{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02908819690471751,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007458512026850643,
      "eval_loss": 11.130187034606934,
      "eval_runtime": 2.8529,
      "eval_samples_per_second": 198.041,
      "eval_steps_per_second": 99.196,
      "step": 1
    },
    {
      "epoch": 0.007458512026850644,
      "grad_norm": 1.3812353610992432,
      "learning_rate": 0.00019396926207859084,
      "loss": 44.5008,
      "step": 10
    },
    {
      "epoch": 0.009696065634905836,
      "eval_loss": 11.094985961914062,
      "eval_runtime": 1.7136,
      "eval_samples_per_second": 329.722,
      "eval_steps_per_second": 165.153,
      "step": 13
    },
    {
      "epoch": 0.014917024053701287,
      "grad_norm": 1.7032216787338257,
      "learning_rate": 0.00015000000000000001,
      "loss": 44.3424,
      "step": 20
    },
    {
      "epoch": 0.019392131269811673,
      "eval_loss": 11.034822463989258,
      "eval_runtime": 1.7283,
      "eval_samples_per_second": 326.915,
      "eval_steps_per_second": 163.747,
      "step": 26
    },
    {
      "epoch": 0.02237553608055193,
      "grad_norm": 1.6237558126449585,
      "learning_rate": 8.263518223330697e-05,
      "loss": 44.1683,
      "step": 30
    },
    {
      "epoch": 0.02908819690471751,
      "eval_loss": 11.001288414001465,
      "eval_runtime": 1.7182,
      "eval_samples_per_second": 328.826,
      "eval_steps_per_second": 164.704,
      "step": 39
    }
  ],
  "logging_steps": 10,
  "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": 749883359232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}