{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6766169154228856,
  "eval_steps": 500,
  "global_step": 1700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03980099502487562,
      "grad_norm": 1.5459058284759521,
      "learning_rate": 4.980474401576887e-07,
      "logits/chosen": -1.4838274717330933,
      "logits/rejected": -1.5693057775497437,
      "logps/chosen": -190.30685424804688,
      "logps/rejected": -190.12179565429688,
      "loss": 0.7107,
      "rewards/accuracies": 0.49312499165534973,
      "rewards/chosen": -0.8337415456771851,
      "rewards/margins": 0.0017802910879254341,
      "rewards/rejected": -0.8355217576026917,
      "step": 100
    },
    {
      "epoch": 0.07960199004975124,
      "grad_norm": 1.247958779335022,
      "learning_rate": 4.922202605502572e-07,
      "logits/chosen": -1.4577226638793945,
      "logits/rejected": -1.544972538948059,
      "logps/chosen": -191.1748504638672,
      "logps/rejected": -191.21063232421875,
      "loss": 0.7063,
      "rewards/accuracies": 0.5017187595367432,
      "rewards/chosen": -0.7915948629379272,
      "rewards/margins": 0.004952423740178347,
      "rewards/rejected": -0.7965472340583801,
      "step": 200
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 1.1431488990783691,
      "learning_rate": 4.82609484512869e-07,
      "logits/chosen": -1.4753738641738892,
      "logits/rejected": -1.5457732677459717,
      "logps/chosen": -189.42088317871094,
      "logps/rejected": -190.7891082763672,
      "loss": 0.7009,
      "rewards/accuracies": 0.5146874785423279,
      "rewards/chosen": -0.7856764197349548,
      "rewards/margins": 0.013686330057680607,
      "rewards/rejected": -0.7993627190589905,
      "step": 300
    },
    {
      "epoch": 0.15920398009950248,
      "grad_norm": 1.1773804426193237,
      "learning_rate": 4.6936523696827614e-07,
      "logits/chosen": -1.4836928844451904,
      "logits/rejected": -1.5391887426376343,
      "logps/chosen": -191.47879028320312,
      "logps/rejected": -192.72312927246094,
      "loss": 0.7031,
      "rewards/accuracies": 0.4935937523841858,
      "rewards/chosen": -0.7633911967277527,
      "rewards/margins": 0.00844556000083685,
      "rewards/rejected": -0.7718366384506226,
      "step": 400
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.1332217454910278,
      "learning_rate": 4.5269439940365644e-07,
      "logits/chosen": -1.5031734704971313,
      "logits/rejected": -1.5771981477737427,
      "logps/chosen": -188.72503662109375,
      "logps/rejected": -188.9233856201172,
      "loss": 0.6982,
      "rewards/accuracies": 0.5159375071525574,
      "rewards/chosen": -0.7517531514167786,
      "rewards/margins": 0.017128920182585716,
      "rewards/rejected": -0.7688820362091064,
      "step": 500
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 1.1783969402313232,
      "learning_rate": 4.328573782827409e-07,
      "logits/chosen": -1.4775351285934448,
      "logits/rejected": -1.5578263998031616,
      "logps/chosen": -187.82449340820312,
      "logps/rejected": -186.08935546875,
      "loss": 0.6956,
      "rewards/accuracies": 0.5301562547683716,
      "rewards/chosen": -0.7211830615997314,
      "rewards/margins": 0.02292461320757866,
      "rewards/rejected": -0.744107723236084,
      "step": 600
    },
    {
      "epoch": 0.27860696517412936,
      "grad_norm": 1.2275896072387695,
      "learning_rate": 4.1016403737218373e-07,
      "logits/chosen": -1.4353595972061157,
      "logits/rejected": -1.5325896739959717,
      "logps/chosen": -190.53240966796875,
      "logps/rejected": -186.2373504638672,
      "loss": 0.6918,
      "rewards/accuracies": 0.5306249856948853,
      "rewards/chosen": -0.7291114926338196,
      "rewards/margins": 0.02977893128991127,
      "rewards/rejected": -0.7588903903961182,
      "step": 700
    },
    {
      "epoch": 0.31840796019900497,
      "grad_norm": 1.2193249464035034,
      "learning_rate": 3.849688575211836e-07,
      "logits/chosen": -1.4531009197235107,
      "logits/rejected": -1.528568148612976,
      "logps/chosen": -193.5086669921875,
      "logps/rejected": -190.48219299316406,
      "loss": 0.6947,
      "rewards/accuracies": 0.5360937714576721,
      "rewards/chosen": -0.7271183729171753,
      "rewards/margins": 0.027006981894373894,
      "rewards/rejected": -0.7541253566741943,
      "step": 800
    },
    {
      "epoch": 0.3582089552238806,
      "grad_norm": 1.3636894226074219,
      "learning_rate": 3.576653995009154e-07,
      "logits/chosen": -1.4581520557403564,
      "logits/rejected": -1.5382471084594727,
      "logps/chosen": -186.9196319580078,
      "logps/rejected": -187.58917236328125,
      "loss": 0.6881,
      "rewards/accuracies": 0.538281261920929,
      "rewards/chosen": -0.7291906476020813,
      "rewards/margins": 0.039425306022167206,
      "rewards/rejected": -0.7686160802841187,
      "step": 900
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 1.2546725273132324,
      "learning_rate": 3.286801563968721e-07,
      "logits/chosen": -1.4330791234970093,
      "logits/rejected": -1.5031362771987915,
      "logps/chosen": -190.80686950683594,
      "logps/rejected": -189.16189575195312,
      "loss": 0.692,
      "rewards/accuracies": 0.5220312476158142,
      "rewards/chosen": -0.7390533685684204,
      "rewards/margins": 0.03137853741645813,
      "rewards/rejected": -0.7704318165779114,
      "step": 1000
    },
    {
      "epoch": 0.43781094527363185,
      "grad_norm": 1.1531291007995605,
      "learning_rate": 2.9846589158269034e-07,
      "logits/chosen": -1.4307806491851807,
      "logits/rejected": -1.5092757940292358,
      "logps/chosen": -193.00648498535156,
      "logps/rejected": -189.84764099121094,
      "loss": 0.6892,
      "rewards/accuracies": 0.5384374856948853,
      "rewards/chosen": -0.7566314935684204,
      "rewards/margins": 0.03836291283369064,
      "rewards/rejected": -0.7949943542480469,
      "step": 1100
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 1.5831681489944458,
      "learning_rate": 2.674945663394993e-07,
      "logits/chosen": -1.430738925933838,
      "logits/rejected": -1.5082927942276,
      "logps/chosen": -189.89476013183594,
      "logps/rejected": -186.1005096435547,
      "loss": 0.6903,
      "rewards/accuracies": 0.5414062738418579,
      "rewards/chosen": -0.754692018032074,
      "rewards/margins": 0.03536057472229004,
      "rewards/rejected": -0.790052592754364,
      "step": 1200
    },
    {
      "epoch": 0.5174129353233831,
      "grad_norm": 1.3418159484863281,
      "learning_rate": 2.3624996759476285e-07,
      "logits/chosen": -1.4191877841949463,
      "logits/rejected": -1.501223087310791,
      "logps/chosen": -190.763671875,
      "logps/rejected": -188.54310607910156,
      "loss": 0.6848,
      "rewards/accuracies": 0.5510937571525574,
      "rewards/chosen": -0.7421095967292786,
      "rewards/margins": 0.05018935725092888,
      "rewards/rejected": -0.7922989726066589,
      "step": 1300
    },
    {
      "epoch": 0.5572139303482587,
      "grad_norm": 1.0886973142623901,
      "learning_rate": 2.0522015093886614e-07,
      "logits/chosen": -1.4274046421051025,
      "logits/rejected": -1.511489748954773,
      "logps/chosen": -190.62181091308594,
      "logps/rejected": -189.4832000732422,
      "loss": 0.6884,
      "rewards/accuracies": 0.5412499904632568,
      "rewards/chosen": -0.742114782333374,
      "rewards/margins": 0.042963698506355286,
      "rewards/rejected": -0.7850785255432129,
      "step": 1400
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 1.2839570045471191,
      "learning_rate": 1.7488981696314154e-07,
      "logits/chosen": -1.4310470819473267,
      "logits/rejected": -1.504390001296997,
      "logps/chosen": -190.2706298828125,
      "logps/rejected": -188.0977020263672,
      "loss": 0.6868,
      "rewards/accuracies": 0.547656238079071,
      "rewards/chosen": -0.7403038144111633,
      "rewards/margins": 0.04620310664176941,
      "rewards/rejected": -0.7865069508552551,
      "step": 1500
    },
    {
      "epoch": 0.6368159203980099,
      "grad_norm": 1.2762988805770874,
      "learning_rate": 1.4573274000458839e-07,
      "logits/chosen": -1.4215110540390015,
      "logits/rejected": -1.5031652450561523,
      "logps/chosen": -189.7293701171875,
      "logps/rejected": -189.09996032714844,
      "loss": 0.6835,
      "rewards/accuracies": 0.5501562356948853,
      "rewards/chosen": -0.7511222958564758,
      "rewards/margins": 0.05315619334578514,
      "rewards/rejected": -0.8042784929275513,
      "step": 1600
    },
    {
      "epoch": 0.6766169154228856,
      "grad_norm": 1.517782211303711,
      "learning_rate": 1.1820436756391414e-07,
      "logits/chosen": -1.385495901107788,
      "logits/rejected": -1.4789422750473022,
      "logps/chosen": -193.28277587890625,
      "logps/rejected": -189.7715606689453,
      "loss": 0.6848,
      "rewards/accuracies": 0.5560937523841858,
      "rewards/chosen": -0.7423578500747681,
      "rewards/margins": 0.052127428352832794,
      "rewards/rejected": -0.794485330581665,
      "step": 1700
    }
  ],
  "logging_steps": 100,
  "max_steps": 2512,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}