checkpoint-600/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9417304296645085,
  "eval_steps": 50,
  "global_step": 600,
  "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
    },
    {
      "epoch": 0.329605650382578,
      "grad_norm": 0.14985737204551697,
      "learning_rate": 4.762067631165049e-06,
      "logits/chosen": 16.92913246154785,
      "logits/rejected": 16.648632049560547,
      "logps/chosen": -0.3326043486595154,
      "logps/rejected": -0.4218205511569977,
      "loss": 0.9225,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.4989064335823059,
      "rewards/margins": 0.13382436335086823,
      "rewards/rejected": -0.6327308416366577,
      "step": 210
    },
    {
      "epoch": 0.34530115754365315,
      "grad_norm": 0.16972233355045319,
      "learning_rate": 4.7392794005985324e-06,
      "logits/chosen": 17.074562072753906,
      "logits/rejected": 16.863161087036133,
      "logps/chosen": -0.3645358383655548,
      "logps/rejected": -0.5221719145774841,
      "loss": 0.9264,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.5468038320541382,
      "rewards/margins": 0.23645417392253876,
      "rewards/rejected": -0.7832580208778381,
      "step": 220
    },
    {
      "epoch": 0.3609966647047283,
      "grad_norm": 0.20796354115009308,
      "learning_rate": 4.715508948078037e-06,
      "logits/chosen": 17.4168643951416,
      "logits/rejected": 17.00813102722168,
      "logps/chosen": -0.35443297028541565,
      "logps/rejected": -0.5115998983383179,
      "loss": 0.9037,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.5316494703292847,
      "rewards/margins": 0.23575039207935333,
      "rewards/rejected": -0.767399787902832,
      "step": 230
    },
    {
      "epoch": 0.3766921718658034,
      "grad_norm": 0.1932348757982254,
      "learning_rate": 4.690766700109659e-06,
      "logits/chosen": 17.034719467163086,
      "logits/rejected": 16.65166664123535,
      "logps/chosen": -0.3426091969013214,
      "logps/rejected": -0.47884297370910645,
      "loss": 0.9154,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.5139138102531433,
      "rewards/margins": 0.20435063540935516,
      "rewards/rejected": -0.7182644605636597,
      "step": 240
    },
    {
      "epoch": 0.39238767902687854,
      "grad_norm": 1.016450047492981,
      "learning_rate": 4.665063509461098e-06,
      "logits/chosen": 16.935081481933594,
      "logits/rejected": 16.65024185180664,
      "logps/chosen": -0.41738080978393555,
      "logps/rejected": -0.48515433073043823,
      "loss": 0.8774,
      "rewards/accuracies": 0.42500001192092896,
      "rewards/chosen": -0.6260712146759033,
      "rewards/margins": 0.10166029632091522,
      "rewards/rejected": -0.7277315258979797,
      "step": 250
    },
    {
      "epoch": 0.39238767902687854,
      "eval_logits/chosen": 17.221881866455078,
      "eval_logits/rejected": 16.536666870117188,
      "eval_logps/chosen": -0.3716265559196472,
      "eval_logps/rejected": -0.87992262840271,
      "eval_loss": 0.8047741651535034,
      "eval_rewards/accuracies": 0.5,
      "eval_rewards/chosen": -0.5574398636817932,
      "eval_rewards/margins": 0.7624441981315613,
      "eval_rewards/rejected": -1.3198840618133545,
      "eval_runtime": 14.6008,
      "eval_samples_per_second": 28.218,
      "eval_steps_per_second": 3.561,
      "step": 250
    },
    {
      "epoch": 0.4080831861879537,
      "grad_norm": 0.2831684648990631,
      "learning_rate": 4.638410650401267e-06,
      "logits/chosen": 17.084096908569336,
      "logits/rejected": 16.564823150634766,
      "logps/chosen": -0.38100525736808777,
      "logps/rejected": -0.8173269033432007,
      "loss": 0.8197,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.5715079307556152,
      "rewards/margins": 0.6544824838638306,
      "rewards/rejected": -1.2259904146194458,
      "step": 260
    },
    {
      "epoch": 0.42377869334902885,
      "grad_norm": 0.9195305109024048,
      "learning_rate": 4.610819813755038e-06,
      "logits/chosen": 17.316537857055664,
      "logits/rejected": 16.623016357421875,
      "logps/chosen": -0.4713365435600281,
      "logps/rejected": -1.2184536457061768,
      "loss": 0.7493,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.7070047855377197,
      "rewards/margins": 1.120675802230835,
      "rewards/rejected": -1.8276805877685547,
      "step": 270
    },
    {
      "epoch": 0.439474200510104,
      "grad_norm": 0.5542411804199219,
      "learning_rate": 4.582303101775249e-06,
      "logits/chosen": 17.173168182373047,
      "logits/rejected": 16.759702682495117,
      "logps/chosen": -0.4629506468772888,
      "logps/rejected": -1.3020483255386353,
      "loss": 0.7638,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.6944260597229004,
      "rewards/margins": 1.2586463689804077,
      "rewards/rejected": -1.9530725479125977,
      "step": 280
    },
    {
      "epoch": 0.45516970767117915,
      "grad_norm": 0.2836654782295227,
      "learning_rate": 4.55287302283426e-06,
      "logits/chosen": 17.022424697875977,
      "logits/rejected": 16.43834114074707,
      "logps/chosen": -0.527222216129303,
      "logps/rejected": -1.632965087890625,
      "loss": 0.7466,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.7908332943916321,
      "rewards/margins": 1.6586145162582397,
      "rewards/rejected": -2.4494476318359375,
      "step": 290
    },
    {
      "epoch": 0.47086521483225424,
      "grad_norm": 0.658358097076416,
      "learning_rate": 4.522542485937369e-06,
      "logits/chosen": 16.6541690826416,
      "logits/rejected": 16.34103012084961,
      "logps/chosen": -0.50589519739151,
      "logps/rejected": -1.8910831212997437,
      "loss": 0.6982,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -0.7588427662849426,
      "rewards/margins": 2.077782154083252,
      "rewards/rejected": -2.8366246223449707,
      "step": 300
    },
    {
      "epoch": 0.47086521483225424,
      "eval_logits/chosen": 16.950870513916016,
      "eval_logits/rejected": 16.154659271240234,
      "eval_logps/chosen": -0.5594518184661865,
      "eval_logps/rejected": -1.9617934226989746,
      "eval_loss": 0.7422243356704712,
      "eval_rewards/accuracies": 0.7115384340286255,
      "eval_rewards/chosen": -0.839177668094635,
      "eval_rewards/margins": 2.103512763977051,
      "eval_rewards/rejected": -2.942690372467041,
      "eval_runtime": 14.5969,
      "eval_samples_per_second": 28.225,
      "eval_steps_per_second": 3.562,
      "step": 300
    },
    {
      "epoch": 0.4865607219933294,
      "grad_norm": 1.1044840812683105,
      "learning_rate": 4.491324795060491e-06,
      "logits/chosen": 17.233802795410156,
      "logits/rejected": 16.292484283447266,
      "logps/chosen": -0.5940151214599609,
      "logps/rejected": -2.041588306427002,
      "loss": 0.7415,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.8910226821899414,
      "rewards/margins": 2.1713600158691406,
      "rewards/rejected": -3.062382459640503,
      "step": 310
    },
    {
      "epoch": 0.5022562291544046,
      "grad_norm": 0.524356484413147,
      "learning_rate": 4.4592336433146e-06,
      "logits/chosen": 17.155719757080078,
      "logits/rejected": 16.328996658325195,
      "logps/chosen": -0.6095865964889526,
      "logps/rejected": -1.831730604171753,
      "loss": 0.7249,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.9143797755241394,
      "rewards/margins": 1.8332160711288452,
      "rewards/rejected": -2.747596025466919,
      "step": 320
    },
    {
      "epoch": 0.5179517363154797,
      "grad_norm": 0.4383145570755005,
      "learning_rate": 4.426283106939474e-06,
      "logits/chosen": 16.774551391601562,
      "logits/rejected": 16.532238006591797,
      "logps/chosen": -0.669482946395874,
      "logps/rejected": -1.7058660984039307,
      "loss": 0.6868,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -1.004224419593811,
      "rewards/margins": 1.5545748472213745,
      "rewards/rejected": -2.5587992668151855,
      "step": 330
    },
    {
      "epoch": 0.5336472434765548,
      "grad_norm": 3.194026231765747,
      "learning_rate": 4.3924876391293915e-06,
      "logits/chosen": 16.963787078857422,
      "logits/rejected": 16.3092041015625,
      "logps/chosen": -0.7091449499130249,
      "logps/rejected": -2.1812453269958496,
      "loss": 0.706,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -1.0637174844741821,
      "rewards/margins": 2.208150863647461,
      "rewards/rejected": -3.2718684673309326,
      "step": 340
    },
    {
      "epoch": 0.5493427506376299,
      "grad_norm": 0.5639687776565552,
      "learning_rate": 4.357862063693486e-06,
      "logits/chosen": 17.019062042236328,
      "logits/rejected": 16.315940856933594,
      "logps/chosen": -0.8996315002441406,
      "logps/rejected": -2.0307648181915283,
      "loss": 0.674,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -1.349447250366211,
      "rewards/margins": 1.696699857711792,
      "rewards/rejected": -3.046147108078003,
      "step": 350
    },
    {
      "epoch": 0.5493427506376299,
      "eval_logits/chosen": 16.70261001586914,
      "eval_logits/rejected": 15.845681190490723,
      "eval_logps/chosen": -0.9138904809951782,
      "eval_logps/rejected": -2.5003392696380615,
      "eval_loss": 0.6938430070877075,
      "eval_rewards/accuracies": 0.8461538553237915,
      "eval_rewards/chosen": -1.3708356618881226,
      "eval_rewards/margins": 2.3796732425689697,
      "eval_rewards/rejected": -3.75050950050354,
      "eval_runtime": 14.6072,
      "eval_samples_per_second": 28.205,
      "eval_steps_per_second": 3.56,
      "step": 350
    },
    {
      "epoch": 0.5650382577987051,
      "grad_norm": 0.6917555928230286,
      "learning_rate": 4.322421568553529e-06,
      "logits/chosen": 16.269399642944336,
      "logits/rejected": 15.73193645477295,
      "logps/chosen": -1.0171478986740112,
      "logps/rejected": -2.201298236846924,
      "loss": 0.651,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -1.525721788406372,
      "rewards/margins": 1.7762253284454346,
      "rewards/rejected": -3.3019473552703857,
      "step": 360
    },
    {
      "epoch": 0.5807337649597802,
      "grad_norm": 1.151584267616272,
      "learning_rate": 4.286181699082008e-06,
      "logits/chosen": 15.88188648223877,
      "logits/rejected": 15.261810302734375,
      "logps/chosen": -1.2272206544876099,
      "logps/rejected": -3.0203287601470947,
      "loss": 0.665,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -1.8408310413360596,
      "rewards/margins": 2.689661741256714,
      "rewards/rejected": -4.530492305755615,
      "step": 370
    },
    {
      "epoch": 0.5964292721208554,
      "grad_norm": 1.1879621744155884,
      "learning_rate": 4.249158351283414e-06,
      "logits/chosen": 15.906834602355957,
      "logits/rejected": 15.42895221710205,
      "logps/chosen": -1.5027008056640625,
      "logps/rejected": -2.9172558784484863,
      "loss": 0.5998,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -2.2540509700775146,
      "rewards/margins": 2.1218326091766357,
      "rewards/rejected": -4.37588357925415,
      "step": 380
    },
    {
      "epoch": 0.6121247792819305,
      "grad_norm": 1.678884744644165,
      "learning_rate": 4.211367764821722e-06,
      "logits/chosen": 15.630645751953125,
      "logits/rejected": 14.888415336608887,
      "logps/chosen": -2.231367349624634,
      "logps/rejected": -3.5754780769348145,
      "loss": 0.5937,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": -3.347050905227661,
      "rewards/margins": 2.0161664485931396,
      "rewards/rejected": -5.363216876983643,
      "step": 390
    },
    {
      "epoch": 0.6278202864430057,
      "grad_norm": 2.008671998977661,
      "learning_rate": 4.172826515897146e-06,
      "logits/chosen": 15.024614334106445,
      "logits/rejected": 14.981277465820312,
      "logps/chosen": -2.665980815887451,
      "logps/rejected": -3.582763195037842,
      "loss": 0.5722,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -3.998971462249756,
      "rewards/margins": 1.3751739263534546,
      "rewards/rejected": -5.374145030975342,
      "step": 400
    },
    {
      "epoch": 0.6278202864430057,
      "eval_logits/chosen": 15.45953369140625,
      "eval_logits/rejected": 14.663763046264648,
      "eval_logps/chosen": -2.7269070148468018,
      "eval_logps/rejected": -4.235719680786133,
      "eval_loss": 0.5668805837631226,
      "eval_rewards/accuracies": 0.8846153616905212,
      "eval_rewards/chosen": -4.090360641479492,
      "eval_rewards/margins": 2.263219118118286,
      "eval_rewards/rejected": -6.353579998016357,
      "eval_runtime": 14.6036,
      "eval_samples_per_second": 28.212,
      "eval_steps_per_second": 3.561,
      "step": 400
    },
    {
      "epoch": 0.6435157936040808,
      "grad_norm": 1.018362045288086,
      "learning_rate": 4.133551509975264e-06,
      "logits/chosen": 15.027656555175781,
      "logits/rejected": 14.74786376953125,
      "logps/chosen": -2.76598858833313,
      "logps/rejected": -4.335003852844238,
      "loss": 0.5412,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -4.148982524871826,
      "rewards/margins": 2.3535237312316895,
      "rewards/rejected": -6.502506256103516,
      "step": 410
    },
    {
      "epoch": 0.659211300765156,
      "grad_norm": 2.2899765968322754,
      "learning_rate": 4.093559974371725e-06,
      "logits/chosen": 15.15197467803955,
      "logits/rejected": 14.681947708129883,
      "logps/chosen": -2.9831995964050293,
      "logps/rejected": -4.723050117492676,
      "loss": 0.4652,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -4.474799633026123,
      "rewards/margins": 2.6097757816314697,
      "rewards/rejected": -7.0845746994018555,
      "step": 420
    },
    {
      "epoch": 0.6749068079262311,
      "grad_norm": 1.419196605682373,
      "learning_rate": 4.052869450695776e-06,
      "logits/chosen": 15.000317573547363,
      "logits/rejected": 14.538591384887695,
      "logps/chosen": -3.543004274368286,
      "logps/rejected": -5.037484169006348,
      "loss": 0.427,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -5.314507007598877,
      "rewards/margins": 2.2417192459106445,
      "rewards/rejected": -7.556225776672363,
      "step": 430
    },
    {
      "epoch": 0.6906023150873063,
      "grad_norm": 1.639215111732483,
      "learning_rate": 4.011497787155938e-06,
      "logits/chosen": 14.798017501831055,
      "logits/rejected": 14.236108779907227,
      "logps/chosen": -4.154418468475342,
      "logps/rejected": -6.0606184005737305,
      "loss": 0.4692,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -6.231626987457275,
      "rewards/margins": 2.859299421310425,
      "rewards/rejected": -9.090926170349121,
      "step": 440
    },
    {
      "epoch": 0.7062978222483814,
      "grad_norm": 1.6229957342147827,
      "learning_rate": 3.969463130731183e-06,
      "logits/chosen": 14.495908737182617,
      "logits/rejected": 13.978658676147461,
      "logps/chosen": -3.4806721210479736,
      "logps/rejected": -5.746390342712402,
      "loss": 0.4218,
      "rewards/accuracies": 0.8500000238418579,
      "rewards/chosen": -5.221007823944092,
      "rewards/margins": 3.3985772132873535,
      "rewards/rejected": -8.619585037231445,
      "step": 450
    },
    {
      "epoch": 0.7062978222483814,
      "eval_logits/chosen": 15.033548355102539,
      "eval_logits/rejected": 14.20669174194336,
      "eval_logps/chosen": -3.423999547958374,
      "eval_logps/rejected": -5.855647563934326,
      "eval_loss": 0.45794492959976196,
      "eval_rewards/accuracies": 0.942307710647583,
      "eval_rewards/chosen": -5.135998725891113,
      "eval_rewards/margins": 3.6474733352661133,
      "eval_rewards/rejected": -8.783472061157227,
      "eval_runtime": 14.6088,
      "eval_samples_per_second": 28.202,
      "eval_steps_per_second": 3.559,
      "step": 450
    },
    {
      "epoch": 0.7219933294094566,
      "grad_norm": 1.7993106842041016,
      "learning_rate": 3.92678391921108e-06,
      "logits/chosen": 14.569323539733887,
      "logits/rejected": 13.937005996704102,
      "logps/chosen": -3.3623528480529785,
      "logps/rejected": -5.784353733062744,
      "loss": 0.3675,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -5.043529033660889,
      "rewards/margins": 3.6330013275146484,
      "rewards/rejected": -8.676530838012695,
      "step": 460
    },
    {
      "epoch": 0.7376888365705316,
      "grad_norm": 2.1828088760375977,
      "learning_rate": 3.88347887310836e-06,
      "logits/chosen": 13.90056037902832,
      "logits/rejected": 13.489587783813477,
      "logps/chosen": -3.959341049194336,
      "logps/rejected": -6.217314720153809,
      "loss": 0.3653,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -5.939011573791504,
      "rewards/margins": 3.3869614601135254,
      "rewards/rejected": -9.325971603393555,
      "step": 470
    },
    {
      "epoch": 0.7533843437316068,
      "grad_norm": 2.128547191619873,
      "learning_rate": 3.839566987447492e-06,
      "logits/chosen": 14.113011360168457,
      "logits/rejected": 13.571691513061523,
      "logps/chosen": -4.004420280456543,
      "logps/rejected": -6.216452121734619,
      "loss": 0.3439,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -6.0066304206848145,
      "rewards/margins": 3.3180477619171143,
      "rewards/rejected": -9.324677467346191,
      "step": 480
    },
    {
      "epoch": 0.7690798508926819,
      "grad_norm": 3.2651569843292236,
      "learning_rate": 3.795067523432826e-06,
      "logits/chosen": 13.918218612670898,
      "logits/rejected": 13.147412300109863,
      "logps/chosen": -4.574521064758301,
      "logps/rejected": -7.411087989807129,
      "loss": 0.3645,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -6.861782073974609,
      "rewards/margins": 4.254849910736084,
      "rewards/rejected": -11.116632461547852,
      "step": 490
    },
    {
      "epoch": 0.7847753580537571,
      "grad_norm": 2.163595676422119,
      "learning_rate": 3.7500000000000005e-06,
      "logits/chosen": 13.972379684448242,
      "logits/rejected": 13.390825271606445,
      "logps/chosen": -3.931866407394409,
      "logps/rejected": -6.547454833984375,
      "loss": 0.3698,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -5.897799491882324,
      "rewards/margins": 3.923382520675659,
      "rewards/rejected": -9.821184158325195,
      "step": 500
    },
    {
      "epoch": 0.7847753580537571,
      "eval_logits/chosen": 14.325434684753418,
      "eval_logits/rejected": 13.4517822265625,
      "eval_logps/chosen": -3.7717440128326416,
      "eval_logps/rejected": -6.710938453674316,
      "eval_loss": 0.38915327191352844,
      "eval_rewards/accuracies": 0.942307710647583,
      "eval_rewards/chosen": -5.657615661621094,
      "eval_rewards/margins": 4.408792018890381,
      "eval_rewards/rejected": -10.066408157348633,
      "eval_runtime": 14.5996,
      "eval_samples_per_second": 28.22,
      "eval_steps_per_second": 3.562,
      "step": 500
    },
    {
      "epoch": 0.8004708652148322,
      "grad_norm": 2.7098453044891357,
      "learning_rate": 3.7043841852542884e-06,
      "logits/chosen": 13.909749984741211,
      "logits/rejected": 13.060315132141113,
      "logps/chosen": -3.848449230194092,
      "logps/rejected": -6.747067928314209,
      "loss": 0.3547,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -5.772673606872559,
      "rewards/margins": 4.347928524017334,
      "rewards/rejected": -10.120603561401367,
      "step": 510
    },
    {
      "epoch": 0.8161663723759074,
      "grad_norm": 1.693467140197754,
      "learning_rate": 3.658240087799655e-06,
      "logits/chosen": 13.52336311340332,
      "logits/rejected": 13.026924133300781,
      "logps/chosen": -4.218991279602051,
      "logps/rejected": -6.984036445617676,
      "loss": 0.3718,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -6.328486442565918,
      "rewards/margins": 4.1475677490234375,
      "rewards/rejected": -10.476054191589355,
      "step": 520
    },
    {
      "epoch": 0.8318618795369825,
      "grad_norm": 2.4496915340423584,
      "learning_rate": 3.611587947962319e-06,
      "logits/chosen": 13.840197563171387,
      "logits/rejected": 13.181543350219727,
      "logps/chosen": -4.708582401275635,
      "logps/rejected": -7.19864559173584,
      "loss": 0.329,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -7.062872886657715,
      "rewards/margins": 3.7350947856903076,
      "rewards/rejected": -10.797967910766602,
      "step": 530
    },
    {
      "epoch": 0.8475573866980577,
      "grad_norm": 5.772508144378662,
      "learning_rate": 3.564448228912682e-06,
      "logits/chosen": 13.432130813598633,
      "logits/rejected": 12.825490951538086,
      "logps/chosen": -4.506819248199463,
      "logps/rejected": -7.506214141845703,
      "loss": 0.2544,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -6.760228633880615,
      "rewards/margins": 4.499091625213623,
      "rewards/rejected": -11.259321212768555,
      "step": 540
    },
    {
      "epoch": 0.8632528938591328,
      "grad_norm": 1.7776503562927246,
      "learning_rate": 3.516841607689501e-06,
      "logits/chosen": 13.536295890808105,
      "logits/rejected": 12.703726768493652,
      "logps/chosen": -4.724976062774658,
      "logps/rejected": -7.864454746246338,
      "loss": 0.2795,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -7.087464332580566,
      "rewards/margins": 4.7092180252075195,
      "rewards/rejected": -11.796682357788086,
      "step": 550
    },
    {
      "epoch": 0.8632528938591328,
      "eval_logits/chosen": 13.692171096801758,
      "eval_logits/rejected": 12.81371021270752,
      "eval_logps/chosen": -4.32358980178833,
      "eval_logps/rejected": -7.658167839050293,
      "eval_loss": 0.335475891828537,
      "eval_rewards/accuracies": 0.942307710647583,
      "eval_rewards/chosen": -6.485384464263916,
      "eval_rewards/margins": 5.00186824798584,
      "eval_rewards/rejected": -11.487252235412598,
      "eval_runtime": 14.6093,
      "eval_samples_per_second": 28.201,
      "eval_steps_per_second": 3.559,
      "step": 550
    },
    {
      "epoch": 0.878948401020208,
      "grad_norm": 1.7613197565078735,
      "learning_rate": 3.4687889661302577e-06,
      "logits/chosen": 13.689091682434082,
      "logits/rejected": 12.911500930786133,
      "logps/chosen": -3.8375942707061768,
      "logps/rejected": -6.98319149017334,
      "loss": 0.3008,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -5.7563910484313965,
      "rewards/margins": 4.7183966636657715,
      "rewards/rejected": -10.474787712097168,
      "step": 560
    },
    {
      "epoch": 0.8946439081812831,
      "grad_norm": 2.1285247802734375,
      "learning_rate": 3.4203113817116955e-06,
      "logits/chosen": 13.902356147766113,
      "logits/rejected": 12.766775131225586,
      "logps/chosen": -3.7727108001708984,
      "logps/rejected": -7.6362409591674805,
      "loss": 0.2816,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -5.6590657234191895,
      "rewards/margins": 5.795297622680664,
      "rewards/rejected": -11.454363822937012,
      "step": 570
    },
    {
      "epoch": 0.9103394153423583,
      "grad_norm": 1.6965669393539429,
      "learning_rate": 3.3714301183045382e-06,
      "logits/chosen": 13.374112129211426,
      "logits/rejected": 12.414613723754883,
      "logps/chosen": -4.747832298278809,
      "logps/rejected": -8.099973678588867,
      "loss": 0.2921,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -7.121748924255371,
      "rewards/margins": 5.028212547302246,
      "rewards/rejected": -12.1499605178833,
      "step": 580
    },
    {
      "epoch": 0.9260349225034334,
      "grad_norm": 2.5470242500305176,
      "learning_rate": 3.3221666168464584e-06,
      "logits/chosen": 13.287660598754883,
      "logits/rejected": 12.554139137268066,
      "logps/chosen": -4.818625450134277,
      "logps/rejected": -8.005637168884277,
      "loss": 0.3155,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": -7.227938175201416,
      "rewards/margins": 4.780518531799316,
      "rewards/rejected": -12.008456230163574,
      "step": 590
    },
    {
      "epoch": 0.9417304296645085,
      "grad_norm": 2.374859571456909,
      "learning_rate": 3.272542485937369e-06,
      "logits/chosen": 13.152572631835938,
      "logits/rejected": 12.557012557983398,
      "logps/chosen": -3.7581982612609863,
      "logps/rejected": -6.985205173492432,
      "loss": 0.2565,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -5.6372971534729,
      "rewards/margins": 4.840510368347168,
      "rewards/rejected": -10.477807998657227,
      "step": 600
    },
    {
      "epoch": 0.9417304296645085,
      "eval_logits/chosen": 13.585193634033203,
      "eval_logits/rejected": 12.657953262329102,
      "eval_logps/chosen": -4.077207088470459,
      "eval_logps/rejected": -7.660572528839111,
      "eval_loss": 0.30504748225212097,
      "eval_rewards/accuracies": 0.9615384340286255,
      "eval_rewards/chosen": -6.115810871124268,
      "eval_rewards/margins": 5.375046730041504,
      "eval_rewards/rejected": -11.49085807800293,
      "eval_runtime": 14.6046,
      "eval_samples_per_second": 28.21,
      "eval_steps_per_second": 3.561,
      "step": 600
    }
  ],
  "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": 1.4354126705797366e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}