spin-v-iter0 / trainer_state.json
AmberYifan's picture
Model save
376e0d0 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 100,
"global_step": 1563,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.1847133757961784e-09,
"logits/generated": -3.0906174182891846,
"logits/real": -2.9071245193481445,
"logps/generated": -108.96115112304688,
"logps/real": -115.27798461914062,
"loss": 0.6931,
"rewards/accuracies": 0.0,
"rewards/generated": 0.0,
"rewards/margins": 0.0,
"rewards/real": 0.0,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 3.184713375796178e-08,
"logits/generated": -3.101412773132324,
"logits/real": -2.8992347717285156,
"logps/generated": -93.12618255615234,
"logps/real": -131.3624725341797,
"loss": 0.673,
"rewards/accuracies": 0.6388888955116272,
"rewards/generated": -0.032944224774837494,
"rewards/margins": 0.043352365493774414,
"rewards/real": 0.010408139787614346,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 6.369426751592356e-08,
"logits/generated": -3.102088212966919,
"logits/real": -2.8661417961120605,
"logps/generated": -102.2353744506836,
"logps/real": -127.91505432128906,
"loss": 0.4029,
"rewards/accuracies": 1.0,
"rewards/generated": -0.6219673156738281,
"rewards/margins": 0.8206232190132141,
"rewards/real": 0.1986558586359024,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 9.554140127388536e-08,
"logits/generated": -3.0356736183166504,
"logits/real": -2.8853580951690674,
"logps/generated": -108.60257720947266,
"logps/real": -136.26560974121094,
"loss": 0.1801,
"rewards/accuracies": 1.0,
"rewards/generated": -1.4173569679260254,
"rewards/margins": 1.8655112981796265,
"rewards/real": 0.44815438985824585,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 1.2738853503184713e-07,
"logits/generated": -2.9984817504882812,
"logits/real": -2.8029284477233887,
"logps/generated": -112.51835632324219,
"logps/real": -127.77607727050781,
"loss": 0.1015,
"rewards/accuracies": 1.0,
"rewards/generated": -2.3742074966430664,
"rewards/margins": 3.116520643234253,
"rewards/real": 0.7423133254051208,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 1.592356687898089e-07,
"logits/generated": -2.9975199699401855,
"logits/real": -2.747887134552002,
"logps/generated": -118.49820709228516,
"logps/real": -118.71574401855469,
"loss": 0.074,
"rewards/accuracies": 0.987500011920929,
"rewards/generated": -2.736589193344116,
"rewards/margins": 3.6365692615509033,
"rewards/real": 0.8999798893928528,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 1.9108280254777072e-07,
"logits/generated": -2.971416711807251,
"logits/real": -2.7840769290924072,
"logps/generated": -135.747802734375,
"logps/real": -127.07137298583984,
"loss": 0.0602,
"rewards/accuracies": 1.0,
"rewards/generated": -3.610677719116211,
"rewards/margins": 4.637597560882568,
"rewards/real": 1.0269203186035156,
"step": 60
},
{
"epoch": 0.04,
"learning_rate": 2.2292993630573247e-07,
"logits/generated": -2.9653122425079346,
"logits/real": -2.7327213287353516,
"logps/generated": -128.2880096435547,
"logps/real": -132.56533813476562,
"loss": 0.0526,
"rewards/accuracies": 1.0,
"rewards/generated": -3.613079786300659,
"rewards/margins": 4.637925148010254,
"rewards/real": 1.024846076965332,
"step": 70
},
{
"epoch": 0.05,
"learning_rate": 2.5477707006369425e-07,
"logits/generated": -2.9529290199279785,
"logits/real": -2.6906723976135254,
"logps/generated": -132.59231567382812,
"logps/real": -117.8273696899414,
"loss": 0.0357,
"rewards/accuracies": 1.0,
"rewards/generated": -4.144764423370361,
"rewards/margins": 5.101811408996582,
"rewards/real": 0.9570469856262207,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 2.86624203821656e-07,
"logits/generated": -2.964216709136963,
"logits/real": -2.6785378456115723,
"logps/generated": -149.37193298339844,
"logps/real": -127.93388366699219,
"loss": 0.0275,
"rewards/accuracies": 1.0,
"rewards/generated": -4.871094703674316,
"rewards/margins": 5.973794460296631,
"rewards/real": 1.1027004718780518,
"step": 90
},
{
"epoch": 0.06,
"learning_rate": 3.184713375796178e-07,
"logits/generated": -2.907114028930664,
"logits/real": -2.6795763969421387,
"logps/generated": -150.70126342773438,
"logps/real": -117.441162109375,
"loss": 0.0225,
"rewards/accuracies": 1.0,
"rewards/generated": -5.468966960906982,
"rewards/margins": 6.453464508056641,
"rewards/real": 0.9844976663589478,
"step": 100
},
{
"epoch": 0.07,
"learning_rate": 3.5031847133757957e-07,
"logits/generated": -2.871616840362549,
"logits/real": -2.663942813873291,
"logps/generated": -157.40907287597656,
"logps/real": -136.9542236328125,
"loss": 0.013,
"rewards/accuracies": 1.0,
"rewards/generated": -6.357569694519043,
"rewards/margins": 7.108318328857422,
"rewards/real": 0.7507485151290894,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 3.8216560509554143e-07,
"logits/generated": -2.8702244758605957,
"logits/real": -2.6590588092803955,
"logps/generated": -170.4289093017578,
"logps/real": -124.03118896484375,
"loss": 0.0223,
"rewards/accuracies": 1.0,
"rewards/generated": -7.1928534507751465,
"rewards/margins": 7.969223976135254,
"rewards/real": 0.7763701677322388,
"step": 120
},
{
"epoch": 0.08,
"learning_rate": 4.140127388535032e-07,
"logits/generated": -2.8153131008148193,
"logits/real": -2.6566903591156006,
"logps/generated": -167.2792510986328,
"logps/real": -136.0323486328125,
"loss": 0.0241,
"rewards/accuracies": 0.987500011920929,
"rewards/generated": -7.404214382171631,
"rewards/margins": 7.8729753494262695,
"rewards/real": 0.46876010298728943,
"step": 130
},
{
"epoch": 0.09,
"learning_rate": 4.4585987261146494e-07,
"logits/generated": -2.8306140899658203,
"logits/real": -2.5934805870056152,
"logps/generated": -177.410400390625,
"logps/real": -118.83491516113281,
"loss": 0.009,
"rewards/accuracies": 1.0,
"rewards/generated": -8.25102710723877,
"rewards/margins": 8.96755599975586,
"rewards/real": 0.7165282368659973,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 4.777070063694267e-07,
"logits/generated": -2.7984092235565186,
"logits/real": -2.5605010986328125,
"logps/generated": -189.8646697998047,
"logps/real": -135.84613037109375,
"loss": 0.0126,
"rewards/accuracies": 1.0,
"rewards/generated": -9.167638778686523,
"rewards/margins": 9.189529418945312,
"rewards/real": 0.02189045585691929,
"step": 150
},
{
"epoch": 0.1,
"learning_rate": 4.989331436699858e-07,
"logits/generated": -2.7396292686462402,
"logits/real": -2.4274842739105225,
"logps/generated": -193.1374969482422,
"logps/real": -132.30447387695312,
"loss": 0.0128,
"rewards/accuracies": 1.0,
"rewards/generated": -9.727991104125977,
"rewards/margins": 9.82439136505127,
"rewards/real": 0.09639892727136612,
"step": 160
},
{
"epoch": 0.11,
"learning_rate": 4.953769559032717e-07,
"logits/generated": -2.6616251468658447,
"logits/real": -2.3478448390960693,
"logps/generated": -217.52468872070312,
"logps/real": -131.3321533203125,
"loss": 0.0058,
"rewards/accuracies": 1.0,
"rewards/generated": -11.674753189086914,
"rewards/margins": 11.104844093322754,
"rewards/real": -0.5699089765548706,
"step": 170
},
{
"epoch": 0.12,
"learning_rate": 4.918207681365576e-07,
"logits/generated": -2.6591293811798096,
"logits/real": -2.494908571243286,
"logps/generated": -206.00320434570312,
"logps/real": -150.77288818359375,
"loss": 0.0142,
"rewards/accuracies": 1.0,
"rewards/generated": -11.094930648803711,
"rewards/margins": 10.854555130004883,
"rewards/real": -0.24037650227546692,
"step": 180
},
{
"epoch": 0.12,
"learning_rate": 4.882645803698435e-07,
"logits/generated": -2.8326282501220703,
"logits/real": -2.6284682750701904,
"logps/generated": -179.343505859375,
"logps/real": -135.4120635986328,
"loss": 0.0122,
"rewards/accuracies": 1.0,
"rewards/generated": -8.551453590393066,
"rewards/margins": 9.140141487121582,
"rewards/real": 0.5886881947517395,
"step": 190
},
{
"epoch": 0.13,
"learning_rate": 4.847083926031294e-07,
"logits/generated": -2.8262526988983154,
"logits/real": -2.5684738159179688,
"logps/generated": -193.8768310546875,
"logps/real": -124.94401550292969,
"loss": 0.0162,
"rewards/accuracies": 1.0,
"rewards/generated": -9.435348510742188,
"rewards/margins": 9.74295711517334,
"rewards/real": 0.30760902166366577,
"step": 200
},
{
"epoch": 0.13,
"learning_rate": 4.811522048364154e-07,
"logits/generated": -2.79144024848938,
"logits/real": -2.559652805328369,
"logps/generated": -190.53530883789062,
"logps/real": -120.87144470214844,
"loss": 0.0062,
"rewards/accuracies": 1.0,
"rewards/generated": -9.56157112121582,
"rewards/margins": 9.428454399108887,
"rewards/real": -0.13311485946178436,
"step": 210
},
{
"epoch": 0.14,
"learning_rate": 4.775960170697012e-07,
"logits/generated": -2.811436891555786,
"logits/real": -2.487448215484619,
"logps/generated": -193.6876678466797,
"logps/real": -121.51069641113281,
"loss": 0.0082,
"rewards/accuracies": 1.0,
"rewards/generated": -9.918183326721191,
"rewards/margins": 9.770201683044434,
"rewards/real": -0.14798107743263245,
"step": 220
},
{
"epoch": 0.15,
"learning_rate": 4.7403982930298717e-07,
"logits/generated": -2.734006643295288,
"logits/real": -2.4587738513946533,
"logps/generated": -213.60696411132812,
"logps/real": -130.74220275878906,
"loss": 0.0071,
"rewards/accuracies": 1.0,
"rewards/generated": -11.748188972473145,
"rewards/margins": 11.48717975616455,
"rewards/real": -0.2610093653202057,
"step": 230
},
{
"epoch": 0.15,
"learning_rate": 4.7048364153627306e-07,
"logits/generated": -2.730823516845703,
"logits/real": -2.5302836894989014,
"logps/generated": -219.81698608398438,
"logps/real": -161.82106018066406,
"loss": 0.0057,
"rewards/accuracies": 1.0,
"rewards/generated": -12.201372146606445,
"rewards/margins": 11.630053520202637,
"rewards/real": -0.5713191628456116,
"step": 240
},
{
"epoch": 0.16,
"learning_rate": 4.66927453769559e-07,
"logits/generated": -2.729020595550537,
"logits/real": -2.496598720550537,
"logps/generated": -215.9888153076172,
"logps/real": -128.60816955566406,
"loss": 0.0045,
"rewards/accuracies": 1.0,
"rewards/generated": -11.882211685180664,
"rewards/margins": 11.468908309936523,
"rewards/real": -0.41330498456954956,
"step": 250
},
{
"epoch": 0.17,
"learning_rate": 4.633712660028449e-07,
"logits/generated": -2.7439448833465576,
"logits/real": -2.3727543354034424,
"logps/generated": -228.0956268310547,
"logps/real": -129.4033966064453,
"loss": 0.003,
"rewards/accuracies": 1.0,
"rewards/generated": -12.761183738708496,
"rewards/margins": 12.336984634399414,
"rewards/real": -0.424199640750885,
"step": 260
},
{
"epoch": 0.17,
"learning_rate": 4.5981507823613085e-07,
"logits/generated": -2.7314658164978027,
"logits/real": -2.4101929664611816,
"logps/generated": -214.00106811523438,
"logps/real": -134.43858337402344,
"loss": 0.0052,
"rewards/accuracies": 1.0,
"rewards/generated": -12.232887268066406,
"rewards/margins": 11.716353416442871,
"rewards/real": -0.5165335536003113,
"step": 270
},
{
"epoch": 0.18,
"learning_rate": 4.562588904694168e-07,
"logits/generated": -2.689013719558716,
"logits/real": -2.4268341064453125,
"logps/generated": -228.33651733398438,
"logps/real": -147.5162811279297,
"loss": 0.0043,
"rewards/accuracies": 1.0,
"rewards/generated": -13.618290901184082,
"rewards/margins": 12.699493408203125,
"rewards/real": -0.9187966585159302,
"step": 280
},
{
"epoch": 0.19,
"learning_rate": 4.5270270270270264e-07,
"logits/generated": -2.7094247341156006,
"logits/real": -2.386305332183838,
"logps/generated": -246.9062957763672,
"logps/real": -146.25164794921875,
"loss": 0.003,
"rewards/accuracies": 1.0,
"rewards/generated": -14.869857788085938,
"rewards/margins": 13.668147087097168,
"rewards/real": -1.2017114162445068,
"step": 290
},
{
"epoch": 0.19,
"learning_rate": 4.491465149359886e-07,
"logits/generated": -2.680655002593994,
"logits/real": -2.3289406299591064,
"logps/generated": -234.94284057617188,
"logps/real": -133.91293334960938,
"loss": 0.0024,
"rewards/accuracies": 1.0,
"rewards/generated": -14.264216423034668,
"rewards/margins": 13.502108573913574,
"rewards/real": -0.7621089220046997,
"step": 300
},
{
"epoch": 0.2,
"learning_rate": 4.4559032716927454e-07,
"logits/generated": -2.669834852218628,
"logits/real": -2.4426522254943848,
"logps/generated": -245.8262939453125,
"logps/real": -157.44009399414062,
"loss": 0.0032,
"rewards/accuracies": 1.0,
"rewards/generated": -14.951329231262207,
"rewards/margins": 14.07829761505127,
"rewards/real": -0.8730317950248718,
"step": 310
},
{
"epoch": 0.2,
"learning_rate": 4.420341394025605e-07,
"logits/generated": -2.663137912750244,
"logits/real": -2.422542095184326,
"logps/generated": -252.69107055664062,
"logps/real": -147.78504943847656,
"loss": 0.0014,
"rewards/accuracies": 1.0,
"rewards/generated": -15.78465747833252,
"rewards/margins": 14.772485733032227,
"rewards/real": -1.0121715068817139,
"step": 320
},
{
"epoch": 0.21,
"learning_rate": 4.384779516358463e-07,
"logits/generated": -2.630758762359619,
"logits/real": -2.3742423057556152,
"logps/generated": -244.6441192626953,
"logps/real": -161.9650421142578,
"loss": 0.0035,
"rewards/accuracies": 1.0,
"rewards/generated": -15.519983291625977,
"rewards/margins": 13.414645195007324,
"rewards/real": -2.1053380966186523,
"step": 330
},
{
"epoch": 0.22,
"learning_rate": 4.3492176386913227e-07,
"logits/generated": -2.6415796279907227,
"logits/real": -2.356398105621338,
"logps/generated": -267.1407775878906,
"logps/real": -170.39505004882812,
"loss": 0.0016,
"rewards/accuracies": 1.0,
"rewards/generated": -17.32520866394043,
"rewards/margins": 14.95826244354248,
"rewards/real": -2.366948366165161,
"step": 340
},
{
"epoch": 0.22,
"learning_rate": 4.313655761024182e-07,
"logits/generated": -2.624446153640747,
"logits/real": -2.2451043128967285,
"logps/generated": -271.24444580078125,
"logps/real": -170.41299438476562,
"loss": 0.0023,
"rewards/accuracies": 1.0,
"rewards/generated": -18.118497848510742,
"rewards/margins": 14.8461332321167,
"rewards/real": -3.2723660469055176,
"step": 350
},
{
"epoch": 0.23,
"learning_rate": 4.278093883357041e-07,
"logits/generated": -2.638278007507324,
"logits/real": -2.3009445667266846,
"logps/generated": -258.6704406738281,
"logps/real": -148.07969665527344,
"loss": 0.0031,
"rewards/accuracies": 1.0,
"rewards/generated": -16.391494750976562,
"rewards/margins": 15.001701354980469,
"rewards/real": -1.3897945880889893,
"step": 360
},
{
"epoch": 0.24,
"learning_rate": 4.2425320056899e-07,
"logits/generated": -2.621098756790161,
"logits/real": -2.34078049659729,
"logps/generated": -257.48077392578125,
"logps/real": -169.0782470703125,
"loss": 0.0015,
"rewards/accuracies": 1.0,
"rewards/generated": -16.38188934326172,
"rewards/margins": 14.900436401367188,
"rewards/real": -1.4814506769180298,
"step": 370
},
{
"epoch": 0.24,
"learning_rate": 4.2069701280227595e-07,
"logits/generated": -2.597550392150879,
"logits/real": -2.2361397743225098,
"logps/generated": -276.8401184082031,
"logps/real": -160.2169189453125,
"loss": 0.0022,
"rewards/accuracies": 1.0,
"rewards/generated": -17.763856887817383,
"rewards/margins": 16.03007698059082,
"rewards/real": -1.7337779998779297,
"step": 380
},
{
"epoch": 0.25,
"learning_rate": 4.1714082503556185e-07,
"logits/generated": -2.5919480323791504,
"logits/real": -2.3185667991638184,
"logps/generated": -278.0733947753906,
"logps/real": -163.49391174316406,
"loss": 0.002,
"rewards/accuracies": 1.0,
"rewards/generated": -18.25893783569336,
"rewards/margins": 15.166206359863281,
"rewards/real": -3.0927340984344482,
"step": 390
},
{
"epoch": 0.26,
"learning_rate": 4.135846372688478e-07,
"logits/generated": -2.635617971420288,
"logits/real": -2.3077096939086914,
"logps/generated": -234.7008056640625,
"logps/real": -155.15969848632812,
"loss": 0.0046,
"rewards/accuracies": 1.0,
"rewards/generated": -15.043414115905762,
"rewards/margins": 13.307294845581055,
"rewards/real": -1.7361185550689697,
"step": 400
},
{
"epoch": 0.26,
"learning_rate": 4.100284495021337e-07,
"logits/generated": -2.6545605659484863,
"logits/real": -2.3340840339660645,
"logps/generated": -252.66220092773438,
"logps/real": -143.4952850341797,
"loss": 0.0018,
"rewards/accuracies": 1.0,
"rewards/generated": -15.794622421264648,
"rewards/margins": 14.8565673828125,
"rewards/real": -0.9380534291267395,
"step": 410
},
{
"epoch": 0.27,
"learning_rate": 4.064722617354196e-07,
"logits/generated": -2.6176822185516357,
"logits/real": -2.291186809539795,
"logps/generated": -255.0669403076172,
"logps/real": -150.9188995361328,
"loss": 0.0036,
"rewards/accuracies": 1.0,
"rewards/generated": -16.221405029296875,
"rewards/margins": 14.909570693969727,
"rewards/real": -1.3118356466293335,
"step": 420
},
{
"epoch": 0.28,
"learning_rate": 4.0291607396870553e-07,
"logits/generated": -2.636864185333252,
"logits/real": -2.341648578643799,
"logps/generated": -249.6366424560547,
"logps/real": -140.9087677001953,
"loss": 0.0023,
"rewards/accuracies": 1.0,
"rewards/generated": -16.15219497680664,
"rewards/margins": 14.91722583770752,
"rewards/real": -1.23496675491333,
"step": 430
},
{
"epoch": 0.28,
"learning_rate": 3.993598862019915e-07,
"logits/generated": -2.6465516090393066,
"logits/real": -2.3501453399658203,
"logps/generated": -243.95895385742188,
"logps/real": -155.9197998046875,
"loss": 0.0097,
"rewards/accuracies": 1.0,
"rewards/generated": -15.268379211425781,
"rewards/margins": 12.943562507629395,
"rewards/real": -2.3248181343078613,
"step": 440
},
{
"epoch": 0.29,
"learning_rate": 3.9580369843527737e-07,
"logits/generated": -2.683403491973877,
"logits/real": -2.467794418334961,
"logps/generated": -246.9853057861328,
"logps/real": -143.61874389648438,
"loss": 0.001,
"rewards/accuracies": 1.0,
"rewards/generated": -14.511987686157227,
"rewards/margins": 13.070988655090332,
"rewards/real": -1.4409997463226318,
"step": 450
},
{
"epoch": 0.29,
"learning_rate": 3.9224751066856327e-07,
"logits/generated": -2.646587610244751,
"logits/real": -2.513019323348999,
"logps/generated": -249.4457550048828,
"logps/real": -171.30072021484375,
"loss": 0.0042,
"rewards/accuracies": 1.0,
"rewards/generated": -15.091230392456055,
"rewards/margins": 13.882911682128906,
"rewards/real": -1.2083193063735962,
"step": 460
},
{
"epoch": 0.3,
"learning_rate": 3.886913229018492e-07,
"logits/generated": -2.6025052070617676,
"logits/real": -2.308351993560791,
"logps/generated": -260.1772155761719,
"logps/real": -152.1533660888672,
"loss": 0.0053,
"rewards/accuracies": 1.0,
"rewards/generated": -16.5654296875,
"rewards/margins": 14.767765998840332,
"rewards/real": -1.7976620197296143,
"step": 470
},
{
"epoch": 0.31,
"learning_rate": 3.851351351351351e-07,
"logits/generated": -2.6486258506774902,
"logits/real": -2.34824538230896,
"logps/generated": -243.5570831298828,
"logps/real": -147.68495178222656,
"loss": 0.0038,
"rewards/accuracies": 1.0,
"rewards/generated": -15.00477123260498,
"rewards/margins": 14.016987800598145,
"rewards/real": -0.9877821207046509,
"step": 480
},
{
"epoch": 0.31,
"learning_rate": 3.8157894736842105e-07,
"logits/generated": -2.6565589904785156,
"logits/real": -2.3215975761413574,
"logps/generated": -236.3148193359375,
"logps/real": -132.85011291503906,
"loss": 0.0023,
"rewards/accuracies": 1.0,
"rewards/generated": -14.406427383422852,
"rewards/margins": 13.613751411437988,
"rewards/real": -0.7926777601242065,
"step": 490
},
{
"epoch": 0.32,
"learning_rate": 3.7802275960170695e-07,
"logits/generated": -2.664989471435547,
"logits/real": -2.4229531288146973,
"logps/generated": -260.98944091796875,
"logps/real": -142.20501708984375,
"loss": 0.0039,
"rewards/accuracies": 1.0,
"rewards/generated": -16.135055541992188,
"rewards/margins": 15.381479263305664,
"rewards/real": -0.753574550151825,
"step": 500
},
{
"epoch": 0.33,
"learning_rate": 3.7446657183499284e-07,
"logits/generated": -2.6360857486724854,
"logits/real": -2.356961488723755,
"logps/generated": -251.55740356445312,
"logps/real": -146.3067169189453,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -15.945223808288574,
"rewards/margins": 14.57160758972168,
"rewards/real": -1.373616337776184,
"step": 510
},
{
"epoch": 0.33,
"learning_rate": 3.709103840682788e-07,
"logits/generated": -2.627017021179199,
"logits/real": -2.3511900901794434,
"logps/generated": -256.36798095703125,
"logps/real": -142.99703979492188,
"loss": 0.001,
"rewards/accuracies": 1.0,
"rewards/generated": -16.528518676757812,
"rewards/margins": 15.134465217590332,
"rewards/real": -1.394053339958191,
"step": 520
},
{
"epoch": 0.34,
"learning_rate": 3.6735419630156474e-07,
"logits/generated": -2.587278366088867,
"logits/real": -2.248208999633789,
"logps/generated": -266.53668212890625,
"logps/real": -140.9051971435547,
"loss": 0.0015,
"rewards/accuracies": 1.0,
"rewards/generated": -17.05879020690918,
"rewards/margins": 15.273892402648926,
"rewards/real": -1.7848970890045166,
"step": 530
},
{
"epoch": 0.35,
"learning_rate": 3.637980085348506e-07,
"logits/generated": -2.5869765281677246,
"logits/real": -2.275988817214966,
"logps/generated": -267.7913513183594,
"logps/real": -154.5830078125,
"loss": 0.0041,
"rewards/accuracies": 1.0,
"rewards/generated": -17.560646057128906,
"rewards/margins": 15.521791458129883,
"rewards/real": -2.038856267929077,
"step": 540
},
{
"epoch": 0.35,
"learning_rate": 3.602418207681365e-07,
"logits/generated": -2.610684871673584,
"logits/real": -2.302337169647217,
"logps/generated": -264.52764892578125,
"logps/real": -150.14028930664062,
"loss": 0.0013,
"rewards/accuracies": 1.0,
"rewards/generated": -16.939865112304688,
"rewards/margins": 15.928593635559082,
"rewards/real": -1.01127028465271,
"step": 550
},
{
"epoch": 0.36,
"learning_rate": 3.5668563300142247e-07,
"logits/generated": -2.5956525802612305,
"logits/real": -2.34203839302063,
"logps/generated": -273.79949951171875,
"logps/real": -144.4397430419922,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/generated": -17.865262985229492,
"rewards/margins": 16.40726661682129,
"rewards/real": -1.4579969644546509,
"step": 560
},
{
"epoch": 0.36,
"learning_rate": 3.5312944523470837e-07,
"logits/generated": -2.558427095413208,
"logits/real": -2.191371440887451,
"logps/generated": -286.45184326171875,
"logps/real": -154.03485107421875,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -19.122371673583984,
"rewards/margins": 16.966218948364258,
"rewards/real": -2.156151294708252,
"step": 570
},
{
"epoch": 0.37,
"learning_rate": 3.495732574679943e-07,
"logits/generated": -2.5747647285461426,
"logits/real": -2.2839667797088623,
"logps/generated": -280.7036437988281,
"logps/real": -149.42234802246094,
"loss": 0.0036,
"rewards/accuracies": 1.0,
"rewards/generated": -18.820329666137695,
"rewards/margins": 16.973482131958008,
"rewards/real": -1.8468481302261353,
"step": 580
},
{
"epoch": 0.38,
"learning_rate": 3.460170697012802e-07,
"logits/generated": -2.647414445877075,
"logits/real": -2.311011791229248,
"logps/generated": -271.14031982421875,
"logps/real": -145.47608947753906,
"loss": 0.0024,
"rewards/accuracies": 1.0,
"rewards/generated": -16.740116119384766,
"rewards/margins": 15.668981552124023,
"rewards/real": -1.0711352825164795,
"step": 590
},
{
"epoch": 0.38,
"learning_rate": 3.424608819345661e-07,
"logits/generated": -2.6572697162628174,
"logits/real": -2.2757163047790527,
"logps/generated": -256.30584716796875,
"logps/real": -147.24533081054688,
"loss": 0.0011,
"rewards/accuracies": 1.0,
"rewards/generated": -16.026338577270508,
"rewards/margins": 14.143951416015625,
"rewards/real": -1.8823878765106201,
"step": 600
},
{
"epoch": 0.39,
"learning_rate": 3.3890469416785205e-07,
"logits/generated": -2.6201155185699463,
"logits/real": -2.3046302795410156,
"logps/generated": -271.51690673828125,
"logps/real": -159.52593994140625,
"loss": 0.0026,
"rewards/accuracies": 1.0,
"rewards/generated": -17.70832633972168,
"rewards/margins": 15.127041816711426,
"rewards/real": -2.581282377243042,
"step": 610
},
{
"epoch": 0.4,
"learning_rate": 3.35348506401138e-07,
"logits/generated": -2.5929877758026123,
"logits/real": -2.066601514816284,
"logps/generated": -276.5373229980469,
"logps/real": -151.35279846191406,
"loss": 0.0014,
"rewards/accuracies": 1.0,
"rewards/generated": -17.873516082763672,
"rewards/margins": 15.789881706237793,
"rewards/real": -2.083634376525879,
"step": 620
},
{
"epoch": 0.4,
"learning_rate": 3.3179231863442384e-07,
"logits/generated": -2.5061452388763428,
"logits/real": -2.165194511413574,
"logps/generated": -269.43182373046875,
"logps/real": -167.6754150390625,
"loss": 0.0008,
"rewards/accuracies": 1.0,
"rewards/generated": -17.984777450561523,
"rewards/margins": 15.614283561706543,
"rewards/real": -2.370495080947876,
"step": 630
},
{
"epoch": 0.41,
"learning_rate": 3.282361308677098e-07,
"logits/generated": -2.535046339035034,
"logits/real": -2.0150370597839355,
"logps/generated": -290.4701232910156,
"logps/real": -155.98748779296875,
"loss": 0.0009,
"rewards/accuracies": 1.0,
"rewards/generated": -19.04861068725586,
"rewards/margins": 17.140892028808594,
"rewards/real": -1.9077173471450806,
"step": 640
},
{
"epoch": 0.42,
"learning_rate": 3.2467994310099573e-07,
"logits/generated": -2.52227783203125,
"logits/real": -2.0042471885681152,
"logps/generated": -297.1048889160156,
"logps/real": -164.85296630859375,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/generated": -19.86203384399414,
"rewards/margins": 18.030447006225586,
"rewards/real": -1.8315849304199219,
"step": 650
},
{
"epoch": 0.42,
"learning_rate": 3.211237553342817e-07,
"logits/generated": -2.4940333366394043,
"logits/real": -1.932329535484314,
"logps/generated": -293.40875244140625,
"logps/real": -152.46395874023438,
"loss": 0.001,
"rewards/accuracies": 1.0,
"rewards/generated": -19.75796890258789,
"rewards/margins": 17.733844757080078,
"rewards/real": -2.02412486076355,
"step": 660
},
{
"epoch": 0.43,
"learning_rate": 3.175675675675675e-07,
"logits/generated": -2.4778501987457275,
"logits/real": -1.9003286361694336,
"logps/generated": -285.62982177734375,
"logps/real": -146.41970825195312,
"loss": 0.0056,
"rewards/accuracies": 1.0,
"rewards/generated": -19.548839569091797,
"rewards/margins": 17.18503189086914,
"rewards/real": -2.363809823989868,
"step": 670
},
{
"epoch": 0.44,
"learning_rate": 3.1401137980085347e-07,
"logits/generated": -2.628258228302002,
"logits/real": -2.3583595752716064,
"logps/generated": -289.90972900390625,
"logps/real": -167.40670776367188,
"loss": 0.0063,
"rewards/accuracies": 0.987500011920929,
"rewards/generated": -19.053691864013672,
"rewards/margins": 15.783452987670898,
"rewards/real": -3.2702412605285645,
"step": 680
},
{
"epoch": 0.44,
"learning_rate": 3.104551920341394e-07,
"logits/generated": -2.6161983013153076,
"logits/real": -2.3759868144989014,
"logps/generated": -275.8905944824219,
"logps/real": -164.04794311523438,
"loss": 0.0027,
"rewards/accuracies": 1.0,
"rewards/generated": -18.127063751220703,
"rewards/margins": 15.362668991088867,
"rewards/real": -2.7643933296203613,
"step": 690
},
{
"epoch": 0.45,
"learning_rate": 3.068990042674253e-07,
"logits/generated": -2.63472318649292,
"logits/real": -2.4305763244628906,
"logps/generated": -252.68026733398438,
"logps/real": -149.27975463867188,
"loss": 0.0089,
"rewards/accuracies": 1.0,
"rewards/generated": -16.35388946533203,
"rewards/margins": 13.695645332336426,
"rewards/real": -2.658242702484131,
"step": 700
},
{
"epoch": 0.45,
"learning_rate": 3.033428165007112e-07,
"logits/generated": -2.6811423301696777,
"logits/real": -2.379275321960449,
"logps/generated": -289.7455139160156,
"logps/real": -153.281005859375,
"loss": 0.0016,
"rewards/accuracies": 1.0,
"rewards/generated": -18.906612396240234,
"rewards/margins": 16.27779197692871,
"rewards/real": -2.6288204193115234,
"step": 710
},
{
"epoch": 0.46,
"learning_rate": 2.9978662873399715e-07,
"logits/generated": -2.642746686935425,
"logits/real": -2.4080071449279785,
"logps/generated": -280.27044677734375,
"logps/real": -163.74325561523438,
"loss": 0.0011,
"rewards/accuracies": 1.0,
"rewards/generated": -18.57528305053711,
"rewards/margins": 15.842401504516602,
"rewards/real": -2.7328832149505615,
"step": 720
},
{
"epoch": 0.47,
"learning_rate": 2.9623044096728305e-07,
"logits/generated": -2.585597276687622,
"logits/real": -2.384023666381836,
"logps/generated": -289.5233459472656,
"logps/real": -178.13461303710938,
"loss": 0.0013,
"rewards/accuracies": 1.0,
"rewards/generated": -20.13193130493164,
"rewards/margins": 17.022491455078125,
"rewards/real": -3.1094412803649902,
"step": 730
},
{
"epoch": 0.47,
"learning_rate": 2.92674253200569e-07,
"logits/generated": -2.564220428466797,
"logits/real": -2.2639899253845215,
"logps/generated": -318.0504455566406,
"logps/real": -165.57601928710938,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/generated": -22.199588775634766,
"rewards/margins": 19.12047004699707,
"rewards/real": -3.0791163444519043,
"step": 740
},
{
"epoch": 0.48,
"learning_rate": 2.8911806543385494e-07,
"logits/generated": -2.54494309425354,
"logits/real": -2.243720054626465,
"logps/generated": -335.9930114746094,
"logps/real": -176.82962036132812,
"loss": 0.0024,
"rewards/accuracies": 1.0,
"rewards/generated": -23.840442657470703,
"rewards/margins": 21.033586502075195,
"rewards/real": -2.8068575859069824,
"step": 750
},
{
"epoch": 0.49,
"learning_rate": 2.855618776671408e-07,
"logits/generated": -2.4757752418518066,
"logits/real": -2.291566848754883,
"logps/generated": -345.89788818359375,
"logps/real": -186.32931518554688,
"loss": 0.0011,
"rewards/accuracies": 1.0,
"rewards/generated": -24.59176254272461,
"rewards/margins": 21.504487991333008,
"rewards/real": -3.0872764587402344,
"step": 760
},
{
"epoch": 0.49,
"learning_rate": 2.8200568990042673e-07,
"logits/generated": -2.4870519638061523,
"logits/real": -2.2031798362731934,
"logps/generated": -311.2699279785156,
"logps/real": -153.85873413085938,
"loss": 0.0007,
"rewards/accuracies": 1.0,
"rewards/generated": -21.774972915649414,
"rewards/margins": 19.98200035095215,
"rewards/real": -1.792970895767212,
"step": 770
},
{
"epoch": 0.5,
"learning_rate": 2.784495021337127e-07,
"logits/generated": -2.4991695880889893,
"logits/real": -2.1358065605163574,
"logps/generated": -317.76593017578125,
"logps/real": -149.97769165039062,
"loss": 0.0037,
"rewards/accuracies": 1.0,
"rewards/generated": -22.39531707763672,
"rewards/margins": 19.940006256103516,
"rewards/real": -2.455310821533203,
"step": 780
},
{
"epoch": 0.51,
"learning_rate": 2.7489331436699857e-07,
"logits/generated": -2.4913153648376465,
"logits/real": -2.2520499229431152,
"logps/generated": -331.97198486328125,
"logps/real": -168.5391845703125,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/generated": -23.301677703857422,
"rewards/margins": 20.83787727355957,
"rewards/real": -2.463801145553589,
"step": 790
},
{
"epoch": 0.51,
"learning_rate": 2.7133712660028446e-07,
"logits/generated": -2.475283145904541,
"logits/real": -2.12270188331604,
"logps/generated": -358.60699462890625,
"logps/real": -153.89566040039062,
"loss": 0.0014,
"rewards/accuracies": 1.0,
"rewards/generated": -25.966594696044922,
"rewards/margins": 23.213787078857422,
"rewards/real": -2.752802848815918,
"step": 800
},
{
"epoch": 0.52,
"learning_rate": 2.677809388335704e-07,
"logits/generated": -2.552203893661499,
"logits/real": -2.231297016143799,
"logps/generated": -306.72418212890625,
"logps/real": -151.74932861328125,
"loss": 0.0047,
"rewards/accuracies": 1.0,
"rewards/generated": -21.487075805664062,
"rewards/margins": 19.052860260009766,
"rewards/real": -2.434213638305664,
"step": 810
},
{
"epoch": 0.52,
"learning_rate": 2.642247510668563e-07,
"logits/generated": -2.5113425254821777,
"logits/real": -2.2336676120758057,
"logps/generated": -338.52764892578125,
"logps/real": -156.8263702392578,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -24.256011962890625,
"rewards/margins": 21.824642181396484,
"rewards/real": -2.431368589401245,
"step": 820
},
{
"epoch": 0.53,
"learning_rate": 2.6066856330014225e-07,
"logits/generated": -2.5100226402282715,
"logits/real": -2.235252618789673,
"logps/generated": -321.89739990234375,
"logps/real": -163.9221954345703,
"loss": 0.0028,
"rewards/accuracies": 1.0,
"rewards/generated": -22.618907928466797,
"rewards/margins": 20.022174835205078,
"rewards/real": -2.596730947494507,
"step": 830
},
{
"epoch": 0.54,
"learning_rate": 2.5711237553342815e-07,
"logits/generated": -2.5395519733428955,
"logits/real": -2.3223767280578613,
"logps/generated": -332.1412048339844,
"logps/real": -173.91867065429688,
"loss": 0.0014,
"rewards/accuracies": 1.0,
"rewards/generated": -22.6175594329834,
"rewards/margins": 20.04648780822754,
"rewards/real": -2.5710747241973877,
"step": 840
},
{
"epoch": 0.54,
"learning_rate": 2.5355618776671404e-07,
"logits/generated": -2.5228655338287354,
"logits/real": -2.258119821548462,
"logps/generated": -310.4747009277344,
"logps/real": -156.8980255126953,
"loss": 0.0026,
"rewards/accuracies": 1.0,
"rewards/generated": -21.987834930419922,
"rewards/margins": 20.325721740722656,
"rewards/real": -1.6621124744415283,
"step": 850
},
{
"epoch": 0.55,
"learning_rate": 2.5e-07,
"logits/generated": -2.494560718536377,
"logits/real": -2.2443575859069824,
"logps/generated": -309.8906555175781,
"logps/real": -150.50845336914062,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -21.8504638671875,
"rewards/margins": 19.960376739501953,
"rewards/real": -1.8900905847549438,
"step": 860
},
{
"epoch": 0.56,
"learning_rate": 2.4644381223328594e-07,
"logits/generated": -2.476022720336914,
"logits/real": -2.208930730819702,
"logps/generated": -324.40386962890625,
"logps/real": -158.23794555664062,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -22.94091033935547,
"rewards/margins": 21.123210906982422,
"rewards/real": -1.8176969289779663,
"step": 870
},
{
"epoch": 0.56,
"learning_rate": 2.4288762446657183e-07,
"logits/generated": -2.469374179840088,
"logits/real": -2.2076289653778076,
"logps/generated": -351.7542419433594,
"logps/real": -168.60581970214844,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -26.091217041015625,
"rewards/margins": 23.471628189086914,
"rewards/real": -2.619591474533081,
"step": 880
},
{
"epoch": 0.57,
"learning_rate": 2.393314366998578e-07,
"logits/generated": -2.462498188018799,
"logits/real": -2.1745076179504395,
"logps/generated": -356.53643798828125,
"logps/real": -166.32203674316406,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -25.77919578552246,
"rewards/margins": 22.798179626464844,
"rewards/real": -2.9810147285461426,
"step": 890
},
{
"epoch": 0.58,
"learning_rate": 2.3577524893314365e-07,
"logits/generated": -2.4472568035125732,
"logits/real": -2.0861692428588867,
"logps/generated": -373.2332458496094,
"logps/real": -161.7514190673828,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -27.64597511291504,
"rewards/margins": 24.518720626831055,
"rewards/real": -3.127256393432617,
"step": 900
},
{
"epoch": 0.58,
"learning_rate": 2.322190611664296e-07,
"logits/generated": -2.4123172760009766,
"logits/real": -2.2399840354919434,
"logps/generated": -347.86602783203125,
"logps/real": -176.418701171875,
"loss": 0.0033,
"rewards/accuracies": 1.0,
"rewards/generated": -25.725696563720703,
"rewards/margins": 23.024372100830078,
"rewards/real": -2.701322078704834,
"step": 910
},
{
"epoch": 0.59,
"learning_rate": 2.2866287339971549e-07,
"logits/generated": -2.4416496753692627,
"logits/real": -2.165473461151123,
"logps/generated": -350.0740051269531,
"logps/real": -163.84527587890625,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -25.062084197998047,
"rewards/margins": 22.562055587768555,
"rewards/real": -2.5000269412994385,
"step": 920
},
{
"epoch": 0.6,
"learning_rate": 2.251066856330014e-07,
"logits/generated": -2.3707525730133057,
"logits/real": -2.133812665939331,
"logps/generated": -331.30523681640625,
"logps/real": -152.8733673095703,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -24.211957931518555,
"rewards/margins": 21.420856475830078,
"rewards/real": -2.791102886199951,
"step": 930
},
{
"epoch": 0.6,
"learning_rate": 2.2155049786628733e-07,
"logits/generated": -2.37143611907959,
"logits/real": -2.1967265605926514,
"logps/generated": -348.8166198730469,
"logps/real": -173.89651489257812,
"loss": 0.0009,
"rewards/accuracies": 1.0,
"rewards/generated": -25.457895278930664,
"rewards/margins": 22.477210998535156,
"rewards/real": -2.980682849884033,
"step": 940
},
{
"epoch": 0.61,
"learning_rate": 2.1799431009957325e-07,
"logits/generated": -2.381801128387451,
"logits/real": -2.059781074523926,
"logps/generated": -362.11383056640625,
"logps/real": -159.50637817382812,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -26.543100357055664,
"rewards/margins": 22.987590789794922,
"rewards/real": -3.5555107593536377,
"step": 950
},
{
"epoch": 0.61,
"learning_rate": 2.1443812233285914e-07,
"logits/generated": -2.3684401512145996,
"logits/real": -2.1415822505950928,
"logps/generated": -351.82196044921875,
"logps/real": -176.533203125,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -26.036602020263672,
"rewards/margins": 22.72909164428711,
"rewards/real": -3.30751371383667,
"step": 960
},
{
"epoch": 0.62,
"learning_rate": 2.108819345661451e-07,
"logits/generated": -2.3761467933654785,
"logits/real": -2.0534472465515137,
"logps/generated": -355.33428955078125,
"logps/real": -168.10891723632812,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -25.50898551940918,
"rewards/margins": 22.156692504882812,
"rewards/real": -3.3522915840148926,
"step": 970
},
{
"epoch": 0.63,
"learning_rate": 2.0732574679943098e-07,
"logits/generated": -2.361323118209839,
"logits/real": -1.9123132228851318,
"logps/generated": -341.6062316894531,
"logps/real": -151.2181854248047,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/generated": -24.98283576965332,
"rewards/margins": 21.82351303100586,
"rewards/real": -3.15932297706604,
"step": 980
},
{
"epoch": 0.63,
"learning_rate": 2.0376955903271693e-07,
"logits/generated": -2.4006187915802,
"logits/real": -2.185279130935669,
"logps/generated": -348.07781982421875,
"logps/real": -179.2666778564453,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -25.35213851928711,
"rewards/margins": 22.43604278564453,
"rewards/real": -2.9160971641540527,
"step": 990
},
{
"epoch": 0.64,
"learning_rate": 2.0021337126600283e-07,
"logits/generated": -2.4060044288635254,
"logits/real": -2.060713529586792,
"logps/generated": -333.03594970703125,
"logps/real": -150.0802001953125,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -23.7082576751709,
"rewards/margins": 21.07244300842285,
"rewards/real": -2.6358113288879395,
"step": 1000
},
{
"epoch": 0.65,
"learning_rate": 1.9665718349928875e-07,
"logits/generated": -2.399757146835327,
"logits/real": -2.0892844200134277,
"logps/generated": -329.17266845703125,
"logps/real": -147.83761596679688,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -24.133182525634766,
"rewards/margins": 22.037132263183594,
"rewards/real": -2.096048593521118,
"step": 1010
},
{
"epoch": 0.65,
"learning_rate": 1.931009957325747e-07,
"logits/generated": -2.435051441192627,
"logits/real": -2.0257344245910645,
"logps/generated": -339.9688720703125,
"logps/real": -136.052734375,
"loss": 0.0027,
"rewards/accuracies": 1.0,
"rewards/generated": -24.32839012145996,
"rewards/margins": 22.426374435424805,
"rewards/real": -1.90201735496521,
"step": 1020
},
{
"epoch": 0.66,
"learning_rate": 1.895448079658606e-07,
"logits/generated": -2.5459911823272705,
"logits/real": -2.294416904449463,
"logps/generated": -295.2132873535156,
"logps/real": -164.39163208007812,
"loss": 0.0065,
"rewards/accuracies": 0.987500011920929,
"rewards/generated": -20.07970428466797,
"rewards/margins": 17.690706253051758,
"rewards/real": -2.3889966011047363,
"step": 1030
},
{
"epoch": 0.67,
"learning_rate": 1.859886201991465e-07,
"logits/generated": -2.557673931121826,
"logits/real": -2.352283000946045,
"logps/generated": -305.96063232421875,
"logps/real": -168.4624481201172,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -20.94136619567871,
"rewards/margins": 18.588964462280273,
"rewards/real": -2.3524010181427,
"step": 1040
},
{
"epoch": 0.67,
"learning_rate": 1.8243243243243243e-07,
"logits/generated": -2.523613691329956,
"logits/real": -2.266178607940674,
"logps/generated": -326.160400390625,
"logps/real": -161.75082397460938,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -22.259069442749023,
"rewards/margins": 19.766599655151367,
"rewards/real": -2.4924685955047607,
"step": 1050
},
{
"epoch": 0.68,
"learning_rate": 1.7887624466571835e-07,
"logits/generated": -2.527306079864502,
"logits/real": -2.2957048416137695,
"logps/generated": -305.22296142578125,
"logps/real": -155.027099609375,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/generated": -20.85342788696289,
"rewards/margins": 18.48206901550293,
"rewards/real": -2.3713603019714355,
"step": 1060
},
{
"epoch": 0.68,
"learning_rate": 1.7532005689900424e-07,
"logits/generated": -2.506270170211792,
"logits/real": -2.255981206893921,
"logps/generated": -325.351318359375,
"logps/real": -159.0684051513672,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -22.69347381591797,
"rewards/margins": 20.053133010864258,
"rewards/real": -2.640340805053711,
"step": 1070
},
{
"epoch": 0.69,
"learning_rate": 1.717638691322902e-07,
"logits/generated": -2.4864695072174072,
"logits/real": -2.2343809604644775,
"logps/generated": -316.3734130859375,
"logps/real": -154.7774200439453,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -22.82534408569336,
"rewards/margins": 20.07224464416504,
"rewards/real": -2.753100633621216,
"step": 1080
},
{
"epoch": 0.7,
"learning_rate": 1.6820768136557609e-07,
"logits/generated": -2.4980576038360596,
"logits/real": -2.2096495628356934,
"logps/generated": -332.5113220214844,
"logps/real": -155.82949829101562,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -23.275163650512695,
"rewards/margins": 20.510225296020508,
"rewards/real": -2.764936923980713,
"step": 1090
},
{
"epoch": 0.7,
"learning_rate": 1.64651493598862e-07,
"logits/generated": -2.4756176471710205,
"logits/real": -2.231832981109619,
"logps/generated": -312.5588073730469,
"logps/real": -164.60313415527344,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/generated": -21.650741577148438,
"rewards/margins": 19.549571990966797,
"rewards/real": -2.101168394088745,
"step": 1100
},
{
"epoch": 0.71,
"learning_rate": 1.6109530583214793e-07,
"logits/generated": -2.479539632797241,
"logits/real": -2.2095680236816406,
"logps/generated": -301.00494384765625,
"logps/real": -146.39959716796875,
"loss": 0.0013,
"rewards/accuracies": 1.0,
"rewards/generated": -21.074636459350586,
"rewards/margins": 19.5632381439209,
"rewards/real": -1.5113978385925293,
"step": 1110
},
{
"epoch": 0.72,
"learning_rate": 1.5753911806543385e-07,
"logits/generated": -2.481510877609253,
"logits/real": -2.1283092498779297,
"logps/generated": -334.80682373046875,
"logps/real": -148.7257537841797,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/generated": -23.64105796813965,
"rewards/margins": 22.138673782348633,
"rewards/real": -1.5023812055587769,
"step": 1120
},
{
"epoch": 0.72,
"learning_rate": 1.5398293029871974e-07,
"logits/generated": -2.427147150039673,
"logits/real": -2.1763315200805664,
"logps/generated": -332.43707275390625,
"logps/real": -164.38101196289062,
"loss": 0.0007,
"rewards/accuracies": 1.0,
"rewards/generated": -23.752038955688477,
"rewards/margins": 21.313995361328125,
"rewards/real": -2.438042640686035,
"step": 1130
},
{
"epoch": 0.73,
"learning_rate": 1.504267425320057e-07,
"logits/generated": -2.4392311573028564,
"logits/real": -2.0997610092163086,
"logps/generated": -334.01568603515625,
"logps/real": -156.3632354736328,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -24.041645050048828,
"rewards/margins": 21.53177833557129,
"rewards/real": -2.50986647605896,
"step": 1140
},
{
"epoch": 0.74,
"learning_rate": 1.4687055476529158e-07,
"logits/generated": -2.419010639190674,
"logits/real": -2.111693859100342,
"logps/generated": -342.69451904296875,
"logps/real": -169.71495056152344,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/generated": -24.21269416809082,
"rewards/margins": 21.255273818969727,
"rewards/real": -2.9574201107025146,
"step": 1150
},
{
"epoch": 0.74,
"learning_rate": 1.4331436699857753e-07,
"logits/generated": -2.381650447845459,
"logits/real": -2.1679978370666504,
"logps/generated": -366.71685791015625,
"logps/real": -173.09190368652344,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/generated": -26.46500015258789,
"rewards/margins": 23.07950782775879,
"rewards/real": -3.385493040084839,
"step": 1160
},
{
"epoch": 0.75,
"learning_rate": 1.3975817923186345e-07,
"logits/generated": -2.3996267318725586,
"logits/real": -2.159729480743408,
"logps/generated": -342.78851318359375,
"logps/real": -178.8369903564453,
"loss": 0.0024,
"rewards/accuracies": 1.0,
"rewards/generated": -25.046499252319336,
"rewards/margins": 22.436920166015625,
"rewards/real": -2.6095809936523438,
"step": 1170
},
{
"epoch": 0.75,
"learning_rate": 1.3620199146514935e-07,
"logits/generated": -2.4095382690429688,
"logits/real": -2.130403518676758,
"logps/generated": -355.113037109375,
"logps/real": -153.84921264648438,
"loss": 0.1458,
"rewards/accuracies": 1.0,
"rewards/generated": -26.34041404724121,
"rewards/margins": 22.976913452148438,
"rewards/real": -3.3634982109069824,
"step": 1180
},
{
"epoch": 0.76,
"learning_rate": 1.326458036984353e-07,
"logits/generated": -2.4847569465637207,
"logits/real": -2.2022132873535156,
"logps/generated": -349.0047607421875,
"logps/real": -167.6402130126953,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -25.467708587646484,
"rewards/margins": 21.79030990600586,
"rewards/real": -3.677398204803467,
"step": 1190
},
{
"epoch": 0.77,
"learning_rate": 1.290896159317212e-07,
"logits/generated": -2.4859986305236816,
"logits/real": -2.1584694385528564,
"logps/generated": -378.67840576171875,
"logps/real": -163.35751342773438,
"loss": 0.003,
"rewards/accuracies": 1.0,
"rewards/generated": -27.922542572021484,
"rewards/margins": 24.293628692626953,
"rewards/real": -3.628913402557373,
"step": 1200
},
{
"epoch": 0.77,
"learning_rate": 1.255334281650071e-07,
"logits/generated": -2.4462192058563232,
"logits/real": -2.1797935962677,
"logps/generated": -360.53839111328125,
"logps/real": -178.1334228515625,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -26.705047607421875,
"rewards/margins": 22.96535301208496,
"rewards/real": -3.7396953105926514,
"step": 1210
},
{
"epoch": 0.78,
"learning_rate": 1.2197724039829303e-07,
"logits/generated": -2.4851443767547607,
"logits/real": -2.0922763347625732,
"logps/generated": -361.0836486816406,
"logps/real": -165.01766967773438,
"loss": 0.0012,
"rewards/accuracies": 1.0,
"rewards/generated": -26.491872787475586,
"rewards/margins": 22.785490036010742,
"rewards/real": -3.7063846588134766,
"step": 1220
},
{
"epoch": 0.79,
"learning_rate": 1.1842105263157894e-07,
"logits/generated": -2.471233606338501,
"logits/real": -2.112055540084839,
"logps/generated": -336.9444274902344,
"logps/real": -156.4147491455078,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -24.630247116088867,
"rewards/margins": 20.876323699951172,
"rewards/real": -3.7539241313934326,
"step": 1230
},
{
"epoch": 0.79,
"learning_rate": 1.1486486486486487e-07,
"logits/generated": -2.475252389907837,
"logits/real": -2.1622281074523926,
"logps/generated": -350.2343444824219,
"logps/real": -170.01983642578125,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -25.50958824157715,
"rewards/margins": 22.2675724029541,
"rewards/real": -3.2420172691345215,
"step": 1240
},
{
"epoch": 0.8,
"learning_rate": 1.1130867709815078e-07,
"logits/generated": -2.4563283920288086,
"logits/real": -2.14430570602417,
"logps/generated": -346.8614196777344,
"logps/real": -169.02615356445312,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -25.24651527404785,
"rewards/margins": 21.750926971435547,
"rewards/real": -3.495588779449463,
"step": 1250
},
{
"epoch": 0.81,
"learning_rate": 1.077524893314367e-07,
"logits/generated": -2.45477032661438,
"logits/real": -2.0709099769592285,
"logps/generated": -356.8681640625,
"logps/real": -159.69961547851562,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -26.31940269470215,
"rewards/margins": 22.827180862426758,
"rewards/real": -3.492220401763916,
"step": 1260
},
{
"epoch": 0.81,
"learning_rate": 1.0419630156472262e-07,
"logits/generated": -2.453141450881958,
"logits/real": -2.2395853996276855,
"logps/generated": -378.34564208984375,
"logps/real": -186.41482543945312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/generated": -28.221569061279297,
"rewards/margins": 24.545499801635742,
"rewards/real": -3.676067352294922,
"step": 1270
},
{
"epoch": 0.82,
"learning_rate": 1.0064011379800854e-07,
"logits/generated": -2.4747064113616943,
"logits/real": -2.2565696239471436,
"logps/generated": -354.7027893066406,
"logps/real": -179.99632263183594,
"loss": 0.0024,
"rewards/accuracies": 1.0,
"rewards/generated": -25.973247528076172,
"rewards/margins": 22.519550323486328,
"rewards/real": -3.4536995887756348,
"step": 1280
},
{
"epoch": 0.83,
"learning_rate": 9.708392603129445e-08,
"logits/generated": -2.4690163135528564,
"logits/real": -2.232900857925415,
"logps/generated": -339.08905029296875,
"logps/real": -170.72555541992188,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -25.025901794433594,
"rewards/margins": 21.20990562438965,
"rewards/real": -3.8159968852996826,
"step": 1290
},
{
"epoch": 0.83,
"learning_rate": 9.352773826458037e-08,
"logits/generated": -2.4715685844421387,
"logits/real": -2.1666557788848877,
"logps/generated": -385.85552978515625,
"logps/real": -176.1797637939453,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -28.624618530273438,
"rewards/margins": 24.681453704833984,
"rewards/real": -3.9431674480438232,
"step": 1300
},
{
"epoch": 0.84,
"learning_rate": 8.997155049786629e-08,
"logits/generated": -2.485658884048462,
"logits/real": -2.087472438812256,
"logps/generated": -363.4739685058594,
"logps/real": -157.5010528564453,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -26.5460262298584,
"rewards/margins": 23.222301483154297,
"rewards/real": -3.3237223625183105,
"step": 1310
},
{
"epoch": 0.84,
"learning_rate": 8.64153627311522e-08,
"logits/generated": -2.4857845306396484,
"logits/real": -2.1609935760498047,
"logps/generated": -358.87042236328125,
"logps/real": -167.06588745117188,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -26.336450576782227,
"rewards/margins": 23.036605834960938,
"rewards/real": -3.2998440265655518,
"step": 1320
},
{
"epoch": 0.85,
"learning_rate": 8.285917496443812e-08,
"logits/generated": -2.488786458969116,
"logits/real": -2.1406562328338623,
"logps/generated": -359.51123046875,
"logps/real": -170.75405883789062,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -26.246429443359375,
"rewards/margins": 23.00771713256836,
"rewards/real": -3.2387115955352783,
"step": 1330
},
{
"epoch": 0.86,
"learning_rate": 7.930298719772404e-08,
"logits/generated": -2.4988155364990234,
"logits/real": -2.2278027534484863,
"logps/generated": -346.3113098144531,
"logps/real": -180.57955932617188,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -25.450998306274414,
"rewards/margins": 21.88384437561035,
"rewards/real": -3.567152738571167,
"step": 1340
},
{
"epoch": 0.86,
"learning_rate": 7.574679943100994e-08,
"logits/generated": -2.4711849689483643,
"logits/real": -2.1394145488739014,
"logps/generated": -363.7166442871094,
"logps/real": -153.56500244140625,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -27.254398345947266,
"rewards/margins": 23.747648239135742,
"rewards/real": -3.5067508220672607,
"step": 1350
},
{
"epoch": 0.87,
"learning_rate": 7.219061166429587e-08,
"logits/generated": -2.4750030040740967,
"logits/real": -2.165269136428833,
"logps/generated": -348.77850341796875,
"logps/real": -166.81552124023438,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -25.863576889038086,
"rewards/margins": 22.189855575561523,
"rewards/real": -3.673719882965088,
"step": 1360
},
{
"epoch": 0.88,
"learning_rate": 6.863442389758179e-08,
"logits/generated": -2.470283269882202,
"logits/real": -2.1896414756774902,
"logps/generated": -360.472412109375,
"logps/real": -183.18991088867188,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -26.284610748291016,
"rewards/margins": 22.66669464111328,
"rewards/real": -3.6179168224334717,
"step": 1370
},
{
"epoch": 0.88,
"learning_rate": 6.507823613086771e-08,
"logits/generated": -2.503307819366455,
"logits/real": -2.1919872760772705,
"logps/generated": -367.18853759765625,
"logps/real": -180.93328857421875,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -26.932886123657227,
"rewards/margins": 23.0779972076416,
"rewards/real": -3.854888916015625,
"step": 1380
},
{
"epoch": 0.89,
"learning_rate": 6.152204836415363e-08,
"logits/generated": -2.4691319465637207,
"logits/real": -2.1717336177825928,
"logps/generated": -356.29571533203125,
"logps/real": -177.71517944335938,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -26.687480926513672,
"rewards/margins": 22.633920669555664,
"rewards/real": -4.053561687469482,
"step": 1390
},
{
"epoch": 0.9,
"learning_rate": 5.796586059743954e-08,
"logits/generated": -2.466785430908203,
"logits/real": -2.1675827503204346,
"logps/generated": -370.415283203125,
"logps/real": -170.87490844726562,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -27.176166534423828,
"rewards/margins": 23.794544219970703,
"rewards/real": -3.381622314453125,
"step": 1400
},
{
"epoch": 0.9,
"learning_rate": 5.4409672830725456e-08,
"logits/generated": -2.4945216178894043,
"logits/real": -2.188453197479248,
"logps/generated": -364.7228088378906,
"logps/real": -170.24136352539062,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -26.309009552001953,
"rewards/margins": 22.98163604736328,
"rewards/real": -3.3273673057556152,
"step": 1410
},
{
"epoch": 0.91,
"learning_rate": 5.0853485064011376e-08,
"logits/generated": -2.460291624069214,
"logits/real": -2.0653367042541504,
"logps/generated": -367.35638427734375,
"logps/real": -158.03836059570312,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -27.220428466796875,
"rewards/margins": 23.743730545043945,
"rewards/real": -3.4767017364501953,
"step": 1420
},
{
"epoch": 0.91,
"learning_rate": 4.72972972972973e-08,
"logits/generated": -2.4655089378356934,
"logits/real": -2.1470799446105957,
"logps/generated": -363.5157165527344,
"logps/real": -169.77064514160156,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -27.16286849975586,
"rewards/margins": 23.716289520263672,
"rewards/real": -3.4465808868408203,
"step": 1430
},
{
"epoch": 0.92,
"learning_rate": 4.374110953058322e-08,
"logits/generated": -2.4361727237701416,
"logits/real": -2.1429202556610107,
"logps/generated": -346.8465270996094,
"logps/real": -169.4228515625,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -25.74833106994629,
"rewards/margins": 21.9796142578125,
"rewards/real": -3.7687153816223145,
"step": 1440
},
{
"epoch": 0.93,
"learning_rate": 4.018492176386913e-08,
"logits/generated": -2.479517936706543,
"logits/real": -2.1686959266662598,
"logps/generated": -345.124267578125,
"logps/real": -168.16627502441406,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -24.663585662841797,
"rewards/margins": 21.2713565826416,
"rewards/real": -3.3922317028045654,
"step": 1450
},
{
"epoch": 0.93,
"learning_rate": 3.6628733997155046e-08,
"logits/generated": -2.4482412338256836,
"logits/real": -2.036306381225586,
"logps/generated": -369.10015869140625,
"logps/real": -149.97622680664062,
"loss": 0.0008,
"rewards/accuracies": 1.0,
"rewards/generated": -27.136011123657227,
"rewards/margins": 23.369976043701172,
"rewards/real": -3.7660350799560547,
"step": 1460
},
{
"epoch": 0.94,
"learning_rate": 3.3072546230440967e-08,
"logits/generated": -2.4708914756774902,
"logits/real": -2.184417247772217,
"logps/generated": -365.8651428222656,
"logps/real": -165.40721130371094,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/generated": -26.8408203125,
"rewards/margins": 23.29212188720703,
"rewards/real": -3.5486953258514404,
"step": 1470
},
{
"epoch": 0.95,
"learning_rate": 2.9516358463726884e-08,
"logits/generated": -2.474561929702759,
"logits/real": -2.19511342048645,
"logps/generated": -355.9462890625,
"logps/real": -176.87612915039062,
"loss": 0.0023,
"rewards/accuracies": 1.0,
"rewards/generated": -25.89398765563965,
"rewards/margins": 22.387157440185547,
"rewards/real": -3.5068275928497314,
"step": 1480
},
{
"epoch": 0.95,
"learning_rate": 2.59601706970128e-08,
"logits/generated": -2.4852168560028076,
"logits/real": -2.187443256378174,
"logps/generated": -361.1342468261719,
"logps/real": -179.21498107910156,
"loss": 0.0047,
"rewards/accuracies": 1.0,
"rewards/generated": -26.83822250366211,
"rewards/margins": 23.508623123168945,
"rewards/real": -3.329601764678955,
"step": 1490
},
{
"epoch": 0.96,
"learning_rate": 2.240398293029872e-08,
"logits/generated": -2.467862606048584,
"logits/real": -2.135467767715454,
"logps/generated": -343.44512939453125,
"logps/real": -165.08482360839844,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -24.802982330322266,
"rewards/margins": 21.32632064819336,
"rewards/real": -3.4766650199890137,
"step": 1500
},
{
"epoch": 0.97,
"learning_rate": 1.8847795163584636e-08,
"logits/generated": -2.481208324432373,
"logits/real": -2.150805950164795,
"logps/generated": -353.4545593261719,
"logps/real": -169.54278564453125,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/generated": -25.823211669921875,
"rewards/margins": 22.245121002197266,
"rewards/real": -3.578090190887451,
"step": 1510
},
{
"epoch": 0.97,
"learning_rate": 1.5291607396870554e-08,
"logits/generated": -2.46956467628479,
"logits/real": -2.140104055404663,
"logps/generated": -342.57061767578125,
"logps/real": -167.4196014404297,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/generated": -25.0306339263916,
"rewards/margins": 21.307403564453125,
"rewards/real": -3.7232296466827393,
"step": 1520
},
{
"epoch": 0.98,
"learning_rate": 1.1735419630156473e-08,
"logits/generated": -2.48580002784729,
"logits/real": -2.194272518157959,
"logps/generated": -368.3807678222656,
"logps/real": -169.20266723632812,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -27.17935562133789,
"rewards/margins": 23.502368927001953,
"rewards/real": -3.6769843101501465,
"step": 1530
},
{
"epoch": 0.99,
"learning_rate": 8.179231863442388e-09,
"logits/generated": -2.4726576805114746,
"logits/real": -2.1791956424713135,
"logps/generated": -354.394775390625,
"logps/real": -170.46163940429688,
"loss": 0.0014,
"rewards/accuracies": 1.0,
"rewards/generated": -25.885757446289062,
"rewards/margins": 22.697250366210938,
"rewards/real": -3.188507080078125,
"step": 1540
},
{
"epoch": 0.99,
"learning_rate": 4.623044096728307e-09,
"logits/generated": -2.4750819206237793,
"logits/real": -2.1696460247039795,
"logps/generated": -358.7183532714844,
"logps/real": -176.12982177734375,
"loss": 0.0003,
"rewards/accuracies": 1.0,
"rewards/generated": -26.65958023071289,
"rewards/margins": 23.13229751586914,
"rewards/real": -3.52728271484375,
"step": 1550
},
{
"epoch": 1.0,
"learning_rate": 1.0668563300142248e-09,
"logits/generated": -2.493542194366455,
"logits/real": -2.1412835121154785,
"logps/generated": -353.84625244140625,
"logps/real": -169.55062866210938,
"loss": 0.0013,
"rewards/accuracies": 1.0,
"rewards/generated": -25.792984008789062,
"rewards/margins": 22.017263412475586,
"rewards/real": -3.7757201194763184,
"step": 1560
},
{
"epoch": 1.0,
"step": 1563,
"total_flos": 0.0,
"train_loss": 0.013782728538135369,
"train_runtime": 6445.5164,
"train_samples_per_second": 7.757,
"train_steps_per_second": 0.242
}
],
"logging_steps": 10,
"max_steps": 1563,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 0.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}