{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.992,
  "eval_steps": 200,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 307.76555800630456,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -2.8404788970947266,
      "logits/real": -2.5973095893859863,
      "logps/generated": -199.41073608398438,
      "logps/real": -84.76593017578125,
      "loss": 0.7771,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 8.428438696613153,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -2.9082934856414795,
      "logits/real": -2.201085329055786,
      "logps/generated": -260.89495849609375,
      "logps/real": -89.60836791992188,
      "loss": 0.2691,
      "rewards/accuracies": 0.8888888955116272,
      "rewards/generated": -3.8854570388793945,
      "rewards/margins": 5.224937438964844,
      "rewards/real": 1.3394801616668701,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.6808156850513947,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -3.0079009532928467,
      "logits/real": -2.238185167312622,
      "logps/generated": -310.7685241699219,
      "logps/real": -82.25010681152344,
      "loss": 0.0707,
      "rewards/accuracies": 1.0,
      "rewards/generated": -8.675054550170898,
      "rewards/margins": 11.541936874389648,
      "rewards/real": 2.866882562637329,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7630367545230997,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -3.0362448692321777,
      "logits/real": -2.1702117919921875,
      "logps/generated": -325.0323181152344,
      "logps/real": -72.29302978515625,
      "loss": 0.0691,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.070144653320312,
      "rewards/margins": 12.167816162109375,
      "rewards/real": 3.0976719856262207,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.8045898247287383,
      "learning_rate": 2e-07,
      "logits/generated": -3.0557637214660645,
      "logits/real": -2.27079176902771,
      "logps/generated": -326.16363525390625,
      "logps/real": -73.30236053466797,
      "loss": 0.0736,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.190264701843262,
      "rewards/margins": 13.376245498657227,
      "rewards/real": 3.1859793663024902,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9553834700952871,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -3.051811933517456,
      "logits/real": -2.1524760723114014,
      "logps/generated": -327.13031005859375,
      "logps/real": -71.540771484375,
      "loss": 0.0724,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.402329444885254,
      "rewards/margins": 13.604934692382812,
      "rewards/real": 3.2026054859161377,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.8111910021687768,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -3.0647284984588623,
      "logits/real": -2.1906068325042725,
      "logps/generated": -329.8739318847656,
      "logps/real": -82.74003601074219,
      "loss": 0.0694,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.355340003967285,
      "rewards/margins": 13.413922309875488,
      "rewards/real": 3.0585832595825195,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.11182688801519332,
      "train_runtime": 795.5053,
      "train_samples_per_second": 2.513,
      "train_steps_per_second": 0.078
    }
  ],
  "logging_steps": 10,
  "max_steps": 62,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}