{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06233766233766234,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002077922077922078,
      "eval_loss": 9.916604042053223,
      "eval_runtime": 1.6123,
      "eval_samples_per_second": 125.907,
      "eval_steps_per_second": 63.264,
      "step": 1
    },
    {
      "epoch": 0.006233766233766234,
      "grad_norm": 820.1131591796875,
      "learning_rate": 3e-05,
      "loss": 38.4924,
      "step": 3
    },
    {
      "epoch": 0.012467532467532468,
      "grad_norm": 877.5899658203125,
      "learning_rate": 6e-05,
      "loss": 41.2044,
      "step": 6
    },
    {
      "epoch": 0.016623376623376623,
      "eval_loss": 9.881518363952637,
      "eval_runtime": 0.8363,
      "eval_samples_per_second": 242.728,
      "eval_steps_per_second": 121.962,
      "step": 8
    },
    {
      "epoch": 0.0187012987012987,
      "grad_norm": 1054.716552734375,
      "learning_rate": 9e-05,
      "loss": 36.0326,
      "step": 9
    },
    {
      "epoch": 0.024935064935064935,
      "grad_norm": 926.1414794921875,
      "learning_rate": 9.755282581475769e-05,
      "loss": 41.1594,
      "step": 12
    },
    {
      "epoch": 0.03116883116883117,
      "grad_norm": 882.9425659179688,
      "learning_rate": 8.535533905932738e-05,
      "loss": 34.3414,
      "step": 15
    },
    {
      "epoch": 0.03324675324675325,
      "eval_loss": 9.777676582336426,
      "eval_runtime": 0.8406,
      "eval_samples_per_second": 241.503,
      "eval_steps_per_second": 121.346,
      "step": 16
    },
    {
      "epoch": 0.0374025974025974,
      "grad_norm": 1138.9920654296875,
      "learning_rate": 6.545084971874738e-05,
      "loss": 40.9554,
      "step": 18
    },
    {
      "epoch": 0.04363636363636364,
      "grad_norm": 842.28564453125,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 37.4363,
      "step": 21
    },
    {
      "epoch": 0.04987012987012987,
      "grad_norm": 929.0403442382812,
      "learning_rate": 2.061073738537635e-05,
      "loss": 36.2179,
      "step": 24
    },
    {
      "epoch": 0.04987012987012987,
      "eval_loss": 9.720993041992188,
      "eval_runtime": 0.8693,
      "eval_samples_per_second": 233.514,
      "eval_steps_per_second": 117.332,
      "step": 24
    },
    {
      "epoch": 0.05610389610389611,
      "grad_norm": 810.7876586914062,
      "learning_rate": 5.449673790581611e-06,
      "loss": 39.4528,
      "step": 27
    },
    {
      "epoch": 0.06233766233766234,
      "grad_norm": 852.4886474609375,
      "learning_rate": 0.0,
      "loss": 32.6003,
      "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": 67029675540480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}