{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9136612021857924,
  "eval_steps": 500,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014571948998178506,
      "grad_norm": 3136.0,
      "learning_rate": 5.531295487627366e-07,
      "loss": 158.3451,
      "step": 20
    },
    {
      "epoch": 0.029143897996357013,
      "grad_norm": 2144.0,
      "learning_rate": 1.1353711790393014e-06,
      "loss": 155.1705,
      "step": 40
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 2496.0,
      "learning_rate": 1.717612809315866e-06,
      "loss": 141.6759,
      "step": 60
    },
    {
      "epoch": 0.058287795992714025,
      "grad_norm": 1936.0,
      "learning_rate": 2.299854439592431e-06,
      "loss": 122.1048,
      "step": 80
    },
    {
      "epoch": 0.07285974499089254,
      "grad_norm": 1000.0,
      "learning_rate": 2.882096069868996e-06,
      "loss": 91.1826,
      "step": 100
    },
    {
      "epoch": 0.08743169398907104,
      "grad_norm": 1072.0,
      "learning_rate": 3.464337700145561e-06,
      "loss": 78.3795,
      "step": 120
    },
    {
      "epoch": 0.10200364298724955,
      "grad_norm": 3520.0,
      "learning_rate": 4.046579330422125e-06,
      "loss": 68.2136,
      "step": 140
    },
    {
      "epoch": 0.11657559198542805,
      "grad_norm": 1080.0,
      "learning_rate": 4.628820960698691e-06,
      "loss": 64.0835,
      "step": 160
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 1440.0,
      "learning_rate": 5.211062590975255e-06,
      "loss": 61.5341,
      "step": 180
    },
    {
      "epoch": 0.14571948998178508,
      "grad_norm": 1432.0,
      "learning_rate": 5.7933042212518195e-06,
      "loss": 58.333,
      "step": 200
    },
    {
      "epoch": 0.16029143897996356,
      "grad_norm": 1760.0,
      "learning_rate": 6.375545851528385e-06,
      "loss": 53.9882,
      "step": 220
    },
    {
      "epoch": 0.17486338797814208,
      "grad_norm": 1976.0,
      "learning_rate": 6.957787481804949e-06,
      "loss": 50.0553,
      "step": 240
    },
    {
      "epoch": 0.1894353369763206,
      "grad_norm": 1576.0,
      "learning_rate": 7.540029112081514e-06,
      "loss": 45.1488,
      "step": 260
    },
    {
      "epoch": 0.2040072859744991,
      "grad_norm": 1456.0,
      "learning_rate": 8.122270742358079e-06,
      "loss": 40.5636,
      "step": 280
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 1328.0,
      "learning_rate": 8.704512372634644e-06,
      "loss": 35.5731,
      "step": 300
    },
    {
      "epoch": 0.2331511839708561,
      "grad_norm": 1336.0,
      "learning_rate": 9.28675400291121e-06,
      "loss": 29.3922,
      "step": 320
    },
    {
      "epoch": 0.24772313296903462,
      "grad_norm": 1184.0,
      "learning_rate": 9.868995633187773e-06,
      "loss": 24.2719,
      "step": 340
    },
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 792.0,
      "learning_rate": 1.0451237263464339e-05,
      "loss": 20.1246,
      "step": 360
    },
    {
      "epoch": 0.2768670309653916,
      "grad_norm": 410.0,
      "learning_rate": 1.1033478893740904e-05,
      "loss": 16.4645,
      "step": 380
    },
    {
      "epoch": 0.29143897996357016,
      "grad_norm": 211.0,
      "learning_rate": 1.1615720524017469e-05,
      "loss": 13.4064,
      "step": 400
    },
    {
      "epoch": 0.30601092896174864,
      "grad_norm": 253.0,
      "learning_rate": 1.2197962154294034e-05,
      "loss": 10.5793,
      "step": 420
    },
    {
      "epoch": 0.3205828779599271,
      "grad_norm": 141.0,
      "learning_rate": 1.2780203784570598e-05,
      "loss": 8.7951,
      "step": 440
    },
    {
      "epoch": 0.33515482695810567,
      "grad_norm": 125.5,
      "learning_rate": 1.3362445414847163e-05,
      "loss": 7.9361,
      "step": 460
    },
    {
      "epoch": 0.34972677595628415,
      "grad_norm": 133.0,
      "learning_rate": 1.3944687045123729e-05,
      "loss": 7.2463,
      "step": 480
    },
    {
      "epoch": 0.36429872495446264,
      "grad_norm": 136.0,
      "learning_rate": 1.452692867540029e-05,
      "loss": 6.3626,
      "step": 500
    },
    {
      "epoch": 0.36429872495446264,
      "eval_loss": 0.32397130131721497,
      "eval_runtime": 99.0019,
      "eval_samples_per_second": 18.111,
      "eval_steps_per_second": 2.273,
      "step": 500
    },
    {
      "epoch": 0.3788706739526412,
      "grad_norm": 109.5,
      "learning_rate": 1.5109170305676858e-05,
      "loss": 6.0476,
      "step": 520
    },
    {
      "epoch": 0.39344262295081966,
      "grad_norm": 97.0,
      "learning_rate": 1.5691411935953423e-05,
      "loss": 5.6971,
      "step": 540
    },
    {
      "epoch": 0.4080145719489982,
      "grad_norm": 112.5,
      "learning_rate": 1.6273653566229986e-05,
      "loss": 5.339,
      "step": 560
    },
    {
      "epoch": 0.4225865209471767,
      "grad_norm": 94.5,
      "learning_rate": 1.685589519650655e-05,
      "loss": 5.0163,
      "step": 580
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 83.0,
      "learning_rate": 1.7438136826783117e-05,
      "loss": 4.8201,
      "step": 600
    },
    {
      "epoch": 0.4517304189435337,
      "grad_norm": 71.5,
      "learning_rate": 1.802037845705968e-05,
      "loss": 4.6324,
      "step": 620
    },
    {
      "epoch": 0.4663023679417122,
      "grad_norm": 83.0,
      "learning_rate": 1.8602620087336244e-05,
      "loss": 4.5086,
      "step": 640
    },
    {
      "epoch": 0.4808743169398907,
      "grad_norm": 82.5,
      "learning_rate": 1.918486171761281e-05,
      "loss": 4.3518,
      "step": 660
    },
    {
      "epoch": 0.49544626593806923,
      "grad_norm": 74.5,
      "learning_rate": 1.9767103347889375e-05,
      "loss": 4.3337,
      "step": 680
    },
    {
      "epoch": 0.5100182149362478,
      "grad_norm": 102.0,
      "learning_rate": 1.999995822880009e-05,
      "loss": 4.1923,
      "step": 700
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 80.5,
      "learning_rate": 1.999970296161993e-05,
      "loss": 4.1708,
      "step": 720
    },
    {
      "epoch": 0.5391621129326047,
      "grad_norm": 91.0,
      "learning_rate": 1.999921563939838e-05,
      "loss": 4.0156,
      "step": 740
    },
    {
      "epoch": 0.5537340619307832,
      "grad_norm": 72.0,
      "learning_rate": 1.9998496273444334e-05,
      "loss": 3.8055,
      "step": 760
    },
    {
      "epoch": 0.5683060109289617,
      "grad_norm": 85.5,
      "learning_rate": 1.999754488045154e-05,
      "loss": 3.6625,
      "step": 780
    },
    {
      "epoch": 0.5828779599271403,
      "grad_norm": 81.5,
      "learning_rate": 1.9996361482498207e-05,
      "loss": 3.755,
      "step": 800
    },
    {
      "epoch": 0.5974499089253188,
      "grad_norm": 63.5,
      "learning_rate": 1.99949461070465e-05,
      "loss": 3.3968,
      "step": 820
    },
    {
      "epoch": 0.6120218579234973,
      "grad_norm": 84.0,
      "learning_rate": 1.9993298786941887e-05,
      "loss": 3.418,
      "step": 840
    },
    {
      "epoch": 0.6265938069216758,
      "grad_norm": 77.0,
      "learning_rate": 1.9991419560412405e-05,
      "loss": 3.4451,
      "step": 860
    },
    {
      "epoch": 0.6411657559198543,
      "grad_norm": 70.0,
      "learning_rate": 1.998930847106774e-05,
      "loss": 3.4411,
      "step": 880
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 72.5,
      "learning_rate": 1.998696556789825e-05,
      "loss": 3.3242,
      "step": 900
    },
    {
      "epoch": 0.6703096539162113,
      "grad_norm": 79.5,
      "learning_rate": 1.9984390905273795e-05,
      "loss": 3.1462,
      "step": 920
    },
    {
      "epoch": 0.6848816029143898,
      "grad_norm": 57.5,
      "learning_rate": 1.998158454294249e-05,
      "loss": 3.0645,
      "step": 940
    },
    {
      "epoch": 0.6994535519125683,
      "grad_norm": 74.5,
      "learning_rate": 1.9978546546029328e-05,
      "loss": 3.1252,
      "step": 960
    },
    {
      "epoch": 0.7140255009107468,
      "grad_norm": 64.0,
      "learning_rate": 1.9975276985034648e-05,
      "loss": 3.1733,
      "step": 980
    },
    {
      "epoch": 0.7285974499089253,
      "grad_norm": 60.75,
      "learning_rate": 1.997177593583252e-05,
      "loss": 3.0225,
      "step": 1000
    },
    {
      "epoch": 0.7285974499089253,
      "eval_loss": 0.15667811036109924,
      "eval_runtime": 65.0211,
      "eval_samples_per_second": 27.576,
      "eval_steps_per_second": 3.46,
      "step": 1000
    },
    {
      "epoch": 0.7431693989071039,
      "grad_norm": 63.0,
      "learning_rate": 1.9968043479668965e-05,
      "loss": 3.0615,
      "step": 1020
    },
    {
      "epoch": 0.7577413479052824,
      "grad_norm": 67.5,
      "learning_rate": 1.996407970316008e-05,
      "loss": 3.035,
      "step": 1040
    },
    {
      "epoch": 0.7723132969034608,
      "grad_norm": 63.25,
      "learning_rate": 1.995988469829004e-05,
      "loss": 3.0076,
      "step": 1060
    },
    {
      "epoch": 0.7868852459016393,
      "grad_norm": 70.0,
      "learning_rate": 1.9955458562408932e-05,
      "loss": 2.9662,
      "step": 1080
    },
    {
      "epoch": 0.8014571948998178,
      "grad_norm": 60.5,
      "learning_rate": 1.9950801398230522e-05,
      "loss": 2.8282,
      "step": 1100
    },
    {
      "epoch": 0.8160291438979964,
      "grad_norm": 63.5,
      "learning_rate": 1.9945913313829865e-05,
      "loss": 2.8459,
      "step": 1120
    },
    {
      "epoch": 0.8306010928961749,
      "grad_norm": 52.5,
      "learning_rate": 1.994079442264079e-05,
      "loss": 2.7764,
      "step": 1140
    },
    {
      "epoch": 0.8451730418943534,
      "grad_norm": 60.25,
      "learning_rate": 1.9935444843453277e-05,
      "loss": 2.8082,
      "step": 1160
    },
    {
      "epoch": 0.8597449908925319,
      "grad_norm": 60.25,
      "learning_rate": 1.99298647004107e-05,
      "loss": 2.7169,
      "step": 1180
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 60.25,
      "learning_rate": 1.992405412300693e-05,
      "loss": 2.7872,
      "step": 1200
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 60.0,
      "learning_rate": 1.991801324608336e-05,
      "loss": 2.7523,
      "step": 1220
    },
    {
      "epoch": 0.9034608378870674,
      "grad_norm": 50.25,
      "learning_rate": 1.9911742209825737e-05,
      "loss": 2.796,
      "step": 1240
    },
    {
      "epoch": 0.9180327868852459,
      "grad_norm": 61.5,
      "learning_rate": 1.9905241159760954e-05,
      "loss": 2.6696,
      "step": 1260
    },
    {
      "epoch": 0.9326047358834244,
      "grad_norm": 57.0,
      "learning_rate": 1.9898510246753627e-05,
      "loss": 2.6553,
      "step": 1280
    },
    {
      "epoch": 0.9471766848816029,
      "grad_norm": 57.5,
      "learning_rate": 1.989154962700263e-05,
      "loss": 2.6849,
      "step": 1300
    },
    {
      "epoch": 0.9617486338797814,
      "grad_norm": 60.75,
      "learning_rate": 1.988435946203745e-05,
      "loss": 2.7262,
      "step": 1320
    },
    {
      "epoch": 0.97632058287796,
      "grad_norm": 68.5,
      "learning_rate": 1.9876939918714445e-05,
      "loss": 2.5417,
      "step": 1340
    },
    {
      "epoch": 0.9908925318761385,
      "grad_norm": 47.5,
      "learning_rate": 1.9869291169212973e-05,
      "loss": 2.4229,
      "step": 1360
    },
    {
      "epoch": 1.0051001821493626,
      "grad_norm": 50.25,
      "learning_rate": 1.98614133910314e-05,
      "loss": 2.2749,
      "step": 1380
    },
    {
      "epoch": 1.019672131147541,
      "grad_norm": 54.5,
      "learning_rate": 1.9853306766982962e-05,
      "loss": 2.2412,
      "step": 1400
    },
    {
      "epoch": 1.0342440801457196,
      "grad_norm": 46.75,
      "learning_rate": 1.984497148519155e-05,
      "loss": 2.2525,
      "step": 1420
    },
    {
      "epoch": 1.048816029143898,
      "grad_norm": 51.0,
      "learning_rate": 1.9836407739087324e-05,
      "loss": 2.2535,
      "step": 1440
    },
    {
      "epoch": 1.0633879781420765,
      "grad_norm": 49.25,
      "learning_rate": 1.9827615727402233e-05,
      "loss": 2.2184,
      "step": 1460
    },
    {
      "epoch": 1.0779599271402551,
      "grad_norm": 51.5,
      "learning_rate": 1.9818595654165402e-05,
      "loss": 2.2432,
      "step": 1480
    },
    {
      "epoch": 1.0925318761384335,
      "grad_norm": 47.5,
      "learning_rate": 1.9809347728698394e-05,
      "loss": 2.1333,
      "step": 1500
    },
    {
      "epoch": 1.0925318761384335,
      "eval_loss": 0.12538094818592072,
      "eval_runtime": 70.4737,
      "eval_samples_per_second": 25.442,
      "eval_steps_per_second": 3.193,
      "step": 1500
    },
    {
      "epoch": 1.107103825136612,
      "grad_norm": 62.5,
      "learning_rate": 1.9799872165610357e-05,
      "loss": 2.0998,
      "step": 1520
    },
    {
      "epoch": 1.1216757741347905,
      "grad_norm": 50.5,
      "learning_rate": 1.9790169184793045e-05,
      "loss": 2.0829,
      "step": 1540
    },
    {
      "epoch": 1.136247723132969,
      "grad_norm": 58.5,
      "learning_rate": 1.9780239011415704e-05,
      "loss": 2.181,
      "step": 1560
    },
    {
      "epoch": 1.1508196721311474,
      "grad_norm": 52.5,
      "learning_rate": 1.9770081875919854e-05,
      "loss": 2.1911,
      "step": 1580
    },
    {
      "epoch": 1.165391621129326,
      "grad_norm": 59.0,
      "learning_rate": 1.975969801401395e-05,
      "loss": 2.0841,
      "step": 1600
    },
    {
      "epoch": 1.1799635701275046,
      "grad_norm": 55.0,
      "learning_rate": 1.9749087666667908e-05,
      "loss": 2.0284,
      "step": 1620
    },
    {
      "epoch": 1.194535519125683,
      "grad_norm": 52.25,
      "learning_rate": 1.973825108010749e-05,
      "loss": 2.1852,
      "step": 1640
    },
    {
      "epoch": 1.2091074681238616,
      "grad_norm": 52.25,
      "learning_rate": 1.9727188505808625e-05,
      "loss": 2.093,
      "step": 1660
    },
    {
      "epoch": 1.22367941712204,
      "grad_norm": 55.25,
      "learning_rate": 1.9715900200491552e-05,
      "loss": 1.9878,
      "step": 1680
    },
    {
      "epoch": 1.2382513661202186,
      "grad_norm": 46.25,
      "learning_rate": 1.9704386426114865e-05,
      "loss": 1.9991,
      "step": 1700
    },
    {
      "epoch": 1.252823315118397,
      "grad_norm": 62.75,
      "learning_rate": 1.9692647449869448e-05,
      "loss": 2.0864,
      "step": 1720
    },
    {
      "epoch": 1.2673952641165755,
      "grad_norm": 52.75,
      "learning_rate": 1.9680683544172244e-05,
      "loss": 2.1087,
      "step": 1740
    },
    {
      "epoch": 1.2819672131147541,
      "grad_norm": 51.75,
      "learning_rate": 1.9668494986659966e-05,
      "loss": 1.9834,
      "step": 1760
    },
    {
      "epoch": 1.2965391621129325,
      "grad_norm": 54.0,
      "learning_rate": 1.9656082060182643e-05,
      "loss": 2.0685,
      "step": 1780
    },
    {
      "epoch": 1.3111111111111111,
      "grad_norm": 52.0,
      "learning_rate": 1.964344505279704e-05,
      "loss": 2.0149,
      "step": 1800
    },
    {
      "epoch": 1.3256830601092897,
      "grad_norm": 47.5,
      "learning_rate": 1.9630584257760004e-05,
      "loss": 1.9994,
      "step": 1820
    },
    {
      "epoch": 1.340255009107468,
      "grad_norm": 58.25,
      "learning_rate": 1.9617499973521625e-05,
      "loss": 2.0543,
      "step": 1840
    },
    {
      "epoch": 1.3548269581056467,
      "grad_norm": 39.0,
      "learning_rate": 1.960419250371834e-05,
      "loss": 2.0198,
      "step": 1860
    },
    {
      "epoch": 1.369398907103825,
      "grad_norm": 53.5,
      "learning_rate": 1.959066215716586e-05,
      "loss": 1.9805,
      "step": 1880
    },
    {
      "epoch": 1.3839708561020037,
      "grad_norm": 48.75,
      "learning_rate": 1.9576909247852035e-05,
      "loss": 2.0276,
      "step": 1900
    },
    {
      "epoch": 1.398542805100182,
      "grad_norm": 49.75,
      "learning_rate": 1.9562934094929532e-05,
      "loss": 1.9901,
      "step": 1920
    },
    {
      "epoch": 1.4131147540983606,
      "grad_norm": 49.0,
      "learning_rate": 1.954873702270845e-05,
      "loss": 2.0076,
      "step": 1940
    },
    {
      "epoch": 1.4276867030965392,
      "grad_norm": 49.5,
      "learning_rate": 1.9534318360648804e-05,
      "loss": 1.8804,
      "step": 1960
    },
    {
      "epoch": 1.4422586520947176,
      "grad_norm": 55.75,
      "learning_rate": 1.951967844335285e-05,
      "loss": 1.9376,
      "step": 1980
    },
    {
      "epoch": 1.4568306010928962,
      "grad_norm": 52.5,
      "learning_rate": 1.950481761055733e-05,
      "loss": 1.9087,
      "step": 2000
    },
    {
      "epoch": 1.4568306010928962,
      "eval_loss": 0.11254730820655823,
      "eval_runtime": 67.3448,
      "eval_samples_per_second": 26.624,
      "eval_steps_per_second": 3.341,
      "step": 2000
    },
    {
      "epoch": 1.4714025500910748,
      "grad_norm": 40.75,
      "learning_rate": 1.9489736207125623e-05,
      "loss": 1.9441,
      "step": 2020
    },
    {
      "epoch": 1.4859744990892532,
      "grad_norm": 44.0,
      "learning_rate": 1.9474434583039687e-05,
      "loss": 1.9067,
      "step": 2040
    },
    {
      "epoch": 1.5005464480874315,
      "grad_norm": 51.0,
      "learning_rate": 1.9458913093391965e-05,
      "loss": 1.9339,
      "step": 2060
    },
    {
      "epoch": 1.5151183970856104,
      "grad_norm": 50.0,
      "learning_rate": 1.9443172098377158e-05,
      "loss": 1.9913,
      "step": 2080
    },
    {
      "epoch": 1.5296903460837887,
      "grad_norm": 40.25,
      "learning_rate": 1.9427211963283838e-05,
      "loss": 1.9971,
      "step": 2100
    },
    {
      "epoch": 1.544262295081967,
      "grad_norm": 61.75,
      "learning_rate": 1.9411033058485983e-05,
      "loss": 1.9614,
      "step": 2120
    },
    {
      "epoch": 1.5588342440801457,
      "grad_norm": 59.75,
      "learning_rate": 1.939463575943439e-05,
      "loss": 1.7754,
      "step": 2140
    },
    {
      "epoch": 1.5734061930783243,
      "grad_norm": 59.25,
      "learning_rate": 1.9378020446647955e-05,
      "loss": 1.9798,
      "step": 2160
    },
    {
      "epoch": 1.5879781420765027,
      "grad_norm": 43.0,
      "learning_rate": 1.936118750570484e-05,
      "loss": 1.9187,
      "step": 2180
    },
    {
      "epoch": 1.6025500910746813,
      "grad_norm": 55.0,
      "learning_rate": 1.9344137327233528e-05,
      "loss": 1.8434,
      "step": 2200
    },
    {
      "epoch": 1.6171220400728599,
      "grad_norm": 51.75,
      "learning_rate": 1.932687030690376e-05,
      "loss": 1.9547,
      "step": 2220
    },
    {
      "epoch": 1.6316939890710382,
      "grad_norm": 41.75,
      "learning_rate": 1.930938684541735e-05,
      "loss": 1.9794,
      "step": 2240
    },
    {
      "epoch": 1.6462659380692166,
      "grad_norm": 51.25,
      "learning_rate": 1.9291687348498887e-05,
      "loss": 1.8965,
      "step": 2260
    },
    {
      "epoch": 1.6608378870673952,
      "grad_norm": 53.0,
      "learning_rate": 1.927377222688632e-05,
      "loss": 1.9359,
      "step": 2280
    },
    {
      "epoch": 1.6754098360655738,
      "grad_norm": 50.75,
      "learning_rate": 1.9255641896321426e-05,
      "loss": 1.8745,
      "step": 2300
    },
    {
      "epoch": 1.6899817850637522,
      "grad_norm": 46.5,
      "learning_rate": 1.9237296777540167e-05,
      "loss": 1.9297,
      "step": 2320
    },
    {
      "epoch": 1.7045537340619308,
      "grad_norm": 43.25,
      "learning_rate": 1.9218737296262917e-05,
      "loss": 1.8551,
      "step": 2340
    },
    {
      "epoch": 1.7191256830601094,
      "grad_norm": 46.5,
      "learning_rate": 1.9199963883184586e-05,
      "loss": 1.9397,
      "step": 2360
    },
    {
      "epoch": 1.7336976320582878,
      "grad_norm": 57.0,
      "learning_rate": 1.918097697396463e-05,
      "loss": 1.8899,
      "step": 2380
    },
    {
      "epoch": 1.7482695810564663,
      "grad_norm": 55.5,
      "learning_rate": 1.9161777009216942e-05,
      "loss": 1.8618,
      "step": 2400
    },
    {
      "epoch": 1.762841530054645,
      "grad_norm": 44.75,
      "learning_rate": 1.9142364434499618e-05,
      "loss": 1.8442,
      "step": 2420
    },
    {
      "epoch": 1.7774134790528233,
      "grad_norm": 55.75,
      "learning_rate": 1.9122739700304614e-05,
      "loss": 1.8146,
      "step": 2440
    },
    {
      "epoch": 1.7919854280510017,
      "grad_norm": 51.75,
      "learning_rate": 1.9102903262047313e-05,
      "loss": 1.7164,
      "step": 2460
    },
    {
      "epoch": 1.8065573770491803,
      "grad_norm": 51.25,
      "learning_rate": 1.9082855580055945e-05,
      "loss": 1.9355,
      "step": 2480
    },
    {
      "epoch": 1.8211293260473589,
      "grad_norm": 45.5,
      "learning_rate": 1.9062597119560887e-05,
      "loss": 1.8544,
      "step": 2500
    },
    {
      "epoch": 1.8211293260473589,
      "eval_loss": 0.10299725830554962,
      "eval_runtime": 74.9026,
      "eval_samples_per_second": 23.938,
      "eval_steps_per_second": 3.004,
      "step": 2500
    },
    {
      "epoch": 1.8357012750455373,
      "grad_norm": 52.0,
      "learning_rate": 1.9042128350683897e-05,
      "loss": 1.8548,
      "step": 2520
    },
    {
      "epoch": 1.8502732240437159,
      "grad_norm": 53.0,
      "learning_rate": 1.9021449748427187e-05,
      "loss": 1.8065,
      "step": 2540
    },
    {
      "epoch": 1.8648451730418945,
      "grad_norm": 45.0,
      "learning_rate": 1.9000561792662396e-05,
      "loss": 1.8204,
      "step": 2560
    },
    {
      "epoch": 1.8794171220400728,
      "grad_norm": 41.5,
      "learning_rate": 1.8979464968119466e-05,
      "loss": 1.7691,
      "step": 2580
    },
    {
      "epoch": 1.8939890710382512,
      "grad_norm": 46.0,
      "learning_rate": 1.89581597643754e-05,
      "loss": 1.717,
      "step": 2600
    },
    {
      "epoch": 1.90856102003643,
      "grad_norm": 54.25,
      "learning_rate": 1.8936646675842862e-05,
      "loss": 1.8515,
      "step": 2620
    },
    {
      "epoch": 1.9231329690346084,
      "grad_norm": 44.75,
      "learning_rate": 1.8914926201758757e-05,
      "loss": 1.7941,
      "step": 2640
    },
    {
      "epoch": 1.9377049180327868,
      "grad_norm": 53.5,
      "learning_rate": 1.8892998846172604e-05,
      "loss": 1.7499,
      "step": 2660
    },
    {
      "epoch": 1.9522768670309654,
      "grad_norm": 49.5,
      "learning_rate": 1.8870865117934857e-05,
      "loss": 1.7328,
      "step": 2680
    },
    {
      "epoch": 1.966848816029144,
      "grad_norm": 51.5,
      "learning_rate": 1.88485255306851e-05,
      "loss": 1.7113,
      "step": 2700
    },
    {
      "epoch": 1.9814207650273223,
      "grad_norm": 56.25,
      "learning_rate": 1.8825980602840116e-05,
      "loss": 1.74,
      "step": 2720
    },
    {
      "epoch": 1.995992714025501,
      "grad_norm": 50.0,
      "learning_rate": 1.8803230857581857e-05,
      "loss": 1.8759,
      "step": 2740
    },
    {
      "epoch": 2.010200364298725,
      "grad_norm": 38.5,
      "learning_rate": 1.8780276822845316e-05,
      "loss": 1.5877,
      "step": 2760
    },
    {
      "epoch": 2.0247723132969035,
      "grad_norm": 46.25,
      "learning_rate": 1.875711903130627e-05,
      "loss": 1.3714,
      "step": 2780
    },
    {
      "epoch": 2.039344262295082,
      "grad_norm": 48.25,
      "learning_rate": 1.8733758020368895e-05,
      "loss": 1.3929,
      "step": 2800
    },
    {
      "epoch": 2.0539162112932603,
      "grad_norm": 43.5,
      "learning_rate": 1.871019433215334e-05,
      "loss": 1.4526,
      "step": 2820
    },
    {
      "epoch": 2.068488160291439,
      "grad_norm": 36.75,
      "learning_rate": 1.8686428513483107e-05,
      "loss": 1.4442,
      "step": 2840
    },
    {
      "epoch": 2.0830601092896175,
      "grad_norm": 50.0,
      "learning_rate": 1.8662461115872386e-05,
      "loss": 1.4693,
      "step": 2860
    },
    {
      "epoch": 2.097632058287796,
      "grad_norm": 41.75,
      "learning_rate": 1.8638292695513243e-05,
      "loss": 1.3698,
      "step": 2880
    },
    {
      "epoch": 2.1122040072859747,
      "grad_norm": 43.25,
      "learning_rate": 1.861392381326271e-05,
      "loss": 1.4342,
      "step": 2900
    },
    {
      "epoch": 2.126775956284153,
      "grad_norm": 42.75,
      "learning_rate": 1.8589355034629792e-05,
      "loss": 1.5037,
      "step": 2920
    },
    {
      "epoch": 2.1413479052823314,
      "grad_norm": 43.75,
      "learning_rate": 1.8564586929762313e-05,
      "loss": 1.4055,
      "step": 2940
    },
    {
      "epoch": 2.1559198542805103,
      "grad_norm": 41.5,
      "learning_rate": 1.85396200734337e-05,
      "loss": 1.4109,
      "step": 2960
    },
    {
      "epoch": 2.1704918032786886,
      "grad_norm": 46.25,
      "learning_rate": 1.8514455045029665e-05,
      "loss": 1.4193,
      "step": 2980
    },
    {
      "epoch": 2.185063752276867,
      "grad_norm": 40.25,
      "learning_rate": 1.8489092428534714e-05,
      "loss": 1.3088,
      "step": 3000
    },
    {
      "epoch": 2.185063752276867,
      "eval_loss": 0.09946708381175995,
      "eval_runtime": 72.3196,
      "eval_samples_per_second": 24.793,
      "eval_steps_per_second": 3.111,
      "step": 3000
    },
    {
      "epoch": 2.1996357012750454,
      "grad_norm": 38.25,
      "learning_rate": 1.8463532812518636e-05,
      "loss": 1.4265,
      "step": 3020
    },
    {
      "epoch": 2.214207650273224,
      "grad_norm": 41.0,
      "learning_rate": 1.843777679012283e-05,
      "loss": 1.4706,
      "step": 3040
    },
    {
      "epoch": 2.2287795992714026,
      "grad_norm": 39.5,
      "learning_rate": 1.841182495904652e-05,
      "loss": 1.4106,
      "step": 3060
    },
    {
      "epoch": 2.243351548269581,
      "grad_norm": 41.5,
      "learning_rate": 1.838567792153293e-05,
      "loss": 1.4444,
      "step": 3080
    },
    {
      "epoch": 2.2579234972677593,
      "grad_norm": 50.0,
      "learning_rate": 1.835933628435527e-05,
      "loss": 1.3515,
      "step": 3100
    },
    {
      "epoch": 2.272495446265938,
      "grad_norm": 49.75,
      "learning_rate": 1.8332800658802665e-05,
      "loss": 1.4409,
      "step": 3120
    },
    {
      "epoch": 2.2870673952641165,
      "grad_norm": 47.5,
      "learning_rate": 1.8306071660665978e-05,
      "loss": 1.4863,
      "step": 3140
    },
    {
      "epoch": 2.301639344262295,
      "grad_norm": 48.5,
      "learning_rate": 1.8279149910223506e-05,
      "loss": 1.401,
      "step": 3160
    },
    {
      "epoch": 2.3162112932604737,
      "grad_norm": 45.0,
      "learning_rate": 1.82520360322266e-05,
      "loss": 1.3694,
      "step": 3180
    },
    {
      "epoch": 2.330783242258652,
      "grad_norm": 46.25,
      "learning_rate": 1.822473065588516e-05,
      "loss": 1.356,
      "step": 3200
    },
    {
      "epoch": 2.3453551912568305,
      "grad_norm": 45.75,
      "learning_rate": 1.819723441485303e-05,
      "loss": 1.4455,
      "step": 3220
    },
    {
      "epoch": 2.3599271402550093,
      "grad_norm": 50.5,
      "learning_rate": 1.81695479472133e-05,
      "loss": 1.3296,
      "step": 3240
    },
    {
      "epoch": 2.3744990892531876,
      "grad_norm": 44.0,
      "learning_rate": 1.814167189546349e-05,
      "loss": 1.368,
      "step": 3260
    },
    {
      "epoch": 2.389071038251366,
      "grad_norm": 49.75,
      "learning_rate": 1.8113606906500652e-05,
      "loss": 1.3675,
      "step": 3280
    },
    {
      "epoch": 2.403642987249545,
      "grad_norm": 53.75,
      "learning_rate": 1.8085353631606356e-05,
      "loss": 1.4088,
      "step": 3300
    },
    {
      "epoch": 2.418214936247723,
      "grad_norm": 49.5,
      "learning_rate": 1.8056912726431552e-05,
      "loss": 1.4397,
      "step": 3320
    },
    {
      "epoch": 2.4327868852459016,
      "grad_norm": 49.5,
      "learning_rate": 1.8028284850981396e-05,
      "loss": 1.4336,
      "step": 3340
    },
    {
      "epoch": 2.44735883424408,
      "grad_norm": 47.75,
      "learning_rate": 1.7999470669599898e-05,
      "loss": 1.4401,
      "step": 3360
    },
    {
      "epoch": 2.461930783242259,
      "grad_norm": 47.5,
      "learning_rate": 1.797047085095453e-05,
      "loss": 1.5122,
      "step": 3380
    },
    {
      "epoch": 2.476502732240437,
      "grad_norm": 47.25,
      "learning_rate": 1.7941286068020695e-05,
      "loss": 1.4507,
      "step": 3400
    },
    {
      "epoch": 2.4910746812386155,
      "grad_norm": 50.0,
      "learning_rate": 1.7911916998066105e-05,
      "loss": 1.3771,
      "step": 3420
    },
    {
      "epoch": 2.505646630236794,
      "grad_norm": 41.75,
      "learning_rate": 1.7882364322635085e-05,
      "loss": 1.4407,
      "step": 3440
    },
    {
      "epoch": 2.5202185792349727,
      "grad_norm": 41.25,
      "learning_rate": 1.785262872753274e-05,
      "loss": 1.4336,
      "step": 3460
    },
    {
      "epoch": 2.534790528233151,
      "grad_norm": 44.25,
      "learning_rate": 1.7822710902809032e-05,
      "loss": 1.4135,
      "step": 3480
    },
    {
      "epoch": 2.5493624772313295,
      "grad_norm": 43.75,
      "learning_rate": 1.7792611542742798e-05,
      "loss": 1.3574,
      "step": 3500
    },
    {
      "epoch": 2.5493624772313295,
      "eval_loss": 0.09350243210792542,
      "eval_runtime": 63.4513,
      "eval_samples_per_second": 28.258,
      "eval_steps_per_second": 3.546,
      "step": 3500
    },
    {
      "epoch": 2.5639344262295083,
      "grad_norm": 47.0,
      "learning_rate": 1.7762331345825608e-05,
      "loss": 1.3841,
      "step": 3520
    },
    {
      "epoch": 2.5785063752276867,
      "grad_norm": 44.25,
      "learning_rate": 1.773187101474557e-05,
      "loss": 1.3778,
      "step": 3540
    },
    {
      "epoch": 2.593078324225865,
      "grad_norm": 36.75,
      "learning_rate": 1.7701231256371016e-05,
      "loss": 1.426,
      "step": 3560
    },
    {
      "epoch": 2.607650273224044,
      "grad_norm": 42.25,
      "learning_rate": 1.7670412781734112e-05,
      "loss": 1.3418,
      "step": 3580
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 41.0,
      "learning_rate": 1.7639416306014338e-05,
      "loss": 1.3827,
      "step": 3600
    },
    {
      "epoch": 2.6367941712204006,
      "grad_norm": 49.0,
      "learning_rate": 1.7608242548521908e-05,
      "loss": 1.3807,
      "step": 3620
    },
    {
      "epoch": 2.6513661202185794,
      "grad_norm": 45.75,
      "learning_rate": 1.7576892232681068e-05,
      "loss": 1.4038,
      "step": 3640
    },
    {
      "epoch": 2.665938069216758,
      "grad_norm": 39.5,
      "learning_rate": 1.7545366086013313e-05,
      "loss": 1.3673,
      "step": 3660
    },
    {
      "epoch": 2.680510018214936,
      "grad_norm": 48.25,
      "learning_rate": 1.75136648401205e-05,
      "loss": 1.4294,
      "step": 3680
    },
    {
      "epoch": 2.695081967213115,
      "grad_norm": 52.25,
      "learning_rate": 1.7481789230667877e-05,
      "loss": 1.4042,
      "step": 3700
    },
    {
      "epoch": 2.7096539162112934,
      "grad_norm": 49.75,
      "learning_rate": 1.7449739997366997e-05,
      "loss": 1.3781,
      "step": 3720
    },
    {
      "epoch": 2.7242258652094717,
      "grad_norm": 44.0,
      "learning_rate": 1.7417517883958576e-05,
      "loss": 1.3645,
      "step": 3740
    },
    {
      "epoch": 2.73879781420765,
      "grad_norm": 45.25,
      "learning_rate": 1.7385123638195206e-05,
      "loss": 1.3784,
      "step": 3760
    },
    {
      "epoch": 2.753369763205829,
      "grad_norm": 45.25,
      "learning_rate": 1.735255801182402e-05,
      "loss": 1.4308,
      "step": 3780
    },
    {
      "epoch": 2.7679417122040073,
      "grad_norm": 53.0,
      "learning_rate": 1.731982176056925e-05,
      "loss": 1.4031,
      "step": 3800
    },
    {
      "epoch": 2.7825136612021857,
      "grad_norm": 48.25,
      "learning_rate": 1.7286915644114668e-05,
      "loss": 1.4014,
      "step": 3820
    },
    {
      "epoch": 2.797085610200364,
      "grad_norm": 39.75,
      "learning_rate": 1.7253840426085982e-05,
      "loss": 1.3615,
      "step": 3840
    },
    {
      "epoch": 2.811657559198543,
      "grad_norm": 48.75,
      "learning_rate": 1.7220596874033096e-05,
      "loss": 1.3646,
      "step": 3860
    },
    {
      "epoch": 2.8262295081967213,
      "grad_norm": 44.5,
      "learning_rate": 1.7187185759412318e-05,
      "loss": 1.3881,
      "step": 3880
    },
    {
      "epoch": 2.8408014571948996,
      "grad_norm": 44.25,
      "learning_rate": 1.715360785756843e-05,
      "loss": 1.2777,
      "step": 3900
    },
    {
      "epoch": 2.8553734061930784,
      "grad_norm": 42.25,
      "learning_rate": 1.7119863947716725e-05,
      "loss": 1.3288,
      "step": 3920
    },
    {
      "epoch": 2.869945355191257,
      "grad_norm": 50.0,
      "learning_rate": 1.7085954812924895e-05,
      "loss": 1.3292,
      "step": 3940
    },
    {
      "epoch": 2.884517304189435,
      "grad_norm": 43.75,
      "learning_rate": 1.7051881240094884e-05,
      "loss": 1.2886,
      "step": 3960
    },
    {
      "epoch": 2.899089253187614,
      "grad_norm": 50.0,
      "learning_rate": 1.7017644019944615e-05,
      "loss": 1.2779,
      "step": 3980
    },
    {
      "epoch": 2.9136612021857924,
      "grad_norm": 37.0,
      "learning_rate": 1.6983243946989646e-05,
      "loss": 1.3498,
      "step": 4000
    },
    {
      "epoch": 2.9136612021857924,
      "eval_loss": 0.09019540995359421,
      "eval_runtime": 60.2297,
      "eval_samples_per_second": 29.769,
      "eval_steps_per_second": 3.736,
      "step": 4000
    }
  ],
  "logging_steps": 20,
  "max_steps": 13730,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 2.01261071184298e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}