{
  "best_global_step": 3500,
  "best_metric": 1.2840659618377686,
  "best_model_checkpoint": "/home/hyang45/se_git_repo/final_addtional_exp_mia_trans/save/new/microsoft_CodeGPT-small-java/1/checkpoint-3500",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 4975,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05027652086475616,
      "grad_norm": 0.38967880606651306,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 1.4062,
      "step": 50
    },
    {
      "epoch": 0.10055304172951232,
      "grad_norm": 0.25512877106666565,
      "learning_rate": 7.92e-05,
      "loss": 0.9927,
      "step": 100
    },
    {
      "epoch": 0.15082956259426847,
      "grad_norm": 0.2808470129966736,
      "learning_rate": 7.998005947565195e-05,
      "loss": 0.8156,
      "step": 150
    },
    {
      "epoch": 0.20110608345902464,
      "grad_norm": 0.2150183469057083,
      "learning_rate": 7.991862264348792e-05,
      "loss": 0.7848,
      "step": 200
    },
    {
      "epoch": 0.2513826043237808,
      "grad_norm": 0.2027038335800171,
      "learning_rate": 7.981574497732115e-05,
      "loss": 0.764,
      "step": 250
    },
    {
      "epoch": 0.30165912518853694,
      "grad_norm": 0.23373721539974213,
      "learning_rate": 7.967153327783776e-05,
      "loss": 0.7302,
      "step": 300
    },
    {
      "epoch": 0.35193564605329314,
      "grad_norm": 0.18324315547943115,
      "learning_rate": 7.948613725594216e-05,
      "loss": 0.7287,
      "step": 350
    },
    {
      "epoch": 0.4022121669180493,
      "grad_norm": 0.21186716854572296,
      "learning_rate": 7.925974937733732e-05,
      "loss": 0.7011,
      "step": 400
    },
    {
      "epoch": 0.45248868778280543,
      "grad_norm": 0.3749410808086395,
      "learning_rate": 7.899260466271975e-05,
      "loss": 0.7029,
      "step": 450
    },
    {
      "epoch": 0.5027652086475616,
      "grad_norm": 0.1961645632982254,
      "learning_rate": 7.868498044379681e-05,
      "loss": 0.6967,
      "step": 500
    },
    {
      "epoch": 0.5027652086475616,
      "eval_accuracy": 0.7520552872875925,
      "eval_loss": 1.3162076473236084,
      "eval_runtime": 85.0292,
      "eval_samples_per_second": 57.91,
      "eval_steps_per_second": 2.423,
      "step": 500
    },
    {
      "epoch": 0.5530417295123178,
      "grad_norm": 0.17420420050621033,
      "learning_rate": 7.833719607537954e-05,
      "loss": 0.6851,
      "step": 550
    },
    {
      "epoch": 0.6033182503770739,
      "grad_norm": 0.2493220567703247,
      "learning_rate": 7.794961260384997e-05,
      "loss": 0.671,
      "step": 600
    },
    {
      "epoch": 0.6535947712418301,
      "grad_norm": 0.20172835886478424,
      "learning_rate": 7.752263239234692e-05,
      "loss": 0.662,
      "step": 650
    },
    {
      "epoch": 0.7038712921065863,
      "grad_norm": 0.25561460852622986,
      "learning_rate": 7.705669870305975e-05,
      "loss": 0.6763,
      "step": 700
    },
    {
      "epoch": 0.7541478129713424,
      "grad_norm": 0.19745612144470215,
      "learning_rate": 7.655229523706317e-05,
      "loss": 0.6545,
      "step": 750
    },
    {
      "epoch": 0.8044243338360986,
      "grad_norm": 0.1649468094110489,
      "learning_rate": 7.600994563217132e-05,
      "loss": 0.6463,
      "step": 800
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.20483672618865967,
      "learning_rate": 7.543021291933214e-05,
      "loss": 0.6625,
      "step": 850
    },
    {
      "epoch": 0.9049773755656109,
      "grad_norm": 0.1755620539188385,
      "learning_rate": 7.481369893812647e-05,
      "loss": 0.6629,
      "step": 900
    },
    {
      "epoch": 0.9552538964303671,
      "grad_norm": 0.1850636750459671,
      "learning_rate": 7.416104371197853e-05,
      "loss": 0.6329,
      "step": 950
    },
    {
      "epoch": 1.0050276520864756,
      "grad_norm": 0.17517416179180145,
      "learning_rate": 7.347292478372667e-05,
      "loss": 0.6481,
      "step": 1000
    },
    {
      "epoch": 1.0050276520864756,
      "eval_accuracy": 0.7550630780433458,
      "eval_loss": 1.3002119064331055,
      "eval_runtime": 91.3368,
      "eval_samples_per_second": 53.91,
      "eval_steps_per_second": 2.255,
      "step": 1000
    },
    {
      "epoch": 1.0553041729512318,
      "grad_norm": 0.14569388329982758,
      "learning_rate": 7.275005651224378e-05,
      "loss": 0.6276,
      "step": 1050
    },
    {
      "epoch": 1.105580693815988,
      "grad_norm": 0.1603846698999405,
      "learning_rate": 7.199318933083797e-05,
      "loss": 0.6346,
      "step": 1100
    },
    {
      "epoch": 1.155857214680744,
      "grad_norm": 0.20617897808551788,
      "learning_rate": 7.120310896820298e-05,
      "loss": 0.6191,
      "step": 1150
    },
    {
      "epoch": 1.2061337355455002,
      "grad_norm": 0.2762608230113983,
      "learning_rate": 7.038063563272751e-05,
      "loss": 0.63,
      "step": 1200
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 0.13912968337535858,
      "learning_rate": 6.952662316100984e-05,
      "loss": 0.6265,
      "step": 1250
    },
    {
      "epoch": 1.3066867772750126,
      "grad_norm": 0.27741900086402893,
      "learning_rate": 6.864195813146212e-05,
      "loss": 0.6204,
      "step": 1300
    },
    {
      "epoch": 1.3569632981397688,
      "grad_norm": 0.15955646336078644,
      "learning_rate": 6.772755894392405e-05,
      "loss": 0.6077,
      "step": 1350
    },
    {
      "epoch": 1.4072398190045248,
      "grad_norm": 0.15095743536949158,
      "learning_rate": 6.678437486624186e-05,
      "loss": 0.6361,
      "step": 1400
    },
    {
      "epoch": 1.457516339869281,
      "grad_norm": 0.14820362627506256,
      "learning_rate": 6.58133850488023e-05,
      "loss": 0.6286,
      "step": 1450
    },
    {
      "epoch": 1.5077928607340372,
      "grad_norm": 0.16185027360916138,
      "learning_rate": 6.481559750804423e-05,
      "loss": 0.6091,
      "step": 1500
    },
    {
      "epoch": 1.5077928607340372,
      "eval_accuracy": 0.7550170211853606,
      "eval_loss": 1.2964880466461182,
      "eval_runtime": 85.294,
      "eval_samples_per_second": 57.73,
      "eval_steps_per_second": 2.415,
      "step": 1500
    },
    {
      "epoch": 1.5580693815987934,
      "grad_norm": 0.16229036450386047,
      "learning_rate": 6.379204808000379e-05,
      "loss": 0.6024,
      "step": 1550
    },
    {
      "epoch": 1.6083459024635496,
      "grad_norm": 0.14892268180847168,
      "learning_rate": 6.274379934497889e-05,
      "loss": 0.605,
      "step": 1600
    },
    {
      "epoch": 1.6586224233283056,
      "grad_norm": 0.15874284505844116,
      "learning_rate": 6.167193952442972e-05,
      "loss": 0.5853,
      "step": 1650
    },
    {
      "epoch": 1.708898944193062,
      "grad_norm": 0.16238285601139069,
      "learning_rate": 6.057758135126026e-05,
      "loss": 0.6054,
      "step": 1700
    },
    {
      "epoch": 1.759175465057818,
      "grad_norm": 0.16057848930358887,
      "learning_rate": 5.946186091465375e-05,
      "loss": 0.6252,
      "step": 1750
    },
    {
      "epoch": 1.8094519859225742,
      "grad_norm": 0.2041744887828827,
      "learning_rate": 5.8325936480661065e-05,
      "loss": 0.5942,
      "step": 1800
    },
    {
      "epoch": 1.8597285067873304,
      "grad_norm": 0.23550090193748474,
      "learning_rate": 5.717098728976677e-05,
      "loss": 0.6056,
      "step": 1850
    },
    {
      "epoch": 1.9100050276520864,
      "grad_norm": 0.2757298946380615,
      "learning_rate": 5.599821233268077e-05,
      "loss": 0.6023,
      "step": 1900
    },
    {
      "epoch": 1.9602815485168428,
      "grad_norm": 0.1491357684135437,
      "learning_rate": 5.4808829105626623e-05,
      "loss": 0.6097,
      "step": 1950
    },
    {
      "epoch": 2.010055304172951,
      "grad_norm": 0.21005308628082275,
      "learning_rate": 5.360407234641879e-05,
      "loss": 0.6091,
      "step": 2000
    },
    {
      "epoch": 2.010055304172951,
      "eval_accuracy": 0.7556497074198393,
      "eval_loss": 1.289443016052246,
      "eval_runtime": 85.2093,
      "eval_samples_per_second": 57.787,
      "eval_steps_per_second": 2.418,
      "step": 2000
    },
    {
      "epoch": 2.060331825037707,
      "grad_norm": 0.15782801806926727,
      "learning_rate": 5.238519275264064e-05,
      "loss": 0.5902,
      "step": 2050
    },
    {
      "epoch": 2.1106083459024636,
      "grad_norm": 0.1624271422624588,
      "learning_rate": 5.1153455683254215e-05,
      "loss": 0.5942,
      "step": 2100
    },
    {
      "epoch": 2.1608848667672196,
      "grad_norm": 0.16978579759597778,
      "learning_rate": 4.9910139844989574e-05,
      "loss": 0.5845,
      "step": 2150
    },
    {
      "epoch": 2.211161387631976,
      "grad_norm": 0.14723461866378784,
      "learning_rate": 4.865653596487719e-05,
      "loss": 0.5954,
      "step": 2200
    },
    {
      "epoch": 2.261437908496732,
      "grad_norm": 0.16163045167922974,
      "learning_rate": 4.739394545030192e-05,
      "loss": 0.5821,
      "step": 2250
    },
    {
      "epoch": 2.311714429361488,
      "grad_norm": 0.22584794461727142,
      "learning_rate": 4.6123679037969156e-05,
      "loss": 0.5811,
      "step": 2300
    },
    {
      "epoch": 2.3619909502262444,
      "grad_norm": 0.16639545559883118,
      "learning_rate": 4.484705543318603e-05,
      "loss": 0.5923,
      "step": 2350
    },
    {
      "epoch": 2.4122674710910004,
      "grad_norm": 0.14507165551185608,
      "learning_rate": 4.356539994087004e-05,
      "loss": 0.5758,
      "step": 2400
    },
    {
      "epoch": 2.462543991955757,
      "grad_norm": 0.17524458467960358,
      "learning_rate": 4.228004308970651e-05,
      "loss": 0.5793,
      "step": 2450
    },
    {
      "epoch": 2.5128205128205128,
      "grad_norm": 0.20955400168895721,
      "learning_rate": 4.099231925088303e-05,
      "loss": 0.5805,
      "step": 2500
    },
    {
      "epoch": 2.5128205128205128,
      "eval_accuracy": 0.7555808206538009,
      "eval_loss": 1.2918362617492676,
      "eval_runtime": 84.9046,
      "eval_samples_per_second": 57.994,
      "eval_steps_per_second": 2.426,
      "step": 2500
    },
    {
      "epoch": 2.5630970336852688,
      "grad_norm": 0.15553168952465057,
      "learning_rate": 3.970356525283485e-05,
      "loss": 0.5902,
      "step": 2550
    },
    {
      "epoch": 2.613373554550025,
      "grad_norm": 0.24212880432605743,
      "learning_rate": 3.841511899343937e-05,
      "loss": 0.5896,
      "step": 2600
    },
    {
      "epoch": 2.663650075414781,
      "grad_norm": 0.14325997233390808,
      "learning_rate": 3.712831805110037e-05,
      "loss": 0.5821,
      "step": 2650
    },
    {
      "epoch": 2.7139265962795376,
      "grad_norm": 0.16522951424121857,
      "learning_rate": 3.584449829616395e-05,
      "loss": 0.5842,
      "step": 2700
    },
    {
      "epoch": 2.7642031171442936,
      "grad_norm": 0.12420392781496048,
      "learning_rate": 3.456499250410759e-05,
      "loss": 0.5844,
      "step": 2750
    },
    {
      "epoch": 2.8144796380090495,
      "grad_norm": 0.17248398065567017,
      "learning_rate": 3.3291128971942105e-05,
      "loss": 0.587,
      "step": 2800
    },
    {
      "epoch": 2.864756158873806,
      "grad_norm": 0.14520220458507538,
      "learning_rate": 3.2024230139262936e-05,
      "loss": 0.5837,
      "step": 2850
    },
    {
      "epoch": 2.915032679738562,
      "grad_norm": 0.14959931373596191,
      "learning_rate": 3.076561121538211e-05,
      "loss": 0.5827,
      "step": 2900
    },
    {
      "epoch": 2.9653092006033184,
      "grad_norm": 0.2161024659872055,
      "learning_rate": 2.9516578813966154e-05,
      "loss": 0.5717,
      "step": 2950
    },
    {
      "epoch": 3.015082956259427,
      "grad_norm": 0.14117109775543213,
      "learning_rate": 2.827842959659771e-05,
      "loss": 0.557,
      "step": 3000
    },
    {
      "epoch": 3.015082956259427,
      "eval_accuracy": 0.7559059979528521,
      "eval_loss": 1.2862486839294434,
      "eval_runtime": 85.3029,
      "eval_samples_per_second": 57.724,
      "eval_steps_per_second": 2.415,
      "step": 3000
    },
    {
      "epoch": 3.065359477124183,
      "grad_norm": 0.180222749710083,
      "learning_rate": 2.7052448926668305e-05,
      "loss": 0.5686,
      "step": 3050
    },
    {
      "epoch": 3.115635997988939,
      "grad_norm": 0.2005385011434555,
      "learning_rate": 2.5839909535000498e-05,
      "loss": 0.5682,
      "step": 3100
    },
    {
      "epoch": 3.165912518853695,
      "grad_norm": 0.18873438239097595,
      "learning_rate": 2.4642070198584236e-05,
      "loss": 0.5816,
      "step": 3150
    },
    {
      "epoch": 3.2161890397184516,
      "grad_norm": 0.18745166063308716,
      "learning_rate": 2.3460174433798927e-05,
      "loss": 0.5739,
      "step": 3200
    },
    {
      "epoch": 3.2664655605832076,
      "grad_norm": 0.17067401111125946,
      "learning_rate": 2.2295449205478362e-05,
      "loss": 0.5864,
      "step": 3250
    },
    {
      "epoch": 3.3167420814479636,
      "grad_norm": 0.16623741388320923,
      "learning_rate": 2.114910365315819e-05,
      "loss": 0.5795,
      "step": 3300
    },
    {
      "epoch": 3.36701860231272,
      "grad_norm": 0.15764974057674408,
      "learning_rate": 2.0022327835828362e-05,
      "loss": 0.5704,
      "step": 3350
    },
    {
      "epoch": 3.417295123177476,
      "grad_norm": 0.14753426611423492,
      "learning_rate": 1.891629149649378e-05,
      "loss": 0.5633,
      "step": 3400
    },
    {
      "epoch": 3.4675716440422324,
      "grad_norm": 0.3436726927757263,
      "learning_rate": 1.7832142847825763e-05,
      "loss": 0.5753,
      "step": 3450
    },
    {
      "epoch": 3.5178481649069884,
      "grad_norm": 0.1702040284872055,
      "learning_rate": 1.677100738016461e-05,
      "loss": 0.5513,
      "step": 3500
    },
    {
      "epoch": 3.5178481649069884,
      "eval_accuracy": 0.7564910391618287,
      "eval_loss": 1.2840659618377686,
      "eval_runtime": 85.0647,
      "eval_samples_per_second": 57.885,
      "eval_steps_per_second": 2.422,
      "step": 3500
    },
    {
      "epoch": 3.5681246857717444,
      "grad_norm": 0.18295463919639587,
      "learning_rate": 1.573398669311116e-05,
      "loss": 0.5823,
      "step": 3550
    },
    {
      "epoch": 3.6184012066365008,
      "grad_norm": 0.17615950107574463,
      "learning_rate": 1.472215735192e-05,
      "loss": 0.5645,
      "step": 3600
    },
    {
      "epoch": 3.6686777275012568,
      "grad_norm": 0.2151349037885666,
      "learning_rate": 1.373656976988175e-05,
      "loss": 0.5725,
      "step": 3650
    },
    {
      "epoch": 3.718954248366013,
      "grad_norm": 0.13829338550567627,
      "learning_rate": 1.2778247117854439e-05,
      "loss": 0.5576,
      "step": 3700
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.16056522727012634,
      "learning_rate": 1.1848184262076306e-05,
      "loss": 0.5768,
      "step": 3750
    },
    {
      "epoch": 3.819507290095525,
      "grad_norm": 0.18423378467559814,
      "learning_rate": 1.0947346731362357e-05,
      "loss": 0.5681,
      "step": 3800
    },
    {
      "epoch": 3.8697838109602816,
      "grad_norm": 0.15498067438602448,
      "learning_rate": 1.0076669714757261e-05,
      "loss": 0.5507,
      "step": 3850
    },
    {
      "epoch": 3.9200603318250375,
      "grad_norm": 0.15752053260803223,
      "learning_rate": 9.237057090684773e-06,
      "loss": 0.5641,
      "step": 3900
    },
    {
      "epoch": 3.970336852689794,
      "grad_norm": 0.14952270686626434,
      "learning_rate": 8.42938048860198e-06,
      "loss": 0.5704,
      "step": 3950
    },
    {
      "epoch": 4.020110608345902,
      "grad_norm": 0.13633842766284943,
      "learning_rate": 7.654478384131975e-06,
      "loss": 0.5468,
      "step": 4000
    },
    {
      "epoch": 4.020110608345902,
      "eval_accuracy": 0.7562369323591513,
      "eval_loss": 1.2848825454711914,
      "eval_runtime": 85.0878,
      "eval_samples_per_second": 57.87,
      "eval_steps_per_second": 2.421,
      "step": 4000
    },
    {
      "epoch": 4.070387129210658,
      "grad_norm": 0.1506165862083435,
      "learning_rate": 6.913155228614838e-06,
      "loss": 0.5674,
      "step": 4050
    },
    {
      "epoch": 4.120663650075414,
      "grad_norm": 0.15265598893165588,
      "learning_rate": 6.206180613980266e-06,
      "loss": 0.5625,
      "step": 4100
    },
    {
      "epoch": 4.170940170940171,
      "grad_norm": 0.13488344848155975,
      "learning_rate": 5.534288473808831e-06,
      "loss": 0.5624,
      "step": 4150
    },
    {
      "epoch": 4.221216691804927,
      "grad_norm": 0.13856124877929688,
      "learning_rate": 4.898176321411478e-06,
      "loss": 0.5628,
      "step": 4200
    },
    {
      "epoch": 4.271493212669683,
      "grad_norm": 0.18089675903320312,
      "learning_rate": 4.2985045257180415e-06,
      "loss": 0.5731,
      "step": 4250
    },
    {
      "epoch": 4.321769733534439,
      "grad_norm": 0.14551880955696106,
      "learning_rate": 3.735895625726493e-06,
      "loss": 0.5562,
      "step": 4300
    },
    {
      "epoch": 4.372046254399196,
      "grad_norm": 0.13140977919101715,
      "learning_rate": 3.210933684224804e-06,
      "loss": 0.5729,
      "step": 4350
    },
    {
      "epoch": 4.422322775263952,
      "grad_norm": 0.16188330948352814,
      "learning_rate": 2.7241636814561514e-06,
      "loss": 0.5633,
      "step": 4400
    },
    {
      "epoch": 4.472599296128708,
      "grad_norm": 0.14776812493801117,
      "learning_rate": 2.2760909493570127e-06,
      "loss": 0.5677,
      "step": 4450
    },
    {
      "epoch": 4.522875816993464,
      "grad_norm": 0.15746714174747467,
      "learning_rate": 1.8671806469554976e-06,
      "loss": 0.5513,
      "step": 4500
    },
    {
      "epoch": 4.522875816993464,
      "eval_accuracy": 0.7559050053481541,
      "eval_loss": 1.2894773483276367,
      "eval_runtime": 85.2306,
      "eval_samples_per_second": 57.773,
      "eval_steps_per_second": 2.417,
      "step": 4500
    },
    {
      "epoch": 4.57315233785822,
      "grad_norm": 0.1549079418182373,
      "learning_rate": 1.497857277474455e-06,
      "loss": 0.5727,
      "step": 4550
    },
    {
      "epoch": 4.623428858722976,
      "grad_norm": 0.1668921858072281,
      "learning_rate": 1.1685042476407404e-06,
      "loss": 0.5641,
      "step": 4600
    },
    {
      "epoch": 4.673705379587733,
      "grad_norm": 0.134994775056839,
      "learning_rate": 8.794634696580551e-07,
      "loss": 0.5597,
      "step": 4650
    },
    {
      "epoch": 4.723981900452489,
      "grad_norm": 0.1448977142572403,
      "learning_rate": 6.310350062567194e-07,
      "loss": 0.5672,
      "step": 4700
    },
    {
      "epoch": 4.774258421317245,
      "grad_norm": 0.16990165412425995,
      "learning_rate": 4.2347675918863463e-07,
      "loss": 0.5669,
      "step": 4750
    },
    {
      "epoch": 4.824534942182001,
      "grad_norm": 0.16192808747291565,
      "learning_rate": 2.5700420149102233e-07,
      "loss": 0.5778,
      "step": 4800
    },
    {
      "epoch": 4.874811463046758,
      "grad_norm": 0.154259592294693,
      "learning_rate": 1.3179015379677585e-07,
      "loss": 0.5774,
      "step": 4850
    },
    {
      "epoch": 4.925087983911514,
      "grad_norm": 0.16326895356178284,
      "learning_rate": 4.796460492368926e-08,
      "loss": 0.5586,
      "step": 4900
    },
    {
      "epoch": 4.97536450477627,
      "grad_norm": 0.18583731353282928,
      "learning_rate": 5.614576928785198e-09,
      "loss": 0.5682,
      "step": 4950
    },
    {
      "epoch": 5.0,
      "step": 4975,
      "total_flos": 8.315357626368e+16,
      "train_loss": 0.615904873986939,
      "train_runtime": 4775.4033,
      "train_samples_per_second": 33.321,
      "train_steps_per_second": 1.042
    }
  ],
  "logging_steps": 50,
  "max_steps": 4975,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.315357626368e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}