{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.887640449438202,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.898876404494382,
      "grad_norm": 4.312319755554199,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.8614,
      "step": 10
    },
    {
      "epoch": 1.797752808988764,
      "grad_norm": 1.8239428997039795,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.9497,
      "step": 20
    },
    {
      "epoch": 2.696629213483146,
      "grad_norm": 2.482679843902588,
      "learning_rate": 9.118382907149165e-05,
      "loss": 0.6147,
      "step": 30
    },
    {
      "epoch": 3.595505617977528,
      "grad_norm": 1.4796712398529053,
      "learning_rate": 8.028048435688333e-05,
      "loss": 0.4921,
      "step": 40
    },
    {
      "epoch": 4.49438202247191,
      "grad_norm": 1.1127064228057861,
      "learning_rate": 6.635339816587109e-05,
      "loss": 0.3398,
      "step": 50
    },
    {
      "epoch": 5.393258426966292,
      "grad_norm": 1.4359052181243896,
      "learning_rate": 5.0793298191740404e-05,
      "loss": 0.2866,
      "step": 60
    },
    {
      "epoch": 6.292134831460674,
      "grad_norm": 1.3968243598937988,
      "learning_rate": 3.515398123358627e-05,
      "loss": 0.2223,
      "step": 70
    },
    {
      "epoch": 7.191011235955056,
      "grad_norm": 1.2981433868408203,
      "learning_rate": 2.09971545214401e-05,
      "loss": 0.1728,
      "step": 80
    },
    {
      "epoch": 8.089887640449438,
      "grad_norm": 0.8524450063705444,
      "learning_rate": 9.73648712344707e-06,
      "loss": 0.1539,
      "step": 90
    },
    {
      "epoch": 8.98876404494382,
      "grad_norm": 1.1347664594650269,
      "learning_rate": 2.496444112952734e-06,
      "loss": 0.1284,
      "step": 100
    },
    {
      "epoch": 9.887640449438202,
      "grad_norm": 0.8518253564834595,
      "learning_rate": 0.0,
      "loss": 0.1219,
      "step": 110
    },
    {
      "epoch": 9.887640449438202,
      "step": 110,
      "total_flos": 580815710552064.0,
      "train_loss": 0.4857807181098244,
      "train_runtime": 12.3878,
      "train_samples_per_second": 71.845,
      "train_steps_per_second": 8.88
    }
  ],
  "logging_steps": 10,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 580815710552064.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}