{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 728,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013736263736263736,
      "grad_norm": 5.281684715615811,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 7.8187,
      "step": 10
    },
    {
      "epoch": 0.027472527472527472,
      "grad_norm": 24.68054565360157,
      "learning_rate": 6.505149978319905e-05,
      "loss": 7.9281,
      "step": 20
    },
    {
      "epoch": 0.04120879120879121,
      "grad_norm": 3.0796940998366895,
      "learning_rate": 7.385606273598311e-05,
      "loss": 7.7094,
      "step": 30
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 8.333067476952397,
      "learning_rate": 8.01029995663981e-05,
      "loss": 7.525,
      "step": 40
    },
    {
      "epoch": 0.06868131868131869,
      "grad_norm": 23.086614801718486,
      "learning_rate": 8.494850021680092e-05,
      "loss": 6.9094,
      "step": 50
    },
    {
      "epoch": 0.08241758241758242,
      "grad_norm": 14.213944887373065,
      "learning_rate": 8.890756251918216e-05,
      "loss": 4.1141,
      "step": 60
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 0.8580927887161656,
      "learning_rate": 9.225490200071284e-05,
      "loss": 2.0804,
      "step": 70
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 0.27570449858382007,
      "learning_rate": 9.515449934959716e-05,
      "loss": 0.0238,
      "step": 80
    },
    {
      "epoch": 0.12362637362637363,
      "grad_norm": 5.11450425512202,
      "learning_rate": 9.771212547196623e-05,
      "loss": 1.7693,
      "step": 90
    },
    {
      "epoch": 0.13736263736263737,
      "grad_norm": 3.0188904083540513,
      "learning_rate": 9.999999999999999e-05,
      "loss": 3.0328,
      "step": 100
    },
    {
      "epoch": 0.1510989010989011,
      "grad_norm": 2.223466986052455,
      "learning_rate": 9.856687898089173e-05,
      "loss": 2.5187,
      "step": 110
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.5958810459345905,
      "learning_rate": 9.697452229299363e-05,
      "loss": 1.7121,
      "step": 120
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.9017097274049742,
      "learning_rate": 9.538216560509554e-05,
      "loss": 0.2382,
      "step": 130
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 2.5797266213086973,
      "learning_rate": 9.378980891719745e-05,
      "loss": 0.96,
      "step": 140
    },
    {
      "epoch": 0.20604395604395603,
      "grad_norm": 1.969151910347761,
      "learning_rate": 9.219745222929936e-05,
      "loss": 0.8195,
      "step": 150
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 1.2964360872016674,
      "learning_rate": 9.060509554140128e-05,
      "loss": 0.667,
      "step": 160
    },
    {
      "epoch": 0.23351648351648352,
      "grad_norm": 0.8334871882607511,
      "learning_rate": 8.901273885350318e-05,
      "loss": 0.7125,
      "step": 170
    },
    {
      "epoch": 0.24725274725274726,
      "grad_norm": 1.9433127558301508,
      "learning_rate": 8.74203821656051e-05,
      "loss": 0.8777,
      "step": 180
    },
    {
      "epoch": 0.260989010989011,
      "grad_norm": 2.888762859831557,
      "learning_rate": 8.582802547770701e-05,
      "loss": 1.3746,
      "step": 190
    },
    {
      "epoch": 0.27472527472527475,
      "grad_norm": 2.218013297748846,
      "learning_rate": 8.423566878980892e-05,
      "loss": 1.5352,
      "step": 200
    },
    {
      "epoch": 0.28846153846153844,
      "grad_norm": 2.43550275477957,
      "learning_rate": 8.264331210191083e-05,
      "loss": 1.4766,
      "step": 210
    },
    {
      "epoch": 0.3021978021978022,
      "grad_norm": 2.793254213699652,
      "learning_rate": 8.105095541401275e-05,
      "loss": 1.4922,
      "step": 220
    },
    {
      "epoch": 0.3159340659340659,
      "grad_norm": 2.3770618942858417,
      "learning_rate": 7.945859872611465e-05,
      "loss": 1.117,
      "step": 230
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.2336001430095062,
      "learning_rate": 7.786624203821657e-05,
      "loss": 0.1422,
      "step": 240
    },
    {
      "epoch": 0.3434065934065934,
      "grad_norm": 0.22856765073027144,
      "learning_rate": 7.627388535031847e-05,
      "loss": 0.0117,
      "step": 250
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.060125491997171404,
      "learning_rate": 7.468152866242038e-05,
      "loss": 0.0054,
      "step": 260
    },
    {
      "epoch": 0.3708791208791209,
      "grad_norm": 0.17072233100687323,
      "learning_rate": 7.30891719745223e-05,
      "loss": 0.007,
      "step": 270
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.2527260405826915,
      "learning_rate": 7.14968152866242e-05,
      "loss": 0.008,
      "step": 280
    },
    {
      "epoch": 0.3983516483516483,
      "grad_norm": 0.0645728697451073,
      "learning_rate": 6.990445859872612e-05,
      "loss": 0.0052,
      "step": 290
    },
    {
      "epoch": 0.41208791208791207,
      "grad_norm": 0.21741744460459944,
      "learning_rate": 6.831210191082804e-05,
      "loss": 0.0036,
      "step": 300
    },
    {
      "epoch": 0.4258241758241758,
      "grad_norm": 0.08947991234943435,
      "learning_rate": 6.671974522292994e-05,
      "loss": 0.0061,
      "step": 310
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 0.18230980143975276,
      "learning_rate": 6.512738853503185e-05,
      "loss": 0.0031,
      "step": 320
    },
    {
      "epoch": 0.4532967032967033,
      "grad_norm": 0.22933179008937474,
      "learning_rate": 6.353503184713377e-05,
      "loss": 0.0044,
      "step": 330
    },
    {
      "epoch": 0.46703296703296704,
      "grad_norm": 0.04926832002954577,
      "learning_rate": 6.194267515923567e-05,
      "loss": 0.0076,
      "step": 340
    },
    {
      "epoch": 0.4807692307692308,
      "grad_norm": 0.04172402454517282,
      "learning_rate": 6.035031847133759e-05,
      "loss": 0.0034,
      "step": 350
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.16913923259852043,
      "learning_rate": 5.87579617834395e-05,
      "loss": 0.0035,
      "step": 360
    },
    {
      "epoch": 0.5082417582417582,
      "grad_norm": 0.11774220375908637,
      "learning_rate": 5.716560509554141e-05,
      "loss": 0.0033,
      "step": 370
    },
    {
      "epoch": 0.521978021978022,
      "grad_norm": 0.13292673922854645,
      "learning_rate": 5.5573248407643317e-05,
      "loss": 0.005,
      "step": 380
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.01815243505852036,
      "learning_rate": 5.398089171974523e-05,
      "loss": 0.0026,
      "step": 390
    },
    {
      "epoch": 0.5494505494505495,
      "grad_norm": 0.04011699411855183,
      "learning_rate": 5.238853503184714e-05,
      "loss": 0.0027,
      "step": 400
    },
    {
      "epoch": 0.5631868131868132,
      "grad_norm": 0.2759252165955475,
      "learning_rate": 5.079617834394905e-05,
      "loss": 0.0048,
      "step": 410
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.05014856149469786,
      "learning_rate": 4.920382165605096e-05,
      "loss": 0.0039,
      "step": 420
    },
    {
      "epoch": 0.5906593406593407,
      "grad_norm": 0.27617966134680133,
      "learning_rate": 4.761146496815287e-05,
      "loss": 0.0027,
      "step": 430
    },
    {
      "epoch": 0.6043956043956044,
      "grad_norm": 0.19749811245827784,
      "learning_rate": 4.601910828025478e-05,
      "loss": 0.005,
      "step": 440
    },
    {
      "epoch": 0.6181318681318682,
      "grad_norm": 0.02810687835594959,
      "learning_rate": 4.442675159235669e-05,
      "loss": 0.0022,
      "step": 450
    },
    {
      "epoch": 0.6318681318681318,
      "grad_norm": 0.1919088763262812,
      "learning_rate": 4.2834394904458604e-05,
      "loss": 0.005,
      "step": 460
    },
    {
      "epoch": 0.6456043956043956,
      "grad_norm": 0.07067931858229538,
      "learning_rate": 4.1242038216560514e-05,
      "loss": 0.0024,
      "step": 470
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.14975480118292797,
      "learning_rate": 3.964968152866242e-05,
      "loss": 0.003,
      "step": 480
    },
    {
      "epoch": 0.6730769230769231,
      "grad_norm": 0.1893501746088407,
      "learning_rate": 3.805732484076434e-05,
      "loss": 0.0041,
      "step": 490
    },
    {
      "epoch": 0.6868131868131868,
      "grad_norm": 0.014297215049724657,
      "learning_rate": 3.646496815286624e-05,
      "loss": 0.0044,
      "step": 500
    },
    {
      "epoch": 0.7005494505494505,
      "grad_norm": 0.16316667250692118,
      "learning_rate": 3.487261146496815e-05,
      "loss": 0.005,
      "step": 510
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.037938192498763186,
      "learning_rate": 3.328025477707007e-05,
      "loss": 0.0037,
      "step": 520
    },
    {
      "epoch": 0.728021978021978,
      "grad_norm": 0.08492737645910046,
      "learning_rate": 3.1687898089171976e-05,
      "loss": 0.0022,
      "step": 530
    },
    {
      "epoch": 0.7417582417582418,
      "grad_norm": 0.06111601739850969,
      "learning_rate": 3.0095541401273885e-05,
      "loss": 0.0025,
      "step": 540
    },
    {
      "epoch": 0.7554945054945055,
      "grad_norm": 0.019848217192186213,
      "learning_rate": 2.8503184713375798e-05,
      "loss": 0.0038,
      "step": 550
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.3383546978796607,
      "learning_rate": 2.6910828025477707e-05,
      "loss": 0.0038,
      "step": 560
    },
    {
      "epoch": 0.782967032967033,
      "grad_norm": 1.9490031970116397,
      "learning_rate": 2.531847133757962e-05,
      "loss": 0.2375,
      "step": 570
    },
    {
      "epoch": 0.7967032967032966,
      "grad_norm": 0.34324620931286737,
      "learning_rate": 2.372611464968153e-05,
      "loss": 0.4318,
      "step": 580
    },
    {
      "epoch": 0.8104395604395604,
      "grad_norm": 1.3941788760561156,
      "learning_rate": 2.2133757961783442e-05,
      "loss": 0.2539,
      "step": 590
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 2.7410333944585688,
      "learning_rate": 2.054140127388535e-05,
      "loss": 1.4498,
      "step": 600
    },
    {
      "epoch": 0.8379120879120879,
      "grad_norm": 1.4457009494440505,
      "learning_rate": 1.8949044585987264e-05,
      "loss": 1.4875,
      "step": 610
    },
    {
      "epoch": 0.8516483516483516,
      "grad_norm": 1.3634589208479944,
      "learning_rate": 1.7356687898089173e-05,
      "loss": 1.6336,
      "step": 620
    },
    {
      "epoch": 0.8653846153846154,
      "grad_norm": 1.298767831617216,
      "learning_rate": 1.5764331210191083e-05,
      "loss": 1.4133,
      "step": 630
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 1.006906042477125,
      "learning_rate": 1.4171974522292993e-05,
      "loss": 1.4242,
      "step": 640
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 1.2219253582787113,
      "learning_rate": 1.2579617834394904e-05,
      "loss": 1.5016,
      "step": 650
    },
    {
      "epoch": 0.9065934065934066,
      "grad_norm": 2.3238849538833266,
      "learning_rate": 1.0987261146496815e-05,
      "loss": 1.7574,
      "step": 660
    },
    {
      "epoch": 0.9203296703296703,
      "grad_norm": 2.398596066971261,
      "learning_rate": 9.394904458598726e-06,
      "loss": 2.3672,
      "step": 670
    },
    {
      "epoch": 0.9340659340659341,
      "grad_norm": 2.397067357911802,
      "learning_rate": 7.802547770700637e-06,
      "loss": 0.7084,
      "step": 680
    },
    {
      "epoch": 0.9478021978021978,
      "grad_norm": 3.623094463011669,
      "learning_rate": 6.210191082802548e-06,
      "loss": 1.5625,
      "step": 690
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 3.023019788637967,
      "learning_rate": 4.6178343949044585e-06,
      "loss": 1.8281,
      "step": 700
    },
    {
      "epoch": 0.9752747252747253,
      "grad_norm": 3.21367238289211,
      "learning_rate": 3.0254777070063695e-06,
      "loss": 1.7805,
      "step": 710
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 1.965949094153684,
      "learning_rate": 1.4331210191082802e-06,
      "loss": 1.8953,
      "step": 720
    }
  ],
  "logging_steps": 10,
  "max_steps": 728,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}