{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 30,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.36675021052360535,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3008,
      "step": 10
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.045268554240465164,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0061,
      "step": 20
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.006114976014941931,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0042,
      "step": 30
    },
    {
      "epoch": 0.13333333333333333,
      "eval_loss": 0.004080221988260746,
      "eval_runtime": 96.8324,
      "eval_samples_per_second": 10.327,
      "eval_steps_per_second": 0.258,
      "step": 30
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.0014940646942704916,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0039,
      "step": 40
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.0011621147859841585,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0039,
      "step": 50
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.005421994719654322,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0039,
      "step": 60
    },
    {
      "epoch": 0.26666666666666666,
      "eval_loss": 0.003909846767783165,
      "eval_runtime": 96.8186,
      "eval_samples_per_second": 10.329,
      "eval_steps_per_second": 0.258,
      "step": 60
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.002968616783618927,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0039,
      "step": 70
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.016864212229847908,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0039,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.004826202057301998,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0039,
      "step": 90
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.0038871022406965494,
      "eval_runtime": 96.843,
      "eval_samples_per_second": 10.326,
      "eval_steps_per_second": 0.258,
      "step": 90
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.003356265602633357,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0039,
      "step": 100
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.0016542698722332716,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0039,
      "step": 110
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.007389770820736885,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0039,
      "step": 120
    },
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 0.0038501631934195757,
      "eval_runtime": 96.845,
      "eval_samples_per_second": 10.326,
      "eval_steps_per_second": 0.258,
      "step": 120
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.009115256369113922,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0038,
      "step": 130
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.006779392249882221,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0037,
      "step": 140
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.022685615345835686,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0033,
      "step": 150
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.0030691924039274454,
      "eval_runtime": 96.8893,
      "eval_samples_per_second": 10.321,
      "eval_steps_per_second": 0.258,
      "step": 150
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.04725850373506546,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0031,
      "step": 160
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.02934485487639904,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0031,
      "step": 170
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.020546529442071915,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0029,
      "step": 180
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.0029199642594903708,
      "eval_runtime": 96.8327,
      "eval_samples_per_second": 10.327,
      "eval_steps_per_second": 0.258,
      "step": 180
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.01967918500304222,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0029,
      "step": 190
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.013359949924051762,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0028,
      "step": 200
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.03619702160358429,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0028,
      "step": 210
    },
    {
      "epoch": 0.9333333333333333,
      "eval_loss": 0.002507995581254363,
      "eval_runtime": 96.8365,
      "eval_samples_per_second": 10.327,
      "eval_steps_per_second": 0.258,
      "step": 210
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.015583088621497154,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0026,
      "step": 220
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 0.02111578918993473,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0028,
      "step": 230
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.014296974055469036,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0025,
      "step": 240
    },
    {
      "epoch": 1.0666666666666667,
      "eval_loss": 0.0024458724074065685,
      "eval_runtime": 96.9524,
      "eval_samples_per_second": 10.314,
      "eval_steps_per_second": 0.258,
      "step": 240
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.036929819732904434,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0025,
      "step": 250
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 0.01881023496389389,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0026,
      "step": 260
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.02219155989587307,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0024,
      "step": 270
    },
    {
      "epoch": 1.2,
      "eval_loss": 0.002419873373582959,
      "eval_runtime": 96.9311,
      "eval_samples_per_second": 10.317,
      "eval_steps_per_second": 0.258,
      "step": 270
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 0.015554447658360004,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0026,
      "step": 280
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 0.014902675524353981,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0026,
      "step": 290
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.023787055164575577,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0027,
      "step": 300
    },
    {
      "epoch": 1.3333333333333333,
      "eval_loss": 0.0023624880705028772,
      "eval_runtime": 96.9344,
      "eval_samples_per_second": 10.316,
      "eval_steps_per_second": 0.258,
      "step": 300
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 0.024232730269432068,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0024,
      "step": 310
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.030378742143511772,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0025,
      "step": 320
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 0.022359298542141914,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0025,
      "step": 330
    },
    {
      "epoch": 1.4666666666666668,
      "eval_loss": 0.0022804364562034607,
      "eval_runtime": 96.9112,
      "eval_samples_per_second": 10.319,
      "eval_steps_per_second": 0.258,
      "step": 330
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 0.01789114437997341,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0024,
      "step": 340
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.019261475652456284,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0027,
      "step": 350
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.021873965859413147,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0023,
      "step": 360
    },
    {
      "epoch": 1.6,
      "eval_loss": 0.002201332012191415,
      "eval_runtime": 96.9199,
      "eval_samples_per_second": 10.318,
      "eval_steps_per_second": 0.258,
      "step": 360
    },
    {
      "epoch": 1.6444444444444444,
      "grad_norm": 0.0286718662828207,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0025,
      "step": 370
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 0.019971389323472977,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0022,
      "step": 380
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 0.02623485028743744,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0023,
      "step": 390
    },
    {
      "epoch": 1.7333333333333334,
      "eval_loss": 0.002075706608593464,
      "eval_runtime": 96.9432,
      "eval_samples_per_second": 10.315,
      "eval_steps_per_second": 0.258,
      "step": 390
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.021184084936976433,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.002,
      "step": 400
    },
    {
      "epoch": 1.8222222222222222,
      "grad_norm": 0.02332981303334236,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.002,
      "step": 410
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.023150313645601273,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.002,
      "step": 420
    },
    {
      "epoch": 1.8666666666666667,
      "eval_loss": 0.0020291407126933336,
      "eval_runtime": 96.9072,
      "eval_samples_per_second": 10.319,
      "eval_steps_per_second": 0.258,
      "step": 420
    },
    {
      "epoch": 1.911111111111111,
      "grad_norm": 0.03483868017792702,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.002,
      "step": 430
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 0.03138676658272743,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0025,
      "step": 440
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.028902092948555946,
      "learning_rate": 0.0,
      "loss": 0.0022,
      "step": 450
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0020088243763893843,
      "eval_runtime": 96.9299,
      "eval_samples_per_second": 10.317,
      "eval_steps_per_second": 0.258,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.4721820638419354e+18,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}