{
  "best_global_step": 900,
  "best_metric": 0.05392824113368988,
  "best_model_checkpoint": "/kaggle/working/billstructai_qwen_lora/checkpoint-900",
  "epoch": 1.9163558870538093,
  "eval_steps": 100,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021310602024507193,
      "grad_norm": 0.5570411682128906,
      "learning_rate": 6.206896551724138e-05,
      "loss": 0.48706421852111814,
      "step": 10
    },
    {
      "epoch": 0.042621204049014386,
      "grad_norm": 0.5630005598068237,
      "learning_rate": 0.00013103448275862068,
      "loss": 0.223022723197937,
      "step": 20
    },
    {
      "epoch": 0.06393180607352157,
      "grad_norm": 0.2142772376537323,
      "learning_rate": 0.0002,
      "loss": 0.11430357694625855,
      "step": 30
    },
    {
      "epoch": 0.08524240809802877,
      "grad_norm": 0.1824568212032318,
      "learning_rate": 0.00019994054478472144,
      "loss": 0.10234310626983642,
      "step": 40
    },
    {
      "epoch": 0.10655301012253596,
      "grad_norm": 0.1363372802734375,
      "learning_rate": 0.00019976224983733816,
      "loss": 0.09078772068023681,
      "step": 50
    },
    {
      "epoch": 0.12786361214704314,
      "grad_norm": 0.22561518847942352,
      "learning_rate": 0.0001994653271691398,
      "loss": 0.08356261253356934,
      "step": 60
    },
    {
      "epoch": 0.14917421417155036,
      "grad_norm": 0.234844371676445,
      "learning_rate": 0.00019905012985214953,
      "loss": 0.08094308376312256,
      "step": 70
    },
    {
      "epoch": 0.17048481619605754,
      "grad_norm": 0.21515238285064697,
      "learning_rate": 0.00019851715159928466,
      "loss": 0.07718738913536072,
      "step": 80
    },
    {
      "epoch": 0.19179541822056473,
      "grad_norm": 0.13278549909591675,
      "learning_rate": 0.0001978670261772804,
      "loss": 0.08123236298561096,
      "step": 90
    },
    {
      "epoch": 0.21310602024507191,
      "grad_norm": 0.17123660445213318,
      "learning_rate": 0.00019710052665307523,
      "loss": 0.0745608925819397,
      "step": 100
    },
    {
      "epoch": 0.21310602024507191,
      "eval_loss": 0.07421404123306274,
      "eval_runtime": 248.5477,
      "eval_samples_per_second": 1.891,
      "eval_steps_per_second": 1.891,
      "step": 100
    },
    {
      "epoch": 0.23441662226957913,
      "grad_norm": 0.16013474762439728,
      "learning_rate": 0.00019621856447455364,
      "loss": 0.07106327414512634,
      "step": 110
    },
    {
      "epoch": 0.2557272242940863,
      "grad_norm": 0.13360778987407684,
      "learning_rate": 0.00019522218838673944,
      "loss": 0.0767333984375,
      "step": 120
    },
    {
      "epoch": 0.2770378263185935,
      "grad_norm": 0.16006118059158325,
      "learning_rate": 0.00019411258318472862,
      "loss": 0.06799736022949218,
      "step": 130
    },
    {
      "epoch": 0.2983484283431007,
      "grad_norm": 0.17742912471294403,
      "learning_rate": 0.00019289106830484436,
      "loss": 0.06742151379585266,
      "step": 140
    },
    {
      "epoch": 0.3196590303676079,
      "grad_norm": 0.19604063034057617,
      "learning_rate": 0.00019155909625568967,
      "loss": 0.06300732493400574,
      "step": 150
    },
    {
      "epoch": 0.3409696323921151,
      "grad_norm": 0.23139697313308716,
      "learning_rate": 0.0001901182508909631,
      "loss": 0.0801832914352417,
      "step": 160
    },
    {
      "epoch": 0.36228023441662227,
      "grad_norm": 0.15756270289421082,
      "learning_rate": 0.00018857024552609145,
      "loss": 0.06489556431770324,
      "step": 170
    },
    {
      "epoch": 0.38359083644112946,
      "grad_norm": 0.16894873976707458,
      "learning_rate": 0.00018691692090091927,
      "loss": 0.06612523198127747,
      "step": 180
    },
    {
      "epoch": 0.40490143846563664,
      "grad_norm": 0.17246082425117493,
      "learning_rate": 0.0001851602429908767,
      "loss": 0.0627750039100647,
      "step": 190
    },
    {
      "epoch": 0.42621204049014383,
      "grad_norm": 0.15236839652061462,
      "learning_rate": 0.00018330230066923022,
      "loss": 0.06336764097213746,
      "step": 200
    },
    {
      "epoch": 0.42621204049014383,
      "eval_loss": 0.0664505884051323,
      "eval_runtime": 249.4364,
      "eval_samples_per_second": 1.884,
      "eval_steps_per_second": 1.884,
      "step": 200
    },
    {
      "epoch": 0.447522642514651,
      "grad_norm": 0.1786014884710312,
      "learning_rate": 0.0001813453032231939,
      "loss": 0.0747511088848114,
      "step": 210
    },
    {
      "epoch": 0.46883324453915826,
      "grad_norm": 0.12548740208148956,
      "learning_rate": 0.00017929157772685685,
      "loss": 0.06296217441558838,
      "step": 220
    },
    {
      "epoch": 0.49014384656366544,
      "grad_norm": 0.12285338342189789,
      "learning_rate": 0.00017714356627404924,
      "loss": 0.05755079984664917,
      "step": 230
    },
    {
      "epoch": 0.5114544485881726,
      "grad_norm": 0.12364857643842697,
      "learning_rate": 0.000174903823074438,
      "loss": 0.07338430285453797,
      "step": 240
    },
    {
      "epoch": 0.5327650506126798,
      "grad_norm": 0.14315958321094513,
      "learning_rate": 0.00017257501141630516,
      "loss": 0.06376387476921082,
      "step": 250
    },
    {
      "epoch": 0.554075652637187,
      "grad_norm": 0.17841553688049316,
      "learning_rate": 0.0001701599004996203,
      "loss": 0.07746977806091308,
      "step": 260
    },
    {
      "epoch": 0.5753862546616942,
      "grad_norm": 0.18484671413898468,
      "learning_rate": 0.00016766136214317286,
      "loss": 0.0655578076839447,
      "step": 270
    },
    {
      "epoch": 0.5966968566862014,
      "grad_norm": 0.15894602239131927,
      "learning_rate": 0.00016508236736968016,
      "loss": 0.059864658117294314,
      "step": 280
    },
    {
      "epoch": 0.6180074587107086,
      "grad_norm": 0.14981523156166077,
      "learning_rate": 0.00016242598287293135,
      "loss": 0.06459205150604248,
      "step": 290
    },
    {
      "epoch": 0.6393180607352158,
      "grad_norm": 0.19262194633483887,
      "learning_rate": 0.00015969536737116879,
      "loss": 0.05724593997001648,
      "step": 300
    },
    {
      "epoch": 0.6393180607352158,
      "eval_loss": 0.06404831260442734,
      "eval_runtime": 248.8778,
      "eval_samples_per_second": 1.888,
      "eval_steps_per_second": 1.888,
      "step": 300
    },
    {
      "epoch": 0.660628662759723,
      "grad_norm": 0.16405339539051056,
      "learning_rate": 0.0001568937678510425,
      "loss": 0.06382941007614136,
      "step": 310
    },
    {
      "epoch": 0.6819392647842302,
      "grad_norm": 0.13134469091892242,
      "learning_rate": 0.00015402451570660437,
      "loss": 0.06093383431434631,
      "step": 320
    },
    {
      "epoch": 0.7032498668087374,
      "grad_norm": 0.19201718270778656,
      "learning_rate": 0.00015109102277793306,
      "loss": 0.0615972101688385,
      "step": 330
    },
    {
      "epoch": 0.7245604688332445,
      "grad_norm": 0.11001285165548325,
      "learning_rate": 0.00014809677729410046,
      "loss": 0.05652051568031311,
      "step": 340
    },
    {
      "epoch": 0.7458710708577517,
      "grad_norm": 0.1298859715461731,
      "learning_rate": 0.0001450453397253033,
      "loss": 0.05437501072883606,
      "step": 350
    },
    {
      "epoch": 0.7671816728822589,
      "grad_norm": 0.1667214184999466,
      "learning_rate": 0.0001419403385490929,
      "loss": 0.05537524223327637,
      "step": 360
    },
    {
      "epoch": 0.7884922749067661,
      "grad_norm": 0.160597026348114,
      "learning_rate": 0.00013878546593573663,
      "loss": 0.06058817505836487,
      "step": 370
    },
    {
      "epoch": 0.8098028769312733,
      "grad_norm": 0.11980368942022324,
      "learning_rate": 0.00013558447335784254,
      "loss": 0.056959474086761476,
      "step": 380
    },
    {
      "epoch": 0.8311134789557805,
      "grad_norm": 0.10598862916231155,
      "learning_rate": 0.00013234116712946715,
      "loss": 0.062009012699127196,
      "step": 390
    },
    {
      "epoch": 0.8524240809802877,
      "grad_norm": 0.1465042680501938,
      "learning_rate": 0.00012905940388001092,
      "loss": 0.06569045186042785,
      "step": 400
    },
    {
      "epoch": 0.8524240809802877,
      "eval_loss": 0.05861470475792885,
      "eval_runtime": 248.8019,
      "eval_samples_per_second": 1.889,
      "eval_steps_per_second": 1.889,
      "step": 400
    },
    {
      "epoch": 0.8737346830047948,
      "grad_norm": 0.13985313475131989,
      "learning_rate": 0.00012574308596828364,
      "loss": 0.059485018253326416,
      "step": 410
    },
    {
      "epoch": 0.895045285029302,
      "grad_norm": 0.09439831972122192,
      "learning_rate": 0.00012239615684219273,
      "loss": 0.04954729676246643,
      "step": 420
    },
    {
      "epoch": 0.9163558870538092,
      "grad_norm": 0.13079901039600372,
      "learning_rate": 0.0001190225963495725,
      "loss": 0.06261422634124755,
      "step": 430
    },
    {
      "epoch": 0.9376664890783165,
      "grad_norm": 0.17101094126701355,
      "learning_rate": 0.00011562641600572993,
      "loss": 0.05220479965209961,
      "step": 440
    },
    {
      "epoch": 0.9589770911028237,
      "grad_norm": 0.18949410319328308,
      "learning_rate": 0.0001122116542233342,
      "loss": 0.05655173659324646,
      "step": 450
    },
    {
      "epoch": 0.9802876931273309,
      "grad_norm": 0.16985633969306946,
      "learning_rate": 0.0001087823715103234,
      "loss": 0.05631093382835388,
      "step": 460
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.21016985177993774,
      "learning_rate": 0.00010534264564153651,
      "loss": 0.0492259293794632,
      "step": 470
    },
    {
      "epoch": 1.0213106020245073,
      "grad_norm": 0.10946141928434372,
      "learning_rate": 0.00010189656680981415,
      "loss": 0.045346027612686156,
      "step": 480
    },
    {
      "epoch": 1.0426212040490144,
      "grad_norm": 0.18159270286560059,
      "learning_rate": 9.844823276233243e-05,
      "loss": 0.04748743176460266,
      "step": 490
    },
    {
      "epoch": 1.0639318060735217,
      "grad_norm": 0.1416451632976532,
      "learning_rate": 9.500174392795431e-05,
      "loss": 0.04537383615970612,
      "step": 500
    },
    {
      "epoch": 1.0639318060735217,
      "eval_loss": 0.05737318471074104,
      "eval_runtime": 249.9023,
      "eval_samples_per_second": 1.881,
      "eval_steps_per_second": 1.881,
      "step": 500
    },
    {
      "epoch": 1.0852424080980287,
      "grad_norm": 0.1302674263715744,
      "learning_rate": 9.156119854139173e-05,
      "loss": 0.042424333095550534,
      "step": 510
    },
    {
      "epoch": 1.106553010122536,
      "grad_norm": 0.15241168439388275,
      "learning_rate": 8.813068776997747e-05,
      "loss": 0.037749645113945005,
      "step": 520
    },
    {
      "epoch": 1.1278636121470431,
      "grad_norm": 0.189493790268898,
      "learning_rate": 8.471429084884012e-05,
      "loss": 0.04497165381908417,
      "step": 530
    },
    {
      "epoch": 1.1491742141715504,
      "grad_norm": 0.1870124340057373,
      "learning_rate": 8.131607023026814e-05,
      "loss": 0.04265827238559723,
      "step": 540
    },
    {
      "epoch": 1.1704848161960575,
      "grad_norm": 0.1087406650185585,
      "learning_rate": 7.794006675303031e-05,
      "loss": 0.035568210482597354,
      "step": 550
    },
    {
      "epoch": 1.1917954182205648,
      "grad_norm": 0.1936003565788269,
      "learning_rate": 7.459029483739711e-05,
      "loss": 0.038499835133552554,
      "step": 560
    },
    {
      "epoch": 1.2131060202450719,
      "grad_norm": 0.1559380143880844,
      "learning_rate": 7.127073771157606e-05,
      "loss": 0.04679949283599853,
      "step": 570
    },
    {
      "epoch": 1.2344166222695792,
      "grad_norm": 0.1537848860025406,
      "learning_rate": 6.798534267523806e-05,
      "loss": 0.04622254967689514,
      "step": 580
    },
    {
      "epoch": 1.2557272242940862,
      "grad_norm": 0.17289568483829498,
      "learning_rate": 6.473801640576633e-05,
      "loss": 0.040285307168960574,
      "step": 590
    },
    {
      "epoch": 1.2770378263185935,
      "grad_norm": 0.14587342739105225,
      "learning_rate": 6.153262031280951e-05,
      "loss": 0.03852958083152771,
      "step": 600
    },
    {
      "epoch": 1.2770378263185935,
      "eval_loss": 0.056128598749637604,
      "eval_runtime": 248.6964,
      "eval_samples_per_second": 1.89,
      "eval_steps_per_second": 1.89,
      "step": 600
    },
    {
      "epoch": 1.2983484283431008,
      "grad_norm": 0.15503859519958496,
      "learning_rate": 5.8372965946662815e-05,
      "loss": 0.03877540528774261,
      "step": 610
    },
    {
      "epoch": 1.319659030367608,
      "grad_norm": 0.10821698606014252,
      "learning_rate": 5.5262810465937045e-05,
      "loss": 0.04052968025207519,
      "step": 620
    },
    {
      "epoch": 1.340969632392115,
      "grad_norm": 0.18947947025299072,
      "learning_rate": 5.2205852169905434e-05,
      "loss": 0.05081030130386353,
      "step": 630
    },
    {
      "epoch": 1.3622802344166223,
      "grad_norm": 0.2615494132041931,
      "learning_rate": 4.920572610083977e-05,
      "loss": 0.04443525373935699,
      "step": 640
    },
    {
      "epoch": 1.3835908364411296,
      "grad_norm": 0.1606501042842865,
      "learning_rate": 4.626599972156593e-05,
      "loss": 0.04287891089916229,
      "step": 650
    },
    {
      "epoch": 1.4049014384656366,
      "grad_norm": 0.14430288970470428,
      "learning_rate": 4.3390168673378775e-05,
      "loss": 0.04097432494163513,
      "step": 660
    },
    {
      "epoch": 1.4262120404901437,
      "grad_norm": 0.14559805393218994,
      "learning_rate": 4.0581652619359775e-05,
      "loss": 0.034264594316482544,
      "step": 670
    },
    {
      "epoch": 1.447522642514651,
      "grad_norm": 0.15087302029132843,
      "learning_rate": 3.7843791178041054e-05,
      "loss": 0.038701537251472476,
      "step": 680
    },
    {
      "epoch": 1.4688332445391583,
      "grad_norm": 0.18511506915092468,
      "learning_rate": 3.5179839952250524e-05,
      "loss": 0.039507734775543216,
      "step": 690
    },
    {
      "epoch": 1.4901438465636654,
      "grad_norm": 0.1208174079656601,
      "learning_rate": 3.2592966657860625e-05,
      "loss": 0.037732216715812686,
      "step": 700
    },
    {
      "epoch": 1.4901438465636654,
      "eval_loss": 0.05517593026161194,
      "eval_runtime": 248.5187,
      "eval_samples_per_second": 1.891,
      "eval_steps_per_second": 1.891,
      "step": 700
    },
    {
      "epoch": 1.5114544485881725,
      "grad_norm": 0.14407405257225037,
      "learning_rate": 3.0086247357043705e-05,
      "loss": 0.04141993820667267,
      "step": 710
    },
    {
      "epoch": 1.5327650506126798,
      "grad_norm": 0.1950131356716156,
      "learning_rate": 2.766266280051316e-05,
      "loss": 0.042274028062820435,
      "step": 720
    },
    {
      "epoch": 1.554075652637187,
      "grad_norm": 0.1330132633447647,
      "learning_rate": 2.5325094883100108e-05,
      "loss": 0.039421483874320984,
      "step": 730
    },
    {
      "epoch": 1.5753862546616944,
      "grad_norm": 0.16335627436637878,
      "learning_rate": 2.3076323216879714e-05,
      "loss": 0.03970510959625244,
      "step": 740
    },
    {
      "epoch": 1.5966968566862014,
      "grad_norm": 0.1316670924425125,
      "learning_rate": 2.0919021825922536e-05,
      "loss": 0.04199607074260712,
      "step": 750
    },
    {
      "epoch": 1.6180074587107085,
      "grad_norm": 0.132982537150383,
      "learning_rate": 1.8855755966600962e-05,
      "loss": 0.04375255405902863,
      "step": 760
    },
    {
      "epoch": 1.6393180607352158,
      "grad_norm": 0.15142162144184113,
      "learning_rate": 1.688897907723186e-05,
      "loss": 0.03803563416004181,
      "step": 770
    },
    {
      "epoch": 1.660628662759723,
      "grad_norm": 0.15250155329704285,
      "learning_rate": 1.50210298606825e-05,
      "loss": 0.03791479468345642,
      "step": 780
    },
    {
      "epoch": 1.6819392647842302,
      "grad_norm": 0.11432624608278275,
      "learning_rate": 1.325412950340882e-05,
      "loss": 0.0383548378944397,
      "step": 790
    },
    {
      "epoch": 1.7032498668087372,
      "grad_norm": 0.15887320041656494,
      "learning_rate": 1.159037903423319e-05,
      "loss": 0.04067508578300476,
      "step": 800
    },
    {
      "epoch": 1.7032498668087372,
      "eval_loss": 0.054582156240940094,
      "eval_runtime": 248.4421,
      "eval_samples_per_second": 1.892,
      "eval_steps_per_second": 1.892,
      "step": 800
    },
    {
      "epoch": 1.7245604688332445,
      "grad_norm": 0.2519368827342987,
      "learning_rate": 1.0031756826001914e-05,
      "loss": 0.0420225739479065,
      "step": 810
    },
    {
      "epoch": 1.7458710708577518,
      "grad_norm": 0.13151676952838898,
      "learning_rate": 8.580116243093562e-06,
      "loss": 0.041281819343566895,
      "step": 820
    },
    {
      "epoch": 1.767181672882259,
      "grad_norm": 0.11074542254209518,
      "learning_rate": 7.23718343757539e-06,
      "loss": 0.03622758090496063,
      "step": 830
    },
    {
      "epoch": 1.788492274906766,
      "grad_norm": 0.17330627143383026,
      "learning_rate": 6.004555296628556e-06,
      "loss": 0.0376776397228241,
      "step": 840
    },
    {
      "epoch": 1.8098028769312733,
      "grad_norm": 0.1254781186580658,
      "learning_rate": 4.88369754368263e-06,
      "loss": 0.03871485292911529,
      "step": 850
    },
    {
      "epoch": 1.8311134789557806,
      "grad_norm": 0.15773062407970428,
      "learning_rate": 3.8759429955175564e-06,
      "loss": 0.041798022389411923,
      "step": 860
    },
    {
      "epoch": 1.8524240809802877,
      "grad_norm": 0.12225436419248581,
      "learning_rate": 2.9824899774055113e-06,
      "loss": 0.036775484681129456,
      "step": 870
    },
    {
      "epoch": 1.8737346830047947,
      "grad_norm": 0.14229069650173187,
      "learning_rate": 2.2044008981771947e-06,
      "loss": 0.03825798928737641,
      "step": 880
    },
    {
      "epoch": 1.895045285029302,
      "grad_norm": 0.12034007161855698,
      "learning_rate": 1.5426009869067948e-06,
      "loss": 0.03620096147060394,
      "step": 890
    },
    {
      "epoch": 1.9163558870538093,
      "grad_norm": 0.16056819260120392,
      "learning_rate": 9.97877192718255e-07,
      "loss": 0.037316632270812986,
      "step": 900
    },
    {
      "epoch": 1.9163558870538093,
      "eval_loss": 0.05392824113368988,
      "eval_runtime": 248.0734,
      "eval_samples_per_second": 1.895,
      "eval_steps_per_second": 1.895,
      "step": 900
    }
  ],
  "logging_steps": 10,
  "max_steps": 940,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.290876726467379e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}