{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002334648518665515,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.6692970373310296e-05,
      "grad_norm": 5.009546756744385,
      "learning_rate": 1e-05,
      "loss": 3.8985,
      "step": 1
    },
    {
      "epoch": 4.6692970373310296e-05,
      "eval_loss": 4.363813877105713,
      "eval_runtime": 1880.8197,
      "eval_samples_per_second": 19.178,
      "eval_steps_per_second": 9.589,
      "step": 1
    },
    {
      "epoch": 9.338594074662059e-05,
      "grad_norm": 7.755334377288818,
      "learning_rate": 2e-05,
      "loss": 4.1898,
      "step": 2
    },
    {
      "epoch": 9.338594074662059e-05,
      "eval_loss": 4.333957195281982,
      "eval_runtime": 1775.0325,
      "eval_samples_per_second": 20.321,
      "eval_steps_per_second": 10.16,
      "step": 2
    },
    {
      "epoch": 0.00014007891111993088,
      "grad_norm": 4.034150123596191,
      "learning_rate": 3e-05,
      "loss": 2.5546,
      "step": 3
    },
    {
      "epoch": 0.00018677188149324118,
      "grad_norm": 25.46023178100586,
      "learning_rate": 4e-05,
      "loss": 4.319,
      "step": 4
    },
    {
      "epoch": 0.00018677188149324118,
      "eval_loss": 4.181405544281006,
      "eval_runtime": 1736.4793,
      "eval_samples_per_second": 20.772,
      "eval_steps_per_second": 10.386,
      "step": 4
    },
    {
      "epoch": 0.0002334648518665515,
      "grad_norm": 5.914666175842285,
      "learning_rate": 5e-05,
      "loss": 4.325,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6362420213710848.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}