{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9934640522875817,
  "eval_steps": 100,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013071895424836602,
      "grad_norm": 1.4728717803955078,
      "learning_rate": 6.25e-07,
      "logits/chosen": -0.29840853810310364,
      "logits/rejected": -0.1390429139137268,
      "logps/chosen": -438.4503479003906,
      "logps/rejected": -394.85345458984375,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 1.3500034809112549,
      "learning_rate": 4.989335440737587e-06,
      "logits/chosen": -0.3996924161911011,
      "logits/rejected": -0.4485740661621094,
      "logps/chosen": -404.26904296875,
      "logps/rejected": -390.83203125,
      "loss": 0.6926,
      "rewards/accuracies": 0.5694444179534912,
      "rewards/chosen": -0.004830248653888702,
      "rewards/margins": 0.0011401758529245853,
      "rewards/rejected": -0.005970424972474575,
      "step": 10
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 1.4397944211959839,
      "learning_rate": 4.625542839324036e-06,
      "logits/chosen": -0.33299124240875244,
      "logits/rejected": -0.33779406547546387,
      "logps/chosen": -395.19940185546875,
      "logps/rejected": -350.80023193359375,
      "loss": 0.6899,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.0326865054666996,
      "rewards/margins": 0.0065984600223600864,
      "rewards/rejected": -0.03928496688604355,
      "step": 20
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 1.6657921075820923,
      "learning_rate": 3.81608040719339e-06,
      "logits/chosen": -0.38426023721694946,
      "logits/rejected": -0.4143997132778168,
      "logps/chosen": -430.2701721191406,
      "logps/rejected": -434.88592529296875,
      "loss": 0.6801,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.0653635784983635,
      "rewards/margins": 0.02730550244450569,
      "rewards/rejected": -0.09266908466815948,
      "step": 30
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 2.407362699508667,
      "learning_rate": 2.730670898658255e-06,
      "logits/chosen": -0.3544152081012726,
      "logits/rejected": -0.3963680565357208,
      "logps/chosen": -384.8106689453125,
      "logps/rejected": -388.267822265625,
      "loss": 0.681,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.12813720107078552,
      "rewards/margins": 0.02618442103266716,
      "rewards/rejected": -0.15432162582874298,
      "step": 40
    },
    {
      "epoch": 0.6535947712418301,
      "grad_norm": 1.42532217502594,
      "learning_rate": 1.5968958345321178e-06,
      "logits/chosen": -0.4702916145324707,
      "logits/rejected": -0.45878657698631287,
      "logps/chosen": -453.4817810058594,
      "logps/rejected": -400.70635986328125,
      "loss": 0.6765,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.1411454975605011,
      "rewards/margins": 0.03618112951517105,
      "rewards/rejected": -0.17732664942741394,
      "step": 50
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 1.6959117650985718,
      "learning_rate": 6.524777069483526e-07,
      "logits/chosen": -0.43231654167175293,
      "logits/rejected": -0.4735133647918701,
      "logps/chosen": -414.21063232421875,
      "logps/rejected": -430.25982666015625,
      "loss": 0.6758,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.17860133945941925,
      "rewards/margins": 0.040012918412685394,
      "rewards/rejected": -0.21861426532268524,
      "step": 60
    },
    {
      "epoch": 0.9150326797385621,
      "grad_norm": 1.7545562982559204,
      "learning_rate": 9.54358920679524e-08,
      "logits/chosen": -0.25477609038352966,
      "logits/rejected": -0.3516315817832947,
      "logps/chosen": -390.6278381347656,
      "logps/rejected": -351.927734375,
      "loss": 0.6737,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.16445334255695343,
      "rewards/margins": 0.044101499021053314,
      "rewards/rejected": -0.20855486392974854,
      "step": 70
    },
    {
      "epoch": 0.9934640522875817,
      "step": 76,
      "total_flos": 0.0,
      "train_loss": 0.6808264882940995,
      "train_runtime": 1624.4693,
      "train_samples_per_second": 0.377,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 10,
  "max_steps": 76,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}