{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 1086,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009208103130755065,
      "grad_norm": 0.7104283979721944,
      "learning_rate": 1.8348623853211011e-06,
      "loss": 1.2184,
      "step": 1
    },
    {
      "epoch": 0.004604051565377533,
      "grad_norm": 0.8484084058142851,
      "learning_rate": 9.174311926605506e-06,
      "loss": 1.2345,
      "step": 5
    },
    {
      "epoch": 0.009208103130755065,
      "grad_norm": 0.8895650483641482,
      "learning_rate": 1.834862385321101e-05,
      "loss": 1.2996,
      "step": 10
    },
    {
      "epoch": 0.013812154696132596,
      "grad_norm": 0.6693826221356033,
      "learning_rate": 2.7522935779816515e-05,
      "loss": 1.2409,
      "step": 15
    },
    {
      "epoch": 0.01841620626151013,
      "grad_norm": 0.9775039809987707,
      "learning_rate": 3.669724770642202e-05,
      "loss": 1.078,
      "step": 20
    },
    {
      "epoch": 0.02302025782688766,
      "grad_norm": 0.42561125364219876,
      "learning_rate": 4.587155963302753e-05,
      "loss": 0.9796,
      "step": 25
    },
    {
      "epoch": 0.027624309392265192,
      "grad_norm": 0.20515777384298603,
      "learning_rate": 5.504587155963303e-05,
      "loss": 0.8728,
      "step": 30
    },
    {
      "epoch": 0.03222836095764273,
      "grad_norm": 0.21277732125436763,
      "learning_rate": 6.422018348623854e-05,
      "loss": 0.8742,
      "step": 35
    },
    {
      "epoch": 0.03683241252302026,
      "grad_norm": 0.2807596133606811,
      "learning_rate": 7.339449541284404e-05,
      "loss": 0.8226,
      "step": 40
    },
    {
      "epoch": 0.04143646408839779,
      "grad_norm": 0.2462315157718494,
      "learning_rate": 8.256880733944955e-05,
      "loss": 0.8238,
      "step": 45
    },
    {
      "epoch": 0.04604051565377532,
      "grad_norm": 0.1796423907240695,
      "learning_rate": 9.174311926605506e-05,
      "loss": 0.8043,
      "step": 50
    },
    {
      "epoch": 0.05064456721915286,
      "grad_norm": 0.16102348645765954,
      "learning_rate": 0.00010091743119266055,
      "loss": 0.7908,
      "step": 55
    },
    {
      "epoch": 0.055248618784530384,
      "grad_norm": 0.1468812473488326,
      "learning_rate": 0.00011009174311926606,
      "loss": 0.7798,
      "step": 60
    },
    {
      "epoch": 0.05985267034990792,
      "grad_norm": 0.15243943821399936,
      "learning_rate": 0.00011926605504587157,
      "loss": 0.7939,
      "step": 65
    },
    {
      "epoch": 0.06445672191528545,
      "grad_norm": 0.16911773454140264,
      "learning_rate": 0.00012844036697247707,
      "loss": 0.7692,
      "step": 70
    },
    {
      "epoch": 0.06906077348066299,
      "grad_norm": 0.14029887618581424,
      "learning_rate": 0.00013761467889908258,
      "loss": 0.7702,
      "step": 75
    },
    {
      "epoch": 0.07366482504604052,
      "grad_norm": 0.15991589862519767,
      "learning_rate": 0.0001467889908256881,
      "loss": 0.7801,
      "step": 80
    },
    {
      "epoch": 0.07826887661141804,
      "grad_norm": 0.16836933389270248,
      "learning_rate": 0.0001559633027522936,
      "loss": 0.7493,
      "step": 85
    },
    {
      "epoch": 0.08287292817679558,
      "grad_norm": 0.17161343155107908,
      "learning_rate": 0.0001651376146788991,
      "loss": 0.752,
      "step": 90
    },
    {
      "epoch": 0.08747697974217311,
      "grad_norm": 0.17139003055306476,
      "learning_rate": 0.00017431192660550458,
      "loss": 0.7504,
      "step": 95
    },
    {
      "epoch": 0.09208103130755065,
      "grad_norm": 0.14118381221233112,
      "learning_rate": 0.00018348623853211012,
      "loss": 0.7474,
      "step": 100
    },
    {
      "epoch": 0.09668508287292818,
      "grad_norm": 0.15274245520687557,
      "learning_rate": 0.0001926605504587156,
      "loss": 0.7153,
      "step": 105
    },
    {
      "epoch": 0.10128913443830571,
      "grad_norm": 0.17243376201491117,
      "learning_rate": 0.00019999948301225543,
      "loss": 0.7418,
      "step": 110
    },
    {
      "epoch": 0.10589318600368323,
      "grad_norm": 0.15501917072069255,
      "learning_rate": 0.00019998138900246913,
      "loss": 0.7471,
      "step": 115
    },
    {
      "epoch": 0.11049723756906077,
      "grad_norm": 0.1721566405839237,
      "learning_rate": 0.00019993745095073183,
      "loss": 0.7453,
      "step": 120
    },
    {
      "epoch": 0.1151012891344383,
      "grad_norm": 0.13679964856454155,
      "learning_rate": 0.00019986768021452574,
      "loss": 0.7228,
      "step": 125
    },
    {
      "epoch": 0.11970534069981584,
      "grad_norm": 0.14703324544205662,
      "learning_rate": 0.00019977209482878574,
      "loss": 0.7124,
      "step": 130
    },
    {
      "epoch": 0.12430939226519337,
      "grad_norm": 0.18865400963921064,
      "learning_rate": 0.00019965071950123732,
      "loss": 0.7536,
      "step": 135
    },
    {
      "epoch": 0.1289134438305709,
      "grad_norm": 0.1474544520231936,
      "learning_rate": 0.00019950358560601013,
      "loss": 0.7429,
      "step": 140
    },
    {
      "epoch": 0.13351749539594843,
      "grad_norm": 0.13523126598394036,
      "learning_rate": 0.00019933073117552795,
      "loss": 0.7267,
      "step": 145
    },
    {
      "epoch": 0.13812154696132597,
      "grad_norm": 0.146238565087472,
      "learning_rate": 0.00019913220089067793,
      "loss": 0.7749,
      "step": 150
    },
    {
      "epoch": 0.1427255985267035,
      "grad_norm": 0.1550423764417148,
      "learning_rate": 0.00019890804606926087,
      "loss": 0.7329,
      "step": 155
    },
    {
      "epoch": 0.14732965009208104,
      "grad_norm": 0.1591980721619053,
      "learning_rate": 0.00019865832465272635,
      "loss": 0.7534,
      "step": 160
    },
    {
      "epoch": 0.15193370165745856,
      "grad_norm": 0.1531186776106742,
      "learning_rate": 0.00019838310119119545,
      "loss": 0.756,
      "step": 165
    },
    {
      "epoch": 0.15653775322283608,
      "grad_norm": 0.1476816081597602,
      "learning_rate": 0.0001980824468267753,
      "loss": 0.7489,
      "step": 170
    },
    {
      "epoch": 0.16114180478821363,
      "grad_norm": 0.14795132619266863,
      "learning_rate": 0.00019775643927516954,
      "loss": 0.7209,
      "step": 175
    },
    {
      "epoch": 0.16574585635359115,
      "grad_norm": 0.14679273124596579,
      "learning_rate": 0.00019740516280559005,
      "loss": 0.7296,
      "step": 180
    },
    {
      "epoch": 0.1703499079189687,
      "grad_norm": 0.14120244970365975,
      "learning_rate": 0.00019702870821897386,
      "loss": 0.7512,
      "step": 185
    },
    {
      "epoch": 0.17495395948434622,
      "grad_norm": 0.1399532146516525,
      "learning_rate": 0.00019662717282451249,
      "loss": 0.7091,
      "step": 190
    },
    {
      "epoch": 0.17955801104972377,
      "grad_norm": 0.1472244949078579,
      "learning_rate": 0.00019620066041449853,
      "loss": 0.7235,
      "step": 195
    },
    {
      "epoch": 0.1841620626151013,
      "grad_norm": 0.13348485928094997,
      "learning_rate": 0.0001957492812374965,
      "loss": 0.7109,
      "step": 200
    },
    {
      "epoch": 0.1841620626151013,
      "eval_loss": 0.7064515352249146,
      "eval_runtime": 48.9511,
      "eval_samples_per_second": 10.214,
      "eval_steps_per_second": 0.654,
      "step": 200
    },
    {
      "epoch": 0.1887661141804788,
      "grad_norm": 0.12975499369978807,
      "learning_rate": 0.00019527315196984487,
      "loss": 0.7103,
      "step": 205
    },
    {
      "epoch": 0.19337016574585636,
      "grad_norm": 0.1309790778507949,
      "learning_rate": 0.00019477239568549667,
      "loss": 0.7166,
      "step": 210
    },
    {
      "epoch": 0.19797421731123388,
      "grad_norm": 0.13709065108741178,
      "learning_rate": 0.00019424714182420604,
      "loss": 0.7043,
      "step": 215
    },
    {
      "epoch": 0.20257826887661143,
      "grad_norm": 0.13342648155684383,
      "learning_rate": 0.00019369752615806988,
      "loss": 0.7136,
      "step": 220
    },
    {
      "epoch": 0.20718232044198895,
      "grad_norm": 0.13844474906898738,
      "learning_rate": 0.00019312369075643194,
      "loss": 0.7207,
      "step": 225
    },
    {
      "epoch": 0.21178637200736647,
      "grad_norm": 0.14186684102196156,
      "learning_rate": 0.00019252578394915988,
      "loss": 0.7255,
      "step": 230
    },
    {
      "epoch": 0.21639042357274402,
      "grad_norm": 0.15866211011849904,
      "learning_rate": 0.0001919039602883035,
      "loss": 0.7223,
      "step": 235
    },
    {
      "epoch": 0.22099447513812154,
      "grad_norm": 0.1314674917628441,
      "learning_rate": 0.00019125838050814472,
      "loss": 0.7228,
      "step": 240
    },
    {
      "epoch": 0.22559852670349909,
      "grad_norm": 0.14491106611651047,
      "learning_rate": 0.00019058921148364994,
      "loss": 0.7261,
      "step": 245
    },
    {
      "epoch": 0.2302025782688766,
      "grad_norm": 0.12821922589500195,
      "learning_rate": 0.00018989662618733446,
      "loss": 0.7071,
      "step": 250
    },
    {
      "epoch": 0.23480662983425415,
      "grad_norm": 0.14571212342587975,
      "learning_rate": 0.00018918080364455122,
      "loss": 0.7016,
      "step": 255
    },
    {
      "epoch": 0.23941068139963168,
      "grad_norm": 0.13772160137757872,
      "learning_rate": 0.0001884419288872147,
      "loss": 0.7069,
      "step": 260
    },
    {
      "epoch": 0.2440147329650092,
      "grad_norm": 0.1423677034382106,
      "learning_rate": 0.00018768019290597252,
      "loss": 0.7294,
      "step": 265
    },
    {
      "epoch": 0.24861878453038674,
      "grad_norm": 0.12203724600652281,
      "learning_rate": 0.0001868957926008362,
      "loss": 0.7168,
      "step": 270
    },
    {
      "epoch": 0.2532228360957643,
      "grad_norm": 0.1329347877570805,
      "learning_rate": 0.00018608893073028505,
      "loss": 0.7026,
      "step": 275
    },
    {
      "epoch": 0.2578268876611418,
      "grad_norm": 0.13186384109645674,
      "learning_rate": 0.00018525981585885536,
      "loss": 0.7082,
      "step": 280
    },
    {
      "epoch": 0.26243093922651933,
      "grad_norm": 0.14256872075438773,
      "learning_rate": 0.00018440866230322878,
      "loss": 0.6917,
      "step": 285
    },
    {
      "epoch": 0.26703499079189685,
      "grad_norm": 0.14428503648361754,
      "learning_rate": 0.00018353569007683394,
      "loss": 0.719,
      "step": 290
    },
    {
      "epoch": 0.2716390423572744,
      "grad_norm": 0.1820352962113873,
      "learning_rate": 0.00018264112483297565,
      "loss": 0.7264,
      "step": 295
    },
    {
      "epoch": 0.27624309392265195,
      "grad_norm": 0.15797994447204652,
      "learning_rate": 0.00018172519780650594,
      "loss": 0.7195,
      "step": 300
    },
    {
      "epoch": 0.28084714548802947,
      "grad_norm": 0.13313017408023753,
      "learning_rate": 0.00018078814575405244,
      "loss": 0.7425,
      "step": 305
    },
    {
      "epoch": 0.285451197053407,
      "grad_norm": 0.13520681133489493,
      "learning_rate": 0.00017983021089281983,
      "loss": 0.707,
      "step": 310
    },
    {
      "epoch": 0.2900552486187845,
      "grad_norm": 0.12245549217896762,
      "learning_rate": 0.0001788516408379791,
      "loss": 0.7154,
      "step": 315
    },
    {
      "epoch": 0.2946593001841621,
      "grad_norm": 0.12748362531526,
      "learning_rate": 0.0001778526885386621,
      "loss": 0.7197,
      "step": 320
    },
    {
      "epoch": 0.2992633517495396,
      "grad_norm": 0.11117223964124032,
      "learning_rate": 0.00017683361221257707,
      "loss": 0.6973,
      "step": 325
    },
    {
      "epoch": 0.30386740331491713,
      "grad_norm": 0.1289936719815313,
      "learning_rate": 0.0001757946752792622,
      "loss": 0.7247,
      "step": 330
    },
    {
      "epoch": 0.30847145488029465,
      "grad_norm": 0.16488859196213657,
      "learning_rate": 0.00017473614629199486,
      "loss": 0.7286,
      "step": 335
    },
    {
      "epoch": 0.31307550644567217,
      "grad_norm": 0.14470083977942239,
      "learning_rate": 0.00017365829886837353,
      "loss": 0.7343,
      "step": 340
    },
    {
      "epoch": 0.31767955801104975,
      "grad_norm": 0.13447366414444684,
      "learning_rate": 0.00017256141161959085,
      "loss": 0.7255,
      "step": 345
    },
    {
      "epoch": 0.32228360957642727,
      "grad_norm": 0.1217662376207493,
      "learning_rate": 0.00017144576807841583,
      "loss": 0.724,
      "step": 350
    },
    {
      "epoch": 0.3268876611418048,
      "grad_norm": 0.15300308488915879,
      "learning_rate": 0.00017031165662590388,
      "loss": 0.7267,
      "step": 355
    },
    {
      "epoch": 0.3314917127071823,
      "grad_norm": 0.13907462570860107,
      "learning_rate": 0.0001691593704168536,
      "loss": 0.748,
      "step": 360
    },
    {
      "epoch": 0.3360957642725598,
      "grad_norm": 0.13780875633005546,
      "learning_rate": 0.0001679892073040296,
      "loss": 0.7262,
      "step": 365
    },
    {
      "epoch": 0.3406998158379374,
      "grad_norm": 0.1305755908910725,
      "learning_rate": 0.00016680146976117105,
      "loss": 0.7155,
      "step": 370
    },
    {
      "epoch": 0.3453038674033149,
      "grad_norm": 0.14568215090440456,
      "learning_rate": 0.00016559646480480562,
      "loss": 0.7223,
      "step": 375
    },
    {
      "epoch": 0.34990791896869244,
      "grad_norm": 0.12857349185078817,
      "learning_rate": 0.00016437450391488926,
      "loss": 0.7336,
      "step": 380
    },
    {
      "epoch": 0.35451197053406996,
      "grad_norm": 0.11784320830005238,
      "learning_rate": 0.00016313590295429224,
      "loss": 0.6889,
      "step": 385
    },
    {
      "epoch": 0.35911602209944754,
      "grad_norm": 0.13646526167574166,
      "learning_rate": 0.00016188098208715218,
      "loss": 0.7192,
      "step": 390
    },
    {
      "epoch": 0.36372007366482506,
      "grad_norm": 0.12175101806984481,
      "learning_rate": 0.00016061006569611524,
      "loss": 0.6836,
      "step": 395
    },
    {
      "epoch": 0.3683241252302026,
      "grad_norm": 0.13758905451063172,
      "learning_rate": 0.00015932348229848702,
      "loss": 0.7185,
      "step": 400
    },
    {
      "epoch": 0.3683241252302026,
      "eval_loss": 0.6904310584068298,
      "eval_runtime": 47.8076,
      "eval_samples_per_second": 10.459,
      "eval_steps_per_second": 0.669,
      "step": 400
    },
    {
      "epoch": 0.3729281767955801,
      "grad_norm": 0.11922226680398379,
      "learning_rate": 0.00015802156446131463,
      "loss": 0.7108,
      "step": 405
    },
    {
      "epoch": 0.3775322283609576,
      "grad_norm": 0.12914369421847746,
      "learning_rate": 0.0001567046487154218,
      "loss": 0.7297,
      "step": 410
    },
    {
      "epoch": 0.3821362799263352,
      "grad_norm": 0.163588935842005,
      "learning_rate": 0.0001553730754684196,
      "loss": 0.7286,
      "step": 415
    },
    {
      "epoch": 0.3867403314917127,
      "grad_norm": 0.1305481480361055,
      "learning_rate": 0.000154027188916715,
      "loss": 0.7083,
      "step": 420
    },
    {
      "epoch": 0.39134438305709024,
      "grad_norm": 0.13075746937102734,
      "learning_rate": 0.00015266733695653998,
      "loss": 0.7022,
      "step": 425
    },
    {
      "epoch": 0.39594843462246776,
      "grad_norm": 0.13867395016440975,
      "learning_rate": 0.0001512938710940244,
      "loss": 0.6883,
      "step": 430
    },
    {
      "epoch": 0.4005524861878453,
      "grad_norm": 0.1468540519744832,
      "learning_rate": 0.00014990714635433567,
      "loss": 0.724,
      "step": 435
    },
    {
      "epoch": 0.40515653775322286,
      "grad_norm": 0.1306098517144093,
      "learning_rate": 0.00014850752118990884,
      "loss": 0.7063,
      "step": 440
    },
    {
      "epoch": 0.4097605893186004,
      "grad_norm": 0.1424067979705426,
      "learning_rate": 0.00014709535738779075,
      "loss": 0.7402,
      "step": 445
    },
    {
      "epoch": 0.4143646408839779,
      "grad_norm": 0.1407997721241163,
      "learning_rate": 0.00014567101997612215,
      "loss": 0.7006,
      "step": 450
    },
    {
      "epoch": 0.4189686924493554,
      "grad_norm": 0.14729031365921527,
      "learning_rate": 0.00014423487712978238,
      "loss": 0.7024,
      "step": 455
    },
    {
      "epoch": 0.42357274401473294,
      "grad_norm": 0.13260028024156117,
      "learning_rate": 0.00014278730007521998,
      "loss": 0.7173,
      "step": 460
    },
    {
      "epoch": 0.4281767955801105,
      "grad_norm": 0.1335675383386336,
      "learning_rate": 0.00014132866299449524,
      "loss": 0.7289,
      "step": 465
    },
    {
      "epoch": 0.43278084714548803,
      "grad_norm": 0.14637775224173455,
      "learning_rate": 0.00013985934292855826,
      "loss": 0.7005,
      "step": 470
    },
    {
      "epoch": 0.43738489871086556,
      "grad_norm": 0.1502047175694278,
      "learning_rate": 0.00013837971967978836,
      "loss": 0.7004,
      "step": 475
    },
    {
      "epoch": 0.4419889502762431,
      "grad_norm": 0.14633484532534424,
      "learning_rate": 0.00013689017571381928,
      "loss": 0.7288,
      "step": 480
    },
    {
      "epoch": 0.44659300184162065,
      "grad_norm": 0.13826365436143537,
      "learning_rate": 0.00013539109606067643,
      "loss": 0.7085,
      "step": 485
    },
    {
      "epoch": 0.45119705340699817,
      "grad_norm": 0.14385098441490782,
      "learning_rate": 0.00013388286821525085,
      "loss": 0.6974,
      "step": 490
    },
    {
      "epoch": 0.4558011049723757,
      "grad_norm": 0.13011880817111474,
      "learning_rate": 0.00013236588203713646,
      "loss": 0.7041,
      "step": 495
    },
    {
      "epoch": 0.4604051565377532,
      "grad_norm": 0.12462262006306969,
      "learning_rate": 0.0001308405296498556,
      "loss": 0.6962,
      "step": 500
    },
    {
      "epoch": 0.46500920810313073,
      "grad_norm": 0.12244444903136163,
      "learning_rate": 0.00012930720533949966,
      "loss": 0.6999,
      "step": 505
    },
    {
      "epoch": 0.4696132596685083,
      "grad_norm": 0.1339305914859919,
      "learning_rate": 0.00012776630545281088,
      "loss": 0.6806,
      "step": 510
    },
    {
      "epoch": 0.47421731123388583,
      "grad_norm": 0.13980664973687393,
      "learning_rate": 0.00012621822829473074,
      "loss": 0.7394,
      "step": 515
    },
    {
      "epoch": 0.47882136279926335,
      "grad_norm": 0.16365863143826853,
      "learning_rate": 0.00012466337402544333,
      "loss": 0.7279,
      "step": 520
    },
    {
      "epoch": 0.48342541436464087,
      "grad_norm": 0.1335430922734083,
      "learning_rate": 0.00012310214455693808,
      "loss": 0.7034,
      "step": 525
    },
    {
      "epoch": 0.4880294659300184,
      "grad_norm": 0.14433559304424956,
      "learning_rate": 0.0001215349434491203,
      "loss": 0.6937,
      "step": 530
    },
    {
      "epoch": 0.49263351749539597,
      "grad_norm": 0.132024243038777,
      "learning_rate": 0.00011996217580549556,
      "loss": 0.6986,
      "step": 535
    },
    {
      "epoch": 0.4972375690607735,
      "grad_norm": 0.13633158247507002,
      "learning_rate": 0.00011838424816845506,
      "loss": 0.7044,
      "step": 540
    },
    {
      "epoch": 0.501841620626151,
      "grad_norm": 0.12135498656651347,
      "learning_rate": 0.0001168015684141891,
      "loss": 0.7231,
      "step": 545
    },
    {
      "epoch": 0.5064456721915286,
      "grad_norm": 0.1381176811216971,
      "learning_rate": 0.0001152145456472558,
      "loss": 0.6942,
      "step": 550
    },
    {
      "epoch": 0.511049723756906,
      "grad_norm": 0.14462125066523807,
      "learning_rate": 0.00011362359009483212,
      "loss": 0.7,
      "step": 555
    },
    {
      "epoch": 0.5156537753222836,
      "grad_norm": 0.1401876774896849,
      "learning_rate": 0.00011202911300067507,
      "loss": 0.6917,
      "step": 560
    },
    {
      "epoch": 0.5202578268876611,
      "grad_norm": 0.12761995189511605,
      "learning_rate": 0.00011043152651881971,
      "loss": 0.6913,
      "step": 565
    },
    {
      "epoch": 0.5248618784530387,
      "grad_norm": 0.1309083720987428,
      "learning_rate": 0.0001088312436070422,
      "loss": 0.7039,
      "step": 570
    },
    {
      "epoch": 0.5294659300184162,
      "grad_norm": 0.13969770628383765,
      "learning_rate": 0.00010722867792011486,
      "loss": 0.7138,
      "step": 575
    },
    {
      "epoch": 0.5340699815837937,
      "grad_norm": 0.12065461537026531,
      "learning_rate": 0.0001056242437028812,
      "loss": 0.7012,
      "step": 580
    },
    {
      "epoch": 0.5386740331491713,
      "grad_norm": 0.1403328333527622,
      "learning_rate": 0.00010401835568317842,
      "loss": 0.7107,
      "step": 585
    },
    {
      "epoch": 0.5432780847145487,
      "grad_norm": 0.1524065503450793,
      "learning_rate": 0.00010241142896463491,
      "loss": 0.7253,
      "step": 590
    },
    {
      "epoch": 0.5478821362799263,
      "grad_norm": 0.1459506865219953,
      "learning_rate": 0.00010080387891937084,
      "loss": 0.7164,
      "step": 595
    },
    {
      "epoch": 0.5524861878453039,
      "grad_norm": 0.13249474415125184,
      "learning_rate": 9.91961210806292e-05,
      "loss": 0.7062,
      "step": 600
    },
    {
      "epoch": 0.5524861878453039,
      "eval_loss": 0.681869387626648,
      "eval_runtime": 47.8405,
      "eval_samples_per_second": 10.451,
      "eval_steps_per_second": 0.669,
      "step": 600
    },
    {
      "epoch": 0.5570902394106814,
      "grad_norm": 0.12788937438752834,
      "learning_rate": 9.758857103536513e-05,
      "loss": 0.7099,
      "step": 605
    },
    {
      "epoch": 0.5616942909760589,
      "grad_norm": 0.14086950862534534,
      "learning_rate": 9.59816443168216e-05,
      "loss": 0.6991,
      "step": 610
    },
    {
      "epoch": 0.5662983425414365,
      "grad_norm": 0.12626280805151868,
      "learning_rate": 9.437575629711882e-05,
      "loss": 0.7099,
      "step": 615
    },
    {
      "epoch": 0.570902394106814,
      "grad_norm": 0.14750922735308492,
      "learning_rate": 9.277132207988517e-05,
      "loss": 0.7116,
      "step": 620
    },
    {
      "epoch": 0.5755064456721916,
      "grad_norm": 0.12947957016862066,
      "learning_rate": 9.116875639295782e-05,
      "loss": 0.7173,
      "step": 625
    },
    {
      "epoch": 0.580110497237569,
      "grad_norm": 0.1217085102913984,
      "learning_rate": 8.95684734811803e-05,
      "loss": 0.6782,
      "step": 630
    },
    {
      "epoch": 0.5847145488029466,
      "grad_norm": 0.12805246153113478,
      "learning_rate": 8.797088699932494e-05,
      "loss": 0.6981,
      "step": 635
    },
    {
      "epoch": 0.5893186003683242,
      "grad_norm": 0.13677967208339983,
      "learning_rate": 8.637640990516792e-05,
      "loss": 0.725,
      "step": 640
    },
    {
      "epoch": 0.5939226519337016,
      "grad_norm": 0.1348897795554575,
      "learning_rate": 8.478545435274423e-05,
      "loss": 0.7403,
      "step": 645
    },
    {
      "epoch": 0.5985267034990792,
      "grad_norm": 0.1425142278541099,
      "learning_rate": 8.319843158581092e-05,
      "loss": 0.7524,
      "step": 650
    },
    {
      "epoch": 0.6031307550644567,
      "grad_norm": 0.1371048777547919,
      "learning_rate": 8.161575183154495e-05,
      "loss": 0.7075,
      "step": 655
    },
    {
      "epoch": 0.6077348066298343,
      "grad_norm": 0.1445081769660327,
      "learning_rate": 8.003782419450447e-05,
      "loss": 0.6835,
      "step": 660
    },
    {
      "epoch": 0.6123388581952118,
      "grad_norm": 0.11760848785277568,
      "learning_rate": 7.846505655087972e-05,
      "loss": 0.7081,
      "step": 665
    },
    {
      "epoch": 0.6169429097605893,
      "grad_norm": 0.1438799054992206,
      "learning_rate": 7.689785544306193e-05,
      "loss": 0.7187,
      "step": 670
    },
    {
      "epoch": 0.6215469613259669,
      "grad_norm": 0.14002441000957835,
      "learning_rate": 7.533662597455667e-05,
      "loss": 0.7009,
      "step": 675
    },
    {
      "epoch": 0.6261510128913443,
      "grad_norm": 0.14656402716158887,
      "learning_rate": 7.378177170526927e-05,
      "loss": 0.6918,
      "step": 680
    },
    {
      "epoch": 0.6307550644567219,
      "grad_norm": 0.15779771059270742,
      "learning_rate": 7.223369454718918e-05,
      "loss": 0.7186,
      "step": 685
    },
    {
      "epoch": 0.6353591160220995,
      "grad_norm": 0.11794313696285232,
      "learning_rate": 7.069279466050035e-05,
      "loss": 0.6843,
      "step": 690
    },
    {
      "epoch": 0.639963167587477,
      "grad_norm": 0.13595292601440173,
      "learning_rate": 6.915947035014443e-05,
      "loss": 0.7168,
      "step": 695
    },
    {
      "epoch": 0.6445672191528545,
      "grad_norm": 0.1344328444601024,
      "learning_rate": 6.763411796286357e-05,
      "loss": 0.6965,
      "step": 700
    },
    {
      "epoch": 0.649171270718232,
      "grad_norm": 0.1231670701178996,
      "learning_rate": 6.611713178474916e-05,
      "loss": 0.7244,
      "step": 705
    },
    {
      "epoch": 0.6537753222836096,
      "grad_norm": 0.1437978280644596,
      "learning_rate": 6.460890393932362e-05,
      "loss": 0.6734,
      "step": 710
    },
    {
      "epoch": 0.6583793738489871,
      "grad_norm": 0.13712514064241163,
      "learning_rate": 6.310982428618077e-05,
      "loss": 0.7112,
      "step": 715
    },
    {
      "epoch": 0.6629834254143646,
      "grad_norm": 0.12729820444217552,
      "learning_rate": 6.162028032021167e-05,
      "loss": 0.677,
      "step": 720
    },
    {
      "epoch": 0.6675874769797422,
      "grad_norm": 0.12007586806931402,
      "learning_rate": 6.014065707144176e-05,
      "loss": 0.6761,
      "step": 725
    },
    {
      "epoch": 0.6721915285451197,
      "grad_norm": 0.11950710825018164,
      "learning_rate": 5.867133700550479e-05,
      "loss": 0.7132,
      "step": 730
    },
    {
      "epoch": 0.6767955801104972,
      "grad_norm": 0.12219449475526536,
      "learning_rate": 5.721269992478002e-05,
      "loss": 0.6891,
      "step": 735
    },
    {
      "epoch": 0.6813996316758748,
      "grad_norm": 0.13820553666745064,
      "learning_rate": 5.576512287021765e-05,
      "loss": 0.7032,
      "step": 740
    },
    {
      "epoch": 0.6860036832412523,
      "grad_norm": 0.12575435617713188,
      "learning_rate": 5.432898002387783e-05,
      "loss": 0.685,
      "step": 745
    },
    {
      "epoch": 0.6906077348066298,
      "grad_norm": 0.12305743189245932,
      "learning_rate": 5.290464261220927e-05,
      "loss": 0.6874,
      "step": 750
    },
    {
      "epoch": 0.6952117863720073,
      "grad_norm": 0.1602899973447253,
      "learning_rate": 5.149247881009118e-05,
      "loss": 0.7074,
      "step": 755
    },
    {
      "epoch": 0.6998158379373849,
      "grad_norm": 0.11125288181618329,
      "learning_rate": 5.009285364566435e-05,
      "loss": 0.6646,
      "step": 760
    },
    {
      "epoch": 0.7044198895027625,
      "grad_norm": 0.12864820726453974,
      "learning_rate": 4.870612890597565e-05,
      "loss": 0.6976,
      "step": 765
    },
    {
      "epoch": 0.7090239410681399,
      "grad_norm": 0.12633554254462218,
      "learning_rate": 4.733266304346005e-05,
      "loss": 0.6886,
      "step": 770
    },
    {
      "epoch": 0.7136279926335175,
      "grad_norm": 0.13645165523957492,
      "learning_rate": 4.5972811083285014e-05,
      "loss": 0.7263,
      "step": 775
    },
    {
      "epoch": 0.7182320441988951,
      "grad_norm": 0.14653256629663075,
      "learning_rate": 4.462692453158039e-05,
      "loss": 0.7078,
      "step": 780
    },
    {
      "epoch": 0.7228360957642725,
      "grad_norm": 0.13327438185784568,
      "learning_rate": 4.329535128457822e-05,
      "loss": 0.7057,
      "step": 785
    },
    {
      "epoch": 0.7274401473296501,
      "grad_norm": 0.1383815308770519,
      "learning_rate": 4.197843553868538e-05,
      "loss": 0.6894,
      "step": 790
    },
    {
      "epoch": 0.7320441988950276,
      "grad_norm": 0.12797224319884995,
      "learning_rate": 4.0676517701513015e-05,
      "loss": 0.685,
      "step": 795
    },
    {
      "epoch": 0.7366482504604052,
      "grad_norm": 0.13203365820667615,
      "learning_rate": 3.93899343038848e-05,
      "loss": 0.6629,
      "step": 800
    },
    {
      "epoch": 0.7366482504604052,
      "eval_loss": 0.6758299469947815,
      "eval_runtime": 47.789,
      "eval_samples_per_second": 10.463,
      "eval_steps_per_second": 0.67,
      "step": 800
    },
    {
      "epoch": 0.7412523020257827,
      "grad_norm": 0.14945609861259754,
      "learning_rate": 3.8119017912847873e-05,
      "loss": 0.7157,
      "step": 805
    },
    {
      "epoch": 0.7458563535911602,
      "grad_norm": 0.14064204226125424,
      "learning_rate": 3.686409704570778e-05,
      "loss": 0.7077,
      "step": 810
    },
    {
      "epoch": 0.7504604051565378,
      "grad_norm": 0.15174343823382735,
      "learning_rate": 3.5625496085110754e-05,
      "loss": 0.714,
      "step": 815
    },
    {
      "epoch": 0.7550644567219152,
      "grad_norm": 0.13218371839998455,
      "learning_rate": 3.440353519519439e-05,
      "loss": 0.7095,
      "step": 820
    },
    {
      "epoch": 0.7596685082872928,
      "grad_norm": 0.1323028538168689,
      "learning_rate": 3.3198530238828976e-05,
      "loss": 0.6971,
      "step": 825
    },
    {
      "epoch": 0.7642725598526704,
      "grad_norm": 0.14745827705981765,
      "learning_rate": 3.20107926959704e-05,
      "loss": 0.7041,
      "step": 830
    },
    {
      "epoch": 0.7688766114180479,
      "grad_norm": 0.1442754442357172,
      "learning_rate": 3.0840629583146416e-05,
      "loss": 0.6814,
      "step": 835
    },
    {
      "epoch": 0.7734806629834254,
      "grad_norm": 0.13106050495634988,
      "learning_rate": 2.9688343374096115e-05,
      "loss": 0.6823,
      "step": 840
    },
    {
      "epoch": 0.7780847145488029,
      "grad_norm": 0.1644775188382007,
      "learning_rate": 2.8554231921584162e-05,
      "loss": 0.7221,
      "step": 845
    },
    {
      "epoch": 0.7826887661141805,
      "grad_norm": 0.13022155447713443,
      "learning_rate": 2.743858838040918e-05,
      "loss": 0.7135,
      "step": 850
    },
    {
      "epoch": 0.787292817679558,
      "grad_norm": 0.13264345669070807,
      "learning_rate": 2.6341701131626486e-05,
      "loss": 0.6979,
      "step": 855
    },
    {
      "epoch": 0.7918968692449355,
      "grad_norm": 0.14323695673993403,
      "learning_rate": 2.526385370800515e-05,
      "loss": 0.6969,
      "step": 860
    },
    {
      "epoch": 0.7965009208103131,
      "grad_norm": 0.1542994659104081,
      "learning_rate": 2.4205324720737786e-05,
      "loss": 0.7042,
      "step": 865
    },
    {
      "epoch": 0.8011049723756906,
      "grad_norm": 0.1449879659078434,
      "learning_rate": 2.316638778742295e-05,
      "loss": 0.6899,
      "step": 870
    },
    {
      "epoch": 0.8057090239410681,
      "grad_norm": 0.13076802781423985,
      "learning_rate": 2.214731146133793e-05,
      "loss": 0.7111,
      "step": 875
    },
    {
      "epoch": 0.8103130755064457,
      "grad_norm": 0.13291253398347233,
      "learning_rate": 2.1148359162020937e-05,
      "loss": 0.6914,
      "step": 880
    },
    {
      "epoch": 0.8149171270718232,
      "grad_norm": 0.13550181071065082,
      "learning_rate": 2.0169789107180193e-05,
      "loss": 0.6866,
      "step": 885
    },
    {
      "epoch": 0.8195211786372008,
      "grad_norm": 0.1210302923733577,
      "learning_rate": 1.921185424594758e-05,
      "loss": 0.6879,
      "step": 890
    },
    {
      "epoch": 0.8241252302025782,
      "grad_norm": 0.14037576745574026,
      "learning_rate": 1.827480219349409e-05,
      "loss": 0.7038,
      "step": 895
    },
    {
      "epoch": 0.8287292817679558,
      "grad_norm": 0.14791019025478577,
      "learning_rate": 1.7358875167024335e-05,
      "loss": 0.6604,
      "step": 900
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.11954867056661006,
      "learning_rate": 1.6464309923166033e-05,
      "loss": 0.7045,
      "step": 905
    },
    {
      "epoch": 0.8379373848987108,
      "grad_norm": 0.13365725863804348,
      "learning_rate": 1.5591337696771246e-05,
      "loss": 0.7313,
      "step": 910
    },
    {
      "epoch": 0.8425414364640884,
      "grad_norm": 0.13259625682339735,
      "learning_rate": 1.4740184141144664e-05,
      "loss": 0.7099,
      "step": 915
    },
    {
      "epoch": 0.8471454880294659,
      "grad_norm": 0.14145923503935914,
      "learning_rate": 1.391106926971496e-05,
      "loss": 0.6952,
      "step": 920
    },
    {
      "epoch": 0.8517495395948435,
      "grad_norm": 0.14338379016355754,
      "learning_rate": 1.3104207399163815e-05,
      "loss": 0.6856,
      "step": 925
    },
    {
      "epoch": 0.856353591160221,
      "grad_norm": 0.14829983664793228,
      "learning_rate": 1.2319807094027492e-05,
      "loss": 0.7156,
      "step": 930
    },
    {
      "epoch": 0.8609576427255985,
      "grad_norm": 0.12075075754668071,
      "learning_rate": 1.1558071112785296e-05,
      "loss": 0.6929,
      "step": 935
    },
    {
      "epoch": 0.8655616942909761,
      "grad_norm": 0.12950812269617865,
      "learning_rate": 1.0819196355448801e-05,
      "loss": 0.7045,
      "step": 940
    },
    {
      "epoch": 0.8701657458563536,
      "grad_norm": 0.1348184333941541,
      "learning_rate": 1.0103373812665551e-05,
      "loss": 0.6891,
      "step": 945
    },
    {
      "epoch": 0.8747697974217311,
      "grad_norm": 0.12025879421103704,
      "learning_rate": 9.410788516350077e-06,
      "loss": 0.6829,
      "step": 950
    },
    {
      "epoch": 0.8793738489871087,
      "grad_norm": 0.1332253794557465,
      "learning_rate": 8.741619491855291e-06,
      "loss": 0.7057,
      "step": 955
    },
    {
      "epoch": 0.8839779005524862,
      "grad_norm": 0.1219486531845245,
      "learning_rate": 8.096039711696545e-06,
      "loss": 0.701,
      "step": 960
    },
    {
      "epoch": 0.8885819521178637,
      "grad_norm": 0.13660210114125856,
      "learning_rate": 7.474216050840122e-06,
      "loss": 0.7016,
      "step": 965
    },
    {
      "epoch": 0.8931860036832413,
      "grad_norm": 0.11517510371236951,
      "learning_rate": 6.876309243568058e-06,
      "loss": 0.6961,
      "step": 970
    },
    {
      "epoch": 0.8977900552486188,
      "grad_norm": 0.14163517493869995,
      "learning_rate": 6.302473841930134e-06,
      "loss": 0.7082,
      "step": 975
    },
    {
      "epoch": 0.9023941068139963,
      "grad_norm": 0.14904472118298337,
      "learning_rate": 5.752858175793951e-06,
      "loss": 0.7017,
      "step": 980
    },
    {
      "epoch": 0.9069981583793738,
      "grad_norm": 0.13222086336141328,
      "learning_rate": 5.2276043145033425e-06,
      "loss": 0.6951,
      "step": 985
    },
    {
      "epoch": 0.9116022099447514,
      "grad_norm": 0.12747716652913677,
      "learning_rate": 4.726848030155129e-06,
      "loss": 0.727,
      "step": 990
    },
    {
      "epoch": 0.916206261510129,
      "grad_norm": 0.142369192844187,
      "learning_rate": 4.2507187625035135e-06,
      "loss": 0.7112,
      "step": 995
    },
    {
      "epoch": 0.9208103130755064,
      "grad_norm": 0.12916678602655413,
      "learning_rate": 3.7993395855014936e-06,
      "loss": 0.6769,
      "step": 1000
    },
    {
      "epoch": 0.9208103130755064,
      "eval_loss": 0.6735966205596924,
      "eval_runtime": 47.6678,
      "eval_samples_per_second": 10.489,
      "eval_steps_per_second": 0.671,
      "step": 1000
    },
    {
      "epoch": 0.925414364640884,
      "grad_norm": 0.1315541461105031,
      "learning_rate": 3.372827175487536e-06,
      "loss": 0.7239,
      "step": 1005
    },
    {
      "epoch": 0.9300184162062615,
      "grad_norm": 0.12551668481359965,
      "learning_rate": 2.9712917810261644e-06,
      "loss": 0.707,
      "step": 1010
    },
    {
      "epoch": 0.934622467771639,
      "grad_norm": 0.13010659142747308,
      "learning_rate": 2.5948371944099713e-06,
      "loss": 0.7066,
      "step": 1015
    },
    {
      "epoch": 0.9392265193370166,
      "grad_norm": 0.1374733909690572,
      "learning_rate": 2.2435607248304623e-06,
      "loss": 0.6981,
      "step": 1020
    },
    {
      "epoch": 0.9438305709023941,
      "grad_norm": 0.1557801553309302,
      "learning_rate": 1.91755317322474e-06,
      "loss": 0.6994,
      "step": 1025
    },
    {
      "epoch": 0.9484346224677717,
      "grad_norm": 0.1264138943615379,
      "learning_rate": 1.6168988088045678e-06,
      "loss": 0.704,
      "step": 1030
    },
    {
      "epoch": 0.9530386740331491,
      "grad_norm": 0.10632950484964579,
      "learning_rate": 1.341675347273652e-06,
      "loss": 0.677,
      "step": 1035
    },
    {
      "epoch": 0.9576427255985267,
      "grad_norm": 0.1230994587161385,
      "learning_rate": 1.0919539307391314e-06,
      "loss": 0.6891,
      "step": 1040
    },
    {
      "epoch": 0.9622467771639043,
      "grad_norm": 0.1356286737876717,
      "learning_rate": 8.67799109322076e-07,
      "loss": 0.6993,
      "step": 1045
    },
    {
      "epoch": 0.9668508287292817,
      "grad_norm": 0.1544804686351126,
      "learning_rate": 6.692688244720358e-07,
      "loss": 0.6888,
      "step": 1050
    },
    {
      "epoch": 0.9714548802946593,
      "grad_norm": 0.1409581730070821,
      "learning_rate": 4.964143939898746e-07,
      "loss": 0.7092,
      "step": 1055
    },
    {
      "epoch": 0.9760589318600368,
      "grad_norm": 0.13126265245760058,
      "learning_rate": 3.49280498762683e-07,
      "loss": 0.7008,
      "step": 1060
    },
    {
      "epoch": 0.9806629834254144,
      "grad_norm": 0.13981476492383843,
      "learning_rate": 2.2790517121428212e-07,
      "loss": 0.682,
      "step": 1065
    },
    {
      "epoch": 0.9852670349907919,
      "grad_norm": 0.11466302388077335,
      "learning_rate": 1.323197854742775e-07,
      "loss": 0.7008,
      "step": 1070
    },
    {
      "epoch": 0.9898710865561694,
      "grad_norm": 0.14514253246885966,
      "learning_rate": 6.254904926820126e-08,
      "loss": 0.7039,
      "step": 1075
    },
    {
      "epoch": 0.994475138121547,
      "grad_norm": 0.12201481168818025,
      "learning_rate": 1.8610997530876807e-08,
      "loss": 0.696,
      "step": 1080
    },
    {
      "epoch": 0.9990791896869244,
      "grad_norm": 0.13117233881672566,
      "learning_rate": 5.169877445809767e-10,
      "loss": 0.6881,
      "step": 1085
    },
    {
      "epoch": 1.0,
      "step": 1086,
      "total_flos": 4801486812086272.0,
      "train_loss": 0.7253576234998405,
      "train_runtime": 22925.9932,
      "train_samples_per_second": 3.031,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 5,
  "max_steps": 1086,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 4801486812086272.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}