{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.2731018246027075, "eval_steps": 50, "global_step": 1450, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.015695507161075144, "grad_norm": 0.07061820477247238, "learning_rate": 4.999451708687114e-06, "logits/chosen": 15.001790046691895, "logits/rejected": 14.624488830566406, "logps/chosen": -0.33085882663726807, "logps/rejected": -0.24924471974372864, "loss": 1.0519, "rewards/accuracies": 0.23749999701976776, "rewards/chosen": -0.4962882399559021, "rewards/margins": -0.12242116779088974, "rewards/rejected": -0.37386709451675415, "step": 10 }, { "epoch": 0.03139101432215029, "grad_norm": 0.060370542109012604, "learning_rate": 4.997807075247147e-06, "logits/chosen": 15.272351264953613, "logits/rejected": 14.801017761230469, "logps/chosen": -0.3379867672920227, "logps/rejected": -0.24759705364704132, "loss": 1.0494, "rewards/accuracies": 0.15000000596046448, "rewards/chosen": -0.5069801211357117, "rewards/margins": -0.13558456301689148, "rewards/rejected": -0.3713955581188202, "step": 20 }, { "epoch": 0.047086521483225424, "grad_norm": 0.050332240760326385, "learning_rate": 4.9950668210706795e-06, "logits/chosen": 15.569372177124023, "logits/rejected": 15.249380111694336, "logps/chosen": -0.3347483277320862, "logps/rejected": -0.275604784488678, "loss": 1.0375, "rewards/accuracies": 0.21250000596046448, "rewards/chosen": -0.5021225214004517, "rewards/margins": -0.08871528506278992, "rewards/rejected": -0.41340717673301697, "step": 30 }, { "epoch": 0.06278202864430057, "grad_norm": 0.054660990834236145, "learning_rate": 4.9912321481237616e-06, "logits/chosen": 15.344067573547363, "logits/rejected": 14.881669998168945, "logps/chosen": -0.3336474299430847, "logps/rejected": -0.27252259850502014, "loss": 1.0375, "rewards/accuracies": 0.20000000298023224, "rewards/chosen": -0.5004712343215942, "rewards/margins": -0.09168727695941925, "rewards/rejected": -0.40878385305404663, "step": 40 }, { "epoch": 0.07847753580537571, "grad_norm": 0.060405269265174866, "learning_rate": 4.986304738420684e-06, "logits/chosen": 15.5701904296875, "logits/rejected": 15.60998821258545, "logps/chosen": -0.3075069785118103, "logps/rejected": -0.24850216507911682, "loss": 1.0341, "rewards/accuracies": 0.20000000298023224, "rewards/chosen": -0.46126049757003784, "rewards/margins": -0.08850721269845963, "rewards/rejected": -0.3727532923221588, "step": 50 }, { "epoch": 0.07847753580537571, "eval_logits/chosen": 15.719181060791016, "eval_logits/rejected": 15.20205307006836, "eval_logps/chosen": -0.32490479946136475, "eval_logps/rejected": -0.26058924198150635, "eval_loss": 1.0295902490615845, "eval_rewards/accuracies": 0.26923078298568726, "eval_rewards/chosen": -0.48735716938972473, "eval_rewards/margins": -0.09647335112094879, "eval_rewards/rejected": -0.39088380336761475, "eval_runtime": 14.6102, "eval_samples_per_second": 28.199, "eval_steps_per_second": 3.559, "step": 50 }, { "epoch": 0.09417304296645085, "grad_norm": 0.06511708348989487, "learning_rate": 4.980286753286196e-06, "logits/chosen": 15.571348190307617, "logits/rejected": 15.418828010559082, "logps/chosen": -0.3217025101184845, "logps/rejected": -0.2813836932182312, "loss": 1.0385, "rewards/accuracies": 0.23749999701976776, "rewards/chosen": -0.48255378007888794, "rewards/margins": -0.060478221625089645, "rewards/rejected": -0.4220755696296692, "step": 60 }, { "epoch": 0.109868550127526, "grad_norm": 0.06922140717506409, "learning_rate": 4.973180832407471e-06, "logits/chosen": 15.926614761352539, "logits/rejected": 15.90565299987793, "logps/chosen": -0.34742942452430725, "logps/rejected": -0.26853513717651367, "loss": 1.0417, "rewards/accuracies": 0.21250000596046448, "rewards/chosen": -0.5211440324783325, "rewards/margins": -0.11834144592285156, "rewards/rejected": -0.40280264616012573, "step": 70 }, { "epoch": 0.12556405728860115, "grad_norm": 0.07853339612483978, "learning_rate": 4.964990092676263e-06, "logits/chosen": 15.876957893371582, "logits/rejected": 15.636863708496094, "logps/chosen": -0.34999752044677734, "logps/rejected": -0.2652502655982971, "loss": 1.0255, "rewards/accuracies": 0.1875, "rewards/chosen": -0.524996280670166, "rewards/margins": -0.12712089717388153, "rewards/rejected": -0.3978753685951233, "step": 80 }, { "epoch": 0.14125956444967627, "grad_norm": 0.07262148708105087, "learning_rate": 4.9557181268217225e-06, "logits/chosen": 16.037456512451172, "logits/rejected": 15.742408752441406, "logps/chosen": -0.32482510805130005, "logps/rejected": -0.2520079016685486, "loss": 1.0297, "rewards/accuracies": 0.21250000596046448, "rewards/chosen": -0.48723769187927246, "rewards/margins": -0.1092257872223854, "rewards/rejected": -0.3780118525028229, "step": 90 }, { "epoch": 0.15695507161075142, "grad_norm": 0.08407289534807205, "learning_rate": 4.9453690018345144e-06, "logits/chosen": 16.34904670715332, "logits/rejected": 16.30767059326172, "logps/chosen": -0.3302846848964691, "logps/rejected": -0.2799247205257416, "loss": 1.0285, "rewards/accuracies": 0.2750000059604645, "rewards/chosen": -0.4954269826412201, "rewards/margins": -0.07553993165493011, "rewards/rejected": -0.41988706588745117, "step": 100 }, { "epoch": 0.15695507161075142, "eval_logits/chosen": 16.43848419189453, "eval_logits/rejected": 15.978095054626465, "eval_logps/chosen": -0.3256901502609253, "eval_logps/rejected": -0.2794351279735565, "eval_loss": 1.0174708366394043, "eval_rewards/accuracies": 0.2884615361690521, "eval_rewards/chosen": -0.4885352551937103, "eval_rewards/margins": -0.06938254088163376, "eval_rewards/rejected": -0.41915270686149597, "eval_runtime": 14.607, "eval_samples_per_second": 28.206, "eval_steps_per_second": 3.56, "step": 100 }, { "epoch": 0.17265057877182657, "grad_norm": 0.07448805868625641, "learning_rate": 4.933947257182901e-06, "logits/chosen": 16.681476593017578, "logits/rejected": 16.208908081054688, "logps/chosen": -0.3410753309726715, "logps/rejected": -0.28177398443222046, "loss": 1.0364, "rewards/accuracies": 0.2874999940395355, "rewards/chosen": -0.5116130113601685, "rewards/margins": -0.08895199000835419, "rewards/rejected": -0.4226610064506531, "step": 110 }, { "epoch": 0.1883460859329017, "grad_norm": 0.17266640067100525, "learning_rate": 4.921457902821578e-06, "logits/chosen": 16.73276710510254, "logits/rejected": 16.46255111694336, "logps/chosen": -0.30808666348457336, "logps/rejected": -0.2663067877292633, "loss": 1.0242, "rewards/accuracies": 0.23749999701976776, "rewards/chosen": -0.46213001012802124, "rewards/margins": -0.0626697838306427, "rewards/rejected": -0.39946022629737854, "step": 120 }, { "epoch": 0.20404159309397685, "grad_norm": 0.1035998985171318, "learning_rate": 4.907906416994146e-06, "logits/chosen": 16.380239486694336, "logits/rejected": 16.233612060546875, "logps/chosen": -0.32250356674194336, "logps/rejected": -0.27460020780563354, "loss": 1.0162, "rewards/accuracies": 0.2874999940395355, "rewards/chosen": -0.48375529050827026, "rewards/margins": -0.0718550831079483, "rewards/rejected": -0.41190028190612793, "step": 130 }, { "epoch": 0.219737100255052, "grad_norm": 0.0961030125617981, "learning_rate": 4.893298743830168e-06, "logits/chosen": 16.440303802490234, "logits/rejected": 16.233903884887695, "logps/chosen": -0.33421438932418823, "logps/rejected": -0.2857271134853363, "loss": 1.0008, "rewards/accuracies": 0.3125, "rewards/chosen": -0.5013214945793152, "rewards/margins": -0.07273083180189133, "rewards/rejected": -0.42859068512916565, "step": 140 }, { "epoch": 0.23543260741612712, "grad_norm": 0.14799565076828003, "learning_rate": 4.8776412907378845e-06, "logits/chosen": 16.600738525390625, "logits/rejected": 16.536447525024414, "logps/chosen": -0.3243326246738434, "logps/rejected": -0.3061785101890564, "loss": 1.0085, "rewards/accuracies": 0.3375000059604645, "rewards/chosen": -0.4864989221096039, "rewards/margins": -0.027231160551309586, "rewards/rejected": -0.459267795085907, "step": 150 }, { "epoch": 0.23543260741612712, "eval_logits/chosen": 16.8078556060791, "eval_logits/rejected": 16.311922073364258, "eval_logps/chosen": -0.326242595911026, "eval_logps/rejected": -0.3398977816104889, "eval_loss": 0.9791463017463684, "eval_rewards/accuracies": 0.4038461446762085, "eval_rewards/chosen": -0.4893638789653778, "eval_rewards/margins": 0.020482787862420082, "eval_rewards/rejected": -0.5098467469215393, "eval_runtime": 14.6072, "eval_samples_per_second": 28.205, "eval_steps_per_second": 3.56, "step": 150 }, { "epoch": 0.2511281145772023, "grad_norm": 0.11464422941207886, "learning_rate": 4.860940925593703e-06, "logits/chosen": 16.586620330810547, "logits/rejected": 16.253028869628906, "logps/chosen": -0.33331993222236633, "logps/rejected": -0.35580095648765564, "loss": 0.9827, "rewards/accuracies": 0.42500001192092896, "rewards/chosen": -0.49997982382774353, "rewards/margins": 0.03372158855199814, "rewards/rejected": -0.5337014198303223, "step": 160 }, { "epoch": 0.2668236217382774, "grad_norm": 0.09462621062994003, "learning_rate": 4.84320497372973e-06, "logits/chosen": 16.220312118530273, "logits/rejected": 16.105356216430664, "logps/chosen": -0.2957116663455963, "logps/rejected": -0.3528788089752197, "loss": 0.9716, "rewards/accuracies": 0.4625000059604645, "rewards/chosen": -0.44356757402420044, "rewards/margins": 0.08575066924095154, "rewards/rejected": -0.5293182134628296, "step": 170 }, { "epoch": 0.28251912889935255, "grad_norm": 0.10995513945817947, "learning_rate": 4.824441214720629e-06, "logits/chosen": 16.811044692993164, "logits/rejected": 16.43205451965332, "logps/chosen": -0.3263992369174957, "logps/rejected": -0.35878634452819824, "loss": 0.9546, "rewards/accuracies": 0.4124999940395355, "rewards/chosen": -0.4895988404750824, "rewards/margins": 0.04858064278960228, "rewards/rejected": -0.5381795167922974, "step": 180 }, { "epoch": 0.2982146360604277, "grad_norm": 0.1348036825656891, "learning_rate": 4.804657878971252e-06, "logits/chosen": 16.816158294677734, "logits/rejected": 16.55413055419922, "logps/chosen": -0.31842875480651855, "logps/rejected": -0.3791810870170593, "loss": 0.9472, "rewards/accuracies": 0.5249999761581421, "rewards/chosen": -0.47764310240745544, "rewards/margins": 0.09112847596406937, "rewards/rejected": -0.5687715411186218, "step": 190 }, { "epoch": 0.31391014322150285, "grad_norm": 0.13393694162368774, "learning_rate": 4.783863644106502e-06, "logits/chosen": 17.075885772705078, "logits/rejected": 16.982004165649414, "logps/chosen": -0.3368823528289795, "logps/rejected": -0.3636801540851593, "loss": 0.9455, "rewards/accuracies": 0.375, "rewards/chosen": -0.5053235292434692, "rewards/margins": 0.04019671678543091, "rewards/rejected": -0.5455202460289001, "step": 200 }, { "epoch": 0.31391014322150285, "eval_logits/chosen": 17.17239761352539, "eval_logits/rejected": 16.609193801879883, "eval_logps/chosen": -0.33508703112602234, "eval_logps/rejected": -0.4493505656719208, "eval_loss": 0.9283667802810669, "eval_rewards/accuracies": 0.4615384638309479, "eval_rewards/chosen": -0.5026305913925171, "eval_rewards/margins": 0.17139528691768646, "eval_rewards/rejected": -0.67402583360672, "eval_runtime": 14.5913, "eval_samples_per_second": 28.236, "eval_steps_per_second": 3.564, "step": 200 }, { "epoch": 0.329605650382578, "grad_norm": 0.14985737204551697, "learning_rate": 4.762067631165049e-06, "logits/chosen": 16.92913246154785, "logits/rejected": 16.648632049560547, "logps/chosen": -0.3326043486595154, "logps/rejected": -0.4218205511569977, "loss": 0.9225, "rewards/accuracies": 0.48750001192092896, "rewards/chosen": -0.4989064335823059, "rewards/margins": 0.13382436335086823, "rewards/rejected": -0.6327308416366577, "step": 210 }, { "epoch": 0.34530115754365315, "grad_norm": 0.16972233355045319, "learning_rate": 4.7392794005985324e-06, "logits/chosen": 17.074562072753906, "logits/rejected": 16.863161087036133, "logps/chosen": -0.3645358383655548, "logps/rejected": -0.5221719145774841, "loss": 0.9264, "rewards/accuracies": 0.512499988079071, "rewards/chosen": -0.5468038320541382, "rewards/margins": 0.23645417392253876, "rewards/rejected": -0.7832580208778381, "step": 220 }, { "epoch": 0.3609966647047283, "grad_norm": 0.20796354115009308, "learning_rate": 4.715508948078037e-06, "logits/chosen": 17.4168643951416, "logits/rejected": 17.00813102722168, "logps/chosen": -0.35443297028541565, "logps/rejected": -0.5115998983383179, "loss": 0.9037, "rewards/accuracies": 0.512499988079071, "rewards/chosen": -0.5316494703292847, "rewards/margins": 0.23575039207935333, "rewards/rejected": -0.767399787902832, "step": 230 }, { "epoch": 0.3766921718658034, "grad_norm": 0.1932348757982254, "learning_rate": 4.690766700109659e-06, "logits/chosen": 17.034719467163086, "logits/rejected": 16.65166664123535, "logps/chosen": -0.3426091969013214, "logps/rejected": -0.47884297370910645, "loss": 0.9154, "rewards/accuracies": 0.5625, "rewards/chosen": -0.5139138102531433, "rewards/margins": 0.20435063540935516, "rewards/rejected": -0.7182644605636597, "step": 240 }, { "epoch": 0.39238767902687854, "grad_norm": 1.016450047492981, "learning_rate": 4.665063509461098e-06, "logits/chosen": 16.935081481933594, "logits/rejected": 16.65024185180664, "logps/chosen": -0.41738080978393555, "logps/rejected": -0.48515433073043823, "loss": 0.8774, "rewards/accuracies": 0.42500001192092896, "rewards/chosen": -0.6260712146759033, "rewards/margins": 0.10166029632091522, "rewards/rejected": -0.7277315258979797, "step": 250 }, { "epoch": 0.39238767902687854, "eval_logits/chosen": 17.221881866455078, "eval_logits/rejected": 16.536666870117188, "eval_logps/chosen": -0.3716265559196472, "eval_logps/rejected": -0.87992262840271, "eval_loss": 0.8047741651535034, "eval_rewards/accuracies": 0.5, "eval_rewards/chosen": -0.5574398636817932, "eval_rewards/margins": 0.7624441981315613, "eval_rewards/rejected": -1.3198840618133545, "eval_runtime": 14.6008, "eval_samples_per_second": 28.218, "eval_steps_per_second": 3.561, "step": 250 }, { "epoch": 0.4080831861879537, "grad_norm": 0.2831684648990631, "learning_rate": 4.638410650401267e-06, "logits/chosen": 17.084096908569336, "logits/rejected": 16.564823150634766, "logps/chosen": -0.38100525736808777, "logps/rejected": -0.8173269033432007, "loss": 0.8197, "rewards/accuracies": 0.4375, "rewards/chosen": -0.5715079307556152, "rewards/margins": 0.6544824838638306, "rewards/rejected": -1.2259904146194458, "step": 260 }, { "epoch": 0.42377869334902885, "grad_norm": 0.9195305109024048, "learning_rate": 4.610819813755038e-06, "logits/chosen": 17.316537857055664, "logits/rejected": 16.623016357421875, "logps/chosen": -0.4713365435600281, "logps/rejected": -1.2184536457061768, "loss": 0.7493, "rewards/accuracies": 0.4375, "rewards/chosen": -0.7070047855377197, "rewards/margins": 1.120675802230835, "rewards/rejected": -1.8276805877685547, "step": 270 }, { "epoch": 0.439474200510104, "grad_norm": 0.5542411804199219, "learning_rate": 4.582303101775249e-06, "logits/chosen": 17.173168182373047, "logits/rejected": 16.759702682495117, "logps/chosen": -0.4629506468772888, "logps/rejected": -1.3020483255386353, "loss": 0.7638, "rewards/accuracies": 0.637499988079071, "rewards/chosen": -0.6944260597229004, "rewards/margins": 1.2586463689804077, "rewards/rejected": -1.9530725479125977, "step": 280 }, { "epoch": 0.45516970767117915, "grad_norm": 0.2836654782295227, "learning_rate": 4.55287302283426e-06, "logits/chosen": 17.022424697875977, "logits/rejected": 16.43834114074707, "logps/chosen": -0.527222216129303, "logps/rejected": -1.632965087890625, "loss": 0.7466, "rewards/accuracies": 0.6625000238418579, "rewards/chosen": -0.7908332943916321, "rewards/margins": 1.6586145162582397, "rewards/rejected": -2.4494476318359375, "step": 290 }, { "epoch": 0.47086521483225424, "grad_norm": 0.658358097076416, "learning_rate": 4.522542485937369e-06, "logits/chosen": 16.6541690826416, "logits/rejected": 16.34103012084961, "logps/chosen": -0.50589519739151, "logps/rejected": -1.8910831212997437, "loss": 0.6982, "rewards/accuracies": 0.699999988079071, "rewards/chosen": -0.7588427662849426, "rewards/margins": 2.077782154083252, "rewards/rejected": -2.8366246223449707, "step": 300 }, { "epoch": 0.47086521483225424, "eval_logits/chosen": 16.950870513916016, "eval_logits/rejected": 16.154659271240234, "eval_logps/chosen": -0.5594518184661865, "eval_logps/rejected": -1.9617934226989746, "eval_loss": 0.7422243356704712, "eval_rewards/accuracies": 0.7115384340286255, "eval_rewards/chosen": -0.839177668094635, "eval_rewards/margins": 2.103512763977051, "eval_rewards/rejected": -2.942690372467041, "eval_runtime": 14.5969, "eval_samples_per_second": 28.225, "eval_steps_per_second": 3.562, "step": 300 }, { "epoch": 0.4865607219933294, "grad_norm": 1.1044840812683105, "learning_rate": 4.491324795060491e-06, "logits/chosen": 17.233802795410156, "logits/rejected": 16.292484283447266, "logps/chosen": -0.5940151214599609, "logps/rejected": -2.041588306427002, "loss": 0.7415, "rewards/accuracies": 0.6625000238418579, "rewards/chosen": -0.8910226821899414, "rewards/margins": 2.1713600158691406, "rewards/rejected": -3.062382459640503, "step": 310 }, { "epoch": 0.5022562291544046, "grad_norm": 0.524356484413147, "learning_rate": 4.4592336433146e-06, "logits/chosen": 17.155719757080078, "logits/rejected": 16.328996658325195, "logps/chosen": -0.6095865964889526, "logps/rejected": -1.831730604171753, "loss": 0.7249, "rewards/accuracies": 0.6499999761581421, "rewards/chosen": -0.9143797755241394, "rewards/margins": 1.8332160711288452, "rewards/rejected": -2.747596025466919, "step": 320 }, { "epoch": 0.5179517363154797, "grad_norm": 0.4383145570755005, "learning_rate": 4.426283106939474e-06, "logits/chosen": 16.774551391601562, "logits/rejected": 16.532238006591797, "logps/chosen": -0.669482946395874, "logps/rejected": -1.7058660984039307, "loss": 0.6868, "rewards/accuracies": 0.6625000238418579, "rewards/chosen": -1.004224419593811, "rewards/margins": 1.5545748472213745, "rewards/rejected": -2.5587992668151855, "step": 330 }, { "epoch": 0.5336472434765548, "grad_norm": 3.194026231765747, "learning_rate": 4.3924876391293915e-06, "logits/chosen": 16.963787078857422, "logits/rejected": 16.3092041015625, "logps/chosen": -0.7091449499130249, "logps/rejected": -2.1812453269958496, "loss": 0.706, "rewards/accuracies": 0.7250000238418579, "rewards/chosen": -1.0637174844741821, "rewards/margins": 2.208150863647461, "rewards/rejected": -3.2718684673309326, "step": 340 }, { "epoch": 0.5493427506376299, "grad_norm": 0.5639687776565552, "learning_rate": 4.357862063693486e-06, "logits/chosen": 17.019062042236328, "logits/rejected": 16.315940856933594, "logps/chosen": -0.8996315002441406, "logps/rejected": -2.0307648181915283, "loss": 0.674, "rewards/accuracies": 0.75, "rewards/chosen": -1.349447250366211, "rewards/margins": 1.696699857711792, "rewards/rejected": -3.046147108078003, "step": 350 }, { "epoch": 0.5493427506376299, "eval_logits/chosen": 16.70261001586914, "eval_logits/rejected": 15.845681190490723, "eval_logps/chosen": -0.9138904809951782, "eval_logps/rejected": -2.5003392696380615, "eval_loss": 0.6938430070877075, "eval_rewards/accuracies": 0.8461538553237915, "eval_rewards/chosen": -1.3708356618881226, "eval_rewards/margins": 2.3796732425689697, "eval_rewards/rejected": -3.75050950050354, "eval_runtime": 14.6072, "eval_samples_per_second": 28.205, "eval_steps_per_second": 3.56, "step": 350 }, { "epoch": 0.5650382577987051, "grad_norm": 0.6917555928230286, "learning_rate": 4.322421568553529e-06, "logits/chosen": 16.269399642944336, "logits/rejected": 15.73193645477295, "logps/chosen": -1.0171478986740112, "logps/rejected": -2.201298236846924, "loss": 0.651, "rewards/accuracies": 0.6499999761581421, "rewards/chosen": -1.525721788406372, "rewards/margins": 1.7762253284454346, "rewards/rejected": -3.3019473552703857, "step": 360 }, { "epoch": 0.5807337649597802, "grad_norm": 1.151584267616272, "learning_rate": 4.286181699082008e-06, "logits/chosen": 15.88188648223877, "logits/rejected": 15.261810302734375, "logps/chosen": -1.2272206544876099, "logps/rejected": -3.0203287601470947, "loss": 0.665, "rewards/accuracies": 0.800000011920929, "rewards/chosen": -1.8408310413360596, "rewards/margins": 2.689661741256714, "rewards/rejected": -4.530492305755615, "step": 370 }, { "epoch": 0.5964292721208554, "grad_norm": 1.1879621744155884, "learning_rate": 4.249158351283414e-06, "logits/chosen": 15.906834602355957, "logits/rejected": 15.42895221710205, "logps/chosen": -1.5027008056640625, "logps/rejected": -2.9172558784484863, "loss": 0.5998, "rewards/accuracies": 0.887499988079071, "rewards/chosen": -2.2540509700775146, "rewards/margins": 2.1218326091766357, "rewards/rejected": -4.37588357925415, "step": 380 }, { "epoch": 0.6121247792819305, "grad_norm": 1.678884744644165, "learning_rate": 4.211367764821722e-06, "logits/chosen": 15.630645751953125, "logits/rejected": 14.888415336608887, "logps/chosen": -2.231367349624634, "logps/rejected": -3.5754780769348145, "loss": 0.5937, "rewards/accuracies": 0.824999988079071, "rewards/chosen": -3.347050905227661, "rewards/margins": 2.0161664485931396, "rewards/rejected": -5.363216876983643, "step": 390 }, { "epoch": 0.6278202864430057, "grad_norm": 2.008671998977661, "learning_rate": 4.172826515897146e-06, "logits/chosen": 15.024614334106445, "logits/rejected": 14.981277465820312, "logps/chosen": -2.665980815887451, "logps/rejected": -3.582763195037842, "loss": 0.5722, "rewards/accuracies": 0.7749999761581421, "rewards/chosen": -3.998971462249756, "rewards/margins": 1.3751739263534546, "rewards/rejected": -5.374145030975342, "step": 400 }, { "epoch": 0.6278202864430057, "eval_logits/chosen": 15.45953369140625, "eval_logits/rejected": 14.663763046264648, "eval_logps/chosen": -2.7269070148468018, "eval_logps/rejected": -4.235719680786133, "eval_loss": 0.5668805837631226, "eval_rewards/accuracies": 0.8846153616905212, "eval_rewards/chosen": -4.090360641479492, "eval_rewards/margins": 2.263219118118286, "eval_rewards/rejected": -6.353579998016357, "eval_runtime": 14.6036, "eval_samples_per_second": 28.212, "eval_steps_per_second": 3.561, "step": 400 }, { "epoch": 0.6435157936040808, "grad_norm": 1.018362045288086, "learning_rate": 4.133551509975264e-06, "logits/chosen": 15.027656555175781, "logits/rejected": 14.74786376953125, "logps/chosen": -2.76598858833313, "logps/rejected": -4.335003852844238, "loss": 0.5412, "rewards/accuracies": 0.8374999761581421, "rewards/chosen": -4.148982524871826, "rewards/margins": 2.3535237312316895, "rewards/rejected": -6.502506256103516, "step": 410 }, { "epoch": 0.659211300765156, "grad_norm": 2.2899765968322754, "learning_rate": 4.093559974371725e-06, "logits/chosen": 15.15197467803955, "logits/rejected": 14.681947708129883, "logps/chosen": -2.9831995964050293, "logps/rejected": -4.723050117492676, "loss": 0.4652, "rewards/accuracies": 0.862500011920929, "rewards/chosen": -4.474799633026123, "rewards/margins": 2.6097757816314697, "rewards/rejected": -7.0845746994018555, "step": 420 }, { "epoch": 0.6749068079262311, "grad_norm": 1.419196605682373, "learning_rate": 4.052869450695776e-06, "logits/chosen": 15.000317573547363, "logits/rejected": 14.538591384887695, "logps/chosen": -3.543004274368286, "logps/rejected": -5.037484169006348, "loss": 0.427, "rewards/accuracies": 0.8999999761581421, "rewards/chosen": -5.314507007598877, "rewards/margins": 2.2417192459106445, "rewards/rejected": -7.556225776672363, "step": 430 }, { "epoch": 0.6906023150873063, "grad_norm": 1.639215111732483, "learning_rate": 4.011497787155938e-06, "logits/chosen": 14.798017501831055, "logits/rejected": 14.236108779907227, "logps/chosen": -4.154418468475342, "logps/rejected": -6.0606184005737305, "loss": 0.4692, "rewards/accuracies": 0.8374999761581421, "rewards/chosen": -6.231626987457275, "rewards/margins": 2.859299421310425, "rewards/rejected": -9.090926170349121, "step": 440 }, { "epoch": 0.7062978222483814, "grad_norm": 1.6229957342147827, "learning_rate": 3.969463130731183e-06, "logits/chosen": 14.495908737182617, "logits/rejected": 13.978658676147461, "logps/chosen": -3.4806721210479736, "logps/rejected": -5.746390342712402, "loss": 0.4218, "rewards/accuracies": 0.8500000238418579, "rewards/chosen": -5.221007823944092, "rewards/margins": 3.3985772132873535, "rewards/rejected": -8.619585037231445, "step": 450 }, { "epoch": 0.7062978222483814, "eval_logits/chosen": 15.033548355102539, "eval_logits/rejected": 14.20669174194336, "eval_logps/chosen": -3.423999547958374, "eval_logps/rejected": -5.855647563934326, "eval_loss": 0.45794492959976196, "eval_rewards/accuracies": 0.942307710647583, "eval_rewards/chosen": -5.135998725891113, "eval_rewards/margins": 3.6474733352661133, "eval_rewards/rejected": -8.783472061157227, "eval_runtime": 14.6088, "eval_samples_per_second": 28.202, "eval_steps_per_second": 3.559, "step": 450 }, { "epoch": 0.7219933294094566, "grad_norm": 1.7993106842041016, "learning_rate": 3.92678391921108e-06, "logits/chosen": 14.569323539733887, "logits/rejected": 13.937005996704102, "logps/chosen": -3.3623528480529785, "logps/rejected": -5.784353733062744, "loss": 0.3675, "rewards/accuracies": 0.8999999761581421, "rewards/chosen": -5.043529033660889, "rewards/margins": 3.6330013275146484, "rewards/rejected": -8.676530838012695, "step": 460 }, { "epoch": 0.7376888365705316, "grad_norm": 2.1828088760375977, "learning_rate": 3.88347887310836e-06, "logits/chosen": 13.90056037902832, "logits/rejected": 13.489587783813477, "logps/chosen": -3.959341049194336, "logps/rejected": -6.217314720153809, "loss": 0.3653, "rewards/accuracies": 0.862500011920929, "rewards/chosen": -5.939011573791504, "rewards/margins": 3.3869614601135254, "rewards/rejected": -9.325971603393555, "step": 470 }, { "epoch": 0.7533843437316068, "grad_norm": 2.128547191619873, "learning_rate": 3.839566987447492e-06, "logits/chosen": 14.113011360168457, "logits/rejected": 13.571691513061523, "logps/chosen": -4.004420280456543, "logps/rejected": -6.216452121734619, "loss": 0.3439, "rewards/accuracies": 0.9125000238418579, "rewards/chosen": -6.0066304206848145, "rewards/margins": 3.3180477619171143, "rewards/rejected": -9.324677467346191, "step": 480 }, { "epoch": 0.7690798508926819, "grad_norm": 3.2651569843292236, "learning_rate": 3.795067523432826e-06, "logits/chosen": 13.918218612670898, "logits/rejected": 13.147412300109863, "logps/chosen": -4.574521064758301, "logps/rejected": -7.411087989807129, "loss": 0.3645, "rewards/accuracies": 0.8999999761581421, "rewards/chosen": -6.861782073974609, "rewards/margins": 4.254849910736084, "rewards/rejected": -11.116632461547852, "step": 490 }, { "epoch": 0.7847753580537571, "grad_norm": 2.163595676422119, "learning_rate": 3.7500000000000005e-06, "logits/chosen": 13.972379684448242, "logits/rejected": 13.390825271606445, "logps/chosen": -3.931866407394409, "logps/rejected": -6.547454833984375, "loss": 0.3698, "rewards/accuracies": 0.9125000238418579, "rewards/chosen": -5.897799491882324, "rewards/margins": 3.923382520675659, "rewards/rejected": -9.821184158325195, "step": 500 }, { "epoch": 0.7847753580537571, "eval_logits/chosen": 14.325434684753418, "eval_logits/rejected": 13.4517822265625, "eval_logps/chosen": -3.7717440128326416, "eval_logps/rejected": -6.710938453674316, "eval_loss": 0.38915327191352844, "eval_rewards/accuracies": 0.942307710647583, "eval_rewards/chosen": -5.657615661621094, "eval_rewards/margins": 4.408792018890381, "eval_rewards/rejected": -10.066408157348633, "eval_runtime": 14.5996, "eval_samples_per_second": 28.22, "eval_steps_per_second": 3.562, "step": 500 }, { "epoch": 0.8004708652148322, "grad_norm": 2.7098453044891357, "learning_rate": 3.7043841852542884e-06, "logits/chosen": 13.909749984741211, "logits/rejected": 13.060315132141113, "logps/chosen": -3.848449230194092, "logps/rejected": -6.747067928314209, "loss": 0.3547, "rewards/accuracies": 0.875, "rewards/chosen": -5.772673606872559, "rewards/margins": 4.347928524017334, "rewards/rejected": -10.120603561401367, "step": 510 }, { "epoch": 0.8161663723759074, "grad_norm": 1.693467140197754, "learning_rate": 3.658240087799655e-06, "logits/chosen": 13.52336311340332, "logits/rejected": 13.026924133300781, "logps/chosen": -4.218991279602051, "logps/rejected": -6.984036445617676, "loss": 0.3718, "rewards/accuracies": 0.9375, "rewards/chosen": -6.328486442565918, "rewards/margins": 4.1475677490234375, "rewards/rejected": -10.476054191589355, "step": 520 }, { "epoch": 0.8318618795369825, "grad_norm": 2.4496915340423584, "learning_rate": 3.611587947962319e-06, "logits/chosen": 13.840197563171387, "logits/rejected": 13.181543350219727, "logps/chosen": -4.708582401275635, "logps/rejected": -7.19864559173584, "loss": 0.329, "rewards/accuracies": 0.925000011920929, "rewards/chosen": -7.062872886657715, "rewards/margins": 3.7350947856903076, "rewards/rejected": -10.797967910766602, "step": 530 }, { "epoch": 0.8475573866980577, "grad_norm": 5.772508144378662, "learning_rate": 3.564448228912682e-06, "logits/chosen": 13.432130813598633, "logits/rejected": 12.825490951538086, "logps/chosen": -4.506819248199463, "logps/rejected": -7.506214141845703, "loss": 0.2544, "rewards/accuracies": 0.925000011920929, "rewards/chosen": -6.760228633880615, "rewards/margins": 4.499091625213623, "rewards/rejected": -11.259321212768555, "step": 540 }, { "epoch": 0.8632528938591328, "grad_norm": 1.7776503562927246, "learning_rate": 3.516841607689501e-06, "logits/chosen": 13.536295890808105, "logits/rejected": 12.703726768493652, "logps/chosen": -4.724976062774658, "logps/rejected": -7.864454746246338, "loss": 0.2795, "rewards/accuracies": 0.925000011920929, "rewards/chosen": -7.087464332580566, "rewards/margins": 4.7092180252075195, "rewards/rejected": -11.796682357788086, "step": 550 }, { "epoch": 0.8632528938591328, "eval_logits/chosen": 13.692171096801758, "eval_logits/rejected": 12.81371021270752, "eval_logps/chosen": -4.32358980178833, "eval_logps/rejected": -7.658167839050293, "eval_loss": 0.335475891828537, "eval_rewards/accuracies": 0.942307710647583, "eval_rewards/chosen": -6.485384464263916, "eval_rewards/margins": 5.00186824798584, "eval_rewards/rejected": -11.487252235412598, "eval_runtime": 14.6093, "eval_samples_per_second": 28.201, "eval_steps_per_second": 3.559, "step": 550 }, { "epoch": 0.878948401020208, "grad_norm": 1.7613197565078735, "learning_rate": 3.4687889661302577e-06, "logits/chosen": 13.689091682434082, "logits/rejected": 12.911500930786133, "logps/chosen": -3.8375942707061768, "logps/rejected": -6.98319149017334, "loss": 0.3008, "rewards/accuracies": 0.9125000238418579, "rewards/chosen": -5.7563910484313965, "rewards/margins": 4.7183966636657715, "rewards/rejected": -10.474787712097168, "step": 560 }, { "epoch": 0.8946439081812831, "grad_norm": 2.1285247802734375, "learning_rate": 3.4203113817116955e-06, "logits/chosen": 13.902356147766113, "logits/rejected": 12.766775131225586, "logps/chosen": -3.7727108001708984, "logps/rejected": -7.6362409591674805, "loss": 0.2816, "rewards/accuracies": 0.9375, "rewards/chosen": -5.6590657234191895, "rewards/margins": 5.795297622680664, "rewards/rejected": -11.454363822937012, "step": 570 }, { "epoch": 0.9103394153423583, "grad_norm": 1.6965669393539429, "learning_rate": 3.3714301183045382e-06, "logits/chosen": 13.374112129211426, "logits/rejected": 12.414613723754883, "logps/chosen": -4.747832298278809, "logps/rejected": -8.099973678588867, "loss": 0.2921, "rewards/accuracies": 0.9125000238418579, "rewards/chosen": -7.121748924255371, "rewards/margins": 5.028212547302246, "rewards/rejected": -12.1499605178833, "step": 580 }, { "epoch": 0.9260349225034334, "grad_norm": 2.5470242500305176, "learning_rate": 3.3221666168464584e-06, "logits/chosen": 13.287660598754883, "logits/rejected": 12.554139137268066, "logps/chosen": -4.818625450134277, "logps/rejected": -8.005637168884277, "loss": 0.3155, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.227938175201416, "rewards/margins": 4.780518531799316, "rewards/rejected": -12.008456230163574, "step": 590 }, { "epoch": 0.9417304296645085, "grad_norm": 2.374859571456909, "learning_rate": 3.272542485937369e-06, "logits/chosen": 13.152572631835938, "logits/rejected": 12.557012557983398, "logps/chosen": -3.7581982612609863, "logps/rejected": -6.985205173492432, "loss": 0.2565, "rewards/accuracies": 0.9375, "rewards/chosen": -5.6372971534729, "rewards/margins": 4.840510368347168, "rewards/rejected": -10.477807998657227, "step": 600 }, { "epoch": 0.9417304296645085, "eval_logits/chosen": 13.585193634033203, "eval_logits/rejected": 12.657953262329102, "eval_logps/chosen": -4.077207088470459, "eval_logps/rejected": -7.660572528839111, "eval_loss": 0.30504748225212097, "eval_rewards/accuracies": 0.9615384340286255, "eval_rewards/chosen": -6.115810871124268, "eval_rewards/margins": 5.375046730041504, "eval_rewards/rejected": -11.49085807800293, "eval_runtime": 14.6046, "eval_samples_per_second": 28.21, "eval_steps_per_second": 3.561, "step": 600 }, { "epoch": 0.9574259368255836, "grad_norm": 3.3574252128601074, "learning_rate": 3.222579492361179e-06, "logits/chosen": 12.703638076782227, "logits/rejected": 11.910614013671875, "logps/chosen": -4.188838005065918, "logps/rejected": -7.538239479064941, "loss": 0.2527, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -6.283257961273193, "rewards/margins": 5.024100303649902, "rewards/rejected": -11.30735969543457, "step": 610 }, { "epoch": 0.9731214439866588, "grad_norm": 1.726338505744934, "learning_rate": 3.1722995515381644e-06, "logits/chosen": 13.002418518066406, "logits/rejected": 12.060869216918945, "logps/chosen": -4.711850166320801, "logps/rejected": -8.62987995147705, "loss": 0.2895, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.067776679992676, "rewards/margins": 5.877043724060059, "rewards/rejected": -12.944819450378418, "step": 620 }, { "epoch": 0.9888169511477339, "grad_norm": 2.5146796703338623, "learning_rate": 3.121724717912138e-06, "logits/chosen": 13.190832138061523, "logits/rejected": 11.927602767944336, "logps/chosen": -4.228806495666504, "logps/rejected": -8.436616897583008, "loss": 0.2284, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -6.343210220336914, "rewards/margins": 6.311715602874756, "rewards/rejected": -12.654926300048828, "step": 630 }, { "epoch": 1.003139101432215, "grad_norm": 4.229348659515381, "learning_rate": 3.0708771752766397e-06, "logits/chosen": 13.159438133239746, "logits/rejected": 12.417133331298828, "logps/chosen": -4.084325313568115, "logps/rejected": -7.705818176269531, "loss": 0.2276, "rewards/accuracies": 0.9178082346916199, "rewards/chosen": -6.126489162445068, "rewards/margins": 5.432239055633545, "rewards/rejected": -11.558727264404297, "step": 640 }, { "epoch": 1.0188346085932902, "grad_norm": 4.93217134475708, "learning_rate": 3.019779227044398e-06, "logits/chosen": 13.347890853881836, "logits/rejected": 12.535311698913574, "logps/chosen": -4.311320781707764, "logps/rejected": -7.402029514312744, "loss": 0.2353, "rewards/accuracies": 0.9375, "rewards/chosen": -6.466981410980225, "rewards/margins": 4.636063098907471, "rewards/rejected": -11.103044509887695, "step": 650 }, { "epoch": 1.0188346085932902, "eval_logits/chosen": 13.296299934387207, "eval_logits/rejected": 12.358522415161133, "eval_logps/chosen": -4.177649974822998, "eval_logps/rejected": -8.009714126586914, "eval_loss": 0.28009530901908875, "eval_rewards/accuracies": 0.9615384340286255, "eval_rewards/chosen": -6.266475200653076, "eval_rewards/margins": 5.748095989227295, "eval_rewards/rejected": -12.014572143554688, "eval_runtime": 14.6091, "eval_samples_per_second": 28.202, "eval_steps_per_second": 3.559, "step": 650 }, { "epoch": 1.0345301157543654, "grad_norm": 2.0475847721099854, "learning_rate": 2.9684532864643123e-06, "logits/chosen": 13.43058967590332, "logits/rejected": 12.661652565002441, "logps/chosen": -3.9617011547088623, "logps/rejected": -7.092957973480225, "loss": 0.2562, "rewards/accuracies": 0.9125000238418579, "rewards/chosen": -5.942551136016846, "rewards/margins": 4.69688606262207, "rewards/rejected": -10.639436721801758, "step": 660 }, { "epoch": 1.0502256229154405, "grad_norm": 4.578652381896973, "learning_rate": 2.9169218667902562e-06, "logits/chosen": 13.032757759094238, "logits/rejected": 12.292248725891113, "logps/chosen": -3.679547071456909, "logps/rejected": -7.649219512939453, "loss": 0.2271, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -5.519320487976074, "rewards/margins": 5.9545087814331055, "rewards/rejected": -11.47382926940918, "step": 670 }, { "epoch": 1.0659211300765157, "grad_norm": 3.0983850955963135, "learning_rate": 2.8652075714060296e-06, "logits/chosen": 12.6952486038208, "logits/rejected": 11.917645454406738, "logps/chosen": -4.468019008636475, "logps/rejected": -8.505170822143555, "loss": 0.179, "rewards/accuracies": 0.9375, "rewards/chosen": -6.702028751373291, "rewards/margins": 6.055727958679199, "rewards/rejected": -12.757757186889648, "step": 680 }, { "epoch": 1.0816166372375908, "grad_norm": 3.071026086807251, "learning_rate": 2.813333083910761e-06, "logits/chosen": 12.464409828186035, "logits/rejected": 11.680208206176758, "logps/chosen": -4.6339874267578125, "logps/rejected": -8.639189720153809, "loss": 0.2541, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -6.950981140136719, "rewards/margins": 6.007803440093994, "rewards/rejected": -12.958784103393555, "step": 690 }, { "epoch": 1.097312144398666, "grad_norm": 1.3732093572616577, "learning_rate": 2.761321158169134e-06, "logits/chosen": 12.308462142944336, "logits/rejected": 11.674012184143066, "logps/chosen": -4.638761043548584, "logps/rejected": -8.936636924743652, "loss": 0.1919, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -6.958141326904297, "rewards/margins": 6.446814060211182, "rewards/rejected": -13.40495491027832, "step": 700 }, { "epoch": 1.097312144398666, "eval_logits/chosen": 13.217435836791992, "eval_logits/rejected": 12.272343635559082, "eval_logps/chosen": -4.347932815551758, "eval_logps/rejected": -8.441193580627441, "eval_loss": 0.25916898250579834, "eval_rewards/accuracies": 0.9615384340286255, "eval_rewards/chosen": -6.521899223327637, "eval_rewards/margins": 6.139890670776367, "eval_rewards/rejected": -12.661789894104004, "eval_runtime": 14.6102, "eval_samples_per_second": 28.2, "eval_steps_per_second": 3.559, "step": 700 }, { "epoch": 1.113007651559741, "grad_norm": 3.5739834308624268, "learning_rate": 2.70919460833079e-06, "logits/chosen": 12.828997611999512, "logits/rejected": 12.09227180480957, "logps/chosen": -4.3685622215271, "logps/rejected": -8.672820091247559, "loss": 0.2187, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -6.552844047546387, "rewards/margins": 6.456387519836426, "rewards/rejected": -13.009231567382812, "step": 710 }, { "epoch": 1.1287031587208163, "grad_norm": 11.475191116333008, "learning_rate": 2.6569762988232838e-06, "logits/chosen": 13.344253540039062, "logits/rejected": 12.190181732177734, "logps/chosen": -4.567076206207275, "logps/rejected": -8.719629287719727, "loss": 0.1847, "rewards/accuracies": 0.9375, "rewards/chosen": -6.85061502456665, "rewards/margins": 6.228829383850098, "rewards/rejected": -13.079442977905273, "step": 720 }, { "epoch": 1.1443986658818912, "grad_norm": 1.8145791292190552, "learning_rate": 2.604689134322999e-06, "logits/chosen": 12.794706344604492, "logits/rejected": 12.407793045043945, "logps/chosen": -4.447361946105957, "logps/rejected": -8.19226360321045, "loss": 0.1914, "rewards/accuracies": 0.9125000238418579, "rewards/chosen": -6.67104434967041, "rewards/margins": 5.6173505783081055, "rewards/rejected": -12.288395881652832, "step": 730 }, { "epoch": 1.1600941730429664, "grad_norm": 3.763374090194702, "learning_rate": 2.5523560497083927e-06, "logits/chosen": 12.97741413116455, "logits/rejected": 12.224584579467773, "logps/chosen": -4.449431419372559, "logps/rejected": -8.755613327026367, "loss": 0.2055, "rewards/accuracies": 0.9375, "rewards/chosen": -6.6741461753845215, "rewards/margins": 6.459272861480713, "rewards/rejected": -13.133418083190918, "step": 740 }, { "epoch": 1.1757896802040415, "grad_norm": 2.816288948059082, "learning_rate": 2.5e-06, "logits/chosen": 12.736323356628418, "logits/rejected": 12.039944648742676, "logps/chosen": -4.300374507904053, "logps/rejected": -8.570680618286133, "loss": 0.185, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -6.4505615234375, "rewards/margins": 6.405457973480225, "rewards/rejected": -12.856019973754883, "step": 750 }, { "epoch": 1.1757896802040415, "eval_logits/chosen": 13.174198150634766, "eval_logits/rejected": 12.189348220825195, "eval_logps/chosen": -4.302711009979248, "eval_logps/rejected": -8.745194435119629, "eval_loss": 0.24307754635810852, "eval_rewards/accuracies": 0.9615384340286255, "eval_rewards/chosen": -6.454067707061768, "eval_rewards/margins": 6.663723945617676, "eval_rewards/rejected": -13.117791175842285, "eval_runtime": 14.5945, "eval_samples_per_second": 28.23, "eval_steps_per_second": 3.563, "step": 750 }, { "epoch": 1.1914851873651167, "grad_norm": 2.6783711910247803, "learning_rate": 2.447643950291608e-06, "logits/chosen": 12.992940902709961, "logits/rejected": 12.16160774230957, "logps/chosen": -4.402331829071045, "logps/rejected": -8.848995208740234, "loss": 0.1958, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -6.603497505187988, "rewards/margins": 6.6699957847595215, "rewards/rejected": -13.273493766784668, "step": 760 }, { "epoch": 1.2071806945261918, "grad_norm": 1.580244779586792, "learning_rate": 2.3953108656770018e-06, "logits/chosen": 12.522805213928223, "logits/rejected": 11.664339065551758, "logps/chosen": -3.9605941772460938, "logps/rejected": -8.103001594543457, "loss": 0.1921, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -5.940891265869141, "rewards/margins": 6.213610649108887, "rewards/rejected": -12.154502868652344, "step": 770 }, { "epoch": 1.222876201687267, "grad_norm": 2.2647345066070557, "learning_rate": 2.3430237011767166e-06, "logits/chosen": 12.654630661010742, "logits/rejected": 11.677509307861328, "logps/chosen": -4.634467601776123, "logps/rejected": -9.647830963134766, "loss": 0.1731, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -6.951702117919922, "rewards/margins": 7.520044803619385, "rewards/rejected": -14.471745491027832, "step": 780 }, { "epoch": 1.2385717088483421, "grad_norm": 3.8534202575683594, "learning_rate": 2.290805391669212e-06, "logits/chosen": 12.548233032226562, "logits/rejected": 11.633279800415039, "logps/chosen": -4.690009593963623, "logps/rejected": -8.73483657836914, "loss": 0.1844, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.0350141525268555, "rewards/margins": 6.067240238189697, "rewards/rejected": -13.102254867553711, "step": 790 }, { "epoch": 1.2542672160094173, "grad_norm": 2.8962628841400146, "learning_rate": 2.238678841830867e-06, "logits/chosen": 11.90459156036377, "logits/rejected": 11.352374076843262, "logps/chosen": -4.448246479034424, "logps/rejected": -8.658299446105957, "loss": 0.1638, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -6.67236852645874, "rewards/margins": 6.315079689025879, "rewards/rejected": -12.987447738647461, "step": 800 }, { "epoch": 1.2542672160094173, "eval_logits/chosen": 12.893868446350098, "eval_logits/rejected": 11.863032341003418, "eval_logps/chosen": -4.604159832000732, "eval_logps/rejected": -9.257932662963867, "eval_loss": 0.21881447732448578, "eval_rewards/accuracies": 0.9615384340286255, "eval_rewards/chosen": -6.906240463256836, "eval_rewards/margins": 6.980658531188965, "eval_rewards/rejected": -13.886898040771484, "eval_runtime": 14.6079, "eval_samples_per_second": 28.204, "eval_steps_per_second": 3.56, "step": 800 }, { "epoch": 1.2699627231704924, "grad_norm": 3.5829524993896484, "learning_rate": 2.186666916089239e-06, "logits/chosen": 12.411908149719238, "logits/rejected": 11.730254173278809, "logps/chosen": -4.65117883682251, "logps/rejected": -9.094849586486816, "loss": 0.1827, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -6.976768493652344, "rewards/margins": 6.665505886077881, "rewards/rejected": -13.642274856567383, "step": 810 }, { "epoch": 1.2856582303315676, "grad_norm": 2.836439371109009, "learning_rate": 2.134792428593971e-06, "logits/chosen": 12.173138618469238, "logits/rejected": 11.570637702941895, "logps/chosen": -4.847201824188232, "logps/rejected": -8.849002838134766, "loss": 0.1716, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.270802974700928, "rewards/margins": 6.002701282501221, "rewards/rejected": -13.273503303527832, "step": 820 }, { "epoch": 1.3013537374926427, "grad_norm": 3.5850038528442383, "learning_rate": 2.0830781332097446e-06, "logits/chosen": 12.883340835571289, "logits/rejected": 12.123892784118652, "logps/chosen": -4.7816948890686035, "logps/rejected": -9.729695320129395, "loss": 0.1652, "rewards/accuracies": 0.9375, "rewards/chosen": -7.172542572021484, "rewards/margins": 7.421999931335449, "rewards/rejected": -14.594541549682617, "step": 830 }, { "epoch": 1.3170492446537179, "grad_norm": 1.9497729539871216, "learning_rate": 2.031546713535688e-06, "logits/chosen": 12.579580307006836, "logits/rejected": 11.674839973449707, "logps/chosen": -4.67056131362915, "logps/rejected": -9.12755298614502, "loss": 0.1881, "rewards/accuracies": 0.9375, "rewards/chosen": -7.0058417320251465, "rewards/margins": 6.68548583984375, "rewards/rejected": -13.691328048706055, "step": 840 }, { "epoch": 1.332744751814793, "grad_norm": 2.5810794830322266, "learning_rate": 1.9802207729556023e-06, "logits/chosen": 12.369009017944336, "logits/rejected": 11.520233154296875, "logps/chosen": -4.780073165893555, "logps/rejected": -9.808363914489746, "loss": 0.2051, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -7.17011022567749, "rewards/margins": 7.542436122894287, "rewards/rejected": -14.712547302246094, "step": 850 }, { "epoch": 1.332744751814793, "eval_logits/chosen": 12.70075511932373, "eval_logits/rejected": 11.632950782775879, "eval_logps/chosen": -4.634037494659424, "eval_logps/rejected": -9.374123573303223, "eval_loss": 0.20189520716667175, "eval_rewards/accuracies": 0.9615384340286255, "eval_rewards/chosen": -6.951055526733398, "eval_rewards/margins": 7.110130310058594, "eval_rewards/rejected": -14.061185836791992, "eval_runtime": 14.6066, "eval_samples_per_second": 28.206, "eval_steps_per_second": 3.56, "step": 850 }, { "epoch": 1.3484402589758682, "grad_norm": 5.187539577484131, "learning_rate": 1.9291228247233607e-06, "logits/chosen": 12.224112510681152, "logits/rejected": 11.01191234588623, "logps/chosen": -4.748395919799805, "logps/rejected": -9.206069946289062, "loss": 0.2083, "rewards/accuracies": 0.925000011920929, "rewards/chosen": -7.122593879699707, "rewards/margins": 6.686511039733887, "rewards/rejected": -13.809106826782227, "step": 860 }, { "epoch": 1.3641357661369433, "grad_norm": 1.1569608449935913, "learning_rate": 1.8782752820878636e-06, "logits/chosen": 11.579218864440918, "logits/rejected": 10.995697975158691, "logps/chosen": -4.387156009674072, "logps/rejected": -8.937141418457031, "loss": 0.1782, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -6.580733299255371, "rewards/margins": 6.824978828430176, "rewards/rejected": -13.405713081359863, "step": 870 }, { "epoch": 1.3798312732980185, "grad_norm": 5.9647111892700195, "learning_rate": 1.827700448461836e-06, "logits/chosen": 12.533722877502441, "logits/rejected": 12.121667861938477, "logps/chosen": -3.9464848041534424, "logps/rejected": -7.782477378845215, "loss": 0.237, "rewards/accuracies": 0.925000011920929, "rewards/chosen": -5.919726848602295, "rewards/margins": 5.753990173339844, "rewards/rejected": -11.67371654510498, "step": 880 }, { "epoch": 1.3955267804590936, "grad_norm": 3.4284207820892334, "learning_rate": 1.7774205076388207e-06, "logits/chosen": 12.185909271240234, "logits/rejected": 11.781715393066406, "logps/chosen": -4.110888481140137, "logps/rejected": -8.276056289672852, "loss": 0.1904, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -6.166332721710205, "rewards/margins": 6.2477498054504395, "rewards/rejected": -12.414082527160645, "step": 890 }, { "epoch": 1.4112222876201688, "grad_norm": 2.537830352783203, "learning_rate": 1.7274575140626318e-06, "logits/chosen": 12.28978443145752, "logits/rejected": 11.305529594421387, "logps/chosen": -3.9210026264190674, "logps/rejected": -8.545848846435547, "loss": 0.1508, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -5.881503582000732, "rewards/margins": 6.937270164489746, "rewards/rejected": -12.818774223327637, "step": 900 }, { "epoch": 1.4112222876201688, "eval_logits/chosen": 12.542530059814453, "eval_logits/rejected": 11.450419425964355, "eval_logps/chosen": -4.722529888153076, "eval_logps/rejected": -9.546163558959961, "eval_loss": 0.18640650808811188, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.083794593811035, "eval_rewards/margins": 7.235450744628906, "eval_rewards/rejected": -14.319246292114258, "eval_runtime": 14.6107, "eval_samples_per_second": 28.199, "eval_steps_per_second": 3.559, "step": 900 }, { "epoch": 1.426917794781244, "grad_norm": 1.1588759422302246, "learning_rate": 1.677833383153542e-06, "logits/chosen": 12.432401657104492, "logits/rejected": 11.247361183166504, "logps/chosen": -4.893294334411621, "logps/rejected": -9.311574935913086, "loss": 0.1446, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -7.339941501617432, "rewards/margins": 6.627419948577881, "rewards/rejected": -13.967363357543945, "step": 910 }, { "epoch": 1.442613301942319, "grad_norm": 2.4712307453155518, "learning_rate": 1.6285698816954626e-06, "logits/chosen": 12.139798164367676, "logits/rejected": 11.248186111450195, "logps/chosen": -5.167681694030762, "logps/rejected": -10.253265380859375, "loss": 0.163, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.751523017883301, "rewards/margins": 7.6283769607543945, "rewards/rejected": -15.379899978637695, "step": 920 }, { "epoch": 1.4583088091033942, "grad_norm": 1.881538987159729, "learning_rate": 1.5796886182883053e-06, "logits/chosen": 11.9426908493042, "logits/rejected": 11.341384887695312, "logps/chosen": -5.030823230743408, "logps/rejected": -9.114843368530273, "loss": 0.1773, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.54623556137085, "rewards/margins": 6.126028060913086, "rewards/rejected": -13.672262191772461, "step": 930 }, { "epoch": 1.4740043162644694, "grad_norm": 5.751014709472656, "learning_rate": 1.5312110338697427e-06, "logits/chosen": 11.921320915222168, "logits/rejected": 11.005578994750977, "logps/chosen": -4.730319976806641, "logps/rejected": -9.198332786560059, "loss": 0.2058, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.095480442047119, "rewards/margins": 6.702019691467285, "rewards/rejected": -13.797500610351562, "step": 940 }, { "epoch": 1.4896998234255445, "grad_norm": 2.656139850616455, "learning_rate": 1.4831583923105e-06, "logits/chosen": 12.132013320922852, "logits/rejected": 11.254085540771484, "logps/chosen": -4.832255840301514, "logps/rejected": -9.473350524902344, "loss": 0.1827, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.24838399887085, "rewards/margins": 6.961642265319824, "rewards/rejected": -14.210027694702148, "step": 950 }, { "epoch": 1.4896998234255445, "eval_logits/chosen": 12.534186363220215, "eval_logits/rejected": 11.43524169921875, "eval_logps/chosen": -4.488946914672852, "eval_logps/rejected": -9.457845687866211, "eval_loss": 0.1744592934846878, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -6.733420372009277, "eval_rewards/margins": 7.4533467292785645, "eval_rewards/rejected": -14.186767578125, "eval_runtime": 14.6075, "eval_samples_per_second": 28.205, "eval_steps_per_second": 3.56, "step": 950 }, { "epoch": 1.5053953305866195, "grad_norm": 4.976431369781494, "learning_rate": 1.4355517710873184e-06, "logits/chosen": 12.053160667419434, "logits/rejected": 11.461877822875977, "logps/chosen": -4.3384108543396, "logps/rejected": -8.933584213256836, "loss": 0.1559, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -6.5076165199279785, "rewards/margins": 6.892758846282959, "rewards/rejected": -13.400375366210938, "step": 960 }, { "epoch": 1.5210908377476948, "grad_norm": 2.786695718765259, "learning_rate": 1.388412052037682e-06, "logits/chosen": 12.072885513305664, "logits/rejected": 10.973172187805176, "logps/chosen": -4.89219331741333, "logps/rejected": -9.545186996459961, "loss": 0.1334, "rewards/accuracies": 0.9375, "rewards/chosen": -7.338289737701416, "rewards/margins": 6.979489803314209, "rewards/rejected": -14.317779541015625, "step": 970 }, { "epoch": 1.5367863449087698, "grad_norm": 5.252014636993408, "learning_rate": 1.3417599122003464e-06, "logits/chosen": 12.37597370147705, "logits/rejected": 11.43901538848877, "logps/chosen": -5.274794101715088, "logps/rejected": -9.821117401123047, "loss": 0.1477, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.912191867828369, "rewards/margins": 6.819484710693359, "rewards/rejected": -14.73167610168457, "step": 980 }, { "epoch": 1.5524818520698451, "grad_norm": 2.243185520172119, "learning_rate": 1.2956158147457116e-06, "logits/chosen": 11.921972274780273, "logits/rejected": 11.30908489227295, "logps/chosen": -5.393095970153809, "logps/rejected": -10.215553283691406, "loss": 0.1561, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -8.089644432067871, "rewards/margins": 7.233686923980713, "rewards/rejected": -15.323330879211426, "step": 990 }, { "epoch": 1.56817735923092, "grad_norm": 3.4886062145233154, "learning_rate": 1.2500000000000007e-06, "logits/chosen": 11.753881454467773, "logits/rejected": 11.269731521606445, "logps/chosen": -5.015429496765137, "logps/rejected": -10.169350624084473, "loss": 0.1771, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.523144721984863, "rewards/margins": 7.7308807373046875, "rewards/rejected": -15.25402545928955, "step": 1000 }, { "epoch": 1.56817735923092, "eval_logits/chosen": 12.437786102294922, "eval_logits/rejected": 11.32490348815918, "eval_logps/chosen": -4.6446380615234375, "eval_logps/rejected": -9.707358360290527, "eval_loss": 0.16595196723937988, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -6.966956615447998, "eval_rewards/margins": 7.594080448150635, "eval_rewards/rejected": -14.561037063598633, "eval_runtime": 14.6109, "eval_samples_per_second": 28.198, "eval_steps_per_second": 3.559, "step": 1000 }, { "epoch": 1.5838728663919954, "grad_norm": 1.7607649564743042, "learning_rate": 1.204932476567175e-06, "logits/chosen": 11.258343696594238, "logits/rejected": 10.613565444946289, "logps/chosen": -4.758576393127441, "logps/rejected": -9.250303268432617, "loss": 0.1668, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.137864589691162, "rewards/margins": 6.7375898361206055, "rewards/rejected": -13.875455856323242, "step": 1010 }, { "epoch": 1.5995683735530704, "grad_norm": 3.2954118251800537, "learning_rate": 1.160433012552508e-06, "logits/chosen": 12.226592063903809, "logits/rejected": 11.355180740356445, "logps/chosen": -4.198899269104004, "logps/rejected": -8.675564765930176, "loss": 0.1824, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -6.298348903656006, "rewards/margins": 6.714995384216309, "rewards/rejected": -13.013345718383789, "step": 1020 }, { "epoch": 1.6152638807141457, "grad_norm": 2.833040237426758, "learning_rate": 1.11652112689164e-06, "logits/chosen": 11.937528610229492, "logits/rejected": 11.127592086791992, "logps/chosen": -4.438723087310791, "logps/rejected": -9.106756210327148, "loss": 0.1567, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -6.658083915710449, "rewards/margins": 7.002050876617432, "rewards/rejected": -13.660135269165039, "step": 1030 }, { "epoch": 1.6309593878752207, "grad_norm": 2.0544891357421875, "learning_rate": 1.073216080788921e-06, "logits/chosen": 12.242444038391113, "logits/rejected": 11.25694465637207, "logps/chosen": -4.525513172149658, "logps/rejected": -9.212661743164062, "loss": 0.1682, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -6.78826904296875, "rewards/margins": 7.030723571777344, "rewards/rejected": -13.818992614746094, "step": 1040 }, { "epoch": 1.6466548950362958, "grad_norm": 1.6990854740142822, "learning_rate": 1.0305368692688175e-06, "logits/chosen": 11.99101448059082, "logits/rejected": 11.161852836608887, "logps/chosen": -4.299143314361572, "logps/rejected": -9.032526016235352, "loss": 0.1143, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -6.448714256286621, "rewards/margins": 7.100072383880615, "rewards/rejected": -13.548787117004395, "step": 1050 }, { "epoch": 1.6466548950362958, "eval_logits/chosen": 12.486811637878418, "eval_logits/rejected": 11.354048728942871, "eval_logps/chosen": -4.389483451843262, "eval_logps/rejected": -9.478667259216309, "eval_loss": 0.16117088496685028, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -6.584225654602051, "eval_rewards/margins": 7.633774280548096, "eval_rewards/rejected": -14.217998504638672, "eval_runtime": 14.6006, "eval_samples_per_second": 28.218, "eval_steps_per_second": 3.561, "step": 1050 }, { "epoch": 1.662350402197371, "grad_norm": 3.3203821182250977, "learning_rate": 9.88502212844063e-07, "logits/chosen": 12.17997932434082, "logits/rejected": 11.155837059020996, "logps/chosen": -4.206795692443848, "logps/rejected": -9.341482162475586, "loss": 0.1631, "rewards/accuracies": 1.0, "rewards/chosen": -6.310193061828613, "rewards/margins": 7.702028751373291, "rewards/rejected": -14.012222290039062, "step": 1060 }, { "epoch": 1.678045909358446, "grad_norm": 2.4238297939300537, "learning_rate": 9.471305493042243e-07, "logits/chosen": 11.849737167358398, "logits/rejected": 10.839106559753418, "logps/chosen": -4.497702598571777, "logps/rejected": -9.431967735290527, "loss": 0.1347, "rewards/accuracies": 1.0, "rewards/chosen": -6.746554374694824, "rewards/margins": 7.401397705078125, "rewards/rejected": -14.14795207977295, "step": 1070 }, { "epoch": 1.6937414165195213, "grad_norm": 1.895890712738037, "learning_rate": 9.064400256282757e-07, "logits/chosen": 12.01026725769043, "logits/rejected": 11.010753631591797, "logps/chosen": -4.6886305809021, "logps/rejected": -9.496674537658691, "loss": 0.1076, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.032945156097412, "rewards/margins": 7.212066650390625, "rewards/rejected": -14.245012283325195, "step": 1080 }, { "epoch": 1.7094369236805964, "grad_norm": 4.748386859893799, "learning_rate": 8.664484900247363e-07, "logits/chosen": 11.74091911315918, "logits/rejected": 11.233245849609375, "logps/chosen": -5.176927089691162, "logps/rejected": -9.68712043762207, "loss": 0.1532, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.765390872955322, "rewards/margins": 6.765290260314941, "rewards/rejected": -14.530679702758789, "step": 1090 }, { "epoch": 1.7251324308416716, "grad_norm": 2.932032346725464, "learning_rate": 8.271734841028553e-07, "logits/chosen": 11.53050708770752, "logits/rejected": 10.704401969909668, "logps/chosen": -5.003798484802246, "logps/rejected": -10.222925186157227, "loss": 0.1632, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.505698204040527, "rewards/margins": 7.8286895751953125, "rewards/rejected": -15.334388732910156, "step": 1100 }, { "epoch": 1.7251324308416716, "eval_logits/chosen": 12.376419067382812, "eval_logits/rejected": 11.235088348388672, "eval_logps/chosen": -4.780559539794922, "eval_logps/rejected": -9.94357967376709, "eval_loss": 0.1563359946012497, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.170839309692383, "eval_rewards/margins": 7.744529724121094, "eval_rewards/rejected": -14.915369033813477, "eval_runtime": 14.5952, "eval_samples_per_second": 28.229, "eval_steps_per_second": 3.563, "step": 1100 }, { "epoch": 1.7408279380027467, "grad_norm": 3.4405391216278076, "learning_rate": 7.886322351782782e-07, "logits/chosen": 12.490205764770508, "logits/rejected": 11.409021377563477, "logps/chosen": -4.385369300842285, "logps/rejected": -9.336843490600586, "loss": 0.1579, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -6.578053951263428, "rewards/margins": 7.427211761474609, "rewards/rejected": -14.005266189575195, "step": 1110 }, { "epoch": 1.7565234451638219, "grad_norm": 4.066647529602051, "learning_rate": 7.508416487165862e-07, "logits/chosen": 11.967781066894531, "logits/rejected": 11.07763671875, "logps/chosen": -4.826973915100098, "logps/rejected": -9.608440399169922, "loss": 0.1603, "rewards/accuracies": 0.9375, "rewards/chosen": -7.2404608726501465, "rewards/margins": 7.172199249267578, "rewards/rejected": -14.412660598754883, "step": 1120 }, { "epoch": 1.772218952324897, "grad_norm": 1.7111518383026123, "learning_rate": 7.138183009179922e-07, "logits/chosen": 12.116536140441895, "logits/rejected": 11.637681007385254, "logps/chosen": -4.51651668548584, "logps/rejected": -9.084489822387695, "loss": 0.1428, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -6.77477502822876, "rewards/margins": 6.8519606590271, "rewards/rejected": -13.626734733581543, "step": 1130 }, { "epoch": 1.7879144594859722, "grad_norm": 4.302910804748535, "learning_rate": 6.775784314464717e-07, "logits/chosen": 11.709549903869629, "logits/rejected": 11.382287979125977, "logps/chosen": -5.279540061950684, "logps/rejected": -9.892831802368164, "loss": 0.163, "rewards/accuracies": 0.9375, "rewards/chosen": -7.919310569763184, "rewards/margins": 6.919938564300537, "rewards/rejected": -14.839248657226562, "step": 1140 }, { "epoch": 1.8036099666470473, "grad_norm": 0.8747031092643738, "learning_rate": 6.421379363065142e-07, "logits/chosen": 12.214895248413086, "logits/rejected": 11.334197998046875, "logps/chosen": -4.599240303039551, "logps/rejected": -8.940774917602539, "loss": 0.1288, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -6.898859977722168, "rewards/margins": 6.512301445007324, "rewards/rejected": -13.411161422729492, "step": 1150 }, { "epoch": 1.8036099666470473, "eval_logits/chosen": 12.347259521484375, "eval_logits/rejected": 11.185004234313965, "eval_logps/chosen": -4.888545036315918, "eval_logps/rejected": -10.101993560791016, "eval_loss": 0.15526321530342102, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.332817077636719, "eval_rewards/margins": 7.8201727867126465, "eval_rewards/rejected": -15.15299129486084, "eval_runtime": 14.6049, "eval_samples_per_second": 28.21, "eval_steps_per_second": 3.56, "step": 1150 }, { "epoch": 1.8193054738081225, "grad_norm": 1.8233786821365356, "learning_rate": 6.075123608706093e-07, "logits/chosen": 11.725976943969727, "logits/rejected": 11.068318367004395, "logps/chosen": -5.016218185424805, "logps/rejected": -9.066827774047852, "loss": 0.1241, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.524327278137207, "rewards/margins": 6.075912952423096, "rewards/rejected": -13.600239753723145, "step": 1160 }, { "epoch": 1.8350009809691976, "grad_norm": 1.6913511753082275, "learning_rate": 5.737168930605272e-07, "logits/chosen": 11.813165664672852, "logits/rejected": 10.936023712158203, "logps/chosen": -5.16327428817749, "logps/rejected": -9.918088912963867, "loss": 0.1337, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.744911193847656, "rewards/margins": 7.132222652435303, "rewards/rejected": -14.877134323120117, "step": 1170 }, { "epoch": 1.8506964881302728, "grad_norm": 4.435967445373535, "learning_rate": 5.407663566854008e-07, "logits/chosen": 11.606057167053223, "logits/rejected": 10.97921085357666, "logps/chosen": -5.703640937805176, "logps/rejected": -10.870219230651855, "loss": 0.1245, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -8.555461883544922, "rewards/margins": 7.749865531921387, "rewards/rejected": -16.305328369140625, "step": 1180 }, { "epoch": 1.8663919952913477, "grad_norm": 2.9056365489959717, "learning_rate": 5.086752049395094e-07, "logits/chosen": 11.697361946105957, "logits/rejected": 10.928617477416992, "logps/chosen": -5.48267936706543, "logps/rejected": -10.689864158630371, "loss": 0.1251, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -8.224019050598145, "rewards/margins": 7.810777187347412, "rewards/rejected": -16.0347957611084, "step": 1190 }, { "epoch": 1.882087502452423, "grad_norm": 2.538482904434204, "learning_rate": 4.774575140626317e-07, "logits/chosen": 11.8221435546875, "logits/rejected": 11.30038070678711, "logps/chosen": -5.215182781219482, "logps/rejected": -9.782806396484375, "loss": 0.1543, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.822774410247803, "rewards/margins": 6.851436614990234, "rewards/rejected": -14.674212455749512, "step": 1200 }, { "epoch": 1.882087502452423, "eval_logits/chosen": 12.300190925598145, "eval_logits/rejected": 11.128490447998047, "eval_logps/chosen": -4.917614936828613, "eval_logps/rejected": -10.187230110168457, "eval_loss": 0.1518644094467163, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.37642240524292, "eval_rewards/margins": 7.904422283172607, "eval_rewards/rejected": -15.280843734741211, "eval_runtime": 14.6081, "eval_samples_per_second": 28.203, "eval_steps_per_second": 3.56, "step": 1200 }, { "epoch": 1.897783009613498, "grad_norm": 1.9161700010299683, "learning_rate": 4.4712697716573994e-07, "logits/chosen": 11.40344524383545, "logits/rejected": 10.652345657348633, "logps/chosen": -5.708310127258301, "logps/rejected": -10.750404357910156, "loss": 0.1319, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -8.562464714050293, "rewards/margins": 7.5631422996521, "rewards/rejected": -16.125606536865234, "step": 1210 }, { "epoch": 1.9134785167745734, "grad_norm": 2.1904044151306152, "learning_rate": 4.1769689822475147e-07, "logits/chosen": 11.742301940917969, "logits/rejected": 10.61946964263916, "logps/chosen": -4.744222640991211, "logps/rejected": -9.856466293334961, "loss": 0.1219, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.116333961486816, "rewards/margins": 7.668366432189941, "rewards/rejected": -14.784701347351074, "step": 1220 }, { "epoch": 1.9291740239356483, "grad_norm": 1.7852545976638794, "learning_rate": 3.891801862449629e-07, "logits/chosen": 11.89977741241455, "logits/rejected": 10.996416091918945, "logps/chosen": -4.8371357917785645, "logps/rejected": -9.81475830078125, "loss": 0.1179, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.255703926086426, "rewards/margins": 7.466433525085449, "rewards/rejected": -14.722137451171875, "step": 1230 }, { "epoch": 1.9448695310967237, "grad_norm": 3.7123889923095703, "learning_rate": 3.615893495987335e-07, "logits/chosen": 11.688365936279297, "logits/rejected": 10.34130573272705, "logps/chosen": -5.3013434410095215, "logps/rejected": -10.476262092590332, "loss": 0.1335, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -7.952016353607178, "rewards/margins": 7.7623772621154785, "rewards/rejected": -15.714391708374023, "step": 1240 }, { "epoch": 1.9605650382577986, "grad_norm": 3.9862449169158936, "learning_rate": 3.3493649053890325e-07, "logits/chosen": 12.021284103393555, "logits/rejected": 11.184505462646484, "logps/chosen": -4.448847770690918, "logps/rejected": -9.278366088867188, "loss": 0.1712, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -6.673272132873535, "rewards/margins": 7.244276523590088, "rewards/rejected": -13.917549133300781, "step": 1250 }, { "epoch": 1.9605650382577986, "eval_logits/chosen": 12.263810157775879, "eval_logits/rejected": 11.079519271850586, "eval_logps/chosen": -4.891733169555664, "eval_logps/rejected": -10.19001293182373, "eval_loss": 0.15064650774002075, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.337599754333496, "eval_rewards/margins": 7.947419166564941, "eval_rewards/rejected": -15.285017967224121, "eval_runtime": 14.5975, "eval_samples_per_second": 28.224, "eval_steps_per_second": 3.562, "step": 1250 }, { "epoch": 1.976260545418874, "grad_norm": 1.567117691040039, "learning_rate": 3.092332998903416e-07, "logits/chosen": 12.057940483093262, "logits/rejected": 11.069997787475586, "logps/chosen": -4.710134506225586, "logps/rejected": -9.204834938049316, "loss": 0.1332, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.065201759338379, "rewards/margins": 6.742051124572754, "rewards/rejected": -13.807252883911133, "step": 1260 }, { "epoch": 1.991956052579949, "grad_norm": 3.7871203422546387, "learning_rate": 2.844910519219632e-07, "logits/chosen": 11.46792984008789, "logits/rejected": 10.572579383850098, "logps/chosen": -5.138741970062256, "logps/rejected": -10.308446884155273, "loss": 0.1687, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.7081122398376465, "rewards/margins": 7.7545576095581055, "rewards/rejected": -15.462671279907227, "step": 1270 }, { "epoch": 2.00627820286443, "grad_norm": 3.568068265914917, "learning_rate": 2.6072059940146775e-07, "logits/chosen": 11.988948822021484, "logits/rejected": 11.214070320129395, "logps/chosen": -4.7047834396362305, "logps/rejected": -9.610939979553223, "loss": 0.1344, "rewards/accuracies": 0.9589040875434875, "rewards/chosen": -7.0571746826171875, "rewards/margins": 7.3592352867126465, "rewards/rejected": -14.416410446166992, "step": 1280 }, { "epoch": 2.021973710025505, "grad_norm": 4.052379608154297, "learning_rate": 2.3793236883495164e-07, "logits/chosen": 11.641098976135254, "logits/rejected": 11.267931938171387, "logps/chosen": -5.0538649559021, "logps/rejected": -9.780375480651855, "loss": 0.163, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.580796718597412, "rewards/margins": 7.089766502380371, "rewards/rejected": -14.670562744140625, "step": 1290 }, { "epoch": 2.0376692171865805, "grad_norm": 3.9337706565856934, "learning_rate": 2.1613635589349756e-07, "logits/chosen": 12.23253059387207, "logits/rejected": 11.380578994750977, "logps/chosen": -4.633624076843262, "logps/rejected": -9.106454849243164, "loss": 0.1749, "rewards/accuracies": 1.0, "rewards/chosen": -6.950437068939209, "rewards/margins": 6.709245204925537, "rewards/rejected": -13.65968132019043, "step": 1300 }, { "epoch": 2.0376692171865805, "eval_logits/chosen": 12.265684127807617, "eval_logits/rejected": 11.080260276794434, "eval_logps/chosen": -4.788154125213623, "eval_logps/rejected": -10.096734046936035, "eval_loss": 0.14751878380775452, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.18223237991333, "eval_rewards/margins": 7.962869644165039, "eval_rewards/rejected": -15.145101547241211, "eval_runtime": 14.6092, "eval_samples_per_second": 28.202, "eval_steps_per_second": 3.559, "step": 1300 }, { "epoch": 2.0533647243476554, "grad_norm": 3.6989145278930664, "learning_rate": 1.95342121028749e-07, "logits/chosen": 11.732830047607422, "logits/rejected": 11.045280456542969, "logps/chosen": -4.425314903259277, "logps/rejected": -9.951812744140625, "loss": 0.1298, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -6.637972831726074, "rewards/margins": 8.28974723815918, "rewards/rejected": -14.927721977233887, "step": 1310 }, { "epoch": 2.0690602315087308, "grad_norm": 1.380689263343811, "learning_rate": 1.7555878527937164e-07, "logits/chosen": 11.639039039611816, "logits/rejected": 10.867536544799805, "logps/chosen": -5.215638160705566, "logps/rejected": -10.307191848754883, "loss": 0.1054, "rewards/accuracies": 0.9375, "rewards/chosen": -7.82345724105835, "rewards/margins": 7.637331485748291, "rewards/rejected": -15.460787773132324, "step": 1320 }, { "epoch": 2.0847557386698057, "grad_norm": 2.8833718299865723, "learning_rate": 1.567950262702714e-07, "logits/chosen": 11.799827575683594, "logits/rejected": 11.053567886352539, "logps/chosen": -5.004476070404053, "logps/rejected": -9.889656066894531, "loss": 0.1195, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.506715297698975, "rewards/margins": 7.327768802642822, "rewards/rejected": -14.834482192993164, "step": 1330 }, { "epoch": 2.100451245830881, "grad_norm": 4.374328136444092, "learning_rate": 1.3905907440629752e-07, "logits/chosen": 11.815560340881348, "logits/rejected": 10.514938354492188, "logps/chosen": -5.09425687789917, "logps/rejected": -10.630200386047363, "loss": 0.1462, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.64138650894165, "rewards/margins": 8.303915023803711, "rewards/rejected": -15.945300102233887, "step": 1340 }, { "epoch": 2.116146752991956, "grad_norm": 5.649663925170898, "learning_rate": 1.223587092621162e-07, "logits/chosen": 11.845888137817383, "logits/rejected": 10.951406478881836, "logps/chosen": -5.54123592376709, "logps/rejected": -10.818798065185547, "loss": 0.151, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -8.311853408813477, "rewards/margins": 7.916342735290527, "rewards/rejected": -16.228199005126953, "step": 1350 }, { "epoch": 2.116146752991956, "eval_logits/chosen": 12.23206615447998, "eval_logits/rejected": 11.042497634887695, "eval_logps/chosen": -4.86654806137085, "eval_logps/rejected": -10.186172485351562, "eval_loss": 0.1482052505016327, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.2998223304748535, "eval_rewards/margins": 7.979436874389648, "eval_rewards/rejected": -15.27925968170166, "eval_runtime": 14.6066, "eval_samples_per_second": 28.206, "eval_steps_per_second": 3.56, "step": 1350 }, { "epoch": 2.1318422601530314, "grad_norm": 1.5727463960647583, "learning_rate": 1.067012561698319e-07, "logits/chosen": 11.984907150268555, "logits/rejected": 11.170934677124023, "logps/chosen": -5.278778076171875, "logps/rejected": -10.719067573547363, "loss": 0.1111, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -7.918168067932129, "rewards/margins": 8.160432815551758, "rewards/rejected": -16.078601837158203, "step": 1360 }, { "epoch": 2.1475377673141063, "grad_norm": 2.5720973014831543, "learning_rate": 9.209358300585474e-08, "logits/chosen": 11.944007873535156, "logits/rejected": 11.239874839782715, "logps/chosen": -4.983370304107666, "logps/rejected": -9.842253684997559, "loss": 0.125, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -7.475054740905762, "rewards/margins": 7.288325309753418, "rewards/rejected": -14.763381958007812, "step": 1370 }, { "epoch": 2.1632332744751817, "grad_norm": 1.8921817541122437, "learning_rate": 7.854209717842231e-08, "logits/chosen": 11.709084510803223, "logits/rejected": 10.745340347290039, "logps/chosen": -5.250277519226074, "logps/rejected": -11.172690391540527, "loss": 0.1323, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.8754167556762695, "rewards/margins": 8.883621215820312, "rewards/rejected": -16.759037017822266, "step": 1380 }, { "epoch": 2.1789287816362566, "grad_norm": 3.5800342559814453, "learning_rate": 6.605274281709929e-08, "logits/chosen": 11.36808967590332, "logits/rejected": 10.22724437713623, "logps/chosen": -5.402105808258057, "logps/rejected": -10.600914001464844, "loss": 0.1365, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -8.103157997131348, "rewards/margins": 7.798213005065918, "rewards/rejected": -15.901371955871582, "step": 1390 }, { "epoch": 2.194624288797332, "grad_norm": 3.021120548248291, "learning_rate": 5.463099816548578e-08, "logits/chosen": 12.123847007751465, "logits/rejected": 10.885251998901367, "logps/chosen": -4.701441287994385, "logps/rejected": -10.605305671691895, "loss": 0.1116, "rewards/accuracies": 0.987500011920929, "rewards/chosen": -7.052162170410156, "rewards/margins": 8.855795860290527, "rewards/rejected": -15.907957077026367, "step": 1400 }, { "epoch": 2.194624288797332, "eval_logits/chosen": 12.214911460876465, "eval_logits/rejected": 11.020902633666992, "eval_logps/chosen": -4.897452354431152, "eval_logps/rejected": -10.230777740478516, "eval_loss": 0.149026557803154, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.3461785316467285, "eval_rewards/margins": 7.999988079071045, "eval_rewards/rejected": -15.346166610717773, "eval_runtime": 14.6104, "eval_samples_per_second": 28.199, "eval_steps_per_second": 3.559, "step": 1400 }, { "epoch": 2.210319795958407, "grad_norm": 1.5570991039276123, "learning_rate": 4.428187317827848e-08, "logits/chosen": 11.934289932250977, "logits/rejected": 11.13194465637207, "logps/chosen": -5.17191743850708, "logps/rejected": -10.771769523620605, "loss": 0.1247, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.757874965667725, "rewards/margins": 8.399779319763184, "rewards/rejected": -16.157655715942383, "step": 1410 }, { "epoch": 2.226015303119482, "grad_norm": 1.9914512634277344, "learning_rate": 3.5009907323737826e-08, "logits/chosen": 11.679354667663574, "logits/rejected": 10.788348197937012, "logps/chosen": -5.224305152893066, "logps/rejected": -10.575732231140137, "loss": 0.1292, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -7.836456298828125, "rewards/margins": 8.027141571044922, "rewards/rejected": -15.86359691619873, "step": 1420 }, { "epoch": 2.241710810280557, "grad_norm": 1.5110270977020264, "learning_rate": 2.681916759252917e-08, "logits/chosen": 11.340958595275879, "logits/rejected": 10.710260391235352, "logps/chosen": -5.453789710998535, "logps/rejected": -10.543638229370117, "loss": 0.1364, "rewards/accuracies": 0.9624999761581421, "rewards/chosen": -8.180685043334961, "rewards/margins": 7.634771823883057, "rewards/rejected": -15.815455436706543, "step": 1430 }, { "epoch": 2.2574063174416326, "grad_norm": 3.2789409160614014, "learning_rate": 1.9713246713805588e-08, "logits/chosen": 11.973535537719727, "logits/rejected": 11.382715225219727, "logps/chosen": -4.661351203918457, "logps/rejected": -10.070053100585938, "loss": 0.1372, "rewards/accuracies": 0.9750000238418579, "rewards/chosen": -6.992027282714844, "rewards/margins": 8.113051414489746, "rewards/rejected": -15.105077743530273, "step": 1440 }, { "epoch": 2.2731018246027075, "grad_norm": 3.0575263500213623, "learning_rate": 1.3695261579316776e-08, "logits/chosen": 11.72465991973877, "logits/rejected": 10.645977973937988, "logps/chosen": -5.164309978485107, "logps/rejected": -10.171631813049316, "loss": 0.1496, "rewards/accuracies": 0.949999988079071, "rewards/chosen": -7.746464729309082, "rewards/margins": 7.510981559753418, "rewards/rejected": -15.2574462890625, "step": 1450 }, { "epoch": 2.2731018246027075, "eval_logits/chosen": 12.213281631469727, "eval_logits/rejected": 11.019485473632812, "eval_logps/chosen": -4.893021583557129, "eval_logps/rejected": -10.233271598815918, "eval_loss": 0.14757712185382843, "eval_rewards/accuracies": 0.9807692170143127, "eval_rewards/chosen": -7.33953332901001, "eval_rewards/margins": 8.010376930236816, "eval_rewards/rejected": -15.349907875061035, "eval_runtime": 14.6125, "eval_samples_per_second": 28.195, "eval_steps_per_second": 3.559, "step": 1450 } ], "logging_steps": 10, "max_steps": 1500, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.466434374075941e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }