{
  "best_metric": 0.541167345355827,
  "best_model_checkpoint": "/content/drive/MyDrive/Inventariado_Mobiliario_Urbano/cars_brand_model/cmmy/checkpoint-2260",
  "epoch": 9.996692392502757,
  "eval_steps": 500,
  "global_step": 2260,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044101433296582136,
      "grad_norm": 4.8150153160095215,
      "learning_rate": 4.424778761061947e-05,
      "loss": 33.4771,
      "step": 10
    },
    {
      "epoch": 0.08820286659316427,
      "grad_norm": 4.733597278594971,
      "learning_rate": 8.849557522123894e-05,
      "loss": 33.1339,
      "step": 20
    },
    {
      "epoch": 0.13230429988974643,
      "grad_norm": 4.442318439483643,
      "learning_rate": 0.00013274336283185842,
      "loss": 32.4884,
      "step": 30
    },
    {
      "epoch": 0.17640573318632854,
      "grad_norm": 4.178449630737305,
      "learning_rate": 0.00017699115044247788,
      "loss": 31.6444,
      "step": 40
    },
    {
      "epoch": 0.2205071664829107,
      "grad_norm": 4.139791965484619,
      "learning_rate": 0.00022123893805309737,
      "loss": 30.7515,
      "step": 50
    },
    {
      "epoch": 0.26460859977949286,
      "grad_norm": 4.265659332275391,
      "learning_rate": 0.00026548672566371683,
      "loss": 29.8171,
      "step": 60
    },
    {
      "epoch": 0.308710033076075,
      "grad_norm": 4.5766921043396,
      "learning_rate": 0.00030973451327433627,
      "loss": 28.6353,
      "step": 70
    },
    {
      "epoch": 0.3528114663726571,
      "grad_norm": 5.000542640686035,
      "learning_rate": 0.00035398230088495576,
      "loss": 27.6647,
      "step": 80
    },
    {
      "epoch": 0.39691289966923926,
      "grad_norm": 4.588747501373291,
      "learning_rate": 0.00039823008849557525,
      "loss": 26.439,
      "step": 90
    },
    {
      "epoch": 0.4410143329658214,
      "grad_norm": 5.457170486450195,
      "learning_rate": 0.00044247787610619474,
      "loss": 25.3025,
      "step": 100
    },
    {
      "epoch": 0.48511576626240355,
      "grad_norm": 5.326786518096924,
      "learning_rate": 0.0004867256637168142,
      "loss": 24.4399,
      "step": 110
    },
    {
      "epoch": 0.5292171995589857,
      "grad_norm": 5.408795356750488,
      "learning_rate": 0.0005309734513274337,
      "loss": 23.267,
      "step": 120
    },
    {
      "epoch": 0.5733186328555678,
      "grad_norm": 5.888697624206543,
      "learning_rate": 0.0005752212389380532,
      "loss": 22.239,
      "step": 130
    },
    {
      "epoch": 0.61742006615215,
      "grad_norm": 6.699647903442383,
      "learning_rate": 0.0006194690265486725,
      "loss": 21.443,
      "step": 140
    },
    {
      "epoch": 0.6615214994487321,
      "grad_norm": 5.940579891204834,
      "learning_rate": 0.0006637168141592921,
      "loss": 20.2496,
      "step": 150
    },
    {
      "epoch": 0.7056229327453142,
      "grad_norm": 6.729783058166504,
      "learning_rate": 0.0007079646017699115,
      "loss": 19.7215,
      "step": 160
    },
    {
      "epoch": 0.7497243660418964,
      "grad_norm": 7.232001781463623,
      "learning_rate": 0.0007522123893805309,
      "loss": 18.8327,
      "step": 170
    },
    {
      "epoch": 0.7938257993384785,
      "grad_norm": 6.139113426208496,
      "learning_rate": 0.0007964601769911505,
      "loss": 18.3153,
      "step": 180
    },
    {
      "epoch": 0.8379272326350606,
      "grad_norm": 6.233616828918457,
      "learning_rate": 0.0008407079646017699,
      "loss": 17.7032,
      "step": 190
    },
    {
      "epoch": 0.8820286659316428,
      "grad_norm": 6.897170543670654,
      "learning_rate": 0.0008849557522123895,
      "loss": 16.9044,
      "step": 200
    },
    {
      "epoch": 0.9261300992282249,
      "grad_norm": 6.186814785003662,
      "learning_rate": 0.0009292035398230089,
      "loss": 16.6313,
      "step": 210
    },
    {
      "epoch": 0.9702315325248071,
      "grad_norm": 6.237786293029785,
      "learning_rate": 0.0009734513274336283,
      "loss": 16.0903,
      "step": 220
    },
    {
      "epoch": 0.9966923925027563,
      "eval_accuracy": 0.19693620321892574,
      "eval_loss": 3.4455316066741943,
      "eval_runtime": 157.5981,
      "eval_samples_per_second": 163.612,
      "eval_steps_per_second": 0.641,
      "step": 226
    },
    {
      "epoch": 1.017640573318633,
      "grad_norm": 5.7300639152526855,
      "learning_rate": 0.0009980334316617503,
      "loss": 16.2564,
      "step": 230
    },
    {
      "epoch": 1.061742006615215,
      "grad_norm": 6.365210056304932,
      "learning_rate": 0.000993117010816126,
      "loss": 14.7841,
      "step": 240
    },
    {
      "epoch": 1.1058434399117971,
      "grad_norm": 6.162064552307129,
      "learning_rate": 0.0009882005899705015,
      "loss": 14.7691,
      "step": 250
    },
    {
      "epoch": 1.1499448732083792,
      "grad_norm": 6.440285682678223,
      "learning_rate": 0.0009832841691248771,
      "loss": 14.1738,
      "step": 260
    },
    {
      "epoch": 1.1940463065049614,
      "grad_norm": 5.520109176635742,
      "learning_rate": 0.0009783677482792527,
      "loss": 14.0754,
      "step": 270
    },
    {
      "epoch": 1.2381477398015435,
      "grad_norm": 6.146816730499268,
      "learning_rate": 0.0009734513274336283,
      "loss": 13.9686,
      "step": 280
    },
    {
      "epoch": 1.2822491730981258,
      "grad_norm": 5.696677207946777,
      "learning_rate": 0.000968534906588004,
      "loss": 13.6213,
      "step": 290
    },
    {
      "epoch": 1.326350606394708,
      "grad_norm": 5.706403732299805,
      "learning_rate": 0.0009636184857423795,
      "loss": 13.2106,
      "step": 300
    },
    {
      "epoch": 1.37045203969129,
      "grad_norm": 6.3477067947387695,
      "learning_rate": 0.0009587020648967551,
      "loss": 13.1036,
      "step": 310
    },
    {
      "epoch": 1.4145534729878722,
      "grad_norm": 6.014346599578857,
      "learning_rate": 0.0009537856440511307,
      "loss": 13.0983,
      "step": 320
    },
    {
      "epoch": 1.4586549062844543,
      "grad_norm": 5.742127895355225,
      "learning_rate": 0.0009488692232055063,
      "loss": 12.6127,
      "step": 330
    },
    {
      "epoch": 1.5027563395810364,
      "grad_norm": 5.869048595428467,
      "learning_rate": 0.0009439528023598821,
      "loss": 12.7718,
      "step": 340
    },
    {
      "epoch": 1.5468577728776185,
      "grad_norm": 5.569489479064941,
      "learning_rate": 0.0009390363815142577,
      "loss": 12.4881,
      "step": 350
    },
    {
      "epoch": 1.5909592061742006,
      "grad_norm": 6.744396686553955,
      "learning_rate": 0.0009341199606686333,
      "loss": 12.3667,
      "step": 360
    },
    {
      "epoch": 1.6350606394707827,
      "grad_norm": 5.721745014190674,
      "learning_rate": 0.0009292035398230089,
      "loss": 12.169,
      "step": 370
    },
    {
      "epoch": 1.6791620727673648,
      "grad_norm": 6.00828742980957,
      "learning_rate": 0.0009242871189773845,
      "loss": 12.163,
      "step": 380
    },
    {
      "epoch": 1.723263506063947,
      "grad_norm": 6.328344345092773,
      "learning_rate": 0.0009193706981317601,
      "loss": 11.9877,
      "step": 390
    },
    {
      "epoch": 1.767364939360529,
      "grad_norm": 5.9762492179870605,
      "learning_rate": 0.0009144542772861358,
      "loss": 11.8959,
      "step": 400
    },
    {
      "epoch": 1.8114663726571112,
      "grad_norm": 5.462543487548828,
      "learning_rate": 0.0009095378564405114,
      "loss": 11.8443,
      "step": 410
    },
    {
      "epoch": 1.8555678059536935,
      "grad_norm": 5.628457069396973,
      "learning_rate": 0.000904621435594887,
      "loss": 11.7006,
      "step": 420
    },
    {
      "epoch": 1.8996692392502756,
      "grad_norm": 5.508877754211426,
      "learning_rate": 0.0008997050147492626,
      "loss": 11.6014,
      "step": 430
    },
    {
      "epoch": 1.9437706725468578,
      "grad_norm": 5.510633945465088,
      "learning_rate": 0.0008947885939036382,
      "loss": 11.4442,
      "step": 440
    },
    {
      "epoch": 1.9878721058434399,
      "grad_norm": 5.567264080047607,
      "learning_rate": 0.0008898721730580139,
      "loss": 11.5438,
      "step": 450
    },
    {
      "epoch": 1.9966923925027564,
      "eval_accuracy": 0.299166181888695,
      "eval_loss": 2.4033162593841553,
      "eval_runtime": 157.919,
      "eval_samples_per_second": 163.28,
      "eval_steps_per_second": 0.64,
      "step": 452
    },
    {
      "epoch": 2.035281146637266,
      "grad_norm": 5.653784275054932,
      "learning_rate": 0.0008849557522123895,
      "loss": 11.2957,
      "step": 460
    },
    {
      "epoch": 2.079382579933848,
      "grad_norm": 5.515305519104004,
      "learning_rate": 0.0008800393313667651,
      "loss": 10.4382,
      "step": 470
    },
    {
      "epoch": 2.12348401323043,
      "grad_norm": 5.540599346160889,
      "learning_rate": 0.0008751229105211407,
      "loss": 10.2655,
      "step": 480
    },
    {
      "epoch": 2.167585446527012,
      "grad_norm": 5.588015079498291,
      "learning_rate": 0.0008702064896755162,
      "loss": 10.4359,
      "step": 490
    },
    {
      "epoch": 2.2116868798235942,
      "grad_norm": 5.268083095550537,
      "learning_rate": 0.0008652900688298918,
      "loss": 10.4373,
      "step": 500
    },
    {
      "epoch": 2.2557883131201764,
      "grad_norm": 5.2158427238464355,
      "learning_rate": 0.0008603736479842675,
      "loss": 10.3617,
      "step": 510
    },
    {
      "epoch": 2.2998897464167585,
      "grad_norm": 5.967540264129639,
      "learning_rate": 0.0008554572271386431,
      "loss": 10.343,
      "step": 520
    },
    {
      "epoch": 2.3439911797133406,
      "grad_norm": 6.330170154571533,
      "learning_rate": 0.0008505408062930187,
      "loss": 10.3236,
      "step": 530
    },
    {
      "epoch": 2.3880926130099227,
      "grad_norm": 5.394957065582275,
      "learning_rate": 0.0008456243854473943,
      "loss": 10.1741,
      "step": 540
    },
    {
      "epoch": 2.432194046306505,
      "grad_norm": 5.637348651885986,
      "learning_rate": 0.0008407079646017699,
      "loss": 10.1634,
      "step": 550
    },
    {
      "epoch": 2.476295479603087,
      "grad_norm": 5.205583572387695,
      "learning_rate": 0.0008357915437561455,
      "loss": 10.0739,
      "step": 560
    },
    {
      "epoch": 2.5203969128996695,
      "grad_norm": 5.155258655548096,
      "learning_rate": 0.0008308751229105212,
      "loss": 10.1469,
      "step": 570
    },
    {
      "epoch": 2.5644983461962516,
      "grad_norm": 5.169893741607666,
      "learning_rate": 0.0008259587020648968,
      "loss": 10.0088,
      "step": 580
    },
    {
      "epoch": 2.6085997794928337,
      "grad_norm": 5.327938556671143,
      "learning_rate": 0.0008210422812192724,
      "loss": 9.9356,
      "step": 590
    },
    {
      "epoch": 2.652701212789416,
      "grad_norm": 5.036328315734863,
      "learning_rate": 0.000816125860373648,
      "loss": 9.8759,
      "step": 600
    },
    {
      "epoch": 2.696802646085998,
      "grad_norm": 5.075291633605957,
      "learning_rate": 0.0008112094395280236,
      "loss": 9.8351,
      "step": 610
    },
    {
      "epoch": 2.74090407938258,
      "grad_norm": 5.24298620223999,
      "learning_rate": 0.0008062930186823992,
      "loss": 9.6878,
      "step": 620
    },
    {
      "epoch": 2.785005512679162,
      "grad_norm": 4.871809005737305,
      "learning_rate": 0.0008013765978367749,
      "loss": 9.9713,
      "step": 630
    },
    {
      "epoch": 2.8291069459757443,
      "grad_norm": 4.931336879730225,
      "learning_rate": 0.0007964601769911505,
      "loss": 9.8542,
      "step": 640
    },
    {
      "epoch": 2.8732083792723264,
      "grad_norm": 5.142650127410889,
      "learning_rate": 0.0007915437561455261,
      "loss": 9.8176,
      "step": 650
    },
    {
      "epoch": 2.9173098125689085,
      "grad_norm": 5.100261211395264,
      "learning_rate": 0.0007866273352999017,
      "loss": 9.5995,
      "step": 660
    },
    {
      "epoch": 2.9614112458654906,
      "grad_norm": 4.906562805175781,
      "learning_rate": 0.0007817109144542773,
      "loss": 9.5963,
      "step": 670
    },
    {
      "epoch": 2.9966923925027564,
      "eval_accuracy": 0.3491564863292612,
      "eval_loss": 2.0761232376098633,
      "eval_runtime": 157.9952,
      "eval_samples_per_second": 163.201,
      "eval_steps_per_second": 0.639,
      "step": 678
    },
    {
      "epoch": 3.0088202866593163,
      "grad_norm": 4.665123462677002,
      "learning_rate": 0.000776794493608653,
      "loss": 9.8294,
      "step": 680
    },
    {
      "epoch": 3.0529217199558984,
      "grad_norm": 5.142998695373535,
      "learning_rate": 0.0007718780727630286,
      "loss": 8.6602,
      "step": 690
    },
    {
      "epoch": 3.0970231532524806,
      "grad_norm": 4.909497261047363,
      "learning_rate": 0.0007669616519174042,
      "loss": 8.5178,
      "step": 700
    },
    {
      "epoch": 3.1411245865490627,
      "grad_norm": 4.914758682250977,
      "learning_rate": 0.0007620452310717798,
      "loss": 8.5225,
      "step": 710
    },
    {
      "epoch": 3.185226019845645,
      "grad_norm": 4.778907299041748,
      "learning_rate": 0.0007571288102261554,
      "loss": 8.6442,
      "step": 720
    },
    {
      "epoch": 3.2293274531422274,
      "grad_norm": 4.7863240242004395,
      "learning_rate": 0.0007522123893805309,
      "loss": 8.6121,
      "step": 730
    },
    {
      "epoch": 3.2734288864388095,
      "grad_norm": 4.866987228393555,
      "learning_rate": 0.0007472959685349066,
      "loss": 8.6773,
      "step": 740
    },
    {
      "epoch": 3.3175303197353916,
      "grad_norm": 4.968977451324463,
      "learning_rate": 0.0007423795476892822,
      "loss": 8.6663,
      "step": 750
    },
    {
      "epoch": 3.3616317530319737,
      "grad_norm": 4.805993556976318,
      "learning_rate": 0.0007374631268436578,
      "loss": 8.6653,
      "step": 760
    },
    {
      "epoch": 3.405733186328556,
      "grad_norm": 4.871044635772705,
      "learning_rate": 0.0007325467059980334,
      "loss": 8.5913,
      "step": 770
    },
    {
      "epoch": 3.449834619625138,
      "grad_norm": 5.305060863494873,
      "learning_rate": 0.000727630285152409,
      "loss": 8.4683,
      "step": 780
    },
    {
      "epoch": 3.49393605292172,
      "grad_norm": 4.906181812286377,
      "learning_rate": 0.0007227138643067846,
      "loss": 8.5715,
      "step": 790
    },
    {
      "epoch": 3.538037486218302,
      "grad_norm": 4.955236434936523,
      "learning_rate": 0.0007177974434611603,
      "loss": 8.5461,
      "step": 800
    },
    {
      "epoch": 3.5821389195148843,
      "grad_norm": 4.7065863609313965,
      "learning_rate": 0.0007128810226155359,
      "loss": 8.5517,
      "step": 810
    },
    {
      "epoch": 3.6262403528114664,
      "grad_norm": 4.8048930168151855,
      "learning_rate": 0.0007079646017699115,
      "loss": 8.6689,
      "step": 820
    },
    {
      "epoch": 3.6703417861080485,
      "grad_norm": 5.108726978302002,
      "learning_rate": 0.0007030481809242871,
      "loss": 8.4989,
      "step": 830
    },
    {
      "epoch": 3.7144432194046306,
      "grad_norm": 4.784049034118652,
      "learning_rate": 0.0006981317600786627,
      "loss": 8.5436,
      "step": 840
    },
    {
      "epoch": 3.7585446527012127,
      "grad_norm": 4.953752517700195,
      "learning_rate": 0.0006932153392330383,
      "loss": 8.3707,
      "step": 850
    },
    {
      "epoch": 3.802646085997795,
      "grad_norm": 4.866833686828613,
      "learning_rate": 0.000688298918387414,
      "loss": 8.5086,
      "step": 860
    },
    {
      "epoch": 3.846747519294377,
      "grad_norm": 4.966568946838379,
      "learning_rate": 0.0006833824975417896,
      "loss": 8.3376,
      "step": 870
    },
    {
      "epoch": 3.890848952590959,
      "grad_norm": 4.906131744384766,
      "learning_rate": 0.0006784660766961652,
      "loss": 8.3634,
      "step": 880
    },
    {
      "epoch": 3.934950385887541,
      "grad_norm": 4.776595115661621,
      "learning_rate": 0.0006735496558505408,
      "loss": 8.3092,
      "step": 890
    },
    {
      "epoch": 3.9790518191841233,
      "grad_norm": 4.59867525100708,
      "learning_rate": 0.0006686332350049164,
      "loss": 8.3873,
      "step": 900
    },
    {
      "epoch": 3.9966923925027564,
      "eval_accuracy": 0.3934458018227652,
      "eval_loss": 1.892139196395874,
      "eval_runtime": 157.998,
      "eval_samples_per_second": 163.198,
      "eval_steps_per_second": 0.639,
      "step": 904
    },
    {
      "epoch": 4.0264608599779494,
      "grad_norm": 4.579000473022461,
      "learning_rate": 0.0006637168141592921,
      "loss": 8.0129,
      "step": 910
    },
    {
      "epoch": 4.070562293274532,
      "grad_norm": 4.628970623016357,
      "learning_rate": 0.0006588003933136677,
      "loss": 7.3258,
      "step": 920
    },
    {
      "epoch": 4.114663726571114,
      "grad_norm": 4.4933953285217285,
      "learning_rate": 0.0006538839724680433,
      "loss": 7.3052,
      "step": 930
    },
    {
      "epoch": 4.158765159867696,
      "grad_norm": 4.572768211364746,
      "learning_rate": 0.0006489675516224189,
      "loss": 7.3455,
      "step": 940
    },
    {
      "epoch": 4.202866593164278,
      "grad_norm": 4.468959331512451,
      "learning_rate": 0.0006440511307767945,
      "loss": 7.3741,
      "step": 950
    },
    {
      "epoch": 4.24696802646086,
      "grad_norm": 4.594937324523926,
      "learning_rate": 0.00063913470993117,
      "loss": 7.3599,
      "step": 960
    },
    {
      "epoch": 4.291069459757442,
      "grad_norm": 4.6465935707092285,
      "learning_rate": 0.0006342182890855457,
      "loss": 7.3735,
      "step": 970
    },
    {
      "epoch": 4.335170893054024,
      "grad_norm": 4.683464527130127,
      "learning_rate": 0.0006293018682399213,
      "loss": 7.447,
      "step": 980
    },
    {
      "epoch": 4.379272326350606,
      "grad_norm": 4.466670989990234,
      "learning_rate": 0.0006243854473942969,
      "loss": 7.4649,
      "step": 990
    },
    {
      "epoch": 4.4233737596471885,
      "grad_norm": 4.653200149536133,
      "learning_rate": 0.0006194690265486725,
      "loss": 7.3462,
      "step": 1000
    },
    {
      "epoch": 4.467475192943771,
      "grad_norm": 4.518767356872559,
      "learning_rate": 0.0006145526057030481,
      "loss": 7.2768,
      "step": 1010
    },
    {
      "epoch": 4.511576626240353,
      "grad_norm": 4.512480735778809,
      "learning_rate": 0.0006096361848574237,
      "loss": 7.306,
      "step": 1020
    },
    {
      "epoch": 4.555678059536935,
      "grad_norm": 4.512141704559326,
      "learning_rate": 0.0006047197640117994,
      "loss": 7.3665,
      "step": 1030
    },
    {
      "epoch": 4.599779492833517,
      "grad_norm": 4.769530773162842,
      "learning_rate": 0.000599803343166175,
      "loss": 7.4248,
      "step": 1040
    },
    {
      "epoch": 4.643880926130099,
      "grad_norm": 4.538891792297363,
      "learning_rate": 0.0005948869223205506,
      "loss": 7.3548,
      "step": 1050
    },
    {
      "epoch": 4.687982359426681,
      "grad_norm": 4.579529762268066,
      "learning_rate": 0.0005899705014749262,
      "loss": 7.1825,
      "step": 1060
    },
    {
      "epoch": 4.732083792723263,
      "grad_norm": 4.407522201538086,
      "learning_rate": 0.0005850540806293018,
      "loss": 7.3086,
      "step": 1070
    },
    {
      "epoch": 4.776185226019845,
      "grad_norm": 4.507376194000244,
      "learning_rate": 0.0005801376597836774,
      "loss": 7.4489,
      "step": 1080
    },
    {
      "epoch": 4.8202866593164275,
      "grad_norm": 4.580904960632324,
      "learning_rate": 0.0005752212389380532,
      "loss": 7.2829,
      "step": 1090
    },
    {
      "epoch": 4.86438809261301,
      "grad_norm": 4.334172248840332,
      "learning_rate": 0.0005703048180924288,
      "loss": 7.3591,
      "step": 1100
    },
    {
      "epoch": 4.908489525909592,
      "grad_norm": 4.6015095710754395,
      "learning_rate": 0.0005653883972468044,
      "loss": 7.3586,
      "step": 1110
    },
    {
      "epoch": 4.952590959206174,
      "grad_norm": 4.470212936401367,
      "learning_rate": 0.00056047197640118,
      "loss": 7.3276,
      "step": 1120
    },
    {
      "epoch": 4.996692392502756,
      "grad_norm": 4.509373664855957,
      "learning_rate": 0.0005555555555555556,
      "loss": 7.3127,
      "step": 1130
    },
    {
      "epoch": 4.996692392502756,
      "eval_accuracy": 0.42877642039945707,
      "eval_loss": 1.7534652948379517,
      "eval_runtime": 157.6275,
      "eval_samples_per_second": 163.582,
      "eval_steps_per_second": 0.641,
      "step": 1130
    },
    {
      "epoch": 5.044101433296582,
      "grad_norm": 4.370789527893066,
      "learning_rate": 0.0005506391347099313,
      "loss": 6.6219,
      "step": 1140
    },
    {
      "epoch": 5.088202866593164,
      "grad_norm": 4.587760925292969,
      "learning_rate": 0.0005457227138643069,
      "loss": 6.382,
      "step": 1150
    },
    {
      "epoch": 5.132304299889746,
      "grad_norm": 4.437044143676758,
      "learning_rate": 0.0005408062930186825,
      "loss": 6.3493,
      "step": 1160
    },
    {
      "epoch": 5.1764057331863285,
      "grad_norm": 4.376111030578613,
      "learning_rate": 0.0005358898721730581,
      "loss": 6.3537,
      "step": 1170
    },
    {
      "epoch": 5.220507166482911,
      "grad_norm": 4.685988903045654,
      "learning_rate": 0.0005309734513274337,
      "loss": 6.3465,
      "step": 1180
    },
    {
      "epoch": 5.264608599779493,
      "grad_norm": 4.62017297744751,
      "learning_rate": 0.0005260570304818093,
      "loss": 6.3306,
      "step": 1190
    },
    {
      "epoch": 5.308710033076075,
      "grad_norm": 4.6863112449646,
      "learning_rate": 0.0005211406096361849,
      "loss": 6.4408,
      "step": 1200
    },
    {
      "epoch": 5.352811466372657,
      "grad_norm": 4.470117092132568,
      "learning_rate": 0.0005162241887905605,
      "loss": 6.4383,
      "step": 1210
    },
    {
      "epoch": 5.396912899669239,
      "grad_norm": 4.46852445602417,
      "learning_rate": 0.0005113077679449361,
      "loss": 6.2687,
      "step": 1220
    },
    {
      "epoch": 5.441014332965821,
      "grad_norm": 4.40092134475708,
      "learning_rate": 0.0005063913470993117,
      "loss": 6.3344,
      "step": 1230
    },
    {
      "epoch": 5.485115766262403,
      "grad_norm": 4.5052595138549805,
      "learning_rate": 0.0005014749262536873,
      "loss": 6.3289,
      "step": 1240
    },
    {
      "epoch": 5.529217199558985,
      "grad_norm": 4.2100419998168945,
      "learning_rate": 0.000496558505408063,
      "loss": 6.4074,
      "step": 1250
    },
    {
      "epoch": 5.5733186328555675,
      "grad_norm": 4.383902549743652,
      "learning_rate": 0.0004916420845624386,
      "loss": 6.3748,
      "step": 1260
    },
    {
      "epoch": 5.61742006615215,
      "grad_norm": 4.348648548126221,
      "learning_rate": 0.0004867256637168142,
      "loss": 6.2771,
      "step": 1270
    },
    {
      "epoch": 5.661521499448732,
      "grad_norm": 4.597408294677734,
      "learning_rate": 0.0004818092428711898,
      "loss": 6.4728,
      "step": 1280
    },
    {
      "epoch": 5.705622932745314,
      "grad_norm": 4.483145236968994,
      "learning_rate": 0.0004768928220255654,
      "loss": 6.3158,
      "step": 1290
    },
    {
      "epoch": 5.749724366041896,
      "grad_norm": 4.486307144165039,
      "learning_rate": 0.00047197640117994103,
      "loss": 6.3443,
      "step": 1300
    },
    {
      "epoch": 5.793825799338478,
      "grad_norm": 4.527980804443359,
      "learning_rate": 0.00046705998033431663,
      "loss": 6.306,
      "step": 1310
    },
    {
      "epoch": 5.83792723263506,
      "grad_norm": 4.423805236816406,
      "learning_rate": 0.00046214355948869223,
      "loss": 6.2912,
      "step": 1320
    },
    {
      "epoch": 5.882028665931642,
      "grad_norm": 4.3704752922058105,
      "learning_rate": 0.0004572271386430679,
      "loss": 6.2006,
      "step": 1330
    },
    {
      "epoch": 5.926130099228224,
      "grad_norm": 4.610422611236572,
      "learning_rate": 0.0004523107177974435,
      "loss": 6.2838,
      "step": 1340
    },
    {
      "epoch": 5.970231532524807,
      "grad_norm": 4.506854057312012,
      "learning_rate": 0.0004473942969518191,
      "loss": 6.2178,
      "step": 1350
    },
    {
      "epoch": 5.996692392502756,
      "eval_accuracy": 0.4608881132441342,
      "eval_loss": 1.6532503366470337,
      "eval_runtime": 157.0061,
      "eval_samples_per_second": 164.229,
      "eval_steps_per_second": 0.643,
      "step": 1356
    },
    {
      "epoch": 6.017640573318633,
      "grad_norm": 4.212904930114746,
      "learning_rate": 0.00044247787610619474,
      "loss": 6.1728,
      "step": 1360
    },
    {
      "epoch": 6.061742006615215,
      "grad_norm": 4.3509931564331055,
      "learning_rate": 0.00043756145526057034,
      "loss": 5.4675,
      "step": 1370
    },
    {
      "epoch": 6.105843439911797,
      "grad_norm": 4.346857070922852,
      "learning_rate": 0.0004326450344149459,
      "loss": 5.4391,
      "step": 1380
    },
    {
      "epoch": 6.149944873208379,
      "grad_norm": 4.269370079040527,
      "learning_rate": 0.00042772861356932154,
      "loss": 5.6166,
      "step": 1390
    },
    {
      "epoch": 6.194046306504961,
      "grad_norm": 4.528676986694336,
      "learning_rate": 0.00042281219272369714,
      "loss": 5.4683,
      "step": 1400
    },
    {
      "epoch": 6.238147739801543,
      "grad_norm": 4.301924705505371,
      "learning_rate": 0.00041789577187807274,
      "loss": 5.6475,
      "step": 1410
    },
    {
      "epoch": 6.282249173098125,
      "grad_norm": 4.408478736877441,
      "learning_rate": 0.0004129793510324484,
      "loss": 5.5012,
      "step": 1420
    },
    {
      "epoch": 6.3263506063947075,
      "grad_norm": 4.205230712890625,
      "learning_rate": 0.000408062930186824,
      "loss": 5.4751,
      "step": 1430
    },
    {
      "epoch": 6.37045203969129,
      "grad_norm": 4.417777061462402,
      "learning_rate": 0.0004031465093411996,
      "loss": 5.4574,
      "step": 1440
    },
    {
      "epoch": 6.414553472987872,
      "grad_norm": 4.562683582305908,
      "learning_rate": 0.00039823008849557525,
      "loss": 5.5681,
      "step": 1450
    },
    {
      "epoch": 6.458654906284455,
      "grad_norm": 4.4911112785339355,
      "learning_rate": 0.00039331366764995085,
      "loss": 5.5747,
      "step": 1460
    },
    {
      "epoch": 6.502756339581037,
      "grad_norm": 4.3542890548706055,
      "learning_rate": 0.0003883972468043265,
      "loss": 5.4824,
      "step": 1470
    },
    {
      "epoch": 6.546857772877619,
      "grad_norm": 4.291258811950684,
      "learning_rate": 0.0003834808259587021,
      "loss": 5.3834,
      "step": 1480
    },
    {
      "epoch": 6.590959206174201,
      "grad_norm": 4.43005895614624,
      "learning_rate": 0.0003785644051130777,
      "loss": 5.4797,
      "step": 1490
    },
    {
      "epoch": 6.635060639470783,
      "grad_norm": 4.461911201477051,
      "learning_rate": 0.0003736479842674533,
      "loss": 5.5312,
      "step": 1500
    },
    {
      "epoch": 6.679162072767365,
      "grad_norm": 4.246000289916992,
      "learning_rate": 0.0003687315634218289,
      "loss": 5.5821,
      "step": 1510
    },
    {
      "epoch": 6.723263506063947,
      "grad_norm": 4.318939685821533,
      "learning_rate": 0.0003638151425762045,
      "loss": 5.5103,
      "step": 1520
    },
    {
      "epoch": 6.7673649393605295,
      "grad_norm": 4.241775989532471,
      "learning_rate": 0.00035889872173058016,
      "loss": 5.4244,
      "step": 1530
    },
    {
      "epoch": 6.811466372657112,
      "grad_norm": 4.246124267578125,
      "learning_rate": 0.00035398230088495576,
      "loss": 5.4415,
      "step": 1540
    },
    {
      "epoch": 6.855567805953694,
      "grad_norm": 4.474425792694092,
      "learning_rate": 0.00034906588003933136,
      "loss": 5.4259,
      "step": 1550
    },
    {
      "epoch": 6.899669239250276,
      "grad_norm": 4.427676677703857,
      "learning_rate": 0.000344149459193707,
      "loss": 5.4803,
      "step": 1560
    },
    {
      "epoch": 6.943770672546858,
      "grad_norm": 4.402575969696045,
      "learning_rate": 0.0003392330383480826,
      "loss": 5.3709,
      "step": 1570
    },
    {
      "epoch": 6.98787210584344,
      "grad_norm": 4.089934349060059,
      "learning_rate": 0.0003343166175024582,
      "loss": 5.4619,
      "step": 1580
    },
    {
      "epoch": 6.996692392502756,
      "eval_accuracy": 0.4855923986814039,
      "eval_loss": 1.5859359502792358,
      "eval_runtime": 157.4699,
      "eval_samples_per_second": 163.746,
      "eval_steps_per_second": 0.641,
      "step": 1582
    },
    {
      "epoch": 7.035281146637265,
      "grad_norm": 4.048954963684082,
      "learning_rate": 0.00032940019665683387,
      "loss": 4.9956,
      "step": 1590
    },
    {
      "epoch": 7.0793825799338475,
      "grad_norm": 4.142811298370361,
      "learning_rate": 0.00032448377581120947,
      "loss": 4.637,
      "step": 1600
    },
    {
      "epoch": 7.12348401323043,
      "grad_norm": 4.157500267028809,
      "learning_rate": 0.000319567354965585,
      "loss": 4.7621,
      "step": 1610
    },
    {
      "epoch": 7.167585446527012,
      "grad_norm": 4.244820594787598,
      "learning_rate": 0.00031465093411996067,
      "loss": 4.671,
      "step": 1620
    },
    {
      "epoch": 7.211686879823595,
      "grad_norm": 4.291553497314453,
      "learning_rate": 0.00030973451327433627,
      "loss": 4.7641,
      "step": 1630
    },
    {
      "epoch": 7.255788313120177,
      "grad_norm": 4.3009233474731445,
      "learning_rate": 0.00030481809242871187,
      "loss": 4.7801,
      "step": 1640
    },
    {
      "epoch": 7.299889746416759,
      "grad_norm": 4.151345729827881,
      "learning_rate": 0.0002999016715830875,
      "loss": 4.7008,
      "step": 1650
    },
    {
      "epoch": 7.343991179713341,
      "grad_norm": 4.11318826675415,
      "learning_rate": 0.0002949852507374631,
      "loss": 4.5749,
      "step": 1660
    },
    {
      "epoch": 7.388092613009923,
      "grad_norm": 4.272958755493164,
      "learning_rate": 0.0002900688298918387,
      "loss": 4.7279,
      "step": 1670
    },
    {
      "epoch": 7.432194046306505,
      "grad_norm": 4.370232105255127,
      "learning_rate": 0.0002851524090462144,
      "loss": 4.6739,
      "step": 1680
    },
    {
      "epoch": 7.476295479603087,
      "grad_norm": 4.224992752075195,
      "learning_rate": 0.00028023598820059,
      "loss": 4.6791,
      "step": 1690
    },
    {
      "epoch": 7.5203969128996695,
      "grad_norm": 4.131043434143066,
      "learning_rate": 0.00027531956735496563,
      "loss": 4.742,
      "step": 1700
    },
    {
      "epoch": 7.564498346196252,
      "grad_norm": 4.325319290161133,
      "learning_rate": 0.00027040314650934123,
      "loss": 4.6848,
      "step": 1710
    },
    {
      "epoch": 7.608599779492834,
      "grad_norm": 4.375499248504639,
      "learning_rate": 0.00026548672566371683,
      "loss": 4.7289,
      "step": 1720
    },
    {
      "epoch": 7.652701212789416,
      "grad_norm": 4.138423442840576,
      "learning_rate": 0.00026057030481809243,
      "loss": 4.7507,
      "step": 1730
    },
    {
      "epoch": 7.696802646085998,
      "grad_norm": 4.30584716796875,
      "learning_rate": 0.00025565388397246803,
      "loss": 4.7498,
      "step": 1740
    },
    {
      "epoch": 7.74090407938258,
      "grad_norm": 4.196134567260742,
      "learning_rate": 0.00025073746312684363,
      "loss": 4.6912,
      "step": 1750
    },
    {
      "epoch": 7.785005512679162,
      "grad_norm": 4.179983615875244,
      "learning_rate": 0.0002458210422812193,
      "loss": 4.6327,
      "step": 1760
    },
    {
      "epoch": 7.829106945975744,
      "grad_norm": 4.482637405395508,
      "learning_rate": 0.0002409046214355949,
      "loss": 4.7178,
      "step": 1770
    },
    {
      "epoch": 7.873208379272326,
      "grad_norm": 4.053654670715332,
      "learning_rate": 0.00023598820058997051,
      "loss": 4.6353,
      "step": 1780
    },
    {
      "epoch": 7.9173098125689085,
      "grad_norm": 4.109724998474121,
      "learning_rate": 0.00023107177974434611,
      "loss": 4.6531,
      "step": 1790
    },
    {
      "epoch": 7.961411245865491,
      "grad_norm": 4.190576553344727,
      "learning_rate": 0.00022615535889872174,
      "loss": 4.618,
      "step": 1800
    },
    {
      "epoch": 7.996692392502756,
      "eval_accuracy": 0.5128950940469265,
      "eval_loss": 1.52533757686615,
      "eval_runtime": 159.0581,
      "eval_samples_per_second": 162.111,
      "eval_steps_per_second": 0.635,
      "step": 1808
    },
    {
      "epoch": 8.008820286659317,
      "grad_norm": 3.9392812252044678,
      "learning_rate": 0.00022123893805309737,
      "loss": 4.6935,
      "step": 1810
    },
    {
      "epoch": 8.052921719955899,
      "grad_norm": 3.8019185066223145,
      "learning_rate": 0.00021632251720747294,
      "loss": 3.9004,
      "step": 1820
    },
    {
      "epoch": 8.097023153252481,
      "grad_norm": 3.8372962474823,
      "learning_rate": 0.00021140609636184857,
      "loss": 4.0764,
      "step": 1830
    },
    {
      "epoch": 8.141124586549063,
      "grad_norm": 4.013173580169678,
      "learning_rate": 0.0002064896755162242,
      "loss": 3.921,
      "step": 1840
    },
    {
      "epoch": 8.185226019845645,
      "grad_norm": 4.06724739074707,
      "learning_rate": 0.0002015732546705998,
      "loss": 4.1819,
      "step": 1850
    },
    {
      "epoch": 8.229327453142227,
      "grad_norm": 3.967484474182129,
      "learning_rate": 0.00019665683382497542,
      "loss": 4.1189,
      "step": 1860
    },
    {
      "epoch": 8.27342888643881,
      "grad_norm": 3.8714957237243652,
      "learning_rate": 0.00019174041297935105,
      "loss": 4.0143,
      "step": 1870
    },
    {
      "epoch": 8.317530319735392,
      "grad_norm": 3.9495551586151123,
      "learning_rate": 0.00018682399213372665,
      "loss": 4.1982,
      "step": 1880
    },
    {
      "epoch": 8.361631753031974,
      "grad_norm": 4.08094596862793,
      "learning_rate": 0.00018190757128810225,
      "loss": 4.0732,
      "step": 1890
    },
    {
      "epoch": 8.405733186328556,
      "grad_norm": 3.997749090194702,
      "learning_rate": 0.00017699115044247788,
      "loss": 4.0657,
      "step": 1900
    },
    {
      "epoch": 8.449834619625138,
      "grad_norm": 3.9958107471466064,
      "learning_rate": 0.0001720747295968535,
      "loss": 4.0651,
      "step": 1910
    },
    {
      "epoch": 8.49393605292172,
      "grad_norm": 4.039346218109131,
      "learning_rate": 0.0001671583087512291,
      "loss": 4.0022,
      "step": 1920
    },
    {
      "epoch": 8.538037486218302,
      "grad_norm": 4.07537317276001,
      "learning_rate": 0.00016224188790560473,
      "loss": 4.0364,
      "step": 1930
    },
    {
      "epoch": 8.582138919514884,
      "grad_norm": 3.949800491333008,
      "learning_rate": 0.00015732546705998033,
      "loss": 4.0273,
      "step": 1940
    },
    {
      "epoch": 8.626240352811466,
      "grad_norm": 3.9785361289978027,
      "learning_rate": 0.00015240904621435593,
      "loss": 4.1008,
      "step": 1950
    },
    {
      "epoch": 8.670341786108049,
      "grad_norm": 4.0533318519592285,
      "learning_rate": 0.00014749262536873156,
      "loss": 3.9856,
      "step": 1960
    },
    {
      "epoch": 8.71444321940463,
      "grad_norm": 3.9734625816345215,
      "learning_rate": 0.0001425762045231072,
      "loss": 3.9327,
      "step": 1970
    },
    {
      "epoch": 8.758544652701213,
      "grad_norm": 4.144639015197754,
      "learning_rate": 0.00013765978367748282,
      "loss": 4.1105,
      "step": 1980
    },
    {
      "epoch": 8.802646085997795,
      "grad_norm": 4.224411487579346,
      "learning_rate": 0.00013274336283185842,
      "loss": 4.0302,
      "step": 1990
    },
    {
      "epoch": 8.846747519294377,
      "grad_norm": 4.210290908813477,
      "learning_rate": 0.00012782694198623402,
      "loss": 3.9702,
      "step": 2000
    },
    {
      "epoch": 8.890848952590959,
      "grad_norm": 3.948779821395874,
      "learning_rate": 0.00012291052114060964,
      "loss": 4.0179,
      "step": 2010
    },
    {
      "epoch": 8.934950385887541,
      "grad_norm": 4.020263671875,
      "learning_rate": 0.00011799410029498526,
      "loss": 3.9426,
      "step": 2020
    },
    {
      "epoch": 8.979051819184123,
      "grad_norm": 3.9727530479431152,
      "learning_rate": 0.00011307767944936087,
      "loss": 3.9349,
      "step": 2030
    },
    {
      "epoch": 8.996692392502757,
      "eval_accuracy": 0.5314717859220477,
      "eval_loss": 1.4693009853363037,
      "eval_runtime": 158.202,
      "eval_samples_per_second": 162.988,
      "eval_steps_per_second": 0.638,
      "step": 2034
    },
    {
      "epoch": 9.026460859977949,
      "grad_norm": 4.023420333862305,
      "learning_rate": 0.00010816125860373647,
      "loss": 4.0029,
      "step": 2040
    },
    {
      "epoch": 9.07056229327453,
      "grad_norm": 3.8481717109680176,
      "learning_rate": 0.0001032448377581121,
      "loss": 3.5067,
      "step": 2050
    },
    {
      "epoch": 9.114663726571113,
      "grad_norm": 3.807828187942505,
      "learning_rate": 9.832841691248771e-05,
      "loss": 3.5354,
      "step": 2060
    },
    {
      "epoch": 9.158765159867695,
      "grad_norm": 3.808962106704712,
      "learning_rate": 9.341199606686333e-05,
      "loss": 3.6032,
      "step": 2070
    },
    {
      "epoch": 9.202866593164277,
      "grad_norm": 3.6250662803649902,
      "learning_rate": 8.849557522123894e-05,
      "loss": 3.5225,
      "step": 2080
    },
    {
      "epoch": 9.24696802646086,
      "grad_norm": 3.9860610961914062,
      "learning_rate": 8.357915437561455e-05,
      "loss": 3.6428,
      "step": 2090
    },
    {
      "epoch": 9.291069459757441,
      "grad_norm": 3.9992544651031494,
      "learning_rate": 7.866273352999017e-05,
      "loss": 3.4771,
      "step": 2100
    },
    {
      "epoch": 9.335170893054023,
      "grad_norm": 3.782989740371704,
      "learning_rate": 7.374631268436578e-05,
      "loss": 3.506,
      "step": 2110
    },
    {
      "epoch": 9.379272326350605,
      "grad_norm": 3.9225122928619385,
      "learning_rate": 6.882989183874141e-05,
      "loss": 3.4989,
      "step": 2120
    },
    {
      "epoch": 9.42337375964719,
      "grad_norm": 3.853450298309326,
      "learning_rate": 6.391347099311701e-05,
      "loss": 3.49,
      "step": 2130
    },
    {
      "epoch": 9.467475192943771,
      "grad_norm": 3.887131452560425,
      "learning_rate": 5.899705014749263e-05,
      "loss": 3.5517,
      "step": 2140
    },
    {
      "epoch": 9.511576626240354,
      "grad_norm": 3.7988171577453613,
      "learning_rate": 5.4080629301868236e-05,
      "loss": 3.4626,
      "step": 2150
    },
    {
      "epoch": 9.555678059536936,
      "grad_norm": 3.80769419670105,
      "learning_rate": 4.9164208456243856e-05,
      "loss": 3.5627,
      "step": 2160
    },
    {
      "epoch": 9.599779492833518,
      "grad_norm": 3.883881092071533,
      "learning_rate": 4.424778761061947e-05,
      "loss": 3.5904,
      "step": 2170
    },
    {
      "epoch": 9.6438809261301,
      "grad_norm": 3.729762554168701,
      "learning_rate": 3.9331366764995083e-05,
      "loss": 3.5366,
      "step": 2180
    },
    {
      "epoch": 9.687982359426682,
      "grad_norm": 3.7784054279327393,
      "learning_rate": 3.4414945919370704e-05,
      "loss": 3.5186,
      "step": 2190
    },
    {
      "epoch": 9.732083792723264,
      "grad_norm": 3.8702545166015625,
      "learning_rate": 2.9498525073746314e-05,
      "loss": 3.385,
      "step": 2200
    },
    {
      "epoch": 9.776185226019846,
      "grad_norm": 3.82987380027771,
      "learning_rate": 2.4582104228121928e-05,
      "loss": 3.4502,
      "step": 2210
    },
    {
      "epoch": 9.820286659316428,
      "grad_norm": 3.7813146114349365,
      "learning_rate": 1.9665683382497542e-05,
      "loss": 3.4203,
      "step": 2220
    },
    {
      "epoch": 9.86438809261301,
      "grad_norm": 3.8914685249328613,
      "learning_rate": 1.4749262536873157e-05,
      "loss": 3.5059,
      "step": 2230
    },
    {
      "epoch": 9.908489525909593,
      "grad_norm": 3.8533997535705566,
      "learning_rate": 9.832841691248771e-06,
      "loss": 3.483,
      "step": 2240
    },
    {
      "epoch": 9.952590959206175,
      "grad_norm": 3.7153797149658203,
      "learning_rate": 4.9164208456243854e-06,
      "loss": 3.5258,
      "step": 2250
    },
    {
      "epoch": 9.996692392502757,
      "grad_norm": 3.670651435852051,
      "learning_rate": 0.0,
      "loss": 3.4667,
      "step": 2260
    },
    {
      "epoch": 9.996692392502757,
      "eval_accuracy": 0.541167345355827,
      "eval_loss": 1.4404356479644775,
      "eval_runtime": 159.5598,
      "eval_samples_per_second": 161.601,
      "eval_steps_per_second": 0.633,
      "step": 2260
    },
    {
      "epoch": 9.996692392502757,
      "step": 2260,
      "total_flos": 1.8565430446260014e+20,
      "train_loss": 8.705859319298668,
      "train_runtime": 25889.9118,
      "train_samples_per_second": 89.633,
      "train_steps_per_second": 0.087
    },
    {
      "epoch": 9.996692392502757,
      "step": 2260,
      "total_flos": 1.8565430446260014e+20,
      "train_loss": 0.0,
      "train_runtime": 9.3339,
      "train_samples_per_second": 248619.036,
      "train_steps_per_second": 242.129
    }
  ],
  "logging_steps": 10,
  "max_steps": 2260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8565430446260014e+20,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}