{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04036326942482341,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008072653884964682,
      "grad_norm": 0.04381619393825531,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.719314575195312,
      "logits/rejected": 15.156938552856445,
      "logps/chosen": -0.2856016755104065,
      "logps/rejected": -0.31895095109939575,
      "loss": 0.9242,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.42840251326560974,
      "rewards/margins": 0.050023891031742096,
      "rewards/rejected": -0.47842639684677124,
      "step": 10
    },
    {
      "epoch": 0.016145307769929364,
      "grad_norm": 0.05155143886804581,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.559402465820312,
      "logits/rejected": 15.32939338684082,
      "logps/chosen": -0.2736968398094177,
      "logps/rejected": -0.3458033502101898,
      "loss": 0.9127,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4105452597141266,
      "rewards/margins": 0.10815979540348053,
      "rewards/rejected": -0.5187050104141235,
      "step": 20
    },
    {
      "epoch": 0.024217961654894045,
      "grad_norm": 0.05071854218840599,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.653738021850586,
      "logits/rejected": 15.168347358703613,
      "logps/chosen": -0.2985997200012207,
      "logps/rejected": -0.34624338150024414,
      "loss": 0.9141,
      "rewards/accuracies": 0.4625000059604645,
      "rewards/chosen": -0.44789963960647583,
      "rewards/margins": 0.07146544009447098,
      "rewards/rejected": -0.5193650722503662,
      "step": 30
    },
    {
      "epoch": 0.03229061553985873,
      "grad_norm": 0.052318744361400604,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.621539115905762,
      "logits/rejected": 15.138806343078613,
      "logps/chosen": -0.27971988916397095,
      "logps/rejected": -0.360626757144928,
      "loss": 0.9313,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.4195798337459564,
      "rewards/margins": 0.12136033922433853,
      "rewards/rejected": -0.5409401655197144,
      "step": 40
    },
    {
      "epoch": 0.04036326942482341,
      "grad_norm": 0.06900553405284882,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.308789253234863,
      "logits/rejected": 14.605737686157227,
      "logps/chosen": -0.2685723304748535,
      "logps/rejected": -0.323064386844635,
      "loss": 0.9076,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.40285855531692505,
      "rewards/margins": 0.08173803985118866,
      "rewards/rejected": -0.4845965802669525,
      "step": 50
    },
    {
      "epoch": 0.04036326942482341,
      "eval_logits/chosen": 14.528907775878906,
      "eval_logits/rejected": 15.016877174377441,
      "eval_logps/chosen": -0.2801212966442108,
      "eval_logps/rejected": -0.34862396121025085,
      "eval_loss": 0.9108895063400269,
      "eval_rewards/accuracies": 0.5544554591178894,
      "eval_rewards/chosen": -0.4201819598674774,
      "eval_rewards/margins": 0.10275395959615707,
      "eval_rewards/rejected": -0.5229359865188599,
      "eval_runtime": 30.01,
      "eval_samples_per_second": 26.691,
      "eval_steps_per_second": 3.366,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2074278135739187e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}