{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 107670,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 1.9537303447723389,
      "learning_rate": 4.976780904615956e-05,
      "loss": 1.9668,
      "step": 500
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.9948451519012451,
      "learning_rate": 4.953561809231913e-05,
      "loss": 1.8978,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.6757797002792358,
      "learning_rate": 4.9303427138478686e-05,
      "loss": 1.8974,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.7021833658218384,
      "learning_rate": 4.9071236184638245e-05,
      "loss": 1.9052,
      "step": 2000
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.8648219108581543,
      "learning_rate": 4.883904523079781e-05,
      "loss": 1.896,
      "step": 2500
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.8240835666656494,
      "learning_rate": 4.860685427695737e-05,
      "loss": 1.868,
      "step": 3000
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.1527557373046875,
      "learning_rate": 4.837466332311693e-05,
      "loss": 1.8731,
      "step": 3500
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.9050869941711426,
      "learning_rate": 4.81424723692765e-05,
      "loss": 1.8807,
      "step": 4000
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.9118114709854126,
      "learning_rate": 4.791028141543606e-05,
      "loss": 1.8889,
      "step": 4500
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.4827492237091064,
      "learning_rate": 4.767809046159562e-05,
      "loss": 1.8786,
      "step": 5000
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.8363677263259888,
      "learning_rate": 4.7445899507755184e-05,
      "loss": 1.8741,
      "step": 5500
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.9690338373184204,
      "learning_rate": 4.721370855391474e-05,
      "loss": 1.8755,
      "step": 6000
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.6585566997528076,
      "learning_rate": 4.69815176000743e-05,
      "loss": 1.8575,
      "step": 6500
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.619232177734375,
      "learning_rate": 4.674932664623387e-05,
      "loss": 1.8638,
      "step": 7000
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.8518427610397339,
      "learning_rate": 4.6517135692393426e-05,
      "loss": 1.8653,
      "step": 7500
    },
    {
      "epoch": 0.22,
      "grad_norm": 2.0025551319122314,
      "learning_rate": 4.6284944738552985e-05,
      "loss": 1.8653,
      "step": 8000
    },
    {
      "epoch": 0.24,
      "grad_norm": 2.128351926803589,
      "learning_rate": 4.605275378471255e-05,
      "loss": 1.863,
      "step": 8500
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.0918049812316895,
      "learning_rate": 4.582056283087211e-05,
      "loss": 1.8472,
      "step": 9000
    },
    {
      "epoch": 0.26,
      "grad_norm": 2.1041295528411865,
      "learning_rate": 4.558837187703167e-05,
      "loss": 1.8523,
      "step": 9500
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.6074202060699463,
      "learning_rate": 4.5356180923191235e-05,
      "loss": 1.8683,
      "step": 10000
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.8500597476959229,
      "learning_rate": 4.5123989969350793e-05,
      "loss": 1.8622,
      "step": 10500
    },
    {
      "epoch": 0.31,
      "grad_norm": 2.6290550231933594,
      "learning_rate": 4.489179901551035e-05,
      "loss": 1.8539,
      "step": 11000
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.9424813985824585,
      "learning_rate": 4.4659608061669925e-05,
      "loss": 1.8579,
      "step": 11500
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.5146945714950562,
      "learning_rate": 4.4427417107829484e-05,
      "loss": 1.8541,
      "step": 12000
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.620976209640503,
      "learning_rate": 4.419522615398904e-05,
      "loss": 1.8601,
      "step": 12500
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.6728603839874268,
      "learning_rate": 4.396303520014861e-05,
      "loss": 1.8716,
      "step": 13000
    },
    {
      "epoch": 0.38,
      "grad_norm": 2.357908010482788,
      "learning_rate": 4.373084424630817e-05,
      "loss": 1.85,
      "step": 13500
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.9841961860656738,
      "learning_rate": 4.3498653292467726e-05,
      "loss": 1.8683,
      "step": 14000
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.6038274765014648,
      "learning_rate": 4.326646233862729e-05,
      "loss": 1.8481,
      "step": 14500
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.645585060119629,
      "learning_rate": 4.303427138478685e-05,
      "loss": 1.8512,
      "step": 15000
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.8110160827636719,
      "learning_rate": 4.280208043094641e-05,
      "loss": 1.8539,
      "step": 15500
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.6607145071029663,
      "learning_rate": 4.2569889477105975e-05,
      "loss": 1.8464,
      "step": 16000
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.4501959085464478,
      "learning_rate": 4.2337698523265534e-05,
      "loss": 1.8304,
      "step": 16500
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.8375539779663086,
      "learning_rate": 4.210550756942509e-05,
      "loss": 1.8413,
      "step": 17000
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.5968436002731323,
      "learning_rate": 4.187331661558466e-05,
      "loss": 1.8373,
      "step": 17500
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.3943761587142944,
      "learning_rate": 4.164112566174422e-05,
      "loss": 1.8509,
      "step": 18000
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.7238069772720337,
      "learning_rate": 4.140893470790378e-05,
      "loss": 1.8549,
      "step": 18500
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.6093735694885254,
      "learning_rate": 4.117674375406335e-05,
      "loss": 1.8272,
      "step": 19000
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.628990888595581,
      "learning_rate": 4.094455280022291e-05,
      "loss": 1.852,
      "step": 19500
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.7063369750976562,
      "learning_rate": 4.071236184638247e-05,
      "loss": 1.8506,
      "step": 20000
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.496973991394043,
      "learning_rate": 4.048017089254203e-05,
      "loss": 1.8382,
      "step": 20500
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.50234854221344,
      "learning_rate": 4.024797993870159e-05,
      "loss": 1.8335,
      "step": 21000
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.779697060585022,
      "learning_rate": 4.001578898486115e-05,
      "loss": 1.8407,
      "step": 21500
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.792860507965088,
      "learning_rate": 3.9783598031020716e-05,
      "loss": 1.8279,
      "step": 22000
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.714028239250183,
      "learning_rate": 3.9551407077180275e-05,
      "loss": 1.8265,
      "step": 22500
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.1110615730285645,
      "learning_rate": 3.9319216123339834e-05,
      "loss": 1.8312,
      "step": 23000
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.8647916316986084,
      "learning_rate": 3.90870251694994e-05,
      "loss": 1.8417,
      "step": 23500
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.669309377670288,
      "learning_rate": 3.885483421565896e-05,
      "loss": 1.8347,
      "step": 24000
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.6504507064819336,
      "learning_rate": 3.862264326181852e-05,
      "loss": 1.8283,
      "step": 24500
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.5461372137069702,
      "learning_rate": 3.839045230797808e-05,
      "loss": 1.8394,
      "step": 25000
    },
    {
      "epoch": 0.71,
      "grad_norm": 2.034350872039795,
      "learning_rate": 3.815826135413764e-05,
      "loss": 1.8326,
      "step": 25500
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.6590315103530884,
      "learning_rate": 3.792607040029721e-05,
      "loss": 1.8343,
      "step": 26000
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.9240669012069702,
      "learning_rate": 3.769387944645677e-05,
      "loss": 1.8601,
      "step": 26500
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.5366922616958618,
      "learning_rate": 3.746168849261633e-05,
      "loss": 1.8191,
      "step": 27000
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.8003100156784058,
      "learning_rate": 3.722949753877589e-05,
      "loss": 1.8313,
      "step": 27500
    },
    {
      "epoch": 0.78,
      "grad_norm": 3.656419277191162,
      "learning_rate": 3.6997306584935456e-05,
      "loss": 1.8192,
      "step": 28000
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.7153360843658447,
      "learning_rate": 3.6765115631095015e-05,
      "loss": 1.844,
      "step": 28500
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.5900826454162598,
      "learning_rate": 3.6532924677254574e-05,
      "loss": 1.8241,
      "step": 29000
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.9120334386825562,
      "learning_rate": 3.630073372341414e-05,
      "loss": 1.8367,
      "step": 29500
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.6516207456588745,
      "learning_rate": 3.60685427695737e-05,
      "loss": 1.8259,
      "step": 30000
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.7761846780776978,
      "learning_rate": 3.583635181573326e-05,
      "loss": 1.8322,
      "step": 30500
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.7233374118804932,
      "learning_rate": 3.560416086189282e-05,
      "loss": 1.8273,
      "step": 31000
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.6779149770736694,
      "learning_rate": 3.537196990805238e-05,
      "loss": 1.8281,
      "step": 31500
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.6603174209594727,
      "learning_rate": 3.513977895421194e-05,
      "loss": 1.8307,
      "step": 32000
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.6743112802505493,
      "learning_rate": 3.490758800037151e-05,
      "loss": 1.8214,
      "step": 32500
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.775214672088623,
      "learning_rate": 3.4675397046531066e-05,
      "loss": 1.8433,
      "step": 33000
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.6865200996398926,
      "learning_rate": 3.444320609269063e-05,
      "loss": 1.8342,
      "step": 33500
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.5064520835876465,
      "learning_rate": 3.42110151388502e-05,
      "loss": 1.8259,
      "step": 34000
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.599684476852417,
      "learning_rate": 3.3978824185009756e-05,
      "loss": 1.8261,
      "step": 34500
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.7616256475448608,
      "learning_rate": 3.3746633231169315e-05,
      "loss": 1.8191,
      "step": 35000
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.7617506980895996,
      "learning_rate": 3.351444227732888e-05,
      "loss": 1.8203,
      "step": 35500
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.03489351272583,
      "learning_rate": 3.328225132348844e-05,
      "loss": 1.825,
      "step": 36000
    },
    {
      "epoch": 1.02,
      "grad_norm": 1.5925586223602295,
      "learning_rate": 3.3050060369648e-05,
      "loss": 1.8058,
      "step": 36500
    },
    {
      "epoch": 1.03,
      "grad_norm": 2.1856117248535156,
      "learning_rate": 3.2817869415807564e-05,
      "loss": 1.8085,
      "step": 37000
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.5426925420761108,
      "learning_rate": 3.258567846196712e-05,
      "loss": 1.8058,
      "step": 37500
    },
    {
      "epoch": 1.06,
      "grad_norm": 2.0849246978759766,
      "learning_rate": 3.235348750812668e-05,
      "loss": 1.796,
      "step": 38000
    },
    {
      "epoch": 1.07,
      "grad_norm": 1.3791111707687378,
      "learning_rate": 3.212129655428625e-05,
      "loss": 1.8027,
      "step": 38500
    },
    {
      "epoch": 1.09,
      "grad_norm": 1.5735108852386475,
      "learning_rate": 3.1889105600445806e-05,
      "loss": 1.8188,
      "step": 39000
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.7609148025512695,
      "learning_rate": 3.1656914646605365e-05,
      "loss": 1.7931,
      "step": 39500
    },
    {
      "epoch": 1.11,
      "grad_norm": 1.814334511756897,
      "learning_rate": 3.142472369276493e-05,
      "loss": 1.8225,
      "step": 40000
    },
    {
      "epoch": 1.13,
      "grad_norm": 1.6874113082885742,
      "learning_rate": 3.119253273892449e-05,
      "loss": 1.8083,
      "step": 40500
    },
    {
      "epoch": 1.14,
      "grad_norm": 1.439292073249817,
      "learning_rate": 3.0960341785084055e-05,
      "loss": 1.82,
      "step": 41000
    },
    {
      "epoch": 1.16,
      "grad_norm": 1.608949065208435,
      "learning_rate": 3.072815083124362e-05,
      "loss": 1.7961,
      "step": 41500
    },
    {
      "epoch": 1.17,
      "grad_norm": 1.7770118713378906,
      "learning_rate": 3.049595987740318e-05,
      "loss": 1.8047,
      "step": 42000
    },
    {
      "epoch": 1.18,
      "grad_norm": 1.6586685180664062,
      "learning_rate": 3.0263768923562742e-05,
      "loss": 1.8114,
      "step": 42500
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.9770480394363403,
      "learning_rate": 3.00315779697223e-05,
      "loss": 1.8178,
      "step": 43000
    },
    {
      "epoch": 1.21,
      "grad_norm": 1.9781038761138916,
      "learning_rate": 2.9799387015881863e-05,
      "loss": 1.7902,
      "step": 43500
    },
    {
      "epoch": 1.23,
      "grad_norm": 1.5816311836242676,
      "learning_rate": 2.9567196062041426e-05,
      "loss": 1.8204,
      "step": 44000
    },
    {
      "epoch": 1.24,
      "grad_norm": 1.7043039798736572,
      "learning_rate": 2.9335005108200985e-05,
      "loss": 1.8009,
      "step": 44500
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.7163785696029663,
      "learning_rate": 2.9102814154360547e-05,
      "loss": 1.8097,
      "step": 45000
    },
    {
      "epoch": 1.27,
      "grad_norm": 1.7846918106079102,
      "learning_rate": 2.887062320052011e-05,
      "loss": 1.7983,
      "step": 45500
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.0754926204681396,
      "learning_rate": 2.8638432246679668e-05,
      "loss": 1.7871,
      "step": 46000
    },
    {
      "epoch": 1.3,
      "grad_norm": 2.4134902954101562,
      "learning_rate": 2.840624129283923e-05,
      "loss": 1.7982,
      "step": 46500
    },
    {
      "epoch": 1.31,
      "grad_norm": 1.5378786325454712,
      "learning_rate": 2.8174050338998793e-05,
      "loss": 1.8158,
      "step": 47000
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.5169446468353271,
      "learning_rate": 2.794185938515835e-05,
      "loss": 1.7911,
      "step": 47500
    },
    {
      "epoch": 1.34,
      "grad_norm": 1.5888478755950928,
      "learning_rate": 2.7709668431317914e-05,
      "loss": 1.7987,
      "step": 48000
    },
    {
      "epoch": 1.35,
      "grad_norm": 1.6548982858657837,
      "learning_rate": 2.7477477477477483e-05,
      "loss": 1.7959,
      "step": 48500
    },
    {
      "epoch": 1.37,
      "grad_norm": 1.9931424856185913,
      "learning_rate": 2.7245286523637042e-05,
      "loss": 1.8071,
      "step": 49000
    },
    {
      "epoch": 1.38,
      "grad_norm": 1.7344861030578613,
      "learning_rate": 2.7013095569796604e-05,
      "loss": 1.7918,
      "step": 49500
    },
    {
      "epoch": 1.39,
      "grad_norm": 1.836928367614746,
      "learning_rate": 2.6780904615956166e-05,
      "loss": 1.8107,
      "step": 50000
    },
    {
      "epoch": 1.41,
      "grad_norm": 1.8835091590881348,
      "learning_rate": 2.6548713662115725e-05,
      "loss": 1.8134,
      "step": 50500
    },
    {
      "epoch": 1.42,
      "grad_norm": 1.6774250268936157,
      "learning_rate": 2.6316522708275288e-05,
      "loss": 1.8117,
      "step": 51000
    },
    {
      "epoch": 1.43,
      "grad_norm": 1.9196052551269531,
      "learning_rate": 2.608433175443485e-05,
      "loss": 1.8253,
      "step": 51500
    },
    {
      "epoch": 1.45,
      "grad_norm": 2.208343505859375,
      "learning_rate": 2.585214080059441e-05,
      "loss": 1.8069,
      "step": 52000
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.866508960723877,
      "learning_rate": 2.561994984675397e-05,
      "loss": 1.801,
      "step": 52500
    },
    {
      "epoch": 1.48,
      "grad_norm": 1.6251405477523804,
      "learning_rate": 2.5387758892913533e-05,
      "loss": 1.7959,
      "step": 53000
    },
    {
      "epoch": 1.49,
      "grad_norm": 1.6582661867141724,
      "learning_rate": 2.5155567939073092e-05,
      "loss": 1.7879,
      "step": 53500
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.6403582096099854,
      "learning_rate": 2.4923376985232658e-05,
      "loss": 1.8034,
      "step": 54000
    },
    {
      "epoch": 1.52,
      "grad_norm": 1.930598258972168,
      "learning_rate": 2.469118603139222e-05,
      "loss": 1.7991,
      "step": 54500
    },
    {
      "epoch": 1.53,
      "grad_norm": 1.7759175300598145,
      "learning_rate": 2.445899507755178e-05,
      "loss": 1.8028,
      "step": 55000
    },
    {
      "epoch": 1.55,
      "grad_norm": 1.8325824737548828,
      "learning_rate": 2.422680412371134e-05,
      "loss": 1.7951,
      "step": 55500
    },
    {
      "epoch": 1.56,
      "grad_norm": 1.7427431344985962,
      "learning_rate": 2.3994613169870904e-05,
      "loss": 1.8051,
      "step": 56000
    },
    {
      "epoch": 1.57,
      "grad_norm": 1.6132415533065796,
      "learning_rate": 2.3762422216030463e-05,
      "loss": 1.8046,
      "step": 56500
    },
    {
      "epoch": 1.59,
      "grad_norm": 1.5871241092681885,
      "learning_rate": 2.3530231262190025e-05,
      "loss": 1.7974,
      "step": 57000
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.6785041093826294,
      "learning_rate": 2.329804030834959e-05,
      "loss": 1.824,
      "step": 57500
    },
    {
      "epoch": 1.62,
      "grad_norm": 1.5425368547439575,
      "learning_rate": 2.306584935450915e-05,
      "loss": 1.8088,
      "step": 58000
    },
    {
      "epoch": 1.63,
      "grad_norm": 2.0951876640319824,
      "learning_rate": 2.283365840066871e-05,
      "loss": 1.7957,
      "step": 58500
    },
    {
      "epoch": 1.64,
      "grad_norm": 1.5651832818984985,
      "learning_rate": 2.2601467446828274e-05,
      "loss": 1.7926,
      "step": 59000
    },
    {
      "epoch": 1.66,
      "grad_norm": 1.9217791557312012,
      "learning_rate": 2.2369276492987833e-05,
      "loss": 1.787,
      "step": 59500
    },
    {
      "epoch": 1.67,
      "grad_norm": 1.565430998802185,
      "learning_rate": 2.2137085539147395e-05,
      "loss": 1.8023,
      "step": 60000
    },
    {
      "epoch": 1.69,
      "grad_norm": 1.7779954671859741,
      "learning_rate": 2.1904894585306957e-05,
      "loss": 1.8024,
      "step": 60500
    },
    {
      "epoch": 1.7,
      "grad_norm": 1.7349501848220825,
      "learning_rate": 2.1672703631466516e-05,
      "loss": 1.7968,
      "step": 61000
    },
    {
      "epoch": 1.71,
      "grad_norm": 2.0634210109710693,
      "learning_rate": 2.1440512677626082e-05,
      "loss": 1.7895,
      "step": 61500
    },
    {
      "epoch": 1.73,
      "grad_norm": 1.7442530393600464,
      "learning_rate": 2.1208321723785644e-05,
      "loss": 1.7896,
      "step": 62000
    },
    {
      "epoch": 1.74,
      "grad_norm": 1.727230191230774,
      "learning_rate": 2.0976130769945203e-05,
      "loss": 1.8213,
      "step": 62500
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.626993179321289,
      "learning_rate": 2.0743939816104765e-05,
      "loss": 1.7983,
      "step": 63000
    },
    {
      "epoch": 1.77,
      "grad_norm": 1.9263286590576172,
      "learning_rate": 2.0511748862264328e-05,
      "loss": 1.8106,
      "step": 63500
    },
    {
      "epoch": 1.78,
      "grad_norm": 2.5916402339935303,
      "learning_rate": 2.0279557908423887e-05,
      "loss": 1.8211,
      "step": 64000
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.739984154701233,
      "learning_rate": 2.004736695458345e-05,
      "loss": 1.8093,
      "step": 64500
    },
    {
      "epoch": 1.81,
      "grad_norm": 1.8712440729141235,
      "learning_rate": 1.9815176000743015e-05,
      "loss": 1.7874,
      "step": 65000
    },
    {
      "epoch": 1.83,
      "grad_norm": 1.425011157989502,
      "learning_rate": 1.9582985046902573e-05,
      "loss": 1.813,
      "step": 65500
    },
    {
      "epoch": 1.84,
      "grad_norm": 1.7112998962402344,
      "learning_rate": 1.9350794093062136e-05,
      "loss": 1.7979,
      "step": 66000
    },
    {
      "epoch": 1.85,
      "grad_norm": 1.6773180961608887,
      "learning_rate": 1.9118603139221698e-05,
      "loss": 1.7976,
      "step": 66500
    },
    {
      "epoch": 1.87,
      "grad_norm": 1.7254269123077393,
      "learning_rate": 1.8886412185381257e-05,
      "loss": 1.8066,
      "step": 67000
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.6539784669876099,
      "learning_rate": 1.865422123154082e-05,
      "loss": 1.7846,
      "step": 67500
    },
    {
      "epoch": 1.89,
      "grad_norm": 1.9257705211639404,
      "learning_rate": 1.842203027770038e-05,
      "loss": 1.8066,
      "step": 68000
    },
    {
      "epoch": 1.91,
      "grad_norm": 2.245328903198242,
      "learning_rate": 1.8189839323859944e-05,
      "loss": 1.7972,
      "step": 68500
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.8069318532943726,
      "learning_rate": 1.7957648370019506e-05,
      "loss": 1.7978,
      "step": 69000
    },
    {
      "epoch": 1.94,
      "grad_norm": 1.8477637767791748,
      "learning_rate": 1.772545741617907e-05,
      "loss": 1.7919,
      "step": 69500
    },
    {
      "epoch": 1.95,
      "grad_norm": 1.6907987594604492,
      "learning_rate": 1.7493266462338627e-05,
      "loss": 1.8147,
      "step": 70000
    },
    {
      "epoch": 1.96,
      "grad_norm": 1.5092899799346924,
      "learning_rate": 1.726107550849819e-05,
      "loss": 1.7916,
      "step": 70500
    },
    {
      "epoch": 1.98,
      "grad_norm": 1.6707723140716553,
      "learning_rate": 1.7028884554657752e-05,
      "loss": 1.8101,
      "step": 71000
    },
    {
      "epoch": 1.99,
      "grad_norm": 1.978575587272644,
      "learning_rate": 1.679669360081731e-05,
      "loss": 1.7955,
      "step": 71500
    },
    {
      "epoch": 2.01,
      "grad_norm": 1.796865463256836,
      "learning_rate": 1.6564502646976873e-05,
      "loss": 1.8171,
      "step": 72000
    },
    {
      "epoch": 2.02,
      "grad_norm": 1.5833417177200317,
      "learning_rate": 1.633231169313644e-05,
      "loss": 1.7683,
      "step": 72500
    },
    {
      "epoch": 2.03,
      "grad_norm": 2.0611090660095215,
      "learning_rate": 1.6100120739295998e-05,
      "loss": 1.7818,
      "step": 73000
    },
    {
      "epoch": 2.05,
      "grad_norm": 1.7287518978118896,
      "learning_rate": 1.586792978545556e-05,
      "loss": 1.7965,
      "step": 73500
    },
    {
      "epoch": 2.06,
      "grad_norm": 1.7561732530593872,
      "learning_rate": 1.5635738831615122e-05,
      "loss": 1.795,
      "step": 74000
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.5913869142532349,
      "learning_rate": 1.540354787777468e-05,
      "loss": 1.7736,
      "step": 74500
    },
    {
      "epoch": 2.09,
      "grad_norm": 1.8258248567581177,
      "learning_rate": 1.5171356923934243e-05,
      "loss": 1.7874,
      "step": 75000
    },
    {
      "epoch": 2.1,
      "grad_norm": 1.7454122304916382,
      "learning_rate": 1.4939165970093804e-05,
      "loss": 1.781,
      "step": 75500
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.4468224048614502,
      "learning_rate": 1.470697501625337e-05,
      "loss": 1.7779,
      "step": 76000
    },
    {
      "epoch": 2.13,
      "grad_norm": 2.2896320819854736,
      "learning_rate": 1.447478406241293e-05,
      "loss": 1.8015,
      "step": 76500
    },
    {
      "epoch": 2.15,
      "grad_norm": 1.531069040298462,
      "learning_rate": 1.424259310857249e-05,
      "loss": 1.7946,
      "step": 77000
    },
    {
      "epoch": 2.16,
      "grad_norm": 2.1092686653137207,
      "learning_rate": 1.4010402154732053e-05,
      "loss": 1.7847,
      "step": 77500
    },
    {
      "epoch": 2.17,
      "grad_norm": 2.2306418418884277,
      "learning_rate": 1.3778211200891614e-05,
      "loss": 1.8005,
      "step": 78000
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.438249111175537,
      "learning_rate": 1.3546020247051174e-05,
      "loss": 1.7836,
      "step": 78500
    },
    {
      "epoch": 2.2,
      "grad_norm": 1.8369108438491821,
      "learning_rate": 1.3313829293210736e-05,
      "loss": 1.7908,
      "step": 79000
    },
    {
      "epoch": 2.22,
      "grad_norm": 1.5445431470870972,
      "learning_rate": 1.30816383393703e-05,
      "loss": 1.7918,
      "step": 79500
    },
    {
      "epoch": 2.23,
      "grad_norm": 1.8314502239227295,
      "learning_rate": 1.2849447385529861e-05,
      "loss": 1.7947,
      "step": 80000
    },
    {
      "epoch": 2.24,
      "grad_norm": 1.5848190784454346,
      "learning_rate": 1.2617256431689423e-05,
      "loss": 1.7758,
      "step": 80500
    },
    {
      "epoch": 2.26,
      "grad_norm": 1.9737972021102905,
      "learning_rate": 1.2385065477848984e-05,
      "loss": 1.7833,
      "step": 81000
    },
    {
      "epoch": 2.27,
      "grad_norm": 1.9529500007629395,
      "learning_rate": 1.2152874524008545e-05,
      "loss": 1.7848,
      "step": 81500
    },
    {
      "epoch": 2.28,
      "grad_norm": 1.7836568355560303,
      "learning_rate": 1.1920683570168107e-05,
      "loss": 1.7671,
      "step": 82000
    },
    {
      "epoch": 2.3,
      "grad_norm": 1.957573652267456,
      "learning_rate": 1.1688492616327669e-05,
      "loss": 1.8016,
      "step": 82500
    },
    {
      "epoch": 2.31,
      "grad_norm": 1.9392001628875732,
      "learning_rate": 1.145630166248723e-05,
      "loss": 1.7987,
      "step": 83000
    },
    {
      "epoch": 2.33,
      "grad_norm": 1.8034446239471436,
      "learning_rate": 1.1224110708646792e-05,
      "loss": 1.7702,
      "step": 83500
    },
    {
      "epoch": 2.34,
      "grad_norm": 2.152960777282715,
      "learning_rate": 1.0991919754806353e-05,
      "loss": 1.7809,
      "step": 84000
    },
    {
      "epoch": 2.35,
      "grad_norm": 2.0862069129943848,
      "learning_rate": 1.0759728800965915e-05,
      "loss": 1.7798,
      "step": 84500
    },
    {
      "epoch": 2.37,
      "grad_norm": 1.8202825784683228,
      "learning_rate": 1.0527537847125477e-05,
      "loss": 1.7818,
      "step": 85000
    },
    {
      "epoch": 2.38,
      "grad_norm": 1.7600897550582886,
      "learning_rate": 1.0295346893285038e-05,
      "loss": 1.7777,
      "step": 85500
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.1568124294281006,
      "learning_rate": 1.00631559394446e-05,
      "loss": 1.7878,
      "step": 86000
    },
    {
      "epoch": 2.41,
      "grad_norm": 1.488659381866455,
      "learning_rate": 9.830964985604162e-06,
      "loss": 1.7871,
      "step": 86500
    },
    {
      "epoch": 2.42,
      "grad_norm": 1.5254462957382202,
      "learning_rate": 9.598774031763723e-06,
      "loss": 1.7701,
      "step": 87000
    },
    {
      "epoch": 2.44,
      "grad_norm": 1.5069713592529297,
      "learning_rate": 9.366583077923283e-06,
      "loss": 1.7826,
      "step": 87500
    },
    {
      "epoch": 2.45,
      "grad_norm": 1.986422061920166,
      "learning_rate": 9.134392124082847e-06,
      "loss": 1.7964,
      "step": 88000
    },
    {
      "epoch": 2.47,
      "grad_norm": 2.4251198768615723,
      "learning_rate": 8.902201170242408e-06,
      "loss": 1.7736,
      "step": 88500
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.583479642868042,
      "learning_rate": 8.670010216401969e-06,
      "loss": 1.7759,
      "step": 89000
    },
    {
      "epoch": 2.49,
      "grad_norm": 2.4297444820404053,
      "learning_rate": 8.437819262561531e-06,
      "loss": 1.7759,
      "step": 89500
    },
    {
      "epoch": 2.51,
      "grad_norm": 1.8693283796310425,
      "learning_rate": 8.205628308721093e-06,
      "loss": 1.7736,
      "step": 90000
    },
    {
      "epoch": 2.52,
      "grad_norm": 1.630678653717041,
      "learning_rate": 7.973437354880654e-06,
      "loss": 1.7768,
      "step": 90500
    },
    {
      "epoch": 2.54,
      "grad_norm": 1.6369069814682007,
      "learning_rate": 7.741246401040216e-06,
      "loss": 1.7699,
      "step": 91000
    },
    {
      "epoch": 2.55,
      "grad_norm": 1.8540914058685303,
      "learning_rate": 7.509055447199777e-06,
      "loss": 1.7691,
      "step": 91500
    },
    {
      "epoch": 2.56,
      "grad_norm": 1.8826764822006226,
      "learning_rate": 7.27686449335934e-06,
      "loss": 1.7866,
      "step": 92000
    },
    {
      "epoch": 2.58,
      "grad_norm": 1.901553750038147,
      "learning_rate": 7.0446735395189e-06,
      "loss": 1.7818,
      "step": 92500
    },
    {
      "epoch": 2.59,
      "grad_norm": 1.9629470109939575,
      "learning_rate": 6.812482585678462e-06,
      "loss": 1.784,
      "step": 93000
    },
    {
      "epoch": 2.61,
      "grad_norm": 2.1246750354766846,
      "learning_rate": 6.580291631838025e-06,
      "loss": 1.7887,
      "step": 93500
    },
    {
      "epoch": 2.62,
      "grad_norm": 2.196052074432373,
      "learning_rate": 6.3481006779975855e-06,
      "loss": 1.7844,
      "step": 94000
    },
    {
      "epoch": 2.63,
      "grad_norm": 1.5874074697494507,
      "learning_rate": 6.115909724157147e-06,
      "loss": 1.7629,
      "step": 94500
    },
    {
      "epoch": 2.65,
      "grad_norm": 1.921108603477478,
      "learning_rate": 5.883718770316709e-06,
      "loss": 1.7698,
      "step": 95000
    },
    {
      "epoch": 2.66,
      "grad_norm": 1.6300297975540161,
      "learning_rate": 5.65152781647627e-06,
      "loss": 1.7853,
      "step": 95500
    },
    {
      "epoch": 2.67,
      "grad_norm": 1.78380286693573,
      "learning_rate": 5.419336862635832e-06,
      "loss": 1.7793,
      "step": 96000
    },
    {
      "epoch": 2.69,
      "grad_norm": 1.6569774150848389,
      "learning_rate": 5.1871459087953935e-06,
      "loss": 1.7808,
      "step": 96500
    },
    {
      "epoch": 2.7,
      "grad_norm": 1.647446632385254,
      "learning_rate": 4.954954954954955e-06,
      "loss": 1.7691,
      "step": 97000
    },
    {
      "epoch": 2.72,
      "grad_norm": 1.3676789999008179,
      "learning_rate": 4.722764001114516e-06,
      "loss": 1.7847,
      "step": 97500
    },
    {
      "epoch": 2.73,
      "grad_norm": 1.8430696725845337,
      "learning_rate": 4.490573047274079e-06,
      "loss": 1.7975,
      "step": 98000
    },
    {
      "epoch": 2.74,
      "grad_norm": 2.3150343894958496,
      "learning_rate": 4.25838209343364e-06,
      "loss": 1.7717,
      "step": 98500
    },
    {
      "epoch": 2.76,
      "grad_norm": 1.6771624088287354,
      "learning_rate": 4.0261911395932016e-06,
      "loss": 1.7868,
      "step": 99000
    },
    {
      "epoch": 2.77,
      "grad_norm": 1.7548917531967163,
      "learning_rate": 3.7940001857527634e-06,
      "loss": 1.7876,
      "step": 99500
    },
    {
      "epoch": 2.79,
      "grad_norm": 1.9142273664474487,
      "learning_rate": 3.561809231912325e-06,
      "loss": 1.7723,
      "step": 100000
    },
    {
      "epoch": 2.8,
      "grad_norm": 2.0858819484710693,
      "learning_rate": 3.3296182780718867e-06,
      "loss": 1.7777,
      "step": 100500
    },
    {
      "epoch": 2.81,
      "grad_norm": 1.5094643831253052,
      "learning_rate": 3.097427324231448e-06,
      "loss": 1.7848,
      "step": 101000
    },
    {
      "epoch": 2.83,
      "grad_norm": 1.6694867610931396,
      "learning_rate": 2.86523637039101e-06,
      "loss": 1.7849,
      "step": 101500
    },
    {
      "epoch": 2.84,
      "grad_norm": 1.7994331121444702,
      "learning_rate": 2.6330454165505714e-06,
      "loss": 1.7929,
      "step": 102000
    },
    {
      "epoch": 2.86,
      "grad_norm": 1.817747950553894,
      "learning_rate": 2.400854462710133e-06,
      "loss": 1.7875,
      "step": 102500
    },
    {
      "epoch": 2.87,
      "grad_norm": 1.7881470918655396,
      "learning_rate": 2.1686635088696947e-06,
      "loss": 1.7861,
      "step": 103000
    },
    {
      "epoch": 2.88,
      "grad_norm": 1.7034624814987183,
      "learning_rate": 1.936472555029256e-06,
      "loss": 1.7788,
      "step": 103500
    },
    {
      "epoch": 2.9,
      "grad_norm": 1.6703755855560303,
      "learning_rate": 1.7042816011888178e-06,
      "loss": 1.7901,
      "step": 104000
    },
    {
      "epoch": 2.91,
      "grad_norm": 1.8089648485183716,
      "learning_rate": 1.4720906473483793e-06,
      "loss": 1.7705,
      "step": 104500
    },
    {
      "epoch": 2.93,
      "grad_norm": 2.2493557929992676,
      "learning_rate": 1.239899693507941e-06,
      "loss": 1.7795,
      "step": 105000
    },
    {
      "epoch": 2.94,
      "grad_norm": 1.8172557353973389,
      "learning_rate": 1.0077087396675028e-06,
      "loss": 1.7897,
      "step": 105500
    },
    {
      "epoch": 2.95,
      "grad_norm": 2.0329835414886475,
      "learning_rate": 7.755177858270642e-07,
      "loss": 1.784,
      "step": 106000
    },
    {
      "epoch": 2.97,
      "grad_norm": 1.859191656112671,
      "learning_rate": 5.433268319866259e-07,
      "loss": 1.775,
      "step": 106500
    },
    {
      "epoch": 2.98,
      "grad_norm": 2.273327589035034,
      "learning_rate": 3.1113587814618745e-07,
      "loss": 1.7793,
      "step": 107000
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7774237394332886,
      "learning_rate": 7.894492430574905e-08,
      "loss": 1.7776,
      "step": 107500
    },
    {
      "epoch": 3.0,
      "step": 107670,
      "total_flos": 2.3281764491516314e+17,
      "train_loss": 1.8120383115867458,
      "train_runtime": 16851.3759,
      "train_samples_per_second": 51.114,
      "train_steps_per_second": 6.389
    }
  ],
  "logging_steps": 500,
  "max_steps": 107670,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.3281764491516314e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}