{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 310,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06477732793522267,
      "grad_norm": 11.852212905883789,
      "learning_rate": 5.625e-06,
      "loss": 0.4967,
      "step": 10
    },
    {
      "epoch": 0.12955465587044535,
      "grad_norm": 7.230913162231445,
      "learning_rate": 9.99743108100344e-06,
      "loss": 0.383,
      "step": 20
    },
    {
      "epoch": 0.19433198380566802,
      "grad_norm": 10.639442443847656,
      "learning_rate": 9.951834807474191e-06,
      "loss": 0.3309,
      "step": 30
    },
    {
      "epoch": 0.2591093117408907,
      "grad_norm": 5.517106533050537,
      "learning_rate": 9.849750306392085e-06,
      "loss": 0.342,
      "step": 40
    },
    {
      "epoch": 0.32388663967611336,
      "grad_norm": 7.627034664154053,
      "learning_rate": 9.692342110248802e-06,
      "loss": 0.2657,
      "step": 50
    },
    {
      "epoch": 0.38866396761133604,
      "grad_norm": 9.22568130493164,
      "learning_rate": 9.481405858508935e-06,
      "loss": 0.3223,
      "step": 60
    },
    {
      "epoch": 0.4534412955465587,
      "grad_norm": 5.751121997833252,
      "learning_rate": 9.219347813790416e-06,
      "loss": 0.2743,
      "step": 70
    },
    {
      "epoch": 0.5182186234817814,
      "grad_norm": 3.9381062984466553,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.2851,
      "step": 80
    },
    {
      "epoch": 0.582995951417004,
      "grad_norm": 6.950188636779785,
      "learning_rate": 8.554373161936176e-06,
      "loss": 0.2701,
      "step": 90
    },
    {
      "epoch": 0.6477732793522267,
      "grad_norm": 5.234208106994629,
      "learning_rate": 8.159042276237308e-06,
      "loss": 0.2502,
      "step": 100
    },
    {
      "epoch": 0.7125506072874493,
      "grad_norm": 4.1850104331970215,
      "learning_rate": 7.727674506052744e-06,
      "loss": 0.2626,
      "step": 110
    },
    {
      "epoch": 0.7773279352226721,
      "grad_norm": 5.396584510803223,
      "learning_rate": 7.265190694203086e-06,
      "loss": 0.2661,
      "step": 120
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 7.559943675994873,
      "learning_rate": 6.7768666408349445e-06,
      "loss": 0.2313,
      "step": 130
    },
    {
      "epoch": 0.9068825910931174,
      "grad_norm": 5.187716960906982,
      "learning_rate": 6.268272919547537e-06,
      "loss": 0.2383,
      "step": 140
    },
    {
      "epoch": 0.97165991902834,
      "grad_norm": 5.379395484924316,
      "learning_rate": 5.745211330880872e-06,
      "loss": 0.2315,
      "step": 150
    },
    {
      "epoch": 1.0323886639676114,
      "grad_norm": 4.931740760803223,
      "learning_rate": 5.213648718074584e-06,
      "loss": 0.2245,
      "step": 160
    },
    {
      "epoch": 1.097165991902834,
      "grad_norm": 4.69789981842041,
      "learning_rate": 4.679648900096436e-06,
      "loss": 0.1497,
      "step": 170
    },
    {
      "epoch": 1.1619433198380567,
      "grad_norm": 3.9414868354797363,
      "learning_rate": 4.149303498416838e-06,
      "loss": 0.189,
      "step": 180
    },
    {
      "epoch": 1.2267206477732793,
      "grad_norm": 5.506087779998779,
      "learning_rate": 3.6286624466253496e-06,
      "loss": 0.1771,
      "step": 190
    },
    {
      "epoch": 1.291497975708502,
      "grad_norm": 4.553317546844482,
      "learning_rate": 3.12366497560313e-06,
      "loss": 0.2094,
      "step": 200
    },
    {
      "epoch": 1.3562753036437247,
      "grad_norm": 6.188657760620117,
      "learning_rate": 2.6400718615403852e-06,
      "loss": 0.1753,
      "step": 210
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 4.113674163818359,
      "learning_rate": 2.1833997096818897e-06,
      "loss": 0.1369,
      "step": 220
    },
    {
      "epoch": 1.48582995951417,
      "grad_norm": 6.216587543487549,
      "learning_rate": 1.7588580234610592e-06,
      "loss": 0.169,
      "step": 230
    },
    {
      "epoch": 1.5506072874493926,
      "grad_norm": 5.111196041107178,
      "learning_rate": 1.3712897769085903e-06,
      "loss": 0.1607,
      "step": 240
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 5.277958393096924,
      "learning_rate": 1.0251161682580125e-06,
      "loss": 0.1159,
      "step": 250
    },
    {
      "epoch": 1.680161943319838,
      "grad_norm": 4.957247257232666,
      "learning_rate": 7.242861849732696e-07,
      "loss": 0.1523,
      "step": 260
    },
    {
      "epoch": 1.7449392712550607,
      "grad_norm": 8.240363121032715,
      "learning_rate": 4.722315555370793e-07,
      "loss": 0.1415,
      "step": 270
    },
    {
      "epoch": 1.8097165991902835,
      "grad_norm": 3.4664766788482666,
      "learning_rate": 2.71827601889067e-07,
      "loss": 0.1441,
      "step": 280
    },
    {
      "epoch": 1.874493927125506,
      "grad_norm": 3.520470380783081,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.1436,
      "step": 290
    },
    {
      "epoch": 1.9392712550607287,
      "grad_norm": 5.953762531280518,
      "learning_rate": 3.450089638922738e-08,
      "loss": 0.1504,
      "step": 300
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.5360658168792725,
      "learning_rate": 2.854571731947253e-10,
      "loss": 0.1196,
      "step": 310
    },
    {
      "epoch": 2.0,
      "step": 310,
      "total_flos": 1.0400414537089024e+16,
      "train_loss": 0.22610075896786105,
      "train_runtime": 630.2322,
      "train_samples_per_second": 3.919,
      "train_steps_per_second": 0.492
    }
  ],
  "logging_steps": 10,
  "max_steps": 310,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0400414537089024e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}