{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 564,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 1.2923625707626343,
      "learning_rate": 9e-05,
      "loss": 3.2385536193847657,
      "step": 10
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 1.8184734582901,
      "learning_rate": 0.00019,
      "loss": 1.9452489852905273,
      "step": 20
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": 0.9270958304405212,
      "learning_rate": 0.000199967442452678,
      "loss": 1.03822603225708,
      "step": 30
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 1.0151121616363525,
      "learning_rate": 0.0001998549250618234,
      "loss": 0.7068291187286377,
      "step": 40
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 0.705467164516449,
      "learning_rate": 0.00019966213631132486,
      "loss": 0.5221255779266357,
      "step": 50
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 0.5946557521820068,
      "learning_rate": 0.00019938923118016923,
      "loss": 0.5408905506134033,
      "step": 60
    },
    {
      "epoch": 0.12416851441241686,
      "grad_norm": 0.5785620808601379,
      "learning_rate": 0.00019903642905128556,
      "loss": 0.4726524353027344,
      "step": 70
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": 0.4515378773212433,
      "learning_rate": 0.00019860401353518728,
      "loss": 0.477645206451416,
      "step": 80
    },
    {
      "epoch": 0.15964523281596452,
      "grad_norm": 0.7210069894790649,
      "learning_rate": 0.00019809233224198363,
      "loss": 0.4259486198425293,
      "step": 90
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 0.6604602932929993,
      "learning_rate": 0.00019750179650194284,
      "loss": 0.3986918210983276,
      "step": 100
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.5442255139350891,
      "learning_rate": 0.00019683288103483206,
      "loss": 0.4763587474822998,
      "step": 110
    },
    {
      "epoch": 0.21286031042128603,
      "grad_norm": 0.5671816468238831,
      "learning_rate": 0.00019608612356829963,
      "loss": 0.5349702358245849,
      "step": 120
    },
    {
      "epoch": 0.23059866962305986,
      "grad_norm": 0.5314913392066956,
      "learning_rate": 0.0001952621244056068,
      "loss": 0.5481620788574219,
      "step": 130
    },
    {
      "epoch": 0.24833702882483372,
      "grad_norm": 0.33398643136024475,
      "learning_rate": 0.00019436154594305592,
      "loss": 0.3566007137298584,
      "step": 140
    },
    {
      "epoch": 0.2660753880266075,
      "grad_norm": 0.46954014897346497,
      "learning_rate": 0.00019338511213750349,
      "loss": 0.4657393455505371,
      "step": 150
    },
    {
      "epoch": 0.2838137472283814,
      "grad_norm": 0.4137198030948639,
      "learning_rate": 0.00019233360792438587,
      "loss": 0.3321133375167847,
      "step": 160
    },
    {
      "epoch": 0.30155210643015523,
      "grad_norm": 0.4157610535621643,
      "learning_rate": 0.00019120787858672547,
      "loss": 0.4684488296508789,
      "step": 170
    },
    {
      "epoch": 0.31929046563192903,
      "grad_norm": 0.32782426476478577,
      "learning_rate": 0.00019000882907562475,
      "loss": 0.4948620319366455,
      "step": 180
    },
    {
      "epoch": 0.3370288248337029,
      "grad_norm": 0.43308839201927185,
      "learning_rate": 0.00018873742328279444,
      "loss": 0.35744609832763674,
      "step": 190
    },
    {
      "epoch": 0.35476718403547675,
      "grad_norm": 0.41532203555107117,
      "learning_rate": 0.00018739468326570025,
      "loss": 0.3800586938858032,
      "step": 200
    },
    {
      "epoch": 0.37250554323725055,
      "grad_norm": 0.2917892634868622,
      "learning_rate": 0.00018598168842595157,
      "loss": 0.47893481254577636,
      "step": 210
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.5077965259552002,
      "learning_rate": 0.0001844995746415924,
      "loss": 0.3925274133682251,
      "step": 220
    },
    {
      "epoch": 0.4079822616407982,
      "grad_norm": 0.4896332919597626,
      "learning_rate": 0.0001829495333539917,
      "loss": 0.45842485427856444,
      "step": 230
    },
    {
      "epoch": 0.42572062084257206,
      "grad_norm": 0.38639843463897705,
      "learning_rate": 0.00018133281061006787,
      "loss": 0.4485672950744629,
      "step": 240
    },
    {
      "epoch": 0.4434589800443459,
      "grad_norm": 0.3063654899597168,
      "learning_rate": 0.00017965070606061674,
      "loss": 0.35635855197906496,
      "step": 250
    },
    {
      "epoch": 0.4611973392461197,
      "grad_norm": 0.3712786138057709,
      "learning_rate": 0.00017790457191554844,
      "loss": 0.37890214920043946,
      "step": 260
    },
    {
      "epoch": 0.4789356984478936,
      "grad_norm": 0.38599035143852234,
      "learning_rate": 0.00017609581185687326,
      "loss": 0.39915194511413576,
      "step": 270
    },
    {
      "epoch": 0.49667405764966743,
      "grad_norm": 0.5249969959259033,
      "learning_rate": 0.00017422587991030994,
      "loss": 0.4316830635070801,
      "step": 280
    },
    {
      "epoch": 0.5144124168514412,
      "grad_norm": 0.4641951024532318,
      "learning_rate": 0.00017229627927642363,
      "loss": 0.5178345203399658,
      "step": 290
    },
    {
      "epoch": 0.532150776053215,
      "grad_norm": 0.44371530413627625,
      "learning_rate": 0.00017030856112223349,
      "loss": 0.3907311201095581,
      "step": 300
    },
    {
      "epoch": 0.549889135254989,
      "grad_norm": 0.38053175806999207,
      "learning_rate": 0.00016826432333426062,
      "loss": 0.34882614612579343,
      "step": 310
    },
    {
      "epoch": 0.5676274944567627,
      "grad_norm": 0.520490825176239,
      "learning_rate": 0.0001661652092340195,
      "loss": 0.445755672454834,
      "step": 320
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.31108957529067993,
      "learning_rate": 0.0001640129062569848,
      "loss": 0.40419764518737794,
      "step": 330
    },
    {
      "epoch": 0.6031042128603105,
      "grad_norm": 0.47880449891090393,
      "learning_rate": 0.00016180914459609623,
      "loss": 0.46592421531677247,
      "step": 340
    },
    {
      "epoch": 0.6208425720620843,
      "grad_norm": 0.44231295585632324,
      "learning_rate": 0.0001595556958108912,
      "loss": 0.48172497749328613,
      "step": 350
    },
    {
      "epoch": 0.6385809312638581,
      "grad_norm": 0.40263035893440247,
      "learning_rate": 0.0001572543714033838,
      "loss": 0.393178129196167,
      "step": 360
    },
    {
      "epoch": 0.656319290465632,
      "grad_norm": 0.3412622809410095,
      "learning_rate": 0.00015490702136183523,
      "loss": 0.3433420658111572,
      "step": 370
    },
    {
      "epoch": 0.6740576496674058,
      "grad_norm": 0.5057907104492188,
      "learning_rate": 0.00015251553267358505,
      "loss": 0.37641880512237547,
      "step": 380
    },
    {
      "epoch": 0.6917960088691796,
      "grad_norm": 0.44416049122810364,
      "learning_rate": 0.00015008182780814052,
      "loss": 0.3957379341125488,
      "step": 390
    },
    {
      "epoch": 0.7095343680709535,
      "grad_norm": 0.4646275043487549,
      "learning_rate": 0.0001476078631717421,
      "loss": 0.34919278621673583,
      "step": 400
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.3557003140449524,
      "learning_rate": 0.00014509562753464757,
      "loss": 0.41344871520996096,
      "step": 410
    },
    {
      "epoch": 0.7450110864745011,
      "grad_norm": 0.390167772769928,
      "learning_rate": 0.0001425471404324004,
      "loss": 0.3651400327682495,
      "step": 420
    },
    {
      "epoch": 0.7627494456762749,
      "grad_norm": 0.4841223359107971,
      "learning_rate": 0.00013996445054236526,
      "loss": 0.4397402286529541,
      "step": 430
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.30715662240982056,
      "learning_rate": 0.00013734963403683797,
      "loss": 0.5118452072143554,
      "step": 440
    },
    {
      "epoch": 0.7982261640798226,
      "grad_norm": 0.34371083974838257,
      "learning_rate": 0.0001347047929140523,
      "loss": 0.37561688423156736,
      "step": 450
    },
    {
      "epoch": 0.8159645232815964,
      "grad_norm": 0.3080121576786041,
      "learning_rate": 0.00013203205330842614,
      "loss": 0.3860162734985352,
      "step": 460
    },
    {
      "epoch": 0.8337028824833703,
      "grad_norm": 0.3681275248527527,
      "learning_rate": 0.00012933356378140495,
      "loss": 0.46400017738342286,
      "step": 470
    },
    {
      "epoch": 0.8514412416851441,
      "grad_norm": 0.28983521461486816,
      "learning_rate": 0.00012661149359427626,
      "loss": 0.39096343517303467,
      "step": 480
    },
    {
      "epoch": 0.8691796008869179,
      "grad_norm": 0.3648522198200226,
      "learning_rate": 0.0001238680309643447,
      "loss": 0.40194950103759763,
      "step": 490
    },
    {
      "epoch": 0.8869179600886918,
      "grad_norm": 0.3269522786140442,
      "learning_rate": 0.00012110538130586807,
      "loss": 0.37705302238464355,
      "step": 500
    },
    {
      "epoch": 0.9046563192904656,
      "grad_norm": 0.34992715716362,
      "learning_rate": 0.00011832576545716913,
      "loss": 0.4994521141052246,
      "step": 510
    },
    {
      "epoch": 0.9223946784922394,
      "grad_norm": 0.30297964811325073,
      "learning_rate": 0.00011553141789534892,
      "loss": 0.3096367597579956,
      "step": 520
    },
    {
      "epoch": 0.9401330376940134,
      "grad_norm": 0.2618395984172821,
      "learning_rate": 0.0001127245849400352,
      "loss": 0.37382805347442627,
      "step": 530
    },
    {
      "epoch": 0.9578713968957872,
      "grad_norm": 0.34870967268943787,
      "learning_rate": 0.00010990752294761177,
      "loss": 0.34928996562957765,
      "step": 540
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.3931839168071747,
      "learning_rate": 0.00010708249649737902,
      "loss": 0.3620719909667969,
      "step": 550
    },
    {
      "epoch": 0.9933481152993349,
      "grad_norm": 0.3809890151023865,
      "learning_rate": 0.00010425177657110426,
      "loss": 0.3819592475891113,
      "step": 560
    }
  ],
  "logging_steps": 10,
  "max_steps": 1128,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8605428658520064.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}