{ "best_global_step": 300, "best_metric": 0.42507252, "best_model_checkpoint": "/data2/kdd/crag/cjz/output/task1_dpo_round2_0dot9_0603/v1-20250603-223558/checkpoint-300", "epoch": 1.7264864864864866, "eval_steps": 300, "global_step": 300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005765765765765766, "grad_norm": 2.1474921703338623, "learning_rate": 7.692307692307694e-06, "logits/chosen": -0.4285973310470581, "logits/rejected": -0.721319854259491, "logps/chosen": -2.468954086303711, "logps/rejected": -59.87730407714844, "loss": 0.22946561872959137, "memory(GiB)": 30.65, "nll_loss": 0.13756254315376282, "rewards/accuracies": 0.96875, "rewards/chosen": 0.23724405467510223, "rewards/margins": 3.9806408882141113, "rewards/rejected": -3.743396759033203, "step": 1, "train_speed(iter/s)": 0.01022 }, { "epoch": 0.011531531531531532, "grad_norm": 2.328110456466675, "learning_rate": 1.5384615384615387e-05, "logits/chosen": -0.3982561528682709, "logits/rejected": -0.7214521169662476, "logps/chosen": -3.335645914077759, "logps/rejected": -60.79209899902344, "loss": 0.3770241439342499, "memory(GiB)": 30.65, "nll_loss": 0.23075783252716064, "rewards/accuracies": 0.96875, "rewards/chosen": 0.10687967389822006, "rewards/margins": 3.9392333030700684, "rewards/rejected": -3.832353353500366, "step": 2, "train_speed(iter/s)": 0.010488 }, { "epoch": 0.017297297297297298, "grad_norm": 14.568985939025879, "learning_rate": 2.307692307692308e-05, "logits/chosen": -0.43175598978996277, "logits/rejected": -0.6921666264533997, "logps/chosen": -5.190546035766602, "logps/rejected": -51.33646011352539, "loss": 0.9886025786399841, "memory(GiB)": 34.1, "nll_loss": 0.6371194124221802, "rewards/accuracies": 0.84375, "rewards/chosen": -0.034887176007032394, "rewards/margins": 3.2021734714508057, "rewards/rejected": -3.237060785293579, "step": 3, "train_speed(iter/s)": 0.010581 }, { "epoch": 0.023063063063063063, "grad_norm": 13.817249298095703, "learning_rate": 3.0769230769230774e-05, "logits/chosen": -0.4616771340370178, "logits/rejected": -0.6264235973358154, "logps/chosen": -3.2552552223205566, "logps/rejected": -51.25586700439453, "loss": 0.5021163821220398, "memory(GiB)": 37.58, "nll_loss": 0.26375898718833923, "rewards/accuracies": 0.875, "rewards/chosen": 0.06816040724515915, "rewards/margins": 3.5297036170959473, "rewards/rejected": -3.461543083190918, "step": 4, "train_speed(iter/s)": 0.010625 }, { "epoch": 0.02882882882882883, "grad_norm": 2.363553524017334, "learning_rate": 3.846153846153846e-05, "logits/chosen": -0.48805952072143555, "logits/rejected": -0.7040677070617676, "logps/chosen": -6.89398717880249, "logps/rejected": -59.37879943847656, "loss": 0.39657193422317505, "memory(GiB)": 37.58, "nll_loss": 0.2818652391433716, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1999940723180771, "rewards/margins": 4.230030059814453, "rewards/rejected": -4.030035495758057, "step": 5, "train_speed(iter/s)": 0.010659 }, { "epoch": 0.034594594594594595, "grad_norm": 4.551424026489258, "learning_rate": 4.615384615384616e-05, "logits/chosen": -0.39471542835235596, "logits/rejected": -0.6508359909057617, "logps/chosen": -6.633285999298096, "logps/rejected": -58.268653869628906, "loss": 0.5636770129203796, "memory(GiB)": 41.24, "nll_loss": 0.41472452878952026, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1396198272705078, "rewards/margins": 3.7723348140716553, "rewards/rejected": -3.6327152252197266, "step": 6, "train_speed(iter/s)": 0.010667 }, { "epoch": 0.04036036036036036, "grad_norm": 4.302145481109619, "learning_rate": 5.384615384615385e-05, "logits/chosen": -0.42404329776763916, "logits/rejected": -0.7084805369377136, "logps/chosen": -4.09792947769165, "logps/rejected": -69.69088745117188, "loss": 0.5202179551124573, "memory(GiB)": 41.24, "nll_loss": 0.3875095546245575, "rewards/accuracies": 0.9375, "rewards/chosen": -0.018997177481651306, "rewards/margins": 5.0437703132629395, "rewards/rejected": -5.062767505645752, "step": 7, "train_speed(iter/s)": 0.010685 }, { "epoch": 0.04612612612612613, "grad_norm": 4.475785255432129, "learning_rate": 6.153846153846155e-05, "logits/chosen": -0.4411894977092743, "logits/rejected": -0.6594015955924988, "logps/chosen": -6.067828178405762, "logps/rejected": -52.161441802978516, "loss": 0.8079419136047363, "memory(GiB)": 41.24, "nll_loss": 0.5527109503746033, "rewards/accuracies": 0.875, "rewards/chosen": 0.13843362033367157, "rewards/margins": 3.638244390487671, "rewards/rejected": -3.4998104572296143, "step": 8, "train_speed(iter/s)": 0.010699 }, { "epoch": 0.05189189189189189, "grad_norm": 7.412286281585693, "learning_rate": 6.923076923076924e-05, "logits/chosen": -0.4308490753173828, "logits/rejected": -0.6868806481361389, "logps/chosen": -4.5601372718811035, "logps/rejected": -75.88018798828125, "loss": 0.3704576790332794, "memory(GiB)": 41.24, "nll_loss": 0.23506566882133484, "rewards/accuracies": 0.9375, "rewards/chosen": 0.1938612163066864, "rewards/margins": 5.914104461669922, "rewards/rejected": -5.720243453979492, "step": 9, "train_speed(iter/s)": 0.010708 }, { "epoch": 0.05765765765765766, "grad_norm": 2.0841763019561768, "learning_rate": 7.692307692307693e-05, "logits/chosen": -0.4546598792076111, "logits/rejected": -0.7517622113227844, "logps/chosen": -1.471292495727539, "logps/rejected": -70.88200378417969, "loss": 0.2737431526184082, "memory(GiB)": 41.24, "nll_loss": 0.14067727327346802, "rewards/accuracies": 0.9375, "rewards/chosen": 0.13278257846832275, "rewards/margins": 5.628582000732422, "rewards/rejected": -5.495799541473389, "step": 10, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.06342342342342343, "grad_norm": 5.912591457366943, "learning_rate": 8.461538461538461e-05, "logits/chosen": -0.4128813147544861, "logits/rejected": -0.5927000045776367, "logps/chosen": -7.319942474365234, "logps/rejected": -61.27806091308594, "loss": 0.5680095553398132, "memory(GiB)": 41.24, "nll_loss": 0.3753523826599121, "rewards/accuracies": 0.90625, "rewards/chosen": 0.07616602629423141, "rewards/margins": 4.830938816070557, "rewards/rejected": -4.754772663116455, "step": 11, "train_speed(iter/s)": 0.010727 }, { "epoch": 0.06918918918918919, "grad_norm": 2.5374209880828857, "learning_rate": 9.230769230769232e-05, "logits/chosen": -0.349031925201416, "logits/rejected": -0.6373917460441589, "logps/chosen": -4.199922561645508, "logps/rejected": -72.83607482910156, "loss": 0.34027042984962463, "memory(GiB)": 41.24, "nll_loss": 0.22808796167373657, "rewards/accuracies": 0.96875, "rewards/chosen": 0.20608201622962952, "rewards/margins": 5.424815654754639, "rewards/rejected": -5.218733787536621, "step": 12, "train_speed(iter/s)": 0.010728 }, { "epoch": 0.07495495495495495, "grad_norm": 2.7130517959594727, "learning_rate": 0.0001, "logits/chosen": -0.3631379306316376, "logits/rejected": -0.6601940989494324, "logps/chosen": -3.3938565254211426, "logps/rejected": -65.2313232421875, "loss": 0.4514213800430298, "memory(GiB)": 41.24, "nll_loss": 0.30333614349365234, "rewards/accuracies": 0.9375, "rewards/chosen": 0.06806281208992004, "rewards/margins": 4.726724624633789, "rewards/rejected": -4.658661365509033, "step": 13, "train_speed(iter/s)": 0.010733 }, { "epoch": 0.08072072072072072, "grad_norm": 1.5474798679351807, "learning_rate": 0.0001076923076923077, "logits/chosen": -0.4096493124961853, "logits/rejected": -0.6515597105026245, "logps/chosen": -2.300206184387207, "logps/rejected": -57.26811218261719, "loss": 0.3060320019721985, "memory(GiB)": 41.24, "nll_loss": 0.1727571338415146, "rewards/accuracies": 0.9375, "rewards/chosen": 0.08898697793483734, "rewards/margins": 4.1406354904174805, "rewards/rejected": -4.0516486167907715, "step": 14, "train_speed(iter/s)": 0.010737 }, { "epoch": 0.08648648648648649, "grad_norm": 1.628075361251831, "learning_rate": 0.00011538461538461538, "logits/chosen": -0.4402551054954529, "logits/rejected": -0.6672070622444153, "logps/chosen": -2.9995224475860596, "logps/rejected": -53.87057113647461, "loss": 0.3575773239135742, "memory(GiB)": 41.24, "nll_loss": 0.2217392474412918, "rewards/accuracies": 0.9375, "rewards/chosen": 0.20550209283828735, "rewards/margins": 3.6874935626983643, "rewards/rejected": -3.4819912910461426, "step": 15, "train_speed(iter/s)": 0.010742 }, { "epoch": 0.09225225225225225, "grad_norm": 1.838375449180603, "learning_rate": 0.0001230769230769231, "logits/chosen": -0.3547935485839844, "logits/rejected": -0.6626885533332825, "logps/chosen": -4.558413982391357, "logps/rejected": -64.36922454833984, "loss": 0.45015937089920044, "memory(GiB)": 41.24, "nll_loss": 0.3128659129142761, "rewards/accuracies": 0.96875, "rewards/chosen": 0.14241908490657806, "rewards/margins": 4.83186149597168, "rewards/rejected": -4.689442157745361, "step": 16, "train_speed(iter/s)": 0.010745 }, { "epoch": 0.09801801801801802, "grad_norm": 3.119417667388916, "learning_rate": 0.00013076923076923077, "logits/chosen": -0.3334687352180481, "logits/rejected": -0.6293997168540955, "logps/chosen": -5.949204444885254, "logps/rejected": -74.25395965576172, "loss": 0.6850419044494629, "memory(GiB)": 41.24, "nll_loss": 0.5004001259803772, "rewards/accuracies": 0.9375, "rewards/chosen": 0.07516612857580185, "rewards/margins": 4.788809776306152, "rewards/rejected": -4.713644027709961, "step": 17, "train_speed(iter/s)": 0.010741 }, { "epoch": 0.10378378378378378, "grad_norm": 1.6356091499328613, "learning_rate": 0.00013846153846153847, "logits/chosen": -0.3526935875415802, "logits/rejected": -0.6357190608978271, "logps/chosen": -2.911073923110962, "logps/rejected": -66.46131896972656, "loss": 0.32070592045783997, "memory(GiB)": 41.24, "nll_loss": 0.18397927284240723, "rewards/accuracies": 0.9375, "rewards/chosen": 0.09694083034992218, "rewards/margins": 5.153117656707764, "rewards/rejected": -5.056177139282227, "step": 18, "train_speed(iter/s)": 0.010741 }, { "epoch": 0.10954954954954955, "grad_norm": 2.7403504848480225, "learning_rate": 0.00014615384615384615, "logits/chosen": -0.3763662278652191, "logits/rejected": -0.586420476436615, "logps/chosen": -4.417596340179443, "logps/rejected": -58.99639892578125, "loss": 0.4634058177471161, "memory(GiB)": 41.24, "nll_loss": 0.28715017437934875, "rewards/accuracies": 0.9375, "rewards/chosen": 0.1435782015323639, "rewards/margins": 4.609218120574951, "rewards/rejected": -4.465640068054199, "step": 19, "train_speed(iter/s)": 0.010743 }, { "epoch": 0.11531531531531532, "grad_norm": 1.982851266860962, "learning_rate": 0.00015384615384615385, "logits/chosen": -0.3701193332672119, "logits/rejected": -0.6088087558746338, "logps/chosen": -4.619842529296875, "logps/rejected": -68.1020278930664, "loss": 0.4344192445278168, "memory(GiB)": 41.24, "nll_loss": 0.26591166853904724, "rewards/accuracies": 0.9375, "rewards/chosen": 0.10610304027795792, "rewards/margins": 5.044137954711914, "rewards/rejected": -4.938034534454346, "step": 20, "train_speed(iter/s)": 0.010745 }, { "epoch": 0.12108108108108108, "grad_norm": 3.175961494445801, "learning_rate": 0.00016153846153846155, "logits/chosen": -0.40009674429893494, "logits/rejected": -0.642030656337738, "logps/chosen": -3.357761859893799, "logps/rejected": -65.21231842041016, "loss": 0.40142354369163513, "memory(GiB)": 41.24, "nll_loss": 0.2889588177204132, "rewards/accuracies": 0.9375, "rewards/chosen": 0.1323939859867096, "rewards/margins": 5.234187602996826, "rewards/rejected": -5.1017937660217285, "step": 21, "train_speed(iter/s)": 0.010748 }, { "epoch": 0.12684684684684686, "grad_norm": 1.9400721788406372, "learning_rate": 0.00016923076923076923, "logits/chosen": -0.3025435209274292, "logits/rejected": -0.6950021386146545, "logps/chosen": -2.492130994796753, "logps/rejected": -107.03312683105469, "loss": 0.2920421361923218, "memory(GiB)": 41.24, "nll_loss": 0.19772115349769592, "rewards/accuracies": 0.96875, "rewards/chosen": 0.19073158502578735, "rewards/margins": 8.599780082702637, "rewards/rejected": -8.409048080444336, "step": 22, "train_speed(iter/s)": 0.010746 }, { "epoch": 0.13261261261261262, "grad_norm": 1.3099267482757568, "learning_rate": 0.00017692307692307693, "logits/chosen": -0.36498135328292847, "logits/rejected": -0.6359634399414062, "logps/chosen": -2.421377658843994, "logps/rejected": -74.05368041992188, "loss": 0.20869436860084534, "memory(GiB)": 41.24, "nll_loss": 0.11023169010877609, "rewards/accuracies": 1.0, "rewards/chosen": 0.18500684201717377, "rewards/margins": 5.958514213562012, "rewards/rejected": -5.773507118225098, "step": 23, "train_speed(iter/s)": 0.010747 }, { "epoch": 0.13837837837837838, "grad_norm": 1.9334064722061157, "learning_rate": 0.00018461538461538463, "logits/chosen": -0.45037421584129333, "logits/rejected": -0.7719848155975342, "logps/chosen": -2.6665430068969727, "logps/rejected": -94.5350570678711, "loss": 0.3057625889778137, "memory(GiB)": 41.24, "nll_loss": 0.2374470978975296, "rewards/accuracies": 0.96875, "rewards/chosen": 0.09573014080524445, "rewards/margins": 8.040020942687988, "rewards/rejected": -7.944291114807129, "step": 24, "train_speed(iter/s)": 0.010749 }, { "epoch": 0.14414414414414414, "grad_norm": 7.789314270019531, "learning_rate": 0.00019230769230769233, "logits/chosen": -0.3473276197910309, "logits/rejected": -0.6793957352638245, "logps/chosen": -4.235269069671631, "logps/rejected": -109.01844024658203, "loss": 0.42337244749069214, "memory(GiB)": 41.24, "nll_loss": 0.21255403757095337, "rewards/accuracies": 0.96875, "rewards/chosen": 0.009569963440299034, "rewards/margins": 8.769816398620605, "rewards/rejected": -8.760246276855469, "step": 25, "train_speed(iter/s)": 0.010747 }, { "epoch": 0.1499099099099099, "grad_norm": 1.970948338508606, "learning_rate": 0.0002, "logits/chosen": -0.40258127450942993, "logits/rejected": -0.7479668259620667, "logps/chosen": -2.0013341903686523, "logps/rejected": -85.51154327392578, "loss": 0.4197818636894226, "memory(GiB)": 41.24, "nll_loss": 0.2574591636657715, "rewards/accuracies": 1.0, "rewards/chosen": 0.16396881639957428, "rewards/margins": 7.033238410949707, "rewards/rejected": -6.869269847869873, "step": 26, "train_speed(iter/s)": 0.010746 }, { "epoch": 0.15567567567567567, "grad_norm": 11.3534574508667, "learning_rate": 0.00019999796963348897, "logits/chosen": -0.5246711373329163, "logits/rejected": -0.7294141054153442, "logps/chosen": -11.85606575012207, "logps/rejected": -76.03211975097656, "loss": 0.8875234127044678, "memory(GiB)": 41.24, "nll_loss": 0.575400710105896, "rewards/accuracies": 0.90625, "rewards/chosen": -0.2269383817911148, "rewards/margins": 5.498793125152588, "rewards/rejected": -5.725731372833252, "step": 27, "train_speed(iter/s)": 0.010747 }, { "epoch": 0.16144144144144143, "grad_norm": 2.0314371585845947, "learning_rate": 0.00019999187861640362, "logits/chosen": -0.5284671187400818, "logits/rejected": -0.7846834063529968, "logps/chosen": -4.434022426605225, "logps/rejected": -87.89623260498047, "loss": 0.3868662416934967, "memory(GiB)": 41.24, "nll_loss": 0.30320096015930176, "rewards/accuracies": 0.96875, "rewards/chosen": 0.07812386751174927, "rewards/margins": 7.374299049377441, "rewards/rejected": -7.296175479888916, "step": 28, "train_speed(iter/s)": 0.010748 }, { "epoch": 0.16720720720720722, "grad_norm": 6.089433193206787, "learning_rate": 0.0001999817271960839, "logits/chosen": -0.4792092442512512, "logits/rejected": -0.7371792793273926, "logps/chosen": -3.6791412830352783, "logps/rejected": -80.48262023925781, "loss": 0.34335166215896606, "memory(GiB)": 41.24, "nll_loss": 0.22308313846588135, "rewards/accuracies": 0.96875, "rewards/chosen": -0.049518827348947525, "rewards/margins": 6.395692825317383, "rewards/rejected": -6.445211410522461, "step": 29, "train_speed(iter/s)": 0.010751 }, { "epoch": 0.17297297297297298, "grad_norm": 1.8896535634994507, "learning_rate": 0.00019996751578475186, "logits/chosen": -0.44468259811401367, "logits/rejected": -0.7023504972457886, "logps/chosen": -3.048004388809204, "logps/rejected": -80.6348648071289, "loss": 0.30949145555496216, "memory(GiB)": 41.24, "nll_loss": 0.1800393909215927, "rewards/accuracies": 1.0, "rewards/chosen": 0.15738406777381897, "rewards/margins": 5.8682780265808105, "rewards/rejected": -5.710893630981445, "step": 30, "train_speed(iter/s)": 0.010749 }, { "epoch": 0.17873873873873874, "grad_norm": 2.7516067028045654, "learning_rate": 0.00019994924495949504, "logits/chosen": -0.4754641652107239, "logits/rejected": -0.7408227920532227, "logps/chosen": -5.943354606628418, "logps/rejected": -79.13115692138672, "loss": 0.6435320973396301, "memory(GiB)": 41.24, "nll_loss": 0.4586246609687805, "rewards/accuracies": 0.875, "rewards/chosen": 0.0629303902387619, "rewards/margins": 6.110820293426514, "rewards/rejected": -6.0478901863098145, "step": 31, "train_speed(iter/s)": 0.01075 }, { "epoch": 0.1845045045045045, "grad_norm": 5.854465007781982, "learning_rate": 0.00019992691546224278, "logits/chosen": -0.45127877593040466, "logits/rejected": -0.7568551898002625, "logps/chosen": -2.736678123474121, "logps/rejected": -66.9885025024414, "loss": 0.3652667701244354, "memory(GiB)": 41.24, "nll_loss": 0.16899552941322327, "rewards/accuracies": 0.875, "rewards/chosen": 0.050895966589450836, "rewards/margins": 4.933393478393555, "rewards/rejected": -4.882497310638428, "step": 32, "train_speed(iter/s)": 0.01075 }, { "epoch": 0.19027027027027027, "grad_norm": 1.3124663829803467, "learning_rate": 0.00019990052819973642, "logits/chosen": -0.3465266227722168, "logits/rejected": -0.6685288548469543, "logps/chosen": -3.301164388656616, "logps/rejected": -85.9378662109375, "loss": 0.3046538233757019, "memory(GiB)": 41.24, "nll_loss": 0.1670866757631302, "rewards/accuracies": 0.96875, "rewards/chosen": 0.17874348163604736, "rewards/margins": 6.709518909454346, "rewards/rejected": -6.530775547027588, "step": 33, "train_speed(iter/s)": 0.010748 }, { "epoch": 0.19603603603603603, "grad_norm": 2.341381549835205, "learning_rate": 0.00019987008424349225, "logits/chosen": -0.38037875294685364, "logits/rejected": -0.699614405632019, "logps/chosen": -1.5970546007156372, "logps/rejected": -74.28025817871094, "loss": 0.20820346474647522, "memory(GiB)": 41.24, "nll_loss": 0.10679290443658829, "rewards/accuracies": 0.9375, "rewards/chosen": 0.11616384983062744, "rewards/margins": 5.825808048248291, "rewards/rejected": -5.709644794464111, "step": 34, "train_speed(iter/s)": 0.010749 }, { "epoch": 0.2018018018018018, "grad_norm": 5.144662380218506, "learning_rate": 0.00019983558482975799, "logits/chosen": -0.46614986658096313, "logits/rejected": -0.6599275469779968, "logps/chosen": -5.982501983642578, "logps/rejected": -67.7139892578125, "loss": 0.5879941582679749, "memory(GiB)": 41.24, "nll_loss": 0.4303022027015686, "rewards/accuracies": 0.9375, "rewards/chosen": 0.16055577993392944, "rewards/margins": 5.052016258239746, "rewards/rejected": -4.89146089553833, "step": 35, "train_speed(iter/s)": 0.010749 }, { "epoch": 0.20756756756756756, "grad_norm": 1.990370273590088, "learning_rate": 0.00019979703135946278, "logits/chosen": -0.4655105471611023, "logits/rejected": -0.6668959856033325, "logps/chosen": -4.062808036804199, "logps/rejected": -72.87210845947266, "loss": 0.4453062415122986, "memory(GiB)": 41.24, "nll_loss": 0.25426411628723145, "rewards/accuracies": 0.875, "rewards/chosen": 0.09591292589902878, "rewards/margins": 5.528655052185059, "rewards/rejected": -5.432741641998291, "step": 36, "train_speed(iter/s)": 0.010749 }, { "epoch": 0.21333333333333335, "grad_norm": 2.0748369693756104, "learning_rate": 0.00019975442539816012, "logits/chosen": -0.4139191210269928, "logits/rejected": -0.7536109685897827, "logps/chosen": -5.956673622131348, "logps/rejected": -66.99488830566406, "loss": 0.5514004826545715, "memory(GiB)": 41.24, "nll_loss": 0.3969358503818512, "rewards/accuracies": 0.96875, "rewards/chosen": 0.33245787024497986, "rewards/margins": 5.0754570960998535, "rewards/rejected": -4.742999076843262, "step": 37, "train_speed(iter/s)": 0.01075 }, { "epoch": 0.2190990990990991, "grad_norm": 1.6668081283569336, "learning_rate": 0.0001997077686759643, "logits/chosen": -0.42306363582611084, "logits/rejected": -0.6915761232376099, "logps/chosen": -3.814265727996826, "logps/rejected": -82.30941772460938, "loss": 0.3710038363933563, "memory(GiB)": 41.24, "nll_loss": 0.22380009293556213, "rewards/accuracies": 0.9375, "rewards/chosen": 0.06087161600589752, "rewards/margins": 6.076653957366943, "rewards/rejected": -6.015782356262207, "step": 38, "train_speed(iter/s)": 0.01075 }, { "epoch": 0.22486486486486487, "grad_norm": 13.827637672424316, "learning_rate": 0.00019965706308748028, "logits/chosen": -0.49769100546836853, "logits/rejected": -0.7370949983596802, "logps/chosen": -3.956310272216797, "logps/rejected": -79.41323852539062, "loss": 0.6633445620536804, "memory(GiB)": 41.24, "nll_loss": 0.3870386779308319, "rewards/accuracies": 0.90625, "rewards/chosen": -0.13494591414928436, "rewards/margins": 6.147372722625732, "rewards/rejected": -6.282319068908691, "step": 39, "train_speed(iter/s)": 0.010751 }, { "epoch": 0.23063063063063063, "grad_norm": 2.19854474067688, "learning_rate": 0.0001996023106917267, "logits/chosen": -0.44343504309654236, "logits/rejected": -0.6730125546455383, "logps/chosen": -2.9238576889038086, "logps/rejected": -77.40494537353516, "loss": 0.3453696668148041, "memory(GiB)": 41.24, "nll_loss": 0.19069285690784454, "rewards/accuracies": 0.9375, "rewards/chosen": 0.14595907926559448, "rewards/margins": 6.002254486083984, "rewards/rejected": -5.856295108795166, "step": 40, "train_speed(iter/s)": 0.010752 }, { "epoch": 0.2363963963963964, "grad_norm": 6.0794596672058105, "learning_rate": 0.00019954351371205203, "logits/chosen": -0.47579658031463623, "logits/rejected": -0.6826990842819214, "logps/chosen": -5.335310935974121, "logps/rejected": -75.78384399414062, "loss": 0.575509250164032, "memory(GiB)": 41.24, "nll_loss": 0.4477939307689667, "rewards/accuracies": 0.96875, "rewards/chosen": 0.2103371024131775, "rewards/margins": 6.012211322784424, "rewards/rejected": -5.801875114440918, "step": 41, "train_speed(iter/s)": 0.010754 }, { "epoch": 0.24216216216216216, "grad_norm": 1.4152264595031738, "learning_rate": 0.00019948067453604473, "logits/chosen": -0.49620914459228516, "logits/rejected": -0.7446714043617249, "logps/chosen": -3.284031867980957, "logps/rejected": -77.9183349609375, "loss": 0.29828324913978577, "memory(GiB)": 41.24, "nll_loss": 0.21160344779491425, "rewards/accuracies": 0.96875, "rewards/chosen": 0.18678154051303864, "rewards/margins": 6.247434616088867, "rewards/rejected": -6.060652732849121, "step": 42, "train_speed(iter/s)": 0.010755 }, { "epoch": 0.24792792792792792, "grad_norm": 2.9591963291168213, "learning_rate": 0.00019941379571543596, "logits/chosen": -0.4777877628803253, "logits/rejected": -0.6974171996116638, "logps/chosen": -2.9466118812561035, "logps/rejected": -66.2719497680664, "loss": 0.35521066188812256, "memory(GiB)": 41.24, "nll_loss": 0.22793087363243103, "rewards/accuracies": 0.9375, "rewards/chosen": 0.27246373891830444, "rewards/margins": 5.403186798095703, "rewards/rejected": -5.130722999572754, "step": 43, "train_speed(iter/s)": 0.010756 }, { "epoch": 0.2536936936936937, "grad_norm": 4.199843883514404, "learning_rate": 0.00019934287996599607, "logits/chosen": -0.4372207522392273, "logits/rejected": -0.700534462928772, "logps/chosen": -3.31451416015625, "logps/rejected": -70.0909194946289, "loss": 0.3793654143810272, "memory(GiB)": 41.24, "nll_loss": 0.20433279871940613, "rewards/accuracies": 0.9375, "rewards/chosen": 0.059201404452323914, "rewards/margins": 4.912087917327881, "rewards/rejected": -4.852885723114014, "step": 44, "train_speed(iter/s)": 0.010756 }, { "epoch": 0.2594594594594595, "grad_norm": 0.7397028803825378, "learning_rate": 0.00019926793016742435, "logits/chosen": -0.42062634229660034, "logits/rejected": -0.7593384981155396, "logps/chosen": -1.404799222946167, "logps/rejected": -102.4892349243164, "loss": 0.1313902586698532, "memory(GiB)": 41.24, "nll_loss": 0.09521690011024475, "rewards/accuracies": 1.0, "rewards/chosen": 0.12229674309492111, "rewards/margins": 8.041703224182129, "rewards/rejected": -7.919405937194824, "step": 45, "train_speed(iter/s)": 0.010754 }, { "epoch": 0.26522522522522524, "grad_norm": 5.14201545715332, "learning_rate": 0.00019918894936323195, "logits/chosen": -0.3798273205757141, "logits/rejected": -0.5865642428398132, "logps/chosen": -6.911247730255127, "logps/rejected": -72.06941223144531, "loss": 0.49299517273902893, "memory(GiB)": 41.24, "nll_loss": 0.27924880385398865, "rewards/accuracies": 0.875, "rewards/chosen": 0.1307646483182907, "rewards/margins": 5.647462368011475, "rewards/rejected": -5.516696929931641, "step": 46, "train_speed(iter/s)": 0.010753 }, { "epoch": 0.270990990990991, "grad_norm": 1.6439752578735352, "learning_rate": 0.00019910594076061853, "logits/chosen": -0.4431299567222595, "logits/rejected": -0.7268660664558411, "logps/chosen": -2.0275888442993164, "logps/rejected": -81.84529876708984, "loss": 0.23740296065807343, "memory(GiB)": 41.24, "nll_loss": 0.14832313358783722, "rewards/accuracies": 0.96875, "rewards/chosen": 0.06923090666532516, "rewards/margins": 6.1783928871154785, "rewards/rejected": -6.109161376953125, "step": 47, "train_speed(iter/s)": 0.010753 }, { "epoch": 0.27675675675675676, "grad_norm": 6.499570846557617, "learning_rate": 0.0001990189077303418, "logits/chosen": -0.45142635703086853, "logits/rejected": -0.7249264121055603, "logps/chosen": -5.794652938842773, "logps/rejected": -78.53363800048828, "loss": 0.46158841252326965, "memory(GiB)": 41.24, "nll_loss": 0.3398270010948181, "rewards/accuracies": 0.96875, "rewards/chosen": 0.24555836617946625, "rewards/margins": 6.308343887329102, "rewards/rejected": -6.062786102294922, "step": 48, "train_speed(iter/s)": 0.010753 }, { "epoch": 0.2825225225225225, "grad_norm": 5.58511209487915, "learning_rate": 0.00019892785380658078, "logits/chosen": -0.4099079370498657, "logits/rejected": -0.6898340582847595, "logps/chosen": -7.449429035186768, "logps/rejected": -92.18098449707031, "loss": 0.5815075039863586, "memory(GiB)": 41.24, "nll_loss": 0.41358357667922974, "rewards/accuracies": 0.9375, "rewards/chosen": -0.053265977650880814, "rewards/margins": 7.150655269622803, "rewards/rejected": -7.203920841217041, "step": 49, "train_speed(iter/s)": 0.010752 }, { "epoch": 0.2882882882882883, "grad_norm": 1.5411535501480103, "learning_rate": 0.00019883278268679216, "logits/chosen": -0.4670988917350769, "logits/rejected": -0.6586328148841858, "logps/chosen": -6.984646320343018, "logps/rejected": -89.9208755493164, "loss": 0.45735102891921997, "memory(GiB)": 41.24, "nll_loss": 0.28862154483795166, "rewards/accuracies": 0.90625, "rewards/chosen": 0.1682412177324295, "rewards/margins": 7.457679748535156, "rewards/rejected": -7.289438247680664, "step": 50, "train_speed(iter/s)": 0.01075 }, { "epoch": 0.29405405405405405, "grad_norm": 6.264907360076904, "learning_rate": 0.00019873369823156036, "logits/chosen": -0.35443419218063354, "logits/rejected": -0.7265148758888245, "logps/chosen": -5.11212158203125, "logps/rejected": -97.37500762939453, "loss": 0.648152232170105, "memory(GiB)": 41.24, "nll_loss": 0.5091428756713867, "rewards/accuracies": 0.9375, "rewards/chosen": -0.03551238775253296, "rewards/margins": 7.55380392074585, "rewards/rejected": -7.589317321777344, "step": 51, "train_speed(iter/s)": 0.010707 }, { "epoch": 0.2998198198198198, "grad_norm": 2.1848013401031494, "learning_rate": 0.00019863060446444054, "logits/chosen": -0.5179776549339294, "logits/rejected": -0.7255269289016724, "logps/chosen": -6.782817363739014, "logps/rejected": -86.8519515991211, "loss": 0.5702924728393555, "memory(GiB)": 41.24, "nll_loss": 0.3926149308681488, "rewards/accuracies": 0.90625, "rewards/chosen": 0.05346503108739853, "rewards/margins": 7.021766185760498, "rewards/rejected": -6.968300819396973, "step": 52, "train_speed(iter/s)": 0.010708 }, { "epoch": 0.3055855855855856, "grad_norm": 3.3478569984436035, "learning_rate": 0.00019852350557179538, "logits/chosen": -0.5434097051620483, "logits/rejected": -0.8009167313575745, "logps/chosen": -4.053906440734863, "logps/rejected": -105.9520263671875, "loss": 0.4421282112598419, "memory(GiB)": 41.24, "nll_loss": 0.3492012917995453, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1857108175754547, "rewards/margins": 9.035101890563965, "rewards/rejected": -8.849390983581543, "step": 53, "train_speed(iter/s)": 0.010709 }, { "epoch": 0.31135135135135134, "grad_norm": 0.8761724829673767, "learning_rate": 0.00019841240590262493, "logits/chosen": -0.45293307304382324, "logits/rejected": -0.7608242034912109, "logps/chosen": -0.6350191831588745, "logps/rejected": -91.82192993164062, "loss": 0.11042662709951401, "memory(GiB)": 41.24, "nll_loss": 0.06284812837839127, "rewards/accuracies": 1.0, "rewards/chosen": 0.1965743899345398, "rewards/margins": 7.520632743835449, "rewards/rejected": -7.324058532714844, "step": 54, "train_speed(iter/s)": 0.01071 }, { "epoch": 0.3171171171171171, "grad_norm": 5.344722747802734, "learning_rate": 0.0001982973099683902, "logits/chosen": -0.5431379675865173, "logits/rejected": -0.8100754022598267, "logps/chosen": -1.98147714138031, "logps/rejected": -91.00532531738281, "loss": 0.3004758059978485, "memory(GiB)": 41.24, "nll_loss": 0.1778518110513687, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1774783581495285, "rewards/margins": 7.744819641113281, "rewards/rejected": -7.567340850830078, "step": 55, "train_speed(iter/s)": 0.010711 }, { "epoch": 0.32288288288288286, "grad_norm": 5.424385070800781, "learning_rate": 0.00019817822244282973, "logits/chosen": -0.48769453167915344, "logits/rejected": -0.7255769371986389, "logps/chosen": -3.6506757736206055, "logps/rejected": -84.81509399414062, "loss": 0.4457959830760956, "memory(GiB)": 41.24, "nll_loss": 0.23988068103790283, "rewards/accuracies": 0.875, "rewards/chosen": 0.11002250760793686, "rewards/margins": 6.652472019195557, "rewards/rejected": -6.542449951171875, "step": 56, "train_speed(iter/s)": 0.010711 }, { "epoch": 0.3286486486486486, "grad_norm": 2.3812549114227295, "learning_rate": 0.00019805514816177006, "logits/chosen": -0.556337833404541, "logits/rejected": -0.7923259735107422, "logps/chosen": -5.455251693725586, "logps/rejected": -89.06196594238281, "loss": 0.4395422339439392, "memory(GiB)": 41.24, "nll_loss": 0.29659417271614075, "rewards/accuracies": 0.9375, "rewards/chosen": -0.01958906650543213, "rewards/margins": 6.816771984100342, "rewards/rejected": -6.836360931396484, "step": 57, "train_speed(iter/s)": 0.01071 }, { "epoch": 0.33441441441441444, "grad_norm": 8.72442626953125, "learning_rate": 0.00019792809212292912, "logits/chosen": -0.6302639842033386, "logits/rejected": -0.9231972098350525, "logps/chosen": -5.753312110900879, "logps/rejected": -103.71651458740234, "loss": 1.1447618007659912, "memory(GiB)": 41.24, "nll_loss": 0.6733683943748474, "rewards/accuracies": 0.96875, "rewards/chosen": -0.26626041531562805, "rewards/margins": 8.245807647705078, "rewards/rejected": -8.512067794799805, "step": 58, "train_speed(iter/s)": 0.010711 }, { "epoch": 0.3401801801801802, "grad_norm": 2.6023576259613037, "learning_rate": 0.00019779705948571346, "logits/chosen": -0.5867213010787964, "logits/rejected": -0.8538931608200073, "logps/chosen": -3.069394111633301, "logps/rejected": -96.5278091430664, "loss": 0.3167837858200073, "memory(GiB)": 41.24, "nll_loss": 0.20217999815940857, "rewards/accuracies": 0.9375, "rewards/chosen": 0.10776210576295853, "rewards/margins": 8.32030963897705, "rewards/rejected": -8.21254825592041, "step": 59, "train_speed(iter/s)": 0.010712 }, { "epoch": 0.34594594594594597, "grad_norm": 2.678529977798462, "learning_rate": 0.00019766205557100868, "logits/chosen": -0.6138476133346558, "logits/rejected": -0.7842435836791992, "logps/chosen": -6.119746208190918, "logps/rejected": -88.4565658569336, "loss": 0.44386592507362366, "memory(GiB)": 41.24, "nll_loss": 0.2780015468597412, "rewards/accuracies": 0.96875, "rewards/chosen": 0.06730165332555771, "rewards/margins": 7.516484260559082, "rewards/rejected": -7.449182987213135, "step": 60, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.3517117117117117, "grad_norm": 2.223165512084961, "learning_rate": 0.00019752308586096326, "logits/chosen": -0.5360291004180908, "logits/rejected": -0.894256591796875, "logps/chosen": -1.3611795902252197, "logps/rejected": -122.1118392944336, "loss": 0.13098187744617462, "memory(GiB)": 41.24, "nll_loss": 0.07775433361530304, "rewards/accuracies": 1.0, "rewards/chosen": 0.12457617372274399, "rewards/margins": 10.008496284484863, "rewards/rejected": -9.883918762207031, "step": 61, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.3574774774774775, "grad_norm": 10.891358375549316, "learning_rate": 0.0001973801559987661, "logits/chosen": -0.7173175811767578, "logits/rejected": -0.8792683482170105, "logps/chosen": -12.6211519241333, "logps/rejected": -73.51658630371094, "loss": 1.0753252506256104, "memory(GiB)": 41.24, "nll_loss": 0.9100903868675232, "rewards/accuracies": 0.9375, "rewards/chosen": -0.495037317276001, "rewards/margins": 5.504097938537598, "rewards/rejected": -5.9991350173950195, "step": 62, "train_speed(iter/s)": 0.010715 }, { "epoch": 0.36324324324324325, "grad_norm": 26.432544708251953, "learning_rate": 0.00019723327178841743, "logits/chosen": -0.6629639267921448, "logits/rejected": -0.8958379030227661, "logps/chosen": -5.678650856018066, "logps/rejected": -81.07159423828125, "loss": 0.6158818602561951, "memory(GiB)": 41.24, "nll_loss": 0.4310333728790283, "rewards/accuracies": 0.875, "rewards/chosen": 0.02597002126276493, "rewards/margins": 6.523518085479736, "rewards/rejected": -6.497547149658203, "step": 63, "train_speed(iter/s)": 0.010716 }, { "epoch": 0.369009009009009, "grad_norm": 4.643962860107422, "learning_rate": 0.0001970824391944927, "logits/chosen": -0.6061327457427979, "logits/rejected": -0.8394734859466553, "logps/chosen": -6.52767276763916, "logps/rejected": -74.48380279541016, "loss": 0.5795359015464783, "memory(GiB)": 41.24, "nll_loss": 0.414874792098999, "rewards/accuracies": 0.9375, "rewards/chosen": 0.0007130205631256104, "rewards/margins": 5.6362080574035645, "rewards/rejected": -5.635494709014893, "step": 64, "train_speed(iter/s)": 0.010716 }, { "epoch": 0.3747747747747748, "grad_norm": 1.8694281578063965, "learning_rate": 0.00019692766434190105, "logits/chosen": -0.6322288513183594, "logits/rejected": -0.8566944003105164, "logps/chosen": -1.9187999963760376, "logps/rejected": -56.726871490478516, "loss": 0.26561087369918823, "memory(GiB)": 41.24, "nll_loss": 0.12671466171741486, "rewards/accuracies": 0.9375, "rewards/chosen": 0.17268410325050354, "rewards/margins": 4.417227268218994, "rewards/rejected": -4.244543075561523, "step": 65, "train_speed(iter/s)": 0.010717 }, { "epoch": 0.38054054054054054, "grad_norm": 2.3087944984436035, "learning_rate": 0.00019676895351563588, "logits/chosen": -0.6048943996429443, "logits/rejected": -0.8088940382003784, "logps/chosen": -4.430207252502441, "logps/rejected": -64.05681610107422, "loss": 0.33754763007164, "memory(GiB)": 41.24, "nll_loss": 0.22767014801502228, "rewards/accuracies": 0.96875, "rewards/chosen": 0.025299668312072754, "rewards/margins": 4.6934709548950195, "rewards/rejected": -4.668170928955078, "step": 66, "train_speed(iter/s)": 0.010717 }, { "epoch": 0.3863063063063063, "grad_norm": 2.2111432552337646, "learning_rate": 0.00019660631316052021, "logits/chosen": -0.623546838760376, "logits/rejected": -0.811290979385376, "logps/chosen": -6.471018314361572, "logps/rejected": -57.678314208984375, "loss": 0.4503980875015259, "memory(GiB)": 41.24, "nll_loss": 0.34320953488349915, "rewards/accuracies": 0.96875, "rewards/chosen": -0.06837636232376099, "rewards/margins": 4.10473108291626, "rewards/rejected": -4.173107624053955, "step": 67, "train_speed(iter/s)": 0.010718 }, { "epoch": 0.39207207207207206, "grad_norm": 1.7001421451568604, "learning_rate": 0.00019643974988094458, "logits/chosen": -0.5895470380783081, "logits/rejected": -0.7888103723526001, "logps/chosen": -5.163002014160156, "logps/rejected": -45.541908264160156, "loss": 0.42964497208595276, "memory(GiB)": 41.24, "nll_loss": 0.3103106617927551, "rewards/accuracies": 1.0, "rewards/chosen": 0.3456801772117615, "rewards/margins": 3.432896614074707, "rewards/rejected": -3.08721661567688, "step": 68, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.3978378378378378, "grad_norm": 3.909360885620117, "learning_rate": 0.00019626927044059914, "logits/chosen": -0.6134467124938965, "logits/rejected": -0.7660009860992432, "logps/chosen": -5.3520307540893555, "logps/rejected": -49.259185791015625, "loss": 0.5181165337562561, "memory(GiB)": 41.24, "nll_loss": 0.30421963334083557, "rewards/accuracies": 0.9375, "rewards/chosen": 0.014049924910068512, "rewards/margins": 3.3693478107452393, "rewards/rejected": -3.355297565460205, "step": 69, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.4036036036036036, "grad_norm": 2.67299485206604, "learning_rate": 0.00019609488176219886, "logits/chosen": -0.6107767820358276, "logits/rejected": -0.7868641018867493, "logps/chosen": -3.616837501525879, "logps/rejected": -50.11117172241211, "loss": 0.3146559000015259, "memory(GiB)": 41.24, "nll_loss": 0.21267317235469818, "rewards/accuracies": 1.0, "rewards/chosen": 0.13358786702156067, "rewards/margins": 3.8761374950408936, "rewards/rejected": -3.742549419403076, "step": 70, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.40936936936936935, "grad_norm": 7.013823509216309, "learning_rate": 0.00019591659092720227, "logits/chosen": -0.5896518230438232, "logits/rejected": -0.858326256275177, "logps/chosen": -2.8418002128601074, "logps/rejected": -64.546630859375, "loss": 0.37414392828941345, "memory(GiB)": 41.24, "nll_loss": 0.25448697805404663, "rewards/accuracies": 0.96875, "rewards/chosen": 0.024522263556718826, "rewards/margins": 4.37087345123291, "rewards/rejected": -4.346351623535156, "step": 71, "train_speed(iter/s)": 0.010722 }, { "epoch": 0.4151351351351351, "grad_norm": 2.0888102054595947, "learning_rate": 0.00019573440517552427, "logits/chosen": -0.5669695138931274, "logits/rejected": -0.7572087049484253, "logps/chosen": -2.418893337249756, "logps/rejected": -50.858699798583984, "loss": 0.3724361062049866, "memory(GiB)": 41.24, "nll_loss": 0.20290419459342957, "rewards/accuracies": 0.90625, "rewards/chosen": 0.16552519798278809, "rewards/margins": 3.5489120483398438, "rewards/rejected": -3.3833868503570557, "step": 72, "train_speed(iter/s)": 0.010723 }, { "epoch": 0.4209009009009009, "grad_norm": 1.9631896018981934, "learning_rate": 0.00019554833190524182, "logits/chosen": -0.575507402420044, "logits/rejected": -0.7697166204452515, "logps/chosen": -3.5829074382781982, "logps/rejected": -52.79640197753906, "loss": 0.400629460811615, "memory(GiB)": 41.24, "nll_loss": 0.2976799011230469, "rewards/accuracies": 0.96875, "rewards/chosen": 0.17720367014408112, "rewards/margins": 4.019702434539795, "rewards/rejected": -3.842499017715454, "step": 73, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.4266666666666667, "grad_norm": 3.227459192276001, "learning_rate": 0.00019535837867229363, "logits/chosen": -0.6866841316223145, "logits/rejected": -0.8467439413070679, "logps/chosen": -1.4898688793182373, "logps/rejected": -52.35246276855469, "loss": 0.2691449224948883, "memory(GiB)": 41.24, "nll_loss": 0.16896064579486847, "rewards/accuracies": 1.0, "rewards/chosen": 0.20350010693073273, "rewards/margins": 4.1118974685668945, "rewards/rejected": -3.9083974361419678, "step": 74, "train_speed(iter/s)": 0.010726 }, { "epoch": 0.43243243243243246, "grad_norm": 2.0599851608276367, "learning_rate": 0.0001951645531901734, "logits/chosen": -0.6125411987304688, "logits/rejected": -0.8178025484085083, "logps/chosen": -5.753840923309326, "logps/rejected": -60.490638732910156, "loss": 0.4720686376094818, "memory(GiB)": 41.24, "nll_loss": 0.2955226004123688, "rewards/accuracies": 0.875, "rewards/chosen": 0.02442253567278385, "rewards/margins": 4.439631462097168, "rewards/rejected": -4.41520881652832, "step": 75, "train_speed(iter/s)": 0.010726 }, { "epoch": 0.4381981981981982, "grad_norm": 1.8315515518188477, "learning_rate": 0.00019496686332961646, "logits/chosen": -0.5511488914489746, "logits/rejected": -0.8103834390640259, "logps/chosen": -2.737548828125, "logps/rejected": -72.79937744140625, "loss": 0.2598808705806732, "memory(GiB)": 41.24, "nll_loss": 0.20735348761081696, "rewards/accuracies": 1.0, "rewards/chosen": 0.20416659116744995, "rewards/margins": 5.639776706695557, "rewards/rejected": -5.435609817504883, "step": 76, "train_speed(iter/s)": 0.010726 }, { "epoch": 0.443963963963964, "grad_norm": 4.658299922943115, "learning_rate": 0.00019476531711828027, "logits/chosen": -0.5621539354324341, "logits/rejected": -0.817601203918457, "logps/chosen": -2.554128646850586, "logps/rejected": -75.40179443359375, "loss": 0.29839468002319336, "memory(GiB)": 41.24, "nll_loss": 0.21096321940422058, "rewards/accuracies": 0.9375, "rewards/chosen": 0.11831088364124298, "rewards/margins": 5.797797679901123, "rewards/rejected": -5.679486274719238, "step": 77, "train_speed(iter/s)": 0.010727 }, { "epoch": 0.44972972972972974, "grad_norm": 7.5920844078063965, "learning_rate": 0.00019455992274041835, "logits/chosen": -0.5446800589561462, "logits/rejected": -0.7866684794425964, "logps/chosen": -5.180241584777832, "logps/rejected": -80.02595520019531, "loss": 0.4992501735687256, "memory(GiB)": 41.24, "nll_loss": 0.4071677029132843, "rewards/accuracies": 0.9375, "rewards/chosen": 0.006200561299920082, "rewards/margins": 6.354435920715332, "rewards/rejected": -6.348235607147217, "step": 78, "train_speed(iter/s)": 0.010728 }, { "epoch": 0.4554954954954955, "grad_norm": 2.045180082321167, "learning_rate": 0.00019435068853654807, "logits/chosen": -0.5892366170883179, "logits/rejected": -0.782485842704773, "logps/chosen": -7.082699775695801, "logps/rejected": -76.8997573852539, "loss": 0.4684464931488037, "memory(GiB)": 41.24, "nll_loss": 0.38624832034111023, "rewards/accuracies": 0.9375, "rewards/chosen": 0.03203499689698219, "rewards/margins": 5.84527587890625, "rewards/rejected": -5.813241004943848, "step": 79, "train_speed(iter/s)": 0.010728 }, { "epoch": 0.46126126126126127, "grad_norm": 6.412923812866211, "learning_rate": 0.00019413762300311182, "logits/chosen": -0.6524518728256226, "logits/rejected": -0.8889943957328796, "logps/chosen": -6.470341682434082, "logps/rejected": -86.74302673339844, "loss": 0.7839629650115967, "memory(GiB)": 41.24, "nll_loss": 0.6858316659927368, "rewards/accuracies": 0.9375, "rewards/chosen": -0.10852594673633575, "rewards/margins": 6.819857120513916, "rewards/rejected": -6.928382873535156, "step": 80, "train_speed(iter/s)": 0.010729 }, { "epoch": 0.46702702702702703, "grad_norm": 2.171276807785034, "learning_rate": 0.00019392073479213213, "logits/chosen": -0.5607702136039734, "logits/rejected": -0.7560180425643921, "logps/chosen": -6.120340347290039, "logps/rejected": -81.5516128540039, "loss": 0.575468897819519, "memory(GiB)": 41.24, "nll_loss": 0.3079308271408081, "rewards/accuracies": 0.9375, "rewards/chosen": -0.05391833186149597, "rewards/margins": 5.951426029205322, "rewards/rejected": -6.005344390869141, "step": 81, "train_speed(iter/s)": 0.010729 }, { "epoch": 0.4727927927927928, "grad_norm": 1.5074808597564697, "learning_rate": 0.0001937000327108601, "logits/chosen": -0.5817635655403137, "logits/rejected": -0.8122580051422119, "logps/chosen": -3.3293583393096924, "logps/rejected": -76.75574493408203, "loss": 0.27197888493537903, "memory(GiB)": 41.24, "nll_loss": 0.1920165866613388, "rewards/accuracies": 0.96875, "rewards/chosen": 0.04472556710243225, "rewards/margins": 6.159332275390625, "rewards/rejected": -6.114606857299805, "step": 82, "train_speed(iter/s)": 0.01073 }, { "epoch": 0.47855855855855856, "grad_norm": 8.971928596496582, "learning_rate": 0.0001934755257214181, "logits/chosen": -0.5557482838630676, "logits/rejected": -0.791240930557251, "logps/chosen": -5.363508701324463, "logps/rejected": -71.66944122314453, "loss": 0.8509294986724854, "memory(GiB)": 41.24, "nll_loss": 0.7254281640052795, "rewards/accuracies": 0.9375, "rewards/chosen": -0.1657000482082367, "rewards/margins": 5.284771919250488, "rewards/rejected": -5.450472354888916, "step": 83, "train_speed(iter/s)": 0.010731 }, { "epoch": 0.4843243243243243, "grad_norm": 3.7317609786987305, "learning_rate": 0.00019324722294043558, "logits/chosen": -0.49631816148757935, "logits/rejected": -0.7238998413085938, "logps/chosen": -5.0319366455078125, "logps/rejected": -55.3072395324707, "loss": 0.4805355668067932, "memory(GiB)": 41.24, "nll_loss": 0.30268925428390503, "rewards/accuracies": 0.90625, "rewards/chosen": 0.16919195652008057, "rewards/margins": 4.183167934417725, "rewards/rejected": -4.013975620269775, "step": 84, "train_speed(iter/s)": 0.010732 }, { "epoch": 0.4900900900900901, "grad_norm": 7.251592636108398, "learning_rate": 0.00019301513363867895, "logits/chosen": -0.4797047972679138, "logits/rejected": -0.699076771736145, "logps/chosen": -4.068089485168457, "logps/rejected": -62.654762268066406, "loss": 0.41215279698371887, "memory(GiB)": 41.24, "nll_loss": 0.3088461756706238, "rewards/accuracies": 0.9375, "rewards/chosen": 0.13345223665237427, "rewards/margins": 4.483903884887695, "rewards/rejected": -4.350452423095703, "step": 85, "train_speed(iter/s)": 0.010732 }, { "epoch": 0.49585585585585584, "grad_norm": 1.6465262174606323, "learning_rate": 0.0001927792672406751, "logits/chosen": -0.4875030219554901, "logits/rejected": -0.7307705879211426, "logps/chosen": -2.494859218597412, "logps/rejected": -57.72221374511719, "loss": 0.31443703174591064, "memory(GiB)": 41.24, "nll_loss": 0.1957024335861206, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1970575600862503, "rewards/margins": 4.039019584655762, "rewards/rejected": -3.8419618606567383, "step": 86, "train_speed(iter/s)": 0.010732 }, { "epoch": 0.5016216216216216, "grad_norm": 2.362053394317627, "learning_rate": 0.00019253963332432878, "logits/chosen": -0.6053374409675598, "logits/rejected": -0.7439757585525513, "logps/chosen": -5.3451008796691895, "logps/rejected": -47.488853454589844, "loss": 0.4348059296607971, "memory(GiB)": 41.24, "nll_loss": 0.23809021711349487, "rewards/accuracies": 0.9375, "rewards/chosen": -0.019803959876298904, "rewards/margins": 3.427215099334717, "rewards/rejected": -3.447019338607788, "step": 87, "train_speed(iter/s)": 0.010733 }, { "epoch": 0.5073873873873874, "grad_norm": 2.1728515625, "learning_rate": 0.00019229624162053356, "logits/chosen": -0.5406431555747986, "logits/rejected": -0.739841103553772, "logps/chosen": -2.6260576248168945, "logps/rejected": -56.7901496887207, "loss": 0.4087463915348053, "memory(GiB)": 41.24, "nll_loss": 0.2899452745914459, "rewards/accuracies": 0.90625, "rewards/chosen": 0.0745973214507103, "rewards/margins": 4.15200662612915, "rewards/rejected": -4.077408790588379, "step": 88, "train_speed(iter/s)": 0.010733 }, { "epoch": 0.5131531531531531, "grad_norm": 1.563063144683838, "learning_rate": 0.00019204910201277672, "logits/chosen": -0.5593241453170776, "logits/rejected": -0.7506377100944519, "logps/chosen": -3.1961171627044678, "logps/rejected": -63.025291442871094, "loss": 0.20274411141872406, "memory(GiB)": 41.24, "nll_loss": 0.15050008893013, "rewards/accuracies": 1.0, "rewards/chosen": 0.13150721788406372, "rewards/margins": 4.959373950958252, "rewards/rejected": -4.827866554260254, "step": 89, "train_speed(iter/s)": 0.010734 }, { "epoch": 0.518918918918919, "grad_norm": 1.8057938814163208, "learning_rate": 0.0001917982245367379, "logits/chosen": -0.5387026071548462, "logits/rejected": -0.779965341091156, "logps/chosen": -5.658284664154053, "logps/rejected": -61.30659484863281, "loss": 0.5316486358642578, "memory(GiB)": 41.24, "nll_loss": 0.4009394347667694, "rewards/accuracies": 0.9375, "rewards/chosen": 0.2519141137599945, "rewards/margins": 4.251716613769531, "rewards/rejected": -3.9998018741607666, "step": 90, "train_speed(iter/s)": 0.010734 }, { "epoch": 0.5246846846846847, "grad_norm": 1.6844978332519531, "learning_rate": 0.00019154361937988163, "logits/chosen": -0.5544890761375427, "logits/rejected": -0.7064109444618225, "logps/chosen": -6.5527496337890625, "logps/rejected": -65.5311050415039, "loss": 0.38739749789237976, "memory(GiB)": 41.24, "nll_loss": 0.2913617193698883, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1942709982395172, "rewards/margins": 5.296841621398926, "rewards/rejected": -5.102570533752441, "step": 91, "train_speed(iter/s)": 0.010734 }, { "epoch": 0.5304504504504505, "grad_norm": 3.110102653503418, "learning_rate": 0.00019128529688104364, "logits/chosen": -0.5477601885795593, "logits/rejected": -0.7957394123077393, "logps/chosen": -2.064303398132324, "logps/rejected": -68.15472412109375, "loss": 0.3176850974559784, "memory(GiB)": 41.24, "nll_loss": 0.21008610725402832, "rewards/accuracies": 0.9375, "rewards/chosen": 0.18838940560817719, "rewards/margins": 5.544022560119629, "rewards/rejected": -5.355632781982422, "step": 92, "train_speed(iter/s)": 0.010735 }, { "epoch": 0.5362162162162162, "grad_norm": 3.8029165267944336, "learning_rate": 0.00019102326753001086, "logits/chosen": -0.5357910394668579, "logits/rejected": -0.7163031101226807, "logps/chosen": -4.390456676483154, "logps/rejected": -55.20818328857422, "loss": 0.4618917405605316, "memory(GiB)": 41.24, "nll_loss": 0.33474794030189514, "rewards/accuracies": 1.0, "rewards/chosen": 0.36951008439064026, "rewards/margins": 4.2895612716674805, "rewards/rejected": -3.920051336288452, "step": 93, "train_speed(iter/s)": 0.010735 }, { "epoch": 0.541981981981982, "grad_norm": 1.8191365003585815, "learning_rate": 0.00019075754196709572, "logits/chosen": -0.5523058176040649, "logits/rejected": -0.7712856531143188, "logps/chosen": -2.1930363178253174, "logps/rejected": -66.22615814208984, "loss": 0.28284692764282227, "memory(GiB)": 41.24, "nll_loss": 0.2161579132080078, "rewards/accuracies": 1.0, "rewards/chosen": 0.14300797879695892, "rewards/margins": 5.302109718322754, "rewards/rejected": -5.159101486206055, "step": 94, "train_speed(iter/s)": 0.010735 }, { "epoch": 0.5477477477477477, "grad_norm": 2.65755558013916, "learning_rate": 0.00019048813098270387, "logits/chosen": -0.49344098567962646, "logits/rejected": -0.7781980633735657, "logps/chosen": -3.545104742050171, "logps/rejected": -78.23759460449219, "loss": 0.3401697278022766, "memory(GiB)": 41.24, "nll_loss": 0.3010118901729584, "rewards/accuracies": 1.0, "rewards/chosen": 0.07626594603061676, "rewards/margins": 5.846086025238037, "rewards/rejected": -5.769820213317871, "step": 95, "train_speed(iter/s)": 0.010736 }, { "epoch": 0.5535135135135135, "grad_norm": 1.6140971183776855, "learning_rate": 0.0001902150455168962, "logits/chosen": -0.4496663808822632, "logits/rejected": -0.7431093454360962, "logps/chosen": -2.8349695205688477, "logps/rejected": -72.62895965576172, "loss": 0.3297802209854126, "memory(GiB)": 41.24, "nll_loss": 0.2532678544521332, "rewards/accuracies": 1.0, "rewards/chosen": 0.149441659450531, "rewards/margins": 5.512978553771973, "rewards/rejected": -5.363536357879639, "step": 96, "train_speed(iter/s)": 0.010735 }, { "epoch": 0.5592792792792792, "grad_norm": 2.243736743927002, "learning_rate": 0.0001899382966589443, "logits/chosen": -0.44952693581581116, "logits/rejected": -0.7028639316558838, "logps/chosen": -5.277416229248047, "logps/rejected": -69.73493957519531, "loss": 0.41486623883247375, "memory(GiB)": 41.24, "nll_loss": 0.25434425473213196, "rewards/accuracies": 0.96875, "rewards/chosen": 0.13436982035636902, "rewards/margins": 4.8991923332214355, "rewards/rejected": -4.764822006225586, "step": 97, "train_speed(iter/s)": 0.010735 }, { "epoch": 0.565045045045045, "grad_norm": 4.0099101066589355, "learning_rate": 0.0001896578956468805, "logits/chosen": -0.5480562448501587, "logits/rejected": -0.7537853717803955, "logps/chosen": -4.075699806213379, "logps/rejected": -61.6773681640625, "loss": 0.34289711713790894, "memory(GiB)": 41.24, "nll_loss": 0.24206680059432983, "rewards/accuracies": 0.96875, "rewards/chosen": 0.09123305231332779, "rewards/margins": 4.509951114654541, "rewards/rejected": -4.418718338012695, "step": 98, "train_speed(iter/s)": 0.010736 }, { "epoch": 0.5708108108108109, "grad_norm": 12.38167667388916, "learning_rate": 0.00018937385386704126, "logits/chosen": -0.6038029789924622, "logits/rejected": -0.7428975105285645, "logps/chosen": -6.938250541687012, "logps/rejected": -58.5086555480957, "loss": 0.4984804391860962, "memory(GiB)": 41.24, "nll_loss": 0.37261444330215454, "rewards/accuracies": 0.9375, "rewards/chosen": 0.10895882546901703, "rewards/margins": 4.678299903869629, "rewards/rejected": -4.569341659545898, "step": 99, "train_speed(iter/s)": 0.010736 }, { "epoch": 0.5765765765765766, "grad_norm": 4.255463123321533, "learning_rate": 0.00018908618285360494, "logits/chosen": -0.5780411958694458, "logits/rejected": -0.7493711709976196, "logps/chosen": -6.087734222412109, "logps/rejected": -68.05068969726562, "loss": 0.5377764701843262, "memory(GiB)": 41.24, "nll_loss": 0.4144035577774048, "rewards/accuracies": 1.0, "rewards/chosen": 0.07401561737060547, "rewards/margins": 5.022759437561035, "rewards/rejected": -4.94874382019043, "step": 100, "train_speed(iter/s)": 0.010737 }, { "epoch": 0.5823423423423424, "grad_norm": 2.052121162414551, "learning_rate": 0.00018879489428812334, "logits/chosen": -0.5155804753303528, "logits/rejected": -0.7454657554626465, "logps/chosen": -4.093721389770508, "logps/rejected": -73.28987121582031, "loss": 0.4639092683792114, "memory(GiB)": 41.24, "nll_loss": 0.3733065724372864, "rewards/accuracies": 0.9375, "rewards/chosen": 0.16241005063056946, "rewards/margins": 5.644482135772705, "rewards/rejected": -5.482071876525879, "step": 101, "train_speed(iter/s)": 0.010718 }, { "epoch": 0.5881081081081081, "grad_norm": 2.1512622833251953, "learning_rate": 0.0001884999999990475, "logits/chosen": -0.5633401274681091, "logits/rejected": -0.7381998896598816, "logps/chosen": -6.3428497314453125, "logps/rejected": -52.1317138671875, "loss": 0.4867536425590515, "memory(GiB)": 41.24, "nll_loss": 0.34330999851226807, "rewards/accuracies": 0.9375, "rewards/chosen": 0.33921706676483154, "rewards/margins": 4.20556116104126, "rewards/rejected": -3.8663439750671387, "step": 102, "train_speed(iter/s)": 0.010718 }, { "epoch": 0.5938738738738739, "grad_norm": 3.3250627517700195, "learning_rate": 0.00018820151196124717, "logits/chosen": -0.5157067179679871, "logits/rejected": -0.8171908855438232, "logps/chosen": -3.4731268882751465, "logps/rejected": -87.99000549316406, "loss": 0.5975285768508911, "memory(GiB)": 41.24, "nll_loss": 0.46800604462623596, "rewards/accuracies": 0.96875, "rewards/chosen": 0.06358014047145844, "rewards/margins": 6.483148097991943, "rewards/rejected": -6.419568061828613, "step": 103, "train_speed(iter/s)": 0.010718 }, { "epoch": 0.5996396396396396, "grad_norm": 3.476541757583618, "learning_rate": 0.0001878994422955246, "logits/chosen": -0.5131168365478516, "logits/rejected": -0.8059231042861938, "logps/chosen": -3.1174309253692627, "logps/rejected": -86.71981811523438, "loss": 0.3160158693790436, "memory(GiB)": 41.24, "nll_loss": 0.25080835819244385, "rewards/accuracies": 0.96875, "rewards/chosen": 0.28578388690948486, "rewards/margins": 6.907861232757568, "rewards/rejected": -6.622077941894531, "step": 104, "train_speed(iter/s)": 0.010718 }, { "epoch": 0.6054054054054054, "grad_norm": 5.32436990737915, "learning_rate": 0.00018759380326812257, "logits/chosen": -0.6340402960777283, "logits/rejected": -0.867938756942749, "logps/chosen": -2.323990821838379, "logps/rejected": -71.03258514404297, "loss": 0.31046488881111145, "memory(GiB)": 41.24, "nll_loss": 0.21423426270484924, "rewards/accuracies": 0.96875, "rewards/chosen": -0.011083951219916344, "rewards/margins": 6.008091926574707, "rewards/rejected": -6.0191755294799805, "step": 105, "train_speed(iter/s)": 0.010719 }, { "epoch": 0.6111711711711711, "grad_norm": 3.4041733741760254, "learning_rate": 0.0001872846072902259, "logits/chosen": -0.589099645614624, "logits/rejected": -0.8120458126068115, "logps/chosen": -1.5791796445846558, "logps/rejected": -82.34098052978516, "loss": 0.2268940657377243, "memory(GiB)": 41.24, "nll_loss": 0.14617523550987244, "rewards/accuracies": 0.9375, "rewards/chosen": 0.2277921438217163, "rewards/margins": 6.835321426391602, "rewards/rejected": -6.607529640197754, "step": 106, "train_speed(iter/s)": 0.010719 }, { "epoch": 0.616936936936937, "grad_norm": 1.9216675758361816, "learning_rate": 0.00018697186691745782, "logits/chosen": -0.599471926689148, "logits/rejected": -0.8271054029464722, "logps/chosen": -4.24713134765625, "logps/rejected": -84.08229064941406, "loss": 0.3841734826564789, "memory(GiB)": 41.24, "nll_loss": 0.31657740473747253, "rewards/accuracies": 1.0, "rewards/chosen": 0.022511344403028488, "rewards/margins": 6.769836902618408, "rewards/rejected": -6.747325897216797, "step": 107, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.6227027027027027, "grad_norm": 4.744035720825195, "learning_rate": 0.0001866555948493699, "logits/chosen": -0.5849882960319519, "logits/rejected": -0.8727071285247803, "logps/chosen": -2.891716718673706, "logps/rejected": -92.83207702636719, "loss": 0.31115370988845825, "memory(GiB)": 41.24, "nll_loss": 0.22799423336982727, "rewards/accuracies": 1.0, "rewards/chosen": 0.19745981693267822, "rewards/margins": 7.553801536560059, "rewards/rejected": -7.35634183883667, "step": 108, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.6284684684684685, "grad_norm": 2.028069019317627, "learning_rate": 0.00018633580392892648, "logits/chosen": -0.5856168270111084, "logits/rejected": -0.8363710641860962, "logps/chosen": -5.515890121459961, "logps/rejected": -83.518310546875, "loss": 0.40675532817840576, "memory(GiB)": 41.24, "nll_loss": 0.33311402797698975, "rewards/accuracies": 0.96875, "rewards/chosen": 0.19537094235420227, "rewards/margins": 6.882720947265625, "rewards/rejected": -6.687350273132324, "step": 109, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.6342342342342342, "grad_norm": 1.8457213640213013, "learning_rate": 0.00018601250714198302, "logits/chosen": -0.6694027185440063, "logits/rejected": -0.8495978713035583, "logps/chosen": -6.527522087097168, "logps/rejected": -69.24601745605469, "loss": 0.4539996385574341, "memory(GiB)": 41.24, "nll_loss": 0.3218171000480652, "rewards/accuracies": 1.0, "rewards/chosen": 0.16864001750946045, "rewards/margins": 5.4212541580200195, "rewards/rejected": -5.252613544464111, "step": 110, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.64, "grad_norm": 1.4716756343841553, "learning_rate": 0.00018568571761675893, "logits/chosen": -0.5902320742607117, "logits/rejected": -0.8840252757072449, "logps/chosen": -5.05216121673584, "logps/rejected": -96.3882064819336, "loss": 0.3378267288208008, "memory(GiB)": 41.24, "nll_loss": 0.2499268501996994, "rewards/accuracies": 0.96875, "rewards/chosen": 0.21043285727500916, "rewards/margins": 7.197650909423828, "rewards/rejected": -6.987217903137207, "step": 111, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.6457657657657657, "grad_norm": 0.7805799245834351, "learning_rate": 0.00018535544862330436, "logits/chosen": -0.6686023473739624, "logits/rejected": -0.986074686050415, "logps/chosen": -2.231717824935913, "logps/rejected": -96.76434326171875, "loss": 0.16498756408691406, "memory(GiB)": 41.24, "nll_loss": 0.14222995936870575, "rewards/accuracies": 1.0, "rewards/chosen": 0.14315873384475708, "rewards/margins": 7.930060386657715, "rewards/rejected": -7.786901473999023, "step": 112, "train_speed(iter/s)": 0.01072 }, { "epoch": 0.6515315315315315, "grad_norm": 2.115647792816162, "learning_rate": 0.00018502171357296144, "logits/chosen": -0.7186330556869507, "logits/rejected": -0.9198458194732666, "logps/chosen": -6.138432502746582, "logps/rejected": -76.40232849121094, "loss": 0.42215695977211, "memory(GiB)": 41.24, "nll_loss": 0.34653419256210327, "rewards/accuracies": 1.0, "rewards/chosen": 0.3074129521846771, "rewards/margins": 6.320471286773682, "rewards/rejected": -6.013057708740234, "step": 113, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.6572972972972972, "grad_norm": 8.20527458190918, "learning_rate": 0.00018468452601781948, "logits/chosen": -0.6733801364898682, "logits/rejected": -0.9577184319496155, "logps/chosen": -5.523393154144287, "logps/rejected": -94.21669006347656, "loss": 0.4980089068412781, "memory(GiB)": 41.24, "nll_loss": 0.37918829917907715, "rewards/accuracies": 0.90625, "rewards/chosen": 0.07570207118988037, "rewards/margins": 7.661881446838379, "rewards/rejected": -7.586179256439209, "step": 114, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.6630630630630631, "grad_norm": 1.4824076890945435, "learning_rate": 0.00018434389965016495, "logits/chosen": -0.6685976386070251, "logits/rejected": -0.9235626459121704, "logps/chosen": -4.8032307624816895, "logps/rejected": -89.84734344482422, "loss": 0.3988059163093567, "memory(GiB)": 41.24, "nll_loss": 0.3272039592266083, "rewards/accuracies": 1.0, "rewards/chosen": 0.1318884938955307, "rewards/margins": 7.2766876220703125, "rewards/rejected": -7.14479923248291, "step": 115, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.6688288288288289, "grad_norm": 6.457195281982422, "learning_rate": 0.00018399984830192522, "logits/chosen": -0.6563739776611328, "logits/rejected": -0.9446012377738953, "logps/chosen": -5.333343505859375, "logps/rejected": -96.29754638671875, "loss": 0.6648478507995605, "memory(GiB)": 41.24, "nll_loss": 0.5736638307571411, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1766398400068283, "rewards/margins": 7.466494560241699, "rewards/rejected": -7.289853572845459, "step": 116, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.6745945945945946, "grad_norm": 0.6062999367713928, "learning_rate": 0.00018365238594410696, "logits/chosen": -0.6826354265213013, "logits/rejected": -0.9526041150093079, "logps/chosen": -2.1560752391815186, "logps/rejected": -97.08880615234375, "loss": 0.15202483534812927, "memory(GiB)": 41.24, "nll_loss": 0.1097334772348404, "rewards/accuracies": 1.0, "rewards/chosen": 0.08674149215221405, "rewards/margins": 8.09538745880127, "rewards/rejected": -8.008646011352539, "step": 117, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.6803603603603604, "grad_norm": 4.866965293884277, "learning_rate": 0.00018330152668622892, "logits/chosen": -0.6270961761474609, "logits/rejected": -0.8659616708755493, "logps/chosen": -6.8050456047058105, "logps/rejected": -94.24461364746094, "loss": 0.5779068470001221, "memory(GiB)": 41.24, "nll_loss": 0.4634403884410858, "rewards/accuracies": 0.9375, "rewards/chosen": 0.08972588181495667, "rewards/margins": 7.540095806121826, "rewards/rejected": -7.450369834899902, "step": 118, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.6861261261261261, "grad_norm": 1.9984689950942993, "learning_rate": 0.00018294728477574886, "logits/chosen": -0.6620824933052063, "logits/rejected": -0.9279792308807373, "logps/chosen": -3.62056303024292, "logps/rejected": -88.79190826416016, "loss": 0.5508708357810974, "memory(GiB)": 41.24, "nll_loss": 0.44049572944641113, "rewards/accuracies": 0.9375, "rewards/chosen": 0.04914311319589615, "rewards/margins": 7.090651512145996, "rewards/rejected": -7.041508197784424, "step": 119, "train_speed(iter/s)": 0.010721 }, { "epoch": 0.6918918918918919, "grad_norm": 2.634037971496582, "learning_rate": 0.000182589674597485, "logits/chosen": -0.6129943132400513, "logits/rejected": -0.891259491443634, "logps/chosen": -4.1637163162231445, "logps/rejected": -89.52510833740234, "loss": 0.5133303999900818, "memory(GiB)": 41.24, "nll_loss": 0.35086461901664734, "rewards/accuracies": 0.90625, "rewards/chosen": 0.015482299029827118, "rewards/margins": 7.1094279289245605, "rewards/rejected": -7.0939459800720215, "step": 120, "train_speed(iter/s)": 0.010722 }, { "epoch": 0.6976576576576576, "grad_norm": 2.7602248191833496, "learning_rate": 0.00018222871067303192, "logits/chosen": -0.644217848777771, "logits/rejected": -0.8804385662078857, "logps/chosen": -4.665724277496338, "logps/rejected": -75.18159484863281, "loss": 0.4733228385448456, "memory(GiB)": 41.24, "nll_loss": 0.3284577429294586, "rewards/accuracies": 0.9375, "rewards/chosen": 0.11940830945968628, "rewards/margins": 6.475360870361328, "rewards/rejected": -6.355952262878418, "step": 121, "train_speed(iter/s)": 0.010722 }, { "epoch": 0.7034234234234235, "grad_norm": 8.460821151733398, "learning_rate": 0.0001818644076601709, "logits/chosen": -0.6995394825935364, "logits/rejected": -0.9071613550186157, "logps/chosen": -8.95744800567627, "logps/rejected": -77.84011840820312, "loss": 0.6963841915130615, "memory(GiB)": 41.24, "nll_loss": 0.5519821047782898, "rewards/accuracies": 0.90625, "rewards/chosen": 0.2606813609600067, "rewards/margins": 6.603857040405273, "rewards/rejected": -6.343176364898682, "step": 122, "train_speed(iter/s)": 0.010722 }, { "epoch": 0.7091891891891892, "grad_norm": 3.587855100631714, "learning_rate": 0.00018149678035227473, "logits/chosen": -0.6442317962646484, "logits/rejected": -0.8487176895141602, "logps/chosen": -6.872650623321533, "logps/rejected": -82.89649963378906, "loss": 0.4728536605834961, "memory(GiB)": 41.24, "nll_loss": 0.3608010411262512, "rewards/accuracies": 0.9375, "rewards/chosen": 0.009775836020708084, "rewards/margins": 6.596733093261719, "rewards/rejected": -6.586956977844238, "step": 123, "train_speed(iter/s)": 0.010723 }, { "epoch": 0.714954954954955, "grad_norm": 1.7244524955749512, "learning_rate": 0.00018112584367770685, "logits/chosen": -0.6685165762901306, "logits/rejected": -0.8828461766242981, "logps/chosen": -5.397648334503174, "logps/rejected": -85.60098266601562, "loss": 0.389848530292511, "memory(GiB)": 41.24, "nll_loss": 0.32140427827835083, "rewards/accuracies": 1.0, "rewards/chosen": 0.12320394814014435, "rewards/margins": 7.233897686004639, "rewards/rejected": -7.11069393157959, "step": 124, "train_speed(iter/s)": 0.010723 }, { "epoch": 0.7207207207207207, "grad_norm": 0.7455915808677673, "learning_rate": 0.00018075161269921527, "logits/chosen": -0.5614687204360962, "logits/rejected": -0.8907942771911621, "logps/chosen": -1.7438545227050781, "logps/rejected": -92.23735809326172, "loss": 0.12226351350545883, "memory(GiB)": 41.24, "nll_loss": 0.10527773201465607, "rewards/accuracies": 1.0, "rewards/chosen": 0.15749390423297882, "rewards/margins": 7.594954967498779, "rewards/rejected": -7.437460422515869, "step": 125, "train_speed(iter/s)": 0.010723 }, { "epoch": 0.7264864864864865, "grad_norm": 1.0758198499679565, "learning_rate": 0.000180374102613321, "logits/chosen": -0.6551331877708435, "logits/rejected": -0.8264045119285583, "logps/chosen": -4.308568000793457, "logps/rejected": -80.06883239746094, "loss": 0.36240947246551514, "memory(GiB)": 41.24, "nll_loss": 0.24730846285820007, "rewards/accuracies": 1.0, "rewards/chosen": 0.10061657428741455, "rewards/margins": 6.429587364196777, "rewards/rejected": -6.328970909118652, "step": 126, "train_speed(iter/s)": 0.010723 }, { "epoch": 0.7322522522522522, "grad_norm": 1.0857983827590942, "learning_rate": 0.0001799933287497007, "logits/chosen": -0.6380553841590881, "logits/rejected": -0.8699716925621033, "logps/chosen": -1.9937247037887573, "logps/rejected": -87.90292358398438, "loss": 0.18343912065029144, "memory(GiB)": 41.24, "nll_loss": 0.12965701520442963, "rewards/accuracies": 1.0, "rewards/chosen": 0.09683795273303986, "rewards/margins": 7.11926794052124, "rewards/rejected": -7.022429943084717, "step": 127, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.738018018018018, "grad_norm": 9.539369583129883, "learning_rate": 0.00017960930657056438, "logits/chosen": -0.6350418925285339, "logits/rejected": -0.8755402565002441, "logps/chosen": -2.645111560821533, "logps/rejected": -82.07209777832031, "loss": 0.23406416177749634, "memory(GiB)": 41.24, "nll_loss": 0.17941246926784515, "rewards/accuracies": 1.0, "rewards/chosen": 0.07386763393878937, "rewards/margins": 6.727149486541748, "rewards/rejected": -6.653281211853027, "step": 128, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.7437837837837837, "grad_norm": 10.807381629943848, "learning_rate": 0.00017922205167002754, "logits/chosen": -0.6329447031021118, "logits/rejected": -0.8397620320320129, "logps/chosen": -4.6306023597717285, "logps/rejected": -67.41867065429688, "loss": 0.5849911570549011, "memory(GiB)": 41.24, "nll_loss": 0.41021403670310974, "rewards/accuracies": 0.9375, "rewards/chosen": 0.06239153444766998, "rewards/margins": 5.311315059661865, "rewards/rejected": -5.248923301696777, "step": 129, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.7495495495495496, "grad_norm": 1.8455349206924438, "learning_rate": 0.00017883157977347774, "logits/chosen": -0.5277632474899292, "logits/rejected": -0.785979151725769, "logps/chosen": -4.069696426391602, "logps/rejected": -82.98876953125, "loss": 0.3647957146167755, "memory(GiB)": 41.24, "nll_loss": 0.24460868537425995, "rewards/accuracies": 0.90625, "rewards/chosen": 0.12994280457496643, "rewards/margins": 6.137853622436523, "rewards/rejected": -6.00791072845459, "step": 130, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.7553153153153153, "grad_norm": 1.5157482624053955, "learning_rate": 0.00017843790673693625, "logits/chosen": -0.533730685710907, "logits/rejected": -0.8200556635856628, "logps/chosen": -4.038061141967773, "logps/rejected": -82.76172637939453, "loss": 0.2888023555278778, "memory(GiB)": 41.24, "nll_loss": 0.2086402326822281, "rewards/accuracies": 1.0, "rewards/chosen": 0.2728549540042877, "rewards/margins": 6.415480613708496, "rewards/rejected": -6.142626762390137, "step": 131, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.7610810810810811, "grad_norm": 1.936601996421814, "learning_rate": 0.00017804104854641408, "logits/chosen": -0.6249516606330872, "logits/rejected": -0.8721716403961182, "logps/chosen": -3.304114818572998, "logps/rejected": -60.27552795410156, "loss": 0.415643572807312, "memory(GiB)": 41.24, "nll_loss": 0.28065580129623413, "rewards/accuracies": 0.96875, "rewards/chosen": 0.2913169264793396, "rewards/margins": 4.785688400268555, "rewards/rejected": -4.49437141418457, "step": 132, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.7668468468468469, "grad_norm": 3.6359870433807373, "learning_rate": 0.0001776410213172628, "logits/chosen": -0.5627670288085938, "logits/rejected": -0.8085115551948547, "logps/chosen": -1.7719781398773193, "logps/rejected": -72.61830139160156, "loss": 0.2871711552143097, "memory(GiB)": 41.24, "nll_loss": 0.1900225728750229, "rewards/accuracies": 0.9375, "rewards/chosen": 0.089139424264431, "rewards/margins": 5.8200178146362305, "rewards/rejected": -5.730878829956055, "step": 133, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.7726126126126126, "grad_norm": 1.4323631525039673, "learning_rate": 0.00017723784129352018, "logits/chosen": -0.6231422424316406, "logits/rejected": -0.8504309058189392, "logps/chosen": -1.730849027633667, "logps/rejected": -68.78044128417969, "loss": 0.2242366373538971, "memory(GiB)": 41.24, "nll_loss": 0.13950544595718384, "rewards/accuracies": 0.96875, "rewards/chosen": 0.18260075151920319, "rewards/margins": 5.708943843841553, "rewards/rejected": -5.526342391967773, "step": 134, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.7783783783783784, "grad_norm": 1.6163887977600098, "learning_rate": 0.00017683152484725066, "logits/chosen": -0.6224597692489624, "logits/rejected": -0.7799749374389648, "logps/chosen": -4.717617988586426, "logps/rejected": -61.31199264526367, "loss": 0.4397742450237274, "memory(GiB)": 41.24, "nll_loss": 0.3140389323234558, "rewards/accuracies": 0.96875, "rewards/chosen": 0.25990185141563416, "rewards/margins": 4.902276039123535, "rewards/rejected": -4.642374515533447, "step": 135, "train_speed(iter/s)": 0.010726 }, { "epoch": 0.7841441441441441, "grad_norm": 1.2988686561584473, "learning_rate": 0.00017642208847788032, "logits/chosen": -0.4455900192260742, "logits/rejected": -0.8272579312324524, "logps/chosen": -3.7604730129241943, "logps/rejected": -91.75283813476562, "loss": 0.3069111108779907, "memory(GiB)": 41.24, "nll_loss": 0.257954478263855, "rewards/accuracies": 0.96875, "rewards/chosen": 0.17708764970302582, "rewards/margins": 7.115184783935547, "rewards/rejected": -6.93809700012207, "step": 136, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.78990990990991, "grad_norm": 3.960479974746704, "learning_rate": 0.00017600954881152693, "logits/chosen": -0.480897456407547, "logits/rejected": -0.806812584400177, "logps/chosen": -2.339344024658203, "logps/rejected": -88.25721740722656, "loss": 0.25455033779144287, "memory(GiB)": 41.24, "nll_loss": 0.1620534360408783, "rewards/accuracies": 0.96875, "rewards/chosen": 0.10610076785087585, "rewards/margins": 6.920160293579102, "rewards/rejected": -6.814059734344482, "step": 137, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.7956756756756757, "grad_norm": 9.401166915893555, "learning_rate": 0.00017559392260032506, "logits/chosen": -0.4589274525642395, "logits/rejected": -0.7634912729263306, "logps/chosen": -5.8359503746032715, "logps/rejected": -96.87335205078125, "loss": 0.5270398855209351, "memory(GiB)": 41.24, "nll_loss": 0.43480122089385986, "rewards/accuracies": 0.96875, "rewards/chosen": -0.14989905059337616, "rewards/margins": 7.5454607009887695, "rewards/rejected": -7.69536018371582, "step": 138, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.8014414414414415, "grad_norm": 4.686446666717529, "learning_rate": 0.00017517522672174548, "logits/chosen": -0.5010412931442261, "logits/rejected": -0.8063571453094482, "logps/chosen": -2.5103189945220947, "logps/rejected": -96.94129943847656, "loss": 0.3778824508190155, "memory(GiB)": 41.24, "nll_loss": 0.252981573343277, "rewards/accuracies": 0.9375, "rewards/chosen": 0.10596343874931335, "rewards/margins": 7.605740070343018, "rewards/rejected": -7.499776840209961, "step": 139, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.8072072072072072, "grad_norm": 1.6708407402038574, "learning_rate": 0.00017475347817790996, "logits/chosen": -0.4751094877719879, "logits/rejected": -0.8238545060157776, "logps/chosen": -3.2878451347351074, "logps/rejected": -86.26036071777344, "loss": 0.24279947578907013, "memory(GiB)": 41.24, "nll_loss": 0.16919009387493134, "rewards/accuracies": 0.96875, "rewards/chosen": 0.07166648656129837, "rewards/margins": 6.587783336639404, "rewards/rejected": -6.516116142272949, "step": 140, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.812972972972973, "grad_norm": 1.4335037469863892, "learning_rate": 0.00017432869409490093, "logits/chosen": -0.5489400625228882, "logits/rejected": -0.7731753587722778, "logps/chosen": -5.348051071166992, "logps/rejected": -70.64154815673828, "loss": 0.36098673939704895, "memory(GiB)": 41.24, "nll_loss": 0.2713705897331238, "rewards/accuracies": 1.0, "rewards/chosen": 0.23904970288276672, "rewards/margins": 5.921088695526123, "rewards/rejected": -5.682039737701416, "step": 141, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.8187387387387387, "grad_norm": 2.012854814529419, "learning_rate": 0.00017390089172206592, "logits/chosen": -0.467896968126297, "logits/rejected": -0.793892502784729, "logps/chosen": -1.7580054998397827, "logps/rejected": -85.476318359375, "loss": 0.23942089080810547, "memory(GiB)": 41.24, "nll_loss": 0.17797623574733734, "rewards/accuracies": 0.96875, "rewards/chosen": 0.09021879732608795, "rewards/margins": 6.8085222244262695, "rewards/rejected": -6.718303680419922, "step": 142, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.8245045045045045, "grad_norm": 5.257446765899658, "learning_rate": 0.00017347008843131712, "logits/chosen": -0.4858510196208954, "logits/rejected": -0.7565414309501648, "logps/chosen": -3.7341561317443848, "logps/rejected": -75.44990539550781, "loss": 0.43588101863861084, "memory(GiB)": 41.24, "nll_loss": 0.3324872553348541, "rewards/accuracies": 0.9375, "rewards/chosen": 0.1589755266904831, "rewards/margins": 5.903942584991455, "rewards/rejected": -5.744967460632324, "step": 143, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.8302702702702702, "grad_norm": 1.9966129064559937, "learning_rate": 0.00017303630171642607, "logits/chosen": -0.4013749659061432, "logits/rejected": -0.7098768353462219, "logps/chosen": -2.0640015602111816, "logps/rejected": -80.94207763671875, "loss": 0.2669733166694641, "memory(GiB)": 41.24, "nll_loss": 0.2289275974035263, "rewards/accuracies": 1.0, "rewards/chosen": 0.20508992671966553, "rewards/margins": 5.947912216186523, "rewards/rejected": -5.742822170257568, "step": 144, "train_speed(iter/s)": 0.010725 }, { "epoch": 0.836036036036036, "grad_norm": 4.144430637359619, "learning_rate": 0.0001725995491923131, "logits/chosen": -0.34412139654159546, "logits/rejected": -0.7268174290657043, "logps/chosen": -2.0844953060150146, "logps/rejected": -86.29147338867188, "loss": 0.2860412001609802, "memory(GiB)": 41.24, "nll_loss": 0.21140313148498535, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1814691722393036, "rewards/margins": 6.325296401977539, "rewards/rejected": -6.143826961517334, "step": 145, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.8418018018018018, "grad_norm": 6.901271343231201, "learning_rate": 0.0001721598485943322, "logits/chosen": -0.4293047785758972, "logits/rejected": -0.6931589841842651, "logps/chosen": -3.5573177337646484, "logps/rejected": -80.00125885009766, "loss": 0.402279257774353, "memory(GiB)": 41.24, "nll_loss": 0.30397528409957886, "rewards/accuracies": 0.96875, "rewards/chosen": -0.027988389134407043, "rewards/margins": 6.108896732330322, "rewards/rejected": -6.136884689331055, "step": 146, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.8475675675675676, "grad_norm": 1.3138624429702759, "learning_rate": 0.00017171721777755074, "logits/chosen": -0.441506952047348, "logits/rejected": -0.6183236241340637, "logps/chosen": -5.245753288269043, "logps/rejected": -61.3995246887207, "loss": 0.5000537633895874, "memory(GiB)": 41.24, "nll_loss": 0.3299512565135956, "rewards/accuracies": 0.90625, "rewards/chosen": 0.1415078043937683, "rewards/margins": 4.831845760345459, "rewards/rejected": -4.690337181091309, "step": 147, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.8533333333333334, "grad_norm": 2.7394113540649414, "learning_rate": 0.00017127167471602447, "logits/chosen": -0.44564759731292725, "logits/rejected": -0.7324830889701843, "logps/chosen": -2.2436249256134033, "logps/rejected": -73.5162124633789, "loss": 0.20336386561393738, "memory(GiB)": 41.24, "nll_loss": 0.11223578453063965, "rewards/accuracies": 0.96875, "rewards/chosen": 0.17428822815418243, "rewards/margins": 5.678185939788818, "rewards/rejected": -5.503897666931152, "step": 148, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.8590990990990991, "grad_norm": 1.488072395324707, "learning_rate": 0.00017082323750206761, "logits/chosen": -0.44784775376319885, "logits/rejected": -0.6909451484680176, "logps/chosen": -3.5523109436035156, "logps/rejected": -70.1702651977539, "loss": 0.31512442231178284, "memory(GiB)": 41.24, "nll_loss": 0.2102314829826355, "rewards/accuracies": 0.96875, "rewards/chosen": 0.11678414791822433, "rewards/margins": 5.312015533447266, "rewards/rejected": -5.1952314376831055, "step": 149, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.8648648648648649, "grad_norm": 2.6578073501586914, "learning_rate": 0.00017037192434551823, "logits/chosen": -0.39348986744880676, "logits/rejected": -0.690170407295227, "logps/chosen": -3.4318065643310547, "logps/rejected": -76.70863342285156, "loss": 0.40308576822280884, "memory(GiB)": 41.24, "nll_loss": 0.2762233316898346, "rewards/accuracies": 0.90625, "rewards/chosen": 0.1851682811975479, "rewards/margins": 5.912222385406494, "rewards/rejected": -5.727054119110107, "step": 150, "train_speed(iter/s)": 0.010724 }, { "epoch": 0.8706306306306306, "grad_norm": 2.9397995471954346, "learning_rate": 0.00016991775357299866, "logits/chosen": -0.4844151735305786, "logits/rejected": -0.7689380645751953, "logps/chosen": -4.010564804077148, "logps/rejected": -85.45973205566406, "loss": 0.3323879539966583, "memory(GiB)": 41.24, "nll_loss": 0.2697053551673889, "rewards/accuracies": 1.0, "rewards/chosen": 0.17146898806095123, "rewards/margins": 6.537592887878418, "rewards/rejected": -6.366123676300049, "step": 151, "train_speed(iter/s)": 0.010712 }, { "epoch": 0.8763963963963964, "grad_norm": 2.216646909713745, "learning_rate": 0.00016946074362717147, "logits/chosen": -0.5326839685440063, "logits/rejected": -0.7718309760093689, "logps/chosen": -4.843362808227539, "logps/rejected": -73.73052978515625, "loss": 0.4268698990345001, "memory(GiB)": 41.24, "nll_loss": 0.36223095655441284, "rewards/accuracies": 1.0, "rewards/chosen": 0.21485474705696106, "rewards/margins": 5.929214000701904, "rewards/rejected": -5.714358329772949, "step": 152, "train_speed(iter/s)": 0.010712 }, { "epoch": 0.8821621621621621, "grad_norm": 6.382073879241943, "learning_rate": 0.00016900091306599042, "logits/chosen": -0.6236099004745483, "logits/rejected": -0.7957028150558472, "logps/chosen": -6.768365859985352, "logps/rejected": -75.18216705322266, "loss": 0.5070593953132629, "memory(GiB)": 41.24, "nll_loss": 0.39859798550605774, "rewards/accuracies": 0.96875, "rewards/chosen": -0.03324725478887558, "rewards/margins": 6.097735404968262, "rewards/rejected": -6.130982875823975, "step": 153, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.887927927927928, "grad_norm": 5.002453327178955, "learning_rate": 0.00016853828056194697, "logits/chosen": -0.47666168212890625, "logits/rejected": -0.7901638150215149, "logps/chosen": -1.6101099252700806, "logps/rejected": -83.95780944824219, "loss": 0.2384922355413437, "memory(GiB)": 41.24, "nll_loss": 0.15521878004074097, "rewards/accuracies": 0.9375, "rewards/chosen": 0.027309579774737358, "rewards/margins": 6.557631492614746, "rewards/rejected": -6.530322074890137, "step": 154, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.8936936936936937, "grad_norm": 2.2284231185913086, "learning_rate": 0.00016807286490131196, "logits/chosen": -0.4581748843193054, "logits/rejected": -0.7216594815254211, "logps/chosen": -4.746794700622559, "logps/rejected": -65.14288330078125, "loss": 0.4944155812263489, "memory(GiB)": 41.24, "nll_loss": 0.38365647196769714, "rewards/accuracies": 1.0, "rewards/chosen": 0.09537286311388016, "rewards/margins": 4.88486909866333, "rewards/rejected": -4.789495944976807, "step": 155, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.8994594594594595, "grad_norm": 1.4425420761108398, "learning_rate": 0.00016760468498337283, "logits/chosen": -0.4141704738140106, "logits/rejected": -0.753037691116333, "logps/chosen": -2.9428489208221436, "logps/rejected": -85.63114166259766, "loss": 0.2691604495048523, "memory(GiB)": 41.24, "nll_loss": 0.22332294285297394, "rewards/accuracies": 1.0, "rewards/chosen": 0.29303914308547974, "rewards/margins": 6.752739906311035, "rewards/rejected": -6.459700584411621, "step": 156, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9052252252252252, "grad_norm": 3.795686960220337, "learning_rate": 0.00016713375981966612, "logits/chosen": -0.4735071659088135, "logits/rejected": -0.7943378686904907, "logps/chosen": -9.046199798583984, "logps/rejected": -86.67741394042969, "loss": 0.602267324924469, "memory(GiB)": 41.24, "nll_loss": 0.5201234817504883, "rewards/accuracies": 0.9375, "rewards/chosen": -0.15314966440200806, "rewards/margins": 6.5488057136535645, "rewards/rejected": -6.7019548416137695, "step": 157, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.910990990990991, "grad_norm": 4.890588760375977, "learning_rate": 0.00016666010853320543, "logits/chosen": -0.5752784013748169, "logits/rejected": -0.7697316408157349, "logps/chosen": -9.034675598144531, "logps/rejected": -79.48356628417969, "loss": 0.7191926836967468, "memory(GiB)": 41.24, "nll_loss": 0.5265187621116638, "rewards/accuracies": 0.96875, "rewards/chosen": -0.07981552183628082, "rewards/margins": 6.082505226135254, "rewards/rejected": -6.162321090698242, "step": 158, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9167567567567567, "grad_norm": 1.312125563621521, "learning_rate": 0.00016618375035770498, "logits/chosen": -0.5153398513793945, "logits/rejected": -0.8238294720649719, "logps/chosen": -3.0522966384887695, "logps/rejected": -84.81144714355469, "loss": 0.32918140292167664, "memory(GiB)": 41.24, "nll_loss": 0.2058570384979248, "rewards/accuracies": 0.9375, "rewards/chosen": 0.19958336651325226, "rewards/margins": 6.894275665283203, "rewards/rejected": -6.694692611694336, "step": 159, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9225225225225225, "grad_norm": 1.3166769742965698, "learning_rate": 0.00016570470463679856, "logits/chosen": -0.4472997486591339, "logits/rejected": -0.7798503041267395, "logps/chosen": -2.2529990673065186, "logps/rejected": -94.50987243652344, "loss": 0.2068968117237091, "memory(GiB)": 41.24, "nll_loss": 0.13873136043548584, "rewards/accuracies": 0.96875, "rewards/chosen": 0.15320263803005219, "rewards/margins": 7.273505687713623, "rewards/rejected": -7.120303153991699, "step": 160, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9282882882882882, "grad_norm": 1.4938724040985107, "learning_rate": 0.00016522299082325382, "logits/chosen": -0.4986165463924408, "logits/rejected": -0.7801789045333862, "logps/chosen": -2.9465794563293457, "logps/rejected": -73.10553741455078, "loss": 0.30796459317207336, "memory(GiB)": 41.24, "nll_loss": 0.2202310413122177, "rewards/accuracies": 0.9375, "rewards/chosen": 0.38857752084732056, "rewards/margins": 5.931979656219482, "rewards/rejected": -5.543401718139648, "step": 161, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9340540540540541, "grad_norm": 1.7879637479782104, "learning_rate": 0.00016473862847818277, "logits/chosen": -0.5118488073348999, "logits/rejected": -0.8153480291366577, "logps/chosen": -4.100103855133057, "logps/rejected": -91.44921875, "loss": 0.35479840636253357, "memory(GiB)": 41.24, "nll_loss": 0.30052870512008667, "rewards/accuracies": 1.0, "rewards/chosen": 0.14176566898822784, "rewards/margins": 7.297792911529541, "rewards/rejected": -7.156026840209961, "step": 162, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9398198198198198, "grad_norm": 2.240473985671997, "learning_rate": 0.00016425163727024707, "logits/chosen": -0.578972339630127, "logits/rejected": -0.7973175048828125, "logps/chosen": -4.10087776184082, "logps/rejected": -75.45283508300781, "loss": 0.41070497035980225, "memory(GiB)": 41.24, "nll_loss": 0.24780017137527466, "rewards/accuracies": 0.9375, "rewards/chosen": 0.003609701991081238, "rewards/margins": 6.174129009246826, "rewards/rejected": -6.17051887512207, "step": 163, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9455855855855856, "grad_norm": 1.820946455001831, "learning_rate": 0.0001637620369748595, "logits/chosen": -0.5063561201095581, "logits/rejected": -0.839270293712616, "logps/chosen": -3.7182536125183105, "logps/rejected": -102.9184341430664, "loss": 0.2363234907388687, "memory(GiB)": 41.24, "nll_loss": 0.16097372770309448, "rewards/accuracies": 0.96875, "rewards/chosen": 0.07240395247936249, "rewards/margins": 8.28852653503418, "rewards/rejected": -8.216121673583984, "step": 164, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9513513513513514, "grad_norm": 1.6907538175582886, "learning_rate": 0.00016326984747338095, "logits/chosen": -0.5052527785301208, "logits/rejected": -0.7384231686592102, "logps/chosen": -4.822022914886475, "logps/rejected": -71.9358901977539, "loss": 0.4056674838066101, "memory(GiB)": 41.24, "nll_loss": 0.30248117446899414, "rewards/accuracies": 0.9375, "rewards/chosen": 0.24947428703308105, "rewards/margins": 5.717057704925537, "rewards/rejected": -5.467583179473877, "step": 165, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9571171171171171, "grad_norm": 2.038442850112915, "learning_rate": 0.00016277508875231302, "logits/chosen": -0.5684705972671509, "logits/rejected": -0.7857838273048401, "logps/chosen": -5.808892250061035, "logps/rejected": -83.46935272216797, "loss": 0.41192197799682617, "memory(GiB)": 41.24, "nll_loss": 0.3203110098838806, "rewards/accuracies": 0.96875, "rewards/chosen": 0.05355273187160492, "rewards/margins": 6.413900375366211, "rewards/rejected": -6.360347747802734, "step": 166, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9628828828828829, "grad_norm": 1.4706615209579468, "learning_rate": 0.00016227778090248648, "logits/chosen": -0.48619288206100464, "logits/rejected": -0.7674732208251953, "logps/chosen": -1.154846429824829, "logps/rejected": -72.29942321777344, "loss": 0.18448084592819214, "memory(GiB)": 41.24, "nll_loss": 0.1356724500656128, "rewards/accuracies": 1.0, "rewards/chosen": 0.2431672066450119, "rewards/margins": 5.5912065505981445, "rewards/rejected": -5.348039150238037, "step": 167, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9686486486486486, "grad_norm": 1.3399150371551514, "learning_rate": 0.00016177794411824544, "logits/chosen": -0.5658018589019775, "logits/rejected": -0.8080291748046875, "logps/chosen": -3.5855631828308105, "logps/rejected": -70.36351013183594, "loss": 0.33944055438041687, "memory(GiB)": 41.24, "nll_loss": 0.2699050009250641, "rewards/accuracies": 0.96875, "rewards/chosen": 0.18274028599262238, "rewards/margins": 5.833596229553223, "rewards/rejected": -5.650856018066406, "step": 168, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9744144144144145, "grad_norm": 3.7518484592437744, "learning_rate": 0.00016127559869662722, "logits/chosen": -0.46642014384269714, "logits/rejected": -0.8066117167472839, "logps/chosen": -3.712211847305298, "logps/rejected": -80.26597595214844, "loss": 0.25077763199806213, "memory(GiB)": 41.24, "nll_loss": 0.19776861369609833, "rewards/accuracies": 0.96875, "rewards/chosen": -0.023500367999076843, "rewards/margins": 6.045979022979736, "rewards/rejected": -6.069479942321777, "step": 169, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9801801801801802, "grad_norm": 1.6079647541046143, "learning_rate": 0.00016077076503653826, "logits/chosen": -0.47919565439224243, "logits/rejected": -0.7426984310150146, "logps/chosen": -3.771472454071045, "logps/rejected": -72.3167495727539, "loss": 0.34788501262664795, "memory(GiB)": 41.24, "nll_loss": 0.26689645648002625, "rewards/accuracies": 1.0, "rewards/chosen": 0.13779021799564362, "rewards/margins": 5.563295364379883, "rewards/rejected": -5.4255051612854, "step": 170, "train_speed(iter/s)": 0.010714 }, { "epoch": 0.985945945945946, "grad_norm": 3.0278408527374268, "learning_rate": 0.00016026346363792567, "logits/chosen": -0.431247353553772, "logits/rejected": -0.7434531450271606, "logps/chosen": -3.02232027053833, "logps/rejected": -71.19493103027344, "loss": 0.3027627468109131, "memory(GiB)": 41.24, "nll_loss": 0.2018585056066513, "rewards/accuracies": 0.96875, "rewards/chosen": 0.1917632669210434, "rewards/margins": 5.246973991394043, "rewards/rejected": -5.055210113525391, "step": 171, "train_speed(iter/s)": 0.010713 }, { "epoch": 0.9917117117117117, "grad_norm": 1.8670094013214111, "learning_rate": 0.00015975371510094485, "logits/chosen": -0.5508197546005249, "logits/rejected": -0.7615008354187012, "logps/chosen": -6.864560604095459, "logps/rejected": -65.1205825805664, "loss": 0.4220251142978668, "memory(GiB)": 41.24, "nll_loss": 0.38794711232185364, "rewards/accuracies": 1.0, "rewards/chosen": 0.46989697217941284, "rewards/margins": 5.622817039489746, "rewards/rejected": -5.152919769287109, "step": 172, "train_speed(iter/s)": 0.010714 }, { "epoch": 0.9974774774774775, "grad_norm": 1.1435422897338867, "learning_rate": 0.00015924154012512308, "logits/chosen": -0.5378420948982239, "logits/rejected": -0.837982177734375, "logps/chosen": -2.298398971557617, "logps/rejected": -76.451904296875, "loss": 0.18354284763336182, "memory(GiB)": 41.24, "nll_loss": 0.1457872986793518, "rewards/accuracies": 1.0, "rewards/chosen": 0.08272568881511688, "rewards/margins": 5.861605167388916, "rewards/rejected": -5.778879165649414, "step": 173, "train_speed(iter/s)": 0.010714 }, { "epoch": 1.0, "grad_norm": 1.1435422897338867, "learning_rate": 0.0001587269595085186, "logits/chosen": -0.46139007806777954, "logits/rejected": -0.787911593914032, "logps/chosen": -2.2199597358703613, "logps/rejected": -95.19585418701172, "loss": 0.09489377588033676, "memory(GiB)": 41.24, "nll_loss": 0.14853443205356598, "rewards/accuracies": 0.9285714030265808, "rewards/chosen": 0.0750870555639267, "rewards/margins": 7.632567882537842, "rewards/rejected": -7.557480812072754, "step": 174, "train_speed(iter/s)": 0.010751 }, { "epoch": 1.0057657657657657, "grad_norm": 1.8974206447601318, "learning_rate": 0.00015820999414687656, "logits/chosen": -0.5884040594100952, "logits/rejected": -0.821685254573822, "logps/chosen": -2.4951252937316895, "logps/rejected": -70.88331604003906, "loss": 0.2344619631767273, "memory(GiB)": 41.24, "nll_loss": 0.19315816462039948, "rewards/accuracies": 1.0, "rewards/chosen": 0.15108144283294678, "rewards/margins": 5.873671531677246, "rewards/rejected": -5.72258996963501, "step": 175, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0115315315315316, "grad_norm": 0.6439478397369385, "learning_rate": 0.00015769066503277997, "logits/chosen": -0.52037113904953, "logits/rejected": -0.7941011786460876, "logps/chosen": -2.5466148853302, "logps/rejected": -88.6285171508789, "loss": 0.16956239938735962, "memory(GiB)": 41.24, "nll_loss": 0.14753001928329468, "rewards/accuracies": 1.0, "rewards/chosen": 0.19697943329811096, "rewards/margins": 6.911043167114258, "rewards/rejected": -6.714064121246338, "step": 176, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0172972972972973, "grad_norm": 0.8241242170333862, "learning_rate": 0.0001571689932547978, "logits/chosen": -0.5486235618591309, "logits/rejected": -0.8218496441841125, "logps/chosen": -4.344364643096924, "logps/rejected": -78.90025329589844, "loss": 0.23550763726234436, "memory(GiB)": 41.24, "nll_loss": 0.1828317493200302, "rewards/accuracies": 1.0, "rewards/chosen": 0.23757538199424744, "rewards/margins": 6.283997058868408, "rewards/rejected": -6.046421527862549, "step": 177, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.023063063063063, "grad_norm": 0.8632805943489075, "learning_rate": 0.00015664499999662815, "logits/chosen": -0.5551503896713257, "logits/rejected": -0.8251141309738159, "logps/chosen": -2.980712890625, "logps/rejected": -83.22628784179688, "loss": 0.15064574778079987, "memory(GiB)": 41.24, "nll_loss": 0.13642281293869019, "rewards/accuracies": 1.0, "rewards/chosen": 0.2624984383583069, "rewards/margins": 6.998701572418213, "rewards/rejected": -6.736203193664551, "step": 178, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0288288288288288, "grad_norm": 1.1632269620895386, "learning_rate": 0.00015611870653623825, "logits/chosen": -0.4921662211418152, "logits/rejected": -0.8483188152313232, "logps/chosen": -1.3713245391845703, "logps/rejected": -85.42861938476562, "loss": 0.1704276204109192, "memory(GiB)": 41.24, "nll_loss": 0.1270376294851303, "rewards/accuracies": 0.96875, "rewards/chosen": 0.12698447704315186, "rewards/margins": 6.958097457885742, "rewards/rejected": -6.831112861633301, "step": 179, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0345945945945947, "grad_norm": 1.6630468368530273, "learning_rate": 0.00015559013424500047, "logits/chosen": -0.6110640168190002, "logits/rejected": -0.8926798105239868, "logps/chosen": -2.6163129806518555, "logps/rejected": -90.13837432861328, "loss": 0.14455236494541168, "memory(GiB)": 41.24, "nll_loss": 0.1374558061361313, "rewards/accuracies": 1.0, "rewards/chosen": 0.3422771096229553, "rewards/margins": 7.565336227416992, "rewards/rejected": -7.223059177398682, "step": 180, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0403603603603604, "grad_norm": 1.077152132987976, "learning_rate": 0.0001550593045868244, "logits/chosen": -0.603461742401123, "logits/rejected": -0.8620364665985107, "logps/chosen": -4.633229732513428, "logps/rejected": -76.99014282226562, "loss": 0.40596532821655273, "memory(GiB)": 41.24, "nll_loss": 0.3524565100669861, "rewards/accuracies": 0.96875, "rewards/chosen": 0.26899972558021545, "rewards/margins": 6.21177864074707, "rewards/rejected": -5.942779064178467, "step": 181, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.046126126126126, "grad_norm": 12.267168045043945, "learning_rate": 0.00015452623911728523, "logits/chosen": -0.6155453324317932, "logits/rejected": -0.906221866607666, "logps/chosen": -4.583263397216797, "logps/rejected": -87.18157196044922, "loss": 0.3373698592185974, "memory(GiB)": 41.24, "nll_loss": 0.3133515417575836, "rewards/accuracies": 1.0, "rewards/chosen": 0.26982182264328003, "rewards/margins": 7.339932441711426, "rewards/rejected": -7.070110321044922, "step": 182, "train_speed(iter/s)": 0.01075 }, { "epoch": 1.0518918918918918, "grad_norm": 0.7905959486961365, "learning_rate": 0.00015399095948274852, "logits/chosen": -0.5579067468643188, "logits/rejected": -0.8554020524024963, "logps/chosen": -1.4490176439285278, "logps/rejected": -91.41957092285156, "loss": 0.12704932689666748, "memory(GiB)": 41.24, "nll_loss": 0.09653271734714508, "rewards/accuracies": 1.0, "rewards/chosen": 0.26760008931159973, "rewards/margins": 7.848196029663086, "rewards/rejected": -7.58059549331665, "step": 183, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0576576576576577, "grad_norm": 1.1468485593795776, "learning_rate": 0.00015345348741949117, "logits/chosen": -0.5733897089958191, "logits/rejected": -0.9108660221099854, "logps/chosen": -3.66715669631958, "logps/rejected": -95.78589630126953, "loss": 0.24044549465179443, "memory(GiB)": 41.24, "nll_loss": 0.21640615165233612, "rewards/accuracies": 1.0, "rewards/chosen": 0.16394057869911194, "rewards/margins": 7.828693389892578, "rewards/rejected": -7.664752960205078, "step": 184, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0634234234234234, "grad_norm": 2.031723976135254, "learning_rate": 0.00015291384475281877, "logits/chosen": -0.49676764011383057, "logits/rejected": -0.8489770293235779, "logps/chosen": -1.7427412271499634, "logps/rejected": -96.12220764160156, "loss": 0.12766067683696747, "memory(GiB)": 41.24, "nll_loss": 0.11571483314037323, "rewards/accuracies": 1.0, "rewards/chosen": 0.14926967024803162, "rewards/margins": 7.909836769104004, "rewards/rejected": -7.760568141937256, "step": 185, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0691891891891891, "grad_norm": 2.5470285415649414, "learning_rate": 0.00015237205339617917, "logits/chosen": -0.5048971772193909, "logits/rejected": -0.7917367219924927, "logps/chosen": -4.352810382843018, "logps/rejected": -81.40713500976562, "loss": 0.31023305654525757, "memory(GiB)": 41.24, "nll_loss": 0.2897438108921051, "rewards/accuracies": 1.0, "rewards/chosen": 0.14250265061855316, "rewards/margins": 6.402338981628418, "rewards/rejected": -6.259836196899414, "step": 186, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0749549549549549, "grad_norm": 1.091139316558838, "learning_rate": 0.000151828135350273, "logits/chosen": -0.5620720982551575, "logits/rejected": -0.841740608215332, "logps/chosen": -1.8221709728240967, "logps/rejected": -82.46046447753906, "loss": 0.15480715036392212, "memory(GiB)": 41.24, "nll_loss": 0.12393927574157715, "rewards/accuracies": 1.0, "rewards/chosen": 0.3422683775424957, "rewards/margins": 6.792727470397949, "rewards/rejected": -6.450459003448486, "step": 187, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0807207207207208, "grad_norm": 0.9704499244689941, "learning_rate": 0.00015128211270215992, "logits/chosen": -0.6280016899108887, "logits/rejected": -0.8943365812301636, "logps/chosen": -2.3877384662628174, "logps/rejected": -81.13067626953125, "loss": 0.18478192389011383, "memory(GiB)": 41.24, "nll_loss": 0.16890017688274384, "rewards/accuracies": 1.0, "rewards/chosen": 0.34920331835746765, "rewards/margins": 6.807940483093262, "rewards/rejected": -6.458736896514893, "step": 188, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0864864864864865, "grad_norm": 1.0640044212341309, "learning_rate": 0.00015073400762436197, "logits/chosen": -0.6785641312599182, "logits/rejected": -0.8755528330802917, "logps/chosen": -3.03802490234375, "logps/rejected": -80.31719970703125, "loss": 0.23102031648159027, "memory(GiB)": 41.24, "nll_loss": 0.20030677318572998, "rewards/accuracies": 1.0, "rewards/chosen": 0.299454927444458, "rewards/margins": 6.583179473876953, "rewards/rejected": -6.283725261688232, "step": 189, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.0922522522522522, "grad_norm": 1.2426904439926147, "learning_rate": 0.00015018384237396292, "logits/chosen": -0.6075233221054077, "logits/rejected": -0.9030817747116089, "logps/chosen": -3.1166131496429443, "logps/rejected": -88.71156311035156, "loss": 0.1606086939573288, "memory(GiB)": 41.24, "nll_loss": 0.1422414779663086, "rewards/accuracies": 1.0, "rewards/chosen": 0.22253718972206116, "rewards/margins": 7.480426788330078, "rewards/rejected": -7.257890224456787, "step": 190, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.098018018018018, "grad_norm": 13.646331787109375, "learning_rate": 0.0001496316392917049, "logits/chosen": -0.5769588351249695, "logits/rejected": -0.9033970236778259, "logps/chosen": -1.5371689796447754, "logps/rejected": -104.17735290527344, "loss": 0.10281458497047424, "memory(GiB)": 41.24, "nll_loss": 0.09561118483543396, "rewards/accuracies": 1.0, "rewards/chosen": 0.2810855209827423, "rewards/margins": 8.708104133605957, "rewards/rejected": -8.427018165588379, "step": 191, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1037837837837838, "grad_norm": 1.8991550207138062, "learning_rate": 0.00014907742080108073, "logits/chosen": -0.6996522545814514, "logits/rejected": -0.9485704302787781, "logps/chosen": -3.0516557693481445, "logps/rejected": -86.58012390136719, "loss": 0.4684174954891205, "memory(GiB)": 41.24, "nll_loss": 0.4487941563129425, "rewards/accuracies": 1.0, "rewards/chosen": 0.19735433161258698, "rewards/margins": 7.334392547607422, "rewards/rejected": -7.137038230895996, "step": 192, "train_speed(iter/s)": 0.01075 }, { "epoch": 1.1095495495495495, "grad_norm": 19.20090675354004, "learning_rate": 0.0001485212094074237, "logits/chosen": -0.576482892036438, "logits/rejected": -0.84342360496521, "logps/chosen": -4.030856132507324, "logps/rejected": -86.30321502685547, "loss": 0.6711006760597229, "memory(GiB)": 41.24, "nll_loss": 0.6366056799888611, "rewards/accuracies": 1.0, "rewards/chosen": 0.26511046290397644, "rewards/margins": 7.336245536804199, "rewards/rejected": -7.071135520935059, "step": 193, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1153153153153152, "grad_norm": 0.9619101881980896, "learning_rate": 0.0001479630276969936, "logits/chosen": -0.6200534701347351, "logits/rejected": -0.8699415922164917, "logps/chosen": -3.693956136703491, "logps/rejected": -93.85980987548828, "loss": 0.09817313402891159, "memory(GiB)": 41.24, "nll_loss": 0.08495140075683594, "rewards/accuracies": 1.0, "rewards/chosen": 0.26861289143562317, "rewards/margins": 8.128625869750977, "rewards/rejected": -7.860013008117676, "step": 194, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1210810810810812, "grad_norm": 0.7348951101303101, "learning_rate": 0.00014740289833605939, "logits/chosen": -0.6436381936073303, "logits/rejected": -0.9239126443862915, "logps/chosen": -3.7549028396606445, "logps/rejected": -93.33834838867188, "loss": 0.26953551173210144, "memory(GiB)": 41.24, "nll_loss": 0.24437427520751953, "rewards/accuracies": 1.0, "rewards/chosen": 0.1677757203578949, "rewards/margins": 7.494346618652344, "rewards/rejected": -7.326571464538574, "step": 195, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1268468468468469, "grad_norm": 5.2597246170043945, "learning_rate": 0.00014684084406997903, "logits/chosen": -0.6959158778190613, "logits/rejected": -0.9090582132339478, "logps/chosen": -2.6071348190307617, "logps/rejected": -81.92942810058594, "loss": 0.1599394530057907, "memory(GiB)": 41.24, "nll_loss": 0.13409104943275452, "rewards/accuracies": 1.0, "rewards/chosen": 0.21387647092342377, "rewards/margins": 6.953554630279541, "rewards/rejected": -6.739677906036377, "step": 196, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1326126126126126, "grad_norm": 0.9787479639053345, "learning_rate": 0.0001462768877222757, "logits/chosen": -0.5895656943321228, "logits/rejected": -0.9225438833236694, "logps/chosen": -1.224118947982788, "logps/rejected": -100.8663558959961, "loss": 0.06828276813030243, "memory(GiB)": 41.24, "nll_loss": 0.06501688808202744, "rewards/accuracies": 1.0, "rewards/chosen": 0.2447878122329712, "rewards/margins": 8.5127534866333, "rewards/rejected": -8.267965316772461, "step": 197, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1383783783783783, "grad_norm": 0.7639157176017761, "learning_rate": 0.00014571105219371102, "logits/chosen": -0.6577166318893433, "logits/rejected": -0.9819097518920898, "logps/chosen": -0.7252616286277771, "logps/rejected": -81.32587432861328, "loss": 0.1278780996799469, "memory(GiB)": 41.24, "nll_loss": 0.10438857972621918, "rewards/accuracies": 1.0, "rewards/chosen": 0.18735525012016296, "rewards/margins": 6.4731879234313965, "rewards/rejected": -6.28583288192749, "step": 198, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1441441441441442, "grad_norm": 0.956177830696106, "learning_rate": 0.00014514336046135518, "logits/chosen": -0.7244867086410522, "logits/rejected": -0.9211379289627075, "logps/chosen": -3.929692268371582, "logps/rejected": -73.1805419921875, "loss": 0.2801938056945801, "memory(GiB)": 41.24, "nll_loss": 0.22287607192993164, "rewards/accuracies": 1.0, "rewards/chosen": 0.23973776400089264, "rewards/margins": 6.041521072387695, "rewards/rejected": -5.801782608032227, "step": 199, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.14990990990991, "grad_norm": 0.9859761595726013, "learning_rate": 0.00014457383557765386, "logits/chosen": -0.6032741069793701, "logits/rejected": -0.8709255456924438, "logps/chosen": -2.3330612182617188, "logps/rejected": -78.04156494140625, "loss": 0.21972186863422394, "memory(GiB)": 41.24, "nll_loss": 0.16077226400375366, "rewards/accuracies": 1.0, "rewards/chosen": 0.6756027936935425, "rewards/margins": 6.16083288192749, "rewards/rejected": -5.485230445861816, "step": 200, "train_speed(iter/s)": 0.010749 }, { "epoch": 1.1556756756756756, "grad_norm": 2.053891658782959, "learning_rate": 0.00014400250066949196, "logits/chosen": -0.7468363642692566, "logits/rejected": -0.9693096876144409, "logps/chosen": -2.202683210372925, "logps/rejected": -83.35052490234375, "loss": 0.1414460837841034, "memory(GiB)": 41.24, "nll_loss": 0.1286502480506897, "rewards/accuracies": 1.0, "rewards/chosen": 0.2432466298341751, "rewards/margins": 7.013325214385986, "rewards/rejected": -6.770079612731934, "step": 201, "train_speed(iter/s)": 0.010738 }, { "epoch": 1.1614414414414413, "grad_norm": 0.7447286248207092, "learning_rate": 0.00014342937893725488, "logits/chosen": -0.6638346910476685, "logits/rejected": -0.9504916071891785, "logps/chosen": -1.4076967239379883, "logps/rejected": -91.8344955444336, "loss": 0.11076842993497849, "memory(GiB)": 41.24, "nll_loss": 0.0927545577287674, "rewards/accuracies": 1.0, "rewards/chosen": 0.2952735722064972, "rewards/margins": 7.439762592315674, "rewards/rejected": -7.144488334655762, "step": 202, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.1672072072072073, "grad_norm": 1.7305192947387695, "learning_rate": 0.00014285449365388598, "logits/chosen": -0.6913129687309265, "logits/rejected": -1.0035713911056519, "logps/chosen": -2.595938205718994, "logps/rejected": -93.46743774414062, "loss": 0.1786770224571228, "memory(GiB)": 41.24, "nll_loss": 0.15392035245895386, "rewards/accuracies": 1.0, "rewards/chosen": 0.16032256186008453, "rewards/margins": 7.787504196166992, "rewards/rejected": -7.627182483673096, "step": 203, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.172972972972973, "grad_norm": 0.7990829944610596, "learning_rate": 0.00014227786816394184, "logits/chosen": -0.7262576818466187, "logits/rejected": -1.0095360279083252, "logps/chosen": -4.604730606079102, "logps/rejected": -94.75875091552734, "loss": 0.1926305592060089, "memory(GiB)": 41.24, "nll_loss": 0.18425899744033813, "rewards/accuracies": 1.0, "rewards/chosen": 0.40172773599624634, "rewards/margins": 7.936948776245117, "rewards/rejected": -7.535220623016357, "step": 204, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.1787387387387387, "grad_norm": 0.7804811596870422, "learning_rate": 0.00014169952588264417, "logits/chosen": -0.7492111921310425, "logits/rejected": -1.052622675895691, "logps/chosen": -2.9088637828826904, "logps/rejected": -99.19158935546875, "loss": 0.13855330646038055, "memory(GiB)": 41.24, "nll_loss": 0.12824688851833344, "rewards/accuracies": 1.0, "rewards/chosen": 0.23516345024108887, "rewards/margins": 8.24970531463623, "rewards/rejected": -8.014541625976562, "step": 205, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.1845045045045044, "grad_norm": 1.3688875436782837, "learning_rate": 0.0001411194902949289, "logits/chosen": -0.7413324117660522, "logits/rejected": -1.0183649063110352, "logps/chosen": -3.5715129375457764, "logps/rejected": -105.68714141845703, "loss": 0.2724800109863281, "memory(GiB)": 41.24, "nll_loss": 0.25694820284843445, "rewards/accuracies": 1.0, "rewards/chosen": 0.313816636800766, "rewards/margins": 8.691929817199707, "rewards/rejected": -8.37811279296875, "step": 206, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.1902702702702703, "grad_norm": 2.0642895698547363, "learning_rate": 0.0001405377849544927, "logits/chosen": -0.6753020286560059, "logits/rejected": -1.0321030616760254, "logps/chosen": -2.917701005935669, "logps/rejected": -96.5132827758789, "loss": 0.17677046358585358, "memory(GiB)": 41.24, "nll_loss": 0.15049855411052704, "rewards/accuracies": 0.96875, "rewards/chosen": 0.27416104078292847, "rewards/margins": 7.89042854309082, "rewards/rejected": -7.616267681121826, "step": 207, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.196036036036036, "grad_norm": 1.8087902069091797, "learning_rate": 0.00013995443348283645, "logits/chosen": -0.6556892395019531, "logits/rejected": -0.991775631904602, "logps/chosen": -2.722226858139038, "logps/rejected": -102.24663543701172, "loss": 0.24504928290843964, "memory(GiB)": 41.24, "nll_loss": 0.20121188461780548, "rewards/accuracies": 0.96875, "rewards/chosen": 0.2066883146762848, "rewards/margins": 8.376320838928223, "rewards/rejected": -8.169632911682129, "step": 208, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2018018018018017, "grad_norm": 1.0671130418777466, "learning_rate": 0.00013936945956830602, "logits/chosen": -0.7256425023078918, "logits/rejected": -1.002614140510559, "logps/chosen": -3.5971474647521973, "logps/rejected": -90.5836181640625, "loss": 0.22293436527252197, "memory(GiB)": 41.24, "nll_loss": 0.18081282079219818, "rewards/accuracies": 1.0, "rewards/chosen": 0.19337910413742065, "rewards/margins": 7.3919477462768555, "rewards/rejected": -7.198568344116211, "step": 209, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2075675675675677, "grad_norm": 1.3437083959579468, "learning_rate": 0.00013878288696513022, "logits/chosen": -0.7431738376617432, "logits/rejected": -1.0425618886947632, "logps/chosen": -2.174896240234375, "logps/rejected": -93.76087951660156, "loss": 0.15365180373191833, "memory(GiB)": 41.24, "nll_loss": 0.14746138453483582, "rewards/accuracies": 1.0, "rewards/chosen": 0.2575794756412506, "rewards/margins": 7.875104904174805, "rewards/rejected": -7.617526054382324, "step": 210, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2133333333333334, "grad_norm": 0.76457679271698, "learning_rate": 0.00013819473949245654, "logits/chosen": -0.6461102962493896, "logits/rejected": -1.0543663501739502, "logps/chosen": -0.8342275619506836, "logps/rejected": -104.50704193115234, "loss": 0.09112594276666641, "memory(GiB)": 41.24, "nll_loss": 0.08857303112745285, "rewards/accuracies": 1.0, "rewards/chosen": 0.23656663298606873, "rewards/margins": 8.866386413574219, "rewards/rejected": -8.629819869995117, "step": 211, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.219099099099099, "grad_norm": 0.6871019005775452, "learning_rate": 0.0001376050410333836, "logits/chosen": -0.6719679236412048, "logits/rejected": -0.9832717776298523, "logps/chosen": -3.1014583110809326, "logps/rejected": -98.14430236816406, "loss": 0.3030906915664673, "memory(GiB)": 41.24, "nll_loss": 0.21772870421409607, "rewards/accuracies": 0.96875, "rewards/chosen": 0.02887733280658722, "rewards/margins": 7.6625895500183105, "rewards/rejected": -7.633711814880371, "step": 212, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2248648648648648, "grad_norm": 2.0604000091552734, "learning_rate": 0.00013701381553399145, "logits/chosen": -0.6421749591827393, "logits/rejected": -1.0211272239685059, "logps/chosen": -2.438856840133667, "logps/rejected": -86.31884002685547, "loss": 0.20499145984649658, "memory(GiB)": 41.24, "nll_loss": 0.1656690537929535, "rewards/accuracies": 1.0, "rewards/chosen": 0.1947031468153, "rewards/margins": 7.004463195800781, "rewards/rejected": -6.809760093688965, "step": 213, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2306306306306307, "grad_norm": 2.321046829223633, "learning_rate": 0.00013642108700236916, "logits/chosen": -0.7420238852500916, "logits/rejected": -1.0413094758987427, "logps/chosen": -0.9865455031394958, "logps/rejected": -72.17105102539062, "loss": 0.13595286011695862, "memory(GiB)": 41.24, "nll_loss": 0.10351557284593582, "rewards/accuracies": 1.0, "rewards/chosen": 0.11004337668418884, "rewards/margins": 5.79013204574585, "rewards/rejected": -5.680088520050049, "step": 214, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2363963963963964, "grad_norm": 4.301558494567871, "learning_rate": 0.00013582687950764, "logits/chosen": -0.6356464624404907, "logits/rejected": -0.986944854259491, "logps/chosen": -1.5492937564849854, "logps/rejected": -79.20093536376953, "loss": 0.19731514155864716, "memory(GiB)": 41.24, "nll_loss": 0.15034356713294983, "rewards/accuracies": 1.0, "rewards/chosen": 0.15903238952159882, "rewards/margins": 6.342228412628174, "rewards/rejected": -6.1831955909729, "step": 215, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2421621621621621, "grad_norm": 1.1075836420059204, "learning_rate": 0.00013523121717898387, "logits/chosen": -0.6029863953590393, "logits/rejected": -0.9658622741699219, "logps/chosen": -3.6208183765411377, "logps/rejected": -97.2186508178711, "loss": 0.4900016784667969, "memory(GiB)": 41.24, "nll_loss": 0.44314447045326233, "rewards/accuracies": 0.96875, "rewards/chosen": 0.04553697258234024, "rewards/margins": 7.420025825500488, "rewards/rejected": -7.374488830566406, "step": 216, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2479279279279278, "grad_norm": 2.592005968093872, "learning_rate": 0.00013463412420465767, "logits/chosen": -0.6447511911392212, "logits/rejected": -0.9609813094139099, "logps/chosen": -2.2061100006103516, "logps/rejected": -88.9801254272461, "loss": 0.21441426873207092, "memory(GiB)": 41.24, "nll_loss": 0.20333540439605713, "rewards/accuracies": 1.0, "rewards/chosen": 0.2582980692386627, "rewards/margins": 6.966536521911621, "rewards/rejected": -6.70823860168457, "step": 217, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2536936936936938, "grad_norm": 1.5074249505996704, "learning_rate": 0.00013403562483101298, "logits/chosen": -0.66890949010849, "logits/rejected": -0.8881216049194336, "logps/chosen": -4.03311014175415, "logps/rejected": -70.53189086914062, "loss": 0.306526780128479, "memory(GiB)": 41.24, "nll_loss": 0.22115619480609894, "rewards/accuracies": 1.0, "rewards/chosen": 0.29509076476097107, "rewards/margins": 5.955531120300293, "rewards/rejected": -5.660440444946289, "step": 218, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2594594594594595, "grad_norm": 0.588188886642456, "learning_rate": 0.00013343574336151153, "logits/chosen": -0.6300919055938721, "logits/rejected": -0.9817159175872803, "logps/chosen": -2.001368761062622, "logps/rejected": -94.01361083984375, "loss": 0.3623042702674866, "memory(GiB)": 41.24, "nll_loss": 0.2725469172000885, "rewards/accuracies": 0.96875, "rewards/chosen": 0.15840183198451996, "rewards/margins": 7.825695991516113, "rewards/rejected": -7.667293548583984, "step": 219, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2652252252252252, "grad_norm": 14.042351722717285, "learning_rate": 0.0001328345041557382, "logits/chosen": -0.759201169013977, "logits/rejected": -1.016777515411377, "logps/chosen": -3.4606502056121826, "logps/rejected": -93.0523910522461, "loss": 0.20867016911506653, "memory(GiB)": 41.24, "nll_loss": 0.15421104431152344, "rewards/accuracies": 0.96875, "rewards/chosen": 0.11695647984743118, "rewards/margins": 7.954014301300049, "rewards/rejected": -7.8370585441589355, "step": 220, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2709909909909909, "grad_norm": 1.2167177200317383, "learning_rate": 0.000132231931628412, "logits/chosen": -0.5667409896850586, "logits/rejected": -0.8965315222740173, "logps/chosen": -3.431696891784668, "logps/rejected": -105.54657745361328, "loss": 0.1707317978143692, "memory(GiB)": 41.24, "nll_loss": 0.1522923707962036, "rewards/accuracies": 1.0, "rewards/chosen": 0.24732309579849243, "rewards/margins": 8.84961223602295, "rewards/rejected": -8.602288246154785, "step": 221, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2767567567567568, "grad_norm": 0.9449612498283386, "learning_rate": 0.00013162805024839448, "logits/chosen": -0.6432092189788818, "logits/rejected": -0.8541032075881958, "logps/chosen": -3.5057826042175293, "logps/rejected": -85.99465942382812, "loss": 0.2346688210964203, "memory(GiB)": 41.24, "nll_loss": 0.19423571228981018, "rewards/accuracies": 1.0, "rewards/chosen": 0.5884712338447571, "rewards/margins": 7.24459981918335, "rewards/rejected": -6.656128883361816, "step": 222, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.2825225225225225, "grad_norm": 1.486234426498413, "learning_rate": 0.00013102288453769632, "logits/chosen": -0.6213188171386719, "logits/rejected": -0.9732288718223572, "logps/chosen": -2.9368274211883545, "logps/rejected": -108.50143432617188, "loss": 0.19141153991222382, "memory(GiB)": 41.24, "nll_loss": 0.1635173112154007, "rewards/accuracies": 1.0, "rewards/chosen": 0.09779652208089828, "rewards/margins": 8.9135103225708, "rewards/rejected": -8.815712928771973, "step": 223, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.2882882882882882, "grad_norm": 1.301498532295227, "learning_rate": 0.0001304164590704813, "logits/chosen": -0.6701276302337646, "logits/rejected": -0.9731598496437073, "logps/chosen": -3.8457467555999756, "logps/rejected": -93.66019439697266, "loss": 0.28035908937454224, "memory(GiB)": 41.24, "nll_loss": 0.24942338466644287, "rewards/accuracies": 0.96875, "rewards/chosen": 0.4500879943370819, "rewards/margins": 8.23204517364502, "rewards/rejected": -7.781956672668457, "step": 224, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.2940540540540542, "grad_norm": 1.0099408626556396, "learning_rate": 0.0001298087984720687, "logits/chosen": -0.7134125232696533, "logits/rejected": -0.9936617612838745, "logps/chosen": -2.324589967727661, "logps/rejected": -90.27128601074219, "loss": 0.39343133568763733, "memory(GiB)": 41.24, "nll_loss": 0.2453940212726593, "rewards/accuracies": 0.96875, "rewards/chosen": 0.25489863753318787, "rewards/margins": 7.6775102615356445, "rewards/rejected": -7.422612190246582, "step": 225, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.2998198198198199, "grad_norm": 2.37233829498291, "learning_rate": 0.00012919992741793307, "logits/chosen": -0.6083082556724548, "logits/rejected": -0.9392067193984985, "logps/chosen": -2.33506441116333, "logps/rejected": -91.54042053222656, "loss": 0.18458783626556396, "memory(GiB)": 41.24, "nll_loss": 0.17687150835990906, "rewards/accuracies": 1.0, "rewards/chosen": 0.32263070344924927, "rewards/margins": 7.811326503753662, "rewards/rejected": -7.488696098327637, "step": 226, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3055855855855856, "grad_norm": 0.9204962253570557, "learning_rate": 0.0001285898706327023, "logits/chosen": -0.6583359837532043, "logits/rejected": -0.9856835007667542, "logps/chosen": -2.480973720550537, "logps/rejected": -98.34219360351562, "loss": 0.22872069478034973, "memory(GiB)": 41.24, "nll_loss": 0.2118297517299652, "rewards/accuracies": 1.0, "rewards/chosen": 0.37609827518463135, "rewards/margins": 8.75016975402832, "rewards/rejected": -8.37407112121582, "step": 227, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3113513513513513, "grad_norm": 1.0065797567367554, "learning_rate": 0.0001279786528891538, "logits/chosen": -0.564249575138092, "logits/rejected": -0.8596559762954712, "logps/chosen": -2.2762789726257324, "logps/rejected": -94.75420379638672, "loss": 0.09863093495368958, "memory(GiB)": 41.24, "nll_loss": 0.09180156141519547, "rewards/accuracies": 1.0, "rewards/chosen": 0.30846285820007324, "rewards/margins": 8.076614379882812, "rewards/rejected": -7.76815128326416, "step": 228, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.317117117117117, "grad_norm": 15.840254783630371, "learning_rate": 0.0001273662990072083, "logits/chosen": -0.6420232057571411, "logits/rejected": -0.9717917442321777, "logps/chosen": -4.723894119262695, "logps/rejected": -91.68743896484375, "loss": 0.5773552656173706, "memory(GiB)": 41.24, "nll_loss": 0.4086422324180603, "rewards/accuracies": 0.9375, "rewards/chosen": 0.09256955981254578, "rewards/margins": 7.509539604187012, "rewards/rejected": -7.416969299316406, "step": 229, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.322882882882883, "grad_norm": 0.9773613810539246, "learning_rate": 0.00012675283385292212, "logits/chosen": -0.5419533252716064, "logits/rejected": -0.908346951007843, "logps/chosen": -2.8323910236358643, "logps/rejected": -92.77593994140625, "loss": 0.18030104041099548, "memory(GiB)": 41.24, "nll_loss": 0.1703605055809021, "rewards/accuracies": 1.0, "rewards/chosen": 0.3452431559562683, "rewards/margins": 7.826876163482666, "rewards/rejected": -7.48163366317749, "step": 230, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3286486486486486, "grad_norm": 0.5861178636550903, "learning_rate": 0.00012613828233747727, "logits/chosen": -0.5227465629577637, "logits/rejected": -0.867357611656189, "logps/chosen": -2.319690704345703, "logps/rejected": -90.09024810791016, "loss": 0.17545996606349945, "memory(GiB)": 41.24, "nll_loss": 0.14297524094581604, "rewards/accuracies": 1.0, "rewards/chosen": 0.15114043653011322, "rewards/margins": 7.286042213439941, "rewards/rejected": -7.134902477264404, "step": 231, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3344144144144146, "grad_norm": 1.1118627786636353, "learning_rate": 0.00012552266941617018, "logits/chosen": -0.6113250851631165, "logits/rejected": -0.7813447713851929, "logps/chosen": -4.297638893127441, "logps/rejected": -73.71047973632812, "loss": 0.2730986773967743, "memory(GiB)": 41.24, "nll_loss": 0.2158653289079666, "rewards/accuracies": 1.0, "rewards/chosen": 0.24944612383842468, "rewards/margins": 6.196266174316406, "rewards/rejected": -5.946820259094238, "step": 232, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3401801801801803, "grad_norm": 0.8542975783348083, "learning_rate": 0.000124906020087398, "logits/chosen": -0.45566728711128235, "logits/rejected": -0.8274158239364624, "logps/chosen": -1.3975021839141846, "logps/rejected": -92.9134750366211, "loss": 0.10510716587305069, "memory(GiB)": 41.24, "nll_loss": 0.08654335141181946, "rewards/accuracies": 1.0, "rewards/chosen": 0.292056143283844, "rewards/margins": 7.4350056648254395, "rewards/rejected": -7.142949104309082, "step": 233, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.345945945945946, "grad_norm": 0.6710683703422546, "learning_rate": 0.00012428835939164363, "logits/chosen": -0.48423632979393005, "logits/rejected": -0.931830883026123, "logps/chosen": -0.9655717611312866, "logps/rejected": -103.34365844726562, "loss": 0.10704699903726578, "memory(GiB)": 41.24, "nll_loss": 0.10177168250083923, "rewards/accuracies": 1.0, "rewards/chosen": 0.27281564474105835, "rewards/margins": 8.59388256072998, "rewards/rejected": -8.321066856384277, "step": 234, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3517117117117117, "grad_norm": 1.0295995473861694, "learning_rate": 0.00012366971241045894, "logits/chosen": -0.5070984959602356, "logits/rejected": -0.8951232433319092, "logps/chosen": -1.928631067276001, "logps/rejected": -88.40235900878906, "loss": 0.21813911199569702, "memory(GiB)": 41.24, "nll_loss": 0.16451862454414368, "rewards/accuracies": 0.96875, "rewards/chosen": 0.064000703394413, "rewards/margins": 7.2806854248046875, "rewards/rejected": -7.216684341430664, "step": 235, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3574774774774774, "grad_norm": 0.8053532242774963, "learning_rate": 0.00012305010426544614, "logits/chosen": -0.5998705625534058, "logits/rejected": -0.9042835831642151, "logps/chosen": -4.446467876434326, "logps/rejected": -86.84009552001953, "loss": 0.25722736120224, "memory(GiB)": 41.24, "nll_loss": 0.24677737057209015, "rewards/accuracies": 1.0, "rewards/chosen": 0.43149375915527344, "rewards/margins": 7.540010929107666, "rewards/rejected": -7.108516693115234, "step": 236, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3632432432432433, "grad_norm": 1.9170420169830322, "learning_rate": 0.00012242956011723782, "logits/chosen": -0.5368235111236572, "logits/rejected": -0.8908076286315918, "logps/chosen": -1.4597830772399902, "logps/rejected": -100.62641906738281, "loss": 0.1386258900165558, "memory(GiB)": 41.24, "nll_loss": 0.13322040438652039, "rewards/accuracies": 1.0, "rewards/chosen": 0.2073771357536316, "rewards/margins": 8.687051773071289, "rewards/rejected": -8.479674339294434, "step": 237, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.369009009009009, "grad_norm": 1.0038492679595947, "learning_rate": 0.00012180810516447512, "logits/chosen": -0.5559844970703125, "logits/rejected": -0.8453220725059509, "logps/chosen": -3.5673227310180664, "logps/rejected": -92.9088134765625, "loss": 0.23567795753479004, "memory(GiB)": 41.24, "nll_loss": 0.20739604532718658, "rewards/accuracies": 1.0, "rewards/chosen": 0.27056020498275757, "rewards/margins": 7.564149379730225, "rewards/rejected": -7.293589115142822, "step": 238, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.3747747747747747, "grad_norm": 0.7483298182487488, "learning_rate": 0.0001211857646427845, "logits/chosen": -0.5241140723228455, "logits/rejected": -0.8691558837890625, "logps/chosen": -1.9950472116470337, "logps/rejected": -82.87139892578125, "loss": 0.15872085094451904, "memory(GiB)": 41.24, "nll_loss": 0.12550276517868042, "rewards/accuracies": 1.0, "rewards/chosen": 0.3112674951553345, "rewards/margins": 6.984847545623779, "rewards/rejected": -6.673579216003418, "step": 239, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.3805405405405407, "grad_norm": 0.9307670593261719, "learning_rate": 0.00012056256382375308, "logits/chosen": -0.5428832769393921, "logits/rejected": -0.9613853096961975, "logps/chosen": -1.8748772144317627, "logps/rejected": -97.14224243164062, "loss": 0.12880003452301025, "memory(GiB)": 41.24, "nll_loss": 0.12042552977800369, "rewards/accuracies": 1.0, "rewards/chosen": 0.31744644045829773, "rewards/margins": 8.378560066223145, "rewards/rejected": -8.061113357543945, "step": 240, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.3863063063063064, "grad_norm": 2.9521400928497314, "learning_rate": 0.00011993852801390226, "logits/chosen": -0.4635058045387268, "logits/rejected": -0.8949097394943237, "logps/chosen": -0.5122127532958984, "logps/rejected": -96.43069458007812, "loss": 0.10679192841053009, "memory(GiB)": 41.24, "nll_loss": 0.053764842450618744, "rewards/accuracies": 0.96875, "rewards/chosen": 0.165335014462471, "rewards/margins": 8.006298065185547, "rewards/rejected": -7.840963840484619, "step": 241, "train_speed(iter/s)": 0.010737 }, { "epoch": 1.392072072072072, "grad_norm": 1.0468616485595703, "learning_rate": 0.00011931368255366027, "logits/chosen": -0.45876914262771606, "logits/rejected": -0.831932544708252, "logps/chosen": -2.4560790061950684, "logps/rejected": -97.22357177734375, "loss": 0.2074245661497116, "memory(GiB)": 41.24, "nll_loss": 0.17626309394836426, "rewards/accuracies": 1.0, "rewards/chosen": 0.24911226332187653, "rewards/margins": 8.137984275817871, "rewards/rejected": -7.888872146606445, "step": 242, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.3978378378378378, "grad_norm": 0.7075209021568298, "learning_rate": 0.00011868805281633304, "logits/chosen": -0.58433997631073, "logits/rejected": -0.9207597970962524, "logps/chosen": -2.2052416801452637, "logps/rejected": -101.76717376708984, "loss": 0.18332861363887787, "memory(GiB)": 41.24, "nll_loss": 0.1732126772403717, "rewards/accuracies": 1.0, "rewards/chosen": 0.4298679530620575, "rewards/margins": 8.984416961669922, "rewards/rejected": -8.554548263549805, "step": 243, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4036036036036035, "grad_norm": 0.9815582036972046, "learning_rate": 0.00011806166420707392, "logits/chosen": -0.48037832975387573, "logits/rejected": -0.9194313883781433, "logps/chosen": -1.8615732192993164, "logps/rejected": -102.38887023925781, "loss": 0.21181951463222504, "memory(GiB)": 41.24, "nll_loss": 0.15694458782672882, "rewards/accuracies": 0.9375, "rewards/chosen": 0.29181793332099915, "rewards/margins": 8.388344764709473, "rewards/rejected": -8.096527099609375, "step": 244, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4093693693693694, "grad_norm": 2.933603525161743, "learning_rate": 0.00011743454216185201, "logits/chosen": -0.640617311000824, "logits/rejected": -0.9676884412765503, "logps/chosen": -3.7124361991882324, "logps/rejected": -97.49540710449219, "loss": 0.2786301076412201, "memory(GiB)": 41.24, "nll_loss": 0.26465094089508057, "rewards/accuracies": 1.0, "rewards/chosen": 0.17746347188949585, "rewards/margins": 8.408309936523438, "rewards/rejected": -8.23084545135498, "step": 245, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4151351351351351, "grad_norm": 0.6771543025970459, "learning_rate": 0.00011680671214641927, "logits/chosen": -0.4917660057544708, "logits/rejected": -0.9493937492370605, "logps/chosen": -1.4353026151657104, "logps/rejected": -133.36654663085938, "loss": 0.10904774069786072, "memory(GiB)": 41.24, "nll_loss": 0.10567378252744675, "rewards/accuracies": 1.0, "rewards/chosen": 0.24828633666038513, "rewards/margins": 11.476335525512695, "rewards/rejected": -11.228048324584961, "step": 246, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4209009009009008, "grad_norm": 0.5642514824867249, "learning_rate": 0.0001161781996552765, "logits/chosen": -0.5594913363456726, "logits/rejected": -1.0035367012023926, "logps/chosen": -2.4414238929748535, "logps/rejected": -129.03379821777344, "loss": 0.1480759233236313, "memory(GiB)": 41.24, "nll_loss": 0.1389404833316803, "rewards/accuracies": 1.0, "rewards/chosen": 0.01771201565861702, "rewards/margins": 11.155719757080078, "rewards/rejected": -11.138009071350098, "step": 247, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4266666666666667, "grad_norm": 2.8613696098327637, "learning_rate": 0.0001155490302106379, "logits/chosen": -0.5504012703895569, "logits/rejected": -0.993097722530365, "logps/chosen": -1.1884583234786987, "logps/rejected": -113.57362365722656, "loss": 0.11941150575876236, "memory(GiB)": 41.24, "nll_loss": 0.10435314476490021, "rewards/accuracies": 1.0, "rewards/chosen": 0.20970577001571655, "rewards/margins": 9.547948837280273, "rewards/rejected": -9.338242530822754, "step": 248, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4324324324324325, "grad_norm": 0.8018273711204529, "learning_rate": 0.00011491922936139499, "logits/chosen": -0.5908212661743164, "logits/rejected": -0.9416083693504333, "logps/chosen": -2.546377182006836, "logps/rejected": -98.2177963256836, "loss": 0.20611125230789185, "memory(GiB)": 41.24, "nll_loss": 0.19133996963500977, "rewards/accuracies": 1.0, "rewards/chosen": 0.17961813509464264, "rewards/margins": 8.596184730529785, "rewards/rejected": -8.416565895080566, "step": 249, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4381981981981982, "grad_norm": 1.2365566492080688, "learning_rate": 0.00011428882268207872, "logits/chosen": -0.6211739778518677, "logits/rejected": -0.8576729893684387, "logps/chosen": -6.602561950683594, "logps/rejected": -92.08356475830078, "loss": 0.3254232406616211, "memory(GiB)": 41.24, "nll_loss": 0.2950092554092407, "rewards/accuracies": 1.0, "rewards/chosen": 0.45778965950012207, "rewards/margins": 8.364259719848633, "rewards/rejected": -7.90647029876709, "step": 250, "train_speed(iter/s)": 0.010736 }, { "epoch": 1.4439639639639639, "grad_norm": 0.8326837420463562, "learning_rate": 0.00011365783577182132, "logits/chosen": -0.5177187919616699, "logits/rejected": -0.9024335145950317, "logps/chosen": -2.21883225440979, "logps/rejected": -105.33366394042969, "loss": 0.1589798927307129, "memory(GiB)": 41.24, "nll_loss": 0.13007135689258575, "rewards/accuracies": 1.0, "rewards/chosen": 0.3507290780544281, "rewards/margins": 9.073866844177246, "rewards/rejected": -8.723137855529785, "step": 251, "train_speed(iter/s)": 0.010728 }, { "epoch": 1.4497297297297298, "grad_norm": 1.8344132900238037, "learning_rate": 0.00011302629425331666, "logits/chosen": -0.603495180606842, "logits/rejected": -0.801387369632721, "logps/chosen": -5.291406154632568, "logps/rejected": -84.78588104248047, "loss": 0.3241059482097626, "memory(GiB)": 41.24, "nll_loss": 0.2689138948917389, "rewards/accuracies": 0.96875, "rewards/chosen": 0.2446574866771698, "rewards/margins": 7.256671905517578, "rewards/rejected": -7.012013912200928, "step": 252, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.4554954954954955, "grad_norm": 0.6599681377410889, "learning_rate": 0.00011239422377177973, "logits/chosen": -0.5089681148529053, "logits/rejected": -0.8658185005187988, "logps/chosen": -3.079047679901123, "logps/rejected": -127.54818725585938, "loss": 0.17893767356872559, "memory(GiB)": 41.24, "nll_loss": 0.17471365630626678, "rewards/accuracies": 1.0, "rewards/chosen": 0.5883893370628357, "rewards/margins": 11.444487571716309, "rewards/rejected": -10.856100082397461, "step": 253, "train_speed(iter/s)": 0.010728 }, { "epoch": 1.4612612612612612, "grad_norm": 0.6386237144470215, "learning_rate": 0.00011176164999390522, "logits/chosen": -0.5488162040710449, "logits/rejected": -0.9546905755996704, "logps/chosen": -3.4519522190093994, "logps/rejected": -109.98165893554688, "loss": 0.22669866681098938, "memory(GiB)": 41.24, "nll_loss": 0.20005784928798676, "rewards/accuracies": 1.0, "rewards/chosen": 0.3646531105041504, "rewards/margins": 9.544320106506348, "rewards/rejected": -9.179666519165039, "step": 254, "train_speed(iter/s)": 0.010728 }, { "epoch": 1.4670270270270271, "grad_norm": 17.654590606689453, "learning_rate": 0.00011112859860682547, "logits/chosen": -0.5480679869651794, "logits/rejected": -0.9488638639450073, "logps/chosen": -3.5623536109924316, "logps/rejected": -115.0560073852539, "loss": 0.4454716145992279, "memory(GiB)": 41.24, "nll_loss": 0.3780556321144104, "rewards/accuracies": 0.96875, "rewards/chosen": 0.10135876387357712, "rewards/margins": 9.828811645507812, "rewards/rejected": -9.727452278137207, "step": 255, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.4727927927927928, "grad_norm": 0.6790575385093689, "learning_rate": 0.0001104950953170672, "logits/chosen": -0.5322855710983276, "logits/rejected": -0.8911909461021423, "logps/chosen": -2.056039571762085, "logps/rejected": -107.23054504394531, "loss": 0.2234971523284912, "memory(GiB)": 41.24, "nll_loss": 0.20333045721054077, "rewards/accuracies": 1.0, "rewards/chosen": 0.2641701102256775, "rewards/margins": 9.115086555480957, "rewards/rejected": -8.850915908813477, "step": 256, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.4785585585585586, "grad_norm": 0.8362141847610474, "learning_rate": 0.00010986116584950774, "logits/chosen": -0.46502387523651123, "logits/rejected": -0.8917255401611328, "logps/chosen": -1.898627758026123, "logps/rejected": -115.86322021484375, "loss": 0.12826178967952728, "memory(GiB)": 41.24, "nll_loss": 0.11593392491340637, "rewards/accuracies": 1.0, "rewards/chosen": 0.29406896233558655, "rewards/margins": 9.646780014038086, "rewards/rejected": -9.352710723876953, "step": 257, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.4843243243243243, "grad_norm": 0.681954026222229, "learning_rate": 0.00010922683594633021, "logits/chosen": -0.5689491033554077, "logits/rejected": -0.8625025153160095, "logps/chosen": -1.7617994546890259, "logps/rejected": -99.32975769042969, "loss": 0.1266973614692688, "memory(GiB)": 41.24, "nll_loss": 0.11154472082853317, "rewards/accuracies": 1.0, "rewards/chosen": 0.283980131149292, "rewards/margins": 8.681015014648438, "rewards/rejected": -8.397034645080566, "step": 258, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.49009009009009, "grad_norm": 0.6331071853637695, "learning_rate": 0.00010859213136597853, "logits/chosen": -0.5191855430603027, "logits/rejected": -0.8886591196060181, "logps/chosen": -1.3958189487457275, "logps/rejected": -97.13671112060547, "loss": 0.13129664957523346, "memory(GiB)": 41.24, "nll_loss": 0.10424058139324188, "rewards/accuracies": 1.0, "rewards/chosen": 0.33293408155441284, "rewards/margins": 8.300026893615723, "rewards/rejected": -7.967093467712402, "step": 259, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.495855855855856, "grad_norm": 0.7260443568229675, "learning_rate": 0.00010795707788211118, "logits/chosen": -0.4627129137516022, "logits/rejected": -0.824970543384552, "logps/chosen": -3.0662460327148438, "logps/rejected": -102.18391418457031, "loss": 0.20565594732761383, "memory(GiB)": 41.24, "nll_loss": 0.18343128263950348, "rewards/accuracies": 1.0, "rewards/chosen": 0.37244486808776855, "rewards/margins": 8.65424919128418, "rewards/rejected": -8.281805038452148, "step": 260, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.5016216216216216, "grad_norm": 0.8002501726150513, "learning_rate": 0.00010732170128255468, "logits/chosen": -0.4538012444972992, "logits/rejected": -0.7942509651184082, "logps/chosen": -3.3011088371276855, "logps/rejected": -107.73184204101562, "loss": 0.23947054147720337, "memory(GiB)": 41.24, "nll_loss": 0.18957434594631195, "rewards/accuracies": 1.0, "rewards/chosen": 0.30125465989112854, "rewards/margins": 8.832905769348145, "rewards/rejected": -8.531651496887207, "step": 261, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.5073873873873875, "grad_norm": 0.789520800113678, "learning_rate": 0.00010668602736825641, "logits/chosen": -0.5109374523162842, "logits/rejected": -0.8500669002532959, "logps/chosen": -1.8806393146514893, "logps/rejected": -104.79667663574219, "loss": 0.20148895680904388, "memory(GiB)": 41.24, "nll_loss": 0.14439257979393005, "rewards/accuracies": 1.0, "rewards/chosen": 0.4746500253677368, "rewards/margins": 9.070365905761719, "rewards/rejected": -8.595715522766113, "step": 262, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.5131531531531532, "grad_norm": 0.6022177338600159, "learning_rate": 0.00010605008195223694, "logits/chosen": -0.5372226238250732, "logits/rejected": -0.8244591951370239, "logps/chosen": -1.747965693473816, "logps/rejected": -95.3003158569336, "loss": 0.14818598330020905, "memory(GiB)": 41.24, "nll_loss": 0.14205510914325714, "rewards/accuracies": 1.0, "rewards/chosen": 0.252836138010025, "rewards/margins": 8.310218811035156, "rewards/rejected": -8.057382583618164, "step": 263, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.518918918918919, "grad_norm": 0.893842339515686, "learning_rate": 0.00010541389085854176, "logits/chosen": -0.5556601285934448, "logits/rejected": -0.8188039660453796, "logps/chosen": -3.6805174350738525, "logps/rejected": -88.07212829589844, "loss": 0.3132077157497406, "memory(GiB)": 41.24, "nll_loss": 0.28640279173851013, "rewards/accuracies": 1.0, "rewards/chosen": 0.16909292340278625, "rewards/margins": 7.427695274353027, "rewards/rejected": -7.258602619171143, "step": 264, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.5246846846846847, "grad_norm": 2.960935592651367, "learning_rate": 0.00010477747992119273, "logits/chosen": -0.47233614325523376, "logits/rejected": -0.8489798903465271, "logps/chosen": -2.1952314376831055, "logps/rejected": -109.46432495117188, "loss": 0.1649601310491562, "memory(GiB)": 41.24, "nll_loss": 0.15151429176330566, "rewards/accuracies": 1.0, "rewards/chosen": 0.3918912410736084, "rewards/margins": 9.63163948059082, "rewards/rejected": -9.23974895477295, "step": 265, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.5304504504504504, "grad_norm": 1.122962474822998, "learning_rate": 0.0001041408749831389, "logits/chosen": -0.3698769807815552, "logits/rejected": -0.8481926321983337, "logps/chosen": -3.5086236000061035, "logps/rejected": -113.31342315673828, "loss": 0.5645697116851807, "memory(GiB)": 41.24, "nll_loss": 0.42728477716445923, "rewards/accuracies": 0.9375, "rewards/chosen": 0.08735576272010803, "rewards/margins": 9.291422843933105, "rewards/rejected": -9.20406723022461, "step": 266, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.536216216216216, "grad_norm": 8.757622718811035, "learning_rate": 0.00010350410189520723, "logits/chosen": -0.48632851243019104, "logits/rejected": -0.8631247282028198, "logps/chosen": -2.381420850753784, "logps/rejected": -115.440673828125, "loss": 0.17880821228027344, "memory(GiB)": 41.24, "nll_loss": 0.1437128782272339, "rewards/accuracies": 1.0, "rewards/chosen": 0.3020068407058716, "rewards/margins": 9.818366050720215, "rewards/rejected": -9.516358375549316, "step": 267, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.541981981981982, "grad_norm": 1.859763264656067, "learning_rate": 0.00010286718651505275, "logits/chosen": -0.6271436214447021, "logits/rejected": -0.9017850756645203, "logps/chosen": -3.4276139736175537, "logps/rejected": -94.77530670166016, "loss": 0.23817601799964905, "memory(GiB)": 41.24, "nll_loss": 0.23029769957065582, "rewards/accuracies": 1.0, "rewards/chosen": 0.2481326013803482, "rewards/margins": 8.214079856872559, "rewards/rejected": -7.965947151184082, "step": 268, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.5477477477477477, "grad_norm": 3.0863282680511475, "learning_rate": 0.00010223015470610871, "logits/chosen": -0.5537242889404297, "logits/rejected": -0.8814469575881958, "logps/chosen": -4.503087520599365, "logps/rejected": -90.9027328491211, "loss": 0.3578626811504364, "memory(GiB)": 41.24, "nll_loss": 0.3030712604522705, "rewards/accuracies": 0.96875, "rewards/chosen": 0.2642664313316345, "rewards/margins": 7.56298828125, "rewards/rejected": -7.298722267150879, "step": 269, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.5535135135135136, "grad_norm": 1.3857908248901367, "learning_rate": 0.00010159303233653604, "logits/chosen": -0.570176899433136, "logits/rejected": -0.8510745763778687, "logps/chosen": -2.5669748783111572, "logps/rejected": -91.87413024902344, "loss": 0.24940097332000732, "memory(GiB)": 41.24, "nll_loss": 0.2209518700838089, "rewards/accuracies": 1.0, "rewards/chosen": 0.4336439371109009, "rewards/margins": 8.137587547302246, "rewards/rejected": -7.703943252563477, "step": 270, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.5592792792792793, "grad_norm": 3.1311755180358887, "learning_rate": 0.00010095584527817319, "logits/chosen": -0.584690272808075, "logits/rejected": -0.9461975693702698, "logps/chosen": -1.4432144165039062, "logps/rejected": -90.90803527832031, "loss": 0.17027394473552704, "memory(GiB)": 41.24, "nll_loss": 0.15755578875541687, "rewards/accuracies": 1.0, "rewards/chosen": 0.1908416450023651, "rewards/margins": 7.701169013977051, "rewards/rejected": -7.510327339172363, "step": 271, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.565045045045045, "grad_norm": 0.8555260300636292, "learning_rate": 0.00010031861940548555, "logits/chosen": -0.5870640873908997, "logits/rejected": -0.8846918940544128, "logps/chosen": -3.1194140911102295, "logps/rejected": -84.05816650390625, "loss": 0.2235853672027588, "memory(GiB)": 41.24, "nll_loss": 0.19342783093452454, "rewards/accuracies": 1.0, "rewards/chosen": 0.32051804661750793, "rewards/margins": 7.1265106201171875, "rewards/rejected": -6.805992126464844, "step": 272, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.5708108108108108, "grad_norm": 0.4469135105609894, "learning_rate": 9.968138059451446e-05, "logits/chosen": -0.561904788017273, "logits/rejected": -0.9012641310691833, "logps/chosen": -3.200127363204956, "logps/rejected": -87.4157943725586, "loss": 0.2398141324520111, "memory(GiB)": 41.24, "nll_loss": 0.21223551034927368, "rewards/accuracies": 1.0, "rewards/chosen": 0.25336456298828125, "rewards/margins": 7.232346534729004, "rewards/rejected": -6.978981971740723, "step": 273, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.5765765765765765, "grad_norm": 1.172140121459961, "learning_rate": 9.904415472182682e-05, "logits/chosen": -0.4839547276496887, "logits/rejected": -0.8654844760894775, "logps/chosen": -1.2689763307571411, "logps/rejected": -100.70805358886719, "loss": 0.13727417588233948, "memory(GiB)": 41.24, "nll_loss": 0.08727098256349564, "rewards/accuracies": 0.96875, "rewards/chosen": 0.45773637294769287, "rewards/margins": 8.578876495361328, "rewards/rejected": -8.121140480041504, "step": 274, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.5823423423423424, "grad_norm": 1.1815749406814575, "learning_rate": 9.840696766346401e-05, "logits/chosen": -0.6512535810470581, "logits/rejected": -0.8718971610069275, "logps/chosen": -2.4228830337524414, "logps/rejected": -83.79597473144531, "loss": 0.2599056363105774, "memory(GiB)": 41.24, "nll_loss": 0.17275774478912354, "rewards/accuracies": 0.96875, "rewards/chosen": 0.30599865317344666, "rewards/margins": 7.236001968383789, "rewards/rejected": -6.930003643035889, "step": 275, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.588108108108108, "grad_norm": 1.087708830833435, "learning_rate": 9.776984529389131e-05, "logits/chosen": -0.5125508904457092, "logits/rejected": -0.8501510620117188, "logps/chosen": -1.924040675163269, "logps/rejected": -95.89266967773438, "loss": 0.13055917620658875, "memory(GiB)": 41.24, "nll_loss": 0.11521827429533005, "rewards/accuracies": 1.0, "rewards/chosen": 0.2806589901447296, "rewards/margins": 7.590930938720703, "rewards/rejected": -7.310272216796875, "step": 276, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.593873873873874, "grad_norm": 0.926349401473999, "learning_rate": 9.713281348494726e-05, "logits/chosen": -0.5143563747406006, "logits/rejected": -0.9174257516860962, "logps/chosen": -0.9051769971847534, "logps/rejected": -98.711669921875, "loss": 0.11217982321977615, "memory(GiB)": 41.24, "nll_loss": 0.057560034096241, "rewards/accuracies": 0.96875, "rewards/chosen": 0.14916111528873444, "rewards/margins": 7.899416446685791, "rewards/rejected": -7.750256538391113, "step": 277, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.5996396396396397, "grad_norm": 1.0033612251281738, "learning_rate": 9.64958981047928e-05, "logits/chosen": -0.5166518688201904, "logits/rejected": -0.8793089389801025, "logps/chosen": -4.466638565063477, "logps/rejected": -103.69050598144531, "loss": 0.3073112368583679, "memory(GiB)": 41.24, "nll_loss": 0.2843497693538666, "rewards/accuracies": 1.0, "rewards/chosen": 0.32026752829551697, "rewards/margins": 8.899625778198242, "rewards/rejected": -8.579357147216797, "step": 278, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6054054054054054, "grad_norm": 1.239680528640747, "learning_rate": 9.585912501686111e-05, "logits/chosen": -0.4977273643016815, "logits/rejected": -0.8297019004821777, "logps/chosen": -2.0252184867858887, "logps/rejected": -93.17738342285156, "loss": 0.2024317979812622, "memory(GiB)": 41.24, "nll_loss": 0.1512202024459839, "rewards/accuracies": 0.96875, "rewards/chosen": 0.35597655177116394, "rewards/margins": 7.539138317108154, "rewards/rejected": -7.183161735534668, "step": 279, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.6111711711711711, "grad_norm": 1.532649040222168, "learning_rate": 9.522252007880732e-05, "logits/chosen": -0.6540271639823914, "logits/rejected": -0.9306864738464355, "logps/chosen": -1.1256556510925293, "logps/rejected": -96.81440734863281, "loss": 0.13118696212768555, "memory(GiB)": 41.24, "nll_loss": 0.06020975112915039, "rewards/accuracies": 0.96875, "rewards/chosen": 0.30623379349708557, "rewards/margins": 8.51535415649414, "rewards/rejected": -8.20911979675293, "step": 280, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6169369369369369, "grad_norm": 1.0006412267684937, "learning_rate": 9.458610914145826e-05, "logits/chosen": -0.5862869024276733, "logits/rejected": -0.9326885938644409, "logps/chosen": -3.7132813930511475, "logps/rejected": -95.93994903564453, "loss": 0.2073487639427185, "memory(GiB)": 41.24, "nll_loss": 0.18085618317127228, "rewards/accuracies": 1.0, "rewards/chosen": 0.3810235559940338, "rewards/margins": 8.14185619354248, "rewards/rejected": -7.760832786560059, "step": 281, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6227027027027026, "grad_norm": 0.9711495637893677, "learning_rate": 9.394991804776309e-05, "logits/chosen": -0.552708089351654, "logits/rejected": -0.8055617809295654, "logps/chosen": -2.3333301544189453, "logps/rejected": -84.41504669189453, "loss": 0.13116180896759033, "memory(GiB)": 41.24, "nll_loss": 0.10828734934329987, "rewards/accuracies": 1.0, "rewards/chosen": 0.40816813707351685, "rewards/margins": 7.26495361328125, "rewards/rejected": -6.856784820556641, "step": 282, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6284684684684685, "grad_norm": 0.6350001692771912, "learning_rate": 9.331397263174364e-05, "logits/chosen": -0.4492097496986389, "logits/rejected": -0.8619819283485413, "logps/chosen": -1.9441540241241455, "logps/rejected": -109.03350067138672, "loss": 0.1653510183095932, "memory(GiB)": 41.24, "nll_loss": 0.14039570093154907, "rewards/accuracies": 1.0, "rewards/chosen": 0.42938756942749023, "rewards/margins": 8.919137954711914, "rewards/rejected": -8.489750862121582, "step": 283, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.6342342342342342, "grad_norm": 0.6960185170173645, "learning_rate": 9.267829871744536e-05, "logits/chosen": -0.618625283241272, "logits/rejected": -0.9121880531311035, "logps/chosen": -1.6954020261764526, "logps/rejected": -94.96092224121094, "loss": 0.07639533281326294, "memory(GiB)": 41.24, "nll_loss": 0.05519339069724083, "rewards/accuracies": 1.0, "rewards/chosen": 0.28837311267852783, "rewards/margins": 8.253684997558594, "rewards/rejected": -7.965311527252197, "step": 284, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.6400000000000001, "grad_norm": 1.3940598964691162, "learning_rate": 9.204292211788884e-05, "logits/chosen": -0.578076183795929, "logits/rejected": -0.9528270959854126, "logps/chosen": -1.8992458581924438, "logps/rejected": -92.11747741699219, "loss": 0.16904497146606445, "memory(GiB)": 41.24, "nll_loss": 0.13233791291713715, "rewards/accuracies": 1.0, "rewards/chosen": 0.26542994379997253, "rewards/margins": 7.916376113891602, "rewards/rejected": -7.650946140289307, "step": 285, "train_speed(iter/s)": 0.010729 }, { "epoch": 1.6457657657657658, "grad_norm": 0.9293711185455322, "learning_rate": 9.140786863402147e-05, "logits/chosen": -0.6649171113967896, "logits/rejected": -0.9644867181777954, "logps/chosen": -2.1775617599487305, "logps/rejected": -78.7835693359375, "loss": 0.19159023463726044, "memory(GiB)": 41.24, "nll_loss": 0.1725030243396759, "rewards/accuracies": 1.0, "rewards/chosen": 0.2781451642513275, "rewards/margins": 6.788741111755371, "rewards/rejected": -6.51059627532959, "step": 286, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6515315315315315, "grad_norm": 1.1537113189697266, "learning_rate": 9.077316405366981e-05, "logits/chosen": -0.6535583138465881, "logits/rejected": -0.9935054183006287, "logps/chosen": -3.1851658821105957, "logps/rejected": -92.34557342529297, "loss": 0.24425984919071198, "memory(GiB)": 41.24, "nll_loss": 0.23288863897323608, "rewards/accuracies": 1.0, "rewards/chosen": 0.31673336029052734, "rewards/margins": 8.090534210205078, "rewards/rejected": -7.773800849914551, "step": 287, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6572972972972972, "grad_norm": 2.202179193496704, "learning_rate": 9.01388341504923e-05, "logits/chosen": -0.5745314955711365, "logits/rejected": -0.9523424506187439, "logps/chosen": -4.3446502685546875, "logps/rejected": -119.23814392089844, "loss": 0.2483672946691513, "memory(GiB)": 41.24, "nll_loss": 0.20222075283527374, "rewards/accuracies": 1.0, "rewards/chosen": 0.33365774154663086, "rewards/margins": 10.17822265625, "rewards/rejected": -9.844566345214844, "step": 288, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.663063063063063, "grad_norm": 0.6017576456069946, "learning_rate": 8.950490468293279e-05, "logits/chosen": -0.6120154857635498, "logits/rejected": -0.9212927222251892, "logps/chosen": -2.7989425659179688, "logps/rejected": -86.53015899658203, "loss": 0.1996924877166748, "memory(GiB)": 41.24, "nll_loss": 0.17490829527378082, "rewards/accuracies": 1.0, "rewards/chosen": 0.286940336227417, "rewards/margins": 7.214242458343506, "rewards/rejected": -6.927302837371826, "step": 289, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6688288288288289, "grad_norm": 0.8434000611305237, "learning_rate": 8.887140139317454e-05, "logits/chosen": -0.6056364178657532, "logits/rejected": -0.9164049029350281, "logps/chosen": -4.816060543060303, "logps/rejected": -95.74642944335938, "loss": 0.2582835555076599, "memory(GiB)": 41.24, "nll_loss": 0.2520279884338379, "rewards/accuracies": 1.0, "rewards/chosen": 0.7545455694198608, "rewards/margins": 8.554335594177246, "rewards/rejected": -7.799790382385254, "step": 290, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6745945945945946, "grad_norm": 4.302709102630615, "learning_rate": 8.823835000609482e-05, "logits/chosen": -0.5834745168685913, "logits/rejected": -1.0115468502044678, "logps/chosen": -2.5484602451324463, "logps/rejected": -108.22164916992188, "loss": 0.3237055838108063, "memory(GiB)": 41.24, "nll_loss": 0.2526852786540985, "rewards/accuracies": 0.96875, "rewards/chosen": 0.12026344239711761, "rewards/margins": 9.108240127563477, "rewards/rejected": -8.98797607421875, "step": 291, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6803603603603605, "grad_norm": 1.4632378816604614, "learning_rate": 8.76057762282203e-05, "logits/chosen": -0.5660637617111206, "logits/rejected": -1.061202049255371, "logps/chosen": -2.468435764312744, "logps/rejected": -112.27369689941406, "loss": 0.24110177159309387, "memory(GiB)": 41.24, "nll_loss": 0.19869710505008698, "rewards/accuracies": 1.0, "rewards/chosen": 0.07396674156188965, "rewards/margins": 9.049920082092285, "rewards/rejected": -8.975954055786133, "step": 292, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.6861261261261262, "grad_norm": 1.314245343208313, "learning_rate": 8.697370574668335e-05, "logits/chosen": -0.6602072715759277, "logits/rejected": -0.9728937149047852, "logps/chosen": -2.3553061485290527, "logps/rejected": -101.07364654541016, "loss": 0.20281532406806946, "memory(GiB)": 41.24, "nll_loss": 0.17743095755577087, "rewards/accuracies": 1.0, "rewards/chosen": 0.5697655081748962, "rewards/margins": 8.947297096252441, "rewards/rejected": -8.377532005310059, "step": 293, "train_speed(iter/s)": 0.01073 }, { "epoch": 1.691891891891892, "grad_norm": 1.3260091543197632, "learning_rate": 8.634216422817867e-05, "logits/chosen": -0.7734063267707825, "logits/rejected": -0.987154483795166, "logps/chosen": -4.309966564178467, "logps/rejected": -78.10920715332031, "loss": 0.3564646542072296, "memory(GiB)": 41.24, "nll_loss": 0.2989146113395691, "rewards/accuracies": 1.0, "rewards/chosen": 0.2878839373588562, "rewards/margins": 6.840456008911133, "rewards/rejected": -6.552572727203369, "step": 294, "train_speed(iter/s)": 0.010731 }, { "epoch": 1.6976576576576576, "grad_norm": 1.6897776126861572, "learning_rate": 8.57111773179213e-05, "logits/chosen": -0.6336952447891235, "logits/rejected": -1.0445548295974731, "logps/chosen": -1.379799723625183, "logps/rejected": -93.2787857055664, "loss": 0.14356985688209534, "memory(GiB)": 41.24, "nll_loss": 0.09856417775154114, "rewards/accuracies": 1.0, "rewards/chosen": 0.23449544608592987, "rewards/margins": 7.955099582672119, "rewards/rejected": -7.720603942871094, "step": 295, "train_speed(iter/s)": 0.010731 }, { "epoch": 1.7034234234234233, "grad_norm": 0.9327660799026489, "learning_rate": 8.508077063860506e-05, "logits/chosen": -0.5344192981719971, "logits/rejected": -1.0205243825912476, "logps/chosen": -0.8863539695739746, "logps/rejected": -122.19490051269531, "loss": 0.20819178223609924, "memory(GiB)": 41.24, "nll_loss": 0.1362844705581665, "rewards/accuracies": 0.9375, "rewards/chosen": 0.10618732124567032, "rewards/margins": 9.871743202209473, "rewards/rejected": -9.765556335449219, "step": 296, "train_speed(iter/s)": 0.010731 }, { "epoch": 1.709189189189189, "grad_norm": 7.680380821228027, "learning_rate": 8.44509697893621e-05, "logits/chosen": -0.6720832586288452, "logits/rejected": -0.9245396852493286, "logps/chosen": -4.568170070648193, "logps/rejected": -91.47016906738281, "loss": 0.3026784062385559, "memory(GiB)": 41.24, "nll_loss": 0.2759172320365906, "rewards/accuracies": 1.0, "rewards/chosen": 0.28561854362487793, "rewards/margins": 7.839561939239502, "rewards/rejected": -7.553943634033203, "step": 297, "train_speed(iter/s)": 0.010731 }, { "epoch": 1.714954954954955, "grad_norm": 1.1304014921188354, "learning_rate": 8.382180034472353e-05, "logits/chosen": -0.5577611327171326, "logits/rejected": -0.9694806337356567, "logps/chosen": -2.482516288757324, "logps/rejected": -124.2740478515625, "loss": 0.17773966491222382, "memory(GiB)": 41.24, "nll_loss": 0.16795828938484192, "rewards/accuracies": 1.0, "rewards/chosen": 0.18939006328582764, "rewards/margins": 10.547513961791992, "rewards/rejected": -10.358122825622559, "step": 298, "train_speed(iter/s)": 0.010731 }, { "epoch": 1.7207207207207207, "grad_norm": 3.0718917846679688, "learning_rate": 8.319328785358078e-05, "logits/chosen": -0.6541886329650879, "logits/rejected": -0.9405132532119751, "logps/chosen": -4.128439903259277, "logps/rejected": -86.01166534423828, "loss": 0.2915968596935272, "memory(GiB)": 41.24, "nll_loss": 0.28397953510284424, "rewards/accuracies": 1.0, "rewards/chosen": 0.6267665028572083, "rewards/margins": 7.876523971557617, "rewards/rejected": -7.249757289886475, "step": 299, "train_speed(iter/s)": 0.010731 }, { "epoch": 1.7264864864864866, "grad_norm": 1.0582029819488525, "learning_rate": 8.256545783814802e-05, "logits/chosen": -0.6806445717811584, "logits/rejected": -0.9849521517753601, "logps/chosen": -1.6571637392044067, "logps/rejected": -89.55918884277344, "loss": 0.15995512902736664, "memory(GiB)": 41.24, "nll_loss": 0.12567465007305145, "rewards/accuracies": 1.0, "rewards/chosen": 0.3345286250114441, "rewards/margins": 7.534932613372803, "rewards/rejected": -7.200402736663818, "step": 300, "train_speed(iter/s)": 0.010731 }, { "epoch": 1.7264864864864866, "eval_logits/chosen": -0.6343019604682922, "eval_logits/rejected": -0.9546191096305847, "eval_logps/chosen": -4.193188190460205, "eval_logps/rejected": -85.89741516113281, "eval_loss": 0.4250725209712982, "eval_nll_loss": 0.36724570393562317, "eval_rewards/accuracies": 0.9642857313156128, "eval_rewards/chosen": 0.2654857933521271, "eval_rewards/margins": 7.137094020843506, "eval_rewards/rejected": -6.871608734130859, "eval_runtime": 64.4253, "eval_samples_per_second": 0.869, "eval_steps_per_second": 0.435, "step": 300 } ], "logging_steps": 1, "max_steps": 519, "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": 1.6381078727661978e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }