diff --git "a/checkpoint-1500/trainer_state.json" "b/checkpoint-1500/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-1500/trainer_state.json"
@@ -0,0 +1,2763 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2887838418564677,
+  "eval_steps": 50,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008594757198109154,
+      "grad_norm": 0.06708361208438873,
+      "learning_rate": 4.999451708687114e-06,
+      "logits/chosen": 14.524938583374023,
+      "logits/rejected": 14.82593822479248,
+      "logps/chosen": -0.31433865427970886,
+      "logps/rejected": -0.32406437397003174,
+      "loss": 0.9442,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.4715079367160797,
+      "rewards/margins": 0.014588532969355583,
+      "rewards/rejected": -0.48609647154808044,
+      "step": 10
+    },
+    {
+      "epoch": 0.017189514396218308,
+      "grad_norm": 0.056814808398485184,
+      "learning_rate": 4.997807075247147e-06,
+      "logits/chosen": 14.309213638305664,
+      "logits/rejected": 14.978128433227539,
+      "logps/chosen": -0.31283506751060486,
+      "logps/rejected": -0.3911947011947632,
+      "loss": 0.928,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -0.46925264596939087,
+      "rewards/margins": 0.1175394207239151,
+      "rewards/rejected": -0.5867919921875,
+      "step": 20
+    },
+    {
+      "epoch": 0.02578427159432746,
+      "grad_norm": 0.061199307441711426,
+      "learning_rate": 4.9950668210706795e-06,
+      "logits/chosen": 14.68384075164795,
+      "logits/rejected": 15.338122367858887,
+      "logps/chosen": -0.3007296621799469,
+      "logps/rejected": -0.3204456865787506,
+      "loss": 0.9439,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.45109447836875916,
+      "rewards/margins": 0.029573997482657433,
+      "rewards/rejected": -0.48066848516464233,
+      "step": 30
+    },
+    {
+      "epoch": 0.034379028792436615,
+      "grad_norm": 0.08423774689435959,
+      "learning_rate": 4.9912321481237616e-06,
+      "logits/chosen": 14.39265251159668,
+      "logits/rejected": 15.059102058410645,
+      "logps/chosen": -0.28216058015823364,
+      "logps/rejected": -0.33495840430259705,
+      "loss": 0.9184,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.42324090003967285,
+      "rewards/margins": 0.07919676601886749,
+      "rewards/rejected": -0.5024376511573792,
+      "step": 40
+    },
+    {
+      "epoch": 0.042973785990545764,
+      "grad_norm": 0.06052614375948906,
+      "learning_rate": 4.986304738420684e-06,
+      "logits/chosen": 14.383735656738281,
+      "logits/rejected": 15.029413223266602,
+      "logps/chosen": -0.27970507740974426,
+      "logps/rejected": -0.33213528990745544,
+      "loss": 0.9317,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.4195576310157776,
+      "rewards/margins": 0.07864536345005035,
+      "rewards/rejected": -0.49820294976234436,
+      "step": 50
+    },
+    {
+      "epoch": 0.042973785990545764,
+      "eval_logits/chosen": 14.424538612365723,
+      "eval_logits/rejected": 15.006633758544922,
+      "eval_logps/chosen": -0.2923925220966339,
+      "eval_logps/rejected": -0.3531996011734009,
+      "eval_loss": 0.9324354529380798,
+      "eval_rewards/accuracies": 0.5052631497383118,
+      "eval_rewards/chosen": -0.43858882784843445,
+      "eval_rewards/margins": 0.09121060371398926,
+      "eval_rewards/rejected": -0.5297994017601013,
+      "eval_runtime": 26.3759,
+      "eval_samples_per_second": 28.549,
+      "eval_steps_per_second": 3.602,
+      "step": 50
+    },
+    {
+      "epoch": 0.05156854318865492,
+      "grad_norm": 0.06899414211511612,
+      "learning_rate": 4.980286753286196e-06,
+      "logits/chosen": 14.888933181762695,
+      "logits/rejected": 15.33955192565918,
+      "logps/chosen": -0.2886829972267151,
+      "logps/rejected": -0.34016504883766174,
+      "loss": 0.9323,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.43302449584007263,
+      "rewards/margins": 0.07722309231758118,
+      "rewards/rejected": -0.5102475881576538,
+      "step": 60
+    },
+    {
+      "epoch": 0.060163300386764075,
+      "grad_norm": 0.06679105013608932,
+      "learning_rate": 4.973180832407471e-06,
+      "logits/chosen": 14.721624374389648,
+      "logits/rejected": 15.614666938781738,
+      "logps/chosen": -0.29435139894485474,
+      "logps/rejected": -0.38699784874916077,
+      "loss": 0.9172,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.4415270686149597,
+      "rewards/margins": 0.13896968960762024,
+      "rewards/rejected": -0.5804967880249023,
+      "step": 70
+    },
+    {
+      "epoch": 0.06875805758487323,
+      "grad_norm": 0.07169903814792633,
+      "learning_rate": 4.964990092676263e-06,
+      "logits/chosen": 13.848808288574219,
+      "logits/rejected": 14.609800338745117,
+      "logps/chosen": -0.26156893372535706,
+      "logps/rejected": -0.33030644059181213,
+      "loss": 0.9245,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.3923533856868744,
+      "rewards/margins": 0.10310628265142441,
+      "rewards/rejected": -0.495459645986557,
+      "step": 80
+    },
+    {
+      "epoch": 0.07735281478298238,
+      "grad_norm": 0.06593246012926102,
+      "learning_rate": 4.9557181268217225e-06,
+      "logits/chosen": 14.603567123413086,
+      "logits/rejected": 14.994171142578125,
+      "logps/chosen": -0.3191321790218353,
+      "logps/rejected": -0.3477073311805725,
+      "loss": 0.9359,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.4786983132362366,
+      "rewards/margins": 0.042862698435783386,
+      "rewards/rejected": -0.5215609669685364,
+      "step": 90
+    },
+    {
+      "epoch": 0.08594757198109153,
+      "grad_norm": 0.0718066617846489,
+      "learning_rate": 4.9453690018345144e-06,
+      "logits/chosen": 13.928094863891602,
+      "logits/rejected": 14.792709350585938,
+      "logps/chosen": -0.24115696549415588,
+      "logps/rejected": -0.3537539839744568,
+      "loss": 0.9066,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.3617354929447174,
+      "rewards/margins": 0.16889554262161255,
+      "rewards/rejected": -0.5306310653686523,
+      "step": 100
+    },
+    {
+      "epoch": 0.08594757198109153,
+      "eval_logits/chosen": 14.40036392211914,
+      "eval_logits/rejected": 14.97786808013916,
+      "eval_logps/chosen": -0.2777771055698395,
+      "eval_logps/rejected": -0.3516874611377716,
+      "eval_loss": 0.9236211180686951,
+      "eval_rewards/accuracies": 0.5052631497383118,
+      "eval_rewards/chosen": -0.4166657328605652,
+      "eval_rewards/margins": 0.11086549609899521,
+      "eval_rewards/rejected": -0.5275312066078186,
+      "eval_runtime": 25.8056,
+      "eval_samples_per_second": 29.18,
+      "eval_steps_per_second": 3.681,
+      "step": 100
+    },
+    {
+      "epoch": 0.09454232917920069,
+      "grad_norm": 0.06681054830551147,
+      "learning_rate": 4.933947257182901e-06,
+      "logits/chosen": 14.76116943359375,
+      "logits/rejected": 15.001077651977539,
+      "logps/chosen": -0.297056645154953,
+      "logps/rejected": -0.3221590518951416,
+      "loss": 0.929,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.4455850124359131,
+      "rewards/margins": 0.03765357658267021,
+      "rewards/rejected": -0.4832385182380676,
+      "step": 110
+    },
+    {
+      "epoch": 0.10313708637730984,
+      "grad_norm": 0.10024584829807281,
+      "learning_rate": 4.921457902821578e-06,
+      "logits/chosen": 14.405306816101074,
+      "logits/rejected": 15.084524154663086,
+      "logps/chosen": -0.2726767361164093,
+      "logps/rejected": -0.3543504774570465,
+      "loss": 0.9299,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.40901508927345276,
+      "rewards/margins": 0.12251058965921402,
+      "rewards/rejected": -0.531525731086731,
+      "step": 120
+    },
+    {
+      "epoch": 0.11173184357541899,
+      "grad_norm": 0.08629737794399261,
+      "learning_rate": 4.907906416994146e-06,
+      "logits/chosen": 14.073992729187012,
+      "logits/rejected": 14.882128715515137,
+      "logps/chosen": -0.2827032506465912,
+      "logps/rejected": -0.369393527507782,
+      "loss": 0.9109,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.42405492067337036,
+      "rewards/margins": 0.13003548979759216,
+      "rewards/rejected": -0.5540903806686401,
+      "step": 130
+    },
+    {
+      "epoch": 0.12032660077352815,
+      "grad_norm": 0.07973086833953857,
+      "learning_rate": 4.893298743830168e-06,
+      "logits/chosen": 13.96656322479248,
+      "logits/rejected": 14.639463424682617,
+      "logps/chosen": -0.28426361083984375,
+      "logps/rejected": -0.3899250030517578,
+      "loss": 0.9138,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.4263954162597656,
+      "rewards/margins": 0.1584920585155487,
+      "rewards/rejected": -0.5848874449729919,
+      "step": 140
+    },
+    {
+      "epoch": 0.1289213579716373,
+      "grad_norm": 0.08767445385456085,
+      "learning_rate": 4.8776412907378845e-06,
+      "logits/chosen": 13.705177307128906,
+      "logits/rejected": 14.19865608215332,
+      "logps/chosen": -0.26735779643058777,
+      "logps/rejected": -0.34726911783218384,
+      "loss": 0.9157,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.40103667974472046,
+      "rewards/margins": 0.1198669821023941,
+      "rewards/rejected": -0.5209037065505981,
+      "step": 150
+    },
+    {
+      "epoch": 0.1289213579716373,
+      "eval_logits/chosen": 13.20260238647461,
+      "eval_logits/rejected": 13.959339141845703,
+      "eval_logps/chosen": -0.27623170614242554,
+      "eval_logps/rejected": -0.3724917769432068,
+      "eval_loss": 0.909102737903595,
+      "eval_rewards/accuracies": 0.557894766330719,
+      "eval_rewards/chosen": -0.4143475592136383,
+      "eval_rewards/margins": 0.14439010620117188,
+      "eval_rewards/rejected": -0.5587376356124878,
+      "eval_runtime": 25.7839,
+      "eval_samples_per_second": 29.204,
+      "eval_steps_per_second": 3.684,
+      "step": 150
+    },
+    {
+      "epoch": 0.13751611516974646,
+      "grad_norm": 0.09749539196491241,
+      "learning_rate": 4.860940925593703e-06,
+      "logits/chosen": 13.301411628723145,
+      "logits/rejected": 14.054819107055664,
+      "logps/chosen": -0.2808162569999695,
+      "logps/rejected": -0.39500662684440613,
+      "loss": 0.9,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.4212244153022766,
+      "rewards/margins": 0.17128555476665497,
+      "rewards/rejected": -0.592509925365448,
+      "step": 160
+    },
+    {
+      "epoch": 0.1461108723678556,
+      "grad_norm": 0.14965052902698517,
+      "learning_rate": 4.84320497372973e-06,
+      "logits/chosen": 12.261284828186035,
+      "logits/rejected": 13.0617036819458,
+      "logps/chosen": -0.29266461730003357,
+      "logps/rejected": -0.4265298843383789,
+      "loss": 0.896,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.43899694085121155,
+      "rewards/margins": 0.20079784095287323,
+      "rewards/rejected": -0.6397948265075684,
+      "step": 170
+    },
+    {
+      "epoch": 0.15470562956596476,
+      "grad_norm": 0.13044072687625885,
+      "learning_rate": 4.824441214720629e-06,
+      "logits/chosen": 11.509119033813477,
+      "logits/rejected": 12.31033706665039,
+      "logps/chosen": -0.27384257316589355,
+      "logps/rejected": -0.3920982778072357,
+      "loss": 0.8911,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.4107638895511627,
+      "rewards/margins": 0.17738358676433563,
+      "rewards/rejected": -0.5881474018096924,
+      "step": 180
+    },
+    {
+      "epoch": 0.1633003867640739,
+      "grad_norm": 0.16182811558246613,
+      "learning_rate": 4.804657878971252e-06,
+      "logits/chosen": 10.68933391571045,
+      "logits/rejected": 11.632065773010254,
+      "logps/chosen": -0.292975515127182,
+      "logps/rejected": -0.42257896065711975,
+      "loss": 0.9002,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.4394632875919342,
+      "rewards/margins": 0.19440510869026184,
+      "rewards/rejected": -0.633868396282196,
+      "step": 190
+    },
+    {
+      "epoch": 0.17189514396218306,
+      "grad_norm": 0.181160107254982,
+      "learning_rate": 4.783863644106502e-06,
+      "logits/chosen": 10.593437194824219,
+      "logits/rejected": 11.435877799987793,
+      "logps/chosen": -0.32495418190956116,
+      "logps/rejected": -0.4480825364589691,
+      "loss": 0.8773,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.48743128776550293,
+      "rewards/margins": 0.18469250202178955,
+      "rewards/rejected": -0.6721237897872925,
+      "step": 200
+    },
+    {
+      "epoch": 0.17189514396218306,
+      "eval_logits/chosen": 9.299257278442383,
+      "eval_logits/rejected": 10.055145263671875,
+      "eval_logps/chosen": -0.31059205532073975,
+      "eval_logps/rejected": -0.47102925181388855,
+      "eval_loss": 0.8721462488174438,
+      "eval_rewards/accuracies": 0.6105263233184814,
+      "eval_rewards/chosen": -0.4658880829811096,
+      "eval_rewards/margins": 0.24065588414669037,
+      "eval_rewards/rejected": -0.7065439224243164,
+      "eval_runtime": 25.78,
+      "eval_samples_per_second": 29.209,
+      "eval_steps_per_second": 3.685,
+      "step": 200
+    },
+    {
+      "epoch": 0.18048990116029223,
+      "grad_norm": 0.24912959337234497,
+      "learning_rate": 4.762067631165049e-06,
+      "logits/chosen": 8.803088188171387,
+      "logits/rejected": 9.326388359069824,
+      "logps/chosen": -0.3249451816082001,
+      "logps/rejected": -0.44993042945861816,
+      "loss": 0.8484,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.4874177575111389,
+      "rewards/margins": 0.18747788667678833,
+      "rewards/rejected": -0.6748956441879272,
+      "step": 210
+    },
+    {
+      "epoch": 0.18908465835840138,
+      "grad_norm": 0.319579541683197,
+      "learning_rate": 4.7392794005985324e-06,
+      "logits/chosen": 6.257112979888916,
+      "logits/rejected": 7.168400764465332,
+      "logps/chosen": -0.335318386554718,
+      "logps/rejected": -0.5439311265945435,
+      "loss": 0.8499,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.5029775500297546,
+      "rewards/margins": 0.31291908025741577,
+      "rewards/rejected": -0.8158966302871704,
+      "step": 220
+    },
+    {
+      "epoch": 0.19767941555651053,
+      "grad_norm": 0.31494757533073425,
+      "learning_rate": 4.715508948078037e-06,
+      "logits/chosen": 5.725883960723877,
+      "logits/rejected": 5.9254865646362305,
+      "logps/chosen": -0.3735908567905426,
+      "logps/rejected": -0.5729750394821167,
+      "loss": 0.826,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.5603862404823303,
+      "rewards/margins": 0.2990763187408447,
+      "rewards/rejected": -0.859462559223175,
+      "step": 230
+    },
+    {
+      "epoch": 0.20627417275461968,
+      "grad_norm": 0.46439653635025024,
+      "learning_rate": 4.690766700109659e-06,
+      "logits/chosen": 5.059751033782959,
+      "logits/rejected": 5.128623008728027,
+      "logps/chosen": -0.4083784222602844,
+      "logps/rejected": -0.6792675852775574,
+      "loss": 0.7992,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.612567663192749,
+      "rewards/margins": 0.40633392333984375,
+      "rewards/rejected": -1.0189014673233032,
+      "step": 240
+    },
+    {
+      "epoch": 0.21486892995272883,
+      "grad_norm": 0.42406076192855835,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 4.128974437713623,
+      "logits/rejected": 4.141166687011719,
+      "logps/chosen": -0.4256651997566223,
+      "logps/rejected": -0.7279168367385864,
+      "loss": 0.7848,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.6384977102279663,
+      "rewards/margins": 0.4533773958683014,
+      "rewards/rejected": -1.0918750762939453,
+      "step": 250
+    },
+    {
+      "epoch": 0.21486892995272883,
+      "eval_logits/chosen": 3.800307512283325,
+      "eval_logits/rejected": 3.1472771167755127,
+      "eval_logps/chosen": -0.4563433527946472,
+      "eval_logps/rejected": -0.8247694373130798,
+      "eval_loss": 0.7728626728057861,
+      "eval_rewards/accuracies": 0.6526315808296204,
+      "eval_rewards/chosen": -0.6845150589942932,
+      "eval_rewards/margins": 0.5526391267776489,
+      "eval_rewards/rejected": -1.237154245376587,
+      "eval_runtime": 25.7836,
+      "eval_samples_per_second": 29.205,
+      "eval_steps_per_second": 3.685,
+      "step": 250
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.4071955680847168,
+      "learning_rate": 4.638410650401267e-06,
+      "logits/chosen": 3.169527530670166,
+      "logits/rejected": 2.603461503982544,
+      "logps/chosen": -0.5029922723770142,
+      "logps/rejected": -0.9469219446182251,
+      "loss": 0.7273,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.7544883489608765,
+      "rewards/margins": 0.6658946871757507,
+      "rewards/rejected": -1.4203828573226929,
+      "step": 260
+    },
+    {
+      "epoch": 0.23205844434894715,
+      "grad_norm": 0.6253886222839355,
+      "learning_rate": 4.610819813755038e-06,
+      "logits/chosen": 3.8718018531799316,
+      "logits/rejected": 2.569753646850586,
+      "logps/chosen": -0.4955294132232666,
+      "logps/rejected": -0.8811863660812378,
+      "loss": 0.7483,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7432941198348999,
+      "rewards/margins": 0.5784854888916016,
+      "rewards/rejected": -1.321779489517212,
+      "step": 270
+    },
+    {
+      "epoch": 0.2406532015470563,
+      "grad_norm": 0.5592113733291626,
+      "learning_rate": 4.582303101775249e-06,
+      "logits/chosen": 3.4818286895751953,
+      "logits/rejected": 2.428328275680542,
+      "logps/chosen": -0.5700691342353821,
+      "logps/rejected": -1.010145664215088,
+      "loss": 0.7165,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.8551036715507507,
+      "rewards/margins": 0.6601148843765259,
+      "rewards/rejected": -1.5152184963226318,
+      "step": 280
+    },
+    {
+      "epoch": 0.24924795874516545,
+      "grad_norm": 0.8438608050346375,
+      "learning_rate": 4.55287302283426e-06,
+      "logits/chosen": 2.5937914848327637,
+      "logits/rejected": 1.8570162057876587,
+      "logps/chosen": -0.592321515083313,
+      "logps/rejected": -1.1775600910186768,
+      "loss": 0.6685,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.8884822130203247,
+      "rewards/margins": 0.8778578042984009,
+      "rewards/rejected": -1.7663400173187256,
+      "step": 290
+    },
+    {
+      "epoch": 0.2578427159432746,
+      "grad_norm": 2.9559757709503174,
+      "learning_rate": 4.522542485937369e-06,
+      "logits/chosen": 3.2419090270996094,
+      "logits/rejected": 1.9082870483398438,
+      "logps/chosen": -0.6832663416862488,
+      "logps/rejected": -1.5631868839263916,
+      "loss": 0.6009,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -1.0248994827270508,
+      "rewards/margins": 1.3198809623718262,
+      "rewards/rejected": -2.344780445098877,
+      "step": 300
+    },
+    {
+      "epoch": 0.2578427159432746,
+      "eval_logits/chosen": 2.5470504760742188,
+      "eval_logits/rejected": 1.492888331413269,
+      "eval_logps/chosen": -0.7285813689231873,
+      "eval_logps/rejected": -1.8318607807159424,
+      "eval_loss": 0.5855891704559326,
+      "eval_rewards/accuracies": 0.7052631378173828,
+      "eval_rewards/chosen": -1.092872142791748,
+      "eval_rewards/margins": 1.6549187898635864,
+      "eval_rewards/rejected": -2.747790813446045,
+      "eval_runtime": 25.8105,
+      "eval_samples_per_second": 29.174,
+      "eval_steps_per_second": 3.681,
+      "step": 300
+    },
+    {
+      "epoch": 0.2664374731413838,
+      "grad_norm": 1.4503060579299927,
+      "learning_rate": 4.491324795060491e-06,
+      "logits/chosen": 1.6672757863998413,
+      "logits/rejected": 0.7888604402542114,
+      "logps/chosen": -0.769140899181366,
+      "logps/rejected": -2.0822532176971436,
+      "loss": 0.512,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.1537113189697266,
+      "rewards/margins": 1.9696683883666992,
+      "rewards/rejected": -3.123379945755005,
+      "step": 310
+    },
+    {
+      "epoch": 0.2750322303394929,
+      "grad_norm": 0.36741188168525696,
+      "learning_rate": 4.4592336433146e-06,
+      "logits/chosen": 2.6584715843200684,
+      "logits/rejected": 1.835911750793457,
+      "logps/chosen": -0.8400143384933472,
+      "logps/rejected": -1.9262489080429077,
+      "loss": 0.5405,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -1.2600215673446655,
+      "rewards/margins": 1.6293519735336304,
+      "rewards/rejected": -2.889373302459717,
+      "step": 320
+    },
+    {
+      "epoch": 0.28362698753760207,
+      "grad_norm": 0.6233783960342407,
+      "learning_rate": 4.426283106939474e-06,
+      "logits/chosen": 3.2203617095947266,
+      "logits/rejected": 2.3215420246124268,
+      "logps/chosen": -0.7985933423042297,
+      "logps/rejected": -2.4170174598693848,
+      "loss": 0.5335,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -1.197890043258667,
+      "rewards/margins": 2.427635669708252,
+      "rewards/rejected": -3.625525712966919,
+      "step": 330
+    },
+    {
+      "epoch": 0.2922217447357112,
+      "grad_norm": 1.0881849527359009,
+      "learning_rate": 4.3924876391293915e-06,
+      "logits/chosen": 2.229017734527588,
+      "logits/rejected": 1.2251309156417847,
+      "logps/chosen": -0.8058193325996399,
+      "logps/rejected": -2.810622215270996,
+      "loss": 0.4903,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.2087291479110718,
+      "rewards/margins": 3.007204294204712,
+      "rewards/rejected": -4.215933799743652,
+      "step": 340
+    },
+    {
+      "epoch": 0.30081650193382037,
+      "grad_norm": 4.168415069580078,
+      "learning_rate": 4.357862063693486e-06,
+      "logits/chosen": 2.4198296070098877,
+      "logits/rejected": 1.5391919612884521,
+      "logps/chosen": -1.010558843612671,
+      "logps/rejected": -2.2362923622131348,
+      "loss": 0.5249,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.515838384628296,
+      "rewards/margins": 1.8385999202728271,
+      "rewards/rejected": -3.3544387817382812,
+      "step": 350
+    },
+    {
+      "epoch": 0.30081650193382037,
+      "eval_logits/chosen": 2.996535539627075,
+      "eval_logits/rejected": 2.064058303833008,
+      "eval_logps/chosen": -0.8687878847122192,
+      "eval_logps/rejected": -2.9790267944335938,
+      "eval_loss": 0.5171241760253906,
+      "eval_rewards/accuracies": 0.7263157963752747,
+      "eval_rewards/chosen": -1.3031818866729736,
+      "eval_rewards/margins": 3.165358781814575,
+      "eval_rewards/rejected": -4.468540668487549,
+      "eval_runtime": 25.8152,
+      "eval_samples_per_second": 29.169,
+      "eval_steps_per_second": 3.68,
+      "step": 350
+    },
+    {
+      "epoch": 0.3094112591319295,
+      "grad_norm": 0.5646592378616333,
+      "learning_rate": 4.322421568553529e-06,
+      "logits/chosen": 3.050445556640625,
+      "logits/rejected": 2.0960793495178223,
+      "logps/chosen": -0.7702202796936035,
+      "logps/rejected": -2.5967533588409424,
+      "loss": 0.5067,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -1.1553303003311157,
+      "rewards/margins": 2.739799737930298,
+      "rewards/rejected": -3.895130157470703,
+      "step": 360
+    },
+    {
+      "epoch": 0.31800601633003867,
+      "grad_norm": 0.5547713041305542,
+      "learning_rate": 4.286181699082008e-06,
+      "logits/chosen": 2.7148895263671875,
+      "logits/rejected": 1.9958852529525757,
+      "logps/chosen": -0.9548311233520508,
+      "logps/rejected": -3.1348252296447754,
+      "loss": 0.4726,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.4322465658187866,
+      "rewards/margins": 3.269991397857666,
+      "rewards/rejected": -4.702237606048584,
+      "step": 370
+    },
+    {
+      "epoch": 0.3266007735281478,
+      "grad_norm": 3.4396660327911377,
+      "learning_rate": 4.249158351283414e-06,
+      "logits/chosen": 2.586766004562378,
+      "logits/rejected": 2.070089340209961,
+      "logps/chosen": -0.9903923273086548,
+      "logps/rejected": -3.0135743618011475,
+      "loss": 0.4801,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -1.485588550567627,
+      "rewards/margins": 3.034773349761963,
+      "rewards/rejected": -4.52036190032959,
+      "step": 380
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.9405317306518555,
+      "learning_rate": 4.211367764821722e-06,
+      "logits/chosen": 4.370789527893066,
+      "logits/rejected": 3.165931224822998,
+      "logps/chosen": -0.7785463929176331,
+      "logps/rejected": -2.456723928451538,
+      "loss": 0.4585,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -1.1678194999694824,
+      "rewards/margins": 2.5172665119171143,
+      "rewards/rejected": -3.6850857734680176,
+      "step": 390
+    },
+    {
+      "epoch": 0.3437902879243661,
+      "grad_norm": 0.7120731472969055,
+      "learning_rate": 4.172826515897146e-06,
+      "logits/chosen": 3.3425400257110596,
+      "logits/rejected": 2.6448545455932617,
+      "logps/chosen": -0.9174768328666687,
+      "logps/rejected": -3.047037124633789,
+      "loss": 0.4771,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -1.3762153387069702,
+      "rewards/margins": 3.194340229034424,
+      "rewards/rejected": -4.570555686950684,
+      "step": 400
+    },
+    {
+      "epoch": 0.3437902879243661,
+      "eval_logits/chosen": 3.548964262008667,
+      "eval_logits/rejected": 2.7726428508758545,
+      "eval_logps/chosen": -1.0053316354751587,
+      "eval_logps/rejected": -3.487654447555542,
+      "eval_loss": 0.47841358184814453,
+      "eval_rewards/accuracies": 0.7368420958518982,
+      "eval_rewards/chosen": -1.5079973936080933,
+      "eval_rewards/margins": 3.723484992980957,
+      "eval_rewards/rejected": -5.231482028961182,
+      "eval_runtime": 25.8148,
+      "eval_samples_per_second": 29.169,
+      "eval_steps_per_second": 3.68,
+      "step": 400
+    },
+    {
+      "epoch": 0.3523850451224753,
+      "grad_norm": 2.403956651687622,
+      "learning_rate": 4.133551509975264e-06,
+      "logits/chosen": 3.2028489112854004,
+      "logits/rejected": 2.2486982345581055,
+      "logps/chosen": -0.9957242012023926,
+      "logps/rejected": -3.243959426879883,
+      "loss": 0.4449,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -1.4935863018035889,
+      "rewards/margins": 3.3723526000976562,
+      "rewards/rejected": -4.865939140319824,
+      "step": 410
+    },
+    {
+      "epoch": 0.36097980232058446,
+      "grad_norm": 0.39530256390571594,
+      "learning_rate": 4.093559974371725e-06,
+      "logits/chosen": 3.8590214252471924,
+      "logits/rejected": 3.1420931816101074,
+      "logps/chosen": -0.9541120529174805,
+      "logps/rejected": -3.0112829208374023,
+      "loss": 0.4598,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.4311680793762207,
+      "rewards/margins": 3.085756301879883,
+      "rewards/rejected": -4.5169243812561035,
+      "step": 420
+    },
+    {
+      "epoch": 0.3695745595186936,
+      "grad_norm": 0.29451707005500793,
+      "learning_rate": 4.052869450695776e-06,
+      "logits/chosen": 4.697268486022949,
+      "logits/rejected": 3.7647697925567627,
+      "logps/chosen": -1.1037578582763672,
+      "logps/rejected": -3.8626160621643066,
+      "loss": 0.4275,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.6556367874145508,
+      "rewards/margins": 4.138287544250488,
+      "rewards/rejected": -5.793923854827881,
+      "step": 430
+    },
+    {
+      "epoch": 0.37816931671680276,
+      "grad_norm": 0.5065125823020935,
+      "learning_rate": 4.011497787155938e-06,
+      "logits/chosen": 3.5233864784240723,
+      "logits/rejected": 2.798567533493042,
+      "logps/chosen": -1.1753087043762207,
+      "logps/rejected": -4.171238899230957,
+      "loss": 0.4132,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.7629629373550415,
+      "rewards/margins": 4.493895053863525,
+      "rewards/rejected": -6.256857872009277,
+      "step": 440
+    },
+    {
+      "epoch": 0.3867640739149119,
+      "grad_norm": 1.414167881011963,
+      "learning_rate": 3.969463130731183e-06,
+      "logits/chosen": 4.733740329742432,
+      "logits/rejected": 4.114102363586426,
+      "logps/chosen": -1.1846634149551392,
+      "logps/rejected": -4.04649543762207,
+      "loss": 0.4266,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.776995301246643,
+      "rewards/margins": 4.292747974395752,
+      "rewards/rejected": -6.0697431564331055,
+      "step": 450
+    },
+    {
+      "epoch": 0.3867640739149119,
+      "eval_logits/chosen": 4.25229549407959,
+      "eval_logits/rejected": 3.900564193725586,
+      "eval_logps/chosen": -1.410205602645874,
+      "eval_logps/rejected": -4.276910781860352,
+      "eval_loss": 0.4397798478603363,
+      "eval_rewards/accuracies": 0.800000011920929,
+      "eval_rewards/chosen": -2.1153085231781006,
+      "eval_rewards/margins": 4.3000569343566895,
+      "eval_rewards/rejected": -6.415364742279053,
+      "eval_runtime": 25.7968,
+      "eval_samples_per_second": 29.19,
+      "eval_steps_per_second": 3.683,
+      "step": 450
+    },
+    {
+      "epoch": 0.39535883111302106,
+      "grad_norm": 1.7992101907730103,
+      "learning_rate": 3.92678391921108e-06,
+      "logits/chosen": 4.718934059143066,
+      "logits/rejected": 4.305315971374512,
+      "logps/chosen": -1.423595666885376,
+      "logps/rejected": -3.9873733520507812,
+      "loss": 0.367,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -2.1353936195373535,
+      "rewards/margins": 3.8456661701202393,
+      "rewards/rejected": -5.981060028076172,
+      "step": 460
+    },
+    {
+      "epoch": 0.4039535883111302,
+      "grad_norm": 1.9630879163742065,
+      "learning_rate": 3.88347887310836e-06,
+      "logits/chosen": 3.8371150493621826,
+      "logits/rejected": 3.5719306468963623,
+      "logps/chosen": -2.0386481285095215,
+      "logps/rejected": -4.779314994812012,
+      "loss": 0.3957,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -3.0579724311828613,
+      "rewards/margins": 4.1110005378723145,
+      "rewards/rejected": -7.168972969055176,
+      "step": 470
+    },
+    {
+      "epoch": 0.41254834550923936,
+      "grad_norm": 4.952139854431152,
+      "learning_rate": 3.839566987447492e-06,
+      "logits/chosen": 5.024113655090332,
+      "logits/rejected": 4.880651950836182,
+      "logps/chosen": -2.3612470626831055,
+      "logps/rejected": -4.691690444946289,
+      "loss": 0.3808,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -3.5418708324432373,
+      "rewards/margins": 3.495664596557617,
+      "rewards/rejected": -7.037535190582275,
+      "step": 480
+    },
+    {
+      "epoch": 0.4211431027073485,
+      "grad_norm": 2.832200527191162,
+      "learning_rate": 3.795067523432826e-06,
+      "logits/chosen": 4.689079284667969,
+      "logits/rejected": 4.435003280639648,
+      "logps/chosen": -2.437671184539795,
+      "logps/rejected": -5.003944396972656,
+      "loss": 0.3555,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -3.6565067768096924,
+      "rewards/margins": 3.849409580230713,
+      "rewards/rejected": -7.505916595458984,
+      "step": 490
+    },
+    {
+      "epoch": 0.42973785990545765,
+      "grad_norm": 3.2997682094573975,
+      "learning_rate": 3.7500000000000005e-06,
+      "logits/chosen": 4.286547660827637,
+      "logits/rejected": 4.181652545928955,
+      "logps/chosen": -2.3390612602233887,
+      "logps/rejected": -4.888935565948486,
+      "loss": 0.3211,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -3.508591890335083,
+      "rewards/margins": 3.8248119354248047,
+      "rewards/rejected": -7.333403587341309,
+      "step": 500
+    },
+    {
+      "epoch": 0.42973785990545765,
+      "eval_logits/chosen": 3.5323922634124756,
+      "eval_logits/rejected": 3.5116958618164062,
+      "eval_logps/chosen": -2.679356575012207,
+      "eval_logps/rejected": -5.927057266235352,
+      "eval_loss": 0.37026864290237427,
+      "eval_rewards/accuracies": 0.8736842274665833,
+      "eval_rewards/chosen": -4.019035339355469,
+      "eval_rewards/margins": 4.871551036834717,
+      "eval_rewards/rejected": -8.890586853027344,
+      "eval_runtime": 25.8768,
+      "eval_samples_per_second": 29.099,
+      "eval_steps_per_second": 3.671,
+      "step": 500
+    },
+    {
+      "epoch": 0.4383326171035668,
+      "grad_norm": 2.6194217205047607,
+      "learning_rate": 3.7043841852542884e-06,
+      "logits/chosen": 4.265946388244629,
+      "logits/rejected": 3.7863662242889404,
+      "logps/chosen": -2.279764413833618,
+      "logps/rejected": -4.825397968292236,
+      "loss": 0.3375,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -3.4196460247039795,
+      "rewards/margins": 3.818450927734375,
+      "rewards/rejected": -7.238096714019775,
+      "step": 510
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 4.434008598327637,
+      "learning_rate": 3.658240087799655e-06,
+      "logits/chosen": 3.4983534812927246,
+      "logits/rejected": 3.3109116554260254,
+      "logps/chosen": -2.7063632011413574,
+      "logps/rejected": -5.9535369873046875,
+      "loss": 0.3388,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -4.059545040130615,
+      "rewards/margins": 4.870760917663574,
+      "rewards/rejected": -8.930305480957031,
+      "step": 520
+    },
+    {
+      "epoch": 0.45552213149978515,
+      "grad_norm": 2.4193809032440186,
+      "learning_rate": 3.611587947962319e-06,
+      "logits/chosen": 3.4949145317077637,
+      "logits/rejected": 3.402980089187622,
+      "logps/chosen": -2.5146005153656006,
+      "logps/rejected": -5.63289737701416,
+      "loss": 0.3281,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -3.7719013690948486,
+      "rewards/margins": 4.677445411682129,
+      "rewards/rejected": -8.449346542358398,
+      "step": 530
+    },
+    {
+      "epoch": 0.4641168886978943,
+      "grad_norm": 10.788633346557617,
+      "learning_rate": 3.564448228912682e-06,
+      "logits/chosen": 3.3073112964630127,
+      "logits/rejected": 3.163470506668091,
+      "logps/chosen": -2.258653163909912,
+      "logps/rejected": -5.642867088317871,
+      "loss": 0.3565,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -3.387979507446289,
+      "rewards/margins": 5.076320648193359,
+      "rewards/rejected": -8.464300155639648,
+      "step": 540
+    },
+    {
+      "epoch": 0.47271164589600345,
+      "grad_norm": 1.6846323013305664,
+      "learning_rate": 3.516841607689501e-06,
+      "logits/chosen": 3.476361036300659,
+      "logits/rejected": 3.375828504562378,
+      "logps/chosen": -2.5325064659118652,
+      "logps/rejected": -5.799270153045654,
+      "loss": 0.3103,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -3.798759937286377,
+      "rewards/margins": 4.900145530700684,
+      "rewards/rejected": -8.698905944824219,
+      "step": 550
+    },
+    {
+      "epoch": 0.47271164589600345,
+      "eval_logits/chosen": 3.451749563217163,
+      "eval_logits/rejected": 3.3771002292633057,
+      "eval_logps/chosen": -2.9835667610168457,
+      "eval_logps/rejected": -6.5389509201049805,
+      "eval_loss": 0.32732319831848145,
+      "eval_rewards/accuracies": 0.9052631855010986,
+      "eval_rewards/chosen": -4.475350379943848,
+      "eval_rewards/margins": 5.333076000213623,
+      "eval_rewards/rejected": -9.808425903320312,
+      "eval_runtime": 25.8141,
+      "eval_samples_per_second": 29.17,
+      "eval_steps_per_second": 3.68,
+      "step": 550
+    },
+    {
+      "epoch": 0.4813064030941126,
+      "grad_norm": 2.7683331966400146,
+      "learning_rate": 3.4687889661302577e-06,
+      "logits/chosen": 2.468799591064453,
+      "logits/rejected": 2.4257254600524902,
+      "logps/chosen": -2.6801788806915283,
+      "logps/rejected": -6.136897087097168,
+      "loss": 0.3171,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -4.020268440246582,
+      "rewards/margins": 5.185078144073486,
+      "rewards/rejected": -9.205347061157227,
+      "step": 560
+    },
+    {
+      "epoch": 0.48990116029222175,
+      "grad_norm": 11.559685707092285,
+      "learning_rate": 3.4203113817116955e-06,
+      "logits/chosen": 3.6535427570343018,
+      "logits/rejected": 3.583962917327881,
+      "logps/chosen": -2.7984983921051025,
+      "logps/rejected": -6.468808650970459,
+      "loss": 0.331,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.197747707366943,
+      "rewards/margins": 5.505465984344482,
+      "rewards/rejected": -9.703214645385742,
+      "step": 570
+    },
+    {
+      "epoch": 0.4984959174903309,
+      "grad_norm": 7.691457271575928,
+      "learning_rate": 3.3714301183045382e-06,
+      "logits/chosen": 2.7467286586761475,
+      "logits/rejected": 2.4911317825317383,
+      "logps/chosen": -2.4207634925842285,
+      "logps/rejected": -6.385074138641357,
+      "loss": 0.2557,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -3.631145477294922,
+      "rewards/margins": 5.946464538574219,
+      "rewards/rejected": -9.577610969543457,
+      "step": 580
+    },
+    {
+      "epoch": 0.50709067468844,
+      "grad_norm": 5.381045341491699,
+      "learning_rate": 3.3221666168464584e-06,
+      "logits/chosen": 3.239227294921875,
+      "logits/rejected": 3.1982555389404297,
+      "logps/chosen": -3.2162883281707764,
+      "logps/rejected": -6.693168640136719,
+      "loss": 0.2921,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.824432373046875,
+      "rewards/margins": 5.215321063995361,
+      "rewards/rejected": -10.039752960205078,
+      "step": 590
+    },
+    {
+      "epoch": 0.5156854318865493,
+      "grad_norm": 2.616710901260376,
+      "learning_rate": 3.272542485937369e-06,
+      "logits/chosen": 2.7326784133911133,
+      "logits/rejected": 2.4248623847961426,
+      "logps/chosen": -3.001952648162842,
+      "logps/rejected": -6.597250461578369,
+      "loss": 0.3225,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.502928733825684,
+      "rewards/margins": 5.392947196960449,
+      "rewards/rejected": -9.89587688446045,
+      "step": 600
+    },
+    {
+      "epoch": 0.5156854318865493,
+      "eval_logits/chosen": 3.1995701789855957,
+      "eval_logits/rejected": 3.2761952877044678,
+      "eval_logps/chosen": -3.166325330734253,
+      "eval_logps/rejected": -7.062953472137451,
+      "eval_loss": 0.29786577820777893,
+      "eval_rewards/accuracies": 0.9263157844543457,
+      "eval_rewards/chosen": -4.74948787689209,
+      "eval_rewards/margins": 5.84494161605835,
+      "eval_rewards/rejected": -10.594429969787598,
+      "eval_runtime": 25.8074,
+      "eval_samples_per_second": 29.178,
+      "eval_steps_per_second": 3.681,
+      "step": 600
+    },
+    {
+      "epoch": 0.5242801890846583,
+      "grad_norm": 3.5550060272216797,
+      "learning_rate": 3.222579492361179e-06,
+      "logits/chosen": 2.8619818687438965,
+      "logits/rejected": 3.014125347137451,
+      "logps/chosen": -2.9217543601989746,
+      "logps/rejected": -6.349586486816406,
+      "loss": 0.2516,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.382631301879883,
+      "rewards/margins": 5.141747951507568,
+      "rewards/rejected": -9.52437973022461,
+      "step": 610
+    },
+    {
+      "epoch": 0.5328749462827675,
+      "grad_norm": 3.6020898818969727,
+      "learning_rate": 3.1722995515381644e-06,
+      "logits/chosen": 2.770552635192871,
+      "logits/rejected": 2.9711716175079346,
+      "logps/chosen": -2.8700039386749268,
+      "logps/rejected": -6.527164459228516,
+      "loss": 0.3062,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.305006504058838,
+      "rewards/margins": 5.485739707946777,
+      "rewards/rejected": -9.790745735168457,
+      "step": 620
+    },
+    {
+      "epoch": 0.5414697034808766,
+      "grad_norm": 2.2209339141845703,
+      "learning_rate": 3.121724717912138e-06,
+      "logits/chosen": 3.1150155067443848,
+      "logits/rejected": 3.038687229156494,
+      "logps/chosen": -2.9821603298187256,
+      "logps/rejected": -6.432187080383301,
+      "loss": 0.2726,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.473240852355957,
+      "rewards/margins": 5.175040245056152,
+      "rewards/rejected": -9.648280143737793,
+      "step": 630
+    },
+    {
+      "epoch": 0.5500644606789858,
+      "grad_norm": 2.148709297180176,
+      "learning_rate": 3.0708771752766397e-06,
+      "logits/chosen": 3.256204605102539,
+      "logits/rejected": 2.9765384197235107,
+      "logps/chosen": -2.7979862689971924,
+      "logps/rejected": -6.7102813720703125,
+      "loss": 0.2861,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.196979522705078,
+      "rewards/margins": 5.868442535400391,
+      "rewards/rejected": -10.065422058105469,
+      "step": 640
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "grad_norm": 7.988170623779297,
+      "learning_rate": 3.019779227044398e-06,
+      "logits/chosen": 2.7312607765197754,
+      "logits/rejected": 2.705409526824951,
+      "logps/chosen": -2.8119194507598877,
+      "logps/rejected": -6.627874851226807,
+      "loss": 0.2507,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.217879295349121,
+      "rewards/margins": 5.723933219909668,
+      "rewards/rejected": -9.941811561584473,
+      "step": 650
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "eval_logits/chosen": 2.9934144020080566,
+      "eval_logits/rejected": 3.124950647354126,
+      "eval_logps/chosen": -3.1934540271759033,
+      "eval_logps/rejected": -7.429007053375244,
+      "eval_loss": 0.28581172227859497,
+      "eval_rewards/accuracies": 0.9368420839309692,
+      "eval_rewards/chosen": -4.7901811599731445,
+      "eval_rewards/margins": 6.353330135345459,
+      "eval_rewards/rejected": -11.143510818481445,
+      "eval_runtime": 25.8075,
+      "eval_samples_per_second": 29.178,
+      "eval_steps_per_second": 3.681,
+      "step": 650
+    },
+    {
+      "epoch": 0.5672539750752041,
+      "grad_norm": 3.133023500442505,
+      "learning_rate": 2.9684532864643123e-06,
+      "logits/chosen": 3.3388328552246094,
+      "logits/rejected": 3.3477108478546143,
+      "logps/chosen": -3.3007023334503174,
+      "logps/rejected": -6.496421813964844,
+      "loss": 0.2635,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.951053619384766,
+      "rewards/margins": 4.793579578399658,
+      "rewards/rejected": -9.744632720947266,
+      "step": 660
+    },
+    {
+      "epoch": 0.5758487322733132,
+      "grad_norm": 3.6694588661193848,
+      "learning_rate": 2.9169218667902562e-06,
+      "logits/chosen": 3.1316323280334473,
+      "logits/rejected": 2.8977527618408203,
+      "logps/chosen": -2.8769032955169678,
+      "logps/rejected": -5.834782123565674,
+      "loss": 0.2854,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -4.31535530090332,
+      "rewards/margins": 4.4368181228637695,
+      "rewards/rejected": -8.752172470092773,
+      "step": 670
+    },
+    {
+      "epoch": 0.5844434894714224,
+      "grad_norm": 3.409086227416992,
+      "learning_rate": 2.8652075714060296e-06,
+      "logits/chosen": 2.726431369781494,
+      "logits/rejected": 2.9928715229034424,
+      "logps/chosen": -3.0180654525756836,
+      "logps/rejected": -7.160694122314453,
+      "loss": 0.2461,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.527098178863525,
+      "rewards/margins": 6.213942050933838,
+      "rewards/rejected": -10.741040229797363,
+      "step": 680
+    },
+    {
+      "epoch": 0.5930382466695315,
+      "grad_norm": 5.1549153327941895,
+      "learning_rate": 2.813333083910761e-06,
+      "logits/chosen": 3.371833086013794,
+      "logits/rejected": 3.317675828933716,
+      "logps/chosen": -3.1700775623321533,
+      "logps/rejected": -6.8295745849609375,
+      "loss": 0.2458,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.755115985870361,
+      "rewards/margins": 5.489245891571045,
+      "rewards/rejected": -10.244361877441406,
+      "step": 690
+    },
+    {
+      "epoch": 0.6016330038676407,
+      "grad_norm": 4.8320112228393555,
+      "learning_rate": 2.761321158169134e-06,
+      "logits/chosen": 2.5933046340942383,
+      "logits/rejected": 2.7114923000335693,
+      "logps/chosen": -3.2017345428466797,
+      "logps/rejected": -7.420884609222412,
+      "loss": 0.2464,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.8026018142700195,
+      "rewards/margins": 6.328725814819336,
+      "rewards/rejected": -11.131326675415039,
+      "step": 700
+    },
+    {
+      "epoch": 0.6016330038676407,
+      "eval_logits/chosen": 2.7770564556121826,
+      "eval_logits/rejected": 2.9842188358306885,
+      "eval_logps/chosen": -3.5835421085357666,
+      "eval_logps/rejected": -8.199637413024902,
+      "eval_loss": 0.26223084330558777,
+      "eval_rewards/accuracies": 0.9263157844543457,
+      "eval_rewards/chosen": -5.375312805175781,
+      "eval_rewards/margins": 6.924142360687256,
+      "eval_rewards/rejected": -12.299455642700195,
+      "eval_runtime": 25.8482,
+      "eval_samples_per_second": 29.132,
+      "eval_steps_per_second": 3.675,
+      "step": 700
+    },
+    {
+      "epoch": 0.6102277610657499,
+      "grad_norm": 3.6024580001831055,
+      "learning_rate": 2.70919460833079e-06,
+      "logits/chosen": 2.4713566303253174,
+      "logits/rejected": 2.523773193359375,
+      "logps/chosen": -2.962407112121582,
+      "logps/rejected": -7.556809902191162,
+      "loss": 0.2785,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -4.443611145019531,
+      "rewards/margins": 6.891604423522949,
+      "rewards/rejected": -11.33521556854248,
+      "step": 710
+    },
+    {
+      "epoch": 0.618822518263859,
+      "grad_norm": 3.6402506828308105,
+      "learning_rate": 2.6569762988232838e-06,
+      "logits/chosen": 3.112736940383911,
+      "logits/rejected": 2.901930809020996,
+      "logps/chosen": -3.1669626235961914,
+      "logps/rejected": -7.049059867858887,
+      "loss": 0.2623,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.750443935394287,
+      "rewards/margins": 5.823145866394043,
+      "rewards/rejected": -10.573590278625488,
+      "step": 720
+    },
+    {
+      "epoch": 0.6274172754619682,
+      "grad_norm": 9.418655395507812,
+      "learning_rate": 2.604689134322999e-06,
+      "logits/chosen": 2.8671321868896484,
+      "logits/rejected": 2.763396739959717,
+      "logps/chosen": -3.1475024223327637,
+      "logps/rejected": -7.338767051696777,
+      "loss": 0.2702,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.721253871917725,
+      "rewards/margins": 6.286896705627441,
+      "rewards/rejected": -11.008151054382324,
+      "step": 730
+    },
+    {
+      "epoch": 0.6360120326600773,
+      "grad_norm": 6.016907215118408,
+      "learning_rate": 2.5523560497083927e-06,
+      "logits/chosen": 2.8831398487091064,
+      "logits/rejected": 2.9516844749450684,
+      "logps/chosen": -3.055087089538574,
+      "logps/rejected": -7.092196464538574,
+      "loss": 0.2103,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.5826311111450195,
+      "rewards/margins": 6.0556640625,
+      "rewards/rejected": -10.638293266296387,
+      "step": 740
+    },
+    {
+      "epoch": 0.6446067898581865,
+      "grad_norm": 2.791388988494873,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 3.5676627159118652,
+      "logits/rejected": 3.4635086059570312,
+      "logps/chosen": -2.8061039447784424,
+      "logps/rejected": -6.826286315917969,
+      "loss": 0.2545,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.209155082702637,
+      "rewards/margins": 6.030273914337158,
+      "rewards/rejected": -10.239428520202637,
+      "step": 750
+    },
+    {
+      "epoch": 0.6446067898581865,
+      "eval_logits/chosen": 2.94565749168396,
+      "eval_logits/rejected": 3.170260190963745,
+      "eval_logps/chosen": -3.455902338027954,
+      "eval_logps/rejected": -8.303979873657227,
+      "eval_loss": 0.2537091076374054,
+      "eval_rewards/accuracies": 0.9368420839309692,
+      "eval_rewards/chosen": -5.1838531494140625,
+      "eval_rewards/margins": 7.272115707397461,
+      "eval_rewards/rejected": -12.455968856811523,
+      "eval_runtime": 25.8128,
+      "eval_samples_per_second": 29.172,
+      "eval_steps_per_second": 3.68,
+      "step": 750
+    },
+    {
+      "epoch": 0.6532015470562956,
+      "grad_norm": 2.978318452835083,
+      "learning_rate": 2.447643950291608e-06,
+      "logits/chosen": 3.1550345420837402,
+      "logits/rejected": 2.9587855339050293,
+      "logps/chosen": -3.403642177581787,
+      "logps/rejected": -7.627197265625,
+      "loss": 0.2261,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.10546350479126,
+      "rewards/margins": 6.335333824157715,
+      "rewards/rejected": -11.440796852111816,
+      "step": 760
+    },
+    {
+      "epoch": 0.6617963042544048,
+      "grad_norm": 4.7188801765441895,
+      "learning_rate": 2.3953108656770018e-06,
+      "logits/chosen": 3.7232565879821777,
+      "logits/rejected": 3.5991597175598145,
+      "logps/chosen": -3.6658260822296143,
+      "logps/rejected": -7.148935794830322,
+      "loss": 0.2703,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -5.498739242553711,
+      "rewards/margins": 5.22466516494751,
+      "rewards/rejected": -10.723405838012695,
+      "step": 770
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 4.847439289093018,
+      "learning_rate": 2.3430237011767166e-06,
+      "logits/chosen": 2.366446018218994,
+      "logits/rejected": 2.4268651008605957,
+      "logps/chosen": -3.6872811317443848,
+      "logps/rejected": -8.306299209594727,
+      "loss": 0.2493,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -5.530921459197998,
+      "rewards/margins": 6.928528785705566,
+      "rewards/rejected": -12.459450721740723,
+      "step": 780
+    },
+    {
+      "epoch": 0.6789858186506231,
+      "grad_norm": 3.72248911857605,
+      "learning_rate": 2.290805391669212e-06,
+      "logits/chosen": 2.7826573848724365,
+      "logits/rejected": 2.9013209342956543,
+      "logps/chosen": -3.5557899475097656,
+      "logps/rejected": -7.959009647369385,
+      "loss": 0.2461,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.33368444442749,
+      "rewards/margins": 6.604828834533691,
+      "rewards/rejected": -11.938512802124023,
+      "step": 790
+    },
+    {
+      "epoch": 0.6875805758487322,
+      "grad_norm": 4.7869343757629395,
+      "learning_rate": 2.238678841830867e-06,
+      "logits/chosen": 2.5417182445526123,
+      "logits/rejected": 2.938063621520996,
+      "logps/chosen": -3.5474331378936768,
+      "logps/rejected": -7.563382148742676,
+      "loss": 0.2483,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.3211493492126465,
+      "rewards/margins": 6.023923873901367,
+      "rewards/rejected": -11.345073699951172,
+      "step": 800
+    },
+    {
+      "epoch": 0.6875805758487322,
+      "eval_logits/chosen": 2.9645943641662598,
+      "eval_logits/rejected": 3.2736430168151855,
+      "eval_logps/chosen": -3.4982783794403076,
+      "eval_logps/rejected": -8.614095687866211,
+      "eval_loss": 0.24035032093524933,
+      "eval_rewards/accuracies": 0.9263157844543457,
+      "eval_rewards/chosen": -5.24741792678833,
+      "eval_rewards/margins": 7.673725128173828,
+      "eval_rewards/rejected": -12.921142578125,
+      "eval_runtime": 25.8098,
+      "eval_samples_per_second": 29.175,
+      "eval_steps_per_second": 3.681,
+      "step": 800
+    },
+    {
+      "epoch": 0.6961753330468414,
+      "grad_norm": 5.635983943939209,
+      "learning_rate": 2.186666916089239e-06,
+      "logits/chosen": 2.7499587535858154,
+      "logits/rejected": 2.6932997703552246,
+      "logps/chosen": -3.2679648399353027,
+      "logps/rejected": -8.038375854492188,
+      "loss": 0.2647,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.901947975158691,
+      "rewards/margins": 7.155615329742432,
+      "rewards/rejected": -12.057561874389648,
+      "step": 810
+    },
+    {
+      "epoch": 0.7047700902449506,
+      "grad_norm": 4.1279215812683105,
+      "learning_rate": 2.134792428593971e-06,
+      "logits/chosen": 3.1286826133728027,
+      "logits/rejected": 3.3689827919006348,
+      "logps/chosen": -3.5489754676818848,
+      "logps/rejected": -8.034095764160156,
+      "loss": 0.1888,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.323462963104248,
+      "rewards/margins": 6.727679252624512,
+      "rewards/rejected": -12.051143646240234,
+      "step": 820
+    },
+    {
+      "epoch": 0.7133648474430597,
+      "grad_norm": 4.562918186187744,
+      "learning_rate": 2.0830781332097446e-06,
+      "logits/chosen": 2.635140895843506,
+      "logits/rejected": 2.909487247467041,
+      "logps/chosen": -3.598254442214966,
+      "logps/rejected": -8.546786308288574,
+      "loss": 0.2141,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.39738130569458,
+      "rewards/margins": 7.422798156738281,
+      "rewards/rejected": -12.820180892944336,
+      "step": 830
+    },
+    {
+      "epoch": 0.7219596046411689,
+      "grad_norm": 5.229101657867432,
+      "learning_rate": 2.031546713535688e-06,
+      "logits/chosen": 3.0485472679138184,
+      "logits/rejected": 3.2676749229431152,
+      "logps/chosen": -3.5765304565429688,
+      "logps/rejected": -8.731932640075684,
+      "loss": 0.1953,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.364795207977295,
+      "rewards/margins": 7.7331037521362305,
+      "rewards/rejected": -13.097898483276367,
+      "step": 840
+    },
+    {
+      "epoch": 0.730554361839278,
+      "grad_norm": 3.0395517349243164,
+      "learning_rate": 1.9802207729556023e-06,
+      "logits/chosen": 3.242750644683838,
+      "logits/rejected": 3.410076141357422,
+      "logps/chosen": -3.5732295513153076,
+      "logps/rejected": -7.774885654449463,
+      "loss": 0.2395,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.359843730926514,
+      "rewards/margins": 6.302483558654785,
+      "rewards/rejected": -11.662328720092773,
+      "step": 850
+    },
+    {
+      "epoch": 0.730554361839278,
+      "eval_logits/chosen": 2.9314279556274414,
+      "eval_logits/rejected": 3.276207208633423,
+      "eval_logps/chosen": -3.8869926929473877,
+      "eval_logps/rejected": -9.050567626953125,
+      "eval_loss": 0.2363433688879013,
+      "eval_rewards/accuracies": 0.9263157844543457,
+      "eval_rewards/chosen": -5.830489158630371,
+      "eval_rewards/margins": 7.745361328125,
+      "eval_rewards/rejected": -13.575852394104004,
+      "eval_runtime": 25.8152,
+      "eval_samples_per_second": 29.169,
+      "eval_steps_per_second": 3.68,
+      "step": 850
+    },
+    {
+      "epoch": 0.7391491190373872,
+      "grad_norm": 3.7891011238098145,
+      "learning_rate": 1.9291228247233607e-06,
+      "logits/chosen": 1.9879547357559204,
+      "logits/rejected": 2.725163698196411,
+      "logps/chosen": -3.3898093700408936,
+      "logps/rejected": -8.569767951965332,
+      "loss": 0.2234,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.084713935852051,
+      "rewards/margins": 7.769936561584473,
+      "rewards/rejected": -12.854650497436523,
+      "step": 860
+    },
+    {
+      "epoch": 0.7477438762354963,
+      "grad_norm": 2.793806552886963,
+      "learning_rate": 1.8782752820878636e-06,
+      "logits/chosen": 2.8827013969421387,
+      "logits/rejected": 3.106083631515503,
+      "logps/chosen": -3.376796245574951,
+      "logps/rejected": -8.713462829589844,
+      "loss": 0.2045,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.065195083618164,
+      "rewards/margins": 8.004999160766602,
+      "rewards/rejected": -13.07019329071045,
+      "step": 870
+    },
+    {
+      "epoch": 0.7563386334336055,
+      "grad_norm": 3.8785598278045654,
+      "learning_rate": 1.827700448461836e-06,
+      "logits/chosen": 3.18955659866333,
+      "logits/rejected": 3.332995653152466,
+      "logps/chosen": -3.6388778686523438,
+      "logps/rejected": -8.38855266571045,
+      "loss": 0.231,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.458316802978516,
+      "rewards/margins": 7.124513149261475,
+      "rewards/rejected": -12.582829475402832,
+      "step": 880
+    },
+    {
+      "epoch": 0.7649333906317146,
+      "grad_norm": 3.2375245094299316,
+      "learning_rate": 1.7774205076388207e-06,
+      "logits/chosen": 3.7443747520446777,
+      "logits/rejected": 3.607149839401245,
+      "logps/chosen": -3.7576351165771484,
+      "logps/rejected": -8.150545120239258,
+      "loss": 0.2398,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.636452674865723,
+      "rewards/margins": 6.589364528656006,
+      "rewards/rejected": -12.22581672668457,
+      "step": 890
+    },
+    {
+      "epoch": 0.7735281478298238,
+      "grad_norm": 3.1005704402923584,
+      "learning_rate": 1.7274575140626318e-06,
+      "logits/chosen": 2.988206386566162,
+      "logits/rejected": 3.322185516357422,
+      "logps/chosen": -3.125667095184326,
+      "logps/rejected": -8.629180908203125,
+      "loss": 0.2388,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -4.68850040435791,
+      "rewards/margins": 8.255270957946777,
+      "rewards/rejected": -12.943771362304688,
+      "step": 900
+    },
+    {
+      "epoch": 0.7735281478298238,
+      "eval_logits/chosen": 3.079637289047241,
+      "eval_logits/rejected": 3.3415913581848145,
+      "eval_logps/chosen": -3.6503636837005615,
+      "eval_logps/rejected": -8.939910888671875,
+      "eval_loss": 0.22793449461460114,
+      "eval_rewards/accuracies": 0.9157894849777222,
+      "eval_rewards/chosen": -5.4755449295043945,
+      "eval_rewards/margins": 7.934320449829102,
+      "eval_rewards/rejected": -13.409865379333496,
+      "eval_runtime": 25.8118,
+      "eval_samples_per_second": 29.173,
+      "eval_steps_per_second": 3.68,
+      "step": 900
+    },
+    {
+      "epoch": 0.7821229050279329,
+      "grad_norm": 2.3264434337615967,
+      "learning_rate": 1.677833383153542e-06,
+      "logits/chosen": 2.6580982208251953,
+      "logits/rejected": 2.6074371337890625,
+      "logps/chosen": -3.126781702041626,
+      "logps/rejected": -8.055559158325195,
+      "loss": 0.2267,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.69017219543457,
+      "rewards/margins": 7.393167018890381,
+      "rewards/rejected": -12.083338737487793,
+      "step": 910
+    },
+    {
+      "epoch": 0.7907176622260421,
+      "grad_norm": 5.1758880615234375,
+      "learning_rate": 1.6285698816954626e-06,
+      "logits/chosen": 3.202477216720581,
+      "logits/rejected": 3.286799907684326,
+      "logps/chosen": -3.5538082122802734,
+      "logps/rejected": -8.186088562011719,
+      "loss": 0.2051,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.330712795257568,
+      "rewards/margins": 6.94842004776001,
+      "rewards/rejected": -12.279133796691895,
+      "step": 920
+    },
+    {
+      "epoch": 0.7993124194241513,
+      "grad_norm": 1.7054041624069214,
+      "learning_rate": 1.5796886182883053e-06,
+      "logits/chosen": 3.129915714263916,
+      "logits/rejected": 3.352510929107666,
+      "logps/chosen": -3.1991374492645264,
+      "logps/rejected": -8.518336296081543,
+      "loss": 0.2353,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.798706531524658,
+      "rewards/margins": 7.978797912597656,
+      "rewards/rejected": -12.777504920959473,
+      "step": 930
+    },
+    {
+      "epoch": 0.8079071766222604,
+      "grad_norm": 2.9931082725524902,
+      "learning_rate": 1.5312110338697427e-06,
+      "logits/chosen": 2.5596461296081543,
+      "logits/rejected": 2.5915169715881348,
+      "logps/chosen": -3.3413949012756348,
+      "logps/rejected": -7.961850643157959,
+      "loss": 0.2516,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -5.012092113494873,
+      "rewards/margins": 6.930683135986328,
+      "rewards/rejected": -11.942774772644043,
+      "step": 940
+    },
+    {
+      "epoch": 0.8165019338203696,
+      "grad_norm": 4.107710838317871,
+      "learning_rate": 1.4831583923105e-06,
+      "logits/chosen": 2.8222692012786865,
+      "logits/rejected": 2.910057306289673,
+      "logps/chosen": -3.256718397140503,
+      "logps/rejected": -8.105169296264648,
+      "loss": 0.2299,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -4.885077476501465,
+      "rewards/margins": 7.272677421569824,
+      "rewards/rejected": -12.157754898071289,
+      "step": 950
+    },
+    {
+      "epoch": 0.8165019338203696,
+      "eval_logits/chosen": 3.0568909645080566,
+      "eval_logits/rejected": 3.3856008052825928,
+      "eval_logps/chosen": -3.493980646133423,
+      "eval_logps/rejected": -8.99133014678955,
+      "eval_loss": 0.2293253093957901,
+      "eval_rewards/accuracies": 0.9368420839309692,
+      "eval_rewards/chosen": -5.240970611572266,
+      "eval_rewards/margins": 8.246024131774902,
+      "eval_rewards/rejected": -13.486994743347168,
+      "eval_runtime": 25.8236,
+      "eval_samples_per_second": 29.159,
+      "eval_steps_per_second": 3.679,
+      "step": 950
+    },
+    {
+      "epoch": 0.8250966910184787,
+      "grad_norm": 4.835093021392822,
+      "learning_rate": 1.4355517710873184e-06,
+      "logits/chosen": 3.3382835388183594,
+      "logits/rejected": 3.328683376312256,
+      "logps/chosen": -3.7020835876464844,
+      "logps/rejected": -8.166964530944824,
+      "loss": 0.2091,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.553124904632568,
+      "rewards/margins": 6.697320461273193,
+      "rewards/rejected": -12.250445365905762,
+      "step": 960
+    },
+    {
+      "epoch": 0.8336914482165879,
+      "grad_norm": 4.466915130615234,
+      "learning_rate": 1.388412052037682e-06,
+      "logits/chosen": 2.396477222442627,
+      "logits/rejected": 2.636380672454834,
+      "logps/chosen": -3.1254048347473145,
+      "logps/rejected": -9.067309379577637,
+      "loss": 0.2295,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.688107013702393,
+      "rewards/margins": 8.912858963012695,
+      "rewards/rejected": -13.600967407226562,
+      "step": 970
+    },
+    {
+      "epoch": 0.842286205414697,
+      "grad_norm": 2.845311403274536,
+      "learning_rate": 1.3417599122003464e-06,
+      "logits/chosen": 2.760969638824463,
+      "logits/rejected": 2.9475345611572266,
+      "logps/chosen": -3.6206259727478027,
+      "logps/rejected": -9.263578414916992,
+      "loss": 0.1765,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.430939674377441,
+      "rewards/margins": 8.464428901672363,
+      "rewards/rejected": -13.895367622375488,
+      "step": 980
+    },
+    {
+      "epoch": 0.8508809626128062,
+      "grad_norm": 4.265077590942383,
+      "learning_rate": 1.2956158147457116e-06,
+      "logits/chosen": 3.060234546661377,
+      "logits/rejected": 3.3040313720703125,
+      "logps/chosen": -3.448155641555786,
+      "logps/rejected": -8.33607292175293,
+      "loss": 0.2154,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.172233581542969,
+      "rewards/margins": 7.3318772315979,
+      "rewards/rejected": -12.504110336303711,
+      "step": 990
+    },
+    {
+      "epoch": 0.8594757198109153,
+      "grad_norm": 2.6619937419891357,
+      "learning_rate": 1.2500000000000007e-06,
+      "logits/chosen": 3.205899715423584,
+      "logits/rejected": 3.2403626441955566,
+      "logps/chosen": -2.9734084606170654,
+      "logps/rejected": -7.3107008934021,
+      "loss": 0.1983,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.460112571716309,
+      "rewards/margins": 6.5059404373168945,
+      "rewards/rejected": -10.966052055358887,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8594757198109153,
+      "eval_logits/chosen": 3.0807368755340576,
+      "eval_logits/rejected": 3.4346303939819336,
+      "eval_logps/chosen": -3.660179376602173,
+      "eval_logps/rejected": -9.305243492126465,
+      "eval_loss": 0.2214924544095993,
+      "eval_rewards/accuracies": 0.9263157844543457,
+      "eval_rewards/chosen": -5.490269184112549,
+      "eval_rewards/margins": 8.467597007751465,
+      "eval_rewards/rejected": -13.957863807678223,
+      "eval_runtime": 25.8036,
+      "eval_samples_per_second": 29.182,
+      "eval_steps_per_second": 3.682,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8680704770090245,
+      "grad_norm": 3.969745635986328,
+      "learning_rate": 1.204932476567175e-06,
+      "logits/chosen": 3.2750396728515625,
+      "logits/rejected": 3.5089526176452637,
+      "logps/chosen": -3.4845385551452637,
+      "logps/rejected": -7.859654903411865,
+      "loss": 0.2136,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.226807594299316,
+      "rewards/margins": 6.562674522399902,
+      "rewards/rejected": -11.789482116699219,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8766652342071336,
+      "grad_norm": 10.868583679199219,
+      "learning_rate": 1.160433012552508e-06,
+      "logits/chosen": 3.5371367931365967,
+      "logits/rejected": 3.6224236488342285,
+      "logps/chosen": -3.4987919330596924,
+      "logps/rejected": -8.714313507080078,
+      "loss": 0.2506,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.248188018798828,
+      "rewards/margins": 7.8232831954956055,
+      "rewards/rejected": -13.071470260620117,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8852599914052428,
+      "grad_norm": 13.34189510345459,
+      "learning_rate": 1.11652112689164e-06,
+      "logits/chosen": 3.0136570930480957,
+      "logits/rejected": 3.227113723754883,
+      "logps/chosen": -3.607630968093872,
+      "logps/rejected": -8.083453178405762,
+      "loss": 0.2267,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.411446571350098,
+      "rewards/margins": 6.7137346267700195,
+      "rewards/rejected": -12.125181198120117,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 3.0865557193756104,
+      "learning_rate": 1.073216080788921e-06,
+      "logits/chosen": 3.20233154296875,
+      "logits/rejected": 3.1444244384765625,
+      "logps/chosen": -3.677372455596924,
+      "logps/rejected": -8.034679412841797,
+      "loss": 0.2019,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.516058921813965,
+      "rewards/margins": 6.535961151123047,
+      "rewards/rejected": -12.052019119262695,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9024495058014611,
+      "grad_norm": 2.896090507507324,
+      "learning_rate": 1.0305368692688175e-06,
+      "logits/chosen": 2.8652000427246094,
+      "logits/rejected": 3.20027494430542,
+      "logps/chosen": -3.3209357261657715,
+      "logps/rejected": -8.070123672485352,
+      "loss": 0.191,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.981403350830078,
+      "rewards/margins": 7.123780727386475,
+      "rewards/rejected": -12.105184555053711,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9024495058014611,
+      "eval_logits/chosen": 3.1477556228637695,
+      "eval_logits/rejected": 3.4350297451019287,
+      "eval_logps/chosen": -3.7262520790100098,
+      "eval_logps/rejected": -9.287687301635742,
+      "eval_loss": 0.21767112612724304,
+      "eval_rewards/accuracies": 0.9368420839309692,
+      "eval_rewards/chosen": -5.589378833770752,
+      "eval_rewards/margins": 8.342151641845703,
+      "eval_rewards/rejected": -13.931530952453613,
+      "eval_runtime": 25.816,
+      "eval_samples_per_second": 29.168,
+      "eval_steps_per_second": 3.68,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9110442629995703,
+      "grad_norm": 5.839542865753174,
+      "learning_rate": 9.88502212844063e-07,
+      "logits/chosen": 3.563368320465088,
+      "logits/rejected": 3.3060708045959473,
+      "logps/chosen": -3.2863879203796387,
+      "logps/rejected": -8.566315650939941,
+      "loss": 0.2254,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -4.929581642150879,
+      "rewards/margins": 7.919892311096191,
+      "rewards/rejected": -12.849472045898438,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9196390201976794,
+      "grad_norm": 4.452107906341553,
+      "learning_rate": 9.471305493042243e-07,
+      "logits/chosen": 2.7673869132995605,
+      "logits/rejected": 3.075416088104248,
+      "logps/chosen": -3.4145348072052,
+      "logps/rejected": -8.784387588500977,
+      "loss": 0.1987,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.12180233001709,
+      "rewards/margins": 8.054778099060059,
+      "rewards/rejected": -13.176579475402832,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9282337773957886,
+      "grad_norm": 3.9341001510620117,
+      "learning_rate": 9.064400256282757e-07,
+      "logits/chosen": 2.969014883041382,
+      "logits/rejected": 3.198265790939331,
+      "logps/chosen": -3.6482291221618652,
+      "logps/rejected": -9.581583023071289,
+      "loss": 0.1973,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.472344398498535,
+      "rewards/margins": 8.900031089782715,
+      "rewards/rejected": -14.37237548828125,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9368285345938977,
+      "grad_norm": 3.811671733856201,
+      "learning_rate": 8.664484900247363e-07,
+      "logits/chosen": 3.182769298553467,
+      "logits/rejected": 3.1134133338928223,
+      "logps/chosen": -3.3463242053985596,
+      "logps/rejected": -8.769086837768555,
+      "loss": 0.2126,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.019486427307129,
+      "rewards/margins": 8.134143829345703,
+      "rewards/rejected": -13.153630256652832,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9454232917920069,
+      "grad_norm": 3.094046115875244,
+      "learning_rate": 8.271734841028553e-07,
+      "logits/chosen": 3.4017093181610107,
+      "logits/rejected": 3.578439235687256,
+      "logps/chosen": -3.4635825157165527,
+      "logps/rejected": -8.677824020385742,
+      "loss": 0.1904,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.195374011993408,
+      "rewards/margins": 7.821363925933838,
+      "rewards/rejected": -13.01673698425293,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9454232917920069,
+      "eval_logits/chosen": 3.0800373554229736,
+      "eval_logits/rejected": 3.422905921936035,
+      "eval_logps/chosen": -3.708962917327881,
+      "eval_logps/rejected": -9.360494613647461,
+      "eval_loss": 0.21661873161792755,
+      "eval_rewards/accuracies": 0.9368420839309692,
+      "eval_rewards/chosen": -5.563443660736084,
+      "eval_rewards/margins": 8.47729778289795,
+      "eval_rewards/rejected": -14.040741920471191,
+      "eval_runtime": 25.8111,
+      "eval_samples_per_second": 29.174,
+      "eval_steps_per_second": 3.681,
+      "step": 1100
+    },
+    {
+      "epoch": 0.954018048990116,
+      "grad_norm": 4.002285003662109,
+      "learning_rate": 7.886322351782782e-07,
+      "logits/chosen": 2.8665084838867188,
+      "logits/rejected": 3.0208096504211426,
+      "logps/chosen": -3.6410727500915527,
+      "logps/rejected": -8.900314331054688,
+      "loss": 0.1988,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.461609363555908,
+      "rewards/margins": 7.888862609863281,
+      "rewards/rejected": -13.350473403930664,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9626128061882252,
+      "grad_norm": 2.3234140872955322,
+      "learning_rate": 7.508416487165862e-07,
+      "logits/chosen": 2.740455389022827,
+      "logits/rejected": 3.0439486503601074,
+      "logps/chosen": -3.088730573654175,
+      "logps/rejected": -8.612493515014648,
+      "loss": 0.1683,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.633096218109131,
+      "rewards/margins": 8.28564453125,
+      "rewards/rejected": -12.918741226196289,
+      "step": 1120
+    },
+    {
+      "epoch": 0.9712075633863343,
+      "grad_norm": 4.9889984130859375,
+      "learning_rate": 7.138183009179922e-07,
+      "logits/chosen": 3.4702610969543457,
+      "logits/rejected": 3.582740068435669,
+      "logps/chosen": -3.6305007934570312,
+      "logps/rejected": -9.135300636291504,
+      "loss": 0.1859,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.445751190185547,
+      "rewards/margins": 8.257198333740234,
+      "rewards/rejected": -13.702949523925781,
+      "step": 1130
+    },
+    {
+      "epoch": 0.9798023205844435,
+      "grad_norm": 4.3878254890441895,
+      "learning_rate": 6.775784314464717e-07,
+      "logits/chosen": 3.0020623207092285,
+      "logits/rejected": 3.030848503112793,
+      "logps/chosen": -3.347019910812378,
+      "logps/rejected": -8.666067123413086,
+      "loss": 0.175,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.020529747009277,
+      "rewards/margins": 7.978570461273193,
+      "rewards/rejected": -12.999099731445312,
+      "step": 1140
+    },
+    {
+      "epoch": 0.9883970777825526,
+      "grad_norm": 2.510340929031372,
+      "learning_rate": 6.421379363065142e-07,
+      "logits/chosen": 3.489284038543701,
+      "logits/rejected": 3.555269956588745,
+      "logps/chosen": -3.5305256843566895,
+      "logps/rejected": -8.848383903503418,
+      "loss": 0.1612,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.295788764953613,
+      "rewards/margins": 7.976788520812988,
+      "rewards/rejected": -13.272577285766602,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9883970777825526,
+      "eval_logits/chosen": 3.0948123931884766,
+      "eval_logits/rejected": 3.442106008529663,
+      "eval_logps/chosen": -3.807739496231079,
+      "eval_logps/rejected": -9.483173370361328,
+      "eval_loss": 0.2131287306547165,
+      "eval_rewards/accuracies": 0.9473684430122375,
+      "eval_rewards/chosen": -5.711609363555908,
+      "eval_rewards/margins": 8.513151168823242,
+      "eval_rewards/rejected": -14.224760055541992,
+      "eval_runtime": 25.8752,
+      "eval_samples_per_second": 29.101,
+      "eval_steps_per_second": 3.671,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9969918349806618,
+      "grad_norm": 4.808183193206787,
+      "learning_rate": 6.075123608706093e-07,
+      "logits/chosen": 3.347472667694092,
+      "logits/rejected": 3.43141508102417,
+      "logps/chosen": -3.588602066040039,
+      "logps/rejected": -8.802007675170898,
+      "loss": 0.22,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.382903099060059,
+      "rewards/margins": 7.820107460021973,
+      "rewards/rejected": -13.203012466430664,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0051568543188656,
+      "grad_norm": 4.898995399475098,
+      "learning_rate": 5.737168930605272e-07,
+      "logits/chosen": 3.6856889724731445,
+      "logits/rejected": 3.534011125564575,
+      "logps/chosen": -3.324617862701416,
+      "logps/rejected": -8.283414840698242,
+      "loss": 0.1738,
+      "rewards/accuracies": 0.9605262875556946,
+      "rewards/chosen": -4.986927032470703,
+      "rewards/margins": 7.438195705413818,
+      "rewards/rejected": -12.425122261047363,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0137516115169747,
+      "grad_norm": 4.611911773681641,
+      "learning_rate": 5.407663566854008e-07,
+      "logits/chosen": 2.828855276107788,
+      "logits/rejected": 3.037381172180176,
+      "logps/chosen": -3.393272876739502,
+      "logps/rejected": -8.736349105834961,
+      "loss": 0.2176,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.089909553527832,
+      "rewards/margins": 8.014615058898926,
+      "rewards/rejected": -13.104524612426758,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0223463687150838,
+      "grad_norm": 1.748143196105957,
+      "learning_rate": 5.086752049395094e-07,
+      "logits/chosen": 3.6575450897216797,
+      "logits/rejected": 3.499067783355713,
+      "logps/chosen": -3.4004104137420654,
+      "logps/rejected": -8.438041687011719,
+      "loss": 0.1689,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.100615501403809,
+      "rewards/margins": 7.5564470291137695,
+      "rewards/rejected": -12.657061576843262,
+      "step": 1190
+    },
+    {
+      "epoch": 1.0309411259131929,
+      "grad_norm": 2.34837007522583,
+      "learning_rate": 4.774575140626317e-07,
+      "logits/chosen": 3.2288806438446045,
+      "logits/rejected": 3.2293314933776855,
+      "logps/chosen": -3.5406124591827393,
+      "logps/rejected": -7.73020076751709,
+      "loss": 0.2052,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.310919284820557,
+      "rewards/margins": 6.284381866455078,
+      "rewards/rejected": -11.595300674438477,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0309411259131929,
+      "eval_logits/chosen": 3.0892465114593506,
+      "eval_logits/rejected": 3.4358115196228027,
+      "eval_logps/chosen": -3.6969687938690186,
+      "eval_logps/rejected": -9.432202339172363,
+      "eval_loss": 0.2119421511888504,
+      "eval_rewards/accuracies": 0.9473684430122375,
+      "eval_rewards/chosen": -5.54545259475708,
+      "eval_rewards/margins": 8.602849960327148,
+      "eval_rewards/rejected": -14.148303031921387,
+      "eval_runtime": 25.8416,
+      "eval_samples_per_second": 29.139,
+      "eval_steps_per_second": 3.676,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0395358831113022,
+      "grad_norm": 3.9524402618408203,
+      "learning_rate": 4.4712697716573994e-07,
+      "logits/chosen": 2.3139894008636475,
+      "logits/rejected": 2.6417737007141113,
+      "logps/chosen": -3.105717182159424,
+      "logps/rejected": -8.101734161376953,
+      "loss": 0.2114,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.658576011657715,
+      "rewards/margins": 7.494024753570557,
+      "rewards/rejected": -12.15260124206543,
+      "step": 1210
+    },
+    {
+      "epoch": 1.0481306403094113,
+      "grad_norm": 14.328203201293945,
+      "learning_rate": 4.1769689822475147e-07,
+      "logits/chosen": 2.255120277404785,
+      "logits/rejected": 2.3336124420166016,
+      "logps/chosen": -3.478384494781494,
+      "logps/rejected": -9.222847938537598,
+      "loss": 0.1962,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.217576503753662,
+      "rewards/margins": 8.61669635772705,
+      "rewards/rejected": -13.834271430969238,
+      "step": 1220
+    },
+    {
+      "epoch": 1.0567253975075204,
+      "grad_norm": 3.609117269515991,
+      "learning_rate": 3.891801862449629e-07,
+      "logits/chosen": 2.4441304206848145,
+      "logits/rejected": 2.6234078407287598,
+      "logps/chosen": -3.4292266368865967,
+      "logps/rejected": -9.432345390319824,
+      "loss": 0.1811,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.1438398361206055,
+      "rewards/margins": 9.004678726196289,
+      "rewards/rejected": -14.148518562316895,
+      "step": 1230
+    },
+    {
+      "epoch": 1.0653201547056295,
+      "grad_norm": 7.8299407958984375,
+      "learning_rate": 3.615893495987335e-07,
+      "logits/chosen": 3.6636886596679688,
+      "logits/rejected": 3.590036392211914,
+      "logps/chosen": -3.4665000438690186,
+      "logps/rejected": -8.519676208496094,
+      "loss": 0.1833,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.1997504234313965,
+      "rewards/margins": 7.579763889312744,
+      "rewards/rejected": -12.779513359069824,
+      "step": 1240
+    },
+    {
+      "epoch": 1.0739149119037388,
+      "grad_norm": 4.044775485992432,
+      "learning_rate": 3.3493649053890325e-07,
+      "logits/chosen": 1.4692296981811523,
+      "logits/rejected": 2.1407761573791504,
+      "logps/chosen": -3.113100290298462,
+      "logps/rejected": -8.523965835571289,
+      "loss": 0.1952,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -4.669650554656982,
+      "rewards/margins": 8.11629867553711,
+      "rewards/rejected": -12.785947799682617,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0739149119037388,
+      "eval_logits/chosen": 3.045609951019287,
+      "eval_logits/rejected": 3.4006409645080566,
+      "eval_logps/chosen": -3.7790019512176514,
+      "eval_logps/rejected": -9.518200874328613,
+      "eval_loss": 0.21290886402130127,
+      "eval_rewards/accuracies": 0.9473684430122375,
+      "eval_rewards/chosen": -5.6685028076171875,
+      "eval_rewards/margins": 8.60879898071289,
+      "eval_rewards/rejected": -14.277301788330078,
+      "eval_runtime": 26.4831,
+      "eval_samples_per_second": 28.433,
+      "eval_steps_per_second": 3.587,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0825096691018479,
+      "grad_norm": 1.5137228965759277,
+      "learning_rate": 3.092332998903416e-07,
+      "logits/chosen": 3.2568295001983643,
+      "logits/rejected": 3.3963840007781982,
+      "logps/chosen": -3.7715327739715576,
+      "logps/rejected": -8.44025993347168,
+      "loss": 0.1889,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.657299041748047,
+      "rewards/margins": 7.003091335296631,
+      "rewards/rejected": -12.66038990020752,
+      "step": 1260
+    },
+    {
+      "epoch": 1.091104426299957,
+      "grad_norm": 5.0704450607299805,
+      "learning_rate": 2.844910519219632e-07,
+      "logits/chosen": 3.2337543964385986,
+      "logits/rejected": 3.2509989738464355,
+      "logps/chosen": -3.7491536140441895,
+      "logps/rejected": -8.670133590698242,
+      "loss": 0.1759,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.623729705810547,
+      "rewards/margins": 7.381471157073975,
+      "rewards/rejected": -13.00520133972168,
+      "step": 1270
+    },
+    {
+      "epoch": 1.0996991834980663,
+      "grad_norm": 3.9842278957366943,
+      "learning_rate": 2.6072059940146775e-07,
+      "logits/chosen": 2.7299351692199707,
+      "logits/rejected": 2.836796522140503,
+      "logps/chosen": -3.711822032928467,
+      "logps/rejected": -8.590496063232422,
+      "loss": 0.1962,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.567732810974121,
+      "rewards/margins": 7.318011283874512,
+      "rewards/rejected": -12.885744094848633,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1082939406961754,
+      "grad_norm": 2.8271355628967285,
+      "learning_rate": 2.3793236883495164e-07,
+      "logits/chosen": 3.108205556869507,
+      "logits/rejected": 3.201073169708252,
+      "logps/chosen": -3.4906444549560547,
+      "logps/rejected": -8.72614860534668,
+      "loss": 0.1807,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.235966205596924,
+      "rewards/margins": 7.853257179260254,
+      "rewards/rejected": -13.089223861694336,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1168886978942845,
+      "grad_norm": 3.8914403915405273,
+      "learning_rate": 2.1613635589349756e-07,
+      "logits/chosen": 3.072404384613037,
+      "logits/rejected": 3.2485923767089844,
+      "logps/chosen": -3.66137957572937,
+      "logps/rejected": -8.52911376953125,
+      "loss": 0.2061,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.492068767547607,
+      "rewards/margins": 7.301600456237793,
+      "rewards/rejected": -12.793669700622559,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1168886978942845,
+      "eval_logits/chosen": 3.037187337875366,
+      "eval_logits/rejected": 3.412123203277588,
+      "eval_logps/chosen": -3.749415636062622,
+      "eval_logps/rejected": -9.534775733947754,
+      "eval_loss": 0.21187786757946014,
+      "eval_rewards/accuracies": 0.9368420839309692,
+      "eval_rewards/chosen": -5.6241230964660645,
+      "eval_rewards/margins": 8.678040504455566,
+      "eval_rewards/rejected": -14.302164077758789,
+      "eval_runtime": 25.8274,
+      "eval_samples_per_second": 29.155,
+      "eval_steps_per_second": 3.678,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1254834550923936,
+      "grad_norm": 15.04666519165039,
+      "learning_rate": 1.95342121028749e-07,
+      "logits/chosen": 3.9055018424987793,
+      "logits/rejected": 3.8385791778564453,
+      "logps/chosen": -3.6365432739257812,
+      "logps/rejected": -8.660530090332031,
+      "loss": 0.1841,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.454814434051514,
+      "rewards/margins": 7.535979270935059,
+      "rewards/rejected": -12.99079418182373,
+      "step": 1310
+    },
+    {
+      "epoch": 1.1340782122905029,
+      "grad_norm": 5.122767448425293,
+      "learning_rate": 1.7555878527937164e-07,
+      "logits/chosen": 3.176830768585205,
+      "logits/rejected": 3.247601270675659,
+      "logps/chosen": -3.0796728134155273,
+      "logps/rejected": -8.773843765258789,
+      "loss": 0.191,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -4.619509220123291,
+      "rewards/margins": 8.54125690460205,
+      "rewards/rejected": -13.1607666015625,
+      "step": 1320
+    },
+    {
+      "epoch": 1.142672969488612,
+      "grad_norm": 6.251256942749023,
+      "learning_rate": 1.567950262702714e-07,
+      "logits/chosen": 3.6342780590057373,
+      "logits/rejected": 3.7938148975372314,
+      "logps/chosen": -3.6899285316467285,
+      "logps/rejected": -9.238265037536621,
+      "loss": 0.1726,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.534893035888672,
+      "rewards/margins": 8.322505950927734,
+      "rewards/rejected": -13.857397079467773,
+      "step": 1330
+    },
+    {
+      "epoch": 1.151267726686721,
+      "grad_norm": 4.957178115844727,
+      "learning_rate": 1.3905907440629752e-07,
+      "logits/chosen": 2.9638419151306152,
+      "logits/rejected": 3.0728535652160645,
+      "logps/chosen": -3.648574113845825,
+      "logps/rejected": -8.764299392700195,
+      "loss": 0.1844,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.472861289978027,
+      "rewards/margins": 7.673587799072266,
+      "rewards/rejected": -13.146449089050293,
+      "step": 1340
+    },
+    {
+      "epoch": 1.1598624838848304,
+      "grad_norm": 4.2299485206604,
+      "learning_rate": 1.223587092621162e-07,
+      "logits/chosen": 3.2515437602996826,
+      "logits/rejected": 3.7325072288513184,
+      "logps/chosen": -3.358280897140503,
+      "logps/rejected": -8.339439392089844,
+      "loss": 0.1844,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.037421226501465,
+      "rewards/margins": 7.471738338470459,
+      "rewards/rejected": -12.509160041809082,
+      "step": 1350
+    },
+    {
+      "epoch": 1.1598624838848304,
+      "eval_logits/chosen": 3.0470423698425293,
+      "eval_logits/rejected": 3.418164014816284,
+      "eval_logps/chosen": -3.772157669067383,
+      "eval_logps/rejected": -9.568300247192383,
+      "eval_loss": 0.21017144620418549,
+      "eval_rewards/accuracies": 0.9473684430122375,
+      "eval_rewards/chosen": -5.658236980438232,
+      "eval_rewards/margins": 8.694212913513184,
+      "eval_rewards/rejected": -14.352449417114258,
+      "eval_runtime": 25.8895,
+      "eval_samples_per_second": 29.085,
+      "eval_steps_per_second": 3.669,
+      "step": 1350
+    },
+    {
+      "epoch": 1.1684572410829395,
+      "grad_norm": 4.214975833892822,
+      "learning_rate": 1.067012561698319e-07,
+      "logits/chosen": 3.704803943634033,
+      "logits/rejected": 3.8189632892608643,
+      "logps/chosen": -3.85011625289917,
+      "logps/rejected": -9.16254997253418,
+      "loss": 0.2093,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.775174140930176,
+      "rewards/margins": 7.968650817871094,
+      "rewards/rejected": -13.74382495880127,
+      "step": 1360
+    },
+    {
+      "epoch": 1.1770519982810486,
+      "grad_norm": 3.5724289417266846,
+      "learning_rate": 9.209358300585474e-08,
+      "logits/chosen": 2.6474967002868652,
+      "logits/rejected": 2.731065273284912,
+      "logps/chosen": -3.5706984996795654,
+      "logps/rejected": -8.443603515625,
+      "loss": 0.1869,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.356047630310059,
+      "rewards/margins": 7.309359073638916,
+      "rewards/rejected": -12.665407180786133,
+      "step": 1370
+    },
+    {
+      "epoch": 1.1856467554791577,
+      "grad_norm": 4.534357070922852,
+      "learning_rate": 7.854209717842231e-08,
+      "logits/chosen": 2.9290528297424316,
+      "logits/rejected": 2.9512946605682373,
+      "logps/chosen": -3.3889000415802,
+      "logps/rejected": -8.342582702636719,
+      "loss": 0.1987,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.08335018157959,
+      "rewards/margins": 7.430523872375488,
+      "rewards/rejected": -12.513874053955078,
+      "step": 1380
+    },
+    {
+      "epoch": 1.1942415126772667,
+      "grad_norm": 4.506289005279541,
+      "learning_rate": 6.605274281709929e-08,
+      "logits/chosen": 3.608332872390747,
+      "logits/rejected": 3.3560242652893066,
+      "logps/chosen": -3.968778133392334,
+      "logps/rejected": -8.82441234588623,
+      "loss": 0.2021,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.953167915344238,
+      "rewards/margins": 7.283451080322266,
+      "rewards/rejected": -13.236618041992188,
+      "step": 1390
+    },
+    {
+      "epoch": 1.202836269875376,
+      "grad_norm": 4.346375465393066,
+      "learning_rate": 5.463099816548578e-08,
+      "logits/chosen": 2.985651969909668,
+      "logits/rejected": 3.0702438354492188,
+      "logps/chosen": -3.7144761085510254,
+      "logps/rejected": -9.05632209777832,
+      "loss": 0.1899,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.571713447570801,
+      "rewards/margins": 8.012768745422363,
+      "rewards/rejected": -13.584482192993164,
+      "step": 1400
+    },
+    {
+      "epoch": 1.202836269875376,
+      "eval_logits/chosen": 3.079235553741455,
+      "eval_logits/rejected": 3.4461560249328613,
+      "eval_logps/chosen": -3.7675580978393555,
+      "eval_logps/rejected": -9.571941375732422,
+      "eval_loss": 0.21005278825759888,
+      "eval_rewards/accuracies": 0.9473684430122375,
+      "eval_rewards/chosen": -5.651337623596191,
+      "eval_rewards/margins": 8.706576347351074,
+      "eval_rewards/rejected": -14.35791301727295,
+      "eval_runtime": 25.8121,
+      "eval_samples_per_second": 29.172,
+      "eval_steps_per_second": 3.68,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2114310270734852,
+      "grad_norm": 5.487856864929199,
+      "learning_rate": 4.428187317827848e-08,
+      "logits/chosen": 2.674164295196533,
+      "logits/rejected": 3.0256829261779785,
+      "logps/chosen": -3.9050068855285645,
+      "logps/rejected": -8.870512008666992,
+      "loss": 0.2233,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.857510089874268,
+      "rewards/margins": 7.448258876800537,
+      "rewards/rejected": -13.305768013000488,
+      "step": 1410
+    },
+    {
+      "epoch": 1.2200257842715942,
+      "grad_norm": 3.1833741664886475,
+      "learning_rate": 3.5009907323737826e-08,
+      "logits/chosen": 3.0203914642333984,
+      "logits/rejected": 3.027055263519287,
+      "logps/chosen": -3.7877228260040283,
+      "logps/rejected": -8.644540786743164,
+      "loss": 0.1814,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.681583404541016,
+      "rewards/margins": 7.285227298736572,
+      "rewards/rejected": -12.96681022644043,
+      "step": 1420
+    },
+    {
+      "epoch": 1.2286205414697036,
+      "grad_norm": 7.401100158691406,
+      "learning_rate": 2.681916759252917e-08,
+      "logits/chosen": 2.8667054176330566,
+      "logits/rejected": 2.849491834640503,
+      "logps/chosen": -3.7197437286376953,
+      "logps/rejected": -8.726221084594727,
+      "loss": 0.2183,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.579615592956543,
+      "rewards/margins": 7.5097150802612305,
+      "rewards/rejected": -13.089330673217773,
+      "step": 1430
+    },
+    {
+      "epoch": 1.2372152986678127,
+      "grad_norm": 3.5204851627349854,
+      "learning_rate": 1.9713246713805588e-08,
+      "logits/chosen": 3.260636568069458,
+      "logits/rejected": 3.4873547554016113,
+      "logps/chosen": -3.686124086380005,
+      "logps/rejected": -8.21646785736084,
+      "loss": 0.1853,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.529186248779297,
+      "rewards/margins": 6.795515537261963,
+      "rewards/rejected": -12.324702262878418,
+      "step": 1440
+    },
+    {
+      "epoch": 1.2458100558659218,
+      "grad_norm": 2.1699864864349365,
+      "learning_rate": 1.3695261579316776e-08,
+      "logits/chosen": 3.3356223106384277,
+      "logits/rejected": 3.056324005126953,
+      "logps/chosen": -3.73126220703125,
+      "logps/rejected": -8.825959205627441,
+      "loss": 0.2072,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.596893787384033,
+      "rewards/margins": 7.6420440673828125,
+      "rewards/rejected": -13.23893928527832,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2458100558659218,
+      "eval_logits/chosen": 3.0708611011505127,
+      "eval_logits/rejected": 3.4387283325195312,
+      "eval_logps/chosen": -3.78403639793396,
+      "eval_logps/rejected": -9.587791442871094,
+      "eval_loss": 0.21267712116241455,
+      "eval_rewards/accuracies": 0.9263157844543457,
+      "eval_rewards/chosen": -5.676054954528809,
+      "eval_rewards/margins": 8.705632209777832,
+      "eval_rewards/rejected": -14.381685256958008,
+      "eval_runtime": 25.8134,
+      "eval_samples_per_second": 29.171,
+      "eval_steps_per_second": 3.68,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2544048130640308,
+      "grad_norm": 11.301566123962402,
+      "learning_rate": 8.767851876239075e-09,
+      "logits/chosen": 3.009819984436035,
+      "logits/rejected": 2.9617419242858887,
+      "logps/chosen": -3.7056832313537598,
+      "logps/rejected": -9.219378471374512,
+      "loss": 0.1712,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.5585246086120605,
+      "rewards/margins": 8.270544052124023,
+      "rewards/rejected": -13.829068183898926,
+      "step": 1460
+    },
+    {
+      "epoch": 1.2629995702621402,
+      "grad_norm": 4.772580146789551,
+      "learning_rate": 4.933178929321103e-09,
+      "logits/chosen": 3.2650065422058105,
+      "logits/rejected": 3.3335583209991455,
+      "logps/chosen": -3.3609511852264404,
+      "logps/rejected": -9.040172576904297,
+      "loss": 0.1677,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.041426658630371,
+      "rewards/margins": 8.518831253051758,
+      "rewards/rejected": -13.560258865356445,
+      "step": 1470
+    },
+    {
+      "epoch": 1.2715943274602493,
+      "grad_norm": 2.760948657989502,
+      "learning_rate": 2.192924752854042e-09,
+      "logits/chosen": 2.8970377445220947,
+      "logits/rejected": 3.1491127014160156,
+      "logps/chosen": -3.9307265281677246,
+      "logps/rejected": -9.542681694030762,
+      "loss": 0.2079,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.896089553833008,
+      "rewards/margins": 8.41793441772461,
+      "rewards/rejected": -14.314023971557617,
+      "step": 1480
+    },
+    {
+      "epoch": 1.2801890846583583,
+      "grad_norm": 3.169368267059326,
+      "learning_rate": 5.48291312886251e-10,
+      "logits/chosen": 3.0523228645324707,
+      "logits/rejected": 3.3422024250030518,
+      "logps/chosen": -3.4001293182373047,
+      "logps/rejected": -8.797501564025879,
+      "loss": 0.1802,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.100194454193115,
+      "rewards/margins": 8.096057891845703,
+      "rewards/rejected": -13.196252822875977,
+      "step": 1490
+    },
+    {
+      "epoch": 1.2887838418564677,
+      "grad_norm": 3.092268228530884,
+      "learning_rate": 0.0,
+      "logits/chosen": 3.0086865425109863,
+      "logits/rejected": 3.2309889793395996,
+      "logps/chosen": -3.507227659225464,
+      "logps/rejected": -8.879232406616211,
+      "loss": 0.1844,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -5.260841369628906,
+      "rewards/margins": 8.058008193969727,
+      "rewards/rejected": -13.31884765625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2887838418564677,
+      "eval_logits/chosen": 3.0669138431549072,
+      "eval_logits/rejected": 3.4271035194396973,
+      "eval_logps/chosen": -3.78071665763855,
+      "eval_logps/rejected": -9.573822021484375,
+      "eval_loss": 0.21044938266277313,
+      "eval_rewards/accuracies": 0.9368420839309692,
+      "eval_rewards/chosen": -5.671075344085693,
+      "eval_rewards/margins": 8.689659118652344,
+      "eval_rewards/rejected": -14.360734939575195,
+      "eval_runtime": 25.8203,
+      "eval_samples_per_second": 29.163,
+      "eval_steps_per_second": 3.679,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.41848597336372e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}