{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.96,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032,
      "grad_norm": 0.18818965554237366,
      "learning_rate": 0.00019942400000000002,
      "loss": 1.4398,
      "step": 10
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.20508623123168945,
      "learning_rate": 0.00019878400000000003,
      "loss": 1.3682,
      "step": 20
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.18839821219444275,
      "learning_rate": 0.000198144,
      "loss": 1.3981,
      "step": 30
    },
    {
      "epoch": 0.0128,
      "grad_norm": 0.20183835923671722,
      "learning_rate": 0.000197504,
      "loss": 1.3109,
      "step": 40
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.22559459507465363,
      "learning_rate": 0.000196864,
      "loss": 1.343,
      "step": 50
    },
    {
      "epoch": 0.0192,
      "grad_norm": 0.21955451369285583,
      "learning_rate": 0.000196224,
      "loss": 1.3645,
      "step": 60
    },
    {
      "epoch": 0.0224,
      "grad_norm": 0.2031077742576599,
      "learning_rate": 0.000195584,
      "loss": 1.2116,
      "step": 70
    },
    {
      "epoch": 0.0256,
      "grad_norm": 0.24542862176895142,
      "learning_rate": 0.000194944,
      "loss": 1.3466,
      "step": 80
    },
    {
      "epoch": 0.0288,
      "grad_norm": 0.24425864219665527,
      "learning_rate": 0.00019430400000000002,
      "loss": 1.2202,
      "step": 90
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.23464636504650116,
      "learning_rate": 0.000193664,
      "loss": 1.2862,
      "step": 100
    },
    {
      "epoch": 0.0352,
      "grad_norm": 0.22896084189414978,
      "learning_rate": 0.000193024,
      "loss": 1.2424,
      "step": 110
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.30132901668548584,
      "learning_rate": 0.000192384,
      "loss": 1.2674,
      "step": 120
    },
    {
      "epoch": 0.0416,
      "grad_norm": 0.2417932003736496,
      "learning_rate": 0.000191744,
      "loss": 1.2433,
      "step": 130
    },
    {
      "epoch": 0.0448,
      "grad_norm": 0.25476428866386414,
      "learning_rate": 0.00019110400000000002,
      "loss": 1.2969,
      "step": 140
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.28159213066101074,
      "learning_rate": 0.00019046400000000002,
      "loss": 1.2396,
      "step": 150
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.2914562225341797,
      "learning_rate": 0.000189824,
      "loss": 1.3067,
      "step": 160
    },
    {
      "epoch": 0.0544,
      "grad_norm": 0.2946033477783203,
      "learning_rate": 0.000189184,
      "loss": 1.1911,
      "step": 170
    },
    {
      "epoch": 0.0576,
      "grad_norm": 0.2544347941875458,
      "learning_rate": 0.00018854400000000002,
      "loss": 1.2062,
      "step": 180
    },
    {
      "epoch": 0.0608,
      "grad_norm": 0.2680202126502991,
      "learning_rate": 0.00018790400000000002,
      "loss": 1.1604,
      "step": 190
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.25478115677833557,
      "learning_rate": 0.00018726400000000003,
      "loss": 1.2515,
      "step": 200
    },
    {
      "epoch": 0.0672,
      "grad_norm": 0.26804226636886597,
      "learning_rate": 0.000186624,
      "loss": 1.2765,
      "step": 210
    },
    {
      "epoch": 0.0704,
      "grad_norm": 0.24587133526802063,
      "learning_rate": 0.00018598400000000001,
      "loss": 1.1768,
      "step": 220
    },
    {
      "epoch": 0.0736,
      "grad_norm": 0.27216073870658875,
      "learning_rate": 0.00018534400000000002,
      "loss": 1.1848,
      "step": 230
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.3114471733570099,
      "learning_rate": 0.000184704,
      "loss": 1.2086,
      "step": 240
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3045384883880615,
      "learning_rate": 0.000184064,
      "loss": 1.1874,
      "step": 250
    },
    {
      "epoch": 0.0832,
      "grad_norm": 0.2793915271759033,
      "learning_rate": 0.000183424,
      "loss": 1.1977,
      "step": 260
    },
    {
      "epoch": 0.0864,
      "grad_norm": 0.34699785709381104,
      "learning_rate": 0.000182784,
      "loss": 1.2089,
      "step": 270
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.25291335582733154,
      "learning_rate": 0.000182144,
      "loss": 1.2459,
      "step": 280
    },
    {
      "epoch": 0.0928,
      "grad_norm": 0.2616818845272064,
      "learning_rate": 0.000181504,
      "loss": 1.2655,
      "step": 290
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.2569883167743683,
      "learning_rate": 0.000180864,
      "loss": 1.2479,
      "step": 300
    },
    {
      "epoch": 0.0992,
      "grad_norm": 0.33097052574157715,
      "learning_rate": 0.00018022400000000001,
      "loss": 1.1975,
      "step": 310
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.2557203471660614,
      "learning_rate": 0.00017958400000000002,
      "loss": 1.1423,
      "step": 320
    },
    {
      "epoch": 0.1056,
      "grad_norm": 0.24836640059947968,
      "learning_rate": 0.000178944,
      "loss": 1.197,
      "step": 330
    },
    {
      "epoch": 0.1088,
      "grad_norm": 0.25998368859291077,
      "learning_rate": 0.000178304,
      "loss": 1.195,
      "step": 340
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.29318585991859436,
      "learning_rate": 0.000177664,
      "loss": 1.1771,
      "step": 350
    },
    {
      "epoch": 0.1152,
      "grad_norm": 0.2819266617298126,
      "learning_rate": 0.00017702400000000002,
      "loss": 1.1113,
      "step": 360
    },
    {
      "epoch": 0.1184,
      "grad_norm": 0.24419356882572174,
      "learning_rate": 0.00017638400000000002,
      "loss": 1.2027,
      "step": 370
    },
    {
      "epoch": 0.1216,
      "grad_norm": 0.30148938298225403,
      "learning_rate": 0.000175744,
      "loss": 1.1583,
      "step": 380
    },
    {
      "epoch": 0.1248,
      "grad_norm": 0.2704978287220001,
      "learning_rate": 0.000175104,
      "loss": 1.2246,
      "step": 390
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.2642189562320709,
      "learning_rate": 0.00017446400000000002,
      "loss": 1.1543,
      "step": 400
    },
    {
      "epoch": 0.1312,
      "grad_norm": 0.31052809953689575,
      "learning_rate": 0.00017382400000000002,
      "loss": 1.2039,
      "step": 410
    },
    {
      "epoch": 0.1344,
      "grad_norm": 0.2596384286880493,
      "learning_rate": 0.000173184,
      "loss": 1.1693,
      "step": 420
    },
    {
      "epoch": 0.1376,
      "grad_norm": 0.2813952565193176,
      "learning_rate": 0.000172544,
      "loss": 1.2213,
      "step": 430
    },
    {
      "epoch": 0.1408,
      "grad_norm": 0.26021143794059753,
      "learning_rate": 0.00017190399999999999,
      "loss": 1.1611,
      "step": 440
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.3072742521762848,
      "learning_rate": 0.000171264,
      "loss": 1.1464,
      "step": 450
    },
    {
      "epoch": 0.1472,
      "grad_norm": 0.3125726580619812,
      "learning_rate": 0.000170624,
      "loss": 1.1901,
      "step": 460
    },
    {
      "epoch": 0.1504,
      "grad_norm": 0.25702011585235596,
      "learning_rate": 0.000169984,
      "loss": 1.1439,
      "step": 470
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.26658275723457336,
      "learning_rate": 0.000169344,
      "loss": 1.1256,
      "step": 480
    },
    {
      "epoch": 0.1568,
      "grad_norm": 0.2687830626964569,
      "learning_rate": 0.00016870400000000002,
      "loss": 1.233,
      "step": 490
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.30417656898498535,
      "learning_rate": 0.000168064,
      "loss": 1.1951,
      "step": 500
    },
    {
      "epoch": 0.1632,
      "grad_norm": 0.24493242800235748,
      "learning_rate": 0.000167424,
      "loss": 1.2125,
      "step": 510
    },
    {
      "epoch": 0.1664,
      "grad_norm": 0.2442469447851181,
      "learning_rate": 0.000166784,
      "loss": 1.2005,
      "step": 520
    },
    {
      "epoch": 0.1696,
      "grad_norm": 0.2598196566104889,
      "learning_rate": 0.00016614400000000001,
      "loss": 1.1361,
      "step": 530
    },
    {
      "epoch": 0.1728,
      "grad_norm": 0.2823512852191925,
      "learning_rate": 0.00016550400000000002,
      "loss": 1.2671,
      "step": 540
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.27284982800483704,
      "learning_rate": 0.00016486400000000003,
      "loss": 1.2019,
      "step": 550
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.4265678822994232,
      "learning_rate": 0.000164224,
      "loss": 1.1557,
      "step": 560
    },
    {
      "epoch": 0.1824,
      "grad_norm": 0.32852381467819214,
      "learning_rate": 0.000163584,
      "loss": 1.1792,
      "step": 570
    },
    {
      "epoch": 0.1856,
      "grad_norm": 0.25044888257980347,
      "learning_rate": 0.00016294400000000002,
      "loss": 1.1814,
      "step": 580
    },
    {
      "epoch": 0.1888,
      "grad_norm": 0.30278605222702026,
      "learning_rate": 0.00016230400000000002,
      "loss": 1.1865,
      "step": 590
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.259230375289917,
      "learning_rate": 0.000161664,
      "loss": 1.2012,
      "step": 600
    },
    {
      "epoch": 0.1952,
      "grad_norm": 0.3037353456020355,
      "learning_rate": 0.000161024,
      "loss": 1.1508,
      "step": 610
    },
    {
      "epoch": 0.1984,
      "grad_norm": 0.32500702142715454,
      "learning_rate": 0.000160384,
      "loss": 1.2302,
      "step": 620
    },
    {
      "epoch": 0.2016,
      "grad_norm": 0.3390319049358368,
      "learning_rate": 0.000159744,
      "loss": 1.1949,
      "step": 630
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.30461153388023376,
      "learning_rate": 0.000159104,
      "loss": 1.1659,
      "step": 640
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.2725638449192047,
      "learning_rate": 0.000158464,
      "loss": 1.1905,
      "step": 650
    },
    {
      "epoch": 0.2112,
      "grad_norm": 0.24364377558231354,
      "learning_rate": 0.000157824,
      "loss": 1.1194,
      "step": 660
    },
    {
      "epoch": 0.2144,
      "grad_norm": 0.2993292510509491,
      "learning_rate": 0.000157184,
      "loss": 1.165,
      "step": 670
    },
    {
      "epoch": 0.2176,
      "grad_norm": 0.22024789452552795,
      "learning_rate": 0.000156544,
      "loss": 1.1187,
      "step": 680
    },
    {
      "epoch": 0.2208,
      "grad_norm": 0.2543094754219055,
      "learning_rate": 0.000155904,
      "loss": 1.0779,
      "step": 690
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.31767502427101135,
      "learning_rate": 0.000155264,
      "loss": 1.1076,
      "step": 700
    },
    {
      "epoch": 0.2272,
      "grad_norm": 0.27651944756507874,
      "learning_rate": 0.00015462400000000002,
      "loss": 1.1748,
      "step": 710
    },
    {
      "epoch": 0.2304,
      "grad_norm": 0.2532593905925751,
      "learning_rate": 0.00015398400000000002,
      "loss": 1.1302,
      "step": 720
    },
    {
      "epoch": 0.2336,
      "grad_norm": 0.26502105593681335,
      "learning_rate": 0.000153344,
      "loss": 1.1652,
      "step": 730
    },
    {
      "epoch": 0.2368,
      "grad_norm": 0.22709833085536957,
      "learning_rate": 0.000152704,
      "loss": 1.1045,
      "step": 740
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.273548424243927,
      "learning_rate": 0.000152064,
      "loss": 1.1216,
      "step": 750
    },
    {
      "epoch": 0.2432,
      "grad_norm": 0.26936766505241394,
      "learning_rate": 0.00015142400000000002,
      "loss": 1.0981,
      "step": 760
    },
    {
      "epoch": 0.2464,
      "grad_norm": 0.2642468810081482,
      "learning_rate": 0.00015078400000000003,
      "loss": 1.1044,
      "step": 770
    },
    {
      "epoch": 0.2496,
      "grad_norm": 0.25724905729293823,
      "learning_rate": 0.000150144,
      "loss": 1.1474,
      "step": 780
    },
    {
      "epoch": 0.2528,
      "grad_norm": 0.27715614438056946,
      "learning_rate": 0.000149504,
      "loss": 1.102,
      "step": 790
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.25462499260902405,
      "learning_rate": 0.00014886400000000002,
      "loss": 1.1834,
      "step": 800
    },
    {
      "epoch": 0.2592,
      "grad_norm": 0.25248298048973083,
      "learning_rate": 0.000148224,
      "loss": 1.2023,
      "step": 810
    },
    {
      "epoch": 0.2624,
      "grad_norm": 0.3147791922092438,
      "learning_rate": 0.000147584,
      "loss": 1.1564,
      "step": 820
    },
    {
      "epoch": 0.2656,
      "grad_norm": 0.30874860286712646,
      "learning_rate": 0.000146944,
      "loss": 1.1722,
      "step": 830
    },
    {
      "epoch": 0.2688,
      "grad_norm": 0.2486383467912674,
      "learning_rate": 0.000146304,
      "loss": 1.1161,
      "step": 840
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.24819347262382507,
      "learning_rate": 0.000145664,
      "loss": 1.1813,
      "step": 850
    },
    {
      "epoch": 0.2752,
      "grad_norm": 0.2713952660560608,
      "learning_rate": 0.000145024,
      "loss": 1.0917,
      "step": 860
    },
    {
      "epoch": 0.2784,
      "grad_norm": 0.2632099986076355,
      "learning_rate": 0.000144384,
      "loss": 1.1806,
      "step": 870
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.24610574543476105,
      "learning_rate": 0.000143744,
      "loss": 1.1397,
      "step": 880
    },
    {
      "epoch": 0.2848,
      "grad_norm": 0.3086780607700348,
      "learning_rate": 0.00014310400000000002,
      "loss": 1.1338,
      "step": 890
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.25754594802856445,
      "learning_rate": 0.000142464,
      "loss": 1.148,
      "step": 900
    },
    {
      "epoch": 0.2912,
      "grad_norm": 0.2540118098258972,
      "learning_rate": 0.000141824,
      "loss": 1.0787,
      "step": 910
    },
    {
      "epoch": 0.2944,
      "grad_norm": 0.3876936733722687,
      "learning_rate": 0.000141184,
      "loss": 1.0841,
      "step": 920
    },
    {
      "epoch": 0.2976,
      "grad_norm": 0.27151429653167725,
      "learning_rate": 0.00014054400000000002,
      "loss": 1.0859,
      "step": 930
    },
    {
      "epoch": 0.3008,
      "grad_norm": 0.2533249855041504,
      "learning_rate": 0.00013990400000000002,
      "loss": 1.1347,
      "step": 940
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.2707951068878174,
      "learning_rate": 0.00013926400000000003,
      "loss": 1.1787,
      "step": 950
    },
    {
      "epoch": 0.3072,
      "grad_norm": 0.27499666810035706,
      "learning_rate": 0.000138624,
      "loss": 1.1991,
      "step": 960
    },
    {
      "epoch": 0.3104,
      "grad_norm": 0.31902188062667847,
      "learning_rate": 0.000137984,
      "loss": 1.2036,
      "step": 970
    },
    {
      "epoch": 0.3136,
      "grad_norm": 0.2782028913497925,
      "learning_rate": 0.00013734400000000002,
      "loss": 1.1654,
      "step": 980
    },
    {
      "epoch": 0.3168,
      "grad_norm": 0.3343225419521332,
      "learning_rate": 0.000136704,
      "loss": 1.1677,
      "step": 990
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2642679810523987,
      "learning_rate": 0.000136064,
      "loss": 1.1241,
      "step": 1000
    },
    {
      "epoch": 0.3232,
      "grad_norm": 0.37036266922950745,
      "learning_rate": 0.000135424,
      "loss": 1.1454,
      "step": 1010
    },
    {
      "epoch": 0.3264,
      "grad_norm": 0.2647375464439392,
      "learning_rate": 0.000134784,
      "loss": 1.1288,
      "step": 1020
    },
    {
      "epoch": 0.3296,
      "grad_norm": 0.3140479028224945,
      "learning_rate": 0.000134144,
      "loss": 1.2205,
      "step": 1030
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.24704284965991974,
      "learning_rate": 0.000133504,
      "loss": 1.1341,
      "step": 1040
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.3063775300979614,
      "learning_rate": 0.000132864,
      "loss": 1.2261,
      "step": 1050
    },
    {
      "epoch": 0.3392,
      "grad_norm": 0.2879609167575836,
      "learning_rate": 0.000132224,
      "loss": 1.1676,
      "step": 1060
    },
    {
      "epoch": 0.3424,
      "grad_norm": 0.27018502354621887,
      "learning_rate": 0.000131584,
      "loss": 1.1237,
      "step": 1070
    },
    {
      "epoch": 0.3456,
      "grad_norm": 0.25358906388282776,
      "learning_rate": 0.000130944,
      "loss": 1.1034,
      "step": 1080
    },
    {
      "epoch": 0.3488,
      "grad_norm": 0.26398876309394836,
      "learning_rate": 0.000130304,
      "loss": 1.2041,
      "step": 1090
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.4267687499523163,
      "learning_rate": 0.000129664,
      "loss": 1.15,
      "step": 1100
    },
    {
      "epoch": 0.3552,
      "grad_norm": 0.26307064294815063,
      "learning_rate": 0.00012902400000000002,
      "loss": 1.0921,
      "step": 1110
    },
    {
      "epoch": 0.3584,
      "grad_norm": 0.38714703917503357,
      "learning_rate": 0.00012838400000000002,
      "loss": 1.225,
      "step": 1120
    },
    {
      "epoch": 0.3616,
      "grad_norm": 0.275495320558548,
      "learning_rate": 0.000127744,
      "loss": 1.1513,
      "step": 1130
    },
    {
      "epoch": 0.3648,
      "grad_norm": 0.26792117953300476,
      "learning_rate": 0.000127104,
      "loss": 1.1293,
      "step": 1140
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.2474093735218048,
      "learning_rate": 0.00012646400000000001,
      "loss": 1.175,
      "step": 1150
    },
    {
      "epoch": 0.3712,
      "grad_norm": 0.2551768124103546,
      "learning_rate": 0.00012582400000000002,
      "loss": 1.1212,
      "step": 1160
    },
    {
      "epoch": 0.3744,
      "grad_norm": 0.2605915665626526,
      "learning_rate": 0.000125184,
      "loss": 1.1303,
      "step": 1170
    },
    {
      "epoch": 0.3776,
      "grad_norm": 0.30072781443595886,
      "learning_rate": 0.000124544,
      "loss": 1.1552,
      "step": 1180
    },
    {
      "epoch": 0.3808,
      "grad_norm": 0.2362007051706314,
      "learning_rate": 0.00012390399999999998,
      "loss": 1.1984,
      "step": 1190
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.3113998472690582,
      "learning_rate": 0.000123264,
      "loss": 1.1239,
      "step": 1200
    },
    {
      "epoch": 0.3872,
      "grad_norm": 0.3142775893211365,
      "learning_rate": 0.000122624,
      "loss": 1.1089,
      "step": 1210
    },
    {
      "epoch": 0.3904,
      "grad_norm": 0.38791659474372864,
      "learning_rate": 0.000121984,
      "loss": 1.1532,
      "step": 1220
    },
    {
      "epoch": 0.3936,
      "grad_norm": 0.37536805868148804,
      "learning_rate": 0.00012134400000000001,
      "loss": 1.1333,
      "step": 1230
    },
    {
      "epoch": 0.3968,
      "grad_norm": 0.2762630879878998,
      "learning_rate": 0.00012070399999999999,
      "loss": 1.0189,
      "step": 1240
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.25079619884490967,
      "learning_rate": 0.000120064,
      "loss": 1.1169,
      "step": 1250
    },
    {
      "epoch": 0.4032,
      "grad_norm": 0.2860804498195648,
      "learning_rate": 0.000119424,
      "loss": 1.0866,
      "step": 1260
    },
    {
      "epoch": 0.4064,
      "grad_norm": 0.2980159819126129,
      "learning_rate": 0.000118784,
      "loss": 1.1898,
      "step": 1270
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.336664080619812,
      "learning_rate": 0.00011814400000000001,
      "loss": 1.1332,
      "step": 1280
    },
    {
      "epoch": 0.4128,
      "grad_norm": 0.26283812522888184,
      "learning_rate": 0.00011750400000000002,
      "loss": 1.1367,
      "step": 1290
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.27355343103408813,
      "learning_rate": 0.000116864,
      "loss": 1.0927,
      "step": 1300
    },
    {
      "epoch": 0.4192,
      "grad_norm": 0.2756136953830719,
      "learning_rate": 0.000116224,
      "loss": 1.1109,
      "step": 1310
    },
    {
      "epoch": 0.4224,
      "grad_norm": 0.26861876249313354,
      "learning_rate": 0.00011558400000000001,
      "loss": 1.1401,
      "step": 1320
    },
    {
      "epoch": 0.4256,
      "grad_norm": 0.23718690872192383,
      "learning_rate": 0.000114944,
      "loss": 1.1717,
      "step": 1330
    },
    {
      "epoch": 0.4288,
      "grad_norm": 0.2714873254299164,
      "learning_rate": 0.00011430400000000001,
      "loss": 1.1032,
      "step": 1340
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.29829949140548706,
      "learning_rate": 0.00011366400000000001,
      "loss": 1.1129,
      "step": 1350
    },
    {
      "epoch": 0.4352,
      "grad_norm": 0.2577730417251587,
      "learning_rate": 0.000113024,
      "loss": 1.0978,
      "step": 1360
    },
    {
      "epoch": 0.4384,
      "grad_norm": 0.24967093765735626,
      "learning_rate": 0.000112384,
      "loss": 1.1533,
      "step": 1370
    },
    {
      "epoch": 0.4416,
      "grad_norm": 0.2530049681663513,
      "learning_rate": 0.000111744,
      "loss": 1.0921,
      "step": 1380
    },
    {
      "epoch": 0.4448,
      "grad_norm": 0.30380481481552124,
      "learning_rate": 0.00011110400000000001,
      "loss": 1.1773,
      "step": 1390
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.25974929332733154,
      "learning_rate": 0.00011046400000000002,
      "loss": 1.1584,
      "step": 1400
    },
    {
      "epoch": 0.4512,
      "grad_norm": 0.37404870986938477,
      "learning_rate": 0.00010982400000000001,
      "loss": 1.1199,
      "step": 1410
    },
    {
      "epoch": 0.4544,
      "grad_norm": 0.32186731696128845,
      "learning_rate": 0.000109184,
      "loss": 1.1392,
      "step": 1420
    },
    {
      "epoch": 0.4576,
      "grad_norm": 0.2843293845653534,
      "learning_rate": 0.000108544,
      "loss": 1.1223,
      "step": 1430
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.310863733291626,
      "learning_rate": 0.000107904,
      "loss": 1.1112,
      "step": 1440
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.2348843812942505,
      "learning_rate": 0.00010726400000000001,
      "loss": 1.227,
      "step": 1450
    },
    {
      "epoch": 0.4672,
      "grad_norm": 0.27787262201309204,
      "learning_rate": 0.00010662400000000001,
      "loss": 1.145,
      "step": 1460
    },
    {
      "epoch": 0.4704,
      "grad_norm": 0.26069822907447815,
      "learning_rate": 0.000105984,
      "loss": 1.1417,
      "step": 1470
    },
    {
      "epoch": 0.4736,
      "grad_norm": 0.27364885807037354,
      "learning_rate": 0.000105344,
      "loss": 1.0959,
      "step": 1480
    },
    {
      "epoch": 0.4768,
      "grad_norm": 0.24618731439113617,
      "learning_rate": 0.000104704,
      "loss": 1.1312,
      "step": 1490
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.28439000248908997,
      "learning_rate": 0.00010406400000000001,
      "loss": 1.1506,
      "step": 1500
    },
    {
      "epoch": 0.4832,
      "grad_norm": 0.26154178380966187,
      "learning_rate": 0.000103424,
      "loss": 1.0225,
      "step": 1510
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.26929762959480286,
      "learning_rate": 0.00010278400000000001,
      "loss": 1.061,
      "step": 1520
    },
    {
      "epoch": 0.4896,
      "grad_norm": 0.2753245532512665,
      "learning_rate": 0.00010214399999999999,
      "loss": 1.1724,
      "step": 1530
    },
    {
      "epoch": 0.4928,
      "grad_norm": 0.23799718916416168,
      "learning_rate": 0.000101504,
      "loss": 1.1397,
      "step": 1540
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.277057945728302,
      "learning_rate": 0.000100864,
      "loss": 1.1924,
      "step": 1550
    },
    {
      "epoch": 0.4992,
      "grad_norm": 0.27867016196250916,
      "learning_rate": 0.00010022400000000001,
      "loss": 1.1841,
      "step": 1560
    },
    {
      "epoch": 0.5024,
      "grad_norm": 0.2876740097999573,
      "learning_rate": 9.9584e-05,
      "loss": 1.1085,
      "step": 1570
    },
    {
      "epoch": 0.5056,
      "grad_norm": 0.2694062292575836,
      "learning_rate": 9.8944e-05,
      "loss": 1.0743,
      "step": 1580
    },
    {
      "epoch": 0.5088,
      "grad_norm": 0.27280256152153015,
      "learning_rate": 9.830400000000001e-05,
      "loss": 1.2189,
      "step": 1590
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.3361833393573761,
      "learning_rate": 9.7664e-05,
      "loss": 1.0771,
      "step": 1600
    },
    {
      "epoch": 0.5152,
      "grad_norm": 0.2917429208755493,
      "learning_rate": 9.7024e-05,
      "loss": 1.1137,
      "step": 1610
    },
    {
      "epoch": 0.5184,
      "grad_norm": 0.306228905916214,
      "learning_rate": 9.6384e-05,
      "loss": 1.1708,
      "step": 1620
    },
    {
      "epoch": 0.5216,
      "grad_norm": 0.25011730194091797,
      "learning_rate": 9.5744e-05,
      "loss": 1.1042,
      "step": 1630
    },
    {
      "epoch": 0.5248,
      "grad_norm": 0.3258339464664459,
      "learning_rate": 9.5104e-05,
      "loss": 1.1781,
      "step": 1640
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.3206620216369629,
      "learning_rate": 9.446400000000001e-05,
      "loss": 1.0991,
      "step": 1650
    },
    {
      "epoch": 0.5312,
      "grad_norm": 0.31144049763679504,
      "learning_rate": 9.3824e-05,
      "loss": 1.101,
      "step": 1660
    },
    {
      "epoch": 0.5344,
      "grad_norm": 0.2294250875711441,
      "learning_rate": 9.318400000000001e-05,
      "loss": 1.1346,
      "step": 1670
    },
    {
      "epoch": 0.5376,
      "grad_norm": 0.34881460666656494,
      "learning_rate": 9.254400000000001e-05,
      "loss": 1.1389,
      "step": 1680
    },
    {
      "epoch": 0.5408,
      "grad_norm": 0.27140548825263977,
      "learning_rate": 9.1904e-05,
      "loss": 1.1214,
      "step": 1690
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.25193724036216736,
      "learning_rate": 9.1264e-05,
      "loss": 1.1273,
      "step": 1700
    },
    {
      "epoch": 0.5472,
      "grad_norm": 0.27552053332328796,
      "learning_rate": 9.0624e-05,
      "loss": 1.1523,
      "step": 1710
    },
    {
      "epoch": 0.5504,
      "grad_norm": 0.2877196967601776,
      "learning_rate": 8.9984e-05,
      "loss": 1.082,
      "step": 1720
    },
    {
      "epoch": 0.5536,
      "grad_norm": 0.23511843383312225,
      "learning_rate": 8.9344e-05,
      "loss": 1.1251,
      "step": 1730
    },
    {
      "epoch": 0.5568,
      "grad_norm": 0.28936073184013367,
      "learning_rate": 8.870400000000001e-05,
      "loss": 1.1742,
      "step": 1740
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.28244665265083313,
      "learning_rate": 8.8064e-05,
      "loss": 1.1665,
      "step": 1750
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.22868531942367554,
      "learning_rate": 8.742400000000001e-05,
      "loss": 1.0733,
      "step": 1760
    },
    {
      "epoch": 0.5664,
      "grad_norm": 0.23258651793003082,
      "learning_rate": 8.6784e-05,
      "loss": 1.0538,
      "step": 1770
    },
    {
      "epoch": 0.5696,
      "grad_norm": 0.2886444330215454,
      "learning_rate": 8.614400000000001e-05,
      "loss": 1.0896,
      "step": 1780
    },
    {
      "epoch": 0.5728,
      "grad_norm": 0.26151803135871887,
      "learning_rate": 8.5504e-05,
      "loss": 1.0771,
      "step": 1790
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.2829320430755615,
      "learning_rate": 8.486399999999999e-05,
      "loss": 1.0796,
      "step": 1800
    },
    {
      "epoch": 0.5792,
      "grad_norm": 0.2471112608909607,
      "learning_rate": 8.4224e-05,
      "loss": 1.1751,
      "step": 1810
    },
    {
      "epoch": 0.5824,
      "grad_norm": 0.35704588890075684,
      "learning_rate": 8.3584e-05,
      "loss": 1.1203,
      "step": 1820
    },
    {
      "epoch": 0.5856,
      "grad_norm": 0.3598352074623108,
      "learning_rate": 8.2944e-05,
      "loss": 1.1982,
      "step": 1830
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.24873049557209015,
      "learning_rate": 8.2304e-05,
      "loss": 1.11,
      "step": 1840
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.2786683142185211,
      "learning_rate": 8.166400000000001e-05,
      "loss": 1.1045,
      "step": 1850
    },
    {
      "epoch": 0.5952,
      "grad_norm": 0.31083497405052185,
      "learning_rate": 8.1024e-05,
      "loss": 1.1094,
      "step": 1860
    },
    {
      "epoch": 0.5984,
      "grad_norm": 0.25888901948928833,
      "learning_rate": 8.038400000000001e-05,
      "loss": 1.0637,
      "step": 1870
    },
    {
      "epoch": 0.6016,
      "grad_norm": 0.27845245599746704,
      "learning_rate": 7.9744e-05,
      "loss": 1.1442,
      "step": 1880
    },
    {
      "epoch": 0.6048,
      "grad_norm": 0.32606974244117737,
      "learning_rate": 7.910400000000001e-05,
      "loss": 1.1409,
      "step": 1890
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.28251323103904724,
      "learning_rate": 7.8464e-05,
      "loss": 1.1037,
      "step": 1900
    },
    {
      "epoch": 0.6112,
      "grad_norm": 0.2702641487121582,
      "learning_rate": 7.7824e-05,
      "loss": 1.11,
      "step": 1910
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.31664419174194336,
      "learning_rate": 7.7184e-05,
      "loss": 1.0634,
      "step": 1920
    },
    {
      "epoch": 0.6176,
      "grad_norm": 0.30974429845809937,
      "learning_rate": 7.6544e-05,
      "loss": 1.0884,
      "step": 1930
    },
    {
      "epoch": 0.6208,
      "grad_norm": 0.27011537551879883,
      "learning_rate": 7.590400000000001e-05,
      "loss": 1.0534,
      "step": 1940
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.26978424191474915,
      "learning_rate": 7.5264e-05,
      "loss": 1.1019,
      "step": 1950
    },
    {
      "epoch": 0.6272,
      "grad_norm": 0.29052773118019104,
      "learning_rate": 7.462400000000001e-05,
      "loss": 1.1617,
      "step": 1960
    },
    {
      "epoch": 0.6304,
      "grad_norm": 0.2614887058734894,
      "learning_rate": 7.398400000000002e-05,
      "loss": 1.1562,
      "step": 1970
    },
    {
      "epoch": 0.6336,
      "grad_norm": 0.27294448018074036,
      "learning_rate": 7.334400000000001e-05,
      "loss": 1.1257,
      "step": 1980
    },
    {
      "epoch": 0.6368,
      "grad_norm": 0.24990952014923096,
      "learning_rate": 7.2704e-05,
      "loss": 1.0977,
      "step": 1990
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.272666335105896,
      "learning_rate": 7.206399999999999e-05,
      "loss": 1.0731,
      "step": 2000
    },
    {
      "epoch": 0.6432,
      "grad_norm": 0.28734877705574036,
      "learning_rate": 7.1424e-05,
      "loss": 1.1062,
      "step": 2010
    },
    {
      "epoch": 0.6464,
      "grad_norm": 0.27861565351486206,
      "learning_rate": 7.0784e-05,
      "loss": 1.1435,
      "step": 2020
    },
    {
      "epoch": 0.6496,
      "grad_norm": 0.34537386894226074,
      "learning_rate": 7.0144e-05,
      "loss": 1.1227,
      "step": 2030
    },
    {
      "epoch": 0.6528,
      "grad_norm": 0.3273583650588989,
      "learning_rate": 6.9504e-05,
      "loss": 1.0856,
      "step": 2040
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.3750070631504059,
      "learning_rate": 6.886400000000001e-05,
      "loss": 1.1438,
      "step": 2050
    },
    {
      "epoch": 0.6592,
      "grad_norm": 0.4590343236923218,
      "learning_rate": 6.8224e-05,
      "loss": 1.1532,
      "step": 2060
    },
    {
      "epoch": 0.6624,
      "grad_norm": 0.3549063503742218,
      "learning_rate": 6.758400000000001e-05,
      "loss": 1.1418,
      "step": 2070
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.33026474714279175,
      "learning_rate": 6.6944e-05,
      "loss": 1.0342,
      "step": 2080
    },
    {
      "epoch": 0.6688,
      "grad_norm": 0.37451469898223877,
      "learning_rate": 6.6304e-05,
      "loss": 1.104,
      "step": 2090
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.32349246740341187,
      "learning_rate": 6.5664e-05,
      "loss": 1.1403,
      "step": 2100
    },
    {
      "epoch": 0.6752,
      "grad_norm": 0.3289710581302643,
      "learning_rate": 6.5024e-05,
      "loss": 1.1349,
      "step": 2110
    },
    {
      "epoch": 0.6784,
      "grad_norm": 0.24263447523117065,
      "learning_rate": 6.4384e-05,
      "loss": 1.1162,
      "step": 2120
    },
    {
      "epoch": 0.6816,
      "grad_norm": 0.3055990934371948,
      "learning_rate": 6.3744e-05,
      "loss": 1.0623,
      "step": 2130
    },
    {
      "epoch": 0.6848,
      "grad_norm": 0.26169636845588684,
      "learning_rate": 6.310400000000001e-05,
      "loss": 1.1566,
      "step": 2140
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.2564956545829773,
      "learning_rate": 6.2464e-05,
      "loss": 1.1615,
      "step": 2150
    },
    {
      "epoch": 0.6912,
      "grad_norm": 0.2543143033981323,
      "learning_rate": 6.182400000000001e-05,
      "loss": 1.14,
      "step": 2160
    },
    {
      "epoch": 0.6944,
      "grad_norm": 0.28348684310913086,
      "learning_rate": 6.1184e-05,
      "loss": 1.1192,
      "step": 2170
    },
    {
      "epoch": 0.6976,
      "grad_norm": 0.25627613067626953,
      "learning_rate": 6.0544e-05,
      "loss": 1.1469,
      "step": 2180
    },
    {
      "epoch": 0.7008,
      "grad_norm": 0.39540451765060425,
      "learning_rate": 5.990400000000001e-05,
      "loss": 1.1497,
      "step": 2190
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.2549257278442383,
      "learning_rate": 5.9264e-05,
      "loss": 1.077,
      "step": 2200
    },
    {
      "epoch": 0.7072,
      "grad_norm": 0.2789277136325836,
      "learning_rate": 5.8624e-05,
      "loss": 1.048,
      "step": 2210
    },
    {
      "epoch": 0.7104,
      "grad_norm": 0.28794965147972107,
      "learning_rate": 5.7984000000000006e-05,
      "loss": 1.14,
      "step": 2220
    },
    {
      "epoch": 0.7136,
      "grad_norm": 0.27266013622283936,
      "learning_rate": 5.7344e-05,
      "loss": 1.1882,
      "step": 2230
    },
    {
      "epoch": 0.7168,
      "grad_norm": 0.31794604659080505,
      "learning_rate": 5.6704000000000005e-05,
      "loss": 1.1174,
      "step": 2240
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.26018059253692627,
      "learning_rate": 5.6064000000000004e-05,
      "loss": 1.0834,
      "step": 2250
    },
    {
      "epoch": 0.7232,
      "grad_norm": 0.30461081862449646,
      "learning_rate": 5.5423999999999997e-05,
      "loss": 1.0549,
      "step": 2260
    },
    {
      "epoch": 0.7264,
      "grad_norm": 0.38113224506378174,
      "learning_rate": 5.4784e-05,
      "loss": 1.1426,
      "step": 2270
    },
    {
      "epoch": 0.7296,
      "grad_norm": 0.2623901069164276,
      "learning_rate": 5.414400000000001e-05,
      "loss": 1.066,
      "step": 2280
    },
    {
      "epoch": 0.7328,
      "grad_norm": 0.2910241484642029,
      "learning_rate": 5.3504e-05,
      "loss": 1.0094,
      "step": 2290
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.2720244228839874,
      "learning_rate": 5.2864e-05,
      "loss": 1.1315,
      "step": 2300
    },
    {
      "epoch": 0.7392,
      "grad_norm": 0.25109943747520447,
      "learning_rate": 5.222400000000001e-05,
      "loss": 1.0621,
      "step": 2310
    },
    {
      "epoch": 0.7424,
      "grad_norm": 0.2956967353820801,
      "learning_rate": 5.1584e-05,
      "loss": 1.0889,
      "step": 2320
    },
    {
      "epoch": 0.7456,
      "grad_norm": 0.2685677409172058,
      "learning_rate": 5.0944000000000006e-05,
      "loss": 1.0868,
      "step": 2330
    },
    {
      "epoch": 0.7488,
      "grad_norm": 0.3329203426837921,
      "learning_rate": 5.0304000000000005e-05,
      "loss": 1.1943,
      "step": 2340
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.30616864562034607,
      "learning_rate": 4.9664000000000004e-05,
      "loss": 1.1168,
      "step": 2350
    },
    {
      "epoch": 0.7552,
      "grad_norm": 0.26512446999549866,
      "learning_rate": 4.9024000000000004e-05,
      "loss": 1.1155,
      "step": 2360
    },
    {
      "epoch": 0.7584,
      "grad_norm": 0.3897416591644287,
      "learning_rate": 4.8384e-05,
      "loss": 1.1451,
      "step": 2370
    },
    {
      "epoch": 0.7616,
      "grad_norm": 0.30231884121894836,
      "learning_rate": 4.7744e-05,
      "loss": 1.1502,
      "step": 2380
    },
    {
      "epoch": 0.7648,
      "grad_norm": 0.3417859673500061,
      "learning_rate": 4.7104e-05,
      "loss": 1.1075,
      "step": 2390
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.2546481788158417,
      "learning_rate": 4.6464e-05,
      "loss": 1.1244,
      "step": 2400
    },
    {
      "epoch": 0.7712,
      "grad_norm": 0.2996661067008972,
      "learning_rate": 4.5824e-05,
      "loss": 1.0609,
      "step": 2410
    },
    {
      "epoch": 0.7744,
      "grad_norm": 0.3443852663040161,
      "learning_rate": 4.5184000000000006e-05,
      "loss": 1.0461,
      "step": 2420
    },
    {
      "epoch": 0.7776,
      "grad_norm": 0.4986393451690674,
      "learning_rate": 4.4544e-05,
      "loss": 1.1281,
      "step": 2430
    },
    {
      "epoch": 0.7808,
      "grad_norm": 0.4183667302131653,
      "learning_rate": 4.3904e-05,
      "loss": 1.1396,
      "step": 2440
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.29799389839172363,
      "learning_rate": 4.3264000000000005e-05,
      "loss": 1.1093,
      "step": 2450
    },
    {
      "epoch": 0.7872,
      "grad_norm": 0.28885000944137573,
      "learning_rate": 4.2624000000000004e-05,
      "loss": 1.0716,
      "step": 2460
    },
    {
      "epoch": 0.7904,
      "grad_norm": 0.31649360060691833,
      "learning_rate": 4.1984e-05,
      "loss": 1.096,
      "step": 2470
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.2691904306411743,
      "learning_rate": 4.1344e-05,
      "loss": 1.1591,
      "step": 2480
    },
    {
      "epoch": 0.7968,
      "grad_norm": 0.31309962272644043,
      "learning_rate": 4.0704e-05,
      "loss": 1.1577,
      "step": 2490
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.27012893557548523,
      "learning_rate": 4.0064e-05,
      "loss": 1.1719,
      "step": 2500
    },
    {
      "epoch": 0.8032,
      "grad_norm": 0.4025005102157593,
      "learning_rate": 3.9424e-05,
      "loss": 1.0755,
      "step": 2510
    },
    {
      "epoch": 0.8064,
      "grad_norm": 0.29118382930755615,
      "learning_rate": 3.878400000000001e-05,
      "loss": 1.1296,
      "step": 2520
    },
    {
      "epoch": 0.8096,
      "grad_norm": 0.26896369457244873,
      "learning_rate": 3.8144e-05,
      "loss": 1.1221,
      "step": 2530
    },
    {
      "epoch": 0.8128,
      "grad_norm": 0.3033294677734375,
      "learning_rate": 3.7504e-05,
      "loss": 1.1374,
      "step": 2540
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.3265039026737213,
      "learning_rate": 3.6864000000000005e-05,
      "loss": 1.0935,
      "step": 2550
    },
    {
      "epoch": 0.8192,
      "grad_norm": 0.24130520224571228,
      "learning_rate": 3.6224000000000004e-05,
      "loss": 1.2369,
      "step": 2560
    },
    {
      "epoch": 0.8224,
      "grad_norm": 0.36245155334472656,
      "learning_rate": 3.5584000000000004e-05,
      "loss": 1.0706,
      "step": 2570
    },
    {
      "epoch": 0.8256,
      "grad_norm": 0.2817525267601013,
      "learning_rate": 3.4943999999999996e-05,
      "loss": 1.0652,
      "step": 2580
    },
    {
      "epoch": 0.8288,
      "grad_norm": 0.2730059027671814,
      "learning_rate": 3.4304e-05,
      "loss": 1.067,
      "step": 2590
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.2850629389286041,
      "learning_rate": 3.3664e-05,
      "loss": 1.0898,
      "step": 2600
    },
    {
      "epoch": 0.8352,
      "grad_norm": 0.4017927348613739,
      "learning_rate": 3.3024e-05,
      "loss": 1.1364,
      "step": 2610
    },
    {
      "epoch": 0.8384,
      "grad_norm": 0.36761587858200073,
      "learning_rate": 3.2384e-05,
      "loss": 1.1171,
      "step": 2620
    },
    {
      "epoch": 0.8416,
      "grad_norm": 0.25396281480789185,
      "learning_rate": 3.1744e-05,
      "loss": 1.0557,
      "step": 2630
    },
    {
      "epoch": 0.8448,
      "grad_norm": 0.2851448059082031,
      "learning_rate": 3.1104e-05,
      "loss": 1.0673,
      "step": 2640
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.2541842758655548,
      "learning_rate": 3.0464000000000005e-05,
      "loss": 1.1323,
      "step": 2650
    },
    {
      "epoch": 0.8512,
      "grad_norm": 0.29052332043647766,
      "learning_rate": 2.9824e-05,
      "loss": 1.114,
      "step": 2660
    },
    {
      "epoch": 0.8544,
      "grad_norm": 0.2773646414279938,
      "learning_rate": 2.9184e-05,
      "loss": 1.0973,
      "step": 2670
    },
    {
      "epoch": 0.8576,
      "grad_norm": 0.28323352336883545,
      "learning_rate": 2.8544000000000003e-05,
      "loss": 1.1452,
      "step": 2680
    },
    {
      "epoch": 0.8608,
      "grad_norm": 0.3044739365577698,
      "learning_rate": 2.7904000000000003e-05,
      "loss": 1.0615,
      "step": 2690
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.2924152612686157,
      "learning_rate": 2.7264000000000002e-05,
      "loss": 1.1456,
      "step": 2700
    },
    {
      "epoch": 0.8672,
      "grad_norm": 0.2642782926559448,
      "learning_rate": 2.6623999999999998e-05,
      "loss": 1.1651,
      "step": 2710
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.3707656264305115,
      "learning_rate": 2.5984000000000004e-05,
      "loss": 1.1247,
      "step": 2720
    },
    {
      "epoch": 0.8736,
      "grad_norm": 0.4668145775794983,
      "learning_rate": 2.5344e-05,
      "loss": 1.1537,
      "step": 2730
    },
    {
      "epoch": 0.8768,
      "grad_norm": 0.34861406683921814,
      "learning_rate": 2.4704000000000003e-05,
      "loss": 1.1141,
      "step": 2740
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.2636050283908844,
      "learning_rate": 2.4064000000000002e-05,
      "loss": 1.0715,
      "step": 2750
    },
    {
      "epoch": 0.8832,
      "grad_norm": 0.30254754424095154,
      "learning_rate": 2.3424e-05,
      "loss": 1.108,
      "step": 2760
    },
    {
      "epoch": 0.8864,
      "grad_norm": 0.298784077167511,
      "learning_rate": 2.2784e-05,
      "loss": 1.2063,
      "step": 2770
    },
    {
      "epoch": 0.8896,
      "grad_norm": 0.34004920721054077,
      "learning_rate": 2.2144e-05,
      "loss": 1.1275,
      "step": 2780
    },
    {
      "epoch": 0.8928,
      "grad_norm": 0.33883705735206604,
      "learning_rate": 2.1504000000000003e-05,
      "loss": 1.083,
      "step": 2790
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.30469802021980286,
      "learning_rate": 2.0864e-05,
      "loss": 1.0508,
      "step": 2800
    },
    {
      "epoch": 0.8992,
      "grad_norm": 0.36350762844085693,
      "learning_rate": 2.0224e-05,
      "loss": 1.112,
      "step": 2810
    },
    {
      "epoch": 0.9024,
      "grad_norm": 0.27796122431755066,
      "learning_rate": 1.9584e-05,
      "loss": 1.1022,
      "step": 2820
    },
    {
      "epoch": 0.9056,
      "grad_norm": 0.2932034134864807,
      "learning_rate": 1.8944e-05,
      "loss": 1.0319,
      "step": 2830
    },
    {
      "epoch": 0.9088,
      "grad_norm": 0.394808828830719,
      "learning_rate": 1.8304000000000003e-05,
      "loss": 1.0978,
      "step": 2840
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.34576427936553955,
      "learning_rate": 1.7664e-05,
      "loss": 1.1566,
      "step": 2850
    },
    {
      "epoch": 0.9152,
      "grad_norm": 0.32156696915626526,
      "learning_rate": 1.7024e-05,
      "loss": 1.1663,
      "step": 2860
    },
    {
      "epoch": 0.9184,
      "grad_norm": 0.3129923939704895,
      "learning_rate": 1.6384e-05,
      "loss": 1.0844,
      "step": 2870
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.24763771891593933,
      "learning_rate": 1.5744e-05,
      "loss": 1.12,
      "step": 2880
    },
    {
      "epoch": 0.9248,
      "grad_norm": 0.3140289783477783,
      "learning_rate": 1.5104000000000001e-05,
      "loss": 1.1582,
      "step": 2890
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.2710714340209961,
      "learning_rate": 1.4463999999999999e-05,
      "loss": 1.0895,
      "step": 2900
    },
    {
      "epoch": 0.9312,
      "grad_norm": 0.3298426568508148,
      "learning_rate": 1.3824e-05,
      "loss": 1.0665,
      "step": 2910
    },
    {
      "epoch": 0.9344,
      "grad_norm": 0.24175623059272766,
      "learning_rate": 1.3184000000000001e-05,
      "loss": 1.0966,
      "step": 2920
    },
    {
      "epoch": 0.9376,
      "grad_norm": 0.31446129083633423,
      "learning_rate": 1.2544e-05,
      "loss": 1.0798,
      "step": 2930
    },
    {
      "epoch": 0.9408,
      "grad_norm": 0.32403141260147095,
      "learning_rate": 1.1904000000000002e-05,
      "loss": 1.1143,
      "step": 2940
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.2862265408039093,
      "learning_rate": 1.1264000000000001e-05,
      "loss": 1.0839,
      "step": 2950
    },
    {
      "epoch": 0.9472,
      "grad_norm": 0.4909001588821411,
      "learning_rate": 1.0624e-05,
      "loss": 1.1413,
      "step": 2960
    },
    {
      "epoch": 0.9504,
      "grad_norm": 0.32599207758903503,
      "learning_rate": 9.984e-06,
      "loss": 1.1079,
      "step": 2970
    },
    {
      "epoch": 0.9536,
      "grad_norm": 0.29065415263175964,
      "learning_rate": 9.344e-06,
      "loss": 1.1232,
      "step": 2980
    },
    {
      "epoch": 0.9568,
      "grad_norm": 0.33668118715286255,
      "learning_rate": 8.704000000000002e-06,
      "loss": 1.2002,
      "step": 2990
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2757526636123657,
      "learning_rate": 8.064000000000001e-06,
      "loss": 1.1951,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3125,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.8776953724928e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}