{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 2000,
  "global_step": 1159,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": NaN,
      "eval_runtime": 130.0879,
      "eval_samples_per_second": 43.863,
      "eval_steps_per_second": 5.489,
      "step": 0
    },
    {
      "epoch": 0.008628127696289905,
      "grad_norm": 208.8164520263672,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 44.1582,
      "step": 10
    },
    {
      "epoch": 0.01725625539257981,
      "grad_norm": 95.85818481445312,
      "learning_rate": 7.000000000000001e-06,
      "loss": 20.8334,
      "step": 20
    },
    {
      "epoch": 0.025884383088869714,
      "grad_norm": 30.946754455566406,
      "learning_rate": 1.2e-05,
      "loss": 6.8289,
      "step": 30
    },
    {
      "epoch": 0.03451251078515962,
      "grad_norm": 15.001774787902832,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 6.1975,
      "step": 40
    },
    {
      "epoch": 0.04314063848144953,
      "grad_norm": 36.383766174316406,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 9.5655,
      "step": 50
    },
    {
      "epoch": 0.05176876617773943,
      "grad_norm": 21.175804138183594,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 8.0912,
      "step": 60
    },
    {
      "epoch": 0.060396893874029335,
      "grad_norm": 18.93609046936035,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 10.4302,
      "step": 70
    },
    {
      "epoch": 0.06902502157031924,
      "grad_norm": 15.232029914855957,
      "learning_rate": 3.7e-05,
      "loss": 9.1437,
      "step": 80
    },
    {
      "epoch": 0.07765314926660914,
      "grad_norm": 61.93816375732422,
      "learning_rate": 4.2e-05,
      "loss": 7.0303,
      "step": 90
    },
    {
      "epoch": 0.08628127696289906,
      "grad_norm": 13.675076484680176,
      "learning_rate": 4.7e-05,
      "loss": 6.6254,
      "step": 100
    },
    {
      "epoch": 0.09490940465918896,
      "grad_norm": 15.733867645263672,
      "learning_rate": 4.9811142587346554e-05,
      "loss": 11.0107,
      "step": 110
    },
    {
      "epoch": 0.10353753235547886,
      "grad_norm": 23.753643035888672,
      "learning_rate": 4.9338999055712935e-05,
      "loss": 8.7021,
      "step": 120
    },
    {
      "epoch": 0.11216566005176877,
      "grad_norm": 17.372941970825195,
      "learning_rate": 4.8866855524079323e-05,
      "loss": 7.971,
      "step": 130
    },
    {
      "epoch": 0.12079378774805867,
      "grad_norm": 16.303627014160156,
      "learning_rate": 4.8394711992445705e-05,
      "loss": 7.7894,
      "step": 140
    },
    {
      "epoch": 0.12942191544434858,
      "grad_norm": 22.732084274291992,
      "learning_rate": 4.7922568460812086e-05,
      "loss": 8.4125,
      "step": 150
    },
    {
      "epoch": 0.13805004314063848,
      "grad_norm": 7.587573528289795,
      "learning_rate": 4.7450424929178475e-05,
      "loss": 8.7211,
      "step": 160
    },
    {
      "epoch": 0.14667817083692838,
      "grad_norm": 11.529291152954102,
      "learning_rate": 4.6978281397544856e-05,
      "loss": 7.4511,
      "step": 170
    },
    {
      "epoch": 0.15530629853321828,
      "grad_norm": 18.30257225036621,
      "learning_rate": 4.650613786591124e-05,
      "loss": 8.3549,
      "step": 180
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 35.710201263427734,
      "learning_rate": 4.6033994334277626e-05,
      "loss": 7.7639,
      "step": 190
    },
    {
      "epoch": 0.1725625539257981,
      "grad_norm": 17.525699615478516,
      "learning_rate": 4.556185080264401e-05,
      "loss": 8.7268,
      "step": 200
    },
    {
      "epoch": 0.181190681622088,
      "grad_norm": 12.543689727783203,
      "learning_rate": 4.508970727101039e-05,
      "loss": 6.5113,
      "step": 210
    },
    {
      "epoch": 0.1898188093183779,
      "grad_norm": 11.80916976928711,
      "learning_rate": 4.461756373937677e-05,
      "loss": 7.9873,
      "step": 220
    },
    {
      "epoch": 0.1984469370146678,
      "grad_norm": 5.335144996643066,
      "learning_rate": 4.414542020774315e-05,
      "loss": 7.3828,
      "step": 230
    },
    {
      "epoch": 0.2070750647109577,
      "grad_norm": 14.807497024536133,
      "learning_rate": 4.3673276676109534e-05,
      "loss": 7.9503,
      "step": 240
    },
    {
      "epoch": 0.21570319240724764,
      "grad_norm": 7.473222255706787,
      "learning_rate": 4.320113314447592e-05,
      "loss": 9.4133,
      "step": 250
    },
    {
      "epoch": 0.22433132010353754,
      "grad_norm": 16.84607696533203,
      "learning_rate": 4.272898961284231e-05,
      "loss": 11.3476,
      "step": 260
    },
    {
      "epoch": 0.23295944779982744,
      "grad_norm": 14.314810752868652,
      "learning_rate": 4.225684608120869e-05,
      "loss": 8.3349,
      "step": 270
    },
    {
      "epoch": 0.24158757549611734,
      "grad_norm": 7.726313591003418,
      "learning_rate": 4.178470254957507e-05,
      "loss": 9.0962,
      "step": 280
    },
    {
      "epoch": 0.25021570319240727,
      "grad_norm": 5.218513488769531,
      "learning_rate": 4.1312559017941455e-05,
      "loss": 9.2658,
      "step": 290
    },
    {
      "epoch": 0.25884383088869717,
      "grad_norm": 8.278141021728516,
      "learning_rate": 4.0840415486307836e-05,
      "loss": 12.7095,
      "step": 300
    },
    {
      "epoch": 0.26747195858498707,
      "grad_norm": 10.2701416015625,
      "learning_rate": 4.0368271954674225e-05,
      "loss": 10.1141,
      "step": 310
    },
    {
      "epoch": 0.27610008628127697,
      "grad_norm": 6.783595085144043,
      "learning_rate": 3.9896128423040606e-05,
      "loss": 9.1178,
      "step": 320
    },
    {
      "epoch": 0.28472821397756687,
      "grad_norm": 12.468270301818848,
      "learning_rate": 3.942398489140699e-05,
      "loss": 7.8647,
      "step": 330
    },
    {
      "epoch": 0.29335634167385677,
      "grad_norm": 8.456822395324707,
      "learning_rate": 3.895184135977337e-05,
      "loss": 8.4621,
      "step": 340
    },
    {
      "epoch": 0.30198446937014667,
      "grad_norm": 11.295036315917969,
      "learning_rate": 3.847969782813976e-05,
      "loss": 9.196,
      "step": 350
    },
    {
      "epoch": 0.31061259706643657,
      "grad_norm": 14.213314056396484,
      "learning_rate": 3.800755429650614e-05,
      "loss": 8.1778,
      "step": 360
    },
    {
      "epoch": 0.31924072476272647,
      "grad_norm": 14.220091819763184,
      "learning_rate": 3.753541076487253e-05,
      "loss": 7.8913,
      "step": 370
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 13.04310131072998,
      "learning_rate": 3.706326723323891e-05,
      "loss": 7.7094,
      "step": 380
    },
    {
      "epoch": 0.3364969801553063,
      "grad_norm": 10.724278450012207,
      "learning_rate": 3.659112370160529e-05,
      "loss": 9.4355,
      "step": 390
    },
    {
      "epoch": 0.3451251078515962,
      "grad_norm": 23.478923797607422,
      "learning_rate": 3.611898016997167e-05,
      "loss": 7.8075,
      "step": 400
    },
    {
      "epoch": 0.3537532355478861,
      "grad_norm": 13.352030754089355,
      "learning_rate": 3.564683663833805e-05,
      "loss": 7.3814,
      "step": 410
    },
    {
      "epoch": 0.362381363244176,
      "grad_norm": 9.937482833862305,
      "learning_rate": 3.5174693106704435e-05,
      "loss": 8.9733,
      "step": 420
    },
    {
      "epoch": 0.3710094909404659,
      "grad_norm": 11.626459121704102,
      "learning_rate": 3.470254957507082e-05,
      "loss": 10.1639,
      "step": 430
    },
    {
      "epoch": 0.3796376186367558,
      "grad_norm": 10.614298820495605,
      "learning_rate": 3.4230406043437205e-05,
      "loss": 7.7592,
      "step": 440
    },
    {
      "epoch": 0.3882657463330457,
      "grad_norm": 4.33737850189209,
      "learning_rate": 3.375826251180359e-05,
      "loss": 9.8424,
      "step": 450
    },
    {
      "epoch": 0.3968938740293356,
      "grad_norm": 13.16214370727539,
      "learning_rate": 3.3286118980169974e-05,
      "loss": 6.1196,
      "step": 460
    },
    {
      "epoch": 0.4055220017256255,
      "grad_norm": 12.274761199951172,
      "learning_rate": 3.2813975448536356e-05,
      "loss": 7.7816,
      "step": 470
    },
    {
      "epoch": 0.4141501294219154,
      "grad_norm": 9.882450103759766,
      "learning_rate": 3.234183191690274e-05,
      "loss": 8.8377,
      "step": 480
    },
    {
      "epoch": 0.4227782571182053,
      "grad_norm": 7.4602766036987305,
      "learning_rate": 3.1869688385269126e-05,
      "loss": 7.8737,
      "step": 490
    },
    {
      "epoch": 0.4314063848144953,
      "grad_norm": 11.084466934204102,
      "learning_rate": 3.139754485363551e-05,
      "loss": 7.4251,
      "step": 500
    },
    {
      "epoch": 0.4400345125107852,
      "grad_norm": 14.730960845947266,
      "learning_rate": 3.092540132200189e-05,
      "loss": 5.4958,
      "step": 510
    },
    {
      "epoch": 0.4486626402070751,
      "grad_norm": 12.292424201965332,
      "learning_rate": 3.0453257790368274e-05,
      "loss": 7.7441,
      "step": 520
    },
    {
      "epoch": 0.457290767903365,
      "grad_norm": 14.31530475616455,
      "learning_rate": 2.9981114258734655e-05,
      "loss": 9.7954,
      "step": 530
    },
    {
      "epoch": 0.4659188955996549,
      "grad_norm": 56.466800689697266,
      "learning_rate": 2.9508970727101037e-05,
      "loss": 7.182,
      "step": 540
    },
    {
      "epoch": 0.4745470232959448,
      "grad_norm": 10.024373054504395,
      "learning_rate": 2.9036827195467425e-05,
      "loss": 9.0355,
      "step": 550
    },
    {
      "epoch": 0.4831751509922347,
      "grad_norm": 6.825662612915039,
      "learning_rate": 2.8564683663833807e-05,
      "loss": 9.4844,
      "step": 560
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 7.98593807220459,
      "learning_rate": 2.809254013220019e-05,
      "loss": 7.0413,
      "step": 570
    },
    {
      "epoch": 0.5004314063848145,
      "grad_norm": 9.947932243347168,
      "learning_rate": 2.7620396600566573e-05,
      "loss": 7.2181,
      "step": 580
    },
    {
      "epoch": 0.5090595340811044,
      "grad_norm": 14.444029808044434,
      "learning_rate": 2.7148253068932954e-05,
      "loss": 8.3113,
      "step": 590
    },
    {
      "epoch": 0.5176876617773943,
      "grad_norm": 5.243804931640625,
      "learning_rate": 2.6676109537299343e-05,
      "loss": 9.8681,
      "step": 600
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 15.272309303283691,
      "learning_rate": 2.6203966005665724e-05,
      "loss": 6.4987,
      "step": 610
    },
    {
      "epoch": 0.5349439171699741,
      "grad_norm": 14.450007438659668,
      "learning_rate": 2.573182247403211e-05,
      "loss": 8.7722,
      "step": 620
    },
    {
      "epoch": 0.543572044866264,
      "grad_norm": 4.825082778930664,
      "learning_rate": 2.525967894239849e-05,
      "loss": 10.2199,
      "step": 630
    },
    {
      "epoch": 0.5522001725625539,
      "grad_norm": 4.846455097198486,
      "learning_rate": 2.4787535410764872e-05,
      "loss": 6.8151,
      "step": 640
    },
    {
      "epoch": 0.5608283002588438,
      "grad_norm": 18.088956832885742,
      "learning_rate": 2.4315391879131257e-05,
      "loss": 6.9832,
      "step": 650
    },
    {
      "epoch": 0.5694564279551337,
      "grad_norm": 3.5512518882751465,
      "learning_rate": 2.3843248347497642e-05,
      "loss": 9.6627,
      "step": 660
    },
    {
      "epoch": 0.5780845556514237,
      "grad_norm": 8.27271842956543,
      "learning_rate": 2.3371104815864024e-05,
      "loss": 8.0493,
      "step": 670
    },
    {
      "epoch": 0.5867126833477135,
      "grad_norm": 7.861291408538818,
      "learning_rate": 2.289896128423041e-05,
      "loss": 6.2845,
      "step": 680
    },
    {
      "epoch": 0.5953408110440035,
      "grad_norm": 11.14802074432373,
      "learning_rate": 2.242681775259679e-05,
      "loss": 8.7777,
      "step": 690
    },
    {
      "epoch": 0.6039689387402933,
      "grad_norm": 8.262513160705566,
      "learning_rate": 2.195467422096317e-05,
      "loss": 8.8687,
      "step": 700
    },
    {
      "epoch": 0.6125970664365833,
      "grad_norm": 18.18682861328125,
      "learning_rate": 2.1482530689329556e-05,
      "loss": 9.9046,
      "step": 710
    },
    {
      "epoch": 0.6212251941328731,
      "grad_norm": 6.271354675292969,
      "learning_rate": 2.101038715769594e-05,
      "loss": 7.5048,
      "step": 720
    },
    {
      "epoch": 0.6298533218291631,
      "grad_norm": 11.321942329406738,
      "learning_rate": 2.0538243626062323e-05,
      "loss": 9.4543,
      "step": 730
    },
    {
      "epoch": 0.6384814495254529,
      "grad_norm": 6.52807092666626,
      "learning_rate": 2.0066100094428708e-05,
      "loss": 7.942,
      "step": 740
    },
    {
      "epoch": 0.6471095772217429,
      "grad_norm": 9.259538650512695,
      "learning_rate": 1.959395656279509e-05,
      "loss": 7.9326,
      "step": 750
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 11.931748390197754,
      "learning_rate": 1.9121813031161474e-05,
      "loss": 10.2928,
      "step": 760
    },
    {
      "epoch": 0.6643658326143227,
      "grad_norm": 26.903627395629883,
      "learning_rate": 1.864966949952786e-05,
      "loss": 7.4203,
      "step": 770
    },
    {
      "epoch": 0.6729939603106126,
      "grad_norm": 4.38643741607666,
      "learning_rate": 1.817752596789424e-05,
      "loss": 8.5358,
      "step": 780
    },
    {
      "epoch": 0.6816220880069025,
      "grad_norm": 13.639317512512207,
      "learning_rate": 1.7705382436260622e-05,
      "loss": 9.0024,
      "step": 790
    },
    {
      "epoch": 0.6902502157031924,
      "grad_norm": 7.604945659637451,
      "learning_rate": 1.7233238904627007e-05,
      "loss": 8.7945,
      "step": 800
    },
    {
      "epoch": 0.6988783433994823,
      "grad_norm": 4.23636531829834,
      "learning_rate": 1.6761095372993392e-05,
      "loss": 9.6466,
      "step": 810
    },
    {
      "epoch": 0.7075064710957722,
      "grad_norm": 9.454889297485352,
      "learning_rate": 1.6288951841359773e-05,
      "loss": 7.9837,
      "step": 820
    },
    {
      "epoch": 0.7161345987920621,
      "grad_norm": 9.216086387634277,
      "learning_rate": 1.5816808309726158e-05,
      "loss": 7.5399,
      "step": 830
    },
    {
      "epoch": 0.724762726488352,
      "grad_norm": 9.077666282653809,
      "learning_rate": 1.534466477809254e-05,
      "loss": 8.0818,
      "step": 840
    },
    {
      "epoch": 0.7333908541846419,
      "grad_norm": 11.995235443115234,
      "learning_rate": 1.4872521246458923e-05,
      "loss": 7.4127,
      "step": 850
    },
    {
      "epoch": 0.7420189818809318,
      "grad_norm": 5.774163722991943,
      "learning_rate": 1.4400377714825308e-05,
      "loss": 7.7635,
      "step": 860
    },
    {
      "epoch": 0.7506471095772217,
      "grad_norm": 3.043311357498169,
      "learning_rate": 1.3928234183191691e-05,
      "loss": 7.4845,
      "step": 870
    },
    {
      "epoch": 0.7592752372735116,
      "grad_norm": 9.676830291748047,
      "learning_rate": 1.3456090651558073e-05,
      "loss": 8.4687,
      "step": 880
    },
    {
      "epoch": 0.7679033649698016,
      "grad_norm": 20.002187728881836,
      "learning_rate": 1.2983947119924458e-05,
      "loss": 6.5787,
      "step": 890
    },
    {
      "epoch": 0.7765314926660914,
      "grad_norm": 7.795656681060791,
      "learning_rate": 1.251180358829084e-05,
      "loss": 5.2528,
      "step": 900
    },
    {
      "epoch": 0.7851596203623814,
      "grad_norm": 10.025925636291504,
      "learning_rate": 1.2039660056657224e-05,
      "loss": 6.2703,
      "step": 910
    },
    {
      "epoch": 0.7937877480586712,
      "grad_norm": 5.656552314758301,
      "learning_rate": 1.1567516525023609e-05,
      "loss": 6.6007,
      "step": 920
    },
    {
      "epoch": 0.8024158757549612,
      "grad_norm": 11.046673774719238,
      "learning_rate": 1.109537299338999e-05,
      "loss": 6.9978,
      "step": 930
    },
    {
      "epoch": 0.811044003451251,
      "grad_norm": 20.649337768554688,
      "learning_rate": 1.0623229461756375e-05,
      "loss": 8.2104,
      "step": 940
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 12.507070541381836,
      "learning_rate": 1.0151085930122758e-05,
      "loss": 7.3538,
      "step": 950
    },
    {
      "epoch": 0.8283002588438308,
      "grad_norm": 8.762845039367676,
      "learning_rate": 9.678942398489142e-06,
      "loss": 6.6649,
      "step": 960
    },
    {
      "epoch": 0.8369283865401208,
      "grad_norm": 4.919765472412109,
      "learning_rate": 9.206798866855525e-06,
      "loss": 6.1039,
      "step": 970
    },
    {
      "epoch": 0.8455565142364107,
      "grad_norm": 13.5018310546875,
      "learning_rate": 8.734655335221908e-06,
      "loss": 7.5592,
      "step": 980
    },
    {
      "epoch": 0.8541846419327006,
      "grad_norm": 7.929318428039551,
      "learning_rate": 8.262511803588291e-06,
      "loss": 7.3745,
      "step": 990
    },
    {
      "epoch": 0.8628127696289906,
      "grad_norm": 2.267650604248047,
      "learning_rate": 7.790368271954675e-06,
      "loss": 6.4057,
      "step": 1000
    },
    {
      "epoch": 0.8714408973252804,
      "grad_norm": 7.356956958770752,
      "learning_rate": 7.3182247403210586e-06,
      "loss": 6.1371,
      "step": 1010
    },
    {
      "epoch": 0.8800690250215704,
      "grad_norm": 9.035082817077637,
      "learning_rate": 6.846081208687441e-06,
      "loss": 6.4763,
      "step": 1020
    },
    {
      "epoch": 0.8886971527178602,
      "grad_norm": 4.9309844970703125,
      "learning_rate": 6.373937677053825e-06,
      "loss": 7.2184,
      "step": 1030
    },
    {
      "epoch": 0.8973252804141502,
      "grad_norm": 13.067819595336914,
      "learning_rate": 5.901794145420208e-06,
      "loss": 9.0975,
      "step": 1040
    },
    {
      "epoch": 0.90595340811044,
      "grad_norm": 1.801363468170166,
      "learning_rate": 5.429650613786591e-06,
      "loss": 8.5242,
      "step": 1050
    },
    {
      "epoch": 0.91458153580673,
      "grad_norm": 21.638532638549805,
      "learning_rate": 4.957507082152975e-06,
      "loss": 6.6817,
      "step": 1060
    },
    {
      "epoch": 0.9232096635030198,
      "grad_norm": 11.125391006469727,
      "learning_rate": 4.485363550519358e-06,
      "loss": 7.3333,
      "step": 1070
    },
    {
      "epoch": 0.9318377911993098,
      "grad_norm": 20.023378372192383,
      "learning_rate": 4.013220018885742e-06,
      "loss": 7.5053,
      "step": 1080
    },
    {
      "epoch": 0.9404659188955996,
      "grad_norm": 6.69666051864624,
      "learning_rate": 3.541076487252125e-06,
      "loss": 7.1582,
      "step": 1090
    },
    {
      "epoch": 0.9490940465918896,
      "grad_norm": 8.274604797363281,
      "learning_rate": 3.0689329556185083e-06,
      "loss": 8.7796,
      "step": 1100
    },
    {
      "epoch": 0.9577221742881795,
      "grad_norm": 5.5356221199035645,
      "learning_rate": 2.5967894239848915e-06,
      "loss": 9.3139,
      "step": 1110
    },
    {
      "epoch": 0.9663503019844694,
      "grad_norm": 5.540348052978516,
      "learning_rate": 2.124645892351275e-06,
      "loss": 8.2046,
      "step": 1120
    },
    {
      "epoch": 0.9749784296807593,
      "grad_norm": 9.052054405212402,
      "learning_rate": 1.6525023607176583e-06,
      "loss": 7.8996,
      "step": 1130
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 2.191704034805298,
      "learning_rate": 1.1803588290840418e-06,
      "loss": 10.2246,
      "step": 1140
    },
    {
      "epoch": 0.9922346850733391,
      "grad_norm": 1.935456395149231,
      "learning_rate": 7.08215297450425e-07,
      "loss": 8.5122,
      "step": 1150
    }
  ],
  "logging_steps": 10,
  "max_steps": 1159,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4000,
  "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
}