{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 100,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.16037533305228002,
      "learning_rate": 5e-06,
      "logits/chosen": -0.496604323387146,
      "logits/rejected": -0.4112662672996521,
      "logps/chosen": -242.63560485839844,
      "logps/ref_response": -0.496604323387146,
      "logps/rejected": -275.38885498046875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.8,
      "step": 3,
      "total_flos": 0.0,
      "train_loss": 0.693049430847168,
      "train_runtime": 130.1581,
      "train_samples_per_second": 1.844,
      "train_steps_per_second": 0.023
    }
  ],
  "logging_steps": 10,
  "max_steps": 3,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}