{"ts": "2025-12-26T15:24:36", "event": "train_log", "step": 2, "epoch": 0.0023357664233576644, "progress_pct": 0.08, "epoch_pct": 0.08, "eta": "07:30:29", "max_grad_norm": 1.0, "loss": 0.6931473016738892, "grad_norm": 1.2424817085266113, "learning_rate": 1.9379844961240311e-07, "rewards/chosen": 0.0, "rewards/rejected": 0.0, "rewards/accuracies": 0.0, "rewards/margins": 0.0, "logps/chosen": -368.911865234375, "logps/rejected": -398.83880615234375, "logits/chosen": 5.179401397705078, "logits/rejected": 5.192930698394775}
{"ts": "2025-12-26T15:24:56", "event": "train_log", "step": 4, "epoch": 0.004671532846715329, "progress_pct": 0.16, "epoch_pct": 0.16, "eta": "07:14:49", "max_grad_norm": 1.0, "loss": 0.693317174911499, "grad_norm": 1.3884541988372803, "learning_rate": 5.813953488372093e-07, "rewards/chosen": 0.022540951147675514, "rewards/rejected": 0.022656824439764023, "rewards/accuracies": 0.5, "rewards/margins": -0.00011587224435061216, "logps/chosen": -338.257568359375, "logps/rejected": -366.88128662109375, "logits/chosen": 5.405174255371094, "logits/rejected": 5.456291675567627}
{"ts": "2025-12-26T15:57:54", "event": "train_log", "step": 2, "epoch": 0.0023357664233576644, "progress_pct": 0.08, "epoch_pct": 0.08, "eta": "07:30:57", "max_grad_norm": 1.0, "loss": 0.6931473016738892, "grad_norm": 1.242694616317749, "learning_rate": 1.9379844961240311e-07, "rewards/chosen": 0.0, "rewards/rejected": 0.0, "rewards/accuracies": 0.0, "rewards/margins": 0.0, "logps/chosen": -368.911865234375, "logps/rejected": -398.83880615234375, "logits/chosen": 5.179401397705078, "logits/rejected": 5.192930698394775}
{"ts": "2025-12-26T15:58:14", "event": "train_log", "step": 4, "epoch": 0.004671532846715329, "progress_pct": 0.16, "epoch_pct": 0.16, "eta": "07:15:10", "max_grad_norm": 1.0, "loss": 0.6949559450149536, "grad_norm": 1.392399787902832, "learning_rate": 5.813953488372093e-07, "rewards/chosen": 0.004504585638642311, "rewards/rejected": 0.007727146148681641, "rewards/accuracies": 0.625, "rewards/margins": -0.003222561441361904, "logps/chosen": -338.43792724609375, "logps/rejected": -367.03057861328125, "logits/chosen": 5.403897762298584, "logits/rejected": 5.4565606117248535}
{"ts": "2025-12-26T15:58:34", "event": "train_log", "step": 6, "epoch": 0.0070072992700729924, "progress_pct": 0.23, "epoch_pct": 0.23, "eta": "07:13:22", "max_grad_norm": 1.0, "loss": 0.689236581325531, "grad_norm": 1.066603183746338, "learning_rate": 9.689922480620155e-07, "rewards/chosen": -0.0034066196531057358, "rewards/rejected": -0.01166229322552681, "rewards/accuracies": 0.5625, "rewards/margins": 0.008255671709775925, "logps/chosen": -362.3431701660156, "logps/rejected": -387.5829772949219, "logits/chosen": 5.291868209838867, "logits/rejected": 5.328356742858887}
{"ts": "2025-12-26T15:58:54", "event": "train_log", "step": 8, "epoch": 0.009343065693430658, "progress_pct": 0.31, "epoch_pct": 0.31, "eta": "07:08:27", "max_grad_norm": 1.0, "loss": 0.6943775415420532, "grad_norm": 1.0005714893341064, "learning_rate": 1.3565891472868218e-06, "rewards/chosen": 0.014657974243164062, "rewards/rejected": 0.015892982482910156, "rewards/accuracies": 0.375, "rewards/margins": -0.0012350091710686684, "logps/chosen": -379.9283447265625, "logps/rejected": -389.0852355957031, "logits/chosen": 5.323437690734863, "logits/rejected": 5.410858631134033}
{"ts": "2025-12-26T15:59:13", "event": "train_log", "step": 10, "epoch": 0.01167883211678832, "progress_pct": 0.39, "epoch_pct": 0.39, "eta": "07:07:21", "max_grad_norm": 1.0, "loss": 0.693260908126831, "grad_norm": 1.2461222410202026, "learning_rate": 1.744186046511628e-06, "rewards/chosen": -0.028497030958533287, "rewards/rejected": -0.028623390942811966, "rewards/accuracies": 0.625, "rewards/margins": 0.00012636138126254082, "logps/chosen": -363.2003479003906, "logps/rejected": -389.67376708984375, "logits/chosen": 5.435908317565918, "logits/rejected": 5.494542121887207}
{"ts": "2025-12-26T15:59:34", "event": "train_log", "step": 12, "epoch": 0.014014598540145985, "progress_pct": 0.47, "epoch_pct": 0.47, "eta": "07:08:38", "max_grad_norm": 1.0, "loss": 0.6882913112640381, "grad_norm": 1.4030137062072754, "learning_rate": 2.131782945736434e-06, "rewards/chosen": 0.01622028276324272, "rewards/rejected": 0.006133650429546833, "rewards/accuracies": 0.5, "rewards/margins": 0.010086631402373314, "logps/chosen": -370.96429443359375, "logps/rejected": -402.4786071777344, "logits/chosen": 5.3550801277160645, "logits/rejected": 5.375768661499023}
{"ts": "2025-12-26T15:59:52", "event": "train_log", "step": 14, "epoch": 0.01635036496350365, "progress_pct": 0.54, "epoch_pct": 0.55, "eta": "07:02:49", "max_grad_norm": 1.0, "loss": 0.6896716356277466, "grad_norm": 1.1157702207565308, "learning_rate": 2.5193798449612402e-06, "rewards/chosen": -0.017319394275546074, "rewards/rejected": -0.024647902697324753, "rewards/accuracies": 0.625, "rewards/margins": 0.007328510750085115, "logps/chosen": -336.7254333496094, "logps/rejected": -357.52203369140625, "logits/chosen": 5.515308380126953, "logits/rejected": 5.561104774475098}
{"ts": "2025-12-26T16:00:12", "event": "train_log", "step": 16, "epoch": 0.018686131386861315, "progress_pct": 0.62, "epoch_pct": 0.62, "eta": "07:03:25", "max_grad_norm": 1.0, "loss": 0.6904245018959045, "grad_norm": 0.9470655918121338, "learning_rate": 2.9069767441860468e-06, "rewards/chosen": 0.03270244598388672, "rewards/rejected": 0.026875685900449753, "rewards/accuracies": 0.5625, "rewards/margins": 0.005826758686453104, "logps/chosen": -415.6842041015625, "logps/rejected": -441.1054992675781, "logits/chosen": 5.553088665008545, "logits/rejected": 5.582851886749268}
{"ts": "2025-12-26T16:00:33", "event": "train_log", "step": 18, "epoch": 0.021021897810218976, "progress_pct": 0.7, "epoch_pct": 0.7, "eta": "07:04:54", "max_grad_norm": 1.0, "loss": 0.683630108833313, "grad_norm": 1.4397331476211548, "learning_rate": 3.2945736434108533e-06, "rewards/chosen": 0.011020278558135033, "rewards/rejected": -0.008498954586684704, "rewards/accuracies": 0.5625, "rewards/margins": 0.01951923407614231, "logps/chosen": -392.46221923828125, "logps/rejected": -420.1712341308594, "logits/chosen": 5.440742015838623, "logits/rejected": 5.489529132843018}
{"ts": "2025-12-26T16:00:52", "event": "train_log", "step": 20, "epoch": 0.02335766423357664, "progress_pct": 0.78, "epoch_pct": 0.78, "eta": "07:03:26", "max_grad_norm": 1.0, "loss": 0.6902388334274292, "grad_norm": 1.5941083431243896, "learning_rate": 3.6821705426356594e-06, "rewards/chosen": 0.006536484230309725, "rewards/rejected": 0.0005230908282101154, "rewards/accuracies": 0.5625, "rewards/margins": 0.006013393402099609, "logps/chosen": -345.2221374511719, "logps/rejected": -365.9537048339844, "logits/chosen": 5.318347930908203, "logits/rejected": 5.397945404052734}
{"ts": "2025-12-26T16:01:12", "event": "train_log", "step": 22, "epoch": 0.025693430656934305, "progress_pct": 0.86, "epoch_pct": 0.86, "eta": "07:03:12", "max_grad_norm": 1.0, "loss": 0.691262423992157, "grad_norm": 1.1363905668258667, "learning_rate": 4.0697674418604655e-06, "rewards/chosen": 0.011908342130482197, "rewards/rejected": 0.007370188366621733, "rewards/accuracies": 0.5, "rewards/margins": 0.004538153763860464, "logps/chosen": -347.9439697265625, "logps/rejected": -370.65777587890625, "logits/chosen": 5.632981300354004, "logits/rejected": 5.7265520095825195}
{"ts": "2025-12-26T16:01:32", "event": "train_log", "step": 24, "epoch": 0.02802919708029197, "progress_pct": 0.93, "epoch_pct": 0.93, "eta": "07:02:08", "max_grad_norm": 1.0, "loss": 0.6769475936889648, "grad_norm": 1.0684627294540405, "learning_rate": 4.457364341085272e-06, "rewards/chosen": 0.01244144607335329, "rewards/rejected": -0.020452119410037994, "rewards/accuracies": 0.875, "rewards/margins": 0.03289356082677841, "logps/chosen": -347.1539001464844, "logps/rejected": -377.6044921875, "logits/chosen": 5.35699987411499, "logits/rejected": 5.405580520629883}
{"ts": "2025-12-26T16:09:16", "event": "train_log", "step": 25, "epoch": 0.029197080291970802, "progress_pct": 0.97, "epoch_pct": 0.97, "eta": "19:53:32", "max_grad_norm": 1.0, "eval_loss": 0.6836819648742676, "eval_runtime": 454.4375, "eval_samples_per_second": 1.677, "eval_steps_per_second": 1.677, "eval_rewards/chosen": 0.024636391550302505, "eval_rewards/rejected": 0.005080964416265488, "eval_rewards/accuracies": 0.665354311466217, "eval_rewards/margins": 0.019555427134037018, "eval_logps/chosen": -370.1607666015625, "eval_logps/rejected": -395.7251892089844, "eval_logits/chosen": 5.295141220092773, "eval_logits/rejected": 5.345211029052734}
{"ts": "2025-12-26T16:09:27", "event": "train_log", "step": 26, "epoch": 0.030364963503649634, "progress_pct": 1.01, "epoch_pct": 1.01, "eta": "19:24:28", "max_grad_norm": 1.0, "loss": 0.6849788427352905, "grad_norm": 1.592353105545044, "learning_rate": 4.844961240310078e-06, "rewards/chosen": 0.026385309174656868, "rewards/rejected": 0.009418869391083717, "rewards/accuracies": 0.625, "rewards/margins": 0.016966437920928, "logps/chosen": -387.54876708984375, "logps/rejected": -412.0630187988281, "logits/chosen": 5.157042026519775, "logits/rejected": 5.244912147521973}
{"ts": "2025-12-26T16:09:47", "event": "train_log", "step": 28, "epoch": 0.0327007299270073, "progress_pct": 1.09, "epoch_pct": 1.09, "eta": "18:30:11", "max_grad_norm": 1.0, "loss": 0.675189733505249, "grad_norm": 1.3181558847427368, "learning_rate": 5.232558139534884e-06, "rewards/chosen": 0.045946408063173294, "rewards/rejected": 0.009190557524561882, "rewards/accuracies": 0.8125, "rewards/margins": 0.03675585240125656, "logps/chosen": -360.41650390625, "logps/rejected": -391.2162170410156, "logits/chosen": 5.545513153076172, "logits/rejected": 5.54400110244751}
{"ts": "2025-12-26T16:10:07", "event": "train_log", "step": 30, "epoch": 0.035036496350364967, "progress_pct": 1.17, "epoch_pct": 1.17, "eta": "17:43:26", "max_grad_norm": 1.0, "loss": 0.6752142310142517, "grad_norm": 1.443650722503662, "learning_rate": 5.620155038759691e-06, "rewards/chosen": 0.04194517061114311, "rewards/rejected": 0.005256845150142908, "rewards/accuracies": 0.8125, "rewards/margins": 0.03668833151459694, "logps/chosen": -378.6293640136719, "logps/rejected": -405.3665466308594, "logits/chosen": 5.136168003082275, "logits/rejected": 5.239327907562256}
{"ts": "2025-12-26T16:10:26", "event": "train_log", "step": 32, "epoch": 0.03737226277372263, "progress_pct": 1.24, "epoch_pct": 1.25, "eta": "17:01:56", "max_grad_norm": 1.0, "loss": 0.6700581312179565, "grad_norm": 1.379568338394165, "learning_rate": 6.007751937984497e-06, "rewards/chosen": 0.06658173352479935, "rewards/rejected": 0.019388392567634583, "rewards/accuracies": 0.875, "rewards/margins": 0.047193337231874466, "logps/chosen": -358.5367736816406, "logps/rejected": -382.4181213378906, "logits/chosen": 5.411487579345703, "logits/rejected": 5.427243232727051}
{"ts": "2025-12-26T16:10:44", "event": "train_log", "step": 34, "epoch": 0.039708029197080295, "progress_pct": 1.32, "epoch_pct": 1.32, "eta": "16:23:25", "max_grad_norm": 1.0, "loss": 0.6610866785049438, "grad_norm": 1.3260451555252075, "learning_rate": 6.395348837209303e-06, "rewards/chosen": 0.07038869708776474, "rewards/rejected": 0.0045137410052120686, "rewards/accuracies": 0.9375, "rewards/margins": 0.06587495654821396, "logps/chosen": -326.9423828125, "logps/rejected": -346.52081298828125, "logits/chosen": 5.207217216491699, "logits/rejected": 5.254848480224609}
{"ts": "2025-12-26T16:11:04", "event": "train_log", "step": 36, "epoch": 0.04204379562043795, "progress_pct": 1.4, "epoch_pct": 1.4, "eta": "15:51:44", "max_grad_norm": 1.0, "loss": 0.6281551718711853, "grad_norm": 1.5776340961456299, "learning_rate": 6.782945736434108e-06, "rewards/chosen": 0.11738375574350357, "rewards/rejected": -0.018992995843291283, "rewards/accuracies": 1.0, "rewards/margins": 0.1363767683506012, "logps/chosen": -359.9613952636719, "logps/rejected": -384.31683349609375, "logits/chosen": 5.550538063049316, "logits/rejected": 5.6374335289001465}
{"ts": "2025-12-26T16:11:23", "event": "train_log", "step": 38, "epoch": 0.04437956204379562, "progress_pct": 1.48, "epoch_pct": 1.48, "eta": "15:21:57", "max_grad_norm": 1.0, "loss": 0.6270830631256104, "grad_norm": 1.8589071035385132, "learning_rate": 7.170542635658915e-06, "rewards/chosen": 0.1617884635925293, "rewards/rejected": 0.022934721782803535, "rewards/accuracies": 0.9375, "rewards/margins": 0.1388537436723709, "logps/chosen": -325.8544616699219, "logps/rejected": -351.9772644042969, "logits/chosen": 5.39143180847168, "logits/rejected": 5.412029266357422}
{"ts": "2025-12-26T16:11:43", "event": "train_log", "step": 40, "epoch": 0.04671532846715328, "progress_pct": 1.56, "epoch_pct": 1.56, "eta": "14:56:25", "max_grad_norm": 1.0, "loss": 0.641180157661438, "grad_norm": 1.3231571912765503, "learning_rate": 7.558139534883721e-06, "rewards/chosen": 0.15248623490333557, "rewards/rejected": 0.04090070724487305, "rewards/accuracies": 0.875, "rewards/margins": 0.11158552765846252, "logps/chosen": -343.3839111328125, "logps/rejected": -374.7848205566406, "logits/chosen": 5.189720153808594, "logits/rejected": 5.203127384185791}
{"ts": "2025-12-26T16:12:02", "event": "train_log", "step": 42, "epoch": 0.049051094890510946, "progress_pct": 1.63, "epoch_pct": 1.64, "eta": "14:31:31", "max_grad_norm": 1.0, "loss": 0.6093671321868896, "grad_norm": 2.5331315994262695, "learning_rate": 7.945736434108528e-06, "rewards/chosen": 0.2898235321044922, "rewards/rejected": 0.10823898762464523, "rewards/accuracies": 0.9375, "rewards/margins": 0.18158456683158875, "logps/chosen": -341.813720703125, "logps/rejected": -372.44952392578125, "logits/chosen": 5.420182228088379, "logits/rejected": 5.45302677154541}
{"ts": "2025-12-26T16:12:20", "event": "train_log", "step": 44, "epoch": 0.05138686131386861, "progress_pct": 1.71, "epoch_pct": 1.71, "eta": "14:08:47", "max_grad_norm": 1.0, "loss": 0.5815833210945129, "grad_norm": 1.5247384309768677, "learning_rate": 8.333333333333334e-06, "rewards/chosen": 0.32459571957588196, "rewards/rejected": 0.07354050129652023, "rewards/accuracies": 0.8125, "rewards/margins": 0.2510552406311035, "logps/chosen": -354.49627685546875, "logps/rejected": -376.88818359375, "logits/chosen": 5.383636951446533, "logits/rejected": 5.397551536560059}
{"ts": "2025-12-26T16:12:40", "event": "train_log", "step": 46, "epoch": 0.053722627737226275, "progress_pct": 1.79, "epoch_pct": 1.79, "eta": "13:49:08", "max_grad_norm": 1.0, "loss": 0.5269681215286255, "grad_norm": 2.0814144611358643, "learning_rate": 8.72093023255814e-06, "rewards/chosen": 0.6465227603912354, "rewards/rejected": 0.27069616317749023, "rewards/accuracies": 0.9375, "rewards/margins": 0.37582656741142273, "logps/chosen": -331.1025390625, "logps/rejected": -362.90118408203125, "logits/chosen": 5.269731044769287, "logits/rejected": 5.287116050720215}
{"ts": "2025-12-26T16:12:59", "event": "train_log", "step": 48, "epoch": 0.05605839416058394, "progress_pct": 1.87, "epoch_pct": 1.87, "eta": "13:31:19", "max_grad_norm": 1.0, "loss": 0.5066201686859131, "grad_norm": 1.769063115119934, "learning_rate": 9.108527131782946e-06, "rewards/chosen": 0.6377636194229126, "rewards/rejected": 0.21126146614551544, "rewards/accuracies": 1.0, "rewards/margins": 0.42650213837623596, "logps/chosen": -369.40283203125, "logps/rejected": -400.18438720703125, "logits/chosen": 5.472540855407715, "logits/rejected": 5.465417861938477}
{"ts": "2025-12-26T16:13:21", "event": "train_log", "step": 50, "epoch": 0.058394160583941604, "progress_pct": 1.94, "epoch_pct": 1.95, "eta": "13:16:33", "max_grad_norm": 1.0, "loss": 0.529259979724884, "grad_norm": 2.84169602394104, "learning_rate": 9.496124031007753e-06, "rewards/chosen": 0.7923164367675781, "rewards/rejected": 0.4136104881763458, "rewards/accuracies": 1.0, "rewards/margins": 0.3787059783935547, "logps/chosen": -363.4556579589844, "logps/rejected": -397.8169860839844, "logits/chosen": 5.050387382507324, "logits/rejected": 5.112288951873779}
{"ts": "2025-12-26T16:20:56", "event": "train_log", "step": 50, "epoch": 0.058394160583941604, "progress_pct": 1.94, "epoch_pct": 1.95, "eta": "19:38:32", "max_grad_norm": 1.0, "eval_loss": 0.4610801041126251, "eval_runtime": 454.5598, "eval_samples_per_second": 1.676, "eval_steps_per_second": 1.676, "eval_rewards/chosen": 0.8944254517555237, "eval_rewards/rejected": 0.3205168545246124, "eval_rewards/accuracies": 0.9619422554969788, "eval_rewards/margins": 0.5739086270332336, "eval_logps/chosen": -361.462890625, "eval_logps/rejected": -392.5708312988281, "eval_logits/chosen": 5.22359037399292, "eval_logits/rejected": 5.286833763122559}
{"ts": "2025-12-26T16:21:15", "event": "train_log", "step": 52, "epoch": 0.06072992700729927, "progress_pct": 2.02, "epoch_pct": 2.02, "eta": "19:08:07", "max_grad_norm": 1.0, "loss": 0.44602835178375244, "grad_norm": 1.6907895803451538, "learning_rate": 9.883720930232558e-06, "rewards/chosen": 0.9869746565818787, "rewards/rejected": 0.3813100755214691, "rewards/accuracies": 0.9375, "rewards/margins": 0.6056646108627319, "logps/chosen": -343.4534606933594, "logps/rejected": -379.39508056640625, "logits/chosen": 5.486469268798828, "logits/rejected": 5.541717529296875}
{"ts": "2025-12-26T16:21:36", "event": "train_log", "step": 54, "epoch": 0.06306569343065693, "progress_pct": 2.1, "epoch_pct": 2.1, "eta": "18:41:01", "max_grad_norm": 1.0, "loss": 0.43609702587127686, "grad_norm": 1.9458682537078857, "learning_rate": 1.0271317829457365e-05, "rewards/chosen": 0.7794930934906006, "rewards/rejected": 0.15292587876319885, "rewards/accuracies": 1.0, "rewards/margins": 0.6265671253204346, "logps/chosen": -379.5437316894531, "logps/rejected": -401.5587463378906, "logits/chosen": 5.169528961181641, "logits/rejected": 5.2688751220703125}
{"ts": "2025-12-26T16:21:57", "event": "train_log", "step": 56, "epoch": 0.0654014598540146, "progress_pct": 2.18, "epoch_pct": 2.18, "eta": "18:15:44", "max_grad_norm": 1.0, "loss": 0.3928414583206177, "grad_norm": 2.1266520023345947, "learning_rate": 1.065891472868217e-05, "rewards/chosen": 1.274291753768921, "rewards/rejected": 0.4878700375556946, "rewards/accuracies": 0.9375, "rewards/margins": 0.7864217758178711, "logps/chosen": -378.0788269042969, "logps/rejected": -413.27392578125, "logits/chosen": 5.097426414489746, "logits/rejected": 5.15327262878418}
{"ts": "2025-12-26T16:22:18", "event": "train_log", "step": 58, "epoch": 0.06773722627737226, "progress_pct": 2.26, "epoch_pct": 2.26, "eta": "17:52:03", "max_grad_norm": 1.0, "loss": 0.35855019092559814, "grad_norm": 1.5381489992141724, "learning_rate": 1.1046511627906977e-05, "rewards/chosen": 1.2897911071777344, "rewards/rejected": 0.35436347126960754, "rewards/accuracies": 0.875, "rewards/margins": 0.9354276061058044, "logps/chosen": -372.93438720703125, "logps/rejected": -401.8287658691406, "logits/chosen": 5.138954162597656, "logits/rejected": 5.20254373550415}
{"ts": "2025-12-26T16:22:39", "event": "train_log", "step": 60, "epoch": 0.07007299270072993, "progress_pct": 2.33, "epoch_pct": 2.34, "eta": "17:29:56", "max_grad_norm": 1.0, "loss": 0.42801612615585327, "grad_norm": 2.358330726623535, "learning_rate": 1.1434108527131783e-05, "rewards/chosen": 1.3823509216308594, "rewards/rejected": 0.6532848477363586, "rewards/accuracies": 0.875, "rewards/margins": 0.729066014289856, "logps/chosen": -360.984619140625, "logps/rejected": -392.3192138671875, "logits/chosen": 5.071888446807861, "logits/rejected": 5.187964916229248}
{"ts": "2025-12-26T16:22:58", "event": "train_log", "step": 62, "epoch": 0.07240875912408759, "progress_pct": 2.41, "epoch_pct": 2.41, "eta": "17:08:40", "max_grad_norm": 1.0, "loss": 0.31365492939949036, "grad_norm": 2.177586317062378, "learning_rate": 1.182170542635659e-05, "rewards/chosen": 1.6637591123580933, "rewards/rejected": 0.5750135183334351, "rewards/accuracies": 1.0, "rewards/margins": 1.0887457132339478, "logps/chosen": -364.808349609375, "logps/rejected": -401.0321044921875, "logits/chosen": 5.264093399047852, "logits/rejected": 5.310842990875244}
{"ts": "2025-12-26T16:23:19", "event": "train_log", "step": 64, "epoch": 0.07474452554744526, "progress_pct": 2.49, "epoch_pct": 2.49, "eta": "16:48:50", "max_grad_norm": 1.0, "loss": 0.3037749230861664, "grad_norm": 1.697789192199707, "learning_rate": 1.2209302325581395e-05, "rewards/chosen": 1.6470392942428589, "rewards/rejected": 0.5321945548057556, "rewards/accuracies": 1.0, "rewards/margins": 1.114844799041748, "logps/chosen": -359.8249816894531, "logps/rejected": -397.2122497558594, "logits/chosen": 5.191982269287109, "logits/rejected": 5.261416912078857}
{"ts": "2025-12-26T16:23:38", "event": "train_log", "step": 66, "epoch": 0.07708029197080292, "progress_pct": 2.57, "epoch_pct": 2.57, "eta": "16:29:40", "max_grad_norm": 1.0, "loss": 0.25026455521583557, "grad_norm": 1.3219914436340332, "learning_rate": 1.2596899224806202e-05, "rewards/chosen": 1.5671364068984985, "rewards/rejected": 0.15732917189598083, "rewards/accuracies": 1.0, "rewards/margins": 1.4098074436187744, "logps/chosen": -352.3752136230469, "logps/rejected": -392.6779479980469, "logits/chosen": 5.293405532836914, "logits/rejected": 5.3094048500061035}
{"ts": "2025-12-26T16:23:57", "event": "train_log", "step": 68, "epoch": 0.07941605839416059, "progress_pct": 2.64, "epoch_pct": 2.65, "eta": "16:11:16", "max_grad_norm": 1.0, "loss": 0.3108353912830353, "grad_norm": 1.8173967599868774, "learning_rate": 1.2984496124031009e-05, "rewards/chosen": 1.4788665771484375, "rewards/rejected": 0.2151254564523697, "rewards/accuracies": 0.9375, "rewards/margins": 1.2637410163879395, "logps/chosen": -319.99700927734375, "logps/rejected": -364.115234375, "logits/chosen": 5.025746822357178, "logits/rejected": 5.114965438842773}
{"ts": "2025-12-26T16:24:16", "event": "train_log", "step": 70, "epoch": 0.08175182481751825, "progress_pct": 2.72, "epoch_pct": 2.73, "eta": "15:54:17", "max_grad_norm": 1.0, "loss": 0.22991834580898285, "grad_norm": 1.0658400058746338, "learning_rate": 1.3372093023255814e-05, "rewards/chosen": 1.3950352668762207, "rewards/rejected": -0.1014888733625412, "rewards/accuracies": 1.0, "rewards/margins": 1.4965243339538574, "logps/chosen": -383.84033203125, "logps/rejected": -431.7752685546875, "logits/chosen": 4.945235729217529, "logits/rejected": 4.959147930145264}
{"ts": "2025-12-26T16:24:35", "event": "train_log", "step": 72, "epoch": 0.0840875912408759, "progress_pct": 2.8, "epoch_pct": 2.8, "eta": "15:38:16", "max_grad_norm": 1.0, "loss": 0.22603684663772583, "grad_norm": 1.0350896120071411, "learning_rate": 1.375968992248062e-05, "rewards/chosen": 1.2978975772857666, "rewards/rejected": -0.34637776017189026, "rewards/accuracies": 1.0, "rewards/margins": 1.644275426864624, "logps/chosen": -350.9471435546875, "logps/rejected": -382.6837158203125, "logits/chosen": 5.00426721572876, "logits/rejected": 5.120238780975342}
{"ts": "2025-12-26T16:24:56", "event": "train_log", "step": 74, "epoch": 0.08642335766423358, "progress_pct": 2.88, "epoch_pct": 2.88, "eta": "15:23:40", "max_grad_norm": 1.0, "loss": 0.18921935558319092, "grad_norm": 1.1595423221588135, "learning_rate": 1.4147286821705426e-05, "rewards/chosen": 1.1984589099884033, "rewards/rejected": -0.5510700941085815, "rewards/accuracies": 1.0, "rewards/margins": 1.7495291233062744, "logps/chosen": -352.34967041015625, "logps/rejected": -399.23028564453125, "logits/chosen": 4.890130043029785, "logits/rejected": 4.9504714012146}
{"ts": "2025-12-26T16:32:39", "event": "train_log", "step": 75, "epoch": 0.08759124087591241, "progress_pct": 2.92, "epoch_pct": 2.92, "eta": "19:27:59", "max_grad_norm": 1.0, "eval_loss": 0.16020436584949493, "eval_runtime": 454.3435, "eval_samples_per_second": 1.677, "eval_steps_per_second": 1.677, "eval_rewards/chosen": 1.1210675239562988, "eval_rewards/rejected": -0.9336051344871521, "eval_rewards/accuracies": 0.9960629940032959, "eval_rewards/margins": 2.0546727180480957, "eval_logps/chosen": -359.19647216796875, "eval_logps/rejected": -405.1120300292969, "eval_logits/chosen": 4.930174827575684, "eval_logits/rejected": 5.032296657562256}
{"ts": "2025-12-26T16:32:49", "event": "train_log", "step": 76, "epoch": 0.08875912408759123, "progress_pct": 2.96, "epoch_pct": 2.96, "eta": "19:17:37", "max_grad_norm": 1.0, "loss": 0.15998858213424683, "grad_norm": 1.1433167457580566, "learning_rate": 1.4534883720930233e-05, "rewards/chosen": 1.2128857374191284, "rewards/rejected": -0.8816256523132324, "rewards/accuracies": 1.0, "rewards/margins": 2.0945115089416504, "logps/chosen": -313.110595703125, "logps/rejected": -356.1000061035156, "logits/chosen": 5.037275314331055, "logits/rejected": 5.1315507888793945}
{"ts": "2025-12-26T16:33:09", "event": "train_log", "step": 78, "epoch": 0.0910948905109489, "progress_pct": 3.03, "epoch_pct": 3.04, "eta": "18:57:48", "max_grad_norm": 1.0, "loss": 0.1894684135913849, "grad_norm": 0.9839214086532593, "learning_rate": 1.4922480620155039e-05, "rewards/chosen": 1.0605502128601074, "rewards/rejected": -0.8470743894577026, "rewards/accuracies": 1.0, "rewards/margins": 1.90762460231781, "logps/chosen": -366.2629089355469, "logps/rejected": -405.7989196777344, "logits/chosen": 4.817085266113281, "logits/rejected": 4.874035835266113}
{"ts": "2025-12-26T16:33:29", "event": "train_log", "step": 80, "epoch": 0.09343065693430656, "progress_pct": 3.11, "epoch_pct": 3.11, "eta": "18:38:40", "max_grad_norm": 1.0, "loss": 0.15948188304901123, "grad_norm": 0.9212782979011536, "learning_rate": 1.5310077519379846e-05, "rewards/chosen": 0.676516056060791, "rewards/rejected": -1.4909145832061768, "rewards/accuracies": 1.0, "rewards/margins": 2.167430877685547, "logps/chosen": -348.0658264160156, "logps/rejected": -395.23870849609375, "logits/chosen": 5.046716690063477, "logits/rejected": 5.157979965209961}
{"ts": "2025-12-26T16:33:49", "event": "train_log", "step": 82, "epoch": 0.09576642335766423, "progress_pct": 3.19, "epoch_pct": 3.19, "eta": "18:20:47", "max_grad_norm": 1.0, "loss": 0.12085139006376266, "grad_norm": 0.9820688366889954, "learning_rate": 1.569767441860465e-05, "rewards/chosen": 0.8719685077667236, "rewards/rejected": -1.7745698690414429, "rewards/accuracies": 1.0, "rewards/margins": 2.646538257598877, "logps/chosen": -378.8666076660156, "logps/rejected": -436.9100036621094, "logits/chosen": 4.690741539001465, "logits/rejected": 4.771791458129883}
{"ts": "2025-12-26T16:34:09", "event": "train_log", "step": 84, "epoch": 0.09810218978102189, "progress_pct": 3.27, "epoch_pct": 3.27, "eta": "18:03:33", "max_grad_norm": 1.0, "loss": 0.08720710873603821, "grad_norm": 0.66785728931427, "learning_rate": 1.608527131782946e-05, "rewards/chosen": 1.1337480545043945, "rewards/rejected": -1.7701961994171143, "rewards/accuracies": 1.0, "rewards/margins": 2.903944253921509, "logps/chosen": -346.51214599609375, "logps/rejected": -400.1110534667969, "logits/chosen": 4.880465984344482, "logits/rejected": 4.961792945861816}
{"ts": "2025-12-26T16:34:28", "event": "train_log", "step": 86, "epoch": 0.10043795620437956, "progress_pct": 3.35, "epoch_pct": 3.35, "eta": "17:46:40", "max_grad_norm": 1.0, "loss": 0.07942983508110046, "grad_norm": 0.5760660767555237, "learning_rate": 1.647286821705426e-05, "rewards/chosen": 1.2459325790405273, "rewards/rejected": -1.7693227529525757, "rewards/accuracies": 1.0, "rewards/margins": 3.0152552127838135, "logps/chosen": -341.7489318847656, "logps/rejected": -398.322021484375, "logits/chosen": 4.464397430419922, "logits/rejected": 4.680055618286133}
{"ts": "2025-12-26T16:34:48", "event": "train_log", "step": 88, "epoch": 0.10277372262773722, "progress_pct": 3.42, "epoch_pct": 3.43, "eta": "17:30:52", "max_grad_norm": 1.0, "loss": 0.1258174479007721, "grad_norm": 1.6020294427871704, "learning_rate": 1.686046511627907e-05, "rewards/chosen": 1.0706769227981567, "rewards/rejected": -2.0480403900146484, "rewards/accuracies": 0.9375, "rewards/margins": 3.118717670440674, "logps/chosen": -344.9147644042969, "logps/rejected": -395.4453125, "logits/chosen": 4.563863277435303, "logits/rejected": 4.680974960327148}
{"ts": "2025-12-26T16:35:06", "event": "train_log", "step": 90, "epoch": 0.10510948905109489, "progress_pct": 3.5, "epoch_pct": 3.5, "eta": "17:14:58", "max_grad_norm": 1.0, "loss": 0.06663060188293457, "grad_norm": 0.46413859724998474, "learning_rate": 1.7248062015503875e-05, "rewards/chosen": 1.4128761291503906, "rewards/rejected": -2.3478102684020996, "rewards/accuracies": 1.0, "rewards/margins": 3.760685920715332, "logps/chosen": -326.9678649902344, "logps/rejected": -388.4164123535156, "logits/chosen": 4.4989237785339355, "logits/rejected": 4.673248291015625}
{"ts": "2025-12-26T16:35:26", "event": "train_log", "step": 92, "epoch": 0.10744525547445255, "progress_pct": 3.58, "epoch_pct": 3.58, "eta": "17:00:34", "max_grad_norm": 1.0, "loss": 0.04481709748506546, "grad_norm": 0.6699568629264832, "learning_rate": 1.7635658914728684e-05, "rewards/chosen": 1.477597713470459, "rewards/rejected": -2.9012341499328613, "rewards/accuracies": 1.0, "rewards/margins": 4.37883186340332, "logps/chosen": -362.7267150878906, "logps/rejected": -439.2985534667969, "logits/chosen": 4.7294535636901855, "logits/rejected": 4.813880920410156}
{"ts": "2025-12-26T16:35:47", "event": "train_log", "step": 94, "epoch": 0.10978102189781022, "progress_pct": 3.66, "epoch_pct": 3.66, "eta": "16:47:17", "max_grad_norm": 1.0, "loss": 0.05632612109184265, "grad_norm": 0.4152977168560028, "learning_rate": 1.802325581395349e-05, "rewards/chosen": 0.71366286277771, "rewards/rejected": -2.744809150695801, "rewards/accuracies": 1.0, "rewards/margins": 3.4584720134735107, "logps/chosen": -381.59246826171875, "logps/rejected": -444.2817687988281, "logits/chosen": 4.785149574279785, "logits/rejected": 4.891542434692383}
{"ts": "2025-12-26T16:36:07", "event": "train_log", "step": 96, "epoch": 0.11211678832116788, "progress_pct": 3.73, "epoch_pct": 3.74, "eta": "16:34:09", "max_grad_norm": 1.0, "loss": 0.040920041501522064, "grad_norm": 0.3152717649936676, "learning_rate": 1.8410852713178295e-05, "rewards/chosen": 1.7566397190093994, "rewards/rejected": -2.263956069946289, "rewards/accuracies": 1.0, "rewards/margins": 4.020595550537109, "logps/chosen": -356.7286376953125, "logps/rejected": -414.69635009765625, "logits/chosen": 4.603940486907959, "logits/rejected": 4.804995536804199}
{"ts": "2025-12-26T16:36:26", "event": "train_log", "step": 98, "epoch": 0.11445255474452555, "progress_pct": 3.81, "epoch_pct": 3.82, "eta": "16:21:07", "max_grad_norm": 1.0, "loss": 0.025794224813580513, "grad_norm": 0.37698569893836975, "learning_rate": 1.8798449612403103e-05, "rewards/chosen": 1.3867536783218384, "rewards/rejected": -3.2675204277038574, "rewards/accuracies": 1.0, "rewards/margins": 4.6542744636535645, "logps/chosen": -339.794189453125, "logps/rejected": -413.8865966796875, "logits/chosen": 4.558542728424072, "logits/rejected": 4.690641403198242}
{"ts": "2025-12-26T16:36:46", "event": "train_log", "step": 100, "epoch": 0.11678832116788321, "progress_pct": 3.89, "epoch_pct": 3.89, "eta": "16:09:03", "max_grad_norm": 1.0, "loss": 0.015155203640460968, "grad_norm": 0.15023073554039001, "learning_rate": 1.918604651162791e-05, "rewards/chosen": 1.7938623428344727, "rewards/rejected": -3.1486666202545166, "rewards/accuracies": 1.0, "rewards/margins": 4.942529201507568, "logps/chosen": -346.2568054199219, "logps/rejected": -418.9315185546875, "logits/chosen": 4.387497425079346, "logits/rejected": 4.494588375091553}
{"ts": "2025-12-26T16:44:21", "event": "train_log", "step": 100, "epoch": 0.11678832116788321, "progress_pct": 3.89, "epoch_pct": 3.89, "eta": "19:16:19", "max_grad_norm": 1.0, "eval_loss": 0.04428481683135033, "eval_runtime": 454.7251, "eval_samples_per_second": 1.676, "eval_steps_per_second": 1.676, "eval_rewards/chosen": 1.7248634099960327, "eval_rewards/rejected": -2.863647222518921, "eval_rewards/accuracies": 0.9921259880065918, "eval_rewards/margins": 4.588510513305664, "eval_logps/chosen": -353.15850830078125, "eval_logps/rejected": -424.4124755859375, "eval_logits/chosen": 4.285891056060791, "eval_logits/rejected": 4.425926208496094}
{"ts": "2025-12-26T16:44:42", "event": "train_log", "step": 102, "epoch": 0.11912408759124088, "progress_pct": 3.97, "epoch_pct": 3.97, "eta": "19:01:01", "max_grad_norm": 1.0, "loss": 0.01589718647301197, "grad_norm": 0.21237261593341827, "learning_rate": 1.9573643410852714e-05, "rewards/chosen": 1.7697646617889404, "rewards/rejected": -3.025937557220459, "rewards/accuracies": 1.0, "rewards/margins": 4.79570198059082, "logps/chosen": -305.01165771484375, "logps/rejected": -384.8538818359375, "logits/chosen": 4.197369575500488, "logits/rejected": 4.352917671203613}
{"ts": "2025-12-26T16:45:01", "event": "train_log", "step": 104, "epoch": 0.12145985401459854, "progress_pct": 4.05, "epoch_pct": 4.05, "eta": "18:45:50", "max_grad_norm": 1.0, "loss": 0.038177840411663055, "grad_norm": 1.1960583925247192, "learning_rate": 1.996124031007752e-05, "rewards/chosen": 1.556309461593628, "rewards/rejected": -3.2670814990997314, "rewards/accuracies": 1.0, "rewards/margins": 4.823390960693359, "logps/chosen": -341.10675048828125, "logps/rejected": -417.59613037109375, "logits/chosen": 4.184627056121826, "logits/rejected": 4.280352592468262}
{"ts": "2025-12-26T16:45:21", "event": "train_log", "step": 106, "epoch": 0.12379562043795621, "progress_pct": 4.12, "epoch_pct": 4.13, "eta": "18:31:17", "max_grad_norm": 1.0, "loss": 0.056792374700307846, "grad_norm": 1.3021241426467896, "learning_rate": 2.0348837209302328e-05, "rewards/chosen": 1.6538318395614624, "rewards/rejected": -3.0760293006896973, "rewards/accuracies": 1.0, "rewards/margins": 4.729861736297607, "logps/chosen": -358.1336669921875, "logps/rejected": -426.8945617675781, "logits/chosen": 4.32430362701416, "logits/rejected": 4.451810359954834}
{"ts": "2025-12-26T16:45:41", "event": "train_log", "step": 108, "epoch": 0.12613138686131387, "progress_pct": 4.2, "epoch_pct": 4.2, "eta": "18:17:24", "max_grad_norm": 1.0, "loss": 0.07614695280790329, "grad_norm": 0.3007296025753021, "learning_rate": 2.0736434108527133e-05, "rewards/chosen": 1.4121378660202026, "rewards/rejected": -3.331850051879883, "rewards/accuracies": 0.9375, "rewards/margins": 4.743987560272217, "logps/chosen": -364.4995422363281, "logps/rejected": -434.4844055175781, "logits/chosen": 4.4918341636657715, "logits/rejected": 4.6333909034729}
{"ts": "2025-12-26T16:45:59", "event": "train_log", "step": 110, "epoch": 0.12846715328467154, "progress_pct": 4.28, "epoch_pct": 4.28, "eta": "18:03:33", "max_grad_norm": 1.0, "loss": 0.014600476250052452, "grad_norm": 0.42474085092544556, "learning_rate": 2.1124031007751938e-05, "rewards/chosen": 1.958223819732666, "rewards/rejected": -4.051264762878418, "rewards/accuracies": 1.0, "rewards/margins": 6.009488582611084, "logps/chosen": -306.4935607910156, "logps/rejected": -392.5444030761719, "logits/chosen": 3.857876777648926, "logits/rejected": 3.9678285121917725}
{"ts": "2025-12-26T16:46:19", "event": "train_log", "step": 112, "epoch": 0.1308029197080292, "progress_pct": 4.36, "epoch_pct": 4.36, "eta": "17:50:24", "max_grad_norm": 1.0, "loss": 0.010151136666536331, "grad_norm": 0.14177864789962769, "learning_rate": 2.1511627906976744e-05, "rewards/chosen": 2.196099281311035, "rewards/rejected": -3.75758695602417, "rewards/accuracies": 1.0, "rewards/margins": 5.953686237335205, "logps/chosen": -339.5606689453125, "logps/rejected": -425.51361083984375, "logits/chosen": 4.254065036773682, "logits/rejected": 4.352800369262695}
{"ts": "2025-12-26T16:46:40", "event": "train_log", "step": 114, "epoch": 0.13313868613138685, "progress_pct": 4.43, "epoch_pct": 4.44, "eta": "17:38:30", "max_grad_norm": 1.0, "loss": 0.011391772888600826, "grad_norm": 0.29438889026641846, "learning_rate": 2.1899224806201552e-05, "rewards/chosen": 1.9949897527694702, "rewards/rejected": -3.3917016983032227, "rewards/accuracies": 1.0, "rewards/margins": 5.386691093444824, "logps/chosen": -349.3886413574219, "logps/rejected": -431.79925537109375, "logits/chosen": 3.7171452045440674, "logits/rejected": 3.9224042892456055}
{"ts": "2025-12-26T16:47:00", "event": "train_log", "step": 116, "epoch": 0.13547445255474452, "progress_pct": 4.51, "epoch_pct": 4.52, "eta": "17:26:32", "max_grad_norm": 1.0, "loss": 0.024509863927960396, "grad_norm": 0.9541389346122742, "learning_rate": 2.2286821705426357e-05, "rewards/chosen": 1.8549680709838867, "rewards/rejected": -3.4747393131256104, "rewards/accuracies": 1.0, "rewards/margins": 5.329707622528076, "logps/chosen": -343.19482421875, "logps/rejected": -423.23565673828125, "logits/chosen": 3.5138039588928223, "logits/rejected": 3.7400965690612793}
{"ts": "2025-12-26T16:47:21", "event": "train_log", "step": 118, "epoch": 0.1378102189781022, "progress_pct": 4.59, "epoch_pct": 4.59, "eta": "17:15:03", "max_grad_norm": 1.0, "loss": 0.007583940401673317, "grad_norm": 0.45693957805633545, "learning_rate": 2.2674418604651163e-05, "rewards/chosen": 2.130192518234253, "rewards/rejected": -4.364559650421143, "rewards/accuracies": 1.0, "rewards/margins": 6.494752407073975, "logps/chosen": -382.1067810058594, "logps/rejected": -480.72265625, "logits/chosen": 3.9002795219421387, "logits/rejected": 3.9630849361419678}
{"ts": "2025-12-26T16:47:41", "event": "train_log", "step": 120, "epoch": 0.14014598540145987, "progress_pct": 4.67, "epoch_pct": 4.67, "eta": "17:03:44", "max_grad_norm": 1.0, "loss": 0.007748167496174574, "grad_norm": 0.20826944708824158, "learning_rate": 2.3062015503875968e-05, "rewards/chosen": 1.398924469947815, "rewards/rejected": -4.580015182495117, "rewards/accuracies": 1.0, "rewards/margins": 5.978940010070801, "logps/chosen": -355.2779541015625, "logps/rejected": -436.54022216796875, "logits/chosen": 3.7722253799438477, "logits/rejected": 3.939023494720459}
{"ts": "2025-12-26T16:48:01", "event": "train_log", "step": 122, "epoch": 0.1424817518248175, "progress_pct": 4.75, "epoch_pct": 4.75, "eta": "16:52:48", "max_grad_norm": 1.0, "loss": 0.014359460212290287, "grad_norm": 0.21926206350326538, "learning_rate": 2.3449612403100777e-05, "rewards/chosen": 1.1770455837249756, "rewards/rejected": -5.205078125, "rewards/accuracies": 1.0, "rewards/margins": 6.382123947143555, "logps/chosen": -327.1947326660156, "logps/rejected": -414.7738037109375, "logits/chosen": 3.656745672225952, "logits/rejected": 3.875434160232544}
{"ts": "2025-12-26T16:48:21", "event": "train_log", "step": 124, "epoch": 0.14481751824817518, "progress_pct": 4.82, "epoch_pct": 4.83, "eta": "16:42:21", "max_grad_norm": 1.0, "loss": 0.007621760480105877, "grad_norm": 0.03550998866558075, "learning_rate": 2.3837209302325582e-05, "rewards/chosen": 0.7802913188934326, "rewards/rejected": -6.6151628494262695, "rewards/accuracies": 1.0, "rewards/margins": 7.395453453063965, "logps/chosen": -369.8974304199219, "logps/rejected": -473.97283935546875, "logits/chosen": 3.659773826599121, "logits/rejected": 3.725044012069702}
{"ts": "2025-12-26T16:56:05", "event": "train_log", "step": 125, "epoch": 0.145985401459854, "progress_pct": 4.86, "epoch_pct": 4.87, "eta": "19:05:16", "max_grad_norm": 1.0, "eval_loss": 0.024107323959469795, "eval_runtime": 454.8045, "eval_samples_per_second": 1.675, "eval_steps_per_second": 1.675, "eval_rewards/chosen": 0.5319492816925049, "eval_rewards/rejected": -6.150709629058838, "eval_rewards/accuracies": 0.9934383034706116, "eval_rewards/margins": 6.682660102844238, "eval_logps/chosen": -365.087646484375, "eval_logps/rejected": -457.28314208984375, "eval_logits/chosen": 3.6694726943969727, "eval_logits/rejected": 3.8436598777770996}
{"ts": "2025-12-26T16:56:15", "event": "train_log", "step": 126, "epoch": 0.14715328467153285, "progress_pct": 4.9, "epoch_pct": 4.91, "eta": "18:59:00", "max_grad_norm": 1.0, "loss": 0.005531508009880781, "grad_norm": 0.21691419184207916, "learning_rate": 2.4224806201550387e-05, "rewards/chosen": 0.9075853824615479, "rewards/rejected": -7.027284622192383, "rewards/accuracies": 1.0, "rewards/margins": 7.934869289398193, "logps/chosen": -345.18023681640625, "logps/rejected": -454.6177978515625, "logits/chosen": 3.777791738510132, "logits/rejected": 3.7573630809783936}
{"ts": "2025-12-26T16:56:36", "event": "train_log", "step": 128, "epoch": 0.14948905109489052, "progress_pct": 4.98, "epoch_pct": 4.98, "eta": "18:46:50", "max_grad_norm": 1.0, "loss": 0.0008547124452888966, "grad_norm": 0.0514506921172142, "learning_rate": 2.4612403100775196e-05, "rewards/chosen": 1.0864180326461792, "rewards/rejected": -6.75621223449707, "rewards/accuracies": 1.0, "rewards/margins": 7.842630863189697, "logps/chosen": -376.30023193359375, "logps/rejected": -486.30615234375, "logits/chosen": 3.6862380504608154, "logits/rejected": 3.77681827545166}
{"ts": "2025-12-26T16:56:54", "event": "train_log", "step": 130, "epoch": 0.15182481751824817, "progress_pct": 5.06, "epoch_pct": 5.06, "eta": "18:34:28", "max_grad_norm": 1.0, "loss": 0.019211476668715477, "grad_norm": 1.0013993978500366, "learning_rate": 2.5e-05, "rewards/chosen": 0.7987843751907349, "rewards/rejected": -6.31362247467041, "rewards/accuracies": 1.0, "rewards/margins": 7.1124067306518555, "logps/chosen": -330.2728271484375, "logps/rejected": -420.1920166015625, "logits/chosen": 3.8558738231658936, "logits/rejected": 4.067385673522949}
{"ts": "2025-12-26T16:57:14", "event": "train_log", "step": 132, "epoch": 0.15416058394160584, "progress_pct": 5.13, "epoch_pct": 5.14, "eta": "18:22:39", "max_grad_norm": 1.0, "loss": 0.005051509942859411, "grad_norm": 0.2909312844276428, "learning_rate": 2.5387596899224806e-05, "rewards/chosen": 0.7269927859306335, "rewards/rejected": -6.733253479003906, "rewards/accuracies": 1.0, "rewards/margins": 7.4602460861206055, "logps/chosen": -346.632568359375, "logps/rejected": -448.4364318847656, "logits/chosen": 3.8564915657043457, "logits/rejected": 4.106588363647461}
{"ts": "2025-12-26T16:57:34", "event": "train_log", "step": 134, "epoch": 0.1564963503649635, "progress_pct": 5.21, "epoch_pct": 5.22, "eta": "18:11:24", "max_grad_norm": 1.0, "loss": 0.029044320806860924, "grad_norm": 0.10341063886880875, "learning_rate": 2.5775193798449615e-05, "rewards/chosen": -0.15517807006835938, "rewards/rejected": -7.108559608459473, "rewards/accuracies": 1.0, "rewards/margins": 6.953381538391113, "logps/chosen": -398.5205078125, "logps/rejected": -493.3382568359375, "logits/chosen": 3.6923415660858154, "logits/rejected": 3.8758797645568848}
{"ts": "2025-12-26T16:57:55", "event": "train_log", "step": 136, "epoch": 0.15883211678832118, "progress_pct": 5.29, "epoch_pct": 5.29, "eta": "18:00:50", "max_grad_norm": 1.0, "loss": 0.008300668559968472, "grad_norm": 0.40827327966690063, "learning_rate": 2.616279069767442e-05, "rewards/chosen": 0.3356212377548218, "rewards/rejected": -6.36344051361084, "rewards/accuracies": 1.0, "rewards/margins": 6.699062347412109, "logps/chosen": -420.5874328613281, "logps/rejected": -511.71661376953125, "logits/chosen": 3.701347827911377, "logits/rejected": 3.8854856491088867}
{"ts": "2025-12-26T16:58:15", "event": "train_log", "step": 138, "epoch": 0.16116788321167883, "progress_pct": 5.37, "epoch_pct": 5.37, "eta": "17:50:12", "max_grad_norm": 1.0, "loss": 0.010793081484735012, "grad_norm": 0.17690710723400116, "learning_rate": 2.655038759689923e-05, "rewards/chosen": 1.5296471118927002, "rewards/rejected": -5.799461364746094, "rewards/accuracies": 1.0, "rewards/margins": 7.329109191894531, "logps/chosen": -361.59417724609375, "logps/rejected": -455.0230407714844, "logits/chosen": 3.476500988006592, "logits/rejected": 3.6296494007110596}
{"ts": "2025-12-26T16:58:35", "event": "train_log", "step": 140, "epoch": 0.1635036496350365, "progress_pct": 5.45, "epoch_pct": 5.45, "eta": "17:39:44", "max_grad_norm": 1.0, "loss": 0.012777667492628098, "grad_norm": 0.15591435134410858, "learning_rate": 2.693798449612403e-05, "rewards/chosen": 1.2819935083389282, "rewards/rejected": -6.812654972076416, "rewards/accuracies": 1.0, "rewards/margins": 8.094648361206055, "logps/chosen": -379.35333251953125, "logps/rejected": -490.0003356933594, "logits/chosen": 3.440129518508911, "logits/rejected": 3.5673890113830566}
{"ts": "2025-12-26T16:58:56", "event": "train_log", "step": 142, "epoch": 0.16583941605839417, "progress_pct": 5.52, "epoch_pct": 5.53, "eta": "17:29:50", "max_grad_norm": 1.0, "loss": 0.007118214387446642, "grad_norm": 0.820688009262085, "learning_rate": 2.7325581395348836e-05, "rewards/chosen": 1.4685018062591553, "rewards/rejected": -6.558856964111328, "rewards/accuracies": 1.0, "rewards/margins": 8.027359008789062, "logps/chosen": -402.8253479003906, "logps/rejected": -506.32000732421875, "logits/chosen": 3.23529052734375, "logits/rejected": 3.393266201019287}