{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00033444256785003593,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.688851357000719e-05,
      "grad_norm": 2.719273567199707,
      "learning_rate": 1e-05,
      "loss": 3.6233,
      "step": 1
    },
    {
      "epoch": 6.688851357000719e-05,
      "eval_loss": 3.8066489696502686,
      "eval_runtime": 990.8233,
      "eval_samples_per_second": 25.413,
      "eval_steps_per_second": 12.707,
      "step": 1
    },
    {
      "epoch": 0.00013377702714001437,
      "grad_norm": 2.9602596759796143,
      "learning_rate": 2e-05,
      "loss": 3.7798,
      "step": 2
    },
    {
      "epoch": 0.00013377702714001437,
      "eval_loss": 3.734171152114868,
      "eval_runtime": 1452.2383,
      "eval_samples_per_second": 17.339,
      "eval_steps_per_second": 8.669,
      "step": 2
    },
    {
      "epoch": 0.00020066554071002156,
      "grad_norm": 2.651723861694336,
      "learning_rate": 3e-05,
      "loss": 3.6619,
      "step": 3
    },
    {
      "epoch": 0.00026755405428002875,
      "grad_norm": 3.156409740447998,
      "learning_rate": 4e-05,
      "loss": 3.8843,
      "step": 4
    },
    {
      "epoch": 0.00026755405428002875,
      "eval_loss": 3.6434168815612793,
      "eval_runtime": 1331.5443,
      "eval_samples_per_second": 18.91,
      "eval_steps_per_second": 9.455,
      "step": 4
    },
    {
      "epoch": 0.00033444256785003593,
      "grad_norm": 2.9092843532562256,
      "learning_rate": 5e-05,
      "loss": 3.6246,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}