{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04594004823705065,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00918800964741013,
      "grad_norm": 0.036612071096897125,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 15.01579761505127,
      "logits/rejected": 15.359031677246094,
      "logps/chosen": -0.2681262791156769,
      "logps/rejected": -0.31947994232177734,
      "loss": 0.9551,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.40218934416770935,
      "rewards/margins": 0.07703053951263428,
      "rewards/rejected": -0.479219913482666,
      "step": 10
    },
    {
      "epoch": 0.01837601929482026,
      "grad_norm": 0.05575725808739662,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.570712089538574,
      "logits/rejected": 15.321355819702148,
      "logps/chosen": -0.2867889404296875,
      "logps/rejected": -0.3514837622642517,
      "loss": 0.923,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.43018341064453125,
      "rewards/margins": 0.09704220294952393,
      "rewards/rejected": -0.5272256135940552,
      "step": 20
    },
    {
      "epoch": 0.02756402894223039,
      "grad_norm": 0.0492466576397419,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.748420715332031,
      "logits/rejected": 14.969354629516602,
      "logps/chosen": -0.28405922651290894,
      "logps/rejected": -0.32855403423309326,
      "loss": 0.9357,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.426088809967041,
      "rewards/margins": 0.06674225628376007,
      "rewards/rejected": -0.4928310811519623,
      "step": 30
    },
    {
      "epoch": 0.03675203858964052,
      "grad_norm": 0.05719422921538353,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.28278923034668,
      "logits/rejected": 14.76964282989502,
      "logps/chosen": -0.27940627932548523,
      "logps/rejected": -0.3408831059932709,
      "loss": 0.9215,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.41910940408706665,
      "rewards/margins": 0.09221524000167847,
      "rewards/rejected": -0.5113246440887451,
      "step": 40
    },
    {
      "epoch": 0.04594004823705065,
      "grad_norm": 0.06247895210981369,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.943578720092773,
      "logits/rejected": 14.936178207397461,
      "logps/chosen": -0.2819541394710541,
      "logps/rejected": -0.3245392441749573,
      "loss": 0.9464,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.4229312539100647,
      "rewards/margins": 0.06387762725353241,
      "rewards/rejected": -0.4868088662624359,
      "step": 50
    },
    {
      "epoch": 0.04594004823705065,
      "eval_logits/chosen": 14.7594575881958,
      "eval_logits/rejected": 15.193694114685059,
      "eval_logps/chosen": -0.2807807922363281,
      "eval_logps/rejected": -0.36209535598754883,
      "eval_loss": 0.9397181868553162,
      "eval_rewards/accuracies": 0.5681818127632141,
      "eval_rewards/chosen": -0.4211711883544922,
      "eval_rewards/margins": 0.12197184562683105,
      "eval_rewards/rejected": -0.5431429743766785,
      "eval_runtime": 24.9762,
      "eval_samples_per_second": 28.187,
      "eval_steps_per_second": 3.523,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2235350146757427e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}