{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001903040106570246,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001903040106570246,
      "grad_norm": 0.06618665158748627,
      "learning_rate": 2e-05,
      "loss": 10.367,
      "step": 1
    },
    {
      "epoch": 0.0001903040106570246,
      "eval_loss": 10.37129020690918,
      "eval_runtime": 5.7719,
      "eval_samples_per_second": 383.409,
      "eval_steps_per_second": 191.791,
      "step": 1
    },
    {
      "epoch": 0.0003806080213140492,
      "grad_norm": 0.1022745743393898,
      "learning_rate": 4e-05,
      "loss": 10.3727,
      "step": 2
    },
    {
      "epoch": 0.0005709120319710738,
      "grad_norm": 0.07936174422502518,
      "learning_rate": 6e-05,
      "loss": 10.3726,
      "step": 3
    },
    {
      "epoch": 0.0005709120319710738,
      "eval_loss": 10.371238708496094,
      "eval_runtime": 5.7061,
      "eval_samples_per_second": 387.828,
      "eval_steps_per_second": 194.001,
      "step": 3
    },
    {
      "epoch": 0.0007612160426280984,
      "grad_norm": 0.10361578315496445,
      "learning_rate": 8e-05,
      "loss": 10.3667,
      "step": 4
    },
    {
      "epoch": 0.000951520053285123,
      "grad_norm": 0.10583080351352692,
      "learning_rate": 0.0001,
      "loss": 10.3749,
      "step": 5
    },
    {
      "epoch": 0.0011418240639421476,
      "grad_norm": 0.11412572115659714,
      "learning_rate": 0.00012,
      "loss": 10.3794,
      "step": 6
    },
    {
      "epoch": 0.0011418240639421476,
      "eval_loss": 10.370984077453613,
      "eval_runtime": 5.9055,
      "eval_samples_per_second": 374.738,
      "eval_steps_per_second": 187.454,
      "step": 6
    },
    {
      "epoch": 0.0013321280745991722,
      "grad_norm": 0.0876602753996849,
      "learning_rate": 0.00014,
      "loss": 10.3745,
      "step": 7
    },
    {
      "epoch": 0.0015224320852561968,
      "grad_norm": 0.08718382567167282,
      "learning_rate": 0.00016,
      "loss": 10.3748,
      "step": 8
    },
    {
      "epoch": 0.0017127360959132215,
      "grad_norm": 0.0812254250049591,
      "learning_rate": 0.00018,
      "loss": 10.3795,
      "step": 9
    },
    {
      "epoch": 0.0017127360959132215,
      "eval_loss": 10.370553970336914,
      "eval_runtime": 5.8097,
      "eval_samples_per_second": 380.912,
      "eval_steps_per_second": 190.542,
      "step": 9
    },
    {
      "epoch": 0.001903040106570246,
      "grad_norm": 0.1216459795832634,
      "learning_rate": 0.0002,
      "loss": 10.38,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 132541808640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}