{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1008,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02976190476190476,
      "grad_norm": 9.855416467128451,
      "learning_rate": 3.2894736842105264e-07,
      "loss": 0.8831,
      "step": 10
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 4.058333207297266,
      "learning_rate": 6.578947368421053e-07,
      "loss": 0.7946,
      "step": 20
    },
    {
      "epoch": 0.08928571428571429,
      "grad_norm": 1.7570375433828875,
      "learning_rate": 9.86842105263158e-07,
      "loss": 0.7122,
      "step": 30
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 1.1575290406793173,
      "learning_rate": 1.3157894736842106e-06,
      "loss": 0.6601,
      "step": 40
    },
    {
      "epoch": 0.1488095238095238,
      "grad_norm": 1.1945148190883437,
      "learning_rate": 1.6447368421052635e-06,
      "loss": 0.6275,
      "step": 50
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.221041026154983,
      "learning_rate": 1.973684210526316e-06,
      "loss": 0.6052,
      "step": 60
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 3.3209006702030646,
      "learning_rate": 2.3026315789473684e-06,
      "loss": 0.586,
      "step": 70
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 3.6681811496303838,
      "learning_rate": 2.631578947368421e-06,
      "loss": 0.5798,
      "step": 80
    },
    {
      "epoch": 0.26785714285714285,
      "grad_norm": 3.2185752709902724,
      "learning_rate": 2.960526315789474e-06,
      "loss": 0.5666,
      "step": 90
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 3.4706862638119795,
      "learning_rate": 3.289473684210527e-06,
      "loss": 0.5638,
      "step": 100
    },
    {
      "epoch": 0.3273809523809524,
      "grad_norm": 3.6113112350238055,
      "learning_rate": 3.618421052631579e-06,
      "loss": 0.5522,
      "step": 110
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 3.2305389516520107,
      "learning_rate": 3.947368421052632e-06,
      "loss": 0.5463,
      "step": 120
    },
    {
      "epoch": 0.3869047619047619,
      "grad_norm": 3.038105776417889,
      "learning_rate": 4.276315789473684e-06,
      "loss": 0.5435,
      "step": 130
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 2.8452115838960004,
      "learning_rate": 4.605263157894737e-06,
      "loss": 0.5368,
      "step": 140
    },
    {
      "epoch": 0.44642857142857145,
      "grad_norm": 2.885654936231309,
      "learning_rate": 4.9342105263157895e-06,
      "loss": 0.5371,
      "step": 150
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.4395389590432695,
      "learning_rate": 4.998922515567496e-06,
      "loss": 0.5311,
      "step": 160
    },
    {
      "epoch": 0.5059523809523809,
      "grad_norm": 3.316027131916539,
      "learning_rate": 4.994546826814266e-06,
      "loss": 0.5306,
      "step": 170
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 2.1091015101835064,
      "learning_rate": 4.986811479610213e-06,
      "loss": 0.5235,
      "step": 180
    },
    {
      "epoch": 0.5654761904761905,
      "grad_norm": 3.105111788839091,
      "learning_rate": 4.975726891929585e-06,
      "loss": 0.5172,
      "step": 190
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 2.4351797747389288,
      "learning_rate": 4.9613079925074435e-06,
      "loss": 0.5127,
      "step": 200
    },
    {
      "epoch": 0.625,
      "grad_norm": 2.058969332069431,
      "learning_rate": 4.943574200733625e-06,
      "loss": 0.5135,
      "step": 210
    },
    {
      "epoch": 0.6547619047619048,
      "grad_norm": 1.777838918535288,
      "learning_rate": 4.922549400498685e-06,
      "loss": 0.5089,
      "step": 220
    },
    {
      "epoch": 0.6845238095238095,
      "grad_norm": 2.7154588748327986,
      "learning_rate": 4.89826190802705e-06,
      "loss": 0.5037,
      "step": 230
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.5679948903593761,
      "learning_rate": 4.870744433740688e-06,
      "loss": 0.4986,
      "step": 240
    },
    {
      "epoch": 0.7440476190476191,
      "grad_norm": 1.4962958992598898,
      "learning_rate": 4.840034038204687e-06,
      "loss": 0.4972,
      "step": 250
    },
    {
      "epoch": 0.7738095238095238,
      "grad_norm": 2.122366808210638,
      "learning_rate": 4.806172082214032e-06,
      "loss": 0.4989,
      "step": 260
    },
    {
      "epoch": 0.8035714285714286,
      "grad_norm": 2.0302822908345153,
      "learning_rate": 4.7692041710888495e-06,
      "loss": 0.4901,
      "step": 270
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 3.5745905459632543,
      "learning_rate": 4.729180093253106e-06,
      "loss": 0.4916,
      "step": 280
    },
    {
      "epoch": 0.8630952380952381,
      "grad_norm": 1.8908937013266554,
      "learning_rate": 4.6861537531795095e-06,
      "loss": 0.4883,
      "step": 290
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 2.6221469442693652,
      "learning_rate": 4.640183098790896e-06,
      "loss": 0.4867,
      "step": 300
    },
    {
      "epoch": 0.9226190476190477,
      "grad_norm": 2.112945737548425,
      "learning_rate": 4.5913300434159095e-06,
      "loss": 0.4808,
      "step": 310
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.167157341115666,
      "learning_rate": 4.53966038240406e-06,
      "loss": 0.4829,
      "step": 320
    },
    {
      "epoch": 0.9821428571428571,
      "grad_norm": 1.7665074082761922,
      "learning_rate": 4.485243704512474e-06,
      "loss": 0.4775,
      "step": 330
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.05986911430954933,
      "eval_runtime": 228.6618,
      "eval_samples_per_second": 79.169,
      "eval_steps_per_second": 0.621,
      "step": 336
    },
    {
      "epoch": 1.0119047619047619,
      "grad_norm": 2.7005444699805397,
      "learning_rate": 4.428153298183676e-06,
      "loss": 0.4615,
      "step": 340
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 2.1637697857642766,
      "learning_rate": 4.368466052840636e-06,
      "loss": 0.4222,
      "step": 350
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 2.1155220244099318,
      "learning_rate": 4.306262355332006e-06,
      "loss": 0.4226,
      "step": 360
    },
    {
      "epoch": 1.1011904761904763,
      "grad_norm": 2.9522060556993805,
      "learning_rate": 4.2416259816670235e-06,
      "loss": 0.4231,
      "step": 370
    },
    {
      "epoch": 1.130952380952381,
      "grad_norm": 3.069829782500402,
      "learning_rate": 4.17464398418589e-06,
      "loss": 0.424,
      "step": 380
    },
    {
      "epoch": 1.1607142857142858,
      "grad_norm": 3.0267979137491263,
      "learning_rate": 4.105406574317579e-06,
      "loss": 0.4244,
      "step": 390
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 2.1977669399883695,
      "learning_rate": 4.034007001082985e-06,
      "loss": 0.418,
      "step": 400
    },
    {
      "epoch": 1.2202380952380953,
      "grad_norm": 2.697858786471712,
      "learning_rate": 3.960541425507039e-06,
      "loss": 0.4233,
      "step": 410
    },
    {
      "epoch": 1.25,
      "grad_norm": 2.493946030937562,
      "learning_rate": 3.8851087911089315e-06,
      "loss": 0.4198,
      "step": 420
    },
    {
      "epoch": 1.2797619047619047,
      "grad_norm": 2.2545695426043544,
      "learning_rate": 3.8078106906448684e-06,
      "loss": 0.4183,
      "step": 430
    },
    {
      "epoch": 1.3095238095238095,
      "grad_norm": 2.375162881348148,
      "learning_rate": 3.7287512292828364e-06,
      "loss": 0.4168,
      "step": 440
    },
    {
      "epoch": 1.3392857142857144,
      "grad_norm": 1.5621396833558368,
      "learning_rate": 3.6480368843936463e-06,
      "loss": 0.4163,
      "step": 450
    },
    {
      "epoch": 1.369047619047619,
      "grad_norm": 1.3598263826513288,
      "learning_rate": 3.5657763621470905e-06,
      "loss": 0.4197,
      "step": 460
    },
    {
      "epoch": 1.3988095238095237,
      "grad_norm": 1.6629757133775533,
      "learning_rate": 3.48208045110635e-06,
      "loss": 0.4187,
      "step": 470
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 2.2093813175502968,
      "learning_rate": 3.39706187301784e-06,
      "loss": 0.4166,
      "step": 480
    },
    {
      "epoch": 1.4583333333333333,
      "grad_norm": 1.884934841996157,
      "learning_rate": 3.3108351309974286e-06,
      "loss": 0.4154,
      "step": 490
    },
    {
      "epoch": 1.4880952380952381,
      "grad_norm": 1.5082137043399462,
      "learning_rate": 3.2235163553175174e-06,
      "loss": 0.417,
      "step": 500
    },
    {
      "epoch": 1.5178571428571428,
      "grad_norm": 1.3657040531080291,
      "learning_rate": 3.1352231470026583e-06,
      "loss": 0.416,
      "step": 510
    },
    {
      "epoch": 1.5476190476190477,
      "grad_norm": 1.2254626355269007,
      "learning_rate": 3.0460744194443658e-06,
      "loss": 0.4142,
      "step": 520
    },
    {
      "epoch": 1.5773809523809523,
      "grad_norm": 1.1398076994088004,
      "learning_rate": 2.956190238248425e-06,
      "loss": 0.4149,
      "step": 530
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 1.1825076561434265,
      "learning_rate": 2.8656916595304026e-06,
      "loss": 0.4133,
      "step": 540
    },
    {
      "epoch": 1.6369047619047619,
      "grad_norm": 1.5151800119422074,
      "learning_rate": 2.7747005668771293e-06,
      "loss": 0.4173,
      "step": 550
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.4847041684984181,
      "learning_rate": 2.68333950719376e-06,
      "loss": 0.4122,
      "step": 560
    },
    {
      "epoch": 1.6964285714285714,
      "grad_norm": 1.4926221075919288,
      "learning_rate": 2.5917315256574543e-06,
      "loss": 0.4138,
      "step": 570
    },
    {
      "epoch": 1.7261904761904763,
      "grad_norm": 1.4851596357393222,
      "learning_rate": 2.5e-06,
      "loss": 0.4146,
      "step": 580
    },
    {
      "epoch": 1.755952380952381,
      "grad_norm": 1.4494102675836165,
      "learning_rate": 2.4082684743425457e-06,
      "loss": 0.41,
      "step": 590
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 1.096907686976151,
      "learning_rate": 2.3166604928062407e-06,
      "loss": 0.4083,
      "step": 600
    },
    {
      "epoch": 1.8154761904761905,
      "grad_norm": 1.1069324511062155,
      "learning_rate": 2.2252994331228715e-06,
      "loss": 0.4092,
      "step": 610
    },
    {
      "epoch": 1.8452380952380953,
      "grad_norm": 1.5676344586960804,
      "learning_rate": 2.1343083404695987e-06,
      "loss": 0.4071,
      "step": 620
    },
    {
      "epoch": 1.875,
      "grad_norm": 1.5244672991700199,
      "learning_rate": 2.0438097617515744e-06,
      "loss": 0.4092,
      "step": 630
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 1.1711984219863045,
      "learning_rate": 1.9539255805556346e-06,
      "loss": 0.4056,
      "step": 640
    },
    {
      "epoch": 1.9345238095238095,
      "grad_norm": 1.2364277364431069,
      "learning_rate": 1.8647768529973426e-06,
      "loss": 0.4065,
      "step": 650
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 1.173689997741917,
      "learning_rate": 1.7764836446824835e-06,
      "loss": 0.4066,
      "step": 660
    },
    {
      "epoch": 1.994047619047619,
      "grad_norm": 1.0429379558488223,
      "learning_rate": 1.689164869002572e-06,
      "loss": 0.4039,
      "step": 670
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.05654621869325638,
      "eval_runtime": 233.1622,
      "eval_samples_per_second": 77.641,
      "eval_steps_per_second": 0.609,
      "step": 672
    },
    {
      "epoch": 2.0238095238095237,
      "grad_norm": 1.8042620783640224,
      "learning_rate": 1.6029381269821607e-06,
      "loss": 0.355,
      "step": 680
    },
    {
      "epoch": 2.0535714285714284,
      "grad_norm": 1.3103423601245003,
      "learning_rate": 1.5179195488936505e-06,
      "loss": 0.342,
      "step": 690
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 1.1981284388735467,
      "learning_rate": 1.4342236378529106e-06,
      "loss": 0.3394,
      "step": 700
    },
    {
      "epoch": 2.113095238095238,
      "grad_norm": 1.3227357738839063,
      "learning_rate": 1.351963115606354e-06,
      "loss": 0.3363,
      "step": 710
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 1.0826862483712594,
      "learning_rate": 1.2712487707171645e-06,
      "loss": 0.3378,
      "step": 720
    },
    {
      "epoch": 2.1726190476190474,
      "grad_norm": 1.2571941714304598,
      "learning_rate": 1.1921893093551324e-06,
      "loss": 0.338,
      "step": 730
    },
    {
      "epoch": 2.2023809523809526,
      "grad_norm": 1.168368127805181,
      "learning_rate": 1.1148912088910687e-06,
      "loss": 0.3363,
      "step": 740
    },
    {
      "epoch": 2.232142857142857,
      "grad_norm": 1.1226203835961706,
      "learning_rate": 1.0394585744929605e-06,
      "loss": 0.3393,
      "step": 750
    },
    {
      "epoch": 2.261904761904762,
      "grad_norm": 1.0656940582932617,
      "learning_rate": 9.659929989170156e-07,
      "loss": 0.3401,
      "step": 760
    },
    {
      "epoch": 2.2916666666666665,
      "grad_norm": 1.074973225972827,
      "learning_rate": 8.945934256824218e-07,
      "loss": 0.3356,
      "step": 770
    },
    {
      "epoch": 2.3214285714285716,
      "grad_norm": 1.1457434350978388,
      "learning_rate": 8.253560158141111e-07,
      "loss": 0.3372,
      "step": 780
    },
    {
      "epoch": 2.3511904761904763,
      "grad_norm": 1.0748233318983023,
      "learning_rate": 7.583740183329769e-07,
      "loss": 0.3339,
      "step": 790
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 1.0162550586451078,
      "learning_rate": 6.93737644667995e-07,
      "loss": 0.3366,
      "step": 800
    },
    {
      "epoch": 2.4107142857142856,
      "grad_norm": 1.0398744748365716,
      "learning_rate": 6.315339471593646e-07,
      "loss": 0.3359,
      "step": 810
    },
    {
      "epoch": 2.4404761904761907,
      "grad_norm": 1.0255604222182617,
      "learning_rate": 5.718467018163243e-07,
      "loss": 0.3344,
      "step": 820
    },
    {
      "epoch": 2.4702380952380953,
      "grad_norm": 0.9872536325493508,
      "learning_rate": 5.147562954875269e-07,
      "loss": 0.3362,
      "step": 830
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.0132034371898346,
      "learning_rate": 4.6033961759594045e-07,
      "loss": 0.3337,
      "step": 840
    },
    {
      "epoch": 2.5297619047619047,
      "grad_norm": 1.0177216034721577,
      "learning_rate": 4.0866995658409155e-07,
      "loss": 0.3363,
      "step": 850
    },
    {
      "epoch": 2.5595238095238093,
      "grad_norm": 0.9981956934484016,
      "learning_rate": 3.598169012091049e-07,
      "loss": 0.3362,
      "step": 860
    },
    {
      "epoch": 2.5892857142857144,
      "grad_norm": 0.9529369028261363,
      "learning_rate": 3.1384624682049144e-07,
      "loss": 0.3394,
      "step": 870
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.9766851469747638,
      "learning_rate": 2.708199067468939e-07,
      "loss": 0.3343,
      "step": 880
    },
    {
      "epoch": 2.6488095238095237,
      "grad_norm": 0.9534173170238686,
      "learning_rate": 2.3079582891115144e-07,
      "loss": 0.3358,
      "step": 890
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.9571473294443575,
      "learning_rate": 1.9382791778596864e-07,
      "loss": 0.3343,
      "step": 900
    },
    {
      "epoch": 2.7083333333333335,
      "grad_norm": 0.9382822776109654,
      "learning_rate": 1.5996596179531365e-07,
      "loss": 0.3348,
      "step": 910
    },
    {
      "epoch": 2.738095238095238,
      "grad_norm": 0.9309707054846061,
      "learning_rate": 1.2925556625931174e-07,
      "loss": 0.3375,
      "step": 920
    },
    {
      "epoch": 2.767857142857143,
      "grad_norm": 0.9621376118686727,
      "learning_rate": 1.0173809197295075e-07,
      "loss": 0.336,
      "step": 930
    },
    {
      "epoch": 2.7976190476190474,
      "grad_norm": 0.9169046599509947,
      "learning_rate": 7.7450599501315e-08,
      "loss": 0.3339,
      "step": 940
    },
    {
      "epoch": 2.8273809523809526,
      "grad_norm": 0.9398290467609749,
      "learning_rate": 5.6425799266375534e-08,
      "loss": 0.335,
      "step": 950
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.9100820752220524,
      "learning_rate": 3.869200749255703e-08,
      "loss": 0.334,
      "step": 960
    },
    {
      "epoch": 2.886904761904762,
      "grad_norm": 0.904751932290303,
      "learning_rate": 2.427310807041561e-08,
      "loss": 0.3327,
      "step": 970
    },
    {
      "epoch": 2.9166666666666665,
      "grad_norm": 0.913682536330684,
      "learning_rate": 1.3188520389787462e-08,
      "loss": 0.3313,
      "step": 980
    },
    {
      "epoch": 2.946428571428571,
      "grad_norm": 0.9340585620250436,
      "learning_rate": 5.453173185734073e-09,
      "loss": 0.336,
      "step": 990
    },
    {
      "epoch": 2.9761904761904763,
      "grad_norm": 0.9406350686317787,
      "learning_rate": 1.0774844325039946e-09,
      "loss": 0.3325,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.057458870112895966,
      "eval_runtime": 228.1192,
      "eval_samples_per_second": 79.358,
      "eval_steps_per_second": 0.622,
      "step": 1008
    },
    {
      "epoch": 3.0,
      "step": 1008,
      "total_flos": 3376456327495680.0,
      "train_loss": 0.4351037277115716,
      "train_runtime": 33019.7588,
      "train_samples_per_second": 31.25,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 1008,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3376456327495680.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}