{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009615384615384616,
      "grad_norm": 28.194065437278258,
      "learning_rate": 1.5625e-08,
      "logits/chosen": -1.609375,
      "logits/rejected": -1.6484375,
      "logps/chosen": -152.0,
      "logps/rejected": -127.5,
      "loss": 0.6914,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 26.916436077863562,
      "learning_rate": 1.5624999999999999e-07,
      "logits/chosen": -1.6015625,
      "logits/rejected": -1.484375,
      "logps/chosen": -149.0,
      "logps/rejected": -128.0,
      "loss": 0.6868,
      "rewards/accuracies": 0.3194444477558136,
      "rewards/chosen": -0.0045166015625,
      "rewards/margins": 0.01080322265625,
      "rewards/rejected": -0.0152587890625,
      "step": 10
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 20.740344035629946,
      "learning_rate": 3.1249999999999997e-07,
      "logits/chosen": -1.59375,
      "logits/rejected": -1.4765625,
      "logps/chosen": -160.0,
      "logps/rejected": -133.0,
      "loss": 0.5799,
      "rewards/accuracies": 0.9624999761581421,
      "rewards/chosen": 0.03662109375,
      "rewards/margins": 0.2734375,
      "rewards/rejected": -0.2373046875,
      "step": 20
    },
    {
      "epoch": 0.28846153846153844,
      "grad_norm": 6.570831756440352,
      "learning_rate": 4.6874999999999996e-07,
      "logits/chosen": -1.5703125,
      "logits/rejected": -1.484375,
      "logps/chosen": -142.0,
      "logps/rejected": -142.0,
      "loss": 0.254,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.0072021484375,
      "rewards/margins": 1.390625,
      "rewards/rejected": -1.3828125,
      "step": 30
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.3430324547403658,
      "learning_rate": 4.857142857142857e-07,
      "logits/chosen": -1.59375,
      "logits/rejected": -1.546875,
      "logps/chosen": -169.0,
      "logps/rejected": -180.0,
      "loss": 0.0296,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.341796875,
      "rewards/margins": 4.8125,
      "rewards/rejected": -5.15625,
      "step": 40
    },
    {
      "epoch": 0.4807692307692308,
      "grad_norm": 1.0998802903857687,
      "learning_rate": 4.6785714285714283e-07,
      "logits/chosen": -1.6484375,
      "logits/rejected": -1.5234375,
      "logps/chosen": -165.0,
      "logps/rejected": -200.0,
      "loss": 0.0098,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.7265625,
      "rewards/margins": 6.625,
      "rewards/rejected": -7.34375,
      "step": 50
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 2.398247571338227,
      "learning_rate": 4.5e-07,
      "logits/chosen": -1.625,
      "logits/rejected": -1.5703125,
      "logps/chosen": -173.0,
      "logps/rejected": -213.0,
      "loss": 0.0084,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.9609375,
      "rewards/margins": 7.4375,
      "rewards/rejected": -8.375,
      "step": 60
    },
    {
      "epoch": 0.6730769230769231,
      "grad_norm": 3.272238721827958,
      "learning_rate": 4.3214285714285713e-07,
      "logits/chosen": -1.640625,
      "logits/rejected": -1.5625,
      "logps/chosen": -169.0,
      "logps/rejected": -219.0,
      "loss": 0.0037,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.796875,
      "rewards/margins": 8.125,
      "rewards/rejected": -8.875,
      "step": 70
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.03234130751760337,
      "learning_rate": 4.142857142857143e-07,
      "logits/chosen": -1.65625,
      "logits/rejected": -1.609375,
      "logps/chosen": -151.0,
      "logps/rejected": -229.0,
      "loss": 0.0027,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.90625,
      "rewards/margins": 9.0,
      "rewards/rejected": -9.875,
      "step": 80
    },
    {
      "epoch": 0.8653846153846154,
      "grad_norm": 2.22694231928167,
      "learning_rate": 3.9642857142857137e-07,
      "logits/chosen": -1.640625,
      "logits/rejected": -1.65625,
      "logps/chosen": -154.0,
      "logps/rejected": -229.0,
      "loss": 0.0023,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.0390625,
      "rewards/margins": 8.75,
      "rewards/rejected": -9.8125,
      "step": 90
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.04456450837390773,
      "learning_rate": 3.785714285714285e-07,
      "logits/chosen": -1.671875,
      "logits/rejected": -1.6328125,
      "logps/chosen": -174.0,
      "logps/rejected": -232.0,
      "loss": 0.0029,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.87109375,
      "rewards/margins": 9.0625,
      "rewards/rejected": -9.9375,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_logits/chosen": -1.4765625,
      "eval_logits/rejected": -1.4140625,
      "eval_logps/chosen": -119.0,
      "eval_logps/rejected": -235.0,
      "eval_loss": 0.02374856546521187,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": -0.83203125,
      "eval_rewards/margins": 9.8125,
      "eval_rewards/rejected": -10.625,
      "eval_runtime": 5.2091,
      "eval_samples_per_second": 13.054,
      "eval_steps_per_second": 0.576,
      "step": 104
    }
  ],
  "logging_steps": 10,
  "max_steps": 312,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}