{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9997049277072882,
  "eval_steps": 500,
  "global_step": 847,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011802891708468575,
      "grad_norm": NaN,
      "learning_rate": 4.11764705882353e-06,
      "loss": 2.4846,
      "step": 10
    },
    {
      "epoch": 0.02360578341693715,
      "grad_norm": 1.4208085536956787,
      "learning_rate": 9.411764705882354e-06,
      "loss": 2.1584,
      "step": 20
    },
    {
      "epoch": 0.03540867512540572,
      "grad_norm": 0.5537272095680237,
      "learning_rate": 1.5294117647058826e-05,
      "loss": 1.6811,
      "step": 30
    },
    {
      "epoch": 0.0472115668338743,
      "grad_norm": 0.7016017436981201,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.4406,
      "step": 40
    },
    {
      "epoch": 0.05901445854234287,
      "grad_norm": 1.1232593059539795,
      "learning_rate": 2.7058823529411766e-05,
      "loss": 1.3102,
      "step": 50
    },
    {
      "epoch": 0.07081735025081144,
      "grad_norm": 2.9730782508850098,
      "learning_rate": 3.294117647058824e-05,
      "loss": 1.2155,
      "step": 60
    },
    {
      "epoch": 0.08262024195928003,
      "grad_norm": 0.692528247833252,
      "learning_rate": 3.882352941176471e-05,
      "loss": 1.1449,
      "step": 70
    },
    {
      "epoch": 0.0944231336677486,
      "grad_norm": 1.3414469957351685,
      "learning_rate": 4.470588235294118e-05,
      "loss": 1.1908,
      "step": 80
    },
    {
      "epoch": 0.10622602537621717,
      "grad_norm": 0.6828320622444153,
      "learning_rate": 4.999978752922572e-05,
      "loss": 1.1663,
      "step": 90
    },
    {
      "epoch": 0.11802891708468574,
      "grad_norm": NaN,
      "learning_rate": 4.998640308387074e-05,
      "loss": 1.1033,
      "step": 100
    },
    {
      "epoch": 0.1298318087931543,
      "grad_norm": 9.297845840454102,
      "learning_rate": 4.993119095936937e-05,
      "loss": 1.1636,
      "step": 110
    },
    {
      "epoch": 0.14163470050162288,
      "grad_norm": 0.8314323425292969,
      "learning_rate": 4.983360758155341e-05,
      "loss": 1.1268,
      "step": 120
    },
    {
      "epoch": 0.15343759221009148,
      "grad_norm": 0.6411977410316467,
      "learning_rate": 4.9693818796090927e-05,
      "loss": 1.1321,
      "step": 130
    },
    {
      "epoch": 0.16524048391856005,
      "grad_norm": 0.5500069856643677,
      "learning_rate": 4.951206217791564e-05,
      "loss": 1.0142,
      "step": 140
    },
    {
      "epoch": 0.17704337562702863,
      "grad_norm": 0.6950828433036804,
      "learning_rate": 4.9288646627461645e-05,
      "loss": 1.1114,
      "step": 150
    },
    {
      "epoch": 0.1888462673354972,
      "grad_norm": 0.6412365436553955,
      "learning_rate": 4.902395184567859e-05,
      "loss": 1.0839,
      "step": 160
    },
    {
      "epoch": 0.20064915904396577,
      "grad_norm": 0.6320505738258362,
      "learning_rate": 4.871842768871928e-05,
      "loss": 1.0705,
      "step": 170
    },
    {
      "epoch": 0.21245205075243434,
      "grad_norm": 0.7705304622650146,
      "learning_rate": 4.837259340339665e-05,
      "loss": 1.0312,
      "step": 180
    },
    {
      "epoch": 0.2242549424609029,
      "grad_norm": 0.6497272849082947,
      "learning_rate": 4.7987036744709326e-05,
      "loss": 1.0162,
      "step": 190
    },
    {
      "epoch": 0.23605783416937148,
      "grad_norm": 2.37109112739563,
      "learning_rate": 4.756241297693566e-05,
      "loss": 1.0297,
      "step": 200
    },
    {
      "epoch": 0.24786072587784008,
      "grad_norm": 0.523530125617981,
      "learning_rate": 4.7099443759993837e-05,
      "loss": 1.0039,
      "step": 210
    },
    {
      "epoch": 0.2596636175863086,
      "grad_norm": 0.8198627233505249,
      "learning_rate": 4.659891592296071e-05,
      "loss": 0.9934,
      "step": 220
    },
    {
      "epoch": 0.2714665092947772,
      "grad_norm": 0.7993373870849609,
      "learning_rate": 4.606168012683394e-05,
      "loss": 1.0378,
      "step": 230
    },
    {
      "epoch": 0.28326940100324577,
      "grad_norm": 0.7412521243095398,
      "learning_rate": 4.548864941880988e-05,
      "loss": 1.007,
      "step": 240
    },
    {
      "epoch": 0.29507229271171437,
      "grad_norm": 0.715391993522644,
      "learning_rate": 4.488079768053447e-05,
      "loss": 0.987,
      "step": 250
    },
    {
      "epoch": 0.30687518442018297,
      "grad_norm": 1.2131056785583496,
      "learning_rate": 4.423915797296425e-05,
      "loss": 0.9728,
      "step": 260
    },
    {
      "epoch": 0.3186780761286515,
      "grad_norm": 0.7467273473739624,
      "learning_rate": 4.3564820780650496e-05,
      "loss": 0.9608,
      "step": 270
    },
    {
      "epoch": 0.3304809678371201,
      "grad_norm": 0.8544695377349854,
      "learning_rate": 4.285893215843037e-05,
      "loss": 0.9591,
      "step": 280
    },
    {
      "epoch": 0.34228385954558865,
      "grad_norm": 0.7751792669296265,
      "learning_rate": 4.2122691783674786e-05,
      "loss": 0.9466,
      "step": 290
    },
    {
      "epoch": 0.35408675125405725,
      "grad_norm": 2.504579544067383,
      "learning_rate": 4.1357350917403314e-05,
      "loss": 0.9384,
      "step": 300
    },
    {
      "epoch": 0.3658896429625258,
      "grad_norm": 22.522701263427734,
      "learning_rate": 4.056421027773126e-05,
      "loss": 0.9517,
      "step": 310
    },
    {
      "epoch": 0.3776925346709944,
      "grad_norm": 0.9187076091766357,
      "learning_rate": 3.974461782926299e-05,
      "loss": 0.9449,
      "step": 320
    },
    {
      "epoch": 0.389495426379463,
      "grad_norm": 1.2791095972061157,
      "learning_rate": 3.889996649218852e-05,
      "loss": 0.9171,
      "step": 330
    },
    {
      "epoch": 0.40129831808793154,
      "grad_norm": 0.7749762535095215,
      "learning_rate": 3.8031691774976904e-05,
      "loss": 0.9611,
      "step": 340
    },
    {
      "epoch": 0.41310120979640014,
      "grad_norm": 0.917222797870636,
      "learning_rate": 3.714126933468959e-05,
      "loss": 0.9678,
      "step": 350
    },
    {
      "epoch": 0.4249041015048687,
      "grad_norm": 0.552499532699585,
      "learning_rate": 3.623021246906018e-05,
      "loss": 0.9134,
      "step": 360
    },
    {
      "epoch": 0.4367069932133373,
      "grad_norm": 0.5541794896125793,
      "learning_rate": 3.530006954460274e-05,
      "loss": 0.928,
      "step": 370
    },
    {
      "epoch": 0.4485098849218058,
      "grad_norm": 0.5857645869255066,
      "learning_rate": 3.435242136511984e-05,
      "loss": 0.8963,
      "step": 380
    },
    {
      "epoch": 0.4603127766302744,
      "grad_norm": 0.5237164497375488,
      "learning_rate": 3.338887848508242e-05,
      "loss": 0.8931,
      "step": 390
    },
    {
      "epoch": 0.47211566833874297,
      "grad_norm": 0.49927598237991333,
      "learning_rate": 3.241107847244769e-05,
      "loss": 0.9113,
      "step": 400
    },
    {
      "epoch": 0.48391856004721157,
      "grad_norm": 1.1223820447921753,
      "learning_rate": 3.14206831255667e-05,
      "loss": 0.9172,
      "step": 410
    },
    {
      "epoch": 0.49572145175568016,
      "grad_norm": 0.7306515574455261,
      "learning_rate": 3.041937564891183e-05,
      "loss": 0.903,
      "step": 420
    },
    {
      "epoch": 0.5075243434641488,
      "grad_norm": 1.0228462219238281,
      "learning_rate": 2.940885779242387e-05,
      "loss": 0.8676,
      "step": 430
    },
    {
      "epoch": 0.5193272351726173,
      "grad_norm": 0.5814535021781921,
      "learning_rate": 2.8390846959340638e-05,
      "loss": 0.8709,
      "step": 440
    },
    {
      "epoch": 0.5311301268810859,
      "grad_norm": 0.7466275095939636,
      "learning_rate": 2.736707328742234e-05,
      "loss": 0.8659,
      "step": 450
    },
    {
      "epoch": 0.5429330185895545,
      "grad_norm": 0.7288652062416077,
      "learning_rate": 2.633927670853425e-05,
      "loss": 0.8683,
      "step": 460
    },
    {
      "epoch": 0.554735910298023,
      "grad_norm": 0.5865510106086731,
      "learning_rate": 2.5309203991584073e-05,
      "loss": 0.871,
      "step": 470
    },
    {
      "epoch": 0.5665388020064915,
      "grad_norm": 0.5332498550415039,
      "learning_rate": 2.4278605773839548e-05,
      "loss": 0.8574,
      "step": 480
    },
    {
      "epoch": 0.5783416937149601,
      "grad_norm": 0.634554922580719,
      "learning_rate": 2.3249233585671636e-05,
      "loss": 0.9529,
      "step": 490
    },
    {
      "epoch": 0.5901445854234287,
      "grad_norm": 0.655619740486145,
      "learning_rate": 2.2222836873779888e-05,
      "loss": 0.8546,
      "step": 500
    },
    {
      "epoch": 0.6019474771318973,
      "grad_norm": 0.5780109167098999,
      "learning_rate": 2.1201160027959077e-05,
      "loss": 0.8452,
      "step": 510
    },
    {
      "epoch": 0.6137503688403659,
      "grad_norm": 0.49844804406166077,
      "learning_rate": 2.0185939416460133e-05,
      "loss": 0.876,
      "step": 520
    },
    {
      "epoch": 0.6255532605488344,
      "grad_norm": 0.430317223072052,
      "learning_rate": 1.917890043498397e-05,
      "loss": 0.8406,
      "step": 530
    },
    {
      "epoch": 0.637356152257303,
      "grad_norm": 0.4516479969024658,
      "learning_rate": 1.8181754574323446e-05,
      "loss": 0.8226,
      "step": 540
    },
    {
      "epoch": 0.6491590439657716,
      "grad_norm": 0.5004287362098694,
      "learning_rate": 1.7196196511637084e-05,
      "loss": 0.9068,
      "step": 550
    },
    {
      "epoch": 0.6609619356742402,
      "grad_norm": 0.6133776307106018,
      "learning_rate": 1.6223901230298062e-05,
      "loss": 0.8361,
      "step": 560
    },
    {
      "epoch": 0.6727648273827088,
      "grad_norm": 1.207897663116455,
      "learning_rate": 1.5266521173213306e-05,
      "loss": 0.8515,
      "step": 570
    },
    {
      "epoch": 0.6845677190911773,
      "grad_norm": 0.5756068825721741,
      "learning_rate": 1.432568343445077e-05,
      "loss": 0.8553,
      "step": 580
    },
    {
      "epoch": 0.6963706107996459,
      "grad_norm": 0.5454249382019043,
      "learning_rate": 1.340298699394777e-05,
      "loss": 0.8731,
      "step": 590
    },
    {
      "epoch": 0.7081735025081145,
      "grad_norm": 0.527680516242981,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.8545,
      "step": 600
    },
    {
      "epoch": 0.7199763942165831,
      "grad_norm": 0.6664750576019287,
      "learning_rate": 1.1618257104149898e-05,
      "loss": 0.8259,
      "step": 610
    },
    {
      "epoch": 0.7317792859250516,
      "grad_norm": 0.7168521881103516,
      "learning_rate": 1.0759256853003578e-05,
      "loss": 0.856,
      "step": 620
    },
    {
      "epoch": 0.7435821776335202,
      "grad_norm": 0.4886401891708374,
      "learning_rate": 9.92445914140912e-06,
      "loss": 0.8448,
      "step": 630
    },
    {
      "epoch": 0.7553850693419888,
      "grad_norm": 0.541182279586792,
      "learning_rate": 9.115282731324696e-06,
      "loss": 0.8142,
      "step": 640
    },
    {
      "epoch": 0.7671879610504574,
      "grad_norm": 0.5412532091140747,
      "learning_rate": 8.333102840593015e-06,
      "loss": 0.8607,
      "step": 650
    },
    {
      "epoch": 0.778990852758926,
      "grad_norm": 0.603594183921814,
      "learning_rate": 7.579248805720396e-06,
      "loss": 0.8283,
      "step": 660
    },
    {
      "epoch": 0.7907937444673945,
      "grad_norm": 0.7654862403869629,
      "learning_rate": 6.855001822632278e-06,
      "loss": 0.8514,
      "step": 670
    },
    {
      "epoch": 0.8025966361758631,
      "grad_norm": 0.5184491872787476,
      "learning_rate": 6.161592769245114e-06,
      "loss": 0.8125,
      "step": 680
    },
    {
      "epoch": 0.8143995278843317,
      "grad_norm": 0.5151306986808777,
      "learning_rate": 5.500200113555071e-06,
      "loss": 0.8122,
      "step": 690
    },
    {
      "epoch": 0.8262024195928003,
      "grad_norm": 0.5323730111122131,
      "learning_rate": 4.871947910798818e-06,
      "loss": 0.7771,
      "step": 700
    },
    {
      "epoch": 0.8380053113012688,
      "grad_norm": 0.6055124402046204,
      "learning_rate": 4.277903893090407e-06,
      "loss": 0.8132,
      "step": 710
    },
    {
      "epoch": 0.8498082030097374,
      "grad_norm": 0.5266196727752686,
      "learning_rate": 3.7190776547807447e-06,
      "loss": 0.8095,
      "step": 720
    },
    {
      "epoch": 0.861611094718206,
      "grad_norm": 0.5904248356819153,
      "learning_rate": 3.1964189366239377e-06,
      "loss": 0.8285,
      "step": 730
    },
    {
      "epoch": 0.8734139864266746,
      "grad_norm": 0.6103527545928955,
      "learning_rate": 2.7108160116663893e-06,
      "loss": 0.8297,
      "step": 740
    },
    {
      "epoch": 0.8852168781351432,
      "grad_norm": 0.5870690941810608,
      "learning_rate": 2.2630941756020512e-06,
      "loss": 0.8621,
      "step": 750
    },
    {
      "epoch": 0.8970197698436116,
      "grad_norm": 0.49599605798721313,
      "learning_rate": 1.8540143441593854e-06,
      "loss": 0.8191,
      "step": 760
    },
    {
      "epoch": 0.9088226615520802,
      "grad_norm": 0.5189609527587891,
      "learning_rate": 1.4842717599039047e-06,
      "loss": 0.8048,
      "step": 770
    },
    {
      "epoch": 0.9206255532605488,
      "grad_norm": 0.485893577337265,
      "learning_rate": 1.1544948106540775e-06,
      "loss": 0.782,
      "step": 780
    },
    {
      "epoch": 0.9324284449690174,
      "grad_norm": 0.5677834749221802,
      "learning_rate": 8.652439615187163e-07,
      "loss": 0.8249,
      "step": 790
    },
    {
      "epoch": 0.9442313366774859,
      "grad_norm": 0.5319679379463196,
      "learning_rate": 6.170108023709348e-07,
      "loss": 0.817,
      "step": 800
    },
    {
      "epoch": 0.9560342283859545,
      "grad_norm": 0.5445159673690796,
      "learning_rate": 4.1021721237745337e-07,
      "loss": 0.8029,
      "step": 810
    },
    {
      "epoch": 0.9678371200944231,
      "grad_norm": 0.618567943572998,
      "learning_rate": 2.452146430032165e-07,
      "loss": 0.8493,
      "step": 820
    },
    {
      "epoch": 0.9796400118028917,
      "grad_norm": 0.5149559378623962,
      "learning_rate": 1.2228352070983719e-07,
      "loss": 0.8134,
      "step": 830
    },
    {
      "epoch": 0.9914429035113603,
      "grad_norm": 0.4901800751686096,
      "learning_rate": 4.1632770363012056e-08,
      "loss": 0.8336,
      "step": 840
    },
    {
      "epoch": 0.9997049277072882,
      "step": 847,
      "total_flos": 1.1591373314404123e+19,
      "train_loss": 0.973909290228149,
      "train_runtime": 71632.8605,
      "train_samples_per_second": 0.378,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 10,
  "max_steps": 847,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1591373314404123e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}