{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 6250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 0.24006609618663788,
      "learning_rate": 0.0001984,
      "loss": 1.0243,
      "step": 50
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.21576859056949615,
      "learning_rate": 0.0001968,
      "loss": 0.9669,
      "step": 100
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.20258210599422455,
      "learning_rate": 0.0001952,
      "loss": 0.9397,
      "step": 150
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.2684886157512665,
      "learning_rate": 0.00019360000000000002,
      "loss": 0.8793,
      "step": 200
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.22625429928302765,
      "learning_rate": 0.000192,
      "loss": 0.9209,
      "step": 250
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.25748205184936523,
      "learning_rate": 0.0001904,
      "loss": 0.8553,
      "step": 300
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.24440611898899078,
      "learning_rate": 0.0001888,
      "loss": 0.9141,
      "step": 350
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.24657492339611053,
      "learning_rate": 0.00018720000000000002,
      "loss": 0.8973,
      "step": 400
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.21331937611103058,
      "learning_rate": 0.0001856,
      "loss": 0.8836,
      "step": 450
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.23378247022628784,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.8992,
      "step": 500
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.21668757498264313,
      "learning_rate": 0.00018240000000000002,
      "loss": 0.8479,
      "step": 550
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.22808493673801422,
      "learning_rate": 0.0001808,
      "loss": 0.8805,
      "step": 600
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.2394104301929474,
      "learning_rate": 0.00017920000000000002,
      "loss": 0.8633,
      "step": 650
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.22561711072921753,
      "learning_rate": 0.0001776,
      "loss": 0.8766,
      "step": 700
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.29312923550605774,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.891,
      "step": 750
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.21683369576931,
      "learning_rate": 0.0001744,
      "loss": 0.8473,
      "step": 800
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.2582944929599762,
      "learning_rate": 0.0001728,
      "loss": 0.8949,
      "step": 850
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.2305222898721695,
      "learning_rate": 0.00017120000000000001,
      "loss": 0.8535,
      "step": 900
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.2317700982093811,
      "learning_rate": 0.0001696,
      "loss": 0.8677,
      "step": 950
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.2534327208995819,
      "learning_rate": 0.000168,
      "loss": 0.8662,
      "step": 1000
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.2503647208213806,
      "learning_rate": 0.0001664,
      "loss": 0.8606,
      "step": 1050
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.2579597234725952,
      "learning_rate": 0.0001648,
      "loss": 0.833,
      "step": 1100
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.2581159472465515,
      "learning_rate": 0.0001632,
      "loss": 0.8415,
      "step": 1150
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.24251115322113037,
      "learning_rate": 0.00016160000000000002,
      "loss": 0.8484,
      "step": 1200
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.28298044204711914,
      "learning_rate": 0.00016,
      "loss": 0.8405,
      "step": 1250
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.2423146665096283,
      "learning_rate": 0.00015840000000000003,
      "loss": 0.8315,
      "step": 1300
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.22693276405334473,
      "learning_rate": 0.00015680000000000002,
      "loss": 0.8757,
      "step": 1350
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.24105730652809143,
      "learning_rate": 0.0001552,
      "loss": 0.8485,
      "step": 1400
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.22538623213768005,
      "learning_rate": 0.00015360000000000002,
      "loss": 0.8946,
      "step": 1450
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.2406863272190094,
      "learning_rate": 0.000152,
      "loss": 0.8389,
      "step": 1500
    },
    {
      "epoch": 0.248,
      "grad_norm": 0.2680400311946869,
      "learning_rate": 0.0001504,
      "loss": 0.8283,
      "step": 1550
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.2538231909275055,
      "learning_rate": 0.0001488,
      "loss": 0.8384,
      "step": 1600
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.26007387042045593,
      "learning_rate": 0.0001472,
      "loss": 0.8589,
      "step": 1650
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.2680321931838989,
      "learning_rate": 0.00014560000000000002,
      "loss": 0.8872,
      "step": 1700
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.2379782646894455,
      "learning_rate": 0.000144,
      "loss": 0.8483,
      "step": 1750
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.2729997932910919,
      "learning_rate": 0.0001424,
      "loss": 0.8381,
      "step": 1800
    },
    {
      "epoch": 0.296,
      "grad_norm": 0.24824947118759155,
      "learning_rate": 0.0001408,
      "loss": 0.8274,
      "step": 1850
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.26121681928634644,
      "learning_rate": 0.0001392,
      "loss": 0.8491,
      "step": 1900
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.24737513065338135,
      "learning_rate": 0.00013759999999999998,
      "loss": 0.8416,
      "step": 1950
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2495298683643341,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.829,
      "step": 2000
    },
    {
      "epoch": 0.328,
      "grad_norm": 0.25478219985961914,
      "learning_rate": 0.00013440000000000001,
      "loss": 0.8247,
      "step": 2050
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.24906663596630096,
      "learning_rate": 0.0001328,
      "loss": 0.853,
      "step": 2100
    },
    {
      "epoch": 0.344,
      "grad_norm": 0.2297120839357376,
      "learning_rate": 0.00013120000000000002,
      "loss": 0.8289,
      "step": 2150
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.2441694438457489,
      "learning_rate": 0.0001296,
      "loss": 0.8592,
      "step": 2200
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.2818741202354431,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.8065,
      "step": 2250
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.2782455086708069,
      "learning_rate": 0.0001264,
      "loss": 0.8333,
      "step": 2300
    },
    {
      "epoch": 0.376,
      "grad_norm": 0.3333749771118164,
      "learning_rate": 0.0001248,
      "loss": 0.8714,
      "step": 2350
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.38234880566596985,
      "learning_rate": 0.0001232,
      "loss": 0.8206,
      "step": 2400
    },
    {
      "epoch": 0.392,
      "grad_norm": 0.2502688765525818,
      "learning_rate": 0.0001216,
      "loss": 0.8561,
      "step": 2450
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.2759045958518982,
      "learning_rate": 0.00012,
      "loss": 0.858,
      "step": 2500
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.3138297200202942,
      "learning_rate": 0.0001184,
      "loss": 0.8148,
      "step": 2550
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.27893930673599243,
      "learning_rate": 0.00011679999999999999,
      "loss": 0.8181,
      "step": 2600
    },
    {
      "epoch": 0.424,
      "grad_norm": 0.2226714789867401,
      "learning_rate": 0.0001152,
      "loss": 0.8326,
      "step": 2650
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.23976224660873413,
      "learning_rate": 0.0001136,
      "loss": 0.8205,
      "step": 2700
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.23596003651618958,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.8336,
      "step": 2750
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.2597508430480957,
      "learning_rate": 0.00011040000000000001,
      "loss": 0.8202,
      "step": 2800
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.2530119717121124,
      "learning_rate": 0.00010880000000000002,
      "loss": 0.8193,
      "step": 2850
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.267026424407959,
      "learning_rate": 0.00010720000000000002,
      "loss": 0.8272,
      "step": 2900
    },
    {
      "epoch": 0.472,
      "grad_norm": 0.3313164710998535,
      "learning_rate": 0.0001056,
      "loss": 0.829,
      "step": 2950
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.24725987017154694,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.8204,
      "step": 3000
    },
    {
      "epoch": 0.488,
      "grad_norm": 0.3102189302444458,
      "learning_rate": 0.00010240000000000001,
      "loss": 0.8344,
      "step": 3050
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.2404993623495102,
      "learning_rate": 0.00010080000000000001,
      "loss": 0.8172,
      "step": 3100
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.24549129605293274,
      "learning_rate": 9.92e-05,
      "loss": 0.833,
      "step": 3150
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.2698763906955719,
      "learning_rate": 9.76e-05,
      "loss": 0.8206,
      "step": 3200
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.26306065917015076,
      "learning_rate": 9.6e-05,
      "loss": 0.8517,
      "step": 3250
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.2710007429122925,
      "learning_rate": 9.44e-05,
      "loss": 0.8115,
      "step": 3300
    },
    {
      "epoch": 0.536,
      "grad_norm": 0.2536482810974121,
      "learning_rate": 9.28e-05,
      "loss": 0.8196,
      "step": 3350
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.28047412633895874,
      "learning_rate": 9.120000000000001e-05,
      "loss": 0.8134,
      "step": 3400
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.2554551661014557,
      "learning_rate": 8.960000000000001e-05,
      "loss": 0.8085,
      "step": 3450
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.2920052707195282,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.8155,
      "step": 3500
    },
    {
      "epoch": 0.568,
      "grad_norm": 0.2649592161178589,
      "learning_rate": 8.64e-05,
      "loss": 0.8123,
      "step": 3550
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.2757607102394104,
      "learning_rate": 8.48e-05,
      "loss": 0.8182,
      "step": 3600
    },
    {
      "epoch": 0.584,
      "grad_norm": 0.2552868127822876,
      "learning_rate": 8.32e-05,
      "loss": 0.8155,
      "step": 3650
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.24389928579330444,
      "learning_rate": 8.16e-05,
      "loss": 0.7927,
      "step": 3700
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.2750285565853119,
      "learning_rate": 8e-05,
      "loss": 0.8362,
      "step": 3750
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.27113068103790283,
      "learning_rate": 7.840000000000001e-05,
      "loss": 0.8225,
      "step": 3800
    },
    {
      "epoch": 0.616,
      "grad_norm": 0.25137266516685486,
      "learning_rate": 7.680000000000001e-05,
      "loss": 0.8049,
      "step": 3850
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.26775482296943665,
      "learning_rate": 7.52e-05,
      "loss": 0.8059,
      "step": 3900
    },
    {
      "epoch": 0.632,
      "grad_norm": 0.24626025557518005,
      "learning_rate": 7.36e-05,
      "loss": 0.8036,
      "step": 3950
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.2576785385608673,
      "learning_rate": 7.2e-05,
      "loss": 0.828,
      "step": 4000
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.28320208191871643,
      "learning_rate": 7.04e-05,
      "loss": 0.8015,
      "step": 4050
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.292799711227417,
      "learning_rate": 6.879999999999999e-05,
      "loss": 0.8165,
      "step": 4100
    },
    {
      "epoch": 0.664,
      "grad_norm": 0.2561057507991791,
      "learning_rate": 6.720000000000001e-05,
      "loss": 0.8035,
      "step": 4150
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.318015456199646,
      "learning_rate": 6.560000000000001e-05,
      "loss": 0.7909,
      "step": 4200
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.2850799858570099,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.8111,
      "step": 4250
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.3318442404270172,
      "learning_rate": 6.24e-05,
      "loss": 0.8216,
      "step": 4300
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.24898533523082733,
      "learning_rate": 6.08e-05,
      "loss": 0.79,
      "step": 4350
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.2550944685935974,
      "learning_rate": 5.92e-05,
      "loss": 0.7977,
      "step": 4400
    },
    {
      "epoch": 0.712,
      "grad_norm": 0.33275166153907776,
      "learning_rate": 5.76e-05,
      "loss": 0.808,
      "step": 4450
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.2537584900856018,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.8177,
      "step": 4500
    },
    {
      "epoch": 0.728,
      "grad_norm": 0.2836528420448303,
      "learning_rate": 5.440000000000001e-05,
      "loss": 0.797,
      "step": 4550
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.24697652459144592,
      "learning_rate": 5.28e-05,
      "loss": 0.8047,
      "step": 4600
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.2920159101486206,
      "learning_rate": 5.1200000000000004e-05,
      "loss": 0.793,
      "step": 4650
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.24589219689369202,
      "learning_rate": 4.96e-05,
      "loss": 0.8218,
      "step": 4700
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.28507670760154724,
      "learning_rate": 4.8e-05,
      "loss": 0.8143,
      "step": 4750
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.22233684360980988,
      "learning_rate": 4.64e-05,
      "loss": 0.8108,
      "step": 4800
    },
    {
      "epoch": 0.776,
      "grad_norm": 0.24076737463474274,
      "learning_rate": 4.4800000000000005e-05,
      "loss": 0.8077,
      "step": 4850
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.24421195685863495,
      "learning_rate": 4.32e-05,
      "loss": 0.8102,
      "step": 4900
    },
    {
      "epoch": 0.792,
      "grad_norm": 0.26924577355384827,
      "learning_rate": 4.16e-05,
      "loss": 0.827,
      "step": 4950
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3362084627151489,
      "learning_rate": 4e-05,
      "loss": 0.8222,
      "step": 5000
    },
    {
      "epoch": 0.808,
      "grad_norm": 0.28752413392066956,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.8209,
      "step": 5050
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.3482488989830017,
      "learning_rate": 3.68e-05,
      "loss": 0.8077,
      "step": 5100
    },
    {
      "epoch": 0.824,
      "grad_norm": 0.2573867738246918,
      "learning_rate": 3.52e-05,
      "loss": 0.8089,
      "step": 5150
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.27762147784233093,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.7974,
      "step": 5200
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.30096402764320374,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.8051,
      "step": 5250
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.25133249163627625,
      "learning_rate": 3.04e-05,
      "loss": 0.8179,
      "step": 5300
    },
    {
      "epoch": 0.856,
      "grad_norm": 0.26828518509864807,
      "learning_rate": 2.88e-05,
      "loss": 0.8136,
      "step": 5350
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.2636822462081909,
      "learning_rate": 2.7200000000000004e-05,
      "loss": 0.8122,
      "step": 5400
    },
    {
      "epoch": 0.872,
      "grad_norm": 0.29320311546325684,
      "learning_rate": 2.5600000000000002e-05,
      "loss": 0.8294,
      "step": 5450
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.25704631209373474,
      "learning_rate": 2.4e-05,
      "loss": 0.8278,
      "step": 5500
    },
    {
      "epoch": 0.888,
      "grad_norm": 0.3402651250362396,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 0.8084,
      "step": 5550
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.24089041352272034,
      "learning_rate": 2.08e-05,
      "loss": 0.8014,
      "step": 5600
    },
    {
      "epoch": 0.904,
      "grad_norm": 0.3702704608440399,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.804,
      "step": 5650
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.295099675655365,
      "learning_rate": 1.76e-05,
      "loss": 0.8098,
      "step": 5700
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.24626977741718292,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.8051,
      "step": 5750
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.27932465076446533,
      "learning_rate": 1.44e-05,
      "loss": 0.8031,
      "step": 5800
    },
    {
      "epoch": 0.936,
      "grad_norm": 0.27001097798347473,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.8068,
      "step": 5850
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.2695982754230499,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.8047,
      "step": 5900
    },
    {
      "epoch": 0.952,
      "grad_norm": 0.27733317017555237,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.8238,
      "step": 5950
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.25620317459106445,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.78,
      "step": 6000
    },
    {
      "epoch": 0.968,
      "grad_norm": 0.24671310186386108,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.8233,
      "step": 6050
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.2986748516559601,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.8183,
      "step": 6100
    },
    {
      "epoch": 0.984,
      "grad_norm": 0.28886911273002625,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.7884,
      "step": 6150
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.27886465191841125,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.7885,
      "step": 6200
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.260232537984848,
      "learning_rate": 0.0,
      "loss": 0.7775,
      "step": 6250
    }
  ],
  "logging_steps": 50,
  "max_steps": 6250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.2752831434633216e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}