{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5191740412979351,
  "eval_steps": 9,
  "global_step": 22,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02359882005899705,
      "eval_loss": 11.216988563537598,
      "eval_runtime": 1.8833,
      "eval_samples_per_second": 151.859,
      "eval_steps_per_second": 19.115,
      "step": 1
    },
    {
      "epoch": 0.21238938053097345,
      "eval_loss": 11.165812492370605,
      "eval_runtime": 0.9078,
      "eval_samples_per_second": 315.047,
      "eval_steps_per_second": 39.656,
      "step": 9
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 15.300642967224121,
      "learning_rate": 9.089646803833589e-05,
      "loss": 179.1345,
      "step": 10
    },
    {
      "epoch": 0.4247787610619469,
      "eval_loss": 11.090907096862793,
      "eval_runtime": 0.9027,
      "eval_samples_per_second": 316.838,
      "eval_steps_per_second": 39.882,
      "step": 18
    },
    {
      "epoch": 0.471976401179941,
      "grad_norm": 17.81786346435547,
      "learning_rate": 5.951955545823342e-05,
      "loss": 177.9139,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 43,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 11,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6789940641792.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}