{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9993913572732805,
  "eval_steps": 500,
  "global_step": 821,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012172854534388313,
      "grad_norm": 1.0562976598739624,
      "learning_rate": 2e-05,
      "loss": 2.4546,
      "step": 10
    },
    {
      "epoch": 0.024345709068776627,
      "grad_norm": 0.8776949048042297,
      "learning_rate": 4e-05,
      "loss": 2.3127,
      "step": 20
    },
    {
      "epoch": 0.036518563603164945,
      "grad_norm": 0.5755876302719116,
      "learning_rate": 6e-05,
      "loss": 1.9313,
      "step": 30
    },
    {
      "epoch": 0.048691418137553254,
      "grad_norm": 0.5708982944488525,
      "learning_rate": 8e-05,
      "loss": 1.7055,
      "step": 40
    },
    {
      "epoch": 0.06086427267194157,
      "grad_norm": 0.5251428484916687,
      "learning_rate": 0.0001,
      "loss": 1.4222,
      "step": 50
    },
    {
      "epoch": 0.07303712720632989,
      "grad_norm": 0.3596666157245636,
      "learning_rate": 0.00012,
      "loss": 1.1843,
      "step": 60
    },
    {
      "epoch": 0.0852099817407182,
      "grad_norm": 0.3925166130065918,
      "learning_rate": 0.00014,
      "loss": 1.0588,
      "step": 70
    },
    {
      "epoch": 0.09738283627510651,
      "grad_norm": 0.326300710439682,
      "learning_rate": 0.00016,
      "loss": 1.0132,
      "step": 80
    },
    {
      "epoch": 0.10955569080949483,
      "grad_norm": 0.4090663492679596,
      "learning_rate": 0.00018,
      "loss": 1.0263,
      "step": 90
    },
    {
      "epoch": 0.12172854534388314,
      "grad_norm": 0.4432264566421509,
      "learning_rate": 0.0002,
      "loss": 0.9522,
      "step": 100
    },
    {
      "epoch": 0.13390139987827146,
      "grad_norm": 0.3732856810092926,
      "learning_rate": 0.00019997924675658132,
      "loss": 0.9245,
      "step": 110
    },
    {
      "epoch": 0.14607425441265978,
      "grad_norm": 0.4144698679447174,
      "learning_rate": 0.00019991699564026757,
      "loss": 0.9304,
      "step": 120
    },
    {
      "epoch": 0.15824710894704808,
      "grad_norm": 0.4099937379360199,
      "learning_rate": 0.00019981327248931008,
      "loss": 0.9071,
      "step": 130
    },
    {
      "epoch": 0.1704199634814364,
      "grad_norm": 0.3997822403907776,
      "learning_rate": 0.00019966812035554488,
      "loss": 0.8639,
      "step": 140
    },
    {
      "epoch": 0.18259281801582472,
      "grad_norm": 0.34451448917388916,
      "learning_rate": 0.00019948159948652324,
      "loss": 0.8899,
      "step": 150
    },
    {
      "epoch": 0.19476567255021301,
      "grad_norm": 0.35060638189315796,
      "learning_rate": 0.00019925378730050518,
      "loss": 0.8583,
      "step": 160
    },
    {
      "epoch": 0.20693852708460134,
      "grad_norm": 0.34680619835853577,
      "learning_rate": 0.00019898477835432566,
      "loss": 0.9045,
      "step": 170
    },
    {
      "epoch": 0.21911138161898966,
      "grad_norm": 0.33215051889419556,
      "learning_rate": 0.0001986746843041475,
      "loss": 0.8594,
      "step": 180
    },
    {
      "epoch": 0.23128423615337795,
      "grad_norm": 0.31248751282691956,
      "learning_rate": 0.00019832363385911684,
      "loss": 0.8649,
      "step": 190
    },
    {
      "epoch": 0.24345709068776628,
      "grad_norm": 0.3884786367416382,
      "learning_rate": 0.00019793177272794043,
      "loss": 0.8331,
      "step": 200
    },
    {
      "epoch": 0.2556299452221546,
      "grad_norm": 0.36668214201927185,
      "learning_rate": 0.00019749926355840716,
      "loss": 0.8754,
      "step": 210
    },
    {
      "epoch": 0.2678027997565429,
      "grad_norm": 0.38938990235328674,
      "learning_rate": 0.00019702628586987846,
      "loss": 0.8369,
      "step": 220
    },
    {
      "epoch": 0.27997565429093124,
      "grad_norm": 0.3469957411289215,
      "learning_rate": 0.0001965130359787764,
      "loss": 0.8395,
      "step": 230
    },
    {
      "epoch": 0.29214850882531956,
      "grad_norm": 0.3345205783843994,
      "learning_rate": 0.00019595972691709948,
      "loss": 0.8863,
      "step": 240
    },
    {
      "epoch": 0.30432136335970783,
      "grad_norm": 0.4035792350769043,
      "learning_rate": 0.00019536658834400057,
      "loss": 0.7724,
      "step": 250
    },
    {
      "epoch": 0.31649421789409615,
      "grad_norm": 0.37310659885406494,
      "learning_rate": 0.00019473386645046343,
      "loss": 0.8441,
      "step": 260
    },
    {
      "epoch": 0.3286670724284845,
      "grad_norm": 0.3561219573020935,
      "learning_rate": 0.00019406182385711752,
      "loss": 0.8246,
      "step": 270
    },
    {
      "epoch": 0.3408399269628728,
      "grad_norm": 0.3558606207370758,
      "learning_rate": 0.00019335073950523335,
      "loss": 0.7924,
      "step": 280
    },
    {
      "epoch": 0.3530127814972611,
      "grad_norm": 0.3646792471408844,
      "learning_rate": 0.00019260090854094389,
      "loss": 0.8221,
      "step": 290
    },
    {
      "epoch": 0.36518563603164944,
      "grad_norm": 0.39410504698753357,
      "learning_rate": 0.00019181264219273958,
      "loss": 0.8122,
      "step": 300
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 0.4360694885253906,
      "learning_rate": 0.00019098626764228852,
      "loss": 0.7864,
      "step": 310
    },
    {
      "epoch": 0.38953134510042603,
      "grad_norm": 0.411204993724823,
      "learning_rate": 0.00019012212788863475,
      "loss": 0.8117,
      "step": 320
    },
    {
      "epoch": 0.40170419963481435,
      "grad_norm": 0.37499114871025085,
      "learning_rate": 0.00018922058160583132,
      "loss": 0.8203,
      "step": 330
    },
    {
      "epoch": 0.4138770541692027,
      "grad_norm": 0.3543803095817566,
      "learning_rate": 0.00018828200299406746,
      "loss": 0.804,
      "step": 340
    },
    {
      "epoch": 0.426049908703591,
      "grad_norm": 0.4047829210758209,
      "learning_rate": 0.0001873067816243511,
      "loss": 0.8417,
      "step": 350
    },
    {
      "epoch": 0.4382227632379793,
      "grad_norm": 0.3936086893081665,
      "learning_rate": 0.00018629532227681174,
      "loss": 0.7673,
      "step": 360
    },
    {
      "epoch": 0.45039561777236764,
      "grad_norm": 0.40592247247695923,
      "learning_rate": 0.0001852480447726903,
      "loss": 0.7866,
      "step": 370
    },
    {
      "epoch": 0.4625684723067559,
      "grad_norm": 0.35532569885253906,
      "learning_rate": 0.00018416538380008616,
      "loss": 0.7698,
      "step": 380
    },
    {
      "epoch": 0.47474132684114423,
      "grad_norm": 0.38175126910209656,
      "learning_rate": 0.00018304778873353344,
      "loss": 0.7507,
      "step": 390
    },
    {
      "epoch": 0.48691418137553255,
      "grad_norm": 0.35053545236587524,
      "learning_rate": 0.00018189572344748132,
      "loss": 0.7901,
      "step": 400
    },
    {
      "epoch": 0.4990870359099209,
      "grad_norm": 0.35815027356147766,
      "learning_rate": 0.00018070966612375612,
      "loss": 0.7696,
      "step": 410
    },
    {
      "epoch": 0.5112598904443092,
      "grad_norm": 0.3681068420410156,
      "learning_rate": 0.0001794901090530848,
      "loss": 0.7892,
      "step": 420
    },
    {
      "epoch": 0.5234327449786975,
      "grad_norm": 0.4286554157733917,
      "learning_rate": 0.00017823755843076233,
      "loss": 0.7534,
      "step": 430
    },
    {
      "epoch": 0.5356055995130858,
      "grad_norm": 0.4017205536365509,
      "learning_rate": 0.00017695253414654795,
      "loss": 0.7361,
      "step": 440
    },
    {
      "epoch": 0.5477784540474742,
      "grad_norm": 0.40098506212234497,
      "learning_rate": 0.00017563556956887703,
      "loss": 0.7421,
      "step": 450
    },
    {
      "epoch": 0.5599513085818625,
      "grad_norm": 0.37902459502220154,
      "learning_rate": 0.00017428721132347862,
      "loss": 0.7823,
      "step": 460
    },
    {
      "epoch": 0.5721241631162508,
      "grad_norm": 0.3943566083908081,
      "learning_rate": 0.0001729080190664904,
      "loss": 0.7696,
      "step": 470
    },
    {
      "epoch": 0.5842970176506391,
      "grad_norm": 0.37313807010650635,
      "learning_rate": 0.00017149856525216502,
      "loss": 0.7464,
      "step": 480
    },
    {
      "epoch": 0.5964698721850273,
      "grad_norm": 0.40370795130729675,
      "learning_rate": 0.0001700594348952643,
      "loss": 0.7785,
      "step": 490
    },
    {
      "epoch": 0.6086427267194157,
      "grad_norm": 0.3891587257385254,
      "learning_rate": 0.00016859122532824047,
      "loss": 0.7407,
      "step": 500
    },
    {
      "epoch": 0.620815581253804,
      "grad_norm": 0.37328803539276123,
      "learning_rate": 0.0001670945459533042,
      "loss": 0.7819,
      "step": 510
    },
    {
      "epoch": 0.6329884357881923,
      "grad_norm": 0.40735870599746704,
      "learning_rate": 0.00016557001798948325,
      "loss": 0.7937,
      "step": 520
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.3800922930240631,
      "learning_rate": 0.00016401827421477623,
      "loss": 0.7491,
      "step": 530
    },
    {
      "epoch": 0.657334144856969,
      "grad_norm": 0.3687744736671448,
      "learning_rate": 0.00016243995870350873,
      "loss": 0.7917,
      "step": 540
    },
    {
      "epoch": 0.6695069993913573,
      "grad_norm": 0.4083586633205414,
      "learning_rate": 0.00016083572655900072,
      "loss": 0.7581,
      "step": 550
    },
    {
      "epoch": 0.6816798539257456,
      "grad_norm": 0.33832359313964844,
      "learning_rate": 0.0001592062436416561,
      "loss": 0.7775,
      "step": 560
    },
    {
      "epoch": 0.6938527084601339,
      "grad_norm": 0.3860386610031128,
      "learning_rate": 0.0001575521862925875,
      "loss": 0.7528,
      "step": 570
    },
    {
      "epoch": 0.7060255629945222,
      "grad_norm": 0.38392528891563416,
      "learning_rate": 0.0001558742410528907,
      "loss": 0.7426,
      "step": 580
    },
    {
      "epoch": 0.7181984175289106,
      "grad_norm": 0.36063849925994873,
      "learning_rate": 0.00015417310437868586,
      "loss": 0.7148,
      "step": 590
    },
    {
      "epoch": 0.7303712720632989,
      "grad_norm": 0.41407009959220886,
      "learning_rate": 0.00015244948235204264,
      "loss": 0.7526,
      "step": 600
    },
    {
      "epoch": 0.7425441265976872,
      "grad_norm": 0.3566502332687378,
      "learning_rate": 0.00015070409038791076,
      "loss": 0.7052,
      "step": 610
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.40627434849739075,
      "learning_rate": 0.00014893765293717598,
      "loss": 0.6922,
      "step": 620
    },
    {
      "epoch": 0.7668898356664637,
      "grad_norm": 0.43230217695236206,
      "learning_rate": 0.00014715090318596636,
      "loss": 0.7096,
      "step": 630
    },
    {
      "epoch": 0.7790626902008521,
      "grad_norm": 0.4245879352092743,
      "learning_rate": 0.00014534458275133213,
      "loss": 0.7204,
      "step": 640
    },
    {
      "epoch": 0.7912355447352404,
      "grad_norm": 0.4921364486217499,
      "learning_rate": 0.00014351944137342679,
      "loss": 0.745,
      "step": 650
    },
    {
      "epoch": 0.8034083992696287,
      "grad_norm": 0.37731364369392395,
      "learning_rate": 0.0001416762366043161,
      "loss": 0.7759,
      "step": 660
    },
    {
      "epoch": 0.815581253804017,
      "grad_norm": 0.3670937716960907,
      "learning_rate": 0.0001398157334935449,
      "loss": 0.6828,
      "step": 670
    },
    {
      "epoch": 0.8277541083384053,
      "grad_norm": 0.3592926561832428,
      "learning_rate": 0.00013793870427059203,
      "loss": 0.7364,
      "step": 680
    },
    {
      "epoch": 0.8399269628727937,
      "grad_norm": 0.37360280752182007,
      "learning_rate": 0.00013604592802434485,
      "loss": 0.6936,
      "step": 690
    },
    {
      "epoch": 0.852099817407182,
      "grad_norm": 0.3820659816265106,
      "learning_rate": 0.0001341381903797268,
      "loss": 0.702,
      "step": 700
    },
    {
      "epoch": 0.8642726719415703,
      "grad_norm": 0.408120721578598,
      "learning_rate": 0.0001322162831716123,
      "loss": 0.7196,
      "step": 710
    },
    {
      "epoch": 0.8764455264759586,
      "grad_norm": 0.40797159075737,
      "learning_rate": 0.00013028100411616368,
      "loss": 0.7137,
      "step": 720
    },
    {
      "epoch": 0.888618381010347,
      "grad_norm": 0.3850896656513214,
      "learning_rate": 0.0001283331564797274,
      "loss": 0.7252,
      "step": 730
    },
    {
      "epoch": 0.9007912355447353,
      "grad_norm": 0.3789777457714081,
      "learning_rate": 0.0001263735487454262,
      "loss": 0.7393,
      "step": 740
    },
    {
      "epoch": 0.9129640900791236,
      "grad_norm": 0.39587724208831787,
      "learning_rate": 0.00012440299427758647,
      "loss": 0.7277,
      "step": 750
    },
    {
      "epoch": 0.9251369446135118,
      "grad_norm": 0.4247297942638397,
      "learning_rate": 0.00012242231098413898,
      "loss": 0.6669,
      "step": 760
    },
    {
      "epoch": 0.9373097991479001,
      "grad_norm": 0.43642064929008484,
      "learning_rate": 0.00012043232097713424,
      "loss": 0.7166,
      "step": 770
    },
    {
      "epoch": 0.9494826536822885,
      "grad_norm": 0.4219953119754791,
      "learning_rate": 0.00011843385023151255,
      "loss": 0.7014,
      "step": 780
    },
    {
      "epoch": 0.9616555082166768,
      "grad_norm": 0.39331114292144775,
      "learning_rate": 0.0001164277282422709,
      "loss": 0.6979,
      "step": 790
    },
    {
      "epoch": 0.9738283627510651,
      "grad_norm": 0.4079013466835022,
      "learning_rate": 0.00011441478768016871,
      "loss": 0.646,
      "step": 800
    },
    {
      "epoch": 0.9860012172854534,
      "grad_norm": 0.4337855577468872,
      "learning_rate": 0.00011239586404611542,
      "loss": 0.7214,
      "step": 810
    },
    {
      "epoch": 0.9981740718198417,
      "grad_norm": 0.36248165369033813,
      "learning_rate": 0.00011037179532438344,
      "loss": 0.7285,
      "step": 820
    }
  ],
  "logging_steps": 10,
  "max_steps": 1642,
  "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": 4.099147479163699e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}