{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014151777817088271,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0028303555634176542,
      "grad_norm": 9.117393493652344,
      "learning_rate": 1e-05,
      "loss": 5.7837,
      "step": 1
    },
    {
      "epoch": 0.0028303555634176542,
      "eval_loss": 6.043972969055176,
      "eval_runtime": 199.695,
      "eval_samples_per_second": 2.98,
      "eval_steps_per_second": 1.492,
      "step": 1
    },
    {
      "epoch": 0.0056607111268353084,
      "grad_norm": 6.640692710876465,
      "learning_rate": 2e-05,
      "loss": 4.7399,
      "step": 2
    },
    {
      "epoch": 0.0056607111268353084,
      "eval_loss": 5.927265167236328,
      "eval_runtime": 48.5486,
      "eval_samples_per_second": 12.256,
      "eval_steps_per_second": 6.138,
      "step": 2
    },
    {
      "epoch": 0.008491066690252963,
      "grad_norm": 8.097134590148926,
      "learning_rate": 3e-05,
      "loss": 5.0591,
      "step": 3
    },
    {
      "epoch": 0.011321422253670617,
      "grad_norm": 8.384385108947754,
      "learning_rate": 4e-05,
      "loss": 5.3656,
      "step": 4
    },
    {
      "epoch": 0.011321422253670617,
      "eval_loss": 5.277862071990967,
      "eval_runtime": 54.9265,
      "eval_samples_per_second": 10.833,
      "eval_steps_per_second": 5.425,
      "step": 4
    },
    {
      "epoch": 0.014151777817088271,
      "grad_norm": 9.92579460144043,
      "learning_rate": 5e-05,
      "loss": 6.0752,
      "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": 4104787234652160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}