{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3175863437872172,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003969829297340214,
      "grad_norm": 0.6961175799369812,
      "learning_rate": 0.00016,
      "loss": 3.2075271606445312,
      "step": 10
    },
    {
      "epoch": 0.007939658594680429,
      "grad_norm": 0.9305199384689331,
      "learning_rate": 0.00019978799522989268,
      "loss": 3.1885648727416993,
      "step": 20
    },
    {
      "epoch": 0.011909487892020643,
      "grad_norm": 0.8452768325805664,
      "learning_rate": 0.00019952298926725852,
      "loss": 2.9959283828735352,
      "step": 30
    },
    {
      "epoch": 0.015879317189360857,
      "grad_norm": 0.9384715557098389,
      "learning_rate": 0.00019925798330462438,
      "loss": 3.132890510559082,
      "step": 40
    },
    {
      "epoch": 0.019849146486701073,
      "grad_norm": 0.9872943162918091,
      "learning_rate": 0.0001989929773419902,
      "loss": 3.1314294815063475,
      "step": 50
    },
    {
      "epoch": 0.023818975784041286,
      "grad_norm": 0.8298355937004089,
      "learning_rate": 0.00019872797137935604,
      "loss": 3.24124755859375,
      "step": 60
    },
    {
      "epoch": 0.027788805081381502,
      "grad_norm": 0.8308970928192139,
      "learning_rate": 0.00019846296541672188,
      "loss": 3.0996198654174805,
      "step": 70
    },
    {
      "epoch": 0.031758634378721715,
      "grad_norm": 0.8442180156707764,
      "learning_rate": 0.0001981979594540877,
      "loss": 3.0475082397460938,
      "step": 80
    },
    {
      "epoch": 0.03572846367606193,
      "grad_norm": 0.9131914377212524,
      "learning_rate": 0.00019793295349145357,
      "loss": 3.1756013870239257,
      "step": 90
    },
    {
      "epoch": 0.03969829297340215,
      "grad_norm": 0.9973925352096558,
      "learning_rate": 0.0001976679475288194,
      "loss": 3.159317398071289,
      "step": 100
    },
    {
      "epoch": 0.043668122270742356,
      "grad_norm": 0.9906535148620605,
      "learning_rate": 0.00019740294156618524,
      "loss": 3.086680603027344,
      "step": 110
    },
    {
      "epoch": 0.04763795156808257,
      "grad_norm": 0.8675328493118286,
      "learning_rate": 0.0001971379356035511,
      "loss": 3.0809303283691407,
      "step": 120
    },
    {
      "epoch": 0.05160778086542279,
      "grad_norm": 1.2756576538085938,
      "learning_rate": 0.00019687292964091694,
      "loss": 2.965633010864258,
      "step": 130
    },
    {
      "epoch": 0.055577610162763004,
      "grad_norm": 0.8540228605270386,
      "learning_rate": 0.00019660792367828277,
      "loss": 3.11167049407959,
      "step": 140
    },
    {
      "epoch": 0.05954743946010321,
      "grad_norm": 0.8471305966377258,
      "learning_rate": 0.0001963429177156486,
      "loss": 2.9493082046508787,
      "step": 150
    },
    {
      "epoch": 0.06351726875744343,
      "grad_norm": 1.0690556764602661,
      "learning_rate": 0.00019607791175301444,
      "loss": 3.1130550384521483,
      "step": 160
    },
    {
      "epoch": 0.06748709805478365,
      "grad_norm": 0.9682918787002563,
      "learning_rate": 0.0001958129057903803,
      "loss": 3.041396713256836,
      "step": 170
    },
    {
      "epoch": 0.07145692735212386,
      "grad_norm": 0.9328762292861938,
      "learning_rate": 0.00019554789982774613,
      "loss": 3.1088594436645507,
      "step": 180
    },
    {
      "epoch": 0.07542675664946408,
      "grad_norm": 0.981307327747345,
      "learning_rate": 0.000195282893865112,
      "loss": 3.1146469116210938,
      "step": 190
    },
    {
      "epoch": 0.0793965859468043,
      "grad_norm": 1.0752034187316895,
      "learning_rate": 0.00019501788790247783,
      "loss": 3.0602563858032226,
      "step": 200
    },
    {
      "epoch": 0.0833664152441445,
      "grad_norm": 0.8543508052825928,
      "learning_rate": 0.00019475288193984363,
      "loss": 2.989186477661133,
      "step": 210
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 0.9234327077865601,
      "learning_rate": 0.0001944878759772095,
      "loss": 3.0583696365356445,
      "step": 220
    },
    {
      "epoch": 0.09130607383882493,
      "grad_norm": 0.8820871710777283,
      "learning_rate": 0.00019422287001457533,
      "loss": 2.868353271484375,
      "step": 230
    },
    {
      "epoch": 0.09527590313616514,
      "grad_norm": 0.9947519898414612,
      "learning_rate": 0.0001939578640519412,
      "loss": 3.110881042480469,
      "step": 240
    },
    {
      "epoch": 0.09924573243350536,
      "grad_norm": 0.8357694745063782,
      "learning_rate": 0.00019369285808930702,
      "loss": 3.01332950592041,
      "step": 250
    },
    {
      "epoch": 0.10321556173084558,
      "grad_norm": 0.9128127694129944,
      "learning_rate": 0.00019342785212667288,
      "loss": 3.149305725097656,
      "step": 260
    },
    {
      "epoch": 0.10718539102818579,
      "grad_norm": 0.9448281526565552,
      "learning_rate": 0.0001931628461640387,
      "loss": 3.172308921813965,
      "step": 270
    },
    {
      "epoch": 0.11115522032552601,
      "grad_norm": 1.0875459909439087,
      "learning_rate": 0.00019289784020140452,
      "loss": 3.1815589904785155,
      "step": 280
    },
    {
      "epoch": 0.11512504962286621,
      "grad_norm": 0.9254504442214966,
      "learning_rate": 0.00019263283423877038,
      "loss": 3.1059280395507813,
      "step": 290
    },
    {
      "epoch": 0.11909487892020643,
      "grad_norm": 0.9273567795753479,
      "learning_rate": 0.00019236782827613622,
      "loss": 3.063690757751465,
      "step": 300
    },
    {
      "epoch": 0.12306470821754664,
      "grad_norm": 0.9300341010093689,
      "learning_rate": 0.00019210282231350208,
      "loss": 2.989412307739258,
      "step": 310
    },
    {
      "epoch": 0.12703453751488686,
      "grad_norm": 1.092647910118103,
      "learning_rate": 0.0001918378163508679,
      "loss": 2.9342714309692384,
      "step": 320
    },
    {
      "epoch": 0.13100436681222707,
      "grad_norm": 0.7696720361709595,
      "learning_rate": 0.00019157281038823375,
      "loss": 2.966893768310547,
      "step": 330
    },
    {
      "epoch": 0.1349741961095673,
      "grad_norm": 0.9847505688667297,
      "learning_rate": 0.00019130780442559958,
      "loss": 3.054021644592285,
      "step": 340
    },
    {
      "epoch": 0.1389440254069075,
      "grad_norm": 1.0354719161987305,
      "learning_rate": 0.00019104279846296541,
      "loss": 2.9900562286376955,
      "step": 350
    },
    {
      "epoch": 0.14291385470424772,
      "grad_norm": 0.8888474106788635,
      "learning_rate": 0.00019077779250033128,
      "loss": 3.1933818817138673,
      "step": 360
    },
    {
      "epoch": 0.14688368400158794,
      "grad_norm": 1.0046141147613525,
      "learning_rate": 0.0001905127865376971,
      "loss": 2.920476722717285,
      "step": 370
    },
    {
      "epoch": 0.15085351329892815,
      "grad_norm": 1.039939522743225,
      "learning_rate": 0.00019024778057506294,
      "loss": 3.1360284805297853,
      "step": 380
    },
    {
      "epoch": 0.15482334259626837,
      "grad_norm": 0.9551829099655151,
      "learning_rate": 0.0001899827746124288,
      "loss": 3.144388198852539,
      "step": 390
    },
    {
      "epoch": 0.1587931718936086,
      "grad_norm": 0.9663012027740479,
      "learning_rate": 0.00018971776864979464,
      "loss": 2.9875814437866213,
      "step": 400
    },
    {
      "epoch": 0.1627630011909488,
      "grad_norm": 0.9962781071662903,
      "learning_rate": 0.00018945276268716047,
      "loss": 3.0062061309814454,
      "step": 410
    },
    {
      "epoch": 0.166732830488289,
      "grad_norm": 1.001230001449585,
      "learning_rate": 0.0001891877567245263,
      "loss": 3.0834712982177734,
      "step": 420
    },
    {
      "epoch": 0.1707026597856292,
      "grad_norm": 0.9189774990081787,
      "learning_rate": 0.00018892275076189214,
      "loss": 2.885240936279297,
      "step": 430
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 1.0268958806991577,
      "learning_rate": 0.000188657744799258,
      "loss": 3.1581113815307615,
      "step": 440
    },
    {
      "epoch": 0.17864231838030964,
      "grad_norm": 0.9994209408760071,
      "learning_rate": 0.00018839273883662383,
      "loss": 2.8793590545654295,
      "step": 450
    },
    {
      "epoch": 0.18261214767764986,
      "grad_norm": 1.0613411664962769,
      "learning_rate": 0.0001881277328739897,
      "loss": 3.029997444152832,
      "step": 460
    },
    {
      "epoch": 0.18658197697499007,
      "grad_norm": 1.0501508712768555,
      "learning_rate": 0.0001878627269113555,
      "loss": 3.150674819946289,
      "step": 470
    },
    {
      "epoch": 0.1905518062723303,
      "grad_norm": 1.0706281661987305,
      "learning_rate": 0.00018759772094872134,
      "loss": 3.0236751556396486,
      "step": 480
    },
    {
      "epoch": 0.1945216355696705,
      "grad_norm": 0.856622040271759,
      "learning_rate": 0.0001873327149860872,
      "loss": 2.9095502853393556,
      "step": 490
    },
    {
      "epoch": 0.19849146486701072,
      "grad_norm": 0.9528838396072388,
      "learning_rate": 0.00018706770902345303,
      "loss": 3.001302146911621,
      "step": 500
    },
    {
      "epoch": 0.20246129416435094,
      "grad_norm": 1.0344288349151611,
      "learning_rate": 0.0001868027030608189,
      "loss": 3.106768035888672,
      "step": 510
    },
    {
      "epoch": 0.20643112346169115,
      "grad_norm": 0.9366422891616821,
      "learning_rate": 0.00018653769709818473,
      "loss": 2.99255428314209,
      "step": 520
    },
    {
      "epoch": 0.21040095275903137,
      "grad_norm": 0.9982316493988037,
      "learning_rate": 0.00018627269113555056,
      "loss": 2.904929351806641,
      "step": 530
    },
    {
      "epoch": 0.21437078205637158,
      "grad_norm": 1.0310651063919067,
      "learning_rate": 0.0001860076851729164,
      "loss": 3.076841926574707,
      "step": 540
    },
    {
      "epoch": 0.2183406113537118,
      "grad_norm": 1.015830397605896,
      "learning_rate": 0.00018574267921028223,
      "loss": 2.995553398132324,
      "step": 550
    },
    {
      "epoch": 0.22231044065105202,
      "grad_norm": 0.9116207957267761,
      "learning_rate": 0.0001854776732476481,
      "loss": 3.0907325744628906,
      "step": 560
    },
    {
      "epoch": 0.22628026994839223,
      "grad_norm": 0.983268141746521,
      "learning_rate": 0.00018521266728501392,
      "loss": 2.9128732681274414,
      "step": 570
    },
    {
      "epoch": 0.23025009924573242,
      "grad_norm": 1.0083118677139282,
      "learning_rate": 0.00018494766132237978,
      "loss": 3.06164665222168,
      "step": 580
    },
    {
      "epoch": 0.23421992854307264,
      "grad_norm": 0.9371793270111084,
      "learning_rate": 0.00018468265535974562,
      "loss": 3.110069465637207,
      "step": 590
    },
    {
      "epoch": 0.23818975784041285,
      "grad_norm": 0.8907871842384338,
      "learning_rate": 0.00018441764939711142,
      "loss": 2.9918779373168944,
      "step": 600
    },
    {
      "epoch": 0.24215958713775307,
      "grad_norm": 1.2298108339309692,
      "learning_rate": 0.00018415264343447728,
      "loss": 2.995768737792969,
      "step": 610
    },
    {
      "epoch": 0.24612941643509328,
      "grad_norm": 1.1198155879974365,
      "learning_rate": 0.00018388763747184312,
      "loss": 2.905741500854492,
      "step": 620
    },
    {
      "epoch": 0.25009924573243353,
      "grad_norm": 0.9270941019058228,
      "learning_rate": 0.00018362263150920898,
      "loss": 3.0602294921875,
      "step": 630
    },
    {
      "epoch": 0.2540690750297737,
      "grad_norm": 0.907201886177063,
      "learning_rate": 0.0001833576255465748,
      "loss": 3.0065471649169924,
      "step": 640
    },
    {
      "epoch": 0.25803890432711396,
      "grad_norm": 1.0519545078277588,
      "learning_rate": 0.00018309261958394065,
      "loss": 3.029597282409668,
      "step": 650
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 0.8725332617759705,
      "learning_rate": 0.00018282761362130648,
      "loss": 2.8936578750610353,
      "step": 660
    },
    {
      "epoch": 0.26597856292179434,
      "grad_norm": 1.040444254875183,
      "learning_rate": 0.0001825626076586723,
      "loss": 3.081193542480469,
      "step": 670
    },
    {
      "epoch": 0.2699483922191346,
      "grad_norm": 0.9259696006774902,
      "learning_rate": 0.00018229760169603817,
      "loss": 2.9740297317504885,
      "step": 680
    },
    {
      "epoch": 0.27391822151647477,
      "grad_norm": 1.0812491178512573,
      "learning_rate": 0.000182032595733404,
      "loss": 3.0157501220703127,
      "step": 690
    },
    {
      "epoch": 0.277888050813815,
      "grad_norm": 1.0642049312591553,
      "learning_rate": 0.00018176758977076984,
      "loss": 2.996814727783203,
      "step": 700
    },
    {
      "epoch": 0.2818578801111552,
      "grad_norm": 1.0878177881240845,
      "learning_rate": 0.0001815025838081357,
      "loss": 3.0396562576293946,
      "step": 710
    },
    {
      "epoch": 0.28582770940849545,
      "grad_norm": 0.8735718131065369,
      "learning_rate": 0.00018123757784550154,
      "loss": 2.8770545959472655,
      "step": 720
    },
    {
      "epoch": 0.28979753870583563,
      "grad_norm": 0.9658878445625305,
      "learning_rate": 0.00018097257188286737,
      "loss": 3.050862121582031,
      "step": 730
    },
    {
      "epoch": 0.2937673680031759,
      "grad_norm": 0.958960771560669,
      "learning_rate": 0.0001807075659202332,
      "loss": 3.0131216049194336,
      "step": 740
    },
    {
      "epoch": 0.29773719730051607,
      "grad_norm": 1.0989668369293213,
      "learning_rate": 0.00018044255995759904,
      "loss": 3.0553775787353517,
      "step": 750
    },
    {
      "epoch": 0.3017070265978563,
      "grad_norm": 0.9090871214866638,
      "learning_rate": 0.0001801775539949649,
      "loss": 2.9768255233764647,
      "step": 760
    },
    {
      "epoch": 0.3056768558951965,
      "grad_norm": 0.9842050671577454,
      "learning_rate": 0.00017991254803233073,
      "loss": 3.028487205505371,
      "step": 770
    },
    {
      "epoch": 0.30964668519253674,
      "grad_norm": 1.1661285161972046,
      "learning_rate": 0.0001796475420696966,
      "loss": 2.9407962799072265,
      "step": 780
    },
    {
      "epoch": 0.31361651448987693,
      "grad_norm": 1.0115314722061157,
      "learning_rate": 0.00017938253610706243,
      "loss": 3.02266845703125,
      "step": 790
    },
    {
      "epoch": 0.3175863437872172,
      "grad_norm": 1.1729583740234375,
      "learning_rate": 0.00017911753014442823,
      "loss": 2.9814245223999025,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 7557,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.547644300288e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}