{
  "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": 7.775175087490474,
      "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": 7.448045779799194,
      "learning_rate": 4.930057285201027e-07,
      "logits/chosen": -2.7555572986602783,
      "logits/rejected": -2.746171474456787,
      "logps/chosen": -271.9293212890625,
      "logps/rejected": -260.67010498046875,
      "loss": 0.6915,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": 0.005406347569078207,
      "rewards/margins": 0.0034980433993041515,
      "rewards/rejected": 0.0019083041697740555,
      "step": 10
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 6.734236245718351,
      "learning_rate": 4.187457503795526e-07,
      "logits/chosen": -2.7869458198547363,
      "logits/rejected": -2.768073320388794,
      "logps/chosen": -261.4452209472656,
      "logps/rejected": -250.89541625976562,
      "loss": 0.6745,
      "rewards/accuracies": 0.715624988079071,
      "rewards/chosen": 0.03236500173807144,
      "rewards/margins": 0.04089399054646492,
      "rewards/rejected": -0.008528990671038628,
      "step": 20
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 7.437539615124712,
      "learning_rate": 2.8691164100062034e-07,
      "logits/chosen": -2.7878143787384033,
      "logits/rejected": -2.7688212394714355,
      "logps/chosen": -293.8128662109375,
      "logps/rejected": -254.24874877929688,
      "loss": 0.6485,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -0.02356739528477192,
      "rewards/margins": 0.12733949720859528,
      "rewards/rejected": -0.15090689063072205,
      "step": 30
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 8.137783776888698,
      "learning_rate": 1.4248369943086995e-07,
      "logits/chosen": -2.760474681854248,
      "logits/rejected": -2.7379024028778076,
      "logps/chosen": -264.1443176269531,
      "logps/rejected": -255.5771026611328,
      "loss": 0.6353,
      "rewards/accuracies": 0.684374988079071,
      "rewards/chosen": -0.11224844306707382,
      "rewards/margins": 0.16041621565818787,
      "rewards/rejected": -0.2726646959781647,
      "step": 40
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 8.560922020463133,
      "learning_rate": 3.473909705816111e-08,
      "logits/chosen": -2.7703192234039307,
      "logits/rejected": -2.7502920627593994,
      "logps/chosen": -279.1363525390625,
      "logps/rejected": -287.27764892578125,
      "loss": 0.6202,
      "rewards/accuracies": 0.628125011920929,
      "rewards/chosen": -0.22127707302570343,
      "rewards/margins": 0.13637453317642212,
      "rewards/rejected": -0.35765162110328674,
      "step": 50
    },
    {
      "epoch": 0.9874476987447699,
      "step": 59,
      "total_flos": 0.0,
      "train_loss": 0.6490362135030455,
      "train_runtime": 1628.642,
      "train_samples_per_second": 9.384,
      "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
}