{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 12.550558090209961,
      "eval_runtime": 1.6104,
      "eval_samples_per_second": 5.589,
      "eval_steps_per_second": 5.589,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_loss": 12.51858139038086,
      "eval_runtime": 1.63,
      "eval_samples_per_second": 5.521,
      "eval_steps_per_second": 5.521,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_loss": 12.355518341064453,
      "eval_runtime": 1.6218,
      "eval_samples_per_second": 5.549,
      "eval_steps_per_second": 5.549,
      "step": 9
    },
    {
      "epoch": 3.4050632911392404,
      "grad_norm": 10.352103233337402,
      "learning_rate": 1e-05,
      "loss": 14.4441,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_loss": 12.163219451904297,
      "eval_runtime": 1.6194,
      "eval_samples_per_second": 5.558,
      "eval_steps_per_second": 5.558,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_loss": 12.0006742477417,
      "eval_runtime": 1.6317,
      "eval_samples_per_second": 5.516,
      "eval_steps_per_second": 5.516,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_loss": 11.79024887084961,
      "eval_runtime": 1.6214,
      "eval_samples_per_second": 5.551,
      "eval_steps_per_second": 5.551,
      "step": 18
    },
    {
      "epoch": 6.810126582278481,
      "grad_norm": 15.923439025878906,
      "learning_rate": 5e-06,
      "loss": 13.8938,
      "step": 20
    },
    {
      "epoch": 7.0,
      "eval_loss": 11.653541564941406,
      "eval_runtime": 1.61,
      "eval_samples_per_second": 5.59,
      "eval_steps_per_second": 5.59,
      "step": 21
    },
    {
      "epoch": 8.0,
      "eval_loss": 11.551719665527344,
      "eval_runtime": 1.6269,
      "eval_samples_per_second": 5.532,
      "eval_steps_per_second": 5.532,
      "step": 24
    },
    {
      "epoch": 9.0,
      "eval_loss": 11.532543182373047,
      "eval_runtime": 1.5988,
      "eval_samples_per_second": 5.629,
      "eval_steps_per_second": 5.629,
      "step": 27
    },
    {
      "epoch": 10.0,
      "grad_norm": 18.979827880859375,
      "learning_rate": 0.0,
      "loss": 13.5263,
      "step": 30
    },
    {
      "epoch": 10.0,
      "eval_loss": 11.54777717590332,
      "eval_runtime": 1.6072,
      "eval_samples_per_second": 5.6,
      "eval_steps_per_second": 5.6,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.60454091472896e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}