{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04706716941559293,
  "eval_steps": 500,
  "global_step": 3052,
  "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
    }
  ],
  "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": 2.12135407810039e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}