{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 287,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017452006980802792,
      "grad_norm": 18.758426666259766,
      "learning_rate": 2.7586206896551725e-06,
      "loss": 1.2108,
      "step": 5
    },
    {
      "epoch": 0.034904013961605584,
      "grad_norm": 0.6289834976196289,
      "learning_rate": 6.206896551724138e-06,
      "loss": 0.2604,
      "step": 10
    },
    {
      "epoch": 0.05235602094240838,
      "grad_norm": 0.7779368758201599,
      "learning_rate": 9.655172413793105e-06,
      "loss": 0.0645,
      "step": 15
    },
    {
      "epoch": 0.06980802792321117,
      "grad_norm": 0.7711329460144043,
      "learning_rate": 1.310344827586207e-05,
      "loss": 0.0643,
      "step": 20
    },
    {
      "epoch": 0.08726003490401396,
      "grad_norm": 1.1758290529251099,
      "learning_rate": 1.6551724137931037e-05,
      "loss": 0.0682,
      "step": 25
    },
    {
      "epoch": 0.10471204188481675,
      "grad_norm": 0.20803742110729218,
      "learning_rate": 2e-05,
      "loss": 0.0648,
      "step": 30
    },
    {
      "epoch": 0.12216404886561955,
      "grad_norm": 0.3231872320175171,
      "learning_rate": 1.998147167378645e-05,
      "loss": 0.0638,
      "step": 35
    },
    {
      "epoch": 0.13961605584642234,
      "grad_norm": 0.20903366804122925,
      "learning_rate": 1.9925955354920265e-05,
      "loss": 0.0631,
      "step": 40
    },
    {
      "epoch": 0.15706806282722513,
      "grad_norm": 0.1551412045955658,
      "learning_rate": 1.983365676829466e-05,
      "loss": 0.0637,
      "step": 45
    },
    {
      "epoch": 0.17452006980802792,
      "grad_norm": 0.10300405323505402,
      "learning_rate": 1.9704917941574053e-05,
      "loss": 0.0633,
      "step": 50
    },
    {
      "epoch": 0.19197207678883071,
      "grad_norm": 0.05463937669992447,
      "learning_rate": 1.954021593775401e-05,
      "loss": 0.0634,
      "step": 55
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 0.05097668617963791,
      "learning_rate": 1.9340161087325483e-05,
      "loss": 0.0637,
      "step": 60
    },
    {
      "epoch": 0.2268760907504363,
      "grad_norm": 0.025731965899467468,
      "learning_rate": 1.9105494726594344e-05,
      "loss": 0.0634,
      "step": 65
    },
    {
      "epoch": 0.2443280977312391,
      "grad_norm": 0.5567801594734192,
      "learning_rate": 1.8837086450537195e-05,
      "loss": 0.0643,
      "step": 70
    },
    {
      "epoch": 0.2617801047120419,
      "grad_norm": 0.07695559412240982,
      "learning_rate": 1.8535930890373467e-05,
      "loss": 0.0633,
      "step": 75
    },
    {
      "epoch": 0.2792321116928447,
      "grad_norm": 0.13339029252529144,
      "learning_rate": 1.820314402779511e-05,
      "loss": 0.0633,
      "step": 80
    },
    {
      "epoch": 0.29668411867364747,
      "grad_norm": 0.10536781698465347,
      "learning_rate": 1.7839959059512016e-05,
      "loss": 0.0638,
      "step": 85
    },
    {
      "epoch": 0.31413612565445026,
      "grad_norm": 0.12401806563138962,
      "learning_rate": 1.744772182743782e-05,
      "loss": 0.0633,
      "step": 90
    },
    {
      "epoch": 0.33158813263525305,
      "grad_norm": 0.1011064425110817,
      "learning_rate": 1.7027885831450318e-05,
      "loss": 0.0629,
      "step": 95
    },
    {
      "epoch": 0.34904013961605584,
      "grad_norm": 0.13563387095928192,
      "learning_rate": 1.658200684320748e-05,
      "loss": 0.0632,
      "step": 100
    },
    {
      "epoch": 0.36649214659685864,
      "grad_norm": 0.26744481921195984,
      "learning_rate": 1.6111737140978495e-05,
      "loss": 0.0633,
      "step": 105
    },
    {
      "epoch": 0.38394415357766143,
      "grad_norm": 0.6496581435203552,
      "learning_rate": 1.5618819386853607e-05,
      "loss": 0.0638,
      "step": 110
    },
    {
      "epoch": 0.4013961605584642,
      "grad_norm": 0.2886026203632355,
      "learning_rate": 1.5105080169021792e-05,
      "loss": 0.0637,
      "step": 115
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 0.07766488194465637,
      "learning_rate": 1.4572423233046386e-05,
      "loss": 0.064,
      "step": 120
    },
    {
      "epoch": 0.4363001745200698,
      "grad_norm": 0.152951180934906,
      "learning_rate": 1.4022822427221325e-05,
      "loss": 0.0637,
      "step": 125
    },
    {
      "epoch": 0.4537521815008726,
      "grad_norm": 0.4545815587043762,
      "learning_rate": 1.3458314388150115e-05,
      "loss": 0.0631,
      "step": 130
    },
    {
      "epoch": 0.4712041884816754,
      "grad_norm": 0.13478335738182068,
      "learning_rate": 1.2880990993652379e-05,
      "loss": 0.0627,
      "step": 135
    },
    {
      "epoch": 0.4886561954624782,
      "grad_norm": 0.45286211371421814,
      "learning_rate": 1.2292991610964902e-05,
      "loss": 0.0637,
      "step": 140
    },
    {
      "epoch": 0.506108202443281,
      "grad_norm": 0.44334903359413147,
      "learning_rate": 1.1696495168962848e-05,
      "loss": 0.0639,
      "step": 145
    },
    {
      "epoch": 0.5235602094240838,
      "grad_norm": 0.6045412421226501,
      "learning_rate": 1.1093712083778748e-05,
      "loss": 0.0644,
      "step": 150
    },
    {
      "epoch": 0.5410122164048866,
      "grad_norm": 0.5224294066429138,
      "learning_rate": 1.0486876067740253e-05,
      "loss": 0.0655,
      "step": 155
    },
    {
      "epoch": 0.5584642233856894,
      "grad_norm": 0.37020203471183777,
      "learning_rate": 9.878235851980027e-06,
      "loss": 0.0639,
      "step": 160
    },
    {
      "epoch": 0.5759162303664922,
      "grad_norm": 0.01445784978568554,
      "learning_rate": 9.270046853390924e-06,
      "loss": 0.0636,
      "step": 165
    },
    {
      "epoch": 0.5933682373472949,
      "grad_norm": 0.5739990472793579,
      "learning_rate": 8.664562816806022e-06,
      "loss": 0.0644,
      "step": 170
    },
    {
      "epoch": 0.6108202443280978,
      "grad_norm": 0.21191075444221497,
      "learning_rate": 8.064027463374702e-06,
      "loss": 0.0629,
      "step": 175
    },
    {
      "epoch": 0.6282722513089005,
      "grad_norm": 0.3500339686870575,
      "learning_rate": 7.470666176083193e-06,
      "loss": 0.0645,
      "step": 180
    },
    {
      "epoch": 0.6457242582897034,
      "grad_norm": 0.31313106417655945,
      "learning_rate": 6.886677753230184e-06,
      "loss": 0.0623,
      "step": 185
    },
    {
      "epoch": 0.6631762652705061,
      "grad_norm": 0.3150012791156769,
      "learning_rate": 6.314226260416383e-06,
      "loss": 0.0624,
      "step": 190
    },
    {
      "epoch": 0.680628272251309,
      "grad_norm": 0.19164550304412842,
      "learning_rate": 5.755433011241851e-06,
      "loss": 0.0621,
      "step": 195
    },
    {
      "epoch": 0.6980802792321117,
      "grad_norm": 0.448416143655777,
      "learning_rate": 5.212368706427913e-06,
      "loss": 0.0638,
      "step": 200
    },
    {
      "epoch": 0.7155322862129145,
      "grad_norm": 0.0443989560008049,
      "learning_rate": 4.687045760493468e-06,
      "loss": 0.0614,
      "step": 205
    },
    {
      "epoch": 0.7329842931937173,
      "grad_norm": 0.32341665029525757,
      "learning_rate": 4.181410844420473e-06,
      "loss": 0.0623,
      "step": 210
    },
    {
      "epoch": 0.7504363001745201,
      "grad_norm": 0.2636391222476959,
      "learning_rate": 3.6973376719429134e-06,
      "loss": 0.0604,
      "step": 215
    },
    {
      "epoch": 0.7678883071553229,
      "grad_norm": 0.27186042070388794,
      "learning_rate": 3.236620056190972e-06,
      "loss": 0.0601,
      "step": 220
    },
    {
      "epoch": 0.7853403141361257,
      "grad_norm": 0.5704047679901123,
      "learning_rate": 2.8009652624200436e-06,
      "loss": 0.0613,
      "step": 225
    },
    {
      "epoch": 0.8027923211169284,
      "grad_norm": 0.4298834204673767,
      "learning_rate": 2.3919876814572197e-06,
      "loss": 0.0592,
      "step": 230
    },
    {
      "epoch": 0.8202443280977313,
      "grad_norm": 0.08873734623193741,
      "learning_rate": 2.0112028473093294e-06,
      "loss": 0.0595,
      "step": 235
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 0.39123955368995667,
      "learning_rate": 1.660021821101222e-06,
      "loss": 0.0567,
      "step": 240
    },
    {
      "epoch": 0.8551483420593369,
      "grad_norm": 0.16050003468990326,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.0571,
      "step": 245
    },
    {
      "epoch": 0.8726003490401396,
      "grad_norm": 0.12748093903064728,
      "learning_rate": 1.051562105591082e-06,
      "loss": 0.0607,
      "step": 250
    },
    {
      "epoch": 0.8900523560209425,
      "grad_norm": 0.1128767654299736,
      "learning_rate": 7.965381643084069e-07,
      "loss": 0.0582,
      "step": 255
    },
    {
      "epoch": 0.9075043630017452,
      "grad_norm": 0.5375702381134033,
      "learning_rate": 5.756191716628556e-07,
      "loss": 0.0621,
      "step": 260
    },
    {
      "epoch": 0.924956369982548,
      "grad_norm": 0.272128164768219,
      "learning_rate": 3.8962377948693395e-07,
      "loss": 0.0579,
      "step": 265
    },
    {
      "epoch": 0.9424083769633508,
      "grad_norm": 0.12358862906694412,
      "learning_rate": 2.392412244407294e-07,
      "loss": 0.058,
      "step": 270
    },
    {
      "epoch": 0.9598603839441536,
      "grad_norm": 0.13405446708202362,
      "learning_rate": 1.2502877393158587e-07,
      "loss": 0.0592,
      "step": 275
    },
    {
      "epoch": 0.9773123909249564,
      "grad_norm": 0.12268463522195816,
      "learning_rate": 4.740966106764222e-08,
      "loss": 0.0565,
      "step": 280
    },
    {
      "epoch": 0.9947643979057592,
      "grad_norm": 0.6271886825561523,
      "learning_rate": 6.671516297606095e-09,
      "loss": 0.0593,
      "step": 285
    },
    {
      "epoch": 1.0,
      "step": 287,
      "total_flos": 3.259472961077248e+17,
      "train_loss": 0.08579332347738618,
      "train_runtime": 1625.0751,
      "train_samples_per_second": 11.273,
      "train_steps_per_second": 0.177
    }
  ],
  "logging_steps": 5,
  "max_steps": 287,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.259472961077248e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}