{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32193158953722334,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32193158953722334,
      "grad_norm": 9.22656536102295,
      "learning_rate": 1.8354878114129364e-06,
      "logits/chosen": -1.4996416568756104,
      "logits/rejected": -2.4245731830596924,
      "logps/chosen": -478.6173095703125,
      "logps/rejected": -385.2591552734375,
      "loss": 0.5053,
      "rewards/accuracies": 0.706250011920929,
      "rewards/chosen": 0.758898913860321,
      "rewards/margins": 0.6253119707107544,
      "rewards/rejected": 0.13358694314956665,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 31,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7103824211043942e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}