{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 150.0,
  "eval_steps": 0,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.0,
      "grad_norm": 44.62799208257571,
      "learning_rate": 9.59731543624161e-06,
      "loss": -0.3495,
      "step": 7
    },
    {
      "epoch": 14.0,
      "grad_norm": 45.38451229743726,
      "learning_rate": 9.12751677852349e-06,
      "loss": -0.0928,
      "step": 14
    },
    {
      "epoch": 21.0,
      "grad_norm": 36.14958116968077,
      "learning_rate": 8.65771812080537e-06,
      "loss": -1.6782,
      "step": 21
    },
    {
      "epoch": 28.0,
      "grad_norm": 35.91531689147897,
      "learning_rate": 8.18791946308725e-06,
      "loss": -1.1517,
      "step": 28
    },
    {
      "epoch": 35.0,
      "grad_norm": 46.791032141929286,
      "learning_rate": 7.718120805369127e-06,
      "loss": -1.9168,
      "step": 35
    },
    {
      "epoch": 42.0,
      "grad_norm": 54.497558599576124,
      "learning_rate": 7.248322147651007e-06,
      "loss": -3.1832,
      "step": 42
    },
    {
      "epoch": 49.0,
      "grad_norm": 57.7829652782273,
      "learning_rate": 6.778523489932887e-06,
      "loss": -4.4813,
      "step": 49
    },
    {
      "epoch": 56.0,
      "grad_norm": 61.09021382550308,
      "learning_rate": 6.308724832214766e-06,
      "loss": -4.8777,
      "step": 56
    },
    {
      "epoch": 63.0,
      "grad_norm": 73.5607357950864,
      "learning_rate": 5.8389261744966455e-06,
      "loss": -6.7882,
      "step": 63
    },
    {
      "epoch": 70.0,
      "grad_norm": 78.1597733595279,
      "learning_rate": 5.369127516778524e-06,
      "loss": -7.1621,
      "step": 70
    },
    {
      "epoch": 77.0,
      "grad_norm": 69.22849020221813,
      "learning_rate": 4.899328859060403e-06,
      "loss": -8.3795,
      "step": 77
    },
    {
      "epoch": 84.0,
      "grad_norm": 66.74212967058439,
      "learning_rate": 4.429530201342283e-06,
      "loss": -9.7835,
      "step": 84
    },
    {
      "epoch": 91.0,
      "grad_norm": 70.11291619161642,
      "learning_rate": 3.959731543624161e-06,
      "loss": -10.1054,
      "step": 91
    },
    {
      "epoch": 98.0,
      "grad_norm": 66.15435699917873,
      "learning_rate": 3.4899328859060407e-06,
      "loss": -11.0959,
      "step": 98
    },
    {
      "epoch": 105.0,
      "grad_norm": 68.63148603314248,
      "learning_rate": 3.02013422818792e-06,
      "loss": -12.5123,
      "step": 105
    },
    {
      "epoch": 112.0,
      "grad_norm": 67.53577541417867,
      "learning_rate": 2.5503355704697992e-06,
      "loss": -13.1337,
      "step": 112
    },
    {
      "epoch": 119.0,
      "grad_norm": 68.22259728362829,
      "learning_rate": 2.080536912751678e-06,
      "loss": -13.5507,
      "step": 119
    },
    {
      "epoch": 126.0,
      "grad_norm": 72.50037490624946,
      "learning_rate": 1.6107382550335572e-06,
      "loss": -13.7385,
      "step": 126
    },
    {
      "epoch": 133.0,
      "grad_norm": 87.09374616251951,
      "learning_rate": 1.1409395973154363e-06,
      "loss": -14.2547,
      "step": 133
    },
    {
      "epoch": 140.0,
      "grad_norm": 72.08324977993553,
      "learning_rate": 6.711409395973155e-07,
      "loss": -14.5871,
      "step": 140
    },
    {
      "epoch": 147.0,
      "grad_norm": 70.79599339905133,
      "learning_rate": 2.0134228187919465e-07,
      "loss": -15.0233,
      "step": 147
    }
  ],
  "logging_steps": 7,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}