{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10771992818671454,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003590664272890485,
      "eval_loss": 3.2816081047058105,
      "eval_runtime": 13.9787,
      "eval_samples_per_second": 8.441,
      "eval_steps_per_second": 4.221,
      "step": 1
    },
    {
      "epoch": 0.010771992818671455,
      "grad_norm": 2.7559964656829834,
      "learning_rate": 3e-05,
      "loss": 3.2042,
      "step": 3
    },
    {
      "epoch": 0.02154398563734291,
      "grad_norm": 2.7881381511688232,
      "learning_rate": 6e-05,
      "loss": 3.2223,
      "step": 6
    },
    {
      "epoch": 0.02872531418312388,
      "eval_loss": 2.627229690551758,
      "eval_runtime": 14.2319,
      "eval_samples_per_second": 8.291,
      "eval_steps_per_second": 4.146,
      "step": 8
    },
    {
      "epoch": 0.03231597845601436,
      "grad_norm": 2.183891773223877,
      "learning_rate": 9e-05,
      "loss": 2.8394,
      "step": 9
    },
    {
      "epoch": 0.04308797127468582,
      "grad_norm": 1.9224225282669067,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1593,
      "step": 12
    },
    {
      "epoch": 0.05385996409335727,
      "grad_norm": 1.8815566301345825,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.604,
      "step": 15
    },
    {
      "epoch": 0.05745062836624776,
      "eval_loss": 1.2865763902664185,
      "eval_runtime": 14.3,
      "eval_samples_per_second": 8.252,
      "eval_steps_per_second": 4.126,
      "step": 16
    },
    {
      "epoch": 0.06463195691202872,
      "grad_norm": 2.7661185264587402,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.298,
      "step": 18
    },
    {
      "epoch": 0.07540394973070018,
      "grad_norm": 0.8492176532745361,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.1753,
      "step": 21
    },
    {
      "epoch": 0.08617594254937164,
      "grad_norm": 0.9100056886672974,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0815,
      "step": 24
    },
    {
      "epoch": 0.08617594254937164,
      "eval_loss": 1.0884000062942505,
      "eval_runtime": 14.3103,
      "eval_samples_per_second": 8.246,
      "eval_steps_per_second": 4.123,
      "step": 24
    },
    {
      "epoch": 0.09694793536804308,
      "grad_norm": 0.8214713335037231,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.2248,
      "step": 27
    },
    {
      "epoch": 0.10771992818671454,
      "grad_norm": 0.8163346648216248,
      "learning_rate": 0.0,
      "loss": 1.0553,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9916411753267200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}