{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013960549812986802,
  "eval_steps": 5,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.307033208657868e-05,
      "grad_norm": Infinity,
      "learning_rate": 1e-05,
      "loss": 113.375,
      "step": 1
    },
    {
      "epoch": 9.307033208657868e-05,
      "eval_loss": 7.2198896408081055,
      "eval_runtime": 239.1747,
      "eval_samples_per_second": 75.664,
      "eval_steps_per_second": 37.834,
      "step": 1
    },
    {
      "epoch": 0.00018614066417315737,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 113.875,
      "step": 2
    },
    {
      "epoch": 0.000279210996259736,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 122.6562,
      "step": 3
    },
    {
      "epoch": 0.00037228132834631473,
      "grad_norm": Infinity,
      "learning_rate": 4e-05,
      "loss": 114.1562,
      "step": 4
    },
    {
      "epoch": 0.0004653516604328934,
      "grad_norm": Infinity,
      "learning_rate": 5e-05,
      "loss": 112.1875,
      "step": 5
    },
    {
      "epoch": 0.0004653516604328934,
      "eval_loss": 7.2212815284729,
      "eval_runtime": 114.7616,
      "eval_samples_per_second": 157.692,
      "eval_steps_per_second": 78.85,
      "step": 5
    },
    {
      "epoch": 0.000558421992519472,
      "grad_norm": Infinity,
      "learning_rate": 6e-05,
      "loss": 113.25,
      "step": 6
    },
    {
      "epoch": 0.0006514923246060507,
      "grad_norm": Infinity,
      "learning_rate": 7e-05,
      "loss": 110.0938,
      "step": 7
    },
    {
      "epoch": 0.0007445626566926295,
      "grad_norm": Infinity,
      "learning_rate": 8e-05,
      "loss": 116.0938,
      "step": 8
    },
    {
      "epoch": 0.0008376329887792081,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 123.0938,
      "step": 9
    },
    {
      "epoch": 0.0009307033208657868,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 115.8438,
      "step": 10
    },
    {
      "epoch": 0.0009307033208657868,
      "eval_loss": 7.2212815284729,
      "eval_runtime": 116.7715,
      "eval_samples_per_second": 154.978,
      "eval_steps_per_second": 77.493,
      "step": 10
    },
    {
      "epoch": 0.0010237736529523655,
      "grad_norm": Infinity,
      "learning_rate": 9.755282581475769e-05,
      "loss": 115.25,
      "step": 11
    },
    {
      "epoch": 0.001116843985038944,
      "grad_norm": Infinity,
      "learning_rate": 9.045084971874738e-05,
      "loss": 103.25,
      "step": 12
    },
    {
      "epoch": 0.0012099143171255228,
      "grad_norm": Infinity,
      "learning_rate": 7.938926261462366e-05,
      "loss": 111.4375,
      "step": 13
    },
    {
      "epoch": 0.0013029846492121015,
      "grad_norm": Infinity,
      "learning_rate": 6.545084971874738e-05,
      "loss": 115.5,
      "step": 14
    },
    {
      "epoch": 0.0013960549812986802,
      "grad_norm": Infinity,
      "learning_rate": 5e-05,
      "loss": 111.2812,
      "step": 15
    },
    {
      "epoch": 0.0013960549812986802,
      "eval_loss": 7.2212815284729,
      "eval_runtime": 115.3728,
      "eval_samples_per_second": 156.857,
      "eval_steps_per_second": 78.433,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 450417917952000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}