{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06730607437321218,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016826518593303045,
      "grad_norm": 3.75418950341011,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.9983,
      "step": 10
    },
    {
      "epoch": 0.003365303718660609,
      "grad_norm": 4.027030925274863,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.9697,
      "step": 20
    },
    {
      "epoch": 0.005047955577990914,
      "grad_norm": 4.048987349136423,
      "learning_rate": 1.5e-05,
      "loss": 0.9412,
      "step": 30
    },
    {
      "epoch": 0.006730607437321218,
      "grad_norm": 5.720158971431411,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.8783,
      "step": 40
    },
    {
      "epoch": 0.008413259296651522,
      "grad_norm": 4.718965032869529,
      "learning_rate": 2.5e-05,
      "loss": 0.8454,
      "step": 50
    },
    {
      "epoch": 0.010095911155981827,
      "grad_norm": 3.5785181087788835,
      "learning_rate": 3e-05,
      "loss": 0.809,
      "step": 60
    },
    {
      "epoch": 0.011778563015312132,
      "grad_norm": 4.11981684712826,
      "learning_rate": 2.9999786123888308e-05,
      "loss": 0.7556,
      "step": 70
    },
    {
      "epoch": 0.013461214874642436,
      "grad_norm": 6.082559649594005,
      "learning_rate": 2.9999144501652298e-05,
      "loss": 0.7613,
      "step": 80
    },
    {
      "epoch": 0.01514386673397274,
      "grad_norm": 1.957553999291205,
      "learning_rate": 2.9998075151588992e-05,
      "loss": 0.7784,
      "step": 90
    },
    {
      "epoch": 0.016826518593303044,
      "grad_norm": 1.6706087540201593,
      "learning_rate": 2.999657810419285e-05,
      "loss": 0.7658,
      "step": 100
    },
    {
      "epoch": 0.01850917045263335,
      "grad_norm": 2.909734954037323,
      "learning_rate": 2.999465340215489e-05,
      "loss": 0.7331,
      "step": 110
    },
    {
      "epoch": 0.020191822311963654,
      "grad_norm": 1.977272298268717,
      "learning_rate": 2.999230110036149e-05,
      "loss": 0.7507,
      "step": 120
    },
    {
      "epoch": 0.02187447417129396,
      "grad_norm": 1.8089524113272115,
      "learning_rate": 2.99895212658928e-05,
      "loss": 0.7309,
      "step": 130
    },
    {
      "epoch": 0.023557126030624265,
      "grad_norm": 2.134962179309057,
      "learning_rate": 2.9986313978020846e-05,
      "loss": 0.721,
      "step": 140
    },
    {
      "epoch": 0.02523977788995457,
      "grad_norm": 11.10353091330302,
      "learning_rate": 2.9982679328207262e-05,
      "loss": 0.7338,
      "step": 150
    },
    {
      "epoch": 0.02692242974928487,
      "grad_norm": 1.4444344817739057,
      "learning_rate": 2.9978617420100692e-05,
      "loss": 0.7227,
      "step": 160
    },
    {
      "epoch": 0.028605081608615177,
      "grad_norm": 1.453288161439029,
      "learning_rate": 2.9974128369533805e-05,
      "loss": 0.7107,
      "step": 170
    },
    {
      "epoch": 0.03028773346794548,
      "grad_norm": 3.475164856876678,
      "learning_rate": 2.9969212304520034e-05,
      "loss": 0.7303,
      "step": 180
    },
    {
      "epoch": 0.03197038532727579,
      "grad_norm": 1.1636824531496957,
      "learning_rate": 2.9963869365249895e-05,
      "loss": 0.6688,
      "step": 190
    },
    {
      "epoch": 0.03365303718660609,
      "grad_norm": 1.8518695174363622,
      "learning_rate": 2.995809970408699e-05,
      "loss": 0.7003,
      "step": 200
    },
    {
      "epoch": 0.0353356890459364,
      "grad_norm": 4.09791760479377,
      "learning_rate": 2.9951903485563685e-05,
      "loss": 0.7442,
      "step": 210
    },
    {
      "epoch": 0.0370183409052667,
      "grad_norm": 2.4987929291159956,
      "learning_rate": 2.99452808863764e-05,
      "loss": 0.7517,
      "step": 220
    },
    {
      "epoch": 0.03870099276459701,
      "grad_norm": 3.4584802037194087,
      "learning_rate": 2.993823209538056e-05,
      "loss": 0.7537,
      "step": 230
    },
    {
      "epoch": 0.04038364462392731,
      "grad_norm": 2.511130636368107,
      "learning_rate": 2.9930757313585238e-05,
      "loss": 0.7599,
      "step": 240
    },
    {
      "epoch": 0.04206629648325761,
      "grad_norm": 1.7030446444812277,
      "learning_rate": 2.9922856754147406e-05,
      "loss": 0.7126,
      "step": 250
    },
    {
      "epoch": 0.04374894834258792,
      "grad_norm": 4.790377413030976,
      "learning_rate": 2.9914530642365852e-05,
      "loss": 0.72,
      "step": 260
    },
    {
      "epoch": 0.04543160020191822,
      "grad_norm": 2.0321244924961976,
      "learning_rate": 2.990577921567476e-05,
      "loss": 0.6733,
      "step": 270
    },
    {
      "epoch": 0.04711425206124853,
      "grad_norm": 2.310370624749643,
      "learning_rate": 2.989660272363696e-05,
      "loss": 0.7212,
      "step": 280
    },
    {
      "epoch": 0.04879690392057883,
      "grad_norm": 3.451763592410144,
      "learning_rate": 2.988700142793676e-05,
      "loss": 0.7237,
      "step": 290
    },
    {
      "epoch": 0.05047955577990914,
      "grad_norm": 5.317302731978485,
      "learning_rate": 2.9876975602372536e-05,
      "loss": 0.7558,
      "step": 300
    },
    {
      "epoch": 0.05216220763923944,
      "grad_norm": 2.3026448136142914,
      "learning_rate": 2.9866525532848906e-05,
      "loss": 0.6985,
      "step": 310
    },
    {
      "epoch": 0.05384485949856974,
      "grad_norm": 1.8320545447196381,
      "learning_rate": 2.9855651517368567e-05,
      "loss": 0.7227,
      "step": 320
    },
    {
      "epoch": 0.05552751135790005,
      "grad_norm": 1.9908218789466392,
      "learning_rate": 2.9844353866023802e-05,
      "loss": 0.7075,
      "step": 330
    },
    {
      "epoch": 0.05721016321723035,
      "grad_norm": 5.182840115712529,
      "learning_rate": 2.9832632900987642e-05,
      "loss": 0.7207,
      "step": 340
    },
    {
      "epoch": 0.05889281507656066,
      "grad_norm": 1.5483797249278837,
      "learning_rate": 2.982048895650468e-05,
      "loss": 0.7233,
      "step": 350
    },
    {
      "epoch": 0.06057546693589096,
      "grad_norm": 2.3382590504722693,
      "learning_rate": 2.9807922378881537e-05,
      "loss": 0.7002,
      "step": 360
    },
    {
      "epoch": 0.06225811879522127,
      "grad_norm": 3.1859655239636937,
      "learning_rate": 2.979493352647697e-05,
      "loss": 0.7201,
      "step": 370
    },
    {
      "epoch": 0.06394077065455157,
      "grad_norm": 0.9149159742557087,
      "learning_rate": 2.9781522769691686e-05,
      "loss": 0.7136,
      "step": 380
    },
    {
      "epoch": 0.06562342251388188,
      "grad_norm": 10.861566072795899,
      "learning_rate": 2.9767690490957758e-05,
      "loss": 0.7068,
      "step": 390
    },
    {
      "epoch": 0.06730607437321218,
      "grad_norm": 2.8618866775651006,
      "learning_rate": 2.9753437084727713e-05,
      "loss": 0.7239,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 5943,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.822380393496576e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}