{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 306,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 1.4516129032258065e-05,
      "logits/chosen": -2.4829204082489014,
      "logits/rejected": -2.623030185699463,
      "logps/chosen": -55.93037033081055,
      "logps/rejected": -33.53595733642578,
      "loss": 0.5107,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": 0.15422411262989044,
      "rewards/margins": 0.5176956057548523,
      "rewards/rejected": -0.36347147822380066,
      "step": 20
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.9563636363636365e-05,
      "logits/chosen": -2.385016918182373,
      "logits/rejected": -2.5468831062316895,
      "logps/chosen": -34.7657585144043,
      "logps/rejected": -52.43476104736328,
      "loss": 0.0274,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.29936146736145,
      "rewards/margins": 4.539745807647705,
      "rewards/rejected": -2.240384578704834,
      "step": 40
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.7381818181818182e-05,
      "logits/chosen": -2.2574870586395264,
      "logits/rejected": -2.420015811920166,
      "logps/chosen": -13.00920295715332,
      "logps/rejected": -70.32115936279297,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.496087074279785,
      "rewards/margins": 8.517866134643555,
      "rewards/rejected": -4.021780490875244,
      "step": 60
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.52e-05,
      "logits/chosen": -2.2138588428497314,
      "logits/rejected": -2.3903181552886963,
      "logps/chosen": -8.080777168273926,
      "logps/rejected": -77.32413482666016,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.011228084564209,
      "rewards/margins": 9.755220413208008,
      "rewards/rejected": -4.743992805480957,
      "step": 80
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.3018181818181816e-05,
      "logits/chosen": -2.1865017414093018,
      "logits/rejected": -2.3809409141540527,
      "logps/chosen": -7.149311065673828,
      "logps/rejected": -79.04914093017578,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.135758399963379,
      "rewards/margins": 10.058463096618652,
      "rewards/rejected": -4.922704696655273,
      "step": 100
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.0836363636363637e-05,
      "logits/chosen": -2.204026699066162,
      "logits/rejected": -2.377389430999756,
      "logps/chosen": -6.087798118591309,
      "logps/rejected": -80.18804931640625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.203327655792236,
      "rewards/margins": 10.240509986877441,
      "rewards/rejected": -5.037181854248047,
      "step": 120
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.8654545454545454e-05,
      "logits/chosen": -2.190598964691162,
      "logits/rejected": -2.3737359046936035,
      "logps/chosen": -5.493344306945801,
      "logps/rejected": -81.6736831665039,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.198002815246582,
      "rewards/margins": 10.370179176330566,
      "rewards/rejected": -5.172175884246826,
      "step": 140
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.647272727272727e-05,
      "logits/chosen": -2.198334217071533,
      "logits/rejected": -2.3750014305114746,
      "logps/chosen": -5.27658224105835,
      "logps/rejected": -83.0462417602539,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.275361061096191,
      "rewards/margins": 10.579935073852539,
      "rewards/rejected": -5.304574012756348,
      "step": 160
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.4290909090909092e-05,
      "logits/chosen": -2.1648800373077393,
      "logits/rejected": -2.3531603813171387,
      "logps/chosen": -5.335925579071045,
      "logps/rejected": -83.67100524902344,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.311135768890381,
      "rewards/margins": 10.685991287231445,
      "rewards/rejected": -5.374855041503906,
      "step": 180
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.210909090909091e-05,
      "logits/chosen": -2.1698648929595947,
      "logits/rejected": -2.350588798522949,
      "logps/chosen": -5.037841796875,
      "logps/rejected": -84.4847183227539,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.284677982330322,
      "rewards/margins": 10.73720932006836,
      "rewards/rejected": -5.4525299072265625,
      "step": 200
    },
    {
      "epoch": 2.16,
      "learning_rate": 9.927272727272728e-06,
      "logits/chosen": -2.172761917114258,
      "logits/rejected": -2.3548429012298584,
      "logps/chosen": -4.5183844566345215,
      "logps/rejected": -85.39585876464844,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.35943603515625,
      "rewards/margins": 10.907907485961914,
      "rewards/rejected": -5.5484724044799805,
      "step": 220
    },
    {
      "epoch": 2.35,
      "learning_rate": 7.745454545454545e-06,
      "logits/chosen": -2.176955223083496,
      "logits/rejected": -2.3584964275360107,
      "logps/chosen": -4.64106559753418,
      "logps/rejected": -85.82803344726562,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.32342004776001,
      "rewards/margins": 10.914727210998535,
      "rewards/rejected": -5.591307640075684,
      "step": 240
    },
    {
      "epoch": 2.55,
      "learning_rate": 5.563636363636363e-06,
      "logits/chosen": -2.137197494506836,
      "logits/rejected": -2.3419229984283447,
      "logps/chosen": -4.342270374298096,
      "logps/rejected": -85.80111694335938,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.375523567199707,
      "rewards/margins": 10.970113754272461,
      "rewards/rejected": -5.594590663909912,
      "step": 260
    },
    {
      "epoch": 2.75,
      "learning_rate": 3.381818181818182e-06,
      "logits/chosen": -2.18381404876709,
      "logits/rejected": -2.362435817718506,
      "logps/chosen": -4.8146867752075195,
      "logps/rejected": -86.47946166992188,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.325329303741455,
      "rewards/margins": 10.978459358215332,
      "rewards/rejected": -5.653130531311035,
      "step": 280
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.2000000000000002e-06,
      "logits/chosen": -2.179290294647217,
      "logits/rejected": -2.3513832092285156,
      "logps/chosen": -4.198988437652588,
      "logps/rejected": -86.9154052734375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.389545917510986,
      "rewards/margins": 11.077142715454102,
      "rewards/rejected": -5.687596321105957,
      "step": 300
    }
  ],
  "logging_steps": 20,
  "max_steps": 306,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}