{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 83,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012048192771084338,
      "grad_norm": 78.63502321747188,
      "learning_rate": 5.555555555555555e-08,
      "logits/chosen": -0.15773604810237885,
      "logits/rejected": 0.06813092529773712,
      "logps/chosen": -141.49667358398438,
      "logps/rejected": -138.58563232421875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.12048192771084337,
      "grad_norm": 88.90141432691846,
      "learning_rate": 4.932432432432432e-07,
      "logits/chosen": 0.70196932554245,
      "logits/rejected": 0.7832146883010864,
      "logps/chosen": -201.90382385253906,
      "logps/rejected": -188.25331115722656,
      "loss": 0.6839,
      "rewards/accuracies": 0.46296295523643494,
      "rewards/chosen": -0.022965913638472557,
      "rewards/margins": 0.006561698392033577,
      "rewards/rejected": -0.029527612030506134,
      "step": 10
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 80.99107716525879,
      "learning_rate": 4.2567567567567566e-07,
      "logits/chosen": 0.4373137354850769,
      "logits/rejected": 0.47410067915916443,
      "logps/chosen": -231.05880737304688,
      "logps/rejected": -206.24331665039062,
      "loss": 0.639,
      "rewards/accuracies": 0.5166666507720947,
      "rewards/chosen": -0.23480196297168732,
      "rewards/margins": 0.091942198574543,
      "rewards/rejected": -0.3267441391944885,
      "step": 20
    },
    {
      "epoch": 0.3614457831325301,
      "grad_norm": 70.05826042544521,
      "learning_rate": 3.5810810810810807e-07,
      "logits/chosen": 0.4946823716163635,
      "logits/rejected": 0.5182942152023315,
      "logps/chosen": -198.873046875,
      "logps/rejected": -209.1875457763672,
      "loss": 0.6132,
      "rewards/accuracies": 0.6666666865348816,
      "rewards/chosen": -0.34537622332572937,
      "rewards/margins": 0.2645321488380432,
      "rewards/rejected": -0.6099082827568054,
      "step": 30
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 73.44013668698199,
      "learning_rate": 2.905405405405405e-07,
      "logits/chosen": 0.6027838587760925,
      "logits/rejected": 0.5924917459487915,
      "logps/chosen": -193.88595581054688,
      "logps/rejected": -207.39035034179688,
      "loss": 0.59,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.38962751626968384,
      "rewards/margins": 0.30494749546051025,
      "rewards/rejected": -0.6945750117301941,
      "step": 40
    },
    {
      "epoch": 0.6024096385542169,
      "grad_norm": 60.19655546024119,
      "learning_rate": 2.2297297297297295e-07,
      "logits/chosen": 0.44521474838256836,
      "logits/rejected": 0.44708484411239624,
      "logps/chosen": -180.35104370117188,
      "logps/rejected": -175.62757873535156,
      "loss": 0.5565,
      "rewards/accuracies": 0.7000000476837158,
      "rewards/chosen": -0.3609669804573059,
      "rewards/margins": 0.35280880331993103,
      "rewards/rejected": -0.7137758135795593,
      "step": 50
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 76.89074162006759,
      "learning_rate": 1.554054054054054e-07,
      "logits/chosen": 0.42552661895751953,
      "logits/rejected": 0.42344537377357483,
      "logps/chosen": -203.36997985839844,
      "logps/rejected": -191.31314086914062,
      "loss": 0.5828,
      "rewards/accuracies": 0.6333333253860474,
      "rewards/chosen": -0.4513484835624695,
      "rewards/margins": 0.287315309047699,
      "rewards/rejected": -0.7386638522148132,
      "step": 60
    },
    {
      "epoch": 0.8433734939759037,
      "grad_norm": 76.3820752555437,
      "learning_rate": 8.783783783783784e-08,
      "logits/chosen": 0.4217614233493805,
      "logits/rejected": 0.41748833656311035,
      "logps/chosen": -163.9698028564453,
      "logps/rejected": -176.10614013671875,
      "loss": 0.5634,
      "rewards/accuracies": 0.7000000476837158,
      "rewards/chosen": -0.3167441189289093,
      "rewards/margins": 0.5091690421104431,
      "rewards/rejected": -0.8259132504463196,
      "step": 70
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 74.01074286574386,
      "learning_rate": 2.027027027027027e-08,
      "logits/chosen": 0.43573635816574097,
      "logits/rejected": 0.45437565445899963,
      "logps/chosen": -225.8251495361328,
      "logps/rejected": -199.63169860839844,
      "loss": 0.5463,
      "rewards/accuracies": 0.7500000596046448,
      "rewards/chosen": -0.41202035546302795,
      "rewards/margins": 0.6277278661727905,
      "rewards/rejected": -1.0397483110427856,
      "step": 80
    },
    {
      "epoch": 1.0,
      "step": 83,
      "total_flos": 0.0,
      "train_loss": 0.5964088123964976,
      "train_runtime": 1125.1043,
      "train_samples_per_second": 3.528,
      "train_steps_per_second": 0.074
    }
  ],
  "logging_steps": 10,
  "max_steps": 83,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}