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": 1.3321492007104796,
+  "eval_steps": 50,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008880994671403197,
+      "grad_norm": 0.045356735587120056,
+      "learning_rate": 4.999451708687114e-06,
+      "logits/chosen": 14.352750778198242,
+      "logits/rejected": 14.82281494140625,
+      "logps/chosen": -0.2592294216156006,
+      "logps/rejected": -0.32852867245674133,
+      "loss": 0.9315,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.38884416222572327,
+      "rewards/margins": 0.10394889116287231,
+      "rewards/rejected": -0.4927930235862732,
+      "step": 10
+    },
+    {
+      "epoch": 0.017761989342806393,
+      "grad_norm": 0.05255189165472984,
+      "learning_rate": 4.997807075247147e-06,
+      "logits/chosen": 14.80792236328125,
+      "logits/rejected": 15.017183303833008,
+      "logps/chosen": -0.2825874388217926,
+      "logps/rejected": -0.36373966932296753,
+      "loss": 0.9318,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.4238811433315277,
+      "rewards/margins": 0.12172831594944,
+      "rewards/rejected": -0.5456094741821289,
+      "step": 20
+    },
+    {
+      "epoch": 0.02664298401420959,
+      "grad_norm": 0.056027185171842575,
+      "learning_rate": 4.9950668210706795e-06,
+      "logits/chosen": 14.45336627960205,
+      "logits/rejected": 15.261484146118164,
+      "logps/chosen": -0.2638034522533417,
+      "logps/rejected": -0.37216562032699585,
+      "loss": 0.9211,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.3957051932811737,
+      "rewards/margins": 0.1625431776046753,
+      "rewards/rejected": -0.5582484006881714,
+      "step": 30
+    },
+    {
+      "epoch": 0.035523978685612786,
+      "grad_norm": 0.06511653959751129,
+      "learning_rate": 4.9912321481237616e-06,
+      "logits/chosen": 14.59851360321045,
+      "logits/rejected": 15.112770080566406,
+      "logps/chosen": -0.28972768783569336,
+      "logps/rejected": -0.36043626070022583,
+      "loss": 0.941,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.43459147214889526,
+      "rewards/margins": 0.10606291145086288,
+      "rewards/rejected": -0.5406544208526611,
+      "step": 40
+    },
+    {
+      "epoch": 0.04440497335701599,
+      "grad_norm": 0.0637577474117279,
+      "learning_rate": 4.986304738420684e-06,
+      "logits/chosen": 14.678179740905762,
+      "logits/rejected": 15.114399909973145,
+      "logps/chosen": -0.3033604919910431,
+      "logps/rejected": -0.3262741267681122,
+      "loss": 0.929,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.45504075288772583,
+      "rewards/margins": 0.03437047079205513,
+      "rewards/rejected": -0.4894111752510071,
+      "step": 50
+    },
+    {
+      "epoch": 0.04440497335701599,
+      "eval_logits/chosen": 14.936029434204102,
+      "eval_logits/rejected": 14.780267715454102,
+      "eval_logps/chosen": -0.29386037588119507,
+      "eval_logps/rejected": -0.3304942548274994,
+      "eval_loss": 0.9458721876144409,
+      "eval_rewards/accuracies": 0.49450549483299255,
+      "eval_rewards/chosen": -0.4407905340194702,
+      "eval_rewards/margins": 0.05495081841945648,
+      "eval_rewards/rejected": -0.49574142694473267,
+      "eval_runtime": 27.7436,
+      "eval_samples_per_second": 26.24,
+      "eval_steps_per_second": 3.28,
+      "step": 50
+    },
+    {
+      "epoch": 0.05328596802841918,
+      "grad_norm": 0.06470987200737,
+      "learning_rate": 4.980286753286196e-06,
+      "logits/chosen": 14.19079303741455,
+      "logits/rejected": 14.986845016479492,
+      "logps/chosen": -0.26126712560653687,
+      "logps/rejected": -0.31976616382598877,
+      "loss": 0.9335,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.3919006288051605,
+      "rewards/margins": 0.08774860948324203,
+      "rewards/rejected": -0.47964924573898315,
+      "step": 60
+    },
+    {
+      "epoch": 0.06216696269982238,
+      "grad_norm": 0.06163545697927475,
+      "learning_rate": 4.973180832407471e-06,
+      "logits/chosen": 14.062408447265625,
+      "logits/rejected": 15.050743103027344,
+      "logps/chosen": -0.2698076367378235,
+      "logps/rejected": -0.37131980061531067,
+      "loss": 0.9234,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.4047114849090576,
+      "rewards/margins": 0.1522682160139084,
+      "rewards/rejected": -0.556979775428772,
+      "step": 70
+    },
+    {
+      "epoch": 0.07104795737122557,
+      "grad_norm": 0.05943402647972107,
+      "learning_rate": 4.964990092676263e-06,
+      "logits/chosen": 14.523780822753906,
+      "logits/rejected": 15.173608779907227,
+      "logps/chosen": -0.2835150957107544,
+      "logps/rejected": -0.35379332304000854,
+      "loss": 0.9317,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -0.4252726137638092,
+      "rewards/margins": 0.10541732609272003,
+      "rewards/rejected": -0.5306899547576904,
+      "step": 80
+    },
+    {
+      "epoch": 0.07992895204262877,
+      "grad_norm": 0.05566830188035965,
+      "learning_rate": 4.9557181268217225e-06,
+      "logits/chosen": 14.752237319946289,
+      "logits/rejected": 15.213434219360352,
+      "logps/chosen": -0.25490278005599976,
+      "logps/rejected": -0.31673288345336914,
+      "loss": 0.9276,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.38235417008399963,
+      "rewards/margins": 0.09274514764547348,
+      "rewards/rejected": -0.4750993847846985,
+      "step": 90
+    },
+    {
+      "epoch": 0.08880994671403197,
+      "grad_norm": 0.07879115641117096,
+      "learning_rate": 4.9453690018345144e-06,
+      "logits/chosen": 14.362078666687012,
+      "logits/rejected": 14.708786010742188,
+      "logps/chosen": -0.27969443798065186,
+      "logps/rejected": -0.3294224143028259,
+      "loss": 0.9448,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.41954168677330017,
+      "rewards/margins": 0.0745919868350029,
+      "rewards/rejected": -0.4941336512565613,
+      "step": 100
+    },
+    {
+      "epoch": 0.08880994671403197,
+      "eval_logits/chosen": 14.668691635131836,
+      "eval_logits/rejected": 14.53217601776123,
+      "eval_logps/chosen": -0.2837528884410858,
+      "eval_logps/rejected": -0.33105531334877014,
+      "eval_loss": 0.9382757544517517,
+      "eval_rewards/accuracies": 0.5164835453033447,
+      "eval_rewards/chosen": -0.4256293475627899,
+      "eval_rewards/margins": 0.07095365226268768,
+      "eval_rewards/rejected": -0.4965830445289612,
+      "eval_runtime": 26.9204,
+      "eval_samples_per_second": 27.043,
+      "eval_steps_per_second": 3.38,
+      "step": 100
+    },
+    {
+      "epoch": 0.09769094138543517,
+      "grad_norm": 0.0677201971411705,
+      "learning_rate": 4.933947257182901e-06,
+      "logits/chosen": 14.2677640914917,
+      "logits/rejected": 14.437828063964844,
+      "logps/chosen": -0.26914283633232117,
+      "logps/rejected": -0.3498677909374237,
+      "loss": 0.9307,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.40371423959732056,
+      "rewards/margins": 0.12108743190765381,
+      "rewards/rejected": -0.5248016715049744,
+      "step": 110
+    },
+    {
+      "epoch": 0.10657193605683836,
+      "grad_norm": 0.08429163694381714,
+      "learning_rate": 4.921457902821578e-06,
+      "logits/chosen": 13.978253364562988,
+      "logits/rejected": 14.673884391784668,
+      "logps/chosen": -0.2842218279838562,
+      "logps/rejected": -0.35421326756477356,
+      "loss": 0.9046,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.4263327121734619,
+      "rewards/margins": 0.10498716682195663,
+      "rewards/rejected": -0.5313198566436768,
+      "step": 120
+    },
+    {
+      "epoch": 0.11545293072824156,
+      "grad_norm": 0.08969741314649582,
+      "learning_rate": 4.907906416994146e-06,
+      "logits/chosen": 13.98906135559082,
+      "logits/rejected": 14.70555305480957,
+      "logps/chosen": -0.26557397842407227,
+      "logps/rejected": -0.3823702037334442,
+      "loss": 0.9151,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.3983609974384308,
+      "rewards/margins": 0.1751943826675415,
+      "rewards/rejected": -0.5735553503036499,
+      "step": 130
+    },
+    {
+      "epoch": 0.12433392539964476,
+      "grad_norm": 0.10470724105834961,
+      "learning_rate": 4.893298743830168e-06,
+      "logits/chosen": 13.948530197143555,
+      "logits/rejected": 14.77311897277832,
+      "logps/chosen": -0.2675064504146576,
+      "logps/rejected": -0.3631269335746765,
+      "loss": 0.9053,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.4012596607208252,
+      "rewards/margins": 0.14343078434467316,
+      "rewards/rejected": -0.5446904301643372,
+      "step": 140
+    },
+    {
+      "epoch": 0.13321492007104796,
+      "grad_norm": 0.09238290041685104,
+      "learning_rate": 4.8776412907378845e-06,
+      "logits/chosen": 12.939355850219727,
+      "logits/rejected": 13.387840270996094,
+      "logps/chosen": -0.27794820070266724,
+      "logps/rejected": -0.3520648777484894,
+      "loss": 0.9097,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.41692233085632324,
+      "rewards/margins": 0.11117497831583023,
+      "rewards/rejected": -0.5280972719192505,
+      "step": 150
+    },
+    {
+      "epoch": 0.13321492007104796,
+      "eval_logits/chosen": 13.123927116394043,
+      "eval_logits/rejected": 13.085403442382812,
+      "eval_logps/chosen": -0.28104570508003235,
+      "eval_logps/rejected": -0.3562033474445343,
+      "eval_loss": 0.9194123148918152,
+      "eval_rewards/accuracies": 0.5824176073074341,
+      "eval_rewards/chosen": -0.42156851291656494,
+      "eval_rewards/margins": 0.11273646354675293,
+      "eval_rewards/rejected": -0.5343050360679626,
+      "eval_runtime": 26.928,
+      "eval_samples_per_second": 27.035,
+      "eval_steps_per_second": 3.379,
+      "step": 150
+    },
+    {
+      "epoch": 0.14209591474245115,
+      "grad_norm": 0.14459910988807678,
+      "learning_rate": 4.860940925593703e-06,
+      "logits/chosen": 11.937938690185547,
+      "logits/rejected": 13.300163269042969,
+      "logps/chosen": -0.24840429425239563,
+      "logps/rejected": -0.4205872118473053,
+      "loss": 0.8929,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.37260642647743225,
+      "rewards/margins": 0.2582743763923645,
+      "rewards/rejected": -0.6308808326721191,
+      "step": 160
+    },
+    {
+      "epoch": 0.15097690941385436,
+      "grad_norm": 0.13749755918979645,
+      "learning_rate": 4.84320497372973e-06,
+      "logits/chosen": 12.549962997436523,
+      "logits/rejected": 12.858027458190918,
+      "logps/chosen": -0.2944340109825134,
+      "logps/rejected": -0.38480544090270996,
+      "loss": 0.895,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.44165101647377014,
+      "rewards/margins": 0.1355571448802948,
+      "rewards/rejected": -0.5772081613540649,
+      "step": 170
+    },
+    {
+      "epoch": 0.15985790408525755,
+      "grad_norm": 0.14530803263187408,
+      "learning_rate": 4.824441214720629e-06,
+      "logits/chosen": 10.892537117004395,
+      "logits/rejected": 11.756756782531738,
+      "logps/chosen": -0.2693363130092621,
+      "logps/rejected": -0.3874126374721527,
+      "loss": 0.8801,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.4040044844150543,
+      "rewards/margins": 0.17711447179317474,
+      "rewards/rejected": -0.5811189413070679,
+      "step": 180
+    },
+    {
+      "epoch": 0.16873889875666073,
+      "grad_norm": 0.20053793489933014,
+      "learning_rate": 4.804657878971252e-06,
+      "logits/chosen": 9.238119125366211,
+      "logits/rejected": 10.233763694763184,
+      "logps/chosen": -0.269479900598526,
+      "logps/rejected": -0.4149019122123718,
+      "loss": 0.8776,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.4042198657989502,
+      "rewards/margins": 0.21813304722309113,
+      "rewards/rejected": -0.6223528385162354,
+      "step": 190
+    },
+    {
+      "epoch": 0.17761989342806395,
+      "grad_norm": 0.20254959166049957,
+      "learning_rate": 4.783863644106502e-06,
+      "logits/chosen": 9.261235237121582,
+      "logits/rejected": 9.7451753616333,
+      "logps/chosen": -0.29611462354660034,
+      "logps/rejected": -0.44530659914016724,
+      "loss": 0.8596,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.4441719651222229,
+      "rewards/margins": 0.22378793358802795,
+      "rewards/rejected": -0.6679598689079285,
+      "step": 200
+    },
+    {
+      "epoch": 0.17761989342806395,
+      "eval_logits/chosen": 8.231317520141602,
+      "eval_logits/rejected": 8.285564422607422,
+      "eval_logps/chosen": -0.3201982080936432,
+      "eval_logps/rejected": -0.4862101078033447,
+      "eval_loss": 0.8602121472358704,
+      "eval_rewards/accuracies": 0.6153846383094788,
+      "eval_rewards/chosen": -0.480297327041626,
+      "eval_rewards/margins": 0.2490178644657135,
+      "eval_rewards/rejected": -0.7293152213096619,
+      "eval_runtime": 26.9054,
+      "eval_samples_per_second": 27.058,
+      "eval_steps_per_second": 3.382,
+      "step": 200
+    },
+    {
+      "epoch": 0.18650088809946713,
+      "grad_norm": 0.25219231843948364,
+      "learning_rate": 4.762067631165049e-06,
+      "logits/chosen": 7.822943687438965,
+      "logits/rejected": 8.847550392150879,
+      "logps/chosen": -0.3111446797847748,
+      "logps/rejected": -0.5253105163574219,
+      "loss": 0.8553,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.46671706438064575,
+      "rewards/margins": 0.3212486803531647,
+      "rewards/rejected": -0.787965714931488,
+      "step": 210
+    },
+    {
+      "epoch": 0.19538188277087035,
+      "grad_norm": 0.29052653908729553,
+      "learning_rate": 4.7392794005985324e-06,
+      "logits/chosen": 7.404467582702637,
+      "logits/rejected": 7.140469551086426,
+      "logps/chosen": -0.35531798005104065,
+      "logps/rejected": -0.4979163110256195,
+      "loss": 0.8204,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.5329769849777222,
+      "rewards/margins": 0.21389751136302948,
+      "rewards/rejected": -0.7468745112419128,
+      "step": 220
+    },
+    {
+      "epoch": 0.20426287744227353,
+      "grad_norm": 0.30769258737564087,
+      "learning_rate": 4.715508948078037e-06,
+      "logits/chosen": 5.096299648284912,
+      "logits/rejected": 5.143233299255371,
+      "logps/chosen": -0.3684440553188324,
+      "logps/rejected": -0.557721734046936,
+      "loss": 0.7884,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.5526660084724426,
+      "rewards/margins": 0.2839165925979614,
+      "rewards/rejected": -0.8365826606750488,
+      "step": 230
+    },
+    {
+      "epoch": 0.21314387211367672,
+      "grad_norm": 0.3165770471096039,
+      "learning_rate": 4.690766700109659e-06,
+      "logits/chosen": 5.376433372497559,
+      "logits/rejected": 4.738249778747559,
+      "logps/chosen": -0.4181212782859802,
+      "logps/rejected": -0.6782273054122925,
+      "loss": 0.7919,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.627181887626648,
+      "rewards/margins": 0.39015907049179077,
+      "rewards/rejected": -1.0173410177230835,
+      "step": 240
+    },
+    {
+      "epoch": 0.22202486678507993,
+      "grad_norm": 0.6854519844055176,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 3.3769917488098145,
+      "logits/rejected": 2.865615129470825,
+      "logps/chosen": -0.42344069480895996,
+      "logps/rejected": -0.8046137094497681,
+      "loss": 0.7456,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.6351610422134399,
+      "rewards/margins": 0.5717595219612122,
+      "rewards/rejected": -1.2069203853607178,
+      "step": 250
+    },
+    {
+      "epoch": 0.22202486678507993,
+      "eval_logits/chosen": 2.8929049968719482,
+      "eval_logits/rejected": 2.0500316619873047,
+      "eval_logps/chosen": -0.46059882640838623,
+      "eval_logps/rejected": -0.8680218458175659,
+      "eval_loss": 0.7499477863311768,
+      "eval_rewards/accuracies": 0.6373626589775085,
+      "eval_rewards/chosen": -0.6908981204032898,
+      "eval_rewards/margins": 0.6111345887184143,
+      "eval_rewards/rejected": -1.3020328283309937,
+      "eval_runtime": 26.9489,
+      "eval_samples_per_second": 27.014,
+      "eval_steps_per_second": 3.377,
+      "step": 250
+    },
+    {
+      "epoch": 0.23090586145648312,
+      "grad_norm": 1.4715200662612915,
+      "learning_rate": 4.638410650401267e-06,
+      "logits/chosen": 1.1702392101287842,
+      "logits/rejected": 0.6887636184692383,
+      "logps/chosen": -0.4449438154697418,
+      "logps/rejected": -1.0861380100250244,
+      "loss": 0.6853,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.6674157381057739,
+      "rewards/margins": 0.9617912173271179,
+      "rewards/rejected": -1.6292070150375366,
+      "step": 260
+    },
+    {
+      "epoch": 0.23978685612788633,
+      "grad_norm": 1.1773816347122192,
+      "learning_rate": 4.610819813755038e-06,
+      "logits/chosen": 2.005816698074341,
+      "logits/rejected": 0.7508751749992371,
+      "logps/chosen": -0.520461916923523,
+      "logps/rejected": -1.2372539043426514,
+      "loss": 0.6514,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.7806928157806396,
+      "rewards/margins": 1.0751880407333374,
+      "rewards/rejected": -1.8558809757232666,
+      "step": 270
+    },
+    {
+      "epoch": 0.24866785079928952,
+      "grad_norm": 0.4426538348197937,
+      "learning_rate": 4.582303101775249e-06,
+      "logits/chosen": 1.3614282608032227,
+      "logits/rejected": 0.17441503703594208,
+      "logps/chosen": -0.628559410572052,
+      "logps/rejected": -1.3841784000396729,
+      "loss": 0.6447,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.9428391456604004,
+      "rewards/margins": 1.1334283351898193,
+      "rewards/rejected": -2.076267719268799,
+      "step": 280
+    },
+    {
+      "epoch": 0.25754884547069273,
+      "grad_norm": 0.781704843044281,
+      "learning_rate": 4.55287302283426e-06,
+      "logits/chosen": 2.0829949378967285,
+      "logits/rejected": 1.0815263986587524,
+      "logps/chosen": -0.6394428014755249,
+      "logps/rejected": -1.8771930932998657,
+      "loss": 0.5863,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.9591643214225769,
+      "rewards/margins": 1.8566251993179321,
+      "rewards/rejected": -2.8157896995544434,
+      "step": 290
+    },
+    {
+      "epoch": 0.2664298401420959,
+      "grad_norm": 1.1327613592147827,
+      "learning_rate": 4.522542485937369e-06,
+      "logits/chosen": 1.197505235671997,
+      "logits/rejected": 0.16260084509849548,
+      "logps/chosen": -0.6966903805732727,
+      "logps/rejected": -2.2350592613220215,
+      "loss": 0.5354,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.0450356006622314,
+      "rewards/margins": 2.30755352973938,
+      "rewards/rejected": -3.3525891304016113,
+      "step": 300
+    },
+    {
+      "epoch": 0.2664298401420959,
+      "eval_logits/chosen": 1.2078615427017212,
+      "eval_logits/rejected": 0.2717524468898773,
+      "eval_logps/chosen": -0.7531170845031738,
+      "eval_logps/rejected": -2.0594394207000732,
+      "eval_loss": 0.5640697479248047,
+      "eval_rewards/accuracies": 0.6703296899795532,
+      "eval_rewards/chosen": -1.1296755075454712,
+      "eval_rewards/margins": 1.9594837427139282,
+      "eval_rewards/rejected": -3.0891592502593994,
+      "eval_runtime": 26.9506,
+      "eval_samples_per_second": 27.012,
+      "eval_steps_per_second": 3.377,
+      "step": 300
+    },
+    {
+      "epoch": 0.2753108348134991,
+      "grad_norm": 0.8920393586158752,
+      "learning_rate": 4.491324795060491e-06,
+      "logits/chosen": 1.12120521068573,
+      "logits/rejected": 0.3509993851184845,
+      "logps/chosen": -0.7844308018684387,
+      "logps/rejected": -2.2886409759521484,
+      "loss": 0.5357,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.176646113395691,
+      "rewards/margins": 2.256315231323242,
+      "rewards/rejected": -3.4329617023468018,
+      "step": 310
+    },
+    {
+      "epoch": 0.2841918294849023,
+      "grad_norm": 0.6658002734184265,
+      "learning_rate": 4.4592336433146e-06,
+      "logits/chosen": 1.750349760055542,
+      "logits/rejected": 0.7707412242889404,
+      "logps/chosen": -0.7995473146438599,
+      "logps/rejected": -2.2184109687805176,
+      "loss": 0.5412,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -1.199320912361145,
+      "rewards/margins": 2.128295421600342,
+      "rewards/rejected": -3.3276162147521973,
+      "step": 320
+    },
+    {
+      "epoch": 0.29307282415630553,
+      "grad_norm": 1.2708265781402588,
+      "learning_rate": 4.426283106939474e-06,
+      "logits/chosen": 1.8776671886444092,
+      "logits/rejected": 1.2588229179382324,
+      "logps/chosen": -0.894809901714325,
+      "logps/rejected": -2.4718618392944336,
+      "loss": 0.5502,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -1.342214822769165,
+      "rewards/margins": 2.3655781745910645,
+      "rewards/rejected": -3.7077927589416504,
+      "step": 330
+    },
+    {
+      "epoch": 0.3019538188277087,
+      "grad_norm": 1.2345410585403442,
+      "learning_rate": 4.3924876391293915e-06,
+      "logits/chosen": 1.9461545944213867,
+      "logits/rejected": 0.9410673975944519,
+      "logps/chosen": -0.891791045665741,
+      "logps/rejected": -2.2217679023742676,
+      "loss": 0.5519,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -1.3376867771148682,
+      "rewards/margins": 1.9949653148651123,
+      "rewards/rejected": -3.3326523303985596,
+      "step": 340
+    },
+    {
+      "epoch": 0.3108348134991119,
+      "grad_norm": 11.159003257751465,
+      "learning_rate": 4.357862063693486e-06,
+      "logits/chosen": 2.396707534790039,
+      "logits/rejected": 1.4882147312164307,
+      "logps/chosen": -1.1443694829940796,
+      "logps/rejected": -2.867492914199829,
+      "loss": 0.4806,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.7165542840957642,
+      "rewards/margins": 2.5846848487854004,
+      "rewards/rejected": -4.301239490509033,
+      "step": 350
+    },
+    {
+      "epoch": 0.3108348134991119,
+      "eval_logits/chosen": 1.7898317575454712,
+      "eval_logits/rejected": 1.109007477760315,
+      "eval_logps/chosen": -1.3312609195709229,
+      "eval_logps/rejected": -3.0454280376434326,
+      "eval_loss": 0.4698469638824463,
+      "eval_rewards/accuracies": 0.8131868243217468,
+      "eval_rewards/chosen": -1.9968912601470947,
+      "eval_rewards/margins": 2.5712504386901855,
+      "eval_rewards/rejected": -4.568141937255859,
+      "eval_runtime": 26.9108,
+      "eval_samples_per_second": 27.052,
+      "eval_steps_per_second": 3.382,
+      "step": 350
+    },
+    {
+      "epoch": 0.3197158081705151,
+      "grad_norm": 2.2653048038482666,
+      "learning_rate": 4.322421568553529e-06,
+      "logits/chosen": 0.36641037464141846,
+      "logits/rejected": -0.4621815085411072,
+      "logps/chosen": -1.5972144603729248,
+      "logps/rejected": -3.1685004234313965,
+      "loss": 0.472,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -2.3958218097686768,
+      "rewards/margins": 2.356929063796997,
+      "rewards/rejected": -4.752750396728516,
+      "step": 360
+    },
+    {
+      "epoch": 0.3285968028419183,
+      "grad_norm": 2.6831283569335938,
+      "learning_rate": 4.286181699082008e-06,
+      "logits/chosen": 1.18975830078125,
+      "logits/rejected": 0.7668083310127258,
+      "logps/chosen": -2.1462299823760986,
+      "logps/rejected": -3.7489593029022217,
+      "loss": 0.4169,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -3.2193446159362793,
+      "rewards/margins": 2.4040939807891846,
+      "rewards/rejected": -5.623438835144043,
+      "step": 370
+    },
+    {
+      "epoch": 0.33747779751332146,
+      "grad_norm": 3.5498828887939453,
+      "learning_rate": 4.249158351283414e-06,
+      "logits/chosen": 1.8030259609222412,
+      "logits/rejected": 1.4276998043060303,
+      "logps/chosen": -2.189352512359619,
+      "logps/rejected": -3.8717925548553467,
+      "loss": 0.4156,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -3.2840285301208496,
+      "rewards/margins": 2.523660182952881,
+      "rewards/rejected": -5.807689189910889,
+      "step": 380
+    },
+    {
+      "epoch": 0.3463587921847247,
+      "grad_norm": 1.46839439868927,
+      "learning_rate": 4.211367764821722e-06,
+      "logits/chosen": 2.2764127254486084,
+      "logits/rejected": 1.9199844598770142,
+      "logps/chosen": -2.4463610649108887,
+      "logps/rejected": -4.317194938659668,
+      "loss": 0.4085,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -3.669541597366333,
+      "rewards/margins": 2.806250810623169,
+      "rewards/rejected": -6.475791931152344,
+      "step": 390
+    },
+    {
+      "epoch": 0.3552397868561279,
+      "grad_norm": 1.6744616031646729,
+      "learning_rate": 4.172826515897146e-06,
+      "logits/chosen": 2.0364136695861816,
+      "logits/rejected": 1.4645214080810547,
+      "logps/chosen": -2.5738539695739746,
+      "logps/rejected": -4.41655158996582,
+      "loss": 0.3723,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -3.8607802391052246,
+      "rewards/margins": 2.764047145843506,
+      "rewards/rejected": -6.6248273849487305,
+      "step": 400
+    },
+    {
+      "epoch": 0.3552397868561279,
+      "eval_logits/chosen": 2.0340981483459473,
+      "eval_logits/rejected": 1.376452922821045,
+      "eval_logps/chosen": -2.6443424224853516,
+      "eval_logps/rejected": -4.638274192810059,
+      "eval_loss": 0.38738909363746643,
+      "eval_rewards/accuracies": 0.901098906993866,
+      "eval_rewards/chosen": -3.9665138721466064,
+      "eval_rewards/margins": 2.9908969402313232,
+      "eval_rewards/rejected": -6.95741081237793,
+      "eval_runtime": 26.943,
+      "eval_samples_per_second": 27.02,
+      "eval_steps_per_second": 3.377,
+      "step": 400
+    },
+    {
+      "epoch": 0.3641207815275311,
+      "grad_norm": 24.103384017944336,
+      "learning_rate": 4.133551509975264e-06,
+      "logits/chosen": 1.3653905391693115,
+      "logits/rejected": 0.7307125329971313,
+      "logps/chosen": -2.450911045074463,
+      "logps/rejected": -4.609705924987793,
+      "loss": 0.4031,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -3.6763663291931152,
+      "rewards/margins": 3.2381927967071533,
+      "rewards/rejected": -6.914559364318848,
+      "step": 410
+    },
+    {
+      "epoch": 0.37300177619893427,
+      "grad_norm": 2.102792263031006,
+      "learning_rate": 4.093559974371725e-06,
+      "logits/chosen": 1.6425203084945679,
+      "logits/rejected": 0.9890750050544739,
+      "logps/chosen": -2.1248934268951416,
+      "logps/rejected": -3.8592541217803955,
+      "loss": 0.3609,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -3.187340497970581,
+      "rewards/margins": 2.601541042327881,
+      "rewards/rejected": -5.788880825042725,
+      "step": 420
+    },
+    {
+      "epoch": 0.38188277087033745,
+      "grad_norm": 2.970210552215576,
+      "learning_rate": 4.052869450695776e-06,
+      "logits/chosen": 2.258129358291626,
+      "logits/rejected": 1.7126191854476929,
+      "logps/chosen": -2.9822497367858887,
+      "logps/rejected": -4.995323657989502,
+      "loss": 0.3669,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -4.473374366760254,
+      "rewards/margins": 3.01961088180542,
+      "rewards/rejected": -7.492985725402832,
+      "step": 430
+    },
+    {
+      "epoch": 0.3907637655417407,
+      "grad_norm": 2.3307077884674072,
+      "learning_rate": 4.011497787155938e-06,
+      "logits/chosen": 1.5054914951324463,
+      "logits/rejected": 0.6257806420326233,
+      "logps/chosen": -3.2783126831054688,
+      "logps/rejected": -5.625805854797363,
+      "loss": 0.3428,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.917469024658203,
+      "rewards/margins": 3.521239757537842,
+      "rewards/rejected": -8.438708305358887,
+      "step": 440
+    },
+    {
+      "epoch": 0.3996447602131439,
+      "grad_norm": 3.2838215827941895,
+      "learning_rate": 3.969463130731183e-06,
+      "logits/chosen": 1.711268424987793,
+      "logits/rejected": 1.4157356023788452,
+      "logps/chosen": -3.0163674354553223,
+      "logps/rejected": -5.020781517028809,
+      "loss": 0.3589,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -4.524550437927246,
+      "rewards/margins": 3.006621837615967,
+      "rewards/rejected": -7.531172752380371,
+      "step": 450
+    },
+    {
+      "epoch": 0.3996447602131439,
+      "eval_logits/chosen": 2.209981679916382,
+      "eval_logits/rejected": 1.6256438493728638,
+      "eval_logps/chosen": -2.841517925262451,
+      "eval_logps/rejected": -5.154296875,
+      "eval_loss": 0.35665163397789,
+      "eval_rewards/accuracies": 0.9120879173278809,
+      "eval_rewards/chosen": -4.262276649475098,
+      "eval_rewards/margins": 3.4691689014434814,
+      "eval_rewards/rejected": -7.7314453125,
+      "eval_runtime": 26.9493,
+      "eval_samples_per_second": 27.014,
+      "eval_steps_per_second": 3.377,
+      "step": 450
+    },
+    {
+      "epoch": 0.40852575488454707,
+      "grad_norm": 3.4476094245910645,
+      "learning_rate": 3.92678391921108e-06,
+      "logits/chosen": 1.3581907749176025,
+      "logits/rejected": 0.8621677160263062,
+      "logps/chosen": -2.831627130508423,
+      "logps/rejected": -5.023026943206787,
+      "loss": 0.3338,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -4.247440338134766,
+      "rewards/margins": 3.287100315093994,
+      "rewards/rejected": -7.534541130065918,
+      "step": 460
+    },
+    {
+      "epoch": 0.41740674955595025,
+      "grad_norm": 2.6653027534484863,
+      "learning_rate": 3.88347887310836e-06,
+      "logits/chosen": 1.8693492412567139,
+      "logits/rejected": 1.605238676071167,
+      "logps/chosen": -2.7347512245178223,
+      "logps/rejected": -5.385977745056152,
+      "loss": 0.3348,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.1021270751953125,
+      "rewards/margins": 3.976839542388916,
+      "rewards/rejected": -8.07896614074707,
+      "step": 470
+    },
+    {
+      "epoch": 0.42628774422735344,
+      "grad_norm": 6.658248424530029,
+      "learning_rate": 3.839566987447492e-06,
+      "logits/chosen": 1.8902003765106201,
+      "logits/rejected": 1.4942703247070312,
+      "logps/chosen": -3.1413326263427734,
+      "logps/rejected": -5.365391731262207,
+      "loss": 0.3171,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -4.71199893951416,
+      "rewards/margins": 3.3360886573791504,
+      "rewards/rejected": -8.048087120056152,
+      "step": 480
+    },
+    {
+      "epoch": 0.4351687388987567,
+      "grad_norm": 3.2576091289520264,
+      "learning_rate": 3.795067523432826e-06,
+      "logits/chosen": 2.301971673965454,
+      "logits/rejected": 1.5673840045928955,
+      "logps/chosen": -2.789170980453491,
+      "logps/rejected": -5.354689598083496,
+      "loss": 0.3238,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.1837568283081055,
+      "rewards/margins": 3.8482773303985596,
+      "rewards/rejected": -8.032033920288086,
+      "step": 490
+    },
+    {
+      "epoch": 0.44404973357015987,
+      "grad_norm": 5.094764709472656,
+      "learning_rate": 3.7500000000000005e-06,
+      "logits/chosen": 2.506347179412842,
+      "logits/rejected": 2.2316441535949707,
+      "logps/chosen": -3.1029722690582275,
+      "logps/rejected": -5.757994651794434,
+      "loss": 0.3052,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -4.654458522796631,
+      "rewards/margins": 3.9825336933135986,
+      "rewards/rejected": -8.636991500854492,
+      "step": 500
+    },
+    {
+      "epoch": 0.44404973357015987,
+      "eval_logits/chosen": 2.332798480987549,
+      "eval_logits/rejected": 1.8098194599151611,
+      "eval_logps/chosen": -3.269892692565918,
+      "eval_logps/rejected": -5.909496307373047,
+      "eval_loss": 0.324949711561203,
+      "eval_rewards/accuracies": 0.9120879173278809,
+      "eval_rewards/chosen": -4.904839038848877,
+      "eval_rewards/margins": 3.9594056606292725,
+      "eval_rewards/rejected": -8.86424446105957,
+      "eval_runtime": 26.9415,
+      "eval_samples_per_second": 27.021,
+      "eval_steps_per_second": 3.378,
+      "step": 500
+    },
+    {
+      "epoch": 0.45293072824156305,
+      "grad_norm": 4.973895072937012,
+      "learning_rate": 3.7043841852542884e-06,
+      "logits/chosen": 1.1408557891845703,
+      "logits/rejected": 0.9078874588012695,
+      "logps/chosen": -3.2813212871551514,
+      "logps/rejected": -5.6853814125061035,
+      "loss": 0.3185,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -4.9219818115234375,
+      "rewards/margins": 3.6060900688171387,
+      "rewards/rejected": -8.528071403503418,
+      "step": 510
+    },
+    {
+      "epoch": 0.46181172291296624,
+      "grad_norm": 2.726701021194458,
+      "learning_rate": 3.658240087799655e-06,
+      "logits/chosen": 1.5950994491577148,
+      "logits/rejected": 1.124607801437378,
+      "logps/chosen": -3.333927631378174,
+      "logps/rejected": -6.0137128829956055,
+      "loss": 0.3148,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -5.000891208648682,
+      "rewards/margins": 4.019678592681885,
+      "rewards/rejected": -9.020570755004883,
+      "step": 520
+    },
+    {
+      "epoch": 0.4706927175843694,
+      "grad_norm": 4.8865556716918945,
+      "learning_rate": 3.611587947962319e-06,
+      "logits/chosen": 2.257068157196045,
+      "logits/rejected": 1.7986671924591064,
+      "logps/chosen": -3.1947333812713623,
+      "logps/rejected": -6.262570381164551,
+      "loss": 0.3191,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.792099952697754,
+      "rewards/margins": 4.601754665374756,
+      "rewards/rejected": -9.393855094909668,
+      "step": 530
+    },
+    {
+      "epoch": 0.47957371225577267,
+      "grad_norm": 4.325016021728516,
+      "learning_rate": 3.564448228912682e-06,
+      "logits/chosen": 2.3096823692321777,
+      "logits/rejected": 1.7991451025009155,
+      "logps/chosen": -3.3641560077667236,
+      "logps/rejected": -6.142219543457031,
+      "loss": 0.276,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.046233654022217,
+      "rewards/margins": 4.167095184326172,
+      "rewards/rejected": -9.213329315185547,
+      "step": 540
+    },
+    {
+      "epoch": 0.48845470692717585,
+      "grad_norm": 3.15216326713562,
+      "learning_rate": 3.516841607689501e-06,
+      "logits/chosen": 1.4415160417556763,
+      "logits/rejected": 1.1298859119415283,
+      "logps/chosen": -2.851362466812134,
+      "logps/rejected": -6.210903167724609,
+      "loss": 0.3257,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.277044296264648,
+      "rewards/margins": 5.039311408996582,
+      "rewards/rejected": -9.316354751586914,
+      "step": 550
+    },
+    {
+      "epoch": 0.48845470692717585,
+      "eval_logits/chosen": 2.296088695526123,
+      "eval_logits/rejected": 1.8609188795089722,
+      "eval_logps/chosen": -3.422206401824951,
+      "eval_logps/rejected": -6.41662073135376,
+      "eval_loss": 0.30456680059432983,
+      "eval_rewards/accuracies": 0.9120879173278809,
+      "eval_rewards/chosen": -5.133309841156006,
+      "eval_rewards/margins": 4.491621971130371,
+      "eval_rewards/rejected": -9.624931335449219,
+      "eval_runtime": 26.9409,
+      "eval_samples_per_second": 27.022,
+      "eval_steps_per_second": 3.378,
+      "step": 550
+    },
+    {
+      "epoch": 0.49733570159857904,
+      "grad_norm": 3.456071615219116,
+      "learning_rate": 3.4687889661302577e-06,
+      "logits/chosen": 1.6153348684310913,
+      "logits/rejected": 1.1999633312225342,
+      "logps/chosen": -3.450087785720825,
+      "logps/rejected": -6.294098854064941,
+      "loss": 0.3094,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.175131797790527,
+      "rewards/margins": 4.266016960144043,
+      "rewards/rejected": -9.44114875793457,
+      "step": 560
+    },
+    {
+      "epoch": 0.5062166962699822,
+      "grad_norm": 3.7813830375671387,
+      "learning_rate": 3.4203113817116955e-06,
+      "logits/chosen": 2.5460948944091797,
+      "logits/rejected": 2.240358829498291,
+      "logps/chosen": -3.441761016845703,
+      "logps/rejected": -6.200081825256348,
+      "loss": 0.2967,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -5.1626410484313965,
+      "rewards/margins": 4.137481212615967,
+      "rewards/rejected": -9.300122261047363,
+      "step": 570
+    },
+    {
+      "epoch": 0.5150976909413855,
+      "grad_norm": 3.561509847640991,
+      "learning_rate": 3.3714301183045382e-06,
+      "logits/chosen": 2.236506223678589,
+      "logits/rejected": 2.0224223136901855,
+      "logps/chosen": -3.6373534202575684,
+      "logps/rejected": -6.733517646789551,
+      "loss": 0.2781,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -5.45603084564209,
+      "rewards/margins": 4.6442461013793945,
+      "rewards/rejected": -10.1002779006958,
+      "step": 580
+    },
+    {
+      "epoch": 0.5239786856127886,
+      "grad_norm": 2.540649175643921,
+      "learning_rate": 3.3221666168464584e-06,
+      "logits/chosen": 1.9122869968414307,
+      "logits/rejected": 1.8370224237442017,
+      "logps/chosen": -3.241629123687744,
+      "logps/rejected": -6.666001319885254,
+      "loss": 0.2678,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.862443447113037,
+      "rewards/margins": 5.1365580558776855,
+      "rewards/rejected": -9.999002456665039,
+      "step": 590
+    },
+    {
+      "epoch": 0.5328596802841918,
+      "grad_norm": 2.05529522895813,
+      "learning_rate": 3.272542485937369e-06,
+      "logits/chosen": 1.9268839359283447,
+      "logits/rejected": 1.4725837707519531,
+      "logps/chosen": -3.7067363262176514,
+      "logps/rejected": -6.972158908843994,
+      "loss": 0.264,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.560103893280029,
+      "rewards/margins": 4.898133754730225,
+      "rewards/rejected": -10.458237648010254,
+      "step": 600
+    },
+    {
+      "epoch": 0.5328596802841918,
+      "eval_logits/chosen": 2.3668525218963623,
+      "eval_logits/rejected": 1.9882280826568604,
+      "eval_logps/chosen": -3.6040353775024414,
+      "eval_logps/rejected": -6.91050386428833,
+      "eval_loss": 0.29209136962890625,
+      "eval_rewards/accuracies": 0.9120879173278809,
+      "eval_rewards/chosen": -5.406052589416504,
+      "eval_rewards/margins": 4.95970344543457,
+      "eval_rewards/rejected": -10.365756034851074,
+      "eval_runtime": 26.9486,
+      "eval_samples_per_second": 27.014,
+      "eval_steps_per_second": 3.377,
+      "step": 600
+    },
+    {
+      "epoch": 0.5417406749555951,
+      "grad_norm": 5.438882350921631,
+      "learning_rate": 3.222579492361179e-06,
+      "logits/chosen": 2.0183475017547607,
+      "logits/rejected": 1.7007204294204712,
+      "logps/chosen": -3.7757949829101562,
+      "logps/rejected": -6.875540256500244,
+      "loss": 0.2787,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.663692951202393,
+      "rewards/margins": 4.6496171951293945,
+      "rewards/rejected": -10.313310623168945,
+      "step": 610
+    },
+    {
+      "epoch": 0.5506216696269982,
+      "grad_norm": 6.464421272277832,
+      "learning_rate": 3.1722995515381644e-06,
+      "logits/chosen": 1.8897826671600342,
+      "logits/rejected": 1.6919243335723877,
+      "logps/chosen": -3.738862991333008,
+      "logps/rejected": -7.225765228271484,
+      "loss": 0.296,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.6082940101623535,
+      "rewards/margins": 5.230353355407715,
+      "rewards/rejected": -10.83864688873291,
+      "step": 620
+    },
+    {
+      "epoch": 0.5595026642984015,
+      "grad_norm": 3.983937978744507,
+      "learning_rate": 3.121724717912138e-06,
+      "logits/chosen": 1.8497775793075562,
+      "logits/rejected": 1.3537144660949707,
+      "logps/chosen": -3.6511616706848145,
+      "logps/rejected": -7.310211181640625,
+      "loss": 0.2604,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.476742267608643,
+      "rewards/margins": 5.488574028015137,
+      "rewards/rejected": -10.965316772460938,
+      "step": 630
+    },
+    {
+      "epoch": 0.5683836589698046,
+      "grad_norm": 9.850502014160156,
+      "learning_rate": 3.0708771752766397e-06,
+      "logits/chosen": 2.073599338531494,
+      "logits/rejected": 1.3638606071472168,
+      "logps/chosen": -4.1297831535339355,
+      "logps/rejected": -7.344725131988525,
+      "loss": 0.2868,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -6.194674491882324,
+      "rewards/margins": 4.822413444519043,
+      "rewards/rejected": -11.017088890075684,
+      "step": 640
+    },
+    {
+      "epoch": 0.5772646536412078,
+      "grad_norm": 3.2157247066497803,
+      "learning_rate": 3.019779227044398e-06,
+      "logits/chosen": 1.492789387702942,
+      "logits/rejected": 1.2012196779251099,
+      "logps/chosen": -3.458716630935669,
+      "logps/rejected": -6.776049613952637,
+      "loss": 0.2489,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.188075542449951,
+      "rewards/margins": 4.975998878479004,
+      "rewards/rejected": -10.164074897766113,
+      "step": 650
+    },
+    {
+      "epoch": 0.5772646536412078,
+      "eval_logits/chosen": 2.4555883407592773,
+      "eval_logits/rejected": 2.1057684421539307,
+      "eval_logps/chosen": -3.6452677249908447,
+      "eval_logps/rejected": -7.163515090942383,
+      "eval_loss": 0.2778012156486511,
+      "eval_rewards/accuracies": 0.901098906993866,
+      "eval_rewards/chosen": -5.467901706695557,
+      "eval_rewards/margins": 5.277371406555176,
+      "eval_rewards/rejected": -10.745272636413574,
+      "eval_runtime": 26.906,
+      "eval_samples_per_second": 27.057,
+      "eval_steps_per_second": 3.382,
+      "step": 650
+    },
+    {
+      "epoch": 0.5861456483126111,
+      "grad_norm": 3.6115524768829346,
+      "learning_rate": 2.9684532864643123e-06,
+      "logits/chosen": 2.066650390625,
+      "logits/rejected": 1.7030436992645264,
+      "logps/chosen": -3.875563859939575,
+      "logps/rejected": -7.133286476135254,
+      "loss": 0.2752,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -5.813345432281494,
+      "rewards/margins": 4.88658332824707,
+      "rewards/rejected": -10.699929237365723,
+      "step": 660
+    },
+    {
+      "epoch": 0.5950266429840142,
+      "grad_norm": 3.460318088531494,
+      "learning_rate": 2.9169218667902562e-06,
+      "logits/chosen": 2.433854341506958,
+      "logits/rejected": 2.045027256011963,
+      "logps/chosen": -3.6893928050994873,
+      "logps/rejected": -6.720344543457031,
+      "loss": 0.2562,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.534089088439941,
+      "rewards/margins": 4.5464277267456055,
+      "rewards/rejected": -10.080517768859863,
+      "step": 670
+    },
+    {
+      "epoch": 0.6039076376554174,
+      "grad_norm": 2.232542037963867,
+      "learning_rate": 2.8652075714060296e-06,
+      "logits/chosen": 2.3069093227386475,
+      "logits/rejected": 1.7321109771728516,
+      "logps/chosen": -3.936506748199463,
+      "logps/rejected": -7.7827630043029785,
+      "loss": 0.2333,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -5.904759883880615,
+      "rewards/margins": 5.769384860992432,
+      "rewards/rejected": -11.674144744873047,
+      "step": 680
+    },
+    {
+      "epoch": 0.6127886323268206,
+      "grad_norm": 3.947690010070801,
+      "learning_rate": 2.813333083910761e-06,
+      "logits/chosen": 1.467885136604309,
+      "logits/rejected": 1.0833615064620972,
+      "logps/chosen": -3.2870895862579346,
+      "logps/rejected": -7.22244930267334,
+      "loss": 0.2739,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.930634498596191,
+      "rewards/margins": 5.90303897857666,
+      "rewards/rejected": -10.833673477172852,
+      "step": 690
+    },
+    {
+      "epoch": 0.6216696269982238,
+      "grad_norm": 4.934174060821533,
+      "learning_rate": 2.761321158169134e-06,
+      "logits/chosen": 2.440274477005005,
+      "logits/rejected": 2.157214403152466,
+      "logps/chosen": -4.241659641265869,
+      "logps/rejected": -7.748563289642334,
+      "loss": 0.2859,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -6.362490177154541,
+      "rewards/margins": 5.260354995727539,
+      "rewards/rejected": -11.622844696044922,
+      "step": 700
+    },
+    {
+      "epoch": 0.6216696269982238,
+      "eval_logits/chosen": 2.5609161853790283,
+      "eval_logits/rejected": 2.258920431137085,
+      "eval_logps/chosen": -3.965893507003784,
+      "eval_logps/rejected": -7.77095365524292,
+      "eval_loss": 0.26121068000793457,
+      "eval_rewards/accuracies": 0.9340659379959106,
+      "eval_rewards/chosen": -5.948840618133545,
+      "eval_rewards/margins": 5.707590579986572,
+      "eval_rewards/rejected": -11.656431198120117,
+      "eval_runtime": 26.9101,
+      "eval_samples_per_second": 27.053,
+      "eval_steps_per_second": 3.382,
+      "step": 700
+    },
+    {
+      "epoch": 0.6305506216696269,
+      "grad_norm": 5.9008684158325195,
+      "learning_rate": 2.70919460833079e-06,
+      "logits/chosen": 1.6100571155548096,
+      "logits/rejected": 1.341528296470642,
+      "logps/chosen": -3.8634166717529297,
+      "logps/rejected": -7.63654088973999,
+      "loss": 0.2351,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.795124053955078,
+      "rewards/margins": 5.659686088562012,
+      "rewards/rejected": -11.454811096191406,
+      "step": 710
+    },
+    {
+      "epoch": 0.6394316163410302,
+      "grad_norm": 2.7195751667022705,
+      "learning_rate": 2.6569762988232838e-06,
+      "logits/chosen": 2.1212353706359863,
+      "logits/rejected": 1.864898443222046,
+      "logps/chosen": -3.8487918376922607,
+      "logps/rejected": -7.823777198791504,
+      "loss": 0.2329,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.77318811416626,
+      "rewards/margins": 5.9624762535095215,
+      "rewards/rejected": -11.735665321350098,
+      "step": 720
+    },
+    {
+      "epoch": 0.6483126110124334,
+      "grad_norm": 4.423059463500977,
+      "learning_rate": 2.604689134322999e-06,
+      "logits/chosen": 2.0979533195495605,
+      "logits/rejected": 1.7213973999023438,
+      "logps/chosen": -3.9874777793884277,
+      "logps/rejected": -7.617144584655762,
+      "loss": 0.2482,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.981216907501221,
+      "rewards/margins": 5.4444990158081055,
+      "rewards/rejected": -11.4257173538208,
+      "step": 730
+    },
+    {
+      "epoch": 0.6571936056838366,
+      "grad_norm": 4.327184200286865,
+      "learning_rate": 2.5523560497083927e-06,
+      "logits/chosen": 2.2398109436035156,
+      "logits/rejected": 1.913095474243164,
+      "logps/chosen": -3.72918701171875,
+      "logps/rejected": -7.094988822937012,
+      "loss": 0.223,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.593780517578125,
+      "rewards/margins": 5.048702716827393,
+      "rewards/rejected": -10.64248275756836,
+      "step": 740
+    },
+    {
+      "epoch": 0.6660746003552398,
+      "grad_norm": 3.1207029819488525,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7178529500961304,
+      "logits/rejected": 1.7194137573242188,
+      "logps/chosen": -3.9564640522003174,
+      "logps/rejected": -7.360040187835693,
+      "loss": 0.2227,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.934695243835449,
+      "rewards/margins": 5.10536527633667,
+      "rewards/rejected": -11.040060043334961,
+      "step": 750
+    },
+    {
+      "epoch": 0.6660746003552398,
+      "eval_logits/chosen": 2.521843671798706,
+      "eval_logits/rejected": 2.2902743816375732,
+      "eval_logps/chosen": -4.141489028930664,
+      "eval_logps/rejected": -8.121171951293945,
+      "eval_loss": 0.25929248332977295,
+      "eval_rewards/accuracies": 0.9120879173278809,
+      "eval_rewards/chosen": -6.212233543395996,
+      "eval_rewards/margins": 5.969525337219238,
+      "eval_rewards/rejected": -12.181758880615234,
+      "eval_runtime": 26.9435,
+      "eval_samples_per_second": 27.019,
+      "eval_steps_per_second": 3.377,
+      "step": 750
+    },
+    {
+      "epoch": 0.6749555950266429,
+      "grad_norm": 2.5788235664367676,
+      "learning_rate": 2.447643950291608e-06,
+      "logits/chosen": 1.7696739435195923,
+      "logits/rejected": 1.624455213546753,
+      "logps/chosen": -4.3122711181640625,
+      "logps/rejected": -8.191080093383789,
+      "loss": 0.1991,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.468405723571777,
+      "rewards/margins": 5.81821346282959,
+      "rewards/rejected": -12.286620140075684,
+      "step": 760
+    },
+    {
+      "epoch": 0.6838365896980462,
+      "grad_norm": 4.544955730438232,
+      "learning_rate": 2.3953108656770018e-06,
+      "logits/chosen": 1.9560623168945312,
+      "logits/rejected": 1.7740411758422852,
+      "logps/chosen": -4.327980041503906,
+      "logps/rejected": -8.547250747680664,
+      "loss": 0.2301,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.491971492767334,
+      "rewards/margins": 6.328906059265137,
+      "rewards/rejected": -12.82087516784668,
+      "step": 770
+    },
+    {
+      "epoch": 0.6927175843694494,
+      "grad_norm": 3.706414222717285,
+      "learning_rate": 2.3430237011767166e-06,
+      "logits/chosen": 2.664365291595459,
+      "logits/rejected": 2.338026285171509,
+      "logps/chosen": -3.8961780071258545,
+      "logps/rejected": -7.658777713775635,
+      "loss": 0.2398,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.84426736831665,
+      "rewards/margins": 5.643899917602539,
+      "rewards/rejected": -11.488167762756348,
+      "step": 780
+    },
+    {
+      "epoch": 0.7015985790408525,
+      "grad_norm": 1.7868493795394897,
+      "learning_rate": 2.290805391669212e-06,
+      "logits/chosen": 3.1498961448669434,
+      "logits/rejected": 2.860450267791748,
+      "logps/chosen": -4.245728492736816,
+      "logps/rejected": -8.142782211303711,
+      "loss": 0.184,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.368593215942383,
+      "rewards/margins": 5.845582008361816,
+      "rewards/rejected": -12.214174270629883,
+      "step": 790
+    },
+    {
+      "epoch": 0.7104795737122558,
+      "grad_norm": 4.593838214874268,
+      "learning_rate": 2.238678841830867e-06,
+      "logits/chosen": 2.4697837829589844,
+      "logits/rejected": 2.062006950378418,
+      "logps/chosen": -4.312434673309326,
+      "logps/rejected": -7.9613471031188965,
+      "loss": 0.2373,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.468652248382568,
+      "rewards/margins": 5.4733686447143555,
+      "rewards/rejected": -11.942021369934082,
+      "step": 800
+    },
+    {
+      "epoch": 0.7104795737122558,
+      "eval_logits/chosen": 2.5936477184295654,
+      "eval_logits/rejected": 2.3626792430877686,
+      "eval_logps/chosen": -3.92742919921875,
+      "eval_logps/rejected": -8.105939865112305,
+      "eval_loss": 0.24979564547538757,
+      "eval_rewards/accuracies": 0.9230769276618958,
+      "eval_rewards/chosen": -5.891143321990967,
+      "eval_rewards/margins": 6.267765045166016,
+      "eval_rewards/rejected": -12.15890884399414,
+      "eval_runtime": 26.9514,
+      "eval_samples_per_second": 27.012,
+      "eval_steps_per_second": 3.376,
+      "step": 800
+    },
+    {
+      "epoch": 0.7193605683836589,
+      "grad_norm": 2.1978909969329834,
+      "learning_rate": 2.186666916089239e-06,
+      "logits/chosen": 2.2280454635620117,
+      "logits/rejected": 2.280139446258545,
+      "logps/chosen": -4.002463340759277,
+      "logps/rejected": -7.377104759216309,
+      "loss": 0.2502,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.003695487976074,
+      "rewards/margins": 5.061962127685547,
+      "rewards/rejected": -11.065656661987305,
+      "step": 810
+    },
+    {
+      "epoch": 0.7282415630550622,
+      "grad_norm": 3.911423444747925,
+      "learning_rate": 2.134792428593971e-06,
+      "logits/chosen": 1.973581314086914,
+      "logits/rejected": 1.8624426126480103,
+      "logps/chosen": -3.6720118522644043,
+      "logps/rejected": -7.79262638092041,
+      "loss": 0.249,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.5080180168151855,
+      "rewards/margins": 6.18092155456543,
+      "rewards/rejected": -11.688939094543457,
+      "step": 820
+    },
+    {
+      "epoch": 0.7371225577264654,
+      "grad_norm": 4.506085395812988,
+      "learning_rate": 2.0830781332097446e-06,
+      "logits/chosen": 1.825543999671936,
+      "logits/rejected": 1.6684534549713135,
+      "logps/chosen": -3.7447516918182373,
+      "logps/rejected": -7.67331075668335,
+      "loss": 0.21,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.617127895355225,
+      "rewards/margins": 5.892838954925537,
+      "rewards/rejected": -11.509965896606445,
+      "step": 830
+    },
+    {
+      "epoch": 0.7460035523978685,
+      "grad_norm": 3.1987173557281494,
+      "learning_rate": 2.031546713535688e-06,
+      "logits/chosen": 2.580594778060913,
+      "logits/rejected": 2.386385917663574,
+      "logps/chosen": -3.8240609169006348,
+      "logps/rejected": -7.2592315673828125,
+      "loss": 0.2173,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.736091613769531,
+      "rewards/margins": 5.1527557373046875,
+      "rewards/rejected": -10.888847351074219,
+      "step": 840
+    },
+    {
+      "epoch": 0.7548845470692718,
+      "grad_norm": 3.36380672454834,
+      "learning_rate": 1.9802207729556023e-06,
+      "logits/chosen": 2.644188404083252,
+      "logits/rejected": 2.3516969680786133,
+      "logps/chosen": -3.945826292037964,
+      "logps/rejected": -7.7842698097229,
+      "loss": 0.2176,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.918739318847656,
+      "rewards/margins": 5.757664680480957,
+      "rewards/rejected": -11.67640495300293,
+      "step": 850
+    },
+    {
+      "epoch": 0.7548845470692718,
+      "eval_logits/chosen": 2.703193187713623,
+      "eval_logits/rejected": 2.4475576877593994,
+      "eval_logps/chosen": -3.872364044189453,
+      "eval_logps/rejected": -8.104667663574219,
+      "eval_loss": 0.23388977348804474,
+      "eval_rewards/accuracies": 0.9230769276618958,
+      "eval_rewards/chosen": -5.80854606628418,
+      "eval_rewards/margins": 6.34845495223999,
+      "eval_rewards/rejected": -12.157001495361328,
+      "eval_runtime": 26.9104,
+      "eval_samples_per_second": 27.053,
+      "eval_steps_per_second": 3.382,
+      "step": 850
+    },
+    {
+      "epoch": 0.7637655417406749,
+      "grad_norm": 5.758064270019531,
+      "learning_rate": 1.9291228247233607e-06,
+      "logits/chosen": 1.682765245437622,
+      "logits/rejected": 1.4204728603363037,
+      "logps/chosen": -3.7396492958068848,
+      "logps/rejected": -7.976266384124756,
+      "loss": 0.2296,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.6094746589660645,
+      "rewards/margins": 6.354925632476807,
+      "rewards/rejected": -11.964399337768555,
+      "step": 860
+    },
+    {
+      "epoch": 0.7726465364120781,
+      "grad_norm": 5.571817874908447,
+      "learning_rate": 1.8782752820878636e-06,
+      "logits/chosen": 3.255483627319336,
+      "logits/rejected": 2.909604787826538,
+      "logps/chosen": -4.347229957580566,
+      "logps/rejected": -8.916404724121094,
+      "loss": 0.1949,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.52084493637085,
+      "rewards/margins": 6.853763580322266,
+      "rewards/rejected": -13.374608039855957,
+      "step": 870
+    },
+    {
+      "epoch": 0.7815275310834814,
+      "grad_norm": 4.394683361053467,
+      "learning_rate": 1.827700448461836e-06,
+      "logits/chosen": 2.1075878143310547,
+      "logits/rejected": 1.9253053665161133,
+      "logps/chosen": -4.578610420227051,
+      "logps/rejected": -9.08405876159668,
+      "loss": 0.203,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.867916107177734,
+      "rewards/margins": 6.758172512054443,
+      "rewards/rejected": -13.62608814239502,
+      "step": 880
+    },
+    {
+      "epoch": 0.7904085257548845,
+      "grad_norm": 3.40975284576416,
+      "learning_rate": 1.7774205076388207e-06,
+      "logits/chosen": 1.9907169342041016,
+      "logits/rejected": 2.0108611583709717,
+      "logps/chosen": -3.837683916091919,
+      "logps/rejected": -8.051701545715332,
+      "loss": 0.2023,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.756525993347168,
+      "rewards/margins": 6.3210248947143555,
+      "rewards/rejected": -12.077550888061523,
+      "step": 890
+    },
+    {
+      "epoch": 0.7992895204262878,
+      "grad_norm": 2.777862548828125,
+      "learning_rate": 1.7274575140626318e-06,
+      "logits/chosen": 2.684932231903076,
+      "logits/rejected": 2.3814995288848877,
+      "logps/chosen": -4.154343128204346,
+      "logps/rejected": -8.115530014038086,
+      "loss": 0.2205,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -6.231514930725098,
+      "rewards/margins": 5.941780090332031,
+      "rewards/rejected": -12.173295021057129,
+      "step": 900
+    },
+    {
+      "epoch": 0.7992895204262878,
+      "eval_logits/chosen": 2.7355191707611084,
+      "eval_logits/rejected": 2.505545139312744,
+      "eval_logps/chosen": -4.136618614196777,
+      "eval_logps/rejected": -8.495417594909668,
+      "eval_loss": 0.23354515433311462,
+      "eval_rewards/accuracies": 0.9230769276618958,
+      "eval_rewards/chosen": -6.204929351806641,
+      "eval_rewards/margins": 6.538197040557861,
+      "eval_rewards/rejected": -12.74312686920166,
+      "eval_runtime": 26.9187,
+      "eval_samples_per_second": 27.044,
+      "eval_steps_per_second": 3.381,
+      "step": 900
+    },
+    {
+      "epoch": 0.8081705150976909,
+      "grad_norm": 4.050413608551025,
+      "learning_rate": 1.677833383153542e-06,
+      "logits/chosen": 2.0889079570770264,
+      "logits/rejected": 1.8775651454925537,
+      "logps/chosen": -4.024281024932861,
+      "logps/rejected": -8.443221092224121,
+      "loss": 0.1897,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.036420822143555,
+      "rewards/margins": 6.628411769866943,
+      "rewards/rejected": -12.664831161499023,
+      "step": 910
+    },
+    {
+      "epoch": 0.8170515097690941,
+      "grad_norm": 3.4868874549865723,
+      "learning_rate": 1.6285698816954626e-06,
+      "logits/chosen": 2.6587109565734863,
+      "logits/rejected": 2.3555827140808105,
+      "logps/chosen": -4.196071147918701,
+      "logps/rejected": -8.115352630615234,
+      "loss": 0.2111,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.294107437133789,
+      "rewards/margins": 5.878922462463379,
+      "rewards/rejected": -12.173029899597168,
+      "step": 920
+    },
+    {
+      "epoch": 0.8259325044404974,
+      "grad_norm": 2.6183993816375732,
+      "learning_rate": 1.5796886182883053e-06,
+      "logits/chosen": 2.5196542739868164,
+      "logits/rejected": 1.975979208946228,
+      "logps/chosen": -3.9688720703125,
+      "logps/rejected": -8.01060962677002,
+      "loss": 0.1988,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.953307628631592,
+      "rewards/margins": 6.062605857849121,
+      "rewards/rejected": -12.015913963317871,
+      "step": 930
+    },
+    {
+      "epoch": 0.8348134991119005,
+      "grad_norm": 5.776535511016846,
+      "learning_rate": 1.5312110338697427e-06,
+      "logits/chosen": 2.420212745666504,
+      "logits/rejected": 2.1600253582000732,
+      "logps/chosen": -3.7991039752960205,
+      "logps/rejected": -7.702652931213379,
+      "loss": 0.2148,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.69865608215332,
+      "rewards/margins": 5.8553242683410645,
+      "rewards/rejected": -11.553979873657227,
+      "step": 940
+    },
+    {
+      "epoch": 0.8436944937833037,
+      "grad_norm": 2.062008857727051,
+      "learning_rate": 1.4831583923105e-06,
+      "logits/chosen": 2.5505709648132324,
+      "logits/rejected": 2.452706813812256,
+      "logps/chosen": -3.9582321643829346,
+      "logps/rejected": -8.513577461242676,
+      "loss": 0.191,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.937348365783691,
+      "rewards/margins": 6.833017826080322,
+      "rewards/rejected": -12.770365715026855,
+      "step": 950
+    },
+    {
+      "epoch": 0.8436944937833037,
+      "eval_logits/chosen": 2.8452956676483154,
+      "eval_logits/rejected": 2.565410852432251,
+      "eval_logps/chosen": -3.9218173027038574,
+      "eval_logps/rejected": -8.294865608215332,
+      "eval_loss": 0.22145631909370422,
+      "eval_rewards/accuracies": 0.9450549483299255,
+      "eval_rewards/chosen": -5.882725238800049,
+      "eval_rewards/margins": 6.559573650360107,
+      "eval_rewards/rejected": -12.442299842834473,
+      "eval_runtime": 26.9101,
+      "eval_samples_per_second": 27.053,
+      "eval_steps_per_second": 3.382,
+      "step": 950
+    },
+    {
+      "epoch": 0.8525754884547069,
+      "grad_norm": 5.711606502532959,
+      "learning_rate": 1.4355517710873184e-06,
+      "logits/chosen": 1.7628614902496338,
+      "logits/rejected": 1.9250881671905518,
+      "logps/chosen": -3.9974637031555176,
+      "logps/rejected": -8.33702278137207,
+      "loss": 0.2268,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.996196269989014,
+      "rewards/margins": 6.509337425231934,
+      "rewards/rejected": -12.505533218383789,
+      "step": 960
+    },
+    {
+      "epoch": 0.8614564831261101,
+      "grad_norm": 3.9296226501464844,
+      "learning_rate": 1.388412052037682e-06,
+      "logits/chosen": 2.9850051403045654,
+      "logits/rejected": 2.8170535564422607,
+      "logps/chosen": -4.006231784820557,
+      "logps/rejected": -8.387389183044434,
+      "loss": 0.2318,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.009347915649414,
+      "rewards/margins": 6.571736812591553,
+      "rewards/rejected": -12.581083297729492,
+      "step": 970
+    },
+    {
+      "epoch": 0.8703374777975134,
+      "grad_norm": 4.998567581176758,
+      "learning_rate": 1.3417599122003464e-06,
+      "logits/chosen": 2.78267240524292,
+      "logits/rejected": 2.7181553840637207,
+      "logps/chosen": -4.036787986755371,
+      "logps/rejected": -8.21368408203125,
+      "loss": 0.1919,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.055181503295898,
+      "rewards/margins": 6.265345096588135,
+      "rewards/rejected": -12.320526123046875,
+      "step": 980
+    },
+    {
+      "epoch": 0.8792184724689165,
+      "grad_norm": 2.5908820629119873,
+      "learning_rate": 1.2956158147457116e-06,
+      "logits/chosen": 1.7903728485107422,
+      "logits/rejected": 1.8292526006698608,
+      "logps/chosen": -4.179145336151123,
+      "logps/rejected": -8.847452163696289,
+      "loss": 0.178,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.2687177658081055,
+      "rewards/margins": 7.002459526062012,
+      "rewards/rejected": -13.271177291870117,
+      "step": 990
+    },
+    {
+      "epoch": 0.8880994671403197,
+      "grad_norm": 5.78056001663208,
+      "learning_rate": 1.2500000000000007e-06,
+      "logits/chosen": 2.100431442260742,
+      "logits/rejected": 1.723537802696228,
+      "logps/chosen": -4.272381782531738,
+      "logps/rejected": -8.2788667678833,
+      "loss": 0.2124,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -6.408572196960449,
+      "rewards/margins": 6.009727478027344,
+      "rewards/rejected": -12.418298721313477,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8880994671403197,
+      "eval_logits/chosen": 2.8812954425811768,
+      "eval_logits/rejected": 2.6032304763793945,
+      "eval_logps/chosen": -4.101572036743164,
+      "eval_logps/rejected": -8.560330390930176,
+      "eval_loss": 0.2120697945356369,
+      "eval_rewards/accuracies": 0.9560439586639404,
+      "eval_rewards/chosen": -6.152358055114746,
+      "eval_rewards/margins": 6.688137054443359,
+      "eval_rewards/rejected": -12.840494155883789,
+      "eval_runtime": 26.9309,
+      "eval_samples_per_second": 27.032,
+      "eval_steps_per_second": 3.379,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8969804618117229,
+      "grad_norm": 3.1136035919189453,
+      "learning_rate": 1.204932476567175e-06,
+      "logits/chosen": 2.881392002105713,
+      "logits/rejected": 2.7345643043518066,
+      "logps/chosen": -3.936549663543701,
+      "logps/rejected": -8.150217056274414,
+      "loss": 0.2411,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.904824733734131,
+      "rewards/margins": 6.320501804351807,
+      "rewards/rejected": -12.225326538085938,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9058614564831261,
+      "grad_norm": 5.691193103790283,
+      "learning_rate": 1.160433012552508e-06,
+      "logits/chosen": 1.6349077224731445,
+      "logits/rejected": 1.4875171184539795,
+      "logps/chosen": -4.224863052368164,
+      "logps/rejected": -8.643598556518555,
+      "loss": 0.1986,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.337294578552246,
+      "rewards/margins": 6.628103733062744,
+      "rewards/rejected": -12.965397834777832,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9147424511545293,
+      "grad_norm": 3.402573823928833,
+      "learning_rate": 1.11652112689164e-06,
+      "logits/chosen": 3.278343915939331,
+      "logits/rejected": 3.057807683944702,
+      "logps/chosen": -3.930039644241333,
+      "logps/rejected": -8.220510482788086,
+      "loss": 0.2296,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.895058631896973,
+      "rewards/margins": 6.435708522796631,
+      "rewards/rejected": -12.330766677856445,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9236234458259325,
+      "grad_norm": 3.68056583404541,
+      "learning_rate": 1.073216080788921e-06,
+      "logits/chosen": 3.3248558044433594,
+      "logits/rejected": 2.7570416927337646,
+      "logps/chosen": -3.971494674682617,
+      "logps/rejected": -8.417669296264648,
+      "loss": 0.2158,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -5.957242488861084,
+      "rewards/margins": 6.6692609786987305,
+      "rewards/rejected": -12.626504898071289,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9325044404973357,
+      "grad_norm": 3.4190564155578613,
+      "learning_rate": 1.0305368692688175e-06,
+      "logits/chosen": 2.377645254135132,
+      "logits/rejected": 2.1726670265197754,
+      "logps/chosen": -3.946305751800537,
+      "logps/rejected": -7.984199523925781,
+      "loss": 0.2567,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.919459342956543,
+      "rewards/margins": 6.056839466094971,
+      "rewards/rejected": -11.976297378540039,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9325044404973357,
+      "eval_logits/chosen": 2.896627187728882,
+      "eval_logits/rejected": 2.6205432415008545,
+      "eval_logps/chosen": -3.944129467010498,
+      "eval_logps/rejected": -8.44783878326416,
+      "eval_loss": 0.208639457821846,
+      "eval_rewards/accuracies": 0.9450549483299255,
+      "eval_rewards/chosen": -5.916193962097168,
+      "eval_rewards/margins": 6.7555670738220215,
+      "eval_rewards/rejected": -12.671759605407715,
+      "eval_runtime": 26.913,
+      "eval_samples_per_second": 27.05,
+      "eval_steps_per_second": 3.381,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9413854351687388,
+      "grad_norm": 4.253269672393799,
+      "learning_rate": 9.88502212844063e-07,
+      "logits/chosen": 1.775570273399353,
+      "logits/rejected": 1.9398529529571533,
+      "logps/chosen": -3.8803114891052246,
+      "logps/rejected": -8.330240249633789,
+      "loss": 0.2095,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.820467948913574,
+      "rewards/margins": 6.674893379211426,
+      "rewards/rejected": -12.495360374450684,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9502664298401421,
+      "grad_norm": 6.887324333190918,
+      "learning_rate": 9.471305493042243e-07,
+      "logits/chosen": 2.857212781906128,
+      "logits/rejected": 2.811908721923828,
+      "logps/chosen": -4.217669486999512,
+      "logps/rejected": -9.236319541931152,
+      "loss": 0.2323,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -6.326503753662109,
+      "rewards/margins": 7.527973175048828,
+      "rewards/rejected": -13.854476928710938,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9591474245115453,
+      "grad_norm": 2.7152857780456543,
+      "learning_rate": 9.064400256282757e-07,
+      "logits/chosen": 2.27998685836792,
+      "logits/rejected": 2.3718767166137695,
+      "logps/chosen": -3.6377360820770264,
+      "logps/rejected": -7.954897880554199,
+      "loss": 0.2004,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.456604480743408,
+      "rewards/margins": 6.475743293762207,
+      "rewards/rejected": -11.932345390319824,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9680284191829485,
+      "grad_norm": 3.9282989501953125,
+      "learning_rate": 8.664484900247363e-07,
+      "logits/chosen": 1.8304803371429443,
+      "logits/rejected": 1.5871257781982422,
+      "logps/chosen": -3.8190300464630127,
+      "logps/rejected": -8.502077102661133,
+      "loss": 0.232,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.728545188903809,
+      "rewards/margins": 7.024571895599365,
+      "rewards/rejected": -12.753117561340332,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9769094138543517,
+      "grad_norm": 5.071885585784912,
+      "learning_rate": 8.271734841028553e-07,
+      "logits/chosen": 2.6612632274627686,
+      "logits/rejected": 2.488330364227295,
+      "logps/chosen": -4.055710315704346,
+      "logps/rejected": -8.566553115844727,
+      "loss": 0.2106,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.083566188812256,
+      "rewards/margins": 6.766263484954834,
+      "rewards/rejected": -12.849828720092773,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9769094138543517,
+      "eval_logits/chosen": 2.8787481784820557,
+      "eval_logits/rejected": 2.6368823051452637,
+      "eval_logps/chosen": -3.9652817249298096,
+      "eval_logps/rejected": -8.534655570983887,
+      "eval_loss": 0.20719259977340698,
+      "eval_rewards/accuracies": 0.9670329689979553,
+      "eval_rewards/chosen": -5.947922229766846,
+      "eval_rewards/margins": 6.854061126708984,
+      "eval_rewards/rejected": -12.801982879638672,
+      "eval_runtime": 26.9639,
+      "eval_samples_per_second": 26.999,
+      "eval_steps_per_second": 3.375,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9857904085257548,
+      "grad_norm": 3.400362491607666,
+      "learning_rate": 7.886322351782782e-07,
+      "logits/chosen": 2.761348247528076,
+      "logits/rejected": 2.3678154945373535,
+      "logps/chosen": -3.752680540084839,
+      "logps/rejected": -8.517599105834961,
+      "loss": 0.1933,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.6290202140808105,
+      "rewards/margins": 7.147379398345947,
+      "rewards/rejected": -12.776400566101074,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9946714031971581,
+      "grad_norm": 3.4339635372161865,
+      "learning_rate": 7.508416487165862e-07,
+      "logits/chosen": 2.4595961570739746,
+      "logits/rejected": 2.378556489944458,
+      "logps/chosen": -4.14182186126709,
+      "logps/rejected": -8.477062225341797,
+      "loss": 0.1744,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.212733268737793,
+      "rewards/margins": 6.502861022949219,
+      "rewards/rejected": -12.715594291687012,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0035523978685612,
+      "grad_norm": 5.267716884613037,
+      "learning_rate": 7.138183009179922e-07,
+      "logits/chosen": 1.7714722156524658,
+      "logits/rejected": 1.619210958480835,
+      "logps/chosen": -3.7322158813476562,
+      "logps/rejected": -8.073896408081055,
+      "loss": 0.2021,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.598322868347168,
+      "rewards/margins": 6.512521266937256,
+      "rewards/rejected": -12.110844612121582,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0124333925399644,
+      "grad_norm": 10.082330703735352,
+      "learning_rate": 6.775784314464717e-07,
+      "logits/chosen": 2.3501925468444824,
+      "logits/rejected": 2.194481611251831,
+      "logps/chosen": -4.003907680511475,
+      "logps/rejected": -8.800313949584961,
+      "loss": 0.2059,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.005861759185791,
+      "rewards/margins": 7.194608211517334,
+      "rewards/rejected": -13.200468063354492,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0213143872113677,
+      "grad_norm": 3.31432843208313,
+      "learning_rate": 6.421379363065142e-07,
+      "logits/chosen": 2.291569232940674,
+      "logits/rejected": 1.8113495111465454,
+      "logps/chosen": -3.580338954925537,
+      "logps/rejected": -7.668196201324463,
+      "loss": 0.2222,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.370509147644043,
+      "rewards/margins": 6.131784915924072,
+      "rewards/rejected": -11.502294540405273,
+      "step": 1150
+    },
+    {
+      "epoch": 1.0213143872113677,
+      "eval_logits/chosen": 2.8636276721954346,
+      "eval_logits/rejected": 2.628934860229492,
+      "eval_logps/chosen": -4.0603508949279785,
+      "eval_logps/rejected": -8.658452987670898,
+      "eval_loss": 0.20542114973068237,
+      "eval_rewards/accuracies": 0.9450549483299255,
+      "eval_rewards/chosen": -6.090526580810547,
+      "eval_rewards/margins": 6.897151947021484,
+      "eval_rewards/rejected": -12.987678527832031,
+      "eval_runtime": 26.9182,
+      "eval_samples_per_second": 27.045,
+      "eval_steps_per_second": 3.381,
+      "step": 1150
+    },
+    {
+      "epoch": 1.030195381882771,
+      "grad_norm": 3.207170009613037,
+      "learning_rate": 6.075123608706093e-07,
+      "logits/chosen": 2.5464391708374023,
+      "logits/rejected": 2.2808260917663574,
+      "logps/chosen": -3.925663471221924,
+      "logps/rejected": -8.906625747680664,
+      "loss": 0.2021,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.888494968414307,
+      "rewards/margins": 7.471442222595215,
+      "rewards/rejected": -13.359936714172363,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0390763765541742,
+      "grad_norm": 4.001806735992432,
+      "learning_rate": 5.737168930605272e-07,
+      "logits/chosen": 2.2392163276672363,
+      "logits/rejected": 1.9872722625732422,
+      "logps/chosen": -4.3011579513549805,
+      "logps/rejected": -8.394268989562988,
+      "loss": 0.2078,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.451737403869629,
+      "rewards/margins": 6.1396660804748535,
+      "rewards/rejected": -12.59140396118164,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0479573712255772,
+      "grad_norm": 2.185001850128174,
+      "learning_rate": 5.407663566854008e-07,
+      "logits/chosen": 1.4553273916244507,
+      "logits/rejected": 1.5538376569747925,
+      "logps/chosen": -3.9231178760528564,
+      "logps/rejected": -8.551255226135254,
+      "loss": 0.1897,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.884676933288574,
+      "rewards/margins": 6.942205905914307,
+      "rewards/rejected": -12.826881408691406,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0568383658969804,
+      "grad_norm": 9.316890716552734,
+      "learning_rate": 5.086752049395094e-07,
+      "logits/chosen": 2.1896653175354004,
+      "logits/rejected": 2.140918731689453,
+      "logps/chosen": -3.9529004096984863,
+      "logps/rejected": -8.447370529174805,
+      "loss": 0.2252,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.92935037612915,
+      "rewards/margins": 6.741705894470215,
+      "rewards/rejected": -12.671055793762207,
+      "step": 1190
+    },
+    {
+      "epoch": 1.0657193605683837,
+      "grad_norm": 2.616591215133667,
+      "learning_rate": 4.774575140626317e-07,
+      "logits/chosen": 2.5030179023742676,
+      "logits/rejected": 2.2901535034179688,
+      "logps/chosen": -4.213486671447754,
+      "logps/rejected": -9.337915420532227,
+      "loss": 0.2029,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.3202290534973145,
+      "rewards/margins": 7.686643123626709,
+      "rewards/rejected": -14.006872177124023,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0657193605683837,
+      "eval_logits/chosen": 2.849980354309082,
+      "eval_logits/rejected": 2.6121249198913574,
+      "eval_logps/chosen": -4.064430236816406,
+      "eval_logps/rejected": -8.704176902770996,
+      "eval_loss": 0.20448654890060425,
+      "eval_rewards/accuracies": 0.9450549483299255,
+      "eval_rewards/chosen": -6.096645355224609,
+      "eval_rewards/margins": 6.959619998931885,
+      "eval_rewards/rejected": -13.056266784667969,
+      "eval_runtime": 27.949,
+      "eval_samples_per_second": 26.047,
+      "eval_steps_per_second": 3.256,
+      "step": 1200
+    },
+    {
+      "epoch": 1.074600355239787,
+      "grad_norm": 3.175405979156494,
+      "learning_rate": 4.4712697716573994e-07,
+      "logits/chosen": 1.7921645641326904,
+      "logits/rejected": 1.5822703838348389,
+      "logps/chosen": -3.969311475753784,
+      "logps/rejected": -7.864555358886719,
+      "loss": 0.161,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.953967094421387,
+      "rewards/margins": 5.842865943908691,
+      "rewards/rejected": -11.796833038330078,
+      "step": 1210
+    },
+    {
+      "epoch": 1.0834813499111902,
+      "grad_norm": 3.2191758155822754,
+      "learning_rate": 4.1769689822475147e-07,
+      "logits/chosen": 2.915822744369507,
+      "logits/rejected": 2.5579092502593994,
+      "logps/chosen": -4.58405065536499,
+      "logps/rejected": -8.522977828979492,
+      "loss": 0.1896,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.876075744628906,
+      "rewards/margins": 5.908390522003174,
+      "rewards/rejected": -12.784466743469238,
+      "step": 1220
+    },
+    {
+      "epoch": 1.0923623445825932,
+      "grad_norm": 0.9130955934524536,
+      "learning_rate": 3.891801862449629e-07,
+      "logits/chosen": 2.671440601348877,
+      "logits/rejected": 2.5282158851623535,
+      "logps/chosen": -3.7401490211486816,
+      "logps/rejected": -8.130763053894043,
+      "loss": 0.1919,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.610223293304443,
+      "rewards/margins": 6.5859222412109375,
+      "rewards/rejected": -12.196146011352539,
+      "step": 1230
+    },
+    {
+      "epoch": 1.1012433392539964,
+      "grad_norm": 3.875812292098999,
+      "learning_rate": 3.615893495987335e-07,
+      "logits/chosen": 2.6439268589019775,
+      "logits/rejected": 2.539719820022583,
+      "logps/chosen": -4.52361536026001,
+      "logps/rejected": -9.09494686126709,
+      "loss": 0.1784,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.785423278808594,
+      "rewards/margins": 6.856997013092041,
+      "rewards/rejected": -13.642419815063477,
+      "step": 1240
+    },
+    {
+      "epoch": 1.1101243339253997,
+      "grad_norm": 7.631316661834717,
+      "learning_rate": 3.3493649053890325e-07,
+      "logits/chosen": 2.893583297729492,
+      "logits/rejected": 2.6538450717926025,
+      "logps/chosen": -3.897947311401367,
+      "logps/rejected": -8.295917510986328,
+      "loss": 0.1609,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.846921443939209,
+      "rewards/margins": 6.596955299377441,
+      "rewards/rejected": -12.443876266479492,
+      "step": 1250
+    },
+    {
+      "epoch": 1.1101243339253997,
+      "eval_logits/chosen": 2.8801681995391846,
+      "eval_logits/rejected": 2.650672197341919,
+      "eval_logps/chosen": -4.073127269744873,
+      "eval_logps/rejected": -8.730562210083008,
+      "eval_loss": 0.20066653192043304,
+      "eval_rewards/accuracies": 0.9450549483299255,
+      "eval_rewards/chosen": -6.109691143035889,
+      "eval_rewards/margins": 6.986151695251465,
+      "eval_rewards/rejected": -13.095842361450195,
+      "eval_runtime": 26.92,
+      "eval_samples_per_second": 27.043,
+      "eval_steps_per_second": 3.38,
+      "step": 1250
+    },
+    {
+      "epoch": 1.119005328596803,
+      "grad_norm": 3.1444709300994873,
+      "learning_rate": 3.092332998903416e-07,
+      "logits/chosen": 2.922412395477295,
+      "logits/rejected": 2.7311949729919434,
+      "logps/chosen": -3.9704699516296387,
+      "logps/rejected": -8.181538581848145,
+      "loss": 0.1991,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.955705165863037,
+      "rewards/margins": 6.316603183746338,
+      "rewards/rejected": -12.272307395935059,
+      "step": 1260
+    },
+    {
+      "epoch": 1.1278863232682061,
+      "grad_norm": 3.2550008296966553,
+      "learning_rate": 2.844910519219632e-07,
+      "logits/chosen": 2.767855167388916,
+      "logits/rejected": 2.494089365005493,
+      "logps/chosen": -4.109368801116943,
+      "logps/rejected": -8.761442184448242,
+      "loss": 0.2242,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.164053916931152,
+      "rewards/margins": 6.978110313415527,
+      "rewards/rejected": -13.14216423034668,
+      "step": 1270
+    },
+    {
+      "epoch": 1.1367673179396092,
+      "grad_norm": 5.788249969482422,
+      "learning_rate": 2.6072059940146775e-07,
+      "logits/chosen": 2.5583932399749756,
+      "logits/rejected": 2.2768542766571045,
+      "logps/chosen": -4.3852667808532715,
+      "logps/rejected": -8.788955688476562,
+      "loss": 0.1869,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.577899932861328,
+      "rewards/margins": 6.605533599853516,
+      "rewards/rejected": -13.183435440063477,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1456483126110124,
+      "grad_norm": 2.779168128967285,
+      "learning_rate": 2.3793236883495164e-07,
+      "logits/chosen": 1.6079776287078857,
+      "logits/rejected": 1.7724790573120117,
+      "logps/chosen": -4.169196128845215,
+      "logps/rejected": -9.207098007202148,
+      "loss": 0.2117,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.2537946701049805,
+      "rewards/margins": 7.556851863861084,
+      "rewards/rejected": -13.810647964477539,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1545293072824157,
+      "grad_norm": 6.886547088623047,
+      "learning_rate": 2.1613635589349756e-07,
+      "logits/chosen": 2.139251708984375,
+      "logits/rejected": 1.9453144073486328,
+      "logps/chosen": -3.8890888690948486,
+      "logps/rejected": -8.812814712524414,
+      "loss": 0.1628,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.833632946014404,
+      "rewards/margins": 7.385587215423584,
+      "rewards/rejected": -13.219220161437988,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1545293072824157,
+      "eval_logits/chosen": 2.90960431098938,
+      "eval_logits/rejected": 2.6688857078552246,
+      "eval_logps/chosen": -4.054955959320068,
+      "eval_logps/rejected": -8.730274200439453,
+      "eval_loss": 0.19974029064178467,
+      "eval_rewards/accuracies": 0.9670329689979553,
+      "eval_rewards/chosen": -6.082433700561523,
+      "eval_rewards/margins": 7.012977600097656,
+      "eval_rewards/rejected": -13.095413208007812,
+      "eval_runtime": 26.9099,
+      "eval_samples_per_second": 27.053,
+      "eval_steps_per_second": 3.382,
+      "step": 1300
+    },
+    {
+      "epoch": 1.163410301953819,
+      "grad_norm": 4.912479400634766,
+      "learning_rate": 1.95342121028749e-07,
+      "logits/chosen": 2.834770679473877,
+      "logits/rejected": 2.735227584838867,
+      "logps/chosen": -3.7550606727600098,
+      "logps/rejected": -8.201028823852539,
+      "loss": 0.1795,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.632591724395752,
+      "rewards/margins": 6.668951988220215,
+      "rewards/rejected": -12.301542282104492,
+      "step": 1310
+    },
+    {
+      "epoch": 1.1722912966252221,
+      "grad_norm": 3.819091796875,
+      "learning_rate": 1.7555878527937164e-07,
+      "logits/chosen": 1.884900689125061,
+      "logits/rejected": 1.6134483814239502,
+      "logps/chosen": -3.9352309703826904,
+      "logps/rejected": -8.994625091552734,
+      "loss": 0.1739,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.902846813201904,
+      "rewards/margins": 7.589089870452881,
+      "rewards/rejected": -13.491937637329102,
+      "step": 1320
+    },
+    {
+      "epoch": 1.1811722912966252,
+      "grad_norm": 5.258669376373291,
+      "learning_rate": 1.567950262702714e-07,
+      "logits/chosen": 2.862034797668457,
+      "logits/rejected": 2.377957820892334,
+      "logps/chosen": -4.412306308746338,
+      "logps/rejected": -8.770759582519531,
+      "loss": 0.1937,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -6.6184587478637695,
+      "rewards/margins": 6.537681579589844,
+      "rewards/rejected": -13.156140327453613,
+      "step": 1330
+    },
+    {
+      "epoch": 1.1900532859680284,
+      "grad_norm": 3.4834094047546387,
+      "learning_rate": 1.3905907440629752e-07,
+      "logits/chosen": 2.71451997756958,
+      "logits/rejected": 2.5707905292510986,
+      "logps/chosen": -3.4515223503112793,
+      "logps/rejected": -8.354561805725098,
+      "loss": 0.1981,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.177282810211182,
+      "rewards/margins": 7.354557991027832,
+      "rewards/rejected": -12.531841278076172,
+      "step": 1340
+    },
+    {
+      "epoch": 1.1989342806394316,
+      "grad_norm": 3.1208136081695557,
+      "learning_rate": 1.223587092621162e-07,
+      "logits/chosen": 2.8508377075195312,
+      "logits/rejected": 2.4623186588287354,
+      "logps/chosen": -4.182574272155762,
+      "logps/rejected": -8.223688125610352,
+      "loss": 0.1963,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.273861408233643,
+      "rewards/margins": 6.061671257019043,
+      "rewards/rejected": -12.335532188415527,
+      "step": 1350
+    },
+    {
+      "epoch": 1.1989342806394316,
+      "eval_logits/chosen": 2.8848037719726562,
+      "eval_logits/rejected": 2.6544930934906006,
+      "eval_logps/chosen": -4.085648536682129,
+      "eval_logps/rejected": -8.76360034942627,
+      "eval_loss": 0.20008008182048798,
+      "eval_rewards/accuracies": 0.9560439586639404,
+      "eval_rewards/chosen": -6.128472328186035,
+      "eval_rewards/margins": 7.016927719116211,
+      "eval_rewards/rejected": -13.145400047302246,
+      "eval_runtime": 26.9454,
+      "eval_samples_per_second": 27.018,
+      "eval_steps_per_second": 3.377,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2078152753108349,
+      "grad_norm": 3.5807321071624756,
+      "learning_rate": 1.067012561698319e-07,
+      "logits/chosen": 1.843492865562439,
+      "logits/rejected": 1.8156530857086182,
+      "logps/chosen": -4.025892734527588,
+      "logps/rejected": -8.078580856323242,
+      "loss": 0.1965,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -6.038838863372803,
+      "rewards/margins": 6.079030990600586,
+      "rewards/rejected": -12.117870330810547,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2166962699822381,
+      "grad_norm": 3.0504233837127686,
+      "learning_rate": 9.209358300585474e-08,
+      "logits/chosen": 1.2856495380401611,
+      "logits/rejected": 1.3604472875595093,
+      "logps/chosen": -3.397179365158081,
+      "logps/rejected": -8.922881126403809,
+      "loss": 0.1569,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.095768928527832,
+      "rewards/margins": 8.288553237915039,
+      "rewards/rejected": -13.384321212768555,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2255772646536411,
+      "grad_norm": 2.8771817684173584,
+      "learning_rate": 7.854209717842231e-08,
+      "logits/chosen": 2.656306505203247,
+      "logits/rejected": 2.7314908504486084,
+      "logps/chosen": -4.436465263366699,
+      "logps/rejected": -8.556421279907227,
+      "loss": 0.1872,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.654697418212891,
+      "rewards/margins": 6.179934501647949,
+      "rewards/rejected": -12.834630966186523,
+      "step": 1380
+    },
+    {
+      "epoch": 1.2344582593250444,
+      "grad_norm": 2.865962505340576,
+      "learning_rate": 6.605274281709929e-08,
+      "logits/chosen": 2.354973793029785,
+      "logits/rejected": 2.103196620941162,
+      "logps/chosen": -3.735572099685669,
+      "logps/rejected": -8.092254638671875,
+      "loss": 0.2055,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.603358268737793,
+      "rewards/margins": 6.5350236892700195,
+      "rewards/rejected": -12.138381958007812,
+      "step": 1390
+    },
+    {
+      "epoch": 1.2433392539964476,
+      "grad_norm": 4.406766891479492,
+      "learning_rate": 5.463099816548578e-08,
+      "logits/chosen": 2.726349115371704,
+      "logits/rejected": 2.6014065742492676,
+      "logps/chosen": -4.092173099517822,
+      "logps/rejected": -8.570141792297363,
+      "loss": 0.1844,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.138258934020996,
+      "rewards/margins": 6.716952323913574,
+      "rewards/rejected": -12.855212211608887,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2433392539964476,
+      "eval_logits/chosen": 2.8822062015533447,
+      "eval_logits/rejected": 2.652130603790283,
+      "eval_logps/chosen": -4.102356433868408,
+      "eval_logps/rejected": -8.80092716217041,
+      "eval_loss": 0.20083114504814148,
+      "eval_rewards/accuracies": 0.9560439586639404,
+      "eval_rewards/chosen": -6.153535842895508,
+      "eval_rewards/margins": 7.04785680770874,
+      "eval_rewards/rejected": -13.201393127441406,
+      "eval_runtime": 26.9467,
+      "eval_samples_per_second": 27.016,
+      "eval_steps_per_second": 3.377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2522202486678509,
+      "grad_norm": 3.6099696159362793,
+      "learning_rate": 4.428187317827848e-08,
+      "logits/chosen": 2.6833858489990234,
+      "logits/rejected": 2.4535012245178223,
+      "logps/chosen": -3.947831392288208,
+      "logps/rejected": -8.458273887634277,
+      "loss": 0.2005,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.92174768447876,
+      "rewards/margins": 6.765664577484131,
+      "rewards/rejected": -12.687411308288574,
+      "step": 1410
+    },
+    {
+      "epoch": 1.261101243339254,
+      "grad_norm": 7.29236364364624,
+      "learning_rate": 3.5009907323737826e-08,
+      "logits/chosen": 2.0532803535461426,
+      "logits/rejected": 1.7998523712158203,
+      "logps/chosen": -4.222895622253418,
+      "logps/rejected": -9.165786743164062,
+      "loss": 0.2063,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.334342956542969,
+      "rewards/margins": 7.414336204528809,
+      "rewards/rejected": -13.748680114746094,
+      "step": 1420
+    },
+    {
+      "epoch": 1.2699822380106571,
+      "grad_norm": 3.2832329273223877,
+      "learning_rate": 2.681916759252917e-08,
+      "logits/chosen": 2.1531262397766113,
+      "logits/rejected": 2.0710244178771973,
+      "logps/chosen": -4.094164848327637,
+      "logps/rejected": -8.960153579711914,
+      "loss": 0.1704,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.141247749328613,
+      "rewards/margins": 7.2989821434021,
+      "rewards/rejected": -13.440229415893555,
+      "step": 1430
+    },
+    {
+      "epoch": 1.2788632326820604,
+      "grad_norm": 3.278916120529175,
+      "learning_rate": 1.9713246713805588e-08,
+      "logits/chosen": 2.748945713043213,
+      "logits/rejected": 2.439786195755005,
+      "logps/chosen": -3.968437910079956,
+      "logps/rejected": -8.686285018920898,
+      "loss": 0.1977,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -5.9526567459106445,
+      "rewards/margins": 7.076769828796387,
+      "rewards/rejected": -13.029426574707031,
+      "step": 1440
+    },
+    {
+      "epoch": 1.2877442273534636,
+      "grad_norm": 2.7193377017974854,
+      "learning_rate": 1.3695261579316776e-08,
+      "logits/chosen": 2.7628045082092285,
+      "logits/rejected": 2.551692247390747,
+      "logps/chosen": -4.074870586395264,
+      "logps/rejected": -9.106779098510742,
+      "loss": 0.1752,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.112306118011475,
+      "rewards/margins": 7.5478620529174805,
+      "rewards/rejected": -13.660168647766113,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2877442273534636,
+      "eval_logits/chosen": 2.8982574939727783,
+      "eval_logits/rejected": 2.6610724925994873,
+      "eval_logps/chosen": -4.0830888748168945,
+      "eval_logps/rejected": -8.783281326293945,
+      "eval_loss": 0.20020365715026855,
+      "eval_rewards/accuracies": 0.9670329689979553,
+      "eval_rewards/chosen": -6.1246337890625,
+      "eval_rewards/margins": 7.050288200378418,
+      "eval_rewards/rejected": -13.174921035766602,
+      "eval_runtime": 26.941,
+      "eval_samples_per_second": 27.022,
+      "eval_steps_per_second": 3.378,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2966252220248669,
+      "grad_norm": 2.02742862701416,
+      "learning_rate": 8.767851876239075e-09,
+      "logits/chosen": 2.2182817459106445,
+      "logits/rejected": 1.9512622356414795,
+      "logps/chosen": -3.714675188064575,
+      "logps/rejected": -8.23040771484375,
+      "loss": 0.1859,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.572012901306152,
+      "rewards/margins": 6.773598670959473,
+      "rewards/rejected": -12.345611572265625,
+      "step": 1460
+    },
+    {
+      "epoch": 1.30550621669627,
+      "grad_norm": 3.790600061416626,
+      "learning_rate": 4.933178929321103e-09,
+      "logits/chosen": 1.9530212879180908,
+      "logits/rejected": 1.8598028421401978,
+      "logps/chosen": -4.5896806716918945,
+      "logps/rejected": -8.957897186279297,
+      "loss": 0.1818,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.884521484375,
+      "rewards/margins": 6.5523247718811035,
+      "rewards/rejected": -13.436845779418945,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3143872113676731,
+      "grad_norm": 1.5860520601272583,
+      "learning_rate": 2.192924752854042e-09,
+      "logits/chosen": 2.4207961559295654,
+      "logits/rejected": 2.1768200397491455,
+      "logps/chosen": -4.266921520233154,
+      "logps/rejected": -8.554713249206543,
+      "loss": 0.1659,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -6.400382995605469,
+      "rewards/margins": 6.431687355041504,
+      "rewards/rejected": -12.832071304321289,
+      "step": 1480
+    },
+    {
+      "epoch": 1.3232682060390764,
+      "grad_norm": 5.297242641448975,
+      "learning_rate": 5.48291312886251e-10,
+      "logits/chosen": 1.6890628337860107,
+      "logits/rejected": 1.763393759727478,
+      "logps/chosen": -4.156857967376709,
+      "logps/rejected": -8.573880195617676,
+      "loss": 0.2256,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -6.235286235809326,
+      "rewards/margins": 6.625532627105713,
+      "rewards/rejected": -12.860818862915039,
+      "step": 1490
+    },
+    {
+      "epoch": 1.3321492007104796,
+      "grad_norm": 2.8218748569488525,
+      "learning_rate": 0.0,
+      "logits/chosen": 1.7690842151641846,
+      "logits/rejected": 1.6849496364593506,
+      "logps/chosen": -4.451314926147461,
+      "logps/rejected": -8.572367668151855,
+      "loss": 0.1845,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -6.676972389221191,
+      "rewards/margins": 6.181580543518066,
+      "rewards/rejected": -12.858552932739258,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3321492007104796,
+      "eval_logits/chosen": 2.8886427879333496,
+      "eval_logits/rejected": 2.6572160720825195,
+      "eval_logps/chosen": -4.096730709075928,
+      "eval_logps/rejected": -8.783284187316895,
+      "eval_loss": 0.19957485795021057,
+      "eval_rewards/accuracies": 0.9560439586639404,
+      "eval_rewards/chosen": -6.1450958251953125,
+      "eval_rewards/margins": 7.029829978942871,
+      "eval_rewards/rejected": -13.174925804138184,
+      "eval_runtime": 26.94,
+      "eval_samples_per_second": 27.023,
+      "eval_steps_per_second": 3.378,
+      "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": 3.6519125646709883e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}