{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07256367462448299,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007256367462448298,
      "grad_norm": 13.1875,
      "learning_rate": 5e-06,
      "loss": 3.553,
      "step": 10
    },
    {
      "epoch": 0.0014512734924896596,
      "grad_norm": 9.375,
      "learning_rate": 1e-05,
      "loss": 3.5658,
      "step": 20
    },
    {
      "epoch": 0.0021769102387344894,
      "grad_norm": 8.8125,
      "learning_rate": 1.5e-05,
      "loss": 3.4669,
      "step": 30
    },
    {
      "epoch": 0.0029025469849793192,
      "grad_norm": 13.25,
      "learning_rate": 2e-05,
      "loss": 3.5007,
      "step": 40
    },
    {
      "epoch": 0.003628183731224149,
      "grad_norm": 9.3125,
      "learning_rate": 2.5e-05,
      "loss": 3.5062,
      "step": 50
    },
    {
      "epoch": 0.004353820477468979,
      "grad_norm": 9.9375,
      "learning_rate": 3e-05,
      "loss": 3.4178,
      "step": 60
    },
    {
      "epoch": 0.005079457223713809,
      "grad_norm": 17.125,
      "learning_rate": 3.5e-05,
      "loss": 3.4136,
      "step": 70
    },
    {
      "epoch": 0.0058050939699586385,
      "grad_norm": 17.5,
      "learning_rate": 4e-05,
      "loss": 3.3792,
      "step": 80
    },
    {
      "epoch": 0.006530730716203468,
      "grad_norm": 17.0,
      "learning_rate": 4.5e-05,
      "loss": 3.3684,
      "step": 90
    },
    {
      "epoch": 0.007256367462448298,
      "grad_norm": 21.875,
      "learning_rate": 5e-05,
      "loss": 3.2698,
      "step": 100
    },
    {
      "epoch": 0.007982004208693128,
      "grad_norm": 32.5,
      "learning_rate": 4.9999934086574596e-05,
      "loss": 3.1523,
      "step": 110
    },
    {
      "epoch": 0.008707640954937958,
      "grad_norm": 73.5,
      "learning_rate": 4.9999736346645943e-05,
      "loss": 3.0884,
      "step": 120
    },
    {
      "epoch": 0.009433277701182788,
      "grad_norm": 34.75,
      "learning_rate": 4.999940678125673e-05,
      "loss": 2.9507,
      "step": 130
    },
    {
      "epoch": 0.010158914447427617,
      "grad_norm": 47.5,
      "learning_rate": 4.9998945392144796e-05,
      "loss": 2.8659,
      "step": 140
    },
    {
      "epoch": 0.010884551193672447,
      "grad_norm": 35.25,
      "learning_rate": 4.999835218174307e-05,
      "loss": 2.9846,
      "step": 150
    },
    {
      "epoch": 0.011610187939917277,
      "grad_norm": 27.5,
      "learning_rate": 4.99976271531796e-05,
      "loss": 2.8913,
      "step": 160
    },
    {
      "epoch": 0.012335824686162107,
      "grad_norm": 38.5,
      "learning_rate": 4.9996770310277506e-05,
      "loss": 2.8982,
      "step": 170
    },
    {
      "epoch": 0.013061461432406937,
      "grad_norm": 52.0,
      "learning_rate": 4.9995781657555e-05,
      "loss": 2.7165,
      "step": 180
    },
    {
      "epoch": 0.013787098178651766,
      "grad_norm": 34.75,
      "learning_rate": 4.99946612002253e-05,
      "loss": 2.4166,
      "step": 190
    },
    {
      "epoch": 0.014512734924896596,
      "grad_norm": 40.25,
      "learning_rate": 4.9993408944196676e-05,
      "loss": 2.2161,
      "step": 200
    },
    {
      "epoch": 0.015238371671141426,
      "grad_norm": 39.25,
      "learning_rate": 4.9992024896072364e-05,
      "loss": 1.7825,
      "step": 210
    },
    {
      "epoch": 0.015964008417386256,
      "grad_norm": 37.25,
      "learning_rate": 4.999050906315055e-05,
      "loss": 1.46,
      "step": 220
    },
    {
      "epoch": 0.016689645163631087,
      "grad_norm": 13.625,
      "learning_rate": 4.998886145342434e-05,
      "loss": 1.3157,
      "step": 230
    },
    {
      "epoch": 0.017415281909875915,
      "grad_norm": 10.4375,
      "learning_rate": 4.9987082075581684e-05,
      "loss": 1.1408,
      "step": 240
    },
    {
      "epoch": 0.018140918656120747,
      "grad_norm": 14.0,
      "learning_rate": 4.9985170939005386e-05,
      "loss": 0.8782,
      "step": 250
    },
    {
      "epoch": 0.018866555402365575,
      "grad_norm": 22.0,
      "learning_rate": 4.998312805377302e-05,
      "loss": 0.9109,
      "step": 260
    },
    {
      "epoch": 0.019592192148610407,
      "grad_norm": 12.625,
      "learning_rate": 4.998095343065685e-05,
      "loss": 0.7414,
      "step": 270
    },
    {
      "epoch": 0.020317828894855235,
      "grad_norm": 15.8125,
      "learning_rate": 4.997864708112384e-05,
      "loss": 0.7926,
      "step": 280
    },
    {
      "epoch": 0.021043465641100066,
      "grad_norm": 16.25,
      "learning_rate": 4.997620901733554e-05,
      "loss": 0.7382,
      "step": 290
    },
    {
      "epoch": 0.021769102387344894,
      "grad_norm": 22.0,
      "learning_rate": 4.997363925214803e-05,
      "loss": 0.7158,
      "step": 300
    },
    {
      "epoch": 0.022494739133589726,
      "grad_norm": 13.375,
      "learning_rate": 4.9970937799111896e-05,
      "loss": 0.526,
      "step": 310
    },
    {
      "epoch": 0.023220375879834554,
      "grad_norm": 12.9375,
      "learning_rate": 4.996810467247207e-05,
      "loss": 0.6137,
      "step": 320
    },
    {
      "epoch": 0.023946012626079385,
      "grad_norm": 6.78125,
      "learning_rate": 4.9965139887167856e-05,
      "loss": 0.4864,
      "step": 330
    },
    {
      "epoch": 0.024671649372324213,
      "grad_norm": 10.25,
      "learning_rate": 4.996204345883278e-05,
      "loss": 0.6921,
      "step": 340
    },
    {
      "epoch": 0.025397286118569045,
      "grad_norm": 6.3125,
      "learning_rate": 4.9958815403794546e-05,
      "loss": 0.5826,
      "step": 350
    },
    {
      "epoch": 0.026122922864813873,
      "grad_norm": 10.625,
      "learning_rate": 4.995545573907492e-05,
      "loss": 0.5838,
      "step": 360
    },
    {
      "epoch": 0.026848559611058705,
      "grad_norm": 17.25,
      "learning_rate": 4.995196448238966e-05,
      "loss": 0.5941,
      "step": 370
    },
    {
      "epoch": 0.027574196357303533,
      "grad_norm": 9.875,
      "learning_rate": 4.9948341652148436e-05,
      "loss": 0.5055,
      "step": 380
    },
    {
      "epoch": 0.028299833103548364,
      "grad_norm": 21.25,
      "learning_rate": 4.994458726745468e-05,
      "loss": 0.6114,
      "step": 390
    },
    {
      "epoch": 0.029025469849793192,
      "grad_norm": 3.375,
      "learning_rate": 4.9940701348105554e-05,
      "loss": 0.5372,
      "step": 400
    },
    {
      "epoch": 0.029751106596038024,
      "grad_norm": 12.625,
      "learning_rate": 4.99366839145918e-05,
      "loss": 0.4815,
      "step": 410
    },
    {
      "epoch": 0.030476743342282852,
      "grad_norm": 10.8125,
      "learning_rate": 4.993253498809762e-05,
      "loss": 0.4903,
      "step": 420
    },
    {
      "epoch": 0.031202380088527683,
      "grad_norm": 9.0,
      "learning_rate": 4.9928254590500646e-05,
      "loss": 0.5927,
      "step": 430
    },
    {
      "epoch": 0.03192801683477251,
      "grad_norm": 6.71875,
      "learning_rate": 4.9923842744371707e-05,
      "loss": 0.4424,
      "step": 440
    },
    {
      "epoch": 0.03265365358101734,
      "grad_norm": 5.0,
      "learning_rate": 4.99192994729748e-05,
      "loss": 0.362,
      "step": 450
    },
    {
      "epoch": 0.033379290327262175,
      "grad_norm": 8.625,
      "learning_rate": 4.991462480026693e-05,
      "loss": 0.593,
      "step": 460
    },
    {
      "epoch": 0.034104927073507,
      "grad_norm": 4.53125,
      "learning_rate": 4.9909818750898e-05,
      "loss": 0.4769,
      "step": 470
    },
    {
      "epoch": 0.03483056381975183,
      "grad_norm": 11.125,
      "learning_rate": 4.990488135021065e-05,
      "loss": 0.4455,
      "step": 480
    },
    {
      "epoch": 0.03555620056599666,
      "grad_norm": 8.375,
      "learning_rate": 4.989981262424017e-05,
      "loss": 0.4713,
      "step": 490
    },
    {
      "epoch": 0.036281837312241494,
      "grad_norm": 7.75,
      "learning_rate": 4.989461259971432e-05,
      "loss": 0.2778,
      "step": 500
    },
    {
      "epoch": 0.03700747405848632,
      "grad_norm": 5.65625,
      "learning_rate": 4.988928130405323e-05,
      "loss": 0.3604,
      "step": 510
    },
    {
      "epoch": 0.03773311080473115,
      "grad_norm": 7.5625,
      "learning_rate": 4.9883818765369194e-05,
      "loss": 0.4234,
      "step": 520
    },
    {
      "epoch": 0.03845874755097598,
      "grad_norm": 8.9375,
      "learning_rate": 4.98782250124666e-05,
      "loss": 0.3531,
      "step": 530
    },
    {
      "epoch": 0.03918438429722081,
      "grad_norm": 6.5,
      "learning_rate": 4.987250007484172e-05,
      "loss": 0.3281,
      "step": 540
    },
    {
      "epoch": 0.03991002104346564,
      "grad_norm": 4.59375,
      "learning_rate": 4.986664398268256e-05,
      "loss": 0.3477,
      "step": 550
    },
    {
      "epoch": 0.04063565778971047,
      "grad_norm": 6.4375,
      "learning_rate": 4.986065676686874e-05,
      "loss": 0.369,
      "step": 560
    },
    {
      "epoch": 0.0413612945359553,
      "grad_norm": 8.0625,
      "learning_rate": 4.98545384589713e-05,
      "loss": 0.3068,
      "step": 570
    },
    {
      "epoch": 0.04208693128220013,
      "grad_norm": 6.28125,
      "learning_rate": 4.984828909125251e-05,
      "loss": 0.2926,
      "step": 580
    },
    {
      "epoch": 0.042812568028444964,
      "grad_norm": 4.4375,
      "learning_rate": 4.9841908696665764e-05,
      "loss": 0.2771,
      "step": 590
    },
    {
      "epoch": 0.04353820477468979,
      "grad_norm": 4.15625,
      "learning_rate": 4.9835397308855344e-05,
      "loss": 0.3676,
      "step": 600
    },
    {
      "epoch": 0.04426384152093462,
      "grad_norm": 4.4375,
      "learning_rate": 4.9828754962156286e-05,
      "loss": 0.3307,
      "step": 610
    },
    {
      "epoch": 0.04498947826717945,
      "grad_norm": 13.75,
      "learning_rate": 4.9821981691594175e-05,
      "loss": 0.3601,
      "step": 620
    },
    {
      "epoch": 0.04571511501342428,
      "grad_norm": 4.59375,
      "learning_rate": 4.981507753288497e-05,
      "loss": 0.2939,
      "step": 630
    },
    {
      "epoch": 0.04644075175966911,
      "grad_norm": 6.1875,
      "learning_rate": 4.9808042522434814e-05,
      "loss": 0.293,
      "step": 640
    },
    {
      "epoch": 0.04716638850591394,
      "grad_norm": 4.65625,
      "learning_rate": 4.9800876697339824e-05,
      "loss": 0.3213,
      "step": 650
    },
    {
      "epoch": 0.04789202525215877,
      "grad_norm": 7.65625,
      "learning_rate": 4.979358009538594e-05,
      "loss": 0.3903,
      "step": 660
    },
    {
      "epoch": 0.0486176619984036,
      "grad_norm": 9.3125,
      "learning_rate": 4.978615275504869e-05,
      "loss": 0.2936,
      "step": 670
    },
    {
      "epoch": 0.04934329874464843,
      "grad_norm": 8.4375,
      "learning_rate": 4.977859471549297e-05,
      "loss": 0.3681,
      "step": 680
    },
    {
      "epoch": 0.05006893549089326,
      "grad_norm": 6.28125,
      "learning_rate": 4.977090601657289e-05,
      "loss": 0.2591,
      "step": 690
    },
    {
      "epoch": 0.05079457223713809,
      "grad_norm": 10.8125,
      "learning_rate": 4.976308669883153e-05,
      "loss": 0.3351,
      "step": 700
    },
    {
      "epoch": 0.05152020898338292,
      "grad_norm": 6.65625,
      "learning_rate": 4.975513680350073e-05,
      "loss": 0.3042,
      "step": 710
    },
    {
      "epoch": 0.052245845729627746,
      "grad_norm": 6.65625,
      "learning_rate": 4.974705637250089e-05,
      "loss": 0.2396,
      "step": 720
    },
    {
      "epoch": 0.05297148247587258,
      "grad_norm": 6.1875,
      "learning_rate": 4.97388454484407e-05,
      "loss": 0.2892,
      "step": 730
    },
    {
      "epoch": 0.05369711922211741,
      "grad_norm": 3.78125,
      "learning_rate": 4.973050407461698e-05,
      "loss": 0.3032,
      "step": 740
    },
    {
      "epoch": 0.05442275596836224,
      "grad_norm": 2.65625,
      "learning_rate": 4.972203229501441e-05,
      "loss": 0.2522,
      "step": 750
    },
    {
      "epoch": 0.055148392714607065,
      "grad_norm": 7.84375,
      "learning_rate": 4.971343015430532e-05,
      "loss": 0.2502,
      "step": 760
    },
    {
      "epoch": 0.0558740294608519,
      "grad_norm": 10.6875,
      "learning_rate": 4.970469769784941e-05,
      "loss": 0.2664,
      "step": 770
    },
    {
      "epoch": 0.05659966620709673,
      "grad_norm": 7.90625,
      "learning_rate": 4.96958349716936e-05,
      "loss": 0.332,
      "step": 780
    },
    {
      "epoch": 0.05732530295334156,
      "grad_norm": 10.75,
      "learning_rate": 4.968684202257169e-05,
      "loss": 0.3737,
      "step": 790
    },
    {
      "epoch": 0.058050939699586385,
      "grad_norm": 6.5,
      "learning_rate": 4.967771889790416e-05,
      "loss": 0.2794,
      "step": 800
    },
    {
      "epoch": 0.058776576445831216,
      "grad_norm": 2.921875,
      "learning_rate": 4.966846564579792e-05,
      "loss": 0.2375,
      "step": 810
    },
    {
      "epoch": 0.05950221319207605,
      "grad_norm": 6.09375,
      "learning_rate": 4.965908231504607e-05,
      "loss": 0.365,
      "step": 820
    },
    {
      "epoch": 0.06022784993832088,
      "grad_norm": 9.0625,
      "learning_rate": 4.964956895512759e-05,
      "loss": 0.3469,
      "step": 830
    },
    {
      "epoch": 0.060953486684565704,
      "grad_norm": 5.25,
      "learning_rate": 4.963992561620714e-05,
      "loss": 0.2904,
      "step": 840
    },
    {
      "epoch": 0.061679123430810535,
      "grad_norm": 5.5,
      "learning_rate": 4.963015234913475e-05,
      "loss": 0.2779,
      "step": 850
    },
    {
      "epoch": 0.06240476017705537,
      "grad_norm": 5.6875,
      "learning_rate": 4.96202492054456e-05,
      "loss": 0.2658,
      "step": 860
    },
    {
      "epoch": 0.06313039692330019,
      "grad_norm": 8.8125,
      "learning_rate": 4.9610216237359684e-05,
      "loss": 0.3973,
      "step": 870
    },
    {
      "epoch": 0.06385603366954502,
      "grad_norm": 10.0,
      "learning_rate": 4.960005349778159e-05,
      "loss": 0.3169,
      "step": 880
    },
    {
      "epoch": 0.06458167041578985,
      "grad_norm": 11.9375,
      "learning_rate": 4.95897610403002e-05,
      "loss": 0.3172,
      "step": 890
    },
    {
      "epoch": 0.06530730716203469,
      "grad_norm": 3.0,
      "learning_rate": 4.95793389191884e-05,
      "loss": 0.2664,
      "step": 900
    },
    {
      "epoch": 0.06603294390827952,
      "grad_norm": 6.90625,
      "learning_rate": 4.95687871894028e-05,
      "loss": 0.2507,
      "step": 910
    },
    {
      "epoch": 0.06675858065452435,
      "grad_norm": 3.796875,
      "learning_rate": 4.9558105906583466e-05,
      "loss": 0.2383,
      "step": 920
    },
    {
      "epoch": 0.06748421740076918,
      "grad_norm": 6.28125,
      "learning_rate": 4.9547295127053586e-05,
      "loss": 0.3942,
      "step": 930
    },
    {
      "epoch": 0.068209854147014,
      "grad_norm": 9.0,
      "learning_rate": 4.95363549078192e-05,
      "loss": 0.2427,
      "step": 940
    },
    {
      "epoch": 0.06893549089325883,
      "grad_norm": 5.59375,
      "learning_rate": 4.952528530656889e-05,
      "loss": 0.2351,
      "step": 950
    },
    {
      "epoch": 0.06966112763950366,
      "grad_norm": 9.5625,
      "learning_rate": 4.9514086381673496e-05,
      "loss": 0.282,
      "step": 960
    },
    {
      "epoch": 0.0703867643857485,
      "grad_norm": 10.0625,
      "learning_rate": 4.9502758192185774e-05,
      "loss": 0.2687,
      "step": 970
    },
    {
      "epoch": 0.07111240113199332,
      "grad_norm": 9.0625,
      "learning_rate": 4.949130079784009e-05,
      "loss": 0.3135,
      "step": 980
    },
    {
      "epoch": 0.07183803787823816,
      "grad_norm": 5.59375,
      "learning_rate": 4.9479714259052143e-05,
      "loss": 0.3207,
      "step": 990
    },
    {
      "epoch": 0.07256367462448299,
      "grad_norm": 8.3125,
      "learning_rate": 4.946799863691862e-05,
      "loss": 0.2572,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 13781,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}