{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 500.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 0.679200291633606,
      "learning_rate": 5e-05,
      "loss": 12.211211204528809,
      "step": 1
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.19637228548526764,
      "learning_rate": 4.9550000000000005e-05,
      "loss": 12.135602315266928,
      "step": 10
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.1901359260082245,
      "learning_rate": 4.905e-05,
      "loss": 12.035923767089844,
      "step": 20
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.18782183527946472,
      "learning_rate": 4.855e-05,
      "loss": 11.941139221191406,
      "step": 30
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.18852435052394867,
      "learning_rate": 4.805e-05,
      "loss": 11.83099594116211,
      "step": 40
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.19028881192207336,
      "learning_rate": 4.755e-05,
      "loss": 11.708907318115234,
      "step": 50
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.1938280314207077,
      "learning_rate": 4.705e-05,
      "loss": 11.597697448730468,
      "step": 60
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.32372087240219116,
      "learning_rate": 4.655000000000001e-05,
      "loss": 11.502000427246093,
      "step": 70
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.20650140941143036,
      "learning_rate": 4.605e-05,
      "loss": 11.435150909423829,
      "step": 80
    },
    {
      "epoch": 45.0,
      "grad_norm": 0.18674910068511963,
      "learning_rate": 4.555e-05,
      "loss": 11.38574676513672,
      "step": 90
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.20134492218494415,
      "learning_rate": 4.5050000000000004e-05,
      "loss": 11.350026702880859,
      "step": 100
    },
    {
      "epoch": 55.0,
      "grad_norm": 0.18685384094715118,
      "learning_rate": 4.4550000000000005e-05,
      "loss": 11.322230529785156,
      "step": 110
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.196379154920578,
      "learning_rate": 4.405e-05,
      "loss": 11.299267578125,
      "step": 120
    },
    {
      "epoch": 65.0,
      "grad_norm": 0.1844422072172165,
      "learning_rate": 4.355e-05,
      "loss": 11.279010009765624,
      "step": 130
    },
    {
      "epoch": 70.0,
      "grad_norm": 0.1804857850074768,
      "learning_rate": 4.305e-05,
      "loss": 11.259839630126953,
      "step": 140
    },
    {
      "epoch": 75.0,
      "grad_norm": 0.19067005813121796,
      "learning_rate": 4.2550000000000004e-05,
      "loss": 11.241000366210937,
      "step": 150
    },
    {
      "epoch": 80.0,
      "grad_norm": 0.1887764036655426,
      "learning_rate": 4.205e-05,
      "loss": 11.222760772705078,
      "step": 160
    },
    {
      "epoch": 85.0,
      "grad_norm": 0.19067640602588654,
      "learning_rate": 4.155e-05,
      "loss": 11.20439453125,
      "step": 170
    },
    {
      "epoch": 90.0,
      "grad_norm": 0.1770990788936615,
      "learning_rate": 4.105e-05,
      "loss": 11.186467742919922,
      "step": 180
    },
    {
      "epoch": 95.0,
      "grad_norm": 0.17499233782291412,
      "learning_rate": 4.055e-05,
      "loss": 11.167765045166016,
      "step": 190
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.1904127597808838,
      "learning_rate": 4.0050000000000004e-05,
      "loss": 11.149557495117188,
      "step": 200
    },
    {
      "epoch": 105.0,
      "grad_norm": 0.1739717274904251,
      "learning_rate": 3.9550000000000006e-05,
      "loss": 11.131022644042968,
      "step": 210
    },
    {
      "epoch": 110.0,
      "grad_norm": 0.2017071694135666,
      "learning_rate": 3.905e-05,
      "loss": 11.112350463867188,
      "step": 220
    },
    {
      "epoch": 115.0,
      "grad_norm": 0.18773476779460907,
      "learning_rate": 3.855e-05,
      "loss": 11.094757843017579,
      "step": 230
    },
    {
      "epoch": 120.0,
      "grad_norm": 0.19418179988861084,
      "learning_rate": 3.805e-05,
      "loss": 11.076486206054687,
      "step": 240
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.1962657868862152,
      "learning_rate": 3.7550000000000005e-05,
      "loss": 11.056719207763672,
      "step": 250
    },
    {
      "epoch": 130.0,
      "grad_norm": 0.19265155494213104,
      "learning_rate": 3.705e-05,
      "loss": 11.037678527832032,
      "step": 260
    },
    {
      "epoch": 135.0,
      "grad_norm": 0.17414163053035736,
      "learning_rate": 3.655e-05,
      "loss": 11.018470764160156,
      "step": 270
    },
    {
      "epoch": 140.0,
      "grad_norm": 0.19136762619018555,
      "learning_rate": 3.605e-05,
      "loss": 10.999581909179687,
      "step": 280
    },
    {
      "epoch": 145.0,
      "grad_norm": 0.17472872138023376,
      "learning_rate": 3.555e-05,
      "loss": 10.980691528320312,
      "step": 290
    },
    {
      "epoch": 150.0,
      "grad_norm": 0.19140979647636414,
      "learning_rate": 3.505e-05,
      "loss": 10.961211395263671,
      "step": 300
    },
    {
      "epoch": 155.0,
      "grad_norm": 0.18277697265148163,
      "learning_rate": 3.455e-05,
      "loss": 10.942373657226563,
      "step": 310
    },
    {
      "epoch": 160.0,
      "grad_norm": 0.18312492966651917,
      "learning_rate": 3.405e-05,
      "loss": 10.923491668701171,
      "step": 320
    },
    {
      "epoch": 165.0,
      "grad_norm": 0.1935737133026123,
      "learning_rate": 3.355e-05,
      "loss": 10.904404449462891,
      "step": 330
    },
    {
      "epoch": 170.0,
      "grad_norm": 0.18423579633235931,
      "learning_rate": 3.3050000000000004e-05,
      "loss": 10.88526611328125,
      "step": 340
    },
    {
      "epoch": 175.0,
      "grad_norm": 0.1741979420185089,
      "learning_rate": 3.2550000000000005e-05,
      "loss": 10.86572036743164,
      "step": 350
    },
    {
      "epoch": 180.0,
      "grad_norm": 0.17369955778121948,
      "learning_rate": 3.205e-05,
      "loss": 10.847341156005859,
      "step": 360
    },
    {
      "epoch": 185.0,
      "grad_norm": 0.18073685467243195,
      "learning_rate": 3.155e-05,
      "loss": 10.827933502197265,
      "step": 370
    },
    {
      "epoch": 190.0,
      "grad_norm": 0.17668183147907257,
      "learning_rate": 3.105e-05,
      "loss": 10.809838104248048,
      "step": 380
    },
    {
      "epoch": 195.0,
      "grad_norm": 0.19311200082302094,
      "learning_rate": 3.0550000000000004e-05,
      "loss": 10.791265869140625,
      "step": 390
    },
    {
      "epoch": 200.0,
      "grad_norm": 0.20700618624687195,
      "learning_rate": 3.0050000000000002e-05,
      "loss": 10.772897338867187,
      "step": 400
    },
    {
      "epoch": 205.0,
      "grad_norm": 0.18541602790355682,
      "learning_rate": 2.955e-05,
      "loss": 10.754539489746094,
      "step": 410
    },
    {
      "epoch": 210.0,
      "grad_norm": 0.19843514263629913,
      "learning_rate": 2.9049999999999998e-05,
      "loss": 10.736498260498047,
      "step": 420
    },
    {
      "epoch": 215.0,
      "grad_norm": 0.1915830671787262,
      "learning_rate": 2.855e-05,
      "loss": 10.718640899658203,
      "step": 430
    },
    {
      "epoch": 220.0,
      "grad_norm": 0.1963329315185547,
      "learning_rate": 2.8050000000000004e-05,
      "loss": 10.701332092285156,
      "step": 440
    },
    {
      "epoch": 225.0,
      "grad_norm": 0.1926761120557785,
      "learning_rate": 2.7550000000000002e-05,
      "loss": 10.683160400390625,
      "step": 450
    },
    {
      "epoch": 230.0,
      "grad_norm": 0.1978655308485031,
      "learning_rate": 2.7050000000000004e-05,
      "loss": 10.665509796142578,
      "step": 460
    },
    {
      "epoch": 235.0,
      "grad_norm": 0.22640474140644073,
      "learning_rate": 2.655e-05,
      "loss": 10.648850250244141,
      "step": 470
    },
    {
      "epoch": 240.0,
      "grad_norm": 0.284628301858902,
      "learning_rate": 2.6050000000000003e-05,
      "loss": 10.6341064453125,
      "step": 480
    },
    {
      "epoch": 245.0,
      "grad_norm": 0.20072966814041138,
      "learning_rate": 2.555e-05,
      "loss": 10.615923309326172,
      "step": 490
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.1898791790008545,
      "learning_rate": 2.5050000000000002e-05,
      "loss": 10.598560333251953,
      "step": 500
    },
    {
      "epoch": 255.0,
      "grad_norm": 0.19185157120227814,
      "learning_rate": 2.455e-05,
      "loss": 10.58202896118164,
      "step": 510
    },
    {
      "epoch": 260.0,
      "grad_norm": 0.1799161583185196,
      "learning_rate": 2.4050000000000002e-05,
      "loss": 10.56644058227539,
      "step": 520
    },
    {
      "epoch": 265.0,
      "grad_norm": 0.18410366773605347,
      "learning_rate": 2.355e-05,
      "loss": 10.549659729003906,
      "step": 530
    },
    {
      "epoch": 270.0,
      "grad_norm": 0.17715789377689362,
      "learning_rate": 2.305e-05,
      "loss": 10.534073638916016,
      "step": 540
    },
    {
      "epoch": 275.0,
      "grad_norm": 0.18409231305122375,
      "learning_rate": 2.2550000000000003e-05,
      "loss": 10.518675231933594,
      "step": 550
    },
    {
      "epoch": 280.0,
      "grad_norm": 0.18424347043037415,
      "learning_rate": 2.205e-05,
      "loss": 10.504659271240234,
      "step": 560
    },
    {
      "epoch": 285.0,
      "grad_norm": 0.19608528912067413,
      "learning_rate": 2.1550000000000002e-05,
      "loss": 10.488896942138672,
      "step": 570
    },
    {
      "epoch": 290.0,
      "grad_norm": 0.18763066828250885,
      "learning_rate": 2.105e-05,
      "loss": 10.47493667602539,
      "step": 580
    },
    {
      "epoch": 295.0,
      "grad_norm": 0.19432927668094635,
      "learning_rate": 2.055e-05,
      "loss": 10.460673522949218,
      "step": 590
    },
    {
      "epoch": 300.0,
      "grad_norm": 0.17795953154563904,
      "learning_rate": 2.0050000000000003e-05,
      "loss": 10.446895599365234,
      "step": 600
    },
    {
      "epoch": 305.0,
      "grad_norm": 0.18806937336921692,
      "learning_rate": 1.955e-05,
      "loss": 10.434019470214844,
      "step": 610
    },
    {
      "epoch": 310.0,
      "grad_norm": 0.19683541357517242,
      "learning_rate": 1.9050000000000002e-05,
      "loss": 10.420983123779298,
      "step": 620
    },
    {
      "epoch": 315.0,
      "grad_norm": 0.18045076727867126,
      "learning_rate": 1.855e-05,
      "loss": 10.408130645751953,
      "step": 630
    },
    {
      "epoch": 320.0,
      "grad_norm": 0.18547658622264862,
      "learning_rate": 1.805e-05,
      "loss": 10.394852447509766,
      "step": 640
    },
    {
      "epoch": 325.0,
      "grad_norm": 0.18074513971805573,
      "learning_rate": 1.755e-05,
      "loss": 10.382632446289062,
      "step": 650
    },
    {
      "epoch": 330.0,
      "grad_norm": 0.19741693139076233,
      "learning_rate": 1.705e-05,
      "loss": 10.370597839355469,
      "step": 660
    },
    {
      "epoch": 335.0,
      "grad_norm": 0.1790037453174591,
      "learning_rate": 1.6550000000000002e-05,
      "loss": 10.358709716796875,
      "step": 670
    },
    {
      "epoch": 340.0,
      "grad_norm": 0.18115782737731934,
      "learning_rate": 1.605e-05,
      "loss": 10.348496246337891,
      "step": 680
    },
    {
      "epoch": 345.0,
      "grad_norm": 0.1861548125743866,
      "learning_rate": 1.5550000000000002e-05,
      "loss": 10.337443542480468,
      "step": 690
    },
    {
      "epoch": 350.0,
      "grad_norm": 0.1893489509820938,
      "learning_rate": 1.505e-05,
      "loss": 10.326724243164062,
      "step": 700
    },
    {
      "epoch": 355.0,
      "grad_norm": 0.17952027916908264,
      "learning_rate": 1.455e-05,
      "loss": 10.316475677490235,
      "step": 710
    },
    {
      "epoch": 360.0,
      "grad_norm": 0.18652576208114624,
      "learning_rate": 1.4050000000000003e-05,
      "loss": 10.30637435913086,
      "step": 720
    },
    {
      "epoch": 365.0,
      "grad_norm": 0.18177944421768188,
      "learning_rate": 1.3550000000000002e-05,
      "loss": 10.297893524169922,
      "step": 730
    },
    {
      "epoch": 370.0,
      "grad_norm": 0.1867525577545166,
      "learning_rate": 1.305e-05,
      "loss": 10.287423706054687,
      "step": 740
    },
    {
      "epoch": 375.0,
      "grad_norm": 0.1868598610162735,
      "learning_rate": 1.255e-05,
      "loss": 10.279433441162109,
      "step": 750
    },
    {
      "epoch": 380.0,
      "grad_norm": 0.1965486854314804,
      "learning_rate": 1.205e-05,
      "loss": 10.26949462890625,
      "step": 760
    },
    {
      "epoch": 385.0,
      "grad_norm": 0.19869227707386017,
      "learning_rate": 1.1550000000000001e-05,
      "loss": 10.261733245849609,
      "step": 770
    },
    {
      "epoch": 390.0,
      "grad_norm": 0.18715552985668182,
      "learning_rate": 1.1050000000000001e-05,
      "loss": 10.254318237304688,
      "step": 780
    },
    {
      "epoch": 395.0,
      "grad_norm": 0.19030500948429108,
      "learning_rate": 1.055e-05,
      "loss": 10.24692153930664,
      "step": 790
    },
    {
      "epoch": 400.0,
      "grad_norm": 0.18732821941375732,
      "learning_rate": 1.005e-05,
      "loss": 10.238652801513672,
      "step": 800
    },
    {
      "epoch": 405.0,
      "grad_norm": 0.18254970014095306,
      "learning_rate": 9.55e-06,
      "loss": 10.232601165771484,
      "step": 810
    },
    {
      "epoch": 410.0,
      "grad_norm": 0.19707037508487701,
      "learning_rate": 9.05e-06,
      "loss": 10.226371002197265,
      "step": 820
    },
    {
      "epoch": 415.0,
      "grad_norm": 0.19714631140232086,
      "learning_rate": 8.550000000000001e-06,
      "loss": 10.219265747070313,
      "step": 830
    },
    {
      "epoch": 420.0,
      "grad_norm": 0.18277062475681305,
      "learning_rate": 8.050000000000001e-06,
      "loss": 10.213637542724609,
      "step": 840
    },
    {
      "epoch": 425.0,
      "grad_norm": 0.1907661110162735,
      "learning_rate": 7.55e-06,
      "loss": 10.208641815185548,
      "step": 850
    },
    {
      "epoch": 430.0,
      "grad_norm": 0.1993841677904129,
      "learning_rate": 7.049999999999999e-06,
      "loss": 10.20284194946289,
      "step": 860
    },
    {
      "epoch": 435.0,
      "grad_norm": 0.1809597760438919,
      "learning_rate": 6.550000000000001e-06,
      "loss": 10.198387908935548,
      "step": 870
    },
    {
      "epoch": 440.0,
      "grad_norm": 0.19093714654445648,
      "learning_rate": 6.0500000000000005e-06,
      "loss": 10.194139862060547,
      "step": 880
    },
    {
      "epoch": 445.0,
      "grad_norm": 0.18106074631214142,
      "learning_rate": 5.55e-06,
      "loss": 10.189845275878906,
      "step": 890
    },
    {
      "epoch": 450.0,
      "grad_norm": 0.18310484290122986,
      "learning_rate": 5.050000000000001e-06,
      "loss": 10.18642807006836,
      "step": 900
    },
    {
      "epoch": 455.0,
      "grad_norm": 0.18800194561481476,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 10.182191467285156,
      "step": 910
    },
    {
      "epoch": 460.0,
      "grad_norm": 0.18118229508399963,
      "learning_rate": 4.05e-06,
      "loss": 10.179602813720702,
      "step": 920
    },
    {
      "epoch": 465.0,
      "grad_norm": 0.18121908605098724,
      "learning_rate": 3.55e-06,
      "loss": 10.17755584716797,
      "step": 930
    },
    {
      "epoch": 470.0,
      "grad_norm": 0.1832403838634491,
      "learning_rate": 3.05e-06,
      "loss": 10.174819946289062,
      "step": 940
    },
    {
      "epoch": 475.0,
      "grad_norm": 0.18326261639595032,
      "learning_rate": 2.55e-06,
      "loss": 10.172626495361328,
      "step": 950
    },
    {
      "epoch": 480.0,
      "grad_norm": 0.1977120339870453,
      "learning_rate": 2.0500000000000003e-06,
      "loss": 10.170863342285156,
      "step": 960
    },
    {
      "epoch": 485.0,
      "grad_norm": 0.1997692734003067,
      "learning_rate": 1.55e-06,
      "loss": 10.169485473632813,
      "step": 970
    },
    {
      "epoch": 490.0,
      "grad_norm": 0.1813110113143921,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 10.168987274169922,
      "step": 980
    },
    {
      "epoch": 495.0,
      "grad_norm": 0.18131709098815918,
      "learning_rate": 5.5e-07,
      "loss": 10.167797088623047,
      "step": 990
    },
    {
      "epoch": 500.0,
      "grad_norm": 0.1997884064912796,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 10.167719268798828,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 500,
  "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": 2683677745152000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}