{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9976438909458096,
  "eval_steps": 371,
  "global_step": 2968,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03365870077415012,
      "grad_norm": 2.984375,
      "learning_rate": 1.8421052631578947e-05,
      "loss": 1.0907,
      "step": 50
    },
    {
      "epoch": 0.06731740154830024,
      "grad_norm": 2.6875,
      "learning_rate": 3.721804511278196e-05,
      "loss": 0.7488,
      "step": 100
    },
    {
      "epoch": 0.10097610232245036,
      "grad_norm": 1.9453125,
      "learning_rate": 4.999831161062044e-05,
      "loss": 0.7217,
      "step": 150
    },
    {
      "epoch": 0.13463480309660047,
      "grad_norm": 1.734375,
      "learning_rate": 4.997127617815812e-05,
      "loss": 0.7079,
      "step": 200
    },
    {
      "epoch": 0.1682935038707506,
      "grad_norm": 1.46875,
      "learning_rate": 4.9911305528702e-05,
      "loss": 0.6731,
      "step": 250
    },
    {
      "epoch": 0.2019522046449007,
      "grad_norm": 1.4609375,
      "learning_rate": 4.981847875898461e-05,
      "loss": 0.6538,
      "step": 300
    },
    {
      "epoch": 0.23561090541905083,
      "grad_norm": 1.40625,
      "learning_rate": 4.9692918300466075e-05,
      "loss": 0.6337,
      "step": 350
    },
    {
      "epoch": 0.24974755974419388,
      "eval_loss": 0.6199322938919067,
      "eval_runtime": 100.4004,
      "eval_samples_per_second": 24.93,
      "eval_steps_per_second": 6.235,
      "step": 371
    },
    {
      "epoch": 0.26926960619320095,
      "grad_norm": 1.3203125,
      "learning_rate": 4.953478975785629e-05,
      "loss": 0.6167,
      "step": 400
    },
    {
      "epoch": 0.30292830696735107,
      "grad_norm": 1.2421875,
      "learning_rate": 4.934430169069488e-05,
      "loss": 0.6001,
      "step": 450
    },
    {
      "epoch": 0.3365870077415012,
      "grad_norm": 1.171875,
      "learning_rate": 4.9121705338277035e-05,
      "loss": 0.595,
      "step": 500
    },
    {
      "epoch": 0.3702457085156513,
      "grad_norm": 1.140625,
      "learning_rate": 4.886729428828791e-05,
      "loss": 0.5824,
      "step": 550
    },
    {
      "epoch": 0.4039044092898014,
      "grad_norm": 1.09375,
      "learning_rate": 4.858140408958282e-05,
      "loss": 0.5798,
      "step": 600
    },
    {
      "epoch": 0.43756311006395154,
      "grad_norm": 1.0546875,
      "learning_rate": 4.826441180962373e-05,
      "loss": 0.563,
      "step": 650
    },
    {
      "epoch": 0.47122181083810166,
      "grad_norm": 1.140625,
      "learning_rate": 4.7916735537155956e-05,
      "loss": 0.561,
      "step": 700
    },
    {
      "epoch": 0.49949511948838776,
      "eval_loss": 0.563587486743927,
      "eval_runtime": 100.0625,
      "eval_samples_per_second": 25.014,
      "eval_steps_per_second": 6.256,
      "step": 742
    },
    {
      "epoch": 0.5048805116122518,
      "grad_norm": 1.0703125,
      "learning_rate": 4.753883383078079e-05,
      "loss": 0.5537,
      "step": 750
    },
    {
      "epoch": 0.5385392123864019,
      "grad_norm": 1.0234375,
      "learning_rate": 4.71312051141516e-05,
      "loss": 0.5381,
      "step": 800
    },
    {
      "epoch": 0.572197913160552,
      "grad_norm": 1.0390625,
      "learning_rate": 4.669438701859086e-05,
      "loss": 0.5376,
      "step": 850
    },
    {
      "epoch": 0.6058566139347021,
      "grad_norm": 0.98046875,
      "learning_rate": 4.6228955673995206e-05,
      "loss": 0.5311,
      "step": 900
    },
    {
      "epoch": 0.6395153147088523,
      "grad_norm": 0.94921875,
      "learning_rate": 4.5735524948963945e-05,
      "loss": 0.5254,
      "step": 950
    },
    {
      "epoch": 0.6731740154830024,
      "grad_norm": 0.94921875,
      "learning_rate": 4.521474564115293e-05,
      "loss": 0.5235,
      "step": 1000
    },
    {
      "epoch": 0.7068327162571525,
      "grad_norm": 1.0,
      "learning_rate": 4.4667304618921875e-05,
      "loss": 0.517,
      "step": 1050
    },
    {
      "epoch": 0.7404914170313026,
      "grad_norm": 0.98828125,
      "learning_rate": 4.4093923915407166e-05,
      "loss": 0.5065,
      "step": 1100
    },
    {
      "epoch": 0.7492426792325816,
      "eval_loss": 0.5226994156837463,
      "eval_runtime": 99.9631,
      "eval_samples_per_second": 25.039,
      "eval_steps_per_second": 6.262,
      "step": 1113
    },
    {
      "epoch": 0.7741501178054527,
      "grad_norm": 1.0,
      "learning_rate": 4.349535977621498e-05,
      "loss": 0.5059,
      "step": 1150
    },
    {
      "epoch": 0.8078088185796028,
      "grad_norm": 0.95703125,
      "learning_rate": 4.2872401661990755e-05,
      "loss": 0.4953,
      "step": 1200
    },
    {
      "epoch": 0.841467519353753,
      "grad_norm": 0.97265625,
      "learning_rate": 4.222587120718056e-05,
      "loss": 0.497,
      "step": 1250
    },
    {
      "epoch": 0.8751262201279031,
      "grad_norm": 0.87890625,
      "learning_rate": 4.155662113635761e-05,
      "loss": 0.4887,
      "step": 1300
    },
    {
      "epoch": 0.9087849209020532,
      "grad_norm": 0.93359375,
      "learning_rate": 4.0865534139543396e-05,
      "loss": 0.492,
      "step": 1350
    },
    {
      "epoch": 0.9424436216762033,
      "grad_norm": 0.890625,
      "learning_rate": 4.0153521708006474e-05,
      "loss": 0.4841,
      "step": 1400
    },
    {
      "epoch": 0.9761023224503534,
      "grad_norm": 0.96875,
      "learning_rate": 3.9421522932074786e-05,
      "loss": 0.4799,
      "step": 1450
    },
    {
      "epoch": 0.9989902389767755,
      "eval_loss": 0.4874838888645172,
      "eval_runtime": 98.6858,
      "eval_samples_per_second": 25.363,
      "eval_steps_per_second": 6.343,
      "step": 1484
    },
    {
      "epoch": 1.009424436216762,
      "grad_norm": 0.7890625,
      "learning_rate": 3.867050326254679e-05,
      "loss": 0.4807,
      "step": 1500
    },
    {
      "epoch": 1.0430831369909122,
      "grad_norm": 0.80078125,
      "learning_rate": 3.790145323733514e-05,
      "loss": 0.385,
      "step": 1550
    },
    {
      "epoch": 1.0767418377650624,
      "grad_norm": 0.77734375,
      "learning_rate": 3.71153871750225e-05,
      "loss": 0.388,
      "step": 1600
    },
    {
      "epoch": 1.1104005385392124,
      "grad_norm": 0.734375,
      "learning_rate": 3.631334183705223e-05,
      "loss": 0.3861,
      "step": 1650
    },
    {
      "epoch": 1.1440592393133624,
      "grad_norm": 0.89453125,
      "learning_rate": 3.5496375060318876e-05,
      "loss": 0.3832,
      "step": 1700
    },
    {
      "epoch": 1.1777179400875126,
      "grad_norm": 0.84375,
      "learning_rate": 3.46655643619616e-05,
      "loss": 0.3813,
      "step": 1750
    },
    {
      "epoch": 1.2113766408616629,
      "grad_norm": 0.890625,
      "learning_rate": 3.3822005518200875e-05,
      "loss": 0.3817,
      "step": 1800
    },
    {
      "epoch": 1.2450353416358129,
      "grad_norm": 0.72265625,
      "learning_rate": 3.296681111909288e-05,
      "loss": 0.3789,
      "step": 1850
    },
    {
      "epoch": 1.248401211713228,
      "eval_loss": 0.46673256158828735,
      "eval_runtime": 100.3992,
      "eval_samples_per_second": 24.93,
      "eval_steps_per_second": 6.235,
      "step": 1855
    },
    {
      "epoch": 1.2786940424099629,
      "grad_norm": 0.921875,
      "learning_rate": 3.210110910110775e-05,
      "loss": 0.378,
      "step": 1900
    },
    {
      "epoch": 1.312352743184113,
      "grad_norm": 0.89453125,
      "learning_rate": 3.122604125946696e-05,
      "loss": 0.3724,
      "step": 1950
    },
    {
      "epoch": 1.3460114439582633,
      "grad_norm": 0.76171875,
      "learning_rate": 3.0342761742202137e-05,
      "loss": 0.3729,
      "step": 2000
    },
    {
      "epoch": 1.3796701447324133,
      "grad_norm": 0.85546875,
      "learning_rate": 2.9452435527921506e-05,
      "loss": 0.3688,
      "step": 2050
    },
    {
      "epoch": 1.4133288455065633,
      "grad_norm": 0.72265625,
      "learning_rate": 2.855623688929152e-05,
      "loss": 0.3681,
      "step": 2100
    },
    {
      "epoch": 1.4469875462807136,
      "grad_norm": 0.90234375,
      "learning_rate": 2.7655347844260417e-05,
      "loss": 0.3629,
      "step": 2150
    },
    {
      "epoch": 1.4806462470548638,
      "grad_norm": 0.82421875,
      "learning_rate": 2.6750956597066286e-05,
      "loss": 0.3637,
      "step": 2200
    },
    {
      "epoch": 1.4981487714574218,
      "eval_loss": 0.4537140727043152,
      "eval_runtime": 100.1826,
      "eval_samples_per_second": 24.984,
      "eval_steps_per_second": 6.249,
      "step": 2226
    },
    {
      "epoch": 1.5143049478290138,
      "grad_norm": 0.91015625,
      "learning_rate": 2.5844255971085913e-05,
      "loss": 0.3652,
      "step": 2250
    },
    {
      "epoch": 1.5479636486031638,
      "grad_norm": 0.7890625,
      "learning_rate": 2.493644183559134e-05,
      "loss": 0.357,
      "step": 2300
    },
    {
      "epoch": 1.581622349377314,
      "grad_norm": 0.73046875,
      "learning_rate": 2.4028711528489107e-05,
      "loss": 0.3573,
      "step": 2350
    },
    {
      "epoch": 1.6152810501514643,
      "grad_norm": 0.78515625,
      "learning_rate": 2.312226227712245e-05,
      "loss": 0.356,
      "step": 2400
    },
    {
      "epoch": 1.6489397509256143,
      "grad_norm": 0.78125,
      "learning_rate": 2.221828961921939e-05,
      "loss": 0.3532,
      "step": 2450
    },
    {
      "epoch": 1.6825984516997643,
      "grad_norm": 0.7890625,
      "learning_rate": 2.1317985826069228e-05,
      "loss": 0.3496,
      "step": 2500
    },
    {
      "epoch": 1.7162571524739145,
      "grad_norm": 0.78515625,
      "learning_rate": 2.042253833000726e-05,
      "loss": 0.3479,
      "step": 2550
    },
    {
      "epoch": 1.7478963312016156,
      "eval_loss": 0.4370940923690796,
      "eval_runtime": 100.667,
      "eval_samples_per_second": 24.864,
      "eval_steps_per_second": 6.219,
      "step": 2597
    },
    {
      "epoch": 1.7499158532480648,
      "grad_norm": 0.9609375,
      "learning_rate": 1.9533128158281727e-05,
      "loss": 0.3489,
      "step": 2600
    },
    {
      "epoch": 1.7835745540222148,
      "grad_norm": 0.89453125,
      "learning_rate": 1.865092837536851e-05,
      "loss": 0.3438,
      "step": 2650
    },
    {
      "epoch": 1.8172332547963648,
      "grad_norm": 0.859375,
      "learning_rate": 1.777710253578821e-05,
      "loss": 0.3439,
      "step": 2700
    },
    {
      "epoch": 1.850891955570515,
      "grad_norm": 0.76953125,
      "learning_rate": 1.6912803149466065e-05,
      "loss": 0.3417,
      "step": 2750
    },
    {
      "epoch": 1.8845506563446652,
      "grad_norm": 0.84765625,
      "learning_rate": 1.605917016165891e-05,
      "loss": 0.3398,
      "step": 2800
    },
    {
      "epoch": 1.9182093571188152,
      "grad_norm": 0.8515625,
      "learning_rate": 1.5217329449453915e-05,
      "loss": 0.3401,
      "step": 2850
    },
    {
      "epoch": 1.9518680578929652,
      "grad_norm": 0.8671875,
      "learning_rate": 1.4388391336822216e-05,
      "loss": 0.3389,
      "step": 2900
    },
    {
      "epoch": 1.9855267586671155,
      "grad_norm": 0.890625,
      "learning_rate": 1.3573449130185945e-05,
      "loss": 0.3311,
      "step": 2950
    },
    {
      "epoch": 1.9976438909458096,
      "eval_loss": 0.4261794984340668,
      "eval_runtime": 99.6602,
      "eval_samples_per_second": 25.115,
      "eval_steps_per_second": 6.281,
      "step": 2968
    }
  ],
  "logging_steps": 50,
  "max_steps": 4458,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 371,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7464408109253181e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}