{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1651287032540067,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01942690626517727,
      "grad_norm": 0.26180756092071533,
      "learning_rate": 8.653846153846155e-06,
      "loss": 0.40127906799316404,
      "step": 10
    },
    {
      "epoch": 0.03885381253035454,
      "grad_norm": 0.1655670404434204,
      "learning_rate": 1.826923076923077e-05,
      "loss": 0.3694923400878906,
      "step": 20
    },
    {
      "epoch": 0.05828071879553181,
      "grad_norm": 0.21055534482002258,
      "learning_rate": 2.7884615384615386e-05,
      "loss": 0.3756622076034546,
      "step": 30
    },
    {
      "epoch": 0.07770762506070908,
      "grad_norm": 0.2429058700799942,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.3154024600982666,
      "step": 40
    },
    {
      "epoch": 0.09713453132588636,
      "grad_norm": 0.18555547297000885,
      "learning_rate": 4.711538461538462e-05,
      "loss": 0.31356382369995117,
      "step": 50
    },
    {
      "epoch": 0.11656143759106362,
      "grad_norm": 0.24774602055549622,
      "learning_rate": 4.99936801054781e-05,
      "loss": 0.23598077297210693,
      "step": 60
    },
    {
      "epoch": 0.1359883438562409,
      "grad_norm": 0.1604267954826355,
      "learning_rate": 4.996273321192579e-05,
      "loss": 0.26249558925628663,
      "step": 70
    },
    {
      "epoch": 0.15541525012141816,
      "grad_norm": 0.18501052260398865,
      "learning_rate": 4.990603041267143e-05,
      "loss": 0.2521421194076538,
      "step": 80
    },
    {
      "epoch": 0.17484215638659542,
      "grad_norm": 0.13454674184322357,
      "learning_rate": 4.982363021220401e-05,
      "loss": 0.31869068145751955,
      "step": 90
    },
    {
      "epoch": 0.1942690626517727,
      "grad_norm": 0.11859218776226044,
      "learning_rate": 4.971561762892976e-05,
      "loss": 0.23399407863616944,
      "step": 100
    },
    {
      "epoch": 0.21369596891694997,
      "grad_norm": 0.16577711701393127,
      "learning_rate": 4.958210410745236e-05,
      "loss": 0.2260490894317627,
      "step": 110
    },
    {
      "epoch": 0.23312287518212724,
      "grad_norm": 0.11132260411977768,
      "learning_rate": 4.942322740358726e-05,
      "loss": 0.23589625358581542,
      "step": 120
    },
    {
      "epoch": 0.2525497814473045,
      "grad_norm": 0.20756852626800537,
      "learning_rate": 4.9239151442228726e-05,
      "loss": 0.3080857038497925,
      "step": 130
    },
    {
      "epoch": 0.2719766877124818,
      "grad_norm": 0.09589740633964539,
      "learning_rate": 4.9030066148216445e-05,
      "loss": 0.23507814407348632,
      "step": 140
    },
    {
      "epoch": 0.2914035939776591,
      "grad_norm": 0.13812342286109924,
      "learning_rate": 4.879618725037587e-05,
      "loss": 0.2745722055435181,
      "step": 150
    },
    {
      "epoch": 0.3108305002428363,
      "grad_norm": 0.17384353280067444,
      "learning_rate": 4.8537756058934826e-05,
      "loss": 0.26914730072021487,
      "step": 160
    },
    {
      "epoch": 0.3302574065080136,
      "grad_norm": 0.1553693562746048,
      "learning_rate": 4.8255039216545814e-05,
      "loss": 0.2960189342498779,
      "step": 170
    },
    {
      "epoch": 0.34968431277319084,
      "grad_norm": 0.15468068420886993,
      "learning_rate": 4.794832842317098e-05,
      "loss": 0.26504876613616946,
      "step": 180
    },
    {
      "epoch": 0.36911121903836813,
      "grad_norm": 0.1495364010334015,
      "learning_rate": 4.7617940135113606e-05,
      "loss": 0.20354897975921632,
      "step": 190
    },
    {
      "epoch": 0.3885381253035454,
      "grad_norm": 0.0979977622628212,
      "learning_rate": 4.726421523850662e-05,
      "loss": 0.23614444732666015,
      "step": 200
    },
    {
      "epoch": 0.40796503156872266,
      "grad_norm": 0.14897684752941132,
      "learning_rate": 4.6887518697595096e-05,
      "loss": 0.24106810092926026,
      "step": 210
    },
    {
      "epoch": 0.42739193783389995,
      "grad_norm": 0.11905848234891891,
      "learning_rate": 4.648823917817551e-05,
      "loss": 0.2708190202713013,
      "step": 220
    },
    {
      "epoch": 0.44681884409907724,
      "grad_norm": 0.1429329812526703,
      "learning_rate": 4.606678864658038e-05,
      "loss": 0.25339953899383544,
      "step": 230
    },
    {
      "epoch": 0.4662457503642545,
      "grad_norm": 0.20242151618003845,
      "learning_rate": 4.5623601944622016e-05,
      "loss": 0.2554117441177368,
      "step": 240
    },
    {
      "epoch": 0.48567265662943176,
      "grad_norm": 0.1589473932981491,
      "learning_rate": 4.5159136340933896e-05,
      "loss": 0.1923211097717285,
      "step": 250
    },
    {
      "epoch": 0.505099562894609,
      "grad_norm": 0.15873779356479645,
      "learning_rate": 4.467387105917269e-05,
      "loss": 0.20048885345458983,
      "step": 260
    },
    {
      "epoch": 0.5245264691597863,
      "grad_norm": 0.15066051483154297,
      "learning_rate": 4.416830678356764e-05,
      "loss": 0.2062215566635132,
      "step": 270
    },
    {
      "epoch": 0.5439533754249636,
      "grad_norm": 0.20589925348758698,
      "learning_rate": 4.36429651423274e-05,
      "loss": 0.29201040267944334,
      "step": 280
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 0.2139367163181305,
      "learning_rate": 4.3098388169437545e-05,
      "loss": 0.23367040157318114,
      "step": 290
    },
    {
      "epoch": 0.5828071879553182,
      "grad_norm": 0.1904798150062561,
      "learning_rate": 4.2535137745403766e-05,
      "loss": 0.2543118953704834,
      "step": 300
    },
    {
      "epoch": 0.6022340942204953,
      "grad_norm": 0.18315282464027405,
      "learning_rate": 4.1953795017518116e-05,
      "loss": 0.2573453664779663,
      "step": 310
    },
    {
      "epoch": 0.6216610004856726,
      "grad_norm": 0.12616890668869019,
      "learning_rate": 4.135495980024615e-05,
      "loss": 0.2318727493286133,
      "step": 320
    },
    {
      "epoch": 0.6410879067508499,
      "grad_norm": 0.17712046205997467,
      "learning_rate": 4.073924995635376e-05,
      "loss": 0.18010640144348145,
      "step": 330
    },
    {
      "epoch": 0.6605148130160272,
      "grad_norm": 0.12199205160140991,
      "learning_rate": 4.010730075941236e-05,
      "loss": 0.19334938526153564,
      "step": 340
    },
    {
      "epoch": 0.6799417192812045,
      "grad_norm": 0.27177831530570984,
      "learning_rate": 3.9459764238339865e-05,
      "loss": 0.21652016639709473,
      "step": 350
    },
    {
      "epoch": 0.6993686255463817,
      "grad_norm": 0.15285901725292206,
      "learning_rate": 3.8797308504654116e-05,
      "loss": 0.26627991199493406,
      "step": 360
    },
    {
      "epoch": 0.718795531811559,
      "grad_norm": 0.12266906350851059,
      "learning_rate": 3.812061706313256e-05,
      "loss": 0.27732465267181394,
      "step": 370
    },
    {
      "epoch": 0.7382224380767363,
      "grad_norm": 0.17022156715393066,
      "learning_rate": 3.743038810658963e-05,
      "loss": 0.24920461177825928,
      "step": 380
    },
    {
      "epoch": 0.7576493443419136,
      "grad_norm": 0.13355037569999695,
      "learning_rate": 3.6727333795499375e-05,
      "loss": 0.19189114570617677,
      "step": 390
    },
    {
      "epoch": 0.7770762506070908,
      "grad_norm": 0.15375971794128418,
      "learning_rate": 3.6012179523206576e-05,
      "loss": 0.20400729179382324,
      "step": 400
    },
    {
      "epoch": 0.7965031568722681,
      "grad_norm": 0.2069733738899231,
      "learning_rate": 3.5285663167484616e-05,
      "loss": 0.3037395715713501,
      "step": 410
    },
    {
      "epoch": 0.8159300631374453,
      "grad_norm": 0.1796797662973404,
      "learning_rate": 3.4548534329212144e-05,
      "loss": 0.34220497608184813,
      "step": 420
    },
    {
      "epoch": 0.8353569694026226,
      "grad_norm": 0.18201130628585815,
      "learning_rate": 3.380155355895416e-05,
      "loss": 0.2813987731933594,
      "step": 430
    },
    {
      "epoch": 0.8547838756677999,
      "grad_norm": 0.14474698901176453,
      "learning_rate": 3.304549157224558e-05,
      "loss": 0.2509459495544434,
      "step": 440
    },
    {
      "epoch": 0.8742107819329772,
      "grad_norm": 0.17002937197685242,
      "learning_rate": 3.228112845438672e-05,
      "loss": 0.25137474536895754,
      "step": 450
    },
    {
      "epoch": 0.8936376881981545,
      "grad_norm": 0.20442189276218414,
      "learning_rate": 3.150925285557141e-05,
      "loss": 0.23509564399719238,
      "step": 460
    },
    {
      "epoch": 0.9130645944633318,
      "grad_norm": 0.14680618047714233,
      "learning_rate": 3.0730661177177954e-05,
      "loss": 0.19746966361999513,
      "step": 470
    },
    {
      "epoch": 0.932491500728509,
      "grad_norm": 0.1439915895462036,
      "learning_rate": 2.994615675006277e-05,
      "loss": 0.254872727394104,
      "step": 480
    },
    {
      "epoch": 0.9519184069936862,
      "grad_norm": 0.16022782027721405,
      "learning_rate": 2.9156549005704203e-05,
      "loss": 0.1682429313659668,
      "step": 490
    },
    {
      "epoch": 0.9713453132588635,
      "grad_norm": 0.17126372456550598,
      "learning_rate": 2.8362652641052025e-05,
      "loss": 0.2580049991607666,
      "step": 500
    },
    {
      "epoch": 0.9907722195240408,
      "grad_norm": 0.19092383980751038,
      "learning_rate": 2.756528677794402e-05,
      "loss": 0.1847946286201477,
      "step": 510
    },
    {
      "epoch": 1.0097134531325886,
      "grad_norm": 0.2421938180923462,
      "learning_rate": 2.6765274117957227e-05,
      "loss": 0.20903294086456298,
      "step": 520
    },
    {
      "epoch": 1.029140359397766,
      "grad_norm": 0.19591616094112396,
      "learning_rate": 2.5963440093565566e-05,
      "loss": 0.15802922248840331,
      "step": 530
    },
    {
      "epoch": 1.0485672656629432,
      "grad_norm": 0.21306180953979492,
      "learning_rate": 2.5160612016479884e-05,
      "loss": 0.18800711631774902,
      "step": 540
    },
    {
      "epoch": 1.0679941719281205,
      "grad_norm": 0.21616265177726746,
      "learning_rate": 2.4357618224049008e-05,
      "loss": 0.2516720056533813,
      "step": 550
    },
    {
      "epoch": 1.0874210781932978,
      "grad_norm": 0.1722310185432434,
      "learning_rate": 2.355528722460261e-05,
      "loss": 0.13848392963409423,
      "step": 560
    },
    {
      "epoch": 1.1068479844584749,
      "grad_norm": 0.16589082777500153,
      "learning_rate": 2.27544468426176e-05,
      "loss": 0.16518881320953369,
      "step": 570
    },
    {
      "epoch": 1.1262748907236522,
      "grad_norm": 0.19981171190738678,
      "learning_rate": 2.1955923364590167e-05,
      "loss": 0.18203474283218385,
      "step": 580
    },
    {
      "epoch": 1.1457017969888295,
      "grad_norm": 0.1736886352300644,
      "learning_rate": 2.1160540686494594e-05,
      "loss": 0.2113028049468994,
      "step": 590
    },
    {
      "epoch": 1.1651287032540067,
      "grad_norm": 0.2363515943288803,
      "learning_rate": 2.0369119463708675e-05,
      "loss": 0.14112727642059325,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 1030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.720649024869451e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}