{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017289820618111088,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034579641236222175,
      "grad_norm": 13.144903182983398,
      "learning_rate": 1e-05,
      "loss": 42.4796,
      "step": 1
    },
    {
      "epoch": 0.0034579641236222175,
      "eval_loss": NaN,
      "eval_runtime": 46.4184,
      "eval_samples_per_second": 10.492,
      "eval_steps_per_second": 5.257,
      "step": 1
    },
    {
      "epoch": 0.006915928247244435,
      "grad_norm": 12.279048919677734,
      "learning_rate": 2e-05,
      "loss": 41.1455,
      "step": 2
    },
    {
      "epoch": 0.006915928247244435,
      "eval_loss": 2.661858320236206,
      "eval_runtime": 25.8469,
      "eval_samples_per_second": 18.842,
      "eval_steps_per_second": 9.44,
      "step": 2
    },
    {
      "epoch": 0.010373892370866653,
      "grad_norm": 13.36858081817627,
      "learning_rate": 3e-05,
      "loss": 44.9327,
      "step": 3
    },
    {
      "epoch": 0.01383185649448887,
      "grad_norm": 17.0398006439209,
      "learning_rate": 4e-05,
      "loss": 44.6562,
      "step": 4
    },
    {
      "epoch": 0.01383185649448887,
      "eval_loss": NaN,
      "eval_runtime": 25.7668,
      "eval_samples_per_second": 18.9,
      "eval_steps_per_second": 9.47,
      "step": 4
    },
    {
      "epoch": 0.017289820618111088,
      "grad_norm": 16.59055519104004,
      "learning_rate": 5e-05,
      "loss": 49.6255,
      "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": 6332448610713600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}