{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.136986301369863,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 6.335273265838623,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.954,
      "step": 10
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 2.381432056427002,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7291,
      "step": 20
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 2.1213607788085938,
      "learning_rate": 2.4e-05,
      "loss": 0.3867,
      "step": 30
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 1.0599077939987183,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2747,
      "step": 40
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 1.1717661619186401,
      "learning_rate": 4e-05,
      "loss": 0.2013,
      "step": 50
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 1.1004457473754883,
      "learning_rate": 4.8e-05,
      "loss": 0.1569,
      "step": 60
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 1.0647892951965332,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.1391,
      "step": 70
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.9715467095375061,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1181,
      "step": 80
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.8772512674331665,
      "learning_rate": 7.2e-05,
      "loss": 0.1051,
      "step": 90
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 1.2750014066696167,
      "learning_rate": 8e-05,
      "loss": 0.0947,
      "step": 100
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 0.6222656965255737,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0978,
      "step": 110
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.6259370446205139,
      "learning_rate": 9.6e-05,
      "loss": 0.0781,
      "step": 120
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 0.6297749876976013,
      "learning_rate": 9.999890641901125e-05,
      "loss": 0.0738,
      "step": 130
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.4628015160560608,
      "learning_rate": 9.999015805811965e-05,
      "loss": 0.0748,
      "step": 140
    },
    {
      "epoch": 1.0273972602739727,
      "grad_norm": 0.6147599816322327,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0641,
      "step": 150
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.5399206280708313,
      "learning_rate": 9.994642390694308e-05,
      "loss": 0.0662,
      "step": 160
    },
    {
      "epoch": 1.1643835616438356,
      "grad_norm": 0.44403907656669617,
      "learning_rate": 9.991144576886823e-05,
      "loss": 0.0592,
      "step": 170
    },
    {
      "epoch": 1.2328767123287672,
      "grad_norm": 0.571832537651062,
      "learning_rate": 9.986773457298311e-05,
      "loss": 0.0556,
      "step": 180
    },
    {
      "epoch": 1.3013698630136985,
      "grad_norm": 0.561576247215271,
      "learning_rate": 9.981529796748134e-05,
      "loss": 0.0596,
      "step": 190
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.4030166268348694,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0539,
      "step": 200
    },
    {
      "epoch": 1.4383561643835616,
      "grad_norm": 0.34468358755111694,
      "learning_rate": 9.968428675226714e-05,
      "loss": 0.0577,
      "step": 210
    },
    {
      "epoch": 1.5068493150684932,
      "grad_norm": 0.483900785446167,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.052,
      "step": 220
    },
    {
      "epoch": 1.5753424657534247,
      "grad_norm": 0.4898487627506256,
      "learning_rate": 9.95185038118915e-05,
      "loss": 0.0477,
      "step": 230
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.5045291781425476,
      "learning_rate": 9.942260825371358e-05,
      "loss": 0.0528,
      "step": 240
    },
    {
      "epoch": 1.7123287671232876,
      "grad_norm": 0.5695160031318665,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0439,
      "step": 250
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 0.33678483963012695,
      "learning_rate": 9.92048928531717e-05,
      "loss": 0.0488,
      "step": 260
    },
    {
      "epoch": 1.8493150684931505,
      "grad_norm": 0.3467772305011749,
      "learning_rate": 9.90831111046988e-05,
      "loss": 0.0448,
      "step": 270
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.4071213901042938,
      "learning_rate": 9.895274123299723e-05,
      "loss": 0.0431,
      "step": 280
    },
    {
      "epoch": 1.9863013698630136,
      "grad_norm": 0.30543234944343567,
      "learning_rate": 9.881380604901964e-05,
      "loss": 0.0429,
      "step": 290
    },
    {
      "epoch": 2.0547945205479454,
      "grad_norm": 0.6378459334373474,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0464,
      "step": 300
    },
    {
      "epoch": 2.1232876712328768,
      "grad_norm": 0.4035351276397705,
      "learning_rate": 9.851033847720166e-05,
      "loss": 0.0488,
      "step": 310
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.3094054162502289,
      "learning_rate": 9.834585918739936e-05,
      "loss": 0.0364,
      "step": 320
    },
    {
      "epoch": 2.26027397260274,
      "grad_norm": 0.45768025517463684,
      "learning_rate": 9.817292077210659e-05,
      "loss": 0.0373,
      "step": 330
    },
    {
      "epoch": 2.328767123287671,
      "grad_norm": 0.504475474357605,
      "learning_rate": 9.799155349053851e-05,
      "loss": 0.047,
      "step": 340
    },
    {
      "epoch": 2.3972602739726026,
      "grad_norm": 0.36838439106941223,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0396,
      "step": 350
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.3892686665058136,
      "learning_rate": 9.760366073392246e-05,
      "loss": 0.04,
      "step": 360
    },
    {
      "epoch": 2.5342465753424657,
      "grad_norm": 0.376288503408432,
      "learning_rate": 9.739720312887535e-05,
      "loss": 0.0352,
      "step": 370
    },
    {
      "epoch": 2.602739726027397,
      "grad_norm": 0.33039844036102295,
      "learning_rate": 9.718245238567939e-05,
      "loss": 0.0364,
      "step": 380
    },
    {
      "epoch": 2.671232876712329,
      "grad_norm": 0.38675811886787415,
      "learning_rate": 9.695944607949649e-05,
      "loss": 0.0367,
      "step": 390
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.3453963100910187,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0337,
      "step": 400
    },
    {
      "epoch": 2.808219178082192,
      "grad_norm": 0.5285444259643555,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.0414,
      "step": 410
    },
    {
      "epoch": 2.8767123287671232,
      "grad_norm": 0.38015297055244446,
      "learning_rate": 9.624129116069694e-05,
      "loss": 0.0348,
      "step": 420
    },
    {
      "epoch": 2.9452054794520546,
      "grad_norm": 0.44161203503608704,
      "learning_rate": 9.598566713995718e-05,
      "loss": 0.0377,
      "step": 430
    },
    {
      "epoch": 3.0136986301369864,
      "grad_norm": 0.4227602779865265,
      "learning_rate": 9.572199695899522e-05,
      "loss": 0.0323,
      "step": 440
    },
    {
      "epoch": 3.0821917808219177,
      "grad_norm": 0.2722010314464569,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0345,
      "step": 450
    },
    {
      "epoch": 3.1506849315068495,
      "grad_norm": 0.4375353753566742,
      "learning_rate": 9.517070405476575e-05,
      "loss": 0.0315,
      "step": 460
    },
    {
      "epoch": 3.219178082191781,
      "grad_norm": 0.4301266372203827,
      "learning_rate": 9.488317779179361e-05,
      "loss": 0.0348,
      "step": 470
    },
    {
      "epoch": 3.287671232876712,
      "grad_norm": 0.458469957113266,
      "learning_rate": 9.458779827231237e-05,
      "loss": 0.0348,
      "step": 480
    },
    {
      "epoch": 3.356164383561644,
      "grad_norm": 0.3810347616672516,
      "learning_rate": 9.428461717918511e-05,
      "loss": 0.0304,
      "step": 490
    },
    {
      "epoch": 3.4246575342465753,
      "grad_norm": 0.3728407919406891,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0332,
      "step": 500
    },
    {
      "epoch": 3.493150684931507,
      "grad_norm": 0.3293081223964691,
      "learning_rate": 9.365506381941066e-05,
      "loss": 0.0305,
      "step": 510
    },
    {
      "epoch": 3.5616438356164384,
      "grad_norm": 0.35907241702079773,
      "learning_rate": 9.332880170637252e-05,
      "loss": 0.0319,
      "step": 520
    },
    {
      "epoch": 3.6301369863013697,
      "grad_norm": 0.3396986126899719,
      "learning_rate": 9.299495830763286e-05,
      "loss": 0.0319,
      "step": 530
    },
    {
      "epoch": 3.6986301369863015,
      "grad_norm": 0.22632896900177002,
      "learning_rate": 9.265359203611987e-05,
      "loss": 0.0318,
      "step": 540
    },
    {
      "epoch": 3.767123287671233,
      "grad_norm": 0.2579493522644043,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0295,
      "step": 550
    },
    {
      "epoch": 3.8356164383561646,
      "grad_norm": 0.2979259788990021,
      "learning_rate": 9.194853109746074e-05,
      "loss": 0.0317,
      "step": 560
    },
    {
      "epoch": 3.904109589041096,
      "grad_norm": 0.28193944692611694,
      "learning_rate": 9.158495979556358e-05,
      "loss": 0.0324,
      "step": 570
    },
    {
      "epoch": 3.9726027397260273,
      "grad_norm": 0.30196675658226013,
      "learning_rate": 9.121411232980588e-05,
      "loss": 0.0282,
      "step": 580
    },
    {
      "epoch": 4.041095890410959,
      "grad_norm": 0.2790427505970001,
      "learning_rate": 9.083605358775612e-05,
      "loss": 0.0322,
      "step": 590
    },
    {
      "epoch": 4.109589041095891,
      "grad_norm": 0.3180605173110962,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0311,
      "step": 600
    },
    {
      "epoch": 4.178082191780822,
      "grad_norm": 0.23422259092330933,
      "learning_rate": 9.005856812230304e-05,
      "loss": 0.0313,
      "step": 610
    },
    {
      "epoch": 4.2465753424657535,
      "grad_norm": 0.1887388378381729,
      "learning_rate": 8.965927743634391e-05,
      "loss": 0.0297,
      "step": 620
    },
    {
      "epoch": 4.315068493150685,
      "grad_norm": 0.21844805777072906,
      "learning_rate": 8.92530475251784e-05,
      "loss": 0.0306,
      "step": 630
    },
    {
      "epoch": 4.383561643835616,
      "grad_norm": 0.45273661613464355,
      "learning_rate": 8.883994946727849e-05,
      "loss": 0.0292,
      "step": 640
    },
    {
      "epoch": 4.4520547945205475,
      "grad_norm": 0.39670127630233765,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0331,
      "step": 650
    },
    {
      "epoch": 4.52054794520548,
      "grad_norm": 0.25612273812294006,
      "learning_rate": 8.799343922115044e-05,
      "loss": 0.0305,
      "step": 660
    },
    {
      "epoch": 4.589041095890411,
      "grad_norm": 0.22720636427402496,
      "learning_rate": 8.756017514770443e-05,
      "loss": 0.0284,
      "step": 670
    },
    {
      "epoch": 4.657534246575342,
      "grad_norm": 0.39644864201545715,
      "learning_rate": 8.71203391311725e-05,
      "loss": 0.0286,
      "step": 680
    },
    {
      "epoch": 4.726027397260274,
      "grad_norm": 0.4030825197696686,
      "learning_rate": 8.6674008130122e-05,
      "loss": 0.0268,
      "step": 690
    },
    {
      "epoch": 4.794520547945205,
      "grad_norm": 0.33811622858047485,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0274,
      "step": 700
    },
    {
      "epoch": 4.863013698630137,
      "grad_norm": 0.27626654505729675,
      "learning_rate": 8.576217467724128e-05,
      "loss": 0.0267,
      "step": 710
    },
    {
      "epoch": 4.931506849315069,
      "grad_norm": 0.3249574899673462,
      "learning_rate": 8.529683176986295e-05,
      "loss": 0.0297,
      "step": 720
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6223666071891785,
      "learning_rate": 8.482531293895412e-05,
      "loss": 0.0289,
      "step": 730
    },
    {
      "epoch": 5.068493150684931,
      "grad_norm": 0.4200395941734314,
      "learning_rate": 8.434770068665723e-05,
      "loss": 0.0293,
      "step": 740
    },
    {
      "epoch": 5.136986301369863,
      "grad_norm": 0.33773040771484375,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0243,
      "step": 750
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 18,
  "save_steps": 125,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0243918948403232e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}