{
  "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": 0.016736401673640166,
      "grad_norm": 7.773013789330872,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": -2.807276487350464,
      "logits/rejected": -2.7759768962860107,
      "logps/chosen": -315.42626953125,
      "logps/rejected": -227.5915985107422,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 7.444333838896045,
      "learning_rate": 4.930057285201027e-07,
      "logits/chosen": -2.755530834197998,
      "logits/rejected": -2.7461330890655518,
      "logps/chosen": -271.9606628417969,
      "logps/rejected": -260.7101745605469,
      "loss": 0.6915,
      "rewards/accuracies": 0.5208333134651184,
      "rewards/chosen": 0.005092799663543701,
      "rewards/margins": 0.003585505299270153,
      "rewards/rejected": 0.00150729448068887,
      "step": 10
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 6.714535781496835,
      "learning_rate": 4.187457503795526e-07,
      "logits/chosen": -2.787006378173828,
      "logits/rejected": -2.768144130706787,
      "logps/chosen": -261.48565673828125,
      "logps/rejected": -250.9136199951172,
      "loss": 0.6745,
      "rewards/accuracies": 0.703125,
      "rewards/chosen": 0.031960152089595795,
      "rewards/margins": 0.04067179188132286,
      "rewards/rejected": -0.008711638860404491,
      "step": 20
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 7.372509129721545,
      "learning_rate": 2.8691164100062034e-07,
      "logits/chosen": -2.7877068519592285,
      "logits/rejected": -2.768649101257324,
      "logps/chosen": -293.81915283203125,
      "logps/rejected": -254.2086639404297,
      "loss": 0.6487,
      "rewards/accuracies": 0.6781250238418579,
      "rewards/chosen": -0.023630935698747635,
      "rewards/margins": 0.12687507271766663,
      "rewards/rejected": -0.15050600469112396,
      "step": 30
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 8.124696915257744,
      "learning_rate": 1.4248369943086995e-07,
      "logits/chosen": -2.760054111480713,
      "logits/rejected": -2.7374792098999023,
      "logps/chosen": -264.1077575683594,
      "logps/rejected": -255.5675048828125,
      "loss": 0.6354,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.11188302934169769,
      "rewards/margins": 0.1606856733560562,
      "rewards/rejected": -0.2725687325000763,
      "step": 40
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 8.573481060543557,
      "learning_rate": 3.473909705816111e-08,
      "logits/chosen": -2.769763946533203,
      "logits/rejected": -2.74979305267334,
      "logps/chosen": -279.1478576660156,
      "logps/rejected": -287.2943420410156,
      "loss": 0.6202,
      "rewards/accuracies": 0.628125011920929,
      "rewards/chosen": -0.22139184176921844,
      "rewards/margins": 0.13642652332782745,
      "rewards/rejected": -0.3578183948993683,
      "step": 50
    },
    {
      "epoch": 0.9874476987447699,
      "step": 59,
      "total_flos": 0.0,
      "train_loss": 0.6490306530968618,
      "train_runtime": 1625.865,
      "train_samples_per_second": 9.4,
      "train_steps_per_second": 0.036
    }
  ],
  "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
}