{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005329385640266469,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005921539600296077,
      "grad_norm": 12.516372680664062,
      "learning_rate": 2e-05,
      "loss": 8.3,
      "step": 1
    },
    {
      "epoch": 0.0005921539600296077,
      "eval_loss": 8.049095153808594,
      "eval_runtime": 74.0575,
      "eval_samples_per_second": 9.614,
      "eval_steps_per_second": 4.807,
      "step": 1
    },
    {
      "epoch": 0.0011843079200592153,
      "grad_norm": 14.498956680297852,
      "learning_rate": 4e-05,
      "loss": 8.0063,
      "step": 2
    },
    {
      "epoch": 0.001776461880088823,
      "grad_norm": 14.787939071655273,
      "learning_rate": 6e-05,
      "loss": 8.2854,
      "step": 3
    },
    {
      "epoch": 0.001776461880088823,
      "eval_loss": 7.804378986358643,
      "eval_runtime": 77.2075,
      "eval_samples_per_second": 9.222,
      "eval_steps_per_second": 4.611,
      "step": 3
    },
    {
      "epoch": 0.0023686158401184307,
      "grad_norm": 15.429038047790527,
      "learning_rate": 8e-05,
      "loss": 8.0241,
      "step": 4
    },
    {
      "epoch": 0.0029607698001480384,
      "grad_norm": 14.693309783935547,
      "learning_rate": 0.0001,
      "loss": 7.2779,
      "step": 5
    },
    {
      "epoch": 0.003552923760177646,
      "grad_norm": 11.910072326660156,
      "learning_rate": 0.00012,
      "loss": 5.3548,
      "step": 6
    },
    {
      "epoch": 0.003552923760177646,
      "eval_loss": 5.038506507873535,
      "eval_runtime": 77.6302,
      "eval_samples_per_second": 9.172,
      "eval_steps_per_second": 4.586,
      "step": 6
    },
    {
      "epoch": 0.004145077720207254,
      "grad_norm": 9.185333251953125,
      "learning_rate": 0.00014,
      "loss": 4.9679,
      "step": 7
    },
    {
      "epoch": 0.004737231680236861,
      "grad_norm": 10.450874328613281,
      "learning_rate": 0.00016,
      "loss": 4.0511,
      "step": 8
    },
    {
      "epoch": 0.005329385640266469,
      "grad_norm": 10.987703323364258,
      "learning_rate": 0.00018,
      "loss": 3.3444,
      "step": 9
    },
    {
      "epoch": 0.005329385640266469,
      "eval_loss": 2.0294888019561768,
      "eval_runtime": 77.5909,
      "eval_samples_per_second": 9.176,
      "eval_steps_per_second": 4.588,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1664607823331328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}