{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994447529150472,
  "eval_steps": 500,
  "global_step": 1125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008883953359244865,
      "grad_norm": 7.145284317443716,
      "learning_rate": 7.964601769911505e-06,
      "loss": 1.8118,
      "step": 10
    },
    {
      "epoch": 0.01776790671848973,
      "grad_norm": 2.7965512211942167,
      "learning_rate": 1.6814159292035402e-05,
      "loss": 0.8943,
      "step": 20
    },
    {
      "epoch": 0.026651860077734593,
      "grad_norm": 2.52198818005358,
      "learning_rate": 2.5663716814159294e-05,
      "loss": 0.7037,
      "step": 30
    },
    {
      "epoch": 0.03553581343697946,
      "grad_norm": 2.640551660044096,
      "learning_rate": 3.451327433628319e-05,
      "loss": 0.6595,
      "step": 40
    },
    {
      "epoch": 0.04441976679622432,
      "grad_norm": 1.9108291045706514,
      "learning_rate": 4.3362831858407084e-05,
      "loss": 0.6665,
      "step": 50
    },
    {
      "epoch": 0.053303720155469185,
      "grad_norm": 2.1546051468612846,
      "learning_rate": 5.221238938053098e-05,
      "loss": 0.6462,
      "step": 60
    },
    {
      "epoch": 0.06218767351471405,
      "grad_norm": 2.004187481902255,
      "learning_rate": 6.106194690265487e-05,
      "loss": 0.6577,
      "step": 70
    },
    {
      "epoch": 0.07107162687395892,
      "grad_norm": 1.9561540008402594,
      "learning_rate": 6.991150442477876e-05,
      "loss": 0.6418,
      "step": 80
    },
    {
      "epoch": 0.07995558023320377,
      "grad_norm": 1.8744879243401817,
      "learning_rate": 7.876106194690266e-05,
      "loss": 0.649,
      "step": 90
    },
    {
      "epoch": 0.08883953359244864,
      "grad_norm": 1.8370317559307139,
      "learning_rate": 8.761061946902655e-05,
      "loss": 0.6445,
      "step": 100
    },
    {
      "epoch": 0.0977234869516935,
      "grad_norm": 1.6170207259621807,
      "learning_rate": 9.646017699115044e-05,
      "loss": 0.6389,
      "step": 110
    },
    {
      "epoch": 0.10660744031093837,
      "grad_norm": 1.9286438033824642,
      "learning_rate": 9.999132701342811e-05,
      "loss": 0.6245,
      "step": 120
    },
    {
      "epoch": 0.11549139367018323,
      "grad_norm": 1.4592782362892012,
      "learning_rate": 9.993833632459674e-05,
      "loss": 0.6505,
      "step": 130
    },
    {
      "epoch": 0.1243753470294281,
      "grad_norm": 1.4603184493249735,
      "learning_rate": 9.983722427355155e-05,
      "loss": 0.634,
      "step": 140
    },
    {
      "epoch": 0.13325930038867295,
      "grad_norm": 1.28461250855234,
      "learning_rate": 9.968808829344692e-05,
      "loss": 0.647,
      "step": 150
    },
    {
      "epoch": 0.14214325374791784,
      "grad_norm": 1.533676258732481,
      "learning_rate": 9.949107209404665e-05,
      "loss": 0.6571,
      "step": 160
    },
    {
      "epoch": 0.1510272071071627,
      "grad_norm": 1.4760774155344853,
      "learning_rate": 9.924636552324296e-05,
      "loss": 0.6497,
      "step": 170
    },
    {
      "epoch": 0.15991116046640755,
      "grad_norm": 1.151413186962416,
      "learning_rate": 9.895420438411616e-05,
      "loss": 0.6532,
      "step": 180
    },
    {
      "epoch": 0.1687951138256524,
      "grad_norm": 1.174712075462672,
      "learning_rate": 9.861487020771101e-05,
      "loss": 0.6467,
      "step": 190
    },
    {
      "epoch": 0.1776790671848973,
      "grad_norm": 1.2455924824979874,
      "learning_rate": 9.822868998174914e-05,
      "loss": 0.6405,
      "step": 200
    },
    {
      "epoch": 0.18656302054414214,
      "grad_norm": 1.2400525428397455,
      "learning_rate": 9.779603583553842e-05,
      "loss": 0.6476,
      "step": 210
    },
    {
      "epoch": 0.195446973903387,
      "grad_norm": 1.0651173413369808,
      "learning_rate": 9.731732468138339e-05,
      "loss": 0.6381,
      "step": 220
    },
    {
      "epoch": 0.20433092726263188,
      "grad_norm": 1.1733400582559406,
      "learning_rate": 9.679301781284208e-05,
      "loss": 0.6439,
      "step": 230
    },
    {
      "epoch": 0.21321488062187674,
      "grad_norm": 1.1082628815442315,
      "learning_rate": 9.622362046021629e-05,
      "loss": 0.6419,
      "step": 240
    },
    {
      "epoch": 0.2220988339811216,
      "grad_norm": 1.0889473659720412,
      "learning_rate": 9.560968130370376e-05,
      "loss": 0.6284,
      "step": 250
    },
    {
      "epoch": 0.23098278734036645,
      "grad_norm": 1.1452635391558985,
      "learning_rate": 9.495179194468136e-05,
      "loss": 0.6335,
      "step": 260
    },
    {
      "epoch": 0.23986674069961134,
      "grad_norm": 0.960785416210124,
      "learning_rate": 9.425058633562869e-05,
      "loss": 0.6354,
      "step": 270
    },
    {
      "epoch": 0.2487506940588562,
      "grad_norm": 1.0941677767497677,
      "learning_rate": 9.350674016924169e-05,
      "loss": 0.6168,
      "step": 280
    },
    {
      "epoch": 0.25763464741810105,
      "grad_norm": 1.1671218385270385,
      "learning_rate": 9.272097022732443e-05,
      "loss": 0.5998,
      "step": 290
    },
    {
      "epoch": 0.2665186007773459,
      "grad_norm": 1.2417631046589852,
      "learning_rate": 9.189403369008704e-05,
      "loss": 0.6022,
      "step": 300
    },
    {
      "epoch": 0.27540255413659076,
      "grad_norm": 1.1142360303839138,
      "learning_rate": 9.102672740651499e-05,
      "loss": 0.6191,
      "step": 310
    },
    {
      "epoch": 0.28428650749583567,
      "grad_norm": 0.9438534459217494,
      "learning_rate": 9.011988712651295e-05,
      "loss": 0.6096,
      "step": 320
    },
    {
      "epoch": 0.29317046085508053,
      "grad_norm": 0.9290837971651253,
      "learning_rate": 8.917438669556306e-05,
      "loss": 0.612,
      "step": 330
    },
    {
      "epoch": 0.3020544142143254,
      "grad_norm": 0.958142682716488,
      "learning_rate": 8.819113721267384e-05,
      "loss": 0.6035,
      "step": 340
    },
    {
      "epoch": 0.31093836757357024,
      "grad_norm": 0.9363183065615976,
      "learning_rate": 8.717108615243082e-05,
      "loss": 0.5999,
      "step": 350
    },
    {
      "epoch": 0.3198223209328151,
      "grad_norm": 0.9514690883713478,
      "learning_rate": 8.611521645199532e-05,
      "loss": 0.6115,
      "step": 360
    },
    {
      "epoch": 0.32870627429205995,
      "grad_norm": 0.9641199416516146,
      "learning_rate": 8.502454556393072e-05,
      "loss": 0.6169,
      "step": 370
    },
    {
      "epoch": 0.3375902276513048,
      "grad_norm": 1.116836429615264,
      "learning_rate": 8.390012447576931e-05,
      "loss": 0.5941,
      "step": 380
    },
    {
      "epoch": 0.3464741810105497,
      "grad_norm": 1.011744171328476,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.6117,
      "step": 390
    },
    {
      "epoch": 0.3553581343697946,
      "grad_norm": 1.0295043832172521,
      "learning_rate": 8.155439721630264e-05,
      "loss": 0.5965,
      "step": 400
    },
    {
      "epoch": 0.36424208772903943,
      "grad_norm": 0.9756558123458504,
      "learning_rate": 8.033535142448569e-05,
      "loss": 0.5908,
      "step": 410
    },
    {
      "epoch": 0.3731260410882843,
      "grad_norm": 1.1086690102344983,
      "learning_rate": 7.908707401341147e-05,
      "loss": 0.6077,
      "step": 420
    },
    {
      "epoch": 0.38200999444752914,
      "grad_norm": 0.9121958416780401,
      "learning_rate": 7.781076784272376e-05,
      "loss": 0.6075,
      "step": 430
    },
    {
      "epoch": 0.390893947806774,
      "grad_norm": 0.8922916792193211,
      "learning_rate": 7.650766278101761e-05,
      "loss": 0.5745,
      "step": 440
    },
    {
      "epoch": 0.39977790116601886,
      "grad_norm": 0.9862289807233917,
      "learning_rate": 7.517901452071881e-05,
      "loss": 0.5855,
      "step": 450
    },
    {
      "epoch": 0.40866185452526377,
      "grad_norm": 1.0420675133889645,
      "learning_rate": 7.382610336807887e-05,
      "loss": 0.5838,
      "step": 460
    },
    {
      "epoch": 0.4175458078845086,
      "grad_norm": 0.8648729913513474,
      "learning_rate": 7.245023300945202e-05,
      "loss": 0.5948,
      "step": 470
    },
    {
      "epoch": 0.4264297612437535,
      "grad_norm": 0.9689655587588671,
      "learning_rate": 7.105272925504263e-05,
      "loss": 0.5979,
      "step": 480
    },
    {
      "epoch": 0.43531371460299834,
      "grad_norm": 0.8566017784460783,
      "learning_rate": 6.963493876133367e-05,
      "loss": 0.5858,
      "step": 490
    },
    {
      "epoch": 0.4441976679622432,
      "grad_norm": 0.8931237327729312,
      "learning_rate": 6.81982277334275e-05,
      "loss": 0.5657,
      "step": 500
    },
    {
      "epoch": 0.45308162132148805,
      "grad_norm": 0.8946007884706231,
      "learning_rate": 6.674398060854931e-05,
      "loss": 0.5827,
      "step": 510
    },
    {
      "epoch": 0.4619655746807329,
      "grad_norm": 0.9598712143919019,
      "learning_rate": 6.527359872198167e-05,
      "loss": 0.5782,
      "step": 520
    },
    {
      "epoch": 0.4708495280399778,
      "grad_norm": 0.8696049364786186,
      "learning_rate": 6.378849895671593e-05,
      "loss": 0.5667,
      "step": 530
    },
    {
      "epoch": 0.47973348139922267,
      "grad_norm": 0.8221319564133971,
      "learning_rate": 6.229011237812172e-05,
      "loss": 0.5679,
      "step": 540
    },
    {
      "epoch": 0.48861743475846753,
      "grad_norm": 0.8491905492884951,
      "learning_rate": 6.0779882854949745e-05,
      "loss": 0.5593,
      "step": 550
    },
    {
      "epoch": 0.4975013881177124,
      "grad_norm": 0.8767241563376581,
      "learning_rate": 5.925926566799753e-05,
      "loss": 0.5585,
      "step": 560
    },
    {
      "epoch": 0.5063853414769572,
      "grad_norm": 0.8460889592200896,
      "learning_rate": 5.772972610777785e-05,
      "loss": 0.5572,
      "step": 570
    },
    {
      "epoch": 0.5152692948362021,
      "grad_norm": 0.8626170213668528,
      "learning_rate": 5.6192738062542005e-05,
      "loss": 0.5728,
      "step": 580
    },
    {
      "epoch": 0.524153248195447,
      "grad_norm": 0.903230081840722,
      "learning_rate": 5.464978259801797e-05,
      "loss": 0.5737,
      "step": 590
    },
    {
      "epoch": 0.5330372015546918,
      "grad_norm": 0.9531284348203876,
      "learning_rate": 5.310234653023236e-05,
      "loss": 0.558,
      "step": 600
    },
    {
      "epoch": 0.5419211549139367,
      "grad_norm": 0.8793523271855779,
      "learning_rate": 5.155192099279113e-05,
      "loss": 0.5559,
      "step": 610
    },
    {
      "epoch": 0.5508051082731815,
      "grad_norm": 0.91078493417537,
      "learning_rate": 5e-05,
      "loss": 0.5581,
      "step": 620
    },
    {
      "epoch": 0.5596890616324264,
      "grad_norm": 0.8720975777927117,
      "learning_rate": 4.844807900720887e-05,
      "loss": 0.5443,
      "step": 630
    },
    {
      "epoch": 0.5685730149916713,
      "grad_norm": 0.8946310380128112,
      "learning_rate": 4.689765346976765e-05,
      "loss": 0.5637,
      "step": 640
    },
    {
      "epoch": 0.5774569683509162,
      "grad_norm": 0.8778823648769881,
      "learning_rate": 4.535021740198202e-05,
      "loss": 0.5712,
      "step": 650
    },
    {
      "epoch": 0.5863409217101611,
      "grad_norm": 0.8735316605144092,
      "learning_rate": 4.380726193745801e-05,
      "loss": 0.5344,
      "step": 660
    },
    {
      "epoch": 0.5952248750694059,
      "grad_norm": 0.8385873835276224,
      "learning_rate": 4.2270273892222155e-05,
      "loss": 0.5335,
      "step": 670
    },
    {
      "epoch": 0.6041088284286508,
      "grad_norm": 0.8510322139108633,
      "learning_rate": 4.0740734332002486e-05,
      "loss": 0.544,
      "step": 680
    },
    {
      "epoch": 0.6129927817878956,
      "grad_norm": 0.789602968940611,
      "learning_rate": 3.922011714505025e-05,
      "loss": 0.5229,
      "step": 690
    },
    {
      "epoch": 0.6218767351471405,
      "grad_norm": 0.7484093832934676,
      "learning_rate": 3.77098876218783e-05,
      "loss": 0.5288,
      "step": 700
    },
    {
      "epoch": 0.6307606885063853,
      "grad_norm": 0.848360601993841,
      "learning_rate": 3.621150104328407e-05,
      "loss": 0.5302,
      "step": 710
    },
    {
      "epoch": 0.6396446418656302,
      "grad_norm": 0.8617539559363584,
      "learning_rate": 3.472640127801835e-05,
      "loss": 0.5453,
      "step": 720
    },
    {
      "epoch": 0.648528595224875,
      "grad_norm": 0.8863608669050927,
      "learning_rate": 3.325601939145069e-05,
      "loss": 0.5493,
      "step": 730
    },
    {
      "epoch": 0.6574125485841199,
      "grad_norm": 0.9060518692128768,
      "learning_rate": 3.1801772266572505e-05,
      "loss": 0.5529,
      "step": 740
    },
    {
      "epoch": 0.6662965019433648,
      "grad_norm": 0.7470350264356581,
      "learning_rate": 3.0365061238666337e-05,
      "loss": 0.512,
      "step": 750
    },
    {
      "epoch": 0.6751804553026096,
      "grad_norm": 0.8086597591862776,
      "learning_rate": 2.8947270744957384e-05,
      "loss": 0.5198,
      "step": 760
    },
    {
      "epoch": 0.6840644086618545,
      "grad_norm": 0.8434593598145564,
      "learning_rate": 2.754976699054797e-05,
      "loss": 0.522,
      "step": 770
    },
    {
      "epoch": 0.6929483620210994,
      "grad_norm": 0.8055132529554618,
      "learning_rate": 2.6173896631921137e-05,
      "loss": 0.5239,
      "step": 780
    },
    {
      "epoch": 0.7018323153803443,
      "grad_norm": 0.7977266847278275,
      "learning_rate": 2.4820985479281183e-05,
      "loss": 0.489,
      "step": 790
    },
    {
      "epoch": 0.7107162687395892,
      "grad_norm": 0.8671313521497748,
      "learning_rate": 2.3492337218982398e-05,
      "loss": 0.5014,
      "step": 800
    },
    {
      "epoch": 0.719600222098834,
      "grad_norm": 0.8036643327932722,
      "learning_rate": 2.2189232157276246e-05,
      "loss": 0.5093,
      "step": 810
    },
    {
      "epoch": 0.7284841754580789,
      "grad_norm": 0.7615023827977124,
      "learning_rate": 2.0912925986588543e-05,
      "loss": 0.5113,
      "step": 820
    },
    {
      "epoch": 0.7373681288173237,
      "grad_norm": 0.8527910441792818,
      "learning_rate": 1.9664648575514316e-05,
      "loss": 0.5079,
      "step": 830
    },
    {
      "epoch": 0.7462520821765686,
      "grad_norm": 0.8399972742356198,
      "learning_rate": 1.8445602783697374e-05,
      "loss": 0.5092,
      "step": 840
    },
    {
      "epoch": 0.7551360355358134,
      "grad_norm": 0.8022987328051595,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.5058,
      "step": 850
    },
    {
      "epoch": 0.7640199888950583,
      "grad_norm": 0.8263901965106663,
      "learning_rate": 1.6099875524230707e-05,
      "loss": 0.5193,
      "step": 860
    },
    {
      "epoch": 0.7729039422543031,
      "grad_norm": 0.7258136513317577,
      "learning_rate": 1.4975454436069292e-05,
      "loss": 0.5015,
      "step": 870
    },
    {
      "epoch": 0.781787895613548,
      "grad_norm": 0.8526065599773422,
      "learning_rate": 1.3884783548004704e-05,
      "loss": 0.5064,
      "step": 880
    },
    {
      "epoch": 0.7906718489727929,
      "grad_norm": 0.7422325570475351,
      "learning_rate": 1.2828913847569186e-05,
      "loss": 0.4959,
      "step": 890
    },
    {
      "epoch": 0.7995558023320377,
      "grad_norm": 0.76204917717199,
      "learning_rate": 1.1808862787326175e-05,
      "loss": 0.5173,
      "step": 900
    },
    {
      "epoch": 0.8084397556912826,
      "grad_norm": 0.820115037949011,
      "learning_rate": 1.0825613304436939e-05,
      "loss": 0.5078,
      "step": 910
    },
    {
      "epoch": 0.8173237090505275,
      "grad_norm": 0.7244050665360098,
      "learning_rate": 9.880112873487069e-06,
      "loss": 0.5062,
      "step": 920
    },
    {
      "epoch": 0.8262076624097724,
      "grad_norm": 0.7916809376691804,
      "learning_rate": 8.973272593485011e-06,
      "loss": 0.507,
      "step": 930
    },
    {
      "epoch": 0.8350916157690172,
      "grad_norm": 0.8308908117520005,
      "learning_rate": 8.105966309912966e-06,
      "loss": 0.5135,
      "step": 940
    },
    {
      "epoch": 0.8439755691282621,
      "grad_norm": 0.8168887546233554,
      "learning_rate": 7.2790297726755716e-06,
      "loss": 0.497,
      "step": 950
    },
    {
      "epoch": 0.852859522487507,
      "grad_norm": 0.734790076115203,
      "learning_rate": 6.493259830758324e-06,
      "loss": 0.497,
      "step": 960
    },
    {
      "epoch": 0.8617434758467518,
      "grad_norm": 0.7680587532831741,
      "learning_rate": 5.749413664371311e-06,
      "loss": 0.4911,
      "step": 970
    },
    {
      "epoch": 0.8706274292059967,
      "grad_norm": 0.7807073547321183,
      "learning_rate": 5.048208055318659e-06,
      "loss": 0.4993,
      "step": 980
    },
    {
      "epoch": 0.8795113825652415,
      "grad_norm": 0.7982653908069431,
      "learning_rate": 4.390318696296247e-06,
      "loss": 0.4879,
      "step": 990
    },
    {
      "epoch": 0.8883953359244864,
      "grad_norm": 0.7876134447703516,
      "learning_rate": 3.7763795397837087e-06,
      "loss": 0.4875,
      "step": 1000
    },
    {
      "epoch": 0.8972792892837312,
      "grad_norm": 0.8484582426764228,
      "learning_rate": 3.2069821871579253e-06,
      "loss": 0.5017,
      "step": 1010
    },
    {
      "epoch": 0.9061632426429761,
      "grad_norm": 0.7456397711600989,
      "learning_rate": 2.6826753186166177e-06,
      "loss": 0.5223,
      "step": 1020
    },
    {
      "epoch": 0.915047196002221,
      "grad_norm": 0.7308291804007805,
      "learning_rate": 2.203964164461597e-06,
      "loss": 0.5111,
      "step": 1030
    },
    {
      "epoch": 0.9239311493614658,
      "grad_norm": 0.7871762011980757,
      "learning_rate": 1.7713100182508603e-06,
      "loss": 0.4859,
      "step": 1040
    },
    {
      "epoch": 0.9328151027207107,
      "grad_norm": 0.7383224820398359,
      "learning_rate": 1.385129792288986e-06,
      "loss": 0.5031,
      "step": 1050
    },
    {
      "epoch": 0.9416990560799556,
      "grad_norm": 0.7618362330303838,
      "learning_rate": 1.0457956158838544e-06,
      "loss": 0.497,
      "step": 1060
    },
    {
      "epoch": 0.9505830094392005,
      "grad_norm": 0.71754164307053,
      "learning_rate": 7.536344767570536e-07,
      "loss": 0.4932,
      "step": 1070
    },
    {
      "epoch": 0.9594669627984453,
      "grad_norm": 0.8855499356377406,
      "learning_rate": 5.089279059533658e-07,
      "loss": 0.5036,
      "step": 1080
    },
    {
      "epoch": 0.9683509161576902,
      "grad_norm": 0.8276594673958173,
      "learning_rate": 3.119117065530808e-07,
      "loss": 0.498,
      "step": 1090
    },
    {
      "epoch": 0.9772348695169351,
      "grad_norm": 0.7304232316816911,
      "learning_rate": 1.627757264484442e-07,
      "loss": 0.4757,
      "step": 1100
    },
    {
      "epoch": 0.9861188228761799,
      "grad_norm": 0.7979420913756442,
      "learning_rate": 6.166367540325624e-08,
      "loss": 0.4846,
      "step": 1110
    },
    {
      "epoch": 0.9950027762354248,
      "grad_norm": 0.8003636692959832,
      "learning_rate": 8.67298657189486e-09,
      "loss": 0.4954,
      "step": 1120
    },
    {
      "epoch": 0.9994447529150472,
      "step": 1125,
      "total_flos": 115517170614272.0,
      "train_loss": 0.5812906358506944,
      "train_runtime": 16348.6073,
      "train_samples_per_second": 4.406,
      "train_steps_per_second": 0.069
    }
  ],
  "logging_steps": 10,
  "max_steps": 1125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 115517170614272.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}