{
  "best_global_step": 1168,
  "best_metric": 1.1582846641540527,
  "best_model_checkpoint": "Qwen3-8B-unsloth-bnb-4bit_finetuned_medical_mapstyle/checkpoint-1168",
  "epoch": 1.9974337040205303,
  "eval_steps": 292,
  "global_step": 1168,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00855431993156544,
      "grad_norm": 2.3634324073791504,
      "learning_rate": 3.4188034188034193e-06,
      "loss": 2.0621,
      "step": 5
    },
    {
      "epoch": 0.01710863986313088,
      "grad_norm": 2.057790756225586,
      "learning_rate": 7.692307692307694e-06,
      "loss": 2.1087,
      "step": 10
    },
    {
      "epoch": 0.02566295979469632,
      "grad_norm": 1.7136727571487427,
      "learning_rate": 1.1965811965811967e-05,
      "loss": 2.1024,
      "step": 15
    },
    {
      "epoch": 0.03421727972626176,
      "grad_norm": 1.32692551612854,
      "learning_rate": 1.623931623931624e-05,
      "loss": 1.9449,
      "step": 20
    },
    {
      "epoch": 0.0427715996578272,
      "grad_norm": 0.8120082020759583,
      "learning_rate": 2.0512820512820512e-05,
      "loss": 1.75,
      "step": 25
    },
    {
      "epoch": 0.05132591958939264,
      "grad_norm": 0.493346244096756,
      "learning_rate": 2.4786324786324787e-05,
      "loss": 1.579,
      "step": 30
    },
    {
      "epoch": 0.059880239520958084,
      "grad_norm": 0.49161383509635925,
      "learning_rate": 2.9059829059829063e-05,
      "loss": 1.4744,
      "step": 35
    },
    {
      "epoch": 0.06843455945252352,
      "grad_norm": 0.37959742546081543,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3668,
      "step": 40
    },
    {
      "epoch": 0.07698887938408897,
      "grad_norm": 0.3216921389102936,
      "learning_rate": 3.760683760683761e-05,
      "loss": 1.2879,
      "step": 45
    },
    {
      "epoch": 0.0855431993156544,
      "grad_norm": 0.2322167009115219,
      "learning_rate": 4.1880341880341886e-05,
      "loss": 1.2373,
      "step": 50
    },
    {
      "epoch": 0.09409751924721985,
      "grad_norm": 0.2078448086977005,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.3536,
      "step": 55
    },
    {
      "epoch": 0.10265183917878529,
      "grad_norm": 0.1465117633342743,
      "learning_rate": 5.042735042735043e-05,
      "loss": 1.3465,
      "step": 60
    },
    {
      "epoch": 0.11120615911035073,
      "grad_norm": 0.15991802513599396,
      "learning_rate": 5.470085470085471e-05,
      "loss": 1.3292,
      "step": 65
    },
    {
      "epoch": 0.11976047904191617,
      "grad_norm": 0.13813048601150513,
      "learning_rate": 5.897435897435898e-05,
      "loss": 1.287,
      "step": 70
    },
    {
      "epoch": 0.1283147989734816,
      "grad_norm": 0.14607124030590057,
      "learning_rate": 6.324786324786325e-05,
      "loss": 1.2481,
      "step": 75
    },
    {
      "epoch": 0.13686911890504705,
      "grad_norm": 0.13568255305290222,
      "learning_rate": 6.752136752136753e-05,
      "loss": 1.2021,
      "step": 80
    },
    {
      "epoch": 0.1454234388366125,
      "grad_norm": 0.1599941998720169,
      "learning_rate": 7.17948717948718e-05,
      "loss": 1.2376,
      "step": 85
    },
    {
      "epoch": 0.15397775876817793,
      "grad_norm": 0.15105901658535004,
      "learning_rate": 7.606837606837607e-05,
      "loss": 1.1937,
      "step": 90
    },
    {
      "epoch": 0.16253207869974337,
      "grad_norm": 0.1635543406009674,
      "learning_rate": 8.034188034188035e-05,
      "loss": 1.1519,
      "step": 95
    },
    {
      "epoch": 0.1710863986313088,
      "grad_norm": 0.22185680270195007,
      "learning_rate": 8.461538461538461e-05,
      "loss": 1.1406,
      "step": 100
    },
    {
      "epoch": 0.17964071856287425,
      "grad_norm": 0.16098278760910034,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.3133,
      "step": 105
    },
    {
      "epoch": 0.1881950384944397,
      "grad_norm": 0.15878444910049438,
      "learning_rate": 9.316239316239317e-05,
      "loss": 1.3012,
      "step": 110
    },
    {
      "epoch": 0.19674935842600513,
      "grad_norm": 0.16532596945762634,
      "learning_rate": 9.743589743589744e-05,
      "loss": 1.2724,
      "step": 115
    },
    {
      "epoch": 0.20530367835757057,
      "grad_norm": 0.16963312029838562,
      "learning_rate": 9.999910650316213e-05,
      "loss": 1.2249,
      "step": 120
    },
    {
      "epoch": 0.21385799828913601,
      "grad_norm": 0.17328128218650818,
      "learning_rate": 9.998905503046827e-05,
      "loss": 1.2253,
      "step": 125
    },
    {
      "epoch": 0.22241231822070145,
      "grad_norm": 0.17903530597686768,
      "learning_rate": 9.996783746672229e-05,
      "loss": 1.2293,
      "step": 130
    },
    {
      "epoch": 0.2309666381522669,
      "grad_norm": 0.18197666108608246,
      "learning_rate": 9.993545855130661e-05,
      "loss": 1.1867,
      "step": 135
    },
    {
      "epoch": 0.23952095808383234,
      "grad_norm": 0.21771149337291718,
      "learning_rate": 9.989192551672277e-05,
      "loss": 1.1775,
      "step": 140
    },
    {
      "epoch": 0.24807527801539778,
      "grad_norm": 0.22616538405418396,
      "learning_rate": 9.983724808697592e-05,
      "loss": 1.164,
      "step": 145
    },
    {
      "epoch": 0.2566295979469632,
      "grad_norm": 0.23522143065929413,
      "learning_rate": 9.97714384754027e-05,
      "loss": 1.1408,
      "step": 150
    },
    {
      "epoch": 0.26518391787852863,
      "grad_norm": 0.18039442598819733,
      "learning_rate": 9.969451138194326e-05,
      "loss": 1.2966,
      "step": 155
    },
    {
      "epoch": 0.2737382378100941,
      "grad_norm": 0.19237828254699707,
      "learning_rate": 9.960648398985759e-05,
      "loss": 1.2979,
      "step": 160
    },
    {
      "epoch": 0.2822925577416595,
      "grad_norm": 0.21537692844867706,
      "learning_rate": 9.950737596188732e-05,
      "loss": 1.2683,
      "step": 165
    },
    {
      "epoch": 0.290846877673225,
      "grad_norm": 0.18789014220237732,
      "learning_rate": 9.939720943586375e-05,
      "loss": 1.2195,
      "step": 170
    },
    {
      "epoch": 0.2994011976047904,
      "grad_norm": 0.17755815386772156,
      "learning_rate": 9.927600901976272e-05,
      "loss": 1.2267,
      "step": 175
    },
    {
      "epoch": 0.30795551753635586,
      "grad_norm": 0.20703640580177307,
      "learning_rate": 9.914380178620806e-05,
      "loss": 1.1912,
      "step": 180
    },
    {
      "epoch": 0.3165098374679213,
      "grad_norm": 0.19146886467933655,
      "learning_rate": 9.900061726642429e-05,
      "loss": 1.185,
      "step": 185
    },
    {
      "epoch": 0.32506415739948674,
      "grad_norm": 0.22206373512744904,
      "learning_rate": 9.884648744364022e-05,
      "loss": 1.1651,
      "step": 190
    },
    {
      "epoch": 0.33361847733105215,
      "grad_norm": 0.20517419278621674,
      "learning_rate": 9.868144674594483e-05,
      "loss": 1.1554,
      "step": 195
    },
    {
      "epoch": 0.3421727972626176,
      "grad_norm": 0.2678244709968567,
      "learning_rate": 9.850553203859706e-05,
      "loss": 1.1136,
      "step": 200
    },
    {
      "epoch": 0.35072711719418304,
      "grad_norm": 0.20938393473625183,
      "learning_rate": 9.831878261579121e-05,
      "loss": 1.2877,
      "step": 205
    },
    {
      "epoch": 0.3592814371257485,
      "grad_norm": 0.19213613867759705,
      "learning_rate": 9.812124019187967e-05,
      "loss": 1.2654,
      "step": 210
    },
    {
      "epoch": 0.3678357570573139,
      "grad_norm": 0.18827538192272186,
      "learning_rate": 9.791294889205527e-05,
      "loss": 1.2394,
      "step": 215
    },
    {
      "epoch": 0.3763900769888794,
      "grad_norm": 0.19291728734970093,
      "learning_rate": 9.769395524249496e-05,
      "loss": 1.2101,
      "step": 220
    },
    {
      "epoch": 0.3849443969204448,
      "grad_norm": 0.19408158957958221,
      "learning_rate": 9.746430815996716e-05,
      "loss": 1.1985,
      "step": 225
    },
    {
      "epoch": 0.39349871685201027,
      "grad_norm": 0.2589378356933594,
      "learning_rate": 9.722405894090535e-05,
      "loss": 1.2101,
      "step": 230
    },
    {
      "epoch": 0.4020530367835757,
      "grad_norm": 0.19482311606407166,
      "learning_rate": 9.697326124994978e-05,
      "loss": 1.1613,
      "step": 235
    },
    {
      "epoch": 0.41060735671514115,
      "grad_norm": 0.2171141356229782,
      "learning_rate": 9.671197110796042e-05,
      "loss": 1.1529,
      "step": 240
    },
    {
      "epoch": 0.41916167664670656,
      "grad_norm": 0.24028359353542328,
      "learning_rate": 9.644024687950358e-05,
      "loss": 1.157,
      "step": 245
    },
    {
      "epoch": 0.42771599657827203,
      "grad_norm": 0.2811010181903839,
      "learning_rate": 9.615814925981493e-05,
      "loss": 1.0873,
      "step": 250
    },
    {
      "epoch": 0.43627031650983744,
      "grad_norm": 0.2882992625236511,
      "learning_rate": 9.586574126124197e-05,
      "loss": 1.2634,
      "step": 255
    },
    {
      "epoch": 0.4448246364414029,
      "grad_norm": 0.3954780101776123,
      "learning_rate": 9.556308819916892e-05,
      "loss": 1.2588,
      "step": 260
    },
    {
      "epoch": 0.4533789563729683,
      "grad_norm": 0.2491636425256729,
      "learning_rate": 9.525025767742722e-05,
      "loss": 1.2261,
      "step": 265
    },
    {
      "epoch": 0.4619332763045338,
      "grad_norm": 0.255014032125473,
      "learning_rate": 9.492731957319467e-05,
      "loss": 1.2291,
      "step": 270
    },
    {
      "epoch": 0.4704875962360992,
      "grad_norm": 0.18478135764598846,
      "learning_rate": 9.459434602138714e-05,
      "loss": 1.1719,
      "step": 275
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 0.23741617798805237,
      "learning_rate": 9.425141139854554e-05,
      "loss": 1.1851,
      "step": 280
    },
    {
      "epoch": 0.4875962360992301,
      "grad_norm": 0.2247925102710724,
      "learning_rate": 9.389859230622238e-05,
      "loss": 1.1614,
      "step": 285
    },
    {
      "epoch": 0.49615055603079555,
      "grad_norm": 0.2277284860610962,
      "learning_rate": 9.353596755387117e-05,
      "loss": 1.1445,
      "step": 290
    },
    {
      "epoch": 0.49957228400342174,
      "eval_loss": 1.1889033317565918,
      "eval_runtime": 192.1886,
      "eval_samples_per_second": 5.203,
      "eval_steps_per_second": 1.301,
      "step": 292
    },
    {
      "epoch": 0.504704875962361,
      "grad_norm": 0.2321709543466568,
      "learning_rate": 9.316361814124278e-05,
      "loss": 1.1325,
      "step": 295
    },
    {
      "epoch": 0.5132591958939264,
      "grad_norm": 0.274766743183136,
      "learning_rate": 9.278162724029238e-05,
      "loss": 1.128,
      "step": 300
    },
    {
      "epoch": 0.5218135158254918,
      "grad_norm": 0.23025205731391907,
      "learning_rate": 9.239008017660133e-05,
      "loss": 1.2711,
      "step": 305
    },
    {
      "epoch": 0.5303678357570573,
      "grad_norm": 0.2014797478914261,
      "learning_rate": 9.198906441031788e-05,
      "loss": 1.2775,
      "step": 310
    },
    {
      "epoch": 0.5389221556886228,
      "grad_norm": 0.2136121690273285,
      "learning_rate": 9.157866951662118e-05,
      "loss": 1.225,
      "step": 315
    },
    {
      "epoch": 0.5474764756201882,
      "grad_norm": 0.21912986040115356,
      "learning_rate": 9.115898716571276e-05,
      "loss": 1.2103,
      "step": 320
    },
    {
      "epoch": 0.5560307955517536,
      "grad_norm": 0.21031109988689423,
      "learning_rate": 9.073011110234017e-05,
      "loss": 1.212,
      "step": 325
    },
    {
      "epoch": 0.564585115483319,
      "grad_norm": 0.2140427976846695,
      "learning_rate": 9.029213712485712e-05,
      "loss": 1.1759,
      "step": 330
    },
    {
      "epoch": 0.5731394354148845,
      "grad_norm": 0.23220868408679962,
      "learning_rate": 8.984516306382482e-05,
      "loss": 1.1584,
      "step": 335
    },
    {
      "epoch": 0.58169375534645,
      "grad_norm": 0.22398880124092102,
      "learning_rate": 8.93892887601597e-05,
      "loss": 1.1159,
      "step": 340
    },
    {
      "epoch": 0.5902480752780154,
      "grad_norm": 0.29221874475479126,
      "learning_rate": 8.892461604283169e-05,
      "loss": 1.1241,
      "step": 345
    },
    {
      "epoch": 0.5988023952095808,
      "grad_norm": 0.3614501357078552,
      "learning_rate": 8.845124870611874e-05,
      "loss": 1.104,
      "step": 350
    },
    {
      "epoch": 0.6073567151411463,
      "grad_norm": 0.1925259232521057,
      "learning_rate": 8.796929248642214e-05,
      "loss": 1.2781,
      "step": 355
    },
    {
      "epoch": 0.6159110350727117,
      "grad_norm": 0.20865660905838013,
      "learning_rate": 8.74788550386481e-05,
      "loss": 1.2619,
      "step": 360
    },
    {
      "epoch": 0.6244653550042771,
      "grad_norm": 0.23581738770008087,
      "learning_rate": 8.698004591216088e-05,
      "loss": 1.2193,
      "step": 365
    },
    {
      "epoch": 0.6330196749358425,
      "grad_norm": 0.208170086145401,
      "learning_rate": 8.64729765263126e-05,
      "loss": 1.1925,
      "step": 370
    },
    {
      "epoch": 0.6415739948674081,
      "grad_norm": 0.2543809711933136,
      "learning_rate": 8.595776014555539e-05,
      "loss": 1.2114,
      "step": 375
    },
    {
      "epoch": 0.6501283147989735,
      "grad_norm": 0.3356539011001587,
      "learning_rate": 8.543451185414152e-05,
      "loss": 1.1841,
      "step": 380
    },
    {
      "epoch": 0.6586826347305389,
      "grad_norm": 0.273034006357193,
      "learning_rate": 8.490334853041689e-05,
      "loss": 1.1722,
      "step": 385
    },
    {
      "epoch": 0.6672369546621043,
      "grad_norm": 0.25472286343574524,
      "learning_rate": 8.43643888207138e-05,
      "loss": 1.1621,
      "step": 390
    },
    {
      "epoch": 0.6757912745936698,
      "grad_norm": 0.21943122148513794,
      "learning_rate": 8.381775311284897e-05,
      "loss": 1.1438,
      "step": 395
    },
    {
      "epoch": 0.6843455945252352,
      "grad_norm": 0.2602487802505493,
      "learning_rate": 8.326356350923222e-05,
      "loss": 1.1009,
      "step": 400
    },
    {
      "epoch": 0.6928999144568007,
      "grad_norm": 0.2104780375957489,
      "learning_rate": 8.270194379959255e-05,
      "loss": 1.2812,
      "step": 405
    },
    {
      "epoch": 0.7014542343883661,
      "grad_norm": 0.24049486219882965,
      "learning_rate": 8.213301943332703e-05,
      "loss": 1.2647,
      "step": 410
    },
    {
      "epoch": 0.7100085543199316,
      "grad_norm": 0.1914437711238861,
      "learning_rate": 8.155691749147917e-05,
      "loss": 1.2009,
      "step": 415
    },
    {
      "epoch": 0.718562874251497,
      "grad_norm": 0.22749020159244537,
      "learning_rate": 8.097376665835259e-05,
      "loss": 1.2208,
      "step": 420
    },
    {
      "epoch": 0.7271171941830624,
      "grad_norm": 0.20557495951652527,
      "learning_rate": 8.038369719276692e-05,
      "loss": 1.1636,
      "step": 425
    },
    {
      "epoch": 0.7356715141146278,
      "grad_norm": 0.22836126387119293,
      "learning_rate": 7.978684089896159e-05,
      "loss": 1.1824,
      "step": 430
    },
    {
      "epoch": 0.7442258340461934,
      "grad_norm": 0.22939206659793854,
      "learning_rate": 7.918333109715474e-05,
      "loss": 1.1433,
      "step": 435
    },
    {
      "epoch": 0.7527801539777588,
      "grad_norm": 0.2617824971675873,
      "learning_rate": 7.857330259376341e-05,
      "loss": 1.127,
      "step": 440
    },
    {
      "epoch": 0.7613344739093242,
      "grad_norm": 0.3292466998100281,
      "learning_rate": 7.79568916512916e-05,
      "loss": 1.1228,
      "step": 445
    },
    {
      "epoch": 0.7698887938408896,
      "grad_norm": 0.2562960982322693,
      "learning_rate": 7.733423595789336e-05,
      "loss": 1.0933,
      "step": 450
    },
    {
      "epoch": 0.7784431137724551,
      "grad_norm": 0.22247634828090668,
      "learning_rate": 7.670547459661723e-05,
      "loss": 1.2606,
      "step": 455
    },
    {
      "epoch": 0.7869974337040205,
      "grad_norm": 0.22019144892692566,
      "learning_rate": 7.607074801433913e-05,
      "loss": 1.2446,
      "step": 460
    },
    {
      "epoch": 0.795551753635586,
      "grad_norm": 0.21663713455200195,
      "learning_rate": 7.54301979903907e-05,
      "loss": 1.2135,
      "step": 465
    },
    {
      "epoch": 0.8041060735671514,
      "grad_norm": 0.20642994344234467,
      "learning_rate": 7.478396760488992e-05,
      "loss": 1.1937,
      "step": 470
    },
    {
      "epoch": 0.8126603934987169,
      "grad_norm": 0.19477106630802155,
      "learning_rate": 7.413220120678115e-05,
      "loss": 1.1723,
      "step": 475
    },
    {
      "epoch": 0.8212147134302823,
      "grad_norm": 0.21169719099998474,
      "learning_rate": 7.347504438159193e-05,
      "loss": 1.1659,
      "step": 480
    },
    {
      "epoch": 0.8297690333618477,
      "grad_norm": 0.22446298599243164,
      "learning_rate": 7.28126439189133e-05,
      "loss": 1.1545,
      "step": 485
    },
    {
      "epoch": 0.8383233532934131,
      "grad_norm": 0.23756328225135803,
      "learning_rate": 7.214514777961139e-05,
      "loss": 1.1135,
      "step": 490
    },
    {
      "epoch": 0.8468776732249786,
      "grad_norm": 0.24515803158283234,
      "learning_rate": 7.14727050627773e-05,
      "loss": 1.1061,
      "step": 495
    },
    {
      "epoch": 0.8554319931565441,
      "grad_norm": 0.2634405791759491,
      "learning_rate": 7.079546597242261e-05,
      "loss": 1.0805,
      "step": 500
    },
    {
      "epoch": 0.8639863130881095,
      "grad_norm": 0.21282422542572021,
      "learning_rate": 7.01135817839284e-05,
      "loss": 1.2815,
      "step": 505
    },
    {
      "epoch": 0.8725406330196749,
      "grad_norm": 0.21851497888565063,
      "learning_rate": 6.942720481025457e-05,
      "loss": 1.2458,
      "step": 510
    },
    {
      "epoch": 0.8810949529512404,
      "grad_norm": 0.23128564655780792,
      "learning_rate": 6.873648836791772e-05,
      "loss": 1.2239,
      "step": 515
    },
    {
      "epoch": 0.8896492728828058,
      "grad_norm": 0.19994930922985077,
      "learning_rate": 6.804158674274461e-05,
      "loss": 1.2049,
      "step": 520
    },
    {
      "epoch": 0.8982035928143712,
      "grad_norm": 0.22093206644058228,
      "learning_rate": 6.734265515540937e-05,
      "loss": 1.1778,
      "step": 525
    },
    {
      "epoch": 0.9067579127459366,
      "grad_norm": 0.2265535593032837,
      "learning_rate": 6.66398497267616e-05,
      "loss": 1.1414,
      "step": 530
    },
    {
      "epoch": 0.9153122326775022,
      "grad_norm": 0.28239762783050537,
      "learning_rate": 6.593332744295365e-05,
      "loss": 1.1787,
      "step": 535
    },
    {
      "epoch": 0.9238665526090676,
      "grad_norm": 0.20534726977348328,
      "learning_rate": 6.522324612037444e-05,
      "loss": 1.1357,
      "step": 540
    },
    {
      "epoch": 0.932420872540633,
      "grad_norm": 0.24073491990566254,
      "learning_rate": 6.450976437039799e-05,
      "loss": 1.0985,
      "step": 545
    },
    {
      "epoch": 0.9409751924721984,
      "grad_norm": 0.2902477979660034,
      "learning_rate": 6.379304156395416e-05,
      "loss": 1.1017,
      "step": 550
    },
    {
      "epoch": 0.9495295124037639,
      "grad_norm": 0.21347130835056305,
      "learning_rate": 6.307323779592993e-05,
      "loss": 1.2609,
      "step": 555
    },
    {
      "epoch": 0.9580838323353293,
      "grad_norm": 0.241712749004364,
      "learning_rate": 6.235051384940889e-05,
      "loss": 1.2557,
      "step": 560
    },
    {
      "epoch": 0.9666381522668948,
      "grad_norm": 0.21896786987781525,
      "learning_rate": 6.1625031159757e-05,
      "loss": 1.1797,
      "step": 565
    },
    {
      "epoch": 0.9751924721984602,
      "grad_norm": 0.20597045123577118,
      "learning_rate": 6.089695177856266e-05,
      "loss": 1.1877,
      "step": 570
    },
    {
      "epoch": 0.9837467921300257,
      "grad_norm": 0.2092043161392212,
      "learning_rate": 6.016643833743908e-05,
      "loss": 1.1504,
      "step": 575
    },
    {
      "epoch": 0.9923011120615911,
      "grad_norm": 0.2444092333316803,
      "learning_rate": 5.943365401169721e-05,
      "loss": 1.1217,
      "step": 580
    },
    {
      "epoch": 0.9991445680068435,
      "eval_loss": 1.1706105470657349,
      "eval_runtime": 190.4588,
      "eval_samples_per_second": 5.25,
      "eval_steps_per_second": 1.313,
      "step": 584
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3430745005607605,
      "learning_rate": 5.8698762483897106e-05,
      "loss": 1.0825,
      "step": 585
    },
    {
      "epoch": 1.0085543199315654,
      "grad_norm": 0.19922564923763275,
      "learning_rate": 5.7961927907286086e-05,
      "loss": 1.252,
      "step": 590
    },
    {
      "epoch": 1.0171086398631308,
      "grad_norm": 0.20606961846351624,
      "learning_rate": 5.722331486913165e-05,
      "loss": 1.2305,
      "step": 595
    },
    {
      "epoch": 1.0256629597946962,
      "grad_norm": 0.21762171387672424,
      "learning_rate": 5.648308835395755e-05,
      "loss": 1.2149,
      "step": 600
    },
    {
      "epoch": 1.0342172797262617,
      "grad_norm": 0.28299635648727417,
      "learning_rate": 5.5741413706691016e-05,
      "loss": 1.171,
      "step": 605
    },
    {
      "epoch": 1.0427715996578273,
      "grad_norm": 0.2637864053249359,
      "learning_rate": 5.499845659572964e-05,
      "loss": 1.1643,
      "step": 610
    },
    {
      "epoch": 1.0513259195893927,
      "grad_norm": 0.22751151025295258,
      "learning_rate": 5.4254382975935794e-05,
      "loss": 1.1202,
      "step": 615
    },
    {
      "epoch": 1.0598802395209581,
      "grad_norm": 0.23186901211738586,
      "learning_rate": 5.3509359051567265e-05,
      "loss": 1.1183,
      "step": 620
    },
    {
      "epoch": 1.0684345594525235,
      "grad_norm": 0.24297842383384705,
      "learning_rate": 5.276355123915203e-05,
      "loss": 1.1011,
      "step": 625
    },
    {
      "epoch": 1.076988879384089,
      "grad_norm": 0.23210163414478302,
      "learning_rate": 5.20171261303157e-05,
      "loss": 1.0862,
      "step": 630
    },
    {
      "epoch": 1.0855431993156544,
      "grad_norm": 0.30550700426101685,
      "learning_rate": 5.127025045456986e-05,
      "loss": 1.064,
      "step": 635
    },
    {
      "epoch": 1.0940975192472198,
      "grad_norm": 0.2281382530927658,
      "learning_rate": 5.0523091042069524e-05,
      "loss": 1.2419,
      "step": 640
    },
    {
      "epoch": 1.1026518391787854,
      "grad_norm": 0.21404342353343964,
      "learning_rate": 4.977581478634819e-05,
      "loss": 1.2199,
      "step": 645
    },
    {
      "epoch": 1.1112061591103508,
      "grad_norm": 0.22572125494480133,
      "learning_rate": 4.9028588607038726e-05,
      "loss": 1.1809,
      "step": 650
    },
    {
      "epoch": 1.1197604790419162,
      "grad_norm": 0.2776021957397461,
      "learning_rate": 4.8281579412588364e-05,
      "loss": 1.135,
      "step": 655
    },
    {
      "epoch": 1.1283147989734816,
      "grad_norm": 0.21900996565818787,
      "learning_rate": 4.753495406297629e-05,
      "loss": 1.1607,
      "step": 660
    },
    {
      "epoch": 1.136869118905047,
      "grad_norm": 0.23510439693927765,
      "learning_rate": 4.678887933244202e-05,
      "loss": 1.1501,
      "step": 665
    },
    {
      "epoch": 1.1454234388366125,
      "grad_norm": 0.22436121106147766,
      "learning_rate": 4.604352187223286e-05,
      "loss": 1.1121,
      "step": 670
    },
    {
      "epoch": 1.1539777587681779,
      "grad_norm": 0.24691715836524963,
      "learning_rate": 4.529904817337892e-05,
      "loss": 1.0906,
      "step": 675
    },
    {
      "epoch": 1.1625320786997433,
      "grad_norm": 0.2613847255706787,
      "learning_rate": 4.4555624529503934e-05,
      "loss": 1.0549,
      "step": 680
    },
    {
      "epoch": 1.1710863986313087,
      "grad_norm": 0.2739933133125305,
      "learning_rate": 4.381341699968008e-05,
      "loss": 1.0665,
      "step": 685
    },
    {
      "epoch": 1.1796407185628743,
      "grad_norm": 0.2270067036151886,
      "learning_rate": 4.307259137133528e-05,
      "loss": 1.2362,
      "step": 690
    },
    {
      "epoch": 1.1881950384944397,
      "grad_norm": 0.30066943168640137,
      "learning_rate": 4.233331312322113e-05,
      "loss": 1.2064,
      "step": 695
    },
    {
      "epoch": 1.1967493584260052,
      "grad_norm": 0.23708266019821167,
      "learning_rate": 4.159574738844979e-05,
      "loss": 1.184,
      "step": 700
    },
    {
      "epoch": 1.2053036783575706,
      "grad_norm": 0.22325414419174194,
      "learning_rate": 4.0860058917608095e-05,
      "loss": 1.1619,
      "step": 705
    },
    {
      "epoch": 1.213857998289136,
      "grad_norm": 0.24410483241081238,
      "learning_rate": 4.012641204195708e-05,
      "loss": 1.1427,
      "step": 710
    },
    {
      "epoch": 1.2224123182207014,
      "grad_norm": 0.22428686916828156,
      "learning_rate": 3.939497063672519e-05,
      "loss": 1.1399,
      "step": 715
    },
    {
      "epoch": 1.2309666381522668,
      "grad_norm": 0.2708205282688141,
      "learning_rate": 3.866589808450342e-05,
      "loss": 1.1341,
      "step": 720
    },
    {
      "epoch": 1.2395209580838324,
      "grad_norm": 0.24272146821022034,
      "learning_rate": 3.79393572387503e-05,
      "loss": 1.0842,
      "step": 725
    },
    {
      "epoch": 1.2480752780153979,
      "grad_norm": 0.2813037931919098,
      "learning_rate": 3.72155103874153e-05,
      "loss": 1.0968,
      "step": 730
    },
    {
      "epoch": 1.2566295979469633,
      "grad_norm": 0.2863466739654541,
      "learning_rate": 3.649451921668843e-05,
      "loss": 1.0313,
      "step": 735
    },
    {
      "epoch": 1.2651839178785287,
      "grad_norm": 0.24261562526226044,
      "learning_rate": 3.5776544774884266e-05,
      "loss": 1.2495,
      "step": 740
    },
    {
      "epoch": 1.273738237810094,
      "grad_norm": 0.25371140241622925,
      "learning_rate": 3.506174743646849e-05,
      "loss": 1.2206,
      "step": 745
    },
    {
      "epoch": 1.2822925577416595,
      "grad_norm": 0.24523141980171204,
      "learning_rate": 3.43502868662349e-05,
      "loss": 1.1952,
      "step": 750
    },
    {
      "epoch": 1.290846877673225,
      "grad_norm": 0.23609282076358795,
      "learning_rate": 3.364232198364104e-05,
      "loss": 1.1366,
      "step": 755
    },
    {
      "epoch": 1.2994011976047903,
      "grad_norm": 0.25029298663139343,
      "learning_rate": 3.2938010927310145e-05,
      "loss": 1.1433,
      "step": 760
    },
    {
      "epoch": 1.3079555175363557,
      "grad_norm": 0.24611520767211914,
      "learning_rate": 3.223751101970772e-05,
      "loss": 1.1139,
      "step": 765
    },
    {
      "epoch": 1.3165098374679212,
      "grad_norm": 0.32934480905532837,
      "learning_rate": 3.1540978732000196e-05,
      "loss": 1.1378,
      "step": 770
    },
    {
      "epoch": 1.3250641573994868,
      "grad_norm": 0.24652425944805145,
      "learning_rate": 3.084856964910393e-05,
      "loss": 1.0827,
      "step": 775
    },
    {
      "epoch": 1.3336184773310522,
      "grad_norm": 0.3137495517730713,
      "learning_rate": 3.016043843493205e-05,
      "loss": 1.07,
      "step": 780
    },
    {
      "epoch": 1.3421727972626176,
      "grad_norm": 0.28230196237564087,
      "learning_rate": 2.9476738797847058e-05,
      "loss": 1.0495,
      "step": 785
    },
    {
      "epoch": 1.350727117194183,
      "grad_norm": 0.23223777115345,
      "learning_rate": 2.8797623456326993e-05,
      "loss": 1.2002,
      "step": 790
    },
    {
      "epoch": 1.3592814371257484,
      "grad_norm": 0.2546311914920807,
      "learning_rate": 2.8123244104852436e-05,
      "loss": 1.2424,
      "step": 795
    },
    {
      "epoch": 1.3678357570573139,
      "grad_norm": 0.2551040053367615,
      "learning_rate": 2.7453751380022457e-05,
      "loss": 1.1713,
      "step": 800
    },
    {
      "epoch": 1.3763900769888795,
      "grad_norm": 0.2640606164932251,
      "learning_rate": 2.6789294826906907e-05,
      "loss": 1.1402,
      "step": 805
    },
    {
      "epoch": 1.384944396920445,
      "grad_norm": 0.24174994230270386,
      "learning_rate": 2.6130022865642274e-05,
      "loss": 1.1297,
      "step": 810
    },
    {
      "epoch": 1.3934987168520103,
      "grad_norm": 0.23402699828147888,
      "learning_rate": 2.5476082758279113e-05,
      "loss": 1.133,
      "step": 815
    },
    {
      "epoch": 1.4020530367835757,
      "grad_norm": 0.24528896808624268,
      "learning_rate": 2.482762057588789e-05,
      "loss": 1.1109,
      "step": 820
    },
    {
      "epoch": 1.4106073567151411,
      "grad_norm": 0.24158333241939545,
      "learning_rate": 2.4184781165931085e-05,
      "loss": 1.0928,
      "step": 825
    },
    {
      "epoch": 1.4191616766467066,
      "grad_norm": 0.2835128605365753,
      "learning_rate": 2.3547708119908485e-05,
      "loss": 1.0913,
      "step": 830
    },
    {
      "epoch": 1.427715996578272,
      "grad_norm": 0.2725597620010376,
      "learning_rate": 2.291654374128297e-05,
      "loss": 1.0371,
      "step": 835
    },
    {
      "epoch": 1.4362703165098374,
      "grad_norm": 0.2303570806980133,
      "learning_rate": 2.229142901369422e-05,
      "loss": 1.2126,
      "step": 840
    },
    {
      "epoch": 1.4448246364414028,
      "grad_norm": 0.22464948892593384,
      "learning_rate": 2.1672503569466957e-05,
      "loss": 1.1971,
      "step": 845
    },
    {
      "epoch": 1.4533789563729682,
      "grad_norm": 0.24435533583164215,
      "learning_rate": 2.1059905658421307e-05,
      "loss": 1.1811,
      "step": 850
    },
    {
      "epoch": 1.4619332763045338,
      "grad_norm": 0.25154009461402893,
      "learning_rate": 2.0453772116991693e-05,
      "loss": 1.1657,
      "step": 855
    },
    {
      "epoch": 1.4704875962360993,
      "grad_norm": 0.24405178427696228,
      "learning_rate": 1.9854238337661784e-05,
      "loss": 1.1521,
      "step": 860
    },
    {
      "epoch": 1.4790419161676647,
      "grad_norm": 0.2422427237033844,
      "learning_rate": 1.926143823872154e-05,
      "loss": 1.1081,
      "step": 865
    },
    {
      "epoch": 1.48759623609923,
      "grad_norm": 0.23662738502025604,
      "learning_rate": 1.8675504234353984e-05,
      "loss": 1.1141,
      "step": 870
    },
    {
      "epoch": 1.4961505560307955,
      "grad_norm": 0.2576230764389038,
      "learning_rate": 1.8096567205057612e-05,
      "loss": 1.0908,
      "step": 875
    },
    {
      "epoch": 1.4978614200171085,
      "eval_loss": 1.1608092784881592,
      "eval_runtime": 189.6105,
      "eval_samples_per_second": 5.274,
      "eval_steps_per_second": 1.318,
      "step": 876
    },
    {
      "epoch": 1.5047048759623611,
      "grad_norm": 0.28986838459968567,
      "learning_rate": 1.752475646841165e-05,
      "loss": 1.0793,
      "step": 880
    },
    {
      "epoch": 1.5132591958939265,
      "grad_norm": 0.292716920375824,
      "learning_rate": 1.6960199750190154e-05,
      "loss": 1.0567,
      "step": 885
    },
    {
      "epoch": 1.521813515825492,
      "grad_norm": 0.24130800366401672,
      "learning_rate": 1.640302315583196e-05,
      "loss": 1.1978,
      "step": 890
    },
    {
      "epoch": 1.5303678357570574,
      "grad_norm": 0.28526702523231506,
      "learning_rate": 1.585335114227227e-05,
      "loss": 1.2527,
      "step": 895
    },
    {
      "epoch": 1.5389221556886228,
      "grad_norm": 0.23622915148735046,
      "learning_rate": 1.5311306490142774e-05,
      "loss": 1.1817,
      "step": 900
    },
    {
      "epoch": 1.5474764756201882,
      "grad_norm": 0.23062996566295624,
      "learning_rate": 1.4777010276345898e-05,
      "loss": 1.1778,
      "step": 905
    },
    {
      "epoch": 1.5560307955517536,
      "grad_norm": 0.26330140233039856,
      "learning_rate": 1.4250581847009903e-05,
      "loss": 1.1525,
      "step": 910
    },
    {
      "epoch": 1.564585115483319,
      "grad_norm": 0.2737792134284973,
      "learning_rate": 1.3732138790830352e-05,
      "loss": 1.1545,
      "step": 915
    },
    {
      "epoch": 1.5731394354148844,
      "grad_norm": 0.2453244924545288,
      "learning_rate": 1.3221796912804302e-05,
      "loss": 1.1046,
      "step": 920
    },
    {
      "epoch": 1.5816937553464498,
      "grad_norm": 0.2568381130695343,
      "learning_rate": 1.271967020836285e-05,
      "loss": 1.0973,
      "step": 925
    },
    {
      "epoch": 1.5902480752780153,
      "grad_norm": 0.2878681719303131,
      "learning_rate": 1.2225870837907877e-05,
      "loss": 1.0767,
      "step": 930
    },
    {
      "epoch": 1.5988023952095807,
      "grad_norm": 0.3123931884765625,
      "learning_rate": 1.1740509101758673e-05,
      "loss": 1.0589,
      "step": 935
    },
    {
      "epoch": 1.6073567151411463,
      "grad_norm": 0.26882365345954895,
      "learning_rate": 1.1263693415514148e-05,
      "loss": 1.2636,
      "step": 940
    },
    {
      "epoch": 1.6159110350727117,
      "grad_norm": 0.2722887396812439,
      "learning_rate": 1.0795530285835882e-05,
      "loss": 1.1943,
      "step": 945
    },
    {
      "epoch": 1.6244653550042771,
      "grad_norm": 0.24011342227458954,
      "learning_rate": 1.0336124286657711e-05,
      "loss": 1.1886,
      "step": 950
    },
    {
      "epoch": 1.6330196749358425,
      "grad_norm": 0.23855996131896973,
      "learning_rate": 9.885578035826975e-06,
      "loss": 1.1636,
      "step": 955
    },
    {
      "epoch": 1.6415739948674082,
      "grad_norm": 0.23547948896884918,
      "learning_rate": 9.443992172182626e-06,
      "loss": 1.1384,
      "step": 960
    },
    {
      "epoch": 1.6501283147989736,
      "grad_norm": 0.2509356737136841,
      "learning_rate": 9.011465333075563e-06,
      "loss": 1.13,
      "step": 965
    },
    {
      "epoch": 1.658682634730539,
      "grad_norm": 0.2562836706638336,
      "learning_rate": 8.588094132335829e-06,
      "loss": 1.1054,
      "step": 970
    },
    {
      "epoch": 1.6672369546621044,
      "grad_norm": 0.2574482858181,
      "learning_rate": 8.173973138692004e-06,
      "loss": 1.0987,
      "step": 975
    },
    {
      "epoch": 1.6757912745936698,
      "grad_norm": 0.2583164870738983,
      "learning_rate": 7.769194854647244e-06,
      "loss": 1.0681,
      "step": 980
    },
    {
      "epoch": 1.6843455945252352,
      "grad_norm": 0.2973106801509857,
      "learning_rate": 7.373849695817009e-06,
      "loss": 1.0497,
      "step": 985
    },
    {
      "epoch": 1.6928999144568007,
      "grad_norm": 0.2410203218460083,
      "learning_rate": 6.988025970732765e-06,
      "loss": 1.2327,
      "step": 990
    },
    {
      "epoch": 1.701454234388366,
      "grad_norm": 0.24606889486312866,
      "learning_rate": 6.611809861116542e-06,
      "loss": 1.196,
      "step": 995
    },
    {
      "epoch": 1.7100085543199315,
      "grad_norm": 0.26388075947761536,
      "learning_rate": 6.245285402630396e-06,
      "loss": 1.1937,
      "step": 1000
    },
    {
      "epoch": 1.718562874251497,
      "grad_norm": 0.22676678001880646,
      "learning_rate": 5.8885344661053446e-06,
      "loss": 1.1763,
      "step": 1005
    },
    {
      "epoch": 1.7271171941830623,
      "grad_norm": 0.25647327303886414,
      "learning_rate": 5.541636739253752e-06,
      "loss": 1.153,
      "step": 1010
    },
    {
      "epoch": 1.7356715141146277,
      "grad_norm": 0.25334250926971436,
      "learning_rate": 5.204669708869536e-06,
      "loss": 1.1261,
      "step": 1015
    },
    {
      "epoch": 1.7442258340461934,
      "grad_norm": 0.2743702530860901,
      "learning_rate": 4.877708643519768e-06,
      "loss": 1.1123,
      "step": 1020
    },
    {
      "epoch": 1.7527801539777588,
      "grad_norm": 0.2641868591308594,
      "learning_rate": 4.560826576731997e-06,
      "loss": 1.075,
      "step": 1025
    },
    {
      "epoch": 1.7613344739093242,
      "grad_norm": 0.2730740010738373,
      "learning_rate": 4.254094290680577e-06,
      "loss": 1.0724,
      "step": 1030
    },
    {
      "epoch": 1.7698887938408896,
      "grad_norm": 0.3020741939544678,
      "learning_rate": 3.957580300376123e-06,
      "loss": 1.0445,
      "step": 1035
    },
    {
      "epoch": 1.7784431137724552,
      "grad_norm": 0.25013259053230286,
      "learning_rate": 3.6713508383611595e-06,
      "loss": 1.2081,
      "step": 1040
    },
    {
      "epoch": 1.7869974337040206,
      "grad_norm": 0.25935712456703186,
      "learning_rate": 3.3954698399157768e-06,
      "loss": 1.1968,
      "step": 1045
    },
    {
      "epoch": 1.795551753635586,
      "grad_norm": 0.2230421006679535,
      "learning_rate": 3.129998928776351e-06,
      "loss": 1.1921,
      "step": 1050
    },
    {
      "epoch": 1.8041060735671515,
      "grad_norm": 0.24666619300842285,
      "learning_rate": 2.874997403370561e-06,
      "loss": 1.1476,
      "step": 1055
    },
    {
      "epoch": 1.8126603934987169,
      "grad_norm": 0.24178998172283173,
      "learning_rate": 2.6305222235719297e-06,
      "loss": 1.1371,
      "step": 1060
    },
    {
      "epoch": 1.8212147134302823,
      "grad_norm": 0.2649187743663788,
      "learning_rate": 2.396627997976575e-06,
      "loss": 1.1008,
      "step": 1065
    },
    {
      "epoch": 1.8297690333618477,
      "grad_norm": 0.26780879497528076,
      "learning_rate": 2.173366971705332e-06,
      "loss": 1.1003,
      "step": 1070
    },
    {
      "epoch": 1.8383233532934131,
      "grad_norm": 0.24656632542610168,
      "learning_rate": 1.9607890147336607e-06,
      "loss": 1.1072,
      "step": 1075
    },
    {
      "epoch": 1.8468776732249785,
      "grad_norm": 0.29173144698143005,
      "learning_rate": 1.758941610752174e-06,
      "loss": 1.0682,
      "step": 1080
    },
    {
      "epoch": 1.855431993156544,
      "grad_norm": 0.327525794506073,
      "learning_rate": 1.567869846560166e-06,
      "loss": 1.0637,
      "step": 1085
    },
    {
      "epoch": 1.8639863130881094,
      "grad_norm": 0.21384185552597046,
      "learning_rate": 1.3876164019945738e-06,
      "loss": 1.1821,
      "step": 1090
    },
    {
      "epoch": 1.8725406330196748,
      "grad_norm": 0.22071972489356995,
      "learning_rate": 1.2182215403964913e-06,
      "loss": 1.2146,
      "step": 1095
    },
    {
      "epoch": 1.8810949529512404,
      "grad_norm": 0.23191356658935547,
      "learning_rate": 1.0597230996175766e-06,
      "loss": 1.1783,
      "step": 1100
    },
    {
      "epoch": 1.8896492728828058,
      "grad_norm": 0.248655304312706,
      "learning_rate": 9.121564835681495e-07,
      "loss": 1.1655,
      "step": 1105
    },
    {
      "epoch": 1.8982035928143712,
      "grad_norm": 0.24524256587028503,
      "learning_rate": 7.755546543090075e-07,
      "loss": 1.1382,
      "step": 1110
    },
    {
      "epoch": 1.9067579127459366,
      "grad_norm": 0.2414981871843338,
      "learning_rate": 6.499481246886596e-07,
      "loss": 1.1333,
      "step": 1115
    },
    {
      "epoch": 1.9153122326775023,
      "grad_norm": 0.24824100732803345,
      "learning_rate": 5.35364951527656e-07,
      "loss": 1.1198,
      "step": 1120
    },
    {
      "epoch": 1.9238665526090677,
      "grad_norm": 0.2868870496749878,
      "learning_rate": 4.318307293515178e-07,
      "loss": 1.0729,
      "step": 1125
    },
    {
      "epoch": 1.932420872540633,
      "grad_norm": 0.2726382315158844,
      "learning_rate": 3.393685846736605e-07,
      "loss": 1.0657,
      "step": 1130
    },
    {
      "epoch": 1.9409751924721985,
      "grad_norm": 0.33020347356796265,
      "learning_rate": 2.5799917082960923e-07,
      "loss": 1.0507,
      "step": 1135
    },
    {
      "epoch": 1.949529512403764,
      "grad_norm": 0.22383831441402435,
      "learning_rate": 1.8774066336366135e-07,
      "loss": 1.2295,
      "step": 1140
    },
    {
      "epoch": 1.9580838323353293,
      "grad_norm": 0.23759938776493073,
      "learning_rate": 1.2860875596898414e-07,
      "loss": 1.1844,
      "step": 1145
    },
    {
      "epoch": 1.9666381522668948,
      "grad_norm": 0.2552230954170227,
      "learning_rate": 8.061665698212428e-08,
      "loss": 1.1668,
      "step": 1150
    },
    {
      "epoch": 1.9751924721984602,
      "grad_norm": 0.23491644859313965,
      "learning_rate": 4.3775086432618075e-08,
      "loss": 1.1328,
      "step": 1155
    },
    {
      "epoch": 1.9837467921300256,
      "grad_norm": 0.2515895962715149,
      "learning_rate": 1.809227364849564e-08,
      "loss": 1.1119,
      "step": 1160
    },
    {
      "epoch": 1.992301112061591,
      "grad_norm": 0.25821658968925476,
      "learning_rate": 3.5739554180458377e-09,
      "loss": 1.072,
      "step": 1165
    },
    {
      "epoch": 1.9974337040205303,
      "eval_loss": 1.1582846641540527,
      "eval_runtime": 190.4614,
      "eval_samples_per_second": 5.25,
      "eval_steps_per_second": 1.313,
      "step": 1168
    },
    {
      "epoch": 1.9974337040205303,
      "step": 1168,
      "total_flos": 1.2135428930398618e+18,
      "train_loss": 1.1893549063434339,
      "train_runtime": 21354.1307,
      "train_samples_per_second": 1.752,
      "train_steps_per_second": 0.055
    }
  ],
  "logging_steps": 5,
  "max_steps": 1168,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 292,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2135428930398618e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}