{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 0.31839632987976074,
      "learning_rate": 4.5e-06,
      "loss": 1.2127,
      "step": 10
    },
    {
      "grad_norm": 0.19609376788139343,
      "learning_rate": 9.5e-06,
      "loss": 1.1842,
      "step": 20
    },
    {
      "grad_norm": 0.4635807275772095,
      "learning_rate": 1.45e-05,
      "loss": 1.1838,
      "step": 30
    },
    {
      "grad_norm": 0.3277273178100586,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 1.1629,
      "step": 40
    },
    {
      "grad_norm": 0.40489643812179565,
      "learning_rate": 2.45e-05,
      "loss": 1.1264,
      "step": 50
    },
    {
      "grad_norm": 1.2546579837799072,
      "learning_rate": 2.95e-05,
      "loss": 1.1117,
      "step": 60
    },
    {
      "grad_norm": 0.3789711594581604,
      "learning_rate": 3.45e-05,
      "loss": 1.1066,
      "step": 70
    },
    {
      "grad_norm": 0.3612673878669739,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 1.1082,
      "step": 80
    },
    {
      "grad_norm": 0.28633758425712585,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 1.1211,
      "step": 90
    },
    {
      "grad_norm": 0.41268351674079895,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 1.0998,
      "step": 100
    },
    {
      "grad_norm": 0.2796061933040619,
      "learning_rate": 5.45e-05,
      "loss": 1.1131,
      "step": 110
    },
    {
      "grad_norm": 0.3423110544681549,
      "learning_rate": 5.95e-05,
      "loss": 1.1004,
      "step": 120
    },
    {
      "grad_norm": 0.33770301938056946,
      "learning_rate": 6.450000000000001e-05,
      "loss": 1.0887,
      "step": 130
    },
    {
      "grad_norm": 0.4104395806789398,
      "learning_rate": 6.95e-05,
      "loss": 1.1043,
      "step": 140
    },
    {
      "grad_norm": 0.38792213797569275,
      "learning_rate": 7.450000000000001e-05,
      "loss": 1.093,
      "step": 150
    },
    {
      "grad_norm": 0.31532591581344604,
      "learning_rate": 7.950000000000001e-05,
      "loss": 1.0992,
      "step": 160
    },
    {
      "grad_norm": 0.37639284133911133,
      "learning_rate": 8.450000000000001e-05,
      "loss": 1.1033,
      "step": 170
    },
    {
      "grad_norm": 0.4326634407043457,
      "learning_rate": 8.950000000000001e-05,
      "loss": 1.0834,
      "step": 180
    },
    {
      "grad_norm": 0.4046025276184082,
      "learning_rate": 9.449999999999999e-05,
      "loss": 1.0852,
      "step": 190
    },
    {
      "grad_norm": 0.45471683144569397,
      "learning_rate": 9.95e-05,
      "loss": 1.0775,
      "step": 200
    },
    {
      "grad_norm": 0.5478058457374573,
      "learning_rate": 9.999861593790126e-05,
      "loss": 1.0781,
      "step": 210
    },
    {
      "grad_norm": 0.3471389412879944,
      "learning_rate": 9.999383162408304e-05,
      "loss": 1.0828,
      "step": 220
    },
    {
      "grad_norm": 0.4683222770690918,
      "learning_rate": 9.998563029828259e-05,
      "loss": 1.0568,
      "step": 230
    },
    {
      "grad_norm": 0.3368767499923706,
      "learning_rate": 9.997401252104962e-05,
      "loss": 1.0364,
      "step": 240
    },
    {
      "grad_norm": 0.425786554813385,
      "learning_rate": 9.995897908644378e-05,
      "loss": 1.0061,
      "step": 250
    },
    {
      "grad_norm": 0.38125181198120117,
      "learning_rate": 9.994053102198034e-05,
      "loss": 1.0064,
      "step": 260
    },
    {
      "grad_norm": 0.569205105304718,
      "learning_rate": 9.991866958856003e-05,
      "loss": 1.0119,
      "step": 270
    },
    {
      "grad_norm": 0.360039621591568,
      "learning_rate": 9.989339628038276e-05,
      "loss": 0.9783,
      "step": 280
    },
    {
      "grad_norm": 0.3894808292388916,
      "learning_rate": 9.98647128248456e-05,
      "loss": 0.9876,
      "step": 290
    },
    {
      "grad_norm": 0.49482613801956177,
      "learning_rate": 9.98326211824246e-05,
      "loss": 0.9774,
      "step": 300
    },
    {
      "grad_norm": 0.43771424889564514,
      "learning_rate": 9.979712354654091e-05,
      "loss": 0.9528,
      "step": 310
    },
    {
      "grad_norm": 0.3924391269683838,
      "learning_rate": 9.975822234341079e-05,
      "loss": 0.949,
      "step": 320
    },
    {
      "grad_norm": 0.3948723077774048,
      "learning_rate": 9.97159202318798e-05,
      "loss": 0.95,
      "step": 330
    },
    {
      "grad_norm": 0.4701744019985199,
      "learning_rate": 9.967022010324105e-05,
      "loss": 0.9263,
      "step": 340
    },
    {
      "grad_norm": 0.5202460289001465,
      "learning_rate": 9.962112508103765e-05,
      "loss": 0.9409,
      "step": 350
    },
    {
      "grad_norm": 0.4282516837120056,
      "learning_rate": 9.956863852084914e-05,
      "loss": 0.9107,
      "step": 360
    },
    {
      "grad_norm": 0.5906583666801453,
      "learning_rate": 9.951276401006221e-05,
      "loss": 0.9072,
      "step": 370
    },
    {
      "grad_norm": 0.4856233298778534,
      "learning_rate": 9.945350536762543e-05,
      "loss": 0.9142,
      "step": 380
    },
    {
      "grad_norm": 0.44197753071784973,
      "learning_rate": 9.939086664378829e-05,
      "loss": 0.8903,
      "step": 390
    },
    {
      "grad_norm": 0.6055497527122498,
      "learning_rate": 9.932485211982437e-05,
      "loss": 0.8942,
      "step": 400
    },
    {
      "grad_norm": 0.5160871744155884,
      "learning_rate": 9.92554663077387e-05,
      "loss": 0.8765,
      "step": 410
    },
    {
      "grad_norm": 0.479907751083374,
      "learning_rate": 9.918271394995935e-05,
      "loss": 0.8774,
      "step": 420
    },
    {
      "grad_norm": 0.5040944218635559,
      "learning_rate": 9.910660001901335e-05,
      "loss": 0.8775,
      "step": 430
    },
    {
      "grad_norm": 0.5206490755081177,
      "learning_rate": 9.902712971718675e-05,
      "loss": 0.8647,
      "step": 440
    },
    {
      "grad_norm": 0.44746702909469604,
      "learning_rate": 9.894430847616915e-05,
      "loss": 0.8619,
      "step": 450
    },
    {
      "grad_norm": 0.4645554721355438,
      "learning_rate": 9.885814195668232e-05,
      "loss": 0.8444,
      "step": 460
    },
    {
      "grad_norm": 0.47834452986717224,
      "learning_rate": 9.876863604809344e-05,
      "loss": 0.8333,
      "step": 470
    },
    {
      "grad_norm": 0.43582776188850403,
      "learning_rate": 9.867579686801245e-05,
      "loss": 0.8598,
      "step": 480
    },
    {
      "grad_norm": 0.4257030189037323,
      "learning_rate": 9.8579630761874e-05,
      "loss": 0.8198,
      "step": 490
    },
    {
      "grad_norm": 0.5325835943222046,
      "learning_rate": 9.848014430250367e-05,
      "loss": 0.8271,
      "step": 500
    },
    {
      "grad_norm": 0.46889224648475647,
      "learning_rate": 9.837734428966885e-05,
      "loss": 0.8202,
      "step": 510
    },
    {
      "grad_norm": 0.5707681775093079,
      "learning_rate": 9.827123774961383e-05,
      "loss": 0.8078,
      "step": 520
    },
    {
      "grad_norm": 0.5601910352706909,
      "learning_rate": 9.816183193457968e-05,
      "loss": 0.8296,
      "step": 530
    },
    {
      "grad_norm": 0.6276665925979614,
      "learning_rate": 9.804913432230856e-05,
      "loss": 0.8248,
      "step": 540
    },
    {
      "grad_norm": 0.6616746187210083,
      "learning_rate": 9.793315261553252e-05,
      "loss": 0.8042,
      "step": 550
    },
    {
      "grad_norm": 0.5051801204681396,
      "learning_rate": 9.781389474144717e-05,
      "loss": 0.8047,
      "step": 560
    },
    {
      "grad_norm": 0.45216768980026245,
      "learning_rate": 9.76913688511698e-05,
      "loss": 0.8061,
      "step": 570
    },
    {
      "grad_norm": 0.5215824246406555,
      "learning_rate": 9.756558331918227e-05,
      "loss": 0.8082,
      "step": 580
    },
    {
      "grad_norm": 0.5071956515312195,
      "learning_rate": 9.743654674275855e-05,
      "loss": 0.8092,
      "step": 590
    },
    {
      "grad_norm": 0.4734920263290405,
      "learning_rate": 9.730426794137727e-05,
      "loss": 0.7902,
      "step": 600
    },
    {
      "grad_norm": 0.6150533556938171,
      "learning_rate": 9.716875595611879e-05,
      "loss": 0.7976,
      "step": 610
    },
    {
      "grad_norm": 0.6230007410049438,
      "learning_rate": 9.703002004904729e-05,
      "loss": 0.7894,
      "step": 620
    },
    {
      "grad_norm": 0.47863709926605225,
      "learning_rate": 9.688806970257773e-05,
      "loss": 0.7771,
      "step": 630
    },
    {
      "grad_norm": 0.5021641850471497,
      "learning_rate": 9.674291461882774e-05,
      "loss": 0.7608,
      "step": 640
    },
    {
      "grad_norm": 0.6127395033836365,
      "learning_rate": 9.659456471895445e-05,
      "loss": 0.7793,
      "step": 650
    },
    {
      "grad_norm": 0.5065549612045288,
      "learning_rate": 9.644303014247648e-05,
      "loss": 0.7759,
      "step": 660
    },
    {
      "grad_norm": 0.5618578195571899,
      "learning_rate": 9.628832124658085e-05,
      "loss": 0.7647,
      "step": 670
    },
    {
      "grad_norm": 0.7806953191757202,
      "learning_rate": 9.613044860541507e-05,
      "loss": 0.7829,
      "step": 680
    },
    {
      "grad_norm": 0.48667505383491516,
      "learning_rate": 9.596942300936445e-05,
      "loss": 0.7624,
      "step": 690
    },
    {
      "grad_norm": 0.4916687309741974,
      "learning_rate": 9.580525546431459e-05,
      "loss": 0.7617,
      "step": 700
    },
    {
      "grad_norm": 0.382213830947876,
      "learning_rate": 9.563795719089911e-05,
      "loss": 0.7561,
      "step": 710
    },
    {
      "grad_norm": 0.7185860276222229,
      "learning_rate": 9.546753962373281e-05,
      "loss": 0.7619,
      "step": 720
    },
    {
      "grad_norm": 0.48129522800445557,
      "learning_rate": 9.529401441062997e-05,
      "loss": 0.773,
      "step": 730
    },
    {
      "grad_norm": 0.5167684555053711,
      "learning_rate": 9.511739341180842e-05,
      "loss": 0.7669,
      "step": 740
    },
    {
      "grad_norm": 0.5255888104438782,
      "learning_rate": 9.493768869907886e-05,
      "loss": 0.764,
      "step": 750
    },
    {
      "grad_norm": 0.3794105052947998,
      "learning_rate": 9.475491255501968e-05,
      "loss": 0.7532,
      "step": 760
    },
    {
      "grad_norm": 0.4577208459377289,
      "learning_rate": 9.456907747213748e-05,
      "loss": 0.7512,
      "step": 770
    },
    {
      "grad_norm": 0.47813680768013,
      "learning_rate": 9.438019615201336e-05,
      "loss": 0.7653,
      "step": 780
    },
    {
      "grad_norm": 0.48698732256889343,
      "learning_rate": 9.418828150443469e-05,
      "loss": 0.7354,
      "step": 790
    },
    {
      "grad_norm": 0.48488903045654297,
      "learning_rate": 9.399334664651262e-05,
      "loss": 0.7649,
      "step": 800
    },
    {
      "grad_norm": 0.46380874514579773,
      "learning_rate": 9.379540490178581e-05,
      "loss": 0.7617,
      "step": 810
    },
    {
      "grad_norm": 0.48268088698387146,
      "learning_rate": 9.359446979930955e-05,
      "loss": 0.7466,
      "step": 820
    },
    {
      "grad_norm": 0.5104127526283264,
      "learning_rate": 9.33905550727312e-05,
      "loss": 0.7389,
      "step": 830
    },
    {
      "grad_norm": 0.4325626790523529,
      "learning_rate": 9.318367465935142e-05,
      "loss": 0.7414,
      "step": 840
    },
    {
      "grad_norm": 0.45519083738327026,
      "learning_rate": 9.29738426991717e-05,
      "loss": 0.7517,
      "step": 850
    },
    {
      "grad_norm": 0.5354924201965332,
      "learning_rate": 9.276107353392774e-05,
      "loss": 0.7427,
      "step": 860
    },
    {
      "grad_norm": 0.5575360655784607,
      "learning_rate": 9.254538170610938e-05,
      "loss": 0.7515,
      "step": 870
    },
    {
      "grad_norm": 0.5105330944061279,
      "learning_rate": 9.232678195796654e-05,
      "loss": 0.722,
      "step": 880
    },
    {
      "grad_norm": 0.5286569595336914,
      "learning_rate": 9.210528923050164e-05,
      "loss": 0.7215,
      "step": 890
    },
    {
      "grad_norm": 0.46469196677207947,
      "learning_rate": 9.188091866244834e-05,
      "loss": 0.72,
      "step": 900
    },
    {
      "grad_norm": 0.43992435932159424,
      "learning_rate": 9.165368558923695e-05,
      "loss": 0.7195,
      "step": 910
    },
    {
      "grad_norm": 0.4441291391849518,
      "learning_rate": 9.142360554194618e-05,
      "loss": 0.7272,
      "step": 920
    },
    {
      "grad_norm": 0.5133683085441589,
      "learning_rate": 9.119069424624163e-05,
      "loss": 0.7142,
      "step": 930
    },
    {
      "grad_norm": 0.5577358603477478,
      "learning_rate": 9.0954967621301e-05,
      "loss": 0.7095,
      "step": 940
    },
    {
      "grad_norm": 0.621738076210022,
      "learning_rate": 9.071644177872594e-05,
      "loss": 0.7276,
      "step": 950
    },
    {
      "grad_norm": 0.4756941497325897,
      "learning_rate": 9.047513302144095e-05,
      "loss": 0.7196,
      "step": 960
    },
    {
      "grad_norm": 0.3742871582508087,
      "learning_rate": 9.023105784257906e-05,
      "loss": 0.7159,
      "step": 970
    },
    {
      "grad_norm": 0.43546372652053833,
      "learning_rate": 8.998423292435454e-05,
      "loss": 0.7127,
      "step": 980
    },
    {
      "grad_norm": 0.5410100817680359,
      "learning_rate": 8.973467513692265e-05,
      "loss": 0.7089,
      "step": 990
    },
    {
      "grad_norm": 0.5081359148025513,
      "learning_rate": 8.94824015372267e-05,
      "loss": 0.6982,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}