{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23675643681562591,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002959455460195324,
      "eval_loss": 10.376261711120605,
      "eval_runtime": 10.819,
      "eval_samples_per_second": 138.829,
      "eval_steps_per_second": 34.754,
      "step": 1
    },
    {
      "epoch": 0.002959455460195324,
      "grad_norm": 0.298828125,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 10.3804,
      "step": 10
    },
    {
      "epoch": 0.005918910920390648,
      "grad_norm": 0.357421875,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 10.3767,
      "step": 20
    },
    {
      "epoch": 0.008878366380585973,
      "grad_norm": 0.443359375,
      "learning_rate": 4.8e-05,
      "loss": 10.3754,
      "step": 30
    },
    {
      "epoch": 0.011837821840781295,
      "grad_norm": 0.5625,
      "learning_rate": 6.400000000000001e-05,
      "loss": 10.3767,
      "step": 40
    },
    {
      "epoch": 0.01479727730097662,
      "grad_norm": 1.109375,
      "learning_rate": 8e-05,
      "loss": 10.3722,
      "step": 50
    },
    {
      "epoch": 0.017756732761171946,
      "grad_norm": 0.294921875,
      "learning_rate": 9.6e-05,
      "loss": 10.3804,
      "step": 60
    },
    {
      "epoch": 0.020716188221367268,
      "grad_norm": 0.373046875,
      "learning_rate": 0.00011200000000000001,
      "loss": 10.3739,
      "step": 70
    },
    {
      "epoch": 0.02367564368156259,
      "grad_norm": 0.42578125,
      "learning_rate": 0.00012800000000000002,
      "loss": 10.3736,
      "step": 80
    },
    {
      "epoch": 0.026635099141757917,
      "grad_norm": 0.70703125,
      "learning_rate": 0.000144,
      "loss": 10.3643,
      "step": 90
    },
    {
      "epoch": 0.02959455460195324,
      "grad_norm": 1.59375,
      "learning_rate": 0.00016,
      "loss": 10.364,
      "step": 100
    },
    {
      "epoch": 0.032554010062148565,
      "grad_norm": 0.478515625,
      "learning_rate": 0.00017600000000000002,
      "loss": 10.3561,
      "step": 110
    },
    {
      "epoch": 0.03551346552234389,
      "grad_norm": 0.73046875,
      "learning_rate": 0.000192,
      "loss": 10.3211,
      "step": 120
    },
    {
      "epoch": 0.03847292098253921,
      "grad_norm": 0.84375,
      "learning_rate": 0.0001999978128380225,
      "loss": 10.2582,
      "step": 130
    },
    {
      "epoch": 0.041432376442734536,
      "grad_norm": 0.72265625,
      "learning_rate": 0.0001999803161162393,
      "loss": 10.172,
      "step": 140
    },
    {
      "epoch": 0.04439183190292986,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019994532573409262,
      "loss": 10.1033,
      "step": 150
    },
    {
      "epoch": 0.04735128736312518,
      "grad_norm": 0.43359375,
      "learning_rate": 0.00019989284781388617,
      "loss": 10.0041,
      "step": 160
    },
    {
      "epoch": 0.05031074282332051,
      "grad_norm": 0.41796875,
      "learning_rate": 0.00019982289153773646,
      "loss": 9.9331,
      "step": 170
    },
    {
      "epoch": 0.053270198283515834,
      "grad_norm": 0.46875,
      "learning_rate": 0.00019973546914596623,
      "loss": 9.8548,
      "step": 180
    },
    {
      "epoch": 0.05622965374371116,
      "grad_norm": 0.64453125,
      "learning_rate": 0.00019963059593496268,
      "loss": 9.7692,
      "step": 190
    },
    {
      "epoch": 0.05918910920390648,
      "grad_norm": 1.140625,
      "learning_rate": 0.00019950829025450114,
      "loss": 9.7054,
      "step": 200
    },
    {
      "epoch": 0.05918910920390648,
      "eval_loss": 9.686193466186523,
      "eval_runtime": 20.1405,
      "eval_samples_per_second": 74.576,
      "eval_steps_per_second": 18.669,
      "step": 200
    },
    {
      "epoch": 0.062148564664101805,
      "grad_norm": 0.46484375,
      "learning_rate": 0.0001993685735045343,
      "loss": 9.6486,
      "step": 210
    },
    {
      "epoch": 0.06510802012429713,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0001992114701314478,
      "loss": 9.6029,
      "step": 220
    },
    {
      "epoch": 0.06806747558449246,
      "grad_norm": 0.5078125,
      "learning_rate": 0.000199037007623783,
      "loss": 9.5554,
      "step": 230
    },
    {
      "epoch": 0.07102693104468778,
      "grad_norm": 0.609375,
      "learning_rate": 0.00019884521650742715,
      "loss": 9.4941,
      "step": 240
    },
    {
      "epoch": 0.0739863865048831,
      "grad_norm": 1.78125,
      "learning_rate": 0.00019863613034027224,
      "loss": 9.508,
      "step": 250
    },
    {
      "epoch": 0.07694584196507842,
      "grad_norm": 0.5078125,
      "learning_rate": 0.0001984097857063434,
      "loss": 9.3502,
      "step": 260
    },
    {
      "epoch": 0.07990529742527375,
      "grad_norm": 0.55859375,
      "learning_rate": 0.0001981662222093976,
      "loss": 9.3473,
      "step": 270
    },
    {
      "epoch": 0.08286475288546907,
      "grad_norm": 0.5234375,
      "learning_rate": 0.00019790548246599447,
      "loss": 9.2955,
      "step": 280
    },
    {
      "epoch": 0.0858242083456644,
      "grad_norm": 0.625,
      "learning_rate": 0.00019762761209803927,
      "loss": 9.2712,
      "step": 290
    },
    {
      "epoch": 0.08878366380585972,
      "grad_norm": 1.140625,
      "learning_rate": 0.0001973326597248006,
      "loss": 9.2969,
      "step": 300
    },
    {
      "epoch": 0.09174311926605505,
      "grad_norm": 0.455078125,
      "learning_rate": 0.00019702067695440332,
      "loss": 9.1616,
      "step": 310
    },
    {
      "epoch": 0.09470257472625036,
      "grad_norm": 0.4609375,
      "learning_rate": 0.00019669171837479873,
      "loss": 9.1605,
      "step": 320
    },
    {
      "epoch": 0.09766203018644569,
      "grad_norm": 0.474609375,
      "learning_rate": 0.00019634584154421317,
      "loss": 9.1402,
      "step": 330
    },
    {
      "epoch": 0.10062148564664102,
      "grad_norm": 0.578125,
      "learning_rate": 0.00019598310698107702,
      "loss": 9.0839,
      "step": 340
    },
    {
      "epoch": 0.10358094110683634,
      "grad_norm": 1.296875,
      "learning_rate": 0.00019560357815343577,
      "loss": 9.0709,
      "step": 350
    },
    {
      "epoch": 0.10654039656703167,
      "grad_norm": 0.57421875,
      "learning_rate": 0.00019520732146784491,
      "loss": 9.0372,
      "step": 360
    },
    {
      "epoch": 0.109499852027227,
      "grad_norm": 0.76953125,
      "learning_rate": 0.0001947944062577507,
      "loss": 9.0209,
      "step": 370
    },
    {
      "epoch": 0.11245930748742232,
      "grad_norm": 0.5390625,
      "learning_rate": 0.00019436490477135878,
      "loss": 8.9724,
      "step": 380
    },
    {
      "epoch": 0.11541876294761765,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00019391889215899299,
      "loss": 9.0212,
      "step": 390
    },
    {
      "epoch": 0.11837821840781296,
      "grad_norm": 1.421875,
      "learning_rate": 0.0001934564464599461,
      "loss": 8.9091,
      "step": 400
    },
    {
      "epoch": 0.11837821840781296,
      "eval_loss": 8.961220741271973,
      "eval_runtime": 13.0065,
      "eval_samples_per_second": 115.48,
      "eval_steps_per_second": 28.909,
      "step": 400
    },
    {
      "epoch": 0.12133767386800828,
      "grad_norm": 0.443359375,
      "learning_rate": 0.00019297764858882514,
      "loss": 8.9547,
      "step": 410
    },
    {
      "epoch": 0.12429712932820361,
      "grad_norm": 0.466796875,
      "learning_rate": 0.00019248258232139388,
      "loss": 8.9394,
      "step": 420
    },
    {
      "epoch": 0.12725658478839894,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00019197133427991436,
      "loss": 8.9748,
      "step": 430
    },
    {
      "epoch": 0.13021604024859426,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00019144399391799043,
      "loss": 8.9198,
      "step": 440
    },
    {
      "epoch": 0.1331754957087896,
      "grad_norm": 1.203125,
      "learning_rate": 0.00019090065350491626,
      "loss": 8.8904,
      "step": 450
    },
    {
      "epoch": 0.1361349511689849,
      "grad_norm": 0.494140625,
      "learning_rate": 0.0001903414081095315,
      "loss": 8.8971,
      "step": 460
    },
    {
      "epoch": 0.13909440662918024,
      "grad_norm": 0.48046875,
      "learning_rate": 0.00018976635558358722,
      "loss": 8.84,
      "step": 470
    },
    {
      "epoch": 0.14205386208937557,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00018917559654462474,
      "loss": 8.838,
      "step": 480
    },
    {
      "epoch": 0.1450133175495709,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00018856923435837022,
      "loss": 8.7761,
      "step": 490
    },
    {
      "epoch": 0.1479727730097662,
      "grad_norm": 0.96875,
      "learning_rate": 0.0001879473751206489,
      "loss": 8.8421,
      "step": 500
    },
    {
      "epoch": 0.15093222846996152,
      "grad_norm": 0.478515625,
      "learning_rate": 0.00018731012763882133,
      "loss": 8.7691,
      "step": 510
    },
    {
      "epoch": 0.15389168393015684,
      "grad_norm": 0.4921875,
      "learning_rate": 0.00018665760341274505,
      "loss": 8.7749,
      "step": 520
    },
    {
      "epoch": 0.15685113939035217,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00018598991661526572,
      "loss": 8.79,
      "step": 530
    },
    {
      "epoch": 0.1598105948505475,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00018530718407223974,
      "loss": 8.8742,
      "step": 540
    },
    {
      "epoch": 0.16277005031074282,
      "grad_norm": 1.234375,
      "learning_rate": 0.00018460952524209355,
      "loss": 8.7845,
      "step": 550
    },
    {
      "epoch": 0.16572950577093815,
      "grad_norm": 0.470703125,
      "learning_rate": 0.00018389706219492147,
      "loss": 8.8165,
      "step": 560
    },
    {
      "epoch": 0.16868896123113347,
      "grad_norm": 0.486328125,
      "learning_rate": 0.00018316991959112716,
      "loss": 8.7024,
      "step": 570
    },
    {
      "epoch": 0.1716484166913288,
      "grad_norm": 0.53515625,
      "learning_rate": 0.00018242822465961176,
      "loss": 8.7764,
      "step": 580
    },
    {
      "epoch": 0.17460787215152412,
      "grad_norm": 0.58984375,
      "learning_rate": 0.00018167210717551224,
      "loss": 8.7501,
      "step": 590
    },
    {
      "epoch": 0.17756732761171945,
      "grad_norm": 1.28125,
      "learning_rate": 0.00018090169943749476,
      "loss": 8.7257,
      "step": 600
    },
    {
      "epoch": 0.17756732761171945,
      "eval_loss": 8.762685775756836,
      "eval_runtime": 18.9408,
      "eval_samples_per_second": 79.3,
      "eval_steps_per_second": 19.851,
      "step": 600
    },
    {
      "epoch": 0.18052678307191478,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00018011713624460608,
      "loss": 8.7709,
      "step": 610
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 0.53515625,
      "learning_rate": 0.00017931855487268782,
      "loss": 8.7334,
      "step": 620
    },
    {
      "epoch": 0.18644569399230543,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001785060950503568,
      "loss": 8.824,
      "step": 630
    },
    {
      "epoch": 0.18940514945250073,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00017767989893455698,
      "loss": 8.6731,
      "step": 640
    },
    {
      "epoch": 0.19236460491269605,
      "grad_norm": 0.90625,
      "learning_rate": 0.00017684011108568592,
      "loss": 8.7669,
      "step": 650
    },
    {
      "epoch": 0.19532406037289138,
      "grad_norm": 0.49609375,
      "learning_rate": 0.00017598687844230088,
      "loss": 8.6911,
      "step": 660
    },
    {
      "epoch": 0.1982835158330867,
      "grad_norm": 0.44140625,
      "learning_rate": 0.00017512035029540885,
      "loss": 8.6932,
      "step": 670
    },
    {
      "epoch": 0.20124297129328203,
      "grad_norm": 0.52734375,
      "learning_rate": 0.000174240678262345,
      "loss": 8.71,
      "step": 680
    },
    {
      "epoch": 0.20420242675347736,
      "grad_norm": 0.59375,
      "learning_rate": 0.000173348016260244,
      "loss": 8.7219,
      "step": 690
    },
    {
      "epoch": 0.20716188221367268,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00017244252047910892,
      "loss": 8.6973,
      "step": 700
    },
    {
      "epoch": 0.210121337673868,
      "grad_norm": 0.462890625,
      "learning_rate": 0.00017152434935448256,
      "loss": 8.6743,
      "step": 710
    },
    {
      "epoch": 0.21308079313406333,
      "grad_norm": 0.451171875,
      "learning_rate": 0.0001705936635397259,
      "loss": 8.7094,
      "step": 720
    },
    {
      "epoch": 0.21604024859425866,
      "grad_norm": 0.57421875,
      "learning_rate": 0.00016965062587790823,
      "loss": 8.7353,
      "step": 730
    },
    {
      "epoch": 0.218999704054454,
      "grad_norm": 0.5546875,
      "learning_rate": 0.00016869540137331445,
      "loss": 8.6939,
      "step": 740
    },
    {
      "epoch": 0.2219591595146493,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00016772815716257412,
      "loss": 8.7202,
      "step": 750
    },
    {
      "epoch": 0.22491861497484464,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00016674906248541726,
      "loss": 8.6779,
      "step": 760
    },
    {
      "epoch": 0.22787807043503996,
      "grad_norm": 0.671875,
      "learning_rate": 0.00016575828865506245,
      "loss": 8.6627,
      "step": 770
    },
    {
      "epoch": 0.2308375258952353,
      "grad_norm": 0.4375,
      "learning_rate": 0.0001647560090282419,
      "loss": 8.7348,
      "step": 780
    },
    {
      "epoch": 0.2337969813554306,
      "grad_norm": 0.6875,
      "learning_rate": 0.000163742398974869,
      "loss": 8.7236,
      "step": 790
    },
    {
      "epoch": 0.23675643681562591,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0001627176358473537,
      "loss": 8.7416,
      "step": 800
    },
    {
      "epoch": 0.23675643681562591,
      "eval_loss": 8.710856437683105,
      "eval_runtime": 16.7859,
      "eval_samples_per_second": 89.48,
      "eval_steps_per_second": 22.4,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 20509072293888.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}