{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0653061224489796,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032653061224489797,
      "grad_norm": 0.3841452896595001,
      "learning_rate": 1e-05,
      "loss": 10.8294,
      "step": 1
    },
    {
      "epoch": 0.0032653061224489797,
      "eval_loss": 10.841578483581543,
      "eval_runtime": 8.2506,
      "eval_samples_per_second": 62.541,
      "eval_steps_per_second": 31.271,
      "step": 1
    },
    {
      "epoch": 0.006530612244897959,
      "grad_norm": 0.3547123670578003,
      "learning_rate": 2e-05,
      "loss": 10.8332,
      "step": 2
    },
    {
      "epoch": 0.009795918367346938,
      "grad_norm": 0.37293732166290283,
      "learning_rate": 3e-05,
      "loss": 10.8352,
      "step": 3
    },
    {
      "epoch": 0.013061224489795919,
      "grad_norm": 0.35608258843421936,
      "learning_rate": 4e-05,
      "loss": 10.8397,
      "step": 4
    },
    {
      "epoch": 0.0163265306122449,
      "grad_norm": 0.3527994751930237,
      "learning_rate": 5e-05,
      "loss": 10.8465,
      "step": 5
    },
    {
      "epoch": 0.0163265306122449,
      "eval_loss": 10.840397834777832,
      "eval_runtime": 0.7152,
      "eval_samples_per_second": 721.472,
      "eval_steps_per_second": 360.736,
      "step": 5
    },
    {
      "epoch": 0.019591836734693877,
      "grad_norm": 0.33146461844444275,
      "learning_rate": 6e-05,
      "loss": 10.8378,
      "step": 6
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.3458758294582367,
      "learning_rate": 7e-05,
      "loss": 10.8361,
      "step": 7
    },
    {
      "epoch": 0.026122448979591838,
      "grad_norm": 0.3253280520439148,
      "learning_rate": 8e-05,
      "loss": 10.8374,
      "step": 8
    },
    {
      "epoch": 0.029387755102040815,
      "grad_norm": 0.3079422116279602,
      "learning_rate": 9e-05,
      "loss": 10.8323,
      "step": 9
    },
    {
      "epoch": 0.0326530612244898,
      "grad_norm": 0.308852881193161,
      "learning_rate": 0.0001,
      "loss": 10.8422,
      "step": 10
    },
    {
      "epoch": 0.0326530612244898,
      "eval_loss": 10.835927963256836,
      "eval_runtime": 0.7246,
      "eval_samples_per_second": 712.072,
      "eval_steps_per_second": 356.036,
      "step": 10
    },
    {
      "epoch": 0.035918367346938776,
      "grad_norm": 0.30548781156539917,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.8319,
      "step": 11
    },
    {
      "epoch": 0.03918367346938775,
      "grad_norm": 0.363088458776474,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.8294,
      "step": 12
    },
    {
      "epoch": 0.04244897959183674,
      "grad_norm": 0.324341744184494,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.8268,
      "step": 13
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.35678061842918396,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.8294,
      "step": 14
    },
    {
      "epoch": 0.04897959183673469,
      "grad_norm": 0.3367568552494049,
      "learning_rate": 5e-05,
      "loss": 10.8316,
      "step": 15
    },
    {
      "epoch": 0.04897959183673469,
      "eval_loss": 10.830291748046875,
      "eval_runtime": 0.7722,
      "eval_samples_per_second": 668.196,
      "eval_steps_per_second": 334.098,
      "step": 15
    },
    {
      "epoch": 0.052244897959183675,
      "grad_norm": 0.3325510323047638,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.8348,
      "step": 16
    },
    {
      "epoch": 0.05551020408163265,
      "grad_norm": 0.32736244797706604,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.8271,
      "step": 17
    },
    {
      "epoch": 0.05877551020408163,
      "grad_norm": 0.33501970767974854,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.828,
      "step": 18
    },
    {
      "epoch": 0.062040816326530614,
      "grad_norm": 0.38715001940727234,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.8287,
      "step": 19
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": 0.3634048402309418,
      "learning_rate": 0.0,
      "loss": 10.8176,
      "step": 20
    },
    {
      "epoch": 0.0653061224489796,
      "eval_loss": 10.828740119934082,
      "eval_runtime": 0.7528,
      "eval_samples_per_second": 685.416,
      "eval_steps_per_second": 342.708,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6562366095360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}