{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.054945054945054944,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005494505494505495,
      "grad_norm": 0.027151547372341156,
      "learning_rate": 1e-05,
      "loss": 11.9328,
      "step": 1
    },
    {
      "epoch": 0.005494505494505495,
      "eval_loss": 11.931960105895996,
      "eval_runtime": 18.0294,
      "eval_samples_per_second": 34.055,
      "eval_steps_per_second": 17.028,
      "step": 1
    },
    {
      "epoch": 0.01098901098901099,
      "grad_norm": 0.027643978595733643,
      "learning_rate": 2e-05,
      "loss": 11.9319,
      "step": 2
    },
    {
      "epoch": 0.016483516483516484,
      "grad_norm": 0.028413433581590652,
      "learning_rate": 3e-05,
      "loss": 11.9315,
      "step": 3
    },
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 0.03067416325211525,
      "learning_rate": 4e-05,
      "loss": 11.9323,
      "step": 4
    },
    {
      "epoch": 0.027472527472527472,
      "grad_norm": 0.02727838046848774,
      "learning_rate": 5e-05,
      "loss": 11.932,
      "step": 5
    },
    {
      "epoch": 0.027472527472527472,
      "eval_loss": 11.931900024414062,
      "eval_runtime": 18.2244,
      "eval_samples_per_second": 33.691,
      "eval_steps_per_second": 16.846,
      "step": 5
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.02454882673919201,
      "learning_rate": 6e-05,
      "loss": 11.932,
      "step": 6
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 0.02835436351597309,
      "learning_rate": 7e-05,
      "loss": 11.9315,
      "step": 7
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 0.026226777583360672,
      "learning_rate": 8e-05,
      "loss": 11.9322,
      "step": 8
    },
    {
      "epoch": 0.04945054945054945,
      "grad_norm": 0.027679918333888054,
      "learning_rate": 9e-05,
      "loss": 11.9327,
      "step": 9
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 0.025617027655243874,
      "learning_rate": 0.0001,
      "loss": 11.9329,
      "step": 10
    },
    {
      "epoch": 0.054945054945054944,
      "eval_loss": 11.931732177734375,
      "eval_runtime": 18.2319,
      "eval_samples_per_second": 33.677,
      "eval_steps_per_second": 16.839,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 119915151360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}