ziansu's picture
Training in progress, step 500, checkpoint
dcb3ce4 verified
raw
history blame
33.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3624173235480656,
"eval_steps": 50,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007248346470961312,
"grad_norm": 0.07201674580574036,
"learning_rate": 4.999451708687114e-06,
"logits/chosen": -1.9793262481689453,
"logits/rejected": -2.5381760597229004,
"logps/chosen": -0.28126341104507446,
"logps/rejected": -0.3779803514480591,
"loss": 7.3904,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -0.4218950867652893,
"rewards/margins": 0.14507544040679932,
"rewards/rejected": -0.5669704675674438,
"step": 10
},
{
"epoch": 0.014496692941922623,
"grad_norm": 0.07562297582626343,
"learning_rate": 4.997807075247147e-06,
"logits/chosen": -2.0567643642425537,
"logits/rejected": -2.4989147186279297,
"logps/chosen": -0.27690139412879944,
"logps/rejected": -0.33544114232063293,
"loss": 7.3756,
"rewards/accuracies": 0.574999988079071,
"rewards/chosen": -0.41535210609436035,
"rewards/margins": 0.08780960738658905,
"rewards/rejected": -0.5031617283821106,
"step": 20
},
{
"epoch": 0.021745039412883936,
"grad_norm": 0.09685570746660233,
"learning_rate": 4.9950668210706795e-06,
"logits/chosen": -2.10174298286438,
"logits/rejected": -2.378197431564331,
"logps/chosen": -0.26717427372932434,
"logps/rejected": -0.30565372109413147,
"loss": 7.451,
"rewards/accuracies": 0.4375,
"rewards/chosen": -0.4007614254951477,
"rewards/margins": 0.05771917849779129,
"rewards/rejected": -0.4584805369377136,
"step": 30
},
{
"epoch": 0.028993385883845247,
"grad_norm": 0.08213861286640167,
"learning_rate": 4.9912321481237616e-06,
"logits/chosen": -2.1633317470550537,
"logits/rejected": -2.387866497039795,
"logps/chosen": -0.27634260058403015,
"logps/rejected": -0.37035584449768066,
"loss": 7.3892,
"rewards/accuracies": 0.6499999761581421,
"rewards/chosen": -0.4145139157772064,
"rewards/margins": 0.14101983606815338,
"rewards/rejected": -0.555533766746521,
"step": 40
},
{
"epoch": 0.03624173235480656,
"grad_norm": 0.08846044540405273,
"learning_rate": 4.986304738420684e-06,
"logits/chosen": -2.1402599811553955,
"logits/rejected": -2.4459526538848877,
"logps/chosen": -0.2535383999347687,
"logps/rejected": -0.3090876042842865,
"loss": 7.5171,
"rewards/accuracies": 0.512499988079071,
"rewards/chosen": -0.3803076148033142,
"rewards/margins": 0.08332376182079315,
"rewards/rejected": -0.4636313319206238,
"step": 50
},
{
"epoch": 0.03624173235480656,
"eval_logits/chosen": -2.1165692806243896,
"eval_logits/rejected": -2.476428747177124,
"eval_logps/chosen": -0.2828062176704407,
"eval_logps/rejected": -0.3432886600494385,
"eval_loss": 0.9120001792907715,
"eval_rewards/accuracies": 0.5089285969734192,
"eval_rewards/chosen": -0.4242093861103058,
"eval_rewards/margins": 0.09072363376617432,
"eval_rewards/rejected": -0.5149329900741577,
"eval_runtime": 30.971,
"eval_samples_per_second": 28.801,
"eval_steps_per_second": 3.616,
"step": 50
},
{
"epoch": 0.04349007882576787,
"grad_norm": 0.11753705143928528,
"learning_rate": 4.980286753286196e-06,
"logits/chosen": -2.0575368404388428,
"logits/rejected": -2.5456700325012207,
"logps/chosen": -0.24622221291065216,
"logps/rejected": -0.32402220368385315,
"loss": 7.3926,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.36933332681655884,
"rewards/margins": 0.11669999361038208,
"rewards/rejected": -0.48603329062461853,
"step": 60
},
{
"epoch": 0.05073842529672919,
"grad_norm": 0.09996571391820908,
"learning_rate": 4.973180832407471e-06,
"logits/chosen": -1.9278606176376343,
"logits/rejected": -2.4620182514190674,
"logps/chosen": -0.2596542239189148,
"logps/rejected": -0.3665880560874939,
"loss": 7.185,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.3894812762737274,
"rewards/margins": 0.160400852560997,
"rewards/rejected": -0.5498821139335632,
"step": 70
},
{
"epoch": 0.057986771767690494,
"grad_norm": 0.07287321239709854,
"learning_rate": 4.964990092676263e-06,
"logits/chosen": -2.078031063079834,
"logits/rejected": -2.461479663848877,
"logps/chosen": -0.24513795971870422,
"logps/rejected": -0.3448730707168579,
"loss": 7.365,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.36770695447921753,
"rewards/margins": 0.14960262179374695,
"rewards/rejected": -0.5173095464706421,
"step": 80
},
{
"epoch": 0.0652351182386518,
"grad_norm": 0.09656044095754623,
"learning_rate": 4.9557181268217225e-06,
"logits/chosen": -1.9979238510131836,
"logits/rejected": -2.4381277561187744,
"logps/chosen": -0.24047240614891052,
"logps/rejected": -0.3277527987957001,
"loss": 7.2664,
"rewards/accuracies": 0.6000000238418579,
"rewards/chosen": -0.36070865392684937,
"rewards/margins": 0.13092057406902313,
"rewards/rejected": -0.4916292130947113,
"step": 90
},
{
"epoch": 0.07248346470961312,
"grad_norm": 0.08125138282775879,
"learning_rate": 4.9453690018345144e-06,
"logits/chosen": -1.8948112726211548,
"logits/rejected": -2.4755520820617676,
"logps/chosen": -0.20189261436462402,
"logps/rejected": -0.29732149839401245,
"loss": 7.2542,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.30283889174461365,
"rewards/margins": 0.14314329624176025,
"rewards/rejected": -0.44598227739334106,
"step": 100
},
{
"epoch": 0.07248346470961312,
"eval_logits/chosen": -2.12322735786438,
"eval_logits/rejected": -2.481174945831299,
"eval_logps/chosen": -0.2438412606716156,
"eval_logps/rejected": -0.3260033428668976,
"eval_loss": 0.891861081123352,
"eval_rewards/accuracies": 0.5625,
"eval_rewards/chosen": -0.3657619059085846,
"eval_rewards/margins": 0.12324309349060059,
"eval_rewards/rejected": -0.48900502920150757,
"eval_runtime": 30.3299,
"eval_samples_per_second": 29.41,
"eval_steps_per_second": 3.693,
"step": 100
},
{
"epoch": 0.07973181118057443,
"grad_norm": 0.05962231010198593,
"learning_rate": 4.933947257182901e-06,
"logits/chosen": -2.1134355068206787,
"logits/rejected": -2.516538381576538,
"logps/chosen": -0.237023264169693,
"logps/rejected": -0.31476154923439026,
"loss": 7.1749,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -0.3555349111557007,
"rewards/margins": 0.11660744249820709,
"rewards/rejected": -0.4721423089504242,
"step": 110
},
{
"epoch": 0.08698015765153574,
"grad_norm": 0.06015922501683235,
"learning_rate": 4.921457902821578e-06,
"logits/chosen": -2.0215041637420654,
"logits/rejected": -2.4902031421661377,
"logps/chosen": -0.1890055537223816,
"logps/rejected": -0.3192065358161926,
"loss": 7.142,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -0.2835083603858948,
"rewards/margins": 0.19530144333839417,
"rewards/rejected": -0.47880974411964417,
"step": 120
},
{
"epoch": 0.09422850412249706,
"grad_norm": 0.06430571526288986,
"learning_rate": 4.907906416994146e-06,
"logits/chosen": -2.0684752464294434,
"logits/rejected": -2.510018825531006,
"logps/chosen": -0.2073744535446167,
"logps/rejected": -0.3121300935745239,
"loss": 7.1438,
"rewards/accuracies": 0.612500011920929,
"rewards/chosen": -0.31106168031692505,
"rewards/margins": 0.15713343024253845,
"rewards/rejected": -0.4681951403617859,
"step": 130
},
{
"epoch": 0.10147685059345837,
"grad_norm": 0.08829955011606216,
"learning_rate": 4.893298743830168e-06,
"logits/chosen": -2.026458263397217,
"logits/rejected": -2.496157646179199,
"logps/chosen": -0.19946983456611633,
"logps/rejected": -0.32050156593322754,
"loss": 7.1196,
"rewards/accuracies": 0.625,
"rewards/chosen": -0.2992047667503357,
"rewards/margins": 0.18154758214950562,
"rewards/rejected": -0.4807523787021637,
"step": 140
},
{
"epoch": 0.10872519706441967,
"grad_norm": 0.09773921221494675,
"learning_rate": 4.8776412907378845e-06,
"logits/chosen": -2.101029872894287,
"logits/rejected": -2.5849032402038574,
"logps/chosen": -0.18889756500720978,
"logps/rejected": -0.36427801847457886,
"loss": 7.1227,
"rewards/accuracies": 0.6499999761581421,
"rewards/chosen": -0.28334635496139526,
"rewards/margins": 0.26307064294815063,
"rewards/rejected": -0.5464169979095459,
"step": 150
},
{
"epoch": 0.10872519706441967,
"eval_logits/chosen": -2.1945455074310303,
"eval_logits/rejected": -2.559415578842163,
"eval_logps/chosen": -0.22209034860134125,
"eval_logps/rejected": -0.32476040720939636,
"eval_loss": 0.8760393261909485,
"eval_rewards/accuracies": 0.5803571343421936,
"eval_rewards/chosen": -0.33313554525375366,
"eval_rewards/margins": 0.15400508046150208,
"eval_rewards/rejected": -0.48714062571525574,
"eval_runtime": 30.3484,
"eval_samples_per_second": 29.392,
"eval_steps_per_second": 3.69,
"step": 150
},
{
"epoch": 0.11597354353538099,
"grad_norm": 0.09142427891492844,
"learning_rate": 4.860940925593703e-06,
"logits/chosen": -2.235069751739502,
"logits/rejected": -2.5513346195220947,
"logps/chosen": -0.19598741829395294,
"logps/rejected": -0.2772120535373688,
"loss": 7.0272,
"rewards/accuracies": 0.5375000238418579,
"rewards/chosen": -0.2939811050891876,
"rewards/margins": 0.12183700501918793,
"rewards/rejected": -0.41581812500953674,
"step": 160
},
{
"epoch": 0.1232218900063423,
"grad_norm": 0.11735275387763977,
"learning_rate": 4.84320497372973e-06,
"logits/chosen": -2.154263496398926,
"logits/rejected": -2.512010335922241,
"logps/chosen": -0.1798369437456131,
"logps/rejected": -0.30910637974739075,
"loss": 7.1603,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -0.26975542306900024,
"rewards/margins": 0.19390416145324707,
"rewards/rejected": -0.4636595845222473,
"step": 170
},
{
"epoch": 0.1304702364773036,
"grad_norm": 0.09398588538169861,
"learning_rate": 4.824441214720629e-06,
"logits/chosen": -2.292147159576416,
"logits/rejected": -2.581425189971924,
"logps/chosen": -0.18498703837394714,
"logps/rejected": -0.31237050890922546,
"loss": 6.995,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -0.2774805426597595,
"rewards/margins": 0.19107523560523987,
"rewards/rejected": -0.4685557782649994,
"step": 180
},
{
"epoch": 0.13771858294826492,
"grad_norm": 0.13551996648311615,
"learning_rate": 4.804657878971252e-06,
"logits/chosen": -2.274120330810547,
"logits/rejected": -2.5797386169433594,
"logps/chosen": -0.21168990433216095,
"logps/rejected": -0.34927254915237427,
"loss": 6.9941,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.317534863948822,
"rewards/margins": 0.20637397468090057,
"rewards/rejected": -0.5239088535308838,
"step": 190
},
{
"epoch": 0.14496692941922623,
"grad_norm": 0.15515944361686707,
"learning_rate": 4.783863644106502e-06,
"logits/chosen": -2.2116379737854004,
"logits/rejected": -2.6693203449249268,
"logps/chosen": -0.1971816122531891,
"logps/rejected": -0.3498842120170593,
"loss": 7.0413,
"rewards/accuracies": 0.6499999761581421,
"rewards/chosen": -0.2957724332809448,
"rewards/margins": 0.22905388474464417,
"rewards/rejected": -0.5248263478279114,
"step": 200
},
{
"epoch": 0.14496692941922623,
"eval_logits/chosen": -2.3369696140289307,
"eval_logits/rejected": -2.7298672199249268,
"eval_logps/chosen": -0.22749511897563934,
"eval_logps/rejected": -0.3613782525062561,
"eval_loss": 0.8543878793716431,
"eval_rewards/accuracies": 0.5714285969734192,
"eval_rewards/chosen": -0.34124264121055603,
"eval_rewards/margins": 0.2008247673511505,
"eval_rewards/rejected": -0.5420674681663513,
"eval_runtime": 30.3397,
"eval_samples_per_second": 29.4,
"eval_steps_per_second": 3.692,
"step": 200
},
{
"epoch": 0.15221527589018755,
"grad_norm": 0.13039635121822357,
"learning_rate": 4.762067631165049e-06,
"logits/chosen": -2.2575619220733643,
"logits/rejected": -2.755174160003662,
"logps/chosen": -0.199218288064003,
"logps/rejected": -0.33260637521743774,
"loss": 6.882,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.2988274097442627,
"rewards/margins": 0.20008206367492676,
"rewards/rejected": -0.49890947341918945,
"step": 210
},
{
"epoch": 0.15946362236114886,
"grad_norm": 0.15020275115966797,
"learning_rate": 4.7392794005985324e-06,
"logits/chosen": -2.2949752807617188,
"logits/rejected": -2.7288482189178467,
"logps/chosen": -0.21987763047218323,
"logps/rejected": -0.385539174079895,
"loss": 6.9158,
"rewards/accuracies": 0.699999988079071,
"rewards/chosen": -0.3298164904117584,
"rewards/margins": 0.24849233031272888,
"rewards/rejected": -0.5783087611198425,
"step": 220
},
{
"epoch": 0.16671196883211017,
"grad_norm": 0.16104522347450256,
"learning_rate": 4.715508948078037e-06,
"logits/chosen": -2.1837964057922363,
"logits/rejected": -2.813563585281372,
"logps/chosen": -0.2069036215543747,
"logps/rejected": -0.3996518552303314,
"loss": 6.8503,
"rewards/accuracies": 0.699999988079071,
"rewards/chosen": -0.31035539507865906,
"rewards/margins": 0.28912240266799927,
"rewards/rejected": -0.5994777679443359,
"step": 230
},
{
"epoch": 0.1739603153030715,
"grad_norm": 0.16533692181110382,
"learning_rate": 4.690766700109659e-06,
"logits/chosen": -2.314570188522339,
"logits/rejected": -2.8867621421813965,
"logps/chosen": -0.18964803218841553,
"logps/rejected": -0.3997463583946228,
"loss": 6.667,
"rewards/accuracies": 0.6499999761581421,
"rewards/chosen": -0.2844720482826233,
"rewards/margins": 0.3151474893093109,
"rewards/rejected": -0.5996195077896118,
"step": 240
},
{
"epoch": 0.1812086617740328,
"grad_norm": 0.24991220235824585,
"learning_rate": 4.665063509461098e-06,
"logits/chosen": -2.46189546585083,
"logits/rejected": -2.847446918487549,
"logps/chosen": -0.24189543724060059,
"logps/rejected": -0.4183991551399231,
"loss": 6.7146,
"rewards/accuracies": 0.5625,
"rewards/chosen": -0.3628431558609009,
"rewards/margins": 0.26475557684898376,
"rewards/rejected": -0.6275987029075623,
"step": 250
},
{
"epoch": 0.1812086617740328,
"eval_logits/chosen": -2.5230772495269775,
"eval_logits/rejected": -2.9182300567626953,
"eval_logps/chosen": -0.2819940149784088,
"eval_logps/rejected": -0.48641347885131836,
"eval_loss": 0.8070082664489746,
"eval_rewards/accuracies": 0.5803571343421936,
"eval_rewards/chosen": -0.4229910671710968,
"eval_rewards/margins": 0.3066291809082031,
"eval_rewards/rejected": -0.7296201586723328,
"eval_runtime": 30.3523,
"eval_samples_per_second": 29.388,
"eval_steps_per_second": 3.69,
"step": 250
},
{
"epoch": 0.18845700824499412,
"grad_norm": 0.3010155260562897,
"learning_rate": 4.638410650401267e-06,
"logits/chosen": -2.4178171157836914,
"logits/rejected": -2.914424419403076,
"logps/chosen": -0.24933743476867676,
"logps/rejected": -0.4757954478263855,
"loss": 6.5743,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -0.3740061819553375,
"rewards/margins": 0.33968693017959595,
"rewards/rejected": -0.7136931419372559,
"step": 260
},
{
"epoch": 0.19570535471595543,
"grad_norm": 0.3765665888786316,
"learning_rate": 4.610819813755038e-06,
"logits/chosen": -2.407275676727295,
"logits/rejected": -2.886014938354492,
"logps/chosen": -0.27837619185447693,
"logps/rejected": -0.6118712425231934,
"loss": 6.4931,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.417564332485199,
"rewards/margins": 0.5002425909042358,
"rewards/rejected": -0.9178068041801453,
"step": 270
},
{
"epoch": 0.20295370118691675,
"grad_norm": 0.29865291714668274,
"learning_rate": 4.582303101775249e-06,
"logits/chosen": -2.5404791831970215,
"logits/rejected": -2.861341953277588,
"logps/chosen": -0.3124132752418518,
"logps/rejected": -0.558597207069397,
"loss": 6.2272,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -0.4686199128627777,
"rewards/margins": 0.3692759573459625,
"rewards/rejected": -0.8378958702087402,
"step": 280
},
{
"epoch": 0.21020204765787803,
"grad_norm": 0.4311545789241791,
"learning_rate": 4.55287302283426e-06,
"logits/chosen": -2.393683910369873,
"logits/rejected": -2.833466053009033,
"logps/chosen": -0.3574284017086029,
"logps/rejected": -0.8571383357048035,
"loss": 5.7937,
"rewards/accuracies": 0.7124999761581421,
"rewards/chosen": -0.5361425876617432,
"rewards/margins": 0.7495648264884949,
"rewards/rejected": -1.2857074737548828,
"step": 290
},
{
"epoch": 0.21745039412883935,
"grad_norm": 0.7148597836494446,
"learning_rate": 4.522542485937369e-06,
"logits/chosen": -2.369452476501465,
"logits/rejected": -2.7431299686431885,
"logps/chosen": -0.46852874755859375,
"logps/rejected": -0.9673423767089844,
"loss": 5.741,
"rewards/accuracies": 0.6875,
"rewards/chosen": -0.7027931213378906,
"rewards/margins": 0.7482204437255859,
"rewards/rejected": -1.4510136842727661,
"step": 300
},
{
"epoch": 0.21745039412883935,
"eval_logits/chosen": -2.5259616374969482,
"eval_logits/rejected": -2.8154189586639404,
"eval_logps/chosen": -0.5109023451805115,
"eval_logps/rejected": -0.9421015381813049,
"eval_loss": 0.6990054845809937,
"eval_rewards/accuracies": 0.5714285969734192,
"eval_rewards/chosen": -0.7663536071777344,
"eval_rewards/margins": 0.6467987895011902,
"eval_rewards/rejected": -1.4131524562835693,
"eval_runtime": 30.3501,
"eval_samples_per_second": 29.39,
"eval_steps_per_second": 3.69,
"step": 300
},
{
"epoch": 0.22469874059980066,
"grad_norm": 0.37795087695121765,
"learning_rate": 4.491324795060491e-06,
"logits/chosen": -2.5089354515075684,
"logits/rejected": -2.827730894088745,
"logps/chosen": -0.4125432074069977,
"logps/rejected": -1.0391974449157715,
"loss": 5.3005,
"rewards/accuracies": 0.625,
"rewards/chosen": -0.6188148260116577,
"rewards/margins": 0.9399812817573547,
"rewards/rejected": -1.5587961673736572,
"step": 310
},
{
"epoch": 0.23194708707076198,
"grad_norm": 0.38493892550468445,
"learning_rate": 4.4592336433146e-06,
"logits/chosen": -2.3596529960632324,
"logits/rejected": -2.8088250160217285,
"logps/chosen": -0.5338706970214844,
"logps/rejected": -1.2868502140045166,
"loss": 5.2832,
"rewards/accuracies": 0.6625000238418579,
"rewards/chosen": -0.8008060455322266,
"rewards/margins": 1.1294692754745483,
"rewards/rejected": -1.930275321006775,
"step": 320
},
{
"epoch": 0.2391954335417233,
"grad_norm": 0.6237270832061768,
"learning_rate": 4.426283106939474e-06,
"logits/chosen": -2.5265612602233887,
"logits/rejected": -2.7830424308776855,
"logps/chosen": -0.6278705596923828,
"logps/rejected": -1.4297993183135986,
"loss": 5.1977,
"rewards/accuracies": 0.6875,
"rewards/chosen": -0.9418058395385742,
"rewards/margins": 1.2028930187225342,
"rewards/rejected": -2.1446988582611084,
"step": 330
},
{
"epoch": 0.2464437800126846,
"grad_norm": 0.9095363020896912,
"learning_rate": 4.3924876391293915e-06,
"logits/chosen": -2.5918514728546143,
"logits/rejected": -2.8718667030334473,
"logps/chosen": -0.6412171125411987,
"logps/rejected": -1.508195161819458,
"loss": 4.7181,
"rewards/accuracies": 0.625,
"rewards/chosen": -0.9618256688117981,
"rewards/margins": 1.3004668951034546,
"rewards/rejected": -2.2622926235198975,
"step": 340
},
{
"epoch": 0.2536921264836459,
"grad_norm": 0.6144569516181946,
"learning_rate": 4.357862063693486e-06,
"logits/chosen": -2.492586612701416,
"logits/rejected": -2.9216372966766357,
"logps/chosen": -0.7246330976486206,
"logps/rejected": -2.0466060638427734,
"loss": 4.6111,
"rewards/accuracies": 0.675000011920929,
"rewards/chosen": -1.0869497060775757,
"rewards/margins": 1.9829593896865845,
"rewards/rejected": -3.06990909576416,
"step": 350
},
{
"epoch": 0.2536921264836459,
"eval_logits/chosen": -2.7258641719818115,
"eval_logits/rejected": -2.9883599281311035,
"eval_logps/chosen": -0.7502545118331909,
"eval_logps/rejected": -1.7796010971069336,
"eval_loss": 0.571855366230011,
"eval_rewards/accuracies": 0.5892857313156128,
"eval_rewards/chosen": -1.1253817081451416,
"eval_rewards/margins": 1.5440199375152588,
"eval_rewards/rejected": -2.6694016456604004,
"eval_runtime": 30.3197,
"eval_samples_per_second": 29.42,
"eval_steps_per_second": 3.694,
"step": 350
},
{
"epoch": 0.2609404729546072,
"grad_norm": 0.6816007494926453,
"learning_rate": 4.322421568553529e-06,
"logits/chosen": -2.6618990898132324,
"logits/rejected": -2.9197638034820557,
"logps/chosen": -0.7783921360969543,
"logps/rejected": -1.9845831394195557,
"loss": 4.8991,
"rewards/accuracies": 0.6625000238418579,
"rewards/chosen": -1.1675881147384644,
"rewards/margins": 1.8092864751815796,
"rewards/rejected": -2.976874589920044,
"step": 360
},
{
"epoch": 0.26818881942556855,
"grad_norm": 0.5186926126480103,
"learning_rate": 4.286181699082008e-06,
"logits/chosen": -2.690049171447754,
"logits/rejected": -2.9129927158355713,
"logps/chosen": -0.7160422205924988,
"logps/rejected": -2.097799777984619,
"loss": 4.6471,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -1.0740633010864258,
"rewards/margins": 2.0726354122161865,
"rewards/rejected": -3.1466989517211914,
"step": 370
},
{
"epoch": 0.27543716589652983,
"grad_norm": 0.7122822403907776,
"learning_rate": 4.249158351283414e-06,
"logits/chosen": -2.6984095573425293,
"logits/rejected": -2.8411834239959717,
"logps/chosen": -0.724581778049469,
"logps/rejected": -2.1322455406188965,
"loss": 4.4326,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -1.0868725776672363,
"rewards/margins": 2.1114957332611084,
"rewards/rejected": -3.198368549346924,
"step": 380
},
{
"epoch": 0.2826855123674912,
"grad_norm": 0.610661506652832,
"learning_rate": 4.211367764821722e-06,
"logits/chosen": -2.5932717323303223,
"logits/rejected": -2.855365514755249,
"logps/chosen": -0.6430361866950989,
"logps/rejected": -2.8457767963409424,
"loss": 4.3874,
"rewards/accuracies": 0.824999988079071,
"rewards/chosen": -0.9645543098449707,
"rewards/margins": 3.3041110038757324,
"rewards/rejected": -4.268665313720703,
"step": 390
},
{
"epoch": 0.28993385883845246,
"grad_norm": 0.627453088760376,
"learning_rate": 4.172826515897146e-06,
"logits/chosen": -2.46079683303833,
"logits/rejected": -2.839109182357788,
"logps/chosen": -0.8076715469360352,
"logps/rejected": -2.6943671703338623,
"loss": 4.2388,
"rewards/accuracies": 0.6875,
"rewards/chosen": -1.2115072011947632,
"rewards/margins": 2.8300435543060303,
"rewards/rejected": -4.041550636291504,
"step": 400
},
{
"epoch": 0.28993385883845246,
"eval_logits/chosen": -2.5736935138702393,
"eval_logits/rejected": -2.8549301624298096,
"eval_logps/chosen": -0.8027606010437012,
"eval_logps/rejected": -2.407195568084717,
"eval_loss": 0.49557629227638245,
"eval_rewards/accuracies": 0.6071428656578064,
"eval_rewards/chosen": -1.2041409015655518,
"eval_rewards/margins": 2.4066522121429443,
"eval_rewards/rejected": -3.6107935905456543,
"eval_runtime": 30.3144,
"eval_samples_per_second": 29.425,
"eval_steps_per_second": 3.695,
"step": 400
},
{
"epoch": 0.2971822053094138,
"grad_norm": 0.582290768623352,
"learning_rate": 4.133551509975264e-06,
"logits/chosen": -2.5232419967651367,
"logits/rejected": -2.8139169216156006,
"logps/chosen": -0.7921724319458008,
"logps/rejected": -2.5887393951416016,
"loss": 3.9161,
"rewards/accuracies": 0.7124999761581421,
"rewards/chosen": -1.1882586479187012,
"rewards/margins": 2.694850206375122,
"rewards/rejected": -3.883108615875244,
"step": 410
},
{
"epoch": 0.3044305517803751,
"grad_norm": 1.0708731412887573,
"learning_rate": 4.093559974371725e-06,
"logits/chosen": -2.402315616607666,
"logits/rejected": -2.6774837970733643,
"logps/chosen": -0.9347984194755554,
"logps/rejected": -3.4818978309631348,
"loss": 3.8304,
"rewards/accuracies": 0.762499988079071,
"rewards/chosen": -1.4021978378295898,
"rewards/margins": 3.8206489086151123,
"rewards/rejected": -5.222846508026123,
"step": 420
},
{
"epoch": 0.31167889825133643,
"grad_norm": 0.6126013398170471,
"learning_rate": 4.052869450695776e-06,
"logits/chosen": -2.4616169929504395,
"logits/rejected": -2.791163921356201,
"logps/chosen": -1.073099970817566,
"logps/rejected": -3.7586822509765625,
"loss": 3.7662,
"rewards/accuracies": 0.7250000238418579,
"rewards/chosen": -1.609649896621704,
"rewards/margins": 4.028374671936035,
"rewards/rejected": -5.63802433013916,
"step": 430
},
{
"epoch": 0.3189272447222977,
"grad_norm": 0.6995553374290466,
"learning_rate": 4.011497787155938e-06,
"logits/chosen": -2.350310802459717,
"logits/rejected": -2.750123977661133,
"logps/chosen": -1.2352540493011475,
"logps/rejected": -4.180838584899902,
"loss": 3.4493,
"rewards/accuracies": 0.7749999761581421,
"rewards/chosen": -1.852880835533142,
"rewards/margins": 4.418376922607422,
"rewards/rejected": -6.271258354187012,
"step": 440
},
{
"epoch": 0.32617559119325906,
"grad_norm": 0.7922266721725464,
"learning_rate": 3.969463130731183e-06,
"logits/chosen": -2.368863344192505,
"logits/rejected": -2.7451913356781006,
"logps/chosen": -1.0907175540924072,
"logps/rejected": -4.085494041442871,
"loss": 4.0187,
"rewards/accuracies": 0.8125,
"rewards/chosen": -1.6360763311386108,
"rewards/margins": 4.4921650886535645,
"rewards/rejected": -6.128241062164307,
"step": 450
},
{
"epoch": 0.32617559119325906,
"eval_logits/chosen": -2.44749116897583,
"eval_logits/rejected": -2.7382781505584717,
"eval_logps/chosen": -1.3378121852874756,
"eval_logps/rejected": -3.6518471240997314,
"eval_loss": 0.45260879397392273,
"eval_rewards/accuracies": 0.6428571343421936,
"eval_rewards/chosen": -2.006718158721924,
"eval_rewards/margins": 3.4710519313812256,
"eval_rewards/rejected": -5.4777703285217285,
"eval_runtime": 30.3269,
"eval_samples_per_second": 29.413,
"eval_steps_per_second": 3.693,
"step": 450
},
{
"epoch": 0.33342393766422035,
"grad_norm": 0.7150818109512329,
"learning_rate": 3.92678391921108e-06,
"logits/chosen": -2.4681639671325684,
"logits/rejected": -2.797795057296753,
"logps/chosen": -1.4199602603912354,
"logps/rejected": -4.342296600341797,
"loss": 3.5788,
"rewards/accuracies": 0.7124999761581421,
"rewards/chosen": -2.1299405097961426,
"rewards/margins": 4.3835039138793945,
"rewards/rejected": -6.513444423675537,
"step": 460
},
{
"epoch": 0.34067228413518164,
"grad_norm": 1.260711431503296,
"learning_rate": 3.88347887310836e-06,
"logits/chosen": -2.4320380687713623,
"logits/rejected": -2.749352216720581,
"logps/chosen": -1.318566918373108,
"logps/rejected": -3.7736339569091797,
"loss": 3.5681,
"rewards/accuracies": 0.75,
"rewards/chosen": -1.977850317955017,
"rewards/margins": 3.682600498199463,
"rewards/rejected": -5.6604509353637695,
"step": 470
},
{
"epoch": 0.347920630606143,
"grad_norm": 0.9010512828826904,
"learning_rate": 3.839566987447492e-06,
"logits/chosen": -2.3840298652648926,
"logits/rejected": -2.7868971824645996,
"logps/chosen": -1.6358540058135986,
"logps/rejected": -5.068122386932373,
"loss": 3.2884,
"rewards/accuracies": 0.862500011920929,
"rewards/chosen": -2.4537811279296875,
"rewards/margins": 5.148402690887451,
"rewards/rejected": -7.602184295654297,
"step": 480
},
{
"epoch": 0.35516897707710426,
"grad_norm": 0.4977961778640747,
"learning_rate": 3.795067523432826e-06,
"logits/chosen": -2.4045886993408203,
"logits/rejected": -2.813812494277954,
"logps/chosen": -1.5761570930480957,
"logps/rejected": -5.026966094970703,
"loss": 3.5505,
"rewards/accuracies": 0.7749999761581421,
"rewards/chosen": -2.3642354011535645,
"rewards/margins": 5.176213264465332,
"rewards/rejected": -7.5404486656188965,
"step": 490
},
{
"epoch": 0.3624173235480656,
"grad_norm": 0.9888324737548828,
"learning_rate": 3.7500000000000005e-06,
"logits/chosen": -2.4877827167510986,
"logits/rejected": -2.7923107147216797,
"logps/chosen": -2.0706987380981445,
"logps/rejected": -5.011548042297363,
"loss": 3.3992,
"rewards/accuracies": 0.800000011920929,
"rewards/chosen": -3.106048107147217,
"rewards/margins": 4.411273002624512,
"rewards/rejected": -7.517321586608887,
"step": 500
},
{
"epoch": 0.3624173235480656,
"eval_logits/chosen": -2.5850253105163574,
"eval_logits/rejected": -2.898167133331299,
"eval_logps/chosen": -2.3814480304718018,
"eval_logps/rejected": -5.132807731628418,
"eval_loss": 0.40332508087158203,
"eval_rewards/accuracies": 0.7142857313156128,
"eval_rewards/chosen": -3.572171926498413,
"eval_rewards/margins": 4.127039432525635,
"eval_rewards/rejected": -7.699211597442627,
"eval_runtime": 30.324,
"eval_samples_per_second": 29.416,
"eval_steps_per_second": 3.693,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 1500,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.8549061636493148e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}