{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9922480620155039,
  "eval_steps": 3,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06201550387596899,
      "grad_norm": 4.862276554107666,
      "learning_rate": 0.0,
      "loss": 95.3351,
      "step": 1
    },
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 4.652088642120361,
      "learning_rate": 0.0002,
      "loss": 95.3436,
      "step": 2
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 5.192637920379639,
      "learning_rate": 0.00019781476007338058,
      "loss": 93.3809,
      "step": 3
    },
    {
      "epoch": 0.18604651162790697,
      "eval_loss": 11.580174446105957,
      "eval_runtime": 0.2088,
      "eval_samples_per_second": 23.944,
      "eval_steps_per_second": 9.578,
      "step": 3
    },
    {
      "epoch": 0.24806201550387597,
      "grad_norm": 6.524551868438721,
      "learning_rate": 0.0001913545457642601,
      "loss": 91.6408,
      "step": 4
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 8.191283226013184,
      "learning_rate": 0.00018090169943749476,
      "loss": 90.1653,
      "step": 5
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 9.808971405029297,
      "learning_rate": 0.00016691306063588583,
      "loss": 88.4358,
      "step": 6
    },
    {
      "epoch": 0.37209302325581395,
      "eval_loss": 11.026472091674805,
      "eval_runtime": 0.1942,
      "eval_samples_per_second": 25.743,
      "eval_steps_per_second": 10.297,
      "step": 6
    },
    {
      "epoch": 0.43410852713178294,
      "grad_norm": 11.63279914855957,
      "learning_rate": 0.00015000000000000001,
      "loss": 86.722,
      "step": 7
    },
    {
      "epoch": 0.49612403100775193,
      "grad_norm": 12.591235160827637,
      "learning_rate": 0.00013090169943749476,
      "loss": 85.2279,
      "step": 8
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 12.81602668762207,
      "learning_rate": 0.00011045284632676536,
      "loss": 84.6683,
      "step": 9
    },
    {
      "epoch": 0.5581395348837209,
      "eval_loss": 10.659093856811523,
      "eval_runtime": 0.1895,
      "eval_samples_per_second": 26.38,
      "eval_steps_per_second": 10.552,
      "step": 9
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 13.371841430664062,
      "learning_rate": 8.954715367323468e-05,
      "loss": 83.69,
      "step": 10
    },
    {
      "epoch": 0.6821705426356589,
      "grad_norm": 13.044097900390625,
      "learning_rate": 6.909830056250527e-05,
      "loss": 83.3816,
      "step": 11
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 12.994512557983398,
      "learning_rate": 5.000000000000002e-05,
      "loss": 83.1422,
      "step": 12
    },
    {
      "epoch": 0.7441860465116279,
      "eval_loss": 10.501452445983887,
      "eval_runtime": 0.213,
      "eval_samples_per_second": 23.478,
      "eval_steps_per_second": 9.391,
      "step": 12
    },
    {
      "epoch": 0.8062015503875969,
      "grad_norm": 13.637518882751465,
      "learning_rate": 3.308693936411421e-05,
      "loss": 82.3943,
      "step": 13
    },
    {
      "epoch": 0.8682170542635659,
      "grad_norm": 12.913551330566406,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 82.7794,
      "step": 14
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 13.087961196899414,
      "learning_rate": 8.645454235739903e-06,
      "loss": 82.4536,
      "step": 15
    },
    {
      "epoch": 0.9302325581395349,
      "eval_loss": 10.455672264099121,
      "eval_runtime": 0.2263,
      "eval_samples_per_second": 22.094,
      "eval_steps_per_second": 8.838,
      "step": 15
    },
    {
      "epoch": 0.9922480620155039,
      "grad_norm": 13.101417541503906,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 82.3338,
      "step": 16
    },
    {
      "epoch": 0.9922480620155039,
      "step": 16,
      "total_flos": 384752733388800.0,
      "train_loss": 86.94341468811035,
      "train_runtime": 61.6055,
      "train_samples_per_second": 8.36,
      "train_steps_per_second": 0.26
    },
    {
      "epoch": 0.9922480620155039,
      "eval_loss": 10.453876495361328,
      "eval_runtime": 0.4463,
      "eval_samples_per_second": 11.203,
      "eval_steps_per_second": 4.481,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 384752733388800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}