{
  "best_metric": 0.08991385996341705,
  "best_model_checkpoint": "./fine_tuned_meta_encoder_20240823_155731/checkpoint-1100",
  "epoch": 2.9042904290429044,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026402640264026403,
      "grad_norm": 1.2209537029266357,
      "learning_rate": 0.0002,
      "loss": 1.3132,
      "step": 10
    },
    {
      "epoch": 0.052805280528052806,
      "grad_norm": 0.8953336477279663,
      "learning_rate": 0.0002,
      "loss": 0.5263,
      "step": 20
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 0.4192950427532196,
      "learning_rate": 0.0002,
      "loss": 0.2848,
      "step": 30
    },
    {
      "epoch": 0.10561056105610561,
      "grad_norm": 0.27445298433303833,
      "learning_rate": 0.0002,
      "loss": 0.2399,
      "step": 40
    },
    {
      "epoch": 0.132013201320132,
      "grad_norm": 0.3270169794559479,
      "learning_rate": 0.0002,
      "loss": 0.2224,
      "step": 50
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 0.27454960346221924,
      "learning_rate": 0.0002,
      "loss": 0.2188,
      "step": 60
    },
    {
      "epoch": 0.1848184818481848,
      "grad_norm": 0.3361058235168457,
      "learning_rate": 0.0002,
      "loss": 0.1904,
      "step": 70
    },
    {
      "epoch": 0.21122112211221122,
      "grad_norm": 0.2786653935909271,
      "learning_rate": 0.0002,
      "loss": 0.1913,
      "step": 80
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 0.2567278742790222,
      "learning_rate": 0.0002,
      "loss": 0.1818,
      "step": 90
    },
    {
      "epoch": 0.264026402640264,
      "grad_norm": 0.26846471428871155,
      "learning_rate": 0.0002,
      "loss": 0.1652,
      "step": 100
    },
    {
      "epoch": 0.264026402640264,
      "eval_loss": 0.17934565246105194,
      "eval_runtime": 35.5662,
      "eval_samples_per_second": 18.951,
      "eval_steps_per_second": 4.752,
      "step": 100
    },
    {
      "epoch": 0.29042904290429045,
      "grad_norm": 0.3001416027545929,
      "learning_rate": 0.0002,
      "loss": 0.1711,
      "step": 110
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 0.27367591857910156,
      "learning_rate": 0.0002,
      "loss": 0.1649,
      "step": 120
    },
    {
      "epoch": 0.3432343234323432,
      "grad_norm": 0.2346794754266739,
      "learning_rate": 0.0002,
      "loss": 0.1721,
      "step": 130
    },
    {
      "epoch": 0.3696369636963696,
      "grad_norm": 0.2470114529132843,
      "learning_rate": 0.0002,
      "loss": 0.1599,
      "step": 140
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 0.2749585807323456,
      "learning_rate": 0.0002,
      "loss": 0.1648,
      "step": 150
    },
    {
      "epoch": 0.42244224422442245,
      "grad_norm": 0.23965956270694733,
      "learning_rate": 0.0002,
      "loss": 0.1584,
      "step": 160
    },
    {
      "epoch": 0.44884488448844884,
      "grad_norm": 0.2817020118236542,
      "learning_rate": 0.0002,
      "loss": 0.1567,
      "step": 170
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 0.3235905170440674,
      "learning_rate": 0.0002,
      "loss": 0.1494,
      "step": 180
    },
    {
      "epoch": 0.5016501650165016,
      "grad_norm": 0.2556610405445099,
      "learning_rate": 0.0002,
      "loss": 0.1494,
      "step": 190
    },
    {
      "epoch": 0.528052805280528,
      "grad_norm": 0.26074209809303284,
      "learning_rate": 0.0002,
      "loss": 0.1496,
      "step": 200
    },
    {
      "epoch": 0.528052805280528,
      "eval_loss": 0.15303318202495575,
      "eval_runtime": 35.5044,
      "eval_samples_per_second": 18.984,
      "eval_steps_per_second": 4.76,
      "step": 200
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 0.24563810229301453,
      "learning_rate": 0.0002,
      "loss": 0.1523,
      "step": 210
    },
    {
      "epoch": 0.5808580858085809,
      "grad_norm": 0.2592566907405853,
      "learning_rate": 0.0002,
      "loss": 0.1453,
      "step": 220
    },
    {
      "epoch": 0.6072607260726073,
      "grad_norm": 0.3210408389568329,
      "learning_rate": 0.0002,
      "loss": 0.1414,
      "step": 230
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 0.2894737720489502,
      "learning_rate": 0.0002,
      "loss": 0.1479,
      "step": 240
    },
    {
      "epoch": 0.6600660066006601,
      "grad_norm": 0.307718425989151,
      "learning_rate": 0.0002,
      "loss": 0.143,
      "step": 250
    },
    {
      "epoch": 0.6864686468646864,
      "grad_norm": 0.2861904799938202,
      "learning_rate": 0.0002,
      "loss": 0.1422,
      "step": 260
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 0.2835065424442291,
      "learning_rate": 0.0002,
      "loss": 0.1381,
      "step": 270
    },
    {
      "epoch": 0.7392739273927392,
      "grad_norm": 0.36195576190948486,
      "learning_rate": 0.0002,
      "loss": 0.1364,
      "step": 280
    },
    {
      "epoch": 0.7656765676567657,
      "grad_norm": 0.36926591396331787,
      "learning_rate": 0.0002,
      "loss": 0.1364,
      "step": 290
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.2543686628341675,
      "learning_rate": 0.0002,
      "loss": 0.1295,
      "step": 300
    },
    {
      "epoch": 0.7920792079207921,
      "eval_loss": 0.13678725063800812,
      "eval_runtime": 35.5612,
      "eval_samples_per_second": 18.953,
      "eval_steps_per_second": 4.752,
      "step": 300
    },
    {
      "epoch": 0.8184818481848185,
      "grad_norm": 0.2578878402709961,
      "learning_rate": 0.0002,
      "loss": 0.1373,
      "step": 310
    },
    {
      "epoch": 0.8448844884488449,
      "grad_norm": 0.2869018018245697,
      "learning_rate": 0.0002,
      "loss": 0.1365,
      "step": 320
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 0.2525601089000702,
      "learning_rate": 0.0002,
      "loss": 0.1263,
      "step": 330
    },
    {
      "epoch": 0.8976897689768977,
      "grad_norm": 0.33318400382995605,
      "learning_rate": 0.0002,
      "loss": 0.1342,
      "step": 340
    },
    {
      "epoch": 0.9240924092409241,
      "grad_norm": 0.26829567551612854,
      "learning_rate": 0.0002,
      "loss": 0.1217,
      "step": 350
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 0.29827719926834106,
      "learning_rate": 0.0002,
      "loss": 0.1251,
      "step": 360
    },
    {
      "epoch": 0.976897689768977,
      "grad_norm": 0.2644639313220978,
      "learning_rate": 0.0002,
      "loss": 0.1172,
      "step": 370
    },
    {
      "epoch": 1.0033003300330032,
      "grad_norm": 0.2535085082054138,
      "learning_rate": 0.0002,
      "loss": 0.1275,
      "step": 380
    },
    {
      "epoch": 1.0297029702970297,
      "grad_norm": 0.2713930606842041,
      "learning_rate": 0.0002,
      "loss": 0.1162,
      "step": 390
    },
    {
      "epoch": 1.056105610561056,
      "grad_norm": 0.26092982292175293,
      "learning_rate": 0.0002,
      "loss": 0.1209,
      "step": 400
    },
    {
      "epoch": 1.056105610561056,
      "eval_loss": 0.12458474934101105,
      "eval_runtime": 35.5248,
      "eval_samples_per_second": 18.973,
      "eval_steps_per_second": 4.757,
      "step": 400
    },
    {
      "epoch": 1.0825082508250825,
      "grad_norm": 0.3101023733615875,
      "learning_rate": 0.0002,
      "loss": 0.1206,
      "step": 410
    },
    {
      "epoch": 1.108910891089109,
      "grad_norm": 0.2629012167453766,
      "learning_rate": 0.0002,
      "loss": 0.1165,
      "step": 420
    },
    {
      "epoch": 1.1353135313531353,
      "grad_norm": 0.2954414188861847,
      "learning_rate": 0.0002,
      "loss": 0.121,
      "step": 430
    },
    {
      "epoch": 1.1617161716171618,
      "grad_norm": 0.3219696879386902,
      "learning_rate": 0.0002,
      "loss": 0.1155,
      "step": 440
    },
    {
      "epoch": 1.188118811881188,
      "grad_norm": 0.2916986346244812,
      "learning_rate": 0.0002,
      "loss": 0.1109,
      "step": 450
    },
    {
      "epoch": 1.2145214521452146,
      "grad_norm": 0.2607131600379944,
      "learning_rate": 0.0002,
      "loss": 0.1125,
      "step": 460
    },
    {
      "epoch": 1.2409240924092408,
      "grad_norm": 0.25215160846710205,
      "learning_rate": 0.0002,
      "loss": 0.1155,
      "step": 470
    },
    {
      "epoch": 1.2673267326732673,
      "grad_norm": 0.2367628961801529,
      "learning_rate": 0.0002,
      "loss": 0.1119,
      "step": 480
    },
    {
      "epoch": 1.2937293729372938,
      "grad_norm": 0.2621775269508362,
      "learning_rate": 0.0002,
      "loss": 0.106,
      "step": 490
    },
    {
      "epoch": 1.3201320132013201,
      "grad_norm": 0.27597054839134216,
      "learning_rate": 0.0002,
      "loss": 0.1071,
      "step": 500
    },
    {
      "epoch": 1.3201320132013201,
      "eval_loss": 0.11538028717041016,
      "eval_runtime": 35.6246,
      "eval_samples_per_second": 18.92,
      "eval_steps_per_second": 4.744,
      "step": 500
    },
    {
      "epoch": 1.3465346534653464,
      "grad_norm": 0.3191552758216858,
      "learning_rate": 0.0002,
      "loss": 0.11,
      "step": 510
    },
    {
      "epoch": 1.372937293729373,
      "grad_norm": 0.32491299510002136,
      "learning_rate": 0.0002,
      "loss": 0.1072,
      "step": 520
    },
    {
      "epoch": 1.3993399339933994,
      "grad_norm": 0.3281764090061188,
      "learning_rate": 0.0002,
      "loss": 0.1141,
      "step": 530
    },
    {
      "epoch": 1.4257425742574257,
      "grad_norm": 0.24705563485622406,
      "learning_rate": 0.0002,
      "loss": 0.1026,
      "step": 540
    },
    {
      "epoch": 1.4521452145214522,
      "grad_norm": 0.24219994246959686,
      "learning_rate": 0.0002,
      "loss": 0.1058,
      "step": 550
    },
    {
      "epoch": 1.4785478547854787,
      "grad_norm": 0.2313147485256195,
      "learning_rate": 0.0002,
      "loss": 0.104,
      "step": 560
    },
    {
      "epoch": 1.504950495049505,
      "grad_norm": 0.34662193059921265,
      "learning_rate": 0.0002,
      "loss": 0.1007,
      "step": 570
    },
    {
      "epoch": 1.5313531353135312,
      "grad_norm": 0.2655913829803467,
      "learning_rate": 0.0002,
      "loss": 0.102,
      "step": 580
    },
    {
      "epoch": 1.5577557755775577,
      "grad_norm": 0.2477431297302246,
      "learning_rate": 0.0002,
      "loss": 0.1073,
      "step": 590
    },
    {
      "epoch": 1.5841584158415842,
      "grad_norm": 0.2847592532634735,
      "learning_rate": 0.0002,
      "loss": 0.1049,
      "step": 600
    },
    {
      "epoch": 1.5841584158415842,
      "eval_loss": 0.10829836875200272,
      "eval_runtime": 35.5648,
      "eval_samples_per_second": 18.951,
      "eval_steps_per_second": 4.752,
      "step": 600
    },
    {
      "epoch": 1.6105610561056105,
      "grad_norm": 0.24044634401798248,
      "learning_rate": 0.0002,
      "loss": 0.1003,
      "step": 610
    },
    {
      "epoch": 1.636963696369637,
      "grad_norm": 0.2383195161819458,
      "learning_rate": 0.0002,
      "loss": 0.1023,
      "step": 620
    },
    {
      "epoch": 1.6633663366336635,
      "grad_norm": 0.2620280981063843,
      "learning_rate": 0.0002,
      "loss": 0.0978,
      "step": 630
    },
    {
      "epoch": 1.6897689768976898,
      "grad_norm": 0.27225416898727417,
      "learning_rate": 0.0002,
      "loss": 0.1055,
      "step": 640
    },
    {
      "epoch": 1.716171617161716,
      "grad_norm": 0.2959238588809967,
      "learning_rate": 0.0002,
      "loss": 0.1015,
      "step": 650
    },
    {
      "epoch": 1.7425742574257426,
      "grad_norm": 0.2089966982603073,
      "learning_rate": 0.0002,
      "loss": 0.1024,
      "step": 660
    },
    {
      "epoch": 1.768976897689769,
      "grad_norm": 0.23935158550739288,
      "learning_rate": 0.0002,
      "loss": 0.1002,
      "step": 670
    },
    {
      "epoch": 1.7953795379537953,
      "grad_norm": 0.2478724718093872,
      "learning_rate": 0.0002,
      "loss": 0.1016,
      "step": 680
    },
    {
      "epoch": 1.8217821782178216,
      "grad_norm": 0.25742414593696594,
      "learning_rate": 0.0002,
      "loss": 0.1016,
      "step": 690
    },
    {
      "epoch": 1.8481848184818483,
      "grad_norm": 0.2547028064727783,
      "learning_rate": 0.0002,
      "loss": 0.0913,
      "step": 700
    },
    {
      "epoch": 1.8481848184818483,
      "eval_loss": 0.10148681700229645,
      "eval_runtime": 35.5107,
      "eval_samples_per_second": 18.98,
      "eval_steps_per_second": 4.759,
      "step": 700
    },
    {
      "epoch": 1.8745874587458746,
      "grad_norm": 0.2965940237045288,
      "learning_rate": 0.0002,
      "loss": 0.0989,
      "step": 710
    },
    {
      "epoch": 1.900990099009901,
      "grad_norm": 0.22955147922039032,
      "learning_rate": 0.0002,
      "loss": 0.0936,
      "step": 720
    },
    {
      "epoch": 1.9273927392739274,
      "grad_norm": 0.2257162481546402,
      "learning_rate": 0.0002,
      "loss": 0.0893,
      "step": 730
    },
    {
      "epoch": 1.953795379537954,
      "grad_norm": 0.274249404668808,
      "learning_rate": 0.0002,
      "loss": 0.0983,
      "step": 740
    },
    {
      "epoch": 1.9801980198019802,
      "grad_norm": 0.25331228971481323,
      "learning_rate": 0.0002,
      "loss": 0.0956,
      "step": 750
    },
    {
      "epoch": 2.0066006600660065,
      "grad_norm": 0.2801855802536011,
      "learning_rate": 0.0002,
      "loss": 0.0948,
      "step": 760
    },
    {
      "epoch": 2.033003300330033,
      "grad_norm": 0.24239327013492584,
      "learning_rate": 0.0002,
      "loss": 0.0874,
      "step": 770
    },
    {
      "epoch": 2.0594059405940595,
      "grad_norm": 0.292223185300827,
      "learning_rate": 0.0002,
      "loss": 0.0874,
      "step": 780
    },
    {
      "epoch": 2.0858085808580857,
      "grad_norm": 0.2646115720272064,
      "learning_rate": 0.0002,
      "loss": 0.0857,
      "step": 790
    },
    {
      "epoch": 2.112211221122112,
      "grad_norm": 0.22307829558849335,
      "learning_rate": 0.0002,
      "loss": 0.0867,
      "step": 800
    },
    {
      "epoch": 2.112211221122112,
      "eval_loss": 0.09895669668912888,
      "eval_runtime": 35.4576,
      "eval_samples_per_second": 19.009,
      "eval_steps_per_second": 4.766,
      "step": 800
    },
    {
      "epoch": 2.1386138613861387,
      "grad_norm": 0.2283334881067276,
      "learning_rate": 0.0002,
      "loss": 0.0861,
      "step": 810
    },
    {
      "epoch": 2.165016501650165,
      "grad_norm": 0.24495747685432434,
      "learning_rate": 0.0002,
      "loss": 0.0865,
      "step": 820
    },
    {
      "epoch": 2.1914191419141913,
      "grad_norm": 0.2823265790939331,
      "learning_rate": 0.0002,
      "loss": 0.0851,
      "step": 830
    },
    {
      "epoch": 2.217821782178218,
      "grad_norm": 0.29882529377937317,
      "learning_rate": 0.0002,
      "loss": 0.0883,
      "step": 840
    },
    {
      "epoch": 2.2442244224422443,
      "grad_norm": 0.2550313174724579,
      "learning_rate": 0.0002,
      "loss": 0.0872,
      "step": 850
    },
    {
      "epoch": 2.2706270627062706,
      "grad_norm": 0.24576956033706665,
      "learning_rate": 0.0002,
      "loss": 0.0871,
      "step": 860
    },
    {
      "epoch": 2.297029702970297,
      "grad_norm": 0.2293216437101364,
      "learning_rate": 0.0002,
      "loss": 0.0852,
      "step": 870
    },
    {
      "epoch": 2.3234323432343236,
      "grad_norm": 0.2510163486003876,
      "learning_rate": 0.0002,
      "loss": 0.087,
      "step": 880
    },
    {
      "epoch": 2.34983498349835,
      "grad_norm": 0.22960515320301056,
      "learning_rate": 0.0002,
      "loss": 0.0829,
      "step": 890
    },
    {
      "epoch": 2.376237623762376,
      "grad_norm": 0.26182201504707336,
      "learning_rate": 0.0002,
      "loss": 0.0788,
      "step": 900
    },
    {
      "epoch": 2.376237623762376,
      "eval_loss": 0.09652868658304214,
      "eval_runtime": 35.4522,
      "eval_samples_per_second": 19.012,
      "eval_steps_per_second": 4.767,
      "step": 900
    },
    {
      "epoch": 2.4026402640264024,
      "grad_norm": 0.22264224290847778,
      "learning_rate": 0.0002,
      "loss": 0.0867,
      "step": 910
    },
    {
      "epoch": 2.429042904290429,
      "grad_norm": 0.24472057819366455,
      "learning_rate": 0.0002,
      "loss": 0.085,
      "step": 920
    },
    {
      "epoch": 2.4554455445544554,
      "grad_norm": 0.21409814059734344,
      "learning_rate": 0.0002,
      "loss": 0.0902,
      "step": 930
    },
    {
      "epoch": 2.4818481848184817,
      "grad_norm": 0.2275090515613556,
      "learning_rate": 0.0002,
      "loss": 0.0833,
      "step": 940
    },
    {
      "epoch": 2.5082508250825084,
      "grad_norm": 0.24984212219715118,
      "learning_rate": 0.0002,
      "loss": 0.0875,
      "step": 950
    },
    {
      "epoch": 2.5346534653465347,
      "grad_norm": 0.2913050949573517,
      "learning_rate": 0.0002,
      "loss": 0.0821,
      "step": 960
    },
    {
      "epoch": 2.561056105610561,
      "grad_norm": 0.30677589774131775,
      "learning_rate": 0.0002,
      "loss": 0.0835,
      "step": 970
    },
    {
      "epoch": 2.5874587458745877,
      "grad_norm": 0.2401341199874878,
      "learning_rate": 0.0002,
      "loss": 0.088,
      "step": 980
    },
    {
      "epoch": 2.613861386138614,
      "grad_norm": 0.25704678893089294,
      "learning_rate": 0.0002,
      "loss": 0.0838,
      "step": 990
    },
    {
      "epoch": 2.6402640264026402,
      "grad_norm": 0.20528723299503326,
      "learning_rate": 0.0002,
      "loss": 0.0839,
      "step": 1000
    },
    {
      "epoch": 2.6402640264026402,
      "eval_loss": 0.09263003617525101,
      "eval_runtime": 35.5469,
      "eval_samples_per_second": 18.961,
      "eval_steps_per_second": 4.754,
      "step": 1000
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.2680225968360901,
      "learning_rate": 0.0002,
      "loss": 0.0877,
      "step": 1010
    },
    {
      "epoch": 2.693069306930693,
      "grad_norm": 0.24241389334201813,
      "learning_rate": 0.0002,
      "loss": 0.0793,
      "step": 1020
    },
    {
      "epoch": 2.7194719471947195,
      "grad_norm": 0.2348719835281372,
      "learning_rate": 0.0002,
      "loss": 0.0857,
      "step": 1030
    },
    {
      "epoch": 2.745874587458746,
      "grad_norm": 0.25451603531837463,
      "learning_rate": 0.0002,
      "loss": 0.0877,
      "step": 1040
    },
    {
      "epoch": 2.772277227722772,
      "grad_norm": 0.28436726331710815,
      "learning_rate": 0.0002,
      "loss": 0.0829,
      "step": 1050
    },
    {
      "epoch": 2.798679867986799,
      "grad_norm": 0.269794225692749,
      "learning_rate": 0.0002,
      "loss": 0.0826,
      "step": 1060
    },
    {
      "epoch": 2.825082508250825,
      "grad_norm": 0.22040368616580963,
      "learning_rate": 0.0002,
      "loss": 0.0814,
      "step": 1070
    },
    {
      "epoch": 2.8514851485148514,
      "grad_norm": 0.2117665708065033,
      "learning_rate": 0.0002,
      "loss": 0.084,
      "step": 1080
    },
    {
      "epoch": 2.877887788778878,
      "grad_norm": 0.21133095026016235,
      "learning_rate": 0.0002,
      "loss": 0.0838,
      "step": 1090
    },
    {
      "epoch": 2.9042904290429044,
      "grad_norm": 0.25484949350357056,
      "learning_rate": 0.0002,
      "loss": 0.082,
      "step": 1100
    },
    {
      "epoch": 2.9042904290429044,
      "eval_loss": 0.08991385996341705,
      "eval_runtime": 35.6202,
      "eval_samples_per_second": 18.922,
      "eval_steps_per_second": 4.744,
      "step": 1100
    }
  ],
  "logging_steps": 10,
  "max_steps": 1134,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.017625090355036e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}