{
  "best_global_step": 1600,
  "best_metric": 0.9785549323655559,
  "best_model_checkpoint": "/kaggle/working/outputs/codebert_rd_keystrokes/checkpoint-1600",
  "epoch": 1.941747572815534,
  "eval_steps": 400,
  "global_step": 2400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008090614886731392,
      "grad_norm": 4.001261234283447,
      "learning_rate": 0.0,
      "loss": 0.748644232749939,
      "step": 1
    },
    {
      "epoch": 0.020226537216828478,
      "grad_norm": 2.0581886768341064,
      "learning_rate": 9.716599190283402e-07,
      "loss": 0.7263915538787842,
      "step": 25
    },
    {
      "epoch": 0.040453074433656956,
      "grad_norm": 3.1348977088928223,
      "learning_rate": 1.9838056680161946e-06,
      "loss": 0.7004936218261719,
      "step": 50
    },
    {
      "epoch": 0.06067961165048544,
      "grad_norm": 7.536289215087891,
      "learning_rate": 2.995951417004049e-06,
      "loss": 0.6983621978759765,
      "step": 75
    },
    {
      "epoch": 0.08090614886731391,
      "grad_norm": 5.387710094451904,
      "learning_rate": 4.008097165991903e-06,
      "loss": 0.6408506774902344,
      "step": 100
    },
    {
      "epoch": 0.1011326860841424,
      "grad_norm": 4.4866790771484375,
      "learning_rate": 5.020242914979757e-06,
      "loss": 0.5292000961303711,
      "step": 125
    },
    {
      "epoch": 0.12135922330097088,
      "grad_norm": 5.9393534660339355,
      "learning_rate": 6.0323886639676124e-06,
      "loss": 0.4315451049804688,
      "step": 150
    },
    {
      "epoch": 0.14158576051779936,
      "grad_norm": 4.814444065093994,
      "learning_rate": 7.044534412955466e-06,
      "loss": 0.3674881362915039,
      "step": 175
    },
    {
      "epoch": 0.16181229773462782,
      "grad_norm": 2.463817834854126,
      "learning_rate": 8.056680161943322e-06,
      "loss": 0.29549776077270506,
      "step": 200
    },
    {
      "epoch": 0.1820388349514563,
      "grad_norm": 1.6270427703857422,
      "learning_rate": 9.068825910931175e-06,
      "loss": 0.19513965606689454,
      "step": 225
    },
    {
      "epoch": 0.2022653721682848,
      "grad_norm": 15.206025123596191,
      "learning_rate": 1.008097165991903e-05,
      "loss": 0.258267822265625,
      "step": 250
    },
    {
      "epoch": 0.22249190938511326,
      "grad_norm": 5.6893134117126465,
      "learning_rate": 1.1093117408906884e-05,
      "loss": 0.3252030563354492,
      "step": 275
    },
    {
      "epoch": 0.24271844660194175,
      "grad_norm": 15.90676498413086,
      "learning_rate": 1.2105263157894737e-05,
      "loss": 0.2558871841430664,
      "step": 300
    },
    {
      "epoch": 0.26294498381877024,
      "grad_norm": 1.5257281064987183,
      "learning_rate": 1.3117408906882592e-05,
      "loss": 0.20428178787231446,
      "step": 325
    },
    {
      "epoch": 0.28317152103559873,
      "grad_norm": 20.172571182250977,
      "learning_rate": 1.4129554655870446e-05,
      "loss": 0.2579817008972168,
      "step": 350
    },
    {
      "epoch": 0.30339805825242716,
      "grad_norm": 0.42674902081489563,
      "learning_rate": 1.5141700404858302e-05,
      "loss": 0.3013817977905273,
      "step": 375
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 0.6443495750427246,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 0.22500619888305665,
      "step": 400
    },
    {
      "epoch": 0.32362459546925565,
      "eval_accuracy": 0.9560384032339565,
      "eval_f1": 0.9716889033517735,
      "eval_loss": 0.16199301183223724,
      "eval_precision": 0.9539936102236422,
      "eval_recall": 0.9900530503978779,
      "eval_runtime": 34.745,
      "eval_samples_per_second": 56.958,
      "eval_steps_per_second": 3.569,
      "step": 400
    },
    {
      "epoch": 0.34385113268608414,
      "grad_norm": 12.952281951904297,
      "learning_rate": 1.716599190283401e-05,
      "loss": 0.23191883087158202,
      "step": 425
    },
    {
      "epoch": 0.3640776699029126,
      "grad_norm": 19.496694564819336,
      "learning_rate": 1.8178137651821864e-05,
      "loss": 0.26200836181640624,
      "step": 450
    },
    {
      "epoch": 0.3843042071197411,
      "grad_norm": 2.9963057041168213,
      "learning_rate": 1.9190283400809718e-05,
      "loss": 0.164515438079834,
      "step": 475
    },
    {
      "epoch": 0.4045307443365696,
      "grad_norm": 0.2180398553609848,
      "learning_rate": 1.999993769982229e-05,
      "loss": 0.2513391304016113,
      "step": 500
    },
    {
      "epoch": 0.42475728155339804,
      "grad_norm": 15.512799263000488,
      "learning_rate": 1.9997757275108847e-05,
      "loss": 0.30474105834960935,
      "step": 525
    },
    {
      "epoch": 0.4449838187702265,
      "grad_norm": 23.762832641601562,
      "learning_rate": 1.9992462617728763e-05,
      "loss": 0.214493408203125,
      "step": 550
    },
    {
      "epoch": 0.465210355987055,
      "grad_norm": 0.5767886638641357,
      "learning_rate": 1.9984055376931414e-05,
      "loss": 0.23740652084350586,
      "step": 575
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 3.6927132606506348,
      "learning_rate": 1.9972538171514525e-05,
      "loss": 0.2517130470275879,
      "step": 600
    },
    {
      "epoch": 0.5056634304207119,
      "grad_norm": 2.146721363067627,
      "learning_rate": 1.9957914589008405e-05,
      "loss": 0.21869991302490235,
      "step": 625
    },
    {
      "epoch": 0.5258899676375405,
      "grad_norm": 9.424388885498047,
      "learning_rate": 1.9940189184558487e-05,
      "loss": 0.2582887077331543,
      "step": 650
    },
    {
      "epoch": 0.5461165048543689,
      "grad_norm": 4.679764747619629,
      "learning_rate": 1.9919367479506413e-05,
      "loss": 0.2324064254760742,
      "step": 675
    },
    {
      "epoch": 0.5663430420711975,
      "grad_norm": 3.0119147300720215,
      "learning_rate": 1.989545595967018e-05,
      "loss": 0.23698102951049804,
      "step": 700
    },
    {
      "epoch": 0.5865695792880259,
      "grad_norm": 10.184627532958984,
      "learning_rate": 1.986846207332384e-05,
      "loss": 0.23535886764526368,
      "step": 725
    },
    {
      "epoch": 0.6067961165048543,
      "grad_norm": 51.39314651489258,
      "learning_rate": 1.9838394228877443e-05,
      "loss": 0.13176690101623534,
      "step": 750
    },
    {
      "epoch": 0.6270226537216829,
      "grad_norm": 18.441652297973633,
      "learning_rate": 1.980526179225785e-05,
      "loss": 0.2888069725036621,
      "step": 775
    },
    {
      "epoch": 0.6472491909385113,
      "grad_norm": 0.9691627621650696,
      "learning_rate": 1.97690750839913e-05,
      "loss": 0.29139081954956053,
      "step": 800
    },
    {
      "epoch": 0.6472491909385113,
      "eval_accuracy": 0.965133906013138,
      "eval_f1": 0.9773547751887102,
      "eval_loss": 0.14249353110790253,
      "eval_precision": 0.967511371020143,
      "eval_recall": 0.9874005305039788,
      "eval_runtime": 34.6417,
      "eval_samples_per_second": 57.128,
      "eval_steps_per_second": 3.58,
      "step": 800
    },
    {
      "epoch": 0.6674757281553398,
      "grad_norm": 7.6904096603393555,
      "learning_rate": 1.9729845375988694e-05,
      "loss": 0.1711592674255371,
      "step": 825
    },
    {
      "epoch": 0.6877022653721683,
      "grad_norm": 6.999588489532471,
      "learning_rate": 1.968758488803439e-05,
      "loss": 0.2283180809020996,
      "step": 850
    },
    {
      "epoch": 0.7079288025889967,
      "grad_norm": 6.149271488189697,
      "learning_rate": 1.9642306783979902e-05,
      "loss": 0.26335405349731444,
      "step": 875
    },
    {
      "epoch": 0.7281553398058253,
      "grad_norm": 9.907973289489746,
      "learning_rate": 1.959402516764339e-05,
      "loss": 0.1903523635864258,
      "step": 900
    },
    {
      "epoch": 0.7483818770226537,
      "grad_norm": 12.104832649230957,
      "learning_rate": 1.954275507841646e-05,
      "loss": 0.1740720748901367,
      "step": 925
    },
    {
      "epoch": 0.7686084142394822,
      "grad_norm": 2.8893074989318848,
      "learning_rate": 1.948851248657947e-05,
      "loss": 0.3097032928466797,
      "step": 950
    },
    {
      "epoch": 0.7888349514563107,
      "grad_norm": 0.07049937546253204,
      "learning_rate": 1.9431314288326925e-05,
      "loss": 0.14465970993041993,
      "step": 975
    },
    {
      "epoch": 0.8090614886731392,
      "grad_norm": 18.34374237060547,
      "learning_rate": 1.9371178300504394e-05,
      "loss": 0.22320323944091797,
      "step": 1000
    },
    {
      "epoch": 0.8292880258899676,
      "grad_norm": 5.898121356964111,
      "learning_rate": 1.930812325505871e-05,
      "loss": 0.09155179023742675,
      "step": 1025
    },
    {
      "epoch": 0.8495145631067961,
      "grad_norm": 9.933682441711426,
      "learning_rate": 1.9242168793203088e-05,
      "loss": 0.28490724563598635,
      "step": 1050
    },
    {
      "epoch": 0.8697411003236246,
      "grad_norm": 0.8073019981384277,
      "learning_rate": 1.9173335459299025e-05,
      "loss": 0.14135926246643066,
      "step": 1075
    },
    {
      "epoch": 0.889967637540453,
      "grad_norm": 23.247236251831055,
      "learning_rate": 1.9101644694456873e-05,
      "loss": 0.2752204895019531,
      "step": 1100
    },
    {
      "epoch": 0.9101941747572816,
      "grad_norm": 10.088881492614746,
      "learning_rate": 1.902711882985708e-05,
      "loss": 0.14879122734069825,
      "step": 1125
    },
    {
      "epoch": 0.93042071197411,
      "grad_norm": 0.5620437860488892,
      "learning_rate": 1.894978107979417e-05,
      "loss": 0.23470134735107423,
      "step": 1150
    },
    {
      "epoch": 0.9506472491909385,
      "grad_norm": 3.2695255279541016,
      "learning_rate": 1.886965553444568e-05,
      "loss": 0.19982004165649414,
      "step": 1175
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 19.842267990112305,
      "learning_rate": 1.8786767152368197e-05,
      "loss": 0.22285139083862304,
      "step": 1200
    },
    {
      "epoch": 0.970873786407767,
      "eval_accuracy": 0.9641232945932289,
      "eval_f1": 0.9767441860465116,
      "eval_loss": 0.14106644690036774,
      "eval_precision": 0.9650485436893204,
      "eval_recall": 0.9887267904509284,
      "eval_runtime": 34.6101,
      "eval_samples_per_second": 57.18,
      "eval_steps_per_second": 3.583,
      "step": 1200
    },
    {
      "epoch": 0.9911003236245954,
      "grad_norm": 17.05675506591797,
      "learning_rate": 1.8701141752722966e-05,
      "loss": 0.13252583503723145,
      "step": 1225
    },
    {
      "epoch": 1.0113268608414239,
      "grad_norm": 14.713388442993164,
      "learning_rate": 1.8612806007233382e-05,
      "loss": 0.13512847900390626,
      "step": 1250
    },
    {
      "epoch": 1.0315533980582525,
      "grad_norm": 16.86681365966797,
      "learning_rate": 1.8521787431876954e-05,
      "loss": 0.15763619422912598,
      "step": 1275
    },
    {
      "epoch": 1.051779935275081,
      "grad_norm": 0.6122269630432129,
      "learning_rate": 1.8428114378314237e-05,
      "loss": 0.18742298126220702,
      "step": 1300
    },
    {
      "epoch": 1.0720064724919094,
      "grad_norm": 6.803472995758057,
      "learning_rate": 1.8331816025057508e-05,
      "loss": 0.16315383911132814,
      "step": 1325
    },
    {
      "epoch": 1.0922330097087378,
      "grad_norm": 3.42342209815979,
      "learning_rate": 1.823292236838186e-05,
      "loss": 0.1462923812866211,
      "step": 1350
    },
    {
      "epoch": 1.1124595469255663,
      "grad_norm": 6.770485877990723,
      "learning_rate": 1.813146421298154e-05,
      "loss": 0.2096657371520996,
      "step": 1375
    },
    {
      "epoch": 1.132686084142395,
      "grad_norm": 6.892830848693848,
      "learning_rate": 1.802747316237454e-05,
      "loss": 0.1903732681274414,
      "step": 1400
    },
    {
      "epoch": 1.1529126213592233,
      "grad_norm": 1.7113957405090332,
      "learning_rate": 1.792098160905829e-05,
      "loss": 0.22764249801635741,
      "step": 1425
    },
    {
      "epoch": 1.1731391585760518,
      "grad_norm": 0.2954396903514862,
      "learning_rate": 1.7812022724419624e-05,
      "loss": 0.08850884437561035,
      "step": 1450
    },
    {
      "epoch": 1.1933656957928802,
      "grad_norm": 1.2150897979736328,
      "learning_rate": 1.7700630448402125e-05,
      "loss": 0.15286758422851562,
      "step": 1475
    },
    {
      "epoch": 1.2135922330097086,
      "grad_norm": 2.9238908290863037,
      "learning_rate": 1.758683947893406e-05,
      "loss": 0.14677520751953124,
      "step": 1500
    },
    {
      "epoch": 1.2338187702265373,
      "grad_norm": 9.288032531738281,
      "learning_rate": 1.747068526112022e-05,
      "loss": 0.13224196434020996,
      "step": 1525
    },
    {
      "epoch": 1.2540453074433657,
      "grad_norm": 21.540422439575195,
      "learning_rate": 1.735220397620101e-05,
      "loss": 0.08127058982849121,
      "step": 1550
    },
    {
      "epoch": 1.2742718446601942,
      "grad_norm": 0.07893255352973938,
      "learning_rate": 1.7231432530282246e-05,
      "loss": 0.10571711540222167,
      "step": 1575
    },
    {
      "epoch": 1.2944983818770226,
      "grad_norm": 0.5910708904266357,
      "learning_rate": 1.7108408542839146e-05,
      "loss": 0.1872186279296875,
      "step": 1600
    },
    {
      "epoch": 1.2944983818770226,
      "eval_accuracy": 0.9671551288529561,
      "eval_f1": 0.9785549323655559,
      "eval_loss": 0.1455843597650528,
      "eval_precision": 0.9737360472751149,
      "eval_recall": 0.98342175066313,
      "eval_runtime": 34.8064,
      "eval_samples_per_second": 56.857,
      "eval_steps_per_second": 3.563,
      "step": 1600
    },
    {
      "epoch": 1.3147249190938513,
      "grad_norm": 0.48737797141075134,
      "learning_rate": 1.698317033499813e-05,
      "loss": 0.1566315174102783,
      "step": 1625
    },
    {
      "epoch": 1.3349514563106797,
      "grad_norm": 17.18292808532715,
      "learning_rate": 1.6855756917600057e-05,
      "loss": 0.15158571243286134,
      "step": 1650
    },
    {
      "epoch": 1.3551779935275081,
      "grad_norm": 10.572613716125488,
      "learning_rate": 1.6726207979048604e-05,
      "loss": 0.16150398254394532,
      "step": 1675
    },
    {
      "epoch": 1.3754045307443366,
      "grad_norm": 0.1977110058069229,
      "learning_rate": 1.6594563872947613e-05,
      "loss": 0.09849663734436036,
      "step": 1700
    },
    {
      "epoch": 1.395631067961165,
      "grad_norm": 2.6522152423858643,
      "learning_rate": 1.6460865605531214e-05,
      "loss": 0.17041929244995116,
      "step": 1725
    },
    {
      "epoch": 1.4158576051779934,
      "grad_norm": 0.18808063864707947,
      "learning_rate": 1.6325154822890663e-05,
      "loss": 0.1783625602722168,
      "step": 1750
    },
    {
      "epoch": 1.436084142394822,
      "grad_norm": 33.89837646484375,
      "learning_rate": 1.618747379800188e-05,
      "loss": 0.15096524238586426,
      "step": 1775
    },
    {
      "epoch": 1.4563106796116505,
      "grad_norm": 10.100881576538086,
      "learning_rate": 1.6047865417557695e-05,
      "loss": 0.2288828659057617,
      "step": 1800
    },
    {
      "epoch": 1.476537216828479,
      "grad_norm": 7.704436302185059,
      "learning_rate": 1.5906373168608952e-05,
      "loss": 0.22033729553222656,
      "step": 1825
    },
    {
      "epoch": 1.4967637540453074,
      "grad_norm": 9.382397651672363,
      "learning_rate": 1.576304112501858e-05,
      "loss": 0.15806819915771483,
      "step": 1850
    },
    {
      "epoch": 1.516990291262136,
      "grad_norm": 6.415167808532715,
      "learning_rate": 1.5617913933732892e-05,
      "loss": 0.16990087509155274,
      "step": 1875
    },
    {
      "epoch": 1.5372168284789645,
      "grad_norm": 8.820036888122559,
      "learning_rate": 1.5471036800874375e-05,
      "loss": 0.1730282974243164,
      "step": 1900
    },
    {
      "epoch": 1.557443365695793,
      "grad_norm": 28.52211570739746,
      "learning_rate": 1.5322455477660274e-05,
      "loss": 0.15791168212890624,
      "step": 1925
    },
    {
      "epoch": 1.5776699029126213,
      "grad_norm": 15.133056640625,
      "learning_rate": 1.5172216246151426e-05,
      "loss": 0.24158744812011718,
      "step": 1950
    },
    {
      "epoch": 1.5978964401294498,
      "grad_norm": 13.767041206359863,
      "learning_rate": 1.50203659048357e-05,
      "loss": 0.07609220504760743,
      "step": 1975
    },
    {
      "epoch": 1.6181229773462782,
      "grad_norm": 2.377875328063965,
      "learning_rate": 1.4866951754050605e-05,
      "loss": 0.2856024742126465,
      "step": 2000
    },
    {
      "epoch": 1.6181229773462782,
      "eval_accuracy": 0.9671551288529561,
      "eval_f1": 0.978369384359401,
      "eval_loss": 0.12881171703338623,
      "eval_precision": 0.9819639278557114,
      "eval_recall": 0.9748010610079576,
      "eval_runtime": 34.7861,
      "eval_samples_per_second": 56.891,
      "eval_steps_per_second": 3.565,
      "step": 2000
    },
    {
      "epoch": 1.6383495145631068,
      "grad_norm": 1.8338792324066162,
      "learning_rate": 1.4712021581249534e-05,
      "loss": 0.18048593521118164,
      "step": 2025
    },
    {
      "epoch": 1.6585760517799353,
      "grad_norm": 0.2766644060611725,
      "learning_rate": 1.4555623646116325e-05,
      "loss": 0.1664619827270508,
      "step": 2050
    },
    {
      "epoch": 1.6788025889967637,
      "grad_norm": 2.5218565464019775,
      "learning_rate": 1.4397806665532693e-05,
      "loss": 0.16300722122192382,
      "step": 2075
    },
    {
      "epoch": 1.6990291262135924,
      "grad_norm": 0.9285559058189392,
      "learning_rate": 1.4238619798403266e-05,
      "loss": 0.14837112426757812,
      "step": 2100
    },
    {
      "epoch": 1.7192556634304208,
      "grad_norm": 10.178064346313477,
      "learning_rate": 1.4078112630342891e-05,
      "loss": 0.15740616798400878,
      "step": 2125
    },
    {
      "epoch": 1.7394822006472492,
      "grad_norm": 19.79058074951172,
      "learning_rate": 1.3916335158231101e-05,
      "loss": 0.22019144058227538,
      "step": 2150
    },
    {
      "epoch": 1.7597087378640777,
      "grad_norm": 8.479653358459473,
      "learning_rate": 1.3753337774638397e-05,
      "loss": 0.10831342697143555,
      "step": 2175
    },
    {
      "epoch": 1.779935275080906,
      "grad_norm": 0.27186402678489685,
      "learning_rate": 1.3589171252129329e-05,
      "loss": 0.14887014389038086,
      "step": 2200
    },
    {
      "epoch": 1.8001618122977345,
      "grad_norm": 5.499264240264893,
      "learning_rate": 1.3423886727447176e-05,
      "loss": 0.19739471435546874,
      "step": 2225
    },
    {
      "epoch": 1.820388349514563,
      "grad_norm": 2.787201166152954,
      "learning_rate": 1.325753568558521e-05,
      "loss": 0.19788772583007813,
      "step": 2250
    },
    {
      "epoch": 1.8406148867313916,
      "grad_norm": 3.942160129547119,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.11929478645324706,
      "step": 2275
    },
    {
      "epoch": 1.86084142394822,
      "grad_norm": 0.19959710538387299,
      "learning_rate": 1.2921841635218082e-05,
      "loss": 0.09196714401245117,
      "step": 2300
    },
    {
      "epoch": 1.8810679611650487,
      "grad_norm": 0.05811980366706848,
      "learning_rate": 1.275260319310205e-05,
      "loss": 0.2154999542236328,
      "step": 2325
    },
    {
      "epoch": 1.9012944983818771,
      "grad_norm": 1.1418527364730835,
      "learning_rate": 1.2582507334012755e-05,
      "loss": 0.1920686912536621,
      "step": 2350
    },
    {
      "epoch": 1.9215210355987056,
      "grad_norm": 3.8587708473205566,
      "learning_rate": 1.2411607041641062e-05,
      "loss": 0.15039829254150391,
      "step": 2375
    },
    {
      "epoch": 1.941747572815534,
      "grad_norm": 0.10201486200094223,
      "learning_rate": 1.2239955550253277e-05,
      "loss": 0.1844302558898926,
      "step": 2400
    },
    {
      "epoch": 1.941747572815534,
      "eval_accuracy": 0.9631126831733199,
      "eval_f1": 0.9760890926957091,
      "eval_loss": 0.14186660945415497,
      "eval_precision": 0.9644012944983819,
      "eval_recall": 0.9880636604774535,
      "eval_runtime": 34.6039,
      "eval_samples_per_second": 57.19,
      "eval_steps_per_second": 3.583,
      "step": 2400
    }
  ],
  "logging_steps": 25,
  "max_steps": 4944,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 400,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.010030719315968e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}