{
  "best_metric": 0.951232302045097,
  "best_model_checkpoint": "/home/avramit/classifier/04122025/classifier/binary/neodictabert-finetuned-binary-041225/checkpoint-1000",
  "epoch": 0.9992323719706108,
  "eval_steps": 500,
  "global_step": 1139,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008772891764447855,
      "grad_norm": 18.548049926757812,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.712,
      "step": 10
    },
    {
      "epoch": 0.01754578352889571,
      "grad_norm": 27.947410583496094,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.7286,
      "step": 20
    },
    {
      "epoch": 0.026318675293343568,
      "grad_norm": 15.611265182495117,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.6691,
      "step": 30
    },
    {
      "epoch": 0.03509156705779142,
      "grad_norm": 14.706952095031738,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.6678,
      "step": 40
    },
    {
      "epoch": 0.04386445882223928,
      "grad_norm": 20.6095027923584,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6755,
      "step": 50
    },
    {
      "epoch": 0.052637350586687136,
      "grad_norm": 15.785083770751953,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.6245,
      "step": 60
    },
    {
      "epoch": 0.06141024235113499,
      "grad_norm": 16.40140724182129,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.6065,
      "step": 70
    },
    {
      "epoch": 0.07018313411558284,
      "grad_norm": 16.08489990234375,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.5906,
      "step": 80
    },
    {
      "epoch": 0.0789560258800307,
      "grad_norm": 10.633989334106445,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.5696,
      "step": 90
    },
    {
      "epoch": 0.08772891764447856,
      "grad_norm": 13.910264015197754,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5952,
      "step": 100
    },
    {
      "epoch": 0.09650180940892641,
      "grad_norm": 16.332483291625977,
      "learning_rate": 4.4e-06,
      "loss": 0.5808,
      "step": 110
    },
    {
      "epoch": 0.10527470117337427,
      "grad_norm": 12.419142723083496,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.564,
      "step": 120
    },
    {
      "epoch": 0.11404759293782213,
      "grad_norm": 14.58597183227539,
      "learning_rate": 5.2e-06,
      "loss": 0.6409,
      "step": 130
    },
    {
      "epoch": 0.12282048470226999,
      "grad_norm": 9.651647567749023,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.5049,
      "step": 140
    },
    {
      "epoch": 0.13159337646671784,
      "grad_norm": 23.112552642822266,
      "learning_rate": 6e-06,
      "loss": 0.6125,
      "step": 150
    },
    {
      "epoch": 0.1403662682311657,
      "grad_norm": 14.535902976989746,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.5401,
      "step": 160
    },
    {
      "epoch": 0.14913915999561356,
      "grad_norm": 19.689529418945312,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.5239,
      "step": 170
    },
    {
      "epoch": 0.1579120517600614,
      "grad_norm": 27.909992218017578,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.5906,
      "step": 180
    },
    {
      "epoch": 0.16668494352450927,
      "grad_norm": 10.908613204956055,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.5276,
      "step": 190
    },
    {
      "epoch": 0.17545783528895711,
      "grad_norm": 11.81062126159668,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5355,
      "step": 200
    },
    {
      "epoch": 0.18423072705340499,
      "grad_norm": 16.26637077331543,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.5265,
      "step": 210
    },
    {
      "epoch": 0.19300361881785283,
      "grad_norm": 9.670770645141602,
      "learning_rate": 8.8e-06,
      "loss": 0.5206,
      "step": 220
    },
    {
      "epoch": 0.2017765105823007,
      "grad_norm": 14.58901309967041,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.5791,
      "step": 230
    },
    {
      "epoch": 0.21054940234674854,
      "grad_norm": 8.426600456237793,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.5681,
      "step": 240
    },
    {
      "epoch": 0.21932229411119641,
      "grad_norm": 10.079155921936035,
      "learning_rate": 1e-05,
      "loss": 0.6321,
      "step": 250
    },
    {
      "epoch": 0.22809518587564426,
      "grad_norm": 11.706363677978516,
      "learning_rate": 1.04e-05,
      "loss": 0.5798,
      "step": 260
    },
    {
      "epoch": 0.23686807764009213,
      "grad_norm": 17.979509353637695,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 0.5672,
      "step": 270
    },
    {
      "epoch": 0.24564096940453997,
      "grad_norm": 10.209049224853516,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.4833,
      "step": 280
    },
    {
      "epoch": 0.25441386116898784,
      "grad_norm": 15.83713150024414,
      "learning_rate": 1.16e-05,
      "loss": 0.5465,
      "step": 290
    },
    {
      "epoch": 0.2631867529334357,
      "grad_norm": 14.48042106628418,
      "learning_rate": 1.2e-05,
      "loss": 0.5025,
      "step": 300
    },
    {
      "epoch": 0.27195964469788353,
      "grad_norm": 14.64489459991455,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 0.4883,
      "step": 310
    },
    {
      "epoch": 0.2807325364623314,
      "grad_norm": 19.78868865966797,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.5079,
      "step": 320
    },
    {
      "epoch": 0.28950542822677927,
      "grad_norm": 11.523838996887207,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 0.5315,
      "step": 330
    },
    {
      "epoch": 0.2982783199912271,
      "grad_norm": 7.584911346435547,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 0.5383,
      "step": 340
    },
    {
      "epoch": 0.30705121175567496,
      "grad_norm": 10.454729080200195,
      "learning_rate": 1.4e-05,
      "loss": 0.6835,
      "step": 350
    },
    {
      "epoch": 0.3158241035201228,
      "grad_norm": 10.022806167602539,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.625,
      "step": 360
    },
    {
      "epoch": 0.3245969952845707,
      "grad_norm": 7.622408866882324,
      "learning_rate": 1.48e-05,
      "loss": 0.6109,
      "step": 370
    },
    {
      "epoch": 0.33336988704901854,
      "grad_norm": 6.975420951843262,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.5333,
      "step": 380
    },
    {
      "epoch": 0.3421427788134664,
      "grad_norm": 10.684267044067383,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 0.4575,
      "step": 390
    },
    {
      "epoch": 0.35091567057791423,
      "grad_norm": 13.571067810058594,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.5544,
      "step": 400
    },
    {
      "epoch": 0.35968856234236213,
      "grad_norm": 7.205085277557373,
      "learning_rate": 1.64e-05,
      "loss": 0.6155,
      "step": 410
    },
    {
      "epoch": 0.36846145410680997,
      "grad_norm": 13.097399711608887,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.5048,
      "step": 420
    },
    {
      "epoch": 0.3772343458712578,
      "grad_norm": 16.442916870117188,
      "learning_rate": 1.72e-05,
      "loss": 0.4976,
      "step": 430
    },
    {
      "epoch": 0.38600723763570566,
      "grad_norm": 6.001971244812012,
      "learning_rate": 1.76e-05,
      "loss": 0.4145,
      "step": 440
    },
    {
      "epoch": 0.3947801294001535,
      "grad_norm": 2.986736297607422,
      "learning_rate": 1.8e-05,
      "loss": 0.5126,
      "step": 450
    },
    {
      "epoch": 0.4035530211646014,
      "grad_norm": 9.169132232666016,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 0.5626,
      "step": 460
    },
    {
      "epoch": 0.41232591292904924,
      "grad_norm": 29.881427764892578,
      "learning_rate": 1.88e-05,
      "loss": 0.5039,
      "step": 470
    },
    {
      "epoch": 0.4210988046934971,
      "grad_norm": 14.136128425598145,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.4363,
      "step": 480
    },
    {
      "epoch": 0.42987169645794493,
      "grad_norm": 10.021966934204102,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.4673,
      "step": 490
    },
    {
      "epoch": 0.43864458822239283,
      "grad_norm": 14.060495376586914,
      "learning_rate": 2e-05,
      "loss": 0.3646,
      "step": 500
    },
    {
      "epoch": 0.43864458822239283,
      "eval_accuracy": 0.8244752121482805,
      "eval_f1": 0.77834179357022,
      "eval_loss": 0.4058316648006439,
      "eval_precision": 0.8146399055489965,
      "eval_recall": 0.7451403887688985,
      "eval_runtime": 561.5176,
      "eval_samples_per_second": 3.987,
      "eval_steps_per_second": 0.499,
      "step": 500
    },
    {
      "epoch": 0.44741747998684067,
      "grad_norm": 60.427162170410156,
      "learning_rate": 1.968701095461659e-05,
      "loss": 0.5038,
      "step": 510
    },
    {
      "epoch": 0.4561903717512885,
      "grad_norm": 10.006261825561523,
      "learning_rate": 1.9374021909233177e-05,
      "loss": 0.4059,
      "step": 520
    },
    {
      "epoch": 0.46496326351573636,
      "grad_norm": 7.567866802215576,
      "learning_rate": 1.9061032863849767e-05,
      "loss": 0.4314,
      "step": 530
    },
    {
      "epoch": 0.47373615528018426,
      "grad_norm": 12.703323364257812,
      "learning_rate": 1.8748043818466356e-05,
      "loss": 0.2459,
      "step": 540
    },
    {
      "epoch": 0.4825090470446321,
      "grad_norm": 3.947957754135132,
      "learning_rate": 1.8435054773082942e-05,
      "loss": 0.1668,
      "step": 550
    },
    {
      "epoch": 0.49128193880907994,
      "grad_norm": 9.213306427001953,
      "learning_rate": 1.8122065727699532e-05,
      "loss": 0.2323,
      "step": 560
    },
    {
      "epoch": 0.5000548305735278,
      "grad_norm": 0.25514841079711914,
      "learning_rate": 1.780907668231612e-05,
      "loss": 0.1923,
      "step": 570
    },
    {
      "epoch": 0.5088277223379757,
      "grad_norm": 50.12841796875,
      "learning_rate": 1.7496087636932707e-05,
      "loss": 0.4251,
      "step": 580
    },
    {
      "epoch": 0.5176006141024235,
      "grad_norm": 6.860497951507568,
      "learning_rate": 1.7183098591549297e-05,
      "loss": 0.3019,
      "step": 590
    },
    {
      "epoch": 0.5263735058668714,
      "grad_norm": 19.863380432128906,
      "learning_rate": 1.6870109546165886e-05,
      "loss": 0.1773,
      "step": 600
    },
    {
      "epoch": 0.5351463976313192,
      "grad_norm": 0.8949945569038391,
      "learning_rate": 1.6557120500782473e-05,
      "loss": 0.1894,
      "step": 610
    },
    {
      "epoch": 0.5439192893957671,
      "grad_norm": 17.815959930419922,
      "learning_rate": 1.6244131455399062e-05,
      "loss": 0.2715,
      "step": 620
    },
    {
      "epoch": 0.5526921811602149,
      "grad_norm": 12.630502700805664,
      "learning_rate": 1.5931142410015648e-05,
      "loss": 0.0829,
      "step": 630
    },
    {
      "epoch": 0.5614650729246627,
      "grad_norm": 10.575263977050781,
      "learning_rate": 1.5618153364632238e-05,
      "loss": 0.1798,
      "step": 640
    },
    {
      "epoch": 0.5702379646891107,
      "grad_norm": 18.799726486206055,
      "learning_rate": 1.5305164319248827e-05,
      "loss": 0.2497,
      "step": 650
    },
    {
      "epoch": 0.5790108564535585,
      "grad_norm": 0.6230038404464722,
      "learning_rate": 1.4992175273865417e-05,
      "loss": 0.1408,
      "step": 660
    },
    {
      "epoch": 0.5877837482180064,
      "grad_norm": 0.14638830721378326,
      "learning_rate": 1.4679186228482005e-05,
      "loss": 0.2073,
      "step": 670
    },
    {
      "epoch": 0.5965566399824542,
      "grad_norm": 11.391288757324219,
      "learning_rate": 1.4366197183098594e-05,
      "loss": 0.2668,
      "step": 680
    },
    {
      "epoch": 0.6053295317469021,
      "grad_norm": 21.246145248413086,
      "learning_rate": 1.4053208137715182e-05,
      "loss": 0.157,
      "step": 690
    },
    {
      "epoch": 0.6141024235113499,
      "grad_norm": 9.763635635375977,
      "learning_rate": 1.374021909233177e-05,
      "loss": 0.2703,
      "step": 700
    },
    {
      "epoch": 0.6228753152757978,
      "grad_norm": 5.701905727386475,
      "learning_rate": 1.342723004694836e-05,
      "loss": 0.1502,
      "step": 710
    },
    {
      "epoch": 0.6316482070402456,
      "grad_norm": 15.160579681396484,
      "learning_rate": 1.3114241001564947e-05,
      "loss": 0.1193,
      "step": 720
    },
    {
      "epoch": 0.6404210988046934,
      "grad_norm": 0.9100450873374939,
      "learning_rate": 1.2801251956181535e-05,
      "loss": 0.1526,
      "step": 730
    },
    {
      "epoch": 0.6491939905691414,
      "grad_norm": 1.2482988834381104,
      "learning_rate": 1.2488262910798124e-05,
      "loss": 0.0877,
      "step": 740
    },
    {
      "epoch": 0.6579668823335892,
      "grad_norm": 33.362972259521484,
      "learning_rate": 1.2175273865414712e-05,
      "loss": 0.2326,
      "step": 750
    },
    {
      "epoch": 0.6667397740980371,
      "grad_norm": 18.053966522216797,
      "learning_rate": 1.18622848200313e-05,
      "loss": 0.1339,
      "step": 760
    },
    {
      "epoch": 0.6755126658624849,
      "grad_norm": 0.13135869801044464,
      "learning_rate": 1.1549295774647888e-05,
      "loss": 0.111,
      "step": 770
    },
    {
      "epoch": 0.6842855576269328,
      "grad_norm": 0.08466053754091263,
      "learning_rate": 1.1236306729264477e-05,
      "loss": 0.1719,
      "step": 780
    },
    {
      "epoch": 0.6930584493913806,
      "grad_norm": 10.705062866210938,
      "learning_rate": 1.0923317683881065e-05,
      "loss": 0.271,
      "step": 790
    },
    {
      "epoch": 0.7018313411558285,
      "grad_norm": 21.25899314880371,
      "learning_rate": 1.0610328638497653e-05,
      "loss": 0.0995,
      "step": 800
    },
    {
      "epoch": 0.7106042329202763,
      "grad_norm": 4.999286651611328,
      "learning_rate": 1.0297339593114242e-05,
      "loss": 0.0837,
      "step": 810
    },
    {
      "epoch": 0.7193771246847243,
      "grad_norm": 8.578291893005371,
      "learning_rate": 9.98435054773083e-06,
      "loss": 0.1303,
      "step": 820
    },
    {
      "epoch": 0.7281500164491721,
      "grad_norm": 14.489535331726074,
      "learning_rate": 9.671361502347418e-06,
      "loss": 0.0931,
      "step": 830
    },
    {
      "epoch": 0.7369229082136199,
      "grad_norm": 0.21449220180511475,
      "learning_rate": 9.358372456964007e-06,
      "loss": 0.151,
      "step": 840
    },
    {
      "epoch": 0.7456957999780678,
      "grad_norm": 6.524932384490967,
      "learning_rate": 9.045383411580595e-06,
      "loss": 0.0509,
      "step": 850
    },
    {
      "epoch": 0.7544686917425156,
      "grad_norm": 12.212717056274414,
      "learning_rate": 8.732394366197183e-06,
      "loss": 0.2197,
      "step": 860
    },
    {
      "epoch": 0.7632415835069635,
      "grad_norm": 7.826491832733154,
      "learning_rate": 8.419405320813773e-06,
      "loss": 0.1044,
      "step": 870
    },
    {
      "epoch": 0.7720144752714113,
      "grad_norm": 0.8386934995651245,
      "learning_rate": 8.10641627543036e-06,
      "loss": 0.1518,
      "step": 880
    },
    {
      "epoch": 0.7807873670358592,
      "grad_norm": 0.19109545648097992,
      "learning_rate": 7.79342723004695e-06,
      "loss": 0.1311,
      "step": 890
    },
    {
      "epoch": 0.789560258800307,
      "grad_norm": 1.3321959972381592,
      "learning_rate": 7.480438184663538e-06,
      "loss": 0.0714,
      "step": 900
    },
    {
      "epoch": 0.798333150564755,
      "grad_norm": 8.981656074523926,
      "learning_rate": 7.167449139280126e-06,
      "loss": 0.1203,
      "step": 910
    },
    {
      "epoch": 0.8071060423292028,
      "grad_norm": 0.2177647352218628,
      "learning_rate": 6.854460093896714e-06,
      "loss": 0.087,
      "step": 920
    },
    {
      "epoch": 0.8158789340936506,
      "grad_norm": 1.4992311000823975,
      "learning_rate": 6.541471048513303e-06,
      "loss": 0.1357,
      "step": 930
    },
    {
      "epoch": 0.8246518258580985,
      "grad_norm": 2.294389486312866,
      "learning_rate": 6.228482003129891e-06,
      "loss": 0.0661,
      "step": 940
    },
    {
      "epoch": 0.8334247176225463,
      "grad_norm": 0.09688606858253479,
      "learning_rate": 5.915492957746479e-06,
      "loss": 0.0544,
      "step": 950
    },
    {
      "epoch": 0.8421976093869942,
      "grad_norm": 0.15929299592971802,
      "learning_rate": 5.602503912363068e-06,
      "loss": 0.07,
      "step": 960
    },
    {
      "epoch": 0.850970501151442,
      "grad_norm": 0.24913333356380463,
      "learning_rate": 5.289514866979656e-06,
      "loss": 0.0736,
      "step": 970
    },
    {
      "epoch": 0.8597433929158899,
      "grad_norm": 23.65605926513672,
      "learning_rate": 4.976525821596244e-06,
      "loss": 0.0595,
      "step": 980
    },
    {
      "epoch": 0.8685162846803377,
      "grad_norm": 14.373787879943848,
      "learning_rate": 4.663536776212833e-06,
      "loss": 0.1203,
      "step": 990
    },
    {
      "epoch": 0.8772891764447857,
      "grad_norm": 1.452081322669983,
      "learning_rate": 4.350547730829422e-06,
      "loss": 0.0877,
      "step": 1000
    },
    {
      "epoch": 0.8772891764447857,
      "eval_accuracy": 0.9584635998213488,
      "eval_f1": 0.951232302045097,
      "eval_loss": 0.1738564521074295,
      "eval_precision": 0.9245667686034659,
      "eval_recall": 0.9794816414686826,
      "eval_runtime": 479.7572,
      "eval_samples_per_second": 4.667,
      "eval_steps_per_second": 0.584,
      "step": 1000
    },
    {
      "epoch": 0.8860620682092335,
      "grad_norm": 7.37061882019043,
      "learning_rate": 4.0375586854460095e-06,
      "loss": 0.0067,
      "step": 1010
    },
    {
      "epoch": 0.8948349599736813,
      "grad_norm": 2.164485216140747,
      "learning_rate": 3.724569640062598e-06,
      "loss": 0.0256,
      "step": 1020
    },
    {
      "epoch": 0.9036078517381292,
      "grad_norm": 20.99627685546875,
      "learning_rate": 3.4115805946791864e-06,
      "loss": 0.1531,
      "step": 1030
    },
    {
      "epoch": 0.912380743502577,
      "grad_norm": 10.877192497253418,
      "learning_rate": 3.0985915492957746e-06,
      "loss": 0.1619,
      "step": 1040
    },
    {
      "epoch": 0.9211536352670249,
      "grad_norm": 0.06543366611003876,
      "learning_rate": 2.7856025039123637e-06,
      "loss": 0.0532,
      "step": 1050
    },
    {
      "epoch": 0.9299265270314727,
      "grad_norm": 1.2488692998886108,
      "learning_rate": 2.4726134585289515e-06,
      "loss": 0.0916,
      "step": 1060
    },
    {
      "epoch": 0.9386994187959206,
      "grad_norm": 0.08849219232797623,
      "learning_rate": 2.15962441314554e-06,
      "loss": 0.0663,
      "step": 1070
    },
    {
      "epoch": 0.9474723105603685,
      "grad_norm": 82.8930892944336,
      "learning_rate": 1.8466353677621286e-06,
      "loss": 0.1457,
      "step": 1080
    },
    {
      "epoch": 0.9562452023248164,
      "grad_norm": 11.937994956970215,
      "learning_rate": 1.5336463223787168e-06,
      "loss": 0.0481,
      "step": 1090
    },
    {
      "epoch": 0.9650180940892642,
      "grad_norm": 45.752872467041016,
      "learning_rate": 1.2206572769953053e-06,
      "loss": 0.1291,
      "step": 1100
    },
    {
      "epoch": 0.973790985853712,
      "grad_norm": 0.06413407623767853,
      "learning_rate": 9.076682316118937e-07,
      "loss": 0.0267,
      "step": 1110
    },
    {
      "epoch": 0.9825638776181599,
      "grad_norm": 11.743976593017578,
      "learning_rate": 5.94679186228482e-07,
      "loss": 0.1039,
      "step": 1120
    },
    {
      "epoch": 0.9913367693826077,
      "grad_norm": 1.0850673913955688,
      "learning_rate": 2.8169014084507043e-07,
      "loss": 0.0433,
      "step": 1130
    },
    {
      "epoch": 0.9992323719706108,
      "step": 1139,
      "total_flos": 1.186312889546834e+17,
      "train_loss": 0.3326558042530222,
      "train_runtime": 10607.6074,
      "train_samples_per_second": 1.719,
      "train_steps_per_second": 0.107
    }
  ],
  "logging_steps": 10,
  "max_steps": 1139,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.186312889546834e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}