{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.985781990521327,
  "eval_steps": 100,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 532.1433587155178,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": 123.11854553222656,
      "logits/rejected": 97.00198364257812,
      "logps/chosen": -425.18585205078125,
      "logps/rejected": -424.1869201660156,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.19,
      "grad_norm": 566.1002259089971,
      "learning_rate": 4.907293218369498e-07,
      "logits/chosen": 117.24137115478516,
      "logits/rejected": 136.07931518554688,
      "logps/chosen": -441.024169921875,
      "logps/rejected": -523.3809204101562,
      "loss": 0.9796,
      "rewards/accuracies": 0.5277777910232544,
      "rewards/chosen": 0.47284841537475586,
      "rewards/margins": 0.3260529637336731,
      "rewards/rejected": 0.14679540693759918,
      "step": 10
    },
    {
      "epoch": 0.38,
      "grad_norm": 404.0281115107519,
      "learning_rate": 3.941700805287168e-07,
      "logits/chosen": 126.44390869140625,
      "logits/rejected": 133.97540283203125,
      "logps/chosen": -428.3494567871094,
      "logps/rejected": -497.9369201660156,
      "loss": 0.8584,
      "rewards/accuracies": 0.668749988079071,
      "rewards/chosen": -0.416983425617218,
      "rewards/margins": 1.6682897806167603,
      "rewards/rejected": -2.085273265838623,
      "step": 20
    },
    {
      "epoch": 0.57,
      "grad_norm": 390.20247413651066,
      "learning_rate": 2.3293939665883228e-07,
      "logits/chosen": 124.90443420410156,
      "logits/rejected": 128.2018585205078,
      "logps/chosen": -471.1220703125,
      "logps/rejected": -534.6819458007812,
      "loss": 0.9208,
      "rewards/accuracies": 0.706250011920929,
      "rewards/chosen": -3.200387954711914,
      "rewards/margins": 2.2930397987365723,
      "rewards/rejected": -5.493427753448486,
      "step": 30
    },
    {
      "epoch": 0.76,
      "grad_norm": 433.63122435275017,
      "learning_rate": 7.936171419533652e-08,
      "logits/chosen": 125.5661392211914,
      "logits/rejected": 120.38105773925781,
      "logps/chosen": -487.0335388183594,
      "logps/rejected": -507.2274475097656,
      "loss": 0.8419,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -2.770435333251953,
      "rewards/margins": 1.7221254110336304,
      "rewards/rejected": -4.492560386657715,
      "step": 40
    },
    {
      "epoch": 0.95,
      "grad_norm": 521.2062578099036,
      "learning_rate": 2.328513490917311e-09,
      "logits/chosen": 135.242919921875,
      "logits/rejected": 135.51016235351562,
      "logps/chosen": -495.3255920410156,
      "logps/rejected": -513.388916015625,
      "loss": 0.8142,
      "rewards/accuracies": 0.6812499761581421,
      "rewards/chosen": -2.5005745887756348,
      "rewards/margins": 1.9275367259979248,
      "rewards/rejected": -4.428111553192139,
      "step": 50
    },
    {
      "epoch": 0.99,
      "step": 52,
      "total_flos": 0.0,
      "train_loss": 0.8682076243253855,
      "train_runtime": 573.101,
      "train_samples_per_second": 11.778,
      "train_steps_per_second": 0.091
    }
  ],
  "logging_steps": 10,
  "max_steps": 52,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}