{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9999768844918056,
  "eval_steps": 500,
  "global_step": 10815,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004623101638889531,
      "grad_norm": 10.25,
      "learning_rate": 2e-05,
      "loss": 5.7331,
      "step": 50
    },
    {
      "epoch": 0.009246203277779062,
      "grad_norm": 8.375,
      "learning_rate": 4e-05,
      "loss": 5.0317,
      "step": 100
    },
    {
      "epoch": 0.013869304916668592,
      "grad_norm": 7.65625,
      "learning_rate": 6e-05,
      "loss": 4.6245,
      "step": 150
    },
    {
      "epoch": 0.018492406555558123,
      "grad_norm": 6.34375,
      "learning_rate": 8e-05,
      "loss": 4.4327,
      "step": 200
    },
    {
      "epoch": 0.023115508194447656,
      "grad_norm": 6.75,
      "learning_rate": 0.0001,
      "loss": 4.2418,
      "step": 250
    },
    {
      "epoch": 0.027738609833337185,
      "grad_norm": 5.75,
      "learning_rate": 0.00012,
      "loss": 4.1714,
      "step": 300
    },
    {
      "epoch": 0.03236171147222672,
      "grad_norm": 5.5,
      "learning_rate": 0.00014,
      "loss": 4.0904,
      "step": 350
    },
    {
      "epoch": 0.036984813111116246,
      "grad_norm": 6.90625,
      "learning_rate": 0.00016,
      "loss": 4.1346,
      "step": 400
    },
    {
      "epoch": 0.041607914750005776,
      "grad_norm": 5.625,
      "learning_rate": 0.00018,
      "loss": 4.1936,
      "step": 450
    },
    {
      "epoch": 0.04623101638889531,
      "grad_norm": 5.15625,
      "learning_rate": 0.0002,
      "loss": 4.167,
      "step": 500
    },
    {
      "epoch": 0.05085411802778484,
      "grad_norm": 5.0625,
      "learning_rate": 0.0001999993252640082,
      "loss": 4.1719,
      "step": 550
    },
    {
      "epoch": 0.05547721966667437,
      "grad_norm": 5.59375,
      "learning_rate": 0.0001999973010651382,
      "loss": 4.0257,
      "step": 600
    },
    {
      "epoch": 0.060100321305563906,
      "grad_norm": 4.84375,
      "learning_rate": 0.00019999392743070592,
      "loss": 4.0536,
      "step": 650
    },
    {
      "epoch": 0.06472342294445343,
      "grad_norm": 4.875,
      "learning_rate": 0.00019998920440623765,
      "loss": 3.9901,
      "step": 700
    },
    {
      "epoch": 0.06934652458334296,
      "grad_norm": 4.78125,
      "learning_rate": 0.0001999831320554693,
      "loss": 3.9791,
      "step": 750
    },
    {
      "epoch": 0.07396962622223249,
      "grad_norm": 4.71875,
      "learning_rate": 0.00019997571046034555,
      "loss": 3.9548,
      "step": 800
    },
    {
      "epoch": 0.07859272786112202,
      "grad_norm": 4.40625,
      "learning_rate": 0.0001999669397210187,
      "loss": 3.8842,
      "step": 850
    },
    {
      "epoch": 0.08321582950001155,
      "grad_norm": 4.84375,
      "learning_rate": 0.00019995681995584746,
      "loss": 3.8699,
      "step": 900
    },
    {
      "epoch": 0.0878389311389011,
      "grad_norm": 5.09375,
      "learning_rate": 0.0001999453513013952,
      "loss": 3.8166,
      "step": 950
    },
    {
      "epoch": 0.09246203277779062,
      "grad_norm": 4.4375,
      "learning_rate": 0.00019993253391242826,
      "loss": 3.785,
      "step": 1000
    },
    {
      "epoch": 0.09708513441668015,
      "grad_norm": 4.96875,
      "learning_rate": 0.00019991836796191364,
      "loss": 3.7597,
      "step": 1050
    },
    {
      "epoch": 0.10170823605556968,
      "grad_norm": 4.75,
      "learning_rate": 0.00019990285364101688,
      "loss": 3.7262,
      "step": 1100
    },
    {
      "epoch": 0.10633133769445921,
      "grad_norm": 4.25,
      "learning_rate": 0.00019988599115909942,
      "loss": 3.7565,
      "step": 1150
    },
    {
      "epoch": 0.11095443933334874,
      "grad_norm": 4.25,
      "learning_rate": 0.00019986778074371575,
      "loss": 3.6486,
      "step": 1200
    },
    {
      "epoch": 0.11557754097223827,
      "grad_norm": 5.09375,
      "learning_rate": 0.00019984822264061024,
      "loss": 3.6558,
      "step": 1250
    },
    {
      "epoch": 0.12020064261112781,
      "grad_norm": 4.1875,
      "learning_rate": 0.0001998273171137141,
      "loss": 3.602,
      "step": 1300
    },
    {
      "epoch": 0.12482374425001734,
      "grad_norm": 4.3125,
      "learning_rate": 0.00019980506444514155,
      "loss": 3.6141,
      "step": 1350
    },
    {
      "epoch": 0.12944684588890687,
      "grad_norm": 3.953125,
      "learning_rate": 0.00019978146493518608,
      "loss": 3.5908,
      "step": 1400
    },
    {
      "epoch": 0.13406994752779638,
      "grad_norm": 4.375,
      "learning_rate": 0.00019975651890231645,
      "loss": 3.5565,
      "step": 1450
    },
    {
      "epoch": 0.13869304916668593,
      "grad_norm": 4.09375,
      "learning_rate": 0.00019973022668317244,
      "loss": 3.5753,
      "step": 1500
    },
    {
      "epoch": 0.14331615080557547,
      "grad_norm": 4.0625,
      "learning_rate": 0.00019970258863256015,
      "loss": 3.5305,
      "step": 1550
    },
    {
      "epoch": 0.14793925244446499,
      "grad_norm": 4.09375,
      "learning_rate": 0.00019967360512344732,
      "loss": 3.5222,
      "step": 1600
    },
    {
      "epoch": 0.15256235408335453,
      "grad_norm": 4.0,
      "learning_rate": 0.00019964327654695835,
      "loss": 3.5663,
      "step": 1650
    },
    {
      "epoch": 0.15718545572224404,
      "grad_norm": 4.25,
      "learning_rate": 0.00019961160331236877,
      "loss": 3.5668,
      "step": 1700
    },
    {
      "epoch": 0.1618085573611336,
      "grad_norm": 4.0625,
      "learning_rate": 0.00019957858584710009,
      "loss": 3.445,
      "step": 1750
    },
    {
      "epoch": 0.1664316590000231,
      "grad_norm": 4.15625,
      "learning_rate": 0.00019954422459671377,
      "loss": 3.4294,
      "step": 1800
    },
    {
      "epoch": 0.17105476063891265,
      "grad_norm": 4.0,
      "learning_rate": 0.00019950852002490518,
      "loss": 3.4634,
      "step": 1850
    },
    {
      "epoch": 0.1756778622778022,
      "grad_norm": 3.859375,
      "learning_rate": 0.00019947147261349755,
      "loss": 3.4504,
      "step": 1900
    },
    {
      "epoch": 0.1803009639166917,
      "grad_norm": 4.15625,
      "learning_rate": 0.00019943308286243534,
      "loss": 3.463,
      "step": 1950
    },
    {
      "epoch": 0.18492406555558125,
      "grad_norm": 3.5,
      "learning_rate": 0.00019939335128977748,
      "loss": 3.4113,
      "step": 2000
    },
    {
      "epoch": 0.18954716719447076,
      "grad_norm": 4.28125,
      "learning_rate": 0.00019935227843169035,
      "loss": 3.4378,
      "step": 2050
    },
    {
      "epoch": 0.1941702688333603,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019930986484244077,
      "loss": 3.3705,
      "step": 2100
    },
    {
      "epoch": 0.19879337047224982,
      "grad_norm": 4.1875,
      "learning_rate": 0.00019926611109438816,
      "loss": 3.4306,
      "step": 2150
    },
    {
      "epoch": 0.20341647211113936,
      "grad_norm": 4.0625,
      "learning_rate": 0.0001992210177779771,
      "loss": 3.366,
      "step": 2200
    },
    {
      "epoch": 0.2080395737500289,
      "grad_norm": 3.703125,
      "learning_rate": 0.00019917458550172928,
      "loss": 3.3909,
      "step": 2250
    },
    {
      "epoch": 0.21266267538891842,
      "grad_norm": 4.09375,
      "learning_rate": 0.0001991268148922353,
      "loss": 3.3814,
      "step": 2300
    },
    {
      "epoch": 0.21728577702780796,
      "grad_norm": 3.796875,
      "learning_rate": 0.00019907770659414607,
      "loss": 3.3391,
      "step": 2350
    },
    {
      "epoch": 0.22190887866669748,
      "grad_norm": 4.09375,
      "learning_rate": 0.0001990272612701644,
      "loss": 3.3336,
      "step": 2400
    },
    {
      "epoch": 0.22653198030558702,
      "grad_norm": 5.0625,
      "learning_rate": 0.0001989754796010357,
      "loss": 3.3146,
      "step": 2450
    },
    {
      "epoch": 0.23115508194447654,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019892236228553916,
      "loss": 3.3387,
      "step": 2500
    },
    {
      "epoch": 0.23577818358336608,
      "grad_norm": 4.09375,
      "learning_rate": 0.0001988679100404781,
      "loss": 3.3373,
      "step": 2550
    },
    {
      "epoch": 0.24040128522225562,
      "grad_norm": 4.125,
      "learning_rate": 0.0001988121236006702,
      "loss": 3.3327,
      "step": 2600
    },
    {
      "epoch": 0.24502438686114514,
      "grad_norm": 4.15625,
      "learning_rate": 0.00019875500371893795,
      "loss": 3.2672,
      "step": 2650
    },
    {
      "epoch": 0.24964748850003468,
      "grad_norm": 4.0,
      "learning_rate": 0.00019869655116609808,
      "loss": 3.2931,
      "step": 2700
    },
    {
      "epoch": 0.2542705901389242,
      "grad_norm": 4.1875,
      "learning_rate": 0.0001986367667309515,
      "loss": 3.2913,
      "step": 2750
    },
    {
      "epoch": 0.25889369177781374,
      "grad_norm": 4.0625,
      "learning_rate": 0.00019857565122027228,
      "loss": 3.2848,
      "step": 2800
    },
    {
      "epoch": 0.26351679341670325,
      "grad_norm": 4.3125,
      "learning_rate": 0.0001985132054587972,
      "loss": 3.2729,
      "step": 2850
    },
    {
      "epoch": 0.26813989505559277,
      "grad_norm": 4.25,
      "learning_rate": 0.00019844943028921432,
      "loss": 3.3057,
      "step": 2900
    },
    {
      "epoch": 0.27276299669448234,
      "grad_norm": 4.34375,
      "learning_rate": 0.00019838432657215166,
      "loss": 3.2535,
      "step": 2950
    },
    {
      "epoch": 0.27738609833337186,
      "grad_norm": 4.59375,
      "learning_rate": 0.00019831789518616567,
      "loss": 3.2543,
      "step": 3000
    },
    {
      "epoch": 0.28200919997226137,
      "grad_norm": 4.75,
      "learning_rate": 0.00019825013702772925,
      "loss": 3.2435,
      "step": 3050
    },
    {
      "epoch": 0.28663230161115094,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019818105301121978,
      "loss": 3.2287,
      "step": 3100
    },
    {
      "epoch": 0.29125540325004046,
      "grad_norm": 4.5,
      "learning_rate": 0.00019811064406890673,
      "loss": 3.2054,
      "step": 3150
    },
    {
      "epoch": 0.29587850488892997,
      "grad_norm": 4.5,
      "learning_rate": 0.00019803891115093903,
      "loss": 3.2044,
      "step": 3200
    },
    {
      "epoch": 0.3005016065278195,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019796585522533232,
      "loss": 3.2105,
      "step": 3250
    },
    {
      "epoch": 0.30512470816670906,
      "grad_norm": 4.5625,
      "learning_rate": 0.00019789147727795588,
      "loss": 3.2122,
      "step": 3300
    },
    {
      "epoch": 0.3097478098055986,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019781577831251917,
      "loss": 3.2451,
      "step": 3350
    },
    {
      "epoch": 0.3143709114444881,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019773875935055862,
      "loss": 3.232,
      "step": 3400
    },
    {
      "epoch": 0.31899401308337766,
      "grad_norm": 4.53125,
      "learning_rate": 0.00019766042143142353,
      "loss": 3.2113,
      "step": 3450
    },
    {
      "epoch": 0.3236171147222672,
      "grad_norm": 4.125,
      "learning_rate": 0.00019758076561226213,
      "loss": 3.2058,
      "step": 3500
    },
    {
      "epoch": 0.3282402163611567,
      "grad_norm": 4.34375,
      "learning_rate": 0.0001974997929680074,
      "loss": 3.2143,
      "step": 3550
    },
    {
      "epoch": 0.3328633180000462,
      "grad_norm": 4.59375,
      "learning_rate": 0.00019741750459136253,
      "loss": 3.2039,
      "step": 3600
    },
    {
      "epoch": 0.3374864196389358,
      "grad_norm": 4.15625,
      "learning_rate": 0.00019733390159278605,
      "loss": 3.224,
      "step": 3650
    },
    {
      "epoch": 0.3421095212778253,
      "grad_norm": 4.5625,
      "learning_rate": 0.00019724898510047701,
      "loss": 3.1668,
      "step": 3700
    },
    {
      "epoch": 0.3467326229167148,
      "grad_norm": 4.59375,
      "learning_rate": 0.00019716275626035972,
      "loss": 3.1734,
      "step": 3750
    },
    {
      "epoch": 0.3513557245556044,
      "grad_norm": 4.40625,
      "learning_rate": 0.0001970752162360682,
      "loss": 3.1776,
      "step": 3800
    },
    {
      "epoch": 0.3559788261944939,
      "grad_norm": 4.125,
      "learning_rate": 0.00019698636620893054,
      "loss": 3.1227,
      "step": 3850
    },
    {
      "epoch": 0.3606019278333834,
      "grad_norm": 4.53125,
      "learning_rate": 0.00019689620737795295,
      "loss": 3.1555,
      "step": 3900
    },
    {
      "epoch": 0.3652250294722729,
      "grad_norm": 4.5625,
      "learning_rate": 0.00019680474095980365,
      "loss": 3.1237,
      "step": 3950
    },
    {
      "epoch": 0.3698481311111625,
      "grad_norm": 4.40625,
      "learning_rate": 0.0001967119681887963,
      "loss": 3.14,
      "step": 4000
    },
    {
      "epoch": 0.374471232750052,
      "grad_norm": 4.03125,
      "learning_rate": 0.00019661789031687343,
      "loss": 3.1183,
      "step": 4050
    },
    {
      "epoch": 0.3790943343889415,
      "grad_norm": 4.5625,
      "learning_rate": 0.0001965225086135896,
      "loss": 3.1166,
      "step": 4100
    },
    {
      "epoch": 0.3837174360278311,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019642582436609415,
      "loss": 3.1272,
      "step": 4150
    },
    {
      "epoch": 0.3883405376667206,
      "grad_norm": 4.78125,
      "learning_rate": 0.00019632783887911393,
      "loss": 3.1201,
      "step": 4200
    },
    {
      "epoch": 0.3929636393056101,
      "grad_norm": 4.03125,
      "learning_rate": 0.0001962285534749356,
      "loss": 3.1078,
      "step": 4250
    },
    {
      "epoch": 0.39758674094449964,
      "grad_norm": 4.71875,
      "learning_rate": 0.00019612796949338793,
      "loss": 3.124,
      "step": 4300
    },
    {
      "epoch": 0.4022098425833892,
      "grad_norm": 4.4375,
      "learning_rate": 0.00019602608829182353,
      "loss": 3.0682,
      "step": 4350
    },
    {
      "epoch": 0.4068329442222787,
      "grad_norm": 4.4375,
      "learning_rate": 0.00019592291124510066,
      "loss": 3.0967,
      "step": 4400
    },
    {
      "epoch": 0.41145604586116824,
      "grad_norm": 4.15625,
      "learning_rate": 0.0001958184397455647,
      "loss": 3.0829,
      "step": 4450
    },
    {
      "epoch": 0.4160791475000578,
      "grad_norm": 4.625,
      "learning_rate": 0.00019571267520302922,
      "loss": 3.0902,
      "step": 4500
    },
    {
      "epoch": 0.4207022491389473,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019560561904475714,
      "loss": 3.0657,
      "step": 4550
    },
    {
      "epoch": 0.42532535077783684,
      "grad_norm": 4.28125,
      "learning_rate": 0.00019549727271544128,
      "loss": 3.0467,
      "step": 4600
    },
    {
      "epoch": 0.42994845241672636,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019538763767718505,
      "loss": 3.0887,
      "step": 4650
    },
    {
      "epoch": 0.4345715540556159,
      "grad_norm": 4.375,
      "learning_rate": 0.0001952767154094825,
      "loss": 3.0263,
      "step": 4700
    },
    {
      "epoch": 0.43919465569450544,
      "grad_norm": 4.09375,
      "learning_rate": 0.00019516450740919865,
      "loss": 3.0493,
      "step": 4750
    },
    {
      "epoch": 0.44381775733339496,
      "grad_norm": 4.3125,
      "learning_rate": 0.00019505101519054895,
      "loss": 3.0268,
      "step": 4800
    },
    {
      "epoch": 0.44844085897228453,
      "grad_norm": 4.28125,
      "learning_rate": 0.00019493624028507912,
      "loss": 3.0399,
      "step": 4850
    },
    {
      "epoch": 0.45306396061117404,
      "grad_norm": 4.4375,
      "learning_rate": 0.00019482018424164436,
      "loss": 3.0722,
      "step": 4900
    },
    {
      "epoch": 0.45768706225006356,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019470284862638845,
      "loss": 3.0155,
      "step": 4950
    },
    {
      "epoch": 0.4623101638889531,
      "grad_norm": 4.46875,
      "learning_rate": 0.00019458423502272267,
      "loss": 3.0341,
      "step": 5000
    },
    {
      "epoch": 0.46693326552784264,
      "grad_norm": 4.0625,
      "learning_rate": 0.00019446434503130432,
      "loss": 3.0222,
      "step": 5050
    },
    {
      "epoch": 0.47155636716673216,
      "grad_norm": 4.53125,
      "learning_rate": 0.0001943431802700153,
      "loss": 3.0176,
      "step": 5100
    },
    {
      "epoch": 0.4761794688056217,
      "grad_norm": 4.0,
      "learning_rate": 0.00019422074237394007,
      "loss": 3.0232,
      "step": 5150
    },
    {
      "epoch": 0.48080257044451125,
      "grad_norm": 4.4375,
      "learning_rate": 0.0001940970329953438,
      "loss": 3.0065,
      "step": 5200
    },
    {
      "epoch": 0.48542567208340076,
      "grad_norm": 4.3125,
      "learning_rate": 0.00019397205380364984,
      "loss": 3.0149,
      "step": 5250
    },
    {
      "epoch": 0.4900487737222903,
      "grad_norm": 4.25,
      "learning_rate": 0.00019384580648541737,
      "loss": 3.0091,
      "step": 5300
    },
    {
      "epoch": 0.4946718753611798,
      "grad_norm": 4.21875,
      "learning_rate": 0.0001937182927443186,
      "loss": 3.0174,
      "step": 5350
    },
    {
      "epoch": 0.49929497700006936,
      "grad_norm": 3.90625,
      "learning_rate": 0.00019358951430111573,
      "loss": 3.0074,
      "step": 5400
    },
    {
      "epoch": 0.5039180786389589,
      "grad_norm": 4.46875,
      "learning_rate": 0.00019345947289363776,
      "loss": 2.9757,
      "step": 5450
    },
    {
      "epoch": 0.5085411802778484,
      "grad_norm": 4.09375,
      "learning_rate": 0.0001933281702767571,
      "loss": 2.9508,
      "step": 5500
    },
    {
      "epoch": 0.5131642819167379,
      "grad_norm": 4.1875,
      "learning_rate": 0.0001931956082223657,
      "loss": 2.95,
      "step": 5550
    },
    {
      "epoch": 0.5177873835556275,
      "grad_norm": 4.125,
      "learning_rate": 0.00019306178851935144,
      "loss": 2.9755,
      "step": 5600
    },
    {
      "epoch": 0.522410485194517,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019292671297357363,
      "loss": 2.9631,
      "step": 5650
    },
    {
      "epoch": 0.5270335868334065,
      "grad_norm": 4.3125,
      "learning_rate": 0.00019279038340783898,
      "loss": 2.9755,
      "step": 5700
    },
    {
      "epoch": 0.5316566884722961,
      "grad_norm": 4.0,
      "learning_rate": 0.00019265280166187674,
      "loss": 2.9691,
      "step": 5750
    },
    {
      "epoch": 0.5362797901111855,
      "grad_norm": 4.03125,
      "learning_rate": 0.00019251396959231408,
      "loss": 2.9681,
      "step": 5800
    },
    {
      "epoch": 0.5409028917500751,
      "grad_norm": 4.03125,
      "learning_rate": 0.00019237388907265078,
      "loss": 2.9503,
      "step": 5850
    },
    {
      "epoch": 0.5455259933889647,
      "grad_norm": 4.59375,
      "learning_rate": 0.00019223256199323436,
      "loss": 2.9646,
      "step": 5900
    },
    {
      "epoch": 0.5501490950278541,
      "grad_norm": 4.0,
      "learning_rate": 0.00019208999026123404,
      "loss": 2.9603,
      "step": 5950
    },
    {
      "epoch": 0.5547721966667437,
      "grad_norm": 3.9375,
      "learning_rate": 0.00019194617580061543,
      "loss": 2.9419,
      "step": 6000
    },
    {
      "epoch": 0.5593952983056333,
      "grad_norm": 4.1875,
      "learning_rate": 0.00019180112055211445,
      "loss": 2.9279,
      "step": 6050
    },
    {
      "epoch": 0.5640183999445227,
      "grad_norm": 4.03125,
      "learning_rate": 0.00019165482647321095,
      "loss": 2.9468,
      "step": 6100
    },
    {
      "epoch": 0.5686415015834123,
      "grad_norm": 4.5,
      "learning_rate": 0.00019150729553810256,
      "loss": 2.9412,
      "step": 6150
    },
    {
      "epoch": 0.5732646032223019,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019135852973767794,
      "loss": 2.9177,
      "step": 6200
    },
    {
      "epoch": 0.5778877048611913,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019120853107948985,
      "loss": 2.9285,
      "step": 6250
    },
    {
      "epoch": 0.5825108065000809,
      "grad_norm": 4.625,
      "learning_rate": 0.00019105730158772824,
      "loss": 2.9534,
      "step": 6300
    },
    {
      "epoch": 0.5871339081389705,
      "grad_norm": 4.1875,
      "learning_rate": 0.00019090484330319262,
      "loss": 2.9199,
      "step": 6350
    },
    {
      "epoch": 0.5917570097778599,
      "grad_norm": 4.09375,
      "learning_rate": 0.00019075115828326493,
      "loss": 2.8957,
      "step": 6400
    },
    {
      "epoch": 0.5963801114167495,
      "grad_norm": 4.25,
      "learning_rate": 0.0001905962486018814,
      "loss": 2.9327,
      "step": 6450
    },
    {
      "epoch": 0.601003213055639,
      "grad_norm": 4.125,
      "learning_rate": 0.0001904401163495048,
      "loss": 2.873,
      "step": 6500
    },
    {
      "epoch": 0.6056263146945285,
      "grad_norm": 4.3125,
      "learning_rate": 0.00019028276363309608,
      "loss": 2.8886,
      "step": 6550
    },
    {
      "epoch": 0.6102494163334181,
      "grad_norm": 4.28125,
      "learning_rate": 0.00019012419257608614,
      "loss": 2.9023,
      "step": 6600
    },
    {
      "epoch": 0.6148725179723076,
      "grad_norm": 4.40625,
      "learning_rate": 0.0001899644053183469,
      "loss": 2.9093,
      "step": 6650
    },
    {
      "epoch": 0.6194956196111971,
      "grad_norm": 4.46875,
      "learning_rate": 0.00018980340401616273,
      "loss": 2.9233,
      "step": 6700
    },
    {
      "epoch": 0.6241187212500867,
      "grad_norm": 4.15625,
      "learning_rate": 0.00018964119084220103,
      "loss": 2.8934,
      "step": 6750
    },
    {
      "epoch": 0.6287418228889762,
      "grad_norm": 4.4375,
      "learning_rate": 0.0001894777679854831,
      "loss": 2.8878,
      "step": 6800
    },
    {
      "epoch": 0.6333649245278657,
      "grad_norm": 4.0,
      "learning_rate": 0.00018931313765135468,
      "loss": 2.8924,
      "step": 6850
    },
    {
      "epoch": 0.6379880261667553,
      "grad_norm": 4.40625,
      "learning_rate": 0.00018914730206145598,
      "loss": 2.9166,
      "step": 6900
    },
    {
      "epoch": 0.6426111278056448,
      "grad_norm": 4.15625,
      "learning_rate": 0.0001889802634536918,
      "loss": 2.8957,
      "step": 6950
    },
    {
      "epoch": 0.6472342294445343,
      "grad_norm": 4.40625,
      "learning_rate": 0.00018881202408220138,
      "loss": 2.8684,
      "step": 7000
    },
    {
      "epoch": 0.6518573310834239,
      "grad_norm": 3.984375,
      "learning_rate": 0.00018864258621732792,
      "loss": 2.9041,
      "step": 7050
    },
    {
      "epoch": 0.6564804327223134,
      "grad_norm": 4.125,
      "learning_rate": 0.0001884719521455879,
      "loss": 2.8904,
      "step": 7100
    },
    {
      "epoch": 0.661103534361203,
      "grad_norm": 3.953125,
      "learning_rate": 0.0001883001241696403,
      "loss": 2.8749,
      "step": 7150
    },
    {
      "epoch": 0.6657266360000924,
      "grad_norm": 4.5,
      "learning_rate": 0.0001881271046082556,
      "loss": 2.852,
      "step": 7200
    },
    {
      "epoch": 0.670349737638982,
      "grad_norm": 4.125,
      "learning_rate": 0.0001879528957962842,
      "loss": 2.8679,
      "step": 7250
    },
    {
      "epoch": 0.6749728392778716,
      "grad_norm": 3.96875,
      "learning_rate": 0.00018777750008462532,
      "loss": 2.8695,
      "step": 7300
    },
    {
      "epoch": 0.679595940916761,
      "grad_norm": 4.0625,
      "learning_rate": 0.00018760091984019482,
      "loss": 2.8536,
      "step": 7350
    },
    {
      "epoch": 0.6842190425556506,
      "grad_norm": 4.40625,
      "learning_rate": 0.00018742315744589374,
      "loss": 2.8616,
      "step": 7400
    },
    {
      "epoch": 0.6888421441945402,
      "grad_norm": 4.125,
      "learning_rate": 0.00018724421530057572,
      "loss": 2.8568,
      "step": 7450
    },
    {
      "epoch": 0.6934652458334296,
      "grad_norm": 4.125,
      "learning_rate": 0.0001870640958190149,
      "loss": 2.8603,
      "step": 7500
    },
    {
      "epoch": 0.6980883474723192,
      "grad_norm": 4.15625,
      "learning_rate": 0.00018688280143187326,
      "loss": 2.888,
      "step": 7550
    },
    {
      "epoch": 0.7027114491112088,
      "grad_norm": 4.0625,
      "learning_rate": 0.0001867003345856677,
      "loss": 2.823,
      "step": 7600
    },
    {
      "epoch": 0.7073345507500982,
      "grad_norm": 4.375,
      "learning_rate": 0.00018651669774273722,
      "loss": 2.8504,
      "step": 7650
    },
    {
      "epoch": 0.7119576523889878,
      "grad_norm": 4.125,
      "learning_rate": 0.00018633189338120956,
      "loss": 2.837,
      "step": 7700
    },
    {
      "epoch": 0.7165807540278774,
      "grad_norm": 3.859375,
      "learning_rate": 0.0001861459239949678,
      "loss": 2.8477,
      "step": 7750
    },
    {
      "epoch": 0.7212038556667668,
      "grad_norm": 4.15625,
      "learning_rate": 0.00018595879209361673,
      "loss": 2.8518,
      "step": 7800
    },
    {
      "epoch": 0.7258269573056564,
      "grad_norm": 4.15625,
      "learning_rate": 0.00018577050020244888,
      "loss": 2.815,
      "step": 7850
    },
    {
      "epoch": 0.7304500589445458,
      "grad_norm": 4.3125,
      "learning_rate": 0.00018558105086241062,
      "loss": 2.8459,
      "step": 7900
    },
    {
      "epoch": 0.7350731605834354,
      "grad_norm": 3.921875,
      "learning_rate": 0.00018539044663006769,
      "loss": 2.8051,
      "step": 7950
    },
    {
      "epoch": 0.739696262222325,
      "grad_norm": 3.9375,
      "learning_rate": 0.0001851986900775708,
      "loss": 2.8473,
      "step": 8000
    },
    {
      "epoch": 0.7443193638612144,
      "grad_norm": 4.09375,
      "learning_rate": 0.00018500578379262094,
      "loss": 2.8471,
      "step": 8050
    },
    {
      "epoch": 0.748942465500104,
      "grad_norm": 4.28125,
      "learning_rate": 0.00018481173037843436,
      "loss": 2.8341,
      "step": 8100
    },
    {
      "epoch": 0.7535655671389936,
      "grad_norm": 4.3125,
      "learning_rate": 0.0001846165324537075,
      "loss": 2.8392,
      "step": 8150
    },
    {
      "epoch": 0.758188668777883,
      "grad_norm": 4.21875,
      "learning_rate": 0.00018442019265258166,
      "loss": 2.8026,
      "step": 8200
    },
    {
      "epoch": 0.7628117704167726,
      "grad_norm": 4.4375,
      "learning_rate": 0.00018422271362460749,
      "loss": 2.7998,
      "step": 8250
    },
    {
      "epoch": 0.7674348720556622,
      "grad_norm": 3.8125,
      "learning_rate": 0.00018402409803470912,
      "loss": 2.8222,
      "step": 8300
    },
    {
      "epoch": 0.7720579736945516,
      "grad_norm": 3.8125,
      "learning_rate": 0.0001838243485631483,
      "loss": 2.794,
      "step": 8350
    },
    {
      "epoch": 0.7766810753334412,
      "grad_norm": 4.03125,
      "learning_rate": 0.0001836234679054882,
      "loss": 2.8043,
      "step": 8400
    },
    {
      "epoch": 0.7813041769723308,
      "grad_norm": 4.09375,
      "learning_rate": 0.00018342145877255694,
      "loss": 2.8087,
      "step": 8450
    },
    {
      "epoch": 0.7859272786112202,
      "grad_norm": 4.03125,
      "learning_rate": 0.00018321832389041126,
      "loss": 2.7922,
      "step": 8500
    },
    {
      "epoch": 0.7905503802501098,
      "grad_norm": 4.15625,
      "learning_rate": 0.00018301406600029947,
      "loss": 2.7813,
      "step": 8550
    },
    {
      "epoch": 0.7951734818889993,
      "grad_norm": 3.921875,
      "learning_rate": 0.00018280868785862454,
      "loss": 2.7775,
      "step": 8600
    },
    {
      "epoch": 0.7997965835278888,
      "grad_norm": 4.03125,
      "learning_rate": 0.00018260219223690697,
      "loss": 2.8344,
      "step": 8650
    },
    {
      "epoch": 0.8044196851667784,
      "grad_norm": 4.09375,
      "learning_rate": 0.0001823945819217473,
      "loss": 2.7897,
      "step": 8700
    },
    {
      "epoch": 0.8090427868056679,
      "grad_norm": 4.0625,
      "learning_rate": 0.00018218585971478864,
      "loss": 2.8006,
      "step": 8750
    },
    {
      "epoch": 0.8136658884445575,
      "grad_norm": 4.4375,
      "learning_rate": 0.0001819760284326786,
      "loss": 2.7929,
      "step": 8800
    },
    {
      "epoch": 0.818288990083447,
      "grad_norm": 3.875,
      "learning_rate": 0.0001817650909070316,
      "loss": 2.7931,
      "step": 8850
    },
    {
      "epoch": 0.8229120917223365,
      "grad_norm": 4.09375,
      "learning_rate": 0.00018155304998439045,
      "loss": 2.7972,
      "step": 8900
    },
    {
      "epoch": 0.827535193361226,
      "grad_norm": 4.0625,
      "learning_rate": 0.00018133990852618796,
      "loss": 2.7644,
      "step": 8950
    },
    {
      "epoch": 0.8321582950001156,
      "grad_norm": 4.65625,
      "learning_rate": 0.00018112566940870842,
      "loss": 2.785,
      "step": 9000
    },
    {
      "epoch": 0.8367813966390051,
      "grad_norm": 4.375,
      "learning_rate": 0.00018091033552304872,
      "loss": 2.8149,
      "step": 9050
    },
    {
      "epoch": 0.8414044982778947,
      "grad_norm": 3.921875,
      "learning_rate": 0.0001806939097750793,
      "loss": 2.7606,
      "step": 9100
    },
    {
      "epoch": 0.8460275999167842,
      "grad_norm": 4.0,
      "learning_rate": 0.00018047639508540498,
      "loss": 2.7607,
      "step": 9150
    },
    {
      "epoch": 0.8506507015556737,
      "grad_norm": 3.8125,
      "learning_rate": 0.00018025779438932555,
      "loss": 2.7729,
      "step": 9200
    },
    {
      "epoch": 0.8552738031945633,
      "grad_norm": 3.796875,
      "learning_rate": 0.00018003811063679618,
      "loss": 2.804,
      "step": 9250
    },
    {
      "epoch": 0.8598969048334527,
      "grad_norm": 4.0625,
      "learning_rate": 0.0001798173467923876,
      "loss": 2.7478,
      "step": 9300
    },
    {
      "epoch": 0.8645200064723423,
      "grad_norm": 4.1875,
      "learning_rate": 0.00017959550583524595,
      "loss": 2.7585,
      "step": 9350
    },
    {
      "epoch": 0.8691431081112319,
      "grad_norm": 4.34375,
      "learning_rate": 0.00017937259075905289,
      "loss": 2.7708,
      "step": 9400
    },
    {
      "epoch": 0.8737662097501213,
      "grad_norm": 3.953125,
      "learning_rate": 0.00017914860457198483,
      "loss": 2.8107,
      "step": 9450
    },
    {
      "epoch": 0.8783893113890109,
      "grad_norm": 4.25,
      "learning_rate": 0.0001789235502966727,
      "loss": 2.7751,
      "step": 9500
    },
    {
      "epoch": 0.8830124130279005,
      "grad_norm": 4.25,
      "learning_rate": 0.00017869743097016083,
      "loss": 2.7921,
      "step": 9550
    },
    {
      "epoch": 0.8876355146667899,
      "grad_norm": 4.0,
      "learning_rate": 0.00017847024964386617,
      "loss": 2.7672,
      "step": 9600
    },
    {
      "epoch": 0.8922586163056795,
      "grad_norm": 4.21875,
      "learning_rate": 0.00017824200938353717,
      "loss": 2.7566,
      "step": 9650
    },
    {
      "epoch": 0.8968817179445691,
      "grad_norm": 4.3125,
      "learning_rate": 0.00017801271326921207,
      "loss": 2.7537,
      "step": 9700
    },
    {
      "epoch": 0.9015048195834585,
      "grad_norm": 4.1875,
      "learning_rate": 0.0001777823643951778,
      "loss": 2.757,
      "step": 9750
    },
    {
      "epoch": 0.9061279212223481,
      "grad_norm": 4.09375,
      "learning_rate": 0.0001775509658699278,
      "loss": 2.7451,
      "step": 9800
    },
    {
      "epoch": 0.9107510228612377,
      "grad_norm": 4.0,
      "learning_rate": 0.00017731852081612036,
      "loss": 2.7302,
      "step": 9850
    },
    {
      "epoch": 0.9153741245001271,
      "grad_norm": 4.1875,
      "learning_rate": 0.00017708503237053638,
      "loss": 2.7548,
      "step": 9900
    },
    {
      "epoch": 0.9199972261390167,
      "grad_norm": 4.125,
      "learning_rate": 0.000176850503684037,
      "loss": 2.761,
      "step": 9950
    },
    {
      "epoch": 0.9246203277779061,
      "grad_norm": 3.953125,
      "learning_rate": 0.00017661493792152117,
      "loss": 2.755,
      "step": 10000
    },
    {
      "epoch": 0.9292434294167957,
      "grad_norm": 3.90625,
      "learning_rate": 0.00017637833826188282,
      "loss": 2.7341,
      "step": 10050
    },
    {
      "epoch": 0.9338665310556853,
      "grad_norm": 4.34375,
      "learning_rate": 0.00017614070789796809,
      "loss": 2.7432,
      "step": 10100
    },
    {
      "epoch": 0.9384896326945747,
      "grad_norm": 3.8125,
      "learning_rate": 0.00017590205003653213,
      "loss": 2.7364,
      "step": 10150
    },
    {
      "epoch": 0.9431127343334643,
      "grad_norm": 4.15625,
      "learning_rate": 0.00017566236789819597,
      "loss": 2.7333,
      "step": 10200
    },
    {
      "epoch": 0.9477358359723539,
      "grad_norm": 4.09375,
      "learning_rate": 0.00017542166471740288,
      "loss": 2.7549,
      "step": 10250
    },
    {
      "epoch": 0.9523589376112434,
      "grad_norm": 4.0625,
      "learning_rate": 0.00017517994374237488,
      "loss": 2.7483,
      "step": 10300
    },
    {
      "epoch": 0.9569820392501329,
      "grad_norm": 4.1875,
      "learning_rate": 0.0001749372082350688,
      "loss": 2.741,
      "step": 10350
    },
    {
      "epoch": 0.9616051408890225,
      "grad_norm": 3.8125,
      "learning_rate": 0.00017469346147113224,
      "loss": 2.7154,
      "step": 10400
    },
    {
      "epoch": 0.966228242527912,
      "grad_norm": 3.765625,
      "learning_rate": 0.00017444870673985957,
      "loss": 2.7204,
      "step": 10450
    },
    {
      "epoch": 0.9708513441668015,
      "grad_norm": 3.875,
      "learning_rate": 0.00017420294734414728,
      "loss": 2.7356,
      "step": 10500
    },
    {
      "epoch": 0.9754744458056911,
      "grad_norm": 4.03125,
      "learning_rate": 0.0001739561866004496,
      "loss": 2.7299,
      "step": 10550
    },
    {
      "epoch": 0.9800975474445806,
      "grad_norm": 4.0,
      "learning_rate": 0.00017370842783873358,
      "loss": 2.7336,
      "step": 10600
    },
    {
      "epoch": 0.9847206490834701,
      "grad_norm": 4.34375,
      "learning_rate": 0.0001734596744024343,
      "loss": 2.7171,
      "step": 10650
    },
    {
      "epoch": 0.9893437507223596,
      "grad_norm": 4.15625,
      "learning_rate": 0.00017320992964840975,
      "loss": 2.74,
      "step": 10700
    },
    {
      "epoch": 0.9939668523612492,
      "grad_norm": 4.0,
      "learning_rate": 0.00017295919694689538,
      "loss": 2.7389,
      "step": 10750
    },
    {
      "epoch": 0.9985899540001387,
      "grad_norm": 4.03125,
      "learning_rate": 0.00017270747968145872,
      "loss": 2.72,
      "step": 10800
    }
  ],
  "logging_steps": 50,
  "max_steps": 43260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.6244943709875814e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}