{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 100.0,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.3850007222248957,
      "epoch": 5.0,
      "grad_norm": 5.218133926391602,
      "learning_rate": 4.85e-06,
      "logits/chosen": 0.5955334049959196,
      "logits/rejected": 0.32116526582606625,
      "logps/chosen": -41.78460889963003,
      "logps/rejected": -46.04202065101037,
      "loss": 0.5778924465179444,
      "mean_token_accuracy": 0.48216897593094754,
      "num_tokens": 3045.0,
      "rewards/accuracies": 0.676923076923077,
      "rewards/chosen": 1.8768298184642425,
      "rewards/margins": 1.1801037300091524,
      "rewards/rejected": 0.696726090231767,
      "step": 10
    },
    {
      "entropy": 2.314448336454538,
      "epoch": 10.0,
      "grad_norm": 2.3608832359313965,
      "learning_rate": 4.683333333333334e-06,
      "logits/chosen": 0.5266339006231595,
      "logits/rejected": 0.21806011517835058,
      "logps/chosen": -39.94469804030199,
      "logps/rejected": -49.08440563495343,
      "loss": 0.36816518306732177,
      "mean_token_accuracy": 0.5069385063189726,
      "num_tokens": 6090.0,
      "rewards/accuracies": 0.9692307692307692,
      "rewards/chosen": 2.0608209357811855,
      "rewards/margins": 1.668333342900643,
      "rewards/rejected": 0.3924875888579453,
      "step": 20
    },
    {
      "entropy": 2.2045343949244574,
      "epoch": 15.0,
      "grad_norm": 1.2208229303359985,
      "learning_rate": 4.516666666666667e-06,
      "logits/chosen": 0.42076279344647916,
      "logits/rejected": 0.0795841027230604,
      "logps/chosen": -38.261579630925105,
      "logps/rejected": -52.489193872305066,
      "loss": 0.25407335758209226,
      "mean_token_accuracy": 0.5410144303853696,
      "num_tokens": 9135.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.22913277057501,
      "rewards/margins": 2.1771240174770354,
      "rewards/rejected": 0.05200875710982543,
      "step": 30
    },
    {
      "entropy": 2.0643920261126296,
      "epoch": 20.0,
      "grad_norm": 1.1566054821014404,
      "learning_rate": 4.350000000000001e-06,
      "logits/chosen": 0.2660081956584437,
      "logits/rejected": -0.11877416602934321,
      "logps/chosen": -36.715302041860724,
      "logps/rejected": -56.045902252197266,
      "loss": 0.18806705474853516,
      "mean_token_accuracy": 0.5574041231320455,
      "num_tokens": 12180.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.3837605155431305,
      "rewards/margins": 2.687422578609907,
      "rewards/rejected": -0.3036620749733769,
      "step": 40
    },
    {
      "entropy": 1.9192953155590937,
      "epoch": 25.0,
      "grad_norm": 1.2787108421325684,
      "learning_rate": 4.183333333333334e-06,
      "logits/chosen": 0.06328228399595424,
      "logits/rejected": -0.36550493553391344,
      "logps/chosen": -35.36447745103102,
      "logps/rejected": -59.87469277015099,
      "loss": 0.1385887861251831,
      "mean_token_accuracy": 0.5706025022726793,
      "num_tokens": 15225.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.5188429571115054,
      "rewards/margins": 3.205384102234474,
      "rewards/rejected": -0.6865411404806834,
      "step": 50
    },
    {
      "entropy": 1.7868539026150336,
      "epoch": 30.0,
      "grad_norm": 0.8686179518699646,
      "learning_rate": 4.0166666666666675e-06,
      "logits/chosen": -0.1935140321445184,
      "logits/rejected": -0.6839043743711061,
      "logps/chosen": -34.12935148385855,
      "logps/rejected": -64.12931248591497,
      "loss": 0.0951196312904358,
      "mean_token_accuracy": 0.5941899987367484,
      "num_tokens": 18270.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.64235560802313,
      "rewards/margins": 3.754358713443463,
      "rewards/rejected": -1.112003114934151,
      "step": 60
    },
    {
      "entropy": 1.6745153069496155,
      "epoch": 35.0,
      "grad_norm": 0.9338397979736328,
      "learning_rate": 3.85e-06,
      "logits/chosen": -0.3970043551674374,
      "logits/rejected": -0.9072793044553101,
      "logps/chosen": -33.13469376197228,
      "logps/rejected": -67.47981532170222,
      "loss": 0.06889303326606751,
      "mean_token_accuracy": 0.6142469997589405,
      "num_tokens": 21315.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.7418213651730463,
      "rewards/margins": 4.188874772878793,
      "rewards/rejected": -1.4470534209806758,
      "step": 70
    },
    {
      "entropy": 1.5280305674442878,
      "epoch": 40.0,
      "grad_norm": 0.33691903948783875,
      "learning_rate": 3.6833333333333338e-06,
      "logits/chosen": -0.645527713806289,
      "logits/rejected": -1.192322842277305,
      "logps/chosen": -32.71983912541316,
      "logps/rejected": -71.29921434842623,
      "loss": 0.05013889670372009,
      "mean_token_accuracy": 0.6215091819946582,
      "num_tokens": 24360.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.783306827911964,
      "rewards/margins": 4.612300166716943,
      "rewards/rejected": -1.8289933227289181,
      "step": 80
    },
    {
      "entropy": 1.4477157487319066,
      "epoch": 45.0,
      "grad_norm": 0.0781475231051445,
      "learning_rate": 3.516666666666667e-06,
      "logits/chosen": -0.8208894431606327,
      "logits/rejected": -1.3862875261002638,
      "logps/chosen": -32.24270979074331,
      "logps/rejected": -74.3404776939979,
      "loss": 0.037910228967666625,
      "mean_token_accuracy": 0.6225866313164051,
      "num_tokens": 27405.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.831019756427178,
      "rewards/margins": 4.964139417501596,
      "rewards/rejected": -2.133119664513148,
      "step": 90
    },
    {
      "entropy": 1.3916929373374352,
      "epoch": 50.0,
      "grad_norm": 0.1870872527360916,
      "learning_rate": 3.3500000000000005e-06,
      "logits/chosen": -0.9026928408855097,
      "logits/rejected": -1.4932921680317246,
      "logps/chosen": -31.6792912703294,
      "logps/rejected": -76.95603843102089,
      "loss": 0.029496246576309205,
      "mean_token_accuracy": 0.6238097415520595,
      "num_tokens": 30450.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.8873616236906785,
      "rewards/margins": 5.282037371855516,
      "rewards/rejected": -2.3946757453708694,
      "step": 100
    },
    {
      "entropy": 1.3489822713228372,
      "epoch": 55.0,
      "grad_norm": 0.15059450268745422,
      "learning_rate": 3.183333333333334e-06,
      "logits/chosen": -0.9584337553499183,
      "logits/rejected": -1.5809670771118987,
      "logps/chosen": -31.16159066420335,
      "logps/rejected": -79.13991223848782,
      "loss": 0.025989437103271486,
      "mean_token_accuracy": 0.6313372121407436,
      "num_tokens": 33495.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.9391316624788137,
      "rewards/margins": 5.552194802577679,
      "rewards/rejected": -2.6130631179190598,
      "step": 110
    },
    {
      "entropy": 1.3076109152573805,
      "epoch": 60.0,
      "grad_norm": 0.4038887619972229,
      "learning_rate": 3.0166666666666673e-06,
      "logits/chosen": -1.0143513353856966,
      "logits/rejected": -1.6518468357354557,
      "logps/chosen": -30.717048087486855,
      "logps/rejected": -80.81175912710337,
      "loss": 0.019894377887248994,
      "mean_token_accuracy": 0.6305825824920948,
      "num_tokens": 36540.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.983585899609786,
      "rewards/margins": 5.763833695191604,
      "rewards/rejected": -2.7802478168589566,
      "step": 120
    },
    {
      "entropy": 1.2777886221042045,
      "epoch": 65.0,
      "grad_norm": 0.11832690238952637,
      "learning_rate": 2.85e-06,
      "logits/chosen": -1.0513172948777008,
      "logits/rejected": -1.70667886808449,
      "logps/chosen": -30.33043086712177,
      "logps/rejected": -82.26801863450271,
      "loss": 0.017130233347415924,
      "mean_token_accuracy": 0.6363077672628256,
      "num_tokens": 39585.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.022247677582961,
      "rewards/margins": 5.94812143949362,
      "rewards/rejected": -2.9258737678711233,
      "step": 130
    },
    {
      "entropy": 1.250800774189142,
      "epoch": 70.0,
      "grad_norm": 0.07396625727415085,
      "learning_rate": 2.683333333333333e-06,
      "logits/chosen": -1.0829184006557993,
      "logits/rejected": -1.7563719300860305,
      "logps/chosen": -30.013790159959058,
      "logps/rejected": -83.55414663461538,
      "loss": 0.014281480014324189,
      "mean_token_accuracy": 0.6392337904526637,
      "num_tokens": 42630.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.053911742797265,
      "rewards/margins": 6.1083983182907104,
      "rewards/rejected": -3.054486560019163,
      "step": 140
    },
    {
      "entropy": 1.223134689606153,
      "epoch": 75.0,
      "grad_norm": 0.05753239244222641,
      "learning_rate": 2.5166666666666666e-06,
      "logits/chosen": -1.1195608680355456,
      "logits/rejected": -1.8052698192809788,
      "logps/chosen": -29.635238119272085,
      "logps/rejected": -84.57547466571515,
      "loss": 0.012452676892280579,
      "mean_token_accuracy": 0.6391755163669586,
      "num_tokens": 45675.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.091766904867612,
      "rewards/margins": 6.248386273017297,
      "rewards/rejected": -3.1566193484343015,
      "step": 150
    },
    {
      "entropy": 1.2027296034189372,
      "epoch": 80.0,
      "grad_norm": 0.3149576485157013,
      "learning_rate": 2.35e-06,
      "logits/chosen": -1.1491697674350145,
      "logits/rejected": -1.8513586526299164,
      "logps/chosen": -29.390566752507137,
      "logps/rejected": -85.54401256854717,
      "loss": 0.010251734405755997,
      "mean_token_accuracy": 0.6281787042434399,
      "num_tokens": 48720.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.1162340833590583,
      "rewards/margins": 6.369707246927114,
      "rewards/rejected": -3.253473144081923,
      "step": 160
    },
    {
      "entropy": 1.1893031638402205,
      "epoch": 85.0,
      "grad_norm": 0.27565744519233704,
      "learning_rate": 2.1833333333333333e-06,
      "logits/chosen": -1.1672777094357023,
      "logits/rejected": -1.8822302021351611,
      "logps/chosen": -29.235072796161358,
      "logps/rejected": -86.43060050377478,
      "loss": 0.010401710867881775,
      "mean_token_accuracy": 0.6251530615183023,
      "num_tokens": 51765.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.1317834468988273,
      "rewards/margins": 6.473915430215689,
      "rewards/rejected": -3.3421319489295667,
      "step": 170
    },
    {
      "entropy": 1.1756579087330745,
      "epoch": 90.0,
      "grad_norm": 0.06536174565553665,
      "learning_rate": 2.0166666666666667e-06,
      "logits/chosen": -1.1910031234123657,
      "logits/rejected": -1.9204785576885457,
      "logps/chosen": -28.8819152538593,
      "logps/rejected": -87.1160526569073,
      "loss": 0.007509545981884002,
      "mean_token_accuracy": 0.6323185668541835,
      "num_tokens": 54810.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.167099202596224,
      "rewards/margins": 6.577776369681725,
      "rewards/rejected": -3.410677168002495,
      "step": 180
    },
    {
      "entropy": 1.1582091863338764,
      "epoch": 95.0,
      "grad_norm": 0.07627511024475098,
      "learning_rate": 1.85e-06,
      "logits/chosen": -1.2080450987055713,
      "logits/rejected": -1.953039308066732,
      "logps/chosen": -28.834403258103592,
      "logps/rejected": -87.93590979942908,
      "loss": 0.006308925151824951,
      "mean_token_accuracy": 0.6208858558764825,
      "num_tokens": 57855.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.17185040804056,
      "rewards/margins": 6.6645133348611685,
      "rewards/rejected": -3.4926629029787506,
      "step": 190
    },
    {
      "entropy": 1.1551778793334961,
      "epoch": 100.0,
      "grad_norm": 0.05331544205546379,
      "learning_rate": 1.6833333333333335e-06,
      "logits/chosen": -1.220794750164101,
      "logits/rejected": -1.981571992290679,
      "logps/chosen": -28.619847635122447,
      "logps/rejected": -88.4375508235051,
      "loss": 0.0059698235243558885,
      "mean_token_accuracy": 0.6226402415679051,
      "num_tokens": 60900.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.1933059848271883,
      "rewards/margins": 6.736132926207322,
      "rewards/rejected": -3.542826987229861,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "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": 559692824371200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}