{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000842522089876044,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001685044179752088,
      "grad_norm": 0.525423526763916,
      "learning_rate": 1e-05,
      "loss": 0.6299,
      "step": 1
    },
    {
      "epoch": 0.0001685044179752088,
      "eval_loss": 0.6569275259971619,
      "eval_runtime": 1917.2387,
      "eval_samples_per_second": 5.213,
      "eval_steps_per_second": 2.607,
      "step": 1
    },
    {
      "epoch": 0.0003370088359504176,
      "grad_norm": 0.48281005024909973,
      "learning_rate": 2e-05,
      "loss": 0.6693,
      "step": 2
    },
    {
      "epoch": 0.0003370088359504176,
      "eval_loss": 0.6328685879707336,
      "eval_runtime": 1719.2444,
      "eval_samples_per_second": 5.814,
      "eval_steps_per_second": 2.907,
      "step": 2
    },
    {
      "epoch": 0.0005055132539256264,
      "grad_norm": 0.43105509877204895,
      "learning_rate": 3e-05,
      "loss": 0.632,
      "step": 3
    },
    {
      "epoch": 0.0006740176719008352,
      "grad_norm": 0.45864245295524597,
      "learning_rate": 4e-05,
      "loss": 0.5996,
      "step": 4
    },
    {
      "epoch": 0.0006740176719008352,
      "eval_loss": 0.6061673164367676,
      "eval_runtime": 2870.8964,
      "eval_samples_per_second": 3.481,
      "eval_steps_per_second": 1.741,
      "step": 4
    },
    {
      "epoch": 0.000842522089876044,
      "grad_norm": 0.4749000370502472,
      "learning_rate": 5e-05,
      "loss": 0.6118,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6142792062468096.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}