{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999569151227919,
  "eval_steps": 500,
  "global_step": 1305,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007659533725884436,
      "grad_norm": 4.585542476127782,
      "learning_rate": 6.870229007633589e-06,
      "loss": 1.5342,
      "step": 10
    },
    {
      "epoch": 0.015319067451768873,
      "grad_norm": 1.9168528825341193,
      "learning_rate": 1.450381679389313e-05,
      "loss": 0.8087,
      "step": 20
    },
    {
      "epoch": 0.02297860117765331,
      "grad_norm": 1.7494595444106944,
      "learning_rate": 2.2137404580152673e-05,
      "loss": 0.6624,
      "step": 30
    },
    {
      "epoch": 0.030638134903537746,
      "grad_norm": 2.2498997742937363,
      "learning_rate": 2.9770992366412214e-05,
      "loss": 0.6558,
      "step": 40
    },
    {
      "epoch": 0.03829766862942218,
      "grad_norm": 1.8180680448843922,
      "learning_rate": 3.7404580152671756e-05,
      "loss": 0.6096,
      "step": 50
    },
    {
      "epoch": 0.04595720235530662,
      "grad_norm": 1.6228088755931114,
      "learning_rate": 4.5038167938931294e-05,
      "loss": 0.6418,
      "step": 60
    },
    {
      "epoch": 0.05361673608119106,
      "grad_norm": 1.8008545319562819,
      "learning_rate": 5.267175572519084e-05,
      "loss": 0.6372,
      "step": 70
    },
    {
      "epoch": 0.06127626980707549,
      "grad_norm": 1.3828949316057764,
      "learning_rate": 6.0305343511450384e-05,
      "loss": 0.6454,
      "step": 80
    },
    {
      "epoch": 0.06893580353295993,
      "grad_norm": 1.5447120083529549,
      "learning_rate": 6.793893129770993e-05,
      "loss": 0.636,
      "step": 90
    },
    {
      "epoch": 0.07659533725884436,
      "grad_norm": 4.189206237497925,
      "learning_rate": 7.557251908396947e-05,
      "loss": 0.6307,
      "step": 100
    },
    {
      "epoch": 0.08425487098472881,
      "grad_norm": 1.4113919986461227,
      "learning_rate": 8.320610687022902e-05,
      "loss": 0.683,
      "step": 110
    },
    {
      "epoch": 0.09191440471061324,
      "grad_norm": 1.2966834984162288,
      "learning_rate": 9.083969465648856e-05,
      "loss": 0.6656,
      "step": 120
    },
    {
      "epoch": 0.09957393843649767,
      "grad_norm": 1.2562948634106306,
      "learning_rate": 9.84732824427481e-05,
      "loss": 0.6729,
      "step": 130
    },
    {
      "epoch": 0.10723347216238212,
      "grad_norm": 1.1134314373972036,
      "learning_rate": 9.998854310460233e-05,
      "loss": 0.6685,
      "step": 140
    },
    {
      "epoch": 0.11489300588826655,
      "grad_norm": 1.1853742832665686,
      "learning_rate": 9.994200846542251e-05,
      "loss": 0.6699,
      "step": 150
    },
    {
      "epoch": 0.12255253961415098,
      "grad_norm": 1.2950541750596993,
      "learning_rate": 9.985971332154984e-05,
      "loss": 0.6848,
      "step": 160
    },
    {
      "epoch": 0.13021207334003543,
      "grad_norm": 1.1203368484907543,
      "learning_rate": 9.974171659964687e-05,
      "loss": 0.7005,
      "step": 170
    },
    {
      "epoch": 0.13787160706591986,
      "grad_norm": 1.3142045395841067,
      "learning_rate": 9.958810279015473e-05,
      "loss": 0.6757,
      "step": 180
    },
    {
      "epoch": 0.1455311407918043,
      "grad_norm": 1.019650080366063,
      "learning_rate": 9.939898188679464e-05,
      "loss": 0.6678,
      "step": 190
    },
    {
      "epoch": 0.15319067451768872,
      "grad_norm": 0.9168855949375643,
      "learning_rate": 9.917448930780786e-05,
      "loss": 0.6781,
      "step": 200
    },
    {
      "epoch": 0.16085020824357318,
      "grad_norm": 1.0530592108443477,
      "learning_rate": 9.891478579899079e-05,
      "loss": 0.6841,
      "step": 210
    },
    {
      "epoch": 0.16850974196945762,
      "grad_norm": 1.0143214926764803,
      "learning_rate": 9.862005731859442e-05,
      "loss": 0.6841,
      "step": 220
    },
    {
      "epoch": 0.17616927569534205,
      "grad_norm": 1.03752898969354,
      "learning_rate": 9.829051490417073e-05,
      "loss": 0.6667,
      "step": 230
    },
    {
      "epoch": 0.18382880942122648,
      "grad_norm": 1.191347331860848,
      "learning_rate": 9.792639452146115e-05,
      "loss": 0.668,
      "step": 240
    },
    {
      "epoch": 0.1914883431471109,
      "grad_norm": 1.0429696856251238,
      "learning_rate": 9.752795689543564e-05,
      "loss": 0.6808,
      "step": 250
    },
    {
      "epoch": 0.19914787687299534,
      "grad_norm": 0.9451116935903828,
      "learning_rate": 9.709548732360285e-05,
      "loss": 0.6701,
      "step": 260
    },
    {
      "epoch": 0.2068074105988798,
      "grad_norm": 1.0069521463660143,
      "learning_rate": 9.662929547172574e-05,
      "loss": 0.6764,
      "step": 270
    },
    {
      "epoch": 0.21446694432476424,
      "grad_norm": 1.013713779413254,
      "learning_rate": 9.61297151520882e-05,
      "loss": 0.6653,
      "step": 280
    },
    {
      "epoch": 0.22212647805064867,
      "grad_norm": 0.8428712955576788,
      "learning_rate": 9.559710408447185e-05,
      "loss": 0.6706,
      "step": 290
    },
    {
      "epoch": 0.2297860117765331,
      "grad_norm": 0.9679286842839989,
      "learning_rate": 9.503184364001431e-05,
      "loss": 0.6506,
      "step": 300
    },
    {
      "epoch": 0.23744554550241753,
      "grad_norm": 0.8636277650595472,
      "learning_rate": 9.443433856813197e-05,
      "loss": 0.6654,
      "step": 310
    },
    {
      "epoch": 0.24510507922830196,
      "grad_norm": 0.9085064112194627,
      "learning_rate": 9.38050167067028e-05,
      "loss": 0.6489,
      "step": 320
    },
    {
      "epoch": 0.2527646129541864,
      "grad_norm": 0.945404545784054,
      "learning_rate": 9.314432867571731e-05,
      "loss": 0.6762,
      "step": 330
    },
    {
      "epoch": 0.26042414668007086,
      "grad_norm": 0.8345456114257215,
      "learning_rate": 9.24527475546162e-05,
      "loss": 0.6519,
      "step": 340
    },
    {
      "epoch": 0.26808368040595526,
      "grad_norm": 1.0600761168334611,
      "learning_rate": 9.173076854354634e-05,
      "loss": 0.6596,
      "step": 350
    },
    {
      "epoch": 0.2757432141318397,
      "grad_norm": 0.8045120836973815,
      "learning_rate": 9.097890860877732e-05,
      "loss": 0.6304,
      "step": 360
    },
    {
      "epoch": 0.2834027478577242,
      "grad_norm": 0.883297712718,
      "learning_rate": 9.01977061125327e-05,
      "loss": 0.6487,
      "step": 370
    },
    {
      "epoch": 0.2910622815836086,
      "grad_norm": 1.1118932234729717,
      "learning_rate": 8.938772042750078e-05,
      "loss": 0.6551,
      "step": 380
    },
    {
      "epoch": 0.29872181530949304,
      "grad_norm": 0.8947188935196859,
      "learning_rate": 8.854953153630097e-05,
      "loss": 0.6434,
      "step": 390
    },
    {
      "epoch": 0.30638134903537745,
      "grad_norm": 0.9133666559350329,
      "learning_rate": 8.768373961619283e-05,
      "loss": 0.6446,
      "step": 400
    },
    {
      "epoch": 0.3140408827612619,
      "grad_norm": 0.800135284242025,
      "learning_rate": 8.679096460932476e-05,
      "loss": 0.6431,
      "step": 410
    },
    {
      "epoch": 0.32170041648714637,
      "grad_norm": 0.7667073263249349,
      "learning_rate": 8.587184577883018e-05,
      "loss": 0.635,
      "step": 420
    },
    {
      "epoch": 0.32935995021303077,
      "grad_norm": 0.7446187579392809,
      "learning_rate": 8.492704125108932e-05,
      "loss": 0.6474,
      "step": 430
    },
    {
      "epoch": 0.33701948393891523,
      "grad_norm": 0.8505474486594474,
      "learning_rate": 8.395722754448392e-05,
      "loss": 0.6435,
      "step": 440
    },
    {
      "epoch": 0.34467901766479964,
      "grad_norm": 0.6912136288838342,
      "learning_rate": 8.296309908498264e-05,
      "loss": 0.6204,
      "step": 450
    },
    {
      "epoch": 0.3523385513906841,
      "grad_norm": 0.8845907739657766,
      "learning_rate": 8.194536770890391e-05,
      "loss": 0.6176,
      "step": 460
    },
    {
      "epoch": 0.35999808511656856,
      "grad_norm": 0.793300893475574,
      "learning_rate": 8.090476215321226e-05,
      "loss": 0.6277,
      "step": 470
    },
    {
      "epoch": 0.36765761884245296,
      "grad_norm": 0.8491940482226472,
      "learning_rate": 7.984202753371299e-05,
      "loss": 0.6374,
      "step": 480
    },
    {
      "epoch": 0.3753171525683374,
      "grad_norm": 0.7020295330180372,
      "learning_rate": 7.875792481151916e-05,
      "loss": 0.619,
      "step": 490
    },
    {
      "epoch": 0.3829766862942218,
      "grad_norm": 0.8353198999548404,
      "learning_rate": 7.765323024817237e-05,
      "loss": 0.6165,
      "step": 500
    },
    {
      "epoch": 0.3906362200201063,
      "grad_norm": 0.8682650673639652,
      "learning_rate": 7.65287348498082e-05,
      "loss": 0.6197,
      "step": 510
    },
    {
      "epoch": 0.3982957537459907,
      "grad_norm": 0.8629527743205716,
      "learning_rate": 7.538524380076351e-05,
      "loss": 0.6371,
      "step": 520
    },
    {
      "epoch": 0.40595528747187515,
      "grad_norm": 0.73321971611232,
      "learning_rate": 7.422357588703195e-05,
      "loss": 0.6122,
      "step": 530
    },
    {
      "epoch": 0.4136148211977596,
      "grad_norm": 0.6743735490891473,
      "learning_rate": 7.304456290997991e-05,
      "loss": 0.6029,
      "step": 540
    },
    {
      "epoch": 0.421274354923644,
      "grad_norm": 0.8045206710775962,
      "learning_rate": 7.184904909074293e-05,
      "loss": 0.6228,
      "step": 550
    },
    {
      "epoch": 0.42893388864952847,
      "grad_norm": 0.7878890213701146,
      "learning_rate": 7.063789046572916e-05,
      "loss": 0.6277,
      "step": 560
    },
    {
      "epoch": 0.4365934223754129,
      "grad_norm": 0.7482466270487711,
      "learning_rate": 6.941195427366259e-05,
      "loss": 0.6037,
      "step": 570
    },
    {
      "epoch": 0.44425295610129734,
      "grad_norm": 0.7787316245382442,
      "learning_rate": 6.817211833460483e-05,
      "loss": 0.5909,
      "step": 580
    },
    {
      "epoch": 0.4519124898271818,
      "grad_norm": 0.7516225911350334,
      "learning_rate": 6.691927042140044e-05,
      "loss": 0.589,
      "step": 590
    },
    {
      "epoch": 0.4595720235530662,
      "grad_norm": 0.7479278612486328,
      "learning_rate": 6.565430762399546e-05,
      "loss": 0.5768,
      "step": 600
    },
    {
      "epoch": 0.46723155727895066,
      "grad_norm": 0.7618232755834888,
      "learning_rate": 6.437813570708463e-05,
      "loss": 0.5912,
      "step": 610
    },
    {
      "epoch": 0.47489109100483506,
      "grad_norm": 0.7497540845592845,
      "learning_rate": 6.309166846154712e-05,
      "loss": 0.5965,
      "step": 620
    },
    {
      "epoch": 0.4825506247307195,
      "grad_norm": 0.722941602138503,
      "learning_rate": 6.179582705013519e-05,
      "loss": 0.6111,
      "step": 630
    },
    {
      "epoch": 0.49021015845660393,
      "grad_norm": 0.7215219222437452,
      "learning_rate": 6.049153934788429e-05,
      "loss": 0.5982,
      "step": 640
    },
    {
      "epoch": 0.4978696921824884,
      "grad_norm": 0.7793222397845758,
      "learning_rate": 5.9179739277716786e-05,
      "loss": 0.603,
      "step": 650
    },
    {
      "epoch": 0.5055292259083728,
      "grad_norm": 0.7357130962658376,
      "learning_rate": 5.7861366141715424e-05,
      "loss": 0.6121,
      "step": 660
    },
    {
      "epoch": 0.5131887596342573,
      "grad_norm": 0.685946141955599,
      "learning_rate": 5.653736394854471e-05,
      "loss": 0.5825,
      "step": 670
    },
    {
      "epoch": 0.5208482933601417,
      "grad_norm": 0.6741723935713323,
      "learning_rate": 5.5208680737502606e-05,
      "loss": 0.578,
      "step": 680
    },
    {
      "epoch": 0.5285078270860262,
      "grad_norm": 0.9915254274904765,
      "learning_rate": 5.387626789968574e-05,
      "loss": 0.5876,
      "step": 690
    },
    {
      "epoch": 0.5361673608119105,
      "grad_norm": 0.7543076820023589,
      "learning_rate": 5.2541079496754933e-05,
      "loss": 0.5862,
      "step": 700
    },
    {
      "epoch": 0.543826894537795,
      "grad_norm": 0.6809288476151739,
      "learning_rate": 5.1204071577788204e-05,
      "loss": 0.5469,
      "step": 710
    },
    {
      "epoch": 0.5514864282636794,
      "grad_norm": 0.6523050317216289,
      "learning_rate": 4.986620149471093e-05,
      "loss": 0.5787,
      "step": 720
    },
    {
      "epoch": 0.5591459619895639,
      "grad_norm": 0.6658435336020647,
      "learning_rate": 4.8528427216792935e-05,
      "loss": 0.5802,
      "step": 730
    },
    {
      "epoch": 0.5668054957154484,
      "grad_norm": 0.7734064939820273,
      "learning_rate": 4.7191706644703706e-05,
      "loss": 0.5758,
      "step": 740
    },
    {
      "epoch": 0.5744650294413327,
      "grad_norm": 0.6696947342532882,
      "learning_rate": 4.585699692461655e-05,
      "loss": 0.5795,
      "step": 750
    },
    {
      "epoch": 0.5821245631672172,
      "grad_norm": 0.737433128812512,
      "learning_rate": 4.4525253762853183e-05,
      "loss": 0.5653,
      "step": 760
    },
    {
      "epoch": 0.5897840968931016,
      "grad_norm": 0.6464215655480927,
      "learning_rate": 4.319743074155916e-05,
      "loss": 0.5732,
      "step": 770
    },
    {
      "epoch": 0.5974436306189861,
      "grad_norm": 0.7611630219437371,
      "learning_rate": 4.187447863590039e-05,
      "loss": 0.5637,
      "step": 780
    },
    {
      "epoch": 0.6051031643448705,
      "grad_norm": 0.7139956952893484,
      "learning_rate": 4.05573447332695e-05,
      "loss": 0.5585,
      "step": 790
    },
    {
      "epoch": 0.6127626980707549,
      "grad_norm": 0.7671531182065541,
      "learning_rate": 3.924697215498971e-05,
      "loss": 0.5663,
      "step": 800
    },
    {
      "epoch": 0.6204222317966394,
      "grad_norm": 0.7250577559514667,
      "learning_rate": 3.794429918100154e-05,
      "loss": 0.5631,
      "step": 810
    },
    {
      "epoch": 0.6280817655225238,
      "grad_norm": 0.834761848137774,
      "learning_rate": 3.665025857801647e-05,
      "loss": 0.5688,
      "step": 820
    },
    {
      "epoch": 0.6357412992484083,
      "grad_norm": 0.6508555293537424,
      "learning_rate": 3.536577693161801e-05,
      "loss": 0.5364,
      "step": 830
    },
    {
      "epoch": 0.6434008329742927,
      "grad_norm": 0.7426226012698264,
      "learning_rate": 3.4091773982788866e-05,
      "loss": 0.5324,
      "step": 840
    },
    {
      "epoch": 0.6510603667001771,
      "grad_norm": 0.6624694254361643,
      "learning_rate": 3.282916196933904e-05,
      "loss": 0.5366,
      "step": 850
    },
    {
      "epoch": 0.6587199004260615,
      "grad_norm": 0.6822377847021348,
      "learning_rate": 3.157884497270658e-05,
      "loss": 0.5499,
      "step": 860
    },
    {
      "epoch": 0.666379434151946,
      "grad_norm": 0.6606367594029701,
      "learning_rate": 3.0341718270598557e-05,
      "loss": 0.5415,
      "step": 870
    },
    {
      "epoch": 0.6740389678778305,
      "grad_norm": 0.7338327155163575,
      "learning_rate": 2.911866769593592e-05,
      "loss": 0.5145,
      "step": 880
    },
    {
      "epoch": 0.6816985016037149,
      "grad_norm": 0.613013131465413,
      "learning_rate": 2.7910569002561138e-05,
      "loss": 0.5366,
      "step": 890
    },
    {
      "epoch": 0.6893580353295993,
      "grad_norm": 0.6773171037933723,
      "learning_rate": 2.6718287238162963e-05,
      "loss": 0.5084,
      "step": 900
    },
    {
      "epoch": 0.6970175690554837,
      "grad_norm": 0.6488882426519923,
      "learning_rate": 2.5542676124867103e-05,
      "loss": 0.5285,
      "step": 910
    },
    {
      "epoch": 0.7046771027813682,
      "grad_norm": 0.653813893870716,
      "learning_rate": 2.4384577447936648e-05,
      "loss": 0.5088,
      "step": 920
    },
    {
      "epoch": 0.7123366365072527,
      "grad_norm": 0.7630538917031888,
      "learning_rate": 2.3244820453019566e-05,
      "loss": 0.5121,
      "step": 930
    },
    {
      "epoch": 0.7199961702331371,
      "grad_norm": 0.7107152117402987,
      "learning_rate": 2.2124221252375216e-05,
      "loss": 0.531,
      "step": 940
    },
    {
      "epoch": 0.7276557039590215,
      "grad_norm": 0.6849386017076563,
      "learning_rate": 2.1023582240504835e-05,
      "loss": 0.531,
      "step": 950
    },
    {
      "epoch": 0.7353152376849059,
      "grad_norm": 0.681713817852427,
      "learning_rate": 1.9943691519604524e-05,
      "loss": 0.5381,
      "step": 960
    },
    {
      "epoch": 0.7429747714107904,
      "grad_norm": 0.6560980468278351,
      "learning_rate": 1.8885322335252077e-05,
      "loss": 0.5235,
      "step": 970
    },
    {
      "epoch": 0.7506343051366748,
      "grad_norm": 0.6387640075811016,
      "learning_rate": 1.7849232522731797e-05,
      "loss": 0.5228,
      "step": 980
    },
    {
      "epoch": 0.7582938388625592,
      "grad_norm": 0.7059290436785569,
      "learning_rate": 1.6836163964393664e-05,
      "loss": 0.5441,
      "step": 990
    },
    {
      "epoch": 0.7659533725884436,
      "grad_norm": 0.6845616969089988,
      "learning_rate": 1.5846842058435458e-05,
      "loss": 0.5099,
      "step": 1000
    },
    {
      "epoch": 0.7736129063143281,
      "grad_norm": 0.6090491321707817,
      "learning_rate": 1.4881975199488245e-05,
      "loss": 0.5114,
      "step": 1010
    },
    {
      "epoch": 0.7812724400402126,
      "grad_norm": 0.6389049963156571,
      "learning_rate": 1.3942254271377003e-05,
      "loss": 0.5003,
      "step": 1020
    },
    {
      "epoch": 0.788931973766097,
      "grad_norm": 0.6801436703795579,
      "learning_rate": 1.3028352152419876e-05,
      "loss": 0.5277,
      "step": 1030
    },
    {
      "epoch": 0.7965915074919814,
      "grad_norm": 0.6313558029206057,
      "learning_rate": 1.21409232336199e-05,
      "loss": 0.5194,
      "step": 1040
    },
    {
      "epoch": 0.8042510412178658,
      "grad_norm": 0.6197855956436422,
      "learning_rate": 1.1280602950094531e-05,
      "loss": 0.5181,
      "step": 1050
    },
    {
      "epoch": 0.8119105749437503,
      "grad_norm": 0.6845783637358089,
      "learning_rate": 1.0448007326078335e-05,
      "loss": 0.5102,
      "step": 1060
    },
    {
      "epoch": 0.8195701086696348,
      "grad_norm": 0.6480827234715484,
      "learning_rate": 9.643732533824546e-06,
      "loss": 0.4972,
      "step": 1070
    },
    {
      "epoch": 0.8272296423955192,
      "grad_norm": 0.6681536341051292,
      "learning_rate": 8.868354466721668e-06,
      "loss": 0.5208,
      "step": 1080
    },
    {
      "epoch": 0.8348891761214036,
      "grad_norm": 0.6621991257490283,
      "learning_rate": 8.122428326930349e-06,
      "loss": 0.5045,
      "step": 1090
    },
    {
      "epoch": 0.842548709847288,
      "grad_norm": 0.7038914668740155,
      "learning_rate": 7.406488227836139e-06,
      "loss": 0.4977,
      "step": 1100
    },
    {
      "epoch": 0.8502082435731725,
      "grad_norm": 0.6714452418325616,
      "learning_rate": 6.721046811602622e-06,
      "loss": 0.5197,
      "step": 1110
    },
    {
      "epoch": 0.8578677772990569,
      "grad_norm": 0.6728865127826114,
      "learning_rate": 6.0665948820988305e-06,
      "loss": 0.5012,
      "step": 1120
    },
    {
      "epoch": 0.8655273110249414,
      "grad_norm": 0.6755473629732173,
      "learning_rate": 5.443601053463743e-06,
      "loss": 0.4948,
      "step": 1130
    },
    {
      "epoch": 0.8731868447508258,
      "grad_norm": 0.6718977935317116,
      "learning_rate": 4.852511414559574e-06,
      "loss": 0.5016,
      "step": 1140
    },
    {
      "epoch": 0.8808463784767102,
      "grad_norm": 0.6998921635398603,
      "learning_rate": 4.293749209554005e-06,
      "loss": 0.4983,
      "step": 1150
    },
    {
      "epoch": 0.8885059122025947,
      "grad_norm": 0.6320217046654734,
      "learning_rate": 3.767714534860223e-06,
      "loss": 0.4992,
      "step": 1160
    },
    {
      "epoch": 0.8961654459284791,
      "grad_norm": 0.6455347742794505,
      "learning_rate": 3.2747840526516416e-06,
      "loss": 0.493,
      "step": 1170
    },
    {
      "epoch": 0.9038249796543636,
      "grad_norm": 0.5955409045440381,
      "learning_rate": 2.8153107211564887e-06,
      "loss": 0.4939,
      "step": 1180
    },
    {
      "epoch": 0.9114845133802479,
      "grad_norm": 0.6352733334971196,
      "learning_rate": 2.3896235419254065e-06,
      "loss": 0.4849,
      "step": 1190
    },
    {
      "epoch": 0.9191440471061324,
      "grad_norm": 0.6100416130741432,
      "learning_rate": 1.9980273242529823e-06,
      "loss": 0.5059,
      "step": 1200
    },
    {
      "epoch": 0.9268035808320169,
      "grad_norm": 0.6670229788776991,
      "learning_rate": 1.6408024669219258e-06,
      "loss": 0.489,
      "step": 1210
    },
    {
      "epoch": 0.9344631145579013,
      "grad_norm": 0.6414138552373387,
      "learning_rate": 1.3182047574261558e-06,
      "loss": 0.4971,
      "step": 1220
    },
    {
      "epoch": 0.9421226482837858,
      "grad_norm": 0.61454383407946,
      "learning_rate": 1.030465188816604e-06,
      "loss": 0.5034,
      "step": 1230
    },
    {
      "epoch": 0.9497821820096701,
      "grad_norm": 0.6480110228205495,
      "learning_rate": 7.777897943007595e-07,
      "loss": 0.5032,
      "step": 1240
    },
    {
      "epoch": 0.9574417157355546,
      "grad_norm": 0.6281167623669748,
      "learning_rate": 5.603594997145967e-07,
      "loss": 0.4898,
      "step": 1250
    },
    {
      "epoch": 0.965101249461439,
      "grad_norm": 0.6796483312027185,
      "learning_rate": 3.7832999397229843e-07,
      "loss": 0.5099,
      "step": 1260
    },
    {
      "epoch": 0.9727607831873235,
      "grad_norm": 0.6155337842087106,
      "learning_rate": 2.318316175866697e-07,
      "loss": 0.499,
      "step": 1270
    },
    {
      "epoch": 0.9804203169132079,
      "grad_norm": 0.5868743351197286,
      "learning_rate": 1.2096926934007102e-07,
      "loss": 0.5054,
      "step": 1280
    },
    {
      "epoch": 0.9880798506390923,
      "grad_norm": 0.7031955279741022,
      "learning_rate": 4.5822331172606926e-08,
      "loss": 0.4933,
      "step": 1290
    },
    {
      "epoch": 0.9957393843649768,
      "grad_norm": 0.5938630135036446,
      "learning_rate": 6.444611341432927e-09,
      "loss": 0.4883,
      "step": 1300
    },
    {
      "epoch": 0.999569151227919,
      "step": 1305,
      "total_flos": 184070382419968.0,
      "train_loss": 0.5936476859096367,
      "train_runtime": 39564.2825,
      "train_samples_per_second": 2.112,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 1305,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 184070382419968.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}