{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.31391014322150285,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015695507161075144,
      "grad_norm": 0.07061820477247238,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 15.001790046691895,
      "logits/rejected": 14.624488830566406,
      "logps/chosen": -0.33085882663726807,
      "logps/rejected": -0.24924471974372864,
      "loss": 1.0519,
      "rewards/accuracies": 0.23749999701976776,
      "rewards/chosen": -0.4962882399559021,
      "rewards/margins": -0.12242116779088974,
      "rewards/rejected": -0.37386709451675415,
      "step": 10
    },
    {
      "epoch": 0.03139101432215029,
      "grad_norm": 0.060370542109012604,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 15.272351264953613,
      "logits/rejected": 14.801017761230469,
      "logps/chosen": -0.3379867672920227,
      "logps/rejected": -0.24759705364704132,
      "loss": 1.0494,
      "rewards/accuracies": 0.15000000596046448,
      "rewards/chosen": -0.5069801211357117,
      "rewards/margins": -0.13558456301689148,
      "rewards/rejected": -0.3713955581188202,
      "step": 20
    },
    {
      "epoch": 0.047086521483225424,
      "grad_norm": 0.050332240760326385,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 15.569372177124023,
      "logits/rejected": 15.249380111694336,
      "logps/chosen": -0.3347483277320862,
      "logps/rejected": -0.275604784488678,
      "loss": 1.0375,
      "rewards/accuracies": 0.21250000596046448,
      "rewards/chosen": -0.5021225214004517,
      "rewards/margins": -0.08871528506278992,
      "rewards/rejected": -0.41340717673301697,
      "step": 30
    },
    {
      "epoch": 0.06278202864430057,
      "grad_norm": 0.054660990834236145,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 15.344067573547363,
      "logits/rejected": 14.881669998168945,
      "logps/chosen": -0.3336474299430847,
      "logps/rejected": -0.27252259850502014,
      "loss": 1.0375,
      "rewards/accuracies": 0.20000000298023224,
      "rewards/chosen": -0.5004712343215942,
      "rewards/margins": -0.09168727695941925,
      "rewards/rejected": -0.40878385305404663,
      "step": 40
    },
    {
      "epoch": 0.07847753580537571,
      "grad_norm": 0.060405269265174866,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 15.5701904296875,
      "logits/rejected": 15.60998821258545,
      "logps/chosen": -0.3075069785118103,
      "logps/rejected": -0.24850216507911682,
      "loss": 1.0341,
      "rewards/accuracies": 0.20000000298023224,
      "rewards/chosen": -0.46126049757003784,
      "rewards/margins": -0.08850721269845963,
      "rewards/rejected": -0.3727532923221588,
      "step": 50
    },
    {
      "epoch": 0.07847753580537571,
      "eval_logits/chosen": 15.719181060791016,
      "eval_logits/rejected": 15.20205307006836,
      "eval_logps/chosen": -0.32490479946136475,
      "eval_logps/rejected": -0.26058924198150635,
      "eval_loss": 1.0295902490615845,
      "eval_rewards/accuracies": 0.26923078298568726,
      "eval_rewards/chosen": -0.48735716938972473,
      "eval_rewards/margins": -0.09647335112094879,
      "eval_rewards/rejected": -0.39088380336761475,
      "eval_runtime": 14.6102,
      "eval_samples_per_second": 28.199,
      "eval_steps_per_second": 3.559,
      "step": 50
    },
    {
      "epoch": 0.09417304296645085,
      "grad_norm": 0.06511708348989487,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 15.571348190307617,
      "logits/rejected": 15.418828010559082,
      "logps/chosen": -0.3217025101184845,
      "logps/rejected": -0.2813836932182312,
      "loss": 1.0385,
      "rewards/accuracies": 0.23749999701976776,
      "rewards/chosen": -0.48255378007888794,
      "rewards/margins": -0.060478221625089645,
      "rewards/rejected": -0.4220755696296692,
      "step": 60
    },
    {
      "epoch": 0.109868550127526,
      "grad_norm": 0.06922140717506409,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 15.926614761352539,
      "logits/rejected": 15.90565299987793,
      "logps/chosen": -0.34742942452430725,
      "logps/rejected": -0.26853513717651367,
      "loss": 1.0417,
      "rewards/accuracies": 0.21250000596046448,
      "rewards/chosen": -0.5211440324783325,
      "rewards/margins": -0.11834144592285156,
      "rewards/rejected": -0.40280264616012573,
      "step": 70
    },
    {
      "epoch": 0.12556405728860115,
      "grad_norm": 0.07853339612483978,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 15.876957893371582,
      "logits/rejected": 15.636863708496094,
      "logps/chosen": -0.34999752044677734,
      "logps/rejected": -0.2652502655982971,
      "loss": 1.0255,
      "rewards/accuracies": 0.1875,
      "rewards/chosen": -0.524996280670166,
      "rewards/margins": -0.12712089717388153,
      "rewards/rejected": -0.3978753685951233,
      "step": 80
    },
    {
      "epoch": 0.14125956444967627,
      "grad_norm": 0.07262148708105087,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 16.037456512451172,
      "logits/rejected": 15.742408752441406,
      "logps/chosen": -0.32482510805130005,
      "logps/rejected": -0.2520079016685486,
      "loss": 1.0297,
      "rewards/accuracies": 0.21250000596046448,
      "rewards/chosen": -0.48723769187927246,
      "rewards/margins": -0.1092257872223854,
      "rewards/rejected": -0.3780118525028229,
      "step": 90
    },
    {
      "epoch": 0.15695507161075142,
      "grad_norm": 0.08407289534807205,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 16.34904670715332,
      "logits/rejected": 16.30767059326172,
      "logps/chosen": -0.3302846848964691,
      "logps/rejected": -0.2799247205257416,
      "loss": 1.0285,
      "rewards/accuracies": 0.2750000059604645,
      "rewards/chosen": -0.4954269826412201,
      "rewards/margins": -0.07553993165493011,
      "rewards/rejected": -0.41988706588745117,
      "step": 100
    },
    {
      "epoch": 0.15695507161075142,
      "eval_logits/chosen": 16.43848419189453,
      "eval_logits/rejected": 15.978095054626465,
      "eval_logps/chosen": -0.3256901502609253,
      "eval_logps/rejected": -0.2794351279735565,
      "eval_loss": 1.0174708366394043,
      "eval_rewards/accuracies": 0.2884615361690521,
      "eval_rewards/chosen": -0.4885352551937103,
      "eval_rewards/margins": -0.06938254088163376,
      "eval_rewards/rejected": -0.41915270686149597,
      "eval_runtime": 14.607,
      "eval_samples_per_second": 28.206,
      "eval_steps_per_second": 3.56,
      "step": 100
    },
    {
      "epoch": 0.17265057877182657,
      "grad_norm": 0.07448805868625641,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 16.681476593017578,
      "logits/rejected": 16.208908081054688,
      "logps/chosen": -0.3410753309726715,
      "logps/rejected": -0.28177398443222046,
      "loss": 1.0364,
      "rewards/accuracies": 0.2874999940395355,
      "rewards/chosen": -0.5116130113601685,
      "rewards/margins": -0.08895199000835419,
      "rewards/rejected": -0.4226610064506531,
      "step": 110
    },
    {
      "epoch": 0.1883460859329017,
      "grad_norm": 0.17266640067100525,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 16.73276710510254,
      "logits/rejected": 16.46255111694336,
      "logps/chosen": -0.30808666348457336,
      "logps/rejected": -0.2663067877292633,
      "loss": 1.0242,
      "rewards/accuracies": 0.23749999701976776,
      "rewards/chosen": -0.46213001012802124,
      "rewards/margins": -0.0626697838306427,
      "rewards/rejected": -0.39946022629737854,
      "step": 120
    },
    {
      "epoch": 0.20404159309397685,
      "grad_norm": 0.1035998985171318,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 16.380239486694336,
      "logits/rejected": 16.233612060546875,
      "logps/chosen": -0.32250356674194336,
      "logps/rejected": -0.27460020780563354,
      "loss": 1.0162,
      "rewards/accuracies": 0.2874999940395355,
      "rewards/chosen": -0.48375529050827026,
      "rewards/margins": -0.0718550831079483,
      "rewards/rejected": -0.41190028190612793,
      "step": 130
    },
    {
      "epoch": 0.219737100255052,
      "grad_norm": 0.0961030125617981,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 16.440303802490234,
      "logits/rejected": 16.233903884887695,
      "logps/chosen": -0.33421438932418823,
      "logps/rejected": -0.2857271134853363,
      "loss": 1.0008,
      "rewards/accuracies": 0.3125,
      "rewards/chosen": -0.5013214945793152,
      "rewards/margins": -0.07273083180189133,
      "rewards/rejected": -0.42859068512916565,
      "step": 140
    },
    {
      "epoch": 0.23543260741612712,
      "grad_norm": 0.14799565076828003,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 16.600738525390625,
      "logits/rejected": 16.536447525024414,
      "logps/chosen": -0.3243326246738434,
      "logps/rejected": -0.3061785101890564,
      "loss": 1.0085,
      "rewards/accuracies": 0.3375000059604645,
      "rewards/chosen": -0.4864989221096039,
      "rewards/margins": -0.027231160551309586,
      "rewards/rejected": -0.459267795085907,
      "step": 150
    },
    {
      "epoch": 0.23543260741612712,
      "eval_logits/chosen": 16.8078556060791,
      "eval_logits/rejected": 16.311922073364258,
      "eval_logps/chosen": -0.326242595911026,
      "eval_logps/rejected": -0.3398977816104889,
      "eval_loss": 0.9791463017463684,
      "eval_rewards/accuracies": 0.4038461446762085,
      "eval_rewards/chosen": -0.4893638789653778,
      "eval_rewards/margins": 0.020482787862420082,
      "eval_rewards/rejected": -0.5098467469215393,
      "eval_runtime": 14.6072,
      "eval_samples_per_second": 28.205,
      "eval_steps_per_second": 3.56,
      "step": 150
    },
    {
      "epoch": 0.2511281145772023,
      "grad_norm": 0.11464422941207886,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": 16.586620330810547,
      "logits/rejected": 16.253028869628906,
      "logps/chosen": -0.33331993222236633,
      "logps/rejected": -0.35580095648765564,
      "loss": 0.9827,
      "rewards/accuracies": 0.42500001192092896,
      "rewards/chosen": -0.49997982382774353,
      "rewards/margins": 0.03372158855199814,
      "rewards/rejected": -0.5337014198303223,
      "step": 160
    },
    {
      "epoch": 0.2668236217382774,
      "grad_norm": 0.09462621062994003,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": 16.220312118530273,
      "logits/rejected": 16.105356216430664,
      "logps/chosen": -0.2957116663455963,
      "logps/rejected": -0.3528788089752197,
      "loss": 0.9716,
      "rewards/accuracies": 0.4625000059604645,
      "rewards/chosen": -0.44356757402420044,
      "rewards/margins": 0.08575066924095154,
      "rewards/rejected": -0.5293182134628296,
      "step": 170
    },
    {
      "epoch": 0.28251912889935255,
      "grad_norm": 0.10995513945817947,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": 16.811044692993164,
      "logits/rejected": 16.43205451965332,
      "logps/chosen": -0.3263992369174957,
      "logps/rejected": -0.35878634452819824,
      "loss": 0.9546,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.4895988404750824,
      "rewards/margins": 0.04858064278960228,
      "rewards/rejected": -0.5381795167922974,
      "step": 180
    },
    {
      "epoch": 0.2982146360604277,
      "grad_norm": 0.1348036825656891,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": 16.816158294677734,
      "logits/rejected": 16.55413055419922,
      "logps/chosen": -0.31842875480651855,
      "logps/rejected": -0.3791810870170593,
      "loss": 0.9472,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.47764310240745544,
      "rewards/margins": 0.09112847596406937,
      "rewards/rejected": -0.5687715411186218,
      "step": 190
    },
    {
      "epoch": 0.31391014322150285,
      "grad_norm": 0.13393694162368774,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": 17.075885772705078,
      "logits/rejected": 16.982004165649414,
      "logps/chosen": -0.3368823528289795,
      "logps/rejected": -0.3636801540851593,
      "loss": 0.9455,
      "rewards/accuracies": 0.375,
      "rewards/chosen": -0.5053235292434692,
      "rewards/margins": 0.04019671678543091,
      "rewards/rejected": -0.5455202460289001,
      "step": 200
    },
    {
      "epoch": 0.31391014322150285,
      "eval_logits/chosen": 17.17239761352539,
      "eval_logits/rejected": 16.609193801879883,
      "eval_logps/chosen": -0.33508703112602234,
      "eval_logps/rejected": -0.4493505656719208,
      "eval_loss": 0.9283667802810669,
      "eval_rewards/accuracies": 0.4615384638309479,
      "eval_rewards/chosen": -0.5026305913925171,
      "eval_rewards/margins": 0.17139528691768646,
      "eval_rewards/rejected": -0.67402583360672,
      "eval_runtime": 14.5913,
      "eval_samples_per_second": 28.236,
      "eval_steps_per_second": 3.564,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.7951015917807206e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}