{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09413433883118585,
  "eval_steps": 500,
  "global_step": 6104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004780741323340042,
      "grad_norm": 3.1866345405578613,
      "learning_rate": 1.0157273918741808e-06,
      "loss": 1.194,
      "step": 31
    },
    {
      "epoch": 0.0009561482646680084,
      "grad_norm": 1.7708723545074463,
      "learning_rate": 2.0314547837483616e-06,
      "loss": 1.1124,
      "step": 62
    },
    {
      "epoch": 0.0014342223970020126,
      "grad_norm": 1.6835601329803467,
      "learning_rate": 3.0471821756225426e-06,
      "loss": 1.0585,
      "step": 93
    },
    {
      "epoch": 0.0019122965293360168,
      "grad_norm": 1.642537236213684,
      "learning_rate": 4.062909567496723e-06,
      "loss": 1.0213,
      "step": 124
    },
    {
      "epoch": 0.002390370661670021,
      "grad_norm": 1.8476150035858154,
      "learning_rate": 5.078636959370905e-06,
      "loss": 1.0024,
      "step": 155
    },
    {
      "epoch": 0.0028684447940040252,
      "grad_norm": 1.96336829662323,
      "learning_rate": 6.094364351245085e-06,
      "loss": 0.9938,
      "step": 186
    },
    {
      "epoch": 0.0033465189263380294,
      "grad_norm": 1.8158528804779053,
      "learning_rate": 7.110091743119267e-06,
      "loss": 0.969,
      "step": 217
    },
    {
      "epoch": 0.0038245930586720336,
      "grad_norm": 1.9796783924102783,
      "learning_rate": 8.125819134993446e-06,
      "loss": 0.9573,
      "step": 248
    },
    {
      "epoch": 0.004302667191006038,
      "grad_norm": 1.8192514181137085,
      "learning_rate": 9.141546526867629e-06,
      "loss": 0.9498,
      "step": 279
    },
    {
      "epoch": 0.004780741323340042,
      "grad_norm": 2.1396358013153076,
      "learning_rate": 1.015727391874181e-05,
      "loss": 0.9294,
      "step": 310
    },
    {
      "epoch": 0.005258815455674046,
      "grad_norm": 2.0807156562805176,
      "learning_rate": 1.117300131061599e-05,
      "loss": 0.9186,
      "step": 341
    },
    {
      "epoch": 0.0057368895880080505,
      "grad_norm": 2.002887010574341,
      "learning_rate": 1.218872870249017e-05,
      "loss": 0.9149,
      "step": 372
    },
    {
      "epoch": 0.006214963720342055,
      "grad_norm": 2.240675687789917,
      "learning_rate": 1.3204456094364351e-05,
      "loss": 0.9139,
      "step": 403
    },
    {
      "epoch": 0.006693037852676059,
      "grad_norm": 1.9016591310501099,
      "learning_rate": 1.4220183486238533e-05,
      "loss": 0.8946,
      "step": 434
    },
    {
      "epoch": 0.007171111985010063,
      "grad_norm": 1.6729310750961304,
      "learning_rate": 1.5235910878112714e-05,
      "loss": 0.8959,
      "step": 465
    },
    {
      "epoch": 0.007649186117344067,
      "grad_norm": 2.2607779502868652,
      "learning_rate": 1.6251638269986893e-05,
      "loss": 0.8847,
      "step": 496
    },
    {
      "epoch": 0.00812726024967807,
      "grad_norm": 1.699507236480713,
      "learning_rate": 1.7267365661861077e-05,
      "loss": 0.8773,
      "step": 527
    },
    {
      "epoch": 0.008605334382012076,
      "grad_norm": 1.93502938747406,
      "learning_rate": 1.8283093053735257e-05,
      "loss": 0.8773,
      "step": 558
    },
    {
      "epoch": 0.009083408514346079,
      "grad_norm": 2.1234281063079834,
      "learning_rate": 1.9298820445609438e-05,
      "loss": 0.8669,
      "step": 589
    },
    {
      "epoch": 0.009561482646680084,
      "grad_norm": 1.7465944290161133,
      "learning_rate": 2.031454783748362e-05,
      "loss": 0.8536,
      "step": 620
    },
    {
      "epoch": 0.010039556779014087,
      "grad_norm": 1.7039932012557983,
      "learning_rate": 2.13302752293578e-05,
      "loss": 0.8624,
      "step": 651
    },
    {
      "epoch": 0.010517630911348093,
      "grad_norm": 1.551837682723999,
      "learning_rate": 2.234600262123198e-05,
      "loss": 0.8555,
      "step": 682
    },
    {
      "epoch": 0.010995705043682096,
      "grad_norm": 1.7622497081756592,
      "learning_rate": 2.336173001310616e-05,
      "loss": 0.8475,
      "step": 713
    },
    {
      "epoch": 0.011473779176016101,
      "grad_norm": 2.000936269760132,
      "learning_rate": 2.437745740498034e-05,
      "loss": 0.852,
      "step": 744
    },
    {
      "epoch": 0.011951853308350104,
      "grad_norm": 1.6770379543304443,
      "learning_rate": 2.5393184796854525e-05,
      "loss": 0.8455,
      "step": 775
    },
    {
      "epoch": 0.01242992744068411,
      "grad_norm": 1.746506929397583,
      "learning_rate": 2.6408912188728702e-05,
      "loss": 0.8406,
      "step": 806
    },
    {
      "epoch": 0.012908001573018113,
      "grad_norm": 1.507759690284729,
      "learning_rate": 2.7424639580602886e-05,
      "loss": 0.8556,
      "step": 837
    },
    {
      "epoch": 0.013386075705352118,
      "grad_norm": 1.6984492540359497,
      "learning_rate": 2.8440366972477066e-05,
      "loss": 0.8281,
      "step": 868
    },
    {
      "epoch": 0.013864149837686121,
      "grad_norm": 1.5145736932754517,
      "learning_rate": 2.9456094364351244e-05,
      "loss": 0.8359,
      "step": 899
    },
    {
      "epoch": 0.014342223970020126,
      "grad_norm": 1.5700000524520874,
      "learning_rate": 3.0471821756225428e-05,
      "loss": 0.8305,
      "step": 930
    },
    {
      "epoch": 0.01482029810235413,
      "grad_norm": 1.6657596826553345,
      "learning_rate": 3.148754914809961e-05,
      "loss": 0.8263,
      "step": 961
    },
    {
      "epoch": 0.015298372234688135,
      "grad_norm": 1.527628779411316,
      "learning_rate": 3.2503276539973785e-05,
      "loss": 0.8318,
      "step": 992
    },
    {
      "epoch": 0.015776446367022138,
      "grad_norm": 1.8353967666625977,
      "learning_rate": 3.351900393184797e-05,
      "loss": 0.8192,
      "step": 1023
    },
    {
      "epoch": 0.01625452049935614,
      "grad_norm": 1.2118042707443237,
      "learning_rate": 3.453473132372215e-05,
      "loss": 0.819,
      "step": 1054
    },
    {
      "epoch": 0.016732594631690145,
      "grad_norm": 1.3235970735549927,
      "learning_rate": 3.555045871559633e-05,
      "loss": 0.8176,
      "step": 1085
    },
    {
      "epoch": 0.01721066876402415,
      "grad_norm": 1.6729888916015625,
      "learning_rate": 3.6566186107470514e-05,
      "loss": 0.8202,
      "step": 1116
    },
    {
      "epoch": 0.017688742896358155,
      "grad_norm": 1.3251298666000366,
      "learning_rate": 3.7581913499344695e-05,
      "loss": 0.8104,
      "step": 1147
    },
    {
      "epoch": 0.018166817028692158,
      "grad_norm": 1.5231342315673828,
      "learning_rate": 3.8597640891218876e-05,
      "loss": 0.8113,
      "step": 1178
    },
    {
      "epoch": 0.01864489116102616,
      "grad_norm": 1.3263883590698242,
      "learning_rate": 3.9613368283093056e-05,
      "loss": 0.7981,
      "step": 1209
    },
    {
      "epoch": 0.019122965293360168,
      "grad_norm": 1.317791223526001,
      "learning_rate": 4.062909567496724e-05,
      "loss": 0.7962,
      "step": 1240
    },
    {
      "epoch": 0.01960103942569417,
      "grad_norm": 1.566698670387268,
      "learning_rate": 4.164482306684142e-05,
      "loss": 0.8072,
      "step": 1271
    },
    {
      "epoch": 0.020079113558028175,
      "grad_norm": 1.2935110330581665,
      "learning_rate": 4.26605504587156e-05,
      "loss": 0.7818,
      "step": 1302
    },
    {
      "epoch": 0.020557187690362178,
      "grad_norm": 1.336227536201477,
      "learning_rate": 4.367627785058978e-05,
      "loss": 0.7917,
      "step": 1333
    },
    {
      "epoch": 0.021035261822696185,
      "grad_norm": 1.5656548738479614,
      "learning_rate": 4.469200524246396e-05,
      "loss": 0.7785,
      "step": 1364
    },
    {
      "epoch": 0.02151333595503019,
      "grad_norm": 1.5208159685134888,
      "learning_rate": 4.570773263433814e-05,
      "loss": 0.7839,
      "step": 1395
    },
    {
      "epoch": 0.02199141008736419,
      "grad_norm": 1.4816375970840454,
      "learning_rate": 4.672346002621232e-05,
      "loss": 0.7789,
      "step": 1426
    },
    {
      "epoch": 0.022469484219698195,
      "grad_norm": 1.402166485786438,
      "learning_rate": 4.77391874180865e-05,
      "loss": 0.7803,
      "step": 1457
    },
    {
      "epoch": 0.022947558352032202,
      "grad_norm": 1.2986265420913696,
      "learning_rate": 4.875491480996068e-05,
      "loss": 0.7739,
      "step": 1488
    },
    {
      "epoch": 0.023425632484366205,
      "grad_norm": 1.3171271085739136,
      "learning_rate": 4.977064220183487e-05,
      "loss": 0.7694,
      "step": 1519
    },
    {
      "epoch": 0.02390370661670021,
      "grad_norm": 1.4870030879974365,
      "learning_rate": 4.9999915451558777e-05,
      "loss": 0.7663,
      "step": 1550
    },
    {
      "epoch": 0.024381780749034212,
      "grad_norm": 1.7419476509094238,
      "learning_rate": 4.999955597496219e-05,
      "loss": 0.7731,
      "step": 1581
    },
    {
      "epoch": 0.02485985488136822,
      "grad_norm": 1.109238624572754,
      "learning_rate": 4.9998914381774255e-05,
      "loss": 0.7704,
      "step": 1612
    },
    {
      "epoch": 0.025337929013702222,
      "grad_norm": 1.3478920459747314,
      "learning_rate": 4.999799067923527e-05,
      "loss": 0.7723,
      "step": 1643
    },
    {
      "epoch": 0.025816003146036225,
      "grad_norm": 1.2739650011062622,
      "learning_rate": 4.999678487776908e-05,
      "loss": 0.7699,
      "step": 1674
    },
    {
      "epoch": 0.02629407727837023,
      "grad_norm": 1.3892935514450073,
      "learning_rate": 4.9995296990983006e-05,
      "loss": 0.7709,
      "step": 1705
    },
    {
      "epoch": 0.026772151410704235,
      "grad_norm": 1.2031512260437012,
      "learning_rate": 4.999352703566763e-05,
      "loss": 0.7557,
      "step": 1736
    },
    {
      "epoch": 0.02725022554303824,
      "grad_norm": 1.185471773147583,
      "learning_rate": 4.999147503179668e-05,
      "loss": 0.7645,
      "step": 1767
    },
    {
      "epoch": 0.027728299675372242,
      "grad_norm": 1.2331740856170654,
      "learning_rate": 4.998914100252672e-05,
      "loss": 0.7655,
      "step": 1798
    },
    {
      "epoch": 0.028206373807706245,
      "grad_norm": 1.1817049980163574,
      "learning_rate": 4.998652497419696e-05,
      "loss": 0.7617,
      "step": 1829
    },
    {
      "epoch": 0.028684447940040252,
      "grad_norm": 1.2225860357284546,
      "learning_rate": 4.9983626976328927e-05,
      "loss": 0.7558,
      "step": 1860
    },
    {
      "epoch": 0.029162522072374256,
      "grad_norm": 1.6452528238296509,
      "learning_rate": 4.998044704162613e-05,
      "loss": 0.7566,
      "step": 1891
    },
    {
      "epoch": 0.02964059620470826,
      "grad_norm": 1.3764828443527222,
      "learning_rate": 4.9976985205973705e-05,
      "loss": 0.7545,
      "step": 1922
    },
    {
      "epoch": 0.030118670337042262,
      "grad_norm": 1.6581465005874634,
      "learning_rate": 4.997324150843799e-05,
      "loss": 0.7519,
      "step": 1953
    },
    {
      "epoch": 0.03059674446937627,
      "grad_norm": 1.1065036058425903,
      "learning_rate": 4.99692159912661e-05,
      "loss": 0.7579,
      "step": 1984
    },
    {
      "epoch": 0.031074818601710272,
      "grad_norm": 2.6465444564819336,
      "learning_rate": 4.996490869988546e-05,
      "loss": 0.7538,
      "step": 2015
    },
    {
      "epoch": 0.031552892734044276,
      "grad_norm": 1.3028968572616577,
      "learning_rate": 4.996031968290326e-05,
      "loss": 0.7522,
      "step": 2046
    },
    {
      "epoch": 0.03203096686637828,
      "grad_norm": 1.0450382232666016,
      "learning_rate": 4.995544899210594e-05,
      "loss": 0.742,
      "step": 2077
    },
    {
      "epoch": 0.03250904099871228,
      "grad_norm": 0.9411994814872742,
      "learning_rate": 4.9950296682458583e-05,
      "loss": 0.7401,
      "step": 2108
    },
    {
      "epoch": 0.03298711513104629,
      "grad_norm": 1.0501608848571777,
      "learning_rate": 4.994486281210429e-05,
      "loss": 0.7455,
      "step": 2139
    },
    {
      "epoch": 0.03346518926338029,
      "grad_norm": 1.266400694847107,
      "learning_rate": 4.9939147442363566e-05,
      "loss": 0.7391,
      "step": 2170
    },
    {
      "epoch": 0.033943263395714296,
      "grad_norm": 1.2862213850021362,
      "learning_rate": 4.9933150637733574e-05,
      "loss": 0.7397,
      "step": 2201
    },
    {
      "epoch": 0.0344213375280483,
      "grad_norm": 1.2715409994125366,
      "learning_rate": 4.992687246588743e-05,
      "loss": 0.7467,
      "step": 2232
    },
    {
      "epoch": 0.0348994116603823,
      "grad_norm": 1.3290003538131714,
      "learning_rate": 4.992031299767347e-05,
      "loss": 0.7432,
      "step": 2263
    },
    {
      "epoch": 0.03537748579271631,
      "grad_norm": 1.0561761856079102,
      "learning_rate": 4.9913472307114386e-05,
      "loss": 0.7336,
      "step": 2294
    },
    {
      "epoch": 0.035855559925050316,
      "grad_norm": 1.3272422552108765,
      "learning_rate": 4.9906350471406446e-05,
      "loss": 0.7251,
      "step": 2325
    },
    {
      "epoch": 0.036333634057384316,
      "grad_norm": 1.0749491453170776,
      "learning_rate": 4.989894757091861e-05,
      "loss": 0.7205,
      "step": 2356
    },
    {
      "epoch": 0.03681170818971832,
      "grad_norm": 1.1581461429595947,
      "learning_rate": 4.989126368919158e-05,
      "loss": 0.7311,
      "step": 2387
    },
    {
      "epoch": 0.03728978232205232,
      "grad_norm": 1.0796961784362793,
      "learning_rate": 4.988329891293693e-05,
      "loss": 0.7259,
      "step": 2418
    },
    {
      "epoch": 0.03776785645438633,
      "grad_norm": 1.1916818618774414,
      "learning_rate": 4.987505333203608e-05,
      "loss": 0.7258,
      "step": 2449
    },
    {
      "epoch": 0.038245930586720336,
      "grad_norm": 0.9515872001647949,
      "learning_rate": 4.9866527039539276e-05,
      "loss": 0.7273,
      "step": 2480
    },
    {
      "epoch": 0.038724004719054336,
      "grad_norm": 1.1217246055603027,
      "learning_rate": 4.9857720131664594e-05,
      "loss": 0.7269,
      "step": 2511
    },
    {
      "epoch": 0.03920207885138834,
      "grad_norm": 0.9570199847221375,
      "learning_rate": 4.9848632707796773e-05,
      "loss": 0.7289,
      "step": 2542
    },
    {
      "epoch": 0.03968015298372235,
      "grad_norm": 1.2980682849884033,
      "learning_rate": 4.9839264870486155e-05,
      "loss": 0.7382,
      "step": 2573
    },
    {
      "epoch": 0.04015822711605635,
      "grad_norm": 2.1257143020629883,
      "learning_rate": 4.9829616725447526e-05,
      "loss": 0.8112,
      "step": 2604
    },
    {
      "epoch": 0.04063630124839036,
      "grad_norm": 1.5091110467910767,
      "learning_rate": 4.981968838155888e-05,
      "loss": 0.7451,
      "step": 2635
    },
    {
      "epoch": 0.041114375380724356,
      "grad_norm": 2.4548749923706055,
      "learning_rate": 4.980947995086024e-05,
      "loss": 0.7358,
      "step": 2666
    },
    {
      "epoch": 0.04159244951305836,
      "grad_norm": 1.176115870475769,
      "learning_rate": 4.979899154855234e-05,
      "loss": 0.7368,
      "step": 2697
    },
    {
      "epoch": 0.04207052364539237,
      "grad_norm": 1.063672661781311,
      "learning_rate": 4.9788223292995386e-05,
      "loss": 0.7465,
      "step": 2728
    },
    {
      "epoch": 0.04254859777772637,
      "grad_norm": 1.3062779903411865,
      "learning_rate": 4.977717530570768e-05,
      "loss": 0.7413,
      "step": 2759
    },
    {
      "epoch": 0.04302667191006038,
      "grad_norm": 1.5550280809402466,
      "learning_rate": 4.976584771136425e-05,
      "loss": 0.724,
      "step": 2790
    },
    {
      "epoch": 0.043504746042394384,
      "grad_norm": 1.2525728940963745,
      "learning_rate": 4.975424063779547e-05,
      "loss": 0.7216,
      "step": 2821
    },
    {
      "epoch": 0.04398282017472838,
      "grad_norm": 1.158134937286377,
      "learning_rate": 4.974235421598557e-05,
      "loss": 0.728,
      "step": 2852
    },
    {
      "epoch": 0.04446089430706239,
      "grad_norm": 1.262291669845581,
      "learning_rate": 4.973018858007122e-05,
      "loss": 0.7191,
      "step": 2883
    },
    {
      "epoch": 0.04493896843939639,
      "grad_norm": 2.826028347015381,
      "learning_rate": 4.9717743867339963e-05,
      "loss": 0.7211,
      "step": 2914
    },
    {
      "epoch": 0.0454170425717304,
      "grad_norm": 1.0346958637237549,
      "learning_rate": 4.9705020218228695e-05,
      "loss": 0.7268,
      "step": 2945
    },
    {
      "epoch": 0.045895116704064404,
      "grad_norm": 1.4338330030441284,
      "learning_rate": 4.969201777632205e-05,
      "loss": 0.7154,
      "step": 2976
    },
    {
      "epoch": 0.046373190836398404,
      "grad_norm": 0.9223676919937134,
      "learning_rate": 4.9678736688350846e-05,
      "loss": 0.7195,
      "step": 3007
    },
    {
      "epoch": 0.04685126496873241,
      "grad_norm": 0.9936623573303223,
      "learning_rate": 4.966517710419033e-05,
      "loss": 0.7194,
      "step": 3038
    },
    {
      "epoch": 0.04732933910106642,
      "grad_norm": 1.017962098121643,
      "learning_rate": 4.965133917685858e-05,
      "loss": 0.713,
      "step": 3069
    },
    {
      "epoch": 0.04780741323340042,
      "grad_norm": 0.9654473662376404,
      "learning_rate": 4.9637223062514714e-05,
      "loss": 0.7096,
      "step": 3100
    },
    {
      "epoch": 0.048285487365734424,
      "grad_norm": 0.9372695684432983,
      "learning_rate": 4.962282892045718e-05,
      "loss": 0.7116,
      "step": 3131
    },
    {
      "epoch": 0.048763561498068424,
      "grad_norm": 0.9450846910476685,
      "learning_rate": 4.9608156913121904e-05,
      "loss": 0.7129,
      "step": 3162
    },
    {
      "epoch": 0.04924163563040243,
      "grad_norm": 1.0803054571151733,
      "learning_rate": 4.959320720608049e-05,
      "loss": 0.706,
      "step": 3193
    },
    {
      "epoch": 0.04971970976273644,
      "grad_norm": 1.2218348979949951,
      "learning_rate": 4.9577979968038354e-05,
      "loss": 0.7076,
      "step": 3224
    },
    {
      "epoch": 0.05019778389507044,
      "grad_norm": 1.0429767370224,
      "learning_rate": 4.956247537083282e-05,
      "loss": 0.7089,
      "step": 3255
    },
    {
      "epoch": 0.050675858027404444,
      "grad_norm": 0.9912049770355225,
      "learning_rate": 4.9546693589431145e-05,
      "loss": 0.7016,
      "step": 3286
    },
    {
      "epoch": 0.051153932159738444,
      "grad_norm": 0.9687103033065796,
      "learning_rate": 4.9530634801928595e-05,
      "loss": 0.7071,
      "step": 3317
    },
    {
      "epoch": 0.05163200629207245,
      "grad_norm": 0.8178670406341553,
      "learning_rate": 4.9514299189546395e-05,
      "loss": 0.6991,
      "step": 3348
    },
    {
      "epoch": 0.05211008042440646,
      "grad_norm": 0.8601382374763489,
      "learning_rate": 4.949768693662973e-05,
      "loss": 0.6978,
      "step": 3379
    },
    {
      "epoch": 0.05258815455674046,
      "grad_norm": 1.076370120048523,
      "learning_rate": 4.948079823064559e-05,
      "loss": 0.7044,
      "step": 3410
    },
    {
      "epoch": 0.053066228689074464,
      "grad_norm": 3.9457356929779053,
      "learning_rate": 4.946363326218074e-05,
      "loss": 0.6978,
      "step": 3441
    },
    {
      "epoch": 0.05354430282140847,
      "grad_norm": 0.8186474442481995,
      "learning_rate": 4.9446192224939525e-05,
      "loss": 0.6974,
      "step": 3472
    },
    {
      "epoch": 0.05402237695374247,
      "grad_norm": 0.9643816947937012,
      "learning_rate": 4.942847531574167e-05,
      "loss": 0.7025,
      "step": 3503
    },
    {
      "epoch": 0.05450045108607648,
      "grad_norm": 1.024248480796814,
      "learning_rate": 4.941048273452008e-05,
      "loss": 0.7006,
      "step": 3534
    },
    {
      "epoch": 0.05497852521841048,
      "grad_norm": 0.7718949317932129,
      "learning_rate": 4.9392214684318605e-05,
      "loss": 0.7024,
      "step": 3565
    },
    {
      "epoch": 0.055456599350744484,
      "grad_norm": 1.1313899755477905,
      "learning_rate": 4.93736713712897e-05,
      "loss": 0.701,
      "step": 3596
    },
    {
      "epoch": 0.05593467348307849,
      "grad_norm": 1.0118827819824219,
      "learning_rate": 4.9354853004692124e-05,
      "loss": 0.7036,
      "step": 3627
    },
    {
      "epoch": 0.05641274761541249,
      "grad_norm": 0.9465724229812622,
      "learning_rate": 4.93357597968886e-05,
      "loss": 0.6869,
      "step": 3658
    },
    {
      "epoch": 0.0568908217477465,
      "grad_norm": 1.0233882665634155,
      "learning_rate": 4.931639196334338e-05,
      "loss": 0.6944,
      "step": 3689
    },
    {
      "epoch": 0.057368895880080505,
      "grad_norm": 1.008609652519226,
      "learning_rate": 4.9296749722619826e-05,
      "loss": 0.6916,
      "step": 3720
    },
    {
      "epoch": 0.057846970012414504,
      "grad_norm": 1.0083181858062744,
      "learning_rate": 4.9276833296377966e-05,
      "loss": 0.6886,
      "step": 3751
    },
    {
      "epoch": 0.05832504414474851,
      "grad_norm": 0.9374220967292786,
      "learning_rate": 4.925664290937196e-05,
      "loss": 0.6976,
      "step": 3782
    },
    {
      "epoch": 0.05880311827708251,
      "grad_norm": 0.9066904783248901,
      "learning_rate": 4.9236178789447576e-05,
      "loss": 0.6911,
      "step": 3813
    },
    {
      "epoch": 0.05928119240941652,
      "grad_norm": 0.9702699780464172,
      "learning_rate": 4.921544116753962e-05,
      "loss": 0.6959,
      "step": 3844
    },
    {
      "epoch": 0.059759266541750525,
      "grad_norm": 0.8405037522315979,
      "learning_rate": 4.919443027766935e-05,
      "loss": 0.6896,
      "step": 3875
    },
    {
      "epoch": 0.060237340674084525,
      "grad_norm": 0.9460383653640747,
      "learning_rate": 4.91731463569418e-05,
      "loss": 0.6871,
      "step": 3906
    },
    {
      "epoch": 0.06071541480641853,
      "grad_norm": 0.9355078339576721,
      "learning_rate": 4.915158964554312e-05,
      "loss": 0.6843,
      "step": 3937
    },
    {
      "epoch": 0.06119348893875254,
      "grad_norm": 0.7211058735847473,
      "learning_rate": 4.912976038673786e-05,
      "loss": 0.6861,
      "step": 3968
    },
    {
      "epoch": 0.06167156307108654,
      "grad_norm": 0.8674766421318054,
      "learning_rate": 4.9107658826866254e-05,
      "loss": 0.6939,
      "step": 3999
    },
    {
      "epoch": 0.062149637203420545,
      "grad_norm": 0.8166181445121765,
      "learning_rate": 4.908528521534139e-05,
      "loss": 0.692,
      "step": 4030
    },
    {
      "epoch": 0.06262771133575455,
      "grad_norm": 0.841305136680603,
      "learning_rate": 4.906263980464644e-05,
      "loss": 0.6855,
      "step": 4061
    },
    {
      "epoch": 0.06310578546808855,
      "grad_norm": 0.8942857384681702,
      "learning_rate": 4.903972285033178e-05,
      "loss": 0.6946,
      "step": 4092
    },
    {
      "epoch": 0.06358385960042255,
      "grad_norm": 0.8595120310783386,
      "learning_rate": 4.901653461101213e-05,
      "loss": 0.6825,
      "step": 4123
    },
    {
      "epoch": 0.06406193373275657,
      "grad_norm": 0.8155812621116638,
      "learning_rate": 4.8993075348363626e-05,
      "loss": 0.6821,
      "step": 4154
    },
    {
      "epoch": 0.06454000786509057,
      "grad_norm": 0.8901113271713257,
      "learning_rate": 4.896934532712084e-05,
      "loss": 0.6898,
      "step": 4185
    },
    {
      "epoch": 0.06501808199742456,
      "grad_norm": 0.9637976288795471,
      "learning_rate": 4.8945344815073846e-05,
      "loss": 0.6829,
      "step": 4216
    },
    {
      "epoch": 0.06549615612975858,
      "grad_norm": 0.7048139572143555,
      "learning_rate": 4.892107408306516e-05,
      "loss": 0.6834,
      "step": 4247
    },
    {
      "epoch": 0.06597423026209258,
      "grad_norm": 0.8655612468719482,
      "learning_rate": 4.889653340498669e-05,
      "loss": 0.6778,
      "step": 4278
    },
    {
      "epoch": 0.06645230439442658,
      "grad_norm": 0.8204261064529419,
      "learning_rate": 4.8871723057776664e-05,
      "loss": 0.6672,
      "step": 4309
    },
    {
      "epoch": 0.06693037852676058,
      "grad_norm": 0.9259466528892517,
      "learning_rate": 4.8846643321416476e-05,
      "loss": 0.6778,
      "step": 4340
    },
    {
      "epoch": 0.06740845265909459,
      "grad_norm": 0.9826278686523438,
      "learning_rate": 4.882129447892753e-05,
      "loss": 0.6882,
      "step": 4371
    },
    {
      "epoch": 0.06788652679142859,
      "grad_norm": 0.7376586198806763,
      "learning_rate": 4.8795676816368076e-05,
      "loss": 0.6802,
      "step": 4402
    },
    {
      "epoch": 0.06836460092376259,
      "grad_norm": 0.6778755784034729,
      "learning_rate": 4.876979062282995e-05,
      "loss": 0.6814,
      "step": 4433
    },
    {
      "epoch": 0.0688426750560966,
      "grad_norm": 0.8117042183876038,
      "learning_rate": 4.8743636190435325e-05,
      "loss": 0.6759,
      "step": 4464
    },
    {
      "epoch": 0.0693207491884306,
      "grad_norm": 0.9493227005004883,
      "learning_rate": 4.871721381433344e-05,
      "loss": 0.6744,
      "step": 4495
    },
    {
      "epoch": 0.0697988233207646,
      "grad_norm": 1.3356900215148926,
      "learning_rate": 4.869052379269719e-05,
      "loss": 0.6763,
      "step": 4526
    },
    {
      "epoch": 0.07027689745309862,
      "grad_norm": 1.1542543172836304,
      "learning_rate": 4.866356642671985e-05,
      "loss": 0.6788,
      "step": 4557
    },
    {
      "epoch": 0.07075497158543262,
      "grad_norm": 0.785176157951355,
      "learning_rate": 4.8636342020611634e-05,
      "loss": 0.6853,
      "step": 4588
    },
    {
      "epoch": 0.07123304571776662,
      "grad_norm": 0.8102776408195496,
      "learning_rate": 4.860885088159626e-05,
      "loss": 0.6794,
      "step": 4619
    },
    {
      "epoch": 0.07171111985010063,
      "grad_norm": 0.9685975313186646,
      "learning_rate": 4.858109331990751e-05,
      "loss": 0.6823,
      "step": 4650
    },
    {
      "epoch": 0.07218919398243463,
      "grad_norm": 0.7929072976112366,
      "learning_rate": 4.855306964878567e-05,
      "loss": 0.6781,
      "step": 4681
    },
    {
      "epoch": 0.07266726811476863,
      "grad_norm": 0.8171564340591431,
      "learning_rate": 4.8524780184474084e-05,
      "loss": 0.6685,
      "step": 4712
    },
    {
      "epoch": 0.07314534224710265,
      "grad_norm": 0.9218119382858276,
      "learning_rate": 4.8496225246215496e-05,
      "loss": 0.6796,
      "step": 4743
    },
    {
      "epoch": 0.07362341637943665,
      "grad_norm": 3.1681158542633057,
      "learning_rate": 4.8467405156248505e-05,
      "loss": 0.676,
      "step": 4774
    },
    {
      "epoch": 0.07410149051177065,
      "grad_norm": 0.9336240887641907,
      "learning_rate": 4.843832023980392e-05,
      "loss": 0.6734,
      "step": 4805
    },
    {
      "epoch": 0.07457956464410465,
      "grad_norm": 0.8264138102531433,
      "learning_rate": 4.840897082510106e-05,
      "loss": 0.6905,
      "step": 4836
    },
    {
      "epoch": 0.07505763877643866,
      "grad_norm": 0.819663405418396,
      "learning_rate": 4.8379357243344084e-05,
      "loss": 0.6814,
      "step": 4867
    },
    {
      "epoch": 0.07553571290877266,
      "grad_norm": 3.124502420425415,
      "learning_rate": 4.8349479828718236e-05,
      "loss": 0.6704,
      "step": 4898
    },
    {
      "epoch": 0.07601378704110666,
      "grad_norm": 0.7769860625267029,
      "learning_rate": 4.8319338918386075e-05,
      "loss": 0.6728,
      "step": 4929
    },
    {
      "epoch": 0.07649186117344067,
      "grad_norm": 0.8232171535491943,
      "learning_rate": 4.828893485248369e-05,
      "loss": 0.6798,
      "step": 4960
    },
    {
      "epoch": 0.07696993530577467,
      "grad_norm": 0.8771420121192932,
      "learning_rate": 4.825826797411682e-05,
      "loss": 0.6722,
      "step": 4991
    },
    {
      "epoch": 0.07744800943810867,
      "grad_norm": 0.8321033716201782,
      "learning_rate": 4.822733862935702e-05,
      "loss": 0.6724,
      "step": 5022
    },
    {
      "epoch": 0.07792608357044269,
      "grad_norm": 0.9346029162406921,
      "learning_rate": 4.819614716723775e-05,
      "loss": 0.6764,
      "step": 5053
    },
    {
      "epoch": 0.07840415770277669,
      "grad_norm": 0.9193580150604248,
      "learning_rate": 4.8164693939750425e-05,
      "loss": 0.6789,
      "step": 5084
    },
    {
      "epoch": 0.07888223183511069,
      "grad_norm": 1.0850661993026733,
      "learning_rate": 4.813297930184042e-05,
      "loss": 0.6685,
      "step": 5115
    },
    {
      "epoch": 0.0793603059674447,
      "grad_norm": 0.6851856708526611,
      "learning_rate": 4.810100361140314e-05,
      "loss": 0.6621,
      "step": 5146
    },
    {
      "epoch": 0.0798383800997787,
      "grad_norm": 0.7950114607810974,
      "learning_rate": 4.8068767229279885e-05,
      "loss": 0.6642,
      "step": 5177
    },
    {
      "epoch": 0.0803164542321127,
      "grad_norm": 0.9632556438446045,
      "learning_rate": 4.8036270519253854e-05,
      "loss": 0.6628,
      "step": 5208
    },
    {
      "epoch": 0.0807945283644467,
      "grad_norm": 0.7066652178764343,
      "learning_rate": 4.8003513848046e-05,
      "loss": 0.6642,
      "step": 5239
    },
    {
      "epoch": 0.08127260249678071,
      "grad_norm": 0.7749651670455933,
      "learning_rate": 4.79704975853109e-05,
      "loss": 0.6633,
      "step": 5270
    },
    {
      "epoch": 0.08175067662911471,
      "grad_norm": 1.702022671699524,
      "learning_rate": 4.793722210363262e-05,
      "loss": 0.6745,
      "step": 5301
    },
    {
      "epoch": 0.08222875076144871,
      "grad_norm": 0.8134759068489075,
      "learning_rate": 4.7903687778520414e-05,
      "loss": 0.659,
      "step": 5332
    },
    {
      "epoch": 0.08270682489378273,
      "grad_norm": 0.8805097341537476,
      "learning_rate": 4.7869894988404593e-05,
      "loss": 0.6779,
      "step": 5363
    },
    {
      "epoch": 0.08318489902611673,
      "grad_norm": 0.9312698841094971,
      "learning_rate": 4.783584411463221e-05,
      "loss": 0.6634,
      "step": 5394
    },
    {
      "epoch": 0.08366297315845073,
      "grad_norm": 0.7013948559761047,
      "learning_rate": 4.780153554146274e-05,
      "loss": 0.6589,
      "step": 5425
    },
    {
      "epoch": 0.08414104729078474,
      "grad_norm": 0.8027428388595581,
      "learning_rate": 4.7766969656063766e-05,
      "loss": 0.6603,
      "step": 5456
    },
    {
      "epoch": 0.08461912142311874,
      "grad_norm": 1.0179306268692017,
      "learning_rate": 4.773214684850662e-05,
      "loss": 0.6595,
      "step": 5487
    },
    {
      "epoch": 0.08509719555545274,
      "grad_norm": 0.8512592911720276,
      "learning_rate": 4.769706751176193e-05,
      "loss": 0.6659,
      "step": 5518
    },
    {
      "epoch": 0.08557526968778675,
      "grad_norm": 0.8476304411888123,
      "learning_rate": 4.7661732041695264e-05,
      "loss": 0.6658,
      "step": 5549
    },
    {
      "epoch": 0.08605334382012075,
      "grad_norm": 0.771584153175354,
      "learning_rate": 4.762614083706258e-05,
      "loss": 0.6622,
      "step": 5580
    },
    {
      "epoch": 0.08653141795245475,
      "grad_norm": 0.8719794154167175,
      "learning_rate": 4.759029429950581e-05,
      "loss": 0.661,
      "step": 5611
    },
    {
      "epoch": 0.08700949208478877,
      "grad_norm": 0.9247443675994873,
      "learning_rate": 4.7554192833548235e-05,
      "loss": 0.6475,
      "step": 5642
    },
    {
      "epoch": 0.08748756621712277,
      "grad_norm": 0.9540857672691345,
      "learning_rate": 4.751783684659e-05,
      "loss": 0.662,
      "step": 5673
    },
    {
      "epoch": 0.08796564034945677,
      "grad_norm": 0.7939008474349976,
      "learning_rate": 4.748122674890348e-05,
      "loss": 0.6514,
      "step": 5704
    },
    {
      "epoch": 0.08844371448179077,
      "grad_norm": 0.613531768321991,
      "learning_rate": 4.7444362953628654e-05,
      "loss": 0.6513,
      "step": 5735
    },
    {
      "epoch": 0.08892178861412478,
      "grad_norm": 0.8084924817085266,
      "learning_rate": 4.7407245876768424e-05,
      "loss": 0.6465,
      "step": 5766
    },
    {
      "epoch": 0.08939986274645878,
      "grad_norm": 0.7709007263183594,
      "learning_rate": 4.736987593718397e-05,
      "loss": 0.6618,
      "step": 5797
    },
    {
      "epoch": 0.08987793687879278,
      "grad_norm": 0.6461811065673828,
      "learning_rate": 4.733225355658999e-05,
      "loss": 0.6516,
      "step": 5828
    },
    {
      "epoch": 0.0903560110111268,
      "grad_norm": 0.6879326105117798,
      "learning_rate": 4.7294379159549926e-05,
      "loss": 0.655,
      "step": 5859
    },
    {
      "epoch": 0.0908340851434608,
      "grad_norm": 0.7594075798988342,
      "learning_rate": 4.725625317347119e-05,
      "loss": 0.655,
      "step": 5890
    },
    {
      "epoch": 0.0913121592757948,
      "grad_norm": 0.774758517742157,
      "learning_rate": 4.7217876028600374e-05,
      "loss": 0.6697,
      "step": 5921
    },
    {
      "epoch": 0.09179023340812881,
      "grad_norm": 0.9164844155311584,
      "learning_rate": 4.717924815801832e-05,
      "loss": 0.6483,
      "step": 5952
    },
    {
      "epoch": 0.09226830754046281,
      "grad_norm": 0.792631208896637,
      "learning_rate": 4.714036999763532e-05,
      "loss": 0.6644,
      "step": 5983
    },
    {
      "epoch": 0.09274638167279681,
      "grad_norm": 0.7735174298286438,
      "learning_rate": 4.7101241986186116e-05,
      "loss": 0.6545,
      "step": 6014
    },
    {
      "epoch": 0.09322445580513082,
      "grad_norm": 0.725825309753418,
      "learning_rate": 4.7061864565225e-05,
      "loss": 0.6579,
      "step": 6045
    },
    {
      "epoch": 0.09370252993746482,
      "grad_norm": 0.7191294431686401,
      "learning_rate": 4.702223817912081e-05,
      "loss": 0.6509,
      "step": 6076
    }
  ],
  "logging_steps": 31,
  "max_steps": 30517,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3052,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.24270815620078e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}