{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1090,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001834862385321101,
      "grad_norm": 0.5285698626925894,
      "learning_rate": 1.8315018315018315e-07,
      "loss": 2.1792,
      "step": 1
    },
    {
      "epoch": 0.01834862385321101,
      "grad_norm": 0.5570483132219919,
      "learning_rate": 1.8315018315018316e-06,
      "loss": 2.1303,
      "step": 10
    },
    {
      "epoch": 0.03669724770642202,
      "grad_norm": 0.43928839139908665,
      "learning_rate": 3.663003663003663e-06,
      "loss": 2.143,
      "step": 20
    },
    {
      "epoch": 0.05504587155963303,
      "grad_norm": 0.4259147884901134,
      "learning_rate": 5.494505494505494e-06,
      "loss": 2.0498,
      "step": 30
    },
    {
      "epoch": 0.07339449541284404,
      "grad_norm": 0.3256334236213354,
      "learning_rate": 7.326007326007326e-06,
      "loss": 2.1005,
      "step": 40
    },
    {
      "epoch": 0.09174311926605505,
      "grad_norm": 0.22687147012199685,
      "learning_rate": 9.157509157509158e-06,
      "loss": 2.032,
      "step": 50
    },
    {
      "epoch": 0.11009174311926606,
      "grad_norm": 0.20407900243790855,
      "learning_rate": 1.0989010989010989e-05,
      "loss": 2.0265,
      "step": 60
    },
    {
      "epoch": 0.12844036697247707,
      "grad_norm": 0.17272636847518857,
      "learning_rate": 1.282051282051282e-05,
      "loss": 2.0593,
      "step": 70
    },
    {
      "epoch": 0.14678899082568808,
      "grad_norm": 0.15668903317199465,
      "learning_rate": 1.4652014652014653e-05,
      "loss": 2.009,
      "step": 80
    },
    {
      "epoch": 0.1651376146788991,
      "grad_norm": 0.13299844821079024,
      "learning_rate": 1.6483516483516486e-05,
      "loss": 2.0319,
      "step": 90
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 0.130419681456145,
      "learning_rate": 1.8315018315018315e-05,
      "loss": 2.0057,
      "step": 100
    },
    {
      "epoch": 0.2018348623853211,
      "grad_norm": 0.13084640056684232,
      "learning_rate": 2.0146520146520148e-05,
      "loss": 2.0418,
      "step": 110
    },
    {
      "epoch": 0.22018348623853212,
      "grad_norm": 0.13600193042807687,
      "learning_rate": 2.1978021978021977e-05,
      "loss": 1.9938,
      "step": 120
    },
    {
      "epoch": 0.23853211009174313,
      "grad_norm": 0.13634836092075994,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.9859,
      "step": 130
    },
    {
      "epoch": 0.25688073394495414,
      "grad_norm": 0.1422134721246097,
      "learning_rate": 2.564102564102564e-05,
      "loss": 2.0146,
      "step": 140
    },
    {
      "epoch": 0.27522935779816515,
      "grad_norm": 0.15208974396882444,
      "learning_rate": 2.7472527472527476e-05,
      "loss": 2.0141,
      "step": 150
    },
    {
      "epoch": 0.29357798165137616,
      "grad_norm": 0.14861311683006395,
      "learning_rate": 2.9304029304029305e-05,
      "loss": 1.9914,
      "step": 160
    },
    {
      "epoch": 0.3119266055045872,
      "grad_norm": 0.154560148894899,
      "learning_rate": 3.113553113553114e-05,
      "loss": 1.9883,
      "step": 170
    },
    {
      "epoch": 0.3302752293577982,
      "grad_norm": 0.14659138270717795,
      "learning_rate": 3.296703296703297e-05,
      "loss": 1.98,
      "step": 180
    },
    {
      "epoch": 0.3486238532110092,
      "grad_norm": 0.14930915757375882,
      "learning_rate": 3.47985347985348e-05,
      "loss": 2.0039,
      "step": 190
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": 0.15222292163468532,
      "learning_rate": 3.663003663003663e-05,
      "loss": 1.9972,
      "step": 200
    },
    {
      "epoch": 0.3853211009174312,
      "grad_norm": 0.1794465203569635,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.961,
      "step": 210
    },
    {
      "epoch": 0.4036697247706422,
      "grad_norm": 0.16111917245406526,
      "learning_rate": 4.0293040293040296e-05,
      "loss": 1.9689,
      "step": 220
    },
    {
      "epoch": 0.42201834862385323,
      "grad_norm": 0.16917075207279755,
      "learning_rate": 4.212454212454213e-05,
      "loss": 1.955,
      "step": 230
    },
    {
      "epoch": 0.44036697247706424,
      "grad_norm": 0.16035752232756367,
      "learning_rate": 4.3956043956043955e-05,
      "loss": 1.9784,
      "step": 240
    },
    {
      "epoch": 0.45871559633027525,
      "grad_norm": 0.15704206875567997,
      "learning_rate": 4.578754578754579e-05,
      "loss": 1.9898,
      "step": 250
    },
    {
      "epoch": 0.47706422018348627,
      "grad_norm": 0.17540759793553962,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.9835,
      "step": 260
    },
    {
      "epoch": 0.4954128440366973,
      "grad_norm": 0.15564282446806355,
      "learning_rate": 4.945054945054945e-05,
      "loss": 1.9849,
      "step": 270
    },
    {
      "epoch": 0.5137614678899083,
      "grad_norm": 0.1731016854986911,
      "learning_rate": 4.9998994546487535e-05,
      "loss": 1.984,
      "step": 280
    },
    {
      "epoch": 0.5321100917431193,
      "grad_norm": 0.16384332591458595,
      "learning_rate": 4.999407007091408e-05,
      "loss": 1.9846,
      "step": 290
    },
    {
      "epoch": 0.5504587155963303,
      "grad_norm": 0.16272027999288557,
      "learning_rate": 4.998504270550914e-05,
      "loss": 1.9773,
      "step": 300
    },
    {
      "epoch": 0.5688073394495413,
      "grad_norm": 0.1895435253320987,
      "learning_rate": 4.997191393215565e-05,
      "loss": 1.9544,
      "step": 310
    },
    {
      "epoch": 0.5871559633027523,
      "grad_norm": 0.153237870046719,
      "learning_rate": 4.995468590600123e-05,
      "loss": 1.9627,
      "step": 320
    },
    {
      "epoch": 0.6055045871559633,
      "grad_norm": 0.15686668474912246,
      "learning_rate": 4.9933361455104425e-05,
      "loss": 1.9977,
      "step": 330
    },
    {
      "epoch": 0.6238532110091743,
      "grad_norm": 0.16748791541980212,
      "learning_rate": 4.990794407997044e-05,
      "loss": 1.9657,
      "step": 340
    },
    {
      "epoch": 0.6422018348623854,
      "grad_norm": 0.1467745903785114,
      "learning_rate": 4.9878437952976563e-05,
      "loss": 1.9625,
      "step": 350
    },
    {
      "epoch": 0.6605504587155964,
      "grad_norm": 0.14836352242961773,
      "learning_rate": 4.984484791768721e-05,
      "loss": 1.9865,
      "step": 360
    },
    {
      "epoch": 0.6788990825688074,
      "grad_norm": 0.15162372625275922,
      "learning_rate": 4.980717948805884e-05,
      "loss": 1.9534,
      "step": 370
    },
    {
      "epoch": 0.6972477064220184,
      "grad_norm": 0.15628620060925916,
      "learning_rate": 4.9765438847534825e-05,
      "loss": 1.976,
      "step": 380
    },
    {
      "epoch": 0.7155963302752294,
      "grad_norm": 0.15072809988708077,
      "learning_rate": 4.9719632848030405e-05,
      "loss": 1.9598,
      "step": 390
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 0.14670892778532468,
      "learning_rate": 4.966976900880791e-05,
      "loss": 2.0001,
      "step": 400
    },
    {
      "epoch": 0.7522935779816514,
      "grad_norm": 0.15020025168070633,
      "learning_rate": 4.9615855515242434e-05,
      "loss": 1.9876,
      "step": 410
    },
    {
      "epoch": 0.7706422018348624,
      "grad_norm": 0.14345074549432202,
      "learning_rate": 4.955790121747821e-05,
      "loss": 1.9839,
      "step": 420
    },
    {
      "epoch": 0.7889908256880734,
      "grad_norm": 0.15176626779360905,
      "learning_rate": 4.949591562897574e-05,
      "loss": 1.9738,
      "step": 430
    },
    {
      "epoch": 0.8073394495412844,
      "grad_norm": 0.15234818977369388,
      "learning_rate": 4.942990892495021e-05,
      "loss": 2.0086,
      "step": 440
    },
    {
      "epoch": 0.8256880733944955,
      "grad_norm": 0.14268394349668895,
      "learning_rate": 4.9359891940701086e-05,
      "loss": 1.9797,
      "step": 450
    },
    {
      "epoch": 0.8440366972477065,
      "grad_norm": 0.15852698385870923,
      "learning_rate": 4.9285876169833544e-05,
      "loss": 1.9532,
      "step": 460
    },
    {
      "epoch": 0.8623853211009175,
      "grad_norm": 0.15294331275157483,
      "learning_rate": 4.920787376237168e-05,
      "loss": 1.992,
      "step": 470
    },
    {
      "epoch": 0.8807339449541285,
      "grad_norm": 0.15177058058835824,
      "learning_rate": 4.9125897522764044e-05,
      "loss": 1.9902,
      "step": 480
    },
    {
      "epoch": 0.8990825688073395,
      "grad_norm": 0.17927892676829146,
      "learning_rate": 4.9039960907781746e-05,
      "loss": 1.9694,
      "step": 490
    },
    {
      "epoch": 0.9174311926605505,
      "grad_norm": 0.14983509077226922,
      "learning_rate": 4.895007802430944e-05,
      "loss": 1.9506,
      "step": 500
    },
    {
      "epoch": 0.9357798165137615,
      "grad_norm": 0.16471555436795565,
      "learning_rate": 4.885626362702966e-05,
      "loss": 1.9841,
      "step": 510
    },
    {
      "epoch": 0.9541284403669725,
      "grad_norm": 0.1472502715125968,
      "learning_rate": 4.8758533116000696e-05,
      "loss": 1.9832,
      "step": 520
    },
    {
      "epoch": 0.9724770642201835,
      "grad_norm": 0.15070629202588426,
      "learning_rate": 4.86569025341287e-05,
      "loss": 1.9774,
      "step": 530
    },
    {
      "epoch": 0.9908256880733946,
      "grad_norm": 0.14316992610781615,
      "learning_rate": 4.855138856453408e-05,
      "loss": 1.9692,
      "step": 540
    },
    {
      "epoch": 1.0091743119266054,
      "grad_norm": 0.14585698001384728,
      "learning_rate": 4.844200852781295e-05,
      "loss": 1.9598,
      "step": 550
    },
    {
      "epoch": 1.0275229357798166,
      "grad_norm": 0.15101510050666817,
      "learning_rate": 4.8328780379193885e-05,
      "loss": 1.9773,
      "step": 560
    },
    {
      "epoch": 1.0458715596330275,
      "grad_norm": 0.15415482414608545,
      "learning_rate": 4.821172270559039e-05,
      "loss": 1.9699,
      "step": 570
    },
    {
      "epoch": 1.0642201834862386,
      "grad_norm": 0.15483797940425081,
      "learning_rate": 4.8090854722549914e-05,
      "loss": 1.993,
      "step": 580
    },
    {
      "epoch": 1.0825688073394495,
      "grad_norm": 0.15815400043247343,
      "learning_rate": 4.796619627109944e-05,
      "loss": 1.939,
      "step": 590
    },
    {
      "epoch": 1.1009174311926606,
      "grad_norm": 0.1645249210360427,
      "learning_rate": 4.7837767814488486e-05,
      "loss": 1.9623,
      "step": 600
    },
    {
      "epoch": 1.1192660550458715,
      "grad_norm": 0.1647619918199487,
      "learning_rate": 4.770559043483003e-05,
      "loss": 1.9816,
      "step": 610
    },
    {
      "epoch": 1.1376146788990826,
      "grad_norm": 0.1679679060709561,
      "learning_rate": 4.7569685829639734e-05,
      "loss": 1.9611,
      "step": 620
    },
    {
      "epoch": 1.1559633027522935,
      "grad_norm": 0.1676170375866798,
      "learning_rate": 4.743007630827423e-05,
      "loss": 1.959,
      "step": 630
    },
    {
      "epoch": 1.1743119266055047,
      "grad_norm": 0.14905089408466188,
      "learning_rate": 4.7286784788268904e-05,
      "loss": 1.9269,
      "step": 640
    },
    {
      "epoch": 1.1926605504587156,
      "grad_norm": 0.162817312686442,
      "learning_rate": 4.713983479157592e-05,
      "loss": 1.9638,
      "step": 650
    },
    {
      "epoch": 1.2110091743119267,
      "grad_norm": 0.18370789078991157,
      "learning_rate": 4.698925044070296e-05,
      "loss": 1.9494,
      "step": 660
    },
    {
      "epoch": 1.2293577981651376,
      "grad_norm": 0.15795771627671365,
      "learning_rate": 4.683505645475339e-05,
      "loss": 1.96,
      "step": 670
    },
    {
      "epoch": 1.2477064220183487,
      "grad_norm": 0.15531127222157262,
      "learning_rate": 4.6677278145368554e-05,
      "loss": 1.969,
      "step": 680
    },
    {
      "epoch": 1.2660550458715596,
      "grad_norm": 0.15599004624517146,
      "learning_rate": 4.65159414125727e-05,
      "loss": 1.9435,
      "step": 690
    },
    {
      "epoch": 1.2844036697247707,
      "grad_norm": 0.16702581452844592,
      "learning_rate": 4.6351072740521415e-05,
      "loss": 1.9323,
      "step": 700
    },
    {
      "epoch": 1.3027522935779816,
      "grad_norm": 0.15898151168116278,
      "learning_rate": 4.6182699193154125e-05,
      "loss": 1.9442,
      "step": 710
    },
    {
      "epoch": 1.3211009174311927,
      "grad_norm": 0.15969818021992918,
      "learning_rate": 4.601084840975139e-05,
      "loss": 1.973,
      "step": 720
    },
    {
      "epoch": 1.3394495412844036,
      "grad_norm": 0.15378573113733301,
      "learning_rate": 4.583554860039784e-05,
      "loss": 1.9366,
      "step": 730
    },
    {
      "epoch": 1.3577981651376148,
      "grad_norm": 0.15121087319924134,
      "learning_rate": 4.565682854135132e-05,
      "loss": 1.9698,
      "step": 740
    },
    {
      "epoch": 1.3761467889908257,
      "grad_norm": 0.15898725981112244,
      "learning_rate": 4.547471757031919e-05,
      "loss": 1.9604,
      "step": 750
    },
    {
      "epoch": 1.3944954128440368,
      "grad_norm": 0.15306064791439133,
      "learning_rate": 4.528924558164233e-05,
      "loss": 1.962,
      "step": 760
    },
    {
      "epoch": 1.4128440366972477,
      "grad_norm": 0.16371512899536222,
      "learning_rate": 4.510044302138793e-05,
      "loss": 1.9793,
      "step": 770
    },
    {
      "epoch": 1.4311926605504588,
      "grad_norm": 0.15788911392614066,
      "learning_rate": 4.490834088235157e-05,
      "loss": 1.9801,
      "step": 780
    },
    {
      "epoch": 1.4495412844036697,
      "grad_norm": 0.16398987312372718,
      "learning_rate": 4.4712970698969645e-05,
      "loss": 1.9236,
      "step": 790
    },
    {
      "epoch": 1.4678899082568808,
      "grad_norm": 0.15020427466606878,
      "learning_rate": 4.451436454214285e-05,
      "loss": 1.9438,
      "step": 800
    },
    {
      "epoch": 1.4862385321100917,
      "grad_norm": 0.1528061160370563,
      "learning_rate": 4.4312555013971534e-05,
      "loss": 1.9364,
      "step": 810
    },
    {
      "epoch": 1.5045871559633026,
      "grad_norm": 0.15222177715019794,
      "learning_rate": 4.4107575242404013e-05,
      "loss": 1.9399,
      "step": 820
    },
    {
      "epoch": 1.5229357798165137,
      "grad_norm": 0.1540985658911008,
      "learning_rate": 4.38994588757984e-05,
      "loss": 1.9483,
      "step": 830
    },
    {
      "epoch": 1.5412844036697249,
      "grad_norm": 0.1599074284657503,
      "learning_rate": 4.3688240077399074e-05,
      "loss": 1.9748,
      "step": 840
    },
    {
      "epoch": 1.5596330275229358,
      "grad_norm": 0.1516707606485465,
      "learning_rate": 4.3473953519728685e-05,
      "loss": 1.9213,
      "step": 850
    },
    {
      "epoch": 1.5779816513761467,
      "grad_norm": 0.15122814764762293,
      "learning_rate": 4.325663437889643e-05,
      "loss": 1.9893,
      "step": 860
    },
    {
      "epoch": 1.5963302752293578,
      "grad_norm": 0.15959987778428422,
      "learning_rate": 4.30363183288238e-05,
      "loss": 1.9602,
      "step": 870
    },
    {
      "epoch": 1.614678899082569,
      "grad_norm": 0.15266741829090746,
      "learning_rate": 4.2813041535388496e-05,
      "loss": 1.9529,
      "step": 880
    },
    {
      "epoch": 1.6330275229357798,
      "grad_norm": 0.16386079884752924,
      "learning_rate": 4.258684065048766e-05,
      "loss": 1.9606,
      "step": 890
    },
    {
      "epoch": 1.6513761467889907,
      "grad_norm": 0.15583648586262694,
      "learning_rate": 4.23577528060213e-05,
      "loss": 1.9581,
      "step": 900
    },
    {
      "epoch": 1.6697247706422018,
      "grad_norm": 0.1585736145888436,
      "learning_rate": 4.212581560779689e-05,
      "loss": 1.9552,
      "step": 910
    },
    {
      "epoch": 1.688073394495413,
      "grad_norm": 0.16965341576331627,
      "learning_rate": 4.1891067129356276e-05,
      "loss": 1.9296,
      "step": 920
    },
    {
      "epoch": 1.7064220183486238,
      "grad_norm": 0.15927292960064882,
      "learning_rate": 4.165354590572564e-05,
      "loss": 1.9762,
      "step": 930
    },
    {
      "epoch": 1.7247706422018347,
      "grad_norm": 0.15450025224674474,
      "learning_rate": 4.14132909270899e-05,
      "loss": 1.9429,
      "step": 940
    },
    {
      "epoch": 1.7431192660550459,
      "grad_norm": 0.15355485102004446,
      "learning_rate": 4.117034163239219e-05,
      "loss": 1.9233,
      "step": 950
    },
    {
      "epoch": 1.761467889908257,
      "grad_norm": 0.15539982061507696,
      "learning_rate": 4.092473790285986e-05,
      "loss": 1.944,
      "step": 960
    },
    {
      "epoch": 1.7798165137614679,
      "grad_norm": 0.1551191369865497,
      "learning_rate": 4.0676520055457765e-05,
      "loss": 1.945,
      "step": 970
    },
    {
      "epoch": 1.7981651376146788,
      "grad_norm": 0.15695341020759185,
      "learning_rate": 4.0425728836270037e-05,
      "loss": 1.9656,
      "step": 980
    },
    {
      "epoch": 1.81651376146789,
      "grad_norm": 0.16047022345268508,
      "learning_rate": 4.017240541381146e-05,
      "loss": 1.9546,
      "step": 990
    },
    {
      "epoch": 1.834862385321101,
      "grad_norm": 0.1561566895170307,
      "learning_rate": 3.9916591372269434e-05,
      "loss": 1.9363,
      "step": 1000
    },
    {
      "epoch": 1.853211009174312,
      "grad_norm": 0.15117586495122826,
      "learning_rate": 3.9658328704677794e-05,
      "loss": 1.978,
      "step": 1010
    },
    {
      "epoch": 1.8715596330275228,
      "grad_norm": 0.1605982135175342,
      "learning_rate": 3.939765980602342e-05,
      "loss": 1.9713,
      "step": 1020
    },
    {
      "epoch": 1.889908256880734,
      "grad_norm": 0.1602836931731585,
      "learning_rate": 3.913462746628691e-05,
      "loss": 2.0041,
      "step": 1030
    },
    {
      "epoch": 1.908256880733945,
      "grad_norm": 0.16286472480475192,
      "learning_rate": 3.886927486341844e-05,
      "loss": 1.9352,
      "step": 1040
    },
    {
      "epoch": 1.926605504587156,
      "grad_norm": 0.15449199584717296,
      "learning_rate": 3.860164555624988e-05,
      "loss": 1.97,
      "step": 1050
    },
    {
      "epoch": 1.9449541284403669,
      "grad_norm": 0.14684566302878604,
      "learning_rate": 3.833178347734443e-05,
      "loss": 1.9433,
      "step": 1060
    },
    {
      "epoch": 1.963302752293578,
      "grad_norm": 0.16167305499507623,
      "learning_rate": 3.80597329257849e-05,
      "loss": 1.9782,
      "step": 1070
    },
    {
      "epoch": 1.981651376146789,
      "grad_norm": 0.1544185075202575,
      "learning_rate": 3.778553855990176e-05,
      "loss": 1.9253,
      "step": 1080
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.16072854970224754,
      "learning_rate": 3.750924538994235e-05,
      "loss": 1.9578,
      "step": 1090
    }
  ],
  "logging_steps": 10,
  "max_steps": 2725,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5869823436193792e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}