{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9142857142857143,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004571428571428572,
      "grad_norm": 10.036954879760742,
      "learning_rate": 6.818181818181818e-06,
      "loss": 1.5061,
      "step": 10
    },
    {
      "epoch": 0.009142857142857144,
      "grad_norm": 6.1826558113098145,
      "learning_rate": 1.4393939393939396e-05,
      "loss": 1.1829,
      "step": 20
    },
    {
      "epoch": 0.013714285714285714,
      "grad_norm": 0.3715404272079468,
      "learning_rate": 2.1969696969696972e-05,
      "loss": 0.8837,
      "step": 30
    },
    {
      "epoch": 0.018285714285714287,
      "grad_norm": 0.3741535246372223,
      "learning_rate": 2.954545454545455e-05,
      "loss": 0.8463,
      "step": 40
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.4058797359466553,
      "learning_rate": 3.712121212121212e-05,
      "loss": 0.8015,
      "step": 50
    },
    {
      "epoch": 0.027428571428571427,
      "grad_norm": 0.42737245559692383,
      "learning_rate": 4.46969696969697e-05,
      "loss": 0.8223,
      "step": 60
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.4415900409221649,
      "learning_rate": 4.999975341832704e-05,
      "loss": 0.8454,
      "step": 70
    },
    {
      "epoch": 0.036571428571428574,
      "grad_norm": 0.4244893789291382,
      "learning_rate": 4.9995369879456624e-05,
      "loss": 0.8802,
      "step": 80
    },
    {
      "epoch": 0.04114285714285714,
      "grad_norm": 0.3938385248184204,
      "learning_rate": 4.99855078537621e-05,
      "loss": 0.8245,
      "step": 90
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.4395196735858917,
      "learning_rate": 4.997016950280291e-05,
      "loss": 0.8391,
      "step": 100
    },
    {
      "epoch": 0.05028571428571429,
      "grad_norm": 0.3913964033126831,
      "learning_rate": 4.994935818843983e-05,
      "loss": 0.8496,
      "step": 110
    },
    {
      "epoch": 0.054857142857142854,
      "grad_norm": 0.3559095859527588,
      "learning_rate": 4.9923078472098126e-05,
      "loss": 0.8749,
      "step": 120
    },
    {
      "epoch": 0.05942857142857143,
      "grad_norm": 0.3371255397796631,
      "learning_rate": 4.989133611376775e-05,
      "loss": 0.8327,
      "step": 130
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.3877238631248474,
      "learning_rate": 4.985413807074092e-05,
      "loss": 0.8574,
      "step": 140
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.3704358637332916,
      "learning_rate": 4.981149249608716e-05,
      "loss": 0.8486,
      "step": 150
    },
    {
      "epoch": 0.07314285714285715,
      "grad_norm": 0.3946303427219391,
      "learning_rate": 4.9763408736866345e-05,
      "loss": 0.8459,
      "step": 160
    },
    {
      "epoch": 0.07771428571428571,
      "grad_norm": 0.41965919733047485,
      "learning_rate": 4.9709897332079994e-05,
      "loss": 0.8634,
      "step": 170
    },
    {
      "epoch": 0.08228571428571428,
      "grad_norm": 0.3696056306362152,
      "learning_rate": 4.965097001036136e-05,
      "loss": 0.828,
      "step": 180
    },
    {
      "epoch": 0.08685714285714285,
      "grad_norm": 0.38095831871032715,
      "learning_rate": 4.958663968740472e-05,
      "loss": 0.8196,
      "step": 190
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.3429420292377472,
      "learning_rate": 4.95169204631345e-05,
      "loss": 0.7923,
      "step": 200
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.33137452602386475,
      "learning_rate": 4.9441827618614906e-05,
      "loss": 0.8226,
      "step": 210
    },
    {
      "epoch": 0.10057142857142858,
      "grad_norm": 0.42856958508491516,
      "learning_rate": 4.936137761270055e-05,
      "loss": 0.863,
      "step": 220
    },
    {
      "epoch": 0.10514285714285715,
      "grad_norm": 0.364279180765152,
      "learning_rate": 4.927558807842908e-05,
      "loss": 0.8453,
      "step": 230
    },
    {
      "epoch": 0.10971428571428571,
      "grad_norm": 0.3308669626712799,
      "learning_rate": 4.9184477819156266e-05,
      "loss": 0.8211,
      "step": 240
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.3423766791820526,
      "learning_rate": 4.9088066804434775e-05,
      "loss": 0.8492,
      "step": 250
    },
    {
      "epoch": 0.11885714285714286,
      "grad_norm": 0.3799251317977905,
      "learning_rate": 4.8986376165637195e-05,
      "loss": 0.865,
      "step": 260
    },
    {
      "epoch": 0.12342857142857143,
      "grad_norm": 0.33849895000457764,
      "learning_rate": 4.887942819132446e-05,
      "loss": 0.8246,
      "step": 270
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.37545016407966614,
      "learning_rate": 4.876724632236067e-05,
      "loss": 0.8398,
      "step": 280
    },
    {
      "epoch": 0.13257142857142856,
      "grad_norm": 0.3809659481048584,
      "learning_rate": 4.864985514677527e-05,
      "loss": 0.7967,
      "step": 290
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.3352556526660919,
      "learning_rate": 4.852728039437391e-05,
      "loss": 0.822,
      "step": 300
    },
    {
      "epoch": 0.1417142857142857,
      "grad_norm": 0.3659832179546356,
      "learning_rate": 4.8399548931098915e-05,
      "loss": 0.7949,
      "step": 310
    },
    {
      "epoch": 0.1462857142857143,
      "grad_norm": 0.38168883323669434,
      "learning_rate": 4.8266688753140873e-05,
      "loss": 0.8771,
      "step": 320
    },
    {
      "epoch": 0.15085714285714286,
      "grad_norm": 0.35578063130378723,
      "learning_rate": 4.812872898080236e-05,
      "loss": 0.8418,
      "step": 330
    },
    {
      "epoch": 0.15542857142857142,
      "grad_norm": 0.33867913484573364,
      "learning_rate": 4.798569985211544e-05,
      "loss": 0.8136,
      "step": 340
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.30473360419273376,
      "learning_rate": 4.7837632716213965e-05,
      "loss": 0.8666,
      "step": 350
    },
    {
      "epoch": 0.16457142857142856,
      "grad_norm": 0.31133362650871277,
      "learning_rate": 4.76845600264626e-05,
      "loss": 0.8196,
      "step": 360
    },
    {
      "epoch": 0.16914285714285715,
      "grad_norm": 0.3315775692462921,
      "learning_rate": 4.75265153333436e-05,
      "loss": 0.834,
      "step": 370
    },
    {
      "epoch": 0.1737142857142857,
      "grad_norm": 0.3724735379219055,
      "learning_rate": 4.736353327710329e-05,
      "loss": 0.8336,
      "step": 380
    },
    {
      "epoch": 0.1782857142857143,
      "grad_norm": 0.39016640186309814,
      "learning_rate": 4.719564958015951e-05,
      "loss": 0.828,
      "step": 390
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.3139747381210327,
      "learning_rate": 4.702290103927207e-05,
      "loss": 0.8224,
      "step": 400
    },
    {
      "epoch": 0.18742857142857142,
      "grad_norm": 0.36381280422210693,
      "learning_rate": 4.6845325517477613e-05,
      "loss": 0.8071,
      "step": 410
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.33313626050949097,
      "learning_rate": 4.666296193579073e-05,
      "loss": 0.84,
      "step": 420
    },
    {
      "epoch": 0.19657142857142856,
      "grad_norm": 0.3412412106990814,
      "learning_rate": 4.647585026467334e-05,
      "loss": 0.8186,
      "step": 430
    },
    {
      "epoch": 0.20114285714285715,
      "grad_norm": 0.3685106039047241,
      "learning_rate": 4.628403151527388e-05,
      "loss": 0.8353,
      "step": 440
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.38284939527511597,
      "learning_rate": 4.608754773043856e-05,
      "loss": 0.8487,
      "step": 450
    },
    {
      "epoch": 0.2102857142857143,
      "grad_norm": 0.3146688938140869,
      "learning_rate": 4.588644197549633e-05,
      "loss": 0.8573,
      "step": 460
    },
    {
      "epoch": 0.21485714285714286,
      "grad_norm": 0.3164137899875641,
      "learning_rate": 4.568075832881987e-05,
      "loss": 0.8577,
      "step": 470
    },
    {
      "epoch": 0.21942857142857142,
      "grad_norm": 0.36855214834213257,
      "learning_rate": 4.547054187216446e-05,
      "loss": 0.8522,
      "step": 480
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.31349271535873413,
      "learning_rate": 4.5255838680786975e-05,
      "loss": 0.8563,
      "step": 490
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.3193899691104889,
      "learning_rate": 4.5036695813347126e-05,
      "loss": 0.8008,
      "step": 500
    },
    {
      "epoch": 0.23314285714285715,
      "grad_norm": 0.3261288106441498,
      "learning_rate": 4.4813161301593094e-05,
      "loss": 0.8493,
      "step": 510
    },
    {
      "epoch": 0.2377142857142857,
      "grad_norm": 0.3024299144744873,
      "learning_rate": 4.458528413983394e-05,
      "loss": 0.8338,
      "step": 520
    },
    {
      "epoch": 0.2422857142857143,
      "grad_norm": 0.35347259044647217,
      "learning_rate": 4.435311427420108e-05,
      "loss": 0.8216,
      "step": 530
    },
    {
      "epoch": 0.24685714285714286,
      "grad_norm": 0.3500995337963104,
      "learning_rate": 4.411670259170101e-05,
      "loss": 0.8171,
      "step": 540
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 0.33161497116088867,
      "learning_rate": 4.3876100909061954e-05,
      "loss": 0.8799,
      "step": 550
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.3572579026222229,
      "learning_rate": 4.363136196137662e-05,
      "loss": 0.8473,
      "step": 560
    },
    {
      "epoch": 0.26057142857142856,
      "grad_norm": 0.34475618600845337,
      "learning_rate": 4.338253939054377e-05,
      "loss": 0.8313,
      "step": 570
    },
    {
      "epoch": 0.2651428571428571,
      "grad_norm": 0.305123507976532,
      "learning_rate": 4.3129687733510935e-05,
      "loss": 0.8183,
      "step": 580
    },
    {
      "epoch": 0.26971428571428574,
      "grad_norm": 0.3515739142894745,
      "learning_rate": 4.287286241032103e-05,
      "loss": 0.8095,
      "step": 590
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.32055890560150146,
      "learning_rate": 4.26121197119654e-05,
      "loss": 0.8445,
      "step": 600
    },
    {
      "epoch": 0.27885714285714286,
      "grad_norm": 0.3288358747959137,
      "learning_rate": 4.234751678804593e-05,
      "loss": 0.8013,
      "step": 610
    },
    {
      "epoch": 0.2834285714285714,
      "grad_norm": 0.3572487235069275,
      "learning_rate": 4.2079111634248966e-05,
      "loss": 0.8555,
      "step": 620
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.3276296555995941,
      "learning_rate": 4.1806963079633884e-05,
      "loss": 0.8134,
      "step": 630
    },
    {
      "epoch": 0.2925714285714286,
      "grad_norm": 0.42274290323257446,
      "learning_rate": 4.153113077373891e-05,
      "loss": 0.8988,
      "step": 640
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 0.30343398451805115,
      "learning_rate": 4.1251675173507084e-05,
      "loss": 0.7984,
      "step": 650
    },
    {
      "epoch": 0.3017142857142857,
      "grad_norm": 0.38233235478401184,
      "learning_rate": 4.0968657530035375e-05,
      "loss": 0.8825,
      "step": 660
    },
    {
      "epoch": 0.3062857142857143,
      "grad_norm": 0.35664182901382446,
      "learning_rate": 4.06821398751496e-05,
      "loss": 0.8257,
      "step": 670
    },
    {
      "epoch": 0.31085714285714283,
      "grad_norm": 0.2929879426956177,
      "learning_rate": 4.039218500780829e-05,
      "loss": 0.8094,
      "step": 680
    },
    {
      "epoch": 0.31542857142857145,
      "grad_norm": 0.35318663716316223,
      "learning_rate": 4.009885648033849e-05,
      "loss": 0.7883,
      "step": 690
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.39150822162628174,
      "learning_rate": 3.980221858450624e-05,
      "loss": 0.8364,
      "step": 700
    },
    {
      "epoch": 0.32457142857142857,
      "grad_norm": 0.3299599289894104,
      "learning_rate": 3.9502336337425185e-05,
      "loss": 0.8357,
      "step": 710
    },
    {
      "epoch": 0.3291428571428571,
      "grad_norm": 0.37028178572654724,
      "learning_rate": 3.919927546730608e-05,
      "loss": 0.8461,
      "step": 720
    },
    {
      "epoch": 0.33371428571428574,
      "grad_norm": 0.40308642387390137,
      "learning_rate": 3.889310239905049e-05,
      "loss": 0.834,
      "step": 730
    },
    {
      "epoch": 0.3382857142857143,
      "grad_norm": 0.3347412049770355,
      "learning_rate": 3.858388423969178e-05,
      "loss": 0.8387,
      "step": 740
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.328976571559906,
      "learning_rate": 3.8271688763686574e-05,
      "loss": 0.8329,
      "step": 750
    },
    {
      "epoch": 0.3474285714285714,
      "grad_norm": 0.36761045455932617,
      "learning_rate": 3.795658439805997e-05,
      "loss": 0.832,
      "step": 760
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.33926573395729065,
      "learning_rate": 3.763864020740766e-05,
      "loss": 0.8186,
      "step": 770
    },
    {
      "epoch": 0.3565714285714286,
      "grad_norm": 0.36478403210639954,
      "learning_rate": 3.7317925878758396e-05,
      "loss": 0.8317,
      "step": 780
    },
    {
      "epoch": 0.36114285714285715,
      "grad_norm": 0.3106362819671631,
      "learning_rate": 3.6994511706299964e-05,
      "loss": 0.8255,
      "step": 790
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.3181576132774353,
      "learning_rate": 3.666846857597207e-05,
      "loss": 0.8656,
      "step": 800
    },
    {
      "epoch": 0.3702857142857143,
      "grad_norm": 0.3051314949989319,
      "learning_rate": 3.63398679499296e-05,
      "loss": 0.8204,
      "step": 810
    },
    {
      "epoch": 0.37485714285714283,
      "grad_norm": 0.34967297315597534,
      "learning_rate": 3.60087818508795e-05,
      "loss": 0.8271,
      "step": 820
    },
    {
      "epoch": 0.37942857142857145,
      "grad_norm": 0.3163996934890747,
      "learning_rate": 3.56752828462949e-05,
      "loss": 0.8543,
      "step": 830
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.35200533270835876,
      "learning_rate": 3.5339444032509656e-05,
      "loss": 0.8201,
      "step": 840
    },
    {
      "epoch": 0.38857142857142857,
      "grad_norm": 0.3649766445159912,
      "learning_rate": 3.5001339018697215e-05,
      "loss": 0.8308,
      "step": 850
    },
    {
      "epoch": 0.3931428571428571,
      "grad_norm": 0.3430212736129761,
      "learning_rate": 3.466104191073687e-05,
      "loss": 0.8223,
      "step": 860
    },
    {
      "epoch": 0.3977142857142857,
      "grad_norm": 0.35261550545692444,
      "learning_rate": 3.431862729497126e-05,
      "loss": 0.8677,
      "step": 870
    },
    {
      "epoch": 0.4022857142857143,
      "grad_norm": 0.3225703835487366,
      "learning_rate": 3.397417022185854e-05,
      "loss": 0.811,
      "step": 880
    },
    {
      "epoch": 0.40685714285714286,
      "grad_norm": 0.30326542258262634,
      "learning_rate": 3.362774618952278e-05,
      "loss": 0.8409,
      "step": 890
    },
    {
      "epoch": 0.4114285714285714,
      "grad_norm": 0.3073750436306,
      "learning_rate": 3.327943112720629e-05,
      "loss": 0.829,
      "step": 900
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.3306390047073364,
      "learning_rate": 3.29293013786275e-05,
      "loss": 0.8273,
      "step": 910
    },
    {
      "epoch": 0.4205714285714286,
      "grad_norm": 0.38851603865623474,
      "learning_rate": 3.257743368524787e-05,
      "loss": 0.8534,
      "step": 920
    },
    {
      "epoch": 0.42514285714285716,
      "grad_norm": 0.32551735639572144,
      "learning_rate": 3.222390516945171e-05,
      "loss": 0.8264,
      "step": 930
    },
    {
      "epoch": 0.4297142857142857,
      "grad_norm": 0.3354673385620117,
      "learning_rate": 3.186879331764251e-05,
      "loss": 0.8441,
      "step": 940
    },
    {
      "epoch": 0.4342857142857143,
      "grad_norm": 0.36562007665634155,
      "learning_rate": 3.151217596325944e-05,
      "loss": 0.8742,
      "step": 950
    },
    {
      "epoch": 0.43885714285714283,
      "grad_norm": 0.3269283175468445,
      "learning_rate": 3.1154131269717834e-05,
      "loss": 0.8578,
      "step": 960
    },
    {
      "epoch": 0.44342857142857145,
      "grad_norm": 0.3420695662498474,
      "learning_rate": 3.079473771327732e-05,
      "loss": 0.8002,
      "step": 970
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.3935994803905487,
      "learning_rate": 3.0434074065841368e-05,
      "loss": 0.851,
      "step": 980
    },
    {
      "epoch": 0.45257142857142857,
      "grad_norm": 0.3524733781814575,
      "learning_rate": 3.0072219377692108e-05,
      "loss": 0.8274,
      "step": 990
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.3497045040130615,
      "learning_rate": 2.970925296016401e-05,
      "loss": 0.8546,
      "step": 1000
    },
    {
      "epoch": 0.4617142857142857,
      "grad_norm": 0.32898032665252686,
      "learning_rate": 2.93452543682605e-05,
      "loss": 0.7847,
      "step": 1010
    },
    {
      "epoch": 0.4662857142857143,
      "grad_norm": 0.33636417984962463,
      "learning_rate": 2.8980303383217024e-05,
      "loss": 0.8663,
      "step": 1020
    },
    {
      "epoch": 0.47085714285714286,
      "grad_norm": 0.3036023676395416,
      "learning_rate": 2.8614479995014642e-05,
      "loss": 0.8327,
      "step": 1030
    },
    {
      "epoch": 0.4754285714285714,
      "grad_norm": 0.34600967168807983,
      "learning_rate": 2.824786438484779e-05,
      "loss": 0.8584,
      "step": 1040
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.3624952435493469,
      "learning_rate": 2.7880536907550148e-05,
      "loss": 0.8527,
      "step": 1050
    },
    {
      "epoch": 0.4845714285714286,
      "grad_norm": 0.3670218884944916,
      "learning_rate": 2.7512578073982515e-05,
      "loss": 0.8517,
      "step": 1060
    },
    {
      "epoch": 0.48914285714285716,
      "grad_norm": 0.39288175106048584,
      "learning_rate": 2.714406853338637e-05,
      "loss": 0.8132,
      "step": 1070
    },
    {
      "epoch": 0.4937142857142857,
      "grad_norm": 0.3547343909740448,
      "learning_rate": 2.67750890557072e-05,
      "loss": 0.8109,
      "step": 1080
    },
    {
      "epoch": 0.4982857142857143,
      "grad_norm": 0.3469362258911133,
      "learning_rate": 2.640572051389134e-05,
      "loss": 0.8649,
      "step": 1090
    },
    {
      "epoch": 0.5028571428571429,
      "grad_norm": 0.34426605701446533,
      "learning_rate": 2.6036043866160236e-05,
      "loss": 0.8512,
      "step": 1100
    },
    {
      "epoch": 0.5074285714285715,
      "grad_norm": 0.4556586444377899,
      "learning_rate": 2.5666140138265997e-05,
      "loss": 0.8436,
      "step": 1110
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.31474241614341736,
      "learning_rate": 2.529609040573217e-05,
      "loss": 0.8416,
      "step": 1120
    },
    {
      "epoch": 0.5165714285714286,
      "grad_norm": 0.319038987159729,
      "learning_rate": 2.4925975776083617e-05,
      "loss": 0.8428,
      "step": 1130
    },
    {
      "epoch": 0.5211428571428571,
      "grad_norm": 0.3263114392757416,
      "learning_rate": 2.4555877371069363e-05,
      "loss": 0.8238,
      "step": 1140
    },
    {
      "epoch": 0.5257142857142857,
      "grad_norm": 0.36383476853370667,
      "learning_rate": 2.418587630888231e-05,
      "loss": 0.84,
      "step": 1150
    },
    {
      "epoch": 0.5302857142857142,
      "grad_norm": 0.3406716287136078,
      "learning_rate": 2.3816053686379747e-05,
      "loss": 0.8313,
      "step": 1160
    },
    {
      "epoch": 0.5348571428571428,
      "grad_norm": 0.4595310389995575,
      "learning_rate": 2.344649056130854e-05,
      "loss": 0.8675,
      "step": 1170
    },
    {
      "epoch": 0.5394285714285715,
      "grad_norm": 0.2908764183521271,
      "learning_rate": 2.3077267934538898e-05,
      "loss": 0.8477,
      "step": 1180
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.32547152042388916,
      "learning_rate": 2.2708466732310593e-05,
      "loss": 0.7898,
      "step": 1190
    },
    {
      "epoch": 0.5485714285714286,
      "grad_norm": 0.3099737763404846,
      "learning_rate": 2.2340167788495533e-05,
      "loss": 0.8219,
      "step": 1200
    },
    {
      "epoch": 0.5531428571428572,
      "grad_norm": 0.3248344361782074,
      "learning_rate": 2.1972451826880593e-05,
      "loss": 0.8419,
      "step": 1210
    },
    {
      "epoch": 0.5577142857142857,
      "grad_norm": 0.36769309639930725,
      "learning_rate": 2.1605399443474554e-05,
      "loss": 0.8297,
      "step": 1220
    },
    {
      "epoch": 0.5622857142857143,
      "grad_norm": 0.32329463958740234,
      "learning_rate": 2.1239091088843124e-05,
      "loss": 0.812,
      "step": 1230
    },
    {
      "epoch": 0.5668571428571428,
      "grad_norm": 0.3232475817203522,
      "learning_rate": 2.0873607050475695e-05,
      "loss": 0.7991,
      "step": 1240
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.3522675931453705,
      "learning_rate": 2.0509027435187988e-05,
      "loss": 0.8575,
      "step": 1250
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.3529416620731354,
      "learning_rate": 2.0145432151564202e-05,
      "loss": 0.8143,
      "step": 1260
    },
    {
      "epoch": 0.5805714285714285,
      "grad_norm": 0.3080810010433197,
      "learning_rate": 1.978290089244265e-05,
      "loss": 0.8417,
      "step": 1270
    },
    {
      "epoch": 0.5851428571428572,
      "grad_norm": 0.3429129421710968,
      "learning_rate": 1.9421513117448714e-05,
      "loss": 0.8387,
      "step": 1280
    },
    {
      "epoch": 0.5897142857142857,
      "grad_norm": 0.3251505494117737,
      "learning_rate": 1.9061348035578824e-05,
      "loss": 0.8164,
      "step": 1290
    },
    {
      "epoch": 0.5942857142857143,
      "grad_norm": 0.3315959870815277,
      "learning_rate": 1.870248458783945e-05,
      "loss": 0.8222,
      "step": 1300
    },
    {
      "epoch": 0.5988571428571429,
      "grad_norm": 0.2929075360298157,
      "learning_rate": 1.834500142994482e-05,
      "loss": 0.8302,
      "step": 1310
    },
    {
      "epoch": 0.6034285714285714,
      "grad_norm": 0.30258625745773315,
      "learning_rate": 1.7988976915077124e-05,
      "loss": 0.8081,
      "step": 1320
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.37455984950065613,
      "learning_rate": 1.7634489076713103e-05,
      "loss": 0.8321,
      "step": 1330
    },
    {
      "epoch": 0.6125714285714285,
      "grad_norm": 0.33142438530921936,
      "learning_rate": 1.728161561152062e-05,
      "loss": 0.8279,
      "step": 1340
    },
    {
      "epoch": 0.6171428571428571,
      "grad_norm": 0.3345928490161896,
      "learning_rate": 1.6930433862329126e-05,
      "loss": 0.8469,
      "step": 1350
    },
    {
      "epoch": 0.6217142857142857,
      "grad_norm": 0.28738102316856384,
      "learning_rate": 1.6581020801177637e-05,
      "loss": 0.8052,
      "step": 1360
    },
    {
      "epoch": 0.6262857142857143,
      "grad_norm": 0.34191104769706726,
      "learning_rate": 1.6233453012444037e-05,
      "loss": 0.8498,
      "step": 1370
    },
    {
      "epoch": 0.6308571428571429,
      "grad_norm": 0.364449679851532,
      "learning_rate": 1.5887806676059242e-05,
      "loss": 0.8027,
      "step": 1380
    },
    {
      "epoch": 0.6354285714285715,
      "grad_norm": 0.3165501356124878,
      "learning_rate": 1.554415755081014e-05,
      "loss": 0.8055,
      "step": 1390
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.340798944234848,
      "learning_rate": 1.520258095773474e-05,
      "loss": 0.8566,
      "step": 1400
    },
    {
      "epoch": 0.6445714285714286,
      "grad_norm": 0.33021771907806396,
      "learning_rate": 1.4863151763613307e-05,
      "loss": 0.8187,
      "step": 1410
    },
    {
      "epoch": 0.6491428571428571,
      "grad_norm": 0.3249121606349945,
      "learning_rate": 1.4525944364559077e-05,
      "loss": 0.842,
      "step": 1420
    },
    {
      "epoch": 0.6537142857142857,
      "grad_norm": 0.3549264073371887,
      "learning_rate": 1.4191032669712095e-05,
      "loss": 0.8759,
      "step": 1430
    },
    {
      "epoch": 0.6582857142857143,
      "grad_norm": 0.3233896791934967,
      "learning_rate": 1.3858490085039782e-05,
      "loss": 0.8187,
      "step": 1440
    },
    {
      "epoch": 0.6628571428571428,
      "grad_norm": 0.32915738224983215,
      "learning_rate": 1.3528389497247857e-05,
      "loss": 0.869,
      "step": 1450
    },
    {
      "epoch": 0.6674285714285715,
      "grad_norm": 0.290789932012558,
      "learning_rate": 1.3200803257804997e-05,
      "loss": 0.8325,
      "step": 1460
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.33994024991989136,
      "learning_rate": 1.2875803167084838e-05,
      "loss": 0.7927,
      "step": 1470
    },
    {
      "epoch": 0.6765714285714286,
      "grad_norm": 0.3167119324207306,
      "learning_rate": 1.2553460458628778e-05,
      "loss": 0.8434,
      "step": 1480
    },
    {
      "epoch": 0.6811428571428572,
      "grad_norm": 0.31095385551452637,
      "learning_rate": 1.2233845783532965e-05,
      "loss": 0.8266,
      "step": 1490
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3284270763397217,
      "learning_rate": 1.1917029194963048e-05,
      "loss": 0.8434,
      "step": 1500
    },
    {
      "epoch": 0.6902857142857143,
      "grad_norm": 0.39227378368377686,
      "learning_rate": 1.1603080132799873e-05,
      "loss": 0.8985,
      "step": 1510
    },
    {
      "epoch": 0.6948571428571428,
      "grad_norm": 0.3767732083797455,
      "learning_rate": 1.129206740841966e-05,
      "loss": 0.8709,
      "step": 1520
    },
    {
      "epoch": 0.6994285714285714,
      "grad_norm": 0.3173609673976898,
      "learning_rate": 1.0984059189611923e-05,
      "loss": 0.8151,
      "step": 1530
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.34913018345832825,
      "learning_rate": 1.0679122985638426e-05,
      "loss": 0.7922,
      "step": 1540
    },
    {
      "epoch": 0.7085714285714285,
      "grad_norm": 0.37159714102745056,
      "learning_rate": 1.0377325632436542e-05,
      "loss": 0.858,
      "step": 1550
    },
    {
      "epoch": 0.7131428571428572,
      "grad_norm": 0.3760693669319153,
      "learning_rate": 1.0078733277970115e-05,
      "loss": 0.8595,
      "step": 1560
    },
    {
      "epoch": 0.7177142857142857,
      "grad_norm": 0.34884318709373474,
      "learning_rate": 9.783411367731155e-06,
      "loss": 0.8508,
      "step": 1570
    },
    {
      "epoch": 0.7222857142857143,
      "grad_norm": 0.29239240288734436,
      "learning_rate": 9.491424630395498e-06,
      "loss": 0.8322,
      "step": 1580
    },
    {
      "epoch": 0.7268571428571429,
      "grad_norm": 0.3242127597332001,
      "learning_rate": 9.20283706363554e-06,
      "loss": 0.8462,
      "step": 1590
    },
    {
      "epoch": 0.7314285714285714,
      "grad_norm": 0.2664639353752136,
      "learning_rate": 8.91771192009326e-06,
      "loss": 0.828,
      "step": 1600
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.3225860893726349,
      "learning_rate": 8.636111693516491e-06,
      "loss": 0.8505,
      "step": 1610
    },
    {
      "epoch": 0.7405714285714285,
      "grad_norm": 0.3004557192325592,
      "learning_rate": 8.35809810506153e-06,
      "loss": 0.8373,
      "step": 1620
    },
    {
      "epoch": 0.7451428571428571,
      "grad_norm": 0.3271797001361847,
      "learning_rate": 8.083732089765092e-06,
      "loss": 0.8349,
      "step": 1630
    },
    {
      "epoch": 0.7497142857142857,
      "grad_norm": 0.3424467444419861,
      "learning_rate": 7.813073783188546e-06,
      "loss": 0.8769,
      "step": 1640
    },
    {
      "epoch": 0.7542857142857143,
      "grad_norm": 0.3310692310333252,
      "learning_rate": 7.546182508237468e-06,
      "loss": 0.8448,
      "step": 1650
    },
    {
      "epoch": 0.7588571428571429,
      "grad_norm": 0.33352503180503845,
      "learning_rate": 7.283116762159134e-06,
      "loss": 0.8573,
      "step": 1660
    },
    {
      "epoch": 0.7634285714285715,
      "grad_norm": 0.29162561893463135,
      "learning_rate": 7.023934203721189e-06,
      "loss": 0.8409,
      "step": 1670
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.303484171628952,
      "learning_rate": 6.768691640573943e-06,
      "loss": 0.8078,
      "step": 1680
    },
    {
      "epoch": 0.7725714285714286,
      "grad_norm": 0.3278193771839142,
      "learning_rate": 6.5174450167992614e-06,
      "loss": 0.8349,
      "step": 1690
    },
    {
      "epoch": 0.7771428571428571,
      "grad_norm": 0.3420460820198059,
      "learning_rate": 6.270249400648792e-06,
      "loss": 0.8236,
      "step": 1700
    },
    {
      "epoch": 0.7817142857142857,
      "grad_norm": 0.32346224784851074,
      "learning_rate": 6.02715897247402e-06,
      "loss": 0.8102,
      "step": 1710
    },
    {
      "epoch": 0.7862857142857143,
      "grad_norm": 0.321027547121048,
      "learning_rate": 5.788227012851083e-06,
      "loss": 0.8232,
      "step": 1720
    },
    {
      "epoch": 0.7908571428571428,
      "grad_norm": 0.28921619057655334,
      "learning_rate": 5.55350589090271e-06,
      "loss": 0.8275,
      "step": 1730
    },
    {
      "epoch": 0.7954285714285714,
      "grad_norm": 0.32297149300575256,
      "learning_rate": 5.323047052819918e-06,
      "loss": 0.8521,
      "step": 1740
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3070310652256012,
      "learning_rate": 5.096901010586119e-06,
      "loss": 0.8477,
      "step": 1750
    },
    {
      "epoch": 0.8045714285714286,
      "grad_norm": 0.2875780463218689,
      "learning_rate": 4.87511733090579e-06,
      "loss": 0.7977,
      "step": 1760
    },
    {
      "epoch": 0.8091428571428572,
      "grad_norm": 0.3313544988632202,
      "learning_rate": 4.657744624340524e-06,
      "loss": 0.8024,
      "step": 1770
    },
    {
      "epoch": 0.8137142857142857,
      "grad_norm": 0.34528982639312744,
      "learning_rate": 4.444830534654535e-06,
      "loss": 0.8444,
      "step": 1780
    },
    {
      "epoch": 0.8182857142857143,
      "grad_norm": 0.3218827247619629,
      "learning_rate": 4.236421728372081e-06,
      "loss": 0.8681,
      "step": 1790
    },
    {
      "epoch": 0.8228571428571428,
      "grad_norm": 0.3953852653503418,
      "learning_rate": 4.0325638845491255e-06,
      "loss": 0.8282,
      "step": 1800
    },
    {
      "epoch": 0.8274285714285714,
      "grad_norm": 0.3236478269100189,
      "learning_rate": 3.833301684761356e-06,
      "loss": 0.8393,
      "step": 1810
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.5141963362693787,
      "learning_rate": 3.638678803310905e-06,
      "loss": 0.8512,
      "step": 1820
    },
    {
      "epoch": 0.8365714285714285,
      "grad_norm": 0.30036330223083496,
      "learning_rate": 3.4487378976538144e-06,
      "loss": 0.8524,
      "step": 1830
    },
    {
      "epoch": 0.8411428571428572,
      "grad_norm": 0.29903078079223633,
      "learning_rate": 3.2635205990503515e-06,
      "loss": 0.8138,
      "step": 1840
    },
    {
      "epoch": 0.8457142857142858,
      "grad_norm": 0.3183756172657013,
      "learning_rate": 3.0830675034402874e-06,
      "loss": 0.8046,
      "step": 1850
    },
    {
      "epoch": 0.8502857142857143,
      "grad_norm": 0.32868391275405884,
      "learning_rate": 2.907418162545045e-06,
      "loss": 0.8175,
      "step": 1860
    },
    {
      "epoch": 0.8548571428571429,
      "grad_norm": 0.30841535329818726,
      "learning_rate": 2.7366110751987887e-06,
      "loss": 0.862,
      "step": 1870
    },
    {
      "epoch": 0.8594285714285714,
      "grad_norm": 0.28565824031829834,
      "learning_rate": 2.5706836789102297e-06,
      "loss": 0.8354,
      "step": 1880
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.37796252965927124,
      "learning_rate": 2.40967234165706e-06,
      "loss": 0.868,
      "step": 1890
    },
    {
      "epoch": 0.8685714285714285,
      "grad_norm": 0.3173869550228119,
      "learning_rate": 2.253612353914844e-06,
      "loss": 0.7954,
      "step": 1900
    },
    {
      "epoch": 0.8731428571428571,
      "grad_norm": 0.29563650488853455,
      "learning_rate": 2.102537920922007e-06,
      "loss": 0.8041,
      "step": 1910
    },
    {
      "epoch": 0.8777142857142857,
      "grad_norm": 0.2928835153579712,
      "learning_rate": 1.956482155182776e-06,
      "loss": 0.8362,
      "step": 1920
    },
    {
      "epoch": 0.8822857142857143,
      "grad_norm": 0.3378143906593323,
      "learning_rate": 1.8154770692095508e-06,
      "loss": 0.8311,
      "step": 1930
    },
    {
      "epoch": 0.8868571428571429,
      "grad_norm": 0.3135128319263458,
      "learning_rate": 1.6795535685064034e-06,
      "loss": 0.819,
      "step": 1940
    },
    {
      "epoch": 0.8914285714285715,
      "grad_norm": 0.33601969480514526,
      "learning_rate": 1.5487414447952181e-06,
      "loss": 0.8293,
      "step": 1950
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.3282657861709595,
      "learning_rate": 1.423069369485913e-06,
      "loss": 0.8132,
      "step": 1960
    },
    {
      "epoch": 0.9005714285714286,
      "grad_norm": 0.40262722969055176,
      "learning_rate": 1.3025648873922796e-06,
      "loss": 0.8189,
      "step": 1970
    },
    {
      "epoch": 0.9051428571428571,
      "grad_norm": 0.3330300450325012,
      "learning_rate": 1.1872544106946742e-06,
      "loss": 0.846,
      "step": 1980
    },
    {
      "epoch": 0.9097142857142857,
      "grad_norm": 0.3627796471118927,
      "learning_rate": 1.0771632131510085e-06,
      "loss": 0.8222,
      "step": 1990
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.33185991644859314,
      "learning_rate": 9.723154245572518e-07,
      "loss": 0.8282,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2188,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4027746692777984e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}