{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.022209567198177675,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005694760820045558,
      "eval_loss": 11.059797286987305,
      "eval_runtime": 4.4025,
      "eval_samples_per_second": 168.085,
      "eval_steps_per_second": 84.043,
      "step": 1
    },
    {
      "epoch": 0.0028473804100227792,
      "grad_norm": 7.55947732925415,
      "learning_rate": 5e-05,
      "loss": 44.2062,
      "step": 5
    },
    {
      "epoch": 0.0056947608200455585,
      "grad_norm": 8.039371490478516,
      "learning_rate": 0.0001,
      "loss": 44.1306,
      "step": 10
    },
    {
      "epoch": 0.0056947608200455585,
      "eval_loss": 11.009163856506348,
      "eval_runtime": 3.5052,
      "eval_samples_per_second": 211.116,
      "eval_steps_per_second": 105.558,
      "step": 10
    },
    {
      "epoch": 0.008542141230068337,
      "grad_norm": 7.748521327972412,
      "learning_rate": 9.619397662556435e-05,
      "loss": 43.8587,
      "step": 15
    },
    {
      "epoch": 0.011389521640091117,
      "grad_norm": 9.04804515838623,
      "learning_rate": 8.535533905932738e-05,
      "loss": 43.7344,
      "step": 20
    },
    {
      "epoch": 0.011389521640091117,
      "eval_loss": 10.871933937072754,
      "eval_runtime": 3.5645,
      "eval_samples_per_second": 207.603,
      "eval_steps_per_second": 103.802,
      "step": 20
    },
    {
      "epoch": 0.014236902050113895,
      "grad_norm": 9.006335258483887,
      "learning_rate": 6.91341716182545e-05,
      "loss": 43.3375,
      "step": 25
    },
    {
      "epoch": 0.017084282460136675,
      "grad_norm": 10.060773849487305,
      "learning_rate": 5e-05,
      "loss": 43.1,
      "step": 30
    },
    {
      "epoch": 0.017084282460136675,
      "eval_loss": 10.74547290802002,
      "eval_runtime": 3.5627,
      "eval_samples_per_second": 207.706,
      "eval_steps_per_second": 103.853,
      "step": 30
    },
    {
      "epoch": 0.019931662870159454,
      "grad_norm": 10.196281433105469,
      "learning_rate": 3.086582838174551e-05,
      "loss": 42.9937,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 629323333632.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}