{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029098898061104047,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002909889806110405,
      "grad_norm": 3.3640072345733643,
      "learning_rate": 0.0002,
      "loss": 1.2361,
      "step": 10
    },
    {
      "epoch": 0.000581977961222081,
      "grad_norm": 0.2830420136451721,
      "learning_rate": 0.0002,
      "loss": 0.1232,
      "step": 20
    },
    {
      "epoch": 0.0008729669418331215,
      "grad_norm": 0.3788599669933319,
      "learning_rate": 0.0002,
      "loss": 0.0874,
      "step": 30
    },
    {
      "epoch": 0.001163955922444162,
      "grad_norm": 0.9566423892974854,
      "learning_rate": 0.0002,
      "loss": 0.1099,
      "step": 40
    },
    {
      "epoch": 0.0014549449030552023,
      "grad_norm": 0.5953503847122192,
      "learning_rate": 0.0002,
      "loss": 0.0727,
      "step": 50
    },
    {
      "epoch": 0.001745933883666243,
      "grad_norm": 0.3039131164550781,
      "learning_rate": 0.0002,
      "loss": 0.0575,
      "step": 60
    },
    {
      "epoch": 0.0020369228642772835,
      "grad_norm": 0.27436479926109314,
      "learning_rate": 0.0002,
      "loss": 0.0511,
      "step": 70
    },
    {
      "epoch": 0.002327911844888324,
      "grad_norm": 0.22409753501415253,
      "learning_rate": 0.0002,
      "loss": 0.0495,
      "step": 80
    },
    {
      "epoch": 0.0026189008254993646,
      "grad_norm": 0.5258105397224426,
      "learning_rate": 0.0002,
      "loss": 0.0447,
      "step": 90
    },
    {
      "epoch": 0.0029098898061104047,
      "grad_norm": 0.3420485854148865,
      "learning_rate": 0.0002,
      "loss": 0.0447,
      "step": 100
    },
    {
      "epoch": 0.0032008787867214453,
      "grad_norm": 0.18883126974105835,
      "learning_rate": 0.0002,
      "loss": 0.0437,
      "step": 110
    },
    {
      "epoch": 0.003491867767332486,
      "grad_norm": 0.09849688410758972,
      "learning_rate": 0.0002,
      "loss": 0.0428,
      "step": 120
    },
    {
      "epoch": 0.0037828567479435264,
      "grad_norm": 0.5861080884933472,
      "learning_rate": 0.0002,
      "loss": 0.0416,
      "step": 130
    },
    {
      "epoch": 0.004073845728554567,
      "grad_norm": 0.8478333353996277,
      "learning_rate": 0.0002,
      "loss": 0.0415,
      "step": 140
    },
    {
      "epoch": 0.004364834709165607,
      "grad_norm": 0.6563957333564758,
      "learning_rate": 0.0002,
      "loss": 0.0416,
      "step": 150
    },
    {
      "epoch": 0.004655823689776648,
      "grad_norm": 0.1496465653181076,
      "learning_rate": 0.0002,
      "loss": 0.04,
      "step": 160
    },
    {
      "epoch": 0.004946812670387688,
      "grad_norm": 0.7356327176094055,
      "learning_rate": 0.0002,
      "loss": 0.0406,
      "step": 170
    },
    {
      "epoch": 0.005237801650998729,
      "grad_norm": 0.5485235452651978,
      "learning_rate": 0.0002,
      "loss": 0.0415,
      "step": 180
    },
    {
      "epoch": 0.005528790631609769,
      "grad_norm": 0.28617948293685913,
      "learning_rate": 0.0002,
      "loss": 0.04,
      "step": 190
    },
    {
      "epoch": 0.005819779612220809,
      "grad_norm": 0.7351231575012207,
      "learning_rate": 0.0002,
      "loss": 0.0462,
      "step": 200
    },
    {
      "epoch": 0.00611076859283185,
      "grad_norm": 0.6597175598144531,
      "learning_rate": 0.0002,
      "loss": 0.042,
      "step": 210
    },
    {
      "epoch": 0.0064017575734428905,
      "grad_norm": 0.5418401956558228,
      "learning_rate": 0.0002,
      "loss": 0.0425,
      "step": 220
    },
    {
      "epoch": 0.0066927465540539315,
      "grad_norm": 0.4611615836620331,
      "learning_rate": 0.0002,
      "loss": 0.0409,
      "step": 230
    },
    {
      "epoch": 0.006983735534664972,
      "grad_norm": 0.039530955255031586,
      "learning_rate": 0.0002,
      "loss": 0.0414,
      "step": 240
    },
    {
      "epoch": 0.007274724515276012,
      "grad_norm": 0.03446557745337486,
      "learning_rate": 0.0002,
      "loss": 0.0393,
      "step": 250
    },
    {
      "epoch": 0.007565713495887053,
      "grad_norm": 0.7747415900230408,
      "learning_rate": 0.0002,
      "loss": 0.0419,
      "step": 260
    },
    {
      "epoch": 0.007856702476498093,
      "grad_norm": 0.3428023159503937,
      "learning_rate": 0.0002,
      "loss": 0.0423,
      "step": 270
    },
    {
      "epoch": 0.008147691457109134,
      "grad_norm": 0.2668132781982422,
      "learning_rate": 0.0002,
      "loss": 0.0404,
      "step": 280
    },
    {
      "epoch": 0.008438680437720175,
      "grad_norm": 0.06787655502557755,
      "learning_rate": 0.0002,
      "loss": 0.0373,
      "step": 290
    },
    {
      "epoch": 0.008729669418331214,
      "grad_norm": 0.17109806835651398,
      "learning_rate": 0.0002,
      "loss": 0.0371,
      "step": 300
    },
    {
      "epoch": 0.009020658398942255,
      "grad_norm": 0.1489395946264267,
      "learning_rate": 0.0002,
      "loss": 0.0377,
      "step": 310
    },
    {
      "epoch": 0.009311647379553296,
      "grad_norm": 0.20444560050964355,
      "learning_rate": 0.0002,
      "loss": 0.0385,
      "step": 320
    },
    {
      "epoch": 0.009602636360164335,
      "grad_norm": 1.251767873764038,
      "learning_rate": 0.0002,
      "loss": 0.0395,
      "step": 330
    },
    {
      "epoch": 0.009893625340775376,
      "grad_norm": 0.17964421212673187,
      "learning_rate": 0.0002,
      "loss": 0.0403,
      "step": 340
    },
    {
      "epoch": 0.010184614321386417,
      "grad_norm": 0.20001742243766785,
      "learning_rate": 0.0002,
      "loss": 0.0374,
      "step": 350
    },
    {
      "epoch": 0.010475603301997458,
      "grad_norm": 0.07885689288377762,
      "learning_rate": 0.0002,
      "loss": 0.0366,
      "step": 360
    },
    {
      "epoch": 0.010766592282608498,
      "grad_norm": 0.1755530834197998,
      "learning_rate": 0.0002,
      "loss": 0.0366,
      "step": 370
    },
    {
      "epoch": 0.011057581263219539,
      "grad_norm": 0.24720287322998047,
      "learning_rate": 0.0002,
      "loss": 0.036,
      "step": 380
    },
    {
      "epoch": 0.01134857024383058,
      "grad_norm": 0.13627253472805023,
      "learning_rate": 0.0002,
      "loss": 0.0384,
      "step": 390
    },
    {
      "epoch": 0.011639559224441619,
      "grad_norm": 0.10238471627235413,
      "learning_rate": 0.0002,
      "loss": 0.037,
      "step": 400
    },
    {
      "epoch": 0.01193054820505266,
      "grad_norm": 0.1790493279695511,
      "learning_rate": 0.0002,
      "loss": 0.036,
      "step": 410
    },
    {
      "epoch": 0.0122215371856637,
      "grad_norm": 0.8142262101173401,
      "learning_rate": 0.0002,
      "loss": 0.0366,
      "step": 420
    },
    {
      "epoch": 0.012512526166274742,
      "grad_norm": 0.3142533600330353,
      "learning_rate": 0.0002,
      "loss": 0.0373,
      "step": 430
    },
    {
      "epoch": 0.012803515146885781,
      "grad_norm": 0.5743248462677002,
      "learning_rate": 0.0002,
      "loss": 0.0364,
      "step": 440
    },
    {
      "epoch": 0.013094504127496822,
      "grad_norm": 0.10562433302402496,
      "learning_rate": 0.0002,
      "loss": 0.0357,
      "step": 450
    },
    {
      "epoch": 0.013385493108107863,
      "grad_norm": 0.1285354048013687,
      "learning_rate": 0.0002,
      "loss": 0.0348,
      "step": 460
    },
    {
      "epoch": 0.013676482088718902,
      "grad_norm": 0.31671035289764404,
      "learning_rate": 0.0002,
      "loss": 0.0367,
      "step": 470
    },
    {
      "epoch": 0.013967471069329943,
      "grad_norm": 0.10281776636838913,
      "learning_rate": 0.0002,
      "loss": 0.0367,
      "step": 480
    },
    {
      "epoch": 0.014258460049940984,
      "grad_norm": 0.10469332337379456,
      "learning_rate": 0.0002,
      "loss": 0.0354,
      "step": 490
    },
    {
      "epoch": 0.014549449030552023,
      "grad_norm": 0.04262165352702141,
      "learning_rate": 0.0002,
      "loss": 0.0358,
      "step": 500
    },
    {
      "epoch": 0.014840438011163064,
      "grad_norm": 0.08256979286670685,
      "learning_rate": 0.0002,
      "loss": 0.0352,
      "step": 510
    },
    {
      "epoch": 0.015131426991774105,
      "grad_norm": 0.2147534042596817,
      "learning_rate": 0.0002,
      "loss": 0.0352,
      "step": 520
    },
    {
      "epoch": 0.015422415972385146,
      "grad_norm": 0.7227026224136353,
      "learning_rate": 0.0002,
      "loss": 0.0367,
      "step": 530
    },
    {
      "epoch": 0.015713404952996186,
      "grad_norm": 0.3186182975769043,
      "learning_rate": 0.0002,
      "loss": 0.0366,
      "step": 540
    },
    {
      "epoch": 0.01600439393360723,
      "grad_norm": 0.5129309296607971,
      "learning_rate": 0.0002,
      "loss": 0.036,
      "step": 550
    },
    {
      "epoch": 0.016295382914218268,
      "grad_norm": 0.3547574281692505,
      "learning_rate": 0.0002,
      "loss": 0.0363,
      "step": 560
    },
    {
      "epoch": 0.016586371894829307,
      "grad_norm": 0.29844892024993896,
      "learning_rate": 0.0002,
      "loss": 0.0369,
      "step": 570
    },
    {
      "epoch": 0.01687736087544035,
      "grad_norm": 0.25678157806396484,
      "learning_rate": 0.0002,
      "loss": 0.0352,
      "step": 580
    },
    {
      "epoch": 0.01716834985605139,
      "grad_norm": 0.07419384270906448,
      "learning_rate": 0.0002,
      "loss": 0.0344,
      "step": 590
    },
    {
      "epoch": 0.017459338836662428,
      "grad_norm": 0.15620607137680054,
      "learning_rate": 0.0002,
      "loss": 0.0343,
      "step": 600
    },
    {
      "epoch": 0.01775032781727347,
      "grad_norm": 0.17426913976669312,
      "learning_rate": 0.0002,
      "loss": 0.0326,
      "step": 610
    },
    {
      "epoch": 0.01804131679788451,
      "grad_norm": 0.18652600049972534,
      "learning_rate": 0.0002,
      "loss": 0.0358,
      "step": 620
    },
    {
      "epoch": 0.01833230577849555,
      "grad_norm": 0.5866808295249939,
      "learning_rate": 0.0002,
      "loss": 0.0364,
      "step": 630
    },
    {
      "epoch": 0.018623294759106592,
      "grad_norm": 0.5470107793807983,
      "learning_rate": 0.0002,
      "loss": 0.0385,
      "step": 640
    },
    {
      "epoch": 0.01891428373971763,
      "grad_norm": 0.4430047273635864,
      "learning_rate": 0.0002,
      "loss": 0.0355,
      "step": 650
    },
    {
      "epoch": 0.01920527272032867,
      "grad_norm": 0.44153594970703125,
      "learning_rate": 0.0002,
      "loss": 0.0374,
      "step": 660
    },
    {
      "epoch": 0.019496261700939713,
      "grad_norm": 0.2025349885225296,
      "learning_rate": 0.0002,
      "loss": 0.0361,
      "step": 670
    },
    {
      "epoch": 0.019787250681550753,
      "grad_norm": 0.05006701499223709,
      "learning_rate": 0.0002,
      "loss": 0.0352,
      "step": 680
    },
    {
      "epoch": 0.020078239662161792,
      "grad_norm": 0.15291444957256317,
      "learning_rate": 0.0002,
      "loss": 0.0339,
      "step": 690
    },
    {
      "epoch": 0.020369228642772835,
      "grad_norm": 0.20080982148647308,
      "learning_rate": 0.0002,
      "loss": 0.034,
      "step": 700
    },
    {
      "epoch": 0.020660217623383874,
      "grad_norm": 0.1934683471918106,
      "learning_rate": 0.0002,
      "loss": 0.0338,
      "step": 710
    },
    {
      "epoch": 0.020951206603994917,
      "grad_norm": 0.2093890905380249,
      "learning_rate": 0.0002,
      "loss": 0.033,
      "step": 720
    },
    {
      "epoch": 0.021242195584605956,
      "grad_norm": 0.17411717772483826,
      "learning_rate": 0.0002,
      "loss": 0.0329,
      "step": 730
    },
    {
      "epoch": 0.021533184565216995,
      "grad_norm": 0.06554729491472244,
      "learning_rate": 0.0002,
      "loss": 0.0328,
      "step": 740
    },
    {
      "epoch": 0.021824173545828038,
      "grad_norm": 0.3035508692264557,
      "learning_rate": 0.0002,
      "loss": 0.0345,
      "step": 750
    },
    {
      "epoch": 0.022115162526439077,
      "grad_norm": 0.1284075379371643,
      "learning_rate": 0.0002,
      "loss": 0.0344,
      "step": 760
    },
    {
      "epoch": 0.022406151507050116,
      "grad_norm": 0.06972914189100266,
      "learning_rate": 0.0002,
      "loss": 0.0326,
      "step": 770
    },
    {
      "epoch": 0.02269714048766116,
      "grad_norm": 0.2625221908092499,
      "learning_rate": 0.0002,
      "loss": 0.0343,
      "step": 780
    },
    {
      "epoch": 0.0229881294682722,
      "grad_norm": 0.2056276947259903,
      "learning_rate": 0.0002,
      "loss": 0.0341,
      "step": 790
    },
    {
      "epoch": 0.023279118448883238,
      "grad_norm": 0.06602438539266586,
      "learning_rate": 0.0002,
      "loss": 0.0331,
      "step": 800
    },
    {
      "epoch": 0.02357010742949428,
      "grad_norm": 0.1302807331085205,
      "learning_rate": 0.0002,
      "loss": 0.0328,
      "step": 810
    },
    {
      "epoch": 0.02386109641010532,
      "grad_norm": 0.07038327306509018,
      "learning_rate": 0.0002,
      "loss": 0.0338,
      "step": 820
    },
    {
      "epoch": 0.02415208539071636,
      "grad_norm": 0.3151911199092865,
      "learning_rate": 0.0002,
      "loss": 0.0353,
      "step": 830
    },
    {
      "epoch": 0.0244430743713274,
      "grad_norm": 0.2942112982273102,
      "learning_rate": 0.0002,
      "loss": 0.0336,
      "step": 840
    },
    {
      "epoch": 0.02473406335193844,
      "grad_norm": 0.09775586426258087,
      "learning_rate": 0.0002,
      "loss": 0.0331,
      "step": 850
    },
    {
      "epoch": 0.025025052332549483,
      "grad_norm": 0.06825686991214752,
      "learning_rate": 0.0002,
      "loss": 0.0338,
      "step": 860
    },
    {
      "epoch": 0.025316041313160523,
      "grad_norm": 0.08698020130395889,
      "learning_rate": 0.0002,
      "loss": 0.0329,
      "step": 870
    },
    {
      "epoch": 0.025607030293771562,
      "grad_norm": 0.29394668340682983,
      "learning_rate": 0.0002,
      "loss": 0.0328,
      "step": 880
    },
    {
      "epoch": 0.025898019274382605,
      "grad_norm": 0.2138691395521164,
      "learning_rate": 0.0002,
      "loss": 0.0327,
      "step": 890
    },
    {
      "epoch": 0.026189008254993644,
      "grad_norm": 0.22760023176670074,
      "learning_rate": 0.0002,
      "loss": 0.0349,
      "step": 900
    },
    {
      "epoch": 0.026479997235604683,
      "grad_norm": 0.07050047069787979,
      "learning_rate": 0.0002,
      "loss": 0.0327,
      "step": 910
    },
    {
      "epoch": 0.026770986216215726,
      "grad_norm": 0.0632275640964508,
      "learning_rate": 0.0002,
      "loss": 0.0332,
      "step": 920
    },
    {
      "epoch": 0.027061975196826765,
      "grad_norm": 0.2537945508956909,
      "learning_rate": 0.0002,
      "loss": 0.0334,
      "step": 930
    },
    {
      "epoch": 0.027352964177437804,
      "grad_norm": 0.17872551083564758,
      "learning_rate": 0.0002,
      "loss": 0.0339,
      "step": 940
    },
    {
      "epoch": 0.027643953158048847,
      "grad_norm": 0.1240101158618927,
      "learning_rate": 0.0002,
      "loss": 0.0328,
      "step": 950
    },
    {
      "epoch": 0.027934942138659886,
      "grad_norm": 0.24408769607543945,
      "learning_rate": 0.0002,
      "loss": 0.0337,
      "step": 960
    },
    {
      "epoch": 0.028225931119270926,
      "grad_norm": 0.06075837463140488,
      "learning_rate": 0.0002,
      "loss": 0.0327,
      "step": 970
    },
    {
      "epoch": 0.02851692009988197,
      "grad_norm": 0.09202170372009277,
      "learning_rate": 0.0002,
      "loss": 0.0326,
      "step": 980
    },
    {
      "epoch": 0.028807909080493008,
      "grad_norm": 0.09207413345575333,
      "learning_rate": 0.0002,
      "loss": 0.0316,
      "step": 990
    },
    {
      "epoch": 0.029098898061104047,
      "grad_norm": 0.056632377207279205,
      "learning_rate": 0.0002,
      "loss": 0.0331,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 40000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.102264300163564e+18,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}