{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014930944382232176,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014930944382232176,
      "grad_norm": 0.34936052560806274,
      "learning_rate": 2e-05,
      "loss": 2.6233,
      "step": 1
    },
    {
      "epoch": 0.0014930944382232176,
      "eval_loss": 2.763261556625366,
      "eval_runtime": 4.2184,
      "eval_samples_per_second": 67.087,
      "eval_steps_per_second": 33.662,
      "step": 1
    },
    {
      "epoch": 0.0029861888764464353,
      "grad_norm": 0.4245949983596802,
      "learning_rate": 4e-05,
      "loss": 2.7503,
      "step": 2
    },
    {
      "epoch": 0.004479283314669653,
      "grad_norm": 0.40954822301864624,
      "learning_rate": 6e-05,
      "loss": 2.9542,
      "step": 3
    },
    {
      "epoch": 0.004479283314669653,
      "eval_loss": 2.7623863220214844,
      "eval_runtime": 2.8189,
      "eval_samples_per_second": 100.393,
      "eval_steps_per_second": 50.374,
      "step": 3
    },
    {
      "epoch": 0.0059723777528928705,
      "grad_norm": 0.5216032862663269,
      "learning_rate": 8e-05,
      "loss": 2.6807,
      "step": 4
    },
    {
      "epoch": 0.007465472191116088,
      "grad_norm": 0.31182873249053955,
      "learning_rate": 0.0001,
      "loss": 2.1168,
      "step": 5
    },
    {
      "epoch": 0.008958566629339306,
      "grad_norm": 1.1391494274139404,
      "learning_rate": 0.00012,
      "loss": 2.7538,
      "step": 6
    },
    {
      "epoch": 0.008958566629339306,
      "eval_loss": 2.7487189769744873,
      "eval_runtime": 2.8564,
      "eval_samples_per_second": 99.076,
      "eval_steps_per_second": 49.713,
      "step": 6
    },
    {
      "epoch": 0.010451661067562523,
      "grad_norm": 0.3502615690231323,
      "learning_rate": 0.00014,
      "loss": 2.5568,
      "step": 7
    },
    {
      "epoch": 0.011944755505785741,
      "grad_norm": 0.33765602111816406,
      "learning_rate": 0.00016,
      "loss": 2.3741,
      "step": 8
    },
    {
      "epoch": 0.013437849944008958,
      "grad_norm": 0.4771394729614258,
      "learning_rate": 0.00018,
      "loss": 2.9972,
      "step": 9
    },
    {
      "epoch": 0.013437849944008958,
      "eval_loss": 2.698538064956665,
      "eval_runtime": 2.8476,
      "eval_samples_per_second": 99.383,
      "eval_steps_per_second": 49.867,
      "step": 9
    },
    {
      "epoch": 0.014930944382232176,
      "grad_norm": 0.39654871821403503,
      "learning_rate": 0.0002,
      "loss": 2.5791,
      "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": 55725557022720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}