{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 879,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011376564277588168,
      "grad_norm": 0.35927149653434753,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 2.8383045196533203,
      "step": 10
    },
    {
      "epoch": 0.022753128555176336,
      "grad_norm": 0.4452897012233734,
      "learning_rate": 8.636363636363637e-05,
      "loss": 2.5093990325927735,
      "step": 20
    },
    {
      "epoch": 0.034129692832764506,
      "grad_norm": 0.4380996823310852,
      "learning_rate": 0.0001318181818181818,
      "loss": 2.066328239440918,
      "step": 30
    },
    {
      "epoch": 0.04550625711035267,
      "grad_norm": 0.4204699695110321,
      "learning_rate": 0.00017727272727272728,
      "loss": 1.6020610809326172,
      "step": 40
    },
    {
      "epoch": 0.05688282138794084,
      "grad_norm": 0.2761755585670471,
      "learning_rate": 0.00019880239520958084,
      "loss": 1.3702651977539062,
      "step": 50
    },
    {
      "epoch": 0.06825938566552901,
      "grad_norm": 0.314470112323761,
      "learning_rate": 0.00019640718562874253,
      "loss": 1.421883487701416,
      "step": 60
    },
    {
      "epoch": 0.07963594994311718,
      "grad_norm": 0.3572886288166046,
      "learning_rate": 0.00019401197604790419,
      "loss": 1.384176540374756,
      "step": 70
    },
    {
      "epoch": 0.09101251422070535,
      "grad_norm": 0.32515978813171387,
      "learning_rate": 0.00019161676646706587,
      "loss": 1.352308177947998,
      "step": 80
    },
    {
      "epoch": 0.10238907849829351,
      "grad_norm": 0.2531631886959076,
      "learning_rate": 0.00018922155688622756,
      "loss": 1.407022762298584,
      "step": 90
    },
    {
      "epoch": 0.11376564277588168,
      "grad_norm": 0.30639082193374634,
      "learning_rate": 0.00018682634730538924,
      "loss": 1.3959112167358398,
      "step": 100
    },
    {
      "epoch": 0.12514220705346984,
      "grad_norm": 0.1899048238992691,
      "learning_rate": 0.00018443113772455093,
      "loss": 1.2709525108337403,
      "step": 110
    },
    {
      "epoch": 0.13651877133105803,
      "grad_norm": 0.28593116998672485,
      "learning_rate": 0.00018203592814371256,
      "loss": 1.3549932479858398,
      "step": 120
    },
    {
      "epoch": 0.14789533560864618,
      "grad_norm": 0.3405962884426117,
      "learning_rate": 0.00017964071856287425,
      "loss": 1.3086001396179199,
      "step": 130
    },
    {
      "epoch": 0.15927189988623436,
      "grad_norm": 0.333600252866745,
      "learning_rate": 0.00017724550898203594,
      "loss": 1.421626377105713,
      "step": 140
    },
    {
      "epoch": 0.17064846416382254,
      "grad_norm": 0.31500062346458435,
      "learning_rate": 0.00017485029940119762,
      "loss": 1.38295259475708,
      "step": 150
    },
    {
      "epoch": 0.1820250284414107,
      "grad_norm": 0.32324257493019104,
      "learning_rate": 0.00017245508982035928,
      "loss": 1.4174630165100097,
      "step": 160
    },
    {
      "epoch": 0.19340159271899887,
      "grad_norm": 0.3555000126361847,
      "learning_rate": 0.00017005988023952097,
      "loss": 1.331777000427246,
      "step": 170
    },
    {
      "epoch": 0.20477815699658702,
      "grad_norm": 0.3577157258987427,
      "learning_rate": 0.00016766467065868263,
      "loss": 1.3180593490600585,
      "step": 180
    },
    {
      "epoch": 0.2161547212741752,
      "grad_norm": 0.36902204155921936,
      "learning_rate": 0.00016526946107784431,
      "loss": 1.238968276977539,
      "step": 190
    },
    {
      "epoch": 0.22753128555176336,
      "grad_norm": 0.2762733995914459,
      "learning_rate": 0.000162874251497006,
      "loss": 1.2129551887512207,
      "step": 200
    },
    {
      "epoch": 0.23890784982935154,
      "grad_norm": 0.3807738423347473,
      "learning_rate": 0.00016047904191616766,
      "loss": 1.4056357383728026,
      "step": 210
    },
    {
      "epoch": 0.2502844141069397,
      "grad_norm": 0.3804709315299988,
      "learning_rate": 0.00015808383233532935,
      "loss": 1.2330207824707031,
      "step": 220
    },
    {
      "epoch": 0.2616609783845279,
      "grad_norm": 0.4553723931312561,
      "learning_rate": 0.00015568862275449103,
      "loss": 1.187899684906006,
      "step": 230
    },
    {
      "epoch": 0.27303754266211605,
      "grad_norm": 0.3560260236263275,
      "learning_rate": 0.00015329341317365272,
      "loss": 1.34483642578125,
      "step": 240
    },
    {
      "epoch": 0.2844141069397042,
      "grad_norm": 0.3588465750217438,
      "learning_rate": 0.00015089820359281438,
      "loss": 1.2554708480834962,
      "step": 250
    },
    {
      "epoch": 0.29579067121729236,
      "grad_norm": 0.34966403245925903,
      "learning_rate": 0.00014850299401197604,
      "loss": 1.204217529296875,
      "step": 260
    },
    {
      "epoch": 0.30716723549488056,
      "grad_norm": 0.3833954334259033,
      "learning_rate": 0.00014610778443113772,
      "loss": 1.1533174514770508,
      "step": 270
    },
    {
      "epoch": 0.3185437997724687,
      "grad_norm": 0.4410889744758606,
      "learning_rate": 0.0001437125748502994,
      "loss": 1.2482272148132325,
      "step": 280
    },
    {
      "epoch": 0.32992036405005687,
      "grad_norm": 0.3203088343143463,
      "learning_rate": 0.0001413173652694611,
      "loss": 1.2887246131896972,
      "step": 290
    },
    {
      "epoch": 0.3412969283276451,
      "grad_norm": 0.4120391607284546,
      "learning_rate": 0.00013892215568862276,
      "loss": 1.2156929969787598,
      "step": 300
    },
    {
      "epoch": 0.35267349260523323,
      "grad_norm": 0.3317709267139435,
      "learning_rate": 0.00013652694610778444,
      "loss": 1.2633889198303223,
      "step": 310
    },
    {
      "epoch": 0.3640500568828214,
      "grad_norm": 0.3894944489002228,
      "learning_rate": 0.0001341317365269461,
      "loss": 1.2147921562194823,
      "step": 320
    },
    {
      "epoch": 0.37542662116040953,
      "grad_norm": 0.2914019823074341,
      "learning_rate": 0.0001317365269461078,
      "loss": 1.2801948547363282,
      "step": 330
    },
    {
      "epoch": 0.38680318543799774,
      "grad_norm": 0.2825303375720978,
      "learning_rate": 0.00012934131736526947,
      "loss": 1.2948213577270509,
      "step": 340
    },
    {
      "epoch": 0.3981797497155859,
      "grad_norm": 0.36970818042755127,
      "learning_rate": 0.00012694610778443113,
      "loss": 1.2043416976928711,
      "step": 350
    },
    {
      "epoch": 0.40955631399317405,
      "grad_norm": 0.39104145765304565,
      "learning_rate": 0.00012455089820359282,
      "loss": 1.2681941032409667,
      "step": 360
    },
    {
      "epoch": 0.42093287827076226,
      "grad_norm": 0.31589847803115845,
      "learning_rate": 0.0001221556886227545,
      "loss": 1.2457168579101563,
      "step": 370
    },
    {
      "epoch": 0.4323094425483504,
      "grad_norm": 0.47189992666244507,
      "learning_rate": 0.00011976047904191617,
      "loss": 1.3064229965209961,
      "step": 380
    },
    {
      "epoch": 0.44368600682593856,
      "grad_norm": 0.278676301240921,
      "learning_rate": 0.00011736526946107784,
      "loss": 1.2180593490600586,
      "step": 390
    },
    {
      "epoch": 0.4550625711035267,
      "grad_norm": 0.3712811768054962,
      "learning_rate": 0.00011497005988023953,
      "loss": 1.2530301094055176,
      "step": 400
    },
    {
      "epoch": 0.4664391353811149,
      "grad_norm": 0.4130960702896118,
      "learning_rate": 0.0001125748502994012,
      "loss": 1.2469879150390626,
      "step": 410
    },
    {
      "epoch": 0.4778156996587031,
      "grad_norm": 0.3994705379009247,
      "learning_rate": 0.00011017964071856288,
      "loss": 1.3015870094299316,
      "step": 420
    },
    {
      "epoch": 0.4891922639362912,
      "grad_norm": 0.49127182364463806,
      "learning_rate": 0.00010778443113772456,
      "loss": 1.2392463684082031,
      "step": 430
    },
    {
      "epoch": 0.5005688282138794,
      "grad_norm": 0.38700762391090393,
      "learning_rate": 0.00010538922155688624,
      "loss": 1.1767354965209962,
      "step": 440
    },
    {
      "epoch": 0.5119453924914675,
      "grad_norm": 0.41579461097717285,
      "learning_rate": 0.0001029940119760479,
      "loss": 1.1897143363952636,
      "step": 450
    },
    {
      "epoch": 0.5233219567690558,
      "grad_norm": 0.3779870867729187,
      "learning_rate": 0.00010059880239520958,
      "loss": 1.2195447921752929,
      "step": 460
    },
    {
      "epoch": 0.534698521046644,
      "grad_norm": 0.3646884560585022,
      "learning_rate": 9.820359281437126e-05,
      "loss": 1.2423855781555175,
      "step": 470
    },
    {
      "epoch": 0.5460750853242321,
      "grad_norm": 0.39075958728790283,
      "learning_rate": 9.580838323353294e-05,
      "loss": 1.2689632415771483,
      "step": 480
    },
    {
      "epoch": 0.5574516496018203,
      "grad_norm": 0.37718430161476135,
      "learning_rate": 9.341317365269462e-05,
      "loss": 1.2134543418884278,
      "step": 490
    },
    {
      "epoch": 0.5688282138794084,
      "grad_norm": 0.4014438986778259,
      "learning_rate": 9.101796407185628e-05,
      "loss": 1.1316455841064452,
      "step": 500
    },
    {
      "epoch": 0.5802047781569966,
      "grad_norm": 0.45317408442497253,
      "learning_rate": 8.862275449101797e-05,
      "loss": 1.2185492515563965,
      "step": 510
    },
    {
      "epoch": 0.5915813424345847,
      "grad_norm": 0.3339143395423889,
      "learning_rate": 8.622754491017964e-05,
      "loss": 1.1707771301269532,
      "step": 520
    },
    {
      "epoch": 0.602957906712173,
      "grad_norm": 0.4250375032424927,
      "learning_rate": 8.383233532934131e-05,
      "loss": 1.1593905448913575,
      "step": 530
    },
    {
      "epoch": 0.6143344709897611,
      "grad_norm": 0.445677250623703,
      "learning_rate": 8.1437125748503e-05,
      "loss": 1.2060506820678711,
      "step": 540
    },
    {
      "epoch": 0.6257110352673493,
      "grad_norm": 0.41856470704078674,
      "learning_rate": 7.904191616766467e-05,
      "loss": 1.3159299850463868,
      "step": 550
    },
    {
      "epoch": 0.6370875995449374,
      "grad_norm": 0.3425860106945038,
      "learning_rate": 7.664670658682636e-05,
      "loss": 1.0997207641601563,
      "step": 560
    },
    {
      "epoch": 0.6484641638225256,
      "grad_norm": 0.3445124924182892,
      "learning_rate": 7.425149700598802e-05,
      "loss": 1.2845489501953125,
      "step": 570
    },
    {
      "epoch": 0.6598407281001137,
      "grad_norm": 0.45617416501045227,
      "learning_rate": 7.18562874251497e-05,
      "loss": 1.1566729545593262,
      "step": 580
    },
    {
      "epoch": 0.6712172923777019,
      "grad_norm": 0.35912832617759705,
      "learning_rate": 6.946107784431138e-05,
      "loss": 1.2122529029846192,
      "step": 590
    },
    {
      "epoch": 0.6825938566552902,
      "grad_norm": 0.5134853720664978,
      "learning_rate": 6.706586826347305e-05,
      "loss": 1.2636856079101562,
      "step": 600
    },
    {
      "epoch": 0.6939704209328783,
      "grad_norm": 0.3869934678077698,
      "learning_rate": 6.467065868263474e-05,
      "loss": 1.2048263549804688,
      "step": 610
    },
    {
      "epoch": 0.7053469852104665,
      "grad_norm": 0.4428758919239044,
      "learning_rate": 6.227544910179641e-05,
      "loss": 1.2033488273620605,
      "step": 620
    },
    {
      "epoch": 0.7167235494880546,
      "grad_norm": 0.3854043483734131,
      "learning_rate": 5.988023952095808e-05,
      "loss": 1.203934669494629,
      "step": 630
    },
    {
      "epoch": 0.7281001137656428,
      "grad_norm": 0.4749031960964203,
      "learning_rate": 5.748502994011976e-05,
      "loss": 1.245382022857666,
      "step": 640
    },
    {
      "epoch": 0.7394766780432309,
      "grad_norm": 0.3372991681098938,
      "learning_rate": 5.508982035928144e-05,
      "loss": 1.1963462829589844,
      "step": 650
    },
    {
      "epoch": 0.7508532423208191,
      "grad_norm": 0.4767475724220276,
      "learning_rate": 5.269461077844312e-05,
      "loss": 1.200768280029297,
      "step": 660
    },
    {
      "epoch": 0.7622298065984073,
      "grad_norm": 0.3248017728328705,
      "learning_rate": 5.029940119760479e-05,
      "loss": 1.2015400886535645,
      "step": 670
    },
    {
      "epoch": 0.7736063708759955,
      "grad_norm": 0.46483004093170166,
      "learning_rate": 4.790419161676647e-05,
      "loss": 1.1695308685302734,
      "step": 680
    },
    {
      "epoch": 0.7849829351535836,
      "grad_norm": 0.4324643909931183,
      "learning_rate": 4.550898203592814e-05,
      "loss": 1.1258634567260741,
      "step": 690
    },
    {
      "epoch": 0.7963594994311718,
      "grad_norm": 0.3934484124183655,
      "learning_rate": 4.311377245508982e-05,
      "loss": 1.2569397926330566,
      "step": 700
    },
    {
      "epoch": 0.8077360637087599,
      "grad_norm": 0.38264092803001404,
      "learning_rate": 4.07185628742515e-05,
      "loss": 1.2250053405761718,
      "step": 710
    },
    {
      "epoch": 0.8191126279863481,
      "grad_norm": 0.5181489586830139,
      "learning_rate": 3.832335329341318e-05,
      "loss": 1.232970905303955,
      "step": 720
    },
    {
      "epoch": 0.8304891922639362,
      "grad_norm": 0.45371928811073303,
      "learning_rate": 3.592814371257485e-05,
      "loss": 1.11167631149292,
      "step": 730
    },
    {
      "epoch": 0.8418657565415245,
      "grad_norm": 0.3426970839500427,
      "learning_rate": 3.3532934131736525e-05,
      "loss": 1.1899587631225585,
      "step": 740
    },
    {
      "epoch": 0.8532423208191127,
      "grad_norm": 0.47472548484802246,
      "learning_rate": 3.1137724550898205e-05,
      "loss": 1.3199144363403321,
      "step": 750
    },
    {
      "epoch": 0.8646188850967008,
      "grad_norm": 0.4320537745952606,
      "learning_rate": 2.874251497005988e-05,
      "loss": 1.2297654151916504,
      "step": 760
    },
    {
      "epoch": 0.875995449374289,
      "grad_norm": 0.5028583407402039,
      "learning_rate": 2.634730538922156e-05,
      "loss": 1.0911432266235352,
      "step": 770
    },
    {
      "epoch": 0.8873720136518771,
      "grad_norm": 0.5217500925064087,
      "learning_rate": 2.3952095808383234e-05,
      "loss": 1.280848217010498,
      "step": 780
    },
    {
      "epoch": 0.8987485779294653,
      "grad_norm": 0.3845643103122711,
      "learning_rate": 2.155688622754491e-05,
      "loss": 1.2265941619873046,
      "step": 790
    },
    {
      "epoch": 0.9101251422070534,
      "grad_norm": 0.4036272168159485,
      "learning_rate": 1.916167664670659e-05,
      "loss": 1.157244873046875,
      "step": 800
    },
    {
      "epoch": 0.9215017064846417,
      "grad_norm": 0.3768911361694336,
      "learning_rate": 1.6766467065868263e-05,
      "loss": 1.1470327377319336,
      "step": 810
    },
    {
      "epoch": 0.9328782707622298,
      "grad_norm": 0.4626820981502533,
      "learning_rate": 1.437125748502994e-05,
      "loss": 1.1281915664672852,
      "step": 820
    },
    {
      "epoch": 0.944254835039818,
      "grad_norm": 0.42136433720588684,
      "learning_rate": 1.1976047904191617e-05,
      "loss": 1.166923999786377,
      "step": 830
    },
    {
      "epoch": 0.9556313993174061,
      "grad_norm": 0.3808249533176422,
      "learning_rate": 9.580838323353295e-06,
      "loss": 1.1876595497131348,
      "step": 840
    },
    {
      "epoch": 0.9670079635949943,
      "grad_norm": 0.4225604832172394,
      "learning_rate": 7.18562874251497e-06,
      "loss": 1.1546753883361816,
      "step": 850
    },
    {
      "epoch": 0.9783845278725825,
      "grad_norm": 0.5485788583755493,
      "learning_rate": 4.7904191616766475e-06,
      "loss": 1.161636734008789,
      "step": 860
    },
    {
      "epoch": 0.9897610921501706,
      "grad_norm": 0.5680049061775208,
      "learning_rate": 2.3952095808383237e-06,
      "loss": 1.146053409576416,
      "step": 870
    }
  ],
  "logging_steps": 10,
  "max_steps": 879,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.002458153363866e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}