trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 478,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 8.482095207381906,
      "learning_rate": 1.0416666666666666e-08,
      "logits/chosen": -2.715719223022461,
      "logits/rejected": -2.648977279663086,
      "logps/chosen": -280.43304443359375,
      "logps/rejected": -269.5838623046875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.02,
      "grad_norm": 8.16883844563723,
      "learning_rate": 1.0416666666666667e-07,
      "logits/chosen": -2.732839345932007,
      "logits/rejected": -2.667829990386963,
      "logps/chosen": -252.18836975097656,
      "logps/rejected": -247.36721801757812,
      "loss": 0.6932,
      "rewards/accuracies": 0.4027777910232544,
      "rewards/chosen": -0.00020123104332014918,
      "rewards/margins": -0.000496760243549943,
      "rewards/rejected": 0.00029552922933362424,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 14.177063698718772,
      "learning_rate": 2.0833333333333333e-07,
      "logits/chosen": -2.69161057472229,
      "logits/rejected": -2.6473488807678223,
      "logps/chosen": -281.9129333496094,
      "logps/rejected": -240.79598999023438,
      "loss": 0.6923,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.0002729900588747114,
      "rewards/margins": 0.0022440399043262005,
      "rewards/rejected": -0.002517030341550708,
      "step": 20
    },
    {
      "epoch": 0.06,
      "grad_norm": 9.049842796547402,
      "learning_rate": 3.1249999999999997e-07,
      "logits/chosen": -2.7057762145996094,
      "logits/rejected": -2.6666598320007324,
      "logps/chosen": -263.8976135253906,
      "logps/rejected": -272.29376220703125,
      "loss": 0.688,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": 0.005987819284200668,
      "rewards/margins": 0.008191236294806004,
      "rewards/rejected": -0.0022034167777746916,
      "step": 30
    },
    {
      "epoch": 0.08,
      "grad_norm": 8.064536836305289,
      "learning_rate": 4.1666666666666667e-07,
      "logits/chosen": -2.644676446914673,
      "logits/rejected": -2.6523287296295166,
      "logps/chosen": -250.64651489257812,
      "logps/rejected": -240.74032592773438,
      "loss": 0.6775,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": 0.03351370617747307,
      "rewards/margins": 0.024272698909044266,
      "rewards/rejected": 0.009241009131073952,
      "step": 40
    },
    {
      "epoch": 0.1,
      "grad_norm": 10.48307069571783,
      "learning_rate": 4.999733114418725e-07,
      "logits/chosen": -2.61690616607666,
      "logits/rejected": -2.606698989868164,
      "logps/chosen": -280.32537841796875,
      "logps/rejected": -285.14044189453125,
      "loss": 0.6572,
      "rewards/accuracies": 0.706250011920929,
      "rewards/chosen": 0.027328694239258766,
      "rewards/margins": 0.08270208537578583,
      "rewards/rejected": -0.05537338927388191,
      "step": 50
    },
    {
      "epoch": 0.13,
      "grad_norm": 11.217495552902317,
      "learning_rate": 4.990398100856366e-07,
      "logits/chosen": -2.6028363704681396,
      "logits/rejected": -2.567634344100952,
      "logps/chosen": -257.1751403808594,
      "logps/rejected": -286.7103271484375,
      "loss": 0.6382,
      "rewards/accuracies": 0.6937500238418579,
      "rewards/chosen": -0.04173869267106056,
      "rewards/margins": 0.14793893694877625,
      "rewards/rejected": -0.1896776258945465,
      "step": 60
    },
    {
      "epoch": 0.15,
      "grad_norm": 17.002512653941917,
      "learning_rate": 4.967775735898179e-07,
      "logits/chosen": -2.5477585792541504,
      "logits/rejected": -2.5538854598999023,
      "logps/chosen": -292.3646240234375,
      "logps/rejected": -295.1927795410156,
      "loss": 0.6089,
      "rewards/accuracies": 0.6312500238418579,
      "rewards/chosen": -0.17977146804332733,
      "rewards/margins": 0.22043642401695251,
      "rewards/rejected": -0.40020790696144104,
      "step": 70
    },
    {
      "epoch": 0.17,
      "grad_norm": 20.83722381714638,
      "learning_rate": 4.931986719649298e-07,
      "logits/chosen": -2.428433895111084,
      "logits/rejected": -2.4765429496765137,
      "logps/chosen": -269.8500671386719,
      "logps/rejected": -280.10003662109375,
      "loss": 0.6115,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.11873555183410645,
      "rewards/margins": 0.21846923232078552,
      "rewards/rejected": -0.3372047543525696,
      "step": 80
    },
    {
      "epoch": 0.19,
      "grad_norm": 20.582635256945927,
      "learning_rate": 4.883222001996351e-07,
      "logits/chosen": -2.3149566650390625,
      "logits/rejected": -2.3007912635803223,
      "logps/chosen": -331.8517761230469,
      "logps/rejected": -353.4700012207031,
      "loss": 0.6084,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.4723566174507141,
      "rewards/margins": 0.2896661162376404,
      "rewards/rejected": -0.7620226740837097,
      "step": 90
    },
    {
      "epoch": 0.21,
      "grad_norm": 15.474211826471516,
      "learning_rate": 4.821741763807186e-07,
      "logits/chosen": -2.2471911907196045,
      "logits/rejected": -2.2106168270111084,
      "logps/chosen": -346.5975646972656,
      "logps/rejected": -342.70501708984375,
      "loss": 0.5875,
      "rewards/accuracies": 0.737500011920929,
      "rewards/chosen": -0.5387172698974609,
      "rewards/margins": 0.4208316206932068,
      "rewards/rejected": -0.9595489501953125,
      "step": 100
    },
    {
      "epoch": 0.21,
      "eval_logits/chosen": -1.839242935180664,
      "eval_logits/rejected": -1.8929309844970703,
      "eval_logps/chosen": -327.45477294921875,
      "eval_logps/rejected": -373.7126159667969,
      "eval_loss": 0.5814013481140137,
      "eval_rewards/accuracies": 0.6953125,
      "eval_rewards/chosen": -0.6485257148742676,
      "eval_rewards/margins": 0.46177732944488525,
      "eval_rewards/rejected": -1.1103030443191528,
      "eval_runtime": 42.9635,
      "eval_samples_per_second": 46.551,
      "eval_steps_per_second": 0.745,
      "step": 100
    },
    {
      "epoch": 0.23,
      "grad_norm": 20.231938142939548,
      "learning_rate": 4.747874028753375e-07,
      "logits/chosen": -1.7017923593521118,
      "logits/rejected": -1.6744320392608643,
      "logps/chosen": -330.83038330078125,
      "logps/rejected": -384.0965576171875,
      "loss": 0.559,
      "rewards/accuracies": 0.7437499761581421,
      "rewards/chosen": -0.6345968246459961,
      "rewards/margins": 0.5422910451889038,
      "rewards/rejected": -1.1768878698349,
      "step": 110
    },
    {
      "epoch": 0.25,
      "grad_norm": 33.96451578064435,
      "learning_rate": 4.662012913161997e-07,
      "logits/chosen": -1.5577061176300049,
      "logits/rejected": -1.454756498336792,
      "logps/chosen": -354.79632568359375,
      "logps/rejected": -374.60076904296875,
      "loss": 0.5508,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -0.6455836892127991,
      "rewards/margins": 0.6170965433120728,
      "rewards/rejected": -1.2626802921295166,
      "step": 120
    },
    {
      "epoch": 0.27,
      "grad_norm": 22.138057395490627,
      "learning_rate": 4.5646165232345103e-07,
      "logits/chosen": -1.985395073890686,
      "logits/rejected": -1.7330490350723267,
      "logps/chosen": -381.68524169921875,
      "logps/rejected": -393.6003723144531,
      "loss": 0.5691,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -0.6896110773086548,
      "rewards/margins": 0.46295279264450073,
      "rewards/rejected": -1.1525638103485107,
      "step": 130
    },
    {
      "epoch": 0.29,
      "grad_norm": 22.948235111766778,
      "learning_rate": 4.456204510851956e-07,
      "logits/chosen": -1.7121162414550781,
      "logits/rejected": -1.4992659091949463,
      "logps/chosen": -352.444580078125,
      "logps/rejected": -359.44293212890625,
      "loss": 0.5444,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.7159131765365601,
      "rewards/margins": 0.5610858798027039,
      "rewards/rejected": -1.2769991159439087,
      "step": 140
    },
    {
      "epoch": 0.31,
      "grad_norm": 21.94614729668817,
      "learning_rate": 4.337355301007335e-07,
      "logits/chosen": -1.6999915838241577,
      "logits/rejected": -1.5280932188034058,
      "logps/chosen": -363.3777770996094,
      "logps/rejected": -409.53472900390625,
      "loss": 0.5354,
      "rewards/accuracies": 0.737500011920929,
      "rewards/chosen": -0.6176407933235168,
      "rewards/margins": 0.7246734499931335,
      "rewards/rejected": -1.3423142433166504,
      "step": 150
    },
    {
      "epoch": 0.33,
      "grad_norm": 25.951614311748312,
      "learning_rate": 4.2087030056579986e-07,
      "logits/chosen": -0.8817731142044067,
      "logits/rejected": -0.6137579679489136,
      "logps/chosen": -382.1938171386719,
      "logps/rejected": -432.11004638671875,
      "loss": 0.5293,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -1.0363513231277466,
      "rewards/margins": 0.7439759373664856,
      "rewards/rejected": -1.7803272008895874,
      "step": 160
    },
    {
      "epoch": 0.36,
      "grad_norm": 22.62183660087882,
      "learning_rate": 4.070934040463998e-07,
      "logits/chosen": -0.8362399339675903,
      "logits/rejected": -0.5129006505012512,
      "logps/chosen": -383.85943603515625,
      "logps/rejected": -450.67376708984375,
      "loss": 0.5396,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -1.1981004476547241,
      "rewards/margins": 0.5252794623374939,
      "rewards/rejected": -1.7233800888061523,
      "step": 170
    },
    {
      "epoch": 0.38,
      "grad_norm": 20.471718314655647,
      "learning_rate": 3.9247834624635404e-07,
      "logits/chosen": -1.1186776161193848,
      "logits/rejected": -0.807415783405304,
      "logps/chosen": -367.24517822265625,
      "logps/rejected": -383.65325927734375,
      "loss": 0.5423,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -0.7441693544387817,
      "rewards/margins": 0.7058154344558716,
      "rewards/rejected": -1.4499847888946533,
      "step": 180
    },
    {
      "epoch": 0.4,
      "grad_norm": 27.806972171143425,
      "learning_rate": 3.7710310482256523e-07,
      "logits/chosen": -0.8124464750289917,
      "logits/rejected": -0.3878273069858551,
      "logps/chosen": -388.7113342285156,
      "logps/rejected": -429.1011657714844,
      "loss": 0.5411,
      "rewards/accuracies": 0.731249988079071,
      "rewards/chosen": -1.1005661487579346,
      "rewards/margins": 0.6401538252830505,
      "rewards/rejected": -1.7407200336456299,
      "step": 190
    },
    {
      "epoch": 0.42,
      "grad_norm": 26.53253409564454,
      "learning_rate": 3.610497133404795e-07,
      "logits/chosen": -0.11316045373678207,
      "logits/rejected": 0.337258517742157,
      "logps/chosen": -417.2351989746094,
      "logps/rejected": -437.7659606933594,
      "loss": 0.5306,
      "rewards/accuracies": 0.7437499761581421,
      "rewards/chosen": -1.1853481531143188,
      "rewards/margins": 0.7383456826210022,
      "rewards/rejected": -1.9236938953399658,
      "step": 200
    },
    {
      "epoch": 0.42,
      "eval_logits/chosen": -0.4834875464439392,
      "eval_logits/rejected": -0.16467474400997162,
      "eval_logps/chosen": -377.3648681640625,
      "eval_logps/rejected": -458.6296691894531,
      "eval_loss": 0.5258087515830994,
      "eval_rewards/accuracies": 0.7578125,
      "eval_rewards/chosen": -1.1476268768310547,
      "eval_rewards/margins": 0.8118469715118408,
      "eval_rewards/rejected": -1.959473729133606,
      "eval_runtime": 42.8446,
      "eval_samples_per_second": 46.68,
      "eval_steps_per_second": 0.747,
      "step": 200
    },
    {
      "epoch": 0.44,
      "grad_norm": 32.607007304168285,
      "learning_rate": 3.4440382358952115e-07,
      "logits/chosen": -0.4726165235042572,
      "logits/rejected": 0.2889423966407776,
      "logps/chosen": -445.2005310058594,
      "logps/rejected": -516.150390625,
      "loss": 0.5157,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": -1.5719295740127563,
      "rewards/margins": 0.899932861328125,
      "rewards/rejected": -2.471862316131592,
      "step": 210
    },
    {
      "epoch": 0.46,
      "grad_norm": 26.982376912169133,
      "learning_rate": 3.272542485937368e-07,
      "logits/chosen": 0.02971530519425869,
      "logits/rejected": 0.6972896456718445,
      "logps/chosen": -488.6690979003906,
      "logps/rejected": -517.7215576171875,
      "loss": 0.5045,
      "rewards/accuracies": 0.706250011920929,
      "rewards/chosen": -1.9397350549697876,
      "rewards/margins": 0.67905592918396,
      "rewards/rejected": -2.618790626525879,
      "step": 220
    },
    {
      "epoch": 0.48,
      "grad_norm": 28.31686307704009,
      "learning_rate": 3.096924887558854e-07,
      "logits/chosen": 0.3274112641811371,
      "logits/rejected": 1.6159236431121826,
      "logps/chosen": -472.36590576171875,
      "logps/rejected": -560.3911743164062,
      "loss": 0.5157,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -2.139970302581787,
      "rewards/margins": 0.9002918004989624,
      "rewards/rejected": -3.040262460708618,
      "step": 230
    },
    {
      "epoch": 0.5,
      "grad_norm": 26.93455267413187,
      "learning_rate": 2.9181224366319943e-07,
      "logits/chosen": 0.34222739934921265,
      "logits/rejected": 1.275580644607544,
      "logps/chosen": -493.95916748046875,
      "logps/rejected": -570.4260864257812,
      "loss": 0.4844,
      "rewards/accuracies": 0.737500011920929,
      "rewards/chosen": -2.126845598220825,
      "rewards/margins": 0.9677503705024719,
      "rewards/rejected": -3.0945961475372314,
      "step": 240
    },
    {
      "epoch": 0.52,
      "grad_norm": 34.97761081158377,
      "learning_rate": 2.7370891215954565e-07,
      "logits/chosen": 0.15051239728927612,
      "logits/rejected": 1.3550792932510376,
      "logps/chosen": -447.21490478515625,
      "logps/rejected": -547.626708984375,
      "loss": 0.5157,
      "rewards/accuracies": 0.768750011920929,
      "rewards/chosen": -2.229414463043213,
      "rewards/margins": 1.004492998123169,
      "rewards/rejected": -3.2339072227478027,
      "step": 250
    },
    {
      "epoch": 0.54,
      "grad_norm": 22.98186057582904,
      "learning_rate": 2.55479083351317e-07,
      "logits/chosen": -0.6737252473831177,
      "logits/rejected": -0.22596630454063416,
      "logps/chosen": -423.21124267578125,
      "logps/rejected": -537.1641845703125,
      "loss": 0.4931,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -1.5507694482803345,
      "rewards/margins": 1.1678037643432617,
      "rewards/rejected": -2.7185730934143066,
      "step": 260
    },
    {
      "epoch": 0.56,
      "grad_norm": 24.568187901601522,
      "learning_rate": 2.3722002126275822e-07,
      "logits/chosen": -0.7251144647598267,
      "logits/rejected": 0.055858515202999115,
      "logps/chosen": -460.47369384765625,
      "logps/rejected": -515.4779663085938,
      "loss": 0.5056,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": -1.7928097248077393,
      "rewards/margins": 0.9766537547111511,
      "rewards/rejected": -2.769463300704956,
      "step": 270
    },
    {
      "epoch": 0.59,
      "grad_norm": 26.18745823449182,
      "learning_rate": 2.19029145890313e-07,
      "logits/chosen": -0.2248018980026245,
      "logits/rejected": 0.7499777674674988,
      "logps/chosen": -570.017822265625,
      "logps/rejected": -637.1007690429688,
      "loss": 0.4807,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -2.686659097671509,
      "rewards/margins": 1.049829125404358,
      "rewards/rejected": -3.736487865447998,
      "step": 280
    },
    {
      "epoch": 0.61,
      "grad_norm": 27.843254345626296,
      "learning_rate": 2.0100351342479216e-07,
      "logits/chosen": 0.017834633588790894,
      "logits/rejected": 0.5087012052536011,
      "logps/chosen": -523.2457275390625,
      "logps/rejected": -614.5767211914062,
      "loss": 0.4986,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -2.559013605117798,
      "rewards/margins": 0.9906851053237915,
      "rewards/rejected": -3.5496985912323,
      "step": 290
    },
    {
      "epoch": 0.63,
      "grad_norm": 28.812343531542734,
      "learning_rate": 1.8323929841460178e-07,
      "logits/chosen": -0.09833024442195892,
      "logits/rejected": 0.13667245209217072,
      "logps/chosen": -530.9118041992188,
      "logps/rejected": -594.4251098632812,
      "loss": 0.5097,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -2.618612766265869,
      "rewards/margins": 0.6055675745010376,
      "rewards/rejected": -3.224180221557617,
      "step": 300
    },
    {
      "epoch": 0.63,
      "eval_logits/chosen": -0.46580713987350464,
      "eval_logits/rejected": -0.05736924335360527,
      "eval_logps/chosen": -498.608642578125,
      "eval_logps/rejected": -600.8517456054688,
      "eval_loss": 0.5078553557395935,
      "eval_rewards/accuracies": 0.765625,
      "eval_rewards/chosen": -2.3600645065307617,
      "eval_rewards/margins": 1.021630048751831,
      "eval_rewards/rejected": -3.3816945552825928,
      "eval_runtime": 42.9133,
      "eval_samples_per_second": 46.606,
      "eval_steps_per_second": 0.746,
      "step": 300
    },
    {
      "epoch": 0.65,
      "grad_norm": 24.395908084810543,
      "learning_rate": 1.6583128063291573e-07,
      "logits/chosen": -0.20998772978782654,
      "logits/rejected": 0.597333550453186,
      "logps/chosen": -553.8638305664062,
      "logps/rejected": -622.6854248046875,
      "loss": 0.4601,
      "rewards/accuracies": 0.8062499761581421,
      "rewards/chosen": -2.6587719917297363,
      "rewards/margins": 1.019250512123108,
      "rewards/rejected": -3.678022861480713,
      "step": 310
    },
    {
      "epoch": 0.67,
      "grad_norm": 34.66768420911215,
      "learning_rate": 1.488723393865766e-07,
      "logits/chosen": 0.16718712449073792,
      "logits/rejected": 0.9329349398612976,
      "logps/chosen": -593.7220458984375,
      "logps/rejected": -669.1134033203125,
      "loss": 0.4733,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -3.0446815490722656,
      "rewards/margins": 1.103857159614563,
      "rewards/rejected": -4.1485395431518555,
      "step": 320
    },
    {
      "epoch": 0.69,
      "grad_norm": 28.471803594507218,
      "learning_rate": 1.3245295796480788e-07,
      "logits/chosen": -0.11941705644130707,
      "logits/rejected": 0.6031097173690796,
      "logps/chosen": -576.390869140625,
      "logps/rejected": -662.9435424804688,
      "loss": 0.4956,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -2.895800828933716,
      "rewards/margins": 1.0525661706924438,
      "rewards/rejected": -3.9483673572540283,
      "step": 330
    },
    {
      "epoch": 0.71,
      "grad_norm": 29.920730024726208,
      "learning_rate": 1.1666074087171627e-07,
      "logits/chosen": -0.6586230397224426,
      "logits/rejected": -0.01618196628987789,
      "logps/chosen": -558.61328125,
      "logps/rejected": -645.0929565429688,
      "loss": 0.4901,
      "rewards/accuracies": 0.78125,
      "rewards/chosen": -2.6631388664245605,
      "rewards/margins": 0.9750139117240906,
      "rewards/rejected": -3.638153076171875,
      "step": 340
    },
    {
      "epoch": 0.73,
      "grad_norm": 28.451943555198234,
      "learning_rate": 1.0157994641835734e-07,
      "logits/chosen": -0.27327781915664673,
      "logits/rejected": 0.1500699818134308,
      "logps/chosen": -551.64501953125,
      "logps/rejected": -615.7404174804688,
      "loss": 0.5079,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -2.8532228469848633,
      "rewards/margins": 0.7952502369880676,
      "rewards/rejected": -3.6484732627868652,
      "step": 350
    },
    {
      "epoch": 0.75,
      "grad_norm": 25.677922944710783,
      "learning_rate": 8.729103716819111e-08,
      "logits/chosen": -0.08269649744033813,
      "logits/rejected": 0.27684250473976135,
      "logps/chosen": -541.1990966796875,
      "logps/rejected": -651.2036743164062,
      "loss": 0.4674,
      "rewards/accuracies": 0.7562500238418579,
      "rewards/chosen": -2.9707937240600586,
      "rewards/margins": 0.9196038246154785,
      "rewards/rejected": -3.8903980255126953,
      "step": 360
    },
    {
      "epoch": 0.77,
      "grad_norm": 36.170517312989006,
      "learning_rate": 7.387025063449081e-08,
      "logits/chosen": -0.2130926102399826,
      "logits/rejected": 0.6245878338813782,
      "logps/chosen": -593.176513671875,
      "logps/rejected": -702.429443359375,
      "loss": 0.4914,
      "rewards/accuracies": 0.768750011920929,
      "rewards/chosen": -3.0834755897521973,
      "rewards/margins": 1.1826813220977783,
      "rewards/rejected": -4.266157150268555,
      "step": 370
    },
    {
      "epoch": 0.79,
      "grad_norm": 29.948938424368286,
      "learning_rate": 6.138919252022435e-08,
      "logits/chosen": -0.31227773427963257,
      "logits/rejected": 0.1758570820093155,
      "logps/chosen": -569.8441162109375,
      "logps/rejected": -653.1160278320312,
      "loss": 0.4834,
      "rewards/accuracies": 0.78125,
      "rewards/chosen": -2.861605644226074,
      "rewards/margins": 1.1251481771469116,
      "rewards/rejected": -3.9867539405822754,
      "step": 380
    },
    {
      "epoch": 0.82,
      "grad_norm": 28.643050867948876,
      "learning_rate": 4.991445467064689e-08,
      "logits/chosen": -0.4378163814544678,
      "logits/rejected": 0.1975017786026001,
      "logps/chosen": -487.02447509765625,
      "logps/rejected": -627.4256591796875,
      "loss": 0.4863,
      "rewards/accuracies": 0.856249988079071,
      "rewards/chosen": -2.4755725860595703,
      "rewards/margins": 1.2951563596725464,
      "rewards/rejected": -3.770728588104248,
      "step": 390
    },
    {
      "epoch": 0.84,
      "grad_norm": 28.740512536833982,
      "learning_rate": 3.9507259776993954e-08,
      "logits/chosen": -0.464282363653183,
      "logits/rejected": 0.3086758852005005,
      "logps/chosen": -510.72564697265625,
      "logps/rejected": -584.2462158203125,
      "loss": 0.4906,
      "rewards/accuracies": 0.706250011920929,
      "rewards/chosen": -2.4956374168395996,
      "rewards/margins": 0.9018915891647339,
      "rewards/rejected": -3.397528886795044,
      "step": 400
    },
    {
      "epoch": 0.84,
      "eval_logits/chosen": -0.5081287026405334,
      "eval_logits/rejected": -0.03897371515631676,
      "eval_logps/chosen": -499.4172058105469,
      "eval_logps/rejected": -610.7911376953125,
      "eval_loss": 0.49998462200164795,
      "eval_rewards/accuracies": 0.76953125,
      "eval_rewards/chosen": -2.368149995803833,
      "eval_rewards/margins": 1.1129380464553833,
      "eval_rewards/rejected": -3.4810879230499268,
      "eval_runtime": 43.5613,
      "eval_samples_per_second": 45.912,
      "eval_steps_per_second": 0.735,
      "step": 400
    },
    {
      "epoch": 0.86,
      "grad_norm": 29.137185743173024,
      "learning_rate": 3.022313472693447e-08,
      "logits/chosen": -0.427814781665802,
      "logits/rejected": 0.47378939390182495,
      "logps/chosen": -502.87939453125,
      "logps/rejected": -579.4691162109375,
      "loss": 0.5048,
      "rewards/accuracies": 0.737500011920929,
      "rewards/chosen": -2.4262542724609375,
      "rewards/margins": 0.9697957038879395,
      "rewards/rejected": -3.396049976348877,
      "step": 410
    },
    {
      "epoch": 0.88,
      "grad_norm": 28.72794205317694,
      "learning_rate": 2.2111614344599684e-08,
      "logits/chosen": -0.4604805111885071,
      "logits/rejected": 0.19487139582633972,
      "logps/chosen": -517.6533813476562,
      "logps/rejected": -557.2385864257812,
      "loss": 0.4911,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -2.416501760482788,
      "rewards/margins": 0.9597095251083374,
      "rewards/rejected": -3.376211643218994,
      "step": 420
    },
    {
      "epoch": 0.9,
      "grad_norm": 21.80245746988776,
      "learning_rate": 1.521597710086439e-08,
      "logits/chosen": -0.3804924488067627,
      "logits/rejected": 0.39526861906051636,
      "logps/chosen": -535.6771240234375,
      "logps/rejected": -618.59326171875,
      "loss": 0.4719,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -2.5517053604125977,
      "rewards/margins": 1.1444313526153564,
      "rewards/rejected": -3.696136474609375,
      "step": 430
    },
    {
      "epoch": 0.92,
      "grad_norm": 25.533460874638475,
      "learning_rate": 9.57301420397924e-09,
      "logits/chosen": -0.2722262442111969,
      "logits/rejected": 0.6270692944526672,
      "logps/chosen": -534.4539184570312,
      "logps/rejected": -636.7295532226562,
      "loss": 0.4921,
      "rewards/accuracies": 0.7562500238418579,
      "rewards/chosen": -2.657174587249756,
      "rewards/margins": 1.1696617603302002,
      "rewards/rejected": -3.826836347579956,
      "step": 440
    },
    {
      "epoch": 0.94,
      "grad_norm": 29.41617255057514,
      "learning_rate": 5.212833302556258e-09,
      "logits/chosen": -0.4902656078338623,
      "logits/rejected": 0.2050538957118988,
      "logps/chosen": -552.1812744140625,
      "logps/rejected": -615.8868408203125,
      "loss": 0.4784,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -2.5670862197875977,
      "rewards/margins": 1.0947918891906738,
      "rewards/rejected": -3.6618781089782715,
      "step": 450
    },
    {
      "epoch": 0.96,
      "grad_norm": 26.40697406008373,
      "learning_rate": 2.158697848236607e-09,
      "logits/chosen": -0.5525180697441101,
      "logits/rejected": 0.4095240533351898,
      "logps/chosen": -521.8342895507812,
      "logps/rejected": -599.0489501953125,
      "loss": 0.4933,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -2.4641835689544678,
      "rewards/margins": 1.049481987953186,
      "rewards/rejected": -3.5136656761169434,
      "step": 460
    },
    {
      "epoch": 0.98,
      "grad_norm": 40.87484210645662,
      "learning_rate": 4.269029751107489e-10,
      "logits/chosen": -0.38540196418762207,
      "logits/rejected": 0.25467342138290405,
      "logps/chosen": -550.1776123046875,
      "logps/rejected": -633.5750732421875,
      "loss": 0.4908,
      "rewards/accuracies": 0.71875,
      "rewards/chosen": -2.6054952144622803,
      "rewards/margins": 0.973294734954834,
      "rewards/rejected": -3.5787901878356934,
      "step": 470
    },
    {
      "epoch": 1.0,
      "step": 478,
      "total_flos": 0.0,
      "train_loss": 0.535196884905444,
      "train_runtime": 3527.4214,
      "train_samples_per_second": 17.331,
      "train_steps_per_second": 0.136
    }
  ],
  "logging_steps": 10,
  "max_steps": 478,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}