{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0746536769268814,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.465367692688139e-05,
      "grad_norm": 41.25,
      "learning_rate": 0.0,
      "loss": 1.8824537992477417,
      "step": 1
    },
    {
      "epoch": 0.0007465367692688139,
      "grad_norm": 45.0,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.0482389662000866,
      "step": 10
    },
    {
      "epoch": 0.0014930735385376278,
      "grad_norm": 47.0,
      "learning_rate": 3.166666666666667e-07,
      "loss": 2.0073740005493166,
      "step": 20
    },
    {
      "epoch": 0.0022396103078064417,
      "grad_norm": 52.5,
      "learning_rate": 4.833333333333334e-07,
      "loss": 2.002447319030762,
      "step": 30
    },
    {
      "epoch": 0.0029861470770752557,
      "grad_norm": 40.75,
      "learning_rate": 6.5e-07,
      "loss": 1.9365406036376953,
      "step": 40
    },
    {
      "epoch": 0.0037326838463440696,
      "grad_norm": 48.75,
      "learning_rate": 8.166666666666668e-07,
      "loss": 1.8309831619262695,
      "step": 50
    },
    {
      "epoch": 0.0044792206156128835,
      "grad_norm": 30.625,
      "learning_rate": 9.833333333333334e-07,
      "loss": 1.6815044403076171,
      "step": 60
    },
    {
      "epoch": 0.005225757384881697,
      "grad_norm": 32.5,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.5275766372680664,
      "step": 70
    },
    {
      "epoch": 0.005972294154150511,
      "grad_norm": 29.375,
      "learning_rate": 1.3166666666666666e-06,
      "loss": 1.3091348648071288,
      "step": 80
    },
    {
      "epoch": 0.006718830923419325,
      "grad_norm": 23.25,
      "learning_rate": 1.4833333333333337e-06,
      "loss": 1.044612979888916,
      "step": 90
    },
    {
      "epoch": 0.007465367692688139,
      "grad_norm": 11.375,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.8313380241394043,
      "step": 100
    },
    {
      "epoch": 0.008211904461956953,
      "grad_norm": 6.03125,
      "learning_rate": 1.816666666666667e-06,
      "loss": 0.6549209594726563,
      "step": 110
    },
    {
      "epoch": 0.008958441231225767,
      "grad_norm": 5.8125,
      "learning_rate": 1.9833333333333335e-06,
      "loss": 0.6153350830078125,
      "step": 120
    },
    {
      "epoch": 0.009704978000494581,
      "grad_norm": 3.890625,
      "learning_rate": 2.15e-06,
      "loss": 0.6363908767700195,
      "step": 130
    },
    {
      "epoch": 0.010451514769763394,
      "grad_norm": 4.0,
      "learning_rate": 2.316666666666667e-06,
      "loss": 0.5566326141357422,
      "step": 140
    },
    {
      "epoch": 0.011198051539032208,
      "grad_norm": 3.9375,
      "learning_rate": 2.4833333333333334e-06,
      "loss": 0.5371531009674072,
      "step": 150
    },
    {
      "epoch": 0.011944588308301023,
      "grad_norm": 2.890625,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.5555124282836914,
      "step": 160
    },
    {
      "epoch": 0.012691125077569837,
      "grad_norm": 5.0625,
      "learning_rate": 2.816666666666667e-06,
      "loss": 0.5494957447052002,
      "step": 170
    },
    {
      "epoch": 0.01343766184683865,
      "grad_norm": 3.046875,
      "learning_rate": 2.9833333333333337e-06,
      "loss": 0.5402939796447754,
      "step": 180
    },
    {
      "epoch": 0.014184198616107464,
      "grad_norm": 3.765625,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.5793848514556885,
      "step": 190
    },
    {
      "epoch": 0.014930735385376278,
      "grad_norm": 2.59375,
      "learning_rate": 3.316666666666667e-06,
      "loss": 0.5502342224121094,
      "step": 200
    },
    {
      "epoch": 0.01567727215464509,
      "grad_norm": 2.953125,
      "learning_rate": 3.4833333333333336e-06,
      "loss": 0.49313879013061523,
      "step": 210
    },
    {
      "epoch": 0.016423808923913905,
      "grad_norm": 3.78125,
      "learning_rate": 3.65e-06,
      "loss": 0.5263992786407471,
      "step": 220
    },
    {
      "epoch": 0.01717034569318272,
      "grad_norm": 3.4375,
      "learning_rate": 3.816666666666667e-06,
      "loss": 0.5459019184112549,
      "step": 230
    },
    {
      "epoch": 0.017916882462451534,
      "grad_norm": 3.140625,
      "learning_rate": 3.983333333333334e-06,
      "loss": 0.5428171634674073,
      "step": 240
    },
    {
      "epoch": 0.01866341923172035,
      "grad_norm": 3.21875,
      "learning_rate": 4.15e-06,
      "loss": 0.49319753646850584,
      "step": 250
    },
    {
      "epoch": 0.019409956000989163,
      "grad_norm": 3.453125,
      "learning_rate": 4.316666666666667e-06,
      "loss": 0.5125864505767822,
      "step": 260
    },
    {
      "epoch": 0.020156492770257974,
      "grad_norm": 3.171875,
      "learning_rate": 4.483333333333333e-06,
      "loss": 0.5314520835876465,
      "step": 270
    },
    {
      "epoch": 0.020903029539526788,
      "grad_norm": 2.546875,
      "learning_rate": 4.65e-06,
      "loss": 0.4978891372680664,
      "step": 280
    },
    {
      "epoch": 0.021649566308795602,
      "grad_norm": 3.03125,
      "learning_rate": 4.816666666666667e-06,
      "loss": 0.5198709487915039,
      "step": 290
    },
    {
      "epoch": 0.022396103078064417,
      "grad_norm": 3.171875,
      "learning_rate": 4.983333333333334e-06,
      "loss": 0.5384783744812012,
      "step": 300
    },
    {
      "epoch": 0.02314263984733323,
      "grad_norm": 2.796875,
      "learning_rate": 5.150000000000001e-06,
      "loss": 0.5182504177093505,
      "step": 310
    },
    {
      "epoch": 0.023889176616602045,
      "grad_norm": 2.734375,
      "learning_rate": 5.316666666666667e-06,
      "loss": 0.507215929031372,
      "step": 320
    },
    {
      "epoch": 0.02463571338587086,
      "grad_norm": 3.5,
      "learning_rate": 5.483333333333334e-06,
      "loss": 0.49228978157043457,
      "step": 330
    },
    {
      "epoch": 0.025382250155139674,
      "grad_norm": 3.125,
      "learning_rate": 5.65e-06,
      "loss": 0.4914403438568115,
      "step": 340
    },
    {
      "epoch": 0.026128786924408485,
      "grad_norm": 3.53125,
      "learning_rate": 5.816666666666667e-06,
      "loss": 0.534427547454834,
      "step": 350
    },
    {
      "epoch": 0.0268753236936773,
      "grad_norm": 3.0,
      "learning_rate": 5.983333333333334e-06,
      "loss": 0.5076132774353027,
      "step": 360
    },
    {
      "epoch": 0.027621860462946114,
      "grad_norm": 3.53125,
      "learning_rate": 6.15e-06,
      "loss": 0.5000465869903564,
      "step": 370
    },
    {
      "epoch": 0.028368397232214928,
      "grad_norm": 2.734375,
      "learning_rate": 6.3166666666666675e-06,
      "loss": 0.49956622123718264,
      "step": 380
    },
    {
      "epoch": 0.029114934001483742,
      "grad_norm": 2.390625,
      "learning_rate": 6.483333333333334e-06,
      "loss": 0.49751648902893064,
      "step": 390
    },
    {
      "epoch": 0.029861470770752557,
      "grad_norm": 2.765625,
      "learning_rate": 6.650000000000001e-06,
      "loss": 0.4907405376434326,
      "step": 400
    },
    {
      "epoch": 0.03060800754002137,
      "grad_norm": 2.90625,
      "learning_rate": 6.816666666666667e-06,
      "loss": 0.497531795501709,
      "step": 410
    },
    {
      "epoch": 0.03135454430929018,
      "grad_norm": 2.703125,
      "learning_rate": 6.983333333333334e-06,
      "loss": 0.4707779884338379,
      "step": 420
    },
    {
      "epoch": 0.032101081078558996,
      "grad_norm": 3.09375,
      "learning_rate": 7.15e-06,
      "loss": 0.4825934886932373,
      "step": 430
    },
    {
      "epoch": 0.03284761784782781,
      "grad_norm": 3.171875,
      "learning_rate": 7.316666666666667e-06,
      "loss": 0.4995779514312744,
      "step": 440
    },
    {
      "epoch": 0.033594154617096625,
      "grad_norm": 2.5,
      "learning_rate": 7.483333333333333e-06,
      "loss": 0.4832624435424805,
      "step": 450
    },
    {
      "epoch": 0.03434069138636544,
      "grad_norm": 2.59375,
      "learning_rate": 7.650000000000001e-06,
      "loss": 0.45832481384277346,
      "step": 460
    },
    {
      "epoch": 0.035087228155634254,
      "grad_norm": 3.15625,
      "learning_rate": 7.816666666666667e-06,
      "loss": 0.48647127151489256,
      "step": 470
    },
    {
      "epoch": 0.03583376492490307,
      "grad_norm": 2.75,
      "learning_rate": 7.983333333333334e-06,
      "loss": 0.4490346908569336,
      "step": 480
    },
    {
      "epoch": 0.03658030169417188,
      "grad_norm": 2.765625,
      "learning_rate": 8.15e-06,
      "loss": 0.46668305397033694,
      "step": 490
    },
    {
      "epoch": 0.0373268384634407,
      "grad_norm": 3.484375,
      "learning_rate": 8.316666666666668e-06,
      "loss": 0.47034263610839844,
      "step": 500
    },
    {
      "epoch": 0.0373268384634407,
      "eval_loss": 0.5070451498031616,
      "eval_runtime": 11.9697,
      "eval_samples_per_second": 41.772,
      "eval_steps_per_second": 41.772,
      "step": 500
    },
    {
      "epoch": 0.03807337523270951,
      "grad_norm": 3.5,
      "learning_rate": 8.483333333333334e-06,
      "loss": 0.4726890563964844,
      "step": 510
    },
    {
      "epoch": 0.038819912001978325,
      "grad_norm": 2.875,
      "learning_rate": 8.65e-06,
      "loss": 0.5026403903961182,
      "step": 520
    },
    {
      "epoch": 0.03956644877124714,
      "grad_norm": 3.296875,
      "learning_rate": 8.816666666666668e-06,
      "loss": 0.5066637992858887,
      "step": 530
    },
    {
      "epoch": 0.04031298554051595,
      "grad_norm": 3.1875,
      "learning_rate": 8.983333333333334e-06,
      "loss": 0.4934993743896484,
      "step": 540
    },
    {
      "epoch": 0.04105952230978476,
      "grad_norm": 3.3125,
      "learning_rate": 9.15e-06,
      "loss": 0.5037405014038085,
      "step": 550
    },
    {
      "epoch": 0.041806059079053576,
      "grad_norm": 2.5,
      "learning_rate": 9.316666666666667e-06,
      "loss": 0.4912420749664307,
      "step": 560
    },
    {
      "epoch": 0.04255259584832239,
      "grad_norm": 2.6875,
      "learning_rate": 9.483333333333335e-06,
      "loss": 0.4600395202636719,
      "step": 570
    },
    {
      "epoch": 0.043299132617591204,
      "grad_norm": 3.375,
      "learning_rate": 9.65e-06,
      "loss": 0.4717693328857422,
      "step": 580
    },
    {
      "epoch": 0.04404566938686002,
      "grad_norm": 3.125,
      "learning_rate": 9.816666666666667e-06,
      "loss": 0.47403817176818847,
      "step": 590
    },
    {
      "epoch": 0.04479220615612883,
      "grad_norm": 3.65625,
      "learning_rate": 9.983333333333333e-06,
      "loss": 0.5240823268890381,
      "step": 600
    },
    {
      "epoch": 0.04553874292539765,
      "grad_norm": 2.6875,
      "learning_rate": 9.999994689673353e-06,
      "loss": 0.4917013645172119,
      "step": 610
    },
    {
      "epoch": 0.04628527969466646,
      "grad_norm": 2.515625,
      "learning_rate": 9.999976333003123e-06,
      "loss": 0.47769603729248045,
      "step": 620
    },
    {
      "epoch": 0.047031816463935276,
      "grad_norm": 3.3125,
      "learning_rate": 9.999944864477851e-06,
      "loss": 0.4795827865600586,
      "step": 630
    },
    {
      "epoch": 0.04777835323320409,
      "grad_norm": 3.21875,
      "learning_rate": 9.99990028418006e-06,
      "loss": 0.43662128448486326,
      "step": 640
    },
    {
      "epoch": 0.048524890002472905,
      "grad_norm": 2.484375,
      "learning_rate": 9.999842592226653e-06,
      "loss": 0.45467290878295896,
      "step": 650
    },
    {
      "epoch": 0.04927142677174172,
      "grad_norm": 2.609375,
      "learning_rate": 9.999771788768926e-06,
      "loss": 0.4696822166442871,
      "step": 660
    },
    {
      "epoch": 0.050017963541010534,
      "grad_norm": 3.078125,
      "learning_rate": 9.99968787399255e-06,
      "loss": 0.48618736267089846,
      "step": 670
    },
    {
      "epoch": 0.05076450031027935,
      "grad_norm": 2.703125,
      "learning_rate": 9.999590848117582e-06,
      "loss": 0.41396608352661135,
      "step": 680
    },
    {
      "epoch": 0.051511037079548155,
      "grad_norm": 2.9375,
      "learning_rate": 9.99948071139846e-06,
      "loss": 0.4746438980102539,
      "step": 690
    },
    {
      "epoch": 0.05225757384881697,
      "grad_norm": 2.5625,
      "learning_rate": 9.999357464124004e-06,
      "loss": 0.41242361068725586,
      "step": 700
    },
    {
      "epoch": 0.053004110618085784,
      "grad_norm": 3.25,
      "learning_rate": 9.99922110661742e-06,
      "loss": 0.511469554901123,
      "step": 710
    },
    {
      "epoch": 0.0537506473873546,
      "grad_norm": 2.46875,
      "learning_rate": 9.999071639236285e-06,
      "loss": 0.4603419303894043,
      "step": 720
    },
    {
      "epoch": 0.05449718415662341,
      "grad_norm": 2.71875,
      "learning_rate": 9.998909062372562e-06,
      "loss": 0.4702977180480957,
      "step": 730
    },
    {
      "epoch": 0.05524372092589223,
      "grad_norm": 2.96875,
      "learning_rate": 9.998733376452589e-06,
      "loss": 0.4667942047119141,
      "step": 740
    },
    {
      "epoch": 0.05599025769516104,
      "grad_norm": 3.03125,
      "learning_rate": 9.998544581937083e-06,
      "loss": 0.45894484519958495,
      "step": 750
    },
    {
      "epoch": 0.056736794464429856,
      "grad_norm": 2.765625,
      "learning_rate": 9.998342679321134e-06,
      "loss": 0.4406691074371338,
      "step": 760
    },
    {
      "epoch": 0.05748333123369867,
      "grad_norm": 2.625,
      "learning_rate": 9.99812766913421e-06,
      "loss": 0.4889220714569092,
      "step": 770
    },
    {
      "epoch": 0.058229868002967484,
      "grad_norm": 2.875,
      "learning_rate": 9.997899551940148e-06,
      "loss": 0.43836426734924316,
      "step": 780
    },
    {
      "epoch": 0.0589764047722363,
      "grad_norm": 3.03125,
      "learning_rate": 9.997658328337161e-06,
      "loss": 0.4346059799194336,
      "step": 790
    },
    {
      "epoch": 0.05972294154150511,
      "grad_norm": 2.578125,
      "learning_rate": 9.997403998957827e-06,
      "loss": 0.4483802795410156,
      "step": 800
    },
    {
      "epoch": 0.06046947831077393,
      "grad_norm": 2.875,
      "learning_rate": 9.997136564469098e-06,
      "loss": 0.4692661762237549,
      "step": 810
    },
    {
      "epoch": 0.06121601508004274,
      "grad_norm": 2.4375,
      "learning_rate": 9.99685602557229e-06,
      "loss": 0.44000725746154784,
      "step": 820
    },
    {
      "epoch": 0.061962551849311556,
      "grad_norm": 2.71875,
      "learning_rate": 9.996562383003079e-06,
      "loss": 0.43952512741088867,
      "step": 830
    },
    {
      "epoch": 0.06270908861858036,
      "grad_norm": 2.96875,
      "learning_rate": 9.996255637531513e-06,
      "loss": 0.44098215103149413,
      "step": 840
    },
    {
      "epoch": 0.06345562538784918,
      "grad_norm": 2.09375,
      "learning_rate": 9.995935789961994e-06,
      "loss": 0.44136600494384765,
      "step": 850
    },
    {
      "epoch": 0.06420216215711799,
      "grad_norm": 2.84375,
      "learning_rate": 9.995602841133287e-06,
      "loss": 0.45519566535949707,
      "step": 860
    },
    {
      "epoch": 0.06494869892638681,
      "grad_norm": 2.796875,
      "learning_rate": 9.995256791918511e-06,
      "loss": 0.44521641731262207,
      "step": 870
    },
    {
      "epoch": 0.06569523569565562,
      "grad_norm": 3.203125,
      "learning_rate": 9.994897643225136e-06,
      "loss": 0.49935183525085447,
      "step": 880
    },
    {
      "epoch": 0.06644177246492444,
      "grad_norm": 2.40625,
      "learning_rate": 9.994525395994993e-06,
      "loss": 0.4272043228149414,
      "step": 890
    },
    {
      "epoch": 0.06718830923419325,
      "grad_norm": 3.046875,
      "learning_rate": 9.994140051204254e-06,
      "loss": 0.4512756824493408,
      "step": 900
    },
    {
      "epoch": 0.06793484600346207,
      "grad_norm": 2.046875,
      "learning_rate": 9.99374160986344e-06,
      "loss": 0.4511909008026123,
      "step": 910
    },
    {
      "epoch": 0.06868138277273088,
      "grad_norm": 2.625,
      "learning_rate": 9.99333007301742e-06,
      "loss": 0.4683080673217773,
      "step": 920
    },
    {
      "epoch": 0.06942791954199969,
      "grad_norm": 2.5625,
      "learning_rate": 9.992905441745398e-06,
      "loss": 0.470552921295166,
      "step": 930
    },
    {
      "epoch": 0.07017445631126851,
      "grad_norm": 3.078125,
      "learning_rate": 9.992467717160924e-06,
      "loss": 0.47638602256774903,
      "step": 940
    },
    {
      "epoch": 0.07092099308053731,
      "grad_norm": 2.3125,
      "learning_rate": 9.992016900411873e-06,
      "loss": 0.4649850845336914,
      "step": 950
    },
    {
      "epoch": 0.07166752984980614,
      "grad_norm": 2.4375,
      "learning_rate": 9.991552992680467e-06,
      "loss": 0.48718810081481934,
      "step": 960
    },
    {
      "epoch": 0.07241406661907494,
      "grad_norm": 3.0,
      "learning_rate": 9.991075995183246e-06,
      "loss": 0.5018165588378907,
      "step": 970
    },
    {
      "epoch": 0.07316060338834376,
      "grad_norm": 2.40625,
      "learning_rate": 9.99058590917108e-06,
      "loss": 0.44672532081604005,
      "step": 980
    },
    {
      "epoch": 0.07390714015761257,
      "grad_norm": 2.703125,
      "learning_rate": 9.990082735929166e-06,
      "loss": 0.4896130084991455,
      "step": 990
    },
    {
      "epoch": 0.0746536769268814,
      "grad_norm": 2.703125,
      "learning_rate": 9.989566476777013e-06,
      "loss": 0.43416008949279783,
      "step": 1000
    },
    {
      "epoch": 0.0746536769268814,
      "eval_loss": 0.48367443680763245,
      "eval_runtime": 12.0879,
      "eval_samples_per_second": 41.364,
      "eval_steps_per_second": 41.364,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 20000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.148408070564659e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}