{
  "best_metric": 1.177372694015503,
  "best_model_checkpoint": "/root/finetuning_executions/finetuning_05_utg4java_src_fm_fc_ms_ff/checkpoint-52644",
  "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": 2.229098081588745,
      "learning_rate": 2.4750000000000002e-05,
      "loss": 3.3229,
      "step": 400
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.5058149099349976,
      "learning_rate": 4.975e-05,
      "loss": 1.748,
      "step": 800
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.120527982711792,
      "learning_rate": 4.977225672877847e-05,
      "loss": 1.5462,
      "step": 1200
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.5305182933807373,
      "learning_rate": 4.9542213020473895e-05,
      "loss": 1.4719,
      "step": 1600
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.0366812944412231,
      "learning_rate": 4.931216931216932e-05,
      "loss": 1.4154,
      "step": 2000
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.1470097303390503,
      "learning_rate": 4.9082125603864734e-05,
      "loss": 1.3773,
      "step": 2400
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.1128191947937012,
      "learning_rate": 4.885208189556016e-05,
      "loss": 1.3428,
      "step": 2800
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.253928303718567,
      "learning_rate": 4.862203818725558e-05,
      "loss": 1.3226,
      "step": 3200
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.0254652500152588,
      "learning_rate": 4.8391994478951e-05,
      "loss": 1.291,
      "step": 3600
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.1027791500091553,
      "learning_rate": 4.8161950770646426e-05,
      "loss": 1.2715,
      "step": 4000
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.1553912162780762,
      "learning_rate": 4.793190706234185e-05,
      "loss": 1.2662,
      "step": 4400
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.144874930381775,
      "learning_rate": 4.770186335403727e-05,
      "loss": 1.242,
      "step": 4800
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.1357582807540894,
      "learning_rate": 4.747181964573269e-05,
      "loss": 1.2392,
      "step": 5200
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.8985121250152588,
      "learning_rate": 4.724177593742811e-05,
      "loss": 1.2093,
      "step": 5600
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.9756821990013123,
      "learning_rate": 4.7011732229123534e-05,
      "loss": 1.1905,
      "step": 6000
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.1240946054458618,
      "learning_rate": 4.678168852081896e-05,
      "loss": 1.1769,
      "step": 6400
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.9794073700904846,
      "learning_rate": 4.655164481251438e-05,
      "loss": 1.1658,
      "step": 6800
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.977505624294281,
      "learning_rate": 4.63216011042098e-05,
      "loss": 1.1749,
      "step": 7200
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.1371684074401855,
      "learning_rate": 4.609155739590522e-05,
      "loss": 1.1424,
      "step": 7600
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.0095725059509277,
      "learning_rate": 4.586151368760065e-05,
      "loss": 1.1417,
      "step": 8000
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0289288759231567,
      "learning_rate": 4.563146997929607e-05,
      "loss": 1.1408,
      "step": 8400
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.1291728019714355,
      "learning_rate": 4.5401426270991495e-05,
      "loss": 1.1243,
      "step": 8800
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.1059273481369019,
      "learning_rate": 4.517138256268692e-05,
      "loss": 1.1143,
      "step": 9200
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.8934476971626282,
      "learning_rate": 4.4941338854382334e-05,
      "loss": 1.1019,
      "step": 9600
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.0957863330841064,
      "learning_rate": 4.471129514607776e-05,
      "loss": 1.094,
      "step": 10000
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.2800277471542358,
      "learning_rate": 4.448125143777318e-05,
      "loss": 1.0773,
      "step": 10400
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.9538272619247437,
      "learning_rate": 4.42512077294686e-05,
      "loss": 1.0952,
      "step": 10800
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9216693639755249,
      "learning_rate": 4.4021164021164026e-05,
      "loss": 1.0725,
      "step": 11200
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.9263585805892944,
      "learning_rate": 4.379112031285945e-05,
      "loss": 1.0693,
      "step": 11600
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.9969348311424255,
      "learning_rate": 4.3561076604554865e-05,
      "loss": 1.0582,
      "step": 12000
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.9046760201454163,
      "learning_rate": 4.333103289625029e-05,
      "loss": 1.062,
      "step": 12400
    },
    {
      "epoch": 0.73,
      "grad_norm": 1.0008882284164429,
      "learning_rate": 4.310098918794571e-05,
      "loss": 1.0676,
      "step": 12800
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.0041269063949585,
      "learning_rate": 4.2870945479641134e-05,
      "loss": 1.0428,
      "step": 13200
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.0424519777297974,
      "learning_rate": 4.264090177133656e-05,
      "loss": 1.0403,
      "step": 13600
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9091747999191284,
      "learning_rate": 4.241143317230274e-05,
      "loss": 1.04,
      "step": 14000
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.0176922082901,
      "learning_rate": 4.218138946399816e-05,
      "loss": 1.0271,
      "step": 14400
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.1477534770965576,
      "learning_rate": 4.1951345755693586e-05,
      "loss": 1.0325,
      "step": 14800
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.9284051060676575,
      "learning_rate": 4.1721302047389e-05,
      "loss": 1.0331,
      "step": 15200
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.9155886173248291,
      "learning_rate": 4.1491258339084425e-05,
      "loss": 1.0081,
      "step": 15600
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.9425845146179199,
      "learning_rate": 4.126121463077985e-05,
      "loss": 1.0014,
      "step": 16000
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.9099463224411011,
      "learning_rate": 4.103117092247527e-05,
      "loss": 1.0117,
      "step": 16400
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.941250205039978,
      "learning_rate": 4.0801127214170694e-05,
      "loss": 1.0021,
      "step": 16800
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.8845394849777222,
      "learning_rate": 4.0571083505866117e-05,
      "loss": 0.9984,
      "step": 17200
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2029205560684204,
      "eval_runtime": 240.0634,
      "eval_samples_per_second": 251.08,
      "eval_steps_per_second": 3.924,
      "step": 17548
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8803815841674805,
      "learning_rate": 4.034103979756153e-05,
      "loss": 0.9937,
      "step": 17600
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.9823230504989624,
      "learning_rate": 4.0110996089256956e-05,
      "loss": 0.9468,
      "step": 18000
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.9398742914199829,
      "learning_rate": 3.9880952380952386e-05,
      "loss": 0.9499,
      "step": 18400
    },
    {
      "epoch": 1.07,
      "grad_norm": 1.0421141386032104,
      "learning_rate": 3.965090867264781e-05,
      "loss": 0.9471,
      "step": 18800
    },
    {
      "epoch": 1.09,
      "grad_norm": 1.0032306909561157,
      "learning_rate": 3.9422015182884744e-05,
      "loss": 0.9375,
      "step": 19200
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.4174487590789795,
      "learning_rate": 3.9191971474580174e-05,
      "loss": 0.9417,
      "step": 19600
    },
    {
      "epoch": 1.14,
      "grad_norm": 1.037479281425476,
      "learning_rate": 3.89619277662756e-05,
      "loss": 0.925,
      "step": 20000
    },
    {
      "epoch": 1.16,
      "grad_norm": 1.0530787706375122,
      "learning_rate": 3.873245916724178e-05,
      "loss": 0.9378,
      "step": 20400
    },
    {
      "epoch": 1.19,
      "grad_norm": 1.1429826021194458,
      "learning_rate": 3.85024154589372e-05,
      "loss": 0.9386,
      "step": 20800
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.8666102886199951,
      "learning_rate": 3.8272371750632626e-05,
      "loss": 0.9169,
      "step": 21200
    },
    {
      "epoch": 1.23,
      "grad_norm": 1.0205742120742798,
      "learning_rate": 3.804232804232805e-05,
      "loss": 0.9247,
      "step": 21600
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.046938180923462,
      "learning_rate": 3.7812284334023465e-05,
      "loss": 0.9168,
      "step": 22000
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.0534473657608032,
      "learning_rate": 3.758224062571889e-05,
      "loss": 0.9179,
      "step": 22400
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.9643887877464294,
      "learning_rate": 3.735219691741431e-05,
      "loss": 0.9147,
      "step": 22800
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.162414312362671,
      "learning_rate": 3.7122153209109734e-05,
      "loss": 0.9252,
      "step": 23200
    },
    {
      "epoch": 1.34,
      "grad_norm": 1.0543121099472046,
      "learning_rate": 3.689210950080516e-05,
      "loss": 0.9002,
      "step": 23600
    },
    {
      "epoch": 1.37,
      "grad_norm": 1.095170021057129,
      "learning_rate": 3.666206579250058e-05,
      "loss": 0.9078,
      "step": 24000
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.938887357711792,
      "learning_rate": 3.6432022084195996e-05,
      "loss": 0.9074,
      "step": 24400
    },
    {
      "epoch": 1.41,
      "grad_norm": 1.1190577745437622,
      "learning_rate": 3.620197837589142e-05,
      "loss": 0.9087,
      "step": 24800
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.9494956731796265,
      "learning_rate": 3.597193466758684e-05,
      "loss": 0.8903,
      "step": 25200
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.1163825988769531,
      "learning_rate": 3.5741890959282265e-05,
      "loss": 0.8934,
      "step": 25600
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.9037898182868958,
      "learning_rate": 3.551184725097769e-05,
      "loss": 0.9022,
      "step": 26000
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.0662837028503418,
      "learning_rate": 3.528237865194387e-05,
      "loss": 0.8859,
      "step": 26400
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.8364838361740112,
      "learning_rate": 3.5052334943639294e-05,
      "loss": 0.8829,
      "step": 26800
    },
    {
      "epoch": 1.55,
      "grad_norm": 1.109578013420105,
      "learning_rate": 3.482229123533472e-05,
      "loss": 0.8784,
      "step": 27200
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.8675488829612732,
      "learning_rate": 3.459224752703013e-05,
      "loss": 0.8822,
      "step": 27600
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.089260458946228,
      "learning_rate": 3.4362203818725556e-05,
      "loss": 0.8864,
      "step": 28000
    },
    {
      "epoch": 1.62,
      "grad_norm": 1.2143120765686035,
      "learning_rate": 3.413216011042098e-05,
      "loss": 0.8872,
      "step": 28400
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.969947099685669,
      "learning_rate": 3.39021164021164e-05,
      "loss": 0.8888,
      "step": 28800
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.9949952960014343,
      "learning_rate": 3.3672647803082585e-05,
      "loss": 0.8837,
      "step": 29200
    },
    {
      "epoch": 1.69,
      "grad_norm": 1.0020053386688232,
      "learning_rate": 3.344260409477801e-05,
      "loss": 0.8832,
      "step": 29600
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.9824060797691345,
      "learning_rate": 3.321256038647343e-05,
      "loss": 0.8772,
      "step": 30000
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.9114558100700378,
      "learning_rate": 3.2982516678168854e-05,
      "loss": 0.8618,
      "step": 30400
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.1614044904708862,
      "learning_rate": 3.275247296986428e-05,
      "loss": 0.8735,
      "step": 30800
    },
    {
      "epoch": 1.78,
      "grad_norm": 1.030380129814148,
      "learning_rate": 3.25224292615597e-05,
      "loss": 0.8657,
      "step": 31200
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.9505811929702759,
      "learning_rate": 3.229238555325512e-05,
      "loss": 0.8783,
      "step": 31600
    },
    {
      "epoch": 1.82,
      "grad_norm": 1.2939780950546265,
      "learning_rate": 3.2062916954221306e-05,
      "loss": 0.8635,
      "step": 32000
    },
    {
      "epoch": 1.85,
      "grad_norm": 1.1592987775802612,
      "learning_rate": 3.183287324591673e-05,
      "loss": 0.8616,
      "step": 32400
    },
    {
      "epoch": 1.87,
      "grad_norm": 1.104283332824707,
      "learning_rate": 3.160340464688291e-05,
      "loss": 0.8613,
      "step": 32800
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.9907343983650208,
      "learning_rate": 3.1373360938578334e-05,
      "loss": 0.8623,
      "step": 33200
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.96369868516922,
      "learning_rate": 3.114331723027376e-05,
      "loss": 0.8467,
      "step": 33600
    },
    {
      "epoch": 1.94,
      "grad_norm": 1.026637315750122,
      "learning_rate": 3.091327352196918e-05,
      "loss": 0.8563,
      "step": 34000
    },
    {
      "epoch": 1.96,
      "grad_norm": 1.00987708568573,
      "learning_rate": 3.0683229813664596e-05,
      "loss": 0.8489,
      "step": 34400
    },
    {
      "epoch": 1.98,
      "grad_norm": 1.0772453546524048,
      "learning_rate": 3.0453761214630783e-05,
      "loss": 0.8597,
      "step": 34800
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1818490028381348,
      "eval_runtime": 240.2583,
      "eval_samples_per_second": 250.876,
      "eval_steps_per_second": 3.921,
      "step": 35096
    },
    {
      "epoch": 2.01,
      "grad_norm": 1.0454893112182617,
      "learning_rate": 3.0223717506326206e-05,
      "loss": 0.8354,
      "step": 35200
    },
    {
      "epoch": 2.03,
      "grad_norm": 1.0722404718399048,
      "learning_rate": 2.9993673798021625e-05,
      "loss": 0.8027,
      "step": 35600
    },
    {
      "epoch": 2.05,
      "grad_norm": 1.144631266593933,
      "learning_rate": 2.9763630089717048e-05,
      "loss": 0.7981,
      "step": 36000
    },
    {
      "epoch": 2.07,
      "grad_norm": 1.0820245742797852,
      "learning_rate": 2.953358638141247e-05,
      "loss": 0.7989,
      "step": 36400
    },
    {
      "epoch": 2.1,
      "grad_norm": 1.1228435039520264,
      "learning_rate": 2.930354267310789e-05,
      "loss": 0.7908,
      "step": 36800
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.0229965448379517,
      "learning_rate": 2.9073498964803314e-05,
      "loss": 0.792,
      "step": 37200
    },
    {
      "epoch": 2.14,
      "grad_norm": 1.0550298690795898,
      "learning_rate": 2.8843455256498737e-05,
      "loss": 0.8046,
      "step": 37600
    },
    {
      "epoch": 2.17,
      "grad_norm": 1.1629900932312012,
      "learning_rate": 2.8613411548194156e-05,
      "loss": 0.8019,
      "step": 38000
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.0293209552764893,
      "learning_rate": 2.838336783988958e-05,
      "loss": 0.7967,
      "step": 38400
    },
    {
      "epoch": 2.21,
      "grad_norm": 1.0259321928024292,
      "learning_rate": 2.8153324131585002e-05,
      "loss": 0.8035,
      "step": 38800
    },
    {
      "epoch": 2.23,
      "grad_norm": 1.2149560451507568,
      "learning_rate": 2.7923280423280422e-05,
      "loss": 0.7979,
      "step": 39200
    },
    {
      "epoch": 2.26,
      "grad_norm": 1.082778811454773,
      "learning_rate": 2.7693236714975845e-05,
      "loss": 0.7913,
      "step": 39600
    },
    {
      "epoch": 2.28,
      "grad_norm": 0.9237461686134338,
      "learning_rate": 2.7463768115942028e-05,
      "loss": 0.7868,
      "step": 40000
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.9772054553031921,
      "learning_rate": 2.723372440763745e-05,
      "loss": 0.8001,
      "step": 40400
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.9553162455558777,
      "learning_rate": 2.7003680699332874e-05,
      "loss": 0.7898,
      "step": 40800
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.9960311055183411,
      "learning_rate": 2.6773636991028293e-05,
      "loss": 0.7935,
      "step": 41200
    },
    {
      "epoch": 2.37,
      "grad_norm": 1.439426302909851,
      "learning_rate": 2.654474350126524e-05,
      "loss": 0.7809,
      "step": 41600
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.9864240288734436,
      "learning_rate": 2.6315850011502185e-05,
      "loss": 0.7857,
      "step": 42000
    },
    {
      "epoch": 2.42,
      "grad_norm": 1.095920205116272,
      "learning_rate": 2.608580630319761e-05,
      "loss": 0.791,
      "step": 42400
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.9908497929573059,
      "learning_rate": 2.5855762594893028e-05,
      "loss": 0.7902,
      "step": 42800
    },
    {
      "epoch": 2.46,
      "grad_norm": 1.1290860176086426,
      "learning_rate": 2.562571888658845e-05,
      "loss": 0.779,
      "step": 43200
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.1015818119049072,
      "learning_rate": 2.5395675178283874e-05,
      "loss": 0.794,
      "step": 43600
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.9187479615211487,
      "learning_rate": 2.5165631469979294e-05,
      "loss": 0.791,
      "step": 44000
    },
    {
      "epoch": 2.53,
      "grad_norm": 1.1698708534240723,
      "learning_rate": 2.493558776167472e-05,
      "loss": 0.788,
      "step": 44400
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.9840272068977356,
      "learning_rate": 2.4705544053370143e-05,
      "loss": 0.7855,
      "step": 44800
    },
    {
      "epoch": 2.58,
      "grad_norm": 1.0132951736450195,
      "learning_rate": 2.4475500345065562e-05,
      "loss": 0.7701,
      "step": 45200
    },
    {
      "epoch": 2.6,
      "grad_norm": 1.0666146278381348,
      "learning_rate": 2.4245456636760985e-05,
      "loss": 0.7799,
      "step": 45600
    },
    {
      "epoch": 2.62,
      "grad_norm": 1.20628023147583,
      "learning_rate": 2.401541292845641e-05,
      "loss": 0.7764,
      "step": 46000
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.8813405632972717,
      "learning_rate": 2.3785369220151828e-05,
      "loss": 0.7746,
      "step": 46400
    },
    {
      "epoch": 2.67,
      "grad_norm": 1.2259961366653442,
      "learning_rate": 2.355532551184725e-05,
      "loss": 0.7734,
      "step": 46800
    },
    {
      "epoch": 2.69,
      "grad_norm": 0.9694178700447083,
      "learning_rate": 2.3325281803542674e-05,
      "loss": 0.7784,
      "step": 47200
    },
    {
      "epoch": 2.71,
      "grad_norm": 1.1529206037521362,
      "learning_rate": 2.3095238095238097e-05,
      "loss": 0.7711,
      "step": 47600
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.9313886165618896,
      "learning_rate": 2.286519438693352e-05,
      "loss": 0.7797,
      "step": 48000
    },
    {
      "epoch": 2.76,
      "grad_norm": 1.1616884469985962,
      "learning_rate": 2.2635150678628943e-05,
      "loss": 0.7694,
      "step": 48400
    },
    {
      "epoch": 2.78,
      "grad_norm": 1.096562147140503,
      "learning_rate": 2.2405106970324362e-05,
      "loss": 0.7627,
      "step": 48800
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.990018904209137,
      "learning_rate": 2.2175063262019785e-05,
      "loss": 0.7674,
      "step": 49200
    },
    {
      "epoch": 2.83,
      "grad_norm": 1.0565036535263062,
      "learning_rate": 2.194501955371521e-05,
      "loss": 0.7606,
      "step": 49600
    },
    {
      "epoch": 2.85,
      "grad_norm": 1.1336785554885864,
      "learning_rate": 2.1714975845410628e-05,
      "loss": 0.759,
      "step": 50000
    },
    {
      "epoch": 2.87,
      "grad_norm": 1.0509406328201294,
      "learning_rate": 2.148493213710605e-05,
      "loss": 0.777,
      "step": 50400
    },
    {
      "epoch": 2.89,
      "grad_norm": 1.0363755226135254,
      "learning_rate": 2.1254888428801474e-05,
      "loss": 0.7692,
      "step": 50800
    },
    {
      "epoch": 2.92,
      "grad_norm": 1.204566240310669,
      "learning_rate": 2.1024844720496894e-05,
      "loss": 0.7695,
      "step": 51200
    },
    {
      "epoch": 2.94,
      "grad_norm": 1.0907776355743408,
      "learning_rate": 2.0794801012192317e-05,
      "loss": 0.7718,
      "step": 51600
    },
    {
      "epoch": 2.96,
      "grad_norm": 1.0475547313690186,
      "learning_rate": 2.05653324131585e-05,
      "loss": 0.7688,
      "step": 52000
    },
    {
      "epoch": 2.99,
      "grad_norm": 1.2301433086395264,
      "learning_rate": 2.0335288704853922e-05,
      "loss": 0.7614,
      "step": 52400
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.177372694015503,
      "eval_runtime": 239.9376,
      "eval_samples_per_second": 251.211,
      "eval_steps_per_second": 3.926,
      "step": 52644
    },
    {
      "epoch": 3.01,
      "grad_norm": 1.330518364906311,
      "learning_rate": 2.0105820105820105e-05,
      "loss": 0.7462,
      "step": 52800
    },
    {
      "epoch": 3.03,
      "grad_norm": 1.0969927310943604,
      "learning_rate": 1.9875776397515528e-05,
      "loss": 0.7272,
      "step": 53200
    },
    {
      "epoch": 3.05,
      "grad_norm": 1.0054128170013428,
      "learning_rate": 1.964573268921095e-05,
      "loss": 0.7164,
      "step": 53600
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.9748343229293823,
      "learning_rate": 1.9416264090177137e-05,
      "loss": 0.7222,
      "step": 54000
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.9346728920936584,
      "learning_rate": 1.9186220381872557e-05,
      "loss": 0.7262,
      "step": 54400
    },
    {
      "epoch": 3.12,
      "grad_norm": 1.0906745195388794,
      "learning_rate": 1.895617667356798e-05,
      "loss": 0.7224,
      "step": 54800
    },
    {
      "epoch": 3.15,
      "grad_norm": 1.0387004613876343,
      "learning_rate": 1.8726132965263403e-05,
      "loss": 0.7319,
      "step": 55200
    },
    {
      "epoch": 3.17,
      "grad_norm": 1.0948784351348877,
      "learning_rate": 1.8496089256958822e-05,
      "loss": 0.7118,
      "step": 55600
    },
    {
      "epoch": 3.19,
      "grad_norm": 0.9571365118026733,
      "learning_rate": 1.8266045548654245e-05,
      "loss": 0.7127,
      "step": 56000
    },
    {
      "epoch": 3.21,
      "grad_norm": 1.0155813694000244,
      "learning_rate": 1.803600184034967e-05,
      "loss": 0.7185,
      "step": 56400
    },
    {
      "epoch": 3.24,
      "grad_norm": 1.0468432903289795,
      "learning_rate": 1.780653324131585e-05,
      "loss": 0.7223,
      "step": 56800
    },
    {
      "epoch": 3.26,
      "grad_norm": 1.0302894115447998,
      "learning_rate": 1.7576489533011274e-05,
      "loss": 0.7179,
      "step": 57200
    },
    {
      "epoch": 3.28,
      "grad_norm": 1.0335286855697632,
      "learning_rate": 1.7346445824706694e-05,
      "loss": 0.7144,
      "step": 57600
    },
    {
      "epoch": 3.31,
      "grad_norm": 1.2124297618865967,
      "learning_rate": 1.7116402116402117e-05,
      "loss": 0.7152,
      "step": 58000
    },
    {
      "epoch": 3.33,
      "grad_norm": 1.2023513317108154,
      "learning_rate": 1.688635840809754e-05,
      "loss": 0.7184,
      "step": 58400
    },
    {
      "epoch": 3.35,
      "grad_norm": 1.0327694416046143,
      "learning_rate": 1.665631469979296e-05,
      "loss": 0.7128,
      "step": 58800
    },
    {
      "epoch": 3.37,
      "grad_norm": 0.9827908873558044,
      "learning_rate": 1.6426270991488382e-05,
      "loss": 0.7162,
      "step": 59200
    },
    {
      "epoch": 3.4,
      "grad_norm": 1.189833641052246,
      "learning_rate": 1.6196227283183805e-05,
      "loss": 0.7235,
      "step": 59600
    },
    {
      "epoch": 3.42,
      "grad_norm": 1.0521001815795898,
      "learning_rate": 1.5966183574879228e-05,
      "loss": 0.7045,
      "step": 60000
    },
    {
      "epoch": 3.44,
      "grad_norm": 1.0198911428451538,
      "learning_rate": 1.573613986657465e-05,
      "loss": 0.711,
      "step": 60400
    },
    {
      "epoch": 3.46,
      "grad_norm": 1.1130218505859375,
      "learning_rate": 1.5506096158270074e-05,
      "loss": 0.7158,
      "step": 60800
    },
    {
      "epoch": 3.49,
      "grad_norm": 0.8894535303115845,
      "learning_rate": 1.5276052449965494e-05,
      "loss": 0.7202,
      "step": 61200
    },
    {
      "epoch": 3.51,
      "grad_norm": 1.1167349815368652,
      "learning_rate": 1.5046008741660917e-05,
      "loss": 0.7139,
      "step": 61600
    },
    {
      "epoch": 3.53,
      "grad_norm": 1.2239285707473755,
      "learning_rate": 1.4815965033356338e-05,
      "loss": 0.7163,
      "step": 62000
    },
    {
      "epoch": 3.56,
      "grad_norm": 1.1781020164489746,
      "learning_rate": 1.458592132505176e-05,
      "loss": 0.7193,
      "step": 62400
    },
    {
      "epoch": 3.58,
      "grad_norm": 1.0834379196166992,
      "learning_rate": 1.4356452726017944e-05,
      "loss": 0.7147,
      "step": 62800
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.991364061832428,
      "learning_rate": 1.4126409017713365e-05,
      "loss": 0.7022,
      "step": 63200
    },
    {
      "epoch": 3.62,
      "grad_norm": 1.1527454853057861,
      "learning_rate": 1.3896365309408788e-05,
      "loss": 0.7171,
      "step": 63600
    },
    {
      "epoch": 3.65,
      "grad_norm": 0.9275304675102234,
      "learning_rate": 1.366632160110421e-05,
      "loss": 0.7083,
      "step": 64000
    },
    {
      "epoch": 3.67,
      "grad_norm": 1.2628445625305176,
      "learning_rate": 1.3436853002070392e-05,
      "loss": 0.7069,
      "step": 64400
    },
    {
      "epoch": 3.69,
      "grad_norm": 1.100540280342102,
      "learning_rate": 1.3206809293765815e-05,
      "loss": 0.7062,
      "step": 64800
    },
    {
      "epoch": 3.72,
      "grad_norm": 1.1310228109359741,
      "learning_rate": 1.2976765585461237e-05,
      "loss": 0.6933,
      "step": 65200
    },
    {
      "epoch": 3.74,
      "grad_norm": 1.2022795677185059,
      "learning_rate": 1.2746721877156661e-05,
      "loss": 0.7096,
      "step": 65600
    },
    {
      "epoch": 3.76,
      "grad_norm": 2.5451197624206543,
      "learning_rate": 1.2516678168852084e-05,
      "loss": 0.7087,
      "step": 66000
    },
    {
      "epoch": 3.78,
      "grad_norm": 1.125082015991211,
      "learning_rate": 1.2286634460547504e-05,
      "loss": 0.6946,
      "step": 66400
    },
    {
      "epoch": 3.81,
      "grad_norm": 1.3816386461257935,
      "learning_rate": 1.2056590752242927e-05,
      "loss": 0.7091,
      "step": 66800
    },
    {
      "epoch": 3.83,
      "grad_norm": 1.197379231452942,
      "learning_rate": 1.182654704393835e-05,
      "loss": 0.7195,
      "step": 67200
    },
    {
      "epoch": 3.85,
      "grad_norm": 1.1002612113952637,
      "learning_rate": 1.1597078444904533e-05,
      "loss": 0.7021,
      "step": 67600
    },
    {
      "epoch": 3.88,
      "grad_norm": 1.1073203086853027,
      "learning_rate": 1.1367034736599954e-05,
      "loss": 0.7033,
      "step": 68000
    },
    {
      "epoch": 3.9,
      "grad_norm": 1.056327223777771,
      "learning_rate": 1.1136991028295377e-05,
      "loss": 0.7127,
      "step": 68400
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.9232028722763062,
      "learning_rate": 1.090752242926156e-05,
      "loss": 0.7055,
      "step": 68800
    },
    {
      "epoch": 3.94,
      "grad_norm": 1.2083985805511475,
      "learning_rate": 1.0678053830227744e-05,
      "loss": 0.702,
      "step": 69200
    },
    {
      "epoch": 3.97,
      "grad_norm": 1.1936637163162231,
      "learning_rate": 1.0448010121923165e-05,
      "loss": 0.6961,
      "step": 69600
    },
    {
      "epoch": 3.99,
      "grad_norm": 1.1006180047988892,
      "learning_rate": 1.0217966413618588e-05,
      "loss": 0.6965,
      "step": 70000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.182397723197937,
      "eval_runtime": 239.7583,
      "eval_samples_per_second": 251.399,
      "eval_steps_per_second": 3.929,
      "step": 70192
    },
    {
      "epoch": 4.01,
      "grad_norm": 0.9501661658287048,
      "learning_rate": 9.988497814584771e-06,
      "loss": 0.681,
      "step": 70400
    },
    {
      "epoch": 4.03,
      "grad_norm": 1.1048214435577393,
      "learning_rate": 9.759029215550954e-06,
      "loss": 0.6718,
      "step": 70800
    },
    {
      "epoch": 4.06,
      "grad_norm": 1.1402852535247803,
      "learning_rate": 9.528985507246377e-06,
      "loss": 0.6646,
      "step": 71200
    },
    {
      "epoch": 4.08,
      "grad_norm": 1.1181689500808716,
      "learning_rate": 9.298941798941798e-06,
      "loss": 0.6803,
      "step": 71600
    },
    {
      "epoch": 4.1,
      "grad_norm": 1.0445771217346191,
      "learning_rate": 9.068898090637221e-06,
      "loss": 0.6681,
      "step": 72000
    },
    {
      "epoch": 4.13,
      "grad_norm": 1.2578911781311035,
      "learning_rate": 8.838854382332644e-06,
      "loss": 0.6743,
      "step": 72400
    },
    {
      "epoch": 4.15,
      "grad_norm": 1.0545594692230225,
      "learning_rate": 8.608810674028066e-06,
      "loss": 0.6721,
      "step": 72800
    },
    {
      "epoch": 4.17,
      "grad_norm": 1.0575259923934937,
      "learning_rate": 8.378766965723487e-06,
      "loss": 0.6692,
      "step": 73200
    },
    {
      "epoch": 4.19,
      "grad_norm": 1.0617632865905762,
      "learning_rate": 8.14872325741891e-06,
      "loss": 0.6634,
      "step": 73600
    },
    {
      "epoch": 4.22,
      "grad_norm": 1.1915861368179321,
      "learning_rate": 7.918679549114331e-06,
      "loss": 0.6712,
      "step": 74000
    },
    {
      "epoch": 4.24,
      "grad_norm": 1.16647207736969,
      "learning_rate": 7.688635840809754e-06,
      "loss": 0.6663,
      "step": 74400
    },
    {
      "epoch": 4.26,
      "grad_norm": 1.0123538970947266,
      "learning_rate": 7.458592132505176e-06,
      "loss": 0.6785,
      "step": 74800
    },
    {
      "epoch": 4.29,
      "grad_norm": 1.0426361560821533,
      "learning_rate": 7.228548424200598e-06,
      "loss": 0.6825,
      "step": 75200
    },
    {
      "epoch": 4.31,
      "grad_norm": 1.0516417026519775,
      "learning_rate": 6.9985047158960205e-06,
      "loss": 0.6662,
      "step": 75600
    },
    {
      "epoch": 4.33,
      "grad_norm": 1.0297150611877441,
      "learning_rate": 6.768461007591443e-06,
      "loss": 0.667,
      "step": 76000
    },
    {
      "epoch": 4.35,
      "grad_norm": 1.1151374578475952,
      "learning_rate": 6.538417299286864e-06,
      "loss": 0.6612,
      "step": 76400
    },
    {
      "epoch": 4.38,
      "grad_norm": 1.100305438041687,
      "learning_rate": 6.308373590982288e-06,
      "loss": 0.6731,
      "step": 76800
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.0381314754486084,
      "learning_rate": 6.078904991948471e-06,
      "loss": 0.6816,
      "step": 77200
    },
    {
      "epoch": 4.42,
      "grad_norm": 1.166762351989746,
      "learning_rate": 5.848861283643893e-06,
      "loss": 0.6674,
      "step": 77600
    },
    {
      "epoch": 4.44,
      "grad_norm": 1.1503565311431885,
      "learning_rate": 5.619392684610076e-06,
      "loss": 0.6711,
      "step": 78000
    },
    {
      "epoch": 4.47,
      "grad_norm": 1.2317191362380981,
      "learning_rate": 5.3893489763054985e-06,
      "loss": 0.6754,
      "step": 78400
    },
    {
      "epoch": 4.49,
      "grad_norm": 1.1069433689117432,
      "learning_rate": 5.159305268000921e-06,
      "loss": 0.6657,
      "step": 78800
    },
    {
      "epoch": 4.51,
      "grad_norm": 1.081761121749878,
      "learning_rate": 4.929261559696342e-06,
      "loss": 0.6632,
      "step": 79200
    },
    {
      "epoch": 4.54,
      "grad_norm": 1.0425435304641724,
      "learning_rate": 4.699217851391765e-06,
      "loss": 0.6607,
      "step": 79600
    },
    {
      "epoch": 4.56,
      "grad_norm": 1.1054120063781738,
      "learning_rate": 4.469174143087187e-06,
      "loss": 0.6747,
      "step": 80000
    },
    {
      "epoch": 4.58,
      "grad_norm": 1.1128557920455933,
      "learning_rate": 4.239130434782608e-06,
      "loss": 0.6686,
      "step": 80400
    },
    {
      "epoch": 4.6,
      "grad_norm": 1.2730941772460938,
      "learning_rate": 4.009086726478031e-06,
      "loss": 0.6733,
      "step": 80800
    },
    {
      "epoch": 4.63,
      "grad_norm": 1.291892647743225,
      "learning_rate": 3.779043018173453e-06,
      "loss": 0.6631,
      "step": 81200
    },
    {
      "epoch": 4.65,
      "grad_norm": 0.9876201152801514,
      "learning_rate": 3.548999309868875e-06,
      "loss": 0.6691,
      "step": 81600
    },
    {
      "epoch": 4.67,
      "grad_norm": 1.2430497407913208,
      "learning_rate": 3.3189556015642977e-06,
      "loss": 0.6579,
      "step": 82000
    },
    {
      "epoch": 4.7,
      "grad_norm": 1.012856364250183,
      "learning_rate": 3.0889118932597194e-06,
      "loss": 0.6637,
      "step": 82400
    },
    {
      "epoch": 4.72,
      "grad_norm": 1.1547410488128662,
      "learning_rate": 2.8588681849551415e-06,
      "loss": 0.6801,
      "step": 82800
    },
    {
      "epoch": 4.74,
      "grad_norm": 1.1335712671279907,
      "learning_rate": 2.6288244766505636e-06,
      "loss": 0.6717,
      "step": 83200
    },
    {
      "epoch": 4.76,
      "grad_norm": 1.0243676900863647,
      "learning_rate": 2.3987807683459858e-06,
      "loss": 0.6639,
      "step": 83600
    },
    {
      "epoch": 4.79,
      "grad_norm": 1.0435352325439453,
      "learning_rate": 2.1693121693121695e-06,
      "loss": 0.677,
      "step": 84000
    },
    {
      "epoch": 4.81,
      "grad_norm": 1.1295571327209473,
      "learning_rate": 1.9398435702783527e-06,
      "loss": 0.6614,
      "step": 84400
    },
    {
      "epoch": 4.83,
      "grad_norm": 1.0412089824676514,
      "learning_rate": 1.7103749712445366e-06,
      "loss": 0.6613,
      "step": 84800
    },
    {
      "epoch": 4.86,
      "grad_norm": 1.0020956993103027,
      "learning_rate": 1.4803312629399585e-06,
      "loss": 0.6729,
      "step": 85200
    },
    {
      "epoch": 4.88,
      "grad_norm": 1.2422608137130737,
      "learning_rate": 1.2502875546353809e-06,
      "loss": 0.6599,
      "step": 85600
    },
    {
      "epoch": 4.9,
      "grad_norm": 1.1637760400772095,
      "learning_rate": 1.0202438463308028e-06,
      "loss": 0.664,
      "step": 86000
    },
    {
      "epoch": 4.92,
      "grad_norm": 1.0108635425567627,
      "learning_rate": 7.902001380262249e-07,
      "loss": 0.6627,
      "step": 86400
    },
    {
      "epoch": 4.95,
      "grad_norm": 1.2056249380111694,
      "learning_rate": 5.601564297216472e-07,
      "loss": 0.67,
      "step": 86800
    },
    {
      "epoch": 4.97,
      "grad_norm": 3.1152091026306152,
      "learning_rate": 3.301127214170693e-07,
      "loss": 0.6619,
      "step": 87200
    },
    {
      "epoch": 4.99,
      "grad_norm": 1.2400481700897217,
      "learning_rate": 1.0006901311249138e-07,
      "loss": 0.6636,
      "step": 87600
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.1956850290298462,
      "eval_runtime": 239.8036,
      "eval_samples_per_second": 251.351,
      "eval_steps_per_second": 3.928,
      "step": 87740
    },
    {
      "epoch": 5.0,
      "step": 87740,
      "total_flos": 1.7097588901675008e+18,
      "train_loss": 0.8546056313098415,
      "train_runtime": 31454.7003,
      "train_samples_per_second": 89.265,
      "train_steps_per_second": 2.789
    }
  ],
  "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
}