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": 1.3776271965085563,
+  "eval_steps": 50,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00918800964741013,
+      "grad_norm": 0.036612071096897125,
+      "learning_rate": 4.999451708687114e-06,
+      "logits/chosen": 15.01579761505127,
+      "logits/rejected": 15.359031677246094,
+      "logps/chosen": -0.2681262791156769,
+      "logps/rejected": -0.31947994232177734,
+      "loss": 0.9551,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.40218934416770935,
+      "rewards/margins": 0.07703053951263428,
+      "rewards/rejected": -0.479219913482666,
+      "step": 10
+    },
+    {
+      "epoch": 0.01837601929482026,
+      "grad_norm": 0.05575725808739662,
+      "learning_rate": 4.997807075247147e-06,
+      "logits/chosen": 14.570712089538574,
+      "logits/rejected": 15.321355819702148,
+      "logps/chosen": -0.2867889404296875,
+      "logps/rejected": -0.3514837622642517,
+      "loss": 0.923,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.43018341064453125,
+      "rewards/margins": 0.09704220294952393,
+      "rewards/rejected": -0.5272256135940552,
+      "step": 20
+    },
+    {
+      "epoch": 0.02756402894223039,
+      "grad_norm": 0.0492466576397419,
+      "learning_rate": 4.9950668210706795e-06,
+      "logits/chosen": 14.748420715332031,
+      "logits/rejected": 14.969354629516602,
+      "logps/chosen": -0.28405922651290894,
+      "logps/rejected": -0.32855403423309326,
+      "loss": 0.9357,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.426088809967041,
+      "rewards/margins": 0.06674225628376007,
+      "rewards/rejected": -0.4928310811519623,
+      "step": 30
+    },
+    {
+      "epoch": 0.03675203858964052,
+      "grad_norm": 0.05719422921538353,
+      "learning_rate": 4.9912321481237616e-06,
+      "logits/chosen": 14.28278923034668,
+      "logits/rejected": 14.76964282989502,
+      "logps/chosen": -0.27940627932548523,
+      "logps/rejected": -0.3408831059932709,
+      "loss": 0.9215,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.41910940408706665,
+      "rewards/margins": 0.09221524000167847,
+      "rewards/rejected": -0.5113246440887451,
+      "step": 40
+    },
+    {
+      "epoch": 0.04594004823705065,
+      "grad_norm": 0.06247895210981369,
+      "learning_rate": 4.986304738420684e-06,
+      "logits/chosen": 14.943578720092773,
+      "logits/rejected": 14.936178207397461,
+      "logps/chosen": -0.2819541394710541,
+      "logps/rejected": -0.3245392441749573,
+      "loss": 0.9464,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.4229312539100647,
+      "rewards/margins": 0.06387762725353241,
+      "rewards/rejected": -0.4868088662624359,
+      "step": 50
+    },
+    {
+      "epoch": 0.04594004823705065,
+      "eval_logits/chosen": 14.7594575881958,
+      "eval_logits/rejected": 15.193694114685059,
+      "eval_logps/chosen": -0.2807807922363281,
+      "eval_logps/rejected": -0.36209535598754883,
+      "eval_loss": 0.9397181868553162,
+      "eval_rewards/accuracies": 0.5681818127632141,
+      "eval_rewards/chosen": -0.4211711883544922,
+      "eval_rewards/margins": 0.12197184562683105,
+      "eval_rewards/rejected": -0.5431429743766785,
+      "eval_runtime": 24.9762,
+      "eval_samples_per_second": 28.187,
+      "eval_steps_per_second": 3.523,
+      "step": 50
+    },
+    {
+      "epoch": 0.05512805788446078,
+      "grad_norm": 0.11519577354192734,
+      "learning_rate": 4.980286753286196e-06,
+      "logits/chosen": 14.996228218078613,
+      "logits/rejected": 15.37781810760498,
+      "logps/chosen": -0.2809831202030182,
+      "logps/rejected": -0.35486167669296265,
+      "loss": 0.9318,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.4214746952056885,
+      "rewards/margins": 0.1108178049325943,
+      "rewards/rejected": -0.5322924852371216,
+      "step": 60
+    },
+    {
+      "epoch": 0.06431606753187091,
+      "grad_norm": 0.06691388040781021,
+      "learning_rate": 4.973180832407471e-06,
+      "logits/chosen": 14.612454414367676,
+      "logits/rejected": 15.678136825561523,
+      "logps/chosen": -0.2569667100906372,
+      "logps/rejected": -0.40047627687454224,
+      "loss": 0.9158,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.3854501247406006,
+      "rewards/margins": 0.21526429057121277,
+      "rewards/rejected": -0.600714385509491,
+      "step": 70
+    },
+    {
+      "epoch": 0.07350407717928104,
+      "grad_norm": 0.05976058170199394,
+      "learning_rate": 4.964990092676263e-06,
+      "logits/chosen": 14.873895645141602,
+      "logits/rejected": 15.50474739074707,
+      "logps/chosen": -0.28742527961730957,
+      "logps/rejected": -0.37555089592933655,
+      "loss": 0.9372,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.43113788962364197,
+      "rewards/margins": 0.13218846917152405,
+      "rewards/rejected": -0.5633264183998108,
+      "step": 80
+    },
+    {
+      "epoch": 0.08269208682669117,
+      "grad_norm": 0.0602131113409996,
+      "learning_rate": 4.9557181268217225e-06,
+      "logits/chosen": 14.356691360473633,
+      "logits/rejected": 14.895658493041992,
+      "logps/chosen": -0.2613506317138672,
+      "logps/rejected": -0.3317110538482666,
+      "loss": 0.9324,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.3920259475708008,
+      "rewards/margins": 0.10554064810276031,
+      "rewards/rejected": -0.4975665509700775,
+      "step": 90
+    },
+    {
+      "epoch": 0.0918800964741013,
+      "grad_norm": 0.07126503437757492,
+      "learning_rate": 4.9453690018345144e-06,
+      "logits/chosen": 14.862826347351074,
+      "logits/rejected": 15.257089614868164,
+      "logps/chosen": -0.2707213759422302,
+      "logps/rejected": -0.3511395752429962,
+      "loss": 0.9353,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.4060820937156677,
+      "rewards/margins": 0.1206272691488266,
+      "rewards/rejected": -0.5267094373703003,
+      "step": 100
+    },
+    {
+      "epoch": 0.0918800964741013,
+      "eval_logits/chosen": 14.664334297180176,
+      "eval_logits/rejected": 15.113536834716797,
+      "eval_logps/chosen": -0.2750833034515381,
+      "eval_logps/rejected": -0.36540210247039795,
+      "eval_loss": 0.9324077367782593,
+      "eval_rewards/accuracies": 0.5795454382896423,
+      "eval_rewards/chosen": -0.41262495517730713,
+      "eval_rewards/margins": 0.1354781985282898,
+      "eval_rewards/rejected": -0.5481031537055969,
+      "eval_runtime": 24.4286,
+      "eval_samples_per_second": 28.819,
+      "eval_steps_per_second": 3.602,
+      "step": 100
+    },
+    {
+      "epoch": 0.10106810612151143,
+      "grad_norm": 0.07136944681406021,
+      "learning_rate": 4.933947257182901e-06,
+      "logits/chosen": 14.942098617553711,
+      "logits/rejected": 15.138586044311523,
+      "logps/chosen": -0.2860812246799469,
+      "logps/rejected": -0.36259371042251587,
+      "loss": 0.934,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.42912182211875916,
+      "rewards/margins": 0.11476878076791763,
+      "rewards/rejected": -0.5438905954360962,
+      "step": 110
+    },
+    {
+      "epoch": 0.11025611576892155,
+      "grad_norm": 0.07038908451795578,
+      "learning_rate": 4.921457902821578e-06,
+      "logits/chosen": 14.488851547241211,
+      "logits/rejected": 14.702054023742676,
+      "logps/chosen": -0.2662215232849121,
+      "logps/rejected": -0.3013685941696167,
+      "loss": 0.9202,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.39933228492736816,
+      "rewards/margins": 0.05272058770060539,
+      "rewards/rejected": -0.45205289125442505,
+      "step": 120
+    },
+    {
+      "epoch": 0.11944412541633169,
+      "grad_norm": 0.06875801086425781,
+      "learning_rate": 4.907906416994146e-06,
+      "logits/chosen": 14.075657844543457,
+      "logits/rejected": 14.696513175964355,
+      "logps/chosen": -0.250360369682312,
+      "logps/rejected": -0.3504650592803955,
+      "loss": 0.9266,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.375540554523468,
+      "rewards/margins": 0.15015706419944763,
+      "rewards/rejected": -0.5256975889205933,
+      "step": 130
+    },
+    {
+      "epoch": 0.12863213506374183,
+      "grad_norm": 0.0984601378440857,
+      "learning_rate": 4.893298743830168e-06,
+      "logits/chosen": 13.738212585449219,
+      "logits/rejected": 14.311574935913086,
+      "logps/chosen": -0.26711025834083557,
+      "logps/rejected": -0.3587702810764313,
+      "loss": 0.9185,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.40066537261009216,
+      "rewards/margins": 0.13749003410339355,
+      "rewards/rejected": -0.5381554365158081,
+      "step": 140
+    },
+    {
+      "epoch": 0.13782014471115195,
+      "grad_norm": 0.10201425850391388,
+      "learning_rate": 4.8776412907378845e-06,
+      "logits/chosen": 13.7462797164917,
+      "logits/rejected": 14.230626106262207,
+      "logps/chosen": -0.25559619069099426,
+      "logps/rejected": -0.3708702623844147,
+      "loss": 0.9106,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.3833943009376526,
+      "rewards/margins": 0.17291104793548584,
+      "rewards/rejected": -0.5563054084777832,
+      "step": 150
+    },
+    {
+      "epoch": 0.13782014471115195,
+      "eval_logits/chosen": 13.458538055419922,
+      "eval_logits/rejected": 13.998083114624023,
+      "eval_logps/chosen": -0.2759075462818146,
+      "eval_logps/rejected": -0.3873325288295746,
+      "eval_loss": 0.9164085388183594,
+      "eval_rewards/accuracies": 0.5795454382896423,
+      "eval_rewards/chosen": -0.41386130452156067,
+      "eval_rewards/margins": 0.1671374887228012,
+      "eval_rewards/rejected": -0.5809988379478455,
+      "eval_runtime": 24.4393,
+      "eval_samples_per_second": 28.806,
+      "eval_steps_per_second": 3.601,
+      "step": 150
+    },
+    {
+      "epoch": 0.14700815435856207,
+      "grad_norm": 0.11537656933069229,
+      "learning_rate": 4.860940925593703e-06,
+      "logits/chosen": 12.686149597167969,
+      "logits/rejected": 13.478736877441406,
+      "logps/chosen": -0.23941929638385773,
+      "logps/rejected": -0.3713286519050598,
+      "loss": 0.9094,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.3591288924217224,
+      "rewards/margins": 0.1978640854358673,
+      "rewards/rejected": -0.5569929480552673,
+      "step": 160
+    },
+    {
+      "epoch": 0.1561961640059722,
+      "grad_norm": 0.1196313351392746,
+      "learning_rate": 4.84320497372973e-06,
+      "logits/chosen": 13.221656799316406,
+      "logits/rejected": 13.317082405090332,
+      "logps/chosen": -0.3033878207206726,
+      "logps/rejected": -0.3784424960613251,
+      "loss": 0.9057,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.4550817608833313,
+      "rewards/margins": 0.11258199065923691,
+      "rewards/rejected": -0.5676637887954712,
+      "step": 170
+    },
+    {
+      "epoch": 0.16538417365338234,
+      "grad_norm": 0.18745549023151398,
+      "learning_rate": 4.824441214720629e-06,
+      "logits/chosen": 11.797627449035645,
+      "logits/rejected": 12.031414985656738,
+      "logps/chosen": -0.2746419608592987,
+      "logps/rejected": -0.3629845976829529,
+      "loss": 0.8954,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.41196292638778687,
+      "rewards/margins": 0.13251398503780365,
+      "rewards/rejected": -0.5444768667221069,
+      "step": 180
+    },
+    {
+      "epoch": 0.17457218330079247,
+      "grad_norm": 0.1806156188249588,
+      "learning_rate": 4.804657878971252e-06,
+      "logits/chosen": 10.275301933288574,
+      "logits/rejected": 10.937273025512695,
+      "logps/chosen": -0.2880379557609558,
+      "logps/rejected": -0.4154580533504486,
+      "loss": 0.8875,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.43205690383911133,
+      "rewards/margins": 0.19113019108772278,
+      "rewards/rejected": -0.6231871247291565,
+      "step": 190
+    },
+    {
+      "epoch": 0.1837601929482026,
+      "grad_norm": 0.1839464157819748,
+      "learning_rate": 4.783863644106502e-06,
+      "logits/chosen": 10.020039558410645,
+      "logits/rejected": 10.66059398651123,
+      "logps/chosen": -0.3136019706726074,
+      "logps/rejected": -0.4385503828525543,
+      "loss": 0.8647,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.47040295600891113,
+      "rewards/margins": 0.18742261826992035,
+      "rewards/rejected": -0.6578255891799927,
+      "step": 200
+    },
+    {
+      "epoch": 0.1837601929482026,
+      "eval_logits/chosen": 9.442557334899902,
+      "eval_logits/rejected": 10.053345680236816,
+      "eval_logps/chosen": -0.3080674409866333,
+      "eval_logps/rejected": -0.4899139702320099,
+      "eval_loss": 0.8702690005302429,
+      "eval_rewards/accuracies": 0.6931818127632141,
+      "eval_rewards/chosen": -0.46210116147994995,
+      "eval_rewards/margins": 0.27276986837387085,
+      "eval_rewards/rejected": -0.7348710894584656,
+      "eval_runtime": 24.4185,
+      "eval_samples_per_second": 28.831,
+      "eval_steps_per_second": 3.604,
+      "step": 200
+    },
+    {
+      "epoch": 0.19294820259561274,
+      "grad_norm": 0.269613116979599,
+      "learning_rate": 4.762067631165049e-06,
+      "logits/chosen": 7.941342353820801,
+      "logits/rejected": 8.542920112609863,
+      "logps/chosen": -0.3083941638469696,
+      "logps/rejected": -0.5024437308311462,
+      "loss": 0.8471,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.4625912606716156,
+      "rewards/margins": 0.29107433557510376,
+      "rewards/rejected": -0.7536656856536865,
+      "step": 210
+    },
+    {
+      "epoch": 0.20213621224302286,
+      "grad_norm": 0.2640094459056854,
+      "learning_rate": 4.7392794005985324e-06,
+      "logits/chosen": 7.587499141693115,
+      "logits/rejected": 7.592519283294678,
+      "logps/chosen": -0.3381899893283844,
+      "logps/rejected": -0.48494213819503784,
+      "loss": 0.8427,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.5072849988937378,
+      "rewards/margins": 0.22012826800346375,
+      "rewards/rejected": -0.7274132966995239,
+      "step": 220
+    },
+    {
+      "epoch": 0.21132422189043298,
+      "grad_norm": 0.29708293080329895,
+      "learning_rate": 4.715508948078037e-06,
+      "logits/chosen": 6.250656604766846,
+      "logits/rejected": 6.7652716636657715,
+      "logps/chosen": -0.3644888997077942,
+      "logps/rejected": -0.5470594167709351,
+      "loss": 0.8201,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.5467333793640137,
+      "rewards/margins": 0.2738557755947113,
+      "rewards/rejected": -0.8205891847610474,
+      "step": 230
+    },
+    {
+      "epoch": 0.2205122315378431,
+      "grad_norm": 0.35299497842788696,
+      "learning_rate": 4.690766700109659e-06,
+      "logits/chosen": 4.6331706047058105,
+      "logits/rejected": 4.710076332092285,
+      "logps/chosen": -0.3634452223777771,
+      "logps/rejected": -0.7193974256515503,
+      "loss": 0.7877,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.545167863368988,
+      "rewards/margins": 0.5339283347129822,
+      "rewards/rejected": -1.0790963172912598,
+      "step": 240
+    },
+    {
+      "epoch": 0.22970024118525326,
+      "grad_norm": 0.4265730082988739,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 4.992984771728516,
+      "logits/rejected": 4.606354713439941,
+      "logps/chosen": -0.413116455078125,
+      "logps/rejected": -0.7104976177215576,
+      "loss": 0.7902,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.6196746826171875,
+      "rewards/margins": 0.4460717737674713,
+      "rewards/rejected": -1.0657463073730469,
+      "step": 250
+    },
+    {
+      "epoch": 0.22970024118525326,
+      "eval_logits/chosen": 4.127804279327393,
+      "eval_logits/rejected": 3.742251396179199,
+      "eval_logps/chosen": -0.420327365398407,
+      "eval_logps/rejected": -0.7902651429176331,
+      "eval_loss": 0.7682384252548218,
+      "eval_rewards/accuracies": 0.7159090638160706,
+      "eval_rewards/chosen": -0.6304910182952881,
+      "eval_rewards/margins": 0.5549066662788391,
+      "eval_rewards/rejected": -1.185397744178772,
+      "eval_runtime": 24.4318,
+      "eval_samples_per_second": 28.815,
+      "eval_steps_per_second": 3.602,
+      "step": 250
+    },
+    {
+      "epoch": 0.23888825083266338,
+      "grad_norm": 0.7236106395721436,
+      "learning_rate": 4.638410650401267e-06,
+      "logits/chosen": 2.454423427581787,
+      "logits/rejected": 1.816563367843628,
+      "logps/chosen": -0.4492695927619934,
+      "logps/rejected": -0.8738088607788086,
+      "loss": 0.6911,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.6739044189453125,
+      "rewards/margins": 0.6368088126182556,
+      "rewards/rejected": -1.3107131719589233,
+      "step": 260
+    },
+    {
+      "epoch": 0.2480762604800735,
+      "grad_norm": 0.5856125950813293,
+      "learning_rate": 4.610819813755038e-06,
+      "logits/chosen": 3.2105612754821777,
+      "logits/rejected": 2.5531132221221924,
+      "logps/chosen": -0.537078320980072,
+      "logps/rejected": -1.2025481462478638,
+      "loss": 0.6774,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.80561763048172,
+      "rewards/margins": 0.9982045888900757,
+      "rewards/rejected": -1.8038222789764404,
+      "step": 270
+    },
+    {
+      "epoch": 0.25726427012748365,
+      "grad_norm": 0.7396731972694397,
+      "learning_rate": 4.582303101775249e-06,
+      "logits/chosen": 2.0327231884002686,
+      "logits/rejected": 1.4601097106933594,
+      "logps/chosen": -0.47658151388168335,
+      "logps/rejected": -1.3808696269989014,
+      "loss": 0.628,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7148722410202026,
+      "rewards/margins": 1.3564319610595703,
+      "rewards/rejected": -2.0713045597076416,
+      "step": 280
+    },
+    {
+      "epoch": 0.2664522797748938,
+      "grad_norm": 2.412203550338745,
+      "learning_rate": 4.55287302283426e-06,
+      "logits/chosen": 1.2262591123580933,
+      "logits/rejected": 0.22599482536315918,
+      "logps/chosen": -0.5671601891517639,
+      "logps/rejected": -1.6760343313217163,
+      "loss": 0.5988,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.8507402539253235,
+      "rewards/margins": 1.6633113622665405,
+      "rewards/rejected": -2.5140514373779297,
+      "step": 290
+    },
+    {
+      "epoch": 0.2756402894223039,
+      "grad_norm": 1.0477895736694336,
+      "learning_rate": 4.522542485937369e-06,
+      "logits/chosen": 1.9952911138534546,
+      "logits/rejected": 1.1298446655273438,
+      "logps/chosen": -0.6152974367141724,
+      "logps/rejected": -2.128481388092041,
+      "loss": 0.5927,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.9229460954666138,
+      "rewards/margins": 2.2697763442993164,
+      "rewards/rejected": -3.192722797393799,
+      "step": 300
+    },
+    {
+      "epoch": 0.2756402894223039,
+      "eval_logits/chosen": 1.6342910528182983,
+      "eval_logits/rejected": 0.633538007736206,
+      "eval_logps/chosen": -0.606099545955658,
+      "eval_logps/rejected": -1.882785439491272,
+      "eval_loss": 0.5978505611419678,
+      "eval_rewards/accuracies": 0.7159090638160706,
+      "eval_rewards/chosen": -0.909149169921875,
+      "eval_rewards/margins": 1.9150291681289673,
+      "eval_rewards/rejected": -2.824178457260132,
+      "eval_runtime": 24.4299,
+      "eval_samples_per_second": 28.817,
+      "eval_steps_per_second": 3.602,
+      "step": 300
+    },
+    {
+      "epoch": 0.284828299069714,
+      "grad_norm": 3.0767388343811035,
+      "learning_rate": 4.491324795060491e-06,
+      "logits/chosen": 1.0374902486801147,
+      "logits/rejected": 0.6220051646232605,
+      "logps/chosen": -0.6778531074523926,
+      "logps/rejected": -1.8290255069732666,
+      "loss": 0.5792,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -1.0167796611785889,
+      "rewards/margins": 1.726758599281311,
+      "rewards/rejected": -2.7435383796691895,
+      "step": 310
+    },
+    {
+      "epoch": 0.29401630871712414,
+      "grad_norm": 0.6015120148658752,
+      "learning_rate": 4.4592336433146e-06,
+      "logits/chosen": 1.0050956010818481,
+      "logits/rejected": -0.016118621453642845,
+      "logps/chosen": -0.6865260004997253,
+      "logps/rejected": -2.113417148590088,
+      "loss": 0.5384,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.0297890901565552,
+      "rewards/margins": 2.140336513519287,
+      "rewards/rejected": -3.1701254844665527,
+      "step": 320
+    },
+    {
+      "epoch": 0.30320431836453426,
+      "grad_norm": 0.7415631413459778,
+      "learning_rate": 4.426283106939474e-06,
+      "logits/chosen": 0.5536144971847534,
+      "logits/rejected": -0.1644023358821869,
+      "logps/chosen": -0.8181726336479187,
+      "logps/rejected": -2.581185817718506,
+      "loss": 0.5671,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.2272589206695557,
+      "rewards/margins": 2.644519805908203,
+      "rewards/rejected": -3.871778964996338,
+      "step": 330
+    },
+    {
+      "epoch": 0.3123923280119444,
+      "grad_norm": 0.8956871628761292,
+      "learning_rate": 4.3924876391293915e-06,
+      "logits/chosen": 1.6062015295028687,
+      "logits/rejected": 0.9243733286857605,
+      "logps/chosen": -0.8991573452949524,
+      "logps/rejected": -2.935060977935791,
+      "loss": 0.5124,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.348736047744751,
+      "rewards/margins": 3.0538551807403564,
+      "rewards/rejected": -4.402591228485107,
+      "step": 340
+    },
+    {
+      "epoch": 0.32158033765935456,
+      "grad_norm": 1.1822264194488525,
+      "learning_rate": 4.357862063693486e-06,
+      "logits/chosen": 1.8171085119247437,
+      "logits/rejected": 1.228049397468567,
+      "logps/chosen": -0.8822734951972961,
+      "logps/rejected": -2.4744174480438232,
+      "loss": 0.516,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.3234103918075562,
+      "rewards/margins": 2.388216018676758,
+      "rewards/rejected": -3.7116265296936035,
+      "step": 350
+    },
+    {
+      "epoch": 0.32158033765935456,
+      "eval_logits/chosen": 1.1368330717086792,
+      "eval_logits/rejected": 0.2795785665512085,
+      "eval_logps/chosen": -0.9485350251197815,
+      "eval_logps/rejected": -2.6484899520874023,
+      "eval_loss": 0.5133901238441467,
+      "eval_rewards/accuracies": 0.7727272510528564,
+      "eval_rewards/chosen": -1.4228025674819946,
+      "eval_rewards/margins": 2.5499324798583984,
+      "eval_rewards/rejected": -3.9727354049682617,
+      "eval_runtime": 24.4277,
+      "eval_samples_per_second": 28.82,
+      "eval_steps_per_second": 3.602,
+      "step": 350
+    },
+    {
+      "epoch": 0.3307683473067647,
+      "grad_norm": 2.5278775691986084,
+      "learning_rate": 4.322421568553529e-06,
+      "logits/chosen": 1.1921958923339844,
+      "logits/rejected": 0.7565670013427734,
+      "logps/chosen": -1.4180412292480469,
+      "logps/rejected": -3.0890870094299316,
+      "loss": 0.4811,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -2.1270618438720703,
+      "rewards/margins": 2.5065689086914062,
+      "rewards/rejected": -4.633630752563477,
+      "step": 360
+    },
+    {
+      "epoch": 0.3399563569541748,
+      "grad_norm": 1.7325788736343384,
+      "learning_rate": 4.286181699082008e-06,
+      "logits/chosen": 0.997096836566925,
+      "logits/rejected": 0.4399908483028412,
+      "logps/chosen": -1.9010308980941772,
+      "logps/rejected": -3.6025185585021973,
+      "loss": 0.4326,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -2.851546287536621,
+      "rewards/margins": 2.552231550216675,
+      "rewards/rejected": -5.403778076171875,
+      "step": 370
+    },
+    {
+      "epoch": 0.34914436660158493,
+      "grad_norm": 4.608370304107666,
+      "learning_rate": 4.249158351283414e-06,
+      "logits/chosen": 1.0715999603271484,
+      "logits/rejected": 0.6113725900650024,
+      "logps/chosen": -2.4032845497131348,
+      "logps/rejected": -3.9940528869628906,
+      "loss": 0.4027,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -3.6049270629882812,
+      "rewards/margins": 2.3861520290374756,
+      "rewards/rejected": -5.991078853607178,
+      "step": 380
+    },
+    {
+      "epoch": 0.35833237624899505,
+      "grad_norm": 4.600816249847412,
+      "learning_rate": 4.211367764821722e-06,
+      "logits/chosen": 1.4443682432174683,
+      "logits/rejected": 0.8617011904716492,
+      "logps/chosen": -2.349093198776245,
+      "logps/rejected": -3.9943203926086426,
+      "loss": 0.4118,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -3.5236401557922363,
+      "rewards/margins": 2.467839479446411,
+      "rewards/rejected": -5.991480350494385,
+      "step": 390
+    },
+    {
+      "epoch": 0.3675203858964052,
+      "grad_norm": 2.1458094120025635,
+      "learning_rate": 4.172826515897146e-06,
+      "logits/chosen": 1.3029582500457764,
+      "logits/rejected": 0.7705980539321899,
+      "logps/chosen": -2.192617416381836,
+      "logps/rejected": -3.8413078784942627,
+      "loss": 0.3557,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -3.288925886154175,
+      "rewards/margins": 2.4730350971221924,
+      "rewards/rejected": -5.761960506439209,
+      "step": 400
+    },
+    {
+      "epoch": 0.3675203858964052,
+      "eval_logits/chosen": 0.8742353320121765,
+      "eval_logits/rejected": 0.14320053160190582,
+      "eval_logps/chosen": -2.0894505977630615,
+      "eval_logps/rejected": -4.20783805847168,
+      "eval_loss": 0.4082850515842438,
+      "eval_rewards/accuracies": 0.8863636255264282,
+      "eval_rewards/chosen": -3.1341757774353027,
+      "eval_rewards/margins": 3.1775810718536377,
+      "eval_rewards/rejected": -6.311756610870361,
+      "eval_runtime": 24.4316,
+      "eval_samples_per_second": 28.815,
+      "eval_steps_per_second": 3.602,
+      "step": 400
+    },
+    {
+      "epoch": 0.3767083955438153,
+      "grad_norm": 2.5496387481689453,
+      "learning_rate": 4.133551509975264e-06,
+      "logits/chosen": 1.9024279117584229,
+      "logits/rejected": 1.4777928590774536,
+      "logps/chosen": -2.7541470527648926,
+      "logps/rejected": -4.542642116546631,
+      "loss": 0.4184,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -4.13122034072876,
+      "rewards/margins": 2.6827428340911865,
+      "rewards/rejected": -6.813962459564209,
+      "step": 410
+    },
+    {
+      "epoch": 0.3858964051912255,
+      "grad_norm": 2.6187174320220947,
+      "learning_rate": 4.093559974371725e-06,
+      "logits/chosen": 1.9345887899398804,
+      "logits/rejected": 1.4047685861587524,
+      "logps/chosen": -2.389430522918701,
+      "logps/rejected": -4.439882755279541,
+      "loss": 0.4096,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -3.5841457843780518,
+      "rewards/margins": 3.0756776332855225,
+      "rewards/rejected": -6.659823417663574,
+      "step": 420
+    },
+    {
+      "epoch": 0.3950844148386356,
+      "grad_norm": 3.762899398803711,
+      "learning_rate": 4.052869450695776e-06,
+      "logits/chosen": 1.2521915435791016,
+      "logits/rejected": 0.7238092422485352,
+      "logps/chosen": -2.5571534633636475,
+      "logps/rejected": -4.675185203552246,
+      "loss": 0.4083,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -3.835730791091919,
+      "rewards/margins": 3.1770474910736084,
+      "rewards/rejected": -7.012777805328369,
+      "step": 430
+    },
+    {
+      "epoch": 0.4042724244860457,
+      "grad_norm": 3.2343404293060303,
+      "learning_rate": 4.011497787155938e-06,
+      "logits/chosen": 1.9626567363739014,
+      "logits/rejected": 1.3136894702911377,
+      "logps/chosen": -2.892967939376831,
+      "logps/rejected": -5.003688335418701,
+      "loss": 0.3783,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -4.339452266693115,
+      "rewards/margins": 3.1660804748535156,
+      "rewards/rejected": -7.505532264709473,
+      "step": 440
+    },
+    {
+      "epoch": 0.41346043413345585,
+      "grad_norm": 3.2979824542999268,
+      "learning_rate": 3.969463130731183e-06,
+      "logits/chosen": 1.159234881401062,
+      "logits/rejected": 0.5396692752838135,
+      "logps/chosen": -2.7545204162597656,
+      "logps/rejected": -5.4179182052612305,
+      "loss": 0.347,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.131781101226807,
+      "rewards/margins": 3.9950966835021973,
+      "rewards/rejected": -8.126876831054688,
+      "step": 450
+    },
+    {
+      "epoch": 0.41346043413345585,
+      "eval_logits/chosen": 0.9304068088531494,
+      "eval_logits/rejected": 0.30015668272972107,
+      "eval_logps/chosen": -2.485308885574341,
+      "eval_logps/rejected": -4.880238056182861,
+      "eval_loss": 0.36501914262771606,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -3.7279627323150635,
+      "eval_rewards/margins": 3.592393636703491,
+      "eval_rewards/rejected": -7.320356845855713,
+      "eval_runtime": 24.4234,
+      "eval_samples_per_second": 28.825,
+      "eval_steps_per_second": 3.603,
+      "step": 450
+    },
+    {
+      "epoch": 0.42264844378086597,
+      "grad_norm": 3.155860185623169,
+      "learning_rate": 3.92678391921108e-06,
+      "logits/chosen": 1.633522391319275,
+      "logits/rejected": 1.0575059652328491,
+      "logps/chosen": -2.7214303016662598,
+      "logps/rejected": -4.766176223754883,
+      "loss": 0.3689,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.082144737243652,
+      "rewards/margins": 3.0671191215515137,
+      "rewards/rejected": -7.149264335632324,
+      "step": 460
+    },
+    {
+      "epoch": 0.4318364534282761,
+      "grad_norm": 2.9949357509613037,
+      "learning_rate": 3.88347887310836e-06,
+      "logits/chosen": 1.3139212131500244,
+      "logits/rejected": 0.5838541388511658,
+      "logps/chosen": -2.5324313640594482,
+      "logps/rejected": -4.993292808532715,
+      "loss": 0.3587,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -3.7986464500427246,
+      "rewards/margins": 3.6912925243377686,
+      "rewards/rejected": -7.489938259124756,
+      "step": 470
+    },
+    {
+      "epoch": 0.4410244630756862,
+      "grad_norm": 2.4548208713531494,
+      "learning_rate": 3.839566987447492e-06,
+      "logits/chosen": 1.2342166900634766,
+      "logits/rejected": 0.8118699193000793,
+      "logps/chosen": -2.876863479614258,
+      "logps/rejected": -5.457588195800781,
+      "loss": 0.2922,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -4.315295219421387,
+      "rewards/margins": 3.871086597442627,
+      "rewards/rejected": -8.186381340026855,
+      "step": 480
+    },
+    {
+      "epoch": 0.45021247272309634,
+      "grad_norm": 2.0953762531280518,
+      "learning_rate": 3.795067523432826e-06,
+      "logits/chosen": 1.8121936321258545,
+      "logits/rejected": 1.454637050628662,
+      "logps/chosen": -3.2022106647491455,
+      "logps/rejected": -5.47930908203125,
+      "loss": 0.3086,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.803316116333008,
+      "rewards/margins": 3.4156479835510254,
+      "rewards/rejected": -8.218963623046875,
+      "step": 490
+    },
+    {
+      "epoch": 0.4594004823705065,
+      "grad_norm": 2.4918301105499268,
+      "learning_rate": 3.7500000000000005e-06,
+      "logits/chosen": 1.5386875867843628,
+      "logits/rejected": 1.2544763088226318,
+      "logps/chosen": -3.2174277305603027,
+      "logps/rejected": -6.012864112854004,
+      "loss": 0.3128,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.826140880584717,
+      "rewards/margins": 4.193154335021973,
+      "rewards/rejected": -9.019296646118164,
+      "step": 500
+    },
+    {
+      "epoch": 0.4594004823705065,
+      "eval_logits/chosen": 0.8257808685302734,
+      "eval_logits/rejected": 0.27475622296333313,
+      "eval_logps/chosen": -2.755974054336548,
+      "eval_logps/rejected": -5.469714641571045,
+      "eval_loss": 0.32884541153907776,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -4.133961200714111,
+      "eval_rewards/margins": 4.070610523223877,
+      "eval_rewards/rejected": -8.204572677612305,
+      "eval_runtime": 24.4191,
+      "eval_samples_per_second": 28.83,
+      "eval_steps_per_second": 3.604,
+      "step": 500
+    },
+    {
+      "epoch": 0.46858849201791664,
+      "grad_norm": 4.017474174499512,
+      "learning_rate": 3.7043841852542884e-06,
+      "logits/chosen": 1.8042447566986084,
+      "logits/rejected": 1.4390740394592285,
+      "logps/chosen": -3.4311797618865967,
+      "logps/rejected": -6.114380359649658,
+      "loss": 0.335,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.1467695236206055,
+      "rewards/margins": 4.0248003005981445,
+      "rewards/rejected": -9.171568870544434,
+      "step": 510
+    },
+    {
+      "epoch": 0.47777650166532676,
+      "grad_norm": 5.516397953033447,
+      "learning_rate": 3.658240087799655e-06,
+      "logits/chosen": 1.1141811609268188,
+      "logits/rejected": 0.7766789197921753,
+      "logps/chosen": -3.1831612586975098,
+      "logps/rejected": -5.615653991699219,
+      "loss": 0.3306,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -4.774742603302002,
+      "rewards/margins": 3.6487393379211426,
+      "rewards/rejected": -8.423480987548828,
+      "step": 520
+    },
+    {
+      "epoch": 0.4869645113127369,
+      "grad_norm": 4.1005635261535645,
+      "learning_rate": 3.611587947962319e-06,
+      "logits/chosen": 1.5796890258789062,
+      "logits/rejected": 1.1561863422393799,
+      "logps/chosen": -3.286179304122925,
+      "logps/rejected": -5.805339813232422,
+      "loss": 0.3151,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.929268836975098,
+      "rewards/margins": 3.778740644454956,
+      "rewards/rejected": -8.708009719848633,
+      "step": 530
+    },
+    {
+      "epoch": 0.496152520960147,
+      "grad_norm": 2.8616511821746826,
+      "learning_rate": 3.564448228912682e-06,
+      "logits/chosen": 0.6956934928894043,
+      "logits/rejected": 0.1268310248851776,
+      "logps/chosen": -2.8933937549591064,
+      "logps/rejected": -5.794272422790527,
+      "loss": 0.2995,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.340090274810791,
+      "rewards/margins": 4.351318836212158,
+      "rewards/rejected": -8.691408157348633,
+      "step": 540
+    },
+    {
+      "epoch": 0.5053405306075571,
+      "grad_norm": 2.237276315689087,
+      "learning_rate": 3.516841607689501e-06,
+      "logits/chosen": 1.7460235357284546,
+      "logits/rejected": 0.9990445375442505,
+      "logps/chosen": -2.860546827316284,
+      "logps/rejected": -5.517810821533203,
+      "loss": 0.3203,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -4.290820121765137,
+      "rewards/margins": 3.985896348953247,
+      "rewards/rejected": -8.276716232299805,
+      "step": 550
+    },
+    {
+      "epoch": 0.5053405306075571,
+      "eval_logits/chosen": 0.8703196048736572,
+      "eval_logits/rejected": 0.3152187466621399,
+      "eval_logps/chosen": -2.709866523742676,
+      "eval_logps/rejected": -5.687611103057861,
+      "eval_loss": 0.304200142621994,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -4.064799785614014,
+      "eval_rewards/margins": 4.466617107391357,
+      "eval_rewards/rejected": -8.531416893005371,
+      "eval_runtime": 24.6083,
+      "eval_samples_per_second": 28.608,
+      "eval_steps_per_second": 3.576,
+      "step": 550
+    },
+    {
+      "epoch": 0.5145285402549673,
+      "grad_norm": 3.7983174324035645,
+      "learning_rate": 3.4687889661302577e-06,
+      "logits/chosen": 1.084142804145813,
+      "logits/rejected": 0.9131366610527039,
+      "logps/chosen": -3.4958484172821045,
+      "logps/rejected": -7.143038749694824,
+      "loss": 0.2728,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.243772506713867,
+      "rewards/margins": 5.470786094665527,
+      "rewards/rejected": -10.714558601379395,
+      "step": 560
+    },
+    {
+      "epoch": 0.5237165499023774,
+      "grad_norm": 2.398188829421997,
+      "learning_rate": 3.4203113817116955e-06,
+      "logits/chosen": 1.2777886390686035,
+      "logits/rejected": 0.6827106475830078,
+      "logps/chosen": -3.4014134407043457,
+      "logps/rejected": -6.260494232177734,
+      "loss": 0.2833,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.102120399475098,
+      "rewards/margins": 4.288620948791504,
+      "rewards/rejected": -9.390741348266602,
+      "step": 570
+    },
+    {
+      "epoch": 0.5329045595497875,
+      "grad_norm": 4.97003173828125,
+      "learning_rate": 3.3714301183045382e-06,
+      "logits/chosen": 1.6978384256362915,
+      "logits/rejected": 1.1092720031738281,
+      "logps/chosen": -3.179011106491089,
+      "logps/rejected": -6.802459716796875,
+      "loss": 0.2942,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.768516540527344,
+      "rewards/margins": 5.435172080993652,
+      "rewards/rejected": -10.203688621520996,
+      "step": 580
+    },
+    {
+      "epoch": 0.5420925691971976,
+      "grad_norm": 4.482264995574951,
+      "learning_rate": 3.3221666168464584e-06,
+      "logits/chosen": 1.0245933532714844,
+      "logits/rejected": 0.7797524929046631,
+      "logps/chosen": -3.2393958568573,
+      "logps/rejected": -5.916412353515625,
+      "loss": 0.3347,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.859094142913818,
+      "rewards/margins": 4.015524864196777,
+      "rewards/rejected": -8.874618530273438,
+      "step": 590
+    },
+    {
+      "epoch": 0.5512805788446078,
+      "grad_norm": 3.913116931915283,
+      "learning_rate": 3.272542485937369e-06,
+      "logits/chosen": 1.3320618867874146,
+      "logits/rejected": 0.9762558937072754,
+      "logps/chosen": -3.2751450538635254,
+      "logps/rejected": -6.7808518409729,
+      "loss": 0.2776,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -4.912716865539551,
+      "rewards/margins": 5.258560657501221,
+      "rewards/rejected": -10.17127799987793,
+      "step": 600
+    },
+    {
+      "epoch": 0.5512805788446078,
+      "eval_logits/chosen": 0.9448758959770203,
+      "eval_logits/rejected": 0.42817041277885437,
+      "eval_logps/chosen": -2.835143804550171,
+      "eval_logps/rejected": -6.087582588195801,
+      "eval_loss": 0.28658536076545715,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -4.252715587615967,
+      "eval_rewards/margins": 4.878659248352051,
+      "eval_rewards/rejected": -9.13137435913086,
+      "eval_runtime": 24.4325,
+      "eval_samples_per_second": 28.814,
+      "eval_steps_per_second": 3.602,
+      "step": 600
+    },
+    {
+      "epoch": 0.560468588492018,
+      "grad_norm": 3.8335089683532715,
+      "learning_rate": 3.222579492361179e-06,
+      "logits/chosen": 1.295569658279419,
+      "logits/rejected": 1.0852326154708862,
+      "logps/chosen": -3.4870052337646484,
+      "logps/rejected": -6.572986602783203,
+      "loss": 0.3243,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.230508327484131,
+      "rewards/margins": 4.628971576690674,
+      "rewards/rejected": -9.859478950500488,
+      "step": 610
+    },
+    {
+      "epoch": 0.569656598139428,
+      "grad_norm": 3.095102071762085,
+      "learning_rate": 3.1722995515381644e-06,
+      "logits/chosen": 1.8339803218841553,
+      "logits/rejected": 1.467551589012146,
+      "logps/chosen": -3.6670470237731934,
+      "logps/rejected": -6.880410194396973,
+      "loss": 0.2615,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -5.500569820404053,
+      "rewards/margins": 4.820044040679932,
+      "rewards/rejected": -10.3206148147583,
+      "step": 620
+    },
+    {
+      "epoch": 0.5788446077868382,
+      "grad_norm": 4.381973743438721,
+      "learning_rate": 3.121724717912138e-06,
+      "logits/chosen": 2.390763521194458,
+      "logits/rejected": 2.155505418777466,
+      "logps/chosen": -3.3569788932800293,
+      "logps/rejected": -6.319291114807129,
+      "loss": 0.2649,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -5.035468101501465,
+      "rewards/margins": 4.4434685707092285,
+      "rewards/rejected": -9.478937149047852,
+      "step": 630
+    },
+    {
+      "epoch": 0.5880326174342483,
+      "grad_norm": 3.9204964637756348,
+      "learning_rate": 3.0708771752766397e-06,
+      "logits/chosen": 1.4343383312225342,
+      "logits/rejected": 1.1991338729858398,
+      "logps/chosen": -3.654259443283081,
+      "logps/rejected": -6.873109340667725,
+      "loss": 0.2761,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.481389045715332,
+      "rewards/margins": 4.828273773193359,
+      "rewards/rejected": -10.309663772583008,
+      "step": 640
+    },
+    {
+      "epoch": 0.5972206270816585,
+      "grad_norm": 3.179067373275757,
+      "learning_rate": 3.019779227044398e-06,
+      "logits/chosen": 2.0368576049804688,
+      "logits/rejected": 1.8037185668945312,
+      "logps/chosen": -3.791682720184326,
+      "logps/rejected": -6.912911415100098,
+      "loss": 0.2739,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.68752384185791,
+      "rewards/margins": 4.68184232711792,
+      "rewards/rejected": -10.369367599487305,
+      "step": 650
+    },
+    {
+      "epoch": 0.5972206270816585,
+      "eval_logits/chosen": 1.0889618396759033,
+      "eval_logits/rejected": 0.5887767672538757,
+      "eval_logps/chosen": -3.0191192626953125,
+      "eval_logps/rejected": -6.388964653015137,
+      "eval_loss": 0.27443525195121765,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -4.528679370880127,
+      "eval_rewards/margins": 5.054768085479736,
+      "eval_rewards/rejected": -9.583446502685547,
+      "eval_runtime": 24.4235,
+      "eval_samples_per_second": 28.825,
+      "eval_steps_per_second": 3.603,
+      "step": 650
+    },
+    {
+      "epoch": 0.6064086367290685,
+      "grad_norm": 2.804940700531006,
+      "learning_rate": 2.9684532864643123e-06,
+      "logits/chosen": 1.8347485065460205,
+      "logits/rejected": 1.3636573553085327,
+      "logps/chosen": -3.398799419403076,
+      "logps/rejected": -6.337627410888672,
+      "loss": 0.2678,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.098199367523193,
+      "rewards/margins": 4.408241271972656,
+      "rewards/rejected": -9.506441116333008,
+      "step": 660
+    },
+    {
+      "epoch": 0.6155966463764787,
+      "grad_norm": 3.7368969917297363,
+      "learning_rate": 2.9169218667902562e-06,
+      "logits/chosen": 1.6734691858291626,
+      "logits/rejected": 1.0945308208465576,
+      "logps/chosen": -3.354790210723877,
+      "logps/rejected": -6.3691864013671875,
+      "loss": 0.294,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.0321855545043945,
+      "rewards/margins": 4.521594524383545,
+      "rewards/rejected": -9.553780555725098,
+      "step": 670
+    },
+    {
+      "epoch": 0.6247846560238888,
+      "grad_norm": 4.483130931854248,
+      "learning_rate": 2.8652075714060296e-06,
+      "logits/chosen": 1.640228509902954,
+      "logits/rejected": 1.1519067287445068,
+      "logps/chosen": -3.4700570106506348,
+      "logps/rejected": -6.6276445388793945,
+      "loss": 0.23,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.205085277557373,
+      "rewards/margins": 4.736380577087402,
+      "rewards/rejected": -9.941465377807617,
+      "step": 680
+    },
+    {
+      "epoch": 0.633972665671299,
+      "grad_norm": 8.508203506469727,
+      "learning_rate": 2.813333083910761e-06,
+      "logits/chosen": 1.0501906871795654,
+      "logits/rejected": 0.5691097974777222,
+      "logps/chosen": -3.4982333183288574,
+      "logps/rejected": -7.144225120544434,
+      "loss": 0.2808,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.247350215911865,
+      "rewards/margins": 5.468987464904785,
+      "rewards/rejected": -10.716337203979492,
+      "step": 690
+    },
+    {
+      "epoch": 0.6431606753187091,
+      "grad_norm": 2.271857738494873,
+      "learning_rate": 2.761321158169134e-06,
+      "logits/chosen": 1.2119544744491577,
+      "logits/rejected": 0.7247776389122009,
+      "logps/chosen": -4.096956253051758,
+      "logps/rejected": -7.4536261558532715,
+      "loss": 0.2808,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -6.145434379577637,
+      "rewards/margins": 5.035003662109375,
+      "rewards/rejected": -11.180438995361328,
+      "step": 700
+    },
+    {
+      "epoch": 0.6431606753187091,
+      "eval_logits/chosen": 1.085008978843689,
+      "eval_logits/rejected": 0.5991834998130798,
+      "eval_logps/chosen": -3.179896354675293,
+      "eval_logps/rejected": -6.738409519195557,
+      "eval_loss": 0.26070258021354675,
+      "eval_rewards/accuracies": 0.9090909361839294,
+      "eval_rewards/chosen": -4.7698445320129395,
+      "eval_rewards/margins": 5.337769031524658,
+      "eval_rewards/rejected": -10.107613563537598,
+      "eval_runtime": 24.465,
+      "eval_samples_per_second": 28.776,
+      "eval_steps_per_second": 3.597,
+      "step": 700
+    },
+    {
+      "epoch": 0.6523486849661192,
+      "grad_norm": 4.058814525604248,
+      "learning_rate": 2.70919460833079e-06,
+      "logits/chosen": 1.2182409763336182,
+      "logits/rejected": 1.0481547117233276,
+      "logps/chosen": -3.532151699066162,
+      "logps/rejected": -7.4123854637146,
+      "loss": 0.2565,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.2982282638549805,
+      "rewards/margins": 5.8203511238098145,
+      "rewards/rejected": -11.118578910827637,
+      "step": 710
+    },
+    {
+      "epoch": 0.6615366946135294,
+      "grad_norm": 3.857574939727783,
+      "learning_rate": 2.6569762988232838e-06,
+      "logits/chosen": 0.8797380328178406,
+      "logits/rejected": 0.6432709693908691,
+      "logps/chosen": -3.3780128955841064,
+      "logps/rejected": -6.922214508056641,
+      "loss": 0.2321,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.067019462585449,
+      "rewards/margins": 5.3163018226623535,
+      "rewards/rejected": -10.383320808410645,
+      "step": 720
+    },
+    {
+      "epoch": 0.6707247042609394,
+      "grad_norm": 3.7125725746154785,
+      "learning_rate": 2.604689134322999e-06,
+      "logits/chosen": 1.447474479675293,
+      "logits/rejected": 1.1114810705184937,
+      "logps/chosen": -3.682945728302002,
+      "logps/rejected": -7.297152519226074,
+      "loss": 0.2812,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.524418830871582,
+      "rewards/margins": 5.421310901641846,
+      "rewards/rejected": -10.94572925567627,
+      "step": 730
+    },
+    {
+      "epoch": 0.6799127139083496,
+      "grad_norm": 2.026604652404785,
+      "learning_rate": 2.5523560497083927e-06,
+      "logits/chosen": 1.9674856662750244,
+      "logits/rejected": 1.593400239944458,
+      "logps/chosen": -3.3987834453582764,
+      "logps/rejected": -6.970278263092041,
+      "loss": 0.2603,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.098175048828125,
+      "rewards/margins": 5.357242107391357,
+      "rewards/rejected": -10.45541763305664,
+      "step": 740
+    },
+    {
+      "epoch": 0.6891007235557597,
+      "grad_norm": 2.357570171356201,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.9729163646697998,
+      "logits/rejected": 1.8791675567626953,
+      "logps/chosen": -3.3879425525665283,
+      "logps/rejected": -6.712514400482178,
+      "loss": 0.2348,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -5.081913948059082,
+      "rewards/margins": 4.986858367919922,
+      "rewards/rejected": -10.068772315979004,
+      "step": 750
+    },
+    {
+      "epoch": 0.6891007235557597,
+      "eval_logits/chosen": 1.1882920265197754,
+      "eval_logits/rejected": 0.7092404961585999,
+      "eval_logps/chosen": -2.855703592300415,
+      "eval_logps/rejected": -6.557665824890137,
+      "eval_loss": 0.25226154923439026,
+      "eval_rewards/accuracies": 0.9090909361839294,
+      "eval_rewards/chosen": -4.283555507659912,
+      "eval_rewards/margins": 5.552942276000977,
+      "eval_rewards/rejected": -9.836498260498047,
+      "eval_runtime": 24.4236,
+      "eval_samples_per_second": 28.825,
+      "eval_steps_per_second": 3.603,
+      "step": 750
+    },
+    {
+      "epoch": 0.6982887332031699,
+      "grad_norm": 3.1369588375091553,
+      "learning_rate": 2.447643950291608e-06,
+      "logits/chosen": 1.908418893814087,
+      "logits/rejected": 1.637202262878418,
+      "logps/chosen": -3.941102981567383,
+      "logps/rejected": -7.562623023986816,
+      "loss": 0.2412,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.911653995513916,
+      "rewards/margins": 5.432280540466309,
+      "rewards/rejected": -11.343935012817383,
+      "step": 760
+    },
+    {
+      "epoch": 0.70747674285058,
+      "grad_norm": 4.2312703132629395,
+      "learning_rate": 2.3953108656770018e-06,
+      "logits/chosen": 1.3125172853469849,
+      "logits/rejected": 0.933386504650116,
+      "logps/chosen": -3.5281143188476562,
+      "logps/rejected": -7.116488456726074,
+      "loss": 0.2528,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.292171001434326,
+      "rewards/margins": 5.382561683654785,
+      "rewards/rejected": -10.674734115600586,
+      "step": 770
+    },
+    {
+      "epoch": 0.7166647524979901,
+      "grad_norm": 5.6951799392700195,
+      "learning_rate": 2.3430237011767166e-06,
+      "logits/chosen": 2.295801877975464,
+      "logits/rejected": 1.8810745477676392,
+      "logps/chosen": -3.3887531757354736,
+      "logps/rejected": -6.8857245445251465,
+      "loss": 0.2672,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.083128929138184,
+      "rewards/margins": 5.245457649230957,
+      "rewards/rejected": -10.32858657836914,
+      "step": 780
+    },
+    {
+      "epoch": 0.7258527621454003,
+      "grad_norm": 3.734528064727783,
+      "learning_rate": 2.290805391669212e-06,
+      "logits/chosen": 1.6154979467391968,
+      "logits/rejected": 1.1886816024780273,
+      "logps/chosen": -3.379617214202881,
+      "logps/rejected": -7.1727166175842285,
+      "loss": 0.2315,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.069426536560059,
+      "rewards/margins": 5.689648628234863,
+      "rewards/rejected": -10.759074211120605,
+      "step": 790
+    },
+    {
+      "epoch": 0.7350407717928104,
+      "grad_norm": 3.2450063228607178,
+      "learning_rate": 2.238678841830867e-06,
+      "logits/chosen": 1.9270827770233154,
+      "logits/rejected": 1.5745903253555298,
+      "logps/chosen": -3.9242210388183594,
+      "logps/rejected": -7.254105567932129,
+      "loss": 0.2301,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.886331081390381,
+      "rewards/margins": 4.9948272705078125,
+      "rewards/rejected": -10.881157875061035,
+      "step": 800
+    },
+    {
+      "epoch": 0.7350407717928104,
+      "eval_logits/chosen": 1.228877067565918,
+      "eval_logits/rejected": 0.7780414819717407,
+      "eval_logps/chosen": -3.096149444580078,
+      "eval_logps/rejected": -6.9255452156066895,
+      "eval_loss": 0.23762211203575134,
+      "eval_rewards/accuracies": 0.9090909361839294,
+      "eval_rewards/chosen": -4.644224166870117,
+      "eval_rewards/margins": 5.744093894958496,
+      "eval_rewards/rejected": -10.388318061828613,
+      "eval_runtime": 24.4202,
+      "eval_samples_per_second": 28.829,
+      "eval_steps_per_second": 3.604,
+      "step": 800
+    },
+    {
+      "epoch": 0.7442287814402205,
+      "grad_norm": 3.6619718074798584,
+      "learning_rate": 2.186666916089239e-06,
+      "logits/chosen": 2.1697134971618652,
+      "logits/rejected": 1.8535985946655273,
+      "logps/chosen": -3.306549549102783,
+      "logps/rejected": -6.570471286773682,
+      "loss": 0.2239,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -4.959824562072754,
+      "rewards/margins": 4.895882606506348,
+      "rewards/rejected": -9.855707168579102,
+      "step": 810
+    },
+    {
+      "epoch": 0.7534167910876306,
+      "grad_norm": 3.9014956951141357,
+      "learning_rate": 2.134792428593971e-06,
+      "logits/chosen": 1.8228479623794556,
+      "logits/rejected": 1.5440882444381714,
+      "logps/chosen": -3.545902967453003,
+      "logps/rejected": -7.393707275390625,
+      "loss": 0.2429,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.318853855133057,
+      "rewards/margins": 5.7717061042785645,
+      "rewards/rejected": -11.090560913085938,
+      "step": 820
+    },
+    {
+      "epoch": 0.7626048007350408,
+      "grad_norm": 4.266237735748291,
+      "learning_rate": 2.0830781332097446e-06,
+      "logits/chosen": 1.6186097860336304,
+      "logits/rejected": 1.4948759078979492,
+      "logps/chosen": -3.6410841941833496,
+      "logps/rejected": -7.069480895996094,
+      "loss": 0.2213,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.461626052856445,
+      "rewards/margins": 5.142596244812012,
+      "rewards/rejected": -10.604223251342773,
+      "step": 830
+    },
+    {
+      "epoch": 0.771792810382451,
+      "grad_norm": 2.3189163208007812,
+      "learning_rate": 2.031546713535688e-06,
+      "logits/chosen": 2.4443275928497314,
+      "logits/rejected": 2.1987624168395996,
+      "logps/chosen": -4.127468585968018,
+      "logps/rejected": -8.15340805053711,
+      "loss": 0.2525,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -6.191202640533447,
+      "rewards/margins": 6.038909435272217,
+      "rewards/rejected": -12.230112075805664,
+      "step": 840
+    },
+    {
+      "epoch": 0.780980820029861,
+      "grad_norm": 5.227460861206055,
+      "learning_rate": 1.9802207729556023e-06,
+      "logits/chosen": 2.0057969093322754,
+      "logits/rejected": 1.7481991052627563,
+      "logps/chosen": -3.890474796295166,
+      "logps/rejected": -7.659049034118652,
+      "loss": 0.2253,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.83571195602417,
+      "rewards/margins": 5.65286111831665,
+      "rewards/rejected": -11.48857307434082,
+      "step": 850
+    },
+    {
+      "epoch": 0.780980820029861,
+      "eval_logits/chosen": 1.2305774688720703,
+      "eval_logits/rejected": 0.8189592957496643,
+      "eval_logps/chosen": -3.205787420272827,
+      "eval_logps/rejected": -7.230924606323242,
+      "eval_loss": 0.23406219482421875,
+      "eval_rewards/accuracies": 0.9090909361839294,
+      "eval_rewards/chosen": -4.808681488037109,
+      "eval_rewards/margins": 6.0377044677734375,
+      "eval_rewards/rejected": -10.846386909484863,
+      "eval_runtime": 24.5257,
+      "eval_samples_per_second": 28.705,
+      "eval_steps_per_second": 3.588,
+      "step": 850
+    },
+    {
+      "epoch": 0.7901688296772712,
+      "grad_norm": 5.743741512298584,
+      "learning_rate": 1.9291228247233607e-06,
+      "logits/chosen": 2.0627987384796143,
+      "logits/rejected": 1.964015245437622,
+      "logps/chosen": -3.810974597930908,
+      "logps/rejected": -7.854369163513184,
+      "loss": 0.254,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.716461658477783,
+      "rewards/margins": 6.065093040466309,
+      "rewards/rejected": -11.78155517578125,
+      "step": 860
+    },
+    {
+      "epoch": 0.7993568393246813,
+      "grad_norm": 3.256955623626709,
+      "learning_rate": 1.8782752820878636e-06,
+      "logits/chosen": 1.892846703529358,
+      "logits/rejected": 1.5955915451049805,
+      "logps/chosen": -4.009222507476807,
+      "logps/rejected": -7.55028772354126,
+      "loss": 0.2325,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.013833045959473,
+      "rewards/margins": 5.3115973472595215,
+      "rewards/rejected": -11.325429916381836,
+      "step": 870
+    },
+    {
+      "epoch": 0.8085448489720914,
+      "grad_norm": 3.6304337978363037,
+      "learning_rate": 1.827700448461836e-06,
+      "logits/chosen": 2.3684587478637695,
+      "logits/rejected": 2.1417429447174072,
+      "logps/chosen": -3.8222625255584717,
+      "logps/rejected": -7.484266757965088,
+      "loss": 0.2427,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -5.73339319229126,
+      "rewards/margins": 5.493006229400635,
+      "rewards/rejected": -11.226400375366211,
+      "step": 880
+    },
+    {
+      "epoch": 0.8177328586195015,
+      "grad_norm": 4.88602352142334,
+      "learning_rate": 1.7774205076388207e-06,
+      "logits/chosen": 1.8633663654327393,
+      "logits/rejected": 1.6100108623504639,
+      "logps/chosen": -3.4299614429473877,
+      "logps/rejected": -7.589132785797119,
+      "loss": 0.1988,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.144942283630371,
+      "rewards/margins": 6.238757133483887,
+      "rewards/rejected": -11.383699417114258,
+      "step": 890
+    },
+    {
+      "epoch": 0.8269208682669117,
+      "grad_norm": 3.657270669937134,
+      "learning_rate": 1.7274575140626318e-06,
+      "logits/chosen": 1.5545165538787842,
+      "logits/rejected": 1.600629448890686,
+      "logps/chosen": -3.981847047805786,
+      "logps/rejected": -8.365175247192383,
+      "loss": 0.2055,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.972771167755127,
+      "rewards/margins": 6.5749921798706055,
+      "rewards/rejected": -12.54776382446289,
+      "step": 900
+    },
+    {
+      "epoch": 0.8269208682669117,
+      "eval_logits/chosen": 1.3828459978103638,
+      "eval_logits/rejected": 0.9709804058074951,
+      "eval_logps/chosen": -3.4689862728118896,
+      "eval_logps/rejected": -7.613832473754883,
+      "eval_loss": 0.2267654538154602,
+      "eval_rewards/accuracies": 0.9090909361839294,
+      "eval_rewards/chosen": -5.203479290008545,
+      "eval_rewards/margins": 6.217269420623779,
+      "eval_rewards/rejected": -11.420748710632324,
+      "eval_runtime": 24.422,
+      "eval_samples_per_second": 28.826,
+      "eval_steps_per_second": 3.603,
+      "step": 900
+    },
+    {
+      "epoch": 0.8361088779143218,
+      "grad_norm": 7.899631500244141,
+      "learning_rate": 1.677833383153542e-06,
+      "logits/chosen": 1.8724586963653564,
+      "logits/rejected": 1.4860353469848633,
+      "logps/chosen": -3.703522205352783,
+      "logps/rejected": -7.718357086181641,
+      "loss": 0.2762,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -5.5552825927734375,
+      "rewards/margins": 6.02225399017334,
+      "rewards/rejected": -11.577536582946777,
+      "step": 910
+    },
+    {
+      "epoch": 0.8452968875617319,
+      "grad_norm": 3.687998056411743,
+      "learning_rate": 1.6285698816954626e-06,
+      "logits/chosen": 3.0009334087371826,
+      "logits/rejected": 2.3279061317443848,
+      "logps/chosen": -4.25749397277832,
+      "logps/rejected": -7.3263139724731445,
+      "loss": 0.2202,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -6.3862409591674805,
+      "rewards/margins": 4.603229522705078,
+      "rewards/rejected": -10.989469528198242,
+      "step": 920
+    },
+    {
+      "epoch": 0.8544848972091421,
+      "grad_norm": 3.9033992290496826,
+      "learning_rate": 1.5796886182883053e-06,
+      "logits/chosen": 2.3675689697265625,
+      "logits/rejected": 2.2341208457946777,
+      "logps/chosen": -4.182201385498047,
+      "logps/rejected": -7.975285530090332,
+      "loss": 0.1945,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.27330207824707,
+      "rewards/margins": 5.6896257400512695,
+      "rewards/rejected": -11.962926864624023,
+      "step": 930
+    },
+    {
+      "epoch": 0.8636729068565522,
+      "grad_norm": 7.484313488006592,
+      "learning_rate": 1.5312110338697427e-06,
+      "logits/chosen": 1.737408995628357,
+      "logits/rejected": 1.6608823537826538,
+      "logps/chosen": -4.052768707275391,
+      "logps/rejected": -7.796560764312744,
+      "loss": 0.2282,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.079153537750244,
+      "rewards/margins": 5.615686893463135,
+      "rewards/rejected": -11.694841384887695,
+      "step": 940
+    },
+    {
+      "epoch": 0.8728609165039624,
+      "grad_norm": 5.176153182983398,
+      "learning_rate": 1.4831583923105e-06,
+      "logits/chosen": 1.5573890209197998,
+      "logits/rejected": 1.1255266666412354,
+      "logps/chosen": -3.52099609375,
+      "logps/rejected": -7.2554473876953125,
+      "loss": 0.2434,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.281493663787842,
+      "rewards/margins": 5.601677417755127,
+      "rewards/rejected": -10.883171081542969,
+      "step": 950
+    },
+    {
+      "epoch": 0.8728609165039624,
+      "eval_logits/chosen": 1.3714543581008911,
+      "eval_logits/rejected": 0.9610424041748047,
+      "eval_logps/chosen": -3.4983131885528564,
+      "eval_logps/rejected": -7.699583053588867,
+      "eval_loss": 0.22121396660804749,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -5.247470378875732,
+      "eval_rewards/margins": 6.301905632019043,
+      "eval_rewards/rejected": -11.549375534057617,
+      "eval_runtime": 24.4334,
+      "eval_samples_per_second": 28.813,
+      "eval_steps_per_second": 3.602,
+      "step": 950
+    },
+    {
+      "epoch": 0.8820489261513724,
+      "grad_norm": 3.092210292816162,
+      "learning_rate": 1.4355517710873184e-06,
+      "logits/chosen": 1.5538525581359863,
+      "logits/rejected": 1.2886962890625,
+      "logps/chosen": -3.7919907569885254,
+      "logps/rejected": -7.742431640625,
+      "loss": 0.2628,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -5.687986373901367,
+      "rewards/margins": 5.925662040710449,
+      "rewards/rejected": -11.613648414611816,
+      "step": 960
+    },
+    {
+      "epoch": 0.8912369357987826,
+      "grad_norm": 2.258793830871582,
+      "learning_rate": 1.388412052037682e-06,
+      "logits/chosen": 1.9938386678695679,
+      "logits/rejected": 1.7578411102294922,
+      "logps/chosen": -3.902163028717041,
+      "logps/rejected": -8.263092041015625,
+      "loss": 0.1893,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.853244781494141,
+      "rewards/margins": 6.541393280029297,
+      "rewards/rejected": -12.394639015197754,
+      "step": 970
+    },
+    {
+      "epoch": 0.9004249454461927,
+      "grad_norm": 3.3003509044647217,
+      "learning_rate": 1.3417599122003464e-06,
+      "logits/chosen": 1.858659029006958,
+      "logits/rejected": 1.7009245157241821,
+      "logps/chosen": -3.995110034942627,
+      "logps/rejected": -7.946316719055176,
+      "loss": 0.2001,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.9926652908325195,
+      "rewards/margins": 5.926809310913086,
+      "rewards/rejected": -11.919473648071289,
+      "step": 980
+    },
+    {
+      "epoch": 0.9096129550936028,
+      "grad_norm": 5.714742183685303,
+      "learning_rate": 1.2956158147457116e-06,
+      "logits/chosen": 2.311112642288208,
+      "logits/rejected": 1.819894790649414,
+      "logps/chosen": -4.011856555938721,
+      "logps/rejected": -8.002031326293945,
+      "loss": 0.216,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -6.01778507232666,
+      "rewards/margins": 5.985262870788574,
+      "rewards/rejected": -12.003047943115234,
+      "step": 990
+    },
+    {
+      "epoch": 0.918800964741013,
+      "grad_norm": 2.5513203144073486,
+      "learning_rate": 1.2500000000000007e-06,
+      "logits/chosen": 2.042844295501709,
+      "logits/rejected": 1.7135541439056396,
+      "logps/chosen": -4.096378803253174,
+      "logps/rejected": -8.864072799682617,
+      "loss": 0.1812,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.144567489624023,
+      "rewards/margins": 7.151541709899902,
+      "rewards/rejected": -13.296109199523926,
+      "step": 1000
+    },
+    {
+      "epoch": 0.918800964741013,
+      "eval_logits/chosen": 1.4344538450241089,
+      "eval_logits/rejected": 1.0740816593170166,
+      "eval_logps/chosen": -3.56337833404541,
+      "eval_logps/rejected": -7.854743957519531,
+      "eval_loss": 0.21498693525791168,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -5.345067977905273,
+      "eval_rewards/margins": 6.437047004699707,
+      "eval_rewards/rejected": -11.782115936279297,
+      "eval_runtime": 24.4225,
+      "eval_samples_per_second": 28.826,
+      "eval_steps_per_second": 3.603,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9279889743884231,
+      "grad_norm": 3.213252067565918,
+      "learning_rate": 1.204932476567175e-06,
+      "logits/chosen": 2.064485788345337,
+      "logits/rejected": 1.9654451608657837,
+      "logps/chosen": -3.7592079639434814,
+      "logps/rejected": -8.004045486450195,
+      "loss": 0.2113,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.638812065124512,
+      "rewards/margins": 6.367256164550781,
+      "rewards/rejected": -12.00606918334961,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9371769840358333,
+      "grad_norm": 3.000185012817383,
+      "learning_rate": 1.160433012552508e-06,
+      "logits/chosen": 1.9040180444717407,
+      "logits/rejected": 1.8388664722442627,
+      "logps/chosen": -4.3835272789001465,
+      "logps/rejected": -8.310102462768555,
+      "loss": 0.2414,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.575291633605957,
+      "rewards/margins": 5.889863014221191,
+      "rewards/rejected": -12.465154647827148,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9463649936832433,
+      "grad_norm": 2.7824106216430664,
+      "learning_rate": 1.11652112689164e-06,
+      "logits/chosen": 1.4278347492218018,
+      "logits/rejected": 1.4083877801895142,
+      "logps/chosen": -3.6480088233947754,
+      "logps/rejected": -8.00098705291748,
+      "loss": 0.1763,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.472012519836426,
+      "rewards/margins": 6.5294671058654785,
+      "rewards/rejected": -12.001480102539062,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9555530033306535,
+      "grad_norm": 5.236849784851074,
+      "learning_rate": 1.073216080788921e-06,
+      "logits/chosen": 2.1868062019348145,
+      "logits/rejected": 1.9401241540908813,
+      "logps/chosen": -4.442656993865967,
+      "logps/rejected": -8.857598304748535,
+      "loss": 0.2158,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.663985252380371,
+      "rewards/margins": 6.622411251068115,
+      "rewards/rejected": -13.286396980285645,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9647410129780636,
+      "grad_norm": 3.4044084548950195,
+      "learning_rate": 1.0305368692688175e-06,
+      "logits/chosen": 1.5827648639678955,
+      "logits/rejected": 1.7356208562850952,
+      "logps/chosen": -3.988180637359619,
+      "logps/rejected": -8.252123832702637,
+      "loss": 0.1967,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.982270240783691,
+      "rewards/margins": 6.3959150314331055,
+      "rewards/rejected": -12.378186225891113,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9647410129780636,
+      "eval_logits/chosen": 1.4267497062683105,
+      "eval_logits/rejected": 1.0997689962387085,
+      "eval_logps/chosen": -3.4779577255249023,
+      "eval_logps/rejected": -7.853654384613037,
+      "eval_loss": 0.20923514664173126,
+      "eval_rewards/accuracies": 0.9318181872367859,
+      "eval_rewards/chosen": -5.216937065124512,
+      "eval_rewards/margins": 6.563545227050781,
+      "eval_rewards/rejected": -11.780481338500977,
+      "eval_runtime": 24.446,
+      "eval_samples_per_second": 28.798,
+      "eval_steps_per_second": 3.6,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9739290226254738,
+      "grad_norm": 7.323760032653809,
+      "learning_rate": 9.88502212844063e-07,
+      "logits/chosen": 1.8404476642608643,
+      "logits/rejected": 1.5995383262634277,
+      "logps/chosen": -3.8108818531036377,
+      "logps/rejected": -8.686467170715332,
+      "loss": 0.2182,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.716322898864746,
+      "rewards/margins": 7.313376426696777,
+      "rewards/rejected": -13.029699325561523,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9831170322728839,
+      "grad_norm": 2.989016056060791,
+      "learning_rate": 9.471305493042243e-07,
+      "logits/chosen": 2.1675870418548584,
+      "logits/rejected": 2.089310646057129,
+      "logps/chosen": -3.7525386810302734,
+      "logps/rejected": -8.541536331176758,
+      "loss": 0.2056,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.628808498382568,
+      "rewards/margins": 7.183494567871094,
+      "rewards/rejected": -12.81230354309082,
+      "step": 1070
+    },
+    {
+      "epoch": 0.992305041920294,
+      "grad_norm": 5.650535583496094,
+      "learning_rate": 9.064400256282757e-07,
+      "logits/chosen": 2.612128496170044,
+      "logits/rejected": 2.198878765106201,
+      "logps/chosen": -4.110289096832275,
+      "logps/rejected": -8.18535327911377,
+      "loss": 0.1974,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.165433406829834,
+      "rewards/margins": 6.11259651184082,
+      "rewards/rejected": -12.278030395507812,
+      "step": 1080
+    },
+    {
+      "epoch": 1.000918800964741,
+      "grad_norm": 3.090592861175537,
+      "learning_rate": 8.664484900247363e-07,
+      "logits/chosen": 2.4326796531677246,
+      "logits/rejected": 2.0719056129455566,
+      "logps/chosen": -4.295161247253418,
+      "logps/rejected": -8.057024955749512,
+      "loss": 0.1982,
+      "rewards/accuracies": 0.9333333373069763,
+      "rewards/chosen": -6.442741394042969,
+      "rewards/margins": 5.642796039581299,
+      "rewards/rejected": -12.085537910461426,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0101068106121511,
+      "grad_norm": 3.5762991905212402,
+      "learning_rate": 8.271734841028553e-07,
+      "logits/chosen": 1.808143973350525,
+      "logits/rejected": 1.3669540882110596,
+      "logps/chosen": -4.025475978851318,
+      "logps/rejected": -8.578283309936523,
+      "loss": 0.2476,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -6.038214683532715,
+      "rewards/margins": 6.829211235046387,
+      "rewards/rejected": -12.867425918579102,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0101068106121511,
+      "eval_logits/chosen": 1.437761902809143,
+      "eval_logits/rejected": 1.1129838228225708,
+      "eval_logps/chosen": -3.463768720626831,
+      "eval_logps/rejected": -7.876412868499756,
+      "eval_loss": 0.2056656777858734,
+      "eval_rewards/accuracies": 0.9318181872367859,
+      "eval_rewards/chosen": -5.195653915405273,
+      "eval_rewards/margins": 6.6189656257629395,
+      "eval_rewards/rejected": -11.814618110656738,
+      "eval_runtime": 24.4283,
+      "eval_samples_per_second": 28.819,
+      "eval_steps_per_second": 3.602,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0192948202595613,
+      "grad_norm": 3.994568109512329,
+      "learning_rate": 7.886322351782782e-07,
+      "logits/chosen": 2.0599985122680664,
+      "logits/rejected": 1.7133548259735107,
+      "logps/chosen": -4.200375080108643,
+      "logps/rejected": -8.241968154907227,
+      "loss": 0.1984,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -6.300562381744385,
+      "rewards/margins": 6.062388896942139,
+      "rewards/rejected": -12.36295223236084,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0284828299069715,
+      "grad_norm": 4.166400909423828,
+      "learning_rate": 7.508416487165862e-07,
+      "logits/chosen": 1.7248255014419556,
+      "logits/rejected": 1.351927399635315,
+      "logps/chosen": -3.682168960571289,
+      "logps/rejected": -8.27522087097168,
+      "loss": 0.186,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.523253440856934,
+      "rewards/margins": 6.889578342437744,
+      "rewards/rejected": -12.412832260131836,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0376708395543814,
+      "grad_norm": 4.695723533630371,
+      "learning_rate": 7.138183009179922e-07,
+      "logits/chosen": 2.1033718585968018,
+      "logits/rejected": 1.9854538440704346,
+      "logps/chosen": -4.065175533294678,
+      "logps/rejected": -8.255699157714844,
+      "loss": 0.1932,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.097762584686279,
+      "rewards/margins": 6.285785675048828,
+      "rewards/rejected": -12.38354778289795,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0468588492017916,
+      "grad_norm": 4.183388710021973,
+      "learning_rate": 6.775784314464717e-07,
+      "logits/chosen": 2.612067699432373,
+      "logits/rejected": 2.1869616508483887,
+      "logps/chosen": -3.6629364490509033,
+      "logps/rejected": -8.047903060913086,
+      "loss": 0.2186,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.494403839111328,
+      "rewards/margins": 6.577451229095459,
+      "rewards/rejected": -12.071855545043945,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0560468588492018,
+      "grad_norm": 5.9020514488220215,
+      "learning_rate": 6.421379363065142e-07,
+      "logits/chosen": 1.2938798666000366,
+      "logits/rejected": 1.1452168226242065,
+      "logps/chosen": -4.144273281097412,
+      "logps/rejected": -8.718961715698242,
+      "loss": 0.2127,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.216409206390381,
+      "rewards/margins": 6.862032890319824,
+      "rewards/rejected": -13.078442573547363,
+      "step": 1150
+    },
+    {
+      "epoch": 1.0560468588492018,
+      "eval_logits/chosen": 1.4493238925933838,
+      "eval_logits/rejected": 1.128269076347351,
+      "eval_logps/chosen": -3.538313150405884,
+      "eval_logps/rejected": -7.989621162414551,
+      "eval_loss": 0.20314906537532806,
+      "eval_rewards/accuracies": 0.9318181872367859,
+      "eval_rewards/chosen": -5.307469367980957,
+      "eval_rewards/margins": 6.676960468292236,
+      "eval_rewards/rejected": -11.984430313110352,
+      "eval_runtime": 24.6248,
+      "eval_samples_per_second": 28.589,
+      "eval_steps_per_second": 3.574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.065234868496612,
+      "grad_norm": 3.6220788955688477,
+      "learning_rate": 6.075123608706093e-07,
+      "logits/chosen": 1.9196579456329346,
+      "logits/rejected": 1.8552544116973877,
+      "logps/chosen": -3.56549334526062,
+      "logps/rejected": -8.362249374389648,
+      "loss": 0.2277,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.348240852355957,
+      "rewards/margins": 7.195133209228516,
+      "rewards/rejected": -12.543375015258789,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0744228781440222,
+      "grad_norm": 3.9738340377807617,
+      "learning_rate": 5.737168930605272e-07,
+      "logits/chosen": 2.693675994873047,
+      "logits/rejected": 2.596327543258667,
+      "logps/chosen": -3.953673839569092,
+      "logps/rejected": -8.083026885986328,
+      "loss": 0.2156,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.930511474609375,
+      "rewards/margins": 6.194031238555908,
+      "rewards/rejected": -12.124540328979492,
+      "step": 1170
+    },
+    {
+      "epoch": 1.083610887791432,
+      "grad_norm": 3.9082953929901123,
+      "learning_rate": 5.407663566854008e-07,
+      "logits/chosen": 2.457482099533081,
+      "logits/rejected": 2.206406354904175,
+      "logps/chosen": -4.224593162536621,
+      "logps/rejected": -8.104263305664062,
+      "loss": 0.1883,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.336889266967773,
+      "rewards/margins": 5.8195061683654785,
+      "rewards/rejected": -12.15639591217041,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0927988974388423,
+      "grad_norm": 2.5964362621307373,
+      "learning_rate": 5.086752049395094e-07,
+      "logits/chosen": 1.9967896938323975,
+      "logits/rejected": 1.618037462234497,
+      "logps/chosen": -3.5683434009552,
+      "logps/rejected": -7.307412624359131,
+      "loss": 0.1798,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.352514743804932,
+      "rewards/margins": 5.608603477478027,
+      "rewards/rejected": -10.961118698120117,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1019869070862525,
+      "grad_norm": 2.499810218811035,
+      "learning_rate": 4.774575140626317e-07,
+      "logits/chosen": 1.7958850860595703,
+      "logits/rejected": 1.480818748474121,
+      "logps/chosen": -3.8547580242156982,
+      "logps/rejected": -8.144584655761719,
+      "loss": 0.2005,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.7821364402771,
+      "rewards/margins": 6.4347405433654785,
+      "rewards/rejected": -12.216877937316895,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1019869070862525,
+      "eval_logits/chosen": 1.4727997779846191,
+      "eval_logits/rejected": 1.1707344055175781,
+      "eval_logps/chosen": -3.532540798187256,
+      "eval_logps/rejected": -8.002986907958984,
+      "eval_loss": 0.2008148729801178,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -5.298811435699463,
+      "eval_rewards/margins": 6.705668926239014,
+      "eval_rewards/rejected": -12.004480361938477,
+      "eval_runtime": 24.695,
+      "eval_samples_per_second": 28.508,
+      "eval_steps_per_second": 3.563,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1111749167336626,
+      "grad_norm": 3.8940417766571045,
+      "learning_rate": 4.4712697716573994e-07,
+      "logits/chosen": 2.203734874725342,
+      "logits/rejected": 2.0729122161865234,
+      "logps/chosen": -4.096261501312256,
+      "logps/rejected": -7.813987731933594,
+      "loss": 0.1796,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.144392490386963,
+      "rewards/margins": 5.5765886306762695,
+      "rewards/rejected": -11.720980644226074,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1203629263810726,
+      "grad_norm": 4.197968006134033,
+      "learning_rate": 4.1769689822475147e-07,
+      "logits/chosen": 1.5070486068725586,
+      "logits/rejected": 1.5961544513702393,
+      "logps/chosen": -3.433948040008545,
+      "logps/rejected": -8.33233642578125,
+      "loss": 0.1742,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.1509222984313965,
+      "rewards/margins": 7.3475823402404785,
+      "rewards/rejected": -12.498504638671875,
+      "step": 1220
+    },
+    {
+      "epoch": 1.1295509360284828,
+      "grad_norm": 3.927893877029419,
+      "learning_rate": 3.891801862449629e-07,
+      "logits/chosen": 2.136690616607666,
+      "logits/rejected": 2.030285120010376,
+      "logps/chosen": -4.768858909606934,
+      "logps/rejected": -8.714016914367676,
+      "loss": 0.1811,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -7.153287410736084,
+      "rewards/margins": 5.917738914489746,
+      "rewards/rejected": -13.071026802062988,
+      "step": 1230
+    },
+    {
+      "epoch": 1.138738945675893,
+      "grad_norm": 3.148071765899658,
+      "learning_rate": 3.615893495987335e-07,
+      "logits/chosen": 2.084843873977661,
+      "logits/rejected": 2.249072551727295,
+      "logps/chosen": -4.252139091491699,
+      "logps/rejected": -8.39255428314209,
+      "loss": 0.1942,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.378207683563232,
+      "rewards/margins": 6.210625648498535,
+      "rewards/rejected": -12.588833808898926,
+      "step": 1240
+    },
+    {
+      "epoch": 1.1479269553233031,
+      "grad_norm": 1.6102039813995361,
+      "learning_rate": 3.3493649053890325e-07,
+      "logits/chosen": 2.5606529712677,
+      "logits/rejected": 2.4942524433135986,
+      "logps/chosen": -4.308623313903809,
+      "logps/rejected": -8.170819282531738,
+      "loss": 0.2088,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -6.4629340171813965,
+      "rewards/margins": 5.793294429779053,
+      "rewards/rejected": -12.256229400634766,
+      "step": 1250
+    },
+    {
+      "epoch": 1.1479269553233031,
+      "eval_logits/chosen": 1.4887795448303223,
+      "eval_logits/rejected": 1.181876540184021,
+      "eval_logps/chosen": -3.5690500736236572,
+      "eval_logps/rejected": -8.063680648803711,
+      "eval_loss": 0.20090900361537933,
+      "eval_rewards/accuracies": 0.9318181872367859,
+      "eval_rewards/chosen": -5.353575229644775,
+      "eval_rewards/margins": 6.741945266723633,
+      "eval_rewards/rejected": -12.09552001953125,
+      "eval_runtime": 24.433,
+      "eval_samples_per_second": 28.813,
+      "eval_steps_per_second": 3.602,
+      "step": 1250
+    },
+    {
+      "epoch": 1.1571149649707133,
+      "grad_norm": 5.161710262298584,
+      "learning_rate": 3.092332998903416e-07,
+      "logits/chosen": 1.6824312210083008,
+      "logits/rejected": 1.8732401132583618,
+      "logps/chosen": -4.1795806884765625,
+      "logps/rejected": -8.756204605102539,
+      "loss": 0.1833,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.269371032714844,
+      "rewards/margins": 6.864935874938965,
+      "rewards/rejected": -13.134305953979492,
+      "step": 1260
+    },
+    {
+      "epoch": 1.1663029746181233,
+      "grad_norm": 11.763586044311523,
+      "learning_rate": 2.844910519219632e-07,
+      "logits/chosen": 1.6715238094329834,
+      "logits/rejected": 1.2933677434921265,
+      "logps/chosen": -3.8149237632751465,
+      "logps/rejected": -8.005244255065918,
+      "loss": 0.2073,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -5.722386360168457,
+      "rewards/margins": 6.285480499267578,
+      "rewards/rejected": -12.007866859436035,
+      "step": 1270
+    },
+    {
+      "epoch": 1.1754909842655334,
+      "grad_norm": 3.0442380905151367,
+      "learning_rate": 2.6072059940146775e-07,
+      "logits/chosen": 1.210684061050415,
+      "logits/rejected": 1.0442299842834473,
+      "logps/chosen": -4.0504326820373535,
+      "logps/rejected": -8.990427017211914,
+      "loss": 0.2031,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.075650215148926,
+      "rewards/margins": 7.409991264343262,
+      "rewards/rejected": -13.485639572143555,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1846789939129436,
+      "grad_norm": 2.9671738147735596,
+      "learning_rate": 2.3793236883495164e-07,
+      "logits/chosen": 2.123716115951538,
+      "logits/rejected": 1.7563165426254272,
+      "logps/chosen": -4.090588092803955,
+      "logps/rejected": -8.25685977935791,
+      "loss": 0.2191,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.1358819007873535,
+      "rewards/margins": 6.249407768249512,
+      "rewards/rejected": -12.385289192199707,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1938670035603538,
+      "grad_norm": 5.619577407836914,
+      "learning_rate": 2.1613635589349756e-07,
+      "logits/chosen": 2.250432252883911,
+      "logits/rejected": 2.119335174560547,
+      "logps/chosen": -4.006811141967773,
+      "logps/rejected": -7.816763401031494,
+      "loss": 0.2523,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.01021671295166,
+      "rewards/margins": 5.71492862701416,
+      "rewards/rejected": -11.72514533996582,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1938670035603538,
+      "eval_logits/chosen": 1.4931063652038574,
+      "eval_logits/rejected": 1.1866812705993652,
+      "eval_logps/chosen": -3.5401999950408936,
+      "eval_logps/rejected": -8.020904541015625,
+      "eval_loss": 0.20123924314975739,
+      "eval_rewards/accuracies": 0.9204545617103577,
+      "eval_rewards/chosen": -5.310299873352051,
+      "eval_rewards/margins": 6.721057415008545,
+      "eval_rewards/rejected": -12.031357765197754,
+      "eval_runtime": 24.4186,
+      "eval_samples_per_second": 28.83,
+      "eval_steps_per_second": 3.604,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2030550132077638,
+      "grad_norm": 5.24505615234375,
+      "learning_rate": 1.95342121028749e-07,
+      "logits/chosen": 2.028916597366333,
+      "logits/rejected": 1.8642489910125732,
+      "logps/chosen": -3.7371432781219482,
+      "logps/rejected": -8.189066886901855,
+      "loss": 0.2,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -5.605715274810791,
+      "rewards/margins": 6.67788553237915,
+      "rewards/rejected": -12.283600807189941,
+      "step": 1310
+    },
+    {
+      "epoch": 1.212243022855174,
+      "grad_norm": 2.5810768604278564,
+      "learning_rate": 1.7555878527937164e-07,
+      "logits/chosen": 2.4587361812591553,
+      "logits/rejected": 2.419093608856201,
+      "logps/chosen": -3.863225221633911,
+      "logps/rejected": -8.523834228515625,
+      "loss": 0.1589,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.7948384284973145,
+      "rewards/margins": 6.990914821624756,
+      "rewards/rejected": -12.785752296447754,
+      "step": 1320
+    },
+    {
+      "epoch": 1.2214310325025841,
+      "grad_norm": 1.403421401977539,
+      "learning_rate": 1.567950262702714e-07,
+      "logits/chosen": 1.8351008892059326,
+      "logits/rejected": 1.7053043842315674,
+      "logps/chosen": -4.444234371185303,
+      "logps/rejected": -8.667207717895508,
+      "loss": 0.1793,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.666351318359375,
+      "rewards/margins": 6.334461212158203,
+      "rewards/rejected": -13.000813484191895,
+      "step": 1330
+    },
+    {
+      "epoch": 1.2306190421499943,
+      "grad_norm": 3.304309368133545,
+      "learning_rate": 1.3905907440629752e-07,
+      "logits/chosen": 2.251183032989502,
+      "logits/rejected": 2.064572811126709,
+      "logps/chosen": -4.050612449645996,
+      "logps/rejected": -8.985613822937012,
+      "loss": 0.1779,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.075918674468994,
+      "rewards/margins": 7.40250301361084,
+      "rewards/rejected": -13.478421211242676,
+      "step": 1340
+    },
+    {
+      "epoch": 1.2398070517974045,
+      "grad_norm": 2.867111921310425,
+      "learning_rate": 1.223587092621162e-07,
+      "logits/chosen": 1.5418930053710938,
+      "logits/rejected": 1.4867240190505981,
+      "logps/chosen": -4.031666278839111,
+      "logps/rejected": -8.506909370422363,
+      "loss": 0.1736,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -6.047499179840088,
+      "rewards/margins": 6.712864875793457,
+      "rewards/rejected": -12.760363578796387,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2398070517974045,
+      "eval_logits/chosen": 1.4972354173660278,
+      "eval_logits/rejected": 1.1784640550613403,
+      "eval_logps/chosen": -3.556915283203125,
+      "eval_logps/rejected": -8.036223411560059,
+      "eval_loss": 0.19999442994594574,
+      "eval_rewards/accuracies": 0.9318181872367859,
+      "eval_rewards/chosen": -5.335372447967529,
+      "eval_rewards/margins": 6.718961715698242,
+      "eval_rewards/rejected": -12.054333686828613,
+      "eval_runtime": 24.4074,
+      "eval_samples_per_second": 28.844,
+      "eval_steps_per_second": 3.605,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2489950614448144,
+      "grad_norm": 2.1836965084075928,
+      "learning_rate": 1.067012561698319e-07,
+      "logits/chosen": 2.2363076210021973,
+      "logits/rejected": 2.0226285457611084,
+      "logps/chosen": -4.427682876586914,
+      "logps/rejected": -8.549234390258789,
+      "loss": 0.2027,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -6.641523838043213,
+      "rewards/margins": 6.1823272705078125,
+      "rewards/rejected": -12.823850631713867,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2581830710922246,
+      "grad_norm": 7.196364402770996,
+      "learning_rate": 9.209358300585474e-08,
+      "logits/chosen": 2.689990758895874,
+      "logits/rejected": 2.3472132682800293,
+      "logps/chosen": -3.9703564643859863,
+      "logps/rejected": -8.000662803649902,
+      "loss": 0.1962,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -5.9555344581604,
+      "rewards/margins": 6.0454607009887695,
+      "rewards/rejected": -12.000995635986328,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2673710807396348,
+      "grad_norm": 8.442782402038574,
+      "learning_rate": 7.854209717842231e-08,
+      "logits/chosen": 2.107114315032959,
+      "logits/rejected": 1.749751091003418,
+      "logps/chosen": -3.971087694168091,
+      "logps/rejected": -8.122562408447266,
+      "loss": 0.2435,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.956631183624268,
+      "rewards/margins": 6.227211952209473,
+      "rewards/rejected": -12.183842658996582,
+      "step": 1380
+    },
+    {
+      "epoch": 1.276559090387045,
+      "grad_norm": 5.254242897033691,
+      "learning_rate": 6.605274281709929e-08,
+      "logits/chosen": 2.106802463531494,
+      "logits/rejected": 1.8030809164047241,
+      "logps/chosen": -4.336814880371094,
+      "logps/rejected": -8.912458419799805,
+      "loss": 0.2051,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.505222320556641,
+      "rewards/margins": 6.863465785980225,
+      "rewards/rejected": -13.368688583374023,
+      "step": 1390
+    },
+    {
+      "epoch": 1.2857471000344551,
+      "grad_norm": 5.613115310668945,
+      "learning_rate": 5.463099816548578e-08,
+      "logits/chosen": 1.6433700323104858,
+      "logits/rejected": 1.274550437927246,
+      "logps/chosen": -3.915881633758545,
+      "logps/rejected": -7.747851371765137,
+      "loss": 0.2139,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -5.873822212219238,
+      "rewards/margins": 5.747954368591309,
+      "rewards/rejected": -11.62177848815918,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2857471000344551,
+      "eval_logits/chosen": 1.4849358797073364,
+      "eval_logits/rejected": 1.166409969329834,
+      "eval_logps/chosen": -3.554471492767334,
+      "eval_logps/rejected": -8.035895347595215,
+      "eval_loss": 0.2001064419746399,
+      "eval_rewards/accuracies": 0.9318181872367859,
+      "eval_rewards/chosen": -5.33170747756958,
+      "eval_rewards/margins": 6.7221360206604,
+      "eval_rewards/rejected": -12.053844451904297,
+      "eval_runtime": 24.4239,
+      "eval_samples_per_second": 28.824,
+      "eval_steps_per_second": 3.603,
+      "step": 1400
+    },
+    {
+      "epoch": 1.294935109681865,
+      "grad_norm": 3.2592716217041016,
+      "learning_rate": 4.428187317827848e-08,
+      "logits/chosen": 1.6605371236801147,
+      "logits/rejected": 1.512782335281372,
+      "logps/chosen": -4.016318321228027,
+      "logps/rejected": -8.222332954406738,
+      "loss": 0.1929,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.024477481842041,
+      "rewards/margins": 6.30902099609375,
+      "rewards/rejected": -12.33349895477295,
+      "step": 1410
+    },
+    {
+      "epoch": 1.3041231193292753,
+      "grad_norm": 3.8764472007751465,
+      "learning_rate": 3.5009907323737826e-08,
+      "logits/chosen": 1.6769720315933228,
+      "logits/rejected": 1.466618299484253,
+      "logps/chosen": -3.6894333362579346,
+      "logps/rejected": -7.910569190979004,
+      "loss": 0.186,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.534149646759033,
+      "rewards/margins": 6.331704139709473,
+      "rewards/rejected": -11.865854263305664,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3133111289766854,
+      "grad_norm": 3.0787954330444336,
+      "learning_rate": 2.681916759252917e-08,
+      "logits/chosen": 2.332460403442383,
+      "logits/rejected": 1.9827533960342407,
+      "logps/chosen": -4.545821189880371,
+      "logps/rejected": -8.547601699829102,
+      "loss": 0.2139,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.818732261657715,
+      "rewards/margins": 6.002669811248779,
+      "rewards/rejected": -12.821401596069336,
+      "step": 1430
+    },
+    {
+      "epoch": 1.3224991386240956,
+      "grad_norm": 4.644412994384766,
+      "learning_rate": 1.9713246713805588e-08,
+      "logits/chosen": 2.217742443084717,
+      "logits/rejected": 1.9464161396026611,
+      "logps/chosen": -3.950064182281494,
+      "logps/rejected": -8.264387130737305,
+      "loss": 0.199,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -5.92509651184082,
+      "rewards/margins": 6.4714837074279785,
+      "rewards/rejected": -12.396580696105957,
+      "step": 1440
+    },
+    {
+      "epoch": 1.3316871482715058,
+      "grad_norm": 4.489632606506348,
+      "learning_rate": 1.3695261579316776e-08,
+      "logits/chosen": 1.3916233777999878,
+      "logits/rejected": 1.4683945178985596,
+      "logps/chosen": -4.025264739990234,
+      "logps/rejected": -9.182435989379883,
+      "loss": 0.2255,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.037897109985352,
+      "rewards/margins": 7.735756874084473,
+      "rewards/rejected": -13.773653984069824,
+      "step": 1450
+    },
+    {
+      "epoch": 1.3316871482715058,
+      "eval_logits/chosen": 1.4939136505126953,
+      "eval_logits/rejected": 1.1826014518737793,
+      "eval_logps/chosen": -3.5562257766723633,
+      "eval_logps/rejected": -8.059898376464844,
+      "eval_loss": 0.19852806627750397,
+      "eval_rewards/accuracies": 0.9431818127632141,
+      "eval_rewards/chosen": -5.334338665008545,
+      "eval_rewards/margins": 6.755507946014404,
+      "eval_rewards/rejected": -12.08984661102295,
+      "eval_runtime": 24.3883,
+      "eval_samples_per_second": 28.866,
+      "eval_steps_per_second": 3.608,
+      "step": 1450
+    },
+    {
+      "epoch": 1.3408751579189158,
+      "grad_norm": 4.516350746154785,
+      "learning_rate": 8.767851876239075e-09,
+      "logits/chosen": 2.247871160507202,
+      "logits/rejected": 2.161593198776245,
+      "logps/chosen": -4.095339298248291,
+      "logps/rejected": -8.592370986938477,
+      "loss": 0.1777,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.143008232116699,
+      "rewards/margins": 6.745549201965332,
+      "rewards/rejected": -12.888557434082031,
+      "step": 1460
+    },
+    {
+      "epoch": 1.350063167566326,
+      "grad_norm": 3.5604116916656494,
+      "learning_rate": 4.933178929321103e-09,
+      "logits/chosen": 2.272150754928589,
+      "logits/rejected": 2.137777090072632,
+      "logps/chosen": -4.238589286804199,
+      "logps/rejected": -8.042024612426758,
+      "loss": 0.2021,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.357884407043457,
+      "rewards/margins": 5.70515251159668,
+      "rewards/rejected": -12.063036918640137,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3592511772137361,
+      "grad_norm": 1.878821849822998,
+      "learning_rate": 2.192924752854042e-09,
+      "logits/chosen": 2.2196030616760254,
+      "logits/rejected": 1.7679128646850586,
+      "logps/chosen": -4.042660236358643,
+      "logps/rejected": -8.428380012512207,
+      "loss": 0.1908,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -6.063990592956543,
+      "rewards/margins": 6.578577995300293,
+      "rewards/rejected": -12.642568588256836,
+      "step": 1480
+    },
+    {
+      "epoch": 1.368439186861146,
+      "grad_norm": 4.727602958679199,
+      "learning_rate": 5.48291312886251e-10,
+      "logits/chosen": 2.2299444675445557,
+      "logits/rejected": 2.112347364425659,
+      "logps/chosen": -4.057961463928223,
+      "logps/rejected": -7.997668266296387,
+      "loss": 0.1912,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -6.086942672729492,
+      "rewards/margins": 5.909560203552246,
+      "rewards/rejected": -11.996503829956055,
+      "step": 1490
+    },
+    {
+      "epoch": 1.3776271965085563,
+      "grad_norm": 3.4773285388946533,
+      "learning_rate": 0.0,
+      "logits/chosen": 2.782447576522827,
+      "logits/rejected": 2.5681684017181396,
+      "logps/chosen": -4.227536678314209,
+      "logps/rejected": -8.583551406860352,
+      "loss": 0.2239,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -6.341304779052734,
+      "rewards/margins": 6.534020900726318,
+      "rewards/rejected": -12.875326156616211,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3776271965085563,
+      "eval_logits/chosen": 1.4909855127334595,
+      "eval_logits/rejected": 1.1811962127685547,
+      "eval_logps/chosen": -3.5707902908325195,
+      "eval_logps/rejected": -8.077098846435547,
+      "eval_loss": 0.2004113346338272,
+      "eval_rewards/accuracies": 0.9318181872367859,
+      "eval_rewards/chosen": -5.3561859130859375,
+      "eval_rewards/margins": 6.759463310241699,
+      "eval_rewards/rejected": -12.115647315979004,
+      "eval_runtime": 24.4303,
+      "eval_samples_per_second": 28.817,
+      "eval_steps_per_second": 3.602,
+      "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": 3.642599643201667e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}