{
  "best_metric": 11.208358764648438,
  "best_model_checkpoint": "./FT_models/[LDH]0219_all_llama31_docs_nodocs/checkpoint-1000",
  "epoch": 2.716904276985743,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009051821679112922,
      "grad_norm": 0.874797523021698,
      "learning_rate": 0.0001999995055317446,
      "loss": 1.9293,
      "step": 10
    },
    {
      "epoch": 0.018103643358225844,
      "grad_norm": 0.5239140391349792,
      "learning_rate": 0.0001999955498150411,
      "loss": 1.1773,
      "step": 20
    },
    {
      "epoch": 0.027155465037338764,
      "grad_norm": 0.49293628334999084,
      "learning_rate": 0.00019998763853811184,
      "loss": 1.1369,
      "step": 30
    },
    {
      "epoch": 0.03620728671645169,
      "grad_norm": 0.4514484405517578,
      "learning_rate": 0.00019997577201390606,
      "loss": 1.1049,
      "step": 40
    },
    {
      "epoch": 0.04525910839556461,
      "grad_norm": 0.480444073677063,
      "learning_rate": 0.0001999599507118322,
      "loss": 1.0472,
      "step": 50
    },
    {
      "epoch": 0.05431093007467753,
      "grad_norm": 0.6258535385131836,
      "learning_rate": 0.00019994017525773913,
      "loss": 1.0656,
      "step": 60
    },
    {
      "epoch": 0.06336275175379046,
      "grad_norm": 0.5886121392250061,
      "learning_rate": 0.0001999164464338918,
      "loss": 0.9311,
      "step": 70
    },
    {
      "epoch": 0.07241457343290338,
      "grad_norm": 0.6107162833213806,
      "learning_rate": 0.0001998887651789398,
      "loss": 1.0476,
      "step": 80
    },
    {
      "epoch": 0.0814663951120163,
      "grad_norm": 0.5811272859573364,
      "learning_rate": 0.0001998571325878806,
      "loss": 0.9568,
      "step": 90
    },
    {
      "epoch": 0.09051821679112922,
      "grad_norm": 0.6300623416900635,
      "learning_rate": 0.00019982154991201608,
      "loss": 0.9121,
      "step": 100
    },
    {
      "epoch": 0.09957003847024214,
      "grad_norm": 0.6835796236991882,
      "learning_rate": 0.00019978201855890308,
      "loss": 0.8682,
      "step": 110
    },
    {
      "epoch": 0.10862186014935506,
      "grad_norm": 0.5953958034515381,
      "learning_rate": 0.00019973854009229763,
      "loss": 0.9708,
      "step": 120
    },
    {
      "epoch": 0.11767368182846798,
      "grad_norm": 0.6399095058441162,
      "learning_rate": 0.00019969111623209323,
      "loss": 0.9063,
      "step": 130
    },
    {
      "epoch": 0.1267255035075809,
      "grad_norm": 0.5774116516113281,
      "learning_rate": 0.00019963974885425266,
      "loss": 0.9571,
      "step": 140
    },
    {
      "epoch": 0.13577732518669383,
      "grad_norm": 0.6394885182380676,
      "learning_rate": 0.00019958443999073397,
      "loss": 0.9187,
      "step": 150
    },
    {
      "epoch": 0.14482914686580675,
      "grad_norm": 0.6276863813400269,
      "learning_rate": 0.00019952519182940993,
      "loss": 0.9531,
      "step": 160
    },
    {
      "epoch": 0.15388096854491967,
      "grad_norm": 0.6715622544288635,
      "learning_rate": 0.0001994620067139815,
      "loss": 0.8558,
      "step": 170
    },
    {
      "epoch": 0.1629327902240326,
      "grad_norm": 0.7086506485939026,
      "learning_rate": 0.00019939488714388524,
      "loss": 0.8611,
      "step": 180
    },
    {
      "epoch": 0.1719846119031455,
      "grad_norm": 0.614281177520752,
      "learning_rate": 0.00019932383577419432,
      "loss": 0.7985,
      "step": 190
    },
    {
      "epoch": 0.18103643358225843,
      "grad_norm": 0.6501333117485046,
      "learning_rate": 0.0001992488554155135,
      "loss": 0.8663,
      "step": 200
    },
    {
      "epoch": 0.19008825526137135,
      "grad_norm": 0.59181809425354,
      "learning_rate": 0.0001991699490338681,
      "loss": 0.7611,
      "step": 210
    },
    {
      "epoch": 0.19914007694048427,
      "grad_norm": 0.6414404511451721,
      "learning_rate": 0.00019908711975058637,
      "loss": 0.7952,
      "step": 220
    },
    {
      "epoch": 0.2081918986195972,
      "grad_norm": 0.5972408056259155,
      "learning_rate": 0.00019900037084217637,
      "loss": 0.7415,
      "step": 230
    },
    {
      "epoch": 0.2172437202987101,
      "grad_norm": 0.6564370393753052,
      "learning_rate": 0.00019890970574019617,
      "loss": 0.7951,
      "step": 240
    },
    {
      "epoch": 0.22629554197782303,
      "grad_norm": 0.7463496327400208,
      "learning_rate": 0.00019881512803111796,
      "loss": 0.7421,
      "step": 250
    },
    {
      "epoch": 0.23534736365693595,
      "grad_norm": 0.6890644431114197,
      "learning_rate": 0.00019871664145618657,
      "loss": 0.7929,
      "step": 260
    },
    {
      "epoch": 0.24439918533604887,
      "grad_norm": 0.5937248468399048,
      "learning_rate": 0.00019861424991127115,
      "loss": 0.7801,
      "step": 270
    },
    {
      "epoch": 0.2534510070151618,
      "grad_norm": 0.7962441444396973,
      "learning_rate": 0.00019850795744671116,
      "loss": 0.7889,
      "step": 280
    },
    {
      "epoch": 0.2625028286942747,
      "grad_norm": 0.5598044991493225,
      "learning_rate": 0.00019839776826715614,
      "loss": 0.773,
      "step": 290
    },
    {
      "epoch": 0.27155465037338766,
      "grad_norm": 0.743926465511322,
      "learning_rate": 0.00019828368673139947,
      "loss": 0.7739,
      "step": 300
    },
    {
      "epoch": 0.28060647205250056,
      "grad_norm": 0.5907182693481445,
      "learning_rate": 0.00019816571735220583,
      "loss": 0.7472,
      "step": 310
    },
    {
      "epoch": 0.2896582937316135,
      "grad_norm": 0.7143293619155884,
      "learning_rate": 0.0001980438647961327,
      "loss": 0.723,
      "step": 320
    },
    {
      "epoch": 0.2987101154107264,
      "grad_norm": 0.6375603079795837,
      "learning_rate": 0.00019791813388334581,
      "loss": 0.7454,
      "step": 330
    },
    {
      "epoch": 0.30776193708983934,
      "grad_norm": 0.7762064933776855,
      "learning_rate": 0.00019778852958742853,
      "loss": 0.6882,
      "step": 340
    },
    {
      "epoch": 0.31681375876895224,
      "grad_norm": 0.5525858998298645,
      "learning_rate": 0.00019765505703518496,
      "loss": 0.6642,
      "step": 350
    },
    {
      "epoch": 0.3258655804480652,
      "grad_norm": 0.6317685842514038,
      "learning_rate": 0.00019751772150643722,
      "loss": 0.6965,
      "step": 360
    },
    {
      "epoch": 0.3349174021271781,
      "grad_norm": 0.664470374584198,
      "learning_rate": 0.0001973765284338167,
      "loss": 0.7218,
      "step": 370
    },
    {
      "epoch": 0.343969223806291,
      "grad_norm": 0.587965190410614,
      "learning_rate": 0.00019723148340254892,
      "loss": 0.7628,
      "step": 380
    },
    {
      "epoch": 0.3530210454854039,
      "grad_norm": 0.6755478978157043,
      "learning_rate": 0.0001970825921502328,
      "loss": 0.6277,
      "step": 390
    },
    {
      "epoch": 0.36207286716451687,
      "grad_norm": 0.6129139065742493,
      "learning_rate": 0.00019692986056661356,
      "loss": 0.7238,
      "step": 400
    },
    {
      "epoch": 0.37112468884362976,
      "grad_norm": 0.6757403612136841,
      "learning_rate": 0.0001967732946933499,
      "loss": 0.6568,
      "step": 410
    },
    {
      "epoch": 0.3801765105227427,
      "grad_norm": 0.7164187431335449,
      "learning_rate": 0.00019661290072377482,
      "loss": 0.6963,
      "step": 420
    },
    {
      "epoch": 0.3892283322018556,
      "grad_norm": 0.6669524908065796,
      "learning_rate": 0.0001964486850026507,
      "loss": 0.6931,
      "step": 430
    },
    {
      "epoch": 0.39828015388096855,
      "grad_norm": 0.6036201119422913,
      "learning_rate": 0.00019628065402591845,
      "loss": 0.6989,
      "step": 440
    },
    {
      "epoch": 0.4073319755600815,
      "grad_norm": 0.6022247076034546,
      "learning_rate": 0.0001961088144404403,
      "loss": 0.7669,
      "step": 450
    },
    {
      "epoch": 0.4163837972391944,
      "grad_norm": 0.6327004432678223,
      "learning_rate": 0.00019593317304373705,
      "loss": 0.6673,
      "step": 460
    },
    {
      "epoch": 0.42543561891830733,
      "grad_norm": 0.6826880574226379,
      "learning_rate": 0.00019575373678371909,
      "loss": 0.6965,
      "step": 470
    },
    {
      "epoch": 0.4344874405974202,
      "grad_norm": 0.6268287897109985,
      "learning_rate": 0.0001955705127584117,
      "loss": 0.6468,
      "step": 480
    },
    {
      "epoch": 0.4435392622765332,
      "grad_norm": 0.6102762818336487,
      "learning_rate": 0.00019538350821567404,
      "loss": 0.6302,
      "step": 490
    },
    {
      "epoch": 0.45259108395564607,
      "grad_norm": 0.672012448310852,
      "learning_rate": 0.00019519273055291266,
      "loss": 0.6529,
      "step": 500
    },
    {
      "epoch": 0.45259108395564607,
      "eval_loss": 11.249969482421875,
      "eval_runtime": 42.473,
      "eval_samples_per_second": 7.464,
      "eval_steps_per_second": 3.744,
      "step": 500
    },
    {
      "epoch": 0.461642905634759,
      "grad_norm": 0.6281114220619202,
      "learning_rate": 0.00019499818731678873,
      "loss": 0.705,
      "step": 510
    },
    {
      "epoch": 0.4706947273138719,
      "grad_norm": 0.6248394250869751,
      "learning_rate": 0.00019479988620291956,
      "loss": 0.6999,
      "step": 520
    },
    {
      "epoch": 0.47974654899298486,
      "grad_norm": 0.5792989134788513,
      "learning_rate": 0.00019459783505557424,
      "loss": 0.6166,
      "step": 530
    },
    {
      "epoch": 0.48879837067209775,
      "grad_norm": 0.6465005278587341,
      "learning_rate": 0.0001943920418673633,
      "loss": 0.5985,
      "step": 540
    },
    {
      "epoch": 0.4978501923512107,
      "grad_norm": 0.7002309560775757,
      "learning_rate": 0.0001941825147789225,
      "loss": 0.7327,
      "step": 550
    },
    {
      "epoch": 0.5069020140303236,
      "grad_norm": 0.6550771594047546,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.6097,
      "step": 560
    },
    {
      "epoch": 0.5159538357094365,
      "grad_norm": 0.6645638942718506,
      "learning_rate": 0.00019375229220208276,
      "loss": 0.6032,
      "step": 570
    },
    {
      "epoch": 0.5250056573885494,
      "grad_norm": 0.6332526803016663,
      "learning_rate": 0.0001935316137321543,
      "loss": 0.647,
      "step": 580
    },
    {
      "epoch": 0.5340574790676623,
      "grad_norm": 0.6539055705070496,
      "learning_rate": 0.00019330723539826375,
      "loss": 0.5964,
      "step": 590
    },
    {
      "epoch": 0.5431093007467753,
      "grad_norm": 0.616939902305603,
      "learning_rate": 0.0001930791660762262,
      "loss": 0.6331,
      "step": 600
    },
    {
      "epoch": 0.5521611224258882,
      "grad_norm": 0.6726529598236084,
      "learning_rate": 0.0001928474147878626,
      "loss": 0.6395,
      "step": 610
    },
    {
      "epoch": 0.5612129441050011,
      "grad_norm": 0.6520217061042786,
      "learning_rate": 0.0001926119907006426,
      "loss": 0.5835,
      "step": 620
    },
    {
      "epoch": 0.570264765784114,
      "grad_norm": 0.6048600077629089,
      "learning_rate": 0.00019237290312732226,
      "loss": 0.5824,
      "step": 630
    },
    {
      "epoch": 0.579316587463227,
      "grad_norm": 0.6220108270645142,
      "learning_rate": 0.0001921301615255754,
      "loss": 0.638,
      "step": 640
    },
    {
      "epoch": 0.5883684091423399,
      "grad_norm": 0.6199471354484558,
      "learning_rate": 0.00019188377549761963,
      "loss": 0.591,
      "step": 650
    },
    {
      "epoch": 0.5974202308214528,
      "grad_norm": 0.6387749910354614,
      "learning_rate": 0.00019163375478983632,
      "loss": 0.5934,
      "step": 660
    },
    {
      "epoch": 0.6064720525005657,
      "grad_norm": 0.6121918559074402,
      "learning_rate": 0.00019138010929238534,
      "loss": 0.5164,
      "step": 670
    },
    {
      "epoch": 0.6155238741796787,
      "grad_norm": 0.5336770415306091,
      "learning_rate": 0.0001911228490388136,
      "loss": 0.5644,
      "step": 680
    },
    {
      "epoch": 0.6245756958587916,
      "grad_norm": 0.6676989793777466,
      "learning_rate": 0.00019086198420565823,
      "loss": 0.6162,
      "step": 690
    },
    {
      "epoch": 0.6336275175379045,
      "grad_norm": 0.7787268161773682,
      "learning_rate": 0.000190597525112044,
      "loss": 0.5458,
      "step": 700
    },
    {
      "epoch": 0.6426793392170175,
      "grad_norm": 0.5786814093589783,
      "learning_rate": 0.00019032948221927524,
      "loss": 0.6159,
      "step": 710
    },
    {
      "epoch": 0.6517311608961304,
      "grad_norm": 0.5182745456695557,
      "learning_rate": 0.00019005786613042185,
      "loss": 0.5528,
      "step": 720
    },
    {
      "epoch": 0.6607829825752433,
      "grad_norm": 0.6106360554695129,
      "learning_rate": 0.00018978268758989991,
      "loss": 0.5792,
      "step": 730
    },
    {
      "epoch": 0.6698348042543562,
      "grad_norm": 0.6614301800727844,
      "learning_rate": 0.00018950395748304678,
      "loss": 0.5251,
      "step": 740
    },
    {
      "epoch": 0.6788866259334692,
      "grad_norm": 0.4879720211029053,
      "learning_rate": 0.0001892216868356904,
      "loss": 0.5596,
      "step": 750
    },
    {
      "epoch": 0.687938447612582,
      "grad_norm": 0.7061878442764282,
      "learning_rate": 0.00018893588681371303,
      "loss": 0.5517,
      "step": 760
    },
    {
      "epoch": 0.6969902692916949,
      "grad_norm": 0.7787359952926636,
      "learning_rate": 0.00018864656872260985,
      "loss": 0.5813,
      "step": 770
    },
    {
      "epoch": 0.7060420909708078,
      "grad_norm": 0.5743793845176697,
      "learning_rate": 0.00018835374400704154,
      "loss": 0.56,
      "step": 780
    },
    {
      "epoch": 0.7150939126499208,
      "grad_norm": 0.5919637680053711,
      "learning_rate": 0.00018805742425038145,
      "loss": 0.5429,
      "step": 790
    },
    {
      "epoch": 0.7241457343290337,
      "grad_norm": 0.5750169157981873,
      "learning_rate": 0.00018775762117425777,
      "loss": 0.5303,
      "step": 800
    },
    {
      "epoch": 0.7331975560081466,
      "grad_norm": 0.5034388899803162,
      "learning_rate": 0.00018745434663808942,
      "loss": 0.554,
      "step": 810
    },
    {
      "epoch": 0.7422493776872595,
      "grad_norm": 0.6673147678375244,
      "learning_rate": 0.00018714761263861728,
      "loss": 0.5769,
      "step": 820
    },
    {
      "epoch": 0.7513011993663725,
      "grad_norm": 0.6599574089050293,
      "learning_rate": 0.00018683743130942928,
      "loss": 0.5316,
      "step": 830
    },
    {
      "epoch": 0.7603530210454854,
      "grad_norm": 0.6396362781524658,
      "learning_rate": 0.00018652381492048083,
      "loss": 0.5061,
      "step": 840
    },
    {
      "epoch": 0.7694048427245983,
      "grad_norm": 0.5517466068267822,
      "learning_rate": 0.00018620677587760916,
      "loss": 0.5951,
      "step": 850
    },
    {
      "epoch": 0.7784566644037112,
      "grad_norm": 0.5412144064903259,
      "learning_rate": 0.00018588632672204264,
      "loss": 0.4929,
      "step": 860
    },
    {
      "epoch": 0.7875084860828242,
      "grad_norm": 0.5431721210479736,
      "learning_rate": 0.00018556248012990468,
      "loss": 0.5358,
      "step": 870
    },
    {
      "epoch": 0.7965603077619371,
      "grad_norm": 0.5506939888000488,
      "learning_rate": 0.0001852352489117124,
      "loss": 0.4487,
      "step": 880
    },
    {
      "epoch": 0.80561212944105,
      "grad_norm": 0.5743805766105652,
      "learning_rate": 0.0001849046460118698,
      "loss": 0.5725,
      "step": 890
    },
    {
      "epoch": 0.814663951120163,
      "grad_norm": 0.573427677154541,
      "learning_rate": 0.00018457068450815562,
      "loss": 0.5078,
      "step": 900
    },
    {
      "epoch": 0.8237157727992759,
      "grad_norm": 0.6854224801063538,
      "learning_rate": 0.00018423337761120618,
      "loss": 0.4688,
      "step": 910
    },
    {
      "epoch": 0.8327675944783888,
      "grad_norm": 0.6372252702713013,
      "learning_rate": 0.00018389273866399275,
      "loss": 0.5169,
      "step": 920
    },
    {
      "epoch": 0.8418194161575017,
      "grad_norm": 0.6130049228668213,
      "learning_rate": 0.00018354878114129367,
      "loss": 0.5089,
      "step": 930
    },
    {
      "epoch": 0.8508712378366147,
      "grad_norm": 0.5654692649841309,
      "learning_rate": 0.00018320151864916135,
      "loss": 0.5492,
      "step": 940
    },
    {
      "epoch": 0.8599230595157276,
      "grad_norm": 0.548478901386261,
      "learning_rate": 0.00018285096492438424,
      "loss": 0.5218,
      "step": 950
    },
    {
      "epoch": 0.8689748811948405,
      "grad_norm": 0.5212107300758362,
      "learning_rate": 0.00018249713383394303,
      "loss": 0.5803,
      "step": 960
    },
    {
      "epoch": 0.8780267028739533,
      "grad_norm": 0.5414544939994812,
      "learning_rate": 0.00018214003937446253,
      "loss": 0.5677,
      "step": 970
    },
    {
      "epoch": 0.8870785245530663,
      "grad_norm": 0.58649742603302,
      "learning_rate": 0.0001817796956716578,
      "loss": 0.5331,
      "step": 980
    },
    {
      "epoch": 0.8961303462321792,
      "grad_norm": 0.5166681408882141,
      "learning_rate": 0.00018141611697977529,
      "loss": 0.5032,
      "step": 990
    },
    {
      "epoch": 0.9051821679112921,
      "grad_norm": 0.6174758076667786,
      "learning_rate": 0.0001810493176810292,
      "loss": 0.5148,
      "step": 1000
    },
    {
      "epoch": 0.9051821679112921,
      "eval_loss": 11.208358764648438,
      "eval_runtime": 42.0152,
      "eval_samples_per_second": 7.545,
      "eval_steps_per_second": 3.784,
      "step": 1000
    },
    {
      "epoch": 0.914233989590405,
      "grad_norm": 0.6219255924224854,
      "learning_rate": 0.00018067931228503246,
      "loss": 0.5486,
      "step": 1010
    },
    {
      "epoch": 0.923285811269518,
      "grad_norm": 0.5557869672775269,
      "learning_rate": 0.00018030611542822257,
      "loss": 0.4645,
      "step": 1020
    },
    {
      "epoch": 0.9323376329486309,
      "grad_norm": 0.6376787424087524,
      "learning_rate": 0.00017992974187328305,
      "loss": 0.5582,
      "step": 1030
    },
    {
      "epoch": 0.9413894546277438,
      "grad_norm": 0.6127185821533203,
      "learning_rate": 0.000179550206508559,
      "loss": 0.5878,
      "step": 1040
    },
    {
      "epoch": 0.9504412763068567,
      "grad_norm": 1.0581947565078735,
      "learning_rate": 0.00017916752434746856,
      "loss": 0.5113,
      "step": 1050
    },
    {
      "epoch": 0.9594930979859697,
      "grad_norm": 0.6159986257553101,
      "learning_rate": 0.00017878171052790868,
      "loss": 0.5226,
      "step": 1060
    },
    {
      "epoch": 0.9685449196650826,
      "grad_norm": 0.6697051525115967,
      "learning_rate": 0.00017839278031165658,
      "loss": 0.5011,
      "step": 1070
    },
    {
      "epoch": 0.9775967413441955,
      "grad_norm": 0.6310513019561768,
      "learning_rate": 0.00017800074908376584,
      "loss": 0.4599,
      "step": 1080
    },
    {
      "epoch": 0.9866485630233084,
      "grad_norm": 0.5671334266662598,
      "learning_rate": 0.0001776056323519579,
      "loss": 0.4455,
      "step": 1090
    },
    {
      "epoch": 0.9957003847024214,
      "grad_norm": 0.5935373902320862,
      "learning_rate": 0.00017720744574600863,
      "loss": 0.472,
      "step": 1100
    },
    {
      "epoch": 1.0054310930074677,
      "grad_norm": 0.4842943251132965,
      "learning_rate": 0.00017680620501712996,
      "loss": 0.4619,
      "step": 1110
    },
    {
      "epoch": 1.0144829146865806,
      "grad_norm": 0.5976426601409912,
      "learning_rate": 0.00017640192603734692,
      "loss": 0.4535,
      "step": 1120
    },
    {
      "epoch": 1.0235347363656937,
      "grad_norm": 0.5157873630523682,
      "learning_rate": 0.00017599462479886974,
      "loss": 0.3832,
      "step": 1130
    },
    {
      "epoch": 1.0325865580448066,
      "grad_norm": 0.6044872403144836,
      "learning_rate": 0.00017558431741346122,
      "loss": 0.4133,
      "step": 1140
    },
    {
      "epoch": 1.0416383797239195,
      "grad_norm": 0.6488142013549805,
      "learning_rate": 0.00017517102011179933,
      "loss": 0.4391,
      "step": 1150
    },
    {
      "epoch": 1.0506902014030324,
      "grad_norm": 0.5446122884750366,
      "learning_rate": 0.00017475474924283536,
      "loss": 0.3626,
      "step": 1160
    },
    {
      "epoch": 1.0597420230821453,
      "grad_norm": 0.4834959805011749,
      "learning_rate": 0.000174335521273147,
      "loss": 0.3712,
      "step": 1170
    },
    {
      "epoch": 1.0687938447612582,
      "grad_norm": 0.506747305393219,
      "learning_rate": 0.00017391335278628712,
      "loss": 0.3985,
      "step": 1180
    },
    {
      "epoch": 1.077845666440371,
      "grad_norm": 0.5550024509429932,
      "learning_rate": 0.0001734882604821276,
      "loss": 0.4201,
      "step": 1190
    },
    {
      "epoch": 1.086897488119484,
      "grad_norm": 0.5207591652870178,
      "learning_rate": 0.00017306026117619889,
      "loss": 0.3782,
      "step": 1200
    },
    {
      "epoch": 1.095949309798597,
      "grad_norm": 0.6619957089424133,
      "learning_rate": 0.00017262937179902472,
      "loss": 0.4203,
      "step": 1210
    },
    {
      "epoch": 1.10500113147771,
      "grad_norm": 0.6261160969734192,
      "learning_rate": 0.00017219560939545246,
      "loss": 0.3877,
      "step": 1220
    },
    {
      "epoch": 1.1140529531568228,
      "grad_norm": 0.6254423260688782,
      "learning_rate": 0.0001717589911239788,
      "loss": 0.4245,
      "step": 1230
    },
    {
      "epoch": 1.1231047748359357,
      "grad_norm": 0.5006200671195984,
      "learning_rate": 0.00017131953425607104,
      "loss": 0.399,
      "step": 1240
    },
    {
      "epoch": 1.1321565965150486,
      "grad_norm": 0.5162988305091858,
      "learning_rate": 0.00017087725617548385,
      "loss": 0.4325,
      "step": 1250
    },
    {
      "epoch": 1.1412084181941615,
      "grad_norm": 0.5567941665649414,
      "learning_rate": 0.00017043217437757164,
      "loss": 0.4391,
      "step": 1260
    },
    {
      "epoch": 1.1502602398732744,
      "grad_norm": 0.6780401468276978,
      "learning_rate": 0.00016998430646859654,
      "loss": 0.4388,
      "step": 1270
    },
    {
      "epoch": 1.1593120615523875,
      "grad_norm": 0.6121058464050293,
      "learning_rate": 0.00016953367016503182,
      "loss": 0.4216,
      "step": 1280
    },
    {
      "epoch": 1.1683638832315004,
      "grad_norm": 0.6004344820976257,
      "learning_rate": 0.00016908028329286112,
      "loss": 0.4171,
      "step": 1290
    },
    {
      "epoch": 1.1774157049106133,
      "grad_norm": 0.46892327070236206,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.3628,
      "step": 1300
    },
    {
      "epoch": 1.1864675265897262,
      "grad_norm": 0.6038176417350769,
      "learning_rate": 0.00016816532968995328,
      "loss": 0.3771,
      "step": 1310
    },
    {
      "epoch": 1.195519348268839,
      "grad_norm": 0.5433237552642822,
      "learning_rate": 0.00016770379915236766,
      "loss": 0.4029,
      "step": 1320
    },
    {
      "epoch": 1.204571169947952,
      "grad_norm": 0.6447364091873169,
      "learning_rate": 0.00016723959043104728,
      "loss": 0.4154,
      "step": 1330
    },
    {
      "epoch": 1.2136229916270649,
      "grad_norm": 0.45961570739746094,
      "learning_rate": 0.00016677272188886483,
      "loss": 0.412,
      "step": 1340
    },
    {
      "epoch": 1.2226748133061778,
      "grad_norm": 0.5007642507553101,
      "learning_rate": 0.00016630321199390867,
      "loss": 0.4137,
      "step": 1350
    },
    {
      "epoch": 1.2317266349852907,
      "grad_norm": 0.4964968264102936,
      "learning_rate": 0.00016583107931875192,
      "loss": 0.3922,
      "step": 1360
    },
    {
      "epoch": 1.2407784566644038,
      "grad_norm": 0.573707640171051,
      "learning_rate": 0.00016535634253971794,
      "loss": 0.3778,
      "step": 1370
    },
    {
      "epoch": 1.2498302783435167,
      "grad_norm": 0.5992773771286011,
      "learning_rate": 0.00016487902043614173,
      "loss": 0.4528,
      "step": 1380
    },
    {
      "epoch": 1.2588821000226296,
      "grad_norm": 0.650651216506958,
      "learning_rate": 0.00016439913188962685,
      "loss": 0.3915,
      "step": 1390
    },
    {
      "epoch": 1.2679339217017425,
      "grad_norm": 0.5636417865753174,
      "learning_rate": 0.0001639166958832985,
      "loss": 0.3947,
      "step": 1400
    },
    {
      "epoch": 1.2769857433808554,
      "grad_norm": 0.5544995665550232,
      "learning_rate": 0.00016343173150105278,
      "loss": 0.4252,
      "step": 1410
    },
    {
      "epoch": 1.2860375650599682,
      "grad_norm": 0.5746600031852722,
      "learning_rate": 0.0001629442579268016,
      "loss": 0.4127,
      "step": 1420
    },
    {
      "epoch": 1.2950893867390811,
      "grad_norm": 0.5972291231155396,
      "learning_rate": 0.0001624542944437139,
      "loss": 0.3918,
      "step": 1430
    },
    {
      "epoch": 1.3041412084181943,
      "grad_norm": 0.6181298494338989,
      "learning_rate": 0.00016196186043345288,
      "loss": 0.3615,
      "step": 1440
    },
    {
      "epoch": 1.3131930300973071,
      "grad_norm": 0.5114730000495911,
      "learning_rate": 0.00016146697537540924,
      "loss": 0.3966,
      "step": 1450
    },
    {
      "epoch": 1.32224485177642,
      "grad_norm": 0.5740589499473572,
      "learning_rate": 0.0001609696588459307,
      "loss": 0.4061,
      "step": 1460
    },
    {
      "epoch": 1.331296673455533,
      "grad_norm": 0.6494064927101135,
      "learning_rate": 0.00016046993051754756,
      "loss": 0.3979,
      "step": 1470
    },
    {
      "epoch": 1.3403484951346458,
      "grad_norm": 0.6532962322235107,
      "learning_rate": 0.0001599678101581945,
      "loss": 0.4531,
      "step": 1480
    },
    {
      "epoch": 1.3494003168137587,
      "grad_norm": 0.7263498306274414,
      "learning_rate": 0.00015946331763042867,
      "loss": 0.3788,
      "step": 1490
    },
    {
      "epoch": 1.3584521384928716,
      "grad_norm": 0.8316817879676819,
      "learning_rate": 0.00015895647289064396,
      "loss": 0.4298,
      "step": 1500
    },
    {
      "epoch": 1.3584521384928716,
      "eval_loss": 11.852625846862793,
      "eval_runtime": 42.2271,
      "eval_samples_per_second": 7.507,
      "eval_steps_per_second": 3.765,
      "step": 1500
    },
    {
      "epoch": 1.3675039601719847,
      "grad_norm": 0.4995158314704895,
      "learning_rate": 0.0001584472959882815,
      "loss": 0.4021,
      "step": 1510
    },
    {
      "epoch": 1.3765557818510976,
      "grad_norm": 0.6390697360038757,
      "learning_rate": 0.0001579358070650367,
      "loss": 0.3633,
      "step": 1520
    },
    {
      "epoch": 1.3856076035302105,
      "grad_norm": 0.5589749217033386,
      "learning_rate": 0.00015742202635406235,
      "loss": 0.3524,
      "step": 1530
    },
    {
      "epoch": 1.3946594252093234,
      "grad_norm": 0.5728365778923035,
      "learning_rate": 0.0001569059741791684,
      "loss": 0.3456,
      "step": 1540
    },
    {
      "epoch": 1.4037112468884363,
      "grad_norm": 0.45577678084373474,
      "learning_rate": 0.0001563876709540178,
      "loss": 0.3706,
      "step": 1550
    },
    {
      "epoch": 1.4127630685675492,
      "grad_norm": 0.7161752581596375,
      "learning_rate": 0.00015586713718131922,
      "loss": 0.362,
      "step": 1560
    },
    {
      "epoch": 1.421814890246662,
      "grad_norm": 0.530432403087616,
      "learning_rate": 0.0001553443934520159,
      "loss": 0.3798,
      "step": 1570
    },
    {
      "epoch": 1.4308667119257752,
      "grad_norm": 0.5991781949996948,
      "learning_rate": 0.00015481946044447099,
      "loss": 0.3965,
      "step": 1580
    },
    {
      "epoch": 1.4399185336048879,
      "grad_norm": 0.5994631052017212,
      "learning_rate": 0.00015429235892364994,
      "loss": 0.3855,
      "step": 1590
    },
    {
      "epoch": 1.448970355284001,
      "grad_norm": 0.5677673816680908,
      "learning_rate": 0.00015376310974029873,
      "loss": 0.3773,
      "step": 1600
    },
    {
      "epoch": 1.4580221769631139,
      "grad_norm": 0.4799586236476898,
      "learning_rate": 0.0001532317338301192,
      "loss": 0.3466,
      "step": 1610
    },
    {
      "epoch": 1.4670739986422268,
      "grad_norm": 0.5448312163352966,
      "learning_rate": 0.00015269825221294098,
      "loss": 0.3664,
      "step": 1620
    },
    {
      "epoch": 1.4761258203213397,
      "grad_norm": 0.5199277400970459,
      "learning_rate": 0.0001521626859918898,
      "loss": 0.3838,
      "step": 1630
    },
    {
      "epoch": 1.4851776420004525,
      "grad_norm": 0.4976363778114319,
      "learning_rate": 0.00015162505635255287,
      "loss": 0.3811,
      "step": 1640
    },
    {
      "epoch": 1.4942294636795654,
      "grad_norm": 0.6075541377067566,
      "learning_rate": 0.0001510853845621409,
      "loss": 0.3756,
      "step": 1650
    },
    {
      "epoch": 1.5032812853586783,
      "grad_norm": 0.5979759097099304,
      "learning_rate": 0.00015054369196864644,
      "loss": 0.3973,
      "step": 1660
    },
    {
      "epoch": 1.5123331070377914,
      "grad_norm": 0.9770258665084839,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4124,
      "step": 1670
    },
    {
      "epoch": 1.5213849287169041,
      "grad_norm": 0.580491840839386,
      "learning_rate": 0.0001494543301632219,
      "loss": 0.3827,
      "step": 1680
    },
    {
      "epoch": 1.5304367503960172,
      "grad_norm": 0.6543178558349609,
      "learning_rate": 0.0001489067040435717,
      "loss": 0.4009,
      "step": 1690
    },
    {
      "epoch": 1.5394885720751301,
      "grad_norm": 0.5909605622291565,
      "learning_rate": 0.00014835714330369446,
      "loss": 0.4272,
      "step": 1700
    },
    {
      "epoch": 1.548540393754243,
      "grad_norm": 0.4959102272987366,
      "learning_rate": 0.0001478056696827636,
      "loss": 0.3536,
      "step": 1710
    },
    {
      "epoch": 1.557592215433356,
      "grad_norm": 0.5864228010177612,
      "learning_rate": 0.00014725230499562119,
      "loss": 0.3657,
      "step": 1720
    },
    {
      "epoch": 1.5666440371124688,
      "grad_norm": 0.6094350814819336,
      "learning_rate": 0.00014669707113191483,
      "loss": 0.3889,
      "step": 1730
    },
    {
      "epoch": 1.575695858791582,
      "grad_norm": 0.45741668343544006,
      "learning_rate": 0.00014613999005523174,
      "loss": 0.37,
      "step": 1740
    },
    {
      "epoch": 1.5847476804706946,
      "grad_norm": 0.5069059729576111,
      "learning_rate": 0.00014558108380223012,
      "loss": 0.3992,
      "step": 1750
    },
    {
      "epoch": 1.5937995021498077,
      "grad_norm": 0.535524845123291,
      "learning_rate": 0.00014502037448176734,
      "loss": 0.3763,
      "step": 1760
    },
    {
      "epoch": 1.6028513238289206,
      "grad_norm": 0.5067459940910339,
      "learning_rate": 0.00014445788427402528,
      "loss": 0.3409,
      "step": 1770
    },
    {
      "epoch": 1.6119031455080335,
      "grad_norm": 0.5375223159790039,
      "learning_rate": 0.00014389363542963306,
      "loss": 0.3778,
      "step": 1780
    },
    {
      "epoch": 1.6209549671871464,
      "grad_norm": 0.5057679414749146,
      "learning_rate": 0.00014332765026878687,
      "loss": 0.362,
      "step": 1790
    },
    {
      "epoch": 1.6300067888662593,
      "grad_norm": 0.5510945320129395,
      "learning_rate": 0.00014275995118036693,
      "loss": 0.374,
      "step": 1800
    },
    {
      "epoch": 1.6390586105453724,
      "grad_norm": 0.619204580783844,
      "learning_rate": 0.00014219056062105193,
      "loss": 0.4279,
      "step": 1810
    },
    {
      "epoch": 1.648110432224485,
      "grad_norm": 0.5340638160705566,
      "learning_rate": 0.00014161950111443077,
      "loss": 0.3675,
      "step": 1820
    },
    {
      "epoch": 1.6571622539035982,
      "grad_norm": 0.6182312965393066,
      "learning_rate": 0.0001410467952501114,
      "loss": 0.3686,
      "step": 1830
    },
    {
      "epoch": 1.666214075582711,
      "grad_norm": 0.5214246511459351,
      "learning_rate": 0.00014047246568282736,
      "loss": 0.4001,
      "step": 1840
    },
    {
      "epoch": 1.675265897261824,
      "grad_norm": 0.4987814128398895,
      "learning_rate": 0.00013989653513154165,
      "loss": 0.357,
      "step": 1850
    },
    {
      "epoch": 1.6843177189409368,
      "grad_norm": 0.6497951149940491,
      "learning_rate": 0.0001393190263785479,
      "loss": 0.3722,
      "step": 1860
    },
    {
      "epoch": 1.6933695406200497,
      "grad_norm": 0.4140976667404175,
      "learning_rate": 0.00013873996226856933,
      "loss": 0.316,
      "step": 1870
    },
    {
      "epoch": 1.7024213622991629,
      "grad_norm": 0.5191941857337952,
      "learning_rate": 0.00013815936570785487,
      "loss": 0.3865,
      "step": 1880
    },
    {
      "epoch": 1.7114731839782755,
      "grad_norm": 0.5386790037155151,
      "learning_rate": 0.00013757725966327322,
      "loss": 0.3499,
      "step": 1890
    },
    {
      "epoch": 1.7205250056573886,
      "grad_norm": 0.5060738921165466,
      "learning_rate": 0.00013699366716140435,
      "loss": 0.3481,
      "step": 1900
    },
    {
      "epoch": 1.7295768273365013,
      "grad_norm": 0.5718989968299866,
      "learning_rate": 0.0001364086112876284,
      "loss": 0.3713,
      "step": 1910
    },
    {
      "epoch": 1.7386286490156144,
      "grad_norm": 0.5812616348266602,
      "learning_rate": 0.00013582211518521273,
      "loss": 0.3651,
      "step": 1920
    },
    {
      "epoch": 1.7476804706947273,
      "grad_norm": 0.42051294445991516,
      "learning_rate": 0.00013523420205439646,
      "loss": 0.3581,
      "step": 1930
    },
    {
      "epoch": 1.7567322923738402,
      "grad_norm": 0.6224139928817749,
      "learning_rate": 0.00013464489515147238,
      "loss": 0.3663,
      "step": 1940
    },
    {
      "epoch": 1.765784114052953,
      "grad_norm": 0.5418313145637512,
      "learning_rate": 0.00013405421778786737,
      "loss": 0.3521,
      "step": 1950
    },
    {
      "epoch": 1.774835935732066,
      "grad_norm": 0.5429657101631165,
      "learning_rate": 0.00013346219332922016,
      "loss": 0.3946,
      "step": 1960
    },
    {
      "epoch": 1.783887757411179,
      "grad_norm": 0.5962104797363281,
      "learning_rate": 0.0001328688451944569,
      "loss": 0.4121,
      "step": 1970
    },
    {
      "epoch": 1.7929395790902918,
      "grad_norm": 0.5818737745285034,
      "learning_rate": 0.00013227419685486492,
      "loss": 0.3209,
      "step": 1980
    },
    {
      "epoch": 1.801991400769405,
      "grad_norm": 0.4606368839740753,
      "learning_rate": 0.0001316782718331643,
      "loss": 0.316,
      "step": 1990
    },
    {
      "epoch": 1.8110432224485178,
      "grad_norm": 0.49896928668022156,
      "learning_rate": 0.00013108109370257712,
      "loss": 0.3538,
      "step": 2000
    },
    {
      "epoch": 1.8110432224485178,
      "eval_loss": 11.89608383178711,
      "eval_runtime": 41.6812,
      "eval_samples_per_second": 7.605,
      "eval_steps_per_second": 3.815,
      "step": 2000
    },
    {
      "epoch": 1.8200950441276307,
      "grad_norm": 0.4855138659477234,
      "learning_rate": 0.00013048268608589533,
      "loss": 0.3578,
      "step": 2010
    },
    {
      "epoch": 1.8291468658067436,
      "grad_norm": 0.577150285243988,
      "learning_rate": 0.00012988307265454597,
      "loss": 0.3644,
      "step": 2020
    },
    {
      "epoch": 1.8381986874858565,
      "grad_norm": 0.5089125037193298,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.398,
      "step": 2030
    },
    {
      "epoch": 1.8472505091649696,
      "grad_norm": 0.44641053676605225,
      "learning_rate": 0.00012868032327110904,
      "loss": 0.3656,
      "step": 2040
    },
    {
      "epoch": 1.8563023308440822,
      "grad_norm": 0.5212085247039795,
      "learning_rate": 0.00012807723489661495,
      "loss": 0.3396,
      "step": 2050
    },
    {
      "epoch": 1.8653541525231954,
      "grad_norm": 0.48269546031951904,
      "learning_rate": 0.0001274730358607583,
      "loss": 0.3649,
      "step": 2060
    },
    {
      "epoch": 1.8744059742023083,
      "grad_norm": 0.5938083529472351,
      "learning_rate": 0.00012686775006405946,
      "loss": 0.3318,
      "step": 2070
    },
    {
      "epoch": 1.8834577958814211,
      "grad_norm": 0.46941766142845154,
      "learning_rate": 0.0001262614014500282,
      "loss": 0.3625,
      "step": 2080
    },
    {
      "epoch": 1.892509617560534,
      "grad_norm": 0.6015097498893738,
      "learning_rate": 0.00012565401400421651,
      "loss": 0.4174,
      "step": 2090
    },
    {
      "epoch": 1.901561439239647,
      "grad_norm": 0.6819751858711243,
      "learning_rate": 0.00012504561175326985,
      "loss": 0.351,
      "step": 2100
    },
    {
      "epoch": 1.91061326091876,
      "grad_norm": 0.4607352018356323,
      "learning_rate": 0.0001244362187639767,
      "loss": 0.3488,
      "step": 2110
    },
    {
      "epoch": 1.9196650825978727,
      "grad_norm": 0.7872518301010132,
      "learning_rate": 0.0001238258591423165,
      "loss": 0.3719,
      "step": 2120
    },
    {
      "epoch": 1.9287169042769858,
      "grad_norm": 0.49948009848594666,
      "learning_rate": 0.00012321455703250616,
      "loss": 0.3415,
      "step": 2130
    },
    {
      "epoch": 1.9377687259560985,
      "grad_norm": 0.513294517993927,
      "learning_rate": 0.0001226023366160449,
      "loss": 0.3575,
      "step": 2140
    },
    {
      "epoch": 1.9468205476352116,
      "grad_norm": 0.7481987476348877,
      "learning_rate": 0.00012198922211075778,
      "loss": 0.3465,
      "step": 2150
    },
    {
      "epoch": 1.9558723693143245,
      "grad_norm": 0.4865647852420807,
      "learning_rate": 0.00012137523776983757,
      "loss": 0.3246,
      "step": 2160
    },
    {
      "epoch": 1.9649241909934374,
      "grad_norm": 0.35988450050354004,
      "learning_rate": 0.00012076040788088554,
      "loss": 0.3506,
      "step": 2170
    },
    {
      "epoch": 1.9739760126725503,
      "grad_norm": 0.46516749262809753,
      "learning_rate": 0.00012014475676495052,
      "loss": 0.3077,
      "step": 2180
    },
    {
      "epoch": 1.9830278343516632,
      "grad_norm": 0.5179293751716614,
      "learning_rate": 0.000119528308775567,
      "loss": 0.375,
      "step": 2190
    },
    {
      "epoch": 1.9920796560307763,
      "grad_norm": 0.5721428394317627,
      "learning_rate": 0.00011891108829779165,
      "loss": 0.3503,
      "step": 2200
    },
    {
      "epoch": 2.0018103643358227,
      "grad_norm": 0.4291672706604004,
      "learning_rate": 0.00011829311974723867,
      "loss": 0.3745,
      "step": 2210
    },
    {
      "epoch": 2.0108621860149354,
      "grad_norm": 0.4879133701324463,
      "learning_rate": 0.00011767442756911417,
      "loss": 0.2479,
      "step": 2220
    },
    {
      "epoch": 2.0199140076940485,
      "grad_norm": 0.5393707752227783,
      "learning_rate": 0.00011705503623724898,
      "loss": 0.222,
      "step": 2230
    },
    {
      "epoch": 2.028965829373161,
      "grad_norm": 0.5438636541366577,
      "learning_rate": 0.00011643497025313061,
      "loss": 0.2726,
      "step": 2240
    },
    {
      "epoch": 2.0380176510522743,
      "grad_norm": 0.5499648451805115,
      "learning_rate": 0.0001158142541449341,
      "loss": 0.2583,
      "step": 2250
    },
    {
      "epoch": 2.0470694727313874,
      "grad_norm": 0.5354553461074829,
      "learning_rate": 0.0001151929124665516,
      "loss": 0.2365,
      "step": 2260
    },
    {
      "epoch": 2.0561212944105,
      "grad_norm": 0.586413562297821,
      "learning_rate": 0.00011457096979662114,
      "loss": 0.243,
      "step": 2270
    },
    {
      "epoch": 2.065173116089613,
      "grad_norm": 0.48880791664123535,
      "learning_rate": 0.00011394845073755455,
      "loss": 0.2534,
      "step": 2280
    },
    {
      "epoch": 2.074224937768726,
      "grad_norm": 0.5162414908409119,
      "learning_rate": 0.00011332537991456398,
      "loss": 0.2279,
      "step": 2290
    },
    {
      "epoch": 2.083276759447839,
      "grad_norm": 0.6083577871322632,
      "learning_rate": 0.00011270178197468789,
      "loss": 0.2353,
      "step": 2300
    },
    {
      "epoch": 2.0923285811269516,
      "grad_norm": 0.5396526455879211,
      "learning_rate": 0.00011207768158581613,
      "loss": 0.2396,
      "step": 2310
    },
    {
      "epoch": 2.1013804028060648,
      "grad_norm": 0.5191901326179504,
      "learning_rate": 0.00011145310343571411,
      "loss": 0.2557,
      "step": 2320
    },
    {
      "epoch": 2.1104322244851774,
      "grad_norm": 0.4944523572921753,
      "learning_rate": 0.0001108280722310462,
      "loss": 0.2332,
      "step": 2330
    },
    {
      "epoch": 2.1194840461642905,
      "grad_norm": 0.49368587136268616,
      "learning_rate": 0.00011020261269639842,
      "loss": 0.2395,
      "step": 2340
    },
    {
      "epoch": 2.1285358678434037,
      "grad_norm": 0.5858927369117737,
      "learning_rate": 0.00010957674957330042,
      "loss": 0.27,
      "step": 2350
    },
    {
      "epoch": 2.1375876895225163,
      "grad_norm": 0.5289851427078247,
      "learning_rate": 0.00010895050761924668,
      "loss": 0.2777,
      "step": 2360
    },
    {
      "epoch": 2.1466395112016294,
      "grad_norm": 0.5512372851371765,
      "learning_rate": 0.00010832391160671729,
      "loss": 0.257,
      "step": 2370
    },
    {
      "epoch": 2.155691332880742,
      "grad_norm": 0.48882365226745605,
      "learning_rate": 0.00010769698632219794,
      "loss": 0.2513,
      "step": 2380
    },
    {
      "epoch": 2.164743154559855,
      "grad_norm": 0.4982316792011261,
      "learning_rate": 0.00010706975656519946,
      "loss": 0.2265,
      "step": 2390
    },
    {
      "epoch": 2.173794976238968,
      "grad_norm": 0.5512099266052246,
      "learning_rate": 0.00010644224714727681,
      "loss": 0.2586,
      "step": 2400
    },
    {
      "epoch": 2.182846797918081,
      "grad_norm": 0.5546220541000366,
      "learning_rate": 0.00010581448289104758,
      "loss": 0.2494,
      "step": 2410
    },
    {
      "epoch": 2.191898619597194,
      "grad_norm": 0.6402847170829773,
      "learning_rate": 0.00010518648862921012,
      "loss": 0.2467,
      "step": 2420
    },
    {
      "epoch": 2.200950441276307,
      "grad_norm": 0.4461919665336609,
      "learning_rate": 0.00010455828920356115,
      "loss": 0.2248,
      "step": 2430
    },
    {
      "epoch": 2.21000226295542,
      "grad_norm": 0.562235951423645,
      "learning_rate": 0.00010392990946401313,
      "loss": 0.2196,
      "step": 2440
    },
    {
      "epoch": 2.2190540846345326,
      "grad_norm": 0.49623265862464905,
      "learning_rate": 0.00010330137426761135,
      "loss": 0.2572,
      "step": 2450
    },
    {
      "epoch": 2.2281059063136457,
      "grad_norm": 0.5660530924797058,
      "learning_rate": 0.00010267270847755048,
      "loss": 0.2523,
      "step": 2460
    },
    {
      "epoch": 2.2371577279927584,
      "grad_norm": 0.5315167307853699,
      "learning_rate": 0.00010204393696219117,
      "loss": 0.2489,
      "step": 2470
    },
    {
      "epoch": 2.2462095496718715,
      "grad_norm": 0.530099093914032,
      "learning_rate": 0.00010141508459407623,
      "loss": 0.2603,
      "step": 2480
    },
    {
      "epoch": 2.2552613713509846,
      "grad_norm": 0.6275547742843628,
      "learning_rate": 0.00010078617624894684,
      "loss": 0.2338,
      "step": 2490
    },
    {
      "epoch": 2.2643131930300973,
      "grad_norm": 0.5999734997749329,
      "learning_rate": 0.00010015723680475846,
      "loss": 0.2418,
      "step": 2500
    },
    {
      "epoch": 2.2643131930300973,
      "eval_loss": 12.012301445007324,
      "eval_runtime": 42.3048,
      "eval_samples_per_second": 7.493,
      "eval_steps_per_second": 3.758,
      "step": 2500
    },
    {
      "epoch": 2.2733650147092104,
      "grad_norm": 0.5600557327270508,
      "learning_rate": 9.95282911406968e-05,
      "loss": 0.2394,
      "step": 2510
    },
    {
      "epoch": 2.282416836388323,
      "grad_norm": 0.383777379989624,
      "learning_rate": 9.889936413619356e-05,
      "loss": 0.2331,
      "step": 2520
    },
    {
      "epoch": 2.291468658067436,
      "grad_norm": 0.5634308457374573,
      "learning_rate": 9.827048066994225e-05,
      "loss": 0.2492,
      "step": 2530
    },
    {
      "epoch": 2.300520479746549,
      "grad_norm": 0.5783660411834717,
      "learning_rate": 9.764166561891432e-05,
      "loss": 0.2524,
      "step": 2540
    },
    {
      "epoch": 2.309572301425662,
      "grad_norm": 0.6156514286994934,
      "learning_rate": 9.70129438573747e-05,
      "loss": 0.2655,
      "step": 2550
    },
    {
      "epoch": 2.318624123104775,
      "grad_norm": 0.3963329493999481,
      "learning_rate": 9.63843402558981e-05,
      "loss": 0.2459,
      "step": 2560
    },
    {
      "epoch": 2.3276759447838877,
      "grad_norm": 0.4392152726650238,
      "learning_rate": 9.57558796803852e-05,
      "loss": 0.2579,
      "step": 2570
    },
    {
      "epoch": 2.336727766463001,
      "grad_norm": 0.5545589327812195,
      "learning_rate": 9.512758699107879e-05,
      "loss": 0.2716,
      "step": 2580
    },
    {
      "epoch": 2.3457795881421135,
      "grad_norm": 0.6256219744682312,
      "learning_rate": 9.449948704158071e-05,
      "loss": 0.2644,
      "step": 2590
    },
    {
      "epoch": 2.3548314098212266,
      "grad_norm": 0.5015664100646973,
      "learning_rate": 9.38716046778684e-05,
      "loss": 0.2603,
      "step": 2600
    },
    {
      "epoch": 2.3638832315003393,
      "grad_norm": 0.5921751260757446,
      "learning_rate": 9.324396473731217e-05,
      "loss": 0.2713,
      "step": 2610
    },
    {
      "epoch": 2.3729350531794524,
      "grad_norm": 0.4421112835407257,
      "learning_rate": 9.261659204769284e-05,
      "loss": 0.2663,
      "step": 2620
    },
    {
      "epoch": 2.3819868748585655,
      "grad_norm": 0.5723668336868286,
      "learning_rate": 9.198951142621929e-05,
      "loss": 0.2757,
      "step": 2630
    },
    {
      "epoch": 2.391038696537678,
      "grad_norm": 0.5875786542892456,
      "learning_rate": 9.136274767854716e-05,
      "loss": 0.2764,
      "step": 2640
    },
    {
      "epoch": 2.4000905182167913,
      "grad_norm": 0.6496031284332275,
      "learning_rate": 9.07363255977973e-05,
      "loss": 0.273,
      "step": 2650
    },
    {
      "epoch": 2.409142339895904,
      "grad_norm": 0.39376866817474365,
      "learning_rate": 9.011026996357503e-05,
      "loss": 0.23,
      "step": 2660
    },
    {
      "epoch": 2.418194161575017,
      "grad_norm": 0.6112829446792603,
      "learning_rate": 8.948460554099018e-05,
      "loss": 0.2605,
      "step": 2670
    },
    {
      "epoch": 2.4272459832541298,
      "grad_norm": 0.519059419631958,
      "learning_rate": 8.885935707967716e-05,
      "loss": 0.2501,
      "step": 2680
    },
    {
      "epoch": 2.436297804933243,
      "grad_norm": 0.8110079765319824,
      "learning_rate": 8.823454931281616e-05,
      "loss": 0.2387,
      "step": 2690
    },
    {
      "epoch": 2.4453496266123556,
      "grad_norm": 0.7474923133850098,
      "learning_rate": 8.76102069561545e-05,
      "loss": 0.2655,
      "step": 2700
    },
    {
      "epoch": 2.4544014482914687,
      "grad_norm": 0.44778284430503845,
      "learning_rate": 8.698635470702923e-05,
      "loss": 0.2285,
      "step": 2710
    },
    {
      "epoch": 2.4634532699705813,
      "grad_norm": 0.5677033066749573,
      "learning_rate": 8.636301724339004e-05,
      "loss": 0.2433,
      "step": 2720
    },
    {
      "epoch": 2.4725050916496945,
      "grad_norm": 0.5416902303695679,
      "learning_rate": 8.574021922282292e-05,
      "loss": 0.238,
      "step": 2730
    },
    {
      "epoch": 2.4815569133288076,
      "grad_norm": 0.5404213666915894,
      "learning_rate": 8.511798528157512e-05,
      "loss": 0.2682,
      "step": 2740
    },
    {
      "epoch": 2.4906087350079202,
      "grad_norm": 0.4115196168422699,
      "learning_rate": 8.449634003358022e-05,
      "loss": 0.2486,
      "step": 2750
    },
    {
      "epoch": 2.4996605566870334,
      "grad_norm": 0.40759924054145813,
      "learning_rate": 8.387530806948476e-05,
      "loss": 0.2381,
      "step": 2760
    },
    {
      "epoch": 2.508712378366146,
      "grad_norm": 0.5902087092399597,
      "learning_rate": 8.325491395567541e-05,
      "loss": 0.2364,
      "step": 2770
    },
    {
      "epoch": 2.517764200045259,
      "grad_norm": 0.5643983483314514,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.2322,
      "step": 2780
    },
    {
      "epoch": 2.526816021724372,
      "grad_norm": 0.55036860704422,
      "learning_rate": 8.201613741733203e-05,
      "loss": 0.2697,
      "step": 2790
    },
    {
      "epoch": 2.535867843403485,
      "grad_norm": 0.5846819877624512,
      "learning_rate": 8.13978039955308e-05,
      "loss": 0.2648,
      "step": 2800
    },
    {
      "epoch": 2.544919665082598,
      "grad_norm": 0.6239003539085388,
      "learning_rate": 8.078020642754274e-05,
      "loss": 0.244,
      "step": 2810
    },
    {
      "epoch": 2.5539714867617107,
      "grad_norm": 0.49254196882247925,
      "learning_rate": 8.016336914389874e-05,
      "loss": 0.2475,
      "step": 2820
    },
    {
      "epoch": 2.563023308440824,
      "grad_norm": 0.737869381904602,
      "learning_rate": 7.954731654505491e-05,
      "loss": 0.2694,
      "step": 2830
    },
    {
      "epoch": 2.5720751301199365,
      "grad_norm": 0.5183305144309998,
      "learning_rate": 7.89320730004274e-05,
      "loss": 0.234,
      "step": 2840
    },
    {
      "epoch": 2.5811269517990496,
      "grad_norm": 0.4777659773826599,
      "learning_rate": 7.831766284742807e-05,
      "loss": 0.2552,
      "step": 2850
    },
    {
      "epoch": 2.5901787734781623,
      "grad_norm": 0.553449809551239,
      "learning_rate": 7.77041103905023e-05,
      "loss": 0.2275,
      "step": 2860
    },
    {
      "epoch": 2.5992305951572754,
      "grad_norm": 0.542242169380188,
      "learning_rate": 7.709143990016702e-05,
      "loss": 0.2736,
      "step": 2870
    },
    {
      "epoch": 2.6082824168363885,
      "grad_norm": 0.564593493938446,
      "learning_rate": 7.6479675612051e-05,
      "loss": 0.2469,
      "step": 2880
    },
    {
      "epoch": 2.617334238515501,
      "grad_norm": 0.37938451766967773,
      "learning_rate": 7.586884172593609e-05,
      "loss": 0.2362,
      "step": 2890
    },
    {
      "epoch": 2.6263860601946143,
      "grad_norm": 0.6128523945808411,
      "learning_rate": 7.525896240479976e-05,
      "loss": 0.2456,
      "step": 2900
    },
    {
      "epoch": 2.635437881873727,
      "grad_norm": 0.6073201894760132,
      "learning_rate": 7.465006177385953e-05,
      "loss": 0.2413,
      "step": 2910
    },
    {
      "epoch": 2.64448970355284,
      "grad_norm": 0.4320588707923889,
      "learning_rate": 7.404216391961847e-05,
      "loss": 0.243,
      "step": 2920
    },
    {
      "epoch": 2.6535415252319527,
      "grad_norm": 0.40451350808143616,
      "learning_rate": 7.343529288891239e-05,
      "loss": 0.265,
      "step": 2930
    },
    {
      "epoch": 2.662593346911066,
      "grad_norm": 0.43473196029663086,
      "learning_rate": 7.282947268795877e-05,
      "loss": 0.2267,
      "step": 2940
    },
    {
      "epoch": 2.671645168590179,
      "grad_norm": 0.6388351917266846,
      "learning_rate": 7.222472728140695e-05,
      "loss": 0.2745,
      "step": 2950
    },
    {
      "epoch": 2.6806969902692916,
      "grad_norm": 0.5615083575248718,
      "learning_rate": 7.162108059139032e-05,
      "loss": 0.25,
      "step": 2960
    },
    {
      "epoch": 2.6897488119484048,
      "grad_norm": 0.6018364429473877,
      "learning_rate": 7.101855649657991e-05,
      "loss": 0.2601,
      "step": 2970
    },
    {
      "epoch": 2.6988006336275174,
      "grad_norm": 0.5931141376495361,
      "learning_rate": 7.041717883123977e-05,
      "loss": 0.2455,
      "step": 2980
    },
    {
      "epoch": 2.7078524553066305,
      "grad_norm": 0.4409467875957489,
      "learning_rate": 6.981697138428434e-05,
      "loss": 0.2584,
      "step": 2990
    },
    {
      "epoch": 2.716904276985743,
      "grad_norm": 0.6161777377128601,
      "learning_rate": 6.921795789833723e-05,
      "loss": 0.2364,
      "step": 3000
    },
    {
      "epoch": 2.716904276985743,
      "eval_loss": 11.997015953063965,
      "eval_runtime": 42.4537,
      "eval_samples_per_second": 7.467,
      "eval_steps_per_second": 3.745,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.6779958650393395e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}