{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00623684415685663,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012473688313713262,
      "grad_norm": 0.018246954306960106,
      "learning_rate": 1e-05,
      "loss": 10.3773,
      "step": 1
    },
    {
      "epoch": 0.0012473688313713262,
      "eval_loss": 10.378649711608887,
      "eval_runtime": 28.3097,
      "eval_samples_per_second": 47.722,
      "eval_steps_per_second": 23.879,
      "step": 1
    },
    {
      "epoch": 0.0024947376627426523,
      "grad_norm": 0.019670143723487854,
      "learning_rate": 2e-05,
      "loss": 10.3795,
      "step": 2
    },
    {
      "epoch": 0.0024947376627426523,
      "eval_loss": 10.378644943237305,
      "eval_runtime": 8.9344,
      "eval_samples_per_second": 151.214,
      "eval_steps_per_second": 75.663,
      "step": 2
    },
    {
      "epoch": 0.0037421064941139783,
      "grad_norm": 0.01910281367599964,
      "learning_rate": 3e-05,
      "loss": 10.3786,
      "step": 3
    },
    {
      "epoch": 0.004989475325485305,
      "grad_norm": 0.017886217683553696,
      "learning_rate": 4e-05,
      "loss": 10.377,
      "step": 4
    },
    {
      "epoch": 0.004989475325485305,
      "eval_loss": 10.378625869750977,
      "eval_runtime": 8.9995,
      "eval_samples_per_second": 150.119,
      "eval_steps_per_second": 75.115,
      "step": 4
    },
    {
      "epoch": 0.00623684415685663,
      "grad_norm": 0.017472613602876663,
      "learning_rate": 5e-05,
      "loss": 10.3791,
      "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": 517236326400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}