{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9874476987447699,
  "eval_steps": 500,
  "global_step": 59,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": -2.828038215637207,
      "logits/rejected": -2.728235960006714,
      "logps/chosen": -198.4669189453125,
      "logps/pi_response": -116.54592895507812,
      "logps/ref_response": -116.54592895507812,
      "logps/rejected": -205.3916015625,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.930057285201027e-07,
      "logits/chosen": -2.7447762489318848,
      "logits/rejected": -2.7068071365356445,
      "logps/chosen": -220.58523559570312,
      "logps/pi_response": -125.61652374267578,
      "logps/ref_response": -125.32001495361328,
      "logps/rejected": -271.0242919921875,
      "loss": 0.6849,
      "rewards/accuracies": 0.5763888955116272,
      "rewards/chosen": -0.025184087455272675,
      "rewards/margins": 0.02512713521718979,
      "rewards/rejected": -0.05031122267246246,
      "step": 10
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.187457503795526e-07,
      "logits/chosen": -2.764012575149536,
      "logits/rejected": -2.720431327819824,
      "logps/chosen": -259.4167785644531,
      "logps/pi_response": -120.57942199707031,
      "logps/ref_response": -122.2673110961914,
      "logps/rejected": -314.50408935546875,
      "loss": 0.6284,
      "rewards/accuracies": 0.640625,
      "rewards/chosen": -0.23503510653972626,
      "rewards/margins": 0.2841939330101013,
      "rewards/rejected": -0.519228994846344,
      "step": 20
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.8691164100062034e-07,
      "logits/chosen": -2.742785930633545,
      "logits/rejected": -2.7049012184143066,
      "logps/chosen": -287.7349853515625,
      "logps/pi_response": -148.02655029296875,
      "logps/ref_response": -124.40946197509766,
      "logps/rejected": -358.1172790527344,
      "loss": 0.5885,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -0.508863091468811,
      "rewards/margins": 0.4599063992500305,
      "rewards/rejected": -0.9687695503234863,
      "step": 30
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.4248369943086995e-07,
      "logits/chosen": -2.6629269123077393,
      "logits/rejected": -2.6268365383148193,
      "logps/chosen": -285.77117919921875,
      "logps/pi_response": -154.98104858398438,
      "logps/ref_response": -118.28387451171875,
      "logps/rejected": -360.41912841796875,
      "loss": 0.5645,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.5763512253761292,
      "rewards/margins": 0.48427286744117737,
      "rewards/rejected": -1.060624122619629,
      "step": 40
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.473909705816111e-08,
      "logits/chosen": -2.6366264820098877,
      "logits/rejected": -2.584380626678467,
      "logps/chosen": -290.7797546386719,
      "logps/pi_response": -167.6616973876953,
      "logps/ref_response": -121.82298278808594,
      "logps/rejected": -365.2950744628906,
      "loss": 0.5586,
      "rewards/accuracies": 0.715624988079071,
      "rewards/chosen": -0.6138635873794556,
      "rewards/margins": 0.5299580097198486,
      "rewards/rejected": -1.1438214778900146,
      "step": 50
    },
    {
      "epoch": 0.99,
      "step": 59,
      "total_flos": 0.0,
      "train_loss": 0.5957206467450675,
      "train_runtime": 3584.1475,
      "train_samples_per_second": 4.264,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 59,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}