{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00437636761487965,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000437636761487965,
      "grad_norm": 2.7574801445007324,
      "learning_rate": 2e-05,
      "loss": 3.009,
      "step": 1
    },
    {
      "epoch": 0.000437636761487965,
      "eval_loss": 2.769320249557495,
      "eval_runtime": 46.6417,
      "eval_samples_per_second": 20.647,
      "eval_steps_per_second": 10.334,
      "step": 1
    },
    {
      "epoch": 0.00087527352297593,
      "grad_norm": 2.5721023082733154,
      "learning_rate": 4e-05,
      "loss": 2.9455,
      "step": 2
    },
    {
      "epoch": 0.001312910284463895,
      "grad_norm": 3.002300262451172,
      "learning_rate": 6e-05,
      "loss": 2.9186,
      "step": 3
    },
    {
      "epoch": 0.001312910284463895,
      "eval_loss": 2.7396295070648193,
      "eval_runtime": 46.8105,
      "eval_samples_per_second": 20.572,
      "eval_steps_per_second": 10.297,
      "step": 3
    },
    {
      "epoch": 0.00175054704595186,
      "grad_norm": 2.330648899078369,
      "learning_rate": 8e-05,
      "loss": 2.5161,
      "step": 4
    },
    {
      "epoch": 0.002188183807439825,
      "grad_norm": 2.688687801361084,
      "learning_rate": 0.0001,
      "loss": 2.7124,
      "step": 5
    },
    {
      "epoch": 0.00262582056892779,
      "grad_norm": 2.513381242752075,
      "learning_rate": 0.00012,
      "loss": 2.587,
      "step": 6
    },
    {
      "epoch": 0.00262582056892779,
      "eval_loss": 2.4182262420654297,
      "eval_runtime": 47.1528,
      "eval_samples_per_second": 20.423,
      "eval_steps_per_second": 10.222,
      "step": 6
    },
    {
      "epoch": 0.003063457330415755,
      "grad_norm": 2.5890634059906006,
      "learning_rate": 0.00014,
      "loss": 2.521,
      "step": 7
    },
    {
      "epoch": 0.00350109409190372,
      "grad_norm": 2.27801513671875,
      "learning_rate": 0.00016,
      "loss": 2.2094,
      "step": 8
    },
    {
      "epoch": 0.003938730853391685,
      "grad_norm": 2.2783007621765137,
      "learning_rate": 0.00018,
      "loss": 2.1087,
      "step": 9
    },
    {
      "epoch": 0.003938730853391685,
      "eval_loss": 2.0514070987701416,
      "eval_runtime": 46.4462,
      "eval_samples_per_second": 20.734,
      "eval_steps_per_second": 10.378,
      "step": 9
    },
    {
      "epoch": 0.00437636761487965,
      "grad_norm": 2.583179473876953,
      "learning_rate": 0.0002,
      "loss": 1.94,
      "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": 500097330708480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}