{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16644474034620507,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003328894806924101,
      "grad_norm": 37.75,
      "learning_rate": 1.9933422103861518e-05,
      "loss": 1.4084,
      "step": 10
    },
    {
      "epoch": 0.006657789613848202,
      "grad_norm": 12.125,
      "learning_rate": 1.9866844207723038e-05,
      "loss": 1.0474,
      "step": 20
    },
    {
      "epoch": 0.009986684420772303,
      "grad_norm": 45.25,
      "learning_rate": 1.9800266311584554e-05,
      "loss": 1.2455,
      "step": 30
    },
    {
      "epoch": 0.013315579227696404,
      "grad_norm": 13.9375,
      "learning_rate": 1.9733688415446073e-05,
      "loss": 1.1969,
      "step": 40
    },
    {
      "epoch": 0.016644474034620507,
      "grad_norm": 32.0,
      "learning_rate": 1.966711051930759e-05,
      "loss": 1.1659,
      "step": 50
    },
    {
      "epoch": 0.019973368841544607,
      "grad_norm": 19.0,
      "learning_rate": 1.960053262316911e-05,
      "loss": 1.1159,
      "step": 60
    },
    {
      "epoch": 0.02330226364846871,
      "grad_norm": 27.5,
      "learning_rate": 1.953395472703063e-05,
      "loss": 1.1861,
      "step": 70
    },
    {
      "epoch": 0.02663115845539281,
      "grad_norm": 17.5,
      "learning_rate": 1.9467376830892145e-05,
      "loss": 1.1073,
      "step": 80
    },
    {
      "epoch": 0.02996005326231691,
      "grad_norm": 33.75,
      "learning_rate": 1.9400798934753665e-05,
      "loss": 1.1506,
      "step": 90
    },
    {
      "epoch": 0.033288948069241014,
      "grad_norm": 9.5,
      "learning_rate": 1.933422103861518e-05,
      "loss": 1.246,
      "step": 100
    },
    {
      "epoch": 0.03661784287616511,
      "grad_norm": 11.3125,
      "learning_rate": 1.92676431424767e-05,
      "loss": 1.1708,
      "step": 110
    },
    {
      "epoch": 0.03994673768308921,
      "grad_norm": 14.375,
      "learning_rate": 1.9201065246338217e-05,
      "loss": 1.1302,
      "step": 120
    },
    {
      "epoch": 0.043275632490013316,
      "grad_norm": 20.625,
      "learning_rate": 1.9134487350199737e-05,
      "loss": 1.0537,
      "step": 130
    },
    {
      "epoch": 0.04660452729693742,
      "grad_norm": 21.75,
      "learning_rate": 1.9067909454061253e-05,
      "loss": 1.0669,
      "step": 140
    },
    {
      "epoch": 0.049933422103861515,
      "grad_norm": 14.125,
      "learning_rate": 1.900133155792277e-05,
      "loss": 1.0482,
      "step": 150
    },
    {
      "epoch": 0.05326231691078562,
      "grad_norm": 27.625,
      "learning_rate": 1.893475366178429e-05,
      "loss": 1.1468,
      "step": 160
    },
    {
      "epoch": 0.05659121171770972,
      "grad_norm": 4.53125,
      "learning_rate": 1.8868175765645805e-05,
      "loss": 1.092,
      "step": 170
    },
    {
      "epoch": 0.05992010652463382,
      "grad_norm": 32.5,
      "learning_rate": 1.8801597869507325e-05,
      "loss": 1.2208,
      "step": 180
    },
    {
      "epoch": 0.06324900133155792,
      "grad_norm": 56.0,
      "learning_rate": 1.873501997336884e-05,
      "loss": 1.2359,
      "step": 190
    },
    {
      "epoch": 0.06657789613848203,
      "grad_norm": 8.375,
      "learning_rate": 1.866844207723036e-05,
      "loss": 1.0712,
      "step": 200
    },
    {
      "epoch": 0.06990679094540612,
      "grad_norm": 26.375,
      "learning_rate": 1.860186418109188e-05,
      "loss": 1.0156,
      "step": 210
    },
    {
      "epoch": 0.07323568575233022,
      "grad_norm": 12.0,
      "learning_rate": 1.8535286284953397e-05,
      "loss": 1.0407,
      "step": 220
    },
    {
      "epoch": 0.07656458055925433,
      "grad_norm": 13.75,
      "learning_rate": 1.8468708388814916e-05,
      "loss": 1.0161,
      "step": 230
    },
    {
      "epoch": 0.07989347536617843,
      "grad_norm": 27.125,
      "learning_rate": 1.8402130492676432e-05,
      "loss": 1.1466,
      "step": 240
    },
    {
      "epoch": 0.08322237017310254,
      "grad_norm": 26.125,
      "learning_rate": 1.8335552596537952e-05,
      "loss": 1.3192,
      "step": 250
    },
    {
      "epoch": 0.08655126498002663,
      "grad_norm": 25.75,
      "learning_rate": 1.826897470039947e-05,
      "loss": 1.0628,
      "step": 260
    },
    {
      "epoch": 0.08988015978695073,
      "grad_norm": 29.25,
      "learning_rate": 1.8202396804260988e-05,
      "loss": 0.967,
      "step": 270
    },
    {
      "epoch": 0.09320905459387484,
      "grad_norm": 29.75,
      "learning_rate": 1.8135818908122504e-05,
      "loss": 1.0356,
      "step": 280
    },
    {
      "epoch": 0.09653794940079893,
      "grad_norm": 11.6875,
      "learning_rate": 1.806924101198402e-05,
      "loss": 0.9853,
      "step": 290
    },
    {
      "epoch": 0.09986684420772303,
      "grad_norm": 27.5,
      "learning_rate": 1.800266311584554e-05,
      "loss": 1.0279,
      "step": 300
    },
    {
      "epoch": 0.10319573901464714,
      "grad_norm": 5.65625,
      "learning_rate": 1.7936085219707056e-05,
      "loss": 1.0115,
      "step": 310
    },
    {
      "epoch": 0.10652463382157124,
      "grad_norm": 8.1875,
      "learning_rate": 1.7869507323568576e-05,
      "loss": 0.942,
      "step": 320
    },
    {
      "epoch": 0.10985352862849534,
      "grad_norm": 65.0,
      "learning_rate": 1.7802929427430096e-05,
      "loss": 1.0208,
      "step": 330
    },
    {
      "epoch": 0.11318242343541944,
      "grad_norm": 9.625,
      "learning_rate": 1.7736351531291612e-05,
      "loss": 1.1729,
      "step": 340
    },
    {
      "epoch": 0.11651131824234354,
      "grad_norm": 17.5,
      "learning_rate": 1.766977363515313e-05,
      "loss": 0.9322,
      "step": 350
    },
    {
      "epoch": 0.11984021304926765,
      "grad_norm": 28.125,
      "learning_rate": 1.7603195739014648e-05,
      "loss": 1.0417,
      "step": 360
    },
    {
      "epoch": 0.12316910785619174,
      "grad_norm": 18.25,
      "learning_rate": 1.7536617842876168e-05,
      "loss": 1.2491,
      "step": 370
    },
    {
      "epoch": 0.12649800266311584,
      "grad_norm": 27.375,
      "learning_rate": 1.7470039946737684e-05,
      "loss": 0.9388,
      "step": 380
    },
    {
      "epoch": 0.12982689747003995,
      "grad_norm": 22.125,
      "learning_rate": 1.7403462050599203e-05,
      "loss": 1.0488,
      "step": 390
    },
    {
      "epoch": 0.13315579227696406,
      "grad_norm": 21.25,
      "learning_rate": 1.733688415446072e-05,
      "loss": 0.9951,
      "step": 400
    },
    {
      "epoch": 0.13648468708388814,
      "grad_norm": 11.75,
      "learning_rate": 1.727030625832224e-05,
      "loss": 0.9212,
      "step": 410
    },
    {
      "epoch": 0.13981358189081225,
      "grad_norm": 16.25,
      "learning_rate": 1.7203728362183756e-05,
      "loss": 1.0548,
      "step": 420
    },
    {
      "epoch": 0.14314247669773636,
      "grad_norm": 19.875,
      "learning_rate": 1.7137150466045275e-05,
      "loss": 1.0238,
      "step": 430
    },
    {
      "epoch": 0.14647137150466044,
      "grad_norm": 18.875,
      "learning_rate": 1.707057256990679e-05,
      "loss": 1.0327,
      "step": 440
    },
    {
      "epoch": 0.14980026631158455,
      "grad_norm": 7.84375,
      "learning_rate": 1.7003994673768308e-05,
      "loss": 1.1155,
      "step": 450
    },
    {
      "epoch": 0.15312916111850866,
      "grad_norm": 14.125,
      "learning_rate": 1.693741677762983e-05,
      "loss": 0.9627,
      "step": 460
    },
    {
      "epoch": 0.15645805592543274,
      "grad_norm": 7.4375,
      "learning_rate": 1.6870838881491347e-05,
      "loss": 1.0216,
      "step": 470
    },
    {
      "epoch": 0.15978695073235685,
      "grad_norm": 9.375,
      "learning_rate": 1.6804260985352863e-05,
      "loss": 1.0489,
      "step": 480
    },
    {
      "epoch": 0.16311584553928096,
      "grad_norm": 19.5,
      "learning_rate": 1.6737683089214383e-05,
      "loss": 1.1254,
      "step": 490
    },
    {
      "epoch": 0.16644474034620507,
      "grad_norm": 26.125,
      "learning_rate": 1.66711051930759e-05,
      "loss": 1.0134,
      "step": 500
    },
    {
      "epoch": 0.16644474034620507,
      "eval_accuracy": 0.5015762402521985,
      "eval_loss": 0.9942083358764648,
      "eval_runtime": 211.8123,
      "eval_samples_per_second": 113.818,
      "eval_steps_per_second": 28.454,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 3004,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}