{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23880597014925373,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03980099502487562,
      "grad_norm": 2.466599941253662,
      "learning_rate": 4.980474401576887e-07,
      "logits/chosen": -1.0382839441299438,
      "logits/rejected": -1.054585576057434,
      "logps/chosen": -180.16372680664062,
      "logps/rejected": -179.63958740234375,
      "loss": 0.7169,
      "rewards/accuracies": 0.508593738079071,
      "rewards/chosen": -0.278283029794693,
      "rewards/margins": 0.017729664221405983,
      "rewards/rejected": -0.2960126996040344,
      "step": 100
    },
    {
      "epoch": 0.07960199004975124,
      "grad_norm": 1.6285502910614014,
      "learning_rate": 4.922202605502572e-07,
      "logits/chosen": -1.0206574201583862,
      "logits/rejected": -1.0379180908203125,
      "logps/chosen": -180.13119506835938,
      "logps/rejected": -180.29315185546875,
      "loss": 0.7103,
      "rewards/accuracies": 0.5193750262260437,
      "rewards/chosen": -0.2392772138118744,
      "rewards/margins": 0.0195913203060627,
      "rewards/rejected": -0.2588685154914856,
      "step": 200
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 2.7344954013824463,
      "learning_rate": 4.82609484512869e-07,
      "logits/chosen": -1.0241189002990723,
      "logits/rejected": -1.0348433256149292,
      "logps/chosen": -178.86837768554688,
      "logps/rejected": -179.53598022460938,
      "loss": 0.7077,
      "rewards/accuracies": 0.5171874761581421,
      "rewards/chosen": -0.21391521394252777,
      "rewards/margins": 0.015260601416230202,
      "rewards/rejected": -0.22917583584785461,
      "step": 300
    },
    {
      "epoch": 0.15920398009950248,
      "grad_norm": 1.7553608417510986,
      "learning_rate": 4.6936523696827614e-07,
      "logits/chosen": -1.0034430027008057,
      "logits/rejected": -1.0131057500839233,
      "logps/chosen": -180.70912170410156,
      "logps/rejected": -181.44435119628906,
      "loss": 0.7064,
      "rewards/accuracies": 0.5106250047683716,
      "rewards/chosen": -0.18936260044574738,
      "rewards/margins": 0.013838082551956177,
      "rewards/rejected": -0.20320068299770355,
      "step": 400
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.4984805583953857,
      "learning_rate": 4.5269439940365644e-07,
      "logits/chosen": -1.0015250444412231,
      "logits/rejected": -1.0229138135910034,
      "logps/chosen": -178.01638793945312,
      "logps/rejected": -177.6285400390625,
      "loss": 0.7093,
      "rewards/accuracies": 0.4985937476158142,
      "rewards/chosen": -0.1724223494529724,
      "rewards/margins": 0.005522388964891434,
      "rewards/rejected": -0.17794474959373474,
      "step": 500
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 1.539502501487732,
      "learning_rate": 4.328573782827409e-07,
      "logits/chosen": -0.9833173155784607,
      "logits/rejected": -1.0065593719482422,
      "logps/chosen": -176.92718505859375,
      "logps/rejected": -174.7305145263672,
      "loss": 0.7017,
      "rewards/accuracies": 0.507031261920929,
      "rewards/chosen": -0.14655204117298126,
      "rewards/margins": 0.01735287345945835,
      "rewards/rejected": -0.16390492022037506,
      "step": 600
    }
  ],
  "logging_steps": 100,
  "max_steps": 2512,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}