{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1208,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 0.12706246972084045,
      "learning_rate": 0.0004324324324324325,
      "loss": 4.2683,
      "step": 16
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 0.1603141874074936,
      "learning_rate": 0.000864864864864865,
      "loss": 4.2333,
      "step": 32
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 0.11292944103479385,
      "learning_rate": 0.0009997822892796068,
      "loss": 4.2693,
      "step": 48
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 0.126583069562912,
      "learning_rate": 0.000998688816161266,
      "loss": 4.2745,
      "step": 64
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.1791575849056244,
      "learning_rate": 0.0009966766110013582,
      "loss": 4.2707,
      "step": 80
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 0.16615551710128784,
      "learning_rate": 0.0009937493808759087,
      "loss": 4.3332,
      "step": 96
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": 0.17333188652992249,
      "learning_rate": 0.0009899125186070988,
      "loss": 4.2671,
      "step": 112
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": 0.14814811944961548,
      "learning_rate": 0.0009851730928280944,
      "loss": 4.2474,
      "step": 128
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": 0.16701027750968933,
      "learning_rate": 0.0009795398349605373,
      "loss": 4.248,
      "step": 144
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 0.11271824687719345,
      "learning_rate": 0.0009730231231286876,
      "loss": 4.2506,
      "step": 160
    },
    {
      "epoch": 0.2913907284768212,
      "grad_norm": 0.10354705899953842,
      "learning_rate": 0.0009656349630398554,
      "loss": 4.2424,
      "step": 176
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 0.1165025606751442,
      "learning_rate": 0.0009573889658663424,
      "loss": 4.2973,
      "step": 192
    },
    {
      "epoch": 0.3443708609271523,
      "grad_norm": 0.1250074803829193,
      "learning_rate": 0.0009483003231696446,
      "loss": 4.2571,
      "step": 208
    },
    {
      "epoch": 0.3708609271523179,
      "grad_norm": 0.13243281841278076,
      "learning_rate": 0.0009383857789131097,
      "loss": 4.2659,
      "step": 224
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 0.10707055032253265,
      "learning_rate": 0.0009276635986146136,
      "loss": 4.2331,
      "step": 240
    },
    {
      "epoch": 0.423841059602649,
      "grad_norm": 0.12676522135734558,
      "learning_rate": 0.0009161535356960828,
      "loss": 4.2585,
      "step": 256
    },
    {
      "epoch": 0.4503311258278146,
      "grad_norm": 0.10248049348592758,
      "learning_rate": 0.0009038767950918592,
      "loss": 4.2375,
      "step": 272
    },
    {
      "epoch": 0.4768211920529801,
      "grad_norm": 0.16809116303920746,
      "learning_rate": 0.0008908559941829497,
      "loss": 4.2249,
      "step": 288
    },
    {
      "epoch": 0.5033112582781457,
      "grad_norm": 0.11593299359083176,
      "learning_rate": 0.0008771151211291332,
      "loss": 4.2411,
      "step": 304
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 0.11452265083789825,
      "learning_rate": 0.0008626794906756866,
      "loss": 4.2158,
      "step": 320
    },
    {
      "epoch": 0.5562913907284768,
      "grad_norm": 0.14648571610450745,
      "learning_rate": 0.0008475756975161504,
      "loss": 4.2718,
      "step": 336
    },
    {
      "epoch": 0.5827814569536424,
      "grad_norm": 0.11873907595872879,
      "learning_rate": 0.00083183156729705,
      "loss": 4.2431,
      "step": 352
    },
    {
      "epoch": 0.609271523178808,
      "grad_norm": 0.13245505094528198,
      "learning_rate": 0.0008154761053548404,
      "loss": 4.2546,
      "step": 368
    },
    {
      "epoch": 0.6357615894039735,
      "grad_norm": 0.12086515128612518,
      "learning_rate": 0.000798539443279511,
      "loss": 4.2042,
      "step": 384
    },
    {
      "epoch": 0.6622516556291391,
      "grad_norm": 0.09804444760084152,
      "learning_rate": 0.0007810527834033009,
      "loss": 4.2046,
      "step": 400
    },
    {
      "epoch": 0.6887417218543046,
      "grad_norm": 0.12007380276918411,
      "learning_rate": 0.00076304834131679,
      "loss": 4.2311,
      "step": 416
    },
    {
      "epoch": 0.7152317880794702,
      "grad_norm": 0.12332040816545486,
      "learning_rate": 0.0007445592865182695,
      "loss": 4.2304,
      "step": 432
    },
    {
      "epoch": 0.7417218543046358,
      "grad_norm": 0.12303052097558975,
      "learning_rate": 0.0007256196813057318,
      "loss": 4.2351,
      "step": 448
    },
    {
      "epoch": 0.7682119205298014,
      "grad_norm": 0.09435882419347763,
      "learning_rate": 0.0007062644180240614,
      "loss": 4.1903,
      "step": 464
    },
    {
      "epoch": 0.7947019867549668,
      "grad_norm": 0.12024106830358505,
      "learning_rate": 0.0006865291547830324,
      "loss": 4.2468,
      "step": 480
    },
    {
      "epoch": 0.8211920529801324,
      "grad_norm": 0.09838169813156128,
      "learning_rate": 0.000666450249764542,
      "loss": 4.1978,
      "step": 496
    },
    {
      "epoch": 0.847682119205298,
      "grad_norm": 0.10983674973249435,
      "learning_rate": 0.0006460646942401058,
      "loss": 4.2443,
      "step": 512
    },
    {
      "epoch": 0.8741721854304636,
      "grad_norm": 0.09954366832971573,
      "learning_rate": 0.0006254100444220115,
      "loss": 4.227,
      "step": 528
    },
    {
      "epoch": 0.9006622516556292,
      "grad_norm": 0.12015046179294586,
      "learning_rate": 0.0006045243522736885,
      "loss": 4.2154,
      "step": 544
    },
    {
      "epoch": 0.9271523178807947,
      "grad_norm": 0.10851255804300308,
      "learning_rate": 0.0005834460954067559,
      "loss": 4.242,
      "step": 560
    },
    {
      "epoch": 0.9536423841059603,
      "grad_norm": 0.0975833460688591,
      "learning_rate": 0.0005622141061939006,
      "loss": 4.2135,
      "step": 576
    },
    {
      "epoch": 0.9801324503311258,
      "grad_norm": 0.10621072351932526,
      "learning_rate": 0.0005408675002281818,
      "loss": 4.2932,
      "step": 592
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.1135024238637086,
      "eval_cap_loss": 1.2033403850351738,
      "eval_con_loss": 1.786089795906812,
      "eval_loss": 2.9894301812380353,
      "step": 604
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.1135024238637086,
      "eval_cap_loss": 1.2033403850351738,
      "eval_con_loss": 1.786089795906812,
      "eval_loss": 2.9894301812380353,
      "eval_runtime": 416.7065,
      "eval_samples_per_second": 11.588,
      "eval_steps_per_second": 1.449,
      "step": 604
    },
    {
      "epoch": 1.0066225165562914,
      "grad_norm": 0.13524451851844788,
      "learning_rate": 0.0005194456042605587,
      "loss": 4.1897,
      "step": 608
    },
    {
      "epoch": 1.033112582781457,
      "grad_norm": 0.09372173994779587,
      "learning_rate": 0.0004979878837484043,
      "loss": 4.2234,
      "step": 624
    },
    {
      "epoch": 1.0596026490066226,
      "grad_norm": 0.10636495053768158,
      "learning_rate": 0.00047653387014848014,
      "loss": 4.2304,
      "step": 640
    },
    {
      "epoch": 1.086092715231788,
      "grad_norm": 0.1295643150806427,
      "learning_rate": 0.0004551230880883208,
      "loss": 4.2388,
      "step": 656
    },
    {
      "epoch": 1.1125827814569536,
      "grad_norm": 0.10932028293609619,
      "learning_rate": 0.00043379498255020037,
      "loss": 4.2505,
      "step": 672
    },
    {
      "epoch": 1.1390728476821192,
      "grad_norm": 0.11317116022109985,
      "learning_rate": 0.00041258884620182804,
      "loss": 4.2256,
      "step": 688
    },
    {
      "epoch": 1.1655629139072847,
      "grad_norm": 0.15960782766342163,
      "learning_rate": 0.00039154374700765316,
      "loss": 4.2248,
      "step": 704
    },
    {
      "epoch": 1.1920529801324504,
      "grad_norm": 0.14448010921478271,
      "learning_rate": 0.00037069845625413954,
      "loss": 4.248,
      "step": 720
    },
    {
      "epoch": 1.218543046357616,
      "grad_norm": 0.12560078501701355,
      "learning_rate": 0.0003500913771216081,
      "loss": 4.2264,
      "step": 736
    },
    {
      "epoch": 1.2450331125827814,
      "grad_norm": 0.15087343752384186,
      "learning_rate": 0.0003297604739342396,
      "loss": 4.2582,
      "step": 752
    },
    {
      "epoch": 1.271523178807947,
      "grad_norm": 0.14385798573493958,
      "learning_rate": 0.00030974320221858066,
      "loss": 4.2413,
      "step": 768
    },
    {
      "epoch": 1.2980132450331126,
      "grad_norm": 0.12157344818115234,
      "learning_rate": 0.0002900764396994049,
      "loss": 4.2285,
      "step": 784
    },
    {
      "epoch": 1.3245033112582782,
      "grad_norm": 0.14533455669879913,
      "learning_rate": 0.00027079641836005473,
      "loss": 4.2719,
      "step": 800
    },
    {
      "epoch": 1.3509933774834437,
      "grad_norm": 0.11581210792064667,
      "learning_rate": 0.0002519386576924303,
      "loss": 4.2191,
      "step": 816
    },
    {
      "epoch": 1.3774834437086092,
      "grad_norm": 0.11933822929859161,
      "learning_rate": 0.0002335378992595995,
      "loss": 4.1929,
      "step": 832
    },
    {
      "epoch": 1.403973509933775,
      "grad_norm": 0.13587485253810883,
      "learning_rate": 0.0002156280426915786,
      "loss": 4.2147,
      "step": 848
    },
    {
      "epoch": 1.4304635761589404,
      "grad_norm": 0.11555938422679901,
      "learning_rate": 0.00019824208323220656,
      "loss": 4.2268,
      "step": 864
    },
    {
      "epoch": 1.4569536423841059,
      "grad_norm": 0.12277619540691376,
      "learning_rate": 0.00018141205095216294,
      "loss": 4.2261,
      "step": 880
    },
    {
      "epoch": 1.4834437086092715,
      "grad_norm": 0.11538510024547577,
      "learning_rate": 0.00016516895174012043,
      "loss": 4.1956,
      "step": 896
    },
    {
      "epoch": 1.5099337748344372,
      "grad_norm": 0.10595931112766266,
      "learning_rate": 0.00014954271018074368,
      "loss": 4.2703,
      "step": 912
    },
    {
      "epoch": 1.5364238410596025,
      "grad_norm": 0.12333059310913086,
      "learning_rate": 0.00013456211442476813,
      "loss": 4.1822,
      "step": 928
    },
    {
      "epoch": 1.5629139072847682,
      "grad_norm": 0.10703016817569733,
      "learning_rate": 0.00012025476315272743,
      "loss": 4.2289,
      "step": 944
    },
    {
      "epoch": 1.589403973509934,
      "grad_norm": 0.11507616937160492,
      "learning_rate": 0.00010664701473003396,
      "loss": 4.2223,
      "step": 960
    },
    {
      "epoch": 1.6158940397350994,
      "grad_norm": 0.09708770364522934,
      "learning_rate": 9.376393864708821e-05,
      "loss": 4.2223,
      "step": 976
    },
    {
      "epoch": 1.6423841059602649,
      "grad_norm": 0.11372318863868713,
      "learning_rate": 8.162926933387499e-05,
      "loss": 4.2433,
      "step": 992
    },
    {
      "epoch": 1.6688741721854305,
      "grad_norm": 0.16325490176677704,
      "learning_rate": 7.026536243413539e-05,
      "loss": 4.2427,
      "step": 1008
    },
    {
      "epoch": 1.695364238410596,
      "grad_norm": 0.10167232900857925,
      "learning_rate": 5.969315361967087e-05,
      "loss": 4.1995,
      "step": 1024
    },
    {
      "epoch": 1.7218543046357615,
      "grad_norm": 0.11737249046564102,
      "learning_rate": 4.9932120020654116e-05,
      "loss": 4.2522,
      "step": 1040
    },
    {
      "epoch": 1.7483443708609272,
      "grad_norm": 0.10857795923948288,
      "learning_rate": 4.100024434300437e-05,
      "loss": 4.1555,
      "step": 1056
    },
    {
      "epoch": 1.7748344370860927,
      "grad_norm": 0.11734642088413239,
      "learning_rate": 3.2913981738933395e-05,
      "loss": 4.208,
      "step": 1072
    },
    {
      "epoch": 1.8013245033112582,
      "grad_norm": 0.10702993720769882,
      "learning_rate": 2.5688229491697356e-05,
      "loss": 4.2835,
      "step": 1088
    },
    {
      "epoch": 1.8278145695364238,
      "grad_norm": 0.12669378519058228,
      "learning_rate": 1.9336299570401396e-05,
      "loss": 4.2288,
      "step": 1104
    },
    {
      "epoch": 1.8543046357615895,
      "grad_norm": 0.0894075259566307,
      "learning_rate": 1.3869894105423109e-05,
      "loss": 4.2051,
      "step": 1120
    },
    {
      "epoch": 1.8807947019867548,
      "grad_norm": 0.09530144929885864,
      "learning_rate": 9.299083829632516e-06,
      "loss": 4.2449,
      "step": 1136
    },
    {
      "epoch": 1.9072847682119205,
      "grad_norm": 0.13094228506088257,
      "learning_rate": 5.632289525129064e-06,
      "loss": 4.2017,
      "step": 1152
    },
    {
      "epoch": 1.9337748344370862,
      "grad_norm": 0.12416987866163254,
      "learning_rate": 2.8762665096744854e-06,
      "loss": 4.1943,
      "step": 1168
    },
    {
      "epoch": 1.9602649006622517,
      "grad_norm": 0.10805880278348923,
      "learning_rate": 1.036092191402882e-06,
      "loss": 4.1936,
      "step": 1184
    },
    {
      "epoch": 1.9867549668874172,
      "grad_norm": 0.11822624504566193,
      "learning_rate": 1.1515671473599775e-07,
      "loss": 4.2833,
      "step": 1200
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.1159956729511227,
      "eval_cap_loss": 1.1952345237037203,
      "eval_con_loss": 1.7797789394066035,
      "eval_loss": 2.975013460544561,
      "step": 1208
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.1159956729511227,
      "eval_cap_loss": 1.1952345237037203,
      "eval_con_loss": 1.7797789394066035,
      "eval_loss": 2.975013460544561,
      "eval_runtime": 297.535,
      "eval_samples_per_second": 16.23,
      "eval_steps_per_second": 2.03,
      "step": 1208
    }
  ],
  "logging_steps": 16,
  "max_steps": 1208,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null,
  "tau_value": 5.2037
}