{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032318009210632625,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032318009210632626,
      "grad_norm": 0.11707008630037308,
      "learning_rate": 2e-05,
      "loss": 10.8242,
      "step": 1
    },
    {
      "epoch": 0.00032318009210632626,
      "eval_loss": 10.823429107666016,
      "eval_runtime": 4.9735,
      "eval_samples_per_second": 261.987,
      "eval_steps_per_second": 131.094,
      "step": 1
    },
    {
      "epoch": 0.0006463601842126525,
      "grad_norm": 0.1304236203432083,
      "learning_rate": 4e-05,
      "loss": 10.8408,
      "step": 2
    },
    {
      "epoch": 0.0009695402763189787,
      "grad_norm": 0.14651831984519958,
      "learning_rate": 6e-05,
      "loss": 10.8094,
      "step": 3
    },
    {
      "epoch": 0.0009695402763189787,
      "eval_loss": 10.823285102844238,
      "eval_runtime": 3.6569,
      "eval_samples_per_second": 356.312,
      "eval_steps_per_second": 178.293,
      "step": 3
    },
    {
      "epoch": 0.001292720368425305,
      "grad_norm": 0.18902043998241425,
      "learning_rate": 8e-05,
      "loss": 10.8192,
      "step": 4
    },
    {
      "epoch": 0.0016159004605316313,
      "grad_norm": 0.20040695369243622,
      "learning_rate": 0.0001,
      "loss": 10.8182,
      "step": 5
    },
    {
      "epoch": 0.0019390805526379575,
      "grad_norm": 0.1375870704650879,
      "learning_rate": 0.00012,
      "loss": 10.8247,
      "step": 6
    },
    {
      "epoch": 0.0019390805526379575,
      "eval_loss": 10.822270393371582,
      "eval_runtime": 3.7611,
      "eval_samples_per_second": 346.438,
      "eval_steps_per_second": 173.352,
      "step": 6
    },
    {
      "epoch": 0.002262260644744284,
      "grad_norm": 0.18067824840545654,
      "learning_rate": 0.00014,
      "loss": 10.8133,
      "step": 7
    },
    {
      "epoch": 0.00258544073685061,
      "grad_norm": 0.15925225615501404,
      "learning_rate": 0.00016,
      "loss": 10.8202,
      "step": 8
    },
    {
      "epoch": 0.0029086208289569363,
      "grad_norm": 0.16329418122768402,
      "learning_rate": 0.00018,
      "loss": 10.8138,
      "step": 9
    },
    {
      "epoch": 0.0029086208289569363,
      "eval_loss": 10.82058334350586,
      "eval_runtime": 3.7228,
      "eval_samples_per_second": 350.004,
      "eval_steps_per_second": 175.136,
      "step": 9
    },
    {
      "epoch": 0.0032318009210632625,
      "grad_norm": 0.12121038883924484,
      "learning_rate": 0.0002,
      "loss": 10.8226,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 984354914304.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}