{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8648648648648649,
  "eval_steps": 300,
  "global_step": 150,
  "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
    }
  ],
  "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": 8.203837372786278e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}