{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00489087240936602,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009781744818732042,
      "grad_norm": 11.524930953979492,
      "learning_rate": 1e-05,
      "loss": 7.3196,
      "step": 1
    },
    {
      "epoch": 0.0009781744818732042,
      "eval_loss": 7.173078536987305,
      "eval_runtime": 88.3064,
      "eval_samples_per_second": 19.5,
      "eval_steps_per_second": 9.75,
      "step": 1
    },
    {
      "epoch": 0.0019563489637464083,
      "grad_norm": 11.45195198059082,
      "learning_rate": 2e-05,
      "loss": 6.8622,
      "step": 2
    },
    {
      "epoch": 0.0019563489637464083,
      "eval_loss": 7.01306676864624,
      "eval_runtime": 59.2052,
      "eval_samples_per_second": 29.085,
      "eval_steps_per_second": 14.543,
      "step": 2
    },
    {
      "epoch": 0.0029345234456196125,
      "grad_norm": 11.135690689086914,
      "learning_rate": 3e-05,
      "loss": 6.8056,
      "step": 3
    },
    {
      "epoch": 0.003912697927492817,
      "grad_norm": 11.064360618591309,
      "learning_rate": 4e-05,
      "loss": 6.3962,
      "step": 4
    },
    {
      "epoch": 0.003912697927492817,
      "eval_loss": 6.577771186828613,
      "eval_runtime": 67.2384,
      "eval_samples_per_second": 25.61,
      "eval_steps_per_second": 12.805,
      "step": 4
    },
    {
      "epoch": 0.00489087240936602,
      "grad_norm": 11.934356689453125,
      "learning_rate": 5e-05,
      "loss": 6.2914,
      "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": 3822182832537600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}