{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7711654268508679,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017711654268508677,
      "grad_norm": 282.9578857421875,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 515.0844,
      "step": 100
    },
    {
      "epoch": 0.035423308537017355,
      "grad_norm": 952.3278198242188,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 282.6205,
      "step": 200
    },
    {
      "epoch": 0.053134962805526036,
      "grad_norm": 421.5475158691406,
      "learning_rate": 3e-06,
      "loss": 187.263,
      "step": 300
    },
    {
      "epoch": 0.07084661707403471,
      "grad_norm": 697.6055908203125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 181.7124,
      "step": 400
    },
    {
      "epoch": 0.08855827134254339,
      "grad_norm": 12816.384765625,
      "learning_rate": 5e-06,
      "loss": 181.1332,
      "step": 500
    },
    {
      "epoch": 0.10626992561105207,
      "grad_norm": 943.728515625,
      "learning_rate": 6e-06,
      "loss": 119.6682,
      "step": 600
    },
    {
      "epoch": 0.12398157987956075,
      "grad_norm": 1511.4503173828125,
      "learning_rate": 7e-06,
      "loss": 265.4774,
      "step": 700
    },
    {
      "epoch": 0.14169323414806942,
      "grad_norm": 738.5520629882812,
      "learning_rate": 8.000000000000001e-06,
      "loss": 293.2895,
      "step": 800
    },
    {
      "epoch": 0.1594048884165781,
      "grad_norm": 683.668212890625,
      "learning_rate": 9e-06,
      "loss": 170.2527,
      "step": 900
    },
    {
      "epoch": 0.17711654268508678,
      "grad_norm": 2968.679443359375,
      "learning_rate": 1e-05,
      "loss": 307.2464,
      "step": 1000
    },
    {
      "epoch": 0.19482819695359546,
      "grad_norm": 358.26092529296875,
      "learning_rate": 9.99695413509548e-06,
      "loss": 191.1959,
      "step": 1100
    },
    {
      "epoch": 0.21253985122210414,
      "grad_norm": 814.0306396484375,
      "learning_rate": 9.987820251299121e-06,
      "loss": 118.1777,
      "step": 1200
    },
    {
      "epoch": 0.23025150549061282,
      "grad_norm": 1002.783935546875,
      "learning_rate": 9.972609476841368e-06,
      "loss": 152.1576,
      "step": 1300
    },
    {
      "epoch": 0.2479631597591215,
      "grad_norm": 3436.5205078125,
      "learning_rate": 9.951340343707852e-06,
      "loss": 139.2181,
      "step": 1400
    },
    {
      "epoch": 0.26567481402763016,
      "grad_norm": 895.021484375,
      "learning_rate": 9.924038765061042e-06,
      "loss": 254.7134,
      "step": 1500
    },
    {
      "epoch": 0.28338646829613884,
      "grad_norm": 485.51300048828125,
      "learning_rate": 9.890738003669029e-06,
      "loss": 130.9937,
      "step": 1600
    },
    {
      "epoch": 0.3010981225646475,
      "grad_norm": 3067.70166015625,
      "learning_rate": 9.851478631379982e-06,
      "loss": 130.5014,
      "step": 1700
    },
    {
      "epoch": 0.3188097768331562,
      "grad_norm": 710.6421508789062,
      "learning_rate": 9.806308479691595e-06,
      "loss": 138.9038,
      "step": 1800
    },
    {
      "epoch": 0.3365214311016649,
      "grad_norm": 791.8126831054688,
      "learning_rate": 9.755282581475769e-06,
      "loss": 135.9246,
      "step": 1900
    },
    {
      "epoch": 0.35423308537017356,
      "grad_norm": 744.6799926757812,
      "learning_rate": 9.698463103929542e-06,
      "loss": 132.2486,
      "step": 2000
    },
    {
      "epoch": 0.37194473963868224,
      "grad_norm": 155.03514099121094,
      "learning_rate": 9.635919272833938e-06,
      "loss": 90.2381,
      "step": 2100
    },
    {
      "epoch": 0.3896563939071909,
      "grad_norm": 553.8131103515625,
      "learning_rate": 9.567727288213005e-06,
      "loss": 93.5386,
      "step": 2200
    },
    {
      "epoch": 0.4073680481756996,
      "grad_norm": 778.4810791015625,
      "learning_rate": 9.493970231495836e-06,
      "loss": 151.3705,
      "step": 2300
    },
    {
      "epoch": 0.4250797024442083,
      "grad_norm": 613.4912109375,
      "learning_rate": 9.414737964294636e-06,
      "loss": 149.8487,
      "step": 2400
    },
    {
      "epoch": 0.44279135671271697,
      "grad_norm": 202.41319274902344,
      "learning_rate": 9.330127018922195e-06,
      "loss": 121.8082,
      "step": 2500
    },
    {
      "epoch": 0.46050301098122565,
      "grad_norm": 1176.41064453125,
      "learning_rate": 9.24024048078213e-06,
      "loss": 92.7877,
      "step": 2600
    },
    {
      "epoch": 0.4782146652497343,
      "grad_norm": 2264.6943359375,
      "learning_rate": 9.145187862775208e-06,
      "loss": 109.0094,
      "step": 2700
    },
    {
      "epoch": 0.495926319518243,
      "grad_norm": 1426.1497802734375,
      "learning_rate": 9.045084971874738e-06,
      "loss": 179.5395,
      "step": 2800
    },
    {
      "epoch": 0.5136379737867517,
      "grad_norm": 1707.4801025390625,
      "learning_rate": 8.94005376803361e-06,
      "loss": 97.74,
      "step": 2900
    },
    {
      "epoch": 0.5313496280552603,
      "grad_norm": 622.0428466796875,
      "learning_rate": 8.83022221559489e-06,
      "loss": 69.5907,
      "step": 3000
    },
    {
      "epoch": 0.549061282323769,
      "grad_norm": 650.7168579101562,
      "learning_rate": 8.715724127386971e-06,
      "loss": 101.6783,
      "step": 3100
    },
    {
      "epoch": 0.5667729365922777,
      "grad_norm": 741.4815673828125,
      "learning_rate": 8.596699001693257e-06,
      "loss": 71.9482,
      "step": 3200
    },
    {
      "epoch": 0.5844845908607864,
      "grad_norm": 232.25784301757812,
      "learning_rate": 8.473291852294986e-06,
      "loss": 84.9108,
      "step": 3300
    },
    {
      "epoch": 0.602196245129295,
      "grad_norm": 1159.53662109375,
      "learning_rate": 8.345653031794292e-06,
      "loss": 81.3379,
      "step": 3400
    },
    {
      "epoch": 0.6199078993978038,
      "grad_norm": 164.65911865234375,
      "learning_rate": 8.213938048432697e-06,
      "loss": 82.0289,
      "step": 3500
    },
    {
      "epoch": 0.6376195536663124,
      "grad_norm": 326.4909362792969,
      "learning_rate": 8.078307376628292e-06,
      "loss": 66.5258,
      "step": 3600
    },
    {
      "epoch": 0.6553312079348211,
      "grad_norm": 404.8460693359375,
      "learning_rate": 7.938926261462366e-06,
      "loss": 77.1912,
      "step": 3700
    },
    {
      "epoch": 0.6730428622033298,
      "grad_norm": 544.1323852539062,
      "learning_rate": 7.795964517353734e-06,
      "loss": 117.8293,
      "step": 3800
    },
    {
      "epoch": 0.6907545164718385,
      "grad_norm": 2064.937744140625,
      "learning_rate": 7.649596321166024e-06,
      "loss": 80.8055,
      "step": 3900
    },
    {
      "epoch": 0.7084661707403471,
      "grad_norm": 403.4572448730469,
      "learning_rate": 7.500000000000001e-06,
      "loss": 96.7227,
      "step": 4000
    },
    {
      "epoch": 0.7261778250088559,
      "grad_norm": 666.6998291015625,
      "learning_rate": 7.347357813929455e-06,
      "loss": 140.3281,
      "step": 4100
    },
    {
      "epoch": 0.7438894792773645,
      "grad_norm": 1186.9765625,
      "learning_rate": 7.191855733945388e-06,
      "loss": 110.6341,
      "step": 4200
    },
    {
      "epoch": 0.7616011335458732,
      "grad_norm": 416.6499938964844,
      "learning_rate": 7.033683215379002e-06,
      "loss": 116.5317,
      "step": 4300
    },
    {
      "epoch": 0.7793127878143818,
      "grad_norm": 1019.04248046875,
      "learning_rate": 6.873032967079562e-06,
      "loss": 159.9792,
      "step": 4400
    },
    {
      "epoch": 0.7970244420828906,
      "grad_norm": 2007.982421875,
      "learning_rate": 6.710100716628345e-06,
      "loss": 96.393,
      "step": 4500
    },
    {
      "epoch": 0.8147360963513992,
      "grad_norm": 1629.4732666015625,
      "learning_rate": 6.545084971874738e-06,
      "loss": 134.7197,
      "step": 4600
    },
    {
      "epoch": 0.832447750619908,
      "grad_norm": 801.6519775390625,
      "learning_rate": 6.378186779084996e-06,
      "loss": 117.0068,
      "step": 4700
    },
    {
      "epoch": 0.8501594048884166,
      "grad_norm": 572.10205078125,
      "learning_rate": 6.209609477998339e-06,
      "loss": 76.2736,
      "step": 4800
    },
    {
      "epoch": 0.8678710591569253,
      "grad_norm": 307.35955810546875,
      "learning_rate": 6.039558454088796e-06,
      "loss": 101.7736,
      "step": 4900
    },
    {
      "epoch": 0.8855827134254339,
      "grad_norm": 356.9403076171875,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 96.7568,
      "step": 5000
    },
    {
      "epoch": 0.9032943676939427,
      "grad_norm": 255.03634643554688,
      "learning_rate": 5.695865504800328e-06,
      "loss": 118.3934,
      "step": 5100
    },
    {
      "epoch": 0.9210060219624513,
      "grad_norm": 567.1763305664062,
      "learning_rate": 5.522642316338268e-06,
      "loss": 117.496,
      "step": 5200
    },
    {
      "epoch": 0.9387176762309599,
      "grad_norm": 1406.6500244140625,
      "learning_rate": 5.348782368720627e-06,
      "loss": 83.3509,
      "step": 5300
    },
    {
      "epoch": 0.9564293304994687,
      "grad_norm": 1967.540283203125,
      "learning_rate": 5.174497483512506e-06,
      "loss": 136.5233,
      "step": 5400
    },
    {
      "epoch": 0.9741409847679773,
      "grad_norm": 329.2083740234375,
      "learning_rate": 5e-06,
      "loss": 163.8091,
      "step": 5500
    },
    {
      "epoch": 0.991852639036486,
      "grad_norm": 1403.033935546875,
      "learning_rate": 4.825502516487497e-06,
      "loss": 85.3021,
      "step": 5600
    },
    {
      "epoch": 1.0,
      "eval_loss": 233.86021423339844,
      "eval_runtime": 45.6534,
      "eval_samples_per_second": 54.98,
      "eval_steps_per_second": 13.756,
      "step": 5646
    },
    {
      "epoch": 1.0095642933049946,
      "grad_norm": 685.2989501953125,
      "learning_rate": 4.651217631279374e-06,
      "loss": 189.6224,
      "step": 5700
    },
    {
      "epoch": 1.0272759475735034,
      "grad_norm": 2071.7216796875,
      "learning_rate": 4.477357683661734e-06,
      "loss": 93.9828,
      "step": 5800
    },
    {
      "epoch": 1.0449876018420121,
      "grad_norm": 3089.990966796875,
      "learning_rate": 4.304134495199675e-06,
      "loss": 95.2696,
      "step": 5900
    },
    {
      "epoch": 1.0626992561105206,
      "grad_norm": 318.3044738769531,
      "learning_rate": 4.131759111665349e-06,
      "loss": 93.2886,
      "step": 6000
    },
    {
      "epoch": 1.0804109103790294,
      "grad_norm": 959.2510375976562,
      "learning_rate": 3.960441545911205e-06,
      "loss": 60.9704,
      "step": 6100
    },
    {
      "epoch": 1.098122564647538,
      "grad_norm": 434.56304931640625,
      "learning_rate": 3.790390522001662e-06,
      "loss": 170.5878,
      "step": 6200
    },
    {
      "epoch": 1.1158342189160468,
      "grad_norm": 437.1268310546875,
      "learning_rate": 3.6218132209150047e-06,
      "loss": 63.596,
      "step": 6300
    },
    {
      "epoch": 1.1335458731845554,
      "grad_norm": 683.8363037109375,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 88.3637,
      "step": 6400
    },
    {
      "epoch": 1.151257527453064,
      "grad_norm": 1063.7440185546875,
      "learning_rate": 3.289899283371657e-06,
      "loss": 90.7109,
      "step": 6500
    },
    {
      "epoch": 1.1689691817215728,
      "grad_norm": 500.3209533691406,
      "learning_rate": 3.12696703292044e-06,
      "loss": 106.912,
      "step": 6600
    },
    {
      "epoch": 1.1866808359900816,
      "grad_norm": 5315.34765625,
      "learning_rate": 2.966316784621e-06,
      "loss": 66.9506,
      "step": 6700
    },
    {
      "epoch": 1.20439249025859,
      "grad_norm": 390.86773681640625,
      "learning_rate": 2.8081442660546126e-06,
      "loss": 72.4987,
      "step": 6800
    },
    {
      "epoch": 1.2221041445270988,
      "grad_norm": 714.1128540039062,
      "learning_rate": 2.6526421860705474e-06,
      "loss": 80.7786,
      "step": 6900
    },
    {
      "epoch": 1.2398157987956075,
      "grad_norm": 625.9713745117188,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 105.9008,
      "step": 7000
    },
    {
      "epoch": 1.257527453064116,
      "grad_norm": 798.7731323242188,
      "learning_rate": 2.3504036788339763e-06,
      "loss": 110.6368,
      "step": 7100
    },
    {
      "epoch": 1.2752391073326248,
      "grad_norm": 503.0509948730469,
      "learning_rate": 2.204035482646267e-06,
      "loss": 65.3358,
      "step": 7200
    },
    {
      "epoch": 1.2929507616011335,
      "grad_norm": 416.53094482421875,
      "learning_rate": 2.061073738537635e-06,
      "loss": 61.5411,
      "step": 7300
    },
    {
      "epoch": 1.3106624158696423,
      "grad_norm": 3666.154541015625,
      "learning_rate": 1.9216926233717087e-06,
      "loss": 84.1701,
      "step": 7400
    },
    {
      "epoch": 1.328374070138151,
      "grad_norm": 330.82928466796875,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 63.6358,
      "step": 7500
    },
    {
      "epoch": 1.3460857244066595,
      "grad_norm": 331.7156066894531,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 116.5511,
      "step": 7600
    },
    {
      "epoch": 1.3637973786751683,
      "grad_norm": 1124.501708984375,
      "learning_rate": 1.5267081477050132e-06,
      "loss": 73.444,
      "step": 7700
    },
    {
      "epoch": 1.381509032943677,
      "grad_norm": 4456.3701171875,
      "learning_rate": 1.4033009983067454e-06,
      "loss": 125.1651,
      "step": 7800
    },
    {
      "epoch": 1.3992206872121855,
      "grad_norm": 254.76058959960938,
      "learning_rate": 1.2842758726130283e-06,
      "loss": 84.9094,
      "step": 7900
    },
    {
      "epoch": 1.4169323414806942,
      "grad_norm": 243.16725158691406,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 70.4103,
      "step": 8000
    },
    {
      "epoch": 1.434643995749203,
      "grad_norm": 444.5528869628906,
      "learning_rate": 1.0599462319663906e-06,
      "loss": 148.3668,
      "step": 8100
    },
    {
      "epoch": 1.4523556500177117,
      "grad_norm": 712.6991577148438,
      "learning_rate": 9.549150281252633e-07,
      "loss": 78.7889,
      "step": 8200
    },
    {
      "epoch": 1.4700673042862205,
      "grad_norm": 1260.743408203125,
      "learning_rate": 8.54812137224792e-07,
      "loss": 133.5537,
      "step": 8300
    },
    {
      "epoch": 1.487778958554729,
      "grad_norm": 375.3415832519531,
      "learning_rate": 7.597595192178702e-07,
      "loss": 96.2294,
      "step": 8400
    },
    {
      "epoch": 1.5054906128232377,
      "grad_norm": 1678.25634765625,
      "learning_rate": 6.698729810778065e-07,
      "loss": 121.3787,
      "step": 8500
    },
    {
      "epoch": 1.5232022670917464,
      "grad_norm": 844.283447265625,
      "learning_rate": 5.852620357053651e-07,
      "loss": 94.1799,
      "step": 8600
    },
    {
      "epoch": 1.540913921360255,
      "grad_norm": 706.9551391601562,
      "learning_rate": 5.06029768504166e-07,
      "loss": 107.5293,
      "step": 8700
    },
    {
      "epoch": 1.5586255756287637,
      "grad_norm": 1072.598388671875,
      "learning_rate": 4.322727117869951e-07,
      "loss": 90.6825,
      "step": 8800
    },
    {
      "epoch": 1.5763372298972724,
      "grad_norm": 534.5012817382812,
      "learning_rate": 3.6408072716606346e-07,
      "loss": 99.7579,
      "step": 8900
    },
    {
      "epoch": 1.594048884165781,
      "grad_norm": 76949.8984375,
      "learning_rate": 3.015368960704584e-07,
      "loss": 186.237,
      "step": 9000
    },
    {
      "epoch": 1.61176053843429,
      "grad_norm": 294.4422302246094,
      "learning_rate": 2.447174185242324e-07,
      "loss": 136.7301,
      "step": 9100
    },
    {
      "epoch": 1.6294721927027984,
      "grad_norm": 347.99017333984375,
      "learning_rate": 1.9369152030840553e-07,
      "loss": 103.0369,
      "step": 9200
    },
    {
      "epoch": 1.6471838469713072,
      "grad_norm": 2896.26806640625,
      "learning_rate": 1.4852136862001766e-07,
      "loss": 73.6874,
      "step": 9300
    },
    {
      "epoch": 1.664895501239816,
      "grad_norm": 398.4006042480469,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 75.4443,
      "step": 9400
    },
    {
      "epoch": 1.6826071555083244,
      "grad_norm": 1028.520751953125,
      "learning_rate": 7.59612349389599e-08,
      "loss": 75.612,
      "step": 9500
    },
    {
      "epoch": 1.7003188097768331,
      "grad_norm": 516.2049560546875,
      "learning_rate": 4.865965629214819e-08,
      "loss": 94.1481,
      "step": 9600
    },
    {
      "epoch": 1.7180304640453419,
      "grad_norm": 1118.83935546875,
      "learning_rate": 2.7390523158633552e-08,
      "loss": 122.414,
      "step": 9700
    },
    {
      "epoch": 1.7357421183138504,
      "grad_norm": 372.98089599609375,
      "learning_rate": 1.2179748700879013e-08,
      "loss": 73.4527,
      "step": 9800
    },
    {
      "epoch": 1.7534537725823593,
      "grad_norm": 1152.221435546875,
      "learning_rate": 3.0458649045211897e-09,
      "loss": 55.3135,
      "step": 9900
    },
    {
      "epoch": 1.7711654268508679,
      "grad_norm": 729.0238037109375,
      "learning_rate": 0.0,
      "loss": 114.0674,
      "step": 10000
    }
  ],
  "logging_steps": 100,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}