{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09780548933308882,
  "eval_steps": 34,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004890274466654441,
      "grad_norm": 0.42223185300827026,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.2369,
      "step": 1
    },
    {
      "epoch": 0.0004890274466654441,
      "eval_loss": 1.3036277294158936,
      "eval_runtime": 1355.2246,
      "eval_samples_per_second": 1.906,
      "eval_steps_per_second": 0.635,
      "step": 1
    },
    {
      "epoch": 0.0009780548933308881,
      "grad_norm": 0.49382174015045166,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.3544,
      "step": 2
    },
    {
      "epoch": 0.0014670823399963323,
      "grad_norm": 0.43727555871009827,
      "learning_rate": 2e-05,
      "loss": 1.403,
      "step": 3
    },
    {
      "epoch": 0.0019561097866617762,
      "grad_norm": 0.3653078079223633,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.189,
      "step": 4
    },
    {
      "epoch": 0.0024451372333272204,
      "grad_norm": 0.3689245283603668,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1686,
      "step": 5
    },
    {
      "epoch": 0.0029341646799926646,
      "grad_norm": 0.44767728447914124,
      "learning_rate": 4e-05,
      "loss": 1.2578,
      "step": 6
    },
    {
      "epoch": 0.0034231921266581087,
      "grad_norm": 0.4529785215854645,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.2452,
      "step": 7
    },
    {
      "epoch": 0.0039122195733235525,
      "grad_norm": 0.6146576404571533,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.5423,
      "step": 8
    },
    {
      "epoch": 0.004401247019988997,
      "grad_norm": 0.42456191778182983,
      "learning_rate": 6e-05,
      "loss": 1.1323,
      "step": 9
    },
    {
      "epoch": 0.004890274466654441,
      "grad_norm": 0.4658707082271576,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2595,
      "step": 10
    },
    {
      "epoch": 0.005379301913319885,
      "grad_norm": 0.6462928652763367,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.3136,
      "step": 11
    },
    {
      "epoch": 0.005868329359985329,
      "grad_norm": 0.514143168926239,
      "learning_rate": 8e-05,
      "loss": 1.1999,
      "step": 12
    },
    {
      "epoch": 0.006357356806650773,
      "grad_norm": 0.43792784214019775,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.0675,
      "step": 13
    },
    {
      "epoch": 0.0068463842533162175,
      "grad_norm": 0.6212848424911499,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.3066,
      "step": 14
    },
    {
      "epoch": 0.007335411699981661,
      "grad_norm": 0.6186118125915527,
      "learning_rate": 0.0001,
      "loss": 1.2355,
      "step": 15
    },
    {
      "epoch": 0.007824439146647105,
      "grad_norm": 0.6825079917907715,
      "learning_rate": 0.00010666666666666667,
      "loss": 1.2258,
      "step": 16
    },
    {
      "epoch": 0.00831346659331255,
      "grad_norm": 0.3936300575733185,
      "learning_rate": 0.00011333333333333334,
      "loss": 1.1337,
      "step": 17
    },
    {
      "epoch": 0.008802494039977994,
      "grad_norm": 0.5038918852806091,
      "learning_rate": 0.00012,
      "loss": 1.1278,
      "step": 18
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 0.5894134640693665,
      "learning_rate": 0.00012666666666666666,
      "loss": 1.1902,
      "step": 19
    },
    {
      "epoch": 0.009780548933308882,
      "grad_norm": 1.1452070474624634,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.1023,
      "step": 20
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": 0.4289817214012146,
      "learning_rate": 0.00014,
      "loss": 1.0195,
      "step": 21
    },
    {
      "epoch": 0.01075860382663977,
      "grad_norm": 1.290226936340332,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.9534,
      "step": 22
    },
    {
      "epoch": 0.011247631273305215,
      "grad_norm": 0.5022335648536682,
      "learning_rate": 0.00015333333333333334,
      "loss": 0.8952,
      "step": 23
    },
    {
      "epoch": 0.011736658719970658,
      "grad_norm": 0.5421992540359497,
      "learning_rate": 0.00016,
      "loss": 0.8553,
      "step": 24
    },
    {
      "epoch": 0.012225686166636102,
      "grad_norm": 1.568458080291748,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.9764,
      "step": 25
    },
    {
      "epoch": 0.012714713613301546,
      "grad_norm": 0.6190416812896729,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.9819,
      "step": 26
    },
    {
      "epoch": 0.013203741059966991,
      "grad_norm": 0.4747830927371979,
      "learning_rate": 0.00018,
      "loss": 0.9395,
      "step": 27
    },
    {
      "epoch": 0.013692768506632435,
      "grad_norm": 0.9486120343208313,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.9669,
      "step": 28
    },
    {
      "epoch": 0.014181795953297879,
      "grad_norm": 0.4615766108036041,
      "learning_rate": 0.00019333333333333333,
      "loss": 0.9341,
      "step": 29
    },
    {
      "epoch": 0.014670823399963322,
      "grad_norm": 0.46146905422210693,
      "learning_rate": 0.0002,
      "loss": 1.0082,
      "step": 30
    },
    {
      "epoch": 0.015159850846628768,
      "grad_norm": 0.47625860571861267,
      "learning_rate": 0.00019998292504580528,
      "loss": 0.9419,
      "step": 31
    },
    {
      "epoch": 0.01564887829329421,
      "grad_norm": 0.5290003418922424,
      "learning_rate": 0.0001999317060143023,
      "loss": 1.1635,
      "step": 32
    },
    {
      "epoch": 0.016137905739959654,
      "grad_norm": 0.5592769980430603,
      "learning_rate": 0.0001998463603967434,
      "loss": 0.9437,
      "step": 33
    },
    {
      "epoch": 0.0166269331866251,
      "grad_norm": 0.3583241403102875,
      "learning_rate": 0.00019972691733857883,
      "loss": 1.1428,
      "step": 34
    },
    {
      "epoch": 0.0166269331866251,
      "eval_loss": 1.0231887102127075,
      "eval_runtime": 1359.3297,
      "eval_samples_per_second": 1.9,
      "eval_steps_per_second": 0.633,
      "step": 34
    },
    {
      "epoch": 0.017115960633290545,
      "grad_norm": 0.41851457953453064,
      "learning_rate": 0.00019957341762950344,
      "loss": 1.0976,
      "step": 35
    },
    {
      "epoch": 0.017604988079955988,
      "grad_norm": 0.46739837527275085,
      "learning_rate": 0.0001993859136895274,
      "loss": 1.0089,
      "step": 36
    },
    {
      "epoch": 0.018094015526621432,
      "grad_norm": 0.3970998227596283,
      "learning_rate": 0.00019916446955107428,
      "loss": 1.1005,
      "step": 37
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 0.5996494293212891,
      "learning_rate": 0.0001989091608371146,
      "loss": 0.9741,
      "step": 38
    },
    {
      "epoch": 0.01907207041995232,
      "grad_norm": 0.27929016947746277,
      "learning_rate": 0.00019862007473534025,
      "loss": 0.9607,
      "step": 39
    },
    {
      "epoch": 0.019561097866617763,
      "grad_norm": 0.33169642090797424,
      "learning_rate": 0.0001982973099683902,
      "loss": 1.1173,
      "step": 40
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": 0.3042043149471283,
      "learning_rate": 0.0001979409767601366,
      "loss": 1.1178,
      "step": 41
    },
    {
      "epoch": 0.02053915275994865,
      "grad_norm": 0.3394615650177002,
      "learning_rate": 0.00019755119679804367,
      "loss": 1.0167,
      "step": 42
    },
    {
      "epoch": 0.021028180206614098,
      "grad_norm": 0.3241017758846283,
      "learning_rate": 0.0001971281031916114,
      "loss": 1.0089,
      "step": 43
    },
    {
      "epoch": 0.02151720765327954,
      "grad_norm": 0.6870384812355042,
      "learning_rate": 0.00019667184042691875,
      "loss": 1.0362,
      "step": 44
    },
    {
      "epoch": 0.022006235099944985,
      "grad_norm": 0.31295979022979736,
      "learning_rate": 0.00019618256431728194,
      "loss": 1.0032,
      "step": 45
    },
    {
      "epoch": 0.02249526254661043,
      "grad_norm": 0.32893508672714233,
      "learning_rate": 0.0001956604419500441,
      "loss": 1.0651,
      "step": 46
    },
    {
      "epoch": 0.022984289993275873,
      "grad_norm": 0.28745728731155396,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.9031,
      "step": 47
    },
    {
      "epoch": 0.023473317439941317,
      "grad_norm": 0.558315098285675,
      "learning_rate": 0.00019451838281608197,
      "loss": 1.0545,
      "step": 48
    },
    {
      "epoch": 0.02396234488660676,
      "grad_norm": 0.5743781924247742,
      "learning_rate": 0.00019389883606150566,
      "loss": 1.0951,
      "step": 49
    },
    {
      "epoch": 0.024451372333272204,
      "grad_norm": 0.41075870394706726,
      "learning_rate": 0.00019324722294043558,
      "loss": 1.0124,
      "step": 50
    },
    {
      "epoch": 0.024940399779937648,
      "grad_norm": 0.2487930953502655,
      "learning_rate": 0.00019256376597815564,
      "loss": 0.9894,
      "step": 51
    },
    {
      "epoch": 0.02542942722660309,
      "grad_norm": 0.39657795429229736,
      "learning_rate": 0.00019184869857459232,
      "loss": 1.138,
      "step": 52
    },
    {
      "epoch": 0.02591845467326854,
      "grad_norm": 0.5362446308135986,
      "learning_rate": 0.00019110226492460885,
      "loss": 1.0342,
      "step": 53
    },
    {
      "epoch": 0.026407482119933982,
      "grad_norm": 0.5089200139045715,
      "learning_rate": 0.0001903247199346129,
      "loss": 1.1193,
      "step": 54
    },
    {
      "epoch": 0.026896509566599426,
      "grad_norm": 0.28259485960006714,
      "learning_rate": 0.00018951632913550626,
      "loss": 0.9054,
      "step": 55
    },
    {
      "epoch": 0.02738553701326487,
      "grad_norm": 0.3576945662498474,
      "learning_rate": 0.0001886773685920062,
      "loss": 1.0002,
      "step": 56
    },
    {
      "epoch": 0.027874564459930314,
      "grad_norm": 0.2915222942829132,
      "learning_rate": 0.0001878081248083698,
      "loss": 0.9491,
      "step": 57
    },
    {
      "epoch": 0.028363591906595757,
      "grad_norm": 0.296265572309494,
      "learning_rate": 0.00018690889463055283,
      "loss": 1.0483,
      "step": 58
    },
    {
      "epoch": 0.0288526193532612,
      "grad_norm": 0.3489420413970947,
      "learning_rate": 0.00018597998514483725,
      "loss": 0.9064,
      "step": 59
    },
    {
      "epoch": 0.029341646799926645,
      "grad_norm": 0.37772810459136963,
      "learning_rate": 0.00018502171357296144,
      "loss": 0.9779,
      "step": 60
    },
    {
      "epoch": 0.02983067424659209,
      "grad_norm": 0.5371522903442383,
      "learning_rate": 0.00018403440716378928,
      "loss": 1.0268,
      "step": 61
    },
    {
      "epoch": 0.030319701693257536,
      "grad_norm": 0.3227771520614624,
      "learning_rate": 0.00018301840308155507,
      "loss": 1.0642,
      "step": 62
    },
    {
      "epoch": 0.03080872913992298,
      "grad_norm": 0.4422720670700073,
      "learning_rate": 0.00018197404829072215,
      "loss": 1.1083,
      "step": 63
    },
    {
      "epoch": 0.03129775658658842,
      "grad_norm": 0.5397651791572571,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.2271,
      "step": 64
    },
    {
      "epoch": 0.03178678403325386,
      "grad_norm": 0.4943908452987671,
      "learning_rate": 0.000179801722728024,
      "loss": 0.9873,
      "step": 65
    },
    {
      "epoch": 0.03227581147991931,
      "grad_norm": 0.31046292185783386,
      "learning_rate": 0.00017867449380334834,
      "loss": 0.9235,
      "step": 66
    },
    {
      "epoch": 0.03276483892658476,
      "grad_norm": 0.4786432981491089,
      "learning_rate": 0.00017752039761111297,
      "loss": 1.0804,
      "step": 67
    },
    {
      "epoch": 0.0332538663732502,
      "grad_norm": 0.38078072667121887,
      "learning_rate": 0.00017633982827411032,
      "loss": 1.0508,
      "step": 68
    },
    {
      "epoch": 0.0332538663732502,
      "eval_loss": 1.0058449506759644,
      "eval_runtime": 1360.1032,
      "eval_samples_per_second": 1.899,
      "eval_steps_per_second": 0.633,
      "step": 68
    },
    {
      "epoch": 0.033742893819915645,
      "grad_norm": 0.302775114774704,
      "learning_rate": 0.00017513318895568737,
      "loss": 1.0186,
      "step": 69
    },
    {
      "epoch": 0.03423192126658109,
      "grad_norm": 0.7890788316726685,
      "learning_rate": 0.00017390089172206592,
      "loss": 0.9441,
      "step": 70
    },
    {
      "epoch": 0.03472094871324653,
      "grad_norm": 0.3507513999938965,
      "learning_rate": 0.00017264335740162242,
      "loss": 0.9604,
      "step": 71
    },
    {
      "epoch": 0.035209976159911976,
      "grad_norm": 0.39182308316230774,
      "learning_rate": 0.00017136101544117525,
      "loss": 1.0598,
      "step": 72
    },
    {
      "epoch": 0.03569900360657742,
      "grad_norm": 0.3877043128013611,
      "learning_rate": 0.0001700543037593291,
      "loss": 0.8719,
      "step": 73
    },
    {
      "epoch": 0.036188031053242864,
      "grad_norm": 0.6628935933113098,
      "learning_rate": 0.00016872366859692627,
      "loss": 0.9241,
      "step": 74
    },
    {
      "epoch": 0.03667705849990831,
      "grad_norm": 0.45674100518226624,
      "learning_rate": 0.00016736956436465573,
      "loss": 1.2833,
      "step": 75
    },
    {
      "epoch": 0.03716608594657375,
      "grad_norm": 0.5053292512893677,
      "learning_rate": 0.0001659924534878723,
      "loss": 0.9678,
      "step": 76
    },
    {
      "epoch": 0.037655113393239195,
      "grad_norm": 0.31924471259117126,
      "learning_rate": 0.00016459280624867874,
      "loss": 0.9702,
      "step": 77
    },
    {
      "epoch": 0.03814414083990464,
      "grad_norm": 0.37664365768432617,
      "learning_rate": 0.0001631711006253251,
      "loss": 0.8382,
      "step": 78
    },
    {
      "epoch": 0.03863316828657008,
      "grad_norm": 0.3583241403102875,
      "learning_rate": 0.0001617278221289793,
      "loss": 1.0149,
      "step": 79
    },
    {
      "epoch": 0.039122195733235526,
      "grad_norm": 0.3891322910785675,
      "learning_rate": 0.00016026346363792567,
      "loss": 1.2247,
      "step": 80
    },
    {
      "epoch": 0.03961122317990097,
      "grad_norm": 0.32489892840385437,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.9108,
      "step": 81
    },
    {
      "epoch": 0.040100250626566414,
      "grad_norm": 0.3395017981529236,
      "learning_rate": 0.00015727351400805052,
      "loss": 0.9968,
      "step": 82
    },
    {
      "epoch": 0.04058927807323186,
      "grad_norm": 0.34815898537635803,
      "learning_rate": 0.00015574894393428855,
      "loss": 0.967,
      "step": 83
    },
    {
      "epoch": 0.0410783055198973,
      "grad_norm": 0.4931004047393799,
      "learning_rate": 0.00015420533564724495,
      "loss": 1.0232,
      "step": 84
    },
    {
      "epoch": 0.041567332966562745,
      "grad_norm": 0.45658788084983826,
      "learning_rate": 0.0001526432162877356,
      "loss": 1.0845,
      "step": 85
    },
    {
      "epoch": 0.042056360413228196,
      "grad_norm": 0.2645609378814697,
      "learning_rate": 0.0001510631193180907,
      "loss": 0.8387,
      "step": 86
    },
    {
      "epoch": 0.04254538785989364,
      "grad_norm": 0.2979009747505188,
      "learning_rate": 0.0001494655843399779,
      "loss": 1.0789,
      "step": 87
    },
    {
      "epoch": 0.04303441530655908,
      "grad_norm": 0.3363690674304962,
      "learning_rate": 0.00014785115691012864,
      "loss": 0.9624,
      "step": 88
    },
    {
      "epoch": 0.04352344275322453,
      "grad_norm": 0.700744092464447,
      "learning_rate": 0.00014622038835403133,
      "loss": 1.0248,
      "step": 89
    },
    {
      "epoch": 0.04401247019988997,
      "grad_norm": 0.4093436300754547,
      "learning_rate": 0.00014457383557765386,
      "loss": 0.993,
      "step": 90
    },
    {
      "epoch": 0.044501497646555414,
      "grad_norm": 0.39897996187210083,
      "learning_rate": 0.0001429120608772609,
      "loss": 1.0264,
      "step": 91
    },
    {
      "epoch": 0.04499052509322086,
      "grad_norm": 0.2525433897972107,
      "learning_rate": 0.00014123563174739037,
      "loss": 1.0285,
      "step": 92
    },
    {
      "epoch": 0.0454795525398863,
      "grad_norm": 0.2693867087364197,
      "learning_rate": 0.00013954512068705424,
      "loss": 0.9909,
      "step": 93
    },
    {
      "epoch": 0.045968579986551746,
      "grad_norm": 0.4188447594642639,
      "learning_rate": 0.00013784110500423104,
      "loss": 0.9365,
      "step": 94
    },
    {
      "epoch": 0.04645760743321719,
      "grad_norm": 0.3923894762992859,
      "learning_rate": 0.00013612416661871533,
      "loss": 1.187,
      "step": 95
    },
    {
      "epoch": 0.04694663487988263,
      "grad_norm": 0.4264492392539978,
      "learning_rate": 0.00013439489186339282,
      "loss": 1.1103,
      "step": 96
    },
    {
      "epoch": 0.04743566232654808,
      "grad_norm": 0.40396761894226074,
      "learning_rate": 0.0001326538712840083,
      "loss": 1.0,
      "step": 97
    },
    {
      "epoch": 0.04792468977321352,
      "grad_norm": 0.30181634426116943,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9821,
      "step": 98
    },
    {
      "epoch": 0.048413717219878964,
      "grad_norm": 0.37075236439704895,
      "learning_rate": 0.00012913897468893248,
      "loss": 1.0607,
      "step": 99
    },
    {
      "epoch": 0.04890274466654441,
      "grad_norm": 0.39950835704803467,
      "learning_rate": 0.0001273662990072083,
      "loss": 1.011,
      "step": 100
    },
    {
      "epoch": 0.04939177211320985,
      "grad_norm": 0.3369726240634918,
      "learning_rate": 0.00012558427775944357,
      "loss": 0.9987,
      "step": 101
    },
    {
      "epoch": 0.049880799559875295,
      "grad_norm": 0.33174750208854675,
      "learning_rate": 0.00012379351950426187,
      "loss": 0.9603,
      "step": 102
    },
    {
      "epoch": 0.049880799559875295,
      "eval_loss": 0.9992830753326416,
      "eval_runtime": 1359.1213,
      "eval_samples_per_second": 1.9,
      "eval_steps_per_second": 0.633,
      "step": 102
    },
    {
      "epoch": 0.05036982700654074,
      "grad_norm": 0.4101943373680115,
      "learning_rate": 0.00012199463578396688,
      "loss": 0.931,
      "step": 103
    },
    {
      "epoch": 0.05085885445320618,
      "grad_norm": 0.39311182498931885,
      "learning_rate": 0.00012018824091570103,
      "loss": 1.1224,
      "step": 104
    },
    {
      "epoch": 0.051347881899871634,
      "grad_norm": 0.3011833429336548,
      "learning_rate": 0.00011837495178165706,
      "loss": 1.0653,
      "step": 105
    },
    {
      "epoch": 0.05183690934653708,
      "grad_norm": 0.28122061491012573,
      "learning_rate": 0.000116555387618413,
      "loss": 1.0055,
      "step": 106
    },
    {
      "epoch": 0.05232593679320252,
      "grad_norm": 0.5028234720230103,
      "learning_rate": 0.00011473016980546377,
      "loss": 0.9866,
      "step": 107
    },
    {
      "epoch": 0.052814964239867965,
      "grad_norm": 0.3072775602340698,
      "learning_rate": 0.00011289992165302035,
      "loss": 1.1557,
      "step": 108
    },
    {
      "epoch": 0.05330399168653341,
      "grad_norm": 0.2929151654243469,
      "learning_rate": 0.00011106526818915008,
      "loss": 1.04,
      "step": 109
    },
    {
      "epoch": 0.05379301913319885,
      "grad_norm": 0.35853561758995056,
      "learning_rate": 0.00010922683594633021,
      "loss": 1.0056,
      "step": 110
    },
    {
      "epoch": 0.054282046579864296,
      "grad_norm": 0.2755361795425415,
      "learning_rate": 0.00010738525274748741,
      "loss": 0.9208,
      "step": 111
    },
    {
      "epoch": 0.05477107402652974,
      "grad_norm": 0.4574558734893799,
      "learning_rate": 0.000105541147491597,
      "loss": 0.8838,
      "step": 112
    },
    {
      "epoch": 0.05526010147319518,
      "grad_norm": 0.4807765781879425,
      "learning_rate": 0.00010369514993891452,
      "loss": 0.8996,
      "step": 113
    },
    {
      "epoch": 0.05574912891986063,
      "grad_norm": 0.3702511489391327,
      "learning_rate": 0.00010184789049591299,
      "loss": 0.9956,
      "step": 114
    },
    {
      "epoch": 0.05623815636652607,
      "grad_norm": 0.6011176705360413,
      "learning_rate": 0.0001,
      "loss": 1.077,
      "step": 115
    },
    {
      "epoch": 0.056727183813191515,
      "grad_norm": 0.2759286165237427,
      "learning_rate": 9.815210950408704e-05,
      "loss": 1.0208,
      "step": 116
    },
    {
      "epoch": 0.05721621125985696,
      "grad_norm": 0.35885995626449585,
      "learning_rate": 9.630485006108553e-05,
      "loss": 0.8758,
      "step": 117
    },
    {
      "epoch": 0.0577052387065224,
      "grad_norm": 0.3405105471611023,
      "learning_rate": 9.4458852508403e-05,
      "loss": 1.012,
      "step": 118
    },
    {
      "epoch": 0.058194266153187846,
      "grad_norm": 0.3069765865802765,
      "learning_rate": 9.261474725251261e-05,
      "loss": 1.0491,
      "step": 119
    },
    {
      "epoch": 0.05868329359985329,
      "grad_norm": 0.4522247016429901,
      "learning_rate": 9.077316405366981e-05,
      "loss": 0.9517,
      "step": 120
    },
    {
      "epoch": 0.05917232104651873,
      "grad_norm": 0.5270655751228333,
      "learning_rate": 8.893473181084994e-05,
      "loss": 1.0467,
      "step": 121
    },
    {
      "epoch": 0.05966134849318418,
      "grad_norm": 0.46659836173057556,
      "learning_rate": 8.710007834697969e-05,
      "loss": 0.924,
      "step": 122
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 0.3675633668899536,
      "learning_rate": 8.526983019453623e-05,
      "loss": 1.0624,
      "step": 123
    },
    {
      "epoch": 0.06063940338651507,
      "grad_norm": 0.38594844937324524,
      "learning_rate": 8.344461238158699e-05,
      "loss": 0.9479,
      "step": 124
    },
    {
      "epoch": 0.061128430833180515,
      "grad_norm": 0.34377649426460266,
      "learning_rate": 8.162504821834295e-05,
      "loss": 1.0532,
      "step": 125
    },
    {
      "epoch": 0.06161745827984596,
      "grad_norm": 0.39318689703941345,
      "learning_rate": 7.9811759084299e-05,
      "loss": 1.06,
      "step": 126
    },
    {
      "epoch": 0.0621064857265114,
      "grad_norm": 0.386799693107605,
      "learning_rate": 7.800536421603317e-05,
      "loss": 1.0903,
      "step": 127
    },
    {
      "epoch": 0.06259551317317684,
      "grad_norm": 0.4709027409553528,
      "learning_rate": 7.620648049573815e-05,
      "loss": 0.9893,
      "step": 128
    },
    {
      "epoch": 0.06308454061984228,
      "grad_norm": 0.38078197836875916,
      "learning_rate": 7.441572224055644e-05,
      "loss": 1.0638,
      "step": 129
    },
    {
      "epoch": 0.06357356806650773,
      "grad_norm": 0.2914995849132538,
      "learning_rate": 7.263370099279172e-05,
      "loss": 1.0144,
      "step": 130
    },
    {
      "epoch": 0.06406259551317317,
      "grad_norm": 0.48772111535072327,
      "learning_rate": 7.086102531106754e-05,
      "loss": 1.055,
      "step": 131
    },
    {
      "epoch": 0.06455162295983861,
      "grad_norm": 0.37441909313201904,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.948,
      "step": 132
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.4598063826560974,
      "learning_rate": 6.734612871599168e-05,
      "loss": 1.0565,
      "step": 133
    },
    {
      "epoch": 0.06552967785316952,
      "grad_norm": 0.34052199125289917,
      "learning_rate": 6.560510813660719e-05,
      "loss": 0.9724,
      "step": 134
    },
    {
      "epoch": 0.06601870529983496,
      "grad_norm": 0.4426654279232025,
      "learning_rate": 6.387583338128471e-05,
      "loss": 1.1751,
      "step": 135
    },
    {
      "epoch": 0.0665077327465004,
      "grad_norm": 0.3435130715370178,
      "learning_rate": 6.215889499576898e-05,
      "loss": 1.0164,
      "step": 136
    },
    {
      "epoch": 0.0665077327465004,
      "eval_loss": 0.9951372146606445,
      "eval_runtime": 1359.5911,
      "eval_samples_per_second": 1.9,
      "eval_steps_per_second": 0.633,
      "step": 136
    },
    {
      "epoch": 0.06699676019316585,
      "grad_norm": 0.2642524540424347,
      "learning_rate": 6.0454879312945754e-05,
      "loss": 0.9332,
      "step": 137
    },
    {
      "epoch": 0.06748578763983129,
      "grad_norm": 0.30863985419273376,
      "learning_rate": 5.876436825260967e-05,
      "loss": 1.0283,
      "step": 138
    },
    {
      "epoch": 0.06797481508649673,
      "grad_norm": 0.5168886780738831,
      "learning_rate": 5.708793912273911e-05,
      "loss": 0.6723,
      "step": 139
    },
    {
      "epoch": 0.06846384253316218,
      "grad_norm": 0.4818655848503113,
      "learning_rate": 5.542616442234618e-05,
      "loss": 1.1226,
      "step": 140
    },
    {
      "epoch": 0.06895286997982762,
      "grad_norm": 0.3270304501056671,
      "learning_rate": 5.37796116459687e-05,
      "loss": 0.818,
      "step": 141
    },
    {
      "epoch": 0.06944189742649307,
      "grad_norm": 0.44965583086013794,
      "learning_rate": 5.214884308987136e-05,
      "loss": 0.865,
      "step": 142
    },
    {
      "epoch": 0.06993092487315851,
      "grad_norm": 0.25816816091537476,
      "learning_rate": 5.0534415660022136e-05,
      "loss": 0.9777,
      "step": 143
    },
    {
      "epoch": 0.07041995231982395,
      "grad_norm": 0.293589323759079,
      "learning_rate": 4.893688068190932e-05,
      "loss": 1.0442,
      "step": 144
    },
    {
      "epoch": 0.0709089797664894,
      "grad_norm": 0.4365968704223633,
      "learning_rate": 4.735678371226441e-05,
      "loss": 0.8951,
      "step": 145
    },
    {
      "epoch": 0.07139800721315484,
      "grad_norm": 0.4603347182273865,
      "learning_rate": 4.5794664352755055e-05,
      "loss": 1.0377,
      "step": 146
    },
    {
      "epoch": 0.07188703465982028,
      "grad_norm": 0.28372839093208313,
      "learning_rate": 4.425105606571145e-05,
      "loss": 1.008,
      "step": 147
    },
    {
      "epoch": 0.07237606210648573,
      "grad_norm": 0.29044821858406067,
      "learning_rate": 4.272648599194948e-05,
      "loss": 1.0118,
      "step": 148
    },
    {
      "epoch": 0.07286508955315117,
      "grad_norm": 0.3254542350769043,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.0088,
      "step": 149
    },
    {
      "epoch": 0.07335411699981662,
      "grad_norm": 0.3154352605342865,
      "learning_rate": 3.973653636207437e-05,
      "loss": 1.0273,
      "step": 150
    },
    {
      "epoch": 0.07384314444648206,
      "grad_norm": 0.3300507664680481,
      "learning_rate": 3.8272177871020723e-05,
      "loss": 1.0187,
      "step": 151
    },
    {
      "epoch": 0.0743321718931475,
      "grad_norm": 0.4003622531890869,
      "learning_rate": 3.682889937467493e-05,
      "loss": 0.9066,
      "step": 152
    },
    {
      "epoch": 0.07482119933981295,
      "grad_norm": 0.3900095522403717,
      "learning_rate": 3.540719375132129e-05,
      "loss": 0.866,
      "step": 153
    },
    {
      "epoch": 0.07531022678647839,
      "grad_norm": 0.54018634557724,
      "learning_rate": 3.400754651212776e-05,
      "loss": 0.981,
      "step": 154
    },
    {
      "epoch": 0.07579925423314383,
      "grad_norm": 0.3802890479564667,
      "learning_rate": 3.263043563534428e-05,
      "loss": 1.0331,
      "step": 155
    },
    {
      "epoch": 0.07628828167980928,
      "grad_norm": 0.40078866481781006,
      "learning_rate": 3.1276331403073735e-05,
      "loss": 0.9615,
      "step": 156
    },
    {
      "epoch": 0.07677730912647472,
      "grad_norm": 0.6274716258049011,
      "learning_rate": 2.9945696240670906e-05,
      "loss": 1.0867,
      "step": 157
    },
    {
      "epoch": 0.07726633657314017,
      "grad_norm": 0.3220311403274536,
      "learning_rate": 2.8638984558824777e-05,
      "loss": 0.9813,
      "step": 158
    },
    {
      "epoch": 0.07775536401980561,
      "grad_norm": 0.3146653473377228,
      "learning_rate": 2.7356642598377603e-05,
      "loss": 0.9991,
      "step": 159
    },
    {
      "epoch": 0.07824439146647105,
      "grad_norm": 0.22245855629444122,
      "learning_rate": 2.6099108277934103e-05,
      "loss": 0.9811,
      "step": 160
    },
    {
      "epoch": 0.0787334189131365,
      "grad_norm": 0.36206722259521484,
      "learning_rate": 2.4866811044312665e-05,
      "loss": 1.1474,
      "step": 161
    },
    {
      "epoch": 0.07922244635980194,
      "grad_norm": 0.38807740807533264,
      "learning_rate": 2.36601717258897e-05,
      "loss": 0.9162,
      "step": 162
    },
    {
      "epoch": 0.07971147380646738,
      "grad_norm": 0.36179038882255554,
      "learning_rate": 2.2479602388887012e-05,
      "loss": 0.8902,
      "step": 163
    },
    {
      "epoch": 0.08020050125313283,
      "grad_norm": 0.40321770310401917,
      "learning_rate": 2.132550619665168e-05,
      "loss": 0.8454,
      "step": 164
    },
    {
      "epoch": 0.08068952869979827,
      "grad_norm": 0.3098496198654175,
      "learning_rate": 2.0198277271976052e-05,
      "loss": 1.0062,
      "step": 165
    },
    {
      "epoch": 0.08117855614646372,
      "grad_norm": 0.45435985922813416,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.8418,
      "step": 166
    },
    {
      "epoch": 0.08166758359312916,
      "grad_norm": 0.37857669591903687,
      "learning_rate": 1.8025951709277898e-05,
      "loss": 1.0043,
      "step": 167
    },
    {
      "epoch": 0.0821566110397946,
      "grad_norm": 0.3529188930988312,
      "learning_rate": 1.6981596918444953e-05,
      "loss": 1.1446,
      "step": 168
    },
    {
      "epoch": 0.08264563848646005,
      "grad_norm": 0.40138813853263855,
      "learning_rate": 1.5965592836210743e-05,
      "loss": 1.0077,
      "step": 169
    },
    {
      "epoch": 0.08313466593312549,
      "grad_norm": 0.3948013186454773,
      "learning_rate": 1.4978286427038601e-05,
      "loss": 0.843,
      "step": 170
    },
    {
      "epoch": 0.08313466593312549,
      "eval_loss": 0.9932751059532166,
      "eval_runtime": 1360.6949,
      "eval_samples_per_second": 1.898,
      "eval_steps_per_second": 0.633,
      "step": 170
    },
    {
      "epoch": 0.08362369337979095,
      "grad_norm": 0.4719301164150238,
      "learning_rate": 1.4020014855162755e-05,
      "loss": 1.0868,
      "step": 171
    },
    {
      "epoch": 0.08411272082645639,
      "grad_norm": 0.3227783143520355,
      "learning_rate": 1.3091105369447165e-05,
      "loss": 0.9113,
      "step": 172
    },
    {
      "epoch": 0.08460174827312184,
      "grad_norm": 0.37850451469421387,
      "learning_rate": 1.2191875191630209e-05,
      "loss": 1.0702,
      "step": 173
    },
    {
      "epoch": 0.08509077571978728,
      "grad_norm": 0.29281488060951233,
      "learning_rate": 1.1322631407993811e-05,
      "loss": 0.978,
      "step": 174
    },
    {
      "epoch": 0.08557980316645272,
      "grad_norm": 0.2620236277580261,
      "learning_rate": 1.0483670864493778e-05,
      "loss": 0.9053,
      "step": 175
    },
    {
      "epoch": 0.08606883061311817,
      "grad_norm": 0.46799540519714355,
      "learning_rate": 9.675280065387116e-06,
      "loss": 0.9817,
      "step": 176
    },
    {
      "epoch": 0.08655785805978361,
      "grad_norm": 0.28441375494003296,
      "learning_rate": 8.897735075391155e-06,
      "loss": 0.8335,
      "step": 177
    },
    {
      "epoch": 0.08704688550644905,
      "grad_norm": 0.3706384301185608,
      "learning_rate": 8.151301425407699e-06,
      "loss": 0.9957,
      "step": 178
    },
    {
      "epoch": 0.0875359129531145,
      "grad_norm": 0.2594084143638611,
      "learning_rate": 7.43623402184438e-06,
      "loss": 0.8361,
      "step": 179
    },
    {
      "epoch": 0.08802494039977994,
      "grad_norm": 0.48771926760673523,
      "learning_rate": 6.75277705956443e-06,
      "loss": 0.9614,
      "step": 180
    },
    {
      "epoch": 0.08851396784644538,
      "grad_norm": 0.3285332918167114,
      "learning_rate": 6.1011639384943585e-06,
      "loss": 1.0667,
      "step": 181
    },
    {
      "epoch": 0.08900299529311083,
      "grad_norm": 0.293144166469574,
      "learning_rate": 5.481617183918053e-06,
      "loss": 1.0208,
      "step": 182
    },
    {
      "epoch": 0.08949202273977627,
      "grad_norm": 0.39136576652526855,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.9498,
      "step": 183
    },
    {
      "epoch": 0.08998105018644172,
      "grad_norm": 0.31894204020500183,
      "learning_rate": 4.339558049955927e-06,
      "loss": 1.06,
      "step": 184
    },
    {
      "epoch": 0.09047007763310716,
      "grad_norm": 0.3131878972053528,
      "learning_rate": 3.817435682718096e-06,
      "loss": 0.9719,
      "step": 185
    },
    {
      "epoch": 0.0909591050797726,
      "grad_norm": 0.26452943682670593,
      "learning_rate": 3.3281595730812575e-06,
      "loss": 0.9504,
      "step": 186
    },
    {
      "epoch": 0.09144813252643805,
      "grad_norm": 0.36320924758911133,
      "learning_rate": 2.8718968083886075e-06,
      "loss": 1.1415,
      "step": 187
    },
    {
      "epoch": 0.09193715997310349,
      "grad_norm": 0.24845726788043976,
      "learning_rate": 2.4488032019563402e-06,
      "loss": 1.0171,
      "step": 188
    },
    {
      "epoch": 0.09242618741976893,
      "grad_norm": 0.5962578058242798,
      "learning_rate": 2.0590232398634114e-06,
      "loss": 0.9151,
      "step": 189
    },
    {
      "epoch": 0.09291521486643438,
      "grad_norm": 0.3705110549926758,
      "learning_rate": 1.7026900316098215e-06,
      "loss": 1.1048,
      "step": 190
    },
    {
      "epoch": 0.09340424231309982,
      "grad_norm": 0.3293691873550415,
      "learning_rate": 1.3799252646597426e-06,
      "loss": 1.1607,
      "step": 191
    },
    {
      "epoch": 0.09389326975976527,
      "grad_norm": 0.28064343333244324,
      "learning_rate": 1.0908391628854041e-06,
      "loss": 0.9642,
      "step": 192
    },
    {
      "epoch": 0.09438229720643071,
      "grad_norm": 0.4100506603717804,
      "learning_rate": 8.355304489257254e-07,
      "loss": 0.931,
      "step": 193
    },
    {
      "epoch": 0.09487132465309615,
      "grad_norm": 0.298096626996994,
      "learning_rate": 6.140863104726391e-07,
      "loss": 0.9616,
      "step": 194
    },
    {
      "epoch": 0.0953603520997616,
      "grad_norm": 0.26067015528678894,
      "learning_rate": 4.2658237049655323e-07,
      "loss": 1.0008,
      "step": 195
    },
    {
      "epoch": 0.09584937954642704,
      "grad_norm": 0.4474238157272339,
      "learning_rate": 2.7308266142119785e-07,
      "loss": 0.9659,
      "step": 196
    },
    {
      "epoch": 0.09633840699309248,
      "grad_norm": 0.27518409490585327,
      "learning_rate": 1.5363960325660565e-07,
      "loss": 1.134,
      "step": 197
    },
    {
      "epoch": 0.09682743443975793,
      "grad_norm": 0.4118005037307739,
      "learning_rate": 6.829398569770939e-08,
      "loss": 0.9985,
      "step": 198
    },
    {
      "epoch": 0.09731646188642337,
      "grad_norm": 0.38307955861091614,
      "learning_rate": 1.7074954194729044e-08,
      "loss": 1.0373,
      "step": 199
    },
    {
      "epoch": 0.09780548933308882,
      "grad_norm": 0.5424556136131287,
      "learning_rate": 0.0,
      "loss": 0.9834,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.877908391100416e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}