{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005795547570578903,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011591095141157805,
      "grad_norm": 0.6819593906402588,
      "learning_rate": 1e-05,
      "loss": 1.2374,
      "step": 1
    },
    {
      "epoch": 0.00011591095141157805,
      "eval_loss": 1.2256087064743042,
      "eval_runtime": 715.9873,
      "eval_samples_per_second": 20.295,
      "eval_steps_per_second": 10.148,
      "step": 1
    },
    {
      "epoch": 0.0002318219028231561,
      "grad_norm": 0.6854197978973389,
      "learning_rate": 2e-05,
      "loss": 1.2311,
      "step": 2
    },
    {
      "epoch": 0.0002318219028231561,
      "eval_loss": 1.1985679864883423,
      "eval_runtime": 351.4093,
      "eval_samples_per_second": 41.351,
      "eval_steps_per_second": 20.677,
      "step": 2
    },
    {
      "epoch": 0.0003477328542347342,
      "grad_norm": 0.5876014828681946,
      "learning_rate": 3e-05,
      "loss": 1.216,
      "step": 3
    },
    {
      "epoch": 0.0004636438056463122,
      "grad_norm": 0.5603479743003845,
      "learning_rate": 4e-05,
      "loss": 1.168,
      "step": 4
    },
    {
      "epoch": 0.0004636438056463122,
      "eval_loss": 1.169231653213501,
      "eval_runtime": 518.0872,
      "eval_samples_per_second": 28.047,
      "eval_steps_per_second": 14.025,
      "step": 4
    },
    {
      "epoch": 0.0005795547570578903,
      "grad_norm": 0.530938446521759,
      "learning_rate": 5e-05,
      "loss": 1.1606,
      "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": 2553884719448064.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}