4435483870967742,
      "grad_norm": 0.8552457094192505,
      "learning_rate": 0.00012352090865070026,
      "loss": 0.1108,
      "step": 440
    },
    {
      "epoch": 0.4536290322580645,
      "grad_norm": 0.6661000847816467,
      "learning_rate": 0.00012343299451136397,
      "loss": 0.0681,
      "step": 450
    },
    {
      "epoch": 0.4536290322580645,
      "eval_loss": 0.06194188818335533,
      "eval_runtime": 57.5815,
      "eval_samples_per_second": 8.683,
      "eval_steps_per_second": 8.683,
      "step": 450
    },
    {
      "epoch": 0.4637096774193548,
      "grad_norm": 0.17224998772144318,
      "learning_rate": 0.00012334257565528155,
      "loss": 0.0752,
      "step": 460
    },
    {
      "epoch": 0.4737903225806452,
      "grad_norm": 0.6695602536201477,
      "learning_rate": 0.000123249655799218,
      "loss": 0.1084,
      "step": 470
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.256228506565094,
      "learning_rate": 0.00012315423876274468,
      "loss": 0.0635,
      "step": 480
    },
    {
      "epoch": 0.4939516129032258,
      "grad_norm": 0.25890034437179565,
      "learning_rate": 0.0001230563284680822,
      "loss": 0.0857,
      "step": 490
    },
    {
      "epoch": 0.5040322580645161,
      "grad_norm": 0.20878875255584717,
      "learning_rate": 0.00012295592893993935,
      "loss": 0.0967,
      "step": 500
    },
    {
      "epoch": 0.5141129032258065,
      "grad_norm": 0.23766882717609406,
      "learning_rate": 0.00012285304430534745,
      "loss": 0.1212,
      "step": 510
    },
    {
      "epoch": 0.5241935483870968,
      "grad_norm": 0.18952979147434235,
      "learning_rate": 0.00012274767879349083,
      "loss": 0.0889,
      "step": 520
    },
    {
      "epoch": 0.5342741935483871,
      "grad_norm": 0.4890676736831665,
      "learning_rate": 0.00012263983673553306,
      "loss": 0.09,
      "step": 530
    },
    {
      "epoch": 0.5443548387096774,
      "grad_norm": 0.6612870097160339,
      "learning_rate": 0.0001225295225644387,
      "loss": 0.1209,
      "step": 540
    },
    {
      "epoch": 0.5544354838709677,
      "grad_norm": 0.3861521780490875,
      "learning_rate": 0.0001224167408147913,
      "loss": 0.085,
      "step": 550
    },
    {
      "epoch": 0.5645161290322581,
      "grad_norm": 0.22604888677597046,
      "learning_rate": 0.0001223014961226068,
      "loss": 0.0877,
      "step": 560
    },
    {
      "epoch": 0.5745967741935484,
      "grad_norm": 0.4841513931751251,
      "learning_rate": 0.00012218379322514317,
      "loss": 0.0861,
      "step": 570
    },
    {
      "epoch": 0.5846774193548387,
      "grad_norm": 0.16400082409381866,
      "learning_rate": 0.00012206363696070545,
      "loss": 0.1509,
      "step": 580
    },
    {
      "epoch": 0.594758064516129,
      "grad_norm": 0.14709672331809998,
      "learning_rate": 0.0001219410322684471,
      "loss": 0.0619,
      "step": 590
    },
    {
      "epoch": 0.6048387096774194,
      "grad_norm": 0.17841552197933197,
      "learning_rate": 0.0001218159841881668,
      "loss": 0.0782,
      "step": 600
    },
    {
      "epoch": 0.6048387096774194,
      "eval_loss": 0.053511977195739746,
      "eval_runtime": 58.4751,
      "eval_samples_per_second": 8.551,
      "eval_steps_per_second": 8.551,
      "step": 600
    },
    {
      "epoch": 0.6149193548387096,
      "grad_norm": 0.6630131006240845,
      "learning_rate": 0.00012168849786010133,
      "loss": 0.077,
      "step": 610
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.16494181752204895,
      "learning_rate": 0.00012155857852471433,
      "loss": 0.1101,
      "step": 620
    },
    {
      "epoch": 0.6350806451612904,
      "grad_norm": 0.9052111506462097,
      "learning_rate": 0.0001214262315224808,
      "loss": 0.1151,
      "step": 630
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.7651068568229675,
      "learning_rate": 0.00012129146229366766,
      "loss": 0.1093,
      "step": 640
    },
    {
      "epoch": 0.655241935483871,
      "grad_norm": 0.16763581335544586,
      "learning_rate": 0.00012115427637811003,
      "loss": 0.0711,
      "step": 650
    },
    {
      "epoch": 0.6653225806451613,
      "grad_norm": 0.6529646515846252,
      "learning_rate": 0.00012101467941498357,
      "loss": 0.1042,
      "step": 660
    },
    {
      "epoch": 0.6754032258064516,
      "grad_norm": 0.21442104876041412,
      "learning_rate": 0.0001208726771425727,
      "loss": 0.0624,
      "step": 670
    },
    {
      "epoch": 0.6854838709677419,
      "grad_norm": 0.27069932222366333,
      "learning_rate": 0.00012072827539803463,
      "loss": 0.0808,
      "step": 680
    },
    {
      "epoch": 0.6955645161290323,
      "grad_norm": 0.203572615981102,
      "learning_rate": 0.00012058148011715949,
      "loss": 0.0861,
      "step": 690
    },
    {
      "epoch": 0.7056451612903226,
      "grad_norm": 0.18072012066841125,
      "learning_rate": 0.00012043229733412636,
      "loss": 0.053,
      "step": 700
    },
    {
      "epoch": 0.7157258064516129,
      "grad_norm": 0.62689608335495,
      "learning_rate": 0.0001202807331812551,
      "loss": 0.0998,
      "step": 710
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 0.14409402012825012,
      "learning_rate": 0.00012012679388875441,
      "loss": 0.0709,
      "step": 720
    },
    {
      "epoch": 0.7358870967741935,
      "grad_norm": 0.17387409508228302,
      "learning_rate": 0.00011997048578446568,
      "loss": 0.1087,
      "step": 730
    },
    {
      "epoch": 0.7459677419354839,
      "grad_norm": 0.6958820223808289,
      "learning_rate": 0.00011981181529360282,
      "loss": 0.1266,
      "step": 740
    },
    {
      "epoch": 0.7560483870967742,
      "grad_norm": 0.6624193787574768,
      "learning_rate": 0.00011965078893848828,
      "loss": 0.1003,
      "step": 750
    },
    {
      "epoch": 0.7560483870967742,
      "eval_loss": 0.05326759070158005,
      "eval_runtime": 57.7375,
      "eval_samples_per_second": 8.66,
      "eval_steps_per_second": 8.66,
      "step": 750
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 150,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.769083236135731e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}