{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02577873254564984,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.486392855644226,
      "eval_runtime": 113.3983,
      "eval_samples_per_second": 4.321,
      "eval_steps_per_second": 2.161,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 3.225036144256592,
      "learning_rate": 3e-05,
      "loss": 6.2813,
      "step": 3
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 3.4695043563842773,
      "learning_rate": 6e-05,
      "loss": 5.7449,
      "step": 6
    },
    {
      "epoch": 0.006874328678839957,
      "eval_loss": 1.2069323062896729,
      "eval_runtime": 114.5394,
      "eval_samples_per_second": 4.278,
      "eval_steps_per_second": 2.139,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 3.102142572402954,
      "learning_rate": 9e-05,
      "loss": 4.9951,
      "step": 9
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 3.2422165870666504,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.3387,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 3.162358045578003,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.3603,
      "step": 15
    },
    {
      "epoch": 0.013748657357679914,
      "eval_loss": 0.9922497868537903,
      "eval_runtime": 114.5697,
      "eval_samples_per_second": 4.277,
      "eval_steps_per_second": 2.138,
      "step": 16
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 1.94317626953125,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.7622,
      "step": 18
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 1.8822708129882812,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 3.6641,
      "step": 21
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 2.2596004009246826,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.664,
      "step": 24
    },
    {
      "epoch": 0.02062298603651987,
      "eval_loss": 0.9132661819458008,
      "eval_runtime": 114.593,
      "eval_samples_per_second": 4.276,
      "eval_steps_per_second": 2.138,
      "step": 24
    },
    {
      "epoch": 0.023200859291084855,
      "grad_norm": 2.5175583362579346,
      "learning_rate": 5.449673790581611e-06,
      "loss": 3.6665,
      "step": 27
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 1.8177056312561035,
      "learning_rate": 0.0,
      "loss": 3.5424,
      "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": 1.4733381298176e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}