{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7636190086588941,
"eval_steps": 500,
"global_step": 700,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 9.782608695652175e-07,
"logits/chosen": -1.8868483304977417,
"logits/rejected": -2.3036646842956543,
"logps/chosen": -466.7117004394531,
"logps/rejected": -99.3152084350586,
"loss": 0.6931,
"rewards/accuracies": 0.0,
"rewards/chosen": 0.0,
"rewards/margins": 0.0,
"rewards/rejected": 0.0,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.956521739130435e-06,
"logits/chosen": -2.2296698093414307,
"logits/rejected": -2.469517469406128,
"logps/chosen": -335.50140380859375,
"logps/rejected": -97.97496032714844,
"loss": 0.6931,
"rewards/accuracies": 0.0,
"rewards/chosen": 0.0,
"rewards/margins": 0.0,
"rewards/rejected": 0.0,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.9347826086956523e-06,
"logits/chosen": -2.125047206878662,
"logits/rejected": -2.445204019546509,
"logps/chosen": -484.7939758300781,
"logps/rejected": -125.93072509765625,
"loss": 1.7268,
"rewards/accuracies": 0.4375,
"rewards/chosen": -1.0339633226394653,
"rewards/margins": -0.9356753826141357,
"rewards/rejected": -0.09828801453113556,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 3.91304347826087e-06,
"logits/chosen": -1.7763867378234863,
"logits/rejected": -2.1961894035339355,
"logps/chosen": -386.8011779785156,
"logps/rejected": -106.04309844970703,
"loss": 2.3806,
"rewards/accuracies": 0.5625,
"rewards/chosen": -0.9238373041152954,
"rewards/margins": -1.2902063131332397,
"rewards/rejected": 0.36636874079704285,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 4.891304347826087e-06,
"logits/chosen": -1.7257812023162842,
"logits/rejected": -2.353095769882202,
"logps/chosen": -524.7261962890625,
"logps/rejected": -70.26946258544922,
"loss": 0.7488,
"rewards/accuracies": 0.625,
"rewards/chosen": 2.197690010070801,
"rewards/margins": 2.0008764266967773,
"rewards/rejected": 0.19681359827518463,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 5.869565217391305e-06,
"logits/chosen": -2.1483359336853027,
"logits/rejected": -2.4817819595336914,
"logps/chosen": -283.6588134765625,
"logps/rejected": -58.25455093383789,
"loss": 0.8712,
"rewards/accuracies": 0.5625,
"rewards/chosen": 0.4915351867675781,
"rewards/margins": 0.2005542814731598,
"rewards/rejected": 0.2909809350967407,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 6.847826086956523e-06,
"logits/chosen": -2.1019060611724854,
"logits/rejected": -2.300177812576294,
"logps/chosen": -297.35235595703125,
"logps/rejected": -175.5060272216797,
"loss": 1.1392,
"rewards/accuracies": 0.5625,
"rewards/chosen": 0.6018204689025879,
"rewards/margins": -0.036775827407836914,
"rewards/rejected": 0.6385962963104248,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 7.82608695652174e-06,
"logits/chosen": -2.0169122219085693,
"logits/rejected": -2.201702117919922,
"logps/chosen": -342.04852294921875,
"logps/rejected": -117.9761962890625,
"loss": 1.1799,
"rewards/accuracies": 0.5625,
"rewards/chosen": 1.111680507659912,
"rewards/margins": 0.17297500371932983,
"rewards/rejected": 0.9387054443359375,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 8.804347826086957e-06,
"logits/chosen": -1.6254596710205078,
"logits/rejected": -2.0724740028381348,
"logps/chosen": -480.1983642578125,
"logps/rejected": -108.05937194824219,
"loss": 0.5203,
"rewards/accuracies": 0.8125,
"rewards/chosen": 2.161550283432007,
"rewards/margins": 1.3515225648880005,
"rewards/rejected": 0.8100277185440063,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 9.782608695652175e-06,
"logits/chosen": -1.4482485055923462,
"logits/rejected": -2.1116294860839844,
"logps/chosen": -451.5759582519531,
"logps/rejected": -67.73944854736328,
"loss": 0.355,
"rewards/accuracies": 0.8125,
"rewards/chosen": 6.18800163269043,
"rewards/margins": 5.184471130371094,
"rewards/rejected": 1.0035302639007568,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1.0760869565217392e-05,
"logits/chosen": -1.2660062313079834,
"logits/rejected": -1.8649226427078247,
"logps/chosen": -265.8935546875,
"logps/rejected": -57.866336822509766,
"loss": 0.3178,
"rewards/accuracies": 0.8125,
"rewards/chosen": 5.78374719619751,
"rewards/margins": 4.856299877166748,
"rewards/rejected": 0.9274475574493408,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 1.173913043478261e-05,
"logits/chosen": -1.1804625988006592,
"logits/rejected": -1.7009960412979126,
"logps/chosen": -247.2069854736328,
"logps/rejected": -79.96739196777344,
"loss": 0.6617,
"rewards/accuracies": 0.75,
"rewards/chosen": 6.5535197257995605,
"rewards/margins": 4.647799015045166,
"rewards/rejected": 1.9057204723358154,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 1.2717391304347827e-05,
"logits/chosen": -0.9693112373352051,
"logits/rejected": -1.6497248411178589,
"logps/chosen": -372.8963623046875,
"logps/rejected": -70.47633361816406,
"loss": 0.2498,
"rewards/accuracies": 0.8125,
"rewards/chosen": 9.02272891998291,
"rewards/margins": 7.325143814086914,
"rewards/rejected": 1.6975862979888916,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 1.3695652173913046e-05,
"logits/chosen": -0.7723280787467957,
"logits/rejected": -1.4176554679870605,
"logps/chosen": -318.0392150878906,
"logps/rejected": -79.94412994384766,
"loss": 0.6401,
"rewards/accuracies": 0.6875,
"rewards/chosen": 6.698611259460449,
"rewards/margins": 4.517416477203369,
"rewards/rejected": 2.18119478225708,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 1.4673913043478261e-05,
"logits/chosen": -0.8084051609039307,
"logits/rejected": -1.4428132772445679,
"logps/chosen": -363.15869140625,
"logps/rejected": -70.70079803466797,
"loss": 0.4963,
"rewards/accuracies": 0.75,
"rewards/chosen": 7.02784538269043,
"rewards/margins": 5.400259971618652,
"rewards/rejected": 1.6275854110717773,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.565217391304348e-05,
"logits/chosen": -0.8056433200836182,
"logits/rejected": -1.4629294872283936,
"logps/chosen": -328.90435791015625,
"logps/rejected": -77.36820983886719,
"loss": 0.544,
"rewards/accuracies": 0.75,
"rewards/chosen": 9.417024612426758,
"rewards/margins": 7.023505687713623,
"rewards/rejected": 2.393519163131714,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 1.6630434782608694e-05,
"logits/chosen": -1.0918309688568115,
"logits/rejected": -1.6613047122955322,
"logps/chosen": -277.37982177734375,
"logps/rejected": -56.75635528564453,
"loss": 0.8958,
"rewards/accuracies": 0.8125,
"rewards/chosen": 6.844330310821533,
"rewards/margins": 4.82295560836792,
"rewards/rejected": 2.0213749408721924,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 1.7608695652173915e-05,
"logits/chosen": -0.9810999631881714,
"logits/rejected": -1.975247859954834,
"logps/chosen": -465.6856689453125,
"logps/rejected": -56.440269470214844,
"loss": 0.2275,
"rewards/accuracies": 0.875,
"rewards/chosen": 7.767542362213135,
"rewards/margins": 6.572459697723389,
"rewards/rejected": 1.1950825452804565,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 1.8586956521739132e-05,
"logits/chosen": -1.2428462505340576,
"logits/rejected": -1.8064367771148682,
"logps/chosen": -322.7100830078125,
"logps/rejected": -108.71321105957031,
"loss": 0.3006,
"rewards/accuracies": 0.875,
"rewards/chosen": 6.459216594696045,
"rewards/margins": 3.9207711219787598,
"rewards/rejected": 2.5384464263916016,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 1.956521739130435e-05,
"logits/chosen": -1.7773098945617676,
"logits/rejected": -2.178387403488159,
"logps/chosen": -357.8656921386719,
"logps/rejected": -112.65576934814453,
"loss": 0.3837,
"rewards/accuracies": 0.9375,
"rewards/chosen": 4.684590816497803,
"rewards/margins": 4.16137170791626,
"rewards/rejected": 0.5232191681861877,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 2.0543478260869567e-05,
"logits/chosen": -1.6802027225494385,
"logits/rejected": -1.943274974822998,
"logps/chosen": -327.85693359375,
"logps/rejected": -87.53279113769531,
"loss": 0.4428,
"rewards/accuracies": 0.9375,
"rewards/chosen": 2.681103229522705,
"rewards/margins": 2.3518502712249756,
"rewards/rejected": 0.32925307750701904,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 2.1521739130434784e-05,
"logits/chosen": -1.5789223909378052,
"logits/rejected": -2.4593281745910645,
"logps/chosen": -590.5732421875,
"logps/rejected": -86.78819274902344,
"loss": 0.252,
"rewards/accuracies": 0.875,
"rewards/chosen": 3.6503655910491943,
"rewards/margins": 3.621542453765869,
"rewards/rejected": 0.028822531923651695,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 2.25e-05,
"logits/chosen": -1.8142305612564087,
"logits/rejected": -2.3507237434387207,
"logps/chosen": -296.42266845703125,
"logps/rejected": -60.37131118774414,
"loss": 0.5602,
"rewards/accuracies": 0.75,
"rewards/chosen": 2.170171022415161,
"rewards/margins": 2.5353941917419434,
"rewards/rejected": -0.36522313952445984,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 2.347826086956522e-05,
"logits/chosen": -1.7050156593322754,
"logits/rejected": -2.158708333969116,
"logps/chosen": -523.41748046875,
"logps/rejected": -81.6954345703125,
"loss": 0.7359,
"rewards/accuracies": 0.9375,
"rewards/chosen": 2.3799068927764893,
"rewards/margins": 2.963341236114502,
"rewards/rejected": -0.583433985710144,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 2.4456521739130436e-05,
"logits/chosen": -1.704190731048584,
"logits/rejected": -2.215942859649658,
"logps/chosen": -457.6519775390625,
"logps/rejected": -91.778076171875,
"loss": 0.0865,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.57167911529541,
"rewards/margins": 4.6597795486450195,
"rewards/rejected": -0.08810039609670639,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 2.5434782608695653e-05,
"logits/chosen": -1.4195502996444702,
"logits/rejected": -2.109910488128662,
"logps/chosen": -445.05908203125,
"logps/rejected": -80.95398712158203,
"loss": 0.1265,
"rewards/accuracies": 0.9375,
"rewards/chosen": 5.362960338592529,
"rewards/margins": 5.412578582763672,
"rewards/rejected": -0.049618080258369446,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 2.6413043478260874e-05,
"logits/chosen": -1.0274971723556519,
"logits/rejected": -1.7681918144226074,
"logps/chosen": -393.85870361328125,
"logps/rejected": -77.79011535644531,
"loss": 0.1702,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.572484016418457,
"rewards/margins": 4.946743488311768,
"rewards/rejected": -0.374259889125824,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 2.739130434782609e-05,
"logits/chosen": -0.7365273237228394,
"logits/rejected": -1.9988534450531006,
"logps/chosen": -569.8936767578125,
"logps/rejected": -79.71562194824219,
"loss": 0.0465,
"rewards/accuracies": 1.0,
"rewards/chosen": 12.751686096191406,
"rewards/margins": 12.474647521972656,
"rewards/rejected": 0.2770393192768097,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 2.836956521739131e-05,
"logits/chosen": -0.6424872279167175,
"logits/rejected": -1.6069284677505493,
"logps/chosen": -368.68292236328125,
"logps/rejected": -103.9141845703125,
"loss": 0.0351,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.144453048706055,
"rewards/margins": 10.381340980529785,
"rewards/rejected": -0.23688830435276031,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 2.9347826086956523e-05,
"logits/chosen": -0.6061868071556091,
"logits/rejected": -1.4256294965744019,
"logps/chosen": -360.4029846191406,
"logps/rejected": -130.27224731445312,
"loss": 0.0414,
"rewards/accuracies": 1.0,
"rewards/chosen": 12.649539947509766,
"rewards/margins": 12.36604118347168,
"rewards/rejected": 0.2834990620613098,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 3.032608695652174e-05,
"logits/chosen": -1.0075111389160156,
"logits/rejected": -1.3918204307556152,
"logps/chosen": -227.05450439453125,
"logps/rejected": -172.67947387695312,
"loss": 1.1145,
"rewards/accuracies": 0.875,
"rewards/chosen": 4.628115653991699,
"rewards/margins": 3.9521055221557617,
"rewards/rejected": 0.6760098934173584,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 3.130434782608696e-05,
"logits/chosen": -0.9060839414596558,
"logits/rejected": -2.0123891830444336,
"logps/chosen": -403.06781005859375,
"logps/rejected": -75.35684967041016,
"loss": 0.0319,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.352475643157959,
"rewards/margins": 8.778717041015625,
"rewards/rejected": -1.4262410402297974,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 3.228260869565217e-05,
"logits/chosen": -1.2984271049499512,
"logits/rejected": -1.9507720470428467,
"logps/chosen": -306.7958984375,
"logps/rejected": -107.01404571533203,
"loss": 0.0795,
"rewards/accuracies": 0.9375,
"rewards/chosen": 5.223363399505615,
"rewards/margins": 7.012631416320801,
"rewards/rejected": -1.7892680168151855,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 3.326086956521739e-05,
"logits/chosen": -1.1749062538146973,
"logits/rejected": -2.004805564880371,
"logps/chosen": -437.9205322265625,
"logps/rejected": -135.21376037597656,
"loss": 0.0021,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.3555908203125,
"rewards/margins": 12.285521507263184,
"rewards/rejected": -2.9299299716949463,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 3.423913043478261e-05,
"logits/chosen": -0.9383536577224731,
"logits/rejected": -2.0366413593292236,
"logps/chosen": -457.8018493652344,
"logps/rejected": -87.7723617553711,
"loss": 0.041,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.836911678314209,
"rewards/margins": 9.43667984008789,
"rewards/rejected": -2.599769115447998,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 3.521739130434783e-05,
"logits/chosen": -1.120687484741211,
"logits/rejected": -1.9933563470840454,
"logps/chosen": -439.6186828613281,
"logps/rejected": -94.24763488769531,
"loss": 0.1906,
"rewards/accuracies": 0.9375,
"rewards/chosen": 6.565365314483643,
"rewards/margins": 9.163484573364258,
"rewards/rejected": -2.5981192588806152,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 3.619565217391305e-05,
"logits/chosen": -1.338189959526062,
"logits/rejected": -1.9118335247039795,
"logps/chosen": -286.96728515625,
"logps/rejected": -127.22909545898438,
"loss": 0.0279,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.9341468811035156,
"rewards/margins": 6.362301349639893,
"rewards/rejected": -3.4281537532806396,
"step": 37
},
{
"epoch": 0.04,
"learning_rate": 3.7173913043478264e-05,
"logits/chosen": -1.2371840476989746,
"logits/rejected": -1.7362310886383057,
"logps/chosen": -319.52911376953125,
"logps/rejected": -151.65084838867188,
"loss": 0.0939,
"rewards/accuracies": 0.9375,
"rewards/chosen": 6.216956615447998,
"rewards/margins": 9.073128700256348,
"rewards/rejected": -2.856172561645508,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 3.815217391304348e-05,
"logits/chosen": -0.8356418609619141,
"logits/rejected": -1.7252635955810547,
"logps/chosen": -391.63275146484375,
"logps/rejected": -154.64361572265625,
"loss": 0.2483,
"rewards/accuracies": 0.9375,
"rewards/chosen": 8.802470207214355,
"rewards/margins": 11.676048278808594,
"rewards/rejected": -2.873577356338501,
"step": 39
},
{
"epoch": 0.04,
"learning_rate": 3.91304347826087e-05,
"logits/chosen": -0.9311200380325317,
"logits/rejected": -1.8107151985168457,
"logps/chosen": -374.2525939941406,
"logps/rejected": -131.86715698242188,
"loss": 0.0058,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.586356163024902,
"rewards/margins": 11.15583324432373,
"rewards/rejected": -2.569479465484619,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.0108695652173916e-05,
"logits/chosen": -0.6861732006072998,
"logits/rejected": -1.6295411586761475,
"logps/chosen": -311.7944641113281,
"logps/rejected": -132.4564666748047,
"loss": 0.0124,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.333560943603516,
"rewards/margins": 10.023443222045898,
"rewards/rejected": -4.689882755279541,
"step": 41
},
{
"epoch": 0.05,
"learning_rate": 4.1086956521739134e-05,
"logits/chosen": -1.1133558750152588,
"logits/rejected": -2.0819039344787598,
"logps/chosen": -282.22332763671875,
"logps/rejected": -98.7315673828125,
"loss": 0.0156,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.930261611938477,
"rewards/margins": 8.344033241271973,
"rewards/rejected": -3.413771629333496,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 4.206521739130435e-05,
"logits/chosen": -1.0311042070388794,
"logits/rejected": -2.0758776664733887,
"logps/chosen": -369.7279052734375,
"logps/rejected": -146.08364868164062,
"loss": 0.0127,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.7552289962768555,
"rewards/margins": 13.249262809753418,
"rewards/rejected": -5.494032859802246,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 4.304347826086957e-05,
"logits/chosen": -1.0191632509231567,
"logits/rejected": -1.995982050895691,
"logps/chosen": -367.692626953125,
"logps/rejected": -152.65135192871094,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.9517822265625,
"rewards/margins": 13.869260787963867,
"rewards/rejected": -5.917478084564209,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 4.4021739130434786e-05,
"logits/chosen": -1.3430471420288086,
"logits/rejected": -2.0910849571228027,
"logps/chosen": -334.8968811035156,
"logps/rejected": -168.4519500732422,
"loss": 0.0057,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.113959312438965,
"rewards/margins": 12.524876594543457,
"rewards/rejected": -7.41091775894165,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 4.5e-05,
"logits/chosen": -0.8516018986701965,
"logits/rejected": -1.9934579133987427,
"logps/chosen": -386.7164001464844,
"logps/rejected": -152.8460235595703,
"loss": 0.0253,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.0803022384643555,
"rewards/margins": 13.202106475830078,
"rewards/rejected": -6.121803283691406,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 4.494827586206897e-05,
"logits/chosen": -0.9460695385932922,
"logits/rejected": -1.9993284940719604,
"logps/chosen": -355.2873229980469,
"logps/rejected": -188.5989532470703,
"loss": 0.1008,
"rewards/accuracies": 0.9375,
"rewards/chosen": 6.138028144836426,
"rewards/margins": 13.93982982635498,
"rewards/rejected": -7.801800727844238,
"step": 47
},
{
"epoch": 0.05,
"learning_rate": 4.489655172413793e-05,
"logits/chosen": -1.212510108947754,
"logits/rejected": -2.0202791690826416,
"logps/chosen": -293.0318908691406,
"logps/rejected": -194.92649841308594,
"loss": 0.0058,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.742659091949463,
"rewards/margins": 17.209505081176758,
"rewards/rejected": -10.466848373413086,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 4.48448275862069e-05,
"logits/chosen": -1.388157606124878,
"logits/rejected": -2.1885251998901367,
"logps/chosen": -330.6868591308594,
"logps/rejected": -214.35423278808594,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.653369903564453,
"rewards/margins": 18.257244110107422,
"rewards/rejected": -12.603873252868652,
"step": 49
},
{
"epoch": 0.05,
"learning_rate": 4.479310344827587e-05,
"logits/chosen": -1.020527958869934,
"logits/rejected": -1.9433815479278564,
"logps/chosen": -347.48394775390625,
"logps/rejected": -191.15147399902344,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.30579137802124,
"rewards/margins": 18.734811782836914,
"rewards/rejected": -11.429021835327148,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 4.474137931034483e-05,
"logits/chosen": -1.2260757684707642,
"logits/rejected": -2.0841352939605713,
"logps/chosen": -243.5459747314453,
"logps/rejected": -188.00442504882812,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.675260543823242,
"rewards/margins": 14.774760246276855,
"rewards/rejected": -11.099499702453613,
"step": 51
},
{
"epoch": 0.06,
"learning_rate": 4.46896551724138e-05,
"logits/chosen": -1.0378711223602295,
"logits/rejected": -2.0174639225006104,
"logps/chosen": -375.9520263671875,
"logps/rejected": -182.97463989257812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.18237829208374,
"rewards/margins": 19.010208129882812,
"rewards/rejected": -11.82783317565918,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 4.4637931034482765e-05,
"logits/chosen": -1.1728301048278809,
"logits/rejected": -1.9667140245437622,
"logps/chosen": -309.5382995605469,
"logps/rejected": -241.13743591308594,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.681103706359863,
"rewards/margins": 21.542236328125,
"rewards/rejected": -14.861133575439453,
"step": 53
},
{
"epoch": 0.06,
"learning_rate": 4.4586206896551726e-05,
"logits/chosen": -1.1491725444793701,
"logits/rejected": -1.760243535041809,
"logps/chosen": -250.09036254882812,
"logps/rejected": -226.221435546875,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.3173880577087402,
"rewards/margins": 16.417604446411133,
"rewards/rejected": -14.100215911865234,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 4.4534482758620694e-05,
"logits/chosen": -1.2637637853622437,
"logits/rejected": -1.8996949195861816,
"logps/chosen": -401.9977722167969,
"logps/rejected": -303.9198303222656,
"loss": 0.0011,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.595758438110352,
"rewards/margins": 26.598325729370117,
"rewards/rejected": -18.002567291259766,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 4.4482758620689656e-05,
"logits/chosen": -0.9855178594589233,
"logits/rejected": -2.0190346240997314,
"logps/chosen": -394.40625,
"logps/rejected": -253.97720336914062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.395060062408447,
"rewards/margins": 23.680639266967773,
"rewards/rejected": -17.28557777404785,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 4.4431034482758624e-05,
"logits/chosen": -1.049959421157837,
"logits/rejected": -1.6531357765197754,
"logps/chosen": -205.54058837890625,
"logps/rejected": -250.66958618164062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.874389171600342,
"rewards/margins": 20.083953857421875,
"rewards/rejected": -15.209564208984375,
"step": 57
},
{
"epoch": 0.06,
"learning_rate": 4.4379310344827585e-05,
"logits/chosen": -0.8982111811637878,
"logits/rejected": -1.6001371145248413,
"logps/chosen": -241.91790771484375,
"logps/rejected": -252.10299682617188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.044814109802246,
"rewards/margins": 21.77715301513672,
"rewards/rejected": -15.732340812683105,
"step": 58
},
{
"epoch": 0.06,
"learning_rate": 4.432758620689655e-05,
"logits/chosen": -0.753044068813324,
"logits/rejected": -1.6325318813323975,
"logps/chosen": -315.30230712890625,
"logps/rejected": -245.91976928710938,
"loss": 0.0078,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.801758289337158,
"rewards/margins": 20.689924240112305,
"rewards/rejected": -14.888164520263672,
"step": 59
},
{
"epoch": 0.07,
"learning_rate": 4.427586206896552e-05,
"logits/chosen": -0.5443448424339294,
"logits/rejected": -1.7224345207214355,
"logps/chosen": -388.339599609375,
"logps/rejected": -211.5500946044922,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 11.5880708694458,
"rewards/margins": 24.889877319335938,
"rewards/rejected": -13.301810264587402,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 4.422413793103448e-05,
"logits/chosen": -0.6921290755271912,
"logits/rejected": -1.6139135360717773,
"logps/chosen": -242.47312927246094,
"logps/rejected": -214.73622131347656,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 11.329044342041016,
"rewards/margins": 21.45581817626953,
"rewards/rejected": -10.1267728805542,
"step": 61
},
{
"epoch": 0.07,
"learning_rate": 4.417241379310345e-05,
"logits/chosen": -0.4828271269798279,
"logits/rejected": -1.649349570274353,
"logps/chosen": -306.6004638671875,
"logps/rejected": -172.2523956298828,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/chosen": 11.373737335205078,
"rewards/margins": 20.521434783935547,
"rewards/rejected": -9.147698402404785,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 4.412068965517242e-05,
"logits/chosen": -0.4676312506198883,
"logits/rejected": -1.6393827199935913,
"logps/chosen": -357.127685546875,
"logps/rejected": -199.84524536132812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 16.730457305908203,
"rewards/margins": 26.409488677978516,
"rewards/rejected": -9.679031372070312,
"step": 63
},
{
"epoch": 0.07,
"learning_rate": 4.406896551724138e-05,
"logits/chosen": -0.7774850726127625,
"logits/rejected": -1.324657678604126,
"logps/chosen": -193.75833129882812,
"logps/rejected": -194.70233154296875,
"loss": 0.0015,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.371121406555176,
"rewards/margins": 15.129293441772461,
"rewards/rejected": -9.758172988891602,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 4.401724137931035e-05,
"logits/chosen": -0.5502160787582397,
"logits/rejected": -1.466262936592102,
"logps/chosen": -240.96836853027344,
"logps/rejected": -174.6772003173828,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.808657169342041,
"rewards/margins": 17.520769119262695,
"rewards/rejected": -9.712109565734863,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 4.3965517241379315e-05,
"logits/chosen": -0.5615445375442505,
"logits/rejected": -1.3243337869644165,
"logps/chosen": -282.65484619140625,
"logps/rejected": -211.33326721191406,
"loss": 0.4403,
"rewards/accuracies": 0.9375,
"rewards/chosen": 9.213937759399414,
"rewards/margins": 18.93706512451172,
"rewards/rejected": -9.723125457763672,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 4.3913793103448277e-05,
"logits/chosen": -0.5882927775382996,
"logits/rejected": -1.4038889408111572,
"logps/chosen": -244.26333618164062,
"logps/rejected": -192.05517578125,
"loss": 0.0007,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.999594688415527,
"rewards/margins": 16.232702255249023,
"rewards/rejected": -10.233107566833496,
"step": 67
},
{
"epoch": 0.07,
"learning_rate": 4.3862068965517245e-05,
"logits/chosen": -0.7710579633712769,
"logits/rejected": -1.5811477899551392,
"logps/chosen": -274.4286804199219,
"logps/rejected": -189.31427001953125,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.483807563781738,
"rewards/margins": 22.807409286499023,
"rewards/rejected": -12.323600769042969,
"step": 68
},
{
"epoch": 0.08,
"learning_rate": 4.381034482758621e-05,
"logits/chosen": -0.2001597136259079,
"logits/rejected": -1.5477687120437622,
"logps/chosen": -398.04296875,
"logps/rejected": -208.8218536376953,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 11.122913360595703,
"rewards/margins": 23.094343185424805,
"rewards/rejected": -11.971429824829102,
"step": 69
},
{
"epoch": 0.08,
"learning_rate": 4.3758620689655174e-05,
"logits/chosen": -0.5891858339309692,
"logits/rejected": -1.500455379486084,
"logps/chosen": -223.07235717773438,
"logps/rejected": -219.37405395507812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.498288154602051,
"rewards/margins": 19.65944480895996,
"rewards/rejected": -12.16115665435791,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 4.370689655172414e-05,
"logits/chosen": -0.5222135186195374,
"logits/rejected": -1.459835410118103,
"logps/chosen": -264.3045349121094,
"logps/rejected": -184.4599609375,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.261447429656982,
"rewards/margins": 17.37218475341797,
"rewards/rejected": -10.110737800598145,
"step": 71
},
{
"epoch": 0.08,
"learning_rate": 4.365517241379311e-05,
"logits/chosen": -0.4974746108055115,
"logits/rejected": -1.5458664894104004,
"logps/chosen": -272.7602233886719,
"logps/rejected": -181.00247192382812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.925564765930176,
"rewards/margins": 22.81020736694336,
"rewards/rejected": -11.88464069366455,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 4.360344827586207e-05,
"logits/chosen": -0.3357059359550476,
"logits/rejected": -1.4441150426864624,
"logps/chosen": -414.8647766113281,
"logps/rejected": -223.109375,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/chosen": 13.181656837463379,
"rewards/margins": 27.527368545532227,
"rewards/rejected": -14.345712661743164,
"step": 73
},
{
"epoch": 0.08,
"learning_rate": 4.355172413793104e-05,
"logits/chosen": -0.6531690359115601,
"logits/rejected": -1.4611525535583496,
"logps/chosen": -221.1251220703125,
"logps/rejected": -226.30352783203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.807477951049805,
"rewards/margins": 21.502174377441406,
"rewards/rejected": -13.694696426391602,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 4.35e-05,
"logits/chosen": -0.5135932564735413,
"logits/rejected": -1.4995931386947632,
"logps/chosen": -332.56842041015625,
"logps/rejected": -270.9891662597656,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 12.301117897033691,
"rewards/margins": 26.830467224121094,
"rewards/rejected": -14.529346466064453,
"step": 75
},
{
"epoch": 0.08,
"learning_rate": 4.344827586206897e-05,
"logits/chosen": -0.3770020604133606,
"logits/rejected": -1.44219970703125,
"logps/chosen": -317.96240234375,
"logps/rejected": -250.3682098388672,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.8860931396484375,
"rewards/margins": 23.53211784362793,
"rewards/rejected": -15.646024703979492,
"step": 76
},
{
"epoch": 0.08,
"learning_rate": 4.339655172413793e-05,
"logits/chosen": -0.49628371000289917,
"logits/rejected": -1.4045476913452148,
"logps/chosen": -367.6162414550781,
"logps/rejected": -265.2467346191406,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.148900985717773,
"rewards/margins": 24.313669204711914,
"rewards/rejected": -14.164766311645508,
"step": 77
},
{
"epoch": 0.09,
"learning_rate": 4.33448275862069e-05,
"logits/chosen": -0.5287263989448547,
"logits/rejected": -1.3665097951889038,
"logps/chosen": -341.87664794921875,
"logps/rejected": -249.6795654296875,
"loss": 0.1517,
"rewards/accuracies": 0.9375,
"rewards/chosen": 8.620326042175293,
"rewards/margins": 19.850658416748047,
"rewards/rejected": -11.230331420898438,
"step": 78
},
{
"epoch": 0.09,
"learning_rate": 4.3293103448275865e-05,
"logits/chosen": -0.2743966281414032,
"logits/rejected": -1.4255130290985107,
"logps/chosen": -334.3340759277344,
"logps/rejected": -265.15032958984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.872364044189453,
"rewards/margins": 27.00977325439453,
"rewards/rejected": -16.13741111755371,
"step": 79
},
{
"epoch": 0.09,
"learning_rate": 4.324137931034483e-05,
"logits/chosen": -0.5563563108444214,
"logits/rejected": -1.6934064626693726,
"logps/chosen": -408.9612731933594,
"logps/rejected": -220.00091552734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.237764358520508,
"rewards/margins": 24.824390411376953,
"rewards/rejected": -14.586627960205078,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 4.3189655172413795e-05,
"logits/chosen": -0.617451548576355,
"logits/rejected": -1.640676736831665,
"logps/chosen": -363.1540222167969,
"logps/rejected": -226.42376708984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.672024726867676,
"rewards/margins": 24.347591400146484,
"rewards/rejected": -13.675565719604492,
"step": 81
},
{
"epoch": 0.09,
"learning_rate": 4.313793103448276e-05,
"logits/chosen": -0.45464372634887695,
"logits/rejected": -1.4708175659179688,
"logps/chosen": -328.35675048828125,
"logps/rejected": -223.79766845703125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.965122699737549,
"rewards/margins": 21.22077178955078,
"rewards/rejected": -14.25564956665039,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 4.3086206896551724e-05,
"logits/chosen": -0.6079340577125549,
"logits/rejected": -1.5333082675933838,
"logps/chosen": -219.4099578857422,
"logps/rejected": -230.07948303222656,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.278050899505615,
"rewards/margins": 20.45656967163086,
"rewards/rejected": -14.178520202636719,
"step": 83
},
{
"epoch": 0.09,
"learning_rate": 4.303448275862069e-05,
"logits/chosen": -0.4874611794948578,
"logits/rejected": -1.5135740041732788,
"logps/chosen": -304.00274658203125,
"logps/rejected": -263.0120849609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.557435989379883,
"rewards/margins": 24.41012954711914,
"rewards/rejected": -14.852693557739258,
"step": 84
},
{
"epoch": 0.09,
"learning_rate": 4.298275862068966e-05,
"logits/chosen": -0.4802761375904083,
"logits/rejected": -1.4294252395629883,
"logps/chosen": -293.41192626953125,
"logps/rejected": -283.2821350097656,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.370968818664551,
"rewards/margins": 24.32880401611328,
"rewards/rejected": -16.957834243774414,
"step": 85
},
{
"epoch": 0.09,
"learning_rate": 4.293103448275862e-05,
"logits/chosen": -0.3580012321472168,
"logits/rejected": -1.499201774597168,
"logps/chosen": -350.5351257324219,
"logps/rejected": -244.6523895263672,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 12.237674713134766,
"rewards/margins": 26.58084487915039,
"rewards/rejected": -14.343170166015625,
"step": 86
},
{
"epoch": 0.09,
"learning_rate": 4.287931034482759e-05,
"logits/chosen": -0.6917211413383484,
"logits/rejected": -1.4503819942474365,
"logps/chosen": -217.5175323486328,
"logps/rejected": -228.9481201171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.635045051574707,
"rewards/margins": 20.42833709716797,
"rewards/rejected": -13.793292999267578,
"step": 87
},
{
"epoch": 0.1,
"learning_rate": 4.282758620689656e-05,
"logits/chosen": -0.8255922794342041,
"logits/rejected": -1.4748644828796387,
"logps/chosen": -217.336669921875,
"logps/rejected": -206.8959197998047,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.22888708114624,
"rewards/margins": 19.673564910888672,
"rewards/rejected": -14.444679260253906,
"step": 88
},
{
"epoch": 0.1,
"learning_rate": 4.2775862068965525e-05,
"logits/chosen": -0.626908004283905,
"logits/rejected": -1.6663663387298584,
"logps/chosen": -328.56231689453125,
"logps/rejected": -235.42843627929688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.891221046447754,
"rewards/margins": 21.77893829345703,
"rewards/rejected": -14.887716293334961,
"step": 89
},
{
"epoch": 0.1,
"learning_rate": 4.2724137931034486e-05,
"logits/chosen": -0.5689429640769958,
"logits/rejected": -1.618609070777893,
"logps/chosen": -298.08770751953125,
"logps/rejected": -237.06094360351562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.328791618347168,
"rewards/margins": 24.572046279907227,
"rewards/rejected": -15.243253707885742,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 4.2672413793103454e-05,
"logits/chosen": -0.5474239587783813,
"logits/rejected": -1.6142076253890991,
"logps/chosen": -295.00494384765625,
"logps/rejected": -268.9505615234375,
"loss": 0.0287,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.715471267700195,
"rewards/margins": 23.968780517578125,
"rewards/rejected": -14.25330924987793,
"step": 91
},
{
"epoch": 0.1,
"learning_rate": 4.2620689655172416e-05,
"logits/chosen": -0.5132906436920166,
"logits/rejected": -1.6248977184295654,
"logps/chosen": -314.5284423828125,
"logps/rejected": -210.1342315673828,
"loss": 0.0595,
"rewards/accuracies": 0.9375,
"rewards/chosen": 7.707674980163574,
"rewards/margins": 20.18167495727539,
"rewards/rejected": -12.474000930786133,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 4.2568965517241384e-05,
"logits/chosen": -0.45244526863098145,
"logits/rejected": -1.7539148330688477,
"logps/chosen": -394.9619140625,
"logps/rejected": -230.32550048828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 11.32716178894043,
"rewards/margins": 26.326129913330078,
"rewards/rejected": -14.998967170715332,
"step": 93
},
{
"epoch": 0.1,
"learning_rate": 4.2517241379310345e-05,
"logits/chosen": -0.7538139224052429,
"logits/rejected": -1.5796599388122559,
"logps/chosen": -286.95281982421875,
"logps/rejected": -266.7412414550781,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.003694534301758,
"rewards/margins": 25.05299949645996,
"rewards/rejected": -17.04930305480957,
"step": 94
},
{
"epoch": 0.1,
"learning_rate": 4.246551724137931e-05,
"logits/chosen": -0.44376400113105774,
"logits/rejected": -1.5493687391281128,
"logps/chosen": -406.93951416015625,
"logps/rejected": -302.9401550292969,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.246862888336182,
"rewards/margins": 27.937149047851562,
"rewards/rejected": -20.69028663635254,
"step": 95
},
{
"epoch": 0.1,
"learning_rate": 4.2413793103448274e-05,
"logits/chosen": -0.7577255964279175,
"logits/rejected": -1.77558171749115,
"logps/chosen": -357.90838623046875,
"logps/rejected": -246.73458862304688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.267894744873047,
"rewards/margins": 24.79804229736328,
"rewards/rejected": -17.530147552490234,
"step": 96
},
{
"epoch": 0.11,
"learning_rate": 4.236206896551724e-05,
"logits/chosen": -0.8565713763237,
"logits/rejected": -1.7760589122772217,
"logps/chosen": -338.751220703125,
"logps/rejected": -304.101806640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.238365173339844,
"rewards/margins": 27.781978607177734,
"rewards/rejected": -18.54361343383789,
"step": 97
},
{
"epoch": 0.11,
"learning_rate": 4.231034482758621e-05,
"logits/chosen": -0.40401750802993774,
"logits/rejected": -1.7701493501663208,
"logps/chosen": -537.5440063476562,
"logps/rejected": -349.8548889160156,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 14.211512565612793,
"rewards/margins": 37.746315002441406,
"rewards/rejected": -23.53480339050293,
"step": 98
},
{
"epoch": 0.11,
"learning_rate": 4.225862068965517e-05,
"logits/chosen": -0.9799883365631104,
"logits/rejected": -1.8936114311218262,
"logps/chosen": -403.7567138671875,
"logps/rejected": -257.6401672363281,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.710639476776123,
"rewards/margins": 23.923961639404297,
"rewards/rejected": -19.213321685791016,
"step": 99
},
{
"epoch": 0.11,
"learning_rate": 4.220689655172414e-05,
"logits/chosen": -0.94623202085495,
"logits/rejected": -1.7190004587173462,
"logps/chosen": -360.8213806152344,
"logps/rejected": -310.1994323730469,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.991710662841797,
"rewards/margins": 26.59444808959961,
"rewards/rejected": -22.60273551940918,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 4.215517241379311e-05,
"logits/chosen": -0.6102348566055298,
"logits/rejected": -1.8472094535827637,
"logps/chosen": -460.48699951171875,
"logps/rejected": -369.1959228515625,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.696294784545898,
"rewards/margins": 32.79343795776367,
"rewards/rejected": -26.097143173217773,
"step": 101
},
{
"epoch": 0.11,
"learning_rate": 4.210344827586207e-05,
"logits/chosen": -0.9649127721786499,
"logits/rejected": -1.8413913249969482,
"logps/chosen": -455.1119079589844,
"logps/rejected": -365.0443420410156,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.14402437210083,
"rewards/margins": 32.23406219482422,
"rewards/rejected": -25.090038299560547,
"step": 102
},
{
"epoch": 0.11,
"learning_rate": 4.2051724137931036e-05,
"logits/chosen": -1.176360011100769,
"logits/rejected": -1.6914632320404053,
"logps/chosen": -283.3887023925781,
"logps/rejected": -343.1808166503906,
"loss": 0.0008,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.03441965579986572,
"rewards/margins": 24.389293670654297,
"rewards/rejected": -24.423709869384766,
"step": 103
},
{
"epoch": 0.11,
"learning_rate": 4.2000000000000004e-05,
"logits/chosen": -0.7725791335105896,
"logits/rejected": -1.943673014640808,
"logps/chosen": -484.6883544921875,
"logps/rejected": -338.5666198730469,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.784733295440674,
"rewards/margins": 31.62430763244629,
"rewards/rejected": -23.839576721191406,
"step": 104
},
{
"epoch": 0.11,
"learning_rate": 4.194827586206897e-05,
"logits/chosen": -0.6000739336013794,
"logits/rejected": -1.681613802909851,
"logps/chosen": -342.3570556640625,
"logps/rejected": -256.06829833984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.42122745513916,
"rewards/margins": 25.636981964111328,
"rewards/rejected": -18.21575355529785,
"step": 105
},
{
"epoch": 0.12,
"learning_rate": 4.1896551724137934e-05,
"logits/chosen": -0.5727726221084595,
"logits/rejected": -1.5278774499893188,
"logps/chosen": -340.2919921875,
"logps/rejected": -246.67628479003906,
"loss": 0.0183,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.279099464416504,
"rewards/margins": 23.8295841217041,
"rewards/rejected": -16.550485610961914,
"step": 106
},
{
"epoch": 0.12,
"learning_rate": 4.18448275862069e-05,
"logits/chosen": -0.588262677192688,
"logits/rejected": -1.4113011360168457,
"logps/chosen": -239.1262664794922,
"logps/rejected": -323.8817443847656,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.26235294342041,
"rewards/margins": 25.60938262939453,
"rewards/rejected": -21.34703254699707,
"step": 107
},
{
"epoch": 0.12,
"learning_rate": 4.179310344827587e-05,
"logits/chosen": -0.825312077999115,
"logits/rejected": -1.6536335945129395,
"logps/chosen": -245.26333618164062,
"logps/rejected": -275.9490966796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.488056182861328,
"rewards/margins": 24.79592514038086,
"rewards/rejected": -20.30786895751953,
"step": 108
},
{
"epoch": 0.12,
"learning_rate": 4.174137931034483e-05,
"logits/chosen": -0.6509658694267273,
"logits/rejected": -1.7768073081970215,
"logps/chosen": -494.1702575683594,
"logps/rejected": -269.7856140136719,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 11.041641235351562,
"rewards/margins": 30.055639266967773,
"rewards/rejected": -19.013999938964844,
"step": 109
},
{
"epoch": 0.12,
"learning_rate": 4.16896551724138e-05,
"logits/chosen": -0.813829243183136,
"logits/rejected": -1.7704083919525146,
"logps/chosen": -370.6927795410156,
"logps/rejected": -288.31463623046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.1367826461792,
"rewards/margins": 30.452945709228516,
"rewards/rejected": -20.316162109375,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 4.163793103448276e-05,
"logits/chosen": -0.450665146112442,
"logits/rejected": -1.4787647724151611,
"logps/chosen": -336.4142761230469,
"logps/rejected": -275.8489990234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.380362510681152,
"rewards/margins": 27.303016662597656,
"rewards/rejected": -20.922651290893555,
"step": 111
},
{
"epoch": 0.12,
"learning_rate": 4.158620689655173e-05,
"logits/chosen": -0.7610673904418945,
"logits/rejected": -1.5079166889190674,
"logps/chosen": -290.8649597167969,
"logps/rejected": -391.47772216796875,
"loss": 0.4671,
"rewards/accuracies": 0.9375,
"rewards/chosen": 4.447336196899414,
"rewards/margins": 27.807403564453125,
"rewards/rejected": -23.36006736755371,
"step": 112
},
{
"epoch": 0.12,
"learning_rate": 4.153448275862069e-05,
"logits/chosen": -0.9873843193054199,
"logits/rejected": -1.6280449628829956,
"logps/chosen": -244.6575164794922,
"logps/rejected": -324.1699523925781,
"loss": 0.0036,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.1840460300445557,
"rewards/margins": 25.491558074951172,
"rewards/rejected": -23.307514190673828,
"step": 113
},
{
"epoch": 0.12,
"learning_rate": 4.148275862068966e-05,
"logits/chosen": -1.0418487787246704,
"logits/rejected": -1.7689330577850342,
"logps/chosen": -309.9642028808594,
"logps/rejected": -433.8427734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.8272902965545654,
"rewards/margins": 33.52722930908203,
"rewards/rejected": -29.69993782043457,
"step": 114
},
{
"epoch": 0.13,
"learning_rate": 4.143103448275862e-05,
"logits/chosen": -0.9574589133262634,
"logits/rejected": -1.9435979127883911,
"logps/chosen": -485.497314453125,
"logps/rejected": -301.46038818359375,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.4343650341033936,
"rewards/margins": 27.89614486694336,
"rewards/rejected": -24.46177864074707,
"step": 115
},
{
"epoch": 0.13,
"learning_rate": 4.1379310344827587e-05,
"logits/chosen": -1.2192739248275757,
"logits/rejected": -1.9555035829544067,
"logps/chosen": -485.7822265625,
"logps/rejected": -452.36566162109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.4936442375183105,
"rewards/margins": 31.84035873413086,
"rewards/rejected": -35.33400344848633,
"step": 116
},
{
"epoch": 0.13,
"learning_rate": 4.1327586206896555e-05,
"logits/chosen": -1.3901960849761963,
"logits/rejected": -2.194340944290161,
"logps/chosen": -556.4442749023438,
"logps/rejected": -403.41094970703125,
"loss": 0.4842,
"rewards/accuracies": 0.9375,
"rewards/chosen": -6.604147434234619,
"rewards/margins": 25.96053695678711,
"rewards/rejected": -32.5646858215332,
"step": 117
},
{
"epoch": 0.13,
"learning_rate": 4.1275862068965516e-05,
"logits/chosen": -1.10233473777771,
"logits/rejected": -1.911782145500183,
"logps/chosen": -319.7232666015625,
"logps/rejected": -366.8639221191406,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5800843238830566,
"rewards/margins": 30.92066192626953,
"rewards/rejected": -30.3405818939209,
"step": 118
},
{
"epoch": 0.13,
"learning_rate": 4.1224137931034484e-05,
"logits/chosen": -0.7030006051063538,
"logits/rejected": -1.7387290000915527,
"logps/chosen": -291.53961181640625,
"logps/rejected": -350.3901062011719,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.4014167785644531,
"rewards/margins": 28.830717086791992,
"rewards/rejected": -27.429298400878906,
"step": 119
},
{
"epoch": 0.13,
"learning_rate": 4.117241379310345e-05,
"logits/chosen": -0.5296112895011902,
"logits/rejected": -1.5072706937789917,
"logps/chosen": -286.94879150390625,
"logps/rejected": -346.3030700683594,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.8979191780090332,
"rewards/margins": 28.363784790039062,
"rewards/rejected": -26.465864181518555,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 4.112068965517242e-05,
"logits/chosen": -0.42470210790634155,
"logits/rejected": -1.7659740447998047,
"logps/chosen": -477.8876953125,
"logps/rejected": -315.16717529296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.757699966430664,
"rewards/margins": 34.151214599609375,
"rewards/rejected": -24.393516540527344,
"step": 121
},
{
"epoch": 0.13,
"learning_rate": 4.106896551724138e-05,
"logits/chosen": -0.37895911931991577,
"logits/rejected": -1.4872817993164062,
"logps/chosen": -360.4671936035156,
"logps/rejected": -311.3260803222656,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.024797439575195,
"rewards/margins": 30.34416961669922,
"rewards/rejected": -20.31937026977539,
"step": 122
},
{
"epoch": 0.13,
"learning_rate": 4.101724137931035e-05,
"logits/chosen": -0.4127517342567444,
"logits/rejected": -1.4179290533065796,
"logps/chosen": -396.7817077636719,
"logps/rejected": -257.0691833496094,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.115121841430664,
"rewards/margins": 25.882369995117188,
"rewards/rejected": -17.767250061035156,
"step": 123
},
{
"epoch": 0.14,
"learning_rate": 4.096551724137932e-05,
"logits/chosen": -0.4867606461048126,
"logits/rejected": -1.433240532875061,
"logps/chosen": -307.6831359863281,
"logps/rejected": -285.9851379394531,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.156608581542969,
"rewards/margins": 24.28235626220703,
"rewards/rejected": -15.12574577331543,
"step": 124
},
{
"epoch": 0.14,
"learning_rate": 4.091379310344828e-05,
"logits/chosen": -0.5465874671936035,
"logits/rejected": -1.398258924484253,
"logps/chosen": -244.0363311767578,
"logps/rejected": -240.68551635742188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.43398904800415,
"rewards/margins": 23.1319522857666,
"rewards/rejected": -18.69796371459961,
"step": 125
},
{
"epoch": 0.14,
"learning_rate": 4.0862068965517246e-05,
"logits/chosen": -0.38893836736679077,
"logits/rejected": -1.427646279335022,
"logps/chosen": -351.76348876953125,
"logps/rejected": -289.0392150878906,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.574392795562744,
"rewards/margins": 25.838218688964844,
"rewards/rejected": -18.26382827758789,
"step": 126
},
{
"epoch": 0.14,
"learning_rate": 4.0810344827586214e-05,
"logits/chosen": -0.3710274398326874,
"logits/rejected": -1.5999269485473633,
"logps/chosen": -394.9821472167969,
"logps/rejected": -246.48887634277344,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.973166465759277,
"rewards/margins": 26.636192321777344,
"rewards/rejected": -17.66302490234375,
"step": 127
},
{
"epoch": 0.14,
"learning_rate": 4.0758620689655175e-05,
"logits/chosen": -0.673173725605011,
"logits/rejected": -1.2474948167800903,
"logps/chosen": -257.3236083984375,
"logps/rejected": -264.7505187988281,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.773941993713379,
"rewards/margins": 19.319332122802734,
"rewards/rejected": -16.545391082763672,
"step": 128
},
{
"epoch": 0.14,
"learning_rate": 4.0706896551724143e-05,
"logits/chosen": -0.560947060585022,
"logits/rejected": -1.374908447265625,
"logps/chosen": -301.8670959472656,
"logps/rejected": -232.6251983642578,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.369309425354004,
"rewards/margins": 26.155746459960938,
"rewards/rejected": -15.786436080932617,
"step": 129
},
{
"epoch": 0.14,
"learning_rate": 4.0655172413793105e-05,
"logits/chosen": -0.6484676003456116,
"logits/rejected": -1.3061511516571045,
"logps/chosen": -240.1058807373047,
"logps/rejected": -292.108154296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.469289302825928,
"rewards/margins": 25.45884132385254,
"rewards/rejected": -20.989551544189453,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 4.060344827586207e-05,
"logits/chosen": -0.4261731505393982,
"logits/rejected": -1.5151227712631226,
"logps/chosen": -402.2912292480469,
"logps/rejected": -289.1283264160156,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.882993698120117,
"rewards/margins": 30.517051696777344,
"rewards/rejected": -19.63405990600586,
"step": 131
},
{
"epoch": 0.14,
"learning_rate": 4.0551724137931034e-05,
"logits/chosen": -0.3702995181083679,
"logits/rejected": -1.5198004245758057,
"logps/chosen": -377.6826477050781,
"logps/rejected": -287.36566162109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.187080383300781,
"rewards/margins": 30.941383361816406,
"rewards/rejected": -20.754301071166992,
"step": 132
},
{
"epoch": 0.15,
"learning_rate": 4.05e-05,
"logits/chosen": -0.394854873418808,
"logits/rejected": -1.641805648803711,
"logps/chosen": -462.9255676269531,
"logps/rejected": -254.52276611328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.504643440246582,
"rewards/margins": 27.564743041992188,
"rewards/rejected": -17.060100555419922,
"step": 133
},
{
"epoch": 0.15,
"learning_rate": 4.044827586206896e-05,
"logits/chosen": -0.3886590600013733,
"logits/rejected": -1.4597467184066772,
"logps/chosen": -378.5803527832031,
"logps/rejected": -263.2305908203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 13.531683921813965,
"rewards/margins": 31.480838775634766,
"rewards/rejected": -17.949153900146484,
"step": 134
},
{
"epoch": 0.15,
"learning_rate": 4.039655172413793e-05,
"logits/chosen": -0.5102599859237671,
"logits/rejected": -1.250558614730835,
"logps/chosen": -295.6455078125,
"logps/rejected": -345.3118591308594,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.247247695922852,
"rewards/margins": 26.292499542236328,
"rewards/rejected": -19.04525375366211,
"step": 135
},
{
"epoch": 0.15,
"learning_rate": 4.03448275862069e-05,
"logits/chosen": -0.39377278089523315,
"logits/rejected": -1.5313684940338135,
"logps/chosen": -441.0325622558594,
"logps/rejected": -223.12750244140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 12.754582405090332,
"rewards/margins": 28.21717071533203,
"rewards/rejected": -15.462587356567383,
"step": 136
},
{
"epoch": 0.15,
"learning_rate": 4.029310344827587e-05,
"logits/chosen": -0.45350462198257446,
"logits/rejected": -1.3594186305999756,
"logps/chosen": -313.7057189941406,
"logps/rejected": -304.0419616699219,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.3996429443359375,
"rewards/margins": 23.64727020263672,
"rewards/rejected": -17.24762725830078,
"step": 137
},
{
"epoch": 0.15,
"learning_rate": 4.024137931034483e-05,
"logits/chosen": -0.17602750658988953,
"logits/rejected": -1.2745662927627563,
"logps/chosen": -371.0513916015625,
"logps/rejected": -299.74481201171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.569783687591553,
"rewards/margins": 26.724822998046875,
"rewards/rejected": -19.155040740966797,
"step": 138
},
{
"epoch": 0.15,
"learning_rate": 4.0189655172413796e-05,
"logits/chosen": -0.44520992040634155,
"logits/rejected": -1.4310128688812256,
"logps/chosen": -334.8761901855469,
"logps/rejected": -278.89349365234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.9243433475494385,
"rewards/margins": 22.313913345336914,
"rewards/rejected": -18.389568328857422,
"step": 139
},
{
"epoch": 0.15,
"learning_rate": 4.0137931034482764e-05,
"logits/chosen": -0.3496861755847931,
"logits/rejected": -1.480123519897461,
"logps/chosen": -345.8548583984375,
"logps/rejected": -295.12042236328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.938793182373047,
"rewards/margins": 28.614458084106445,
"rewards/rejected": -18.67566680908203,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 4.0086206896551726e-05,
"logits/chosen": -0.4202902913093567,
"logits/rejected": -1.5481184720993042,
"logps/chosen": -408.18121337890625,
"logps/rejected": -273.8868408203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.119111061096191,
"rewards/margins": 29.09032440185547,
"rewards/rejected": -19.971214294433594,
"step": 141
},
{
"epoch": 0.15,
"learning_rate": 4.0034482758620694e-05,
"logits/chosen": -0.5120177268981934,
"logits/rejected": -1.4507927894592285,
"logps/chosen": -271.6726989746094,
"logps/rejected": -297.4678955078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.688560962677002,
"rewards/margins": 26.492656707763672,
"rewards/rejected": -20.804094314575195,
"step": 142
},
{
"epoch": 0.16,
"learning_rate": 3.998275862068966e-05,
"logits/chosen": -0.41148996353149414,
"logits/rejected": -1.4985872507095337,
"logps/chosen": -343.8206481933594,
"logps/rejected": -241.0497589111328,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.314858436584473,
"rewards/margins": 26.18862533569336,
"rewards/rejected": -16.87376594543457,
"step": 143
},
{
"epoch": 0.16,
"learning_rate": 3.993103448275862e-05,
"logits/chosen": -0.1992441862821579,
"logits/rejected": -1.8458625078201294,
"logps/chosen": -504.0348205566406,
"logps/rejected": -318.8588562011719,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 12.68671989440918,
"rewards/margins": 34.4812126159668,
"rewards/rejected": -21.79449462890625,
"step": 144
},
{
"epoch": 0.16,
"learning_rate": 3.987931034482759e-05,
"logits/chosen": -0.5546131730079651,
"logits/rejected": -1.527896761894226,
"logps/chosen": -333.9448547363281,
"logps/rejected": -303.9145202636719,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.168367385864258,
"rewards/margins": 30.0524959564209,
"rewards/rejected": -19.88412857055664,
"step": 145
},
{
"epoch": 0.16,
"learning_rate": 3.982758620689656e-05,
"logits/chosen": -0.3886173367500305,
"logits/rejected": -1.621660828590393,
"logps/chosen": -369.8122253417969,
"logps/rejected": -272.4569396972656,
"loss": 0.0016,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.674747467041016,
"rewards/margins": 26.678119659423828,
"rewards/rejected": -18.003372192382812,
"step": 146
},
{
"epoch": 0.16,
"learning_rate": 3.977586206896552e-05,
"logits/chosen": -0.61821049451828,
"logits/rejected": -1.6792049407958984,
"logps/chosen": -345.2456359863281,
"logps/rejected": -307.6291809082031,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.595407485961914,
"rewards/margins": 29.619413375854492,
"rewards/rejected": -22.024009704589844,
"step": 147
},
{
"epoch": 0.16,
"learning_rate": 3.972413793103449e-05,
"logits/chosen": -0.23747998476028442,
"logits/rejected": -1.287044644355774,
"logps/chosen": -361.4759521484375,
"logps/rejected": -267.63592529296875,
"loss": 0.2105,
"rewards/accuracies": 0.9375,
"rewards/chosen": 7.393239974975586,
"rewards/margins": 23.982959747314453,
"rewards/rejected": -16.5897216796875,
"step": 148
},
{
"epoch": 0.16,
"learning_rate": 3.967241379310345e-05,
"logits/chosen": -0.3899969160556793,
"logits/rejected": -1.6496773958206177,
"logps/chosen": -331.9876403808594,
"logps/rejected": -278.04522705078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.100687026977539,
"rewards/margins": 29.64002227783203,
"rewards/rejected": -21.539335250854492,
"step": 149
},
{
"epoch": 0.16,
"learning_rate": 3.962068965517242e-05,
"logits/chosen": -0.4621184766292572,
"logits/rejected": -1.3823509216308594,
"logps/chosen": -291.25494384765625,
"logps/rejected": -313.21734619140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.036273002624512,
"rewards/margins": 25.113258361816406,
"rewards/rejected": -21.076988220214844,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 3.956896551724138e-05,
"logits/chosen": -0.3050623834133148,
"logits/rejected": -1.3223061561584473,
"logps/chosen": -388.243896484375,
"logps/rejected": -266.01983642578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.008649826049805,
"rewards/margins": 24.918262481689453,
"rewards/rejected": -17.90961265563965,
"step": 151
},
{
"epoch": 0.17,
"learning_rate": 3.9517241379310346e-05,
"logits/chosen": -0.26263201236724854,
"logits/rejected": -1.262205958366394,
"logps/chosen": -300.5107421875,
"logps/rejected": -266.810302734375,
"loss": 0.0007,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.9579243659973145,
"rewards/margins": 23.850536346435547,
"rewards/rejected": -17.892614364624023,
"step": 152
},
{
"epoch": 0.17,
"learning_rate": 3.9465517241379314e-05,
"logits/chosen": -0.34424301981925964,
"logits/rejected": -1.2062197923660278,
"logps/chosen": -273.7149353027344,
"logps/rejected": -266.54150390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.983701705932617,
"rewards/margins": 26.13591957092285,
"rewards/rejected": -20.1522216796875,
"step": 153
},
{
"epoch": 0.17,
"learning_rate": 3.9413793103448276e-05,
"logits/chosen": -0.1809622049331665,
"logits/rejected": -1.4350645542144775,
"logps/chosen": -418.6148376464844,
"logps/rejected": -297.8706359863281,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.36530876159668,
"rewards/margins": 30.20969581604004,
"rewards/rejected": -21.84438705444336,
"step": 154
},
{
"epoch": 0.17,
"learning_rate": 3.9362068965517244e-05,
"logits/chosen": -0.3474291265010834,
"logits/rejected": -1.3261463642120361,
"logps/chosen": -392.76068115234375,
"logps/rejected": -282.137451171875,
"loss": 0.12,
"rewards/accuracies": 0.9375,
"rewards/chosen": 8.480328559875488,
"rewards/margins": 24.708953857421875,
"rewards/rejected": -16.228626251220703,
"step": 155
},
{
"epoch": 0.17,
"learning_rate": 3.931034482758621e-05,
"logits/chosen": -0.29881787300109863,
"logits/rejected": -1.59579598903656,
"logps/chosen": -491.68280029296875,
"logps/rejected": -329.0652160644531,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.562919616699219,
"rewards/margins": 31.969928741455078,
"rewards/rejected": -22.407007217407227,
"step": 156
},
{
"epoch": 0.17,
"learning_rate": 3.925862068965517e-05,
"logits/chosen": -0.24624793231487274,
"logits/rejected": -1.2760369777679443,
"logps/chosen": -309.42950439453125,
"logps/rejected": -337.400634765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.126012802124023,
"rewards/margins": 27.284088134765625,
"rewards/rejected": -22.1580753326416,
"step": 157
},
{
"epoch": 0.17,
"learning_rate": 3.920689655172414e-05,
"logits/chosen": -0.24486477673053741,
"logits/rejected": -1.4145996570587158,
"logps/chosen": -435.2896423339844,
"logps/rejected": -347.84698486328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.421405076980591,
"rewards/margins": 30.74762725830078,
"rewards/rejected": -27.32622528076172,
"step": 158
},
{
"epoch": 0.17,
"learning_rate": 3.915517241379311e-05,
"logits/chosen": -0.4706140458583832,
"logits/rejected": -1.4215468168258667,
"logps/chosen": -427.6326904296875,
"logps/rejected": -399.431640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.1375885009765625,
"rewards/margins": 31.478370666503906,
"rewards/rejected": -27.340782165527344,
"step": 159
},
{
"epoch": 0.17,
"learning_rate": 3.910344827586207e-05,
"logits/chosen": -0.25800830125808716,
"logits/rejected": -1.604130744934082,
"logps/chosen": -430.5594482421875,
"logps/rejected": -431.40301513671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.8110466003417969,
"rewards/margins": 36.45166015625,
"rewards/rejected": -34.64060974121094,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 3.905172413793104e-05,
"logits/chosen": -0.3043404221534729,
"logits/rejected": -1.5278654098510742,
"logps/chosen": -465.7344970703125,
"logps/rejected": -436.65899658203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.1547170877456665,
"rewards/margins": 33.50754928588867,
"rewards/rejected": -34.66226577758789,
"step": 161
},
{
"epoch": 0.18,
"learning_rate": 3.9000000000000006e-05,
"logits/chosen": -0.22293318808078766,
"logits/rejected": -1.2031610012054443,
"logps/chosen": -428.4457092285156,
"logps/rejected": -419.1228332519531,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.0903587341308594,
"rewards/margins": 28.546253204345703,
"rewards/rejected": -31.636613845825195,
"step": 162
},
{
"epoch": 0.18,
"learning_rate": 3.894827586206897e-05,
"logits/chosen": -0.18892326951026917,
"logits/rejected": -1.481589913368225,
"logps/chosen": -513.7359008789062,
"logps/rejected": -456.95208740234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.6842398643493652,
"rewards/margins": 39.1934928894043,
"rewards/rejected": -36.509254455566406,
"step": 163
},
{
"epoch": 0.18,
"learning_rate": 3.8896551724137935e-05,
"logits/chosen": -0.48873329162597656,
"logits/rejected": -1.4820678234100342,
"logps/chosen": -393.00079345703125,
"logps/rejected": -426.32696533203125,
"loss": 0.0194,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.972713470458984,
"rewards/margins": 28.33656120300293,
"rewards/rejected": -34.30927276611328,
"step": 164
},
{
"epoch": 0.18,
"learning_rate": 3.88448275862069e-05,
"logits/chosen": -0.4431387484073639,
"logits/rejected": -1.3382742404937744,
"logps/chosen": -392.2378845214844,
"logps/rejected": -503.30194091796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.949856758117676,
"rewards/margins": 34.904537200927734,
"rewards/rejected": -40.854393005371094,
"step": 165
},
{
"epoch": 0.18,
"learning_rate": 3.8793103448275865e-05,
"logits/chosen": -0.2996464669704437,
"logits/rejected": -1.4847010374069214,
"logps/chosen": -483.34161376953125,
"logps/rejected": -548.205078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.7714486122131348,
"rewards/margins": 47.965972900390625,
"rewards/rejected": -44.19452667236328,
"step": 166
},
{
"epoch": 0.18,
"learning_rate": 3.874137931034483e-05,
"logits/chosen": -0.3217467963695526,
"logits/rejected": -1.2237169742584229,
"logps/chosen": -396.9007568359375,
"logps/rejected": -509.6751708984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.9992933869361877,
"rewards/margins": 39.428592681884766,
"rewards/rejected": -38.429298400878906,
"step": 167
},
{
"epoch": 0.18,
"learning_rate": 3.8689655172413794e-05,
"logits/chosen": -0.26858553290367126,
"logits/rejected": -1.3162765502929688,
"logps/chosen": -436.47088623046875,
"logps/rejected": -461.6593933105469,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.6044464111328125,
"rewards/margins": 38.4824104309082,
"rewards/rejected": -35.87796401977539,
"step": 168
},
{
"epoch": 0.18,
"learning_rate": 3.863793103448276e-05,
"logits/chosen": -0.343127965927124,
"logits/rejected": -1.390782117843628,
"logps/chosen": -392.77978515625,
"logps/rejected": -443.3890686035156,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.19043821096420288,
"rewards/margins": 34.40040969848633,
"rewards/rejected": -34.20996856689453,
"step": 169
},
{
"epoch": 0.19,
"learning_rate": 3.858620689655172e-05,
"logits/chosen": -0.43945077061653137,
"logits/rejected": -1.3458408117294312,
"logps/chosen": -386.0972595214844,
"logps/rejected": -481.8536071777344,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.2730538845062256,
"rewards/margins": 35.0412483215332,
"rewards/rejected": -33.76819610595703,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 3.853448275862069e-05,
"logits/chosen": -0.28766676783561707,
"logits/rejected": -1.314267873764038,
"logps/chosen": -423.24981689453125,
"logps/rejected": -416.8682861328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.9727609157562256,
"rewards/margins": 34.98452377319336,
"rewards/rejected": -33.01176834106445,
"step": 171
},
{
"epoch": 0.19,
"learning_rate": 3.848275862068966e-05,
"logits/chosen": -0.3893183767795563,
"logits/rejected": -1.443713903427124,
"logps/chosen": -474.935546875,
"logps/rejected": -453.4057922363281,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.1096689701080322,
"rewards/margins": 38.80006790161133,
"rewards/rejected": -36.690399169921875,
"step": 172
},
{
"epoch": 0.19,
"learning_rate": 3.843103448275862e-05,
"logits/chosen": -0.34813588857650757,
"logits/rejected": -1.271755337715149,
"logps/chosen": -392.284423828125,
"logps/rejected": -496.442138671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.8468620777130127,
"rewards/margins": 41.135921478271484,
"rewards/rejected": -38.289058685302734,
"step": 173
},
{
"epoch": 0.19,
"learning_rate": 3.837931034482759e-05,
"logits/chosen": -0.3464352786540985,
"logits/rejected": -1.223905324935913,
"logps/chosen": -372.1242370605469,
"logps/rejected": -446.0730285644531,
"loss": 0.0073,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.18368953466415405,
"rewards/margins": 33.218013763427734,
"rewards/rejected": -33.034324645996094,
"step": 174
},
{
"epoch": 0.19,
"learning_rate": 3.8327586206896556e-05,
"logits/chosen": -0.42792245745658875,
"logits/rejected": -1.189011812210083,
"logps/chosen": -324.2301940917969,
"logps/rejected": -503.5957946777344,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.7187633514404297,
"rewards/margins": 37.19697189331055,
"rewards/rejected": -38.91573715209961,
"step": 175
},
{
"epoch": 0.19,
"learning_rate": 3.827586206896552e-05,
"logits/chosen": -0.16668730974197388,
"logits/rejected": -1.5985019207000732,
"logps/chosen": -482.8082580566406,
"logps/rejected": -449.761474609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.7022485733032227,
"rewards/margins": 42.01506805419922,
"rewards/rejected": -38.31282043457031,
"step": 176
},
{
"epoch": 0.19,
"learning_rate": 3.8224137931034485e-05,
"logits/chosen": -0.26949506998062134,
"logits/rejected": -1.2986763715744019,
"logps/chosen": -348.618896484375,
"logps/rejected": -442.8262023925781,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.1358022689819336,
"rewards/margins": 35.771461486816406,
"rewards/rejected": -33.63566207885742,
"step": 177
},
{
"epoch": 0.19,
"learning_rate": 3.8172413793103453e-05,
"logits/chosen": -0.3438015580177307,
"logits/rejected": -1.3001600503921509,
"logps/chosen": -333.9195251464844,
"logps/rejected": -457.9849853515625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.145051956176758,
"rewards/margins": 41.207923889160156,
"rewards/rejected": -39.06287384033203,
"step": 178
},
{
"epoch": 0.2,
"learning_rate": 3.8120689655172415e-05,
"logits/chosen": -0.10503964871168137,
"logits/rejected": -1.2384865283966064,
"logps/chosen": -451.48663330078125,
"logps/rejected": -479.8037414550781,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.525763988494873,
"rewards/margins": 38.3972282409668,
"rewards/rejected": -37.8714599609375,
"step": 179
},
{
"epoch": 0.2,
"learning_rate": 3.806896551724138e-05,
"logits/chosen": -0.30969691276550293,
"logits/rejected": -1.1278965473175049,
"logps/chosen": -298.7955322265625,
"logps/rejected": -499.42279052734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.1820168495178223,
"rewards/margins": 37.28181457519531,
"rewards/rejected": -39.463829040527344,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 3.801724137931035e-05,
"logits/chosen": -0.3709387183189392,
"logits/rejected": -1.5942573547363281,
"logps/chosen": -422.3631286621094,
"logps/rejected": -511.52008056640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.8516347408294678,
"rewards/margins": 41.39206314086914,
"rewards/rejected": -38.540428161621094,
"step": 181
},
{
"epoch": 0.2,
"learning_rate": 3.796551724137931e-05,
"logits/chosen": -0.2693447470664978,
"logits/rejected": -1.5490005016326904,
"logps/chosen": -480.881591796875,
"logps/rejected": -414.71917724609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.7573628425598145,
"rewards/margins": 39.35446548461914,
"rewards/rejected": -36.59709930419922,
"step": 182
},
{
"epoch": 0.2,
"learning_rate": 3.791379310344828e-05,
"logits/chosen": -0.39544716477394104,
"logits/rejected": -1.4232298135757446,
"logps/chosen": -400.05267333984375,
"logps/rejected": -465.1136169433594,
"loss": 0.0018,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.5475125312805176,
"rewards/margins": 38.094913482666016,
"rewards/rejected": -34.547393798828125,
"step": 183
},
{
"epoch": 0.2,
"learning_rate": 3.786206896551725e-05,
"logits/chosen": -0.3474569320678711,
"logits/rejected": -1.4260185956954956,
"logps/chosen": -334.5423889160156,
"logps/rejected": -438.87408447265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.5236696004867554,
"rewards/margins": 33.86663055419922,
"rewards/rejected": -35.390296936035156,
"step": 184
},
{
"epoch": 0.2,
"learning_rate": 3.781034482758621e-05,
"logits/chosen": -0.3836357593536377,
"logits/rejected": -1.554406762123108,
"logps/chosen": -372.57830810546875,
"logps/rejected": -439.4316101074219,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.840342402458191,
"rewards/margins": 34.46831512451172,
"rewards/rejected": -32.627967834472656,
"step": 185
},
{
"epoch": 0.2,
"learning_rate": 3.775862068965517e-05,
"logits/chosen": -0.18503640592098236,
"logits/rejected": -1.800915241241455,
"logps/chosen": -485.19354248046875,
"logps/rejected": -432.1221923828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.203826427459717,
"rewards/margins": 39.722900390625,
"rewards/rejected": -35.51907730102539,
"step": 186
},
{
"epoch": 0.2,
"learning_rate": 3.770689655172414e-05,
"logits/chosen": -0.3300974667072296,
"logits/rejected": -1.5052634477615356,
"logps/chosen": -418.87017822265625,
"logps/rejected": -408.99554443359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.9931721687316895,
"rewards/margins": 35.2595100402832,
"rewards/rejected": -32.266334533691406,
"step": 187
},
{
"epoch": 0.21,
"learning_rate": 3.7655172413793106e-05,
"logits/chosen": -0.27791130542755127,
"logits/rejected": -1.4637497663497925,
"logps/chosen": -370.642822265625,
"logps/rejected": -457.7041320800781,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.304169178009033,
"rewards/margins": 40.587310791015625,
"rewards/rejected": -36.283138275146484,
"step": 188
},
{
"epoch": 0.21,
"learning_rate": 3.760344827586207e-05,
"logits/chosen": -0.4701173007488251,
"logits/rejected": -1.403714895248413,
"logps/chosen": -333.7972717285156,
"logps/rejected": -436.09967041015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.8245915174484253,
"rewards/margins": 36.37276077270508,
"rewards/rejected": -34.54816818237305,
"step": 189
},
{
"epoch": 0.21,
"learning_rate": 3.7551724137931035e-05,
"logits/chosen": -0.08819374442100525,
"logits/rejected": -1.395701289176941,
"logps/chosen": -401.96673583984375,
"logps/rejected": -440.0989685058594,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.565300941467285,
"rewards/margins": 33.236175537109375,
"rewards/rejected": -30.670875549316406,
"step": 190
},
{
"epoch": 0.21,
"learning_rate": 3.7500000000000003e-05,
"logits/chosen": -0.17811371386051178,
"logits/rejected": -1.501448154449463,
"logps/chosen": -447.5896301269531,
"logps/rejected": -375.3368835449219,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.7833425998687744,
"rewards/margins": 31.601383209228516,
"rewards/rejected": -28.818038940429688,
"step": 191
},
{
"epoch": 0.21,
"learning_rate": 3.7448275862068965e-05,
"logits/chosen": -0.44955122470855713,
"logits/rejected": -1.550938606262207,
"logps/chosen": -289.89959716796875,
"logps/rejected": -400.880859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.4812740385532379,
"rewards/margins": 33.061256408691406,
"rewards/rejected": -33.54253005981445,
"step": 192
},
{
"epoch": 0.21,
"learning_rate": 3.739655172413793e-05,
"logits/chosen": -0.18104656040668488,
"logits/rejected": -1.4971003532409668,
"logps/chosen": -418.8290710449219,
"logps/rejected": -424.74859619140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.926714897155762,
"rewards/margins": 39.01382064819336,
"rewards/rejected": -32.08710861206055,
"step": 193
},
{
"epoch": 0.21,
"learning_rate": 3.73448275862069e-05,
"logits/chosen": -0.16005319356918335,
"logits/rejected": -1.4771628379821777,
"logps/chosen": -437.9535827636719,
"logps/rejected": -435.7216796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.183934688568115,
"rewards/margins": 40.51701354980469,
"rewards/rejected": -35.33308410644531,
"step": 194
},
{
"epoch": 0.21,
"learning_rate": 3.729310344827586e-05,
"logits/chosen": -0.35886967182159424,
"logits/rejected": -1.6980268955230713,
"logps/chosen": -404.4248962402344,
"logps/rejected": -412.4001159667969,
"loss": 0.0068,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.873406887054443,
"rewards/margins": 38.6983757019043,
"rewards/rejected": -30.824968338012695,
"step": 195
},
{
"epoch": 0.21,
"learning_rate": 3.724137931034483e-05,
"logits/chosen": -0.4241984486579895,
"logits/rejected": -1.4724136590957642,
"logps/chosen": -353.877197265625,
"logps/rejected": -414.2342529296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.698596954345703,
"rewards/margins": 36.431583404541016,
"rewards/rejected": -33.73298645019531,
"step": 196
},
{
"epoch": 0.21,
"learning_rate": 3.71896551724138e-05,
"logits/chosen": -0.38190075755119324,
"logits/rejected": -1.520878553390503,
"logps/chosen": -303.9383544921875,
"logps/rejected": -443.4150390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.500533103942871,
"rewards/margins": 41.76572036743164,
"rewards/rejected": -36.26518630981445,
"step": 197
},
{
"epoch": 0.22,
"learning_rate": 3.713793103448276e-05,
"logits/chosen": -0.5008329153060913,
"logits/rejected": -1.4159965515136719,
"logps/chosen": -298.4696044921875,
"logps/rejected": -496.4792175292969,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.6865413188934326,
"rewards/margins": 43.41154098510742,
"rewards/rejected": -39.72499465942383,
"step": 198
},
{
"epoch": 0.22,
"learning_rate": 3.708620689655173e-05,
"logits/chosen": -0.30573636293411255,
"logits/rejected": -1.4757778644561768,
"logps/chosen": -404.08349609375,
"logps/rejected": -536.4090576171875,
"loss": 0.0994,
"rewards/accuracies": 0.9375,
"rewards/chosen": 2.837350606918335,
"rewards/margins": 47.625877380371094,
"rewards/rejected": -44.78852844238281,
"step": 199
},
{
"epoch": 0.22,
"learning_rate": 3.7034482758620695e-05,
"logits/chosen": -0.08167792111635208,
"logits/rejected": -1.6543066501617432,
"logps/chosen": -478.5865173339844,
"logps/rejected": -535.1455078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.218913555145264,
"rewards/margins": 51.752662658691406,
"rewards/rejected": -45.533748626708984,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 3.698275862068966e-05,
"logits/chosen": -0.4204535186290741,
"logits/rejected": -1.4588035345077515,
"logps/chosen": -488.2334899902344,
"logps/rejected": -772.4085083007812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.8939381837844849,
"rewards/margins": 68.2295913696289,
"rewards/rejected": -67.33565521240234,
"step": 201
},
{
"epoch": 0.22,
"learning_rate": 3.6931034482758624e-05,
"logits/chosen": -0.21560296416282654,
"logits/rejected": -1.2928329706192017,
"logps/chosen": -516.2886352539062,
"logps/rejected": -823.55908203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.315321922302246,
"rewards/margins": 68.40852355957031,
"rewards/rejected": -74.72383880615234,
"step": 202
},
{
"epoch": 0.22,
"learning_rate": 3.6879310344827586e-05,
"logits/chosen": -0.42431268095970154,
"logits/rejected": -0.9408793449401855,
"logps/chosen": -475.7739562988281,
"logps/rejected": -990.97802734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -15.18862247467041,
"rewards/margins": 75.22517395019531,
"rewards/rejected": -90.41380310058594,
"step": 203
},
{
"epoch": 0.22,
"learning_rate": 3.6827586206896554e-05,
"logits/chosen": -0.3706437051296234,
"logits/rejected": -1.5770463943481445,
"logps/chosen": -580.4349365234375,
"logps/rejected": -982.412841796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.3259365558624268,
"rewards/margins": 85.03890991210938,
"rewards/rejected": -87.36485290527344,
"step": 204
},
{
"epoch": 0.22,
"learning_rate": 3.6775862068965515e-05,
"logits/chosen": -0.46955880522727966,
"logits/rejected": -1.2554025650024414,
"logps/chosen": -406.4046325683594,
"logps/rejected": -807.9384155273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.099958419799805,
"rewards/margins": 62.139991760253906,
"rewards/rejected": -70.23995208740234,
"step": 205
},
{
"epoch": 0.22,
"learning_rate": 3.672413793103448e-05,
"logits/chosen": -0.1373772770166397,
"logits/rejected": -1.2258226871490479,
"logps/chosen": -484.78289794921875,
"logps/rejected": -775.5526123046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.985532283782959,
"rewards/margins": 62.29596710205078,
"rewards/rejected": -69.28150177001953,
"step": 206
},
{
"epoch": 0.23,
"learning_rate": 3.667241379310345e-05,
"logits/chosen": -0.3842742145061493,
"logits/rejected": -1.3139704465866089,
"logps/chosen": -575.8878784179688,
"logps/rejected": -772.5504150390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.301702499389648,
"rewards/margins": 63.3919563293457,
"rewards/rejected": -67.69366455078125,
"step": 207
},
{
"epoch": 0.23,
"learning_rate": 3.662068965517241e-05,
"logits/chosen": -0.16872625052928925,
"logits/rejected": -1.103173017501831,
"logps/chosen": -407.3558349609375,
"logps/rejected": -742.6690063476562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.2132223844528198,
"rewards/margins": 64.90454864501953,
"rewards/rejected": -66.11776733398438,
"step": 208
},
{
"epoch": 0.23,
"learning_rate": 3.656896551724138e-05,
"logits/chosen": -0.22817087173461914,
"logits/rejected": -1.299288272857666,
"logps/chosen": -535.9667358398438,
"logps/rejected": -746.4730224609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.898517608642578,
"rewards/margins": 60.320106506347656,
"rewards/rejected": -66.21862030029297,
"step": 209
},
{
"epoch": 0.23,
"learning_rate": 3.651724137931035e-05,
"logits/chosen": -0.43456578254699707,
"logits/rejected": -1.3410723209381104,
"logps/chosen": -434.5975036621094,
"logps/rejected": -722.338623046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.796084880828857,
"rewards/margins": 59.60700988769531,
"rewards/rejected": -64.40309143066406,
"step": 210
},
{
"epoch": 0.23,
"learning_rate": 3.646551724137931e-05,
"logits/chosen": -0.099545419216156,
"logits/rejected": -1.4023548364639282,
"logps/chosen": -587.4548950195312,
"logps/rejected": -724.5460205078125,
"loss": 0.0007,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.0788767337799072,
"rewards/margins": 62.40778350830078,
"rewards/rejected": -64.48665618896484,
"step": 211
},
{
"epoch": 0.23,
"learning_rate": 3.641379310344828e-05,
"logits/chosen": -0.39735737442970276,
"logits/rejected": -1.2577073574066162,
"logps/chosen": -360.4342956542969,
"logps/rejected": -707.16552734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.821351051330566,
"rewards/margins": 52.31917953491211,
"rewards/rejected": -57.140525817871094,
"step": 212
},
{
"epoch": 0.23,
"learning_rate": 3.6362068965517245e-05,
"logits/chosen": -0.32743093371391296,
"logits/rejected": -1.23341965675354,
"logps/chosen": -430.1988830566406,
"logps/rejected": -682.2755126953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.829233407974243,
"rewards/margins": 54.4882926940918,
"rewards/rejected": -58.317527770996094,
"step": 213
},
{
"epoch": 0.23,
"learning_rate": 3.6310344827586206e-05,
"logits/chosen": -0.1188780814409256,
"logits/rejected": -1.211256980895996,
"logps/chosen": -478.95294189453125,
"logps/rejected": -628.7106323242188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.967594146728516,
"rewards/margins": 46.12427520751953,
"rewards/rejected": -52.09186935424805,
"step": 214
},
{
"epoch": 0.23,
"learning_rate": 3.6258620689655174e-05,
"logits/chosen": -0.15380708873271942,
"logits/rejected": -1.4826284646987915,
"logps/chosen": -502.1640319824219,
"logps/rejected": -613.2930297851562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.2820662260055542,
"rewards/margins": 54.291709899902344,
"rewards/rejected": -53.0096435546875,
"step": 215
},
{
"epoch": 0.24,
"learning_rate": 3.620689655172414e-05,
"logits/chosen": -0.04195930063724518,
"logits/rejected": -1.2043323516845703,
"logps/chosen": -408.9276123046875,
"logps/rejected": -659.142578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.6782640218734741,
"rewards/margins": 56.35860824584961,
"rewards/rejected": -54.68034362792969,
"step": 216
},
{
"epoch": 0.24,
"learning_rate": 3.615517241379311e-05,
"logits/chosen": -0.06693141162395477,
"logits/rejected": -1.0604804754257202,
"logps/chosen": -480.0716247558594,
"logps/rejected": -639.0257568359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.6284542083740234,
"rewards/margins": 51.55681228637695,
"rewards/rejected": -55.18526840209961,
"step": 217
},
{
"epoch": 0.24,
"learning_rate": 3.610344827586207e-05,
"logits/chosen": -0.1353115737438202,
"logits/rejected": -1.2414418458938599,
"logps/chosen": -441.62567138671875,
"logps/rejected": -601.8602905273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.7760581970214844,
"rewards/margins": 48.804161071777344,
"rewards/rejected": -50.58022689819336,
"step": 218
},
{
"epoch": 0.24,
"learning_rate": 3.605172413793104e-05,
"logits/chosen": -0.1814473569393158,
"logits/rejected": -1.4145801067352295,
"logps/chosen": -499.2064514160156,
"logps/rejected": -635.701904296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.639859199523926,
"rewards/margins": 49.006500244140625,
"rewards/rejected": -54.646358489990234,
"step": 219
},
{
"epoch": 0.24,
"learning_rate": 3.6e-05,
"logits/chosen": -0.13956058025360107,
"logits/rejected": -0.8658940196037292,
"logps/chosen": -353.8810729980469,
"logps/rejected": -680.6879272460938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.038844347000122,
"rewards/margins": 52.220481872558594,
"rewards/rejected": -54.25932312011719,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 3.594827586206897e-05,
"logits/chosen": -0.191183939576149,
"logits/rejected": -1.2838574647903442,
"logps/chosen": -574.6087646484375,
"logps/rejected": -622.7803955078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7797561883926392,
"rewards/margins": 50.8365592956543,
"rewards/rejected": -50.05680465698242,
"step": 221
},
{
"epoch": 0.24,
"learning_rate": 3.589655172413793e-05,
"logits/chosen": 0.004895269870758057,
"logits/rejected": -1.0355963706970215,
"logps/chosen": -378.75286865234375,
"logps/rejected": -611.6342163085938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.560927152633667,
"rewards/margins": 53.636077880859375,
"rewards/rejected": -52.07514953613281,
"step": 222
},
{
"epoch": 0.24,
"learning_rate": 3.58448275862069e-05,
"logits/chosen": -0.0416397899389267,
"logits/rejected": -1.0201894044876099,
"logps/chosen": -286.4012145996094,
"logps/rejected": -585.0177001953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.24752166867256165,
"rewards/margins": 52.19663619995117,
"rewards/rejected": -51.94911193847656,
"step": 223
},
{
"epoch": 0.24,
"learning_rate": 3.579310344827586e-05,
"logits/chosen": 0.08275717496871948,
"logits/rejected": -1.165152668952942,
"logps/chosen": -402.03204345703125,
"logps/rejected": -646.4345092773438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.17879903316497803,
"rewards/margins": 52.9560546875,
"rewards/rejected": -53.13485336303711,
"step": 224
},
{
"epoch": 0.25,
"learning_rate": 3.574137931034483e-05,
"logits/chosen": 0.046931296586990356,
"logits/rejected": -1.2173397541046143,
"logps/chosen": -379.2846374511719,
"logps/rejected": -596.7713623046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.054905891418457,
"rewards/margins": 49.74352264404297,
"rewards/rejected": -52.79842758178711,
"step": 225
},
{
"epoch": 0.25,
"learning_rate": 3.5689655172413795e-05,
"logits/chosen": -0.16892120242118835,
"logits/rejected": -1.086595892906189,
"logps/chosen": -383.6666564941406,
"logps/rejected": -613.8699951171875,
"loss": 0.0022,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.7993450164794922,
"rewards/margins": 48.63136291503906,
"rewards/rejected": -50.43070602416992,
"step": 226
},
{
"epoch": 0.25,
"learning_rate": 3.5637931034482757e-05,
"logits/chosen": -0.0628051906824112,
"logits/rejected": -1.2338706254959106,
"logps/chosen": -420.1468505859375,
"logps/rejected": -569.7159423828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.7352135181427002,
"rewards/margins": 48.35806655883789,
"rewards/rejected": -50.09328079223633,
"step": 227
},
{
"epoch": 0.25,
"learning_rate": 3.5586206896551725e-05,
"logits/chosen": -0.13550832867622375,
"logits/rejected": -1.3356702327728271,
"logps/chosen": -471.48358154296875,
"logps/rejected": -597.1064453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.008322715759277,
"rewards/margins": 46.82109832763672,
"rewards/rejected": -50.82941818237305,
"step": 228
},
{
"epoch": 0.25,
"learning_rate": 3.553448275862069e-05,
"logits/chosen": -0.19657878577709198,
"logits/rejected": -1.144600510597229,
"logps/chosen": -416.9407653808594,
"logps/rejected": -661.7545166015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.8045517206192017,
"rewards/margins": 57.125457763671875,
"rewards/rejected": -58.93001174926758,
"step": 229
},
{
"epoch": 0.25,
"learning_rate": 3.5482758620689654e-05,
"logits/chosen": -0.16479764878749847,
"logits/rejected": -1.1088446378707886,
"logps/chosen": -361.6660461425781,
"logps/rejected": -531.82275390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.02301928400993347,
"rewards/margins": 45.43212127685547,
"rewards/rejected": -45.455135345458984,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 3.543103448275862e-05,
"logits/chosen": -0.06933975219726562,
"logits/rejected": -1.1754459142684937,
"logps/chosen": -392.62481689453125,
"logps/rejected": -581.8388671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.2902095317840576,
"rewards/margins": 48.50893783569336,
"rewards/rejected": -49.79915237426758,
"step": 231
},
{
"epoch": 0.25,
"learning_rate": 3.537931034482759e-05,
"logits/chosen": -0.26539716124534607,
"logits/rejected": -1.2646820545196533,
"logps/chosen": -315.2926940917969,
"logps/rejected": -573.3612670898438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7868924140930176,
"rewards/margins": 45.750999450683594,
"rewards/rejected": -44.964107513427734,
"step": 232
},
{
"epoch": 0.25,
"learning_rate": 3.532758620689656e-05,
"logits/chosen": 0.00513702817261219,
"logits/rejected": -1.4749549627304077,
"logps/chosen": -537.417724609375,
"logps/rejected": -592.2806396484375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.04149657487869263,
"rewards/margins": 50.454158782958984,
"rewards/rejected": -50.412662506103516,
"step": 233
},
{
"epoch": 0.26,
"learning_rate": 3.527586206896552e-05,
"logits/chosen": -0.05358482524752617,
"logits/rejected": -1.2646411657333374,
"logps/chosen": -435.2836608886719,
"logps/rejected": -563.5516357421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.9884543418884277,
"rewards/margins": 47.98497009277344,
"rewards/rejected": -45.99651336669922,
"step": 234
},
{
"epoch": 0.26,
"learning_rate": 3.522413793103449e-05,
"logits/chosen": 0.0024913623929023743,
"logits/rejected": -1.0907244682312012,
"logps/chosen": -382.8013000488281,
"logps/rejected": -551.0772705078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.0033998489379883,
"rewards/margins": 44.1395263671875,
"rewards/rejected": -45.14292526245117,
"step": 235
},
{
"epoch": 0.26,
"learning_rate": 3.5172413793103455e-05,
"logits/chosen": -0.054612670093774796,
"logits/rejected": -1.1346925497055054,
"logps/chosen": -414.9861755371094,
"logps/rejected": -596.8836059570312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.3777976036071777,
"rewards/margins": 48.898712158203125,
"rewards/rejected": -50.276512145996094,
"step": 236
},
{
"epoch": 0.26,
"learning_rate": 3.5120689655172416e-05,
"logits/chosen": -0.04273924231529236,
"logits/rejected": -1.4653762578964233,
"logps/chosen": -521.715576171875,
"logps/rejected": -577.45263671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.3539397120475769,
"rewards/margins": 48.13010025024414,
"rewards/rejected": -47.776161193847656,
"step": 237
},
{
"epoch": 0.26,
"learning_rate": 3.5068965517241384e-05,
"logits/chosen": -0.09971227496862411,
"logits/rejected": -1.412309169769287,
"logps/chosen": -541.3079833984375,
"logps/rejected": -546.3953857421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.18726038932800293,
"rewards/margins": 47.805355072021484,
"rewards/rejected": -47.61809539794922,
"step": 238
},
{
"epoch": 0.26,
"learning_rate": 3.5017241379310345e-05,
"logits/chosen": 0.04640922695398331,
"logits/rejected": -1.2290853261947632,
"logps/chosen": -445.3258056640625,
"logps/rejected": -590.5760498046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5043596029281616,
"rewards/margins": 49.53385543823242,
"rewards/rejected": -49.02949523925781,
"step": 239
},
{
"epoch": 0.26,
"learning_rate": 3.4965517241379313e-05,
"logits/chosen": -0.2436431348323822,
"logits/rejected": -1.1010798215866089,
"logps/chosen": -310.34173583984375,
"logps/rejected": -582.0191650390625,
"loss": 0.0723,
"rewards/accuracies": 0.9375,
"rewards/chosen": -6.261377334594727,
"rewards/margins": 41.790748596191406,
"rewards/rejected": -48.0521240234375,
"step": 240
},
{
"epoch": 0.26,
"learning_rate": 3.4913793103448275e-05,
"logits/chosen": -0.0976068302989006,
"logits/rejected": -1.1630501747131348,
"logps/chosen": -407.0189514160156,
"logps/rejected": -587.5228881835938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.1800687313079834,
"rewards/margins": 50.658512115478516,
"rewards/rejected": -48.47844314575195,
"step": 241
},
{
"epoch": 0.26,
"learning_rate": 3.486206896551724e-05,
"logits/chosen": -0.16128882765769958,
"logits/rejected": -1.3036680221557617,
"logps/chosen": -364.50506591796875,
"logps/rejected": -502.24871826171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.9164876341819763,
"rewards/margins": 44.952972412109375,
"rewards/rejected": -44.03648376464844,
"step": 242
},
{
"epoch": 0.27,
"learning_rate": 3.4810344827586204e-05,
"logits/chosen": -0.020467162132263184,
"logits/rejected": -1.3299024105072021,
"logps/chosen": -440.3603820800781,
"logps/rejected": -508.4949645996094,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.407674789428711,
"rewards/margins": 41.96260070800781,
"rewards/rejected": -39.55492401123047,
"step": 243
},
{
"epoch": 0.27,
"learning_rate": 3.475862068965517e-05,
"logits/chosen": -0.12424595654010773,
"logits/rejected": -1.2621549367904663,
"logps/chosen": -372.3587951660156,
"logps/rejected": -545.2764282226562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.37911176681518555,
"rewards/margins": 44.348899841308594,
"rewards/rejected": -43.96978759765625,
"step": 244
},
{
"epoch": 0.27,
"learning_rate": 3.470689655172414e-05,
"logits/chosen": -0.254048228263855,
"logits/rejected": -1.3378281593322754,
"logps/chosen": -400.1960754394531,
"logps/rejected": -541.253173828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.260645866394043,
"rewards/margins": 48.459110260009766,
"rewards/rejected": -44.198463439941406,
"step": 245
},
{
"epoch": 0.27,
"learning_rate": 3.46551724137931e-05,
"logits/chosen": -0.09928327798843384,
"logits/rejected": -1.0079985857009888,
"logps/chosen": -318.05535888671875,
"logps/rejected": -475.6454162597656,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.3407931327819824,
"rewards/margins": 39.11427307128906,
"rewards/rejected": -37.773475646972656,
"step": 246
},
{
"epoch": 0.27,
"learning_rate": 3.460344827586207e-05,
"logits/chosen": -0.17899078130722046,
"logits/rejected": -1.0408397912979126,
"logps/chosen": -260.2774658203125,
"logps/rejected": -587.495361328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.1181957721710205,
"rewards/margins": 47.448177337646484,
"rewards/rejected": -48.566375732421875,
"step": 247
},
{
"epoch": 0.27,
"learning_rate": 3.455172413793104e-05,
"logits/chosen": -0.15649932622909546,
"logits/rejected": -1.3504737615585327,
"logps/chosen": -352.34295654296875,
"logps/rejected": -463.55999755859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.939250946044922,
"rewards/margins": 40.67493438720703,
"rewards/rejected": -36.73568344116211,
"step": 248
},
{
"epoch": 0.27,
"learning_rate": 3.4500000000000005e-05,
"logits/chosen": -0.047948114573955536,
"logits/rejected": -1.2849537134170532,
"logps/chosen": -394.3268737792969,
"logps/rejected": -474.2886962890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.573990821838379,
"rewards/margins": 43.014068603515625,
"rewards/rejected": -40.44007873535156,
"step": 249
},
{
"epoch": 0.27,
"learning_rate": 3.4448275862068966e-05,
"logits/chosen": -0.23074887692928314,
"logits/rejected": -1.2006328105926514,
"logps/chosen": -316.7071228027344,
"logps/rejected": -518.9232177734375,
"loss": 0.4199,
"rewards/accuracies": 0.9375,
"rewards/chosen": 2.6951587200164795,
"rewards/margins": 36.5284309387207,
"rewards/rejected": -33.833274841308594,
"step": 250
},
{
"epoch": 0.27,
"learning_rate": 3.4396551724137934e-05,
"logits/chosen": -0.16572320461273193,
"logits/rejected": -1.3215007781982422,
"logps/chosen": -444.8575744628906,
"logps/rejected": -486.4254455566406,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.5085513591766357,
"rewards/margins": 45.29148483276367,
"rewards/rejected": -42.78293228149414,
"step": 251
},
{
"epoch": 0.27,
"learning_rate": 3.43448275862069e-05,
"logits/chosen": -0.38803166151046753,
"logits/rejected": -1.2651021480560303,
"logps/chosen": -350.4290771484375,
"logps/rejected": -569.2044677734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.44204509258270264,
"rewards/margins": 48.26247787475586,
"rewards/rejected": -47.820430755615234,
"step": 252
},
{
"epoch": 0.28,
"learning_rate": 3.4293103448275864e-05,
"logits/chosen": -0.19859111309051514,
"logits/rejected": -1.1871520280838013,
"logps/chosen": -354.1485900878906,
"logps/rejected": -605.5889892578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.625746250152588,
"rewards/margins": 48.65724563598633,
"rewards/rejected": -52.282989501953125,
"step": 253
},
{
"epoch": 0.28,
"learning_rate": 3.424137931034483e-05,
"logits/chosen": -0.003446124028414488,
"logits/rejected": -1.4357542991638184,
"logps/chosen": -464.06402587890625,
"logps/rejected": -584.0009155273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.0634913444519043,
"rewards/margins": 49.579891204833984,
"rewards/rejected": -51.64338302612305,
"step": 254
},
{
"epoch": 0.28,
"learning_rate": 3.41896551724138e-05,
"logits/chosen": 0.005802547559142113,
"logits/rejected": -1.1215245723724365,
"logps/chosen": -487.831298828125,
"logps/rejected": -645.035400390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.5290374755859375,
"rewards/margins": 52.562137603759766,
"rewards/rejected": -56.0911750793457,
"step": 255
},
{
"epoch": 0.28,
"learning_rate": 3.413793103448276e-05,
"logits/chosen": -0.27775824069976807,
"logits/rejected": -1.4532489776611328,
"logps/chosen": -468.9490051269531,
"logps/rejected": -570.933837890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.029543161392212,
"rewards/margins": 45.34672927856445,
"rewards/rejected": -48.37627029418945,
"step": 256
},
{
"epoch": 0.28,
"learning_rate": 3.408620689655173e-05,
"logits/chosen": -0.04865233972668648,
"logits/rejected": -1.0499883890151978,
"logps/chosen": -517.0708618164062,
"logps/rejected": -639.54541015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.305459499359131,
"rewards/margins": 50.58137512207031,
"rewards/rejected": -55.88683319091797,
"step": 257
},
{
"epoch": 0.28,
"learning_rate": 3.403448275862069e-05,
"logits/chosen": -0.2616862654685974,
"logits/rejected": -1.0700899362564087,
"logps/chosen": -401.421875,
"logps/rejected": -618.0116577148438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.54936408996582,
"rewards/margins": 44.39057922363281,
"rewards/rejected": -54.939937591552734,
"step": 258
},
{
"epoch": 0.28,
"learning_rate": 3.398275862068966e-05,
"logits/chosen": 0.02191777713596821,
"logits/rejected": -1.4829727411270142,
"logps/chosen": -577.8099365234375,
"logps/rejected": -660.3970947265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.7517547607421875,
"rewards/margins": 47.69034194946289,
"rewards/rejected": -55.442100524902344,
"step": 259
},
{
"epoch": 0.28,
"learning_rate": 3.393103448275862e-05,
"logits/chosen": -0.055667877197265625,
"logits/rejected": -1.1761151552200317,
"logps/chosen": -493.5972900390625,
"logps/rejected": -705.7115478515625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.951239585876465,
"rewards/margins": 50.98706817626953,
"rewards/rejected": -59.93830871582031,
"step": 260
},
{
"epoch": 0.28,
"learning_rate": 3.387931034482759e-05,
"logits/chosen": -0.010112253949046135,
"logits/rejected": -1.1061949729919434,
"logps/chosen": -544.2592163085938,
"logps/rejected": -648.0838012695312,
"loss": 0.0685,
"rewards/accuracies": 0.9375,
"rewards/chosen": -10.865694999694824,
"rewards/margins": 42.983341217041016,
"rewards/rejected": -53.84903335571289,
"step": 261
},
{
"epoch": 0.29,
"learning_rate": 3.382758620689655e-05,
"logits/chosen": -0.3130599856376648,
"logits/rejected": -1.1265610456466675,
"logps/chosen": -394.48321533203125,
"logps/rejected": -624.9985961914062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.234168529510498,
"rewards/margins": 44.61975860595703,
"rewards/rejected": -51.853919982910156,
"step": 262
},
{
"epoch": 0.29,
"learning_rate": 3.3775862068965516e-05,
"logits/chosen": -0.5001847743988037,
"logits/rejected": -1.2859660387039185,
"logps/chosen": -381.885009765625,
"logps/rejected": -276.1200256347656,
"loss": 0.0274,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.0845551490783691,
"rewards/margins": 17.89061737060547,
"rewards/rejected": -18.975173950195312,
"step": 263
},
{
"epoch": 0.29,
"learning_rate": 3.3724137931034484e-05,
"logits/chosen": -0.16429847478866577,
"logits/rejected": -1.3770393133163452,
"logps/chosen": -416.09918212890625,
"logps/rejected": -444.2696533203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.0829229354858398,
"rewards/margins": 36.78654098510742,
"rewards/rejected": -37.86946487426758,
"step": 264
},
{
"epoch": 0.29,
"learning_rate": 3.367241379310345e-05,
"logits/chosen": -0.027936279773712158,
"logits/rejected": -1.2221875190734863,
"logps/chosen": -522.7379150390625,
"logps/rejected": -575.3955688476562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.6051886081695557,
"rewards/margins": 44.91753005981445,
"rewards/rejected": -48.52272033691406,
"step": 265
},
{
"epoch": 0.29,
"learning_rate": 3.3620689655172414e-05,
"logits/chosen": -0.023054365068674088,
"logits/rejected": -1.0561506748199463,
"logps/chosen": -476.08087158203125,
"logps/rejected": -584.338134765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.656482994556427,
"rewards/margins": 47.59941864013672,
"rewards/rejected": -48.25589370727539,
"step": 266
},
{
"epoch": 0.29,
"learning_rate": 3.356896551724138e-05,
"logits/chosen": -0.21733063459396362,
"logits/rejected": -0.9282070994377136,
"logps/chosen": -309.57916259765625,
"logps/rejected": -548.53564453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.397457122802734,
"rewards/margins": 38.486846923828125,
"rewards/rejected": -47.884307861328125,
"step": 267
},
{
"epoch": 0.29,
"learning_rate": 3.351724137931035e-05,
"logits/chosen": -0.13685892522335052,
"logits/rejected": -0.881144642829895,
"logps/chosen": -402.0709228515625,
"logps/rejected": -593.3131103515625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.071722984313965,
"rewards/margins": 41.16486358642578,
"rewards/rejected": -51.23658752441406,
"step": 268
},
{
"epoch": 0.29,
"learning_rate": 3.346551724137931e-05,
"logits/chosen": 0.0004104040563106537,
"logits/rejected": -1.2138159275054932,
"logps/chosen": -586.6741333007812,
"logps/rejected": -579.4757080078125,
"loss": 0.0041,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.9185256958007812,
"rewards/margins": 41.63846206665039,
"rewards/rejected": -44.556983947753906,
"step": 269
},
{
"epoch": 0.29,
"learning_rate": 3.341379310344828e-05,
"logits/chosen": -0.11678376793861389,
"logits/rejected": -1.2740269899368286,
"logps/chosen": -518.05908203125,
"logps/rejected": -548.7737426757812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.559596061706543,
"rewards/margins": 40.736881256103516,
"rewards/rejected": -48.296478271484375,
"step": 270
},
{
"epoch": 0.3,
"learning_rate": 3.336206896551725e-05,
"logits/chosen": -0.2319948375225067,
"logits/rejected": -1.038511872291565,
"logps/chosen": -457.996337890625,
"logps/rejected": -614.3683471679688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.421997547149658,
"rewards/margins": 46.14197540283203,
"rewards/rejected": -49.56397247314453,
"step": 271
},
{
"epoch": 0.3,
"learning_rate": 3.331034482758621e-05,
"logits/chosen": -0.175481915473938,
"logits/rejected": -0.9189218878746033,
"logps/chosen": -413.4037170410156,
"logps/rejected": -577.8434448242188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.640353679656982,
"rewards/margins": 43.46728515625,
"rewards/rejected": -49.107635498046875,
"step": 272
},
{
"epoch": 0.3,
"learning_rate": 3.3258620689655176e-05,
"logits/chosen": 0.041123226284980774,
"logits/rejected": -1.239971399307251,
"logps/chosen": -625.6574096679688,
"logps/rejected": -620.5679321289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.8174872398376465,
"rewards/margins": 47.40455627441406,
"rewards/rejected": -52.2220458984375,
"step": 273
},
{
"epoch": 0.3,
"learning_rate": 3.3206896551724144e-05,
"logits/chosen": 0.016035079956054688,
"logits/rejected": -1.058797836303711,
"logps/chosen": -433.7515869140625,
"logps/rejected": -610.6272583007812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.2071919441223145,
"rewards/margins": 46.5596809387207,
"rewards/rejected": -51.766876220703125,
"step": 274
},
{
"epoch": 0.3,
"learning_rate": 3.3155172413793105e-05,
"logits/chosen": 0.005678463727235794,
"logits/rejected": -1.0126562118530273,
"logps/chosen": -519.1249389648438,
"logps/rejected": -667.5272216796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.07732820510864258,
"rewards/margins": 48.706153869628906,
"rewards/rejected": -48.628822326660156,
"step": 275
},
{
"epoch": 0.3,
"learning_rate": 3.310344827586207e-05,
"logits/chosen": -0.06707608699798584,
"logits/rejected": -1.1867536306381226,
"logps/chosen": -434.00762939453125,
"logps/rejected": -475.2304382324219,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.4429032802581787,
"rewards/margins": 38.4698486328125,
"rewards/rejected": -41.91275405883789,
"step": 276
},
{
"epoch": 0.3,
"learning_rate": 3.3051724137931035e-05,
"logits/chosen": 0.016937214881181717,
"logits/rejected": -0.9644786715507507,
"logps/chosen": -438.28424072265625,
"logps/rejected": -540.373291015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.785179615020752,
"rewards/margins": 39.099998474121094,
"rewards/rejected": -42.88517761230469,
"step": 277
},
{
"epoch": 0.3,
"learning_rate": 3.3e-05,
"logits/chosen": -0.13098500669002533,
"logits/rejected": -1.1797230243682861,
"logps/chosen": -481.2913818359375,
"logps/rejected": -575.146240234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.13218802213668823,
"rewards/margins": 49.17036056518555,
"rewards/rejected": -49.03817367553711,
"step": 278
},
{
"epoch": 0.3,
"learning_rate": 3.2948275862068964e-05,
"logits/chosen": -0.14736391603946686,
"logits/rejected": -1.0556457042694092,
"logps/chosen": -449.7217712402344,
"logps/rejected": -555.5156860351562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.082195281982422,
"rewards/margins": 34.08275604248047,
"rewards/rejected": -43.16495132446289,
"step": 279
},
{
"epoch": 0.31,
"learning_rate": 3.289655172413793e-05,
"logits/chosen": -0.1435016244649887,
"logits/rejected": -1.0380524396896362,
"logps/chosen": -338.7105712890625,
"logps/rejected": -543.041259765625,
"loss": 0.0016,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.8971967697143555,
"rewards/margins": 37.95754623413086,
"rewards/rejected": -43.85474395751953,
"step": 280
},
{
"epoch": 0.31,
"learning_rate": 3.28448275862069e-05,
"logits/chosen": -0.013942647725343704,
"logits/rejected": -1.056246042251587,
"logps/chosen": -434.2045593261719,
"logps/rejected": -555.7156372070312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.764453887939453,
"rewards/margins": 43.68494415283203,
"rewards/rejected": -46.44939422607422,
"step": 281
},
{
"epoch": 0.31,
"learning_rate": 3.279310344827586e-05,
"logits/chosen": -0.11425824463367462,
"logits/rejected": -0.994450569152832,
"logps/chosen": -397.4031677246094,
"logps/rejected": -641.703369140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.2452192306518555,
"rewards/margins": 43.18861389160156,
"rewards/rejected": -50.433834075927734,
"step": 282
},
{
"epoch": 0.31,
"learning_rate": 3.274137931034483e-05,
"logits/chosen": 0.03589939698576927,
"logits/rejected": -1.0763846635818481,
"logps/chosen": -394.02056884765625,
"logps/rejected": -567.1450805664062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.877297401428223,
"rewards/margins": 43.63758850097656,
"rewards/rejected": -51.514888763427734,
"step": 283
},
{
"epoch": 0.31,
"learning_rate": 3.26896551724138e-05,
"logits/chosen": -0.042599305510520935,
"logits/rejected": -0.9894676208496094,
"logps/chosen": -390.73968505859375,
"logps/rejected": -588.50244140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.6523871421813965,
"rewards/margins": 41.83343505859375,
"rewards/rejected": -48.48582077026367,
"step": 284
},
{
"epoch": 0.31,
"learning_rate": 3.263793103448276e-05,
"logits/chosen": -0.04844583570957184,
"logits/rejected": -1.3764398097991943,
"logps/chosen": -520.421875,
"logps/rejected": -584.4087524414062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.5111515522003174,
"rewards/margins": 48.571834564208984,
"rewards/rejected": -49.082984924316406,
"step": 285
},
{
"epoch": 0.31,
"learning_rate": 3.2586206896551726e-05,
"logits/chosen": -0.10487770289182663,
"logits/rejected": -1.2500025033950806,
"logps/chosen": -576.0562133789062,
"logps/rejected": -532.1016235351562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.098315238952637,
"rewards/margins": 37.71330261230469,
"rewards/rejected": -45.811614990234375,
"step": 286
},
{
"epoch": 0.31,
"learning_rate": 3.2534482758620694e-05,
"logits/chosen": -0.015081293880939484,
"logits/rejected": -1.127041220664978,
"logps/chosen": -518.3914794921875,
"logps/rejected": -600.3658447265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.67361068725586,
"rewards/margins": 43.359867095947266,
"rewards/rejected": -53.033477783203125,
"step": 287
},
{
"epoch": 0.31,
"learning_rate": 3.2482758620689655e-05,
"logits/chosen": -0.10006409883499146,
"logits/rejected": -0.9317835569381714,
"logps/chosen": -492.3525085449219,
"logps/rejected": -598.6736450195312,
"loss": 0.0192,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.045526504516602,
"rewards/margins": 40.16624450683594,
"rewards/rejected": -48.21177291870117,
"step": 288
},
{
"epoch": 0.32,
"learning_rate": 3.2431034482758623e-05,
"logits/chosen": -0.14413213729858398,
"logits/rejected": -0.8675107955932617,
"logps/chosen": -349.6807556152344,
"logps/rejected": -615.5933227539062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.971858978271484,
"rewards/margins": 42.66694641113281,
"rewards/rejected": -51.63880920410156,
"step": 289
},
{
"epoch": 0.32,
"learning_rate": 3.237931034482759e-05,
"logits/chosen": -0.06418796628713608,
"logits/rejected": -1.261458396911621,
"logps/chosen": -456.44097900390625,
"logps/rejected": -582.775634765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.9118471145629883,
"rewards/margins": 45.231956481933594,
"rewards/rejected": -49.143798828125,
"step": 290
},
{
"epoch": 0.32,
"learning_rate": 3.232758620689655e-05,
"logits/chosen": 0.015173820778727531,
"logits/rejected": -1.3602452278137207,
"logps/chosen": -556.77294921875,
"logps/rejected": -552.7382202148438,
"loss": 0.249,
"rewards/accuracies": 0.9375,
"rewards/chosen": -5.175498008728027,
"rewards/margins": 42.23072052001953,
"rewards/rejected": -47.40621566772461,
"step": 291
},
{
"epoch": 0.32,
"learning_rate": 3.227586206896552e-05,
"logits/chosen": 0.0050443485379219055,
"logits/rejected": -1.1559348106384277,
"logps/chosen": -483.6645812988281,
"logps/rejected": -579.65478515625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.6171573996543884,
"rewards/margins": 46.14912414550781,
"rewards/rejected": -46.76628112792969,
"step": 292
},
{
"epoch": 0.32,
"learning_rate": 3.222413793103449e-05,
"logits/chosen": -0.015672463923692703,
"logits/rejected": -0.8948309421539307,
"logps/chosen": -404.2826843261719,
"logps/rejected": -543.1045532226562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.27553945779800415,
"rewards/margins": 44.960777282714844,
"rewards/rejected": -44.68523406982422,
"step": 293
},
{
"epoch": 0.32,
"learning_rate": 3.217241379310345e-05,
"logits/chosen": -0.0836256816983223,
"logits/rejected": -0.947052538394928,
"logps/chosen": -308.1258850097656,
"logps/rejected": -547.1864013671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.2600884437561035,
"rewards/margins": 40.025543212890625,
"rewards/rejected": -43.28562927246094,
"step": 294
},
{
"epoch": 0.32,
"learning_rate": 3.212068965517242e-05,
"logits/chosen": 0.0691690593957901,
"logits/rejected": -1.4175320863723755,
"logps/chosen": -564.2918701171875,
"logps/rejected": -524.4912719726562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.575163841247559,
"rewards/margins": 46.277183532714844,
"rewards/rejected": -40.70201873779297,
"step": 295
},
{
"epoch": 0.32,
"learning_rate": 3.206896551724138e-05,
"logits/chosen": -0.2818552851676941,
"logits/rejected": -1.078634262084961,
"logps/chosen": -350.2765808105469,
"logps/rejected": -537.8307495117188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.6971882581710815,
"rewards/margins": 41.953392028808594,
"rewards/rejected": -41.256202697753906,
"step": 296
},
{
"epoch": 0.32,
"learning_rate": 3.201724137931035e-05,
"logits/chosen": -0.16628246009349823,
"logits/rejected": -1.2242597341537476,
"logps/chosen": -388.05078125,
"logps/rejected": -504.51910400390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.7080140113830566,
"rewards/margins": 41.291893005371094,
"rewards/rejected": -39.58388137817383,
"step": 297
},
{
"epoch": 0.33,
"learning_rate": 3.196551724137931e-05,
"logits/chosen": -0.13853780925273895,
"logits/rejected": -1.0252296924591064,
"logps/chosen": -358.7446594238281,
"logps/rejected": -497.95281982421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.08794373273849487,
"rewards/margins": 39.5137825012207,
"rewards/rejected": -39.425838470458984,
"step": 298
},
{
"epoch": 0.33,
"learning_rate": 3.1913793103448276e-05,
"logits/chosen": -0.10767735540866852,
"logits/rejected": -1.0644776821136475,
"logps/chosen": -374.3890075683594,
"logps/rejected": -475.7244873046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7640305161476135,
"rewards/margins": 39.74821472167969,
"rewards/rejected": -38.984188079833984,
"step": 299
},
{
"epoch": 0.33,
"learning_rate": 3.1862068965517244e-05,
"logits/chosen": -0.09947740286588669,
"logits/rejected": -1.1763038635253906,
"logps/chosen": -364.96258544921875,
"logps/rejected": -410.973876953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.1341031789779663,
"rewards/margins": 34.35022735595703,
"rewards/rejected": -33.21612548828125,
"step": 300
},
{
"epoch": 0.33,
"learning_rate": 3.1810344827586206e-05,
"logits/chosen": -0.034785281866788864,
"logits/rejected": -1.2451276779174805,
"logps/chosen": -440.1756896972656,
"logps/rejected": -425.47509765625,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.590677261352539,
"rewards/margins": 37.24711990356445,
"rewards/rejected": -33.65644454956055,
"step": 301
},
{
"epoch": 0.33,
"learning_rate": 3.1758620689655174e-05,
"logits/chosen": -0.15350031852722168,
"logits/rejected": -1.0885205268859863,
"logps/chosen": -402.491455078125,
"logps/rejected": -392.4815673828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.4919495582580566,
"rewards/margins": 31.594680786132812,
"rewards/rejected": -28.10272979736328,
"step": 302
},
{
"epoch": 0.33,
"learning_rate": 3.170689655172414e-05,
"logits/chosen": -0.14404729008674622,
"logits/rejected": -1.1483252048492432,
"logps/chosen": -376.1712646484375,
"logps/rejected": -410.5417175292969,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.8741713762283325,
"rewards/margins": 34.73831558227539,
"rewards/rejected": -33.8641471862793,
"step": 303
},
{
"epoch": 0.33,
"learning_rate": 3.16551724137931e-05,
"logits/chosen": -0.19463568925857544,
"logits/rejected": -1.184244155883789,
"logps/chosen": -337.38482666015625,
"logps/rejected": -382.4162292480469,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.7294703722000122,
"rewards/margins": 30.66646957397461,
"rewards/rejected": -28.93699836730957,
"step": 304
},
{
"epoch": 0.33,
"learning_rate": 3.160344827586207e-05,
"logits/chosen": -0.1128799319267273,
"logits/rejected": -1.1655908823013306,
"logps/chosen": -394.9966735839844,
"logps/rejected": -388.04351806640625,
"loss": 0.0024,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.233245849609375,
"rewards/margins": 32.936092376708984,
"rewards/rejected": -30.702844619750977,
"step": 305
},
{
"epoch": 0.33,
"learning_rate": 3.155172413793104e-05,
"logits/chosen": -0.12499256432056427,
"logits/rejected": -1.0794974565505981,
"logps/chosen": -402.0507507324219,
"logps/rejected": -449.8464660644531,
"loss": 0.0965,
"rewards/accuracies": 0.9375,
"rewards/chosen": 0.6880790591239929,
"rewards/margins": 32.26117706298828,
"rewards/rejected": -31.573097229003906,
"step": 306
},
{
"epoch": 0.33,
"learning_rate": 3.15e-05,
"logits/chosen": -0.16316160559654236,
"logits/rejected": -1.1093841791152954,
"logps/chosen": -339.54443359375,
"logps/rejected": -498.3818664550781,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.30418586730957,
"rewards/margins": 36.54359436035156,
"rewards/rejected": -40.84778594970703,
"step": 307
},
{
"epoch": 0.34,
"learning_rate": 3.144827586206897e-05,
"logits/chosen": 0.031052295118570328,
"logits/rejected": -1.198643684387207,
"logps/chosen": -394.73394775390625,
"logps/rejected": -528.90966796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.43565046787261963,
"rewards/margins": 45.74468231201172,
"rewards/rejected": -46.180335998535156,
"step": 308
},
{
"epoch": 0.34,
"learning_rate": 3.1396551724137936e-05,
"logits/chosen": -0.05930813029408455,
"logits/rejected": -1.2569350004196167,
"logps/chosen": -515.5428466796875,
"logps/rejected": -561.1205444335938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.4287011623382568,
"rewards/margins": 46.44762420654297,
"rewards/rejected": -45.0189208984375,
"step": 309
},
{
"epoch": 0.34,
"learning_rate": 3.13448275862069e-05,
"logits/chosen": 0.14158597588539124,
"logits/rejected": -1.1525517702102661,
"logps/chosen": -493.8555603027344,
"logps/rejected": -557.8233642578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.293236255645752,
"rewards/margins": 44.08985137939453,
"rewards/rejected": -46.38308334350586,
"step": 310
},
{
"epoch": 0.34,
"learning_rate": 3.1293103448275865e-05,
"logits/chosen": -0.13309258222579956,
"logits/rejected": -1.1186158657073975,
"logps/chosen": -478.7046203613281,
"logps/rejected": -570.7393798828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.5453602075576782,
"rewards/margins": 45.14695739746094,
"rewards/rejected": -45.692317962646484,
"step": 311
},
{
"epoch": 0.34,
"learning_rate": 3.124137931034483e-05,
"logits/chosen": 0.05075529217720032,
"logits/rejected": -1.1768913269042969,
"logps/chosen": -471.7716064453125,
"logps/rejected": -529.3003540039062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.3143967390060425,
"rewards/margins": 44.80303192138672,
"rewards/rejected": -43.48863220214844,
"step": 312
},
{
"epoch": 0.34,
"learning_rate": 3.1189655172413794e-05,
"logits/chosen": 0.08374657481908798,
"logits/rejected": -1.1194422245025635,
"logps/chosen": -453.62115478515625,
"logps/rejected": -556.13232421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.535671591758728,
"rewards/margins": 45.361289978027344,
"rewards/rejected": -45.89696502685547,
"step": 313
},
{
"epoch": 0.34,
"learning_rate": 3.113793103448276e-05,
"logits/chosen": -0.18719206750392914,
"logits/rejected": -1.005627989768982,
"logps/chosen": -429.99652099609375,
"logps/rejected": -530.39697265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.788636207580566,
"rewards/margins": 38.725555419921875,
"rewards/rejected": -45.51419448852539,
"step": 314
},
{
"epoch": 0.34,
"learning_rate": 3.1086206896551724e-05,
"logits/chosen": -0.058684833347797394,
"logits/rejected": -1.0559102296829224,
"logps/chosen": -467.2474365234375,
"logps/rejected": -530.8262939453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.27678483724594116,
"rewards/margins": 44.17549133300781,
"rewards/rejected": -44.45227813720703,
"step": 315
},
{
"epoch": 0.34,
"learning_rate": 3.103448275862069e-05,
"logits/chosen": -0.19090279936790466,
"logits/rejected": -0.876602053642273,
"logps/chosen": -315.1255187988281,
"logps/rejected": -588.2965698242188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.501945495605469,
"rewards/margins": 45.68769073486328,
"rewards/rejected": -51.18963623046875,
"step": 316
},
{
"epoch": 0.35,
"learning_rate": 3.098275862068965e-05,
"logits/chosen": -0.10631687939167023,
"logits/rejected": -1.1011039018630981,
"logps/chosen": -434.1145935058594,
"logps/rejected": -521.3406982421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.0800139904022217,
"rewards/margins": 44.002647399902344,
"rewards/rejected": -45.08266067504883,
"step": 317
},
{
"epoch": 0.35,
"learning_rate": 3.093103448275862e-05,
"logits/chosen": -0.03321276232600212,
"logits/rejected": -1.3932230472564697,
"logps/chosen": -575.6842651367188,
"logps/rejected": -527.6025390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.441707968711853,
"rewards/margins": 43.618465423583984,
"rewards/rejected": -43.176753997802734,
"step": 318
},
{
"epoch": 0.35,
"learning_rate": 3.087931034482759e-05,
"logits/chosen": -0.139996737241745,
"logits/rejected": -1.3197453022003174,
"logps/chosen": -504.41864013671875,
"logps/rejected": -563.311767578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.6999825835227966,
"rewards/margins": 47.611934661865234,
"rewards/rejected": -48.31192398071289,
"step": 319
},
{
"epoch": 0.35,
"learning_rate": 3.082758620689655e-05,
"logits/chosen": -0.126600980758667,
"logits/rejected": -1.053550362586975,
"logps/chosen": -388.8297119140625,
"logps/rejected": -544.5347290039062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.8857545852661133,
"rewards/margins": 43.31074523925781,
"rewards/rejected": -46.196502685546875,
"step": 320
},
{
"epoch": 0.35,
"learning_rate": 3.077586206896552e-05,
"logits/chosen": -0.3051377832889557,
"logits/rejected": -1.2079377174377441,
"logps/chosen": -376.6958923339844,
"logps/rejected": -553.730224609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.7709710597991943,
"rewards/margins": 44.744571685791016,
"rewards/rejected": -46.515541076660156,
"step": 321
},
{
"epoch": 0.35,
"learning_rate": 3.0724137931034486e-05,
"logits/chosen": -0.18020763993263245,
"logits/rejected": -1.040939211845398,
"logps/chosen": -332.655029296875,
"logps/rejected": -551.4888916015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.484922409057617,
"rewards/margins": 42.93204879760742,
"rewards/rejected": -47.41697311401367,
"step": 322
},
{
"epoch": 0.35,
"learning_rate": 3.067241379310345e-05,
"logits/chosen": -0.2714073061943054,
"logits/rejected": -1.1973769664764404,
"logps/chosen": -468.3298645019531,
"logps/rejected": -537.9442749023438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.890547752380371,
"rewards/margins": 40.39543151855469,
"rewards/rejected": -46.285980224609375,
"step": 323
},
{
"epoch": 0.35,
"learning_rate": 3.0620689655172415e-05,
"logits/chosen": -0.055039308965206146,
"logits/rejected": -0.961100697517395,
"logps/chosen": -479.1692810058594,
"logps/rejected": -544.91259765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.017467498779297,
"rewards/margins": 37.9600944519043,
"rewards/rejected": -42.977561950683594,
"step": 324
},
{
"epoch": 0.35,
"learning_rate": 3.056896551724138e-05,
"logits/chosen": -0.09231775254011154,
"logits/rejected": -0.9333654046058655,
"logps/chosen": -383.6116943359375,
"logps/rejected": -508.18865966796875,
"loss": 0.0358,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.502808094024658,
"rewards/margins": 34.478755950927734,
"rewards/rejected": -41.981563568115234,
"step": 325
},
{
"epoch": 0.36,
"learning_rate": 3.0517241379310344e-05,
"logits/chosen": -0.15142463147640228,
"logits/rejected": -0.8942531943321228,
"logps/chosen": -362.30755615234375,
"logps/rejected": -582.6021728515625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.6099252700805664,
"rewards/margins": 42.51545715332031,
"rewards/rejected": -46.12538528442383,
"step": 326
},
{
"epoch": 0.36,
"learning_rate": 3.0465517241379312e-05,
"logits/chosen": -0.0636628121137619,
"logits/rejected": -1.1498801708221436,
"logps/chosen": -452.0404052734375,
"logps/rejected": -537.0067138671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.492896556854248,
"rewards/margins": 41.51354217529297,
"rewards/rejected": -44.00643539428711,
"step": 327
},
{
"epoch": 0.36,
"learning_rate": 3.0413793103448277e-05,
"logits/chosen": -0.3045711815357208,
"logits/rejected": -1.0503120422363281,
"logps/chosen": -339.1358642578125,
"logps/rejected": -538.6072998046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.034678369760513306,
"rewards/margins": 42.621681213378906,
"rewards/rejected": -42.65635681152344,
"step": 328
},
{
"epoch": 0.36,
"learning_rate": 3.0362068965517245e-05,
"logits/chosen": -0.175112783908844,
"logits/rejected": -1.0160049200057983,
"logps/chosen": -369.64373779296875,
"logps/rejected": -531.3986206054688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.621337890625,
"rewards/margins": 38.97738265991211,
"rewards/rejected": -44.598716735839844,
"step": 329
},
{
"epoch": 0.36,
"learning_rate": 3.0310344827586206e-05,
"logits/chosen": -0.0202659722417593,
"logits/rejected": -1.1052290201187134,
"logps/chosen": -492.6905822753906,
"logps/rejected": -529.3641357421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.384145259857178,
"rewards/margins": 37.67775344848633,
"rewards/rejected": -42.06189727783203,
"step": 330
},
{
"epoch": 0.36,
"learning_rate": 3.0258620689655174e-05,
"logits/chosen": -0.16101710498332977,
"logits/rejected": -1.336228370666504,
"logps/chosen": -614.8682250976562,
"logps/rejected": -522.0177612304688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.8445982933044434,
"rewards/margins": 38.63414764404297,
"rewards/rejected": -42.47874450683594,
"step": 331
},
{
"epoch": 0.36,
"learning_rate": 3.0206896551724142e-05,
"logits/chosen": -0.09683067351579666,
"logits/rejected": -0.8590956926345825,
"logps/chosen": -291.6666564941406,
"logps/rejected": -464.15509033203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.470726728439331,
"rewards/margins": 34.38860321044922,
"rewards/rejected": -37.85932922363281,
"step": 332
},
{
"epoch": 0.36,
"learning_rate": 3.0155172413793104e-05,
"logits/chosen": -0.125202476978302,
"logits/rejected": -1.1684645414352417,
"logps/chosen": -504.86669921875,
"logps/rejected": -515.8795776367188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.095594882965088,
"rewards/margins": 34.49415969848633,
"rewards/rejected": -39.589752197265625,
"step": 333
},
{
"epoch": 0.36,
"learning_rate": 3.010344827586207e-05,
"logits/chosen": -0.10065445303916931,
"logits/rejected": -1.05722177028656,
"logps/chosen": -409.2242736816406,
"logps/rejected": -541.786376953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.751873254776001,
"rewards/margins": 41.32733917236328,
"rewards/rejected": -44.0792121887207,
"step": 334
},
{
"epoch": 0.37,
"learning_rate": 3.005172413793104e-05,
"logits/chosen": -0.25555816292762756,
"logits/rejected": -0.9541343450546265,
"logps/chosen": -296.4285888671875,
"logps/rejected": -459.89288330078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.3731026649475098,
"rewards/margins": 32.92158889770508,
"rewards/rejected": -36.29469299316406,
"step": 335
},
{
"epoch": 0.37,
"learning_rate": 3e-05,
"logits/chosen": -0.21287637948989868,
"logits/rejected": -1.1649916172027588,
"logps/chosen": -414.73040771484375,
"logps/rejected": -463.68597412109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.076710224151611,
"rewards/margins": 33.77467727661133,
"rewards/rejected": -37.851383209228516,
"step": 336
},
{
"epoch": 0.37,
"learning_rate": 2.994827586206897e-05,
"logits/chosen": -0.07227441668510437,
"logits/rejected": -1.0752284526824951,
"logps/chosen": -487.4039001464844,
"logps/rejected": -503.8778076171875,
"loss": 0.0008,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.989980697631836,
"rewards/margins": 36.903316497802734,
"rewards/rejected": -40.89329528808594,
"step": 337
},
{
"epoch": 0.37,
"learning_rate": 2.9896551724137933e-05,
"logits/chosen": -0.12217733263969421,
"logits/rejected": -0.9584940075874329,
"logps/chosen": -344.06573486328125,
"logps/rejected": -557.3684692382812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.471970558166504,
"rewards/margins": 41.59339141845703,
"rewards/rejected": -46.06536102294922,
"step": 338
},
{
"epoch": 0.37,
"learning_rate": 2.9844827586206898e-05,
"logits/chosen": 0.02000473439693451,
"logits/rejected": -1.2773916721343994,
"logps/chosen": -457.06158447265625,
"logps/rejected": -545.4772338867188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.6830273866653442,
"rewards/margins": 48.27865982055664,
"rewards/rejected": -47.59563064575195,
"step": 339
},
{
"epoch": 0.37,
"learning_rate": 2.9793103448275863e-05,
"logits/chosen": 0.009161004796624184,
"logits/rejected": -1.1769722700119019,
"logps/chosen": -514.1297607421875,
"logps/rejected": -524.6531982421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.6481988430023193,
"rewards/margins": 40.810298919677734,
"rewards/rejected": -43.45849609375,
"step": 340
},
{
"epoch": 0.37,
"learning_rate": 2.974137931034483e-05,
"logits/chosen": -0.07262174040079117,
"logits/rejected": -1.0641191005706787,
"logps/chosen": -353.1182861328125,
"logps/rejected": -554.7969970703125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.7675700187683105,
"rewards/margins": 41.664825439453125,
"rewards/rejected": -45.432395935058594,
"step": 341
},
{
"epoch": 0.37,
"learning_rate": 2.9689655172413792e-05,
"logits/chosen": -0.1689426451921463,
"logits/rejected": -1.1683162450790405,
"logps/chosen": -441.01202392578125,
"logps/rejected": -631.0665893554688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.520883083343506,
"rewards/margins": 47.718502044677734,
"rewards/rejected": -53.2393798828125,
"step": 342
},
{
"epoch": 0.37,
"learning_rate": 2.963793103448276e-05,
"logits/chosen": -0.02344764769077301,
"logits/rejected": -1.1594109535217285,
"logps/chosen": -453.4601135253906,
"logps/rejected": -522.5077514648438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.1243491172790527,
"rewards/margins": 41.7907600402832,
"rewards/rejected": -44.91510772705078,
"step": 343
},
{
"epoch": 0.38,
"learning_rate": 2.9586206896551728e-05,
"logits/chosen": -0.01729479804635048,
"logits/rejected": -1.094846248626709,
"logps/chosen": -427.6337890625,
"logps/rejected": -603.2669067382812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.31561219692230225,
"rewards/margins": 49.68363952636719,
"rewards/rejected": -49.36802673339844,
"step": 344
},
{
"epoch": 0.38,
"learning_rate": 2.9534482758620692e-05,
"logits/chosen": -0.12101568281650543,
"logits/rejected": -1.2158620357513428,
"logps/chosen": -491.6488342285156,
"logps/rejected": -572.5497436523438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.2570481300354004,
"rewards/margins": 51.22979736328125,
"rewards/rejected": -47.972747802734375,
"step": 345
},
{
"epoch": 0.38,
"learning_rate": 2.9482758620689657e-05,
"logits/chosen": -0.009567921981215477,
"logits/rejected": -1.029674768447876,
"logps/chosen": -377.886962890625,
"logps/rejected": -559.27294921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.400155544281006,
"rewards/margins": 41.55246353149414,
"rewards/rejected": -46.9526252746582,
"step": 346
},
{
"epoch": 0.38,
"learning_rate": 2.943103448275862e-05,
"logits/chosen": -0.005190672352910042,
"logits/rejected": -1.157238483428955,
"logps/chosen": -438.5839538574219,
"logps/rejected": -551.5087890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.0165094137191772,
"rewards/margins": 45.29164505004883,
"rewards/rejected": -44.27513885498047,
"step": 347
},
{
"epoch": 0.38,
"learning_rate": 2.937931034482759e-05,
"logits/chosen": -0.10370245575904846,
"logits/rejected": -1.1599996089935303,
"logps/chosen": -553.7239379882812,
"logps/rejected": -591.9037475585938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.530036449432373,
"rewards/margins": 49.52385330200195,
"rewards/rejected": -46.99381637573242,
"step": 348
},
{
"epoch": 0.38,
"learning_rate": 2.932758620689655e-05,
"logits/chosen": 0.012315813452005386,
"logits/rejected": -1.1227484941482544,
"logps/chosen": -420.30572509765625,
"logps/rejected": -541.201171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.01237416267395,
"rewards/margins": 42.71653747558594,
"rewards/rejected": -44.72890853881836,
"step": 349
},
{
"epoch": 0.38,
"learning_rate": 2.927586206896552e-05,
"logits/chosen": -0.19439992308616638,
"logits/rejected": -1.0316534042358398,
"logps/chosen": -284.17578125,
"logps/rejected": -527.9844970703125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.887413024902344,
"rewards/margins": 37.930118560791016,
"rewards/rejected": -45.817535400390625,
"step": 350
},
{
"epoch": 0.38,
"learning_rate": 2.9224137931034487e-05,
"logits/chosen": -0.06830094754695892,
"logits/rejected": -1.3009464740753174,
"logps/chosen": -437.2919006347656,
"logps/rejected": -561.503662109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.028534173965454,
"rewards/margins": 46.798194885253906,
"rewards/rejected": -45.76966094970703,
"step": 351
},
{
"epoch": 0.38,
"learning_rate": 2.9172413793103448e-05,
"logits/chosen": 0.03125571832060814,
"logits/rejected": -1.259416937828064,
"logps/chosen": -436.17852783203125,
"logps/rejected": -551.797119140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.8364152908325195,
"rewards/margins": 48.23833465576172,
"rewards/rejected": -47.401920318603516,
"step": 352
},
{
"epoch": 0.39,
"learning_rate": 2.9120689655172416e-05,
"logits/chosen": 0.0014629308134317398,
"logits/rejected": -1.458472490310669,
"logps/chosen": -554.6463623046875,
"logps/rejected": -531.5646362304688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.006325721740723,
"rewards/margins": 50.37799072265625,
"rewards/rejected": -45.371665954589844,
"step": 353
},
{
"epoch": 0.39,
"learning_rate": 2.9068965517241384e-05,
"logits/chosen": -0.16050775349140167,
"logits/rejected": -0.8299065828323364,
"logps/chosen": -335.6762390136719,
"logps/rejected": -590.0164184570312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.606829643249512,
"rewards/margins": 43.23134994506836,
"rewards/rejected": -47.83818054199219,
"step": 354
},
{
"epoch": 0.39,
"learning_rate": 2.9017241379310345e-05,
"logits/chosen": -0.07219342142343521,
"logits/rejected": -0.9463921189308167,
"logps/chosen": -391.2060852050781,
"logps/rejected": -568.3679809570312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.065673828125,
"rewards/margins": 41.32851028442383,
"rewards/rejected": -43.39418411254883,
"step": 355
},
{
"epoch": 0.39,
"learning_rate": 2.8965517241379313e-05,
"logits/chosen": -0.04772268235683441,
"logits/rejected": -1.164974570274353,
"logps/chosen": -408.1875,
"logps/rejected": -565.4370727539062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.738417387008667,
"rewards/margins": 45.41836929321289,
"rewards/rejected": -49.15678787231445,
"step": 356
},
{
"epoch": 0.39,
"learning_rate": 2.8913793103448278e-05,
"logits/chosen": -0.026131443679332733,
"logits/rejected": -1.257594108581543,
"logps/chosen": -436.87200927734375,
"logps/rejected": -602.8794555664062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.374298095703125,
"rewards/margins": 48.57533645629883,
"rewards/rejected": -48.94963073730469,
"step": 357
},
{
"epoch": 0.39,
"learning_rate": 2.8862068965517243e-05,
"logits/chosen": 0.04897276684641838,
"logits/rejected": -1.1252198219299316,
"logps/chosen": -406.7869873046875,
"logps/rejected": -565.0485229492188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.1319797039031982,
"rewards/margins": 45.98715591430664,
"rewards/rejected": -48.119140625,
"step": 358
},
{
"epoch": 0.39,
"learning_rate": 2.8810344827586207e-05,
"logits/chosen": -0.05338538438081741,
"logits/rejected": -1.0763384103775024,
"logps/chosen": -355.9891662597656,
"logps/rejected": -621.0955200195312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.576101779937744,
"rewards/margins": 49.743812561035156,
"rewards/rejected": -52.319915771484375,
"step": 359
},
{
"epoch": 0.39,
"learning_rate": 2.8758620689655175e-05,
"logits/chosen": -0.18446527421474457,
"logits/rejected": -1.0962433815002441,
"logps/chosen": -393.23675537109375,
"logps/rejected": -607.602783203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.4161076545715332,
"rewards/margins": 50.76775360107422,
"rewards/rejected": -51.183860778808594,
"step": 360
},
{
"epoch": 0.39,
"learning_rate": 2.8706896551724143e-05,
"logits/chosen": -0.12225188314914703,
"logits/rejected": -1.0412880182266235,
"logps/chosen": -375.52166748046875,
"logps/rejected": -589.2161865234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.385780930519104,
"rewards/margins": 49.27238464355469,
"rewards/rejected": -49.65816879272461,
"step": 361
},
{
"epoch": 0.39,
"learning_rate": 2.8655172413793104e-05,
"logits/chosen": -0.20962819457054138,
"logits/rejected": -1.0904340744018555,
"logps/chosen": -395.50238037109375,
"logps/rejected": -568.0843505859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.58205509185791,
"rewards/margins": 40.50846862792969,
"rewards/rejected": -47.09052276611328,
"step": 362
},
{
"epoch": 0.4,
"learning_rate": 2.8603448275862072e-05,
"logits/chosen": 0.003986477851867676,
"logits/rejected": -1.0085983276367188,
"logps/chosen": -438.2725830078125,
"logps/rejected": -592.7444458007812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.6302861571311951,
"rewards/margins": 51.214351654052734,
"rewards/rejected": -50.58406066894531,
"step": 363
},
{
"epoch": 0.4,
"learning_rate": 2.8551724137931037e-05,
"logits/chosen": -0.04182690009474754,
"logits/rejected": -1.2840299606323242,
"logps/chosen": -501.47357177734375,
"logps/rejected": -599.254638671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.2677664756774902,
"rewards/margins": 47.65995407104492,
"rewards/rejected": -44.39219665527344,
"step": 364
},
{
"epoch": 0.4,
"learning_rate": 2.85e-05,
"logits/chosen": 0.07004736363887787,
"logits/rejected": -1.3011246919631958,
"logps/chosen": -511.8918762207031,
"logps/rejected": -555.033447265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.474068641662598,
"rewards/margins": 51.881038665771484,
"rewards/rejected": -47.40697479248047,
"step": 365
},
{
"epoch": 0.4,
"learning_rate": 2.8448275862068966e-05,
"logits/chosen": -0.03457900136709213,
"logits/rejected": -1.2160018682479858,
"logps/chosen": -474.7510070800781,
"logps/rejected": -588.1536865234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.557379722595215,
"rewards/margins": 54.3979606628418,
"rewards/rejected": -49.840576171875,
"step": 366
},
{
"epoch": 0.4,
"learning_rate": 2.8396551724137934e-05,
"logits/chosen": 0.02054227888584137,
"logits/rejected": -1.1687372922897339,
"logps/chosen": -407.9102478027344,
"logps/rejected": -534.5169067382812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.0955076217651367,
"rewards/margins": 40.78862762451172,
"rewards/rejected": -39.693119049072266,
"step": 367
},
{
"epoch": 0.4,
"learning_rate": 2.8344827586206895e-05,
"logits/chosen": 0.07716276496648788,
"logits/rejected": -0.8440214395523071,
"logps/chosen": -330.560546875,
"logps/rejected": -596.030517578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.727421283721924,
"rewards/margins": 46.38547897338867,
"rewards/rejected": -51.1129035949707,
"step": 368
},
{
"epoch": 0.4,
"learning_rate": 2.8293103448275863e-05,
"logits/chosen": 0.014307685196399689,
"logits/rejected": -1.3238158226013184,
"logps/chosen": -495.6667175292969,
"logps/rejected": -584.3401489257812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.3049987554550171,
"rewards/margins": 48.27531051635742,
"rewards/rejected": -48.58030700683594,
"step": 369
},
{
"epoch": 0.4,
"learning_rate": 2.824137931034483e-05,
"logits/chosen": 0.07619799673557281,
"logits/rejected": -1.2337863445281982,
"logps/chosen": -568.0042724609375,
"logps/rejected": -586.55908203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.8983986377716064,
"rewards/margins": 50.09109878540039,
"rewards/rejected": -49.19269561767578,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 2.8189655172413793e-05,
"logits/chosen": 0.030935000628232956,
"logits/rejected": -1.1124335527420044,
"logps/chosen": -389.4969177246094,
"logps/rejected": -559.1497802734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.30449792742729187,
"rewards/margins": 44.675933837890625,
"rewards/rejected": -44.98043441772461,
"step": 371
},
{
"epoch": 0.41,
"learning_rate": 2.813793103448276e-05,
"logits/chosen": -0.09724840521812439,
"logits/rejected": -1.4216426610946655,
"logps/chosen": -487.3270568847656,
"logps/rejected": -557.8433227539062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7180730104446411,
"rewards/margins": 47.800254821777344,
"rewards/rejected": -47.082183837890625,
"step": 372
},
{
"epoch": 0.41,
"learning_rate": 2.808620689655173e-05,
"logits/chosen": 0.06473588198423386,
"logits/rejected": -1.2265748977661133,
"logps/chosen": -457.49407958984375,
"logps/rejected": -584.40966796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.494109630584717,
"rewards/margins": 47.470645904541016,
"rewards/rejected": -49.964752197265625,
"step": 373
},
{
"epoch": 0.41,
"learning_rate": 2.803448275862069e-05,
"logits/chosen": 0.09420200437307358,
"logits/rejected": -1.1941781044006348,
"logps/chosen": -537.9132080078125,
"logps/rejected": -560.3892211914062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.515617609024048,
"rewards/margins": 48.64773178100586,
"rewards/rejected": -46.132110595703125,
"step": 374
},
{
"epoch": 0.41,
"learning_rate": 2.7982758620689658e-05,
"logits/chosen": -0.2046179175376892,
"logits/rejected": -1.214766025543213,
"logps/chosen": -473.283447265625,
"logps/rejected": -613.4475708007812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.620456218719482,
"rewards/margins": 57.01899719238281,
"rewards/rejected": -51.39854431152344,
"step": 375
},
{
"epoch": 0.41,
"learning_rate": 2.7931034482758622e-05,
"logits/chosen": -0.0699472650885582,
"logits/rejected": -1.3432188034057617,
"logps/chosen": -434.32293701171875,
"logps/rejected": -562.9783325195312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.728281021118164,
"rewards/margins": 44.719356536865234,
"rewards/rejected": -49.447635650634766,
"step": 376
},
{
"epoch": 0.41,
"learning_rate": 2.787931034482759e-05,
"logits/chosen": -0.01713864505290985,
"logits/rejected": -0.9077965021133423,
"logps/chosen": -345.4331970214844,
"logps/rejected": -560.2376098632812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.396304607391357,
"rewards/margins": 39.71217727661133,
"rewards/rejected": -44.108482360839844,
"step": 377
},
{
"epoch": 0.41,
"learning_rate": 2.782758620689655e-05,
"logits/chosen": 0.001452295109629631,
"logits/rejected": -1.2449791431427002,
"logps/chosen": -455.90850830078125,
"logps/rejected": -564.8043212890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.484553575515747,
"rewards/margins": 45.819183349609375,
"rewards/rejected": -48.303741455078125,
"step": 378
},
{
"epoch": 0.41,
"learning_rate": 2.777586206896552e-05,
"logits/chosen": 0.04156869277358055,
"logits/rejected": -1.0869159698486328,
"logps/chosen": -431.6122741699219,
"logps/rejected": -553.697021484375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.3313959836959839,
"rewards/margins": 44.75462341308594,
"rewards/rejected": -44.42322540283203,
"step": 379
},
{
"epoch": 0.41,
"learning_rate": 2.7724137931034488e-05,
"logits/chosen": 0.0004380419850349426,
"logits/rejected": -1.0738462209701538,
"logps/chosen": -392.25018310546875,
"logps/rejected": -583.8248901367188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.7267297506332397,
"rewards/margins": 48.91001892089844,
"rewards/rejected": -50.63674545288086,
"step": 380
},
{
"epoch": 0.42,
"learning_rate": 2.767241379310345e-05,
"logits/chosen": -0.05203678458929062,
"logits/rejected": -0.9276233315467834,
"logps/chosen": -341.73779296875,
"logps/rejected": -574.5068359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.9113528728485107,
"rewards/margins": 48.13732147216797,
"rewards/rejected": -51.048675537109375,
"step": 381
},
{
"epoch": 0.42,
"learning_rate": 2.7620689655172417e-05,
"logits/chosen": 0.12498117983341217,
"logits/rejected": -1.2847096920013428,
"logps/chosen": -471.0482177734375,
"logps/rejected": -578.107177734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.4137356281280518,
"rewards/margins": 51.37191390991211,
"rewards/rejected": -48.95817565917969,
"step": 382
},
{
"epoch": 0.42,
"learning_rate": 2.756896551724138e-05,
"logits/chosen": -0.15520095825195312,
"logits/rejected": -1.0619099140167236,
"logps/chosen": -404.9841613769531,
"logps/rejected": -578.9855346679688,
"loss": 0.0194,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.767134666442871,
"rewards/margins": 47.32525634765625,
"rewards/rejected": -51.09239196777344,
"step": 383
},
{
"epoch": 0.42,
"learning_rate": 2.7517241379310346e-05,
"logits/chosen": 0.04274128004908562,
"logits/rejected": -1.1932741403579712,
"logps/chosen": -418.20404052734375,
"logps/rejected": -512.047607421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.06832236051559448,
"rewards/margins": 44.48112487792969,
"rewards/rejected": -44.412803649902344,
"step": 384
},
{
"epoch": 0.42,
"learning_rate": 2.746551724137931e-05,
"logits/chosen": 0.01695055142045021,
"logits/rejected": -1.1045211553573608,
"logps/chosen": -367.1639404296875,
"logps/rejected": -537.3077392578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.1754894256591797,
"rewards/margins": 43.70709991455078,
"rewards/rejected": -43.882591247558594,
"step": 385
},
{
"epoch": 0.42,
"learning_rate": 2.741379310344828e-05,
"logits/chosen": 0.12017740309238434,
"logits/rejected": -1.0955898761749268,
"logps/chosen": -463.5010986328125,
"logps/rejected": -543.324462890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.6687986850738525,
"rewards/margins": 46.83396911621094,
"rewards/rejected": -44.16516876220703,
"step": 386
},
{
"epoch": 0.42,
"learning_rate": 2.736206896551724e-05,
"logits/chosen": -0.07626432925462723,
"logits/rejected": -1.0542856454849243,
"logps/chosen": -368.75933837890625,
"logps/rejected": -546.5941772460938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.629738450050354,
"rewards/margins": 47.353370666503906,
"rewards/rejected": -46.7236328125,
"step": 387
},
{
"epoch": 0.42,
"learning_rate": 2.7310344827586208e-05,
"logits/chosen": -0.039779115468263626,
"logits/rejected": -1.3472245931625366,
"logps/chosen": -466.123779296875,
"logps/rejected": -488.5738525390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.2881481647491455,
"rewards/margins": 40.72649383544922,
"rewards/rejected": -40.4383430480957,
"step": 388
},
{
"epoch": 0.42,
"learning_rate": 2.7258620689655176e-05,
"logits/chosen": -0.033790040761232376,
"logits/rejected": -1.141743779182434,
"logps/chosen": -403.8807067871094,
"logps/rejected": -495.78570556640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.32837265729904175,
"rewards/margins": 38.956748962402344,
"rewards/rejected": -39.285118103027344,
"step": 389
},
{
"epoch": 0.43,
"learning_rate": 2.7206896551724137e-05,
"logits/chosen": -0.015193854458630085,
"logits/rejected": -1.3545093536376953,
"logps/chosen": -489.96087646484375,
"logps/rejected": -515.5687866210938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.122744560241699,
"rewards/margins": 52.13509750366211,
"rewards/rejected": -46.012351989746094,
"step": 390
},
{
"epoch": 0.43,
"learning_rate": 2.7155172413793105e-05,
"logits/chosen": 0.02489817887544632,
"logits/rejected": -0.991384744644165,
"logps/chosen": -390.23370361328125,
"logps/rejected": -568.0363159179688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.53804612159729,
"rewards/margins": 42.114593505859375,
"rewards/rejected": -42.652645111083984,
"step": 391
},
{
"epoch": 0.43,
"learning_rate": 2.7103448275862073e-05,
"logits/chosen": -0.15990671515464783,
"logits/rejected": -0.9720957279205322,
"logps/chosen": -299.734619140625,
"logps/rejected": -480.4046630859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.4684109687805176,
"rewards/margins": 39.979103088378906,
"rewards/rejected": -40.447513580322266,
"step": 392
},
{
"epoch": 0.43,
"learning_rate": 2.7051724137931038e-05,
"logits/chosen": -0.03375757485628128,
"logits/rejected": -1.021787166595459,
"logps/chosen": -322.0400390625,
"logps/rejected": -487.57537841796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.355576753616333,
"rewards/margins": 44.75249481201172,
"rewards/rejected": -42.39692306518555,
"step": 393
},
{
"epoch": 0.43,
"learning_rate": 2.7000000000000002e-05,
"logits/chosen": -0.020571894943714142,
"logits/rejected": -1.2173579931259155,
"logps/chosen": -417.3011169433594,
"logps/rejected": -449.94512939453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.091635227203369,
"rewards/margins": 37.5725212097168,
"rewards/rejected": -34.48088455200195,
"step": 394
},
{
"epoch": 0.43,
"learning_rate": 2.6948275862068967e-05,
"logits/chosen": 0.026321958750486374,
"logits/rejected": -0.9667563438415527,
"logps/chosen": -341.38720703125,
"logps/rejected": -466.8248291015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.7460142374038696,
"rewards/margins": 40.34065628051758,
"rewards/rejected": -38.594642639160156,
"step": 395
},
{
"epoch": 0.43,
"learning_rate": 2.6896551724137935e-05,
"logits/chosen": -0.08959555625915527,
"logits/rejected": -1.1910420656204224,
"logps/chosen": -381.2998962402344,
"logps/rejected": -472.2957763671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.0525035858154297,
"rewards/margins": 42.368186950683594,
"rewards/rejected": -40.31568145751953,
"step": 396
},
{
"epoch": 0.43,
"learning_rate": 2.6844827586206896e-05,
"logits/chosen": -0.17987710237503052,
"logits/rejected": -1.02032470703125,
"logps/chosen": -298.4346923828125,
"logps/rejected": -471.966552734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.6901694536209106,
"rewards/margins": 35.03578567504883,
"rewards/rejected": -36.725955963134766,
"step": 397
},
{
"epoch": 0.43,
"learning_rate": 2.6793103448275864e-05,
"logits/chosen": -0.20967192947864532,
"logits/rejected": -0.9511845707893372,
"logps/chosen": -299.4791564941406,
"logps/rejected": -455.33782958984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.385829448699951,
"rewards/margins": 37.45805358886719,
"rewards/rejected": -35.07223129272461,
"step": 398
},
{
"epoch": 0.44,
"learning_rate": 2.6741379310344832e-05,
"logits/chosen": -0.01965043693780899,
"logits/rejected": -1.0445890426635742,
"logps/chosen": -275.1196594238281,
"logps/rejected": -483.07647705078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.6957775354385376,
"rewards/margins": 38.007179260253906,
"rewards/rejected": -39.70295715332031,
"step": 399
},
{
"epoch": 0.44,
"learning_rate": 2.6689655172413793e-05,
"logits/chosen": -0.098607636988163,
"logits/rejected": -1.0000914335250854,
"logps/chosen": -346.13018798828125,
"logps/rejected": -495.4217224121094,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.0000643730163574,
"rewards/margins": 42.866764068603516,
"rewards/rejected": -39.866703033447266,
"step": 400
},
{
"epoch": 0.44,
"learning_rate": 2.663793103448276e-05,
"logits/chosen": 0.1724672019481659,
"logits/rejected": -1.2024016380310059,
"logps/chosen": -505.9283752441406,
"logps/rejected": -510.1684875488281,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.5972766876220703,
"rewards/margins": 42.12846755981445,
"rewards/rejected": -40.531192779541016,
"step": 401
},
{
"epoch": 0.44,
"learning_rate": 2.6586206896551726e-05,
"logits/chosen": -0.1967574805021286,
"logits/rejected": -1.045470952987671,
"logps/chosen": -335.9580993652344,
"logps/rejected": -520.8634643554688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.14454174041748047,
"rewards/margins": 41.4933967590332,
"rewards/rejected": -41.637939453125,
"step": 402
},
{
"epoch": 0.44,
"learning_rate": 2.653448275862069e-05,
"logits/chosen": 0.11029797792434692,
"logits/rejected": -1.4310297966003418,
"logps/chosen": -571.0155029296875,
"logps/rejected": -496.65087890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 9.46963119506836,
"rewards/margins": 48.58985900878906,
"rewards/rejected": -39.12022399902344,
"step": 403
},
{
"epoch": 0.44,
"learning_rate": 2.6482758620689655e-05,
"logits/chosen": 0.030145570635795593,
"logits/rejected": -1.0499293804168701,
"logps/chosen": -399.5472717285156,
"logps/rejected": -472.23272705078125,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.7181732654571533,
"rewards/margins": 40.335968017578125,
"rewards/rejected": -37.617794036865234,
"step": 404
},
{
"epoch": 0.44,
"learning_rate": 2.6431034482758623e-05,
"logits/chosen": -0.17437051236629486,
"logits/rejected": -0.8545927405357361,
"logps/chosen": -317.4663391113281,
"logps/rejected": -524.6553955078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.37684276700019836,
"rewards/margins": 39.592159271240234,
"rewards/rejected": -39.96900177001953,
"step": 405
},
{
"epoch": 0.44,
"learning_rate": 2.6379310344827584e-05,
"logits/chosen": -0.2994159460067749,
"logits/rejected": -1.063322901725769,
"logps/chosen": -286.9337158203125,
"logps/rejected": -480.55389404296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.5861432552337646,
"rewards/margins": 36.732574462890625,
"rewards/rejected": -37.318721771240234,
"step": 406
},
{
"epoch": 0.44,
"learning_rate": 2.6327586206896552e-05,
"logits/chosen": -0.1211957260966301,
"logits/rejected": -0.9387801885604858,
"logps/chosen": -288.6614990234375,
"logps/rejected": -440.61798095703125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.6156797409057617,
"rewards/margins": 36.306339263916016,
"rewards/rejected": -35.6906623840332,
"step": 407
},
{
"epoch": 0.45,
"learning_rate": 2.627586206896552e-05,
"logits/chosen": -0.1856449842453003,
"logits/rejected": -0.8845812082290649,
"logps/chosen": -263.8268127441406,
"logps/rejected": -498.94940185546875,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.013650417327881,
"rewards/margins": 37.46383285522461,
"rewards/rejected": -41.47748565673828,
"step": 408
},
{
"epoch": 0.45,
"learning_rate": 2.622413793103449e-05,
"logits/chosen": 0.009420637041330338,
"logits/rejected": -1.0488317012786865,
"logps/chosen": -388.43743896484375,
"logps/rejected": -487.9730224609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5363948345184326,
"rewards/margins": 41.2370719909668,
"rewards/rejected": -40.700679779052734,
"step": 409
},
{
"epoch": 0.45,
"learning_rate": 2.617241379310345e-05,
"logits/chosen": -0.1033945381641388,
"logits/rejected": -1.3271011114120483,
"logps/chosen": -510.8887939453125,
"logps/rejected": -464.1139221191406,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.8576178550720215,
"rewards/margins": 45.34534454345703,
"rewards/rejected": -37.487728118896484,
"step": 410
},
{
"epoch": 0.45,
"learning_rate": 2.6120689655172418e-05,
"logits/chosen": 0.012298082932829857,
"logits/rejected": -1.1230072975158691,
"logps/chosen": -376.9397277832031,
"logps/rejected": -465.98681640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.2561565339565277,
"rewards/margins": 37.64347839355469,
"rewards/rejected": -37.387325286865234,
"step": 411
},
{
"epoch": 0.45,
"learning_rate": 2.6068965517241382e-05,
"logits/chosen": -0.0367039330303669,
"logits/rejected": -1.370044469833374,
"logps/chosen": -433.99237060546875,
"logps/rejected": -526.426513671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.9706013202667236,
"rewards/margins": 47.25657272338867,
"rewards/rejected": -45.285972595214844,
"step": 412
},
{
"epoch": 0.45,
"learning_rate": 2.6017241379310344e-05,
"logits/chosen": 0.05295756831765175,
"logits/rejected": -1.0558881759643555,
"logps/chosen": -333.7112731933594,
"logps/rejected": -486.7742614746094,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.21756157279014587,
"rewards/margins": 43.01340103149414,
"rewards/rejected": -42.79584503173828,
"step": 413
},
{
"epoch": 0.45,
"learning_rate": 2.596551724137931e-05,
"logits/chosen": -0.16404397785663605,
"logits/rejected": -1.3011796474456787,
"logps/chosen": -487.19012451171875,
"logps/rejected": -492.16259765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.502512454986572,
"rewards/margins": 45.011375427246094,
"rewards/rejected": -39.50886535644531,
"step": 414
},
{
"epoch": 0.45,
"learning_rate": 2.591379310344828e-05,
"logits/chosen": -0.03245847672224045,
"logits/rejected": -1.338456153869629,
"logps/chosen": -393.41278076171875,
"logps/rejected": -507.5992431640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.42661714553833,
"rewards/margins": 46.058433532714844,
"rewards/rejected": -43.631813049316406,
"step": 415
},
{
"epoch": 0.45,
"learning_rate": 2.586206896551724e-05,
"logits/chosen": -0.17630226910114288,
"logits/rejected": -1.2694957256317139,
"logps/chosen": -406.9403076171875,
"logps/rejected": -529.5288696289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.6201605796813965,
"rewards/margins": 45.6422004699707,
"rewards/rejected": -43.022037506103516,
"step": 416
},
{
"epoch": 0.45,
"learning_rate": 2.581034482758621e-05,
"logits/chosen": 0.04229099303483963,
"logits/rejected": -1.3653508424758911,
"logps/chosen": -456.75592041015625,
"logps/rejected": -489.34307861328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.883845806121826,
"rewards/margins": 45.551551818847656,
"rewards/rejected": -39.66770553588867,
"step": 417
},
{
"epoch": 0.46,
"learning_rate": 2.5758620689655177e-05,
"logits/chosen": -0.07038390636444092,
"logits/rejected": -1.2386696338653564,
"logps/chosen": -437.032958984375,
"logps/rejected": -516.738037109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5063050985336304,
"rewards/margins": 42.439186096191406,
"rewards/rejected": -41.93287658691406,
"step": 418
},
{
"epoch": 0.46,
"learning_rate": 2.5706896551724138e-05,
"logits/chosen": 0.04438025876879692,
"logits/rejected": -1.2710415124893188,
"logps/chosen": -419.35028076171875,
"logps/rejected": -500.75164794921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.6055812239646912,
"rewards/margins": 43.148094177246094,
"rewards/rejected": -42.542510986328125,
"step": 419
},
{
"epoch": 0.46,
"learning_rate": 2.5655172413793106e-05,
"logits/chosen": -0.14012601971626282,
"logits/rejected": -0.9432665109634399,
"logps/chosen": -322.7103271484375,
"logps/rejected": -559.9931030273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.232179045677185,
"rewards/margins": 46.507049560546875,
"rewards/rejected": -47.739227294921875,
"step": 420
},
{
"epoch": 0.46,
"learning_rate": 2.560344827586207e-05,
"logits/chosen": -0.13305935263633728,
"logits/rejected": -1.078338384628296,
"logps/chosen": -298.7225646972656,
"logps/rejected": -552.3433837890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.11677652597427368,
"rewards/margins": 48.314998626708984,
"rewards/rejected": -48.43178176879883,
"step": 421
},
{
"epoch": 0.46,
"learning_rate": 2.5551724137931035e-05,
"logits/chosen": -0.09384839236736298,
"logits/rejected": -1.350205898284912,
"logps/chosen": -406.8752746582031,
"logps/rejected": -576.1410522460938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.6324269771575928,
"rewards/margins": 51.2014274597168,
"rewards/rejected": -47.569000244140625,
"step": 422
},
{
"epoch": 0.46,
"learning_rate": 2.55e-05,
"logits/chosen": -0.14802265167236328,
"logits/rejected": -1.068876028060913,
"logps/chosen": -297.4754333496094,
"logps/rejected": -581.18994140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.11329731345176697,
"rewards/margins": 49.50238037109375,
"rewards/rejected": -49.61567687988281,
"step": 423
},
{
"epoch": 0.46,
"learning_rate": 2.5448275862068968e-05,
"logits/chosen": 0.1324731409549713,
"logits/rejected": -1.66242253780365,
"logps/chosen": -557.9464721679688,
"logps/rejected": -542.5173950195312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 10.66864013671875,
"rewards/margins": 57.00450897216797,
"rewards/rejected": -46.33586883544922,
"step": 424
},
{
"epoch": 0.46,
"learning_rate": 2.5396551724137936e-05,
"logits/chosen": -0.14472703635692596,
"logits/rejected": -1.0066394805908203,
"logps/chosen": -287.56622314453125,
"logps/rejected": -527.8837280273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.7066973447799683,
"rewards/margins": 41.968414306640625,
"rewards/rejected": -42.67510986328125,
"step": 425
},
{
"epoch": 0.46,
"learning_rate": 2.5344827586206897e-05,
"logits/chosen": -0.1694573163986206,
"logits/rejected": -1.0617188215255737,
"logps/chosen": -359.6497497558594,
"logps/rejected": -551.6131591796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.4302568435668945,
"rewards/margins": 48.28759002685547,
"rewards/rejected": -46.857330322265625,
"step": 426
},
{
"epoch": 0.47,
"learning_rate": 2.5293103448275865e-05,
"logits/chosen": -0.12637755274772644,
"logits/rejected": -0.9839163422584534,
"logps/chosen": -312.71148681640625,
"logps/rejected": -523.2889404296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.07784199714660645,
"rewards/margins": 42.848533630371094,
"rewards/rejected": -42.92637634277344,
"step": 427
},
{
"epoch": 0.47,
"learning_rate": 2.5241379310344833e-05,
"logits/chosen": -0.15449154376983643,
"logits/rejected": -1.0122627019882202,
"logps/chosen": -364.6027526855469,
"logps/rejected": -519.9754638671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.042532920837402,
"rewards/margins": 44.28017807006836,
"rewards/rejected": -40.237648010253906,
"step": 428
},
{
"epoch": 0.47,
"learning_rate": 2.5189655172413794e-05,
"logits/chosen": -0.015961170196533203,
"logits/rejected": -0.9020889401435852,
"logps/chosen": -385.604736328125,
"logps/rejected": -582.2443237304688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.09042125940322876,
"rewards/margins": 45.73094177246094,
"rewards/rejected": -45.82136535644531,
"step": 429
},
{
"epoch": 0.47,
"learning_rate": 2.513793103448276e-05,
"logits/chosen": -0.08048711717128754,
"logits/rejected": -1.1989467144012451,
"logps/chosen": -406.6160888671875,
"logps/rejected": -526.4555053710938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.1125061511993408,
"rewards/margins": 44.74122619628906,
"rewards/rejected": -45.85373306274414,
"step": 430
},
{
"epoch": 0.47,
"learning_rate": 2.5086206896551727e-05,
"logits/chosen": -0.07307261973619461,
"logits/rejected": -1.1985551118850708,
"logps/chosen": -395.5963439941406,
"logps/rejected": -579.1031494140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7303085327148438,
"rewards/margins": 49.54568862915039,
"rewards/rejected": -48.81537628173828,
"step": 431
},
{
"epoch": 0.47,
"learning_rate": 2.5034482758620688e-05,
"logits/chosen": 0.11793918162584305,
"logits/rejected": -1.4616129398345947,
"logps/chosen": -433.7359619140625,
"logps/rejected": -542.4663696289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.1155309677124023,
"rewards/margins": 48.859405517578125,
"rewards/rejected": -45.743873596191406,
"step": 432
},
{
"epoch": 0.47,
"learning_rate": 2.4982758620689656e-05,
"logits/chosen": -0.06499344110488892,
"logits/rejected": -1.393472671508789,
"logps/chosen": -494.056640625,
"logps/rejected": -539.1574096679688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.363572120666504,
"rewards/margins": 50.28820037841797,
"rewards/rejected": -45.92462921142578,
"step": 433
},
{
"epoch": 0.47,
"learning_rate": 2.4931034482758624e-05,
"logits/chosen": -0.18045151233673096,
"logits/rejected": -0.9066936373710632,
"logps/chosen": -269.164794921875,
"logps/rejected": -516.2396850585938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.3069080114364624,
"rewards/margins": 39.70387649536133,
"rewards/rejected": -41.010780334472656,
"step": 434
},
{
"epoch": 0.47,
"learning_rate": 2.4879310344827585e-05,
"logits/chosen": -0.16510559618473053,
"logits/rejected": -0.9158352017402649,
"logps/chosen": -342.11920166015625,
"logps/rejected": -594.5755615234375,
"loss": 0.0037,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.06957662105560303,
"rewards/margins": 44.563594818115234,
"rewards/rejected": -44.494014739990234,
"step": 435
},
{
"epoch": 0.48,
"learning_rate": 2.4827586206896553e-05,
"logits/chosen": -0.08779498934745789,
"logits/rejected": -0.9681074023246765,
"logps/chosen": -233.8495330810547,
"logps/rejected": -577.7623291015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.8844499588012695,
"rewards/margins": 47.862998962402344,
"rewards/rejected": -48.7474479675293,
"step": 436
},
{
"epoch": 0.48,
"learning_rate": 2.477586206896552e-05,
"logits/chosen": 0.04494841396808624,
"logits/rejected": -1.3290835618972778,
"logps/chosen": -458.4309387207031,
"logps/rejected": -547.5213012695312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.0667998790740967,
"rewards/margins": 49.19175338745117,
"rewards/rejected": -46.12495422363281,
"step": 437
},
{
"epoch": 0.48,
"learning_rate": 2.4724137931034483e-05,
"logits/chosen": -0.07239006459712982,
"logits/rejected": -1.1752184629440308,
"logps/chosen": -362.7398681640625,
"logps/rejected": -527.936279296875,
"loss": 0.0051,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.697190523147583,
"rewards/margins": 42.5650634765625,
"rewards/rejected": -43.26225662231445,
"step": 438
},
{
"epoch": 0.48,
"learning_rate": 2.467241379310345e-05,
"logits/chosen": -0.11375527083873749,
"logits/rejected": -1.442746639251709,
"logps/chosen": -463.52410888671875,
"logps/rejected": -559.883056640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.263465881347656,
"rewards/margins": 53.06332778930664,
"rewards/rejected": -48.79986572265625,
"step": 439
},
{
"epoch": 0.48,
"learning_rate": 2.4620689655172415e-05,
"logits/chosen": 0.02915153093636036,
"logits/rejected": -1.106976866722107,
"logps/chosen": -505.97552490234375,
"logps/rejected": -572.701171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.4833635687828064,
"rewards/margins": 50.768310546875,
"rewards/rejected": -50.28494644165039,
"step": 440
},
{
"epoch": 0.48,
"learning_rate": 2.4568965517241383e-05,
"logits/chosen": -0.012120015919208527,
"logits/rejected": -1.398685336112976,
"logps/chosen": -491.70361328125,
"logps/rejected": -593.99951171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.6562215089797974,
"rewards/margins": 49.44664001464844,
"rewards/rejected": -51.10285949707031,
"step": 441
},
{
"epoch": 0.48,
"learning_rate": 2.4517241379310344e-05,
"logits/chosen": -0.02736329287290573,
"logits/rejected": -1.475520372390747,
"logps/chosen": -519.62255859375,
"logps/rejected": -649.6115112304688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.501253604888916,
"rewards/margins": 54.74308395385742,
"rewards/rejected": -55.24433517456055,
"step": 442
},
{
"epoch": 0.48,
"learning_rate": 2.4465517241379312e-05,
"logits/chosen": -0.14074942469596863,
"logits/rejected": -1.3152858018875122,
"logps/chosen": -390.683349609375,
"logps/rejected": -604.4539794921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.0559771060943604,
"rewards/margins": 50.112056732177734,
"rewards/rejected": -53.16802978515625,
"step": 443
},
{
"epoch": 0.48,
"learning_rate": 2.441379310344828e-05,
"logits/chosen": -0.11957734823226929,
"logits/rejected": -1.1977393627166748,
"logps/chosen": -309.5727844238281,
"logps/rejected": -558.4000244140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.4718704223632812,
"rewards/margins": 47.193809509277344,
"rewards/rejected": -49.66568374633789,
"step": 444
},
{
"epoch": 0.49,
"learning_rate": 2.436206896551724e-05,
"logits/chosen": -0.027118626981973648,
"logits/rejected": -1.4130396842956543,
"logps/chosen": -512.9483642578125,
"logps/rejected": -661.2791748046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.5184032917022705,
"rewards/margins": 58.53022766113281,
"rewards/rejected": -56.01182556152344,
"step": 445
},
{
"epoch": 0.49,
"learning_rate": 2.431034482758621e-05,
"logits/chosen": -0.10026545077562332,
"logits/rejected": -1.0776184797286987,
"logps/chosen": -390.74957275390625,
"logps/rejected": -613.8366088867188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.3963590860366821,
"rewards/margins": 51.305171966552734,
"rewards/rejected": -52.701534271240234,
"step": 446
},
{
"epoch": 0.49,
"learning_rate": 2.4258620689655174e-05,
"logits/chosen": -0.06135738641023636,
"logits/rejected": -1.1190871000289917,
"logps/chosen": -402.94940185546875,
"logps/rejected": -593.6253662109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.729300022125244,
"rewards/margins": 46.670902252197266,
"rewards/rejected": -49.40019989013672,
"step": 447
},
{
"epoch": 0.49,
"learning_rate": 2.420689655172414e-05,
"logits/chosen": -0.08222100138664246,
"logits/rejected": -0.9519947171211243,
"logps/chosen": -333.4215087890625,
"logps/rejected": -581.1034545898438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.2264509201049805,
"rewards/margins": 45.486000061035156,
"rewards/rejected": -49.71245574951172,
"step": 448
},
{
"epoch": 0.49,
"learning_rate": 2.4155172413793103e-05,
"logits/chosen": -0.09325332939624786,
"logits/rejected": -1.1721282005310059,
"logps/chosen": -467.85150146484375,
"logps/rejected": -599.2661743164062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5591703057289124,
"rewards/margins": 47.47113037109375,
"rewards/rejected": -46.911964416503906,
"step": 449
},
{
"epoch": 0.49,
"learning_rate": 2.410344827586207e-05,
"logits/chosen": -0.1012139841914177,
"logits/rejected": -1.1209399700164795,
"logps/chosen": -377.45355224609375,
"logps/rejected": -592.563232421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.7665712833404541,
"rewards/margins": 47.60783386230469,
"rewards/rejected": -48.37440872192383,
"step": 450
},
{
"epoch": 0.49,
"learning_rate": 2.4051724137931033e-05,
"logits/chosen": -0.25119173526763916,
"logits/rejected": -1.3089392185211182,
"logps/chosen": -395.1696472167969,
"logps/rejected": -575.6404418945312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.25265008211135864,
"rewards/margins": 50.09402847290039,
"rewards/rejected": -49.841373443603516,
"step": 451
},
{
"epoch": 0.49,
"learning_rate": 2.4e-05,
"logits/chosen": -0.06219256669282913,
"logits/rejected": -1.17987859249115,
"logps/chosen": -423.6275634765625,
"logps/rejected": -604.2877807617188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.2522249221801758,
"rewards/margins": 55.68733596801758,
"rewards/rejected": -54.43511199951172,
"step": 452
},
{
"epoch": 0.49,
"learning_rate": 2.394827586206897e-05,
"logits/chosen": -0.15801295638084412,
"logits/rejected": -1.2335947751998901,
"logps/chosen": -380.48291015625,
"logps/rejected": -573.8751831054688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.369384765625,
"rewards/margins": 46.3884391784668,
"rewards/rejected": -48.7578239440918,
"step": 453
},
{
"epoch": 0.5,
"learning_rate": 2.389655172413793e-05,
"logits/chosen": -0.10853154957294464,
"logits/rejected": -1.2493653297424316,
"logps/chosen": -535.5428466796875,
"logps/rejected": -618.5908813476562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.8845133781433105,
"rewards/margins": 54.12300491333008,
"rewards/rejected": -50.238494873046875,
"step": 454
},
{
"epoch": 0.5,
"learning_rate": 2.3844827586206898e-05,
"logits/chosen": -0.22083908319473267,
"logits/rejected": -1.021941900253296,
"logps/chosen": -373.7161865234375,
"logps/rejected": -669.4287719726562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.2017593383789062,
"rewards/margins": 50.782039642333984,
"rewards/rejected": -52.98379898071289,
"step": 455
},
{
"epoch": 0.5,
"learning_rate": 2.3793103448275866e-05,
"logits/chosen": -0.004196269437670708,
"logits/rejected": -1.2873380184173584,
"logps/chosen": -507.622802734375,
"logps/rejected": -605.938232421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.7006635665893555,
"rewards/margins": 50.75455093383789,
"rewards/rejected": -53.4552116394043,
"step": 456
},
{
"epoch": 0.5,
"learning_rate": 2.374137931034483e-05,
"logits/chosen": -0.06312916427850723,
"logits/rejected": -1.2262274026870728,
"logps/chosen": -396.0963134765625,
"logps/rejected": -557.1597290039062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.6157703399658203,
"rewards/margins": 45.1955680847168,
"rewards/rejected": -46.81133270263672,
"step": 457
},
{
"epoch": 0.5,
"learning_rate": 2.3689655172413795e-05,
"logits/chosen": 0.06958001852035522,
"logits/rejected": -1.2452892065048218,
"logps/chosen": -524.7869873046875,
"logps/rejected": -566.8543701171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.04834580421447754,
"rewards/margins": 48.23228073120117,
"rewards/rejected": -48.28062438964844,
"step": 458
},
{
"epoch": 0.5,
"learning_rate": 2.363793103448276e-05,
"logits/chosen": -0.16556937992572784,
"logits/rejected": -1.327263355255127,
"logps/chosen": -464.6548767089844,
"logps/rejected": -662.5446166992188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.6031289100646973,
"rewards/margins": 57.662391662597656,
"rewards/rejected": -54.059261322021484,
"step": 459
},
{
"epoch": 0.5,
"learning_rate": 2.3586206896551728e-05,
"logits/chosen": 0.03939518332481384,
"logits/rejected": -1.1463898420333862,
"logps/chosen": -471.4759216308594,
"logps/rejected": -572.1267700195312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.5924675464630127,
"rewards/margins": 47.605220794677734,
"rewards/rejected": -50.197689056396484,
"step": 460
},
{
"epoch": 0.5,
"learning_rate": 2.353448275862069e-05,
"logits/chosen": -0.148860901594162,
"logits/rejected": -1.0923480987548828,
"logps/chosen": -390.76983642578125,
"logps/rejected": -567.6170043945312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.437652111053467,
"rewards/margins": 46.786190032958984,
"rewards/rejected": -49.223838806152344,
"step": 461
},
{
"epoch": 0.5,
"learning_rate": 2.3482758620689657e-05,
"logits/chosen": -0.10093279182910919,
"logits/rejected": -1.3032270669937134,
"logps/chosen": -547.587890625,
"logps/rejected": -627.3497314453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.0484240055084229,
"rewards/margins": 48.94506072998047,
"rewards/rejected": -47.89663314819336,
"step": 462
},
{
"epoch": 0.51,
"learning_rate": 2.3431034482758625e-05,
"logits/chosen": -0.2709757685661316,
"logits/rejected": -1.1485973596572876,
"logps/chosen": -395.17950439453125,
"logps/rejected": -636.9188232421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.9400150775909424,
"rewards/margins": 54.22304153442383,
"rewards/rejected": -53.28302764892578,
"step": 463
},
{
"epoch": 0.51,
"learning_rate": 2.3379310344827586e-05,
"logits/chosen": -0.06289319694042206,
"logits/rejected": -1.114414930343628,
"logps/chosen": -409.9918212890625,
"logps/rejected": -590.608642578125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.87382972240448,
"rewards/margins": 48.40852737426758,
"rewards/rejected": -50.28235626220703,
"step": 464
},
{
"epoch": 0.51,
"learning_rate": 2.3327586206896554e-05,
"logits/chosen": -0.14943581819534302,
"logits/rejected": -1.1048765182495117,
"logps/chosen": -391.01165771484375,
"logps/rejected": -591.4696655273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.6352293491363525,
"rewards/margins": 51.1685905456543,
"rewards/rejected": -49.533363342285156,
"step": 465
},
{
"epoch": 0.51,
"learning_rate": 2.327586206896552e-05,
"logits/chosen": -0.27370375394821167,
"logits/rejected": -0.9103720188140869,
"logps/chosen": -281.7870788574219,
"logps/rejected": -599.569091796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.6924283504486084,
"rewards/margins": 46.583003997802734,
"rewards/rejected": -50.275428771972656,
"step": 466
},
{
"epoch": 0.51,
"learning_rate": 2.3224137931034483e-05,
"logits/chosen": -0.07111064344644547,
"logits/rejected": -1.0503026247024536,
"logps/chosen": -385.4219970703125,
"logps/rejected": -592.8201293945312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.1101531982421875,
"rewards/margins": 44.58013916015625,
"rewards/rejected": -49.69029235839844,
"step": 467
},
{
"epoch": 0.51,
"learning_rate": 2.3172413793103448e-05,
"logits/chosen": -0.09694894403219223,
"logits/rejected": -1.4143892526626587,
"logps/chosen": -435.46929931640625,
"logps/rejected": -538.757568359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.979873538017273,
"rewards/margins": 43.746910095214844,
"rewards/rejected": -45.726783752441406,
"step": 468
},
{
"epoch": 0.51,
"learning_rate": 2.3120689655172416e-05,
"logits/chosen": -0.18315471708774567,
"logits/rejected": -0.99836266040802,
"logps/chosen": -350.4498291015625,
"logps/rejected": -529.862548828125,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.8093771934509277,
"rewards/margins": 41.57612991333008,
"rewards/rejected": -44.38550567626953,
"step": 469
},
{
"epoch": 0.51,
"learning_rate": 2.3068965517241377e-05,
"logits/chosen": -0.18518385291099548,
"logits/rejected": -1.1606504917144775,
"logps/chosen": -393.2962646484375,
"logps/rejected": -538.1412353515625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.910660743713379,
"rewards/margins": 42.86040115356445,
"rewards/rejected": -48.771060943603516,
"step": 470
},
{
"epoch": 0.51,
"learning_rate": 2.3017241379310345e-05,
"logits/chosen": 0.00019899383187294006,
"logits/rejected": -1.1684370040893555,
"logps/chosen": -479.20159912109375,
"logps/rejected": -641.7985229492188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.2206273078918457,
"rewards/margins": 54.14768600463867,
"rewards/rejected": -53.92705535888672,
"step": 471
},
{
"epoch": 0.51,
"learning_rate": 2.2965517241379313e-05,
"logits/chosen": -0.03899521380662918,
"logits/rejected": -1.3559366464614868,
"logps/chosen": -433.9493103027344,
"logps/rejected": -585.2498779296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.505762100219727,
"rewards/margins": 46.427223205566406,
"rewards/rejected": -51.932987213134766,
"step": 472
},
{
"epoch": 0.52,
"learning_rate": 2.291379310344828e-05,
"logits/chosen": -0.1787998378276825,
"logits/rejected": -1.2400846481323242,
"logps/chosen": -417.8245849609375,
"logps/rejected": -625.9854736328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.0074243545532227,
"rewards/margins": 57.41107940673828,
"rewards/rejected": -55.403656005859375,
"step": 473
},
{
"epoch": 0.52,
"learning_rate": 2.2862068965517242e-05,
"logits/chosen": -0.1422000527381897,
"logits/rejected": -1.2094967365264893,
"logps/chosen": -420.824462890625,
"logps/rejected": -646.4536743164062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.564375638961792,
"rewards/margins": 52.2685546875,
"rewards/rejected": -54.83293151855469,
"step": 474
},
{
"epoch": 0.52,
"learning_rate": 2.281034482758621e-05,
"logits/chosen": -0.26421085000038147,
"logits/rejected": -1.0333547592163086,
"logps/chosen": -301.2657165527344,
"logps/rejected": -649.3005981445312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.931241989135742,
"rewards/margins": 50.742645263671875,
"rewards/rejected": -55.673885345458984,
"step": 475
},
{
"epoch": 0.52,
"learning_rate": 2.2758620689655175e-05,
"logits/chosen": -0.3443467915058136,
"logits/rejected": -1.1682060956954956,
"logps/chosen": -374.7920837402344,
"logps/rejected": -641.9935913085938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.4264507293701172,
"rewards/margins": 48.89411544799805,
"rewards/rejected": -50.3205680847168,
"step": 476
},
{
"epoch": 0.52,
"learning_rate": 2.270689655172414e-05,
"logits/chosen": -0.14052361249923706,
"logits/rejected": -1.365431547164917,
"logps/chosen": -428.28253173828125,
"logps/rejected": -611.1834716796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.9522128105163574,
"rewards/margins": 49.015159606933594,
"rewards/rejected": -52.967376708984375,
"step": 477
},
{
"epoch": 0.52,
"learning_rate": 2.2655172413793104e-05,
"logits/chosen": -0.07368788123130798,
"logits/rejected": -1.3622853755950928,
"logps/chosen": -448.222412109375,
"logps/rejected": -609.247802734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.316495895385742,
"rewards/margins": 51.841697692871094,
"rewards/rejected": -55.15819549560547,
"step": 478
},
{
"epoch": 0.52,
"learning_rate": 2.2603448275862072e-05,
"logits/chosen": -0.15994326770305634,
"logits/rejected": -1.2854161262512207,
"logps/chosen": -365.8324890136719,
"logps/rejected": -639.3682861328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.163121223449707,
"rewards/margins": 51.78949737548828,
"rewards/rejected": -55.95261764526367,
"step": 479
},
{
"epoch": 0.52,
"learning_rate": 2.2551724137931033e-05,
"logits/chosen": -0.15817472338676453,
"logits/rejected": -1.3019388914108276,
"logps/chosen": -445.13543701171875,
"logps/rejected": -656.9911499023438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.5493353605270386,
"rewards/margins": 54.51856231689453,
"rewards/rejected": -55.067893981933594,
"step": 480
},
{
"epoch": 0.52,
"learning_rate": 2.25e-05,
"logits/chosen": -0.39189618825912476,
"logits/rejected": -1.1742621660232544,
"logps/chosen": -364.6230773925781,
"logps/rejected": -649.7832641601562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.308798789978027,
"rewards/margins": 49.49714660644531,
"rewards/rejected": -56.80595016479492,
"step": 481
},
{
"epoch": 0.53,
"learning_rate": 2.2448275862068966e-05,
"logits/chosen": -0.17453332245349884,
"logits/rejected": -1.2001525163650513,
"logps/chosen": -444.8879699707031,
"logps/rejected": -657.28515625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.9432910680770874,
"rewards/margins": 53.479248046875,
"rewards/rejected": -55.42253875732422,
"step": 482
},
{
"epoch": 0.53,
"learning_rate": 2.2396551724137934e-05,
"logits/chosen": -0.11637411266565323,
"logits/rejected": -1.3278591632843018,
"logps/chosen": -434.76885986328125,
"logps/rejected": -645.82275390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.3694510459899902,
"rewards/margins": 53.313201904296875,
"rewards/rejected": -56.682647705078125,
"step": 483
},
{
"epoch": 0.53,
"learning_rate": 2.23448275862069e-05,
"logits/chosen": -0.07361380755901337,
"logits/rejected": -1.4948939085006714,
"logps/chosen": -519.01416015625,
"logps/rejected": -701.379150390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.0733790397644043,
"rewards/margins": 57.03836441040039,
"rewards/rejected": -59.11174392700195,
"step": 484
},
{
"epoch": 0.53,
"learning_rate": 2.2293103448275863e-05,
"logits/chosen": -0.12567904591560364,
"logits/rejected": -1.4412992000579834,
"logps/chosen": -454.69085693359375,
"logps/rejected": -657.5882568359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.14197838306427002,
"rewards/margins": 58.170379638671875,
"rewards/rejected": -58.312355041503906,
"step": 485
},
{
"epoch": 0.53,
"learning_rate": 2.2241379310344828e-05,
"logits/chosen": -0.10440649092197418,
"logits/rejected": -1.5682653188705444,
"logps/chosen": -645.4185180664062,
"logps/rejected": -665.8847045898438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.017826557159424,
"rewards/margins": 60.47355270385742,
"rewards/rejected": -55.45573043823242,
"step": 486
},
{
"epoch": 0.53,
"learning_rate": 2.2189655172413792e-05,
"logits/chosen": -0.005357783287763596,
"logits/rejected": -1.3899575471878052,
"logps/chosen": -551.1363525390625,
"logps/rejected": -617.5321044921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.363417148590088,
"rewards/margins": 49.92127990722656,
"rewards/rejected": -54.284698486328125,
"step": 487
},
{
"epoch": 0.53,
"learning_rate": 2.213793103448276e-05,
"logits/chosen": -0.20832586288452148,
"logits/rejected": -1.3670223951339722,
"logps/chosen": -424.8078308105469,
"logps/rejected": -620.9976806640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.274914264678955,
"rewards/margins": 52.706390380859375,
"rewards/rejected": -54.981300354003906,
"step": 488
},
{
"epoch": 0.53,
"learning_rate": 2.2086206896551725e-05,
"logits/chosen": -0.28159618377685547,
"logits/rejected": -1.283168077468872,
"logps/chosen": -391.3514099121094,
"logps/rejected": -634.2545776367188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.998907089233398,
"rewards/margins": 50.08463668823242,
"rewards/rejected": -56.08354187011719,
"step": 489
},
{
"epoch": 0.53,
"learning_rate": 2.203448275862069e-05,
"logits/chosen": -0.022036129608750343,
"logits/rejected": -1.4799420833587646,
"logps/chosen": -567.5009155273438,
"logps/rejected": -633.41259765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.2931156158447266,
"rewards/margins": 54.43924331665039,
"rewards/rejected": -53.1461296081543,
"step": 490
},
{
"epoch": 0.54,
"learning_rate": 2.1982758620689658e-05,
"logits/chosen": -0.189289852976799,
"logits/rejected": -1.0637376308441162,
"logps/chosen": -420.50128173828125,
"logps/rejected": -661.4995727539062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.507000207901001,
"rewards/margins": 54.35142135620117,
"rewards/rejected": -57.85841751098633,
"step": 491
},
{
"epoch": 0.54,
"learning_rate": 2.1931034482758622e-05,
"logits/chosen": -0.03940558806061745,
"logits/rejected": -1.313617467880249,
"logps/chosen": -475.4183349609375,
"logps/rejected": -630.4754638671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5654001235961914,
"rewards/margins": 54.049644470214844,
"rewards/rejected": -53.4842414855957,
"step": 492
},
{
"epoch": 0.54,
"learning_rate": 2.1879310344827587e-05,
"logits/chosen": -0.07513591647148132,
"logits/rejected": -1.212783694267273,
"logps/chosen": -403.09796142578125,
"logps/rejected": -616.3046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.01631498336792,
"rewards/margins": 51.85172653198242,
"rewards/rejected": -54.868045806884766,
"step": 493
},
{
"epoch": 0.54,
"learning_rate": 2.1827586206896555e-05,
"logits/chosen": -0.2881481647491455,
"logits/rejected": -1.2288963794708252,
"logps/chosen": -396.6158752441406,
"logps/rejected": -694.475341796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.2079168558120728,
"rewards/margins": 54.35879135131836,
"rewards/rejected": -55.566707611083984,
"step": 494
},
{
"epoch": 0.54,
"learning_rate": 2.177586206896552e-05,
"logits/chosen": 0.02672622725367546,
"logits/rejected": -1.3478881120681763,
"logps/chosen": -530.7757568359375,
"logps/rejected": -684.7239990234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.0076181888580322,
"rewards/margins": 56.306922912597656,
"rewards/rejected": -58.31454086303711,
"step": 495
},
{
"epoch": 0.54,
"learning_rate": 2.1724137931034484e-05,
"logits/chosen": -0.1358601450920105,
"logits/rejected": -1.2526161670684814,
"logps/chosen": -440.38702392578125,
"logps/rejected": -610.0796508789062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.512816429138184,
"rewards/margins": 48.28220748901367,
"rewards/rejected": -52.79502487182617,
"step": 496
},
{
"epoch": 0.54,
"learning_rate": 2.167241379310345e-05,
"logits/chosen": -0.06988359987735748,
"logits/rejected": -1.1959302425384521,
"logps/chosen": -449.9613342285156,
"logps/rejected": -671.1732788085938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.2779130935668945,
"rewards/margins": 55.88106155395508,
"rewards/rejected": -60.15897750854492,
"step": 497
},
{
"epoch": 0.54,
"learning_rate": 2.1620689655172413e-05,
"logits/chosen": -0.28054380416870117,
"logits/rejected": -1.2163547277450562,
"logps/chosen": -388.01300048828125,
"logps/rejected": -652.7429809570312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.8053398132324219,
"rewards/margins": 56.216575622558594,
"rewards/rejected": -57.02192306518555,
"step": 498
},
{
"epoch": 0.54,
"learning_rate": 2.156896551724138e-05,
"logits/chosen": -0.06607590615749359,
"logits/rejected": -1.2197513580322266,
"logps/chosen": -454.84771728515625,
"logps/rejected": -654.5570678710938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.4068199396133423,
"rewards/margins": 56.8363151550293,
"rewards/rejected": -58.24313735961914,
"step": 499
},
{
"epoch": 0.55,
"learning_rate": 2.1517241379310346e-05,
"logits/chosen": -0.28458642959594727,
"logits/rejected": -1.0344970226287842,
"logps/chosen": -370.1960144042969,
"logps/rejected": -655.9469604492188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.959820747375488,
"rewards/margins": 51.25876998901367,
"rewards/rejected": -56.218589782714844,
"step": 500
},
{
"epoch": 0.55,
"learning_rate": 2.146551724137931e-05,
"logits/chosen": -0.20156291127204895,
"logits/rejected": -1.1681430339813232,
"logps/chosen": -385.0158386230469,
"logps/rejected": -635.7328491210938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.1334333419799805,
"rewards/margins": 50.82726287841797,
"rewards/rejected": -55.960693359375,
"step": 501
},
{
"epoch": 0.55,
"learning_rate": 2.141379310344828e-05,
"logits/chosen": -0.0020601898431777954,
"logits/rejected": -1.1352349519729614,
"logps/chosen": -448.7326965332031,
"logps/rejected": -693.2049560546875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.15153491497039795,
"rewards/margins": 58.00741958618164,
"rewards/rejected": -58.15895462036133,
"step": 502
},
{
"epoch": 0.55,
"learning_rate": 2.1362068965517243e-05,
"logits/chosen": 0.022678162902593613,
"logits/rejected": -1.2108732461929321,
"logps/chosen": -430.61895751953125,
"logps/rejected": -625.4843139648438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.665067672729492,
"rewards/margins": 50.22642517089844,
"rewards/rejected": -54.89149475097656,
"step": 503
},
{
"epoch": 0.55,
"learning_rate": 2.1310344827586208e-05,
"logits/chosen": -0.13953523337841034,
"logits/rejected": -1.1829777956008911,
"logps/chosen": -472.4615173339844,
"logps/rejected": -752.0328369140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.490379810333252,
"rewards/margins": 54.96733474731445,
"rewards/rejected": -56.45771408081055,
"step": 504
},
{
"epoch": 0.55,
"learning_rate": 2.1258620689655172e-05,
"logits/chosen": -0.12544049322605133,
"logits/rejected": -1.331096887588501,
"logps/chosen": -456.3561706542969,
"logps/rejected": -655.4522705078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.4183454513549805,
"rewards/margins": 53.30242156982422,
"rewards/rejected": -56.72076416015625,
"step": 505
},
{
"epoch": 0.55,
"learning_rate": 2.1206896551724137e-05,
"logits/chosen": -0.15563945472240448,
"logits/rejected": -1.2740764617919922,
"logps/chosen": -437.84893798828125,
"logps/rejected": -658.6337280273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.4970543384552002,
"rewards/margins": 58.15724563598633,
"rewards/rejected": -57.660194396972656,
"step": 506
},
{
"epoch": 0.55,
"learning_rate": 2.1155172413793105e-05,
"logits/chosen": -0.08426739275455475,
"logits/rejected": -1.1883736848831177,
"logps/chosen": -474.1285705566406,
"logps/rejected": -654.4371337890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.8744089603424072,
"rewards/margins": 52.474884033203125,
"rewards/rejected": -53.34928894042969,
"step": 507
},
{
"epoch": 0.55,
"learning_rate": 2.110344827586207e-05,
"logits/chosen": -0.014494461007416248,
"logits/rejected": -1.1064589023590088,
"logps/chosen": -423.87103271484375,
"logps/rejected": -697.6011962890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.6249542236328125,
"rewards/margins": 58.5837287902832,
"rewards/rejected": -61.20867919921875,
"step": 508
},
{
"epoch": 0.56,
"learning_rate": 2.1051724137931034e-05,
"logits/chosen": -0.12398696690797806,
"logits/rejected": -1.3565784692764282,
"logps/chosen": -491.5214538574219,
"logps/rejected": -613.30712890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.7314184308052063,
"rewards/margins": 53.077938079833984,
"rewards/rejected": -53.80936050415039,
"step": 509
},
{
"epoch": 0.56,
"learning_rate": 2.1000000000000002e-05,
"logits/chosen": -0.051289428025484085,
"logits/rejected": -1.492192268371582,
"logps/chosen": -518.4822387695312,
"logps/rejected": -630.14013671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.1812780499458313,
"rewards/margins": 54.831336975097656,
"rewards/rejected": -54.650054931640625,
"step": 510
},
{
"epoch": 0.56,
"learning_rate": 2.0948275862068967e-05,
"logits/chosen": -0.2157306969165802,
"logits/rejected": -1.2566158771514893,
"logps/chosen": -459.4637145996094,
"logps/rejected": -669.658935546875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.579399585723877,
"rewards/margins": 53.49375915527344,
"rewards/rejected": -55.073158264160156,
"step": 511
},
{
"epoch": 0.56,
"learning_rate": 2.0896551724137935e-05,
"logits/chosen": -0.11594392359256744,
"logits/rejected": -1.24819815158844,
"logps/chosen": -514.4534912109375,
"logps/rejected": -639.0775146484375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.502558171749115,
"rewards/margins": 54.507659912109375,
"rewards/rejected": -55.010215759277344,
"step": 512
},
{
"epoch": 0.56,
"learning_rate": 2.08448275862069e-05,
"logits/chosen": -0.17627860605716705,
"logits/rejected": -1.393364429473877,
"logps/chosen": -440.92340087890625,
"logps/rejected": -675.639404296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.33227670192718506,
"rewards/margins": 60.44564437866211,
"rewards/rejected": -60.777923583984375,
"step": 513
},
{
"epoch": 0.56,
"learning_rate": 2.0793103448275864e-05,
"logits/chosen": -0.14404740929603577,
"logits/rejected": -1.421351671218872,
"logps/chosen": -504.71197509765625,
"logps/rejected": -648.1561889648438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.6551969051361084,
"rewards/margins": 57.213863372802734,
"rewards/rejected": -56.55866622924805,
"step": 514
},
{
"epoch": 0.56,
"learning_rate": 2.074137931034483e-05,
"logits/chosen": 0.004668328911066055,
"logits/rejected": -1.4230290651321411,
"logps/chosen": -436.03009033203125,
"logps/rejected": -611.609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.6679420471191406,
"rewards/margins": 49.031368255615234,
"rewards/rejected": -51.699310302734375,
"step": 515
},
{
"epoch": 0.56,
"learning_rate": 2.0689655172413793e-05,
"logits/chosen": -0.029186539351940155,
"logits/rejected": -1.4701117277145386,
"logps/chosen": -523.4320068359375,
"logps/rejected": -659.4295654296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.930753707885742,
"rewards/margins": 55.25088882446289,
"rewards/rejected": -59.181644439697266,
"step": 516
},
{
"epoch": 0.56,
"learning_rate": 2.0637931034482758e-05,
"logits/chosen": -0.2120245397090912,
"logits/rejected": -0.9436817765235901,
"logps/chosen": -356.55645751953125,
"logps/rejected": -751.9764404296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.7937495708465576,
"rewards/margins": 54.103370666503906,
"rewards/rejected": -57.897125244140625,
"step": 517
},
{
"epoch": 0.57,
"learning_rate": 2.0586206896551726e-05,
"logits/chosen": -0.155109241604805,
"logits/rejected": -1.2690709829330444,
"logps/chosen": -445.1922912597656,
"logps/rejected": -650.4595947265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.628649711608887,
"rewards/margins": 51.917388916015625,
"rewards/rejected": -56.54603576660156,
"step": 518
},
{
"epoch": 0.57,
"learning_rate": 2.053448275862069e-05,
"logits/chosen": -0.04659181088209152,
"logits/rejected": -1.4601080417633057,
"logps/chosen": -477.2423095703125,
"logps/rejected": -616.805908203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.1397993117570877,
"rewards/margins": 53.21185302734375,
"rewards/rejected": -53.07205581665039,
"step": 519
},
{
"epoch": 0.57,
"learning_rate": 2.048275862068966e-05,
"logits/chosen": -0.1084991991519928,
"logits/rejected": -1.009717583656311,
"logps/chosen": -416.266845703125,
"logps/rejected": -649.83251953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.471712112426758,
"rewards/margins": 49.83021926879883,
"rewards/rejected": -57.30193328857422,
"step": 520
},
{
"epoch": 0.57,
"learning_rate": 2.0431034482758623e-05,
"logits/chosen": -0.11132999509572983,
"logits/rejected": -1.2182048559188843,
"logps/chosen": -427.03985595703125,
"logps/rejected": -652.3914184570312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.08266544342041,
"rewards/margins": 52.819427490234375,
"rewards/rejected": -57.90208435058594,
"step": 521
},
{
"epoch": 0.57,
"learning_rate": 2.0379310344827588e-05,
"logits/chosen": -0.07166096568107605,
"logits/rejected": -0.8901804089546204,
"logps/chosen": -398.4652404785156,
"logps/rejected": -603.7015991210938,
"loss": 0.0472,
"rewards/accuracies": 0.9375,
"rewards/chosen": -7.047485828399658,
"rewards/margins": 45.51860809326172,
"rewards/rejected": -52.566097259521484,
"step": 522
},
{
"epoch": 0.57,
"learning_rate": 2.0327586206896552e-05,
"logits/chosen": -0.10595792531967163,
"logits/rejected": -1.0550121068954468,
"logps/chosen": -347.60546875,
"logps/rejected": -728.9971313476562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.260272026062012,
"rewards/margins": 56.09633255004883,
"rewards/rejected": -62.35660171508789,
"step": 523
},
{
"epoch": 0.57,
"learning_rate": 2.0275862068965517e-05,
"logits/chosen": -0.27664729952812195,
"logits/rejected": -1.2738081216812134,
"logps/chosen": -419.85357666015625,
"logps/rejected": -647.8483276367188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.494794845581055,
"rewards/margins": 52.42628860473633,
"rewards/rejected": -56.92108154296875,
"step": 524
},
{
"epoch": 0.57,
"learning_rate": 2.022413793103448e-05,
"logits/chosen": -0.07392889261245728,
"logits/rejected": -1.3131624460220337,
"logps/chosen": -538.642333984375,
"logps/rejected": -608.0081787109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.9629731178283691,
"rewards/margins": 52.443206787109375,
"rewards/rejected": -53.40617752075195,
"step": 525
},
{
"epoch": 0.57,
"learning_rate": 2.017241379310345e-05,
"logits/chosen": -0.21235141158103943,
"logits/rejected": -1.2620832920074463,
"logps/chosen": -470.26904296875,
"logps/rejected": -648.2606811523438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.8237268924713135,
"rewards/margins": 51.55657196044922,
"rewards/rejected": -54.38030242919922,
"step": 526
},
{
"epoch": 0.57,
"learning_rate": 2.0120689655172414e-05,
"logits/chosen": -0.07883001118898392,
"logits/rejected": -1.4777758121490479,
"logps/chosen": -513.1040649414062,
"logps/rejected": -663.640380859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.5773372650146484,
"rewards/margins": 58.29991149902344,
"rewards/rejected": -60.87725067138672,
"step": 527
},
{
"epoch": 0.58,
"learning_rate": 2.0068965517241382e-05,
"logits/chosen": -0.31512337923049927,
"logits/rejected": -1.1388442516326904,
"logps/chosen": -370.7431640625,
"logps/rejected": -662.3712768554688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.118474960327148,
"rewards/margins": 48.47383117675781,
"rewards/rejected": -57.59230422973633,
"step": 528
},
{
"epoch": 0.58,
"learning_rate": 2.0017241379310347e-05,
"logits/chosen": -0.2608606815338135,
"logits/rejected": -1.227593183517456,
"logps/chosen": -443.54779052734375,
"logps/rejected": -685.2706298828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.979219436645508,
"rewards/margins": 54.63554000854492,
"rewards/rejected": -58.6147575378418,
"step": 529
},
{
"epoch": 0.58,
"learning_rate": 1.996551724137931e-05,
"logits/chosen": -0.21307611465454102,
"logits/rejected": -1.1337976455688477,
"logps/chosen": -437.9703063964844,
"logps/rejected": -671.6073608398438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.212578296661377,
"rewards/margins": 53.49246597290039,
"rewards/rejected": -57.705047607421875,
"step": 530
},
{
"epoch": 0.58,
"learning_rate": 1.991379310344828e-05,
"logits/chosen": -0.16399875283241272,
"logits/rejected": -1.2640507221221924,
"logps/chosen": -428.9464111328125,
"logps/rejected": -718.56884765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.8005006313323975,
"rewards/margins": 59.8723030090332,
"rewards/rejected": -62.67280578613281,
"step": 531
},
{
"epoch": 0.58,
"learning_rate": 1.9862068965517244e-05,
"logits/chosen": -0.03811350464820862,
"logits/rejected": -1.584404468536377,
"logps/chosen": -647.8243408203125,
"logps/rejected": -653.6069946289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.426783084869385,
"rewards/margins": 55.79122543334961,
"rewards/rejected": -60.2180061340332,
"step": 532
},
{
"epoch": 0.58,
"learning_rate": 1.981034482758621e-05,
"logits/chosen": -0.16661666333675385,
"logits/rejected": -1.3489412069320679,
"logps/chosen": -576.0233154296875,
"logps/rejected": -677.5670776367188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.02166748046875,
"rewards/margins": 55.28102111816406,
"rewards/rejected": -60.30269241333008,
"step": 533
},
{
"epoch": 0.58,
"learning_rate": 1.9758620689655173e-05,
"logits/chosen": -0.42992162704467773,
"logits/rejected": -1.0344213247299194,
"logps/chosen": -331.75604248046875,
"logps/rejected": -705.9281005859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.415375709533691,
"rewards/margins": 49.89491271972656,
"rewards/rejected": -60.31028747558594,
"step": 534
},
{
"epoch": 0.58,
"learning_rate": 1.9706896551724138e-05,
"logits/chosen": -0.15657415986061096,
"logits/rejected": -1.419963002204895,
"logps/chosen": -616.8851928710938,
"logps/rejected": -672.5630493164062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.5933356285095215,
"rewards/margins": 52.59075927734375,
"rewards/rejected": -60.1840934753418,
"step": 535
},
{
"epoch": 0.58,
"learning_rate": 1.9655172413793106e-05,
"logits/chosen": -0.38475874066352844,
"logits/rejected": -1.1948922872543335,
"logps/chosen": -431.2165832519531,
"logps/rejected": -674.835205078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.450318813323975,
"rewards/margins": 51.454200744628906,
"rewards/rejected": -58.90452575683594,
"step": 536
},
{
"epoch": 0.59,
"learning_rate": 1.960344827586207e-05,
"logits/chosen": -0.6328589916229248,
"logits/rejected": -1.2824782133102417,
"logps/chosen": -460.2396545410156,
"logps/rejected": -756.9679565429688,
"loss": 0.0105,
"rewards/accuracies": 1.0,
"rewards/chosen": -11.223982810974121,
"rewards/margins": 51.80082321166992,
"rewards/rejected": -63.024803161621094,
"step": 537
},
{
"epoch": 0.59,
"learning_rate": 1.9551724137931035e-05,
"logits/chosen": -0.28524112701416016,
"logits/rejected": -1.3562718629837036,
"logps/chosen": -548.3995971679688,
"logps/rejected": -717.23388671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.4443503618240356,
"rewards/margins": 59.99860382080078,
"rewards/rejected": -61.44295883178711,
"step": 538
},
{
"epoch": 0.59,
"learning_rate": 1.9500000000000003e-05,
"logits/chosen": -0.2540721595287323,
"logits/rejected": -1.2168906927108765,
"logps/chosen": -408.9739074707031,
"logps/rejected": -692.2616577148438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.923998832702637,
"rewards/margins": 49.68036651611328,
"rewards/rejected": -59.6043701171875,
"step": 539
},
{
"epoch": 0.59,
"learning_rate": 1.9448275862068968e-05,
"logits/chosen": -0.42604437470436096,
"logits/rejected": -1.289304256439209,
"logps/chosen": -458.89276123046875,
"logps/rejected": -748.4998779296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -11.387511253356934,
"rewards/margins": 51.951114654541016,
"rewards/rejected": -63.338623046875,
"step": 540
},
{
"epoch": 0.59,
"learning_rate": 1.9396551724137932e-05,
"logits/chosen": -0.30175092816352844,
"logits/rejected": -1.4019683599472046,
"logps/chosen": -481.57489013671875,
"logps/rejected": -683.3731079101562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.1864436864852905,
"rewards/margins": 59.80683898925781,
"rewards/rejected": -60.993282318115234,
"step": 541
},
{
"epoch": 0.59,
"learning_rate": 1.9344827586206897e-05,
"logits/chosen": -0.22525370121002197,
"logits/rejected": -1.2713929414749146,
"logps/chosen": -441.145751953125,
"logps/rejected": -655.5973510742188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.433875322341919,
"rewards/margins": 54.15318298339844,
"rewards/rejected": -57.58705139160156,
"step": 542
},
{
"epoch": 0.59,
"learning_rate": 1.929310344827586e-05,
"logits/chosen": -0.36525341868400574,
"logits/rejected": -1.1360570192337036,
"logps/chosen": -379.4644470214844,
"logps/rejected": -715.0608520507812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.589846611022949,
"rewards/margins": 54.25578689575195,
"rewards/rejected": -59.84563064575195,
"step": 543
},
{
"epoch": 0.59,
"learning_rate": 1.924137931034483e-05,
"logits/chosen": -0.06538578867912292,
"logits/rejected": -1.3779454231262207,
"logps/chosen": -580.675537109375,
"logps/rejected": -661.8748168945312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.214271545410156,
"rewards/margins": 48.59384536743164,
"rewards/rejected": -56.8081169128418,
"step": 544
},
{
"epoch": 0.59,
"learning_rate": 1.9189655172413794e-05,
"logits/chosen": -0.1274988353252411,
"logits/rejected": -1.3928804397583008,
"logps/chosen": -509.0260925292969,
"logps/rejected": -606.0980224609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.795976161956787,
"rewards/margins": 46.74262237548828,
"rewards/rejected": -50.538597106933594,
"step": 545
},
{
"epoch": 0.6,
"learning_rate": 1.913793103448276e-05,
"logits/chosen": -0.08550414443016052,
"logits/rejected": -1.2893277406692505,
"logps/chosen": -506.2032165527344,
"logps/rejected": -692.5704956054688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.392428874969482,
"rewards/margins": 55.658851623535156,
"rewards/rejected": -60.0512809753418,
"step": 546
},
{
"epoch": 0.6,
"learning_rate": 1.9086206896551727e-05,
"logits/chosen": -0.24850007891654968,
"logits/rejected": -1.2666964530944824,
"logps/chosen": -445.8536071777344,
"logps/rejected": -691.1626586914062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.471304416656494,
"rewards/margins": 50.54898452758789,
"rewards/rejected": -58.020286560058594,
"step": 547
},
{
"epoch": 0.6,
"learning_rate": 1.903448275862069e-05,
"logits/chosen": -0.09865757077932358,
"logits/rejected": -1.2371084690093994,
"logps/chosen": -543.6181640625,
"logps/rejected": -687.4448852539062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.3608412742614746,
"rewards/margins": 54.74359893798828,
"rewards/rejected": -57.104434967041016,
"step": 548
},
{
"epoch": 0.6,
"learning_rate": 1.8982758620689656e-05,
"logits/chosen": -0.10665954649448395,
"logits/rejected": -1.450705885887146,
"logps/chosen": -486.8913879394531,
"logps/rejected": -677.2809448242188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.5832552909851074,
"rewards/margins": 57.06523132324219,
"rewards/rejected": -58.64849090576172,
"step": 549
},
{
"epoch": 0.6,
"learning_rate": 1.8931034482758624e-05,
"logits/chosen": -0.1286657452583313,
"logits/rejected": -1.407023549079895,
"logps/chosen": -486.1256103515625,
"logps/rejected": -709.9680786132812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.5269105434417725,
"rewards/margins": 59.747928619384766,
"rewards/rejected": -62.274845123291016,
"step": 550
},
{
"epoch": 0.6,
"learning_rate": 1.8879310344827585e-05,
"logits/chosen": -0.0675632432103157,
"logits/rejected": -1.272240400314331,
"logps/chosen": -468.42352294921875,
"logps/rejected": -674.0982055664062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.776965141296387,
"rewards/margins": 52.262508392333984,
"rewards/rejected": -59.03947830200195,
"step": 551
},
{
"epoch": 0.6,
"learning_rate": 1.8827586206896553e-05,
"logits/chosen": -0.34433895349502563,
"logits/rejected": -1.113890290260315,
"logps/chosen": -298.00396728515625,
"logps/rejected": -606.363525390625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.223278045654297,
"rewards/margins": 44.2802619934082,
"rewards/rejected": -53.5035400390625,
"step": 552
},
{
"epoch": 0.6,
"learning_rate": 1.8775862068965518e-05,
"logits/chosen": -0.21515408158302307,
"logits/rejected": -1.428251028060913,
"logps/chosen": -425.70794677734375,
"logps/rejected": -670.1383666992188,
"loss": 0.0167,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.1336541175842285,
"rewards/margins": 50.13953399658203,
"rewards/rejected": -56.273189544677734,
"step": 553
},
{
"epoch": 0.6,
"learning_rate": 1.8724137931034482e-05,
"logits/chosen": -0.21798893809318542,
"logits/rejected": -1.3687691688537598,
"logps/chosen": -487.7384033203125,
"logps/rejected": -666.2149658203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.636868476867676,
"rewards/margins": 54.46982192993164,
"rewards/rejected": -57.106689453125,
"step": 554
},
{
"epoch": 0.61,
"learning_rate": 1.867241379310345e-05,
"logits/chosen": -0.2618967592716217,
"logits/rejected": -1.3180971145629883,
"logps/chosen": -451.2808837890625,
"logps/rejected": -653.58837890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.717561721801758,
"rewards/margins": 50.419822692871094,
"rewards/rejected": -58.13738250732422,
"step": 555
},
{
"epoch": 0.61,
"learning_rate": 1.8620689655172415e-05,
"logits/chosen": -0.30724576115608215,
"logits/rejected": -1.066850185394287,
"logps/chosen": -341.5390930175781,
"logps/rejected": -702.739501953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.248960971832275,
"rewards/margins": 53.42186737060547,
"rewards/rejected": -59.67082595825195,
"step": 556
},
{
"epoch": 0.61,
"learning_rate": 1.856896551724138e-05,
"logits/chosen": -0.2094910740852356,
"logits/rejected": -1.2574561834335327,
"logps/chosen": -449.03106689453125,
"logps/rejected": -726.781982421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.954678535461426,
"rewards/margins": 52.55630874633789,
"rewards/rejected": -61.510990142822266,
"step": 557
},
{
"epoch": 0.61,
"learning_rate": 1.8517241379310348e-05,
"logits/chosen": -0.0532219298183918,
"logits/rejected": -1.2439594268798828,
"logps/chosen": -488.92144775390625,
"logps/rejected": -674.4827270507812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.375113487243652,
"rewards/margins": 51.293792724609375,
"rewards/rejected": -59.668907165527344,
"step": 558
},
{
"epoch": 0.61,
"learning_rate": 1.8465517241379312e-05,
"logits/chosen": 0.03209938108921051,
"logits/rejected": -1.5995020866394043,
"logps/chosen": -532.6072998046875,
"logps/rejected": -616.2276611328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.855282783508301,
"rewards/margins": 50.27061462402344,
"rewards/rejected": -54.125892639160156,
"step": 559
},
{
"epoch": 0.61,
"learning_rate": 1.8413793103448277e-05,
"logits/chosen": -0.12263540923595428,
"logits/rejected": -1.1568797826766968,
"logps/chosen": -516.74365234375,
"logps/rejected": -714.9854736328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.593143463134766,
"rewards/margins": 52.229610443115234,
"rewards/rejected": -58.82275390625,
"step": 560
},
{
"epoch": 0.61,
"learning_rate": 1.836206896551724e-05,
"logits/chosen": -0.13906851410865784,
"logits/rejected": -1.1512776613235474,
"logps/chosen": -455.60467529296875,
"logps/rejected": -710.459716796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.503664493560791,
"rewards/margins": 55.149513244628906,
"rewards/rejected": -60.65318298339844,
"step": 561
},
{
"epoch": 0.61,
"learning_rate": 1.8310344827586206e-05,
"logits/chosen": -0.01586013287305832,
"logits/rejected": -1.5763020515441895,
"logps/chosen": -649.6324462890625,
"logps/rejected": -634.0162963867188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.6673918962478638,
"rewards/margins": 52.934112548828125,
"rewards/rejected": -54.60150146484375,
"step": 562
},
{
"epoch": 0.61,
"learning_rate": 1.8258620689655174e-05,
"logits/chosen": -0.09369073808193207,
"logits/rejected": -1.5399290323257446,
"logps/chosen": -532.3624877929688,
"logps/rejected": -650.81689453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.8866522312164307,
"rewards/margins": 54.70314025878906,
"rewards/rejected": -56.58979415893555,
"step": 563
},
{
"epoch": 0.62,
"learning_rate": 1.820689655172414e-05,
"logits/chosen": -0.1317727118730545,
"logits/rejected": -1.3313921689987183,
"logps/chosen": -494.91180419921875,
"logps/rejected": -686.72607421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.157313108444214,
"rewards/margins": 55.9873046875,
"rewards/rejected": -58.14461898803711,
"step": 564
},
{
"epoch": 0.62,
"learning_rate": 1.8155172413793103e-05,
"logits/chosen": -0.12760236859321594,
"logits/rejected": -1.4653446674346924,
"logps/chosen": -491.8769836425781,
"logps/rejected": -678.2470092773438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.088787078857422,
"rewards/margins": 56.210838317871094,
"rewards/rejected": -60.299625396728516,
"step": 565
},
{
"epoch": 0.62,
"learning_rate": 1.810344827586207e-05,
"logits/chosen": -0.2516867220401764,
"logits/rejected": -1.2494770288467407,
"logps/chosen": -428.3562316894531,
"logps/rejected": -669.3509521484375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.195309638977051,
"rewards/margins": 52.69432067871094,
"rewards/rejected": -58.889625549316406,
"step": 566
},
{
"epoch": 0.62,
"learning_rate": 1.8051724137931036e-05,
"logits/chosen": -0.30673977732658386,
"logits/rejected": -1.483799695968628,
"logps/chosen": -428.2577209472656,
"logps/rejected": -589.807373046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.883467674255371,
"rewards/margins": 43.719886779785156,
"rewards/rejected": -51.603355407714844,
"step": 567
},
{
"epoch": 0.62,
"learning_rate": 1.8e-05,
"logits/chosen": -0.19813589751720428,
"logits/rejected": -1.5698930025100708,
"logps/chosen": -486.477783203125,
"logps/rejected": -661.2116088867188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.44511079788208,
"rewards/margins": 55.299400329589844,
"rewards/rejected": -58.7445068359375,
"step": 568
},
{
"epoch": 0.62,
"learning_rate": 1.7948275862068965e-05,
"logits/chosen": -0.22892844676971436,
"logits/rejected": -1.4997096061706543,
"logps/chosen": -470.40216064453125,
"logps/rejected": -651.0798950195312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.123993873596191,
"rewards/margins": 48.75234603881836,
"rewards/rejected": -57.876338958740234,
"step": 569
},
{
"epoch": 0.62,
"learning_rate": 1.789655172413793e-05,
"logits/chosen": -0.10823440551757812,
"logits/rejected": -1.3152951002120972,
"logps/chosen": -547.5245971679688,
"logps/rejected": -685.3779907226562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.454561233520508,
"rewards/margins": 52.54243850708008,
"rewards/rejected": -56.99700164794922,
"step": 570
},
{
"epoch": 0.62,
"learning_rate": 1.7844827586206898e-05,
"logits/chosen": -0.24758121371269226,
"logits/rejected": -1.208099603652954,
"logps/chosen": -401.03070068359375,
"logps/rejected": -678.6541137695312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.605196952819824,
"rewards/margins": 49.06074142456055,
"rewards/rejected": -56.66593551635742,
"step": 571
},
{
"epoch": 0.62,
"learning_rate": 1.7793103448275862e-05,
"logits/chosen": -0.2494858354330063,
"logits/rejected": -1.3483632802963257,
"logps/chosen": -478.4145812988281,
"logps/rejected": -692.2071533203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.4422650337219238,
"rewards/margins": 55.957786560058594,
"rewards/rejected": -57.400054931640625,
"step": 572
},
{
"epoch": 0.63,
"learning_rate": 1.7741379310344827e-05,
"logits/chosen": -0.18455466628074646,
"logits/rejected": -1.5773600339889526,
"logps/chosen": -532.016845703125,
"logps/rejected": -631.9456787109375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.839169502258301,
"rewards/margins": 52.62319564819336,
"rewards/rejected": -55.462364196777344,
"step": 573
},
{
"epoch": 0.63,
"learning_rate": 1.7689655172413795e-05,
"logits/chosen": -0.08394797146320343,
"logits/rejected": -1.2678709030151367,
"logps/chosen": -426.6719665527344,
"logps/rejected": -693.8532104492188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.079269409179688,
"rewards/margins": 54.31288528442383,
"rewards/rejected": -62.39215087890625,
"step": 574
},
{
"epoch": 0.63,
"learning_rate": 1.763793103448276e-05,
"logits/chosen": -0.13648506999015808,
"logits/rejected": -1.4690591096878052,
"logps/chosen": -586.6487426757812,
"logps/rejected": -710.5147094726562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.839778184890747,
"rewards/margins": 59.91093444824219,
"rewards/rejected": -61.750709533691406,
"step": 575
},
{
"epoch": 0.63,
"learning_rate": 1.7586206896551728e-05,
"logits/chosen": -0.21827536821365356,
"logits/rejected": -1.2792953252792358,
"logps/chosen": -414.493408203125,
"logps/rejected": -647.998779296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.311338901519775,
"rewards/margins": 51.5853157043457,
"rewards/rejected": -56.89664840698242,
"step": 576
},
{
"epoch": 0.63,
"learning_rate": 1.7534482758620692e-05,
"logits/chosen": -0.0653618648648262,
"logits/rejected": -1.6563713550567627,
"logps/chosen": -604.5464477539062,
"logps/rejected": -647.69873046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.1551756858825684,
"rewards/margins": 54.157005310058594,
"rewards/rejected": -55.31217956542969,
"step": 577
},
{
"epoch": 0.63,
"learning_rate": 1.7482758620689657e-05,
"logits/chosen": -0.10746625810861588,
"logits/rejected": -1.0887423753738403,
"logps/chosen": -423.400634765625,
"logps/rejected": -635.4210205078125,
"loss": 0.6823,
"rewards/accuracies": 0.9375,
"rewards/chosen": -7.090230941772461,
"rewards/margins": 45.47228240966797,
"rewards/rejected": -52.56251525878906,
"step": 578
},
{
"epoch": 0.63,
"learning_rate": 1.743103448275862e-05,
"logits/chosen": -0.2545757591724396,
"logits/rejected": -1.3590258359909058,
"logps/chosen": -404.650146484375,
"logps/rejected": -669.2538452148438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.74318265914917,
"rewards/margins": 56.251548767089844,
"rewards/rejected": -58.99473190307617,
"step": 579
},
{
"epoch": 0.63,
"learning_rate": 1.7379310344827586e-05,
"logits/chosen": -0.050807081162929535,
"logits/rejected": -1.2381399869918823,
"logps/chosen": -412.51385498046875,
"logps/rejected": -616.2285766601562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.05122709274292,
"rewards/margins": 50.5135498046875,
"rewards/rejected": -53.564781188964844,
"step": 580
},
{
"epoch": 0.63,
"learning_rate": 1.732758620689655e-05,
"logits/chosen": -0.14367303252220154,
"logits/rejected": -1.3293488025665283,
"logps/chosen": -436.77374267578125,
"logps/rejected": -644.4839477539062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.5984394550323486,
"rewards/margins": 51.456111907958984,
"rewards/rejected": -55.0545539855957,
"step": 581
},
{
"epoch": 0.63,
"learning_rate": 1.727586206896552e-05,
"logits/chosen": -0.08829887211322784,
"logits/rejected": -1.4413114786148071,
"logps/chosen": -538.6859130859375,
"logps/rejected": -633.6636962890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.367769718170166,
"rewards/margins": 54.034610748291016,
"rewards/rejected": -56.40237808227539,
"step": 582
},
{
"epoch": 0.64,
"learning_rate": 1.7224137931034483e-05,
"logits/chosen": -0.35657984018325806,
"logits/rejected": -1.4725849628448486,
"logps/chosen": -414.2039794921875,
"logps/rejected": -550.0541381835938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.6985023021698,
"rewards/margins": 46.69954299926758,
"rewards/rejected": -49.39804458618164,
"step": 583
},
{
"epoch": 0.64,
"learning_rate": 1.717241379310345e-05,
"logits/chosen": -0.08540710806846619,
"logits/rejected": -1.550531268119812,
"logps/chosen": -530.1245727539062,
"logps/rejected": -635.4656372070312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.296605110168457,
"rewards/margins": 48.70091247558594,
"rewards/rejected": -54.99751663208008,
"step": 584
},
{
"epoch": 0.64,
"learning_rate": 1.7120689655172416e-05,
"logits/chosen": -0.11361716687679291,
"logits/rejected": -1.359609842300415,
"logps/chosen": -429.12786865234375,
"logps/rejected": -649.3413696289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.8643945455551147,
"rewards/margins": 53.536781311035156,
"rewards/rejected": -54.40117645263672,
"step": 585
},
{
"epoch": 0.64,
"learning_rate": 1.706896551724138e-05,
"logits/chosen": -0.24846045672893524,
"logits/rejected": -1.479831576347351,
"logps/chosen": -515.0034790039062,
"logps/rejected": -680.9791870117188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7362096309661865,
"rewards/margins": 52.485355377197266,
"rewards/rejected": -51.749141693115234,
"step": 586
},
{
"epoch": 0.64,
"learning_rate": 1.7017241379310345e-05,
"logits/chosen": -0.3287639617919922,
"logits/rejected": -1.1477540731430054,
"logps/chosen": -367.2208251953125,
"logps/rejected": -636.5546264648438,
"loss": 0.0023,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.831266403198242,
"rewards/margins": 45.8513069152832,
"rewards/rejected": -50.68257522583008,
"step": 587
},
{
"epoch": 0.64,
"learning_rate": 1.696551724137931e-05,
"logits/chosen": -0.2563868463039398,
"logits/rejected": -1.21188485622406,
"logps/chosen": -340.62530517578125,
"logps/rejected": -597.3062744140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.9416985511779785,
"rewards/margins": 44.73276901245117,
"rewards/rejected": -49.67446517944336,
"step": 588
},
{
"epoch": 0.64,
"learning_rate": 1.6913793103448274e-05,
"logits/chosen": -0.06057710573077202,
"logits/rejected": -1.5127232074737549,
"logps/chosen": -515.742919921875,
"logps/rejected": -595.0543212890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.528551697731018,
"rewards/margins": 50.152740478515625,
"rewards/rejected": -51.68128967285156,
"step": 589
},
{
"epoch": 0.64,
"learning_rate": 1.6862068965517242e-05,
"logits/chosen": -0.2441636025905609,
"logits/rejected": -1.4141565561294556,
"logps/chosen": -401.9132995605469,
"logps/rejected": -682.8711547851562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.38480621576309204,
"rewards/margins": 52.949195861816406,
"rewards/rejected": -52.56439208984375,
"step": 590
},
{
"epoch": 0.64,
"learning_rate": 1.6810344827586207e-05,
"logits/chosen": -0.19429653882980347,
"logits/rejected": -1.3483132123947144,
"logps/chosen": -394.2885437011719,
"logps/rejected": -612.275634765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.2922842502593994,
"rewards/margins": 52.64678955078125,
"rewards/rejected": -52.9390754699707,
"step": 591
},
{
"epoch": 0.65,
"learning_rate": 1.6758620689655175e-05,
"logits/chosen": -0.1201917976140976,
"logits/rejected": -1.3542145490646362,
"logps/chosen": -425.7287292480469,
"logps/rejected": -636.2640991210938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.1215896606445312,
"rewards/margins": 54.03361892700195,
"rewards/rejected": -50.912025451660156,
"step": 592
},
{
"epoch": 0.65,
"learning_rate": 1.670689655172414e-05,
"logits/chosen": -0.2743023931980133,
"logits/rejected": -1.4589341878890991,
"logps/chosen": -355.8106689453125,
"logps/rejected": -547.2426147460938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.09041150659322739,
"rewards/margins": 46.82219314575195,
"rewards/rejected": -46.731781005859375,
"step": 593
},
{
"epoch": 0.65,
"learning_rate": 1.6655172413793104e-05,
"logits/chosen": -0.2365323305130005,
"logits/rejected": -1.5025275945663452,
"logps/chosen": -385.47705078125,
"logps/rejected": -538.5193481445312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.30189573764801025,
"rewards/margins": 46.392642974853516,
"rewards/rejected": -46.69453811645508,
"step": 594
},
{
"epoch": 0.65,
"learning_rate": 1.6603448275862072e-05,
"logits/chosen": -0.1523529291152954,
"logits/rejected": -1.3015763759613037,
"logps/chosen": -412.3084716796875,
"logps/rejected": -591.6860961914062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.2983438968658447,
"rewards/margins": 45.98234558105469,
"rewards/rejected": -46.28068542480469,
"step": 595
},
{
"epoch": 0.65,
"learning_rate": 1.6551724137931037e-05,
"logits/chosen": -0.0005629090592265129,
"logits/rejected": -1.2052149772644043,
"logps/chosen": -383.7427673339844,
"logps/rejected": -578.141357421875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.46424204111099243,
"rewards/margins": 48.80424499511719,
"rewards/rejected": -48.34000778198242,
"step": 596
},
{
"epoch": 0.65,
"learning_rate": 1.65e-05,
"logits/chosen": -0.14516018331050873,
"logits/rejected": -1.4024372100830078,
"logps/chosen": -506.8284912109375,
"logps/rejected": -537.9654541015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7340108156204224,
"rewards/margins": 46.76782989501953,
"rewards/rejected": -46.033817291259766,
"step": 597
},
{
"epoch": 0.65,
"learning_rate": 1.6448275862068966e-05,
"logits/chosen": -0.13159377872943878,
"logits/rejected": -1.1646668910980225,
"logps/chosen": -351.59735107421875,
"logps/rejected": -531.7355346679688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.1915807723999023,
"rewards/margins": 41.97750473022461,
"rewards/rejected": -44.169090270996094,
"step": 598
},
{
"epoch": 0.65,
"learning_rate": 1.639655172413793e-05,
"logits/chosen": -0.12550602853298187,
"logits/rejected": -1.2537415027618408,
"logps/chosen": -360.52362060546875,
"logps/rejected": -534.72265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.4122576713562012,
"rewards/margins": 43.383888244628906,
"rewards/rejected": -41.97162628173828,
"step": 599
},
{
"epoch": 0.65,
"learning_rate": 1.63448275862069e-05,
"logits/chosen": -0.35067713260650635,
"logits/rejected": -1.285046100616455,
"logps/chosen": -342.4931640625,
"logps/rejected": -598.63330078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.16610080003738403,
"rewards/margins": 50.52566909790039,
"rewards/rejected": -50.35956573486328,
"step": 600
},
{
"epoch": 0.66,
"learning_rate": 1.6293103448275863e-05,
"logits/chosen": -0.05313819646835327,
"logits/rejected": -1.6483476161956787,
"logps/chosen": -498.56707763671875,
"logps/rejected": -560.79541015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 7.678995609283447,
"rewards/margins": 56.548095703125,
"rewards/rejected": -48.86909866333008,
"step": 601
},
{
"epoch": 0.66,
"learning_rate": 1.6241379310344828e-05,
"logits/chosen": -0.00626419298350811,
"logits/rejected": -1.4823583364486694,
"logps/chosen": -574.1875,
"logps/rejected": -544.60302734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.469341278076172,
"rewards/margins": 46.32347106933594,
"rewards/rejected": -43.8541259765625,
"step": 602
},
{
"epoch": 0.66,
"learning_rate": 1.6189655172413796e-05,
"logits/chosen": -0.2479826658964157,
"logits/rejected": -1.2744426727294922,
"logps/chosen": -427.8579406738281,
"logps/rejected": -573.8703002929688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.790971040725708,
"rewards/margins": 44.90638732910156,
"rewards/rejected": -43.11541748046875,
"step": 603
},
{
"epoch": 0.66,
"learning_rate": 1.613793103448276e-05,
"logits/chosen": -0.22728334367275238,
"logits/rejected": -1.0308204889297485,
"logps/chosen": -311.8193359375,
"logps/rejected": -536.7919311523438,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.5045533180236816,
"rewards/margins": 35.646881103515625,
"rewards/rejected": -39.151432037353516,
"step": 604
},
{
"epoch": 0.66,
"learning_rate": 1.6086206896551725e-05,
"logits/chosen": -0.5185431838035583,
"logits/rejected": -1.3834552764892578,
"logps/chosen": -269.7243957519531,
"logps/rejected": -575.7864379882812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.5515775680541992,
"rewards/margins": 45.755775451660156,
"rewards/rejected": -46.30735397338867,
"step": 605
},
{
"epoch": 0.66,
"learning_rate": 1.603448275862069e-05,
"logits/chosen": -0.2218950241804123,
"logits/rejected": -1.3695735931396484,
"logps/chosen": -407.8547058105469,
"logps/rejected": -541.52099609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.885260581970215,
"rewards/margins": 42.87828826904297,
"rewards/rejected": -45.763553619384766,
"step": 606
},
{
"epoch": 0.66,
"learning_rate": 1.5982758620689654e-05,
"logits/chosen": -0.0793599933385849,
"logits/rejected": -1.3909116983413696,
"logps/chosen": -479.3802490234375,
"logps/rejected": -564.6279296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.8253229856491089,
"rewards/margins": 46.38885498046875,
"rewards/rejected": -45.563533782958984,
"step": 607
},
{
"epoch": 0.66,
"learning_rate": 1.5931034482758622e-05,
"logits/chosen": -0.2918356955051422,
"logits/rejected": -1.4191017150878906,
"logps/chosen": -426.25250244140625,
"logps/rejected": -561.0745849609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.03518211841583252,
"rewards/margins": 48.18317413330078,
"rewards/rejected": -48.218353271484375,
"step": 608
},
{
"epoch": 0.66,
"learning_rate": 1.5879310344827587e-05,
"logits/chosen": -0.02587204799056053,
"logits/rejected": -1.6397631168365479,
"logps/chosen": -512.5316772460938,
"logps/rejected": -578.6962890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.294554233551025,
"rewards/margins": 54.153038024902344,
"rewards/rejected": -47.85848617553711,
"step": 609
},
{
"epoch": 0.67,
"learning_rate": 1.582758620689655e-05,
"logits/chosen": -0.1111781969666481,
"logits/rejected": -1.660740852355957,
"logps/chosen": -539.9187622070312,
"logps/rejected": -529.7341918945312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.2654643058776855,
"rewards/margins": 49.64447021484375,
"rewards/rejected": -44.37900161743164,
"step": 610
},
{
"epoch": 0.67,
"learning_rate": 1.577586206896552e-05,
"logits/chosen": -0.34613269567489624,
"logits/rejected": -1.256672739982605,
"logps/chosen": -286.6711730957031,
"logps/rejected": -601.25927734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.5742961168289185,
"rewards/margins": 49.86055374145508,
"rewards/rejected": -48.286258697509766,
"step": 611
},
{
"epoch": 0.67,
"learning_rate": 1.5724137931034484e-05,
"logits/chosen": 0.08210857212543488,
"logits/rejected": -1.394779920578003,
"logps/chosen": -454.6331481933594,
"logps/rejected": -548.888671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.741332530975342,
"rewards/margins": 50.020511627197266,
"rewards/rejected": -47.279178619384766,
"step": 612
},
{
"epoch": 0.67,
"learning_rate": 1.567241379310345e-05,
"logits/chosen": -0.14018212258815765,
"logits/rejected": -1.1777931451797485,
"logps/chosen": -330.23046875,
"logps/rejected": -555.2692260742188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.9217461347579956,
"rewards/margins": 44.80604934692383,
"rewards/rejected": -46.7277946472168,
"step": 613
},
{
"epoch": 0.67,
"learning_rate": 1.5620689655172417e-05,
"logits/chosen": -0.21515248715877533,
"logits/rejected": -1.533896565437317,
"logps/chosen": -451.9747314453125,
"logps/rejected": -555.5947265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.842181444168091,
"rewards/margins": 48.474666595458984,
"rewards/rejected": -45.63249206542969,
"step": 614
},
{
"epoch": 0.67,
"learning_rate": 1.556896551724138e-05,
"logits/chosen": -0.1645764410495758,
"logits/rejected": -1.1189565658569336,
"logps/chosen": -305.49365234375,
"logps/rejected": -509.23590087890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.9992731809616089,
"rewards/margins": 41.10477066040039,
"rewards/rejected": -43.104042053222656,
"step": 615
},
{
"epoch": 0.67,
"learning_rate": 1.5517241379310346e-05,
"logits/chosen": -0.04968830943107605,
"logits/rejected": -1.4535218477249146,
"logps/chosen": -488.84185791015625,
"logps/rejected": -516.9566040039062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.233278751373291,
"rewards/margins": 44.68144226074219,
"rewards/rejected": -40.44816970825195,
"step": 616
},
{
"epoch": 0.67,
"learning_rate": 1.546551724137931e-05,
"logits/chosen": -0.1743217259645462,
"logits/rejected": -1.4794538021087646,
"logps/chosen": -550.0068969726562,
"logps/rejected": -529.5560913085938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.273037910461426,
"rewards/margins": 44.289337158203125,
"rewards/rejected": -42.01629638671875,
"step": 617
},
{
"epoch": 0.67,
"learning_rate": 1.5413793103448275e-05,
"logits/chosen": -0.16211533546447754,
"logits/rejected": -1.1423048973083496,
"logps/chosen": -349.4170227050781,
"logps/rejected": -523.6246948242188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.9724212288856506,
"rewards/margins": 48.36107635498047,
"rewards/rejected": -47.38865280151367,
"step": 618
},
{
"epoch": 0.68,
"learning_rate": 1.5362068965517243e-05,
"logits/chosen": -0.15734046697616577,
"logits/rejected": -1.2859727144241333,
"logps/chosen": -335.3069763183594,
"logps/rejected": -533.359130859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.9588116407394409,
"rewards/margins": 42.21016311645508,
"rewards/rejected": -43.16897964477539,
"step": 619
},
{
"epoch": 0.68,
"learning_rate": 1.5310344827586208e-05,
"logits/chosen": -0.1451762467622757,
"logits/rejected": -1.2424870729446411,
"logps/chosen": -388.3422546386719,
"logps/rejected": -519.1555786132812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.18462783098220825,
"rewards/margins": 45.364524841308594,
"rewards/rejected": -45.54915237426758,
"step": 620
},
{
"epoch": 0.68,
"learning_rate": 1.5258620689655172e-05,
"logits/chosen": -0.033223796635866165,
"logits/rejected": -1.55014967918396,
"logps/chosen": -621.535400390625,
"logps/rejected": -508.3518371582031,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.288414478302002,
"rewards/margins": 45.626564025878906,
"rewards/rejected": -41.33815002441406,
"step": 621
},
{
"epoch": 0.68,
"learning_rate": 1.5206896551724139e-05,
"logits/chosen": -0.28730061650276184,
"logits/rejected": -1.3408746719360352,
"logps/chosen": -420.8293762207031,
"logps/rejected": -494.9945068359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.09170261025428772,
"rewards/margins": 42.52814865112305,
"rewards/rejected": -42.43645095825195,
"step": 622
},
{
"epoch": 0.68,
"learning_rate": 1.5155172413793103e-05,
"logits/chosen": -0.08658464252948761,
"logits/rejected": -1.4125157594680786,
"logps/chosen": -446.3509521484375,
"logps/rejected": -545.7614135742188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.2800441086292267,
"rewards/margins": 45.323646545410156,
"rewards/rejected": -45.043601989746094,
"step": 623
},
{
"epoch": 0.68,
"learning_rate": 1.5103448275862071e-05,
"logits/chosen": -0.2937692403793335,
"logits/rejected": -1.3026137351989746,
"logps/chosen": -320.6386413574219,
"logps/rejected": -528.2933959960938,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7214214205741882,
"rewards/margins": 44.59417724609375,
"rewards/rejected": -43.87274932861328,
"step": 624
},
{
"epoch": 0.68,
"learning_rate": 1.5051724137931036e-05,
"logits/chosen": -0.15354903042316437,
"logits/rejected": -1.4917157888412476,
"logps/chosen": -394.09259033203125,
"logps/rejected": -537.6986694335938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.2884288728237152,
"rewards/margins": 45.02061080932617,
"rewards/rejected": -45.30903625488281,
"step": 625
},
{
"epoch": 0.68,
"learning_rate": 1.5e-05,
"logits/chosen": -0.0401911586523056,
"logits/rejected": -1.4450793266296387,
"logps/chosen": -405.8299255371094,
"logps/rejected": -544.3627319335938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.1770844459533691,
"rewards/margins": 47.842506408691406,
"rewards/rejected": -46.66542053222656,
"step": 626
},
{
"epoch": 0.68,
"learning_rate": 1.4948275862068967e-05,
"logits/chosen": -0.08096438646316528,
"logits/rejected": -1.5375018119812012,
"logps/chosen": -469.0930480957031,
"logps/rejected": -517.4960327148438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.0593535900115967,
"rewards/margins": 44.87061309814453,
"rewards/rejected": -41.811256408691406,
"step": 627
},
{
"epoch": 0.69,
"learning_rate": 1.4896551724137931e-05,
"logits/chosen": -0.10965342819690704,
"logits/rejected": -1.202269434928894,
"logps/chosen": -384.6773681640625,
"logps/rejected": -531.308349609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.8238025903701782,
"rewards/margins": 43.14710235595703,
"rewards/rejected": -42.32329177856445,
"step": 628
},
{
"epoch": 0.69,
"learning_rate": 1.4844827586206896e-05,
"logits/chosen": -0.06810637563467026,
"logits/rejected": -1.3470923900604248,
"logps/chosen": -437.27947998046875,
"logps/rejected": -509.29443359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.51701545715332,
"rewards/margins": 46.15340042114258,
"rewards/rejected": -41.636383056640625,
"step": 629
},
{
"epoch": 0.69,
"learning_rate": 1.4793103448275864e-05,
"logits/chosen": -0.2248406708240509,
"logits/rejected": -1.3975605964660645,
"logps/chosen": -341.30010986328125,
"logps/rejected": -519.501953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.0808305740356445,
"rewards/margins": 40.74700164794922,
"rewards/rejected": -42.82783126831055,
"step": 630
},
{
"epoch": 0.69,
"learning_rate": 1.4741379310344829e-05,
"logits/chosen": -0.1267438530921936,
"logits/rejected": -1.2797744274139404,
"logps/chosen": -402.70172119140625,
"logps/rejected": -568.7130737304688,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.3171030580997467,
"rewards/margins": 46.492828369140625,
"rewards/rejected": -46.17572021484375,
"step": 631
},
{
"epoch": 0.69,
"learning_rate": 1.4689655172413795e-05,
"logits/chosen": -0.27014362812042236,
"logits/rejected": -1.4330971240997314,
"logps/chosen": -315.55706787109375,
"logps/rejected": -537.5396118164062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.189436912536621,
"rewards/margins": 47.06514358520508,
"rewards/rejected": -43.875709533691406,
"step": 632
},
{
"epoch": 0.69,
"learning_rate": 1.463793103448276e-05,
"logits/chosen": -0.3762741684913635,
"logits/rejected": -1.147342324256897,
"logps/chosen": -306.3317565917969,
"logps/rejected": -525.963623046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.08659607172012329,
"rewards/margins": 43.48544692993164,
"rewards/rejected": -43.572044372558594,
"step": 633
},
{
"epoch": 0.69,
"learning_rate": 1.4586206896551724e-05,
"logits/chosen": -0.24545836448669434,
"logits/rejected": -1.2215213775634766,
"logps/chosen": -313.8126220703125,
"logps/rejected": -523.89111328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.9955374598503113,
"rewards/margins": 42.0698127746582,
"rewards/rejected": -43.06534957885742,
"step": 634
},
{
"epoch": 0.69,
"learning_rate": 1.4534482758620692e-05,
"logits/chosen": -0.3359462022781372,
"logits/rejected": -1.3295055627822876,
"logps/chosen": -422.6155090332031,
"logps/rejected": -530.6246337890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5714225769042969,
"rewards/margins": 41.921669006347656,
"rewards/rejected": -41.350242614746094,
"step": 635
},
{
"epoch": 0.69,
"learning_rate": 1.4482758620689657e-05,
"logits/chosen": -0.13072825968265533,
"logits/rejected": -1.5437922477722168,
"logps/chosen": -520.2494506835938,
"logps/rejected": -502.7685546875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.3034181594848633,
"rewards/margins": 44.092994689941406,
"rewards/rejected": -40.789573669433594,
"step": 636
},
{
"epoch": 0.69,
"learning_rate": 1.4431034482758621e-05,
"logits/chosen": -0.04517197981476784,
"logits/rejected": -1.6300750970840454,
"logps/chosen": -465.6365966796875,
"logps/rejected": -516.446533203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.421183109283447,
"rewards/margins": 47.232208251953125,
"rewards/rejected": -42.81102752685547,
"step": 637
},
{
"epoch": 0.7,
"learning_rate": 1.4379310344827588e-05,
"logits/chosen": -0.015193352475762367,
"logits/rejected": -1.5817826986312866,
"logps/chosen": -502.16845703125,
"logps/rejected": -550.2406005859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.9052822589874268,
"rewards/margins": 49.294677734375,
"rewards/rejected": -46.38939666748047,
"step": 638
},
{
"epoch": 0.7,
"learning_rate": 1.4327586206896552e-05,
"logits/chosen": -0.31254029273986816,
"logits/rejected": -1.3829731941223145,
"logps/chosen": -282.6502380371094,
"logps/rejected": -471.7291564941406,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.455610752105713,
"rewards/margins": 39.598594665527344,
"rewards/rejected": -41.05420684814453,
"step": 639
},
{
"epoch": 0.7,
"learning_rate": 1.4275862068965518e-05,
"logits/chosen": -0.022501356899738312,
"logits/rejected": -1.5619714260101318,
"logps/chosen": -438.0868835449219,
"logps/rejected": -462.1986389160156,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.933338165283203,
"rewards/margins": 44.02751541137695,
"rewards/rejected": -40.09416961669922,
"step": 640
},
{
"epoch": 0.7,
"learning_rate": 1.4224137931034483e-05,
"logits/chosen": -0.25200387835502625,
"logits/rejected": -1.3560858964920044,
"logps/chosen": -398.2036437988281,
"logps/rejected": -535.743408203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.0920121669769287,
"rewards/margins": 46.25288391113281,
"rewards/rejected": -45.16087341308594,
"step": 641
},
{
"epoch": 0.7,
"learning_rate": 1.4172413793103448e-05,
"logits/chosen": -0.08297184109687805,
"logits/rejected": -1.4250469207763672,
"logps/chosen": -503.2852478027344,
"logps/rejected": -576.9325561523438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 4.053221702575684,
"rewards/margins": 50.68095779418945,
"rewards/rejected": -46.62773513793945,
"step": 642
},
{
"epoch": 0.7,
"learning_rate": 1.4120689655172416e-05,
"logits/chosen": 0.031028956174850464,
"logits/rejected": -1.5391318798065186,
"logps/chosen": -506.672119140625,
"logps/rejected": -528.0322875976562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.037855625152588,
"rewards/margins": 50.48542022705078,
"rewards/rejected": -45.44756317138672,
"step": 643
},
{
"epoch": 0.7,
"learning_rate": 1.406896551724138e-05,
"logits/chosen": -0.303537517786026,
"logits/rejected": -1.3789228200912476,
"logps/chosen": -358.866455078125,
"logps/rejected": -512.6773071289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.4551244378089905,
"rewards/margins": 42.338409423828125,
"rewards/rejected": -42.79353332519531,
"step": 644
},
{
"epoch": 0.7,
"learning_rate": 1.4017241379310345e-05,
"logits/chosen": -0.2305237501859665,
"logits/rejected": -1.196969747543335,
"logps/chosen": -333.74456787109375,
"logps/rejected": -562.4696655273438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.2080453634262085,
"rewards/margins": 43.72755813598633,
"rewards/rejected": -44.935604095458984,
"step": 645
},
{
"epoch": 0.7,
"learning_rate": 1.3965517241379311e-05,
"logits/chosen": -0.28576573729515076,
"logits/rejected": -1.430737853050232,
"logps/chosen": -381.3027648925781,
"logps/rejected": -523.885986328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.6614712476730347,
"rewards/margins": 40.87557601928711,
"rewards/rejected": -41.53704833984375,
"step": 646
},
{
"epoch": 0.71,
"learning_rate": 1.3913793103448276e-05,
"logits/chosen": -0.04188717156648636,
"logits/rejected": -1.3778163194656372,
"logps/chosen": -506.2252502441406,
"logps/rejected": -551.3240966796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.9459335803985596,
"rewards/margins": 48.985408782958984,
"rewards/rejected": -46.03947448730469,
"step": 647
},
{
"epoch": 0.71,
"learning_rate": 1.3862068965517244e-05,
"logits/chosen": -0.27598288655281067,
"logits/rejected": -1.0301058292388916,
"logps/chosen": -285.4984436035156,
"logps/rejected": -535.9169311523438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.29662734270095825,
"rewards/margins": 42.88330841064453,
"rewards/rejected": -43.179931640625,
"step": 648
},
{
"epoch": 0.71,
"learning_rate": 1.3810344827586208e-05,
"logits/chosen": -0.1300501823425293,
"logits/rejected": -1.5005356073379517,
"logps/chosen": -425.9429626464844,
"logps/rejected": -479.8569641113281,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.6732308864593506,
"rewards/margins": 41.68931198120117,
"rewards/rejected": -39.016082763671875,
"step": 649
},
{
"epoch": 0.71,
"learning_rate": 1.3758620689655173e-05,
"logits/chosen": -0.04178273305296898,
"logits/rejected": -1.523526906967163,
"logps/chosen": -423.0726318359375,
"logps/rejected": -539.8958129882812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.544985771179199,
"rewards/margins": 47.55220031738281,
"rewards/rejected": -45.0072135925293,
"step": 650
},
{
"epoch": 0.71,
"learning_rate": 1.370689655172414e-05,
"logits/chosen": -0.1655365526676178,
"logits/rejected": -1.5684573650360107,
"logps/chosen": -430.7422790527344,
"logps/rejected": -489.2760009765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.3517260551452637,
"rewards/margins": 44.93771743774414,
"rewards/rejected": -41.585994720458984,
"step": 651
},
{
"epoch": 0.71,
"learning_rate": 1.3655172413793104e-05,
"logits/chosen": -0.2269890308380127,
"logits/rejected": -1.4303154945373535,
"logps/chosen": -358.328369140625,
"logps/rejected": -570.949951171875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.13788434863090515,
"rewards/margins": 47.54113006591797,
"rewards/rejected": -47.40325164794922,
"step": 652
},
{
"epoch": 0.71,
"learning_rate": 1.3603448275862069e-05,
"logits/chosen": -0.39984795451164246,
"logits/rejected": -1.350335955619812,
"logps/chosen": -280.1457824707031,
"logps/rejected": -507.47808837890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.025997459888458252,
"rewards/margins": 41.7269401550293,
"rewards/rejected": -41.75293731689453,
"step": 653
},
{
"epoch": 0.71,
"learning_rate": 1.3551724137931037e-05,
"logits/chosen": -0.3223649561405182,
"logits/rejected": -1.3828343152999878,
"logps/chosen": -334.5537414550781,
"logps/rejected": -506.3958435058594,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.21468442678451538,
"rewards/margins": 44.35294723510742,
"rewards/rejected": -44.13825988769531,
"step": 654
},
{
"epoch": 0.71,
"learning_rate": 1.3500000000000001e-05,
"logits/chosen": -0.3293633759021759,
"logits/rejected": -1.333666443824768,
"logps/chosen": -323.5306701660156,
"logps/rejected": -511.315185546875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.06329803913831711,
"rewards/margins": 42.38307571411133,
"rewards/rejected": -42.446372985839844,
"step": 655
},
{
"epoch": 0.72,
"learning_rate": 1.3448275862068967e-05,
"logits/chosen": -0.11880247294902802,
"logits/rejected": -1.29387629032135,
"logps/chosen": -400.0235900878906,
"logps/rejected": -535.8289794921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.5334283709526062,
"rewards/margins": 44.15065383911133,
"rewards/rejected": -43.61722946166992,
"step": 656
},
{
"epoch": 0.72,
"learning_rate": 1.3396551724137932e-05,
"logits/chosen": -0.15652622282505035,
"logits/rejected": -1.434822916984558,
"logps/chosen": -408.1186218261719,
"logps/rejected": -553.8369140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.40162843465805054,
"rewards/margins": 47.67634582519531,
"rewards/rejected": -47.27471160888672,
"step": 657
},
{
"epoch": 0.72,
"learning_rate": 1.3344827586206897e-05,
"logits/chosen": -0.0915599837899208,
"logits/rejected": -1.5216375589370728,
"logps/chosen": -477.429443359375,
"logps/rejected": -531.134521484375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.0920250415802,
"rewards/margins": 45.700225830078125,
"rewards/rejected": -43.60820007324219,
"step": 658
},
{
"epoch": 0.72,
"learning_rate": 1.3293103448275863e-05,
"logits/chosen": -0.1342640519142151,
"logits/rejected": -1.3003381490707397,
"logps/chosen": -340.65655517578125,
"logps/rejected": -537.4246215820312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.2339905500411987,
"rewards/margins": 45.6250114440918,
"rewards/rejected": -46.8590087890625,
"step": 659
},
{
"epoch": 0.72,
"learning_rate": 1.3241379310344828e-05,
"logits/chosen": -0.2628743648529053,
"logits/rejected": -1.5235884189605713,
"logps/chosen": -385.9111633300781,
"logps/rejected": -488.7979431152344,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.9308697581291199,
"rewards/margins": 40.1331901550293,
"rewards/rejected": -41.06406021118164,
"step": 660
},
{
"epoch": 0.72,
"learning_rate": 1.3189655172413792e-05,
"logits/chosen": -0.35871365666389465,
"logits/rejected": -1.2679202556610107,
"logps/chosen": -331.3196716308594,
"logps/rejected": -539.1953125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.141901969909668,
"rewards/margins": 39.91340255737305,
"rewards/rejected": -41.05530548095703,
"step": 661
},
{
"epoch": 0.72,
"learning_rate": 1.313793103448276e-05,
"logits/chosen": -0.10699907690286636,
"logits/rejected": -1.1208184957504272,
"logps/chosen": -307.62115478515625,
"logps/rejected": -582.8983154296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.7876830101013184,
"rewards/margins": 46.260215759277344,
"rewards/rejected": -47.04790115356445,
"step": 662
},
{
"epoch": 0.72,
"learning_rate": 1.3086206896551725e-05,
"logits/chosen": -0.12584511935710907,
"logits/rejected": -1.3415498733520508,
"logps/chosen": -445.26910400390625,
"logps/rejected": -551.9942016601562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.583847999572754,
"rewards/margins": 46.69656753540039,
"rewards/rejected": -43.11271667480469,
"step": 663
},
{
"epoch": 0.72,
"learning_rate": 1.3034482758620691e-05,
"logits/chosen": -0.039403751492500305,
"logits/rejected": -1.5524853467941284,
"logps/chosen": -431.6235656738281,
"logps/rejected": -548.6947021484375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.0976274013519287,
"rewards/margins": 46.144187927246094,
"rewards/rejected": -48.2418098449707,
"step": 664
},
{
"epoch": 0.73,
"learning_rate": 1.2982758620689656e-05,
"logits/chosen": -0.07293981313705444,
"logits/rejected": -1.555285930633545,
"logps/chosen": -477.1157531738281,
"logps/rejected": -531.8021240234375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.3638932704925537,
"rewards/margins": 47.931007385253906,
"rewards/rejected": -44.567115783691406,
"step": 665
},
{
"epoch": 0.73,
"learning_rate": 1.293103448275862e-05,
"logits/chosen": -0.11820126324892044,
"logits/rejected": -1.6684420108795166,
"logps/chosen": -517.3621215820312,
"logps/rejected": -509.4004211425781,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.188424587249756,
"rewards/margins": 45.912174224853516,
"rewards/rejected": -42.723751068115234,
"step": 666
},
{
"epoch": 0.73,
"learning_rate": 1.2879310344827588e-05,
"logits/chosen": -0.05734536051750183,
"logits/rejected": -1.5235246419906616,
"logps/chosen": -592.1263427734375,
"logps/rejected": -585.6410522460938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 8.330058097839355,
"rewards/margins": 54.89848327636719,
"rewards/rejected": -46.56842041015625,
"step": 667
},
{
"epoch": 0.73,
"learning_rate": 1.2827586206896553e-05,
"logits/chosen": -0.23646149039268494,
"logits/rejected": -1.4570469856262207,
"logps/chosen": -388.5771484375,
"logps/rejected": -562.6555786132812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.438934803009033,
"rewards/margins": 48.871097564697266,
"rewards/rejected": -46.432159423828125,
"step": 668
},
{
"epoch": 0.73,
"learning_rate": 1.2775862068965518e-05,
"logits/chosen": -0.277557909488678,
"logits/rejected": -1.520776391029358,
"logps/chosen": -431.8119812011719,
"logps/rejected": -535.2166748046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.241364002227783,
"rewards/margins": 47.845359802246094,
"rewards/rejected": -45.60399627685547,
"step": 669
},
{
"epoch": 0.73,
"learning_rate": 1.2724137931034484e-05,
"logits/chosen": -0.37299636006355286,
"logits/rejected": -1.433702826499939,
"logps/chosen": -367.0413513183594,
"logps/rejected": -529.3248901367188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.2390081882476807,
"rewards/margins": 44.13026428222656,
"rewards/rejected": -41.89125442504883,
"step": 670
},
{
"epoch": 0.73,
"learning_rate": 1.2672413793103449e-05,
"logits/chosen": -0.135738343000412,
"logits/rejected": -1.4803038835525513,
"logps/chosen": -486.78131103515625,
"logps/rejected": -586.236572265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.0751945972442627,
"rewards/margins": 44.44581604003906,
"rewards/rejected": -45.52101516723633,
"step": 671
},
{
"epoch": 0.73,
"learning_rate": 1.2620689655172417e-05,
"logits/chosen": -0.37156784534454346,
"logits/rejected": -1.2309331893920898,
"logps/chosen": -310.4812927246094,
"logps/rejected": -520.0112915039062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.6325098276138306,
"rewards/margins": 42.75358963012695,
"rewards/rejected": -41.12108612060547,
"step": 672
},
{
"epoch": 0.73,
"learning_rate": 1.256896551724138e-05,
"logits/chosen": -0.20378383994102478,
"logits/rejected": -1.3526654243469238,
"logps/chosen": -379.8397521972656,
"logps/rejected": -542.7678833007812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.5514822006225586,
"rewards/margins": 43.52738571166992,
"rewards/rejected": -44.07886505126953,
"step": 673
},
{
"epoch": 0.74,
"learning_rate": 1.2517241379310344e-05,
"logits/chosen": -0.07714121043682098,
"logits/rejected": -1.528071403503418,
"logps/chosen": -472.7803955078125,
"logps/rejected": -530.1329345703125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 5.302211284637451,
"rewards/margins": 50.1279411315918,
"rewards/rejected": -44.82572555541992,
"step": 674
},
{
"epoch": 0.74,
"learning_rate": 1.2465517241379312e-05,
"logits/chosen": -0.03753519058227539,
"logits/rejected": -1.259669303894043,
"logps/chosen": -373.8651123046875,
"logps/rejected": -540.652099609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7355949878692627,
"rewards/margins": 44.318416595458984,
"rewards/rejected": -43.58282470703125,
"step": 675
},
{
"epoch": 0.74,
"learning_rate": 1.2413793103448277e-05,
"logits/chosen": -0.4580439329147339,
"logits/rejected": -1.498665690422058,
"logps/chosen": -304.34051513671875,
"logps/rejected": -517.0997314453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.3485918045043945,
"rewards/margins": 46.20613098144531,
"rewards/rejected": -42.8575439453125,
"step": 676
},
{
"epoch": 0.74,
"learning_rate": 1.2362068965517241e-05,
"logits/chosen": -0.08015082776546478,
"logits/rejected": -1.5275059938430786,
"logps/chosen": -477.7775573730469,
"logps/rejected": -539.4383544921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 3.337691307067871,
"rewards/margins": 48.43022155761719,
"rewards/rejected": -45.092533111572266,
"step": 677
},
{
"epoch": 0.74,
"learning_rate": 1.2310344827586208e-05,
"logits/chosen": -0.07246221601963043,
"logits/rejected": -1.1152292490005493,
"logps/chosen": -283.9908752441406,
"logps/rejected": -551.6624755859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.0209674835205078,
"rewards/margins": 47.72657012939453,
"rewards/rejected": -46.70560073852539,
"step": 678
},
{
"epoch": 0.74,
"learning_rate": 1.2258620689655172e-05,
"logits/chosen": -0.17554022371768951,
"logits/rejected": -1.381176471710205,
"logps/chosen": -391.78155517578125,
"logps/rejected": -587.4243774414062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.602041721343994,
"rewards/margins": 51.59418869018555,
"rewards/rejected": -48.99215316772461,
"step": 679
},
{
"epoch": 0.74,
"learning_rate": 1.220689655172414e-05,
"logits/chosen": -0.17825302481651306,
"logits/rejected": -1.2341221570968628,
"logps/chosen": -376.4874267578125,
"logps/rejected": -495.99993896484375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.1336874961853027,
"rewards/margins": 40.05615997314453,
"rewards/rejected": -38.92247009277344,
"step": 680
},
{
"epoch": 0.74,
"learning_rate": 1.2155172413793105e-05,
"logits/chosen": -0.26450762152671814,
"logits/rejected": -1.11971914768219,
"logps/chosen": -328.3924255371094,
"logps/rejected": -612.40673828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.4581549167633057,
"rewards/margins": 45.34051513671875,
"rewards/rejected": -46.798667907714844,
"step": 681
},
{
"epoch": 0.74,
"learning_rate": 1.210344827586207e-05,
"logits/chosen": -0.21210908889770508,
"logits/rejected": -1.5598255395889282,
"logps/chosen": -469.20172119140625,
"logps/rejected": -538.340087890625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.307070732116699,
"rewards/margins": 50.93186950683594,
"rewards/rejected": -44.62479782104492,
"step": 682
},
{
"epoch": 0.75,
"learning_rate": 1.2051724137931036e-05,
"logits/chosen": -0.1790524572134018,
"logits/rejected": -1.5198571681976318,
"logps/chosen": -408.3398132324219,
"logps/rejected": -512.6113891601562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.877450704574585,
"rewards/margins": 47.00334167480469,
"rewards/rejected": -44.125892639160156,
"step": 683
},
{
"epoch": 0.75,
"learning_rate": 1.2e-05,
"logits/chosen": -0.08723405003547668,
"logits/rejected": -1.3432382345199585,
"logps/chosen": -401.7087707519531,
"logps/rejected": -542.4974975585938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.334695339202881,
"rewards/margins": 46.966678619384766,
"rewards/rejected": -44.631988525390625,
"step": 684
},
{
"epoch": 0.75,
"learning_rate": 1.1948275862068965e-05,
"logits/chosen": -0.14494843780994415,
"logits/rejected": -1.2598520517349243,
"logps/chosen": -376.4900817871094,
"logps/rejected": -536.0132446289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.4198228418827057,
"rewards/margins": 41.54653549194336,
"rewards/rejected": -41.126708984375,
"step": 685
},
{
"epoch": 0.75,
"learning_rate": 1.1896551724137933e-05,
"logits/chosen": 0.07660377770662308,
"logits/rejected": -1.5494967699050903,
"logps/chosen": -583.0078735351562,
"logps/rejected": -480.3558349609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.250246047973633,
"rewards/margins": 44.277164459228516,
"rewards/rejected": -38.02691650390625,
"step": 686
},
{
"epoch": 0.75,
"learning_rate": 1.1844827586206898e-05,
"logits/chosen": -0.38664710521698,
"logits/rejected": -1.5083786249160767,
"logps/chosen": -289.0353698730469,
"logps/rejected": -502.0042419433594,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.9512491226196289,
"rewards/margins": 42.77705383300781,
"rewards/rejected": -43.72829818725586,
"step": 687
},
{
"epoch": 0.75,
"learning_rate": 1.1793103448275864e-05,
"logits/chosen": -0.042457547038793564,
"logits/rejected": -1.386946201324463,
"logps/chosen": -455.3371276855469,
"logps/rejected": -545.7581176757812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.2653028964996338,
"rewards/margins": 46.720619201660156,
"rewards/rejected": -45.45531463623047,
"step": 688
},
{
"epoch": 0.75,
"learning_rate": 1.1741379310344828e-05,
"logits/chosen": -0.4539385139942169,
"logits/rejected": -1.2734832763671875,
"logps/chosen": -255.11451721191406,
"logps/rejected": -506.87811279296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.33655714988708496,
"rewards/margins": 41.31004333496094,
"rewards/rejected": -40.973487854003906,
"step": 689
},
{
"epoch": 0.75,
"learning_rate": 1.1689655172413793e-05,
"logits/chosen": -0.2328207790851593,
"logits/rejected": -1.257619023323059,
"logps/chosen": -375.7318115234375,
"logps/rejected": -545.8134765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.9642629623413086,
"rewards/margins": 43.943382263183594,
"rewards/rejected": -44.90764617919922,
"step": 690
},
{
"epoch": 0.75,
"learning_rate": 1.163793103448276e-05,
"logits/chosen": 0.0281175896525383,
"logits/rejected": -1.4880707263946533,
"logps/chosen": -515.5869140625,
"logps/rejected": -544.9164428710938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.243173122406006,
"rewards/margins": 45.39672088623047,
"rewards/rejected": -47.639892578125,
"step": 691
},
{
"epoch": 0.75,
"learning_rate": 1.1586206896551724e-05,
"logits/chosen": -0.2516327500343323,
"logits/rejected": -1.316880702972412,
"logps/chosen": -299.51953125,
"logps/rejected": -528.8114624023438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.6539808511734009,
"rewards/margins": 43.63589859008789,
"rewards/rejected": -44.28988265991211,
"step": 692
},
{
"epoch": 0.76,
"learning_rate": 1.1534482758620689e-05,
"logits/chosen": -0.00018626078963279724,
"logits/rejected": -1.4975652694702148,
"logps/chosen": -448.61126708984375,
"logps/rejected": -538.84375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.434826374053955,
"rewards/margins": 48.413856506347656,
"rewards/rejected": -45.979034423828125,
"step": 693
},
{
"epoch": 0.76,
"learning_rate": 1.1482758620689657e-05,
"logits/chosen": -0.16736753284931183,
"logits/rejected": -1.333862543106079,
"logps/chosen": -464.8886413574219,
"logps/rejected": -554.8616943359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.5128366947174072,
"rewards/margins": 47.98447036743164,
"rewards/rejected": -46.47163772583008,
"step": 694
},
{
"epoch": 0.76,
"learning_rate": 1.1431034482758621e-05,
"logits/chosen": -0.33041834831237793,
"logits/rejected": -1.2662274837493896,
"logps/chosen": -372.60516357421875,
"logps/rejected": -512.045654296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.0543805360794067,
"rewards/margins": 42.66836166381836,
"rewards/rejected": -41.61397933959961,
"step": 695
},
{
"epoch": 0.76,
"learning_rate": 1.1379310344827587e-05,
"logits/chosen": -0.24941149353981018,
"logits/rejected": -1.3205037117004395,
"logps/chosen": -318.0282897949219,
"logps/rejected": -536.583984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.4145708084106445,
"rewards/margins": 48.180206298828125,
"rewards/rejected": -45.76564025878906,
"step": 696
},
{
"epoch": 0.76,
"learning_rate": 1.1327586206896552e-05,
"logits/chosen": -0.1426786631345749,
"logits/rejected": -1.5278555154800415,
"logps/chosen": -491.4092712402344,
"logps/rejected": -490.41351318359375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 6.8129377365112305,
"rewards/margins": 47.30105209350586,
"rewards/rejected": -40.48811721801758,
"step": 697
},
{
"epoch": 0.76,
"learning_rate": 1.1275862068965517e-05,
"logits/chosen": -0.2483963519334793,
"logits/rejected": -1.4913365840911865,
"logps/chosen": -435.83770751953125,
"logps/rejected": -544.1882934570312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.600954294204712,
"rewards/margins": 47.01934814453125,
"rewards/rejected": -44.418392181396484,
"step": 698
},
{
"epoch": 0.76,
"learning_rate": 1.1224137931034483e-05,
"logits/chosen": -0.24883654713630676,
"logits/rejected": -1.4840902090072632,
"logps/chosen": -385.3328857421875,
"logps/rejected": -508.5963439941406,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": 2.485741376876831,
"rewards/margins": 45.306007385253906,
"rewards/rejected": -42.82026672363281,
"step": 699
},
{
"epoch": 0.76,
"learning_rate": 1.117241379310345e-05,
"logits/chosen": -0.26029643416404724,
"logits/rejected": -1.319836139678955,
"logps/chosen": -328.52813720703125,
"logps/rejected": -542.1229858398438,
"loss": 0.0045,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.319135069847107,
"rewards/margins": 40.14945983886719,
"rewards/rejected": -41.468589782714844,
"step": 700
}
],
"logging_steps": 1,
"max_steps": 916,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}