{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 17.094017094017094,
  "eval_steps": 1000,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005698005698005698,
      "grad_norm": 6.307312488555908,
      "learning_rate": 0.0,
      "loss": 3.0911,
      "step": 1
    },
    {
      "epoch": 0.2849002849002849,
      "grad_norm": 4.076864719390869,
      "learning_rate": 0.0001977977977977978,
      "loss": 1.4649,
      "step": 50
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 2.819526195526123,
      "learning_rate": 0.0001952952952952953,
      "loss": 1.1601,
      "step": 100
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 3.7976534366607666,
      "learning_rate": 0.00019279279279279282,
      "loss": 1.1284,
      "step": 150
    },
    {
      "epoch": 1.1396011396011396,
      "grad_norm": 3.787907838821411,
      "learning_rate": 0.0001902902902902903,
      "loss": 0.91,
      "step": 200
    },
    {
      "epoch": 1.4245014245014245,
      "grad_norm": 3.807788133621216,
      "learning_rate": 0.0001877877877877878,
      "loss": 0.7007,
      "step": 250
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 3.6782045364379883,
      "learning_rate": 0.00018528528528528532,
      "loss": 0.6793,
      "step": 300
    },
    {
      "epoch": 1.9943019943019942,
      "grad_norm": 3.648346424102783,
      "learning_rate": 0.0001827827827827828,
      "loss": 0.7325,
      "step": 350
    },
    {
      "epoch": 2.2792022792022792,
      "grad_norm": 3.3711447715759277,
      "learning_rate": 0.00018028028028028027,
      "loss": 0.3936,
      "step": 400
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 3.362125873565674,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.3844,
      "step": 450
    },
    {
      "epoch": 2.849002849002849,
      "grad_norm": 3.8006858825683594,
      "learning_rate": 0.00017527527527527528,
      "loss": 0.4327,
      "step": 500
    },
    {
      "epoch": 3.133903133903134,
      "grad_norm": 3.940809488296509,
      "learning_rate": 0.00017277277277277277,
      "loss": 0.3364,
      "step": 550
    },
    {
      "epoch": 3.4188034188034186,
      "grad_norm": 3.061803102493286,
      "learning_rate": 0.00017027027027027028,
      "loss": 0.2445,
      "step": 600
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 3.389284372329712,
      "learning_rate": 0.00016776776776776777,
      "loss": 0.2597,
      "step": 650
    },
    {
      "epoch": 3.9886039886039883,
      "grad_norm": 3.320084810256958,
      "learning_rate": 0.00016526526526526526,
      "loss": 0.2698,
      "step": 700
    },
    {
      "epoch": 4.273504273504273,
      "grad_norm": 2.7199738025665283,
      "learning_rate": 0.00016276276276276275,
      "loss": 0.1781,
      "step": 750
    },
    {
      "epoch": 4.5584045584045585,
      "grad_norm": 3.226743459701538,
      "learning_rate": 0.00016026026026026027,
      "loss": 0.1902,
      "step": 800
    },
    {
      "epoch": 4.843304843304844,
      "grad_norm": 4.62879753112793,
      "learning_rate": 0.00015775775775775776,
      "loss": 0.209,
      "step": 850
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 2.747284412384033,
      "learning_rate": 0.00015525525525525525,
      "loss": 0.1786,
      "step": 900
    },
    {
      "epoch": 5.413105413105413,
      "grad_norm": 2.259187936782837,
      "learning_rate": 0.00015275275275275277,
      "loss": 0.1536,
      "step": 950
    },
    {
      "epoch": 5.698005698005698,
      "grad_norm": 1.9622772932052612,
      "learning_rate": 0.00015025025025025026,
      "loss": 0.156,
      "step": 1000
    },
    {
      "epoch": 5.982905982905983,
      "grad_norm": 2.236668825149536,
      "learning_rate": 0.00014774774774774775,
      "loss": 0.1618,
      "step": 1050
    },
    {
      "epoch": 6.267806267806268,
      "grad_norm": 3.983106851577759,
      "learning_rate": 0.00014524524524524526,
      "loss": 0.1273,
      "step": 1100
    },
    {
      "epoch": 6.552706552706553,
      "grad_norm": 1.7318657636642456,
      "learning_rate": 0.00014274274274274275,
      "loss": 0.1334,
      "step": 1150
    },
    {
      "epoch": 6.837606837606837,
      "grad_norm": 1.885850191116333,
      "learning_rate": 0.00014024024024024024,
      "loss": 0.1329,
      "step": 1200
    },
    {
      "epoch": 7.122507122507122,
      "grad_norm": 4.529383659362793,
      "learning_rate": 0.00013773773773773776,
      "loss": 0.1313,
      "step": 1250
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 2.217284679412842,
      "learning_rate": 0.00013523523523523525,
      "loss": 0.114,
      "step": 1300
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 2.4019832611083984,
      "learning_rate": 0.00013273273273273274,
      "loss": 0.1175,
      "step": 1350
    },
    {
      "epoch": 7.977207977207978,
      "grad_norm": 2.7499570846557617,
      "learning_rate": 0.00013023023023023023,
      "loss": 0.1229,
      "step": 1400
    },
    {
      "epoch": 8.262108262108262,
      "grad_norm": 1.7632925510406494,
      "learning_rate": 0.00012772772772772775,
      "loss": 0.0974,
      "step": 1450
    },
    {
      "epoch": 8.547008547008547,
      "grad_norm": 1.798587441444397,
      "learning_rate": 0.00012522522522522524,
      "loss": 0.1031,
      "step": 1500
    },
    {
      "epoch": 8.831908831908832,
      "grad_norm": 2.925875663757324,
      "learning_rate": 0.00012272272272272273,
      "loss": 0.1098,
      "step": 1550
    },
    {
      "epoch": 9.116809116809117,
      "grad_norm": 2.593219757080078,
      "learning_rate": 0.00012022022022022023,
      "loss": 0.0979,
      "step": 1600
    },
    {
      "epoch": 9.401709401709402,
      "grad_norm": 2.457099199295044,
      "learning_rate": 0.00011771771771771771,
      "loss": 0.0917,
      "step": 1650
    },
    {
      "epoch": 9.686609686609687,
      "grad_norm": 2.513124465942383,
      "learning_rate": 0.00011521521521521521,
      "loss": 0.0884,
      "step": 1700
    },
    {
      "epoch": 9.971509971509972,
      "grad_norm": 0.9835783243179321,
      "learning_rate": 0.00011271271271271271,
      "loss": 0.0891,
      "step": 1750
    },
    {
      "epoch": 10.256410256410255,
      "grad_norm": 1.4291648864746094,
      "learning_rate": 0.0001102102102102102,
      "loss": 0.0792,
      "step": 1800
    },
    {
      "epoch": 10.54131054131054,
      "grad_norm": 0.974391758441925,
      "learning_rate": 0.00010770770770770771,
      "loss": 0.0834,
      "step": 1850
    },
    {
      "epoch": 10.826210826210826,
      "grad_norm": 2.3604581356048584,
      "learning_rate": 0.0001052052052052052,
      "loss": 0.0829,
      "step": 1900
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 1.6176166534423828,
      "learning_rate": 0.0001027027027027027,
      "loss": 0.08,
      "step": 1950
    },
    {
      "epoch": 11.396011396011396,
      "grad_norm": 1.9266570806503296,
      "learning_rate": 0.0001002002002002002,
      "loss": 0.0763,
      "step": 2000
    },
    {
      "epoch": 11.68091168091168,
      "grad_norm": 2.1315979957580566,
      "learning_rate": 9.76976976976977e-05,
      "loss": 0.0769,
      "step": 2050
    },
    {
      "epoch": 11.965811965811966,
      "grad_norm": 1.4953100681304932,
      "learning_rate": 9.51951951951952e-05,
      "loss": 0.0787,
      "step": 2100
    },
    {
      "epoch": 12.250712250712251,
      "grad_norm": 1.715878963470459,
      "learning_rate": 9.26926926926927e-05,
      "loss": 0.0699,
      "step": 2150
    },
    {
      "epoch": 12.535612535612536,
      "grad_norm": 0.5827972888946533,
      "learning_rate": 9.019019019019019e-05,
      "loss": 0.0738,
      "step": 2200
    },
    {
      "epoch": 12.820512820512821,
      "grad_norm": 0.3549967408180237,
      "learning_rate": 8.76876876876877e-05,
      "loss": 0.0743,
      "step": 2250
    },
    {
      "epoch": 13.105413105413106,
      "grad_norm": 2.361628532409668,
      "learning_rate": 8.518518518518518e-05,
      "loss": 0.0692,
      "step": 2300
    },
    {
      "epoch": 13.39031339031339,
      "grad_norm": 1.2454289197921753,
      "learning_rate": 8.268268268268269e-05,
      "loss": 0.0711,
      "step": 2350
    },
    {
      "epoch": 13.675213675213675,
      "grad_norm": 1.1497353315353394,
      "learning_rate": 8.018018018018019e-05,
      "loss": 0.0688,
      "step": 2400
    },
    {
      "epoch": 13.96011396011396,
      "grad_norm": 2.107264995574951,
      "learning_rate": 7.767767767767768e-05,
      "loss": 0.0706,
      "step": 2450
    },
    {
      "epoch": 14.245014245014245,
      "grad_norm": 0.4413589537143707,
      "learning_rate": 7.517517517517519e-05,
      "loss": 0.0664,
      "step": 2500
    },
    {
      "epoch": 14.52991452991453,
      "grad_norm": 1.1788307428359985,
      "learning_rate": 7.267267267267268e-05,
      "loss": 0.0658,
      "step": 2550
    },
    {
      "epoch": 14.814814814814815,
      "grad_norm": 0.5639584064483643,
      "learning_rate": 7.017017017017016e-05,
      "loss": 0.063,
      "step": 2600
    },
    {
      "epoch": 15.0997150997151,
      "grad_norm": 0.2644463777542114,
      "learning_rate": 6.766766766766767e-05,
      "loss": 0.0653,
      "step": 2650
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 0.10696238279342651,
      "learning_rate": 6.516516516516516e-05,
      "loss": 0.0614,
      "step": 2700
    },
    {
      "epoch": 15.66951566951567,
      "grad_norm": 1.1413618326187134,
      "learning_rate": 6.266266266266266e-05,
      "loss": 0.0637,
      "step": 2750
    },
    {
      "epoch": 15.954415954415955,
      "grad_norm": 0.09536276012659073,
      "learning_rate": 6.016016016016016e-05,
      "loss": 0.0617,
      "step": 2800
    },
    {
      "epoch": 16.23931623931624,
      "grad_norm": 0.09245631843805313,
      "learning_rate": 5.765765765765766e-05,
      "loss": 0.06,
      "step": 2850
    },
    {
      "epoch": 16.524216524216524,
      "grad_norm": 1.483127474784851,
      "learning_rate": 5.515515515515516e-05,
      "loss": 0.0605,
      "step": 2900
    },
    {
      "epoch": 16.80911680911681,
      "grad_norm": 0.12009686231613159,
      "learning_rate": 5.2652652652652655e-05,
      "loss": 0.062,
      "step": 2950
    },
    {
      "epoch": 17.094017094017094,
      "grad_norm": 0.0926225408911705,
      "learning_rate": 5.015015015015015e-05,
      "loss": 0.0586,
      "step": 3000
    }
  ],
  "logging_steps": 50,
  "max_steps": 4001,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 23,
  "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": 9.09931874049065e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}