{
  "best_metric": 1.0747156143188477,
  "best_model_checkpoint": "/root/finetuning_executions/finetuning_01_codet5p_src_fm_fc_dctx/checkpoint-17548",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 87740,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 1.5826328992843628,
      "learning_rate": 2.4750000000000002e-05,
      "loss": 1.404,
      "step": 400
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.5471534729003906,
      "learning_rate": 4.975e-05,
      "loss": 1.1707,
      "step": 800
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.150067687034607,
      "learning_rate": 4.977225672877847e-05,
      "loss": 1.1319,
      "step": 1200
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.197001338005066,
      "learning_rate": 4.9542213020473895e-05,
      "loss": 1.1168,
      "step": 1600
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.0678050518035889,
      "learning_rate": 4.931216931216932e-05,
      "loss": 1.098,
      "step": 2000
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.196992039680481,
      "learning_rate": 4.9082125603864734e-05,
      "loss": 1.0811,
      "step": 2400
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.0403153896331787,
      "learning_rate": 4.885208189556016e-05,
      "loss": 1.0642,
      "step": 2800
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.290574073791504,
      "learning_rate": 4.862203818725558e-05,
      "loss": 1.0573,
      "step": 3200
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1538596153259277,
      "learning_rate": 4.8391994478951e-05,
      "loss": 1.0422,
      "step": 3600
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.1622496843338013,
      "learning_rate": 4.8161950770646426e-05,
      "loss": 1.0302,
      "step": 4000
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.2310576438903809,
      "learning_rate": 4.793190706234185e-05,
      "loss": 1.0327,
      "step": 4400
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.7041934728622437,
      "learning_rate": 4.770186335403727e-05,
      "loss": 1.016,
      "step": 4800
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.2586933374404907,
      "learning_rate": 4.747181964573269e-05,
      "loss": 1.022,
      "step": 5200
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9497622847557068,
      "learning_rate": 4.724177593742811e-05,
      "loss": 1.0008,
      "step": 5600
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.1111699342727661,
      "learning_rate": 4.7011732229123534e-05,
      "loss": 0.9878,
      "step": 6000
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.177351951599121,
      "learning_rate": 4.678168852081896e-05,
      "loss": 0.9804,
      "step": 6400
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.1454102993011475,
      "learning_rate": 4.655164481251438e-05,
      "loss": 0.9739,
      "step": 6800
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.0769121646881104,
      "learning_rate": 4.63216011042098e-05,
      "loss": 0.9873,
      "step": 7200
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.2958855628967285,
      "learning_rate": 4.609155739590522e-05,
      "loss": 0.9615,
      "step": 7600
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.1914528608322144,
      "learning_rate": 4.586151368760065e-05,
      "loss": 0.9637,
      "step": 8000
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.036251425743103,
      "learning_rate": 4.563146997929607e-05,
      "loss": 0.9651,
      "step": 8400
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.2706526517868042,
      "learning_rate": 4.5401426270991495e-05,
      "loss": 0.9538,
      "step": 8800
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.1763725280761719,
      "learning_rate": 4.517138256268692e-05,
      "loss": 0.9481,
      "step": 9200
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.0269743204116821,
      "learning_rate": 4.4941338854382334e-05,
      "loss": 0.9406,
      "step": 9600
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.1849923133850098,
      "learning_rate": 4.471129514607776e-05,
      "loss": 0.9325,
      "step": 10000
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.289588451385498,
      "learning_rate": 4.448125143777318e-05,
      "loss": 0.9198,
      "step": 10400
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.0682235956192017,
      "learning_rate": 4.42512077294686e-05,
      "loss": 0.938,
      "step": 10800
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.0467722415924072,
      "learning_rate": 4.4021164021164026e-05,
      "loss": 0.9191,
      "step": 11200
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.0143468379974365,
      "learning_rate": 4.379112031285945e-05,
      "loss": 0.9193,
      "step": 11600
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.0179190635681152,
      "learning_rate": 4.3561076604554865e-05,
      "loss": 0.9109,
      "step": 12000
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.0898582935333252,
      "learning_rate": 4.333103289625029e-05,
      "loss": 0.9173,
      "step": 12400
    },
    {
      "epoch": 0.73,
      "grad_norm": 1.0596779584884644,
      "learning_rate": 4.310098918794571e-05,
      "loss": 0.9236,
      "step": 12800
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.1058505773544312,
      "learning_rate": 4.2870945479641134e-05,
      "loss": 0.9006,
      "step": 13200
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.2219908237457275,
      "learning_rate": 4.264090177133656e-05,
      "loss": 0.9,
      "step": 13600
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9692860245704651,
      "learning_rate": 4.241143317230274e-05,
      "loss": 0.9014,
      "step": 14000
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.1939465999603271,
      "learning_rate": 4.218138946399816e-05,
      "loss": 0.8905,
      "step": 14400
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.2843443155288696,
      "learning_rate": 4.1951345755693586e-05,
      "loss": 0.8988,
      "step": 14800
    },
    {
      "epoch": 0.87,
      "grad_norm": 1.074813723564148,
      "learning_rate": 4.1721302047389e-05,
      "loss": 0.8979,
      "step": 15200
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.9322890043258667,
      "learning_rate": 4.1491258339084425e-05,
      "loss": 0.8782,
      "step": 15600
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.005053162574768,
      "learning_rate": 4.126121463077985e-05,
      "loss": 0.8735,
      "step": 16000
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.0346530675888062,
      "learning_rate": 4.103117092247527e-05,
      "loss": 0.884,
      "step": 16400
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.113724946975708,
      "learning_rate": 4.0801127214170694e-05,
      "loss": 0.8765,
      "step": 16800
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.9634864926338196,
      "learning_rate": 4.0571083505866117e-05,
      "loss": 0.8734,
      "step": 17200
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0747156143188477,
      "eval_runtime": 239.6824,
      "eval_samples_per_second": 251.479,
      "eval_steps_per_second": 3.93,
      "step": 17548
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9827917218208313,
      "learning_rate": 4.034103979756153e-05,
      "loss": 0.8706,
      "step": 17600
    },
    {
      "epoch": 1.03,
      "grad_norm": 1.1454176902770996,
      "learning_rate": 4.0110996089256956e-05,
      "loss": 0.825,
      "step": 18000
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.9637428522109985,
      "learning_rate": 3.988152749022314e-05,
      "loss": 0.829,
      "step": 18400
    },
    {
      "epoch": 1.07,
      "grad_norm": 1.0976300239562988,
      "learning_rate": 3.965148378191857e-05,
      "loss": 0.8276,
      "step": 18800
    },
    {
      "epoch": 1.09,
      "grad_norm": 1.104611873626709,
      "learning_rate": 3.9422015182884744e-05,
      "loss": 0.8206,
      "step": 19200
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.373989224433899,
      "learning_rate": 3.9193121693121694e-05,
      "loss": 0.8225,
      "step": 19600
    },
    {
      "epoch": 1.14,
      "grad_norm": 1.0706731081008911,
      "learning_rate": 3.896307798481712e-05,
      "loss": 0.8084,
      "step": 20000
    },
    {
      "epoch": 1.16,
      "grad_norm": 1.1869192123413086,
      "learning_rate": 3.873303427651253e-05,
      "loss": 0.8222,
      "step": 20400
    },
    {
      "epoch": 1.19,
      "grad_norm": 1.2390427589416504,
      "learning_rate": 3.850299056820796e-05,
      "loss": 0.8231,
      "step": 20800
    },
    {
      "epoch": 1.21,
      "grad_norm": 1.0254757404327393,
      "learning_rate": 3.8272946859903386e-05,
      "loss": 0.8039,
      "step": 21200
    },
    {
      "epoch": 1.23,
      "grad_norm": 1.2318751811981201,
      "learning_rate": 3.804290315159881e-05,
      "loss": 0.8122,
      "step": 21600
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.0611391067504883,
      "learning_rate": 3.781285944329423e-05,
      "loss": 0.8054,
      "step": 22000
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.1104662418365479,
      "learning_rate": 3.7582815734989655e-05,
      "loss": 0.8065,
      "step": 22400
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.9983170032501221,
      "learning_rate": 3.735277202668507e-05,
      "loss": 0.8058,
      "step": 22800
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.5960198640823364,
      "learning_rate": 3.7122728318380494e-05,
      "loss": 0.8135,
      "step": 23200
    },
    {
      "epoch": 1.34,
      "grad_norm": 1.1167716979980469,
      "learning_rate": 3.689268461007592e-05,
      "loss": 0.7942,
      "step": 23600
    },
    {
      "epoch": 1.37,
      "grad_norm": 1.1541776657104492,
      "learning_rate": 3.666264090177134e-05,
      "loss": 0.7997,
      "step": 24000
    },
    {
      "epoch": 1.39,
      "grad_norm": 1.0213623046875,
      "learning_rate": 3.643259719346676e-05,
      "loss": 0.8009,
      "step": 24400
    },
    {
      "epoch": 1.41,
      "grad_norm": 1.2691611051559448,
      "learning_rate": 3.6202553485162186e-05,
      "loss": 0.801,
      "step": 24800
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.0916258096694946,
      "learning_rate": 3.59725097768576e-05,
      "loss": 0.7868,
      "step": 25200
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.2260217666625977,
      "learning_rate": 3.5742466068553025e-05,
      "loss": 0.7905,
      "step": 25600
    },
    {
      "epoch": 1.48,
      "grad_norm": 1.0053335428237915,
      "learning_rate": 3.5513572578789974e-05,
      "loss": 0.7976,
      "step": 26000
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.2022624015808105,
      "learning_rate": 3.528352887048539e-05,
      "loss": 0.7821,
      "step": 26400
    },
    {
      "epoch": 1.53,
      "grad_norm": 1.7201203107833862,
      "learning_rate": 3.5053485162180814e-05,
      "loss": 0.7812,
      "step": 26800
    },
    {
      "epoch": 1.55,
      "grad_norm": 1.288846731185913,
      "learning_rate": 3.482344145387624e-05,
      "loss": 0.7773,
      "step": 27200
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.9436947107315063,
      "learning_rate": 3.459339774557166e-05,
      "loss": 0.7816,
      "step": 27600
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.2146368026733398,
      "learning_rate": 3.436335403726708e-05,
      "loss": 0.7879,
      "step": 28000
    },
    {
      "epoch": 1.62,
      "grad_norm": 1.2685799598693848,
      "learning_rate": 3.4133310328962506e-05,
      "loss": 0.7851,
      "step": 28400
    },
    {
      "epoch": 1.64,
      "grad_norm": 1.0855278968811035,
      "learning_rate": 3.390326662065793e-05,
      "loss": 0.7878,
      "step": 28800
    },
    {
      "epoch": 1.66,
      "grad_norm": 1.039978265762329,
      "learning_rate": 3.367379802162411e-05,
      "loss": 0.7842,
      "step": 29200
    },
    {
      "epoch": 1.69,
      "grad_norm": 1.144707202911377,
      "learning_rate": 3.344375431331953e-05,
      "loss": 0.7835,
      "step": 29600
    },
    {
      "epoch": 1.71,
      "grad_norm": 1.112640380859375,
      "learning_rate": 3.321371060501495e-05,
      "loss": 0.7787,
      "step": 30000
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.9749494194984436,
      "learning_rate": 3.2983666896710374e-05,
      "loss": 0.7665,
      "step": 30400
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.2835110425949097,
      "learning_rate": 3.2753623188405796e-05,
      "loss": 0.7778,
      "step": 30800
    },
    {
      "epoch": 1.78,
      "grad_norm": 1.1826539039611816,
      "learning_rate": 3.252357948010122e-05,
      "loss": 0.7702,
      "step": 31200
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.0026845932006836,
      "learning_rate": 3.229353577179664e-05,
      "loss": 0.7807,
      "step": 31600
    },
    {
      "epoch": 1.82,
      "grad_norm": 1.314173698425293,
      "learning_rate": 3.2063492063492065e-05,
      "loss": 0.7693,
      "step": 32000
    },
    {
      "epoch": 1.85,
      "grad_norm": 1.2866084575653076,
      "learning_rate": 3.183344835518749e-05,
      "loss": 0.7672,
      "step": 32400
    },
    {
      "epoch": 1.87,
      "grad_norm": 1.2260661125183105,
      "learning_rate": 3.160340464688291e-05,
      "loss": 0.7679,
      "step": 32800
    },
    {
      "epoch": 1.89,
      "grad_norm": 1.05460524559021,
      "learning_rate": 3.1373360938578334e-05,
      "loss": 0.7678,
      "step": 33200
    },
    {
      "epoch": 1.91,
      "grad_norm": 1.020358920097351,
      "learning_rate": 3.114331723027376e-05,
      "loss": 0.7543,
      "step": 33600
    },
    {
      "epoch": 1.94,
      "grad_norm": 1.2354198694229126,
      "learning_rate": 3.091327352196918e-05,
      "loss": 0.7627,
      "step": 34000
    },
    {
      "epoch": 1.96,
      "grad_norm": 1.1465234756469727,
      "learning_rate": 3.0683229813664596e-05,
      "loss": 0.7575,
      "step": 34400
    },
    {
      "epoch": 1.98,
      "grad_norm": 1.2132583856582642,
      "learning_rate": 3.045318610536002e-05,
      "loss": 0.7667,
      "step": 34800
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0832360982894897,
      "eval_runtime": 239.646,
      "eval_samples_per_second": 251.517,
      "eval_steps_per_second": 3.931,
      "step": 35096
    },
    {
      "epoch": 2.01,
      "grad_norm": 1.150380253791809,
      "learning_rate": 3.0223142397055442e-05,
      "loss": 0.7454,
      "step": 35200
    },
    {
      "epoch": 2.03,
      "grad_norm": 1.1517704725265503,
      "learning_rate": 2.9993098688750865e-05,
      "loss": 0.7151,
      "step": 35600
    },
    {
      "epoch": 2.05,
      "grad_norm": 1.2216242551803589,
      "learning_rate": 2.9763054980446285e-05,
      "loss": 0.7085,
      "step": 36000
    },
    {
      "epoch": 2.07,
      "grad_norm": 1.1124303340911865,
      "learning_rate": 2.9533011272141708e-05,
      "loss": 0.7112,
      "step": 36400
    },
    {
      "epoch": 2.1,
      "grad_norm": 1.2349203824996948,
      "learning_rate": 2.930296756383713e-05,
      "loss": 0.7028,
      "step": 36800
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.1383484601974487,
      "learning_rate": 2.9073498964803314e-05,
      "loss": 0.7043,
      "step": 37200
    },
    {
      "epoch": 2.14,
      "grad_norm": 1.156599521636963,
      "learning_rate": 2.8843455256498737e-05,
      "loss": 0.7171,
      "step": 37600
    },
    {
      "epoch": 2.17,
      "grad_norm": 1.2010080814361572,
      "learning_rate": 2.8613411548194156e-05,
      "loss": 0.7131,
      "step": 38000
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.0973454713821411,
      "learning_rate": 2.838336783988958e-05,
      "loss": 0.7107,
      "step": 38400
    },
    {
      "epoch": 2.21,
      "grad_norm": 1.1451126337051392,
      "learning_rate": 2.8153324131585002e-05,
      "loss": 0.7144,
      "step": 38800
    },
    {
      "epoch": 2.23,
      "grad_norm": 1.3358917236328125,
      "learning_rate": 2.7923855532551185e-05,
      "loss": 0.7095,
      "step": 39200
    },
    {
      "epoch": 2.26,
      "grad_norm": 1.142595887184143,
      "learning_rate": 2.7694386933517368e-05,
      "loss": 0.7057,
      "step": 39600
    },
    {
      "epoch": 2.28,
      "grad_norm": 1.0060242414474487,
      "learning_rate": 2.746434322521279e-05,
      "loss": 0.7015,
      "step": 40000
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.9941455721855164,
      "learning_rate": 2.7234299516908214e-05,
      "loss": 0.7132,
      "step": 40400
    },
    {
      "epoch": 2.33,
      "grad_norm": 1.0412284135818481,
      "learning_rate": 2.7004255808603634e-05,
      "loss": 0.705,
      "step": 40800
    },
    {
      "epoch": 2.35,
      "grad_norm": 1.099241852760315,
      "learning_rate": 2.6774212100299057e-05,
      "loss": 0.7084,
      "step": 41200
    },
    {
      "epoch": 2.37,
      "grad_norm": 1.1212828159332275,
      "learning_rate": 2.654474350126524e-05,
      "loss": 0.6978,
      "step": 41600
    },
    {
      "epoch": 2.39,
      "grad_norm": 1.0526177883148193,
      "learning_rate": 2.6315274902231422e-05,
      "loss": 0.7004,
      "step": 42000
    },
    {
      "epoch": 2.42,
      "grad_norm": 1.1355630159378052,
      "learning_rate": 2.6085231193926845e-05,
      "loss": 0.7066,
      "step": 42400
    },
    {
      "epoch": 2.44,
      "grad_norm": 1.1076544523239136,
      "learning_rate": 2.5855187485622268e-05,
      "loss": 0.7059,
      "step": 42800
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.9984206557273865,
      "learning_rate": 2.562514377731769e-05,
      "loss": 0.6959,
      "step": 43200
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.267728567123413,
      "learning_rate": 2.5395675178283874e-05,
      "loss": 0.7109,
      "step": 43600
    },
    {
      "epoch": 2.51,
      "grad_norm": 1.010473370552063,
      "learning_rate": 2.5165631469979294e-05,
      "loss": 0.707,
      "step": 44000
    },
    {
      "epoch": 2.53,
      "grad_norm": 1.3132517337799072,
      "learning_rate": 2.493616287094548e-05,
      "loss": 0.7049,
      "step": 44400
    },
    {
      "epoch": 2.55,
      "grad_norm": 1.0806896686553955,
      "learning_rate": 2.4706119162640903e-05,
      "loss": 0.7032,
      "step": 44800
    },
    {
      "epoch": 2.58,
      "grad_norm": 1.0918660163879395,
      "learning_rate": 2.4476075454336326e-05,
      "loss": 0.6876,
      "step": 45200
    },
    {
      "epoch": 2.6,
      "grad_norm": 1.172402024269104,
      "learning_rate": 2.424603174603175e-05,
      "loss": 0.697,
      "step": 45600
    },
    {
      "epoch": 2.62,
      "grad_norm": 1.3677465915679932,
      "learning_rate": 2.4015988037727168e-05,
      "loss": 0.694,
      "step": 46000
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.9764865636825562,
      "learning_rate": 2.378594432942259e-05,
      "loss": 0.692,
      "step": 46400
    },
    {
      "epoch": 2.67,
      "grad_norm": 1.168467402458191,
      "learning_rate": 2.3555900621118014e-05,
      "loss": 0.6907,
      "step": 46800
    },
    {
      "epoch": 2.69,
      "grad_norm": 1.0712902545928955,
      "learning_rate": 2.3325856912813434e-05,
      "loss": 0.6969,
      "step": 47200
    },
    {
      "epoch": 2.71,
      "grad_norm": 1.2307454347610474,
      "learning_rate": 2.3095813204508857e-05,
      "loss": 0.6912,
      "step": 47600
    },
    {
      "epoch": 2.74,
      "grad_norm": 1.0218665599822998,
      "learning_rate": 2.286576949620428e-05,
      "loss": 0.6977,
      "step": 48000
    },
    {
      "epoch": 2.76,
      "grad_norm": 1.2914952039718628,
      "learning_rate": 2.2635725787899703e-05,
      "loss": 0.6902,
      "step": 48400
    },
    {
      "epoch": 2.78,
      "grad_norm": 1.1566945314407349,
      "learning_rate": 2.2405682079595126e-05,
      "loss": 0.6812,
      "step": 48800
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.0954487323760986,
      "learning_rate": 2.2175638371290545e-05,
      "loss": 0.6884,
      "step": 49200
    },
    {
      "epoch": 2.83,
      "grad_norm": 1.2148932218551636,
      "learning_rate": 2.1945594662985968e-05,
      "loss": 0.6815,
      "step": 49600
    },
    {
      "epoch": 2.85,
      "grad_norm": 1.3392747640609741,
      "learning_rate": 2.171555095468139e-05,
      "loss": 0.68,
      "step": 50000
    },
    {
      "epoch": 2.87,
      "grad_norm": 1.1132878065109253,
      "learning_rate": 2.1485507246376814e-05,
      "loss": 0.6985,
      "step": 50400
    },
    {
      "epoch": 2.89,
      "grad_norm": 1.1941944360733032,
      "learning_rate": 2.1255463538072234e-05,
      "loss": 0.6888,
      "step": 50800
    },
    {
      "epoch": 2.92,
      "grad_norm": 1.3875670433044434,
      "learning_rate": 2.1025994939038417e-05,
      "loss": 0.689,
      "step": 51200
    },
    {
      "epoch": 2.94,
      "grad_norm": 1.1829801797866821,
      "learning_rate": 2.079595123073384e-05,
      "loss": 0.6913,
      "step": 51600
    },
    {
      "epoch": 2.96,
      "grad_norm": 1.1661145687103271,
      "learning_rate": 2.0565907522429263e-05,
      "loss": 0.6889,
      "step": 52000
    },
    {
      "epoch": 2.99,
      "grad_norm": 1.4086240530014038,
      "learning_rate": 2.0335863814124682e-05,
      "loss": 0.6835,
      "step": 52400
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.08446204662323,
      "eval_runtime": 239.6214,
      "eval_samples_per_second": 251.543,
      "eval_steps_per_second": 3.931,
      "step": 52644
    },
    {
      "epoch": 3.01,
      "grad_norm": 1.4694873094558716,
      "learning_rate": 2.0105820105820105e-05,
      "loss": 0.6682,
      "step": 52800
    },
    {
      "epoch": 3.03,
      "grad_norm": 1.2044637203216553,
      "learning_rate": 1.9875776397515528e-05,
      "loss": 0.6507,
      "step": 53200
    },
    {
      "epoch": 3.05,
      "grad_norm": 1.100796103477478,
      "learning_rate": 1.964573268921095e-05,
      "loss": 0.6401,
      "step": 53600
    },
    {
      "epoch": 3.08,
      "grad_norm": 1.0444916486740112,
      "learning_rate": 1.9415688980906374e-05,
      "loss": 0.6449,
      "step": 54000
    },
    {
      "epoch": 3.1,
      "grad_norm": 1.0386139154434204,
      "learning_rate": 1.918679549114332e-05,
      "loss": 0.6501,
      "step": 54400
    },
    {
      "epoch": 3.12,
      "grad_norm": 1.1518653631210327,
      "learning_rate": 1.895675178283874e-05,
      "loss": 0.6461,
      "step": 54800
    },
    {
      "epoch": 3.15,
      "grad_norm": 1.1994818449020386,
      "learning_rate": 1.8726708074534163e-05,
      "loss": 0.6556,
      "step": 55200
    },
    {
      "epoch": 3.17,
      "grad_norm": 1.1442828178405762,
      "learning_rate": 1.8496664366229586e-05,
      "loss": 0.6361,
      "step": 55600
    },
    {
      "epoch": 3.19,
      "grad_norm": 1.0276410579681396,
      "learning_rate": 1.826662065792501e-05,
      "loss": 0.6378,
      "step": 56000
    },
    {
      "epoch": 3.21,
      "grad_norm": 1.1680177450180054,
      "learning_rate": 1.8036576949620428e-05,
      "loss": 0.6439,
      "step": 56400
    },
    {
      "epoch": 3.24,
      "grad_norm": 1.1519464254379272,
      "learning_rate": 1.780653324131585e-05,
      "loss": 0.6466,
      "step": 56800
    },
    {
      "epoch": 3.26,
      "grad_norm": 1.1728110313415527,
      "learning_rate": 1.7576489533011274e-05,
      "loss": 0.6419,
      "step": 57200
    },
    {
      "epoch": 3.28,
      "grad_norm": 1.1479480266571045,
      "learning_rate": 1.7347020933977457e-05,
      "loss": 0.6398,
      "step": 57600
    },
    {
      "epoch": 3.31,
      "grad_norm": 1.3310575485229492,
      "learning_rate": 1.7116977225672877e-05,
      "loss": 0.6407,
      "step": 58000
    },
    {
      "epoch": 3.33,
      "grad_norm": 1.3201924562454224,
      "learning_rate": 1.68869335173683e-05,
      "loss": 0.643,
      "step": 58400
    },
    {
      "epoch": 3.35,
      "grad_norm": 1.1604301929473877,
      "learning_rate": 1.6656889809063723e-05,
      "loss": 0.638,
      "step": 58800
    },
    {
      "epoch": 3.37,
      "grad_norm": 1.0410959720611572,
      "learning_rate": 1.6426846100759146e-05,
      "loss": 0.6418,
      "step": 59200
    },
    {
      "epoch": 3.4,
      "grad_norm": 1.3607354164123535,
      "learning_rate": 1.6196802392454565e-05,
      "loss": 0.6486,
      "step": 59600
    },
    {
      "epoch": 3.42,
      "grad_norm": 1.0975886583328247,
      "learning_rate": 1.596675868414999e-05,
      "loss": 0.6309,
      "step": 60000
    },
    {
      "epoch": 3.44,
      "grad_norm": 1.1079365015029907,
      "learning_rate": 1.573671497584541e-05,
      "loss": 0.6362,
      "step": 60400
    },
    {
      "epoch": 3.46,
      "grad_norm": 1.1985440254211426,
      "learning_rate": 1.5506671267540834e-05,
      "loss": 0.6402,
      "step": 60800
    },
    {
      "epoch": 3.49,
      "grad_norm": 0.9779540300369263,
      "learning_rate": 1.5276627559236257e-05,
      "loss": 0.6441,
      "step": 61200
    },
    {
      "epoch": 3.51,
      "grad_norm": 1.2140247821807861,
      "learning_rate": 1.5046583850931678e-05,
      "loss": 0.6393,
      "step": 61600
    },
    {
      "epoch": 3.53,
      "grad_norm": 1.3921316862106323,
      "learning_rate": 1.48165401426271e-05,
      "loss": 0.6407,
      "step": 62000
    },
    {
      "epoch": 3.56,
      "grad_norm": 1.286074161529541,
      "learning_rate": 1.4587071543593284e-05,
      "loss": 0.6447,
      "step": 62400
    },
    {
      "epoch": 3.58,
      "grad_norm": 1.2328264713287354,
      "learning_rate": 1.4357027835288705e-05,
      "loss": 0.6387,
      "step": 62800
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.1091105937957764,
      "learning_rate": 1.4126984126984127e-05,
      "loss": 0.6287,
      "step": 63200
    },
    {
      "epoch": 3.62,
      "grad_norm": 1.3000015020370483,
      "learning_rate": 1.389694041867955e-05,
      "loss": 0.6421,
      "step": 63600
    },
    {
      "epoch": 3.65,
      "grad_norm": 0.9806800484657288,
      "learning_rate": 1.3666896710374971e-05,
      "loss": 0.6342,
      "step": 64000
    },
    {
      "epoch": 3.67,
      "grad_norm": 1.4063104391098022,
      "learning_rate": 1.3436853002070392e-05,
      "loss": 0.6323,
      "step": 64400
    },
    {
      "epoch": 3.69,
      "grad_norm": 1.1137511730194092,
      "learning_rate": 1.3206809293765815e-05,
      "loss": 0.6316,
      "step": 64800
    },
    {
      "epoch": 3.72,
      "grad_norm": 1.307237148284912,
      "learning_rate": 1.2976765585461237e-05,
      "loss": 0.6209,
      "step": 65200
    },
    {
      "epoch": 3.74,
      "grad_norm": 1.2854503393173218,
      "learning_rate": 1.2746721877156661e-05,
      "loss": 0.635,
      "step": 65600
    },
    {
      "epoch": 3.76,
      "grad_norm": 1.4092977046966553,
      "learning_rate": 1.2516678168852084e-05,
      "loss": 0.6337,
      "step": 66000
    },
    {
      "epoch": 3.78,
      "grad_norm": 1.146622657775879,
      "learning_rate": 1.2286634460547504e-05,
      "loss": 0.621,
      "step": 66400
    },
    {
      "epoch": 3.81,
      "grad_norm": 1.4500105381011963,
      "learning_rate": 1.2056590752242927e-05,
      "loss": 0.6351,
      "step": 66800
    },
    {
      "epoch": 3.83,
      "grad_norm": 1.3374382257461548,
      "learning_rate": 1.182654704393835e-05,
      "loss": 0.6434,
      "step": 67200
    },
    {
      "epoch": 3.85,
      "grad_norm": 1.172215223312378,
      "learning_rate": 1.1596503335633771e-05,
      "loss": 0.6299,
      "step": 67600
    },
    {
      "epoch": 3.88,
      "grad_norm": 1.228962779045105,
      "learning_rate": 1.1366459627329192e-05,
      "loss": 0.6289,
      "step": 68000
    },
    {
      "epoch": 3.9,
      "grad_norm": 1.1930328607559204,
      "learning_rate": 1.1136415919024615e-05,
      "loss": 0.6387,
      "step": 68400
    },
    {
      "epoch": 3.92,
      "grad_norm": 1.0659236907958984,
      "learning_rate": 1.0906947319990798e-05,
      "loss": 0.6323,
      "step": 68800
    },
    {
      "epoch": 3.94,
      "grad_norm": 1.2611548900604248,
      "learning_rate": 1.0677478720956983e-05,
      "loss": 0.6287,
      "step": 69200
    },
    {
      "epoch": 3.97,
      "grad_norm": 1.186289668083191,
      "learning_rate": 1.0447435012652404e-05,
      "loss": 0.6232,
      "step": 69600
    },
    {
      "epoch": 3.99,
      "grad_norm": 1.2363786697387695,
      "learning_rate": 1.0217391304347827e-05,
      "loss": 0.6239,
      "step": 70000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0999037027359009,
      "eval_runtime": 239.6686,
      "eval_samples_per_second": 251.493,
      "eval_steps_per_second": 3.93,
      "step": 70192
    },
    {
      "epoch": 4.01,
      "grad_norm": 1.0348886251449585,
      "learning_rate": 9.98734759604325e-06,
      "loss": 0.6073,
      "step": 70400
    },
    {
      "epoch": 4.03,
      "grad_norm": 1.2015148401260376,
      "learning_rate": 9.757303887738671e-06,
      "loss": 0.5995,
      "step": 70800
    },
    {
      "epoch": 4.06,
      "grad_norm": 1.2094097137451172,
      "learning_rate": 9.527260179434092e-06,
      "loss": 0.5939,
      "step": 71200
    },
    {
      "epoch": 4.08,
      "grad_norm": 1.1249605417251587,
      "learning_rate": 9.297216471129515e-06,
      "loss": 0.6087,
      "step": 71600
    },
    {
      "epoch": 4.1,
      "grad_norm": 1.1234875917434692,
      "learning_rate": 9.067172762824937e-06,
      "loss": 0.5966,
      "step": 72000
    },
    {
      "epoch": 4.13,
      "grad_norm": 1.3029675483703613,
      "learning_rate": 8.837704163791121e-06,
      "loss": 0.6023,
      "step": 72400
    },
    {
      "epoch": 4.15,
      "grad_norm": 1.1492359638214111,
      "learning_rate": 8.607660455486542e-06,
      "loss": 0.6014,
      "step": 72800
    },
    {
      "epoch": 4.17,
      "grad_norm": 1.1293883323669434,
      "learning_rate": 8.377616747181965e-06,
      "loss": 0.5975,
      "step": 73200
    },
    {
      "epoch": 4.19,
      "grad_norm": 1.1434813737869263,
      "learning_rate": 8.147573038877387e-06,
      "loss": 0.5928,
      "step": 73600
    },
    {
      "epoch": 4.22,
      "grad_norm": 1.2983373403549194,
      "learning_rate": 7.91752933057281e-06,
      "loss": 0.5987,
      "step": 74000
    },
    {
      "epoch": 4.24,
      "grad_norm": 1.190185785293579,
      "learning_rate": 7.687485622268231e-06,
      "loss": 0.5948,
      "step": 74400
    },
    {
      "epoch": 4.26,
      "grad_norm": 1.068985939025879,
      "learning_rate": 7.457441913963653e-06,
      "loss": 0.6059,
      "step": 74800
    },
    {
      "epoch": 4.29,
      "grad_norm": 1.0893745422363281,
      "learning_rate": 7.227398205659075e-06,
      "loss": 0.61,
      "step": 75200
    },
    {
      "epoch": 4.31,
      "grad_norm": 1.1232637166976929,
      "learning_rate": 6.997354497354498e-06,
      "loss": 0.5947,
      "step": 75600
    },
    {
      "epoch": 4.33,
      "grad_norm": 1.1357260942459106,
      "learning_rate": 6.76731078904992e-06,
      "loss": 0.596,
      "step": 76000
    },
    {
      "epoch": 4.35,
      "grad_norm": 1.1744706630706787,
      "learning_rate": 6.537267080745342e-06,
      "loss": 0.5909,
      "step": 76400
    },
    {
      "epoch": 4.38,
      "grad_norm": 1.2433269023895264,
      "learning_rate": 6.307223372440764e-06,
      "loss": 0.6008,
      "step": 76800
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.1302207708358765,
      "learning_rate": 6.0777547734069475e-06,
      "loss": 0.6091,
      "step": 77200
    },
    {
      "epoch": 4.42,
      "grad_norm": 1.309975504875183,
      "learning_rate": 5.848286174373131e-06,
      "loss": 0.5954,
      "step": 77600
    },
    {
      "epoch": 4.44,
      "grad_norm": 1.2409945726394653,
      "learning_rate": 5.618242466068553e-06,
      "loss": 0.5986,
      "step": 78000
    },
    {
      "epoch": 4.47,
      "grad_norm": 1.274553894996643,
      "learning_rate": 5.388198757763975e-06,
      "loss": 0.6031,
      "step": 78400
    },
    {
      "epoch": 4.49,
      "grad_norm": 1.2017253637313843,
      "learning_rate": 5.1581550494593975e-06,
      "loss": 0.5944,
      "step": 78800
    },
    {
      "epoch": 4.51,
      "grad_norm": 1.2163805961608887,
      "learning_rate": 4.92811134115482e-06,
      "loss": 0.5921,
      "step": 79200
    },
    {
      "epoch": 4.54,
      "grad_norm": 1.2417266368865967,
      "learning_rate": 4.698067632850242e-06,
      "loss": 0.5897,
      "step": 79600
    },
    {
      "epoch": 4.56,
      "grad_norm": 1.212352991104126,
      "learning_rate": 4.468023924545664e-06,
      "loss": 0.6028,
      "step": 80000
    },
    {
      "epoch": 4.58,
      "grad_norm": 1.2147575616836548,
      "learning_rate": 4.237980216241086e-06,
      "loss": 0.5964,
      "step": 80400
    },
    {
      "epoch": 4.6,
      "grad_norm": 1.315047025680542,
      "learning_rate": 4.007936507936508e-06,
      "loss": 0.6008,
      "step": 80800
    },
    {
      "epoch": 4.63,
      "grad_norm": 1.3426513671875,
      "learning_rate": 3.7778927996319303e-06,
      "loss": 0.5913,
      "step": 81200
    },
    {
      "epoch": 4.65,
      "grad_norm": 1.1529968976974487,
      "learning_rate": 3.5478490913273524e-06,
      "loss": 0.5966,
      "step": 81600
    },
    {
      "epoch": 4.67,
      "grad_norm": 1.2418185472488403,
      "learning_rate": 3.317805383022775e-06,
      "loss": 0.5878,
      "step": 82000
    },
    {
      "epoch": 4.7,
      "grad_norm": 1.1235523223876953,
      "learning_rate": 3.0877616747181967e-06,
      "loss": 0.5931,
      "step": 82400
    },
    {
      "epoch": 4.72,
      "grad_norm": 1.3443814516067505,
      "learning_rate": 2.85829307568438e-06,
      "loss": 0.6064,
      "step": 82800
    },
    {
      "epoch": 4.74,
      "grad_norm": 1.2628613710403442,
      "learning_rate": 2.6288244766505636e-06,
      "loss": 0.6001,
      "step": 83200
    },
    {
      "epoch": 4.76,
      "grad_norm": 1.1324889659881592,
      "learning_rate": 2.3987807683459858e-06,
      "loss": 0.5916,
      "step": 83600
    },
    {
      "epoch": 4.79,
      "grad_norm": 1.1024839878082275,
      "learning_rate": 2.168737060041408e-06,
      "loss": 0.6048,
      "step": 84000
    },
    {
      "epoch": 4.81,
      "grad_norm": 1.3531837463378906,
      "learning_rate": 1.93869335173683e-06,
      "loss": 0.5896,
      "step": 84400
    },
    {
      "epoch": 4.83,
      "grad_norm": 1.1726586818695068,
      "learning_rate": 1.7086496434322524e-06,
      "loss": 0.5905,
      "step": 84800
    },
    {
      "epoch": 4.86,
      "grad_norm": 1.0651309490203857,
      "learning_rate": 1.4791810443984358e-06,
      "loss": 0.6002,
      "step": 85200
    },
    {
      "epoch": 4.88,
      "grad_norm": 1.277769684791565,
      "learning_rate": 1.2497124453646193e-06,
      "loss": 0.5899,
      "step": 85600
    },
    {
      "epoch": 4.9,
      "grad_norm": 1.2923473119735718,
      "learning_rate": 1.0196687370600414e-06,
      "loss": 0.5924,
      "step": 86000
    },
    {
      "epoch": 4.92,
      "grad_norm": 1.1012171506881714,
      "learning_rate": 7.896250287554636e-07,
      "loss": 0.591,
      "step": 86400
    },
    {
      "epoch": 4.95,
      "grad_norm": 1.2737475633621216,
      "learning_rate": 5.595813204508857e-07,
      "loss": 0.5968,
      "step": 86800
    },
    {
      "epoch": 4.97,
      "grad_norm": 1.2628225088119507,
      "learning_rate": 3.295376121463078e-07,
      "loss": 0.591,
      "step": 87200
    },
    {
      "epoch": 4.99,
      "grad_norm": 1.3517860174179077,
      "learning_rate": 9.949390384172993e-08,
      "loss": 0.5918,
      "step": 87600
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.1124831438064575,
      "eval_runtime": 239.5934,
      "eval_samples_per_second": 251.572,
      "eval_steps_per_second": 3.932,
      "step": 87740
    },
    {
      "epoch": 5.0,
      "step": 87740,
      "total_flos": 1.7097588901675008e+18,
      "train_loss": 0.74035006675955,
      "train_runtime": 31417.8788,
      "train_samples_per_second": 89.369,
      "train_steps_per_second": 2.793
    }
  ],
  "logging_steps": 400,
  "max_steps": 87740,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.7097588901675008e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}